Blame view

kernel/linux-rt-4.4.41/arch/mn10300/mm/fault.c 10.2 KB
5113f6f70   김현기   kernel add
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
  /* MN10300 MMU Fault handler
   *
   * Copyright (C) 2007 Matsushita Electric Industrial Co., Ltd.
   * Copyright (C) 2007 Red Hat, Inc. All Rights Reserved.
   * Modified by David Howells (dhowells@redhat.com)
   *
   * This program is free software; you can redistribute it and/or
   * modify it under the terms of the GNU General Public Licence
   * as published by the Free Software Foundation; either version
   * 2 of the Licence, or (at your option) any later version.
   */
  
  #include <linux/signal.h>
  #include <linux/sched.h>
  #include <linux/kernel.h>
  #include <linux/errno.h>
  #include <linux/string.h>
  #include <linux/types.h>
  #include <linux/ptrace.h>
  #include <linux/mman.h>
  #include <linux/mm.h>
  #include <linux/smp.h>
  #include <linux/interrupt.h>
  #include <linux/init.h>
  #include <linux/vt_kern.h>		/* For unblank_screen() */
  #include <linux/uaccess.h>
  
  #include <asm/pgalloc.h>
  #include <asm/hardirq.h>
  #include <asm/cpu-regs.h>
  #include <asm/debugger.h>
  #include <asm/gdb-stub.h>
  
  /*
   * Unlock any spinlocks which will prevent us from getting the
   * message out
   */
  void bust_spinlocks(int yes)
  {
  	if (yes) {
  		oops_in_progress = 1;
  	} else {
  		int loglevel_save = console_loglevel;
  #ifdef CONFIG_VT
  		unblank_screen();
  #endif
  		oops_in_progress = 0;
  		/*
  		 * OK, the message is on the console.  Now we call printk()
  		 * without oops_in_progress set so that printk will give klogd
  		 * a poke.  Hold onto your hats...
  		 */
  		console_loglevel = 15;	/* NMI oopser may have shut the console
  					 * up */
  		printk(" ");
  		console_loglevel = loglevel_save;
  	}
  }
  
  void do_BUG(const char *file, int line)
  {
  	bust_spinlocks(1);
  	printk(KERN_EMERG "------------[ cut here ]------------
  ");
  	printk(KERN_EMERG "kernel BUG at %s:%d!
  ", file, line);
  }
  
  #if 0
  static void print_pagetable_entries(pgd_t *pgdir, unsigned long address)
  {
  	pgd_t *pgd;
  	pmd_t *pmd;
  	pte_t *pte;
  
  	pgd = pgdir + __pgd_offset(address);
  	printk(KERN_DEBUG "pgd entry %p: %016Lx
  ",
  	       pgd, (long long) pgd_val(*pgd));
  
  	if (!pgd_present(*pgd)) {
  		printk(KERN_DEBUG "... pgd not present!
  ");
  		return;
  	}
  	pmd = pmd_offset(pgd, address);
  	printk(KERN_DEBUG "pmd entry %p: %016Lx
  ",
  	       pmd, (long long)pmd_val(*pmd));
  
  	if (!pmd_present(*pmd)) {
  		printk(KERN_DEBUG "... pmd not present!
  ");
  		return;
  	}
  	pte = pte_offset(pmd, address);
  	printk(KERN_DEBUG "pte entry %p: %016Lx
  ",
  	       pte, (long long) pte_val(*pte));
  
  	if (!pte_present(*pte))
  		printk(KERN_DEBUG "... pte not present!
  ");
  }
  #endif
  
  /*
   * This routine handles page faults.  It determines the address,
   * and the problem, and then passes it off to one of the appropriate
   * routines.
   *
   * fault_code:
   * - LSW: either MMUFCR_IFC or MMUFCR_DFC as appropriate
   * - MSW: 0 if data access, 1 if instruction access
   * - bit 0: TLB miss flag
   * - bit 1: initial write
   * - bit 2: page invalid
   * - bit 3: protection violation
   * - bit 4: accessor (0=user 1=kernel)
   * - bit 5: 0=read 1=write
   * - bit 6-8: page protection spec
   * - bit 9: illegal address
   * - bit 16: 0=data 1=ins
   *
   */
  asmlinkage void do_page_fault(struct pt_regs *regs, unsigned long fault_code,
  			      unsigned long address)
  {
  	struct vm_area_struct *vma;
  	struct task_struct *tsk;
  	struct mm_struct *mm;
  	unsigned long page;
  	siginfo_t info;
  	int fault;
  	unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE;
  
  #ifdef CONFIG_GDBSTUB
  	/* handle GDB stub causing a fault */
  	if (gdbstub_busy) {
  		gdbstub_exception(regs, TBR & TBR_INT_CODE);
  		return;
  	}
  #endif
  
  #if 0
  	printk(KERN_DEBUG "--- do_page_fault(%p,%s:%04lx,%08lx)
  ",
  	       regs,
  	       fault_code & 0x10000 ? "ins" : "data",
  	       fault_code & 0xffff, address);
  #endif
  
  	tsk = current;
  
