Cliff Wickman | 1812924 | 2008-06-02 08:56:14 -0500 | [diff] [blame^] | 1 | /* |
| 2 | * SGI UltraViolet TLB flush routines. |
| 3 | * |
| 4 | * (c) 2008 Cliff Wickman <cpw@sgi.com>, SGI. |
| 5 | * |
| 6 | * This code is released under the GNU General Public License version 2 or |
| 7 | * later. |
| 8 | */ |
| 9 | #include <linux/mc146818rtc.h> |
| 10 | #include <linux/proc_fs.h> |
| 11 | #include <linux/kernel.h> |
| 12 | |
| 13 | #include <asm/mach-bigsmp/mach_apic.h> |
| 14 | #include <asm/mmu_context.h> |
| 15 | #include <asm/idle.h> |
| 16 | #include <asm/genapic.h> |
| 17 | #include <asm/uv/uv_hub.h> |
| 18 | #include <asm/uv/uv_mmrs.h> |
| 19 | #include <asm/uv/uv_bau.h> |
| 20 | |
| 21 | struct bau_control **uv_bau_table_bases; |
| 22 | static int uv_bau_retry_limit; |
| 23 | static int uv_nshift; /* position of pnode (which is nasid>>1) */ |
| 24 | static unsigned long uv_mmask; |
| 25 | |
| 26 | char *status_table[] = { |
| 27 | "IDLE", |
| 28 | "ACTIVE", |
| 29 | "DESTINATION TIMEOUT", |
| 30 | "SOURCE TIMEOUT" |
| 31 | }; |
| 32 | |
| 33 | DEFINE_PER_CPU(struct ptc_stats, ptcstats); |
| 34 | DEFINE_PER_CPU(struct bau_control, bau_control); |
| 35 | |
| 36 | /* |
| 37 | * Free a software acknowledge hardware resource by clearing its Pending |
| 38 | * bit. This will return a reply to the sender. |
| 39 | * If the message has timed out, a reply has already been sent by the |
| 40 | * hardware but the resource has not been released. In that case our |
| 41 | * clear of the Timeout bit (as well) will free the resource. No reply will |
| 42 | * be sent (the hardware will only do one reply per message). |
| 43 | */ |
| 44 | static void |
| 45 | uv_reply_to_message(int resource, |
| 46 | struct bau_payload_queue_entry *msg, |
| 47 | struct bau_msg_status *msp) |
| 48 | { |
| 49 | int fw; |
| 50 | |
| 51 | fw = (1 << (resource + UV_SW_ACK_NPENDING)) | (1 << resource); |
| 52 | msg->replied_to = 1; |
| 53 | msg->sw_ack_vector = 0; |
| 54 | if (msp) |
| 55 | msp->seen_by.bits = 0; |
| 56 | uv_write_local_mmr(UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_ALIAS, fw); |
| 57 | return; |
| 58 | } |
| 59 | |
| 60 | /* |
| 61 | * Do all the things a cpu should do for a TLB shootdown message. |
| 62 | * Other cpu's may come here at the same time for this message. |
| 63 | */ |
| 64 | static void |
| 65 | uv_bau_process_message(struct bau_payload_queue_entry *msg, |
| 66 | int msg_slot, int sw_ack_slot) |
| 67 | { |
| 68 | int cpu; |
| 69 | unsigned long this_cpu_mask; |
| 70 | struct bau_msg_status *msp; |
| 71 | |
| 72 | msp = __get_cpu_var(bau_control).msg_statuses + msg_slot; |
| 73 | cpu = uv_blade_processor_id(); |
| 74 | msg->number_of_cpus = |
| 75 | uv_blade_nr_online_cpus(uv_node_to_blade_id(numa_node_id())); |
| 76 | this_cpu_mask = (unsigned long)1 << cpu; |
| 77 | if (msp->seen_by.bits & this_cpu_mask) |
| 78 | return; |
| 79 | atomic_or_long(&msp->seen_by.bits, this_cpu_mask); |
| 80 | |
| 81 | if (msg->replied_to == 1) |
| 82 | return; |
| 83 | |
| 84 | if (msg->address == TLB_FLUSH_ALL) { |
| 85 | local_flush_tlb(); |
| 86 | __get_cpu_var(ptcstats).alltlb++; |
| 87 | } else { |
