1 /* SPDX-License-Identifier: GPL-2.0 */ 2 /* 3 * Here is where the ball gets rolling as far as the kernel is concerned. 4 * When control is transferred to _start, the bootload has already 5 * loaded us to the correct address. All that's left to do here is 6 * to set up the kernel's global pointer and jump to the kernel 7 * entry point. 8 * 9 * Copyright (C) 1998-2001, 2003, 2005 Hewlett-Packard Co 10 * David Mosberger-Tang <davidm@hpl.hp.com> 11 * Stephane Eranian <eranian@hpl.hp.com> 12 * Copyright (C) 1999 VA Linux Systems 13 * Copyright (C) 1999 Walt Drummond <drummond@valinux.com> 14 * Copyright (C) 1999 Intel Corp. 15 * Copyright (C) 1999 Asit Mallick <Asit.K.Mallick@intel.com> 16 * Copyright (C) 1999 Don Dugger <Don.Dugger@intel.com> 17 * Copyright (C) 2002 Fenghua Yu <fenghua.yu@intel.com> 18 * -Optimize __ia64_save_fpu() and __ia64_load_fpu() for Itanium 2. 19 * Copyright (C) 2004 Ashok Raj <ashok.raj@intel.com> 20 * Support for CPU Hotplug 21 */ 22 23 #include <linux/export.h> 24 #include <linux/pgtable.h> 25 #include <asm/asmmacro.h> 26 #include <asm/fpu.h> 27 #include <asm/kregs.h> 28 #include <asm/mmu_context.h> 29 #include <asm/asm-offsets.h> 30 #include <asm/pal.h> 31 #include <asm/processor.h> 32 #include <asm/ptrace.h> 33 #include <asm/mca_asm.h> 34 #include <linux/init.h> 35 #include <linux/linkage.h> 36 37 #ifdef CONFIG_HOTPLUG_CPU 38 #define SAL_PSR_BITS_TO_SET \ 39 (IA64_PSR_AC | IA64_PSR_BN | IA64_PSR_MFH | IA64_PSR_MFL) 40 41 #define SAVE_FROM_REG(src, ptr, dest) \ 42 mov dest=src;; \ 43 st8 [ptr]=dest,0x08 44 45 #define RESTORE_REG(reg, ptr, _tmp) \ 46 ld8 _tmp=[ptr],0x08;; \ 47 mov reg=_tmp 48 49 #define SAVE_BREAK_REGS(ptr, _idx, _breg, _dest)\ 50 mov ar.lc=IA64_NUM_DBG_REGS-1;; \ 51 mov _idx=0;; \ 52 1: \ 53 SAVE_FROM_REG(_breg[_idx], ptr, _dest);; \ 54 add _idx=1,_idx;; \ 55 br.cloop.sptk.many 1b 56 57 #define RESTORE_BREAK_REGS(ptr, _idx, _breg, _tmp, _lbl)\ 58 mov ar.lc=IA64_NUM_DBG_REGS-1;; \ 59 mov _idx=0;; \ 60 _lbl: RESTORE_REG(_breg[_idx], ptr, _tmp);; \ 61 add _idx=1, _idx;; \ 62 br.cloop.sptk.many _lbl 63 64 #define SAVE_ONE_RR(num, _reg, _tmp) \ 65 movl _tmp=(num<<61);; \ 66 mov _reg=rr[_tmp] 67 68 #define SAVE_REGION_REGS(_tmp, _r0, _r1, _r2, _r3, _r4, _r5, _r6, _r7) \ 69 SAVE_ONE_RR(0,_r0, _tmp);; \ 70 SAVE_ONE_RR(1,_r1, _tmp);; \ 71 SAVE_ONE_RR(2,_r2, _tmp);; \ 72 SAVE_ONE_RR(3,_r3, _tmp);; \ 73 SAVE_ONE_RR(4,_r4, _tmp);; \ 74 SAVE_ONE_RR(5,_r5, _tmp);; \ 75 SAVE_ONE_RR(6,_r6, _tmp);; \ 76 SAVE_ONE_RR(7,_r7, _tmp);; 77 78 #define STORE_REGION_REGS(ptr, _r0, _r1, _r2, _r3, _r4, _r5, _r6, _r7) \ 79 st8 [ptr]=_r0, 8;; \ 80 st8 [ptr]=_r1, 8;; \ 81 st8 [ptr]=_r2, 8;; \ 82 st8 [ptr]=_r3, 8;; \ 83 st8 [ptr]=_r4, 8;; \ 84 st8 [ptr]=_r5, 8;; \ 85 st8 [ptr]=_r6, 8;; \ 86 st8 [ptr]=_r7, 8;; 87 88 #define RESTORE_REGION_REGS(ptr, _idx1, _idx2, _tmp) \ 89 mov ar.lc=0x08-1;; \ 90 movl _idx1=0x00;; \ 91 RestRR: \ 92 dep.z _idx2=_idx1,61,3;; \ 93 ld8 _tmp=[ptr],8;; \ 94 mov rr[_idx2]=_tmp;; \ 95 srlz.d;; \ 96 add _idx1=1,_idx1;; \ 97 br.cloop.sptk.few RestRR 98 99 #define SET_AREA_FOR_BOOTING_CPU(reg1, reg2) \ 100 movl reg1=sal_state_for_booting_cpu;; \ 101 ld8 reg2=[reg1];; 102 103 /* 104 * Adjust region registers saved before starting to save 105 * break regs and rest of the states that need to be preserved. 106 */ 107 #define SAL_TO_OS_BOOT_HANDOFF_STATE_SAVE(_reg1,_reg2,_pred) \ 108 SAVE_FROM_REG(b0,_reg1,_reg2);; \ 109 SAVE_FROM_REG(b1,_reg1,_reg2);; \ 110 SAVE_FROM_REG(b2,_reg1,_reg2);; \ 111 SAVE_FROM_REG(b3,_reg1,_reg2);; \ 112 SAVE_FROM_REG(b4,_reg1,_reg2);; \ 113 SAVE_FROM_REG(b5,_reg1,_reg2);; \ 114 st8 [_reg1]=r1,0x08;; \ 115 st8 [_reg1]=r12,0x08;; \ 116 st8 [_reg1]=r13,0x08;; \ 117 SAVE_FROM_REG(ar.fpsr,_reg1,_reg2);; \ 118 SAVE_FROM_REG(ar.pfs,_reg1,_reg2);; \ 119 SAVE_FROM_REG(ar.rnat,_reg1,_reg2);; \ 120 SAVE_FROM_REG(ar.unat,_reg1,_reg2);; \ 121 SAVE_FROM_REG(ar.bspstore,_reg1,_reg2);; \ 