fault.c 15.1 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 33 34
/*
 * 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>

#include <asm/exception.h>
#include <asm/debug-monitors.h>
35
#include <asm/esr.h>
36 37 38 39
#include <asm/system_misc.h>
#include <asm/pgtable.h>
#include <asm/tlbflush.h>

40 41
static const char *fault_name(unsigned int esr);

42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60
/*
 * 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;

61
		if (pgd_none(*pgd) || pgd_bad(*pgd))
62 63 64
			break;

		pud = pud_offset(pgd, addr);
65
		printk(", *pud=%016llx", pud_val(*pud));
66
		if (pud_none(*pud) || pud_bad(*pud))
67 68 69 70
			break;

		pmd = pmd_offset(pud, addr);
		printk(", *pmd=%016llx", pmd_val(*pmd));
71
		if (pmd_none(*pmd) || pmd_bad(*pmd))
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
			break;

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

	printk("\n");
}

/*
 * 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?
	 */
	if (fixup_exception(regs))
		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;

118 119
	if (show_unhandled_signals && unhandled_signal(tsk, sig) &&
	    printk_ratelimit()) {
120 121 122
		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);
123 124 125 126 127
		show_pte(tsk->mm, addr);
		show_regs(regs);
	}

	tsk->thread.fault_address = addr;
128
	tsk->thread.fault_code = esr;
129 130 131 132 133 134 135
	si.si_signo = sig;
	si.si_errno = 0;
	si.si_code = code;
	si.si_addr = (void __user *)addr;
	force_sig_info(sig, &si, tsk);
}

136
static void do_bad_area(unsigned long addr, unsigned int esr, struct pt_regs *regs)
137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156
{
	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

#define ESR_LNX_EXEC		(1 << 24)

static int __do_page_fault(struct mm_struct *mm, unsigned long addr,
157
			   unsigned int mm_flags, unsigned long vm_flags,
158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174
			   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:
175 176
	/*
	 * Check that the permissions on the VMA allow for the fault which
177 178
	 * occurred. If we encountered a write or exec fault, we must have
	 * appropriate permissions, otherwise we allow any permission.
179 180
	 */
	if (!(vma->vm_flags & vm_flags)) {
181 182 183 184
		fault = VM_FAULT_BADACCESS;
		goto out;
	}

185
	return handle_mm_fault(mm, vma, addr & PAGE_MASK, mm_flags);
186 187 188 189 190 191 192 193 194 195 196 197 198 199

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

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;
200
	unsigned long vm_flags = VM_READ | VM_WRITE | VM_EXEC;
201 202
	unsigned int mm_flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE;

203 204 205 206 207 208 209 210 211 212 213 214 215 216
	tsk = current;
	mm  = tsk->mm;

	/* Enable interrupts if they were enabled in the parent context. */
	if (interrupts_enabled(regs))
		local_irq_enable();

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

217 218 219 220 221
	if (user_mode(regs))
		mm_flags |= FAULT_FLAG_USER;

	if (esr & ESR_LNX_EXEC) {
		vm_flags = VM_EXEC;
M
Mark Rutland 已提交
222
	} else if ((esr & ESR_ELx_WNR) && !(esr & ESR_ELx_CM)) {
223 224 225 226
		vm_flags = VM_WRITE;
		mm_flags |= FAULT_FLAG_WRITE;
	}

227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248
	/*
	 * 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
	}

249
	fault = __do_page_fault(mm, addr, mm_flags, vm_flags, tsk);
250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265

	/*
	 * 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);
266
	if (mm_flags & FAULT_FLAG_ALLOW_RETRY) {
267 268 269 270 271 272 273 274 275 276 277 278 279 280
		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.
			 */
281
			mm_flags &= ~FAULT_FLAG_ALLOW_RETRY;
282 283 284 285 286 287 288 289 290 291 292 293 294
			goto retry;
		}
	}

	up_read(&mm->mmap_sem);

