| 3 3 3 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 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * Cryptographic API. * * ARIA Cipher Algorithm. * * Documentation of ARIA can be found in RFC 5794. * Copyright (c) 2022 Taehee Yoo <ap420073@gmail.com> * Copyright (c) 2022 Taehee Yoo <ap420073@gmail.com> * * Information for ARIA * http://210.104.33.10/ARIA/index-e.html (English) * http://seed.kisa.or.kr/ (Korean) * * Public domain version is distributed above. */ #ifndef _CRYPTO_ARIA_H #define _CRYPTO_ARIA_H #include <crypto/algapi.h> #include <linux/module.h> #include <linux/init.h> #include <linux/types.h> #include <linux/errno.h> #include <asm/byteorder.h> #define ARIA_MIN_KEY_SIZE 16 #define ARIA_MAX_KEY_SIZE 32 #define ARIA_BLOCK_SIZE 16 #define ARIA_MAX_RD_KEYS 17 #define ARIA_RD_KEY_WORDS (ARIA_BLOCK_SIZE / sizeof(u32)) struct aria_ctx { u32 enc_key[ARIA_MAX_RD_KEYS][ARIA_RD_KEY_WORDS]; u32 dec_key[ARIA_MAX_RD_KEYS][ARIA_RD_KEY_WORDS]; int rounds; int key_length; }; static const u32 s1[256] = { 0x00636363, 0x007c7c7c, 0x00777777, 0x007b7b7b, 0x00f2f2f2, 0x006b6b6b, 0x006f6f6f, 0x00c5c5c5, 0x00303030, 0x00010101, 0x00676767, 0x002b2b2b, 0x00fefefe, 0x00d7d7d7, 0x00ababab, 0x00767676, 0x00cacaca, 0x00828282, 0x00c9c9c9, 0x007d7d7d, 0x00fafafa, 0x00595959, 0x00474747, 0x00f0f0f0, 0x00adadad, 0x00d4d4d4, 0x00a2a2a2, 0x00afafaf, 0x009c9c9c, 0x00a4a4a4, 0x00727272, 0x00c0c0c0, 0x00b7b7b7, 0x00fdfdfd, 0x00939393, 0x00262626, 0x00363636, 0x003f3f3f, 0x00f7f7f7, 0x00cccccc, 0x00343434, 0x00a5a5a5, 0x00e5e5e5, 0x00f1f1f1, 0x00717171, 0x00d8d8d8, 0x00313131, 0x00151515, 0x00040404, 0x00c7c7c7, 0x00232323, 0x00c3c3c3, 0x00181818, 0x00969696, 0x00050505, 0x009a9a9a, 0x00070707, 0x00121212, 0x00808080, 0x00e2e2e2, 0x00ebebeb, 0x00272727, 0x00b2b2b2, 0x00757575, 0x00090909, 0x00838383, 0x002c2c2c, 0x001a1a1a, 0x001b1b1b, 0x006e6e6e, 0x005a5a5a, 0x00a0a0a0, 0x00525252, 0x003b3b3b, 0x00d6d6d6, 0x00b3b3b3, 0x00292929, 0x00e3e3e3, 0x002f2f2f, 0x00848484, 0x00535353, 0x00d1d1d1, 0x00000000, 0x00ededed, 0x00202020, 0x00fcfcfc, 0x00b1b1b1, 0x005b5b5b, 0x006a6a6a, 0x00cbcbcb, 0x00bebebe, 0x00393939, 0x004a4a4a, 0x004c4c4c, 0x00585858, 0x00cfcfcf, 0x00d0d0d0, 0x00efefef, 0x00aaaaaa, 0x00fbfbfb, 0x00434343, 0x004d4d4d, 0x00333333, 0x00858585, 0x00454545, 0x00f9f9f9, 0x00020202, 0x007f7f7f, 0x00505050, 0x003c3c3c, 0x009f9f9f, 0x00a8a8a8, 0x00515151, 0x00a3a3a3, 0x00404040, 0x008f8f8f, 0x00929292, 0x009d9d9d, 0x00383838, 0x00f5f5f5, 0x00bcbcbc, 0x00b6b6b6, 0x00dadada, 0x00212121, 0x00101010, 0x00ffffff, 0x00f3f3f3, 0x00d2d2d2, 0x00cdcdcd, 0x000c0c0c, 0x00131313, 0x00ececec, 0x005f5f5f, 0x00979797, 0x00444444, 0x00171717, 0x00c4c4c4, 0x00a7a7a7, 0x007e7e7e, 0x003d3d3d, 0x00646464, 0x005d5d5d, 0x00191919, 0x00737373, 0x00606060, 0x00818181, 0x004f4f4f, 0x00dcdcdc, 0x00222222, 0x002a2a2a, 0x00909090, 0x00888888, 0x00464646, 0x00eeeeee, 0x00b8b8b8, 0x00141414, 0x00dedede, 0x005e5e5e, 0x000b0b0b, 0x00dbdbdb, 0x00e0e0e0, 0x00323232, 0x003a3a3a, 0x000a0a0a, 0x00494949, 0x00060606, 0x00242424, 0x005c5c5c, 0x00c2c2c2, 0x00d3d3d3, 0x00acacac, 0x00626262, 0x00919191, 0x00959595, 0x00e4e4e4, 0x00797979, 0x00e7e7e7, 0x00c8c8c8, 0x00373737, 0x006d6d6d, 0x008d8d8d, 0x00d5d5d5, 0x004e4e4e, 0x00a9a9a9, 0x006c6c6c, 0x00565656, 0x00f4f4f4, 0x00eaeaea, 0x00656565, 0x007a7a7a, 0x00aeaeae, 0x00080808, 0x00bababa, 0x00787878, 0x00252525, 0x002e2e2e, 0x001c1c1c, 0x00a6a6a6, 0x00b4b4b4, 0x00c6c6c6, 0x00e8e8e8, 0x00dddddd, 0x00747474, 0x001f1f1f, 0x004b4b4b, 0x00bdbdbd, 0x008b8b8b, 0x008a8a8a, 0x00707070, 0x003e3e3e, 0x00b5b5b5, 0x00666666, 0x00484848, 0x00030303, 0x00f6f6f6, 0x000e0e0e, 0x00616161, 0x00353535, 0x00575757, 0x00b9b9b9, 0x00868686, 0x00c1c1c1, 0x001d1d1d, 0x009e9e9e, 0x00e1e1e1, 0x00f8f8f8, 0x00989898, 0x00111111, 0x00696969, 0x00d9d9d9, 0x008e8e8e, 0x00949494, 0x009b9b9b, 0x001e1e1e, 0x00878787, 0x00e9e9e9, 0x00cecece, 0x00555555, 0x00282828, 0x00dfdfdf, 0x008c8c8c, 0x00a1a1a1, 0x00898989, 0x000d0d0d, 0x00bfbfbf, 0x00e6e6e6, 0x00424242, 0x00686868, 0x00414141, 0x00999999, 0x002d2d2d, 0x000f0f0f, 0x00b0b0b0, 0x00545454, 0x00bbbbbb, 0x00161616 }; static const u32 s2[256] = { 0xe200e2e2, 0x4e004e4e, 0x54005454, 0xfc00fcfc, 0x94009494, 0xc200c2c2, 0x4a004a4a, 0xcc00cccc, 0x62006262, 0x0d000d0d, 0x6a006a6a, 0x46004646, 0x3c003c3c, 0x4d004d4d, 0x8b008b8b, 0xd100d1d1, 0x5e005e5e, 0xfa00fafa, 0x64006464, 0xcb00cbcb, 0xb400b4b4, 0x97009797, 0xbe00bebe, 0x2b002b2b, 0xbc00bcbc, 0x77007777, 0x2e002e2e, 0x03000303, 0xd300d3d3, 0x19001919, 0x59005959, 0xc100c1c1, 0x1d001d1d, 0x06000606, 0x41004141, 0x6b006b6b, 0x55005555, 0xf000f0f0, 0x99009999, 0x69006969, 0xea00eaea, 0x9c009c9c, 0x18001818, 0xae00aeae, 0x63006363, 0xdf00dfdf, 0xe700e7e7, 0xbb00bbbb, 0x00000000, 0x73007373, 0x66006666, 0xfb00fbfb, 0x96009696, 0x4c004c4c, 0x85008585, 0xe400e4e4, 0x3a003a3a, 0x09000909, 0x45004545, 0xaa00aaaa, 0x0f000f0f, 0xee00eeee, 0x10001010, 0xeb00ebeb, 0x2d002d2d, 0x7f007f7f, 0xf400f4f4, 0x29002929, 0xac00acac, 0xcf00cfcf, 0xad00adad, 0x91009191, 0x8d008d8d, 0x78007878, 0xc800c8c8, 0x95009595, 0xf900f9f9, 0x2f002f2f, 0xce00cece, 0xcd00cdcd, 0x08000808, 0x7a007a7a, 0x88008888, 0x38003838, 0x5c005c5c, 0x83008383, 0x2a002a2a, 0x28002828, 0x47004747, 0xdb00dbdb, 0xb800b8b8, 0xc700c7c7, 0x93009393, 0xa400a4a4, 0x12001212, 0x53005353, 0xff00ffff, 0x87008787, 0x0e000e0e, 0x31003131, 0x36003636, 0x21002121, 0x58005858, 0x48004848, 0x01000101, 0x8e008e8e, 0x37003737, 0x74007474, 0x32003232, 0xca00caca, 0xe900e9e9, 0xb100b1b1, 0xb700b7b7, 0xab00abab, 0x0c000c0c, 0xd700d7d7, 0xc400c4c4, 0x56005656, 0x42004242, 0x26002626, 0x07000707, 0x98009898, 0x60006060, 0xd900d9d9, 0xb600b6b6, 0xb900b9b9, 0x11001111, 0x40004040, 0xec00ecec, 0x20002020, 0x8c008c8c, 0xbd00bdbd, 0xa000a0a0, 0xc900c9c9, 0x84008484, 0x04000404, 0x49004949, 0x23002323, 0xf100f1f1, 0x4f004f4f, 0x50005050, 0x1f001f1f, 0x13001313, 0xdc00dcdc, 0xd800d8d8, 0xc000c0c0, 0x9e009e9e, 0x57005757, 0xe300e3e3, 0xc300c3c3, 0x7b007b7b, 0x65006565, 0x3b003b3b, 0x02000202, 0x8f008f8f, 0x3e003e3e, 0xe800e8e8, 0x25002525, 0x92009292, 0xe500e5e5, 0x15001515, 0xdd00dddd, 0xfd00fdfd, 0x17001717, 0xa900a9a9, 0xbf00bfbf, 0xd400d4d4, 0x9a009a9a, 0x7e007e7e, 0xc500c5c5, 0x39003939, 0x67006767, 0xfe00fefe, 0x76007676, 0x9d009d9d, 0x43004343, 0xa700a7a7, 0xe100e1e1, 0xd000d0d0, 0xf500f5f5, 0x68006868, 0xf200f2f2, 0x1b001b1b, 0x34003434, 0x70007070, 0x05000505, 0xa300a3a3, 0x8a008a8a, 0xd500d5d5, 0x79007979, 0x86008686, 0xa800a8a8, 0x30003030, 0xc600c6c6, 0x51005151, 0x4b004b4b, 0x1e001e1e, 0xa600a6a6, 0x27002727, 0xf600f6f6, 0x35003535, 0xd200d2d2, 0x6e006e6e, 0x24002424, 0x16001616, 0x82008282, 0x5f005f5f, 0xda00dada, 0xe600e6e6, 0x75007575, 0xa200a2a2, 0xef00efef, 0x2c002c2c, 0xb200b2b2, 0x1c001c1c, 0x9f009f9f, 0x5d005d5d, 0x6f006f6f, 0x80008080, 0x0a000a0a, 0x72007272, 0x44004444, 0x9b009b9b, 0x6c006c6c, 0x90009090, 0x0b000b0b, 0x5b005b5b, 0x33003333, 0x7d007d7d, 0x5a005a5a, 0x52005252, 0xf300f3f3, 0x61006161, 0xa100a1a1, 0xf700f7f7, 0xb000b0b0, 0xd600d6d6, 0x3f003f3f, 0x7c007c7c, 0x6d006d6d, 0xed00eded, 0x14001414, 0xe000e0e0, 0xa500a5a5, 0x3d003d3d, 0x22002222, 0xb300b3b3, 0xf800f8f8, 0x89008989, 0xde00dede, 0x71007171, 0x1a001a1a, 0xaf00afaf, 0xba00baba, 0xb500b5b5, 0x81008181 }; static const u32 x1[256] = { 0x52520052, 0x09090009, 0x6a6a006a, 0xd5d500d5, 0x30300030, 0x36360036, 0xa5a500a5, 0x38380038, 0xbfbf00bf, 0x40400040, 0xa3a300a3, 0x9e9e009e, 0x81810081, 0xf3f300f3, 0xd7d700d7, 0xfbfb00fb, 0x7c7c007c, 0xe3e300e3, 0x39390039, 0x82820082, 0x9b9b009b, 0x2f2f002f, 0xffff00ff, 0x87870087, 0x34340034, 0x8e8e008e, 0x43430043, 0x44440044, 0xc4c400c4, 0xdede00de, 0xe9e900e9, 0xcbcb00cb, 0x54540054, 0x7b7b007b, 0x94940094, 0x32320032, 0xa6a600a6, 0xc2c200c2, 0x23230023, 0x3d3d003d, 0xeeee00ee, 0x4c4c004c, 0x95950095, 0x0b0b000b, 0x42420042, 0xfafa00fa, 0xc3c300c3, 0x4e4e004e, 0x08080008, 0x2e2e002e, 0xa1a100a1, 0x66660066, 0x28280028, 0xd9d900d9, 0x24240024, 0xb2b200b2, 0x76760076, 0x5b5b005b, 0xa2a200a2, 0x49490049, 0x6d6d006d, 0x8b8b008b, 0xd1d100d1, 0x25250025, 0x72720072, 0xf8f800f8, 0xf6f600f6, 0x64640064, 0x86860086, 0x68680068, 0x98980098, 0x16160016, 0xd4d400d4, 0xa4a400a4, 0x5c5c005c, 0xcccc00cc, 0x5d5d005d, 0x65650065, 0xb6b600b6, 0x92920092, 0x6c6c006c, 0x70700070, 0x48480048, 0x50500050, 0xfdfd00fd, 0xeded00ed, 0xb9b900b9, 0xdada00da, 0x5e5e005e, 0x15150015, 0x46460046, 0x57570057, 0xa7a700a7, 0x8d8d008d, 0x9d9d009d, 0x84840084, 0x90900090, 0xd8d800d8, 0xabab00ab, 0x00000000, 0x8c8c008c, 0xbcbc00bc, 0xd3d300d3, 0x0a0a000a, 0xf7f700f7, 0xe4e400e4, 0x58580058, 0x05050005, 0xb8b800b8, 0xb3b300b3, 0x45450045, 0x06060006, 0xd0d000d0, 0x2c2c002c, 0x1e1e001e, 0x8f8f008f, 0xcaca00ca, 0x3f3f003f, 0x0f0f000f, 0x02020002, 0xc1c100c1, 0xafaf00af, 0xbdbd00bd, 0x03030003, 0x01010001, 0x13130013, 0x8a8a008a, 0x6b6b006b, 0x3a3a003a, 0x91910091, 0x11110011, 0x41410041, 0x4f4f004f, 0x67670067, 0xdcdc00dc, 0xeaea00ea, 0x97970097, 0xf2f200f2, 0xcfcf00cf, 0xcece00ce, 0xf0f000f0, 0xb4b400b4, 0xe6e600e6, 0x73730073, 0x96960096, 0xacac00ac, 0x74740074, 0x22220022, 0xe7e700e7, 0xadad00ad, 0x35350035, 0x85850085, 0xe2e200e2, 0xf9f900f9, 0x37370037, 0xe8e800e8, 0x1c1c001c, 0x75750075, 0xdfdf00df, 0x6e6e006e, 0x47470047, 0xf1f100f1, 0x1a1a001a, 0x71710071, 0x1d1d001d, 0x29290029, 0xc5c500c5, 0x89890089, 0x6f6f006f, 0xb7b700b7, 0x62620062, 0x0e0e000e, 0xaaaa00aa, 0x18180018, 0xbebe00be, 0x1b1b001b, 0xfcfc00fc, 0x56560056, 0x3e3e003e, 0x4b4b004b, 0xc6c600c6, 0xd2d200d2, 0x79790079, 0x20200020, 0x9a9a009a, 0xdbdb00db, 0xc0c000c0, 0xfefe00fe, 0x78780078, 0xcdcd00cd, 0x5a5a005a, 0xf4f400f4, 0x1f1f001f, 0xdddd00dd, 0xa8a800a8, 0x33330033, 0x88880088, 0x07070007, 0xc7c700c7, 0x31310031, 0xb1b100b1, 0x12120012, 0x10100010, 0x59590059, 0x27270027, 0x80800080, 0xecec00ec, 0x5f5f005f, 0x60600060, 0x51510051, 0x7f7f007f, 0xa9a900a9, 0x19190019, 0xb5b500b5, 0x4a4a004a, 0x0d0d000d, 0x2d2d002d, 0xe5e500e5, 0x7a7a007a, 0x9f9f009f, 0x93930093, 0xc9c900c9, 0x9c9c009c, 0xefef00ef, 0xa0a000a0, 0xe0e000e0, 0x3b3b003b, 0x4d4d004d, 0xaeae00ae, 0x2a2a002a, 0xf5f500f5, 0xb0b000b0, 0xc8c800c8, 0xebeb00eb, 0xbbbb00bb, 0x3c3c003c, 0x83830083, 0x53530053, 0x99990099, 0x61610061, 0x17170017, 0x2b2b002b, 0x04040004, 0x7e7e007e, 0xbaba00ba, 0x77770077, 0xd6d600d6, 0x26260026, 0xe1e100e1, 0x69690069, 0x14140014, 0x63630063, 0x55550055, 0x21210021, 0x0c0c000c, 0x7d7d007d }; static const u32 x2[256] = { 0x30303000, 0x68686800, 0x99999900, 0x1b1b1b00, 0x87878700, 0xb9b9b900, 0x21212100, 0x78787800, 0x50505000, 0x39393900, 0xdbdbdb00, 0xe1e1e100, 0x72727200, 0x09090900, 0x62626200, 0x3c3c3c00, 0x3e3e3e00, 0x7e7e7e00, 0x5e5e5e00, 0x8e8e8e00, 0xf1f1f100, 0xa0a0a000, 0xcccccc00, 0xa3a3a300, 0x2a2a2a00, 0x1d1d1d00, 0xfbfbfb00, 0xb6b6b600, 0xd6d6d600, 0x20202000, 0xc4c4c400, 0x8d8d8d00, 0x81818100, 0x65656500, 0xf5f5f500, 0x89898900, 0xcbcbcb00, 0x9d9d9d00, 0x77777700, 0xc6c6c600, 0x57575700, 0x43434300, 0x56565600, 0x17171700, 0xd4d4d400, 0x40404000, 0x1a1a1a00, 0x4d4d4d00, 0xc0c0c000, 0x63636300, 0x6c6c6c00, 0xe3e3e300, 0xb7b7b700, 0xc8c8c800, 0x64646400, 0x6a6a6a00, 0x53535300, 0xaaaaaa00, 0x38383800, 0x98989800, 0x0c0c0c00, 0xf4f4f400, 0x9b9b9b00, 0xededed00, 0x7f7f7f00, 0x22222200, 0x76767600, 0xafafaf00, 0xdddddd00, 0x3a3a3a00, 0x0b0b0b00, 0x58585800, 0x67676700, 0x88888800, 0x06060600, 0xc3c3c300, 0x35353500, 0x0d0d0d00, 0x01010100, 0x8b8b8b00, 0x8c8c8c00, 0xc2c2c200, 0xe6e6e600, 0x5f5f5f00, 0x02020200, 0x24242400, 0x75757500, 0x93939300, 0x66666600, 0x1e1e1e00, 0xe5e5e500, 0xe2e2e200, 0x54545400, 0xd8d8d800, 0x10101000, 0xcecece00, 0x7a7a7a00, 0xe8e8e800, 0x08080800, 0x2c2c2c00, 0x12121200, 0x97979700, 0x32323200, 0xababab00, 0xb4b4b400, 0x27272700, 0x0a0a0a00, 0x23232300, 0xdfdfdf00, 0xefefef00, 0xcacaca00, 0xd9d9d900, 0xb8b8b800, 0xfafafa00, 0xdcdcdc00, 0x31313100, 0x6b6b6b00, 0xd1d1d100, 0xadadad00, 0x19191900, 0x49494900, 0xbdbdbd00, 0x51515100, 0x96969600, 0xeeeeee00, 0xe4e4e400, 0xa8a8a800, 0x41414100, 0xdadada00, 0xffffff00, 0xcdcdcd00, 0x55555500, 0x86868600, 0x36363600, 0xbebebe00, 0x61616100, 0x52525200, 0xf8f8f800, 0xbbbbbb00, 0x0e0e0e00, 0x82828200, 0x48484800, 0x69696900, 0x9a9a9a00, 0xe0e0e000, 0x47474700, 0x9e9e9e00, 0x5c5c5c00, 0x04040400, 0x4b4b4b00, 0x34343400, 0x15151500, 0x79797900, 0x26262600, 0xa7a7a700, 0xdedede00, 0x29292900, 0xaeaeae00, 0x92929200, 0xd7d7d700, 0x84848400, 0xe9e9e900, 0xd2d2d200, 0xbababa00, 0x5d5d5d00, 0xf3f3f300, 0xc5c5c500, 0xb0b0b000, 0xbfbfbf00, 0xa4a4a400, 0x3b3b3b00, 0x71717100, 0x44444400, 0x46464600, 0x2b2b2b00, 0xfcfcfc00, 0xebebeb00, 0x6f6f6f00, 0xd5d5d500, 0xf6f6f600, 0x14141400, 0xfefefe00, 0x7c7c7c00, 0x70707000, 0x5a5a5a00, 0x7d7d7d00, 0xfdfdfd00, 0x2f2f2f00, 0x18181800, 0x83838300, 0x16161600, 0xa5a5a500, 0x91919100, 0x1f1f1f00, 0x05050500, 0x95959500, 0x74747400, 0xa9a9a900, 0xc1c1c100, 0x5b5b5b00, 0x4a4a4a00, 0x85858500, 0x6d6d6d00, 0x13131300, 0x07070700, 0x4f4f4f00, 0x4e4e4e00, 0x45454500, 0xb2b2b200, 0x0f0f0f00, 0xc9c9c900, 0x1c1c1c00, 0xa6a6a600, 0xbcbcbc00, 0xececec00, 0x73737300, 0x90909000, 0x7b7b7b00, 0xcfcfcf00, 0x59595900, 0x8f8f8f00, 0xa1a1a100, 0xf9f9f900, 0x2d2d2d00, 0xf2f2f200, 0xb1b1b100, 0x00000000, 0x94949400, 0x37373700, 0x9f9f9f00, 0xd0d0d000, 0x2e2e2e00, 0x9c9c9c00, 0x6e6e6e00, 0x28282800, 0x3f3f3f00, 0x80808000, 0xf0f0f000, 0x3d3d3d00, 0xd3d3d300, 0x25252500, 0x8a8a8a00, 0xb5b5b500, 0xe7e7e700, 0x42424200, 0xb3b3b300, 0xc7c7c700, 0xeaeaea00, 0xf7f7f700, 0x4c4c4c00, 0x11111100, 0x33333300, 0x03030300, 0xa2a2a200, 0xacacac00, 0x60606000 }; static inline u32 rotl32(u32 v, u32 r) { return ((v << r) | (v >> (32 - r))); } static inline u32 rotr32(u32 v, u32 r) { return ((v >> r) | (v << (32 - r))); } static inline u32 bswap32(u32 v) { return ((v << 24) ^ (v >> 24) ^ ((v & 0x0000ff00) << 8) ^ ((v & 0x00ff0000) >> 8)); } static inline u8 get_u8(u32 x, u32 y) { return (x >> ((3 - y) * 8)); } static inline u32 make_u32(u8 v0, u8 v1, u8 v2, u8 v3) { return ((u32)v0 << 24) | ((u32)v1 << 16) | ((u32)v2 << 8) | ((u32)v3); } static inline u32 aria_m(u32 t0) { return rotr32(t0, 8) ^ rotr32(t0 ^ rotr32(t0, 8), 16); } /* S-Box Layer 1 + M */ static inline void aria_sbox_layer1_with_pre_diff(u32 *t0, u32 *t1, u32 *t2, u32 *t3) { *t0 = s1[get_u8(*t0, 0)] ^ s2[get_u8(*t0, 1)] ^ x1[get_u8(*t0, 2)] ^ x2[get_u8(*t0, 3)]; *t1 = s1[get_u8(*t1, 0)] ^ s2[get_u8(*t1, 1)] ^ x1[get_u8(*t1, 2)] ^ x2[get_u8(*t1, 3)]; *t2 = s1[get_u8(*t2, 0)] ^ s2[get_u8(*t2, 1)] ^ x1[get_u8(*t2, 2)] ^ x2[get_u8(*t2, 3)]; *t3 = s1[get_u8(*t3, 0)] ^ s2[get_u8(*t3, 1)] ^ x1[get_u8(*t3, 2)] ^ x2[get_u8(*t3, 3)]; } /* S-Box Layer 2 + M */ static inline void aria_sbox_layer2_with_pre_diff(u32 *t0, u32 *t1, u32 *t2, u32 *t3) { *t0 = x1[get_u8(*t0, 0)] ^ x2[get_u8(*t0, 1)] ^ s1[get_u8(*t0, 2)] ^ s2[get_u8(*t0, 3)]; *t1 = x1[get_u8(*t1, 0)] ^ x2[get_u8(*t1, 1)] ^ s1[get_u8(*t1, 2)] ^ s2[get_u8(*t1, 3)]; *t2 = x1[get_u8(*t2, 0)] ^ x2[get_u8(*t2, 1)] ^ s1[get_u8(*t2, 2)] ^ s2[get_u8(*t2, 3)]; *t3 = x1[get_u8(*t3, 0)] ^ x2[get_u8(*t3, 1)] ^ s1[get_u8(*t3, 2)] ^ s2[get_u8(*t3, 3)]; } /* Word-level diffusion */ static inline void aria_diff_word(u32 *t0, u32 *t1, u32 *t2, u32 *t3) { *t1 ^= *t2; *t2 ^= *t3; *t0 ^= *t1; *t3 ^= *t1; *t2 ^= *t0; *t1 ^= *t2; } /* Byte-level diffusion */ static inline void aria_diff_byte(u32 *t1, u32 *t2, u32 *t3) { *t1 = ((*t1 << 8) & 0xff00ff00) ^ ((*t1 >> 8) & 0x00ff00ff); *t2 = rotr32(*t2, 16); *t3 = bswap32(*t3); } /* Key XOR Layer */ static inline void aria_add_round_key(u32 *rk, u32 *t0, u32 *t1, u32 *t2, u32 *t3) { *t0 ^= rk[0]; *t1 ^= rk[1]; *t2 ^= rk[2]; *t3 ^= rk[3]; } /* Odd round Substitution & Diffusion */ static inline void aria_subst_diff_odd(u32 *t0, u32 *t1, u32 *t2, u32 *t3) { aria_sbox_layer1_with_pre_diff(t0, t1, t2, t3); aria_diff_word(t0, t1, t2, t3); aria_diff_byte(t1, t2, t3); aria_diff_word(t0, t1, t2, t3); } /* Even round Substitution & Diffusion */ static inline void aria_subst_diff_even(u32 *t0, u32 *t1, u32 *t2, u32 *t3) { aria_sbox_layer2_with_pre_diff(t0, t1, t2, t3); aria_diff_word(t0, t1, t2, t3); aria_diff_byte(t3, t0, t1); aria_diff_word(t0, t1, t2, t3); } /* Q, R Macro expanded ARIA GSRK */ static inline void aria_gsrk(u32 *rk, u32 *x, u32 *y, u32 n) { int q = 4 - (n / 32); int r = n % 32; rk[0] = (x[0]) ^ ((y[q % 4]) >> r) ^ ((y[(q + 3) % 4]) << (32 - r)); rk[1] = (x[1]) ^ ((y[(q + 1) % 4]) >> r) ^ ((y[q % 4]) << (32 - r)); rk[2] = (x[2]) ^ ((y[(q + 2) % 4]) >> r) ^ ((y[(q + 1) % 4]) << (32 - r)); rk[3] = (x[3]) ^ ((y[(q + 3) % 4]) >> r) ^ ((y[(q + 2) % 4]) << (32 - r)); } void aria_encrypt(void *ctx, u8 *out, const u8 *in); void aria_decrypt(void *ctx, u8 *out, const u8 *in); int aria_set_key(struct crypto_tfm *tfm, const u8 *in_key, unsigned int key_len); #endif |
| 11 11 | 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 /* * * Authors: * Alexander Aring <aar@pengutronix.de> * * Based on: net/wireless/sysfs.c */ #include <linux/device.h> #include <linux/rtnetlink.h> #include <net/cfg802154.h> #include "core.h" #include "sysfs.h" #include "rdev-ops.h" static inline struct cfg802154_registered_device * dev_to_rdev(struct device *dev) { return container_of(dev, struct cfg802154_registered_device, wpan_phy.dev); } #define SHOW_FMT(name, fmt, member) \ static ssize_t name ## _show(struct device *dev, \ struct device_attribute *attr, \ char *buf) \ { \ return sprintf(buf, fmt "\n", dev_to_rdev(dev)->member); \ } \ static DEVICE_ATTR_RO(name) SHOW_FMT(index, "%d", wpan_phy_idx); static ssize_t name_show(struct device *dev, struct device_attribute *attr, char *buf) { struct wpan_phy *wpan_phy = &dev_to_rdev(dev)->wpan_phy; return sprintf(buf, "%s\n", dev_name(&wpan_phy->dev)); } static DEVICE_ATTR_RO(name); static void wpan_phy_release(struct device *dev) { struct cfg802154_registered_device *rdev = dev_to_rdev(dev); cfg802154_dev_free(rdev); } static struct attribute *pmib_attrs[] = { &dev_attr_index.attr, &dev_attr_name.attr, NULL, }; ATTRIBUTE_GROUPS(pmib); #ifdef CONFIG_PM_SLEEP static int wpan_phy_suspend(struct device *dev) { struct cfg802154_registered_device *rdev = dev_to_rdev(dev); int ret = 0; if (rdev->ops->suspend) { rtnl_lock(); ret = rdev_suspend(rdev); rtnl_unlock(); } return ret; } static int wpan_phy_resume(struct device *dev) { struct cfg802154_registered_device *rdev = dev_to_rdev(dev); int ret = 0; if (rdev->ops->resume) { rtnl_lock(); ret = rdev_resume(rdev); rtnl_unlock(); } return ret; } static SIMPLE_DEV_PM_OPS(wpan_phy_pm_ops, wpan_phy_suspend, wpan_phy_resume); #define WPAN_PHY_PM_OPS (&wpan_phy_pm_ops) #else #define WPAN_PHY_PM_OPS NULL #endif const struct class wpan_phy_class = { .name = "ieee802154", .dev_release = wpan_phy_release, .dev_groups = pmib_groups, .pm = WPAN_PHY_PM_OPS, }; int wpan_phy_sysfs_init(void) { return class_register(&wpan_phy_class); } void wpan_phy_sysfs_exit(void) { class_unregister(&wpan_phy_class); } |
| 34 15 3 2 1 1 33 13 16 8 7 3 2 1 1 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 | // SPDX-License-Identifier: GPL-2.0-only /* * System calls implementing the Linux Security Module API. * * Copyright (C) 2022 Casey Schaufler <casey@schaufler-ca.com> * Copyright (C) 2022 Intel Corporation */ #include <asm/current.h> #include <linux/compiler_types.h> #include <linux/err.h> #include <linux/errno.h> #include <linux/security.h> #include <linux/stddef.h> #include <linux/syscalls.h> #include <linux/types.h> #include <linux/lsm_hooks.h> #include <uapi/linux/lsm.h> /** * lsm_name_to_attr - map an LSM attribute name to its ID * @name: name of the attribute * * Returns the LSM attribute value associated with @name, or 0 if * there is no mapping. */ u64 lsm_name_to_attr(const char *name) { if (!strcmp(name, "current")) return LSM_ATTR_CURRENT; if (!strcmp(name, "exec")) return LSM_ATTR_EXEC; if (!strcmp(name, "fscreate")) return LSM_ATTR_FSCREATE; if (!strcmp(name, "keycreate")) return LSM_ATTR_KEYCREATE; if (!strcmp(name, "prev")) return LSM_ATTR_PREV; if (!strcmp(name, "sockcreate")) return LSM_ATTR_SOCKCREATE; return LSM_ATTR_UNDEF; } /** * sys_lsm_set_self_attr - Set current task's security module attribute * @attr: which attribute to set * @ctx: the LSM contexts * @size: size of @ctx * @flags: reserved for future use * * Sets the calling task's LSM context. On success this function * returns 0. If the attribute specified cannot be set a negative * value indicating the reason for the error is returned. */ SYSCALL_DEFINE4(lsm_set_self_attr, unsigned int, attr, struct lsm_ctx __user *, ctx, u32, size, u32, flags) { return security_setselfattr(attr, ctx, size, flags); } /** * sys_lsm_get_self_attr - Return current task's security module attributes * @attr: which attribute to return * @ctx: the user-space destination for the information, or NULL * @size: pointer to the size of space available to receive the data * @flags: special handling options. LSM_FLAG_SINGLE indicates that only * attributes associated with the LSM identified in the passed @ctx be * reported. * * Returns the calling task's LSM contexts. On success this * function returns the number of @ctx array elements. This value * may be zero if there are no LSM contexts assigned. If @size is * insufficient to contain the return data -E2BIG is returned and * @size is set to the minimum required size. In all other cases * a negative value indicating the error is returned. */ SYSCALL_DEFINE4(lsm_get_self_attr, unsigned int, attr, struct lsm_ctx __user *, ctx, u32 __user *, size, u32, flags) { return security_getselfattr(attr, ctx, size, flags); } /** * sys_lsm_list_modules - Return a list of the active security modules * @ids: the LSM module ids * @size: pointer to size of @ids, updated on return * @flags: reserved for future use, must be zero * * Returns a list of the active LSM ids. On success this function * returns the number of @ids array elements. This value may be zero * if there are no LSMs active. If @size is insufficient to contain * the return data -E2BIG is returned and @size is set to the minimum * required size. In all other cases a negative value indicating the * error is returned. */ SYSCALL_DEFINE3(lsm_list_modules, u64 __user *, ids, u32 __user *, size, u32, flags) { u32 total_size = lsm_active_cnt * sizeof(*ids); u32 usize; int i; if (flags) return -EINVAL; if (get_user(usize, size)) return -EFAULT; if (put_user(total_size, size) != 0) return -EFAULT; if (usize < total_size) return -E2BIG; for (i = 0; i < lsm_active_cnt; i++) if (put_user(lsm_idlist[i]->id, ids++)) return -EFAULT; return lsm_active_cnt; } |
| 3 3 2 3 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 3 3 3 3 1 2 1 1 1 1 1 1 2 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * AirSpy SDR driver * * Copyright (C) 2014 Antti Palosaari <crope@iki.fi> */ #include <linux/module.h> #include <linux/slab.h> #include <linux/usb.h> #include <media/v4l2-device.h> #include <media/v4l2-ioctl.h> #include <media/v4l2-ctrls.h> #include <media/v4l2-event.h> #include <media/videobuf2-v4l2.h> #include <media/videobuf2-vmalloc.h> /* AirSpy USB API commands (from AirSpy Library) */ enum { CMD_INVALID = 0x00, CMD_RECEIVER_MODE = 0x01, CMD_SI5351C_WRITE = 0x02, CMD_SI5351C_READ = 0x03, CMD_R820T_WRITE = 0x04, CMD_R820T_READ = 0x05, CMD_SPIFLASH_ERASE = 0x06, CMD_SPIFLASH_WRITE = 0x07, CMD_SPIFLASH_READ = 0x08, CMD_BOARD_ID_READ = 0x09, CMD_VERSION_STRING_READ = 0x0a, CMD_BOARD_PARTID_SERIALNO_READ = 0x0b, CMD_SET_SAMPLE_RATE = 0x0c, CMD_SET_FREQ = 0x0d, CMD_SET_LNA_GAIN = 0x0e, CMD_SET_MIXER_GAIN = 0x0f, CMD_SET_VGA_GAIN = 0x10, CMD_SET_LNA_AGC = 0x11, CMD_SET_MIXER_AGC = 0x12, CMD_SET_PACKING = 0x13, }; /* * bEndpointAddress 0x81 EP 1 IN * Transfer Type Bulk * wMaxPacketSize 0x0200 1x 512 bytes */ #define MAX_BULK_BUFS (6) #define BULK_BUFFER_SIZE (128 * 512) static const struct v4l2_frequency_band bands[] = { { .tuner = 0, .type = V4L2_TUNER_ADC, .index = 0, .capability = V4L2_TUNER_CAP_1HZ | V4L2_TUNER_CAP_FREQ_BANDS, .rangelow = 20000000, .rangehigh = 20000000, }, }; static const struct v4l2_frequency_band bands_rf[] = { { .tuner = 1, .type = V4L2_TUNER_RF, .index = 0, .capability = V4L2_TUNER_CAP_1HZ | V4L2_TUNER_CAP_FREQ_BANDS, .rangelow = 24000000, .rangehigh = 1750000000, }, }; /* stream formats */ struct airspy_format { u32 pixelformat; u32 buffersize; }; /* format descriptions for capture and preview */ static struct airspy_format formats[] = { { .pixelformat = V4L2_SDR_FMT_RU12LE, .buffersize = BULK_BUFFER_SIZE, }, }; static const unsigned int NUM_FORMATS = ARRAY_SIZE(formats); /* intermediate buffers with raw data from the USB device */ struct airspy_frame_buf { /* common v4l buffer stuff -- must be first */ struct vb2_v4l2_buffer vb; struct list_head list; }; struct airspy { #define POWER_ON 1 #define USB_STATE_URB_BUF 2 unsigned long flags; struct device *dev; struct usb_device *udev; struct video_device vdev; struct v4l2_device v4l2_dev; /* videobuf2 queue and queued buffers list */ struct vb2_queue vb_queue; struct list_head queued_bufs; spinlock_t queued_bufs_lock; /* Protects queued_bufs */ unsigned sequence; /* Buffer sequence counter */ unsigned int vb_full; /* vb is full and packets dropped */ /* Note if taking both locks v4l2_lock must always be locked first! */ struct mutex v4l2_lock; /* Protects everything else */ struct mutex vb_queue_lock; /* Protects vb_queue and capt_file */ struct urb *urb_list[MAX_BULK_BUFS]; int buf_num; unsigned long buf_size; u8 *buf_list[MAX_BULK_BUFS]; dma_addr_t dma_addr[MAX_BULK_BUFS]; int urbs_initialized; int urbs_submitted; /* USB control message buffer */ #define BUF_SIZE 128 u8 *buf; /* Current configuration */ unsigned int f_adc; unsigned int f_rf; u32 pixelformat; u32 buffersize; /* Controls */ struct v4l2_ctrl_handler hdl; struct v4l2_ctrl *lna_gain_auto; struct v4l2_ctrl *lna_gain; struct v4l2_ctrl *mixer_gain_auto; struct v4l2_ctrl *mixer_gain; struct v4l2_ctrl *if_gain; /* Sample rate calc */ unsigned long jiffies_next; unsigned int sample; unsigned int sample_measured; }; #define airspy_dbg_usb_control_msg(_dev, _r, _t, _v, _i, _b, _l) { \ char *_direction; \ if (_t & USB_DIR_IN) \ _direction = "<<<"; \ else \ _direction = ">>>"; \ dev_dbg(_dev, "%02x %02x %02x %02x %02x %02x %02x %02x %s %*ph\n", \ _t, _r, _v & 0xff, _v >> 8, _i & 0xff, _i >> 8, \ _l & 0xff, _l >> 8, _direction, _l, _b); \ } /* execute firmware command */ static int airspy_ctrl_msg(struct airspy *s, u8 request, u16 value, u16 index, u8 *data, u16 size) { int ret; unsigned int pipe; u8 requesttype; switch (request) { case CMD_RECEIVER_MODE: case CMD_SET_FREQ: pipe = usb_sndctrlpipe(s->udev, 0); requesttype = (USB_TYPE_VENDOR | USB_DIR_OUT); break; case CMD_BOARD_ID_READ: case CMD_VERSION_STRING_READ: case CMD_BOARD_PARTID_SERIALNO_READ: case CMD_SET_LNA_GAIN: case CMD_SET_MIXER_GAIN: case CMD_SET_VGA_GAIN: case CMD_SET_LNA_AGC: case CMD_SET_MIXER_AGC: pipe = usb_rcvctrlpipe(s->udev, 0); requesttype = (USB_TYPE_VENDOR | USB_DIR_IN); break; default: dev_err(s->dev, "Unknown command %02x\n", request); ret = -EINVAL; goto err; } /* write request */ if (!(requesttype & USB_DIR_IN)) memcpy(s->buf, data, size); ret = usb_control_msg(s->udev, pipe, request, requesttype, value, index, s->buf, size, 1000); airspy_dbg_usb_control_msg(s->dev, request, requesttype, value, index, s->buf, size); if (ret < 0) { dev_err(s->dev, "usb_control_msg() failed %d request %02x\n", ret, request); goto err; } /* read request */ if (requesttype & USB_DIR_IN) memcpy(data, s->buf, size); return 0; err: return ret; } /* Private functions */ static struct airspy_frame_buf *airspy_get_next_fill_buf(struct airspy *s) { unsigned long flags; struct airspy_frame_buf *buf = NULL; spin_lock_irqsave(&s->queued_bufs_lock, flags); if (list_empty(&s->queued_bufs)) goto leave; buf = list_entry(s->queued_bufs.next, struct airspy_frame_buf, list); list_del(&buf->list); leave: spin_unlock_irqrestore(&s->queued_bufs_lock, flags); return buf; } static unsigned int airspy_convert_stream(struct airspy *s, void *dst, void *src, unsigned int src_len) { unsigned int dst_len; if (s->pixelformat == V4L2_SDR_FMT_RU12LE) { memcpy(dst, src, src_len); dst_len = src_len; } else { dst_len = 0; } /* calculate sample rate and output it in 10 seconds intervals */ if (unlikely(time_is_before_jiffies(s->jiffies_next))) { #define MSECS 10000UL unsigned int msecs = jiffies_to_msecs(jiffies - s->jiffies_next + msecs_to_jiffies(MSECS)); unsigned int samples = s->sample - s->sample_measured; s->jiffies_next = jiffies + msecs_to_jiffies(MSECS); s->sample_measured = s->sample; dev_dbg(s->dev, "slen=%u samples=%u msecs=%u sample rate=%lu\n", src_len, samples, msecs, samples * 1000UL / msecs); } /* total number of samples */ s->sample += src_len / 2; return dst_len; } /* * This gets called for the bulk stream pipe. This is done in interrupt * time, so it has to be fast, not crash, and not stall. Neat. */ static void airspy_urb_complete(struct urb *urb) { struct airspy *s = urb->context; struct airspy_frame_buf *fbuf; dev_dbg_ratelimited(s->dev, "status=%d length=%d/%d errors=%d\n", urb->status, urb->actual_length, urb->transfer_buffer_length, urb->error_count); switch (urb->status) { case 0: /* success */ case -ETIMEDOUT: /* NAK */ break; case -ECONNRESET: /* kill */ case -ENOENT: case -ESHUTDOWN: return; default: /* error */ dev_err_ratelimited(s->dev, "URB failed %d\n", urb->status); break; } if (likely(urb->actual_length > 0)) { void *ptr; unsigned int len; /* get free framebuffer */ fbuf = airspy_get_next_fill_buf(s); if (unlikely(fbuf == NULL)) { s->vb_full++; dev_notice_ratelimited(s->dev, "video buffer is full, %d packets dropped\n", s->vb_full); goto skip; } /* fill framebuffer */ ptr = vb2_plane_vaddr(&fbuf->vb.vb2_buf, 0); len = airspy_convert_stream(s, ptr, urb->transfer_buffer, urb->actual_length); vb2_set_plane_payload(&fbuf->vb.vb2_buf, 0, len); fbuf->vb.vb2_buf.timestamp = ktime_get_ns(); fbuf->vb.sequence = s->sequence++; vb2_buffer_done(&fbuf->vb.vb2_buf, VB2_BUF_STATE_DONE); } skip: usb_submit_urb(urb, GFP_ATOMIC); } static int airspy_kill_urbs(struct airspy *s) { int i; for (i = s->urbs_submitted - 1; i >= 0; i--) { dev_dbg(s->dev, "kill urb=%d\n", i); /* stop the URB */ usb_kill_urb(s->urb_list[i]); } s->urbs_submitted = 0; return 0; } static int airspy_submit_urbs(struct airspy *s) { int i, ret; for (i = 0; i < s->urbs_initialized; i++) { dev_dbg(s->dev, "submit urb=%d\n", i); ret = usb_submit_urb(s->urb_list[i], GFP_ATOMIC); if (ret) { dev_err(s->dev, "Could not submit URB no. %d - get them all back\n", i); airspy_kill_urbs(s); return ret; } s->urbs_submitted++; } return 0; } static int airspy_free_stream_bufs(struct airspy *s) { if (test_bit(USB_STATE_URB_BUF, &s->flags)) { while (s->buf_num) { s->buf_num--; dev_dbg(s->dev, "free buf=%d\n", s->buf_num); usb_free_coherent(s->udev, s->buf_size, s->buf_list[s->buf_num], s->dma_addr[s->buf_num]); } } clear_bit(USB_STATE_URB_BUF, &s->flags); return 0; } static int airspy_alloc_stream_bufs(struct airspy *s) { s->buf_num = 0; s->buf_size = BULK_BUFFER_SIZE; dev_dbg(s->dev, "all in all I will use %u bytes for streaming\n", MAX_BULK_BUFS * BULK_BUFFER_SIZE); for (s->buf_num = 0; s->buf_num < MAX_BULK_BUFS; s->buf_num++) { s->buf_list[s->buf_num] = usb_alloc_coherent(s->udev, BULK_BUFFER_SIZE, GFP_ATOMIC, &s->dma_addr[s->buf_num]); if (!s->buf_list[s->buf_num]) { dev_dbg(s->dev, "alloc buf=%d failed\n", s->buf_num); airspy_free_stream_bufs(s); return -ENOMEM; } dev_dbg(s->dev, "alloc buf=%d %p (dma %llu)\n", s->buf_num, s->buf_list[s->buf_num], (long long)s->dma_addr[s->buf_num]); set_bit(USB_STATE_URB_BUF, &s->flags); } return 0; } static int airspy_free_urbs(struct airspy *s) { int i; airspy_kill_urbs(s); for (i = s->urbs_initialized - 1; i >= 0; i--) { if (s->urb_list[i]) { dev_dbg(s->dev, "free urb=%d\n", i); /* free the URBs */ usb_free_urb(s->urb_list[i]); } } s->urbs_initialized = 0; return 0; } static int airspy_alloc_urbs(struct airspy *s) { int i, j; /* allocate the URBs */ for (i = 0; i < MAX_BULK_BUFS; i++) { dev_dbg(s->dev, "alloc urb=%d\n", i); s->urb_list[i] = usb_alloc_urb(0, GFP_ATOMIC); if (!s->urb_list[i]) { for (j = 0; j < i; j++) { usb_free_urb(s->urb_list[j]); s->urb_list[j] = NULL; } s->urbs_initialized = 0; return -ENOMEM; } usb_fill_bulk_urb(s->urb_list[i], s->udev, usb_rcvbulkpipe(s->udev, 0x81), s->buf_list[i], BULK_BUFFER_SIZE, airspy_urb_complete, s); s->urb_list[i]->transfer_flags = URB_NO_TRANSFER_DMA_MAP; s->urb_list[i]->transfer_dma = s->dma_addr[i]; s->urbs_initialized++; } return 0; } /* Must be called with vb_queue_lock hold */ static void airspy_cleanup_queued_bufs(struct airspy *s) { unsigned long flags; dev_dbg(s->dev, "\n"); spin_lock_irqsave(&s->queued_bufs_lock, flags); while (!list_empty(&s->queued_bufs)) { struct airspy_frame_buf *buf; buf = list_entry(s->queued_bufs.next, struct airspy_frame_buf, list); list_del(&buf->list); vb2_buffer_done(&buf->vb.vb2_buf, VB2_BUF_STATE_ERROR); } spin_unlock_irqrestore(&s->queued_bufs_lock, flags); } /* The user yanked out the cable... */ static void airspy_disconnect(struct usb_interface *intf) { struct v4l2_device *v = usb_get_intfdata(intf); struct airspy *s = container_of(v, struct airspy, v4l2_dev); dev_dbg(s->dev, "\n"); mutex_lock(&s->vb_queue_lock); mutex_lock(&s->v4l2_lock); /* No need to keep the urbs around after disconnection */ s->udev = NULL; v4l2_device_disconnect(&s->v4l2_dev); video_unregister_device(&s->vdev); mutex_unlock(&s->v4l2_lock); mutex_unlock(&s->vb_queue_lock); v4l2_device_put(&s->v4l2_dev); } /* Videobuf2 operations */ static int airspy_queue_setup(struct vb2_queue *vq, unsigned int *nbuffers, unsigned int *nplanes, unsigned int sizes[], struct device *alloc_devs[]) { struct airspy *s = vb2_get_drv_priv(vq); unsigned int q_num_bufs = vb2_get_num_buffers(vq); dev_dbg(s->dev, "nbuffers=%d\n", *nbuffers); /* Need at least 8 buffers */ if (q_num_bufs + *nbuffers < 8) *nbuffers = 8 - q_num_bufs; *nplanes = 1; sizes[0] = PAGE_ALIGN(s->buffersize); dev_dbg(s->dev, "nbuffers=%d sizes[0]=%d\n", *nbuffers, sizes[0]); return 0; } static void airspy_buf_queue(struct vb2_buffer *vb) { struct vb2_v4l2_buffer *vbuf = to_vb2_v4l2_buffer(vb); struct airspy *s = vb2_get_drv_priv(vb->vb2_queue); struct airspy_frame_buf *buf = container_of(vbuf, struct airspy_frame_buf, vb); unsigned long flags; /* Check the device has not disconnected between prep and queuing */ if (unlikely(!s->udev)) { vb2_buffer_done(&buf->vb.vb2_buf, VB2_BUF_STATE_ERROR); return; } spin_lock_irqsave(&s->queued_bufs_lock, flags); list_add_tail(&buf->list, &s->queued_bufs); spin_unlock_irqrestore(&s->queued_bufs_lock, flags); } static int airspy_start_streaming(struct vb2_queue *vq, unsigned int count) { struct airspy *s = vb2_get_drv_priv(vq); int ret; dev_dbg(s->dev, "\n"); if (!s->udev) return -ENODEV; mutex_lock(&s->v4l2_lock); s->sequence = 0; set_bit(POWER_ON, &s->flags); ret = airspy_alloc_stream_bufs(s); if (ret) goto err_clear_bit; ret = airspy_alloc_urbs(s); if (ret) goto err_free_stream_bufs; ret = airspy_submit_urbs(s); if (ret) goto err_free_urbs; /* start hardware streaming */ ret = airspy_ctrl_msg(s, CMD_RECEIVER_MODE, 1, 0, NULL, 0); if (ret) goto err_kill_urbs; goto exit_mutex_unlock; err_kill_urbs: airspy_kill_urbs(s); err_free_urbs: airspy_free_urbs(s); err_free_stream_bufs: airspy_free_stream_bufs(s); err_clear_bit: clear_bit(POWER_ON, &s->flags); /* return all queued buffers to vb2 */ { struct airspy_frame_buf *buf, *tmp; list_for_each_entry_safe(buf, tmp, &s->queued_bufs, list) { list_del(&buf->list); vb2_buffer_done(&buf->vb.vb2_buf, VB2_BUF_STATE_QUEUED); } } exit_mutex_unlock: mutex_unlock(&s->v4l2_lock); return ret; } static void airspy_stop_streaming(struct vb2_queue *vq) { struct airspy *s = vb2_get_drv_priv(vq); dev_dbg(s->dev, "\n"); mutex_lock(&s->v4l2_lock); /* stop hardware streaming */ airspy_ctrl_msg(s, CMD_RECEIVER_MODE, 0, 0, NULL, 0); airspy_kill_urbs(s); airspy_free_urbs(s); airspy_free_stream_bufs(s); airspy_cleanup_queued_bufs(s); clear_bit(POWER_ON, &s->flags); mutex_unlock(&s->v4l2_lock); } static const struct vb2_ops airspy_vb2_ops = { .queue_setup = airspy_queue_setup, .buf_queue = airspy_buf_queue, .start_streaming = airspy_start_streaming, .stop_streaming = airspy_stop_streaming, }; static int airspy_querycap(struct file *file, void *fh, struct v4l2_capability *cap) { struct airspy *s = video_drvdata(file); strscpy(cap->driver, KBUILD_MODNAME, sizeof(cap->driver)); strscpy(cap->card, s->vdev.name, sizeof(cap->card)); usb_make_path(s->udev, cap->bus_info, sizeof(cap->bus_info)); return 0; } static int airspy_enum_fmt_sdr_cap(struct file *file, void *priv, struct v4l2_fmtdesc *f) { if (f->index >= NUM_FORMATS) return -EINVAL; f->pixelformat = formats[f->index].pixelformat; return 0; } static int airspy_g_fmt_sdr_cap(struct file *file, void *priv, struct v4l2_format *f) { struct airspy *s = video_drvdata(file); f->fmt.sdr.pixelformat = s->pixelformat; f->fmt.sdr.buffersize = s->buffersize; return 0; } static int airspy_s_fmt_sdr_cap(struct file *file, void *priv, struct v4l2_format *f) { struct airspy *s = video_drvdata(file); struct vb2_queue *q = &s->vb_queue; int i; if (vb2_is_busy(q)) return -EBUSY; for (i = 0; i < NUM_FORMATS; i++) { if (formats[i].pixelformat == f->fmt.sdr.pixelformat) { s->pixelformat = formats[i].pixelformat; s->buffersize = formats[i].buffersize; f->fmt.sdr.buffersize = formats[i].buffersize; return 0; } } s->pixelformat = formats[0].pixelformat; s->buffersize = formats[0].buffersize; f->fmt.sdr.pixelformat = formats[0].pixelformat; f->fmt.sdr.buffersize = formats[0].buffersize; return 0; } static int airspy_try_fmt_sdr_cap(struct file *file, void *priv, struct v4l2_format *f) { int i; for (i = 0; i < NUM_FORMATS; i++) { if (formats[i].pixelformat == f->fmt.sdr.pixelformat) { f->fmt.sdr.buffersize = formats[i].buffersize; return 0; } } f->fmt.sdr.pixelformat = formats[0].pixelformat; f->fmt.sdr.buffersize = formats[0].buffersize; return 0; } static int airspy_s_tuner(struct file *file, void *priv, const struct v4l2_tuner *v) { int ret; if (v->index == 0) ret = 0; else if (v->index == 1) ret = 0; else ret = -EINVAL; return ret; } static int airspy_g_tuner(struct file *file, void *priv, struct v4l2_tuner *v) { int ret; if (v->index == 0) { strscpy(v->name, "AirSpy ADC", sizeof(v->name)); v->type = V4L2_TUNER_ADC; v->capability = V4L2_TUNER_CAP_1HZ | V4L2_TUNER_CAP_FREQ_BANDS; v->rangelow = bands[0].rangelow; v->rangehigh = bands[0].rangehigh; ret = 0; } else if (v->index == 1) { strscpy(v->name, "AirSpy RF", sizeof(v->name)); v->type = V4L2_TUNER_RF; v->capability = V4L2_TUNER_CAP_1HZ | V4L2_TUNER_CAP_FREQ_BANDS; v->rangelow = bands_rf[0].rangelow; v->rangehigh = bands_rf[0].rangehigh; ret = 0; } else { ret = -EINVAL; } return ret; } static int airspy_g_frequency(struct file *file, void *priv, struct v4l2_frequency *f) { struct airspy *s = video_drvdata(file); int ret; if (f->tuner == 0) { f->type = V4L2_TUNER_ADC; f->frequency = s->f_adc; dev_dbg(s->dev, "ADC frequency=%u Hz\n", s->f_adc); ret = 0; } else if (f->tuner == 1) { f->type = V4L2_TUNER_RF; f->frequency = s->f_rf; dev_dbg(s->dev, "RF frequency=%u Hz\n", s->f_rf); ret = 0; } else { ret = -EINVAL; } return ret; } static int airspy_s_frequency(struct file *file, void *priv, const struct v4l2_frequency *f) { struct airspy *s = video_drvdata(file); int ret; u8 buf[4]; if (f->tuner == 0) { s->f_adc = clamp_t(unsigned int, f->frequency, bands[0].rangelow, bands[0].rangehigh); dev_dbg(s->dev, "ADC frequency=%u Hz\n", s->f_adc); ret = 0; } else if (f->tuner == 1) { s->f_rf = clamp_t(unsigned int, f->frequency, bands_rf[0].rangelow, bands_rf[0].rangehigh); dev_dbg(s->dev, "RF frequency=%u Hz\n", s->f_rf); buf[0] = (s->f_rf >> 0) & 0xff; buf[1] = (s->f_rf >> 8) & 0xff; buf[2] = (s->f_rf >> 16) & 0xff; buf[3] = (s->f_rf >> 24) & 0xff; ret = airspy_ctrl_msg(s, CMD_SET_FREQ, 0, 0, buf, 4); } else { ret = -EINVAL; } return ret; } static int airspy_enum_freq_bands(struct file *file, void *priv, struct v4l2_frequency_band *band) { int ret; if (band->tuner == 0) { if (band->index >= ARRAY_SIZE(bands)) { ret = -EINVAL; } else { *band = bands[band->index]; ret = 0; } } else if (band->tuner == 1) { if (band->index >= ARRAY_SIZE(bands_rf)) { ret = -EINVAL; } else { *band = bands_rf[band->index]; ret = 0; } } else { ret = -EINVAL; } return ret; } static const struct v4l2_ioctl_ops airspy_ioctl_ops = { .vidioc_querycap = airspy_querycap, .vidioc_enum_fmt_sdr_cap = airspy_enum_fmt_sdr_cap, .vidioc_g_fmt_sdr_cap = airspy_g_fmt_sdr_cap, .vidioc_s_fmt_sdr_cap = airspy_s_fmt_sdr_cap, .vidioc_try_fmt_sdr_cap = airspy_try_fmt_sdr_cap, .vidioc_reqbufs = vb2_ioctl_reqbufs, .vidioc_create_bufs = vb2_ioctl_create_bufs, .vidioc_prepare_buf = vb2_ioctl_prepare_buf, .vidioc_querybuf = vb2_ioctl_querybuf, .vidioc_qbuf = vb2_ioctl_qbuf, .vidioc_dqbuf = vb2_ioctl_dqbuf, .vidioc_streamon = vb2_ioctl_streamon, .vidioc_streamoff = vb2_ioctl_streamoff, .vidioc_g_tuner = airspy_g_tuner, .vidioc_s_tuner = airspy_s_tuner, .vidioc_g_frequency = airspy_g_frequency, .vidioc_s_frequency = airspy_s_frequency, .vidioc_enum_freq_bands = airspy_enum_freq_bands, .vidioc_subscribe_event = v4l2_ctrl_subscribe_event, .vidioc_unsubscribe_event = v4l2_event_unsubscribe, .vidioc_log_status = v4l2_ctrl_log_status, }; static const struct v4l2_file_operations airspy_fops = { .owner = THIS_MODULE, .open = v4l2_fh_open, .release = vb2_fop_release, .read = vb2_fop_read, .poll = vb2_fop_poll, .mmap = vb2_fop_mmap, .unlocked_ioctl = video_ioctl2, }; static const struct video_device airspy_template = { .name = "AirSpy SDR", .release = video_device_release_empty, .fops = &airspy_fops, .ioctl_ops = &airspy_ioctl_ops, }; static void airspy_video_release(struct v4l2_device *v) { struct airspy *s = container_of(v, struct airspy, v4l2_dev); v4l2_ctrl_handler_free(&s->hdl); v4l2_device_unregister(&s->v4l2_dev); kfree(s->buf); kfree(s); } static int airspy_set_lna_gain(struct airspy *s) { int ret; u8 u8tmp; dev_dbg(s->dev, "lna auto=%d->%d val=%d->%d\n", s->lna_gain_auto->cur.val, s->lna_gain_auto->val, s->lna_gain->cur.val, s->lna_gain->val); ret = airspy_ctrl_msg(s, CMD_SET_LNA_AGC, 0, s->lna_gain_auto->val, &u8tmp, 1); if (ret) goto err; if (s->lna_gain_auto->val == false) { ret = airspy_ctrl_msg(s, CMD_SET_LNA_GAIN, 0, s->lna_gain->val, &u8tmp, 1); if (ret) goto err; } err: if (ret) dev_dbg(s->dev, "failed=%d\n", ret); return ret; } static int airspy_set_mixer_gain(struct airspy *s) { int ret; u8 u8tmp; dev_dbg(s->dev, "mixer auto=%d->%d val=%d->%d\n", s->mixer_gain_auto->cur.val, s->mixer_gain_auto->val, s->mixer_gain->cur.val, s->mixer_gain->val); ret = airspy_ctrl_msg(s, CMD_SET_MIXER_AGC, 0, s->mixer_gain_auto->val, &u8tmp, 1); if (ret) goto err; if (s->mixer_gain_auto->val == false) { ret = airspy_ctrl_msg(s, CMD_SET_MIXER_GAIN, 0, s->mixer_gain->val, &u8tmp, 1); if (ret) goto err; } err: if (ret) dev_dbg(s->dev, "failed=%d\n", ret); return ret; } static int airspy_set_if_gain(struct airspy *s) { int ret; u8 u8tmp; dev_dbg(s->dev, "val=%d->%d\n", s->if_gain->cur.val, s->if_gain->val); ret = airspy_ctrl_msg(s, CMD_SET_VGA_GAIN, 0, s->if_gain->val, &u8tmp, 1); if (ret) dev_dbg(s->dev, "failed=%d\n", ret); return ret; } static int airspy_s_ctrl(struct v4l2_ctrl *ctrl) { struct airspy *s = container_of(ctrl->handler, struct airspy, hdl); int ret; switch (ctrl->id) { case V4L2_CID_RF_TUNER_LNA_GAIN_AUTO: case V4L2_CID_RF_TUNER_LNA_GAIN: ret = airspy_set_lna_gain(s); break; case V4L2_CID_RF_TUNER_MIXER_GAIN_AUTO: case V4L2_CID_RF_TUNER_MIXER_GAIN: ret = airspy_set_mixer_gain(s); break; case V4L2_CID_RF_TUNER_IF_GAIN: ret = airspy_set_if_gain(s); break; default: dev_dbg(s->dev, "unknown ctrl: id=%d name=%s\n", ctrl->id, ctrl->name); ret = -EINVAL; } return ret; } static const struct v4l2_ctrl_ops airspy_ctrl_ops = { .s_ctrl = airspy_s_ctrl, }; static int airspy_probe(struct usb_interface *intf, const struct usb_device_id *id) { struct airspy *s; int ret; u8 u8tmp, *buf; buf = NULL; ret = -ENOMEM; s = kzalloc(sizeof(struct airspy), GFP_KERNEL); if (s == NULL) { dev_err(&intf->dev, "Could not allocate memory for state\n"); return -ENOMEM; } s->buf = kzalloc(BUF_SIZE, GFP_KERNEL); if (!s->buf) goto err_free_mem; buf = kzalloc(BUF_SIZE, GFP_KERNEL); if (!buf) goto err_free_mem; mutex_init(&s->v4l2_lock); mutex_init(&s->vb_queue_lock); spin_lock_init(&s->queued_bufs_lock); INIT_LIST_HEAD(&s->queued_bufs); s->dev = &intf->dev; s->udev = interface_to_usbdev(intf); s->f_adc = bands[0].rangelow; s->f_rf = bands_rf[0].rangelow; s->pixelformat = formats[0].pixelformat; s->buffersize = formats[0].buffersize; /* Detect device */ ret = airspy_ctrl_msg(s, CMD_BOARD_ID_READ, 0, 0, &u8tmp, 1); if (ret == 0) ret = airspy_ctrl_msg(s, CMD_VERSION_STRING_READ, 0, 0, buf, BUF_SIZE); if (ret) { dev_err(s->dev, "Could not detect board\n"); goto err_free_mem; } buf[BUF_SIZE - 1] = '\0'; dev_info(s->dev, "Board ID: %02x\n", u8tmp); dev_info(s->dev, "Firmware version: %s\n", buf); /* Init videobuf2 queue structure */ s->vb_queue.type = V4L2_BUF_TYPE_SDR_CAPTURE; s->vb_queue.io_modes = VB2_MMAP | VB2_USERPTR | VB2_READ; s->vb_queue.drv_priv = s; s->vb_queue.buf_struct_size = sizeof(struct airspy_frame_buf); s->vb_queue.ops = &airspy_vb2_ops; s->vb_queue.mem_ops = &vb2_vmalloc_memops; s->vb_queue.timestamp_flags = V4L2_BUF_FLAG_TIMESTAMP_MONOTONIC; s->vb_queue.lock = &s->vb_queue_lock; ret = vb2_queue_init(&s->vb_queue); if (ret) { dev_err(s->dev, "Could not initialize vb2 queue\n"); goto err_free_mem; } /* Init video_device structure */ s->vdev = airspy_template; s->vdev.queue = &s->vb_queue; video_set_drvdata(&s->vdev, s); /* Register the v4l2_device structure */ s->v4l2_dev.release = airspy_video_release; ret = v4l2_device_register(&intf->dev, &s->v4l2_dev); if (ret) { dev_err(s->dev, "Failed to register v4l2-device (%d)\n", ret); goto err_free_mem; } /* Register controls */ v4l2_ctrl_handler_init(&s->hdl, 5); s->lna_gain_auto = v4l2_ctrl_new_std(&s->hdl, &airspy_ctrl_ops, V4L2_CID_RF_TUNER_LNA_GAIN_AUTO, 0, 1, 1, 0); s->lna_gain = v4l2_ctrl_new_std(&s->hdl, &airspy_ctrl_ops, V4L2_CID_RF_TUNER_LNA_GAIN, 0, 14, 1, 8); v4l2_ctrl_auto_cluster(2, &s->lna_gain_auto, 0, false); s->mixer_gain_auto = v4l2_ctrl_new_std(&s->hdl, &airspy_ctrl_ops, V4L2_CID_RF_TUNER_MIXER_GAIN_AUTO, 0, 1, 1, 0); s->mixer_gain = v4l2_ctrl_new_std(&s->hdl, &airspy_ctrl_ops, V4L2_CID_RF_TUNER_MIXER_GAIN, 0, 15, 1, 8); v4l2_ctrl_auto_cluster(2, &s->mixer_gain_auto, 0, false); s->if_gain = v4l2_ctrl_new_std(&s->hdl, &airspy_ctrl_ops, V4L2_CID_RF_TUNER_IF_GAIN, 0, 15, 1, 0); if (s->hdl.error) { ret = s->hdl.error; dev_err(s->dev, "Could not initialize controls\n"); goto err_free_controls; } v4l2_ctrl_handler_setup(&s->hdl); s->v4l2_dev.ctrl_handler = &s->hdl; s->vdev.v4l2_dev = &s->v4l2_dev; s->vdev.lock = &s->v4l2_lock; s->vdev.device_caps = V4L2_CAP_SDR_CAPTURE | V4L2_CAP_STREAMING | V4L2_CAP_READWRITE | V4L2_CAP_TUNER; ret = video_register_device(&s->vdev, VFL_TYPE_SDR, -1); if (ret) { dev_err(s->dev, "Failed to register as video device (%d)\n", ret); goto err_free_controls; } /* Free buf if success*/ kfree(buf); dev_info(s->dev, "Registered as %s\n", video_device_node_name(&s->vdev)); dev_notice(s->dev, "SDR API is still slightly experimental and functionality changes may follow\n"); return 0; err_free_controls: v4l2_ctrl_handler_free(&s->hdl); v4l2_device_unregister(&s->v4l2_dev); err_free_mem: kfree(buf); kfree(s->buf); kfree(s); return ret; } /* USB device ID list */ static const struct usb_device_id airspy_id_table[] = { { USB_DEVICE(0x1d50, 0x60a1) }, /* AirSpy */ { } }; MODULE_DEVICE_TABLE(usb, airspy_id_table); /* USB subsystem interface */ static struct usb_driver airspy_driver = { .name = KBUILD_MODNAME, .probe = airspy_probe, .disconnect = airspy_disconnect, .id_table = airspy_id_table, }; module_usb_driver(airspy_driver); MODULE_AUTHOR("Antti Palosaari <crope@iki.fi>"); MODULE_DESCRIPTION("AirSpy SDR"); MODULE_LICENSE("GPL"); |
| 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 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 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 | // SPDX-License-Identifier: GPL-2.0 // // Register map access API // // Copyright 2011 Wolfson Microelectronics plc // // Author: Mark Brown <broonie@opensource.wolfsonmicro.com> #include <linux/device.h> #include <linux/slab.h> #include <linux/export.h> #include <linux/mutex.h> #include <linux/err.h> #include <linux/property.h> #include <linux/rbtree.h> #include <linux/sched.h> #include <linux/delay.h> #include <linux/log2.h> #include <linux/hwspinlock.h> #include <linux/unaligned.h> #define CREATE_TRACE_POINTS #include "trace.h" #include "internal.h" /* * Sometimes for failures during very early init the trace * infrastructure isn't available early enough to be used. For this * sort of problem defining LOG_DEVICE will add printks for basic * register I/O on a specific device. */ #undef LOG_DEVICE #ifdef LOG_DEVICE static inline bool regmap_should_log(struct regmap *map) { return (map->dev && strcmp(dev_name(map->dev), LOG_DEVICE) == 0); } #else static inline bool regmap_should_log(struct regmap *map) { return false; } #endif static int _regmap_update_bits(struct regmap *map, unsigned int reg, unsigned int mask, unsigned int val, bool *change, bool force_write); static int _regmap_bus_reg_read(void *context, unsigned int reg, unsigned int *val); static int _regmap_bus_read(void *context, unsigned int reg, unsigned int *val); static int _regmap_bus_formatted_write(void *context, unsigned int reg, unsigned int val); static int _regmap_bus_reg_write(void *context, unsigned int reg, unsigned int val); static int _regmap_bus_raw_write(void *context, unsigned int reg, unsigned int val); bool regmap_reg_in_ranges(unsigned int reg, const struct regmap_range *ranges, unsigned int nranges) { const struct regmap_range *r; int i; for (i = 0, r = ranges; i < nranges; i++, r++) if (regmap_reg_in_range(reg, r)) return true; return false; } EXPORT_SYMBOL_GPL(regmap_reg_in_ranges); bool regmap_check_range_table(struct regmap *map, unsigned int reg, const struct regmap_access_table *table) { /* Check "no ranges" first */ if (regmap_reg_in_ranges(reg, table->no_ranges, table->n_no_ranges)) return false; /* In case zero "yes ranges" are supplied, any reg is OK */ if (!table->n_yes_ranges) return true; return regmap_reg_in_ranges(reg, table->yes_ranges, table->n_yes_ranges); } EXPORT_SYMBOL_GPL(regmap_check_range_table); bool regmap_writeable(struct regmap *map, unsigned int reg) { if (map->max_register_is_set && reg > map->max_register) return false; if (map->writeable_reg) return map->writeable_reg(map->dev, reg); if (map->wr_table) return regmap_check_range_table(map, reg, map->wr_table); return true; } bool regmap_cached(struct regmap *map, unsigned int reg) { int ret; unsigned int val; if (map->cache_type == REGCACHE_NONE) return false; if (!map->cache_ops) return false; if (map->max_register_is_set && reg > map->max_register) return false; map->lock(map->lock_arg); ret = regcache_read(map, reg, &val); map->unlock(map->lock_arg); if (ret) return false; return true; } bool regmap_readable(struct regmap *map, unsigned int reg) { if (!map->reg_read) return false; if (map->max_register_is_set && reg > map->max_register) return false; if (map->format.format_write) return false; if (map->readable_reg) return map->readable_reg(map->dev, reg); if (map->rd_table) return regmap_check_range_table(map, reg, map->rd_table); return true; } bool regmap_volatile(struct regmap *map, unsigned int reg) { if (!map->format.format_write && !regmap_readable(map, reg)) return false; if (map->volatile_reg) return map->volatile_reg(map->dev, reg); if (map->volatile_table) return regmap_check_range_table(map, reg, map->volatile_table); if (map->cache_ops) return false; else return true; } bool regmap_precious(struct regmap *map, unsigned int reg) { if (!regmap_readable(map, reg)) return false; if (map->precious_reg) return map->precious_reg(map->dev, reg); if (map->precious_table) return regmap_check_range_table(map, reg, map->precious_table); return false; } bool regmap_writeable_noinc(struct regmap *map, unsigned int reg) { if (map->writeable_noinc_reg) return map->writeable_noinc_reg(map->dev, reg); if (map->wr_noinc_table) return regmap_check_range_table(map, reg, map->wr_noinc_table); return true; } bool regmap_readable_noinc(struct regmap *map, unsigned int reg) { if (map->readable_noinc_reg) return map->readable_noinc_reg(map->dev, reg); if (map->rd_noinc_table) return regmap_check_range_table(map, reg, map->rd_noinc_table); return true; } static bool regmap_volatile_range(struct regmap *map, unsigned int reg, size_t num) { unsigned int i; for (i = 0; i < num; i++) if (!regmap_volatile(map, reg + regmap_get_offset(map, i))) return false; return true; } static void regmap_format_12_20_write(struct regmap *map, unsigned int reg, unsigned int val) { u8 *out = map->work_buf; out[0] = reg >> 4; out[1] = (reg << 4) | (val >> 16); out[2] = val >> 8; out[3] = val; } static void regmap_format_2_6_write(struct regmap *map, unsigned int reg, unsigned int val) { u8 *out = map->work_buf; *out = (reg << 6) | val; } static void regmap_format_4_12_write(struct regmap *map, unsigned int reg, unsigned int val) { __be16 *out = map->work_buf; *out = cpu_to_be16((reg << 12) | val); } static void regmap_format_7_9_write(struct regmap *map, unsigned int reg, unsigned int val) { __be16 *out = map->work_buf; *out = cpu_to_be16((reg << 9) | val); } static void regmap_format_7_17_write(struct regmap *map, unsigned int reg, unsigned int val) { u8 *out = map->work_buf; out[2] = val; out[1] = val >> 8; out[0] = (val >> 16) | (reg << 1); } static void regmap_format_10_14_write(struct regmap *map, unsigned int reg, unsigned int val) { u8 *out = map->work_buf; out[2] = val; out[1] = (val >> 8) | (reg << 6); out[0] = reg >> 2; } static void regmap_format_8(void *buf, unsigned int val, unsigned int shift) { u8 *b = buf; b[0] = val << shift; } static void regmap_format_16_be(void *buf, unsigned int val, unsigned int shift) { put_unaligned_be16(val << shift, buf); } static void regmap_format_16_le(void *buf, unsigned int val, unsigned int shift) { put_unaligned_le16(val << shift, buf); } static void regmap_format_16_native(void *buf, unsigned int val, unsigned int shift) { u16 v = val << shift; memcpy(buf, &v, sizeof(v)); } static void regmap_format_24_be(void *buf, unsigned int val, unsigned int shift) { put_unaligned_be24(val << shift, buf); } static void regmap_format_32_be(void *buf, unsigned int val, unsigned int shift) { put_unaligned_be32(val << shift, buf); } static void regmap_format_32_le(void *buf, unsigned int val, unsigned int shift) { put_unaligned_le32(val << shift, buf); } static void regmap_format_32_native(void *buf, unsigned int val, unsigned int shift) { u32 v = val << shift; memcpy(buf, &v, sizeof(v)); } static void regmap_parse_inplace_noop(void *buf) { } static unsigned int regmap_parse_8(const void *buf) { const u8 *b = buf; return b[0]; } static unsigned int regmap_parse_16_be(const void *buf) { return get_unaligned_be16(buf); } static unsigned int regmap_parse_16_le(const void *buf) { return get_unaligned_le16(buf); } static void regmap_parse_16_be_inplace(void *buf) { u16 v = get_unaligned_be16(buf); memcpy(buf, &v, sizeof(v)); } static void regmap_parse_16_le_inplace(void *buf) { u16 v = get_unaligned_le16(buf); memcpy(buf, &v, sizeof(v)); } static unsigned int regmap_parse_16_native(const void *buf) { u16 v; memcpy(&v, buf, sizeof(v)); return v; } static unsigned int regmap_parse_24_be(const void *buf) { return get_unaligned_be24(buf); } static unsigned int regmap_parse_32_be(const void *buf) { return get_unaligned_be32(buf); } static unsigned int regmap_parse_32_le(const void *buf) { return get_unaligned_le32(buf); } static void regmap_parse_32_be_inplace(void *buf) { u32 v = get_unaligned_be32(buf); memcpy(buf, &v, sizeof(v)); } static void regmap_parse_32_le_inplace(void *buf) { u32 v = get_unaligned_le32(buf); memcpy(buf, &v, sizeof(v)); } static unsigned int regmap_parse_32_native(const void *buf) { u32 v; memcpy(&v, buf, sizeof(v)); return v; } static void regmap_lock_hwlock(void *__map) { struct regmap *map = __map; hwspin_lock_timeout(map->hwlock, UINT_MAX); } static void regmap_lock_hwlock_irq(void *__map) { struct regmap *map = __map; hwspin_lock_timeout_irq(map->hwlock, UINT_MAX); } static void regmap_lock_hwlock_irqsave(void *__map) { struct regmap *map = __map; hwspin_lock_timeout_irqsave(map->hwlock, UINT_MAX, &map->spinlock_flags); } static void regmap_unlock_hwlock(void *__map) { struct regmap *map = __map; hwspin_unlock(map->hwlock); } static void regmap_unlock_hwlock_irq(void *__map) { struct regmap *map = __map; hwspin_unlock_irq(map->hwlock); } static void regmap_unlock_hwlock_irqrestore(void *__map) { struct regmap *map = __map; hwspin_unlock_irqrestore(map->hwlock, &map->spinlock_flags); } static void regmap_lock_unlock_none(void *__map) { } static void regmap_lock_mutex(void *__map) { struct regmap *map = __map; mutex_lock(&map->mutex); } static void regmap_unlock_mutex(void *__map) { struct regmap *map = __map; mutex_unlock(&map->mutex); } static void regmap_lock_spinlock(void *__map) __acquires(&map->spinlock) { struct regmap *map = __map; unsigned long flags; spin_lock_irqsave(&map->spinlock, flags); map->spinlock_flags = flags; } static void regmap_unlock_spinlock(void *__map) __releases(&map->spinlock) { struct regmap *map = __map; spin_unlock_irqrestore(&map->spinlock, map->spinlock_flags); } static void regmap_lock_raw_spinlock(void *__map) __acquires(&map->raw_spinlock) { struct regmap *map = __map; unsigned long flags; raw_spin_lock_irqsave(&map->raw_spinlock, flags); map->raw_spinlock_flags = flags; } static void regmap_unlock_raw_spinlock(void *__map) __releases(&map->raw_spinlock) { struct regmap *map = __map; raw_spin_unlock_irqrestore(&map->raw_spinlock, map->raw_spinlock_flags); } static void dev_get_regmap_release(struct device *dev, void *res) { /* * We don't actually have anything to do here; the goal here * is not to manage the regmap but to provide a simple way to * get the regmap back given a struct device. */ } static bool _regmap_range_add(struct regmap *map, struct regmap_range_node *data) { struct rb_root *root = &map->range_tree; struct rb_node **new = &(root->rb_node), *parent = NULL; while (*new) { struct regmap_range_node *this = rb_entry(*new, struct regmap_range_node, node); parent = *new; if (data->range_max < this->range_min) new = &((*new)->rb_left); else if (data->range_min > this->range_max) new = &((*new)->rb_right); else return false; } rb_link_node(&data->node, parent, new); rb_insert_color(&data->node, root); return true; } static struct regmap_range_node *_regmap_range_lookup(struct regmap *map, unsigned int reg) { struct rb_node *node = map->range_tree.rb_node; while (node) { struct regmap_range_node *this = rb_entry(node, struct regmap_range_node, node); if (reg < this->range_min) node = node->rb_left; else if (reg > this->range_max) node = node->rb_right; else return this; } return NULL; } static void regmap_range_exit(struct regmap *map) { struct rb_node *next; struct regmap_range_node *range_node; next = rb_first(&map->range_tree); while (next) { range_node = rb_entry(next, struct regmap_range_node, node); next = rb_next(&range_node->node); rb_erase(&range_node->node, &map->range_tree); kfree(range_node); } kfree(map->selector_work_buf); } static int regmap_set_name(struct regmap *map, const struct regmap_config *config) { if (config->name) { const char *name = kstrdup_const(config->name, GFP_KERNEL); if (!name) return -ENOMEM; kfree_const(map->name); map->name = name; } return 0; } int regmap_attach_dev(struct device *dev, struct regmap *map, const struct regmap_config *config) { struct regmap **m; int ret; map->dev = dev; ret = regmap_set_name(map, config); if (ret) return ret; regmap_debugfs_exit(map); regmap_debugfs_init(map); /* Add a devres resource for dev_get_regmap() */ m = devres_alloc(dev_get_regmap_release, sizeof(*m), GFP_KERNEL); if (!m) { regmap_debugfs_exit(map); return -ENOMEM; } *m = map; devres_add(dev, m); return 0; } EXPORT_SYMBOL_GPL(regmap_attach_dev); static int dev_get_regmap_match(struct device *dev, void *res, void *data); static int regmap_detach_dev(struct device *dev, struct regmap *map) { if (!dev) return 0; return devres_release(dev, dev_get_regmap_release, dev_get_regmap_match, (void *)map->name); } static enum regmap_endian regmap_get_reg_endian(const struct regmap_bus *bus, const struct regmap_config *config) { enum regmap_endian endian; /* Retrieve the endianness specification from the regmap config */ endian = config->reg_format_endian; /* If the regmap config specified a non-default value, use that */ if (endian != REGMAP_ENDIAN_DEFAULT) return endian; /* Retrieve the endianness specification from the bus config */ if (bus && bus->reg_format_endian_default) endian = bus->reg_format_endian_default; /* If the bus specified a non-default value, use that */ if (endian != REGMAP_ENDIAN_DEFAULT) return endian; /* Use this if no other value was found */ return REGMAP_ENDIAN_BIG; } enum regmap_endian regmap_get_val_endian(struct device *dev, const struct regmap_bus *bus, const struct regmap_config *config) { struct fwnode_handle *fwnode = dev ? dev_fwnode(dev) : NULL; enum regmap_endian endian; /* Retrieve the endianness specification from the regmap config */ endian = config->val_format_endian; /* If the regmap config specified a non-default value, use that */ if (endian != REGMAP_ENDIAN_DEFAULT) return endian; /* If the firmware node exist try to get endianness from it */ if (fwnode_property_read_bool(fwnode, "big-endian")) endian = REGMAP_ENDIAN_BIG; else if (fwnode_property_read_bool(fwnode, "little-endian")) endian = REGMAP_ENDIAN_LITTLE; else if (fwnode_property_read_bool(fwnode, "native-endian")) endian = REGMAP_ENDIAN_NATIVE; /* If the endianness was specified in fwnode, use that */ if (endian != REGMAP_ENDIAN_DEFAULT) return endian; /* Retrieve the endianness specification from the bus config */ if (bus && bus->val_format_endian_default) endian = bus->val_format_endian_default; /* If the bus specified a non-default value, use that */ if (endian != REGMAP_ENDIAN_DEFAULT) return endian; /* Use this if no other value was found */ return REGMAP_ENDIAN_BIG; } EXPORT_SYMBOL_GPL(regmap_get_val_endian); struct regmap *__regmap_init(struct device *dev, const struct regmap_bus *bus, void *bus_context, const struct regmap_config *config, struct lock_class_key *lock_key, const char *lock_name) { struct regmap *map; int ret = -EINVAL; enum regmap_endian reg_endian, val_endian; int i, j; if (!config) goto err; map = kzalloc(sizeof(*map), GFP_KERNEL); if (map == NULL) { ret = -ENOMEM; goto err; } ret = regmap_set_name(map, config); if (ret) goto err_map; ret = -EINVAL; /* Later error paths rely on this */ if (config->disable_locking) { map->lock = map->unlock = regmap_lock_unlock_none; map->can_sleep = config->can_sleep; regmap_debugfs_disable(map); } else if (config->lock && config->unlock) { map->lock = config->lock; map->unlock = config->unlock; map->lock_arg = config->lock_arg; map->can_sleep = config->can_sleep; } else if (config->use_hwlock) { map->hwlock = hwspin_lock_request_specific(config->hwlock_id); if (!map->hwlock) { ret = -ENXIO; goto err_name; } switch (config->hwlock_mode) { case HWLOCK_IRQSTATE: map->lock = regmap_lock_hwlock_irqsave; map->unlock = regmap_unlock_hwlock_irqrestore; break; case HWLOCK_IRQ: map->lock = regmap_lock_hwlock_irq; map->unlock = regmap_unlock_hwlock_irq; break; default: map->lock = regmap_lock_hwlock; map->unlock = regmap_unlock_hwlock; break; } map->lock_arg = map; } else { if ((bus && bus->fast_io) || config->fast_io) { if (config->use_raw_spinlock) { raw_spin_lock_init(&map->raw_spinlock); map->lock = regmap_lock_raw_spinlock; map->unlock = regmap_unlock_raw_spinlock; lockdep_set_class_and_name(&map->raw_spinlock, lock_key, lock_name); } else { spin_lock_init(&map->spinlock); map->lock = regmap_lock_spinlock; map->unlock = regmap_unlock_spinlock; lockdep_set_class_and_name(&map->spinlock, lock_key, lock_name); } } else { mutex_init(&map->mutex); map->lock = regmap_lock_mutex; map->unlock = regmap_unlock_mutex; map->can_sleep = true; lockdep_set_class_and_name(&map->mutex, lock_key, lock_name); } map->lock_arg = map; map->lock_key = lock_key; } /* * When we write in fast-paths with regmap_bulk_write() don't allocate * scratch buffers with sleeping allocations. */ if ((bus && bus->fast_io) || config->fast_io) map->alloc_flags = GFP_ATOMIC; else map->alloc_flags = GFP_KERNEL; map->reg_base = config->reg_base; map->reg_shift = config->pad_bits % 8; map->format.pad_bytes = config->pad_bits / 8; map->format.reg_shift = config->reg_shift; map->format.reg_bytes = BITS_TO_BYTES(config->reg_bits); map->format.val_bytes = BITS_TO_BYTES(config->val_bits); map->format.buf_size = BITS_TO_BYTES(config->reg_bits + config->val_bits + config->pad_bits); if (config->reg_stride) map->reg_stride = config->reg_stride; else map->reg_stride = 1; if (is_power_of_2(map->reg_stride)) map->reg_stride_order = ilog2(map->reg_stride); else map->reg_stride_order = -1; map->use_single_read = config->use_single_read || !(config->read || (bus && bus->read)); map->use_single_write = config->use_single_write || !(config->write || (bus && bus->write)); map->can_multi_write = config->can_multi_write && (config->write || (bus && bus->write)); if (bus) { map->max_raw_read = bus->max_raw_read; map->max_raw_write = bus->max_raw_write; } else if (config->max_raw_read && config->max_raw_write) { map->max_raw_read = config->max_raw_read; map->max_raw_write = config->max_raw_write; } map->dev = dev; map->bus = bus; map->bus_context = bus_context; map->max_register = config->max_register; map->max_register_is_set = map->max_register ?: config->max_register_is_0; map->wr_table = config->wr_table; map->rd_table = config->rd_table; map->volatile_table = config->volatile_table; map->precious_table = config->precious_table; map->wr_noinc_table = config->wr_noinc_table; map->rd_noinc_table = config->rd_noinc_table; map->writeable_reg = config->writeable_reg; map->readable_reg = config->readable_reg; map->volatile_reg = config->volatile_reg; map->precious_reg = config->precious_reg; map->writeable_noinc_reg = config->writeable_noinc_reg; map->readable_noinc_reg = config->readable_noinc_reg; map->cache_type = config->cache_type; spin_lock_init(&map->async_lock); INIT_LIST_HEAD(&map->async_list); INIT_LIST_HEAD(&map->async_free); init_waitqueue_head(&map->async_waitq); if (config->read_flag_mask || config->write_flag_mask || config->zero_flag_mask) { map->read_flag_mask = config->read_flag_mask; map->write_flag_mask = config->write_flag_mask; } else if (bus) { map->read_flag_mask = bus->read_flag_mask; } if (config && config->read && config->write) { map->reg_read = _regmap_bus_read; if (config->reg_update_bits) map->reg_update_bits = config->reg_update_bits; /* Bulk read/write */ map->read = config->read; map->write = config->write; reg_endian = REGMAP_ENDIAN_NATIVE; val_endian = REGMAP_ENDIAN_NATIVE; } else if (!bus) { map->reg_read = config->reg_read; map->reg_write = config->reg_write; map->reg_update_bits = config->reg_update_bits; map->defer_caching = false; goto skip_format_initialization; } else if (!bus->read || !bus->write) { map->reg_read = _regmap_bus_reg_read; map->reg_write = _regmap_bus_reg_write; map->reg_update_bits = bus->reg_update_bits; map->defer_caching = false; goto skip_format_initialization; } else { map->reg_read = _regmap_bus_read; map->reg_update_bits = bus->reg_update_bits; /* Bulk read/write */ map->read = bus->read; map->write = bus->write; reg_endian = regmap_get_reg_endian(bus, config); val_endian = regmap_get_val_endian(dev, bus, config); } switch (config->reg_bits + map->reg_shift) { case 2: switch (config->val_bits) { case 6: map->format.format_write = regmap_format_2_6_write; break; default: goto err_hwlock; } break; case 4: switch (config->val_bits) { case 12: map->format.format_write = regmap_format_4_12_write; break; default: goto err_hwlock; } break; case 7: switch (config->val_bits) { case 9: map->format.format_write = regmap_format_7_9_write; break; case 17: map->format.format_write = regmap_format_7_17_write; break; default: goto err_hwlock; } break; case 10: switch (config->val_bits) { case 14: map->format.format_write = regmap_format_10_14_write; break; default: goto err_hwlock; } break; case 12: switch (config->val_bits) { case 20: map->format.format_write = regmap_format_12_20_write; break; default: goto err_hwlock; } break; case 8: map->format.format_reg = regmap_format_8; break; case 16: switch (reg_endian) { case REGMAP_ENDIAN_BIG: map->format.format_reg = regmap_format_16_be; break; case REGMAP_ENDIAN_LITTLE: map->format.format_reg = regmap_format_16_le; break; case REGMAP_ENDIAN_NATIVE: map->format.format_reg = regmap_format_16_native; break; default: goto err_hwlock; } break; case 24: switch (reg_endian) { case REGMAP_ENDIAN_BIG: map->format.format_reg = regmap_format_24_be; break; default: goto err_hwlock; } break; case 32: switch (reg_endian) { case REGMAP_ENDIAN_BIG: map->format.format_reg = regmap_format_32_be; break; case REGMAP_ENDIAN_LITTLE: map->format.format_reg = regmap_format_32_le; break; case REGMAP_ENDIAN_NATIVE: map->format.format_reg = regmap_format_32_native; break; default: goto err_hwlock; } break; default: goto err_hwlock; } if (val_endian == REGMAP_ENDIAN_NATIVE) map->format.parse_inplace = regmap_parse_inplace_noop; switch (config->val_bits) { case 8: map->format.format_val = regmap_format_8; map->format.parse_val = regmap_parse_8; map->format.parse_inplace = regmap_parse_inplace_noop; break; case 16: switch (val_endian) { case REGMAP_ENDIAN_BIG: map->format.format_val = regmap_format_16_be; map->format.parse_val = regmap_parse_16_be; map->format.parse_inplace = regmap_parse_16_be_inplace; break; case REGMAP_ENDIAN_LITTLE: map->format.format_val = regmap_format_16_le; map->format.parse_val = regmap_parse_16_le; map->format.parse_inplace = regmap_parse_16_le_inplace; break; case REGMAP_ENDIAN_NATIVE: map->format.format_val = regmap_format_16_native; map->format.parse_val = regmap_parse_16_native; break; default: goto err_hwlock; } break; case 24: switch (val_endian) { case REGMAP_ENDIAN_BIG: map->format.format_val = regmap_format_24_be; map->format.parse_val = regmap_parse_24_be; break; default: goto err_hwlock; } break; case 32: switch (val_endian) { case REGMAP_ENDIAN_BIG: map->format.format_val = regmap_format_32_be; map->format.parse_val = regmap_parse_32_be; map->format.parse_inplace = regmap_parse_32_be_inplace; break; case REGMAP_ENDIAN_LITTLE: map->format.format_val = regmap_format_32_le; map->format.parse_val = regmap_parse_32_le; map->format.parse_inplace = regmap_parse_32_le_inplace; break; case REGMAP_ENDIAN_NATIVE: map->format.format_val = regmap_format_32_native; map->format.parse_val = regmap_parse_32_native; break; default: goto err_hwlock; } break; } if (map->format.format_write) { if ((reg_endian != REGMAP_ENDIAN_BIG) || (val_endian != REGMAP_ENDIAN_BIG)) goto err_hwlock; map->use_single_write = true; } if (!map->format.format_write && !(map->format.format_reg && map->format.format_val)) goto err_hwlock; map->work_buf = kzalloc(map->format.buf_size, GFP_KERNEL); if (map->work_buf == NULL) { ret = -ENOMEM; goto err_hwlock; } if (map->format.format_write) { map->defer_caching = false; map->reg_write = _regmap_bus_formatted_write; } else if (map->format.format_val) { map->defer_caching = true; map->reg_write = _regmap_bus_raw_write; } skip_format_initialization: map->range_tree = RB_ROOT; for (i = 0; i < config->num_ranges; i++) { const struct regmap_range_cfg *range_cfg = &config->ranges[i]; struct regmap_range_node *new; /* Sanity check */ if (range_cfg->range_max < range_cfg->range_min) { dev_err(map->dev, "Invalid range %d: %u < %u\n", i, range_cfg->range_max, range_cfg->range_min); goto err_range; } if (range_cfg->range_max > map->max_register) { dev_err(map->dev, "Invalid range %d: %u > %u\n", i, range_cfg->range_max, map->max_register); goto err_range; } if (range_cfg->selector_reg > map->max_register) { dev_err(map->dev, "Invalid range %d: selector out of map\n", i); goto err_range; } if (range_cfg->window_len == 0) { dev_err(map->dev, "Invalid range %d: window_len 0\n", i); goto err_range; } /* Make sure, that this register range has no selector or data window within its boundary */ for (j = 0; j < config->num_ranges; j++) { unsigned int sel_reg = config->ranges[j].selector_reg; unsigned int win_min = config->ranges[j].window_start; unsigned int win_max = win_min + config->ranges[j].window_len - 1; /* Allow data window inside its own virtual range */ if (j == i) continue; if (range_cfg->range_min <= sel_reg && sel_reg <= range_cfg->range_max) { dev_err(map->dev, "Range %d: selector for %d in window\n", i, j); goto err_range; } if (!(win_max < range_cfg->range_min || win_min > range_cfg->range_max)) { dev_err(map->dev, "Range %d: window for %d in window\n", i, j); goto err_range; } } new = kzalloc(sizeof(*new), GFP_KERNEL); if (new == NULL) { ret = -ENOMEM; goto err_range; } new->map = map; new->name = range_cfg->name; new->range_min = range_cfg->range_min; new->range_max = range_cfg->range_max; new->selector_reg = range_cfg->selector_reg; new->selector_mask = range_cfg->selector_mask; new->selector_shift = range_cfg->selector_shift; new->window_start = range_cfg->window_start; new->window_len = range_cfg->window_len; if (!_regmap_range_add(map, new)) { dev_err(map->dev, "Failed to add range %d\n", i); kfree(new); goto err_range; } if (map->selector_work_buf == NULL) { map->selector_work_buf = kzalloc(map->format.buf_size, GFP_KERNEL); if (map->selector_work_buf == NULL) { ret = -ENOMEM; goto err_range; } } } ret = regcache_init(map, config); if (ret != 0) goto err_range; if (dev) { ret = regmap_attach_dev(dev, map, config); if (ret != 0) goto err_regcache; } else { regmap_debugfs_init(map); } return map; err_regcache: regcache_exit(map); err_range: regmap_range_exit(map); kfree(map->work_buf); err_hwlock: if (map->hwlock) hwspin_lock_free(map->hwlock); err_name: kfree_const(map->name); err_map: kfree(map); err: if (bus && bus->free_on_exit) kfree(bus); return ERR_PTR(ret); } EXPORT_SYMBOL_GPL(__regmap_init); static void devm_regmap_release(struct device *dev, void *res) { regmap_exit(*(struct regmap **)res); } struct regmap *__devm_regmap_init(struct device *dev, const struct regmap_bus *bus, void *bus_context, const struct regmap_config *config, struct lock_class_key *lock_key, const char *lock_name) { struct regmap **ptr, *regmap; ptr = devres_alloc(devm_regmap_release, sizeof(*ptr), GFP_KERNEL); if (!ptr) return ERR_PTR(-ENOMEM); regmap = __regmap_init(dev, bus, bus_context, config, lock_key, lock_name); if (!IS_ERR(regmap)) { *ptr = regmap; devres_add(dev, ptr); } else { devres_free(ptr); } return regmap; } EXPORT_SYMBOL_GPL(__devm_regmap_init); static void regmap_field_init(struct regmap_field *rm_field, struct regmap *regmap, struct reg_field reg_field) { rm_field->regmap = regmap; rm_field->reg = reg_field.reg; rm_field->shift = reg_field.lsb; rm_field->mask = GENMASK(reg_field.msb, reg_field.lsb); WARN_ONCE(rm_field->mask == 0, "invalid empty mask defined\n"); rm_field->id_size = reg_field.id_size; rm_field->id_offset = reg_field.id_offset; } /** * devm_regmap_field_alloc() - Allocate and initialise a register field. * * @dev: Device that will be interacted with * @regmap: regmap bank in which this register field is located. * @reg_field: Register field with in the bank. * * The return value will be an ERR_PTR() on error or a valid pointer * to a struct regmap_field. The regmap_field will be automatically freed * by the device management code. */ struct regmap_field *devm_regmap_field_alloc(struct device *dev, struct regmap *regmap, struct reg_field reg_field) { struct regmap_field *rm_field = devm_kzalloc(dev, sizeof(*rm_field), GFP_KERNEL); if (!rm_field) return ERR_PTR(-ENOMEM); regmap_field_init(rm_field, regmap, reg_field); return rm_field; } EXPORT_SYMBOL_GPL(devm_regmap_field_alloc); /** * regmap_field_bulk_alloc() - Allocate and initialise a bulk register field. * * @regmap: regmap bank in which this register field is located. * @rm_field: regmap register fields within the bank. * @reg_field: Register fields within the bank. * @num_fields: Number of register fields. * * The return value will be an -ENOMEM on error or zero for success. * Newly allocated regmap_fields should be freed by calling * regmap_field_bulk_free() */ int regmap_field_bulk_alloc(struct regmap *regmap, struct regmap_field **rm_field, const struct reg_field *reg_field, int num_fields) { struct regmap_field *rf; int i; rf = kcalloc(num_fields, sizeof(*rf), GFP_KERNEL); if (!rf) return -ENOMEM; for (i = 0; i < num_fields; i++) { regmap_field_init(&rf[i], regmap, reg_field[i]); rm_field[i] = &rf[i]; } return 0; } EXPORT_SYMBOL_GPL(regmap_field_bulk_alloc); /** * devm_regmap_field_bulk_alloc() - Allocate and initialise a bulk register * fields. * * @dev: Device that will be interacted with * @regmap: regmap bank in which this register field is located. * @rm_field: regmap register fields within the bank. * @reg_field: Register fields within the bank. * @num_fields: Number of register fields. * * The return value will be an -ENOMEM on error or zero for success. * Newly allocated regmap_fields will be automatically freed by the * device management code. */ int devm_regmap_field_bulk_alloc(struct device *dev, struct regmap *regmap, struct regmap_field **rm_field, const struct reg_field *reg_field, int num_fields) { struct regmap_field *rf; int i; rf = devm_kcalloc(dev, num_fields, sizeof(*rf), GFP_KERNEL); if (!rf) return -ENOMEM; for (i = 0; i < num_fields; i++) { regmap_field_init(&rf[i], regmap, reg_field[i]); rm_field[i] = &rf[i]; } return 0; } EXPORT_SYMBOL_GPL(devm_regmap_field_bulk_alloc); /** * regmap_field_bulk_free() - Free register field allocated using * regmap_field_bulk_alloc. * * @field: regmap fields which should be freed. */ void regmap_field_bulk_free(struct regmap_field *field) { kfree(field); } EXPORT_SYMBOL_GPL(regmap_field_bulk_free); /** * devm_regmap_field_bulk_free() - Free a bulk register field allocated using * devm_regmap_field_bulk_alloc. * * @dev: Device that will be interacted with * @field: regmap field which should be freed. * * Free register field allocated using devm_regmap_field_bulk_alloc(). Usually * drivers need not call this function, as the memory allocated via devm * will be freed as per device-driver life-cycle. */ void devm_regmap_field_bulk_free(struct device *dev, struct regmap_field *field) { devm_kfree(dev, field); } EXPORT_SYMBOL_GPL(devm_regmap_field_bulk_free); /** * devm_regmap_field_free() - Free a register field allocated using * devm_regmap_field_alloc. * * @dev: Device that will be interacted with * @field: regmap field which should be freed. * * Free register field allocated using devm_regmap_field_alloc(). Usually * drivers need not call this function, as the memory allocated via devm * will be freed as per device-driver life-cyle. */ void devm_regmap_field_free(struct device *dev, struct regmap_field *field) { devm_kfree(dev, field); } EXPORT_SYMBOL_GPL(devm_regmap_field_free); /** * regmap_field_alloc() - Allocate and initialise a register field. * * @regmap: regmap bank in which this register field is located. * @reg_field: Register field with in the bank. * * The return value will be an ERR_PTR() on error or a valid pointer * to a struct regmap_field. The regmap_field should be freed by the * user once its finished working with it using regmap_field_free(). */ struct regmap_field *regmap_field_alloc(struct regmap *regmap, struct reg_field reg_field) { struct regmap_field *rm_field = kzalloc(sizeof(*rm_field), GFP_KERNEL); if (!rm_field) return ERR_PTR(-ENOMEM); regmap_field_init(rm_field, regmap, reg_field); return rm_field; } EXPORT_SYMBOL_GPL(regmap_field_alloc); /** * regmap_field_free() - Free register field allocated using * regmap_field_alloc. * * @field: regmap field which should be freed. */ void regmap_field_free(struct regmap_field *field) { kfree(field); } EXPORT_SYMBOL_GPL(regmap_field_free); /** * regmap_reinit_cache() - Reinitialise the current register cache * * @map: Register map to operate on. * @config: New configuration. Only the cache data will be used. * * Discard any existing register cache for the map and initialize a * new cache. This can be used to restore the cache to defaults or to * update the cache configuration to reflect runtime discovery of the * hardware. * * No explicit locking is done here, the user needs to ensure that * this function will not race with other calls to regmap. */ int regmap_reinit_cache(struct regmap *map, const struct regmap_config *config) { int ret; regcache_exit(map); regmap_debugfs_exit(map); map->max_register = config->max_register; map->max_register_is_set = map->max_register ?: config->max_register_is_0; map->writeable_reg = config->writeable_reg; map->readable_reg = config->readable_reg; map->volatile_reg = config->volatile_reg; map->precious_reg = config->precious_reg; map->writeable_noinc_reg = config->writeable_noinc_reg; map->readable_noinc_reg = config->readable_noinc_reg; map->cache_type = config->cache_type; ret = regmap_set_name(map, config); if (ret) return ret; regmap_debugfs_init(map); map->cache_bypass = false; map->cache_only = false; return regcache_init(map, config); } EXPORT_SYMBOL_GPL(regmap_reinit_cache); /** * regmap_exit() - Free a previously allocated register map * * @map: Register map to operate on. */ void regmap_exit(struct regmap *map) { struct regmap_async *async; regmap_detach_dev(map->dev, map); regcache_exit(map); regmap_debugfs_exit(map); regmap_range_exit(map); if (map->bus && map->bus->free_context) map->bus->free_context(map->bus_context); kfree(map->work_buf); while (!list_empty(&map->async_free)) { async = list_first_entry_or_null(&map->async_free, struct regmap_async, list); list_del(&async->list); kfree(async->work_buf); kfree(async); } if (map->hwlock) hwspin_lock_free(map->hwlock); if (map->lock == regmap_lock_mutex) mutex_destroy(&map->mutex); kfree_const(map->name); kfree(map->patch); if (map->bus && map->bus->free_on_exit) kfree(map->bus); kfree(map); } EXPORT_SYMBOL_GPL(regmap_exit); static int dev_get_regmap_match(struct device *dev, void *res, void *data) { struct regmap **r = res; if (!r || !*r) { WARN_ON(!r || !*r); return 0; } /* If the user didn't specify a name match any */ if (data) return (*r)->name && !strcmp((*r)->name, data); else return 1; } /** * dev_get_regmap() - Obtain the regmap (if any) for a device * * @dev: Device to retrieve the map for * @name: Optional name for the register map, usually NULL. * * Returns the regmap for the device if one is present, or NULL. If * name is specified then it must match the name specified when * registering the device, if it is NULL then the first regmap found * will be used. Devices with multiple register maps are very rare, * generic code should normally not need to specify a name. */ struct regmap *dev_get_regmap(struct device *dev, const char *name) { struct regmap **r = devres_find(dev, dev_get_regmap_release, dev_get_regmap_match, (void *)name); if (!r) return NULL; return *r; } EXPORT_SYMBOL_GPL(dev_get_regmap); /** * regmap_get_device() - Obtain the device from a regmap * * @map: Register map to operate on. * * Returns the underlying device that the regmap has been created for. */ struct device *regmap_get_device(struct regmap *map) { return map->dev; } EXPORT_SYMBOL_GPL(regmap_get_device); static int _regmap_select_page(struct regmap *map, unsigned int *reg, struct regmap_range_node *range, unsigned int val_num) { void *orig_work_buf; unsigned int win_offset; unsigned int win_page; bool page_chg; int ret; win_offset = (*reg - range->range_min) % range->window_len; win_page = (*reg - range->range_min) / range->window_len; if (val_num > 1) { /* Bulk write shouldn't cross range boundary */ if (*reg + val_num - 1 > range->range_max) return -EINVAL; /* ... or single page boundary */ if (val_num > range->window_len - win_offset) return -EINVAL; } /* It is possible to have selector register inside data window. In that case, selector register is located on every page and it needs no page switching, when accessed alone. */ if (val_num > 1 || range->window_start + win_offset != range->selector_reg) { /* Use separate work_buf during page switching */ orig_work_buf = map->work_buf; map->work_buf = map->selector_work_buf; ret = _regmap_update_bits(map, range->selector_reg, range->selector_mask, win_page << range->selector_shift, &page_chg, false); map->work_buf = orig_work_buf; if (ret != 0) return ret; } *reg = range->window_start + win_offset; return 0; } static void regmap_set_work_buf_flag_mask(struct regmap *map, int max_bytes, unsigned long mask) { u8 *buf; int i; if (!mask || !map->work_buf) return; buf = map->work_buf; for (i = 0; i < max_bytes; i++) buf[i] |= (mask >> (8 * i)) & 0xff; } static unsigned int regmap_reg_addr(struct regmap *map, unsigned int reg) { reg += map->reg_base; if (map->format.reg_shift > 0) reg >>= map->format.reg_shift; else if (map->format.reg_shift < 0) reg <<= -(map->format.reg_shift); return reg; } static int _regmap_raw_write_impl(struct regmap *map, unsigned int reg, const void *val, size_t val_len, bool noinc) { struct regmap_range_node *range; unsigned long flags; void *work_val = map->work_buf + map->format.reg_bytes + map->format.pad_bytes; void *buf; int ret = -ENOTSUPP; size_t len; int i; /* Check for unwritable or noinc registers in range * before we start */ if (!regmap_writeable_noinc(map, reg)) { for (i = 0; i < val_len / map->format.val_bytes; i++) { unsigned int element = reg + regmap_get_offset(map, i); if (!regmap_writeable(map, element) || regmap_writeable_noinc(map, element)) return -EINVAL; } } if (!map->cache_bypass && map->format.parse_val) { unsigned int ival, offset; int val_bytes = map->format.val_bytes; /* Cache the last written value for noinc writes */ i = noinc ? val_len - val_bytes : 0; for (; i < val_len; i += val_bytes) { ival = map->format.parse_val(val + i); offset = noinc ? 0 : regmap_get_offset(map, i / val_bytes); ret = regcache_write(map, reg + offset, ival); if (ret) { dev_err(map->dev, "Error in caching of register: %x ret: %d\n", reg + offset, ret); return ret; } } if (map->cache_only) { map->cache_dirty = true; return 0; } } range = _regmap_range_lookup(map, reg); if (range) { int val_num = val_len / map->format.val_bytes; int win_offset = (reg - range->range_min) % range->window_len; int win_residue = range->window_len - win_offset; /* If the write goes beyond the end of the window split it */ while (val_num > win_residue) { dev_dbg(map->dev, "Writing window %d/%zu\n", win_residue, val_len / map->format.val_bytes); ret = _regmap_raw_write_impl(map, reg, val, win_residue * map->format.val_bytes, noinc); if (ret != 0) return ret; reg += win_residue; val_num -= win_residue; val += win_residue * map->format.val_bytes; val_len -= win_residue * map->format.val_bytes; win_offset = (reg - range->range_min) % range->window_len; win_residue = range->window_len - win_offset; } ret = _regmap_select_page(map, ®, range, noinc ? 1 : val_num); if (ret != 0) return ret; } reg = regmap_reg_addr(map, reg); map->format.format_reg(map->work_buf, reg, map->reg_shift); regmap_set_work_buf_flag_mask(map, map->format.reg_bytes, map->write_flag_mask); /* * Essentially all I/O mechanisms will be faster with a single * buffer to write. Since register syncs often generate raw * writes of single registers optimise that case. */ if (val != work_val && val_len == map->format.val_bytes) { memcpy(work_val, val, map->format.val_bytes); val = work_val; } if (map->async && map->bus && map->bus->async_write) { struct regmap_async *async; trace_regmap_async_write_start(map, reg, val_len); spin_lock_irqsave(&map->async_lock, flags); async = list_first_entry_or_null(&map->async_free, struct regmap_async, list); if (async) list_del(&async->list); spin_unlock_irqrestore(&map->async_lock, flags); if (!async) { async = map->bus->async_alloc(); if (!async) return -ENOMEM; async->work_buf = kzalloc(map->format.buf_size, GFP_KERNEL | GFP_DMA); if (!async->work_buf) { kfree(async); return -ENOMEM; } } async->map = map; /* If the caller supplied the value we can use it safely. */ memcpy(async->work_buf, map->work_buf, map->format.pad_bytes + map->format.reg_bytes + map->format.val_bytes); spin_lock_irqsave(&map->async_lock, flags); list_add_tail(&async->list, &map->async_list); spin_unlock_irqrestore(&map->async_lock, flags); if (val != work_val) ret = map->bus->async_write(map->bus_context, async->work_buf, map->format.reg_bytes + map->format.pad_bytes, val, val_len, async); else ret = map->bus->async_write(map->bus_context, async->work_buf, map->format.reg_bytes + map->format.pad_bytes + val_len, NULL, 0, async); if (ret != 0) { dev_err(map->dev, "Failed to schedule write: %d\n", ret); spin_lock_irqsave(&map->async_lock, flags); list_move(&async->list, &map->async_free); spin_unlock_irqrestore(&map->async_lock, flags); } return ret; } trace_regmap_hw_write_start(map, reg, val_len / map->format.val_bytes); /* If we're doing a single register write we can probably just * send the work_buf directly, otherwise try to do a gather * write. */ if (val == work_val) ret = map->write(map->bus_context, map->work_buf, map->format.reg_bytes + map->format.pad_bytes + val_len); else if (map->bus && map->bus->gather_write) ret = map->bus->gather_write(map->bus_context, map->work_buf, map->format.reg_bytes + map->format.pad_bytes, val, val_len); else ret = -ENOTSUPP; /* If that didn't work fall back on linearising by hand. */ if (ret == -ENOTSUPP) { len = map->format.reg_bytes + map->format.pad_bytes + val_len; buf = kzalloc(len, GFP_KERNEL); if (!buf) return -ENOMEM; memcpy(buf, map->work_buf, map->format.reg_bytes); memcpy(buf + map->format.reg_bytes + map->format.pad_bytes, val, val_len); ret = map->write(map->bus_context, buf, len); kfree(buf); } else if (ret != 0 && !map->cache_bypass && map->format.parse_val) { /* regcache_drop_region() takes lock that we already have, * thus call map->cache_ops->drop() directly */ if (map->cache_ops && map->cache_ops->drop) map->cache_ops->drop(map, reg, reg + 1); } trace_regmap_hw_write_done(map, reg, val_len / map->format.val_bytes); return ret; } /** * regmap_can_raw_write - Test if regmap_raw_write() is supported * * @map: Map to check. */ bool regmap_can_raw_write(struct regmap *map) { return map->write && map->format.format_val && map->format.format_reg; } EXPORT_SYMBOL_GPL(regmap_can_raw_write); /** * regmap_get_raw_read_max - Get the maximum size we can read * * @map: Map to check. */ size_t regmap_get_raw_read_max(struct regmap *map) { return map->max_raw_read; } EXPORT_SYMBOL_GPL(regmap_get_raw_read_max); /** * regmap_get_raw_write_max - Get the maximum size we can read * * @map: Map to check. */ size_t regmap_get_raw_write_max(struct regmap *map) { return map->max_raw_write; } EXPORT_SYMBOL_GPL(regmap_get_raw_write_max); static int _regmap_bus_formatted_write(void *context, unsigned int reg, unsigned int val) { int ret; struct regmap_range_node *range; struct regmap *map = context; WARN_ON(!map->format.format_write); range = _regmap_range_lookup(map, reg); if (range) { ret = _regmap_select_page(map, ®, range, 1); if (ret != 0) return ret; } reg = regmap_reg_addr(map, reg); map->format.format_write(map, reg, val); trace_regmap_hw_write_start(map, reg, 1); ret = map->write(map->bus_context, map->work_buf, map->format.buf_size); trace_regmap_hw_write_done(map, reg, 1); return ret; } static int _regmap_bus_reg_write(void *context, unsigned int reg, unsigned int val) { struct regmap *map = context; struct regmap_range_node *range; int ret; range = _regmap_range_lookup(map, reg); if (range) { ret = _regmap_select_page(map, ®, range, 1); if (ret != 0) return ret; } reg = regmap_reg_addr(map, reg); return map->bus->reg_write(map->bus_context, reg, val); } static int _regmap_bus_raw_write(void *context, unsigned int reg, unsigned int val) { struct regmap *map = context; WARN_ON(!map->format.format_val); map->format.format_val(map->work_buf + map->format.reg_bytes + map->format.pad_bytes, val, 0); return _regmap_raw_write_impl(map, reg, map->work_buf + map->format.reg_bytes + map->format.pad_bytes, map->format.val_bytes, false); } static inline void *_regmap_map_get_context(struct regmap *map) { return (map->bus || (!map->bus && map->read)) ? map : map->bus_context; } int _regmap_write(struct regmap *map, unsigned int reg, unsigned int val) { int ret; void *context = _regmap_map_get_context(map); if (!regmap_writeable(map, reg)) return -EIO; if (!map->cache_bypass && !map->defer_caching) { ret = regcache_write(map, reg, val); if (ret != 0) return ret; if (map->cache_only) { map->cache_dirty = true; return 0; } } ret = map->reg_write(context, reg, val); if (ret == 0) { if (regmap_should_log(map)) dev_info(map->dev, "%x <= %x\n", reg, val); trace_regmap_reg_write(map, reg, val); } return ret; } /** * regmap_write() - Write a value to a single register * * @map: Register map to write to * @reg: Register to write to * @val: Value to be written * * A value of zero will be returned on success, a negative errno will * be returned in error cases. */ int regmap_write(struct regmap *map, unsigned int reg, unsigned int val) { int ret; if (!IS_ALIGNED(reg, map->reg_stride)) return -EINVAL; map->lock(map->lock_arg); ret = _regmap_write(map, reg, val); map->unlock(map->lock_arg); return ret; } EXPORT_SYMBOL_GPL(regmap_write); /** * regmap_write_async() - Write a value to a single register asynchronously * * @map: Register map to write to * @reg: Register to write to * @val: Value to be written * * A value of zero will be returned on success, a negative errno will * be returned in error cases. */ int regmap_write_async(struct regmap *map, unsigned int reg, unsigned int val) { int ret; if (!IS_ALIGNED(reg, map->reg_stride)) return -EINVAL; map->lock(map->lock_arg); map->async = true; ret = _regmap_write(map, reg, val); map->async = false; map->unlock(map->lock_arg); return ret; } EXPORT_SYMBOL_GPL(regmap_write_async); int _regmap_raw_write(struct regmap *map, unsigned int reg, const void *val, size_t val_len, bool noinc) { size_t val_bytes = map->format.val_bytes; size_t val_count = val_len / val_bytes; size_t chunk_count, chunk_bytes; size_t chunk_regs = val_count; int ret, i; if (!val_count) return -EINVAL; if (map->use_single_write) chunk_regs = 1; else if (map->max_raw_write && val_len > map->max_raw_write) chunk_regs = map->max_raw_write / val_bytes; chunk_count = val_count / chunk_regs; chunk_bytes = chunk_regs * val_bytes; /* Write as many bytes as possible with chunk_size */ for (i = 0; i < chunk_count; i++) { ret = _regmap_raw_write_impl(map, reg, val, chunk_bytes, noinc); if (ret) return ret; reg += regmap_get_offset(map, chunk_regs); val += chunk_bytes; val_len -= chunk_bytes; } /* Write remaining bytes */ if (val_len) ret = _regmap_raw_write_impl(map, reg, val, val_len, noinc); return ret; } /** * regmap_raw_write() - Write raw values to one or more registers * * @map: Register map to write to * @reg: Initial register to write to * @val: Block of data to be written, laid out for direct transmission to the * device * @val_len: Length of data pointed to by val. * * This function is intended to be used for things like firmware * download where a large block of data needs to be transferred to the * device. No formatting will be done on the data provided. * * A value of zero will be returned on success, a negative errno will * be returned in error cases. */ int regmap_raw_write(struct regmap *map, unsigned int reg, const void *val, size_t val_len) { int ret; if (!regmap_can_raw_write(map)) return -EINVAL; if (val_len % map->format.val_bytes) return -EINVAL; map->lock(map->lock_arg); ret = _regmap_raw_write(map, reg, val, val_len, false); map->unlock(map->lock_arg); return ret; } EXPORT_SYMBOL_GPL(regmap_raw_write); static int regmap_noinc_readwrite(struct regmap *map, unsigned int reg, void *val, unsigned int val_len, bool write) { size_t val_bytes = map->format.val_bytes; size_t val_count = val_len / val_bytes; unsigned int lastval; u8 *u8p; u16 *u16p; u32 *u32p; int ret; int i; switch (val_bytes) { case 1: u8p = val; if (write) lastval = (unsigned int)u8p[val_count - 1]; break; case 2: u16p = val; if (write) lastval = (unsigned int)u16p[val_count - 1]; break; case 4: u32p = val; if (write) lastval = (unsigned int)u32p[val_count - 1]; break; default: return -EINVAL; } /* * Update the cache with the last value we write, the rest is just * gone down in the hardware FIFO. We can't cache FIFOs. This makes * sure a single read from the cache will work. */ if (write) { if (!map->cache_bypass && !map->defer_caching) { ret = regcache_write(map, reg, lastval); if (ret != 0) return ret; if (map->cache_only) { map->cache_dirty = true; return 0; } } ret = map->bus->reg_noinc_write(map->bus_context, reg, val, val_count); } else { ret = map->bus->reg_noinc_read(map->bus_context, reg, val, val_count); } if (!ret && regmap_should_log(map)) { dev_info(map->dev, "%x %s [", reg, write ? "<=" : "=>"); for (i = 0; i < val_count; i++) { switch (val_bytes) { case 1: pr_cont("%x", u8p[i]); break; case 2: pr_cont("%x", u16p[i]); break; case 4: pr_cont("%x", u32p[i]); break; default: break; } if (i == (val_count - 1)) pr_cont("]\n"); else pr_cont(","); } } return 0; } /** * regmap_noinc_write(): Write data to a register without incrementing the * register number * * @map: Register map to write to * @reg: Register to write to * @val: Pointer to data buffer * @val_len: Length of output buffer in bytes. * * The regmap API usually assumes that bulk bus write operations will write a * range of registers. Some devices have certain registers for which a write * operation can write to an internal FIFO. * * The target register must be volatile but registers after it can be * completely unrelated cacheable registers. * * This will attempt multiple writes as required to write val_len bytes. * * A value of zero will be returned on success, a negative errno will be * returned in error cases. */ int regmap_noinc_write(struct regmap *map, unsigned int reg, const void *val, size_t val_len) { size_t write_len; int ret; if (!map->write && !(map->bus && map->bus->reg_noinc_write)) return -EINVAL; if (val_len % map->format.val_bytes) return -EINVAL; if (!IS_ALIGNED(reg, map->reg_stride)) return -EINVAL; if (val_len == 0) return -EINVAL; map->lock(map->lock_arg); if (!regmap_volatile(map, reg) || !regmap_writeable_noinc(map, reg)) { ret = -EINVAL; goto out_unlock; } /* * Use the accelerated operation if we can. The val drops the const * typing in order to facilitate code reuse in regmap_noinc_readwrite(). */ if (map->bus->reg_noinc_write) { ret = regmap_noinc_readwrite(map, reg, (void *)val, val_len, true); goto out_unlock; } while (val_len) { if (map->max_raw_write && map->max_raw_write < val_len) write_len = map->max_raw_write; else write_len = val_len; ret = _regmap_raw_write(map, reg, val, write_len, true); if (ret) goto out_unlock; val = ((u8 *)val) + write_len; val_len -= write_len; } out_unlock: map->unlock(map->lock_arg); return ret; } EXPORT_SYMBOL_GPL(regmap_noinc_write); /** * regmap_field_update_bits_base() - Perform a read/modify/write cycle a * register field. * * @field: Register field to write to * @mask: Bitmask to change * @val: Value to be written * @change: Boolean indicating if a write was done * @async: Boolean indicating asynchronously * @force: Boolean indicating use force update * * Perform a read/modify/write cycle on the register field with change, * async, force option. * * A value of zero will be returned on success, a negative errno will * be returned in error cases. */ int regmap_field_update_bits_base(struct regmap_field *field, unsigned int mask, unsigned int val, bool *change, bool async, bool force) { mask = (mask << field->shift) & field->mask; return regmap_update_bits_base(field->regmap, field->reg, mask, val << field->shift, change, async, force); } EXPORT_SYMBOL_GPL(regmap_field_update_bits_base); /** * regmap_field_test_bits() - Check if all specified bits are set in a * register field. * * @field: Register field to operate on * @bits: Bits to test * * Returns -1 if the underlying regmap_field_read() fails, 0 if at least one of the * tested bits is not set and 1 if all tested bits are set. */ int regmap_field_test_bits(struct regmap_field *field, unsigned int bits) { unsigned int val, ret; ret = regmap_field_read(field, &val); if (ret) return ret; return (val & bits) == bits; } EXPORT_SYMBOL_GPL(regmap_field_test_bits); /** * regmap_fields_update_bits_base() - Perform a read/modify/write cycle a * register field with port ID * * @field: Register field to write to * @id: port ID * @mask: Bitmask to change * @val: Value to be written * @change: Boolean indicating if a write was done * @async: Boolean indicating asynchronously * @force: Boolean indicating use force update * * A value of zero will be returned on success, a negative errno will * be returned in error cases. */ int regmap_fields_update_bits_base(struct regmap_field *field, unsigned int id, unsigned int mask, unsigned int val, bool *change, bool async, bool force) { if (id >= field->id_size) return -EINVAL; mask = (mask << field->shift) & field->mask; return regmap_update_bits_base(field->regmap, field->reg + (field->id_offset * id), mask, val << field->shift, change, async, force); } EXPORT_SYMBOL_GPL(regmap_fields_update_bits_base); /** * regmap_bulk_write() - Write multiple registers to the device * * @map: Register map to write to * @reg: First register to be write from * @val: Block of data to be written, in native register size for device * @val_count: Number of registers to write * * This function is intended to be used for writing a large block of * data to the device either in single transfer or multiple transfer. * * A value of zero will be returned on success, a negative errno will * be returned in error cases. */ int regmap_bulk_write(struct regmap *map, unsigned int reg, const void *val, size_t val_count) { int ret = 0, i; size_t val_bytes = map->format.val_bytes; if (!IS_ALIGNED(reg, map->reg_stride)) return -EINVAL; /* * Some devices don't support bulk write, for them we have a series of * single write operations. */ if (!map->write || !map->format.parse_inplace) { map->lock(map->lock_arg); for (i = 0; i < val_count; i++) { unsigned int ival; switch (val_bytes) { case 1: ival = *(u8 *)(val + (i * val_bytes)); break; case 2: ival = *(u16 *)(val + (i * val_bytes)); break; case 4: ival = *(u32 *)(val + (i * val_bytes)); break; default: ret = -EINVAL; goto out; } ret = _regmap_write(map, reg + regmap_get_offset(map, i), ival); if (ret != 0) goto out; } out: map->unlock(map->lock_arg); } else { void *wval; wval = kmemdup_array(val, val_count, val_bytes, map->alloc_flags); if (!wval) return -ENOMEM; for (i = 0; i < val_count * val_bytes; i += val_bytes) map->format.parse_inplace(wval + i); ret = regmap_raw_write(map, reg, wval, val_bytes * val_count); kfree(wval); } if (!ret) trace_regmap_bulk_write(map, reg, val, val_bytes * val_count); return ret; } EXPORT_SYMBOL_GPL(regmap_bulk_write); /* * _regmap_raw_multi_reg_write() * * the (register,newvalue) pairs in regs have not been formatted, but * they are all in the same page and have been changed to being page * relative. The page register has been written if that was necessary. */ static int _regmap_raw_multi_reg_write(struct regmap *map, const struct reg_sequence *regs, size_t num_regs) { int ret; void *buf; int i; u8 *u8; size_t val_bytes = map->format.val_bytes; size_t reg_bytes = map->format.reg_bytes; size_t pad_bytes = map->format.pad_bytes; size_t pair_size = reg_bytes + pad_bytes + val_bytes; size_t len = pair_size * num_regs; if (!len) return -EINVAL; buf = kzalloc(len, GFP_KERNEL); if (!buf) return -ENOMEM; /* We have to linearise by hand. */ u8 = buf; for (i = 0; i < num_regs; i++) { unsigned int reg = regs[i].reg; unsigned int val = regs[i].def; trace_regmap_hw_write_start(map, reg, 1); reg = regmap_reg_addr(map, reg); map->format.format_reg(u8, reg, map->reg_shift); u8 += reg_bytes + pad_bytes; map->format.format_val(u8, val, 0); u8 += val_bytes; } u8 = buf; *u8 |= map->write_flag_mask; ret = map->write(map->bus_context, buf, len); kfree(buf); for (i = 0; i < num_regs; i++) { int reg = regs[i].reg; trace_regmap_hw_write_done(map, reg, 1); } return ret; } static unsigned int _regmap_register_page(struct regmap *map, unsigned int reg, struct regmap_range_node *range) { unsigned int win_page = (reg - range->range_min) / range->window_len; return win_page; } static int _regmap_range_multi_paged_reg_write(struct regmap *map, struct reg_sequence *regs, size_t num_regs) { int ret; int i, n; struct reg_sequence *base; unsigned int this_page = 0; unsigned int page_change = 0; /* * the set of registers are not neccessarily in order, but * since the order of write must be preserved this algorithm * chops the set each time the page changes. This also applies * if there is a delay required at any point in the sequence. */ base = regs; for (i = 0, n = 0; i < num_regs; i++, n++) { unsigned int reg = regs[i].reg; struct regmap_range_node *range; range = _regmap_range_lookup(map, reg); if (range) { unsigned int win_page = _regmap_register_page(map, reg, range); if (i == 0) this_page = win_page; if (win_page != this_page) { this_page = win_page; page_change = 1; } } /* If we have both a page change and a delay make sure to * write the regs and apply the delay before we change the * page. */ if (page_change || regs[i].delay_us) { /* For situations where the first write requires * a delay we need to make sure we don't call * raw_multi_reg_write with n=0 * This can't occur with page breaks as we * never write on the first iteration */ if (regs[i].delay_us && i == 0) n = 1; ret = _regmap_raw_multi_reg_write(map, base, n); if (ret != 0) return ret; if (regs[i].delay_us) { if (map->can_sleep) fsleep(regs[i].delay_us); else udelay(regs[i].delay_us); } base += n; n = 0; if (page_change) { ret = _regmap_select_page(map, &base[n].reg, range, 1); if (ret != 0) return ret; page_change = 0; } } } if (n > 0) return _regmap_raw_multi_reg_write(map, base, n); return 0; } static int _regmap_multi_reg_write(struct regmap *map, const struct reg_sequence *regs, size_t num_regs) { int i; int ret; if (!map->can_multi_write) { for (i = 0; i < num_regs; i++) { ret = _regmap_write(map, regs[i].reg, regs[i].def); if (ret != 0) return ret; if (regs[i].delay_us) { if (map->can_sleep) fsleep(regs[i].delay_us); else udelay(regs[i].delay_us); } } return 0; } if (!map->format.parse_inplace) return -EINVAL; if (map->writeable_reg) for (i = 0; i < num_regs; i++) { int reg = regs[i].reg; if (!map->writeable_reg(map->dev, reg)) return -EINVAL; if (!IS_ALIGNED(reg, map->reg_stride)) return -EINVAL; } if (!map->cache_bypass) { for (i = 0; i < num_regs; i++) { unsigned int val = regs[i].def; unsigned int reg = regs[i].reg; ret = regcache_write(map, reg, val); if (ret) { dev_err(map->dev, "Error in caching of register: %x ret: %d\n", reg, ret); return ret; } } if (map->cache_only) { map->cache_dirty = true; return 0; } } WARN_ON(!map->bus); for (i = 0; i < num_regs; i++) { unsigned int reg = regs[i].reg; struct regmap_range_node *range; /* Coalesce all the writes between a page break or a delay * in a sequence */ range = _regmap_range_lookup(map, reg); if (range || regs[i].delay_us) { size_t len = sizeof(struct reg_sequence)*num_regs; struct reg_sequence *base = kmemdup(regs, len, GFP_KERNEL); if (!base) return -ENOMEM; ret = _regmap_range_multi_paged_reg_write(map, base, num_regs); kfree(base); return ret; } } return _regmap_raw_multi_reg_write(map, regs, num_regs); } /** * regmap_multi_reg_write() - Write multiple registers to the device * * @map: Register map to write to * @regs: Array of structures containing register,value to be written * @num_regs: Number of registers to write * * Write multiple registers to the device where the set of register, value * pairs are supplied in any order, possibly not all in a single range. * * The 'normal' block write mode will send ultimately send data on the * target bus as R,V1,V2,V3,..,Vn where successively higher registers are * addressed. However, this alternative block multi write mode will send * the data as R1,V1,R2,V2,..,Rn,Vn on the target bus. The target device * must of course support the mode. * * A value of zero will be returned on success, a negative errno will be * returned in error cases. */ int regmap_multi_reg_write(struct regmap *map, const struct reg_sequence *regs, int num_regs) { int ret; map->lock(map->lock_arg); ret = _regmap_multi_reg_write(map, regs, num_regs); map->unlock(map->lock_arg); return ret; } EXPORT_SYMBOL_GPL(regmap_multi_reg_write); /** * regmap_multi_reg_write_bypassed() - Write multiple registers to the * device but not the cache * * @map: Register map to write to * @regs: Array of structures containing register,value to be written * @num_regs: Number of registers to write * * Write multiple registers to the device but not the cache where the set * of register are supplied in any order. * * This function is intended to be used for writing a large block of data * atomically to the device in single transfer for those I2C client devices * that implement this alternative block write mode. * * A value of zero will be returned on success, a negative errno will * be returned in error cases. */ int regmap_multi_reg_write_bypassed(struct regmap *map, const struct reg_sequence *regs, int num_regs) { int ret; bool bypass; map->lock(map->lock_arg); bypass = map->cache_bypass; map->cache_bypass = true; ret = _regmap_multi_reg_write(map, regs, num_regs); map->cache_bypass = bypass; map->unlock(map->lock_arg); return ret; } EXPORT_SYMBOL_GPL(regmap_multi_reg_write_bypassed); /** * regmap_raw_write_async() - Write raw values to one or more registers * asynchronously * * @map: Register map to write to * @reg: Initial register to write to * @val: Block of data to be written, laid out for direct transmission to the * device. Must be valid until regmap_async_complete() is called. * @val_len: Length of data pointed to by val. * * This function is intended to be used for things like firmware * download where a large block of data needs to be transferred to the * device. No formatting will be done on the data provided. * * If supported by the underlying bus the write will be scheduled * asynchronously, helping maximise I/O speed on higher speed buses * like SPI. regmap_async_complete() can be called to ensure that all * asynchrnous writes have been completed. * * A value of zero will be returned on success, a negative errno will * be returned in error cases. */ int regmap_raw_write_async(struct regmap *map, unsigned int reg, const void *val, size_t val_len) { int ret; if (val_len % map->format.val_bytes) return -EINVAL; if (!IS_ALIGNED(reg, map->reg_stride)) return -EINVAL; map->lock(map->lock_arg); map->async = true; ret = _regmap_raw_write(map, reg, val, val_len, false); map->async = false; map->unlock(map->lock_arg); return ret; } EXPORT_SYMBOL_GPL(regmap_raw_write_async); static int _regmap_raw_read(struct regmap *map, unsigned int reg, void *val, unsigned int val_len, bool noinc) { struct regmap_range_node *range; int ret; if (!map->read) return -EINVAL; range = _regmap_range_lookup(map, reg); if (range) { ret = _regmap_select_page(map, ®, range, noinc ? 