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
/*
 * arch/sparc64/mm/fault.c: Page fault handlers for the 64-bit Sparc.
 *
 * Copyright (C) 1996, 2008 David S. Miller (davem@davemloft.net)
 * Copyright (C) 1997, 1999 Jakub Jelinek (jj@ultra.linux.cz)
 */

#include <asm/head.h>

#include <linux/string.h>
#include <linux/types.h>
#include <linux/sched.h>
#include <linux/ptrace.h>
#include <linux/mman.h>
#include <linux/signal.h>
#include <linux/mm.h>
#include <linux/module.h>
#include <linux/init.h>
#include <linux/perf_event.h>
#include <linux/interrupt.h>
#include <linux/kprobes.h>
#include <linux/kdebug.h>
#include <linux/percpu.h>

#include <asm/page.h>
#include <asm/pgtable.h>
#include <asm/openprom.h>
#include <asm/oplib.h>
#include <asm/uaccess.h>
#include <asm/asi.h>
#include <asm/lsu.h>
#include <asm/sections.h>
#include <asm/mmu_context.h>

int show_unhandled_signals = 1;

static inline __kprobes int notify_page_fault(struct pt_regs *regs)
{
	int ret = 0;

	/* kprobe_running() needs smp_processor_id() */
	if (kprobes_built_in() && !user_mode(regs)) {
		preempt_disable();
		if (kprobe_running() && kprobe_fault_handler(regs, 0))
			ret = 1;
		preempt_enable();
	}
	return ret;
}

static void __kprobes unhandled_fault(unsigned long address,
				      struct task_struct *tsk,
				      struct pt_regs *regs)
{
	if ((unsigned long) address < PAGE_SIZE) {
		printk(KERN_ALERT "Unable to handle kernel NULL "
		       "pointer dereference\n");
	} else {
		printk(KERN_ALERT "Unable to handle kernel paging request "
		       "at virtual address %016lx\n", (unsigned long)address);
	}
	printk(KERN_ALERT "tsk->{mm,active_mm}->context = %016lx\n",
	       (tsk->mm ?
		CTX_HWBITS(tsk->mm->context) :
		CTX_HWBITS(tsk->active_mm->context)));
	printk(KERN_ALERT "tsk->{mm,active_mm}->pgd = %016lx\n",
	       (tsk->mm ? (unsigned long) tsk->mm->pgd :
		          (unsigned long) tsk->active_mm->pgd));
	die_if_kernel("Oops", regs);
}

static void __kprobes bad_kernel_pc(struct pt_regs *regs, unsigned long vaddr)
{
	printk(KERN_CRIT "OOPS: Bogus kernel PC [%016lx] in fault handler\n",
	       regs->tpc);
	printk(KERN_CRIT "OOPS: RPC [%016lx]\n", regs->u_regs[15]);
	printk("OOPS: RPC <%pS>\n", (void *) regs->u_regs[15]);
	printk(KERN_CRIT "OOPS: Fault was to vaddr[%lx]\n", vaddr);
	dump_stack();
	unhandled_fault(regs->tpc, current, regs);
}

/*
 * We now make sure that mmap_sem is held in all paths that call 
 * this. Additionally, to prevent kswapd from ripping ptes from
 * under us, raise interrupts around the time that we look at the
 * pte, kswapd will have to wait to get his smp ipi response from
 * us. vmtruncate likewise. This saves us having to get pte lock.
 */
static unsigned int get_user_insn(unsigned long tpc)
{
	pgd_t *pgdp = pgd_offset(current->mm, tpc);
	pud_t *pudp;
	pmd_t *pmdp;
	pte_t *ptep, pte;
	unsigned long pa;
	u32 insn = 0;
	unsigned long pstate;

	if (pgd_none(*pgdp))
		goto outret;
	pudp = pud_offset(pgdp, tpc);
	if (pud_none(*pudp))
		goto outret;
	pmdp = pmd_offset(pudp, tpc);
	if (pmd_none(*pmdp))
		goto outret;

