skmsg.c 28.3 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

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);
30
	u32 osize = msg->sg.size;
31 32 33 34 35 36 37 38
	int ret = 0;

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

39 40 41 42
		if (!sk_page_frag_refill(sk, pfrag)) {
			ret = -ENOMEM;
			goto msg_trim;
		}
43 44 45

		orig_offset = pfrag->offset;
		use = min_t(int, len, pfrag->size - orig_offset);
46 47 48 49
		if (!sk_wmem_schedule(sk, use)) {
			ret = -ENOMEM;
			goto msg_trim;
		}
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

		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;
79 80 81 82

msg_trim:
	sk_msg_trim(sk, msg, osize);
	return ret;
83 84 85
}
EXPORT_SYMBOL_GPL(sk_msg_alloc);

86 87 88 89 90
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);
91
	struct scatterlist *sgd = NULL;
92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107
	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;
108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123

		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;
		}

124 125 126 127 128 129 130 131 132 133 134 135 136
		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);

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
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;

182 183 184 185
	/* When the skb owns the memory we free it from consume_skb path. */
	if (!msg->skb) {
		if (charge)
			sk_mem_uncharge(sk, len);
186
		put_page(sg_page(sge));
187
	}
188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204
	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);
	}
205
	consume_skb(msg->skb);
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
	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);
285 286 287
	/* 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;
288
out:
289 290 291 292 293 294
	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.
295 296 297
	 * However trimed data that has not yet been used in a copy op
	 * does not require an update.
	 */
298 299 300 301 302 303
	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);
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
		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);

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
/* 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;
465
		} while (!sg_is_last(sge));
466 467 468 469 470 471 472 473 474

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

		msg_rx->sg.start = i;
475
		if (!sge->length && sg_is_last(sge)) {
476 477 478 479 480 481 482 483 484 485
			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);

486 487 488 489 490 491 492 493 494 495 496 497 498 499
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);

500
static struct sk_msg *alloc_sk_msg(void)
501 502 503
{
	struct sk_msg *msg;

504 505
	msg = kzalloc(sizeof(*msg), __GFP_NOWARN | GFP_KERNEL);
	if (unlikely(!msg))
506
		return NULL;
507 508 509
	sg_init_marker(msg->sg.data, NR_MSG_FRAG_IDS);
	return msg;
}
510

511 512 513 514
static struct sk_msg *sk_psock_create_ingress_msg(struct sock *sk,
						  struct sk_buff *skb)
{
	if (atomic_read(&sk->sk_rmem_alloc) > sk->sk_rcvbuf)
515
		return NULL;
516

517
	if (!sk_rmem_schedule(sk, skb, skb->truesize))
518
		return NULL;
519

520
	return alloc_sk_msg();
521 522 523
}

static int sk_psock_skb_ingress_enqueue(struct sk_buff *skb,
524
					u32 off, u32 len,
525 526 527 528
					struct sk_psock *psock,
					struct sock *sk,
					struct sk_msg *msg)
{
529
	int num_sge, copied;
530

531
	num_sge = skb_to_sgvec(skb, msg->sg.data, off, len);
532 533 534 535 536 537 538 539 540 541 542 543 544
	if (num_sge < 0) {
		/* 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;

		num_sge = skb_to_sgvec(skb, msg->sg.data, off, len);
		if (unlikely(num_sge < 0))
			return num_sge;
	}
545

546
	copied = len;
547
	msg->sg.start = 0;
548
	msg->sg.size = copied;
549
	msg->sg.end = num_sge;
550 551 552
	msg->skb = skb;

	sk_psock_queue_msg(psock, msg);
553
	sk_psock_data_ready(sk, psock);
554 555 556
	return copied;
}

557 558
static int sk_psock_skb_ingress_self(struct sk_psock *psock, struct sk_buff *skb,
				     u32 off, u32 len);
559

560 561
static int sk_psock_skb_ingress(struct sk_psock *psock, struct sk_buff *skb,
				u32 off, u32 len)
562 563 564
{
	struct sock *sk = psock->sk;
	struct sk_msg *msg;
565
	int err;
566

