Linux preempt-rt

Check our new training course

Real-Time Linux with PREEMPT_RT

Check our new training course
with Creative Commons CC-BY-SA
lecture and lab materials

Bootlin logo

Elixir Cross Referencer

   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
// SPDX-License-Identifier: GPL-2.0
/*
 *  Copyright (C) 1991, 1992  Linus Torvalds
 *  Copyright (C) 2000, 2001, 2002 Andi Kleen SuSE Labs
 *
 *  1997-11-28  Modified for POSIX.1b signals by Richard Henderson
 *  2000-06-20  Pentium III FXSR, SSE support by Gareth Hughes
 *  2000-2002   x86-64 support by Andi Kleen
 */

#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt

#include <linux/sched.h>
#include <linux/sched/task_stack.h>
#include <linux/mm.h>
#include <linux/smp.h>
#include <linux/kernel.h>
#include <linux/kstrtox.h>
#include <linux/errno.h>
#include <linux/wait.h>
#include <linux/unistd.h>
#include <linux/stddef.h>
#include <linux/personality.h>
#include <linux/uaccess.h>
#include <linux/user-return-notifier.h>
#include <linux/uprobes.h>
#include <linux/context_tracking.h>
#include <linux/entry-common.h>
#include <linux/syscalls.h>

#include <asm/processor.h>
#include <asm/ucontext.h>
#include <asm/fpu/signal.h>
#include <asm/fpu/xstate.h>
#include <asm/vdso.h>
#include <asm/mce.h>
#include <asm/sighandling.h>
#include <asm/vm86.h>

#ifdef CONFIG_X86_64
#include <linux/compat.h>
#include <asm/proto.h>
#include <asm/ia32_unistd.h>
#include <asm/fpu/xstate.h>
#endif /* CONFIG_X86_64 */

#include <asm/syscall.h>
#include <asm/sigframe.h>
#include <asm/signal.h>

#ifdef CONFIG_X86_64
/*
 * If regs->ss will cause an IRET fault, change it.  Otherwise leave it
 * alone.  Using this generally makes no sense unless
 * user_64bit_mode(regs) would return true.
 */
static void force_valid_ss(struct pt_regs *regs)
{
	u32 ar;
	asm volatile ("lar %[old_ss], %[ar]\n\t"
		      "jz 1f\n\t"		/* If invalid: */
		      "xorl %[ar], %[ar]\n\t"	/* set ar = 0 */
		      "1:"
		      : [ar] "=r" (ar)
		      : [old_ss] "rm" ((u16)regs->ss));

	/*
	 * For a valid 64-bit user context, we need DPL 3, type
	 * read-write data or read-write exp-down data, and S and P
	 * set.  We can't use VERW because VERW doesn't check the
	 * P bit.
	 */
	ar &= AR_DPL_MASK | AR_S | AR_P | AR_TYPE_MASK;
	if (ar != (AR_DPL3 | AR_S | AR_P | AR_TYPE_RWDATA) &&
	    ar != (AR_DPL3 | AR_S | AR_P | AR_TYPE_RWDATA_EXPDOWN))
		regs->ss = __USER_DS;
}
# define CONTEXT_COPY_SIZE	offsetof(struct sigcontext, reserved1)
#else
# define CONTEXT_COPY_SIZE	sizeof(struct sigcontext)
#endif

static bool restore_sigcontext(struct pt_regs *regs,
			       struct sigcontext __user *usc,
			       unsigned long uc_flags)
{
	struct sigcontext sc;

	/* Always make any pending restarted system calls return -EINTR */
	current->restart_block.fn = do_no_restart_syscall;

	if (copy_from_user(&sc, usc, CONTEXT_COPY_SIZE))
		return false;

#ifdef CONFIG_X86_32
	loadsegment(gs, sc.gs);
	regs->fs = sc.fs;
	regs->es = sc.es;
	regs->ds = sc.ds;
#endif /* CONFIG_X86_32 */

	regs->bx = sc.bx;
	regs->cx = sc.cx;
	regs->dx = sc.dx;
	regs->si = sc.si;
	regs->di = sc.di;
	regs->bp = sc.bp;
	regs->ax = sc.ax;
	regs->sp = sc.sp;
	regs->ip = sc.ip;

#ifdef CONFIG_X86_64
	regs->r8 = sc.r8;
	regs->r9 = sc.r9;
	regs->r10 = sc.r10;
	regs->r11 = sc.r11;
	regs->r12 = sc.r12;
	regs->r13 = sc.r13;
	regs->r14 = sc.r14;
	regs->r15 = sc.r15;
#endif /* CONFIG_X86_64 */

