xsk.c 9.9 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 24 25 26 27 28 29 30 31 32 33
// SPDX-License-Identifier: GPL-2.0
/* XDP sockets
 *
 * AF_XDP sockets allows a channel between XDP programs and userspace
 * applications.
 * Copyright(c) 2018 Intel Corporation.
 *
 * This program is free software; you can redistribute it and/or modify it
 * under the terms and conditions of the GNU General Public License,
 * version 2, as published by the Free Software Foundation.
 *
 * This program is distributed in the hope it will be useful, but WITHOUT
 * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
 * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
 * more details.
 *
 * Author(s): Björn Töpel <bjorn.topel@intel.com>
 *	      Magnus Karlsson <magnus.karlsson@intel.com>
 */

#define pr_fmt(fmt) "AF_XDP: %s: " fmt, __func__

#include <linux/if_xdp.h>
#include <linux/init.h>
#include <linux/sched/mm.h>
#include <linux/sched/signal.h>
#include <linux/sched/task.h>
#include <linux/socket.h>
#include <linux/file.h>
#include <linux/uaccess.h>
#include <linux/net.h>
#include <linux/netdevice.h>
#include <net/xdp_sock.h>
34
#include <net/xdp.h>
35

36
#include "xsk_queue.h"
37 38 39 40 41 42 43
#include "xdp_umem.h"

static struct xdp_sock *xdp_sk(struct sock *sk)
{
	return (struct xdp_sock *)sk;
}

44 45 46 47 48
bool xsk_is_setup_for_bpf_map(struct xdp_sock *xs)
{
	return !!xs->rx;
}

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
static int __xsk_rcv(struct xdp_sock *xs, struct xdp_buff *xdp)
{
	u32 *id, len = xdp->data_end - xdp->data;
	void *buffer;
	int err = 0;

	if (xs->dev != xdp->rxq->dev || xs->queue_id != xdp->rxq->queue_index)
		return -EINVAL;

	id = xskq_peek_id(xs->umem->fq);
	if (!id)
		return -ENOSPC;

	buffer = xdp_umem_get_data_with_headroom(xs->umem, *id);
	memcpy(buffer, xdp->data, len);
	err = xskq_produce_batch_desc(xs->rx, *id, len,
				      xs->umem->frame_headroom);
	if (!err)
		xskq_discard_id(xs->umem->fq);

	return err;
}

int xsk_rcv(struct xdp_sock *xs, struct xdp_buff *xdp)
{
	int err;

	err = __xsk_rcv(xs, xdp);
	if (likely(!err))
		xdp_return_buff(xdp);
	else
		xs->rx_dropped++;

	return err;
}

void xsk_flush(struct xdp_sock *xs)
{
	xskq_produce_flush_desc(xs->rx);
	xs->sk.sk_data_ready(&xs->sk);
}

int xsk_generic_rcv(struct xdp_sock *xs, struct xdp_buff *xdp)
{
	int err;

	err = __xsk_rcv(xs, xdp);
	if (!err)
		xsk_flush(xs);
	else
		xs->rx_dropped++;

	return err;
}

static unsigned int xsk_poll(struct file *file, struct socket *sock,
			     struct poll_table_struct *wait)
{
	unsigned int mask = datagram_poll(file, sock, wait);
	struct sock *sk = sock->sk;
	struct xdp_sock *xs = xdp_sk(sk);

	if (xs->rx && !xskq_empty_desc(xs->rx))
		mask |= POLLIN | POLLRDNORM;

	return mask;
}

117 118
static int xsk_init_queue(u32 entries, struct xsk_queue **queue,
			  bool umem_queue)
119 120 121 122 123 124
{
	struct xsk_queue *q;

	if (entries == 0 || *queue || !is_power_of_2(entries))
		return -EINVAL;

125
	q = xskq_create(entries, umem_queue);
126 127 128 129 130 131 132
	if (!q)
		return -ENOMEM;

	*queue = q;
	return 0;
}

133 134 135 136 137 138 139 140
static void __xsk_release(struct xdp_sock *xs)
{
	/* Wait for driver to stop using the xdp socket. */
	synchronize_net();

	dev_put(xs->dev);
}

141 142 143
static int xsk_release(struct socket *sock)
{
	struct sock *sk = sock->sk;
144
	struct xdp_sock *xs = xdp_sk(sk);
145 146 147 148 149 150 151 152 153 154 155
	struct net *net;

	if (!sk)
		return 0;

	net = sock_net(sk);

	local_bh_disable();
	sock_prot_inuse_add(net, sk->sk_prot, -1);
	local_bh_enable();

