threadasm.s 10.2 KB
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
#include <asm.h>
#include <regdef.h>
#include <os.h>
#include <R4300.h>

LOCALSZ=	24
FRAMESZ=	(((NARGSAVE+LOCALSZ)*SZREG)+ALSZ)&ALMASK

RAOFF=		FRAMESZ-(1*SZREG)
S8OFF=		FRAMESZ-(2*SZREG)
GPOFF=		FRAMESZ-(3*SZREG)
S7OFF=		FRAMESZ-(4*SZREG)
S6OFF=		FRAMESZ-(5*SZREG)
S5OFF=		FRAMESZ-(6*SZREG)
S4OFF=		FRAMESZ-(7*SZREG)
S3OFF=		FRAMESZ-(8*SZREG)
S2OFF=		FRAMESZ-(9*SZREG)
S1OFF=		FRAMESZ-(10*SZREG)
S0OFF=		FRAMESZ-(11*SZREG)

FP20OFF =	FRAMESZ-(12*SZREG)
FP21OFF =	FRAMESZ-(13*SZREG)
FP22OFF =	FRAMESZ-(14*SZREG)
FP23OFF =	FRAMESZ-(15*SZREG)
FP24OFF =	FRAMESZ-(16*SZREG)
FP25OFF =	FRAMESZ-(17*SZREG)
FP26OFF =	FRAMESZ-(18*SZREG)
FP27OFF =	FRAMESZ-(19*SZREG)
FP28OFF =	FRAMESZ-(20*SZREG)
FP29OFF =	FRAMESZ-(21*SZREG)
FP30OFF =	FRAMESZ-(22*SZREG)
FP31OFF =	FRAMESZ-(23*SZREG)

ATOFF=		FRAMESZ-(24*SZREG)
A0OFF=		FRAMESZ

/*
 * int yieldAndCheck(unsigned int);
 *
 * Dirty callee saved registers, call osYieldThread, and then check
 * that registers have been restored correctly.
 *
 */
NESTED(yieldAndCheck, FRAMESZ, ra)
	subu	sp,FRAMESZ
	sw	ra,RAOFF(sp)
	sw	s8,S8OFF(sp)
	sw	gp,GPOFF(sp)
	sw	s7,S7OFF(sp)
	sw	s6,S6OFF(sp)
	sw	s5,S5OFF(sp)
	sw	s4,S4OFF(sp)
	sw	s3,S3OFF(sp)
	sw	s2,S2OFF(sp)
	sw	s1,S1OFF(sp)
	sw	s0,S0OFF(sp)
	sw	a0,A0OFF(sp)

	addi	s0,a0,0
	addi	s1,a0,1
	addi	s2,a0,2
	addi	s3,a0,3
	addi	s4,a0,4
	addi	s5,a0,5
	addi	s6,a0,6
	addi	s7,a0,7
	addi	gp,a0,8
	addi	s8,a0,9

	jal	osYieldThread

	lw	a0,A0OFF(sp)
	addi	t0,a0,0
	bne	s0,t0,bad0
	addi	t0,a0,1
	bne	s1,t0,bad0
	addi	t0,a0,2
	bne	s2,t0,bad0
	addi	t0,a0,3
	bne	s3,t0,bad0
	addi	t0,a0,4
	bne	s4,t0,bad0
	addi	t0,a0,5
	bne	s5,t0,bad0
	addi	t0,a0,6
	bne	s6,t0,bad0
	addi	t0,a0,7
	bne	s7,t0,bad0
	addi	t0,a0,8
	bne	gp,t0,bad0
	addi	t0,a0,9
	bne	s8,t0,bad0
	move	v0,zero
	b	common0
bad0:
	li	v0,-1
common0:
	lw	s0, S0OFF(sp)
	lw	s1, S1OFF(sp)
	lw	s2, S2OFF(sp)
	lw	s3, S3OFF(sp)
	lw	s4, S4OFF(sp)
	lw	s5, S5OFF(sp)
	lw	s6, S6OFF(sp)
	lw	s7, S7OFF(sp)
	lw	gp, GPOFF(sp)
	lw	s8, S8OFF(sp)
	lw	ra, RAOFF(sp)
	addu	sp, FRAMESZ
	j	ra
	END(yieldAndCheck)