567 568 569 570 571
	/* 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))
572
		return sk_psock_skb_ingress_self(psock, skb, off, len);
573 574 575 576 577 578 579 580 581 582 583
	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);
584
	err = sk_psock_skb_ingress_enqueue(skb, off, len, psock, sk, msg);
585 586 587
	if (err < 0)
		kfree(msg);
	return err;
588 589 590 591 592 593
}

/* 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.
 */
594 595
static int sk_psock_skb_ingress_self(struct sk_psock *psock, struct sk_buff *skb,
				     u32 off, u32 len)
596
{
597
	struct sk_msg *msg = alloc_sk_msg();
598
	struct sock *sk = psock->sk;
599
	int err;
600 601 602

	if (unlikely(!msg))
		return -EAGAIN;
603
	skb_set_owner_r(skb, sk);
604
	err = sk_psock_skb_ingress_enqueue(skb, off, len, psock, sk, msg);
605 606 607
	if (err < 0)
		kfree(msg);
	return err;
608 609
}

610 611 612
static int sk_psock_handle_skb(struct sk_psock *psock, struct sk_buff *skb,
			       u32 off, u32 len, bool ingress)
{
613 614 615
	if (!ingress) {
		if (!sock_writeable(psock->sk))
			return -EAGAIN;
616
		return skb_send_sock(psock->sk, skb, off, len);
617
	}
618
	return sk_psock_skb_ingress(psock, skb, off, len);
619 620
}

621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636
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);
}

637 638 639 640
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;
641
	struct sk_buff *skb = NULL;
642 643 644 645
	bool ingress;
	u32 len, off;
	int ret;

646
	mutex_lock(&psock->work_mutex);
647 648
	if (unlikely(state->skb)) {
		spin_lock_bh(&psock->ingress_lock);
649 650 651 652
		skb = state->skb;
		len = state->len;
		off = state->off;
		state->skb = NULL;
653
		spin_unlock_bh(&psock->ingress_lock);
654
	}
655 656
	if (skb)
		goto start;
657 658 659 660

	while ((skb = skb_dequeue(&psock->ingress_skb))) {
		len = skb->len;
		off = 0;
661 662 663 664 665 666
		if (skb_bpf_strparser(skb)) {
			struct strp_msg *stm = strp_msg(skb);

			off = stm->offset;
			len = stm->full_len;
		}
667
start:
668 669
		ingress = skb_bpf_ingress(skb);
		skb_bpf_redirect_clear(skb);
670 671
		do {
			ret = -EIO;
672
			if (!sock_flag(psock->sk, SOCK_DEAD))
673 674 675 676
				ret = sk_psock_handle_skb(psock, skb, off,
							  len, ingress);
			if (ret <= 0) {
				if (ret == -EAGAIN) {
677 678
					sk_psock_skb_state(psock, state, skb,
							   len, off);
679 680 681 682 683
					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);
684
				sock_drop(psock->sk, skb);
685 686 687 688 689 690 691 692 693 694
				goto end;
			}
			off += ret;
			len -= ret;
		} while (len);

		if (!ingress)
			kfree_skb(skb);
	}
end:
695
	mutex_unlock(&psock->work_mutex);
696 697 698 699
}

struct sk_psock *sk_psock_init(struct sock *sk, int node)
{
700 701
	struct sk_psock *psock;
	struct proto *prot;
702

703 704
	write_lock_bh(&sk->sk_callback_lock);

705 706 707 708 709
	if (sk_is_inet(sk) && inet_csk_has_ulp(sk)) {
		psock = ERR_PTR(-EINVAL);
		goto out;
	}

710 711 712 713 714 715 716 717 718 719 720 721
	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);
722
	psock->sk = sk;
723 724 725
	psock->eval = __SK_NONE;
	psock->sk_proto = prot;
	psock->saved_unhash = prot->unhash;
726
	psock->saved_destroy = prot->destroy;
727 728
	psock->saved_close = prot->close;
	psock->saved_write_space = sk->sk_write_space;
729 730 731 732 733

