1 // SPDX-License-Identifier: GPL-2.0-only
2 /*
3  *  linux/arch/arm/mm/fault.c
4  *
5  *  Copyright (C) 1995  Linus Torvalds
6  *  Modifications for ARM processor (c) 1995-2004 Russell King
7  */
8 #include <linux/extable.h>
9 #include <linux/signal.h>
10 #include <linux/mm.h>
11 #include <linux/hardirq.h>
12 #include <linux/init.h>
13 #include <linux/kprobes.h>
14 #include <linux/uaccess.h>
15 #include <linux/page-flags.h>
16 #include <linux/sched/signal.h>
17 #include <linux/sched/debug.h>
18 #include <linux/highmem.h>
19 #include <linux/perf_event.h>
20 #include <linux/kfence.h>
21 
22 #include <asm/system_misc.h>
23 #include <asm/system_info.h>
24 #include <asm/tlbflush.h>
25 
26 #include "fault.h"
27 
28 #ifdef CONFIG_MMU
29 
30 /*
31  * This is useful to dump out the page tables associated with
32  * 'addr' in mm 'mm'.
33  */
show_pte(const char * lvl,struct mm_struct * mm,unsigned long addr)34 void show_pte(const char *lvl, struct mm_struct *mm, unsigned long addr)
35 {
36 	pgd_t *pgd;
37 
38 	if (!mm)
39 		mm = &init_mm;
40 
41 	pgd = pgd_offset(mm, addr);
42 	printk("%s[%08lx] *pgd=%08llx", lvl, addr, (long long)pgd_val(*pgd));
43 
44 	do {
45 		p4d_t *p4d;
46 		pud_t *pud;
47 		pmd_t *pmd;
48 		pte_t *pte;
49 
50 		p4d = p4d_offset(pgd, addr);
51 		if (p4d_none(*p4d))
52 			break;
53 
54 		if (p4d_bad(*p4d)) {
55 			pr_cont("(bad)");
56 			break;
57 		}
58 
59 		pud = pud_offset(p4d, addr);
60 		if (PTRS_PER_PUD != 1)
61 			pr_cont(", *pud=%08llx", (long long)pud_val(*pud));
62 
63 		if (pud_none(*pud))
64 			break;
65 
66 		if (pud_bad(*pud)) {
67 			pr_cont("(bad)");
68 			break;
69 		}
70 
71 		pmd = pmd_offset(pud, addr);
72 		if (PTRS_PER_PMD != 1)
73 			pr_cont(", *pmd=%08llx", (long long)pmd_val(*pmd));
74 
75 		if (pmd_none(*pmd))
76 			break;
77 
78 		if (pmd_bad(*pmd)) {
79 			pr_cont("(bad)");
80 			break;
81 		}
82 
83 		/* We must not map this if we have highmem enabled */
84 		if (PageHighMem(pfn_to_page(pmd_val(*pmd) >> PAGE_SHIFT)))
85 			break;
86 
87 		pte = pte_offset_map(pmd, addr);
88 		pr_cont(", *pte=%08llx", (long long)pte_val(*pte));
89 #ifndef CONFIG_ARM_LPAE
90 		pr_cont(", *ppte=%08llx",
91 		       (long long)pte_val(pte[PTE_HWTABLE_PTRS]));
92 #endif
93 		pte_unmap(pte);
94 	} while(0);
95 
96 	pr_cont("\n");
97 }
98 #else					/* CONFIG_MMU */
show_pte(const char * lvl,struct mm_struct * mm,unsigned long addr)99 void show_pte(const char *lvl, struct mm_struct *mm, unsigned long addr)
100 { }
101 #endif					/* CONFIG_MMU */
102 
is_write_fault(unsigned int fsr)103 static inline bool is_write_fault(unsigned int fsr)
104 {
105 	return (fsr & FSR_WRITE) && !(fsr & FSR_CM);
106 }
107 
is_translation_fault(unsigned int fsr)108 static inline bool is_translation_fault(unsigned int fsr)
109 {
110 	int fs = fsr_fs(fsr);
111 #ifdef CONFIG_ARM_LPAE
112 	if ((fs & FS_MMU_NOLL_MASK) == FS_TRANS_NOLL)
113 		return true;
114 #else
115 	if (fs == FS_L1_TRANS || fs == FS_L2_TRANS)
116 		return true;
117 #endif
118 	return false;
119 }
120 
die_kernel_fault(const char * msg,struct mm_struct * mm,unsigned long addr,unsigned int fsr,struct pt_regs * regs)121 static void die_kernel_fault(const char *msg, struct mm_struct *mm,
122 			     unsigned long addr, unsigned int fsr,
123 			     struct pt_regs *regs)
124 {
125 	bust_spinlocks(1);
126 	pr_alert("8<--- cut here ---\n");
127 	pr_alert("Unable to handle kernel %s at virtual address %08lx when %s\n",
128 		 msg, addr, fsr & FSR_LNX_PF ? "execute" :
129 		 fsr & FSR_WRITE ? "write" : "read");
130 
131 	show_pte(KERN_ALERT, mm, addr);
132 	die("Oops", regs, fsr);
133 	bust_spinlocks(0);
134 	make_task_dead(SIGKILL);
135 }
136 
137 /*
138  * Oops.  The kernel tried to access some page that wasn't present.