  	/*
  	 * We fault-in kernel-space virtual memory on-demand. The
  	 * 'reference' page table is init_mm.pgd.
  	 *
  	 * 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.
  	 *
  	 * This verifies that the fault happens in kernel space
  	 * and that the fault was a page not present (invalid) error
  	 */
  	if (address >= VMALLOC_START && address < VMALLOC_END &&
  	    (fault_code & MMUFCR_xFC_ACCESS) == MMUFCR_xFC_ACCESS_SR &&
  	    (fault_code & MMUFCR_xFC_PGINVAL) == MMUFCR_xFC_PGINVAL
  	    )
  		goto vmalloc_fault;
  
  	mm = tsk->mm;
  	info.si_code = SEGV_MAPERR;
  
  	/*
  	 * If we're in an interrupt or have no user
  	 * context, we must not take the fault..
  	 */
  	if (faulthandler_disabled() || !mm)
  		goto no_context;
  
  	if ((fault_code & MMUFCR_xFC_ACCESS) == MMUFCR_xFC_ACCESS_USR)
  		flags |= FAULT_FLAG_USER;
  retry:
  	down_read(&mm->mmap_sem);
  
  	vma = find_vma(mm, address);
  	if (!vma)
  		goto bad_area;
  	if (vma->vm_start <= address)
  		goto good_area;
  	if (!(vma->vm_flags & VM_GROWSDOWN))
  		goto bad_area;
  
  	if ((fault_code & MMUFCR_xFC_ACCESS) == MMUFCR_xFC_ACCESS_USR) {
  		/* accessing the stack below the stack pointer is always a
  		 * bug */
  		if ((address & PAGE_MASK) + 2 * PAGE_SIZE < regs->sp) {
  #if 0
  			printk(KERN_WARNING
  			       "[%d] ### Access below stack @%lx (sp=%lx)
  ",
  			       current->pid, address, regs->sp);
  			printk(KERN_WARNING
  			       "vma [%08x - %08x]
  ",
  			       vma->vm_start, vma->vm_end);
  			show_registers(regs);
  			printk(KERN_WARNING
  			       "[%d] ### Code: [%08lx]"
  			       " %02x %02x %02x %02x %02x %02x %02x %02x
  ",
  			       current->pid,
  			       regs->pc,
  			       ((u8 *) regs->pc)[0],
  			       ((u8 *) regs->pc)[1],
  			       ((u8 *) regs->pc)[2],
  			       ((u8 *) regs->pc)[3],
  			       ((u8 *) regs->pc)[4],
  			       ((u8 *) regs->pc)[5],
  			       ((u8 *) regs->pc)[6],
  			       ((u8 *) regs->pc)[7]
  			       );
  #endif
  			goto bad_area;
  		}
  	}
  
  	if (expand_stack(vma, address))
  		goto bad_area;
  
  /*
   * Ok, we have a good vm_area for this memory access, so
   * we can handle it..
   */
  good_area:
  	info.si_code = SEGV_ACCERR;
  	switch (fault_code & (MMUFCR_xFC_PGINVAL|MMUFCR_xFC_TYPE)) {
  	default:	/* 3: write, present */
  	case MMUFCR_xFC_TYPE_WRITE:
  #ifdef TEST_VERIFY_AREA
  		if ((fault_code & MMUFCR_xFC_ACCESS) == MMUFCR_xFC_ACCESS_SR)
  			printk(KERN_DEBUG "WP fault at %08lx
  ", regs->pc);
  #endif
  		/* write to absent page */
  	case MMUFCR_xFC_PGINVAL | MMUFCR_xFC_TYPE_WRITE:
  		if (!(vma->vm_flags & VM_WRITE))
  			goto bad_area;
  		flags |= FAULT_FLAG_WRITE;
  		break;
  
  		/* read from protected page */
  	case MMUFCR_xFC_TYPE_READ:
  		goto bad_area;
  
  		/* read from absent page present */
  	case MMUFCR_xFC_PGINVAL | MMUFCR_xFC_TYPE_READ:
  		if (!(vma->vm_flags & (VM_READ | VM_EXEC)))
  			goto bad_area;
  		break;
  	}
  
  	/*
  	 * If for any reason at all we couldn't handle the fault,
  	 * make sure we exit gracefully rather than endlessly redo
  	 * the fault.
  	 */
  	fault = handle_mm_fault(mm, vma, address, flags);
  
  	if ((fault & VM_FAULT_RETRY) && fatal_signal_pending(current))
  		return;
  
  	if (unlikely(fault & VM_FAULT_ERROR)) {
  		if (fault & VM_FAULT_OOM)
  			goto out_of_memory;
  		else if (fault & VM_FAULT_SIGSEGV)
  			goto bad_area;
  		else if (fault & VM_FAULT_SIGBUS)
  			goto do_sigbus;
  		BUG();
  	}
  	if (flags & FAULT_FLAG_ALLOW_RETRY) {
  		if (fault & VM_FAULT_MAJOR)
  			current->maj_flt++;
  		else
  			current->min_flt++;
  		if (fault & VM_FAULT_RETRY) {
  			flags &= ~FAULT_FLAG_ALLOW_RETRY;
  
