summaryrefslogtreecommitdiffstats
path: root/arch/x86/kernel/vsyscall_64.c
blob: ea5b5709aa76acc00ba3721570d31f6ee7901975 (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
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
/*
 *  Copyright (C) 2001 Andrea Arcangeli <andrea@suse.de> SuSE
 *  Copyright 2003 Andi Kleen, SuSE Labs.
 *
 *  [ NOTE: this mechanism is now deprecated in favor of the vDSO. ]
 *
 *  Thanks to hpa@transmeta.com for some useful hint.
 *  Special thanks to Ingo Molnar for his early experience with
 *  a different vsyscall implementation for Linux/IA32 and for the name.
 *
 *  vsyscall 1 is located at -10Mbyte, vsyscall 2 is located
 *  at virtual address -10Mbyte+1024bytes etc... There are at max 4
 *  vsyscalls. One vsyscall can reserve more than 1 slot to avoid
 *  jumping out of line if necessary. We cannot add more with this
 *  mechanism because older kernels won't return -ENOSYS.
 *
 *  Note: the concept clashes with user mode linux.  UML users should
 *  use the vDSO.
 */

#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt

#include <linux/time.h>
#include <linux/init.h>
#include <linux/kernel.h>
#include <linux/timer.h>
#include <linux/seqlock.h>
#include <linux/jiffies.h>
#include <linux/sysctl.h>
#include <linux/topology.h>
#include <linux/timekeeper_internal.h>
#include <linux/getcpu.h>
#include <linux/cpu.h>
#include <linux/smp.h>
#include <linux/notifier.h>
#include <linux/syscalls.h>
#include <linux/ratelimit.h>

#include <asm/vsyscall.h>
#include <asm/pgtable.h>
#include <asm/compat.h>
#include <asm/page.h>
#include <asm/unistd.h>
#include <asm/fixmap.h>
#include <asm/errno.h>
#include <asm/io.h>
#include <asm/segment.h>
#include <asm/desc.h>
#include <asm/topology.h>
#include <asm/traps.h>

#define CREATE_TRACE_POINTS
#include "vsyscall_trace.h"

DEFINE_VVAR(int, vgetcpu_mode);

static enum { EMULATE, NATIVE, NONE } vsyscall_mode = EMULATE;

static int __init vsyscall_setup(char *str)
{
	if (str) {
		if (!strcmp("emulate", str))
			vsyscall_mode = EMULATE;
		else if (!strcmp("native", str))
			vsyscall_mode = NATIVE;
		else if (!strcmp("none", str))
			vsyscall_mode = NONE;
		else
			return -EINVAL;

		return 0;
	}

	return -EINVAL;
}
early_param("vsyscall", vsyscall_setup);

static void warn_bad_vsyscall(const char *level, struct pt_regs *regs,
			      const char *message)
{
	if (!show_unhandled_signals)
		return;

	pr_notice_ratelimited("%s%s[%d] %s ip:%lx cs:%lx sp:%lx ax:%lx si:%lx di:%lx\n",
			      level, current->comm, task_pid_nr(current),
			      message, regs->ip, regs->cs,
			      regs->sp, regs->ax, regs->si, regs->di);
}

static int addr_to_vsyscall_nr(unsigned long addr)
{
	int nr;

	if ((addr & ~0xC00UL) != VSYSCALL_ADDR)
		return -EINVAL;

	nr = (addr & 0xC00UL) >> 10;
	if (nr >= 3)
		return -EINVAL;

	return nr;
}

static bool write_ok_or_segv(unsigned long ptr, size_t size)
{
	/*
	 * XXX: if access_ok, get_user, and put_user handled
	 * sig_on_uaccess_error, this could go away.
	 */

	if (!access_ok(VERIFY_WRITE, (void __user *)ptr, size)) {
		siginfo_t info;
		struct thread_struct *thread = &current->thread;

		thread->error_code	= 6;  /* user fault, no page, write */
		thread->cr2		= ptr;
		thread->trap_nr		= X86_TRAP_PF;

		memset(&info, 0, sizeof(info));
		info.si_signo		= SIGSEGV;
		info.si_errno		= 0;
		info.si_code		= SEGV_MAPERR;
		info.si_addr		= (void __user *)ptr;

		force_sig_info(SIGSEGV, &info, current);
		return false;
	} else {
		return true;
	}
}

bool emulate_vsyscall(struct pt_regs *regs, unsigned long address)
{
	struct task_struct *tsk;
	unsigned long caller;
	int vsyscall_nr, syscall_nr, tmp;
	int prev_sig_on_uaccess_error;
	long ret;

	/*
	 * No point in checking CS -- the only way to get here is a user mode
	 * trap to a high address, which means that we're in 64-bit user code.
	 */

	WARN_ON_ONCE(address != regs->ip);

	if (vsyscall_mode == NONE) {
		warn_bad_vsyscall(KERN_INFO, regs,
				  "vsyscall attempted with vsyscall=none");
		return false;
	}

	vsyscall_nr = addr_to_vsyscall_nr(address);

	trace_emulate_vsyscall(vsyscall_nr);

	if (vsyscall_nr < 0) {
		warn_bad_vsyscall(KERN_WARNING, regs,
				  "misaligned vsyscall (exploit attempt or buggy program) -- look up the vsyscall kernel parameter if you need a workaround");
		goto sigsegv;
	}

	if (get_user(caller, (unsigned long __user *)regs->sp) != 0) {
		warn_bad_vsyscall(KERN_WARNING, regs,
				  "vsyscall with bad stack (exploit attempt?)");
		goto sigsegv;
	}

	tsk = current;

