1// SPDX-License-Identifier: GPL-2.0
2/*
3 * Copyright (c) 2012-2014 Andy Lutomirski <luto@amacapital.net>
4 *
5 * Based on the original implementation which is:
6 *  Copyright (C) 2001 Andrea Arcangeli <andrea@suse.de> SuSE
7 *  Copyright 2003 Andi Kleen, SuSE Labs.
8 *
9 *  Parts of the original code have been moved to arch/x86/vdso/vma.c
10 *
11 * This file implements vsyscall emulation.  vsyscalls are a legacy ABI:
12 * Userspace can request certain kernel services by calling fixed
13 * addresses.  This concept is problematic:
14 *
15 * - It interferes with ASLR.
16 * - It's awkward to write code that lives in kernel addresses but is
17 *   callable by userspace at fixed addresses.
18 * - The whole concept is impossible for 32-bit compat userspace.
19 * - UML cannot easily virtualize a vsyscall.
20 *
21 * As of mid-2014, I believe that there is no new userspace code that
22 * will use a vsyscall if the vDSO is present.  I hope that there will
23 * soon be no new userspace code that will ever use a vsyscall.
24 *
25 * The code in this file emulates vsyscalls when notified of a page
26 * fault to a vsyscall address.
27 */
28
29#include <linux/kernel.h>
30#include <linux/timer.h>
31#include <linux/sched/signal.h>
32#include <linux/mm_types.h>
33#include <linux/syscalls.h>
34#include <linux/ratelimit.h>
35
36#include <asm/vsyscall.h>
37#include <asm/unistd.h>
38#include <asm/fixmap.h>
39#include <asm/traps.h>
40#include <asm/paravirt.h>
41
42#define CREATE_TRACE_POINTS
43#include "vsyscall_trace.h"
44
45static enum { EMULATE, XONLY, NONE } vsyscall_mode __ro_after_init =
46#ifdef CONFIG_LEGACY_VSYSCALL_NONE
47	NONE;
48#elif defined(CONFIG_LEGACY_VSYSCALL_XONLY)
49	XONLY;
50#else
51	EMULATE;
52#endif
53
54static int __init vsyscall_setup(char *str)
55{
56	if (str) {
57		if (!strcmp("emulate", str))
58			vsyscall_mode = EMULATE;
59		else if (!strcmp("xonly", str))
60			vsyscall_mode = XONLY;
61		else if (!strcmp("none", str))
62			vsyscall_mode = NONE;
63		else
64			return -EINVAL;
65
66		return 0;
67	}
68
69	return -EINVAL;
70}
71early_param("vsyscall", vsyscall_setup);
72
73static void warn_bad_vsyscall(const char *level, struct pt_regs *regs,
74			      const char *message)
75{
76	if (!show_unhandled_signals)
77		return;
78
79	printk_ratelimited("%s%s[%d] %s ip:%lx cs:%lx sp:%lx ax:%lx si:%lx di:%lx\n",
80			   level, current->comm, task_pid_nr(current),
81			   message, regs->ip, regs->cs,
82			   regs->sp, regs->ax, regs->si, regs->di);
83}
84
85static int addr_to_vsyscall_nr(unsigned long addr)
86{
87	int nr;
88
89	if ((addr & ~0xC00UL) != VSYSCALL_ADDR)
90		return -EINVAL;
91
92	nr = (addr & 0xC00UL) >> 10;
93	if (nr >= 3)
94		return -EINVAL;
95
96	return nr;
97}
98
99static bool write_ok_or_segv(unsigned long ptr, size_t size)
100{
101	/*
102	 * XXX: if access_ok, get_user, and put_user handled
103	 * sig_on_uaccess_err, this could go away.
104	 */
105
106	if (!access_ok((void __user *)ptr, size)) {
107		struct thread_struct *thread = &current->thread;
108
109		thread->error_code	= X86_PF_USER | X86_PF_WRITE;
110		thread->cr2		= ptr;
111		thread->trap_nr		= X86_TRAP_PF;
112
113		force_sig_fault(SIGSEGV, SEGV_MAPERR, (void __user *)ptr);
114		return false;
115	} else {
116		return true;
117	}
118}
119
120bool emulate_vsyscall(unsigned long error_code,
121		      struct pt_regs *regs, unsigned long address)
122{
123	struct task_struct *tsk;
124	unsigned long caller;
125	int vsyscall_nr, syscall_nr, tmp;
126	int prev_sig_on_uaccess_err;
127	long ret;
128	unsigned long orig_dx;
129
130	/* Write faults or kernel-privilege faults never get fixed up. */
131	if ((error_code & (X86_PF_WRITE | X86_PF_USER)) != X86_PF_USER)
132		return false;
133
134	if (!(error_code & X86_PF_INSTR)) {
135		/* Failed vsyscall read */
136		if (vsyscall_mode == EMULATE)
137			return false;
138
139		/*
140		 * User code tried and failed to read the vsyscall page.