	/* Get CS/SS and force CPL3 */
	regs->cs = sc.cs | 0x03;
	regs->ss = sc.ss | 0x03;

	regs->flags = (regs->flags & ~FIX_EFLAGS) | (sc.flags & FIX_EFLAGS);
	/* disable syscall checks */
	regs->orig_ax = -1;

#ifdef CONFIG_X86_64
	/*
	 * Fix up SS if needed for the benefit of old DOSEMU and
	 * CRIU.
	 */
	if (unlikely(!(uc_flags & UC_STRICT_RESTORE_SS) && user_64bit_mode(regs)))
		force_valid_ss(regs);
#endif

	return fpu__restore_sig((void __user *)sc.fpstate,
			       IS_ENABLED(CONFIG_X86_32));
}

static __always_inline int
__unsafe_setup_sigcontext(struct sigcontext __user *sc, void __user *fpstate,
		     struct pt_regs *regs, unsigned long mask)
{
#ifdef CONFIG_X86_32
	unsigned int gs;
	savesegment(gs, gs);

	unsafe_put_user(gs,	  (unsigned int __user *)&sc->gs, Efault);
	unsafe_put_user(regs->fs, (unsigned int __user *)&sc->fs, Efault);
	unsafe_put_user(regs->es, (unsigned int __user *)&sc->es, Efault);
	unsafe_put_user(regs->ds, (unsigned int __user *)&sc->ds, Efault);
#endif /* CONFIG_X86_32 */

	unsafe_put_user(regs->di, &sc->di, Efault);
	unsafe_put_user(regs->si, &sc->si, Efault);
	unsafe_put_user(regs->bp, &sc->bp, Efault);
	unsafe_put_user(regs->sp, &sc->sp, Efault);
	unsafe_put_user(regs->bx, &sc->bx, Efault);
	unsafe_put_user(regs->dx, &sc->dx, Efault);
	unsafe_put_user(regs->cx, &sc->cx, Efault);
	unsafe_put_user(regs->ax, &sc->ax, Efault);
#ifdef CONFIG_X86_64
	unsafe_put_user(regs->r8, &sc->r8, Efault);
	unsafe_put_user(regs->r9, &sc->r9, Efault);
	unsafe_put_user(regs->r10, &sc->r10, Efault);
	unsafe_put_user(regs->r11, &sc->r11, Efault);
	unsafe_put_user(regs->r12, &sc->r12, Efault);
	unsafe_put_user(regs->r13, &sc->r13, Efault);
	unsafe_put_user(regs->r14, &sc->r14, Efault);
	unsafe_put_user(regs->r15, &sc->r15, Efault);
#endif /* CONFIG_X86_64 */

	unsafe_put_user(current->thread.trap_nr, &sc->trapno, Efault);
	unsafe_put_user(current->thread.error_code, &sc->err, Efault);
	unsafe_put_user(regs->ip, &sc->ip, Efault);
#ifdef CONFIG_X86_32
	unsafe_put_user(regs->cs, (unsigned int __user *)&sc->cs, Efault);
	unsafe_put_user(regs->flags, &sc->flags, Efault);
	unsafe_put_user(regs->sp, &sc->sp_at_signal, Efault);
	unsafe_put_user(regs->ss, (unsigned int __user *)&sc->ss, Efault);
#else /* !CONFIG_X86_32 */
	unsafe_put_user(regs->flags, &sc->flags, Efault);
	unsafe_put_user(regs->cs, &sc->cs, Efault);
	unsafe_put_user(0, &sc->gs, Efault);
	unsafe_put_user(0, &sc->fs, Efault);
	unsafe_put_user(regs->ss, &sc->ss, Efault);
#endif /* CONFIG_X86_32 */

	unsafe_put_user(fpstate, (unsigned long __user *)&sc->fpstate, Efault);

	/* non-iBCS2 extensions.. */
	unsafe_put_user(mask, &sc->oldmask, Efault);
	unsafe_put_user(current->thread.cr2, &sc->cr2, Efault);
	return 0;
Efault:
	return -EFAULT;
}

#define unsafe_put_sigcontext(sc, fp, regs, set, label)			\
do {									\
	if (__unsafe_setup_sigcontext(sc, fp, regs, set->sig[0]))	\
		goto label;						\
} while(0);

#define unsafe_put_sigmask(set, frame, label) \
	unsafe_put_user(*(__u64 *)(set), \
			(__u64 __user *)&(frame)->uc.uc_sigmask, \
			label)

/*
 * Set up a signal frame.
 */

/* x86 ABI requires 16-byte alignment */
#define FRAME_ALIGNMENT	16UL

#define MAX_FRAME_PADDING	(FRAME_ALIGNMENT - 1)

