Re: [PATCH v6 2/8] tcp: move buffers management functions to their own file

[Stefano Brivio <sbrivio@redhat.com>]

On Wed, 12 Jun 2024 17:47:28 +0200
Laurent Vivier <lvivier@redhat.com> wrote:

> Move all the TCP parts using internal buffers to tcp_buf.c
> and keep generic TCP management functions in tcp.c.
> Add tcp_internal.h to export needed functions from tcp.c and
> tcp_buf.h from tcp_buf.c
> 
> With this change we can use existing TCP functions with a
> different kind of memory storage as for instance the shared
> memory provided by the guest via vhost-user.
> 
> Signed-off-by: Laurent Vivier <lvivier@redhat.com>
> ---
> 
> Notes:
>     v5:
>       - as we export now tcp_l2_buf_fill_headers() move
>         also enum tcp_iov_part to tcp_internal.h
>     
>     v4:
>       - rename tcp_send_flag() and tcp_data_from_sock() to
>         tcp_buf_send_flag() and tcp_buf_data_from_sock()
> 
>  Makefile       |   5 +-
>  tcp.c          | 562 ++-----------------------------------------------
>  tcp_buf.c      | 513 ++++++++++++++++++++++++++++++++++++++++++++
>  tcp_buf.h      |  16 ++
>  tcp_internal.h |  96 +++++++++
>  5 files changed, 648 insertions(+), 544 deletions(-)
>  create mode 100644 tcp_buf.c
>  create mode 100644 tcp_buf.h
>  create mode 100644 tcp_internal.h
> 
> diff --git a/Makefile b/Makefile
> index e2180b599bdb..09fc461d087e 100644
> --- a/Makefile
> +++ b/Makefile
> @@ -47,7 +47,7 @@ FLAGS += -DDUAL_STACK_SOCKETS=$(DUAL_STACK_SOCKETS)
>  PASST_SRCS = arch.c arp.c checksum.c conf.c dhcp.c dhcpv6.c flow.c fwd.c \
>  	icmp.c igmp.c inany.c iov.c ip.c isolation.c lineread.c log.c mld.c \
>  	ndp.c netlink.c packet.c passt.c pasta.c pcap.c pif.c tap.c tcp.c \
> -	tcp_splice.c udp.c util.c
> +	tcp_buf.c tcp_splice.c udp.c util.c
>  QRAP_SRCS = qrap.c
>  SRCS = $(PASST_SRCS) $(QRAP_SRCS)
>  
> @@ -56,7 +56,8 @@ MANPAGES = passt.1 pasta.1 qrap.1
>  PASST_HEADERS = arch.h arp.h checksum.h conf.h dhcp.h dhcpv6.h flow.h fwd.h \
>  	flow_table.h icmp.h icmp_flow.h inany.h iov.h ip.h isolation.h \
>  	lineread.h log.h ndp.h netlink.h packet.h passt.h pasta.h pcap.h pif.h \
> -	siphash.h tap.h tcp.h tcp_conn.h tcp_splice.h udp.h util.h
> +	siphash.h tap.h tcp.h tcp_buf.h tcp_conn.h tcp_internal.h tcp_splice.h \
> +	udp.h util.h
>  HEADERS = $(PASST_HEADERS) seccomp.h
>  
>  C := \#include <linux/tcp.h>\nstruct tcp_info x = { .tcpi_snd_wnd = 0 };
> diff --git a/tcp.c b/tcp.c
> index 6800209d4122..875e318c925b 100644
> --- a/tcp.c
> +++ b/tcp.c
> @@ -302,28 +302,14 @@
>  #include "flow.h"
>  
>  #include "flow_table.h"
> -
> -#define TCP_FRAMES_MEM			128
> -#define TCP_FRAMES							\
> -	(c->mode == MODE_PASST ? TCP_FRAMES_MEM : 1)
> +#include "tcp_internal.h"
> +#include "tcp_buf.h"
>  
>  #define TCP_HASH_TABLE_LOAD		70		/* % */
>  #define TCP_HASH_TABLE_SIZE		(FLOW_MAX * 100 / TCP_HASH_TABLE_LOAD)
>  
> -#define MAX_WS				8
> -#define MAX_WINDOW			(1 << (16 + (MAX_WS)))
> -
>  /* MSS rounding: see SET_MSS() */
>  #define MSS_DEFAULT			536
> -#define MSS4				ROUND_DOWN(IP_MAX_MTU -		   \
> -						   sizeof(struct tcphdr) - \
> -						   sizeof(struct iphdr),   \
> -						   sizeof(uint32_t))
> -#define MSS6				ROUND_DOWN(IP_MAX_MTU -		   \
> -						   sizeof(struct tcphdr) - \
> -						   sizeof(struct ipv6hdr), \
> -						   sizeof(uint32_t))
> -
>  #define WINDOW_DEFAULT			14600		/* RFC 6928 */
>  #ifdef HAS_SND_WND
>  # define KERNEL_REPORTS_SND_WND(c)	((c)->tcp.kernel_snd_wnd)
> @@ -345,33 +331,10 @@
>   */
>  #define SOL_TCP				IPPROTO_TCP
>  
> -#define SEQ_LE(a, b)			((b) - (a) < MAX_WINDOW)
> -#define SEQ_LT(a, b)			((b) - (a) - 1 < MAX_WINDOW)
> -#define SEQ_GE(a, b)			((a) - (b) < MAX_WINDOW)
> -#define SEQ_GT(a, b)			((a) - (b) - 1 < MAX_WINDOW)
> -
> -#define FIN		(1 << 0)
> -#define SYN		(1 << 1)
> -#define RST		(1 << 2)
> -#define ACK		(1 << 4)
> -/* Flags for internal usage */
> -#define DUP_ACK		(1 << 5)
>  #define ACK_IF_NEEDED	0		/* See tcp_send_flag() */
>  
> -#define OPT_EOL		0
> -#define OPT_NOP		1
> -#define OPT_MSS		2
> -#define OPT_MSS_LEN	4
> -#define OPT_WS		3
> -#define OPT_WS_LEN	3
> -#define OPT_SACKP	4
> -#define OPT_SACK	5
> -#define OPT_TS		8
> -
>  #define TAPSIDE(conn_)	((conn_)->f.pif[1] == PIF_TAP)
>  
> -#define CONN_V4(conn)		(!!inany_v4(&(conn)->faddr))
> -#define CONN_V6(conn)		(!CONN_V4(conn))
>  #define CONN_IS_CLOSING(conn)						\
>  	(((conn)->events & ESTABLISHED) &&				\
>  	 ((conn)->events & (SOCK_FIN_RCVD | TAP_FIN_RCVD)))
> @@ -408,106 +371,7 @@ static int tcp_sock_ns		[NUM_PORTS][IP_VERSIONS];
>   */
>  static union inany_addr low_rtt_dst[LOW_RTT_TABLE_SIZE];
>  
> -/* Static buffers */
> -/**
> - * struct tcp_payload_t - TCP header and data to send segments with payload
> - * @th:		TCP header
> - * @data:	TCP data
> - */
> -struct tcp_payload_t {
> -	struct tcphdr th;
> -	uint8_t data[IP_MAX_MTU - sizeof(struct tcphdr)];
> -#ifdef __AVX2__
> -} __attribute__ ((packed, aligned(32)));    /* For AVX2 checksum routines */
> -#else
> -} __attribute__ ((packed, aligned(__alignof__(unsigned int))));
> -#endif
> -
> -/**
> - * struct tcp_flags_t - TCP header and data to send zero-length
> - *                      segments (flags)
> - * @th:		TCP header
> - * @opts	TCP options
> - */
> -struct tcp_flags_t {
> -	struct tcphdr th;
> -	char opts[OPT_MSS_LEN + OPT_WS_LEN + 1];
> -#ifdef __AVX2__
> -} __attribute__ ((packed, aligned(32)));
> -#else
> -} __attribute__ ((packed, aligned(__alignof__(unsigned int))));
> -#endif
> -
> -/* Ethernet header for IPv4 frames */
> -static struct ethhdr		tcp4_eth_src;
