fault.c 19.5 KB
Newer Older
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
/*
 * Based on arch/arm/mm/fault.c
 *
 * Copyright (C) 1995  Linus Torvalds
 * Copyright (C) 1995-2004 Russell King
 * Copyright (C) 2012 ARM Ltd.
 *
 * This program is free software; you can redistribute it and/or modify
 * it under the terms of the GNU General Public License version 2 as
 * published by the Free Software Foundation.
 *
 * This program is distributed in the hope that it will be useful,
 * but WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
 * GNU General Public License for more details.
 *
 * You should have received a copy of the GNU General Public License
 * along with this program.  If not, see <http://www.gnu.org/licenses/>.
 */

#include <linux/module.h>
#include <linux/signal.h>
#include <linux/mm.h>
#include <linux/hardirq.h>
#include <linux/init.h>
#include <linux/kprobes.h>
#include <linux/uaccess.h>
#include <linux/page-flags.h>
#include <linux/sched.h>
#include <linux/highmem.h>
#include <linux/perf_event.h>

33
#include <asm/cpufeature.h>
34 35
#include <asm/exception.h>
#include <asm/debug-monitors.h>
36
#include <asm/esr.h>
37
#include <asm/sysreg.h>
38 39 40 41
#include <asm/system_misc.h>
#include <asm/pgtable.h>
#include <asm/tlbflush.h>

42 43
static const char *fault_name(unsigned int esr);

44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65
#ifdef CONFIG_KPROBES
static inline int notify_page_fault(struct pt_regs *regs, unsigned int esr)
{
	int ret = 0;

	/* kprobe_running() needs smp_processor_id() */
	if (!user_mode(regs)) {
		preempt_disable();
		if (kprobe_running() && kprobe_fault_handler(regs, esr))
			ret = 1;
		preempt_enable();
	}

	return ret;
}
#else
static inline int notify_page_fault(struct pt_regs *regs, unsigned int esr)
{
	return 0;
}
#endif

66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84
/*
 * Dump out the page tables associated with 'addr' in mm 'mm'.
 */
void show_pte(struct mm_struct *mm, unsigned long addr)
{
	pgd_t *pgd;

	if (!mm)
		mm = &init_mm;

	pr_alert("pgd = %p\n", mm->pgd);
	pgd = pgd_offset(mm, addr);
	pr_alert("[%08lx] *pgd=%016llx", addr, pgd_val(*pgd));

	do {
		pud_t *pud;
		pmd_t *pmd;
		pte_t *pte;

85
		if (pgd_none(*pgd) || pgd_bad(*pgd))
86 87 88
			break;

		pud = pud_offset(pgd, addr);
89
		printk(", *pud=%016llx", pud_val(*pud));
90
		if (pud_none(*pud) || pud_bad(*pud))
91 92 93 94
			break;

		pmd = pmd_offset(pud, addr);
		printk(", *pmd=%016llx", pmd_val(*pmd));
95
		if (pmd_none(*pmd) || pmd_bad(*pmd))
96 97 98 99 100 101 102 103 104 105
			break;

		pte = pte_offset_map(pmd, addr);
		printk(", *pte=%016llx", pte_val(*pte));
		pte_unmap(pte);
	} while(0);

	printk("\n");
}

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
#ifdef CONFIG_ARM64_HW_AFDBM
/*
 * This function sets the access flags (dirty, accessed), as well as write
 * permission, and only to a more permissive setting.
 *
 * It needs to cope with hardware update of the accessed/dirty state by other
 * agents in the system and can safely skip the __sync_icache_dcache() call as,
 * like set_pte_at(), the PTE is never changed from no-exec to exec here.
 *
 * Returns whether or not the PTE actually changed.
 */
int ptep_set_access_flags(struct vm_area_struct *vma,
			  unsigned long address, pte_t *ptep,
			  pte_t entry, int dirty)
{
	pteval_t old_pteval;
	unsigned int tmp;

	if (pte_same(*ptep, entry))
		return 0;

	/* only preserve the access flags and write permission */
	pte_val(entry) &= PTE_AF | PTE_WRITE | PTE_DIRTY;