/*
 * Determine which stack to use..
 */
static unsigned long align_sigframe(unsigned long sp)
{
#ifdef CONFIG_X86_32
	/*
	 * Align the stack pointer according to the i386 ABI,
	 * i.e. so that on function entry ((sp + 4) & 15) == 0.
	 */
	sp = ((sp + 4) & -FRAME_ALIGNMENT) - 4;
#else /* !CONFIG_X86_32 */
	sp = round_down(sp, FRAME_ALIGNMENT) - 8;
#endif
	return sp;
}

static void __user *
get_sigframe(struct k_sigaction *ka, struct pt_regs *regs, size_t frame_size,
	     void __user **fpstate)
{
	/* Default to using normal stack */
	bool nested_altstack = on_sig_stack(regs->sp);
	bool entering_altstack = false;
	unsigned long math_size = 0;
	unsigned long sp = regs->sp;
	unsigned long buf_fx = 0;

	/* redzone */
	if (IS_ENABLED(CONFIG_X86_64))
		sp -= 128;

	/* This is the X/Open sanctioned signal stack switching.  */
	if (ka->sa.sa_flags & SA_ONSTACK) {
		/*
		 * This checks nested_altstack via sas_ss_flags(). Sensible
		 * programs use SS_AUTODISARM, which disables that check, and
		 * programs that don't use SS_AUTODISARM get compatible.
		 */
		if (sas_ss_flags(sp) == 0) {
			sp = current->sas_ss_sp + current->sas_ss_size;
			entering_altstack = true;
		}
	} else if (IS_ENABLED(CONFIG_X86_32) &&
		   !nested_altstack &&
		   regs->ss != __USER_DS &&
		   !(ka->sa.sa_flags & SA_RESTORER) &&
		   ka->sa.sa_restorer) {
		/* This is the legacy signal stack switching. */
		sp = (unsigned long) ka->sa.sa_restorer;
		entering_altstack = true;
	}

	sp = fpu__alloc_mathframe(sp, IS_ENABLED(CONFIG_X86_32),
				  &buf_fx, &math_size);
	*fpstate = (void __user *)sp;

	sp = align_sigframe(sp - frame_size);

	/*
	 * If we are on the alternate signal stack and would overflow it, don't.
	 * Return an always-bogus address instead so we will die with SIGSEGV.
	 */
	if (unlikely((nested_altstack || entering_altstack) &&
		     !__on_sig_stack(sp))) {

		if (show_unhandled_signals && printk_ratelimit())
			pr_info("%s[%d] overflowed sigaltstack\n",
				current->comm, task_pid_nr(current));

		return (void __user *)-1L;
	}

	/* save i387 and extended state */
	if (!copy_fpstate_to_sigframe(*fpstate, (void __user *)buf_fx, math_size))
		return (void __user *)-1L;

	return (void __user *)sp;
}

#ifdef CONFIG_X86_32
static const struct {
	u16 poplmovl;
	u32 val;
	u16 int80;
} __attribute__((packed)) retcode = {
	0xb858,		/* popl %eax; movl $..., %eax */
	__NR_sigreturn,
	0x80cd,		/* int $0x80 */
};

static const struct {
	u8  movl;
	u32 val;
	u16 int80;
	u8  pad;
} __attribute__((packed)) rt_retcode = {
	0xb8,		/* movl $..., %eax */
	__NR_rt_sigreturn,
	0x80cd,		/* int $0x80 */
	0
};

static int
__setup_frame(int sig, struct ksignal *ksig, sigset_t *set,
	      struct pt_regs *regs)
{
	struct sigframe __user *frame;
	void __user *restorer;
	void __user *fp = NULL;

	frame = get_sigframe(&ksig->ka, regs, sizeof(*frame), &fp);

	if (!user_access_begin(frame, sizeof(*frame)))
		return -EFAULT;

	unsafe_put_user(sig, &frame->sig, Efault);
	unsafe_put_sigcontext(&frame->sc, fp, regs, set, Efault);
	unsafe_put_user(set->sig[1], &frame->extramask[0], Efault);
	if (current->mm->context.vdso)
		restorer = current->mm->context.vdso +
			vdso_image_32.sym___kernel_sigreturn;
	else
		restorer = &frame->retcode;
	if (ksig->ka.sa.sa_flags & SA_RESTORER)
		restorer = ksig->ka.sa.sa_restorer;

	/* Set up to return from userspace.  */
	unsafe_put_user(restorer, &frame->pretcode, Efault);

