summaryrefslogtreecommitdiffstats
path: root/mm/secretmem.c
blob: 3f715409979588ee58374cb14a464d4b6c26280e (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
// SPDX-License-Identifier: GPL-2.0
/*
 * Copyright IBM Corporation, 2021
 *
 * Author: Mike Rapoport <rppt@linux.ibm.com>
 */

#include <linux/mm.h>
#include <linux/fs.h>
#include <linux/swap.h>
#include <linux/mount.h>
#include <linux/memfd.h>
#include <linux/bitops.h>
#include <linux/printk.h>
#include <linux/pagemap.h>
#include <linux/syscalls.h>
#include <linux/pseudo_fs.h>
#include <linux/secretmem.h>
#include <linux/set_memory.h>
#include <linux/sched/signal.h>

#include <uapi/linux/magic.h>

#include <asm/tlbflush.h>

#include "internal.h"

#undef pr_fmt
#define pr_fmt(fmt) "secretmem: " fmt

/*
 * Define mode and flag masks to allow validation of the system call
 * parameters.
 */
#define SECRETMEM_MODE_MASK	(0x0)
#define SECRETMEM_FLAGS_MASK	SECRETMEM_MODE_MASK

static bool secretmem_enable __ro_after_init;
module_param_named(enable, secretmem_enable, bool, 0400);
MODULE_PARM_DESC(secretmem_enable,
		 "Enable secretmem and memfd_secret(2) system call");

static atomic_t secretmem_users;

bool secretmem_active(void)
{
	return !!atomic_read(&secretmem_users);
}

static vm_fault_t secretmem_fault(struct vm_fault *vmf)
{
	struct address_space *mapping = vmf->vma->vm_file->f_mapping;
	struct inode *inode = file_inode(vmf->vma->vm_file);
	pgoff_t offset = vmf->pgoff;
	gfp_t gfp = vmf->gfp_mask;
	unsigned long addr;
	struct page *page;
	vm_fault_t ret;
	int err;

	if (((loff_t)vmf->pgoff << PAGE_SHIFT) >= i_size_read(inode))
		return vmf_error(-EINVAL);

	filemap_invalidate_lock_shared(mapping);

retry:
	page = find_lock_page(mapping, offset);
	if (!page) {
		page = alloc_page(gfp | __GFP_ZERO);
		if (!page) {
			ret = VM_FAULT_OOM;
			goto out;
		}

		err = set_direct_map_invalid_noflush(page);
		if (err) {
			put_page(page);
			ret = vmf_error(err);
			goto out;
		}

		__SetPageUptodate(page);
		err = add_to_page_cache_lru(page, mapping, offset, gfp);
		if (unlikely(err)) {
			put_page(page);
			/*
			 * If a split of large page was required, it
			 * already happened when we marked the page invalid
			 * which guarantees that this call won't fail
			 */
			set_direct_map_default_noflush(page);
			if (err == -EEXIST)
				goto retry;

			ret = vmf_error(err);
			goto out;
		}

		addr = (unsigned long)page_address(page);
		flush_tlb_kernel_range(addr, addr + PAGE_SIZE);
	}

	vmf->page = page;
	ret = VM_FAULT_LOCKED;

out:
	filemap_invalidate_unlock_shared(mapping);
	return ret;
}

static const struct vm_operations_struct secretmem_vm_ops = {
	.fault = secretmem_fault,
};

static int secretmem_release(struct inode *inode, struct file *file)
{
	atomic_dec(&secretmem_users);
	return 0;
}

static int secretmem_mmap(struct file *file, struct vm_area_struct *vma)
{
	unsigned long len = vma->vm_end - vma->vm_start;

	if ((vma->vm_flags & (VM_SHARED | VM_MAYSHARE)) == 0)
		return -EINVAL;

	if (mlock_future_check(vma->vm_mm, vma->vm_flags | VM_LOCKED, len))
		return -EAGAIN;

	vma->vm_flags |= VM_LOCKED | VM_DONTDUMP;
	vma->vm_ops = &secretmem_vm_ops;

	return 0;
}

bool vma_is_secretmem(struct vm_area_struct *vma)
{
	return vma->vm_ops == &secretmem_vm_ops;
}

static const struct file_operations secretmem_fops = {
	.release	= secretmem_release,
	.mmap		= secretmem_mmap,
};