141		 */
142		warn_bad_vsyscall(KERN_INFO, regs, "vsyscall read attempt denied -- look up the vsyscall kernel parameter if you need a workaround");
143		return false;
144	}
145
146	/*
147	 * No point in checking CS -- the only way to get here is a user mode
148	 * trap to a high address, which means that we're in 64-bit user code.
149	 */
150
151	WARN_ON_ONCE(address != regs->ip);
152
153	if (vsyscall_mode == NONE) {
154		warn_bad_vsyscall(KERN_INFO, regs,
155				  "vsyscall attempted with vsyscall=none");
156		return false;
157	}
158
159	vsyscall_nr = addr_to_vsyscall_nr(address);
160
161	trace_emulate_vsyscall(vsyscall_nr);
162
163	if (vsyscall_nr < 0) {
164		warn_bad_vsyscall(KERN_WARNING, regs,
165				  "misaligned vsyscall (exploit attempt or buggy program) -- look up the vsyscall kernel parameter if you need a workaround");
166		goto sigsegv;
167	}
168
169	if (get_user(caller, (unsigned long __user *)regs->sp) != 0) {
170		warn_bad_vsyscall(KERN_WARNING, regs,
171				  "vsyscall with bad stack (exploit attempt?)");
172		goto sigsegv;
173	}
174
175	tsk = current;
176
177	/*
178	 * Check for access_ok violations and find the syscall nr.
179	 *
180	 * NULL is a valid user pointer (in the access_ok sense) on 32-bit and
181	 * 64-bit, so we don't need to special-case it here.  For all the
182	 * vsyscalls, NULL means "don't write anything" not "write it at
183	 * address 0".
184	 */
185	switch (vsyscall_nr) {
186	case 0:
187		if (!write_ok_or_segv(regs->di, sizeof(struct __kernel_old_timeval)) ||
188		    !write_ok_or_segv(regs->si, sizeof(struct timezone))) {
189			ret = -EFAULT;
190			goto check_fault;
191		}
192
193		syscall_nr = __NR_gettimeofday;
194		break;
195
196	case 1:
197		if (!write_ok_or_segv(regs->di, sizeof(__kernel_old_time_t))) {
198			ret = -EFAULT;
199			goto check_fault;
200		}
201
202		syscall_nr = __NR_time;
203		break;
204
205	case 2:
206		if (!write_ok_or_segv(regs->di, sizeof(unsigned)) ||
207		    !write_ok_or_segv(regs->si, sizeof(unsigned))) {
208			ret = -EFAULT;
209			goto check_fault;
210		}
211
212		syscall_nr = __NR_getcpu;
213		break;
214	}
215
216	/*
217	 * Handle seccomp.  regs->ip must be the original value.
218	 * See seccomp_send_sigsys and Documentation/userspace-api/seccomp_filter.rst.
219	 *
220	 * We could optimize the seccomp disabled case, but performance
221	 * here doesn't matter.
222	 */
223	regs->orig_ax = syscall_nr;
224	regs->ax = -ENOSYS;
225	tmp = secure_computing();
226	if ((!tmp && regs->orig_ax != syscall_nr) || regs->ip != address) {
227		warn_bad_vsyscall(KERN_DEBUG, regs,
228				  "seccomp tried to change syscall nr or ip");
229		do_exit(SIGSYS);
230	}
231	regs->orig_ax = -1;
232	if (tmp)
233		goto do_ret;  /* skip requested */
234
235	/*
236	 * With a real vsyscall, page faults cause SIGSEGV.  We want to
237	 * preserve that behavior to make writing exploits harder.
238	 */
239	prev_sig_on_uaccess_err = current->thread.sig_on_uaccess_err;
240	current->thread.sig_on_uaccess_err = 1;
241
242	ret = -EFAULT;
243	switch (vsyscall_nr) {
244	case 0:
245		/* this decodes regs->di and regs->si on its own */
246		ret = __x64_sys_gettimeofday(regs);
247		break;
248
249	case 1:
250		/* this decodes regs->di on its own */
251		ret = __x64_sys_time(regs);
252		break;
253
254	case 2:
255		/* while we could clobber regs->dx, we didn't in the past... */
256		orig_dx = regs->dx;
257		regs->dx = 0;
258		/* this decodes regs->di, regs->si and regs->dx on its own */
259		ret = __x64_sys_getcpu(regs);
260		regs->dx = orig_dx;
261		break;
262	}
263
264	current->thread.sig_on_uaccess_err = prev_sig_on_uaccess_err;
265
266check_fault:
267	if (ret == -EFAULT) {
268		/* Bad news -- userspace fed a bad pointer to a vsyscall. */
269		warn_bad_vsyscall(KERN_INFO, regs,
270				  "vsyscall fault (exploit attempt?)");
271
272		/*
273		 * If we failed to generate a signal for any reason,
274		 * generate one here.  (This should be impossible.)