1 : val_len / map->format.val_bytes); if (ret != 0) return ret; } reg = regmap_reg_addr(map, reg); map->format.format_reg(map->work_buf, reg, map->reg_shift); regmap_set_work_buf_flag_mask(map, map->format.reg_bytes, map->read_flag_mask); trace_regmap_hw_read_start(map, reg, val_len / map->format.val_bytes); ret = map->read(map->bus_context, map->work_buf, map->format.reg_bytes + map->format.pad_bytes, val, val_len); trace_regmap_hw_read_done(map, reg, val_len / map->format.val_bytes); return ret; } static int _regmap_bus_reg_read(void *context, unsigned int reg, unsigned int *val) { struct regmap *map = context; struct regmap_range_node *range; int ret; range = _regmap_range_lookup(map, reg); if (range) { ret = _regmap_select_page(map, ®, range, 1); if (ret != 0) return ret; } reg = regmap_reg_addr(map, reg); return map->bus->reg_read(map->bus_context, reg, val); } static int _regmap_bus_read(void *context, unsigned int reg, unsigned int *val) { int ret; struct regmap *map = context; void *work_val = map->work_buf + map->format.reg_bytes + map->format.pad_bytes; if (!map->format.parse_val) return -EINVAL; ret = _regmap_raw_read(map, reg, work_val, map->format.val_bytes, false); if (ret == 0) *val = map->format.parse_val(work_val); return ret; } static int _regmap_read(struct regmap *map, unsigned int reg, unsigned int *val) { int ret; void *context = _regmap_map_get_context(map); if (!map->cache_bypass) { ret = regcache_read(map, reg, val); if (ret == 0) return 0; } if (map->cache_only) return -EBUSY; if (!regmap_readable(map, reg)) return -EIO; ret = map->reg_read(context, reg, val); if (ret == 0) { if (regmap_should_log(map)) dev_info(map->dev, "%x => %x\n", reg, *val); trace_regmap_reg_read(map, reg, *val); if (!map->cache_bypass) regcache_write(map, reg, *val); } return ret; } /** * regmap_read() - Read a value from a single register * * @map: Register map to read from * @reg: Register to be read from * @val: Pointer to store read value * * A value of zero will be returned on success, a negative errno will * be returned in error cases. */ int regmap_read(struct regmap *map, unsigned int reg, unsigned int *val) { int ret; if (!IS_ALIGNED(reg, map->reg_stride)) return -EINVAL; map->lock(map->lock_arg); ret = _regmap_read(map, reg, val); map->unlock(map->lock_arg); return ret; } EXPORT_SYMBOL_GPL(regmap_read); /** * regmap_read_bypassed() - Read a value from a single register direct * from the device, bypassing the cache * * @map: Register map to read from * @reg: Register to be read from * @val: Pointer to store read value * * A value of zero will be returned on success, a negative errno will * be returned in error cases. */ int regmap_read_bypassed(struct regmap *map, unsigned int reg, unsigned int *val) { int ret; bool bypass, cache_only; if (!IS_ALIGNED(reg, map->reg_stride)) return -EINVAL; map->lock(map->lock_arg); bypass = map->cache_bypass; cache_only = map->cache_only; map->cache_bypass = true; map->cache_only = false; ret = _regmap_read(map, reg, val); map->cache_bypass = bypass; map->cache_only = cache_only; map->unlock(map->lock_arg); return ret; } EXPORT_SYMBOL_GPL(regmap_read_bypassed); /** * regmap_raw_read() - Read raw data from the device * * @map: Register map to read from * @reg: First register to be read from * @val: Pointer to store read value * @val_len: Size of data to read * * A value of zero will be returned on success, a negative errno will * be returned in error cases. */ int regmap_raw_read(struct regmap *map, unsigned int reg, void *val, size_t val_len) { size_t val_bytes = map->format.val_bytes; size_t val_count = val_len / val_bytes; unsigned int v; int ret, i; if (val_len % map->format.val_bytes) return -EINVAL; if (!IS_ALIGNED(reg, map->reg_stride)) return -EINVAL; if (val_count == 0) return -EINVAL; map->lock(map->lock_arg); if (regmap_volatile_range(map, reg, val_count) || map->cache_bypass || map->cache_type == REGCACHE_NONE) { size_t chunk_count, chunk_bytes; size_t chunk_regs = val_count; if (!map->cache_bypass && map->cache_only) { ret = -EBUSY; goto out; } if (!map->read) { ret = -ENOTSUPP; goto out; } if (map->use_single_read) chunk_regs = 1; else if (map->max_raw_read && val_len > map->max_raw_read) chunk_regs = map->max_raw_read / val_bytes; chunk_count = val_count / chunk_regs; chunk_bytes = chunk_regs * val_bytes; /* Read bytes that fit into whole chunks */ for (i = 0; i < chunk_count; i++) { ret = _regmap_raw_read(map, reg, val, chunk_bytes, false); if (ret != 0) goto out; reg += regmap_get_offset(map, chunk_regs); val += chunk_bytes; val_len -= chunk_bytes; } /* Read remaining bytes */ if (val_len) { ret = _regmap_raw_read(map, reg, val, val_len, false); if (ret != 0) goto out; } } else { /* Otherwise go word by word for the cache; should be low * cost as we expect to hit the cache. */ for (i = 0; i < val_count; i++) { ret = _regmap_read(map, reg + regmap_get_offset(map, i), &v); if (ret != 0) goto out; map->format.format_val(val + (i * val_bytes), v, 0); } } out: map->unlock(map->lock_arg); return ret; } EXPORT_SYMBOL_GPL(regmap_raw_read); /** * regmap_noinc_read(): Read data from a register without incrementing the * register number * * @map: Register map to read from * @reg: Register to read from * @val: Pointer to data buffer * @val_len: Length of output buffer in bytes. * * The regmap API usually assumes that bulk read operations will read a * range of registers. Some devices have certain registers for which a read * operation read will read from an internal FIFO. * * The target register must be volatile but registers after it can be * completely unrelated cacheable registers. * * This will attempt multiple reads as required to read val_len bytes. * * A value of zero will be returned on success, a negative errno will be * returned in error cases. */ int regmap_noinc_read(struct regmap *map, unsigned int reg, void *val, size_t val_len) { size_t read_len; int ret; if (!map->read) return -ENOTSUPP; if (val_len % map->format.val_bytes) return -EINVAL; if (!IS_ALIGNED(reg, map->reg_stride)) return -EINVAL; if (val_len == 0) return -EINVAL; map->lock(map->lock_arg); if (!regmap_volatile(map, reg) || !regmap_readable_noinc(map, reg)) { ret = -EINVAL; goto out_unlock; } /* * We have not defined the FIFO semantics for cache, as the * cache is just one value deep. Should we return the last * written value? Just avoid this by always reading the FIFO * even when using cache. Cache only will not work. */ if (!map->cache_bypass && map->cache_only) { ret = -EBUSY; goto out_unlock; } /* Use the accelerated operation if we can */ if (map->bus->reg_noinc_read) { ret = regmap_noinc_readwrite(map, reg, val, val_len, false); goto out_unlock; } while (val_len) { if (map->max_raw_read && map->max_raw_read < val_len) read_len = map->max_raw_read; else read_len = val_len; ret = _regmap_raw_read(map, reg, val, read_len, true); if (ret) goto out_unlock; val = ((u8 *)val) + read_len; val_len -= read_len; } out_unlock: map->unlock(map->lock_arg); return ret; } EXPORT_SYMBOL_GPL(regmap_noinc_read); /** * regmap_field_read(): Read a value to a single register field * * @field: Register field to read from * @val: Pointer to store read value * * A value of zero will be returned on success, a negative errno will * be returned in error cases. */ int regmap_field_read(struct regmap_field *field, unsigned int *val) { int ret; unsigned int reg_val; ret = regmap_read(field->regmap, field->reg, ®_val); if (ret != 0) return ret; reg_val &= field->mask; reg_val >>= field->shift; *val = reg_val; return ret; } EXPORT_SYMBOL_GPL(regmap_field_read); /** * regmap_fields_read() - Read a value to a single register field with port ID * * @field: Register field to read from * @id: port ID * @val: Pointer to store read value * * A value of zero will be returned on success, a negative errno will * be returned in error cases. */ int regmap_fields_read(struct regmap_field *field, unsigned int id, unsigned int *val) { int ret; unsigned int reg_val; if (id >= field->id_size) return -EINVAL; ret = regmap_read(field->regmap, field->reg + (field->id_offset * id), ®_val); if (ret != 0) return ret; reg_val &= field->mask; reg_val >>= field->shift; *val = reg_val; return ret; } EXPORT_SYMBOL_GPL(regmap_fields_read); static int _regmap_bulk_read(struct regmap *map, unsigned int reg, const unsigned int *regs, void *val, size_t val_count) { u32 *u32 = val; u16 *u16 = val; u8 *u8 = val; int ret, i; map->lock(map->lock_arg); for (i = 0; i < val_count; i++) { unsigned int ival; if (regs) { if (!IS_ALIGNED(regs[i], map->reg_stride)) { ret = -EINVAL; goto out; } ret = _regmap_read(map, regs[i], &ival); } else { ret = _regmap_read(map, reg + regmap_get_offset(map, i), &ival); } if (ret != 0) goto out; switch (map->format.val_bytes) { case 4: u32[i] = ival; break; case 2: u16[i] = ival; break; case 1: u8[i] = ival; break; default: ret = -EINVAL; goto out; } } out: map->unlock(map->lock_arg); return ret; } /** * regmap_bulk_read() - Read multiple sequential registers from the device * * @map: Register map to read from * @reg: First register to be read from * @val: Pointer to store read value, in native register size for device * @val_count: Number of registers to read * * A value of zero will be returned on success, a negative errno will * be returned in error cases. */ int regmap_bulk_read(struct regmap *map, unsigned int reg, void *val, size_t val_count) { int ret, i; size_t val_bytes = map->format.val_bytes; bool vol = regmap_volatile_range(map, reg, val_count); if (!IS_ALIGNED(reg, map->reg_stride)) return -EINVAL; if (val_count == 0) return -EINVAL; if (map->read && map->format.parse_inplace && (vol || map->cache_type == REGCACHE_NONE)) { ret = regmap_raw_read(map, reg, val, val_bytes * val_count); if (ret != 0) return ret; for (i = 0; i < val_count * val_bytes; i += val_bytes) map->format.parse_inplace(val + i); } else { ret = _regmap_bulk_read(map, reg, NULL, val, val_count); } if (!ret) trace_regmap_bulk_read(map, reg, val, val_bytes * val_count); return ret; } EXPORT_SYMBOL_GPL(regmap_bulk_read); /** * regmap_multi_reg_read() - Read multiple non-sequential registers from the device * * @map: Register map to read from * @regs: Array of registers to read from * @val: Pointer to store read value, in native register size for device * @val_count: Number of registers to read * * A value of zero will be returned on success, a negative errno will * be returned in error cases. */ int regmap_multi_reg_read(struct regmap *map, const unsigned int *regs, void *val, size_t val_count) { if (val_count == 0) return -EINVAL; return _regmap_bulk_read(map, 0, regs, val, val_count); } EXPORT_SYMBOL_GPL(regmap_multi_reg_read); static int _regmap_update_bits(struct regmap *map, unsigned int reg, unsigned int mask, unsigned int val, bool *change, bool force_write) { int ret; unsigned int tmp, orig; if (change) *change = false; if (regmap_volatile(map, reg) && map->reg_update_bits) { reg = regmap_reg_addr(map, reg); ret = map->reg_update_bits(map->bus_context, reg, mask, val); if (ret == 0 && change) *change = true; } else { ret = _regmap_read(map, reg, &orig); if (ret != 0) return ret; tmp = orig & ~mask; tmp |= val & mask; if (force_write || (tmp != orig) || map->force_write_field) { ret = _regmap_write(map, reg, tmp); if (ret == 0 && change) *change = true; } } return ret; } /** * regmap_update_bits_base() - Perform a read/modify/write cycle on a register * * @map: Register map to update * @reg: Register to update * @mask: Bitmask to change * @val: New value for bitmask * @change: Boolean indicating if a write was done * @async: Boolean indicating asynchronously * @force: Boolean indicating use force update * * Perform a read/modify/write cycle on a register map with change, async, force * options. * * If async is true: * * With most buses the read must be done synchronously so this is most useful * for devices with a cache which do not need to interact with the hardware to * determine the current register value. * * Returns zero for success, a negative number on error. */ int regmap_update_bits_base(struct regmap *map, unsigned int reg, unsigned int mask, unsigned int val, bool *change, bool async, bool force) { int ret; map->lock(map->lock_arg); map->async = async; ret = _regmap_update_bits(map, reg, mask, val, change, force); map->async = false; map->unlock(map->lock_arg); return ret; } EXPORT_SYMBOL_GPL(regmap_update_bits_base); /** * regmap_test_bits() - Check if all specified bits are set in a register. * * @map: Register map to operate on * @reg: Register to read from * @bits: Bits to test * * Returns 0 if at least one of the tested bits is not set, 1 if all tested * bits are set and a negative error number if the underlying regmap_read() * fails. */ int regmap_test_bits(struct regmap *map, unsigned int reg, unsigned int bits) { unsigned int val, ret; ret = regmap_read(map, reg, &val); if (ret) return ret; return (val & bits) == bits; } EXPORT_SYMBOL_GPL(regmap_test_bits); void regmap_async_complete_cb(struct regmap_async *async, int ret) { struct regmap *map = async->map; bool wake; trace_regmap_async_io_complete(map); spin_lock(&map->async_lock); list_move(&async->list, &map->async_free); wake = list_empty(&map->async_list); if (ret != 0) map->async_ret = ret; spin_unlock(&map->async_lock); if (wake) wake_up(&map->async_waitq); } EXPORT_SYMBOL_GPL(regmap_async_complete_cb); static int regmap_async_is_done(struct regmap *map) { unsigned long flags; int ret; spin_lock_irqsave(&map->async_lock, flags); ret = list_empty(&map->async_list); spin_unlock_irqrestore(&map->async_lock, flags); return ret; } /** * regmap_async_complete - Ensure all asynchronous I/O has completed. * * @map: Map to operate on. * * Blocks until any pending asynchronous I/O has completed. Returns * an error code for any failed I/O operations. */ int regmap_async_complete(struct regmap *map) { unsigned long flags; int ret; /* Nothing to do with no async support */ if (!map->bus || !map->bus->async_write) return 0; trace_regmap_async_complete_start(map); wait_event(map->async_waitq, regmap_async_is_done(map)); spin_lock_irqsave(&map->async_lock, flags); ret = map->async_ret; map->async_ret = 0; spin_unlock_irqrestore(&map->async_lock, flags); trace_regmap_async_complete_done(map); return ret; } EXPORT_SYMBOL_GPL(regmap_async_complete); /** * regmap_register_patch - Register and apply register updates to be applied * on device initialistion * * @map: Register map to apply updates to. * @regs: Values to update. * @num_regs: Number of entries in regs. * * Register a set of register updates to be applied to the device * whenever the device registers are synchronised with the cache and * apply them immediately. Typically this is used to apply * corrections to be applied to the device defaults on startup, such * as the updates some vendors provide to undocumented registers. * * The caller must ensure that this function cannot be called * concurrently with either itself or regcache_sync(). */ int regmap_register_patch(struct regmap *map, const struct reg_sequence *regs, int num_regs) { struct reg_sequence *p; int ret; bool bypass; if (WARN_ONCE(num_regs <= 0, "invalid registers number (%d)\n", num_regs)) return 0; p = krealloc(map->patch, sizeof(struct reg_sequence) * (map->patch_regs + num_regs), GFP_KERNEL); if (p) { memcpy(p + map->patch_regs, regs, num_regs * sizeof(*regs)); map->patch = p; map->patch_regs += num_regs; } else { return -ENOMEM; } map->lock(map->lock_arg); bypass = map->cache_bypass; map->cache_bypass = true; map->async = true; ret = _regmap_multi_reg_write(map, regs, num_regs); map->async = false; map->cache_bypass = bypass; map->unlock(map->lock_arg); regmap_async_complete(map); return ret; } EXPORT_SYMBOL_GPL(regmap_register_patch); /** * regmap_get_val_bytes() - Report the size of a register value * * @map: Register map to operate on. * * Report the size of a register value, mainly intended to for use by * generic infrastructure built on top of regmap. */ int regmap_get_val_bytes(struct regmap *map) { if (map->format.format_write) return -EINVAL; return map->format.val_bytes; } EXPORT_SYMBOL_GPL(regmap_get_val_bytes); /** * regmap_get_max_register() - Report the max register value * * @map: Register map to operate on. * * Report the max register value, mainly intended to for use by * generic infrastructure built on top of regmap. */ int regmap_get_max_register(struct regmap *map) { return map->max_register_is_set ? map->max_register : -EINVAL; } EXPORT_SYMBOL_GPL(regmap_get_max_register); /** * regmap_get_reg_stride() - Report the register address stride * * @map: Register map to operate on. * * Report the register address stride, mainly intended to for use by * generic infrastructure built on top of regmap. */ int regmap_get_reg_stride(struct regmap *map) { return map->reg_stride; } EXPORT_SYMBOL_GPL(regmap_get_reg_stride); /** * regmap_might_sleep() - Returns whether a regmap access might sleep. * * @map: Register map to operate on. * * Returns true if an access to the register might sleep, else false. */ bool regmap_might_sleep(struct regmap *map) { return map->can_sleep; } EXPORT_SYMBOL_GPL(regmap_might_sleep); int regmap_parse_val(struct regmap *map, const void *buf, unsigned int *val) { if (!map->format.parse_val) return -EINVAL; *val = map->format.parse_val(buf); return 0; } EXPORT_SYMBOL_GPL(regmap_parse_val); static int __init regmap_initcall(void) { regmap_debugfs_initcall(); return 0; } postcore_initcall(regmap_initcall); |
| 60 | 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: GPL-2.0 */ #ifndef _NF_SYNPROXY_SHARED_H #define _NF_SYNPROXY_SHARED_H #include <linux/module.h> #include <linux/skbuff.h> #include <net/ip6_checksum.h> #include <net/ip6_route.h> #include <net/tcp.h> #include <net/netfilter/nf_conntrack_seqadj.h> #include <net/netfilter/nf_conntrack_synproxy.h> struct synproxy_stats { unsigned int syn_received; unsigned int cookie_invalid; unsigned int cookie_valid; unsigned int cookie_retrans; unsigned int conn_reopened; }; struct synproxy_net { struct nf_conn *tmpl; struct synproxy_stats __percpu *stats; unsigned int hook_ref4; unsigned int hook_ref6; }; extern unsigned int synproxy_net_id; static inline struct synproxy_net *synproxy_pernet(struct net *net) { return net_generic(net, synproxy_net_id); } struct synproxy_options { u8 options; u8 wscale; u16 mss_option; u16 mss_encode; u32 tsval; u32 tsecr; }; struct nf_synproxy_info; bool synproxy_parse_options(const struct sk_buff *skb, unsigned int doff, const struct tcphdr *th, struct synproxy_options *opts); void synproxy_init_timestamp_cookie(const struct nf_synproxy_info *info, struct synproxy_options *opts); void synproxy_send_client_synack(struct net *net, const struct sk_buff *skb, const struct tcphdr *th, const struct synproxy_options *opts); bool synproxy_recv_client_ack(struct net *net, const struct sk_buff *skb, const struct tcphdr *th, struct synproxy_options *opts, u32 recv_seq); struct nf_hook_state; unsigned int ipv4_synproxy_hook(void *priv, struct sk_buff *skb, const struct nf_hook_state *nhs); int nf_synproxy_ipv4_init(struct synproxy_net *snet, struct net *net); void nf_synproxy_ipv4_fini(struct synproxy_net *snet, struct net *net); #if IS_ENABLED(CONFIG_IPV6) void synproxy_send_client_synack_ipv6(struct net *net, const struct sk_buff *skb, const struct tcphdr *th, const struct synproxy_options *opts); bool synproxy_recv_client_ack_ipv6(struct net *net, const struct sk_buff *skb, const struct tcphdr *th, struct synproxy_options *opts, u32 recv_seq); unsigned int ipv6_synproxy_hook(void *priv, struct sk_buff *skb, const struct nf_hook_state *nhs); int nf_synproxy_ipv6_init(struct synproxy_net *snet, struct net *net); void nf_synproxy_ipv6_fini(struct synproxy_net *snet, struct net *net); #else static inline int nf_synproxy_ipv6_init(struct synproxy_net *snet, struct net *net) { return 0; } static inline void nf_synproxy_ipv6_fini(struct synproxy_net *snet, struct net *net) {}; #endif /* CONFIG_IPV6 */ #endif /* _NF_SYNPROXY_SHARED_H */ |
| 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 | // SPDX-License-Identifier: GPL-2.0 #include <linux/ceph/ceph_debug.h> #include <linux/device.h> #include <linux/slab.h> #include <linux/module.h> #include <linux/ctype.h> #include <linux/debugfs.h> #include <linux/seq_file.h> #include <linux/ceph/libceph.h> #include <linux/ceph/mon_client.h> #include <linux/ceph/auth.h> #include <linux/ceph/debugfs.h> #ifdef CONFIG_DEBUG_FS /* * Implement /sys/kernel/debug/ceph fun * * /sys/kernel/debug/ceph/client* - an instance of the ceph client * .../osdmap - current osdmap * .../monmap - current monmap * .../osdc - active osd requests * .../monc - mon client state * .../client_options - libceph-only (i.e. not rbd or cephfs) options * .../dentry_lru - dump contents of dentry lru * .../caps - expose cap (reservation) stats * .../bdi - symlink to ../../bdi/something */ static struct dentry *ceph_debugfs_dir; static int monmap_show(struct seq_file *s, void *p) { int i; struct ceph_client *client = s->private; if (client->monc.monmap == NULL) return 0; seq_printf(s, "epoch %d\n", client->monc.monmap->epoch); for (i = 0; i < client->monc.monmap->num_mon; i++) { struct ceph_entity_inst *inst = &client->monc.monmap->mon_inst[i]; seq_printf(s, "\t%s%lld\t%s\n", ENTITY_NAME(inst->name), ceph_pr_addr(&inst->addr)); } return 0; } static int osdmap_show(struct seq_file *s, void *p) { int i; struct ceph_client *client = s->private; struct ceph_osd_client *osdc = &client->osdc; struct ceph_osdmap *map = osdc->osdmap; struct rb_node *n; if (map == NULL) return 0; down_read(&osdc->lock); seq_printf(s, "epoch %u barrier %u flags 0x%x\n", map->epoch, osdc->epoch_barrier, map->flags); for (n = rb_first(&map->pg_pools); n; n = rb_next(n)) { struct ceph_pg_pool_info *pi = rb_entry(n, struct ceph_pg_pool_info, node); seq_printf(s, "pool %lld '%s' type %d size %d min_size %d pg_num %u pg_num_mask %d flags 0x%llx lfor %u read_tier %lld write_tier %lld\n", pi->id, pi->name, pi->type, pi->size, pi->min_size, pi->pg_num, pi->pg_num_mask, pi->flags, pi->last_force_request_resend, pi->read_tier, pi->write_tier); } for (i = 0; i < map->max_osd; i++) { struct ceph_entity_addr *addr = &map->osd_addr[i]; u32 state = map->osd_state[i]; char sb[64]; seq_printf(s, "osd%d\t%s\t%3d%%\t(%s)\t%3d%%\t%2d\n", i, ceph_pr_addr(addr), ((map->osd_weight[i]*100) >> 16), ceph_osdmap_state_str(sb, sizeof(sb), state), ((ceph_get_primary_affinity(map, i)*100) >> 16), ceph_get_crush_locality(map, i, &client->options->crush_locs)); } for (n = rb_first(&map->pg_temp); n; n = rb_next(n)) { struct ceph_pg_mapping *pg = rb_entry(n, struct ceph_pg_mapping, node); seq_printf(s, "pg_temp %llu.%x [", pg->pgid.pool, pg->pgid.seed); for (i = 0; i < pg->pg_temp.len; i++) seq_printf(s, "%s%d", (i == 0 ? "" : ","), pg->pg_temp.osds[i]); seq_printf(s, "]\n"); } for (n = rb_first(&map->primary_temp); n; n = rb_next(n)) { struct ceph_pg_mapping *pg = rb_entry(n, struct ceph_pg_mapping, node); seq_printf(s, "primary_temp %llu.%x %d\n", pg->pgid.pool, pg->pgid.seed, pg->primary_temp.osd); } for (n = rb_first(&map->pg_upmap); n; n = rb_next(n)) { struct ceph_pg_mapping *pg = rb_entry(n, struct ceph_pg_mapping, node); seq_printf(s, "pg_upmap %llu.%x [", pg->pgid.pool, pg->pgid.seed); for (i = 0; i < pg->pg_upmap.len; i++) seq_printf(s, "%s%d", (i == 0 ? "" : ","), pg->pg_upmap.osds[i]); seq_printf(s, "]\n"); } for (n = rb_first(&map->pg_upmap_items); n; n = rb_next(n)) { struct ceph_pg_mapping *pg = rb_entry(n, struct ceph_pg_mapping, node); seq_printf(s, "pg_upmap_items %llu.%x [", pg->pgid.pool, pg->pgid.seed); for (i = 0; i < pg->pg_upmap_items.len; i++) seq_printf(s, "%s%d->%d", (i == 0 ? "" : ","), pg->pg_upmap_items.from_to[i][0], pg->pg_upmap_items.from_to[i][1]); seq_printf(s, "]\n"); } up_read(&osdc->lock); return 0; } static int monc_show(struct seq_file *s, void *p) { struct ceph_client *client = s->private; struct ceph_mon_generic_request *req; struct ceph_mon_client *monc = &client->monc; struct rb_node *rp; int i; mutex_lock(&monc->mutex); for (i = 0; i < ARRAY_SIZE(monc->subs); i++) { seq_printf(s, "have %s %u", ceph_sub_str[i], monc->subs[i].have); if (monc->subs[i].want) seq_printf(s, " want %llu%s", le64_to_cpu(monc->subs[i].item.start), (monc->subs[i].item.flags & CEPH_SUBSCRIBE_ONETIME ? "" : "+")); seq_putc(s, '\n'); } seq_printf(s, "fs_cluster_id %d\n", monc->fs_cluster_id); for (rp = rb_first(&monc->generic_request_tree); rp; rp = rb_next(rp)) { __u16 op; req = rb_entry(rp, struct ceph_mon_generic_request, node); op = le16_to_cpu(req->request->hdr.type); if (op == CEPH_MSG_STATFS) seq_printf(s, "%llu statfs\n", req->tid); else if (op == CEPH_MSG_MON_GET_VERSION) seq_printf(s, "%llu mon_get_version", req->tid); else seq_printf(s, "%llu unknown\n", req->tid); } mutex_unlock(&monc->mutex); return 0; } static void dump_spgid(struct seq_file *s, const struct ceph_spg *spgid) { seq_printf(s, "%llu.%x", spgid->pgid.pool, spgid->pgid.seed); if (spgid->shard != CEPH_SPG_NOSHARD) seq_printf(s, "s%d", spgid->shard); } static void dump_target(struct seq_file *s, struct ceph_osd_request_target *t) { int i; seq_printf(s, "osd%d\t%llu.%x\t", t->osd, t->pgid.pool, t->pgid.seed); dump_spgid(s, &t->spgid); seq_puts(s, "\t["); for (i = 0; i < t->up.size; i++) seq_printf(s, "%s%d", (!i ? "" : ","), t->up.osds[i]); seq_printf(s, "]/%d\t[", t->up.primary); for (i = 0; i < t->acting.size; i++) seq_printf(s, "%s%d", (!i ? "" : ","), t->acting.osds[i]); seq_printf(s, "]/%d\te%u\t", t->acting.primary, t->epoch); if (t->target_oloc.pool_ns) { seq_printf(s, "%*pE/%*pE\t0x%x", (int)t->target_oloc.pool_ns->len, t->target_oloc.pool_ns->str, t->target_oid.name_len, t->target_oid.name, t->flags); } else { seq_printf(s, "%*pE\t0x%x", t->target_oid.name_len, t->target_oid.name, t->flags); } if (t->paused) seq_puts(s, "\tP"); } static void dump_request(struct seq_file *s, struct ceph_osd_request *req) { int i; seq_printf(s, "%llu\t", req->r_tid); dump_target(s, &req->r_t); seq_printf(s, "\t%d", req->r_attempts); for (i = 0; i < req->r_num_ops; i++) { struct ceph_osd_req_op *op = &req->r_ops[i]; seq_printf(s, "%s%s", (i == 0 ? "\t" : ","), ceph_osd_op_name(op->op)); if (op->op == CEPH_OSD_OP_WATCH) seq_printf(s, "-%s", ceph_osd_watch_op_name(op->watch.op)); else if (op->op == CEPH_OSD_OP_CALL) seq_printf(s, "-%s/%s", op->cls.class_name, op->cls.method_name); } seq_putc(s, '\n'); } static void dump_requests(struct seq_file *s, struct ceph_osd *osd) { struct rb_node *n; mutex_lock(&osd->lock); for (n = rb_first(&osd->o_requests); n; n = rb_next(n)) { struct ceph_osd_request *req = rb_entry(n, struct ceph_osd_request, r_node); dump_request(s, req); } mutex_unlock(&osd->lock); } static void dump_linger_request(struct seq_file *s, struct ceph_osd_linger_request *lreq) { seq_printf(s, "%llu\t", lreq->linger_id); dump_target(s, &lreq->t); seq_printf(s, "\t%u\t%s%s/%d\n", lreq->register_gen, lreq->is_watch ? "W" : "N", lreq->committed ? "C" : "", lreq->last_error); } static void dump_linger_requests(struct seq_file *s, struct ceph_osd *osd) { struct rb_node *n; mutex_lock(&osd->lock); for (n = rb_first(&osd->o_linger_requests); n; n = rb_next(n)) { struct ceph_osd_linger_request *lreq = rb_entry(n, struct ceph_osd_linger_request, node); dump_linger_request(s, lreq); } mutex_unlock(&osd->lock); } static void dump_snapid(struct seq_file *s, u64 snapid) { if (snapid == CEPH_NOSNAP) seq_puts(s, "head"); else if (snapid == CEPH_SNAPDIR) seq_puts(s, "snapdir"); else seq_printf(s, "%llx", snapid); } static void dump_name_escaped(struct seq_file *s, unsigned char *name, size_t len) { size_t i; for (i = 0; i < len; i++) { if (name[i] == '%' || name[i] == ':' || name[i] == '/' || name[i] < 32 || name[i] >= 127) { seq_printf(s, "%%%02x", name[i]); } else { seq_putc(s, name[i]); } } } static void dump_hoid(struct seq_file *s, const struct ceph_hobject_id *hoid) { if (hoid->snapid == 0 && hoid->hash == 0 && !hoid->is_max && hoid->pool == S64_MIN) { seq_puts(s, "MIN"); return; } if (hoid->is_max) { seq_puts(s, "MAX"); return; } seq_printf(s, "%lld:%08x:", hoid->pool, hoid->hash_reverse_bits); dump_name_escaped(s, hoid->nspace, hoid->nspace_len); seq_putc(s, ':'); dump_name_escaped(s, hoid->key, hoid->key_len); seq_putc(s, ':'); dump_name_escaped(s, hoid->oid, hoid->oid_len); seq_putc(s, ':'); dump_snapid(s, hoid->snapid); } static void dump_backoffs(struct seq_file *s, struct ceph_osd *osd) { struct rb_node *n; mutex_lock(&osd->lock); for (n = rb_first(&osd->o_backoffs_by_id); n; n = rb_next(n)) { struct ceph_osd_backoff *backoff = rb_entry(n, struct ceph_osd_backoff, id_node); seq_printf(s, "osd%d\t", osd->o_osd); dump_spgid(s, &backoff->spgid); seq_printf(s, "\t%llu\t", backoff->id); dump_hoid(s, backoff->begin); seq_putc(s, '\t'); dump_hoid(s, backoff->end); seq_putc(s, '\n'); } mutex_unlock(&osd->lock); } static int osdc_show(struct seq_file *s, void *pp) { struct ceph_client *client = s->private; struct ceph_osd_client *osdc = &client->osdc; struct rb_node *n; down_read(&osdc->lock); seq_printf(s, "REQUESTS %d homeless %d\n", atomic_read(&osdc->num_requests), atomic_read(&osdc->num_homeless)); for (n = rb_first(&osdc->osds); n; n = rb_next(n)) { struct ceph_osd *osd = rb_entry(n, struct ceph_osd, o_node); dump_requests(s, osd); } dump_requests(s, &osdc->homeless_osd); seq_puts(s, "LINGER REQUESTS\n"); for (n = rb_first(&osdc->osds); n; n = rb_next(n)) { struct ceph_osd *osd = rb_entry(n, struct ceph_osd, o_node); dump_linger_requests(s, osd); } dump_linger_requests(s, &osdc->homeless_osd); seq_puts(s, "BACKOFFS\n"); for (n = rb_first(&osdc->osds); n; n = rb_next(n)) { struct ceph_osd *osd = rb_entry(n, struct ceph_osd, o_node); dump_backoffs(s, osd); } up_read(&osdc->lock); return 0; } static int client_options_show(struct seq_file *s, void *p) { struct ceph_client *client = s->private; int ret; ret = ceph_print_client_options(s, client, true); if (ret) return ret; seq_putc(s, '\n'); return 0; } DEFINE_SHOW_ATTRIBUTE(monmap); DEFINE_SHOW_ATTRIBUTE(osdmap); DEFINE_SHOW_ATTRIBUTE(monc); DEFINE_SHOW_ATTRIBUTE(osdc); DEFINE_SHOW_ATTRIBUTE(client_options); void __init ceph_debugfs_init(void) { ceph_debugfs_dir = debugfs_create_dir("ceph", NULL); } void ceph_debugfs_cleanup(void) { debugfs_remove(ceph_debugfs_dir); } void ceph_debugfs_client_init(struct ceph_client *client) { char name[80]; snprintf(name, sizeof(name), "%pU.client%lld", &client->fsid, client->monc.auth->global_id); dout("ceph_debugfs_client_init %p %s\n", client, name); client->debugfs_dir = debugfs_create_dir(name, ceph_debugfs_dir); client->monc.debugfs_file = debugfs_create_file("monc", 0400, client->debugfs_dir, client, &monc_fops); client->osdc.debugfs_file = debugfs_create_file("osdc", 0400, client->debugfs_dir, client, &osdc_fops); client->debugfs_monmap = debugfs_create_file("monmap", 0400, client->debugfs_dir, client, &monmap_fops); client->debugfs_osdmap = debugfs_create_file("osdmap", 0400, client->debugfs_dir, client, &osdmap_fops); client->debugfs_options = debugfs_create_file("client_options", 0400, client->debugfs_dir, client, &client_options_fops); } void ceph_debugfs_client_cleanup(struct ceph_client *client) { dout("ceph_debugfs_client_cleanup %p\n", client); debugfs_remove(client->debugfs_options); debugfs_remove(client->debugfs_osdmap); debugfs_remove(client->debugfs_monmap); debugfs_remove(client->osdc.debugfs_file); debugfs_remove(client->monc.debugfs_file); debugfs_remove(client->debugfs_dir); } #else /* CONFIG_DEBUG_FS */ void __init ceph_debugfs_init(void) { } void ceph_debugfs_cleanup(void) { } void ceph_debugfs_client_init(struct ceph_client *client) { } void ceph_debugfs_client_cleanup(struct ceph_client *client) { } #endif /* CONFIG_DEBUG_FS */ |
| 207 206 74 74 67 66 74 77 76 77 77 61 76 77 205 205 205 232 203 204 205 204 204 1 231 1 1 1 1 1 1 1 1 212 205 205 205 205 204 204 205 203 205 204 204 205 189 205 204 202 213 | 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 | // SPDX-License-Identifier: GPL-2.0 /* * Superblock section that contains a list of recovery passes to run when * downgrading past a given version */ #include "bcachefs.h" #include "darray.h" #include "recovery_passes.h" #include "sb-downgrade.h" #include "sb-errors.h" #include "super-io.h" #define RECOVERY_PASS_ALL_FSCK BIT_ULL(63) /* * Upgrade, downgrade tables - run certain recovery passes, fix certain errors * * x(version, recovery_passes, errors...) */ #define UPGRADE_TABLE() \ x(snapshot_2, \ RECOVERY_PASS_ALL_FSCK, \ BCH_FSCK_ERR_subvol_root_wrong_bi_subvol, \ BCH_FSCK_ERR_subvol_not_master_and_not_snapshot) \ x(backpointers, \ RECOVERY_PASS_ALL_FSCK) \ x(inode_v3, \ RECOVERY_PASS_ALL_FSCK) \ x(unwritten_extents, \ RECOVERY_PASS_ALL_FSCK) \ x(bucket_gens, \ BIT_ULL(BCH_RECOVERY_PASS_bucket_gens_init)| \ RECOVERY_PASS_ALL_FSCK) \ x(lru_v2, \ RECOVERY_PASS_ALL_FSCK) \ x(fragmentation_lru, \ RECOVERY_PASS_ALL_FSCK) \ x(no_bps_in_alloc_keys, \ RECOVERY_PASS_ALL_FSCK) \ x(snapshot_trees, \ RECOVERY_PASS_ALL_FSCK) \ x(snapshot_skiplists, \ BIT_ULL(BCH_RECOVERY_PASS_check_snapshots), \ BCH_FSCK_ERR_snapshot_bad_depth, \ BCH_FSCK_ERR_snapshot_bad_skiplist) \ x(deleted_inodes, \ BIT_ULL(BCH_RECOVERY_PASS_check_inodes), \ BCH_FSCK_ERR_unlinked_inode_not_on_deleted_list) \ x(rebalance_work, \ BIT_ULL(BCH_RECOVERY_PASS_set_fs_needs_rebalance)) \ x(subvolume_fs_parent, \ BIT_ULL(BCH_RECOVERY_PASS_check_dirents), \ BCH_FSCK_ERR_subvol_fs_path_parent_wrong) \ x(btree_subvolume_children, \ BIT_ULL(BCH_RECOVERY_PASS_check_subvols), \ BCH_FSCK_ERR_subvol_children_not_set) \ x(mi_btree_bitmap, \ BIT_ULL(BCH_RECOVERY_PASS_check_allocations), \ BCH_FSCK_ERR_btree_bitmap_not_marked) \ x(disk_accounting_v2, \ BIT_ULL(BCH_RECOVERY_PASS_check_allocations), \ BCH_FSCK_ERR_bkey_version_in_future, \ BCH_FSCK_ERR_dev_usage_buckets_wrong, \ BCH_FSCK_ERR_dev_usage_sectors_wrong, \ BCH_FSCK_ERR_dev_usage_fragmented_wrong, \ BCH_FSCK_ERR_accounting_mismatch) \ x(disk_accounting_v3, \ BIT_ULL(BCH_RECOVERY_PASS_check_allocations), \ BCH_FSCK_ERR_bkey_version_in_future, \ BCH_FSCK_ERR_dev_usage_buckets_wrong, \ BCH_FSCK_ERR_dev_usage_sectors_wrong, \ BCH_FSCK_ERR_dev_usage_fragmented_wrong, \ BCH_FSCK_ERR_accounting_mismatch, \ BCH_FSCK_ERR_accounting_key_replicas_nr_devs_0, \ BCH_FSCK_ERR_accounting_key_replicas_nr_required_bad, \ BCH_FSCK_ERR_accounting_key_replicas_devs_unsorted, \ BCH_FSCK_ERR_accounting_key_junk_at_end) \ x(disk_accounting_inum, \ BIT_ULL(BCH_RECOVERY_PASS_check_allocations), \ BCH_FSCK_ERR_accounting_mismatch) \ x(rebalance_work_acct_fix, \ BIT_ULL(BCH_RECOVERY_PASS_check_allocations), \ BCH_FSCK_ERR_accounting_mismatch) \ x(inode_has_child_snapshots, \ BIT_ULL(BCH_RECOVERY_PASS_check_inodes), \ BCH_FSCK_ERR_inode_has_child_snapshots_wrong) \ x(backpointer_bucket_gen, \ BIT_ULL(BCH_RECOVERY_PASS_check_extents_to_backpointers),\ BCH_FSCK_ERR_backpointer_to_missing_ptr, \ BCH_FSCK_ERR_ptr_to_missing_backpointer) \ x(disk_accounting_big_endian, \ BIT_ULL(BCH_RECOVERY_PASS_check_allocations), \ BCH_FSCK_ERR_accounting_mismatch, \ BCH_FSCK_ERR_accounting_key_replicas_nr_devs_0, \ BCH_FSCK_ERR_accounting_key_junk_at_end) \ x(cached_backpointers, \ BIT_ULL(BCH_RECOVERY_PASS_check_extents_to_backpointers),\ BCH_FSCK_ERR_ptr_to_missing_backpointer) \ x(stripe_backpointers, \ BIT_ULL(BCH_RECOVERY_PASS_check_extents_to_backpointers),\ BCH_FSCK_ERR_ptr_to_missing_backpointer) \ x(inode_has_case_insensitive, \ BIT_ULL(BCH_RECOVERY_PASS_check_inodes), \ BCH_FSCK_ERR_inode_has_case_insensitive_not_set, \ BCH_FSCK_ERR_inode_parent_has_case_insensitive_not_set) #define DOWNGRADE_TABLE() \ x(bucket_stripe_sectors, \ 0) \ x(disk_accounting_v2, \ BIT_ULL(BCH_RECOVERY_PASS_check_allocations), \ BCH_FSCK_ERR_dev_usage_buckets_wrong, \ BCH_FSCK_ERR_dev_usage_sectors_wrong, \ BCH_FSCK_ERR_dev_usage_fragmented_wrong, \ BCH_FSCK_ERR_fs_usage_hidden_wrong, \ BCH_FSCK_ERR_fs_usage_btree_wrong, \ BCH_FSCK_ERR_fs_usage_data_wrong, \ BCH_FSCK_ERR_fs_usage_cached_wrong, \ BCH_FSCK_ERR_fs_usage_reserved_wrong, \ BCH_FSCK_ERR_fs_usage_nr_inodes_wrong, \ BCH_FSCK_ERR_fs_usage_persistent_reserved_wrong, \ BCH_FSCK_ERR_fs_usage_replicas_wrong, \ BCH_FSCK_ERR_bkey_version_in_future) \ x(disk_accounting_v3, \ BIT_ULL(BCH_RECOVERY_PASS_check_allocations), \ BCH_FSCK_ERR_dev_usage_buckets_wrong, \ BCH_FSCK_ERR_dev_usage_sectors_wrong, \ BCH_FSCK_ERR_dev_usage_fragmented_wrong, \ BCH_FSCK_ERR_fs_usage_hidden_wrong, \ BCH_FSCK_ERR_fs_usage_btree_wrong, \ BCH_FSCK_ERR_fs_usage_data_wrong, \ BCH_FSCK_ERR_fs_usage_cached_wrong, \ BCH_FSCK_ERR_fs_usage_reserved_wrong, \ BCH_FSCK_ERR_fs_usage_nr_inodes_wrong, \ BCH_FSCK_ERR_fs_usage_persistent_reserved_wrong, \ BCH_FSCK_ERR_fs_usage_replicas_wrong, \ BCH_FSCK_ERR_accounting_replicas_not_marked, \ BCH_FSCK_ERR_bkey_version_in_future) \ x(rebalance_work_acct_fix, \ BIT_ULL(BCH_RECOVERY_PASS_check_allocations), \ BCH_FSCK_ERR_accounting_mismatch, \ BCH_FSCK_ERR_accounting_key_replicas_nr_devs_0, \ BCH_FSCK_ERR_accounting_key_junk_at_end) \ x(backpointer_bucket_gen, \ BIT_ULL(BCH_RECOVERY_PASS_check_extents_to_backpointers),\ BCH_FSCK_ERR_backpointer_bucket_offset_wrong, \ BCH_FSCK_ERR_backpointer_to_missing_ptr, \ BCH_FSCK_ERR_ptr_to_missing_backpointer) \ x(disk_accounting_big_endian, \ BIT_ULL(BCH_RECOVERY_PASS_check_allocations), \ BCH_FSCK_ERR_accounting_mismatch, \ BCH_FSCK_ERR_accounting_key_replicas_nr_devs_0, \ BCH_FSCK_ERR_accounting_key_junk_at_end) struct upgrade_downgrade_entry { u64 recovery_passes; u16 version; u16 nr_errors; const u16 *errors; }; #define x(ver, passes, ...) static const u16 upgrade_##ver##_errors[] = { __VA_ARGS__ }; UPGRADE_TABLE() #undef x static const struct upgrade_downgrade_entry upgrade_table[] = { #define x(ver, passes, ...) { \ .recovery_passes = passes, \ .version = bcachefs_metadata_version_##ver,\ .nr_errors = ARRAY_SIZE(upgrade_##ver##_errors), \ .errors = upgrade_##ver##_errors, \ }, UPGRADE_TABLE() #undef x }; static int have_stripes(struct bch_fs *c) { if (IS_ERR_OR_NULL(c->btree_roots_known[BTREE_ID_stripes].b)) return 0; return !btree_node_fake(c->btree_roots_known[BTREE_ID_stripes].b); } int bch2_sb_set_upgrade_extra(struct bch_fs *c) { unsigned old_version = c->sb.version_upgrade_complete ?: c->sb.version; unsigned new_version = c->sb.version; bool write_sb = false; int ret = 0; mutex_lock(&c->sb_lock); struct bch_sb_field_ext *ext = bch2_sb_field_get(c->disk_sb.sb, ext); if (old_version < bcachefs_metadata_version_bucket_stripe_sectors && new_version >= bcachefs_metadata_version_bucket_stripe_sectors && (ret = have_stripes(c) > 0)) { __set_bit_le64(BCH_RECOVERY_PASS_STABLE_check_allocations, ext->recovery_passes_required); __set_bit_le64(BCH_FSCK_ERR_alloc_key_dirty_sectors_wrong, ext->errors_silent); __set_bit_le64(BCH_FSCK_ERR_alloc_key_stripe_sectors_wrong, ext->errors_silent); write_sb = true; } if (write_sb) bch2_write_super(c); mutex_unlock(&c->sb_lock); return ret < 0 ? ret : 0; } void bch2_sb_set_upgrade(struct bch_fs *c, unsigned old_version, unsigned new_version) { lockdep_assert_held(&c->sb_lock); struct bch_sb_field_ext *ext = bch2_sb_field_get(c->disk_sb.sb, ext); for (const struct upgrade_downgrade_entry *i = upgrade_table; i < upgrade_table + ARRAY_SIZE(upgrade_table); i++) if (i->version > old_version && i->version <= new_version) { u64 passes = i->recovery_passes; if (passes & RECOVERY_PASS_ALL_FSCK) passes |= bch2_fsck_recovery_passes(); passes &= ~RECOVERY_PASS_ALL_FSCK; ext->recovery_passes_required[0] |= cpu_to_le64(bch2_recovery_passes_to_stable(passes)); for (const u16 *e = i->errors; e < i->errors + i->nr_errors; e++) __set_bit_le64(*e, ext->errors_silent); } } #define x(ver, passes, ...) static const u16 downgrade_##ver##_errors[] = { __VA_ARGS__ }; DOWNGRADE_TABLE() #undef x static const struct upgrade_downgrade_entry downgrade_table[] = { #define x(ver, passes, ...) { \ .recovery_passes = passes, \ .version = bcachefs_metadata_version_##ver,\ .nr_errors = ARRAY_SIZE(downgrade_##ver##_errors), \ .errors = downgrade_##ver##_errors, \ }, DOWNGRADE_TABLE() #undef x }; static int downgrade_table_extra(struct bch_fs *c, darray_char *table) { unsigned dst_offset = table->nr; struct bch_sb_field_downgrade_entry *dst = (void *) &darray_top(*table); unsigned bytes = sizeof(*dst) + sizeof(dst->errors[0]) * le16_to_cpu(dst->nr_errors); int ret = 0; unsigned nr_errors = le16_to_cpu(dst->nr_errors); switch (le16_to_cpu(dst->version)) { case bcachefs_metadata_version_bucket_stripe_sectors: if (have_stripes(c)) { bytes += sizeof(dst->errors[0]) * 2; ret = darray_make_room(table, bytes); if (ret) return ret; dst = (void *) &table->data[dst_offset]; dst->nr_errors = cpu_to_le16(nr_errors + 1); /* open coded __set_bit_le64, as dst is packed and * dst->recovery_passes is misaligned */ unsigned b = BCH_RECOVERY_PASS_STABLE_check_allocations; dst->recovery_passes[b / 64] |= cpu_to_le64(BIT_ULL(b % 64)); dst->errors[nr_errors++] = cpu_to_le16(BCH_FSCK_ERR_alloc_key_dirty_sectors_wrong); } break; } return ret; } static inline const struct bch_sb_field_downgrade_entry * downgrade_entry_next_c(const struct bch_sb_field_downgrade_entry *e) { return (void *) &e->errors[le16_to_cpu(e->nr_errors)]; } #define for_each_downgrade_entry(_d, _i) \ for (const struct bch_sb_field_downgrade_entry *_i = (_d)->entries; \ (void *) _i < vstruct_end(&(_d)->field) && \ (void *) &_i->errors[0] <= vstruct_end(&(_d)->field) && \ (void *) downgrade_entry_next_c(_i) <= vstruct_end(&(_d)->field); \ _i = downgrade_entry_next_c(_i)) static int bch2_sb_downgrade_validate(struct bch_sb *sb, struct bch_sb_field *f, enum bch_validate_flags flags, struct printbuf *err) { struct bch_sb_field_downgrade *e = field_to_type(f, downgrade); for (const struct bch_sb_field_downgrade_entry *i = e->entries; (void *) i < vstruct_end(&e->field); i = downgrade_entry_next_c(i)) { /* * Careful: sb_field_downgrade_entry is only 2 byte aligned, but * section sizes are 8 byte aligned - an empty entry spanning * the end of the section is allowed (and ignored): */ if ((void *) &i->errors[0] > vstruct_end(&e->field)) break; if (flags & BCH_VALIDATE_write && (void *) downgrade_entry_next_c(i) > vstruct_end(&e->field)) { prt_printf(err, "downgrade entry overruns end of superblock section"); return -BCH_ERR_invalid_sb_downgrade; } if (BCH_VERSION_MAJOR(le16_to_cpu(i->version)) != BCH_VERSION_MAJOR(le16_to_cpu(sb->version))) { prt_printf(err, "downgrade entry with mismatched major version (%u != %u)", BCH_VERSION_MAJOR(le16_to_cpu(i->version)), BCH_VERSION_MAJOR(le16_to_cpu(sb->version))); return -BCH_ERR_invalid_sb_downgrade; } } return 0; } static void bch2_sb_downgrade_to_text(struct printbuf *out, struct bch_sb *sb, struct bch_sb_field *f) { struct bch_sb_field_downgrade *e = field_to_type(f, downgrade); if (out->nr_tabstops <= 1) printbuf_tabstop_push(out, 16); for_each_downgrade_entry(e, i) { prt_str(out, "version:\t"); bch2_version_to_text(out, le16_to_cpu(i->version)); prt_newline(out); prt_str(out, "recovery passes:\t"); prt_bitflags(out, bch2_recovery_passes, bch2_recovery_passes_from_stable(le64_to_cpu(i->recovery_passes[0]))); prt_newline(out); prt_str(out, "errors:\t"); bool first = true; for (unsigned j = 0; j < le16_to_cpu(i->nr_errors); j++) { if (!first) prt_char(out, ','); first = false; bch2_sb_error_id_to_text(out, le16_to_cpu(i->errors[j])); } prt_newline(out); } } const struct bch_sb_field_ops bch_sb_field_ops_downgrade = { .validate = bch2_sb_downgrade_validate, .to_text = bch2_sb_downgrade_to_text, }; int bch2_sb_downgrade_update(struct bch_fs *c) { if (!test_bit(BCH_FS_btree_running, &c->flags)) return 0; darray_char table = {}; int ret = 0; for (const struct upgrade_downgrade_entry *src = downgrade_table; src < downgrade_table + ARRAY_SIZE(downgrade_table); src++) { if (BCH_VERSION_MAJOR(src->version) != BCH_VERSION_MAJOR(le16_to_cpu(c->disk_sb.sb->version))) continue; if (src->version < c->sb.version_incompat) continue; struct bch_sb_field_downgrade_entry *dst; unsigned bytes = sizeof(*dst) + sizeof(dst->errors[0]) * src->nr_errors; ret = darray_make_room(&table, bytes); if (ret) goto out; dst = (void *) &darray_top(table); dst->version = cpu_to_le16(src->version); dst->recovery_passes[0] = cpu_to_le64(bch2_recovery_passes_to_stable(src->recovery_passes)); dst->recovery_passes[1] = 0; dst->nr_errors = cpu_to_le16(src->nr_errors); for (unsigned i = 0; i < src->nr_errors; i++) dst->errors[i] = cpu_to_le16(src->errors[i]); ret = downgrade_table_extra(c, &table); if (ret) goto out; if (!dst->recovery_passes[0] && !dst->recovery_passes[1] && !dst->nr_errors) continue; table.nr += sizeof(*dst) + sizeof(dst->errors[0]) * le16_to_cpu(dst->nr_errors); } struct bch_sb_field_downgrade *d = bch2_sb_field_get(c->disk_sb.sb, downgrade); unsigned sb_u64s = DIV_ROUND_UP(sizeof(*d) + table.nr, sizeof(u64)); if (d && le32_to_cpu(d->field.u64s) > sb_u64s) goto out; d = bch2_sb_field_resize(&c->disk_sb, downgrade, sb_u64s); if (!d) { ret = bch_err_throw(c, ENOSPC_sb_downgrade); goto out; } memcpy(d->entries, table.data, table.nr); memset_u64s_tail(d->entries, 0, table.nr); out: darray_exit(&table); return ret; } void bch2_sb_set_downgrade(struct bch_fs *c, unsigned new_minor, unsigned old_minor) { struct bch_sb_field_downgrade *d = bch2_sb_field_get(c->disk_sb.sb, downgrade); if (!d) return; struct bch_sb_field_ext *ext = bch2_sb_field_get(c->disk_sb.sb, ext); for_each_downgrade_entry(d, i) { unsigned minor = BCH_VERSION_MINOR(le16_to_cpu(i->version)); if (new_minor < minor && minor <= old_minor) { ext->recovery_passes_required[0] |= i->recovery_passes[0]; ext->recovery_passes_required[1] |= i->recovery_passes[1]; for (unsigned j = 0; j < le16_to_cpu(i->nr_errors); j++) { unsigned e = le16_to_cpu(i->errors[j]); if (e < BCH_FSCK_ERR_MAX) __set_bit(e, c->sb.errors_silent); if (e < sizeof(ext->errors_silent) * 8) __set_bit_le64(e, ext->errors_silent); } } } } |
| 3 3 1 2 2 1 2 3 3 5 5 2 2 5 5 5 5 10 12 2 10 5 5 12 13 12 12 13 5 5 4 3 2 2 3 5 6 5 4 4 3 6 5 3 3 3 3 3 5 6 5 6 4 4 4 2 4 5 5 3 2 1 3 15 1 14 13 2 12 1 10 10 10 4 1 3 3 4 18 5 5 2 1 6 1 4 4 2 1 2 4 1 4 1 3 3 3 18 4 3 1 1 1 1 3 4 19 4 15 13 4 3 1 1 1 2 3 1 1 1 13 19 8 8 8 7 7 3 2 2 7 7 10 5 2 1 1 5 10 1 1 10 10 2 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 | /* BlueZ - Bluetooth protocol stack for Linux Copyright (C) 2000-2001 Qualcomm Incorporated Written 2000,2001 by Maxim Krasnyansky <maxk@qualcomm.com> 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 SCO sockets. */ #include <linux/module.h> #include <linux/debugfs.h> #include <linux/seq_file.h> #include <linux/sched/signal.h> #include <net/bluetooth/bluetooth.h> #include <net/bluetooth/hci_core.h> #include <net/bluetooth/sco.h> static bool disable_esco; static const struct proto_ops sco_sock_ops; static struct bt_sock_list sco_sk_list = { .lock = __RW_LOCK_UNLOCKED(sco_sk_list.lock) }; /* ---- SCO connections ---- */ struct sco_conn { struct hci_conn *hcon; spinlock_t lock; struct sock *sk; struct delayed_work timeout_work; unsigned int mtu; struct kref ref; }; #define sco_conn_lock(c) spin_lock(&c->lock) #define sco_conn_unlock(c) spin_unlock(&c->lock) static void sco_sock_close(struct sock *sk); static void sco_sock_kill(struct sock *sk); /* ----- SCO socket info ----- */ #define sco_pi(sk) ((struct sco_pinfo *) sk) struct sco_pinfo { struct bt_sock bt; bdaddr_t src; bdaddr_t dst; __u32 flags; __u16 setting; struct bt_codec codec; struct sco_conn *conn; }; /* ---- SCO timers ---- */ #define SCO_CONN_TIMEOUT (HZ * 40) #define SCO_DISCONN_TIMEOUT (HZ * 2) static void sco_conn_free(struct kref *ref) { struct sco_conn *conn = container_of(ref, struct sco_conn, ref); BT_DBG("conn %p", conn); if (conn->sk) sco_pi(conn->sk)->conn = NULL; if (conn->hcon) { conn->hcon->sco_data = NULL; hci_conn_drop(conn->hcon); } /* Ensure no more work items will run since hci_conn has been dropped */ disable_delayed_work_sync(&conn->timeout_work); kfree(conn); } static void sco_conn_put(struct sco_conn *conn) { if (!conn) return; BT_DBG("conn %p refcnt %d", conn, kref_read(&conn->ref)); kref_put(&conn->ref, sco_conn_free); } static struct sco_conn *sco_conn_hold(struct sco_conn *conn) { BT_DBG("conn %p refcnt %u", conn, kref_read(&conn->ref)); kref_get(&conn->ref); return conn; } static struct sco_conn *sco_conn_hold_unless_zero(struct sco_conn *conn) { if (!conn) return NULL; BT_DBG("conn %p refcnt %u", conn, kref_read(&conn->ref)); if (!kref_get_unless_zero(&conn->ref)) return NULL; return conn; } static struct sock *sco_sock_hold(struct sco_conn *conn) { if (!conn || !bt_sock_linked(&sco_sk_list, conn->sk)) return NULL; sock_hold(conn->sk); return conn->sk; } static void sco_sock_timeout(struct work_struct *work) { struct sco_conn *conn = container_of(work, struct sco_conn, timeout_work.work); struct sock *sk; conn = sco_conn_hold_unless_zero(conn); if (!conn) return; sco_conn_lock(conn); if (!conn->hcon) { sco_conn_unlock(conn); sco_conn_put(conn); return; } sk = sco_sock_hold(conn); sco_conn_unlock(conn); sco_conn_put(conn); if (!sk) return; BT_DBG("sock %p state %d", sk, sk->sk_state); lock_sock(sk); sk->sk_err = ETIMEDOUT; sk->sk_state_change(sk); release_sock(sk); sock_put(sk); } static void sco_sock_set_timer(struct sock *sk, long timeout) { if (!sco_pi(sk)->conn) return; BT_DBG("sock %p state %d timeout %ld", sk, sk->sk_state, timeout); cancel_delayed_work(&sco_pi(sk)->conn->timeout_work); schedule_delayed_work(&sco_pi(sk)->conn->timeout_work, timeout); } static void sco_sock_clear_timer(struct sock *sk) { if (!sco_pi(sk)->conn) return; BT_DBG("sock %p state %d", sk, sk->sk_state); cancel_delayed_work(&sco_pi(sk)->conn->timeout_work); } /* ---- SCO connections ---- */ static struct sco_conn *sco_conn_add(struct hci_conn *hcon) { struct sco_conn *conn = hcon->sco_data; conn = sco_conn_hold_unless_zero(conn); if (conn) { if (!conn->hcon) { sco_conn_lock(conn); conn->hcon = hcon; sco_conn_unlock(conn); } return conn; } conn = kzalloc(sizeof(struct sco_conn), GFP_KERNEL); if (!conn) return NULL; kref_init(&conn->ref); spin_lock_init(&conn->lock); INIT_DELAYED_WORK(&conn->timeout_work, sco_sock_timeout); hcon->sco_data = conn; conn->hcon = hcon; conn->mtu = hcon->mtu; if (hcon->mtu > 0) conn->mtu = hcon->mtu; else conn->mtu = 60; BT_DBG("hcon %p conn %p", hcon, conn); return conn; } /* Delete channel. * Must be called on the locked socket. */ static void sco_chan_del(struct sock *sk, int err) { struct sco_conn *conn; conn = sco_pi(sk)->conn; sco_pi(sk)->conn = NULL; BT_DBG("sk %p, conn %p, err %d", sk, conn, err); if (conn) { sco_conn_lock(conn); conn->sk = NULL; sco_conn_unlock(conn); sco_conn_put(conn); } sk->sk_state = BT_CLOSED; sk->sk_err = err; sk->sk_state_change(sk); sock_set_flag(sk, SOCK_ZAPPED); } static void sco_conn_del(struct hci_conn *hcon, int err) { struct sco_conn *conn = hcon->sco_data; struct sock *sk; conn = sco_conn_hold_unless_zero(conn); if (!conn) return; BT_DBG("hcon %p conn %p, err %d", hcon, conn, err); sco_conn_lock(conn); sk = sco_sock_hold(conn); sco_conn_unlock(conn); sco_conn_put(conn); if (!sk) { sco_conn_put(conn); return; } /* Kill socket */ lock_sock(sk); sco_sock_clear_timer(sk); sco_chan_del(sk, err); release_sock(sk); sock_put(sk); } static void __sco_chan_add(struct sco_conn *conn, struct sock *sk, struct sock *parent) { BT_DBG("conn %p", conn); sco_pi(sk)->conn = conn; conn->sk = sk; if (parent) bt_accept_enqueue(parent, sk, true); } static int sco_chan_add(struct sco_conn *conn, struct sock *sk, struct sock *parent) { int err = 0; sco_conn_lock(conn); if (conn->sk) err = -EBUSY; else __sco_chan_add(conn, sk, parent); sco_conn_unlock(conn); return err; } static int sco_connect(struct sock *sk) { struct sco_conn *conn; struct hci_conn *hcon; struct hci_dev *hdev; int err, type; BT_DBG("%pMR -> %pMR", &sco_pi(sk)->src, &sco_pi(sk)->dst); hdev = hci_get_route(&sco_pi(sk)->dst, &sco_pi(sk)->src, BDADDR_BREDR); if (!hdev) return -EHOSTUNREACH; hci_dev_lock(hdev); if (lmp_esco_capable(hdev) && !disable_esco) type = ESCO_LINK; else type = SCO_LINK; switch (sco_pi(sk)->setting & SCO_AIRMODE_MASK) { case SCO_AIRMODE_TRANSP: if (!lmp_transp_capable(hdev) || !lmp_esco_capable(hdev)) { err = -EOPNOTSUPP; goto unlock; } break; } hcon = hci_connect_sco(hdev, type, &sco_pi(sk)->dst, sco_pi(sk)->setting, &sco_pi(sk)->codec, READ_ONCE(sk->sk_sndtimeo)); if (IS_ERR(hcon)) { err = PTR_ERR(hcon); goto unlock; } conn = sco_conn_add(hcon); if (!conn) { hci_conn_drop(hcon); err = -ENOMEM; goto unlock; } lock_sock(sk); err = sco_chan_add(conn, sk, NULL); if (err) { release_sock(sk); goto unlock; } /* Update source addr of the socket */ bacpy(&sco_pi(sk)->src, &hcon->src); if (hcon->state == BT_CONNECTED) { sco_sock_clear_timer(sk); sk->sk_state = BT_CONNECTED; } else { sk->sk_state = BT_CONNECT; sco_sock_set_timer(sk, READ_ONCE(sk->sk_sndtimeo)); } release_sock(sk); unlock: hci_dev_unlock(hdev); hci_dev_put(hdev); return err; } static int sco_send_frame(struct sock *sk, struct sk_buff *skb, const struct sockcm_cookie *sockc) { struct sco_conn *conn = sco_pi(sk)->conn; int len = skb->len; /* Check outgoing MTU */ if (len > conn->mtu) return -EINVAL; BT_DBG("sk %p len %d", sk, len); hci_setup_tx_timestamp(skb, 1, sockc); hci_send_sco(conn->hcon, skb); return len; } static void sco_recv_frame(struct sco_conn *conn, struct sk_buff *skb) { struct sock *sk; sco_conn_lock(conn); sk = conn->sk; sco_conn_unlock(conn); if (!sk) goto drop; BT_DBG("sk %p len %u", sk, skb->len); if (sk->sk_state != BT_CONNECTED) goto drop; if (!sock_queue_rcv_skb(sk, skb)) return; drop: kfree_skb(skb); } /* -------- Socket interface ---------- */ static struct sock *__sco_get_sock_listen_by_addr(bdaddr_t *ba) { struct sock *sk; sk_for_each(sk, &sco_sk_list.head) { if (sk->sk_state != BT_LISTEN) continue; if (!bacmp(&sco_pi(sk)->src, ba)) return sk; } return NULL; } /* Find socket listening on source bdaddr. * Returns closest match. */ static struct sock *sco_get_sock_listen(bdaddr_t *src) { struct sock *sk = NULL, *sk1 = NULL; read_lock(&sco_sk_list.lock); sk_for_each(sk, &sco_sk_list.head) { if (sk->sk_state != BT_LISTEN) continue; /* Exact match. */ if (!bacmp(&sco_pi(sk)->src, src)) break; /* Closest match */ if (!bacmp(&sco_pi(sk)->src, BDADDR_ANY)) sk1 = sk; } read_unlock(&sco_sk_list.lock); return sk ? sk : sk1; } static void sco_sock_destruct(struct sock *sk) { BT_DBG("sk %p", sk); sco_conn_put(sco_pi(sk)->conn); skb_queue_purge(&sk->sk_receive_queue); skb_queue_purge(&sk->sk_write_queue); } static void sco_sock_cleanup_listen(struct sock *parent) { struct sock *sk; BT_DBG("parent %p", parent); /* Close not yet accepted channels */ while ((sk = bt_accept_dequeue(parent, NULL))) { sco_sock_close(sk); sco_sock_kill(sk); } parent->sk_state = BT_CLOSED; sock_set_flag(parent, SOCK_ZAPPED); } /* Kill socket (only if zapped and orphan) * Must be called on unlocked socket. */ static void sco_sock_kill(struct sock *sk) { if (!sock_flag(sk, SOCK_ZAPPED) || sk->sk_socket) return; BT_DBG("sk %p state %d", sk, sk->sk_state); /* Kill poor orphan */ bt_sock_unlink(&sco_sk_list, sk); sock_set_flag(sk, SOCK_DEAD); sock_put(sk); } static void __sco_sock_close(struct sock *sk) { BT_DBG("sk %p state %d socket %p", sk, sk->sk_state, sk->sk_socket); switch (sk->sk_state) { case BT_LISTEN: sco_sock_cleanup_listen(sk); break; case BT_CONNECTED: case BT_CONFIG: case BT_CONNECT2: case BT_CONNECT: case BT_DISCONN: sco_chan_del(sk, ECONNRESET); break; default: sock_set_flag(sk, SOCK_ZAPPED); break; } } /* Must be called on unlocked socket. */ static void sco_sock_close(struct sock *sk) { lock_sock(sk); sco_sock_clear_timer(sk); __sco_sock_close(sk); release_sock(sk); } static void sco_sock_init(struct sock *sk, struct sock *parent) { BT_DBG("sk %p", sk); if (parent) { sk->sk_type = parent->sk_type; bt_sk(sk)->flags = bt_sk(parent)->flags; security_sk_clone(parent, sk); } } static struct proto sco_proto = { .name = "SCO", .owner = THIS_MODULE, .obj_size = sizeof(struct sco_pinfo) }; static struct sock *sco_sock_alloc(struct net *net, struct socket *sock, int proto, gfp_t prio, int kern) { struct sock *sk; sk = bt_sock_alloc(net, sock, &sco_proto, proto, prio, kern); if (!sk) return NULL; sk->sk_destruct = sco_sock_destruct; sk->sk_sndtimeo = SCO_CONN_TIMEOUT; sco_pi(sk)->setting = BT_VOICE_CVSD_16BIT; sco_pi(sk)->codec.id = BT_CODEC_CVSD; sco_pi(sk)->codec.cid = 0xffff; sco_pi(sk)->codec.vid = 0xffff; sco_pi(sk)->codec.data_path = 0x00; bt_sock_link(&sco_sk_list, sk); return sk; } static int sco_sock_create(struct net *net, struct socket *sock, int protocol, int kern) { struct sock *sk; BT_DBG("sock %p", sock); sock->state = SS_UNCONNECTED; if (sock->type != SOCK_SEQPACKET) return -ESOCKTNOSUPPORT; sock->ops = &sco_sock_ops; sk = sco_sock_alloc(net, sock, protocol, GFP_ATOMIC, kern); if (!sk) return -ENOMEM; sco_sock_init(sk, NULL); return 0; } static int sco_sock_bind(struct socket *sock, struct sockaddr *addr, int addr_len) { struct sockaddr_sco *sa = (struct sockaddr_sco *) addr; struct sock *sk = sock->sk; int err = 0; if (!addr || addr_len < sizeof(struct sockaddr_sco) || addr->sa_family != AF_BLUETOOTH) return -EINVAL; BT_DBG("sk %p %pMR", sk, &sa->sco_bdaddr); lock_sock(sk); if (sk->sk_state != BT_OPEN) { err = -EBADFD; goto done; } if (sk->sk_type != SOCK_SEQPACKET) { err = -EINVAL; goto done; } bacpy(&sco_pi(sk)->src, &sa->sco_bdaddr); sk->sk_state = BT_BOUND; done: release_sock(sk); return err; } static int sco_sock_connect(struct socket *sock, struct sockaddr *addr, int alen, int flags) { struct sockaddr_sco *sa = (struct sockaddr_sco *) addr; struct sock *sk = sock->sk; int err; BT_DBG("sk %p", sk); if (alen < sizeof(struct sockaddr_sco) || addr->sa_family != AF_BLUETOOTH) return -EINVAL; if (sk->sk_state != BT_OPEN && sk->sk_state != BT_BOUND) return -EBADFD; if (sk->sk_type != SOCK_SEQPACKET) err = -EINVAL; lock_sock(sk); /* Set destination address and psm */ bacpy(&sco_pi(sk)->dst, &sa->sco_bdaddr); release_sock(sk); err = sco_connect(sk); if (err) return err; lock_sock(sk); err = bt_sock_wait_state(sk, BT_CONNECTED, sock_sndtimeo(sk, flags & O_NONBLOCK)); release_sock(sk); return err; } static int sco_sock_listen(struct socket *sock, int backlog) { struct sock *sk = sock->sk; bdaddr_t *src = &sco_pi(sk)->src; int err = 0; BT_DBG("sk %p backlog %d", sk, backlog); lock_sock(sk); if (sk->sk_state != BT_BOUND) { err = -EBADFD; goto done; } if (sk->sk_type != SOCK_SEQPACKET) { err = -EINVAL; goto done; } write_lock(&sco_sk_list.lock); if (__sco_get_sock_listen_by_addr(src)) { err = -EADDRINUSE; goto unlock; } sk->sk_max_ack_backlog = backlog; sk->sk_ack_backlog = 0; sk->sk_state = BT_LISTEN; unlock: write_unlock(&sco_sk_list.lock); done: release_sock(sk); return err; } static int sco_sock_accept(struct socket *sock, struct socket *newsock, struct proto_accept_arg *arg) { DEFINE_WAIT_FUNC(wait, woken_wake_function); struct sock *sk = sock->sk, *ch; long timeo; int err = 0; lock_sock(sk); timeo = sock_rcvtimeo(sk, arg->flags & O_NONBLOCK); BT_DBG("sk %p timeo %ld", sk, timeo); /* Wait for an incoming connection. (wake-one). */ add_wait_queue_exclusive(sk_sleep(sk), &wait); while (1) { if (sk->sk_state != BT_LISTEN) { err = -EBADFD; break; } ch = bt_accept_dequeue(sk, newsock); if (ch) break; if (!timeo) { err = -EAGAIN; break; } if (signal_pending(current)) { err = sock_intr_errno(timeo); break; } release_sock(sk); timeo = wait_woken(&wait, TASK_INTERRUPTIBLE, timeo); lock_sock(sk); } remove_wait_queue(sk_sleep(sk), &wait); if (err) goto done; newsock->state = SS_CONNECTED; BT_DBG("new socket %p", ch); done: release_sock(sk); return err; } static int sco_sock_getname(struct socket *sock, struct sockaddr *addr, int peer) { struct sockaddr_sco *sa = (struct sockaddr_sco *) addr; struct sock *sk = sock->sk; BT_DBG("sock %p, sk %p", sock, sk); addr->sa_family = AF_BLUETOOTH; if (peer) bacpy(&sa->sco_bdaddr, &sco_pi(sk)->dst); else bacpy(&sa->sco_bdaddr, &sco_pi(sk)->src); return sizeof(struct sockaddr_sco); } static int sco_sock_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) { struct sock *sk = sock->sk; struct sk_buff *skb; struct sockcm_cookie sockc; int err; BT_DBG("sock %p, sk %p", sock, sk); err = sock_error(sk); if (err) return err; if (msg->msg_flags & MSG_OOB) return -EOPNOTSUPP; hci_sockcm_init(&sockc, sk); if (msg->msg_controllen) { err = sock_cmsg_send(sk, msg, &sockc); if (err) return err; } skb = bt_skb_sendmsg(sk, msg, len, len, 0, 0); if (IS_ERR(skb)) return PTR_ERR(skb); lock_sock(sk); if (sk->sk_state == BT_CONNECTED) err = sco_send_frame(sk, skb, &sockc); else err = -ENOTCONN; release_sock(sk); if (err < 0) kfree_skb(skb); return err; } static void sco_conn_defer_accept(struct hci_conn *conn, u16 setting) { struct hci_dev *hdev = conn->hdev; BT_DBG("conn %p", conn); conn->state = BT_CONFIG; if (!lmp_esco_capable(hdev)) { struct hci_cp_accept_conn_req cp; bacpy(&cp.bdaddr, &conn->dst); cp.role = 0x00; /* Ignored */ hci_send_cmd(hdev, HCI_OP_ACCEPT_CONN_REQ, sizeof(cp), &cp); } else { struct hci_cp_accept_sync_conn_req cp; bacpy(&cp.bdaddr, &conn->dst); cp.pkt_type = cpu_to_le16(conn->pkt_type); cp.tx_bandwidth = cpu_to_le32(0x00001f40); cp.rx_bandwidth = cpu_to_le32(0x00001f40); cp.content_format = cpu_to_le16(setting); switch (setting & SCO_AIRMODE_MASK) { case SCO_AIRMODE_TRANSP: if (conn->pkt_type & ESCO_2EV3) cp.max_latency = cpu_to_le16(0x0008); else cp.max_latency = cpu_to_le16(0x000D); cp.retrans_effort = 0x02; break; case SCO_AIRMODE_CVSD: cp.max_latency = cpu_to_le16(0xffff); cp.retrans_effort = 0xff; break; default: /* use CVSD settings as fallback */ cp.max_latency = cpu_to_le16(0xffff); cp.retrans_effort = 0xff; break; } hci_send_cmd(hdev, HCI_OP_ACCEPT_SYNC_CONN_REQ, sizeof(cp), &cp); } } static int sco_sock_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, int flags) { struct sock *sk = sock->sk; struct sco_pinfo *pi = sco_pi(sk); if (unlikely(flags & MSG_ERRQUEUE)) return sock_recv_errqueue(sk, msg, len, SOL_BLUETOOTH, BT_SCM_ERROR); lock_sock(sk); if (sk->sk_state == BT_CONNECT2 && test_bit(BT_SK_DEFER_SETUP, &bt_sk(sk)->flags)) { sco_conn_defer_accept(pi->conn->hcon, pi->setting); sk->sk_state = BT_CONFIG; release_sock(sk); return 0; } release_sock(sk); return bt_sock_recvmsg(sock, msg, len, flags); } static int sco_sock_setsockopt(struct socket *sock, int level, int optname, sockptr_t optval, unsigned int optlen) { struct sock *sk = sock->sk; int err = 0; struct bt_voice voice; u32 opt; struct bt_codecs *codecs; struct hci_dev *hdev; __u8 buffer[255]; BT_DBG("sk %p", sk); lock_sock(sk); switch (optname) { case BT_DEFER_SETUP: if (sk->sk_state != BT_BOUND && sk->sk_state != BT_LISTEN) { err = -EINVAL; break; } err = copy_safe_from_sockptr(&opt, sizeof(opt), optval, optlen); if (err) break; if (opt) set_bit(BT_SK_DEFER_SETUP, &bt_sk(sk)->flags); else clear_bit(BT_SK_DEFER_SETUP, &bt_sk(sk)->flags); break; case BT_VOICE: if (sk->sk_state != BT_OPEN && sk->sk_state != BT_BOUND && sk->sk_state != BT_CONNECT2) { err = -EINVAL; break; } voice.setting = sco_pi(sk)->setting; err = copy_safe_from_sockptr(&voice, sizeof(voice), optval, optlen); if (err) break; sco_pi(sk)->setting = voice.setting; hdev = hci_get_route(&sco_pi(sk)->dst, &sco_pi(sk)->src, BDADDR_BREDR); if (!hdev) { err = -EBADFD; break; } switch (sco_pi(sk)->setting & SCO_AIRMODE_MASK) { case SCO_AIRMODE_TRANSP: if (enhanced_sync_conn_capable(hdev)) sco_pi(sk)->codec.id = BT_CODEC_TRANSPARENT; break; } hci_dev_put(hdev); break; case BT_PKT_STATUS: err = copy_safe_from_sockptr(&opt, sizeof(opt), optval, optlen); if (err) break; if (opt) set_bit(BT_SK_PKT_STATUS, &bt_sk(sk)->flags); else clear_bit(BT_SK_PKT_STATUS, &bt_sk(sk)->flags); break; case BT_CODEC: if (sk->sk_state != BT_OPEN && sk->sk_state != BT_BOUND && sk->sk_state != BT_CONNECT2) { err = -EINVAL; break; } hdev = hci_get_route(&sco_pi(sk)->dst, &sco_pi(sk)->src, BDADDR_BREDR); if (!hdev) { err = -EBADFD; break; } if (!hci_dev_test_flag(hdev, HCI_OFFLOAD_CODECS_ENABLED)) { hci_dev_put(hdev); err = -EOPNOTSUPP; break; } if (!hdev->get_data_path_id) { hci_dev_put(hdev); err = -EOPNOTSUPP; break; } if (optlen < sizeof(struct bt_codecs) || optlen > sizeof(buffer)) { hci_dev_put(hdev); err = -EINVAL; break; } err = copy_struct_from_sockptr(buffer, sizeof(buffer), optval, optlen); if (err) { hci_dev_put(hdev); break; } codecs = (void *)buffer; if (codecs->num_codecs > 1) { hci_dev_put(hdev); err = -EINVAL; break; } sco_pi(sk)->codec = codecs->codecs[0]; hci_dev_put(hdev); break; default: err = -ENOPROTOOPT; break; } release_sock(sk); return err; } static int sco_sock_getsockopt_old(struct socket *sock, int optname, char __user *optval, int __user *optlen) { struct sock *sk = sock->sk; struct sco_options opts; struct sco_conninfo cinfo; int err = 0; size_t len; BT_DBG("sk %p", sk); if (get_user(len, optlen)) return -EFAULT; lock_sock(sk); switch (optname) { case SCO_OPTIONS: if (sk->sk_state != BT_CONNECTED && !(sk->sk_state == BT_CONNECT2 && test_bit(BT_SK_DEFER_SETUP, &bt_sk(sk)->flags))) { err = -ENOTCONN; break; } opts.mtu = sco_pi(sk)->conn->mtu; BT_DBG("mtu %u", opts.mtu); len = min(len, sizeof(opts)); if (copy_to_user(optval, (char *)&opts, len)) err = -EFAULT; break; case SCO_CONNINFO: if (sk->sk_state != BT_CONNECTED && !(sk->sk_state == BT_CONNECT2 && test_bit(BT_SK_DEFER_SETUP, &bt_sk(sk)->flags))) { err = -ENOTCONN; break; } memset(&cinfo, 0, sizeof(cinfo)); cinfo.hci_handle = sco_pi(sk)->conn->hcon->handle; memcpy(cinfo.dev_class, sco_pi(sk)->conn->hcon->dev_class, 3); len = min(len, sizeof(cinfo)); if (copy_to_user(optval, (char *)&cinfo, len)) err = -EFAULT; break; default: err = -ENOPROTOOPT; break; } release_sock(sk); return err; } static int sco_sock_getsockopt(struct socket *sock, int level, int optname, char __user *optval, int __user *optlen) { struct sock *sk = sock->sk; int len, err = 0; struct bt_voice voice; u32 phys; int buf_len; struct codec_list *c; u8 num_codecs, i, __user *ptr; struct hci_dev *hdev; struct hci_codec_caps *caps; struct bt_codec codec; BT_DBG("sk %p", sk); if (level == SOL_SCO) return sco_sock_getsockopt_old(sock, optname, optval, optlen); if (get_user(len, optlen)) return -EFAULT; lock_sock(sk); switch (optname) { case BT_DEFER_SETUP: if (sk->sk_state != BT_BOUND && sk->sk_state != BT_LISTEN) { err = -EINVAL; break; } if (put_user(test_bit(BT_SK_DEFER_SETUP, &bt_sk(sk)->flags), (u32 __user *)optval)) err = -EFAULT; break; case BT_VOICE: voice.setting = sco_pi(sk)->setting; len = min_t(unsigned int, len, sizeof(voice)); if (copy_to_user(optval, (char *)&voice, len)) err = -EFAULT; break; case BT_PHY: if (sk->sk_state != BT_CONNECTED) { err = -ENOTCONN; break; } phys = hci_conn_get_phy(sco_pi(sk)->conn->hcon); if (put_user(phys, (u32 __user *) optval)) err = -EFAULT; break; case BT_PKT_STATUS: if (put_user(test_bit(BT_SK_PKT_STATUS, &bt_sk(sk)->flags), (int __user *)optval)) err = -EFAULT; break; case BT_SNDMTU: case BT_RCVMTU: if (sk->sk_state != BT_CONNECTED) { err = -ENOTCONN; break; } if (put_user(sco_pi(sk)->conn->mtu, (u32 __user *)optval)) err = -EFAULT; break; case BT_CODEC: num_codecs = 0; buf_len = 0; hdev = hci_get_route(&sco_pi(sk)->dst, &sco_pi(sk)->src, BDADDR_BREDR); if (!hdev) { err = -EBADFD; break; } if (!hci_dev_test_flag(hdev, HCI_OFFLOAD_CODECS_ENABLED)) { hci_dev_put(hdev); err = -EOPNOTSUPP; break; } if (!hdev->get_data_path_id) { hci_dev_put(hdev); err = -EOPNOTSUPP; break; } release_sock(sk); /* find total buffer size required to copy codec + caps */ hci_dev_lock(hdev); list_for_each_entry(c, &hdev->local_codecs, list) { if (c->transport != HCI_TRANSPORT_SCO_ESCO) continue; num_codecs++; for (i = 0, caps = c->caps; i < c->num_caps; i++) { buf_len += 1 + caps->len; caps = (void *)&caps->data[caps->len]; } buf_len += sizeof(struct bt_codec); } hci_dev_unlock(hdev); buf_len += sizeof(struct bt_codecs); if (buf_len > len) { hci_dev_put(hdev); return -ENOBUFS; } ptr = optval; if (put_user(num_codecs, ptr)) { hci_dev_put(hdev); return -EFAULT; } ptr += sizeof(num_codecs); /* Iterate all the codecs supported over SCO and populate * codec data */ hci_dev_lock(hdev); list_for_each_entry(c, &hdev->local_codecs, list) { if (c->transport != HCI_TRANSPORT_SCO_ESCO) continue; codec.id = c->id; codec.cid = c->cid; codec.vid = c->vid; err = hdev->get_data_path_id(hdev, &codec.data_path); if (err < 0) break; codec.num_caps = c->num_caps; if (copy_to_user(ptr, &codec, sizeof(codec))) { err = -EFAULT; break; } ptr += sizeof(codec); /* find codec capabilities data length */ len = 0; for (i = 0, caps = c->caps; i < c->num_caps; i++) { len += 1 + caps->len; caps = (void *)&caps->data[caps->len]; } /* copy codec capabilities data */ if (len && copy_to_user(ptr, c->caps, len)) { err = -EFAULT; break; } ptr += len; } hci_dev_unlock(hdev); hci_dev_put(hdev); lock_sock(sk); if (!err && put_user(buf_len, optlen)) err = -EFAULT; break; default: err = -ENOPROTOOPT; break; } release_sock(sk); return err; } static int sco_sock_shutdown(struct socket *sock, int how) { struct sock *sk = sock->sk; int err = 0; BT_DBG("sock %p, sk %p", sock, sk); if (!sk) return 0; sock_hold(sk); lock_sock(sk); if (!sk->sk_shutdown) { sk->sk_shutdown = SHUTDOWN_MASK; sco_sock_clear_timer(sk); __sco_sock_close(sk); if (sock_flag(sk, SOCK_LINGER) && sk->sk_lingertime && !(current->flags & PF_EXITING)) err = bt_sock_wait_state(sk, BT_CLOSED, sk->sk_lingertime); } release_sock(sk); sock_put(sk); return err; } static int sco_sock_release(struct socket *sock) { struct sock *sk = sock->sk; int err = 0; BT_DBG("sock %p, sk %p", sock, sk); if (!sk) return 0; sco_sock_close(sk); if (sock_flag(sk, SOCK_LINGER) && READ_ONCE(sk->sk_lingertime) && !(current->flags & PF_EXITING)) { lock_sock(sk); err = bt_sock_wait_state(sk, BT_CLOSED, sk->sk_lingertime); release_sock(sk); } sock_orphan(sk); sco_sock_kill(sk); return err; } static void sco_conn_ready(struct sco_conn *conn) { struct sock *parent; struct sock *sk = conn->sk; BT_DBG("conn %p", conn); if (sk) { lock_sock(sk); sco_sock_clear_timer(sk); sk->sk_state = BT_CONNECTED; sk->sk_state_change(sk); release_sock(sk); } else { sco_conn_lock(conn); if (!conn->hcon) { sco_conn_unlock(conn); return; } parent = sco_get_sock_listen(&conn->hcon->src); if (!parent) { sco_conn_unlock(conn); return; } lock_sock(parent); sk = sco_sock_alloc(sock_net(parent), NULL, BTPROTO_SCO, GFP_ATOMIC, 0); if (!sk) { release_sock(parent); sco_conn_unlock(conn); return; } sco_sock_init(sk, parent); bacpy(&sco_pi(sk)->src, &conn->hcon->src); bacpy(&sco_pi(sk)->dst, &conn->hcon->dst); sco_conn_hold(conn); hci_conn_hold(conn->hcon); __sco_chan_add(conn, sk, parent); if (test_bit(BT_SK_DEFER_SETUP, &bt_sk(parent)->flags)) sk->sk_state = BT_CONNECT2; else sk->sk_state = BT_CONNECTED; /* Wake up parent */ parent->sk_data_ready(parent); release_sock(parent); sco_conn_unlock(conn); } } /* ----- SCO interface with lower layer (HCI) ----- */ int sco_connect_ind(struct hci_dev *hdev, bdaddr_t *bdaddr, __u8 *flags) { struct sock *sk; int lm = 0; BT_DBG("hdev %s, bdaddr %pMR", hdev->name, bdaddr); /* Find listening sockets */ read_lock(&sco_sk_list.lock); sk_for_each(sk, &sco_sk_list.head) { if (sk->sk_state != BT_LISTEN) continue; if (!bacmp(&sco_pi(sk)->src, &hdev->bdaddr) || !bacmp(&sco_pi(sk)->src, BDADDR_ANY)) { lm |= HCI_LM_ACCEPT; if (test_bit(BT_SK_DEFER_SETUP, &bt_sk(sk)->flags)) *flags |= HCI_PROTO_DEFER; break; } } read_unlock(&sco_sk_list.lock); return lm; } static void sco_connect_cfm(struct hci_conn *hcon, __u8 status) { if (hcon->type != SCO_LINK && hcon->type != ESCO_LINK) return; BT_DBG("hcon %p bdaddr %pMR status %u", hcon, &hcon->dst, status); if (!status) { struct sco_conn *conn; conn = sco_conn_add(hcon); if (conn) { sco_conn_ready(conn); sco_conn_put(conn); } } else sco_conn_del(hcon, bt_to_errno(status)); } static void sco_disconn_cfm(struct hci_conn *hcon, __u8 reason) { if (hcon->type != SCO_LINK && hcon->type != ESCO_LINK) return; BT_DBG("hcon %p reason %d", hcon, reason); sco_conn_del(hcon, bt_to_errno(reason)); } void sco_recv_scodata(struct hci_conn *hcon, struct sk_buff *skb) { struct sco_conn *conn = hcon->sco_data; if (!conn) goto drop; BT_DBG("conn %p len %u", conn, skb->len); if (skb->len) { sco_recv_frame(conn, skb); return; } drop: kfree_skb(skb); } static struct hci_cb sco_cb = { .name = "SCO", .connect_cfm = sco_connect_cfm, .disconn_cfm = sco_disconn_cfm, }; static int sco_debugfs_show(struct seq_file *f, void *p) { struct sock *sk; read_lock(&sco_sk_list.lock); sk_for_each(sk, &sco_sk_list.head) { seq_printf(f, "%pMR %pMR %d\n", &sco_pi(sk)->src, &sco_pi(sk)->dst, sk->sk_state); } read_unlock(&sco_sk_list.lock); return 0; } DEFINE_SHOW_ATTRIBUTE(sco_debugfs); static struct dentry *sco_debugfs; static const struct proto_ops sco_sock_ops = { .family = PF_BLUETOOTH, .owner = THIS_MODULE, .release = sco_sock_release, .bind = sco_sock_bind, .connect = sco_sock_connect, .listen = sco_sock_listen, .accept = sco_sock_accept, .getname = sco_sock_getname, .sendmsg = sco_sock_sendmsg, .recvmsg = sco_sock_recvmsg, .poll = bt_sock_poll, .ioctl = bt_sock_ioctl, .gettstamp = sock_gettstamp, .mmap = sock_no_mmap, .socketpair = sock_no_socketpair, .shutdown = sco_sock_shutdown, .setsockopt = sco_sock_setsockopt, .getsockopt = sco_sock_getsockopt }; static const struct net_proto_family sco_sock_family_ops = { .family = PF_BLUETOOTH, .owner = THIS_MODULE, .create = sco_sock_create, }; int __init sco_init(void) { int err; BUILD_BUG_ON(sizeof(struct sockaddr_sco) > sizeof(struct sockaddr)); err = proto_register(&sco_proto, 0); if (err < 0) return err; err = bt_sock_register(BTPROTO_SCO, &sco_sock_family_ops); if (err < 0) { BT_ERR("SCO socket registration failed"); goto error; } err = bt_procfs_init(&init_net, "sco", &sco_sk_list, NULL); if (err < 0) { BT_ERR("Failed to create SCO proc file"); bt_sock_unregister(BTPROTO_SCO); goto error; } BT_INFO("SCO socket layer initialized"); hci_register_cb(&sco_cb); if (IS_ERR_OR_NULL(bt_debugfs)) return 0; sco_debugfs = debugfs_create_file("sco", 0444, bt_debugfs, NULL, &sco_debugfs_fops); return 0; error: proto_unregister(&sco_proto); return err; } void sco_exit(void) { bt_procfs_cleanup(&init_net, "sco"); debugfs_remove(sco_debugfs); hci_unregister_cb(&sco_cb); bt_sock_unregister(BTPROTO_SCO); proto_unregister(&sco_proto); } module_param(disable_esco, bool, 0644); MODULE_PARM_DESC(disable_esco, "Disable eSCO connection creation"); |
| 135 135 134 71 135 135 135 135 135 135 135 4 135 1 5 1 135 134 135 135 135 4 4 2 2 4 2 4 4 4 4 4 2 4 3 2 4 135 10 9 3 2 8 10 8 1 6 1 5 27 26 26 26 26 26 25 24 24 22 22 21 11 11 9 9 10 9 9 8 7 4 7 3 5 5 10 10 9 8 6 10 9 8 8 8 1 29 8 7 6 5 5 1 3 8 2 2 1 2 1 2 1 2 2 2 2 2 4 4 1 1 1 1 1 2 2 2 2 8 1 1 1 1 1 8 3 29 27 7 7 5 2 3 5 4 4 4 4 4 3 3 2 3 4 4 3 2 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-only /* * binfmt_misc.c * * Copyright (C) 1997 Richard Günther * * binfmt_misc detects binaries via a magic or filename extension and invokes * a specified wrapper. See Documentation/admin-guide/binfmt-misc.rst for more details. */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/kernel.h> #include <linux/module.h> #include <linux/init.h> #include <linux/sched/mm.h> #include <linux/magic.h> #include <linux/binfmts.h> #include <linux/slab.h> #include <linux/ctype.h> #include <linux/string_helpers.h> #include <linux/file.h> #include <linux/pagemap.h> #include <linux/namei.h> #include <linux/mount.h> #include <linux/fs_context.h> #include <linux/syscalls.h> #include <linux/fs.h> #include <linux/uaccess.h> #include "internal.h" #ifdef DEBUG # define USE_DEBUG 1 #else # define USE_DEBUG 0 #endif enum { VERBOSE_STATUS = 1 /* make it zero to save 400 bytes kernel memory */ }; enum {Enabled, Magic}; #define MISC_FMT_PRESERVE_ARGV0 (1UL << 31) #define MISC_FMT_OPEN_BINARY (1UL << 30) #define MISC_FMT_CREDENTIALS (1UL << 29) #define MISC_FMT_OPEN_FILE (1UL << 28) typedef struct { struct list_head list; unsigned long flags; /* type, status, etc. */ int offset; /* offset of magic */ int size; /* size of magic/mask */ char *magic; /* magic or filename extension */ char *mask; /* mask, NULL for exact match */ const char *interpreter; /* filename of interpreter */ char *name; struct dentry *dentry; struct file *interp_file; refcount_t users; /* sync removal with load_misc_binary() */ } Node; static struct file_system_type bm_fs_type; /* * Max length of the register string. Determined by: * - 7 delimiters * - name: ~50 bytes * - type: 1 byte * - offset: 3 bytes (has to be smaller than BINPRM_BUF_SIZE) * - magic: 128 bytes (512 in escaped form) * - mask: 128 bytes (512 in escaped form) * - interp: ~50 bytes * - flags: 5 bytes * Round that up a bit, and then back off to hold the internal data * (like struct Node). */ #define MAX_REGISTER_LENGTH 1920 /** * search_binfmt_handler - search for a binary handler for @bprm * @misc: handle to binfmt_misc instance * @bprm: binary for which we are looking for a handler * * Search for a binary type handler for @bprm in the list of registered binary * type handlers. * * Return: binary type list entry on success, NULL on failure */ static Node *search_binfmt_handler(struct binfmt_misc *misc, struct linux_binprm *bprm) { char *p = strrchr(bprm->interp, '.'); Node *e; /* Walk all the registered handlers. */ list_for_each_entry(e, &misc->entries, list) { char *s; int j; /* Make sure this one is currently enabled. */ if (!test_bit(Enabled, &e->flags)) continue; /* Do matching based on extension if applicable. */ if (!test_bit(Magic, &e->flags)) { if (p && !strcmp(e->magic, p + 1)) return e; continue; } /* Do matching based on magic & mask. */ s = bprm->buf + e->offset; if (e->mask) { for (j = 0; j < e->size; j++) if ((*s++ ^ e->magic[j]) & e->mask[j]) break; } else { for (j = 0; j < e->size; j++) if ((*s++ ^ e->magic[j])) break; } if (j == e->size) return e; } return NULL; } /** * get_binfmt_handler - try to find a binary type handler * @misc: handle to binfmt_misc instance * @bprm: binary for which we are looking for a handler * * Try to find a binfmt handler for the binary type. If one is found take a * reference to protect against removal via bm_{entry,status}_write(). * * Return: binary type list entry on success, NULL on failure */ static Node *get_binfmt_handler(struct binfmt_misc *misc, struct linux_binprm *bprm) { Node *e; read_lock(&misc->entries_lock); e = search_binfmt_handler(misc, bprm); if (e) refcount_inc(&e->users); read_unlock(&misc->entries_lock); return e; } /** * put_binfmt_handler - put binary handler node * @e: node to put * * Free node syncing with load_misc_binary() and defer final free to * load_misc_binary() in case it is using the binary type handler we were * requested to remove. */ static void put_binfmt_handler(Node *e) { if (refcount_dec_and_test(&e->users)) { if (e->flags & MISC_FMT_OPEN_FILE) filp_close(e->interp_file, NULL); kfree(e); } } /** * load_binfmt_misc - load the binfmt_misc of the caller's user namespace * * To be called in load_misc_binary() to load the relevant struct binfmt_misc. * If a user namespace doesn't have its own binfmt_misc mount it can make use * of its ancestor's binfmt_misc handlers. This mimicks the behavior of * pre-namespaced binfmt_misc where all registered binfmt_misc handlers where * available to all user and user namespaces on the system. * * Return: the binfmt_misc instance of the caller's user namespace */ static struct binfmt_misc *load_binfmt_misc(void) { const struct user_namespace *user_ns; struct binfmt_misc *misc; user_ns = current_user_ns(); while (user_ns) { /* Pairs with smp_store_release() in bm_fill_super(). */ misc = smp_load_acquire(&user_ns->binfmt_misc); if (misc) return misc; user_ns = user_ns->parent; } return &init_binfmt_misc; } /* * the loader itself */ static int load_misc_binary(struct linux_binprm *bprm) { Node *fmt; struct file *interp_file = NULL; int retval = -ENOEXEC; struct binfmt_misc *misc; misc = load_binfmt_misc(); if (!misc->enabled) return retval; fmt = get_binfmt_handler(misc, bprm); if (!fmt) return retval; /* Need to be able to load the file after exec */ retval = -ENOENT; if (bprm->interp_flags & BINPRM_FLAGS_PATH_INACCESSIBLE) goto ret; if (fmt->flags & MISC_FMT_PRESERVE_ARGV0) { bprm->interp_flags |= BINPRM_FLAGS_PRESERVE_ARGV0; } else { retval = remove_arg_zero(bprm); if (retval) goto ret; } if (fmt->flags & MISC_FMT_OPEN_BINARY) bprm->have_execfd = 1; /* make argv[1] be the path to the binary */ retval = copy_string_kernel(bprm->interp, bprm); if (retval < 0) goto ret; bprm->argc++; /* add the interp as argv[0] */ retval = copy_string_kernel(fmt->interpreter, bprm); if (retval < 0) goto ret; bprm->argc++; /* Update interp in case binfmt_script needs it. */ retval = bprm_change_interp(fmt->interpreter, bprm); if (retval < 0) goto ret; if (fmt->flags & MISC_FMT_OPEN_FILE) { interp_file = file_clone_open(fmt->interp_file); if (!IS_ERR(interp_file)) deny_write_access(interp_file); } else { interp_file = open_exec(fmt->interpreter); } retval = PTR_ERR(interp_file); if (IS_ERR(interp_file)) goto ret; bprm->interpreter = interp_file; if (fmt->flags & MISC_FMT_CREDENTIALS) bprm->execfd_creds = 1; retval = 0; ret: /* * If we actually put the node here all concurrent calls to * load_misc_binary() will have finished. We also know * that for the refcount to be zero someone must have concurently * removed the binary type handler from the list and it's our job to * free it. */ put_binfmt_handler(fmt); return retval; } /* Command parsers */ /* * parses and copies one argument enclosed in del from *sp to *dp, * recognising the \x special. * returns pointer to the copied argument or NULL in case of an * error (and sets err) or null argument length. */ static char *scanarg(char *s, char del) { char c; while ((c = *s++) != del) { if (c == '\\' && *s == 'x') { s++; if (!isxdigit(*s++)) return NULL; if (!isxdigit(*s++)) return NULL; } } s[-1] ='\0'; return s; } static char *check_special_flags(char *sfs, Node *e) { char *p = sfs; int cont = 1; /* special flags */ while (cont) { switch (*p) { case 'P': pr_debug("register: flag: P (preserve argv0)\n"); p++; e->flags |= MISC_FMT_PRESERVE_ARGV0; break; case 'O': pr_debug("register: flag: O (open binary)\n"); p++; e->flags |= MISC_FMT_OPEN_BINARY; break; case 'C': pr_debug("register: flag: C (preserve creds)\n"); p++; /* this flags also implies the open-binary flag */ e->flags |= (MISC_FMT_CREDENTIALS | MISC_FMT_OPEN_BINARY); break; case 'F': pr_debug("register: flag: F: open interpreter file now\n"); p++; e->flags |= MISC_FMT_OPEN_FILE; break; default: cont = 0; } } return p; } /* * This registers a new binary format, it recognises the syntax * ':name:type:offset:magic:mask:interpreter:flags' * where the ':' is the IFS, that can be chosen with the first char */ static Node *create_entry(const char __user *buffer, size_t count) { Node *e; int memsize, err; char *buf, *p; char del; pr_debug("register: received %zu bytes\n", count); /* some sanity checks */ err = -EINVAL; if ((count < 11) || (count > MAX_REGISTER_LENGTH)) goto out; err = -ENOMEM; memsize = sizeof(Node) + count + 8; e = kmalloc(memsize, GFP_KERNEL_ACCOUNT); if (!e) goto out; p = buf = (char *)e + sizeof(Node); memset(e, 0, sizeof(Node)); if (copy_from_user(buf, buffer, count)) goto efault; del = *p++; /* delimeter */ pr_debug("register: delim: %#x {%c}\n", del, del); /* Pad the buffer with the delim to simplify parsing below. */ memset(buf + count, del, 8); /* Parse the 'name' field. */ e->name = p; p = strchr(p, del); if (!p) goto einval; *p++ = '\0'; if (!e->name[0] || !strcmp(e->name, ".") || !strcmp(e->name, "..") || strchr(e->name, '/')) goto einval; pr_debug("register: name: {%s}\n", e->name); /* Parse the 'type' field. */ switch (*p++) { case 'E': pr_debug("register: type: E (extension)\n"); e->flags = 1 << Enabled; break; case 'M': pr_debug("register: type: M (magic)\n"); e->flags = (1 << Enabled) | (1 << Magic); break; default: goto einval; } if (*p++ != del) goto einval; if (test_bit(Magic, &e->flags)) { /* Handle the 'M' (magic) format. */ char *s; /* Parse the 'offset' field. */ s = strchr(p, del); if (!s) goto einval; *s = '\0'; if (p != s) { int r = kstrtoint(p, 10, &e->offset); if (r != 0 || e->offset < 0) goto einval; } p = s; if (*p++) goto einval; pr_debug("register: offset: %#x\n", e->offset); /* Parse the 'magic' field. */ e->magic = p; p = scanarg(p, del); if (!p) goto einval; if (!e->magic[0]) goto einval; if (USE_DEBUG) print_hex_dump_bytes( KBUILD_MODNAME ": register: magic[raw]: ", DUMP_PREFIX_NONE, e->magic, p - e->magic); /* Parse the 'mask' field. */ e->mask = p; p = scanarg(p, del); if (!p) goto einval; if (!e->mask[0]) { e->mask = NULL; pr_debug("register: mask[raw]: none\n"); } else if (USE_DEBUG) print_hex_dump_bytes( KBUILD_MODNAME ": register: mask[raw]: ", DUMP_PREFIX_NONE, e->mask, p - e->mask); /* * Decode the magic & mask fields. * Note: while we might have accepted embedded NUL bytes from * above, the unescape helpers here will stop at the first one * it encounters. */ e->size = string_unescape_inplace(e->magic, UNESCAPE_HEX); if (e->mask && string_unescape_inplace(e->mask, UNESCAPE_HEX) != e->size) goto einval; if (e->size > BINPRM_BUF_SIZE || BINPRM_BUF_SIZE - e->size < e->offset) goto einval; pr_debug("register: magic/mask length: %i\n", e->size); if (USE_DEBUG) { print_hex_dump_bytes( KBUILD_MODNAME ": register: magic[decoded]: ", DUMP_PREFIX_NONE, e->magic, e->size); if (e->mask) { int i; char *masked = kmalloc(e->size, GFP_KERNEL_ACCOUNT); print_hex_dump_bytes( KBUILD_MODNAME ": register: mask[decoded]: ", DUMP_PREFIX_NONE, e->mask, e->size); if (masked) { for (i = 0; i < e->size; ++i) masked[i] = e->magic[i] & e->mask[i]; print_hex_dump_bytes( KBUILD_MODNAME ": register: magic[masked]: ", DUMP_PREFIX_NONE, masked, e->size); kfree(masked); } } } } else { /* Handle the 'E' (extension) format. */ /* Skip the 'offset' field. */ p = strchr(p, del); if (!p) goto einval; *p++ = '\0'; /* Parse the 'magic' field. */ e->magic = p; p = strchr(p, del); if (!p) goto einval; *p++ = '\0'; if (!e->magic[0] || strchr(e->magic, '/')) goto einval; pr_debug("register: extension: {%s}\n", e->magic); /* Skip the 'mask' field. */ p = strchr(p, del); if (!p) goto einval; *p++ = '\0'; } /* Parse the 'interpreter' field. */ e->interpreter = p; p = strchr(p, del); if (!p) goto einval; *p++ = '\0'; if (!e->interpreter[0]) goto einval; pr_debug("register: interpreter: {%s}\n", e->interpreter); /* Parse the 'flags' field. */ p = check_special_flags(p, e); if (*p == '\n') p++; if (p != buf + count) goto einval; return e; out: return ERR_PTR(err); efault: kfree(e); return ERR_PTR(-EFAULT); einval: kfree(e); return ERR_PTR(-EINVAL); } /* * Set status of entry/binfmt_misc: * '1' enables, '0' disables and '-1' clears entry/binfmt_misc */ static int parse_command(const char __user *buffer, size_t count) { char s[4]; if (count > 3) return -EINVAL; if (copy_from_user(s, buffer, count)) return -EFAULT; if (!count) return 0; if (s[count - 1] == '\n') count--; if (count == 1 && s[0] == '0') return 1; if (count == 1 && s[0] == '1') return 2; if (count == 2 && s[0] == '-' && s[1] == '1') return 3; return -EINVAL; } /* generic stuff */ static void entry_status(Node *e, char *page) { char *dp = page; const char *status = "disabled"; if (test_bit(Enabled, &e->flags)) status = "enabled"; if (!VERBOSE_STATUS) { sprintf(page, "%s\n", status); return; } dp += sprintf(dp, "%s\ninterpreter %s\n", status, e->interpreter); /* print the special flags */ dp += sprintf(dp, "flags: "); if (e->flags & MISC_FMT_PRESERVE_ARGV0) *dp++ = 'P'; if (e->flags & MISC_FMT_OPEN_BINARY) *dp++ = 'O'; if (e->flags & MISC_FMT_CREDENTIALS) *dp++ = 'C'; if (e->flags & MISC_FMT_OPEN_FILE) *dp++ = 'F'; *dp++ = '\n'; if (!test_bit(Magic, &e->flags)) { sprintf(dp, "extension .%s\n", e->magic); } else { dp += sprintf(dp, "offset %i\nmagic ", e->offset); dp = bin2hex(dp, e->magic, e->size); if (e->mask) { dp += sprintf(dp, "\nmask "); dp = bin2hex(dp, e->mask, e->size); } *dp++ = '\n'; *dp = '\0'; } } static struct inode *bm_get_inode(struct super_block *sb, int mode) { struct inode *inode = new_inode(sb); if (inode) { inode->i_ino = get_next_ino(); inode->i_mode = mode; simple_inode_init_ts(inode); } return inode; } /** * i_binfmt_misc - retrieve struct binfmt_misc from a binfmt_misc inode * @inode: inode of the relevant binfmt_misc instance * * This helper retrieves struct binfmt_misc from a binfmt_misc inode. This can * be done without any memory barriers because we are guaranteed that * user_ns->binfmt_misc is fully initialized. It was fully initialized when the * binfmt_misc mount was first created. * * Return: struct binfmt_misc of the relevant binfmt_misc instance */ static struct binfmt_misc *i_binfmt_misc(struct inode *inode) { return inode->i_sb->s_user_ns->binfmt_misc; } /** * bm_evict_inode - cleanup data associated with @inode * @inode: inode to which the data is attached * * Cleanup the binary type handler data associated with @inode if a binary type * entry is removed or the filesystem is unmounted and the super block is * shutdown. * * If the ->evict call was not caused by a super block shutdown but by a write * to remove the entry or all entries via bm_{entry,status}_write() the entry * will have already been removed from the list. We keep the list_empty() check * to make that explicit. */ static void bm_evict_inode(struct inode *inode) { Node *e = inode->i_private; clear_inode(inode); if (e) { struct binfmt_misc *misc; misc = i_binfmt_misc(inode); write_lock(&misc->entries_lock); if (!list_empty(&e->list)) list_del_init(&e->list); write_unlock(&misc->entries_lock); put_binfmt_handler(e); } } /** * remove_binfmt_handler - remove a binary type handler * @misc: handle to binfmt_misc instance * @e: binary type handler to remove * * Remove a binary type handler from the list of binary type handlers and * remove its associated dentry. This is called from * binfmt_{entry,status}_write(). In the future, we might want to think about * adding a proper ->unlink() method to binfmt_misc instead of forcing caller's * to use writes to files in order to delete binary type handlers. But it has * worked for so long that it's not a pressing issue. */ static void remove_binfmt_handler(struct binfmt_misc *misc, Node *e) { write_lock(&misc->entries_lock); list_del_init(&e->list); write_unlock(&misc->entries_lock); locked_recursive_removal(e->dentry, NULL); } /* /<entry> */ static ssize_t bm_entry_read(struct file *file, char __user *buf, size_t nbytes, loff_t *ppos) { Node *e = file_inode(file)->i_private; ssize_t res; char *page; page = (char *) __get_free_page(GFP_KERNEL); if (!page) return -ENOMEM; entry_status(e, page); res = simple_read_from_buffer(buf, nbytes, ppos, page, strlen(page)); free_page((unsigned long) page); return res; } static ssize_t bm_entry_write(struct file *file, const char __user *buffer, size_t count, loff_t *ppos) { struct inode *inode = file_inode(file); Node *e = inode->i_private; int res = parse_command(buffer, count); switch (res) { case 1: /* Disable this handler. */ clear_bit(Enabled, &e->flags); break; case 2: /* Enable this handler. */ set_bit(Enabled, &e->flags); break; case 3: /* Delete this handler. */ inode = d_inode(inode->i_sb->s_root); inode_lock_nested(inode, I_MUTEX_PARENT); /* * In order to add new element or remove elements from the list * via bm_{entry,register,status}_write() inode_lock() on the * root inode must be held. * The lock is exclusive ensuring that the list can't be * modified. Only load_misc_binary() can access but does so * read-only. So we only need to take the write lock when we * actually remove the entry from the list. */ if (!list_empty(&e->list)) remove_binfmt_handler(i_binfmt_misc(inode), e); inode_unlock(inode); break; default: return res; } return count; } static const struct file_operations bm_entry_operations = { .read = bm_entry_read, .write = bm_entry_write, .llseek = default_llseek, }; /* /register */ static ssize_t bm_register_write(struct file *file, const char __user *buffer, size_t count, loff_t *ppos) { Node *e; struct inode *inode; struct super_block *sb = file_inode(file)->i_sb; struct dentry *root = sb->s_root, *dentry; struct binfmt_misc *misc; int err = 0; struct file *f = NULL; e = create_entry(buffer, count); if (IS_ERR(e)) return PTR_ERR(e); if (e->flags & MISC_FMT_OPEN_FILE) { const struct cred *old_cred; /* * Now that we support unprivileged binfmt_misc mounts make * sure we use the credentials that the register @file was * opened with to also open the interpreter. Before that this * didn't matter much as only a privileged process could open * the register file. */ old_cred = override_creds(file->f_cred); f = open_exec(e->interpreter); revert_creds(old_cred); if (IS_ERR(f)) { pr_notice("register: failed to install interpreter file %s\n", e->interpreter); kfree(e); return PTR_ERR(f); } e->interp_file = f; } inode_lock(d_inode(root)); dentry = lookup_noperm(&QSTR(e->name), root); err = PTR_ERR(dentry); if (IS_ERR(dentry)) goto out; err = -EEXIST; if (d_really_is_positive(dentry)) goto out2; inode = bm_get_inode(sb, S_IFREG | 0644); err = -ENOMEM; if (!inode) goto out2; refcount_set(&e->users, 1); e->dentry = dget(dentry); inode->i_private = e; inode->i_fop = &bm_entry_operations; d_instantiate(dentry, inode); misc = i_binfmt_misc(inode); write_lock(&misc->entries_lock); list_add(&e->list, &misc->entries); write_unlock(&misc->entries_lock); err = 0; out2: dput(dentry); out: inode_unlock(d_inode(root)); if (err) { if (f) filp_close(f, NULL); kfree(e); return err; } return count; } static const struct file_operations bm_register_operations = { .write = bm_register_write, .llseek = noop_llseek, }; /* /status */ static ssize_t bm_status_read(struct file *file, char __user *buf, size_t nbytes, loff_t *ppos) { struct binfmt_misc *misc; char *s; misc = i_binfmt_misc(file_inode(file)); s = misc->enabled ? "enabled\n" : "disabled\n"; return simple_read_from_buffer(buf, nbytes, ppos, s, strlen(s)); } static ssize_t bm_status_write(struct file *file, const char __user *buffer, size_t count, loff_t *ppos) { struct binfmt_misc *misc; int res = parse_command(buffer, count); Node *e, *next; struct inode *inode; misc = i_binfmt_misc(file_inode(file)); switch (res) { case 1: /* Disable all handlers. */ misc->enabled = false; break; case 2: /* Enable all handlers. */ misc->enabled = true; break; case 3: /* Delete all handlers. */ inode = d_inode(file_inode(file)->i_sb->s_root); inode_lock_nested(inode, I_MUTEX_PARENT); /* * In order to add new element or remove elements from the list * via bm_{entry,register,status}_write() inode_lock() on the * root inode must be held. * The lock is exclusive ensuring that the list can't be * modified. Only load_misc_binary() can access but does so * read-only. So we only need to take the write lock when we * actually remove the entry from the list. */ list_for_each_entry_safe(e, next, &misc->entries, list) remove_binfmt_handler(misc, e); inode_unlock(inode); break; default: return res; } return count; } static const struct file_operations bm_status_operations = { .read = bm_status_read, .write = bm_status_write, .llseek = default_llseek, }; /* Superblock handling */ static void bm_put_super(struct super_block *sb) { struct user_namespace *user_ns = sb->s_fs_info; sb->s_fs_info = NULL; put_user_ns(user_ns); } static const struct super_operations s_ops = { .statfs = simple_statfs, .evict_inode = bm_evict_inode, .put_super = bm_put_super, }; static int bm_fill_super(struct super_block *sb, struct fs_context *fc) { int err; struct user_namespace *user_ns = sb->s_user_ns; struct binfmt_misc *misc; static const struct tree_descr bm_files[] = { [2] = {"status", &bm_status_operations, S_IWUSR|S_IRUGO}, [3] = {"register", &bm_register_operations, S_IWUSR}, /* last one */ {""} }; if (WARN_ON(user_ns != current_user_ns())) return -EINVAL; /* * Lazily allocate a new binfmt_misc instance for this namespace, i.e. * do it here during the first mount of binfmt_misc. We don't need to * waste memory for every user namespace allocation. It's likely much * more common to not mount a separate binfmt_misc instance than it is * to mount one. * * While multiple superblocks can exist they are keyed by userns in * s_fs_info for binfmt_misc. Hence, the vfs guarantees that * bm_fill_super() is called exactly once whenever a binfmt_misc * superblock for a userns is created. This in turn lets us conclude * that when a binfmt_misc superblock is created for the first time for * a userns there's no one racing us. Therefore we don't need any * barriers when we dereference binfmt_misc. */ misc = user_ns->binfmt_misc; if (!misc) { /* * If it turns out that most user namespaces actually want to * register their own binary type handler and therefore all * create their own separate binfmt_misc mounts we should * consider turning this into a kmem cache. */ misc = kzalloc(sizeof(struct binfmt_misc), GFP_KERNEL); if (!misc) return -ENOMEM; INIT_LIST_HEAD(&misc->entries); rwlock_init(&misc->entries_lock); /* Pairs with smp_load_acquire() in load_binfmt_misc(). */ smp_store_release(&user_ns->binfmt_misc, misc); } /* * When the binfmt_misc superblock for this userns is shutdown * ->enabled might have been set to false and we don't reinitialize * ->enabled again in put_super() as someone might already be mounting * binfmt_misc again. It also would be pointless since by the time * ->put_super() is called we know that the binary type list for this * bintfmt_misc mount is empty making load_misc_binary() return * -ENOEXEC independent of whether ->enabled is true. Instead, if * someone mounts binfmt_misc for the first time or again we simply * reset ->enabled to true. */ misc->enabled = true; err = simple_fill_super(sb, BINFMTFS_MAGIC, bm_files); if (!err) sb->s_op = &s_ops; return err; } static void bm_free(struct fs_context *fc) { if (fc->s_fs_info) put_user_ns(fc->s_fs_info); } static int bm_get_tree(struct fs_context *fc) { return get_tree_keyed(fc, bm_fill_super, get_user_ns(fc->user_ns)); } static const struct fs_context_operations bm_context_ops = { .free = bm_free, .get_tree = bm_get_tree, }; static int bm_init_fs_context(struct fs_context *fc) { fc->ops = &bm_context_ops; return 0; } static struct linux_binfmt misc_format = { .module = THIS_MODULE, .load_binary = load_misc_binary, }; static struct file_system_type bm_fs_type = { .owner = THIS_MODULE, .name = "binfmt_misc", .init_fs_context = bm_init_fs_context, .fs_flags = FS_USERNS_MOUNT, .kill_sb = kill_litter_super, }; MODULE_ALIAS_FS("binfmt_misc"); static int __init init_misc_binfmt(void) { int err = register_filesystem(&bm_fs_type); if (!err) insert_binfmt(&misc_format); return err; } static void __exit exit_misc_binfmt(void) { unregister_binfmt(&misc_format); unregister_filesystem(&bm_fs_type); } core_initcall(init_misc_binfmt); module_exit(exit_misc_binfmt); MODULE_DESCRIPTION("Kernel support for miscellaneous binaries"); MODULE_LICENSE("GPL"); |
