vhost.c 32.6 KB
Newer Older
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23
/* Copyright (C) 2009 Red Hat, Inc.
 * Copyright (C) 2006 Rusty Russell IBM Corporation
 *
 * Author: Michael S. Tsirkin <mst@redhat.com>
 *
 * Inspiration, some code, and most witty comments come from
 * Documentation/lguest/lguest.c, by Rusty Russell
 *
 * This work is licensed under the terms of the GNU GPL, version 2.
 *
 * Generic code for virtio server in host kernel.
 */

#include <linux/eventfd.h>
#include <linux/vhost.h>
#include <linux/virtio_net.h>
#include <linux/mm.h>
#include <linux/miscdevice.h>
#include <linux/mutex.h>
#include <linux/rcupdate.h>
#include <linux/poll.h>
#include <linux/file.h>
#include <linux/highmem.h>
24
#include <linux/slab.h>
25
#include <linux/kthread.h>
26
#include <linux/cgroup.h>
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

#include <linux/net.h>
#include <linux/if_packet.h>
#include <linux/if_arp.h>

#include <net/sock.h>

#include "vhost.h"

enum {
	VHOST_MEMORY_MAX_NREGIONS = 64,
	VHOST_MEMORY_F_LOG = 0x1,
};

static void vhost_poll_func(struct file *file, wait_queue_head_t *wqh,
			    poll_table *pt)
{
	struct vhost_poll *poll;
	poll = container_of(pt, struct vhost_poll, table);

	poll->wqh = wqh;
	add_wait_queue(wqh, &poll->wait);
}

static int vhost_poll_wakeup(wait_queue_t *wait, unsigned mode, int sync,
			     void *key)
{
54 55
	struct vhost_poll *poll = container_of(wait, struct vhost_poll, wait);

56 57 58
	if (!((unsigned long)key & poll->mask))
		return 0;

59
	vhost_poll_queue(poll);
60 61 62 63
	return 0;
}

/* Init poll structure */
64 65
void vhost_poll_init(struct vhost_poll *poll, vhost_work_fn_t fn,
		     unsigned long mask, struct vhost_dev *dev)
66
{
67 68
	struct vhost_work *work = &poll->work;

69 70 71
	init_waitqueue_func_entry(&poll->wait, vhost_poll_wakeup);
	init_poll_funcptr(&poll->table, vhost_poll_func);
	poll->mask = mask;
72 73 74 75 76 77 78
	poll->dev = dev;

	INIT_LIST_HEAD(&work->node);
	work->fn = fn;
	init_waitqueue_head(&work->done);
	work->flushing = 0;
	work->queue_seq = work->done_seq = 0;
79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101
}

/* Start polling a file. We add ourselves to file's wait queue. The caller must
 * keep a reference to a file until after vhost_poll_stop is called. */
void vhost_poll_start(struct vhost_poll *poll, struct file *file)
{
	unsigned long mask;
	mask = file->f_op->poll(file, &poll->table);
	if (mask)
		vhost_poll_wakeup(&poll->wait, 0, 0, (void *)mask);
}

/* Stop polling a file. After this function returns, it becomes safe to drop the
 * file reference. You must also flush afterwards. */
void vhost_poll_stop(struct vhost_poll *poll)
{
	remove_wait_queue(poll->wqh, &poll->wait);
}

/* Flush any work that has been scheduled. When calling this, don't hold any
 * locks that are also used by the callback. */
void vhost_poll_flush(struct vhost_poll *poll)
{
102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120
	struct vhost_work *work = &poll->work;
	unsigned seq;
	int left;
	int flushing;

	spin_lock_irq(&poll->dev->work_lock);
	seq = work->queue_seq;
	work->flushing++;
	spin_unlock_irq(&poll->dev->work_lock);
	wait_event(work->done, ({
		   spin_lock_irq(&poll->dev->work_lock);
		   left = seq - work->done_seq <= 0;
		   spin_unlock_irq(&poll->dev->work_lock);
		   left;
	}));
	spin_lock_irq(&poll->dev->work_lock);
	flushing = --work->flushing;
	spin_unlock_irq(&poll->dev->work_lock);
	BUG_ON(flushing < 0);
121 122 123 124
}

void vhost_poll_queue(struct vhost_poll *poll)
{
125 126 127 128 129 130 131 132 133 134 135
	struct vhost_dev *dev = poll->dev;
	struct vhost_work *work = &poll->work;
	unsigned long flags;

	spin_lock_irqsave(&dev->work_lock, flags);
	if (list_empty(&work->node)) {
		list_add_tail(&work->node, &dev->work_list);
		work->queue_seq++;
		wake_up_process(dev->worker);
	}
	spin_unlock_irqrestore(&dev->work_lock, flags);
136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151
}

static void vhost_vq_reset(struct vhost_dev *dev,
			   struct vhost_virtqueue *vq)
{
	vq->num = 1;
	vq->desc = NULL;
	vq->avail = NULL;
	vq->used = NULL;
	vq->last_avail_idx = 0;
	vq->avail_idx = 0;
	vq->last_used_idx = 0;
	vq->used_flags = 0;
	vq->used_flags = 0;
	vq->log_used = false;
	vq->log_addr = -1ull;
152 153
	vq->vhost_hlen = 0;
	vq->sock_hlen = 0;
154 155 156 157 158 159 160
	vq->private_data = NULL;
	vq->log_base = NULL;
	vq->error_ctx = NULL;
	vq->error = NULL;
	vq->kick = NULL;
	vq->call_ctx = NULL;
	vq->call = NULL;
161
	vq->log_ctx = NULL;
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
static int vhost_worker(void *data)
{
	struct vhost_dev *dev = data;
	struct vhost_work *work = NULL;
	unsigned uninitialized_var(seq);