| 88 | __flush_tlb_one(msg->address); |
| 89 | __get_cpu_var(ptcstats).onetlb++; |
| 90 | } |
| 91 | |
| 92 | __get_cpu_var(ptcstats).requestee++; |
| 93 | |
| 94 | atomic_inc_short(&msg->acknowledge_count); |
| 95 | if (msg->number_of_cpus == msg->acknowledge_count) |
| 96 | uv_reply_to_message(sw_ack_slot, msg, msp); |
| 97 | return; |
| 98 | } |
| 99 | |
| 100 | /* |
| 101 | * Examine the payload queue on all the distribution nodes to see |
| 102 | * which messages have not been seen, and which cpu(s) have not seen them. |
| 103 | * |
| 104 | * Returns the number of cpu's that have not responded. |
| 105 | */ |
| 106 | static int |
| 107 | uv_examine_destinations(struct bau_target_nodemask *distribution) |
| 108 | { |
| 109 | int sender; |
| 110 | int i; |
| 111 | int j; |
| 112 | int k; |
| 113 | int count = 0; |
| 114 | struct bau_control *bau_tablesp; |
| 115 | struct bau_payload_queue_entry *msg; |
| 116 | struct bau_msg_status *msp; |
| 117 | |
| 118 | sender = smp_processor_id(); |
| 119 | for (i = 0; i < (sizeof(struct bau_target_nodemask) * BITSPERBYTE); |
| 120 | i++) { |
| 121 | if (bau_node_isset(i, distribution)) { |
| 122 | bau_tablesp = uv_bau_table_bases[i]; |
| 123 | for (msg = bau_tablesp->va_queue_first, j = 0; |
| 124 | j < DESTINATION_PAYLOAD_QUEUE_SIZE; msg++, j++) { |
| 125 | if ((msg->sending_cpu == sender) && |
| 126 | (!msg->replied_to)) { |
| 127 | msp = bau_tablesp->msg_statuses + j; |
| 128 | printk(KERN_DEBUG |
| 129 | "blade %d: address:%#lx %d of %d, not cpu(s): ", |
| 130 | i, msg->address, |
| 131 | msg->acknowledge_count, |
| 132 | msg->number_of_cpus); |
| 133 | for (k = 0; k < msg->number_of_cpus; |
| 134 | k++) { |
| 135 | if (!((long)1 << k & msp-> |
| 136 | seen_by.bits)) { |
| 137 | count++; |
| 138 | printk("%d ", k); |
| 139 | } |
| 140 | } |
| 141 | printk("\n"); |
| 142 | } |
| 143 | } |
| 144 | } |
| 145 | } |
| 146 | return count; |
| 147 | } |
| 148 | |
| 149 | /** |
| 150 | * uv_flush_tlb_others - globally purge translation cache of a virtual |
| 151 | * address or all TLB's |
| 152 | * @cpumaskp: mask of all cpu's in which the address is to be removed |
| 153 | * @mm: mm_struct containing virtual address range |
| 154 | * @va: virtual address to be removed (or TLB_FLUSH_ALL for all TLB's on cpu) |
| 155 | * |
| 156 | * This is the entry point for initiating any UV global TLB shootdown. |
| 157 | * |
| 158 | * Purges the translation caches of all specified processors of the given |
| 159 | * virtual address, or purges all TLB's on specified processors. |
| 160 | * |
| 161 | * The caller has derived the cpumaskp from the mm_struct and has subtracted |
| 162 | * the local cpu from the mask. This function is called only if there |
| 163 | * are bits set in the mask. (e.g. flush_tlb_page()) |
| 164 | * |
| 165 | * The cpumaskp is converted into a nodemask of the nodes containing |
| 166 | * the cpus. |
| 167 | */ |
| 168 | int |
| 169 | uv_flush_tlb_others(cpumask_t *cpumaskp, struct mm_struct *mm, unsigned long va) |
| 170 | { |
| 171 | int i; |
| 172 | int blade; |
| 173 | int cpu; |
| 174 | int bit; |
| 175 | int right_shift; |
| 176 | int this_blade; |
| 177 | int exams = 0; |
