网络数据的接收

static int igb_clean_rx_irq(struct igb_q_vector *q_vector, const int budget)
{
	struct igb_adapter *adapter = q_vector->adapter;
	struct igb_ring *rx_ring = q_vector->rx.ring;
	struct sk_buff *skb = rx_ring->skb;
	unsigned int total_bytes = 0, total_packets = 0;
	u16 cleaned_count = igb_desc_unused(rx_ring);
	unsigned int xdp_xmit = 0;
	struct xdp_buff xdp;
	u32 frame_sz = 0;
	int rx_buf_pgcnt;

	/* Frame size depend on rx_ring setup when PAGE_SIZE=4K */
#if (PAGE_SIZE < 8192)
	frame_sz = igb_rx_frame_truesize(rx_ring, 0);
#endif
	xdp_init_buff(&xdp, frame_sz, &rx_ring->xdp_rxq);

	while (likely(total_packets < budget)) {
		union e1000_adv_rx_desc *rx_desc;
		struct igb_rx_buffer *rx_buffer;
		ktime_t timestamp = 0;
		int pkt_offset = 0;
		unsigned int size;
		void *pktbuf;

		/* return some buffers to hardware, one at a time is too slow */
		if (cleaned_count >= IGB_RX_BUFFER_WRITE) {
			igb_alloc_rx_buffers(rx_ring, cleaned_count);
			cleaned_count = 0;
		}

		rx_desc = IGB_RX_DESC(rx_ring, rx_ring->next_to_clean);
		size = le16_to_cpu(rx_desc->wb.upper.length);
		if (!size)
			break;

		/* This memory barrier is needed to keep us from reading
		 * any other fields out of the rx_desc until we know the
		 * descriptor has been written back
		 */
		dma_rmb();

		rx_buffer = igb_get_rx_buffer(rx_ring, size, &rx_buf_pgcnt);
		pktbuf = page_address(rx_buffer->page) + rx_buffer->page_offset;

		/* pull rx packet timestamp if available and valid */
		if (igb_test_staterr(rx_desc, E1000_RXDADV_STAT_TSIP)) {
			int ts_hdr_len;

			ts_hdr_len = igb_ptp_rx_pktstamp(rx_ring->q_vector,
							 pktbuf, &timestamp);

			pkt_offset += ts_hdr_len;
			size -= ts_hdr_len;
		}

		/* retrieve a buffer from the ring */
		if (!skb) {
			unsigned char *hard_start = pktbuf - igb_rx_offset(rx_ring);
			unsigned int offset = pkt_offset + igb_rx_offset(rx_ring);

			xdp_prepare_buff(&xdp, hard_start, offset, size, true);
			xdp_buff_clear_frags_flag(&xdp);
#if (PAGE_SIZE > 4096)
			/* At larger PAGE_SIZE, frame_sz depend on len size */
			xdp.frame_sz = igb_rx_frame_truesize(rx_ring, size);
#endif
			skb = igb_run_xdp(adapter, rx_ring, &xdp);
		}

		if (IS_ERR(skb)) {
			unsigned int xdp_res = -PTR_ERR(skb);

			if (xdp_res & (IGB_XDP_TX | IGB_XDP_REDIR)) {
				xdp_xmit |= xdp_res;
				igb_rx_buffer_flip(rx_ring, rx_buffer, size);
			} else {
				rx_buffer->pagecnt_bias++;
			}
			total_packets++;
			total_bytes += size;
		} else if (skb)
			igb_add_rx_frag(rx_ring, rx_buffer, skb, size);
		else if (ring_uses_build_skb(rx_ring))
			skb = igb_build_skb(rx_ring, rx_buffer, &xdp,
					    timestamp);
		else
			skb = igb_construct_skb(rx_ring, rx_buffer,
						&xdp, timestamp);

		/* exit if we failed to retrieve a buffer */
		if (!skb) {
			rx_ring->rx_stats.alloc_failed++;
			rx_buffer->pagecnt_bias++;
			break;
		}

		igb_put_rx_buffer(rx_ring, rx_buffer, rx_buf_pgcnt);
		cleaned_count++;

		/* fetch next buffer in frame if non-eop */
		if (igb_is_non_eop(rx_ring, rx_desc))
			continue;

		/* verify the packet layout is correct */
		if (igb_cleanup_headers(rx_ring, rx_desc, skb)) {
			skb = NULL;
			continue;
		}

		/* probably a little skewed due to removing CRC */
		total_bytes += skb->len;

		/* populate checksum, timestamp, VLAN, and protocol */
		igb_process_skb_fields(rx_ring, rx_desc, skb);

		napi_gro_receive(&q_vector->napi, skb);

		/* reset skb pointer */
		skb = NULL;