	/*
	 * This is popl %eax ; movl $__NR_sigreturn, %eax ; int $0x80
	 *
	 * WE DO NOT USE IT ANY MORE! It's only left here for historical
	 * reasons and because gdb uses it as a signature to notice
	 * signal handler stack frames.
	 */
	unsafe_put_user(*((u64 *)&retcode), (u64 *)frame->retcode, Efault);
	user_access_end();

	/* Set up registers for signal handler */
	regs->sp = (unsigned long)frame;
	regs->ip = (unsigned long)ksig->ka.sa.sa_handler;
	regs->ax = (unsigned long)sig;
	regs->dx = 0;
	regs->cx = 0;

	regs->ds = __USER_DS;
	regs->es = __USER_DS;
	regs->ss = __USER_DS;
	regs->cs = __USER_CS;

	return 0;

Efault:
	user_access_end();
	return -EFAULT;
}

static int __setup_rt_frame(int sig, struct ksignal *ksig,
			    sigset_t *set, struct pt_regs *regs)
{
	struct rt_sigframe __user *frame;
	void __user *restorer;
	void __user *fp = NULL;

	frame = get_sigframe(&ksig->ka, regs, sizeof(*frame), &fp);

	if (!user_access_begin(frame, sizeof(*frame)))
		return -EFAULT;

	unsafe_put_user(sig, &frame->sig, Efault);
	unsafe_put_user(&frame->info, &frame->pinfo, Efault);
	unsafe_put_user(&frame->uc, &frame->puc, Efault);

	/* Create the ucontext.  */
	if (static_cpu_has(X86_FEATURE_XSAVE))
		unsafe_put_user(UC_FP_XSTATE, &frame->uc.uc_flags, Efault);
	else
		unsafe_put_user(0, &frame->uc.uc_flags, Efault);
	unsafe_put_user(0, &frame->uc.uc_link, Efault);
	unsafe_save_altstack(&frame->uc.uc_stack, regs->sp, Efault);

	/* Set up to return from userspace.  */
	restorer = current->mm->context.vdso +
		vdso_image_32.sym___kernel_rt_sigreturn;
	if (ksig->ka.sa.sa_flags & SA_RESTORER)
		restorer = ksig->ka.sa.sa_restorer;
	unsafe_put_user(restorer, &frame->pretcode, Efault);

	/*
	 * This is movl $__NR_rt_sigreturn, %ax ; int $0x80
	 *
	 * WE DO NOT USE IT ANY MORE! It's only left here for historical
	 * reasons and because gdb uses it as a signature to notice
	 * signal handler stack frames.
	 */
	unsafe_put_user(*((u64 *)&rt_retcode), (u64 *)frame->retcode, Efault);
	unsafe_put_sigcontext(&frame->uc.uc_mcontext, fp, regs, set, Efault);
	unsafe_put_sigmask(set, frame, Efault);
	user_access_end();
	
	if (copy_siginfo_to_user(&frame->info, &ksig->info))
		return -EFAULT;

	/* Set up registers for signal handler */
	regs->sp = (unsigned long)frame;
	regs->ip = (unsigned long)ksig->ka.sa.sa_handler;
	regs->ax = (unsigned long)sig;
	regs->dx = (unsigned long)&frame->info;
	regs->cx = (unsigned long)&frame->uc;

	regs->ds = __USER_DS;
	regs->es = __USER_DS;
	regs->ss = __USER_DS;
	regs->cs = __USER_CS;

	return 0;
Efault:
	user_access_end();
	return -EFAULT;
}
#else /* !CONFIG_X86_32 */
static unsigned long frame_uc_flags(struct pt_regs *regs)
{
	unsigned long flags;

	if (boot_cpu_has(X86_FEATURE_XSAVE))
		flags = UC_FP_XSTATE | UC_SIGCONTEXT_SS;
	else
		flags = UC_SIGCONTEXT_SS;

	if (likely(user_64bit_mode(regs)))
		flags |= UC_STRICT_RESTORE_SS;

	return flags;
}

static int __setup_rt_frame(int sig, struct ksignal *ksig,
			    sigset_t *set, struct pt_regs *regs)
{
	struct rt_sigframe __user *frame;
	void __user *fp = NULL;
	unsigned long uc_flags;

	/* x86-64 should always use SA_RESTORER. */
	if (!(ksig->ka.sa.sa_flags & SA_RESTORER))
		return -EFAULT;

	frame = get_sigframe(&ksig->ka, regs, sizeof(struct rt_sigframe), &fp);
	uc_flags = frame_uc_flags(regs);

	if (!user_access_begin(frame, sizeof(*frame)))
		return -EFAULT;