> -
> -static struct tap_hdr		tcp4_payload_tap_hdr[TCP_FRAMES_MEM];
> -/* IPv4 headers */
> -static struct iphdr		tcp4_payload_ip[TCP_FRAMES_MEM];
> -/* TCP segments with payload for IPv4 frames */
> -static struct tcp_payload_t	tcp4_payload[TCP_FRAMES_MEM];
> -
> -static_assert(MSS4 <= sizeof(tcp4_payload[0].data), "MSS4 is greater than 65516");
> -
> -/* References tracking the owner connection of frames in the tap outqueue */
> -static struct tcp_tap_conn *tcp4_frame_conns[TCP_FRAMES_MEM];
> -static unsigned int tcp4_payload_used;
> -
> -static struct tap_hdr		tcp4_flags_tap_hdr[TCP_FRAMES_MEM];
> -/* IPv4 headers for TCP segment without payload */
> -static struct iphdr		tcp4_flags_ip[TCP_FRAMES_MEM];
> -/* TCP segments without payload for IPv4 frames */
> -static struct tcp_flags_t	tcp4_flags[TCP_FRAMES_MEM];
> -
> -static unsigned int tcp4_flags_used;
> -
> -/* Ethernet header for IPv6 frames */
> -static struct ethhdr		tcp6_eth_src;
> -
> -static struct tap_hdr		tcp6_payload_tap_hdr[TCP_FRAMES_MEM];
> -/* IPv6 headers */
> -static struct ipv6hdr		tcp6_payload_ip[TCP_FRAMES_MEM];
> -/* TCP headers and data for IPv6 frames */
> -static struct tcp_payload_t	tcp6_payload[TCP_FRAMES_MEM];
> -
> -static_assert(MSS6 <= sizeof(tcp6_payload[0].data), "MSS6 is greater than 65516");
> -
> -/* References tracking the owner connection of frames in the tap outqueue */
> -static struct tcp_tap_conn *tcp6_frame_conns[TCP_FRAMES_MEM];
> -static unsigned int tcp6_payload_used;
> -
> -static struct tap_hdr		tcp6_flags_tap_hdr[TCP_FRAMES_MEM];
> -/* IPv6 headers for TCP segment without payload */
> -static struct ipv6hdr		tcp6_flags_ip[TCP_FRAMES_MEM];
> -/* TCP segment without payload for IPv6 frames */
> -static struct tcp_flags_t	tcp6_flags[TCP_FRAMES_MEM];
> -
> -static unsigned int tcp6_flags_used;
> -
> -/* recvmsg()/sendmsg() data for tap */
> -static char 		tcp_buf_discard		[MAX_WINDOW];
> -static struct iovec	iov_sock		[TCP_FRAMES_MEM + 1];
> -
> -/*
> - * enum tcp_iov_parts - I/O vector parts for one TCP frame
> - * @TCP_IOV_TAP		tap backend specific header
> - * @TCP_IOV_ETH		Ethernet header
> - * @TCP_IOV_IP		IP (v4/v6) header
> - * @TCP_IOV_PAYLOAD	IP payload (TCP header + data)
> - * @TCP_NUM_IOVS 	the number of entries in the iovec array
> - */
> -enum tcp_iov_parts {
> -	TCP_IOV_TAP	= 0,
> -	TCP_IOV_ETH	= 1,
> -	TCP_IOV_IP	= 2,
> -	TCP_IOV_PAYLOAD	= 3,
> -	TCP_NUM_IOVS
> -};
> -
> -static struct iovec	tcp4_l2_iov		[TCP_FRAMES_MEM][TCP_NUM_IOVS];
> -static struct iovec	tcp6_l2_iov		[TCP_FRAMES_MEM][TCP_NUM_IOVS];
> -static struct iovec	tcp4_l2_flags_iov	[TCP_FRAMES_MEM][TCP_NUM_IOVS];
> -static struct iovec	tcp6_l2_flags_iov	[TCP_FRAMES_MEM][TCP_NUM_IOVS];
> +char		tcp_buf_discard		[MAX_WINDOW];
>  
>  /* sendmsg() to socket */
>  static struct iovec	tcp_iov			[UIO_MAXIOV];
> @@ -552,14 +416,6 @@ static uint32_t tcp_conn_epoll_events(uint8_t events, uint8_t conn_flags)
>  	return EPOLLRDHUP;
>  }
>  
> -static void conn_flag_do(const struct ctx *c, struct tcp_tap_conn *conn,
> -			 unsigned long flag);
> -#define conn_flag(c, conn, flag)					\
> -	do {								\
> -		flow_trace(conn, "flag at %s:%i", __func__, __LINE__);	\
> -		conn_flag_do(c, conn, flag);				\
> -	} while (0)
> -
>  /**
>   * tcp_epoll_ctl() - Add/modify/delete epoll state from connection events
>   * @c:		Execution context
> @@ -671,8 +527,8 @@ static void tcp_timer_ctl(const struct ctx *c, struct tcp_tap_conn *conn)
>   * @conn:	Connection pointer
>   * @flag:	Flag to set, or ~flag to unset
>   */
> -static void conn_flag_do(const struct ctx *c, struct tcp_tap_conn *conn,
> -			 unsigned long flag)
> +void conn_flag_do(const struct ctx *c, struct tcp_tap_conn *conn,
> +		  unsigned long flag)
>  {
>  	if (flag & (flag - 1)) {
>  		int flag_index = fls(~flag);
> @@ -722,8 +578,8 @@ static void tcp_hash_remove(const struct ctx *c,
>   * @conn:	Connection pointer
>   * @event:	Connection event
>   */
> -static void conn_event_do(const struct ctx *c, struct tcp_tap_conn *conn,
> -			  unsigned long event)
> +void conn_event_do(const struct ctx *c, struct tcp_tap_conn *conn,
> +		   unsigned long event)
>  {
>  	int prev, new, num = fls(event);
>  
> @@ -771,12 +627,6 @@ static void conn_event_do(const struct ctx *c, struct tcp_tap_conn *conn,
>  		tcp_timer_ctl(c, conn);
>  }
>  
> -#define conn_event(c, conn, event)					\
> -	do {								\
> -		flow_trace(conn, "event at %s:%i", __func__, __LINE__);	\
> -		conn_event_do(c, conn, event);				\
> -	} while (0)
> -
>  /**
>   * tcp_rtt_dst_low() - Check if low RTT was seen for connection endpoint
>   * @conn:	Connection pointer
> @@ -906,104 +756,6 @@ static void tcp_update_check_tcp6(struct ipv6hdr *ip6h, struct tcphdr *th)
>  	th->check = csum(th, l4len, sum);
>  }
>  
> -/**
> - * tcp_update_l2_buf() - Update Ethernet header buffers with addresses
> - * @eth_d:	Ethernet destination address, NULL if unchanged
> - * @eth_s:	Ethernet source address, NULL if unchanged
> - */
> -void tcp_update_l2_buf(const unsigned char *eth_d, const unsigned char *eth_s)
> -{
> -	eth_update_mac(&tcp4_eth_src, eth_d, eth_s);
> -	eth_update_mac(&tcp6_eth_src, eth_d, eth_s);
> -}
> -
> -/**
> - * tcp_sock4_iov_init() - Initialise scatter-gather L2 buffers for IPv4 sockets
> - * @c:		Execution context
> - */
> -static void tcp_sock4_iov_init(const struct ctx *c)
> -{
> -	struct iphdr iph = L2_BUF_IP4_INIT(IPPROTO_TCP);
> -	struct iovec *iov;
> -	int i;
> -
> -	tcp4_eth_src.h_proto = htons_constant(ETH_P_IP);
> -
> -	for (i = 0; i < ARRAY_SIZE(tcp4_payload); i++) {