	for (;;) {
		/* mb paired w/ kthread_stop */
		set_current_state(TASK_INTERRUPTIBLE);

		spin_lock_irq(&dev->work_lock);
		if (work) {
			work->done_seq = seq;
			if (work->flushing)
				wake_up_all(&work->done);
		}

		if (kthread_should_stop()) {
			spin_unlock_irq(&dev->work_lock);
			__set_current_state(TASK_RUNNING);
			return 0;
		}
		if (!list_empty(&dev->work_list)) {
			work = list_first_entry(&dev->work_list,
						struct vhost_work, node);
			list_del_init(&work->node);
			seq = work->queue_seq;
		} else
			work = NULL;
		spin_unlock_irq(&dev->work_lock);

		if (work) {
			__set_current_state(TASK_RUNNING);
			work->fn(work);
		} else
			schedule();

	}
}

204 205 206 207
long vhost_dev_init(struct vhost_dev *dev,
		    struct vhost_virtqueue *vqs, int nvqs)
{
	int i;
208

209 210 211 212 213 214 215
	dev->vqs = vqs;
	dev->nvqs = nvqs;
	mutex_init(&dev->mutex);
	dev->log_ctx = NULL;
	dev->log_file = NULL;
	dev->memory = NULL;
	dev->mm = NULL;
216 217 218
	spin_lock_init(&dev->work_lock);
	INIT_LIST_HEAD(&dev->work_list);
	dev->worker = NULL;
219 220 221 222 223 224 225

	for (i = 0; i < dev->nvqs; ++i) {
		dev->vqs[i].dev = dev;
		mutex_init(&dev->vqs[i].mutex);
		vhost_vq_reset(dev, dev->vqs + i);
		if (dev->vqs[i].handle_kick)
			vhost_poll_init(&dev->vqs[i].poll,
226
					dev->vqs[i].handle_kick, POLLIN, dev);
227
	}
228

229 230 231 232 233 234 235 236 237 238 239 240 241
	return 0;
}

/* Caller should have device mutex */
long vhost_dev_check_owner(struct vhost_dev *dev)
{
	/* Are you the owner? If not, I don't think you mean to do that */
	return dev->mm == current->mm ? 0 : -EPERM;
}

/* Caller should have device mutex */
static long vhost_dev_set_owner(struct vhost_dev *dev)
{
242 243
	struct task_struct *worker;
	int err;
244
	/* Is there an owner already? */
245 246 247 248
	if (dev->mm) {
		err = -EBUSY;
		goto err_mm;
	}
249 250
	/* No owner, become one */
	dev->mm = get_task_mm(current);
251 252 253 254 255 256 257
	worker = kthread_create(vhost_worker, dev, "vhost-%d", current->pid);
	if (IS_ERR(worker)) {
		err = PTR_ERR(worker);
		goto err_worker;
	}

	dev->worker = worker;
258 259 260
	err = cgroup_attach_task_current_cg(worker);
	if (err)
		goto err_cgroup;
261 262
	wake_up_process(worker);	/* avoid contributing to loadavg */

263
	return 0;
264 265
err_cgroup:
	kthread_stop(worker);
266 267 268 269 270 271
err_worker:
	if (dev->mm)
		mmput(dev->mm);
	dev->mm = NULL;
err_mm:
	return err;
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
}

/* Caller should have device mutex */
long vhost_dev_reset_owner(struct vhost_dev *dev)
{
	struct vhost_memory *memory;

	/* Restore memory to default empty mapping. */
	memory = kmalloc(offsetof(struct vhost_memory, regions), GFP_KERNEL);
	if (!memory)
		return -ENOMEM;

	vhost_dev_cleanup(dev);

	memory->nregions = 0;
	dev->memory = memory;
	return 0;
}

/* Caller should have device mutex */
void vhost_dev_cleanup(struct vhost_dev *dev)
{
	int i;
	for (i = 0; i < dev->nvqs; ++i) {
		if (dev->vqs[i].kick && dev->vqs[i].handle_kick) {
			vhost_poll_stop(&dev->vqs[i].poll);
			vhost_poll_flush(&dev->vqs[i].poll);
		}
		if (dev->vqs[i].error_ctx)
			eventfd_ctx_put(dev->vqs[i].error_ctx);
		if (dev->vqs[i].error)
			fput(dev->vqs[i].error);
		if (dev->vqs[i].kick)
			fput(dev->vqs[i].kick);
		if (dev->vqs[i].call_ctx)
			eventfd_ctx_put(dev->vqs[i].call_ctx);
		if (dev->vqs[i].call)
			fput(dev->vqs[i].call);
		vhost_vq_reset(dev, dev->vqs + i);
	}
	if (dev->log_ctx)
		eventfd_ctx_put(dev->log_ctx);
	dev->log_ctx = NULL;
	if (dev->log_file)
		fput(dev->log_file);
	dev->log_file = NULL;
	/* No one will access memory at this point */
	kfree(dev->memory);
	dev->memory = NULL;
	if (dev->mm)
		mmput(dev->mm);
	dev->mm = NULL;
324 325

	WARN_ON(!list_empty(&dev->work_list));
326 327 328 329
	if (dev->worker) {
		kthread_stop(dev->worker);
		dev->worker = NULL;
	}
330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348
}

static int log_access_ok(void __user *log_base, u64 addr, unsigned long sz)
{
	u64 a = addr / VHOST_PAGE_SIZE / 8;
	/* Make sure 64 bit math will not overflow. */
	if (a > ULONG_MAX - (unsigned long)log_base ||
	    a + (unsigned long)log_base > ULONG_MAX)
		return -EFAULT;

	return access_ok(VERIFY_WRITE, log_base + a,
			 (sz + VHOST_PAGE_SIZE * 8 - 1) / VHOST_PAGE_SIZE / 8);
}

