summaryrefslogtreecommitdiffstats
path: root/arch/s390/kernel/uv.c
blob: c296e5c8dbf97ab4fd793dd7a10c9618392034fe (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
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
// SPDX-License-Identifier: GPL-2.0
/*
 * Common Ultravisor functions and initialization
 *
 * Copyright IBM Corp. 2019, 2020
 */
#define KMSG_COMPONENT "prot_virt"
#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt

#include <linux/kernel.h>
#include <linux/types.h>
#include <linux/sizes.h>
#include <linux/bitmap.h>
#include <linux/memblock.h>
#include <linux/pagemap.h>
#include <linux/swap.h>
#include <asm/facility.h>
#include <asm/sections.h>
#include <asm/uv.h>

/* the bootdata_preserved fields come from ones in arch/s390/boot/uv.c */
#ifdef CONFIG_PROTECTED_VIRTUALIZATION_GUEST
int __bootdata_preserved(prot_virt_guest);
#endif

struct uv_info __bootdata_preserved(uv_info);

#if IS_ENABLED(CONFIG_KVM)
int prot_virt_host;
EXPORT_SYMBOL(prot_virt_host);
EXPORT_SYMBOL(uv_info);

static int __init prot_virt_setup(char *val)
{
	bool enabled;
	int rc;

	rc = kstrtobool(val, &enabled);
	if (!rc && enabled)
		prot_virt_host = 1;

	if (is_prot_virt_guest() && prot_virt_host) {
		prot_virt_host = 0;
		pr_warn("Protected virtualization not available in protected guests.");
	}

	if (prot_virt_host && !test_facility(158)) {
		prot_virt_host = 0;
		pr_warn("Protected virtualization not supported by the hardware.");
	}

	return rc;
}
early_param("prot_virt", prot_virt_setup);

static int __init uv_init(unsigned long stor_base, unsigned long stor_len)
{
	struct uv_cb_init uvcb = {
		.header.cmd = UVC_CMD_INIT_UV,
		.header.len = sizeof(uvcb),
		.stor_origin = stor_base,
		.stor_len = stor_len,
	};

	if (uv_call(0, (uint64_t)&uvcb)) {
		pr_err("Ultravisor init failed with rc: 0x%x rrc: 0%x\n",
		       uvcb.header.rc, uvcb.header.rrc);
		return -1;
	}
	return 0;
}

void __init setup_uv(void)
{
	unsigned long uv_stor_base;

	uv_stor_base = (unsigned long)memblock_alloc_try_nid(
		uv_info.uv_base_stor_len, SZ_1M, SZ_2G,
		MEMBLOCK_ALLOC_ACCESSIBLE, NUMA_NO_NODE);
	if (!uv_stor_base) {
		pr_warn("Failed to reserve %lu bytes for ultravisor base storage\n",
			uv_info.uv_base_stor_len);
		goto fail;
	}

	if (uv_init(uv_stor_base, uv_info.uv_base_stor_len)) {
		memblock_free(uv_stor_base, uv_info.uv_base_stor_len);
		goto fail;
	}

	pr_info("Reserving %luMB as ultravisor base storage\n",
		uv_info.uv_base_stor_len >> 20);
	return;
fail:
	pr_info("Disabling support for protected virtualization");
	prot_virt_host = 0;
}

void adjust_to_uv_max(unsigned long *vmax)
{
	*vmax = min_t(unsigned long, *vmax, uv_info.max_sec_stor_addr);
}

/*
 * Requests the Ultravisor to pin the page in the shared state. This will
 * cause an intercept when the guest attempts to unshare the pinned page.
 */
static int uv_pin_shared(unsigned long paddr)
{
	struct uv_cb_cfs uvcb = {
		.header.cmd = UVC_CMD_PIN_PAGE_SHARED,
		.header.len = sizeof(uvcb),
		.paddr = paddr,
	};

	if (uv_call(0, (u64)&uvcb))
		return -EINVAL;
	return 0;
}

/*
 * Requests the Ultravisor to encrypt a guest page and make it
 * accessible to the host for paging (export).
 *
 * @paddr: Absolute host address of page to be exported
 */
int uv_convert_from_secure(unsigned long paddr)
{
	struct uv_cb_cfs uvcb = {
		.header.cmd = UVC_CMD_CONV_FROM_SEC_STOR,
		.header.len = sizeof(uvcb),
		.paddr = paddr
	};

