skmsg.c 28.1 KB
Newer Older
1 2 3 4 5 6 7 8 9
// SPDX-License-Identifier: GPL-2.0
/* Copyright (c) 2017 - 2018 Covalent IO, Inc. http://covalent.io */

#include <linux/skmsg.h>
#include <linux/skbuff.h>
#include <linux/scatterlist.h>

#include <net/sock.h>
#include <net/tcp.h>
10
#include <net/tls.h>
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

static bool sk_msg_try_coalesce_ok(struct sk_msg *msg, int elem_first_coalesce)
{
	if (msg->sg.end > msg->sg.start &&
	    elem_first_coalesce < msg->sg.end)
		return true;

	if (msg->sg.end < msg->sg.start &&
	    (elem_first_coalesce > msg->sg.start ||
	     elem_first_coalesce < msg->sg.end))
		return true;

	return false;
}

int sk_msg_alloc(struct sock *sk, struct sk_msg *msg, int len,
		 int elem_first_coalesce)
{
	struct page_frag *pfrag = sk_page_frag(sk);
	int ret = 0;

	len -= msg->sg.size;
	while (len > 0) {
		struct scatterlist *sge;
		u32 orig_offset;
		int use, i;

		if (!sk_page_frag_refill(sk, pfrag))
			return -ENOMEM;

		orig_offset = pfrag->offset;
		use = min_t(int, len, pfrag->size - orig_offset);
		if (!sk_wmem_schedule(sk, use))
			return -ENOMEM;

		i = msg->sg.end;
		sk_msg_iter_var_prev(i);
		sge = &msg->sg.data[i];

		if (sk_msg_try_coalesce_ok(msg, elem_first_coalesce) &&
		    sg_page(sge) == pfrag->page &&
		    sge->offset + sge->length == orig_offset) {
			sge->length += use;
		} else {
			if (sk_msg_full(msg)) {
				ret = -ENOSPC;
				break;
			}

			sge = &msg->sg.data[msg->sg.end];
			sg_unmark_end(sge);
			sg_set_page(sge, pfrag->page, use, orig_offset);
			get_page(pfrag->page);
			sk_msg_iter_next(msg, end);
		}

		sk_mem_charge(sk, use);
		msg->sg.size += use;
		pfrag->offset += use;
		len -= use;
	}

	return ret;
}
EXPORT_SYMBOL_GPL(sk_msg_alloc);

77 78 79 80 81
int sk_msg_clone(struct sock *sk, struct sk_msg *dst, struct sk_msg *src,
		 u32 off, u32 len)
{
	int i = src->sg.start;
	struct scatterlist *sge = sk_msg_elem(src, i);
82
	struct scatterlist *sgd = NULL;
83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98
	u32 sge_len, sge_off;

	while (off) {
		if (sge->length > off)
			break;
		off -= sge->length;
		sk_msg_iter_var_next(i);
		if (i == src->sg.end && off)
			return -ENOSPC;
		sge = sk_msg_elem(src, i);
	}

	while (len) {
		sge_len = sge->length - off;
		if (sge_len > len)
			sge_len = len;
99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114

		if (dst->sg.end)
			sgd = sk_msg_elem(dst, dst->sg.end - 1);

		if (sgd &&
		    (sg_page(sge) == sg_page(sgd)) &&
		    (sg_virt(sge) + off == sg_virt(sgd) + sgd->length)) {
			sgd->length += sge_len;
			dst->sg.size += sge_len;
		} else if (!sk_msg_full(dst)) {
			sge_off = sge->offset + off;
			sk_msg_page_add(dst, sg_page(sge), sge_len, sge_off);
		} else {
			return -ENOSPC;
		}

115 116 117 118 119 120 121 122 123 124 125 126 127
		off = 0;
		len -= sge_len;
		sk_mem_charge(sk, sge_len);
		sk_msg_iter_var_next(i);
		if (i == src->sg.end && len)
			return -ENOSPC;
		sge = sk_msg_elem(src, i);
	}

	return 0;
}
EXPORT_SYMBOL_GPL(sk_msg_clone);

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
void sk_msg_return_zero(struct sock *sk, struct sk_msg *msg, int bytes)
{
	int i = msg->sg.start;

	do {
		struct scatterlist *sge = sk_msg_elem(msg, i);

		if (bytes < sge->length) {
			sge->length -= bytes;
			sge->offset += bytes;
			sk_mem_uncharge(sk, bytes);
			break;
		}

		sk_mem_uncharge(sk, sge->length);
		bytes -= sge->length;
		sge->length = 0;
		sge->offset = 0;
		sk_msg_iter_var_next(i);
	} while (bytes && i != msg->sg.end);
	msg->sg.start = i;
}
EXPORT_SYMBOL_GPL(sk_msg_return_zero);

void sk_msg_return(struct sock *sk, struct sk_msg *msg, int bytes)
{
	int i = msg->sg.start;

	do {
		struct scatterlist *sge = &msg->sg.data[i];
		int uncharge = (bytes < sge->length) ? bytes : sge->length;

		sk_mem_uncharge(sk, uncharge);
		bytes -= uncharge;
		sk_msg_iter_var_next(i);
	} while (i != msg->sg.end);
}
EXPORT_SYMBOL_GPL(sk_msg_return);

static int sk_msg_free_elem(struct sock *sk, struct sk_msg *msg, u32 i,
			    bool charge)
{
	struct scatterlist *sge = sk_msg_elem(msg, i);
	u32 len = sge->length;