> -		tcp4_payload_ip[i] = iph;
> -		tcp4_payload[i].th.doff = sizeof(struct tcphdr) / 4;
> -		tcp4_payload[i].th.ack = 1;
> -	}
> -
> -	for (i = 0; i < ARRAY_SIZE(tcp4_flags); i++) {
> -		tcp4_flags_ip[i] = iph;
> -		tcp4_flags[i].th.doff = sizeof(struct tcphdr) / 4;
> -		tcp4_flags[i].th.ack = 1;
> -	}
> -
> -	for (i = 0; i < TCP_FRAMES_MEM; i++) {
> -		iov = tcp4_l2_iov[i];
> -
> -		iov[TCP_IOV_TAP] = tap_hdr_iov(c, &tcp4_payload_tap_hdr[i]);
> -		iov[TCP_IOV_ETH] = IOV_OF_LVALUE(tcp4_eth_src);
> -		iov[TCP_IOV_IP] = IOV_OF_LVALUE(tcp4_payload_ip[i]);
> -		iov[TCP_IOV_PAYLOAD].iov_base = &tcp4_payload[i];
> -	}
> -
> -	for (i = 0; i < TCP_FRAMES_MEM; i++) {
> -		iov = tcp4_l2_flags_iov[i];
> -
> -		iov[TCP_IOV_TAP] = tap_hdr_iov(c, &tcp4_flags_tap_hdr[i]);
> -		iov[TCP_IOV_ETH].iov_base = &tcp4_eth_src;
> -		iov[TCP_IOV_ETH] = IOV_OF_LVALUE(tcp4_eth_src);
> -		iov[TCP_IOV_IP] = IOV_OF_LVALUE(tcp4_flags_ip[i]);
> -		iov[TCP_IOV_PAYLOAD].iov_base = &tcp4_flags[i];
> -	}
> -}
> -
> -/**
> - * tcp_sock6_iov_init() - Initialise scatter-gather L2 buffers for IPv6 sockets
> - * @c:		Execution context
> - */
> -static void tcp_sock6_iov_init(const struct ctx *c)
> -{
> -	struct ipv6hdr ip6 = L2_BUF_IP6_INIT(IPPROTO_TCP);
> -	struct iovec *iov;
> -	int i;
> -
> -	tcp6_eth_src.h_proto = htons_constant(ETH_P_IPV6);
> -
> -	for (i = 0; i < ARRAY_SIZE(tcp6_payload); i++) {
> -		tcp6_payload_ip[i] = ip6;
> -		tcp6_payload[i].th.doff = sizeof(struct tcphdr) / 4;
> -		tcp6_payload[i].th.ack = 1;
> -	}
> -
> -	for (i = 0; i < ARRAY_SIZE(tcp6_flags); i++) {
> -		tcp6_flags_ip[i] = ip6;
> -		tcp6_flags[i].th.doff = sizeof(struct tcphdr) / 4;
> -		tcp6_flags[i].th .ack = 1;
> -	}
> -
> -	for (i = 0; i < TCP_FRAMES_MEM; i++) {
> -		iov = tcp6_l2_iov[i];
> -
> -		iov[TCP_IOV_TAP] = tap_hdr_iov(c, &tcp6_payload_tap_hdr[i]);
> -		iov[TCP_IOV_ETH] = IOV_OF_LVALUE(tcp6_eth_src);
> -		iov[TCP_IOV_IP] = IOV_OF_LVALUE(tcp6_payload_ip[i]);
> -		iov[TCP_IOV_PAYLOAD].iov_base = &tcp6_payload[i];
> -	}
> -
> -	for (i = 0; i < TCP_FRAMES_MEM; i++) {
> -		iov = tcp6_l2_flags_iov[i];
> -
> -		iov[TCP_IOV_TAP] = tap_hdr_iov(c, &tcp6_flags_tap_hdr[i]);
> -		iov[TCP_IOV_ETH] = IOV_OF_LVALUE(tcp6_eth_src);
> -		iov[TCP_IOV_IP] = IOV_OF_LVALUE(tcp6_flags_ip[i]);
> -		iov[TCP_IOV_PAYLOAD].iov_base = &tcp6_flags[i];
> -	}
> -}
> -
>  /**
>   * tcp_opt_get() - Get option, and value if any, from TCP header
>   * @opts:	Pointer to start of TCP options in header
> @@ -1227,76 +979,6 @@ bool tcp_flow_defer(const struct tcp_tap_conn *conn)
>  	return true;
>  }
>  
> -static void tcp_rst_do(struct ctx *c, struct tcp_tap_conn *conn);
> -#define tcp_rst(c, conn)						\
> -	do {								\
> -		flow_dbg((conn), "TCP reset at %s:%i", __func__, __LINE__); \
> -		tcp_rst_do(c, conn);					\
> -	} while (0)
> -
> -/**
> - * tcp_flags_flush() - Send out buffers for segments with no data (flags)
> - * @c:		Execution context
> - */
> -static void tcp_flags_flush(const struct ctx *c)
> -{
> -	tap_send_frames(c, &tcp6_l2_flags_iov[0][0], TCP_NUM_IOVS,
> -			tcp6_flags_used);
> -	tcp6_flags_used = 0;
> -
> -	tap_send_frames(c, &tcp4_l2_flags_iov[0][0], TCP_NUM_IOVS,
> -			tcp4_flags_used);
> -	tcp4_flags_used = 0;
> -}
> -
> -/**
> - * tcp_revert_seq() - Revert affected conn->seq_to_tap after failed transmission
> - * @conns:       Array of connection pointers corresponding to queued frames
> - * @frames:      Two-dimensional array containing queued frames with sub-iovs
> - * @num_frames:  Number of entries in the two arrays to be compared
> - */
> -static void tcp_revert_seq(struct tcp_tap_conn **conns, struct iovec (*frames)[TCP_NUM_IOVS],
> -			   int num_frames)
> -{
> -	int i;
> -
> -	for (i = 0; i < num_frames; i++) {
> -		const struct tcphdr *th = frames[i][TCP_IOV_PAYLOAD].iov_base;
> -		struct tcp_tap_conn *conn = conns[i];
> -		uint32_t seq = ntohl(th->seq);
> -
> -		if (SEQ_LE(conn->seq_to_tap, seq))
> -			continue;
> -
> -		conn->seq_to_tap = seq;
> -	}
> -}
> -
> -/**
> - * tcp_payload_flush() - Send out buffers for segments with data
> - * @c:		Execution context
> - */
> -static void tcp_payload_flush(const struct ctx *c)
> -{
> -	size_t m;
> -
> -	m = tap_send_frames(c, &tcp6_l2_iov[0][0], TCP_NUM_IOVS,
> -			    tcp6_payload_used);
> -	if (m != tcp6_payload_used) {
> -		tcp_revert_seq(&tcp6_frame_conns[m], &tcp6_l2_iov[m],
> -			       tcp6_payload_used - m);
> -	}
> -	tcp6_payload_used = 0;
> -
> -	m = tap_send_frames(c, &tcp4_l2_iov[0][0], TCP_NUM_IOVS,
> -			    tcp4_payload_used);
> -	if (m != tcp4_payload_used) {
> -		tcp_revert_seq(&tcp4_frame_conns[m], &tcp4_l2_iov[m],
> -			       tcp4_payload_used - m);
> -	}
> -	tcp4_payload_used = 0;
> -}
> -
>  /**
>   * tcp_defer_handler() - Handler for TCP deferred tasks
>   * @c:		Execution context
> @@ -1430,10 +1112,10 @@ static size_t tcp_fill_headers6(const struct ctx *c,
>   *
>   * Return: IP payload length, host order
>   */
> -static size_t tcp_l2_buf_fill_headers(const struct ctx *c,
> -				      const struct tcp_tap_conn *conn,
> -				      struct iovec *iov, size_t dlen,
> -				      const uint16_t *check, uint32_t seq)
> +size_t tcp_l2_buf_fill_headers(const struct ctx *c,
> +			       const struct tcp_tap_conn *conn,
> +			       struct iovec *iov, size_t dlen,
> +			       const uint16_t *check, uint32_t seq)
>  {
>  	const struct in_addr *a4 = inany_v4(&conn->faddr);
>  
> @@ -1459,8 +1141,8 @@ static size_t tcp_l2_buf_fill_headers(const struct ctx *c,
>   *
>   * Return: 1 if sequence or window were updated, 0 otherwise