122 SAVE_FROM_REG(cr.dcr,_reg1,_reg2);; \ 123 SAVE_FROM_REG(cr.iva,_reg1,_reg2);; \ 124 SAVE_FROM_REG(cr.pta,_reg1,_reg2);; \ 125 SAVE_FROM_REG(cr.itv,_reg1,_reg2);; \ 126 SAVE_FROM_REG(cr.pmv,_reg1,_reg2);; \ 127 SAVE_FROM_REG(cr.cmcv,_reg1,_reg2);; \ 128 SAVE_FROM_REG(cr.lrr0,_reg1,_reg2);; \ 129 SAVE_FROM_REG(cr.lrr1,_reg1,_reg2);; \ 130 st8 [_reg1]=r4,0x08;; \ 131 st8 [_reg1]=r5,0x08;; \ 132 st8 [_reg1]=r6,0x08;; \ 133 st8 [_reg1]=r7,0x08;; \ 134 st8 [_reg1]=_pred,0x08;; \ 135 SAVE_FROM_REG(ar.lc, _reg1, _reg2);; \ 136 stf.spill.nta [_reg1]=f2,16;; \ 137 stf.spill.nta [_reg1]=f3,16;; \ 138 stf.spill.nta [_reg1]=f4,16;; \ 139 stf.spill.nta [_reg1]=f5,16;; \ 140 stf.spill.nta [_reg1]=f16,16;; \ 141 stf.spill.nta [_reg1]=f17,16;; \ 142 stf.spill.nta [_reg1]=f18,16;; \ 143 stf.spill.nta [_reg1]=f19,16;; \ 144 stf.spill.nta [_reg1]=f20,16;; \ 145 stf.spill.nta [_reg1]=f21,16;; \ 146 stf.spill.nta [_reg1]=f22,16;; \ 147 stf.spill.nta [_reg1]=f23,16;; \ 148 stf.spill.nta [_reg1]=f24,16;; \ 149 stf.spill.nta [_reg1]=f25,16;; \ 150 stf.spill.nta [_reg1]=f26,16;; \ 151 stf.spill.nta [_reg1]=f27,16;; \ 152 stf.spill.nta [_reg1]=f28,16;; \ 153 stf.spill.nta [_reg1]=f29,16;; \ 154 stf.spill.nta [_reg1]=f30,16;; \ 155 stf.spill.nta [_reg1]=f31,16;; 156 157 #else 158 #define SET_AREA_FOR_BOOTING_CPU(a1, a2) 159 #define SAL_TO_OS_BOOT_HANDOFF_STATE_SAVE(a1,a2, a3) 160 #define SAVE_REGION_REGS(_tmp, _r0, _r1, _r2, _r3, _r4, _r5, _r6, _r7) 161 #define STORE_REGION_REGS(ptr, _r0, _r1, _r2, _r3, _r4, _r5, _r6, _r7) 162 #endif 163 164 #define SET_ONE_RR(num, pgsize, _tmp1, _tmp2, vhpt) \ 165 movl _tmp1=(num << 61);; \ 166 mov _tmp2=((ia64_rid(IA64_REGION_ID_KERNEL, (num<<61)) << 8) | (pgsize << 2) | vhpt);; \ 167 mov rr[_tmp1]=_tmp2 168 169 __PAGE_ALIGNED_DATA 170 171 .global empty_zero_page 172 EXPORT_SYMBOL_GPL(empty_zero_page) 173 empty_zero_page: 174 .skip PAGE_SIZE 175 176 .global swapper_pg_dir 177 swapper_pg_dir: 178 .skip PAGE_SIZE 179 180 .rodata 181 halt_msg: 182 stringz "Halting kernel\n" 183 184 __REF 185 186 .global start_ap 187 188 /* 189 * Start the kernel. When the bootloader passes control to _start(), r28 190 * points to the address of the boot parameter area. Execution reaches 191 * here in physical mode. 192 */ 193 GLOBAL_ENTRY(_start) 194 start_ap: 195 .prologue 196 .save rp, r0 // terminate unwind chain with a NULL rp 197 .body 198 199 rsm psr.i | psr.ic 200 ;; 201 srlz.i 202 ;; 203 { 204 flushrs // must be first insn in group 205 srlz.i 206 } 207 ;; 208 /* 209 * Save the region registers, predicate before they get clobbered 210 */ 211 SAVE_REGION_REGS(r2, r8,r9,r10,r11,r12,r13,r14,r15); 212 mov r25=pr;; 213 214 /* 215 * Initialize kernel region registers: 216 * rr[0]: VHPT enabled, page size = PAGE_SHIFT 217 * rr[1]: VHPT enabled, page size = PAGE_SHIFT 218 * rr[2]: VHPT enabled, page size = PAGE_SHIFT 219 * rr[3]: VHPT enabled, page size = PAGE_SHIFT 220 * rr[4]: VHPT enabled, page size = PAGE_SHIFT 221 * rr[5]: VHPT enabled, page size = PAGE_SHIFT 222 * rr[6]: VHPT disabled, page size = IA64_GRANULE_SHIFT 223 * rr[7]: VHPT disabled, page size = IA64_GRANULE_SHIFT 224 * We initialize all of them to prevent inadvertently assuming 225 * something about the state of address translation early in boot. 226 */ 227 SET_ONE_RR(0, PAGE_SHIFT, r2, r16, 1);; 228 SET_ONE_RR(1, PAGE_SHIFT, r2, r16, 1);; 229 SET_ONE_RR(2, PAGE_SHIFT, r2, r16, 1);; 230 SET_ONE_RR(3, PAGE_SHIFT, r2, r16, 1);; 231 SET_ONE_RR(4, PAGE_SHIFT, r2, r16, 1);; 232 SET_ONE_RR(5, PAGE_SHIFT, r2, r16, 1);; 233 SET_ONE_RR(6, IA64_GRANULE_SHIFT, r2, r16, 0);; 234 SET_ONE_RR(7, IA64_GRANULE_SHIFT, r2, r16, 0);; 235 /* 236 * Now pin mappings into the TLB for kernel text and data 237 */ 238 mov r18=KERNEL_TR_PAGE_SHIFT<<2 239 movl r17=KERNEL_START 240 ;; 241 mov cr.itir=r18 242 mov cr.ifa=r17 243 mov r16=IA64_TR_KERNEL 244 mov r3=ip 245 movl