| 178 | int tries = 0; |
| 179 | long source_timeouts = 0; |
| 180 | long destination_timeouts = 0; |
| 181 | unsigned long index; |
| 182 | unsigned long mmr_offset; |
| 183 | unsigned long descriptor_status; |
| 184 | struct bau_activation_descriptor *bau_desc; |
| 185 | ktime_t time1, time2; |
| 186 | |
| 187 | cpu = uv_blade_processor_id(); |
| 188 | this_blade = uv_numa_blade_id(); |
| 189 | bau_desc = __get_cpu_var(bau_control).descriptor_base; |
| 190 | bau_desc += (UV_ITEMS_PER_DESCRIPTOR * cpu); |
| 191 | |
| 192 | bau_nodes_clear(&bau_desc->distribution, UV_DISTRIBUTION_SIZE); |
| 193 | |
| 194 | i = 0; |
| 195 | for_each_cpu_mask(bit, *cpumaskp) { |
| 196 | blade = uv_cpu_to_blade_id(bit); |
| 197 | if (blade > (UV_DISTRIBUTION_SIZE - 1)) |
| 198 | BUG(); |
| 199 | if (blade == this_blade) |
| 200 | continue; |
| 201 | bau_node_set(blade, &bau_desc->distribution); |
| 202 | /* leave the bits for the remote cpu's in the mask until |
| 203 | success; on failure we fall back to the IPI method */ |
| 204 | i++; |
| 205 | } |
| 206 | if (i == 0) |
| 207 | goto none_to_flush; |
| 208 | __get_cpu_var(ptcstats).requestor++; |
| 209 | __get_cpu_var(ptcstats).ntargeted += i; |
| 210 | |
| 211 | bau_desc->payload.address = va; |
| 212 | bau_desc->payload.sending_cpu = smp_processor_id(); |
| 213 | |
| 214 | if (cpu < UV_CPUS_PER_ACT_STATUS) { |
| 215 | mmr_offset = UVH_LB_BAU_SB_ACTIVATION_STATUS_0; |
| 216 | right_shift = cpu * UV_ACT_STATUS_SIZE; |
| 217 | } else { |
| 218 | mmr_offset = UVH_LB_BAU_SB_ACTIVATION_STATUS_1; |
| 219 | right_shift = |
| 220 | ((cpu - UV_CPUS_PER_ACT_STATUS) * UV_ACT_STATUS_SIZE); |
| 221 | } |
| 222 | time1 = ktime_get(); |
| 223 | |
| 224 | retry: |
| 225 | tries++; |
| 226 | index = ((unsigned long) |
| 227 | 1 << UVH_LB_BAU_SB_ACTIVATION_CONTROL_PUSH_SHFT) | cpu; |
| 228 | uv_write_local_mmr(UVH_LB_BAU_SB_ACTIVATION_CONTROL, index); |
| 229 | |
| 230 | while ((descriptor_status = (((unsigned long) |
| 231 | uv_read_local_mmr(mmr_offset) >> |
| 232 | right_shift) & UV_ACT_STATUS_MASK)) != |
| 233 | DESC_STATUS_IDLE) { |
| 234 | if (descriptor_status == DESC_STATUS_SOURCE_TIMEOUT) { |
| 235 | source_timeouts++; |
| 236 | if (source_timeouts > SOURCE_TIMEOUT_LIMIT) |
| 237 | source_timeouts = 0; |
| 238 | __get_cpu_var(ptcstats).s_retry++; |
| 239 | goto retry; |
| 240 | } |
| 241 | /* spin here looking for progress at the destinations */ |
| 242 | if (descriptor_status == DESC_STATUS_DESTINATION_TIMEOUT) { |
| 243 | destination_timeouts++; |
| 244 | if (destination_timeouts > DESTINATION_TIMEOUT_LIMIT) { |
| 245 | /* returns # of cpus not responding */ |
| 246 | if (uv_examine_destinations |
| 247 | (&bau_desc->distribution) == 0) { |
| 248 | __get_cpu_var(ptcstats).d_retry++; |
| 249 | goto retry; |
| 250 | } |
| 251 | exams++; |
| 252 | if (exams >= uv_bau_retry_limit) { |
| 253 | printk(KERN_DEBUG |
| 254 | "uv_flush_tlb_others"); |
| 255 | printk("giving up on cpu %d\n", |
| 256 | smp_processor_id()); |
| 257 | goto unsuccessful; |
| 258 | } |
| 259 | /* delays can hang up the simulator |
| 260 | udelay(1000); |
| 261 | */ |
| 262 | destination_timeouts = 0; |