	/*
	 * Check for access_ok violations and find the syscall nr.
	 *
	 * NULL is a valid user pointer (in the access_ok sense) on 32-bit and
	 * 64-bit, so we don't need to special-case it here.  For all the
	 * vsyscalls, NULL means "don't write anything" not "write it at
	 * address 0".
	 */
	switch (vsyscall_nr) {
	case 0:
		if (!write_ok_or_segv(regs->di, sizeof(struct timeval)) ||
		    !write_ok_or_segv(regs->si, sizeof(struct timezone))) {
			ret = -EFAULT;
			goto check_fault;
		}

		syscall_nr = __NR_gettimeofday;
		break;

	case 1:
		if (!write_ok_or_segv(regs->di, sizeof(time_t))) {
			ret = -EFAULT;
			goto check_fault;
		}

		syscall_nr = __NR_time;
		break;

	case 2:
		if (!write_ok_or_segv(regs->di, sizeof(unsigned)) ||
		    !write_ok_or_segv(regs->si, sizeof(unsigned))) {
			ret = -EFAULT;
			goto check_fault;
		}

		syscall_nr = __NR_getcpu;
		break;
	}

	/*
	 * Handle seccomp.  regs->ip must be the original value.
	 * See seccomp_send_sigsys and Documentation/prctl/seccomp_filter.txt.
	 *
	 * We could optimize the seccomp disabled case, but performance
	 * here doesn't matter.
	 */
	regs->orig_ax = syscall_nr;
	regs->ax = -ENOSYS;
	tmp = secure_computing(syscall_nr);
	if ((!tmp && regs->orig_ax != syscall_nr) || regs->ip != address) {
		warn_bad_vsyscall(KERN_DEBUG, regs,
				  "seccomp tried to change syscall nr or ip");
		do_exit(SIGSYS);
	}
	if (tmp)
		goto do_ret;  /* skip requested */

	/*
	 * With a real vsyscall, page faults cause SIGSEGV.  We want to
	 * preserve that behavior to make writing exploits harder.
	 */
	prev_sig_on_uaccess_error = current_thread_info()->sig_on_uaccess_error;
	current_thread_info()->sig_on_uaccess_error = 1;

	ret = -EFAULT;
	switch (vsyscall_nr) {
	case 0:
		ret = sys_gettimeofday(
			(struct timeval __user *)regs->di,
			(struct timezone __user *)regs->si);
		break;

	case 1:
		ret = sys_time((time_t __user *)regs->di);
		break;

	case 2:
		ret = sys_getcpu((unsigned __user *)regs->di,
				 (unsigned __user *)regs->si,
				 NULL);
		break;
	}

	current_thread_info()->sig_on_uaccess_error = prev_sig_on_uaccess_error;

check_fault:
	if (ret == -EFAULT) {
		/* Bad news -- userspace fed a bad pointer to a vsyscall. */
		warn_bad_vsyscall(KERN_INFO, regs,
				  "vsyscall fault (exploit attempt?)");

		/*
		 * If we failed to generate a signal for any reason,
		 * generate one here.  (This should be impossible.)
		 */
		if (WARN_ON_ONCE(!sigismember(&tsk->pending.signal, SIGBUS) &&
				 !sigismember(&tsk->pending.signal, SIGSEGV)))
			goto sigsegv;

		return true;  /* Don't emulate the ret. */
	}

	regs->ax = ret;

do_ret:
	/* Emulate a ret instruction. */
	regs->ip = caller;
	regs->sp += 8;
	return true;

sigsegv:
	force_sig(SIGSEGV, current);
	return true;
}

/*
 * Assume __initcall executes before all user space. Hopefully kmod
 * doesn't violate that. We'll find out if it does.
 */
static void vsyscall_set_cpu(int cpu)
{
	unsigned long d;
	unsigned long node = 0;
#ifdef CONFIG_NUMA
	node = cpu_to_node(cpu);
#endif
	if (cpu_has(&cpu_data(cpu), X86_FEATURE_RDTSCP))
		write_rdtscp_aux((node << 12) | cpu);

	/*
	 * Store cpu number in limit so that it can be loaded quickly
	 * in user space in vgetcpu. (12 bits for the CPU and 8 bits for the node)
	 */
	d = 0x0f40000000000ULL;
	d |= cpu;
	d |= (node & 0xf) << 12;
	d |= (node >> 4) << 48;

	write_gdt_entry(get_cpu_gdt_table(cpu), GDT_ENTRY_PER_CPU, &d, DESCTYPE_S);
}

static void cpu_vsyscall_init(void *arg)
{
	/* preemption should be already off */
	vsyscall_set_cpu(raw_smp_processor_id());
}

static int
cpu_vsyscall_notifier(struct notifier_block *n, unsigned long action, void *arg)
{
	long cpu = (long)arg;

	if (action == CPU_ONLINE || action == CPU_ONLINE_FROZEN)
		smp_call_function_single(cpu, cpu_vsyscall_init, NULL, 1);

	return NOTIFY_DONE;
}

void __init map_vsyscall(void)
{
	extern char __vsyscall_page;
	unsigned long physaddr_vsyscall = __pa_symbol(&__vsyscall_page);

	__set_fixmap(VSYSCALL_PAGE, physaddr_vsyscall,
		     vsyscall_mode == NATIVE
		     ? PAGE_KERNEL_VSYSCALL
		     : PAGE_KERNEL_VVAR);
	BUILD_BUG_ON((unsigned long)__fix_to_virt(VSYSCALL_PAGE) !=
		     (unsigned long)VSYSCALL_ADDR);
}

static int __init vsyscall_init(void)
{
	cpu_notifier_register_begin();

	on_each_cpu(cpu_vsyscall_init, NULL, 1);
	/* notifier priority > KVM */
	__hotcpu_notifier(cpu_vsyscall_notifier, 30);

	cpu_notifier_register_done();

	return 0;
}
__initcall(vsyscall_init);