summaryrefslogtreecommitdiffstats
path: root/arch/um/kernel/trap.c
blob: 8f18cf56b3ddfde62df96f09aeaed68278640b08 (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
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
// SPDX-License-Identifier: GPL-2.0
/*
 * Copyright (C) 2000 - 2007 Jeff Dike (jdike@{addtoit,linux.intel}.com)
 */

#include <linux/mm.h>
#include <linux/sched/signal.h>
#include <linux/hardirq.h>
#include <linux/module.h>
#include <linux/uaccess.h>
#include <linux/sched/debug.h>
#include <asm/current.h>
#include <asm/pgtable.h>
#include <asm/tlbflush.h>
#include <arch.h>
#include <as-layout.h>
#include <kern_util.h>
#include <os.h>
#include <skas.h>

/*
 * Note this is constrained to return 0, -EFAULT, -EACCES, -ENOMEM by
 * segv().
 */
int handle_page_fault(unsigned long address, unsigned long ip,
		      int is_write, int is_user, int *code_out)
{
	struct mm_struct *mm = current->mm;
	struct vm_area_struct *vma;
	pgd_t *pgd;
	p4d_t *p4d;
	pud_t *pud;
	pmd_t *pmd;
	pte_t *pte;
	int err = -EFAULT;
	unsigned int flags = FAULT_FLAG_DEFAULT;

	*code_out = SEGV_MAPERR;

	/*
	 * If the fault was with pagefaults disabled, don't take the fault, just
	 * fail.
	 */
	if (faulthandler_disabled())
		goto out_nosemaphore;

	if (is_user)
		flags |= FAULT_FLAG_USER;
retry:
	down_read(&mm->mmap_sem);
	vma = find_vma(mm, address);
	if (!vma)
		goto out;
	else if (vma->vm_start <= address)
		goto good_area;
	else if (!(vma->vm_flags & VM_GROWSDOWN))
		goto out;
	else if (is_user && !ARCH_IS_STACKGROW(address))
		goto out;
	else if (expand_stack(vma, address))
		goto out;

good_area:
	*code_out = SEGV_ACCERR;
	if (is_write) {
		if (!(vma->vm_flags & VM_WRITE))
			goto out;
		flags |= FAULT_FLAG_WRITE;
	} else {
		/* Don't require VM_READ|VM_EXEC for write faults! */
		if (!(vma->vm_flags & (VM_READ | VM_EXEC)))
			goto out;
	}

	do {
		vm_fault_t fault;

		fault = handle_mm_fault(vma, address, flags);

		if ((fault & VM_FAULT_RETRY) && fatal_signal_pending(current))
			goto out_nosemaphore;

		if (unlikely(fault & VM_FAULT_ERROR)) {
			if (fault & VM_FAULT_OOM) {
				goto out_of_memory;
			} else if (fault & VM_FAULT_SIGSEGV) {
				goto out;
			} else if (fault & VM_FAULT_SIGBUS) {
				err = -EACCES;
				goto out;
			}
			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_TRIED;

				goto retry;
			}
		}

		pgd = pgd_offset(mm, address);
		p4d = p4d_offset(pgd, address);
		pud = pud_offset(p4d, address);
		pmd = pmd_offset(pud, address);
		pte = pte_offset_kernel(pmd, address);
	} while (!pte_present(*pte));
	err = 0;
	/*
	 * The below warning was added in place of
	 *	pte_mkyoung(); if (is_write) pte_mkdirty();
	 * If it's triggered, we'd see normally a hang here (a clean pte is
	 * marked read-only to emulate the dirty bit).
	 * However, the generic code can mark a PTE writable but clean on a
	 * concurrent read fault, triggering this harmlessly. So comment it out.
	 */
#if 0
	WARN_ON(!pte_young(*pte) || (is_write && !pte_dirty(*pte)));
#endif
	flush_tlb_page(vma, address);
out:
	up_read(&mm->mmap_sem);
out_nosemaphore:
	return err;

out_of_memory:
	/*
	 * We ran out of memory, call the OOM killer, and return the userspace
	 * (which will retry the fault, or kill us if we got oom-killed).
	 */
	up_read(&mm->mmap_sem);
	if (!is_user)
		goto out_nosemaphore;
	pagefault_out_of_memory();
	return 0;
}
EXPORT_SYMBOL(handle_page_fault);

static void show_segv_info(struct uml_pt_regs *regs)
{
	struct task_struct *tsk = current;
	struct faultinfo *fi = UPT_FAULTINFO(regs);

	if (!unhandled_signal(tsk, SIGSEGV))
		return;

	if (!printk_ratelimit())
		return;

	printk("%s%s[%d]: segfault at %lx ip %px sp %px error %x",
		task_pid_nr(tsk) > 1 ? KERN_INFO : KERN_EMERG,
		tsk->comm, task_pid_nr(tsk), FAULT_ADDRESS(*fi),
		(void *)UPT_IP(regs), (void *)UPT_SP(regs),
		fi->error_code);

	print_vma_addr(KERN_CONT " in ", UPT_IP(regs));
	printk(KERN_CONT "\n");
}

static void bad_segv(struct faultinfo fi, unsigned long ip)
{
	current->thread.arch.faultinfo = fi;
	force_sig_fault(SIGSEGV, SEGV_ACCERR, (void __user *) FAULT_ADDRESS(fi));
}

void fatal_sigsegv(void)
{
	force_sigsegv(SIGSEGV);
	do_signal(&current->thread.regs);
	/*
	 * This is to tell gcc that we're not returning - do_signal
	 * can, in general, return, but in this case, it's not, since
	 * we just got a fatal SIGSEGV queued.
	 */
	os_dump_core();
}