| 263 | } |
| 264 | } |
| 265 | } |
| 266 | if (tries > 1) |
| 267 | __get_cpu_var(ptcstats).retriesok++; |
| 268 | /* on success, clear the remote cpu's from the mask so we don't |
| 269 | use the IPI method of shootdown on them */ |
| 270 | for_each_cpu_mask(bit, *cpumaskp) { |
| 271 | blade = uv_cpu_to_blade_id(bit); |
| 272 | if (blade == this_blade) |
| 273 | continue; |
| 274 | cpu_clear(bit, *cpumaskp); |
| 275 | } |
| 276 | |
| 277 | unsuccessful: |
| 278 | time2 = ktime_get(); |
| 279 | __get_cpu_var(ptcstats).sflush_ns += (time2.tv64 - time1.tv64); |
| 280 | |
| 281 | none_to_flush: |
| 282 | if (cpus_empty(*cpumaskp)) |
| 283 | return 1; |
| 284 | |
| 285 | /* Cause the caller to do an IPI-style TLB shootdown on |
| 286 | the cpu's still in the mask */ |
| 287 | __get_cpu_var(ptcstats).ptc_i++; |
| 288 | return 0; |
| 289 | } |
| 290 | |
| 291 | /* |
| 292 | * The BAU message interrupt comes here. (registered by set_intr_gate) |
| 293 | * See entry_64.S |
| 294 | * |
| 295 | * We received a broadcast assist message. |
| 296 | * |
| 297 | * Interrupts may have been disabled; this interrupt could represent |
| 298 | * the receipt of several messages. |
| 299 | * |
| 300 | * All cores/threads on this node get this interrupt. |
| 301 | * The last one to see it does the s/w ack. |
| 302 | * (the resource will not be freed until noninterruptable cpus see this |
| 303 | * interrupt; hardware will timeout the s/w ack and reply ERROR) |
| 304 | */ |
| 305 | void |
| 306 | uv_bau_message_interrupt(struct pt_regs *regs) |
| 307 | { |
| 308 | struct bau_payload_queue_entry *pqp; |
| 309 | struct bau_payload_queue_entry *msg; |
| 310 | struct pt_regs *old_regs = set_irq_regs(regs); |
| 311 | ktime_t time1, time2; |
| 312 | int msg_slot; |
| 313 | int sw_ack_slot; |
| 314 | int fw; |
| 315 | int count = 0; |
| 316 | unsigned long local_pnode; |
| 317 | |
| 318 | ack_APIC_irq(); |
| 319 | exit_idle(); |
| 320 | irq_enter(); |
| 321 | |
| 322 | time1 = ktime_get(); |
| 323 | |
| 324 | local_pnode = uv_blade_to_pnode(uv_numa_blade_id()); |
| 325 | |
| 326 | pqp = __get_cpu_var(bau_control).va_queue_first; |
| 327 | msg = __get_cpu_var(bau_control).bau_msg_head; |
| 328 | while (msg->sw_ack_vector) { |
| 329 | count++; |
| 330 | fw = msg->sw_ack_vector; |
| 331 | msg_slot = msg - pqp; |
| 332 | sw_ack_slot = ffs(fw) - 1; |
| 333 | |
| 334 | uv_bau_process_message(msg, msg_slot, sw_ack_slot); |
| 335 | |
| 336 | msg++; |
| 337 | if (msg > __get_cpu_var(bau_control).va_queue_last) |
| 338 | msg = __get_cpu_var(bau_control).va_queue_first; |
| 339 | __get_cpu_var(bau_control).bau_msg_head = msg; |
| 340 | } |
| 341 | if (!count) |
| 342 | __get_cpu_var(ptcstats).nomsg++; |
| 343 | else if (count > 1) |
| 344 | __get_cpu_var(ptcstats).multmsg++; |
| 345 | |
| 346 | time2 = ktime_get(); |
| 347 | __get_cpu_var(ptcstats).dflush_ns += (time2.tv64 - time1.tv64); |
| 348 | |
| 349 | irq_exit(); |
| 350 | set_irq_regs(old_regs); |
| 351 | return; |
| 352 | } |
| 353 | |
| 354 | static void |
| 355 | uv_enable_timeouts(void) |
| 356 | { |
| 357 | int i; |
| 358 | int blade; |
| 359 | int last_blade; |
| 360 | int pnode; |
