Loading...
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 | // SPDX-License-Identifier: GPL-2.0 /* * Setup routines for AGP 3.5 compliant bridges. */ #include <linux/list.h> #include <linux/pci.h> #include <linux/agp_backend.h> #include <linux/module.h> #include <linux/slab.h> #include "agp.h" /* Generic AGP 3.5 enabling routines */ struct agp_3_5_dev { struct list_head list; u8 capndx; u32 maxbw; struct pci_dev *dev; }; static void agp_3_5_dev_list_insert(struct list_head *head, struct list_head *new) { struct agp_3_5_dev *cur, *n = list_entry(new, struct agp_3_5_dev, list); struct list_head *pos; list_for_each(pos, head) { cur = list_entry(pos, struct agp_3_5_dev, list); if (cur->maxbw > n->maxbw) break; } list_add_tail(new, pos); } static void agp_3_5_dev_list_sort(struct agp_3_5_dev *list, unsigned int ndevs) { struct agp_3_5_dev *cur; struct pci_dev *dev; struct list_head *pos, *tmp, *head = &list->list, *start = head->next; u32 nistat; INIT_LIST_HEAD(head); for (pos=start; pos!=head; ) { cur = list_entry(pos, struct agp_3_5_dev, list); dev = cur->dev; pci_read_config_dword(dev, cur->capndx+AGPNISTAT, &nistat); cur->maxbw = (nistat >> 16) & 0xff; tmp = pos; pos = pos->next; agp_3_5_dev_list_insert(head, tmp); } } /* * Initialize all isochronous transfer parameters for an AGP 3.0 * node (i.e. a host bridge in combination with the adapters * lying behind it...) */ static int agp_3_5_isochronous_node_enable(struct agp_bridge_data *bridge, struct agp_3_5_dev *dev_list, unsigned int ndevs) { /* * Convenience structure to make the calculations clearer * here. The field names come straight from the AGP 3.0 spec. */ struct isoch_data { u32 maxbw; u32 n; u32 y; u32 l; u32 rq; struct agp_3_5_dev *dev; }; struct pci_dev *td = bridge->dev, *dev; struct list_head *head = &dev_list->list, *pos; struct agp_3_5_dev *cur; struct isoch_data *master, target; unsigned int cdev = 0; u32 mnistat, tnistat, tstatus, mcmd; u16 tnicmd, mnicmd; u8 mcapndx; u32 tot_bw = 0, tot_n = 0, tot_rq = 0, y_max, rq_isoch, rq_async; u32 step, rem, rem_isoch, rem_async; int ret = 0; /* * We'll work with an array of isoch_data's (one for each * device in dev_list) throughout this function. */ if ((master = kmalloc(ndevs * sizeof(*master), GFP_KERNEL)) == NULL) { ret = -ENOMEM; goto get_out; } /* * Sort the device list by maxbw. We need to do this because the * spec suggests that the devices with the smallest requirements * have their resources allocated first, with all remaining resources * falling to the device with the largest requirement. * * We don't exactly do this, we divide target resources by ndevs * and split them amongst the AGP 3.0 devices. The remainder of such * division operations are dropped on the last device, sort of like * the spec mentions it should be done. * * We can't do this sort when we initially construct the dev_list * because we don't know until this function whether isochronous * transfers are enabled and consequently whether maxbw will mean * anything. */ agp_3_5_dev_list_sort(dev_list, ndevs); pci_read_config_dword(td, bridge->capndx+AGPNISTAT, &tnistat); pci_read_config_dword(td, bridge->capndx+AGPSTAT, &tstatus); /* Extract power-on defaults from the target */ target.maxbw = (tnistat >> 16) & 0xff; target.n = (tnistat >> 8) & 0xff; target.y = (tnistat >> 6) & 0x3; target.l = (tnistat >> 3) & 0x7; target.rq = (tstatus >> 24) & 0xff; y_max = target.y; /* * Extract power-on defaults for each device in dev_list. Along * the way, calculate the total isochronous bandwidth required * by these devices and the largest requested payload size. */ list_for_each(pos, head) { cur = list_entry(pos, struct agp_3_5_dev, list); dev = cur->dev; mcapndx = cur->capndx; pci_read_config_dword(dev, cur->capndx+AGPNISTAT, &mnistat); master[cdev].maxbw = (mnistat >> 16) & 0xff; master[cdev].n = (mnistat >> 8) & 0xff; master[cdev].y = (mnistat >> 6) & 0x3; master[cdev].dev = cur; tot_bw += master[cdev].maxbw; y_max = max(y_max, master[cdev].y); cdev++; } /* Check if this configuration has any chance of working */ if (tot_bw > target.maxbw) { dev_err(&td->dev, "isochronous bandwidth required " "by AGP 3.0 devices exceeds that which is supported by " "the AGP 3.0 bridge!