/**
 * segv_handler() - the SIGSEGV handler
 * @sig:	the signal number
 * @unused_si:	the signal info struct; unused in this handler
 * @regs:	the ptrace register information
 *
 * The handler first extracts the faultinfo from the UML ptrace regs struct.
 * If the userfault did not happen in an UML userspace process, bad_segv is called.
 * Otherwise the signal did happen in a cloned userspace process, handle it.
 */
void segv_handler(int sig, struct siginfo *unused_si, struct uml_pt_regs *regs)
{
	struct faultinfo * fi = UPT_FAULTINFO(regs);

	if (UPT_IS_USER(regs) && !SEGV_IS_FIXABLE(fi)) {
		show_segv_info(regs);
		bad_segv(*fi, UPT_IP(regs));
		return;
	}
	segv(*fi, UPT_IP(regs), UPT_IS_USER(regs), regs);
}

/*
 * We give a *copy* of the faultinfo in the regs to segv.
 * This must be done, since nesting SEGVs could overwrite
 * the info in the regs. A pointer to the info then would
 * give us bad data!
 */
unsigned long segv(struct faultinfo fi, unsigned long ip, int is_user,
		   struct uml_pt_regs *regs)
{
	jmp_buf *catcher;
	int si_code;
	int err;
	int is_write = FAULT_WRITE(fi);
	unsigned long address = FAULT_ADDRESS(fi);

	if (!is_user && regs)
		current->thread.segv_regs = container_of(regs, struct pt_regs, regs);

	if (!is_user && (address >= start_vm) && (address < end_vm)) {
		flush_tlb_kernel_vm();
		goto out;
	}
	else if (current->mm == NULL) {
		show_regs(container_of(regs, struct pt_regs, regs));
		panic("Segfault with no mm");
	}
	else if (!is_user && address > PAGE_SIZE && address < TASK_SIZE) {
		show_regs(container_of(regs, struct pt_regs, regs));
		panic("Kernel tried to access user memory at addr 0x%lx, ip 0x%lx",
		       address, ip);
	}

	if (SEGV_IS_FIXABLE(&fi))
		err = handle_page_fault(address, ip, is_write, is_user,
					&si_code);
	else {
		err = -EFAULT;
		/*
		 * A thread accessed NULL, we get a fault, but CR2 is invalid.
		 * This code is used in __do_copy_from_user() of TT mode.
		 * XXX tt mode is gone, so maybe this isn't needed any more
		 */
		address = 0;
	}

	catcher = current->thread.fault_catcher;
	if (!err)
		goto out;
	else if (catcher != NULL) {
		current->thread.fault_addr = (void *) address;
		UML_LONGJMP(catcher, 1);
	}
	else if (current->thread.fault_addr != NULL)
		panic("fault_addr set but no fault catcher");
	else if (!is_user && arch_fixup(ip, regs))
		goto out;

	if (!is_user) {
		show_regs(container_of(regs, struct pt_regs, regs));
		panic("Kernel mode fault at addr 0x%lx, ip 0x%lx",
		      address, ip);
	}

	show_segv_info(regs);

	if (err == -EACCES) {
		current->thread.arch.faultinfo = fi;
		force_sig_fault(SIGBUS, BUS_ADRERR, (void __user *)address);
	} else {
		BUG_ON(err != -EFAULT);
		current->thread.arch.faultinfo = fi;
		force_sig_fault(SIGSEGV, si_code, (void __user *) address);
	}

out:
	if (regs)
		current->thread.segv_regs = NULL;

	return 0;
}

void relay_signal(int sig, struct siginfo *si, struct uml_pt_regs *regs)
{
	int code, err;
	if (!UPT_IS_USER(regs)) {
		if (sig == SIGBUS)
			printk(KERN_ERR "Bus error - the host /dev/shm or /tmp "
			       "mount likely just ran out of space\n");
		panic("Kernel mode signal %d", sig);
	}

	arch_examine_signal(sig, regs);

	/* Is the signal layout for the signal known?
	 * Signal data must be scrubbed to prevent information leaks.
	 */
	code = si->si_code;
	err = si->si_errno;
	if ((err == 0) && (siginfo_layout(sig, code) == SIL_FAULT)) {
		struct faultinfo *fi = UPT_FAULTINFO(regs);
		current->thread.arch.faultinfo = *fi;
		force_sig_fault(sig, code, (void __user *)FAULT_ADDRESS(*fi));
	} else {
		printk(KERN_ERR "Attempted to relay unknown signal %d (si_code = %d) with errno %d\n",
		       sig, code, err);
		force_sig(sig);
	}
}

void bus_handler(int sig, struct siginfo *si, struct uml_pt_regs *regs)
{
	if (current->thread.fault_catcher != NULL)
		UML_LONGJMP(current->thread.fault_catcher, 1);
	else
		relay_signal(sig, si, regs);
}

void winch(int sig, struct siginfo *unused_si, struct uml_pt_regs *regs)
{
	do_IRQ(WINCH_IRQ, regs);
}

void trap_init(void)
{
}