	/* Create the ucontext.  */
	unsafe_put_user(uc_flags, &frame->uc.uc_flags, Efault);
	unsafe_put_user(0, &frame->uc.uc_link, Efault);
	unsafe_save_altstack(&frame->uc.uc_stack, regs->sp, Efault);

	/* Set up to return from userspace.  If provided, use a stub
	   already in userspace.  */
	unsafe_put_user(ksig->ka.sa.sa_restorer, &frame->pretcode, Efault);
	unsafe_put_sigcontext(&frame->uc.uc_mcontext, fp, regs, set, Efault);
	unsafe_put_sigmask(set, frame, Efault);
	user_access_end();

	if (ksig->ka.sa.sa_flags & SA_SIGINFO) {
		if (copy_siginfo_to_user(&frame->info, &ksig->info))
			return -EFAULT;
	}

	/* Set up registers for signal handler */
	regs->di = sig;
	/* In case the signal handler was declared without prototypes */
	regs->ax = 0;

	/* This also works for non SA_SIGINFO handlers because they expect the
	   next argument after the signal number on the stack. */
	regs->si = (unsigned long)&frame->info;
	regs->dx = (unsigned long)&frame->uc;
	regs->ip = (unsigned long) ksig->ka.sa.sa_handler;

	regs->sp = (unsigned long)frame;

	/*
	 * Set up the CS and SS registers to run signal handlers in
	 * 64-bit mode, even if the handler happens to be interrupting
	 * 32-bit or 16-bit code.
	 *
	 * SS is subtle.  In 64-bit mode, we don't need any particular
	 * SS descriptor, but we do need SS to be valid.  It's possible
	 * that the old SS is entirely bogus -- this can happen if the
	 * signal we're trying to deliver is #GP or #SS caused by a bad
	 * SS value.  We also have a compatibility issue here: DOSEMU
	 * relies on the contents of the SS register indicating the
	 * SS value at the time of the signal, even though that code in
	 * DOSEMU predates sigreturn's ability to restore SS.  (DOSEMU
	 * avoids relying on sigreturn to restore SS; instead it uses
	 * a trampoline.)  So we do our best: if the old SS was valid,
	 * we keep it.  Otherwise we replace it.
	 */
	regs->cs = __USER_CS;

	if (unlikely(regs->ss != __USER_DS))
		force_valid_ss(regs);

	return 0;

Efault:
	user_access_end();
	return -EFAULT;
}
#endif /* CONFIG_X86_32 */

#ifdef CONFIG_X86_X32_ABI
static int x32_copy_siginfo_to_user(struct compat_siginfo __user *to,
		const struct kernel_siginfo *from)
{
	struct compat_siginfo new;

	copy_siginfo_to_external32(&new, from);
	if (from->si_signo == SIGCHLD) {
		new._sifields._sigchld_x32._utime = from->si_utime;
		new._sifields._sigchld_x32._stime = from->si_stime;
	}
	if (copy_to_user(to, &new, sizeof(struct compat_siginfo)))
		return -EFAULT;
	return 0;
}

int copy_siginfo_to_user32(struct compat_siginfo __user *to,
			   const struct kernel_siginfo *from)
{
	if (in_x32_syscall())
		return x32_copy_siginfo_to_user(to, from);
	return __copy_siginfo_to_user32(to, from);
}
#endif /* CONFIG_X86_X32_ABI */

static int x32_setup_rt_frame(struct ksignal *ksig,
			      compat_sigset_t *set,
			      struct pt_regs *regs)
{
#ifdef CONFIG_X86_X32_ABI
	struct rt_sigframe_x32 __user *frame;
	unsigned long uc_flags;
	void __user *restorer;
	void __user *fp = NULL;

	if (!(ksig->ka.sa.sa_flags & SA_RESTORER))
		return -EFAULT;

	frame = get_sigframe(&ksig->ka, regs, sizeof(*frame), &fp);

	uc_flags = frame_uc_flags(regs);

	if (!user_access_begin(frame, sizeof(*frame)))
		return -EFAULT;

	/* Create the ucontext.  */
	unsafe_put_user(uc_flags, &frame->uc.uc_flags, Efault);
	unsafe_put_user(0, &frame->uc.uc_link, Efault);
	unsafe_compat_save_altstack(&frame->uc.uc_stack, regs->sp, Efault);
	unsafe_put_user(0, &frame->uc.uc__pad0, Efault);
	restorer = ksig->ka.sa.sa_restorer;
	unsafe_put_user(restorer, (unsigned long __user *)&frame->pretcode, Efault);
	unsafe_put_sigcontext(&frame->uc.uc_mcontext, fp, regs, set, Efault);
	unsafe_put_sigmask(set, frame, Efault);
	user_access_end();

	if (ksig->ka.sa.sa_flags & SA_SIGINFO) {
		if (x32_copy_siginfo_to_user(&frame->info, &ksig->info))
			return -EFAULT;
	}