\n"); ret = -ENODEV; goto free_and_exit; } target.y = y_max; /* * Write the calculated payload size into the target's NICMD * register. Doing this directly effects the ISOCH_N value * in the target's NISTAT register, so we need to do this now * to get an accurate value for ISOCH_N later. */ pci_read_config_word(td, bridge->capndx+AGPNICMD, &tnicmd); tnicmd &= ~(0x3 << 6); tnicmd |= target.y << 6; pci_write_config_word(td, bridge->capndx+AGPNICMD, tnicmd); /* Reread the target's ISOCH_N */ pci_read_config_dword(td, bridge->capndx+AGPNISTAT, &tnistat); target.n = (tnistat >> 8) & 0xff; /* Calculate the minimum ISOCH_N needed by each master */ for (cdev=0; cdev<ndevs; cdev++) { master[cdev].y = target.y; master[cdev].n = master[cdev].maxbw / (master[cdev].y + 1); tot_n += master[cdev].n; } /* Exit if the minimal ISOCH_N allocation among the masters is more * than the target can handle. */ if (tot_n > target.n) { dev_err(&td->dev, "number of isochronous " "transactions per period required by AGP 3.0 devices " "exceeds that which is supported by the AGP 3.0 " "bridge!\n"); ret = -ENODEV; goto free_and_exit; } /* Calculate left over ISOCH_N capability in the target. We'll give * this to the hungriest device (as per the spec) */ rem = target.n - tot_n; /* * Calculate the minimum isochronous RQ depth needed by each master. * Along the way, distribute the extra ISOCH_N capability calculated * above. */ for (cdev=0; cdev<ndevs; cdev++) { /* * This is a little subtle. If ISOCH_Y > 64B, then ISOCH_Y * byte isochronous writes will be broken into 64B pieces. * This means we need to budget more RQ depth to account for * these kind of writes (each isochronous write is actually * many writes on the AGP bus). */ master[cdev].rq = master[cdev].n; if (master[cdev].y > 0x1) master[cdev].rq *= (1 << (master[cdev].y - 1)); tot_rq += master[cdev].rq; } master[ndevs-1].n += rem; /* Figure the number of isochronous and asynchronous RQ slots the * target is providing. */ rq_isoch = (target.y > 0x1) ? target.n * (1 << (target.y - 1)) : target.n; rq_async = target.rq - rq_isoch; /* Exit if the minimal RQ needs of the masters exceeds what the target * can provide. */ if (tot_rq > rq_isoch) { dev_err(&td->dev, "number of request queue slots " "required by the isochronous bandwidth requested by " "AGP 3.0 devices exceeds the number provided by the " "AGP 3.0 bridge!\n"); ret = -ENODEV; goto free_and_exit; } /* Calculate asynchronous RQ capability in the target (per master) as * well as the total number of leftover isochronous RQ slots. */ step = rq_async / ndevs; rem_async = step + (rq_async % ndevs); rem_isoch = rq_isoch - tot_rq; /* Distribute the extra RQ slots calculated above and write our * isochronous settings out to the actual devices. */ for (cdev=0; cdev<ndevs; cdev++) { cur = master[cdev].dev; dev = cur->dev; mcapndx = cur->capndx; master[cdev].rq += (cdev == ndevs - 1) ? (rem_async + rem_isoch) : step; pci_read_config_word(dev, cur->capndx+AGPNICMD, &mnicmd); pci_read_config_dword(dev, cur->capndx+AGPCMD, &mcmd); mnicmd &= ~(0xff << 8); mnicmd &= ~(0x3 << 6); mcmd &= ~(0xff << 24); mnicmd |= master[cdev].n << 8; mnicmd |= master[cdev].y << 6; mcmd |= master[cdev].rq << 24; pci_write_config_dword(dev, cur->capndx+AGPCMD, mcmd); pci_write_config_word(dev, cur->capndx+AGPNICMD, mnicmd); } free_and_exit: kfree(master); get_out: return ret; } /* * This function basically allocates request queue slots among the * AGP 3.0 systems in nonisochronous nodes. The algorithm is * pretty stupid, divide the total number of RQ slots provided by the * target by ndevs. Distribute this many slots to each AGP 3.0 device, * giving any left over slots to the last device in dev_list. */ static void agp_3_5_nonisochronous_node_enable(struct agp_bridge_data *bridge, struct agp_3_5_dev *dev_list, unsigned int ndevs) { struct agp_3_5_dev *cur; struct list_head *head = &dev_list->list, *pos; u32 tstatus, mcmd; u32 trq, mrq, rem; unsigned int cdev = 0; pci_read_config_dword(bridge->dev, bridge->capndx+AGPSTAT, &tstatus); trq = (tstatus >> 24) & 0xff; mrq = trq / ndevs; rem = mrq + (trq % ndevs); for (pos=head->next; cdev<ndevs; cdev++, pos=pos->next) { cur = list_entry(pos, struct agp_3_5_dev, list); pci_read_config_dword(cur->dev, cur->capndx+AGPCMD, &mcmd); mcmd &= ~(0xff << 24); mcmd |= ((cdev == ndevs - 1) ? rem : mrq) << 24; pci_write_config_dword(cur->dev, cur->capndx+AGPCMD, mcmd); } } /* * Fully configure and enable an AGP 3.0 host bridge and all the devices * lying behind it. */ int agp_3_5_enable(struct agp_bridge_data *bridge) { struct pci_dev *td = bridge->dev, *dev = NULL; u8 mcapndx; u32 isoch, arqsz; u32 tstatus, mstatus, ncapid; u32 mmajor; u16 mpstat; struct agp_3_5_dev *dev_list, *cur; struct list_head *head, *pos; unsigned int ndevs = 0; int ret = 0; /* Extract some power-on defaults from the target */ pci_read_config_dword(td, bridge->capndx+AGPSTAT, &tstatus); isoch = (tstatus >> 17) & 0x1; if (isoch == 0) /* isoch xfers not available, bail out. */ return -ENODEV; arqsz = (tstatus >> 13) & 0x7; /* * Allocate a head for our AGP 3.5 device list * (multiple AGP v3 devices are allowed behind a single bridge). */ if ((dev_list = kmalloc(sizeof(*dev_list), GFP_KERNEL)) == NULL) { ret = -ENOMEM; goto get_out; } head = &dev_list->list; INIT_LIST_HEAD(head); /* Find all AGP devices, and add them to dev_list. */ for_each_pci_dev(dev) { mcapndx = pci_find_capability(dev, PCI_CAP_ID_AGP); if (mcapndx == 0) continue; switch ((dev->class >>8) & 0xff00) { case 0x0600: /* Bridge */ /* Skip bridges. We should call this function for each one. */ continue; case 0x0001: /* Unclassified device */ /* Don't know what this is, but log it for investigation. */ if (mcapndx != 0) { dev_info(&td->dev, "wacky, found unclassified AGP device %s [%04x/%04x]\n", pci_name(dev), dev->vendor, dev->device); } continue; case 0x0300: /* Display controller */ case 0x0400: /* Multimedia controller */ if ((cur = kmalloc(sizeof(*cur), GFP_KERNEL)) == NULL) { ret = -ENOMEM; goto free_and_exit; } cur->dev = dev; pos = &cur->list; list_add(pos, head); ndevs++; continue; default: continue; } } /* * Take an initial pass through the devices lying behind our host * bridge. Make sure each one is actually an AGP 3.0 device, otherwise * exit with an error message. Along the way store the AGP 3.0 * cap_ptr for each device */ list_for_each(pos, head) { cur = list_entry(pos, struct agp_3_5_dev, list); dev = cur->dev; pci_read_config_word(dev, PCI_STATUS, &mpstat); if ((mpstat & PCI_STATUS_CAP_LIST) == 0) continue; pci_read_config_byte(dev, PCI_CAPABILITY_LIST, &mcapndx); if (mcapndx != 0) { do { pci_read_config_dword(dev, mcapndx, &ncapid); if ((ncapid & 0xff) != 2) mcapndx = (ncapid >> 8) & 0xff; } while (((ncapid & 0xff) != 2) && (mcapndx != 0)); } if (mcapndx == 0) { dev_err(&td->dev, "woah! Non-AGP device %s on " "secondary bus of AGP 3.5 bridge!\n", pci_name(dev)); ret = -ENODEV; goto free_and_exit; } mmajor = (ncapid >> AGP_MAJOR_VERSION_SHIFT) & 0xf; if (mmajor < 3) { dev_err(&td->dev, "woah! AGP 2.0 device %s on " "secondary bus of AGP 3.5 bridge operating " "with AGP 3.0 electricals!\n", pci_name(dev)); ret = -ENODEV; goto free_and_exit; } cur->capndx = mcapndx; pci_read_config_dword(dev, cur->capndx+AGPSTAT, &mstatus); if (((mstatus >> 3) & 0x1) == 0) { dev_err(&td->dev, "woah! AGP 3.x device %s not " "operating in AGP 3.x mode on secondary bus " "of AGP 3.5 bridge operating with AGP 3.0 " "electricals!\n", pci_name(dev)); ret = -ENODEV; goto free_and_exit; } } /* * Call functions to divide target resources amongst the AGP 3.0 * masters. This process is dramatically different depending on * whether isochronous transfers are supported. */ if (isoch) { ret = agp_3_5_isochronous_node_enable(bridge, dev_list, ndevs); if (ret) { dev_info(&td->dev, "something bad happened setting " "up isochronous xfers; falling back to " "non-isochronous xfer mode\n"); } else { goto free_and_exit; } } agp_3_5_nonisochronous_node_enable(bridge, dev_list, ndevs); free_and_exit: /* Be sure to free the dev_list */ for (pos=head->next; pos!=head; ) { cur = list_entry(pos, struct agp_3_5_dev, list); pos = pos->next; kfree(cur); } kfree(dev_list); get_out: return ret; } |