156 157 158 159 160
	if (xs->dev) {
		__xsk_release(xs);
		xs->dev = NULL;
	}

161 162 163 164 165 166 167 168 169
	sock_orphan(sk);
	sock->sk = NULL;

	sk_refcnt_debug_release(sk);
	sock_put(sk);

	return 0;
}

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
static struct socket *xsk_lookup_xsk_from_fd(int fd)
{
	struct socket *sock;
	int err;

	sock = sockfd_lookup(fd, &err);
	if (!sock)
		return ERR_PTR(-ENOTSOCK);

	if (sock->sk->sk_family != PF_XDP) {
		sockfd_put(sock);
		return ERR_PTR(-ENOPROTOOPT);
	}

	return sock;
}

static int xsk_bind(struct socket *sock, struct sockaddr *addr, int addr_len)
{
	struct sockaddr_xdp *sxdp = (struct sockaddr_xdp *)addr;
	struct sock *sk = sock->sk;
	struct net_device *dev, *dev_curr;
	struct xdp_sock *xs = xdp_sk(sk);
	struct xdp_umem *old_umem = NULL;
	int err = 0;

	if (addr_len < sizeof(struct sockaddr_xdp))
		return -EINVAL;
	if (sxdp->sxdp_family != AF_XDP)
		return -EINVAL;

	mutex_lock(&xs->mutex);
	dev_curr = xs->dev;
	dev = dev_get_by_index(sock_net(sk), sxdp->sxdp_ifindex);
	if (!dev) {
		err = -ENODEV;
		goto out_release;
	}

	if (!xs->rx) {
		err = -EINVAL;
		goto out_unlock;
	}

	if (sxdp->sxdp_queue_id >= dev->num_rx_queues) {
		err = -EINVAL;
		goto out_unlock;
	}

	if (sxdp->sxdp_flags & XDP_SHARED_UMEM) {
		struct xdp_sock *umem_xs;
		struct socket *sock;

		if (xs->umem) {
			/* We have already our own. */
			err = -EINVAL;
			goto out_unlock;
		}

		sock = xsk_lookup_xsk_from_fd(sxdp->sxdp_shared_umem_fd);
		if (IS_ERR(sock)) {
			err = PTR_ERR(sock);
			goto out_unlock;
		}

		umem_xs = xdp_sk(sock->sk);
		if (!umem_xs->umem) {
			/* No umem to inherit. */
			err = -EBADF;
			sockfd_put(sock);
			goto out_unlock;
		} else if (umem_xs->dev != dev ||
			   umem_xs->queue_id != sxdp->sxdp_queue_id) {
			err = -EINVAL;
			sockfd_put(sock);
			goto out_unlock;
		}

		xdp_get_umem(umem_xs->umem);
		old_umem = xs->umem;
		xs->umem = umem_xs->umem;
		sockfd_put(sock);
	} else if (!xs->umem || !xdp_umem_validate_queues(xs->umem)) {
		err = -EINVAL;
		goto out_unlock;
255 256 257
	} else {
		/* This xsk has its own umem. */
		xskq_set_umem(xs->umem->fq, &xs->umem->props);
258
		xskq_set_umem(xs->umem->cq, &xs->umem->props);
259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281
	}

	/* Rebind? */
	if (dev_curr && (dev_curr != dev ||
			 xs->queue_id != sxdp->sxdp_queue_id)) {
		__xsk_release(xs);
		if (old_umem)
			xdp_put_umem(old_umem);
	}

	xs->dev = dev;
	xs->queue_id = sxdp->sxdp_queue_id;

	xskq_set_umem(xs->rx, &xs->umem->props);

out_unlock:
	if (err)
		dev_put(dev);
out_release:
	mutex_unlock(&xs->mutex);
	return err;
}

282 283 284 285 286 287 288 289 290 291 292
static int xsk_setsockopt(struct socket *sock, int level, int optname,
			  char __user *optval, unsigned int optlen)
{
	struct sock *sk = sock->sk;
	struct xdp_sock *xs = xdp_sk(sk);
	int err;

	if (level != SOL_XDP)
		return -ENOPROTOOPT;

	switch (optname) {
293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308
	case XDP_RX_RING:
	{
		struct xsk_queue **q;
		int entries;

		if (optlen < sizeof(entries))
			return -EINVAL;
		if (copy_from_user(&entries, optval, sizeof(entries)))
			return -EFAULT;

		mutex_lock(&xs->mutex);
		q = &xs->rx;
		err = xsk_init_queue(entries, q, false);
		mutex_unlock(&xs->mutex);
		return err;
	}
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
	case XDP_UMEM_REG:
	{
		struct xdp_umem_reg mr;
		struct xdp_umem *umem;

		if (xs->umem)
			return -EBUSY;

		if (copy_from_user(&mr, optval, sizeof(mr)))
			return -EFAULT;

		mutex_lock(&xs->mutex);
		err = xdp_umem_create(&umem);

		err = xdp_umem_reg(umem, &mr);
		if (err) {
			kfree(umem);
			mutex_unlock(&xs->mutex);
			return err;
		}