| 361 | int cur_cpu = 0; |
| 362 | unsigned long apicid; |
| 363 | |
| 364 | /* better if we had each_online_blade */ |
| 365 | last_blade = -1; |
| 366 | for_each_online_node(i) { |
| 367 | blade = uv_node_to_blade_id(i); |
| 368 | if (blade == last_blade) |
| 369 | continue; |
| 370 | last_blade = blade; |
| 371 | apicid = per_cpu(x86_cpu_to_apicid, cur_cpu); |
| 372 | pnode = uv_blade_to_pnode(blade); |
| 373 | cur_cpu += uv_blade_nr_possible_cpus(i); |
| 374 | } |
| 375 | return; |
| 376 | } |
| 377 | |
| 378 | static void * |
| 379 | uv_ptc_seq_start(struct seq_file *file, loff_t *offset) |
| 380 | { |
| 381 | if (*offset < num_possible_cpus()) |
| 382 | return offset; |
| 383 | return NULL; |
| 384 | } |
| 385 | |
| 386 | static void * |
| 387 | uv_ptc_seq_next(struct seq_file *file, void *data, loff_t *offset) |
| 388 | { |
| 389 | (*offset)++; |
| 390 | if (*offset < num_possible_cpus()) |
| 391 | return offset; |
| 392 | return NULL; |
| 393 | } |
| 394 | |
| 395 | static void |
| 396 | uv_ptc_seq_stop(struct seq_file *file, void *data) |
| 397 | { |
| 398 | } |
| 399 | |
| 400 | /* |
| 401 | * Display the statistics thru /proc |
| 402 | * data points to the cpu number |
| 403 | */ |
| 404 | static int |
| 405 | uv_ptc_seq_show(struct seq_file *file, void *data) |
| 406 | { |
| 407 | struct ptc_stats *stat; |
| 408 | int cpu; |
| 409 | |
| 410 | cpu = *(loff_t *)data; |
| 411 | |
| 412 | if (!cpu) { |
| 413 | seq_printf(file, |
| 414 | "# cpu requestor requestee one all sretry dretry ptc_i "); |
| 415 | seq_printf(file, |
| 416 | "sw_ack sflush_us dflush_us sok dnomsg dmult starget\n"); |
| 417 | } |
| 418 | if (cpu < num_possible_cpus() && cpu_online(cpu)) { |
| 419 | stat = &per_cpu(ptcstats, cpu); |
| 420 | seq_printf(file, "cpu %d %ld %ld %ld %ld %ld %ld %ld ", |
| 421 | cpu, stat->requestor, |
| 422 | stat->requestee, stat->onetlb, stat->alltlb, |
| 423 | stat->s_retry, stat->d_retry, stat->ptc_i); |
| 424 | seq_printf(file, "%lx %ld %ld %ld %ld %ld %ld\n", |
| 425 | uv_read_global_mmr64(uv_blade_to_pnode |
| 426 | (uv_cpu_to_blade_id(cpu)), |
| 427 | UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE), |
| 428 | stat->sflush_ns / 1000, stat->dflush_ns / 1000, |
| 429 | stat->retriesok, stat->nomsg, |
| 430 | stat->multmsg, stat->ntargeted); |
| 431 | } |
| 432 | |
| 433 | return 0; |
| 434 | } |
| 435 | |
| 436 | /* |
| 437 | * 0: display meaning of the statistics |
| 438 | * >0: retry limit |
| 439 | */ |
| 440 | static ssize_t |
| 441 | uv_ptc_proc_write(struct file *file, const char __user *user, |
| 442 | size_t count, loff_t *data) |
| 443 | { |
| 444 | long newmode; |
| 445 | char optstr[64]; |
| 446 | |
| 447 | if (copy_from_user(optstr, user, count)) |
| 448 | return -EFAULT; |
| 449 | optstr[count - 1] = '\0'; |
| 450 | if (strict_strtoul(optstr, 10, &newmode) < 0) { |
| 451 | printk(KERN_DEBUG "%s is invalid\n", optstr); |
| 452 | return -EINVAL; |
| 453 | } |
| 454 | |
| 455 | if (newmode == 0) { |
| 456 | printk(KERN_DEBUG "# cpu: cpu number\n"); |
| 457 | printk(KERN_DEBUG |
| 458 | "requestor: times this cpu was the flush requestor\n"); |
| 459 | printk(KERN_DEBUG |