>   */
> -static int tcp_update_seqack_wnd(const struct ctx *c, struct tcp_tap_conn *conn,
> -				 int force_seq, struct tcp_info *tinfo)
> +int tcp_update_seqack_wnd(const struct ctx *c, struct tcp_tap_conn *conn,
> +			  int force_seq, struct tcp_info *tinfo)
>  {
>  	uint32_t prev_wnd_to_tap = conn->wnd_to_tap << conn->ws_to_tap;
>  	uint32_t prev_ack_to_tap = conn->seq_ack_to_tap;
> @@ -1579,9 +1261,9 @@ static void tcp_update_seqack_from_tap(const struct ctx *c,
>   *	     0 if there is no flag to send
>   *	     1 otherwise
>   */
> -static int tcp_prepare_flags(struct ctx *c, struct tcp_tap_conn *conn,
> -			     int flags, struct tcphdr *th, char *data,
> -			     size_t *optlen)
> +int tcp_prepare_flags(struct ctx *c, struct tcp_tap_conn *conn,
> +		      int flags, struct tcphdr *th, char *data,
> +		      size_t *optlen)
>  {
>  	struct tcp_info tinfo = { 0 };
>  	socklen_t sl = sizeof(tinfo);
> @@ -1678,54 +1360,9 @@ static int tcp_prepare_flags(struct ctx *c, struct tcp_tap_conn *conn,
>   *
>   * Return: negative error code on connection reset, 0 otherwise
>   */
> -static int tcp_send_flag(struct ctx *c, struct tcp_tap_conn *conn, int flags)
> +int tcp_send_flag(struct ctx *c, struct tcp_tap_conn *conn, int flags)
>  {
> -	struct tcp_flags_t *payload;
> -	struct iovec *iov;
> -	size_t optlen;
> -	size_t l4len;
> -	int ret;
> -
> -	if (CONN_V4(conn))
> -		iov = tcp4_l2_flags_iov[tcp4_flags_used++];
> -	else
> -		iov = tcp6_l2_flags_iov[tcp6_flags_used++];
> -
> -	payload = iov[TCP_IOV_PAYLOAD].iov_base;
> -
> -	ret = tcp_prepare_flags(c, conn, flags, &payload->th,
> -				payload->opts, &optlen);
> -	if (ret <= 0)
> -		return ret;
> -
> -	l4len = tcp_l2_buf_fill_headers(c, conn, iov, optlen, NULL,
> -					conn->seq_to_tap);
> -	iov[TCP_IOV_PAYLOAD].iov_len = l4len;
> -
> -	if (flags & DUP_ACK) {
> -		struct iovec *dup_iov;
> -		int i;
> -
> -		if (CONN_V4(conn))
> -			dup_iov = tcp4_l2_flags_iov[tcp4_flags_used++];
> -		else
> -			dup_iov = tcp6_l2_flags_iov[tcp6_flags_used++];
> -
> -		for (i = 0; i < TCP_NUM_IOVS; i++)
> -			memcpy(dup_iov[i].iov_base, iov[i].iov_base,
> -			       iov[i].iov_len);
> -		dup_iov[TCP_IOV_PAYLOAD].iov_len = iov[TCP_IOV_PAYLOAD].iov_len;
> -	}
> -
> -	if (CONN_V4(conn)) {
> -		if (tcp4_flags_used > TCP_FRAMES_MEM - 2)
> -			tcp_flags_flush(c);
> -	} else {
> -		if (tcp6_flags_used > TCP_FRAMES_MEM - 2)
> -			tcp_flags_flush(c);
> -	}
> -
> -	return 0;
> +	return tcp_buf_send_flag(c, conn, flags);
>  }
>  
>  /**
> @@ -1733,7 +1370,7 @@ static int tcp_send_flag(struct ctx *c, struct tcp_tap_conn *conn, int flags)
>   * @c:		Execution context
>   * @conn:	Connection pointer
>   */
> -static void tcp_rst_do(struct ctx *c, struct tcp_tap_conn *conn)
> +void tcp_rst_do(struct ctx *c, struct tcp_tap_conn *conn)
>  {
>  	if (conn->events == CLOSED)
>  		return;
> @@ -2160,49 +1797,6 @@ static int tcp_sock_consume(const struct tcp_tap_conn *conn, uint32_t ack_seq)
>  	return 0;
>  }
>  
> -/**
> - * tcp_data_to_tap() - Finalise (queue) highest-numbered scatter-gather buffer
> - * @c:		Execution context
> - * @conn:	Connection pointer
> - * @dlen:	TCP payload length
> - * @no_csum:	Don't compute IPv4 checksum, use the one from previous buffer
> - * @seq:	Sequence number to be sent
> - */
> -static void tcp_data_to_tap(const struct ctx *c, struct tcp_tap_conn *conn,
> -			    ssize_t dlen, int no_csum, uint32_t seq)
> -{
> -	struct iovec *iov;
> -	size_t l4len;
> -
> -	conn->seq_to_tap = seq + dlen;
> -
> -	if (CONN_V4(conn)) {
> -		struct iovec *iov_prev = tcp4_l2_iov[tcp4_payload_used - 1];
> -		const uint16_t *check = NULL;
> -
> -		if (no_csum) {
> -			struct iphdr *iph = iov_prev[TCP_IOV_IP].iov_base;
> -			check = &iph->check;
> -		}
> -
> -		tcp4_frame_conns[tcp4_payload_used] = conn;
> -
> -		iov = tcp4_l2_iov[tcp4_payload_used++];
> -		l4len = tcp_l2_buf_fill_headers(c, conn, iov, dlen, check, seq);
> -		iov[TCP_IOV_PAYLOAD].iov_len = l4len;
> -		if (tcp4_payload_used > TCP_FRAMES_MEM - 1)
> -			tcp_payload_flush(c);
> -	} else if (CONN_V6(conn)) {
> -		tcp6_frame_conns[tcp6_payload_used] = conn;
> -
> -		iov = tcp6_l2_iov[tcp6_payload_used++];
> -		l4len = tcp_l2_buf_fill_headers(c, conn, iov, dlen, NULL, seq);
> -		iov[TCP_IOV_PAYLOAD].iov_len = l4len;
> -		if (tcp6_payload_used > TCP_FRAMES_MEM - 1)
> -			tcp_payload_flush(c);
> -	}
> -}
> -
>  /**
>   * tcp_data_from_sock() - Handle new data from socket, queue to tap, in window
>   * @c:		Execution context
> @@ -2214,123 +1808,7 @@ static void tcp_data_to_tap(const struct ctx *c, struct tcp_tap_conn *conn,
>   */
>  static int tcp_data_from_sock(struct ctx *c, struct tcp_tap_conn *conn)
>  {
> -	uint32_t wnd_scaled = conn->wnd_from_tap << conn->ws_from_tap;
> -	int fill_bufs, send_bufs = 0, last_len, iov_rem = 0;
> -	int sendlen, len, dlen, v4 = CONN_V4(conn);
> -	int s = conn->sock, i, ret = 0;
> -	struct msghdr mh_sock = { 0 };
> -	uint16_t mss = MSS_GET(conn);
> -	uint32_t already_sent, seq;
> -	struct iovec *iov;
> -
> -	already_sent = conn->seq_to_tap - conn->seq_ack_from_tap;
> -
> -	if (SEQ_LT(already_sent, 0)) {
> -		/* RFC 761, section 2.1. */
> -		flow_trace(conn, "ACK sequence gap: ACK for %u, sent: %u",
> -			   conn->seq_ack_from_tap, conn->seq_to_tap);
> -		conn->seq_to_tap = conn->seq_ack_from_tap;
> -		already_sent = 0;
> -	}
> -
> -	if (!wnd_scaled || already_sent >= wnd_scaled) {
> -		conn_flag(c, conn, STALLED);
> -		conn_flag(c, conn, ACK_FROM_TAP_DUE);
> -		return 0;
> -	}
> -