173 174 175 176
	/* When the skb owns the memory we free it from consume_skb path. */
	if (!msg->skb) {
		if (charge)
			sk_mem_uncharge(sk, len);
177
		put_page(sg_page(sge));
178
	}
179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195
	memset(sge, 0, sizeof(*sge));
	return len;
}

static int __sk_msg_free(struct sock *sk, struct sk_msg *msg, u32 i,
			 bool charge)
{
	struct scatterlist *sge = sk_msg_elem(msg, i);
	int freed = 0;

	while (msg->sg.size) {
		msg->sg.size -= sge->length;
		freed += sk_msg_free_elem(sk, msg, i, charge);
		sk_msg_iter_var_next(i);
		sk_msg_check_to_free(msg, i, msg->sg.size);
		sge = sk_msg_elem(msg, i);
	}
196
	consume_skb(msg->skb);
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
	sk_msg_init(msg);
	return freed;
}

int sk_msg_free_nocharge(struct sock *sk, struct sk_msg *msg)
{
	return __sk_msg_free(sk, msg, msg->sg.start, false);
}
EXPORT_SYMBOL_GPL(sk_msg_free_nocharge);

int sk_msg_free(struct sock *sk, struct sk_msg *msg)
{
	return __sk_msg_free(sk, msg, msg->sg.start, true);
}
EXPORT_SYMBOL_GPL(sk_msg_free);

static void __sk_msg_free_partial(struct sock *sk, struct sk_msg *msg,
				  u32 bytes, bool charge)
{
	struct scatterlist *sge;
	u32 i = msg->sg.start;

	while (bytes) {
		sge = sk_msg_elem(msg, i);
		if (!sge->length)
			break;
		if (bytes < sge->length) {
			if (charge)
				sk_mem_uncharge(sk, bytes);
			sge->length -= bytes;
			sge->offset += bytes;
			msg->sg.size -= bytes;
			break;
		}

		msg->sg.size -= sge->length;
		bytes -= sge->length;
		sk_msg_free_elem(sk, msg, i, charge);
		sk_msg_iter_var_next(i);
		sk_msg_check_to_free(msg, i, bytes);
	}
	msg->sg.start = i;
}

void sk_msg_free_partial(struct sock *sk, struct sk_msg *msg, u32 bytes)
{
	__sk_msg_free_partial(sk, msg, bytes, true);
}
EXPORT_SYMBOL_GPL(sk_msg_free_partial);

void sk_msg_free_partial_nocharge(struct sock *sk, struct sk_msg *msg,
				  u32 bytes)
{
	__sk_msg_free_partial(sk, msg, bytes, false);
}

void sk_msg_trim(struct sock *sk, struct sk_msg *msg, int len)
{
	int trim = msg->sg.size - len;
	u32 i = msg->sg.end;

	if (trim <= 0) {
		WARN_ON(trim < 0);
		return;
	}

	sk_msg_iter_var_prev(i);
	msg->sg.size = len;
	while (msg->sg.data[i].length &&
	       trim >= msg->sg.data[i].length) {
		trim -= msg->sg.data[i].length;
		sk_msg_free_elem(sk, msg, i, true);
		sk_msg_iter_var_prev(i);
		if (!trim)
			goto out;
	}

	msg->sg.data[i].length -= trim;
	sk_mem_uncharge(sk, trim);
276 277 278
	/* Adjust copybreak if it falls into the trimmed part of last buf */
	if (msg->sg.curr == i && msg->sg.copybreak > msg->sg.data[i].length)
		msg->sg.copybreak = msg->sg.data[i].length;
279
out:
280 281 282 283 284 285
	sk_msg_iter_var_next(i);
	msg->sg.end = i;

	/* If we trim data a full sg elem before curr pointer update
	 * copybreak and current so that any future copy operations
	 * start at new copy location.
286 287 288
	 * However trimed data that has not yet been used in a copy op
	 * does not require an update.
	 */
289 290 291 292 293 294
	if (!msg->sg.size) {
		msg->sg.curr = msg->sg.start;
		msg->sg.copybreak = 0;
	} else if (sk_msg_iter_dist(msg->sg.start, msg->sg.curr) >=
		   sk_msg_iter_dist(msg->sg.start, msg->sg.end)) {
		sk_msg_iter_var_prev(i);
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
		msg->sg.curr = i;
		msg->sg.copybreak = msg->sg.data[i].length;
	}
}
EXPORT_SYMBOL_GPL(sk_msg_trim);

int sk_msg_zerocopy_from_iter(struct sock *sk, struct iov_iter *from,
			      struct sk_msg *msg, u32 bytes)
{
	int i, maxpages, ret = 0, num_elems = sk_msg_elem_used(msg);
	const int to_max_pages = MAX_MSG_FRAGS;
	struct page *pages[MAX_MSG_FRAGS];
	ssize_t orig, copied, use, offset;

	orig = msg->sg.size;
	while (bytes > 0) {
		i = 0;
		maxpages = to_max_pages - num_elems;
		if (maxpages == 0) {
			ret = -EFAULT;
			goto out;
		}

		copied = iov_iter_get_pages(from, pages, bytes, maxpages,
					    &offset);
		if (copied <= 0) {
			ret = -EFAULT;
			goto out;
		}