	.set	noat
/*
 * int dirtyAndCheck(unsigned int);
 *
 * Dirty all registers and check them.
 *
 */
LEAF(dirtyAndCheck)
	subu	sp,FRAMESZ
	sw	ra,RAOFF(sp)
	sw	s8,S8OFF(sp)
	sw	gp,GPOFF(sp)
	sw	s7,S7OFF(sp)
	sw	s6,S6OFF(sp)
	sw	s5,S5OFF(sp)
	sw	s4,S4OFF(sp)
	sw	s3,S3OFF(sp)
	sw	s2,S2OFF(sp)
	sw	s1,S1OFF(sp)
	sw	s0,S0OFF(sp)
	mfc1	t0,$f20
	sw	t0,FP20OFF(sp)
	mfc1	t0,$f21
	sw	t0,FP21OFF(sp)
	mfc1	t0,$f22
	sw	t0,FP22OFF(sp)
	mfc1	t0,$f23
	sw	t0,FP23OFF(sp)
	mfc1	t0,$f24
	sw	t0,FP24OFF(sp)
	mfc1	t0,$f25
	sw	t0,FP25OFF(sp)
	mfc1	t0,$f26
	sw	t0,FP26OFF(sp)
	mfc1	t0,$f27
	sw	t0,FP27OFF(sp)
	mfc1	t0,$f28
	sw	t0,FP28OFF(sp)
	mfc1	t0,$f29
	sw	t0,FP29OFF(sp)
	mfc1	t0,$f30
	sw	t0,FP30OFF(sp)
	mfc1	t0,$f31
	sw	t0,FP31OFF(sp)
	sw	a0,A0OFF(sp)

	/*
	 * Set each CPU to a unique value.
	 */
	addi	AT,a0,1
	addi	v0,AT,1
	addi	v1,v0,1
	addi	a1,v1,1
	addi	a2,a1,1
	addi	a3,a2,1
	addi	t0,a3,1
	addi	t1,t0,1
	addi	t2,t1,1
	addi	t3,t2,1
	addi	t4,t3,1
	addi	t5,t4,1
	addi	t6,t5,1
	addi	t7,t6,1
	addi	s0,t7,1
	addi	s1,s0,1
	addi	s2,s1,1
	addi	s3,s2,1
	addi	s4,s3,1
	addi	s5,s4,1
	addi	s6,s5,1
	addi	s7,s6,1
	addi	t8,s7,1
	addi	t9,t8,1
	addi	gp,t9,1
	addi	s8,gp,1
	addi	ra,s8,1

	/*
	 * Set each floating point register to a unique value.
	 */
	mtc1	a0,$f0
	addi	a0,1
	mtc1	a0,$f1
	addi	a0,1
	mtc1	a0,$f2
	addi	a0,1
	mtc1	a0,$f3
	addi	a0,1
	mtc1	a0,$f4
	addi	a0,1
	mtc1	a0,$f5
	addi	a0,1
	mtc1	a0,$f6
	addi	a0,1
	mtc1	a0,$f7
	addi	a0,1
	mtc1	a0,$f8
	addi	a0,1
	mtc1	a0,$f9
	addi	a0,1
	mtc1	a0,$f10
	addi	a0,1
	mtc1	a0,$f11
	addi	a0,1
	mtc1	a0,$f12
	addi	a0,1
	mtc1	a0,$f13
	addi	a0,1
	mtc1	a0,$f14
	addi	a0,1
	mtc1	a0,$f15
	addi	a0,1
	mtc1	a0,$f16
	addi	a0,1
	mtc1	a0,$f17
	addi	a0,1
	mtc1	a0,$f18
	addi	a0,1
	mtc1	a0,$f19
	addi	a0,1
	mtc1	a0,$f20
	addi	a0,1
	mtc1	a0,$f21
	addi	a0,1
	mtc1	a0,$f22
	addi	a0,1
	mtc1	a0,$f23
	addi	a0,1
	mtc1	a0,$f24
	addi	a0,1
	mtc1	a0,$f25
	addi	a0,1
	mtc1	a0,$f26
	addi	a0,1
	mtc1	a0,$f27
	addi	a0,1
	mtc1	a0,$f28
	addi	a0,1
	mtc1	a0,$f29
	addi	a0,1
	mtc1	a0,$f30
	addi	a0,1
	mtc1	a0,$f31
	addi	a0,1

	li	a0,0x01000000
	ctc1	a0,$31

	/*
	 * Enable SW2 interrupt, which will allow a higher
	 * priority thread to be scheduled and dirty the registers.
	 */
	.set	noreorder
	mfc0	a0, C0_SR
	ori	a0, OS_IM_SW2
	mtc0	a0, C0_SR
	lw	a0,A0OFF(sp)
	.set	reorder