| 460 | "requestee: times this cpu was requested to flush its TLBs\n"); |
| 461 | printk(KERN_DEBUG |
| 462 | "one: times requested to flush a single address\n"); |
| 463 | printk(KERN_DEBUG |
| 464 | "all: times requested to flush all TLB's\n"); |
| 465 | printk(KERN_DEBUG |
| 466 | "sretry: number of retries of source-side timeouts\n"); |
| 467 | printk(KERN_DEBUG |
| 468 | "dretry: number of retries of destination-side timeouts\n"); |
| 469 | printk(KERN_DEBUG |
| 470 | "ptc_i: times UV fell through to IPI-style flushes\n"); |
| 471 | printk(KERN_DEBUG |
| 472 | "sw_ack: image of UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE\n"); |
| 473 | printk(KERN_DEBUG |
| 474 | "sflush_us: microseconds spent in uv_flush_tlb_others()\n"); |
| 475 | printk(KERN_DEBUG |
| 476 | "dflush_us: microseconds spent in handling flush requests\n"); |
| 477 | printk(KERN_DEBUG "sok: successes on retry\n"); |
| 478 | printk(KERN_DEBUG "dnomsg: interrupts with no message\n"); |
| 479 | printk(KERN_DEBUG |
| 480 | "dmult: interrupts with multiple messages\n"); |
| 481 | printk(KERN_DEBUG "starget: nodes targeted\n"); |
| 482 | } else { |
| 483 | uv_bau_retry_limit = newmode; |
| 484 | printk(KERN_DEBUG "timeout retry limit:%d\n", |
| 485 | uv_bau_retry_limit); |
| 486 | } |
| 487 | |
| 488 | return count; |
| 489 | } |
| 490 | |
| 491 | static const struct seq_operations uv_ptc_seq_ops = { |
| 492 | .start = uv_ptc_seq_start, |
| 493 | .next = uv_ptc_seq_next, |
| 494 | .stop = uv_ptc_seq_stop, |
| 495 | .show = uv_ptc_seq_show |
| 496 | }; |
| 497 | |
| 498 | static int |
| 499 | uv_ptc_proc_open(struct inode *inode, struct file *file) |
| 500 | { |
| 501 | return seq_open(file, &uv_ptc_seq_ops); |
| 502 | } |
| 503 | |
| 504 | static const struct file_operations proc_uv_ptc_operations = { |
| 505 | .open = uv_ptc_proc_open, |
| 506 | .read = seq_read, |
| 507 | .write = uv_ptc_proc_write, |
| 508 | .llseek = seq_lseek, |
| 509 | .release = seq_release, |
| 510 | }; |
| 511 | |
| 512 | static struct proc_dir_entry *proc_uv_ptc; |
| 513 | |
| 514 | static int __init |
| 515 | uv_ptc_init(void) |
| 516 | { |
| 517 | static struct proc_dir_entry *sgi_proc_dir; |
| 518 | |
| 519 | sgi_proc_dir = NULL; |
| 520 | |
| 521 | if (!is_uv_system()) |
| 522 | return 0; |
| 523 | |
| 524 | sgi_proc_dir = proc_mkdir("sgi_uv", NULL); |
| 525 | if (!sgi_proc_dir) |
| 526 | return -EINVAL; |
| 527 | |
| 528 | proc_uv_ptc = create_proc_entry(UV_PTC_BASENAME, 0444, NULL); |
| 529 | if (!proc_uv_ptc) { |
| 530 | printk(KERN_ERR "unable to create %s proc entry\n", |
| 531 | UV_PTC_BASENAME); |
| 532 | return -EINVAL; |
| 533 | } |
| 534 | proc_uv_ptc->proc_fops = &proc_uv_ptc_operations; |
| 535 | return 0; |
| 536 | } |
| 537 | |
| 538 | static void __exit |
| 539 | uv_ptc_exit(void) |
| 540 | { |
| 541 | remove_proc_entry(UV_PTC_BASENAME, NULL); |
| 542 | } |
| 543 | |
| 544 | module_init(uv_ptc_init); |
| 545 | module_exit(uv_ptc_exit); |
| 546 | |
| 547 | /* |
| 548 | * Initialization of BAU-related structures |
| 549 | */ |
| 550 | int __init |
| 551 | uv_bau_init(void) |
| 552 | { |
| 553 | int i; |
| 554 | int j; |
| 555 | int blade; |