		iov_iter_advance(from, copied);
		bytes -= copied;
		msg->sg.size += copied;

		while (copied) {
			use = min_t(int, copied, PAGE_SIZE - offset);
			sg_set_page(&msg->sg.data[msg->sg.end],
				    pages[i], use, offset);
			sg_unmark_end(&msg->sg.data[msg->sg.end]);
			sk_mem_charge(sk, use);

			offset = 0;
			copied -= use;
			sk_msg_iter_next(msg, end);
			num_elems++;
			i++;
		}
		/* When zerocopy is mixed with sk_msg_*copy* operations we
		 * may have a copybreak set in this case clear and prefer
		 * zerocopy remainder when possible.
		 */
		msg->sg.copybreak = 0;
		msg->sg.curr = msg->sg.end;
	}
out:
	/* Revert iov_iter updates, msg will need to use 'trim' later if it
	 * also needs to be cleared.
	 */
	if (ret)
		iov_iter_revert(from, msg->sg.size - orig);
	return ret;
}
EXPORT_SYMBOL_GPL(sk_msg_zerocopy_from_iter);

int sk_msg_memcopy_from_iter(struct sock *sk, struct iov_iter *from,
			     struct sk_msg *msg, u32 bytes)
{
	int ret = -ENOSPC, i = msg->sg.curr;
	struct scatterlist *sge;
	u32 copy, buf_size;
	void *to;

	do {
		sge = sk_msg_elem(msg, i);
		/* This is possible if a trim operation shrunk the buffer */
		if (msg->sg.copybreak >= sge->length) {
			msg->sg.copybreak = 0;
			sk_msg_iter_var_next(i);
			if (i == msg->sg.end)
				break;
			sge = sk_msg_elem(msg, i);
		}

		buf_size = sge->length - msg->sg.copybreak;
		copy = (buf_size > bytes) ? bytes : buf_size;
		to = sg_virt(sge) + msg->sg.copybreak;
		msg->sg.copybreak += copy;
		if (sk->sk_route_caps & NETIF_F_NOCACHE_COPY)
			ret = copy_from_iter_nocache(to, copy, from);
		else
			ret = copy_from_iter(to, copy, from);
		if (ret != copy) {
			ret = -EFAULT;
			goto out;
		}
		bytes -= copy;
		if (!bytes)
			break;
		msg->sg.copybreak = 0;
		sk_msg_iter_var_next(i);
	} while (i != msg->sg.end);
out:
	msg->sg.curr = i;
	return ret;
}
EXPORT_SYMBOL_GPL(sk_msg_memcopy_from_iter);

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
/* Receive sk_msg from psock->ingress_msg to @msg. */
int sk_msg_recvmsg(struct sock *sk, struct sk_psock *psock, struct msghdr *msg,
		   int len, int flags)
{
	struct iov_iter *iter = &msg->msg_iter;
	int peek = flags & MSG_PEEK;
	struct sk_msg *msg_rx;
	int i, copied = 0;

	msg_rx = sk_psock_peek_msg(psock);
	while (copied != len) {
		struct scatterlist *sge;

		if (unlikely(!msg_rx))
			break;

		i = msg_rx->sg.start;
		do {
			struct page *page;
			int copy;

			sge = sk_msg_elem(msg_rx, i);
			copy = sge->length;
			page = sg_page(sge);
			if (copied + copy > len)
				copy = len - copied;
			copy = copy_page_to_iter(page, sge->offset, copy, iter);
			if (!copy)
				return copied ? copied : -EFAULT;

			copied += copy;
			if (likely(!peek)) {
				sge->offset += copy;
				sge->length -= copy;
				if (!msg_rx->skb)
					sk_mem_uncharge(sk, copy);
				msg_rx->sg.size -= copy;

				if (!sge->length) {
					sk_msg_iter_var_next(i);
					if (!msg_rx->skb)
						put_page(page);
				}
			} else {
				/* Lets not optimize peek case if copy_page_to_iter
				 * didn't copy the entire length lets just break.
				 */
				if (copy != sge->length)
					return copied;
				sk_msg_iter_var_next(i);
			}

			if (copied == len)
				break;
		} while (i != msg_rx->sg.end);

		if (unlikely(peek)) {
			msg_rx = sk_psock_next_msg(psock, msg_rx);
			if (!msg_rx)
				break;
			continue;
		}

		msg_rx->sg.start = i;
		if (!sge->length && msg_rx->sg.start == msg_rx->sg.end) {
			msg_rx = sk_psock_dequeue_msg(psock);
			kfree_sk_msg(msg_rx);
		}
		msg_rx = sk_psock_peek_msg(psock);
	}

	return copied;
}
EXPORT_SYMBOL_GPL(sk_msg_recvmsg);

477 478 479 480 481 482 483 484 485 486 487 488 489 490
bool sk_msg_is_readable(struct sock *sk)
{
	struct sk_psock *psock;
	bool empty = true;

	rcu_read_lock();
	psock = sk_psock(sk);
	if (likely(psock))
		empty = list_empty(&psock->ingress_msg);
	rcu_read_unlock();
	return !empty;
}
EXPORT_SYMBOL_GPL(sk_msg_is_readable);

491 492
static struct sk_msg *sk_psock_create_ingress_msg(struct sock *sk,
						  struct sk_buff *skb)
493 494 495
{
	struct sk_msg *msg;