/* Caller should have vq mutex and device mutex. */
static int vq_memory_access_ok(void __user *log_base, struct vhost_memory *mem,
			       int log_all)
{
	int i;
349

Michael S. Tsirkin's avatar
Michael S. Tsirkin committed
350 351
	if (!mem)
		return 0;
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
	for (i = 0; i < mem->nregions; ++i) {
		struct vhost_memory_region *m = mem->regions + i;
		unsigned long a = m->userspace_addr;
		if (m->memory_size > ULONG_MAX)
			return 0;
		else if (!access_ok(VERIFY_WRITE, (void __user *)a,
				    m->memory_size))
			return 0;
		else if (log_all && !log_access_ok(log_base,
						   m->guest_phys_addr,
						   m->memory_size))
			return 0;
	}
	return 1;
}

/* Can we switch to this memory table? */
/* Caller should have device mutex but not vq mutex */
static int memory_access_ok(struct vhost_dev *d, struct vhost_memory *mem,
			    int log_all)
{
	int i;
	for (i = 0; i < d->nvqs; ++i) {
		int ok;
		mutex_lock(&d->vqs[i].mutex);
		/* If ring is inactive, will check when it's enabled. */
		if (d->vqs[i].private_data)
			ok = vq_memory_access_ok(d->vqs[i].log_base, mem,
						 log_all);
		else
			ok = 1;
		mutex_unlock(&d->vqs[i].mutex);
		if (!ok)
			return 0;
	}
	return 1;
}

static int vq_access_ok(unsigned int num,
			struct vring_desc __user *desc,
			struct vring_avail __user *avail,
			struct vring_used __user *used)
{
	return access_ok(VERIFY_READ, desc, num * sizeof *desc) &&
	       access_ok(VERIFY_READ, avail,
			 sizeof *avail + num * sizeof *avail->ring) &&
	       access_ok(VERIFY_WRITE, used,
			sizeof *used + num * sizeof *used->ring);
}

/* Can we log writes? */
/* Caller should have device mutex but not vq mutex */
int vhost_log_access_ok(struct vhost_dev *dev)
{
	return memory_access_ok(dev, dev->memory, 1);
}

/* Verify access for write logging. */
/* Caller should have vq mutex and device mutex */
static int vq_log_access_ok(struct vhost_virtqueue *vq, void __user *log_base)
{
	return vq_memory_access_ok(log_base, vq->dev->memory,
			    vhost_has_feature(vq->dev, VHOST_F_LOG_ALL)) &&
		(!vq->log_used || log_access_ok(log_base, vq->log_addr,
					sizeof *vq->used +
					vq->num * sizeof *vq->used->ring));
}

/* Can we start vq? */
/* Caller should have vq mutex and device mutex */
int vhost_vq_access_ok(struct vhost_virtqueue *vq)
{
	return vq_access_ok(vq->num, vq->desc, vq->avail, vq->used) &&
		vq_log_access_ok(vq, vq->log_base);
}

static long vhost_set_memory(struct vhost_dev *d, struct vhost_memory __user *m)
{
	struct vhost_memory mem, *newmem, *oldmem;
	unsigned long size = offsetof(struct vhost_memory, regions);
433 434
	if (copy_from_user(&mem, m, size))
		return -EFAULT;
435 436 437 438 439 440 441 442 443
	if (mem.padding)
		return -EOPNOTSUPP;
	if (mem.nregions > VHOST_MEMORY_MAX_NREGIONS)
		return -E2BIG;
	newmem = kmalloc(size + mem.nregions * sizeof *m->regions, GFP_KERNEL);
	if (!newmem)
		return -ENOMEM;

	memcpy(newmem, &mem, size);
444 445
	if (copy_from_user(newmem->regions, m->regions,
			   mem.nregions * sizeof *m->regions)) {
446
		kfree(newmem);
447
		return -EFAULT;
448 449
	}

450 451
	if (!memory_access_ok(d, newmem, vhost_has_feature(d, VHOST_F_LOG_ALL))) {
		kfree(newmem);
452
		return -EFAULT;
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
	oldmem = d->memory;
	rcu_assign_pointer(d->memory, newmem);
	synchronize_rcu();
	kfree(oldmem);
	return 0;
}

static int init_used(struct vhost_virtqueue *vq,
		     struct vring_used __user *used)
{
	int r = put_user(vq->used_flags, &used->flags);
	if (r)
		return r;
	return get_user(vq->last_used_idx, &used->idx);
}

static long vhost_set_vring(struct vhost_dev *d, int ioctl, void __user *argp)
{
	struct file *eventfp, *filep = NULL,
		    *pollstart = NULL, *pollstop = NULL;
	struct eventfd_ctx *ctx = NULL;
	u32 __user *idxp = argp;
	struct vhost_virtqueue *vq;
	struct vhost_vring_state s;
	struct vhost_vring_file f;
	struct vhost_vring_addr a;
	u32 idx;
	long r;

	r = get_user(idx, idxp);
	if (r < 0)
		return r;
486
	if (idx >= d->nvqs)
487 488 489 490 491 492 493 494 495 496 497 498 499 500
		return -ENOBUFS;

	vq = d->vqs + idx;

	mutex_lock(&vq->mutex);