	if (uv_call(0, (u64)&uvcb))
		return -EINVAL;
	return 0;
}

/*
 * Calculate the expected ref_count for a page that would otherwise have no
 * further pins. This was cribbed from similar functions in other places in
 * the kernel, but with some slight modifications. We know that a secure
 * page can not be a huge page for example.
 */
static int expected_page_refs(struct page *page)
{
	int res;

	res = page_mapcount(page);
	if (PageSwapCache(page)) {
		res++;
	} else if (page_mapping(page)) {
		res++;
		if (page_has_private(page))
			res++;
	}
	return res;
}

static int make_secure_pte(pte_t *ptep, unsigned long addr,
			   struct page *exp_page, struct uv_cb_header *uvcb)
{
	pte_t entry = READ_ONCE(*ptep);
	struct page *page;
	int expected, rc = 0;

	if (!pte_present(entry))
		return -ENXIO;
	if (pte_val(entry) & _PAGE_INVALID)
		return -ENXIO;

	page = pte_page(entry);
	if (page != exp_page)
		return -ENXIO;
	if (PageWriteback(page))
		return -EAGAIN;
	expected = expected_page_refs(page);
	if (!page_ref_freeze(page, expected))
		return -EBUSY;
	set_bit(PG_arch_1, &page->flags);
	rc = uv_call(0, (u64)uvcb);
	page_ref_unfreeze(page, expected);
	/* Return -ENXIO if the page was not mapped, -EINVAL otherwise */
	if (rc)
		rc = uvcb->rc == 0x10a ? -ENXIO : -EINVAL;
	return rc;
}

/*
 * Requests the Ultravisor to make a page accessible to a guest.
 * If it's brought in the first time, it will be cleared. If
 * it has been exported before, it will be decrypted and integrity
 * checked.
 */
int gmap_make_secure(struct gmap *gmap, unsigned long gaddr, void *uvcb)
{
	struct vm_area_struct *vma;
	bool local_drain = false;
	spinlock_t *ptelock;
	unsigned long uaddr;
	struct page *page;
	pte_t *ptep;
	int rc;

again:
	rc = -EFAULT;
	mmap_read_lock(gmap->mm);

	uaddr = __gmap_translate(gmap, gaddr);
	if (IS_ERR_VALUE(uaddr))
		goto out;
	vma = find_vma(gmap->mm, uaddr);
	if (!vma)
		goto out;
	/*
	 * Secure pages cannot be huge and userspace should not combine both.
	 * In case userspace does it anyway this will result in an -EFAULT for
	 * the unpack. The guest is thus never reaching secure mode. If
	 * userspace is playing dirty tricky with mapping huge pages later
	 * on this will result in a segmentation fault.
	 */
	if (is_vm_hugetlb_page(vma))
		goto out;

	rc = -ENXIO;
	page = follow_page(vma, uaddr, FOLL_WRITE);
	if (IS_ERR_OR_NULL(page))
		goto out;

	lock_page(page);
	ptep = get_locked_pte(gmap->mm, uaddr, &ptelock);
	rc = make_secure_pte(ptep, uaddr, page, uvcb);
	pte_unmap_unlock(ptep, ptelock);
	unlock_page(page);
out:
	mmap_read_unlock(gmap->mm);

	if (rc == -EAGAIN) {
		wait_on_page_writeback(page);
	} else if (rc == -EBUSY) {
		/*
		 * If we have tried a local drain and the page refcount
		 * still does not match our expected safe value, try with a
		 * system wide drain. This is needed if the pagevecs holding
		 * the page are on a different CPU.
		 */
		if (local_drain) {
			lru_add_drain_all();
			/* We give up here, and let the caller try again */
			return -EAGAIN;
		}
		/*
		 * We are here if the page refcount does not match the
		 * expected safe value. The main culprits are usually
		 * pagevecs. With lru_add_drain() we drain the pagevecs
		 * on the local CPU so that hopefully the refcount will
		 * reach the expected safe value.
		 */
		lru_add_drain();
		local_drain = true;
		/* And now we try again immediately after draining */
		goto again;
	} else if (rc == -ENXIO) {
		if (gmap_fault(gmap, gaddr, FAULT_FLAG_WRITE))
			return -EFAULT;
		return -EAGAIN;
	}
	return rc;
}
EXPORT_SYMBOL_GPL(gmap_make_secure);

int gmap_convert_to_secure(struct gmap *gmap, unsigned long gaddr)
{
	struct uv_cb_cts uvcb = {
		.header.cmd = UVC_CMD_CONV_TO_SEC_STOR,
		.header.len = sizeof(uvcb),
		.guest_handle = gmap->guest_handle,
		.gaddr = gaddr,
	};

	return gmap_make_secure(gmap, gaddr, &uvcb);
}
EXPORT_SYMBOL_GPL(gmap_convert_to_secure);