496
	if (atomic_read(&sk->sk_rmem_alloc) > sk->sk_rcvbuf)
497 498 499 500
		return NULL;

	if (!sk_rmem_schedule(sk, skb, skb->truesize))
		return NULL;
501

502
	msg = kzalloc(sizeof(*msg), __GFP_NOWARN | GFP_KERNEL);
503
	if (unlikely(!msg))
504
		return NULL;
505 506

	sk_msg_init(msg);
507 508 509 510
	return msg;
}

static int sk_psock_skb_ingress_enqueue(struct sk_buff *skb,
511
					u32 off, u32 len,
512 513 514 515
					struct sk_psock *psock,
					struct sock *sk,
					struct sk_msg *msg)
{
516
	int num_sge, copied;
517

518 519 520 521 522 523 524
	/* skb linearize may fail with ENOMEM, but lets simply try again
	 * later if this happens. Under memory pressure we don't want to
	 * drop the skb. We need to linearize the skb so that the mapping
	 * in skb_to_sgvec can not error.
	 */
	if (skb_linearize(skb))
		return -EAGAIN;
525
	num_sge = skb_to_sgvec(skb, msg->sg.data, off, len);
526
	if (unlikely(num_sge < 0))
527 528
		return num_sge;

529
	copied = len;
530
	msg->sg.start = 0;
531
	msg->sg.size = copied;
532
	msg->sg.end = num_sge;
533 534 535
	msg->skb = skb;

	sk_psock_queue_msg(psock, msg);
536
	sk_psock_data_ready(sk, psock);
537 538 539
	return copied;
}

540 541
static int sk_psock_skb_ingress_self(struct sk_psock *psock, struct sk_buff *skb,
				     u32 off, u32 len);
542

543 544
static int sk_psock_skb_ingress(struct sk_psock *psock, struct sk_buff *skb,
				u32 off, u32 len)
545 546 547
{
	struct sock *sk = psock->sk;
	struct sk_msg *msg;
548
	int err;
549

550 551 552 553 554
	/* If we are receiving on the same sock skb->sk is already assigned,
	 * skip memory accounting and owner transition seeing it already set
	 * correctly.
	 */
	if (unlikely(skb->sk == sk))
555
		return sk_psock_skb_ingress_self(psock, skb, off, len);
556 557 558 559 560 561 562 563 564 565 566
	msg = sk_psock_create_ingress_msg(sk, skb);
	if (!msg)
		return -EAGAIN;

	/* This will transition ownership of the data from the socket where
	 * the BPF program was run initiating the redirect to the socket
	 * we will eventually receive this data on. The data will be released
	 * from skb_consume found in __tcp_bpf_recvmsg() after its been copied
	 * into user buffers.
	 */
	skb_set_owner_r(skb, sk);
567
	err = sk_psock_skb_ingress_enqueue(skb, off, len, psock, sk, msg);
568 569 570
	if (err < 0)
		kfree(msg);
	return err;
571 572 573 574 575 576
}

/* Puts an skb on the ingress queue of the socket already assigned to the
 * skb. In this case we do not need to check memory limits or skb_set_owner_r
 * because the skb is already accounted for here.
 */
577 578
static int sk_psock_skb_ingress_self(struct sk_psock *psock, struct sk_buff *skb,
				     u32 off, u32 len)
579 580 581
{
	struct sk_msg *msg = kzalloc(sizeof(*msg), __GFP_NOWARN | GFP_ATOMIC);
	struct sock *sk = psock->sk;
582
	int err;
583 584 585 586

	if (unlikely(!msg))
		return -EAGAIN;
	sk_msg_init(msg);
587
	skb_set_owner_r(skb, sk);
588
	err = sk_psock_skb_ingress_enqueue(skb, off, len, psock, sk, msg);
589 590 591
	if (err < 0)
		kfree(msg);
	return err;
592 593
}

594 595 596
static int sk_psock_handle_skb(struct sk_psock *psock, struct sk_buff *skb,
			       u32 off, u32 len, bool ingress)
{
597 598 599
	if (!ingress) {
		if (!sock_writeable(psock->sk))
			return -EAGAIN;
600
		return skb_send_sock(psock->sk, skb, off, len);
601
	}
602
	return sk_psock_skb_ingress(psock, skb, off, len);
603 604
}

605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620
static void sk_psock_skb_state(struct sk_psock *psock,
			       struct sk_psock_work_state *state,
			       struct sk_buff *skb,
			       int len, int off)
{
	spin_lock_bh(&psock->ingress_lock);
	if (sk_psock_test_state(psock, SK_PSOCK_TX_ENABLED)) {
		state->skb = skb;
		state->len = len;
		state->off = off;
	} else {
		sock_drop(psock->sk, skb);
	}
	spin_unlock_bh(&psock->ingress_lock);
}

621 622 623 624
static void sk_psock_backlog(struct work_struct *work)
{
	struct sk_psock *psock = container_of(work, struct sk_psock, work);
	struct sk_psock_work_state *state = &psock->work_state;
625
	struct sk_buff *skb = NULL;
626 627 628 629
	bool ingress;
	u32 len, off;
	int ret;