	switch (ioctl) {
	case VHOST_SET_VRING_NUM:
		/* Resizing ring with an active backend?
		 * You don't want to do that. */
		if (vq->private_data) {
			r = -EBUSY;
			break;
		}
501 502
		if (copy_from_user(&s, argp, sizeof s)) {
			r = -EFAULT;
503
			break;
504
		}
505 506 507 508 509 510 511 512 513 514 515 516 517
		if (!s.num || s.num > 0xffff || (s.num & (s.num - 1))) {
			r = -EINVAL;
			break;
		}
		vq->num = s.num;
		break;
	case VHOST_SET_VRING_BASE:
		/* Moving base with an active backend?
		 * You don't want to do that. */
		if (vq->private_data) {
			r = -EBUSY;
			break;
		}
518 519
		if (copy_from_user(&s, argp, sizeof s)) {
			r = -EFAULT;
520
			break;
521
		}
522 523 524 525 526 527 528 529 530 531 532
		if (s.num > 0xffff) {
			r = -EINVAL;
			break;
		}
		vq->last_avail_idx = s.num;
		/* Forget the cached index value. */
		vq->avail_idx = vq->last_avail_idx;
		break;
	case VHOST_GET_VRING_BASE:
		s.index = idx;
		s.num = vq->last_avail_idx;
533 534
		if (copy_to_user(argp, &s, sizeof s))
			r = -EFAULT;
535 536
		break;
	case VHOST_SET_VRING_ADDR:
537 538
		if (copy_from_user(&a, argp, sizeof a)) {
			r = -EFAULT;
539
			break;
540
		}
541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592
		if (a.flags & ~(0x1 << VHOST_VRING_F_LOG)) {
			r = -EOPNOTSUPP;
			break;
		}
		/* For 32bit, verify that the top 32bits of the user
		   data are set to zero. */
		if ((u64)(unsigned long)a.desc_user_addr != a.desc_user_addr ||
		    (u64)(unsigned long)a.used_user_addr != a.used_user_addr ||
		    (u64)(unsigned long)a.avail_user_addr != a.avail_user_addr) {
			r = -EFAULT;
			break;
		}
		if ((a.avail_user_addr & (sizeof *vq->avail->ring - 1)) ||
		    (a.used_user_addr & (sizeof *vq->used->ring - 1)) ||
		    (a.log_guest_addr & (sizeof *vq->used->ring - 1))) {
			r = -EINVAL;
			break;
		}

		/* We only verify access here if backend is configured.
		 * If it is not, we don't as size might not have been setup.
		 * We will verify when backend is configured. */
		if (vq->private_data) {
			if (!vq_access_ok(vq->num,
				(void __user *)(unsigned long)a.desc_user_addr,
				(void __user *)(unsigned long)a.avail_user_addr,
				(void __user *)(unsigned long)a.used_user_addr)) {
				r = -EINVAL;
				break;
			}

			/* Also validate log access for used ring if enabled. */
			if ((a.flags & (0x1 << VHOST_VRING_F_LOG)) &&
			    !log_access_ok(vq->log_base, a.log_guest_addr,
					   sizeof *vq->used +
					   vq->num * sizeof *vq->used->ring)) {
				r = -EINVAL;
				break;
			}
		}

		r = init_used(vq, (struct vring_used __user *)(unsigned long)
			      a.used_user_addr);
		if (r)
			break;
		vq->log_used = !!(a.flags & (0x1 << VHOST_VRING_F_LOG));
		vq->desc = (void __user *)(unsigned long)a.desc_user_addr;
		vq->avail = (void __user *)(unsigned long)a.avail_user_addr;
		vq->log_addr = a.log_guest_addr;
		vq->used = (void __user *)(unsigned long)a.used_user_addr;
		break;
	case VHOST_SET_VRING_KICK:
593 594
		if (copy_from_user(&f, argp, sizeof f)) {
			r = -EFAULT;
595
			break;
596
		}
597
		eventfp = f.fd == -1 ? NULL : eventfd_fget(f.fd);
598 599 600 601
		if (IS_ERR(eventfp)) {
			r = PTR_ERR(eventfp);
			break;
		}
602 603 604 605 606 607 608
		if (eventfp != vq->kick) {
			pollstop = filep = vq->kick;
			pollstart = vq->kick = eventfp;
		} else
			filep = eventfp;
		break;
	case VHOST_SET_VRING_CALL:
609 610
		if (copy_from_user(&f, argp, sizeof f)) {
			r = -EFAULT;
611
			break;
612
		}
613
		eventfp = f.fd == -1 ? NULL : eventfd_fget(f.fd);
614 615 616 617
		if (IS_ERR(eventfp)) {
			r = PTR_ERR(eventfp);
			break;
		}
618 619 620 621 622 623 624 625 626 627
		if (eventfp != vq->call) {
			filep = vq->call;
			ctx = vq->call_ctx;
			vq->call = eventfp;
			vq->call_ctx = eventfp ?
				eventfd_ctx_fileget(eventfp) : NULL;
		} else
			filep = eventfp;
		break;
	case VHOST_SET_VRING_ERR:
628 629
		if (copy_from_user(&f, argp, sizeof f)) {
			r = -EFAULT;
630
			break;
631
		}
632
		eventfp = f.fd == -1 ? NULL : eventfd_fget(f.fd);
633 634 635 636
		if (IS_ERR(eventfp)) {
			r = PTR_ERR(eventfp);
			break;
		}
637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693
		if (eventfp != vq->error) {
			filep = vq->error;
			vq->error = eventfp;
			ctx = vq->error_ctx;
			vq->error_ctx = eventfp ?
				eventfd_ctx_fileget(eventfp) : NULL;
		} else
			filep = eventfp;
		break;
	default:
		r = -ENOIOCTLCMD;
	}

	if (pollstop && vq->handle_kick)
		vhost_poll_stop(&vq->poll);

	if (ctx)
		eventfd_ctx_put(ctx);
	if (filep)
		fput(filep);

	if (pollstart && vq->handle_kick)
		vhost_poll_start(&vq->poll, vq->kick);

	mutex_unlock(&vq->mutex);

	if (pollstop && vq->handle_kick)
		vhost_poll_flush(&vq->poll);
	return r;
}

/* Caller must have device mutex */
long vhost_dev_ioctl(struct vhost_dev *d, unsigned int ioctl, unsigned long arg)
{
	void __user *argp = (void __user *)arg;
	struct file *eventfp, *filep = NULL;
	struct eventfd_ctx *ctx = NULL;
	u64 p;
	long r;
	int i, fd;