	/*
	 * PTE_RDONLY is cleared by default in the asm below, so set it in
	 * back if necessary (read-only or clean PTE).
	 */
134
	if (!pte_write(entry) || !pte_sw_dirty(entry))
135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155
		pte_val(entry) |= PTE_RDONLY;

	/*
	 * Setting the flags must be done atomically to avoid racing with the
	 * hardware update of the access/dirty state.
	 */
	asm volatile("//	ptep_set_access_flags\n"
	"	prfm	pstl1strm, %2\n"
	"1:	ldxr	%0, %2\n"
	"	and	%0, %0, %3		// clear PTE_RDONLY\n"
	"	orr	%0, %0, %4		// set flags\n"
	"	stxr	%w1, %0, %2\n"
	"	cbnz	%w1, 1b\n"
	: "=&r" (old_pteval), "=&r" (tmp), "+Q" (pte_val(*ptep))
	: "L" (~PTE_RDONLY), "r" (pte_val(entry)));

	flush_tlb_fix_spurious_fault(vma, address);
	return 1;
}
#endif

156 157 158 159 160
static bool is_el1_instruction_abort(unsigned int esr)
{
	return ESR_ELx_EC(esr) == ESR_ELx_EC_IABT_CUR;
}

161 162 163 164 165 166 167 168
/*
 * The kernel tried to access some page that wasn't present.
 */
static void __do_kernel_fault(struct mm_struct *mm, unsigned long addr,
			      unsigned int esr, struct pt_regs *regs)
{
	/*
	 * Are we prepared to handle this kernel fault?
169
	 * We are almost certainly not prepared to handle instruction faults.
170
	 */
171
	if (!is_el1_instruction_abort(esr) && fixup_exception(regs))
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
		return;

	/*
	 * No handler, we'll have to terminate things with extreme prejudice.
	 */
	bust_spinlocks(1);
	pr_alert("Unable to handle kernel %s at virtual address %08lx\n",
		 (addr < PAGE_SIZE) ? "NULL pointer dereference" :
		 "paging request", addr);

	show_pte(mm, addr);
	die("Oops", regs, esr);
	bust_spinlocks(0);
	do_exit(SIGKILL);
}

/*
 * Something tried to access memory that isn't in our memory map. User mode
 * accesses just cause a SIGSEGV
 */
static void __do_user_fault(struct task_struct *tsk, unsigned long addr,
			    unsigned int esr, unsigned int sig, int code,
			    struct pt_regs *regs)
{
	struct siginfo si;

198
	if (unhandled_signal(tsk, sig) && show_unhandled_signals_ratelimited()) {
199 200 201
		pr_info("%s[%d]: unhandled %s (%d) at 0x%08lx, esr 0x%03x\n",
			tsk->comm, task_pid_nr(tsk), fault_name(esr), sig,
			addr, esr);
202 203 204 205 206
		show_pte(tsk->mm, addr);
		show_regs(regs);
	}

	tsk->thread.fault_address = addr;
207
	tsk->thread.fault_code = esr;
208 209 210 211 212 213 214
	si.si_signo = sig;
	si.si_errno = 0;
	si.si_code = code;
	si.si_addr = (void __user *)addr;
	force_sig_info(sig, &si, tsk);
}

215
static void do_bad_area(unsigned long addr, unsigned int esr, struct pt_regs *regs)
216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233
{
	struct task_struct *tsk = current;
	struct mm_struct *mm = tsk->active_mm;

	/*
	 * If we are in kernel mode at this point, we have no context to
	 * handle this fault with.
	 */
	if (user_mode(regs))
		__do_user_fault(tsk, addr, esr, SIGSEGV, SEGV_MAPERR, regs);
	else
		__do_kernel_fault(mm, addr, esr, regs);
}