139  */
140 static void
__do_kernel_fault(struct mm_struct * mm,unsigned long addr,unsigned int fsr,struct pt_regs * regs)141 __do_kernel_fault(struct mm_struct *mm, unsigned long addr, unsigned int fsr,
142 		  struct pt_regs *regs)
143 {
144 	const char *msg;
145 	/*
146 	 * Are we prepared to handle this kernel fault?
147 	 */
148 	if (fixup_exception(regs))
149 		return;
150 
151 	/*
152 	 * No handler, we'll have to terminate things with extreme prejudice.
153 	 */
154 	if (addr < PAGE_SIZE) {
155 		msg = "NULL pointer dereference";
156 	} else {
157 		if (is_translation_fault(fsr) &&
158 		    kfence_handle_page_fault(addr, is_write_fault(fsr), regs))
159 			return;
160 
161 		msg = "paging request";
162 	}
163 
164 	die_kernel_fault(msg, mm, addr, fsr, regs);
165 }
166 
167 /*
168  * Something tried to access memory that isn't in our memory map..
169  * User mode accesses just cause a SIGSEGV
170  */
171 static void
__do_user_fault(unsigned long addr,unsigned int fsr,unsigned int sig,int code,struct pt_regs * regs)172 __do_user_fault(unsigned long addr, unsigned int fsr, unsigned int sig,
173 		int code, struct pt_regs *regs)
174 {
175 	struct task_struct *tsk = current;
176 
177 	if (addr > TASK_SIZE)
178 		harden_branch_predictor();
179 
180 #ifdef CONFIG_DEBUG_USER
181 	if (((user_debug & UDBG_SEGV) && (sig == SIGSEGV)) ||
182 	    ((user_debug & UDBG_BUS)  && (sig == SIGBUS))) {
183 		pr_err("8<--- cut here ---\n");
184 		pr_err("%s: unhandled page fault (%d) at 0x%08lx, code 0x%03x\n",
185 		       tsk->comm, sig, addr, fsr);
186 		show_pte(KERN_ERR, tsk->mm, addr);
187 		show_regs(regs);
188 	}
189 #endif
190 #ifndef CONFIG_KUSER_HELPERS
191 	if ((sig == SIGSEGV) && ((addr & PAGE_MASK) == 0xffff0000))
192 		printk_ratelimited(KERN_DEBUG
193 				   "%s: CONFIG_KUSER_HELPERS disabled at 0x%08lx\n",
194 				   tsk->comm, addr);
195 #endif
196 
197 	tsk->thread.address = addr;
198 	tsk->thread.error_code = fsr;
199 	tsk->thread.trap_no = 14;
200 	force_sig_fault(sig, code, (void __user *)addr);
201 }
202 
do_bad_area(unsigned long addr,unsigned int fsr,struct pt_regs * regs)203 void do_bad_area(unsigned long addr, unsigned int fsr, struct pt_regs *regs)
204 {
205 	struct task_struct *tsk = current;
206 	struct mm_struct *mm = tsk->active_mm;
207 
208 	/*
209 	 * If we are in kernel mode at this point, we
210 	 * have no context to handle this fault with.