		/* update budget accounting */
		total_packets++;
	}

	/* place incomplete frames back on ring for completion */
	rx_ring->skb = skb;

	if (xdp_xmit & IGB_XDP_REDIR)
		xdp_do_flush();

	if (xdp_xmit & IGB_XDP_TX) {
		struct igb_ring *tx_ring = igb_xdp_tx_queue_mapping(adapter);

		igb_xdp_ring_update_tail(tx_ring);
	}

	u64_stats_update_begin(&rx_ring->rx_syncp);
	rx_ring->rx_stats.packets += total_packets;
	rx_ring->rx_stats.bytes += total_bytes;
	u64_stats_update_end(&rx_ring->rx_syncp);
	q_vector->rx.total_packets += total_packets;
	q_vector->rx.total_bytes += total_bytes;

	if (cleaned_count)
		igb_alloc_rx_buffers(rx_ring, cleaned_count);

	return total_packets;
}

gro_result_t napi_gro_receive(struct napi_struct *napi, struct sk_buff *skb)
{
	//...
	ret = napi_skb_finish(napi, skb, dev_gro_receive(napi, skb));
	//...
}

static gro_result_t napi_skb_finish(struct napi_struct *napi,
				    struct sk_buff *skb,
				    gro_result_t ret)
{
	//...
	gro_normal_one(napi, skb, 1);
	//..
}

static inline int deliver_skb(struct sk_buff *skb,
			      struct packet_type *pt_prev,
			      struct net_device *orig_dev)
{
	if (unlikely(skb_orphan_frags_rx(skb, GFP_ATOMIC)))
		return -ENOMEM;
	refcount_inc(&skb->users);
	return pt_prev->func(skb, skb->dev, pt_prev, orig_dev);
}

/*
 *	The list of packet types we will receive (as opposed to discard)
 *	and the routines to invoke.
 *
 *	Why 16. Because with 16 the only overlap we get on a hash of the
 *	low nibble of the protocol value is RARP/SNAP/X.25.
 *
 *		0800	IP
 *		0001	802.3
 *		0002	AX.25
 *		0004	802.2
 *		8035	RARP
 *		0005	SNAP
 *		0805	X.25
 *		0806	ARP
 *		8137	IPX
 *		0009	Localtalk
 *		86DD	IPv6
 */
#define PTYPE_HASH_SIZE	(16)
#define PTYPE_HASH_MASK	(PTYPE_HASH_SIZE - 1)

extern struct list_head ptype_all __read_mostly;
extern struct list_head ptype_base[PTYPE_HASH_SIZE] __read_mostly;

static struct packet_type ip_packet_type __read_mostly = {
	.type = cpu_to_be16(ETH_P_IP),
	.func = ip_rcv,
	.list_func = ip_list_rcv,
};

int ip_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt,
	   struct net_device *orig_dev)
{
	struct net *net = dev_net(dev);

	skb = ip_rcv_core(skb, net);
	if (skb == NULL)
		return NET_RX_DROP;

	return NF_HOOK(NFPROTO_IPV4, NF_INET_PRE_ROUTING,
		       net, NULL, skb, dev, NULL,
		       ip_rcv_finish);
}

static int ip_rcv_finish(struct net *net, struct sock *sk, struct sk_buff *skb)
{
	struct net_device *dev = skb->dev;
	int ret;

	/* if ingress device is enslaved to an L3 master device pass the
	 * skb to its handler for processing
	 */
	skb = l3mdev_ip_rcv(skb);
	if (!skb)
		return NET_RX_SUCCESS;

	ret = ip_rcv_finish_core(net, sk, skb, dev, NULL);
	if (ret != NET_RX_DROP)
		ret = dst_input(skb);
	return ret;
}

/* Input packet from network to transport.  */
static inline int dst_input(struct sk_buff *skb)
{
	return INDIRECT_CALL_INET(skb_dst(skb)->input,
				  ip6_input, ip_local_deliver, skb);
}

void ip_protocol_deliver_rcu(struct net *net, struct sk_buff *skb, int protocol)
{
	//...
	ret = INDIRECT_CALL_2(ipprot->handler, tcp_v4_rcv, udp_rcv, skb);
	//...
}

int tcp_v4_rcv(struct sk_buff *skb)
{
	//...
	bh_lock_sock_nested(sk);
	tcp_segs_in(tcp_sk(sk), skb);
	ret = 0;
	if (!sock_owned_by_user(sk)) {
		ret = tcp_v4_do_rcv(sk, skb);
	} else {
		if (tcp_add_backlog(sk, skb, &drop_reason))
			goto discard_and_relse;
	}
	bh_unlock_sock(sk);
	//...
}