r18=PAGE_KERNEL 246 ;; 247 dep r2=0,r3,0,KERNEL_TR_PAGE_SHIFT 248 ;; 249 or r18=r2,r18 250 ;; 251 srlz.i 252 ;; 253 itr.i itr[r16]=r18 254 ;; 255 itr.d dtr[r16]=r18 256 ;; 257 srlz.i 258 259 /* 260 * Switch into virtual mode: 261 */ 262 movl r16=(IA64_PSR_IT|IA64_PSR_IC|IA64_PSR_DT|IA64_PSR_RT|IA64_PSR_DFH|IA64_PSR_BN \ 263 |IA64_PSR_DI) 264 ;; 265 mov cr.ipsr=r16 266 movl r17=1f 267 ;; 268 mov cr.iip=r17 269 mov cr.ifs=r0 270 ;; 271 rfi 272 ;; 273 1: // now we are in virtual mode 274 275 SET_AREA_FOR_BOOTING_CPU(r2, r16); 276 277 STORE_REGION_REGS(r16, r8,r9,r10,r11,r12,r13,r14,r15); 278 SAL_TO_OS_BOOT_HANDOFF_STATE_SAVE(r16,r17,r25) 279 ;; 280 281 // set IVT entry point---can't access I/O ports without it 282 movl r3=ia64_ivt 283 ;; 284 mov cr.iva=r3 285 movl r2=FPSR_DEFAULT 286 ;; 287 srlz.i 288 movl gp=__gp 289 290 mov ar.fpsr=r2 291 ;; 292 293 #define isAP p2 // are we an Application Processor? 294 #define isBP p3 // are we the Bootstrap Processor? 295 296 #ifdef CONFIG_SMP 297 /* 298 * Find the init_task for the currently booting CPU. At poweron, and in 299 * UP mode, task_for_booting_cpu is NULL. 300 */ 301 movl r3=task_for_booting_cpu 302 ;; 303 ld8 r3=[r3] 304 movl r2=init_task 305 ;; 306 cmp.eq isBP,isAP=r3,r0 307 ;; 308 (isAP) mov r2=r3 309 #else 310 movl r2=init_task 311 cmp.eq isBP,isAP=r0,r0 312 #endif 313 ;; 314 tpa r3=r2 // r3 == phys addr of task struct 315 mov r16=-1 316 (isBP) br.cond.dpnt .load_current // BP stack is on region 5 --- no need to map it 317 318 // load mapping for stack (virtaddr in r2, physaddr in r3) 319 rsm psr.ic 320 movl r17=PAGE_KERNEL 321 ;; 322 srlz.d 323 dep r18=0,r3,0,12 324 ;; 325 or r18=r17,r18 326 dep r2=-1,r3,61,3 // IMVA of task 327 ;; 328 mov r17=rr[r2] 329 shr.u r16=r3,IA64_GRANULE_SHIFT 330 ;; 331 dep r17=0,r17,8,24 332 ;; 333 mov cr.itir=r17 334 mov cr.ifa=r2 335 336 mov r19=IA64_TR_CURRENT_STACK 337 ;; 338 itr.d dtr[r19]=r18 339 ;; 340 ssm psr.ic 341 srlz.d 342 ;; 343 344 .load_current: 345 // load the "current" pointer (r13) and ar.k6 with the current task 346 mov IA64_KR(CURRENT)=r2 // virtual address 347 mov IA64_KR(CURRENT_STACK)=r16 348 mov r13=r2 349 /* 350 * Reserve space at the top of the stack for "struct pt_regs". Kernel 351 * threads don't store interesting values in that structure, but the space 352 * still needs to be there because time-critical stuff such as the context 353 * switching can be implemented more efficiently (for example, __switch_to() 354 * always sets the psr.dfh bit of the task it is switching to). 355 */ 356 357 addl r12=IA64_STK_OFFSET-IA64_PT_REGS_SIZE-16,r2 358 addl r2=IA64_RBS_OFFSET,r2 // initialize the RSE 359 mov ar.rsc=0 // place RSE in enforced lazy mode 360 ;; 361 loadrs // clear the dirty partition 362 movl r19=__phys_per_cpu_start 363 mov r18=PERCPU_PAGE_SIZE 364 ;; 365 #ifndef CONFIG_SMP 366 add r19=r19,r18 367 ;; 368 #else 369 (isAP) br.few 2f 370 movl r20=__cpu0_per_cpu 371 ;; 372 shr.u r18=r18,3 373 1: 374 ld8 r21=[r19],8;; 375 st8[r20]=r21,8 376 adds r18=-1,r18;; 377 cmp4.lt p7,p6=0,r18 378 (p7) br.cond.dptk.few 1b 379 mov r19=r20 380 ;; 381 2: 382 #endif 383 tpa r19=r19 384 ;; 385 .pred.rel.mutex isBP,isAP 386 (isBP) mov IA64_KR(PER_CPU_DATA)=r19 // per-CPU base for cpu0 387 (isAP) mov IA64_KR(PER_CPU_DATA)=r0 // clear physical per-CPU base 388 ;; 389 mov ar.bspstore=r2 // establish the new RSE stack 390 ;; 391 mov ar.rsc=0x3 // place RSE in eager mode 392 393 (isBP) dep r28=-1,r28,61,3 // make address virtual 394 (isBP) movl r2=ia64_boot_param 395 ;; 396 (isBP) st8 [r2]=r28 // save the address of the boot param area passed by the bootloader 397 398 #ifdef CONFIG_SMP 399 (isAP) br.call.sptk.many rp=start_secondary 400 .ret0: 401 (isAP) br.cond.sptk self 402 #endif 403 404 // This is executed by the bootstrap processor (bsp) only: 405 406 br.call.sptk.many rp=start_kernel 407 .ret2: addl r3=@ltoff(halt_msg),gp 408 ;; 409 alloc r2=ar.pfs,8,0,2,0 410 ;; 411 ld8 out0=[r3] 412 br.call.sptk.many b0=console_print 413 414 self: hint @pause 415 br.sptk.many self // endless loop 416 END(_start) 417 418 .text 419 420 GLOBAL_ENTRY(ia64_save_debug_regs) 421 alloc r16=ar.pfs,1,0,0,0 422 mov r20=ar.lc // preserve ar.lc 423 mov ar.lc=IA64_NUM_DBG_REGS-1 424 mov r18=0 425 add r19=IA64_NUM_DBG_REGS*8,in0 426 ;; 427 1: mov r16=dbr[r18] 428 #ifdef CONFIG_ITANIUM 429 ;; 430 srlz.d 431 #endif 432 mov r17=ibr[r18] 433 add r18=1,r18 434 ;; 435 st8.nta [in0]=r16,8 436 st8.nta [r19]=r17,8 437 br.cloop.sptk.many 1b 438 ;; 439 mov ar.lc=r20 // restore ar.lc 440 br.ret.sptk.many rp 441 END(ia64_save_debug_regs) 442 443 GLOBAL_ENTRY(ia64_load_debug_regs) 444 alloc r16=ar.pfs,1,0,0,0 445 lfetch.nta [in0] 446 mov r20=ar.lc // preserve ar.lc 447 add r19=IA64_NUM_DBG_REGS*8,in0 448 mov ar.lc=IA64_NUM_DBG_REGS-1 449 mov r18=-1 450 ;; 451 1: ld8.nta r16=[in0],8 452 ld8.nta r17=[r19],8 453 add r18=1,r18 454 ;; 455 mov dbr[r18]=r16 456 #ifdef CONFIG_ITANIUM 457 ;; 458 srlz.d // Errata 132 (NoFix status) 459 #endif 460 mov ibr[r18]=r17 461 br.cloop.sptk.many 1b 462 ;; 463 mov ar.lc=r20 // restore ar.lc 464 br.ret.sptk.many rp 465 END(ia64_load_debug_regs) 466 467 GLOBAL_ENTRY(__ia64_save_fpu) 468 alloc r2=ar.pfs,1,4,0,0 469 adds loc0=96*16-16,in0 470 adds loc1=96*16-16-128,in0 471 ;; 472 stf.spill.nta [loc0]=f127,-256 473 stf.spill.nta [loc1]=f119,-256 474 ;; 475 stf.spill.nta [loc0]=f111,-256 476 stf.spill.nta [loc1]=f103,-256 477 ;; 478 stf.spill.nta [loc0]=f95,-256 479 stf.spill.nta [loc1]=f87,-256 480 ;; 481 stf.spill.nta [loc0]=f79,-256 482 stf.spill.nta [loc1]=f71,-256 483 ;; 484 stf.spill.nta [loc0]=f63,-256 485 stf.spill.nta [loc1]=f55,-256 486 adds loc2=96*16-32,in0 487 ;; 488 stf.spill.nta [loc0]=f47,-256 489 stf.spill.nta [loc1]=f39,-256 490 adds loc3=96*16-32-128,in0 491 ;; 492 stf.spill.nta [loc2]=f126,-256 493 stf.spill.nta [loc3]=f118,-256 494 ;; 495 stf.spill.nta [loc2]=f110,-256 496 stf.spill.nta [loc3]=f102,-256 497 ;; 498 stf.spill.nta [loc2]=f94,-256 499 stf.spill.nta [loc3]=f86,-256 500 ;; 501 stf.spill.nta [loc2]=f78,-256 502 stf.spill.nta [loc3]=f70,-256 503 ;; 504 stf.spill.nta [loc2]=f62,-256 505 stf.spill.nta [loc3]=f54,-256 506 adds loc0=96*16-48,in0 507 ;; 508 stf.spill.nta [loc2]=f46,-256 509 stf.spill.nta [loc3]=f38,-256 510 adds loc1=96*16-48-128,in0 511 ;; 512 stf.spill.nta [loc0]=f125,-256 513 stf.spill.nta [loc1]=f117,-256 514 ;; 515 stf.spill.nta [loc0]=f109,-256 516 stf.spill.nta [loc1]=f101,-256 517 ;; 518 stf.spill.nta [loc0]=f93,-256 519 stf.spill.nta [loc1]=f85,-256 520 ;; 521 stf.spill.nta [loc0]=f77,-256 522 stf.spill.nta [loc1]=f69,-256 523 ;; 524 stf.spill.nta [loc0]=f61,-256 525 stf.spill.nta [loc1]=f53,-256 526 adds loc2=96*16-64,in0 527 ;; 528 stf.spill.nta [loc0]=f45,-256 529 stf.spill.nta [loc1]=f37,-256 530 adds loc3=96*16-64-128,in0 531 ;; 532 stf.spill.nta [loc2]=f124,-256 533 stf.spill.nta [loc3]=f116,-256 534 ;; 535 stf.spill.nta [loc2]=f108,-256 536 stf.spill.nta [loc3]=f100,-256 537 ;; 538 stf.spill.nta [loc2]=f92,-256 539 stf.spill.nta [loc3]=f84,-256 540 ;; 541 stf.spill.nta [loc2]=f76,-256 542 stf.spill.nta [loc3]=f68,-256 543 ;; 544 stf.spill.nta [loc2]=f60,-256 545 stf.spill.nta [loc3]=f52,-256 546 adds loc0=96*16-80,in0 547 ;; 548 stf.spill.nta [loc2]=f44,-256 549 stf.spill.nta [loc3]=f36,-256 550 adds loc1=96*16-80-128,in0 551 ;; 552 stf.spill.nta [loc0]=f123,-256 553 stf.spill.nta [loc1]=f115,-256 554 ;; 555 stf.spill.nta [loc0]=f107,-256 556 stf.spill.nta [loc1]=f99,-256 557 ;; 558 stf.spill.nta [loc0]=f91,-256 559 stf.spill.nta [loc1]=f83,-256 560 ;; 561 stf.spill.nta [loc0]=f75,-256 562 stf.spill.nta [loc1]=f67,-256 563 ;; 564 stf.spill.nta [loc0]=f59,-256 565 stf.spill.nta [loc1]=f51,-256 566 adds loc2=96*16-96,in0 567 ;; 568 stf.spill.nta [loc0]=f43,-256 569 stf.spill.nta [loc1]=f35,-256 570 