summaryrefslogtreecommitdiffstats
path: root/arch/x86/kernel/ldt.c
blob: a6b5d62f45a737b84124411f56a64fdd869ca4f8 (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
// SPDX-License-Identifier: GPL-2.0
/*
 * Copyright (C) 1992 Krishna Balasubramanian and Linus Torvalds
 * Copyright (C) 1999 Ingo Molnar <mingo@redhat.com>
 * Copyright (C) 2002 Andi Kleen
 *
 * This handles calls from both 32bit and 64bit mode.
 *
 * Lock order:
 *	contex.ldt_usr_sem
 *	  mmap_sem
 *	    context.lock
 */

#include <linux/errno.h>
#include <linux/gfp.h>
#include <linux/sched.h>
#include <linux/string.h>
#include <linux/mm.h>
#include <linux/smp.h>
#include <linux/syscalls.h>
#include <linux/slab.h>
#include <linux/vmalloc.h>
#include <linux/uaccess.h>

#include <asm/ldt.h>
#include <asm/desc.h>
#include <asm/mmu_context.h>
#include <asm/syscalls.h>

static void refresh_ldt_segments(void)
{
#ifdef CONFIG_X86_64
	unsigned short sel;

	/*
	 * Make sure that the cached DS and ES descriptors match the updated
	 * LDT.
	 */
	savesegment(ds, sel);
	if ((sel & SEGMENT_TI_MASK) == SEGMENT_LDT)
		loadsegment(ds, sel);

	savesegment(es, sel);
	if ((sel & SEGMENT_TI_MASK) == SEGMENT_LDT)
		loadsegment(es, sel);
#endif
}

/* context.lock is held by the task which issued the smp function call */
static void flush_ldt(void *__mm)
{
	struct mm_struct *mm = __mm;
	mm_context_t *pc;

	if (this_cpu_read(cpu_tlbstate.loaded_mm) != mm)
		return;

	pc = &mm->context;
	set_ldt(pc->ldt->entries, pc->ldt->nr_entries);

	refresh_ldt_segments();
}

/* The caller must call finalize_ldt_struct on the result. LDT starts zeroed. */
static struct ldt_struct *alloc_ldt_struct(unsigned int num_entries)
{
	struct ldt_struct *new_ldt;
	unsigned int alloc_size;

	if (num_entries > LDT_ENTRIES)
		return NULL;

	new_ldt = kmalloc(sizeof(struct ldt_struct), GFP_KERNEL);
	if (!new_ldt)
		return NULL;

	BUILD_BUG_ON(LDT_ENTRY_SIZE != sizeof(struct desc_struct));
	alloc_size = num_entries * LDT_ENTRY_SIZE;

	/*
	 * Xen is very picky: it requires a page-aligned LDT that has no
	 * trailing nonzero bytes in any page that contains LDT descriptors.
	 * Keep it simple: zero the whole allocation and never allocate less
	 * than PAGE_SIZE.
	 */
	if (alloc_size > PAGE_SIZE)
		new_ldt->entries = vzalloc(alloc_size);
	else
		new_ldt->entries = (void *)get_zeroed_page(GFP_KERNEL);

	if (!new_ldt->entries) {
		kfree(new_ldt);
		return NULL;
	}

	new_ldt->nr_entries = num_entries;
	return new_ldt;
}

/* After calling this, the LDT is immutable. */
static void finalize_ldt_struct(struct ldt_struct *ldt)
{
	paravirt_alloc_ldt(ldt->entries, ldt->nr_entries);
}

static void install_ldt(struct mm_struct *mm, struct ldt_struct *ldt)
{
	mutex_lock(&mm->context.lock);

	/* Synchronizes with READ_ONCE in load_mm_ldt. */
	smp_store_release(&mm->context.ldt, ldt);

	/* Activate the LDT for all CPUs using currents mm. */
	on_each_cpu_mask(mm_cpumask(mm), flush_ldt, mm, true);

	mutex_unlock(&mm->context.lock);
}

static void free_ldt_struct(struct ldt_struct *ldt)
{
	if (likely(!ldt))
		return;

	paravirt_free_ldt(ldt->entries, ldt->nr_entries);
	if (ldt->nr_entries * LDT_ENTRY_SIZE > PAGE_SIZE)
		vfree_atomic(ldt->entries);
	else
		free_page((unsigned long)ldt->entries);
	kfree(ldt);
}

/*
 * Called on fork from arch_dup_mmap(). Just copy the current LDT state,
 * the new task is not running, so nothing can be installed.
 */
int ldt_dup_context(struct mm_struct *old_mm, struct mm_struct *mm)
{
	struct ldt_struct *new_ldt;
	int retval = 0;

	if (!old_mm)
		return 0;

	mutex_lock(&old_mm->context.lock);
	if (!old_mm->context.ldt)
		goto out_unlock;

	new_ldt = alloc_ldt_struct(old_mm->context.ldt->nr_entries);
	if (!new_ldt) {
		retval = -ENOMEM;
		goto out_unlock;
	}

	memcpy(new_ldt->entries, old_mm->context.ldt->entries,
	       new_ldt->nr_entries * LDT_ENTRY_SIZE);
	finalize_ldt_struct(new_ldt);