	/*
	 * Handle the "normal" case first - VM_FAULT_MAJOR / VM_FAULT_MINOR
	 */
	if (likely(!(fault & (VM_FAULT_ERROR | VM_FAULT_BADMAP |
			      VM_FAULT_BADACCESS))))
		return 0;

295 296 297 298 299 300 301
	/*
	 * 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;

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
	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;
}

/*
 * This abort handler always returns "fault".
 */
static int do_bad(unsigned long addr, unsigned int esr, struct pt_regs *regs)
{
	return 1;
}

static struct fault_info {
	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"	},
383
	{ do_translation_fault,	SIGSEGV, SEGV_MAPERR,	"level 0 translation fault"	},
384 385 386 387
	{ 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"	},
	{ do_bad,		SIGBUS,  0,		"reserved access flag fault"	},
S
Steve Capper 已提交
388 389
	{ do_page_fault,	SIGSEGV, SEGV_ACCERR,	"level 1 access flag fault"	},
	{ do_page_fault,	SIGSEGV, SEGV_ACCERR,	"level 2 access flag fault"	},
390 391
	{ do_page_fault,	SIGSEGV, SEGV_ACCERR,	"level 3 access flag fault"	},
	{ do_bad,		SIGBUS,  0,		"reserved permission fault"	},
S
Steve Capper 已提交
392 393
	{ do_page_fault,	SIGSEGV, SEGV_ACCERR,	"level 1 permission fault"	},
	{ do_page_fault,	SIGSEGV, SEGV_ACCERR,	"level 2 permission fault"	},
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
	{ do_page_fault,	SIGSEGV, SEGV_ACCERR,	"level 3 permission fault"	},
	{ do_bad,		SIGBUS,  0,		"synchronous external abort"	},
	{ do_bad,		SIGBUS,  0,		"asynchronous external abort"	},
	{ 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"	},
	{ do_bad,		SIGBUS,  0,		"asynchronous parity error"	},
	{ do_bad,		SIGBUS,  0,		"unknown 26"			},
	{ do_bad,		SIGBUS,  0,		"unknown 27"			},
	{ 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" },
	{ do_bad,		SIGBUS,  0,		"unknown 32"			},
	{ do_bad,		SIGBUS,  BUS_ADRALN,	"alignment fault"		},
	{ do_bad,		SIGBUS,  0,		"debug event"			},
	{ 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"			},
	{ do_bad,		SIGBUS,  0,		"unknown 48"			},
	{ 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)" },
	{ do_bad,		SIGBUS,  0,		"unknown 53"			},
	{ do_bad,		SIGBUS,  0,		"unknown 54"			},
	{ do_bad,		SIGBUS,  0,		"unknown 55"			},
	{ do_bad,		SIGBUS,  0,		"unknown 56"			},
	{ do_bad,		SIGBUS,  0,		"unknown 57"			},
	{ do_bad,		SIGBUS,  0,		"implementation fault (coprocessor abort)" },
	{ do_bad,		SIGBUS,  0,		"unknown 59"			},
	{ do_bad,		SIGBUS,  0,		"unknown 60"			},
	{ do_bad,		SIGBUS,  0,		"unknown 61"			},
	{ do_bad,		SIGBUS,  0,		"unknown 62"			},
	{ do_bad,		SIGBUS,  0,		"unknown 63"			},
};

445 446 447 448 449 450
static const char *fault_name(unsigned int esr)
{
	const struct fault_info *inf = fault_info + (esr & 63);
	return inf->name;
}

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
/*
 * 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;

	info.si_signo = SIGBUS;
	info.si_errno = 0;
	info.si_code  = BUS_ADRALN;
	info.si_addr  = (void __user *)addr;
	arm64_notify_die("", regs, &info, esr);
}

static struct fault_info debug_fault_info[] = {
	{ 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"	},
	{ do_bad,	SIGTRAP,	TRAP_BRKPT,	"aarch64 BRK"		},
	{ 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;

	if (!inf->fn(addr, esr, regs))
		return 1;

	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;
529
	arm64_notify_die("", regs, &info, 0);
530 531 532

	return 0;
}