public inbox for passt-dev@passt.top
 help / color / mirror / code / Atom feed
From: Stefano Brivio <sbrivio@redhat.com>
To: David Gibson <david@gibson.dropbear.id.au>
Cc: passt-dev@passt.top
Subject: Re: [PATCH 14/32] tcp: Separate helpers to create ns listening sockets
Date: Thu, 17 Nov 2022 00:51:38 +0100	[thread overview]
Message-ID: <20221117005138.17007cb1@elisabeth> (raw)
In-Reply-To: <20221116044212.3876516-15-david@gibson.dropbear.id.au>

On Wed, 16 Nov 2022 15:41:54 +1100
David Gibson <david@gibson.dropbear.id.au> wrote:

> tcp_sock_init*() can create either sockets listening on the host, or in
> the pasta network namespace (with @ns==1).  There are, however, a number
> of differences in how these two cases work in practice though.  "ns"
> sockets are only used in pasta mode, and they always lead to spliced
> connections only.  The functions are also only ever called in "ns" mode
> with a NULL address and interface name, and it doesn't really make sense
> for them to be called any other way.
> 
> Later changes will introduce further differences in behaviour between these
> two cases, so it makes more sense to use separate functions for creating
> the ns listening sockets than the regular external/host listening sockets.
> ---
>  conf.c |   6 +--
>  tcp.c  | 130 ++++++++++++++++++++++++++++++++++++++-------------------
>  tcp.h  |   4 +-
>  3 files changed, 92 insertions(+), 48 deletions(-)
> 
> diff --git a/conf.c b/conf.c
> index 3ad247e..2b39d18 100644
> --- a/conf.c
> +++ b/conf.c
> @@ -209,7 +209,7 @@ static int conf_ports(const struct ctx *c, char optname, const char *optarg,
>  
>  		for (i = 0; i < PORT_EPHEMERAL_MIN; i++) {
>  			if (optname == 't')
> -				tcp_sock_init(c, 0, AF_UNSPEC, NULL, NULL, i);
> +				tcp_sock_init(c, AF_UNSPEC, NULL, NULL, i);
>  			else if (optname == 'u')
>  				udp_sock_init(c, 0, AF_UNSPEC, NULL, NULL, i);
>  		}
> @@ -287,7 +287,7 @@ static int conf_ports(const struct ctx *c, char optname, const char *optarg,
>  			bitmap_set(fwd->map, i);
>  
>  			if (optname == 't')
> -				tcp_sock_init(c, 0, af, addr, ifname, i);
> +				tcp_sock_init(c, af, addr, ifname, i);
>  			else if (optname == 'u')
>  				udp_sock_init(c, 0, af, addr, ifname, i);
>  		}
> @@ -333,7 +333,7 @@ static int conf_ports(const struct ctx *c, char optname, const char *optarg,
>  			fwd->delta[i] = mapped_range.first - orig_range.first;
>  
>  			if (optname == 't')
> -				tcp_sock_init(c, 0, af, addr, ifname, i);
> +				tcp_sock_init(c, af, addr, ifname, i);
>  			else if (optname == 'u')
>  				udp_sock_init(c, 0, af, addr, ifname, i);
>  		}
> diff --git a/tcp.c b/tcp.c
> index aac70cd..72d3b49 100644
> --- a/tcp.c
> +++ b/tcp.c
> @@ -2987,15 +2987,15 @@ void tcp_sock_handler(struct ctx *c, union epoll_ref ref, uint32_t events,
>  /**
>   * tcp_sock_init4() - Initialise listening sockets for a given IPv4 port
>   * @c:		Execution context
> - * @ns:		In pasta mode, if set, bind with loopback address in namespace
>   * @addr:	Pointer to address for binding, NULL if not configured
>   * @ifname:	Name of interface to bind to, NULL if not configured
>   * @port:	Port, host order
>   */
> -static void tcp_sock_init4(const struct ctx *c, int ns, const struct in_addr *addr,
> +static void tcp_sock_init4(const struct ctx *c, const struct in_addr *addr,
>  			   const char *ifname, in_port_t port)
>  {
> -	union tcp_epoll_ref tref = { .tcp.listen = 1, .tcp.outbound = ns };
> +	in_port_t idx = port + c->tcp.fwd_in.delta[port];
> +	union tcp_epoll_ref tref = { .tcp.listen = 1, .tcp.index = idx };

Usual order here...