adds loc3=96*16-96-128,in0 571 ;; 572 stf.spill.nta [loc2]=f122,-256 573 stf.spill.nta [loc3]=f114,-256 574 ;; 575 stf.spill.nta [loc2]=f106,-256 576 stf.spill.nta [loc3]=f98,-256 577 ;; 578 stf.spill.nta [loc2]=f90,-256 579 stf.spill.nta [loc3]=f82,-256 580 ;; 581 stf.spill.nta [loc2]=f74,-256 582 stf.spill.nta [loc3]=f66,-256 583 ;; 584 stf.spill.nta [loc2]=f58,-256 585 stf.spill.nta [loc3]=f50,-256 586 adds loc0=96*16-112,in0 587 ;; 588 stf.spill.nta [loc2]=f42,-256 589 stf.spill.nta [loc3]=f34,-256 590 adds loc1=96*16-112-128,in0 591 ;; 592 stf.spill.nta [loc0]=f121,-256 593 stf.spill.nta [loc1]=f113,-256 594 ;; 595 stf.spill.nta [loc0]=f105,-256 596 stf.spill.nta [loc1]=f97,-256 597 ;; 598 stf.spill.nta [loc0]=f89,-256 599 stf.spill.nta [loc1]=f81,-256 600 ;; 601 stf.spill.nta [loc0]=f73,-256 602 stf.spill.nta [loc1]=f65,-256 603 ;; 604 stf.spill.nta [loc0]=f57,-256 605 stf.spill.nta [loc1]=f49,-256 606 adds loc2=96*16-128,in0 607 ;; 608 stf.spill.nta [loc0]=f41,-256 609 stf.spill.nta [loc1]=f33,-256 610 adds loc3=96*16-128-128,in0 611 ;; 612 stf.spill.nta [loc2]=f120,-256 613 stf.spill.nta [loc3]=f112,-256 614 ;; 615 stf.spill.nta [loc2]=f104,-256 616 stf.spill.nta [loc3]=f96,-256 617 ;; 618 stf.spill.nta [loc2]=f88,-256 619 stf.spill.nta [loc3]=f80,-256 620 ;; 621 stf.spill.nta [loc2]=f72,-256 622 stf.spill.nta [loc3]=f64,-256 623 ;; 624 stf.spill.nta [loc2]=f56,-256 625 stf.spill.nta [loc3]=f48,-256 626 ;; 627 stf.spill.nta [loc2]=f40 628 stf.spill.nta [loc3]=f32 629 br.ret.sptk.many rp 630 END(__ia64_save_fpu) 631 632 GLOBAL_ENTRY(__ia64_load_fpu) 633 alloc r2=ar.pfs,1,2,0,0 634 adds r3=128,in0 635 adds r14=256,in0 636 adds r15=384,in0 637 mov loc0=512 638 mov loc1=-1024+16 639 ;; 640 ldf.fill.nta f32=[in0],loc0 641 ldf.fill.nta f40=[ r3],loc0 642 ldf.fill.nta f48=[r14],loc0 643 ldf.fill.nta f56=[r15],loc0 644 ;; 645 ldf.fill.nta f64=[in0],loc0 646 ldf.fill.nta f72=[ r3],loc0 647 ldf.fill.nta f80=[r14],loc0 648 ldf.fill.nta f88=[r15],loc0 649 ;; 650 ldf.fill.nta f96=[in0],loc1 651 ldf.fill.nta f104=[ r3],loc1 652 ldf.fill.nta f112=[r14],loc1 653 ldf.fill.nta f120=[r15],loc1 654 ;; 655 ldf.fill.nta f33=[in0],loc0 656 ldf.fill.nta f41=[ r3],loc0 657 ldf.fill.nta f49=[r14],loc0 658 ldf.fill.nta f57=[r15],loc0 659 ;; 660 ldf.fill.nta f65=[in0],loc0 661 ldf.fill.nta f73=[ r3],loc0 662 ldf.fill.nta f81=[r14],loc0 663 ldf.fill.nta f89=[r15],loc0 664 ;; 665 ldf.fill.nta f97=[in0],loc1 666 ldf.fill.nta f105=[ r3],loc1 667 ldf.fill.nta f113=[r14],loc1 668 ldf.fill.nta f121=[r15],loc1 669 ;; 670 ldf.fill.nta f34=[in0],loc0 671 ldf.fill.nta f42=[ r3],loc0 672 ldf.fill.nta f50=[r14],loc0 673 ldf.fill.nta f58=[r15],loc0 674 ;; 675 ldf.fill.nta f66=[in0],loc0 676 ldf.fill.nta f74=[ r3],loc0 677 ldf.fill.nta f82=[r14],loc0 678 ldf.fill.nta f90=[r15],loc0 679 ;; 680 ldf.fill.nta f98=[in0],loc1 681 ldf.fill.nta f106=[ r3],loc1 682 ldf.fill.nta f114=[r14],loc1 683 ldf.fill.nta f122=[r15],loc1 684 ;; 685 ldf.fill.nta f35=[in0],loc0 686 ldf.fill.nta f43=[ r3],loc0 687 ldf.fill.nta f51=[r14],loc0 688 ldf.fill.nta f59=[r15],loc0 689 ;; 690 ldf.fill.nta f67=[in0],loc0 691 ldf.fill.nta f75=[ r3],loc0 692 ldf.fill.nta f83=[r14],loc0 693 ldf.fill.nta f91=[r15],loc0 694 ;; 695 ldf.fill.nta f99=[in0],loc1 696 ldf.fill.nta f107=[ r3],loc1 697 ldf.fill.nta f115=[r14],loc1 698 ldf.fill.nta f123=[r15],loc1 699 ;; 700 ldf.fill.nta f36=[in0],loc0 701 ldf.fill.nta f44=[ r3],loc0 702 ldf.fill.nta f52=[r14],loc0 703 ldf.fill.nta f60=[r15],loc0 704 ;; 705 ldf.fill.nta f68=[in0],loc0 706 ldf.fill.nta f76=[ r3],loc0 707 ldf.fill.nta f84=[r14],loc0 708 ldf.fill.nta f92=[r15],loc0 709 ;; 710 ldf.fill.nta f100=[in0],loc1 711 ldf.fill.nta f108=[ r3],loc1 712 ldf.fill.nta f116=[r14],loc1 713 ldf.fill.nta f124=[r15],loc1 714 ;; 715 ldf.fill.nta f37=[in0],loc0 716 ldf.fill.nta f45=[ r3],loc0 717 ldf.fill.nta f53=[r14],loc0 718 ldf.fill.nta f61=[r15],loc0 