	/* This disables preemption for us as well. */
	__asm__ __volatile__("rdpr %%pstate, %0" : "=r" (pstate));
	__asm__ __volatile__("wrpr %0, %1, %%pstate"
				: : "r" (pstate), "i" (PSTATE_IE));
	ptep = pte_offset_map(pmdp, tpc);
	pte = *ptep;
	if (!pte_present(pte))
		goto out;

	pa  = (pte_pfn(pte) << PAGE_SHIFT);
	pa += (tpc & ~PAGE_MASK);

	/* Use phys bypass so we don't pollute dtlb/dcache. */
	__asm__ __volatile__("lduwa [%1] %2, %0"
			     : "=r" (insn)
			     : "r" (pa), "i" (ASI_PHYS_USE_EC));

out:
	pte_unmap(ptep);
	__asm__ __volatile__("wrpr %0, 0x0, %%pstate" : : "r" (pstate));
outret:
	return insn;
}

static inline void
show_signal_msg(struct pt_regs *regs, int sig, int code,
		unsigned long address, struct task_struct *tsk)
{
	if (!unhandled_signal(tsk, sig))
		return;

	if (!printk_ratelimit())
		return;

	printk("%s%s[%d]: segfault at %lx ip %p (rpc %p) sp %p error %x",
	       task_pid_nr(tsk) > 1 ? KERN_INFO : KERN_EMERG,
	       tsk->comm, task_pid_nr(tsk), address,
	       (void *)regs->tpc, (void *)regs->u_regs[UREG_I7],
	       (void *)regs->u_regs[UREG_FP], code);

	print_vma_addr(KERN_CONT " in ", regs->tpc);

	printk(KERN_CONT "\n");
}

extern unsigned long compute_effective_address(struct pt_regs *, unsigned int, unsigned int);

static void do_fault_siginfo(int code, int sig, struct pt_regs *regs,
			     unsigned int insn, int fault_code)
{
	unsigned long addr;
	siginfo_t info;

	info.si_code = code;
	info.si_signo = sig;
	info.si_errno = 0;
	if (fault_code & FAULT_CODE_ITLB)
		addr = regs->tpc;
	else
		addr = compute_effective_address(regs, insn, 0);
	info.si_addr = (void __user *) addr;
	info.si_trapno = 0;

	if (unlikely(show_unhandled_signals))
		show_signal_msg(regs, sig, code, addr, current);

	force_sig_info(sig, &info, current);
}

extern int handle_ldf_stq(u32, struct pt_regs *);
extern int handle_ld_nf(u32, struct pt_regs *);

static unsigned int get_fault_insn(struct pt_regs *regs, unsigned int insn)
{
	if (!insn) {
		if (!regs->tpc || (regs->tpc & 0x3))
			return 0;
		if (regs->tstate & TSTATE_PRIV) {
			insn = *(unsigned int *) regs->tpc;
		} else {
			insn = get_user_insn(regs->tpc);
		}
	}
	return insn;
}

static void __kprobes do_kernel_fault(struct pt_regs *regs, int si_code,
				      int fault_code, unsigned int insn,
				      unsigned long address)
{
	unsigned char asi = ASI_P;
 
	if ((!insn) && (regs->tstate & TSTATE_PRIV))
		goto cannot_handle;

	/* If user insn could be read (thus insn is zero), that
	 * is fine.  We will just gun down the process with a signal
	 * in that case.
	 */

	if (!(fault_code & (FAULT_CODE_WRITE|FAULT_CODE_ITLB)) &&
	    (insn & 0xc0800000) == 0xc0800000) {
		if (insn & 0x2000)
			asi = (regs->tstate >> 24);
		else
			asi = (insn >> 5);
		if ((asi & 0xf2) == 0x82) {
			if (insn & 0x1000000) {
				handle_ldf_stq(insn, regs);
			} else {
				/* This was a non-faulting load. Just clear the
				 * destination register(s) and continue with the next
				 * instruction. -jj
				 */
				handle_ld_nf(insn, regs);
			}
			return;
		}
	}
		