  			 /* No need to up_read(&mm->mmap_sem) as we would
  			 * have already released it in __lock_page_or_retry
  			 * in mm/filemap.c.
  			 */
  
  			goto retry;
  		}
  	}
  
  	up_read(&mm->mmap_sem);
  	return;
  
  /*
   * Something tried to access memory that isn't in our memory map..
   * Fix it, but check if it's kernel or user first..
   */
  bad_area:
  	up_read(&mm->mmap_sem);
  
  	/* User mode accesses just cause a SIGSEGV */
  	if ((fault_code & MMUFCR_xFC_ACCESS) == MMUFCR_xFC_ACCESS_USR) {
  		info.si_signo = SIGSEGV;
  		info.si_errno = 0;
  		/* info.si_code has been set above */
  		info.si_addr = (void *)address;
  		force_sig_info(SIGSEGV, &info, tsk);
  		return;
  	}
  
  no_context:
  	/* Are we prepared to handle this kernel fault?  */
  	if (fixup_exception(regs))
  		return;
  
  /*
   * Oops. The kernel tried to access some bad page. We'll have to
   * terminate things with extreme prejudice.
   */
  
  	bust_spinlocks(1);
  
  	if (address < PAGE_SIZE)
  		printk(KERN_ALERT
  		       "Unable to handle kernel NULL pointer dereference");
  	else
  		printk(KERN_ALERT
  		       "Unable to handle kernel paging request");
  	printk(" at virtual address %08lx
  ", address);
  	printk(" printing pc:
  ");
  	printk(KERN_ALERT "%08lx
  ", regs->pc);
  
  	debugger_intercept(fault_code & 0x00010000 ? EXCEP_IAERROR : EXCEP_DAERROR,
  			   SIGSEGV, SEGV_ACCERR, regs);
  
  	page = PTBR;
  	page = ((unsigned long *) __va(page))[address >> 22];
  	printk(KERN_ALERT "*pde = %08lx
  ", page);
  	if (page & 1) {
  		page &= PAGE_MASK;
  		address &= 0x003ff000;
  		page = ((unsigned long *) __va(page))[address >> PAGE_SHIFT];
  		printk(KERN_ALERT "*pte = %08lx
  ", page);
  	}
  
  	die("Oops", regs, fault_code);
  	do_exit(SIGKILL);
  
  /*
   * We ran out of memory, or some other thing happened to us that made
   * us unable to handle the page fault gracefully.
   */
  out_of_memory:
  	up_read(&mm->mmap_sem);
  	if ((fault_code & MMUFCR_xFC_ACCESS) == MMUFCR_xFC_ACCESS_USR) {
  		pagefault_out_of_memory();
  		return;
  	}
  	goto no_context;
  
  do_sigbus:
  	up_read(&mm->mmap_sem);
  
  	/*
  	 * Send a sigbus, regardless of whether we were in kernel
  	 * or user mode.
  	 */
  	info.si_signo = SIGBUS;
  	info.si_errno = 0;
  	info.si_code = BUS_ADRERR;
  	info.si_addr = (void *)address;
  	force_sig_info(SIGBUS, &info, tsk);
  
  	/* Kernel mode? Handle exceptions or die */
  	if ((fault_code & MMUFCR_xFC_ACCESS) == MMUFCR_xFC_ACCESS_SR)
  		goto no_context;
  	return;
  
  vmalloc_fault:
  	{
  		/*
  		 * Synchronize this task's top level page-table
  		 * with the 'reference' page table.
  		 *
  		 * Do _not_ use "tsk" here. We might be inside
  		 * an interrupt in the middle of a task switch..
  		 */
  		int index = pgd_index(address);
  		pgd_t *pgd, *pgd_k;
  		pud_t *pud, *pud_k;
  		pmd_t *pmd, *pmd_k;
  		pte_t *pte_k;
  
  		pgd_k = init_mm.pgd + index;
  
  		if (!pgd_present(*pgd_k))
  			goto no_context;
  
  		pud_k = pud_offset(pgd_k, address);
  		if (!pud_present(*pud_k))
  			goto no_context;
  
  		pmd_k = pmd_offset(pud_k, address);
  		if (!pmd_present(*pmd_k))
  			goto no_context;
  
  		pgd = (pgd_t *) PTBR + index;
  		pud = pud_offset(pgd, address);
  		pmd = pmd_offset(pud, address);
  		set_pmd(pmd, *pmd_k);
  
  		pte_k = pte_offset_kernel(pmd_k, address);
  		if (!pte_present(*pte_k))
  			goto no_context;
  		return;
  	}
  }