630
	mutex_lock(&psock->work_mutex);
631 632
	if (unlikely(state->skb)) {
		spin_lock_bh(&psock->ingress_lock);
633 634 635 636
		skb = state->skb;
		len = state->len;
		off = state->off;
		state->skb = NULL;
637
		spin_unlock_bh(&psock->ingress_lock);
638
	}
639 640
	if (skb)
		goto start;
641 642 643 644

	while ((skb = skb_dequeue(&psock->ingress_skb))) {
		len = skb->len;
		off = 0;
645 646 647 648 649 650
		if (skb_bpf_strparser(skb)) {
			struct strp_msg *stm = strp_msg(skb);

			off = stm->offset;
			len = stm->full_len;
		}
651
start:
652 653
		ingress = skb_bpf_ingress(skb);
		skb_bpf_redirect_clear(skb);
654 655
		do {
			ret = -EIO;
656
			if (!sock_flag(psock->sk, SOCK_DEAD))
657 658 659 660
				ret = sk_psock_handle_skb(psock, skb, off,
							  len, ingress);
			if (ret <= 0) {
				if (ret == -EAGAIN) {
661 662
					sk_psock_skb_state(psock, state, skb,
							   len, off);
663 664 665 666 667
					goto end;
				}
				/* Hard errors break pipe and stop xmit. */
				sk_psock_report_error(psock, ret ? -ret : EPIPE);
				sk_psock_clear_state(psock, SK_PSOCK_TX_ENABLED);
668
				sock_drop(psock->sk, skb);
669 670 671 672 673 674 675 676 677 678
				goto end;
			}
			off += ret;
			len -= ret;
		} while (len);

		if (!ingress)
			kfree_skb(skb);
	}
end:
679
	mutex_unlock(&psock->work_mutex);
680 681 682 683
}

struct sk_psock *sk_psock_init(struct sock *sk, int node)
{
684 685
	struct sk_psock *psock;
	struct proto *prot;
686

687 688 689 690 691 692 693 694 695 696 697 698 699 700
	write_lock_bh(&sk->sk_callback_lock);

	if (sk->sk_user_data) {
		psock = ERR_PTR(-EBUSY);
		goto out;
	}

	psock = kzalloc_node(sizeof(*psock), GFP_ATOMIC | __GFP_NOWARN, node);
	if (!psock) {
		psock = ERR_PTR(-ENOMEM);
		goto out;
	}

	prot = READ_ONCE(sk->sk_prot);
701
	psock->sk = sk;
702 703 704 705 706
	psock->eval = __SK_NONE;
	psock->sk_proto = prot;
	psock->saved_unhash = prot->unhash;
	psock->saved_close = prot->close;
	psock->saved_write_space = sk->sk_write_space;
707 708 709 710 711

	INIT_LIST_HEAD(&psock->link);
	spin_lock_init(&psock->link_lock);

	INIT_WORK(&psock->work, sk_psock_backlog);
712
	mutex_init(&psock->work_mutex);
713
	INIT_LIST_HEAD(&psock->ingress_msg);
714
	spin_lock_init(&psock->ingress_lock);
715 716 717 718 719
	skb_queue_head_init(&psock->ingress_skb);

	sk_psock_set_state(psock, SK_PSOCK_TX_ENABLED);
	refcount_set(&psock->refcnt, 1);

720
	rcu_assign_sk_user_data_nocopy(sk, psock);
721 722
	sock_hold(sk);

723 724
out:
	write_unlock_bh(&sk->sk_callback_lock);
725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741
	return psock;
}
EXPORT_SYMBOL_GPL(sk_psock_init);

struct sk_psock_link *sk_psock_link_pop(struct sk_psock *psock)
{
	struct sk_psock_link *link;

	spin_lock_bh(&psock->link_lock);
	link = list_first_entry_or_null(&psock->link, struct sk_psock_link,
					list);
	if (link)
		list_del(&link->list);
	spin_unlock_bh(&psock->link_lock);
	return link;
}

742
static void __sk_psock_purge_ingress_msg(struct sk_psock *psock)
743 744 745 746 747 748 749 750 751 752
{
	struct sk_msg *msg, *tmp;

	list_for_each_entry_safe(msg, tmp, &psock->ingress_msg, list) {
		list_del(&msg->list);
		sk_msg_free(psock->sk, msg);
		kfree(msg);
	}
}

753
static void __sk_psock_zap_ingress(struct sk_psock *psock)
754
{
755 756
	struct sk_buff *skb;

757
	while ((skb = skb_dequeue(&psock->ingress_skb)) != NULL) {
758
		skb_bpf_redirect_clear(skb);
759
		sock_drop(psock->sk, skb);
760
	}
761 762 763 764 765
	kfree_skb(psock->work_state.skb);
	/* We null the skb here to ensure that calls to sk_psock_backlog
	 * do not pick up the free'd skb.
	 */
	psock->work_state.skb = NULL;
766 767 768 769 770 771 772 773 774 775 776 777 778
	__sk_psock_purge_ingress_msg(psock);
}

static void sk_psock_link_destroy(struct sk_psock *psock)
{
	struct sk_psock_link *link, *tmp;

	list_for_each_entry_safe(link, tmp, &psock->link, list) {
		list_del(&link->list);
		sk_psock_free_link(link);
	}
}