static int secretmem_migrate_folio(struct address_space *mapping,
		struct folio *dst, struct folio *src, enum migrate_mode mode)
{
	return -EBUSY;
}

static void secretmem_free_folio(struct folio *folio)
{
	set_direct_map_default_noflush(&folio->page);
	folio_zero_segment(folio, 0, folio_size(folio));
}

const struct address_space_operations secretmem_aops = {
	.dirty_folio	= noop_dirty_folio,
	.free_folio	= secretmem_free_folio,
	.migrate_folio	= secretmem_migrate_folio,
};

static int secretmem_setattr(struct user_namespace *mnt_userns,
			     struct dentry *dentry, struct iattr *iattr)
{
	struct inode *inode = d_inode(dentry);
	struct address_space *mapping = inode->i_mapping;
	unsigned int ia_valid = iattr->ia_valid;
	int ret;

	filemap_invalidate_lock(mapping);

	if ((ia_valid & ATTR_SIZE) && inode->i_size)
		ret = -EINVAL;
	else
		ret = simple_setattr(mnt_userns, dentry, iattr);

	filemap_invalidate_unlock(mapping);

	return ret;
}

static const struct inode_operations secretmem_iops = {
	.setattr = secretmem_setattr,
};

static struct vfsmount *secretmem_mnt;

static struct file *secretmem_file_create(unsigned long flags)
{
	struct file *file = ERR_PTR(-ENOMEM);
	struct inode *inode;
	const char *anon_name = "[secretmem]";
	const struct qstr qname = QSTR_INIT(anon_name, strlen(anon_name));
	int err;

	inode = alloc_anon_inode(secretmem_mnt->mnt_sb);
	if (IS_ERR(inode))
		return ERR_CAST(inode);

	err = security_inode_init_security_anon(inode, &qname, NULL);
	if (err) {
		file = ERR_PTR(err);
		goto err_free_inode;
	}

	file = alloc_file_pseudo(inode, secretmem_mnt, "secretmem",
				 O_RDWR, &secretmem_fops);
	if (IS_ERR(file))
		goto err_free_inode;

	mapping_set_gfp_mask(inode->i_mapping, GFP_HIGHUSER);
	mapping_set_unevictable(inode->i_mapping);

	inode->i_op = &secretmem_iops;
	inode->i_mapping->a_ops = &secretmem_aops;

	/* pretend we are a normal file with zero size */
	inode->i_mode |= S_IFREG;
	inode->i_size = 0;

	return file;

err_free_inode:
	iput(inode);
	return file;
}

SYSCALL_DEFINE1(memfd_secret, unsigned int, flags)
{
	struct file *file;
	int fd, err;

	/* make sure local flags do not confict with global fcntl.h */
	BUILD_BUG_ON(SECRETMEM_FLAGS_MASK & O_CLOEXEC);

	if (!secretmem_enable)
		return -ENOSYS;

	if (flags & ~(SECRETMEM_FLAGS_MASK | O_CLOEXEC))
		return -EINVAL;
	if (atomic_read(&secretmem_users) < 0)
		return -ENFILE;

	fd = get_unused_fd_flags(flags & O_CLOEXEC);
	if (fd < 0)
		return fd;

	file = secretmem_file_create(flags);
	if (IS_ERR(file)) {
		err = PTR_ERR(file);
		goto err_put_fd;
	}

	file->f_flags |= O_LARGEFILE;

	atomic_inc(&secretmem_users);
	fd_install(fd, file);
	return fd;

err_put_fd:
	put_unused_fd(fd);
	return err;
}

static int secretmem_init_fs_context(struct fs_context *fc)
{
	return init_pseudo(fc, SECRETMEM_MAGIC) ? 0 : -ENOMEM;
}

static struct file_system_type secretmem_fs = {
	.name		= "secretmem",
	.init_fs_context = secretmem_init_fs_context,
	.kill_sb	= kill_anon_super,
};

static int secretmem_init(void)
{
	int ret = 0;

	if (!secretmem_enable)
		return ret;

	secretmem_mnt = kern_mount(&secretmem_fs);
	if (IS_ERR(secretmem_mnt))
		return PTR_ERR(secretmem_mnt);

	/* prevent secretmem mappings from ever getting PROT_EXEC */
	secretmem_mnt->mnt_flags |= MNT_NOEXEC;

	return ret;
}
fs_initcall(secretmem_init);