Free Electrons

Embedded Linux Experts

  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
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
/*
 * virtio for kvm on s390
 *
 * Copyright IBM Corp. 2008
 *
 * This program is free software; you can redistribute it and/or modify
 * it under the terms of the GNU General Public License (version 2 only)
 * as published by the Free Software Foundation.
 *
 *    Author(s): Christian Borntraeger <borntraeger@de.ibm.com>
 */

#include <linux/kernel_stat.h>
#include <linux/init.h>
#include <linux/bootmem.h>
#include <linux/err.h>
#include <linux/virtio.h>
#include <linux/virtio_config.h>
#include <linux/slab.h>
#include <linux/virtio_console.h>
#include <linux/interrupt.h>
#include <linux/virtio_ring.h>
#include <linux/export.h>
#include <linux/pfn.h>
#include <asm/io.h>
#include <asm/kvm_para.h>
#include <asm/kvm_virtio.h>
#include <asm/sclp.h>
#include <asm/setup.h>
#include <asm/irq.h>

#define VIRTIO_SUBCODE_64 0x0D00

/*
 * The pointer to our (page) of device descriptions.
 */
static void *kvm_devices;
static struct work_struct hotplug_work;

struct kvm_device {
	struct virtio_device vdev;
	struct kvm_device_desc *desc;
};

#define to_kvmdev(vd) container_of(vd, struct kvm_device, vdev)

/*
 * memory layout:
 * - kvm_device_descriptor
 *        struct kvm_device_desc
 * - configuration
 *        struct kvm_vqconfig
 * - feature bits
 * - config space
 */
static struct kvm_vqconfig *kvm_vq_config(const struct kvm_device_desc *desc)
{
	return (struct kvm_vqconfig *)(desc + 1);
}

static u8 *kvm_vq_features(const struct kvm_device_desc *desc)
{
	return (u8 *)(kvm_vq_config(desc) + desc->num_vq);
}

static u8 *kvm_vq_configspace(const struct kvm_device_desc *desc)
{
	return kvm_vq_features(desc) + desc->feature_len * 2;
}

/*
 * The total size of the config page used by this device (incl. desc)
 */
static unsigned desc_size(const struct kvm_device_desc *desc)
{
	return sizeof(*desc)
		+ desc->num_vq * sizeof(struct kvm_vqconfig)
		+ desc->feature_len * 2
		+ desc->config_len;
}

/* This gets the device's feature bits. */
static u64 kvm_get_features(struct virtio_device *vdev)
{
	unsigned int i;
	u32 features = 0;
	struct kvm_device_desc *desc = to_kvmdev(vdev)->desc;
	u8 *in_features = kvm_vq_features(desc);

	for (i = 0; i < min(desc->feature_len * 8, 32); i++)
		if (in_features[i / 8] & (1 << (i % 8)))
			features |= (1 << i);
	return features;
}

static int kvm_finalize_features(struct virtio_device *vdev)
{
	unsigned int i, bits;
	struct kvm_device_desc *desc = to_kvmdev(vdev)->desc;
	/* Second half of bitmap is features we accept. */
	u8 *out_features = kvm_vq_features(desc) + desc->feature_len;

	/* Give virtio_ring a chance to accept features. */
	vring_transport_features(vdev);

	/* Make sure we don't have any features > 32 bits! */
	BUG_ON((u32)vdev->features != vdev->features);

	memset(out_features, 0, desc->feature_len);
	bits = min_t(unsigned, desc->feature_len, sizeof(vdev->features)) * 8;
	for (i = 0; i < bits; i++) {
		if (__virtio_test_bit(vdev, i))
			out_features[i / 8] |= (1 << (i % 8));
	}

	return 0;
}

/*
 * Reading and writing elements in config space
 */
static void kvm_get(struct virtio_device *vdev, unsigned int offset,
		   void *buf, unsigned len)
{
	struct kvm_device_desc *desc = to_kvmdev(vdev)->desc;

	BUG_ON(offset + len > desc->config_len);
	memcpy(buf, kvm_vq_configspace(desc) + offset, len);
}

static void kvm_set(struct virtio_device *vdev, unsigned int offset,
		   const void *buf, unsigned len)
{
	struct kvm_device_desc *desc = to_kvmdev(vdev)->desc;

	BUG_ON(offset + len > desc->config_len);
	memcpy(kvm_vq_configspace(desc) + offset, buf, len);
}

/*
 * The operations to get and set the status word just access
 * the status field of the device descriptor. set_status will also
 * make a hypercall to the host, to tell about status changes
 */
static u8 kvm_get_status(struct virtio_device *vdev)
{
	return to_kvmdev(vdev)->desc->status;
}

static void kvm_set_status(struct virtio_device *vdev, u8 status)
{
	BUG_ON(!status);
	to_kvmdev(vdev)->desc->status = status;
	kvm_hypercall1(KVM_S390_VIRTIO_SET_STATUS,
		       (unsigned long) to_kvmdev(vdev)->desc);
}