| 11 46 44 16 58 43 19 6 6 13 193 | 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 | /* SPDX-License-Identifier: GPL-2.0 */ /* * Copyright (c) 2000,2002-2003,2005 Silicon Graphics, Inc. * All Rights Reserved. */ #ifndef __XFS_ATTR_H__ #define __XFS_ATTR_H__ struct xfs_inode; struct xfs_da_args; struct xfs_attr_list_context; /* * Large attribute lists are structured around Btrees where all the data * elements are in the leaf nodes. Attribute names are hashed into an int, * then that int is used as the index into the Btree. Since the hashval * of an attribute name may not be unique, we may have duplicate keys. * The internal links in the Btree are logical block offsets into the file. * * Small attribute lists use a different format and are packed as tightly * as possible so as to fit into the literal area of the inode. */ /* * The maximum size (into the kernel or returned from the kernel) of an * attribute value or the buffer used for an attr_list() call. Larger * sizes will result in an ERANGE return code. */ #define ATTR_MAX_VALUELEN (64*1024) /* max length of a value */ /* * Kernel-internal version of the attrlist cursor. */ struct xfs_attrlist_cursor_kern { __u32 hashval; /* hash value of next entry to add */ __u32 blkno; /* block containing entry (suggestion) */ __u32 offset; /* offset in list of equal-hashvals */ __u16 pad1; /* padding to match user-level */ __u8 pad2; /* padding to match user-level */ __u8 initted; /* T/F: cursor has been initialized */ }; /*======================================================================== * Structure used to pass context around among the routines. *========================================================================*/ /* void; state communicated via *context */ typedef void (*put_listent_func_t)(struct xfs_attr_list_context *context, int flags, unsigned char *name, int namelen, void *value, int valuelen); struct xfs_attr_list_context { struct xfs_trans *tp; struct xfs_inode *dp; /* inode */ struct xfs_attrlist_cursor_kern cursor; /* position in list */ void *buffer; /* output buffer */ /* * Abort attribute list iteration if non-zero. Can be used to pass * error values to the xfs_attr_list caller. */ int seen_enough; bool allow_incomplete; ssize_t count; /* num used entries */ int dupcnt; /* count dup hashvals seen */ int bufsize; /* total buffer size */ int firstu; /* first used byte in buffer */ unsigned int attr_filter; /* XFS_ATTR_{ROOT,SECURE} */ int resynch; /* T/F: resynch with cursor */ put_listent_func_t put_listent; /* list output fmt function */ int index; /* index into output buffer */ }; /* * ======================================================================== * Structure used to pass context around among the delayed routines. * ======================================================================== */ /* * Below is a state machine diagram for attr remove operations. The XFS_DAS_* * states indicate places where the function would return -EAGAIN, and then * immediately resume from after being called by the calling function. States * marked as a "subroutine state" indicate that they belong to a subroutine, and * so the calling function needs to pass them back to that subroutine to allow * it to finish where it left off. But they otherwise do not have a role in the * calling function other than just passing through. * * xfs_attr_remove_iter() * │ * v * have attr to remove? ──n──> done * │ * y * │ * v * are we short form? ──y──> xfs_attr_shortform_remove ──> done * │ * n * │ * V * are we leaf form? ──y──> xfs_attr_leaf_removename ──> done * │ * n * │ * V * ┌── need to setup state? * │ │ * n y * │ │ * │ v * │ find attr and get state * │ attr has remote blks? ──n─┐ * │ │ v * │ │ find and invalidate * │ y the remote blocks. * │ │ mark attr incomplete * │ ├────────────────┘ * └──────────┤ * │ * v * Have remote blks to remove? ───y─────┐ * │ ^ remove the blks * │ │ │ * │ │ v * │ XFS_DAS_RMTBLK <─n── done? * │ re-enter with │ * │ one less blk to y * │ remove │ * │ V * │ refill the state * n │ * │ v * │ XFS_DAS_RM_NAME * │ │ * ├─────────────────────────┘ * │ * v * remove leaf and * update hash with * xfs_attr_node_remove_cleanup * │ * v * need to * shrink tree? ─n─┐ * │ │ * y │ * │ │ * v │ * join leaf │ * │ │ * v │ * XFS_DAS_RM_SHRINK │ * │ │ * v │ * do the shrink │ * │ │ * v │ * free state <──┘ * │ * v * done * * * Below is a state machine diagram for attr set operations. * * It seems the challenge with understanding this system comes from trying to * absorb the state machine all at once, when really one should only be looking * at it with in the context of a single function. Once a state sensitive * function is called, the idea is that it "takes ownership" of the * state machine. It isn't concerned with the states that may have belonged to * it's calling parent. Only the states relevant to itself or any other * subroutines there in. Once a calling function hands off the state machine to * a subroutine, it needs to respect the simple rule that it doesn't "own" the * state machine anymore, and it's the responsibility of that calling function * to propagate the -EAGAIN back up the call stack. Upon reentry, it is * committed to re-calling that subroutine until it returns something other than * -EAGAIN. Once that subroutine signals completion (by returning anything other * than -EAGAIN), the calling function can resume using the state machine. * * xfs_attr_set_iter() * │ * v * ┌─y─ has an attr fork? * │ | * │ n * │ | * │ V * │ add a fork * │ │ * └──────────┤ * │ * V * ┌─── is shortform? * │ │ * │ y * │ │ * │ V * │ xfs_attr_set_fmt * │ | * │ V * │ xfs_attr_try_sf_addname * │ │ * │ V * │ had enough ──y──> done * │ space? * n │ * │ n * │ │ * │ V * │ transform to leaf * │ │ * │ V * │ hold the leaf buffer * │ │ * │ V * │ return -EAGAIN * │ Re-enter in * │ leaf form * │ * └─> release leaf buffer * if needed * │ * V * ┌───n── fork has * │ only 1 blk? * │ │ * │ y * │ │ * │ v * │ xfs_attr_leaf_try_add() * │ │ * │ v * │ had enough ──────────────y─────────────┐ * │ space? │ * │ │ │ * │ n │ * │ │ │ * │ v │ * │ return -EAGAIN │ * │ re-enter in │ * │ node form │ * │ │ │ * └──────────┤ │ * │ │ * V │ * xfs_attr_node_addname_find_attr │ * determines if this │ * is create or rename │ * find space to store attr │ * │ │ * v │ * xfs_attr_node_addname │ * │ │ * v │ * fits in a node leaf? ────n─────┐ │ * │ ^ v │ * │ │ single leaf node? │ * │ │ │ │ │ * y │ y n │ * │ │ │ │ │ * v │ v v │ * update │ grow the leaf split if │ * hashvals └── return -EAGAIN needed │ * │ retry leaf add │ │ * │ on reentry │ │ * ├────────────────────────────┘ │ * │ │ * v │ * need to alloc │ * ┌─y── or flip flag? │ * │ │ │ * │ n │ * │ │ │ * │ v │ * │ done │ * │ │ * │ │ * │ XFS_DAS_FOUND_LBLK <────────────────┘ * │ │ * │ V * │ xfs_attr_leaf_addname() * │ │ * │ v * │ ┌──first time through? * │ │ │ * │ │ y * │ │ │ * │ n v * │ │ if we have rmt blks * │ │ find space for them * │ │ │ * │ └──────────┤ * │ │ * │ v * │ still have * │ ┌─n─ blks to alloc? <──┐ * │ │ │ │ * │ │ y │ * │ │ │ │ * │ │ v │ * │ │ alloc one blk │ * │ │ return -EAGAIN ──┘ * │ │ re-enter with one * │ │ less blk to alloc * │ │ * │ │ * │ └───> set the rmt * │ value * │ │ * │ v * │ was this * │ a rename? ──n─┐ * │ │ │ * │ y │ * │ │ │ * │ v │ * │ flip incomplete │ * │ flag │ * │ │ │ * │ v │ * │ XFS_DAS_FLIP_LFLAG │ * │ │ │ * │ v │ * │ need to remove │ * │ old bks? ──n──┤ * │ │ │ * │ y │ * │ │ │ * │ V │ * │ remove │ * │ ┌───> old blks │ * │ │ │ │ * │ XFS_DAS_RM_LBLK │ │ * │ ^ │ │ * │ │ v │ * │ └──y── more to │ * │ remove? │ * │ │ │ * │ n │ * │ │ │ * │ v │ * │ XFS_DAS_RD_LEAF │ * │ │ │ * │ v │ * │ remove leaf │ * │ │ │ * │ v │ * │ shrink to sf │ * │ if needed │ * │ │ │ * │ v │ * │ done <──────┘ * │ * └──────> XFS_DAS_FOUND_NBLK * │ * v * ┌─────n── need to * │ alloc blks? * │ │ * │ y * │ │ * │ v * │ find space * │ │ * │ v * │ ┌─>XFS_DAS_ALLOC_NODE * │ │ │ * │ │ v * │ │ alloc blk * │ │ │ * │ │ v * │ └──y── need to alloc * │ more blocks? * │ │ * │ n * │ │ * │ v * │ set the rmt value * │ │ * │ v * │ was this * └────────> a rename? ──n─┐ * │ │ * y │ * │ │ * v │ * flip incomplete │ * flag │ * │ │ * v │ * XFS_DAS_FLIP_NFLAG │ * │ │ * v │ * need to │ * remove blks? ─n──┤ * │ │ * y │ * │ │ * v │ * remove │ * ┌────────> old blks │ * │ │ │ * XFS_DAS_RM_NBLK │ │ * ^ │ │ * │ v │ * └──────y── more to │ * remove │ * │ │ * n │ * │ │ * v │ * XFS_DAS_CLR_FLAG │ * │ │ * v │ * clear flags │ * │ │ * ├──────────┘ * │ * v * done */ /* * Enum values for xfs_attr_intent.xattri_da_state * * These values are used by delayed attribute operations to keep track of where * they were before they returned -EAGAIN. A return code of -EAGAIN signals the * calling function to roll the transaction, and then call the subroutine to * finish the operation. The enum is then used by the subroutine to jump back * to where it was and resume executing where it left off. */ enum xfs_delattr_state { XFS_DAS_UNINIT = 0, /* No state has been set yet */ /* * Initial sequence states. The replace setup code relies on the * ADD and REMOVE states for a specific format to be sequential so * that we can transform the initial operation to be performed * according to the xfs_has_larp() state easily. */ XFS_DAS_SF_ADD, /* Initial sf add state */ XFS_DAS_SF_REMOVE, /* Initial sf replace/remove state */ XFS_DAS_LEAF_ADD, /* Initial leaf add state */ XFS_DAS_LEAF_REMOVE, /* Initial leaf replace/remove state */ XFS_DAS_NODE_ADD, /* Initial node add state */ XFS_DAS_NODE_REMOVE, /* Initial node replace/remove state */ /* Leaf state set/replace/remove sequence */ XFS_DAS_LEAF_SET_RMT, /* set a remote xattr from a leaf */ XFS_DAS_LEAF_ALLOC_RMT, /* We are allocating remote blocks */ XFS_DAS_LEAF_REPLACE, /* Perform replace ops on a leaf */ XFS_DAS_LEAF_REMOVE_OLD, /* Start removing old attr from leaf */ XFS_DAS_LEAF_REMOVE_RMT, /* A rename is removing remote blocks */ XFS_DAS_LEAF_REMOVE_ATTR, /* Remove the old attr from a leaf */ /* Node state sequence, must match leaf state above */ XFS_DAS_NODE_SET_RMT, /* set a remote xattr from a node */ XFS_DAS_NODE_ALLOC_RMT, /* We are allocating remote blocks */ XFS_DAS_NODE_REPLACE, /* Perform replace ops on a node */ XFS_DAS_NODE_REMOVE_OLD, /* Start removing old attr from node */ XFS_DAS_NODE_REMOVE_RMT, /* A rename is removing remote blocks */ XFS_DAS_NODE_REMOVE_ATTR, /* Remove the old attr from a node */ XFS_DAS_DONE, /* finished operation */ }; #define XFS_DAS_STRINGS \ { XFS_DAS_UNINIT, "XFS_DAS_UNINIT" }, \ { XFS_DAS_SF_ADD, "XFS_DAS_SF_ADD" }, \ { XFS_DAS_SF_REMOVE, "XFS_DAS_SF_REMOVE" }, \ { XFS_DAS_LEAF_ADD, "XFS_DAS_LEAF_ADD" }, \ { XFS_DAS_LEAF_REMOVE, "XFS_DAS_LEAF_REMOVE" }, \ { XFS_DAS_NODE_ADD, "XFS_DAS_NODE_ADD" }, \ { XFS_DAS_NODE_REMOVE, "XFS_DAS_NODE_REMOVE" }, \ { XFS_DAS_LEAF_SET_RMT, "XFS_DAS_LEAF_SET_RMT" }, \ { XFS_DAS_LEAF_ALLOC_RMT, "XFS_DAS_LEAF_ALLOC_RMT" }, \ { XFS_DAS_LEAF_REPLACE, "XFS_DAS_LEAF_REPLACE" }, \ { XFS_DAS_LEAF_REMOVE_OLD, "XFS_DAS_LEAF_REMOVE_OLD" }, \ { XFS_DAS_LEAF_REMOVE_RMT, "XFS_DAS_LEAF_REMOVE_RMT" }, \ { XFS_DAS_LEAF_REMOVE_ATTR, "XFS_DAS_LEAF_REMOVE_ATTR" }, \ { XFS_DAS_NODE_SET_RMT, "XFS_DAS_NODE_SET_RMT" }, \ { XFS_DAS_NODE_ALLOC_RMT, "XFS_DAS_NODE_ALLOC_RMT" }, \ { XFS_DAS_NODE_REPLACE, "XFS_DAS_NODE_REPLACE" }, \ { XFS_DAS_NODE_REMOVE_OLD, "XFS_DAS_NODE_REMOVE_OLD" }, \ { XFS_DAS_NODE_REMOVE_RMT, "XFS_DAS_NODE_REMOVE_RMT" }, \ { XFS_DAS_NODE_REMOVE_ATTR, "XFS_DAS_NODE_REMOVE_ATTR" }, \ { XFS_DAS_DONE, "XFS_DAS_DONE" } struct xfs_attri_log_nameval; /* * Context used for keeping track of delayed attribute operations */ struct xfs_attr_intent { /* * used to log this item to an intent containing a list of attrs to * commit later */ struct list_head xattri_list; /* Used in xfs_attr_node_removename to roll through removing blocks */ struct xfs_da_state *xattri_da_state; struct xfs_da_args *xattri_da_args; /* * Shared buffer containing the attr name, new name, and value so that * the logging code can share large memory buffers between log items. */ struct xfs_attri_log_nameval *xattri_nameval; /* Used to keep track of current state of delayed operation */ enum xfs_delattr_state xattri_dela_state; /* * Attr operation being performed - XFS_ATTRI_OP_FLAGS_* */ unsigned int xattri_op_flags; /* Used in xfs_attr_rmtval_set_blk to roll through allocating blocks */ xfs_dablk_t xattri_lblkno; int xattri_blkcnt; struct xfs_bmbt_irec xattri_map; }; static inline unsigned int xfs_attr_intent_op(const struct xfs_attr_intent *attr) { return attr->xattri_op_flags & XFS_ATTRI_OP_FLAGS_TYPE_MASK; } /*======================================================================== * Function prototypes for the kernel. *========================================================================*/ /* * Overall external interface routines. */ int xfs_attr_inactive(struct xfs_inode *dp); int xfs_attr_list_ilocked(struct xfs_attr_list_context *); int xfs_attr_list(struct xfs_attr_list_context *); int xfs_inode_hasattr(struct xfs_inode *ip); bool xfs_attr_is_leaf(struct xfs_inode *ip); int xfs_attr_get_ilocked(struct xfs_da_args *args); int xfs_attr_get(struct xfs_da_args *args); enum xfs_attr_update { XFS_ATTRUPDATE_REMOVE, /* remove attr */ XFS_ATTRUPDATE_UPSERT, /* set value, replace any existing attr */ XFS_ATTRUPDATE_CREATE, /* set value, fail if attr already exists */ XFS_ATTRUPDATE_REPLACE, /* set value, fail if attr does not exist */ }; int xfs_attr_set(struct xfs_da_args *args, enum xfs_attr_update op, bool rsvd); int xfs_attr_set_iter(struct xfs_attr_intent *attr); int xfs_attr_remove_iter(struct xfs_attr_intent *attr); bool xfs_attr_check_namespace(unsigned int attr_flags); bool xfs_attr_namecheck(unsigned int attr_flags, const void *name, size_t length); int xfs_attr_calc_size(struct xfs_da_args *args, int *local); struct xfs_trans_res xfs_attr_set_resv(const struct xfs_da_args *args); /* * Check to see if the attr should be upgraded from non-existent or shortform to * single-leaf-block attribute list. */ static inline bool xfs_attr_is_shortform( struct xfs_inode *ip) { return ip->i_af.if_format == XFS_DINODE_FMT_LOCAL || (ip->i_af.if_format == XFS_DINODE_FMT_EXTENTS && ip->i_af.if_nextents == 0); } static inline enum xfs_delattr_state xfs_attr_init_add_state(struct xfs_da_args *args) { /* * When called from the completion of a attr remove to determine the * next state, the attribute fork may be null. This can occur only occur * on a pure remove, but we grab the next state before we check if a * replace operation is being performed. If we are called from any other * context, i_af is guaranteed to exist. Hence if the attr fork is * null, we were called from a pure remove operation and so we are done. */ if (!xfs_inode_has_attr_fork(args->dp)) return XFS_DAS_DONE; args->op_flags |= XFS_DA_OP_ADDNAME; if (xfs_attr_is_shortform(args->dp)) return XFS_DAS_SF_ADD; if (xfs_attr_is_leaf(args->dp)) return XFS_DAS_LEAF_ADD; return XFS_DAS_NODE_ADD; } static inline enum xfs_delattr_state xfs_attr_init_remove_state(struct xfs_da_args *args) { if (xfs_attr_is_shortform(args->dp)) return XFS_DAS_SF_REMOVE; if (xfs_attr_is_leaf(args->dp)) return XFS_DAS_LEAF_REMOVE; return XFS_DAS_NODE_REMOVE; } /* * If we are logging the attributes, then we have to start with removal of the * old attribute so that there is always consistent state that we can recover * from if the system goes down part way through. We always log the new attr * value, so even when we remove the attr first we still have the information in * the log to finish the replace operation atomically. */ static inline enum xfs_delattr_state xfs_attr_init_replace_state(struct xfs_da_args *args) { args->op_flags |= XFS_DA_OP_ADDNAME | XFS_DA_OP_REPLACE; if (args->op_flags & XFS_DA_OP_LOGGED) return xfs_attr_init_remove_state(args); return xfs_attr_init_add_state(args); } xfs_dahash_t xfs_attr_hashname(const uint8_t *name, int namelen); xfs_dahash_t xfs_attr_hashval(struct xfs_mount *mp, unsigned int attr_flags, const uint8_t *name, int namelen, const void *value, int valuelen); /* Set the hash value for any extended attribute from any namespace. */ static inline void xfs_attr_sethash(struct xfs_da_args *args) { args->hashval = xfs_attr_hashval(args->dp->i_mount, args->attr_filter, args->name, args->namelen, args->value, args->valuelen); } extern struct kmem_cache *xfs_attr_intent_cache; int __init xfs_attr_intent_init_cache(void); void xfs_attr_intent_destroy_cache(void); int xfs_attr_sf_totsize(struct xfs_inode *dp); int xfs_attr_add_fork(struct xfs_inode *ip, int size, int rsvd); #endif /* __XFS_ATTR_H__ */ |
| 19 19 19 19 | 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 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * Public Key Encryption * * Copyright (c) 2015, Intel Corporation * Authors: Tadeusz Struk <tadeusz.struk@intel.com> */ #ifndef _CRYPTO_AKCIPHER_H #define _CRYPTO_AKCIPHER_H #include <linux/atomic.h> #include <linux/crypto.h> /** * struct akcipher_request - public key cipher request * * @base: Common attributes for async crypto requests * @src: Source data * @dst: Destination data * @src_len: Size of the input buffer * @dst_len: Size of @dst buffer * It needs to be at least as big as the expected result * depending on the operation. * After operation it will be updated with the actual size of the * result. * In case of error where the dst sgl size was insufficient, * it will be updated to the size required for the operation. * @__ctx: Start of private context data */ struct akcipher_request { struct crypto_async_request base; struct scatterlist *src; struct scatterlist *dst; unsigned int src_len; unsigned int dst_len; void *__ctx[] CRYPTO_MINALIGN_ATTR; }; /** * struct crypto_akcipher - user-instantiated objects which encapsulate * algorithms and core processing logic * * @reqsize: Request context size required by algorithm implementation * @base: Common crypto API algorithm data structure */ struct crypto_akcipher { unsigned int reqsize; struct crypto_tfm base; }; /** * struct akcipher_alg - generic public key cipher algorithm * * @encrypt: Function performs an encrypt operation as defined by public key * algorithm. In case of error, where the dst_len was insufficient, * the req->dst_len will be updated to the size required for the * operation * @decrypt: Function performs a decrypt operation as defined by public key * algorithm. In case of error, where the dst_len was insufficient, * the req->dst_len will be updated to the size required for the * operation * @set_pub_key: Function invokes the algorithm specific set public key * function, which knows how to decode and interpret * the BER encoded public key and parameters * @set_priv_key: Function invokes the algorithm specific set private key * function, which knows how to decode and interpret * the BER encoded private key and parameters * @max_size: Function returns dest buffer size required for a given key. * @init: Initialize the cryptographic transformation object. * This function is used to initialize the cryptographic * transformation object. This function is called only once at * the instantiation time, right after the transformation context * was allocated. In case the cryptographic hardware has some * special requirements which need to be handled by software, this * function shall check for the precise requirement of the * transformation and put any software fallbacks in place. * @exit: Deinitialize the cryptographic transformation object. This is a * counterpart to @init, used to remove various changes set in * @init. * * @base: Common crypto API algorithm data structure */ struct akcipher_alg { int (*encrypt)(struct akcipher_request *req); int (*decrypt)(struct akcipher_request *req); int (*set_pub_key)(struct crypto_akcipher *tfm, const void *key, unsigned int keylen); int (*set_priv_key)(struct crypto_akcipher *tfm, const void *key, unsigned int keylen); unsigned int (*max_size)(struct crypto_akcipher *tfm); int (*init)(struct crypto_akcipher *tfm); void (*exit)(struct crypto_akcipher *tfm); struct crypto_alg base; }; /** * DOC: Generic Public Key Cipher API * * The Public Key Cipher API is used with the algorithms of type * CRYPTO_ALG_TYPE_AKCIPHER (listed as type "akcipher" in /proc/crypto) */ /** * crypto_alloc_akcipher() - allocate AKCIPHER tfm handle * @alg_name: is the cra_name / name or cra_driver_name / driver name of the * public key algorithm e.g. "rsa" * @type: specifies the type of the algorithm * @mask: specifies the mask for the algorithm * * Allocate a handle for public key algorithm. The returned struct * crypto_akcipher is the handle that is required for any subsequent * API invocation for the public key operations. * * Return: allocated handle in case of success; IS_ERR() is true in case * of an error, PTR_ERR() returns the error code. */ struct crypto_akcipher *crypto_alloc_akcipher(const char *alg_name, u32 type, u32 mask); static inline struct crypto_tfm *crypto_akcipher_tfm( struct crypto_akcipher *tfm) { return &tfm->base; } static inline struct akcipher_alg *__crypto_akcipher_alg(struct crypto_alg *alg) { return container_of(alg, struct akcipher_alg, base); } static inline struct crypto_akcipher *__crypto_akcipher_tfm( struct crypto_tfm *tfm) { return container_of(tfm, struct crypto_akcipher, base); } static inline struct akcipher_alg *crypto_akcipher_alg( struct crypto_akcipher *tfm) { return __crypto_akcipher_alg(crypto_akcipher_tfm(tfm)->__crt_alg); } static inline unsigned int crypto_akcipher_reqsize(struct crypto_akcipher *tfm) { return tfm->reqsize; } static inline void akcipher_request_set_tfm(struct akcipher_request *req, struct crypto_akcipher *tfm) { req->base.tfm = crypto_akcipher_tfm(tfm); } static inline struct crypto_akcipher *crypto_akcipher_reqtfm( struct akcipher_request *req) { return __crypto_akcipher_tfm(req->base.tfm); } /** * crypto_free_akcipher() - free AKCIPHER tfm handle * * @tfm: AKCIPHER tfm handle allocated with crypto_alloc_akcipher() * * If @tfm is a NULL or error pointer, this function does nothing. */ static inline void crypto_free_akcipher(struct crypto_akcipher *tfm) { crypto_destroy_tfm(tfm, crypto_akcipher_tfm(tfm)); } /** * akcipher_request_alloc() - allocates public key request * * @tfm: AKCIPHER tfm handle allocated with crypto_alloc_akcipher() * @gfp: allocation flags * * Return: allocated handle in case of success or NULL in case of an error. */ static inline struct akcipher_request *akcipher_request_alloc( struct crypto_akcipher *tfm, gfp_t gfp) { struct akcipher_request *req; req = kmalloc(sizeof(*req) + crypto_akcipher_reqsize(tfm), gfp); if (likely(req)) akcipher_request_set_tfm(req, tfm); return req; } /** * akcipher_request_free() - zeroize and free public key request * * @req: request to free */ static inline void akcipher_request_free(struct akcipher_request *req) { kfree_sensitive(req); } /** * akcipher_request_set_callback() - Sets an asynchronous callback. * * Callback will be called when an asynchronous operation on a given * request is finished. * * @req: request that the callback will be set for * @flgs: specify for instance if the operation may backlog * @cmpl: callback which will be called * @data: private data used by the caller */ static inline void akcipher_request_set_callback(struct akcipher_request *req, u32 flgs, crypto_completion_t cmpl, void *data) { req->base.complete = cmpl; req->base.data = data; req->base.flags = flgs; } /** * akcipher_request_set_crypt() - Sets request parameters * * Sets parameters required by crypto operation * * @req: public key request * @src: ptr to input scatter list * @dst: ptr to output scatter list * @src_len: size of the src input scatter list to be processed * @dst_len: size of the dst output scatter list */ static inline void akcipher_request_set_crypt(struct akcipher_request *req, struct scatterlist *src, struct scatterlist *dst, unsigned int src_len, unsigned int dst_len) { req->src = src; req->dst = dst; req->src_len = src_len; req->dst_len = dst_len; } /** * crypto_akcipher_maxsize() - Get len for output buffer * * Function returns the dest buffer size required for a given key. * Function assumes that the key is already set in the transformation. If this * function is called without a setkey or with a failed setkey, you will end up * in a NULL dereference. * * @tfm: AKCIPHER tfm handle allocated with crypto_alloc_akcipher() */ static inline unsigned int crypto_akcipher_maxsize(struct crypto_akcipher *tfm) { struct akcipher_alg *alg = crypto_akcipher_alg(tfm); return alg->max_size(tfm); } /** * crypto_akcipher_encrypt() - Invoke public key encrypt operation * * Function invokes the specific public key encrypt operation for a given * public key algorithm * * @req: asymmetric key request * * Return: zero on success; error code in case of error */ static inline int crypto_akcipher_encrypt(struct akcipher_request *req) { struct crypto_akcipher *tfm = crypto_akcipher_reqtfm(req); return crypto_akcipher_alg(tfm)->encrypt(req); } /** * crypto_akcipher_decrypt() - Invoke public key decrypt operation * * Function invokes the specific public key decrypt operation for a given * public key algorithm * * @req: asymmetric key request * * Return: zero on success; error code in case of error */ static inline int crypto_akcipher_decrypt(struct akcipher_request *req) { struct crypto_akcipher *tfm = crypto_akcipher_reqtfm(req); return crypto_akcipher_alg(tfm)->decrypt(req); } /** * crypto_akcipher_sync_encrypt() - Invoke public key encrypt operation * * Function invokes the specific public key encrypt operation for a given * public key algorithm * * @tfm: AKCIPHER tfm handle allocated with crypto_alloc_akcipher() * @src: source buffer * @slen: source length * @dst: destination obuffer * @dlen: destination length * * Return: zero on success; error code in case of error */ int crypto_akcipher_sync_encrypt(struct crypto_akcipher *tfm, const void *src, unsigned int slen, void *dst, unsigned int dlen); /** * crypto_akcipher_sync_decrypt() - Invoke public key decrypt operation * * Function invokes the specific public key decrypt operation for a given * public key algorithm * * @tfm: AKCIPHER tfm handle allocated with crypto_alloc_akcipher() * @src: source buffer * @slen: source length * @dst: destination obuffer * @dlen: destination length * * Return: Output length on success; error code in case of error */ int crypto_akcipher_sync_decrypt(struct crypto_akcipher *tfm, const void *src, unsigned int slen, void *dst, unsigned int dlen); /** * crypto_akcipher_set_pub_key() - Invoke set public key operation * * Function invokes the algorithm specific set key function, which knows * how to decode and interpret the encoded key and parameters * * @tfm: tfm handle * @key: BER encoded public key, algo OID, paramlen, BER encoded * parameters * @keylen: length of the key (not including other data) * * Return: zero on success; error code in case of error */ static inline int crypto_akcipher_set_pub_key(struct crypto_akcipher *tfm, const void *key, unsigned int keylen) { struct akcipher_alg *alg = crypto_akcipher_alg(tfm); return alg->set_pub_key(tfm, key, keylen); } /** * crypto_akcipher_set_priv_key() - Invoke set private key operation * * Function invokes the algorithm specific set key function, which knows * how to decode and interpret the encoded key and parameters * * @tfm: tfm handle * @key: BER encoded private key, algo OID, paramlen, BER encoded * parameters * @keylen: length of the key (not including other data) * * Return: zero on success; error code in case of error */ static inline int crypto_akcipher_set_priv_key(struct crypto_akcipher *tfm, const void *key, unsigned int keylen) { struct akcipher_alg *alg = crypto_akcipher_alg(tfm); return alg->set_priv_key(tfm, key, keylen); } #endif |
| 3 3 3 3 3 3 3 2 1 3 3 3 3 3 3 3 2 3 2 1 3 2 2 3 3 3 7 7 6 6 6 4 6 4 6 4 3 3 3 3 3 7 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Sony NFC Port-100 Series driver * Copyright (c) 2013, Intel Corporation. * * Partly based/Inspired by Stephen Tiedemann's nfcpy */ #include <linux/module.h> #include <linux/usb.h> #include <net/nfc/digital.h> #define VERSION "0.1" #define SONY_VENDOR_ID 0x054c #define RCS380S_PRODUCT_ID 0x06c1 #define RCS380P_PRODUCT_ID 0x06c3 #define PORT100_PROTOCOLS (NFC_PROTO_JEWEL_MASK | \ NFC_PROTO_MIFARE_MASK | \ NFC_PROTO_FELICA_MASK | \ NFC_PROTO_NFC_DEP_MASK | \ NFC_PROTO_ISO14443_MASK | \ NFC_PROTO_ISO14443_B_MASK) #define PORT100_CAPABILITIES (NFC_DIGITAL_DRV_CAPS_IN_CRC | \ NFC_DIGITAL_DRV_CAPS_TG_CRC) /* Standard port100 frame definitions */ #define PORT100_FRAME_HEADER_LEN (sizeof(struct port100_frame) \ + 2) /* data[0] CC, data[1] SCC */ #define PORT100_FRAME_TAIL_LEN 2 /* data[len] DCS, data[len + 1] postamble*/ #define PORT100_COMM_RF_HEAD_MAX_LEN (sizeof(struct port100_tg_comm_rf_cmd)) /* * Max extended frame payload len, excluding CC and SCC * which are already in PORT100_FRAME_HEADER_LEN. */ #define PORT100_FRAME_MAX_PAYLOAD_LEN 1001 #define PORT100_FRAME_ACK_SIZE 6 /* Preamble (1), SoPC (2), ACK Code (2), Postamble (1) */ static u8 ack_frame[PORT100_FRAME_ACK_SIZE] = { 0x00, 0x00, 0xff, 0x00, 0xff, 0x00 }; #define PORT100_FRAME_CHECKSUM(f) (f->data[le16_to_cpu(f->datalen)]) #define PORT100_FRAME_POSTAMBLE(f) (f->data[le16_to_cpu(f->datalen) + 1]) /* start of frame */ #define PORT100_FRAME_SOF 0x00FF #define PORT100_FRAME_EXT 0xFFFF #define PORT100_FRAME_ACK 0x00FF /* Port-100 command: in or out */ #define PORT100_FRAME_DIRECTION(f) (f->data[0]) /* CC */ #define PORT100_FRAME_DIR_OUT 0xD6 #define PORT100_FRAME_DIR_IN 0xD7 /* Port-100 sub-command */ #define PORT100_FRAME_CMD(f) (f->data[1]) /* SCC */ #define PORT100_CMD_GET_FIRMWARE_VERSION 0x20 #define PORT100_CMD_GET_COMMAND_TYPE 0x28 #define PORT100_CMD_SET_COMMAND_TYPE 0x2A #define PORT100_CMD_IN_SET_RF 0x00 #define PORT100_CMD_IN_SET_PROTOCOL 0x02 #define PORT100_CMD_IN_COMM_RF 0x04 #define PORT100_CMD_TG_SET_RF 0x40 #define PORT100_CMD_TG_SET_PROTOCOL 0x42 #define PORT100_CMD_TG_SET_RF_OFF 0x46 #define PORT100_CMD_TG_COMM_RF 0x48 #define PORT100_CMD_SWITCH_RF 0x06 #define PORT100_CMD_RESPONSE(cmd) (cmd + 1) #define PORT100_CMD_TYPE_IS_SUPPORTED(mask, cmd_type) \ ((mask) & (0x01 << (cmd_type))) #define PORT100_CMD_TYPE_0 0 #define PORT100_CMD_TYPE_1 1 #define PORT100_CMD_STATUS_OK 0x00 #define PORT100_CMD_STATUS_TIMEOUT 0x80 #define PORT100_MDAA_TGT_HAS_BEEN_ACTIVATED_MASK 0x01 #define PORT100_MDAA_TGT_WAS_ACTIVATED_MASK 0x02 struct port100; typedef void (*port100_send_async_complete_t)(struct port100 *dev, void *arg, struct sk_buff *resp); /* * Setting sets structure for in_set_rf command * * @in_*_set_number: Represent the entry indexes in the port-100 RF Base Table. * This table contains multiple RF setting sets required for RF * communication. * * @in_*_comm_type: Theses fields set the communication type to be used. */ struct port100_in_rf_setting { u8 in_send_set_number; u8 in_send_comm_type; u8 in_recv_set_number; u8 in_recv_comm_type; } __packed; #define PORT100_COMM_TYPE_IN_212F 0x01 #define PORT100_COMM_TYPE_IN_424F 0x02 #define PORT100_COMM_TYPE_IN_106A 0x03 #define PORT100_COMM_TYPE_IN_106B 0x07 static const struct port100_in_rf_setting in_rf_settings[] = { [NFC_DIGITAL_RF_TECH_212F] = { .in_send_set_number = 1, .in_send_comm_type = PORT100_COMM_TYPE_IN_212F, .in_recv_set_number = 15, .in_recv_comm_type = PORT100_COMM_TYPE_IN_212F, }, [NFC_DIGITAL_RF_TECH_424F] = { .in_send_set_number = 1, .in_send_comm_type = PORT100_COMM_TYPE_IN_424F, .in_recv_set_number = 15, .in_recv_comm_type = PORT100_COMM_TYPE_IN_424F, }, [NFC_DIGITAL_RF_TECH_106A] = { .in_send_set_number = 2, .in_send_comm_type = PORT100_COMM_TYPE_IN_106A, .in_recv_set_number = 15, .in_recv_comm_type = PORT100_COMM_TYPE_IN_106A, }, [NFC_DIGITAL_RF_TECH_106B] = { .in_send_set_number = 3, .in_send_comm_type = PORT100_COMM_TYPE_IN_106B, .in_recv_set_number = 15, .in_recv_comm_type = PORT100_COMM_TYPE_IN_106B, }, /* Ensures the array has NFC_DIGITAL_RF_TECH_LAST elements */ [NFC_DIGITAL_RF_TECH_LAST] = { 0 }, }; /** * struct port100_tg_rf_setting - Setting sets structure for tg_set_rf command * * @tg_set_number: Represents the entry index in the port-100 RF Base Table. * This table contains multiple RF setting sets required for RF * communication. this field is used for both send and receive * settings. * * @tg_comm_type: Sets the communication type to be used to send and receive * data. */ struct port100_tg_rf_setting { u8 tg_set_number; u8 tg_comm_type; } __packed; #define PORT100_COMM_TYPE_TG_106A 0x0B #define PORT100_COMM_TYPE_TG_212F 0x0C #define PORT100_COMM_TYPE_TG_424F 0x0D static const struct port100_tg_rf_setting tg_rf_settings[] = { [NFC_DIGITAL_RF_TECH_106A] = { .tg_set_number = 8, .tg_comm_type = PORT100_COMM_TYPE_TG_106A, }, [NFC_DIGITAL_RF_TECH_212F] = { .tg_set_number = 8, .tg_comm_type = PORT100_COMM_TYPE_TG_212F, }, [NFC_DIGITAL_RF_TECH_424F] = { .tg_set_number = 8, .tg_comm_type = PORT100_COMM_TYPE_TG_424F, }, /* Ensures the array has NFC_DIGITAL_RF_TECH_LAST elements */ [NFC_DIGITAL_RF_TECH_LAST] = { 0 }, }; #define PORT100_IN_PROT_INITIAL_GUARD_TIME 0x00 #define PORT100_IN_PROT_ADD_CRC 0x01 #define PORT100_IN_PROT_CHECK_CRC 0x02 #define PORT100_IN_PROT_MULTI_CARD 0x03 #define PORT100_IN_PROT_ADD_PARITY 0x04 #define PORT100_IN_PROT_CHECK_PARITY 0x05 #define PORT100_IN_PROT_BITWISE_AC_RECV_MODE 0x06 #define PORT100_IN_PROT_VALID_BIT_NUMBER 0x07 #define PORT100_IN_PROT_CRYPTO1 0x08 #define PORT100_IN_PROT_ADD_SOF 0x09 #define PORT100_IN_PROT_CHECK_SOF 0x0A #define PORT100_IN_PROT_ADD_EOF 0x0B #define PORT100_IN_PROT_CHECK_EOF 0x0C #define PORT100_IN_PROT_DEAF_TIME 0x0E #define PORT100_IN_PROT_CRM 0x0F #define PORT100_IN_PROT_CRM_MIN_LEN 0x10 #define PORT100_IN_PROT_T1_TAG_FRAME 0x11 #define PORT100_IN_PROT_RFCA 0x12 #define PORT100_IN_PROT_GUARD_TIME_AT_INITIATOR 0x13 #define PORT100_IN_PROT_END 0x14 #define PORT100_IN_MAX_NUM_PROTOCOLS 19 #define PORT100_TG_PROT_TU 0x00 #define PORT100_TG_PROT_RF_OFF 0x01 #define PORT100_TG_PROT_CRM 0x02 #define PORT100_TG_PROT_END 0x03 #define PORT100_TG_MAX_NUM_PROTOCOLS 3 struct port100_protocol { u8 number; u8 value; } __packed; static const struct port100_protocol in_protocols[][PORT100_IN_MAX_NUM_PROTOCOLS + 1] = { [NFC_DIGITAL_FRAMING_NFCA_SHORT] = { { PORT100_IN_PROT_INITIAL_GUARD_TIME, 6 }, { PORT100_IN_PROT_ADD_CRC, 0 }, { PORT100_IN_PROT_CHECK_CRC, 0 }, { PORT100_IN_PROT_MULTI_CARD, 0 }, { PORT100_IN_PROT_ADD_PARITY, 0 }, { PORT100_IN_PROT_CHECK_PARITY, 1 }, { PORT100_IN_PROT_BITWISE_AC_RECV_MODE, 0 }, { PORT100_IN_PROT_VALID_BIT_NUMBER, 7 }, { PORT100_IN_PROT_CRYPTO1, 0 }, { PORT100_IN_PROT_ADD_SOF, 0 }, { PORT100_IN_PROT_CHECK_SOF, 0 }, { PORT100_IN_PROT_ADD_EOF, 0 }, { PORT100_IN_PROT_CHECK_EOF, 0 }, { PORT100_IN_PROT_DEAF_TIME, 4 }, { PORT100_IN_PROT_CRM, 0 }, { PORT100_IN_PROT_CRM_MIN_LEN, 0 }, { PORT100_IN_PROT_T1_TAG_FRAME, 0 }, { PORT100_IN_PROT_RFCA, 0 }, { PORT100_IN_PROT_GUARD_TIME_AT_INITIATOR, 6 }, { PORT100_IN_PROT_END, 0 }, }, [NFC_DIGITAL_FRAMING_NFCA_STANDARD] = { { PORT100_IN_PROT_INITIAL_GUARD_TIME, 6 }, { PORT100_IN_PROT_ADD_CRC, 0 }, { PORT100_IN_PROT_CHECK_CRC, 0 }, { PORT100_IN_PROT_MULTI_CARD, 0 }, { PORT100_IN_PROT_ADD_PARITY, 1 }, { PORT100_IN_PROT_CHECK_PARITY, 1 }, { PORT100_IN_PROT_BITWISE_AC_RECV_MODE, 0 }, { PORT100_IN_PROT_VALID_BIT_NUMBER, 8 }, { PORT100_IN_PROT_CRYPTO1, 0 }, { PORT100_IN_PROT_ADD_SOF, 0 }, { PORT100_IN_PROT_CHECK_SOF, 0 }, { PORT100_IN_PROT_ADD_EOF, 0 }, { PORT100_IN_PROT_CHECK_EOF, 0 }, { PORT100_IN_PROT_DEAF_TIME, 4 }, { PORT100_IN_PROT_CRM, 0 }, { PORT100_IN_PROT_CRM_MIN_LEN, 0 }, { PORT100_IN_PROT_T1_TAG_FRAME, 0 }, { PORT100_IN_PROT_RFCA, 0 }, { PORT100_IN_PROT_GUARD_TIME_AT_INITIATOR, 6 }, { PORT100_IN_PROT_END, 0 }, }, [NFC_DIGITAL_FRAMING_NFCA_STANDARD_WITH_CRC_A] = { { PORT100_IN_PROT_INITIAL_GUARD_TIME, 6 }, { PORT100_IN_PROT_ADD_CRC, 1 }, { PORT100_IN_PROT_CHECK_CRC, 1 }, { PORT100_IN_PROT_MULTI_CARD, 0 }, { PORT100_IN_PROT_ADD_PARITY, 1 }, { PORT100_IN_PROT_CHECK_PARITY, 1 }, { PORT100_IN_PROT_BITWISE_AC_RECV_MODE, 0 }, { PORT100_IN_PROT_VALID_BIT_NUMBER, 8 }, { PORT100_IN_PROT_CRYPTO1, 0 }, { PORT100_IN_PROT_ADD_SOF, 0 }, { PORT100_IN_PROT_CHECK_SOF, 0 }, { PORT100_IN_PROT_ADD_EOF, 0 }, { PORT100_IN_PROT_CHECK_EOF, 0 }, { PORT100_IN_PROT_DEAF_TIME, 4 }, { PORT100_IN_PROT_CRM, 0 }, { PORT100_IN_PROT_CRM_MIN_LEN, 0 }, { PORT100_IN_PROT_T1_TAG_FRAME, 0 }, { PORT100_IN_PROT_RFCA, 0 }, { PORT100_IN_PROT_GUARD_TIME_AT_INITIATOR, 6 }, { PORT100_IN_PROT_END, 0 }, }, [NFC_DIGITAL_FRAMING_NFCA_T1T] = { /* nfc_digital_framing_nfca_short */ { PORT100_IN_PROT_ADD_CRC, 2 }, { PORT100_IN_PROT_CHECK_CRC, 2 }, { PORT100_IN_PROT_VALID_BIT_NUMBER, 8 }, { PORT100_IN_PROT_T1_TAG_FRAME, 2 }, { PORT100_IN_PROT_END, 0 }, }, [NFC_DIGITAL_FRAMING_NFCA_T2T] = { /* nfc_digital_framing_nfca_standard */ { PORT100_IN_PROT_ADD_CRC, 1 }, { PORT100_IN_PROT_CHECK_CRC, 0 }, { PORT100_IN_PROT_END, 0 }, }, [NFC_DIGITAL_FRAMING_NFCA_T4T] = { /* nfc_digital_framing_nfca_standard_with_crc_a */ { PORT100_IN_PROT_END, 0 }, }, [NFC_DIGITAL_FRAMING_NFCA_NFC_DEP] = { /* nfc_digital_framing_nfca_standard */ { PORT100_IN_PROT_END, 0 }, }, [NFC_DIGITAL_FRAMING_NFCF] = { { PORT100_IN_PROT_INITIAL_GUARD_TIME, 18 }, { PORT100_IN_PROT_ADD_CRC, 1 }, { PORT100_IN_PROT_CHECK_CRC, 1 }, { PORT100_IN_PROT_MULTI_CARD, 0 }, { PORT100_IN_PROT_ADD_PARITY, 0 }, { PORT100_IN_PROT_CHECK_PARITY, 0 }, { PORT100_IN_PROT_BITWISE_AC_RECV_MODE, 0 }, { PORT100_IN_PROT_VALID_BIT_NUMBER, 8 }, { PORT100_IN_PROT_CRYPTO1, 0 }, { PORT100_IN_PROT_ADD_SOF, 0 }, { PORT100_IN_PROT_CHECK_SOF, 0 }, { PORT100_IN_PROT_ADD_EOF, 0 }, { PORT100_IN_PROT_CHECK_EOF, 0 }, { PORT100_IN_PROT_DEAF_TIME, 4 }, { PORT100_IN_PROT_CRM, 0 }, { PORT100_IN_PROT_CRM_MIN_LEN, 0 }, { PORT100_IN_PROT_T1_TAG_FRAME, 0 }, { PORT100_IN_PROT_RFCA, 0 }, { PORT100_IN_PROT_GUARD_TIME_AT_INITIATOR, 6 }, { PORT100_IN_PROT_END, 0 }, }, [NFC_DIGITAL_FRAMING_NFCF_T3T] = { /* nfc_digital_framing_nfcf */ { PORT100_IN_PROT_END, 0 }, }, [NFC_DIGITAL_FRAMING_NFCF_NFC_DEP] = { /* nfc_digital_framing_nfcf */ { PORT100_IN_PROT_INITIAL_GUARD_TIME, 18 }, { PORT100_IN_PROT_ADD_CRC, 1 }, { PORT100_IN_PROT_CHECK_CRC, 1 }, { PORT100_IN_PROT_MULTI_CARD, 0 }, { PORT100_IN_PROT_ADD_PARITY, 0 }, { PORT100_IN_PROT_CHECK_PARITY, 0 }, { PORT100_IN_PROT_BITWISE_AC_RECV_MODE, 0 }, { PORT100_IN_PROT_VALID_BIT_NUMBER, 8 }, { PORT100_IN_PROT_CRYPTO1, 0 }, { PORT100_IN_PROT_ADD_SOF, 0 }, { PORT100_IN_PROT_CHECK_SOF, 0 }, { PORT100_IN_PROT_ADD_EOF, 0 }, { PORT100_IN_PROT_CHECK_EOF, 0 }, { PORT100_IN_PROT_DEAF_TIME, 4 }, { PORT100_IN_PROT_CRM, 0 }, { PORT100_IN_PROT_CRM_MIN_LEN, 0 }, { PORT100_IN_PROT_T1_TAG_FRAME, 0 }, { PORT100_IN_PROT_RFCA, 0 }, { PORT100_IN_PROT_GUARD_TIME_AT_INITIATOR, 6 }, { PORT100_IN_PROT_END, 0 }, }, [NFC_DIGITAL_FRAMING_NFC_DEP_ACTIVATED] = { { PORT100_IN_PROT_END, 0 }, }, [NFC_DIGITAL_FRAMING_NFCB] = { { PORT100_IN_PROT_INITIAL_GUARD_TIME, 20 }, { PORT100_IN_PROT_ADD_CRC, 1 }, { PORT100_IN_PROT_CHECK_CRC, 1 }, { PORT100_IN_PROT_MULTI_CARD, 0 }, { PORT100_IN_PROT_ADD_PARITY, 0 }, { PORT100_IN_PROT_CHECK_PARITY, 0 }, { PORT100_IN_PROT_BITWISE_AC_RECV_MODE, 0 }, { PORT100_IN_PROT_VALID_BIT_NUMBER, 8 }, { PORT100_IN_PROT_CRYPTO1, 0 }, { PORT100_IN_PROT_ADD_SOF, 1 }, { PORT100_IN_PROT_CHECK_SOF, 1 }, { PORT100_IN_PROT_ADD_EOF, 1 }, { PORT100_IN_PROT_CHECK_EOF, 1 }, { PORT100_IN_PROT_DEAF_TIME, 4 }, { PORT100_IN_PROT_CRM, 0 }, { PORT100_IN_PROT_CRM_MIN_LEN, 0 }, { PORT100_IN_PROT_T1_TAG_FRAME, 0 }, { PORT100_IN_PROT_RFCA, 0 }, { PORT100_IN_PROT_GUARD_TIME_AT_INITIATOR, 6 }, { PORT100_IN_PROT_END, 0 }, }, [NFC_DIGITAL_FRAMING_NFCB_T4T] = { /* nfc_digital_framing_nfcb */ { PORT100_IN_PROT_END, 0 }, }, /* Ensures the array has NFC_DIGITAL_FRAMING_LAST elements */ [NFC_DIGITAL_FRAMING_LAST] = { { PORT100_IN_PROT_END, 0 }, }, }; static const struct port100_protocol tg_protocols[][PORT100_TG_MAX_NUM_PROTOCOLS + 1] = { [NFC_DIGITAL_FRAMING_NFCA_SHORT] = { { PORT100_TG_PROT_END, 0 }, }, [NFC_DIGITAL_FRAMING_NFCA_STANDARD] = { { PORT100_TG_PROT_END, 0 }, }, [NFC_DIGITAL_FRAMING_NFCA_STANDARD_WITH_CRC_A] = { { PORT100_TG_PROT_END, 0 }, }, [NFC_DIGITAL_FRAMING_NFCA_T1T] = { { PORT100_TG_PROT_END, 0 }, }, [NFC_DIGITAL_FRAMING_NFCA_T2T] = { { PORT100_TG_PROT_END, 0 }, }, [NFC_DIGITAL_FRAMING_NFCA_NFC_DEP] = { { PORT100_TG_PROT_TU, 1 }, { PORT100_TG_PROT_RF_OFF, 0 }, { PORT100_TG_PROT_CRM, 7 }, { PORT100_TG_PROT_END, 0 }, }, [NFC_DIGITAL_FRAMING_NFCF] = { { PORT100_TG_PROT_END, 0 }, }, [NFC_DIGITAL_FRAMING_NFCF_T3T] = { { PORT100_TG_PROT_END, 0 }, }, [NFC_DIGITAL_FRAMING_NFCF_NFC_DEP] = { { PORT100_TG_PROT_TU, 1 }, { PORT100_TG_PROT_RF_OFF, 0 }, { PORT100_TG_PROT_CRM, 7 }, { PORT100_TG_PROT_END, 0 }, }, [NFC_DIGITAL_FRAMING_NFC_DEP_ACTIVATED] = { { PORT100_TG_PROT_RF_OFF, 1 }, { PORT100_TG_PROT_END, 0 }, }, /* Ensures the array has NFC_DIGITAL_FRAMING_LAST elements */ [NFC_DIGITAL_FRAMING_LAST] = { { PORT100_TG_PROT_END, 0 }, }, }; struct port100 { struct nfc_digital_dev *nfc_digital_dev; int skb_headroom; int skb_tailroom; struct usb_device *udev; struct usb_interface *interface; struct urb *out_urb; struct urb *in_urb; /* This mutex protects the out_urb and avoids to submit a new command * through port100_send_frame_async() while the previous one is being * canceled through port100_abort_cmd(). */ struct mutex out_urb_lock; struct work_struct cmd_complete_work; u8 cmd_type; /* The digital stack serializes commands to be sent. There is no need * for any queuing/locking mechanism at driver level. */ struct port100_cmd *cmd; bool cmd_cancel; struct completion cmd_cancel_done; }; struct port100_cmd { u8 code; int status; struct sk_buff *req; struct sk_buff *resp; int resp_len; port100_send_async_complete_t complete_cb; void *complete_cb_context; }; struct port100_frame { u8 preamble; __be16 start_frame; __be16 extended_frame; __le16 datalen; u8 datalen_checksum; u8 data[]; } __packed; struct port100_ack_frame { u8 preamble; __be16 start_frame; __be16 ack_frame; u8 postambule; } __packed; struct port100_cb_arg { nfc_digital_cmd_complete_t complete_cb; void *complete_arg; u8 mdaa; }; struct port100_tg_comm_rf_cmd { __le16 guard_time; __le16 send_timeout; u8 mdaa; u8 nfca_param[6]; u8 nfcf_param[18]; u8 mf_halted; u8 arae_flag; __le16 recv_timeout; u8 data[]; } __packed; struct port100_tg_comm_rf_res { u8 comm_type; u8 ar_status; u8 target_activated; __le32 status; u8 data[]; } __packed; /* The rule: value + checksum = 0 */ static inline u8 port100_checksum(u16 value) { return ~(((u8 *)&value)[0] + ((u8 *)&value)[1]) + 1; } /* The rule: sum(data elements) + checksum = 0 */ static u8 port100_data_checksum(const u8 *data, int datalen) { u8 sum = 0; int i; for (i = 0; i < datalen; i++) sum += data[i]; return port100_checksum(sum); } static void port100_tx_frame_init(void *_frame, u8 cmd_code) { struct port100_frame *frame = _frame; frame->preamble = 0; frame->start_frame = cpu_to_be16(PORT100_FRAME_SOF); frame->extended_frame = cpu_to_be16(PORT100_FRAME_EXT); PORT100_FRAME_DIRECTION(frame) = PORT100_FRAME_DIR_OUT; PORT100_FRAME_CMD(frame) = cmd_code; frame->datalen = cpu_to_le16(2); } static void port100_tx_frame_finish(void *_frame) { struct port100_frame *frame = _frame; frame->datalen_checksum = port100_checksum(le16_to_cpu(frame->datalen)); PORT100_FRAME_CHECKSUM(frame) = port100_data_checksum(frame->data, le16_to_cpu(frame->datalen)); PORT100_FRAME_POSTAMBLE(frame) = 0; } static void port100_tx_update_payload_len(void *_frame, int len) { struct port100_frame *frame = _frame; le16_add_cpu(&frame->datalen, len); } static bool port100_rx_frame_is_valid(const void *_frame) { u8 checksum; const struct port100_frame *frame = _frame; if (frame->start_frame != cpu_to_be16(PORT100_FRAME_SOF) || frame->extended_frame != cpu_to_be16(PORT100_FRAME_EXT)) return false; checksum = port100_checksum(le16_to_cpu(frame->datalen)); if (checksum != frame->datalen_checksum) return false; checksum = port100_data_checksum(frame->data, le16_to_cpu(frame->datalen)); if (checksum != PORT100_FRAME_CHECKSUM(frame)) return false; return true; } static bool port100_rx_frame_is_ack(const struct port100_ack_frame *frame) { return (frame->start_frame == cpu_to_be16(PORT100_FRAME_SOF) && frame->ack_frame == cpu_to_be16(PORT100_FRAME_ACK)); } static inline int port100_rx_frame_size(const void *frame) { const struct port100_frame *f = frame; return sizeof(struct port100_frame) + le16_to_cpu(f->datalen) + PORT100_FRAME_TAIL_LEN; } static bool port100_rx_frame_is_cmd_response(const struct port100 *dev, const void *frame) { const struct port100_frame *f = frame; return (PORT100_FRAME_CMD(f) == PORT100_CMD_RESPONSE(dev->cmd->code)); } static void port100_recv_response(struct urb *urb) { struct port100 *dev = urb->context; struct port100_cmd *cmd = dev->cmd; u8 *in_frame; cmd->status = urb->status; switch (urb->status) { case 0: break; /* success */ case -ECONNRESET: case -ENOENT: nfc_dbg(&dev->interface->dev, "The urb has been canceled (status %d)\n", urb->status); goto sched_wq; case -ESHUTDOWN: default: nfc_err(&dev->interface->dev, "Urb failure (status %d)\n", urb->status); goto sched_wq; } in_frame = dev->in_urb->transfer_buffer; if (!port100_rx_frame_is_valid(in_frame)) { nfc_err(&dev->interface->dev, "Received an invalid frame\n"); cmd->status = -EIO; goto sched_wq; } print_hex_dump_debug("PORT100 RX: ", DUMP_PREFIX_NONE, 16, 1, in_frame, port100_rx_frame_size(in_frame), false); if (!port100_rx_frame_is_cmd_response(dev, in_frame)) { nfc_err(&dev->interface->dev, "It's not the response to the last command\n"); cmd->status = -EIO; goto sched_wq; } sched_wq: schedule_work(&dev->cmd_complete_work); } static int port100_submit_urb_for_response(const struct port100 *dev, gfp_t flags) { dev->in_urb->complete = port100_recv_response; return usb_submit_urb(dev->in_urb, flags); } static void port100_recv_ack(struct urb *urb) { struct port100 *dev = urb->context; struct port100_cmd *cmd = dev->cmd; const struct port100_ack_frame *in_frame; int rc; cmd->status = urb->status; switch (urb->status) { case 0: break; /* success */ case -ECONNRESET: case -ENOENT: nfc_dbg(&dev->interface->dev, "The urb has been stopped (status %d)\n", urb->status); goto sched_wq; case -ESHUTDOWN: default: nfc_err(&dev->interface->dev, "Urb failure (status %d)\n", urb->status); goto sched_wq; } in_frame = dev->in_urb->transfer_buffer; if (!port100_rx_frame_is_ack(in_frame)) { nfc_err(&dev->interface->dev, "Received an invalid ack\n"); cmd->status = -EIO; goto sched_wq; } rc = port100_submit_urb_for_response(dev, GFP_ATOMIC); if (rc) { nfc_err(&dev->interface->dev, "usb_submit_urb failed with result %d\n", rc); cmd->status = rc; goto sched_wq; } return; sched_wq: schedule_work(&dev->cmd_complete_work); } static int port100_submit_urb_for_ack(const struct port100 *dev, gfp_t flags) { dev->in_urb->complete = port100_recv_ack; return usb_submit_urb(dev->in_urb, flags); } static int port100_send_ack(struct port100 *dev) { int rc = 0; mutex_lock(&dev->out_urb_lock); /* * If prior cancel is in-flight (dev->cmd_cancel == true), we * can skip to send cancel. Then this will wait the prior * cancel, or merged into the next cancel rarely if next * cancel was started before waiting done. In any case, this * will be waked up soon or later. */ if (!dev->cmd_cancel) { reinit_completion(&dev->cmd_cancel_done); usb_kill_urb(dev->out_urb); dev->out_urb->transfer_buffer = ack_frame; dev->out_urb->transfer_buffer_length = sizeof(ack_frame); rc = usb_submit_urb(dev->out_urb, GFP_KERNEL); /* * Set the cmd_cancel flag only if the URB has been * successfully submitted. It will be reset by the out * URB completion callback port100_send_complete(). */ dev->cmd_cancel = !rc; } mutex_unlock(&dev->out_urb_lock); if (!rc) wait_for_completion(&dev->cmd_cancel_done); return rc; } static int port100_send_frame_async(struct port100 *dev, const struct sk_buff *out, const struct sk_buff *in, int in_len) { int rc; mutex_lock(&dev->out_urb_lock); /* A command cancel frame as been sent through dev->out_urb. Don't try * to submit a new one. */ if (dev->cmd_cancel) { rc = -EAGAIN; goto exit; } dev->out_urb->transfer_buffer = out->data; dev->out_urb->transfer_buffer_length = out->len; dev->in_urb->transfer_buffer = in->data; dev->in_urb->transfer_buffer_length = in_len; print_hex_dump_debug("PORT100 TX: ", DUMP_PREFIX_NONE, 16, 1, out->data, out->len, false); rc = usb_submit_urb(dev->out_urb, GFP_KERNEL); if (rc) goto exit; rc = port100_submit_urb_for_ack(dev, GFP_KERNEL); if (rc) usb_kill_urb(dev->out_urb); exit: mutex_unlock(&dev->out_urb_lock); return rc; } static void port100_build_cmd_frame(struct port100 *dev, u8 cmd_code, struct sk_buff *skb) { /* payload is already there, just update datalen */ int payload_len = skb->len; skb_push(skb, PORT100_FRAME_HEADER_LEN); skb_put(skb, PORT100_FRAME_TAIL_LEN); port100_tx_frame_init(skb->data, cmd_code); port100_tx_update_payload_len(skb->data, payload_len); port100_tx_frame_finish(skb->data); } static void port100_send_async_complete(struct port100 *dev) { struct port100_cmd *cmd = dev->cmd; int status = cmd->status; struct sk_buff *req = cmd->req; struct sk_buff *resp = cmd->resp; dev_kfree_skb(req); dev->cmd = NULL; if (status < 0) { cmd->complete_cb(dev, cmd->complete_cb_context, ERR_PTR(status)); dev_kfree_skb(resp); goto done; } skb_put(resp, port100_rx_frame_size(resp->data)); skb_pull(resp, PORT100_FRAME_HEADER_LEN); skb_trim(resp, resp->len - PORT100_FRAME_TAIL_LEN); cmd->complete_cb(dev, cmd->complete_cb_context, resp); done: kfree(cmd); } static int port100_send_cmd_async(struct port100 *dev, u8 cmd_code, struct sk_buff *req, port100_send_async_complete_t complete_cb, void *complete_cb_context) { struct port100_cmd *cmd; struct sk_buff *resp; int rc; int resp_len = PORT100_FRAME_HEADER_LEN + PORT100_FRAME_MAX_PAYLOAD_LEN + PORT100_FRAME_TAIL_LEN; if (dev->cmd) { nfc_err(&dev->interface->dev, "A command is still in process\n"); return -EBUSY; } resp = alloc_skb(resp_len, GFP_KERNEL); if (!resp) return -ENOMEM; cmd = kzalloc(sizeof(*cmd), GFP_KERNEL); if (!cmd) { dev_kfree_skb(resp); return -ENOMEM; } cmd->code = cmd_code; cmd->req = req; cmd->resp = resp; cmd->resp_len = resp_len; cmd->complete_cb = complete_cb; cmd->complete_cb_context = complete_cb_context; port100_build_cmd_frame(dev, cmd_code, req); dev->cmd = cmd; rc = port100_send_frame_async(dev, req, resp, resp_len); if (rc) { kfree(cmd); dev_kfree_skb(resp); dev->cmd = NULL; } return rc; } struct port100_sync_cmd_response { struct sk_buff *resp; struct completion done; }; static void port100_wq_cmd_complete(struct work_struct *work) { struct port100 *dev = container_of(work, struct port100, cmd_complete_work); port100_send_async_complete(dev); } static void port100_send_sync_complete(struct port100 *dev, void *_arg, struct sk_buff *resp) { struct port100_sync_cmd_response *arg = _arg; arg->resp = resp; complete(&arg->done); } static struct sk_buff *port100_send_cmd_sync(struct port100 *dev, u8 cmd_code, struct sk_buff *req) { int rc; struct port100_sync_cmd_response arg; init_completion(&arg.done); rc = port100_send_cmd_async(dev, cmd_code, req, port100_send_sync_complete, &arg); if (rc) { dev_kfree_skb(req); return ERR_PTR(rc); } wait_for_completion(&arg.done); return arg.resp; } static void port100_send_complete(struct urb *urb) { struct port100 *dev = urb->context; if (dev->cmd_cancel) { complete_all(&dev->cmd_cancel_done); dev->cmd_cancel = false; } switch (urb->status) { case 0: break; /* success */ case -ECONNRESET: case -ENOENT: nfc_dbg(&dev->interface->dev, "The urb has been stopped (status %d)\n", urb->status); break; case -ESHUTDOWN: default: nfc_err(&dev->interface->dev, "Urb failure (status %d)\n", urb->status); } } static void port100_abort_cmd(struct nfc_digital_dev *ddev) { struct port100 *dev = nfc_digital_get_drvdata(ddev); /* An ack will cancel the last issued command */ port100_send_ack(dev); /* cancel the urb request */ usb_kill_urb(dev->in_urb); } static struct sk_buff *port100_alloc_skb(const struct port100 *dev, unsigned int size) { struct sk_buff *skb; skb = alloc_skb(dev->skb_headroom + dev->skb_tailroom + size, GFP_KERNEL); if (skb) skb_reserve(skb, dev->skb_headroom); return skb; } static int port100_set_command_type(struct port100 *dev, u8 command_type) { struct sk_buff *skb; struct sk_buff *resp; int rc; skb = port100_alloc_skb(dev, 1); if (!skb) return -ENOMEM; skb_put_u8(skb, command_type); resp = port100_send_cmd_sync(dev, PORT100_CMD_SET_COMMAND_TYPE, skb); if (IS_ERR(resp)) return PTR_ERR(resp); rc = resp->data[0]; dev_kfree_skb(resp); return rc; } static u64 port100_get_command_type_mask(struct port100 *dev) { struct sk_buff *skb; struct sk_buff *resp; u64 mask; skb = port100_alloc_skb(dev, 0); if (!skb) return 0; resp = port100_send_cmd_sync(dev, PORT100_CMD_GET_COMMAND_TYPE, skb); if (IS_ERR(resp)) return 0; if (resp->len < 8) mask = 0; else mask = be64_to_cpu(*(__be64 *)resp->data); dev_kfree_skb(resp); return mask; } static u16 port100_get_firmware_version(struct port100 *dev) { struct sk_buff *skb; struct sk_buff *resp; u16 fw_ver; skb = port100_alloc_skb(dev, 0); if (!skb) return 0; resp = port100_send_cmd_sync(dev, PORT100_CMD_GET_FIRMWARE_VERSION, skb); if (IS_ERR(resp)) return 0; fw_ver = le16_to_cpu(*(__le16 *)resp->data); dev_kfree_skb(resp); return fw_ver; } static int port100_switch_rf(struct nfc_digital_dev *ddev, bool on) { struct port100 *dev = nfc_digital_get_drvdata(ddev); struct sk_buff *skb, *resp; skb = port100_alloc_skb(dev, 1); if (!skb) return -ENOMEM; skb_put_u8(skb, on ? 1 : 0); /* Cancel the last command if the device is being switched off */ if (!on) port100_abort_cmd(ddev); resp = port100_send_cmd_sync(dev, PORT100_CMD_SWITCH_RF, skb); if (IS_ERR(resp)) return PTR_ERR(resp); dev_kfree_skb(resp); return 0; } static int port100_in_set_rf(struct nfc_digital_dev *ddev, u8 rf) { struct port100 *dev = nfc_digital_get_drvdata(ddev); struct sk_buff *skb; struct sk_buff *resp; int rc; if (rf >= NFC_DIGITAL_RF_TECH_LAST) return -EINVAL; skb = port100_alloc_skb(dev, sizeof(struct port100_in_rf_setting)); if (!skb) return -ENOMEM; skb_put_data(skb, &in_rf_settings[rf], sizeof(struct port100_in_rf_setting)); resp = port100_send_cmd_sync(dev, PORT100_CMD_IN_SET_RF, skb); if (IS_ERR(resp)) return PTR_ERR(resp); rc = resp->data[0]; dev_kfree_skb(resp); return rc; } static int port100_in_set_framing(struct nfc_digital_dev *ddev, int param) { struct port100 *dev = nfc_digital_get_drvdata(ddev); const struct port100_protocol *protocols; struct sk_buff *skb; struct sk_buff *resp; int num_protocols; size_t size; int rc; if (param >= NFC_DIGITAL_FRAMING_LAST) return -EINVAL; protocols = in_protocols[param]; num_protocols = 0; while (protocols[num_protocols].number != PORT100_IN_PROT_END) num_protocols++; if (!num_protocols) return 0; size = sizeof(struct port100_protocol) * num_protocols; skb = port100_alloc_skb(dev, size); if (!skb) return -ENOMEM; skb_put_data(skb, protocols, size); resp = port100_send_cmd_sync(dev, PORT100_CMD_IN_SET_PROTOCOL, skb); if (IS_ERR(resp)) return PTR_ERR(resp); rc = resp->data[0]; dev_kfree_skb(resp); return rc; } static int port100_in_configure_hw(struct nfc_digital_dev *ddev, int type, int param) { if (type == NFC_DIGITAL_CONFIG_RF_TECH) return port100_in_set_rf(ddev, param); if (type == NFC_DIGITAL_CONFIG_FRAMING) return port100_in_set_framing(ddev, param); return -EINVAL; } static void port100_in_comm_rf_complete(struct port100 *dev, void *arg, struct sk_buff *resp) { const struct port100_cb_arg *cb_arg = arg; nfc_digital_cmd_complete_t cb = cb_arg->complete_cb; u32 status; int rc; if (IS_ERR(resp)) { rc = PTR_ERR(resp); goto exit; } if (resp->len < 4) { nfc_err(&dev->interface->dev, "Invalid packet length received\n"); rc = -EIO; goto error; } status = le32_to_cpu(*(__le32 *)resp->data); skb_pull(resp, sizeof(u32)); if (status == PORT100_CMD_STATUS_TIMEOUT) { rc = -ETIMEDOUT; goto error; } if (status != PORT100_CMD_STATUS_OK) { nfc_err(&dev->interface->dev, "in_comm_rf failed with status 0x%08x\n", status); rc = -EIO; goto error; } /* Remove collision bits byte */ skb_pull(resp, 1); goto exit; error: kfree_skb(resp); resp = ERR_PTR(rc); exit: cb(dev->nfc_digital_dev, cb_arg->complete_arg, resp); kfree(cb_arg); } static int port100_in_send_cmd(struct nfc_digital_dev *ddev, struct sk_buff *skb, u16 _timeout, nfc_digital_cmd_complete_t cb, void *arg) { struct port100 *dev = nfc_digital_get_drvdata(ddev); struct port100_cb_arg *cb_arg; __le16 timeout; cb_arg = kzalloc(sizeof(struct port100_cb_arg), GFP_KERNEL); if (!cb_arg) return -ENOMEM; cb_arg->complete_cb = cb; cb_arg->complete_arg = arg; timeout = cpu_to_le16(_timeout * 10); memcpy(skb_push(skb, sizeof(__le16)), &timeout, sizeof(__le16)); return port100_send_cmd_async(dev, PORT100_CMD_IN_COMM_RF, skb, port100_in_comm_rf_complete, cb_arg); } static int port100_tg_set_rf(struct nfc_digital_dev *ddev, u8 rf) { struct port100 *dev = nfc_digital_get_drvdata(ddev); struct sk_buff *skb; struct sk_buff *resp; int rc; if (rf >= NFC_DIGITAL_RF_TECH_LAST) return -EINVAL; skb = port100_alloc_skb(dev, sizeof(struct port100_tg_rf_setting)); if (!skb) return -ENOMEM; skb_put_data(skb, &tg_rf_settings[rf], sizeof(struct port100_tg_rf_setting)); resp = port100_send_cmd_sync(dev, PORT100_CMD_TG_SET_RF, skb); if (IS_ERR(resp)) return PTR_ERR(resp); rc = resp->data[0]; dev_kfree_skb(resp); return rc; } static int port100_tg_set_framing(struct nfc_digital_dev *ddev, int param) { struct port100 *dev = nfc_digital_get_drvdata(ddev); const struct port100_protocol *protocols; struct sk_buff *skb; struct sk_buff *resp; int rc; int num_protocols; size_t size; if (param >= NFC_DIGITAL_FRAMING_LAST) return -EINVAL; protocols = tg_protocols[param]; num_protocols = 0; while (protocols[num_protocols].number != PORT100_TG_PROT_END) num_protocols++; if (!num_protocols) return 0; size = sizeof(struct port100_protocol) * num_protocols; skb = port100_alloc_skb(dev, size); if (!skb) return -ENOMEM; skb_put_data(skb, protocols, size); resp = port100_send_cmd_sync(dev, PORT100_CMD_TG_SET_PROTOCOL, skb); if (IS_ERR(resp)) return PTR_ERR(resp); rc = resp->data[0]; dev_kfree_skb(resp); return rc; } static int port100_tg_configure_hw(struct nfc_digital_dev *ddev, int type, int param) { if (type == NFC_DIGITAL_CONFIG_RF_TECH) return port100_tg_set_rf(ddev, param); if (type == NFC_DIGITAL_CONFIG_FRAMING) return port100_tg_set_framing(ddev, param); return -EINVAL; } static bool port100_tg_target_activated(struct port100 *dev, u8 tgt_activated) { u8 mask; switch (dev->cmd_type) { case PORT100_CMD_TYPE_0: mask = PORT100_MDAA_TGT_HAS_BEEN_ACTIVATED_MASK; break; case PORT100_CMD_TYPE_1: mask = PORT100_MDAA_TGT_HAS_BEEN_ACTIVATED_MASK | PORT100_MDAA_TGT_WAS_ACTIVATED_MASK; break; default: nfc_err(&dev->interface->dev, "Unknown command type\n"); return false; } return ((tgt_activated & mask) == mask); } static void port100_tg_comm_rf_complete(struct port100 *dev, void *arg, struct sk_buff *resp) { u32 status; const struct port100_cb_arg *cb_arg = arg; nfc_digital_cmd_complete_t cb = cb_arg->complete_cb; struct port100_tg_comm_rf_res *hdr; if (IS_ERR(resp)) goto exit; hdr = (struct port100_tg_comm_rf_res *)resp->data; status = le32_to_cpu(hdr->status); if (cb_arg->mdaa && !port100_tg_target_activated(dev, hdr->target_activated)) { kfree_skb(resp); resp = ERR_PTR(-ETIMEDOUT); goto exit; } skb_pull(resp, sizeof(struct port100_tg_comm_rf_res)); if (status != PORT100_CMD_STATUS_OK) { kfree_skb(resp); if (status == PORT100_CMD_STATUS_TIMEOUT) resp = ERR_PTR(-ETIMEDOUT); else resp = ERR_PTR(-EIO); } exit: cb(dev->nfc_digital_dev, cb_arg->complete_arg, resp); kfree(cb_arg); } static int port100_tg_send_cmd(struct nfc_digital_dev *ddev, struct sk_buff *skb, u16 timeout, nfc_digital_cmd_complete_t cb, void *arg) { struct port100 *dev = nfc_digital_get_drvdata(ddev); struct port100_tg_comm_rf_cmd *hdr; struct port100_cb_arg *cb_arg; cb_arg = kzalloc(sizeof(struct port100_cb_arg), GFP_KERNEL); if (!cb_arg) return -ENOMEM; cb_arg->complete_cb = cb; cb_arg->complete_arg = arg; skb_push(skb, sizeof(struct port100_tg_comm_rf_cmd)); hdr = (struct port100_tg_comm_rf_cmd *)skb->data; memset(hdr, 0, sizeof(struct port100_tg_comm_rf_cmd)); hdr->guard_time = cpu_to_le16(500); hdr->send_timeout = cpu_to_le16(0xFFFF); hdr->recv_timeout = cpu_to_le16(timeout); return port100_send_cmd_async(dev, PORT100_CMD_TG_COMM_RF, skb, port100_tg_comm_rf_complete, cb_arg); } static int port100_listen_mdaa(struct nfc_digital_dev *ddev, struct digital_tg_mdaa_params *params, u16 timeout, nfc_digital_cmd_complete_t cb, void *arg) { struct port100 *dev = nfc_digital_get_drvdata(ddev); struct port100_tg_comm_rf_cmd *hdr; struct port100_cb_arg *cb_arg; struct sk_buff *skb; int rc; rc = port100_tg_configure_hw(ddev, NFC_DIGITAL_CONFIG_RF_TECH, NFC_DIGITAL_RF_TECH_106A); if (rc) return rc; rc = port100_tg_configure_hw(ddev, NFC_DIGITAL_CONFIG_FRAMING, NFC_DIGITAL_FRAMING_NFCA_NFC_DEP); if (rc) return rc; cb_arg = kzalloc(sizeof(struct port100_cb_arg), GFP_KERNEL); if (!cb_arg) return -ENOMEM; cb_arg->complete_cb = cb; cb_arg->complete_arg = arg; cb_arg->mdaa = 1; skb = port100_alloc_skb(dev, 0); if (!skb) { kfree(cb_arg); return -ENOMEM; } skb_push(skb, sizeof(struct port100_tg_comm_rf_cmd)); hdr = (struct port100_tg_comm_rf_cmd *)skb->data; memset(hdr, 0, sizeof(struct port100_tg_comm_rf_cmd)); hdr->guard_time = 0; hdr->send_timeout = cpu_to_le16(0xFFFF); hdr->mdaa = 1; hdr->nfca_param[0] = (params->sens_res >> 8) & 0xFF; hdr->nfca_param[1] = params->sens_res & 0xFF; memcpy(hdr->nfca_param + 2, params->nfcid1, 3); hdr->nfca_param[5] = params->sel_res; memcpy(hdr->nfcf_param, params->nfcid2, 8); hdr->nfcf_param[16] = (params->sc >> 8) & 0xFF; hdr->nfcf_param[17] = params->sc & 0xFF; hdr->recv_timeout = cpu_to_le16(timeout); return port100_send_cmd_async(dev, PORT100_CMD_TG_COMM_RF, skb, port100_tg_comm_rf_complete, cb_arg); } static int port100_listen(struct nfc_digital_dev *ddev, u16 timeout, nfc_digital_cmd_complete_t cb, void *arg) { const struct port100 *dev = nfc_digital_get_drvdata(ddev); struct sk_buff *skb; skb = port100_alloc_skb(dev, 0); if (!skb) return -ENOMEM; return port100_tg_send_cmd(ddev, skb, timeout, cb, arg); } static const struct nfc_digital_ops port100_digital_ops = { .in_configure_hw = port100_in_configure_hw, .in_send_cmd = port100_in_send_cmd, .tg_listen_mdaa = port100_listen_mdaa, .tg_listen = port100_listen, .tg_configure_hw = port100_tg_configure_hw, .tg_send_cmd = port100_tg_send_cmd, .switch_rf = port100_switch_rf, .abort_cmd = port100_abort_cmd, }; static const struct usb_device_id port100_table[] = { { USB_DEVICE(SONY_VENDOR_ID, RCS380S_PRODUCT_ID), }, { USB_DEVICE(SONY_VENDOR_ID, RCS380P_PRODUCT_ID), }, { } }; MODULE_DEVICE_TABLE(usb, port100_table); static int port100_probe(struct usb_interface *interface, const struct usb_device_id *id) { struct port100 *dev; int rc; struct usb_host_interface *iface_desc; struct usb_endpoint_descriptor *endpoint; int in_endpoint; int out_endpoint; u16 fw_version; u64 cmd_type_mask; int i; dev = devm_kzalloc(&interface->dev, sizeof(struct port100), GFP_KERNEL); if (!dev) return -ENOMEM; mutex_init(&dev->out_urb_lock); dev->udev = usb_get_dev(interface_to_usbdev(interface)); dev->interface = interface; usb_set_intfdata(interface, dev); in_endpoint = out_endpoint = 0; iface_desc = interface->cur_altsetting; for (i = 0; i < iface_desc->desc.bNumEndpoints; ++i) { endpoint = &iface_desc->endpoint[i].desc; if (!in_endpoint && usb_endpoint_is_bulk_in(endpoint)) in_endpoint = endpoint->bEndpointAddress; if (!out_endpoint && usb_endpoint_is_bulk_out(endpoint)) out_endpoint = endpoint->bEndpointAddress; } if (!in_endpoint || !out_endpoint) { nfc_err(&interface->dev, "Could not find bulk-in or bulk-out endpoint\n"); rc = -ENODEV; goto error; } dev->in_urb = usb_alloc_urb(0, GFP_KERNEL); dev->out_urb = usb_alloc_urb(0, GFP_KERNEL); if (!dev->in_urb || !dev->out_urb) { nfc_err(&interface->dev, "Could not allocate USB URBs\n"); rc = -ENOMEM; goto error; } usb_fill_bulk_urb(dev->in_urb, dev->udev, usb_rcvbulkpipe(dev->udev, in_endpoint), NULL, 0, NULL, dev); usb_fill_bulk_urb(dev->out_urb, dev->udev, usb_sndbulkpipe(dev->udev, out_endpoint), NULL, 0, port100_send_complete, dev); dev->out_urb->transfer_flags = URB_ZERO_PACKET; dev->skb_headroom = PORT100_FRAME_HEADER_LEN + PORT100_COMM_RF_HEAD_MAX_LEN; dev->skb_tailroom = PORT100_FRAME_TAIL_LEN; init_completion(&dev->cmd_cancel_done); INIT_WORK(&dev->cmd_complete_work, port100_wq_cmd_complete); /* The first thing to do with the Port-100 is to set the command type * to be used. If supported we use command type 1. 0 otherwise. */ cmd_type_mask = port100_get_command_type_mask(dev); if (!cmd_type_mask) { nfc_err(&interface->dev, "Could not get supported command types\n"); rc = -ENODEV; goto error; } if (PORT100_CMD_TYPE_IS_SUPPORTED(cmd_type_mask, PORT100_CMD_TYPE_1)) dev->cmd_type = PORT100_CMD_TYPE_1; else dev->cmd_type = PORT100_CMD_TYPE_0; rc = port100_set_command_type(dev, dev->cmd_type); if (rc) { nfc_err(&interface->dev, "The device does not support command type %u\n", dev->cmd_type); goto error; } fw_version = port100_get_firmware_version(dev); if (!fw_version) nfc_err(&interface->dev, "Could not get device firmware version\n"); nfc_info(&interface->dev, "Sony NFC Port-100 Series attached (firmware v%x.%02x)\n", (fw_version & 0xFF00) >> 8, fw_version & 0xFF); dev->nfc_digital_dev = nfc_digital_allocate_device(&port100_digital_ops, PORT100_PROTOCOLS, PORT100_CAPABILITIES, dev->skb_headroom, dev->skb_tailroom); if (!dev->nfc_digital_dev) { nfc_err(&interface->dev, "Could not allocate nfc_digital_dev\n"); rc = -ENOMEM; goto error; } nfc_digital_set_parent_dev(dev->nfc_digital_dev, &interface->dev); nfc_digital_set_drvdata(dev->nfc_digital_dev, dev); rc = nfc_digital_register_device(dev->nfc_digital_dev); if (rc) { nfc_err(&interface->dev, "Could not register digital device\n"); goto free_nfc_dev; } return 0; free_nfc_dev: nfc_digital_free_device(dev->nfc_digital_dev); error: usb_kill_urb(dev->in_urb); usb_free_urb(dev->in_urb); usb_kill_urb(dev->out_urb); usb_free_urb(dev->out_urb); usb_put_dev(dev->udev); return rc; } static void port100_disconnect(struct usb_interface *interface) { struct port100 *dev; dev = usb_get_intfdata(interface); usb_set_intfdata(interface, NULL); nfc_digital_unregister_device(dev->nfc_digital_dev); nfc_digital_free_device(dev->nfc_digital_dev); usb_kill_urb(dev->in_urb); usb_kill_urb(dev->out_urb); usb_free_urb(dev->in_urb); usb_free_urb(dev->out_urb); usb_put_dev(dev->udev); kfree(dev->cmd); nfc_info(&interface->dev, "Sony Port-100 NFC device disconnected\n"); } static struct usb_driver port100_driver = { .name = "port100", .probe = port100_probe, .disconnect = port100_disconnect, .id_table = port100_table, }; module_usb_driver(port100_driver); MODULE_DESCRIPTION("NFC Port-100 series usb driver ver " VERSION); MODULE_VERSION(VERSION); MODULE_LICENSE("GPL"); |
| 9 132 132 133 132 132 | 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 | /* SPDX-License-Identifier: GPL-2.0-only */ /* * Pointer abstraction for IO/system memory */ #ifndef __IOSYS_MAP_H__ #define __IOSYS_MAP_H__ #include <linux/compiler_types.h> #include <linux/io.h> #include <linux/string.h> /** * DOC: overview * * When accessing a memory region, depending on its location, users may have to * access it with I/O operations or memory load/store operations. For example, * copying to system memory could be done with memcpy(), copying to I/O memory * would be done with memcpy_toio(). * * .. code-block:: c * * void *vaddr = ...; // pointer to system memory * memcpy(vaddr, src, len); * * void *vaddr_iomem = ...; // pointer to I/O memory * memcpy_toio(vaddr_iomem, src, len); * * The user of such pointer may not have information about the mapping of that * region or may want to have a single code path to handle operations on that * buffer, regardless if it's located in system or IO memory. The type * :c:type:`struct iosys_map <iosys_map>` and its helpers abstract that so the * buffer can be passed around to other drivers or have separate duties inside * the same driver for allocation, read and write operations. * * Open-coding access to :c:type:`struct iosys_map <iosys_map>` is considered * bad style. Rather than accessing its fields directly, use one of the provided * helper functions, or implement your own. For example, instances of * :c:type:`struct iosys_map <iosys_map>` can be initialized statically with * IOSYS_MAP_INIT_VADDR(), or at runtime with iosys_map_set_vaddr(). These * helpers will set an address in system memory. * * .. code-block:: c * * struct iosys_map map = IOSYS_MAP_INIT_VADDR(0xdeadbeaf); * * iosys_map_set_vaddr(&map, 0xdeadbeaf); * * To set an address in I/O memory, use IOSYS_MAP_INIT_VADDR_IOMEM() or * iosys_map_set_vaddr_iomem(). * * .. code-block:: c * * struct iosys_map map = IOSYS_MAP_INIT_VADDR_IOMEM(0xdeadbeaf); * * iosys_map_set_vaddr_iomem(&map, 0xdeadbeaf); * * Instances of struct iosys_map do not have to be cleaned up, but * can be cleared to NULL with iosys_map_clear(). Cleared mappings * always refer to system memory. * * .. code-block:: c * * iosys_map_clear(&map); * * Test if a mapping is valid with either iosys_map_is_set() or * iosys_map_is_null(). * * .. code-block:: c * * if (iosys_map_is_set(&map) != iosys_map_is_null(&map)) * // always true * * Instances of :c:type:`struct iosys_map <iosys_map>` can be compared for * equality with iosys_map_is_equal(). Mappings that point to different memory * spaces, system or I/O, are never equal. That's even true if both spaces are * located in the same address space, both mappings contain the same address * value, or both mappings refer to NULL. * * .. code-block:: c * * struct iosys_map sys_map; // refers to system memory * struct iosys_map io_map; // refers to I/O memory * * if (iosys_map_is_equal(&sys_map, &io_map)) * // always false * * A set up instance of struct iosys_map can be used to access or manipulate the * buffer memory. Depending on the location of the memory, the provided helpers * will pick the correct operations. Data can be copied into the memory with * iosys_map_memcpy_to(). The address can be manipulated with iosys_map_incr(). * * .. code-block:: c * * const void *src = ...; // source buffer * size_t len = ...; // length of src * * iosys_map_memcpy_to(&map, src, len); * iosys_map_incr(&map, len); // go to first byte after the memcpy */ /** * struct iosys_map - Pointer to IO/system memory * @vaddr_iomem: The buffer's address if in I/O memory * @vaddr: The buffer's address if in system memory * @is_iomem: True if the buffer is located in I/O memory, or false * otherwise. */ struct iosys_map { union { void __iomem *vaddr_iomem; void *vaddr; }; bool is_iomem; }; /** * IOSYS_MAP_INIT_VADDR - Initializes struct iosys_map to an address in system memory * @vaddr_: A system-memory address */ #define IOSYS_MAP_INIT_VADDR(vaddr_) \ { \ .vaddr = (vaddr_), \ .is_iomem = false, \ } /** * IOSYS_MAP_INIT_VADDR_IOMEM - Initializes struct iosys_map to an address in I/O memory * @vaddr_iomem_: An I/O-memory address */ #define IOSYS_MAP_INIT_VADDR_IOMEM(vaddr_iomem_) \ { \ .vaddr_iomem = (vaddr_iomem_), \ .is_iomem = true, \ } /** * IOSYS_MAP_INIT_OFFSET - Initializes struct iosys_map from another iosys_map * @map_: The dma-buf mapping structure to copy from * @offset_: Offset to add to the other mapping * * Initializes a new iosys_map struct based on another passed as argument. It * does a shallow copy of the struct so it's possible to update the back storage * without changing where the original map points to. It is the equivalent of * doing: * * .. code-block:: c * * iosys_map map = other_map; * iosys_map_incr(&map, &offset); * * Example usage: * * .. code-block:: c * * void foo(struct device *dev, struct iosys_map *base_map) * { * ... * struct iosys_map map = IOSYS_MAP_INIT_OFFSET(base_map, FIELD_OFFSET); * ... * } * * The advantage of using the initializer over just increasing the offset with * iosys_map_incr() like above is that the new map will always point to the * right place of the buffer during its scope. It reduces the risk of updating * the wrong part of the buffer and having no compiler warning about that. If * the assignment to IOSYS_MAP_INIT_OFFSET() is forgotten, the compiler can warn * about the use of uninitialized variable. */ #define IOSYS_MAP_INIT_OFFSET(map_, offset_) ({ \ struct iosys_map copy_ = *map_; \ iosys_map_incr(©_, offset_); \ copy_; \ }) /** * iosys_map_set_vaddr - Sets a iosys mapping structure to an address in system memory * @map: The iosys_map structure * @vaddr: A system-memory address * * Sets the address and clears the I/O-memory flag. */ static inline void iosys_map_set_vaddr(struct iosys_map *map, void *vaddr) { map->vaddr = vaddr; map->is_iomem = false; } /** * iosys_map_set_vaddr_iomem - Sets a iosys mapping structure to an address in I/O memory * @map: The iosys_map structure * @vaddr_iomem: An I/O-memory address * * Sets the address and the I/O-memory flag. */ static inline void iosys_map_set_vaddr_iomem(struct iosys_map *map, void __iomem *vaddr_iomem) { map->vaddr_iomem = vaddr_iomem; map->is_iomem = true; } /** * iosys_map_is_equal - Compares two iosys mapping structures for equality * @lhs: The iosys_map structure * @rhs: A iosys_map structure to compare with * * Two iosys mapping structures are equal if they both refer to the same type of memory * and to the same address within that memory. * * Returns: * True is both structures are equal, or false otherwise. */ static inline bool iosys_map_is_equal(const struct iosys_map *lhs, const struct iosys_map *rhs) { if (lhs->is_iomem != rhs->is_iomem) return false; else if (lhs->is_iomem) return lhs->vaddr_iomem == rhs->vaddr_iomem; else return lhs->vaddr == rhs->vaddr; } /** * iosys_map_is_null - Tests for a iosys mapping to be NULL * @map: The iosys_map structure * * Depending on the state of struct iosys_map.is_iomem, tests if the * mapping is NULL. * * Returns: * True if the mapping is NULL, or false otherwise. */ static inline bool iosys_map_is_null(const struct iosys_map *map) { if (map->is_iomem) return !map->vaddr_iomem; return !map->vaddr; } /** * iosys_map_is_set - Tests if the iosys mapping has been set * @map: The iosys_map structure * * Depending on the state of struct iosys_map.is_iomem, tests if the * mapping has been set. * * Returns: * True if the mapping is been set, or false otherwise. */ static inline bool iosys_map_is_set(const struct iosys_map *map) { return !iosys_map_is_null(map); } /** * iosys_map_clear - Clears a iosys mapping structure * @map: The iosys_map structure * * Clears all fields to zero, including struct iosys_map.is_iomem, so * mapping structures that were set to point to I/O memory are reset for * system memory. Pointers are cleared to NULL. This is the default. */ static inline void iosys_map_clear(struct iosys_map *map) { if (map->is_iomem) { map->vaddr_iomem = NULL; map->is_iomem = false; } else { map->vaddr = NULL; } } /** * iosys_map_memcpy_to - Memcpy into offset of iosys_map * @dst: The iosys_map structure * @dst_offset: The offset from which to copy * @src: The source buffer * @len: The number of byte in src * * Copies data into a iosys_map with an offset. The source buffer is in * system memory. Depending on the buffer's location, the helper picks the * correct method of accessing the memory. */ static inline void iosys_map_memcpy_to(struct iosys_map *dst, size_t dst_offset, const void *src, size_t len) { if (dst->is_iomem) memcpy_toio(dst->vaddr_iomem + dst_offset, src, len); else memcpy(dst->vaddr + dst_offset, src, len); } /** * iosys_map_memcpy_from - Memcpy from iosys_map into system memory * @dst: Destination in system memory * @src: The iosys_map structure * @src_offset: The offset from which to copy * @len: The number of byte in src * * Copies data from a iosys_map with an offset. The dest buffer is in * system memory. Depending on the mapping location, the helper picks the * correct method of accessing the memory. */ static inline void iosys_map_memcpy_from(void *dst, const struct iosys_map *src, size_t src_offset, size_t len) { if (src->is_iomem) memcpy_fromio(dst, src->vaddr_iomem + src_offset, len); else memcpy(dst, src->vaddr + src_offset, len); } /** * iosys_map_incr - Increments the address stored in a iosys mapping * @map: The iosys_map structure * @incr: The number of bytes to increment * * Increments the address stored in a iosys mapping. Depending on the * buffer's location, the correct value will be updated. */ static inline void iosys_map_incr(struct iosys_map *map, size_t incr) { if (map->is_iomem) map->vaddr_iomem += incr; else map->vaddr += incr; } /** * iosys_map_memset - Memset iosys_map * @dst: The iosys_map structure * @offset: Offset from dst where to start setting value * @value: The value to set * @len: The number of bytes to set in dst * * Set value in iosys_map. Depending on the buffer's location, the helper * picks the correct method of accessing the memory. */ static inline void iosys_map_memset(struct iosys_map *dst, size_t offset, int value, size_t len) { if (dst->is_iomem) memset_io(dst->vaddr_iomem + offset, value, len); else memset(dst->vaddr + offset, value, len); } #ifdef CONFIG_64BIT #define __iosys_map_rd_io_u64_case(val_, vaddr_iomem_) \ u64: val_ = readq(vaddr_iomem_) #define __iosys_map_wr_io_u64_case(val_, vaddr_iomem_) \ u64: writeq(val_, vaddr_iomem_) #else #define __iosys_map_rd_io_u64_case(val_, vaddr_iomem_) \ u64: memcpy_fromio(&(val_), vaddr_iomem_, sizeof(u64)) #define __iosys_map_wr_io_u64_case(val_, vaddr_iomem_) \ u64: memcpy_toio(vaddr_iomem_, &(val_), sizeof(u64)) #endif #define __iosys_map_rd_io(val__, vaddr_iomem__, type__) _Generic(val__, \ u8: val__ = readb(vaddr_iomem__), \ u16: val__ = readw(vaddr_iomem__), \ u32: val__ = readl(vaddr_iomem__), \ __iosys_map_rd_io_u64_case(val__, vaddr_iomem__)) #define __iosys_map_rd_sys(val__, vaddr__, type__) \ val__ = READ_ONCE(*(type__ *)(vaddr__)) #define __iosys_map_wr_io(val__, vaddr_iomem__, type__) _Generic(val__, \ u8: writeb(val__, vaddr_iomem__), \ u16: writew(val__, vaddr_iomem__), \ u32: writel(val__, vaddr_iomem__), \ __iosys_map_wr_io_u64_case(val__, vaddr_iomem__)) #define __iosys_map_wr_sys(val__, vaddr__, type__) \ WRITE_ONCE(*(type__ *)(vaddr__), val__) /** * iosys_map_rd - Read a C-type value from the iosys_map * * @map__: The iosys_map structure * @offset__: The offset from which to read * @type__: Type of the value being read * * Read a C type value (u8, u16, u32 and u64) from iosys_map. For other types or * if pointer may be unaligned (and problematic for the architecture supported), * use iosys_map_memcpy_from(). * * Returns: * The value read from the mapping. */ #define iosys_map_rd(map__, offset__, type__) ({ \ type__ val_; \ if ((map__)->is_iomem) { \ __iosys_map_rd_io(val_, (map__)->vaddr_iomem + (offset__), type__); \ } else { \ __iosys_map_rd_sys(val_, (map__)->vaddr + (offset__), type__); \ } \ val_; \ }) /** * iosys_map_wr - Write a C-type value to the iosys_map * * @map__: The iosys_map structure * @offset__: The offset from the mapping to write to * @type__: Type of the value being written * @val__: Value to write * * Write a C type value (u8, u16, u32 and u64) to the iosys_map. For other types * or if pointer may be unaligned (and problematic for the architecture * supported), use iosys_map_memcpy_to() */ #define iosys_map_wr(map__, offset__, type__, val__) ({ \ type__ val_ = (val__); \ if ((map__)->is_iomem) { \ __iosys_map_wr_io(val_, (map__)->vaddr_iomem + (offset__), type__); \ } else { \ __iosys_map_wr_sys(val_, (map__)->vaddr + (offset__), type__); \ } \ }) /** * iosys_map_rd_field - Read a member from a struct in the iosys_map * * @map__: The iosys_map structure * @struct_offset__: Offset from the beginning of the map, where the struct * is located * @struct_type__: The struct describing the layout of the mapping * @field__: Member of the struct to read * * Read a value from iosys_map considering its layout is described by a C struct * starting at @struct_offset__. The field offset and size is calculated and its * value read. If the field access would incur in un-aligned access, then either * iosys_map_memcpy_from() needs to be used or the architecture must support it. * For example: suppose there is a @struct foo defined as below and the value * ``foo.field2.inner2`` needs to be read from the iosys_map: * * .. code-block:: c * * struct foo { * int field1; * struct { * int inner1; * int inner2; * } field2; * int field3; * } __packed; * * This is the expected memory layout of a buffer using iosys_map_rd_field(): * * +------------------------------+--------------------------+ * | Address | Content | * +==============================+==========================+ * | buffer + 0000 | start of mmapped buffer | * | | pointed by iosys_map | * +------------------------------+--------------------------+ * | ... | ... | * +------------------------------+--------------------------+ * | buffer + ``struct_offset__`` | start of ``struct foo`` | * +------------------------------+--------------------------+ * | ... | ... | * +------------------------------+--------------------------+ * | buffer + wwww | ``foo.field2.inner2`` | * +------------------------------+--------------------------+ * | ... | ... | * +------------------------------+--------------------------+ * | buffer + yyyy | end of ``struct foo`` | * +------------------------------+--------------------------+ * | ... | ... | * +------------------------------+--------------------------+ * | buffer + zzzz | end of mmaped buffer | * +------------------------------+--------------------------+ * * Values automatically calculated by this macro or not needed are denoted by * wwww, yyyy and zzzz. This is the code to read that value: * * .. code-block:: c * * x = iosys_map_rd_field(&map, offset, struct foo, field2.inner2); * * Returns: * The value read from the mapping. */ #define iosys_map_rd_field(map__, struct_offset__, struct_type__, field__) ({ \ struct_type__ *s_; \ iosys_map_rd(map__, struct_offset__ + offsetof(struct_type__, field__), \ typeof(s_->field__)); \ }) /** * iosys_map_wr_field - Write to a member of a struct in the iosys_map * * @map__: The iosys_map structure * @struct_offset__: Offset from the beginning of the map, where the struct * is located * @struct_type__: The struct describing the layout of the mapping * @field__: Member of the struct to read * @val__: Value to write * * Write a value to the iosys_map considering its layout is described by a C * struct starting at @struct_offset__. The field offset and size is calculated * and the @val__ is written. If the field access would incur in un-aligned * access, then either iosys_map_memcpy_to() needs to be used or the * architecture must support it. Refer to iosys_map_rd_field() for expected * usage and memory layout. */ #define iosys_map_wr_field(map__, struct_offset__, struct_type__, field__, val__) ({ \ struct_type__ *s_; \ iosys_map_wr(map__, struct_offset__ + offsetof(struct_type__, field__), \ typeof(s_->field__), val__); \ }) #endif /* __IOSYS_MAP_H__ */ |
| 7 106 | 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 | /* SPDX-License-Identifier: GPL-2.0 */ /* * Copyright (C) 2008 Oracle. All rights reserved. */ #ifndef BTRFS_TREE_LOG_H #define BTRFS_TREE_LOG_H #include <linux/list.h> #include <linux/fs.h> #include "messages.h" #include "ctree.h" #include "transaction.h" struct inode; struct dentry; struct btrfs_ordered_extent; struct btrfs_root; struct btrfs_trans_handle; /* return value for btrfs_log_dentry_safe that means we don't need to log it at all */ #define BTRFS_NO_LOG_SYNC 256 /* * We can't use the tree log for whatever reason, force a transaction commit. * We use a negative value because there are functions through the logging code * that need to return an error (< 0 value), false (0) or true (1). Any negative * value will do, as it will cause the log to be marked for a full sync. */ #define BTRFS_LOG_FORCE_COMMIT (-(MAX_ERRNO + 1)) struct btrfs_log_ctx { int log_ret; int log_transid; bool log_new_dentries; bool logging_new_name; bool logging_new_delayed_dentries; /* Indicate if the inode being logged was logged before. */ bool logged_before; struct btrfs_inode *inode; struct list_head list; /* Only used for fast fsyncs. */ struct list_head ordered_extents; struct list_head conflict_inodes; int num_conflict_inodes; bool logging_conflict_inodes; /* * Used for fsyncs that need to copy items from the subvolume tree to * the log tree (full sync flag set or copy everything flag set) to * avoid allocating a temporary extent buffer while holding a lock on * an extent buffer of the subvolume tree and under the log transaction. * Also helps to avoid allocating and freeing a temporary extent buffer * in case we need to process multiple leaves from the subvolume tree. */ struct extent_buffer *scratch_eb; }; void btrfs_init_log_ctx(struct btrfs_log_ctx *ctx, struct btrfs_inode *inode); void btrfs_init_log_ctx_scratch_eb(struct btrfs_log_ctx *ctx); void btrfs_release_log_ctx_extents(struct btrfs_log_ctx *ctx); static inline void btrfs_set_log_full_commit(struct btrfs_trans_handle *trans) { WRITE_ONCE(trans->fs_info->last_trans_log_full_commit, trans->transid); } static inline int btrfs_need_log_full_commit(struct btrfs_trans_handle *trans) { return READ_ONCE(trans->fs_info->last_trans_log_full_commit) == trans->transid; } int btrfs_sync_log(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct btrfs_log_ctx *ctx); int btrfs_free_log(struct btrfs_trans_handle *trans, struct btrfs_root *root); int btrfs_free_log_root_tree(struct btrfs_trans_handle *trans, struct btrfs_fs_info *fs_info); int btrfs_recover_log_trees(struct btrfs_root *tree_root); int btrfs_log_dentry_safe(struct btrfs_trans_handle *trans, struct dentry *dentry, struct btrfs_log_ctx *ctx); void btrfs_del_dir_entries_in_log(struct btrfs_trans_handle *trans, struct btrfs_root *root, const struct fscrypt_str *name, struct btrfs_inode *dir, u64 index); void btrfs_del_inode_ref_in_log(struct btrfs_trans_handle *trans, struct btrfs_root *root, const struct fscrypt_str *name, struct btrfs_inode *inode, u64 dirid); void btrfs_end_log_trans(struct btrfs_root *root); void btrfs_pin_log_trans(struct btrfs_root *root); void btrfs_record_unlink_dir(struct btrfs_trans_handle *trans, struct btrfs_inode *dir, struct btrfs_inode *inode, bool for_rename); void btrfs_record_snapshot_destroy(struct btrfs_trans_handle *trans, struct btrfs_inode *dir); void btrfs_record_new_subvolume(const struct btrfs_trans_handle *trans, struct btrfs_inode *dir); void btrfs_log_new_name(struct btrfs_trans_handle *trans, struct dentry *old_dentry, struct btrfs_inode *old_dir, u64 old_dir_index, struct dentry *parent); #endif |
| 584 | 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 | /* SPDX-License-Identifier: GPL-2.0 */ /* Stage 5 definitions for creating trace events */ /* * remember the offset of each array from the beginning of the event. */ #undef __entry #define __entry entry #ifndef __STAGE5_STRING_SRC_H #define __STAGE5_STRING_SRC_H static inline const char *__string_src(const char *str) { if (!str) return EVENT_NULL_STR; return str; } #endif /* __STAGE5_STRING_SRC_H */ /* * Fields should never declare an array: i.e. __field(int, arr[5]) * If they do, it will cause issues in parsing and possibly corrupt the * events. To prevent that from happening, test the sizeof() a fictitious * type called "struct _test_no_array_##item" which will fail if "item" * contains array elements (like "arr[5]"). * * If you hit this, use __array(int, arr, 5) instead. */ #undef __field #define __field(type, item) \ { (void)sizeof(struct _test_no_array_##item *); } #undef __field_ext #define __field_ext(type, item, filter_type) \ { (void)sizeof(struct _test_no_array_##item *); } #undef __field_struct #define __field_struct(type, item) \ { (void)sizeof(struct _test_no_array_##item *); } #undef __field_struct_ext #define __field_struct_ext(type, item, filter_type) \ { (void)sizeof(struct _test_no_array_##item *); } #undef __array #define __array(type, item, len) #undef __dynamic_array #define __dynamic_array(type, item, len) \ __item_length = (len) * sizeof(type); \ __data_offsets->item = __data_size + \ offsetof(typeof(*entry), __data); \ __data_offsets->item |= __item_length << 16; \ __data_size += __item_length; #undef __string #define __string(item, src) __dynamic_array(char, item, \ strlen(__string_src(src)) + 1) \ __data_offsets->item##_ptr_ = src; #undef __string_len #define __string_len(item, src, len) __dynamic_array(char, item, (len) + 1)\ __data_offsets->item##_ptr_ = src; #undef __vstring #define __vstring(item, fmt, ap) __dynamic_array(char, item, \ __trace_event_vstr_len(fmt, ap)) #undef __rel_dynamic_array #define __rel_dynamic_array(type, item, len) \ __item_length = (len) * sizeof(type); \ __data_offsets->item = __data_size + \ offsetof(typeof(*entry), __data) - \ offsetof(typeof(*entry), __rel_loc_##item) - \ sizeof(u32); \ __data_offsets->item |= __item_length << 16; \ __data_size += __item_length; #undef __rel_string #define __rel_string(item, src) __rel_dynamic_array(char, item, \ strlen(__string_src(src)) + 1) \ __data_offsets->item##_ptr_ = src; #undef __rel_string_len #define __rel_string_len(item, src, len) __rel_dynamic_array(char, item, (len) + 1)\ __data_offsets->item##_ptr_ = src; /* * __bitmask_size_in_bytes_raw is the number of bytes needed to hold * num_possible_cpus(). */ #define __bitmask_size_in_bytes_raw(nr_bits) \ (((nr_bits) + 7) / 8) #define __bitmask_size_in_longs(nr_bits) \ ((__bitmask_size_in_bytes_raw(nr_bits) + \ ((BITS_PER_LONG / 8) - 1)) / (BITS_PER_LONG / 8)) /* * __bitmask_size_in_bytes is the number of bytes needed to hold * num_possible_cpus() padded out to the nearest long. This is what * is saved in the buffer, just to be consistent. */ #define __bitmask_size_in_bytes(nr_bits) \ (__bitmask_size_in_longs(nr_bits) * (BITS_PER_LONG / 8)) #undef __bitmask #define __bitmask(item, nr_bits) __dynamic_array(unsigned long, item, \ __bitmask_size_in_longs(nr_bits)) #undef __cpumask #define __cpumask(item) __bitmask(item, nr_cpumask_bits) #undef __rel_bitmask #define __rel_bitmask(item, nr_bits) __rel_dynamic_array(unsigned long, item, \ __bitmask_size_in_longs(nr_bits)) #undef __rel_cpumask #define __rel_cpumask(item) __rel_bitmask(item, nr_cpumask_bits) #undef __sockaddr #define __sockaddr(field, len) __dynamic_array(u8, field, len) #undef __rel_sockaddr #define __rel_sockaddr(field, len) __rel_dynamic_array(u8, field, len) |
| 2 1 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 | // SPDX-License-Identifier: GPL-2.0-only /* * The NFC Controller Interface is the communication protocol between an * NFC Controller (NFCC) and a Device Host (DH). * * Copyright (C) 2011 Texas Instruments, Inc. * * Written by Ilan Elias <ilane@ti.com> * * Acknowledgements: * This file is based on lib.c, which was written * by Maxim Krasnyansky. */ #include <linux/module.h> #include <linux/kernel.h> #include <linux/types.h> #include <linux/errno.h> #include <net/nfc/nci.h> #include <net/nfc/nci_core.h> /* NCI status codes to Unix errno mapping */ int nci_to_errno(__u8 code) { switch (code) { case NCI_STATUS_OK: return 0; case NCI_STATUS_REJECTED: return -EBUSY; case NCI_STATUS_RF_FRAME_CORRUPTED: return -EBADMSG; case NCI_STATUS_NOT_INITIALIZED: return -EHOSTDOWN; case NCI_STATUS_SYNTAX_ERROR: case NCI_STATUS_SEMANTIC_ERROR: case NCI_STATUS_INVALID_PARAM: case NCI_STATUS_RF_PROTOCOL_ERROR: case NCI_STATUS_NFCEE_PROTOCOL_ERROR: return -EPROTO; case NCI_STATUS_UNKNOWN_GID: case NCI_STATUS_UNKNOWN_OID: return -EBADRQC; case NCI_STATUS_MESSAGE_SIZE_EXCEEDED: return -EMSGSIZE; case NCI_STATUS_DISCOVERY_ALREADY_STARTED: return -EALREADY; case NCI_STATUS_DISCOVERY_TARGET_ACTIVATION_FAILED: case NCI_STATUS_NFCEE_INTERFACE_ACTIVATION_FAILED: return -ECONNREFUSED; case NCI_STATUS_RF_TRANSMISSION_ERROR: case NCI_STATUS_NFCEE_TRANSMISSION_ERROR: return -ECOMM; case NCI_STATUS_RF_TIMEOUT_ERROR: case NCI_STATUS_NFCEE_TIMEOUT_ERROR: return -ETIMEDOUT; case NCI_STATUS_FAILED: default: return -ENOSYS; } } EXPORT_SYMBOL(nci_to_errno); |
| 5 5 3 5 1 1 3 3 2 2 1 2 3 3 1 4 4 4 4 3 4 3 3 4 5 5 5 1 1 4 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * MOSCHIP MCS7830 based (7730/7830/7832) USB 2.0 Ethernet Devices * * based on usbnet.c, asix.c and the vendor provided mcs7830 driver * * Copyright (C) 2010 Andreas Mohr <andi@lisas.de> * Copyright (C) 2006 Arnd Bergmann <arnd@arndb.de> * Copyright (C) 2003-2005 David Hollis <dhollis@davehollis.com> * Copyright (C) 2005 Phil Chang <pchang23@sbcglobal.net> * Copyright (c) 2002-2003 TiVo Inc. * * Definitions gathered from MOSCHIP, Data Sheet_7830DA.pdf (thanks!). * * 2010-12-19: add 7832 USB PID ("functionality same as MCS7830"), * per active notification by manufacturer * * TODO: * - support HIF_REG_CONFIG_SLEEPMODE/HIF_REG_CONFIG_TXENABLE (via autopm?) * - implement ethtool_ops get_pauseparam/set_pauseparam * via HIF_REG_PAUSE_THRESHOLD (>= revision C only!) * - implement get_eeprom/[set_eeprom] * - switch PHY on/off on ifup/ifdown (perhaps in usbnet.c, via MII) * - mcs7830_get_regs() handling is weird: for rev 2 we return 32 regs, * can access only ~ 24, remaining user buffer is uninitialized garbage * - anything else? */ #include <linux/crc32.h> #include <linux/etherdevice.h> #include <linux/ethtool.h> #include <linux/mii.h> #include <linux/module.h> #include <linux/netdevice.h> #include <linux/slab.h> #include <linux/usb.h> #include <linux/usb/usbnet.h> /* requests */ #define MCS7830_RD_BMREQ (USB_DIR_IN | USB_TYPE_VENDOR | \ USB_RECIP_DEVICE) #define MCS7830_WR_BMREQ (USB_DIR_OUT | USB_TYPE_VENDOR | \ USB_RECIP_DEVICE) #define MCS7830_RD_BREQ 0x0E #define MCS7830_WR_BREQ 0x0D #define MCS7830_CTRL_TIMEOUT 1000 #define MCS7830_MAX_MCAST 64 #define MCS7830_VENDOR_ID 0x9710 #define MCS7832_PRODUCT_ID 0x7832 #define MCS7830_PRODUCT_ID 0x7830 #define MCS7730_PRODUCT_ID 0x7730 #define SITECOM_VENDOR_ID 0x0DF6 #define LN_030_PRODUCT_ID 0x0021 #define MCS7830_MII_ADVERTISE (ADVERTISE_PAUSE_CAP | ADVERTISE_100FULL | \ ADVERTISE_100HALF | ADVERTISE_10FULL | \ ADVERTISE_10HALF | ADVERTISE_CSMA) /* HIF_REG_XX corresponding index value */ enum { HIF_REG_MULTICAST_HASH = 0x00, HIF_REG_PACKET_GAP1 = 0x08, HIF_REG_PACKET_GAP2 = 0x09, HIF_REG_PHY_DATA = 0x0a, HIF_REG_PHY_CMD1 = 0x0c, HIF_REG_PHY_CMD1_READ = 0x40, HIF_REG_PHY_CMD1_WRITE = 0x20, HIF_REG_PHY_CMD1_PHYADDR = 0x01, HIF_REG_PHY_CMD2 = 0x0d, HIF_REG_PHY_CMD2_PEND_FLAG_BIT = 0x80, HIF_REG_PHY_CMD2_READY_FLAG_BIT = 0x40, HIF_REG_CONFIG = 0x0e, /* hmm, spec sez: "R/W", "Except bit 3" (likely TXENABLE). */ HIF_REG_CONFIG_CFG = 0x80, HIF_REG_CONFIG_SPEED100 = 0x40, HIF_REG_CONFIG_FULLDUPLEX_ENABLE = 0x20, HIF_REG_CONFIG_RXENABLE = 0x10, HIF_REG_CONFIG_TXENABLE = 0x08, HIF_REG_CONFIG_SLEEPMODE = 0x04, HIF_REG_CONFIG_ALLMULTICAST = 0x02, HIF_REG_CONFIG_PROMISCUOUS = 0x01, HIF_REG_ETHERNET_ADDR = 0x0f, HIF_REG_FRAME_DROP_COUNTER = 0x15, /* 0..ff; reset: 0 */ HIF_REG_PAUSE_THRESHOLD = 0x16, HIF_REG_PAUSE_THRESHOLD_DEFAULT = 0, }; /* Trailing status byte in Ethernet Rx frame */ enum { MCS7830_RX_SHORT_FRAME = 0x01, /* < 64 bytes */ MCS7830_RX_LENGTH_ERROR = 0x02, /* framelen != Ethernet length field */ MCS7830_RX_ALIGNMENT_ERROR = 0x04, /* non-even number of nibbles */ MCS7830_RX_CRC_ERROR = 0x08, MCS7830_RX_LARGE_FRAME = 0x10, /* > 1518 bytes */ MCS7830_RX_FRAME_CORRECT = 0x20, /* frame is correct */ /* [7:6] reserved */ }; struct mcs7830_data { u8 multi_filter[8]; u8 config; }; static const char driver_name[] = "MOSCHIP usb-ethernet driver"; static int mcs7830_get_reg(struct usbnet *dev, u16 index, u16 size, void *data) { int ret; ret = usbnet_read_cmd(dev, MCS7830_RD_BREQ, MCS7830_RD_BMREQ, 0x0000, index, data, size); if (ret < 0) return ret; else if (ret < size) return -ENODATA; return ret; } static int mcs7830_set_reg(struct usbnet *dev, u16 index, u16 size, const void *data) { return usbnet_write_cmd(dev, MCS7830_WR_BREQ, MCS7830_WR_BMREQ, 0x0000, index, data, size); } static void mcs7830_set_reg_async(struct usbnet *dev, u16 index, u16 size, void *data) { usbnet_write_cmd_async(dev, MCS7830_WR_BREQ, MCS7830_WR_BMREQ, 0x0000, index, data, size); } static int mcs7830_hif_get_mac_address(struct usbnet *dev, unsigned char *addr) { int ret = mcs7830_get_reg(dev, HIF_REG_ETHERNET_ADDR, ETH_ALEN, addr); if (ret < 0) return ret; return 0; } static int mcs7830_hif_set_mac_address(struct usbnet *dev, const unsigned char *addr) { int ret = mcs7830_set_reg(dev, HIF_REG_ETHERNET_ADDR, ETH_ALEN, addr); if (ret < 0) return ret; return 0; } static int mcs7830_set_mac_address(struct net_device *netdev, void *p) { int ret; struct usbnet *dev = netdev_priv(netdev); struct sockaddr *addr = p; if (netif_running(netdev)) return -EBUSY; if (!is_valid_ether_addr(addr->sa_data)) return -EADDRNOTAVAIL; ret = mcs7830_hif_set_mac_address(dev, addr->sa_data); if (ret < 0) return ret; /* it worked --> adopt it on netdev side */ eth_hw_addr_set(netdev, addr->sa_data); return 0; } static int mcs7830_read_phy(struct usbnet *dev, u8 index) { int ret; int i; __le16 val; u8 cmd[2] = { HIF_REG_PHY_CMD1_READ | HIF_REG_PHY_CMD1_PHYADDR, HIF_REG_PHY_CMD2_PEND_FLAG_BIT | index, }; mutex_lock(&dev->phy_mutex); /* write the MII command */ ret = mcs7830_set_reg(dev, HIF_REG_PHY_CMD1, 2, cmd); if (ret < 0) goto out; /* wait for the data to become valid, should be within < 1ms */ for (i = 0; i < 10; i++) { ret = mcs7830_get_reg(dev, HIF_REG_PHY_CMD1, 2, cmd); if ((ret < 0) || (cmd[1] & HIF_REG_PHY_CMD2_READY_FLAG_BIT)) break; ret = -EIO; msleep(1); } if (ret < 0) goto out; /* read actual register contents */ ret = mcs7830_get_reg(dev, HIF_REG_PHY_DATA, 2, &val); if (ret < 0) goto out; ret = le16_to_cpu(val); dev_dbg(&dev->udev->dev, "read PHY reg %02x: %04x (%d tries)\n", index, val, i); out: mutex_unlock(&dev->phy_mutex); return ret; } static int mcs7830_write_phy(struct usbnet *dev, u8 index, u16 val) { int ret; int i; __le16 le_val; u8 cmd[2] = { HIF_REG_PHY_CMD1_WRITE | HIF_REG_PHY_CMD1_PHYADDR, HIF_REG_PHY_CMD2_PEND_FLAG_BIT | (index & 0x1F), }; mutex_lock(&dev->phy_mutex); /* write the new register contents */ le_val = cpu_to_le16(val); ret = mcs7830_set_reg(dev, HIF_REG_PHY_DATA, 2, &le_val); if (ret < 0) goto out; /* write the MII command */ ret = mcs7830_set_reg(dev, HIF_REG_PHY_CMD1, 2, cmd); if (ret < 0) goto out; /* wait for the command to be accepted by the PHY */ for (i = 0; i < 10; i++) { ret = mcs7830_get_reg(dev, HIF_REG_PHY_CMD1, 2, cmd); if ((ret < 0) || (cmd[1] & HIF_REG_PHY_CMD2_READY_FLAG_BIT)) break; ret = -EIO; msleep(1); } if (ret < 0) goto out; ret = 0; dev_dbg(&dev->udev->dev, "write PHY reg %02x: %04x (%d tries)\n", index, val, i); out: mutex_unlock(&dev->phy_mutex); return ret; } /* * This algorithm comes from the original mcs7830 version 1.4 driver, * not sure if it is needed. */ static int mcs7830_set_autoneg(struct usbnet *dev, int ptrUserPhyMode) { int ret; /* Enable all media types */ ret = mcs7830_write_phy(dev, MII_ADVERTISE, MCS7830_MII_ADVERTISE); /* First reset BMCR */ if (!ret) ret = mcs7830_write_phy(dev, MII_BMCR, 0x0000); /* Enable Auto Neg */ if (!ret) ret = mcs7830_write_phy(dev, MII_BMCR, BMCR_ANENABLE); /* Restart Auto Neg (Keep the Enable Auto Neg Bit Set) */ if (!ret) ret = mcs7830_write_phy(dev, MII_BMCR, BMCR_ANENABLE | BMCR_ANRESTART ); return ret; } /* * if we can read register 22, the chip revision is C or higher */ static int mcs7830_get_rev(struct usbnet *dev) { u8 dummy[2]; int ret; ret = mcs7830_get_reg(dev, HIF_REG_FRAME_DROP_COUNTER, 2, dummy); if (ret > 0) return 2; /* Rev C or later */ return 1; /* earlier revision */ } /* * On rev. C we need to set the pause threshold */ static void mcs7830_rev_C_fixup(struct usbnet *dev) { u8 pause_threshold = HIF_REG_PAUSE_THRESHOLD_DEFAULT; int retry; for (retry = 0; retry < 2; retry++) { if (mcs7830_get_rev(dev) == 2) { dev_info(&dev->udev->dev, "applying rev.C fixup\n"); mcs7830_set_reg(dev, HIF_REG_PAUSE_THRESHOLD, 1, &pause_threshold); } msleep(1); } } static int mcs7830_mdio_read(struct net_device *netdev, int phy_id, int location) { struct usbnet *dev = netdev_priv(netdev); return mcs7830_read_phy(dev, location); } static void mcs7830_mdio_write(struct net_device *netdev, int phy_id, int location, int val) { struct usbnet *dev = netdev_priv(netdev); mcs7830_write_phy(dev, location, val); } static int mcs7830_ioctl(struct net_device *net, struct ifreq *rq, int cmd) { struct usbnet *dev = netdev_priv(net); return generic_mii_ioctl(&dev->mii, if_mii(rq), cmd, NULL); } static inline struct mcs7830_data *mcs7830_get_data(struct usbnet *dev) { return (struct mcs7830_data *)&dev->data; } static void mcs7830_hif_update_multicast_hash(struct usbnet *dev) { struct mcs7830_data *data = mcs7830_get_data(dev); mcs7830_set_reg_async(dev, HIF_REG_MULTICAST_HASH, sizeof data->multi_filter, data->multi_filter); } static void mcs7830_hif_update_config(struct usbnet *dev) { /* implementation specific to data->config (argument needs to be heap-based anyway - USB DMA!) */ struct mcs7830_data *data = mcs7830_get_data(dev); mcs7830_set_reg_async(dev, HIF_REG_CONFIG, 1, &data->config); } static void mcs7830_data_set_multicast(struct net_device *net) { struct usbnet *dev = netdev_priv(net); struct mcs7830_data *data = mcs7830_get_data(dev); memset(data->multi_filter, 0, sizeof data->multi_filter); data->config = HIF_REG_CONFIG_TXENABLE; /* this should not be needed, but it doesn't work otherwise */ data->config |= HIF_REG_CONFIG_ALLMULTICAST; if (net->flags & IFF_PROMISC) { data->config |= HIF_REG_CONFIG_PROMISCUOUS; } else if (net->flags & IFF_ALLMULTI || netdev_mc_count(net) > MCS7830_MAX_MCAST) { data->config |= HIF_REG_CONFIG_ALLMULTICAST; } else if (netdev_mc_empty(net)) { /* just broadcast and directed */ } else { /* We use the 20 byte dev->data * for our 8 byte filter buffer * to avoid allocating memory that * is tricky to free later */ struct netdev_hw_addr *ha; u32 crc_bits; /* Build the multicast hash filter. */ netdev_for_each_mc_addr(ha, net) { crc_bits = ether_crc(ETH_ALEN, ha->addr) >> 26; data->multi_filter[crc_bits >> 3] |= 1 << (crc_bits & 7); } } } static int mcs7830_apply_base_config(struct usbnet *dev) { int ret; /* re-configure known MAC (suspend case etc.) */ ret = mcs7830_hif_set_mac_address(dev, dev->net->dev_addr); if (ret) { dev_info(&dev->udev->dev, "Cannot set MAC address\n"); goto out; } /* Set up PHY */ ret = mcs7830_set_autoneg(dev, 0); if (ret) { dev_info(&dev->udev->dev, "Cannot set autoneg\n"); goto out; } mcs7830_hif_update_multicast_hash(dev); mcs7830_hif_update_config(dev); mcs7830_rev_C_fixup(dev); ret = 0; out: return ret; } /* credits go to asix_set_multicast */ static void mcs7830_set_multicast(struct net_device *net) { struct usbnet *dev = netdev_priv(net); mcs7830_data_set_multicast(net); mcs7830_hif_update_multicast_hash(dev); mcs7830_hif_update_config(dev); } static int mcs7830_get_regs_len(struct net_device *net) { struct usbnet *dev = netdev_priv(net); switch (mcs7830_get_rev(dev)) { case 1: return 21; case 2: return 32; } return 0; } static void mcs7830_get_drvinfo(struct net_device *net, struct ethtool_drvinfo *drvinfo) { usbnet_get_drvinfo(net, drvinfo); } static void mcs7830_get_regs(struct net_device *net, struct ethtool_regs *regs, void *data) { struct usbnet *dev = netdev_priv(net); regs->version = mcs7830_get_rev(dev); mcs7830_get_reg(dev, 0, regs->len, data); } static const struct ethtool_ops mcs7830_ethtool_ops = { .get_drvinfo = mcs7830_get_drvinfo, .get_regs_len = mcs7830_get_regs_len, .get_regs = mcs7830_get_regs, /* common usbnet calls */ .get_link = usbnet_get_link, .get_msglevel = usbnet_get_msglevel, .set_msglevel = usbnet_set_msglevel, .nway_reset = usbnet_nway_reset, .get_link_ksettings = usbnet_get_link_ksettings_mii, .set_link_ksettings = usbnet_set_link_ksettings_mii, }; static const struct net_device_ops mcs7830_netdev_ops = { .ndo_open = usbnet_open, .ndo_stop = usbnet_stop, .ndo_start_xmit = usbnet_start_xmit, .ndo_tx_timeout = usbnet_tx_timeout, .ndo_change_mtu = usbnet_change_mtu, .ndo_get_stats64 = dev_get_tstats64, .ndo_validate_addr = eth_validate_addr, .ndo_eth_ioctl = mcs7830_ioctl, .ndo_set_rx_mode = mcs7830_set_multicast, .ndo_set_mac_address = mcs7830_set_mac_address, }; static int mcs7830_bind(struct usbnet *dev, struct usb_interface *udev) { struct net_device *net = dev->net; u8 addr[ETH_ALEN]; int ret; int retry; /* Initial startup: Gather MAC address setting from EEPROM */ ret = -EINVAL; for (retry = 0; retry < 5 && ret; retry++) ret = mcs7830_hif_get_mac_address(dev, addr); if (ret) { dev_warn(&dev->udev->dev, "Cannot read MAC address\n"); goto out; } eth_hw_addr_set(net, addr); mcs7830_data_set_multicast(net); ret = mcs7830_apply_base_config(dev); if (ret) goto out; net->ethtool_ops = &mcs7830_ethtool_ops; net->netdev_ops = &mcs7830_netdev_ops; /* reserve space for the status byte on rx */ dev->rx_urb_size = ETH_FRAME_LEN + 1; dev->mii.mdio_read = mcs7830_mdio_read; dev->mii.mdio_write = mcs7830_mdio_write; dev->mii.dev = net; dev->mii.phy_id_mask = 0x3f; dev->mii.reg_num_mask = 0x1f; dev->mii.phy_id = *((u8 *) net->dev_addr + 1); ret = usbnet_get_endpoints(dev, udev); out: return ret; } /* The chip always appends a status byte that we need to strip */ static int mcs7830_rx_fixup(struct usbnet *dev, struct sk_buff *skb) { u8 status; /* This check is no longer done by usbnet */ if (skb->len < dev->net->hard_header_len) { dev_err(&dev->udev->dev, "unexpected tiny rx frame\n"); return 0; } skb_trim(skb, skb->len - 1); status = skb->data[skb->len]; if (status != MCS7830_RX_FRAME_CORRECT) { dev_dbg(&dev->udev->dev, "rx fixup status %x\n", status); /* hmm, perhaps usbnet.c already sees a globally visible frame error and increments rx_errors on its own already? */ dev->net->stats.rx_errors++; if (status & (MCS7830_RX_SHORT_FRAME |MCS7830_RX_LENGTH_ERROR |MCS7830_RX_LARGE_FRAME)) dev->net->stats.rx_length_errors++; if (status & MCS7830_RX_ALIGNMENT_ERROR) dev->net->stats.rx_frame_errors++; if (status & MCS7830_RX_CRC_ERROR) dev->net->stats.rx_crc_errors++; } return skb->len > 0; } static void mcs7830_status(struct usbnet *dev, struct urb *urb) { u8 *buf = urb->transfer_buffer; bool link, link_changed; if (urb->actual_length < 16) return; link = !(buf[1] == 0x20); link_changed = netif_carrier_ok(dev->net) != link; if (link_changed) { usbnet_link_change(dev, link, 0); netdev_dbg(dev->net, "Link Status is: %d\n", link); } } static const struct driver_info moschip_info = { .description = "MOSCHIP 7830/7832/7730 usb-NET adapter", .bind = mcs7830_bind, .rx_fixup = mcs7830_rx_fixup, .flags = FLAG_ETHER | FLAG_LINK_INTR, .status = mcs7830_status, .in = 1, .out = 2, }; static const struct driver_info sitecom_info = { .description = "Sitecom LN-30 usb-NET adapter", .bind = mcs7830_bind, .rx_fixup = mcs7830_rx_fixup, .flags = FLAG_ETHER | FLAG_LINK_INTR, .status = mcs7830_status, .in = 1, .out = 2, }; static const struct usb_device_id products[] = { { USB_DEVICE(MCS7830_VENDOR_ID, MCS7832_PRODUCT_ID), .driver_info = (unsigned long) &moschip_info, }, { USB_DEVICE(MCS7830_VENDOR_ID, MCS7830_PRODUCT_ID), .driver_info = (unsigned long) &moschip_info, }, { USB_DEVICE(MCS7830_VENDOR_ID, MCS7730_PRODUCT_ID), .driver_info = (unsigned long) &moschip_info, }, { USB_DEVICE(SITECOM_VENDOR_ID, LN_030_PRODUCT_ID), .driver_info = (unsigned long) &sitecom_info, }, {}, }; MODULE_DEVICE_TABLE(usb, products); static int mcs7830_reset_resume (struct usb_interface *intf) { /* YES, this function is successful enough that ethtool -d does show same output pre-/post-suspend */ struct usbnet *dev = usb_get_intfdata(intf); mcs7830_apply_base_config(dev); usbnet_resume(intf); return 0; } static struct usb_driver mcs7830_driver = { .name = driver_name, .id_table = products, .probe = usbnet_probe, .disconnect = usbnet_disconnect, .suspend = usbnet_suspend, .resume = usbnet_resume, .reset_resume = mcs7830_reset_resume, .disable_hub_initiated_lpm = 1, }; module_usb_driver(mcs7830_driver); MODULE_DESCRIPTION("USB to network adapter MCS7830)"); MODULE_LICENSE("GPL"); |