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

	INIT_WORK(&psock->work, sk_psock_backlog);
734
	mutex_init(&psock->work_mutex);
735
	INIT_LIST_HEAD(&psock->ingress_msg);
736
	spin_lock_init(&psock->ingress_lock);
737 738 739 740 741
	skb_queue_head_init(&psock->ingress_skb);

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

742
	rcu_assign_sk_user_data_nocopy(sk, psock);
743 744
	sock_hold(sk);

745 746
out:
	write_unlock_bh(&sk->sk_callback_lock);
747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763
	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;
}

764
static void __sk_psock_purge_ingress_msg(struct sk_psock *psock)
765 766 767 768 769 770 771 772 773 774
{
	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);
	}
}

775
static void __sk_psock_zap_ingress(struct sk_psock *psock)
776
{
777 778
	struct sk_buff *skb;

779
	while ((skb = skb_dequeue(&psock->ingress_skb)) != NULL) {
780
		skb_bpf_redirect_clear(skb);
781
		sock_drop(psock->sk, skb);
782
	}
783 784 785 786 787
	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;
788 789 790 791 792 793 794 795 796 797 798 799 800
	__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);
	}
}

801 802 803 804 805 806 807 808 809 810 811 812
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);
}

813 814
static void sk_psock_done_strp(struct sk_psock *psock);

815
static void sk_psock_destroy(struct work_struct *work)
816
{
817 818
	struct sk_psock *psock = container_of(to_rcu_work(work),
					      struct sk_psock, rwork);
819
	/* No sk_callback_lock since already detached. */
820

821
	sk_psock_done_strp(psock);
822 823

	cancel_work_sync(&psock->work);
824
	mutex_destroy(&psock->work_mutex);
825 826 827 828 829 830 831 832 833 834 835 836 837 838 839

	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);
840 841
	sk_psock_restore_proto(sk, psock);
	rcu_assign_sk_user_data(sk, NULL);
842
	if (psock->progs.stream_parser)
843
		sk_psock_stop_strp(sk, psock);
844
	else if (psock->progs.stream_verdict || psock->progs.skb_verdict)
845
		sk_psock_stop_verdict(sk, psock);
846 847
	write_unlock_bh(&sk->sk_callback_lock);

848 849
	sk_psock_stop(psock, false);

850 851
	INIT_RCU_WORK(&psock->rwork, sk_psock_destroy);
	queue_rcu_work(system_wq, &psock->rwork);
852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882
}
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;
883
	ret = bpf_prog_run_pin_on_cpu(prog, msg);
884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901
	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);

902
static int sk_psock_skb_redirect(struct sk_psock *from, struct sk_buff *skb)
903 904 905 906
{
	struct sk_psock *psock_other;
	struct sock *sk_other;

907
	sk_other = skb_bpf_redirect_fetch(skb);
908 909 910
	/* This error is a buggy BPF program, it returned a redirect
	 * return code, but then didn't set a redirect interface.
	 */
911
	if (unlikely(!sk_other)) {
912
		skb_bpf_redirect_clear(skb);
913
		sock_drop(from->sk, skb);
914
		return -EIO;
915 916
	}
	psock_other = sk_psock(sk_other);
917 918 919 920
	/* 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.
	 */
921
	if (!psock_other || sock_flag(sk_other, SOCK_DEAD)) {
922
		skb_bpf_redirect_clear(skb);
923
		sock_drop(from->sk, skb);
924
		return -EIO;
925 926 927 928
	}
	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);
929
		skb_bpf_redirect_clear(skb);
930
		sock_drop(from->sk, skb);
931
		return -EIO;
932 933
	}

934 935
	skb_queue_tail(&psock_other->ingress_skb, skb);
	schedule_work(&psock_other->work);
936
	spin_unlock_bh(&psock_other->ingress_lock);
937
	return 0;
938 939
}