/*
 * To reset the device, we use the KVM_VIRTIO_RESET hypercall, using the
 * descriptor address. The Host will zero the status and all the
 * features.
 */
static void kvm_reset(struct virtio_device *vdev)
{
	kvm_hypercall1(KVM_S390_VIRTIO_RESET,
		       (unsigned long) to_kvmdev(vdev)->desc);
}

/*
 * When the virtio_ring code wants to notify the Host, it calls us here and we
 * make a hypercall.  We hand the address  of the virtqueue so the Host
 * knows which virtqueue we're talking about.
 */
static bool kvm_notify(struct virtqueue *vq)
{
	long rc;
	struct kvm_vqconfig *config = vq->priv;

	rc = kvm_hypercall1(KVM_S390_VIRTIO_NOTIFY, config->address);
	if (rc < 0)
		return false;
	return true;
}

/*
 * This routine finds the first virtqueue described in the configuration of
 * this device and sets it up.
 */
static struct virtqueue *kvm_find_vq(struct virtio_device *vdev,
				     unsigned index,
				     void (*callback)(struct virtqueue *vq),
				     const char *name, bool ctx)
{
	struct kvm_device *kdev = to_kvmdev(vdev);
	struct kvm_vqconfig *config;
	struct virtqueue *vq;
	int err;

	if (index >= kdev->desc->num_vq)
		return ERR_PTR(-ENOENT);

	if (!name)
		return NULL;

	config = kvm_vq_config(kdev->desc)+index;

	err = vmem_add_mapping(config->address,
			       vring_size(config->num,
					  KVM_S390_VIRTIO_RING_ALIGN));
	if (err)
		goto out;

	vq = vring_new_virtqueue(index, config->num, KVM_S390_VIRTIO_RING_ALIGN,
				 vdev, true, ctx, (void *) config->address,
				 kvm_notify, callback, name);
	if (!vq) {
		err = -ENOMEM;
		goto unmap;
	}

	/*
	 * register a callback token
	 * The host will sent this via the external interrupt parameter
	 */
	config->token = (u64) vq;

	vq->priv = config;
	return vq;
unmap:
	vmem_remove_mapping(config->address,
			    vring_size(config->num,
				       KVM_S390_VIRTIO_RING_ALIGN));
out:
	return ERR_PTR(err);
}

static void kvm_del_vq(struct virtqueue *vq)
{
	struct kvm_vqconfig *config = vq->priv;

	vring_del_virtqueue(vq);
	vmem_remove_mapping(config->address,
			    vring_size(config->num,
				       KVM_S390_VIRTIO_RING_ALIGN));
}

static void kvm_del_vqs(struct virtio_device *vdev)
{
	struct virtqueue *vq, *n;

	list_for_each_entry_safe(vq, n, &vdev->vqs, list)
		kvm_del_vq(vq);
}

static int kvm_find_vqs(struct virtio_device *vdev, unsigned nvqs,
			struct virtqueue *vqs[],
			vq_callback_t *callbacks[],
			const char * const names[],
			const bool *ctx,
			struct irq_affinity *desc)
{
	struct kvm_device *kdev = to_kvmdev(vdev);
	int i;

	/* We must have this many virtqueues. */
	if (nvqs > kdev->desc->num_vq)
		return -ENOENT;

	for (i = 0; i < nvqs; ++i) {
		vqs[i] = kvm_find_vq(vdev, i, callbacks[i], names[i],
				     ctx ? ctx[i] : false);
		if (IS_ERR(vqs[i]))
			goto error;
	}
	return 0;

error:
	kvm_del_vqs(vdev);
	return PTR_ERR(vqs[i]);
}

static const char *kvm_bus_name(struct virtio_device *vdev)
{
	return "";
}

/*
 * The config ops structure as defined by virtio config
 */
static const struct virtio_config_ops kvm_vq_configspace_ops = {
	.get_features = kvm_get_features,
	.finalize_features = kvm_finalize_features,
	.get = kvm_get,
	.set = kvm_set,
	.get_status = kvm_get_status,
	.set_status = kvm_set_status,
	.reset = kvm_reset,
	.find_vqs = kvm_find_vqs,
	.del_vqs = kvm_del_vqs,
	.bus_name = kvm_bus_name,
};

/*
 * The root device for the kvm virtio devices.
 * This makes them appear as /sys/devices/kvm_s390/0,1,2 not /sys/devices/0,1,2.
 */
static struct device *kvm_root;

/*
 * adds a new device and register it with virtio
 * appropriate drivers are loaded by the device model
 */
static void add_kvm_device(struct kvm_device_desc *d, unsigned int offset)
{
	struct kvm_device *kdev;

	kdev = kzalloc(sizeof(*kdev), GFP_KERNEL);
	if (!kdev) {
		printk(KERN_EMERG "Cannot allocate kvm dev %u type %u\n",
		       offset, d->type);
		return;
	}

	kdev->vdev.dev.parent = kvm_root;
	kdev->vdev.id.device = d->type;
	kdev->vdev.config = &kvm_vq_configspace_ops;
	kdev->desc = d;

	if (register_virtio_device(&kdev->vdev) != 0) {
		printk(KERN_ERR "Failed to register kvm device %u type %u\n",
		       offset, d->type);
		kfree(kdev);
	}
}