#define VM_FAULT_BADMAP		0x010000
#define VM_FAULT_BADACCESS	0x020000

static int __do_page_fault(struct mm_struct *mm, unsigned long addr,
234
			   unsigned int mm_flags, unsigned long vm_flags,
235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251
			   struct task_struct *tsk)
{
	struct vm_area_struct *vma;
	int fault;

	vma = find_vma(mm, addr);
	fault = VM_FAULT_BADMAP;
	if (unlikely(!vma))
		goto out;
	if (unlikely(vma->vm_start > addr))
		goto check_stack;

	/*
	 * Ok, we have a good vm_area for this memory access, so we can handle
	 * it.
	 */
good_area:
252 253
	/*
	 * Check that the permissions on the VMA allow for the fault which
254 255
	 * occurred. If we encountered a write or exec fault, we must have
	 * appropriate permissions, otherwise we allow any permission.
256 257
	 */
	if (!(vma->vm_flags & vm_flags)) {
258 259 260 261
		fault = VM_FAULT_BADACCESS;
		goto out;
	}

262
	return handle_mm_fault(vma, addr & PAGE_MASK, mm_flags);
263 264 265 266 267 268 269 270

check_stack:
	if (vma->vm_flags & VM_GROWSDOWN && !expand_stack(vma, addr))
		goto good_area;
out:
	return fault;
}

M
Mark Rutland 已提交
271
static inline bool is_permission_fault(unsigned int esr)
272
{
273
	unsigned int ec       = ESR_ELx_EC(esr);
274 275
	unsigned int fsc_type = esr & ESR_ELx_FSC_TYPE;

276 277
	return (ec == ESR_ELx_EC_DABT_CUR && fsc_type == ESR_ELx_FSC_PERM) ||
	       (ec == ESR_ELx_EC_IABT_CUR && fsc_type == ESR_ELx_FSC_PERM);
278 279
}

M
Mark Rutland 已提交
280 281 282 283 284
static bool is_el0_instruction_abort(unsigned int esr)
{
	return ESR_ELx_EC(esr) == ESR_ELx_EC_IABT_LOW;
}

285 286 287 288 289 290
static int __kprobes do_page_fault(unsigned long addr, unsigned int esr,
				   struct pt_regs *regs)
{
	struct task_struct *tsk;
	struct mm_struct *mm;
	int fault, sig, code;
291
	unsigned long vm_flags = VM_READ | VM_WRITE | VM_EXEC;
292 293
	unsigned int mm_flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE;

294 295 296
	if (notify_page_fault(regs, esr))
		return 0;

297 298 299 300 301 302 303
	tsk = current;
	mm  = tsk->mm;

	/*
	 * If we're in an interrupt or have no user context, we must not take
	 * the fault.
	 */
304
	if (faulthandler_disabled() || !mm)
305 306
		goto no_context;

307 308 309
	if (user_mode(regs))
		mm_flags |= FAULT_FLAG_USER;

M
Mark Rutland 已提交
310
	if (is_el0_instruction_abort(esr)) {
311
		vm_flags = VM_EXEC;
M
Mark Rutland 已提交
312
	} else if ((esr & ESR_ELx_WNR) && !(esr & ESR_ELx_CM)) {
313 314 315 316
		vm_flags = VM_WRITE;
		mm_flags |= FAULT_FLAG_WRITE;
	}

M
Mark Rutland 已提交
317
	if (is_permission_fault(esr) && (addr < USER_DS)) {
318 319
		/* regs->orig_addr_limit may be 0 if we entered from EL0 */
		if (regs->orig_addr_limit == KERNEL_DS)
320
			die("Accessing user space memory with fs=KERNEL_DS", regs, esr);
321

322 323 324
		if (is_el1_instruction_abort(esr))
			die("Attempting to execute userspace memory", regs, esr);

325
		if (!search_exception_tables(regs->pc))
326
			die("Accessing user space memory outside uaccess.h routines", regs, esr);
327
	}
328