static int tcp_recvmsg_locked(struct sock *sk, struct msghdr *msg, size_t len,
			      int flags, struct scm_timestamping_internal *tss,
			      int *cmsg_flags)
{
	struct tcp_sock *tp = tcp_sk(sk);
	int copied = 0;
	u32 peek_seq;
	u32 *seq;
	unsigned long used;
	int err;
	int target;		/* Read at least this many bytes */
	long timeo;
	struct sk_buff *skb, *last;
	u32 urg_hole = 0;

	err = -ENOTCONN;
	if (sk->sk_state == TCP_LISTEN)
		goto out;

	if (tp->recvmsg_inq) {
		*cmsg_flags = TCP_CMSG_INQ;
		msg->msg_get_inq = 1;
	}
	timeo = sock_rcvtimeo(sk, flags & MSG_DONTWAIT);

	/* Urgent data needs to be handled specially. */
	if (flags & MSG_OOB)
		goto recv_urg;

	if (unlikely(tp->repair)) {
		err = -EPERM;
		if (!(flags & MSG_PEEK))
			goto out;

		if (tp->repair_queue == TCP_SEND_QUEUE)
			goto recv_sndq;

		err = -EINVAL;
		if (tp->repair_queue == TCP_NO_QUEUE)
			goto out;

		/* 'common' recv queue MSG_PEEK-ing */
	}

	seq = &tp->copied_seq;
	if (flags & MSG_PEEK) {
		peek_seq = tp->copied_seq;
		seq = &peek_seq;
	}

	target = sock_rcvlowat(sk, flags & MSG_WAITALL, len);

	do {
		u32 offset;

		/* Are we at urgent data? Stop if we have read anything or have SIGURG pending. */
		if (unlikely(tp->urg_data) && tp->urg_seq == *seq) {
			if (copied)
				break;
			if (signal_pending(current)) {
				copied = timeo ? sock_intr_errno(timeo) : -EAGAIN;
				break;
			}
		}

		/* Next get a buffer. */

		last = skb_peek_tail(&sk->sk_receive_queue);
		skb_queue_walk(&sk->sk_receive_queue, skb) {
			last = skb;
			/* Now that we have two receive queues this
			 * shouldn't happen.
			 */
			if (WARN(before(*seq, TCP_SKB_CB(skb)->seq),
				 "TCP recvmsg seq # bug: copied %X, seq %X, rcvnxt %X, fl %X\n",
				 *seq, TCP_SKB_CB(skb)->seq, tp->rcv_nxt,
				 flags))
				break;

			offset = *seq - TCP_SKB_CB(skb)->seq;
			if (unlikely(TCP_SKB_CB(skb)->tcp_flags & TCPHDR_SYN)) {
				pr_err_once("%s: found a SYN, please report !\n", __func__);
				offset--;
			}
			if (offset < skb->len)
				goto found_ok_skb;
			if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN)
				goto found_fin_ok;
			WARN(!(flags & MSG_PEEK),
			     "TCP recvmsg seq # bug 2: copied %X, seq %X, rcvnxt %X, fl %X\n",
			     *seq, TCP_SKB_CB(skb)->seq, tp->rcv_nxt, flags);
		}

		/* Well, if we have backlog, try to process it now yet. */

		if (copied >= target && !READ_ONCE(sk->sk_backlog.tail))
			break;

		if (copied) {
			if (!timeo ||
			    sk->sk_err ||
			    sk->sk_state == TCP_CLOSE ||
			    (sk->sk_shutdown & RCV_SHUTDOWN) ||
			    signal_pending(current))
				break;
		} else {
			if (sock_flag(sk, SOCK_DONE))
				break;

			if (sk->sk_err) {
				copied = sock_error(sk);
				break;
			}

			if (sk->sk_shutdown & RCV_SHUTDOWN)
				break;

			if (sk->sk_state == TCP_CLOSE) {
				/* This occurs when user tries to read
				 * from never connected socket.
				 */
				copied = -ENOTCONN;
				break;
			}

			if (!timeo) {
				copied = -EAGAIN;
				break;
			}

			if (signal_pending(current)) {
				copied = sock_intr_errno(timeo);
				break;
			}
		}

		if (copied >= target) {
			/* Do not sleep, just process backlog. */
			__sk_flush_backlog(sk);
		} else {
			tcp_cleanup_rbuf(sk, copied);
			sk_wait_data(sk, &timeo, last);
		}

		if ((flags & MSG_PEEK) &&
		    (peek_seq - copied - urg_hole != tp->copied_seq)) {
			net_dbg_ratelimited("TCP(%s:%d): Application bug, race in MSG_PEEK\n",
					    current->comm,
					    task_pid_nr(current));
			peek_seq = tp->copied_seq;
		}
		continue;

found_ok_skb:
		/* Ok so how much can we use? */
		used = skb->len - offset;
		if (len < used)
			used = len;