	/* Is this in ex_table? */
	if (regs->tstate & TSTATE_PRIV) {
		const struct exception_table_entry *entry;

		entry = search_exception_tables(regs->tpc);
		if (entry) {
			regs->tpc = entry->fixup;
			regs->tnpc = regs->tpc + 4;
			return;
		}
	} else {
		/* The si_code was set to make clear whether
		 * this was a SEGV_MAPERR or SEGV_ACCERR fault.
		 */
		do_fault_siginfo(si_code, SIGSEGV, regs, insn, fault_code);
		return;
	}

cannot_handle:
	unhandled_fault (address, current, regs);
}

static void noinline __kprobes bogus_32bit_fault_tpc(struct pt_regs *regs)
{
	static int times;

	if (times++ < 10)
		printk(KERN_ERR "FAULT[%s:%d]: 32-bit process reports "
		       "64-bit TPC [%lx]\n",
		       current->comm, current->pid,
		       regs->tpc);
	show_regs(regs);
}

static void noinline __kprobes bogus_32bit_fault_address(struct pt_regs *regs,
							 unsigned long addr)
{
	static int times;

	if (times++ < 10)
		printk(KERN_ERR "FAULT[%s:%d]: 32-bit process "
		       "reports 64-bit fault address [%lx]\n",
		       current->comm, current->pid, addr);
	show_regs(regs);
}

asmlinkage void __kprobes do_sparc64_fault(struct pt_regs *regs)
{
	struct mm_struct *mm = current->mm;
	struct vm_area_struct *vma;
	unsigned int insn = 0;
	int si_code, fault_code, fault;
	unsigned long address, mm_rss;

	fault_code = get_thread_fault_code();

	if (notify_page_fault(regs))
		return;

	si_code = SEGV_MAPERR;
	address = current_thread_info()->fault_address;

	if ((fault_code & FAULT_CODE_ITLB) &&
	    (fault_code & FAULT_CODE_DTLB))
		BUG();

	if (test_thread_flag(TIF_32BIT)) {
		if (!(regs->tstate & TSTATE_PRIV)) {
			if (unlikely((regs->tpc >> 32) != 0)) {
				bogus_32bit_fault_tpc(regs);
				goto intr_or_no_mm;
			}
		}
		if (unlikely((address >> 32) != 0)) {
			bogus_32bit_fault_address(regs, address);
			goto intr_or_no_mm;
		}
	}

	if (regs->tstate & TSTATE_PRIV) {
		unsigned long tpc = regs->tpc;

		/* Sanity check the PC. */
		if ((tpc >= KERNBASE && tpc < (unsigned long) __init_end) ||
		    (tpc >= MODULES_VADDR && tpc < MODULES_END)) {
			/* Valid, no problems... */
		} else {
			bad_kernel_pc(regs, address);
			return;
		}
	}

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

	perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, 0, regs, address);

	if (!down_read_trylock(&mm->mmap_sem)) {
		if ((regs->tstate & TSTATE_PRIV) &&
		    !search_exception_tables(regs->tpc)) {
			insn = get_fault_insn(regs, insn);
			goto handle_kernel_fault;
		}
		down_read(&mm->mmap_sem);
	}

	vma = find_vma(mm, address);
	if (!vma)
		goto bad_area;

	/* Pure DTLB misses do not tell us whether the fault causing
	 * load/store/atomic was a write or not, it only says that there
	 * was no match.  So in such a case we (carefully) read the
	 * instruction to try and figure this out.  It's an optimization
	 * so it's ok if we can't do this.
	 *
	 * Special hack, window spill/fill knows the exact fault type.
	 */
	if (((fault_code &
	      (FAULT_CODE_DTLB | FAULT_CODE_WRITE | FAULT_CODE_WINFIXUP)) == FAULT_CODE_DTLB) &&
	    (vma->vm_flags & VM_WRITE) != 0) {
		insn = get_fault_insn(regs, 0);
		if (!insn)
			goto continue_fault;
		/* All loads, stores and atomics have bits 30 and 31 both set
		 * in the instruction.  Bit 21 is set in all stores, but we
		 * have to avoid prefetches which also have bit 21 set.
		 */
		if ((insn & 0xc0200000) == 0xc0200000 &&
		    (insn & 0x01780000) != 0x01680000) {
			/* Don't bother updating thread struct value,
			 * because update_mmu_cache only cares which tlb
			 * the access came from.
			 */
			fault_code |= FAULT_CODE_WRITE;
		}
	}
continue_fault:

