fault.c 11.7 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
/*
 *  PowerPC version
 *    Copyright (C) 1995-1996 Gary Thomas (gdt@linuxppc.org)
 *
 *  Derived from "arch/i386/mm/fault.c"
 *    Copyright (C) 1991, 1992, 1993, 1994  Linus Torvalds
 *
 *  Modified by Cort Dougan and Paul Mackerras.
 *
 *  Modified for PPC64 by Dave Engebretsen (engebret@ibm.com)
 *
 *  This program is free software; you can redistribute it and/or
 *  modify it under the terms of the GNU General Public License
 *  as published by the Free Software Foundation; either version
 *  2 of the License, 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/interrupt.h>
#include <linux/highmem.h>
#include <linux/module.h>
#include <linux/kprobes.h>
31
#include <linux/kdebug.h>
32 33 34 35 36 37 38 39 40 41

#include <asm/page.h>
#include <asm/pgtable.h>
#include <asm/mmu.h>
#include <asm/mmu_context.h>
#include <asm/system.h>
#include <asm/uaccess.h>
#include <asm/tlbflush.h>
#include <asm/siginfo.h>

42

43 44
#ifdef CONFIG_KPROBES
static inline int notify_page_fault(struct pt_regs *regs)
45
{
46 47 48 49 50 51 52 53 54
	int ret = 0;

	/* kprobe_running() needs smp_processor_id() */
	if (!user_mode(regs)) {
		preempt_disable();
		if (kprobe_running() && kprobe_fault_handler(regs, 11))
			ret = 1;
		preempt_enable();
	}
55

56
	return ret;
57 58
}
#else
59
static inline int notify_page_fault(struct pt_regs *regs)
60
{
61
	return 0;
62 63 64
}
#endif

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
/*
 * Check whether the instruction at regs->nip is a store using
 * an update addressing form which will update r1.
 */
static int store_updates_sp(struct pt_regs *regs)
{
	unsigned int inst;

	if (get_user(inst, (unsigned int __user *)regs->nip))
		return 0;
	/* check for 1 in the rA field */
	if (((inst >> 16) & 0x1f) != 1)
		return 0;
	/* check major opcode */
	switch (inst >> 26) {
	case 37:	/* stwu */
	case 39:	/* stbu */
	case 45:	/* sthu */
	case 53:	/* stfsu */
	case 55:	/* stfdu */
		return 1;
	case 62:	/* std or stdu */
		return (inst & 3) == 1;
	case 31:
		/* check minor opcode */
		switch ((inst >> 1) & 0x3ff) {
		case 181:	/* stdux */
		case 183:	/* stwux */
		case 247:	/* stbux */
		case 439:	/* sthux */
		case 695:	/* stfsux */
		case 759:	/* stfdux */
			return 1;
		}
	}
	return 0;
}

103
#if !(defined(CONFIG_4xx) || defined(CONFIG_BOOKE))
104 105
static void do_dabr(struct pt_regs *regs, unsigned long address,
		    unsigned long error_code)
106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122
{
	siginfo_t info;

	if (notify_die(DIE_DABR_MATCH, "dabr_match", regs, error_code,
			11, SIGSEGV) == NOTIFY_STOP)
		return;

	if (debugger_dabr_match(regs))
		return;

	/* Clear the DABR */
	set_dabr(0);

	/* Deliver the signal to userspace */
	info.si_signo = SIGTRAP;
	info.si_errno = 0;
	info.si_code = TRAP_HWBKPT;
123
	info.si_addr = (void __user *)address;
124 125
	force_sig_info(SIGTRAP, &info, current);
}
126
#endif /* !(CONFIG_4xx || CONFIG_BOOKE)*/
127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147

/*
 * For 600- and 800-family processors, the error_code parameter is DSISR
 * for a data fault, SRR1 for an instruction fault. For 400-family processors
 * the error_code parameter is ESR for a data fault, 0 for an instruction
 * fault.
 * For 64-bit processors, the error_code parameter is
 *  - DSISR for a non-SLB data access fault,
 *  - SRR1 & 0x08000000 for a non-SLB instruction access fault
 *  - 0 any SLB fault.
 *
 * The return value is 0 if the fault was handled, or the signal
 * number if this is a kernel fault that can't be handled here.
 */
int __kprobes do_page_fault(struct pt_regs *regs, unsigned long address,
			    unsigned long error_code)
{
	struct vm_area_struct * vma;
	struct mm_struct *mm = current->mm;
	siginfo_t info;
	int code = SEGV_MAPERR;
N
Nick Piggin 已提交
148
	int is_write = 0, ret;
149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166
	int trap = TRAP(regs);
 	int is_exec = trap == 0x400;