	/*
	 * Check that a0 was the value just re-loaded before the interrupt.
	 * If the interrupt occurs before the re-loading of a0 above,
	 * the test below is kind of useless.  It appears, however, that
	 * interrupt occurs several instructions after the mtc0.
	 */
	sw	AT,ATOFF(sp)
	lw	AT,A0OFF(sp)
	bne	a0,AT,bad1
	lw	AT,ATOFF(sp)

	/* 
	 * Now use a0 as temporary register to compare against all
	 * other CPU registers.
	*/
	lw	a0,A0OFF(sp)
	addi	a0,1
	bne	AT,a0,bad1
	addi	a0,1
	bne	v0,a0,bad1
	addi	a0,1
	bne	v1,a0,bad1
	addi	a0,1
	bne	a1,a0,bad1
	addi	a0,1
	bne	a2,a0,bad1
	addi	a0,1
	bne	a3,a0,bad1
	addi	a0,1
	bne	t0,a0,bad1
	addi	a0,1
	bne	t1,a0,bad1
	addi	a0,1
	bne	t2,a0,bad1
	addi	a0,1
	bne	t3,a0,bad1
	addi	a0,1
	bne	t4,a0,bad1
	addi	a0,1
	bne	t5,a0,bad1
	addi	a0,1
	bne	t6,a0,bad1
	addi	a0,1
	bne	t7,a0,bad1
	addi	a0,1
	bne	s0,a0,bad1
	addi	a0,1
	bne	s1,a0,bad1
	addi	a0,1
	bne	s2,a0,bad1
	addi	a0,1
	bne	s3,a0,bad1
	addi	a0,1
	bne	s4,a0,bad1
	addi	a0,1
	bne	s5,a0,bad1
	addi	a0,1
	bne	s6,a0,bad1
	addi	a0,1
	bne	s7,a0,bad1
	addi	a0,1
	bne	t8,a0,bad1
	addi	a0,1
	bne	t9,a0,bad1
	addi	a0,1
	bne	gp,a0,bad1
	addi	a0,1
	bne	s8,a0,bad1
	addi	a0,1
	bne	ra,a0,bad1

	/*
	 * Now check floating point registers
	 */
	lw	a0,A0OFF(sp)
	mfc1	t0,$f0
	bne	a0,t0,bad1
	addi	a0,1
	mfc1	t0,$f1
	bne	a0,t0,bad1
	addi	a0,1
	mfc1	t0,$f2
	bne	a0,t0,bad1
	addi	a0,1
	mfc1	t0,$f3
	bne	a0,t0,bad1
	addi	a0,1
	mfc1	t0,$f4
	bne	a0,t0,bad1
	addi	a0,1
	mfc1	t0,$f5
	bne	a0,t0,bad1
	addi	a0,1
	mfc1	t0,$f6
	bne	a0,t0,bad1
	addi	a0,1
	mfc1	t0,$f7
	bne	a0,t0,bad1
	addi	a0,1
	mfc1	t0,$f8
	bne	a0,t0,bad1
	addi	a0,1
	mfc1	t0,$f9
	bne	a0,t0,bad1
	addi	a0,1
	mfc1	t0,$f10
	bne	a0,t0,bad1
	addi	a0,1
	mfc1	t0,$f11
	bne	a0,t0,bad1
	addi	a0,1
	mfc1	t0,$f12
	bne	a0,t0,bad1
	addi	a0,1
	mfc1	t0,$f13
	bne	a0,t0,bad1
	addi	a0,1
	mfc1	t0,$f14
	bne	a0,t0,bad1
	addi	a0,1
	mfc1	t0,$f15
	bne	a0,t0,bad1
	addi	a0,1
	mfc1	t0,$f16
	bne	a0,t0,bad1
	addi	a0,1
	mfc1	t0,$f17
	bne	a0,t0,bad1
	addi	a0,1
	mfc1	t0,$f18
	bne	a0,t0,bad1
	addi	a0,1
	mfc1	t0,$f19
	bne	a0,t0,bad1
	addi	a0,1
	mfc1	t0,$f20
	bne	a0,t0,bad1
	addi	a0,1
	mfc1	t0,$f21
	bne	a0,t0,bad1
	addi	a0,1
	mfc1	t0,$f22
	bne	a0,t0,bad1
	addi	a0,1
	mfc1	t0,$f23
	bne	a0,t0,bad1
	addi	a0,1
	mfc1	t0,$f24
	bne	a0,t0,bad1
	addi	a0,1
	mfc1	t0,$f25
	bne	a0,t0,bad1
	addi	a0,1
	mfc1	t0,$f26
	bne	a0,t0,bad1
	addi	a0,1
	mfc1	t0,$f27
	bne	a0,t0,bad1
	addi	a0,1
	mfc1	t0,$f28
	bne	a0,t0,bad1
	addi	a0,1
	mfc1	t0,$f29
	bne	a0,t0,bad1
	addi	a0,1
	mfc1	t0,$f30
	bne	a0,t0,bad1
	addi	a0,1
	mfc1	t0,$f31
	bne	a0,t0,bad1