	/* If you are not the owner, you can become one */
	if (ioctl == VHOST_SET_OWNER) {
		r = vhost_dev_set_owner(d);
		goto done;
	}

	/* You must be the owner to do anything else */
	r = vhost_dev_check_owner(d);
	if (r)
		goto done;

	switch (ioctl) {
	case VHOST_SET_MEM_TABLE:
		r = vhost_set_memory(d, argp);
		break;
	case VHOST_SET_LOG_BASE:
694 695
		if (copy_from_user(&p, argp, sizeof p)) {
			r = -EFAULT;
696
			break;
697
		}
698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776
		if ((u64)(unsigned long)p != p) {
			r = -EFAULT;
			break;
		}
		for (i = 0; i < d->nvqs; ++i) {
			struct vhost_virtqueue *vq;
			void __user *base = (void __user *)(unsigned long)p;
			vq = d->vqs + i;
			mutex_lock(&vq->mutex);
			/* If ring is inactive, will check when it's enabled. */
			if (vq->private_data && !vq_log_access_ok(vq, base))
				r = -EFAULT;
			else
				vq->log_base = base;
			mutex_unlock(&vq->mutex);
		}
		break;
	case VHOST_SET_LOG_FD:
		r = get_user(fd, (int __user *)argp);
		if (r < 0)
			break;
		eventfp = fd == -1 ? NULL : eventfd_fget(fd);
		if (IS_ERR(eventfp)) {
			r = PTR_ERR(eventfp);
			break;
		}
		if (eventfp != d->log_file) {
			filep = d->log_file;
			ctx = d->log_ctx;
			d->log_ctx = eventfp ?
				eventfd_ctx_fileget(eventfp) : NULL;
		} else
			filep = eventfp;
		for (i = 0; i < d->nvqs; ++i) {
			mutex_lock(&d->vqs[i].mutex);
			d->vqs[i].log_ctx = d->log_ctx;
			mutex_unlock(&d->vqs[i].mutex);
		}
		if (ctx)
			eventfd_ctx_put(ctx);
		if (filep)
			fput(filep);
		break;
	default:
		r = vhost_set_vring(d, ioctl, argp);
		break;
	}
done:
	return r;
}

static const struct vhost_memory_region *find_region(struct vhost_memory *mem,
						     __u64 addr, __u32 len)
{
	struct vhost_memory_region *reg;
	int i;
	/* linear search is not brilliant, but we really have on the order of 6
	 * regions in practice */
	for (i = 0; i < mem->nregions; ++i) {
		reg = mem->regions + i;
		if (reg->guest_phys_addr <= addr &&
		    reg->guest_phys_addr + reg->memory_size - 1 >= addr)
			return reg;
	}
	return NULL;
}

/* TODO: This is really inefficient.  We need something like get_user()
 * (instruction directly accesses the data, with an exception table entry
 * returning -EFAULT). See Documentation/x86/exception-tables.txt.
 */
static int set_bit_to_user(int nr, void __user *addr)
{
	unsigned long log = (unsigned long)addr;
	struct page *page;
	void *base;
	int bit = nr + (log % PAGE_SIZE) * 8;
	int r;
	r = get_user_pages_fast(log, 1, 1, &page);
777
	if (r < 0)
778
		return r;
779
	BUG_ON(r != 1);
780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817
	base = kmap_atomic(page, KM_USER0);
	set_bit(bit, base);
	kunmap_atomic(base, KM_USER0);
	set_page_dirty_lock(page);
	put_page(page);
	return 0;
}

static int log_write(void __user *log_base,
		     u64 write_address, u64 write_length)
{
	int r;
	if (!write_length)
		return 0;
	write_address /= VHOST_PAGE_SIZE;
	for (;;) {
		u64 base = (u64)(unsigned long)log_base;
		u64 log = base + write_address / 8;
		int bit = write_address % 8;
		if ((u64)(unsigned long)log != log)
			return -EFAULT;
		r = set_bit_to_user(bit, (void __user *)(unsigned long)log);
		if (r < 0)
			return r;
		if (write_length <= VHOST_PAGE_SIZE)
			break;
		write_length -= VHOST_PAGE_SIZE;
		write_address += VHOST_PAGE_SIZE;
	}
	return r;
}

int vhost_log_write(struct vhost_virtqueue *vq, struct vhost_log *log,
		    unsigned int log_num, u64 len)
{
	int i, r;

	/* Make sure data written is seen before log. */
818
	smp_wmb();
819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834
	for (i = 0; i < log_num; ++i) {
		u64 l = min(log[i].len, len);
		r = log_write(vq->log_base, log[i].addr, l);
		if (r < 0)
			return r;
		len -= l;
		if (!len)
			return 0;
	}
	if (vq->log_ctx)
		eventfd_signal(vq->log_ctx, 1);
	/* Length written exceeds what we have stored. This is a bug. */
	BUG();
	return 0;
}