329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350
	/*
	 * As per x86, we may deadlock here. However, since the kernel only
	 * validly references user space from well defined areas of the code,
	 * we can bug out early if this is from code which shouldn't.
	 */
	if (!down_read_trylock(&mm->mmap_sem)) {
		if (!user_mode(regs) && !search_exception_tables(regs->pc))
			goto no_context;
retry:
		down_read(&mm->mmap_sem);
	} else {
		/*
		 * The above down_read_trylock() might have succeeded in which
		 * case, we'll have missed the might_sleep() from down_read().
		 */
		might_sleep();
#ifdef CONFIG_DEBUG_VM
		if (!user_mode(regs) && !search_exception_tables(regs->pc))
			goto no_context;
#endif
	}

351
	fault = __do_page_fault(mm, addr, mm_flags, vm_flags, tsk);
352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367

	/*
	 * If we need to retry but a fatal signal is pending, handle the
	 * signal first. We do not need to release the mmap_sem because it
	 * would already be released in __lock_page_or_retry in mm/filemap.c.
	 */
	if ((fault & VM_FAULT_RETRY) && fatal_signal_pending(current))
		return 0;

	/*
	 * Major/minor page fault accounting is only done on the initial
	 * attempt. If we go through a retry, it is extremely likely that the
	 * page will be found in page cache at that point.
	 */

	perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, addr);
368
	if (mm_flags & FAULT_FLAG_ALLOW_RETRY) {
369 370 371 372 373 374 375 376 377 378 379 380 381 382
		if (fault & VM_FAULT_MAJOR) {
			tsk->maj_flt++;
			perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MAJ, 1, regs,
				      addr);
		} else {
			tsk->min_flt++;
			perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MIN, 1, regs,
				      addr);
		}
		if (fault & VM_FAULT_RETRY) {
			/*
			 * Clear FAULT_FLAG_ALLOW_RETRY to avoid any risk of
			 * starvation.
			 */
383
			mm_flags &= ~FAULT_FLAG_ALLOW_RETRY;
384
			mm_flags |= FAULT_FLAG_TRIED;
385 386 387 388 389 390 391
			goto retry;
		}
	}

	up_read(&mm->mmap_sem);

	/*
J
Jan Kara 已提交
392
	 * Handle the "normal" case first - VM_FAULT_MAJOR
393 394 395 396 397
	 */
	if (likely(!(fault & (VM_FAULT_ERROR | VM_FAULT_BADMAP |
			      VM_FAULT_BADACCESS))))
		return 0;

398 399 400 401 402 403 404
	/*
	 * If we are in kernel mode at this point, we have no context to
	 * handle this fault with.
	 */
	if (!user_mode(regs))
		goto no_context;

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
	if (fault & VM_FAULT_OOM) {
		/*
		 * We ran out of memory, call the OOM killer, and return to
		 * userspace (which will retry the fault, or kill us if we got
		 * oom-killed).
		 */
		pagefault_out_of_memory();
		return 0;
	}

	if (fault & VM_FAULT_SIGBUS) {
		/*
		 * We had some memory, but were unable to successfully fix up
		 * this page fault.
		 */
		sig = SIGBUS;
		code = BUS_ADRERR;
	} else {
		/*
		 * Something tried to access memory that isn't in our memory
		 * map.
		 */
		sig = SIGSEGV;
		code = fault == VM_FAULT_BADACCESS ?
			SEGV_ACCERR : SEGV_MAPERR;
	}

	__do_user_fault(tsk, addr, esr, sig, code, regs);
	return 0;

no_context:
	__do_kernel_fault(mm, addr, esr, regs);
	return 0;
}

/*
 * First Level Translation Fault Handler
 *
 * We enter here because the first level page table doesn't contain a valid
 * entry for the address.
 *
 * If the address is in kernel space (>= TASK_SIZE), then we are probably
 * faulting in the vmalloc() area.
 *
 * If the init_task's first level page tables contains the relevant entry, we
 * copy the it to this task.  If not, we send the process a signal, fixup the
 * exception, or oops the kernel.
 *
 * NOTE! We MUST NOT take any locks for this case. We may be in an interrupt
 * or a critical region, and should only copy the information from the master
 * page table, nothing more.
 */
static int __kprobes do_translation_fault(unsigned long addr,
					  unsigned int esr,
					  struct pt_regs *regs)
{
	if (addr < TASK_SIZE)
		return do_page_fault(addr, esr, regs);

	do_bad_area(addr, esr, regs);
	return 0;
}

468 469 470 471 472 473 474
static int do_alignment_fault(unsigned long addr, unsigned int esr,
			      struct pt_regs *regs)
{
	do_bad_area(addr, esr, regs);
	return 0;
}