> -	/* Set up buffer descriptors we'll fill completely and partially. */
> -	fill_bufs = DIV_ROUND_UP(wnd_scaled - already_sent, mss);
> -	if (fill_bufs > TCP_FRAMES) {
> -		fill_bufs = TCP_FRAMES;
> -		iov_rem = 0;
> -	} else {
> -		iov_rem = (wnd_scaled - already_sent) % mss;
> -	}
> -
> -	mh_sock.msg_iov = iov_sock;
> -	mh_sock.msg_iovlen = fill_bufs + 1;
> -
> -	iov_sock[0].iov_base = tcp_buf_discard;
> -	iov_sock[0].iov_len = already_sent;
> -
> -	if (( v4 && tcp4_payload_used + fill_bufs > TCP_FRAMES_MEM) ||
> -	    (!v4 && tcp6_payload_used + fill_bufs > TCP_FRAMES_MEM)) {
> -		tcp_payload_flush(c);
> -
> -		/* Silence Coverity CWE-125 false positive */
> -		tcp4_payload_used = tcp6_payload_used = 0;
> -	}
> -
> -	for (i = 0, iov = iov_sock + 1; i < fill_bufs; i++, iov++) {
> -		if (v4)
> -			iov->iov_base = &tcp4_payload[tcp4_payload_used + i].data;
> -		else
> -			iov->iov_base = &tcp6_payload[tcp6_payload_used + i].data;
> -		iov->iov_len = mss;
> -	}
> -	if (iov_rem)
> -		iov_sock[fill_bufs].iov_len = iov_rem;
> -
> -	/* Receive into buffers, don't dequeue until acknowledged by guest. */
> -	do
> -		len = recvmsg(s, &mh_sock, MSG_PEEK);
> -	while (len < 0 && errno == EINTR);
> -
> -	if (len < 0)
> -		goto err;
> -
> -	if (!len) {
> -		if ((conn->events & (SOCK_FIN_RCVD | TAP_FIN_SENT)) == SOCK_FIN_RCVD) {
> -			if ((ret = tcp_send_flag(c, conn, FIN | ACK))) {
> -				tcp_rst(c, conn);
> -				return ret;
> -			}
> -
> -			conn_event(c, conn, TAP_FIN_SENT);
> -		}
> -
> -		return 0;
> -	}
> -
> -	sendlen = len - already_sent;
> -	if (sendlen <= 0) {
> -		conn_flag(c, conn, STALLED);
> -		return 0;
> -	}
> -
> -	conn_flag(c, conn, ~STALLED);
> -
> -	send_bufs = DIV_ROUND_UP(sendlen, mss);
> -	last_len = sendlen - (send_bufs - 1) * mss;
> -
> -	/* Likely, some new data was acked too. */
> -	tcp_update_seqack_wnd(c, conn, 0, NULL);
> -
> -	/* Finally, queue to tap */
> -	dlen = mss;
> -	seq = conn->seq_to_tap;
> -	for (i = 0; i < send_bufs; i++) {
> -		int no_csum = i && i != send_bufs - 1 && tcp4_payload_used;
> -
> -		if (i == send_bufs - 1)
> -			dlen = last_len;
> -
> -		tcp_data_to_tap(c, conn, dlen, no_csum, seq);
> -		seq += dlen;
> -	}
> -
> -	conn_flag(c, conn, ACK_FROM_TAP_DUE);
> -
> -	return 0;
> -
> -err:
> -	if (errno != EAGAIN && errno != EWOULDBLOCK) {
> -		ret = -errno;
> -		tcp_rst(c, conn);
> -	}
> -
> -	return ret;
> +	return tcp_buf_data_from_sock(c, conn);
>  }
>  
>  /**
> diff --git a/tcp_buf.c b/tcp_buf.c
> new file mode 100644
> index 000000000000..0c7d07b8d0bd
> --- /dev/null
> +++ b/tcp_buf.c
> @@ -0,0 +1,513 @@
> +// SPDX-License-Identifier: GPL-2.0-or-later
> +
> +/* PASST - Plug A Simple Socket Transport
> + *  for qemu/UNIX domain socket mode
> + *
> + * PASTA - Pack A Subtle Tap Abstraction
> + *  for network namespace/tap device mode
> + *
> + * tcp_buf.c - TCP L2-L4 buffer management functions

This still has "L2-L4", but L4 doesn't really make sense I think. I can
also drop "-L4" on merge.

> + *
> + * Copyright Red Hat
> + * Author: Stefano Brivio <sbrivio@redhat.com>
> + */
> +
> +#include <stddef.h>
> +#include <stdint.h>
> +#include <limits.h>
> +#include <string.h>
> +#include <errno.h>
> +
> +#include <netinet/ip.h>
> +
> +#include <linux/tcp.h>
> +
> +#include "util.h"
> +#include "ip.h"
> +#include "iov.h"
> +#include "passt.h"
> +#include "tap.h"
> +#include "siphash.h"
> +#include "inany.h"
> +#include "tcp_conn.h"
> +#include "tcp_internal.h"
> +#include "tcp_buf.h"
> +
> +#define TCP_FRAMES_MEM			128
> +#define TCP_FRAMES							   \
> +	(c->mode == MODE_PASST ? TCP_FRAMES_MEM : 1)
> +
> +/* Static buffers */
> +/**
> + * struct tcp_payload_t - TCP header and data to send segments with payload
> + * @th:		TCP header
> + * @data:	TCP data
> + */
> +struct tcp_payload_t {
> +	struct tcphdr th;
> +	uint8_t data[IP_MAX_MTU - sizeof(struct tcphdr)];
> +#ifdef __AVX2__
> +} __attribute__ ((packed, aligned(32)));    /* For AVX2 checksum routines */
> +#else
> +} __attribute__ ((packed, aligned(__alignof__(unsigned int))));
> +#endif
> +
> +/**
> + * struct tcp_flags_t - TCP header and data to send zero-length
> + *                      segments (flags)
> + * @th:		TCP header
> + * @opts	TCP options
> + */
> +struct tcp_flags_t {
> +	struct tcphdr th;
> +	char opts[OPT_MSS_LEN + OPT_WS_LEN + 1];
> +#ifdef __AVX2__
> +} __attribute__ ((packed, aligned(32)));
> +#else
> +} __attribute__ ((packed, aligned(__alignof__(unsigned int))));
> +#endif
> +
> +/* Ethernet header for IPv4 frames */
> +static struct ethhdr		tcp4_eth_src;
> +
> +static struct tap_hdr		tcp4_payload_tap_hdr[TCP_FRAMES_MEM];
> +/* IPv4 headers */
> +static struct iphdr		tcp4_payload_ip[TCP_FRAMES_MEM];
> +/* TCP segments with payload for IPv4 frames */
> +static struct tcp_payload_t	tcp4_payload[TCP_FRAMES_MEM];
> +
> +static_assert(MSS4 <= sizeof(tcp4_payload[0].data), "MSS4 is greater than 65516");
> +
> +/* References tracking the owner connection of frames in the tap outqueue */
> +static struct tcp_tap_conn *tcp4_frame_conns[TCP_FRAMES_MEM];
> +static unsigned int tcp4_payload_used;
> +
> +static struct tap_hdr		tcp4_flags_tap_hdr[TCP_FRAMES_MEM];
> +/* IPv4 headers for TCP segment without payload */
> +static struct iphdr		tcp4_flags_ip[TCP_FRAMES_MEM];
> +/* TCP segments without payload for IPv4 frames */
> +static struct tcp_flags_t	tcp4_flags[TCP_FRAMES_MEM];
> +
> +static unsigned int tcp4_flags_used;
> +
> +/* Ethernet header for IPv6 frames */
> +static struct ethhdr		tcp6_eth_src;
> +
> +static struct tap_hdr		tcp6_payload_tap_hdr[TCP_FRAMES_MEM];