940 941
static void sk_psock_tls_verdict_apply(struct sk_buff *skb,
				       struct sk_psock *from, int verdict)
942 943 944
{
	switch (verdict) {
	case __SK_REDIRECT:
945
		sk_psock_skb_redirect(from, skb);
946 947 948 949 950 951 952 953 954 955 956 957 958 959
		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();
960
	prog = READ_ONCE(psock->progs.stream_verdict);
961
	if (likely(prog)) {
962
		skb->sk = psock->sk;
963 964
		skb_dst_drop(skb);
		skb_bpf_redirect_clear(skb);
965
		ret = bpf_prog_run_pin_on_cpu(prog, skb);
966
		ret = sk_psock_map_verd(ret, skb_bpf_redirect_fetch(skb));
967
		skb->sk = NULL;
968
	}
969
	sk_psock_tls_verdict_apply(skb, psock, ret);
970 971 972 973 974
	rcu_read_unlock();
	return ret;
}
EXPORT_SYMBOL_GPL(sk_psock_tls_strp_read);

975 976
static int sk_psock_verdict_apply(struct sk_psock *psock, struct sk_buff *skb,
				  int verdict)
977 978
{
	struct sock *sk_other;
979
	int err = 0;
980
	u32 len, off;
981

982
	switch (verdict) {
983
	case __SK_PASS:
984
		err = -EIO;
985 986 987
		sk_other = psock->sk;
		if (sock_flag(sk_other, SOCK_DEAD) ||
		    !sk_psock_test_state(psock, SK_PSOCK_TX_ENABLED)) {
988
			skb_bpf_redirect_clear(skb);
989 990 991
			goto out_free;
		}

992
		skb_bpf_set_ingress(skb);
993 994 995 996 997 998 999 1000

		/* 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)) {
1001 1002 1003 1004 1005 1006 1007 1008 1009
			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);
1010 1011
		}
		if (err < 0) {
1012 1013 1014 1015
			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);
1016
				err = 0;
1017 1018
			}
			spin_unlock_bh(&psock->ingress_lock);
1019 1020 1021 1022
			if (err < 0) {
				skb_bpf_redirect_clear(skb);
				goto out_free;
			}
1023
		}
1024
		break;
1025
	case __SK_REDIRECT:
1026
		err = sk_psock_skb_redirect(psock, skb);
1027
		break;
1028 1029 1030
	case __SK_DROP:
	default:
out_free:
1031
		sock_drop(psock->sk, skb);
1032
	}
1033 1034

	return err;
1035 1036
}

1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054
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)
1055 1056
static void sk_psock_strp_read(struct strparser *strp, struct sk_buff *skb)
{
1057
	struct sk_psock *psock;
1058 1059
	struct bpf_prog *prog;
	int ret = __SK_DROP;
1060
	struct sock *sk;
1061 1062

	rcu_read_lock();
1063 1064 1065
	sk = strp->sk;
	psock = sk_psock(sk);
	if (unlikely(!psock)) {
1066
		sock_drop(sk, skb);
1067 1068
		goto out;
	}
1069
	prog = READ_ONCE(psock->progs.stream_verdict);
1070
	if (likely(prog)) {
1071
		skb->sk = sk;
1072 1073
		skb_dst_drop(skb);
		skb_bpf_redirect_clear(skb);
1074
		ret = bpf_prog_run_pin_on_cpu(prog, skb);
1075 1076
		if (ret == SK_PASS)
			skb_bpf_set_strparser(skb);
1077
		ret = sk_psock_map_verd(ret, skb_bpf_redirect_fetch(skb));
1078
		skb->sk = NULL;
1079 1080
	}
	sk_psock_verdict_apply(psock, skb, ret);
1081
out:
1082
	rcu_read_unlock();
1083 1084 1085 1086 1087 1088 1089 1090 1091
}

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)
{
1092
	struct sk_psock *psock = container_of(strp, struct sk_psock, strp);
1093 1094 1095 1096
	struct bpf_prog *prog;
	int ret = skb->len;

	rcu_read_lock();
1097
	prog = READ_ONCE(psock->progs.stream_parser);
1098 1099
	if (likely(prog)) {
		skb->sk = psock->sk;
1100
		ret = bpf_prog_run_pin_on_cpu(prog, skb);
1101 1102
		skb->sk = NULL;
	}
1103 1104 1105 1106 1107
	rcu_read_unlock();
	return ret;
}