	/* Set up registers for signal handler */
	regs->sp = (unsigned long) frame;
	regs->ip = (unsigned long) ksig->ka.sa.sa_handler;

	/* We use the x32 calling convention here... */
	regs->di = ksig->sig;
	regs->si = (unsigned long) &frame->info;
	regs->dx = (unsigned long) &frame->uc;

	loadsegment(ds, __USER_DS);
	loadsegment(es, __USER_DS);

	regs->cs = __USER_CS;
	regs->ss = __USER_DS;
#endif	/* CONFIG_X86_X32_ABI */

	return 0;
#ifdef CONFIG_X86_X32_ABI
Efault:
	user_access_end();
	return -EFAULT;
#endif
}

/*
 * Do a signal return; undo the signal stack.
 */
#ifdef CONFIG_X86_32
SYSCALL_DEFINE0(sigreturn)
{
	struct pt_regs *regs = current_pt_regs();
	struct sigframe __user *frame;
	sigset_t set;

	frame = (struct sigframe __user *)(regs->sp - 8);

	if (!access_ok(frame, sizeof(*frame)))
		goto badframe;
	if (__get_user(set.sig[0], &frame->sc.oldmask) ||
	    __get_user(set.sig[1], &frame->extramask[0]))
		goto badframe;

	set_current_blocked(&set);

	/*
	 * x86_32 has no uc_flags bits relevant to restore_sigcontext.
	 * Save a few cycles by skipping the __get_user.
	 */
	if (!restore_sigcontext(regs, &frame->sc, 0))
		goto badframe;
	return regs->ax;

badframe:
	signal_fault(regs, frame, "sigreturn");

	return 0;
}
#endif /* CONFIG_X86_32 */

SYSCALL_DEFINE0(rt_sigreturn)
{
	struct pt_regs *regs = current_pt_regs();
	struct rt_sigframe __user *frame;
	sigset_t set;
	unsigned long uc_flags;

	frame = (struct rt_sigframe __user *)(regs->sp - sizeof(long));
	if (!access_ok(frame, sizeof(*frame)))
		goto badframe;
	if (__get_user(*(__u64 *)&set, (__u64 __user *)&frame->uc.uc_sigmask))
		goto badframe;
	if (__get_user(uc_flags, &frame->uc.uc_flags))
		goto badframe;

	set_current_blocked(&set);

	if (!restore_sigcontext(regs, &frame->uc.uc_mcontext, uc_flags))
		goto badframe;

	if (restore_altstack(&frame->uc.uc_stack))
		goto badframe;

	return regs->ax;

badframe:
	signal_fault(regs, frame, "rt_sigreturn");
	return 0;
}

/*
 * There are four different struct types for signal frame: sigframe_ia32,
 * rt_sigframe_ia32, rt_sigframe_x32, and rt_sigframe. Use the worst case
 * -- the largest size. It means the size for 64-bit apps is a bit more
 * than needed, but this keeps the code simple.
 */
#if defined(CONFIG_X86_32) || defined(CONFIG_IA32_EMULATION)
# define MAX_FRAME_SIGINFO_UCTXT_SIZE	sizeof(struct sigframe_ia32)
#else
# define MAX_FRAME_SIGINFO_UCTXT_SIZE	sizeof(struct rt_sigframe)
#endif

/*
 * The FP state frame contains an XSAVE buffer which must be 64-byte aligned.
 * If a signal frame starts at an unaligned address, extra space is required.
 * This is the max alignment padding, conservatively.
 */
#define MAX_XSAVE_PADDING	63UL

/*
 * The frame data is composed of the following areas and laid out as:
 *
 * -------------------------
 * | alignment padding     |
 * -------------------------
 * | (f)xsave frame        |
 * -------------------------
 * | fsave header          |
 * -------------------------
 * | alignment padding     |
 * -------------------------
 * | siginfo + ucontext    |
 * -------------------------
 */

/* max_frame_size tells userspace the worst case signal stack size. */
static unsigned long __ro_after_init max_frame_size;
static unsigned int __ro_after_init fpu_default_state_size;

void __init init_sigframe_size(void)
{
	fpu_default_state_size = fpu__get_fpstate_size();

	max_frame_size = MAX_FRAME_SIGINFO_UCTXT_SIZE + MAX_FRAME_PADDING;

	max_frame_size += fpu_default_state_size + MAX_XSAVE_PADDING;