475 476 477 478 479 480 481 482
/*
 * This abort handler always returns "fault".
 */
static int do_bad(unsigned long addr, unsigned int esr, struct pt_regs *regs)
{
	return 1;
}

483
static const struct fault_info {
484 485 486 487 488 489 490 491 492
	int	(*fn)(unsigned long addr, unsigned int esr, struct pt_regs *regs);
	int	sig;
	int	code;
	const char *name;
} fault_info[] = {
	{ do_bad,		SIGBUS,  0,		"ttbr address size fault"	},
	{ do_bad,		SIGBUS,  0,		"level 1 address size fault"	},
	{ do_bad,		SIGBUS,  0,		"level 2 address size fault"	},
	{ do_bad,		SIGBUS,  0,		"level 3 address size fault"	},
493
	{ do_translation_fault,	SIGSEGV, SEGV_MAPERR,	"level 0 translation fault"	},
494 495 496
	{ do_translation_fault,	SIGSEGV, SEGV_MAPERR,	"level 1 translation fault"	},
	{ do_translation_fault,	SIGSEGV, SEGV_MAPERR,	"level 2 translation fault"	},
	{ do_page_fault,	SIGSEGV, SEGV_MAPERR,	"level 3 translation fault"	},
497
	{ do_bad,		SIGBUS,  0,		"unknown 8"			},
S
Steve Capper 已提交
498 499
	{ do_page_fault,	SIGSEGV, SEGV_ACCERR,	"level 1 access flag fault"	},
	{ do_page_fault,	SIGSEGV, SEGV_ACCERR,	"level 2 access flag fault"	},
500
	{ do_page_fault,	SIGSEGV, SEGV_ACCERR,	"level 3 access flag fault"	},
501
	{ do_bad,		SIGBUS,  0,		"unknown 12"			},
S
Steve Capper 已提交
502 503
	{ do_page_fault,	SIGSEGV, SEGV_ACCERR,	"level 1 permission fault"	},
	{ do_page_fault,	SIGSEGV, SEGV_ACCERR,	"level 2 permission fault"	},
504 505
	{ do_page_fault,	SIGSEGV, SEGV_ACCERR,	"level 3 permission fault"	},
	{ do_bad,		SIGBUS,  0,		"synchronous external abort"	},
506
	{ do_bad,		SIGBUS,  0,		"unknown 17"			},
507 508 509 510 511 512 513
	{ do_bad,		SIGBUS,  0,		"unknown 18"			},
	{ do_bad,		SIGBUS,  0,		"unknown 19"			},
	{ do_bad,		SIGBUS,  0,		"synchronous abort (translation table walk)" },
	{ do_bad,		SIGBUS,  0,		"synchronous abort (translation table walk)" },
	{ do_bad,		SIGBUS,  0,		"synchronous abort (translation table walk)" },
	{ do_bad,		SIGBUS,  0,		"synchronous abort (translation table walk)" },
	{ do_bad,		SIGBUS,  0,		"synchronous parity error"	},
514
	{ do_bad,		SIGBUS,  0,		"unknown 25"			},
515 516
	{ do_bad,		SIGBUS,  0,		"unknown 26"			},
	{ do_bad,		SIGBUS,  0,		"unknown 27"			},
517 518 519 520
	{ do_bad,		SIGBUS,  0,		"synchronous parity error (translation table walk)" },
	{ do_bad,		SIGBUS,  0,		"synchronous parity error (translation table walk)" },
	{ do_bad,		SIGBUS,  0,		"synchronous parity error (translation table walk)" },
	{ do_bad,		SIGBUS,  0,		"synchronous parity error (translation table walk)" },
521
	{ do_bad,		SIGBUS,  0,		"unknown 32"			},
522
	{ do_alignment_fault,	SIGBUS,  BUS_ADRALN,	"alignment fault"		},
523
	{ do_bad,		SIGBUS,  0,		"unknown 34"			},
524 525 526 527 528 529 530 531 532 533 534 535 536
	{ do_bad,		SIGBUS,  0,		"unknown 35"			},
	{ do_bad,		SIGBUS,  0,		"unknown 36"			},
	{ do_bad,		SIGBUS,  0,		"unknown 37"			},
	{ do_bad,		SIGBUS,  0,		"unknown 38"			},
	{ do_bad,		SIGBUS,  0,		"unknown 39"			},
	{ do_bad,		SIGBUS,  0,		"unknown 40"			},
	{ do_bad,		SIGBUS,  0,		"unknown 41"			},
	{ do_bad,		SIGBUS,  0,		"unknown 42"			},
	{ do_bad,		SIGBUS,  0,		"unknown 43"			},
	{ do_bad,		SIGBUS,  0,		"unknown 44"			},
	{ do_bad,		SIGBUS,  0,		"unknown 45"			},
	{ do_bad,		SIGBUS,  0,		"unknown 46"			},
	{ do_bad,		SIGBUS,  0,		"unknown 47"			},
537
	{ do_bad,		SIGBUS,  0,		"TLB conflict abort"		},
538 539 540 541
	{ do_bad,		SIGBUS,  0,		"unknown 49"			},
	{ do_bad,		SIGBUS,  0,		"unknown 50"			},
	{ do_bad,		SIGBUS,  0,		"unknown 51"			},
	{ do_bad,		SIGBUS,  0,		"implementation fault (lockdown abort)" },
542
	{ do_bad,		SIGBUS,  0,		"implementation fault (unsupported exclusive)" },
543 544 545 546
	{ do_bad,		SIGBUS,  0,		"unknown 54"			},
	{ do_bad,		SIGBUS,  0,		"unknown 55"			},
	{ do_bad,		SIGBUS,  0,		"unknown 56"			},
	{ do_bad,		SIGBUS,  0,		"unknown 57"			},
547
	{ do_bad,		SIGBUS,  0,		"unknown 58" 			},
548 549
	{ do_bad,		SIGBUS,  0,		"unknown 59"			},
	{ do_bad,		SIGBUS,  0,		"unknown 60"			},
550 551
	{ do_bad,		SIGBUS,  0,		"section domain fault"		},
	{ do_bad,		SIGBUS,  0,		"page domain fault"		},
552 553 554
	{ do_bad,		SIGBUS,  0,		"unknown 63"			},
};