#if !(defined(CONFIG_4xx) || defined(CONFIG_BOOKE))
	/*
	 * Fortunately the bit assignments in SRR1 for an instruction
	 * fault and DSISR for a data fault are mostly the same for the
	 * bits we are interested in.  But there are some bits which
	 * indicate errors in DSISR but can validly be set in SRR1.
	 */
	if (trap == 0x400)
		error_code &= 0x48200000;
	else
		is_write = error_code & DSISR_ISSTORE;
#else
	is_write = error_code & ESR_DST;
#endif /* CONFIG_4xx || CONFIG_BOOKE */

167
	if (notify_page_fault(regs))
168 169 170 171 172 173 174 175 176 177 178 179 180 181
		return 0;

	if (trap == 0x300) {
		if (debugger_fault_handler(regs))
			return 0;
	}

	/* On a kernel SLB miss we can only check for a valid exception entry */
	if (!user_mode(regs) && (address >= TASK_SIZE))
		return SIGSEGV;

#if !(defined(CONFIG_4xx) || defined(CONFIG_BOOKE))
  	if (error_code & DSISR_DABRMATCH) {
		/* DABR match */
182
		do_dabr(regs, address, error_code);
183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200
		return 0;
	}
#endif /* !(CONFIG_4xx || CONFIG_BOOKE)*/

	if (in_atomic() || mm == NULL) {
		if (!user_mode(regs))
			return SIGSEGV;
		/* in_atomic() in user mode is really bad,
		   as is current->mm == NULL. */
		printk(KERN_EMERG "Page fault in user mode with"
		       "in_atomic() = %d mm = %p\n", in_atomic(), mm);
		printk(KERN_EMERG "NIP = %lx  MSR = %lx\n",
		       regs->nip, regs->msr);
		die("Weird page fault", regs, SIGSEGV);
	}

	/* When running in the kernel we expect faults to occur only to
	 * addresses in user space.  All other faults represent errors in the
201 202
	 * kernel and should generate an OOPS.  Unfortunately, in the case of an
	 * erroneous fault occurring in a code path which already holds mmap_sem
203 204 205 206 207 208
	 * we will deadlock attempting to validate the fault against the
	 * address space.  Luckily the kernel only validly references user
	 * space from well defined areas of code, which are listed in the
	 * exceptions table.
	 *
	 * As the vast majority of faults will be valid we will only perform
209
	 * the source reference check when there is a possibility of a deadlock.
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
	 * Attempt to lock the address space, if we cannot we then validate the
	 * source.  If this is invalid we can skip the address space check,
	 * thus avoiding the deadlock.
	 */
	if (!down_read_trylock(&mm->mmap_sem)) {
		if (!user_mode(regs) && !search_exception_tables(regs->nip))
			goto bad_area_nosemaphore;

		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;

	/*
	 * N.B. The POWER/Open ABI allows programs to access up to
	 * 288 bytes below the stack pointer.
	 * The kernel signal delivery code writes up to about 1.5kB
	 * below the stack pointer (r1) before decrementing it.
	 * The exec code can write slightly over 640kB to the stack
	 * before setting the user r1.  Thus we allow the stack to
	 * expand to 1MB without further checks.
	 */
	if (address + 0x100000 < vma->vm_end) {
		/* get user regs even if this fault is in kernel mode */
		struct pt_regs *uregs = current->thread.regs;
		if (uregs == NULL)
			goto bad_area;

		/*
		 * A user-mode access to an address a long way below
		 * the stack pointer is only valid if the instruction
		 * is one which would update the stack pointer to the
		 * address accessed if the instruction completed,
		 * i.e. either stwu rs,n(r1) or stwux rs,r1,rb
		 * (or the byte, halfword, float or double forms).
		 *
		 * If we don't check this then any write to the area
		 * between the last mapped region and the stack will
		 * expand the stack rather than segfaulting.
		 */
		if (address + 2048 < uregs->gpr[1]
		    && (!user_mode(regs) || !store_updates_sp(regs)))
			goto bad_area;
	}
	if (expand_stack(vma, address))
		goto bad_area;

good_area:
	code = SEGV_ACCERR;
#if defined(CONFIG_6xx)
	if (error_code & 0x95700000)
		/* an error such as lwarx to I/O controller space,
		   address matching DABR, eciwx, etc. */
		goto bad_area;
#endif /* CONFIG_6xx */
#if defined(CONFIG_8xx)
        /* The MPC8xx seems to always set 0x80000000, which is
         * "undefined".  Of those that can be set, this is the only
         * one which seems bad.
         */
	if (error_code & 0x10000000)
                /* Guarded storage error. */
		goto bad_area;
#endif /* CONFIG_8xx */

	if (is_exec) {
282
#if !(defined(CONFIG_4xx) || defined(CONFIG_BOOKE))
283 284 285
		/* protection fault */
		if (error_code & DSISR_PROTFAULT)
			goto bad_area;
286 287 288 289 290 291 292
		/*
		 * Allow execution from readable areas if the MMU does not
		 * provide separate controls over reading and executing.
		 */
		if (!(vma->vm_flags & VM_EXEC) &&
		    (cpu_has_feature(CPU_FTR_NOEXECUTE) ||
		     !(vma->vm_flags & (VM_READ | VM_WRITE))))
293
			goto bad_area;
294
#else
295
		pte_t *ptep;
296
		pmd_t *pmdp;
297 298 299 300