/*
 * To be called with the page locked or with an extra reference! This will
 * prevent gmap_make_secure from touching the page concurrently. Having 2
 * parallel make_page_accessible is fine, as the UV calls will become a
 * no-op if the page is already exported.
 */
int arch_make_page_accessible(struct page *page)
{
	int rc = 0;

	/* Hugepage cannot be protected, so nothing to do */
	if (PageHuge(page))
		return 0;

	/*
	 * PG_arch_1 is used in 3 places:
	 * 1. for kernel page tables during early boot
	 * 2. for storage keys of huge pages and KVM
	 * 3. As an indication that this page might be secure. This can
	 *    overindicate, e.g. we set the bit before calling
	 *    convert_to_secure.
	 * As secure pages are never huge, all 3 variants can co-exists.
	 */
	if (!test_bit(PG_arch_1, &page->flags))
		return 0;

	rc = uv_pin_shared(page_to_phys(page));
	if (!rc) {
		clear_bit(PG_arch_1, &page->flags);
		return 0;
	}

	rc = uv_convert_from_secure(page_to_phys(page));
	if (!rc) {
		clear_bit(PG_arch_1, &page->flags);
		return 0;
	}

	return rc;
}
EXPORT_SYMBOL_GPL(arch_make_page_accessible);

#endif

#if defined(CONFIG_PROTECTED_VIRTUALIZATION_GUEST) || IS_ENABLED(CONFIG_KVM)
static ssize_t uv_query_facilities(struct kobject *kobj,
				   struct kobj_attribute *attr, char *page)
{
	return scnprintf(page, PAGE_SIZE, "%lx\n%lx\n%lx\n%lx\n",
			uv_info.inst_calls_list[0],
			uv_info.inst_calls_list[1],
			uv_info.inst_calls_list[2],
			uv_info.inst_calls_list[3]);
}

static struct kobj_attribute uv_query_facilities_attr =
	__ATTR(facilities, 0444, uv_query_facilities, NULL);

static ssize_t uv_query_max_guest_cpus(struct kobject *kobj,
				       struct kobj_attribute *attr, char *page)
{
	return scnprintf(page, PAGE_SIZE, "%d\n",
			uv_info.max_guest_cpus);
}

static struct kobj_attribute uv_query_max_guest_cpus_attr =
	__ATTR(max_cpus, 0444, uv_query_max_guest_cpus, NULL);

static ssize_t uv_query_max_guest_vms(struct kobject *kobj,
				      struct kobj_attribute *attr, char *page)
{
	return scnprintf(page, PAGE_SIZE, "%d\n",
			uv_info.max_num_sec_conf);
}

static struct kobj_attribute uv_query_max_guest_vms_attr =
	__ATTR(max_guests, 0444, uv_query_max_guest_vms, NULL);

static ssize_t uv_query_max_guest_addr(struct kobject *kobj,
				       struct kobj_attribute *attr, char *page)
{
	return scnprintf(page, PAGE_SIZE, "%lx\n",
			uv_info.max_sec_stor_addr);
}

static struct kobj_attribute uv_query_max_guest_addr_attr =
	__ATTR(max_address, 0444, uv_query_max_guest_addr, NULL);

static struct attribute *uv_query_attrs[] = {
	&uv_query_facilities_attr.attr,
	&uv_query_max_guest_cpus_attr.attr,
	&uv_query_max_guest_vms_attr.attr,
	&uv_query_max_guest_addr_attr.attr,
	NULL,
};

static struct attribute_group uv_query_attr_group = {
	.attrs = uv_query_attrs,
};

static struct kset *uv_query_kset;
static struct kobject *uv_kobj;

static int __init uv_info_init(void)
{
	int rc = -ENOMEM;

	if (!test_facility(158))
		return 0;

	uv_kobj = kobject_create_and_add("uv", firmware_kobj);
	if (!uv_kobj)
		return -ENOMEM;

	uv_query_kset = kset_create_and_add("query", NULL, uv_kobj);
	if (!uv_query_kset)
		goto out_kobj;

	rc = sysfs_create_group(&uv_query_kset->kobj, &uv_query_attr_group);
	if (!rc)
		return 0;

	kset_unregister(uv_query_kset);
out_kobj:
	kobject_del(uv_kobj);
	kobject_put(uv_kobj);
	return rc;
}
device_initcall(uv_info_init);
#endif