/*
 * scan_devices() simply iterates through the device page.
 * The type 0 is reserved to mean "end of devices".
 */
static void scan_devices(void)
{
	unsigned int i;
	struct kvm_device_desc *d;

	for (i = 0; i < PAGE_SIZE; i += desc_size(d)) {
		d = kvm_devices + i;

		if (d->type == 0)
			break;

		add_kvm_device(d, i);
	}
}

/*
 * match for a kvm device with a specific desc pointer
 */
static int match_desc(struct device *dev, void *data)
{
	struct virtio_device *vdev = dev_to_virtio(dev);
	struct kvm_device *kdev = to_kvmdev(vdev);

	return kdev->desc == data;
}

/*
 * hotplug_device tries to find changes in the device page.
 */
static void hotplug_devices(struct work_struct *dummy)
{
	unsigned int i;
	struct kvm_device_desc *d;
	struct device *dev;

	for (i = 0; i < PAGE_SIZE; i += desc_size(d)) {
		d = kvm_devices + i;

		/* end of list */
		if (d->type == 0)
			break;

		/* device already exists */
		dev = device_find_child(kvm_root, d, match_desc);
		if (dev) {
			/* XXX check for hotplug remove */
			put_device(dev);
			continue;
		}

		/* new device */
		printk(KERN_INFO "Adding new virtio device %p\n", d);
		add_kvm_device(d, i);
	}
}

/*
 * we emulate the request_irq behaviour on top of s390 extints
 */
static void kvm_extint_handler(struct ext_code ext_code,
			       unsigned int param32, unsigned long param64)
{
	struct virtqueue *vq;
	u32 param;

	if ((ext_code.subcode & 0xff00) != VIRTIO_SUBCODE_64)
		return;
	inc_irq_stat(IRQEXT_VRT);

	/* The LSB might be overloaded, we have to mask it */
	vq = (struct virtqueue *)(param64 & ~1UL);

	/* We use ext_params to decide what this interrupt means */
	param = param32 & VIRTIO_PARAM_MASK;

	switch (param) {
	case VIRTIO_PARAM_CONFIG_CHANGED:
		virtio_config_changed(vq->vdev);
		break;
	case VIRTIO_PARAM_DEV_ADD:
		schedule_work(&hotplug_work);
		break;
	case VIRTIO_PARAM_VRING_INTERRUPT:
	default:
		vring_interrupt(0, vq);
		break;
	}
}

/*
 * For s390-virtio, we expect a page above main storage containing
 * the virtio configuration. Try to actually load from this area
 * in order to figure out if the host provides this page.
 */
static int __init test_devices_support(unsigned long addr)
{
	int ret = -EIO;

	asm volatile(
		"0:	lura	0,%1\n"
		"1:	xgr	%0,%0\n"
		"2:\n"
		EX_TABLE(0b,2b)
		EX_TABLE(1b,2b)
		: "+d" (ret)
		: "a" (addr)
		: "0", "cc");
	return ret;
}
/*
 * Init function for virtio
 * devices are in a single page above top of "normal" + standby mem
 */
static int __init kvm_devices_init(void)
{
	int rc;
	unsigned long total_memory_size = sclp.rzm * sclp.rnmax;

	if (!MACHINE_IS_KVM)
		return -ENODEV;

	if (test_devices_support(total_memory_size) < 0)
		return -ENODEV;

	pr_warn("The s390-virtio transport is deprecated. Please switch to a modern host providing virtio-ccw.\n");

	rc = vmem_add_mapping(total_memory_size, PAGE_SIZE);
	if (rc)
		return rc;

	kvm_devices = (void *) total_memory_size;

	kvm_root = root_device_register("kvm_s390");
	if (IS_ERR(kvm_root)) {
		rc = PTR_ERR(kvm_root);
		printk(KERN_ERR "Could not register kvm_s390 root device");
		vmem_remove_mapping(total_memory_size, PAGE_SIZE);
		return rc;
	}

	INIT_WORK(&hotplug_work, hotplug_devices);

	irq_subclass_register(IRQ_SUBCLASS_SERVICE_SIGNAL);
	register_external_irq(EXT_IRQ_CP_SERVICE, kvm_extint_handler);

	scan_devices();
	return 0;
}

/* code for early console output with virtio_console */
static int early_put_chars(u32 vtermno, const char *buf, int count)
{
	char scratch[17];
	unsigned int len = count;

	if (len > sizeof(scratch) - 1)
		len = sizeof(scratch) - 1;
	scratch[len] = '\0';
	memcpy(scratch, buf, len);
	kvm_hypercall1(KVM_S390_VIRTIO_NOTIFY, __pa(scratch));
	return len;
}

static int __init s390_virtio_console_init(void)
{
	if (sclp.has_vt220 || sclp.has_linemode)
		return -ENODEV;
	return virtio_cons_early_init(early_put_chars);
}
console_initcall(s390_virtio_console_init);


/*
 * We do this after core stuff, but before the drivers.
 */
postcore_initcall(kvm_devices_init);