	li	a0,0x01000000
	cfc1	t0,$31
	bne	a0,t0,bad1

	move	v0,zero
	b	common1
bad1:
	li	v0,-1
common1:
	lw	t0,FP20OFF(sp)
	mtc1	t0,$f20
	lw	t0,FP21OFF(sp)
	mtc1	t0,$f21
	lw	t0,FP22OFF(sp)
	mtc1	t0,$f22
	lw	t0,FP23OFF(sp)
	mtc1	t0,$f23
	lw	t0,FP24OFF(sp)
	mtc1	t0,$f24
	lw	t0,FP25OFF(sp)
	mtc1	t0,$f25
	lw	t0,FP26OFF(sp)
	mtc1	t0,$f26
	lw	t0,FP27OFF(sp)
	mtc1	t0,$f27
	lw	t0,FP28OFF(sp)
	mtc1	t0,$f28
	lw	t0,FP29OFF(sp)
	mtc1	t0,$f29
	lw	t0,FP30OFF(sp)
	mtc1	t0,$f30
	lw	t0,FP31OFF(sp)
	mtc1	t0,$f31
	lw	s0,S0OFF(sp)
	lw	s1,S1OFF(sp)
	lw	s2,S2OFF(sp)
	lw	s3,S3OFF(sp)
	lw	s4,S4OFF(sp)
	lw	s5,S5OFF(sp)
	lw	s6,S6OFF(sp)
	lw	s7,S7OFF(sp)
	lw	gp,GPOFF(sp)
	lw	s8,S8OFF(sp)
	lw	ra,RAOFF(sp)
	addu	sp,FRAMESZ
	j	ra
END(dirtyAndCheck)

/*
 * void waitAndDirty(unsigned int);
 *
 * Block for interrupt message; then dirty all registers.
 *
 */

	.extern	softintMesgQueue

LEAF(waitAndDirty)
	subu	sp,FRAMESZ
	sw	ra,RAOFF(sp)
	sw	s8,S8OFF(sp)
	sw	gp,GPOFF(sp)
	sw	s7,S7OFF(sp)
	sw	s6,S6OFF(sp)
	sw	s5,S5OFF(sp)
	sw	s4,S4OFF(sp)
	sw	s3,S3OFF(sp)
	sw	s2,S2OFF(sp)
	sw	s1,S1OFF(sp)
	sw	s0,S0OFF(sp)
	mfc1	t0,$f20
	sw	t0,FP20OFF(sp)
	mfc1	t0,$f21
	sw	t0,FP21OFF(sp)
	mfc1	t0,$f22
	sw	t0,FP22OFF(sp)
	mfc1	t0,$f23
	sw	t0,FP23OFF(sp)
	mfc1	t0,$f24
	sw	t0,FP24OFF(sp)
	mfc1	t0,$f25
	sw	t0,FP25OFF(sp)
	mfc1	t0,$f26
	sw	t0,FP26OFF(sp)
	mfc1	t0,$f27
	sw	t0,FP27OFF(sp)
	mfc1	t0,$f28
	sw	t0,FP28OFF(sp)
	mfc1	t0,$f29
	sw	t0,FP29OFF(sp)
	mfc1	t0,$f30
	sw	t0,FP30OFF(sp)
	mfc1	t0,$f31
	sw	t0,FP31OFF(sp)
	sw	a0,A0OFF(sp)

	/*
	 * (void)osRecvMesg(&softintMesgQueue, OS_MESG_BLOCK);
	 */
	la	a0,softintMesgQueue
	li	a1,OS_MESG_BLOCK
	jal	osRecvMesg