211 	 */
212 	if (user_mode(regs))
213 		__do_user_fault(addr, fsr, SIGSEGV, SEGV_MAPERR, regs);
214 	else
215 		__do_kernel_fault(mm, addr, fsr, regs);
216 }
217 
218 #ifdef CONFIG_MMU
219 #define VM_FAULT_BADMAP		((__force vm_fault_t)0x010000)
220 #define VM_FAULT_BADACCESS	((__force vm_fault_t)0x020000)
221 
is_permission_fault(unsigned int fsr)222 static inline bool is_permission_fault(unsigned int fsr)
223 {
224 	int fs = fsr_fs(fsr);
225 #ifdef CONFIG_ARM_LPAE
226 	if ((fs & FS_MMU_NOLL_MASK) == FS_PERM_NOLL)
227 		return true;
228 #else
229 	if (fs == FS_L1_PERM || fs == FS_L2_PERM)
230 		return true;
231 #endif
232 	return false;
233 }
234 
235 static vm_fault_t __kprobes
__do_page_fault(struct mm_struct * mm,unsigned long addr,unsigned int flags,unsigned long vma_flags,struct pt_regs * regs)236 __do_page_fault(struct mm_struct *mm, unsigned long addr, unsigned int flags,
237 		unsigned long vma_flags, struct pt_regs *regs)
238 {
239 	struct vm_area_struct *vma = find_vma(mm, addr);
240 	if (unlikely(!vma))
241 		return VM_FAULT_BADMAP;
242 
243 	if (unlikely(vma->vm_start > addr)) {
244 		if (!(vma->vm_flags & VM_GROWSDOWN))
245 			return VM_FAULT_BADMAP;
246 		if (addr < FIRST_USER_ADDRESS)
247 			return VM_FAULT_BADMAP;
248 		if (expand_stack(vma, addr))
249 			return VM_FAULT_BADMAP;
250 	}
251 
252 	/*
253 	 * ok, we have a good vm_area for this memory access, check the
254 	 * permissions on the VMA allow for the fault which occurred.
255 	 */
256 	if (!(vma->vm_flags & vma_flags))
257 		return VM_FAULT_BADACCESS;
258 
259 	return handle_mm_fault(vma, addr & PAGE_MASK, flags, regs);
260 }
261 
262 static int __kprobes
do_page_fault(unsigned long addr,unsigned int fsr,struct pt_regs * regs)263 do_page_fault(unsigned long addr, unsigned int fsr, struct pt_regs *regs)
264 {
265 	struct mm_struct *mm = current->mm;
266 	int sig, code;
267 	vm_fault_t fault;
268 	unsigned int flags = FAULT_FLAG_DEFAULT;
269 	unsigned long vm_flags = VM_ACCESS_FLAGS;
270 
271 	if (kprobe_page_fault(regs, fsr))
272 		return 0;
273 
274 
275 	/* Enable interrupts if they were enabled in the parent context. */
276 	if (interrupts_enabled(regs))
277 		local_irq_enable();
278 
279 	/*
280 	 * If we're in an interrupt or have no user
281 	 * context, we must not take the fault..
282 	 */
283 	if (faulthandler_disabled() || !mm)
284 		goto no_context;
285 
286 	if (user_mode(regs))
287 		flags |= FAULT_FLAG_USER;
288 
289 	if (is_write_fault(fsr)) {
290 		flags |= FAULT_FLAG_WRITE;
291 		vm_flags = VM_WRITE;
292 	}
293 
294 	if (fsr & FSR_LNX_PF) {
295 		vm_flags = VM_EXEC;
296 
297 		if (is_permission_fault(fsr) && !user_mode(regs))
298 			die_kernel_fault("execution of memory",
299 					 mm, addr, fsr, regs);
300 	}
301 
302 	perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, addr);
303 
304 	/*
305 	 * As per x86, we may deadlock here.  However, since the kernel only
306 	 * validly references user space from well defined areas of the code,
307 	 * we can bug out early if this is from code which shouldn't.