555 556 557 558 559 560
static const char *fault_name(unsigned int esr)
{
	const struct fault_info *inf = fault_info + (esr & 63);
	return inf->name;
}

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
/*
 * Dispatch a data abort to the relevant handler.
 */
asmlinkage void __exception do_mem_abort(unsigned long addr, unsigned int esr,
					 struct pt_regs *regs)
{
	const struct fault_info *inf = fault_info + (esr & 63);
	struct siginfo info;

	if (!inf->fn(addr, esr, regs))
		return;

	pr_alert("Unhandled fault: %s (0x%08x) at 0x%016lx\n",
		 inf->name, esr, addr);

	info.si_signo = inf->sig;
	info.si_errno = 0;
	info.si_code  = inf->code;
	info.si_addr  = (void __user *)addr;
	arm64_notify_die("", regs, &info, esr);
}

/*
 * Handle stack alignment exceptions.
 */
asmlinkage void __exception do_sp_pc_abort(unsigned long addr,
					   unsigned int esr,
					   struct pt_regs *regs)
{
	struct siginfo info;
591 592 593 594 595 596 597
	struct task_struct *tsk = current;

	if (show_unhandled_signals && unhandled_signal(tsk, SIGBUS))
		pr_info_ratelimited("%s[%d]: %s exception: pc=%p sp=%p\n",
				    tsk->comm, task_pid_nr(tsk),
				    esr_get_class_string(esr), (void *)regs->pc,
				    (void *)regs->sp);
598 599 600 601 602

	info.si_signo = SIGBUS;
	info.si_errno = 0;
	info.si_code  = BUS_ADRALN;
	info.si_addr  = (void __user *)addr;
603
	arm64_notify_die("Oops - SP/PC alignment exception", regs, &info, esr);
604 605
}