275		 */
276		if (WARN_ON_ONCE(!sigismember(&tsk->pending.signal, SIGBUS) &&
277				 !sigismember(&tsk->pending.signal, SIGSEGV)))
278			goto sigsegv;
279
280		return true;  /* Don't emulate the ret. */
281	}
282
283	regs->ax = ret;
284
285do_ret:
286	/* Emulate a ret instruction. */
287	regs->ip = caller;
288	regs->sp += 8;
289	return true;
290
291sigsegv:
292	force_sig(SIGSEGV);
293	return true;
294}
295
296/*
297 * A pseudo VMA to allow ptrace access for the vsyscall page.  This only
298 * covers the 64bit vsyscall page now. 32bit has a real VMA now and does
299 * not need special handling anymore:
300 */
301static const char *gate_vma_name(struct vm_area_struct *vma)
302{
303	return "[vsyscall]";
304}
305static const struct vm_operations_struct gate_vma_ops = {
306	.name = gate_vma_name,
307};
308static struct vm_area_struct gate_vma __ro_after_init = {
309	.vm_start	= VSYSCALL_ADDR,
310	.vm_end		= VSYSCALL_ADDR + PAGE_SIZE,
311	.vm_page_prot	= PAGE_READONLY_EXEC,
312	.vm_flags	= VM_READ | VM_EXEC,
313	.vm_ops		= &gate_vma_ops,
314};
315
316struct vm_area_struct *get_gate_vma(struct mm_struct *mm)
317{
318#ifdef CONFIG_COMPAT
319	if (!mm || mm->context.ia32_compat)
320		return NULL;
321#endif
322	if (vsyscall_mode == NONE)
323		return NULL;
324	return &gate_vma;
325}
326
327int in_gate_area(struct mm_struct *mm, unsigned long addr)
328{
329	struct vm_area_struct *vma = get_gate_vma(mm);
330
331	if (!vma)
332		return 0;
333
334	return (addr >= vma->vm_start) && (addr < vma->vm_end);
335}
336
337/*
338 * Use this when you have no reliable mm, typically from interrupt
339 * context. It is less reliable than using a task's mm and may give
340 * false positives.
341 */
342int in_gate_area_no_mm(unsigned long addr)
343{
344	return vsyscall_mode != NONE && (addr & PAGE_MASK) == VSYSCALL_ADDR;
345}
346
347/*
348 * The VSYSCALL page is the only user-accessible page in the kernel address
349 * range.  Normally, the kernel page tables can have _PAGE_USER clear, but
350 * the tables covering VSYSCALL_ADDR need _PAGE_USER set if vsyscalls
351 * are enabled.
352 *
353 * Some day we may create a "minimal" vsyscall mode in which we emulate
354 * vsyscalls but leave the page not present.  If so, we skip calling
355 * this.
356 */
357void __init set_vsyscall_pgtable_user_bits(pgd_t *root)
358{
359	pgd_t *pgd;
360	p4d_t *p4d;
361	pud_t *pud;
362	pmd_t *pmd;
363
364	pgd = pgd_offset_pgd(root, VSYSCALL_ADDR);
365	set_pgd(pgd, __pgd(pgd_val(*pgd) | _PAGE_USER));
366	p4d = p4d_offset(pgd, VSYSCALL_ADDR);
367#if CONFIG_PGTABLE_LEVELS >= 5
368	set_p4d(p4d, __p4d(p4d_val(*p4d) | _PAGE_USER));
369#endif
370	pud = pud_offset(p4d, VSYSCALL_ADDR);
371	set_pud(pud, __pud(pud_val(*pud) | _PAGE_USER));
372	pmd = pmd_offset(pud, VSYSCALL_ADDR);
373	set_pmd(pmd, __pmd(pmd_val(*pmd) | _PAGE_USER));
374}
375
376void __init map_vsyscall(void)
377{
378	extern char __vsyscall_page;
379	unsigned long physaddr_vsyscall = __pa_symbol(&__vsyscall_page);
380
381	/*
382	 * For full emulation, the page needs to exist for real.  In
383	 * execute-only mode, there is no PTE at all backing the vsyscall
384	 * page.
385	 */
386	if (vsyscall_mode == EMULATE) {
387		__set_fixmap(VSYSCALL_PAGE, physaddr_vsyscall,
388			     PAGE_KERNEL_VVAR);
389		set_vsyscall_pgtable_user_bits(swapper_pg_dir);
390	}
391
392	if (vsyscall_mode == XONLY)
393		gate_vma.vm_flags = VM_EXEC;
394
395	BUILD_BUG_ON((unsigned long)__fix_to_virt(VSYSCALL_PAGE) !=
396		     (unsigned long)VSYSCALL_ADDR);
397}
398