| 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 2 1 1 1 1 1 1 1 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 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 | // SPDX-License-Identifier: GPL-2.0 #include "bcachefs.h" #include "bcachefs_ioctl.h" #include "bkey_buf.h" #include "btree_cache.h" #include "btree_update.h" #include "buckets.h" #include "darray.h" #include "dirent.h" #include "error.h" #include "fs.h" #include "fsck.h" #include "inode.h" #include "io_misc.h" #include "keylist.h" #include "namei.h" #include "recovery_passes.h" #include "snapshot.h" #include "super.h" #include "thread_with_file.h" #include "xattr.h" #include <linux/bsearch.h> #include <linux/dcache.h> /* struct qstr */ static int dirent_points_to_inode_nowarn(struct bch_fs *c, struct bkey_s_c_dirent d, struct bch_inode_unpacked *inode) { if (d.v->d_type == DT_SUBVOL ? le32_to_cpu(d.v->d_child_subvol) == inode->bi_subvol : le64_to_cpu(d.v->d_inum) == inode->bi_inum) return 0; return bch_err_throw(c, ENOENT_dirent_doesnt_match_inode); } static void dirent_inode_mismatch_msg(struct printbuf *out, struct bch_fs *c, struct bkey_s_c_dirent dirent, struct bch_inode_unpacked *inode) { prt_str(out, "inode points to dirent that does not point back:"); prt_newline(out); bch2_bkey_val_to_text(out, c, dirent.s_c); prt_newline(out); bch2_inode_unpacked_to_text(out, inode); } static int dirent_points_to_inode(struct bch_fs *c, struct bkey_s_c_dirent dirent, struct bch_inode_unpacked *inode) { int ret = dirent_points_to_inode_nowarn(c, dirent, inode); if (ret) { struct printbuf buf = PRINTBUF; dirent_inode_mismatch_msg(&buf, c, dirent, inode); bch_warn(c, "%s", buf.buf); printbuf_exit(&buf); } return ret; } /* * XXX: this is handling transaction restarts without returning * -BCH_ERR_transaction_restart_nested, this is not how we do things anymore: */ static s64 bch2_count_inode_sectors(struct btree_trans *trans, u64 inum, u32 snapshot) { u64 sectors = 0; int ret = for_each_btree_key_max(trans, iter, BTREE_ID_extents, SPOS(inum, 0, snapshot), POS(inum, U64_MAX), 0, k, ({ if (bkey_extent_is_allocation(k.k)) sectors += k.k->size; 0; })); return ret ?: sectors; } static s64 bch2_count_subdirs(struct btree_trans *trans, u64 inum, u32 snapshot) { u64 subdirs = 0; int ret = for_each_btree_key_max(trans, iter, BTREE_ID_dirents, SPOS(inum, 0, snapshot), POS(inum, U64_MAX), 0, k, ({ if (k.k->type == KEY_TYPE_dirent && bkey_s_c_to_dirent(k).v->d_type == DT_DIR) subdirs++; 0; })); return ret ?: subdirs; } static int subvol_lookup(struct btree_trans *trans, u32 subvol, u32 *snapshot, u64 *inum) { struct bch_subvolume s; int ret = bch2_subvolume_get(trans, subvol, false, &s); *snapshot = le32_to_cpu(s.snapshot); *inum = le64_to_cpu(s.inode); return ret; } static int lookup_dirent_in_snapshot(struct btree_trans *trans, struct bch_hash_info hash_info, subvol_inum dir, struct qstr *name, u64 *target, unsigned *type, u32 snapshot) { struct btree_iter iter; struct bkey_s_c k = bch2_hash_lookup_in_snapshot(trans, &iter, bch2_dirent_hash_desc, &hash_info, dir, name, 0, snapshot); int ret = bkey_err(k); if (ret) return ret; struct bkey_s_c_dirent d = bkey_s_c_to_dirent(k); *target = le64_to_cpu(d.v->d_inum); *type = d.v->d_type; bch2_trans_iter_exit(trans, &iter); return 0; } /* * Find any subvolume associated with a tree of snapshots * We can't rely on master_subvol - it might have been deleted. */ static int find_snapshot_tree_subvol(struct btree_trans *trans, u32 tree_id, u32 *subvol) { struct btree_iter iter; struct bkey_s_c k; int ret; for_each_btree_key_norestart(trans, iter, BTREE_ID_snapshots, POS_MIN, 0, k, ret) { if (k.k->type != KEY_TYPE_snapshot) continue; struct bkey_s_c_snapshot s = bkey_s_c_to_snapshot(k); if (le32_to_cpu(s.v->tree) != tree_id) continue; if (s.v->subvol) { *subvol = le32_to_cpu(s.v->subvol); goto found; } } ret = bch_err_throw(trans->c, ENOENT_no_snapshot_tree_subvol); found: bch2_trans_iter_exit(trans, &iter); return ret; } /* Get lost+found, create if it doesn't exist: */ static int lookup_lostfound(struct btree_trans *trans, u32 snapshot, struct bch_inode_unpacked *lostfound, u64 reattaching_inum) { struct bch_fs *c = trans->c; struct qstr lostfound_str = QSTR("lost+found"); struct btree_iter lostfound_iter = {}; u64 inum = 0; unsigned d_type = 0; int ret; struct bch_snapshot_tree st; ret = bch2_snapshot_tree_lookup(trans, bch2_snapshot_tree(c, snapshot), &st); if (ret) return ret; u32 subvolid; ret = find_snapshot_tree_subvol(trans, bch2_snapshot_tree(c, snapshot), &subvolid); bch_err_msg(c, ret, "finding subvol associated with snapshot tree %u", bch2_snapshot_tree(c, snapshot)); if (ret) return ret; struct bch_subvolume subvol; ret = bch2_subvolume_get(trans, subvolid, false, &subvol); bch_err_msg(c, ret, "looking up subvol %u for snapshot %u", subvolid, snapshot); if (ret) return ret; if (!subvol.inode) { struct btree_iter iter; struct bkey_i_subvolume *subvol = bch2_bkey_get_mut_typed(trans, &iter, BTREE_ID_subvolumes, POS(0, subvolid), 0, subvolume); ret = PTR_ERR_OR_ZERO(subvol); if (ret) return ret; subvol->v.inode = cpu_to_le64(reattaching_inum); bch2_trans_iter_exit(trans, &iter); } subvol_inum root_inum = { .subvol = subvolid, .inum = le64_to_cpu(subvol.inode) }; struct bch_inode_unpacked root_inode; struct bch_hash_info root_hash_info; ret = bch2_inode_find_by_inum_snapshot(trans, root_inum.inum, snapshot, &root_inode, 0); bch_err_msg(c, ret, "looking up root inode %llu for subvol %u", root_inum.inum, subvolid); if (ret) return ret; root_hash_info = bch2_hash_info_init(c, &root_inode); ret = lookup_dirent_in_snapshot(trans, root_hash_info, root_inum, &lostfound_str, &inum, &d_type, snapshot); if (bch2_err_matches(ret, ENOENT)) goto create_lostfound; bch_err_fn(c, ret); if (ret) return ret; if (d_type != DT_DIR) { bch_err(c, "error looking up lost+found: not a directory"); return bch_err_throw(c, ENOENT_not_directory); } /* * The bch2_check_dirents pass has already run, dangling dirents * shouldn't exist here: */ ret = bch2_inode_find_by_inum_snapshot(trans, inum, snapshot, lostfound, 0); bch_err_msg(c, ret, "looking up lost+found %llu:%u in (root inode %llu, snapshot root %u)", inum, snapshot, root_inum.inum, bch2_snapshot_root(c, snapshot)); return ret; create_lostfound: /* * we always create lost+found in the root snapshot; we don't want * different branches of the snapshot tree to have different lost+found */ snapshot = le32_to_cpu(st.root_snapshot); /* * XXX: we could have a nicer log message here if we had a nice way to * walk backpointers to print a path */ struct printbuf path = PRINTBUF; ret = bch2_inum_to_path(trans, root_inum, &path); if (ret) goto err; bch_notice(c, "creating %s/lost+found in subvol %llu snapshot %u", path.buf, root_inum.subvol, snapshot); printbuf_exit(&path); u64 now = bch2_current_time(c); u64 cpu = raw_smp_processor_id(); bch2_inode_init_early(c, lostfound); bch2_inode_init_late(c, lostfound, now, 0, 0, S_IFDIR|0700, 0, &root_inode); lostfound->bi_dir = root_inode.bi_inum; lostfound->bi_snapshot = le32_to_cpu(st.root_snapshot); root_inode.bi_nlink++; ret = bch2_inode_create(trans, &lostfound_iter, lostfound, snapshot, cpu); if (ret) goto err; bch2_btree_iter_set_snapshot(trans, &lostfound_iter, snapshot); ret = bch2_btree_iter_traverse(trans, &lostfound_iter); if (ret) goto err; ret = bch2_dirent_create_snapshot(trans, 0, root_inode.bi_inum, snapshot, &root_hash_info, mode_to_type(lostfound->bi_mode), &lostfound_str, lostfound->bi_inum, &lostfound->bi_dir_offset, BTREE_UPDATE_internal_snapshot_node| STR_HASH_must_create) ?: bch2_inode_write_flags(trans, &lostfound_iter, lostfound, BTREE_UPDATE_internal_snapshot_node); err: bch_err_msg(c, ret, "creating lost+found"); bch2_trans_iter_exit(trans, &lostfound_iter); return ret; } static inline bool inode_should_reattach(struct bch_inode_unpacked *inode) { if (inode->bi_inum == BCACHEFS_ROOT_INO && inode->bi_subvol == BCACHEFS_ROOT_SUBVOL) return false; /* * Subvolume roots are special: older versions of subvolume roots may be * disconnected, it's only the newest version that matters. * * We only keep a single dirent pointing to a subvolume root, i.e. * older versions of snapshots will not have a different dirent pointing * to the same subvolume root. * * This is because dirents that point to subvolumes are only visible in * the parent subvolume - versioning is not needed - and keeping them * around would break fsck, because when we're crossing subvolumes we * don't have a consistent snapshot ID to do check the inode <-> dirent * relationships. * * Thus, a subvolume root that's been renamed after a snapshot will have * a disconnected older version - that's expected. * * Note that taking a snapshot always updates the root inode (to update * the dirent backpointer), so a subvolume root inode with * BCH_INODE_has_child_snapshot is never visible. */ if (inode->bi_subvol && (inode->bi_flags & BCH_INODE_has_child_snapshot)) return false; return !bch2_inode_has_backpointer(inode) && !(inode->bi_flags & BCH_INODE_unlinked); } static int maybe_delete_dirent(struct btree_trans *trans, struct bpos d_pos, u32 snapshot) { struct btree_iter iter; struct bkey_s_c k = bch2_bkey_get_iter(trans, &iter, BTREE_ID_dirents, SPOS(d_pos.inode, d_pos.offset, snapshot), BTREE_ITER_intent| BTREE_ITER_with_updates); int ret = bkey_err(k); if (ret) return ret; if (bpos_eq(k.k->p, d_pos)) { /* * delet_at() doesn't work because the update path doesn't * internally use BTREE_ITER_with_updates yet */ struct bkey_i *k = bch2_trans_kmalloc(trans, sizeof(*k)); ret = PTR_ERR_OR_ZERO(k); if (ret) goto err; bkey_init(&k->k); k->k.type = KEY_TYPE_whiteout; k->k.p = iter.pos; ret = bch2_trans_update(trans, &iter, k, BTREE_UPDATE_internal_snapshot_node); } err: bch2_trans_iter_exit(trans, &iter); return ret; } static int reattach_inode(struct btree_trans *trans, struct bch_inode_unpacked *inode) { struct bch_fs *c = trans->c; struct bch_inode_unpacked lostfound; char name_buf[20]; int ret; u32 dirent_snapshot = inode->bi_snapshot; if (inode->bi_subvol) { inode->bi_parent_subvol = BCACHEFS_ROOT_SUBVOL; struct btree_iter subvol_iter; struct bkey_i_subvolume *subvol = bch2_bkey_get_mut_typed(trans, &subvol_iter, BTREE_ID_subvolumes, POS(0, inode->bi_subvol), 0, subvolume); ret = PTR_ERR_OR_ZERO(subvol); if (ret) return ret; subvol->v.fs_path_parent = BCACHEFS_ROOT_SUBVOL; bch2_trans_iter_exit(trans, &subvol_iter); u64 root_inum; ret = subvol_lookup(trans, inode->bi_parent_subvol, &dirent_snapshot, &root_inum); if (ret) return ret; snprintf(name_buf, sizeof(name_buf), "subvol-%u", inode->bi_subvol); } else { snprintf(name_buf, sizeof(name_buf), "%llu", inode->bi_inum); } ret = lookup_lostfound(trans, dirent_snapshot, &lostfound, inode->bi_inum); if (ret) return ret; bch_verbose(c, "got lostfound inum %llu", lostfound.bi_inum); lostfound.bi_nlink += S_ISDIR(inode->bi_mode); /* ensure lost+found inode is also present in inode snapshot */ if (!inode->bi_subvol) { BUG_ON(!bch2_snapshot_is_ancestor(c, inode->bi_snapshot, lostfound.bi_snapshot)); lostfound.bi_snapshot = inode->bi_snapshot; } ret = __bch2_fsck_write_inode(trans, &lostfound); if (ret) return ret; struct bch_hash_info dir_hash = bch2_hash_info_init(c, &lostfound); struct qstr name = QSTR(name_buf); inode->bi_dir = lostfound.bi_inum; ret = bch2_dirent_create_snapshot(trans, inode->bi_parent_subvol, lostfound.bi_inum, dirent_snapshot, &dir_hash, inode_d_type(inode), &name, inode->bi_subvol ?: inode->bi_inum, &inode->bi_dir_offset, BTREE_UPDATE_internal_snapshot_node| STR_HASH_must_create); if (ret) { bch_err_msg(c, ret, "error creating dirent"); return ret; } ret = __bch2_fsck_write_inode(trans, inode); if (ret) return ret; { CLASS(printbuf, buf)(); ret = bch2_inum_snapshot_to_path(trans, inode->bi_inum, inode->bi_snapshot, NULL, &buf); if (ret) return ret; bch_info(c, "reattached at %s", buf.buf); } /* * Fix up inodes in child snapshots: if they should also be reattached * update the backpointer field, if they should not be we need to emit * whiteouts for the dirent we just created. */ if (!inode->bi_subvol && bch2_snapshot_is_leaf(c, inode->bi_snapshot) <= 0) { snapshot_id_list whiteouts_done; struct btree_iter iter; struct bkey_s_c k; darray_init(&whiteouts_done); for_each_btree_key_reverse_norestart(trans, iter, BTREE_ID_inodes, SPOS(0, inode->bi_inum, inode->bi_snapshot - 1), BTREE_ITER_all_snapshots|BTREE_ITER_intent, k, ret) { if (k.k->p.offset != inode->bi_inum) break; if (!bkey_is_inode(k.k) || !bch2_snapshot_is_ancestor(c, k.k->p.snapshot, inode->bi_snapshot) || snapshot_list_has_ancestor(c, &whiteouts_done, k.k->p.snapshot)) continue; struct bch_inode_unpacked child_inode; ret = bch2_inode_unpack(k, &child_inode); if (ret) break; if (!inode_should_reattach(&child_inode)) { ret = maybe_delete_dirent(trans, SPOS(lostfound.bi_inum, inode->bi_dir_offset, dirent_snapshot), k.k->p.snapshot); if (ret) break; ret = snapshot_list_add(c, &whiteouts_done, k.k->p.snapshot); if (ret) break; } else { iter.snapshot = k.k->p.snapshot; child_inode.bi_dir = inode->bi_dir; child_inode.bi_dir_offset = inode->bi_dir_offset; ret = bch2_inode_write_flags(trans, &iter, &child_inode, BTREE_UPDATE_internal_snapshot_node); if (ret) break; } } darray_exit(&whiteouts_done); bch2_trans_iter_exit(trans, &iter); } return ret; } static struct bkey_s_c_dirent dirent_get_by_pos(struct btree_trans *trans, struct btree_iter *iter, struct bpos pos) { return bch2_bkey_get_iter_typed(trans, iter, BTREE_ID_dirents, pos, 0, dirent); } static int remove_backpointer(struct btree_trans *trans, struct bch_inode_unpacked *inode) { if (!bch2_inode_has_backpointer(inode)) return 0; u32 snapshot = inode->bi_snapshot; if (inode->bi_parent_subvol) { int ret = bch2_subvolume_get_snapshot(trans, inode->bi_parent_subvol, &snapshot); if (ret) return ret; } struct bch_fs *c = trans->c; struct btree_iter iter; struct bkey_s_c_dirent d = dirent_get_by_pos(trans, &iter, SPOS(inode->bi_dir, inode->bi_dir_offset, snapshot)); int ret = bkey_err(d) ?: dirent_points_to_inode(c, d, inode) ?: bch2_fsck_remove_dirent(trans, d.k->p); bch2_trans_iter_exit(trans, &iter); return ret; } static int reattach_subvol(struct btree_trans *trans, struct bkey_s_c_subvolume s) { struct bch_fs *c = trans->c; struct bch_inode_unpacked inode; int ret = bch2_inode_find_by_inum_trans(trans, (subvol_inum) { s.k->p.offset, le64_to_cpu(s.v->inode) }, &inode); if (ret) return ret; ret = remove_backpointer(trans, &inode); if (!bch2_err_matches(ret, ENOENT)) bch_err_msg(c, ret, "removing dirent"); if (ret) return ret; ret = reattach_inode(trans, &inode); bch_err_msg(c, ret, "reattaching inode %llu", inode.bi_inum); return ret; } static int reconstruct_subvol(struct btree_trans *trans, u32 snapshotid, u32 subvolid, u64 inum) { struct bch_fs *c = trans->c; if (!bch2_snapshot_is_leaf(c, snapshotid)) { bch_err(c, "need to reconstruct subvol, but have interior node snapshot"); return bch_err_throw(c, fsck_repair_unimplemented); } /* * If inum isn't set, that means we're being called from check_dirents, * not check_inodes - the root of this subvolume doesn't exist or we * would have found it there: */ if (!inum) { struct btree_iter inode_iter = {}; struct bch_inode_unpacked new_inode; u64 cpu = raw_smp_processor_id(); bch2_inode_init_early(c, &new_inode); bch2_inode_init_late(c, &new_inode, bch2_current_time(c), 0, 0, S_IFDIR|0755, 0, NULL); new_inode.bi_subvol = subvolid; int ret = bch2_inode_create(trans, &inode_iter, &new_inode, snapshotid, cpu) ?: bch2_btree_iter_traverse(trans, &inode_iter) ?: bch2_inode_write(trans, &inode_iter, &new_inode); bch2_trans_iter_exit(trans, &inode_iter); if (ret) return ret; inum = new_inode.bi_inum; } bch_info(c, "reconstructing subvol %u with root inode %llu", subvolid, inum); struct bkey_i_subvolume *new_subvol = bch2_trans_kmalloc(trans, sizeof(*new_subvol)); int ret = PTR_ERR_OR_ZERO(new_subvol); if (ret) return ret; bkey_subvolume_init(&new_subvol->k_i); new_subvol->k.p.offset = subvolid; new_subvol->v.snapshot = cpu_to_le32(snapshotid); new_subvol->v.inode = cpu_to_le64(inum); ret = bch2_btree_insert_trans(trans, BTREE_ID_subvolumes, &new_subvol->k_i, 0); if (ret) return ret; struct btree_iter iter; struct bkey_i_snapshot *s = bch2_bkey_get_mut_typed(trans, &iter, BTREE_ID_snapshots, POS(0, snapshotid), 0, snapshot); ret = PTR_ERR_OR_ZERO(s); bch_err_msg(c, ret, "getting snapshot %u", snapshotid); if (ret) return ret; u32 snapshot_tree = le32_to_cpu(s->v.tree); s->v.subvol = cpu_to_le32(subvolid); SET_BCH_SNAPSHOT_SUBVOL(&s->v, true); bch2_trans_iter_exit(trans, &iter); struct bkey_i_snapshot_tree *st = bch2_bkey_get_mut_typed(trans, &iter, BTREE_ID_snapshot_trees, POS(0, snapshot_tree), 0, snapshot_tree); ret = PTR_ERR_OR_ZERO(st); bch_err_msg(c, ret, "getting snapshot tree %u", snapshot_tree); if (ret) return ret; if (!st->v.master_subvol) st->v.master_subvol = cpu_to_le32(subvolid); bch2_trans_iter_exit(trans, &iter); return 0; } static int reconstruct_inode(struct btree_trans *trans, enum btree_id btree, u32 snapshot, u64 inum) { struct bch_fs *c = trans->c; unsigned i_mode = S_IFREG; u64 i_size = 0; switch (btree) { case BTREE_ID_extents: { struct btree_iter iter = {}; bch2_trans_iter_init(trans, &iter, BTREE_ID_extents, SPOS(inum, U64_MAX, snapshot), 0); struct bkey_s_c k = bch2_btree_iter_peek_prev_min(trans, &iter, POS(inum, 0)); bch2_trans_iter_exit(trans, &iter); int ret = bkey_err(k); if (ret) return ret; i_size = k.k->p.offset << 9; break; } case BTREE_ID_dirents: i_mode = S_IFDIR; break; case BTREE_ID_xattrs: break; default: BUG(); } struct bch_inode_unpacked new_inode; bch2_inode_init_early(c, &new_inode); bch2_inode_init_late(c, &new_inode, bch2_current_time(c), 0, 0, i_mode|0600, 0, NULL); new_inode.bi_size = i_size; new_inode.bi_inum = inum; new_inode.bi_snapshot = snapshot; return __bch2_fsck_write_inode(trans, &new_inode); } static inline void snapshots_seen_exit(struct snapshots_seen *s) { darray_exit(&s->ids); } static inline void snapshots_seen_init(struct snapshots_seen *s) { memset(s, 0, sizeof(*s)); } static int snapshots_seen_add_inorder(struct bch_fs *c, struct snapshots_seen *s, u32 id) { u32 *i; __darray_for_each(s->ids, i) { if (*i == id) return 0; if (*i > id) break; } int ret = darray_insert_item(&s->ids, i - s->ids.data, id); if (ret) bch_err(c, "error reallocating snapshots_seen table (size %zu)", s->ids.size); return ret; } static int snapshots_seen_update(struct bch_fs *c, struct snapshots_seen *s, enum btree_id btree_id, struct bpos pos) { if (!bkey_eq(s->pos, pos)) s->ids.nr = 0; s->pos = pos; return snapshot_list_add_nodup(c, &s->ids, pos.snapshot); } /** * key_visible_in_snapshot - returns true if @id is a descendent of @ancestor, * and @ancestor hasn't been overwritten in @seen * * @c: filesystem handle * @seen: list of snapshot ids already seen at current position * @id: descendent snapshot id * @ancestor: ancestor snapshot id * * Returns: whether key in @ancestor snapshot is visible in @id snapshot */ static bool key_visible_in_snapshot(struct bch_fs *c, struct snapshots_seen *seen, u32 id, u32 ancestor) { EBUG_ON(id > ancestor); if (id == ancestor) return true; if (!bch2_snapshot_is_ancestor(c, id, ancestor)) return false; /* * We know that @id is a descendant of @ancestor, we're checking if * we've seen a key that overwrote @ancestor - i.e. also a descendent of * @ascestor and with @id as a descendent. * * But we already know that we're scanning IDs between @id and @ancestor * numerically, since snapshot ID lists are kept sorted, so if we find * an id that's an ancestor of @id we're done: */ darray_for_each_reverse(seen->ids, i) if (*i != ancestor && bch2_snapshot_is_ancestor(c, id, *i)) return false; return true; } /** * ref_visible - given a key with snapshot id @src that points to a key with * snapshot id @dst, test whether there is some snapshot in which @dst is * visible. * * @c: filesystem handle * @s: list of snapshot IDs already seen at @src * @src: snapshot ID of src key * @dst: snapshot ID of dst key * Returns: true if there is some snapshot in which @dst is visible * * Assumes we're visiting @src keys in natural key order */ static bool ref_visible(struct bch_fs *c, struct snapshots_seen *s, u32 src, u32 dst) { return dst <= src ? key_visible_in_snapshot(c, s, dst, src) : bch2_snapshot_is_ancestor(c, src, dst); } static int ref_visible2(struct bch_fs *c, u32 src, struct snapshots_seen *src_seen, u32 dst, struct snapshots_seen *dst_seen) { if (dst > src) { swap(dst, src); swap(dst_seen, src_seen); } return key_visible_in_snapshot(c, src_seen, dst, src); } #define for_each_visible_inode(_c, _s, _w, _snapshot, _i) \ for (_i = (_w)->inodes.data; _i < (_w)->inodes.data + (_w)->inodes.nr && \ (_i)->inode.bi_snapshot <= (_snapshot); _i++) \ if (key_visible_in_snapshot(_c, _s, _i->inode.bi_snapshot, _snapshot)) struct inode_walker_entry { struct bch_inode_unpacked inode; bool whiteout; u64 count; u64 i_size; }; struct inode_walker { bool first_this_inode; bool have_inodes; bool recalculate_sums; struct bpos last_pos; DARRAY(struct inode_walker_entry) inodes; snapshot_id_list deletes; }; static void inode_walker_exit(struct inode_walker *w) { darray_exit(&w->inodes); darray_exit(&w->deletes); } static struct inode_walker inode_walker_init(void) { return (struct inode_walker) { 0, }; } static int add_inode(struct bch_fs *c, struct inode_walker *w, struct bkey_s_c inode) { int ret = darray_push(&w->inodes, ((struct inode_walker_entry) { .whiteout = !bkey_is_inode(inode.k), })); if (ret) return ret; struct inode_walker_entry *n = &darray_last(w->inodes); if (!n->whiteout) { return bch2_inode_unpack(inode, &n->inode); } else { n->inode.bi_inum = inode.k->p.offset; n->inode.bi_snapshot = inode.k->p.snapshot; return 0; } } static int get_inodes_all_snapshots(struct btree_trans *trans, struct inode_walker *w, u64 inum) { struct bch_fs *c = trans->c; struct btree_iter iter; struct bkey_s_c k; int ret; /* * We no longer have inodes for w->last_pos; clear this to avoid * screwing up check_i_sectors/check_subdir_count if we take a * transaction restart here: */ w->have_inodes = false; w->recalculate_sums = false; w->inodes.nr = 0; for_each_btree_key_max_norestart(trans, iter, BTREE_ID_inodes, POS(0, inum), SPOS(0, inum, U32_MAX), BTREE_ITER_all_snapshots, k, ret) { ret = add_inode(c, w, k); if (ret) break; } bch2_trans_iter_exit(trans, &iter); if (ret) return ret; w->first_this_inode = true; w->have_inodes = true; return 0; } static int get_visible_inodes(struct btree_trans *trans, struct inode_walker *w, struct snapshots_seen *s, u64 inum) { struct bch_fs *c = trans->c; struct btree_iter iter; struct bkey_s_c k; int ret; w->inodes.nr = 0; w->deletes.nr = 0; for_each_btree_key_reverse_norestart(trans, iter, BTREE_ID_inodes, SPOS(0, inum, s->pos.snapshot), BTREE_ITER_all_snapshots, k, ret) { if (k.k->p.offset != inum) break; if (!ref_visible(c, s, s->pos.snapshot, k.k->p.snapshot)) continue; if (snapshot_list_has_ancestor(c, &w->deletes, k.k->p.snapshot)) continue; ret = bkey_is_inode(k.k) ? add_inode(c, w, k) : snapshot_list_add(c, &w->deletes, k.k->p.snapshot); if (ret) break; } bch2_trans_iter_exit(trans, &iter); return ret; } static struct inode_walker_entry * lookup_inode_for_snapshot(struct btree_trans *trans, struct inode_walker *w, struct bkey_s_c k) { struct bch_fs *c = trans->c; struct inode_walker_entry *i = darray_find_p(w->inodes, i, bch2_snapshot_is_ancestor(c, k.k->p.snapshot, i->inode.bi_snapshot)); if (!i) return NULL; struct printbuf buf = PRINTBUF; int ret = 0; if (fsck_err_on(k.k->p.snapshot != i->inode.bi_snapshot, trans, snapshot_key_missing_inode_snapshot, "have key for inode %llu:%u but have inode in ancestor snapshot %u\n" "unexpected because we should always update the inode when we update a key in that inode\n" "%s", w->last_pos.inode, k.k->p.snapshot, i->inode.bi_snapshot, (bch2_bkey_val_to_text(&buf, c, k), buf.buf))) { if (!i->whiteout) { struct bch_inode_unpacked new = i->inode; new.bi_snapshot = k.k->p.snapshot; ret = __bch2_fsck_write_inode(trans, &new); } else { struct bkey_i whiteout; bkey_init(&whiteout.k); whiteout.k.type = KEY_TYPE_whiteout; whiteout.k.p = SPOS(0, i->inode.bi_inum, k.k->p.snapshot); ret = bch2_btree_insert_nonextent(trans, BTREE_ID_inodes, &whiteout, BTREE_UPDATE_internal_snapshot_node); } if (ret) goto fsck_err; ret = bch2_trans_commit(trans, NULL, NULL, 0); if (ret) goto fsck_err; struct inode_walker_entry new_entry = *i; new_entry.inode.bi_snapshot = k.k->p.snapshot; new_entry.count = 0; new_entry.i_size = 0; while (i > w->inodes.data && i[-1].inode.bi_snapshot > k.k->p.snapshot) --i; size_t pos = i - w->inodes.data; ret = darray_insert_item(&w->inodes, pos, new_entry); if (ret) goto fsck_err; ret = bch_err_throw(c, transaction_restart_nested); goto fsck_err; } printbuf_exit(&buf); return i; fsck_err: printbuf_exit(&buf); return ERR_PTR(ret); } static struct inode_walker_entry *walk_inode(struct btree_trans *trans, struct inode_walker *w, struct bkey_s_c k) { if (w->last_pos.inode != k.k->p.inode) { int ret = get_inodes_all_snapshots(trans, w, k.k->p.inode); if (ret) return ERR_PTR(ret); } w->last_pos = k.k->p; return lookup_inode_for_snapshot(trans, w, k); } /* * Prefer to delete the first one, since that will be the one at the wrong * offset: * return value: 0 -> delete k1, 1 -> delete k2 */ int bch2_fsck_update_backpointers(struct btree_trans *trans, struct snapshots_seen *s, const struct bch_hash_desc desc, struct bch_hash_info *hash_info, struct bkey_i *new) { if (new->k.type != KEY_TYPE_dirent) return 0; struct bkey_i_dirent *d = bkey_i_to_dirent(new); struct inode_walker target = inode_walker_init(); int ret = 0; if (d->v.d_type == DT_SUBVOL) { bch_err(trans->c, "%s does not support DT_SUBVOL", __func__); ret = -BCH_ERR_fsck_repair_unimplemented; } else { ret = get_visible_inodes(trans, &target, s, le64_to_cpu(d->v.d_inum)); if (ret) goto err; darray_for_each(target.inodes, i) { i->inode.bi_dir_offset = d->k.p.offset; ret = __bch2_fsck_write_inode(trans, &i->inode); if (ret) goto err; } } err: inode_walker_exit(&target); return ret; } static struct bkey_s_c_dirent inode_get_dirent(struct btree_trans *trans, struct btree_iter *iter, struct bch_inode_unpacked *inode, u32 *snapshot) { if (inode->bi_subvol) { u64 inum; int ret = subvol_lookup(trans, inode->bi_parent_subvol, snapshot, &inum); if (ret) return ((struct bkey_s_c_dirent) { .k = ERR_PTR(ret) }); } return dirent_get_by_pos(trans, iter, SPOS(inode->bi_dir, inode->bi_dir_offset, *snapshot)); } static int check_inode_deleted_list(struct btree_trans *trans, struct bpos p) { struct btree_iter iter; struct bkey_s_c k = bch2_bkey_get_iter(trans, &iter, BTREE_ID_deleted_inodes, p, 0); int ret = bkey_err(k) ?: k.k->type == KEY_TYPE_set; bch2_trans_iter_exit(trans, &iter); return ret; } static int check_inode_dirent_inode(struct btree_trans *trans, struct bch_inode_unpacked *inode, bool *write_inode) { struct bch_fs *c = trans->c; struct printbuf buf = PRINTBUF; u32 inode_snapshot = inode->bi_snapshot; struct btree_iter dirent_iter = {}; struct bkey_s_c_dirent d = inode_get_dirent(trans, &dirent_iter, inode, &inode_snapshot); int ret = bkey_err(d); if (ret && !bch2_err_matches(ret, ENOENT)) return ret; if ((ret || dirent_points_to_inode_nowarn(c, d, inode)) && inode->bi_subvol && (inode->bi_flags & BCH_INODE_has_child_snapshot)) { /* Older version of a renamed subvolume root: we won't have a * correct dirent for it. That's expected, see * inode_should_reattach(). * * We don't clear the backpointer field when doing the rename * because there might be arbitrarily many versions in older * snapshots. */ inode->bi_dir = 0; inode->bi_dir_offset = 0; *write_inode = true; goto out; } if (fsck_err_on(ret, trans, inode_points_to_missing_dirent, "inode points to missing dirent\n%s", (bch2_inode_unpacked_to_text(&buf, inode), buf.buf)) || fsck_err_on(!ret && dirent_points_to_inode_nowarn(c, d, inode), trans, inode_points_to_wrong_dirent, "%s", (printbuf_reset(&buf), dirent_inode_mismatch_msg(&buf, c, d, inode), buf.buf))) { /* * We just clear the backpointer fields for now. If we find a * dirent that points to this inode in check_dirents(), we'll * update it then; then when we get to check_path() if the * backpointer is still 0 we'll reattach it. */ inode->bi_dir = 0; inode->bi_dir_offset = 0; *write_inode = true; } out: ret = 0; fsck_err: bch2_trans_iter_exit(trans, &dirent_iter); printbuf_exit(&buf); bch_err_fn(c, ret); return ret; } static int check_inode(struct btree_trans *trans, struct btree_iter *iter, struct bkey_s_c k, struct bch_inode_unpacked *snapshot_root, struct snapshots_seen *s) { struct bch_fs *c = trans->c; struct printbuf buf = PRINTBUF; struct bch_inode_unpacked u; bool do_update = false; int ret; ret = bch2_check_key_has_snapshot(trans, iter, k); if (ret < 0) goto err; if (ret) return 0; ret = snapshots_seen_update(c, s, iter->btree_id, k.k->p); if (ret) goto err; if (!bkey_is_inode(k.k)) return 0; ret = bch2_inode_unpack(k, &u); if (ret) goto err; if (snapshot_root->bi_inum != u.bi_inum) { ret = bch2_inode_find_snapshot_root(trans, u.bi_inum, snapshot_root); if (ret) goto err; } if (u.bi_hash_seed != snapshot_root->bi_hash_seed || INODE_STR_HASH(&u) != INODE_STR_HASH(snapshot_root)) { ret = bch2_repair_inode_hash_info(trans, snapshot_root); BUG_ON(ret == -BCH_ERR_fsck_repair_unimplemented); if (ret) goto err; } ret = bch2_check_inode_has_case_insensitive(trans, &u, &s->ids, &do_update); if (ret) goto err; if (bch2_inode_has_backpointer(&u)) { ret = check_inode_dirent_inode(trans, &u, &do_update); if (ret) goto err; } if (fsck_err_on(bch2_inode_has_backpointer(&u) && (u.bi_flags & BCH_INODE_unlinked), trans, inode_unlinked_but_has_dirent, "inode unlinked but has dirent\n%s", (printbuf_reset(&buf), bch2_inode_unpacked_to_text(&buf, &u), buf.buf))) { u.bi_flags &= ~BCH_INODE_unlinked; do_update = true; } if (S_ISDIR(u.bi_mode) && (u.bi_flags & BCH_INODE_unlinked)) { /* Check for this early so that check_unreachable_inode() will reattach it */ ret = bch2_empty_dir_snapshot(trans, k.k->p.offset, 0, k.k->p.snapshot); if (ret && ret != -BCH_ERR_ENOTEMPTY_dir_not_empty) goto err; fsck_err_on(ret, trans, inode_dir_unlinked_but_not_empty, "dir unlinked but not empty\n%s", (printbuf_reset(&buf), bch2_inode_unpacked_to_text(&buf, &u), buf.buf)); u.bi_flags &= ~BCH_INODE_unlinked; do_update = true; ret = 0; } if (fsck_err_on(S_ISDIR(u.bi_mode) && u.bi_size, trans, inode_dir_has_nonzero_i_size, "directory %llu:%u with nonzero i_size %lli", u.bi_inum, u.bi_snapshot, u.bi_size)) { u.bi_size = 0; do_update = true; } ret = bch2_inode_has_child_snapshots(trans, k.k->p); if (ret < 0) goto err; if (fsck_err_on(ret != !!(u.bi_flags & BCH_INODE_has_child_snapshot), trans, inode_has_child_snapshots_wrong, "inode has_child_snapshots flag wrong (should be %u)\n%s", ret, (printbuf_reset(&buf), bch2_inode_unpacked_to_text(&buf, &u), buf.buf))) { if (ret) u.bi_flags |= BCH_INODE_has_child_snapshot; else u.bi_flags &= ~BCH_INODE_has_child_snapshot; do_update = true; } ret = 0; if ((u.bi_flags & BCH_INODE_unlinked) && !(u.bi_flags & BCH_INODE_has_child_snapshot)) { if (!test_bit(BCH_FS_started, &c->flags)) { /* * If we're not in online fsck, don't delete unlinked * inodes, just make sure they're on the deleted list. * * They might be referred to by a logged operation - * i.e. we might have crashed in the middle of a * truncate on an unlinked but open file - so we want to * let the delete_dead_inodes kill it after resuming * logged ops. */ ret = check_inode_deleted_list(trans, k.k->p); if (ret < 0) goto err_noprint; fsck_err_on(!ret, trans, unlinked_inode_not_on_deleted_list, "inode %llu:%u unlinked, but not on deleted list", u.bi_inum, k.k->p.snapshot); ret = bch2_btree_bit_mod_buffered(trans, BTREE_ID_deleted_inodes, k.k->p, 1); if (ret) goto err; } else { ret = bch2_inode_or_descendents_is_open(trans, k.k->p); if (ret < 0) goto err; if (fsck_err_on(!ret, trans, inode_unlinked_and_not_open, "inode %llu:%u unlinked and not open", u.bi_inum, u.bi_snapshot)) { ret = bch2_inode_rm_snapshot(trans, u.bi_inum, iter->pos.snapshot); bch_err_msg(c, ret, "in fsck deleting inode"); goto err_noprint; } ret = 0; } } if (fsck_err_on(u.bi_parent_subvol && (u.bi_subvol == 0 || u.bi_subvol == BCACHEFS_ROOT_SUBVOL), trans, inode_bi_parent_nonzero, "inode %llu:%u has subvol %u but nonzero parent subvol %u", u.bi_inum, k.k->p.snapshot, u.bi_subvol, u.bi_parent_subvol)) { u.bi_parent_subvol = 0; do_update = true; } if (u.bi_subvol) { struct bch_subvolume s; ret = bch2_subvolume_get(trans, u.bi_subvol, false, &s); if (ret && !bch2_err_matches(ret, ENOENT)) goto err; if (ret && (c->sb.btrees_lost_data & BIT_ULL(BTREE_ID_subvolumes))) { ret = reconstruct_subvol(trans, k.k->p.snapshot, u.bi_subvol, u.bi_inum); goto do_update; } if (fsck_err_on(ret, trans, inode_bi_subvol_missing, "inode %llu:%u bi_subvol points to missing subvolume %u", u.bi_inum, k.k->p.snapshot, u.bi_subvol) || fsck_err_on(le64_to_cpu(s.inode) != u.bi_inum || !bch2_snapshot_is_ancestor(c, le32_to_cpu(s.snapshot), k.k->p.snapshot), trans, inode_bi_subvol_wrong, "inode %llu:%u points to subvol %u, but subvol points to %llu:%u", u.bi_inum, k.k->p.snapshot, u.bi_subvol, le64_to_cpu(s.inode), le32_to_cpu(s.snapshot))) { u.bi_subvol = 0; u.bi_parent_subvol = 0; do_update = true; } } if (fsck_err_on(u.bi_journal_seq > journal_cur_seq(&c->journal), trans, inode_journal_seq_in_future, "inode journal seq in future (currently at %llu)\n%s", journal_cur_seq(&c->journal), (printbuf_reset(&buf), bch2_inode_unpacked_to_text(&buf, &u), buf.buf))) { u.bi_journal_seq = journal_cur_seq(&c->journal); do_update = true; } do_update: if (do_update) { ret = __bch2_fsck_write_inode(trans, &u); bch_err_msg(c, ret, "in fsck updating inode"); if (ret) goto err_noprint; } err: fsck_err: bch_err_fn(c, ret); err_noprint: printbuf_exit(&buf); return ret; } int bch2_check_inodes(struct bch_fs *c) { struct bch_inode_unpacked snapshot_root = {}; struct snapshots_seen s; snapshots_seen_init(&s); int ret = bch2_trans_run(c, for_each_btree_key_commit(trans, iter, BTREE_ID_inodes, POS_MIN, BTREE_ITER_prefetch|BTREE_ITER_all_snapshots, k, NULL, NULL, BCH_TRANS_COMMIT_no_enospc, check_inode(trans, &iter, k, &snapshot_root, &s))); snapshots_seen_exit(&s); bch_err_fn(c, ret); return ret; } static int find_oldest_inode_needs_reattach(struct btree_trans *trans, struct bch_inode_unpacked *inode) { struct bch_fs *c = trans->c; struct btree_iter iter; struct bkey_s_c k; int ret = 0; /* * We look for inodes to reattach in natural key order, leaves first, * but we should do the reattach at the oldest version that needs to be * reattached: */ for_each_btree_key_norestart(trans, iter, BTREE_ID_inodes, SPOS(0, inode->bi_inum, inode->bi_snapshot + 1), BTREE_ITER_all_snapshots, k, ret) { if (k.k->p.offset != inode->bi_inum) break; if (!bch2_snapshot_is_ancestor(c, inode->bi_snapshot, k.k->p.snapshot)) continue; if (!bkey_is_inode(k.k)) break; struct bch_inode_unpacked parent_inode; ret = bch2_inode_unpack(k, &parent_inode); if (ret) break; if (!inode_should_reattach(&parent_inode)) break; *inode = parent_inode; } bch2_trans_iter_exit(trans, &iter); return ret; } static int check_unreachable_inode(struct btree_trans *trans, struct btree_iter *iter, struct bkey_s_c k) { struct printbuf buf = PRINTBUF; int ret = 0; if (!bkey_is_inode(k.k)) return 0; struct bch_inode_unpacked inode; ret = bch2_inode_unpack(k, &inode); if (ret) return ret; if (!inode_should_reattach(&inode)) return 0; ret = find_oldest_inode_needs_reattach(trans, &inode); if (ret) return ret; if (fsck_err(trans, inode_unreachable, "unreachable inode:\n%s", (bch2_inode_unpacked_to_text(&buf, &inode), buf.buf))) ret = reattach_inode(trans, &inode); fsck_err: printbuf_exit(&buf); return ret; } /* * Reattach unreachable (but not unlinked) inodes * * Run after check_inodes() and check_dirents(), so we node that inode * backpointer fields point to valid dirents, and every inode that has a dirent * that points to it has its backpointer field set - so we're just looking for * non-unlinked inodes without backpointers: * * XXX: this is racy w.r.t. hardlink removal in online fsck */ int bch2_check_unreachable_inodes(struct bch_fs *c) { int ret = bch2_trans_run(c, for_each_btree_key_commit(trans, iter, BTREE_ID_inodes, POS_MIN, BTREE_ITER_prefetch|BTREE_ITER_all_snapshots, k, NULL, NULL, BCH_TRANS_COMMIT_no_enospc, check_unreachable_inode(trans, &iter, k))); bch_err_fn(c, ret); return ret; } static inline bool btree_matches_i_mode(enum btree_id btree, unsigned mode) { switch (btree) { case BTREE_ID_extents: return S_ISREG(mode) || S_ISLNK(mode); case BTREE_ID_dirents: return S_ISDIR(mode); case BTREE_ID_xattrs: return true; default: BUG(); } } static int check_key_has_inode(struct btree_trans *trans, struct btree_iter *iter, struct inode_walker *inode, struct inode_walker_entry *i, struct bkey_s_c k) { struct bch_fs *c = trans->c; struct printbuf buf = PRINTBUF; struct btree_iter iter2 = {}; int ret = PTR_ERR_OR_ZERO(i); if (ret) return ret; if (k.k->type == KEY_TYPE_whiteout) goto out; bool have_inode = i && !i->whiteout; if (!have_inode && (c->sb.btrees_lost_data & BIT_ULL(BTREE_ID_inodes))) goto reconstruct; if (have_inode && btree_matches_i_mode(iter->btree_id, i->inode.bi_mode)) goto out; prt_printf(&buf, ", "); bool have_old_inode = false; darray_for_each(inode->inodes, i2) if (!i2->whiteout && bch2_snapshot_is_ancestor(c, k.k->p.snapshot, i2->inode.bi_snapshot) && btree_matches_i_mode(iter->btree_id, i2->inode.bi_mode)) { prt_printf(&buf, "but found good inode in older snapshot\n"); bch2_inode_unpacked_to_text(&buf, &i2->inode); prt_newline(&buf); have_old_inode = true; break; } struct bkey_s_c k2; unsigned nr_keys = 0; prt_printf(&buf, "found keys:\n"); for_each_btree_key_max_norestart(trans, iter2, iter->btree_id, SPOS(k.k->p.inode, 0, k.k->p.snapshot), POS(k.k->p.inode, U64_MAX), 0, k2, ret) { nr_keys++; if (nr_keys <= 10) { bch2_bkey_val_to_text(&buf, c, k2); prt_newline(&buf); } if (nr_keys >= 100) break; } if (ret) goto err; if (nr_keys > 100) prt_printf(&buf, "found > %u keys for this missing inode\n", nr_keys); else if (nr_keys > 10) prt_printf(&buf, "found %u keys for this missing inode\n", nr_keys); if (!have_inode) { if (fsck_err_on(!have_inode, trans, key_in_missing_inode, "key in missing inode%s", buf.buf)) { /* * Maybe a deletion that raced with data move, or something * weird like that? But if we know the inode was deleted, or * it's just a few keys, we can safely delete them. * * If it's many keys, we should probably recreate the inode */ if (have_old_inode || nr_keys <= 2) goto delete; else goto reconstruct; } } else { /* * not autofix, this one would be a giant wtf - bit error in the * inode corrupting i_mode? * * may want to try repairing inode instead of deleting */ if (fsck_err_on(!btree_matches_i_mode(iter->btree_id, i->inode.bi_mode), trans, key_in_wrong_inode_type, "key for wrong inode mode %o%s", i->inode.bi_mode, buf.buf)) goto delete; } out: err: fsck_err: bch2_trans_iter_exit(trans, &iter2); printbuf_exit(&buf); bch_err_fn(c, ret); return ret; delete: /* * XXX: print out more info * count up extents for this inode, check if we have different inode in * an older snapshot version, perhaps decide if we want to reconstitute */ ret = bch2_btree_delete_at(trans, iter, BTREE_UPDATE_internal_snapshot_node); goto out; reconstruct: ret = reconstruct_inode(trans, iter->btree_id, k.k->p.snapshot, k.k->p.inode) ?: bch2_trans_commit(trans, NULL, NULL, BCH_TRANS_COMMIT_no_enospc); if (ret) goto err; inode->last_pos.inode--; ret = bch_err_throw(c, transaction_restart_nested); goto out; } static int check_i_sectors_notnested(struct btree_trans *trans, struct inode_walker *w) { struct bch_fs *c = trans->c; int ret = 0; s64 count2; darray_for_each(w->inodes, i) { if (i->inode.bi_sectors == i->count) continue; count2 = bch2_count_inode_sectors(trans, w->last_pos.inode, i->inode.bi_snapshot); if (w->recalculate_sums) i->count = count2; if (i->count != count2) { bch_err_ratelimited(c, "fsck counted i_sectors wrong for inode %llu:%u: got %llu should be %llu", w->last_pos.inode, i->inode.bi_snapshot, i->count, count2); i->count = count2; } if (fsck_err_on(!(i->inode.bi_flags & BCH_INODE_i_sectors_dirty), trans, inode_i_sectors_wrong, "inode %llu:%u has incorrect i_sectors: got %llu, should be %llu", w->last_pos.inode, i->inode.bi_snapshot, i->inode.bi_sectors, i->count)) { i->inode.bi_sectors = i->count; ret = bch2_fsck_write_inode(trans, &i->inode); if (ret) break; } } fsck_err: bch_err_fn(c, ret); return ret; } static int check_i_sectors(struct btree_trans *trans, struct inode_walker *w) { u32 restart_count = trans->restart_count; return check_i_sectors_notnested(trans, w) ?: trans_was_restarted(trans, restart_count); } struct extent_end { u32 snapshot; u64 offset; struct snapshots_seen seen; }; struct extent_ends { struct bpos last_pos; DARRAY(struct extent_end) e; }; static void extent_ends_reset(struct extent_ends *extent_ends) { darray_for_each(extent_ends->e, i) snapshots_seen_exit(&i->seen); extent_ends->e.nr = 0; } static void extent_ends_exit(struct extent_ends *extent_ends) { extent_ends_reset(extent_ends); darray_exit(&extent_ends->e); } static void extent_ends_init(struct extent_ends *extent_ends) { memset(extent_ends, 0, sizeof(*extent_ends)); } static int extent_ends_at(struct bch_fs *c, struct extent_ends *extent_ends, struct snapshots_seen *seen, struct bkey_s_c k) { struct extent_end *i, n = (struct extent_end) { .offset = k.k->p.offset, .snapshot = k.k->p.snapshot, .seen = *seen, }; n.seen.ids.data = kmemdup(seen->ids.data, sizeof(seen->ids.data[0]) * seen->ids.size, GFP_KERNEL); if (!n.seen.ids.data) return bch_err_throw(c, ENOMEM_fsck_extent_ends_at); __darray_for_each(extent_ends->e, i) { if (i->snapshot == k.k->p.snapshot) { snapshots_seen_exit(&i->seen); *i = n; return 0; } if (i->snapshot >= k.k->p.snapshot) break; } return darray_insert_item(&extent_ends->e, i - extent_ends->e.data, n); } static int overlapping_extents_found(struct btree_trans *trans, enum btree_id btree, struct bpos pos1, struct snapshots_seen *pos1_seen, struct bkey pos2, bool *fixed, struct extent_end *extent_end) { struct bch_fs *c = trans->c; struct printbuf buf = PRINTBUF; struct btree_iter iter1, iter2 = {}; struct bkey_s_c k1, k2; int ret; BUG_ON(bkey_le(pos1, bkey_start_pos(&pos2))); bch2_trans_iter_init(trans, &iter1, btree, pos1, BTREE_ITER_all_snapshots| BTREE_ITER_not_extents); k1 = bch2_btree_iter_peek_max(trans, &iter1, POS(pos1.inode, U64_MAX)); ret = bkey_err(k1); if (ret) goto err; prt_newline(&buf); bch2_bkey_val_to_text(&buf, c, k1); if (!bpos_eq(pos1, k1.k->p)) { prt_str(&buf, "\nwanted\n "); bch2_bpos_to_text(&buf, pos1); prt_str(&buf, "\n"); bch2_bkey_to_text(&buf, &pos2); bch_err(c, "%s: error finding first overlapping extent when repairing, got%s", __func__, buf.buf); ret = bch_err_throw(c, internal_fsck_err); goto err; } bch2_trans_copy_iter(trans, &iter2, &iter1); while (1) { bch2_btree_iter_advance(trans, &iter2); k2 = bch2_btree_iter_peek_max(trans, &iter2, POS(pos1.inode, U64_MAX)); ret = bkey_err(k2); if (ret) goto err; if (bpos_ge(k2.k->p, pos2.p)) break; } prt_newline(&buf); bch2_bkey_val_to_text(&buf, c, k2); if (bpos_gt(k2.k->p, pos2.p) || pos2.size != k2.k->size) { bch_err(c, "%s: error finding seconding overlapping extent when repairing%s", __func__, buf.buf); ret = bch_err_throw(c, internal_fsck_err); goto err; } prt_printf(&buf, "\noverwriting %s extent", pos1.snapshot >= pos2.p.snapshot ? "first" : "second"); if (fsck_err(trans, extent_overlapping, "overlapping extents%s", buf.buf)) { struct btree_iter *old_iter = &iter1; struct disk_reservation res = { 0 }; if (pos1.snapshot < pos2.p.snapshot) { old_iter = &iter2; swap(k1, k2); } trans->extra_disk_res += bch2_bkey_sectors_compressed(k2); ret = bch2_trans_update_extent_overwrite(trans, old_iter, BTREE_UPDATE_internal_snapshot_node, k1, k2) ?: bch2_trans_commit(trans, &res, NULL, BCH_TRANS_COMMIT_no_enospc); bch2_disk_reservation_put(c, &res); bch_info(c, "repair ret %s", bch2_err_str(ret)); if (ret) goto err; *fixed = true; if (pos1.snapshot == pos2.p.snapshot) { /* * We overwrote the first extent, and did the overwrite * in the same snapshot: */ extent_end->offset = bkey_start_offset(&pos2); } else if (pos1.snapshot > pos2.p.snapshot) { /* * We overwrote the first extent in pos2's snapshot: */ ret = snapshots_seen_add_inorder(c, pos1_seen, pos2.p.snapshot); } else { /* * We overwrote the second extent - restart * check_extent() from the top: */ ret = bch_err_throw(c, transaction_restart_nested); } } fsck_err: err: bch2_trans_iter_exit(trans, &iter2); bch2_trans_iter_exit(trans, &iter1); printbuf_exit(&buf); return ret; } static int check_overlapping_extents(struct btree_trans *trans, struct snapshots_seen *seen, struct extent_ends *extent_ends, struct bkey_s_c k, struct btree_iter *iter, bool *fixed) { struct bch_fs *c = trans->c; int ret = 0; /* transaction restart, running again */ if (bpos_eq(extent_ends->last_pos, k.k->p)) return 0; if (extent_ends->last_pos.inode != k.k->p.inode) extent_ends_reset(extent_ends); darray_for_each(extent_ends->e, i) { if (i->offset <= bkey_start_offset(k.k)) continue; if (!ref_visible2(c, k.k->p.snapshot, seen, i->snapshot, &i->seen)) continue; ret = overlapping_extents_found(trans, iter->btree_id, SPOS(iter->pos.inode, i->offset, i->snapshot), &i->seen, *k.k, fixed, i); if (ret) goto err; } extent_ends->last_pos = k.k->p; err: return ret; } static int check_extent_overbig(struct btree_trans *trans, struct btree_iter *iter, struct bkey_s_c k) { struct bch_fs *c = trans->c; struct bkey_ptrs_c ptrs = bch2_bkey_ptrs_c(k); struct bch_extent_crc_unpacked crc; const union bch_extent_entry *i; unsigned encoded_extent_max_sectors = c->opts.encoded_extent_max >> 9; bkey_for_each_crc(k.k, ptrs, crc, i) if (crc_is_encoded(crc) && crc.uncompressed_size > encoded_extent_max_sectors) { struct printbuf buf = PRINTBUF; bch2_bkey_val_to_text(&buf, c, k); bch_err(c, "overbig encoded extent, please report this:\n %s", buf.buf); printbuf_exit(&buf); } return 0; } static int check_extent(struct btree_trans *trans, struct btree_iter *iter, struct bkey_s_c k, struct inode_walker *inode, struct snapshots_seen *s, struct extent_ends *extent_ends, struct disk_reservation *res) { struct bch_fs *c = trans->c; struct printbuf buf = PRINTBUF; int ret = 0; ret = bch2_check_key_has_snapshot(trans, iter, k); if (ret) { ret = ret < 0 ? ret : 0; goto out; } if (inode->last_pos.inode != k.k->p.inode && inode->have_inodes) { ret = check_i_sectors(trans, inode); if (ret) goto err; } ret = snapshots_seen_update(c, s, iter->btree_id, k.k->p); if (ret) goto err; struct inode_walker_entry *extent_i = walk_inode(trans, inode, k); ret = PTR_ERR_OR_ZERO(extent_i); if (ret) goto err; ret = check_key_has_inode(trans, iter, inode, extent_i, k); if (ret) goto err; if (k.k->type != KEY_TYPE_whiteout) { ret = check_overlapping_extents(trans, s, extent_ends, k, iter, &inode->recalculate_sums); if (ret) goto err; /* * Check inodes in reverse order, from oldest snapshots to * newest, starting from the inode that matches this extent's * snapshot. If we didn't have one, iterate over all inodes: */ for (struct inode_walker_entry *i = extent_i ?: &darray_last(inode->inodes); inode->inodes.data && i >= inode->inodes.data; --i) { if (i->inode.bi_snapshot > k.k->p.snapshot || !key_visible_in_snapshot(c, s, i->inode.bi_snapshot, k.k->p.snapshot)) continue; u64 last_block = round_up(i->inode.bi_size, block_bytes(c)) >> 9; if (fsck_err_on(k.k->p.offset > last_block && !bkey_extent_is_reservation(k), trans, extent_past_end_of_inode, "extent type past end of inode %llu:%u, i_size %llu\n%s", i->inode.bi_inum, i->inode.bi_snapshot, i->inode.bi_size, (bch2_bkey_val_to_text(&buf, c, k), buf.buf))) { ret = snapshots_seen_add_inorder(c, s, i->inode.bi_snapshot) ?: bch2_fpunch_snapshot(trans, SPOS(i->inode.bi_inum, last_block, i->inode.bi_snapshot), POS(i->inode.bi_inum, U64_MAX)); if (ret) goto err; iter->k.type = KEY_TYPE_whiteout; break; } } } ret = bch2_trans_commit(trans, res, NULL, BCH_TRANS_COMMIT_no_enospc); if (ret) goto err; if (bkey_extent_is_allocation(k.k)) { for (struct inode_walker_entry *i = extent_i ?: &darray_last(inode->inodes); inode->inodes.data && i >= inode->inodes.data; --i) { if (i->whiteout || i->inode.bi_snapshot > k.k->p.snapshot || !key_visible_in_snapshot(c, s, i->inode.bi_snapshot, k.k->p.snapshot)) continue; i->count += k.k->size; } } if (k.k->type != KEY_TYPE_whiteout) { ret = extent_ends_at(c, extent_ends, s, k); if (ret) goto err; } out: err: fsck_err: printbuf_exit(&buf); bch_err_fn(c, ret); return ret; } /* * Walk extents: verify that extents have a corresponding S_ISREG inode, and * that i_size an i_sectors are consistent */ int bch2_check_extents(struct bch_fs *c) { struct inode_walker w = inode_walker_init(); struct snapshots_seen s; struct extent_ends extent_ends; struct disk_reservation res = { 0 }; snapshots_seen_init(&s); extent_ends_init(&extent_ends); int ret = bch2_trans_run(c, for_each_btree_key(trans, iter, BTREE_ID_extents, POS(BCACHEFS_ROOT_INO, 0), BTREE_ITER_prefetch|BTREE_ITER_all_snapshots, k, ({ bch2_disk_reservation_put(c, &res); check_extent(trans, &iter, k, &w, &s, &extent_ends, &res) ?: check_extent_overbig(trans, &iter, k); })) ?: check_i_sectors_notnested(trans, &w)); bch2_disk_reservation_put(c, &res); extent_ends_exit(&extent_ends); inode_walker_exit(&w); snapshots_seen_exit(&s); bch_err_fn(c, ret); return ret; } int bch2_check_indirect_extents(struct bch_fs *c) { struct disk_reservation res = { 0 }; int ret = bch2_trans_run(c, for_each_btree_key_commit(trans, iter, BTREE_ID_reflink, POS_MIN, BTREE_ITER_prefetch, k, &res, NULL, BCH_TRANS_COMMIT_no_enospc, ({ bch2_disk_reservation_put(c, &res); check_extent_overbig(trans, &iter, k); }))); bch2_disk_reservation_put(c, &res); bch_err_fn(c, ret); return ret; } static int check_subdir_count_notnested(struct btree_trans *trans, struct inode_walker *w) { struct bch_fs *c = trans->c; int ret = 0; s64 count2; darray_for_each(w->inodes, i) { if (i->inode.bi_nlink == i->count) continue; count2 = bch2_count_subdirs(trans, w->last_pos.inode, i->inode.bi_snapshot); if (count2 < 0) return count2; if (i->count != count2) { bch_err_ratelimited(c, "fsck counted subdirectories wrong for inum %llu:%u: got %llu should be %llu", w->last_pos.inode, i->inode.bi_snapshot, i->count, count2); i->count = count2; if (i->inode.bi_nlink == i->count) continue; } if (i->inode.bi_nlink != i->count) { CLASS(printbuf, buf)(); lockrestart_do(trans, bch2_inum_snapshot_to_path(trans, w->last_pos.inode, i->inode.bi_snapshot, NULL, &buf)); if (fsck_err_on(i->inode.bi_nlink != i->count, trans, inode_dir_wrong_nlink, "directory with wrong i_nlink: got %u, should be %llu\n%s", i->inode.bi_nlink, i->count, buf.buf)) { i->inode.bi_nlink = i->count; ret = bch2_fsck_write_inode(trans, &i->inode); if (ret) break; } } } fsck_err: bch_err_fn(c, ret); return ret; } static int check_subdir_dirents_count(struct btree_trans *trans, struct inode_walker *w) { u32 restart_count = trans->restart_count; return check_subdir_count_notnested(trans, w) ?: trans_was_restarted(trans, restart_count); } /* find a subvolume that's a descendent of @snapshot: */ static int find_snapshot_subvol(struct btree_trans *trans, u32 snapshot, u32 *subvolid) { struct btree_iter iter; struct bkey_s_c k; int ret; for_each_btree_key_norestart(trans, iter, BTREE_ID_subvolumes, POS_MIN, 0, k, ret) { if (k.k->type != KEY_TYPE_subvolume) continue; struct bkey_s_c_subvolume s = bkey_s_c_to_subvolume(k); if (bch2_snapshot_is_ancestor(trans->c, le32_to_cpu(s.v->snapshot), snapshot)) { bch2_trans_iter_exit(trans, &iter); *subvolid = k.k->p.offset; goto found; } } if (!ret) ret = -ENOENT; found: bch2_trans_iter_exit(trans, &iter); return ret; } noinline_for_stack static int check_dirent_to_subvol(struct btree_trans *trans, struct btree_iter *iter, struct bkey_s_c_dirent d) { struct bch_fs *c = trans->c; struct btree_iter subvol_iter = {}; struct bch_inode_unpacked subvol_root; u32 parent_subvol = le32_to_cpu(d.v->d_parent_subvol); u32 target_subvol = le32_to_cpu(d.v->d_child_subvol); u32 parent_snapshot; u32 new_parent_subvol = 0; u64 parent_inum; struct printbuf buf = PRINTBUF; int ret = 0; ret = subvol_lookup(trans, parent_subvol, &parent_snapshot, &parent_inum); if (ret && !bch2_err_matches(ret, ENOENT)) return ret; if (ret || (!ret && !bch2_snapshot_is_ancestor(c, parent_snapshot, d.k->p.snapshot))) { int ret2 = find_snapshot_subvol(trans, d.k->p.snapshot, &new_parent_subvol); if (ret2 && !bch2_err_matches(ret, ENOENT)) return ret2; } if (ret && !new_parent_subvol && (c->sb.btrees_lost_data & BIT_ULL(BTREE_ID_subvolumes))) { /* * Couldn't find a subvol for dirent's snapshot - but we lost * subvols, so we need to reconstruct: */ ret = reconstruct_subvol(trans, d.k->p.snapshot, parent_subvol, 0); if (ret) return ret; parent_snapshot = d.k->p.snapshot; } if (fsck_err_on(ret, trans, dirent_to_missing_parent_subvol, "dirent parent_subvol points to missing subvolume\n%s", (bch2_bkey_val_to_text(&buf, c, d.s_c), buf.buf)) || fsck_err_on(!ret && !bch2_snapshot_is_ancestor(c, parent_snapshot, d.k->p.snapshot), trans, dirent_not_visible_in_parent_subvol, "dirent not visible in parent_subvol (not an ancestor of subvol snap %u)\n%s", parent_snapshot, (bch2_bkey_val_to_text(&buf, c, d.s_c), buf.buf))) { if (!new_parent_subvol) { bch_err(c, "could not find a subvol for snapshot %u", d.k->p.snapshot); return bch_err_throw(c, fsck_repair_unimplemented); } struct bkey_i_dirent *new_dirent = bch2_bkey_make_mut_typed(trans, iter, &d.s_c, 0, dirent); ret = PTR_ERR_OR_ZERO(new_dirent); if (ret) goto err; new_dirent->v.d_parent_subvol = cpu_to_le32(new_parent_subvol); } struct bkey_s_c_subvolume s = bch2_bkey_get_iter_typed(trans, &subvol_iter, BTREE_ID_subvolumes, POS(0, target_subvol), 0, subvolume); ret = bkey_err(s.s_c); if (ret && !bch2_err_matches(ret, ENOENT)) goto err; if (ret) { if (fsck_err(trans, dirent_to_missing_subvol, "dirent points to missing subvolume\n%s", (bch2_bkey_val_to_text(&buf, c, d.s_c), buf.buf))) return bch2_fsck_remove_dirent(trans, d.k->p); ret = 0; goto out; } if (le32_to_cpu(s.v->fs_path_parent) != parent_subvol) { printbuf_reset(&buf); prt_printf(&buf, "subvol with wrong fs_path_parent, should be be %u\n", parent_subvol); ret = bch2_inum_to_path(trans, (subvol_inum) { s.k->p.offset, le64_to_cpu(s.v->inode) }, &buf); if (ret) goto err; prt_newline(&buf); bch2_bkey_val_to_text(&buf, c, s.s_c); if (fsck_err(trans, subvol_fs_path_parent_wrong, "%s", buf.buf)) { struct bkey_i_subvolume *n = bch2_bkey_make_mut_typed(trans, &subvol_iter, &s.s_c, 0, subvolume); ret = PTR_ERR_OR_ZERO(n); if (ret) goto err; n->v.fs_path_parent = cpu_to_le32(parent_subvol); } } u64 target_inum = le64_to_cpu(s.v->inode); u32 target_snapshot = le32_to_cpu(s.v->snapshot); ret = bch2_inode_find_by_inum_snapshot(trans, target_inum, target_snapshot, &subvol_root, 0); if (ret && !bch2_err_matches(ret, ENOENT)) goto err; if (ret) { bch_err(c, "subvol %u points to missing inode root %llu", target_subvol, target_inum); ret = bch_err_throw(c, fsck_repair_unimplemented); goto err; } if (fsck_err_on(!ret && parent_subvol != subvol_root.bi_parent_subvol, trans, inode_bi_parent_wrong, "subvol root %llu has wrong bi_parent_subvol: got %u, should be %u", target_inum, subvol_root.bi_parent_subvol, parent_subvol)) { subvol_root.bi_parent_subvol = parent_subvol; subvol_root.bi_snapshot = le32_to_cpu(s.v->snapshot); ret = __bch2_fsck_write_inode(trans, &subvol_root); if (ret) goto err; } ret = bch2_check_dirent_target(trans, iter, d, &subvol_root, true); if (ret) goto err; out: err: fsck_err: bch2_trans_iter_exit(trans, &subvol_iter); printbuf_exit(&buf); return ret; } static int check_dirent(struct btree_trans *trans, struct btree_iter *iter, struct bkey_s_c k, struct bch_hash_info *hash_info, struct inode_walker *dir, struct inode_walker *target, struct snapshots_seen *s, bool *need_second_pass) { struct bch_fs *c = trans->c; struct inode_walker_entry *i; struct printbuf buf = PRINTBUF; int ret = 0; ret = bch2_check_key_has_snapshot(trans, iter, k); if (ret) { ret = ret < 0 ? ret : 0; goto out; } ret = snapshots_seen_update(c, s, iter->btree_id, k.k->p); if (ret) goto err; if (k.k->type == KEY_TYPE_whiteout) goto out; if (dir->last_pos.inode != k.k->p.inode && dir->have_inodes) { ret = check_subdir_dirents_count(trans, dir); if (ret) goto err; } i = walk_inode(trans, dir, k); ret = PTR_ERR_OR_ZERO(i); if (ret < 0) goto err; ret = check_key_has_inode(trans, iter, dir, i, k); if (ret) goto err; if (!i || i->whiteout) goto out; if (dir->first_this_inode) *hash_info = bch2_hash_info_init(c, &i->inode); dir->first_this_inode = false; hash_info->cf_encoding = bch2_inode_casefold(c, &i->inode) ? c->cf_encoding : NULL; ret = bch2_str_hash_check_key(trans, s, &bch2_dirent_hash_desc, hash_info, iter, k, need_second_pass); if (ret < 0) goto err; if (ret) { /* dirent has been deleted */ ret = 0; goto out; } if (k.k->type != KEY_TYPE_dirent) goto out; struct bkey_s_c_dirent d = bkey_s_c_to_dirent(k); /* check casefold */ if (fsck_err_on(d.v->d_casefold != !!hash_info->cf_encoding, trans, dirent_casefold_mismatch, "dirent casefold does not match dir casefold\n%s", (printbuf_reset(&buf), bch2_bkey_val_to_text(&buf, c, k), buf.buf))) { subvol_inum dir_inum = { .subvol = d.v->d_type == DT_SUBVOL ? le32_to_cpu(d.v->d_parent_subvol) : 0, }; u64 target = d.v->d_type == DT_SUBVOL ? le32_to_cpu(d.v->d_child_subvol) : le64_to_cpu(d.v->d_inum); struct qstr name = bch2_dirent_get_name(d); struct bkey_i_dirent *new_d = bch2_dirent_create_key(trans, hash_info, dir_inum, d.v->d_type, &name, NULL, target); ret = PTR_ERR_OR_ZERO(new_d); if (ret) goto out; new_d->k.p.inode = d.k->p.inode; new_d->k.p.snapshot = d.k->p.snapshot; struct btree_iter dup_iter = {}; ret = bch2_hash_delete_at(trans, bch2_dirent_hash_desc, hash_info, iter, BTREE_UPDATE_internal_snapshot_node) ?: bch2_str_hash_repair_key(trans, s, &bch2_dirent_hash_desc, hash_info, iter, bkey_i_to_s_c(&new_d->k_i), &dup_iter, bkey_s_c_null, need_second_pass); goto out; } if (d.v->d_type == DT_SUBVOL) { ret = check_dirent_to_subvol(trans, iter, d); if (ret) goto err; } else { ret = get_visible_inodes(trans, target, s, le64_to_cpu(d.v->d_inum)); if (ret) goto err; if (fsck_err_on(!target->inodes.nr, trans, dirent_to_missing_inode, "dirent points to missing inode:\n%s", (printbuf_reset(&buf), bch2_bkey_val_to_text(&buf, c, k), buf.buf))) { ret = bch2_fsck_remove_dirent(trans, d.k->p); if (ret) goto err; } darray_for_each(target->inodes, i) { ret = bch2_check_dirent_target(trans, iter, d, &i->inode, true); if (ret) goto err; } darray_for_each(target->deletes, i) if (fsck_err_on(!snapshot_list_has_id(&s->ids, *i), trans, dirent_to_overwritten_inode, "dirent points to inode overwritten in snapshot %u:\n%s", *i, (printbuf_reset(&buf), bch2_bkey_val_to_text(&buf, c, k), buf.buf))) { struct btree_iter delete_iter; bch2_trans_iter_init(trans, &delete_iter, BTREE_ID_dirents, SPOS(k.k->p.inode, k.k->p.offset, *i), BTREE_ITER_intent); ret = bch2_btree_iter_traverse(trans, &delete_iter) ?: bch2_hash_delete_at(trans, bch2_dirent_hash_desc, hash_info, &delete_iter, BTREE_UPDATE_internal_snapshot_node); bch2_trans_iter_exit(trans, &delete_iter); if (ret) goto err; } } ret = bch2_trans_commit(trans, NULL, NULL, BCH_TRANS_COMMIT_no_enospc); if (ret) goto err; for_each_visible_inode(c, s, dir, d.k->p.snapshot, i) { if (d.v->d_type == DT_DIR) i->count++; i->i_size += bkey_bytes(d.k); } out: err: fsck_err: printbuf_exit(&buf); return ret; } /* * Walk dirents: verify that they all have a corresponding S_ISDIR inode, * validate d_type */ int bch2_check_dirents(struct bch_fs *c) { struct inode_walker dir = inode_walker_init(); struct inode_walker target = inode_walker_init(); struct snapshots_seen s; struct bch_hash_info hash_info; bool need_second_pass = false, did_second_pass = false; int ret; snapshots_seen_init(&s); again: ret = bch2_trans_run(c, for_each_btree_key_commit(trans, iter, BTREE_ID_dirents, POS(BCACHEFS_ROOT_INO, 0), BTREE_ITER_prefetch|BTREE_ITER_all_snapshots, k, NULL, NULL, BCH_TRANS_COMMIT_no_enospc, check_dirent(trans, &iter, k, &hash_info, &dir, &target, &s, &need_second_pass)) ?: check_subdir_count_notnested(trans, &dir)); if (!ret && need_second_pass && !did_second_pass) { bch_info(c, "check_dirents requires second pass"); swap(did_second_pass, need_second_pass); goto again; } if (!ret && need_second_pass) { bch_err(c, "dirents not repairing"); ret = -EINVAL; } snapshots_seen_exit(&s); inode_walker_exit(&dir); inode_walker_exit(&target); bch_err_fn(c, ret); return ret; } static int check_xattr(struct btree_trans *trans, struct btree_iter *iter, struct bkey_s_c k, struct bch_hash_info *hash_info, struct inode_walker *inode) { struct bch_fs *c = trans->c; int ret = bch2_check_key_has_snapshot(trans, iter, k); if (ret < 0) return ret; if (ret) return 0; struct inode_walker_entry *i = walk_inode(trans, inode, k); ret = PTR_ERR_OR_ZERO(i); if (ret) return ret; ret = check_key_has_inode(trans, iter, inode, i, k); if (ret) return ret; if (!i || i->whiteout) return 0; if (inode->first_this_inode) *hash_info = bch2_hash_info_init(c, &i->inode); inode->first_this_inode = false; bool need_second_pass = false; return bch2_str_hash_check_key(trans, NULL, &bch2_xattr_hash_desc, hash_info, iter, k, &need_second_pass); } /* * Walk xattrs: verify that they all have a corresponding inode */ int bch2_check_xattrs(struct bch_fs *c) { struct inode_walker inode = inode_walker_init(); struct bch_hash_info hash_info; int ret = 0; ret = bch2_trans_run(c, for_each_btree_key_commit(trans, iter, BTREE_ID_xattrs, POS(BCACHEFS_ROOT_INO, 0), BTREE_ITER_prefetch|BTREE_ITER_all_snapshots, k, NULL, NULL, BCH_TRANS_COMMIT_no_enospc, check_xattr(trans, &iter, k, &hash_info, &inode))); inode_walker_exit(&inode); bch_err_fn(c, ret); return ret; } static int check_root_trans(struct btree_trans *trans) { struct bch_fs *c = trans->c; struct bch_inode_unpacked root_inode; u32 snapshot; u64 inum; int ret; ret = subvol_lookup(trans, BCACHEFS_ROOT_SUBVOL, &snapshot, &inum); if (ret && !bch2_err_matches(ret, ENOENT)) return ret; if (mustfix_fsck_err_on(ret, trans, root_subvol_missing, "root subvol missing")) { struct bkey_i_subvolume *root_subvol = bch2_trans_kmalloc(trans, sizeof(*root_subvol)); ret = PTR_ERR_OR_ZERO(root_subvol); if (ret) goto err; snapshot = U32_MAX; inum = BCACHEFS_ROOT_INO; bkey_subvolume_init(&root_subvol->k_i); root_subvol->k.p.offset = BCACHEFS_ROOT_SUBVOL; root_subvol->v.flags = 0; root_subvol->v.snapshot = cpu_to_le32(snapshot); root_subvol->v.inode = cpu_to_le64(inum); ret = bch2_btree_insert_trans(trans, BTREE_ID_subvolumes, &root_subvol->k_i, 0); bch_err_msg(c, ret, "writing root subvol"); if (ret) goto err; } ret = bch2_inode_find_by_inum_snapshot(trans, BCACHEFS_ROOT_INO, snapshot, &root_inode, 0); if (ret && !bch2_err_matches(ret, ENOENT)) return ret; if (mustfix_fsck_err_on(ret, trans, root_dir_missing, "root directory missing") || mustfix_fsck_err_on(!S_ISDIR(root_inode.bi_mode), trans, root_inode_not_dir, "root inode not a directory")) { bch2_inode_init(c, &root_inode, 0, 0, S_IFDIR|0755, 0, NULL); root_inode.bi_inum = inum; root_inode.bi_snapshot = snapshot; ret = __bch2_fsck_write_inode(trans, &root_inode); bch_err_msg(c, ret, "writing root inode"); } err: fsck_err: return ret; } /* Get root directory, create if it doesn't exist: */ int bch2_check_root(struct bch_fs *c) { int ret = bch2_trans_commit_do(c, NULL, NULL, BCH_TRANS_COMMIT_no_enospc, check_root_trans(trans)); bch_err_fn(c, ret); return ret; } static bool darray_u32_has(darray_u32 *d, u32 v) { darray_for_each(*d, i) if (*i == v) return true; return false; } static int check_subvol_path(struct btree_trans *trans, struct btree_iter *iter, struct bkey_s_c k) { struct bch_fs *c = trans->c; struct btree_iter parent_iter = {}; darray_u32 subvol_path = {}; struct printbuf buf = PRINTBUF; int ret = 0; if (k.k->type != KEY_TYPE_subvolume) return 0; subvol_inum start = { .subvol = k.k->p.offset, .inum = le64_to_cpu(bkey_s_c_to_subvolume(k).v->inode), }; while (k.k->p.offset != BCACHEFS_ROOT_SUBVOL) { ret = darray_push(&subvol_path, k.k->p.offset); if (ret) goto err; struct bkey_s_c_subvolume s = bkey_s_c_to_subvolume(k); struct bch_inode_unpacked subvol_root; ret = bch2_inode_find_by_inum_trans(trans, (subvol_inum) { s.k->p.offset, le64_to_cpu(s.v->inode) }, &subvol_root); if (ret) break; u32 parent = le32_to_cpu(s.v->fs_path_parent); if (darray_u32_has(&subvol_path, parent)) { printbuf_reset(&buf); prt_printf(&buf, "subvolume loop: "); ret = bch2_inum_to_path(trans, start, &buf); if (ret) goto err; if (fsck_err(trans, subvol_loop, "%s", buf.buf)) ret = reattach_subvol(trans, s); break; } bch2_trans_iter_exit(trans, &parent_iter); bch2_trans_iter_init(trans, &parent_iter, BTREE_ID_subvolumes, POS(0, parent), 0); k = bch2_btree_iter_peek_slot(trans, &parent_iter); ret = bkey_err(k); if (ret) goto err; if (fsck_err_on(k.k->type != KEY_TYPE_subvolume, trans, subvol_unreachable, "unreachable subvolume %s", (printbuf_reset(&buf), bch2_bkey_val_to_text(&buf, c, s.s_c), buf.buf))) { ret = reattach_subvol(trans, s); break; } } fsck_err: err: printbuf_exit(&buf); darray_exit(&subvol_path); bch2_trans_iter_exit(trans, &parent_iter); return ret; } int bch2_check_subvolume_structure(struct bch_fs *c) { int ret = bch2_trans_run(c, for_each_btree_key_commit(trans, iter, BTREE_ID_subvolumes, POS_MIN, BTREE_ITER_prefetch, k, NULL, NULL, BCH_TRANS_COMMIT_no_enospc, check_subvol_path(trans, &iter, k))); bch_err_fn(c, ret); return ret; } static int bch2_bi_depth_renumber_one(struct btree_trans *trans, u64 inum, u32 snapshot, u32 new_depth) { struct btree_iter iter; struct bkey_s_c k = bch2_bkey_get_iter(trans, &iter, BTREE_ID_inodes, SPOS(0, inum, snapshot), 0); struct bch_inode_unpacked inode; int ret = bkey_err(k) ?: !bkey_is_inode(k.k) ? -BCH_ERR_ENOENT_inode : bch2_inode_unpack(k, &inode); if (ret) goto err; if (inode.bi_depth != new_depth) { inode.bi_depth = new_depth; ret = __bch2_fsck_write_inode(trans, &inode) ?: bch2_trans_commit(trans, NULL, NULL, 0); } err: bch2_trans_iter_exit(trans, &iter); return ret; } static int bch2_bi_depth_renumber(struct btree_trans *trans, darray_u64 *path, u32 snapshot, u32 new_bi_depth) { u32 restart_count = trans->restart_count; int ret = 0; darray_for_each_reverse(*path, i) { ret = nested_lockrestart_do(trans, bch2_bi_depth_renumber_one(trans, *i, snapshot, new_bi_depth)); bch_err_fn(trans->c, ret); if (ret) break; new_bi_depth++; } return ret ?: trans_was_restarted(trans, restart_count); } static int check_path_loop(struct btree_trans *trans, struct bkey_s_c inode_k) { struct bch_fs *c = trans->c; struct btree_iter inode_iter = {}; darray_u64 path = {}; struct printbuf buf = PRINTBUF; u32 snapshot = inode_k.k->p.snapshot; bool redo_bi_depth = false; u32 min_bi_depth = U32_MAX; int ret = 0; struct bpos start = inode_k.k->p; struct bch_inode_unpacked inode; ret = bch2_inode_unpack(inode_k, &inode); if (ret) return ret; /* * If we're running full fsck, check_dirents() will have already ran, * and we shouldn't see any missing backpointers here - otherwise that's * handled separately, by check_unreachable_inodes */ while (!inode.bi_subvol && bch2_inode_has_backpointer(&inode)) { struct btree_iter dirent_iter; struct bkey_s_c_dirent d; d = dirent_get_by_pos(trans, &dirent_iter, SPOS(inode.bi_dir, inode.bi_dir_offset, snapshot)); ret = bkey_err(d.s_c); if (ret && !bch2_err_matches(ret, ENOENT)) goto out; if (!ret && (ret = dirent_points_to_inode(c, d, &inode))) bch2_trans_iter_exit(trans, &dirent_iter); if (bch2_err_matches(ret, ENOENT)) { printbuf_reset(&buf); bch2_bkey_val_to_text(&buf, c, inode_k); bch_err(c, "unreachable inode in check_directory_structure: %s\n%s", bch2_err_str(ret), buf.buf); goto out; } bch2_trans_iter_exit(trans, &dirent_iter); ret = darray_push(&path, inode.bi_inum); if (ret) return ret; bch2_trans_iter_exit(trans, &inode_iter); inode_k = bch2_bkey_get_iter(trans, &inode_iter, BTREE_ID_inodes, SPOS(0, inode.bi_dir, snapshot), 0); struct bch_inode_unpacked parent_inode; ret = bkey_err(inode_k) ?: !bkey_is_inode(inode_k.k) ? -BCH_ERR_ENOENT_inode : bch2_inode_unpack(inode_k, &parent_inode); if (ret) { /* Should have been caught in dirents pass */ bch_err_msg(c, ret, "error looking up parent directory"); goto out; } min_bi_depth = parent_inode.bi_depth; if (parent_inode.bi_depth < inode.bi_depth && min_bi_depth < U16_MAX) break; inode = parent_inode; redo_bi_depth = true; if (darray_find(path, inode.bi_inum)) { printbuf_reset(&buf); prt_printf(&buf, "directory structure loop in snapshot %u: ", snapshot); ret = bch2_inum_snapshot_to_path(trans, start.offset, start.snapshot, NULL, &buf); if (ret) goto out; if (c->opts.verbose) { prt_newline(&buf); darray_for_each(path, i) prt_printf(&buf, "%llu ", *i); } if (fsck_err(trans, dir_loop, "%s", buf.buf)) { ret = remove_backpointer(trans, &inode); bch_err_msg(c, ret, "removing dirent"); if (ret) goto out; ret = reattach_inode(trans, &inode); bch_err_msg(c, ret, "reattaching inode %llu", inode.bi_inum); } goto out; } } if (inode.bi_subvol) min_bi_depth = 0; if (redo_bi_depth) ret = bch2_bi_depth_renumber(trans, &path, snapshot, min_bi_depth); out: fsck_err: bch2_trans_iter_exit(trans, &inode_iter); darray_exit(&path); printbuf_exit(&buf); bch_err_fn(c, ret); return ret; } /* * Check for loops in the directory structure: all other connectivity issues * have been fixed by prior passes */ int bch2_check_directory_structure(struct bch_fs *c) { int ret = bch2_trans_run(c, for_each_btree_key_reverse_commit(trans, iter, BTREE_ID_inodes, POS_MIN, BTREE_ITER_intent| BTREE_ITER_prefetch| BTREE_ITER_all_snapshots, k, NULL, NULL, BCH_TRANS_COMMIT_no_enospc, ({ if (!S_ISDIR(bkey_inode_mode(k))) continue; if (bch2_inode_flags(k) & BCH_INODE_unlinked) continue; check_path_loop(trans, k); }))); bch_err_fn(c, ret); return ret; } struct nlink_table { size_t nr; size_t size; struct nlink { u64 inum; u32 snapshot; u32 count; } *d; }; static int add_nlink(struct bch_fs *c, struct nlink_table *t, u64 inum, u32 snapshot) { if (t->nr == t->size) { size_t new_size = max_t(size_t, 128UL, t->size * 2); void *d = kvmalloc_array(new_size, sizeof(t->d[0]), GFP_KERNEL); if (!d) { bch_err(c, "fsck: error allocating memory for nlink_table, size %zu", new_size); return bch_err_throw(c, ENOMEM_fsck_add_nlink); } if (t->d) memcpy(d, t->d, t->size * sizeof(t->d[0])); kvfree(t->d); t->d = d; t->size = new_size; } t->d[t->nr++] = (struct nlink) { .inum = inum, .snapshot = snapshot, }; return 0; } static int nlink_cmp(const void *_l, const void *_r) { const struct nlink *l = _l; const struct nlink *r = _r; return cmp_int(l->inum, r->inum); } static void inc_link(struct bch_fs *c, struct snapshots_seen *s, struct nlink_table *links, u64 range_start, u64 range_end, u64 inum, u32 snapshot) { struct nlink *link, key = { .inum = inum, .snapshot = U32_MAX, }; if (inum < range_start || inum >= range_end) return; link = __inline_bsearch(&key, links->d, links->nr, sizeof(links->d[0]), nlink_cmp); if (!link) return; while (link > links->d && link[0].inum == link[-1].inum) --link; for (; link < links->d + links->nr && link->inum == inum; link++) if (ref_visible(c, s, snapshot, link->snapshot)) { link->count++; if (link->snapshot >= snapshot) break; } } noinline_for_stack static int check_nlinks_find_hardlinks(struct bch_fs *c, struct nlink_table *t, u64 start, u64 *end) { int ret = bch2_trans_run(c, for_each_btree_key(trans, iter, BTREE_ID_inodes, POS(0, start), BTREE_ITER_intent| BTREE_ITER_prefetch| BTREE_ITER_all_snapshots, k, ({ if (!bkey_is_inode(k.k)) continue; /* Should never fail, checked by bch2_inode_invalid: */ struct bch_inode_unpacked u; _ret3 = bch2_inode_unpack(k, &u); if (_ret3) break; /* * Backpointer and directory structure checks are sufficient for * directories, since they can't have hardlinks: */ if (S_ISDIR(u.bi_mode)) continue; /* * Previous passes ensured that bi_nlink is nonzero if * it had multiple hardlinks: */ if (!u.bi_nlink) continue; ret = add_nlink(c, t, k.k->p.offset, k.k->p.snapshot); if (ret) { *end = k.k->p.offset; ret = 0; break; } 0; }))); bch_err_fn(c, ret); return ret; } noinline_for_stack static int check_nlinks_walk_dirents(struct bch_fs *c, struct nlink_table *links, u64 range_start, u64 range_end) { struct snapshots_seen s; snapshots_seen_init(&s); int ret = bch2_trans_run(c, for_each_btree_key(trans, iter, BTREE_ID_dirents, POS_MIN, BTREE_ITER_intent| BTREE_ITER_prefetch| BTREE_ITER_all_snapshots, k, ({ ret = snapshots_seen_update(c, &s, iter.btree_id, k.k->p); if (ret) break; if (k.k->type == KEY_TYPE_dirent) { struct bkey_s_c_dirent d = bkey_s_c_to_dirent(k); if (d.v->d_type != DT_DIR && d.v->d_type != DT_SUBVOL) inc_link(c, &s, links, range_start, range_end, le64_to_cpu(d.v->d_inum), d.k->p.snapshot); } 0; }))); snapshots_seen_exit(&s); bch_err_fn(c, ret); return ret; } static int check_nlinks_update_inode(struct btree_trans *trans, struct btree_iter *iter, struct bkey_s_c k, struct nlink_table *links, size_t *idx, u64 range_end) { struct bch_inode_unpacked u; struct nlink *link = &links->d[*idx]; int ret = 0; if (k.k->p.offset >= range_end) return 1; if (!bkey_is_inode(k.k)) return 0; ret = bch2_inode_unpack(k, &u); if (ret) return ret; if (S_ISDIR(u.bi_mode)) return 0; if (!u.bi_nlink) return 0; while ((cmp_int(link->inum, k.k->p.offset) ?: cmp_int(link->snapshot, k.k->p.snapshot)) < 0) { BUG_ON(*idx == links->nr); link = &links->d[++*idx]; } if (fsck_err_on(bch2_inode_nlink_get(&u) != link->count, trans, inode_wrong_nlink, "inode %llu type %s has wrong i_nlink (%u, should be %u)", u.bi_inum, bch2_d_types[mode_to_type(u.bi_mode)], bch2_inode_nlink_get(&u), link->count)) { bch2_inode_nlink_set(&u, link->count); ret = __bch2_fsck_write_inode(trans, &u); } fsck_err: return ret; } noinline_for_stack static int check_nlinks_update_hardlinks(struct bch_fs *c, struct nlink_table *links, u64 range_start, u64 range_end) { size_t idx = 0; int ret = bch2_trans_run(c, for_each_btree_key_commit(trans, iter, BTREE_ID_inodes, POS(0, range_start), BTREE_ITER_intent|BTREE_ITER_prefetch|BTREE_ITER_all_snapshots, k, NULL, NULL, BCH_TRANS_COMMIT_no_enospc, check_nlinks_update_inode(trans, &iter, k, links, &idx, range_end))); if (ret < 0) { bch_err(c, "error in fsck walking inodes: %s", bch2_err_str(ret)); return ret; } return 0; } int bch2_check_nlinks(struct bch_fs *c) { struct nlink_table links = { 0 }; u64 this_iter_range_start, next_iter_range_start = 0; int ret = 0; do { this_iter_range_start = next_iter_range_start; next_iter_range_start = U64_MAX; ret = check_nlinks_find_hardlinks(c, &links, this_iter_range_start, &next_iter_range_start); ret = check_nlinks_walk_dirents(c, &links, this_iter_range_start, next_iter_range_start); if (ret) break; ret = check_nlinks_update_hardlinks(c, &links, this_iter_range_start, next_iter_range_start); if (ret) break; links.nr = 0; } while (next_iter_range_start != U64_MAX); kvfree(links.d); bch_err_fn(c, ret); return ret; } static int fix_reflink_p_key(struct btree_trans *trans, struct btree_iter *iter, struct bkey_s_c k) { struct bkey_s_c_reflink_p p; struct bkey_i_reflink_p *u; if (k.k->type != KEY_TYPE_reflink_p) return 0; p = bkey_s_c_to_reflink_p(k); if (!p.v->front_pad && !p.v->back_pad) return 0; u = bch2_trans_kmalloc(trans, sizeof(*u)); int ret = PTR_ERR_OR_ZERO(u); if (ret) return ret; bkey_reassemble(&u->k_i, k); u->v.front_pad = 0; u->v.back_pad = 0; return bch2_trans_update(trans, iter, &u->k_i, BTREE_TRIGGER_norun); } int bch2_fix_reflink_p(struct bch_fs *c) { if (c->sb.version >= bcachefs_metadata_version_reflink_p_fix) return 0; int ret = bch2_trans_run(c, for_each_btree_key_commit(trans, iter, BTREE_ID_extents, POS_MIN, BTREE_ITER_intent|BTREE_ITER_prefetch| BTREE_ITER_all_snapshots, k, NULL, NULL, BCH_TRANS_COMMIT_no_enospc, fix_reflink_p_key(trans, &iter, k))); bch_err_fn(c, ret); return ret; } #ifndef NO_BCACHEFS_CHARDEV struct fsck_thread { struct thread_with_stdio thr; struct bch_fs *c; struct bch_opts opts; }; static void bch2_fsck_thread_exit(struct thread_with_stdio *_thr) { struct fsck_thread *thr = container_of(_thr, struct fsck_thread, thr); kfree(thr); } static int bch2_fsck_offline_thread_fn(struct thread_with_stdio *stdio) { struct fsck_thread *thr = container_of(stdio, struct fsck_thread, thr); struct bch_fs *c = thr->c; int ret = PTR_ERR_OR_ZERO(c); if (ret) return ret; ret = bch2_fs_start(thr->c); if (ret) goto err; if (test_bit(BCH_FS_errors_fixed, &c->flags)) { bch2_stdio_redirect_printf(&stdio->stdio, false, "%s: errors fixed\n", c->name); ret |= 1; } if (test_bit(BCH_FS_error, &c->flags)) { bch2_stdio_redirect_printf(&stdio->stdio, false, "%s: still has errors\n", c->name); ret |= 4; } err: bch2_fs_stop(c); return ret; } static const struct thread_with_stdio_ops bch2_offline_fsck_ops = { .exit = bch2_fsck_thread_exit, .fn = bch2_fsck_offline_thread_fn, }; long bch2_ioctl_fsck_offline(struct bch_ioctl_fsck_offline __user *user_arg) { struct bch_ioctl_fsck_offline arg; struct fsck_thread *thr = NULL; darray_const_str devs = {}; long ret = 0; if (copy_from_user(&arg, user_arg, sizeof(arg))) return -EFAULT; if (arg.flags) return -EINVAL; if (!capable(CAP_SYS_ADMIN)) return -EPERM; for (size_t i = 0; i < arg.nr_devs; i++) { u64 dev_u64; ret = copy_from_user_errcode(&dev_u64, &user_arg->devs[i], sizeof(u64)); if (ret) goto err; char *dev_str = strndup_user((char __user *)(unsigned long) dev_u64, PATH_MAX); ret = PTR_ERR_OR_ZERO(dev_str); if (ret) goto err; ret = darray_push(&devs, dev_str); if (ret) { kfree(dev_str); goto err; } } thr = kzalloc(sizeof(*thr), GFP_KERNEL); if (!thr) { ret = -ENOMEM; goto err; } thr->opts = bch2_opts_empty(); if (arg.opts) { char *optstr = strndup_user((char __user *)(unsigned long) arg.opts, 1 << 16); ret = PTR_ERR_OR_ZERO(optstr) ?: bch2_parse_mount_opts(NULL, &thr->opts, NULL, optstr, false); if (!IS_ERR(optstr)) kfree(optstr); if (ret) goto err; } opt_set(thr->opts, stdio, (u64)(unsigned long)&thr->thr.stdio); opt_set(thr->opts, read_only, 1); opt_set(thr->opts, ratelimit_errors, 0); /* We need request_key() to be called before we punt to kthread: */ opt_set(thr->opts, nostart, true); bch2_thread_with_stdio_init(&thr->thr, &bch2_offline_fsck_ops); thr->c = bch2_fs_open(&devs, &thr->opts); if (!IS_ERR(thr->c) && thr->c->opts.errors == BCH_ON_ERROR_panic) thr->c->opts.errors = BCH_ON_ERROR_ro; ret = __bch2_run_thread_with_stdio(&thr->thr); out: darray_for_each(devs, i) kfree(*i); darray_exit(&devs); return ret; err: if (thr) bch2_fsck_thread_exit(&thr->thr); pr_err("ret %s", bch2_err_str(ret)); goto out; } static int bch2_fsck_online_thread_fn(struct thread_with_stdio *stdio) { struct fsck_thread *thr = container_of(stdio, struct fsck_thread, thr); struct bch_fs *c = thr->c; c->stdio_filter = current; c->stdio = &thr->thr.stdio; /* * XXX: can we figure out a way to do this without mucking with c->opts? */ unsigned old_fix_errors = c->opts.fix_errors; if (opt_defined(thr->opts, fix_errors)) c->opts.fix_errors = thr->opts.fix_errors; else c->opts.fix_errors = FSCK_FIX_ask; c->opts.fsck = true; set_bit(BCH_FS_in_fsck, &c->flags); int ret = bch2_run_online_recovery_passes(c, ~0ULL); clear_bit(BCH_FS_in_fsck, &c->flags); bch_err_fn(c, ret); c->stdio = NULL; c->stdio_filter = NULL; c->opts.fix_errors = old_fix_errors; up(&c->recovery.run_lock); bch2_ro_ref_put(c); return ret; } static const struct thread_with_stdio_ops bch2_online_fsck_ops = { .exit = bch2_fsck_thread_exit, .fn = bch2_fsck_online_thread_fn, }; long bch2_ioctl_fsck_online(struct bch_fs *c, struct bch_ioctl_fsck_online arg) { struct fsck_thread *thr = NULL; long ret = 0; if (arg.flags) return -EINVAL; if (!capable(CAP_SYS_ADMIN)) return -EPERM; if (!bch2_ro_ref_tryget(c)) return -EROFS; if (down_trylock(&c->recovery.run_lock)) { bch2_ro_ref_put(c); return -EAGAIN; } thr = kzalloc(sizeof(*thr), GFP_KERNEL); if (!thr) { ret = -ENOMEM; goto err; } thr->c = c; thr->opts = bch2_opts_empty(); if (arg.opts) { char *optstr = strndup_user((char __user *)(unsigned long) arg.opts, 1 << 16); ret = PTR_ERR_OR_ZERO(optstr) ?: bch2_parse_mount_opts(c, &thr->opts, NULL, optstr, false); if (!IS_ERR(optstr)) kfree(optstr); if (ret) goto err; } ret = bch2_run_thread_with_stdio(&thr->thr, &bch2_online_fsck_ops); err: if (ret < 0) { bch_err_fn(c, ret); if (thr) bch2_fsck_thread_exit(&thr->thr); up(&c->recovery.run_lock); bch2_ro_ref_put(c); } return ret; } #endif /* NO_BCACHEFS_CHARDEV */ |
| 18 18 18 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0 #include <linux/ceph/ceph_debug.h> #include <linux/fs.h> #include <linux/sort.h> #include <linux/slab.h> #include <linux/iversion.h> #include "super.h" #include "mds_client.h" #include <linux/ceph/decode.h> /* unused map expires after 5 minutes */ #define CEPH_SNAPID_MAP_TIMEOUT (5 * 60 * HZ) /* * Snapshots in ceph are driven in large part by cooperation from the * client. In contrast to local file systems or file servers that * implement snapshots at a single point in the system, ceph's * distributed access to storage requires clients to help decide * whether a write logically occurs before or after a recently created * snapshot. * * This provides a perfect instantanous client-wide snapshot. Between * clients, however, snapshots may appear to be applied at slightly * different points in time, depending on delays in delivering the * snapshot notification. * * Snapshots are _not_ file system-wide. Instead, each snapshot * applies to the subdirectory nested beneath some directory. This * effectively divides the hierarchy into multiple "realms," where all * of the files contained by each realm share the same set of * snapshots. An individual realm's snap set contains snapshots * explicitly created on that realm, as well as any snaps in its * parent's snap set _after_ the point at which the parent became it's * parent (due to, say, a rename). Similarly, snaps from prior parents * during the time intervals during which they were the parent are included. * * The client is spared most of this detail, fortunately... it must only * maintains a hierarchy of realms reflecting the current parent/child * realm relationship, and for each realm has an explicit list of snaps * inherited from prior parents. * * A snap_realm struct is maintained for realms containing every inode * with an open cap in the system. (The needed snap realm information is * provided by the MDS whenever a cap is issued, i.e., on open.) A 'seq' * version number is used to ensure that as realm parameters change (new * snapshot, new parent, etc.) the client's realm hierarchy is updated. * * The realm hierarchy drives the generation of a 'snap context' for each * realm, which simply lists the resulting set of snaps for the realm. This * is attached to any writes sent to OSDs. */ /* * Unfortunately error handling is a bit mixed here. If we get a snap * update, but don't have enough memory to update our realm hierarchy, * it's not clear what we can do about it (besides complaining to the * console). */ /* * increase ref count for the realm * * caller must hold snap_rwsem. */ void ceph_get_snap_realm(struct ceph_mds_client *mdsc, struct ceph_snap_realm *realm) { lockdep_assert_held(&mdsc->snap_rwsem); /* * The 0->1 and 1->0 transitions must take the snap_empty_lock * atomically with the refcount change. Go ahead and bump the * nref here, unless it's 0, in which case we take the spinlock * and then do the increment and remove it from the list. */ if (atomic_inc_not_zero(&realm->nref)) return; spin_lock(&mdsc->snap_empty_lock); if (atomic_inc_return(&realm->nref) == 1) list_del_init(&realm->empty_item); spin_unlock(&mdsc->snap_empty_lock); } static void __insert_snap_realm(struct rb_root *root, struct ceph_snap_realm *new) { struct rb_node **p = &root->rb_node; struct rb_node *parent = NULL; struct ceph_snap_realm *r = NULL; while (*p) { parent = *p; r = rb_entry(parent, struct ceph_snap_realm, node); if (new->ino < r->ino) p = &(*p)->rb_left; else if (new->ino > r->ino) p = &(*p)->rb_right; else BUG(); } rb_link_node(&new->node, parent, p); rb_insert_color(&new->node, root); } /* * create and get the realm rooted at @ino and bump its ref count. * * caller must hold snap_rwsem for write. */ static struct ceph_snap_realm *ceph_create_snap_realm( struct ceph_mds_client *mdsc, u64 ino) { struct ceph_snap_realm *realm; lockdep_assert_held_write(&mdsc->snap_rwsem); realm = kzalloc(sizeof(*realm), GFP_NOFS); if (!realm) return ERR_PTR(-ENOMEM); /* Do not release the global dummy snaprealm until unmouting */ if (ino == CEPH_INO_GLOBAL_SNAPREALM) atomic_set(&realm->nref, 2); else atomic_set(&realm->nref, 1); realm->ino = ino; INIT_LIST_HEAD(&realm->children); INIT_LIST_HEAD(&realm->child_item); INIT_LIST_HEAD(&realm->empty_item); INIT_LIST_HEAD(&realm->dirty_item); INIT_LIST_HEAD(&realm->rebuild_item); INIT_LIST_HEAD(&realm->inodes_with_caps); spin_lock_init(&realm->inodes_with_caps_lock); __insert_snap_realm(&mdsc->snap_realms, realm); mdsc->num_snap_realms++; doutc(mdsc->fsc->client, "%llx %p\n", realm->ino, realm); return realm; } /* * lookup the realm rooted at @ino. * * caller must hold snap_rwsem. */ static struct ceph_snap_realm *__lookup_snap_realm(struct ceph_mds_client *mdsc, u64 ino) { struct ceph_client *cl = mdsc->fsc->client; struct rb_node *n = mdsc->snap_realms.rb_node; struct ceph_snap_realm *r; lockdep_assert_held(&mdsc->snap_rwsem); while (n) { r = rb_entry(n, struct ceph_snap_realm, node); if (ino < r->ino) n = n->rb_left; else if (ino > r->ino) n = n->rb_right; else { doutc(cl, "%llx %p\n", r->ino, r); return r; } } return NULL; } struct ceph_snap_realm *ceph_lookup_snap_realm(struct ceph_mds_client *mdsc, u64 ino) { struct ceph_snap_realm *r; r = __lookup_snap_realm(mdsc, ino); if (r) ceph_get_snap_realm(mdsc, r); return r; } static void __put_snap_realm(struct ceph_mds_client *mdsc, struct ceph_snap_realm *realm); /* * called with snap_rwsem (write) */ static void __destroy_snap_realm(struct ceph_mds_client *mdsc, struct ceph_snap_realm *realm) { struct ceph_client *cl = mdsc->fsc->client; lockdep_assert_held_write(&mdsc->snap_rwsem); doutc(cl, "%p %llx\n", realm, realm->ino); rb_erase(&realm->node, &mdsc->snap_realms); mdsc->num_snap_realms--; if (realm->parent) { list_del_init(&realm->child_item); __put_snap_realm(mdsc, realm->parent); } kfree(realm->prior_parent_snaps); kfree(realm->snaps); ceph_put_snap_context(realm->cached_context); kfree(realm); } /* * caller holds snap_rwsem (write) */ static void __put_snap_realm(struct ceph_mds_client *mdsc, struct ceph_snap_realm *realm) { lockdep_assert_held_write(&mdsc->snap_rwsem); /* * We do not require the snap_empty_lock here, as any caller that * increments the value must hold the snap_rwsem. */ if (atomic_dec_and_test(&realm->nref)) __destroy_snap_realm(mdsc, realm); } /* * See comments in ceph_get_snap_realm. Caller needn't hold any locks. */ void ceph_put_snap_realm(struct ceph_mds_client *mdsc, struct ceph_snap_realm *realm) { if (!atomic_dec_and_lock(&realm->nref, &mdsc->snap_empty_lock)) return; if (down_write_trylock(&mdsc->snap_rwsem)) { spin_unlock(&mdsc->snap_empty_lock); __destroy_snap_realm(mdsc, realm); up_write(&mdsc->snap_rwsem); } else { list_add(&realm->empty_item, &mdsc->snap_empty); spin_unlock(&mdsc->snap_empty_lock); } } /* * Clean up any realms whose ref counts have dropped to zero. Note * that this does not include realms who were created but not yet * used. * * Called under snap_rwsem (write) */ static void __cleanup_empty_realms(struct ceph_mds_client *mdsc) { struct ceph_snap_realm *realm; lockdep_assert_held_write(&mdsc->snap_rwsem); spin_lock(&mdsc->snap_empty_lock); while (!list_empty(&mdsc->snap_empty)) { realm = list_first_entry(&mdsc->snap_empty, struct ceph_snap_realm, empty_item); list_del(&realm->empty_item); spin_unlock(&mdsc->snap_empty_lock); __destroy_snap_realm(mdsc, realm); spin_lock(&mdsc->snap_empty_lock); } spin_unlock(&mdsc->snap_empty_lock); } void ceph_cleanup_global_and_empty_realms(struct ceph_mds_client *mdsc) { struct ceph_snap_realm *global_realm; down_write(&mdsc->snap_rwsem); global_realm = __lookup_snap_realm(mdsc, CEPH_INO_GLOBAL_SNAPREALM); if (global_realm) ceph_put_snap_realm(mdsc, global_realm); __cleanup_empty_realms(mdsc); up_write(&mdsc->snap_rwsem); } /* * adjust the parent realm of a given @realm. adjust child list, and parent * pointers, and ref counts appropriately. * * return true if parent was changed, 0 if unchanged, <0 on error. * * caller must hold snap_rwsem for write. */ static int adjust_snap_realm_parent(struct ceph_mds_client *mdsc, struct ceph_snap_realm *realm, u64 parentino) { struct ceph_client *cl = mdsc->fsc->client; struct ceph_snap_realm *parent; lockdep_assert_held_write(&mdsc->snap_rwsem); if (realm->parent_ino == parentino) return 0; parent = ceph_lookup_snap_realm(mdsc, parentino); if (!parent) { parent = ceph_create_snap_realm(mdsc, parentino); if (IS_ERR(parent)) return PTR_ERR(parent); } doutc(cl, "%llx %p: %llx %p -> %llx %p\n", realm->ino, realm, realm->parent_ino, realm->parent, parentino, parent); if (realm->parent) { list_del_init(&realm->child_item); ceph_put_snap_realm(mdsc, realm->parent); } realm->parent_ino = parentino; realm->parent = parent; list_add(&realm->child_item, &parent->children); return 1; } static int cmpu64_rev(const void *a, const void *b) { if (*(u64 *)a < *(u64 *)b) return 1; if (*(u64 *)a > *(u64 *)b) return -1; return 0; } /* * build the snap context for a given realm. */ static int build_snap_context(struct ceph_mds_client *mdsc, struct ceph_snap_realm *realm, struct list_head *realm_queue, struct list_head *dirty_realms) { struct ceph_client *cl = mdsc->fsc->client; struct ceph_snap_realm *parent = realm->parent; struct ceph_snap_context *snapc; int err = 0; u32 num = realm->num_prior_parent_snaps + realm->num_snaps; /* * build parent context, if it hasn't been built. * conservatively estimate that all parent snaps might be * included by us. */ if (parent) { if (!parent->cached_context) { /* add to the queue head */ list_add(&parent->rebuild_item, realm_queue); return 1; } num += parent->cached_context->num_snaps; } /* do i actually need to update? not if my context seq matches realm seq, and my parents' does to. (this works because we rebuild_snap_realms() works _downward_ in hierarchy after each update.) */ if (realm->cached_context && realm->cached_context->seq == realm->seq && (!parent || realm->cached_context->seq >= parent->cached_context->seq)) { doutc(cl, "%llx %p: %p seq %lld (%u snaps) (unchanged)\n", realm->ino, realm, realm->cached_context, realm->cached_context->seq, (unsigned int)realm->cached_context->num_snaps); return 0; } /* alloc new snap context */ err = -ENOMEM; if (num > (SIZE_MAX - sizeof(*snapc)) / sizeof(u64)) goto fail; snapc = ceph_create_snap_context(num, GFP_NOFS); if (!snapc) goto fail; /* build (reverse sorted) snap vector */ num = 0; snapc->seq = realm->seq; if (parent) { u32 i; /* include any of parent's snaps occurring _after_ my parent became my parent */ for (i = 0; i < parent->cached_context->num_snaps; i++) if (parent->cached_context->snaps[i] >= realm->parent_since) snapc->snaps[num++] = parent->cached_context->snaps[i]; if (parent->cached_context->seq > snapc->seq) snapc->seq = parent->cached_context->seq; } memcpy(snapc->snaps + num, realm->snaps, sizeof(u64)*realm->num_snaps); num += realm->num_snaps; memcpy(snapc->snaps + num, realm->prior_parent_snaps, sizeof(u64)*realm->num_prior_parent_snaps); num += realm->num_prior_parent_snaps; sort(snapc->snaps, num, sizeof(u64), cmpu64_rev, NULL); snapc->num_snaps = num; doutc(cl, "%llx %p: %p seq %lld (%u snaps)\n", realm->ino, realm, snapc, snapc->seq, (unsigned int) snapc->num_snaps); ceph_put_snap_context(realm->cached_context); realm->cached_context = snapc; /* queue realm for cap_snap creation */ list_add_tail(&realm->dirty_item, dirty_realms); return 0; fail: /* * if we fail, clear old (incorrect) cached_context... hopefully * we'll have better luck building it later */ if (realm->cached_context) { ceph_put_snap_context(realm->cached_context); realm->cached_context = NULL; } pr_err_client(cl, "%llx %p fail %d\n", realm->ino, realm, err); return err; } /* * rebuild snap context for the given realm and all of its children. */ static void rebuild_snap_realms(struct ceph_mds_client *mdsc, struct ceph_snap_realm *realm, struct list_head *dirty_realms) { struct ceph_client *cl = mdsc->fsc->client; LIST_HEAD(realm_queue); int last = 0; bool skip = false; list_add_tail(&realm->rebuild_item, &realm_queue); while (!list_empty(&realm_queue)) { struct ceph_snap_realm *_realm, *child; _realm = list_first_entry(&realm_queue, struct ceph_snap_realm, rebuild_item); /* * If the last building failed dues to memory * issue, just empty the realm_queue and return * to avoid infinite loop. */ if (last < 0) { list_del_init(&_realm->rebuild_item); continue; } last = build_snap_context(mdsc, _realm, &realm_queue, dirty_realms); doutc(cl, "%llx %p, %s\n", realm->ino, realm, last > 0 ? "is deferred" : !last ? "succeeded" : "failed"); /* is any child in the list ? */ list_for_each_entry(child, &_realm->children, child_item) { if (!list_empty(&child->rebuild_item)) { skip = true; break; } } if (!skip) { list_for_each_entry(child, &_realm->children, child_item) list_add_tail(&child->rebuild_item, &realm_queue); } /* last == 1 means need to build parent first */ if (last <= 0) list_del_init(&_realm->rebuild_item); } } /* * helper to allocate and decode an array of snapids. free prior * instance, if any. */ static int dup_array(u64 **dst, __le64 *src, u32 num) { u32 i; kfree(*dst); if (num) { *dst = kcalloc(num, sizeof(u64), GFP_NOFS); if (!*dst) return -ENOMEM; for (i = 0; i < num; i++) (*dst)[i] = get_unaligned_le64(src + i); } else { *dst = NULL; } return 0; } static bool has_new_snaps(struct ceph_snap_context *o, struct ceph_snap_context *n) { if (n->num_snaps == 0) return false; /* snaps are in descending order */ return n->snaps[0] > o->seq; } /* * When a snapshot is applied, the size/mtime inode metadata is queued * in a ceph_cap_snap (one for each snapshot) until writeback * completes and the metadata can be flushed back to the MDS. * * However, if a (sync) write is currently in-progress when we apply * the snapshot, we have to wait until the write succeeds or fails * (and a final size/mtime is known). In this case the * cap_snap->writing = 1, and is said to be "pending." When the write * finishes, we __ceph_finish_cap_snap(). * * Caller must hold snap_rwsem for read (i.e., the realm topology won't * change). */ static void ceph_queue_cap_snap(struct ceph_inode_info *ci, struct ceph_cap_snap **pcapsnap) { struct inode *inode = &ci->netfs.inode; struct ceph_client *cl = ceph_inode_to_client(inode); struct ceph_snap_context *old_snapc, *new_snapc; struct ceph_cap_snap *capsnap = *pcapsnap; struct ceph_buffer *old_blob = NULL; int used, dirty; spin_lock(&ci->i_ceph_lock); used = __ceph_caps_used(ci); dirty = __ceph_caps_dirty(ci); old_snapc = ci->i_head_snapc; new_snapc = ci->i_snap_realm->cached_context; /* * If there is a write in progress, treat that as a dirty Fw, * even though it hasn't completed yet; by the time we finish * up this capsnap it will be. */ if (used & CEPH_CAP_FILE_WR) dirty |= CEPH_CAP_FILE_WR; if (__ceph_have_pending_cap_snap(ci)) { /* there is no point in queuing multiple "pending" cap_snaps, as no new writes are allowed to start when pending, so any writes in progress now were started before the previous cap_snap. lucky us. */ doutc(cl, "%p %llx.%llx already pending\n", inode, ceph_vinop(inode)); goto update_snapc; } if (ci->i_wrbuffer_ref_head == 0 && !(dirty & (CEPH_CAP_ANY_EXCL|CEPH_CAP_FILE_WR))) { doutc(cl, "%p %llx.%llx nothing dirty|writing\n", inode, ceph_vinop(inode)); goto update_snapc; } BUG_ON(!old_snapc); /* * There is no need to send FLUSHSNAP message to MDS if there is * no new snapshot. But when there is dirty pages or on-going * writes, we still need to create cap_snap. cap_snap is needed * by the write path and page writeback path. * * also see ceph_try_drop_cap_snap() */ if (has_new_snaps(old_snapc, new_snapc)) { if (dirty & (CEPH_CAP_ANY_EXCL|CEPH_CAP_FILE_WR)) capsnap->need_flush = true; } else { if (!(used & CEPH_CAP_FILE_WR) && ci->i_wrbuffer_ref_head == 0) { doutc(cl, "%p %llx.%llx no new_snap|dirty_page|writing\n", inode, ceph_vinop(inode)); goto update_snapc; } } doutc(cl, "%p %llx.%llx cap_snap %p queuing under %p %s %s\n", inode, ceph_vinop(inode), capsnap, old_snapc, ceph_cap_string(dirty), capsnap->need_flush ? "" : "no_flush"); ihold(inode); capsnap->follows = old_snapc->seq; capsnap->issued = __ceph_caps_issued(ci, NULL); capsnap->dirty = dirty; capsnap->mode = inode->i_mode; capsnap->uid = inode->i_uid; capsnap->gid = inode->i_gid; if (dirty & CEPH_CAP_XATTR_EXCL) { old_blob = __ceph_build_xattrs_blob(ci); capsnap->xattr_blob = ceph_buffer_get(ci->i_xattrs.blob); capsnap->xattr_version = ci->i_xattrs.version; } else { capsnap->xattr_blob = NULL; capsnap->xattr_version = 0; } capsnap->inline_data = ci->i_inline_version != CEPH_INLINE_NONE; /* dirty page count moved from _head to this cap_snap; all subsequent writes page dirties occur _after_ this snapshot. */ capsnap->dirty_pages = ci->i_wrbuffer_ref_head; ci->i_wrbuffer_ref_head = 0; capsnap->context = old_snapc; list_add_tail(&capsnap->ci_item, &ci->i_cap_snaps); if (used & CEPH_CAP_FILE_WR) { doutc(cl, "%p %llx.%llx cap_snap %p snapc %p seq %llu used WR," " now pending\n", inode, ceph_vinop(inode), capsnap, old_snapc, old_snapc->seq); capsnap->writing = 1; } else { /* note mtime, size NOW. */ __ceph_finish_cap_snap(ci, capsnap); } *pcapsnap = NULL; old_snapc = NULL; update_snapc: if (ci->i_wrbuffer_ref_head == 0 && ci->i_wr_ref == 0 && ci->i_dirty_caps == 0 && ci->i_flushing_caps == 0) { ci->i_head_snapc = NULL; } else { ci->i_head_snapc = ceph_get_snap_context(new_snapc); doutc(cl, " new snapc is %p\n", new_snapc); } spin_unlock(&ci->i_ceph_lock); ceph_buffer_put(old_blob); ceph_put_snap_context(old_snapc); } /* * Finalize the size, mtime for a cap_snap.. that is, settle on final values * to be used for the snapshot, to be flushed back to the mds. * * If capsnap can now be flushed, add to snap_flush list, and return 1. * * Caller must hold i_ceph_lock. */ int __ceph_finish_cap_snap(struct ceph_inode_info *ci, struct ceph_cap_snap *capsnap) { struct inode *inode = &ci->netfs.inode; struct ceph_mds_client *mdsc = ceph_sb_to_mdsc(inode->i_sb); struct ceph_client *cl = mdsc->fsc->client; BUG_ON(capsnap->writing); capsnap->size = i_size_read(inode); capsnap->mtime = inode_get_mtime(inode); capsnap->atime = inode_get_atime(inode); capsnap->ctime = inode_get_ctime(inode); capsnap->btime = ci->i_btime; capsnap->change_attr = inode_peek_iversion_raw(inode); capsnap->time_warp_seq = ci->i_time_warp_seq; capsnap->truncate_size = ci->i_truncate_size; capsnap->truncate_seq = ci->i_truncate_seq; if (capsnap->dirty_pages) { doutc(cl, "%p %llx.%llx cap_snap %p snapc %p %llu %s " "s=%llu still has %d dirty pages\n", inode, ceph_vinop(inode), capsnap, capsnap->context, capsnap->context->seq, ceph_cap_string(capsnap->dirty), capsnap->size, capsnap->dirty_pages); return 0; } /* * Defer flushing the capsnap if the dirty buffer not flushed yet. * And trigger to flush the buffer immediately. */ if (ci->i_wrbuffer_ref) { doutc(cl, "%p %llx.%llx cap_snap %p snapc %p %llu %s " "s=%llu used WRBUFFER, delaying\n", inode, ceph_vinop(inode), capsnap, capsnap->context, capsnap->context->seq, ceph_cap_string(capsnap->dirty), capsnap->size); ceph_queue_writeback(inode); return 0; } ci->i_ceph_flags |= CEPH_I_FLUSH_SNAPS; doutc(cl, "%p %llx.%llx cap_snap %p snapc %p %llu %s s=%llu\n", inode, ceph_vinop(inode), capsnap, capsnap->context, capsnap->context->seq, ceph_cap_string(capsnap->dirty), capsnap->size); spin_lock(&mdsc->snap_flush_lock); if (list_empty(&ci->i_snap_flush_item)) { ihold(inode); list_add_tail(&ci->i_snap_flush_item, &mdsc->snap_flush_list); } spin_unlock(&mdsc->snap_flush_lock); return 1; /* caller may want to ceph_flush_snaps */ } /* * Queue cap_snaps for snap writeback for this realm and its children. * Called under snap_rwsem, so realm topology won't change. */ static void queue_realm_cap_snaps(struct ceph_mds_client *mdsc, struct ceph_snap_realm *realm) { struct ceph_client *cl = mdsc->fsc->client; struct ceph_inode_info *ci; struct inode *lastinode = NULL; struct ceph_cap_snap *capsnap = NULL; doutc(cl, "%p %llx inode\n", realm, realm->ino); spin_lock(&realm->inodes_with_caps_lock); list_for_each_entry(ci, &realm->inodes_with_caps, i_snap_realm_item) { struct inode *inode = igrab(&ci->netfs.inode); if (!inode) continue; spin_unlock(&realm->inodes_with_caps_lock); iput(lastinode); lastinode = inode; /* * Allocate the capsnap memory outside of ceph_queue_cap_snap() * to reduce very possible but unnecessary frequently memory * allocate/free in this loop. */ if (!capsnap) { capsnap = kmem_cache_zalloc(ceph_cap_snap_cachep, GFP_NOFS); if (!capsnap) { pr_err_client(cl, "ENOMEM allocating ceph_cap_snap on %p\n", inode); return; } } capsnap->cap_flush.is_capsnap = true; refcount_set(&capsnap->nref, 1); INIT_LIST_HEAD(&capsnap->cap_flush.i_list); INIT_LIST_HEAD(&capsnap->cap_flush.g_list); INIT_LIST_HEAD(&capsnap->ci_item); ceph_queue_cap_snap(ci, &capsnap); spin_lock(&realm->inodes_with_caps_lock); } spin_unlock(&realm->inodes_with_caps_lock); iput(lastinode); if (capsnap) kmem_cache_free(ceph_cap_snap_cachep, capsnap); doutc(cl, "%p %llx done\n", realm, realm->ino); } /* * Parse and apply a snapblob "snap trace" from the MDS. This specifies * the snap realm parameters from a given realm and all of its ancestors, * up to the root. * * Caller must hold snap_rwsem for write. */ int ceph_update_snap_trace(struct ceph_mds_client *mdsc, void *p, void *e, bool deletion, struct ceph_snap_realm **realm_ret) { struct ceph_client *cl = mdsc->fsc->client; struct ceph_mds_snap_realm *ri; /* encoded */ __le64 *snaps; /* encoded */ __le64 *prior_parent_snaps; /* encoded */ struct ceph_snap_realm *realm; struct ceph_snap_realm *first_realm = NULL; struct ceph_snap_realm *realm_to_rebuild = NULL; struct ceph_client *client = mdsc->fsc->client; int rebuild_snapcs; int err = -ENOMEM; int ret; LIST_HEAD(dirty_realms); lockdep_assert_held_write(&mdsc->snap_rwsem); doutc(cl, "deletion=%d\n", deletion); more: realm = NULL; rebuild_snapcs = 0; ceph_decode_need(&p, e, sizeof(*ri), bad); ri = p; p += sizeof(*ri); ceph_decode_need(&p, e, sizeof(u64)*(le32_to_cpu(ri->num_snaps) + le32_to_cpu(ri->num_prior_parent_snaps)), bad); snaps = p; p += sizeof(u64) * le32_to_cpu(ri->num_snaps); prior_parent_snaps = p; p += sizeof(u64) * le32_to_cpu(ri->num_prior_parent_snaps); realm = ceph_lookup_snap_realm(mdsc, le64_to_cpu(ri->ino)); if (!realm) { realm = ceph_create_snap_realm(mdsc, le64_to_cpu(ri->ino)); if (IS_ERR(realm)) { err = PTR_ERR(realm); goto fail; } } /* ensure the parent is correct */ err = adjust_snap_realm_parent(mdsc, realm, le64_to_cpu(ri->parent)); if (err < 0) goto fail; rebuild_snapcs += err; if (le64_to_cpu(ri->seq) > realm->seq) { doutc(cl, "updating %llx %p %lld -> %lld\n", realm->ino, realm, realm->seq, le64_to_cpu(ri->seq)); /* update realm parameters, snap lists */ realm->seq = le64_to_cpu(ri->seq); realm->created = le64_to_cpu(ri->created); realm->parent_since = le64_to_cpu(ri->parent_since); realm->num_snaps = le32_to_cpu(ri->num_snaps); err = dup_array(&realm->snaps, snaps, realm->num_snaps); if (err < 0) goto fail; realm->num_prior_parent_snaps = le32_to_cpu(ri->num_prior_parent_snaps); err = dup_array(&realm->prior_parent_snaps, prior_parent_snaps, realm->num_prior_parent_snaps); if (err < 0) goto fail; if (realm->seq > mdsc->last_snap_seq) mdsc->last_snap_seq = realm->seq; rebuild_snapcs = 1; } else if (!realm->cached_context) { doutc(cl, "%llx %p seq %lld new\n", realm->ino, realm, realm->seq); rebuild_snapcs = 1; } else { doutc(cl, "%llx %p seq %lld unchanged\n", realm->ino, realm, realm->seq); } doutc(cl, "done with %llx %p, rebuild_snapcs=%d, %p %p\n", realm->ino, realm, rebuild_snapcs, p, e); /* * this will always track the uppest parent realm from which * we need to rebuild the snapshot contexts _downward_ in * hierarchy. */ if (rebuild_snapcs) realm_to_rebuild = realm; /* rebuild_snapcs when we reach the _end_ (root) of the trace */ if (realm_to_rebuild && p >= e) rebuild_snap_realms(mdsc, realm_to_rebuild, &dirty_realms); if (!first_realm) first_realm = realm; else ceph_put_snap_realm(mdsc, realm); if (p < e) goto more; /* * queue cap snaps _after_ we've built the new snap contexts, * so that i_head_snapc can be set appropriately. */ while (!list_empty(&dirty_realms)) { realm = list_first_entry(&dirty_realms, struct ceph_snap_realm, dirty_item); list_del_init(&realm->dirty_item); queue_realm_cap_snaps(mdsc, realm); } if (realm_ret) *realm_ret = first_realm; else ceph_put_snap_realm(mdsc, first_realm); __cleanup_empty_realms(mdsc); return 0; bad: err = -EIO; fail: if (realm && !IS_ERR(realm)) ceph_put_snap_realm(mdsc, realm); if (first_realm) ceph_put_snap_realm(mdsc, first_realm); pr_err_client(cl, "error %d\n", err); /* * When receiving a corrupted snap trace we don't know what * exactly has happened in MDS side. And we shouldn't continue * writing to OSD, which may corrupt the snapshot contents. * * Just try to blocklist this kclient and then this kclient * must be remounted to continue after the corrupted metadata * fixed in the MDS side. */ WRITE_ONCE(mdsc->fsc->mount_state, CEPH_MOUNT_FENCE_IO); ret = ceph_monc_blocklist_add(&client->monc, &client->msgr.inst.addr); if (ret) pr_err_client(cl, "failed to blocklist %s: %d\n", ceph_pr_addr(&client->msgr.inst.addr), ret); WARN(1, "[client.%lld] %s %s%sdo remount to continue%s", client->monc.auth->global_id, __func__, ret ? "" : ceph_pr_addr(&client->msgr.inst.addr), ret ? "" : " was blocklisted, ", err == -EIO ? " after corrupted snaptrace is fixed" : ""); return err; } /* * Send any cap_snaps that are queued for flush. Try to carry * s_mutex across multiple snap flushes to avoid locking overhead. * * Caller holds no locks. */ static void flush_snaps(struct ceph_mds_client *mdsc) { struct ceph_client *cl = mdsc->fsc->client; struct ceph_inode_info *ci; struct inode *inode; struct ceph_mds_session *session = NULL; doutc(cl, "begin\n"); spin_lock(&mdsc->snap_flush_lock); while (!list_empty(&mdsc->snap_flush_list)) { ci = list_first_entry(&mdsc->snap_flush_list, struct ceph_inode_info, i_snap_flush_item); inode = &ci->netfs.inode; ihold(inode); spin_unlock(&mdsc->snap_flush_lock); ceph_flush_snaps(ci, &session); iput(inode); spin_lock(&mdsc->snap_flush_lock); } spin_unlock(&mdsc->snap_flush_lock); ceph_put_mds_session(session); doutc(cl, "done\n"); } /** * ceph_change_snap_realm - change the snap_realm for an inode * @inode: inode to move to new snap realm * @realm: new realm to move inode into (may be NULL) * * Detach an inode from its old snaprealm (if any) and attach it to * the new snaprealm (if any). The old snap realm reference held by * the inode is put. If realm is non-NULL, then the caller's reference * to it is taken over by the inode. */ void ceph_change_snap_realm(struct inode *inode, struct ceph_snap_realm *realm) { struct ceph_inode_info *ci = ceph_inode(inode); struct ceph_mds_client *mdsc = ceph_inode_to_fs_client(inode)->mdsc; struct ceph_snap_realm *oldrealm = ci->i_snap_realm; lockdep_assert_held(&ci->i_ceph_lock); if (oldrealm) { spin_lock(&oldrealm->inodes_with_caps_lock); list_del_init(&ci->i_snap_realm_item); if (oldrealm->ino == ci->i_vino.ino) oldrealm->inode = NULL; spin_unlock(&oldrealm->inodes_with_caps_lock); ceph_put_snap_realm(mdsc, oldrealm); } ci->i_snap_realm = realm; if (realm) { spin_lock(&realm->inodes_with_caps_lock); list_add(&ci->i_snap_realm_item, &realm->inodes_with_caps); if (realm->ino == ci->i_vino.ino) realm->inode = inode; spin_unlock(&realm->inodes_with_caps_lock); } } /* * Handle a snap notification from the MDS. * * This can take two basic forms: the simplest is just a snap creation * or deletion notification on an existing realm. This should update the * realm and its children. * * The more difficult case is realm creation, due to snap creation at a * new point in the file hierarchy, or due to a rename that moves a file or * directory into another realm. */ void ceph_handle_snap(struct ceph_mds_client *mdsc, struct ceph_mds_session *session, struct ceph_msg *msg) { struct ceph_client *cl = mdsc->fsc->client; struct super_block *sb = mdsc->fsc->sb; int mds = session->s_mds; u64 split; int op; int trace_len; struct ceph_snap_realm *realm = NULL; void *p = msg->front.iov_base; void *e = p + msg->front.iov_len; struct ceph_mds_snap_head *h; int num_split_inos, num_split_realms; __le64 *split_inos = NULL, *split_realms = NULL; int i; int locked_rwsem = 0; bool close_sessions = false; if (!ceph_inc_mds_stopping_blocker(mdsc, session)) return; /* decode */ if (msg->front.iov_len < sizeof(*h)) goto bad; h = p; op = le32_to_cpu(h->op); split = le64_to_cpu(h->split); /* non-zero if we are splitting an * existing realm */ num_split_inos = le32_to_cpu(h->num_split_inos); num_split_realms = le32_to_cpu(h->num_split_realms); trace_len = le32_to_cpu(h->trace_len); p += sizeof(*h); doutc(cl, "from mds%d op %s split %llx tracelen %d\n", mds, ceph_snap_op_name(op), split, trace_len); down_write(&mdsc->snap_rwsem); locked_rwsem = 1; if (op == CEPH_SNAP_OP_SPLIT) { struct ceph_mds_snap_realm *ri; /* * A "split" breaks part of an existing realm off into * a new realm. The MDS provides a list of inodes * (with caps) and child realms that belong to the new * child. */ split_inos = p; p += sizeof(u64) * num_split_inos; split_realms = p; p += sizeof(u64) * num_split_realms; ceph_decode_need(&p, e, sizeof(*ri), bad); /* we will peek at realm info here, but will _not_ * advance p, as the realm update will occur below in * ceph_update_snap_trace. */ ri = p; realm = ceph_lookup_snap_realm(mdsc, split); if (!realm) { realm = ceph_create_snap_realm(mdsc, split); if (IS_ERR(realm)) goto out; } doutc(cl, "splitting snap_realm %llx %p\n", realm->ino, realm); for (i = 0; i < num_split_inos; i++) { struct ceph_vino vino = { .ino = le64_to_cpu(split_inos[i]), .snap = CEPH_NOSNAP, }; struct inode *inode = ceph_find_inode(sb, vino); struct ceph_inode_info *ci; if (!inode) continue; ci = ceph_inode(inode); spin_lock(&ci->i_ceph_lock); if (!ci->i_snap_realm) goto skip_inode; /* * If this inode belongs to a realm that was * created after our new realm, we experienced * a race (due to another split notifications * arriving from a different MDS). So skip * this inode. */ if (ci->i_snap_realm->created > le64_to_cpu(ri->created)) { doutc(cl, " leaving %p %llx.%llx in newer realm %llx %p\n", inode, ceph_vinop(inode), ci->i_snap_realm->ino, ci->i_snap_realm); goto skip_inode; } doutc(cl, " will move %p %llx.%llx to split realm %llx %p\n", inode, ceph_vinop(inode), realm->ino, realm); ceph_get_snap_realm(mdsc, realm); ceph_change_snap_realm(inode, realm); spin_unlock(&ci->i_ceph_lock); iput(inode); continue; skip_inode: spin_unlock(&ci->i_ceph_lock); iput(inode); } /* we may have taken some of the old realm's children. */ for (i = 0; i < num_split_realms; i++) { struct ceph_snap_realm *child = __lookup_snap_realm(mdsc, le64_to_cpu(split_realms[i])); if (!child) continue; adjust_snap_realm_parent(mdsc, child, realm->ino); } } else { /* * In the non-split case both 'num_split_inos' and * 'num_split_realms' should be 0, making this a no-op. * However the MDS happens to populate 'split_realms' list * in one of the UPDATE op cases by mistake. * * Skip both lists just in case to ensure that 'p' is * positioned at the start of realm info, as expected by * ceph_update_snap_trace(). */ p += sizeof(u64) * num_split_inos; p += sizeof(u64) * num_split_realms; } /* * update using the provided snap trace. if we are deleting a * snap, we can avoid queueing cap_snaps. */ if (ceph_update_snap_trace(mdsc, p, e, op == CEPH_SNAP_OP_DESTROY, NULL)) { close_sessions = true; goto bad; } if (op == CEPH_SNAP_OP_SPLIT) /* we took a reference when we created the realm, above */ ceph_put_snap_realm(mdsc, realm); __cleanup_empty_realms(mdsc); up_write(&mdsc->snap_rwsem); flush_snaps(mdsc); ceph_dec_mds_stopping_blocker(mdsc); return; bad: pr_err_client(cl, "corrupt snap message from mds%d\n", mds); ceph_msg_dump(msg); out: if (locked_rwsem) up_write(&mdsc->snap_rwsem); ceph_dec_mds_stopping_blocker(mdsc); if (close_sessions) ceph_mdsc_close_sessions(mdsc); return; } struct ceph_snapid_map* ceph_get_snapid_map(struct ceph_mds_client *mdsc, u64 snap) { struct ceph_client *cl = mdsc->fsc->client; struct ceph_snapid_map *sm, *exist; struct rb_node **p, *parent; int ret; exist = NULL; spin_lock(&mdsc->snapid_map_lock); p = &mdsc->snapid_map_tree.rb_node; while (*p) { exist = rb_entry(*p, struct ceph_snapid_map, node); if (snap > exist->snap) { p = &(*p)->rb_left; } else if (snap < exist->snap) { p = &(*p)->rb_right; } else { if (atomic_inc_return(&exist->ref) == 1) list_del_init(&exist->lru); break; } exist = NULL; } spin_unlock(&mdsc->snapid_map_lock); if (exist) { doutc(cl, "found snapid map %llx -> %x\n", exist->snap, exist->dev); return exist; } sm = kmalloc(sizeof(*sm), GFP_NOFS); if (!sm) return NULL; ret = get_anon_bdev(&sm->dev); if (ret < 0) { kfree(sm); return NULL; } INIT_LIST_HEAD(&sm->lru); atomic_set(&sm->ref, 1); sm->snap = snap; exist = NULL; parent = NULL; p = &mdsc->snapid_map_tree.rb_node; spin_lock(&mdsc->snapid_map_lock); while (*p) { parent = *p; exist = rb_entry(*p, struct ceph_snapid_map, node); if (snap > exist->snap) p = &(*p)->rb_left; else if (snap < exist->snap) p = &(*p)->rb_right; else break; exist = NULL; } if (exist) { if (atomic_inc_return(&exist->ref) == 1) list_del_init(&exist->lru); } else { rb_link_node(&sm->node, parent, p); rb_insert_color(&sm->node, &mdsc->snapid_map_tree); } spin_unlock(&mdsc->snapid_map_lock); if (exist) { free_anon_bdev(sm->dev); kfree(sm); doutc(cl, "found snapid map %llx -> %x\n", exist->snap, exist->dev); return exist; } doutc(cl, "create snapid map %llx -> %x\n", sm->snap, sm->dev); return sm; } void ceph_put_snapid_map(struct ceph_mds_client* mdsc, struct ceph_snapid_map *sm) { if (!sm) return; if (atomic_dec_and_lock(&sm->ref, &mdsc->snapid_map_lock)) { if (!RB_EMPTY_NODE(&sm->node)) { sm->last_used = jiffies; list_add_tail(&sm->lru, &mdsc->snapid_map_lru); spin_unlock(&mdsc->snapid_map_lock); } else { /* already cleaned up by * ceph_cleanup_snapid_map() */ spin_unlock(&mdsc->snapid_map_lock); kfree(sm); } } } void ceph_trim_snapid_map(struct ceph_mds_client *mdsc) { struct ceph_client *cl = mdsc->fsc->client; struct ceph_snapid_map *sm; unsigned long now; LIST_HEAD(to_free); spin_lock(&mdsc->snapid_map_lock); now = jiffies; while (!list_empty(&mdsc->snapid_map_lru)) { sm = list_first_entry(&mdsc->snapid_map_lru, struct ceph_snapid_map, lru); if (time_after(sm->last_used + CEPH_SNAPID_MAP_TIMEOUT, now)) break; rb_erase(&sm->node, &mdsc->snapid_map_tree); list_move(&sm->lru, &to_free); } spin_unlock(&mdsc->snapid_map_lock); while (!list_empty(&to_free)) { sm = list_first_entry(&to_free, struct ceph_snapid_map, lru); list_del(&sm->lru); doutc(cl, "trim snapid map %llx -> %x\n", sm->snap, sm->dev); free_anon_bdev(sm->dev); kfree(sm); } } void ceph_cleanup_snapid_map(struct ceph_mds_client *mdsc) { struct ceph_client *cl = mdsc->fsc->client; struct ceph_snapid_map *sm; struct rb_node *p; LIST_HEAD(to_free); spin_lock(&mdsc->snapid_map_lock); while ((p = rb_first(&mdsc->snapid_map_tree))) { sm = rb_entry(p, struct ceph_snapid_map, node); rb_erase(p, &mdsc->snapid_map_tree); RB_CLEAR_NODE(p); list_move(&sm->lru, &to_free); } spin_unlock(&mdsc->snapid_map_lock); while (!list_empty(&to_free)) { sm = list_first_entry(&to_free, struct ceph_snapid_map, lru); list_del(&sm->lru); free_anon_bdev(sm->dev); if (WARN_ON_ONCE(atomic_read(&sm->ref))) { pr_err_client(cl, "snapid map %llx -> %x still in use\n", sm->snap, sm->dev); } kfree(sm); } } |