308 	 */
309 	if (!mmap_read_trylock(mm)) {
310 		if (!user_mode(regs) && !search_exception_tables(regs->ARM_pc))
311 			goto no_context;
312 retry:
313 		mmap_read_lock(mm);
314 	} else {
315 		/*
316 		 * The above down_read_trylock() might have succeeded in
317 		 * which case, we'll have missed the might_sleep() from
318 		 * down_read()
319 		 */
320 		might_sleep();
321 #ifdef CONFIG_DEBUG_VM
322 		if (!user_mode(regs) &&
323 		    !search_exception_tables(regs->ARM_pc))
324 			goto no_context;
325 #endif
326 	}
327 
328 	fault = __do_page_fault(mm, addr, flags, vm_flags, regs);
329 
330 	/* If we need to retry but a fatal signal is pending, handle the
331 	 * signal first. We do not need to release the mmap_lock because
332 	 * it would already be released in __lock_page_or_retry in
333 	 * mm/filemap.c. */
334 	if (fault_signal_pending(fault, regs)) {
335 		if (!user_mode(regs))
336 			goto no_context;
337 		return 0;
338 	}
339 
340 	/* The fault is fully completed (including releasing mmap lock) */
341 	if (fault & VM_FAULT_COMPLETED)
342 		return 0;
343 
344 	if (!(fault & VM_FAULT_ERROR)) {
345 		if (fault & VM_FAULT_RETRY) {
346 			flags |= FAULT_FLAG_TRIED;
347 			goto retry;
348 		}
349 	}
350 
351 	mmap_read_unlock(mm);
352 
353 	/*
354 	 * Handle the "normal" case first - VM_FAULT_MAJOR
355 	 */
356 	if (likely(!(fault & (VM_FAULT_ERROR | VM_FAULT_BADMAP | VM_FAULT_BADACCESS))))
357 		return 0;
358 
359 	/*
360 	 * If we are in kernel mode at this point, we
361 	 * have no context to handle this fault with.
362 	 */
363 	if (!user_mode(regs))
364 		goto no_context;
365 
366 	if (fault & VM_FAULT_OOM) {
367 		/*
368 		 * We ran out of memory, call the OOM killer, and return to
369 		 * userspace (which will retry the fault, or kill us if we
370 		 * got oom-killed)
371 		 */
372 		pagefault_out_of_memory();
373 		return 0;
374 	}
375 
376 	if (fault & VM_FAULT_SIGBUS) {
377 		/*
378 		 * We had some memory, but were unable to
379 		 * successfully fix up this page fault.
380 		 */
381 		sig = SIGBUS;
382 		code = BUS_ADRERR;
383 	} else {
384 		/*
385 		 * Something tried to access memory that
386 		 * isn't in our memory map..
387 		 */
388 		sig = SIGSEGV;
389 		code = fault == VM_FAULT_BADACCESS ?
390 			SEGV_ACCERR : SEGV_MAPERR;
391 	}
392 
393 	__do_user_fault(addr, fsr, sig, code, regs);
394 	return 0;
395 
396 no_context:
397 	__do_kernel_fault(mm, addr, fsr, regs);
398 	return 0;
399 }
400 #else					/* CONFIG_MMU */
401 static int
do_page_fault(unsigned long addr,unsigned int fsr,struct pt_regs * regs)402 do_page_fault(unsigned long addr, unsigned int fsr, struct pt_regs *regs)
403 {
404 	return 0;
405 }
406 #endif					/* CONFIG_MMU */
407 
408 /*
409  * First Level Translation Fault Handler
410  *
411  * We enter here because the first level page table doesn't contain
412  * a valid entry for the address.
413  *
414  * If the address is in kernel space (>= TASK_SIZE), then we are
415  * probably faulting in the vmalloc() area.
416  *
417  * If the init_task's first level page tables contains the relevant
418  * entry, we copy the it to this task.  If not, we send the process
419  * a signal, fixup the exception, or oops the kernel.
420  *
421  * NOTE! We MUST NOT take any locks for this case. We may be in an
422  * interrupt or a critical region, and should only copy the information
423  * from the master page table, nothing more.