719 ;; 720 ldf.fill.nta f69=[in0],loc0 721 ldf.fill.nta f77=[ r3],loc0 722 ldf.fill.nta f85=[r14],loc0 723 ldf.fill.nta f93=[r15],loc0 724 ;; 725 ldf.fill.nta f101=[in0],loc1 726 ldf.fill.nta f109=[ r3],loc1 727 ldf.fill.nta f117=[r14],loc1 728 ldf.fill.nta f125=[r15],loc1 729 ;; 730 ldf.fill.nta f38 =[in0],loc0 731 ldf.fill.nta f46 =[ r3],loc0 732 ldf.fill.nta f54 =[r14],loc0 733 ldf.fill.nta f62 =[r15],loc0 734 ;; 735 ldf.fill.nta f70 =[in0],loc0 736 ldf.fill.nta f78 =[ r3],loc0 737 ldf.fill.nta f86 =[r14],loc0 738 ldf.fill.nta f94 =[r15],loc0 739 ;; 740 ldf.fill.nta f102=[in0],loc1 741 ldf.fill.nta f110=[ r3],loc1 742 ldf.fill.nta f118=[r14],loc1 743 ldf.fill.nta f126=[r15],loc1 744 ;; 745 ldf.fill.nta f39 =[in0],loc0 746 ldf.fill.nta f47 =[ r3],loc0 747 ldf.fill.nta f55 =[r14],loc0 748 ldf.fill.nta f63 =[r15],loc0 749 ;; 750 ldf.fill.nta f71 =[in0],loc0 751 ldf.fill.nta f79 =[ r3],loc0 752 ldf.fill.nta f87 =[r14],loc0 753 ldf.fill.nta f95 =[r15],loc0 754 ;; 755 ldf.fill.nta f103=[in0] 756 ldf.fill.nta f111=[ r3] 757 ldf.fill.nta f119=[r14] 758 ldf.fill.nta f127=[r15] 759 br.ret.sptk.many rp 760 END(__ia64_load_fpu) 761 762 GLOBAL_ENTRY(__ia64_init_fpu) 763 stf.spill [sp]=f0 // M3 764 mov f32=f0 // F 765 nop.b 0 766 767 ldfps f33,f34=[sp] // M0 768 ldfps f35,f36=[sp] // M1 769 mov f37=f0 // F 770 ;; 771 772 setf.s f38=r0 // M2 773 setf.s f39=r0 // M3 774 mov f40=f0 // F 775 776 ldfps f41,f42=[sp] // M0 777 ldfps f43,f44=[sp] // M1 778 mov f45=f0 // F 779 780 setf.s f46=r0 // M2 781 setf.s f47=r0 // M3 782 mov f48=f0 // F 783 784 ldfps f49,f50=[sp] // M0 785 ldfps f51,f52=[sp] // M1 786 mov f53=f0 // F 787 788 setf.s f54=r0 // M2 789 setf.s f55=r0 // M3 790 mov f56=f0 // F 791 792 ldfps f57,f58=[sp] // M0 793 ldfps f59,f60=[sp] // M1 794 mov f61=f0 // F 795 796 setf.s f62=r0 // M2 797 setf.s f63=r0 // M3 798 mov f64=f0 // F 799 800 ldfps f65,f66=[sp] // M0 801 ldfps f67,f68=[sp] // M1 802 mov f69=f0 // F 803 804 setf.s f70=r0 // M2 805 setf.s f71=r0 // M3 806 mov f72=f0 // F 807 808 ldfps f73,f74=[sp] // M0 809 ldfps f75,f76=[sp] // M1 810 mov f77=f0 // F 811 812 setf.s f78=r0 // M2 813 setf.s f79=r0 // M3 814 mov f80=f0 // F 815 816 ldfps f81,f82=[sp] // M0 817 ldfps f83,f84=[sp] // M1 818 mov f85=f0 // F 819 820 setf.s f86=r0 // M2 821 setf.s f87=r0 // M3 822 mov f88=f0 // F 823 824 /* 825 * When the instructions are cached, it would be faster to initialize 826 * the remaining registers with simply mov instructions (F-unit). 827 * This gets the time down to ~29 cycles. However, this would use up 828 * 33 bundles, whereas continuing with the above pattern yields 829 * 10 bundles and ~30 cycles. 830 */ 831 832 ldfps f89,f90=[sp] // M0 833 ldfps f91,f92=[sp] // M1 834 mov f93=f0 // F 835 836 setf.s f94=r0 // M2 837 setf.s f95=r0 // M3 838 mov f96=f0 // F 839 840 ldfps f97,f98=[sp] // M0 841 ldfps f99,f100=[sp] // M1 842 mov f101=f0 // F 843 844 setf.s f102=r0 // M2 845 setf.s f103=r0 // M3 846 mov f104=f0 // F 847 848 ldfps f105,f106=[sp] // M0 849 ldfps f107,f108=[sp] // M1 850 mov f109=f0 // F 851 852 setf.s f110=r0 // M2 853 setf.s f111=r0 // M3 854 mov f112=f0 // F 855 856 ldfps f113,f114=[sp] // M0 857 ldfps f115,f116=[sp] // M1 858 mov f117=f0 // F 859 860 setf.s f118=r0 // M2 861 setf.s f119=r0 // M3 862 mov f120=f0 // F 863 864 ldfps f121,f122=[sp] // M0 865 ldfps f123,f124=[sp] // M1 866 mov f125=f0 // F 867 868 setf.s f126=r0 // M2 869 setf.s f127=r0 // M3 870 br.ret.sptk.many rp // F 871 END(__ia64_init_fpu) 872 873 /* 874 * Switch execution mode from virtual to physical 875 * 876 * Inputs: 877 * r16 = new psr to establish 878 * Output: 879 * r19 = old virtual address of ar.bsp 880 * r20 = old virtual address of sp 881 * 882 * Note: RSE must already be in enforced lazy mode 883 */ 884 GLOBAL_ENTRY(ia64_switch_mode_phys) 885 { 886 rsm psr.i | psr.ic // disable interrupts and interrupt collection 887 mov