| 3715 380 2586 1226 1327 221 1229 1226 1227 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 2008 IBM Corporation * * Authors: * Mimi Zohar <zohar@us.ibm.com> * * File: ima_iint.c * - implements the IMA hook: ima_inode_free * - cache integrity information in the inode security blob */ #include <linux/slab.h> #include "ima.h" static struct kmem_cache *ima_iint_cache __ro_after_init; /** * ima_iint_find - Return the iint associated with an inode * @inode: Pointer to the inode * * Return the IMA integrity information (iint) associated with an inode, if the * inode was processed by IMA. * * Return: Found iint or NULL. */ struct ima_iint_cache *ima_iint_find(struct inode *inode) { if (!IS_IMA(inode)) return NULL; return ima_inode_get_iint(inode); } #define IMA_MAX_NESTING (FILESYSTEM_MAX_STACK_DEPTH + 1) /* * It is not clear that IMA should be nested at all, but as long is it measures * files both on overlayfs and on underlying fs, we need to annotate the iint * mutex to avoid lockdep false positives related to IMA + overlayfs. * See ovl_lockdep_annotate_inode_mutex_key() for more details. */ static inline void ima_iint_lockdep_annotate(struct ima_iint_cache *iint, struct inode *inode) { #ifdef CONFIG_LOCKDEP static struct lock_class_key ima_iint_mutex_key[IMA_MAX_NESTING]; int depth = inode->i_sb->s_stack_depth; if (WARN_ON_ONCE(depth < 0 || depth >= IMA_MAX_NESTING)) depth = 0; lockdep_set_class(&iint->mutex, &ima_iint_mutex_key[depth]); #endif } static void ima_iint_init_always(struct ima_iint_cache *iint, struct inode *inode) { iint->ima_hash = NULL; iint->real_inode.version = 0; iint->flags = 0UL; iint->atomic_flags = 0UL; iint->ima_file_status = INTEGRITY_UNKNOWN; iint->ima_mmap_status = INTEGRITY_UNKNOWN; iint->ima_bprm_status = INTEGRITY_UNKNOWN; iint->ima_read_status = INTEGRITY_UNKNOWN; iint->ima_creds_status = INTEGRITY_UNKNOWN; iint->measured_pcrs = 0; mutex_init(&iint->mutex); ima_iint_lockdep_annotate(iint, inode); } static void ima_iint_free(struct ima_iint_cache *iint) { kfree(iint->ima_hash); mutex_destroy(&iint->mutex); kmem_cache_free(ima_iint_cache, iint); } /** * ima_inode_get - Find or allocate an iint associated with an inode * @inode: Pointer to the inode * * Find an iint associated with an inode, and allocate a new one if not found. * Caller must lock i_mutex. * * Return: An iint on success, NULL on error. */ struct ima_iint_cache *ima_inode_get(struct inode *inode) { struct ima_iint_cache *iint; iint = ima_iint_find(inode); if (iint) return iint; iint = kmem_cache_alloc(ima_iint_cache, GFP_NOFS); if (!iint) return NULL; ima_iint_init_always(iint, inode); inode->i_flags |= S_IMA; ima_inode_set_iint(inode, iint); return iint; } /** * ima_inode_free_rcu - Called to free an inode via a RCU callback * @inode_security: The inode->i_security pointer * * Free the IMA data associated with an inode. */ void ima_inode_free_rcu(void *inode_security) { struct ima_iint_cache **iint_p = inode_security + ima_blob_sizes.lbs_inode; /* *iint_p should be NULL if !IS_IMA(inode) */ if (*iint_p) ima_iint_free(*iint_p); } static void ima_iint_init_once(void *foo) { struct ima_iint_cache *iint = (struct ima_iint_cache *)foo; memset(iint, 0, sizeof(*iint)); } void __init ima_iintcache_init(void) { ima_iint_cache = kmem_cache_create("ima_iint_cache", sizeof(struct ima_iint_cache), 0, SLAB_PANIC, ima_iint_init_once); } |
| 1715 183 161 1 650 420 201 635 185 17 173 186 98 1715 183 1777 1719 1721 1458 1454 1458 1874 1738 1587 1573 184 183 183 182 126 162 57 161 161 181 115 75 1740 99 99 603 603 68 11 8 11 8 11 11 8 11 8 8 5 8 5 8 8 5 8 6 640 644 642 45 644 45 7 9 540 | 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Synchronous Cryptographic Hash operations. * * Copyright (c) 2008 Herbert Xu <herbert@gondor.apana.org.au> */ #include <crypto/scatterwalk.h> #include <linux/cryptouser.h> #include <linux/err.h> #include <linux/kernel.h> #include <linux/module.h> #include <linux/seq_file.h> #include <linux/string.h> #include <net/netlink.h> #include "hash.h" static inline bool crypto_shash_block_only(struct crypto_shash *tfm) { return crypto_shash_alg(tfm)->base.cra_flags & CRYPTO_AHASH_ALG_BLOCK_ONLY; } static inline bool crypto_shash_final_nonzero(struct crypto_shash *tfm) { return crypto_shash_alg(tfm)->base.cra_flags & CRYPTO_AHASH_ALG_FINAL_NONZERO; } static inline bool crypto_shash_finup_max(struct crypto_shash *tfm) { return crypto_shash_alg(tfm)->base.cra_flags & CRYPTO_AHASH_ALG_FINUP_MAX; } int shash_no_setkey(struct crypto_shash *tfm, const u8 *key, unsigned int keylen) { return -ENOSYS; } EXPORT_SYMBOL_GPL(shash_no_setkey); static void shash_set_needkey(struct crypto_shash *tfm, struct shash_alg *alg) { if (crypto_shash_alg_needs_key(alg)) crypto_shash_set_flags(tfm, CRYPTO_TFM_NEED_KEY); } int crypto_shash_setkey(struct crypto_shash *tfm, const u8 *key, unsigned int keylen) { struct shash_alg *shash = crypto_shash_alg(tfm); int err; err = shash->setkey(tfm, key, keylen); if (unlikely(err)) { shash_set_needkey(tfm, shash); return err; } crypto_shash_clear_flags(tfm, CRYPTO_TFM_NEED_KEY); return 0; } EXPORT_SYMBOL_GPL(crypto_shash_setkey); static int __crypto_shash_init(struct shash_desc *desc) { struct crypto_shash *tfm = desc->tfm; if (crypto_shash_block_only(tfm)) { u8 *buf = shash_desc_ctx(desc); buf += crypto_shash_descsize(tfm) - 1; *buf = 0; } return crypto_shash_alg(tfm)->init(desc); } int crypto_shash_init(struct shash_desc *desc) { if (crypto_shash_get_flags(desc->tfm) & CRYPTO_TFM_NEED_KEY) return -ENOKEY; return __crypto_shash_init(desc); } EXPORT_SYMBOL_GPL(crypto_shash_init); static int shash_default_finup(struct shash_desc *desc, const u8 *data, unsigned int len, u8 *out) { struct shash_alg *shash = crypto_shash_alg(desc->tfm); return shash->update(desc, data, len) ?: shash->final(desc, out); } static int crypto_shash_op_and_zero( int (*op)(struct shash_desc *desc, const u8 *data, unsigned int len, u8 *out), struct shash_desc *desc, const u8 *data, unsigned int len, u8 *out) { int err; err = op(desc, data, len, out); memset(shash_desc_ctx(desc), 0, crypto_shash_descsize(desc->tfm)); return err; } int crypto_shash_finup(struct shash_desc *restrict desc, const u8 *data, unsigned int len, u8 *restrict out) { struct crypto_shash *tfm = desc->tfm; u8 *blenp = shash_desc_ctx(desc); bool finup_max, nonzero; unsigned int bs; int err; u8 *buf; if (!crypto_shash_block_only(tfm)) { if (out) goto finup; return crypto_shash_alg(tfm)->update(desc, data, len); } finup_max = out && crypto_shash_finup_max(tfm); /* Retain extra block for final nonzero algorithms. */ nonzero = crypto_shash_final_nonzero(tfm); /* * The partial block buffer follows the algorithm desc context. * The byte following that contains the length. */ blenp += crypto_shash_descsize(tfm) - 1; bs = crypto_shash_blocksize(tfm); buf = blenp - bs; if (likely(!*blenp && finup_max)) goto finup; while ((*blenp + len) >= bs + nonzero) { unsigned int nbytes = len - nonzero; const u8 *src = data; if (*blenp) { memcpy(buf + *blenp, data, bs - *blenp); nbytes = bs; src = buf; } err = crypto_shash_alg(tfm)->update(desc, src, nbytes); if (err < 0) return err; data += nbytes - err - *blenp; len -= nbytes - err - *blenp; *blenp = 0; } if (*blenp || !out) { memcpy(buf + *blenp, data, len); *blenp += len; if (!out) return 0; data = buf; len = *blenp; } finup: return crypto_shash_op_and_zero(crypto_shash_alg(tfm)->finup, desc, data, len, out); } EXPORT_SYMBOL_GPL(crypto_shash_finup); static int shash_default_digest(struct shash_desc *desc, const u8 *data, unsigned int len, u8 *out) { return __crypto_shash_init(desc) ?: crypto_shash_finup(desc, data, len, out); } int crypto_shash_digest(struct shash_desc *desc, const u8 *data, unsigned int len, u8 *out) { struct crypto_shash *tfm = desc->tfm; if (crypto_shash_get_flags(tfm) & CRYPTO_TFM_NEED_KEY) return -ENOKEY; return crypto_shash_op_and_zero(crypto_shash_alg(tfm)->digest, desc, data, len, out); } EXPORT_SYMBOL_GPL(crypto_shash_digest); int crypto_shash_tfm_digest(struct crypto_shash *tfm, const u8 *data, unsigned int len, u8 *out) { SHASH_DESC_ON_STACK(desc, tfm); desc->tfm = tfm; return crypto_shash_digest(desc, data, len, out); } EXPORT_SYMBOL_GPL(crypto_shash_tfm_digest); static int __crypto_shash_export(struct shash_desc *desc, void *out, int (*export)(struct shash_desc *desc, void *out)) { struct crypto_shash *tfm = desc->tfm; u8 *buf = shash_desc_ctx(desc); unsigned int plen, ss; plen = crypto_shash_blocksize(tfm) + 1; ss = crypto_shash_statesize(tfm); if (crypto_shash_block_only(tfm)) ss -= plen; if (!export) { memcpy(out, buf, ss); return 0; } return export(desc, out); } int crypto_shash_export_core(struct shash_desc *desc, void *out) { return __crypto_shash_export(desc, out, crypto_shash_alg(desc->tfm)->export_core); } EXPORT_SYMBOL_GPL(crypto_shash_export_core); int crypto_shash_export(struct shash_desc *desc, void *out) { struct crypto_shash *tfm = desc->tfm; if (crypto_shash_block_only(tfm)) { unsigned int plen = crypto_shash_blocksize(tfm) + 1; unsigned int descsize = crypto_shash_descsize(tfm); unsigned int ss = crypto_shash_statesize(tfm); u8 *buf = shash_desc_ctx(desc); memcpy(out + ss - plen, buf + descsize - plen, plen); } return __crypto_shash_export(desc, out, crypto_shash_alg(tfm)->export); } EXPORT_SYMBOL_GPL(crypto_shash_export); static int __crypto_shash_import(struct shash_desc *desc, const void *in, int (*import)(struct shash_desc *desc, const void *in)) { struct crypto_shash *tfm = desc->tfm; unsigned int descsize, plen, ss; u8 *buf = shash_desc_ctx(desc); if (crypto_shash_get_flags(tfm) & CRYPTO_TFM_NEED_KEY) return -ENOKEY; ss = crypto_shash_statesize(tfm); if (crypto_shash_block_only(tfm)) { plen = crypto_shash_blocksize(tfm) + 1; ss -= plen; descsize = crypto_shash_descsize(tfm); buf[descsize - 1] = 0; } if (!import) { memcpy(buf, in, ss); return 0; } return import(desc, in); } int crypto_shash_import_core(struct shash_desc *desc, const void *in) { return __crypto_shash_import(desc, in, crypto_shash_alg(desc->tfm)->import_core); } EXPORT_SYMBOL_GPL(crypto_shash_import_core); int crypto_shash_import(struct shash_desc *desc, const void *in) { struct crypto_shash *tfm = desc->tfm; int err; err = __crypto_shash_import(desc, in, crypto_shash_alg(tfm)->import); if (crypto_shash_block_only(tfm)) { unsigned int plen = crypto_shash_blocksize(tfm) + 1; unsigned int descsize = crypto_shash_descsize(tfm); unsigned int ss = crypto_shash_statesize(tfm); u8 *buf = shash_desc_ctx(desc); memcpy(buf + descsize - plen, in + ss - plen, plen); if (buf[descsize - 1] >= plen) err = -EOVERFLOW; } return err; } EXPORT_SYMBOL_GPL(crypto_shash_import); static void crypto_shash_exit_tfm(struct crypto_tfm *tfm) { struct crypto_shash *hash = __crypto_shash_cast(tfm); struct shash_alg *alg = crypto_shash_alg(hash); alg->exit_tfm(hash); } static int crypto_shash_init_tfm(struct crypto_tfm *tfm) { struct crypto_shash *hash = __crypto_shash_cast(tfm); struct shash_alg *alg = crypto_shash_alg(hash); shash_set_needkey(hash, alg); if (alg->exit_tfm) tfm->exit = crypto_shash_exit_tfm; if (!alg->init_tfm) return 0; return alg->init_tfm(hash); } static void crypto_shash_free_instance(struct crypto_instance *inst) { struct shash_instance *shash = shash_instance(inst); shash->free(shash); } static int __maybe_unused crypto_shash_report( struct sk_buff *skb, struct crypto_alg *alg) { struct crypto_report_hash rhash; struct shash_alg *salg = __crypto_shash_alg(alg); memset(&rhash, 0, sizeof(rhash)); strscpy(rhash.type, "shash", sizeof(rhash.type)); rhash.blocksize = alg->cra_blocksize; rhash.digestsize = salg->digestsize; return nla_put(skb, CRYPTOCFGA_REPORT_HASH, sizeof(rhash), &rhash); } static void crypto_shash_show(struct seq_file *m, struct crypto_alg *alg) __maybe_unused; static void crypto_shash_show(struct seq_file *m, struct crypto_alg *alg) { struct shash_alg *salg = __crypto_shash_alg(alg); seq_printf(m, "type : shash\n"); seq_printf(m, "blocksize : %u\n", alg->cra_blocksize); seq_printf(m, "digestsize : %u\n", salg->digestsize); } const struct crypto_type crypto_shash_type = { .extsize = crypto_alg_extsize, .init_tfm = crypto_shash_init_tfm, .free = crypto_shash_free_instance, #ifdef CONFIG_PROC_FS .show = crypto_shash_show, #endif #if IS_ENABLED(CONFIG_CRYPTO_USER) .report = crypto_shash_report, #endif .maskclear = ~CRYPTO_ALG_TYPE_MASK, .maskset = CRYPTO_ALG_TYPE_MASK, .type = CRYPTO_ALG_TYPE_SHASH, .tfmsize = offsetof(struct crypto_shash, base), .algsize = offsetof(struct shash_alg, base), }; int crypto_grab_shash(struct crypto_shash_spawn *spawn, struct crypto_instance *inst, const char *name, u32 type, u32 mask) { spawn->base.frontend = &crypto_shash_type; return crypto_grab_spawn(&spawn->base, inst, name, type, mask); } EXPORT_SYMBOL_GPL(crypto_grab_shash); struct crypto_shash *crypto_alloc_shash(const char *alg_name, u32 type, u32 mask) { return crypto_alloc_tfm(alg_name, &crypto_shash_type, type, mask); } EXPORT_SYMBOL_GPL(crypto_alloc_shash); int crypto_has_shash(const char *alg_name, u32 type, u32 mask) { return crypto_type_has_alg(alg_name, &crypto_shash_type, type, mask); } EXPORT_SYMBOL_GPL(crypto_has_shash); struct crypto_shash *crypto_clone_shash(struct crypto_shash *hash) { struct crypto_tfm *tfm = crypto_shash_tfm(hash); struct shash_alg *alg = crypto_shash_alg(hash); struct crypto_shash *nhash; int err; if (!crypto_shash_alg_has_setkey(alg)) { tfm = crypto_tfm_get(tfm); if (IS_ERR(tfm)) return ERR_CAST(tfm); return hash; } if (!alg->clone_tfm && (alg->init_tfm || alg->base.cra_init)) return ERR_PTR(-ENOSYS); nhash = crypto_clone_tfm(&crypto_shash_type, tfm); if (IS_ERR(nhash)) return nhash; if (alg->clone_tfm) { err = alg->clone_tfm(nhash, hash); if (err) { crypto_free_shash(nhash); return ERR_PTR(err); } } if (alg->exit_tfm) crypto_shash_tfm(nhash)->exit = crypto_shash_exit_tfm; return nhash; } EXPORT_SYMBOL_GPL(crypto_clone_shash); int hash_prepare_alg(struct hash_alg_common *alg) { struct crypto_alg *base = &alg->base; if (alg->digestsize > HASH_MAX_DIGESTSIZE) return -EINVAL; /* alignmask is not useful for hashes, so it is not supported. */ if (base->cra_alignmask) return -EINVAL; base->cra_flags &= ~CRYPTO_ALG_TYPE_MASK; return 0; } static int shash_default_export_core(struct shash_desc *desc, void *out) { return -ENOSYS; } static int shash_default_import_core(struct shash_desc *desc, const void *in) { return -ENOSYS; } static int shash_prepare_alg(struct shash_alg *alg) { struct crypto_alg *base = &alg->halg.base; int err; if ((alg->export && !alg->import) || (alg->import && !alg->export)) return -EINVAL; err = hash_prepare_alg(&alg->halg); if (err) return err; base->cra_type = &crypto_shash_type; base->cra_flags |= CRYPTO_ALG_TYPE_SHASH; base->cra_flags |= CRYPTO_ALG_REQ_VIRT; /* * Handle missing optional functions. For each one we can either * install a default here, or we can leave the pointer as NULL and check * the pointer for NULL in crypto_shash_*(), avoiding an indirect call * when the default behavior is desired. For ->finup and ->digest we * install defaults, since for optimal performance algorithms should * implement these anyway. On the other hand, for ->import and * ->export the common case and best performance comes from the simple * memcpy of the shash_desc_ctx, so when those pointers are NULL we * leave them NULL and provide the memcpy with no indirect call. */ if (!alg->finup) alg->finup = shash_default_finup; if (!alg->digest) alg->digest = shash_default_digest; if (!alg->export && !alg->halg.statesize) alg->halg.statesize = alg->descsize; if (!alg->setkey) alg->setkey = shash_no_setkey; if (base->cra_flags & CRYPTO_AHASH_ALG_BLOCK_ONLY) { BUILD_BUG_ON(MAX_ALGAPI_BLOCKSIZE >= 256); alg->descsize += base->cra_blocksize + 1; alg->statesize += base->cra_blocksize + 1; alg->export_core = alg->export; alg->import_core = alg->import; } else if (!alg->export_core || !alg->import_core) { alg->export_core = shash_default_export_core; alg->import_core = shash_default_import_core; base->cra_flags |= CRYPTO_AHASH_ALG_NO_EXPORT_CORE; } if (alg->descsize > HASH_MAX_DESCSIZE) return -EINVAL; if (alg->statesize > HASH_MAX_STATESIZE) return -EINVAL; base->cra_reqsize = sizeof(struct shash_desc) + alg->descsize; return 0; } int crypto_register_shash(struct shash_alg *alg) { struct crypto_alg *base = &alg->base; int err; err = shash_prepare_alg(alg); if (err) return err; return crypto_register_alg(base); } EXPORT_SYMBOL_GPL(crypto_register_shash); void crypto_unregister_shash(struct shash_alg *alg) { crypto_unregister_alg(&alg->base); } EXPORT_SYMBOL_GPL(crypto_unregister_shash); int crypto_register_shashes(struct shash_alg *algs, int count) { int i, ret; for (i = 0; i < count; i++) { ret = crypto_register_shash(&algs[i]); if (ret) goto err; } return 0; err: for (--i; i >= 0; --i) crypto_unregister_shash(&algs[i]); return ret; } EXPORT_SYMBOL_GPL(crypto_register_shashes); void crypto_unregister_shashes(struct shash_alg *algs, int count) { int i; for (i = count - 1; i >= 0; --i) crypto_unregister_shash(&algs[i]); } EXPORT_SYMBOL_GPL(crypto_unregister_shashes); int shash_register_instance(struct crypto_template *tmpl, struct shash_instance *inst) { int err; if (WARN_ON(!inst->free)) return -EINVAL; err = shash_prepare_alg(&inst->alg); if (err) return err; return crypto_register_instance(tmpl, shash_crypto_instance(inst)); } EXPORT_SYMBOL_GPL(shash_register_instance); void shash_free_singlespawn_instance(struct shash_instance *inst) { crypto_drop_spawn(shash_instance_ctx(inst)); kfree(inst); } EXPORT_SYMBOL_GPL(shash_free_singlespawn_instance); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("Synchronous cryptographic hash type"); |
| 6 5 5 1 8 8 8 1 8 1 7 7 7 7 7 7 6 6 6 2 1 18 18 18 9 8 8 16 16 16 18 18 18 18 16 11 11 11 17 16 18 18 18 18 18 18 18 18 18 18 18 18 19 18 18 18 18 18 1 18 18 18 13 13 13 | 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 | /* * Copyright (c) 2010-2011 Atheros Communications Inc. * * Permission to use, copy, modify, and/or distribute this software for any * purpose with or without fee is hereby granted, provided that the above * copyright notice and this permission notice appear in all copies. * * THE SOFTWARE IS PROVIDED "AS IS" AND THE AUTHOR DISCLAIMS ALL WARRANTIES * WITH REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF * MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR * ANY SPECIAL, DIRECT, 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. */ #include <linux/unaligned.h> #include "htc.h" MODULE_FIRMWARE(HTC_7010_MODULE_FW); MODULE_FIRMWARE(HTC_9271_MODULE_FW); static const struct usb_device_id ath9k_hif_usb_ids[] = { { USB_DEVICE(0x0cf3, 0x9271) }, /* Atheros */ { USB_DEVICE(0x0cf3, 0x1006) }, /* Atheros */ { USB_DEVICE(0x0846, 0x9030) }, /* Netgear N150 */ { USB_DEVICE(0x07b8, 0x9271) }, /* Altai WA1011N-GU */ { USB_DEVICE(0x07D1, 0x3A10) }, /* Dlink Wireless 150 */ { USB_DEVICE(0x13D3, 0x3327) }, /* Azurewave */ { USB_DEVICE(0x13D3, 0x3328) }, /* Azurewave */ { USB_DEVICE(0x13D3, 0x3346) }, /* IMC Networks */ { USB_DEVICE(0x13D3, 0x3348) }, /* Azurewave */ { USB_DEVICE(0x13D3, 0x3349) }, /* Azurewave */ { USB_DEVICE(0x13D3, 0x3350) }, /* Azurewave */ { USB_DEVICE(0x04CA, 0x4605) }, /* Liteon */ { USB_DEVICE(0x040D, 0x3801) }, /* VIA */ { USB_DEVICE(0x0cf3, 0xb003) }, /* Ubiquiti WifiStation Ext */ { USB_DEVICE(0x0cf3, 0xb002) }, /* Ubiquiti WifiStation */ { USB_DEVICE(0x057c, 0x8403) }, /* AVM FRITZ!WLAN 11N v2 USB */ { USB_DEVICE(0x0471, 0x209e) }, /* Philips (or NXP) PTA01 */ { USB_DEVICE(0x1eda, 0x2315) }, /* AirTies */ { USB_DEVICE(0x0cf3, 0x7015), .driver_info = AR9287_USB }, /* Atheros */ { USB_DEVICE(0x0cf3, 0x7010), .driver_info = AR9280_USB }, /* Atheros */ { USB_DEVICE(0x0846, 0x9018), .driver_info = AR9280_USB }, /* Netgear WNDA3200 */ { USB_DEVICE(0x083A, 0xA704), .driver_info = AR9280_USB }, /* SMC Networks */ { USB_DEVICE(0x0411, 0x017f), .driver_info = AR9280_USB }, /* Sony UWA-BR100 */ { USB_DEVICE(0x0411, 0x0197), .driver_info = AR9280_USB }, /* Buffalo WLI-UV-AG300P */ { USB_DEVICE(0x04da, 0x3904), .driver_info = AR9280_USB }, { USB_DEVICE(0x0930, 0x0a08), .driver_info = AR9280_USB }, /* Toshiba WLM-20U2 and GN-1080 */ { USB_DEVICE(0x0cf3, 0x20ff), .driver_info = STORAGE_DEVICE }, { }, }; MODULE_DEVICE_TABLE(usb, ath9k_hif_usb_ids); static int __hif_usb_tx(struct hif_device_usb *hif_dev); static void hif_usb_regout_cb(struct urb *urb) { struct cmd_buf *cmd = urb->context; switch (urb->status) { case 0: break; case -ENOENT: case -ECONNRESET: case -ENODEV: case -ESHUTDOWN: goto free; default: break; } if (cmd) { ath9k_htc_txcompletion_cb(cmd->hif_dev->htc_handle, cmd->skb, true); kfree(cmd); } return; free: kfree_skb(cmd->skb); kfree(cmd); } static int hif_usb_send_regout(struct hif_device_usb *hif_dev, struct sk_buff *skb) { struct urb *urb; struct cmd_buf *cmd; int ret = 0; urb = usb_alloc_urb(0, GFP_KERNEL); if (urb == NULL) return -ENOMEM; cmd = kzalloc(sizeof(*cmd), GFP_KERNEL); if (cmd == NULL) { usb_free_urb(urb); return -ENOMEM; } cmd->skb = skb; cmd->hif_dev = hif_dev; usb_fill_int_urb(urb, hif_dev->udev, usb_sndintpipe(hif_dev->udev, USB_REG_OUT_PIPE), skb->data, skb->len, hif_usb_regout_cb, cmd, 1); usb_anchor_urb(urb, &hif_dev->regout_submitted); ret = usb_submit_urb(urb, GFP_KERNEL); if (ret) { usb_unanchor_urb(urb); kfree(cmd); } usb_free_urb(urb); return ret; } static void hif_usb_mgmt_cb(struct urb *urb) { struct cmd_buf *cmd = urb->context; struct hif_device_usb *hif_dev; unsigned long flags; bool txok = true; if (!cmd || !cmd->skb || !cmd->hif_dev) return; hif_dev = cmd->hif_dev; switch (urb->status) { case 0: break; case -ENOENT: case -ECONNRESET: case -ENODEV: case -ESHUTDOWN: txok = false; /* * If the URBs are being flushed, no need to complete * this packet. */ spin_lock_irqsave(&hif_dev->tx.tx_lock, flags); if (hif_dev->tx.flags & HIF_USB_TX_FLUSH) { spin_unlock_irqrestore(&hif_dev->tx.tx_lock, flags); dev_kfree_skb_any(cmd->skb); kfree(cmd); return; } spin_unlock_irqrestore(&hif_dev->tx.tx_lock, flags); break; default: txok = false; break; } skb_pull(cmd->skb, 4); ath9k_htc_txcompletion_cb(cmd->hif_dev->htc_handle, cmd->skb, txok); kfree(cmd); } static int hif_usb_send_mgmt(struct hif_device_usb *hif_dev, struct sk_buff *skb) { struct urb *urb; struct cmd_buf *cmd; int ret = 0; __le16 *hdr; urb = usb_alloc_urb(0, GFP_ATOMIC); if (urb == NULL) return -ENOMEM; cmd = kzalloc(sizeof(*cmd), GFP_ATOMIC); if (cmd == NULL) { usb_free_urb(urb); return -ENOMEM; } cmd->skb = skb; cmd->hif_dev = hif_dev; hdr = skb_push(skb, 4); *hdr++ = cpu_to_le16(skb->len - 4); *hdr++ = cpu_to_le16(ATH_USB_TX_STREAM_MODE_TAG); usb_fill_bulk_urb(urb, hif_dev->udev, usb_sndbulkpipe(hif_dev->udev, USB_WLAN_TX_PIPE), skb->data, skb->len, hif_usb_mgmt_cb, cmd); usb_anchor_urb(urb, &hif_dev->mgmt_submitted); ret = usb_submit_urb(urb, GFP_ATOMIC); if (ret) { usb_unanchor_urb(urb); kfree(cmd); } usb_free_urb(urb); return ret; } static inline void ath9k_skb_queue_purge(struct hif_device_usb *hif_dev, struct sk_buff_head *list) { struct sk_buff *skb; while ((skb = __skb_dequeue(list)) != NULL) { dev_kfree_skb_any(skb); } } static inline void ath9k_skb_queue_complete(struct hif_device_usb *hif_dev, struct sk_buff_head *queue, bool txok) { struct sk_buff *skb; while ((skb = __skb_dequeue(queue)) != NULL) { #ifdef CONFIG_ATH9K_HTC_DEBUGFS int ln = skb->len; #endif ath9k_htc_txcompletion_cb(hif_dev->htc_handle, skb, txok); if (txok) { TX_STAT_INC(hif_dev, skb_success); TX_STAT_ADD(hif_dev, skb_success_bytes, ln); } else TX_STAT_INC(hif_dev, skb_failed); } } static void hif_usb_tx_cb(struct urb *urb) { struct tx_buf *tx_buf = urb->context; struct hif_device_usb *hif_dev; bool txok = true; if (!tx_buf || !tx_buf->hif_dev) return; hif_dev = tx_buf->hif_dev; switch (urb->status) { case 0: break; case -ENOENT: case -ECONNRESET: case -ENODEV: case -ESHUTDOWN: txok = false; /* * If the URBs are being flushed, no need to add this * URB to the free list. */ spin_lock(&hif_dev->tx.tx_lock); if (hif_dev->tx.flags & HIF_USB_TX_FLUSH) { spin_unlock(&hif_dev->tx.tx_lock); ath9k_skb_queue_purge(hif_dev, &tx_buf->skb_queue); return; } spin_unlock(&hif_dev->tx.tx_lock); break; default: txok = false; break; } ath9k_skb_queue_complete(hif_dev, &tx_buf->skb_queue, txok); /* Re-initialize the SKB queue */ tx_buf->len = tx_buf->offset = 0; __skb_queue_head_init(&tx_buf->skb_queue); /* Add this TX buffer to the free list */ spin_lock(&hif_dev->tx.tx_lock); list_move_tail(&tx_buf->list, &hif_dev->tx.tx_buf); hif_dev->tx.tx_buf_cnt++; if (!(hif_dev->tx.flags & HIF_USB_TX_STOP)) __hif_usb_tx(hif_dev); /* Check for pending SKBs */ TX_STAT_INC(hif_dev, buf_completed); spin_unlock(&hif_dev->tx.tx_lock); } /* TX lock has to be taken */ static int __hif_usb_tx(struct hif_device_usb *hif_dev) { struct tx_buf *tx_buf = NULL; struct sk_buff *nskb = NULL; int ret = 0, i; u16 tx_skb_cnt = 0; u8 *buf; __le16 *hdr; if (hif_dev->tx.tx_skb_cnt == 0) return 0; /* Check if a free TX buffer is available */ if (list_empty(&hif_dev->tx.tx_buf)) return 0; tx_buf = list_first_entry(&hif_dev->tx.tx_buf, struct tx_buf, list); list_move_tail(&tx_buf->list, &hif_dev->tx.tx_pending); hif_dev->tx.tx_buf_cnt--; tx_skb_cnt = min_t(u16, hif_dev->tx.tx_skb_cnt, MAX_TX_AGGR_NUM); for (i = 0; i < tx_skb_cnt; i++) { nskb = __skb_dequeue(&hif_dev->tx.tx_skb_queue); /* Should never be NULL */ BUG_ON(!nskb); hif_dev->tx.tx_skb_cnt--; buf = tx_buf->buf; buf += tx_buf->offset; hdr = (__le16 *)buf; *hdr++ = cpu_to_le16(nskb->len); *hdr++ = cpu_to_le16(ATH_USB_TX_STREAM_MODE_TAG); buf += 4; memcpy(buf, nskb->data, nskb->len); tx_buf->len = nskb->len + 4; if (i < (tx_skb_cnt - 1)) tx_buf->offset += (((tx_buf->len - 1) / 4) + 1) * 4; if (i == (tx_skb_cnt - 1)) tx_buf->len += tx_buf->offset; __skb_queue_tail(&tx_buf->skb_queue, nskb); TX_STAT_INC(hif_dev, skb_queued); } usb_fill_bulk_urb(tx_buf->urb, hif_dev->udev, usb_sndbulkpipe(hif_dev->udev, USB_WLAN_TX_PIPE), tx_buf->buf, tx_buf->len, hif_usb_tx_cb, tx_buf); ret = usb_submit_urb(tx_buf->urb, GFP_ATOMIC); if (ret) { tx_buf->len = tx_buf->offset = 0; ath9k_skb_queue_complete(hif_dev, &tx_buf->skb_queue, false); __skb_queue_head_init(&tx_buf->skb_queue); list_move_tail(&tx_buf->list, &hif_dev->tx.tx_buf); hif_dev->tx.tx_buf_cnt++; } else { TX_STAT_INC(hif_dev, buf_queued); } return ret; } static int hif_usb_send_tx(struct hif_device_usb *hif_dev, struct sk_buff *skb) { struct ath9k_htc_tx_ctl *tx_ctl; unsigned long flags; int ret = 0; spin_lock_irqsave(&hif_dev->tx.tx_lock, flags); if (hif_dev->tx.flags & HIF_USB_TX_STOP) { spin_unlock_irqrestore(&hif_dev->tx.tx_lock, flags); return -ENODEV; } /* Check if the max queue count has been reached */ if (hif_dev->tx.tx_skb_cnt > MAX_TX_BUF_NUM) { spin_unlock_irqrestore(&hif_dev->tx.tx_lock, flags); return -ENOMEM; } spin_unlock_irqrestore(&hif_dev->tx.tx_lock, flags); tx_ctl = HTC_SKB_CB(skb); /* Mgmt/Beacon frames don't use the TX buffer pool */ if ((tx_ctl->type == ATH9K_HTC_MGMT) || (tx_ctl->type == ATH9K_HTC_BEACON)) { ret = hif_usb_send_mgmt(hif_dev, skb); } spin_lock_irqsave(&hif_dev->tx.tx_lock, flags); if ((tx_ctl->type == ATH9K_HTC_NORMAL) || (tx_ctl->type == ATH9K_HTC_AMPDU)) { __skb_queue_tail(&hif_dev->tx.tx_skb_queue, skb); hif_dev->tx.tx_skb_cnt++; } /* Check if AMPDUs have to be sent immediately */ if ((hif_dev->tx.tx_buf_cnt == MAX_TX_URB_NUM) && (hif_dev->tx.tx_skb_cnt < 2)) { __hif_usb_tx(hif_dev); } spin_unlock_irqrestore(&hif_dev->tx.tx_lock, flags); return ret; } static void hif_usb_start(void *hif_handle) { struct hif_device_usb *hif_dev = hif_handle; unsigned long flags; hif_dev->flags |= HIF_USB_START; spin_lock_irqsave(&hif_dev->tx.tx_lock, flags); hif_dev->tx.flags &= ~HIF_USB_TX_STOP; spin_unlock_irqrestore(&hif_dev->tx.tx_lock, flags); } static void hif_usb_stop(void *hif_handle) { struct hif_device_usb *hif_dev = hif_handle; struct tx_buf *tx_buf = NULL, *tx_buf_tmp = NULL; unsigned long flags; spin_lock_irqsave(&hif_dev->tx.tx_lock, flags); ath9k_skb_queue_complete(hif_dev, &hif_dev->tx.tx_skb_queue, false); hif_dev->tx.tx_skb_cnt = 0; hif_dev->tx.flags |= HIF_USB_TX_STOP; spin_unlock_irqrestore(&hif_dev->tx.tx_lock, flags); /* The pending URBs have to be canceled. */ spin_lock_irqsave(&hif_dev->tx.tx_lock, flags); list_for_each_entry_safe(tx_buf, tx_buf_tmp, &hif_dev->tx.tx_pending, list) { usb_get_urb(tx_buf->urb); spin_unlock_irqrestore(&hif_dev->tx.tx_lock, flags); usb_kill_urb(tx_buf->urb); list_del(&tx_buf->list); usb_free_urb(tx_buf->urb); kfree(tx_buf->buf); kfree(tx_buf); spin_lock_irqsave(&hif_dev->tx.tx_lock, flags); } spin_unlock_irqrestore(&hif_dev->tx.tx_lock, flags); usb_kill_anchored_urbs(&hif_dev->mgmt_submitted); } static int hif_usb_send(void *hif_handle, u8 pipe_id, struct sk_buff *skb) { struct hif_device_usb *hif_dev = hif_handle; int ret = 0; switch (pipe_id) { case USB_WLAN_TX_PIPE: ret = hif_usb_send_tx(hif_dev, skb); break; case USB_REG_OUT_PIPE: ret = hif_usb_send_regout(hif_dev, skb); break; default: dev_err(&hif_dev->udev->dev, "ath9k_htc: Invalid TX pipe: %d\n", pipe_id); ret = -EINVAL; break; } return ret; } static inline bool check_index(struct sk_buff *skb, u8 idx) { struct ath9k_htc_tx_ctl *tx_ctl; tx_ctl = HTC_SKB_CB(skb); if ((tx_ctl->type == ATH9K_HTC_AMPDU) && (tx_ctl->sta_idx == idx)) return true; return false; } static void hif_usb_sta_drain(void *hif_handle, u8 idx) { struct hif_device_usb *hif_dev = hif_handle; struct sk_buff *skb, *tmp; unsigned long flags; spin_lock_irqsave(&hif_dev->tx.tx_lock, flags); skb_queue_walk_safe(&hif_dev->tx.tx_skb_queue, skb, tmp) { if (check_index(skb, idx)) { __skb_unlink(skb, &hif_dev->tx.tx_skb_queue); ath9k_htc_txcompletion_cb(hif_dev->htc_handle, skb, false); hif_dev->tx.tx_skb_cnt--; TX_STAT_INC(hif_dev, skb_failed); } } spin_unlock_irqrestore(&hif_dev->tx.tx_lock, flags); } static struct ath9k_htc_hif hif_usb = { .transport = ATH9K_HIF_USB, .name = "ath9k_hif_usb", .control_ul_pipe = USB_REG_OUT_PIPE, .control_dl_pipe = USB_REG_IN_PIPE, .start = hif_usb_start, .stop = hif_usb_stop, .sta_drain = hif_usb_sta_drain, .send = hif_usb_send, }; /* Need to free remain_skb allocated in ath9k_hif_usb_rx_stream * in case ath9k_hif_usb_rx_stream wasn't called next time to * process the buffer and subsequently free it. */ static void ath9k_hif_usb_free_rx_remain_skb(struct hif_device_usb *hif_dev) { unsigned long flags; spin_lock_irqsave(&hif_dev->rx_lock, flags); if (hif_dev->remain_skb) { dev_kfree_skb_any(hif_dev->remain_skb); hif_dev->remain_skb = NULL; hif_dev->rx_remain_len = 0; RX_STAT_INC(hif_dev, skb_dropped); } spin_unlock_irqrestore(&hif_dev->rx_lock, flags); } static void ath9k_hif_usb_rx_stream(struct hif_device_usb *hif_dev, struct sk_buff *skb) { struct sk_buff *nskb, *skb_pool[MAX_PKT_NUM_IN_TRANSFER]; int index = 0, i, len = skb->len; int rx_remain_len, rx_pkt_len; u16 pool_index = 0; u8 *ptr; spin_lock(&hif_dev->rx_lock); rx_remain_len = hif_dev->rx_remain_len; rx_pkt_len = hif_dev->rx_transfer_len; if (rx_remain_len != 0) { struct sk_buff *remain_skb = hif_dev->remain_skb; if (remain_skb) { ptr = (u8 *) remain_skb->data; index = rx_remain_len; rx_remain_len -= hif_dev->rx_pad_len; ptr += rx_pkt_len; memcpy(ptr, skb->data, rx_remain_len); rx_pkt_len += rx_remain_len; skb_put(remain_skb, rx_pkt_len); skb_pool[pool_index++] = remain_skb; hif_dev->remain_skb = NULL; hif_dev->rx_remain_len = 0; } else { index = rx_remain_len; } } spin_unlock(&hif_dev->rx_lock); while (index < len) { u16 pkt_len; u16 pkt_tag; u16 pad_len; int chk_idx; ptr = (u8 *) skb->data; pkt_len = get_unaligned_le16(ptr + index); pkt_tag = get_unaligned_le16(ptr + index + 2); /* It is supposed that if we have an invalid pkt_tag or * pkt_len then the whole input SKB is considered invalid * and dropped; the associated packets already in skb_pool * are dropped, too. */ if (pkt_tag != ATH_USB_RX_STREAM_MODE_TAG) { RX_STAT_INC(hif_dev, skb_dropped); goto invalid_pkt; } if (pkt_len > 2 * MAX_RX_BUF_SIZE) { dev_err(&hif_dev->udev->dev, "ath9k_htc: invalid pkt_len (%x)\n", pkt_len); RX_STAT_INC(hif_dev, skb_dropped); goto invalid_pkt; } pad_len = 4 - (pkt_len & 0x3); if (pad_len == 4) pad_len = 0; chk_idx = index; index = index + 4 + pkt_len + pad_len; if (index > MAX_RX_BUF_SIZE) { spin_lock(&hif_dev->rx_lock); nskb = __dev_alloc_skb(pkt_len + 32, GFP_ATOMIC); if (!nskb) { dev_err(&hif_dev->udev->dev, "ath9k_htc: RX memory allocation error\n"); spin_unlock(&hif_dev->rx_lock); goto err; } hif_dev->rx_remain_len = index - MAX_RX_BUF_SIZE; hif_dev->rx_transfer_len = MAX_RX_BUF_SIZE - chk_idx - 4; hif_dev->rx_pad_len = pad_len; skb_reserve(nskb, 32); RX_STAT_INC(hif_dev, skb_allocated); memcpy(nskb->data, &(skb->data[chk_idx+4]), hif_dev->rx_transfer_len); /* Record the buffer pointer */ hif_dev->remain_skb = nskb; spin_unlock(&hif_dev->rx_lock); } else { if (pool_index == MAX_PKT_NUM_IN_TRANSFER) { dev_err(&hif_dev->udev->dev, "ath9k_htc: over RX MAX_PKT_NUM\n"); goto err; } nskb = __dev_alloc_skb(pkt_len + 32, GFP_ATOMIC); if (!nskb) { dev_err(&hif_dev->udev->dev, "ath9k_htc: RX memory allocation error\n"); goto err; } skb_reserve(nskb, 32); RX_STAT_INC(hif_dev, skb_allocated); memcpy(nskb->data, &(skb->data[chk_idx+4]), pkt_len); skb_put(nskb, pkt_len); skb_pool[pool_index++] = nskb; } } err: for (i = 0; i < pool_index; i++) { RX_STAT_ADD(hif_dev, skb_completed_bytes, skb_pool[i]->len); ath9k_htc_rx_msg(hif_dev->htc_handle, skb_pool[i], skb_pool[i]->len, USB_WLAN_RX_PIPE); RX_STAT_INC(hif_dev, skb_completed); } return; invalid_pkt: for (i = 0; i < pool_index; i++) { dev_kfree_skb_any(skb_pool[i]); RX_STAT_INC(hif_dev, skb_dropped); } return; } static void ath9k_hif_usb_rx_cb(struct urb *urb) { struct rx_buf *rx_buf = urb->context; struct hif_device_usb *hif_dev = rx_buf->hif_dev; struct sk_buff *skb = rx_buf->skb; int ret; if (!skb) return; if (!hif_dev) goto free; switch (urb->status) { case 0: break; case -ENOENT: case -ECONNRESET: case -ENODEV: case -ESHUTDOWN: goto free; default: goto resubmit; } if (likely(urb->actual_length != 0)) { skb_put(skb, urb->actual_length); ath9k_hif_usb_rx_stream(hif_dev, skb); } resubmit: __skb_set_length(skb, 0); usb_anchor_urb(urb, &hif_dev->rx_submitted); ret = usb_submit_urb(urb, GFP_ATOMIC); if (ret) { usb_unanchor_urb(urb); goto free; } return; free: kfree_skb(skb); kfree(rx_buf); } static void ath9k_hif_usb_reg_in_cb(struct urb *urb) { struct rx_buf *rx_buf = urb->context; struct hif_device_usb *hif_dev = rx_buf->hif_dev; struct sk_buff *skb = rx_buf->skb; int ret; if (!skb) return; if (!hif_dev) goto free_skb; switch (urb->status) { case 0: break; case -ENOENT: case -ECONNRESET: case -ENODEV: case -ESHUTDOWN: goto free_skb; default: __skb_set_length(skb, 0); goto resubmit; } if (likely(urb->actual_length != 0)) { skb_put(skb, urb->actual_length); /* * Process the command first. * skb is either freed here or passed to be * managed to another callback function. */ ath9k_htc_rx_msg(hif_dev->htc_handle, skb, skb->len, USB_REG_IN_PIPE); skb = alloc_skb(MAX_REG_IN_BUF_SIZE, GFP_ATOMIC); if (!skb) { dev_err(&hif_dev->udev->dev, "ath9k_htc: REG_IN memory allocation failure\n"); goto free_rx_buf; } rx_buf->skb = skb; usb_fill_int_urb(urb, hif_dev->udev, usb_rcvintpipe(hif_dev->udev, USB_REG_IN_PIPE), skb->data, MAX_REG_IN_BUF_SIZE, ath9k_hif_usb_reg_in_cb, rx_buf, 1); } resubmit: usb_anchor_urb(urb, &hif_dev->reg_in_submitted); ret = usb_submit_urb(urb, GFP_ATOMIC); if (ret) { usb_unanchor_urb(urb); goto free_skb; } return; free_skb: kfree_skb(skb); free_rx_buf: kfree(rx_buf); urb->context = NULL; } static void ath9k_hif_usb_dealloc_tx_urbs(struct hif_device_usb *hif_dev) { struct tx_buf *tx_buf = NULL, *tx_buf_tmp = NULL; unsigned long flags; spin_lock_irqsave(&hif_dev->tx.tx_lock, flags); list_for_each_entry_safe(tx_buf, tx_buf_tmp, &hif_dev->tx.tx_buf, list) { list_del(&tx_buf->list); usb_free_urb(tx_buf->urb); kfree(tx_buf->buf); kfree(tx_buf); } spin_unlock_irqrestore(&hif_dev->tx.tx_lock, flags); spin_lock_irqsave(&hif_dev->tx.tx_lock, flags); hif_dev->tx.flags |= HIF_USB_TX_FLUSH; spin_unlock_irqrestore(&hif_dev->tx.tx_lock, flags); spin_lock_irqsave(&hif_dev->tx.tx_lock, flags); list_for_each_entry_safe(tx_buf, tx_buf_tmp, &hif_dev->tx.tx_pending, list) { usb_get_urb(tx_buf->urb); spin_unlock_irqrestore(&hif_dev->tx.tx_lock, flags); usb_kill_urb(tx_buf->urb); list_del(&tx_buf->list); usb_free_urb(tx_buf->urb); kfree(tx_buf->buf); kfree(tx_buf); spin_lock_irqsave(&hif_dev->tx.tx_lock, flags); } spin_unlock_irqrestore(&hif_dev->tx.tx_lock, flags); usb_kill_anchored_urbs(&hif_dev->mgmt_submitted); } static int ath9k_hif_usb_alloc_tx_urbs(struct hif_device_usb *hif_dev) { struct tx_buf *tx_buf; int i; INIT_LIST_HEAD(&hif_dev->tx.tx_buf); INIT_LIST_HEAD(&hif_dev->tx.tx_pending); spin_lock_init(&hif_dev->tx.tx_lock); __skb_queue_head_init(&hif_dev->tx.tx_skb_queue); init_usb_anchor(&hif_dev->mgmt_submitted); for (i = 0; i < MAX_TX_URB_NUM; i++) { tx_buf = kzalloc(sizeof(*tx_buf), GFP_KERNEL); if (!tx_buf) goto err; tx_buf->buf = kzalloc(MAX_TX_BUF_SIZE, GFP_KERNEL); if (!tx_buf->buf) goto err; tx_buf->urb = usb_alloc_urb(0, GFP_KERNEL); if (!tx_buf->urb) goto err; tx_buf->hif_dev = hif_dev; __skb_queue_head_init(&tx_buf->skb_queue); list_add_tail(&tx_buf->list, &hif_dev->tx.tx_buf); } hif_dev->tx.tx_buf_cnt = MAX_TX_URB_NUM; return 0; err: if (tx_buf) { kfree(tx_buf->buf); kfree(tx_buf); } ath9k_hif_usb_dealloc_tx_urbs(hif_dev); return -ENOMEM; } static void ath9k_hif_usb_dealloc_rx_urbs(struct hif_device_usb *hif_dev) { usb_kill_anchored_urbs(&hif_dev->rx_submitted); ath9k_hif_usb_free_rx_remain_skb(hif_dev); } static int ath9k_hif_usb_alloc_rx_urbs(struct hif_device_usb *hif_dev) { struct rx_buf *rx_buf = NULL; struct sk_buff *skb = NULL; struct urb *urb = NULL; int i, ret; init_usb_anchor(&hif_dev->rx_submitted); spin_lock_init(&hif_dev->rx_lock); for (i = 0; i < MAX_RX_URB_NUM; i++) { rx_buf = kzalloc(sizeof(*rx_buf), GFP_KERNEL); if (!rx_buf) { ret = -ENOMEM; goto err_rxb; } /* Allocate URB */ urb = usb_alloc_urb(0, GFP_KERNEL); if (urb == NULL) { ret = -ENOMEM; goto err_urb; } /* Allocate buffer */ skb = alloc_skb(MAX_RX_BUF_SIZE, GFP_KERNEL); if (!skb) { ret = -ENOMEM; goto err_skb; } rx_buf->hif_dev = hif_dev; rx_buf->skb = skb; usb_fill_bulk_urb(urb, hif_dev->udev, usb_rcvbulkpipe(hif_dev->udev, USB_WLAN_RX_PIPE), skb->data, MAX_RX_BUF_SIZE, ath9k_hif_usb_rx_cb, rx_buf); /* Anchor URB */ usb_anchor_urb(urb, &hif_dev->rx_submitted); /* Submit URB */ ret = usb_submit_urb(urb, GFP_KERNEL); if (ret) { usb_unanchor_urb(urb); goto err_submit; } /* * Drop reference count. * This ensures that the URB is freed when killing them. */ usb_free_urb(urb); } return 0; err_submit: kfree_skb(skb); err_skb: usb_free_urb(urb); err_urb: kfree(rx_buf); err_rxb: ath9k_hif_usb_dealloc_rx_urbs(hif_dev); return ret; } static void ath9k_hif_usb_dealloc_reg_in_urbs(struct hif_device_usb *hif_dev) { usb_kill_anchored_urbs(&hif_dev->reg_in_submitted); } static int ath9k_hif_usb_alloc_reg_in_urbs(struct hif_device_usb *hif_dev) { struct rx_buf *rx_buf = NULL; struct sk_buff *skb = NULL; struct urb *urb = NULL; int i, ret; init_usb_anchor(&hif_dev->reg_in_submitted); for (i = 0; i < MAX_REG_IN_URB_NUM; i++) { rx_buf = kzalloc(sizeof(*rx_buf), GFP_KERNEL); if (!rx_buf) { ret = -ENOMEM; goto err_rxb; } /* Allocate URB */ urb = usb_alloc_urb(0, GFP_KERNEL); if (urb == NULL) { ret = -ENOMEM; goto err_urb; } /* Allocate buffer */ skb = alloc_skb(MAX_REG_IN_BUF_SIZE, GFP_KERNEL); if (!skb) { ret = -ENOMEM; goto err_skb; } rx_buf->hif_dev = hif_dev; rx_buf->skb = skb; usb_fill_int_urb(urb, hif_dev->udev, usb_rcvintpipe(hif_dev->udev, USB_REG_IN_PIPE), skb->data, MAX_REG_IN_BUF_SIZE, ath9k_hif_usb_reg_in_cb, rx_buf, 1); /* Anchor URB */ usb_anchor_urb(urb, &hif_dev->reg_in_submitted); /* Submit URB */ ret = usb_submit_urb(urb, GFP_KERNEL); if (ret) { usb_unanchor_urb(urb); goto err_submit; } /* * Drop reference count. * This ensures that the URB is freed when killing them. */ usb_free_urb(urb); } return 0; err_submit: kfree_skb(skb); err_skb: usb_free_urb(urb); err_urb: kfree(rx_buf); err_rxb: ath9k_hif_usb_dealloc_reg_in_urbs(hif_dev); return ret; } static int ath9k_hif_usb_alloc_urbs(struct hif_device_usb *hif_dev) { /* Register Write */ init_usb_anchor(&hif_dev->regout_submitted); /* TX */ if (ath9k_hif_usb_alloc_tx_urbs(hif_dev) < 0) goto err; /* RX */ if (ath9k_hif_usb_alloc_rx_urbs(hif_dev) < 0) goto err_rx; /* Register Read */ if (ath9k_hif_usb_alloc_reg_in_urbs(hif_dev) < 0) goto err_reg; return 0; err_reg: ath9k_hif_usb_dealloc_rx_urbs(hif_dev); err_rx: ath9k_hif_usb_dealloc_tx_urbs(hif_dev); err: return -ENOMEM; } void ath9k_hif_usb_dealloc_urbs(struct hif_device_usb *hif_dev) { usb_kill_anchored_urbs(&hif_dev->regout_submitted); ath9k_hif_usb_dealloc_reg_in_urbs(hif_dev); ath9k_hif_usb_dealloc_tx_urbs(hif_dev); ath9k_hif_usb_dealloc_rx_urbs(hif_dev); } static int ath9k_hif_usb_download_fw(struct hif_device_usb *hif_dev) { int transfer, err; const void *data = hif_dev->fw_data; size_t len = hif_dev->fw_size; u32 addr = AR9271_FIRMWARE; u8 *buf = kzalloc(4096, GFP_KERNEL); u32 firm_offset; if (!buf) return -ENOMEM; while (len) { transfer = min_t(size_t, len, 4096); memcpy(buf, data, transfer); err = usb_control_msg(hif_dev->udev, usb_sndctrlpipe(hif_dev->udev, 0), FIRMWARE_DOWNLOAD, 0x40 | USB_DIR_OUT, addr >> 8, 0, buf, transfer, USB_MSG_TIMEOUT); if (err < 0) { kfree(buf); return err; } len -= transfer; data += transfer; addr += transfer; } kfree(buf); if (IS_AR7010_DEVICE(hif_dev->usb_device_id->driver_info)) firm_offset = AR7010_FIRMWARE_TEXT; else firm_offset = AR9271_FIRMWARE_TEXT; /* * Issue FW download complete command to firmware. */ err = usb_control_msg(hif_dev->udev, usb_sndctrlpipe(hif_dev->udev, 0), FIRMWARE_DOWNLOAD_COMP, 0x40 | USB_DIR_OUT, firm_offset >> 8, 0, NULL, 0, USB_MSG_TIMEOUT); if (err) return -EIO; dev_info(&hif_dev->udev->dev, "ath9k_htc: Transferred FW: %s, size: %ld\n", hif_dev->fw_name, (unsigned long) hif_dev->fw_size); return 0; } static int ath9k_hif_usb_dev_init(struct hif_device_usb *hif_dev) { int ret; ret = ath9k_hif_usb_download_fw(hif_dev); if (ret) { dev_err(&hif_dev->udev->dev, "ath9k_htc: Firmware - %s download failed\n", hif_dev->fw_name); return ret; } /* Alloc URBs */ ret = ath9k_hif_usb_alloc_urbs(hif_dev); if (ret) { dev_err(&hif_dev->udev->dev, "ath9k_htc: Unable to allocate URBs\n"); return ret; } return 0; } static void ath9k_hif_usb_dev_deinit(struct hif_device_usb *hif_dev) { ath9k_hif_usb_dealloc_urbs(hif_dev); } /* * If initialization fails or the FW cannot be retrieved, * detach the device. */ static void ath9k_hif_usb_firmware_fail(struct hif_device_usb *hif_dev) { struct device *dev = &hif_dev->udev->dev; struct device *parent = dev->parent; complete_all(&hif_dev->fw_done); if (parent) device_lock(parent); device_release_driver(dev); if (parent) device_unlock(parent); } static void ath9k_hif_usb_firmware_cb(const struct firmware *fw, void *context); /* taken from iwlwifi */ static int ath9k_hif_request_firmware(struct hif_device_usb *hif_dev, bool first) { char index[8], *chip; int ret; if (first) { if (htc_use_dev_fw) { hif_dev->fw_minor_index = FIRMWARE_MINOR_IDX_MAX + 1; sprintf(index, "%s", "dev"); } else { hif_dev->fw_minor_index = FIRMWARE_MINOR_IDX_MAX; sprintf(index, "%d", hif_dev->fw_minor_index); } } else { hif_dev->fw_minor_index--; sprintf(index, "%d", hif_dev->fw_minor_index); } /* test for FW 1.3 */ if (MAJOR_VERSION_REQ == 1 && hif_dev->fw_minor_index == 3) { const char *filename; if (IS_AR7010_DEVICE(hif_dev->usb_device_id->driver_info)) filename = FIRMWARE_AR7010_1_1; else filename = FIRMWARE_AR9271; /* expected fw locations: * - htc_9271.fw (stable version 1.3, deprecated) */ snprintf(hif_dev->fw_name, sizeof(hif_dev->fw_name), "%s", filename); } else if (hif_dev->fw_minor_index < FIRMWARE_MINOR_IDX_MIN) { dev_err(&hif_dev->udev->dev, "no suitable firmware found!\n"); return -ENOENT; } else { if (IS_AR7010_DEVICE(hif_dev->usb_device_id->driver_info)) chip = "7010"; else chip = "9271"; /* expected fw locations: * - ath9k_htc/htc_9271-1.dev.0.fw (development version) * - ath9k_htc/htc_9271-1.4.0.fw (stable version) */ snprintf(hif_dev->fw_name, sizeof(hif_dev->fw_name), "%s/htc_%s-%d.%s.0.fw", HTC_FW_PATH, chip, MAJOR_VERSION_REQ, index); } ret = request_firmware_nowait(THIS_MODULE, true, hif_dev->fw_name, &hif_dev->udev->dev, GFP_KERNEL, hif_dev, ath9k_hif_usb_firmware_cb); if (ret) { dev_err(&hif_dev->udev->dev, "ath9k_htc: Async request for firmware %s failed\n", hif_dev->fw_name); return ret; } dev_info(&hif_dev->udev->dev, "ath9k_htc: Firmware %s requested\n", hif_dev->fw_name); return ret; } static void ath9k_hif_usb_firmware_cb(const struct firmware *fw, void *context) { struct hif_device_usb *hif_dev = context; int ret; if (!fw) { ret = ath9k_hif_request_firmware(hif_dev, false); if (!ret) return; dev_err(&hif_dev->udev->dev, "ath9k_htc: Failed to get firmware %s\n", hif_dev->fw_name); goto err_fw; } hif_dev->htc_handle = ath9k_htc_hw_alloc(hif_dev, &hif_usb, &hif_dev->udev->dev); if (hif_dev->htc_handle == NULL) goto err_dev_alloc; hif_dev->fw_data = fw->data; hif_dev->fw_size = fw->size; /* Proceed with initialization */ ret = ath9k_hif_usb_dev_init(hif_dev); if (ret) goto err_dev_init; ret = ath9k_htc_hw_init(hif_dev->htc_handle, &hif_dev->interface->dev, hif_dev->usb_device_id->idProduct, hif_dev->udev->product, hif_dev->usb_device_id->driver_info); if (ret) { ret = -EINVAL; goto err_htc_hw_init; } release_firmware(fw); hif_dev->flags |= HIF_USB_READY; complete_all(&hif_dev->fw_done); return; err_htc_hw_init: ath9k_hif_usb_dev_deinit(hif_dev); err_dev_init: ath9k_htc_hw_free(hif_dev->htc_handle); err_dev_alloc: release_firmware(fw); err_fw: ath9k_hif_usb_firmware_fail(hif_dev); } /* * An exact copy of the function from zd1211rw. */ static int send_eject_command(struct usb_interface *interface) { struct usb_device *udev = interface_to_usbdev(interface); struct usb_host_interface *iface_desc = interface->cur_altsetting; struct usb_endpoint_descriptor *endpoint; unsigned char *cmd; u8 bulk_out_ep; int r; if (iface_desc->desc.bNumEndpoints < 2) return -ENODEV; /* Find bulk out endpoint */ for (r = 1; r >= 0; r--) { endpoint = &iface_desc->endpoint[r].desc; if (usb_endpoint_dir_out(endpoint) && usb_endpoint_xfer_bulk(endpoint)) { bulk_out_ep = endpoint->bEndpointAddress; break; } } if (r == -1) { dev_err(&udev->dev, "ath9k_htc: Could not find bulk out endpoint\n"); return -ENODEV; } cmd = kzalloc(31, GFP_KERNEL); if (cmd == NULL) return -ENODEV; /* USB bulk command block */ cmd[0] = 0x55; /* bulk command signature */ cmd[1] = 0x53; /* bulk command signature */ cmd[2] = 0x42; /* bulk command signature */ cmd[3] = 0x43; /* bulk command signature */ cmd[14] = 6; /* command length */ cmd[15] = 0x1b; /* SCSI command: START STOP UNIT */ cmd[19] = 0x2; /* eject disc */ dev_info(&udev->dev, "Ejecting storage device...\n"); r = usb_bulk_msg(udev, usb_sndbulkpipe(udev, bulk_out_ep), cmd, 31, NULL, 2 * USB_MSG_TIMEOUT); kfree(cmd); if (r) return r; /* At this point, the device disconnects and reconnects with the real * ID numbers. */ usb_set_intfdata(interface, NULL); return 0; } static int ath9k_hif_usb_probe(struct usb_interface *interface, const struct usb_device_id *id) { struct usb_endpoint_descriptor *bulk_in, *bulk_out, *int_in, *int_out; struct usb_device *udev = interface_to_usbdev(interface); struct usb_host_interface *alt; struct hif_device_usb *hif_dev; int ret = 0; /* Verify the expected endpoints are present */ alt = interface->cur_altsetting; if (usb_find_common_endpoints(alt, &bulk_in, &bulk_out, &int_in, &int_out) < 0 || usb_endpoint_num(bulk_in) != USB_WLAN_RX_PIPE || usb_endpoint_num(bulk_out) != USB_WLAN_TX_PIPE || usb_endpoint_num(int_in) != USB_REG_IN_PIPE || usb_endpoint_num(int_out) != USB_REG_OUT_PIPE) { dev_err(&udev->dev, "ath9k_htc: Device endpoint numbers are not the expected ones\n"); return -ENODEV; } if (id->driver_info == STORAGE_DEVICE) return send_eject_command(interface); hif_dev = kzalloc(sizeof(struct hif_device_usb), GFP_KERNEL); if (!hif_dev) { ret = -ENOMEM; goto err_alloc; } usb_get_dev(udev); hif_dev->udev = udev; hif_dev->interface = interface; hif_dev->usb_device_id = id; #ifdef CONFIG_PM udev->reset_resume = 1; #endif usb_set_intfdata(interface, hif_dev); init_completion(&hif_dev->fw_done); ret = ath9k_hif_request_firmware(hif_dev, true); if (ret) goto err_fw_req; return ret; err_fw_req: usb_set_intfdata(interface, NULL); kfree(hif_dev); usb_put_dev(udev); err_alloc: return ret; } static void ath9k_hif_usb_reboot(struct usb_device *udev) { u32 reboot_cmd = 0xffffffff; void *buf; int ret; buf = kmemdup(&reboot_cmd, 4, GFP_KERNEL); if (!buf) return; ret = usb_interrupt_msg(udev, usb_sndintpipe(udev, USB_REG_OUT_PIPE), buf, 4, NULL, USB_MSG_TIMEOUT); if (ret) dev_err(&udev->dev, "ath9k_htc: USB reboot failed\n"); kfree(buf); } static void ath9k_hif_usb_disconnect(struct usb_interface *interface) { struct usb_device *udev = interface_to_usbdev(interface); struct hif_device_usb *hif_dev = usb_get_intfdata(interface); bool unplugged = udev->state == USB_STATE_NOTATTACHED; if (!hif_dev) return; wait_for_completion(&hif_dev->fw_done); if (hif_dev->flags & HIF_USB_READY) { ath9k_htc_hw_deinit(hif_dev->htc_handle, unplugged); ath9k_htc_hw_free(hif_dev->htc_handle); } usb_set_intfdata(interface, NULL); /* If firmware was loaded we should drop it * go back to first stage bootloader. */ if (!unplugged && (hif_dev->flags & HIF_USB_READY)) ath9k_hif_usb_reboot(udev); kfree(hif_dev); dev_info(&udev->dev, "ath9k_htc: USB layer deinitialized\n"); usb_put_dev(udev); } #ifdef CONFIG_PM static int ath9k_hif_usb_suspend(struct usb_interface *interface, pm_message_t message) { struct hif_device_usb *hif_dev = usb_get_intfdata(interface); /* * The device has to be set to FULLSLEEP mode in case no * interface is up. */ if (!(hif_dev->flags & HIF_USB_START)) ath9k_htc_suspend(hif_dev->htc_handle); wait_for_completion(&hif_dev->fw_done); if (hif_dev->flags & HIF_USB_READY) ath9k_hif_usb_dealloc_urbs(hif_dev); return 0; } static int ath9k_hif_usb_resume(struct usb_interface *interface) { struct hif_device_usb *hif_dev = usb_get_intfdata(interface); struct htc_target *htc_handle = hif_dev->htc_handle; const struct firmware *fw; int ret; ret = ath9k_hif_usb_alloc_urbs(hif_dev); if (ret) return ret; if (!(hif_dev->flags & HIF_USB_READY)) { ret = -EIO; goto fail_resume; } /* request cached firmware during suspend/resume cycle */ ret = request_firmware(&fw, hif_dev->fw_name, &hif_dev->udev->dev); if (ret) goto fail_resume; hif_dev->fw_data = fw->data; hif_dev->fw_size = fw->size; ret = ath9k_hif_usb_download_fw(hif_dev); release_firmware(fw); if (ret) goto fail_resume; mdelay(100); ret = ath9k_htc_resume(htc_handle); if (ret) goto fail_resume; return 0; fail_resume: ath9k_hif_usb_dealloc_urbs(hif_dev); return ret; } #endif static struct usb_driver ath9k_hif_usb_driver = { .name = KBUILD_MODNAME, .probe = ath9k_hif_usb_probe, .disconnect = ath9k_hif_usb_disconnect, #ifdef CONFIG_PM .suspend = ath9k_hif_usb_suspend, .resume = ath9k_hif_usb_resume, .reset_resume = ath9k_hif_usb_resume, #endif .id_table = ath9k_hif_usb_ids, .soft_unbind = 1, .disable_hub_initiated_lpm = 1, }; int ath9k_hif_usb_init(void) { return usb_register(&ath9k_hif_usb_driver); } void ath9k_hif_usb_exit(void) { usb_deregister(&ath9k_hif_usb_driver); } |
| 13 13 13 1 6 5 3 5 5 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 | /* * videobuf2-memops.c - generic memory handling routines for videobuf2 * * Copyright (C) 2010 Samsung Electronics * * Author: Pawel Osciak <pawel@osciak.com> * Marek Szyprowski <m.szyprowski@samsung.com> * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License as published by * the Free Software Foundation. */ #include <linux/slab.h> #include <linux/module.h> #include <linux/dma-mapping.h> #include <linux/vmalloc.h> #include <linux/mm.h> #include <linux/sched.h> #include <linux/file.h> #include <media/videobuf2-v4l2.h> #include <media/videobuf2-memops.h> /** * vb2_create_framevec() - map virtual addresses to pfns * @start: Virtual user address where we start mapping * @length: Length of a range to map * @write: Should we map for writing into the area * * This function allocates and fills in a vector with pfns corresponding to * virtual address range passed in arguments. If pfns have corresponding pages, * page references are also grabbed to pin pages in memory. The function * returns pointer to the vector on success and error pointer in case of * failure. Returned vector needs to be freed via vb2_destroy_pfnvec(). */ struct frame_vector *vb2_create_framevec(unsigned long start, unsigned long length, bool write) { int ret; unsigned long first, last; unsigned long nr; struct frame_vector *vec; first = start >> PAGE_SHIFT; last = (start + length - 1) >> PAGE_SHIFT; nr = last - first + 1; vec = frame_vector_create(nr); if (!vec) return ERR_PTR(-ENOMEM); ret = get_vaddr_frames(start & PAGE_MASK, nr, write, vec); if (ret < 0) goto out_destroy; /* We accept only complete set of PFNs */ if (ret != nr) { ret = -EFAULT; goto out_release; } return vec; out_release: put_vaddr_frames(vec); out_destroy: frame_vector_destroy(vec); return ERR_PTR(ret); } EXPORT_SYMBOL(vb2_create_framevec); /** * vb2_destroy_framevec() - release vector of mapped pfns * @vec: vector of pfns / pages to release * * This releases references to all pages in the vector @vec (if corresponding * pfns are backed by pages) and frees the passed vector. */ void vb2_destroy_framevec(struct frame_vector *vec) { put_vaddr_frames(vec); frame_vector_destroy(vec); } EXPORT_SYMBOL(vb2_destroy_framevec); /** * vb2_common_vm_open() - increase refcount of the vma * @vma: virtual memory region for the mapping * * This function adds another user to the provided vma. It expects * struct vb2_vmarea_handler pointer in vma->vm_private_data. */ static void vb2_common_vm_open(struct vm_area_struct *vma) { struct vb2_vmarea_handler *h = vma->vm_private_data; pr_debug("%s: %p, refcount: %d, vma: %08lx-%08lx\n", __func__, h, refcount_read(h->refcount), vma->vm_start, vma->vm_end); refcount_inc(h->refcount); } /** * vb2_common_vm_close() - decrease refcount of the vma * @vma: virtual memory region for the mapping * * This function releases the user from the provided vma. It expects * struct vb2_vmarea_handler pointer in vma->vm_private_data. */ static void vb2_common_vm_close(struct vm_area_struct *vma) { struct vb2_vmarea_handler *h = vma->vm_private_data; pr_debug("%s: %p, refcount: %d, vma: %08lx-%08lx\n", __func__, h, refcount_read(h->refcount), vma->vm_start, vma->vm_end); h->put(h->arg); } /* * vb2_common_vm_ops - common vm_ops used for tracking refcount of mmapped * video buffers */ const struct vm_operations_struct vb2_common_vm_ops = { .open = vb2_common_vm_open, .close = vb2_common_vm_close, }; EXPORT_SYMBOL_GPL(vb2_common_vm_ops); MODULE_DESCRIPTION("common memory handling routines for videobuf2"); MODULE_AUTHOR("Pawel Osciak <pawel@osciak.com>"); MODULE_LICENSE("GPL"); |
| 57 | 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 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * RNG: Random Number Generator algorithms under the crypto API * * Copyright (c) 2008 Neil Horman <nhorman@tuxdriver.com> * Copyright (c) 2015 Herbert Xu <herbert@gondor.apana.org.au> */ #ifndef _CRYPTO_INTERNAL_RNG_H #define _CRYPTO_INTERNAL_RNG_H #include <crypto/algapi.h> #include <crypto/rng.h> int crypto_register_rng(struct rng_alg *alg); void crypto_unregister_rng(struct rng_alg *alg); int crypto_register_rngs(struct rng_alg *algs, int count); void crypto_unregister_rngs(struct rng_alg *algs, int count); #if defined(CONFIG_CRYPTO_RNG) || defined(CONFIG_CRYPTO_RNG_MODULE) int crypto_del_default_rng(void); #else static inline int crypto_del_default_rng(void) { return 0; } #endif static inline void *crypto_rng_ctx(struct crypto_rng *tfm) { return crypto_tfm_ctx(&tfm->base); } static inline void crypto_rng_set_entropy(struct crypto_rng *tfm, const u8 *data, unsigned int len) { crypto_rng_alg(tfm)->set_ent(tfm, data, len); } #endif |
| 426 423 426 427 426 427 17 17 442 379 444 444 444 443 442 441 35 33 32 32 166 166 41 41 41 165 445 442 444 442 446 17 16 17 17 17 17 261 262 27 262 27 260 261 262 262 262 261 298 295 3 298 297 6 292 291 289 16 275 275 297 16 22 263 265 28 236 28 28 28 236 263 263 12 139 261 262 15 179 179 180 142 143 70 180 180 27 27 27 27 27 27 27 27 27 27 27 33 27 27 27 27 35 35 35 33 15 15 15 483 442 443 440 440 28 29 9 9 9 9 9 29 29 29 29 29 297 295 297 152 298 4 298 297 298 298 298 298 296 298 298 298 297 261 260 261 163 262 163 293 163 293 2 261 261 262 260 262 261 261 262 261 261 262 262 262 260 261 261 261 37 37 37 27 27 27 27 27 27 27 27 27 27 27 27 27 27 27 27 27 27 27 27 27 27 27 27 167 166 167 167 167 41 167 443 440 392 443 441 364 441 442 440 261 261 262 262 260 260 262 262 161 262 261 212 211 210 210 210 136 161 161 198 198 80 151 212 5 138 138 139 139 139 138 1 139 139 47 129 130 86 138 138 138 138 139 1 443 182 443 167 517 517 513 515 494 516 299 494 379 493 18 18 18 11 18 17 3 17 9 9 9 347 347 343 344 | 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 | // 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_mount.h" #include "xfs_errortag.h" #include "xfs_error.h" #include "xfs_trans.h" #include "xfs_trans_priv.h" #include "xfs_log.h" #include "xfs_log_priv.h" #include "xfs_trace.h" #include "xfs_sysfs.h" #include "xfs_sb.h" #include "xfs_health.h" #include "xfs_zone_alloc.h" struct kmem_cache *xfs_log_ticket_cache; /* Local miscellaneous function prototypes */ STATIC struct xlog * xlog_alloc_log( struct xfs_mount *mp, struct xfs_buftarg *log_target, xfs_daddr_t blk_offset, int num_bblks); STATIC void xlog_dealloc_log( struct xlog *log); /* local state machine functions */ STATIC void xlog_state_done_syncing( struct xlog_in_core *iclog); STATIC void xlog_state_do_callback( struct xlog *log); STATIC int xlog_state_get_iclog_space( struct xlog *log, int len, struct xlog_in_core **iclog, struct xlog_ticket *ticket, int *logoffsetp); STATIC void xlog_sync( struct xlog *log, struct xlog_in_core *iclog, struct xlog_ticket *ticket); #if defined(DEBUG) STATIC void xlog_verify_iclog( struct xlog *log, struct xlog_in_core *iclog, int count); STATIC void xlog_verify_tail_lsn( struct xlog *log, struct xlog_in_core *iclog); #else #define xlog_verify_iclog(a,b,c) #define xlog_verify_tail_lsn(a,b) #endif STATIC int xlog_iclogs_empty( struct xlog *log); static int xfs_log_cover(struct xfs_mount *); /* * We need to make sure the buffer pointer returned is naturally aligned for the * biggest basic data type we put into it. We have already accounted for this * padding when sizing the buffer. * * However, this padding does not get written into the log, and hence we have to * track the space used by the log vectors separately to prevent log space hangs * due to inaccurate accounting (i.e. a leak) of the used log space through the * CIL context ticket. * * We also add space for the xlog_op_header that describes this region in the * log. This prepends the data region we return to the caller to copy their data * into, so do all the static initialisation of the ophdr now. Because the ophdr * is not 8 byte aligned, we have to be careful to ensure that we align the * start of the buffer such that the region we return to the call is 8 byte * aligned and packed against the tail of the ophdr. */ void * xlog_prepare_iovec( struct xfs_log_vec *lv, struct xfs_log_iovec **vecp, uint type) { struct xfs_log_iovec *vec = *vecp; struct xlog_op_header *oph; uint32_t len; void *buf; if (vec) { ASSERT(vec - lv->lv_iovecp < lv->lv_niovecs); vec++; } else { vec = &lv->lv_iovecp[0]; } len = lv->lv_buf_used + sizeof(struct xlog_op_header); if (!IS_ALIGNED(len, sizeof(uint64_t))) { lv->lv_buf_used = round_up(len, sizeof(uint64_t)) - sizeof(struct xlog_op_header); } vec->i_type = type; vec->i_addr = lv->lv_buf + lv->lv_buf_used; oph = vec->i_addr; oph->oh_clientid = XFS_TRANSACTION; oph->oh_res2 = 0; oph->oh_flags = 0; buf = vec->i_addr + sizeof(struct xlog_op_header); ASSERT(IS_ALIGNED((unsigned long)buf, sizeof(uint64_t))); *vecp = vec; return buf; } static inline void xlog_grant_sub_space( struct xlog_grant_head *head, int64_t bytes) { atomic64_sub(bytes, &head->grant); } static inline void xlog_grant_add_space( struct xlog_grant_head *head, int64_t bytes) { atomic64_add(bytes, &head->grant); } static void xlog_grant_head_init( struct xlog_grant_head *head) { atomic64_set(&head->grant, 0); INIT_LIST_HEAD(&head->waiters); spin_lock_init(&head->lock); } void xlog_grant_return_space( struct xlog *log, xfs_lsn_t old_head, xfs_lsn_t new_head) { int64_t diff = xlog_lsn_sub(log, new_head, old_head); xlog_grant_sub_space(&log->l_reserve_head, diff); xlog_grant_sub_space(&log->l_write_head, diff); } /* * Return the space in the log between the tail and the head. In the case where * we have overrun available reservation space, return 0. The memory barrier * pairs with the smp_wmb() in xlog_cil_ail_insert() to ensure that grant head * vs tail space updates are seen in the correct order and hence avoid * transients as space is transferred from the grant heads to the AIL on commit * completion. */ static uint64_t xlog_grant_space_left( struct xlog *log, struct xlog_grant_head *head) { int64_t free_bytes; smp_rmb(); /* paired with smp_wmb in xlog_cil_ail_insert() */ free_bytes = log->l_logsize - READ_ONCE(log->l_tail_space) - atomic64_read(&head->grant); if (free_bytes > 0) return free_bytes; return 0; } STATIC void xlog_grant_head_wake_all( struct xlog_grant_head *head) { struct xlog_ticket *tic; spin_lock(&head->lock); list_for_each_entry(tic, &head->waiters, t_queue) wake_up_process(tic->t_task); spin_unlock(&head->lock); } static inline int xlog_ticket_reservation( struct xlog *log, struct xlog_grant_head *head, struct xlog_ticket *tic) { if (head == &log->l_write_head) { ASSERT(tic->t_flags & XLOG_TIC_PERM_RESERV); return tic->t_unit_res; } if (tic->t_flags & XLOG_TIC_PERM_RESERV) return tic->t_unit_res * tic->t_cnt; return tic->t_unit_res; } STATIC bool xlog_grant_head_wake( struct xlog *log, struct xlog_grant_head *head, int *free_bytes) { struct xlog_ticket *tic; int need_bytes; list_for_each_entry(tic, &head->waiters, t_queue) { need_bytes = xlog_ticket_reservation(log, head, tic); if (*free_bytes < need_bytes) return false; *free_bytes -= need_bytes; trace_xfs_log_grant_wake_up(log, tic); wake_up_process(tic->t_task); } return true; } STATIC int xlog_grant_head_wait( struct xlog *log, struct xlog_grant_head *head, struct xlog_ticket *tic, int need_bytes) __releases(&head->lock) __acquires(&head->lock) { list_add_tail(&tic->t_queue, &head->waiters); do { if (xlog_is_shutdown(log)) goto shutdown; __set_current_state(TASK_UNINTERRUPTIBLE); spin_unlock(&head->lock); XFS_STATS_INC(log->l_mp, xs_sleep_logspace); /* Push on the AIL to free up all the log space. */ xfs_ail_push_all(log->l_ailp); trace_xfs_log_grant_sleep(log, tic); schedule(); trace_xfs_log_grant_wake(log, tic); spin_lock(&head->lock); if (xlog_is_shutdown(log)) goto shutdown; } while (xlog_grant_space_left(log, head) < need_bytes); list_del_init(&tic->t_queue); return 0; shutdown: list_del_init(&tic->t_queue); return -EIO; } /* * Atomically get the log space required for a log ticket. * * Once a ticket gets put onto head->waiters, it will only return after the * needed reservation is satisfied. * * This function is structured so that it has a lock free fast path. This is * necessary because every new transaction reservation will come through this * path. Hence any lock will be globally hot if we take it unconditionally on * every pass. * * As tickets are only ever moved on and off head->waiters under head->lock, we * only need to take that lock if we are going to add the ticket to the queue * and sleep. We can avoid taking the lock if the ticket was never added to * head->waiters because the t_queue list head will be empty and we hold the * only reference to it so it can safely be checked unlocked. */ STATIC int xlog_grant_head_check( struct xlog *log, struct xlog_grant_head *head, struct xlog_ticket *tic, int *need_bytes) { int free_bytes; int error = 0; ASSERT(!xlog_in_recovery(log)); /* * If there are other waiters on the queue then give them a chance at * logspace before us. Wake up the first waiters, if we do not wake * up all the waiters then go to sleep waiting for more free space, * otherwise try to get some space for this transaction. */ *need_bytes = xlog_ticket_reservation(log, head, tic); free_bytes = xlog_grant_space_left(log, head); if (!list_empty_careful(&head->waiters)) { spin_lock(&head->lock); if (!xlog_grant_head_wake(log, head, &free_bytes) || free_bytes < *need_bytes) { error = xlog_grant_head_wait(log, head, tic, *need_bytes); } spin_unlock(&head->lock); } else if (free_bytes < *need_bytes) { spin_lock(&head->lock); error = xlog_grant_head_wait(log, head, tic, *need_bytes); spin_unlock(&head->lock); } return error; } bool xfs_log_writable( struct xfs_mount *mp) { /* * Do not write to the log on norecovery mounts, if the data or log * devices are read-only, or if the filesystem is shutdown. Read-only * mounts allow internal writes for log recovery and unmount purposes, * so don't restrict that case. */ if (xfs_has_norecovery(mp)) return false; if (xfs_readonly_buftarg(mp->m_ddev_targp)) return false; if (xfs_readonly_buftarg(mp->m_log->l_targ)) return false; if (xlog_is_shutdown(mp->m_log)) return false; return true; } /* * Replenish the byte reservation required by moving the grant write head. */ int xfs_log_regrant( struct xfs_mount *mp, struct xlog_ticket *tic) { struct xlog *log = mp->m_log; int need_bytes; int error = 0; if (xlog_is_shutdown(log)) return -EIO; XFS_STATS_INC(mp, xs_try_logspace); /* * This is a new transaction on the ticket, so we need to change the * transaction ID so that the next transaction has a different TID in * the log. Just add one to the existing tid so that we can see chains * of rolling transactions in the log easily. */ tic->t_tid++; tic->t_curr_res = tic->t_unit_res; if (tic->t_cnt > 0) return 0; trace_xfs_log_regrant(log, tic); error = xlog_grant_head_check(log, &log->l_write_head, tic, &need_bytes); if (error) goto out_error; xlog_grant_add_space(&log->l_write_head, need_bytes); trace_xfs_log_regrant_exit(log, tic); return 0; out_error: /* * If we are failing, make sure the ticket doesn't have any current * reservations. We don't want to add this back when the ticket/ * transaction gets cancelled. */ tic->t_curr_res = 0; tic->t_cnt = 0; /* ungrant will give back unit_res * t_cnt. */ return error; } /* * Reserve log space and return a ticket corresponding to the reservation. * * Each reservation is going to reserve extra space for a log record header. * When writes happen to the on-disk log, we don't subtract the length of the * log record header from any reservation. By wasting space in each * reservation, we prevent over allocation problems. */ int xfs_log_reserve( struct xfs_mount *mp, int unit_bytes, int cnt, struct xlog_ticket **ticp, bool permanent) { struct xlog *log = mp->m_log; struct xlog_ticket *tic; int need_bytes; int error = 0; if (xlog_is_shutdown(log)) return -EIO; XFS_STATS_INC(mp, xs_try_logspace); ASSERT(*ticp == NULL); tic = xlog_ticket_alloc(log, unit_bytes, cnt, permanent); *ticp = tic; trace_xfs_log_reserve(log, tic); error = xlog_grant_head_check(log, &log->l_reserve_head, tic, &need_bytes); if (error) goto out_error; xlog_grant_add_space(&log->l_reserve_head, need_bytes); xlog_grant_add_space(&log->l_write_head, need_bytes); trace_xfs_log_reserve_exit(log, tic); return 0; out_error: /* * If we are failing, make sure the ticket doesn't have any current * reservations. We don't want to add this back when the ticket/ * transaction gets cancelled. */ tic->t_curr_res = 0; tic->t_cnt = 0; /* ungrant will give back unit_res * t_cnt. */ return error; } /* * Run all the pending iclog callbacks and wake log force waiters and iclog * space waiters so they can process the newly set shutdown state. We really * don't care what order we process callbacks here because the log is shut down * and so state cannot change on disk anymore. However, we cannot wake waiters * until the callbacks have been processed because we may be in unmount and * we must ensure that all AIL operations the callbacks perform have completed * before we tear down the AIL. * * We avoid processing actively referenced iclogs so that we don't run callbacks * while the iclog owner might still be preparing the iclog for IO submssion. * These will be caught by xlog_state_iclog_release() and call this function * again to process any callbacks that may have been added to that iclog. */ static void xlog_state_shutdown_callbacks( struct xlog *log) { struct xlog_in_core *iclog; LIST_HEAD(cb_list); iclog = log->l_iclog; do { if (atomic_read(&iclog->ic_refcnt)) { /* Reference holder will re-run iclog callbacks. */ continue; } list_splice_init(&iclog->ic_callbacks, &cb_list); spin_unlock(&log->l_icloglock); xlog_cil_process_committed(&cb_list); spin_lock(&log->l_icloglock); wake_up_all(&iclog->ic_write_wait); wake_up_all(&iclog->ic_force_wait); } while ((iclog = iclog->ic_next) != log->l_iclog); wake_up_all(&log->l_flush_wait); } /* * Flush iclog to disk if this is the last reference to the given iclog and the * it is in the WANT_SYNC state. * * If XLOG_ICL_NEED_FUA is already set on the iclog, we need to ensure that the * log tail is updated correctly. NEED_FUA indicates that the iclog will be * written to stable storage, and implies that a commit record is contained * within the iclog. We need to ensure that the log tail does not move beyond * the tail that the first commit record in the iclog ordered against, otherwise * correct recovery of that checkpoint becomes dependent on future operations * performed on this iclog. * * Hence if NEED_FUA is set and the current iclog tail lsn is empty, write the * current tail into iclog. Once the iclog tail is set, future operations must * not modify it, otherwise they potentially violate ordering constraints for * the checkpoint commit that wrote the initial tail lsn value. The tail lsn in * the iclog will get zeroed on activation of the iclog after sync, so we * always capture the tail lsn on the iclog on the first NEED_FUA release * regardless of the number of active reference counts on this iclog. */ int xlog_state_release_iclog( struct xlog *log, struct xlog_in_core *iclog, struct xlog_ticket *ticket) { bool last_ref; lockdep_assert_held(&log->l_icloglock); trace_xlog_iclog_release(iclog, _RET_IP_); /* * Grabbing the current log tail needs to be atomic w.r.t. the writing * of the tail LSN into the iclog so we guarantee that the log tail does * not move between the first time we know that the iclog needs to be * made stable and when we eventually submit it. */ if ((iclog->ic_state == XLOG_STATE_WANT_SYNC || (iclog->ic_flags & XLOG_ICL_NEED_FUA)) && !iclog->ic_header.h_tail_lsn) { iclog->ic_header.h_tail_lsn = cpu_to_be64(atomic64_read(&log->l_tail_lsn)); } last_ref = atomic_dec_and_test(&iclog->ic_refcnt); if (xlog_is_shutdown(log)) { /* * If there are no more references to this iclog, process the * pending iclog callbacks that were waiting on the release of * this iclog. */ if (last_ref) xlog_state_shutdown_callbacks(log); return -EIO; } if (!last_ref) return 0; if (iclog->ic_state != XLOG_STATE_WANT_SYNC) { ASSERT(iclog->ic_state == XLOG_STATE_ACTIVE); return 0; } iclog->ic_state = XLOG_STATE_SYNCING; xlog_verify_tail_lsn(log, iclog); trace_xlog_iclog_syncing(iclog, _RET_IP_); spin_unlock(&log->l_icloglock); xlog_sync(log, iclog, ticket); spin_lock(&log->l_icloglock); return 0; } /* * Mount a log filesystem * * mp - ubiquitous xfs mount point structure * log_target - buftarg of on-disk log device * blk_offset - Start block # where block size is 512 bytes (BBSIZE) * num_bblocks - Number of BBSIZE blocks in on-disk log * * Return error or zero. */ int xfs_log_mount( xfs_mount_t *mp, struct xfs_buftarg *log_target, xfs_daddr_t blk_offset, int num_bblks) { struct xlog *log; int error = 0; int min_logfsbs; if (!xfs_has_norecovery(mp)) { xfs_notice(mp, "Mounting V%d Filesystem %pU", XFS_SB_VERSION_NUM(&mp->m_sb), &mp->m_sb.sb_uuid); } else { xfs_notice(mp, "Mounting V%d filesystem %pU in no-recovery mode. Filesystem will be inconsistent.", XFS_SB_VERSION_NUM(&mp->m_sb), &mp->m_sb.sb_uuid); ASSERT(xfs_is_readonly(mp)); } log = xlog_alloc_log(mp, log_target, blk_offset, num_bblks); if (IS_ERR(log)) { error = PTR_ERR(log); goto out; } mp->m_log = log; /* * Now that we have set up the log and it's internal geometry * parameters, we can validate the given log space and drop a critical * message via syslog if the log size is too small. A log that is too * small can lead to unexpected situations in transaction log space * reservation stage. The superblock verifier has already validated all * the other log geometry constraints, so we don't have to check those * here. * * Note: For v4 filesystems, we can't just reject the mount if the * validation fails. This would mean that people would have to * downgrade their kernel just to remedy the situation as there is no * way to grow the log (short of black magic surgery with xfs_db). * * We can, however, reject mounts for V5 format filesystems, as the * mkfs binary being used to make the filesystem should never create a * filesystem with a log that is too small. */ min_logfsbs = xfs_log_calc_minimum_size(mp); if (mp->m_sb.sb_logblocks < min_logfsbs) { xfs_warn(mp, "Log size %d blocks too small, minimum size is %d blocks", mp->m_sb.sb_logblocks, min_logfsbs); /* * Log check errors are always fatal on v5; or whenever bad * metadata leads to a crash. */ if (xfs_has_crc(mp)) { xfs_crit(mp, "AAIEEE! Log failed size checks. Abort!"); ASSERT(0); error = -EINVAL; goto out_free_log; } xfs_crit(mp, "Log size out of supported range."); xfs_crit(mp, "Continuing onwards, but if log hangs are experienced then please report this message in the bug report."); } /* * Initialize the AIL now we have a log. */ error = xfs_trans_ail_init(mp); if (error) { xfs_warn(mp, "AIL initialisation failed: error %d", error); goto out_free_log; } log->l_ailp = mp->m_ail; /* * skip log recovery on a norecovery mount. pretend it all * just worked. */ if (!xfs_has_norecovery(mp)) { error = xlog_recover(log); if (error) { xfs_warn(mp, "log mount/recovery failed: error %d", error); xlog_recover_cancel(log); goto out_destroy_ail; } } error = xfs_sysfs_init(&log->l_kobj, &xfs_log_ktype, &mp->m_kobj, "log"); if (error) goto out_destroy_ail; /* Normal transactions can now occur */ clear_bit(XLOG_ACTIVE_RECOVERY, &log->l_opstate); /* * Now the log has been fully initialised and we know were our * space grant counters are, we can initialise the permanent ticket * needed for delayed logging to work. */ xlog_cil_init_post_recovery(log); return 0; out_destroy_ail: xfs_trans_ail_destroy(mp); out_free_log: xlog_dealloc_log(log); out: return error; } /* * Finish the recovery of the file system. This is separate from the * xfs_log_mount() call, because it depends on the code in xfs_mountfs() to read * in the root and real-time bitmap inodes between calling xfs_log_mount() and * here. * * If we finish recovery successfully, start the background log work. If we are * not doing recovery, then we have a RO filesystem and we don't need to start * it. */ int xfs_log_mount_finish( struct xfs_mount *mp) { struct xlog *log = mp->m_log; int error = 0; if (xfs_has_norecovery(mp)) { ASSERT(xfs_is_readonly(mp)); return 0; } /* * During the second phase of log recovery, we need iget and * iput to behave like they do for an active filesystem. * xfs_fs_drop_inode needs to be able to prevent the deletion * of inodes before we're done replaying log items on those * inodes. Turn it off immediately after recovery finishes * so that we don't leak the quota inodes if subsequent mount * activities fail. * * We let all inodes involved in redo item processing end up on * the LRU instead of being evicted immediately so that if we do * something to an unlinked inode, the irele won't cause * premature truncation and freeing of the inode, which results * in log recovery failure. We have to evict the unreferenced * lru inodes after clearing SB_ACTIVE because we don't * otherwise clean up the lru if there's a subsequent failure in * xfs_mountfs, which leads to us leaking the inodes if nothing * else (e.g. quotacheck) references the inodes before the * mount failure occurs. */ mp->m_super->s_flags |= SB_ACTIVE; xfs_log_work_queue(mp); if (xlog_recovery_needed(log)) error = xlog_recover_finish(log); mp->m_super->s_flags &= ~SB_ACTIVE; evict_inodes(mp->m_super); /* * Drain the buffer LRU after log recovery. This is required for v4 * filesystems to avoid leaving around buffers with NULL verifier ops, * but we do it unconditionally to make sure we're always in a clean * cache state after mount. * * Don't push in the error case because the AIL may have pending intents * that aren't removed until recovery is cancelled. */ if (xlog_recovery_needed(log)) { if (!error) { xfs_log_force(mp, XFS_LOG_SYNC); xfs_ail_push_all_sync(mp->m_ail); } xfs_notice(mp, "Ending recovery (logdev: %s)", mp->m_logname ? mp->m_logname : "internal"); } else { xfs_info(mp, "Ending clean mount"); } xfs_buftarg_drain(mp->m_ddev_targp); clear_bit(XLOG_RECOVERY_NEEDED, &log->l_opstate); /* Make sure the log is dead if we're returning failure. */ ASSERT(!error || xlog_is_shutdown(log)); return error; } /* * The mount has failed. Cancel the recovery if it hasn't completed and destroy * the log. */ void xfs_log_mount_cancel( struct xfs_mount *mp) { xlog_recover_cancel(mp->m_log); xfs_log_unmount(mp); } /* * Flush out the iclog to disk ensuring that device caches are flushed and * the iclog hits stable storage before any completion waiters are woken. */ static inline int xlog_force_iclog( struct xlog_in_core *iclog) { atomic_inc(&iclog->ic_refcnt); iclog->ic_flags |= XLOG_ICL_NEED_FLUSH | XLOG_ICL_NEED_FUA; if (iclog->ic_state == XLOG_STATE_ACTIVE) xlog_state_switch_iclogs(iclog->ic_log, iclog, 0); return xlog_state_release_iclog(iclog->ic_log, iclog, NULL); } /* * Cycle all the iclogbuf locks to make sure all log IO completion * is done before we tear down these buffers. */ static void xlog_wait_iclog_completion(struct xlog *log) { int i; struct xlog_in_core *iclog = log->l_iclog; for (i = 0; i < log->l_iclog_bufs; i++) { down(&iclog->ic_sema); up(&iclog->ic_sema); iclog = iclog->ic_next; } } /* * Wait for the iclog and all prior iclogs to be written disk as required by the * log force state machine. Waiting on ic_force_wait ensures iclog completions * have been ordered and callbacks run before we are woken here, hence * guaranteeing that all the iclogs up to this one are on stable storage. */ int xlog_wait_on_iclog( struct xlog_in_core *iclog) __releases(iclog->ic_log->l_icloglock) { struct xlog *log = iclog->ic_log; trace_xlog_iclog_wait_on(iclog, _RET_IP_); if (!xlog_is_shutdown(log) && iclog->ic_state != XLOG_STATE_ACTIVE && iclog->ic_state != XLOG_STATE_DIRTY) { XFS_STATS_INC(log->l_mp, xs_log_force_sleep); xlog_wait(&iclog->ic_force_wait, &log->l_icloglock); } else { spin_unlock(&log->l_icloglock); } if (xlog_is_shutdown(log)) return -EIO; return 0; } /* * Write out an unmount record using the ticket provided. We have to account for * the data space used in the unmount ticket as this write is not done from a * transaction context that has already done the accounting for us. */ static int xlog_write_unmount_record( struct xlog *log, struct xlog_ticket *ticket) { struct { struct xlog_op_header ophdr; struct xfs_unmount_log_format ulf; } unmount_rec = { .ophdr = { .oh_clientid = XFS_LOG, .oh_tid = cpu_to_be32(ticket->t_tid), .oh_flags = XLOG_UNMOUNT_TRANS, }, .ulf = { .magic = XLOG_UNMOUNT_TYPE, }, }; struct xfs_log_iovec reg = { .i_addr = &unmount_rec, .i_len = sizeof(unmount_rec), .i_type = XLOG_REG_TYPE_UNMOUNT, }; struct xfs_log_vec vec = { .lv_niovecs = 1, .lv_iovecp = ®, }; LIST_HEAD(lv_chain); list_add(&vec.lv_list, &lv_chain); BUILD_BUG_ON((sizeof(struct xlog_op_header) + sizeof(struct xfs_unmount_log_format)) != sizeof(unmount_rec)); /* account for space used by record data */ ticket->t_curr_res -= sizeof(unmount_rec); return xlog_write(log, NULL, &lv_chain, ticket, reg.i_len); } /* * Mark the filesystem clean by writing an unmount record to the head of the * log. */ static void xlog_unmount_write( struct xlog *log) { struct xfs_mount *mp = log->l_mp; struct xlog_in_core *iclog; struct xlog_ticket *tic = NULL; int error; error = xfs_log_reserve(mp, 600, 1, &tic, 0); if (error) goto out_err; error = xlog_write_unmount_record(log, tic); /* * At this point, we're umounting anyway, so there's no point in * transitioning log state to shutdown. Just continue... */ out_err: if (error) xfs_alert(mp, "%s: unmount record failed", __func__); spin_lock(&log->l_icloglock); iclog = log->l_iclog; error = xlog_force_iclog(iclog); xlog_wait_on_iclog(iclog); if (tic) { trace_xfs_log_umount_write(log, tic); xfs_log_ticket_ungrant(log, tic); } } static void xfs_log_unmount_verify_iclog( struct xlog *log) { struct xlog_in_core *iclog = log->l_iclog; do { ASSERT(iclog->ic_state == XLOG_STATE_ACTIVE); ASSERT(iclog->ic_offset == 0); } while ((iclog = iclog->ic_next) != log->l_iclog); } /* * Unmount record used to have a string "Unmount filesystem--" in the * data section where the "Un" was really a magic number (XLOG_UNMOUNT_TYPE). * We just write the magic number now since that particular field isn't * currently architecture converted and "Unmount" is a bit foo. * As far as I know, there weren't any dependencies on the old behaviour. */ static void xfs_log_unmount_write( struct xfs_mount *mp) { struct xlog *log = mp->m_log; if (!xfs_log_writable(mp)) return; xfs_log_force(mp, XFS_LOG_SYNC); if (xlog_is_shutdown(log)) return; /* * If we think the summary counters are bad, avoid writing the unmount * record to force log recovery at next mount, after which the summary * counters will be recalculated. Refer to xlog_check_unmount_rec for * more details. */ if (XFS_TEST_ERROR(xfs_fs_has_sickness(mp, XFS_SICK_FS_COUNTERS), mp, XFS_ERRTAG_FORCE_SUMMARY_RECALC)) { xfs_alert(mp, "%s: will fix summary counters at next mount", __func__); return; } xfs_log_unmount_verify_iclog(log); xlog_unmount_write(log); } /* * Empty the log for unmount/freeze. * * To do this, we first need to shut down the background log work so it is not * trying to cover the log as we clean up. We then need to unpin all objects in * the log so we can then flush them out. Once they have completed their IO and * run the callbacks removing themselves from the AIL, we can cover the log. */ int xfs_log_quiesce( struct xfs_mount *mp) { /* * Clear log incompat features since we're quiescing the log. Report * failures, though it's not fatal to have a higher log feature * protection level than the log contents actually require. */ if (xfs_clear_incompat_log_features(mp)) { int error; error = xfs_sync_sb(mp, false); if (error) xfs_warn(mp, "Failed to clear log incompat features on quiesce"); } cancel_delayed_work_sync(&mp->m_log->l_work); xfs_log_force(mp, XFS_LOG_SYNC); /* * The superblock buffer is uncached and while xfs_ail_push_all_sync() * will push it, xfs_buftarg_wait() will not wait for it. Further, * xfs_buf_iowait() cannot be used because it was pushed with the * XBF_ASYNC flag set, so we need to use a lock/unlock pair to wait for * the IO to complete. */ xfs_ail_push_all_sync(mp->m_ail); xfs_buftarg_wait(mp->m_ddev_targp); xfs_buf_lock(mp->m_sb_bp); xfs_buf_unlock(mp->m_sb_bp); return xfs_log_cover(mp); } void xfs_log_clean( struct xfs_mount *mp) { xfs_log_quiesce(mp); xfs_log_unmount_write(mp); } /* * Shut down and release the AIL and Log. * * During unmount, we need to ensure we flush all the dirty metadata objects * from the AIL so that the log is empty before we write the unmount record to * the log. Once this is done, we can tear down the AIL and the log. */ void xfs_log_unmount( struct xfs_mount *mp) { xfs_log_clean(mp); /* * If shutdown has come from iclog IO context, the log * cleaning will have been skipped and so we need to wait * for the iclog to complete shutdown processing before we * tear anything down. */ xlog_wait_iclog_completion(mp->m_log); xfs_buftarg_drain(mp->m_ddev_targp); xfs_trans_ail_destroy(mp); xfs_sysfs_del(&mp->m_log->l_kobj); xlog_dealloc_log(mp->m_log); } void xfs_log_item_init( struct xfs_mount *mp, struct xfs_log_item *item, int type, const struct xfs_item_ops *ops) { item->li_log = mp->m_log; item->li_ailp = mp->m_ail; item->li_type = type; item->li_ops = ops; item->li_lv = NULL; INIT_LIST_HEAD(&item->li_ail); INIT_LIST_HEAD(&item->li_cil); INIT_LIST_HEAD(&item->li_bio_list); INIT_LIST_HEAD(&item->li_trans); } /* * Wake up processes waiting for log space after we have moved the log tail. */ void xfs_log_space_wake( struct xfs_mount *mp) { struct xlog *log = mp->m_log; int free_bytes; if (xlog_is_shutdown(log)) return; if (!list_empty_careful(&log->l_write_head.waiters)) { ASSERT(!xlog_in_recovery(log)); spin_lock(&log->l_write_head.lock); free_bytes = xlog_grant_space_left(log, &log->l_write_head); xlog_grant_head_wake(log, &log->l_write_head, &free_bytes); spin_unlock(&log->l_write_head.lock); } if (!list_empty_careful(&log->l_reserve_head.waiters)) { ASSERT(!xlog_in_recovery(log)); spin_lock(&log->l_reserve_head.lock); free_bytes = xlog_grant_space_left(log, &log->l_reserve_head); xlog_grant_head_wake(log, &log->l_reserve_head, &free_bytes); spin_unlock(&log->l_reserve_head.lock); } } /* * Determine if we have a transaction that has gone to disk that needs to be * covered. To begin the transition to the idle state firstly the log needs to * be idle. That means the CIL, the AIL and the iclogs needs to be empty before * we start attempting to cover the log. * * Only if we are then in a state where covering is needed, the caller is * informed that dummy transactions are required to move the log into the idle * state. * * If there are any items in the AIl or CIL, then we do not want to attempt to * cover the log as we may be in a situation where there isn't log space * available to run a dummy transaction and this can lead to deadlocks when the * tail of the log is pinned by an item that is modified in the CIL. Hence * there's no point in running a dummy transaction at this point because we * can't start trying to idle the log until both the CIL and AIL are empty. */ static bool xfs_log_need_covered( struct xfs_mount *mp) { struct xlog *log = mp->m_log; bool needed = false; if (!xlog_cil_empty(log)) return false; spin_lock(&log->l_icloglock); switch (log->l_covered_state) { case XLOG_STATE_COVER_DONE: case XLOG_STATE_COVER_DONE2: case XLOG_STATE_COVER_IDLE: break; case XLOG_STATE_COVER_NEED: case XLOG_STATE_COVER_NEED2: if (xfs_ail_min_lsn(log->l_ailp)) break; if (!xlog_iclogs_empty(log)) break; needed = true; if (log->l_covered_state == XLOG_STATE_COVER_NEED) log->l_covered_state = XLOG_STATE_COVER_DONE; else log->l_covered_state = XLOG_STATE_COVER_DONE2; break; default: needed = true; break; } spin_unlock(&log->l_icloglock); return needed; } /* * Explicitly cover the log. This is similar to background log covering but * intended for usage in quiesce codepaths. The caller is responsible to ensure * the log is idle and suitable for covering. The CIL, iclog buffers and AIL * must all be empty. */ static int xfs_log_cover( struct xfs_mount *mp) { int error = 0; bool need_covered; ASSERT((xlog_cil_empty(mp->m_log) && xlog_iclogs_empty(mp->m_log) && !xfs_ail_min_lsn(mp->m_log->l_ailp)) || xlog_is_shutdown(mp->m_log)); if (!xfs_log_writable(mp)) return 0; /* * xfs_log_need_covered() is not idempotent because it progresses the * state machine if the log requires covering. Therefore, we must call * this function once and use the result until we've issued an sb sync. * Do so first to make that abundantly clear. * * Fall into the covering sequence if the log needs covering or the * mount has lazy superblock accounting to sync to disk. The sb sync * used for covering accumulates the in-core counters, so covering * handles this for us. */ need_covered = xfs_log_need_covered(mp); if (!need_covered && !xfs_has_lazysbcount(mp)) return 0; /* * To cover the log, commit the superblock twice (at most) in * independent checkpoints. The first serves as a reference for the * tail pointer. The sync transaction and AIL push empties the AIL and * updates the in-core tail to the LSN of the first checkpoint. The * second commit updates the on-disk tail with the in-core LSN, * covering the log. Push the AIL one more time to leave it empty, as * we found it. */ do { error = xfs_sync_sb(mp, true); if (error) break; xfs_ail_push_all_sync(mp->m_ail); } while (xfs_log_need_covered(mp)); return error; } static void xlog_ioend_work( struct work_struct *work) { struct xlog_in_core *iclog = container_of(work, struct xlog_in_core, ic_end_io_work); struct xlog *log = iclog->ic_log; int error; error = blk_status_to_errno(iclog->ic_bio.bi_status); #ifdef DEBUG /* treat writes with injected CRC errors as failed */ if (iclog->ic_fail_crc) error = -EIO; #endif /* * Race to shutdown the filesystem if we see an error. */ if (XFS_TEST_ERROR(error, log->l_mp, XFS_ERRTAG_IODONE_IOERR)) { xfs_alert(log->l_mp, "log I/O error %d", error); xlog_force_shutdown(log, SHUTDOWN_LOG_IO_ERROR); } xlog_state_done_syncing(iclog); bio_uninit(&iclog->ic_bio); /* * Drop the lock to signal that we are done. Nothing references the * iclog after this, so an unmount waiting on this lock can now tear it * down safely. As such, it is unsafe to reference the iclog after the * unlock as we could race with it being freed. */ up(&iclog->ic_sema); } /* * Return size of each in-core log record buffer. * * All machines get 8 x 32kB buffers by default, unless tuned otherwise. * * If the filesystem blocksize is too large, we may need to choose a * larger size since the directory code currently logs entire blocks. */ STATIC void xlog_get_iclog_buffer_size( struct xfs_mount *mp, struct xlog *log) { if (mp->m_logbufs <= 0) mp->m_logbufs = XLOG_MAX_ICLOGS; if (mp->m_logbsize <= 0) mp->m_logbsize = XLOG_BIG_RECORD_BSIZE; log->l_iclog_bufs = mp->m_logbufs; log->l_iclog_size = mp->m_logbsize; /* * # headers = size / 32k - one header holds cycles from 32k of data. */ log->l_iclog_heads = DIV_ROUND_UP(mp->m_logbsize, XLOG_HEADER_CYCLE_SIZE); log->l_iclog_hsize = log->l_iclog_heads << BBSHIFT; } void xfs_log_work_queue( struct xfs_mount *mp) { queue_delayed_work(mp->m_sync_workqueue, &mp->m_log->l_work, msecs_to_jiffies(xfs_syncd_centisecs * 10)); } /* * Clear the log incompat flags if we have the opportunity. * * This only happens if we're about to log the second dummy transaction as part * of covering the log. */ static inline void xlog_clear_incompat( struct xlog *log) { struct xfs_mount *mp = log->l_mp; if (!xfs_sb_has_incompat_log_feature(&mp->m_sb, XFS_SB_FEAT_INCOMPAT_LOG_ALL)) return; if (log->l_covered_state != XLOG_STATE_COVER_DONE2) return; xfs_clear_incompat_log_features(mp); } /* * Every sync period we need to unpin all items in the AIL and push them to * disk. If there is nothing dirty, then we might need to cover the log to * indicate that the filesystem is idle. */ static void xfs_log_worker( struct work_struct *work) { struct xlog *log = container_of(to_delayed_work(work), struct xlog, l_work); struct xfs_mount *mp = log->l_mp; /* dgc: errors ignored - not fatal and nowhere to report them */ if (xfs_fs_writable(mp, SB_FREEZE_WRITE) && xfs_log_need_covered(mp)) { /* * Dump a transaction into the log that contains no real change. * This is needed to stamp the current tail LSN into the log * during the covering operation. * * We cannot use an inode here for this - that will push dirty * state back up into the VFS and then periodic inode flushing * will prevent log covering from making progress. Hence we * synchronously log the superblock instead to ensure the * superblock is immediately unpinned and can be written back. */ xlog_clear_incompat(log); xfs_sync_sb(mp, true); } else xfs_log_force(mp, 0); /* start pushing all the metadata that is currently dirty */ xfs_ail_push_all(mp->m_ail); /* queue us up again */ xfs_log_work_queue(mp); } /* * This routine initializes some of the log structure for a given mount point. * Its primary purpose is to fill in enough, so recovery can occur. However, * some other stuff may be filled in too. */ STATIC struct xlog * xlog_alloc_log( struct xfs_mount *mp, struct xfs_buftarg *log_target, xfs_daddr_t blk_offset, int num_bblks) { struct xlog *log; xlog_rec_header_t *head; xlog_in_core_t **iclogp; xlog_in_core_t *iclog, *prev_iclog=NULL; int i; int error = -ENOMEM; uint log2_size = 0; log = kzalloc(sizeof(struct xlog), GFP_KERNEL | __GFP_RETRY_MAYFAIL); if (!log) { xfs_warn(mp, "Log allocation failed: No memory!"); goto out; } log->l_mp = mp; log->l_targ = log_target; log->l_logsize = BBTOB(num_bblks); log->l_logBBstart = blk_offset; log->l_logBBsize = num_bblks; log->l_covered_state = XLOG_STATE_COVER_IDLE; set_bit(XLOG_ACTIVE_RECOVERY, &log->l_opstate); INIT_DELAYED_WORK(&log->l_work, xfs_log_worker); INIT_LIST_HEAD(&log->r_dfops); log->l_prev_block = -1; /* log->l_tail_lsn = 0x100000000LL; cycle = 1; current block = 0 */ xlog_assign_atomic_lsn(&log->l_tail_lsn, 1, 0); log->l_curr_cycle = 1; /* 0 is bad since this is initial value */ if (xfs_has_logv2(mp) && mp->m_sb.sb_logsunit > 1) log->l_iclog_roundoff = mp->m_sb.sb_logsunit; else log->l_iclog_roundoff = BBSIZE; xlog_grant_head_init(&log->l_reserve_head); xlog_grant_head_init(&log->l_write_head); error = -EFSCORRUPTED; if (xfs_has_sector(mp)) { log2_size = mp->m_sb.sb_logsectlog; if (log2_size < BBSHIFT) { xfs_warn(mp, "Log sector size too small (0x%x < 0x%x)", log2_size, BBSHIFT); goto out_free_log; } log2_size -= BBSHIFT; if (log2_size > mp->m_sectbb_log) { xfs_warn(mp, "Log sector size too large (0x%x > 0x%x)", log2_size, mp->m_sectbb_log); goto out_free_log; } /* for larger sector sizes, must have v2 or external log */ if (log2_size && log->l_logBBstart > 0 && !xfs_has_logv2(mp)) { xfs_warn(mp, "log sector size (0x%x) invalid for configuration.", log2_size); goto out_free_log; } } log->l_sectBBsize = 1 << log2_size; xlog_get_iclog_buffer_size(mp, log); spin_lock_init(&log->l_icloglock); init_waitqueue_head(&log->l_flush_wait); iclogp = &log->l_iclog; /* * The amount of memory to allocate for the iclog structure is * rather funky due to the way the structure is defined. It is * done this way so that we can use different sizes for machines * with different amounts of memory. See the definition of * xlog_in_core_t in xfs_log_priv.h for details. */ ASSERT(log->l_iclog_size >= 4096); for (i = 0; i < log->l_iclog_bufs; i++) { size_t bvec_size = howmany(log->l_iclog_size, PAGE_SIZE) * sizeof(struct bio_vec); iclog = kzalloc(sizeof(*iclog) + bvec_size, GFP_KERNEL | __GFP_RETRY_MAYFAIL); if (!iclog) goto out_free_iclog; *iclogp = iclog; iclog->ic_prev = prev_iclog; prev_iclog = iclog; iclog->ic_data = kvzalloc(log->l_iclog_size, GFP_KERNEL | __GFP_RETRY_MAYFAIL); if (!iclog->ic_data) goto out_free_iclog; head = &iclog->ic_header; memset(head, 0, sizeof(xlog_rec_header_t)); head->h_magicno = cpu_to_be32(XLOG_HEADER_MAGIC_NUM); head->h_version = cpu_to_be32( xfs_has_logv2(log->l_mp) ? 