424  */
425 #ifdef CONFIG_MMU
426 static int __kprobes
do_translation_fault(unsigned long addr,unsigned int fsr,struct pt_regs * regs)427 do_translation_fault(unsigned long addr, unsigned int fsr,
428 		     struct pt_regs *regs)
429 {
430 	unsigned int index;
431 	pgd_t *pgd, *pgd_k;
432 	p4d_t *p4d, *p4d_k;
433 	pud_t *pud, *pud_k;
434 	pmd_t *pmd, *pmd_k;
435 
436 	if (addr < TASK_SIZE)
437 		return do_page_fault(addr, fsr, regs);
438 
439 	if (user_mode(regs))
440 		goto bad_area;
441 
442 	index = pgd_index(addr);
443 
444 	pgd = cpu_get_pgd() + index;
445 	pgd_k = init_mm.pgd + index;
446 
447 	p4d = p4d_offset(pgd, addr);
448 	p4d_k = p4d_offset(pgd_k, addr);
449 
450 	if (p4d_none(*p4d_k))
451 		goto bad_area;
452 	if (!p4d_present(*p4d))
453 		set_p4d(p4d, *p4d_k);
454 
455 	pud = pud_offset(p4d, addr);
456 	pud_k = pud_offset(p4d_k, addr);
457 
458 	if (pud_none(*pud_k))
459 		goto bad_area;
460 	if (!pud_present(*pud))
461 		set_pud(pud, *pud_k);
462 
463 	pmd = pmd_offset(pud, addr);
464 	pmd_k = pmd_offset(pud_k, addr);
465 
466 #ifdef CONFIG_ARM_LPAE
467 	/*
468 	 * Only one hardware entry per PMD with LPAE.
469 	 */
470 	index = 0;
471 #else
472 	/*
473 	 * On ARM one Linux PGD entry contains two hardware entries (see page
474 	 * tables layout in pgtable.h). We normally guarantee that we always
475 	 * fill both L1 entries. But create_mapping() doesn't follow the rule.
476 	 * It can create inidividual L1 entries, so here we have to call
477 	 * pmd_none() check for the entry really corresponded to address, not
478 	 * for the first of pair.
479 	 */
480 	index = (addr >> SECTION_SHIFT) & 1;
481 #endif
482 	if (pmd_none(pmd_k[index]))
483 		goto bad_area;
484 
485 	copy_pmd(pmd, pmd_k);
486 	return 0;
487 
488 bad_area:
489 	do_bad_area(addr, fsr, regs);
490 	return 0;
491 }
492 #else					/* CONFIG_MMU */
493 static int
do_translation_fault(unsigned long addr,unsigned int fsr,struct pt_regs * regs)494 do_translation_fault(unsigned long addr, unsigned int fsr,
495 		     struct pt_regs *regs)
496 {
497 	return 0;
498 }
499 #endif					/* CONFIG_MMU */
500 
501 /*
502  * Some section permission faults need to be handled gracefully.
503  * They can happen due to a __{get,put}_user during an oops.
504  */
505 #ifndef CONFIG_ARM_LPAE
506 static int
do_sect_fault(unsigned long addr,unsigned int fsr,struct pt_regs * regs)507 do_sect_fault(unsigned long addr, unsigned int fsr, struct pt_regs *regs)
508 {
509 	do_bad_area(addr, fsr, regs);
510 	return 0;
511 }
512 #endif /* CONFIG_ARM_LPAE */
513 
514 /*
515  * This abort handler always returns "fault".
516  */
517 static int
do_bad(unsigned long addr,unsigned int fsr,struct pt_regs * regs)518 do_bad(unsigned long addr, unsigned int fsr, struct pt_regs *regs)
519 {
520 	return 1;
521 }
522 
523 struct fsr_info {
524 	int	(*fn)(unsigned long addr, unsigned int fsr, struct pt_regs *regs);
525 	int	sig;
526 	int	code;
527 	const char *name;
528 };
529 
530 /* FSR definition */
531 #ifdef CONFIG_ARM_LPAE
532 #include "fsr-3level.c"
533 #else
534 #include "fsr-2level.c"
535 #endif
536 
537 void __init
hook_fault_code(int nr,int (* fn)(unsigned long,unsigned int,struct pt_regs *),int sig,int code,const char * name)538 hook_fault_code(int nr, int (*fn)(unsigned long, unsigned int, struct pt_regs *),
539 		int sig, int code, const char *name)
540 {
541 	if (nr < 0 || nr >= ARRAY_SIZE(fsr_info))
542 		BUG();
543 
544 	fsr_info[nr].fn   = fn;
545 	fsr_info[nr].sig  = sig;
546 	fsr_info[nr].code = code;
547 	fsr_info[nr].name = name;
548 }
549 
550 /*
551  * Dispatch a data abort to the relevant handler.