779 780 781 782 783 784 785 786 787 788 789 790
void sk_psock_stop(struct sk_psock *psock, bool wait)
{
	spin_lock_bh(&psock->ingress_lock);
	sk_psock_clear_state(psock, SK_PSOCK_TX_ENABLED);
	sk_psock_cork_free(psock);
	__sk_psock_zap_ingress(psock);
	spin_unlock_bh(&psock->ingress_lock);

	if (wait)
		cancel_work_sync(&psock->work);
}

791 792
static void sk_psock_done_strp(struct sk_psock *psock);

793
static void sk_psock_destroy(struct work_struct *work)
794
{
795 796
	struct sk_psock *psock = container_of(to_rcu_work(work),
					      struct sk_psock, rwork);
797
	/* No sk_callback_lock since already detached. */
798

799
	sk_psock_done_strp(psock);
800 801

	cancel_work_sync(&psock->work);
802
	mutex_destroy(&psock->work_mutex);
803 804 805 806 807 808 809 810 811 812 813 814 815 816 817

	psock_progs_drop(&psock->progs);

	sk_psock_link_destroy(psock);
	sk_psock_cork_free(psock);

	if (psock->sk_redir)
		sock_put(psock->sk_redir);
	sock_put(psock->sk);
	kfree(psock);
}

void sk_psock_drop(struct sock *sk, struct sk_psock *psock)
{
	write_lock_bh(&sk->sk_callback_lock);
818 819
	sk_psock_restore_proto(sk, psock);
	rcu_assign_sk_user_data(sk, NULL);
820
	if (psock->progs.stream_parser)
821
		sk_psock_stop_strp(sk, psock);
822
	else if (psock->progs.stream_verdict || psock->progs.skb_verdict)
823
		sk_psock_stop_verdict(sk, psock);
824 825
	write_unlock_bh(&sk->sk_callback_lock);

826 827
	sk_psock_stop(psock, false);

828 829
	INIT_RCU_WORK(&psock->rwork, sk_psock_destroy);
	queue_rcu_work(system_wq, &psock->rwork);
830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860
}
EXPORT_SYMBOL_GPL(sk_psock_drop);

static int sk_psock_map_verd(int verdict, bool redir)
{
	switch (verdict) {
	case SK_PASS:
		return redir ? __SK_REDIRECT : __SK_PASS;
	case SK_DROP:
	default:
		break;
	}

	return __SK_DROP;
}

int sk_psock_msg_verdict(struct sock *sk, struct sk_psock *psock,
			 struct sk_msg *msg)
{
	struct bpf_prog *prog;
	int ret;

	rcu_read_lock();
	prog = READ_ONCE(psock->progs.msg_parser);
	if (unlikely(!prog)) {
		ret = __SK_PASS;
		goto out;
	}

	sk_msg_compute_data_pointers(msg);
	msg->sk = sk;
861
	ret = bpf_prog_run_pin_on_cpu(prog, msg);
862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879
	ret = sk_psock_map_verd(ret, msg->sk_redir);
	psock->apply_bytes = msg->apply_bytes;
	if (ret == __SK_REDIRECT) {
		if (psock->sk_redir)
			sock_put(psock->sk_redir);
		psock->sk_redir = msg->sk_redir;
		if (!psock->sk_redir) {
			ret = __SK_DROP;
			goto out;
		}
		sock_hold(psock->sk_redir);
	}
out:
	rcu_read_unlock();
	return ret;
}
EXPORT_SYMBOL_GPL(sk_psock_msg_verdict);

880
static int sk_psock_skb_redirect(struct sk_psock *from, struct sk_buff *skb)
881 882 883 884
{
	struct sk_psock *psock_other;
	struct sock *sk_other;

885
	sk_other = skb_bpf_redirect_fetch(skb);
886 887 888
	/* This error is a buggy BPF program, it returned a redirect
	 * return code, but then didn't set a redirect interface.
	 */
889
	if (unlikely(!sk_other)) {
890
		skb_bpf_redirect_clear(skb);
891
		sock_drop(from->sk, skb);
892
		return -EIO;
893 894
	}
	psock_other = sk_psock(sk_other);
895 896 897 898
	/* This error indicates the socket is being torn down or had another
	 * error that caused the pipe to break. We can't send a packet on
	 * a socket that is in this state so we drop the skb.
	 */
899
	if (!psock_other || sock_flag(sk_other, SOCK_DEAD)) {
900
		skb_bpf_redirect_clear(skb);
901
		sock_drop(from->sk, skb);
902
		return -EIO;
903 904 905 906
	}
	spin_lock_bh(&psock_other->ingress_lock);
	if (!sk_psock_test_state(psock_other, SK_PSOCK_TX_ENABLED)) {
		spin_unlock_bh(&psock_other->ingress_lock);
907
		skb_bpf_redirect_clear(skb);
908
		sock_drop(from->sk, skb);
909
		return -EIO;
910 911
	}

912 913
	skb_queue_tail(&psock_other->ingress_skb, skb);
	schedule_work(&psock_other->work);
914
	spin_unlock_bh(&psock_other->ingress_lock);
915
	return 0;
916 917
}