	/* Userspace expects an aligned size. */
	max_frame_size = round_up(max_frame_size, FRAME_ALIGNMENT);

	pr_info("max sigframe size: %lu\n", max_frame_size);
}

unsigned long get_sigframe_size(void)
{
	return max_frame_size;
}

static inline int is_ia32_compat_frame(struct ksignal *ksig)
{
	return IS_ENABLED(CONFIG_IA32_EMULATION) &&
		ksig->ka.sa.sa_flags & SA_IA32_ABI;
}

static inline int is_ia32_frame(struct ksignal *ksig)
{
	return IS_ENABLED(CONFIG_X86_32) || is_ia32_compat_frame(ksig);
}

static inline int is_x32_frame(struct ksignal *ksig)
{
	return IS_ENABLED(CONFIG_X86_X32_ABI) &&
		ksig->ka.sa.sa_flags & SA_X32_ABI;
}

static int
setup_rt_frame(struct ksignal *ksig, struct pt_regs *regs)
{
	int usig = ksig->sig;
	sigset_t *set = sigmask_to_save();
	compat_sigset_t *cset = (compat_sigset_t *) set;

	/* Perform fixup for the pre-signal frame. */
	rseq_signal_deliver(ksig, regs);

	/* Set up the stack frame */
	if (is_ia32_frame(ksig)) {
		if (ksig->ka.sa.sa_flags & SA_SIGINFO)
			return ia32_setup_rt_frame(usig, ksig, cset, regs);
		else
			return ia32_setup_frame(usig, ksig, cset, regs);
	} else if (is_x32_frame(ksig)) {
		return x32_setup_rt_frame(ksig, cset, regs);
	} else {
		return __setup_rt_frame(ksig->sig, ksig, set, regs);
	}
}

static void
handle_signal(struct ksignal *ksig, struct pt_regs *regs)
{
	bool stepping, failed;
	struct fpu *fpu = &current->thread.fpu;

	if (v8086_mode(regs))
		save_v86_state((struct kernel_vm86_regs *) regs, VM86_SIGNAL);

	/* Are we from a system call? */
	if (syscall_get_nr(current, regs) != -1) {
		/* If so, check system call restarting.. */
		switch (syscall_get_error(current, regs)) {
		case -ERESTART_RESTARTBLOCK:
		case -ERESTARTNOHAND:
			regs->ax = -EINTR;
			break;

		case -ERESTARTSYS:
			if (!(ksig->ka.sa.sa_flags & SA_RESTART)) {
				regs->ax = -EINTR;
				break;
			}
			fallthrough;
		case -ERESTARTNOINTR:
			regs->ax = regs->orig_ax;
			regs->ip -= 2;
			break;
		}
	}

	/*
	 * If TF is set due to a debugger (TIF_FORCED_TF), clear TF now
	 * so that register information in the sigcontext is correct and
	 * then notify the tracer before entering the signal handler.
	 */
	stepping = test_thread_flag(TIF_SINGLESTEP);
	if (stepping)
		user_disable_single_step(current);

	failed = (setup_rt_frame(ksig, regs) < 0);
	if (!failed) {
		/*
		 * Clear the direction flag as per the ABI for function entry.
		 *
		 * Clear RF when entering the signal handler, because
		 * it might disable possible debug exception from the
		 * signal handler.
		 *
		 * Clear TF for the case when it wasn't set by debugger to
		 * avoid the recursive send_sigtrap() in SIGTRAP handler.
		 */
		regs->flags &= ~(X86_EFLAGS_DF|X86_EFLAGS_RF|X86_EFLAGS_TF);
		/*
		 * Ensure the signal handler starts with the new fpu state.
		 */
		fpu__clear_user_states(fpu);
	}
	signal_setup_done(failed, ksig, stepping);
}

static inline unsigned long get_nr_restart_syscall(const struct pt_regs *regs)
{
#ifdef CONFIG_IA32_EMULATION
	if (current->restart_block.arch_data & TS_COMPAT)
		return __NR_ia32_restart_syscall;
#endif
#ifdef CONFIG_X86_X32_ABI
	return __NR_restart_syscall | (regs->orig_ax & __X32_SYSCALL_BIT);
#else
	return __NR_restart_syscall;
#endif
}

/*
 * Note that 'init' is a special process: it doesn't get signals it doesn't
 * want to handle. Thus you cannot kill init even with a SIGKILL even by
 * mistake.
 */
void arch_do_signal_or_restart(struct pt_regs *regs)
{
	struct ksignal ksig;

	if (get_signal(&ksig)) {
		/* Whee! Actually deliver the signal.  */
		handle_signal(&ksig, regs);
		return;
	}