		/* Make sure umem is ready before it can be seen by others */
		smp_wmb();

		xs->umem = umem;
		mutex_unlock(&xs->mutex);
		return 0;
	}
337
	case XDP_UMEM_FILL_RING:
338
	case XDP_UMEM_COMPLETION_RING:
339 340 341 342 343 344 345 346 347 348 349
	{
		struct xsk_queue **q;
		int entries;

		if (!xs->umem)
			return -EINVAL;

		if (copy_from_user(&entries, optval, sizeof(entries)))
			return -EFAULT;

		mutex_lock(&xs->mutex);
350 351
		q = (optname == XDP_UMEM_FILL_RING) ? &xs->umem->fq :
			&xs->umem->cq;
352
		err = xsk_init_queue(entries, q, true);
353 354 355
		mutex_unlock(&xs->mutex);
		return err;
	}
356 357 358 359 360 361 362
	default:
		break;
	}

	return -ENOPROTOOPT;
}

363 364 365 366 367 368 369 370 371 372
static int xsk_mmap(struct file *file, struct socket *sock,
		    struct vm_area_struct *vma)
{
	unsigned long offset = vma->vm_pgoff << PAGE_SHIFT;
	unsigned long size = vma->vm_end - vma->vm_start;
	struct xdp_sock *xs = xdp_sk(sock->sk);
	struct xsk_queue *q = NULL;
	unsigned long pfn;
	struct page *qpg;

373 374 375 376 377
	if (offset == XDP_PGOFF_RX_RING) {
		q = xs->rx;
	} else {
		if (!xs->umem)
			return -EINVAL;
378

379 380
		if (offset == XDP_UMEM_PGOFF_FILL_RING)
			q = xs->umem->fq;
381 382
		else if (offset == XDP_UMEM_PGOFF_COMPLETION_RING)
			q = xs->umem->cq;
383 384 385
		else
			return -EINVAL;
	}
386 387 388 389 390 391 392 393 394 395 396 397 398

	if (!q)
		return -EINVAL;

	qpg = virt_to_head_page(q->ring);
	if (size > (PAGE_SIZE << compound_order(qpg)))
		return -EINVAL;

	pfn = virt_to_phys(q->ring) >> PAGE_SHIFT;
	return remap_pfn_range(vma, vma->vm_start, pfn,
			       size, vma->vm_page_prot);
}

399 400 401 402 403 404 405 406 407 408
static struct proto xsk_proto = {
	.name =		"XDP",
	.owner =	THIS_MODULE,
	.obj_size =	sizeof(struct xdp_sock),
};

static const struct proto_ops xsk_proto_ops = {
	.family =	PF_XDP,
	.owner =	THIS_MODULE,
	.release =	xsk_release,
409
	.bind =		xsk_bind,
410 411 412 413
	.connect =	sock_no_connect,
	.socketpair =	sock_no_socketpair,
	.accept =	sock_no_accept,
	.getname =	sock_no_getname,
414
	.poll =		xsk_poll,
415 416 417 418 419 420 421
	.ioctl =	sock_no_ioctl,
	.listen =	sock_no_listen,
	.shutdown =	sock_no_shutdown,
	.setsockopt =	xsk_setsockopt,
	.getsockopt =	sock_no_getsockopt,
	.sendmsg =	sock_no_sendmsg,
	.recvmsg =	sock_no_recvmsg,
422
	.mmap =		xsk_mmap,
423 424 425 426 427 428 429 430 431 432
	.sendpage =	sock_no_sendpage,
};

static void xsk_destruct(struct sock *sk)
{
	struct xdp_sock *xs = xdp_sk(sk);

	if (!sock_flag(sk, SOCK_DEAD))
		return;

433
	xskq_destroy(xs->rx);
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
	xdp_put_umem(xs->umem);

	sk_refcnt_debug_dec(sk);
}

static int xsk_create(struct net *net, struct socket *sock, int protocol,
		      int kern)
{
	struct sock *sk;
	struct xdp_sock *xs;

	if (!ns_capable(net->user_ns, CAP_NET_RAW))
		return -EPERM;
	if (sock->type != SOCK_RAW)
		return -ESOCKTNOSUPPORT;

	if (protocol)
		return -EPROTONOSUPPORT;

	sock->state = SS_UNCONNECTED;

	sk = sk_alloc(net, PF_XDP, GFP_KERNEL, &xsk_proto, kern);
	if (!sk)
		return -ENOBUFS;

	sock->ops = &xsk_proto_ops;

	sock_init_data(sock, sk);

	sk->sk_family = PF_XDP;

	sk->sk_destruct = xsk_destruct;
	sk_refcnt_debug_inc(sk);

	xs = xdp_sk(sk);
	mutex_init(&xs->mutex);

	local_bh_disable();
	sock_prot_inuse_add(net, &xsk_proto, 1);
	local_bh_enable();

	return 0;
}

static const struct net_proto_family xsk_family_ops = {
	.family = PF_XDP,
	.create = xsk_create,
	.owner	= THIS_MODULE,
};

static int __init xsk_init(void)
{
	int err;

	err = proto_register(&xsk_proto, 0 /* no slab */);
	if (err)
		goto out;

	err = sock_register(&xsk_family_ops);
	if (err)
		goto out_proto;

	return 0;

out_proto:
	proto_unregister(&xsk_proto);
out:
	return err;
}

fs_initcall(xsk_init);