| 556 | int nblades; |
| 557 | int *ip; |
| 558 | int pnode; |
| 559 | int last_blade; |
| 560 | int cur_cpu = 0; |
| 561 | unsigned long pa; |
| 562 | unsigned long n; |
| 563 | unsigned long m; |
| 564 | unsigned long mmr_image; |
| 565 | unsigned long apicid; |
| 566 | char *cp; |
| 567 | struct bau_control *bau_tablesp; |
| 568 | struct bau_activation_descriptor *adp, *ad2; |
| 569 | struct bau_payload_queue_entry *pqp; |
| 570 | struct bau_msg_status *msp; |
| 571 | struct bau_control *bcp; |
| 572 | |
| 573 | if (!is_uv_system()) |
| 574 | return 0; |
| 575 | |
| 576 | uv_bau_retry_limit = 1; |
| 577 | |
| 578 | if ((sizeof(struct bau_local_cpumask) * BITSPERBYTE) < |
| 579 | MAX_CPUS_PER_NODE) { |
| 580 | printk(KERN_ERR |
| 581 | "uv_bau_init: bau_local_cpumask.bits too small\n"); |
| 582 | BUG(); |
| 583 | } |
| 584 | |
| 585 | uv_nshift = uv_hub_info->n_val; |
| 586 | uv_mmask = ((unsigned long)1 << uv_hub_info->n_val) - 1; |
| 587 | nblades = 0; |
| 588 | last_blade = -1; |
| 589 | for_each_online_node(i) { |
| 590 | blade = uv_node_to_blade_id(i); |
| 591 | if (blade == last_blade) |
| 592 | continue; |
| 593 | last_blade = blade; |
| 594 | nblades++; |
| 595 | } |
| 596 | |
| 597 | uv_bau_table_bases = (struct bau_control **) |
| 598 | kmalloc(nblades * sizeof(struct bau_control *), GFP_KERNEL); |
| 599 | if (!uv_bau_table_bases) |
| 600 | BUG(); |
| 601 | |
| 602 | /* better if we had each_online_blade */ |
| 603 | last_blade = -1; |
| 604 | for_each_online_node(i) { |
| 605 | blade = uv_node_to_blade_id(i); |
| 606 | if (blade == last_blade) |
| 607 | continue; |
| 608 | last_blade = blade; |
| 609 | |
| 610 | bau_tablesp = |
| 611 | kmalloc_node(sizeof(struct bau_control), GFP_KERNEL, i); |
| 612 | if (!bau_tablesp) |
| 613 | BUG(); |
| 614 | |
| 615 | bau_tablesp->msg_statuses = |
| 616 | kmalloc_node(sizeof(struct bau_msg_status) * |
| 617 | DESTINATION_PAYLOAD_QUEUE_SIZE, GFP_KERNEL, i); |
| 618 | if (!bau_tablesp->msg_statuses) |
| 619 | BUG(); |
| 620 | for (j = 0, msp = bau_tablesp->msg_statuses; |
| 621 | j < DESTINATION_PAYLOAD_QUEUE_SIZE; j++, msp++) { |
| 622 | bau_cpubits_clear(&msp->seen_by, (int) |
| 623 | uv_blade_nr_possible_cpus(blade)); |
| 624 | } |
| 625 | |
| 626 | bau_tablesp->watching = |
| 627 | kmalloc_node(sizeof(int) * DESTINATION_NUM_RESOURCES, |
| 628 | GFP_KERNEL, i); |
| 629 | if (!bau_tablesp->watching) |
| 630 | BUG(); |
| 631 | for (j = 0, ip = bau_tablesp->watching; |
| 632 | j < DESTINATION_PAYLOAD_QUEUE_SIZE; j++, ip++) { |
| 633 | *ip = 0; |
| 634 | } |
| 635 | |
| 636 | uv_bau_table_bases[i] = bau_tablesp; |
| 637 | |
| 638 | pnode = uv_blade_to_pnode(blade); |
| 639 | |
| 640 | if (sizeof(struct bau_activation_descriptor) != 64) |
| 641 | BUG(); |
| 642 | |
| 643 | adp = (struct bau_activation_descriptor *) |
| 644 | kmalloc_node(16384, GFP_KERNEL, i); |
| 645 | if (!adp) |
| 646 | BUG(); |
| 647 | if ((unsigned long)adp & 0xfff) |
| 648 | BUG(); |
| 649 | pa = __pa((unsigned long)adp); |
| 650 | n = pa >> uv_nshift; |
| 651 | m = pa & uv_mmask; |
| 652 | |
| 653 | mmr_image = uv_read_global_mmr64(pnode, |
| 654 | UVH_LB_BAU_SB_DESCRIPTOR_BASE); |