918 919
static void sk_psock_tls_verdict_apply(struct sk_buff *skb,
				       struct sk_psock *from, int verdict)
920 921 922
{
	switch (verdict) {
	case __SK_REDIRECT:
923
		sk_psock_skb_redirect(from, skb);
924 925 926 927 928 929 930 931 932 933 934 935 936 937
		break;
	case __SK_PASS:
	case __SK_DROP:
	default:
		break;
	}
}

int sk_psock_tls_strp_read(struct sk_psock *psock, struct sk_buff *skb)
{
	struct bpf_prog *prog;
	int ret = __SK_PASS;

	rcu_read_lock();
938
	prog = READ_ONCE(psock->progs.stream_verdict);
939
	if (likely(prog)) {
940
		skb->sk = psock->sk;
941 942
		skb_dst_drop(skb);
		skb_bpf_redirect_clear(skb);
943
		ret = bpf_prog_run_pin_on_cpu(prog, skb);
944
		ret = sk_psock_map_verd(ret, skb_bpf_redirect_fetch(skb));
945
		skb->sk = NULL;
946
	}
947
	sk_psock_tls_verdict_apply(skb, psock, ret);
948 949 950 951 952
	rcu_read_unlock();
	return ret;
}
EXPORT_SYMBOL_GPL(sk_psock_tls_strp_read);

953 954
static int sk_psock_verdict_apply(struct sk_psock *psock, struct sk_buff *skb,
				  int verdict)
955 956
{
	struct sock *sk_other;
957
	int err = 0;
958
	u32 len, off;
959

960
	switch (verdict) {
961
	case __SK_PASS:
962
		err = -EIO;
963 964 965
		sk_other = psock->sk;
		if (sock_flag(sk_other, SOCK_DEAD) ||
		    !sk_psock_test_state(psock, SK_PSOCK_TX_ENABLED)) {
966
			skb_bpf_redirect_clear(skb);
967 968 969
			goto out_free;
		}

970
		skb_bpf_set_ingress(skb);
971 972 973 974 975 976 977 978

		/* If the queue is empty then we can submit directly
		 * into the msg queue. If its not empty we have to
		 * queue work otherwise we may get OOO data. Otherwise,
		 * if sk_psock_skb_ingress errors will be handled by
		 * retrying later from workqueue.
		 */
		if (skb_queue_empty(&psock->ingress_skb)) {
979 980 981 982 983 984 985 986 987
			len = skb->len;
			off = 0;
			if (skb_bpf_strparser(skb)) {
				struct strp_msg *stm = strp_msg(skb);

				off = stm->offset;
				len = stm->full_len;
			}
			err = sk_psock_skb_ingress_self(psock, skb, off, len);
988 989
		}
		if (err < 0) {
990 991 992 993
			spin_lock_bh(&psock->ingress_lock);
			if (sk_psock_test_state(psock, SK_PSOCK_TX_ENABLED)) {
				skb_queue_tail(&psock->ingress_skb, skb);
				schedule_work(&psock->work);
994
				err = 0;
995 996
			}
			spin_unlock_bh(&psock->ingress_lock);
997 998 999 1000
			if (err < 0) {
				skb_bpf_redirect_clear(skb);
				goto out_free;
			}
1001
		}
1002
		break;
1003
	case __SK_REDIRECT:
1004
		err = sk_psock_skb_redirect(psock, skb);
1005
		break;
1006 1007 1008
	case __SK_DROP:
	default:
out_free:
1009
		sock_drop(psock->sk, skb);
1010
	}
1011 1012

	return err;
1013 1014
}

1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032
static void sk_psock_write_space(struct sock *sk)
{
	struct sk_psock *psock;
	void (*write_space)(struct sock *sk) = NULL;

	rcu_read_lock();
	psock = sk_psock(sk);
	if (likely(psock)) {
		if (sk_psock_test_state(psock, SK_PSOCK_TX_ENABLED))
			schedule_work(&psock->work);
		write_space = psock->saved_write_space;
	}
	rcu_read_unlock();
	if (write_space)
		write_space(sk);
}

#if IS_ENABLED(CONFIG_BPF_STREAM_PARSER)
1033 1034
static void sk_psock_strp_read(struct strparser *strp, struct sk_buff *skb)
{
1035
	struct sk_psock *psock;
1036 1037
	struct bpf_prog *prog;
	int ret = __SK_DROP;
1038
	struct sock *sk;
1039 1040

	rcu_read_lock();
1041 1042 1043
	sk = strp->sk;
	psock = sk_psock(sk);
	if (unlikely(!psock)) {
1044
		sock_drop(sk, skb);
1045 1046
		goto out;
	}
1047
	prog = READ_ONCE(psock->progs.stream_verdict);
1048
	if (likely(prog)) {
1049
		skb->sk = sk;
1050 1051
		skb_dst_drop(skb);
		skb_bpf_redirect_clear(skb);
1052
		ret = bpf_prog_run_pin_on_cpu(prog, skb);
1053 1054
		if (ret == SK_PASS)
			skb_bpf_set_strparser(skb);
1055
		ret = sk_psock_map_verd(ret, skb_bpf_redirect_fetch(skb));
1056
		skb->sk = NULL;
1057 1058
	}
	sk_psock_verdict_apply(psock, skb, ret);
1059
out:
1060
	rcu_read_unlock();
1061 1062 1063 1064 1065 1066 1067 1068 1069
}

static int sk_psock_strp_read_done(struct strparser *strp, int err)
{
	return err;
}

static int sk_psock_strp_parse(struct strparser *strp, struct sk_buff *skb)
{
1070
	struct sk_psock *psock = container_of(strp, struct sk_psock, strp);
1071 1072 1073 1074
	struct bpf_prog *prog;
	int ret = skb->len;

	rcu_read_lock();
1075
	prog = READ_ONCE(psock->progs.stream_parser);
1076 1077
	if (likely(prog)) {
		skb->sk = psock->sk;
1078
		ret = bpf_prog_run_pin_on_cpu(prog, skb);
1079 1080
		skb->sk = NULL;
	}
1081 1082 1083 1084 1085
	rcu_read_unlock();
	return ret;
}