	/* Did we come from a system call? */
	if (syscall_get_nr(current, regs) != -1) {
		/* Restart the system call - no handlers present */
		switch (syscall_get_error(current, regs)) {
		case -ERESTARTNOHAND:
		case -ERESTARTSYS:
		case -ERESTARTNOINTR:
			regs->ax = regs->orig_ax;
			regs->ip -= 2;
			break;

		case -ERESTART_RESTARTBLOCK:
			regs->ax = get_nr_restart_syscall(regs);
			regs->ip -= 2;
			break;
		}
	}

	/*
	 * If there's no signal to deliver, we just put the saved sigmask
	 * back.
	 */
	restore_saved_sigmask();
}

void signal_fault(struct pt_regs *regs, void __user *frame, char *where)
{
	struct task_struct *me = current;

	if (show_unhandled_signals && printk_ratelimit()) {
		printk("%s"
		       "%s[%d] bad frame in %s frame:%p ip:%lx sp:%lx orax:%lx",
		       task_pid_nr(current) > 1 ? KERN_INFO : KERN_EMERG,
		       me->comm, me->pid, where, frame,
		       regs->ip, regs->sp, regs->orig_ax);
		print_vma_addr(KERN_CONT " in ", regs->ip);
		pr_cont("\n");
	}

	force_sig(SIGSEGV);
}

#ifdef CONFIG_DYNAMIC_SIGFRAME
#ifdef CONFIG_STRICT_SIGALTSTACK_SIZE
static bool strict_sigaltstack_size __ro_after_init = true;
#else
static bool strict_sigaltstack_size __ro_after_init = false;
#endif

static int __init strict_sas_size(char *arg)
{
	return kstrtobool(arg, &strict_sigaltstack_size);
}
__setup("strict_sas_size", strict_sas_size);

/*
 * MINSIGSTKSZ is 2048 and can't be changed despite the fact that AVX512
 * exceeds that size already. As such programs might never use the
 * sigaltstack they just continued to work. While always checking against
 * the real size would be correct, this might be considered a regression.
 *
 * Therefore avoid the sanity check, unless enforced by kernel
 * configuration or command line option.
 *
 * When dynamic FPU features are supported, the check is also enforced when
 * the task has permissions to use dynamic features. Tasks which have no
 * permission are checked against the size of the non-dynamic feature set
 * if strict checking is enabled. This avoids forcing all tasks on the
 * system to allocate large sigaltstacks even if they are never going
 * to use a dynamic feature. As this is serialized via sighand::siglock
 * any permission request for a dynamic feature either happened already
 * or will see the newly install sigaltstack size in the permission checks.
 */
bool sigaltstack_size_valid(size_t ss_size)
{
	unsigned long fsize = max_frame_size - fpu_default_state_size;
	u64 mask;

	lockdep_assert_held(&current->sighand->siglock);

	if (!fpu_state_size_dynamic() && !strict_sigaltstack_size)
		return true;

	fsize += current->group_leader->thread.fpu.perm.__user_state_size;
	if (likely(ss_size > fsize))
		return true;

	if (strict_sigaltstack_size)
		return ss_size > fsize;

	mask = current->group_leader->thread.fpu.perm.__state_perm;
	if (mask & XFEATURE_MASK_USER_DYNAMIC)
		return ss_size > fsize;

	return true;
}
#endif /* CONFIG_DYNAMIC_SIGFRAME */

#ifdef CONFIG_X86_X32_ABI
COMPAT_SYSCALL_DEFINE0(x32_rt_sigreturn)
{
	struct pt_regs *regs = current_pt_regs();
	struct rt_sigframe_x32 __user *frame;
	sigset_t set;
	unsigned long uc_flags;

	frame = (struct rt_sigframe_x32 __user *)(regs->sp - 8);

	if (!access_ok(frame, sizeof(*frame)))
		goto badframe;
	if (__get_user(set.sig[0], (__u64 __user *)&frame->uc.uc_sigmask))
		goto badframe;
	if (__get_user(uc_flags, &frame->uc.uc_flags))
		goto badframe;

	set_current_blocked(&set);

	if (!restore_sigcontext(regs, &frame->uc.uc_mcontext, uc_flags))
		goto badframe;

	if (compat_restore_altstack(&frame->uc.uc_stack))
		goto badframe;

	return regs->ax;

badframe:
	signal_fault(regs, frame, "x32 rt_sigreturn");
	return 0;
}
#endif