r15=ip 888 } 889 ;; 890 { 891 flushrs // must be first insn in group 892 srlz.i 893 } 894 ;; 895 mov cr.ipsr=r16 // set new PSR 896 add r3=1f-ia64_switch_mode_phys,r15 897 898 mov r19=ar.bsp 899 mov r20=sp 900 mov r14=rp // get return address into a general register 901 ;; 902 903 // going to physical mode, use tpa to translate virt->phys 904 tpa r17=r19 905 tpa r3=r3 906 tpa sp=sp 907 tpa r14=r14 908 ;; 909 910 mov r18=ar.rnat // save ar.rnat 911 mov ar.bspstore=r17 // this steps on ar.rnat 912 mov cr.iip=r3 913 mov cr.ifs=r0 914 ;; 915 mov ar.rnat=r18 // restore ar.rnat 916 rfi // must be last insn in group 917 ;; 918 1: mov rp=r14 919 br.ret.sptk.many rp 920 END(ia64_switch_mode_phys) 921 922 /* 923 * Switch execution mode from physical to virtual 924 * 925 * Inputs: 926 * r16 = new psr to establish 927 * r19 = new bspstore to establish 928 * r20 = new sp to establish 929 * 930 * Note: RSE must already be in enforced lazy mode 931 */ 932 GLOBAL_ENTRY(ia64_switch_mode_virt) 933 { 934 rsm psr.i | psr.ic // disable interrupts and interrupt collection 935 mov r15=ip 936 } 937 ;; 938 { 939 flushrs // must be first insn in group 940 srlz.i 941 } 942 ;; 943 mov cr.ipsr=r16 // set new PSR 944 add r3=1f-ia64_switch_mode_virt,r15 945 946 mov r14=rp // get return address into a general register 947 ;; 948 949 // going to virtual 950 // - for code addresses, set upper bits of addr to KERNEL_START 951 // - for stack addresses, copy from input argument 952 movl r18=KERNEL_START 953 dep r3=0,r3,KERNEL_TR_PAGE_SHIFT,64-KERNEL_TR_PAGE_SHIFT 954 dep r14=0,r14,KERNEL_TR_PAGE_SHIFT,64-KERNEL_TR_PAGE_SHIFT 955 mov sp=r20 956 ;; 957 or r3=r3,r18 958 or r14=r14,r18 959 ;; 960 961 mov r18=ar.rnat // save ar.rnat 962 mov ar.bspstore=r19 // this steps on ar.rnat 963 mov cr.iip=r3 964 mov cr.ifs=r0 965 ;; 966 mov ar.rnat=r18 // restore ar.rnat 967 rfi // must be last insn in group 968 ;; 969 1: mov rp=r14 970 br.ret.sptk.many rp 971 END(ia64_switch_mode_virt) 972 973 GLOBAL_ENTRY(ia64_delay_loop) 974 .prologue 975 { nop 0 // work around GAS unwind info generation bug... 976 .save ar.lc,r2 977 mov r2=ar.lc 978 .body 979 ;; 980 mov ar.lc=r32 981 } 982 ;; 983 // force loop to be 32-byte aligned (GAS bug means we cannot use .align 984 // inside function body without corrupting unwind info). 985 { nop 0 } 986 1: br.cloop.sptk.few 1b 987 ;; 988 mov ar.lc=r2 989 br.ret.sptk.many rp 990 END(ia64_delay_loop) 991 992 /* 993 * Return a CPU-local timestamp in nano-seconds. This timestamp is 994 * NOT synchronized across CPUs its return value must never be 995 * compared against the values returned on another CPU. The usage in 996 * kernel/sched/core.c ensures that. 997 * 998 * The return-value of sched_clock() is NOT supposed to wrap-around. 999 * If it did, it would cause some scheduling hiccups (at the worst). 1000 * Fortunately, with a 64-bit cycle-counter ticking at 100GHz, even 1001 * that would happen only once every 5+ years. 1002 * 1003 * The code below basically calculates: 1004 * 1005 * (ia64_get_itc() * local_cpu_data->nsec_per_cyc) >> IA64_NSEC_PER_CYC_SHIFT 1006 * 1007 * except that the multiplication and the shift are done with 128-bit 1008 * intermediate precision so that we can produce a full 64-bit result. 1009 */ 1010 GLOBAL_ENTRY(ia64_native_sched_clock) 1011 addl r8=THIS_CPU(ia64_cpu_info) + IA64_CPUINFO_NSEC_PER_CYC_OFFSET,r0 1012 mov.m r9=ar.itc // fetch cycle-counter (35 cyc) 1013 ;; 1014 ldf8 f8=[r8] 1015 ;; 1016 setf.sig f9=r9 // certain to stall, so issue it _after_ ldf8... 