/* Called with socket lock held. */
1108
static void sk_psock_strp_data_ready(struct sock *sk)
1109 1110 1111 1112 1113 1114
{
	struct sk_psock *psock;

	rcu_read_lock();
	psock = sk_psock(sk);
	if (likely(psock)) {
1115
		if (tls_sw_has_ctx_rx(sk)) {
1116
			psock->saved_data_ready(sk);
1117 1118
		} else {
			write_lock_bh(&sk->sk_callback_lock);
1119
			strp_data_ready(&psock->strp);
1120 1121
			write_unlock_bh(&sk->sk_callback_lock);
		}
1122 1123 1124 1125
	}
	rcu_read_unlock();
}

1126 1127 1128 1129 1130 1131 1132 1133
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,
	};

1134
	return strp_init(&psock->strp, sk, &cb);
1135 1136 1137 1138
}

void sk_psock_start_strp(struct sock *sk, struct sk_psock *psock)
{
1139
	if (psock->saved_data_ready)
1140 1141
		return;

1142
	psock->saved_data_ready = sk->sk_data_ready;
1143 1144 1145 1146 1147 1148
	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)
{
1149 1150
	psock_set_prog(&psock->progs.stream_parser, NULL);

1151
	if (!psock->saved_data_ready)
1152 1153
		return;

1154 1155 1156
	sk->sk_data_ready = psock->saved_data_ready;
	psock->saved_data_ready = NULL;
	strp_stop(&psock->strp);
1157 1158 1159 1160 1161
}

static void sk_psock_done_strp(struct sk_psock *psock)
{
	/* Parser has been stopped */
1162
	if (psock->progs.stream_parser)
1163
		strp_done(&psock->strp);
1164 1165 1166 1167 1168 1169 1170
}
#else
static void sk_psock_done_strp(struct sk_psock *psock)
{
}
#endif /* CONFIG_BPF_STREAM_PARSER */

1171
static int sk_psock_verdict_recv(struct sock *sk, struct sk_buff *skb)
1172 1173 1174 1175
{
	struct sk_psock *psock;
	struct bpf_prog *prog;
	int ret = __SK_DROP;
1176
	int len = skb->len;
1177

1178
	skb_get(skb);
1179 1180 1181 1182 1183

	rcu_read_lock();
	psock = sk_psock(sk);
	if (unlikely(!psock)) {
		len = 0;
1184
		sock_drop(sk, skb);
1185 1186
		goto out;
	}
1187
	prog = READ_ONCE(psock->progs.stream_verdict);
1188 1189
	if (!prog)
		prog = READ_ONCE(psock->progs.skb_verdict);
1190
	if (likely(prog)) {
1191 1192
		skb_dst_drop(skb);
		skb_bpf_redirect_clear(skb);
1193
		ret = bpf_prog_run_pin_on_cpu(prog, skb);
1194
		ret = sk_psock_map_verd(ret, skb_bpf_redirect_fetch(skb));
1195
	}
1196 1197
	if (sk_psock_verdict_apply(psock, skb, ret) < 0)
		len = 0;
1198 1199 1200 1201 1202 1203 1204 1205 1206
out:
	rcu_read_unlock();
	return len;
}

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

1207
	if (unlikely(!sock || !sock->ops || !sock->ops->read_skb))
1208
		return;
1209
	sock->ops->read_skb(sk, sk_psock_verdict_recv);
1210 1211 1212 1213
}

void sk_psock_start_verdict(struct sock *sk, struct sk_psock *psock)
{
1214
	if (psock->saved_data_ready)
1215 1216
		return;

1217
	psock->saved_data_ready = sk->sk_data_ready;
1218 1219 1220 1221 1222 1223
	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)
{
1224 1225 1226
	psock_set_prog(&psock->progs.stream_verdict, NULL);
	psock_set_prog(&psock->progs.skb_verdict, NULL);

1227
	if (!psock->saved_data_ready)
1228 1229
		return;

1230 1231
	sk->sk_data_ready = psock->saved_data_ready;
	psock->saved_data_ready = NULL;
1232
}