| 655 | if (mmr_image) |
| 656 | uv_write_global_mmr64(pnode, (unsigned long) |
| 657 | UVH_LB_BAU_SB_DESCRIPTOR_BASE, |
| 658 | (n << UV_DESC_BASE_PNODE_SHIFT | |
| 659 | m)); |
| 660 | for (j = 0, ad2 = adp; j < UV_ACTIVATION_DESCRIPTOR_SIZE; |
| 661 | j++, ad2++) { |
| 662 | memset(ad2, 0, |
| 663 | sizeof(struct bau_activation_descriptor)); |
| 664 | ad2->header.sw_ack_flag = 1; |
| 665 | ad2->header.base_dest_nodeid = |
| 666 | uv_blade_to_pnode(uv_cpu_to_blade_id(0)); |
| 667 | ad2->header.command = UV_NET_ENDPOINT_INTD; |
| 668 | ad2->header.int_both = 1; |
| 669 | /* all others need to be set to zero: |
| 670 | fairness chaining multilevel count replied_to */ |
| 671 | } |
| 672 | |
| 673 | pqp = (struct bau_payload_queue_entry *) |
| 674 | kmalloc_node((DESTINATION_PAYLOAD_QUEUE_SIZE + 1) * |
| 675 | sizeof(struct bau_payload_queue_entry), |
| 676 | GFP_KERNEL, i); |
| 677 | if (!pqp) |
| 678 | BUG(); |
| 679 | if (sizeof(struct bau_payload_queue_entry) != 32) |
| 680 | BUG(); |
| 681 | if ((unsigned long)(&((struct bau_payload_queue_entry *)0)-> |
| 682 | sw_ack_vector) != 15) |
| 683 | BUG(); |
| 684 | |
| 685 | cp = (char *)pqp + 31; |
| 686 | pqp = (struct bau_payload_queue_entry *) |
| 687 | (((unsigned long)cp >> 5) << 5); |
| 688 | bau_tablesp->va_queue_first = pqp; |
| 689 | uv_write_global_mmr64(pnode, |
| 690 | UVH_LB_BAU_INTD_PAYLOAD_QUEUE_FIRST, |
| 691 | ((unsigned long)pnode << |
| 692 | UV_PAYLOADQ_PNODE_SHIFT) | |
| 693 | uv_physnodeaddr(pqp)); |
| 694 | uv_write_global_mmr64(pnode, UVH_LB_BAU_INTD_PAYLOAD_QUEUE_TAIL, |
| 695 | uv_physnodeaddr(pqp)); |
| 696 | bau_tablesp->va_queue_last = |
| 697 | pqp + (DESTINATION_PAYLOAD_QUEUE_SIZE - 1); |
| 698 | uv_write_global_mmr64(pnode, UVH_LB_BAU_INTD_PAYLOAD_QUEUE_LAST, |
| 699 | (unsigned long) |
| 700 | uv_physnodeaddr(bau_tablesp-> |
| 701 | va_queue_last)); |
| 702 | memset(pqp, 0, sizeof(struct bau_payload_queue_entry) * |
| 703 | DESTINATION_PAYLOAD_QUEUE_SIZE); |
| 704 | |
| 705 | /* this initialization can't be in firmware because the |
| 706 | messaging IRQ will be determined by the OS */ |
| 707 | apicid = per_cpu(x86_cpu_to_apicid, cur_cpu); |
| 708 | pa = uv_read_global_mmr64(pnode, UVH_BAU_DATA_CONFIG); |
| 709 | if ((pa & 0xff) != UV_BAU_MESSAGE) { |
| 710 | uv_write_global_mmr64(pnode, UVH_BAU_DATA_CONFIG, |
| 711 | ((apicid << 32) | |
| 712 | UV_BAU_MESSAGE)); |
| 713 | } |
| 714 | |
| 715 | for (j = cur_cpu; j < (cur_cpu + uv_blade_nr_possible_cpus(i)); |
| 716 | j++) { |
| 717 | bcp = (struct bau_control *)&per_cpu(bau_control, j); |
| 718 | bcp->bau_msg_head = bau_tablesp->va_queue_first; |
| 719 | bcp->va_queue_first = bau_tablesp->va_queue_first; |
| 720 | |
| 721 | bcp->va_queue_last = bau_tablesp->va_queue_last; |
| 722 | bcp->watching = bau_tablesp->watching; |
| 723 | bcp->msg_statuses = bau_tablesp->msg_statuses; |
| 724 | bcp->descriptor_base = adp; |
| 725 | } |
| 726 | cur_cpu += uv_blade_nr_possible_cpus(i); |
| 727 | } |
| 728 | |
| 729 | set_intr_gate(UV_BAU_MESSAGE, uv_bau_message_intr1); |
| 730 | |
| 731 | uv_enable_timeouts(); |
| 732 | |
| 733 | return 0; |
| 734 | } |
| 735 | |
| 736 | __initcall(uv_bau_init); |