835 836
static int translate_desc(struct vhost_dev *dev, u64 addr, u32 len,
			  struct iovec iov[], int iov_size)
837 838 839 840 841 842 843 844 845 846 847 848
{
	const struct vhost_memory_region *reg;
	struct vhost_memory *mem;
	struct iovec *_iov;
	u64 s = 0;
	int ret = 0;

	rcu_read_lock();

	mem = rcu_dereference(dev->memory);
	while ((u64)len > s) {
		u64 size;
849
		if (unlikely(ret >= iov_size)) {
850 851 852 853
			ret = -ENOBUFS;
			break;
		}
		reg = find_region(mem, addr, len);
854
		if (unlikely(!reg)) {
855 856 857 858 859 860
			ret = -EFAULT;
			break;
		}
		_iov = iov + ret;
		size = reg->memory_size - addr + reg->guest_phys_addr;
		_iov->iov_len = min((u64)len, size);
861
		_iov->iov_base = (void __user *)(unsigned long)
862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892
			(reg->userspace_addr + addr - reg->guest_phys_addr);
		s += size;
		addr += size;
		++ret;
	}

	rcu_read_unlock();
	return ret;
}

/* Each buffer in the virtqueues is actually a chain of descriptors.  This
 * function returns the next descriptor in the chain,
 * or -1U if we're at the end. */
static unsigned next_desc(struct vring_desc *desc)
{
	unsigned int next;

	/* If this descriptor says it doesn't chain, we're done. */
	if (!(desc->flags & VRING_DESC_F_NEXT))
		return -1U;

	/* Check they're not leading us off end of descriptors. */
	next = desc->next;
	/* Make sure compiler knows to grab that: we don't want it changing! */
	/* We will use the result as an index in an array, so most
	 * architectures only need a compiler barrier here. */
	read_barrier_depends();

	return next;
}

893 894 895 896 897
static int get_indirect(struct vhost_dev *dev, struct vhost_virtqueue *vq,
			struct iovec iov[], unsigned int iov_size,
			unsigned int *out_num, unsigned int *in_num,
			struct vhost_log *log, unsigned int *log_num,
			struct vring_desc *indirect)
898 899 900 901 902 903
{
	struct vring_desc desc;
	unsigned int i = 0, count, found = 0;
	int ret;

	/* Sanity check */
904
	if (unlikely(indirect->len % sizeof desc)) {
905 906 907 908 909 910 911 912 913
		vq_err(vq, "Invalid length in indirect descriptor: "
		       "len 0x%llx not multiple of 0x%zx\n",
		       (unsigned long long)indirect->len,
		       sizeof desc);
		return -EINVAL;
	}

	ret = translate_desc(dev, indirect->addr, indirect->len, vq->indirect,
			     ARRAY_SIZE(vq->indirect));
914
	if (unlikely(ret < 0)) {
915 916 917 918 919 920 921 922 923 924 925
		vq_err(vq, "Translation failure %d in indirect.\n", ret);
		return ret;
	}

	/* We will use the result as an address to read from, so most
	 * architectures only need a compiler barrier here. */
	read_barrier_depends();

	count = indirect->len / sizeof desc;
	/* Buffers are chained via a 16 bit next field, so
	 * we can have at most 2^16 of these. */
926
	if (unlikely(count > USHRT_MAX + 1)) {
927 928 929 930 931 932 933
		vq_err(vq, "Indirect buffer length too big: %d\n",
		       indirect->len);
		return -E2BIG;
	}

	do {
		unsigned iov_count = *in_num + *out_num;
934
		if (unlikely(++found > count)) {
935 936 937 938 939
			vq_err(vq, "Loop detected: last one at %u "
			       "indirect size %u\n",
			       i, count);
			return -EINVAL;
		}
940 941
		if (unlikely(memcpy_fromiovec((unsigned char *)&desc, vq->indirect,
					      sizeof desc))) {
942 943 944 945
			vq_err(vq, "Failed indirect descriptor: idx %d, %zx\n",
			       i, (size_t)indirect->addr + i * sizeof desc);
			return -EINVAL;
		}
946
		if (unlikely(desc.flags & VRING_DESC_F_INDIRECT)) {
947 948 949 950 951 952 953
			vq_err(vq, "Nested indirect descriptor: idx %d, %zx\n",
			       i, (size_t)indirect->addr + i * sizeof desc);
			return -EINVAL;
		}

		ret = translate_desc(dev, desc.addr, desc.len, iov + iov_count,
				     iov_size - iov_count);
954
		if (unlikely(ret < 0)) {
955 956 957 958 959 960 961 962 963 964 965 966 967 968 969
			vq_err(vq, "Translation failure %d indirect idx %d\n",
			       ret, i);
			return ret;
		}
		/* If this is an input descriptor, increment that count. */
		if (desc.flags & VRING_DESC_F_WRITE) {
			*in_num += ret;
			if (unlikely(log)) {
				log[*log_num].addr = desc.addr;
				log[*log_num].len = desc.len;
				++*log_num;
			}
		} else {
			/* If it's an output descriptor, they're all supposed
			 * to come before any input descriptors. */
970
			if (unlikely(*in_num)) {
971 972 973 974 975 976 977 978 979 980 981 982 983 984 985
				vq_err(vq, "Indirect descriptor "
				       "has out after in: idx %d\n", i);
				return -EINVAL;
			}
			*out_num += ret;
		}
	} while ((i = next_desc(&desc)) != -1);
	return 0;
}

/* This looks in the virtqueue and for the first available buffer, and converts
 * it to an iovec for convenient access.  Since descriptors consist of some
 * number of output then some number of input descriptors, it's actually two
 * iovecs, but we pack them into one and note how many of each there were.
 *
986 987 988 989 990 991 992
 * This function returns the descriptor number found, or vq->num (which is
 * never a valid descriptor number) if none was found.  A negative code is
 * returned on error. */
int vhost_get_vq_desc(struct vhost_dev *dev, struct vhost_virtqueue *vq,
		      struct iovec iov[], unsigned int iov_size,
		      unsigned int *out_num, unsigned int *in_num,
		      struct vhost_log *log, unsigned int *log_num)
993 994 995 996 997 998 999 1000
{
	struct vring_desc desc;
	unsigned int i, head, found = 0;
	u16 last_avail_idx;
	int ret;

