summaryrefslogtreecommitdiffstats
path: root/arch/microblaze/mm/fault.c
blob: a9626e6a68af93f34962129870c5d5c91cee40a0 (plain)
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
/*
 *  arch/microblaze/mm/fault.c
 *
 *    Copyright (C) 2007 Xilinx, Inc.  All rights reserved.
 *
 *  Derived from "arch/ppc/mm/fault.c"
 *    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.
 *
 * This file is subject to the terms and conditions of the GNU General
 * Public License.  See the file COPYING in the main directory of this
 * archive for more details.
 *
 */

#include <linux/extable.h>
#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/perf_event.h>

#include <asm/page.h>
#include <asm/mmu.h>
#include <linux/mmu_context.h>
#include <linux/uaccess.h>
#include <asm/exceptions.h>

static unsigned long pte_misses;	/* updated by do_page_fault() */
static unsigned long pte_errors;	/* updated by do_page_fault() */

/*
 * Check whether the instruction at regs->pc 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->pc))
		return 0;
	/* check for 1 in the rD field */
	if (((inst >> 21) & 0x1f) != 1)
		return 0;
	/* check for store opcodes */
	if ((inst & 0xd0000000) == 0xd0000000)
		return 1;
	return 0;
}


/*
 * bad_page_fault is called when we have a bad access from the kernel.
 * It is called from do_page_fault above 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 *fixup;
/* MS: no context */
	/* Are we prepared to handle this fault?  */
	fixup = search_exception_tables(regs->pc);
	if (fixup) {
		regs->pc = fixup->fixup;
		return;
	}

	/* kernel has accessed a bad area */
	die("kernel access of bad area", regs, sig);
}

/*
 * The error_code parameter is ESR for a data fault,
 * 0 for an instruction fault.
 */
void 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;
	int code = SEGV_MAPERR;
	int is_write = error_code & ESR_S;
	vm_fault_t fault;
	unsigned int flags = FAULT_FLAG_DEFAULT;

	regs->ear = address;
	regs->esr = error_code;

	/* On a kernel SLB miss we can only check for a valid exception entry */
	if (unlikely(kernel_mode(regs) && (address >= TASK_SIZE))) {
		pr_warn("kernel task_size exceed");
		_exception(SIGSEGV, regs, code, address);
	}

	/* for instr TLB miss and instr storage exception ESR_S is undefined */
	if ((error_code & 0x13) == 0x13 || (error_code & 0x11) == 0x11)
		is_write = 0;

	if (unlikely(faulthandler_disabled() || !mm)) {
		if (kernel_mode(regs))
			goto bad_area_nosemaphore;

		/* faulthandler_disabled() in user mode is really bad,
		   as is current->mm == NULL. */
		pr_emerg("Page fault in user mode with faulthandler_disabled(), mm = %p\n",
			 mm);
		pr_emerg("r15 = %lx  MSR = %lx\n",
		       regs->r15, regs->msr);
		die("Weird page fault", regs, SIGSEGV);
	}

	if (user_mode(regs))
		flags |= FAULT_FLAG_USER;

	perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, address);

	/* When running in the kernel we expect faults to occur only to
	 * addresses in user space.  All other faults represent errors in the
	 * kernel and should generate an OOPS.  Unfortunately, in the case of an
	 * erroneous fault occurring in a code path which already holds mmap_lock
	 * 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
	 * the source reference check when there is a possibility of a deadlock.
	 * 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 (unlikely(!mmap_read_trylock(mm))) {
		if (kernel_mode(regs) && !search_exception_tables(regs->pc))
			goto bad_area_nosemaphore;

retry:
		mmap_read_lock(mm);
	}

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

	if (vma->vm_start <= address)
		goto good_area;

	if (unlikely(!(vma->vm_flags & VM_GROWSDOWN)))
		goto bad_area;

	if (unlikely(!is_write))
		goto bad_area;

	/*
	 * N.B. The ABI allows programs to access up to
	 * a few hundred bytes below the stack pointer (TBD).
	 * 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 (unlikely(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->r1
			&& (kernel_mode(regs) || !store_updates_sp(regs)))
				goto bad_area;
	}
	if (expand_stack(vma, address))
		goto bad_area;

good_area:
	code = SEGV_ACCERR;

	/* a write */
	if (unlikely(is_write)) {
		if (unlikely(!(vma->vm_flags & VM_WRITE)))
			goto bad_area;
		flags |= FAULT_FLAG_WRITE;
	/* a read */
	} else {
		/* protection fault */
		if (unlikely(error_code & 0x08000000))
			goto bad_area;
		if (unlikely(!(vma->vm_flags & (VM_READ | VM_EXEC))))
			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.
	 */
	fault = handle_mm_fault(vma, address, flags, regs);

	if (fault_signal_pending(fault, regs))
		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 (fault & VM_FAULT_RETRY) {
		flags |= FAULT_FLAG_TRIED;

		/*
		 * No need to mmap_read_unlock(mm) as we would
		 * have already released it in __lock_page_or_retry
		 * in mm/filemap.c.
		 */

		goto retry;
	}

	mmap_read_unlock(mm);

	/*
	 * keep track of tlb+htab misses that are good addrs but
	 * just need pte's created via handle_mm_fault()
	 * -- Cort
	 */
	pte_misses++;
	return;

bad_area:
	mmap_read_unlock(mm);

bad_area_nosemaphore:
	pte_errors++;

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

	bad_page_fault(regs, address, SIGSEGV);
	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:
	mmap_read_unlock(mm);
	if (!user_mode(regs))
		bad_page_fault(regs, address, SIGKILL);
	else
		pagefault_out_of_memory();
	return;

do_sigbus:
	mmap_read_unlock(mm);
	if (user_mode(regs)) {
		force_sig_fault(SIGBUS, BUS_ADRERR, (void __user *)address);
		return;
	}
	bad_page_fault(regs, address, SIGBUS);
}