552  */
553 asmlinkage void
do_DataAbort(unsigned long addr,unsigned int fsr,struct pt_regs * regs)554 do_DataAbort(unsigned long addr, unsigned int fsr, struct pt_regs *regs)
555 {
556 	const struct fsr_info *inf = fsr_info + fsr_fs(fsr);
557 
558 	if (!inf->fn(addr, fsr & ~FSR_LNX_PF, regs))
559 		return;
560 
561 	pr_alert("8<--- cut here ---\n");
562 	pr_alert("Unhandled fault: %s (0x%03x) at 0x%08lx\n",
563 		inf->name, fsr, addr);
564 	show_pte(KERN_ALERT, current->mm, addr);
565 
566 	arm_notify_die("", regs, inf->sig, inf->code, (void __user *)addr,
567 		       fsr, 0);
568 }
569 
570 void __init
hook_ifault_code(int nr,int (* fn)(unsigned long,unsigned int,struct pt_regs *),int sig,int code,const char * name)571 hook_ifault_code(int nr, int (*fn)(unsigned long, unsigned int, struct pt_regs *),
572 		 int sig, int code, const char *name)
573 {
574 	if (nr < 0 || nr >= ARRAY_SIZE(ifsr_info))
575 		BUG();
576 
577 	ifsr_info[nr].fn   = fn;
578 	ifsr_info[nr].sig  = sig;
579 	ifsr_info[nr].code = code;
580 	ifsr_info[nr].name = name;
581 }
582 
583 asmlinkage void
do_PrefetchAbort(unsigned long addr,unsigned int ifsr,struct pt_regs * regs)584 do_PrefetchAbort(unsigned long addr, unsigned int ifsr, struct pt_regs *regs)
585 {
586 	const struct fsr_info *inf = ifsr_info + fsr_fs(ifsr);
587 
588 	if (!inf->fn(addr, ifsr | FSR_LNX_PF, regs))
589 		return;
590 
591 	pr_alert("Unhandled prefetch abort: %s (0x%03x) at 0x%08lx\n",
592 		inf->name, ifsr, addr);
593 
594 	arm_notify_die("", regs, inf->sig, inf->code, (void __user *)addr,
595 		       ifsr, 0);
596 }
597 
598 /*
599  * Abort handler to be used only during first unmasking of asynchronous aborts
600  * on the boot CPU. This makes sure that the machine will not die if the
601  * firmware/bootloader left an imprecise abort pending for us to trip over.
602  */
early_abort_handler(unsigned long addr,unsigned int fsr,struct pt_regs * regs)603 static int __init early_abort_handler(unsigned long addr, unsigned int fsr,
604 				      struct pt_regs *regs)
605 {
606 	pr_warn("Hit pending asynchronous external abort (FSR=0x%08x) during "
607 		"first unmask, this is most likely caused by a "
608 		"firmware/bootloader bug.\n", fsr);
609 
610 	return 0;
611 }
612 
early_abt_enable(void)613 void __init early_abt_enable(void)
614 {
615 	fsr_info[FSR_FS_AEA].fn = early_abort_handler;
616 	local_abt_enable();
617 	fsr_info[FSR_FS_AEA].fn = do_bad;
618 }
619 
620 #ifndef CONFIG_ARM_LPAE
exceptions_init(void)621 static int __init exceptions_init(void)
622 {
623 	if (cpu_architecture() >= CPU_ARCH_ARMv6) {
624 		hook_fault_code(4, do_translation_fault, SIGSEGV, SEGV_MAPERR,
625 				"I-cache maintenance fault");
626 	}
627 
628 	if (cpu_architecture() >= CPU_ARCH_ARMv7) {
629 		/*
630 		 * TODO: Access flag faults introduced in ARMv6K.
631 		 * Runtime check for 'K' extension is needed
632 		 */
633 		hook_fault_code(3, do_bad, SIGSEGV, SEGV_MAPERR,
634 				"section access flag fault");
635 		hook_fault_code(6, do_bad, SIGSEGV, SEGV_MAPERR,
636 				"section access flag fault");
637 	}
638 
639 	return 0;
640 }
641 
642 arch_initcall(exceptions_init);
643 #endif
644