2 : 1); head->h_size = cpu_to_be32(log->l_iclog_size); /* new fields */ head->h_fmt = cpu_to_be32(XLOG_FMT); memcpy(&head->h_fs_uuid, &mp->m_sb.sb_uuid, sizeof(uuid_t)); iclog->ic_size = log->l_iclog_size - log->l_iclog_hsize; iclog->ic_state = XLOG_STATE_ACTIVE; iclog->ic_log = log; atomic_set(&iclog->ic_refcnt, 0); INIT_LIST_HEAD(&iclog->ic_callbacks); iclog->ic_datap = (void *)iclog->ic_data + log->l_iclog_hsize; init_waitqueue_head(&iclog->ic_force_wait); init_waitqueue_head(&iclog->ic_write_wait); INIT_WORK(&iclog->ic_end_io_work, xlog_ioend_work); sema_init(&iclog->ic_sema, 1); iclogp = &iclog->ic_next; } *iclogp = log->l_iclog; /* complete ring */ log->l_iclog->ic_prev = prev_iclog; /* re-write 1st prev ptr */ log->l_ioend_workqueue = alloc_workqueue("xfs-log/%s", XFS_WQFLAGS(WQ_FREEZABLE | WQ_MEM_RECLAIM | WQ_HIGHPRI), 0, mp->m_super->s_id); if (!log->l_ioend_workqueue) goto out_free_iclog; error = xlog_cil_init(log); if (error) goto out_destroy_workqueue; return log; out_destroy_workqueue: destroy_workqueue(log->l_ioend_workqueue); out_free_iclog: for (iclog = log->l_iclog; iclog; iclog = prev_iclog) { prev_iclog = iclog->ic_next; kvfree(iclog->ic_data); kfree(iclog); if (prev_iclog == log->l_iclog) break; } out_free_log: kfree(log); out: return ERR_PTR(error); } /* xlog_alloc_log */ /* * Stamp cycle number in every block */ STATIC void xlog_pack_data( struct xlog *log, struct xlog_in_core *iclog, int roundoff) { int i, j, k; int size = iclog->ic_offset + roundoff; __be32 cycle_lsn; char *dp; cycle_lsn = CYCLE_LSN_DISK(iclog->ic_header.h_lsn); dp = iclog->ic_datap; for (i = 0; i < BTOBB(size); i++) { if (i >= (XLOG_HEADER_CYCLE_SIZE / BBSIZE)) break; iclog->ic_header.h_cycle_data[i] = *(__be32 *)dp; *(__be32 *)dp = cycle_lsn; dp += BBSIZE; } if (xfs_has_logv2(log->l_mp)) { xlog_in_core_2_t *xhdr = iclog->ic_data; for ( ; i < BTOBB(size); i++) { j = i / (XLOG_HEADER_CYCLE_SIZE / BBSIZE); k = i % (XLOG_HEADER_CYCLE_SIZE / BBSIZE); xhdr[j].hic_xheader.xh_cycle_data[k] = *(__be32 *)dp; *(__be32 *)dp = cycle_lsn; dp += BBSIZE; } for (i = 1; i < log->l_iclog_heads; i++) xhdr[i].hic_xheader.xh_cycle = cycle_lsn; } } /* * Calculate the checksum for a log buffer. * * This is a little more complicated than it should be because the various * headers and the actual data are non-contiguous. */ __le32 xlog_cksum( struct xlog *log, struct xlog_rec_header *rhead, char *dp, int size) { uint32_t crc; /* first generate the crc for the record header ... */ crc = xfs_start_cksum_update((char *)rhead, sizeof(struct xlog_rec_header), offsetof(struct xlog_rec_header, h_crc)); /* ... then for additional cycle data for v2 logs ... */ if (xfs_has_logv2(log->l_mp)) { union xlog_in_core2 *xhdr = (union xlog_in_core2 *)rhead; int i; int xheads; xheads = DIV_ROUND_UP(size, XLOG_HEADER_CYCLE_SIZE); for (i = 1; i < xheads; i++) { crc = crc32c(crc, &xhdr[i].hic_xheader, sizeof(struct xlog_rec_ext_header)); } } /* ... and finally for the payload */ crc = crc32c(crc, dp, size); return xfs_end_cksum(crc); } static void xlog_bio_end_io( struct bio *bio) { struct xlog_in_core *iclog = bio->bi_private; queue_work(iclog->ic_log->l_ioend_workqueue, &iclog->ic_end_io_work); } STATIC void xlog_write_iclog( struct xlog *log, struct xlog_in_core *iclog, uint64_t bno, unsigned int count) { ASSERT(bno < log->l_logBBsize); trace_xlog_iclog_write(iclog, _RET_IP_); /* * We lock the iclogbufs here so that we can serialise against I/O * completion during unmount. We might be processing a shutdown * triggered during unmount, and that can occur asynchronously to the * unmount thread, and hence we need to ensure that completes before * tearing down the iclogbufs. Hence we need to hold the buffer lock * across the log IO to archieve that. */ down(&iclog->ic_sema); if (xlog_is_shutdown(log)) { /* * It would seem logical to return EIO here, but we rely on * the log state machine to propagate I/O errors instead of * doing it here. We kick of the state machine and unlock * the buffer manually, the code needs to be kept in sync * with the I/O completion path. */ goto sync; } /* * We use REQ_SYNC | REQ_IDLE here to tell the block layer the are more * IOs coming immediately after this one. This prevents the block layer * writeback throttle from throttling log writes behind background * metadata writeback and causing priority inversions. */ bio_init(&iclog->ic_bio, log->l_targ->bt_bdev, iclog->ic_bvec, howmany(count, PAGE_SIZE), REQ_OP_WRITE | REQ_META | REQ_SYNC | REQ_IDLE); iclog->ic_bio.bi_iter.bi_sector = log->l_logBBstart + bno; iclog->ic_bio.bi_end_io = xlog_bio_end_io; iclog->ic_bio.bi_private = iclog; if (iclog->ic_flags & XLOG_ICL_NEED_FLUSH) { iclog->ic_bio.bi_opf |= REQ_PREFLUSH; /* * For external log devices, we also need to flush the data * device cache first to ensure all metadata writeback covered * by the LSN in this iclog is on stable storage. This is slow, * but it *must* complete before we issue the external log IO. * * If the flush fails, we cannot conclude that past metadata * writeback from the log succeeded. Repeating the flush is * not possible, hence we must shut down with log IO error to * avoid shutdown re-entering this path and erroring out again. */ if (log->l_targ != log->l_mp->m_ddev_targp && blkdev_issue_flush(log->l_mp->m_ddev_targp->bt_bdev)) goto shutdown; } if (iclog->ic_flags & XLOG_ICL_NEED_FUA) iclog->ic_bio.bi_opf |= REQ_FUA; iclog->ic_flags &= ~(XLOG_ICL_NEED_FLUSH | XLOG_ICL_NEED_FUA); if (is_vmalloc_addr(iclog->ic_data)) { if (!bio_add_vmalloc(&iclog->ic_bio, iclog->ic_data, count)) goto shutdown; } else { bio_add_virt_nofail(&iclog->ic_bio, iclog->ic_data, count); } /* * If this log buffer would straddle the end of the log we will have * to split it up into two bios, so that we can continue at the start. */ if (bno + BTOBB(count) > log->l_logBBsize) { struct bio *split; split = bio_split(&iclog->ic_bio, log->l_logBBsize - bno, GFP_NOIO, &fs_bio_set); bio_chain(split, &iclog->ic_bio); submit_bio(split); /* restart at logical offset zero for the remainder */ iclog->ic_bio.bi_iter.bi_sector = log->l_logBBstart; } submit_bio(&iclog->ic_bio); return; shutdown: xlog_force_shutdown(log, SHUTDOWN_LOG_IO_ERROR); sync: xlog_state_done_syncing(iclog); up(&iclog->ic_sema); } /* * We need to bump cycle number for the part of the iclog that is * written to the start of the log. Watch out for the header magic * number case, though. */ static void xlog_split_iclog( struct xlog *log, void *data, uint64_t bno, unsigned int count) { unsigned int split_offset = BBTOB(log->l_logBBsize - bno); unsigned int i; for (i = split_offset; i < count; i += BBSIZE) { uint32_t cycle = get_unaligned_be32(data + i); if (++cycle == XLOG_HEADER_MAGIC_NUM) cycle++; put_unaligned_be32(cycle, data + i); } } static int xlog_calc_iclog_size( struct xlog *log, struct xlog_in_core *iclog, uint32_t *roundoff) { uint32_t count_init, count; /* Add for LR header */ count_init = log->l_iclog_hsize + iclog->ic_offset; count = roundup(count_init, log->l_iclog_roundoff); *roundoff = count - count_init; ASSERT(count >= count_init); ASSERT(*roundoff < log->l_iclog_roundoff); return count; } /* * Flush out the in-core log (iclog) to the on-disk log in an asynchronous * fashion. Previously, we should have moved the current iclog * ptr in the log to point to the next available iclog. This allows further * write to continue while this code syncs out an iclog ready to go. * Before an in-core log can be written out, the data section must be scanned * to save away the 1st word of each BBSIZE block into the header. We replace * it with the current cycle count. Each BBSIZE block is tagged with the * cycle count because there in an implicit assumption that drives will * guarantee that entire 512 byte blocks get written at once. In other words, * we can't have part of a 512 byte block written and part not written. By * tagging each block, we will know which blocks are valid when recovering * after an unclean shutdown. * * This routine is single threaded on the iclog. No other thread can be in * this routine with the same iclog. Changing contents of iclog can there- * fore be done without grabbing the state machine lock. Updating the global * log will require grabbing the lock though. * * The entire log manager uses a logical block numbering scheme. Only * xlog_write_iclog knows about the fact that the log may not start with * block zero on a given device. */ STATIC void xlog_sync( struct xlog *log, struct xlog_in_core *iclog, struct xlog_ticket *ticket) { unsigned int count; /* byte count of bwrite */ unsigned int roundoff; /* roundoff to BB or stripe */ uint64_t bno; unsigned int size; ASSERT(atomic_read(&iclog->ic_refcnt) == 0); trace_xlog_iclog_sync(iclog, _RET_IP_); count = xlog_calc_iclog_size(log, iclog, &roundoff); /* * If we have a ticket, account for the roundoff via the ticket * reservation to avoid touching the hot grant heads needlessly. * Otherwise, we have to move grant heads directly. */ if (ticket) { ticket->t_curr_res -= roundoff; } else { xlog_grant_add_space(&log->l_reserve_head, roundoff); xlog_grant_add_space(&log->l_write_head, roundoff); } /* put cycle number in every block */ xlog_pack_data(log, iclog, roundoff); /* real byte length */ size = iclog->ic_offset; if (xfs_has_logv2(log->l_mp)) size += roundoff; iclog->ic_header.h_len = cpu_to_be32(size); XFS_STATS_INC(log->l_mp, xs_log_writes); XFS_STATS_ADD(log->l_mp, xs_log_blocks, BTOBB(count)); bno = BLOCK_LSN(be64_to_cpu(iclog->ic_header.h_lsn)); /* Do we need to split this write into 2 parts? */ if (bno + BTOBB(count) > log->l_logBBsize) xlog_split_iclog(log, &iclog->ic_header, bno, count); /* calculcate the checksum */ iclog->ic_header.h_crc = xlog_cksum(log, &iclog->ic_header, iclog->ic_datap, size); /* * Intentionally corrupt the log record CRC based on the error injection * frequency, if defined. This facilitates testing log recovery in the * event of torn writes. Hence, set the IOABORT state to abort the log * write on I/O completion and shutdown the fs. The subsequent mount * detects the bad CRC and attempts to recover. */ #ifdef DEBUG if (XFS_TEST_ERROR(false, log->l_mp, XFS_ERRTAG_LOG_BAD_CRC)) { iclog->ic_header.h_crc &= cpu_to_le32(0xAAAAAAAA); iclog->ic_fail_crc = true; xfs_warn(log->l_mp, "Intentionally corrupted log record at LSN 0x%llx. Shutdown imminent.", be64_to_cpu(iclog->ic_header.h_lsn)); } #endif xlog_verify_iclog(log, iclog, count); xlog_write_iclog(log, iclog, bno, count); } /* * Deallocate a log structure */ STATIC void xlog_dealloc_log( struct xlog *log) { xlog_in_core_t *iclog, *next_iclog; int i; /* * Destroy the CIL after waiting for iclog IO completion because an * iclog EIO error will try to shut down the log, which accesses the * CIL to wake up the waiters. */ xlog_cil_destroy(log); iclog = log->l_iclog; for (i = 0; i < log->l_iclog_bufs; i++) { next_iclog = iclog->ic_next; kvfree(iclog->ic_data); kfree(iclog); iclog = next_iclog; } log->l_mp->m_log = NULL; destroy_workqueue(log->l_ioend_workqueue); kfree(log); } /* * Update counters atomically now that memcpy is done. */ static inline void xlog_state_finish_copy( struct xlog *log, struct xlog_in_core *iclog, int record_cnt, int copy_bytes) { lockdep_assert_held(&log->l_icloglock); be32_add_cpu(&iclog->ic_header.h_num_logops, record_cnt); iclog->ic_offset += copy_bytes; } /* * print out info relating to regions written which consume * the reservation */ void xlog_print_tic_res( struct xfs_mount *mp, struct xlog_ticket *ticket) { xfs_warn(mp, "ticket reservation summary:"); xfs_warn(mp, " unit res = %d bytes", ticket->t_unit_res); xfs_warn(mp, " current res = %d bytes", ticket->t_curr_res); xfs_warn(mp, " original count = %d", ticket->t_ocnt); xfs_warn(mp, " remaining count = %d", ticket->t_cnt); } /* * Print a summary of the transaction. */ void xlog_print_trans( struct xfs_trans *tp) { struct xfs_mount *mp = tp->t_mountp; struct xfs_log_item *lip; /* dump core transaction and ticket info */ xfs_warn(mp, "transaction summary:"); xfs_warn(mp, " log res = %d", tp->t_log_res); xfs_warn(mp, " log count = %d", tp->t_log_count); xfs_warn(mp, " flags = 0x%x", tp->t_flags); xlog_print_tic_res(mp, tp->t_ticket); /* dump each log item */ list_for_each_entry(lip, &tp->t_items, li_trans) { struct xfs_log_vec *lv = lip->li_lv; struct xfs_log_iovec *vec; int i; xfs_warn(mp, "log item: "); xfs_warn(mp, " type = 0x%x", lip->li_type); xfs_warn(mp, " flags = 0x%lx", lip->li_flags); if (!lv) continue; xfs_warn(mp, " niovecs = %d", lv->lv_niovecs); xfs_warn(mp, " alloc_size = %d", lv->lv_alloc_size); xfs_warn(mp, " bytes = %d", lv->lv_bytes); xfs_warn(mp, " buf used= %d", lv->lv_buf_used); /* dump each iovec for the log item */ vec = lv->lv_iovecp; for (i = 0; i < lv->lv_niovecs; i++) { int dumplen = min(vec->i_len, 32); xfs_warn(mp, " iovec[%d]", i); xfs_warn(mp, " type = 0x%x", vec->i_type); xfs_warn(mp, " len = %d", vec->i_len); xfs_warn(mp, " first %d bytes of iovec[%d]:", dumplen, i); xfs_hex_dump(vec->i_addr, dumplen); vec++; } } } static inline void xlog_write_iovec( struct xlog_in_core *iclog, uint32_t *log_offset, void *data, uint32_t write_len, int *bytes_left, uint32_t *record_cnt, uint32_t *data_cnt) { ASSERT(*log_offset < iclog->ic_log->l_iclog_size); ASSERT(*log_offset % sizeof(int32_t) == 0); ASSERT(write_len % sizeof(int32_t) == 0); memcpy(iclog->ic_datap + *log_offset, data, write_len); *log_offset += write_len; *bytes_left -= write_len; (*record_cnt)++; *data_cnt += write_len; } /* * Write log vectors into a single iclog which is guaranteed by the caller * to have enough space to write the entire log vector into. */ static void xlog_write_full( struct xfs_log_vec *lv, struct xlog_ticket *ticket, struct xlog_in_core *iclog, uint32_t *log_offset, uint32_t *len, uint32_t *record_cnt, uint32_t *data_cnt) { int index; ASSERT(*log_offset + *len <= iclog->ic_size || iclog->ic_state == XLOG_STATE_WANT_SYNC); /* * Ordered log vectors have no regions to write so this * loop will naturally skip them. */ for (index = 0; index < lv->lv_niovecs; index++) { struct xfs_log_iovec *reg = &lv->lv_iovecp[index]; struct xlog_op_header *ophdr = reg->i_addr; ophdr->oh_tid = cpu_to_be32(ticket->t_tid); xlog_write_iovec(iclog, log_offset, reg->i_addr, reg->i_len, len, record_cnt, data_cnt); } } static int xlog_write_get_more_iclog_space( struct xlog_ticket *ticket, struct xlog_in_core **iclogp, uint32_t *log_offset, uint32_t len, uint32_t *record_cnt, uint32_t *data_cnt) { struct xlog_in_core *iclog = *iclogp; struct xlog *log = iclog->ic_log; int error; spin_lock(&log->l_icloglock); ASSERT(iclog->ic_state == XLOG_STATE_WANT_SYNC); xlog_state_finish_copy(log, iclog, *record_cnt, *data_cnt); error = xlog_state_release_iclog(log, iclog, ticket); spin_unlock(&log->l_icloglock); if (error) return error; error = xlog_state_get_iclog_space(log, len, &iclog, ticket, log_offset); if (error) return error; *record_cnt = 0; *data_cnt = 0; *iclogp = iclog; return 0; } /* * Write log vectors into a single iclog which is smaller than the current chain * length. We write until we cannot fit a full record into the remaining space * and then stop. We return the log vector that is to be written that cannot * wholly fit in the iclog. */ static int xlog_write_partial( struct xfs_log_vec *lv, struct xlog_ticket *ticket, struct xlog_in_core **iclogp, uint32_t *log_offset, uint32_t *len, uint32_t *record_cnt, uint32_t *data_cnt) { struct xlog_in_core *iclog = *iclogp; struct xlog_op_header *ophdr; int index = 0; uint32_t rlen; int error; /* walk the logvec, copying until we run out of space in the iclog */ for (index = 0; index < lv->lv_niovecs; index++) { struct xfs_log_iovec *reg = &lv->lv_iovecp[index]; uint32_t reg_offset = 0; /* * The first region of a continuation must have a non-zero * length otherwise log recovery will just skip over it and * start recovering from the next opheader it finds. Because we * mark the next opheader as a continuation, recovery will then * incorrectly add the continuation to the previous region and * that breaks stuff. * * Hence if there isn't space for region data after the * opheader, then we need to start afresh with a new iclog. */ if (iclog->ic_size - *log_offset <= sizeof(struct xlog_op_header)) { error = xlog_write_get_more_iclog_space(ticket, &iclog, log_offset, *len, record_cnt, data_cnt); if (error) return error; } ophdr = reg->i_addr; rlen = min_t(uint32_t, reg->i_len, iclog->ic_size - *log_offset); ophdr->oh_tid = cpu_to_be32(ticket->t_tid); ophdr->oh_len = cpu_to_be32(rlen - sizeof(struct xlog_op_header)); if (rlen != reg->i_len) ophdr->oh_flags |= XLOG_CONTINUE_TRANS; xlog_write_iovec(iclog, log_offset, reg->i_addr, rlen, len, record_cnt, data_cnt); /* If we wrote the whole region, move to the next. */ if (rlen == reg->i_len) continue; /* * We now have a partially written iovec, but it can span * multiple iclogs so we loop here. First we release the iclog * we currently have, then we get a new iclog and add a new * opheader. Then we continue copying from where we were until * we either complete the iovec or fill the iclog. If we * complete the iovec, then we increment the index and go right * back to the top of the outer loop. if we fill the iclog, we * run the inner loop again. * * This is complicated by the tail of a region using all the * space in an iclog and hence requiring us to release the iclog * and get a new one before returning to the outer loop. We must * always guarantee that we exit this inner loop with at least * space for log transaction opheaders left in the current * iclog, hence we cannot just terminate the loop at the end * of the of the continuation. So we loop while there is no * space left in the current iclog, and check for the end of the * continuation after getting a new iclog. */ do { /* * Ensure we include the continuation opheader in the * space we need in the new iclog by adding that size * to the length we require. This continuation opheader * needs to be accounted to the ticket as the space it * consumes hasn't been accounted to the lv we are * writing. */ error = xlog_write_get_more_iclog_space(ticket, &iclog, log_offset, *len + sizeof(struct xlog_op_header), record_cnt, data_cnt); if (error) return error; ophdr = iclog->ic_datap + *log_offset; ophdr->oh_tid = cpu_to_be32(ticket->t_tid); ophdr->oh_clientid = XFS_TRANSACTION; ophdr->oh_res2 = 0; ophdr->oh_flags = XLOG_WAS_CONT_TRANS; ticket->t_curr_res -= sizeof(struct xlog_op_header); *log_offset += sizeof(struct xlog_op_header); *data_cnt += sizeof(struct xlog_op_header); /* * If rlen fits in the iclog, then end the region * continuation. Otherwise we're going around again. */ reg_offset += rlen; rlen = reg->i_len - reg_offset; if (rlen <= iclog->ic_size - *log_offset) ophdr->oh_flags |= XLOG_END_TRANS; else ophdr->oh_flags |= XLOG_CONTINUE_TRANS; rlen = min_t(uint32_t, rlen, iclog->ic_size - *log_offset); ophdr->oh_len = cpu_to_be32(rlen); xlog_write_iovec(iclog, log_offset, reg->i_addr + reg_offset, rlen, len, record_cnt, data_cnt); } while (ophdr->oh_flags & XLOG_CONTINUE_TRANS); } /* * No more iovecs remain in this logvec so return the next log vec to * the caller so it can go back to fast path copying. */ *iclogp = iclog; return 0; } /* * Write some region out to in-core log * * This will be called when writing externally provided regions or when * writing out a commit record for a given transaction. * * General algorithm: * 1. Find total length of this write. This may include adding to the * lengths passed in. * 2. Check whether we violate the tickets reservation. * 3. While writing to this iclog * A. Reserve as much space in this iclog as can get * B. If this is first write, save away start lsn * C. While writing this region: * 1. If first write of transaction, write start record * 2. Write log operation header (header per region) * 3. Find out if we can fit entire region into this iclog * 4. Potentially, verify destination memcpy ptr * 5. Memcpy (partial) region * 6. If partial copy, release iclog; otherwise, continue * copying more regions into current iclog * 4. Mark want sync bit (in simulation mode) * 5. Release iclog for potential flush to on-disk log. * * ERRORS: * 1. Panic if reservation is overrun. This should never happen since * reservation amounts are generated internal to the filesystem. * NOTES: * 1. Tickets are single threaded data structures. * 2. The XLOG_END_TRANS & XLOG_CONTINUE_TRANS flags are passed down to the * syncing routine. When a single log_write region needs to span * multiple in-core logs, the XLOG_CONTINUE_TRANS bit should be set * on all log operation writes which don't contain the end of the * region. The XLOG_END_TRANS bit is used for the in-core log * operation which contains the end of the continued log_write region. * 3. When xlog_state_get_iclog_space() grabs the rest of the current iclog, * we don't really know exactly how much space will be used. As a result, * we don't update ic_offset until the end when we know exactly how many * bytes have been written out. */ int xlog_write( struct xlog *log, struct xfs_cil_ctx *ctx, struct list_head *lv_chain, struct xlog_ticket *ticket, uint32_t len) { struct xlog_in_core *iclog = NULL; struct xfs_log_vec *lv; uint32_t record_cnt = 0; uint32_t data_cnt = 0; int error = 0; int log_offset; if (ticket->t_curr_res < 0) { xfs_alert_tag(log->l_mp, XFS_PTAG_LOGRES, "ctx ticket reservation ran out. Need to up reservation"); xlog_print_tic_res(log->l_mp, ticket); xlog_force_shutdown(log, SHUTDOWN_LOG_IO_ERROR); } error = xlog_state_get_iclog_space(log, len, &iclog, ticket, &log_offset); if (error) return error; ASSERT(log_offset <= iclog->ic_size - 1); /* * If we have a context pointer, pass it the first iclog we are * writing to so it can record state needed for iclog write * ordering. */ if (ctx) xlog_cil_set_ctx_write_state(ctx, iclog); list_for_each_entry(lv, lv_chain, lv_list) { /* * If the entire log vec does not fit in the iclog, punt it to * the partial copy loop which can handle this case. */ if (lv->lv_niovecs && lv->lv_bytes > iclog->ic_size - log_offset) { error = xlog_write_partial(lv, ticket, &iclog, &log_offset, &len, &record_cnt, &data_cnt); if (error) { /* * We have no iclog to release, so just return * the error immediately. */ return error; } } else { xlog_write_full(lv, ticket, iclog, &log_offset, &len, &record_cnt, &data_cnt); } } ASSERT(len == 0); /* * We've already been guaranteed that the last writes will fit inside * the current iclog, and hence it will already have the space used by * those writes accounted to it. Hence we do not need to update the * iclog with the number of bytes written here. */ spin_lock(&log->l_icloglock); xlog_state_finish_copy(log, iclog, record_cnt, 0); error = xlog_state_release_iclog(log, iclog, ticket); spin_unlock(&log->l_icloglock); return error; } static void xlog_state_activate_iclog( struct xlog_in_core *iclog, int *iclogs_changed) { ASSERT(list_empty_careful(&iclog->ic_callbacks)); trace_xlog_iclog_activate(iclog, _RET_IP_); /* * If the number of ops in this iclog indicate it just contains the * dummy transaction, we can change state into IDLE (the second time * around). Otherwise we should change the state into NEED a dummy. * We don't need to cover the dummy. */ if (*iclogs_changed == 0 && iclog->ic_header.h_num_logops == cpu_to_be32(XLOG_COVER_OPS)) { *iclogs_changed = 1; } else { /* * We have two dirty iclogs so start over. This could also be * num of ops indicating this is not the dummy going out. */ *iclogs_changed = 2; } iclog->ic_state = XLOG_STATE_ACTIVE; iclog->ic_offset = 0; iclog->ic_header.h_num_logops = 0; memset(iclog->ic_header.h_cycle_data, 0, sizeof(iclog->ic_header.h_cycle_data)); iclog->ic_header.h_lsn = 0; iclog->ic_header.h_tail_lsn = 0; } /* * Loop through all iclogs and mark all iclogs currently marked DIRTY as * ACTIVE after iclog I/O has completed. */ static void xlog_state_activate_iclogs( struct xlog *log, int *iclogs_changed) { struct xlog_in_core *iclog = log->l_iclog; do { if (iclog->ic_state == XLOG_STATE_DIRTY) xlog_state_activate_iclog(iclog, iclogs_changed); /* * The ordering of marking iclogs ACTIVE must be maintained, so * an iclog doesn't become ACTIVE beyond one that is SYNCING. */ else if (iclog->ic_state != XLOG_STATE_ACTIVE) break; } while ((iclog = iclog->ic_next) != log->l_iclog); } static int xlog_covered_state( int prev_state, int iclogs_changed) { /* * We go to NEED for any non-covering writes. We go to NEED2 if we just * wrote the first covering record (DONE). We go to IDLE if we just * wrote the second covering record (DONE2) and remain in IDLE until a * non-covering write occurs. */ switch (prev_state) { case XLOG_STATE_COVER_IDLE: if (iclogs_changed == 1) return XLOG_STATE_COVER_IDLE; fallthrough; case XLOG_STATE_COVER_NEED: case XLOG_STATE_COVER_NEED2: break; case XLOG_STATE_COVER_DONE: if (iclogs_changed == 1) return XLOG_STATE_COVER_NEED2; break; case XLOG_STATE_COVER_DONE2: if (iclogs_changed == 1) return XLOG_STATE_COVER_IDLE; break; default: ASSERT(0); } return XLOG_STATE_COVER_NEED; } STATIC void xlog_state_clean_iclog( struct xlog *log, struct xlog_in_core *dirty_iclog) { int iclogs_changed = 0; trace_xlog_iclog_clean(dirty_iclog, _RET_IP_); dirty_iclog->ic_state = XLOG_STATE_DIRTY; xlog_state_activate_iclogs(log, &iclogs_changed); wake_up_all(&dirty_iclog->ic_force_wait); if (iclogs_changed) { log->l_covered_state = xlog_covered_state(log->l_covered_state, iclogs_changed); } } STATIC xfs_lsn_t xlog_get_lowest_lsn( struct xlog *log) { struct xlog_in_core *iclog = log->l_iclog; xfs_lsn_t lowest_lsn = 0, lsn; do { if (iclog->ic_state == XLOG_STATE_ACTIVE || iclog->ic_state == XLOG_STATE_DIRTY) continue; lsn = be64_to_cpu(iclog->ic_header.h_lsn); if ((lsn && !lowest_lsn) || XFS_LSN_CMP(lsn, lowest_lsn) < 0) lowest_lsn = lsn; } while ((iclog = iclog->ic_next) != log->l_iclog); return lowest_lsn; } /* * Return true if we need to stop processing, false to continue to the next * iclog. The caller will need to run callbacks if the iclog is returned in the * XLOG_STATE_CALLBACK state. */ static bool xlog_state_iodone_process_iclog( struct xlog *log, struct xlog_in_core *iclog) { xfs_lsn_t lowest_lsn; xfs_lsn_t header_lsn; switch (iclog->ic_state) { case XLOG_STATE_ACTIVE: case XLOG_STATE_DIRTY: /* * Skip all iclogs in the ACTIVE & DIRTY states: */ return false; case XLOG_STATE_DONE_SYNC: /* * Now that we have an iclog that is in the DONE_SYNC state, do * one more check here to see if we have chased our tail around. * If this is not the lowest lsn iclog, then we will leave it * for another completion to process. */ header_lsn = be64_to_cpu(iclog->ic_header.h_lsn); lowest_lsn = xlog_get_lowest_lsn(log); if (lowest_lsn && XFS_LSN_CMP(lowest_lsn, header_lsn) < 0) return false; /* * If there are no callbacks on this iclog, we can mark it clean * immediately and return. Otherwise we need to run the * callbacks. */ if (list_empty(&iclog->ic_callbacks)) { xlog_state_clean_iclog(log, iclog); return false; } trace_xlog_iclog_callback(iclog, _RET_IP_); iclog->ic_state = XLOG_STATE_CALLBACK; return false; default: /* * Can only perform callbacks in order. Since this iclog is not * in the DONE_SYNC state, we skip the rest and just try to * clean up. */ return true; } } /* * Loop over all the iclogs, running attached callbacks on them. Return true if * we ran any callbacks, indicating that we dropped the icloglock. We don't need * to handle transient shutdown state here at all because * xlog_state_shutdown_callbacks() will be run to do the necessary shutdown * cleanup of the callbacks. */ static bool xlog_state_do_iclog_callbacks( struct xlog *log) __releases(&log->l_icloglock) __acquires(&log->l_icloglock) { struct xlog_in_core *first_iclog = log->l_iclog; struct xlog_in_core *iclog = first_iclog; bool ran_callback = false; do { LIST_HEAD(cb_list); if (xlog_state_iodone_process_iclog(log, iclog)) break; if (iclog->ic_state != XLOG_STATE_CALLBACK) { iclog = iclog->ic_next; continue; } list_splice_init(&iclog->ic_callbacks, &cb_list); spin_unlock(&log->l_icloglock); trace_xlog_iclog_callbacks_start(iclog, _RET_IP_); xlog_cil_process_committed(&cb_list); trace_xlog_iclog_callbacks_done(iclog, _RET_IP_); ran_callback = true; spin_lock(&log->l_icloglock); xlog_state_clean_iclog(log, iclog); iclog = iclog->ic_next; } while (iclog != first_iclog); return ran_callback; } /* * Loop running iclog completion callbacks until there are no more iclogs in a * state that can run callbacks. */ STATIC void xlog_state_do_callback( struct xlog *log) { int flushcnt = 0; int repeats = 0; spin_lock(&log->l_icloglock); while (xlog_state_do_iclog_callbacks(log)) { if (xlog_is_shutdown(log)) break; if (++repeats > 5000) { flushcnt += repeats; repeats = 0; xfs_warn(log->l_mp, "%s: possible infinite loop (%d iterations)", __func__, flushcnt); } } if (log->l_iclog->ic_state == XLOG_STATE_ACTIVE) wake_up_all(&log->l_flush_wait); spin_unlock(&log->l_icloglock); } /* * Finish transitioning this iclog to the dirty state. * * Callbacks could take time, so they are done outside the scope of the * global state machine log lock. */ STATIC void xlog_state_done_syncing( struct xlog_in_core *iclog) { struct xlog *log = iclog->ic_log; spin_lock(&log->l_icloglock); ASSERT(atomic_read(&iclog->ic_refcnt) == 0); trace_xlog_iclog_sync_done(iclog, _RET_IP_); /* * If we got an error, either on the first buffer, or in the case of * split log writes, on the second, we shut down the file system and * no iclogs should ever be attempted to be written to disk again. */ if (!xlog_is_shutdown(log)) { ASSERT(iclog->ic_state == XLOG_STATE_SYNCING); iclog->ic_state = XLOG_STATE_DONE_SYNC; } /* * Someone could be sleeping prior to writing out the next * iclog buffer, we wake them all, one will get to do the * I/O, the others get to wait for the result. */ wake_up_all(&iclog->ic_write_wait); spin_unlock(&log->l_icloglock); xlog_state_do_callback(log); } /* * If the head of the in-core log ring is not (ACTIVE or DIRTY), then we must * sleep. We wait on the flush queue on the head iclog as that should be * the first iclog to complete flushing. Hence if all iclogs are syncing, * we will wait here and all new writes will sleep until a sync completes. * * The in-core logs are used in a circular fashion. They are not used * out-of-order even when an iclog past the head is free. * * return: * * log_offset where xlog_write() can start writing into the in-core * log's data space. * * in-core log pointer to which xlog_write() should write. * * boolean indicating this is a continued write to an in-core log. * If this is the last write, then the in-core log's offset field * needs to be incremented, depending on the amount of data which * is copied. */ STATIC int xlog_state_get_iclog_space( struct xlog *log, int len, struct xlog_in_core **iclogp, struct xlog_ticket *ticket, int *logoffsetp) { int log_offset; xlog_rec_header_t *head; xlog_in_core_t *iclog; restart: spin_lock(&log->l_icloglock); if (xlog_is_shutdown(log)) { spin_unlock(&log->l_icloglock); return -EIO; } iclog = log->l_iclog; if (iclog->ic_state != XLOG_STATE_ACTIVE) { XFS_STATS_INC(log->l_mp, xs_log_noiclogs); /* Wait for log writes to have flushed */ xlog_wait(&log->l_flush_wait, &log->l_icloglock); goto restart; } head = &iclog->ic_header; atomic_inc(&iclog->ic_refcnt); /* prevents sync */ log_offset = iclog->ic_offset; trace_xlog_iclog_get_space(iclog, _RET_IP_); /* On the 1st write to an iclog, figure out lsn. This works * if iclogs marked XLOG_STATE_WANT_SYNC always write out what they are * committing to. If the offset is set, that's how many blocks * must be written. */ if (log_offset == 0) { ticket->t_curr_res -= log->l_iclog_hsize; head->h_cycle = cpu_to_be32(log->l_curr_cycle); head->h_lsn = cpu_to_be64( xlog_assign_lsn(log->l_curr_cycle, log->l_curr_block)); ASSERT(log->l_curr_block >= 0); } /* If there is enough room to write everything, then do it. Otherwise, * claim the rest of the region and make sure the XLOG_STATE_WANT_SYNC * bit is on, so this will get flushed out. Don't update ic_offset * until you know exactly how many bytes get copied. Therefore, wait * until later to update ic_offset. * * xlog_write() algorithm assumes that at least 2 xlog_op_header_t's * can fit into remaining data section. */ if (iclog->ic_size - iclog->ic_offset < 2*sizeof(xlog_op_header_t)) { int error = 0; xlog_state_switch_iclogs(log, iclog, iclog->ic_size); /* * If we are the only one writing to this iclog, sync it to * disk. We need to do an atomic compare and decrement here to * avoid racing with concurrent atomic_dec_and_lock() calls in * xlog_state_release_iclog() when there is more than one * reference to the iclog. */ if (!atomic_add_unless(&iclog->ic_refcnt, -1, 1)) error = xlog_state_release_iclog(log, iclog, ticket); spin_unlock(&log->l_icloglock); if (error) return error; goto restart; } /* Do we have enough room to write the full amount in the remainder * of this iclog? Or must we continue a write on the next iclog and * mark this iclog as completely taken? In the case where we switch * iclogs (to mark it taken), this particular iclog will release/sync * to disk in xlog_write(). */ if (len <= iclog->ic_size - iclog->ic_offset) iclog->ic_offset += len; else xlog_state_switch_iclogs(log, iclog, iclog->ic_size); *iclogp = iclog; ASSERT(iclog->ic_offset <= iclog->ic_size); spin_unlock(&log->l_icloglock); *logoffsetp = log_offset; return 0; } /* * The first cnt-1 times a ticket goes through here we don't need to move the * grant write head because the permanent reservation has reserved cnt times the * unit amount. Release part of current permanent unit reservation and reset * current reservation to be one units worth. Also move grant reservation head * forward. */ void xfs_log_ticket_regrant( struct xlog *log, struct xlog_ticket *ticket) { trace_xfs_log_ticket_regrant(log, ticket); if (ticket->t_cnt > 0) ticket->t_cnt--; xlog_grant_sub_space(&log->l_reserve_head, ticket->t_curr_res); xlog_grant_sub_space(&log->l_write_head, ticket->t_curr_res); ticket->t_curr_res = ticket->t_unit_res; trace_xfs_log_ticket_regrant_sub(log, ticket); /* just return if we still have some of the pre-reserved space */ if (!ticket->t_cnt) { xlog_grant_add_space(&log->l_reserve_head, ticket->t_unit_res); trace_xfs_log_ticket_regrant_exit(log, ticket); } xfs_log_ticket_put(ticket); } /* * Give back the space left from a reservation. * * All the information we need to make a correct determination of space left * is present. For non-permanent reservations, things are quite easy. The * count should have been decremented to zero. We only need to deal with the * space remaining in the current reservation part of the ticket. If the * ticket contains a permanent reservation, there may be left over space which * needs to be released. A count of N means that N-1 refills of the current * reservation can be done before we need to ask for more space. The first * one goes to fill up the first current reservation. Once we run out of * space, the count will stay at zero and the only space remaining will be * in the current reservation field. */ void xfs_log_ticket_ungrant( struct xlog *log, struct xlog_ticket *ticket) { int bytes; trace_xfs_log_ticket_ungrant(log, ticket); if (ticket->t_cnt > 0) ticket->t_cnt--; trace_xfs_log_ticket_ungrant_sub(log, ticket); /* * If this is a permanent reservation ticket, we may be able to free * up more space based on the remaining count. */ bytes = ticket->t_curr_res; if (ticket->t_cnt > 0) { ASSERT(ticket->t_flags & XLOG_TIC_PERM_RESERV); bytes += ticket->t_unit_res*ticket->t_cnt; } xlog_grant_sub_space(&log->l_reserve_head, bytes); xlog_grant_sub_space(&log->l_write_head, bytes); trace_xfs_log_ticket_ungrant_exit(log, ticket); xfs_log_space_wake(log->l_mp); xfs_log_ticket_put(ticket); } /* * This routine will mark the current iclog in the ring as WANT_SYNC and move * the current iclog pointer to the next iclog in the ring. */ void xlog_state_switch_iclogs( struct xlog *log, struct xlog_in_core *iclog, int eventual_size) { ASSERT(iclog->ic_state == XLOG_STATE_ACTIVE); assert_spin_locked(&log->l_icloglock); trace_xlog_iclog_switch(iclog, _RET_IP_); if (!eventual_size) eventual_size = iclog->ic_offset; iclog->ic_state = XLOG_STATE_WANT_SYNC; iclog->ic_header.h_prev_block = cpu_to_be32(log->l_prev_block); log->l_prev_block = log->l_curr_block; log->l_prev_cycle = log->l_curr_cycle; /* roll log?: ic_offset changed later */ log->l_curr_block += BTOBB(eventual_size)+BTOBB(log->l_iclog_hsize); /* Round up to next log-sunit */ if (log->l_iclog_roundoff > BBSIZE) { uint32_t sunit_bb = BTOBB(log->l_iclog_roundoff); log->l_curr_block = roundup(log->l_curr_block, sunit_bb); } if (log->l_curr_block >= log->l_logBBsize) { /* * Rewind the current block before the cycle is bumped to make * sure that the combined LSN never transiently moves forward * when the log wraps to the next cycle. This is to support the * unlocked sample of these fields from xlog_valid_lsn(). Most * other cases should acquire l_icloglock. */ log->l_curr_block -= log->l_logBBsize; ASSERT(log->l_curr_block >= 0); smp_wmb(); log->l_curr_cycle++; if (log->l_curr_cycle == XLOG_HEADER_MAGIC_NUM) log->l_curr_cycle++; } ASSERT(iclog == log->l_iclog); log->l_iclog = iclog->ic_next; } /* * Force the iclog to disk and check if the iclog has been completed before * xlog_force_iclog() returns. This can happen on synchronous (e.g. * pmem) or fast async storage because we drop the icloglock to issue the IO. * If completion has already occurred, tell the caller so that it can avoid an * unnecessary wait on the iclog. */ static int xlog_force_and_check_iclog( struct xlog_in_core *iclog, bool *completed) { xfs_lsn_t lsn = be64_to_cpu(iclog->ic_header.h_lsn); int error; *completed = false; error = xlog_force_iclog(iclog); if (error) return error; /* * If the iclog has already been completed and reused the header LSN * will have been rewritten by completion */ if (be64_to_cpu(iclog->ic_header.h_lsn) != lsn) *completed = true; return 0; } /* * Write out all data in the in-core log as of this exact moment in time. * * Data may be written to the in-core log during this call. However, * we don't guarantee this data will be written out. A change from past * implementation means this routine will *not* write out zero length LRs. * * Basically, we try and perform an intelligent scan of the in-core logs. * If we determine there is no flushable data, we just return. There is no * flushable data if: * * 1. the current iclog is active and has no data; the previous iclog * is in the active or dirty state. * 2. the current iclog is dirty, and the previous iclog is in the * active or dirty state. * * We may sleep if: * * 1. the current iclog is not in the active nor dirty state. * 2. the current iclog dirty, and the previous iclog is not in the * active nor dirty state. * 3. the current iclog is active, and there is another thread writing * to this particular iclog. * 4. a) the current iclog is active and has no other writers * b) when we return from flushing out this iclog, it is still * not in the active nor dirty state. */ int xfs_log_force( struct xfs_mount *mp, uint flags) { struct xlog *log = mp->m_log; struct xlog_in_core *iclog; XFS_STATS_INC(mp, xs_log_force); trace_xfs_log_force(mp, 0, _RET_IP_); xlog_cil_force(log); spin_lock(&log->l_icloglock); if (xlog_is_shutdown(log)) goto out_error; iclog = log->l_iclog; trace_xlog_iclog_force(iclog, _RET_IP_); if (iclog->ic_state == XLOG_STATE_DIRTY || (iclog->ic_state == XLOG_STATE_ACTIVE && atomic_read(&iclog->ic_refcnt) == 0 && iclog->ic_offset == 0)) { /* * If the head is dirty or (active and empty), then we need to * look at the previous iclog. * * If the previous iclog is active or dirty we are done. There * is nothing to sync out. Otherwise, we attach ourselves to the * previous iclog and go to sleep. */ iclog = iclog->ic_prev; } else if (iclog->ic_state == XLOG_STATE_ACTIVE) { if (atomic_read(&iclog->ic_refcnt) == 0) { /* We have exclusive access to this iclog. */ bool completed; if (xlog_force_and_check_iclog(iclog, &completed)) goto out_error; if (completed) goto out_unlock; } else { /* * Someone else is still writing to this iclog, so we * need to ensure that when they release the iclog it * gets synced immediately as we may be waiting on it. */ xlog_state_switch_iclogs(log, iclog, 0); } } /* * The iclog we are about to wait on may contain the checkpoint pushed * by the above xlog_cil_force() call, but it may not have been pushed * to disk yet. Like the ACTIVE case above, we need to make sure caches * are flushed when this iclog is written. */ if (iclog->ic_state == XLOG_STATE_WANT_SYNC) iclog->ic_flags |= XLOG_ICL_NEED_FLUSH | XLOG_ICL_NEED_FUA; if (flags & XFS_LOG_SYNC) return xlog_wait_on_iclog(iclog); out_unlock: spin_unlock(&log->l_icloglock); return 0; out_error: spin_unlock(&log->l_icloglock); return -EIO; } /* * Force the log to a specific LSN. * * If an iclog with that lsn can be found: * If it is in the DIRTY state, just return. * If it is in the ACTIVE state, move the in-core log into the WANT_SYNC * state and go to sleep or return. * If it is in any other state, go to sleep or return. * * Synchronous forces are implemented with a wait queue. All callers trying * to force a given lsn to disk must wait on the queue attached to the * specific in-core log. When given in-core log finally completes its write * to disk, that thread will wake up all threads waiting on the queue. */ static int xlog_force_lsn( struct xlog *log, xfs_lsn_t lsn, uint flags, int *log_flushed, bool already_slept) { struct xlog_in_core *iclog; bool completed; spin_lock(&log->l_icloglock); if (xlog_is_shutdown(log)) goto out_error; iclog = log->l_iclog; while (be64_to_cpu(iclog->ic_header.h_lsn) != lsn) { trace_xlog_iclog_force_lsn(iclog, _RET_IP_); iclog = iclog->ic_next; if (iclog == log->l_iclog) goto out_unlock; } switch (iclog->ic_state) { case XLOG_STATE_ACTIVE: /* * We sleep here if we haven't already slept (e.g. this is the * first time we've looked at the correct iclog buf) and the * buffer before us is going to be sync'ed. The reason for this * is that if we are doing sync transactions here, by waiting * for the previous I/O to complete, we can allow a few more * transactions into this iclog before we close it down. * * Otherwise, we mark the buffer WANT_SYNC, and bump up the * refcnt so we can release the log (which drops the ref count). * The state switch keeps new transaction commits from using * this buffer. When the current commits finish writing into * the buffer, the refcount will drop to zero and the buffer * will go out then. */ if (!already_slept && (iclog->ic_prev->ic_state == XLOG_STATE_WANT_SYNC || iclog->ic_prev->ic_state == XLOG_STATE_SYNCING)) { xlog_wait(&iclog->ic_prev->ic_write_wait, &log->l_icloglock); return -EAGAIN; } if (xlog_force_and_check_iclog(iclog, &completed)) goto out_error; if (log_flushed) *log_flushed = 1; if (completed) goto out_unlock; break; case XLOG_STATE_WANT_SYNC: /* * This iclog may contain the checkpoint pushed by the * xlog_cil_force_seq() call, but there are other writers still * accessing it so it hasn't been pushed to disk yet. Like the * ACTIVE case above, we need to make sure caches are flushed * when this iclog is written. */ iclog->ic_flags |= XLOG_ICL_NEED_FLUSH | XLOG_ICL_NEED_FUA; break; default: /* * The entire checkpoint was written by the CIL force and is on * its way to disk already. It will be stable when it * completes, so we don't need to manipulate caches here at all. * We just need to wait for completion if necessary. */ break; } if (flags & XFS_LOG_SYNC) return xlog_wait_on_iclog(iclog); out_unlock: spin_unlock(&log->l_icloglock); return 0; out_error: spin_unlock(&log->l_icloglock); return -EIO; } /* * Force the log to a specific checkpoint sequence. * * First force the CIL so that all the required changes have been flushed to the * iclogs. If the CIL force completed it will return a commit LSN that indicates * the iclog that needs to be flushed to stable storage. If the caller needs * a synchronous log force, we will wait on the iclog with the LSN returned by * xlog_cil_force_seq() to be completed. */ int xfs_log_force_seq( struct xfs_mount *mp, xfs_csn_t seq, uint flags, int *log_flushed) { struct xlog *log = mp->m_log; xfs_lsn_t lsn; int ret; ASSERT(seq != 0); XFS_STATS_INC(mp, xs_log_force); trace_xfs_log_force(mp, seq, _RET_IP_); lsn = xlog_cil_force_seq(log, seq); if (lsn == NULLCOMMITLSN) return 0; ret = xlog_force_lsn(log, lsn, flags, log_flushed, false); if (ret == -EAGAIN) { XFS_STATS_INC(mp, xs_log_force_sleep); ret = xlog_force_lsn(log, lsn, flags, log_flushed, true); } return ret; } /* * Free a used ticket when its refcount falls to zero. */ void xfs_log_ticket_put( struct xlog_ticket *ticket) { ASSERT(atomic_read(&ticket->t_ref) > 0); if (atomic_dec_and_test(&ticket->t_ref)) kmem_cache_free(xfs_log_ticket_cache, ticket); } struct xlog_ticket * xfs_log_ticket_get( struct xlog_ticket *ticket) { ASSERT(atomic_read(&ticket->t_ref) > 0); atomic_inc(&ticket->t_ref); return ticket; } /* * Figure out the total log space unit (in bytes) that would be * required for a log ticket. */ static int xlog_calc_unit_res( struct xlog *log, int unit_bytes, int *niclogs) { int iclog_space; uint num_headers; /* * Permanent reservations have up to 'cnt'-1 active log operations * in the log. A unit in this case is the amount of space for one * of these log operations. Normal reservations have a cnt of 1 * and their unit amount is the total amount of space required. * * The following lines of code account for non-transaction data * which occupy space in the on-disk log. * * Normal form of a transaction is: * <oph><trans-hdr><start-oph><reg1-oph><reg1><reg2-oph>...<commit-oph> * and then there are LR hdrs, split-recs and roundoff at end of syncs. * * We need to account for all the leadup data and trailer data * around the transaction data. * And then we need to account for the worst case in terms of using * more space. * The worst case will happen if: * - the placement of the transaction happens to be such that the * roundoff is at its maximum * - the transaction data is synced before the commit record is synced * i.e. <transaction-data><roundoff> | <commit-rec><roundoff> * Therefore the commit record is in its own Log Record. * This can happen as the commit record is called with its * own region to xlog_write(). * This then means that in the worst case, roundoff can happen for * the commit-rec as well. * The commit-rec is smaller than padding in this scenario and so it is * not added separately. */ /* for trans header */ unit_bytes += sizeof(xlog_op_header_t); unit_bytes += sizeof(xfs_trans_header_t); /* for start-rec */ unit_bytes += sizeof(xlog_op_header_t); /* * for LR headers - the space for data in an iclog is the size minus * the space used for the headers. If we use the iclog size, then we * undercalculate the number of headers required. * * Furthermore - the addition of op headers for split-recs might * increase the space required enough to require more log and op * headers, so take that into account too. * * IMPORTANT: This reservation makes the assumption that if this * transaction is the first in an iclog and hence has the LR headers * accounted to it, then the remaining space in the iclog is * exclusively for this transaction. i.e. if the transaction is larger * than the iclog, it will be the only thing in that iclog. * Fundamentally, this means we must pass the entire log vector to * xlog_write to guarantee this. */ iclog_space = log->l_iclog_size - log->l_iclog_hsize; num_headers = howmany(unit_bytes, iclog_space); /* for split-recs - ophdrs added when data split over LRs */ unit_bytes += sizeof(xlog_op_header_t) * num_headers; /* add extra header reservations if we overrun */ while (!num_headers || howmany(unit_bytes, iclog_space) > num_headers) { unit_bytes += sizeof(xlog_op_header_t); num_headers++; } unit_bytes += log->l_iclog_hsize * num_headers; /* for commit-rec LR header - note: padding will subsume the ophdr */ unit_bytes += log->l_iclog_hsize; /* roundoff padding for transaction data and one for commit record */ unit_bytes += 2 * log->l_iclog_roundoff; if (niclogs) *niclogs = num_headers; return unit_bytes; } int xfs_log_calc_unit_res( struct xfs_mount *mp, int unit_bytes) { return xlog_calc_unit_res(mp->m_log, unit_bytes, NULL); } /* * Allocate and initialise a new log ticket. */ struct xlog_ticket * xlog_ticket_alloc( struct xlog *log, int unit_bytes, int cnt, bool permanent) { struct xlog_ticket *tic; int unit_res; tic = kmem_cache_zalloc(xfs_log_ticket_cache, GFP_KERNEL | __GFP_NOFAIL); unit_res = xlog_calc_unit_res(log, unit_bytes, &tic->t_iclog_hdrs); atomic_set(&tic->t_ref, 1); tic->t_task = current; INIT_LIST_HEAD(&tic->t_queue); tic->t_unit_res = unit_res; tic->t_curr_res = unit_res; tic->t_cnt = cnt; tic->t_ocnt = cnt; tic->t_tid = get_random_u32(); if (permanent) tic->t_flags |= XLOG_TIC_PERM_RESERV; return tic; } #if defined(DEBUG) static void xlog_verify_dump_tail( struct xlog *log, struct xlog_in_core *iclog) { xfs_alert(log->l_mp, "ran out of log space tail 0x%llx/0x%llx, head lsn 0x%llx, head 0x%x/0x%x, prev head 0x%x/0x%x", iclog ? be64_to_cpu(iclog->ic_header.h_tail_lsn) : -1, atomic64_read(&log->l_tail_lsn), log->l_ailp->ail_head_lsn, log->l_curr_cycle, log->l_curr_block, log->l_prev_cycle, log->l_prev_block); xfs_alert(log->l_mp, "write grant 0x%llx, reserve grant 0x%llx, tail_space 0x%llx, size 0x%x, iclog flags 0x%x", atomic64_read(&log->l_write_head.grant), atomic64_read(&log->l_reserve_head.grant), log->l_tail_space, log->l_logsize, iclog ? iclog->ic_flags : -1); } /* Check if the new iclog will fit in the log. */ STATIC void xlog_verify_tail_lsn( struct xlog *log, struct xlog_in_core *iclog) { xfs_lsn_t tail_lsn = be64_to_cpu(iclog->ic_header.h_tail_lsn); int blocks; if (CYCLE_LSN(tail_lsn) == log->l_prev_cycle) { blocks = log->l_logBBsize - (log->l_prev_block - BLOCK_LSN(tail_lsn)); if (blocks < BTOBB(iclog->ic_offset) + BTOBB(log->l_iclog_hsize)) { xfs_emerg(log->l_mp, "%s: ran out of log space", __func__); xlog_verify_dump_tail(log, iclog); } return; } if (CYCLE_LSN(tail_lsn) + 1 != log->l_prev_cycle) { xfs_emerg(log->l_mp, "%s: head has wrapped tail.", __func__); xlog_verify_dump_tail(log, iclog); return; } if (BLOCK_LSN(tail_lsn) == log->l_prev_block) { xfs_emerg(log->l_mp, "%s: tail wrapped", __func__); xlog_verify_dump_tail(log, iclog); return; } blocks = BLOCK_LSN(tail_lsn) - log->l_prev_block; if (blocks < BTOBB(iclog->ic_offset) + 1) { xfs_emerg(log->l_mp, "%s: ran out of iclog space", __func__); xlog_verify_dump_tail(log, iclog); } } /* * Perform a number of checks on the iclog before writing to disk. * * 1. Make sure the iclogs are still circular * 2. Make sure we have a good magic number * 3. Make sure we don't have magic numbers in the data * 4. Check fields of each log operation header for: * A. Valid client identifier * B. tid ptr value falls in valid ptr space (user space code) * C. Length in log record header is correct according to the * individual operation headers within record. * 5. When a bwrite will occur within 5 blocks of the front of the physical * log, check the preceding blocks of the physical log to make sure all * the cycle numbers agree with the current cycle number. */ STATIC void xlog_verify_iclog( struct xlog *log, struct xlog_in_core *iclog, int count) { xlog_op_header_t *ophead; xlog_in_core_t *icptr; xlog_in_core_2_t *xhdr; void *base_ptr, *ptr, *p; ptrdiff_t field_offset; uint8_t clientid; int len, i, j, k, op_len; int idx; /* check validity of iclog pointers */ spin_lock(&log->l_icloglock); icptr = log->l_iclog; for (i = 0; i < log->l_iclog_bufs; i++, icptr = icptr->ic_next) ASSERT(icptr); if (icptr != log->l_iclog) xfs_emerg(log->l_mp, "%s: corrupt iclog ring", __func__); spin_unlock(&log->l_icloglock); /* check log magic numbers */ if (iclog->ic_header.h_magicno != cpu_to_be32(XLOG_HEADER_MAGIC_NUM)) xfs_emerg(log->l_mp, "%s: invalid magic num", __func__); base_ptr = ptr = &iclog->ic_header; p = &iclog->ic_header; for (ptr += BBSIZE; ptr < base_ptr + count; ptr += BBSIZE) { if (*(__be32 *)ptr == cpu_to_be32(XLOG_HEADER_MAGIC_NUM)) xfs_emerg(log->l_mp, "%s: unexpected magic num", __func__); } /* check fields */ len = be32_to_cpu(iclog->ic_header.h_num_logops); base_ptr = ptr = iclog->ic_datap; ophead = ptr; xhdr = iclog->ic_data; for (i = 0; i < len; i++) { ophead = ptr; /* clientid is only 1 byte */ p = &ophead->oh_clientid; field_offset = p - base_ptr; if (field_offset & 0x1ff) { clientid = ophead->oh_clientid; } else { idx = BTOBBT((void *)&ophead->oh_clientid - iclog->ic_datap); if (idx >= (XLOG_HEADER_CYCLE_SIZE / BBSIZE)) { j = idx / (XLOG_HEADER_CYCLE_SIZE / BBSIZE); k = idx % (XLOG_HEADER_CYCLE_SIZE / BBSIZE); clientid = xlog_get_client_id( xhdr[j].hic_xheader.xh_cycle_data[k]); } else { clientid = xlog_get_client_id( iclog->ic_header.h_cycle_data[idx]); } } if (clientid != XFS_TRANSACTION && clientid != XFS_LOG) { xfs_warn(log->l_mp, "%s: op %d invalid clientid %d op "PTR_FMT" offset 0x%lx", __func__, i, clientid, ophead, (unsigned long)field_offset); } /* check length */ p = &ophead->oh_len; field_offset = p - base_ptr; if (field_offset & 0x1ff) { op_len = be32_to_cpu(ophead->oh_len); } else { idx = BTOBBT((void *)&ophead->oh_len - iclog->ic_datap); if (idx >= (XLOG_HEADER_CYCLE_SIZE / BBSIZE)) { j = idx / (XLOG_HEADER_CYCLE_SIZE / BBSIZE); k = idx % (XLOG_HEADER_CYCLE_SIZE / BBSIZE); op_len = be32_to_cpu(xhdr[j].hic_xheader.xh_cycle_data[k]); } else { op_len = be32_to_cpu(iclog->ic_header.h_cycle_data[idx]); } } ptr += sizeof(xlog_op_header_t) + op_len; } } #endif /* * Perform a forced shutdown on the log. * * This can be called from low level log code to trigger a shutdown, or from the * high level mount shutdown code when the mount shuts down. * * Our main objectives here are to make sure that: * a. if the shutdown was not due to a log IO error, flush the logs to * disk. Anything modified after this is ignored. * b. the log gets atomically marked 'XLOG_IO_ERROR' for all interested * parties to find out. Nothing new gets queued after this is done. * c. Tasks sleeping on log reservations, pinned objects and * other resources get woken up. * d. The mount is also marked as shut down so that log triggered shutdowns * still behave the same as if they called xfs_forced_shutdown(). * * Return true if the shutdown cause was a log IO error and we actually shut the * log down. */ bool xlog_force_shutdown( struct xlog *log, uint32_t shutdown_flags) { bool log_error = (shutdown_flags & SHUTDOWN_LOG_IO_ERROR); if (!log) return false; /* * Ensure that there is only ever one log shutdown being processed. * If we allow the log force below on a second pass after shutting * down the log, we risk deadlocking the CIL push as it may require * locks on objects the current shutdown context holds (e.g. taking * buffer locks to abort buffers on last unpin of buf log items). */ if (test_and_set_bit(XLOG_SHUTDOWN_STARTED, &log->l_opstate)) return false; /* * Flush all the completed transactions to disk before marking the log * being shut down. We need to do this first as shutting down the log * before the force will prevent the log force from flushing the iclogs * to disk. * * When we are in recovery, there are no transactions to flush, and * we don't want to touch the log because we don't want to perturb the * current head/tail for future recovery attempts. Hence we need to * avoid a log force in this case. * * If we are shutting down due to a log IO error, then we must avoid * trying to write the log as that may just result in more IO errors and * an endless shutdown/force loop. */ if (!log_error && !xlog_in_recovery(log)) xfs_log_force(log->l_mp, XFS_LOG_SYNC); /* * Atomically set the shutdown state. If the shutdown state is already * set, there someone else is performing the shutdown and so we are done * here. This should never happen because we should only ever get called * once by the first shutdown caller. * * Much of the log state machine transitions assume that shutdown state * cannot change once they hold the log->l_icloglock. Hence we need to * hold that lock here, even though we use the atomic test_and_set_bit() * operation to set the shutdown state. */ spin_lock(&log->l_icloglock); if (test_and_set_bit(XLOG_IO_ERROR, &log->l_opstate)) { spin_unlock(&log->l_icloglock); ASSERT(0); return false; } spin_unlock(&log->l_icloglock); /* * If this log shutdown also sets the mount shutdown state, issue a * shutdown warning message. */ if (!xfs_set_shutdown(log->l_mp)) { xfs_alert_tag(log->l_mp, XFS_PTAG_SHUTDOWN_LOGERROR, "Filesystem has been shut down due to log error (0x%x).", shutdown_flags); xfs_alert(log->l_mp, "Please unmount the filesystem and rectify the problem(s)."); if (xfs_error_level >= XFS_ERRLEVEL_HIGH) xfs_stack_trace(); } /* * We don't want anybody waiting for log reservations after this. That * means we have to wake up everybody queued up on reserveq as well as * writeq. In addition, we make sure in xlog_{re}grant_log_space that * we don't enqueue anything once the SHUTDOWN flag is set, and this * action is protected by the grant locks. */ xlog_grant_head_wake_all(&log->l_reserve_head); xlog_grant_head_wake_all(&log->l_write_head); /* * Wake up everybody waiting on xfs_log_force. Wake the CIL push first * as if the log writes were completed. The abort handling in the log * item committed callback functions will do this again under lock to * avoid races. */ spin_lock(&log->l_cilp->xc_push_lock); wake_up_all(&log->l_cilp->xc_start_wait); wake_up_all(&log->l_cilp->xc_commit_wait); spin_unlock(&log->l_cilp->xc_push_lock); spin_lock(&log->l_icloglock); xlog_state_shutdown_callbacks(log); spin_unlock(&log->l_icloglock); wake_up_var(&log->l_opstate); if (IS_ENABLED(CONFIG_XFS_RT) && xfs_has_zoned(log->l_mp)) xfs_zoned_wake_all(log->l_mp); return log_error; } STATIC int xlog_iclogs_empty( struct xlog *log) { xlog_in_core_t *iclog; iclog = log->l_iclog; do { /* endianness does not matter here, zero is zero in * any language. */ if (iclog->ic_header.h_num_logops) return 0; iclog = iclog->ic_next; } while (iclog != log->l_iclog); return 1; } /* * Verify that an LSN stamped into a piece of metadata is valid. This is * intended for use in read verifiers on v5 superblocks. */ bool xfs_log_check_lsn( struct xfs_mount *mp, xfs_lsn_t lsn) { struct xlog *log = mp->m_log; bool valid; /* * norecovery mode skips mount-time log processing and unconditionally * resets the in-core LSN. We can't validate in this mode, but * modifications are not allowed anyways so just return true. */ if (xfs_has_norecovery(mp)) return true; /* * Some metadata LSNs are initialized to NULL (e.g., the agfl). This is * handled by recovery and thus safe to ignore here. */ if (lsn == NULLCOMMITLSN) return true; valid = xlog_valid_lsn(mp->m_log, lsn); /* warn the user about what's gone wrong before verifier failure */ if (!valid) { spin_lock(&log->l_icloglock); xfs_warn(mp, "Corruption warning: Metadata has LSN (%d:%d) ahead of current LSN (%d:%d). " "Please unmount and run xfs_repair (>= v4.3) to resolve.", CYCLE_LSN(lsn), BLOCK_LSN(lsn), log->l_curr_cycle, log->l_curr_block); spin_unlock(&log->l_icloglock); } return valid; } |
| 15 15 11 12 12 10 2 10 18 1 4 2 4 4 3 2 3 3 2 1 3 7 6 5 4 1 7 1 1 11 11 9 11 8 11 11 11 17 17 16 16 16 14 15 15 15 13 11 11 11 11 11 11 11 11 11 11 11 11 6 6 11 11 11 10 10 2 9 8 9 9 8 2 8 11 2 3 2 2 3 2 2 2 2 11 11 11 2 2 2 5 11 11 10 8 5 5 8 3 3 11 | 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 | /* * Copyright (c) 2007, 2020 Oracle and/or its affiliates. * * 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/pagemap.h> #include <linux/slab.h> #include <linux/rbtree.h> #include <linux/dma-mapping.h> /* for DMA_*_DEVICE */ #include "rds.h" /* * XXX * - build with sparse * - should we detect duplicate keys on a socket? hmm. * - an rdma is an mlock, apply rlimit? */ /* * get the number of pages by looking at the page indices that the start and * end addresses fall in. * * Returns 0 if the vec is invalid. It is invalid if the number of bytes * causes the address to wrap or overflows an unsigned int. This comes * from being stored in the 'length' member of 'struct scatterlist'. */ static unsigned int rds_pages_in_vec(struct rds_iovec *vec) { if ((vec->addr + vec->bytes <= vec->addr) || (vec->bytes > (u64)UINT_MAX)) return 0; return ((vec->addr + vec->bytes + PAGE_SIZE - 1) >> PAGE_SHIFT) - (vec->addr >> PAGE_SHIFT); } static struct rds_mr *rds_mr_tree_walk(struct rb_root *root, u64 key, struct rds_mr *insert) { struct rb_node **p = &root->rb_node; struct rb_node *parent = NULL; struct rds_mr *mr; while (*p) { parent = *p; mr = rb_entry(parent, struct rds_mr, r_rb_node); if (key < mr->r_key) p = &(*p)->rb_left; else if (key > mr->r_key) p = &(*p)->rb_right; else return mr; } if (insert) { rb_link_node(&insert->r_rb_node, parent, p); rb_insert_color(&insert->r_rb_node, root); kref_get(&insert->r_kref); } return NULL; } /* * Destroy the transport-specific part of a MR. */ static void rds_destroy_mr(struct rds_mr *mr) { struct rds_sock *rs = mr->r_sock; void *trans_private = NULL; unsigned long flags; rdsdebug("RDS: destroy mr key is %x refcnt %u\n", mr->r_key, kref_read(&mr->r_kref)); spin_lock_irqsave(&rs->rs_rdma_lock, flags); if (!RB_EMPTY_NODE(&mr->r_rb_node)) rb_erase(&mr->r_rb_node, &rs->rs_rdma_keys); trans_private = mr->r_trans_private; mr->r_trans_private = NULL; spin_unlock_irqrestore(&rs->rs_rdma_lock, flags); if (trans_private) mr->r_trans->free_mr(trans_private, mr->r_invalidate); } void __rds_put_mr_final(struct kref *kref) { struct rds_mr *mr = container_of(kref, struct rds_mr, r_kref); rds_destroy_mr(mr); kfree(mr); } /* * By the time this is called we can't have any more ioctls called on * the socket so we don't need to worry about racing with others. */ void rds_rdma_drop_keys(struct rds_sock *rs) { struct rds_mr *mr; struct rb_node *node; unsigned long flags; /* Release any MRs associated with this socket */ spin_lock_irqsave(&rs->rs_rdma_lock, flags); while ((node = rb_first(&rs->rs_rdma_keys))) { mr = rb_entry(node, struct rds_mr, r_rb_node); if (mr->r_trans == rs->rs_transport) mr->r_invalidate = 0; rb_erase(&mr->r_rb_node, &rs->rs_rdma_keys); RB_CLEAR_NODE(&mr->r_rb_node); spin_unlock_irqrestore(&rs->rs_rdma_lock, flags); kref_put(&mr->r_kref, __rds_put_mr_final); spin_lock_irqsave(&rs->rs_rdma_lock, flags); } spin_unlock_irqrestore(&rs->rs_rdma_lock, flags); if (rs->rs_transport && rs->rs_transport->flush_mrs) rs->rs_transport->flush_mrs(); } /* * Helper function to pin user pages. */ static int rds_pin_pages(unsigned long user_addr, unsigned int nr_pages, struct page **pages, int write) { unsigned int gup_flags = FOLL_LONGTERM; int ret; if (write) gup_flags |= FOLL_WRITE; ret = pin_user_pages_fast(user_addr, nr_pages, gup_flags, pages); if (ret >= 0 && ret < nr_pages) { unpin_user_pages(pages, ret); ret = -EFAULT; } return ret; } static int __rds_rdma_map(struct rds_sock *rs, struct rds_get_mr_args *args, u64 *cookie_ret, struct rds_mr **mr_ret, struct rds_conn_path *cp) { struct rds_mr *mr = NULL, *found; struct scatterlist *sg = NULL; unsigned int nr_pages; struct page **pages = NULL; void *trans_private; unsigned long flags; rds_rdma_cookie_t cookie; unsigned int nents = 0; int need_odp = 0; long i; int ret; if (ipv6_addr_any(&rs->rs_bound_addr) || !rs->rs_transport) { ret = -ENOTCONN; /* XXX not a great errno */ goto out; } if (!rs->rs_transport->get_mr) { ret = -EOPNOTSUPP; goto out; } /* If the combination of the addr and size requested for this memory * region causes an integer overflow, return error. */ if (((args->vec.addr + args->vec.bytes) < args->vec.addr) || PAGE_ALIGN(args->vec.addr + args->vec.bytes) < (args->vec.addr + args->vec.bytes)) { ret = -EINVAL; goto out; } if (!can_do_mlock()) { ret = -EPERM; goto out; } nr_pages = rds_pages_in_vec(&args->vec); if (nr_pages == 0) { ret = -EINVAL; goto out; } /* Restrict the size of mr irrespective of underlying transport * To account for unaligned mr regions, subtract one from nr_pages */ if ((nr_pages - 1) > (RDS_MAX_MSG_SIZE >> PAGE_SHIFT)) { ret = -EMSGSIZE; goto out; } rdsdebug("RDS: get_mr addr %llx len %llu nr_pages %u\n", args->vec.addr, args->vec.bytes, nr_pages); /* XXX clamp nr_pages to limit the size of this alloc? */ pages = kcalloc(nr_pages, sizeof(struct page *), GFP_KERNEL); if (!pages) { ret = -ENOMEM; goto out; } mr = kzalloc(sizeof(struct rds_mr), GFP_KERNEL); if (!mr) { ret = -ENOMEM; goto out; } kref_init(&mr->r_kref); RB_CLEAR_NODE(&mr->r_rb_node); mr->r_trans = rs->rs_transport; mr->r_sock = rs; if (args->flags & RDS_RDMA_USE_ONCE) mr->r_use_once = 1; if (args->flags & RDS_RDMA_INVALIDATE) mr->r_invalidate = 1; if (args->flags & RDS_RDMA_READWRITE) mr->r_write = 1; /* * Pin the pages that make up the user buffer and transfer the page * pointers to the mr's sg array. We check to see if we've mapped * the whole region after transferring the partial page references * to the sg array so that we can have one page ref cleanup path. * * For now we have no flag that tells us whether the mapping is * r/o or r/w. We need to assume r/w, or we'll do a lot of RDMA to * the zero page. */ ret = rds_pin_pages(args->vec.addr, nr_pages, pages, 1); if (ret == -EOPNOTSUPP) { need_odp = 1; } else if (ret <= 0) { goto out; } else { nents = ret; sg = kmalloc_array(nents, sizeof(*sg), GFP_KERNEL); if (!sg) { ret = -ENOMEM; goto out; } WARN_ON(!nents); sg_init_table(sg, nents); /* Stick all pages into the scatterlist */ for (i = 0 ; i < nents; i++) sg_set_page(&sg[i], pages[i], PAGE_SIZE, 0); rdsdebug("RDS: trans_private nents is %u\n", nents); } /* Obtain a transport specific MR. If this succeeds, the * s/g list is now owned by the MR. * Note that dma_map() implies that pending writes are * flushed to RAM, so no dma_sync is needed here. */ trans_private = rs->rs_transport->get_mr( sg, nents, rs, &mr->r_key, cp ? cp->cp_conn : NULL, args->vec.addr, args->vec.bytes, need_odp ? ODP_ZEROBASED : ODP_NOT_NEEDED); if (IS_ERR(trans_private)) { /* In ODP case, we don't GUP pages, so don't need * to release anything. */ if (!need_odp) { unpin_user_pages(pages, nr_pages); kfree(sg); } ret = PTR_ERR(trans_private); /* Trigger connection so that its ready for the next retry */ if (ret == -ENODEV && cp) rds_conn_connect_if_down(cp->cp_conn); goto out; } mr->r_trans_private = trans_private; rdsdebug("RDS: get_mr put_user key is %x cookie_addr %p\n", mr->r_key, (void *)(unsigned long) args->cookie_addr); /* The user may pass us an unaligned address, but we can only * map page aligned regions. So we keep the offset, and build * a 64bit cookie containing <R_Key, offset> and pass that * around. */ if (need_odp) cookie = rds_rdma_make_cookie(mr->r_key, 0); else cookie = rds_rdma_make_cookie(mr->r_key, args->vec.addr & ~PAGE_MASK); if (cookie_ret) *cookie_ret = cookie; if (args->cookie_addr && put_user(cookie, (u64 __user *)(unsigned long)args->cookie_addr)) { if (!need_odp) { unpin_user_pages(pages, nr_pages); kfree(sg); } ret = -EFAULT; goto out; } /* Inserting the new MR into the rbtree bumps its * reference count. */ spin_lock_irqsave(&rs->rs_rdma_lock, flags); found = rds_mr_tree_walk(&rs->rs_rdma_keys, mr->r_key, mr); spin_unlock_irqrestore(&rs->rs_rdma_lock, flags); BUG_ON(found && found != mr); rdsdebug("RDS: get_mr key is %x\n", mr->r_key); if (mr_ret) { kref_get(&mr->r_kref); *mr_ret = mr; } ret = 0; out: kfree(pages); if (mr) kref_put(&mr->r_kref, __rds_put_mr_final); return ret; } int rds_get_mr(struct rds_sock *rs, sockptr_t optval, int optlen) { struct rds_get_mr_args args; if (optlen != sizeof(struct rds_get_mr_args)) return -EINVAL; if (copy_from_sockptr(&args, optval, sizeof(struct rds_get_mr_args))) return -EFAULT; return __rds_rdma_map(rs, &args, NULL, NULL, NULL); } int rds_get_mr_for_dest(struct rds_sock *rs, sockptr_t optval, int optlen) { struct rds_get_mr_for_dest_args args; struct rds_get_mr_args new_args; if (optlen != sizeof(struct rds_get_mr_for_dest_args)) return -EINVAL; if (copy_from_sockptr(&args, optval, sizeof(struct rds_get_mr_for_dest_args))) return -EFAULT; /* * Initially, just behave like get_mr(). * TODO: Implement get_mr as wrapper around this * and deprecate it. */ new_args.vec = args.vec; new_args.cookie_addr = args.cookie_addr; new_args.flags = args.flags; return __rds_rdma_map(rs, &new_args, NULL, NULL, NULL); } /* * Free the MR indicated by the given R_Key */ int rds_free_mr(struct rds_sock *rs, sockptr_t optval, int optlen) { struct rds_free_mr_args args; struct rds_mr *mr; unsigned long flags; if (optlen != sizeof(struct rds_free_mr_args)) return -EINVAL; if (copy_from_sockptr(&args, optval, sizeof(struct rds_free_mr_args))) return -EFAULT; /* Special case - a null cookie means flush all unused MRs */ if (args.cookie == 0) { if (!rs->rs_transport || !rs->rs_transport->flush_mrs) return -EINVAL; rs->rs_transport->flush_mrs(); return 0; } /* Look up the MR given its R_key and remove it from the rbtree * so nobody else finds it. * This should also prevent races with rds_rdma_unuse. */ spin_lock_irqsave(&rs->rs_rdma_lock, flags); mr = rds_mr_tree_walk(&rs->rs_rdma_keys, rds_rdma_cookie_key(args.cookie), NULL); if (mr) { rb_erase(&mr->r_rb_node, &rs->rs_rdma_keys); RB_CLEAR_NODE(&mr->r_rb_node); if (args.flags & RDS_RDMA_INVALIDATE) mr->r_invalidate = 1; } spin_unlock_irqrestore(&rs->rs_rdma_lock, flags); if (!mr) return -EINVAL; kref_put(&mr->r_kref, __rds_put_mr_final); return 0; } /* * This is called when we receive an extension header that * tells us this MR was used. It allows us to implement * use_once semantics */ void rds_rdma_unuse(struct rds_sock *rs, u32 r_key, int force) { struct rds_mr *mr; unsigned long flags; int zot_me = 0; spin_lock_irqsave(&rs->rs_rdma_lock, flags); mr = rds_mr_tree_walk(&rs->rs_rdma_keys, r_key, NULL); if (!mr) { pr_debug("rds: trying to unuse MR with unknown r_key %u!\n", r_key); spin_unlock_irqrestore(&rs->rs_rdma_lock, flags); return; } /* Get a reference so that the MR won't go away before calling * sync_mr() below. */ kref_get(&mr->r_kref); /* If it is going to be freed, remove it from the tree now so * that no other thread can find it and free it. */ if (mr->r_use_once || force) { rb_erase(&mr->r_rb_node, &rs->rs_rdma_keys); RB_CLEAR_NODE(&mr->r_rb_node); zot_me = 1; } spin_unlock_irqrestore(&rs->rs_rdma_lock, flags); /* May have to issue a dma_sync on this memory region. * Note we could avoid this if the operation was a RDMA READ, * but at this point we can't tell. */ if (mr->r_trans->sync_mr) mr->r_trans->sync_mr(mr->r_trans_private, DMA_FROM_DEVICE); /* Release the reference held above. */ kref_put(&mr->r_kref, __rds_put_mr_final); /* If the MR was marked as invalidate, this will * trigger an async flush. */ if (zot_me) kref_put(&mr->r_kref, __rds_put_mr_final); } void rds_rdma_free_op(struct rm_rdma_op *ro) { unsigned int i; if (ro->op_odp_mr) { kref_put(&ro->op_odp_mr->r_kref, __rds_put_mr_final); } else { for (i = 0; i < ro->op_nents; i++) { struct page *page = sg_page(&ro->op_sg[i]); /* Mark page dirty if it was possibly modified, which * is the case for a RDMA_READ which copies from remote * to local memory */ unpin_user_pages_dirty_lock(&page, 1, !ro->op_write); } } kfree(ro->op_notifier); ro->op_notifier = NULL; ro->op_active = 0; ro->op_odp_mr = NULL; } void rds_atomic_free_op(struct rm_atomic_op *ao) { struct page *page = sg_page(ao->op_sg); /* Mark page dirty if it was possibly modified, which * is the case for a RDMA_READ which copies from remote * to local memory */ unpin_user_pages_dirty_lock(&page, 1, true); kfree(ao->op_notifier); ao->op_notifier = NULL; ao->op_active = 0; } /* * Count the number of pages needed to describe an incoming iovec array. */ static int rds_rdma_pages(struct rds_iovec iov[], int nr_iovecs) { int tot_pages = 0; unsigned int nr_pages; unsigned int i; /* figure out the number of pages in the vector */ for (i = 0; i < nr_iovecs; i++) { nr_pages = rds_pages_in_vec(&iov[i]); if (nr_pages == 0) return -EINVAL; tot_pages += nr_pages; /* * nr_pages for one entry is limited to (UINT_MAX>>PAGE_SHIFT)+1, * so tot_pages cannot overflow without first going negative. */ if (tot_pages < 0) return -EINVAL; } return tot_pages; } int rds_rdma_extra_size(struct rds_rdma_args *args, struct rds_iov_vector *iov) { struct rds_iovec *vec; struct rds_iovec __user *local_vec; int tot_pages = 0; unsigned int nr_pages; unsigned int i; local_vec = (struct rds_iovec __user *)(unsigned long) args->local_vec_addr; if (args->nr_local == 0) return -EINVAL; if (args->nr_local > UIO_MAXIOV) return -EMSGSIZE; iov->iov = kcalloc(args->nr_local, sizeof(struct rds_iovec), GFP_KERNEL); if (!iov->iov) return -ENOMEM; vec = &iov->iov[0]; if (copy_from_user(vec, local_vec, args->nr_local * sizeof(struct rds_iovec))) return -EFAULT; iov->len = args->nr_local; /* figure out the number of pages in the vector */ for (i = 0; i < args->nr_local; i++, vec++) { nr_pages = rds_pages_in_vec(vec); if (nr_pages == 0) return -EINVAL; tot_pages += nr_pages; /* * nr_pages for one entry is limited to (UINT_MAX>>PAGE_SHIFT)+1, * so tot_pages cannot overflow without first going negative. */ if (tot_pages < 0) return -EINVAL; } return tot_pages * sizeof(struct scatterlist); } /* * The application asks for a RDMA transfer. * Extract all arguments and set up the rdma_op */ int rds_cmsg_rdma_args(struct rds_sock *rs, struct rds_message *rm, struct cmsghdr *cmsg, struct rds_iov_vector *vec) { struct rds_rdma_args *args; struct rm_rdma_op *op = &rm->rdma; int nr_pages; unsigned int nr_bytes; struct page **pages = NULL; struct rds_iovec *iovs; unsigned int i, j; int ret = 0; bool odp_supported = true; if (cmsg->cmsg_len < CMSG_LEN(sizeof(struct rds_rdma_args)) || rm->rdma.op_active) return -EINVAL; args = CMSG_DATA(cmsg); if (ipv6_addr_any(&rs->rs_bound_addr)) { ret = -ENOTCONN; /* XXX not a great errno */ goto out_ret; } if (args->nr_local > UIO_MAXIOV) { ret = -EMSGSIZE; goto out_ret; } if (vec->len != args->nr_local) { ret = -EINVAL; goto out_ret; } /* odp-mr is not supported for multiple requests within one message */ if (args->nr_local != 1) odp_supported = false; iovs = vec->iov; nr_pages = rds_rdma_pages(iovs, args->nr_local); if (nr_pages < 0) { ret = -EINVAL; goto out_ret; } pages = kcalloc(nr_pages, sizeof(struct page *), GFP_KERNEL); if (!pages) { ret = -ENOMEM; goto out_ret; } op->op_write = !!(args->flags & RDS_RDMA_READWRITE); op->op_fence = !!(args->flags & RDS_RDMA_FENCE); op->op_notify = !!(args->flags & RDS_RDMA_NOTIFY_ME); op->op_silent = !!(args->flags & RDS_RDMA_SILENT); op->op_active = 1; op->op_recverr = rs->rs_recverr; op->op_odp_mr = NULL; WARN_ON(!nr_pages); op->op_sg = rds_message_alloc_sgs(rm, nr_pages); if (IS_ERR(op->op_sg)) { ret = PTR_ERR(op->op_sg); goto out_pages; } if (op->op_notify || op->op_recverr) { /* We allocate an uninitialized notifier here, because * we don't want to do that in the completion handler. We * would have to use GFP_ATOMIC there, and don't want to deal * with failed allocations. */ op->op_notifier = kmalloc(sizeof(struct rds_notifier), GFP_KERNEL); if (!op->op_notifier) { ret = -ENOMEM; goto out_pages; } op->op_notifier->n_user_token = args->user_token; op->op_notifier->n_status = RDS_RDMA_SUCCESS; } /* The cookie contains the R_Key of the remote memory region, and * optionally an offset into it. This is how we implement RDMA into * unaligned memory. * When setting up the RDMA, we need to add that offset to the * destination address (which is really an offset into the MR) * FIXME: We may want to move this into ib_rdma.c */ op->op_rkey = rds_rdma_cookie_key(args->cookie); op->op_remote_addr = args->remote_vec.addr + rds_rdma_cookie_offset(args->cookie); nr_bytes = 0; rdsdebug("RDS: rdma prepare nr_local %llu rva %llx rkey %x\n", (unsigned long long)args->nr_local, (unsigned long long)args->remote_vec.addr, op->op_rkey); for (i = 0; i < args->nr_local; i++) { struct rds_iovec *iov = &iovs[i]; /* don't need to check, rds_rdma_pages() verified nr will be +nonzero */ unsigned int nr = rds_pages_in_vec(iov); rs->rs_user_addr = iov->addr; rs->rs_user_bytes = iov->bytes; /* If it's a WRITE operation, we want to pin the pages for reading. * If it's a READ operation, we need to pin the pages for writing. */ ret = rds_pin_pages(iov->addr, nr, pages, !op->op_write); if ((!odp_supported && ret <= 0) || (odp_supported && ret <= 0 && ret != -EOPNOTSUPP)) goto out_pages; if (ret == -EOPNOTSUPP) { struct rds_mr *local_odp_mr; if (!rs->rs_transport->get_mr) { ret = -EOPNOTSUPP; goto out_pages; } local_odp_mr = kzalloc(sizeof(*local_odp_mr), GFP_KERNEL); if (!local_odp_mr) { ret = -ENOMEM; goto out_pages; } RB_CLEAR_NODE(&local_odp_mr->r_rb_node); kref_init(&local_odp_mr->r_kref); local_odp_mr->r_trans = rs->rs_transport; local_odp_mr->r_sock = rs; local_odp_mr->r_trans_private = rs->rs_transport->get_mr( NULL, 0, rs, &local_odp_mr->r_key, NULL, iov->addr, iov->bytes, ODP_VIRTUAL); if (IS_ERR(local_odp_mr->r_trans_private)) { ret = PTR_ERR(local_odp_mr->r_trans_private); rdsdebug("get_mr ret %d %p\"", ret, local_odp_mr->r_trans_private); kfree(local_odp_mr); ret = -EOPNOTSUPP; goto out_pages; } rdsdebug("Need odp; local_odp_mr %p trans_private %p\n", local_odp_mr, local_odp_mr->r_trans_private); op->op_odp_mr = local_odp_mr; op->op_odp_addr = iov->addr; } rdsdebug("RDS: nr_bytes %u nr %u iov->bytes %llu iov->addr %llx\n", nr_bytes, nr, iov->bytes, iov->addr); nr_bytes += iov->bytes; for (j = 0; j < nr; j++) { unsigned int offset = iov->addr & ~PAGE_MASK; struct scatterlist *sg; sg = &op->op_sg[op->op_nents + j]; sg_set_page(sg, pages[j], min_t(unsigned int, iov->bytes, PAGE_SIZE - offset), offset); sg_dma_len(sg) = sg->length; rdsdebug("RDS: sg->offset %x sg->len %x iov->addr %llx iov->bytes %llu\n", sg->offset, sg->length, iov->addr, iov->bytes); iov->addr += sg->length; iov->bytes -= sg->length; } op->op_nents += nr; } if (nr_bytes > args->remote_vec.bytes) { rdsdebug("RDS nr_bytes %u remote_bytes %u do not match\n", nr_bytes, (unsigned int) args->remote_vec.bytes); ret = -EINVAL; goto out_pages; } op->op_bytes = nr_bytes; ret = 0; out_pages: kfree(pages); out_ret: if (ret) rds_rdma_free_op(op); else rds_stats_inc(s_send_rdma); return ret; } /* * The application wants us to pass an RDMA destination (aka MR) * to the remote */ int rds_cmsg_rdma_dest(struct rds_sock *rs, struct rds_message *rm, struct cmsghdr *cmsg) { unsigned long flags; struct rds_mr *mr; u32 r_key; int err = 0; if (cmsg->cmsg_len < CMSG_LEN(sizeof(rds_rdma_cookie_t)) || rm->m_rdma_cookie != 0) return -EINVAL; memcpy(&rm->m_rdma_cookie, CMSG_DATA(cmsg), sizeof(rm->m_rdma_cookie)); /* We are reusing a previously mapped MR here. Most likely, the * application has written to the buffer, so we need to explicitly * flush those writes to RAM. Otherwise the HCA may not see them * when doing a DMA from that buffer. */ r_key = rds_rdma_cookie_key(rm->m_rdma_cookie); spin_lock_irqsave(&rs->rs_rdma_lock, flags); mr = rds_mr_tree_walk(&rs->rs_rdma_keys, r_key, NULL); if (!mr) err = -EINVAL; /* invalid r_key */ else kref_get(&mr->r_kref); spin_unlock_irqrestore(&rs->rs_rdma_lock, flags); if (mr) { mr->r_trans->sync_mr(mr->r_trans_private, DMA_TO_DEVICE); rm->rdma.op_rdma_mr = mr; } return err; } /* * The application passes us an address range it wants to enable RDMA * to/from. We map the area, and save the <R_Key,offset> pair * in rm->m_rdma_cookie. This causes it to be sent along to the peer * in an extension header. */ int rds_cmsg_rdma_map(struct rds_sock *rs, struct rds_message *rm, struct cmsghdr *cmsg) { if (cmsg->cmsg_len < CMSG_LEN(sizeof(struct rds_get_mr_args)) || rm->m_rdma_cookie != 0) return -EINVAL; return __rds_rdma_map(rs, CMSG_DATA(cmsg), &rm->m_rdma_cookie, &rm->rdma.op_rdma_mr, rm->m_conn_path); } /* * Fill in rds_message for an atomic request. */ int rds_cmsg_atomic(struct rds_sock *rs, struct rds_message *rm, struct cmsghdr *cmsg) { struct page *page = NULL; struct rds_atomic_args *args; int ret = 0; if (cmsg->cmsg_len < CMSG_LEN(sizeof(struct rds_atomic_args)) || rm->atomic.op_active) return -EINVAL; args = CMSG_DATA(cmsg); /* Nonmasked & masked cmsg ops converted to masked hw ops */ switch (cmsg->cmsg_type) { case RDS_CMSG_ATOMIC_FADD: rm->atomic.op_type = RDS_ATOMIC_TYPE_FADD; rm->atomic.op_m_fadd.add = args->fadd.add; rm->atomic.op_m_fadd.nocarry_mask = 0; break; case RDS_CMSG_MASKED_ATOMIC_FADD: rm->atomic.op_type = RDS_ATOMIC_TYPE_FADD; rm->atomic.op_m_fadd.add = args->m_fadd.add; rm->atomic.op_m_fadd.nocarry_mask = args->m_fadd.nocarry_mask; break; case RDS_CMSG_ATOMIC_CSWP: rm->atomic.op_type = RDS_ATOMIC_TYPE_CSWP; rm->atomic.op_m_cswp.compare = args->cswp.compare; rm->atomic.op_m_cswp.swap = args->cswp.swap; rm->atomic.op_m_cswp.compare_mask = ~0; rm->atomic.op_m_cswp.swap_mask = ~0; break; case RDS_CMSG_MASKED_ATOMIC_CSWP: rm->atomic.op_type = RDS_ATOMIC_TYPE_CSWP; rm->atomic.op_m_cswp.compare = args->m_cswp.compare; rm->atomic.op_m_cswp.swap = args->m_cswp.swap; rm->atomic.op_m_cswp.compare_mask = args->m_cswp.compare_mask; rm->atomic.op_m_cswp.swap_mask = args->m_cswp.swap_mask; break; default: BUG(); /* should never happen */ } rm->atomic.op_notify = !!(args->flags & RDS_RDMA_NOTIFY_ME); rm->atomic.op_silent = !!(args->flags & RDS_RDMA_SILENT); rm->atomic.op_active = 1; rm->atomic.op_recverr = rs->rs_recverr; rm->atomic.op_sg = rds_message_alloc_sgs(rm, 1); if (IS_ERR(rm->atomic.op_sg)) { ret = PTR_ERR(rm->atomic.op_sg); goto err; } /* verify 8 byte-aligned */ if (args->local_addr & 0x7) { ret = -EFAULT; goto err; } ret = rds_pin_pages(args->local_addr, 1, &page, 1); if (ret != 1) goto err; ret = 0; sg_set_page(rm->atomic.op_sg, page, 8, offset_in_page(args->local_addr)); if (rm->atomic.op_notify || rm->atomic.op_recverr) { /* We allocate an uninitialized notifier here, because * we don't want to do that in the completion handler. We * would have to use GFP_ATOMIC there, and don't want to deal * with failed allocations. */ rm->atomic.op_notifier = kmalloc(sizeof(*rm->atomic.op_notifier), GFP_KERNEL); if (!rm->atomic.op_notifier) { ret = -ENOMEM; goto err; } rm->atomic.op_notifier->n_user_token = args->user_token; rm->atomic.op_notifier->n_status = RDS_RDMA_SUCCESS; } rm->atomic.op_rkey = rds_rdma_cookie_key(args->cookie); rm->atomic.op_remote_addr = args->remote_addr + rds_rdma_cookie_offset(args->cookie); return ret; err: if (page) unpin_user_page(page); rm->atomic.op_active = 0; kfree(rm->atomic.op_notifier); return ret; } |
| 1 1 1 1 1 1 1 1 1 1 1 1 1 1 2 1 1 2 1 1 1 1 1 1 1 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 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * HID driver for Sony DualSense(TM) controller. * * Copyright (c) 2020-2022 Sony Interactive Entertainment */ #include <linux/bits.h> #include <linux/crc32.h> #include <linux/device.h> #include <linux/hid.h> #include <linux/idr.h> #include <linux/input/mt.h> #include <linux/leds.h> #include <linux/led-class-multicolor.h> #include <linux/module.h> #include <linux/unaligned.h> #include "hid-ids.h" /* List of connected playstation devices. */ static DEFINE_MUTEX(ps_devices_lock); static LIST_HEAD(ps_devices_list); static DEFINE_IDA(ps_player_id_allocator); #define HID_PLAYSTATION_VERSION_PATCH 0x8000 enum PS_TYPE { PS_TYPE_PS4_DUALSHOCK4, PS_TYPE_PS5_DUALSENSE, }; /* Base class for playstation devices. */ struct ps_device { struct list_head list; struct hid_device *hdev; spinlock_t lock; uint32_t player_id; struct power_supply_desc battery_desc; struct power_supply *battery; uint8_t battery_capacity; int battery_status; const char *input_dev_name; /* Name of primary input device. */ uint8_t mac_address[6]; /* Note: stored in little endian order. */ uint32_t hw_version; uint32_t fw_version; int (*parse_report)(struct ps_device *dev, struct hid_report *report, u8 *data, int size); void (*remove)(struct ps_device *dev); }; /* Calibration data for playstation motion sensors. */ struct ps_calibration_data { int abs_code; short bias; int sens_numer; int sens_denom; }; struct ps_led_info { const char *name; const char *color; int max_brightness; enum led_brightness (*brightness_get)(struct led_classdev *cdev); int (*brightness_set)(struct led_classdev *cdev, enum led_brightness); int (*blink_set)(struct led_classdev *led, unsigned long *on, unsigned long *off); }; /* Seed values for DualShock4 / DualSense CRC32 for different report types. */ #define PS_INPUT_CRC32_SEED 0xA1 #define PS_OUTPUT_CRC32_SEED 0xA2 #define PS_FEATURE_CRC32_SEED 0xA3 #define DS_INPUT_REPORT_USB 0x01 #define DS_INPUT_REPORT_USB_SIZE 64 #define DS_INPUT_REPORT_BT 0x31 #define DS_INPUT_REPORT_BT_SIZE 78 #define DS_OUTPUT_REPORT_USB 0x02 #define DS_OUTPUT_REPORT_USB_SIZE 63 #define DS_OUTPUT_REPORT_BT 0x31 #define DS_OUTPUT_REPORT_BT_SIZE 78 #define DS_FEATURE_REPORT_CALIBRATION 0x05 #define DS_FEATURE_REPORT_CALIBRATION_SIZE 41 #define DS_FEATURE_REPORT_PAIRING_INFO 0x09 #define DS_FEATURE_REPORT_PAIRING_INFO_SIZE 20 #define DS_FEATURE_REPORT_FIRMWARE_INFO 0x20 #define DS_FEATURE_REPORT_FIRMWARE_INFO_SIZE 64 /* Button masks for DualSense input report. */ #define DS_BUTTONS0_HAT_SWITCH GENMASK(3, 0) #define DS_BUTTONS0_SQUARE BIT(4) #define DS_BUTTONS0_CROSS BIT(5) #define DS_BUTTONS0_CIRCLE BIT(6) #define DS_BUTTONS0_TRIANGLE BIT(7) #define DS_BUTTONS1_L1 BIT(0) #define DS_BUTTONS1_R1 BIT(1) #define DS_BUTTONS1_L2 BIT(2) #define DS_BUTTONS1_R2 BIT(3) #define DS_BUTTONS1_CREATE BIT(4) #define DS_BUTTONS1_OPTIONS BIT(5) #define DS_BUTTONS1_L3 BIT(6) #define DS_BUTTONS1_R3 BIT(7) #define DS_BUTTONS2_PS_HOME BIT(0) #define DS_BUTTONS2_TOUCHPAD BIT(1) #define DS_BUTTONS2_MIC_MUTE BIT(2) /* Status field of DualSense input report. */ #define DS_STATUS_BATTERY_CAPACITY GENMASK(3, 0) #define DS_STATUS_CHARGING GENMASK(7, 4) #define DS_STATUS_CHARGING_SHIFT 4 /* Feature version from DualSense Firmware Info report. */ #define DS_FEATURE_VERSION(major, minor) ((major & 0xff) << 8 | (minor & 0xff)) /* * Status of a DualSense touch point contact. * Contact IDs, with highest bit set are 'inactive' * and any associated data is then invalid. */ #define DS_TOUCH_POINT_INACTIVE BIT(7) /* Magic value required in tag field of Bluetooth output report. */ #define DS_OUTPUT_TAG 0x10 /* Flags for DualSense output report. */ #define DS_OUTPUT_VALID_FLAG0_COMPATIBLE_VIBRATION BIT(0) #define DS_OUTPUT_VALID_FLAG0_HAPTICS_SELECT BIT(1) #define DS_OUTPUT_VALID_FLAG1_MIC_MUTE_LED_CONTROL_ENABLE BIT(0) #define DS_OUTPUT_VALID_FLAG1_POWER_SAVE_CONTROL_ENABLE BIT(1) #define DS_OUTPUT_VALID_FLAG1_LIGHTBAR_CONTROL_ENABLE BIT(2) #define DS_OUTPUT_VALID_FLAG1_RELEASE_LEDS BIT(3) #define DS_OUTPUT_VALID_FLAG1_PLAYER_INDICATOR_CONTROL_ENABLE BIT(4) #define DS_OUTPUT_VALID_FLAG2_LIGHTBAR_SETUP_CONTROL_ENABLE BIT(1) #define DS_OUTPUT_VALID_FLAG2_COMPATIBLE_VIBRATION2 BIT(2) #define DS_OUTPUT_POWER_SAVE_CONTROL_MIC_MUTE BIT(4) #define DS_OUTPUT_LIGHTBAR_SETUP_LIGHT_OUT BIT(1) /* DualSense hardware limits */ #define DS_ACC_RES_PER_G 8192 #define DS_ACC_RANGE (4*DS_ACC_RES_PER_G) #define DS_GYRO_RES_PER_DEG_S 1024 #define DS_GYRO_RANGE (2048*DS_GYRO_RES_PER_DEG_S) #define DS_TOUCHPAD_WIDTH 1920 #define DS_TOUCHPAD_HEIGHT 1080 struct dualsense { struct ps_device base; struct input_dev *gamepad; struct input_dev *sensors; struct input_dev *touchpad; /* Update version is used as a feature/capability version. */ uint16_t update_version; /* Calibration data for accelerometer and gyroscope. */ struct ps_calibration_data accel_calib_data[3]; struct ps_calibration_data gyro_calib_data[3]; /* Timestamp for sensor data */ bool sensor_timestamp_initialized; uint32_t prev_sensor_timestamp; uint32_t sensor_timestamp_us; /* Compatible rumble state */ bool use_vibration_v2; bool update_rumble; uint8_t motor_left; uint8_t motor_right; /* RGB lightbar */ struct led_classdev_mc lightbar; bool update_lightbar; uint8_t lightbar_red; uint8_t lightbar_green; uint8_t lightbar_blue; /* Microphone */ bool update_mic_mute; bool mic_muted; bool last_btn_mic_state; /* Player leds */ bool update_player_leds; uint8_t player_leds_state; struct led_classdev player_leds[5]; struct work_struct output_worker; bool output_worker_initialized; void *output_report_dmabuf; uint8_t output_seq; /* Sequence number for output report. */ }; struct dualsense_touch_point { uint8_t contact; uint8_t x_lo; uint8_t x_hi:4, y_lo:4; uint8_t y_hi; } __packed; static_assert(sizeof(struct dualsense_touch_point) == 4); /* Main DualSense input report excluding any BT/USB specific headers. */ struct dualsense_input_report { uint8_t x, y; uint8_t rx, ry; uint8_t z, rz; uint8_t seq_number; uint8_t buttons[4]; uint8_t reserved[4]; /* Motion sensors */ __le16 gyro[3]; /* x, y, z */ __le16 accel[3]; /* x, y, z */ __le32 sensor_timestamp; uint8_t reserved2; /* Touchpad */ struct dualsense_touch_point points[2]; uint8_t reserved3[12]; uint8_t status; uint8_t reserved4[10]; } __packed; /* Common input report size shared equals the size of the USB report minus 1 byte for ReportID. */ static_assert(sizeof(struct dualsense_input_report) == DS_INPUT_REPORT_USB_SIZE - 1); /* Common data between DualSense BT/USB main output report. */ struct dualsense_output_report_common { uint8_t valid_flag0; uint8_t valid_flag1; /* For DualShock 4 compatibility mode. */ uint8_t motor_right; uint8_t motor_left; /* Audio controls */ uint8_t reserved[4]; uint8_t mute_button_led; uint8_t power_save_control; uint8_t reserved2[28]; /* LEDs and lightbar */ uint8_t valid_flag2; uint8_t reserved3[2]; uint8_t lightbar_setup; uint8_t led_brightness; uint8_t player_leds; uint8_t lightbar_red; uint8_t lightbar_green; uint8_t lightbar_blue; } __packed; static_assert(sizeof(struct dualsense_output_report_common) == 47); struct dualsense_output_report_bt { uint8_t report_id; /* 0x31 */ uint8_t seq_tag; uint8_t tag; struct dualsense_output_report_common common; uint8_t reserved[24]; __le32 crc32; } __packed; static_assert(sizeof(struct dualsense_output_report_bt) == DS_OUTPUT_REPORT_BT_SIZE); struct dualsense_output_report_usb { uint8_t report_id; /* 0x02 */ struct dualsense_output_report_common common; uint8_t reserved[15]; } __packed; static_assert(sizeof(struct dualsense_output_report_usb) == DS_OUTPUT_REPORT_USB_SIZE); /* * The DualSense has a main output report used to control most features. It is * largely the same between Bluetooth and USB except for different headers and CRC. * This structure hide the differences between the two to simplify sending output reports. */ struct dualsense_output_report { uint8_t *data; /* Start of data */ uint8_t len; /* Size of output report */ /* Points to Bluetooth data payload in case for a Bluetooth report else NULL. */ struct dualsense_output_report_bt *bt; /* Points to USB data payload in case for a USB report else NULL. */ struct dualsense_output_report_usb *usb; /* Points to common section of report, so past any headers. */ struct dualsense_output_report_common *common; }; #define DS4_INPUT_REPORT_USB 0x01 #define DS4_INPUT_REPORT_USB_SIZE 64 #define DS4_INPUT_REPORT_BT_MINIMAL 0x01 #define DS4_INPUT_REPORT_BT_MINIMAL_SIZE 10 #define DS4_INPUT_REPORT_BT 0x11 #define DS4_INPUT_REPORT_BT_SIZE 78 #define DS4_OUTPUT_REPORT_USB 0x05 #define DS4_OUTPUT_REPORT_USB_SIZE 32 #define DS4_OUTPUT_REPORT_BT 0x11 #define DS4_OUTPUT_REPORT_BT_SIZE 78 #define DS4_FEATURE_REPORT_CALIBRATION 0x02 #define DS4_FEATURE_REPORT_CALIBRATION_SIZE 37 #define DS4_FEATURE_REPORT_CALIBRATION_BT 0x05 #define DS4_FEATURE_REPORT_CALIBRATION_BT_SIZE 41 #define DS4_FEATURE_REPORT_FIRMWARE_INFO 0xa3 #define DS4_FEATURE_REPORT_FIRMWARE_INFO_SIZE 49 #define DS4_FEATURE_REPORT_PAIRING_INFO 0x12 #define DS4_FEATURE_REPORT_PAIRING_INFO_SIZE 16 /* * Status of a DualShock4 touch point contact. * Contact IDs, with highest bit set are 'inactive' * and any associated data is then invalid. */ #define DS4_TOUCH_POINT_INACTIVE BIT(7) /* Status field of DualShock4 input report. */ #define DS4_STATUS0_BATTERY_CAPACITY GENMASK(3, 0) #define DS4_STATUS0_CABLE_STATE BIT(4) /* Battery status within batery_status field. */ #define DS4_BATTERY_STATUS_FULL 11 /* Status1 bit2 contains dongle connection state: * 0 = connectd * 1 = disconnected */ #define DS4_STATUS1_DONGLE_STATE BIT(2) /* The lower 6 bits of hw_control of the Bluetooth main output report * control the interval at which Dualshock 4 reports data: * 0x00 - 1ms * 0x01 - 1ms * 0x02 - 2ms * 0x3E - 62ms * 0x3F - disabled */ #define DS4_OUTPUT_HWCTL_BT_POLL_MASK 0x3F /* Default to 4ms poll interval, which is same as USB (not adjustable). */ #define DS4_BT_DEFAULT_POLL_INTERVAL_MS 4 #define DS4_OUTPUT_HWCTL_CRC32 0x40 #define DS4_OUTPUT_HWCTL_HID 0x80 /* Flags for DualShock4 output report. */ #define DS4_OUTPUT_VALID_FLAG0_MOTOR 0x01 #define DS4_OUTPUT_VALID_FLAG0_LED 0x02 #define DS4_OUTPUT_VALID_FLAG0_LED_BLINK 0x04 /* DualShock4 hardware limits */ #define DS4_ACC_RES_PER_G 8192 #define DS4_ACC_RANGE (4*DS_ACC_RES_PER_G) #define DS4_GYRO_RES_PER_DEG_S 1024 #define DS4_GYRO_RANGE (2048*DS_GYRO_RES_PER_DEG_S) #define DS4_LIGHTBAR_MAX_BLINK 255 /* 255 centiseconds */ #define DS4_TOUCHPAD_WIDTH 1920 #define DS4_TOUCHPAD_HEIGHT 942 enum dualshock4_dongle_state { DONGLE_DISCONNECTED, DONGLE_CALIBRATING, DONGLE_CONNECTED, DONGLE_DISABLED }; struct dualshock4 { struct ps_device base; struct input_dev *gamepad; struct input_dev *sensors; struct input_dev *touchpad; /* Calibration data for accelerometer and gyroscope. */ struct ps_calibration_data accel_calib_data[3]; struct ps_calibration_data gyro_calib_data[3]; /* Only used on dongle to track state transitions. */ enum dualshock4_dongle_state dongle_state; /* Used during calibration. */ struct work_struct dongle_hotplug_worker; /* Timestamp for sensor data */ bool sensor_timestamp_initialized; uint32_t prev_sensor_timestamp; uint32_t sensor_timestamp_us; /* Bluetooth poll interval */ bool update_bt_poll_interval; uint8_t bt_poll_interval; bool update_rumble; uint8_t motor_left; uint8_t motor_right; /* Lightbar leds */ bool update_lightbar; bool update_lightbar_blink; bool lightbar_enabled; /* For use by global LED control. */ uint8_t lightbar_red; uint8_t lightbar_green; uint8_t lightbar_blue; uint8_t lightbar_blink_on; /* In increments of 10ms. */ uint8_t lightbar_blink_off; /* In increments of 10ms. */ struct led_classdev lightbar_leds[4]; struct work_struct output_worker; bool output_worker_initialized; void *output_report_dmabuf; }; struct dualshock4_touch_point { uint8_t contact; uint8_t x_lo; uint8_t x_hi:4, y_lo:4; uint8_t y_hi; } __packed; static_assert(sizeof(struct dualshock4_touch_point) == 4); struct dualshock4_touch_report { uint8_t timestamp; struct dualshock4_touch_point points[2]; } __packed; static_assert(sizeof(struct dualshock4_touch_report) == 9); /* Main DualShock4 input report excluding any BT/USB specific headers. */ struct dualshock4_input_report_common { uint8_t x, y; uint8_t rx, ry; uint8_t buttons[3]; uint8_t z, rz; /* Motion sensors */ __le16 sensor_timestamp; uint8_t sensor_temperature; __le16 gyro[3]; /* x, y, z */ __le16 accel[3]; /* x, y, z */ uint8_t reserved2[5]; uint8_t status[2]; uint8_t reserved3; } __packed; static_assert(sizeof(struct dualshock4_input_report_common) == 32); struct dualshock4_input_report_usb { uint8_t report_id; /* 0x01 */ struct dualshock4_input_report_common common; uint8_t num_touch_reports; struct dualshock4_touch_report touch_reports[3]; uint8_t reserved[3]; } __packed; static_assert(sizeof(struct dualshock4_input_report_usb) == DS4_INPUT_REPORT_USB_SIZE); struct dualshock4_input_report_bt { uint8_t report_id; /* 0x11 */ uint8_t reserved[2]; struct dualshock4_input_report_common common; uint8_t num_touch_reports; struct dualshock4_touch_report touch_reports[4]; /* BT has 4 compared to 3 for USB */ uint8_t reserved2[2]; __le32 crc32; } __packed; static_assert(sizeof(struct dualshock4_input_report_bt) == DS4_INPUT_REPORT_BT_SIZE); /* Common data between Bluetooth and USB DualShock4 output reports. */ struct dualshock4_output_report_common { uint8_t valid_flag0; uint8_t valid_flag1; uint8_t reserved; uint8_t motor_right; uint8_t motor_left; uint8_t lightbar_red; uint8_t lightbar_green; uint8_t lightbar_blue; uint8_t lightbar_blink_on; uint8_t lightbar_blink_off; } __packed; struct dualshock4_output_report_usb { uint8_t report_id; /* 0x5 */ struct dualshock4_output_report_common common; uint8_t reserved[21]; } __packed; static_assert(sizeof(struct dualshock4_output_report_usb) == DS4_OUTPUT_REPORT_USB_SIZE); struct dualshock4_output_report_bt { uint8_t report_id; /* 0x11 */ uint8_t hw_control; uint8_t audio_control; struct dualshock4_output_report_common common; uint8_t reserved[61]; __le32 crc32; } __packed; static_assert(sizeof(struct dualshock4_output_report_bt) == DS4_OUTPUT_REPORT_BT_SIZE); /* * The DualShock4 has a main output report used to control most features. It is * largely the same between Bluetooth and USB except for different headers and CRC. * This structure hide the differences between the two to simplify sending output reports. */ struct dualshock4_output_report { uint8_t *data; /* Start of data */ uint8_t len; /* Size of output report */ /* Points to Bluetooth data payload in case for a Bluetooth report else NULL. */ struct dualshock4_output_report_bt *bt; /* Points to USB data payload in case for a USB report else NULL. */ struct dualshock4_output_report_usb *usb; /* Points to common section of report, so past any headers. */ struct dualshock4_output_report_common *common; }; /* * Common gamepad buttons across DualShock 3 / 4 and DualSense. * Note: for device with a touchpad, touchpad button is not included * as it will be part of the touchpad device. */ static const int ps_gamepad_buttons[] = { BTN_WEST, /* Square */ BTN_NORTH, /* Triangle */ BTN_EAST, /* Circle */ BTN_SOUTH, /* Cross */ BTN_TL, /* L1 */ BTN_TR, /* R1 */ BTN_TL2, /* L2 */ BTN_TR2, /* R2 */ BTN_SELECT, /* Create (PS5) / Share (PS4) */ BTN_START, /* Option */ BTN_THUMBL, /* L3 */ BTN_THUMBR, /* R3 */ BTN_MODE, /* PS Home */ }; static const struct {int x; int y; } ps_gamepad_hat_mapping[] = { {0, -1}, {1, -1}, {1, 0}, {1, 1}, {0, 1}, {-1, 1}, {-1, 0}, {-1, -1}, {0, 0}, }; static int dualshock4_get_calibration_data(struct dualshock4 *ds4); static inline void dualsense_schedule_work(struct dualsense *ds); static inline void dualshock4_schedule_work(struct dualshock4 *ds4); static void dualsense_set_lightbar(struct dualsense *ds, uint8_t red, uint8_t green, uint8_t blue); static void dualshock4_set_default_lightbar_colors(struct dualshock4 *ds4); /* * Add a new ps_device to ps_devices if it doesn't exist. * Return error on duplicate device, which can happen if the same * device is connected using both Bluetooth and USB. */ static int ps_devices_list_add(struct ps_device *dev) { struct ps_device *entry; mutex_lock(&ps_devices_lock); list_for_each_entry(entry, &ps_devices_list, list) { if (!memcmp(entry->mac_address, dev->mac_address, sizeof(dev->mac_address))) { hid_err(dev->hdev, "Duplicate device found for MAC address %pMR.\n", dev->mac_address); mutex_unlock(&ps_devices_lock); return -EEXIST; } } list_add_tail(&dev->list, &ps_devices_list); mutex_unlock(&ps_devices_lock); return 0; } static int ps_devices_list_remove(struct ps_device *dev) { mutex_lock(&ps_devices_lock); list_del(&dev->list); mutex_unlock(&ps_devices_lock); return 0; } static int ps_device_set_player_id(struct ps_device *dev) { int ret = ida_alloc(&ps_player_id_allocator, GFP_KERNEL); if (ret < 0) return ret; dev->player_id = ret; return 0; } static void ps_device_release_player_id(struct ps_device *dev) { ida_free(&ps_player_id_allocator, dev->player_id); dev->player_id = U32_MAX; } static struct input_dev *ps_allocate_input_dev(struct hid_device *hdev, const char *name_suffix) { struct input_dev *input_dev; input_dev = devm_input_allocate_device(&hdev->dev); if (!input_dev) return ERR_PTR(-ENOMEM); input_dev->id.bustype = hdev->bus; input_dev->id.vendor = hdev->vendor; input_dev->id.product = hdev->product; input_dev->id.version = hdev->version; input_dev->uniq = hdev->uniq; if (name_suffix) { input_dev->name = devm_kasprintf(&hdev->dev, GFP_KERNEL, "%s %s", hdev->name, name_suffix); if (!input_dev->name) return ERR_PTR(-ENOMEM); } else { input_dev->name = hdev->name; } input_set_drvdata(input_dev, hdev); return input_dev; } static enum power_supply_property ps_power_supply_props[] = { POWER_SUPPLY_PROP_STATUS, POWER_SUPPLY_PROP_PRESENT, POWER_SUPPLY_PROP_CAPACITY, POWER_SUPPLY_PROP_SCOPE, }; static int ps_battery_get_property(struct power_supply *psy, enum power_supply_property psp, union power_supply_propval *val) { struct ps_device *dev = power_supply_get_drvdata(psy); uint8_t battery_capacity; int battery_status; unsigned long flags; int ret = 0; spin_lock_irqsave(&dev->lock, flags); battery_capacity = dev->battery_capacity; battery_status = dev->battery_status; spin_unlock_irqrestore(&dev->lock, flags); switch (psp) { case POWER_SUPPLY_PROP_STATUS: val->intval = battery_status; break; case POWER_SUPPLY_PROP_PRESENT: val->intval = 1; break; case POWER_SUPPLY_PROP_CAPACITY: val->intval = battery_capacity; break; case POWER_SUPPLY_PROP_SCOPE: val->intval = POWER_SUPPLY_SCOPE_DEVICE; break; default: ret = -EINVAL; break; } return ret; } static int ps_device_register_battery(struct ps_device *dev) { struct power_supply *battery; struct power_supply_config battery_cfg = { .drv_data = dev }; int ret; dev->battery_desc.type = POWER_SUPPLY_TYPE_BATTERY; dev->battery_desc.properties = ps_power_supply_props; dev->battery_desc.num_properties = ARRAY_SIZE(ps_power_supply_props); dev->battery_desc.get_property = ps_battery_get_property; dev->battery_desc.name = devm_kasprintf(&dev->hdev->dev, GFP_KERNEL, "ps-controller-battery-%pMR", dev->mac_address); if (!dev->battery_desc.name) return -ENOMEM; battery = devm_power_supply_register(&dev->hdev->dev, &dev->battery_desc, &battery_cfg); if (IS_ERR(battery)) { ret = PTR_ERR(battery); hid_err(dev->hdev, "Unable to register battery device: %d\n", ret); return ret; } dev->battery = battery; ret = power_supply_powers(dev->battery, &dev->hdev->dev); if (ret) { hid_err(dev->hdev, "Unable to activate battery device: %d\n", ret); return ret; } return 0; } /* Compute crc32 of HID data and compare against expected CRC. */ static bool ps_check_crc32(uint8_t seed, uint8_t *data, size_t len, uint32_t report_crc) { uint32_t crc; crc = crc32_le(0xFFFFFFFF, &seed, 1); crc = ~crc32_le(crc, data, len); return crc == report_crc; } static struct input_dev *ps_gamepad_create(struct hid_device *hdev, int (*play_effect)(struct input_dev *, void *, struct ff_effect *)) { struct input_dev *gamepad; unsigned int i; int ret; gamepad = ps_allocate_input_dev(hdev, NULL); if (IS_ERR(gamepad)) return ERR_CAST(gamepad); input_set_abs_params(gamepad, ABS_X, 0, 255, 0, 0); input_set_abs_params(gamepad, ABS_Y, 0, 255, 0, 0); input_set_abs_params(gamepad, ABS_Z, 0, 255, 0, 0); input_set_abs_params(gamepad, ABS_RX, 0, 255, 0, 0); input_set_abs_params(gamepad, ABS_RY, 0, 255, 0, 0); input_set_abs_params(gamepad, ABS_RZ, 0, 255, 0, 0); input_set_abs_params(gamepad, ABS_HAT0X, -1, 1, 0, 0); input_set_abs_params(gamepad, ABS_HAT0Y, -1, 1, 0, 0); for (i = 0; i < ARRAY_SIZE(ps_gamepad_buttons); i++) input_set_capability(gamepad, EV_KEY, ps_gamepad_buttons[i]); #if IS_ENABLED(CONFIG_PLAYSTATION_FF) if (play_effect) { input_set_capability(gamepad, EV_FF, FF_RUMBLE); input_ff_create_memless(gamepad, NULL, play_effect); } #endif ret = input_register_device(gamepad); if (ret) return ERR_PTR(ret); return gamepad; } static int ps_get_report(struct hid_device *hdev, uint8_t report_id, uint8_t *buf, size_t size, bool check_crc) { int ret; ret = hid_hw_raw_request(hdev, report_id, buf, size, HID_FEATURE_REPORT, HID_REQ_GET_REPORT); if (ret < 0) { hid_err(hdev, "Failed to retrieve feature with reportID %d: %d\n", report_id, ret); return ret; } if (ret != size) { hid_err(hdev, "Invalid byte count transferred, expected %zu got %d\n", size, ret); return -EINVAL; } if (buf[0] != report_id) { hid_err(hdev, "Invalid reportID received, expected %d got %d\n", report_id, buf[0]); return -EINVAL; } if (hdev->bus == BUS_BLUETOOTH && check_crc) { /* Last 4 bytes contains crc32. */ uint8_t crc_offset = size - 4; uint32_t report_crc = get_unaligned_le32(&buf[crc_offset]); if (!ps_check_crc32(PS_FEATURE_CRC32_SEED, buf, crc_offset, report_crc)) { hid_err(hdev, "CRC check failed for reportID=%d\n", report_id); return -EILSEQ; } } return 0; } static int ps_led_register(struct ps_device *ps_dev, struct led_classdev *led, const struct ps_led_info *led_info) { int ret; if (led_info->name) { led->name = devm_kasprintf(&ps_dev->hdev->dev, GFP_KERNEL, "%s:%s:%s", ps_dev->input_dev_name, led_info->color, led_info->name); } else { /* Backwards compatible mode for hid-sony, but not compliant with LED class spec. */ led->name = devm_kasprintf(&ps_dev->hdev->dev, GFP_KERNEL, "%s:%s", ps_dev->input_dev_name, led_info->color); } if (!led->name) return -ENOMEM; led->brightness = 0; led->max_brightness = led_info->max_brightness; led->flags = LED_CORE_SUSPENDRESUME; led->brightness_get = led_info->brightness_get; led->brightness_set_blocking = led_info->brightness_set; led->blink_set = led_info->blink_set; ret = devm_led_classdev_register(&ps_dev->hdev->dev, led); if (ret) { hid_err(ps_dev->hdev, "Failed to register LED %s: %d\n", led_info->name, ret); return ret; } return 0; } /* Register a DualSense/DualShock4 RGB lightbar represented by a multicolor LED. */ static int ps_lightbar_register(struct ps_device *ps_dev, struct led_classdev_mc *lightbar_mc_dev, int (*brightness_set)(struct led_classdev *, enum led_brightness)) { struct hid_device *hdev = ps_dev->hdev; struct mc_subled *mc_led_info; struct led_classdev *led_cdev; int ret; mc_led_info = devm_kmalloc_array(&hdev->dev, 3, sizeof(*mc_led_info), GFP_KERNEL | __GFP_ZERO); if (!mc_led_info) return -ENOMEM; mc_led_info[0].color_index = LED_COLOR_ID_RED; mc_led_info[1].color_index = LED_COLOR_ID_GREEN; mc_led_info[2].color_index = LED_COLOR_ID_BLUE; lightbar_mc_dev->subled_info = mc_led_info; lightbar_mc_dev->num_colors = 3; led_cdev = &lightbar_mc_dev->led_cdev; led_cdev->name = devm_kasprintf(&hdev->dev, GFP_KERNEL, "%s:rgb:indicator", ps_dev->input_dev_name); if (!led_cdev->name) return -ENOMEM; led_cdev->brightness = 255; led_cdev->max_brightness = 255; led_cdev->brightness_set_blocking = brightness_set; ret = devm_led_classdev_multicolor_register(&hdev->dev, lightbar_mc_dev); if (ret < 0) { hid_err(hdev, "Cannot register multicolor LED device\n"); return ret; } return 0; } static struct input_dev *ps_sensors_create(struct hid_device *hdev, int accel_range, int accel_res, int gyro_range, int gyro_res) { struct input_dev *sensors; int ret; sensors = ps_allocate_input_dev(hdev, "Motion Sensors"); if (IS_ERR(sensors)) return ERR_CAST(sensors); __set_bit(INPUT_PROP_ACCELEROMETER, sensors->propbit); __set_bit(EV_MSC, sensors->evbit); __set_bit(MSC_TIMESTAMP, sensors->mscbit); /* Accelerometer */ input_set_abs_params(sensors, ABS_X, -accel_range, accel_range, 16, 0); input_set_abs_params(sensors, ABS_Y, -accel_range, accel_range, 16, 0); input_set_abs_params(sensors, ABS_Z, -accel_range, accel_range, 16, 0); input_abs_set_res(sensors, ABS_X, accel_res); input_abs_set_res(sensors, ABS_Y, accel_res); input_abs_set_res(sensors, ABS_Z, accel_res); /* Gyroscope */ input_set_abs_params(sensors, ABS_RX, -gyro_range, gyro_range, 16, 0); input_set_abs_params(sensors, ABS_RY, -gyro_range, gyro_range, 16, 0); input_set_abs_params(sensors, ABS_RZ, -gyro_range, gyro_range, 16, 0); input_abs_set_res(sensors, ABS_RX, gyro_res); input_abs_set_res(sensors, ABS_RY, gyro_res); input_abs_set_res(sensors, ABS_RZ, gyro_res); ret = input_register_device(sensors); if (ret) return ERR_PTR(ret); return sensors; } static struct input_dev *ps_touchpad_create(struct hid_device *hdev, int width, int height, unsigned int num_contacts) { struct input_dev *touchpad; int ret; touchpad = ps_allocate_input_dev(hdev, "Touchpad"); if (IS_ERR(touchpad)) return ERR_CAST(touchpad); /* Map button underneath touchpad to BTN_LEFT. */ input_set_capability(touchpad, EV_KEY, BTN_LEFT); __set_bit(INPUT_PROP_BUTTONPAD, touchpad->propbit); input_set_abs_params(touchpad, ABS_MT_POSITION_X, 0, width - 1, 0, 0); input_set_abs_params(touchpad, ABS_MT_POSITION_Y, 0, height - 1, 0, 0); ret = input_mt_init_slots(touchpad, num_contacts, INPUT_MT_POINTER); if (ret) return ERR_PTR(ret); ret = input_register_device(touchpad); if (ret) return ERR_PTR(ret); return touchpad; } static ssize_t firmware_version_show(struct device *dev, struct device_attribute *attr, char *buf) { struct hid_device *hdev = to_hid_device(dev); struct ps_device *ps_dev = hid_get_drvdata(hdev); return sysfs_emit(buf, "0x%08x\n", ps_dev->fw_version); } static DEVICE_ATTR_RO(firmware_version); static ssize_t hardware_version_show(struct device *dev, struct device_attribute *attr, char *buf) { struct hid_device *hdev = to_hid_device(dev); struct ps_device *ps_dev = hid_get_drvdata(hdev); return sysfs_emit(buf, "0x%08x\n", ps_dev->hw_version); } static DEVICE_ATTR_RO(hardware_version); static struct attribute *ps_device_attrs[] = { &dev_attr_firmware_version.attr, &dev_attr_hardware_version.attr, NULL }; ATTRIBUTE_GROUPS(ps_device); static int dualsense_get_calibration_data(struct dualsense *ds) { struct hid_device *hdev = ds->base.hdev; short gyro_pitch_bias, gyro_pitch_plus, gyro_pitch_minus; short gyro_yaw_bias, gyro_yaw_plus, gyro_yaw_minus; short gyro_roll_bias, gyro_roll_plus, gyro_roll_minus; short gyro_speed_plus, gyro_speed_minus; short acc_x_plus, acc_x_minus; short acc_y_plus, acc_y_minus; short acc_z_plus, acc_z_minus; int speed_2x; int range_2g; int ret = 0; int i; uint8_t *buf; buf = kzalloc(DS_FEATURE_REPORT_CALIBRATION_SIZE, GFP_KERNEL); if (!buf) return -ENOMEM; ret = ps_get_report(ds->base.hdev, DS_FEATURE_REPORT_CALIBRATION, buf, DS_FEATURE_REPORT_CALIBRATION_SIZE, true); if (ret) { hid_err(ds->base.hdev, "Failed to retrieve DualSense calibration info: %d\n", ret); goto err_free; } gyro_pitch_bias = get_unaligned_le16(&buf[1]); gyro_yaw_bias = get_unaligned_le16(&buf[3]); gyro_roll_bias = get_unaligned_le16(&buf[5]); gyro_pitch_plus = get_unaligned_le16(&buf[7]); gyro_pitch_minus = get_unaligned_le16(&buf[9]); gyro_yaw_plus = get_unaligned_le16(&buf[11]); gyro_yaw_minus = get_unaligned_le16(&buf[13]); gyro_roll_plus = get_unaligned_le16(&buf[15]); gyro_roll_minus = get_unaligned_le16(&buf[17]); gyro_speed_plus = get_unaligned_le16(&buf[19]); gyro_speed_minus = get_unaligned_le16(&buf[21]); acc_x_plus = get_unaligned_le16(&buf[23]); acc_x_minus = get_unaligned_le16(&buf[25]); acc_y_plus = get_unaligned_le16(&buf[27]); acc_y_minus = get_unaligned_le16(&buf[29]); acc_z_plus = get_unaligned_le16(&buf[31]); acc_z_minus = get_unaligned_le16(&buf[33]); /* * Set gyroscope calibration and normalization parameters. * Data values will be normalized to 1/DS_GYRO_RES_PER_DEG_S degree/s. */ speed_2x = (gyro_speed_plus + gyro_speed_minus); ds->gyro_calib_data[0].abs_code = ABS_RX; ds->gyro_calib_data[0].bias = 0; ds->gyro_calib_data[0].sens_numer = speed_2x*DS_GYRO_RES_PER_DEG_S; ds->gyro_calib_data[0].sens_denom = abs(gyro_pitch_plus - gyro_pitch_bias) + abs(gyro_pitch_minus - gyro_pitch_bias); ds->gyro_calib_data[1].abs_code = ABS_RY; ds->gyro_calib_data[1].bias = 0; ds->gyro_calib_data[1].sens_numer = speed_2x*DS_GYRO_RES_PER_DEG_S; ds->gyro_calib_data[1].sens_denom = abs(gyro_yaw_plus - gyro_yaw_bias) + abs(gyro_yaw_minus - gyro_yaw_bias); ds->gyro_calib_data[2].abs_code = ABS_RZ; ds->gyro_calib_data[2].bias = 0; ds->gyro_calib_data[2].sens_numer = speed_2x*DS_GYRO_RES_PER_DEG_S; ds->gyro_calib_data[2].sens_denom = abs(gyro_roll_plus - gyro_roll_bias) + abs(gyro_roll_minus - gyro_roll_bias); /* * Sanity check gyro calibration data. This is needed to prevent crashes * during report handling of virtual, clone or broken devices not implementing * calibration data properly. */ for (i = 0; i < ARRAY_SIZE(ds->gyro_calib_data); i++) { if (ds->gyro_calib_data[i].sens_denom == 0) { hid_warn(hdev, "Invalid gyro calibration data for axis (%d), disabling calibration.", ds->gyro_calib_data[i].abs_code); ds->gyro_calib_data[i].bias = 0; ds->gyro_calib_data[i].sens_numer = DS_GYRO_RANGE; ds->gyro_calib_data[i].sens_denom = S16_MAX; } } /* * Set accelerometer calibration and normalization parameters. * Data values will be normalized to 1/DS_ACC_RES_PER_G g. */ range_2g = acc_x_plus - acc_x_minus; ds->accel_calib_data[0].abs_code = ABS_X; ds->accel_calib_data[0].bias = acc_x_plus - range_2g / 2; ds->accel_calib_data[0].sens_numer = 2*DS_ACC_RES_PER_G; ds->accel_calib_data[0].sens_denom = range_2g; range_2g = acc_y_plus - acc_y_minus; ds->accel_calib_data[1].abs_code = ABS_Y; ds->accel_calib_data[1].bias = acc_y_plus - range_2g / 2; ds->accel_calib_data[1].sens_numer = 2*DS_ACC_RES_PER_G; ds->accel_calib_data[1].sens_denom = range_2g; range_2g = acc_z_plus - acc_z_minus; ds->accel_calib_data[2].abs_code = ABS_Z; ds->accel_calib_data[2].bias = acc_z_plus - range_2g / 2; ds->accel_calib_data[2].sens_numer = 2*DS_ACC_RES_PER_G; ds->accel_calib_data[2].sens_denom = range_2g; /* * Sanity check accelerometer calibration data. This is needed to prevent crashes * during report handling of virtual, clone or broken devices not implementing calibration * data properly. */ for (i = 0; i < ARRAY_SIZE(ds->accel_calib_data); i++) { if (ds->accel_calib_data[i].sens_denom == 0) { hid_warn(hdev, "Invalid accelerometer calibration data for axis (%d), disabling calibration.", ds->accel_calib_data[i].abs_code); ds->accel_calib_data[i].bias = 0; ds->accel_calib_data[i].sens_numer = DS_ACC_RANGE; ds->accel_calib_data[i].sens_denom = S16_MAX; } } err_free: kfree(buf); return ret; } static int dualsense_get_firmware_info(struct dualsense *ds) { uint8_t *buf; int ret; buf = kzalloc(DS_FEATURE_REPORT_FIRMWARE_INFO_SIZE, GFP_KERNEL); if (!buf) return -ENOMEM; ret = ps_get_report(ds->base.hdev, DS_FEATURE_REPORT_FIRMWARE_INFO, buf, DS_FEATURE_REPORT_FIRMWARE_INFO_SIZE, true); if (ret) { hid_err(ds->base.hdev, "Failed to retrieve DualSense firmware info: %d\n", ret); goto err_free; } ds->base.hw_version = get_unaligned_le32(&buf[24]); ds->base.fw_version = get_unaligned_le32(&buf[28]); /* Update version is some kind of feature version. It is distinct from * the firmware version as there can be many different variations of a * controller over time with the same physical shell, but with different * PCBs and other internal changes. The update version (internal name) is * used as a means to detect what features are available and change behavior. * Note: the version is different between DualSense and DualSense Edge. */ ds->update_version = get_unaligned_le16(&buf[44]); err_free: kfree(buf); return ret; } static int dualsense_get_mac_address(struct dualsense *ds) { uint8_t *buf; int ret = 0; buf = kzalloc(DS_FEATURE_REPORT_PAIRING_INFO_SIZE, GFP_KERNEL); if (!buf) return -ENOMEM; ret = ps_get_report(ds->base.hdev, DS_FEATURE_REPORT_PAIRING_INFO, buf, DS_FEATURE_REPORT_PAIRING_INFO_SIZE, true); if (ret) { hid_err(ds->base.hdev, "Failed to retrieve DualSense pairing info: %d\n", ret); goto err_free; } memcpy(ds->base.mac_address, &buf[1], sizeof(ds->base.mac_address)); err_free: kfree(buf); return ret; } static int dualsense_lightbar_set_brightness(struct led_classdev *cdev, enum led_brightness brightness) { struct led_classdev_mc *mc_cdev = lcdev_to_mccdev(cdev); struct dualsense *ds = container_of(mc_cdev, struct dualsense, lightbar); uint8_t red, green, blue; led_mc_calc_color_components(mc_cdev, brightness); red = mc_cdev->subled_info[0].brightness; green = mc_cdev->subled_info[1].brightness; blue = mc_cdev->subled_info[2].brightness; dualsense_set_lightbar(ds, red, green, blue); return 0; } static enum led_brightness dualsense_player_led_get_brightness(struct led_classdev *led) { struct hid_device *hdev = to_hid_device(led->dev->parent); struct dualsense *ds = hid_get_drvdata(hdev); return !!