> +/* IPv6 headers */
> +static struct ipv6hdr		tcp6_payload_ip[TCP_FRAMES_MEM];
> +/* TCP headers and data for IPv6 frames */
> +static struct tcp_payload_t	tcp6_payload[TCP_FRAMES_MEM];
> +
> +static_assert(MSS6 <= sizeof(tcp6_payload[0].data), "MSS6 is greater than 65516");
> +
> +/* References tracking the owner connection of frames in the tap outqueue */
> +static struct tcp_tap_conn *tcp6_frame_conns[TCP_FRAMES_MEM];
> +static unsigned int tcp6_payload_used;
> +
> +static struct tap_hdr		tcp6_flags_tap_hdr[TCP_FRAMES_MEM];
> +/* IPv6 headers for TCP segment without payload */
> +static struct ipv6hdr		tcp6_flags_ip[TCP_FRAMES_MEM];
> +/* TCP segment without payload for IPv6 frames */
> +static struct tcp_flags_t	tcp6_flags[TCP_FRAMES_MEM];
> +
> +static unsigned int tcp6_flags_used;
> +
> +/* recvmsg()/sendmsg() data for tap */
> +static struct iovec	iov_sock		[TCP_FRAMES_MEM + 1];
> +
> +static struct iovec	tcp4_l2_iov		[TCP_FRAMES_MEM][TCP_NUM_IOVS];
> +static struct iovec	tcp6_l2_iov		[TCP_FRAMES_MEM][TCP_NUM_IOVS];
> +static struct iovec	tcp4_l2_flags_iov	[TCP_FRAMES_MEM][TCP_NUM_IOVS];
> +static struct iovec	tcp6_l2_flags_iov	[TCP_FRAMES_MEM][TCP_NUM_IOVS];
> +/**
> + * tcp_update_l2_buf() - Update Ethernet header buffers with addresses
> + * @eth_d:	Ethernet destination address, NULL if unchanged
> + * @eth_s:	Ethernet source address, NULL if unchanged
> + */
> +void tcp_update_l2_buf(const unsigned char *eth_d, const unsigned char *eth_s)
> +{
> +	eth_update_mac(&tcp4_eth_src, eth_d, eth_s);
> +	eth_update_mac(&tcp6_eth_src, eth_d, eth_s);
> +}
> +
> +/**
> + * tcp_sock4_iov_init() - Initialise scatter-gather L2 buffers for IPv4 sockets
> + * @c:		Execution context
> + */
> +void tcp_sock4_iov_init(const struct ctx *c)
> +{
> +	struct iphdr iph = L2_BUF_IP4_INIT(IPPROTO_TCP);
> +	struct iovec *iov;
> +	int i;
> +
> +	tcp4_eth_src.h_proto = htons_constant(ETH_P_IP);
> +
> +	for (i = 0; i < ARRAY_SIZE(tcp4_payload); i++) {
> +		tcp4_payload_ip[i] = iph;
> +		tcp4_payload[i].th.doff = sizeof(struct tcphdr) / 4;
> +		tcp4_payload[i].th.ack = 1;
> +	}
> +
> +	for (i = 0; i < ARRAY_SIZE(tcp4_flags); i++) {
> +		tcp4_flags_ip[i] = iph;
> +		tcp4_flags[i].th.doff = sizeof(struct tcphdr) / 4;
> +		tcp4_flags[i].th.ack = 1;
> +	}
> +
> +	for (i = 0; i < TCP_FRAMES_MEM; i++) {
> +		iov = tcp4_l2_iov[i];
> +
> +		iov[TCP_IOV_TAP] = tap_hdr_iov(c, &tcp4_payload_tap_hdr[i]);
> +		iov[TCP_IOV_ETH] = IOV_OF_LVALUE(tcp4_eth_src);
> +		iov[TCP_IOV_IP] = IOV_OF_LVALUE(tcp4_payload_ip[i]);
> +		iov[TCP_IOV_PAYLOAD].iov_base = &tcp4_payload[i];
> +	}
> +
> +	for (i = 0; i < TCP_FRAMES_MEM; i++) {
> +		iov = tcp4_l2_flags_iov[i];
> +
> +		iov[TCP_IOV_TAP] = tap_hdr_iov(c, &tcp4_flags_tap_hdr[i]);
> +		iov[TCP_IOV_ETH].iov_base = &tcp4_eth_src;
> +		iov[TCP_IOV_ETH] = IOV_OF_LVALUE(tcp4_eth_src);
> +		iov[TCP_IOV_IP] = IOV_OF_LVALUE(tcp4_flags_ip[i]);
> +		iov[TCP_IOV_PAYLOAD].iov_base = &tcp4_flags[i];
> +	}
> +}
> +
> +/**
> + * tcp_sock6_iov_init() - Initialise scatter-gather L2 buffers for IPv6 sockets
> + * @c:		Execution context
> + */
> +void tcp_sock6_iov_init(const struct ctx *c)
> +{
> +	struct ipv6hdr ip6 = L2_BUF_IP6_INIT(IPPROTO_TCP);
> +	struct iovec *iov;
> +	int i;
> +
> +	tcp6_eth_src.h_proto = htons_constant(ETH_P_IPV6);
> +
> +	for (i = 0; i < ARRAY_SIZE(tcp6_payload); i++) {
> +		tcp6_payload_ip[i] = ip6;
> +		tcp6_payload[i].th.doff = sizeof(struct tcphdr) / 4;
> +		tcp6_payload[i].th.ack = 1;
> +	}
> +
> +	for (i = 0; i < ARRAY_SIZE(tcp6_flags); i++) {
> +		tcp6_flags_ip[i] = ip6;
> +		tcp6_flags[i].th.doff = sizeof(struct tcphdr) / 4;
> +		tcp6_flags[i].th .ack = 1;
> +	}
> +
> +	for (i = 0; i < TCP_FRAMES_MEM; i++) {
> +		iov = tcp6_l2_iov[i];
> +
> +		iov[TCP_IOV_TAP] = tap_hdr_iov(c, &tcp6_payload_tap_hdr[i]);
> +		iov[TCP_IOV_ETH] = IOV_OF_LVALUE(tcp6_eth_src);
> +		iov[TCP_IOV_IP] = IOV_OF_LVALUE(tcp6_payload_ip[i]);
> +		iov[TCP_IOV_PAYLOAD].iov_base = &tcp6_payload[i];
> +	}
> +
> +	for (i = 0; i < TCP_FRAMES_MEM; i++) {
> +		iov = tcp6_l2_flags_iov[i];
> +
> +		iov[TCP_IOV_TAP] = tap_hdr_iov(c, &tcp6_flags_tap_hdr[i]);
> +		iov[TCP_IOV_ETH] = IOV_OF_LVALUE(tcp6_eth_src);
> +		iov[TCP_IOV_IP] = IOV_OF_LVALUE(tcp6_flags_ip[i]);
> +		iov[TCP_IOV_PAYLOAD].iov_base = &tcp6_flags[i];
> +	}
> +}
> +
> +/**
> + * tcp_flags_flush() - Send out buffers for segments with no data (flags)
> + * @c:		Execution context
> + */
> +void tcp_flags_flush(const struct ctx *c)
> +{
> +	tap_send_frames(c, &tcp6_l2_flags_iov[0][0], TCP_NUM_IOVS,
> +			tcp6_flags_used);
> +	tcp6_flags_used = 0;
> +
> +	tap_send_frames(c, &tcp4_l2_flags_iov[0][0], TCP_NUM_IOVS,
> +			tcp4_flags_used);
> +	tcp4_flags_used = 0;
> +}
> +
> +/**
> + * tcp_revert_seq() - Revert affected conn->seq_to_tap after failed transmission
> + * @conns:       Array of connection pointers corresponding to queued frames
> + * @frames:      Two-dimensional array containing queued frames with sub-iovs
> + * @num_frames:  Number of entries in the two arrays to be compared
> + */
> +static void tcp_revert_seq(struct tcp_tap_conn **conns, struct iovec (*frames)[TCP_NUM_IOVS],
> +			   int num_frames)
> +{
> +	int i;
> +
> +	for (i = 0; i < num_frames; i++) {
> +		const struct tcphdr *th = frames[i][TCP_IOV_PAYLOAD].iov_base;
> +		struct tcp_tap_conn *conn = conns[i];
> +		uint32_t seq = ntohl(th->seq);
> +
> +		if (SEQ_LE(conn->seq_to_tap, seq))
> +			continue;
> +
> +		conn->seq_to_tap = seq;
> +	}
> +}
> +
> +/**
> + * tcp_payload_flush() - Send out buffers for segments with data