/* Called with socket lock held. */
1086
static void sk_psock_strp_data_ready(struct sock *sk)
1087 1088 1089 1090 1091 1092
{
	struct sk_psock *psock;

	rcu_read_lock();
	psock = sk_psock(sk);
	if (likely(psock)) {
1093
		if (tls_sw_has_ctx_rx(sk)) {
1094
			psock->saved_data_ready(sk);
1095 1096
		} else {
			write_lock_bh(&sk->sk_callback_lock);
1097
			strp_data_ready(&psock->strp);
1098 1099
			write_unlock_bh(&sk->sk_callback_lock);
		}
1100 1101 1102 1103
	}
	rcu_read_unlock();
}

1104 1105 1106 1107 1108 1109 1110 1111
int sk_psock_init_strp(struct sock *sk, struct sk_psock *psock)
{
	static const struct strp_callbacks cb = {
		.rcv_msg	= sk_psock_strp_read,
		.read_sock_done	= sk_psock_strp_read_done,
		.parse_msg	= sk_psock_strp_parse,
	};

1112
	return strp_init(&psock->strp, sk, &cb);
1113 1114 1115 1116
}

void sk_psock_start_strp(struct sock *sk, struct sk_psock *psock)
{
1117
	if (psock->saved_data_ready)
1118 1119
		return;

1120
	psock->saved_data_ready = sk->sk_data_ready;
1121 1122 1123 1124 1125 1126
	sk->sk_data_ready = sk_psock_strp_data_ready;
	sk->sk_write_space = sk_psock_write_space;
}

void sk_psock_stop_strp(struct sock *sk, struct sk_psock *psock)
{
1127
	if (!psock->saved_data_ready)
1128 1129
		return;

1130 1131 1132
	sk->sk_data_ready = psock->saved_data_ready;
	psock->saved_data_ready = NULL;
	strp_stop(&psock->strp);
1133 1134 1135 1136 1137
}

static void sk_psock_done_strp(struct sk_psock *psock)
{
	/* Parser has been stopped */
1138
	if (psock->progs.stream_parser)
1139
		strp_done(&psock->strp);
1140 1141 1142 1143 1144 1145 1146
}
#else
static void sk_psock_done_strp(struct sk_psock *psock)
{
}
#endif /* CONFIG_BPF_STREAM_PARSER */

1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166
static int sk_psock_verdict_recv(read_descriptor_t *desc, struct sk_buff *skb,
				 unsigned int offset, size_t orig_len)
{
	struct sock *sk = (struct sock *)desc->arg.data;
	struct sk_psock *psock;
	struct bpf_prog *prog;
	int ret = __SK_DROP;
	int len = skb->len;

	/* clone here so sk_eat_skb() in tcp_read_sock does not drop our data */
	skb = skb_clone(skb, GFP_ATOMIC);
	if (!skb) {
		desc->error = -ENOMEM;
		return 0;
	}

	rcu_read_lock();
	psock = sk_psock(sk);
	if (unlikely(!psock)) {
		len = 0;
1167
		sock_drop(sk, skb);
1168 1169
		goto out;
	}
1170
	prog = READ_ONCE(psock->progs.stream_verdict);
1171 1172
	if (!prog)
		prog = READ_ONCE(psock->progs.skb_verdict);
1173
	if (likely(prog)) {
1174
		skb->sk = sk;
1175 1176
		skb_dst_drop(skb);
		skb_bpf_redirect_clear(skb);
1177
		ret = bpf_prog_run_pin_on_cpu(prog, skb);
1178
		ret = sk_psock_map_verd(ret, skb_bpf_redirect_fetch(skb));
1179
		skb->sk = NULL;
1180
	}
1181 1182
	if (sk_psock_verdict_apply(psock, skb, ret) < 0)
		len = 0;
1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204
out:
	rcu_read_unlock();
	return len;
}

static void sk_psock_verdict_data_ready(struct sock *sk)
{
	struct socket *sock = sk->sk_socket;
	read_descriptor_t desc;

	if (unlikely(!sock || !sock->ops || !sock->ops->read_sock))
		return;

	desc.arg.data = sk;
	desc.error = 0;
	desc.count = 1;

	sock->ops->read_sock(sk, &desc, sk_psock_verdict_recv);
}

void sk_psock_start_verdict(struct sock *sk, struct sk_psock *psock)
{
1205
	if (psock->saved_data_ready)
1206 1207
		return;

1208
	psock->saved_data_ready = sk->sk_data_ready;
1209 1210 1211 1212 1213 1214
	sk->sk_data_ready = sk_psock_verdict_data_ready;
	sk->sk_write_space = sk_psock_write_space;
}

void sk_psock_stop_verdict(struct sock *sk, struct sk_psock *psock)
{
1215
	if (!psock->saved_data_ready)
1216 1217
		return;

1218 1219
	sk->sk_data_ready = psock->saved_data_ready;
	psock->saved_data_ready = NULL;
1220
}