		/* Do we have urgent data here? */
		if (unlikely(tp->urg_data)) {
			u32 urg_offset = tp->urg_seq - *seq;
			if (urg_offset < used) {
				if (!urg_offset) {
					if (!sock_flag(sk, SOCK_URGINLINE)) {
						WRITE_ONCE(*seq, *seq + 1);
						urg_hole++;
						offset++;
						used--;
						if (!used)
							goto skip_copy;
					}
				} else
					used = urg_offset;
			}
		}

		if (!(flags & MSG_TRUNC)) {
			err = skb_copy_datagram_msg(skb, offset, msg, used);
			if (err) {
				/* Exception. Bailout! */
				if (!copied)
					copied = -EFAULT;
				break;
			}
		}

		WRITE_ONCE(*seq, *seq + used);
		copied += used;
		len -= used;

		tcp_rcv_space_adjust(sk);

skip_copy:
		if (unlikely(tp->urg_data) && after(tp->copied_seq, tp->urg_seq)) {
			WRITE_ONCE(tp->urg_data, 0);
			tcp_fast_path_check(sk);
		}

		if (TCP_SKB_CB(skb)->has_rxtstamp) {
			tcp_update_recv_tstamps(skb, tss);
			*cmsg_flags |= TCP_CMSG_TS;
		}

		if (used + offset < skb->len)
			continue;

		if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN)
			goto found_fin_ok;
		if (!(flags & MSG_PEEK))
			tcp_eat_recv_skb(sk, skb);
		continue;

found_fin_ok:
		/* Process the FIN. */
		WRITE_ONCE(*seq, *seq + 1);
		if (!(flags & MSG_PEEK))
			tcp_eat_recv_skb(sk, skb);
		break;
	} while (len > 0);

	/* According to UNIX98, msg_name/msg_namelen are ignored
	 * on connected socket. I was just happy when found this 8) --ANK
	 */

	/* Clean up data we have read: This will do ACK frames. */
	tcp_cleanup_rbuf(sk, copied);
	return copied;

out:
	return err;

recv_urg:
	err = tcp_recv_urg(sk, msg, len, flags);
	goto out;

recv_sndq:
	err = tcp_peek_sndq(sk, msg, len);
	goto out;
}

/*
 * 	This should be easy, if there is something there we
 * 	return it, otherwise we block.
 */

int udp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int flags,
		int *addr_len)
{
	//...
	skb = __skb_recv_udp(sk, flags, &off, &err);
	if (!skb)
		return err;
	//...
	if (checksum_valid || udp_skb_csum_unnecessary(skb)) {
		if (udp_skb_is_linear(skb))
			err = copy_linear_skb(skb, copied, off, &msg->msg_iter);
		else
			err = skb_copy_datagram_msg(skb, off, msg, copied);
	} else {
		err = skb_copy_and_csum_datagram_msg(skb, off, msg);
		//...
	}
	//...
}

static ssize_t sock_read_iter(struct kiocb *iocb, struct iov_iter *to)
{
	//...
	res = sock_recvmsg(sock, &msg, msg.msg_flags);
	//...
}

SYSCALL_DEFINE4(recv, int, fd, void __user *, ubuf, size_t, size,
		unsigned int, flags)
{
	return __sys_recvfrom(fd, ubuf, size, flags, NULL, NULL);
}

SYSCALL_DEFINE6(recvfrom, int, fd, void __user *, ubuf, size_t, size,
		unsigned int, flags, struct sockaddr __user *, addr,
		int __user *, addr_len)
{
	return __sys_recvfrom(fd, ubuf, size, flags, addr, addr_len);
}

SYSCALL_DEFINE3(recvmsg, int, fd, struct user_msghdr __user *, msg,
		unsigned int, flags)
{
	return __sys_recvmsg(fd, msg, flags, true);
}

static inline int sock_recvmsg_nosec(struct socket *sock, struct msghdr *msg,
				     int flags)
{
	//...
	int ret = INDIRECT_CALL_INET(sock->ops->recvmsg, inet6_recvmsg,
				     inet_recvmsg, sock, msg,
				     msg_data_left(msg), flags);
	//...
}

int inet_recvmsg(struct socket *sock, struct msghdr *msg, size_t size,
		 int flags)
{
	//...
	err = INDIRECT_CALL_2(sk->sk_prot->recvmsg, tcp_recvmsg, udp_recvmsg,
			      sk, msg, size, flags, &addr_len);
	//...
}

int inet6_recvmsg(struct socket *sock, struct msghdr *msg, size_t size,
		  int flags)
{
	//...
	err = INDIRECT_CALL_2(prot->recvmsg, tcp_recvmsg, udpv6_recvmsg,
			      sk, msg, size, flags, &addr_len);
	//...
}