> + * @c:		Execution context
> + */
> +void tcp_payload_flush(const struct ctx *c)
> +{
> +	size_t m;
> +
> +	m = tap_send_frames(c, &tcp6_l2_iov[0][0], TCP_NUM_IOVS,
> +			    tcp6_payload_used);
> +	if (m != tcp6_payload_used) {
> +		tcp_revert_seq(&tcp6_frame_conns[m], &tcp6_l2_iov[m],
> +			       tcp6_payload_used - m);
> +	}
> +	tcp6_payload_used = 0;
> +
> +	m = tap_send_frames(c, &tcp4_l2_iov[0][0], TCP_NUM_IOVS,
> +			    tcp4_payload_used);
> +	if (m != tcp4_payload_used) {
> +		tcp_revert_seq(&tcp4_frame_conns[m], &tcp4_l2_iov[m],
> +			       tcp4_payload_used - m);
> +	}
> +	tcp4_payload_used = 0;
> +}
> +
> +/**
> + * tcp_buf_send_flag() - Send segment with flags to tap (no payload)
> + * @c:         Execution context
> + * @conn:      Connection pointer
> + * @flags:     TCP flags: if not set, send segment only if ACK is due
> + *
> + * Return: negative error code on connection reset, 0 otherwise
> + */
> +int tcp_buf_send_flag(struct ctx *c, struct tcp_tap_conn *conn, int flags)
> +{
> +	struct tcp_flags_t *payload;
> +	struct iovec *iov;
> +	size_t optlen;
> +	size_t l4len;
> +	int ret;
> +
> +	if (CONN_V4(conn))
> +		iov = tcp4_l2_flags_iov[tcp4_flags_used++];
> +	else
> +		iov = tcp6_l2_flags_iov[tcp6_flags_used++];
> +
> +	payload = iov[TCP_IOV_PAYLOAD].iov_base;
> +
> +	ret = tcp_prepare_flags(c, conn, flags, &payload->th,
> +				payload->opts, &optlen);
> +	if (ret <= 0)
> +		return ret;
> +
> +	l4len = tcp_l2_buf_fill_headers(c, conn, iov, optlen, NULL,
> +					conn->seq_to_tap);
> +	iov[TCP_IOV_PAYLOAD].iov_len = l4len;
> +
> +	if (flags & DUP_ACK) {
> +		struct iovec *dup_iov;
> +		int i;
> +
> +		if (CONN_V4(conn))
> +			dup_iov = tcp4_l2_flags_iov[tcp4_flags_used++];
> +		else
> +			dup_iov = tcp6_l2_flags_iov[tcp6_flags_used++];
> +
> +		for (i = 0; i < TCP_NUM_IOVS; i++)
> +			memcpy(dup_iov[i].iov_base, iov[i].iov_base,
> +			       iov[i].iov_len);
> +		dup_iov[TCP_IOV_PAYLOAD].iov_len = iov[TCP_IOV_PAYLOAD].iov_len;
> +	}
> +
> +	if (CONN_V4(conn)) {
> +		if (tcp4_flags_used > TCP_FRAMES_MEM - 2)
> +			tcp_flags_flush(c);
> +	} else {
> +		if (tcp6_flags_used > TCP_FRAMES_MEM - 2)
> +			tcp_flags_flush(c);
> +	}
> +
> +	return 0;
> +}
> +
> +/**
> + * tcp_data_to_tap() - Finalise (queue) highest-numbered scatter-gather buffer
> + * @c:		Execution context
> + * @conn:	Connection pointer
> + * @dlen:	TCP payload length
> + * @no_csum:	Don't compute IPv4 checksum, use the one from previous buffer
> + * @seq:	Sequence number to be sent
> + */
> +static void tcp_data_to_tap(const struct ctx *c, struct tcp_tap_conn *conn,
> +			    ssize_t dlen, int no_csum, uint32_t seq)
> +{
> +	struct iovec *iov;
> +	size_t l4len;
> +
> +	conn->seq_to_tap = seq + dlen;
> +
> +	if (CONN_V4(conn)) {
> +		struct iovec *iov_prev = tcp4_l2_iov[tcp4_payload_used - 1];
> +		const uint16_t *check = NULL;
> +
> +		if (no_csum) {
> +			struct iphdr *iph = iov_prev[TCP_IOV_IP].iov_base;
> +			check = &iph->check;
> +		}
> +
> +		tcp4_frame_conns[tcp4_payload_used] = conn;
> +
> +		iov = tcp4_l2_iov[tcp4_payload_used++];
> +		l4len = tcp_l2_buf_fill_headers(c, conn, iov, dlen, check, seq);
> +		iov[TCP_IOV_PAYLOAD].iov_len = l4len;
> +		if (tcp4_payload_used > TCP_FRAMES_MEM - 1)
> +			tcp_payload_flush(c);
> +	} else if (CONN_V6(conn)) {
> +		tcp6_frame_conns[tcp6_payload_used] = conn;
> +
> +		iov = tcp6_l2_iov[tcp6_payload_used++];
> +		l4len = tcp_l2_buf_fill_headers(c, conn, iov, dlen, NULL, seq);
> +		iov[TCP_IOV_PAYLOAD].iov_len = l4len;
> +		if (tcp6_payload_used > TCP_FRAMES_MEM - 1)
> +			tcp_payload_flush(c);
> +	}
> +}
> +
> +/**
> + * tcp_buf_data_from_sock() - Handle new data from socket, queue to tap, in window
> + * @c:		Execution context
> + * @conn:	Connection pointer
> + *
> + * Return: negative on connection reset, 0 otherwise
> + *
> + * #syscalls recvmsg
> + */
> +int tcp_buf_data_from_sock(struct ctx *c, struct tcp_tap_conn *conn)
> +{
> +	uint32_t wnd_scaled = conn->wnd_from_tap << conn->ws_from_tap;
> +	int fill_bufs, send_bufs = 0, last_len, iov_rem = 0;
> +	int sendlen, len, dlen, v4 = CONN_V4(conn);
> +	int s = conn->sock, i, ret = 0;
> +	struct msghdr mh_sock = { 0 };
> +	uint16_t mss = MSS_GET(conn);
> +	uint32_t already_sent, seq;
> +	struct iovec *iov;
> +
> +	already_sent = conn->seq_to_tap - conn->seq_ack_from_tap;
> +
> +	if (SEQ_LT(already_sent, 0)) {
> +		/* RFC 761, section 2.1. */
> +		flow_trace(conn, "ACK sequence gap: ACK for %u, sent: %u",
> +			   conn->seq_ack_from_tap, conn->seq_to_tap);
> +		conn->seq_to_tap = conn->seq_ack_from_tap;
> +		already_sent = 0;
> +	}
> +
> +	if (!wnd_scaled || already_sent >= wnd_scaled) {
> +		conn_flag(c, conn, STALLED);
> +		conn_flag(c, conn, ACK_FROM_TAP_DUE);
> +		return 0;
> +	}
> +
> +	/* Set up buffer descriptors we'll fill completely and partially. */
> +	fill_bufs = DIV_ROUND_UP(wnd_scaled - already_sent, mss);
> +	if (fill_bufs > TCP_FRAMES) {
> +		fill_bufs = TCP_FRAMES;
> +		iov_rem = 0;
> +	} else {
> +		iov_rem = (wnd_scaled - already_sent) % mss;
> +	}
> +
> +	mh_sock.msg_iov = iov_sock;
> +	mh_sock.msg_iovlen = fill_bufs + 1;
> +
> +	iov_sock[0].iov_base = tcp_buf_discard;
> +	iov_sock[0].iov_len = already_sent;
> +
> +	if (( v4 && tcp4_payload_used + fill_bufs > TCP_FRAMES_MEM) ||
> +	    (!v4 && tcp6_payload_used + fill_bufs > TCP_FRAMES_MEM)) {
> +		tcp_payload_flush(c);
> +
> +		/* Silence Coverity CWE-125 false positive */
> +		tcp4_payload_used = tcp6_payload_used = 0;
> +	}
> +
> +	for (i = 0, iov = iov_sock + 1; i < fill_bufs; i++, iov++) {
> +		if (v4)