1017 ;; 1018 xmpy.lu f10=f9,f8 // calculate low 64 bits of 128-bit product (4 cyc) 1019 xmpy.hu f11=f9,f8 // calculate high 64 bits of 128-bit product 1020 ;; 1021 getf.sig r8=f10 // (5 cyc) 1022 getf.sig r9=f11 1023 ;; 1024 shrp r8=r9,r8,IA64_NSEC_PER_CYC_SHIFT 1025 br.ret.sptk.many rp 1026 END(ia64_native_sched_clock) 1027 1028 #ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE 1029 GLOBAL_ENTRY(cycle_to_nsec) 1030 alloc r16=ar.pfs,1,0,0,0 1031 addl r8=THIS_CPU(ia64_cpu_info) + IA64_CPUINFO_NSEC_PER_CYC_OFFSET,r0 1032 ;; 1033 ldf8 f8=[r8] 1034 ;; 1035 setf.sig f9=r32 1036 ;; 1037 xmpy.lu f10=f9,f8 // calculate low 64 bits of 128-bit product (4 cyc) 1038 xmpy.hu f11=f9,f8 // calculate high 64 bits of 128-bit product 1039 ;; 1040 getf.sig r8=f10 // (5 cyc) 1041 getf.sig r9=f11 1042 ;; 1043 shrp r8=r9,r8,IA64_NSEC_PER_CYC_SHIFT 1044 br.ret.sptk.many rp 1045 END(cycle_to_nsec) 1046 #endif /* CONFIG_VIRT_CPU_ACCOUNTING_NATIVE */ 1047 1048 #ifdef CONFIG_IA64_BRL_EMU 1049 1050 /* 1051 * Assembly routines used by brl_emu.c to set preserved register state. 1052 */ 1053 1054 #define SET_REG(reg) \ 1055 GLOBAL_ENTRY(ia64_set_##reg); \ 1056 alloc r16=ar.pfs,1,0,0,0; \ 1057 mov reg=r32; \ 1058 ;; \ 1059 br.ret.sptk.many rp; \ 1060 END(ia64_set_##reg) 1061 1062 SET_REG(b1); 1063 SET_REG(b2); 1064 SET_REG(b3); 1065 SET_REG(b4); 1066 SET_REG(b5); 1067 1068 #endif /* CONFIG_IA64_BRL_EMU */ 1069 1070 #ifdef CONFIG_SMP 1071 1072 #ifdef CONFIG_HOTPLUG_CPU 1073 GLOBAL_ENTRY(ia64_jump_to_sal) 1074 alloc r16=ar.pfs,1,0,0,0;; 1075 rsm psr.i | psr.ic 1076 { 1077 flushrs 1078 srlz.i 1079 } 1080 tpa r25=in0 1081 movl r18=tlb_purge_done;; 1082 DATA_VA_TO_PA(r18);; 1083 mov b1=r18 // Return location 1084 movl r18=ia64_do_tlb_purge;; 1085 DATA_VA_TO_PA(r18);; 1086 mov b2=r18 // doing tlb_flush work 1087 mov ar.rsc=0 // Put RSE in enforced lazy, LE mode 1088 movl r17=1f;; 1089 DATA_VA_TO_PA(r17);; 1090 mov cr.iip=r17 1091 movl r16=SAL_PSR_BITS_TO_SET;; 1092 mov cr.ipsr=r16 1093 mov cr.ifs=r0;; 1094 rfi;; // note: this unmask MCA/INIT (psr.mc) 1095 1: 1096 /* 1097 * Invalidate all TLB data/inst 1098 */ 1099 br.sptk.many b2;; // jump to tlb purge code 1100 1101 tlb_purge_done: 1102 RESTORE_REGION_REGS(r25, r17,r18,r19);; 1103 RESTORE_REG(b0, r25, r17);; 1104 RESTORE_REG(b1, r25, r17);; 1105 RESTORE_REG(b2, r25, r17);; 1106 RESTORE_REG(b3, r25, r17);; 1107 RESTORE_REG(b4, r25, r17);; 1108 RESTORE_REG(b5, r25, r17);; 1109 ld8 r1=[r25],0x08;; 1110 ld8 r12=[r25],0x08;; 1111 ld8 r13=[r25],0x08;; 1112 RESTORE_REG(ar.fpsr, r25, r17);; 1113 RESTORE_REG(ar.pfs, r25, r17);; 1114 RESTORE_REG(ar.rnat, r25, r17);; 1115 RESTORE_REG(ar.unat, r25, r17);; 1116 RESTORE_REG(ar.bspstore, r25, r17);; 1117 RESTORE_REG(cr.dcr, r25, r17);; 1118 RESTORE_REG(cr.iva, r25, r17);; 1119 RESTORE_REG(cr.pta, r25, r17);; 1120 srlz.d;; // required not to violate RAW dependency 1121 RESTORE_REG(cr.itv, r25, r17);; 1122 RESTORE_REG(cr.pmv, r25, r17);; 1123 RESTORE_REG(cr.cmcv, r25, r17);; 1124 RESTORE_REG(cr.lrr0, r25, r17);; 1125 RESTORE_REG(cr.lrr1, r25, r17);; 1126 ld8 r4=[r25],0x08;; 1127 ld8 r5=[r25],0x08;; 1128 ld8 r6=[r25],0x08;; 1129 ld8 r7=[r25],0x08;; 1130 ld8 r17=[r25],0x08;; 1131 mov pr=r17,-1;; 1132 RESTORE_REG(ar.lc, r25, r17);; 1133 /* 1134 * Now Restore floating point regs 1135 */ 1136 ldf.fill.nta f2=[r25],16;; 1137 ldf.fill.nta f3=[r25],16;; 1138 ldf.fill.nta f4=[r25],16;; 1139 ldf.fill.nta f5=[r25],16;; 1140 ldf.fill.nta f16=[r25],16;; 1141 ldf.fill.nta f17=[r25],16;; 1142 ldf.fill.nta f18=[r25],16;; 1143 ldf.fill.nta f19=[r25],16;; 1144 ldf.fill.nta f20=[r25],16;; 1145 ldf.fill.nta f21=[r25],16;; 1146 ldf.fill.nta f22=[r25],16;; 1147 ldf.fill.nta f23=[r25],16;; 1148 ldf.fill.nta f24=[r25],16;; 1149 ldf.fill.nta f25=[r25],16;; 1150 ldf.fill.nta f26=[r25],16;; 1151 ldf.fill.nta f27=[r25],16;; 1152 ldf.fill.nta f28=[r25],16;; 1153 ldf.fill.nta f29=[r25],16;; 1154 ldf.fill.nta f30=[r25],16;; 1155 ldf.fill.nta f31=[r25],16;; 1156 1157 /* 1158 * Now that we have done all the register restores 1159 * we are now ready for the big DIVE to SAL Land 1160 */ 1161 ssm psr.ic;; 1162 srlz.d;; 1163 br.ret.sptk.many b0;; 1164 END(ia64_jump_to_sal) 1165 #endif /* CONFIG_HOTPLUG_CPU */ 1166 1167 #endif /* CONFIG_SMP */ 1168