	mm->context.ldt = new_ldt;

out_unlock:
	mutex_unlock(&old_mm->context.lock);
	return retval;
}

/*
 * No need to lock the MM as we are the last user
 *
 * 64bit: Don't touch the LDT register - we're already in the next thread.
 */
void destroy_context_ldt(struct mm_struct *mm)
{
	free_ldt_struct(mm->context.ldt);
	mm->context.ldt = NULL;
}

static int read_ldt(void __user *ptr, unsigned long bytecount)
{
	struct mm_struct *mm = current->mm;
	unsigned long entries_size;
	int retval;

	down_read(&mm->context.ldt_usr_sem);

	if (!mm->context.ldt) {
		retval = 0;
		goto out_unlock;
	}

	if (bytecount > LDT_ENTRY_SIZE * LDT_ENTRIES)
		bytecount = LDT_ENTRY_SIZE * LDT_ENTRIES;

	entries_size = mm->context.ldt->nr_entries * LDT_ENTRY_SIZE;
	if (entries_size > bytecount)
		entries_size = bytecount;

	if (copy_to_user(ptr, mm->context.ldt->entries, entries_size)) {
		retval = -EFAULT;
		goto out_unlock;
	}

	if (entries_size != bytecount) {
		/* Zero-fill the rest and pretend we read bytecount bytes. */
		if (clear_user(ptr + entries_size, bytecount - entries_size)) {
			retval = -EFAULT;
			goto out_unlock;
		}
	}
	retval = bytecount;

out_unlock:
	up_read(&mm->context.ldt_usr_sem);
	return retval;
}

static int read_default_ldt(void __user *ptr, unsigned long bytecount)
{
	/* CHECKME: Can we use _one_ random number ? */
#ifdef CONFIG_X86_32
	unsigned long size = 5 * sizeof(struct desc_struct);
#else
	unsigned long size = 128;
#endif
	if (bytecount > size)
		bytecount = size;
	if (clear_user(ptr, bytecount))
		return -EFAULT;
	return bytecount;
}

static int write_ldt(void __user *ptr, unsigned long bytecount, int oldmode)
{
	struct mm_struct *mm = current->mm;
	struct ldt_struct *new_ldt, *old_ldt;
	unsigned int old_nr_entries, new_nr_entries;
	struct user_desc ldt_info;
	struct desc_struct ldt;
	int error;

	error = -EINVAL;
	if (bytecount != sizeof(ldt_info))
		goto out;
	error = -EFAULT;
	if (copy_from_user(&ldt_info, ptr, sizeof(ldt_info)))
		goto out;

	error = -EINVAL;
	if (ldt_info.entry_number >= LDT_ENTRIES)
		goto out;
	if (ldt_info.contents == 3) {
		if (oldmode)
			goto out;
		if (ldt_info.seg_not_present == 0)
			goto out;
	}

	if ((oldmode && !ldt_info.base_addr && !ldt_info.limit) ||
	    LDT_empty(&ldt_info)) {
		/* The user wants to clear the entry. */
		memset(&ldt, 0, sizeof(ldt));
	} else {
		if (!IS_ENABLED(CONFIG_X86_16BIT) && !ldt_info.seg_32bit) {
			error = -EINVAL;
			goto out;
		}

		fill_ldt(&ldt, &ldt_info);
		if (oldmode)
			ldt.avl = 0;
	}

	if (down_write_killable(&mm->context.ldt_usr_sem))
		return -EINTR;

	old_ldt       = mm->context.ldt;
	old_nr_entries = old_ldt ? old_ldt->nr_entries : 0;
	new_nr_entries = max(ldt_info.entry_number + 1, old_nr_entries);

	error = -ENOMEM;
	new_ldt = alloc_ldt_struct(new_nr_entries);
	if (!new_ldt)
		goto out_unlock;

	if (old_ldt)
		memcpy(new_ldt->entries, old_ldt->entries, old_nr_entries * LDT_ENTRY_SIZE);

	new_ldt->entries[ldt_info.entry_number] = ldt;
	finalize_ldt_struct(new_ldt);

	install_ldt(mm, new_ldt);
	free_ldt_struct(old_ldt);
	error = 0;

out_unlock:
	up_write(&mm->context.ldt_usr_sem);
out:
	return error;
}

SYSCALL_DEFINE3(modify_ldt, int , func , void __user * , ptr ,
		unsigned long , bytecount)
{
	int ret = -ENOSYS;

	switch (func) {
	case 0:
		ret = read_ldt(ptr, bytecount);
		break;
	case 1:
		ret = write_ldt(ptr, bytecount, 1);
		break;
	case 2:
		ret = read_default_ldt(ptr, bytecount);
		break;
	case 0x11:
		ret = write_ldt(ptr, bytecount, 0);
		break;
	}
	/*
	 * The SYSCALL_DEFINE() macros give us an 'unsigned long'
	 * return type, but tht ABI for sys_modify_ldt() expects
	 * 'int'.  This cast gives us an int-sized value in %rax
	 * for the return code.  The 'unsigned' is necessary so
	 * the compiler does not try to sign-extend the negative
	 * return codes into the high half of the register when
	 * taking the value from int->long.
	 */
	return (unsigned int)ret;
}