	/*
	 * Set each CPU register to a unique value.
	 */
	lw	a0,A0OFF(sp)
	addi	AT,a0,1
	addi	v0,AT,1
	addi	v1,v0,1
	addi	a1,v1,1
	addi	a2,a1,1
	addi	a3,a2,1
	addi	t0,a3,1
	addi	t1,t0,1
	addi	t2,t1,1
	addi	t3,t2,1
	addi	t4,t3,1
	addi	t5,t4,1
	addi	t6,t5,1
	addi	t7,t6,1
	addi	s0,t7,1
	addi	s1,s0,1
	addi	s2,s1,1
	addi	s3,s2,1
	addi	s4,s3,1
	addi	s5,s4,1
	addi	s6,s5,1
	addi	s7,s6,1
	addi	t8,s7,1
	addi	t9,t8,1
	addi	gp,t9,1
	addi	s8,gp,1
	addi	ra,s8,1

	/*
	 * Set each FPU register to a unique value.
	 */
	mtc1	a0,$f0
	addi	a0,1
	mtc1	a0,$f1
	addi	a0,1
	mtc1	a0,$f2
	addi	a0,1
	mtc1	a0,$f3
	addi	a0,1
	mtc1	a0,$f4
	addi	a0,1
	mtc1	a0,$f5
	addi	a0,1
	mtc1	a0,$f6
	addi	a0,1
	mtc1	a0,$f7
	addi	a0,1
	mtc1	a0,$f8
	addi	a0,1
	mtc1	a0,$f9
	addi	a0,1
	mtc1	a0,$f10
	addi	a0,1
	mtc1	a0,$f11
	addi	a0,1
	mtc1	a0,$f12
	addi	a0,1
	mtc1	a0,$f13
	addi	a0,1
	mtc1	a0,$f14
	addi	a0,1
	mtc1	a0,$f15
	addi	a0,1
	mtc1	a0,$f16
	addi	a0,1
	mtc1	a0,$f17
	addi	a0,1
	mtc1	a0,$f18
	addi	a0,1
	mtc1	a0,$f19
	addi	a0,1
	mtc1	a0,$f20
	addi	a0,1
	mtc1	a0,$f21
	addi	a0,1
	mtc1	a0,$f22
	addi	a0,1
	mtc1	a0,$f23
	addi	a0,1
	mtc1	a0,$f24
	addi	a0,1
	mtc1	a0,$f25
	addi	a0,1
	mtc1	a0,$f26
	addi	a0,1
	mtc1	a0,$f27
	addi	a0,1
	mtc1	a0,$f28
	addi	a0,1
	mtc1	a0,$f29
	addi	a0,1
	mtc1	a0,$f30
	addi	a0,1
	mtc1	a0,$f31

	move	v0,zero
	lw	t0,FP20OFF(sp)
	mtc1	t0,$f20
	lw	t0,FP21OFF(sp)
	mtc1	t0,$f21
	lw	t0,FP22OFF(sp)
	mtc1	t0,$f22
	lw	t0,FP23OFF(sp)
	mtc1	t0,$f23
	lw	t0,FP24OFF(sp)
	mtc1	t0,$f24
	lw	t0,FP25OFF(sp)
	mtc1	t0,$f25
	lw	t0,FP26OFF(sp)
	mtc1	t0,$f26
	lw	t0,FP27OFF(sp)
	mtc1	t0,$f27
	lw	t0,FP28OFF(sp)
	mtc1	t0,$f28
	lw	t0,FP29OFF(sp)
	mtc1	t0,$f29
	lw	t0,FP30OFF(sp)
	mtc1	t0,$f30
	lw	t0,FP31OFF(sp)
	mtc1	t0,$f31
	lw	s0,S0OFF(sp)
	lw	s1,S1OFF(sp)
	lw	s2,S2OFF(sp)
	lw	s3,S3OFF(sp)
	lw	s4,S4OFF(sp)
	lw	s5,S5OFF(sp)
	lw	s6,S6OFF(sp)
	lw	s7,S7OFF(sp)
	lw	gp,GPOFF(sp)
	lw	s8,S8OFF(sp)
	lw	ra,RAOFF(sp)
	addu	sp,FRAMESZ
	j	ra
END(dirtyRegs)
	.set	at

LEAF(doBreak)
	break	0
	j	ra
END(doBreak)