606 607 608 609 610 611 612 613 614
int __init early_brk64(unsigned long addr, unsigned int esr,
		       struct pt_regs *regs);

/*
 * __refdata because early_brk64 is __init, but the reference to it is
 * clobbered at arch_initcall time.
 * See traps.c and debug-monitors.c:debug_traps_init().
 */
static struct fault_info __refdata debug_fault_info[] = {
615 616 617 618 619 620
	{ do_bad,	SIGTRAP,	TRAP_HWBKPT,	"hardware breakpoint"	},
	{ do_bad,	SIGTRAP,	TRAP_HWBKPT,	"hardware single-step"	},
	{ do_bad,	SIGTRAP,	TRAP_HWBKPT,	"hardware watchpoint"	},
	{ do_bad,	SIGBUS,		0,		"unknown 3"		},
	{ do_bad,	SIGTRAP,	TRAP_BRKPT,	"aarch32 BKPT"		},
	{ do_bad,	SIGTRAP,	0,		"aarch32 vector catch"	},
621
	{ early_brk64,	SIGTRAP,	TRAP_BRKPT,	"aarch64 BRK"		},
622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642
	{ do_bad,	SIGBUS,		0,		"unknown 7"		},
};

void __init hook_debug_fault_code(int nr,
				  int (*fn)(unsigned long, unsigned int, struct pt_regs *),
				  int sig, int code, const char *name)
{
	BUG_ON(nr < 0 || nr >= ARRAY_SIZE(debug_fault_info));

	debug_fault_info[nr].fn		= fn;
	debug_fault_info[nr].sig	= sig;
	debug_fault_info[nr].code	= code;
	debug_fault_info[nr].name	= name;
}

asmlinkage int __exception do_debug_exception(unsigned long addr,
					      unsigned int esr,
					      struct pt_regs *regs)
{
	const struct fault_info *inf = debug_fault_info + DBG_ESR_EVT(esr);
	struct siginfo info;
643
	int rv;
644

645 646 647 648 649 650
	/*
	 * Tell lockdep we disabled irqs in entry.S. Do nothing if they were
	 * already disabled to preserve the last enabled/disabled addresses.
	 */
	if (interrupts_enabled(regs))
		trace_hardirqs_off();
651

652 653 654 655 656 657 658 659 660 661 662 663 664
	if (!inf->fn(addr, esr, regs)) {
		rv = 1;
	} else {
		pr_alert("Unhandled debug exception: %s (0x%08x) at 0x%016lx\n",
			 inf->name, esr, addr);

		info.si_signo = inf->sig;
		info.si_errno = 0;
		info.si_code  = inf->code;
		info.si_addr  = (void __user *)addr;
		arm64_notify_die("", regs, &info, 0);
		rv = 0;
	}
665

666 667
	if (interrupts_enabled(regs))
		trace_hardirqs_on();
668

669
	return rv;
670
}
671
NOKPROBE_SYMBOL(do_debug_exception);
672 673

#ifdef CONFIG_ARM64_PAN
674
void cpu_enable_pan(void *__unused)
675 676 677 678
{
	config_sctlr_el1(SCTLR_EL1_SPAN, 0);
}
#endif /* CONFIG_ARM64_PAN */
679 680 681 682 683 684 685 686 687 688 689 690 691

#ifdef CONFIG_ARM64_UAO
/*
 * Kernel threads have fs=KERNEL_DS by default, and don't need to call
 * set_fs(), devtmpfs in particular relies on this behaviour.
 * We need to enable the feature at runtime (instead of adding it to
 * PSR_MODE_EL1h) as the feature may not be implemented by the cpu.
 */
void cpu_enable_uao(void *__unused)
{
	asm(SET_PSTATE_UAO(1));
}
#endif /* CONFIG_ARM64_UAO */