	if (vma->vm_start <= address)
		goto good_area;
	if (!(vma->vm_flags & VM_GROWSDOWN))
		goto bad_area;
	if (!(fault_code & FAULT_CODE_WRITE)) {
		/* Non-faulting loads shouldn't expand stack. */
		insn = get_fault_insn(regs, insn);
		if ((insn & 0xc0800000) == 0xc0800000) {
			unsigned char asi;

			if (insn & 0x2000)
				asi = (regs->tstate >> 24);
			else
				asi = (insn >> 5);
			if ((asi & 0xf2) == 0x82)
				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:
	si_code = SEGV_ACCERR;

	/* If we took a ITLB miss on a non-executable page, catch
	 * that here.
	 */
	if ((fault_code & FAULT_CODE_ITLB) && !(vma->vm_flags & VM_EXEC)) {
		BUG_ON(address != regs->tpc);
		BUG_ON(regs->tstate & TSTATE_PRIV);
		goto bad_area;
	}

	if (fault_code & FAULT_CODE_WRITE) {
		if (!(vma->vm_flags & VM_WRITE))
			goto bad_area;

		/* Spitfire has an icache which does not snoop
		 * processor stores.  Later processors do...
		 */
		if (tlb_type == spitfire &&
		    (vma->vm_flags & VM_EXEC) != 0 &&
		    vma->vm_file != NULL)
			set_thread_fault_code(fault_code |
					      FAULT_CODE_BLKCOMMIT);
	} else {
		/* Allow reads even for write-only mappings */
		if (!(vma->vm_flags & (VM_READ | VM_EXEC)))
			goto bad_area;
	}

	fault = handle_mm_fault(mm, vma, address, (fault_code & FAULT_CODE_WRITE) ? FAULT_FLAG_WRITE : 0);
	if (unlikely(fault & VM_FAULT_ERROR)) {
		if (fault & VM_FAULT_OOM)
			goto out_of_memory;
		else if (fault & VM_FAULT_SIGBUS)
			goto do_sigbus;
		BUG();
	}
	if (fault & VM_FAULT_MAJOR) {
		current->maj_flt++;
		perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MAJ, 1, 0,
			      regs, address);
	} else {
		current->min_flt++;
		perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MIN, 1, 0,
			      regs, address);
	}
	up_read(&mm->mmap_sem);

	mm_rss = get_mm_rss(mm);
#ifdef CONFIG_HUGETLB_PAGE
	mm_rss -= (mm->context.huge_pte_count * (HPAGE_SIZE / PAGE_SIZE));
#endif
	if (unlikely(mm_rss >
		     mm->context.tsb_block[MM_TSB_BASE].tsb_rss_limit))
		tsb_grow(mm, MM_TSB_BASE, mm_rss);
#ifdef CONFIG_HUGETLB_PAGE
	mm_rss = mm->context.huge_pte_count;
	if (unlikely(mm_rss >
		     mm->context.tsb_block[MM_TSB_HUGE].tsb_rss_limit))
		tsb_grow(mm, MM_TSB_HUGE, mm_rss);
#endif
	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:
	insn = get_fault_insn(regs, insn);
	up_read(&mm->mmap_sem);

handle_kernel_fault:
	do_kernel_fault(regs, si_code, fault_code, insn, address);
	return;

/*
 * 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:
	insn = get_fault_insn(regs, insn);
	up_read(&mm->mmap_sem);
	if (!(regs->tstate & TSTATE_PRIV)) {
		pagefault_out_of_memory();
		return;
	}
	goto handle_kernel_fault;

intr_or_no_mm:
	insn = get_fault_insn(regs, 0);
	goto handle_kernel_fault;

do_sigbus:
	insn = get_fault_insn(regs, insn);
	up_read(&mm->mmap_sem);

	/*
	 * Send a sigbus, regardless of whether we were in kernel
	 * or user mode.
	 */
	do_fault_siginfo(BUS_ADRERR, SIGBUS, regs, insn, fault_code);

	/* Kernel mode? Handle exceptions or die */
	if (regs->tstate & TSTATE_PRIV)
		goto handle_kernel_fault;
}