(ds->player_leds_state & BIT(led - ds->player_leds)); } static int dualsense_player_led_set_brightness(struct led_classdev *led, enum led_brightness value) { struct hid_device *hdev = to_hid_device(led->dev->parent); struct dualsense *ds = hid_get_drvdata(hdev); unsigned long flags; unsigned int led_index; spin_lock_irqsave(&ds->base.lock, flags); led_index = led - ds->player_leds; if (value == LED_OFF) ds->player_leds_state &= ~BIT(led_index); else ds->player_leds_state |= BIT(led_index); ds->update_player_leds = true; spin_unlock_irqrestore(&ds->base.lock, flags); dualsense_schedule_work(ds); return 0; } static void dualsense_init_output_report(struct dualsense *ds, struct dualsense_output_report *rp, void *buf) { struct hid_device *hdev = ds->base.hdev; if (hdev->bus == BUS_BLUETOOTH) { struct dualsense_output_report_bt *bt = buf; memset(bt, 0, sizeof(*bt)); bt->report_id = DS_OUTPUT_REPORT_BT; bt->tag = DS_OUTPUT_TAG; /* Tag must be set. Exact meaning is unclear. */ /* * Highest 4-bit is a sequence number, which needs to be increased * every report. Lowest 4-bit is tag and can be zero for now. */ bt->seq_tag = (ds->output_seq << 4) | 0x0; if (++ds->output_seq == 16) ds->output_seq = 0; rp->data = buf; rp->len = sizeof(*bt); rp->bt = bt; rp->usb = NULL; rp->common = &bt->common; } else { /* USB */ struct dualsense_output_report_usb *usb = buf; memset(usb, 0, sizeof(*usb)); usb->report_id = DS_OUTPUT_REPORT_USB; rp->data = buf; rp->len = sizeof(*usb); rp->bt = NULL; rp->usb = usb; rp->common = &usb->common; } } static inline void dualsense_schedule_work(struct dualsense *ds) { unsigned long flags; spin_lock_irqsave(&ds->base.lock, flags); if (ds->output_worker_initialized) schedule_work(&ds->output_worker); spin_unlock_irqrestore(&ds->base.lock, flags); } /* * Helper function to send DualSense output reports. Applies a CRC at the end of a report * for Bluetooth reports. */ static void dualsense_send_output_report(struct dualsense *ds, struct dualsense_output_report *report) { struct hid_device *hdev = ds->base.hdev; /* Bluetooth packets need to be signed with a CRC in the last 4 bytes. */ if (report->bt) { uint32_t crc; uint8_t seed = PS_OUTPUT_CRC32_SEED; crc = crc32_le(0xFFFFFFFF, &seed, 1); crc = ~crc32_le(crc, report->data, report->len - 4); report->bt->crc32 = cpu_to_le32(crc); } hid_hw_output_report(hdev, report->data, report->len); } static void dualsense_output_worker(struct work_struct *work) { struct dualsense *ds = container_of(work, struct dualsense, output_worker); struct dualsense_output_report report; struct dualsense_output_report_common *common; unsigned long flags; dualsense_init_output_report(ds, &report, ds->output_report_dmabuf); common = report.common; spin_lock_irqsave(&ds->base.lock, flags); if (ds->update_rumble) { /* Select classic rumble style haptics and enable it. */ common->valid_flag0 |= DS_OUTPUT_VALID_FLAG0_HAPTICS_SELECT; if (ds->use_vibration_v2) common->valid_flag2 |= DS_OUTPUT_VALID_FLAG2_COMPATIBLE_VIBRATION2; else common->valid_flag0 |= DS_OUTPUT_VALID_FLAG0_COMPATIBLE_VIBRATION; common->motor_left = ds->motor_left; common->motor_right = ds->motor_right; ds->update_rumble = false; } if (ds->update_lightbar) { common->valid_flag1 |= DS_OUTPUT_VALID_FLAG1_LIGHTBAR_CONTROL_ENABLE; common->lightbar_red = ds->lightbar_red; common->lightbar_green = ds->lightbar_green; common->lightbar_blue = ds->lightbar_blue; ds->update_lightbar = false; } if (ds->update_player_leds) { common->valid_flag1 |= DS_OUTPUT_VALID_FLAG1_PLAYER_INDICATOR_CONTROL_ENABLE; common->player_leds = ds->player_leds_state; ds->update_player_leds = false; } if (ds->update_mic_mute) { common->valid_flag1 |= DS_OUTPUT_VALID_FLAG1_MIC_MUTE_LED_CONTROL_ENABLE; common->mute_button_led = ds->mic_muted; if (ds->mic_muted) { /* Disable microphone */ common->valid_flag1 |= DS_OUTPUT_VALID_FLAG1_POWER_SAVE_CONTROL_ENABLE; common->power_save_control |= DS_OUTPUT_POWER_SAVE_CONTROL_MIC_MUTE; } else { /* Enable microphone */ common->valid_flag1 |= DS_OUTPUT_VALID_FLAG1_POWER_SAVE_CONTROL_ENABLE; common->power_save_control &= ~DS_OUTPUT_POWER_SAVE_CONTROL_MIC_MUTE; } ds->update_mic_mute = false; } spin_unlock_irqrestore(&ds->base.lock, flags); dualsense_send_output_report(ds, &report); } static int dualsense_parse_report(struct ps_device *ps_dev, struct hid_report *report, u8 *data, int size) { struct hid_device *hdev = ps_dev->hdev; struct dualsense *ds = container_of(ps_dev, struct dualsense, base); struct dualsense_input_report *ds_report; uint8_t battery_data, battery_capacity, charging_status, value; int battery_status; uint32_t sensor_timestamp; bool btn_mic_state; unsigned long flags; int i; /* * DualSense in USB uses the full HID report for reportID 1, but * Bluetooth uses a minimal HID report for reportID 1 and reports * the full report using reportID 49. */ if (hdev->bus == BUS_USB && report->id == DS_INPUT_REPORT_USB && size == DS_INPUT_REPORT_USB_SIZE) { ds_report = (struct dualsense_input_report *)&data[1]; } else if (hdev->bus == BUS_BLUETOOTH && report->id == DS_INPUT_REPORT_BT && size == DS_INPUT_REPORT_BT_SIZE) { /* Last 4 bytes of input report contain crc32 */ uint32_t report_crc = get_unaligned_le32(&data[size - 4]); if (!ps_check_crc32(PS_INPUT_CRC32_SEED, data, size - 4, report_crc)) { hid_err(hdev, "DualSense input CRC's check failed\n"); return -EILSEQ; } ds_report = (struct dualsense_input_report *)&data[2]; } else { hid_err(hdev, "Unhandled reportID=%d\n", report->id); return -1; } input_report_abs(ds->gamepad, ABS_X, ds_report->x); input_report_abs(ds->gamepad, ABS_Y, ds_report->y); input_report_abs(ds->gamepad, ABS_RX, ds_report->rx); input_report_abs(ds->gamepad, ABS_RY, ds_report->ry); input_report_abs(ds->gamepad, ABS_Z, ds_report->z); input_report_abs(ds->gamepad, ABS_RZ, ds_report->rz); value = ds_report->buttons[0] & DS_BUTTONS0_HAT_SWITCH; if (value >= ARRAY_SIZE(ps_gamepad_hat_mapping)) value = 8; /* center */ input_report_abs(ds->gamepad, ABS_HAT0X, ps_gamepad_hat_mapping[value].x); input_report_abs(ds->gamepad, ABS_HAT0Y, ps_gamepad_hat_mapping[value].y); input_report_key(ds->gamepad, BTN_WEST, ds_report->buttons[0] & DS_BUTTONS0_SQUARE); input_report_key(ds->gamepad, BTN_SOUTH, ds_report->buttons[0] & DS_BUTTONS0_CROSS); input_report_key(ds->gamepad, BTN_EAST, ds_report->buttons[0] & DS_BUTTONS0_CIRCLE); input_report_key(ds->gamepad, BTN_NORTH, ds_report->buttons[0] & DS_BUTTONS0_TRIANGLE); input_report_key(ds->gamepad, BTN_TL, ds_report->buttons[1] & DS_BUTTONS1_L1); input_report_key(ds->gamepad, BTN_TR, ds_report->buttons[1] & DS_BUTTONS1_R1); input_report_key(ds->gamepad, BTN_TL2, ds_report->buttons[1] & DS_BUTTONS1_L2); input_report_key(ds->gamepad, BTN_TR2, ds_report->buttons[1] & DS_BUTTONS1_R2); input_report_key(ds->gamepad, BTN_SELECT, ds_report->buttons[1] & DS_BUTTONS1_CREATE); input_report_key(ds->gamepad, BTN_START, ds_report->buttons[1] & DS_BUTTONS1_OPTIONS); input_report_key(ds->gamepad, BTN_THUMBL, ds_report->buttons[1] & DS_BUTTONS1_L3); input_report_key(ds->gamepad, BTN_THUMBR, ds_report->buttons[1] & DS_BUTTONS1_R3); input_report_key(ds->gamepad, BTN_MODE, ds_report->buttons[2] & DS_BUTTONS2_PS_HOME); input_sync(ds->gamepad); /* * The DualSense has an internal microphone, which can be muted through a mute button * on the device. The driver is expected to read the button state and program the device * to mute/unmute audio at the hardware level. */ btn_mic_state = !!(ds_report->buttons[2] & DS_BUTTONS2_MIC_MUTE); if (btn_mic_state && !ds->last_btn_mic_state) { spin_lock_irqsave(&ps_dev->lock, flags); ds->update_mic_mute = true; ds->mic_muted = !ds->mic_muted; /* toggle */ spin_unlock_irqrestore(&ps_dev->lock, flags); /* Schedule updating of microphone state at hardware level. */ dualsense_schedule_work(ds); } ds->last_btn_mic_state = btn_mic_state; /* Parse and calibrate gyroscope data. */ for (i = 0; i < ARRAY_SIZE(ds_report->gyro); i++) { int raw_data = (short)le16_to_cpu(ds_report->gyro[i]); int calib_data = mult_frac(ds->gyro_calib_data[i].sens_numer, raw_data, ds->gyro_calib_data[i].sens_denom); input_report_abs(ds->sensors, ds->gyro_calib_data[i].abs_code, calib_data); } /* Parse and calibrate accelerometer data. */ for (i = 0; i < ARRAY_SIZE(ds_report->accel); i++) { int raw_data = (short)le16_to_cpu(ds_report->accel[i]); int calib_data = mult_frac(ds->accel_calib_data[i].sens_numer, raw_data - ds->accel_calib_data[i].bias, ds->accel_calib_data[i].sens_denom); input_report_abs(ds->sensors, ds->accel_calib_data[i].abs_code, calib_data); } /* Convert timestamp (in 0.33us unit) to timestamp_us */ sensor_timestamp = le32_to_cpu(ds_report->sensor_timestamp); if (!ds->sensor_timestamp_initialized) { ds->sensor_timestamp_us = DIV_ROUND_CLOSEST(sensor_timestamp, 3); ds->sensor_timestamp_initialized = true; } else { uint32_t delta; if (ds->prev_sensor_timestamp > sensor_timestamp) delta = (U32_MAX - ds->prev_sensor_timestamp + sensor_timestamp + 1); else delta = sensor_timestamp - ds->prev_sensor_timestamp; ds->sensor_timestamp_us += DIV_ROUND_CLOSEST(delta, 3); } ds->prev_sensor_timestamp = sensor_timestamp; input_event(ds->sensors, EV_MSC, MSC_TIMESTAMP, ds->sensor_timestamp_us); input_sync(ds->sensors); for (i = 0; i < ARRAY_SIZE(ds_report->points); i++) { struct dualsense_touch_point *point = &ds_report->points[i]; bool active = (point->contact & DS_TOUCH_POINT_INACTIVE) ? false : true; input_mt_slot(ds->touchpad, i); input_mt_report_slot_state(ds->touchpad, MT_TOOL_FINGER, active); if (active) { int x = (point->x_hi << 8) | point->x_lo; int y = (point->y_hi << 4) | point->y_lo; input_report_abs(ds->touchpad, ABS_MT_POSITION_X, x); input_report_abs(ds->touchpad, ABS_MT_POSITION_Y, y); } } input_mt_sync_frame(ds->touchpad); input_report_key(ds->touchpad, BTN_LEFT, ds_report->buttons[2] & DS_BUTTONS2_TOUCHPAD); input_sync(ds->touchpad); battery_data = ds_report->status & DS_STATUS_BATTERY_CAPACITY; charging_status = (ds_report->status & DS_STATUS_CHARGING) >> DS_STATUS_CHARGING_SHIFT; switch (charging_status) { case 0x0: /* * Each unit of battery data corresponds to 10% * 0 = 0-9%, 1 = 10-19%, .. and 10 = 100% */ battery_capacity = min(battery_data * 10 + 5, 100); battery_status = POWER_SUPPLY_STATUS_DISCHARGING; break; case 0x1: battery_capacity = min(battery_data * 10 + 5, 100); battery_status = POWER_SUPPLY_STATUS_CHARGING; break; case 0x2: battery_capacity = 100; battery_status = POWER_SUPPLY_STATUS_FULL; break; case 0xa: /* voltage or temperature out of range */ case 0xb: /* temperature error */ battery_capacity = 0; battery_status = POWER_SUPPLY_STATUS_NOT_CHARGING; break; case 0xf: /* charging error */ default: battery_capacity = 0; battery_status = POWER_SUPPLY_STATUS_UNKNOWN; } spin_lock_irqsave(&ps_dev->lock, flags); ps_dev->battery_capacity = battery_capacity; ps_dev->battery_status = battery_status; spin_unlock_irqrestore(&ps_dev->lock, flags); return 0; } static int dualsense_play_effect(struct input_dev *dev, void *data, struct ff_effect *effect) { struct hid_device *hdev = input_get_drvdata(dev); struct dualsense *ds = hid_get_drvdata(hdev); unsigned long flags; if (effect->type != FF_RUMBLE) return 0; spin_lock_irqsave(&ds->base.lock, flags); ds->update_rumble = true; ds->motor_left = effect->u.rumble.strong_magnitude / 256; ds->motor_right = effect->u.rumble.weak_magnitude / 256; spin_unlock_irqrestore(&ds->base.lock, flags); dualsense_schedule_work(ds); return 0; } static void dualsense_remove(struct ps_device *ps_dev) { struct dualsense *ds = container_of(ps_dev, struct dualsense, base); unsigned long flags; spin_lock_irqsave(&ds->base.lock, flags); ds->output_worker_initialized = false; spin_unlock_irqrestore(&ds->base.lock, flags); cancel_work_sync(&ds->output_worker); } static int dualsense_reset_leds(struct dualsense *ds) { struct dualsense_output_report report; uint8_t *buf; buf = kzalloc(sizeof(struct dualsense_output_report_bt), GFP_KERNEL); if (!buf) return -ENOMEM; dualsense_init_output_report(ds, &report, buf); /* * On Bluetooth the DualSense outputs an animation on the lightbar * during startup and maintains a color afterwards. We need to explicitly * reconfigure the lightbar before we can do any programming later on. * In USB the lightbar is not on by default, but redoing the setup there * doesn't hurt. */ report.common->valid_flag2 = DS_OUTPUT_VALID_FLAG2_LIGHTBAR_SETUP_CONTROL_ENABLE; report.common->lightbar_setup = DS_OUTPUT_LIGHTBAR_SETUP_LIGHT_OUT; /* Fade light out. */ dualsense_send_output_report(ds, &report); kfree(buf); return 0; } static void dualsense_set_lightbar(struct dualsense *ds, uint8_t red, uint8_t green, uint8_t blue) { unsigned long flags; spin_lock_irqsave(&ds->base.lock, flags); ds->update_lightbar = true; ds->lightbar_red = red; ds->lightbar_green = green; ds->lightbar_blue = blue; spin_unlock_irqrestore(&ds->base.lock, flags); dualsense_schedule_work(ds); } static void dualsense_set_player_leds(struct dualsense *ds) { /* * The DualSense controller has a row of 5 LEDs used for player ids. * Behavior on the PlayStation 5 console is to center the player id * across the LEDs, so e.g. player 1 would be "--x--" with x being 'on'. * Follow a similar mapping here. */ static const int player_ids[5] = { BIT(2), BIT(3) | BIT(1), BIT(4) | BIT(2) | BIT(0), BIT(4) | BIT(3) | BIT(1) | BIT(0), BIT(4) | BIT(3) | BIT(2) | BIT(1) | BIT(0) }; uint8_t player_id = ds->base.player_id % ARRAY_SIZE(player_ids); ds->update_player_leds = true; ds->player_leds_state = player_ids[player_id]; dualsense_schedule_work(ds); } static struct ps_device *dualsense_create(struct hid_device *hdev) { struct dualsense *ds; struct ps_device *ps_dev; uint8_t max_output_report_size; int i, ret; static const struct ps_led_info player_leds_info[] = { { LED_FUNCTION_PLAYER1, "white", 1, dualsense_player_led_get_brightness, dualsense_player_led_set_brightness }, { LED_FUNCTION_PLAYER2, "white", 1, dualsense_player_led_get_brightness, dualsense_player_led_set_brightness }, { LED_FUNCTION_PLAYER3, "white", 1, dualsense_player_led_get_brightness, dualsense_player_led_set_brightness }, { LED_FUNCTION_PLAYER4, "white", 1, dualsense_player_led_get_brightness, dualsense_player_led_set_brightness }, { LED_FUNCTION_PLAYER5, "white", 1, dualsense_player_led_get_brightness, dualsense_player_led_set_brightness } }; ds = devm_kzalloc(&hdev->dev, sizeof(*ds), GFP_KERNEL); if (!ds) return ERR_PTR(-ENOMEM); /* * Patch version to allow userspace to distinguish between * hid-generic vs hid-playstation axis and button mapping. */ hdev->version |= HID_PLAYSTATION_VERSION_PATCH; ps_dev = &ds->base; ps_dev->hdev = hdev; spin_lock_init(&ps_dev->lock); ps_dev->battery_capacity = 100; /* initial value until parse_report. */ ps_dev->battery_status = POWER_SUPPLY_STATUS_UNKNOWN; ps_dev->parse_report = dualsense_parse_report; ps_dev->remove = dualsense_remove; INIT_WORK(&ds->output_worker, dualsense_output_worker); ds->output_worker_initialized = true; hid_set_drvdata(hdev, ds); max_output_report_size = sizeof(struct dualsense_output_report_bt); ds->output_report_dmabuf = devm_kzalloc(&hdev->dev, max_output_report_size, GFP_KERNEL); if (!ds->output_report_dmabuf) return ERR_PTR(-ENOMEM); ret = dualsense_get_mac_address(ds); if (ret) { hid_err(hdev, "Failed to get MAC address from DualSense\n"); return ERR_PTR(ret); } snprintf(hdev->uniq, sizeof(hdev->uniq), "%pMR", ds->base.mac_address); ret = dualsense_get_firmware_info(ds); if (ret) { hid_err(hdev, "Failed to get firmware info from DualSense\n"); return ERR_PTR(ret); } /* Original DualSense firmware simulated classic controller rumble through * its new haptics hardware. It felt different from classic rumble users * were used to. Since then new firmwares were introduced to change behavior * and make this new 'v2' behavior default on PlayStation and other platforms. * The original DualSense requires a new enough firmware as bundled with PS5 * software released in 2021. DualSense edge supports it out of the box. * Both devices also support the old mode, but it is not really used. */ if (hdev->product == USB_DEVICE_ID_SONY_PS5_CONTROLLER) { /* Feature version 2.21 introduced new vibration method. */ ds->use_vibration_v2 = ds->update_version >= DS_FEATURE_VERSION(2, 21); } else if (hdev->product == USB_DEVICE_ID_SONY_PS5_CONTROLLER_2) { ds->use_vibration_v2 = true; } ret = ps_devices_list_add(ps_dev); if (ret) return ERR_PTR(ret); ret = dualsense_get_calibration_data(ds); if (ret) { hid_err(hdev, "Failed to get calibration data from DualSense\n"); goto err; } ds->gamepad = ps_gamepad_create(hdev, dualsense_play_effect); if (IS_ERR(ds->gamepad)) { ret = PTR_ERR(ds->gamepad); goto err; } /* Use gamepad input device name as primary device name for e.g. LEDs */ ps_dev->input_dev_name = dev_name(&ds->gamepad->dev); ds->sensors = ps_sensors_create(hdev, DS_ACC_RANGE, DS_ACC_RES_PER_G, DS_GYRO_RANGE, DS_GYRO_RES_PER_DEG_S); if (IS_ERR(ds->sensors)) { ret = PTR_ERR(ds->sensors); goto err; } ds->touchpad = ps_touchpad_create(hdev, DS_TOUCHPAD_WIDTH, DS_TOUCHPAD_HEIGHT, 2); if (IS_ERR(ds->touchpad)) { ret = PTR_ERR(ds->touchpad); goto err; } ret = ps_device_register_battery(ps_dev); if (ret) goto err; /* * The hardware may have control over the LEDs (e.g. in Bluetooth on startup). * Reset the LEDs (lightbar, mute, player leds), so we can control them * from software. */ ret = dualsense_reset_leds(ds); if (ret) goto err; ret = ps_lightbar_register(ps_dev, &ds->lightbar, dualsense_lightbar_set_brightness); if (ret) goto err; /* Set default lightbar color. */ dualsense_set_lightbar(ds, 0, 0, 128); /* blue */ for (i = 0; i < ARRAY_SIZE(player_leds_info); i++) { const struct ps_led_info *led_info = &player_leds_info[i]; ret = ps_led_register(ps_dev, &ds->player_leds[i], led_info); if (ret < 0) goto err; } ret = ps_device_set_player_id(ps_dev); if (ret) { hid_err(hdev, "Failed to assign player id for DualSense: %d\n", ret); goto err; } /* Set player LEDs to our player id. */ dualsense_set_player_leds(ds); /* * Reporting hardware and firmware is important as there are frequent updates, which * can change behavior. */ hid_info(hdev, "Registered DualSense controller hw_version=0x%08x fw_version=0x%08x\n", ds->base.hw_version, ds->base.fw_version); return &ds->base; err: ps_devices_list_remove(ps_dev); return ERR_PTR(ret); } static void dualshock4_dongle_calibration_work(struct work_struct *work) { struct dualshock4 *ds4 = container_of(work, struct dualshock4, dongle_hotplug_worker); unsigned long flags; enum dualshock4_dongle_state dongle_state; int ret; ret = dualshock4_get_calibration_data(ds4); if (ret < 0) { /* This call is very unlikely to fail for the dongle. When it * fails we are probably in a very bad state, so mark the * dongle as disabled. We will re-enable the dongle if a new * DS4 hotplug is detect from sony_raw_event as any issues * are likely resolved then (the dongle is quite stupid). */ hid_err(ds4->base.hdev, "DualShock 4 USB dongle: calibration failed, disabling device\n"); dongle_state = DONGLE_DISABLED; } else { hid_info(ds4->base.hdev, "DualShock 4 USB dongle: calibration completed\n"); dongle_state = DONGLE_CONNECTED; } spin_lock_irqsave(&ds4->base.lock, flags); ds4->dongle_state = dongle_state; spin_unlock_irqrestore(&ds4->base.lock, flags); } static int dualshock4_get_calibration_data(struct dualshock4 *ds4) { struct hid_device *hdev = ds4->base.hdev; short gyro_pitch_bias, gyro_pitch_plus, gyro_pitch_minus; short gyro_yaw_bias, gyro_yaw_plus, gyro_yaw_minus; short gyro_roll_bias, gyro_roll_plus, gyro_roll_minus; short gyro_speed_plus, gyro_speed_minus; short acc_x_plus, acc_x_minus; short acc_y_plus, acc_y_minus; short acc_z_plus, acc_z_minus; int speed_2x; int range_2g; int ret = 0; int i; uint8_t *buf; if (ds4->base.hdev->bus == BUS_USB) { int retries; buf = kzalloc(DS4_FEATURE_REPORT_CALIBRATION_SIZE, GFP_KERNEL); if (!buf) { ret = -ENOMEM; goto transfer_failed; } /* We should normally receive the feature report data we asked * for, but hidraw applications such as Steam can issue feature * reports as well. In particular for Dongle reconnects, Steam * and this function are competing resulting in often receiving * data for a different HID report, so retry a few times. */ for (retries = 0; retries < 3; retries++) { ret = ps_get_report(hdev, DS4_FEATURE_REPORT_CALIBRATION, buf, DS4_FEATURE_REPORT_CALIBRATION_SIZE, true); if (ret) { if (retries < 2) { hid_warn(hdev, "Retrying DualShock 4 get calibration report (0x02) request\n"); continue; } hid_warn(hdev, "Failed to retrieve DualShock4 calibration info: %d\n", ret); ret = -EILSEQ; goto transfer_failed; } else { break; } } } else { /* Bluetooth */ buf = kzalloc(DS4_FEATURE_REPORT_CALIBRATION_BT_SIZE, GFP_KERNEL); if (!buf) { ret = -ENOMEM; goto transfer_failed; } ret = ps_get_report(hdev, DS4_FEATURE_REPORT_CALIBRATION_BT, buf, DS4_FEATURE_REPORT_CALIBRATION_BT_SIZE, true); if (ret) { hid_warn(hdev, "Failed to retrieve DualShock4 calibration info: %d\n", ret); goto transfer_failed; } } /* Transfer succeeded - parse the calibration data received. */ gyro_pitch_bias = get_unaligned_le16(&buf[1]); gyro_yaw_bias = get_unaligned_le16(&buf[3]); gyro_roll_bias = get_unaligned_le16(&buf[5]); if (ds4->base.hdev->bus == BUS_USB) { gyro_pitch_plus = get_unaligned_le16(&buf[7]); gyro_pitch_minus = get_unaligned_le16(&buf[9]); gyro_yaw_plus = get_unaligned_le16(&buf[11]); gyro_yaw_minus = get_unaligned_le16(&buf[13]); gyro_roll_plus = get_unaligned_le16(&buf[15]); gyro_roll_minus = get_unaligned_le16(&buf[17]); } else { /* BT + Dongle */ gyro_pitch_plus = get_unaligned_le16(&buf[7]); gyro_yaw_plus = get_unaligned_le16(&buf[9]); gyro_roll_plus = get_unaligned_le16(&buf[11]); gyro_pitch_minus = get_unaligned_le16(&buf[13]); gyro_yaw_minus = get_unaligned_le16(&buf[15]); gyro_roll_minus = get_unaligned_le16(&buf[17]); } gyro_speed_plus = get_unaligned_le16(&buf[19]); gyro_speed_minus = get_unaligned_le16(&buf[21]); acc_x_plus = get_unaligned_le16(&buf[23]); acc_x_minus = get_unaligned_le16(&buf[25]); acc_y_plus = get_unaligned_le16(&buf[27]); acc_y_minus = get_unaligned_le16(&buf[29]); acc_z_plus = get_unaligned_le16(&buf[31]); acc_z_minus = get_unaligned_le16(&buf[33]); /* Done parsing the buffer, so let's free it. */ kfree(buf); /* * Set gyroscope calibration and normalization parameters. * Data values will be normalized to 1/DS4_GYRO_RES_PER_DEG_S degree/s. */ speed_2x = (gyro_speed_plus + gyro_speed_minus); ds4->gyro_calib_data[0].abs_code = ABS_RX; ds4->gyro_calib_data[0].bias = 0; ds4->gyro_calib_data[0].sens_numer = speed_2x*DS4_GYRO_RES_PER_DEG_S; ds4->gyro_calib_data[0].sens_denom = abs(gyro_pitch_plus - gyro_pitch_bias) + abs(gyro_pitch_minus - gyro_pitch_bias); ds4->gyro_calib_data[1].abs_code = ABS_RY; ds4->gyro_calib_data[1].bias = 0; ds4->gyro_calib_data[1].sens_numer = speed_2x*DS4_GYRO_RES_PER_DEG_S; ds4->gyro_calib_data[1].sens_denom = abs(gyro_yaw_plus - gyro_yaw_bias) + abs(gyro_yaw_minus - gyro_yaw_bias); ds4->gyro_calib_data[2].abs_code = ABS_RZ; ds4->gyro_calib_data[2].bias = 0; ds4->gyro_calib_data[2].sens_numer = speed_2x*DS4_GYRO_RES_PER_DEG_S; ds4->gyro_calib_data[2].sens_denom = abs(gyro_roll_plus - gyro_roll_bias) + abs(gyro_roll_minus - gyro_roll_bias); /* * Set accelerometer calibration and normalization parameters. * Data values will be normalized to 1/DS4_ACC_RES_PER_G g. */ range_2g = acc_x_plus - acc_x_minus; ds4->accel_calib_data[0].abs_code = ABS_X; ds4->accel_calib_data[0].bias = acc_x_plus - range_2g / 2; ds4->accel_calib_data[0].sens_numer = 2*DS4_ACC_RES_PER_G; ds4->accel_calib_data[0].sens_denom = range_2g; range_2g = acc_y_plus - acc_y_minus; ds4->accel_calib_data[1].abs_code = ABS_Y; ds4->accel_calib_data[1].bias = acc_y_plus - range_2g / 2; ds4->accel_calib_data[1].sens_numer = 2*DS4_ACC_RES_PER_G; ds4->accel_calib_data[1].sens_denom = range_2g; range_2g = acc_z_plus - acc_z_minus; ds4->accel_calib_data[2].abs_code = ABS_Z; ds4->accel_calib_data[2].bias = acc_z_plus - range_2g / 2; ds4->accel_calib_data[2].sens_numer = 2*DS4_ACC_RES_PER_G; ds4->accel_calib_data[2].sens_denom = range_2g; transfer_failed: /* * Sanity check gyro calibration data. This is needed to prevent crashes * during report handling of virtual, clone or broken devices not implementing * calibration data properly. */ for (i = 0; i < ARRAY_SIZE(ds4->gyro_calib_data); i++) { if (ds4->gyro_calib_data[i].sens_denom == 0) { ds4->gyro_calib_data[i].abs_code = ABS_RX + i; hid_warn(hdev, "Invalid gyro calibration data for axis (%d), disabling calibration.", ds4->gyro_calib_data[i].abs_code); ds4->gyro_calib_data[i].bias = 0; ds4->gyro_calib_data[i].sens_numer = DS4_GYRO_RANGE; ds4->gyro_calib_data[i].sens_denom = S16_MAX; } } /* * Sanity check accelerometer calibration data. This is needed to prevent crashes * during report handling of virtual, clone or broken devices not implementing calibration * data properly. */ for (i = 0; i < ARRAY_SIZE(ds4->accel_calib_data); i++) { if (ds4->accel_calib_data[i].sens_denom == 0) { ds4->accel_calib_data[i].abs_code = ABS_X + i; hid_warn(hdev, "Invalid accelerometer calibration data for axis (%d), disabling calibration.", ds4->accel_calib_data[i].abs_code); ds4->accel_calib_data[i].bias = 0; ds4->accel_calib_data[i].sens_numer = DS4_ACC_RANGE; ds4->accel_calib_data[i].sens_denom = S16_MAX; } } return ret; } static int dualshock4_get_firmware_info(struct dualshock4 *ds4) { uint8_t *buf; int ret; buf = kzalloc(DS4_FEATURE_REPORT_FIRMWARE_INFO_SIZE, GFP_KERNEL); if (!buf) return -ENOMEM; /* Note USB and BT support the same feature report, but this report * lacks CRC support, so must be disabled in ps_get_report. */ ret = ps_get_report(ds4->base.hdev, DS4_FEATURE_REPORT_FIRMWARE_INFO, buf, DS4_FEATURE_REPORT_FIRMWARE_INFO_SIZE, false); if (ret) { hid_err(ds4->base.hdev, "Failed to retrieve DualShock4 firmware info: %d\n", ret); goto err_free; } ds4->base.hw_version = get_unaligned_le16(&buf[35]); ds4->base.fw_version = get_unaligned_le16(&buf[41]); err_free: kfree(buf); return ret; } static int dualshock4_get_mac_address(struct dualshock4 *ds4) { struct hid_device *hdev = ds4->base.hdev; uint8_t *buf; int ret = 0; if (hdev->bus == BUS_USB) { buf = kzalloc(DS4_FEATURE_REPORT_PAIRING_INFO_SIZE, GFP_KERNEL); if (!buf) return -ENOMEM; ret = ps_get_report(hdev, DS4_FEATURE_REPORT_PAIRING_INFO, buf, DS4_FEATURE_REPORT_PAIRING_INFO_SIZE, false); if (ret) { hid_err(hdev, "Failed to retrieve DualShock4 pairing info: %d\n", ret); goto err_free; } memcpy(ds4->base.mac_address, &buf[1], sizeof(ds4->base.mac_address)); } else { /* Rely on HIDP for Bluetooth */ if (strlen(hdev->uniq) != 17) return -EINVAL; ret = sscanf(hdev->uniq, "%02hhx:%02hhx:%02hhx:%02hhx:%02hhx:%02hhx", &ds4->base.mac_address[5], &ds4->base.mac_address[4], &ds4->base.mac_address[3], &ds4->base.mac_address[2], &ds4->base.mac_address[1], &ds4->base.mac_address[0]); if (ret != sizeof(ds4->base.mac_address)) return -EINVAL; return 0; } err_free: kfree(buf); return ret; } static enum led_brightness dualshock4_led_get_brightness(struct led_classdev *led) { struct hid_device *hdev = to_hid_device(led->dev->parent); struct dualshock4 *ds4 = hid_get_drvdata(hdev); unsigned int led_index; led_index = led - ds4->lightbar_leds; switch (led_index) { case 0: return ds4->lightbar_red; case 1: return ds4->lightbar_green; case 2: return ds4->lightbar_blue; case 3: return ds4->lightbar_enabled; } return -1; } static int dualshock4_led_set_blink(struct led_classdev *led, unsigned long *delay_on, unsigned long *delay_off) { struct hid_device *hdev = to_hid_device(led->dev->parent); struct dualshock4 *ds4 = hid_get_drvdata(hdev); unsigned long flags; spin_lock_irqsave(&ds4->base.lock, flags); if (!*delay_on && !*delay_off) { /* Default to 1 Hz (50 centiseconds on, 50 centiseconds off). */ ds4->lightbar_blink_on = 50; ds4->lightbar_blink_off = 50; } else { /* Blink delays in centiseconds. */ ds4->lightbar_blink_on = min_t(unsigned long, *delay_on/10, DS4_LIGHTBAR_MAX_BLINK); ds4->lightbar_blink_off = min_t(unsigned long, *delay_off/10, DS4_LIGHTBAR_MAX_BLINK); } ds4->update_lightbar_blink = true; spin_unlock_irqrestore(&ds4->base.lock, flags); dualshock4_schedule_work(ds4); /* Report scaled values back to LED subsystem */ *delay_on = ds4->lightbar_blink_on * 10; *delay_off = ds4->lightbar_blink_off * 10; return 0; } static int dualshock4_led_set_brightness(struct led_classdev *led, enum led_brightness value) { struct hid_device *hdev = to_hid_device(led->dev->parent); struct dualshock4 *ds4 = hid_get_drvdata(hdev); unsigned long flags; unsigned int led_index; spin_lock_irqsave(&ds4->base.lock, flags); led_index = led - ds4->lightbar_leds; switch (led_index) { case 0: ds4->lightbar_red = value; break; case 1: ds4->lightbar_green = value; break; case 2: ds4->lightbar_blue = value; break; case 3: ds4->lightbar_enabled = !!value; /* brightness = 0 also cancels blinking in Linux. */ if (!ds4->lightbar_enabled) { ds4->lightbar_blink_off = 0; ds4->lightbar_blink_on = 0; ds4->update_lightbar_blink = true; } } ds4->update_lightbar = true; spin_unlock_irqrestore(&ds4->base.lock, flags); dualshock4_schedule_work(ds4); return 0; } static void dualshock4_init_output_report(struct dualshock4 *ds4, struct dualshock4_output_report *rp, void *buf) { struct hid_device *hdev = ds4->base.hdev; if (hdev->bus == BUS_BLUETOOTH) { struct dualshock4_output_report_bt *bt = buf; memset(bt, 0, sizeof(*bt)); bt->report_id = DS4_OUTPUT_REPORT_BT; rp->data = buf; rp->len = sizeof(*bt); rp->bt = bt; rp->usb = NULL; rp->common = &bt->common; } else { /* USB */ struct dualshock4_output_report_usb *usb = buf; memset(usb, 0, sizeof(*usb)); usb->report_id = DS4_OUTPUT_REPORT_USB; rp->data = buf; rp->len = sizeof(*usb); rp->bt = NULL; rp->usb = usb; rp->common = &usb->common; } } static void dualshock4_output_worker(struct work_struct *work) { struct dualshock4 *ds4 = container_of(work, struct dualshock4, output_worker); struct dualshock4_output_report report; struct dualshock4_output_report_common *common; unsigned long flags; dualshock4_init_output_report(ds4, &report, ds4->output_report_dmabuf); common = report.common; spin_lock_irqsave(&ds4->base.lock, flags); /* * Some 3rd party gamepads expect updates to rumble and lightbar * together, and setting one may cancel the other. * * Let's maximise compatibility by always sending rumble and lightbar * updates together, even when only one has been scheduled, resulting * in: * * ds4->valid_flag0 >= 0x03 * * Hopefully this will maximise compatibility with third-party pads. * * Any further update bits, such as 0x04 for lightbar blinking, will * be or'd on top of this like before. */ if (ds4->update_rumble || ds4->update_lightbar) { ds4->update_rumble = true; /* 0x01 */ ds4->update_lightbar = true; /* 0x02 */ } if (ds4->update_rumble) { /* Select classic rumble style haptics and enable it. */ common->valid_flag0 |= DS4_OUTPUT_VALID_FLAG0_MOTOR; common->motor_left = ds4->motor_left; common->motor_right = ds4->motor_right; ds4->update_rumble = false; } if (ds4->update_lightbar) { common->valid_flag0 |= DS4_OUTPUT_VALID_FLAG0_LED; /* Comptabile behavior with hid-sony, which used a dummy global LED to * allow enabling/disabling the lightbar. The global LED maps to * lightbar_enabled. */ common->lightbar_red = ds4->lightbar_enabled ? ds4->lightbar_red : 0; common->lightbar_green = ds4->lightbar_enabled ? ds4->lightbar_green : 0; common->lightbar_blue = ds4->lightbar_enabled ? ds4->lightbar_blue : 0; ds4->update_lightbar = false; } if (ds4->update_lightbar_blink) { common->valid_flag0 |= DS4_OUTPUT_VALID_FLAG0_LED_BLINK; common->lightbar_blink_on = ds4->lightbar_blink_on; common->lightbar_blink_off = ds4->lightbar_blink_off; ds4->update_lightbar_blink = false; } spin_unlock_irqrestore(&ds4->base.lock, flags); /* Bluetooth packets need additional flags as well as a CRC in the last 4 bytes. */ if (report.bt) { uint32_t crc; uint8_t seed = PS_OUTPUT_CRC32_SEED; /* Hardware control flags need to set to let the device know * there is HID data as well as CRC. */ report.bt->hw_control = DS4_OUTPUT_HWCTL_HID | DS4_OUTPUT_HWCTL_CRC32; if (ds4->update_bt_poll_interval) { report.bt->hw_control |= ds4->bt_poll_interval; ds4->update_bt_poll_interval = false; } crc = crc32_le(0xFFFFFFFF, &seed, 1); crc = ~crc32_le(crc, report.data, report.len - 4); report.bt->crc32 = cpu_to_le32(crc); } hid_hw_output_report(ds4->base.hdev, report.data, report.len); } static int dualshock4_parse_report(struct ps_device *ps_dev, struct hid_report *report, u8 *data, int size) { struct hid_device *hdev = ps_dev->hdev; struct dualshock4 *ds4 = container_of(ps_dev, struct dualshock4, base); struct dualshock4_input_report_common *ds4_report; struct dualshock4_touch_report *touch_reports; uint8_t battery_capacity, num_touch_reports, value; int battery_status, i, j; uint16_t sensor_timestamp; unsigned long flags; bool is_minimal = false; /* * DualShock4 in USB uses the full HID report for reportID 1, but * Bluetooth uses a minimal HID report for reportID 1 and reports * the full report using reportID 17. */ if (hdev->bus == BUS_USB && report->id == DS4_INPUT_REPORT_USB && size == DS4_INPUT_REPORT_USB_SIZE) { struct dualshock4_input_report_usb *usb = (struct dualshock4_input_report_usb *)data; ds4_report = &usb->common; num_touch_reports = usb->num_touch_reports; touch_reports = usb->touch_reports; } else if (hdev->bus == BUS_BLUETOOTH && report->id == DS4_INPUT_REPORT_BT && size == DS4_INPUT_REPORT_BT_SIZE) { struct dualshock4_input_report_bt *bt = (struct dualshock4_input_report_bt *)data; uint32_t report_crc = get_unaligned_le32(&bt->crc32); /* Last 4 bytes of input report contains CRC. */ if (!ps_check_crc32(PS_INPUT_CRC32_SEED, data, size - 4, report_crc)) { hid_err(hdev, "DualShock4 input CRC's check failed\n"); return -EILSEQ; } ds4_report = &bt->common; num_touch_reports = bt->num_touch_reports; touch_reports = bt->touch_reports; } else if (hdev->bus == BUS_BLUETOOTH && report->id == DS4_INPUT_REPORT_BT_MINIMAL && size == DS4_INPUT_REPORT_BT_MINIMAL_SIZE) { /* Some third-party pads never switch to the full 0x11 report. * The short 0x01 report is 10 bytes long: * u8 report_id == 0x01 * u8 first_bytes_of_full_report[9] * So let's reuse the full report parser, and stop it after * parsing the buttons. */ ds4_report = (struct dualshock4_input_report_common *)&data[1]; is_minimal = true; } else { hid_err(hdev, "Unhandled reportID=%d\n", report->id); return -1; } input_report_abs(ds4->gamepad, ABS_X, ds4_report->x); input_report_abs(ds4->gamepad, ABS_Y, ds4_report->y); input_report_abs(ds4->gamepad, ABS_RX, ds4_report->rx); input_report_abs(ds4->gamepad, ABS_RY, ds4_report->ry); input_report_abs(ds4->gamepad, ABS_Z, ds4_report->z); input_report_abs(ds4->gamepad, ABS_RZ, ds4_report->rz); value = ds4_report->buttons[0] & DS_BUTTONS0_HAT_SWITCH; if (value >= ARRAY_SIZE(ps_gamepad_hat_mapping)) value = 8; /* center */ input_report_abs(ds4->gamepad, ABS_HAT0X, ps_gamepad_hat_mapping[value].x); input_report_abs(ds4->gamepad, ABS_HAT0Y, ps_gamepad_hat_mapping[value].y); input_report_key(ds4->gamepad, BTN_WEST, ds4_report->buttons[0] & DS_BUTTONS0_SQUARE); input_report_key(ds4->gamepad, BTN_SOUTH, ds4_report->buttons[0] & DS_BUTTONS0_CROSS); input_report_key(ds4->gamepad, BTN_EAST, ds4_report->buttons[0] & DS_BUTTONS0_CIRCLE); input_report_key(ds4->gamepad, BTN_NORTH, ds4_report->buttons[0] & DS_BUTTONS0_TRIANGLE); input_report_key(ds4->gamepad, BTN_TL, ds4_report->buttons[1] & DS_BUTTONS1_L1); input_report_key(ds4->gamepad, BTN_TR, ds4_report->buttons[1] & DS_BUTTONS1_R1); input_report_key(ds4->gamepad, BTN_TL2, ds4_report->buttons[1] & DS_BUTTONS1_L2); input_report_key(ds4->gamepad, BTN_TR2, ds4_report->buttons[1] & DS_BUTTONS1_R2); input_report_key(ds4->gamepad, BTN_SELECT, ds4_report->buttons[1] & DS_BUTTONS1_CREATE); input_report_key(ds4->gamepad, BTN_START, ds4_report->buttons[1] & DS_BUTTONS1_OPTIONS); input_report_key(ds4->gamepad, BTN_THUMBL, ds4_report->buttons[1] & DS_BUTTONS1_L3); input_report_key(ds4->gamepad, BTN_THUMBR, ds4_report->buttons[1] & DS_BUTTONS1_R3); input_report_key(ds4->gamepad, BTN_MODE, ds4_report->buttons[2] & DS_BUTTONS2_PS_HOME); input_sync(ds4->gamepad); if (is_minimal) return 0; /* Parse and calibrate gyroscope data. */ for (i = 0; i < ARRAY_SIZE(ds4_report->gyro); i++) { int raw_data = (short)le16_to_cpu(ds4_report->gyro[i]); int calib_data = mult_frac(ds4->gyro_calib_data[i].sens_numer, raw_data, ds4->gyro_calib_data[i].sens_denom); input_report_abs(ds4->sensors, ds4->gyro_calib_data[i].abs_code, calib_data); } /* Parse and calibrate accelerometer data. */ for (i = 0; i < ARRAY_SIZE(ds4_report->accel); i++) { int raw_data = (short)le16_to_cpu(ds4_report->accel[i]); int calib_data = mult_frac(ds4->accel_calib_data[i].sens_numer, raw_data - ds4->accel_calib_data[i].bias, ds4->accel_calib_data[i].sens_denom); input_report_abs(ds4->sensors, ds4->accel_calib_data[i].abs_code, calib_data); } /* Convert timestamp (in 5.33us unit) to timestamp_us */ sensor_timestamp = le16_to_cpu(ds4_report->sensor_timestamp); if (!ds4->sensor_timestamp_initialized) { ds4->sensor_timestamp_us = DIV_ROUND_CLOSEST(sensor_timestamp*16, 3); ds4->sensor_timestamp_initialized = true; } else { uint16_t delta; if (ds4->prev_sensor_timestamp > sensor_timestamp) delta = (U16_MAX - ds4->prev_sensor_timestamp + sensor_timestamp + 1); else delta = sensor_timestamp - ds4->prev_sensor_timestamp; ds4->sensor_timestamp_us += DIV_ROUND_CLOSEST(delta*16, 3); } ds4->prev_sensor_timestamp = sensor_timestamp; input_event(ds4->sensors, EV_MSC, MSC_TIMESTAMP, ds4->sensor_timestamp_us); input_sync(ds4->sensors); for (i = 0; i < num_touch_reports; i++) { struct dualshock4_touch_report *touch_report = &touch_reports[i]; for (j = 0; j < ARRAY_SIZE(touch_report->points); j++) { struct dualshock4_touch_point *point = &touch_report->points[j]; bool active = (point->contact & DS4_TOUCH_POINT_INACTIVE) ? false : true; input_mt_slot(ds4->touchpad, j); input_mt_report_slot_state(ds4->touchpad, MT_TOOL_FINGER, active); if (active) { int x = (point->x_hi << 8) | point->x_lo; int y = (point->y_hi << 4) | point->y_lo; input_report_abs(ds4->touchpad, ABS_MT_POSITION_X, x); input_report_abs(ds4->touchpad, ABS_MT_POSITION_Y, y); } } input_mt_sync_frame(ds4->touchpad); input_sync(ds4->touchpad); } input_report_key(ds4->touchpad, BTN_LEFT, ds4_report->buttons[2] & DS_BUTTONS2_TOUCHPAD); /* * Interpretation of the battery_capacity data depends on the cable state. * When no cable is connected (bit4 is 0): * - 0:10: percentage in units of 10%. * When a cable is plugged in: * - 0-10: percentage in units of 10%. * - 11: battery is full * - 14: not charging due to Voltage or temperature error * - 15: charge error */ if (ds4_report->status[0] & DS4_STATUS0_CABLE_STATE) { uint8_t battery_data = ds4_report->status[0] & DS4_STATUS0_BATTERY_CAPACITY; if (battery_data < 10) { /* Take the mid-point for each battery capacity value, * because on the hardware side 0 = 0-9%, 1=10-19%, etc. * This matches official platform behavior, which does * the same. */ battery_capacity = battery_data * 10 + 5; battery_status = POWER_SUPPLY_STATUS_CHARGING; } else if (battery_data == 10) { battery_capacity = 100; battery_status = POWER_SUPPLY_STATUS_CHARGING; } else if (battery_data == DS4_BATTERY_STATUS_FULL) { battery_capacity = 100; battery_status = POWER_SUPPLY_STATUS_FULL; } else { /* 14, 15 and undefined values */ battery_capacity = 0; battery_status = POWER_SUPPLY_STATUS_UNKNOWN; } } else { uint8_t battery_data = ds4_report->status[0] & DS4_STATUS0_BATTERY_CAPACITY; if (battery_data < 10) battery_capacity = battery_data * 10 + 5; else /* 10 */ battery_capacity = 100; battery_status = POWER_SUPPLY_STATUS_DISCHARGING; } spin_lock_irqsave(&ps_dev->lock, flags); ps_dev->battery_capacity = battery_capacity; ps_dev->battery_status = battery_status; spin_unlock_irqrestore(&ps_dev->lock, flags); return 0; } static int dualshock4_dongle_parse_report(struct ps_device *ps_dev, struct hid_report *report, u8 *data, int size) { struct dualshock4 *ds4 = container_of(ps_dev, struct dualshock4, base); bool connected = false; /* The dongle reports data using the main USB report (0x1) no matter whether a controller * is connected with mostly zeros. The report does contain dongle status, which we use to * determine if a controller is connected and if so we forward to the regular DualShock4 * parsing code. */ if (data[0] == DS4_INPUT_REPORT_USB && size == DS4_INPUT_REPORT_USB_SIZE) { struct dualshock4_input_report_common *ds4_report = (struct dualshock4_input_report_common *)&data[1]; unsigned long flags; connected = ds4_report->status[1] & DS4_STATUS1_DONGLE_STATE ? false : true; if (ds4->dongle_state == DONGLE_DISCONNECTED && connected) { hid_info(ps_dev->hdev, "DualShock 4 USB dongle: controller connected\n"); dualshock4_set_default_lightbar_colors(ds4); spin_lock_irqsave(&ps_dev->lock, flags); ds4->dongle_state = DONGLE_CALIBRATING; spin_unlock_irqrestore(&ps_dev->lock, flags); schedule_work(&ds4->dongle_hotplug_worker); /* Don't process the report since we don't have * calibration data, but let hidraw have it anyway. */ return 0; } else if ((ds4->dongle_state == DONGLE_CONNECTED || ds4->dongle_state == DONGLE_DISABLED) && !connected) { hid_info(ps_dev->hdev, "DualShock 4 USB dongle: controller disconnected\n"); spin_lock_irqsave(&ps_dev->lock, flags); ds4->dongle_state = DONGLE_DISCONNECTED; spin_unlock_irqrestore(&ps_dev->lock, flags); /* Return 0, so hidraw can get the report. */ return 0; } else if (ds4->dongle_state == DONGLE_CALIBRATING || ds4->dongle_state == DONGLE_DISABLED || ds4->dongle_state == DONGLE_DISCONNECTED) { /* Return 0, so hidraw can get the report. */ return 0; } } if (connected) return dualshock4_parse_report(ps_dev, report, data, size); return 0; } static int dualshock4_play_effect(struct input_dev *dev, void *data, struct ff_effect *effect) { struct hid_device *hdev = input_get_drvdata(dev); struct dualshock4 *ds4 = hid_get_drvdata(hdev); unsigned long flags; if (effect->type != FF_RUMBLE) return 0; spin_lock_irqsave(&ds4->base.lock, flags); ds4->update_rumble = true; ds4->motor_left = effect->u.rumble.strong_magnitude / 256; ds4->motor_right = effect->u.rumble.weak_magnitude / 256; spin_unlock_irqrestore(&ds4->base.lock, flags); dualshock4_schedule_work(ds4); return 0; } static void dualshock4_remove(struct ps_device *ps_dev) { struct dualshock4 *ds4 = container_of(ps_dev, struct dualshock4, base); unsigned long flags; spin_lock_irqsave(&ds4->base.lock, flags); ds4->output_worker_initialized = false; spin_unlock_irqrestore(&ds4->base.lock, flags); cancel_work_sync(&ds4->output_worker); if (ps_dev->hdev->product == USB_DEVICE_ID_SONY_PS4_CONTROLLER_DONGLE) cancel_work_sync(&ds4->dongle_hotplug_worker); } static inline void dualshock4_schedule_work(struct dualshock4 *ds4) { unsigned long flags; spin_lock_irqsave(&ds4->base.lock, flags); if (ds4->output_worker_initialized) schedule_work(&ds4->output_worker); spin_unlock_irqrestore(&ds4->base.lock, flags); } static void dualshock4_set_bt_poll_interval(struct dualshock4 *ds4, uint8_t interval) { ds4->bt_poll_interval = interval; ds4->update_bt_poll_interval = true; dualshock4_schedule_work(ds4); } /* Set default lightbar color based on player. */ static void dualshock4_set_default_lightbar_colors(struct dualshock4 *ds4) { /* Use same player colors as PlayStation 4. * Array of colors is in RGB. */ static const int player_colors[4][3] = { { 0x00, 0x00, 0x40 }, /* Blue */ { 0x40, 0x00, 0x00 }, /* Red */ { 0x00, 0x40, 0x00 }, /* Green */ { 0x20, 0x00, 0x20 } /* Pink */ }; uint8_t player_id = ds4->base.player_id % ARRAY_SIZE(player_colors); ds4->lightbar_enabled = true; ds4->lightbar_red = player_colors[player_id][0]; ds4->lightbar_green = player_colors[player_id][1]; ds4->lightbar_blue = player_colors[player_id][2]; ds4->update_lightbar = true; dualshock4_schedule_work(ds4); } static struct ps_device *dualshock4_create(struct hid_device *hdev) { struct dualshock4 *ds4; struct ps_device *ps_dev; uint8_t max_output_report_size; int i, ret; /* The DualShock4 has an RGB lightbar, which the original hid-sony driver * exposed as a set of 4 LEDs for the 3 color channels and a global control. * Ideally this should have used the multi-color LED class, which didn't exist * yet. In addition the driver used a naming scheme not compliant with the LED * naming spec by using "<mac_address>:<color>", which contained many colons. * We use a more compliant by using "<device_name>:<color>" name now. Ideally * would have been "<device_name>:<color>:indicator", but that would break * existing applications (e.g. Android). Nothing matches against MAC address. */ static const struct ps_led_info lightbar_leds_info[] = { { NULL, "red", 255, dualshock4_led_get_brightness, dualshock4_led_set_brightness }, { NULL, "green", 255, dualshock4_led_get_brightness, dualshock4_led_set_brightness }, { NULL, "blue", 255, dualshock4_led_get_brightness, dualshock4_led_set_brightness }, { NULL, "global", 1, dualshock4_led_get_brightness, dualshock4_led_set_brightness, dualshock4_led_set_blink }, }; ds4 = devm_kzalloc(&hdev->dev, sizeof(*ds4), GFP_KERNEL); if (!ds4) return ERR_PTR(-ENOMEM); /* * Patch version to allow userspace to distinguish between * hid-generic vs hid-playstation axis and button mapping. */ hdev->version |= HID_PLAYSTATION_VERSION_PATCH; ps_dev = &ds4->base; ps_dev->hdev = hdev; spin_lock_init(&ps_dev->lock); ps_dev->battery_capacity = 100; /* initial value until parse_report. */ ps_dev->battery_status = POWER_SUPPLY_STATUS_UNKNOWN; ps_dev->parse_report = dualshock4_parse_report; ps_dev->remove = dualshock4_remove; INIT_WORK(&ds4->output_worker, dualshock4_output_worker); ds4->output_worker_initialized = true; hid_set_drvdata(hdev, ds4); max_output_report_size = sizeof(struct dualshock4_output_report_bt); ds4->output_report_dmabuf = devm_kzalloc(&hdev->dev, max_output_report_size, GFP_KERNEL); if (!ds4->output_report_dmabuf) return ERR_PTR(-ENOMEM); if (hdev->product == USB_DEVICE_ID_SONY_PS4_CONTROLLER_DONGLE) { ds4->dongle_state = DONGLE_DISCONNECTED; INIT_WORK(&ds4->dongle_hotplug_worker, dualshock4_dongle_calibration_work); /* Override parse report for dongle specific hotplug handling. */ ps_dev->parse_report = dualshock4_dongle_parse_report; } ret = dualshock4_get_mac_address(ds4); if (ret) { hid_err(hdev, "Failed to get MAC address from DualShock4\n"); return ERR_PTR(ret); } snprintf(hdev->uniq, sizeof(hdev->uniq), "%pMR", ds4->base.mac_address); ret = dualshock4_get_firmware_info(ds4); if (ret) { hid_warn(hdev, "Failed to get firmware info from DualShock4\n"); hid_warn(hdev, "HW/FW version data in sysfs will be invalid.\n"); } ret = ps_devices_list_add(ps_dev); if (ret) return ERR_PTR(ret); ret = dualshock4_get_calibration_data(ds4); if (ret) { hid_warn(hdev, "Failed to get calibration data from DualShock4\n"); hid_warn(hdev, "Gyroscope and accelerometer will be inaccurate.\n"); } ds4->gamepad = ps_gamepad_create(hdev, dualshock4_play_effect); if (IS_ERR(ds4->gamepad)) { ret = PTR_ERR(ds4->gamepad); goto err; } /* Use gamepad input device name as primary device name for e.g. LEDs */ ps_dev->input_dev_name = dev_name(&ds4->gamepad->dev); ds4->sensors = ps_sensors_create(hdev, DS4_ACC_RANGE, DS4_ACC_RES_PER_G, DS4_GYRO_RANGE, DS4_GYRO_RES_PER_DEG_S); if (IS_ERR(ds4->sensors)) { ret = PTR_ERR(ds4->sensors); goto err; } ds4->touchpad = ps_touchpad_create(hdev, DS4_TOUCHPAD_WIDTH, DS4_TOUCHPAD_HEIGHT, 2); if (IS_ERR(ds4->touchpad)) { ret = PTR_ERR(ds4->touchpad); goto err; } ret = ps_device_register_battery(ps_dev); if (ret) goto err; for (i = 0; i < ARRAY_SIZE(lightbar_leds_info); i++) { const struct ps_led_info *led_info = &lightbar_leds_info[i]; ret = ps_led_register(ps_dev, &ds4->lightbar_leds[i], led_info); if (ret < 0) goto err; } dualshock4_set_bt_poll_interval(ds4, DS4_BT_DEFAULT_POLL_INTERVAL_MS); ret = ps_device_set_player_id(ps_dev); if (ret) { hid_err(hdev, "Failed to assign player id for DualShock4: %d\n", ret); goto err; } dualshock4_set_default_lightbar_colors(ds4); /* * Reporting hardware and firmware is important as there are frequent updates, which * can change behavior. */ hid_info(hdev, "Registered DualShock4 controller hw_version=0x%08x fw_version=0x%08x\n", ds4->base.hw_version, ds4->base.fw_version); return &ds4->base; err: ps_devices_list_remove(ps_dev); return ERR_PTR(ret); } static int ps_raw_event(struct hid_device *hdev, struct hid_report *report, u8 *data, int size) { struct ps_device *dev = hid_get_drvdata(hdev); if (dev && dev->parse_report) return dev->parse_report(dev, report, data, size); return 0; } static int ps_probe(struct hid_device *hdev, const struct hid_device_id *id) { struct ps_device *dev; int ret; ret = hid_parse(hdev); if (ret) { hid_err(hdev, "Parse failed\n"); return ret; } ret = hid_hw_start(hdev, HID_CONNECT_HIDRAW); if (ret) { hid_err(hdev, "Failed to start HID device\n"); return ret; } ret = hid_hw_open(hdev); if (ret) { hid_err(hdev, "Failed to open HID device\n"); goto err_stop; } if (id->driver_data == PS_TYPE_PS4_DUALSHOCK4) { dev = dualshock4_create(hdev); if (IS_ERR(dev)) { hid_err(hdev, "Failed to create dualshock4.\n"); ret = PTR_ERR(dev); goto err_close; } } else if (id->driver_data == PS_TYPE_PS5_DUALSENSE) { dev = dualsense_create(hdev); if (IS_ERR(dev)) { hid_err(hdev, "Failed to create dualsense.\n"); ret = PTR_ERR(dev); goto err_close; } } return ret; err_close: hid_hw_close(hdev); err_stop: hid_hw_stop(hdev); return ret; } static void ps_remove(struct hid_device *hdev) { struct ps_device *dev = hid_get_drvdata(hdev); ps_devices_list_remove(dev); ps_device_release_player_id(dev); if (dev->remove) dev->remove(dev); hid_hw_close(hdev); hid_hw_stop(hdev); } static const struct hid_device_id ps_devices[] = { /* Sony DualShock 4 controllers for PS4 */ { HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_SONY, USB_DEVICE_ID_SONY_PS4_CONTROLLER), .driver_data = PS_TYPE_PS4_DUALSHOCK4 }, { HID_USB_DEVICE(USB_VENDOR_ID_SONY, USB_DEVICE_ID_SONY_PS4_CONTROLLER), .driver_data = PS_TYPE_PS4_DUALSHOCK4 }, { HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_SONY, USB_DEVICE_ID_SONY_PS4_CONTROLLER_2), .driver_data = PS_TYPE_PS4_DUALSHOCK4 }, { HID_USB_DEVICE(USB_VENDOR_ID_SONY, USB_DEVICE_ID_SONY_PS4_CONTROLLER_2), .driver_data = PS_TYPE_PS4_DUALSHOCK4 }, { HID_USB_DEVICE(USB_VENDOR_ID_SONY, USB_DEVICE_ID_SONY_PS4_CONTROLLER_DONGLE), .driver_data = PS_TYPE_PS4_DUALSHOCK4 }, /* Sony DualSense controllers for PS5 */ { HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_SONY, USB_DEVICE_ID_SONY_PS5_CONTROLLER), .driver_data = PS_TYPE_PS5_DUALSENSE }, { HID_USB_DEVICE(USB_VENDOR_ID_SONY, USB_DEVICE_ID_SONY_PS5_CONTROLLER), .driver_data = PS_TYPE_PS5_DUALSENSE }, { HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_SONY, USB_DEVICE_ID_SONY_PS5_CONTROLLER_2), .driver_data = PS_TYPE_PS5_DUALSENSE }, { HID_USB_DEVICE(USB_VENDOR_ID_SONY, USB_DEVICE_ID_SONY_PS5_CONTROLLER_2), .driver_data = PS_TYPE_PS5_DUALSENSE }, { } }; MODULE_DEVICE_TABLE(hid, ps_devices); static struct hid_driver ps_driver = { .name = "playstation", .id_table = ps_devices, .probe = ps_probe, .remove = ps_remove, .raw_event = ps_raw_event, .driver = { .dev_groups = ps_device_groups, }, }; static int __init ps_init(void) { return hid_register_driver(&ps_driver); } static void __exit ps_exit(void) { hid_unregister_driver(&ps_driver); ida_destroy(&ps_player_id_allocator); } module_init(ps_init); module_exit(ps_exit); MODULE_AUTHOR("Sony Interactive Entertainment"); MODULE_DESCRIPTION("HID Driver for PlayStation peripherals."); MODULE_LICENSE("GPL"); |
| 279 280 534 520 517 1 519 820 820 816 395 18 83 407 801 103 4 46 181 331 219 803 142 12 12 1 816 11 5 6 21 21 2 3 13 17 17 17 15 4 546 806 811 76 8 3 47 18 76 2 7680 7665 2793 167 7690 5258 635 631 8 7670 1937 514 1 1267 1252 4 7693 6 1 239 5 1 279 280 1414 1230 1419 4271 4266 2348 2338 1305 3893 3663 3655 326 548 533 530 534 531 1927 31 1892 5260 5259 7654 820 76 106 106 144 8838 8838 8716 8880 7818 7779 257 14 7761 7719 7679 8745 1536 1536 1530 8844 269 29 29 29 29 29 29 8730 211 191 209 2192 2188 2196 2174 15 2167 2191 2184 545 547 546 544 546 895 25 895 13 12 13 1465 1472 1468 1464 1469 4085 2494 1989 1856 1855 1705 1708 1708 30 30 4075 2463 80 4096 4066 4075 2463 2475 2464 2459 80 80 80 1 11 11 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 | // SPDX-License-Identifier: GPL-2.0 /* * NETLINK Netlink attributes * * Authors: Thomas Graf <tgraf@suug.ch> * Alexey Kuznetsov <kuznet@ms2.inr.ac.ru> */ #include <linux/export.h> #include <linux/kernel.h> #include <linux/errno.h> #include <linux/jiffies.h> #include <linux/nospec.h> #include <linux/skbuff.h> #include <linux/string.h> #include <linux/types.h> #include <net/netlink.h> /* For these data types, attribute length should be exactly the given * size. However, to maintain compatibility with broken commands, if the * attribute length does not match the expected size a warning is emitted * to the user that the command is sending invalid data and needs to be fixed. */ static const u8 nla_attr_len[NLA_TYPE_MAX+1] = { [NLA_U8] = sizeof(u8), [NLA_U16] = sizeof(u16), [NLA_U32] = sizeof(u32), [NLA_U64] = sizeof(u64), [NLA_S8] = sizeof(s8), [NLA_S16] = sizeof(s16), [NLA_S32] = sizeof(s32), [NLA_S64] = sizeof(s64), [NLA_BE16] = sizeof(__be16), [NLA_BE32] = sizeof(__be32), }; static const u8 nla_attr_minlen[NLA_TYPE_MAX+1] = { [NLA_U8] = sizeof(u8), [NLA_U16] = sizeof(u16), [NLA_U32] = sizeof(u32), [NLA_U64] = sizeof(u64), [NLA_MSECS] = sizeof(u64), [NLA_NESTED] = NLA_HDRLEN, [NLA_S8] = sizeof(s8), [NLA_S16] = sizeof(s16), [NLA_S32] = sizeof(s32), [NLA_S64] = sizeof(s64), [NLA_BE16] = sizeof(__be16), [NLA_BE32] = sizeof(__be32), }; /* * Nested policies might refer back to the original * policy in some cases, and userspace could try to * abuse that and recurse by nesting in the right * ways. Limit recursion to avoid this problem. */ #define MAX_POLICY_RECURSION_DEPTH 10 static int __nla_validate_parse(const struct nlattr *head, int len, int maxtype, const struct nla_policy *policy, unsigned int validate, struct netlink_ext_ack *extack, struct nlattr **tb, unsigned int depth); static int validate_nla_bitfield32(const struct nlattr *nla, const u32 valid_flags_mask) { const struct nla_bitfield32 *bf = nla_data(nla); if (!valid_flags_mask) return -EINVAL; /*disallow invalid bit selector */ if (bf->selector & ~valid_flags_mask) return -EINVAL; /*disallow invalid bit values */ if (bf->value & ~valid_flags_mask) return -EINVAL; /*disallow valid bit values that are not selected*/ if (bf->value & ~bf->selector) return -EINVAL; return 0; } static int nla_validate_array(const struct nlattr *head, int len, int maxtype, const struct nla_policy *policy, struct netlink_ext_ack *extack, unsigned int validate, unsigned int depth) { const struct nlattr *entry; int rem; nla_for_each_attr(entry, head, len, rem) { int ret; if (nla_len(entry) == 0) continue; if (nla_len(entry) < NLA_HDRLEN) { NL_SET_ERR_MSG_ATTR_POL(extack, entry, policy, "Array element too short"); return -ERANGE; } ret = __nla_validate_parse(nla_data(entry), nla_len(entry), maxtype, policy, validate, extack, NULL, depth + 1); if (ret < 0) return ret; } return 0; } void nla_get_range_unsigned(const struct nla_policy *pt, struct netlink_range_validation *range) { WARN_ON_ONCE(pt->validation_type != NLA_VALIDATE_RANGE_PTR && (pt->min < 0 || pt->max < 0)); range->min = 0; switch (pt->type) { case NLA_U8: range->max = U8_MAX; break; case NLA_U16: case NLA_BE16: case NLA_BINARY: range->max = U16_MAX; break; case NLA_U32: case NLA_BE32: range->max = U32_MAX; break; case NLA_U64: case NLA_UINT: case NLA_MSECS: range->max = U64_MAX; break; default: WARN_ON_ONCE(1); return; } switch (pt->validation_type) { case NLA_VALIDATE_RANGE: case NLA_VALIDATE_RANGE_WARN_TOO_LONG: range->min = pt->min; range->max = pt->max; break; case NLA_VALIDATE_RANGE_PTR: *range = *pt->range; break; case NLA_VALIDATE_MIN: range->min = pt->min; break; case NLA_VALIDATE_MAX: range->max = pt->max; break; default: break; } } static int nla_validate_range_unsigned(const struct nla_policy *pt, const struct nlattr *nla, struct netlink_ext_ack *extack, unsigned int validate) { struct netlink_range_validation range; u64 value; switch (pt->type) { case NLA_U8: value = nla_get_u8(nla); break; case NLA_U16: value = nla_get_u16(nla); break; case NLA_U32: value = nla_get_u32(nla); break; case NLA_U64: value = nla_get_u64(nla); break; case NLA_UINT: value = nla_get_uint(nla); break; case NLA_MSECS: value = nla_get_u64(nla); break; case NLA_BINARY: value = nla_len(nla); break; case NLA_BE16: value = ntohs(nla_get_be16(nla)); break; case NLA_BE32: value = ntohl(nla_get_be32(nla)); break; default: return -EINVAL; } nla_get_range_unsigned(pt, &range); if (pt->validation_type == NLA_VALIDATE_RANGE_WARN_TOO_LONG && pt->type == NLA_BINARY && value > range.max) { pr_warn_ratelimited("netlink: '%s': attribute type %d has an invalid length.\n", current->comm, pt->type); if (validate & NL_VALIDATE_STRICT_ATTRS) { NL_SET_ERR_MSG_ATTR_POL(extack, nla, pt, "invalid attribute length"); return -EINVAL; } /* this assumes min <= max (don't validate against min) */ return 0; } if (value < range.min || value > range.max) { bool binary = pt->type == NLA_BINARY; if (binary) NL_SET_ERR_MSG_ATTR_POL(extack, nla, pt, "binary attribute size out of range"); else NL_SET_ERR_MSG_ATTR_POL(extack, nla, pt, "integer out of range"); return -ERANGE; } return 0; } void nla_get_range_signed(const struct nla_policy *pt, struct netlink_range_validation_signed *range) { switch (pt->type) { case NLA_S8: range->min = S8_MIN; range->max = S8_MAX; break; case NLA_S16: range->min = S16_MIN; range->max = S16_MAX; break; case NLA_S32: range->min = S32_MIN; range->max = S32_MAX; break; case NLA_S64: case NLA_SINT: range->min = S64_MIN; range->max = S64_MAX; break; default: WARN_ON_ONCE(1); return; } switch (pt->validation_type) { case NLA_VALIDATE_RANGE: range->min = pt->min; range->max = pt->max; break; case NLA_VALIDATE_RANGE_PTR: *range = *pt->range_signed; break; case NLA_VALIDATE_MIN: range->min = pt->min; break; case NLA_VALIDATE_MAX: range->max = pt->max; break; default: break; } } static int nla_validate_int_range_signed(const struct nla_policy *pt, const struct nlattr *nla, struct netlink_ext_ack *extack) { struct netlink_range_validation_signed range; s64 value; switch (pt->type) { case NLA_S8: value = nla_get_s8(nla); break; case NLA_S16: value = nla_get_s16(nla); break; case NLA_S32: value = nla_get_s32(nla); break; case NLA_S64: value = nla_get_s64(nla); break; case NLA_SINT: value = nla_get_sint(nla); break; default: return -EINVAL; } nla_get_range_signed(pt, &range); if (value < range.min || value > range.max) { NL_SET_ERR_MSG_ATTR_POL(extack, nla, pt, "integer out of range"); return -ERANGE; } return 0; } static int nla_validate_int_range(const struct nla_policy *pt, const struct nlattr *nla, struct netlink_ext_ack *extack, unsigned int validate) { switch (pt->type) { case NLA_U8: case NLA_U16: case NLA_U32: case NLA_U64: case NLA_UINT: case NLA_MSECS: case NLA_BINARY: case NLA_BE16: case NLA_BE32: return nla_validate_range_unsigned(pt, nla, extack, validate); case NLA_S8: case NLA_S16: case NLA_S32: case NLA_S64: case NLA_SINT: return nla_validate_int_range_signed(pt, nla, extack); default: WARN_ON(1); return -EINVAL; } } static int nla_validate_mask(const struct nla_policy *pt, const struct nlattr *nla, struct netlink_ext_ack *extack) { u64 value; switch (pt->type) { case NLA_U8: value = nla_get_u8(nla); break; case NLA_U16: value = nla_get_u16(nla); break; case NLA_U32: value = nla_get_u32(nla); break; case NLA_U64: value = nla_get_u64(nla); break; case NLA_UINT: value = nla_get_uint(nla); break; case NLA_BE16: value = ntohs(nla_get_be16(nla)); break; case NLA_BE32: value = ntohl(nla_get_be32(nla)); break; default: return -EINVAL; } if (value & ~(u64)pt->mask) { NL_SET_ERR_MSG_ATTR(extack, nla, "reserved bit set"); return -EINVAL; } return 0; } static int validate_nla(const struct nlattr *nla, int maxtype, const struct nla_policy *policy, unsigned int validate, struct netlink_ext_ack *extack, unsigned int depth) { u16 strict_start_type = policy[0].strict_start_type; const struct nla_policy *pt; int minlen = 0, attrlen = nla_len(nla), type = nla_type(nla); int err = -ERANGE; if (strict_start_type && type >= strict_start_type) validate |= NL_VALIDATE_STRICT; if (type <= 0 || type > maxtype) return 0; type = array_index_nospec(type, maxtype + 1); pt = &policy[type]; BUG_ON(pt->type > NLA_TYPE_MAX); if (nla_attr_len[pt->type] && attrlen != nla_attr_len[pt->type]) { pr_warn_ratelimited("netlink: '%s': attribute type %d has an invalid length.\n", current->comm, type); if (validate & NL_VALIDATE_STRICT_ATTRS) { NL_SET_ERR_MSG_ATTR_POL(extack, nla, pt, "invalid attribute length"); return -EINVAL; } } if (validate & NL_VALIDATE_NESTED) { if ((pt->type == NLA_NESTED || pt->type == NLA_NESTED_ARRAY) && !(nla->nla_type & NLA_F_NESTED)) { NL_SET_ERR_MSG_ATTR_POL(extack, nla, pt, "NLA_F_NESTED is missing"); return -EINVAL; } if (pt->type != NLA_NESTED && pt->type != NLA_NESTED_ARRAY && pt->type != NLA_UNSPEC && (nla->nla_type & NLA_F_NESTED)) { NL_SET_ERR_MSG_ATTR_POL(extack, nla, pt, "NLA_F_NESTED not expected"); return -EINVAL; } } switch (pt->type) { case NLA_REJECT: if (extack && pt->reject_message) { NL_SET_BAD_ATTR(extack, nla); extack->_msg = pt->reject_message; return -EINVAL; } err = -EINVAL; goto out_err; case NLA_FLAG: if (attrlen > 0) goto out_err; break; case NLA_SINT: case NLA_UINT: if (attrlen != sizeof(u32) && attrlen != sizeof(u64)) { NL_SET_ERR_MSG_ATTR_POL(extack, nla, pt, "invalid attribute length"); return -EINVAL; } break; case NLA_BITFIELD32: if (attrlen != sizeof(struct nla_bitfield32)) goto out_err; err = validate_nla_bitfield32(nla, pt->bitfield32_valid); if (err) goto out_err; break; case NLA_NUL_STRING: if (pt->len) minlen = min_t(int, attrlen, pt->len + 1); else minlen = attrlen; if (!minlen || memchr(nla_data(nla), '\0', minlen) == NULL) { err = -EINVAL; goto out_err; } fallthrough; case NLA_STRING: if (attrlen < 1) goto out_err; if (pt->len) { char *buf = nla_data(nla); if (buf[attrlen - 1] == '\0') attrlen--; if (attrlen > pt->len) goto out_err; } break; case NLA_BINARY: if (pt->len && attrlen > pt->len) goto out_err; break; case NLA_NESTED: /* a nested attributes is allowed to be empty; if its not, * it must have a size of at least NLA_HDRLEN. */ if (attrlen == 0) break; if (attrlen < NLA_HDRLEN) goto out_err; if (pt->nested_policy) { err = __nla_validate_parse(nla_data(nla), nla_len(nla), pt->len, pt->nested_policy, validate, extack, NULL, depth + 1); if (err < 0) { /* * return directly to preserve the inner * error message/attribute pointer */ return err; } } break; case NLA_NESTED_ARRAY: /* a nested array attribute is allowed to be empty; if its not, * it must have a size of at least NLA_HDRLEN. */ if (attrlen == 0) break; if (attrlen < NLA_HDRLEN) goto out_err; if (pt->nested_policy) { int err; err = nla_validate_array(nla_data(nla), nla_len(nla), pt->len, pt->nested_policy, extack, validate, depth); if (err < 0) { /* * return directly to preserve the inner * error message/attribute pointer */ return err; } } break; case NLA_UNSPEC: if (validate & NL_VALIDATE_UNSPEC) { NL_SET_ERR_MSG_ATTR(extack, nla, "Unsupported attribute"); return -EINVAL; } if (attrlen < pt->len) goto out_err; break; default: if (pt->len) minlen = pt->len; else minlen = nla_attr_minlen[pt->type]; if (attrlen < minlen) goto out_err; } /* further validation */ switch (pt->validation_type) { case NLA_VALIDATE_NONE: /* nothing to do */ break; case NLA_VALIDATE_RANGE_PTR: case NLA_VALIDATE_RANGE: case NLA_VALIDATE_RANGE_WARN_TOO_LONG: case NLA_VALIDATE_MIN: case NLA_VALIDATE_MAX: err = nla_validate_int_range(pt, nla, extack, validate); if (err) return err; break; case NLA_VALIDATE_MASK: err = nla_validate_mask(pt, nla, extack); if (err) return err; break; case NLA_VALIDATE_FUNCTION: if (pt->validate) { err = pt->validate(nla, extack); if (err) return err; } break; } return 0; out_err: NL_SET_ERR_MSG_ATTR_POL(extack, nla, pt, "Attribute failed policy validation"); return err; } static int __nla_validate_parse(const struct nlattr *head, int len, int maxtype, const struct nla_policy *policy, unsigned int validate, struct netlink_ext_ack *extack, struct nlattr **tb, unsigned int depth) { const struct nlattr *nla; int rem; if (depth >= MAX_POLICY_RECURSION_DEPTH) { NL_SET_ERR_MSG(extack, "allowed policy recursion depth exceeded"); return -EINVAL; } if (tb) memset(tb, 0, sizeof(struct nlattr *) * (maxtype + 1)); nla_for_each_attr(nla, head, len, rem) { u16 type = nla_type(nla); if (type == 0 || type > maxtype) { if (validate & NL_VALIDATE_MAXTYPE) { NL_SET_ERR_MSG_ATTR(extack, nla, "Unknown attribute type"); return -EINVAL; } continue; } type = array_index_nospec(type, maxtype + 1); if (policy) { int err = validate_nla(nla, maxtype, policy, validate, extack, depth); if (err < 0) return err; } if (tb) tb[type] = (struct nlattr *)nla; } if (unlikely(rem > 0)) { pr_warn_ratelimited("netlink: %d bytes leftover after parsing attributes in process `%s'.\n", rem, current->comm); NL_SET_ERR_MSG(extack, "bytes leftover after parsing attributes"); if (validate & NL_VALIDATE_TRAILING) return -EINVAL; } return 0; } /** * __nla_validate - Validate a stream of attributes * @head: head of attribute stream * @len: length of attribute stream * @maxtype: maximum attribute type to be expected * @policy: validation policy * @validate: validation strictness * @extack: extended ACK report struct * * Validates all attributes in the specified attribute stream against the * specified policy. Validation depends on the validate flags passed, see * &enum netlink_validation for more details on that. * See documentation of struct nla_policy for more details. * * Returns 0 on success or a negative error code. */ int __nla_validate(const struct nlattr *head, int len, int maxtype, const struct nla_policy *policy, unsigned int validate, struct netlink_ext_ack *extack) { return __nla_validate_parse(head, len, maxtype, policy, validate, extack, NULL, 0); } EXPORT_SYMBOL(__nla_validate); /** * nla_policy_len - Determine the max. length of a policy * @p: policy to use * @n: number of policies * * Determines the max. length of the policy. It is currently used * to allocated Netlink buffers roughly the size of the actual * message. * * Returns 0 on success or a negative error code. */ int nla_policy_len(const struct nla_policy *p, int n) { int i, len = 0; for (i = 0; i < n; i++, p++) { if (p->len) len += nla_total_size(p->len); else if (nla_attr_len[p->type]) len += nla_total_size(nla_attr_len[p->type]); else if (nla_attr_minlen[p->type]) len += nla_total_size(nla_attr_minlen[p->type]); } return len; } EXPORT_SYMBOL(nla_policy_len); /** * __nla_parse - Parse a stream of attributes into a tb buffer * @tb: destination array with maxtype+1 elements * @maxtype: maximum attribute type to be expected * @head: head of attribute stream * @len: length of attribute stream * @policy: validation policy * @validate: validation strictness * @extack: extended ACK pointer * * Parses a stream of attributes and stores a pointer to each attribute in * the tb array accessible via the attribute type. * Validation is controlled by the @validate parameter. * * Returns 0 on success or a negative error code. */ int __nla_parse(struct nlattr **tb, int maxtype, const struct nlattr *head, int len, const struct nla_policy *policy, unsigned int validate, struct netlink_ext_ack *extack) { return __nla_validate_parse(head, len, maxtype, policy, validate, extack, tb, 0); } EXPORT_SYMBOL(__nla_parse); /** * nla_find - Find a specific attribute in a stream of attributes * @head: head of attribute stream * @len: length of attribute stream * @attrtype: type of attribute to look for * * Returns the first attribute in the stream matching the specified type. */ struct nlattr *nla_find(const struct nlattr *head, int len, int attrtype) { const struct nlattr *nla; int rem; nla_for_each_attr(nla, head, len, rem) if (nla_type(nla) == attrtype) return (struct nlattr *)nla; return NULL; } EXPORT_SYMBOL(nla_find); /** * nla_strscpy - Copy string attribute payload into a sized buffer * @dst: Where to copy the string to. * @nla: Attribute to copy the string from. * @dstsize: Size of destination buffer. * * Copies at most dstsize - 1 bytes into the destination buffer. * Unlike strscpy() the destination buffer is always padded out. * * Return: * * srclen - Returns @nla length (not including the trailing %NUL). * * -E2BIG - If @dstsize is 0 or greater than U16_MAX or @nla length greater * than @dstsize. */ ssize_t nla_strscpy(char *dst, const struct nlattr *nla, size_t dstsize) { size_t srclen = nla_len(nla); char *src = nla_data(nla); ssize_t ret; size_t len; if (dstsize == 0 || WARN_ON_ONCE(dstsize > U16_MAX)) return -E2BIG; if (srclen > 0 && src[srclen - 1] == '\0') srclen--; if (srclen >= dstsize) { len = dstsize - 1; ret = -E2BIG; } else { len = srclen; ret = len; } memcpy(dst, src, len); /* Zero pad end of dst. */ memset(dst + len, 0, dstsize - len); return ret; } EXPORT_SYMBOL(nla_strscpy); /** * nla_strdup - Copy string attribute payload into a newly allocated buffer * @nla: attribute to copy the string from * @flags: the type of memory to allocate (see kmalloc). * * Returns a pointer to the allocated buffer or NULL on error. */ char *nla_strdup(const struct nlattr *nla, gfp_t flags) { size_t srclen = nla_len(nla); char *src = nla_data(nla), *dst; if (srclen > 0 && src[srclen - 1] == '\0') srclen--; dst = kmalloc(srclen + 1, flags); if (dst != NULL) { memcpy(dst, src, srclen); dst[srclen] = '\0'; } return dst; } EXPORT_SYMBOL(nla_strdup); /** * nla_memcpy - Copy a netlink attribute into another memory area * @dest: where to copy to memcpy * @src: netlink attribute to copy from * @count: size of the destination area * * Note: The number of bytes copied is limited by the length of * attribute's payload. memcpy * * Returns the number of bytes copied. */ int nla_memcpy(void *dest, const struct nlattr *src, int count) { int minlen = min_t(int, count, nla_len(src)); memcpy(dest, nla_data(src), minlen); if (count > minlen) memset(dest + minlen, 0, count - minlen); return minlen; } EXPORT_SYMBOL(nla_memcpy); /** * nla_memcmp - Compare an attribute with sized memory area * @nla: netlink attribute * @data: memory area * @size: size of memory area */ int nla_memcmp(const struct nlattr *nla, const void *data, size_t size) { int d = nla_len(nla) - size; if (d == 0) d = memcmp(nla_data(nla), data, size); return d; } EXPORT_SYMBOL(nla_memcmp); /** * nla_strcmp - Compare a string attribute against a string * @nla: netlink string attribute * @str: another string */ int nla_strcmp(const struct nlattr *nla, const char *str) { int len = strlen(str); char *buf = nla_data(nla); int attrlen = nla_len(nla); int d; while (attrlen > 0 && buf[attrlen - 1] == '\0') attrlen--; d = attrlen - len; if (d == 0) d = memcmp(nla_data(nla), str, len); return d; } EXPORT_SYMBOL(nla_strcmp); #ifdef CONFIG_NET /** * __nla_reserve - reserve room for attribute on the skb * @skb: socket buffer to reserve room on * @attrtype: attribute type * @attrlen: length of attribute payload * * Adds a netlink attribute header to a socket buffer and reserves * room for the payload but does not copy it. * * The caller is responsible to ensure that the skb provides enough * tailroom for the attribute header and payload. */ struct nlattr *__nla_reserve(struct sk_buff *skb, int attrtype, int attrlen) { struct nlattr *nla; nla = skb_put(skb, nla_total_size(attrlen)); nla->nla_type = attrtype; nla->nla_len = nla_attr_size(attrlen); memset((unsigned char *) nla + nla->nla_len, 0, nla_padlen(attrlen)); return nla; } EXPORT_SYMBOL(__nla_reserve); /** * __nla_reserve_64bit - reserve room for attribute on the skb and align it * @skb: socket buffer to reserve room on * @attrtype: attribute type * @attrlen: length of attribute payload * @padattr: attribute type for the padding * * Adds a netlink attribute header to a socket buffer and reserves * room for the payload but does not copy it. It also ensure that this * attribute will have a 64-bit aligned nla_data() area. * * The caller is responsible to ensure that the skb provides enough * tailroom for the attribute header and payload. */ struct nlattr *__nla_reserve_64bit(struct sk_buff *skb, int attrtype, int attrlen, int padattr) { nla_align_64bit(skb, padattr); return __nla_reserve(skb, attrtype, attrlen); } EXPORT_SYMBOL(__nla_reserve_64bit); /** * __nla_reserve_nohdr - reserve room for attribute without header * @skb: socket buffer to reserve room on * @attrlen: length of attribute payload * * Reserves room for attribute payload without a header. * * The caller is responsible to ensure that the skb provides enough * tailroom for the payload. */ void *__nla_reserve_nohdr(struct sk_buff *skb, int attrlen) { return skb_put_zero(skb, NLA_ALIGN(attrlen)); } EXPORT_SYMBOL(__nla_reserve_nohdr); /** * nla_reserve - reserve room for attribute on the skb * @skb: socket buffer to reserve room on * @attrtype: attribute type * @attrlen: length of attribute payload * * Adds a netlink attribute header to a socket buffer and reserves * room for the payload but does not copy it. * * Returns NULL if the tailroom of the skb is insufficient to store * the attribute header and payload. */ struct nlattr *nla_reserve(struct sk_buff *skb, int attrtype, int attrlen) { if (unlikely(skb_tailroom(skb) < nla_total_size(attrlen))) return NULL; return __nla_reserve(skb, attrtype, attrlen); } EXPORT_SYMBOL(nla_reserve); /** * nla_reserve_64bit - reserve room for attribute on the skb and align it * @skb: socket buffer to reserve room on * @attrtype: attribute type * @attrlen: length of attribute payload * @padattr: attribute type for the padding * * Adds a netlink attribute header to a socket buffer and reserves * room for the payload but does not copy it. It also ensure that this * attribute will have a 64-bit aligned nla_data() area. * * Returns NULL if the tailroom of the skb is insufficient to store * the attribute header and payload. */ struct nlattr *nla_reserve_64bit(struct sk_buff *skb, int attrtype, int attrlen, int padattr) { size_t len; if (nla_need_padding_for_64bit(skb)) len = nla_total_size_64bit(attrlen); else len = nla_total_size(attrlen); if (unlikely(skb_tailroom(skb) < len)) return NULL; return __nla_reserve_64bit(skb, attrtype, attrlen, padattr); } EXPORT_SYMBOL(nla_reserve_64bit); /** * nla_reserve_nohdr - reserve room for attribute without header * @skb: socket buffer to reserve room on * @attrlen: length of attribute payload * * Reserves room for attribute payload without a header. * * Returns NULL if the tailroom of the skb is insufficient to store * the attribute payload. */ void *nla_reserve_nohdr(struct sk_buff *skb, int attrlen) { if (unlikely(skb_tailroom(skb) < NLA_ALIGN(attrlen))) return NULL; return __nla_reserve_nohdr(skb, attrlen); } EXPORT_SYMBOL(nla_reserve_nohdr); /** * __nla_put - Add a netlink attribute to a socket buffer * @skb: socket buffer to add attribute to * @attrtype: attribute type * @attrlen: length of attribute payload * @data: head of attribute payload * * The caller is responsible to ensure that the skb provides enough * tailroom for the attribute header and payload. */ void __nla_put(struct sk_buff *skb, int attrtype, int attrlen, const void *data) { struct nlattr *nla; nla = __nla_reserve(skb, attrtype, attrlen); memcpy(nla_data(nla), data, attrlen); } EXPORT_SYMBOL(__nla_put); /** * __nla_put_64bit - Add a netlink attribute to a socket buffer and align it * @skb: socket buffer to add attribute to * @attrtype: attribute type * @attrlen: length of attribute payload * @data: head of attribute payload * @padattr: attribute type for the padding * * The caller is responsible to ensure that the skb provides enough * tailroom for the attribute header and payload. */ void __nla_put_64bit(struct sk_buff *skb, int attrtype, int attrlen, const void *data, int padattr) { struct nlattr *nla; nla = __nla_reserve_64bit(skb, attrtype, attrlen, padattr); memcpy(nla_data(nla), data, attrlen); } EXPORT_SYMBOL(__nla_put_64bit); /** * __nla_put_nohdr - Add a netlink attribute without header * @skb: socket buffer to add attribute to * @attrlen: length of attribute payload * @data: head of attribute payload * * The caller is responsible to ensure that the skb provides enough * tailroom for the attribute payload. */ void __nla_put_nohdr(struct sk_buff *skb, int attrlen, const void *data) { void *start; start = __nla_reserve_nohdr(skb, attrlen); memcpy(start, data, attrlen); } EXPORT_SYMBOL(__nla_put_nohdr); /** * nla_put - Add a netlink attribute to a socket buffer * @skb: socket buffer to add attribute to * @attrtype: attribute type * @attrlen: length of attribute payload * @data: head of attribute payload * * Returns -EMSGSIZE if the tailroom of the skb is insufficient to store * the attribute header and payload. */ int nla_put(struct sk_buff *skb, int attrtype, int attrlen, const void *data) { if (unlikely(skb_tailroom(skb) < nla_total_size(attrlen))) return -EMSGSIZE; __nla_put(skb, attrtype, attrlen, data); return 0; } EXPORT_SYMBOL(nla_put); /** * nla_put_64bit - Add a netlink attribute to a socket buffer and align it * @skb: socket buffer to add attribute to * @attrtype: attribute type * @attrlen: length of attribute payload * @data: head of attribute payload * @padattr: attribute type for the padding * * Returns -EMSGSIZE if the tailroom of the skb is insufficient to store * the attribute header and payload. */ int nla_put_64bit(struct sk_buff *skb, int attrtype, int attrlen, const void *data, int padattr) { size_t len; if (nla_need_padding_for_64bit(skb)) len = nla_total_size_64bit(attrlen); else len = nla_total_size(attrlen); if (unlikely(skb_tailroom(skb) < len)) return -EMSGSIZE; __nla_put_64bit(skb, attrtype, attrlen, data, padattr); return 0; } EXPORT_SYMBOL(nla_put_64bit); /** * nla_put_nohdr - Add a netlink attribute without header * @skb: socket buffer to add attribute to * @attrlen: length of attribute payload * @data: head of attribute payload * * Returns -EMSGSIZE if the tailroom of the skb is insufficient to store * the attribute payload. */ int nla_put_nohdr(struct sk_buff *skb, int attrlen, const void *data) { if (unlikely(skb_tailroom(skb) < NLA_ALIGN(attrlen))) return -EMSGSIZE; __nla_put_nohdr(skb, attrlen, data); return 0; } EXPORT_SYMBOL(nla_put_nohdr); /** * nla_append - Add a netlink attribute without header or padding * @skb: socket buffer to add attribute to * @attrlen: length of attribute payload * @data: head of attribute payload * * Returns -EMSGSIZE if the tailroom of the skb is insufficient to store * the attribute payload. */ int nla_append(struct sk_buff *skb, int attrlen, const void *data) { if (unlikely(skb_tailroom(skb) < NLA_ALIGN(attrlen))) return -EMSGSIZE; skb_put_data(skb, data, attrlen); return 0; } EXPORT_SYMBOL(nla_append); #endif |
| 25 73 73 73 43 43 43 43 25 8 14 3 3 24 47 2 47 8 8 18 18 20 19 47 47 47 47 47 11 11 11 11 1 1 7 7 7 7 7 7 7 7 7 7 7 47 47 7 7 6 47 172 171 47 47 47 47 47 1 1 47 47 47 47 17 46 46 46 46 28 7 6 12 12 18 18 18 18 18 7 7 7 4 3 7 7 7 7 11 11 9 9 11 7 11 9 2 2 2 2 2 2 2 7 7 7 7 7 7 7 7 2 2 1 1 6 6 6 6 67 3 66 3 5 3 20 20 20 6 37 33 33 33 26 26 26 19 2 19 4 54 73 73 73 68 50 50 50 50 1 1 70 72 55 46 46 55 55 2 54 3 55 55 75 75 54 72 53 1 1 1 1 5 5 5 5 5 5 2 5 5 5 5 5 4 2 2 5 5 2 4 4 2 2 2 20 20 3 2 192 204 197 204 196 196 196 190 19 19 6 6 19 191 17 17 1 1 196 190 6 6 4 4 2 3 4 4 4 4 1 1 8 8 5 5 5 5 3 3 8 5 3 3 5 2 3 4 4 4 2 2 2 5 5 5 3 2 2 2 2 1 2 4 4 1 5 4 4 1 1 1 3 3 2 3 3 4 2 2 1 4 3 3 1 1 1 1 1 1 1 1 1 3 1 1 1 2 3 2 2 11 3 3 2 1 3 2 1 1 1 3 25 8 2 6 4 3 2 3 56 18 8 10 2 1 5 2 10 28 15 14 12 2 14 3 11 1 5 4 1 11 56 54 1 1 56 56 28 96 41 81 35 35 35 35 47 47 47 47 42 48 42 38 38 36 36 3 3 2 2 2 33 67 137 114 92 94 92 5 33 33 1 1 3 3 1 1 3 3 8 8 6 2 4 4 4 1 4 3 42 42 3 3 2 2 2 39 28 7 28 5 1 2 2 5 3 3 3 1 5 5 5 1 4 1 1 1 1 1 1 1 1 1 1 1 1 5 10 10 10 10 4 4 4 4 4 4 4 10 9 8 8 8 8 9 8 8 9 11 10 10 10 10 10 10 11 2 1 2 3 2 3 2 1 2 2 1 2 54 78 28 15 15 8 8 15 15 15 15 15 78 78 78 28 | 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Bridge multicast support. * * Copyright (c) 2010 Herbert Xu <herbert@gondor.apana.org.au> */ #include <linux/err.h> #include <linux/export.h> #include <linux/if_ether.h> #include <linux/igmp.h> #include <linux/in.h> #include <linux/jhash.h> #include <linux/kernel.h> #include <linux/log2.h> #include <linux/netdevice.h> #include <linux/netfilter_bridge.h> #include <linux/random.h> #include <linux/rculist.h> #include <linux/skbuff.h> #include <linux/slab.h> #include <linux/timer.h> #include <linux/inetdevice.h> #include <linux/mroute.h> #include <net/ip.h> #include <net/switchdev.h> #if IS_ENABLED(CONFIG_IPV6) #include <linux/icmpv6.h> #include <net/ipv6.h> #include <net/mld.h> #include <net/ip6_checksum.h> #include <net/addrconf.h> #endif #include <trace/events/bridge.h> #include "br_private.h" #include "br_private_mcast_eht.h" static const struct rhashtable_params br_mdb_rht_params = { .head_offset = offsetof(struct net_bridge_mdb_entry, rhnode), .key_offset = offsetof(struct net_bridge_mdb_entry, addr), .key_len = sizeof(struct br_ip), .automatic_shrinking = true, }; static const struct rhashtable_params br_sg_port_rht_params = { .head_offset = offsetof(struct net_bridge_port_group, rhnode), .key_offset = offsetof(struct net_bridge_port_group, key), .key_len = sizeof(struct net_bridge_port_group_sg_key), .automatic_shrinking = true, }; static void br_multicast_start_querier(struct net_bridge_mcast *brmctx, struct bridge_mcast_own_query *query); static void br_ip4_multicast_add_router(struct net_bridge_mcast *brmctx, struct net_bridge_mcast_port *pmctx); static void br_ip4_multicast_leave_group(struct net_bridge_mcast *brmctx, struct net_bridge_mcast_port *pmctx, __be32 group, __u16 vid, const unsigned char *src); static void br_multicast_port_group_rexmit(struct timer_list *t); static void br_multicast_rport_del_notify(struct net_bridge_mcast_port *pmctx, bool deleted); static void br_ip6_multicast_add_router(struct net_bridge_mcast *brmctx, struct net_bridge_mcast_port *pmctx); #if IS_ENABLED(CONFIG_IPV6) static void br_ip6_multicast_leave_group(struct net_bridge_mcast *brmctx, struct net_bridge_mcast_port *pmctx, const struct in6_addr *group, __u16 vid, const unsigned char *src); #endif static struct net_bridge_port_group * __br_multicast_add_group(struct net_bridge_mcast *brmctx, struct net_bridge_mcast_port *pmctx, struct br_ip *group, const unsigned char *src, u8 filter_mode, bool igmpv2_mldv1, bool blocked); static void br_multicast_find_del_pg(struct net_bridge *br, struct net_bridge_port_group *pg); static void __br_multicast_stop(struct net_bridge_mcast *brmctx); static int br_mc_disabled_update(struct net_device *dev, bool value, struct netlink_ext_ack *extack); static struct net_bridge_port_group * br_sg_port_find(struct net_bridge *br, struct net_bridge_port_group_sg_key *sg_p) { lockdep_assert_held_once(&br->multicast_lock); return rhashtable_lookup_fast(&br->sg_port_tbl, sg_p, br_sg_port_rht_params); } static struct net_bridge_mdb_entry *br_mdb_ip_get_rcu(struct net_bridge *br, struct br_ip *dst) { return rhashtable_lookup(&br->mdb_hash_tbl, dst, br_mdb_rht_params); } struct net_bridge_mdb_entry *br_mdb_ip_get(struct net_bridge *br, struct br_ip *dst) { struct net_bridge_mdb_entry *ent; lockdep_assert_held_once(&br->multicast_lock); rcu_read_lock(); ent = rhashtable_lookup(&br->mdb_hash_tbl, dst, br_mdb_rht_params); rcu_read_unlock(); return ent; } static struct net_bridge_mdb_entry *br_mdb_ip4_get(struct net_bridge *br, __be32 dst, __u16 vid) { struct br_ip br_dst; memset(&br_dst, 0, sizeof(br_dst)); br_dst.dst.ip4 = dst; br_dst.proto = htons(ETH_P_IP); br_dst.vid = vid; return br_mdb_ip_get(br, &br_dst); } #if IS_ENABLED(CONFIG_IPV6) static struct net_bridge_mdb_entry *br_mdb_ip6_get(struct net_bridge *br, const struct in6_addr *dst, __u16 vid) { struct br_ip br_dst; memset(&br_dst, 0, sizeof(br_dst)); br_dst.dst.ip6 = *dst; br_dst.proto = htons(ETH_P_IPV6); br_dst.vid = vid; return br_mdb_ip_get(br, &br_dst); } #endif struct net_bridge_mdb_entry * br_mdb_entry_skb_get(struct net_bridge_mcast *brmctx, struct sk_buff *skb, u16 vid) { struct net_bridge *br = brmctx->br; struct br_ip ip; if (!br_opt_get(br, BROPT_MULTICAST_ENABLED) || br_multicast_ctx_vlan_global_disabled(brmctx)) return NULL; if (BR_INPUT_SKB_CB(skb)->igmp) return NULL; memset(&ip, 0, sizeof(ip)); ip.proto = skb->protocol; ip.vid = vid; switch (skb->protocol) { case htons(ETH_P_IP): ip.dst.ip4 = ip_hdr(skb)->daddr; if (brmctx->multicast_igmp_version == 3) { struct net_bridge_mdb_entry *mdb; ip.src.ip4 = ip_hdr(skb)->saddr; mdb = br_mdb_ip_get_rcu(br, &ip); if (mdb) return mdb; ip.src.ip4 = 0; } break; #if IS_ENABLED(CONFIG_IPV6) case htons(ETH_P_IPV6): ip.dst.ip6 = ipv6_hdr(skb)->daddr; if (brmctx->multicast_mld_version == 2) { struct net_bridge_mdb_entry *mdb; ip.src.ip6 = ipv6_hdr(skb)->saddr; mdb = br_mdb_ip_get_rcu(br, &ip); if (mdb) return mdb; memset(&ip.src.ip6, 0, sizeof(ip.src.ip6)); } break; #endif default: ip.proto = 0; ether_addr_copy(ip.dst.mac_addr, eth_hdr(skb)->h_dest); } return br_mdb_ip_get_rcu(br, &ip); } /* IMPORTANT: this function must be used only when the contexts cannot be * passed down (e.g. timer) and must be used for read-only purposes because * the vlan snooping option can change, so it can return any context * (non-vlan or vlan). Its initial intended purpose is to read timer values * from the *current* context based on the option. At worst that could lead * to inconsistent timers when the contexts are changed, i.e. src timer * which needs to re-arm with a specific delay taken from the old context */ static struct net_bridge_mcast_port * br_multicast_pg_to_port_ctx(const struct net_bridge_port_group *pg) { struct net_bridge_mcast_port *pmctx = &pg->key.port->multicast_ctx; struct net_bridge_vlan *vlan; lockdep_assert_held_once(&pg->key.port->br->multicast_lock); /* if vlan snooping is disabled use the port's multicast context */ if (!pg->key.addr.vid || !br_opt_get(pg->key.port->br, BROPT_MCAST_VLAN_SNOOPING_ENABLED)) goto out; /* locking is tricky here, due to different rules for multicast and * vlans we need to take rcu to find the vlan and make sure it has * the BR_VLFLAG_MCAST_ENABLED flag set, it can only change under * multicast_lock which must be already held here, so the vlan's pmctx * can safely be used on return */ rcu_read_lock(); vlan = br_vlan_find(nbp_vlan_group_rcu(pg->key.port), pg->key.addr.vid); if (vlan && !br_multicast_port_ctx_vlan_disabled(&vlan->port_mcast_ctx)) pmctx = &vlan->port_mcast_ctx; else pmctx = NULL; rcu_read_unlock(); out: return pmctx; } static struct net_bridge_mcast_port * br_multicast_port_vid_to_port_ctx(struct net_bridge_port *port, u16 vid) { struct net_bridge_mcast_port *pmctx = NULL; struct net_bridge_vlan *vlan; lockdep_assert_held_once(&port->br->multicast_lock); if (!br_opt_get(port->br, BROPT_MCAST_VLAN_SNOOPING_ENABLED)) return NULL; /* Take RCU to access the vlan. */ rcu_read_lock(); vlan = br_vlan_find(nbp_vlan_group_rcu(port), vid); if (vlan && !br_multicast_port_ctx_vlan_disabled(&vlan->port_mcast_ctx)) pmctx = &vlan->port_mcast_ctx; rcu_read_unlock(); return pmctx; } /* when snooping we need to check if the contexts should be used * in the following order: * - if pmctx is non-NULL (port), check if it should be used * - if pmctx is NULL (bridge), check if brmctx should be used */ static bool br_multicast_ctx_should_use(const struct net_bridge_mcast *brmctx, const struct net_bridge_mcast_port *pmctx) { if (!netif_running(brmctx->br->dev)) return false; if (pmctx) return !br_multicast_port_ctx_state_disabled(pmctx); else return !br_multicast_ctx_vlan_disabled(brmctx); } static bool br_port_group_equal(struct net_bridge_port_group *p, struct net_bridge_port *port, const unsigned char *src) { if (p->key.port != port) return false; if (!(port->flags & BR_MULTICAST_TO_UNICAST)) return true; return ether_addr_equal(src, p->eth_addr); } static void __fwd_add_star_excl(struct net_bridge_mcast_port *pmctx, struct net_bridge_port_group *pg, struct br_ip *sg_ip) { struct net_bridge_port_group_sg_key sg_key; struct net_bridge_port_group *src_pg; struct net_bridge_mcast *brmctx; memset(&sg_key, 0, sizeof(sg_key)); brmctx = br_multicast_port_ctx_get_global(pmctx); sg_key.port = pg->key.port; sg_key.addr = *sg_ip; if (br_sg_port_find(brmctx->br, &sg_key)) return; src_pg = __br_multicast_add_group(brmctx, pmctx, sg_ip, pg->eth_addr, MCAST_INCLUDE, false, false); if (IS_ERR_OR_NULL(src_pg) || src_pg->rt_protocol != RTPROT_KERNEL) return; src_pg->flags |= MDB_PG_FLAGS_STAR_EXCL; } static void __fwd_del_star_excl(struct net_bridge_port_group *pg, struct br_ip *sg_ip) { struct net_bridge_port_group_sg_key sg_key; struct net_bridge *br = pg->key.port->br; struct net_bridge_port_group *src_pg; memset(&sg_key, 0, sizeof(sg_key)); sg_key.port = pg->key.port; sg_key.addr = *sg_ip; src_pg = br_sg_port_find(br, &sg_key); if (!src_pg || !(src_pg->flags & MDB_PG_FLAGS_STAR_EXCL) || src_pg->rt_protocol != RTPROT_KERNEL) return; br_multicast_find_del_pg(br, src_pg); } /* When a port group transitions to (or is added as) EXCLUDE we need to add it * to all other ports' S,G entries which are not blocked by the current group * for proper replication, the assumption is that any S,G blocked entries * are already added so the S,G,port lookup should skip them. * When a port group transitions from EXCLUDE -> INCLUDE mode or is being * deleted we need to remove it from all ports' S,G entries where it was * automatically installed before (i.e. where it's MDB_PG_FLAGS_STAR_EXCL). */ void br_multicast_star_g_handle_mode(struct net_bridge_port_group *pg, u8 filter_mode) { struct net_bridge *br = pg->key.port->br; struct net_bridge_port_group *pg_lst; struct net_bridge_mcast_port *pmctx; struct net_bridge_mdb_entry *mp; struct br_ip sg_ip; if (WARN_ON(!br_multicast_is_star_g(&pg->key.addr))) return; mp = br_mdb_ip_get(br, &pg->key.addr); if (!mp) return; pmctx = br_multicast_pg_to_port_ctx(pg); if (!pmctx) return; memset(&sg_ip, 0, sizeof(sg_ip)); sg_ip = pg->key.addr; for (pg_lst = mlock_dereference(mp->ports, br); pg_lst; pg_lst = mlock_dereference(pg_lst->next, br)) { struct net_bridge_group_src *src_ent; if (pg_lst == pg) continue; hlist_for_each_entry(src_ent, &pg_lst->src_list, node) { if (!(src_ent->flags & BR_SGRP_F_INSTALLED)) continue; sg_ip.src = src_ent->addr.src; switch (filter_mode) { case MCAST_INCLUDE: __fwd_del_star_excl(pg, &sg_ip); break; case MCAST_EXCLUDE: __fwd_add_star_excl(pmctx, pg, &sg_ip); break; } } } } /* called when adding a new S,G with host_joined == false by default */ static void br_multicast_sg_host_state(struct net_bridge_mdb_entry *star_mp, struct net_bridge_port_group *sg) { struct net_bridge_mdb_entry *sg_mp; if (WARN_ON(!br_multicast_is_star_g(&star_mp->addr))) return; if (!star_mp->host_joined) return; sg_mp = br_mdb_ip_get(star_mp->br, &sg->key.addr); if (!sg_mp) return; sg_mp->host_joined = true; } /* set the host_joined state of all of *,G's S,G entries */ static void br_multicast_star_g_host_state(struct net_bridge_mdb_entry *star_mp) { struct net_bridge *br = star_mp->br; struct net_bridge_mdb_entry *sg_mp; struct net_bridge_port_group *pg; struct br_ip sg_ip; if (WARN_ON(!br_multicast_is_star_g(&star_mp->addr))) return; memset(&sg_ip, 0, sizeof(sg_ip)); sg_ip = star_mp->addr; for (pg = mlock_dereference(star_mp->ports, br); pg; pg = mlock_dereference(pg->next, br)) { struct net_bridge_group_src *src_ent; hlist_for_each_entry(src_ent, &pg->src_list, node) { if (!(src_ent->flags & BR_SGRP_F_INSTALLED)) continue; sg_ip.src = src_ent->addr.src; sg_mp = br_mdb_ip_get(br, &sg_ip); if (!sg_mp) continue; sg_mp->host_joined = star_mp->host_joined; } } } static void br_multicast_sg_del_exclude_ports(struct net_bridge_mdb_entry *sgmp) { struct net_bridge_port_group __rcu **pp; struct net_bridge_port_group *p; /* *,G exclude ports are only added to S,G entries */ if (WARN_ON(br_multicast_is_star_g(&sgmp->addr))) return; /* we need the STAR_EXCLUDE ports if there are non-STAR_EXCLUDE ports * we should ignore perm entries since they're managed by user-space */ for (pp = &sgmp->ports; (p = mlock_dereference(*pp, sgmp->br)) != NULL; pp = &p->next) if (!(p->flags & (MDB_PG_FLAGS_STAR_EXCL | MDB_PG_FLAGS_PERMANENT))) return; /* currently the host can only have joined the *,G which means * we treat it as EXCLUDE {}, so for an S,G it's considered a * STAR_EXCLUDE entry and we can safely leave it */ sgmp->host_joined = false; for (pp = &sgmp->ports; (p = mlock_dereference(*pp, sgmp->br)) != NULL;) { if (!(p->flags & MDB_PG_FLAGS_PERMANENT)) br_multicast_del_pg(sgmp, p, pp); else pp = &p->next; } } void br_multicast_sg_add_exclude_ports(struct net_bridge_mdb_entry *star_mp, struct net_bridge_port_group *sg) { struct net_bridge_port_group_sg_key sg_key; struct net_bridge *br = star_mp->br; struct net_bridge_mcast_port *pmctx; struct net_bridge_port_group *pg; struct net_bridge_mcast *brmctx; if (WARN_ON(br_multicast_is_star_g(&sg->key.addr))) return; if (WARN_ON(!br_multicast_is_star_g(&star_mp->addr))) return; br_multicast_sg_host_state(star_mp, sg); memset(&sg_key, 0, sizeof(sg_key)); sg_key.addr = sg->key.addr; /* we need to add all exclude ports to the S,G */ for (pg = mlock_dereference(star_mp->ports, br); pg; pg = mlock_dereference(pg->next, br)) { struct net_bridge_port_group *src_pg; if (pg == sg || pg->filter_mode == MCAST_INCLUDE) continue; sg_key.port = pg->key.port; if (br_sg_port_find(br, &sg_key)) continue; pmctx = br_multicast_pg_to_port_ctx(pg); if (!pmctx) continue; brmctx = br_multicast_port_ctx_get_global(pmctx); src_pg = __br_multicast_add_group(brmctx, pmctx, &sg->key.addr, sg->eth_addr, MCAST_INCLUDE, false, false); if (IS_ERR_OR_NULL(src_pg) || src_pg->rt_protocol != RTPROT_KERNEL) continue; src_pg->flags |= MDB_PG_FLAGS_STAR_EXCL; } } static void br_multicast_fwd_src_add(struct net_bridge_group_src *src) { struct net_bridge_mdb_entry *star_mp; struct net_bridge_mcast_port *pmctx; struct net_bridge_port_group *sg; struct net_bridge_mcast *brmctx; struct br_ip sg_ip; if (src->flags & BR_SGRP_F_INSTALLED) return; memset(&sg_ip, 0, sizeof(sg_ip)); pmctx = br_multicast_pg_to_port_ctx(src->pg); if (!pmctx) return; brmctx = br_multicast_port_ctx_get_global(pmctx); sg_ip = src->pg->key.addr; sg_ip.src = src->addr.src; sg = __br_multicast_add_group(brmctx, pmctx, &sg_ip, src->pg->eth_addr, MCAST_INCLUDE, false, !timer_pending(&src->timer)); if (IS_ERR_OR_NULL(sg)) return; src->flags |= BR_SGRP_F_INSTALLED; sg->flags &= ~MDB_PG_FLAGS_STAR_EXCL; /* if it was added by user-space as perm we can skip next steps */ if (sg->rt_protocol != RTPROT_KERNEL && (sg->flags & MDB_PG_FLAGS_PERMANENT)) return; /* the kernel is now responsible for removing this S,G */ timer_delete(&sg->timer); star_mp = br_mdb_ip_get(src->br, &src->pg->key.addr); if (!star_mp) return; br_multicast_sg_add_exclude_ports(star_mp, sg); } static void br_multicast_fwd_src_remove(struct net_bridge_group_src *src, bool fastleave) { struct net_bridge_port_group *p, *pg = src->pg; struct net_bridge_port_group __rcu **pp; struct net_bridge_mdb_entry *mp; struct br_ip sg_ip; memset(&sg_ip, 0, sizeof(sg_ip)); sg_ip = pg->key.addr; sg_ip.src = src->addr.src; mp = br_mdb_ip_get(src->br, &sg_ip); if (!mp) return; for (pp = &mp->ports; (p = mlock_dereference(*pp, src->br)) != NULL; pp = &p->next) { if (!br_port_group_equal(p, pg->key.port, pg->eth_addr)) continue; if (p->rt_protocol != RTPROT_KERNEL && (p->flags & MDB_PG_FLAGS_PERMANENT) && !(src->flags & BR_SGRP_F_USER_ADDED)) break; if (fastleave) p->flags |= MDB_PG_FLAGS_FAST_LEAVE; br_multicast_del_pg(mp, p, pp); break; } src->flags &= ~BR_SGRP_F_INSTALLED; } /* install S,G and based on src's timer enable or disable forwarding */ static void br_multicast_fwd_src_handle(struct net_bridge_group_src *src) { struct net_bridge_port_group_sg_key sg_key; struct net_bridge_port_group *sg; u8 old_flags; br_multicast_fwd_src_add(src); memset(&sg_key, 0, sizeof(sg_key)); sg_key.addr = src->pg->key.addr; sg_key.addr.src = src->addr.src; sg_key.port = src->pg->key.port; sg = br_sg_port_find(src->br, &sg_key); if (!sg || (sg->flags & MDB_PG_FLAGS_PERMANENT)) return; old_flags = sg->flags; if (timer_pending(&src->timer)) sg->flags &= ~MDB_PG_FLAGS_BLOCKED; else sg->flags |= MDB_PG_FLAGS_BLOCKED; if (old_flags != sg->flags) { struct net_bridge_mdb_entry *sg_mp; sg_mp = br_mdb_ip_get(src->br, &sg_key.addr); if (!sg_mp) return; br_mdb_notify(src->br->dev, sg_mp, sg, RTM_NEWMDB); } } static void br_multicast_destroy_mdb_entry(struct net_bridge_mcast_gc *gc) { struct net_bridge_mdb_entry *mp; mp = container_of(gc, struct net_bridge_mdb_entry, mcast_gc); WARN_ON(!hlist_unhashed(&mp->mdb_node)); WARN_ON(mp->ports); timer_shutdown_sync(&mp->timer); kfree_rcu(mp, rcu); } static void br_multicast_del_mdb_entry(struct net_bridge_mdb_entry *mp) { struct net_bridge *br = mp->br; rhashtable_remove_fast(&br->mdb_hash_tbl, &mp->rhnode, br_mdb_rht_params); hlist_del_init_rcu(&mp->mdb_node); hlist_add_head(&mp->mcast_gc.gc_node, &br->mcast_gc_list); queue_work(system_long_wq, &br->mcast_gc_work); } static void br_multicast_group_expired(struct timer_list *t) { struct net_bridge_mdb_entry *mp = timer_container_of(mp, t, timer); struct net_bridge *br = mp->br; spin_lock(&br->multicast_lock); if (hlist_unhashed(&mp->mdb_node) || !netif_running(br->dev) || timer_pending(&mp->timer)) goto out; br_multicast_host_leave(mp, true); if (mp->ports) goto out; br_multicast_del_mdb_entry(mp); out: spin_unlock(&br->multicast_lock); } static void br_multicast_destroy_group_src(struct net_bridge_mcast_gc *gc) { struct net_bridge_group_src *src; src = container_of(gc, struct net_bridge_group_src, mcast_gc); WARN_ON(!hlist_unhashed(&src->node)); timer_shutdown_sync(&src->timer); kfree_rcu(src, rcu); } void __br_multicast_del_group_src(struct net_bridge_group_src *src) { struct net_bridge *br = src->pg->key.port->br; hlist_del_init_rcu(&src->node); src->pg->src_ents--; hlist_add_head(&src->mcast_gc.gc_node, &br->mcast_gc_list); queue_work(system_long_wq, &br->mcast_gc_work); } void br_multicast_del_group_src(struct net_bridge_group_src *src, bool fastleave) { br_multicast_fwd_src_remove(src, fastleave); __br_multicast_del_group_src(src); } static int br_multicast_port_ngroups_inc_one(struct net_bridge_mcast_port *pmctx, struct netlink_ext_ack *extack, const char *what) { u32 max = READ_ONCE(pmctx->mdb_max_entries); u32 n = READ_ONCE(pmctx->mdb_n_entries); if (max && n >= max) { NL_SET_ERR_MSG_FMT_MOD(extack, "%s is already in %u groups, and mcast_max_groups=%u", what, n, max); return -E2BIG; } WRITE_ONCE(pmctx->mdb_n_entries, n + 1); return 0; } static void br_multicast_port_ngroups_dec_one(struct net_bridge_mcast_port *pmctx) { u32 n = READ_ONCE(pmctx->mdb_n_entries); WARN_ON_ONCE(n == 0); WRITE_ONCE(pmctx->mdb_n_entries, n - 1); } static int br_multicast_port_ngroups_inc(struct net_bridge_port *port, const struct br_ip *group, struct netlink_ext_ack *extack) { struct net_bridge_mcast_port *pmctx; int err; lockdep_assert_held_once(&port->br->multicast_lock); /* Always count on the port context. */ err = br_multicast_port_ngroups_inc_one(&port->multicast_ctx, extack, "Port"); if (err) { trace_br_mdb_full(port->dev, group); return err; } /* Only count on the VLAN context if VID is given, and if snooping on * that VLAN is enabled. */ if (!group->vid) return 0; pmctx = br_multicast_port_vid_to_port_ctx(port, group->vid); if (!pmctx) return 0; err = br_multicast_port_ngroups_inc_one(pmctx, extack, "Port-VLAN"); if (err) { trace_br_mdb_full(port->dev, group); goto dec_one_out; } return 0; dec_one_out: br_multicast_port_ngroups_dec_one(&port->multicast_ctx); return err; } static void br_multicast_port_ngroups_dec(struct net_bridge_port *port, u16 vid) { struct net_bridge_mcast_port *pmctx; lockdep_assert_held_once(&port->br->multicast_lock); if (vid) { pmctx = br_multicast_port_vid_to_port_ctx(port, vid); if (pmctx) br_multicast_port_ngroups_dec_one(pmctx); } br_multicast_port_ngroups_dec_one(&port->multicast_ctx); } u32 br_multicast_ngroups_get(const struct net_bridge_mcast_port *pmctx) { return READ_ONCE(pmctx->mdb_n_entries); } void br_multicast_ngroups_set_max(struct net_bridge_mcast_port *pmctx, u32 max) { WRITE_ONCE(pmctx->mdb_max_entries, max); } u32 br_multicast_ngroups_get_max(const struct net_bridge_mcast_port *pmctx) { return READ_ONCE(pmctx->mdb_max_entries); } static void br_multicast_destroy_port_group(struct net_bridge_mcast_gc *gc) { struct net_bridge_port_group *pg; pg = container_of(gc, struct net_bridge_port_group, mcast_gc); WARN_ON(!hlist_unhashed(&pg->mglist)); WARN_ON(!hlist_empty(&pg->src_list)); timer_shutdown_sync(&pg->rexmit_timer); timer_shutdown_sync(&pg->timer); kfree_rcu(pg, rcu); } void br_multicast_del_pg(struct net_bridge_mdb_entry *mp, struct net_bridge_port_group *pg, struct net_bridge_port_group __rcu **pp) { struct net_bridge *br = pg->key.port->br; struct net_bridge_group_src *ent; struct hlist_node *tmp; rcu_assign_pointer(*pp, pg->next); hlist_del_init(&pg->mglist); br_multicast_eht_clean_sets(pg); hlist_for_each_entry_safe(ent, tmp, &pg->src_list, node) br_multicast_del_group_src(ent, false); br_mdb_notify(br->dev, mp, pg, RTM_DELMDB); if (!br_multicast_is_star_g(&mp->addr)) { rhashtable_remove_fast(&br->sg_port_tbl, &pg->rhnode, br_sg_port_rht_params); br_multicast_sg_del_exclude_ports(mp); } else { br_multicast_star_g_handle_mode(pg, MCAST_INCLUDE); } br_multicast_port_ngroups_dec(pg->key.port, pg->key.addr.vid); hlist_add_head(&pg->mcast_gc.gc_node, &br->mcast_gc_list); queue_work(system_long_wq, &br->mcast_gc_work); if (!mp->ports && !mp->host_joined && netif_running(br->dev)) mod_timer(&mp->timer, jiffies); } static void br_multicast_find_del_pg(struct net_bridge *br, struct net_bridge_port_group *pg) { struct net_bridge_port_group __rcu **pp; struct net_bridge_mdb_entry *mp; struct net_bridge_port_group *p; mp = br_mdb_ip_get(br, &pg->key.addr); if (WARN_ON(!mp)) return; for (pp = &mp->ports; (p = mlock_dereference(*pp, br)) != NULL; pp = &p->next) { if (p != pg) continue; br_multicast_del_pg(mp, pg, pp); return; } WARN_ON(1); } static void br_multicast_port_group_expired(struct timer_list *t) { struct net_bridge_port_group *pg = timer_container_of(pg, t, timer); struct net_bridge_group_src *src_ent; struct net_bridge *br = pg->key.port->br; struct hlist_node *tmp; bool changed; spin_lock(&br->multicast_lock); if (!netif_running(br->dev) || timer_pending(&pg->timer) || hlist_unhashed(&pg->mglist) || pg->flags & MDB_PG_FLAGS_PERMANENT) goto out; changed = !!(pg->filter_mode == MCAST_EXCLUDE); pg->filter_mode = MCAST_INCLUDE; hlist_for_each_entry_safe(src_ent, tmp, &pg->src_list, node) { if (!timer_pending(&src_ent->timer)) { br_multicast_del_group_src(src_ent, false); changed = true; } } if (hlist_empty(&pg->src_list)) { br_multicast_find_del_pg(br, pg); } else if (changed) { struct net_bridge_mdb_entry *mp = br_mdb_ip_get(br, &pg->key.addr); if (changed && br_multicast_is_star_g(&pg->key.addr)) br_multicast_star_g_handle_mode(pg, MCAST_INCLUDE); if (WARN_ON(!mp)) goto out; br_mdb_notify(br->dev, mp, pg, RTM_NEWMDB); } out: spin_unlock(&br->multicast_lock); } static void br_multicast_gc(struct hlist_head *head) { struct net_bridge_mcast_gc *gcent; struct hlist_node *tmp; hlist_for_each_entry_safe(gcent, tmp, head, gc_node) { hlist_del_init(&gcent->gc_node); gcent->destroy(gcent); } } static void __br_multicast_query_handle_vlan(struct net_bridge_mcast *brmctx, struct net_bridge_mcast_port *pmctx, struct sk_buff *skb) { struct net_bridge_vlan *vlan = NULL; if (pmctx && br_multicast_port_ctx_is_vlan(pmctx)) vlan = pmctx->vlan; else if (br_multicast_ctx_is_vlan(brmctx)) vlan = brmctx->vlan; if (vlan && !