> +			iov->iov_base = &tcp4_payload[tcp4_payload_used + i].data;
> +		else
> +			iov->iov_base = &tcp6_payload[tcp6_payload_used + i].data;
> +		iov->iov_len = mss;
> +	}
> +	if (iov_rem)
> +		iov_sock[fill_bufs].iov_len = iov_rem;
> +
> +	/* Receive into buffers, don't dequeue until acknowledged by guest. */
> +	do
> +		len = recvmsg(s, &mh_sock, MSG_PEEK);
> +	while (len < 0 && errno == EINTR);
> +
> +	if (len < 0)
> +		goto err;
> +
> +	if (!len) {
> +		if ((conn->events & (SOCK_FIN_RCVD | TAP_FIN_SENT)) == SOCK_FIN_RCVD) {
> +			if ((ret = tcp_buf_send_flag(c, conn, FIN | ACK))) {
> +				tcp_rst(c, conn);
> +				return ret;
> +			}
> +
> +			conn_event(c, conn, TAP_FIN_SENT);
> +		}
> +
> +		return 0;
> +	}
> +
> +	sendlen = len - already_sent;
> +	if (sendlen <= 0) {
> +		conn_flag(c, conn, STALLED);
> +		return 0;
> +	}
> +
> +	conn_flag(c, conn, ~STALLED);
> +
> +	send_bufs = DIV_ROUND_UP(sendlen, mss);
> +	last_len = sendlen - (send_bufs - 1) * mss;
> +
> +	/* Likely, some new data was acked too. */
> +	tcp_update_seqack_wnd(c, conn, 0, NULL);
> +
> +	/* Finally, queue to tap */
> +	dlen = mss;
> +	seq = conn->seq_to_tap;
> +	for (i = 0; i < send_bufs; i++) {
> +		int no_csum = i && i != send_bufs - 1 && tcp4_payload_used;
> +
> +		if (i == send_bufs - 1)
> +			dlen = last_len;
> +
> +		tcp_data_to_tap(c, conn, dlen, no_csum, seq);
> +		seq += dlen;
> +	}
> +
> +	conn_flag(c, conn, ACK_FROM_TAP_DUE);
> +
> +	return 0;
> +
> +err:
> +	if (errno != EAGAIN && errno != EWOULDBLOCK) {
> +		ret = -errno;
> +		tcp_rst(c, conn);
> +	}
> +
> +	return ret;
> +}
> diff --git a/tcp_buf.h b/tcp_buf.h
> new file mode 100644
> index 000000000000..14be7b945285
> --- /dev/null
> +++ b/tcp_buf.h
> @@ -0,0 +1,16 @@
> +/* SPDX-License-Identifier: GPL-2.0-or-later
> + * Copyright (c) 2021 Red Hat GmbH
> + * Author: Stefano Brivio <sbrivio@redhat.com>
> + */
> +
> +#ifndef TCP_BUF_H
> +#define TCP_BUF_H
> +
> +void tcp_sock4_iov_init(const struct ctx *c);
> +void tcp_sock6_iov_init(const struct ctx *c);
> +void tcp_flags_flush(const struct ctx *c);
> +void tcp_payload_flush(const struct ctx *c);
> +int tcp_buf_data_from_sock(struct ctx *c, struct tcp_tap_conn *conn);
> +int tcp_buf_send_flag(struct ctx *c, struct tcp_tap_conn *conn, int flags);
> +
> +#endif  /*TCP_BUF_H */
> diff --git a/tcp_internal.h b/tcp_internal.h
> new file mode 100644
> index 000000000000..51aaa16918cf
> --- /dev/null
> +++ b/tcp_internal.h
> @@ -0,0 +1,96 @@
> +/* SPDX-License-Identifier: GPL-2.0-or-later
> + * Copyright (c) 2021 Red Hat GmbH
> + * Author: Stefano Brivio <sbrivio@redhat.com>
> + */
> +
> +#ifndef TCP_INTERNAL_H
> +#define TCP_INTERNAL_H
> +
> +#define MAX_WS				8
> +#define MAX_WINDOW			(1 << (16 + (MAX_WS)))
> +
> +#define MSS4				ROUND_DOWN(IP_MAX_MTU -		   \
> +						   sizeof(struct tcphdr) - \
> +						   sizeof(struct iphdr),   \
> +						   sizeof(uint32_t))
> +#define MSS6				ROUND_DOWN(IP_MAX_MTU -		   \
> +						   sizeof(struct tcphdr) - \
> +						   sizeof(struct ipv6hdr), \
> +						   sizeof(uint32_t))
> +
> +#define SEQ_LE(a, b)			((b) - (a) < MAX_WINDOW)
> +#define SEQ_LT(a, b)			((b) - (a) - 1 < MAX_WINDOW)
> +#define SEQ_GE(a, b)			((a) - (b) < MAX_WINDOW)
> +#define SEQ_GT(a, b)			((a) - (b) - 1 < MAX_WINDOW)
> +
> +#define FIN		(1 << 0)
> +#define SYN		(1 << 1)
> +#define RST		(1 << 2)
> +#define ACK		(1 << 4)
> +
> +/* Flags for internal usage */
> +#define DUP_ACK		(1 << 5)
> +#define OPT_EOL		0
> +#define OPT_NOP		1
> +#define OPT_MSS		2
> +#define OPT_MSS_LEN	4
> +#define OPT_WS		3
> +#define OPT_WS_LEN	3
> +#define OPT_SACKP	4
> +#define OPT_SACK	5
> +#define OPT_TS		8
> +#define CONN_V4(conn)		(!!inany_v4(&(conn)->faddr))
> +#define CONN_V6(conn)		(!CONN_V4(conn))
> +
> +/*
> + * enum tcp_iov_parts - I/O vector parts for one TCP frame
> + * @TCP_IOV_TAP		tap backend specific header
> + * @TCP_IOV_ETH		Ethernet header
> + * @TCP_IOV_IP		IP (v4/v6) header
> + * @TCP_IOV_PAYLOAD	IP payload (TCP header + data)
> + * @TCP_NUM_IOVS 	the number of entries in the iovec array
> + */
> +enum tcp_iov_parts {
> +	TCP_IOV_TAP	= 0,
> +	TCP_IOV_ETH	= 1,
> +	TCP_IOV_IP	= 2,
> +	TCP_IOV_PAYLOAD	= 3,
> +	TCP_NUM_IOVS
> +};
> +
> +extern char tcp_buf_discard [MAX_WINDOW];
> +
> +void conn_flag_do(const struct ctx *c, struct tcp_tap_conn *conn,
> +		  unsigned long flag);
> +#define conn_flag(c, conn, flag)					\
> +	do {								\
> +		flow_trace(conn, "flag at %s:%i", __func__, __LINE__);	\
> +		conn_flag_do(c, conn, flag);				\
> +	} while (0)
> +
> +
> +void conn_event_do(const struct ctx *c, struct tcp_tap_conn *conn,
> +		   unsigned long event);
> +#define conn_event(c, conn, event)					\
> +	do {								\
> +		flow_trace(conn, "event at %s:%i", __func__, __LINE__);	\
> +		conn_event_do(c, conn, event);				\
> +	} while (0)
> +
> +void tcp_rst_do(struct ctx *c, struct tcp_tap_conn *conn);
> +#define tcp_rst(c, conn)						\
> +	do {								\
> +		flow_dbg((conn), "TCP reset at %s:%i", __func__, __LINE__); \
> +		tcp_rst_do(c, conn);					\
> +	} while (0)
> +
> +size_t tcp_l2_buf_fill_headers(const struct ctx *c,
> +			       const struct tcp_tap_conn *conn,
> +			       struct iovec *iov, size_t dlen,
> +			       const uint16_t *check, uint32_t seq);
> +int tcp_update_seqack_wnd(const struct ctx *c, struct tcp_tap_conn *conn,
> +			  int force_seq, struct tcp_info *tinfo);
> +int tcp_prepare_flags(struct ctx *c, struct tcp_tap_conn *conn, int flags,
> +		      struct tcphdr *th, char *data, size_t *optlen);
> +
> +#endif /* TCP_INTERNAL_H */

-- 
Stefano