	/* Check it isn't doing very strange things with descriptor numbers. */
	last_avail_idx = vq->last_avail_idx;
1001
	if (unlikely(get_user(vq->avail_idx, &vq->avail->idx))) {
1002 1003
		vq_err(vq, "Failed to access avail idx at %p\n",
		       &vq->avail->idx);
1004
		return -EFAULT;
1005 1006
	}

1007
	if (unlikely((u16)(vq->avail_idx - last_avail_idx) > vq->num)) {
1008 1009
		vq_err(vq, "Guest moved used index from %u to %u",
		       last_avail_idx, vq->avail_idx);
1010
		return -EFAULT;
1011 1012 1013 1014 1015 1016 1017
	}

	/* If there's nothing new since last we looked, return invalid. */
	if (vq->avail_idx == last_avail_idx)
		return vq->num;

	/* Only get avail ring entries after they have been exposed by guest. */
1018
	smp_rmb();
1019 1020 1021

	/* Grab the next descriptor number they're advertising, and increment
	 * the index we've seen. */
1022 1023
	if (unlikely(get_user(head,
			      &vq->avail->ring[last_avail_idx % vq->num]))) {
1024 1025 1026
		vq_err(vq, "Failed to read head: idx %d address %p\n",
		       last_avail_idx,
		       &vq->avail->ring[last_avail_idx % vq->num]);
1027
		return -EFAULT;
1028 1029 1030
	}

	/* If their number is silly, that's an error. */
1031
	if (unlikely(head >= vq->num)) {
1032 1033
		vq_err(vq, "Guest says index %u > %u is available",
		       head, vq->num);
1034
		return -EINVAL;
1035 1036 1037 1038 1039 1040 1041 1042 1043 1044
	}

	/* When we start there are none of either input nor output. */
	*out_num = *in_num = 0;
	if (unlikely(log))
		*log_num = 0;

	i = head;
	do {
		unsigned iov_count = *in_num + *out_num;
1045
		if (unlikely(i >= vq->num)) {
1046 1047
			vq_err(vq, "Desc index is %u > %u, head = %u",
			       i, vq->num, head);
1048
			return -EINVAL;
1049
		}
1050
		if (unlikely(++found > vq->num)) {
1051 1052 1053
			vq_err(vq, "Loop detected: last one at %u "
			       "vq size %u head %u\n",
			       i, vq->num, head);
1054
			return -EINVAL;
1055 1056
		}
		ret = copy_from_user(&desc, vq->desc + i, sizeof desc);
1057
		if (unlikely(ret)) {
1058 1059
			vq_err(vq, "Failed to get descriptor: idx %d addr %p\n",
			       i, vq->desc + i);
1060
			return -EFAULT;
1061 1062 1063 1064 1065
		}
		if (desc.flags & VRING_DESC_F_INDIRECT) {
			ret = get_indirect(dev, vq, iov, iov_size,
					   out_num, in_num,
					   log, log_num, &desc);
1066
			if (unlikely(ret < 0)) {
1067 1068
				vq_err(vq, "Failure detected "
				       "in indirect descriptor at idx %d\n", i);
1069
				return ret;
1070 1071 1072 1073 1074 1075
			}
			continue;
		}

		ret = translate_desc(dev, desc.addr, desc.len, iov + iov_count,
				     iov_size - iov_count);
1076
		if (unlikely(ret < 0)) {
1077 1078
			vq_err(vq, "Translation failure %d descriptor idx %d\n",
			       ret, i);
1079
			return ret;
1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092
		}
		if (desc.flags & VRING_DESC_F_WRITE) {
			/* If this is an input descriptor,
			 * increment that count. */
			*in_num += ret;
			if (unlikely(log)) {
				log[*log_num].addr = desc.addr;
				log[*log_num].len = desc.len;
				++*log_num;
			}
		} else {
			/* If it's an output descriptor, they're all supposed
			 * to come before any input descriptors. */
1093
			if (unlikely(*in_num)) {
1094 1095
				vq_err(vq, "Descriptor has out after in: "
				       "idx %d\n", i);
1096
				return -EINVAL;
1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107
			}
			*out_num += ret;
		}
	} while ((i = next_desc(&desc)) != -1);

	/* On success, increment avail index. */
	vq->last_avail_idx++;
	return head;
}

/* Reverse the effect of vhost_get_vq_desc. Useful for error handling. */
1108
void vhost_discard_vq_desc(struct vhost_virtqueue *vq, int n)
1109
{
1110
	vq->last_avail_idx -= n;
1111 1112 1113 1114 1115 1116
}

/* After we've used one of their buffers, we tell them about it.  We'll then
 * want to notify the guest, using eventfd. */
int vhost_add_used(struct vhost_virtqueue *vq, unsigned int head, int len)
{
1117
	struct vring_used_elem __user *used;
1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130