(vlan->flags & BRIDGE_VLAN_INFO_UNTAGGED)) { u16 vlan_proto; if (br_vlan_get_proto(brmctx->br->dev, &vlan_proto) != 0) return; __vlan_hwaccel_put_tag(skb, htons(vlan_proto), vlan->vid); } } static struct sk_buff *br_ip4_multicast_alloc_query(struct net_bridge_mcast *brmctx, struct net_bridge_mcast_port *pmctx, struct net_bridge_port_group *pg, __be32 ip_dst, __be32 group, bool with_srcs, bool over_lmqt, u8 sflag, u8 *igmp_type, bool *need_rexmit) { struct net_bridge_port *p = pg ? pg->key.port : NULL; struct net_bridge_group_src *ent; size_t pkt_size, igmp_hdr_size; unsigned long now = jiffies; struct igmpv3_query *ihv3; void *csum_start = NULL; __sum16 *csum = NULL; struct sk_buff *skb; struct igmphdr *ih; struct ethhdr *eth; unsigned long lmqt; struct iphdr *iph; u16 lmqt_srcs = 0; igmp_hdr_size = sizeof(*ih); if (brmctx->multicast_igmp_version == 3) { igmp_hdr_size = sizeof(*ihv3); if (pg && with_srcs) { lmqt = now + (brmctx->multicast_last_member_interval * brmctx->multicast_last_member_count); hlist_for_each_entry(ent, &pg->src_list, node) { if (over_lmqt == time_after(ent->timer.expires, lmqt) && ent->src_query_rexmit_cnt > 0) lmqt_srcs++; } if (!lmqt_srcs) return NULL; igmp_hdr_size += lmqt_srcs * sizeof(__be32); } } pkt_size = sizeof(*eth) + sizeof(*iph) + 4 + igmp_hdr_size; if ((p && pkt_size > p->dev->mtu) || pkt_size > brmctx->br->dev->mtu) return NULL; skb = netdev_alloc_skb_ip_align(brmctx->br->dev, pkt_size); if (!skb) goto out; __br_multicast_query_handle_vlan(brmctx, pmctx, skb); skb->protocol = htons(ETH_P_IP); skb_reset_mac_header(skb); eth = eth_hdr(skb); ether_addr_copy(eth->h_source, brmctx->br->dev->dev_addr); ip_eth_mc_map(ip_dst, eth->h_dest); eth->h_proto = htons(ETH_P_IP); skb_put(skb, sizeof(*eth)); skb_set_network_header(skb, skb->len); iph = ip_hdr(skb); iph->tot_len = htons(pkt_size - sizeof(*eth)); iph->version = 4; iph->ihl = 6; iph->tos = 0xc0; iph->id = 0; iph->frag_off = htons(IP_DF); iph->ttl = 1; iph->protocol = IPPROTO_IGMP; iph->saddr = br_opt_get(brmctx->br, BROPT_MULTICAST_QUERY_USE_IFADDR) ? inet_select_addr(brmctx->br->dev, 0, RT_SCOPE_LINK) : 0; iph->daddr = ip_dst; ((u8 *)&iph[1])[0] = IPOPT_RA; ((u8 *)&iph[1])[1] = 4; ((u8 *)&iph[1])[2] = 0; ((u8 *)&iph[1])[3] = 0; ip_send_check(iph); skb_put(skb, 24); skb_set_transport_header(skb, skb->len); *igmp_type = IGMP_HOST_MEMBERSHIP_QUERY; switch (brmctx->multicast_igmp_version) { case 2: ih = igmp_hdr(skb); ih->type = IGMP_HOST_MEMBERSHIP_QUERY; ih->code = (group ? brmctx->multicast_last_member_interval : brmctx->multicast_query_response_interval) / (HZ / IGMP_TIMER_SCALE); ih->group = group; ih->csum = 0; csum = &ih->csum; csum_start = (void *)ih; break; case 3: ihv3 = igmpv3_query_hdr(skb); ihv3->type = IGMP_HOST_MEMBERSHIP_QUERY; ihv3->code = (group ? brmctx->multicast_last_member_interval : brmctx->multicast_query_response_interval) / (HZ / IGMP_TIMER_SCALE); ihv3->group = group; ihv3->qqic = brmctx->multicast_query_interval / HZ; ihv3->nsrcs = htons(lmqt_srcs); ihv3->resv = 0; ihv3->suppress = sflag; ihv3->qrv = 2; ihv3->csum = 0; csum = &ihv3->csum; csum_start = (void *)ihv3; if (!pg || !with_srcs) break; lmqt_srcs = 0; hlist_for_each_entry(ent, &pg->src_list, node) { if (over_lmqt == time_after(ent->timer.expires, lmqt) && ent->src_query_rexmit_cnt > 0) { ihv3->srcs[lmqt_srcs++] = ent->addr.src.ip4; ent->src_query_rexmit_cnt--; if (need_rexmit && ent->src_query_rexmit_cnt) *need_rexmit = true; } } if (WARN_ON(lmqt_srcs != ntohs(ihv3->nsrcs))) { kfree_skb(skb); return NULL; } break; } if (WARN_ON(!csum || !csum_start)) { kfree_skb(skb); return NULL; } *csum = ip_compute_csum(csum_start, igmp_hdr_size); skb_put(skb, igmp_hdr_size); __skb_pull(skb, sizeof(*eth)); out: return skb; } #if IS_ENABLED(CONFIG_IPV6) static struct sk_buff *br_ip6_multicast_alloc_query(struct net_bridge_mcast *brmctx, struct net_bridge_mcast_port *pmctx, struct net_bridge_port_group *pg, const struct in6_addr *ip6_dst, const struct in6_addr *group, bool with_srcs, bool over_llqt, u8 sflag, u8 *igmp_type, bool *need_rexmit) { struct net_bridge_port *p = pg ? pg->key.port : NULL; struct net_bridge_group_src *ent; size_t pkt_size, mld_hdr_size; unsigned long now = jiffies; struct mld2_query *mld2q; void *csum_start = NULL; unsigned long interval; __sum16 *csum = NULL; struct ipv6hdr *ip6h; struct mld_msg *mldq; struct sk_buff *skb; unsigned long llqt; struct ethhdr *eth; u16 llqt_srcs = 0; u8 *hopopt; mld_hdr_size = sizeof(*mldq); if (brmctx->multicast_mld_version == 2) { mld_hdr_size = sizeof(*mld2q); if (pg && with_srcs) { llqt = now + (brmctx->multicast_last_member_interval * brmctx->multicast_last_member_count); hlist_for_each_entry(ent, &pg->src_list, node) { if (over_llqt == time_after(ent->timer.expires, llqt) && ent->src_query_rexmit_cnt > 0) llqt_srcs++; } if (!llqt_srcs) return NULL; mld_hdr_size += llqt_srcs * sizeof(struct in6_addr); } } pkt_size = sizeof(*eth) + sizeof(*ip6h) + 8 + mld_hdr_size; if ((p && pkt_size > p->dev->mtu) || pkt_size > brmctx->br->dev->mtu) return NULL; skb = netdev_alloc_skb_ip_align(brmctx->br->dev, pkt_size); if (!skb) goto out; __br_multicast_query_handle_vlan(brmctx, pmctx, skb); skb->protocol = htons(ETH_P_IPV6); /* Ethernet header */ skb_reset_mac_header(skb); eth = eth_hdr(skb); ether_addr_copy(eth->h_source, brmctx->br->dev->dev_addr); eth->h_proto = htons(ETH_P_IPV6); skb_put(skb, sizeof(*eth)); /* IPv6 header + HbH option */ skb_set_network_header(skb, skb->len); ip6h = ipv6_hdr(skb); *(__force __be32 *)ip6h = htonl(0x60000000); ip6h->payload_len = htons(8 + mld_hdr_size); ip6h->nexthdr = IPPROTO_HOPOPTS; ip6h->hop_limit = 1; ip6h->daddr = *ip6_dst; if (ipv6_dev_get_saddr(dev_net(brmctx->br->dev), brmctx->br->dev, &ip6h->daddr, 0, &ip6h->saddr)) { kfree_skb(skb); br_opt_toggle(brmctx->br, BROPT_HAS_IPV6_ADDR, false); return NULL; } br_opt_toggle(brmctx->br, BROPT_HAS_IPV6_ADDR, true); ipv6_eth_mc_map(&ip6h->daddr, eth->h_dest); hopopt = (u8 *)(ip6h + 1); hopopt[0] = IPPROTO_ICMPV6; /* next hdr */ hopopt[1] = 0; /* length of HbH */ hopopt[2] = IPV6_TLV_ROUTERALERT; /* Router Alert */ hopopt[3] = 2; /* Length of RA Option */ hopopt[4] = 0; /* Type = 0x0000 (MLD) */ hopopt[5] = 0; hopopt[6] = IPV6_TLV_PAD1; /* Pad1 */ hopopt[7] = IPV6_TLV_PAD1; /* Pad1 */ skb_put(skb, sizeof(*ip6h) + 8); /* ICMPv6 */ skb_set_transport_header(skb, skb->len); interval = ipv6_addr_any(group) ? brmctx->multicast_query_response_interval : brmctx->multicast_last_member_interval; *igmp_type = ICMPV6_MGM_QUERY; switch (brmctx->multicast_mld_version) { case 1: mldq = (struct mld_msg *)icmp6_hdr(skb); mldq->mld_type = ICMPV6_MGM_QUERY; mldq->mld_code = 0; mldq->mld_cksum = 0; mldq->mld_maxdelay = htons((u16)jiffies_to_msecs(interval)); mldq->mld_reserved = 0; mldq->mld_mca = *group; csum = &mldq->mld_cksum; csum_start = (void *)mldq; break; case 2: mld2q = (struct mld2_query *)icmp6_hdr(skb); mld2q->mld2q_mrc = htons((u16)jiffies_to_msecs(interval)); mld2q->mld2q_type = ICMPV6_MGM_QUERY; mld2q->mld2q_code = 0; mld2q->mld2q_cksum = 0; mld2q->mld2q_resv1 = 0; mld2q->mld2q_resv2 = 0; mld2q->mld2q_suppress = sflag; mld2q->mld2q_qrv = 2; mld2q->mld2q_nsrcs = htons(llqt_srcs); mld2q->mld2q_qqic = brmctx->multicast_query_interval / HZ; mld2q->mld2q_mca = *group; csum = &mld2q->mld2q_cksum; csum_start = (void *)mld2q; if (!pg || !with_srcs) break; llqt_srcs = 0; hlist_for_each_entry(ent, &pg->src_list, node) { if (over_llqt == time_after(ent->timer.expires, llqt) && ent->src_query_rexmit_cnt > 0) { mld2q->mld2q_srcs[llqt_srcs++] = ent->addr.src.ip6; ent->src_query_rexmit_cnt--; if (need_rexmit && ent->src_query_rexmit_cnt) *need_rexmit = true; } } if (WARN_ON(llqt_srcs != ntohs(mld2q->mld2q_nsrcs))) { kfree_skb(skb); return NULL; } break; } if (WARN_ON(!csum || !csum_start)) { kfree_skb(skb); return NULL; } *csum = csum_ipv6_magic(&ip6h->saddr, &ip6h->daddr, mld_hdr_size, IPPROTO_ICMPV6, csum_partial(csum_start, mld_hdr_size, 0)); skb_put(skb, mld_hdr_size); __skb_pull(skb, sizeof(*eth)); out: return skb; } #endif static struct sk_buff *br_multicast_alloc_query(struct net_bridge_mcast *brmctx, struct net_bridge_mcast_port *pmctx, struct net_bridge_port_group *pg, struct br_ip *ip_dst, struct br_ip *group, bool with_srcs, bool over_lmqt, u8 sflag, u8 *igmp_type, bool *need_rexmit) { __be32 ip4_dst; switch (group->proto) { case htons(ETH_P_IP): ip4_dst = ip_dst ? ip_dst->dst.ip4 : htonl(INADDR_ALLHOSTS_GROUP); return br_ip4_multicast_alloc_query(brmctx, pmctx, pg, ip4_dst, group->dst.ip4, with_srcs, over_lmqt, sflag, igmp_type, need_rexmit); #if IS_ENABLED(CONFIG_IPV6) case htons(ETH_P_IPV6): { struct in6_addr ip6_dst; if (ip_dst) ip6_dst = ip_dst->dst.ip6; else ipv6_addr_set(&ip6_dst, htonl(0xff020000), 0, 0, htonl(1)); return br_ip6_multicast_alloc_query(brmctx, pmctx, pg, &ip6_dst, &group->dst.ip6, with_srcs, over_lmqt, sflag, igmp_type, need_rexmit); } #endif } return NULL; } struct net_bridge_mdb_entry *br_multicast_new_group(struct net_bridge *br, struct br_ip *group) { struct net_bridge_mdb_entry *mp; int err; mp = br_mdb_ip_get(br, group); if (mp) return mp; if (atomic_read(&br->mdb_hash_tbl.nelems) >= br->hash_max) { trace_br_mdb_full(br->dev, group); br_mc_disabled_update(br->dev, false, NULL); br_opt_toggle(br, BROPT_MULTICAST_ENABLED, false); return ERR_PTR(-E2BIG); } mp = kzalloc(sizeof(*mp), GFP_ATOMIC); if (unlikely(!mp)) return ERR_PTR(-ENOMEM); mp->br = br; mp->addr = *group; mp->mcast_gc.destroy = br_multicast_destroy_mdb_entry; timer_setup(&mp->timer, br_multicast_group_expired, 0); err = rhashtable_lookup_insert_fast(&br->mdb_hash_tbl, &mp->rhnode, br_mdb_rht_params); if (err) { kfree(mp); mp = ERR_PTR(err); } else { hlist_add_head_rcu(&mp->mdb_node, &br->mdb_list); } return mp; } static void br_multicast_group_src_expired(struct timer_list *t) { struct net_bridge_group_src *src = timer_container_of(src, t, timer); struct net_bridge_port_group *pg; struct net_bridge *br = src->br; spin_lock(&br->multicast_lock); if (hlist_unhashed(&src->node) || !netif_running(br->dev) || timer_pending(&src->timer)) goto out; pg = src->pg; if (pg->filter_mode == MCAST_INCLUDE) { br_multicast_del_group_src(src, false); if (!hlist_empty(&pg->src_list)) goto out; br_multicast_find_del_pg(br, pg); } else { br_multicast_fwd_src_handle(src); } out: spin_unlock(&br->multicast_lock); } struct net_bridge_group_src * br_multicast_find_group_src(struct net_bridge_port_group *pg, struct br_ip *ip) { struct net_bridge_group_src *ent; switch (ip->proto) { case htons(ETH_P_IP): hlist_for_each_entry(ent, &pg->src_list, node) if (ip->src.ip4 == ent->addr.src.ip4) return ent; break; #if IS_ENABLED(CONFIG_IPV6) case htons(ETH_P_IPV6): hlist_for_each_entry(ent, &pg->src_list, node) if (!ipv6_addr_cmp(&ent->addr.src.ip6, &ip->src.ip6)) return ent; break; #endif } return NULL; } struct net_bridge_group_src * br_multicast_new_group_src(struct net_bridge_port_group *pg, struct br_ip *src_ip) { struct net_bridge_group_src *grp_src; if (unlikely(pg->src_ents >= PG_SRC_ENT_LIMIT)) return NULL; switch (src_ip->proto) { case htons(ETH_P_IP): if (ipv4_is_zeronet(src_ip->src.ip4) || ipv4_is_multicast(src_ip->src.ip4)) return NULL; break; #if IS_ENABLED(CONFIG_IPV6) case htons(ETH_P_IPV6): if (ipv6_addr_any(&src_ip->src.ip6) || ipv6_addr_is_multicast(&src_ip->src.ip6)) return NULL; break; #endif } grp_src = kzalloc(sizeof(*grp_src), GFP_ATOMIC); if (unlikely(!grp_src)) return NULL; grp_src->pg = pg; grp_src->br = pg->key.port->br; grp_src->addr = *src_ip; grp_src->mcast_gc.destroy = br_multicast_destroy_group_src; timer_setup(&grp_src->timer, br_multicast_group_src_expired, 0); hlist_add_head_rcu(&grp_src->node, &pg->src_list); pg->src_ents++; return grp_src; } struct net_bridge_port_group *br_multicast_new_port_group( struct net_bridge_port *port, const struct br_ip *group, struct net_bridge_port_group __rcu *next, unsigned char flags, const unsigned char *src, u8 filter_mode, u8 rt_protocol, struct netlink_ext_ack *extack) { struct net_bridge_port_group *p; int err; err = br_multicast_port_ngroups_inc(port, group, extack); if (err) return NULL; p = kzalloc(sizeof(*p), GFP_ATOMIC); if (unlikely(!p)) { NL_SET_ERR_MSG_MOD(extack, "Couldn't allocate new port group"); goto dec_out; } p->key.addr = *group; p->key.port = port; p->flags = flags; p->filter_mode = filter_mode; p->rt_protocol = rt_protocol; p->eht_host_tree = RB_ROOT; p->eht_set_tree = RB_ROOT; p->mcast_gc.destroy = br_multicast_destroy_port_group; INIT_HLIST_HEAD(&p->src_list); if (!br_multicast_is_star_g(group) && rhashtable_lookup_insert_fast(&port->br->sg_port_tbl, &p->rhnode, br_sg_port_rht_params)) { NL_SET_ERR_MSG_MOD(extack, "Couldn't insert new port group"); goto free_out; } rcu_assign_pointer(p->next, next); timer_setup(&p->timer, br_multicast_port_group_expired, 0); timer_setup(&p->rexmit_timer, br_multicast_port_group_rexmit, 0); hlist_add_head(&p->mglist, &port->mglist); if (src) memcpy(p->eth_addr, src, ETH_ALEN); else eth_broadcast_addr(p->eth_addr); return p; free_out: kfree(p); dec_out: br_multicast_port_ngroups_dec(port, group->vid); return NULL; } void br_multicast_del_port_group(struct net_bridge_port_group *p) { struct net_bridge_port *port = p->key.port; __u16 vid = p->key.addr.vid; hlist_del_init(&p->mglist); if (!br_multicast_is_star_g(&p->key.addr)) rhashtable_remove_fast(&port->br->sg_port_tbl, &p->rhnode, br_sg_port_rht_params); kfree(p); br_multicast_port_ngroups_dec(port, vid); } void br_multicast_host_join(const struct net_bridge_mcast *brmctx, struct net_bridge_mdb_entry *mp, bool notify) { if (!mp->host_joined) { mp->host_joined = true; if (br_multicast_is_star_g(&mp->addr)) br_multicast_star_g_host_state(mp); if (notify) br_mdb_notify(mp->br->dev, mp, NULL, RTM_NEWMDB); } if (br_group_is_l2(&mp->addr)) return; mod_timer(&mp->timer, jiffies + brmctx->multicast_membership_interval); } void br_multicast_host_leave(struct net_bridge_mdb_entry *mp, bool notify) { if (!mp->host_joined) return; mp->host_joined = false; if (br_multicast_is_star_g(&mp->addr)) br_multicast_star_g_host_state(mp); if (notify) br_mdb_notify(mp->br->dev, mp, NULL, RTM_DELMDB); } static struct net_bridge_port_group * __br_multicast_add_group(struct net_bridge_mcast *brmctx, struct net_bridge_mcast_port *pmctx, struct br_ip *group, const unsigned char *src, u8 filter_mode, bool igmpv2_mldv1, bool blocked) { struct net_bridge_port_group __rcu **pp; struct net_bridge_port_group *p = NULL; struct net_bridge_mdb_entry *mp; unsigned long now = jiffies; if (!br_multicast_ctx_should_use(brmctx, pmctx)) goto out; mp = br_multicast_new_group(brmctx->br, group); if (IS_ERR(mp)) return ERR_CAST(mp); if (!pmctx) { br_multicast_host_join(brmctx, mp, true); goto out; } for (pp = &mp->ports; (p = mlock_dereference(*pp, brmctx->br)) != NULL; pp = &p->next) { if (br_port_group_equal(p, pmctx->port, src)) goto found; if ((unsigned long)p->key.port < (unsigned long)pmctx->port) break; } p = br_multicast_new_port_group(pmctx->port, group, *pp, 0, src, filter_mode, RTPROT_KERNEL, NULL); if (unlikely(!p)) { p = ERR_PTR(-ENOMEM); goto out; } rcu_assign_pointer(*pp, p); if (blocked) p->flags |= MDB_PG_FLAGS_BLOCKED; br_mdb_notify(brmctx->br->dev, mp, p, RTM_NEWMDB); found: if (igmpv2_mldv1) mod_timer(&p->timer, now + brmctx->multicast_membership_interval); out: return p; } static int br_multicast_add_group(struct net_bridge_mcast *brmctx, struct net_bridge_mcast_port *pmctx, struct br_ip *group, const unsigned char *src, u8 filter_mode, bool igmpv2_mldv1) { struct net_bridge_port_group *pg; int err; spin_lock(&brmctx->br->multicast_lock); pg = __br_multicast_add_group(brmctx, pmctx, group, src, filter_mode, igmpv2_mldv1, false); /* NULL is considered valid for host joined groups */ err = PTR_ERR_OR_ZERO(pg); spin_unlock(&brmctx->br->multicast_lock); return err; } static int br_ip4_multicast_add_group(struct net_bridge_mcast *brmctx, struct net_bridge_mcast_port *pmctx, __be32 group, __u16 vid, const unsigned char *src, bool igmpv2) { struct br_ip br_group; u8 filter_mode; if (ipv4_is_local_multicast(group)) return 0; memset(&br_group, 0, sizeof(br_group)); br_group.dst.ip4 = group; br_group.proto = htons(ETH_P_IP); br_group.vid = vid; filter_mode = igmpv2 ? MCAST_EXCLUDE : MCAST_INCLUDE; return br_multicast_add_group(brmctx, pmctx, &br_group, src, filter_mode, igmpv2); } #if IS_ENABLED(CONFIG_IPV6) static int br_ip6_multicast_add_group(struct net_bridge_mcast *brmctx, struct net_bridge_mcast_port *pmctx, const struct in6_addr *group, __u16 vid, const unsigned char *src, bool mldv1) { struct br_ip br_group; u8 filter_mode; if (ipv6_addr_is_ll_all_nodes(group)) return 0; memset(&br_group, 0, sizeof(br_group)); br_group.dst.ip6 = *group; br_group.proto = htons(ETH_P_IPV6); br_group.vid = vid; filter_mode = mldv1 ? MCAST_EXCLUDE : MCAST_INCLUDE; return br_multicast_add_group(brmctx, pmctx, &br_group, src, filter_mode, mldv1); } #endif static bool br_multicast_rport_del(struct hlist_node *rlist) { if (hlist_unhashed(rlist)) return false; hlist_del_init_rcu(rlist); return true; } static bool br_ip4_multicast_rport_del(struct net_bridge_mcast_port *pmctx) { return br_multicast_rport_del(&pmctx->ip4_rlist); } static bool br_ip6_multicast_rport_del(struct net_bridge_mcast_port *pmctx) { #if IS_ENABLED(CONFIG_IPV6) return br_multicast_rport_del(&pmctx->ip6_rlist); #else return false; #endif } static void br_multicast_router_expired(struct net_bridge_mcast_port *pmctx, struct timer_list *t, struct hlist_node *rlist) { struct net_bridge *br = pmctx->port->br; bool del; spin_lock(&br->multicast_lock); if (pmctx->multicast_router == MDB_RTR_TYPE_DISABLED || pmctx->multicast_router == MDB_RTR_TYPE_PERM || timer_pending(t)) goto out; del = br_multicast_rport_del(rlist); br_multicast_rport_del_notify(pmctx, del); out: spin_unlock(&br->multicast_lock); } static void br_ip4_multicast_router_expired(struct timer_list *t) { struct net_bridge_mcast_port *pmctx = timer_container_of(pmctx, t, ip4_mc_router_timer); br_multicast_router_expired(pmctx, t, &pmctx->ip4_rlist); } #if IS_ENABLED(CONFIG_IPV6) static void br_ip6_multicast_router_expired(struct timer_list *t) { struct net_bridge_mcast_port *pmctx = timer_container_of(pmctx, t, ip6_mc_router_timer); br_multicast_router_expired(pmctx, t, &pmctx->ip6_rlist); } #endif static void br_mc_router_state_change(struct net_bridge *p, bool is_mc_router) { struct switchdev_attr attr = { .orig_dev = p->dev, .id = SWITCHDEV_ATTR_ID_BRIDGE_MROUTER, .flags = SWITCHDEV_F_DEFER, .u.mrouter = is_mc_router, }; switchdev_port_attr_set(p->dev, &attr, NULL); } static void br_multicast_local_router_expired(struct net_bridge_mcast *brmctx, struct timer_list *timer) { spin_lock(&brmctx->br->multicast_lock); if (brmctx->multicast_router == MDB_RTR_TYPE_DISABLED || brmctx->multicast_router == MDB_RTR_TYPE_PERM || br_ip4_multicast_is_router(brmctx) || br_ip6_multicast_is_router(brmctx)) goto out; br_mc_router_state_change(brmctx->br, false); out: spin_unlock(&brmctx->br->multicast_lock); } static void br_ip4_multicast_local_router_expired(struct timer_list *t) { struct net_bridge_mcast *brmctx = timer_container_of(brmctx, t, ip4_mc_router_timer); br_multicast_local_router_expired(brmctx, t); } #if IS_ENABLED(CONFIG_IPV6) static void br_ip6_multicast_local_router_expired(struct timer_list *t) { struct net_bridge_mcast *brmctx = timer_container_of(brmctx, t, ip6_mc_router_timer); br_multicast_local_router_expired(brmctx, t); } #endif static void br_multicast_querier_expired(struct net_bridge_mcast *brmctx, struct bridge_mcast_own_query *query) { spin_lock(&brmctx->br->multicast_lock); if (!netif_running(brmctx->br->dev) || br_multicast_ctx_vlan_global_disabled(brmctx) || !br_opt_get(brmctx->br, BROPT_MULTICAST_ENABLED)) goto out; br_multicast_start_querier(brmctx, query); out: spin_unlock(&brmctx->br->multicast_lock); } static void br_ip4_multicast_querier_expired(struct timer_list *t) { struct net_bridge_mcast *brmctx = timer_container_of(brmctx, t, ip4_other_query.timer); br_multicast_querier_expired(brmctx, &brmctx->ip4_own_query); } #if IS_ENABLED(CONFIG_IPV6) static void br_ip6_multicast_querier_expired(struct timer_list *t) { struct net_bridge_mcast *brmctx = timer_container_of(brmctx, t, ip6_other_query.timer); br_multicast_querier_expired(brmctx, &brmctx->ip6_own_query); } #endif static void br_multicast_query_delay_expired(struct timer_list *t) { } static void br_multicast_select_own_querier(struct net_bridge_mcast *brmctx, struct br_ip *ip, struct sk_buff *skb) { if (ip->proto == htons(ETH_P_IP)) brmctx->ip4_querier.addr.src.ip4 = ip_hdr(skb)->saddr; #if IS_ENABLED(CONFIG_IPV6) else brmctx->ip6_querier.addr.src.ip6 = ipv6_hdr(skb)->saddr; #endif } static void __br_multicast_send_query(struct net_bridge_mcast *brmctx, struct net_bridge_mcast_port *pmctx, struct net_bridge_port_group *pg, struct br_ip *ip_dst, struct br_ip *group, bool with_srcs, u8 sflag, bool *need_rexmit) { bool over_lmqt = !!sflag; struct sk_buff *skb; u8 igmp_type; if (!br_multicast_ctx_should_use(brmctx, pmctx) || !br_multicast_ctx_matches_vlan_snooping(brmctx)) return; again_under_lmqt: skb = br_multicast_alloc_query(brmctx, pmctx, pg, ip_dst, group, with_srcs, over_lmqt, sflag, &igmp_type, need_rexmit); if (!skb) return; if (pmctx) { skb->dev = pmctx->port->dev; br_multicast_count(brmctx->br, pmctx->port, skb, igmp_type, BR_MCAST_DIR_TX); NF_HOOK(NFPROTO_BRIDGE, NF_BR_LOCAL_OUT, dev_net(pmctx->port->dev), NULL, skb, NULL, skb->dev, br_dev_queue_push_xmit); if (over_lmqt && with_srcs && sflag) { over_lmqt = false; goto again_under_lmqt; } } else { br_multicast_select_own_querier(brmctx, group, skb); br_multicast_count(brmctx->br, NULL, skb, igmp_type, BR_MCAST_DIR_RX); netif_rx(skb); } } static void br_multicast_read_querier(const struct bridge_mcast_querier *querier, struct bridge_mcast_querier *dest) { unsigned int seq; memset(dest, 0, sizeof(*dest)); do { seq = read_seqcount_begin(&querier->seq); dest->port_ifidx = querier->port_ifidx; memcpy(&dest->addr, &querier->addr, sizeof(struct br_ip)); } while (read_seqcount_retry(&querier->seq, seq)); } static void br_multicast_update_querier(struct net_bridge_mcast *brmctx, struct bridge_mcast_querier *querier, int ifindex, struct br_ip *saddr) { write_seqcount_begin(&querier->seq); querier->port_ifidx = ifindex; memcpy(&querier->addr, saddr, sizeof(*saddr)); write_seqcount_end(&querier->seq); } static void br_multicast_send_query(struct net_bridge_mcast *brmctx, struct net_bridge_mcast_port *pmctx, struct bridge_mcast_own_query *own_query) { struct bridge_mcast_other_query *other_query = NULL; struct bridge_mcast_querier *querier; struct br_ip br_group; unsigned long time; if (!br_multicast_ctx_should_use(brmctx, pmctx) || !br_opt_get(brmctx->br, BROPT_MULTICAST_ENABLED) || !brmctx->multicast_querier) return; memset(&br_group.dst, 0, sizeof(br_group.dst)); if (pmctx ? (own_query == &pmctx->ip4_own_query) : (own_query == &brmctx->ip4_own_query)) { querier = &brmctx->ip4_querier; other_query = &brmctx->ip4_other_query; br_group.proto = htons(ETH_P_IP); #if IS_ENABLED(CONFIG_IPV6) } else { querier = &brmctx->ip6_querier; other_query = &brmctx->ip6_other_query; br_group.proto = htons(ETH_P_IPV6); #endif } if (!other_query || timer_pending(&other_query->timer)) return; /* we're about to select ourselves as querier */ if (!pmctx && querier->port_ifidx) { struct br_ip zeroip = {}; br_multicast_update_querier(brmctx, querier, 0, &zeroip); } __br_multicast_send_query(brmctx, pmctx, NULL, NULL, &br_group, false, 0, NULL); time = jiffies; time += own_query->startup_sent < brmctx->multicast_startup_query_count ? brmctx->multicast_startup_query_interval : brmctx->multicast_query_interval; mod_timer(&own_query->timer, time); } static void br_multicast_port_query_expired(struct net_bridge_mcast_port *pmctx, struct bridge_mcast_own_query *query) { struct net_bridge *br = pmctx->port->br; struct net_bridge_mcast *brmctx; spin_lock(&br->multicast_lock); if (br_multicast_port_ctx_state_stopped(pmctx)) goto out; brmctx = br_multicast_port_ctx_get_global(pmctx); if (query->startup_sent < brmctx->multicast_startup_query_count) query->startup_sent++; br_multicast_send_query(brmctx, pmctx, query); out: spin_unlock(&br->multicast_lock); } static void br_ip4_multicast_port_query_expired(struct timer_list *t) { struct net_bridge_mcast_port *pmctx = timer_container_of(pmctx, t, ip4_own_query.timer); br_multicast_port_query_expired(pmctx, &pmctx->ip4_own_query); } #if IS_ENABLED(CONFIG_IPV6) static void br_ip6_multicast_port_query_expired(struct timer_list *t) { struct net_bridge_mcast_port *pmctx = timer_container_of(pmctx, t, ip6_own_query.timer); br_multicast_port_query_expired(pmctx, &pmctx->ip6_own_query); } #endif static void br_multicast_port_group_rexmit(struct timer_list *t) { struct net_bridge_port_group *pg = timer_container_of(pg, t, rexmit_timer); struct bridge_mcast_other_query *other_query = NULL; struct net_bridge *br = pg->key.port->br; struct net_bridge_mcast_port *pmctx; struct net_bridge_mcast *brmctx; bool need_rexmit = false; spin_lock(&br->multicast_lock); if (!netif_running(br->dev) || hlist_unhashed(&pg->mglist) || !br_opt_get(br, BROPT_MULTICAST_ENABLED)) goto out; pmctx = br_multicast_pg_to_port_ctx(pg); if (!pmctx) goto out; brmctx = br_multicast_port_ctx_get_global(pmctx); if (!brmctx->multicast_querier) goto out; if (pg->key.addr.proto == htons(ETH_P_IP)) other_query = &brmctx->ip4_other_query; #if IS_ENABLED(CONFIG_IPV6) else other_query = &brmctx->ip6_other_query; #endif if (!other_query || timer_pending(&other_query->timer)) goto out; if (pg->grp_query_rexmit_cnt) { pg->grp_query_rexmit_cnt--; __br_multicast_send_query(brmctx, pmctx, pg, &pg->key.addr, &pg->key.addr, false, 1, NULL); } __br_multicast_send_query(brmctx, pmctx, pg, &pg->key.addr, &pg->key.addr, true, 0, &need_rexmit); if (pg->grp_query_rexmit_cnt || need_rexmit) mod_timer(&pg->rexmit_timer, jiffies + brmctx->multicast_last_member_interval); out: spin_unlock(&br->multicast_lock); } static int br_mc_disabled_update(struct net_device *dev, bool value, struct netlink_ext_ack *extack) { struct switchdev_attr attr = { .orig_dev = dev, .id = SWITCHDEV_ATTR_ID_BRIDGE_MC_DISABLED, .flags = SWITCHDEV_F_DEFER, .u.mc_disabled = !value, }; return switchdev_port_attr_set(dev, &attr, extack); } void br_multicast_port_ctx_init(struct net_bridge_port *port, struct net_bridge_vlan *vlan, struct net_bridge_mcast_port *pmctx) { pmctx->port = port; pmctx->vlan = vlan; pmctx->multicast_router = MDB_RTR_TYPE_TEMP_QUERY; timer_setup(&pmctx->ip4_mc_router_timer, br_ip4_multicast_router_expired, 0); timer_setup(&pmctx->ip4_own_query.timer, br_ip4_multicast_port_query_expired, 0); #if IS_ENABLED(CONFIG_IPV6) timer_setup(&pmctx->ip6_mc_router_timer, br_ip6_multicast_router_expired, 0); timer_setup(&pmctx->ip6_own_query.timer, br_ip6_multicast_port_query_expired, 0); #endif } void br_multicast_port_ctx_deinit(struct net_bridge_mcast_port *pmctx) { struct net_bridge *br = pmctx->port->br; bool del = false; #if IS_ENABLED(CONFIG_IPV6) timer_delete_sync(&pmctx->ip6_mc_router_timer); #endif timer_delete_sync(&pmctx->ip4_mc_router_timer); spin_lock_bh(&br->multicast_lock); del |= br_ip6_multicast_rport_del(pmctx); del |= br_ip4_multicast_rport_del(pmctx); br_multicast_rport_del_notify(pmctx, del); spin_unlock_bh(&br->multicast_lock); } int br_multicast_add_port(struct net_bridge_port *port) { int err; port->multicast_eht_hosts_limit = BR_MCAST_DEFAULT_EHT_HOSTS_LIMIT; br_multicast_port_ctx_init(port, NULL, &port->multicast_ctx); err = br_mc_disabled_update(port->dev, br_opt_get(port->br, BROPT_MULTICAST_ENABLED), NULL); if (err && err != -EOPNOTSUPP) return err; port->mcast_stats = netdev_alloc_pcpu_stats(struct bridge_mcast_stats); if (!port->mcast_stats) return -ENOMEM; return 0; } void br_multicast_del_port(struct net_bridge_port *port) { struct net_bridge *br = port->br; struct net_bridge_port_group *pg; struct hlist_node *n; /* Take care of the remaining groups, only perm ones should be left */ spin_lock_bh(&br->multicast_lock); hlist_for_each_entry_safe(pg, n, &port->mglist, mglist) br_multicast_find_del_pg(br, pg); spin_unlock_bh(&br->multicast_lock); flush_work(&br->mcast_gc_work); br_multicast_port_ctx_deinit(&port->multicast_ctx); free_percpu(port->mcast_stats); } static void br_multicast_enable(struct bridge_mcast_own_query *query) { query->startup_sent = 0; if (timer_delete_sync_try(&query->timer) >= 0 || timer_delete(&query->timer)) mod_timer(&query->timer, jiffies); } static void __br_multicast_enable_port_ctx(struct net_bridge_mcast_port *pmctx) { struct net_bridge *br = pmctx->port->br; struct net_bridge_mcast *brmctx; brmctx = br_multicast_port_ctx_get_global(pmctx); if (!br_opt_get(br, BROPT_MULTICAST_ENABLED) || !netif_running(br->dev)) return; br_multicast_enable(&pmctx->ip4_own_query); #if IS_ENABLED(CONFIG_IPV6) br_multicast_enable(&pmctx->ip6_own_query); #endif if (pmctx->multicast_router == MDB_RTR_TYPE_PERM) { br_ip4_multicast_add_router(brmctx, pmctx); br_ip6_multicast_add_router(brmctx, pmctx); } if (br_multicast_port_ctx_is_vlan(pmctx)) { struct net_bridge_port_group *pg; u32 n = 0; /* The mcast_n_groups counter might be wrong. First, * BR_VLFLAG_MCAST_ENABLED is toggled before temporary entries * are flushed, thus mcast_n_groups after the toggle does not * reflect the true values. And second, permanent entries added * while BR_VLFLAG_MCAST_ENABLED was disabled, are not reflected * either. Thus we have to refresh the counter. */ hlist_for_each_entry(pg, &pmctx->port->mglist, mglist) { if (pg->key.addr.vid == pmctx->vlan->vid) n++; } WRITE_ONCE(pmctx->mdb_n_entries, n); } } static void br_multicast_enable_port_ctx(struct net_bridge_mcast_port *pmctx) { struct net_bridge *br = pmctx->port->br; spin_lock_bh(&br->multicast_lock); if (br_multicast_port_ctx_is_vlan(pmctx) && !(pmctx->vlan->priv_flags & BR_VLFLAG_MCAST_ENABLED)) { spin_unlock_bh(&br->multicast_lock); return; } __br_multicast_enable_port_ctx(pmctx); spin_unlock_bh(&br->multicast_lock); } static void __br_multicast_disable_port_ctx(struct net_bridge_mcast_port *pmctx) { struct net_bridge_port_group *pg; struct hlist_node *n; bool del = false; hlist_for_each_entry_safe(pg, n, &pmctx->port->mglist, mglist) if (!(pg->flags & MDB_PG_FLAGS_PERMANENT) && (!br_multicast_port_ctx_is_vlan(pmctx) || pg->key.addr.vid == pmctx->vlan->vid)) br_multicast_find_del_pg(pmctx->port->br, pg); del |= br_ip4_multicast_rport_del(pmctx); timer_delete(&pmctx->ip4_mc_router_timer); timer_delete(&pmctx->ip4_own_query.timer); del |= br_ip6_multicast_rport_del(pmctx); #if IS_ENABLED(CONFIG_IPV6) timer_delete(&pmctx->ip6_mc_router_timer); timer_delete(&pmctx->ip6_own_query.timer); #endif br_multicast_rport_del_notify(pmctx, del); } static void br_multicast_disable_port_ctx(struct net_bridge_mcast_port *pmctx) { struct net_bridge *br = pmctx->port->br; spin_lock_bh(&br->multicast_lock); if (br_multicast_port_ctx_is_vlan(pmctx) && !(pmctx->vlan->priv_flags & BR_VLFLAG_MCAST_ENABLED)) { spin_unlock_bh(&br->multicast_lock); return; } __br_multicast_disable_port_ctx(pmctx); spin_unlock_bh(&br->multicast_lock); } static void br_multicast_toggle_port(struct net_bridge_port *port, bool on) { #if IS_ENABLED(CONFIG_BRIDGE_VLAN_FILTERING) if (br_opt_get(port->br, BROPT_MCAST_VLAN_SNOOPING_ENABLED)) { struct net_bridge_vlan_group *vg; struct net_bridge_vlan *vlan; rcu_read_lock(); vg = nbp_vlan_group_rcu(port); if (!vg) { rcu_read_unlock(); return; } /* iterate each vlan, toggle vlan multicast context */ list_for_each_entry_rcu(vlan, &vg->vlan_list, vlist) { struct net_bridge_mcast_port *pmctx = &vlan->port_mcast_ctx; u8 state = br_vlan_get_state(vlan); /* enable vlan multicast context when state is * LEARNING or FORWARDING */ if (on && br_vlan_state_allowed(state, true)) br_multicast_enable_port_ctx(pmctx); else br_multicast_disable_port_ctx(pmctx); } rcu_read_unlock(); return; } #endif /* toggle port multicast context when vlan snooping is disabled */ if (on) br_multicast_enable_port_ctx(&port->multicast_ctx); else br_multicast_disable_port_ctx(&port->multicast_ctx); } void br_multicast_enable_port(struct net_bridge_port *port) { br_multicast_toggle_port(port, true); } void br_multicast_disable_port(struct net_bridge_port *port) { br_multicast_toggle_port(port, false); } static int __grp_src_delete_marked(struct net_bridge_port_group *pg) { struct net_bridge_group_src *ent; struct hlist_node *tmp; int deleted = 0; hlist_for_each_entry_safe(ent, tmp, &pg->src_list, node) if (ent->flags & BR_SGRP_F_DELETE) { br_multicast_del_group_src(ent, false); deleted++; } return deleted; } static void __grp_src_mod_timer(struct net_bridge_group_src *src, unsigned long expires) { mod_timer(&src->timer, expires); br_multicast_fwd_src_handle(src); } static void __grp_src_query_marked_and_rexmit(struct net_bridge_mcast *brmctx, struct net_bridge_mcast_port *pmctx, struct net_bridge_port_group *pg) { struct bridge_mcast_other_query *other_query = NULL; u32 lmqc = brmctx->multicast_last_member_count; unsigned long lmqt, lmi, now = jiffies; struct net_bridge_group_src *ent; if (!netif_running(brmctx->br->dev) || !br_opt_get(brmctx->br, BROPT_MULTICAST_ENABLED)) return; if (pg->key.addr.proto == htons(ETH_P_IP)) other_query = &brmctx->ip4_other_query; #if IS_ENABLED(CONFIG_IPV6) else other_query = &brmctx->ip6_other_query; #endif lmqt = now + br_multicast_lmqt(brmctx); hlist_for_each_entry(ent, &pg->src_list, node) { if (ent->flags & BR_SGRP_F_SEND) { ent->flags &= ~BR_SGRP_F_SEND; if (ent->timer.expires > lmqt) { if (brmctx->multicast_querier && other_query && !timer_pending(&other_query->timer)) ent->src_query_rexmit_cnt = lmqc; __grp_src_mod_timer(ent, lmqt); } } } if (!brmctx->multicast_querier || !other_query || timer_pending(&other_query->timer)) return; __br_multicast_send_query(brmctx, pmctx, pg, &pg->key.addr, &pg->key.addr, true, 1, NULL); lmi = now + brmctx->multicast_last_member_interval; if (!timer_pending(&pg->rexmit_timer) || time_after(pg->rexmit_timer.expires, lmi)) mod_timer(&pg->rexmit_timer, lmi); } static void __grp_send_query_and_rexmit(struct net_bridge_mcast *brmctx, struct net_bridge_mcast_port *pmctx, struct net_bridge_port_group *pg) { struct bridge_mcast_other_query *other_query = NULL; unsigned long now = jiffies, lmi; if (!netif_running(brmctx->br->dev) || !br_opt_get(brmctx->br, BROPT_MULTICAST_ENABLED)) return; if (pg->key.addr.proto == htons(ETH_P_IP)) other_query = &brmctx->ip4_other_query; #if IS_ENABLED(CONFIG_IPV6) else other_query = &brmctx->ip6_other_query; #endif if (brmctx->multicast_querier && other_query && !timer_pending(&other_query->timer)) { lmi = now + brmctx->multicast_last_member_interval; pg->grp_query_rexmit_cnt = brmctx->multicast_last_member_count - 1; __br_multicast_send_query(brmctx, pmctx, pg, &pg->key.addr, &pg->key.addr, false, 0, NULL); if (!timer_pending(&pg->rexmit_timer) || time_after(pg->rexmit_timer.expires, lmi)) mod_timer(&pg->rexmit_timer, lmi); } if (pg->filter_mode == MCAST_EXCLUDE && (!timer_pending(&pg->timer) || time_after(pg->timer.expires, now + br_multicast_lmqt(brmctx)))) mod_timer(&pg->timer, now + br_multicast_lmqt(brmctx)); } /* State Msg type New state Actions * INCLUDE (A) IS_IN (B) INCLUDE (A+B) (B)=GMI * INCLUDE (A) ALLOW (B) INCLUDE (A+B) (B)=GMI * EXCLUDE (X,Y) ALLOW (A) EXCLUDE (X+A,Y-A) (A)=GMI */ static bool br_multicast_isinc_allow(const struct net_bridge_mcast *brmctx, struct net_bridge_port_group *pg, void *h_addr, void *srcs, u32 nsrcs, size_t addr_size, int grec_type) { struct net_bridge_group_src *ent; unsigned long now = jiffies; bool changed = false; struct br_ip src_ip; u32 src_idx; memset(&src_ip, 0, sizeof(src_ip)); src_ip.proto = pg->key.addr.proto; for (src_idx = 0; src_idx < nsrcs; src_idx++) { memcpy(&src_ip.src, srcs + (src_idx * addr_size), addr_size); ent = br_multicast_find_group_src(pg, &src_ip); if (!ent) { ent = br_multicast_new_group_src(pg, &src_ip); if (ent) changed = true; } if (ent) __grp_src_mod_timer(ent, now + br_multicast_gmi(brmctx)); } if (br_multicast_eht_handle(brmctx, pg, h_addr, srcs, nsrcs, addr_size, grec_type)) changed = true; return changed; } /* State Msg type New state Actions * INCLUDE (A) IS_EX (B) EXCLUDE (A*B,B-A) (B-A)=0 * Delete (A-B) * Group Timer=GMI */ static void __grp_src_isexc_incl(const struct net_bridge_mcast *brmctx, struct net_bridge_port_group *pg, void *h_addr, void *srcs, u32 nsrcs, size_t addr_size, int grec_type) { struct net_bridge_group_src *ent; struct br_ip src_ip; u32 src_idx; hlist_for_each_entry(ent, &pg->src_list, node) ent->flags |= BR_SGRP_F_DELETE; memset(&src_ip, 0, sizeof(src_ip)); src_ip.proto = pg->key.addr.proto; for (src_idx = 0; src_idx < nsrcs; src_idx++) { memcpy(&src_ip.src, srcs + (src_idx * addr_size), addr_size); ent = br_multicast_find_group_src(pg, &src_ip); if (ent) ent->flags &= ~BR_SGRP_F_DELETE; else ent = br_multicast_new_group_src(pg, &src_ip); if (ent) br_multicast_fwd_src_handle(ent); } br_multicast_eht_handle(brmctx, pg, h_addr, srcs, nsrcs, addr_size, grec_type); __grp_src_delete_marked(pg); } /* State Msg type New state Actions * EXCLUDE (X,Y) IS_EX (A) EXCLUDE (A-Y,Y*A) (A-X-Y)=GMI * Delete (X-A) * Delete (Y-A) * Group Timer=GMI */ static bool __grp_src_isexc_excl(const struct net_bridge_mcast *brmctx, struct net_bridge_port_group *pg, void *h_addr, void *srcs, u32 nsrcs, size_t addr_size, int grec_type) { struct net_bridge_group_src *ent; unsigned long now = jiffies; bool changed = false; struct br_ip src_ip; u32 src_idx; hlist_for_each_entry(ent, &pg->src_list, node) ent->flags |= BR_SGRP_F_DELETE; memset(&src_ip, 0, sizeof(src_ip)); src_ip.proto = pg->key.addr.proto; for (src_idx = 0; src_idx < nsrcs; src_idx++) { memcpy(&src_ip.src, srcs + (src_idx * addr_size), addr_size); ent = br_multicast_find_group_src(pg, &src_ip); if (ent) { ent->flags &= ~BR_SGRP_F_DELETE; } else { ent = br_multicast_new_group_src(pg, &src_ip); if (ent) { __grp_src_mod_timer(ent, now + br_multicast_gmi(brmctx)); changed = true; } } } if (br_multicast_eht_handle(brmctx, pg, h_addr, srcs, nsrcs, addr_size, grec_type)) changed = true; if (__grp_src_delete_marked(pg)) changed = true; return changed; } static bool br_multicast_isexc(const struct net_bridge_mcast *brmctx, struct net_bridge_port_group *pg, void *h_addr, void *srcs, u32 nsrcs, size_t addr_size, int grec_type) { bool changed = false; switch (pg->filter_mode) { case MCAST_INCLUDE: __grp_src_isexc_incl(brmctx, pg, h_addr, srcs, nsrcs, addr_size, grec_type); br_multicast_star_g_handle_mode(pg, MCAST_EXCLUDE); changed = true; break; case MCAST_EXCLUDE: changed = __grp_src_isexc_excl(brmctx, pg, h_addr, srcs, nsrcs, addr_size, grec_type); break; } pg->filter_mode = MCAST_EXCLUDE; mod_timer(&pg->timer, jiffies + br_multicast_gmi(brmctx)); return changed; } /* State Msg type New state Actions * INCLUDE (A) TO_IN (B) INCLUDE (A+B) (B)=GMI * Send Q(G,A-B) */ static bool __grp_src_toin_incl(struct net_bridge_mcast *brmctx, struct net_bridge_mcast_port *pmctx, struct net_bridge_port_group *pg, void *h_addr, void *srcs, u32 nsrcs, size_t addr_size, int grec_type) { u32 src_idx, to_send = pg->src_ents; struct net_bridge_group_src *ent; unsigned long now = jiffies; bool changed = false; struct br_ip src_ip; hlist_for_each_entry(ent, &pg->src_list, node) ent->flags |= BR_SGRP_F_SEND; memset(&src_ip, 0, sizeof(src_ip)); src_ip.proto = pg->key.addr.proto; for (src_idx = 0; src_idx < nsrcs; src_idx++) { memcpy(&src_ip.src, srcs + (src_idx * addr_size), addr_size); ent = br_multicast_find_group_src(pg, &src_ip); if (ent) { ent->flags &= ~BR_SGRP_F_SEND; to_send--; } else { ent = br_multicast_new_group_src(pg, &src_ip); if (ent) changed = true; } if (ent) __grp_src_mod_timer(ent, now + br_multicast_gmi(brmctx)); } if (br_multicast_eht_handle(brmctx, pg, h_addr, srcs, nsrcs, addr_size, grec_type)) changed = true; if (to_send) __grp_src_query_marked_and_rexmit(brmctx, pmctx, pg); return changed; } /* State Msg type New state Actions * EXCLUDE (X,Y) TO_IN (A) EXCLUDE (X+A,Y-A) (A)=GMI * Send Q(G,X-A) * Send Q(G) */ static bool __grp_src_toin_excl(struct net_bridge_mcast *brmctx, struct net_bridge_mcast_port *pmctx, struct net_bridge_port_group *pg, void *h_addr, void *srcs, u32 nsrcs, size_t addr_size, int grec_type) { u32 src_idx, to_send = pg->src_ents; struct net_bridge_group_src *ent; unsigned long now = jiffies; bool changed = false; struct br_ip src_ip; hlist_for_each_entry(ent, &pg->src_list, node) if (timer_pending(&ent->timer)) ent->flags |= BR_SGRP_F_SEND; memset(&src_ip, 0, sizeof(src_ip)); src_ip.proto = pg->key.addr.proto; for (src_idx = 0; src_idx < nsrcs; src_idx++) { memcpy(&src_ip.src, srcs + (src_idx * addr_size), addr_size); ent = br_multicast_find_group_src(pg, &src_ip); if (ent) { if (timer_pending(&ent->timer)) { ent->flags &= ~BR_SGRP_F_SEND; to_send--; } } else { ent = br_multicast_new_group_src(pg, &src_ip); if (ent) changed = true; } if (ent) __grp_src_mod_timer(ent, now + br_multicast_gmi(brmctx)); } if (br_multicast_eht_handle(brmctx, pg, h_addr, srcs, nsrcs, addr_size, grec_type)) changed = true; if (to_send) __grp_src_query_marked_and_rexmit(brmctx, pmctx, pg); __grp_send_query_and_rexmit(brmctx, pmctx, pg); return changed; } static bool br_multicast_toin(struct net_bridge_mcast *brmctx, struct net_bridge_mcast_port *pmctx, struct net_bridge_port_group *pg, void *h_addr, void *srcs, u32 nsrcs, size_t addr_size, int grec_type) { bool changed = false; switch (pg->filter_mode) { case MCAST_INCLUDE: changed = __grp_src_toin_incl(brmctx, pmctx, pg, h_addr, srcs, nsrcs, addr_size, grec_type); break; case MCAST_EXCLUDE: changed = __grp_src_toin_excl(brmctx, pmctx, pg, h_addr, srcs, nsrcs, addr_size, grec_type); break; } if (br_multicast_eht_should_del_pg(pg)) { pg->flags |= MDB_PG_FLAGS_FAST_LEAVE; br_multicast_find_del_pg(pg->key.port->br, pg); /* a notification has already been sent and we shouldn't * access pg after the delete so we have to return false */ changed = false; } return changed; } /* State Msg type New state Actions * INCLUDE (A) TO_EX (B) EXCLUDE (A*B,B-A) (B-A)=0 * Delete (A-B) * Send Q(G,A*B) * Group Timer=GMI */ static void __grp_src_toex_incl(struct net_bridge_mcast *brmctx, struct net_bridge_mcast_port *pmctx, struct net_bridge_port_group *pg, void *h_addr, void *srcs, u32 nsrcs, size_t addr_size, int grec_type) { struct net_bridge_group_src *ent; u32 src_idx, to_send = 0; struct br_ip src_ip; hlist_for_each_entry(ent, &pg->src_list, node) ent->flags = (ent->flags & ~BR_SGRP_F_SEND) | BR_SGRP_F_DELETE; memset(&src_ip, 0, sizeof(src_ip)); src_ip.proto = pg->key.addr.proto; for (src_idx = 0; src_idx < nsrcs; src_idx++) { memcpy(&src_ip.src, srcs + (src_idx * addr_size), addr_size); ent = br_multicast_find_group_src(pg, &src_ip); if (ent) { ent->flags = (ent->flags & ~BR_SGRP_F_DELETE) | BR_SGRP_F_SEND; to_send++; } else { ent = br_multicast_new_group_src(pg, &src_ip); } if (ent) br_multicast_fwd_src_handle(ent); } br_multicast_eht_handle(brmctx, pg, h_addr, srcs, nsrcs, addr_size, grec_type); __grp_src_delete_marked(pg); if (to_send) __grp_src_query_marked_and_rexmit(brmctx, pmctx, pg); } /* State Msg type New state Actions * EXCLUDE (X,Y) TO_EX (A) EXCLUDE (A-Y,Y*A) (A-X-Y)=Group Timer * Delete (X-A) * Delete (Y-A) * Send Q(G,A-Y) * Group Timer=GMI */ static bool __grp_src_toex_excl(struct net_bridge_mcast *brmctx, struct net_bridge_mcast_port *pmctx, struct net_bridge_port_group *pg, void *h_addr, void *srcs, u32 nsrcs, size_t addr_size, int grec_type) { struct net_bridge_group_src *ent; u32 src_idx, to_send = 0; bool changed = false; struct br_ip src_ip; hlist_for_each_entry(ent, &pg->src_list, node) ent->flags = (ent->flags & ~BR_SGRP_F_SEND) | BR_SGRP_F_DELETE; memset(&src_ip, 0, sizeof(src_ip)); src_ip.proto = pg->key.addr.proto; for (src_idx = 0; src_idx < nsrcs; src_idx++) { memcpy(&src_ip.src, srcs + (src_idx * addr_size), addr_size); ent = br_multicast_find_group_src(pg, &src_ip); if (ent) { ent->flags &= ~BR_SGRP_F_DELETE; } else { ent = br_multicast_new_group_src(pg, &src_ip); if (ent) { __grp_src_mod_timer(ent, pg->timer.expires); changed = true; } } if (ent && timer_pending(&ent->timer)) { ent->flags |= BR_SGRP_F_SEND; to_send++; } } if (br_multicast_eht_handle(brmctx, pg, h_addr, srcs, nsrcs, addr_size, grec_type)) changed = true; if (__grp_src_delete_marked(pg)) changed = true; if (to_send) __grp_src_query_marked_and_rexmit(brmctx, pmctx, pg); return changed; } static bool br_multicast_toex(struct net_bridge_mcast *brmctx, struct net_bridge_mcast_port *pmctx, struct net_bridge_port_group *pg, void *h_addr, void *srcs, u32 nsrcs, size_t addr_size, int grec_type) { bool changed = false; switch (pg->filter_mode) { case MCAST_INCLUDE: __grp_src_toex_incl(brmctx, pmctx, pg, h_addr, srcs, nsrcs, addr_size, grec_type); br_multicast_star_g_handle_mode(pg, MCAST_EXCLUDE); changed = true; break; case MCAST_EXCLUDE: changed = __grp_src_toex_excl(brmctx, pmctx, pg, h_addr, srcs, nsrcs, addr_size, grec_type); break; } pg->filter_mode = MCAST_EXCLUDE; mod_timer(&pg->timer, jiffies + br_multicast_gmi(brmctx)); return changed; } /* State Msg type New state Actions * INCLUDE (A) BLOCK (B) INCLUDE (A) Send Q(G,A*B) */ static bool __grp_src_block_incl(struct net_bridge_mcast *brmctx, struct net_bridge_mcast_port *pmctx, struct net_bridge_port_group *pg, void *h_addr, void *srcs, u32 nsrcs, size_t addr_size, int grec_type) { struct net_bridge_group_src *ent; u32 src_idx, to_send = 0; bool changed = false; struct br_ip src_ip; hlist_for_each_entry(ent, &pg->src_list, node) ent->flags &= ~BR_SGRP_F_SEND; memset(&src_ip, 0, sizeof(src_ip)); src_ip.proto = pg->key.addr.proto; for (src_idx = 0; src_idx < nsrcs; src_idx++) { memcpy(&src_ip.src, srcs + (src_idx * addr_size), addr_size); ent = br_multicast_find_group_src(pg, &src_ip); if (ent) { ent->flags |= BR_SGRP_F_SEND; to_send++; } } if (br_multicast_eht_handle(brmctx, pg, h_addr, srcs, nsrcs, addr_size, grec_type)) changed = true; if (to_send) __grp_src_query_marked_and_rexmit(brmctx, pmctx, pg); return changed; } /* State Msg type New state Actions * EXCLUDE (X,Y) BLOCK (A) EXCLUDE (X+(A-Y),Y) (A-X-Y)=Group Timer * Send Q(G,A-Y) */ static bool __grp_src_block_excl(struct net_bridge_mcast *brmctx, struct net_bridge_mcast_port *pmctx, struct net_bridge_port_group *pg, void *h_addr, void *srcs, u32 nsrcs, size_t addr_size, int grec_type) { struct net_bridge_group_src *ent; u32 src_idx, to_send = 0; bool changed = false; struct br_ip src_ip; hlist_for_each_entry(ent, &pg->src_list, node) ent->flags &= ~BR_SGRP_F_SEND; memset(&src_ip, 0, sizeof(src_ip)); src_ip.proto = pg->key.addr.proto; for (src_idx = 0; src_idx < nsrcs; src_idx++) { memcpy(&src_ip.src, srcs + (src_idx * addr_size), addr_size); ent = br_multicast_find_group_src(pg, &src_ip); if (!ent) { ent = br_multicast_new_group_src(pg, &src_ip); if (ent) { __grp_src_mod_timer(ent, pg->timer.expires); changed = true; } } if (ent && timer_pending(&ent->timer)) { ent->flags |= BR_SGRP_F_SEND; to_send++; } } if (br_multicast_eht_handle(brmctx, pg, h_addr, srcs, nsrcs, addr_size, grec_type)) changed = true; if (to_send) __grp_src_query_marked_and_rexmit(brmctx, pmctx, pg); return changed; } static bool br_multicast_block(struct net_bridge_mcast *brmctx, struct net_bridge_mcast_port *pmctx, struct net_bridge_port_group *pg, void *h_addr, void *srcs, u32 nsrcs, size_t addr_size, int grec_type) { bool changed = false; switch (pg->filter_mode) { case MCAST_INCLUDE: changed = __grp_src_block_incl(brmctx, pmctx, pg, h_addr, srcs, nsrcs, addr_size, grec_type); break; case MCAST_EXCLUDE: changed = __grp_src_block_excl(brmctx, pmctx, pg, h_addr, srcs, nsrcs, addr_size, grec_type); break; } if ((pg->filter_mode == MCAST_INCLUDE && hlist_empty(&pg->src_list)) || br_multicast_eht_should_del_pg(pg)) { if (br_multicast_eht_should_del_pg(pg)) pg->flags |= MDB_PG_FLAGS_FAST_LEAVE; br_multicast_find_del_pg(pg->key.port->br, pg); /* a notification has already been sent and we shouldn't * access pg after the delete so we have to return false */ changed = false; } return changed; } static struct net_bridge_port_group * br_multicast_find_port(struct net_bridge_mdb_entry *mp, struct net_bridge_port *p, const unsigned char *src) { struct net_bridge *br __maybe_unused = mp->br; struct net_bridge_port_group *pg; for (pg = mlock_dereference(mp->ports, br); pg; pg = mlock_dereference(pg->next, br)) if (br_port_group_equal(pg, p, src)) return pg; return NULL; } static int br_ip4_multicast_igmp3_report(struct net_bridge_mcast *brmctx, struct net_bridge_mcast_port *pmctx, struct sk_buff *skb, u16 vid) { bool igmpv2 = brmctx->multicast_igmp_version == 2; struct net_bridge_mdb_entry *mdst; struct net_bridge_port_group *pg; const unsigned char *src; struct igmpv3_report *ih; struct igmpv3_grec *grec; int i, len, num, type; __be32 group, *h_addr; bool changed = false; int err = 0; u16 nsrcs; ih = igmpv3_report_hdr(skb); num = ntohs(ih->ngrec); len = skb_transport_offset(skb) + sizeof(*ih); for (i = 0; i < num; i++) { len += sizeof(*grec); if (!ip_mc_may_pull(skb, len)) return -EINVAL; grec = (void *)(skb->data + len - sizeof(*grec)); group = grec->grec_mca; type = grec->grec_type; nsrcs = ntohs(grec->grec_nsrcs); len += nsrcs * 4; if (!ip_mc_may_pull(skb, len)) return -EINVAL; switch (type) { case IGMPV3_MODE_IS_INCLUDE: case IGMPV3_MODE_IS_EXCLUDE: case IGMPV3_CHANGE_TO_INCLUDE: case IGMPV3_CHANGE_TO_EXCLUDE: case IGMPV3_ALLOW_NEW_SOURCES: case IGMPV3_BLOCK_OLD_SOURCES: break; default: continue; } src = eth_hdr(skb)->h_source; if (nsrcs == 0 && (type == IGMPV3_CHANGE_TO_INCLUDE || type == IGMPV3_MODE_IS_INCLUDE)) { if (!pmctx || igmpv2) { br_ip4_multicast_leave_group(brmctx, pmctx, group, vid, src); continue; } } else { err = br_ip4_multicast_add_group(brmctx, pmctx, group, vid, src, igmpv2); if (err) break; } if (!pmctx || igmpv2) continue; spin_lock(&brmctx->br->multicast_lock); if (!br_multicast_ctx_should_use(brmctx, pmctx)) goto unlock_continue; mdst = br_mdb_ip4_get(brmctx->br, group, vid); if (!mdst) goto unlock_continue; pg = br_multicast_find_port(mdst, pmctx->port, src); if (!pg || (pg->flags & MDB_PG_FLAGS_PERMANENT)) goto unlock_continue; /* reload grec and host addr */ grec = (void *)(skb->data + len - sizeof(*grec) - (nsrcs * 4)); h_addr = &ip_hdr(skb)->saddr; switch (type) { case IGMPV3_ALLOW_NEW_SOURCES: changed = br_multicast_isinc_allow(brmctx, pg, h_addr, grec->grec_src, nsrcs, sizeof(__be32), type); break; case IGMPV3_MODE_IS_INCLUDE: changed = br_multicast_isinc_allow(brmctx, pg, h_addr, grec->grec_src, nsrcs, sizeof(__be32), type); break; case IGMPV3_MODE_IS_EXCLUDE: changed = br_multicast_isexc(brmctx, pg, h_addr, grec->grec_src, nsrcs, sizeof(__be32), type); break; case IGMPV3_CHANGE_TO_INCLUDE: changed = br_multicast_toin(brmctx, pmctx, pg, h_addr, grec->grec_src, nsrcs, sizeof(__be32), type); break; case IGMPV3_CHANGE_TO_EXCLUDE: changed = br_multicast_toex(brmctx, pmctx, pg, h_addr, grec->grec_src, nsrcs, sizeof(__be32), type); break; case IGMPV3_BLOCK_OLD_SOURCES: changed = br_multicast_block(brmctx, pmctx, pg, h_addr, grec->grec_src, nsrcs, sizeof(__be32), type); break; } if (changed) br_mdb_notify(brmctx->br->dev, mdst, pg, RTM_NEWMDB); unlock_continue: spin_unlock(&brmctx->br->multicast_lock); } return err; } #if IS_ENABLED(CONFIG_IPV6) static int br_ip6_multicast_mld2_report(struct net_bridge_mcast *brmctx, struct net_bridge_mcast_port *pmctx, struct sk_buff *skb, u16 vid) { bool mldv1 = brmctx->multicast_mld_version == 1; struct net_bridge_mdb_entry *mdst; struct net_bridge_port_group *pg; unsigned int nsrcs_offset; struct mld2_report *mld2r; const unsigned char *src; struct in6_addr *h_addr; struct mld2_grec *grec; unsigned int grec_len; bool changed = false; int i, len, num; int err = 0; if (!ipv6_mc_may_pull(skb, sizeof(*mld2r))) return -EINVAL; mld2r = (struct mld2_report *)icmp6_hdr(skb); num = ntohs(mld2r->mld2r_ngrec); len = skb_transport_offset(skb) + sizeof(*mld2r); for (i = 0; i < num; i++) { __be16 *_nsrcs, __nsrcs; u16 nsrcs; nsrcs_offset = len + offsetof(struct mld2_grec, grec_nsrcs); if (skb_transport_offset(skb) + ipv6_transport_len(skb) < nsrcs_offset + sizeof(__nsrcs)) return -EINVAL; _nsrcs = skb_header_pointer(skb, nsrcs_offset, sizeof(__nsrcs), &__nsrcs); if (!_nsrcs) return -EINVAL; nsrcs = ntohs(*_nsrcs); grec_len = struct_size(grec, grec_src, nsrcs); if (!ipv6_mc_may_pull(skb, len + grec_len)) return -EINVAL; grec = (struct mld2_grec *)(skb->data + len); len += grec_len; switch (grec->grec_type) { case MLD2_MODE_IS_INCLUDE: case MLD2_MODE_IS_EXCLUDE: case MLD2_CHANGE_TO_INCLUDE: case MLD2_CHANGE_TO_EXCLUDE: case MLD2_ALLOW_NEW_SOURCES: case MLD2_BLOCK_OLD_SOURCES: break; default: continue; } src = eth_hdr(skb)->h_source; if ((grec->grec_type == MLD2_CHANGE_TO_INCLUDE || grec->grec_type == MLD2_MODE_IS_INCLUDE) && nsrcs == 0) { if (!pmctx || mldv1) { br_ip6_multicast_leave_group(brmctx, pmctx, &grec->grec_mca, vid, src); continue; } } else { err = br_ip6_multicast_add_group(brmctx, pmctx, &grec->grec_mca, vid, src, mldv1); if (err) break; } if (!pmctx || mldv1) continue; spin_lock(&brmctx->br->multicast_lock); if (!br_multicast_ctx_should_use(brmctx, pmctx)) goto unlock_continue; mdst = br_mdb_ip6_get(brmctx->br, &grec->grec_mca, vid); if (!mdst) goto unlock_continue; pg = br_multicast_find_port(mdst, pmctx->port, src); if (!pg || (pg->flags & MDB_PG_FLAGS_PERMANENT)) goto unlock_continue; h_addr = &ipv6_hdr(skb)->saddr; switch (grec->grec_type) { case MLD2_ALLOW_NEW_SOURCES: changed = br_multicast_isinc_allow(brmctx, pg, h_addr, grec->grec_src, nsrcs, sizeof(struct in6_addr), grec->grec_type); break; case MLD2_MODE_IS_INCLUDE: changed = br_multicast_isinc_allow(brmctx, pg, h_addr, grec->grec_src, nsrcs, sizeof(struct in6_addr), grec->grec_type); break; case MLD2_MODE_IS_EXCLUDE: changed = br_multicast_isexc(brmctx, pg, h_addr, grec->grec_src, nsrcs, sizeof(struct in6_addr), grec->grec_type); break; case MLD2_CHANGE_TO_INCLUDE: changed = br_multicast_toin(brmctx, pmctx, pg, h_addr, grec->grec_src, nsrcs, sizeof(struct in6_addr), grec->grec_type); break; case MLD2_CHANGE_TO_EXCLUDE: changed = br_multicast_toex(brmctx, pmctx, pg, h_addr, grec->grec_src, nsrcs, sizeof(struct in6_addr), grec->grec_type); break; case MLD2_BLOCK_OLD_SOURCES: changed = br_multicast_block(brmctx, pmctx, pg, h_addr, grec->grec_src, nsrcs, sizeof(struct in6_addr), grec->grec_type); break; } if (changed) br_mdb_notify(brmctx->br->dev, mdst, pg, RTM_NEWMDB); unlock_continue: spin_unlock(&brmctx->br->multicast_lock); } return err; } #endif static bool br_multicast_select_querier(struct net_bridge_mcast *brmctx, struct net_bridge_mcast_port *pmctx, struct br_ip *saddr) { int port_ifidx = pmctx ? pmctx->port->dev->ifindex : 0; struct timer_list *own_timer, *other_timer; struct bridge_mcast_querier *querier; switch (saddr->proto) { case htons(ETH_P_IP): querier = &brmctx->ip4_querier; own_timer = &brmctx->ip4_own_query.timer; other_timer = &brmctx->ip4_other_query.timer; if (!querier->addr.src.ip4 || ntohl(saddr->src.ip4) <= ntohl(querier->addr.src.ip4)) goto update; break; #if IS_ENABLED(CONFIG_IPV6) case htons(ETH_P_IPV6): querier = &brmctx->ip6_querier; own_timer = &brmctx->ip6_own_query.timer; other_timer = &brmctx->ip6_other_query.timer; if (ipv6_addr_cmp(&saddr->src.ip6, &querier->addr.src.ip6) <= 0) goto update; break; #endif default: return false; } if (!timer_pending(own_timer) && !timer_pending(other_timer)) goto update; return false; update: br_multicast_update_querier(brmctx, querier, port_ifidx, saddr); return true; } static struct net_bridge_port * __br_multicast_get_querier_port(struct net_bridge *br, const struct bridge_mcast_querier *querier) { int port_ifidx = READ_ONCE(querier->port_ifidx); struct net_bridge_port *p; struct net_device *dev; if (port_ifidx == 0) return NULL; dev = dev_get_by_index_rcu(dev_net(br->dev), port_ifidx); if (!dev) return NULL; p = br_port_get_rtnl_rcu(dev); if (!p || p->br != br) return NULL; return p; } size_t br_multicast_querier_state_size(void) { return nla_total_size(0) + /* nest attribute */ nla_total_size(sizeof(__be32)) + /* BRIDGE_QUERIER_IP_ADDRESS */ nla_total_size(sizeof(int)) + /* BRIDGE_QUERIER_IP_PORT */ nla_total_size_64bit(sizeof(u64)) + /* BRIDGE_QUERIER_IP_OTHER_TIMER */ #if IS_ENABLED(CONFIG_IPV6) nla_total_size(sizeof(struct in6_addr)) + /* BRIDGE_QUERIER_IPV6_ADDRESS */ nla_total_size(sizeof(int)) + /* BRIDGE_QUERIER_IPV6_PORT */ nla_total_size_64bit(sizeof(u64)) + /* BRIDGE_QUERIER_IPV6_OTHER_TIMER */ #endif 0; } /* protected by rtnl or rcu */ int br_multicast_dump_querier_state(struct sk_buff *skb, const struct net_bridge_mcast *brmctx, int nest_attr) { struct bridge_mcast_querier querier = {}; struct net_bridge_port *p; struct nlattr *nest; if (!br_opt_get(brmctx->br, BROPT_MULTICAST_ENABLED) || br_multicast_ctx_vlan_global_disabled(brmctx)) return 0; nest = nla_nest_start(skb, nest_attr); if (!nest) return -EMSGSIZE; rcu_read_lock(); if (!brmctx->multicast_querier && !timer_pending(&brmctx->ip4_other_query.timer)) goto out_v6; br_multicast_read_querier(&brmctx->ip4_querier, &querier); if (nla_put_in_addr(skb, BRIDGE_QUERIER_IP_ADDRESS, querier.addr.src.ip4)) { rcu_read_unlock(); goto out_err; } p = __br_multicast_get_querier_port(brmctx->br, &querier); if (timer_pending(&brmctx->ip4_other_query.timer) && (nla_put_u64_64bit(skb, BRIDGE_QUERIER_IP_OTHER_TIMER, br_timer_value(&brmctx->ip4_other_query.timer), BRIDGE_QUERIER_PAD) || (p && nla_put_u32(skb, BRIDGE_QUERIER_IP_PORT, p->dev->ifindex)))) { rcu_read_unlock(); goto out_err; } out_v6: #if IS_ENABLED(CONFIG_IPV6) if (!brmctx->multicast_querier && !timer_pending(&brmctx->ip6_other_query.timer)) goto out; br_multicast_read_querier(&brmctx->ip6_querier, &querier); if (nla_put_in6_addr(skb, BRIDGE_QUERIER_IPV6_ADDRESS, &querier.addr.src.ip6)) { rcu_read_unlock(); goto out_err; } p = __br_multicast_get_querier_port(brmctx->br, &querier); if (timer_pending(&brmctx->ip6_other_query.timer) && (nla_put_u64_64bit(skb, BRIDGE_QUERIER_IPV6_OTHER_TIMER, br_timer_value(&brmctx->ip6_other_query.timer), BRIDGE_QUERIER_PAD) || (p && nla_put_u32(skb, BRIDGE_QUERIER_IPV6_PORT, p->dev->ifindex)))) { rcu_read_unlock(); goto out_err; } out: #endif rcu_read_unlock(); nla_nest_end(skb, nest); if (!nla_len(nest)) nla_nest_cancel(skb, nest); return 0; out_err: nla_nest_cancel(skb, nest); return -EMSGSIZE; } static void br_multicast_update_query_timer(struct net_bridge_mcast *brmctx, struct bridge_mcast_other_query *query, unsigned long max_delay) { if (!timer_pending(&query->timer)) mod_timer(&query->delay_timer, jiffies + max_delay); mod_timer(&query->timer, jiffies + brmctx->multicast_querier_interval); } static void br_port_mc_router_state_change(struct net_bridge_port *p, bool is_mc_router) { struct switchdev_attr attr = { .orig_dev = p->dev, .id = SWITCHDEV_ATTR_ID_PORT_MROUTER, .flags = SWITCHDEV_F_DEFER, .u.mrouter = is_mc_router, }; switchdev_port_attr_set(p->dev, &attr, NULL); } static struct net_bridge_port * br_multicast_rport_from_node(struct net_bridge_mcast *brmctx, struct hlist_head *mc_router_list, struct hlist_node *rlist) { struct net_bridge_mcast_port *pmctx; #if IS_ENABLED(CONFIG_IPV6) if (mc_router_list == &brmctx->ip6_mc_router_list) pmctx = hlist_entry(rlist, struct net_bridge_mcast_port, ip6_rlist); else #endif pmctx = hlist_entry(rlist, struct net_bridge_mcast_port, ip4_rlist); return pmctx->port; } static struct hlist_node * br_multicast_get_rport_slot(struct net_bridge_mcast *brmctx, struct net_bridge_port *port, struct hlist_head *mc_router_list) { struct hlist_node *slot = NULL; struct net_bridge_port *p; struct hlist_node *rlist; hlist_for_each(rlist, mc_router_list) { p = br_multicast_rport_from_node(brmctx, mc_router_list, rlist); if ((unsigned long)port >= (unsigned long)p) break; slot = rlist; } return slot; } static bool br_multicast_no_router_otherpf(struct net_bridge_mcast_port *pmctx, struct hlist_node *rnode) { #if IS_ENABLED(CONFIG_IPV6) if (rnode != &pmctx->ip6_rlist) return hlist_unhashed(&pmctx->ip6_rlist); else return hlist_unhashed(&pmctx->ip4_rlist); #else return true; #endif } /* Add port to router_list * list is maintained ordered by pointer value * and locked by br->multicast_lock and RCU */ static void br_multicast_add_router(struct net_bridge_mcast *brmctx, struct net_bridge_mcast_port *pmctx, struct hlist_node *rlist, struct hlist_head *mc_router_list) { struct hlist_node *slot; if (!hlist_unhashed(rlist)) return; slot = br_multicast_get_rport_slot(brmctx, pmctx->port, mc_router_list); if (slot) hlist_add_behind_rcu(rlist, slot); else hlist_add_head_rcu(rlist, mc_router_list); /* For backwards compatibility for now, only notify if we * switched from no IPv4/IPv6 multicast router to a new * IPv4 or IPv6 multicast router. */ if (br_multicast_no_router_otherpf(pmctx, rlist)) { br_rtr_notify(pmctx->port->br->dev, pmctx, RTM_NEWMDB); br_port_mc_router_state_change(pmctx->port, true); } } /* Add port to router_list * list is maintained ordered by pointer value * and locked by br->multicast_lock and RCU */ static void br_ip4_multicast_add_router(struct net_bridge_mcast *brmctx, struct net_bridge_mcast_port *pmctx) { br_multicast_add_router(brmctx, pmctx, &pmctx->ip4_rlist, &brmctx->ip4_mc_router_list); } /* Add port to router_list * list is maintained ordered by pointer value * and locked by br->multicast_lock and RCU */ static void br_ip6_multicast_add_router(struct net_bridge_mcast *brmctx, struct net_bridge_mcast_port *pmctx) { #if IS_ENABLED(CONFIG_IPV6) br_multicast_add_router(brmctx, pmctx, &pmctx->ip6_rlist, &brmctx->ip6_mc_router_list); #endif } static void br_multicast_mark_router(struct net_bridge_mcast *brmctx, struct net_bridge_mcast_port *pmctx, struct timer_list *timer, struct hlist_node *rlist, struct hlist_head *mc_router_list) { unsigned long now = jiffies; if (!br_multicast_ctx_should_use(brmctx, pmctx)) return; if (!pmctx) { if (brmctx->multicast_router == MDB_RTR_TYPE_TEMP_QUERY) { if (!br_ip4_multicast_is_router(brmctx) && !br_ip6_multicast_is_router(brmctx)) br_mc_router_state_change(brmctx->br, true); mod_timer(timer, now + brmctx->multicast_querier_interval); } return; } if (pmctx->multicast_router == MDB_RTR_TYPE_DISABLED || pmctx->multicast_router == MDB_RTR_TYPE_PERM) return; br_multicast_add_router(brmctx, pmctx, rlist, mc_router_list); mod_timer(timer, now + brmctx->multicast_querier_interval); } static void br_ip4_multicast_mark_router(struct net_bridge_mcast *brmctx, struct net_bridge_mcast_port *pmctx) { struct timer_list *timer = &brmctx->ip4_mc_router_timer; struct hlist_node *rlist = NULL; if (pmctx) { timer = &pmctx->ip4_mc_router_timer; rlist = &pmctx->ip4_rlist; } br_multicast_mark_router(brmctx, pmctx, timer, rlist, &brmctx->ip4_mc_router_list); } static void br_ip6_multicast_mark_router(struct net_bridge_mcast *brmctx, struct net_bridge_mcast_port *pmctx) { #if IS_ENABLED(CONFIG_IPV6) struct timer_list *timer = &brmctx->ip6_mc_router_timer; struct hlist_node *rlist = NULL; if (pmctx) { timer = &pmctx->ip6_mc_router_timer; rlist = &pmctx->ip6_rlist; } br_multicast_mark_router(brmctx, pmctx, timer, rlist, &brmctx->ip6_mc_router_list); #endif } static void br_ip4_multicast_query_received(struct net_bridge_mcast *brmctx, struct net_bridge_mcast_port *pmctx, struct bridge_mcast_other_query *query, struct br_ip *saddr, unsigned long max_delay) { if (!br_multicast_select_querier(brmctx, pmctx, saddr)) return; br_multicast_update_query_timer(brmctx, query, max_delay); br_ip4_multicast_mark_router(brmctx, pmctx); } #if IS_ENABLED(CONFIG_IPV6) static void br_ip6_multicast_query_received(struct net_bridge_mcast *brmctx, struct net_bridge_mcast_port *pmctx, struct bridge_mcast_other_query *query, struct br_ip *saddr, unsigned long max_delay) { if (!br_multicast_select_querier(brmctx, pmctx, saddr)) return; br_multicast_update_query_timer(brmctx, query, max_delay); br_ip6_multicast_mark_router(brmctx, pmctx); } #endif static void br_ip4_multicast_query(struct net_bridge_mcast *brmctx, struct net_bridge_mcast_port *pmctx, struct sk_buff *skb, u16 vid) { unsigned int transport_len = ip_transport_len(skb); const struct iphdr *iph = ip_hdr(skb); struct igmphdr *ih = igmp_hdr(skb); struct net_bridge_mdb_entry *mp; struct igmpv3_query *ih3; struct net_bridge_port_group *p; struct net_bridge_port_group __rcu **pp; struct br_ip saddr = {}; unsigned long max_delay; unsigned long now = jiffies; __be32 group; spin_lock(&brmctx->br->multicast_lock); if (!br_multicast_ctx_should_use(brmctx, pmctx)) goto out; group = ih->group; if (transport_len == sizeof(*ih)) { max_delay = ih->code * (HZ / IGMP_TIMER_SCALE); if (!max_delay) { max_delay = 10 * HZ; group = 0; } } else if (transport_len >= sizeof(*ih3)) { ih3 = igmpv3_query_hdr(skb); if (ih3->nsrcs || (brmctx->multicast_igmp_version == 3 && group && ih3->suppress)) goto out; max_delay = ih3->code ? IGMPV3_MRC(ih3->code) * (HZ / IGMP_TIMER_SCALE) : 1; } else { goto out; } if (!group) { saddr.proto = htons(ETH_P_IP); saddr.src.ip4 = iph->saddr; br_ip4_multicast_query_received(brmctx, pmctx, &brmctx->ip4_other_query, &saddr, max_delay); goto out; } mp = br_mdb_ip4_get(brmctx->br, group, vid); if (!mp) goto out; max_delay *= brmctx->multicast_last_member_count; if (mp->host_joined && (timer_pending(&mp->timer) ? time_after(mp->timer.expires, now + max_delay) : timer_delete_sync_try(&mp->timer) >= 0)) mod_timer(&mp->timer, now + max_delay); for (pp = &mp->ports; (p = mlock_dereference(*pp, brmctx->br)) != NULL; pp = &p->next) { if (timer_pending(&p->timer) ? time_after(p->timer.expires, now + max_delay) : timer_delete_sync_try(&p->timer) >= 0 && (brmctx->multicast_igmp_version == 2 || p->filter_mode == MCAST_EXCLUDE)) mod_timer(&p->timer, now + max_delay); } out: spin_unlock(&brmctx->br->multicast_lock); } #if IS_ENABLED(CONFIG_IPV6) static int br_ip6_multicast_query(struct net_bridge_mcast *brmctx, struct net_bridge_mcast_port *pmctx, struct sk_buff *skb, u16 vid) { unsigned int transport_len = ipv6_transport_len(skb); struct mld_msg *mld; struct net_bridge_mdb_entry *mp; struct mld2_query *mld2q; struct net_bridge_port_group *p; struct net_bridge_port_group __rcu **pp; struct br_ip saddr = {}; unsigned long max_delay; unsigned long now = jiffies; unsigned int offset = skb_transport_offset(skb); const struct in6_addr *group = NULL; bool is_general_query; int err = 0; spin_lock(&brmctx->br->multicast_lock); if (!br_multicast_ctx_should_use(brmctx, pmctx)) goto out; if (transport_len == sizeof(*mld)) { if (!pskb_may_pull(skb, offset + sizeof(*mld))) { err = -EINVAL; goto out; } mld = (struct mld_msg *) icmp6_hdr(skb); max_delay = msecs_to_jiffies(ntohs(mld->mld_maxdelay)); if (max_delay) group = &mld->mld_mca; } else { if (!pskb_may_pull(skb, offset + sizeof(*mld2q))) { err = -EINVAL; goto out; } mld2q = (struct mld2_query *)icmp6_hdr(skb); if (!mld2q->mld2q_nsrcs) group = &mld2q->mld2q_mca; if (brmctx->multicast_mld_version == 2 && !ipv6_addr_any(&mld2q->mld2q_mca) && mld2q->mld2q_suppress) goto out; max_delay = max(msecs_to_jiffies(mldv2_mrc(mld2q)), 1UL); } is_general_query = group && ipv6_addr_any(group); if (is_general_query) { saddr.proto = htons(ETH_P_IPV6); saddr.src.ip6 = ipv6_hdr(skb)->saddr; br_ip6_multicast_query_received(brmctx, pmctx, &brmctx->ip6_other_query, &saddr, max_delay); goto out; } else if (!group) { goto out; } mp = br_mdb_ip6_get(brmctx->br, group, vid); if (!mp) goto out; max_delay *= brmctx->multicast_last_member_count; if (mp->host_joined && (timer_pending(&mp->timer) ? time_after(mp->timer.expires, now + max_delay) : timer_delete_sync_try(&mp->timer) >= 0)) mod_timer(&mp->timer, now + max_delay); for (pp = &mp->ports; (p = mlock_dereference(*pp, brmctx->br)) != NULL; pp = &p->next) { if (timer_pending(&p->timer) ? time_after(p->timer.expires, now + max_delay) : timer_delete_sync_try(&p->timer) >= 0 && (brmctx->multicast_mld_version == 1 || p->filter_mode == MCAST_EXCLUDE)) mod_timer(&p->timer, now + max_delay); } out: spin_unlock(&brmctx->br->multicast_lock); return err; } #endif static void br_multicast_leave_group(struct net_bridge_mcast *brmctx, struct net_bridge_mcast_port *pmctx, struct br_ip *group, struct bridge_mcast_other_query *other_query, struct bridge_mcast_own_query *own_query, const unsigned char *src) { struct net_bridge_mdb_entry *mp; struct net_bridge_port_group *p; unsigned long now; unsigned long time; spin_lock(&brmctx->br->multicast_lock); if (!br_multicast_ctx_should_use(brmctx, pmctx)) goto out; mp = br_mdb_ip_get(brmctx->br, group); if (!mp) goto out; if (pmctx && (pmctx->port->flags & BR_MULTICAST_FAST_LEAVE)) { struct net_bridge_port_group __rcu **pp; for (pp = &mp->ports; (p = mlock_dereference(*pp, brmctx->br)) != NULL; pp = &p->next) { if (!br_port_group_equal(p, pmctx->port, src)) continue; if (p->flags & MDB_PG_FLAGS_PERMANENT) break; p->flags |= MDB_PG_FLAGS_FAST_LEAVE; br_multicast_del_pg(mp, p, pp); } goto out; } if (timer_pending(&other_query->timer)) goto out; if (brmctx->multicast_querier) { __br_multicast_send_query(brmctx, pmctx, NULL, NULL, &mp->addr, false, 0, NULL); time = jiffies + brmctx->multicast_last_member_count * brmctx->multicast_last_member_interval; mod_timer(&own_query->timer, time); for (p = mlock_dereference(mp->ports, brmctx->br); p != NULL && pmctx != NULL; p = mlock_dereference(p->next, brmctx->br)) { if (!br_port_group_equal(p, pmctx->port, src)) continue; if (!hlist_unhashed(&p->mglist) && (timer_pending(&p->timer) ? time_after(p->timer.expires, time) : timer_delete_sync_try(&p->timer) >= 0)) { mod_timer(&p->timer, time); } break; } } now = jiffies; time = now + brmctx->multicast_last_member_count * brmctx->multicast_last_member_interval; if (!pmctx) { if (mp->host_joined && (timer_pending(&mp->timer) ? time_after(mp->timer.expires, time) : timer_delete_sync_try(&mp->timer) >= 0)) { mod_timer(&mp->timer, time); } goto out; } for (p = mlock_dereference(mp->ports, brmctx->br); p != NULL; p = mlock_dereference(p->next, brmctx->br)) { if (p->key.port != pmctx->port) continue; if (!hlist_unhashed(&p->mglist) && (timer_pending(&p->timer) ? time_after(p->timer.expires, time) : timer_delete_sync_try(&p->timer) >= 0)) { mod_timer(&p->timer, time); } break; } out: spin_unlock(&brmctx->br->multicast_lock); } static void br_ip4_multicast_leave_group(struct net_bridge_mcast *brmctx, struct net_bridge_mcast_port *pmctx, __be32 group, __u16 vid, const unsigned char *src) { struct br_ip br_group; struct bridge_mcast_own_query *own_query; if (ipv4_is_local_multicast(group)) return; own_query = pmctx ? &pmctx->ip4_own_query : &brmctx->ip4_own_query; memset(&br_group, 0, sizeof(br_group)); br_group.dst.ip4 = group; br_group.proto = htons(ETH_P_IP); br_group.vid = vid; br_multicast_leave_group(brmctx, pmctx, &br_group, &brmctx->ip4_other_query, own_query, src); } #if IS_ENABLED(CONFIG_IPV6) static void br_ip6_multicast_leave_group(struct net_bridge_mcast *brmctx, struct net_bridge_mcast_port *pmctx, const struct in6_addr *group, __u16 vid, const unsigned char *src) { struct br_ip br_group; struct bridge_mcast_own_query *own_query; if (ipv6_addr_is_ll_all_nodes(group)) return; own_query = pmctx ? &pmctx->ip6_own_query : &brmctx->ip6_own_query; memset(&br_group, 0, sizeof(br_group)); br_group.dst.ip6 = *group; br_group.proto = htons(ETH_P_IPV6); br_group.vid = vid; br_multicast_leave_group(brmctx, pmctx, &br_group, &brmctx->ip6_other_query, own_query, src); } #endif static void br_multicast_err_count(const struct net_bridge *br, const struct net_bridge_port *p, __be16 proto) { struct bridge_mcast_stats __percpu *stats; struct bridge_mcast_stats *pstats; if (!br_opt_get(br, BROPT_MULTICAST_STATS_ENABLED)) return; if (p) stats = p->mcast_stats; else stats = br->mcast_stats; if (WARN_ON(!stats)) return; pstats = this_cpu_ptr(stats); u64_stats_update_begin(&pstats->syncp); switch (proto) { case htons(ETH_P_IP): pstats->mstats.igmp_parse_errors++; break; #if IS_ENABLED(CONFIG_IPV6) case htons(ETH_P_IPV6): pstats->mstats.mld_parse_errors++; break; #endif } u64_stats_update_end(&pstats->syncp); } static void br_multicast_pim(struct net_bridge_mcast *brmctx, struct net_bridge_mcast_port *pmctx, const struct sk_buff *skb) { unsigned int offset = skb_transport_offset(skb); struct pimhdr *pimhdr, _pimhdr; pimhdr = skb_header_pointer(skb, offset, sizeof(_pimhdr), &_pimhdr); if (!pimhdr || pim_hdr_version(pimhdr) != PIM_VERSION || pim_hdr_type(pimhdr) != PIM_TYPE_HELLO) return; spin_lock(&brmctx->br->multicast_lock); br_ip4_multicast_mark_router(brmctx, pmctx); spin_unlock(&brmctx->br->multicast_lock); } static int br_ip4_multicast_mrd_rcv(struct net_bridge_mcast *brmctx, struct net_bridge_mcast_port *pmctx, struct sk_buff *skb) { if (ip_hdr(skb)->protocol != IPPROTO_IGMP || igmp_hdr(skb)->type != IGMP_MRDISC_ADV) return -ENOMSG; spin_lock(&brmctx->br->multicast_lock); br_ip4_multicast_mark_router(brmctx, pmctx); spin_unlock(&brmctx->br->multicast_lock); return 0; } static int br_multicast_ipv4_rcv(struct net_bridge_mcast *brmctx, struct net_bridge_mcast_port *pmctx, struct sk_buff *skb, u16 vid) { struct net_bridge_port *p = pmctx ? pmctx->port : NULL; const unsigned char *src; struct igmphdr *ih; int err; err = ip_mc_check_igmp(skb); if (err == -ENOMSG) { if (!ipv4_is_local_multicast(ip_hdr(skb)->daddr)) { BR_INPUT_SKB_CB(skb)->mrouters_only = 1; } else if (pim_ipv4_all_pim_routers(ip_hdr(skb)->daddr)) { if (ip_hdr(skb)->protocol == IPPROTO_PIM) br_multicast_pim(brmctx, pmctx, skb); } else if (ipv4_is_all_snoopers(ip_hdr(skb)->daddr)) { br_ip4_multicast_mrd_rcv(brmctx, pmctx, skb); } return 0; } else if (err < 0) { br_multicast_err_count(brmctx->br, p, skb->protocol); return err; } ih = igmp_hdr(skb); src = eth_hdr(skb)->h_source; BR_INPUT_SKB_CB(skb)->igmp = ih->type; switch (ih->type) { case IGMP_HOST_MEMBERSHIP_REPORT: case IGMPV2_HOST_MEMBERSHIP_REPORT: BR_INPUT_SKB_CB(skb)->mrouters_only = 1; err = br_ip4_multicast_add_group(brmctx, pmctx, ih->group, vid, src, true); break; case IGMPV3_HOST_MEMBERSHIP_REPORT: err = br_ip4_multicast_igmp3_report(brmctx, pmctx, skb, vid); break; case IGMP_HOST_MEMBERSHIP_QUERY: br_ip4_multicast_query(brmctx, pmctx, skb, vid); break; case IGMP_HOST_LEAVE_MESSAGE: br_ip4_multicast_leave_group(brmctx, pmctx, ih->group, vid, src); break; } br_multicast_count(brmctx->br, p, skb, BR_INPUT_SKB_CB(skb)->igmp, BR_MCAST_DIR_RX); return err; } #if IS_ENABLED(CONFIG_IPV6) static void br_ip6_multicast_mrd_rcv(struct net_bridge_mcast *brmctx, struct net_bridge_mcast_port *pmctx, struct sk_buff *skb) { if (icmp6_hdr(skb)->icmp6_type != ICMPV6_MRDISC_ADV) return; spin_lock(&brmctx->br->multicast_lock); br_ip6_multicast_mark_router(brmctx, pmctx); spin_unlock(&brmctx->br->multicast_lock); } static int br_multicast_ipv6_rcv(struct net_bridge_mcast *brmctx, struct net_bridge_mcast_port *pmctx, struct sk_buff *skb, u16 vid) { struct net_bridge_port *p = pmctx ? pmctx->port : NULL; const unsigned char *src; struct mld_msg *mld; int err; err = ipv6_mc_check_mld(skb); if (err == -ENOMSG || err == -ENODATA) { if (!ipv6_addr_is_ll_all_nodes(&ipv6_hdr(skb)->daddr)) BR_INPUT_SKB_CB(skb)->mrouters_only = 1; if (err == -ENODATA && ipv6_addr_is_all_snoopers(&ipv6_hdr(skb)->daddr)) br_ip6_multicast_mrd_rcv(brmctx, pmctx, skb); return 0; } else if (err < 0) { br_multicast_err_count(brmctx->br, p, skb->protocol); return err; } mld = (struct mld_msg *)skb_transport_header(skb); BR_INPUT_SKB_CB(skb)->igmp = mld->mld_type; switch (mld->mld_type) { case ICMPV6_MGM_REPORT: src = eth_hdr(skb)->h_source; BR_INPUT_SKB_CB(skb)->mrouters_only = 1; err = br_ip6_multicast_add_group(brmctx, pmctx, &mld->mld_mca, vid, src, true); break; case ICMPV6_MLD2_REPORT: err = br_ip6_multicast_mld2_report(brmctx, pmctx, skb, vid); break; case ICMPV6_MGM_QUERY: err = br_ip6_multicast_query(brmctx, pmctx, skb, vid); break; case ICMPV6_MGM_REDUCTION: src = eth_hdr(skb)->h_source; br_ip6_multicast_leave_group(brmctx, pmctx, &mld->mld_mca, vid, src); break; } br_multicast_count(brmctx->br, p, skb, BR_INPUT_SKB_CB(skb)->igmp, BR_MCAST_DIR_RX); return err; } #endif int br_multicast_rcv(struct net_bridge_mcast **brmctx, struct net_bridge_mcast_port **pmctx, struct net_bridge_vlan *vlan, struct sk_buff *skb, u16 vid) { int ret = 0; BR_INPUT_SKB_CB(skb)->igmp = 0; BR_INPUT_SKB_CB(skb)->mrouters_only = 0; if (!br_opt_get((*brmctx)->br, BROPT_MULTICAST_ENABLED)) return 0; if (br_opt_get((*brmctx)->br, BROPT_MCAST_VLAN_SNOOPING_ENABLED) && vlan) { const struct net_bridge_vlan *masterv; /* the vlan has the master flag set only when transmitting * through the bridge device */ if (br_vlan_is_master(vlan)) { masterv = vlan; *brmctx = &vlan->br_mcast_ctx; *pmctx = NULL; } else { masterv = vlan->brvlan; *brmctx = &vlan->brvlan->br_mcast_ctx; *pmctx = &vlan->port_mcast_ctx; } if (!(masterv->priv_flags & BR_VLFLAG_GLOBAL_MCAST_ENABLED)) return 0; } switch (skb->protocol) { case htons(ETH_P_IP): ret = br_multicast_ipv4_rcv(*brmctx, *pmctx, skb, vid); break; #if IS_ENABLED(CONFIG_IPV6) case htons(ETH_P_IPV6): ret = br_multicast_ipv6_rcv(*brmctx, *pmctx, skb, vid); break; #endif } return ret; } static void br_multicast_query_expired(struct net_bridge_mcast *brmctx, struct bridge_mcast_own_query *query, struct bridge_mcast_querier *querier) { spin_lock(&brmctx->br->multicast_lock); if (br_multicast_ctx_vlan_disabled(brmctx)) goto out; if (query->startup_sent < brmctx->multicast_startup_query_count) query->startup_sent++; br_multicast_send_query(brmctx, NULL, query); out: spin_unlock(&brmctx->br->multicast_lock); } static void br_ip4_multicast_query_expired(struct timer_list *t) { struct net_bridge_mcast *brmctx = timer_container_of(brmctx, t, ip4_own_query.timer); br_multicast_query_expired(brmctx, &brmctx->ip4_own_query, &brmctx->ip4_querier); } #if IS_ENABLED(CONFIG_IPV6) static void br_ip6_multicast_query_expired(struct timer_list *t) { struct net_bridge_mcast *brmctx = timer_container_of(brmctx, t, ip6_own_query.timer); br_multicast_query_expired(brmctx, &brmctx->ip6_own_query, &brmctx->ip6_querier); } #endif static void br_multicast_gc_work(struct work_struct *work) { struct net_bridge *br = container_of(work, struct net_bridge, mcast_gc_work); HLIST_HEAD(deleted_head); spin_lock_bh(&br->multicast_lock); hlist_move_list(&br->mcast_gc_list, &deleted_head); spin_unlock_bh(&br->multicast_lock); br_multicast_gc(&deleted_head); } void br_multicast_ctx_init(struct net_bridge *br, struct net_bridge_vlan *vlan, struct net_bridge_mcast *brmctx) { brmctx->br = br; brmctx->vlan = vlan; brmctx->multicast_router = MDB_RTR_TYPE_TEMP_QUERY; brmctx->multicast_last_member_count = 2; brmctx->multicast_startup_query_count = 2; brmctx->multicast_last_member_interval = HZ; brmctx->multicast_query_response_interval = 10 * HZ; brmctx->multicast_startup_query_interval = 125 * HZ / 4; brmctx->multicast_query_interval = 125 * HZ; brmctx->multicast_querier_interval = 255 * HZ; brmctx->multicast_membership_interval = 260 * HZ; brmctx->ip4_querier.port_ifidx = 0; seqcount_spinlock_init(&brmctx->ip4_querier.seq, &br->multicast_lock); brmctx->multicast_igmp_version = 2; #if IS_ENABLED(CONFIG_IPV6) brmctx->multicast_mld_version = 1; brmctx->ip6_querier.port_ifidx = 0; seqcount_spinlock_init(&brmctx->ip6_querier.seq, &br->multicast_lock); #endif timer_setup(&brmctx->ip4_mc_router_timer, br_ip4_multicast_local_router_expired, 0); timer_setup(&brmctx->ip4_other_query.timer, br_ip4_multicast_querier_expired, 0); timer_setup(&brmctx->ip4_other_query.delay_timer, br_multicast_query_delay_expired, 0); timer_setup(&brmctx->ip4_own_query.timer, br_ip4_multicast_query_expired, 0); #if IS_ENABLED(CONFIG_IPV6) timer_setup(&brmctx->ip6_mc_router_timer, br_ip6_multicast_local_router_expired, 0); timer_setup(&brmctx->ip6_other_query.timer, br_ip6_multicast_querier_expired, 0); timer_setup(&brmctx->ip6_other_query.delay_timer, br_multicast_query_delay_expired, 0); timer_setup(&brmctx->ip6_own_query.timer, br_ip6_multicast_query_expired, 0); #endif } void br_multicast_ctx_deinit(struct net_bridge_mcast *brmctx) { __br_multicast_stop(brmctx); } void br_multicast_init(struct net_bridge *br) { br->hash_max = BR_MULTICAST_DEFAULT_HASH_MAX; br_multicast_ctx_init(br, NULL, &br->multicast_ctx); br_opt_toggle(br, BROPT_MULTICAST_ENABLED, true); br_opt_toggle(br, BROPT_HAS_IPV6_ADDR, true); spin_lock_init(&br->multicast_lock); INIT_HLIST_HEAD(&br->mdb_list); INIT_HLIST_HEAD(&br->mcast_gc_list); INIT_WORK(&br->mcast_gc_work, br_multicast_gc_work); } static void br_ip4_multicast_join_snoopers(struct net_bridge *br) { struct in_device *in_dev = in_dev_get(br->dev); if (!in_dev) return; __ip_mc_inc_group(in_dev, htonl(INADDR_ALLSNOOPERS_GROUP), GFP_ATOMIC); in_dev_put(in_dev); } #if IS_ENABLED(CONFIG_IPV6) static void br_ip6_multicast_join_snoopers(struct net_bridge *br) { struct in6_addr addr; ipv6_addr_set(&addr, htonl(0xff020000), 0, 0, htonl(0x6a)); ipv6_dev_mc_inc(br->dev, &addr); } #else static inline void br_ip6_multicast_join_snoopers(struct net_bridge *br) { } #endif void br_multicast_join_snoopers(struct net_bridge *br) { br_ip4_multicast_join_snoopers(br); br_ip6_multicast_join_snoopers(br); } static void br_ip4_multicast_leave_snoopers(struct net_bridge *br) { struct in_device *in_dev = in_dev_get(br->dev); if (WARN_ON(!in_dev)) return; __ip_mc_dec_group(in_dev, htonl(INADDR_ALLSNOOPERS_GROUP), GFP_ATOMIC); in_dev_put(in_dev); } #if IS_ENABLED(CONFIG_IPV6) static void br_ip6_multicast_leave_snoopers(struct net_bridge *br) { struct in6_addr addr; ipv6_addr_set(&addr, htonl(0xff020000), 0, 0, htonl(0x6a)); ipv6_dev_mc_dec(br->dev, &addr); } #else static inline void br_ip6_multicast_leave_snoopers(struct net_bridge *br) { } #endif void br_multicast_leave_snoopers(struct net_bridge *br) { br_ip4_multicast_leave_snoopers(br); br_ip6_multicast_leave_snoopers(br); } static void __br_multicast_open_query(struct net_bridge *br, struct bridge_mcast_own_query *query) { query->startup_sent = 0; if (!br_opt_get(br, BROPT_MULTICAST_ENABLED)) return; mod_timer(&query->timer, jiffies); } static void __br_multicast_open(struct net_bridge_mcast *brmctx) { __br_multicast_open_query(brmctx->br, &brmctx->ip4_own_query); #if IS_ENABLED(CONFIG_IPV6) __br_multicast_open_query(brmctx->br, &brmctx->ip6_own_query); #endif } void br_multicast_open(struct net_bridge *br) { ASSERT_RTNL(); if (br_opt_get(br, BROPT_MCAST_VLAN_SNOOPING_ENABLED)) { struct net_bridge_vlan_group *vg; struct net_bridge_vlan *vlan; vg = br_vlan_group(br); if (vg) { list_for_each_entry(vlan, &vg->vlan_list, vlist) { struct net_bridge_mcast *brmctx; brmctx = &vlan->br_mcast_ctx; if (br_vlan_is_brentry(vlan) && !br_multicast_ctx_vlan_disabled(brmctx)) __br_multicast_open(&vlan->br_mcast_ctx); } } } else { __br_multicast_open(&br->multicast_ctx); } } static void __br_multicast_stop(struct net_bridge_mcast *brmctx) { timer_delete_sync(&brmctx->ip4_mc_router_timer); timer_delete_sync(&brmctx->ip4_other_query.timer); timer_delete_sync(&brmctx->ip4_other_query.delay_timer); timer_delete_sync(&brmctx->ip4_own_query.timer); #if IS_ENABLED(CONFIG_IPV6) timer_delete_sync(&brmctx->ip6_mc_router_timer); timer_delete_sync(&brmctx->ip6_other_query.timer); timer_delete_sync(&brmctx->ip6_other_query.delay_timer); timer_delete_sync(&brmctx->ip6_own_query.timer); #endif } void br_multicast_update_vlan_mcast_ctx(struct net_bridge_vlan *v, u8 state) { #if IS_ENABLED(CONFIG_BRIDGE_VLAN_FILTERING) struct net_bridge *br; if (!br_vlan_should_use(v)) return; if (br_vlan_is_master(v)) return; br = v->port->br; if (!br_opt_get(br, BROPT_MCAST_VLAN_SNOOPING_ENABLED)) return; if (br_vlan_state_allowed(state, true)) br_multicast_enable_port_ctx(&v->port_mcast_ctx); /* Multicast is not disabled for the vlan when it goes in * blocking state because the timers will expire and stop by * themselves without sending more queries. */ #endif } void br_multicast_toggle_one_vlan(struct net_bridge_vlan *vlan, bool on) { struct net_bridge *br; /* it's okay to check for the flag without the multicast lock because it * can only change under RTNL -> multicast_lock, we need the latter to * sync with timers and packets */ if (on == !!(vlan->priv_flags & BR_VLFLAG_MCAST_ENABLED)) return; if (br_vlan_is_master(vlan)) { br = vlan->br; if (!br_vlan_is_brentry(vlan) || (on && br_multicast_ctx_vlan_global_disabled(&vlan->br_mcast_ctx))) return; spin_lock_bh(&br->multicast_lock); vlan->priv_flags ^= BR_VLFLAG_MCAST_ENABLED; spin_unlock_bh(&br->multicast_lock); if (on) __br_multicast_open(&vlan->br_mcast_ctx); else __br_multicast_stop(&vlan->br_mcast_ctx); } else { struct net_bridge_mcast *brmctx; brmctx = br_multicast_port_ctx_get_global(&vlan->port_mcast_ctx); if (on && br_multicast_ctx_vlan_global_disabled(brmctx)) return; br = vlan->port->br; spin_lock_bh(&br->multicast_lock); vlan->priv_flags ^= BR_VLFLAG_MCAST_ENABLED; if (on) __br_multicast_enable_port_ctx(&vlan->port_mcast_ctx); else __br_multicast_disable_port_ctx(&vlan->port_mcast_ctx); spin_unlock_bh(&br->multicast_lock); } } static void br_multicast_toggle_vlan(struct net_bridge_vlan *vlan, bool on) { struct net_bridge_port *p; if (WARN_ON_ONCE(!br_vlan_is_master(vlan))) return; list_for_each_entry(p, &vlan->br->port_list, list) { struct net_bridge_vlan *vport; vport = br_vlan_find(nbp_vlan_group(p), vlan->vid); if (!vport) continue; br_multicast_toggle_one_vlan(vport, on); } if (br_vlan_is_brentry(vlan)) br_multicast_toggle_one_vlan(vlan, on); } int br_multicast_toggle_vlan_snooping(struct net_bridge *br, bool on, struct netlink_ext_ack *extack) { struct net_bridge_vlan_group *vg; struct net_bridge_vlan *vlan; struct net_bridge_port *p; if (br_opt_get(br, BROPT_MCAST_VLAN_SNOOPING_ENABLED) == on) return 0; if (on && !br_opt_get(br, BROPT_VLAN_ENABLED)) { NL_SET_ERR_MSG_MOD(extack, "Cannot enable multicast vlan snooping with vlan filtering disabled"); return -EINVAL; } vg = br_vlan_group(br); if (!vg) return 0; br_opt_toggle(br, BROPT_MCAST_VLAN_SNOOPING_ENABLED, on); /* disable/enable non-vlan mcast contexts based on vlan snooping */ if (on) __br_multicast_stop(&br->multicast_ctx); else __br_multicast_open(&br->multicast_ctx); list_for_each_entry(p, &br->port_list, list) { if (on) br_multicast_disable_port_ctx(&p->multicast_ctx); else br_multicast_enable_port_ctx(&p->multicast_ctx); } list_for_each_entry(vlan, &vg->vlan_list, vlist) br_multicast_toggle_vlan(vlan, on); return 0; } bool br_multicast_toggle_global_vlan(struct net_bridge_vlan *vlan, bool on) { ASSERT_RTNL(); /* BR_VLFLAG_GLOBAL_MCAST_ENABLED relies on eventual consistency and * requires only RTNL to change */ if (on == !!(vlan->priv_flags & BR_VLFLAG_GLOBAL_MCAST_ENABLED)) return false; vlan->priv_flags ^= BR_VLFLAG_GLOBAL_MCAST_ENABLED; br_multicast_toggle_vlan(vlan, on); return true; } void br_multicast_stop(struct net_bridge *br) { ASSERT_RTNL(); if (br_opt_get(br, BROPT_MCAST_VLAN_SNOOPING_ENABLED)) { struct net_bridge_vlan_group *vg; struct net_bridge_vlan *vlan; vg = br_vlan_group(br); if (vg) { list_for_each_entry(vlan, &vg->vlan_list, vlist) { struct net_bridge_mcast *brmctx; brmctx = &vlan->br_mcast_ctx; if (br_vlan_is_brentry(vlan) && !br_multicast_ctx_vlan_disabled(brmctx)) __br_multicast_stop(&vlan->br_mcast_ctx); } } } else { __br_multicast_stop(&br->multicast_ctx); } } void br_multicast_dev_del(struct net_bridge *br) { struct net_bridge_mdb_entry *mp; HLIST_HEAD(deleted_head); struct hlist_node *tmp; spin_lock_bh(&br->multicast_lock); hlist_for_each_entry_safe(mp, tmp, &br->mdb_list, mdb_node) br_multicast_del_mdb_entry(mp); hlist_move_list(&br->mcast_gc_list, &deleted_head); spin_unlock_bh(&br->multicast_lock); br_multicast_ctx_deinit(&br->multicast_ctx); br_multicast_gc(&deleted_head); cancel_work_sync(&br->mcast_gc_work); rcu_barrier(); } int br_multicast_set_router(struct net_bridge_mcast *brmctx, unsigned long val) { int err = -EINVAL; spin_lock_bh(&brmctx->br->multicast_lock); switch (val) { case MDB_RTR_TYPE_DISABLED: case MDB_RTR_TYPE_PERM: br_mc_router_state_change(brmctx->br, val == MDB_RTR_TYPE_PERM); timer_delete(&brmctx->ip4_mc_router_timer); #if IS_ENABLED(CONFIG_IPV6) timer_delete(&brmctx->ip6_mc_router_timer); #endif brmctx->multicast_router = val; err = 0; break; case MDB_RTR_TYPE_TEMP_QUERY: if (brmctx->multicast_router != MDB_RTR_TYPE_TEMP_QUERY) br_mc_router_state_change(brmctx->br, false); brmctx->multicast_router = val; err = 0; break; } spin_unlock_bh(&brmctx->br->multicast_lock); return err; } static void br_multicast_rport_del_notify(struct net_bridge_mcast_port *pmctx, bool deleted) { if (!deleted) return; /* For backwards compatibility for now, only notify if there is * no multicast router anymore for both IPv4 and IPv6. */ if (!hlist_unhashed(&pmctx->ip4_rlist)) return; #if IS_ENABLED(CONFIG_IPV6) if (!hlist_unhashed(&pmctx->ip6_rlist)) return; #endif br_rtr_notify(pmctx->port->br->dev, pmctx, RTM_DELMDB); br_port_mc_router_state_change(pmctx->port, false); /* don't allow timer refresh */ if (pmctx->multicast_router == MDB_RTR_TYPE_TEMP) pmctx->multicast_router = MDB_RTR_TYPE_TEMP_QUERY; } int br_multicast_set_port_router(struct net_bridge_mcast_port *pmctx, unsigned long val) { struct net_bridge_mcast *brmctx; unsigned long now = jiffies; int err = -EINVAL; bool del = false; brmctx = br_multicast_port_ctx_get_global(pmctx); spin_lock_bh(&brmctx->br->multicast_lock); if (pmctx->multicast_router == val) { /* Refresh the temp router port timer */ if (pmctx->multicast_router == MDB_RTR_TYPE_TEMP) { mod_timer(&pmctx->ip4_mc_router_timer, now + brmctx->multicast_querier_interval); #if IS_ENABLED(CONFIG_IPV6) mod_timer(&pmctx->ip6_mc_router_timer, now + brmctx->multicast_querier_interval); #endif } err = 0; goto unlock; } switch (val) { case MDB_RTR_TYPE_DISABLED: pmctx->multicast_router = MDB_RTR_TYPE_DISABLED; del |= br_ip4_multicast_rport_del(pmctx); timer_delete(&pmctx->ip4_mc_router_timer); del |= br_ip6_multicast_rport_del(pmctx); #if IS_ENABLED(CONFIG_IPV6) timer_delete(&pmctx->ip6_mc_router_timer); #endif br_multicast_rport_del_notify(pmctx, del); break; case MDB_RTR_TYPE_TEMP_QUERY: pmctx->multicast_router = MDB_RTR_TYPE_TEMP_QUERY; del |= br_ip4_multicast_rport_del(pmctx); del |= br_ip6_multicast_rport_del(pmctx); br_multicast_rport_del_notify(pmctx, del); break; case MDB_RTR_TYPE_PERM: pmctx->multicast_router = MDB_RTR_TYPE_PERM; timer_delete(&pmctx->ip4_mc_router_timer); br_ip4_multicast_add_router(brmctx, pmctx); #if IS_ENABLED(CONFIG_IPV6) timer_delete(&pmctx->ip6_mc_router_timer); #endif br_ip6_multicast_add_router(brmctx, pmctx); break; case MDB_RTR_TYPE_TEMP: pmctx->multicast_router = MDB_RTR_TYPE_TEMP; br_ip4_multicast_mark_router(brmctx, pmctx); br_ip6_multicast_mark_router(brmctx, pmctx); break; default: goto unlock; } err = 0; unlock: spin_unlock_bh(&brmctx->br->multicast_lock); return err; } int br_multicast_set_vlan_router(struct net_bridge_vlan *v, u8 mcast_router) { int err; if (br_vlan_is_master(v)) err = br_multicast_set_router(&v->br_mcast_ctx, mcast_router); else err = br_multicast_set_port_router(&v->port_mcast_ctx, mcast_router); return err; } static void br_multicast_start_querier(struct net_bridge_mcast *brmctx, struct bridge_mcast_own_query *query) { struct net_bridge_port *port; if (!br_multicast_ctx_matches_vlan_snooping(brmctx)) return; __br_multicast_open_query(brmctx->br, query); rcu_read_lock(); list_for_each_entry_rcu(port, &brmctx->br->port_list, list) { struct bridge_mcast_own_query *ip4_own_query; #if IS_ENABLED(CONFIG_IPV6) struct bridge_mcast_own_query *ip6_own_query; #endif if (br_multicast_port_ctx_state_stopped(&port->multicast_ctx)) continue; if (br_multicast_ctx_is_vlan(brmctx)) { struct net_bridge_vlan *vlan; vlan = br_vlan_find(nbp_vlan_group_rcu(port), brmctx->vlan->vid); if (!vlan || br_multicast_port_ctx_state_stopped(&vlan->port_mcast_ctx)) continue; ip4_own_query = &vlan->port_mcast_ctx.ip4_own_query; #if IS_ENABLED(CONFIG_IPV6) ip6_own_query = &vlan->port_mcast_ctx.ip6_own_query; #endif } else { ip4_own_query = &port->multicast_ctx.ip4_own_query; #if IS_ENABLED(CONFIG_IPV6) ip6_own_query = &port->multicast_ctx.ip6_own_query; #endif } if (query == &brmctx->ip4_own_query) br_multicast_enable(ip4_own_query); #if IS_ENABLED(CONFIG_IPV6) else br_multicast_enable(ip6_own_query); #endif } rcu_read_unlock(); } int br_multicast_toggle(struct net_bridge *br, unsigned long val, struct netlink_ext_ack *extack) { struct net_bridge_port *port; bool change_snoopers = false; int err = 0; spin_lock_bh(&br->multicast_lock); if (!!br_opt_get(br, BROPT_MULTICAST_ENABLED) == !!val) goto unlock; err = br_mc_disabled_update(br->dev, val, extack); if (err == -EOPNOTSUPP) err = 0; if (err) goto unlock; br_opt_toggle(br, BROPT_MULTICAST_ENABLED, !!val); if (!br_opt_get(br, BROPT_MULTICAST_ENABLED)) { change_snoopers = true; goto unlock; } if (!netif_running(br->dev)) goto unlock; br_multicast_open(br); list_for_each_entry(port, &br->port_list, list) __br_multicast_enable_port_ctx(&port->multicast_ctx); change_snoopers = true; unlock: spin_unlock_bh(&br->multicast_lock); /* br_multicast_join_snoopers has the potential to cause * an MLD Report/Leave to be delivered to br_multicast_rcv, * which would in turn call br_multicast_add_group, which would * attempt to acquire multicast_lock. This function should be * called after the lock has been released to avoid deadlocks on * multicast_lock. * * br_multicast_leave_snoopers does not have the problem since * br_multicast_rcv first checks BROPT_MULTICAST_ENABLED, and * returns without calling br_multicast_ipv4/6_rcv if it's not * enabled. Moved both functions out just for symmetry. */ if (change_snoopers) { if (br_opt_get(br, BROPT_MULTICAST_ENABLED)) br_multicast_join_snoopers(br); else br_multicast_leave_snoopers(br); } return err; } bool br_multicast_enabled(const struct net_device *dev) { struct net_bridge *br = netdev_priv(dev); return !!br_opt_get(br, BROPT_MULTICAST_ENABLED); } EXPORT_SYMBOL_GPL(br_multicast_enabled); bool br_multicast_router(const struct net_device *dev) { struct net_bridge *br = netdev_priv(dev); bool is_router; spin_lock_bh(&br->multicast_lock); is_router = br_multicast_is_router(&br->multicast_ctx, NULL); spin_unlock_bh(&br->multicast_lock); return is_router; } EXPORT_SYMBOL_GPL(br_multicast_router); int br_multicast_set_querier(struct net_bridge_mcast *brmctx, unsigned long val) { unsigned long max_delay; val = !!val; spin_lock_bh(&brmctx->br->multicast_lock); if (brmctx->multicast_querier == val) goto unlock; WRITE_ONCE(brmctx->multicast_querier, val); if (!val) goto unlock; max_delay = brmctx->multicast_query_response_interval; if (!timer_pending(&brmctx->ip4_other_query.timer)) mod_timer(&brmctx->ip4_other_query.delay_timer, jiffies + max_delay); br_multicast_start_querier(brmctx, &brmctx->ip4_own_query); #if IS_ENABLED(CONFIG_IPV6) if (!timer_pending(&brmctx->ip6_other_query.timer)) mod_timer(&brmctx->ip6_other_query.delay_timer, jiffies + max_delay); br_multicast_start_querier(brmctx, &brmctx->ip6_own_query); #endif unlock: spin_unlock_bh(&brmctx->br->multicast_lock); return 0; } int br_multicast_set_igmp_version(struct net_bridge_mcast *brmctx, unsigned long val) { /* Currently we support only version 2 and 3 */ switch (val) { case 2: case 3: break; default: return -EINVAL; } spin_lock_bh(&brmctx->br->multicast_lock); brmctx->multicast_igmp_version = val; spin_unlock_bh(&brmctx->br->multicast_lock); return 0; } #if IS_ENABLED(CONFIG_IPV6) int br_multicast_set_mld_version(struct net_bridge_mcast *brmctx, unsigned long val) { /* Currently we support version 1 and 2 */ switch (val) { case 1: case 2: break; default: return -EINVAL; } spin_lock_bh(&brmctx->br->multicast_lock); brmctx->multicast_mld_version = val; spin_unlock_bh(&brmctx->br->multicast_lock); return 0; } #endif void br_multicast_set_query_intvl(struct net_bridge_mcast *brmctx, unsigned long val) { unsigned long intvl_jiffies = clock_t_to_jiffies(val); if (intvl_jiffies < BR_MULTICAST_QUERY_INTVL_MIN) { br_info(brmctx->br, "trying to set multicast query interval below minimum, setting to %lu (%ums)\n", jiffies_to_clock_t(BR_MULTICAST_QUERY_INTVL_MIN), jiffies_to_msecs(BR_MULTICAST_QUERY_INTVL_MIN)); intvl_jiffies = BR_MULTICAST_QUERY_INTVL_MIN; } brmctx->multicast_query_interval = intvl_jiffies; } void br_multicast_set_startup_query_intvl(struct net_bridge_mcast *brmctx, unsigned long val) { unsigned long intvl_jiffies = clock_t_to_jiffies(val); if (intvl_jiffies < BR_MULTICAST_STARTUP_QUERY_INTVL_MIN) { br_info(brmctx->br, "trying to set multicast startup query interval below minimum, setting to %lu (%ums)\n", jiffies_to_clock_t(BR_MULTICAST_STARTUP_QUERY_INTVL_MIN), jiffies_to_msecs(BR_MULTICAST_STARTUP_QUERY_INTVL_MIN)); intvl_jiffies = BR_MULTICAST_STARTUP_QUERY_INTVL_MIN; } brmctx->multicast_startup_query_interval = intvl_jiffies; } /** * br_multicast_list_adjacent - Returns snooped multicast addresses * @dev: The bridge port adjacent to which to retrieve addresses * @br_ip_list: The list to store found, snooped multicast IP addresses in * * Creates a list of IP addresses (struct br_ip_list) sensed by the multicast * snooping feature on all bridge ports of dev's bridge device, excluding * the addresses from dev itself. * * Returns the number of items added to br_ip_list. * * Notes: * - br_ip_list needs to be initialized by caller * - br_ip_list might contain duplicates in the end * (needs to be taken care of by caller) * - br_ip_list needs to be freed by caller */ int br_multicast_list_adjacent(struct net_device *dev, struct list_head *br_ip_list) { struct net_bridge *br; struct net_bridge_port *port; struct net_bridge_port_group *group; struct br_ip_list *entry; int count = 0; rcu_read_lock(); if (!br_ip_list || !netif_is_bridge_port(dev)) goto unlock; port = br_port_get_rcu(dev); if (!port || !port->br) goto unlock; br = port->br; list_for_each_entry_rcu(port, &br->port_list, list) { if (!port->dev || port->dev == dev) continue; hlist_for_each_entry_rcu(group, &port->mglist, mglist) { entry = kmalloc(sizeof(*entry), GFP_ATOMIC); if (!entry) goto unlock; entry->addr = group->key.addr; list_add(&entry->list, br_ip_list); count++; } } unlock: rcu_read_unlock(); return count; } EXPORT_SYMBOL_GPL(br_multicast_list_adjacent); /** * br_multicast_has_querier_anywhere - Checks for a querier on a bridge * @dev: The bridge port providing the bridge on which to check for a querier * @proto: The protocol family to check for: IGMP -> ETH_P_IP, MLD -> ETH_P_IPV6 * * Checks whether the given interface has a bridge on top and if so returns * true if a valid querier exists anywhere on the bridged link layer. * Otherwise returns false. */ bool br_multicast_has_querier_anywhere(struct net_device *dev, int proto) { struct net_bridge *br; struct net_bridge_port *port; struct ethhdr eth; bool ret = false; rcu_read_lock(); if (!netif_is_bridge_port(dev)) goto unlock; port = br_port_get_rcu(dev); if (!port || !port->br) goto unlock; br = port->br; memset(ð, 0, sizeof(eth)); eth.h_proto = htons(proto); ret = br_multicast_querier_exists(&br->multicast_ctx, ð, NULL); unlock: rcu_read_unlock(); return ret; } EXPORT_SYMBOL_GPL(br_multicast_has_querier_anywhere); /** * br_multicast_has_querier_adjacent - Checks for a querier behind a bridge port * @dev: The bridge port adjacent to which to check for a querier * @proto: The protocol family to check for: IGMP -> ETH_P_IP, MLD -> ETH_P_IPV6 * * Checks whether the given interface has a bridge on top and if so returns * true if a selected querier is behind one of the other ports of this * bridge. Otherwise returns false. */ bool br_multicast_has_querier_adjacent(struct net_device *dev, int proto) { struct net_bridge_mcast *brmctx; struct net_bridge *br; struct net_bridge_port *port; bool ret = false; int port_ifidx; rcu_read_lock(); if (!netif_is_bridge_port(dev)) goto unlock; port = br_port_get_rcu(dev); if (!port || !port->br) goto unlock; br = port->br; brmctx = &br->multicast_ctx; switch (proto) { case ETH_P_IP: port_ifidx = brmctx->ip4_querier.port_ifidx; if (!timer_pending(&brmctx->ip4_other_query.timer) || port_ifidx == port->dev->ifindex) goto unlock; break; #if IS_ENABLED(CONFIG_IPV6) case ETH_P_IPV6: port_ifidx = brmctx->ip6_querier.port_ifidx; if (!timer_pending(&brmctx->ip6_other_query.timer) || port_ifidx == port->dev->ifindex) goto unlock; break; #endif default: goto unlock; } ret = true; unlock: rcu_read_unlock(); return ret; } EXPORT_SYMBOL_GPL(br_multicast_has_querier_adjacent); /** * br_multicast_has_router_adjacent - Checks for a router behind a bridge port * @dev: The bridge port adjacent to which to check for a multicast router * @proto: The protocol family to check for: IGMP -> ETH_P_IP, MLD -> ETH_P_IPV6 * * Checks whether the given interface has a bridge on top and if so returns * true if a multicast router is behind one of the other ports of this * bridge. Otherwise returns false. */ bool br_multicast_has_router_adjacent(struct net_device *dev, int proto) { struct net_bridge_mcast_port *pmctx; struct net_bridge_mcast *brmctx; struct net_bridge_port *port; bool ret = false; rcu_read_lock(); port = br_port_get_check_rcu(dev); if (!port) goto unlock; brmctx = &port->br->multicast_ctx; switch (proto) { case ETH_P_IP: hlist_for_each_entry_rcu(pmctx, &brmctx->ip4_mc_router_list, ip4_rlist) { if (pmctx->port == port) continue; ret = true; goto unlock; } break; #if IS_ENABLED(CONFIG_IPV6) case ETH_P_IPV6: hlist_for_each_entry_rcu(pmctx, &brmctx->ip6_mc_router_list, ip6_rlist) { if (pmctx->port == port) continue; ret = true; goto unlock; } break; #endif default: /* when compiled without IPv6 support, be conservative and * always assume presence of an IPv6 multicast router */ ret = true; } unlock: rcu_read_unlock(); return ret; } EXPORT_SYMBOL_GPL(br_multicast_has_router_adjacent); static void br_mcast_stats_add(struct bridge_mcast_stats __percpu *stats, const struct sk_buff *skb, u8 type, u8 dir) { struct bridge_mcast_stats *pstats = this_cpu_ptr(stats); __be16 proto = skb->protocol; unsigned int t_len; u64_stats_update_begin(&pstats->syncp); switch (proto) { case htons(ETH_P_IP): t_len = ntohs(ip_hdr(skb)->tot_len) - ip_hdrlen(skb); switch (type) { case IGMP_HOST_MEMBERSHIP_REPORT: pstats->mstats.igmp_v1reports[dir]++; break; case IGMPV2_HOST_MEMBERSHIP_REPORT: pstats->mstats.igmp_v2reports[dir]++; break; case IGMPV3_HOST_MEMBERSHIP_REPORT: pstats->mstats.igmp_v3reports[dir]++; break; case IGMP_HOST_MEMBERSHIP_QUERY: if (t_len != sizeof(struct igmphdr)) { pstats->mstats.igmp_v3queries[dir]++; } else { unsigned int offset = skb_transport_offset(skb); struct igmphdr *ih, _ihdr; ih = skb_header_pointer(skb, offset, sizeof(_ihdr), &_ihdr); if (!ih) break; if (!ih->code) pstats->mstats.igmp_v1queries[dir]++; else pstats->mstats.igmp_v2queries[dir]++; } break; case IGMP_HOST_LEAVE_MESSAGE: pstats->mstats.igmp_leaves[dir]++; break; } break; #if IS_ENABLED(CONFIG_IPV6) case htons(ETH_P_IPV6): t_len = ntohs(ipv6_hdr(skb)->payload_len) + sizeof(struct ipv6hdr); t_len -= skb_network_header_len(skb); switch (type) { case ICMPV6_MGM_REPORT: pstats->mstats.mld_v1reports[dir]++; break; case ICMPV6_MLD2_REPORT: pstats->mstats.mld_v2reports[dir]++; break; case ICMPV6_MGM_QUERY: if (t_len != sizeof(struct mld_msg)) pstats->mstats.mld_v2queries[dir]++; else pstats->mstats.mld_v1queries[dir]++; break; case ICMPV6_MGM_REDUCTION: pstats->mstats.mld_leaves[dir]++; break; } break; #endif /* CONFIG_IPV6 */ } u64_stats_update_end(&pstats->syncp); } void br_multicast_count(struct net_bridge *br, const struct net_bridge_port *p, const struct sk_buff *skb, u8 type, u8 dir) { struct bridge_mcast_stats __percpu *stats; /* if multicast_disabled is true then igmp type can't be set */ if (!type || !br_opt_get(br, BROPT_MULTICAST_STATS_ENABLED)) return; if (p) stats = p->mcast_stats; else stats = br->mcast_stats; if (WARN_ON(!stats)) return; br_mcast_stats_add(stats, skb, type, dir); } int br_multicast_init_stats(struct net_bridge *br) { br->mcast_stats = netdev_alloc_pcpu_stats(struct bridge_mcast_stats); if (!br->mcast_stats) return -ENOMEM; return 0; } void br_multicast_uninit_stats(struct net_bridge *br) { free_percpu(br->mcast_stats); } /* noinline for https://llvm.org/pr45802#c9 */ static noinline_for_stack void mcast_stats_add_dir(u64 *dst, u64 *src) { dst[BR_MCAST_DIR_RX] += src[BR_MCAST_DIR_RX]; dst[BR_MCAST_DIR_TX] += src[BR_MCAST_DIR_TX]; } void br_multicast_get_stats(const struct net_bridge *br, const struct net_bridge_port *p, struct br_mcast_stats *dest) { struct bridge_mcast_stats __percpu *stats; struct br_mcast_stats tdst; int i; memset(dest, 0, sizeof(*dest)); if (p) stats = p->mcast_stats; else stats = br->mcast_stats; if (WARN_ON(!stats)) return; memset(&tdst, 0, sizeof(tdst)); for_each_possible_cpu(i) { struct bridge_mcast_stats *cpu_stats = per_cpu_ptr(stats, i); struct br_mcast_stats temp; unsigned int start; do { start = u64_stats_fetch_begin(&cpu_stats->syncp); memcpy(&temp, &cpu_stats->mstats, sizeof(temp)); } while (u64_stats_fetch_retry(&cpu_stats->syncp, start)); mcast_stats_add_dir(tdst.igmp_v1queries, temp.igmp_v1queries); mcast_stats_add_dir(tdst.igmp_v2queries, temp.igmp_v2queries); mcast_stats_add_dir(tdst.igmp_v3queries, temp.igmp_v3queries); mcast_stats_add_dir(tdst.igmp_leaves, temp.igmp_leaves); mcast_stats_add_dir(tdst.igmp_v1reports, temp.igmp_v1reports); mcast_stats_add_dir(tdst.igmp_v2reports, temp.igmp_v2reports); mcast_stats_add_dir(tdst.igmp_v3reports, temp.igmp_v3reports); tdst.igmp_parse_errors += temp.igmp_parse_errors; mcast_stats_add_dir(tdst.mld_v1queries, temp.mld_v1queries); mcast_stats_add_dir(tdst.mld_v2queries, temp.mld_v2queries); mcast_stats_add_dir(tdst.mld_leaves, temp.mld_leaves); mcast_stats_add_dir(tdst.mld_v1reports, temp.mld_v1reports); mcast_stats_add_dir(tdst.mld_v2reports, temp.mld_v2reports); tdst.mld_parse_errors += temp.mld_parse_errors; } memcpy(dest, &tdst, sizeof(*dest)); } int br_mdb_hash_init(struct net_bridge *br) { int err; err = rhashtable_init(&br->sg_port_tbl, &br_sg_port_rht_params); if (err) return err; err = rhashtable_init(&br->mdb_hash_tbl, &br_mdb_rht_params); if (err) { rhashtable_destroy(&br->sg_port_tbl); return err; } return 0; } void br_mdb_hash_fini(struct net_bridge *br) { rhashtable_destroy(&br->sg_port_tbl); rhashtable_destroy(&br->mdb_hash_tbl); } |
| 9 3 1 6 9 9 9 9 9 9 9 9 9 9 9 15 3 15 15 15 5 5 5 3 12 12 11 11 11 11 11 11 11 9 9 9 9 9 5 5 9 2 9 8 9 9 9 9 6 9 9 9 9 9 5 9 9 9 9 1 6 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* RxRPC recvmsg() implementation * * Copyright (C) 2007 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) */ #de |