		/* Since 4xx/Book-E supports per-page execute permission,
		 * we lazily flush dcache to icache. */
		ptep = NULL;
301 302 303 304 305
		if (get_pteptr(mm, address, &ptep, &pmdp)) {
			spinlock_t *ptl = pte_lockptr(mm, pmdp);
			spin_lock(ptl);
			if (pte_present(*ptep)) {
				struct page *page = pte_page(*ptep);
306

307 308 309 310 311 312 313 314 315
				if (!test_bit(PG_arch_1, &page->flags)) {
					flush_dcache_icache_page(page);
					set_bit(PG_arch_1, &page->flags);
				}
				pte_update(ptep, 0, _PAGE_HWEXEC);
				_tlbie(address);
				pte_unmap_unlock(ptep, ptl);
				up_read(&mm->mmap_sem);
				return 0;
316
			}
317
			pte_unmap_unlock(ptep, ptl);
318 319 320 321 322 323 324 325 326 327 328
		}
#endif
	/* a write */
	} else if (is_write) {
		if (!(vma->vm_flags & VM_WRITE))
			goto bad_area;
	/* a read */
	} else {
		/* protection fault */
		if (error_code & 0x08000000)
			goto bad_area;
329
		if (!(vma->vm_flags & (VM_READ | VM_EXEC | VM_WRITE)))
330 331 332 333 334 335 336 337 338
			goto bad_area;
	}

	/*
	 * If for any reason at all we couldn't handle the fault,
	 * make sure we exit gracefully rather than endlessly redo
	 * the fault.
	 */
 survive:
N
Nick Piggin 已提交
339 340 341 342 343 344
	ret = handle_mm_fault(mm, vma, address, is_write);
	if (unlikely(ret & VM_FAULT_ERROR)) {
		if (ret & VM_FAULT_OOM)
			goto out_of_memory;
		else if (ret & VM_FAULT_SIGBUS)
			goto do_sigbus;
345 346
		BUG();
	}
N
Nick Piggin 已提交
347 348 349 350
	if (ret & VM_FAULT_MAJOR)
		current->maj_flt++;
	else
		current->min_flt++;
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
	up_read(&mm->mmap_sem);
	return 0;

bad_area:
	up_read(&mm->mmap_sem);

bad_area_nosemaphore:
	/* User mode accesses cause a SIGSEGV */
	if (user_mode(regs)) {
		_exception(SIGSEGV, regs, code, address);
		return 0;
	}

	if (is_exec && (error_code & DSISR_PROTFAULT)
	    && printk_ratelimit())
		printk(KERN_CRIT "kernel tried to execute NX-protected"
		       " page (%lx) - exploit attempt? (uid: %d)\n",
		       address, current->uid);

	return SIGSEGV;

/*
 * 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);
378
	if (is_init(current)) {
379 380 381 382 383 384
		yield();
		down_read(&mm->mmap_sem);
		goto survive;
	}
	printk("VM: killing process %s\n", current->comm);
	if (user_mode(regs))
385
		do_group_exit(SIGKILL);
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
	return SIGKILL;

do_sigbus:
	up_read(&mm->mmap_sem);
	if (user_mode(regs)) {
		info.si_signo = SIGBUS;
		info.si_errno = 0;
		info.si_code = BUS_ADRERR;
		info.si_addr = (void __user *)address;
		force_sig_info(SIGBUS, &info, current);
		return 0;
	}
	return SIGBUS;
}

/*
 * bad_page_fault is called when we have a bad access from the kernel.
 * It is called from the DSI and ISI handlers in head.S and from some
 * of the procedures in traps.c.
 */
void bad_page_fault(struct pt_regs *regs, unsigned long address, int sig)
{
	const struct exception_table_entry *entry;

	/* Are we prepared to handle this fault?  */
	if ((entry = search_exception_tables(regs->nip)) != NULL) {
		regs->nip = entry->fixup;
		return;
	}

	/* kernel has accessed a bad area */
417 418

	switch (regs->trap) {
419 420 421 422 423 424 425 426 427 428 429 430 431 432
	case 0x300:
	case 0x380:
		printk(KERN_ALERT "Unable to handle kernel paging request for "
			"data at address 0x%08lx\n", regs->dar);
		break;
	case 0x400:
	case 0x480:
		printk(KERN_ALERT "Unable to handle kernel paging request for "
			"instruction fetch\n");
		break;
	default:
		printk(KERN_ALERT "Unable to handle kernel paging request for "
			"unknown fault\n");
		break;
433 434 435 436
	}
	printk(KERN_ALERT "Faulting instruction address: 0x%08lx\n",
		regs->nip);

437 438
	die("Kernel access of bad area", regs, sig);
}