	/* The virtqueue contains a ring of used buffers.  Get a pointer to the
	 * next entry in that used ring. */
	used = &vq->used->ring[vq->last_used_idx % vq->num];
	if (put_user(head, &used->id)) {
		vq_err(vq, "Failed to write used id");
		return -EFAULT;
	}
	if (put_user(len, &used->len)) {
		vq_err(vq, "Failed to write used len");
		return -EFAULT;
	}
	/* Make sure buffer is written before we update index. */
1131
	smp_wmb();
1132 1133 1134 1135 1136 1137
	if (put_user(vq->last_used_idx + 1, &vq->used->idx)) {
		vq_err(vq, "Failed to increment used idx");
		return -EFAULT;
	}
	if (unlikely(vq->log_used)) {
		/* Make sure data is seen before log. */
1138
		smp_wmb();
1139 1140
		/* Log used ring entry write. */
		log_write(vq->log_base,
1141 1142
			  vq->log_addr +
			   ((void __user *)used - (void __user *)vq->used),
1143 1144 1145 1146 1147
			  sizeof *used);
		/* Log used index update. */
		log_write(vq->log_base,
			  vq->log_addr + offsetof(struct vring_used, idx),
			  sizeof vq->used->idx);
1148 1149 1150 1151 1152 1153 1154
		if (vq->log_ctx)
			eventfd_signal(vq->log_ctx, 1);
	}
	vq->last_used_idx++;
	return 0;
}

1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215
static int __vhost_add_used_n(struct vhost_virtqueue *vq,
			    struct vring_used_elem *heads,
			    unsigned count)
{
	struct vring_used_elem __user *used;
	int start;

	start = vq->last_used_idx % vq->num;
	used = vq->used->ring + start;
	if (copy_to_user(used, heads, count * sizeof *used)) {
		vq_err(vq, "Failed to write used");
		return -EFAULT;
	}
	if (unlikely(vq->log_used)) {
		/* Make sure data is seen before log. */
		smp_wmb();
		/* Log used ring entry write. */
		log_write(vq->log_base,
			  vq->log_addr +
			   ((void __user *)used - (void __user *)vq->used),
			  count * sizeof *used);
	}
	vq->last_used_idx += count;
	return 0;
}

/* After we've used one of their buffers, we tell them about it.  We'll then
 * want to notify the guest, using eventfd. */
int vhost_add_used_n(struct vhost_virtqueue *vq, struct vring_used_elem *heads,
		     unsigned count)
{
	int start, n, r;

	start = vq->last_used_idx % vq->num;
	n = vq->num - start;
	if (n < count) {
		r = __vhost_add_used_n(vq, heads, n);
		if (r < 0)
			return r;
		heads += n;
		count -= n;
	}
	r = __vhost_add_used_n(vq, heads, count);

	/* Make sure buffer is written before we update index. */
	smp_wmb();
	if (put_user(vq->last_used_idx, &vq->used->idx)) {
		vq_err(vq, "Failed to increment used idx");
		return -EFAULT;
	}
	if (unlikely(vq->log_used)) {
		/* Log used index update. */
		log_write(vq->log_base,
			  vq->log_addr + offsetof(struct vring_used, idx),
			  sizeof vq->used->idx);
		if (vq->log_ctx)
			eventfd_signal(vq->log_ctx, 1);
	}
	return r;
}

1216 1217 1218
/* This actually signals the guest, using eventfd. */
void vhost_signal(struct vhost_dev *dev, struct vhost_virtqueue *vq)
{
1219 1220 1221 1222 1223 1224
	__u16 flags;
	/* Flush out used index updates. This is paired
	 * with the barrier that the Guest executes when enabling
	 * interrupts. */
	smp_mb();

1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249
	if (get_user(flags, &vq->avail->flags)) {
		vq_err(vq, "Failed to get flags");
		return;
	}

	/* If they don't want an interrupt, don't signal, unless empty. */
	if ((flags & VRING_AVAIL_F_NO_INTERRUPT) &&
	    (vq->avail_idx != vq->last_avail_idx ||
	     !vhost_has_feature(dev, VIRTIO_F_NOTIFY_ON_EMPTY)))
		return;

	/* Signal the Guest tell them we used something up. */
	if (vq->call_ctx)
		eventfd_signal(vq->call_ctx, 1);
}

/* And here's the combo meal deal.  Supersize me! */
void vhost_add_used_and_signal(struct vhost_dev *dev,
			       struct vhost_virtqueue *vq,
			       unsigned int head, int len)
{
	vhost_add_used(vq, head, len);
	vhost_signal(dev, vq);
}

1250 1251 1252 1253 1254 1255 1256 1257 1258
/* multi-buffer version of vhost_add_used_and_signal */
void vhost_add_used_and_signal_n(struct vhost_dev *dev,
				 struct vhost_virtqueue *vq,
				 struct vring_used_elem *heads, unsigned count)
{
	vhost_add_used_n(vq, heads, count);
	vhost_signal(dev, vq);
}

1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274
/* OK, now we need to know about added descriptors. */
bool vhost_enable_notify(struct vhost_virtqueue *vq)
{
	u16 avail_idx;
	int r;
	if (!(vq->used_flags & VRING_USED_F_NO_NOTIFY))
		return false;
	vq->used_flags &= ~VRING_USED_F_NO_NOTIFY;
	r = put_user(vq->used_flags, &vq->used->flags);
	if (r) {
		vq_err(vq, "Failed to enable notification at %p: %d\n",
		       &vq->used->flags, r);
		return false;
	}
	/* They could have slipped one in as we were doing that: make
	 * sure it's written, then check again. */
1275
	smp_mb();
1276 1277 1278 1279 1280 1281 1282
	r = get_user(avail_idx, &vq->avail->idx);
	if (r) {
		vq_err(vq, "Failed to check avail idx at %p: %d\n",
		       &vq->avail->idx, r);
		return false;
	}

1283
	return avail_idx != vq->avail_idx;
1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297
}

/* We don't need to be notified again. */
void vhost_disable_notify(struct vhost_virtqueue *vq)
{
	int r;
	if (vq->used_flags & VRING_USED_F_NO_NOTIFY)
		return;
	vq->used_flags |= VRING_USED_F_NO_NOTIFY;
	r = put_user(vq->used_flags, &vq->used->flags);
	if (r)
		vq_err(vq, "Failed to enable notification at %p: %d\n",
		       &vq->used->flags, r);
}