>  	bool spliced = false, tap = true;
>  	int s;
>  
> @@ -3006,14 +3006,9 @@ static void tcp_sock_init4(const struct ctx *c, int ns, const struct in_addr *ad
>  		if (!addr)
>  			addr = &c->ip4.addr;
>  
> -		tap = !ns && !IN4_IS_ADDR_LOOPBACK(addr);
> +		tap = !IN4_IS_ADDR_LOOPBACK(addr);
>  	}
>  
> -	if (ns)
> -		tref.tcp.index = (in_port_t)(port + c->tcp.fwd_out.delta[port]);
> -	else
> -		tref.tcp.index = (in_port_t)(port + c->tcp.fwd_in.delta[port]);
> -
>  	if (tap) {
>  		s = sock_l4(c, AF_INET, IPPROTO_TCP, addr, ifname, port,
>  			    tref.u32);
> @@ -3039,29 +3034,25 @@ static void tcp_sock_init4(const struct ctx *c, int ns, const struct in_addr *ad
>  		else
>  			s = -1;
>  
> -		if (c->tcp.fwd_out.mode == FWD_AUTO) {
> -			if (ns)
> -				tcp_sock_ns[port][V4] = s;
> -			else
> -				tcp_sock_init_lo[port][V4] = s;
> -		}
> +		if (c->tcp.fwd_out.mode == FWD_AUTO)
> +			tcp_sock_init_lo[port][V4] = s;
>  	}
>  }
>  
>  /**
>   * tcp_sock_init6() - Initialise listening sockets for a given IPv6 port
>   * @c:		Execution context
> - * @ns:		In pasta mode, if set, bind with loopback address in namespace
>   * @addr:	Pointer to address for binding, NULL if not configured
>   * @ifname:	Name of interface to bind to, NULL if not configured
>   * @port:	Port, host order
>   */
> -static void tcp_sock_init6(const struct ctx *c, int ns,
> +static void tcp_sock_init6(const struct ctx *c,
>  			   const struct in6_addr *addr, const char *ifname,
>  			   in_port_t port)
>  {
> -	union tcp_epoll_ref tref = { .tcp.listen = 1, .tcp.outbound = ns,
> -				     .tcp.v6 = 1 };
> +	in_port_t idx = port + c->tcp.fwd_in.delta[port];
> +	union tcp_epoll_ref tref = { .tcp.listen = 1, .tcp.v6 = 1,
> +				     .tcp.index = idx	};

Excess whitespace.

>  	bool spliced = false, tap = true;
>  	int s;
>  
> @@ -3073,14 +3064,9 @@ static void tcp_sock_init6(const struct ctx *c, int ns,
>  		if (!addr)
>  			addr = &c->ip6.addr;
>  
> -		tap = !ns && !IN6_IS_ADDR_LOOPBACK(addr);
> +		tap = !IN6_IS_ADDR_LOOPBACK(addr);
>  	}
>  
> -	if (ns)
> -		tref.tcp.index = (in_port_t)(port + c->tcp.fwd_out.delta[port]);
> -	else
> -		tref.tcp.index = (in_port_t)(port + c->tcp.fwd_in.delta[port]);
> -
>  	if (tap) {
>  		s = sock_l4(c, AF_INET6, IPPROTO_TCP, addr, ifname, port,
>  			    tref.u32);
> @@ -3105,40 +3091,99 @@ static void tcp_sock_init6(const struct ctx *c, int ns,
>  		else
>  			s = -1;
>  
> -		if (c->tcp.fwd_out.mode == FWD_AUTO) {
> -			if (ns)
> -				tcp_sock_ns[port][V6] = s;
> -			else
> -				tcp_sock_init_lo[port][V6] = s;
> -		}
> +		if (c->tcp.fwd_out.mode == FWD_AUTO)
> +			tcp_sock_init_lo[port][V6] = s;
>  	}
>  }
>  
>  /**
>   * tcp_sock_init() - Initialise listening sockets for a given port

Maybe we should now indicate this is for "inbound" connections only
("for a given, inbound, port"?)

>   * @c:		Execution context
> - * @ns:		In pasta mode, if set, bind with loopback address in namespace
>   * @af:		Address family to select a specific IP version, or AF_UNSPEC
>   * @addr:	Pointer to address for binding, NULL if not configured
>   * @ifname:	Name of interface to bind to, NULL if not configured
>   * @port:	Port, host order
>   */
> -void tcp_sock_init(const struct ctx *c, int ns, sa_family_t af,
> -		   const void *addr, const char *ifname, in_port_t port)
> +void tcp_sock_init(const struct ctx *c, sa_family_t af, const void *addr,
> +		   const char *ifname, in_port_t port)
>  {
>  	if ((af == AF_INET  || af == AF_UNSPEC) && c->ifi4)
> -		tcp_sock_init4(c, ns, addr, ifname, port);
> +		tcp_sock_init4(c, addr, ifname, port);
>  	if ((af == AF_INET6 || af == AF_UNSPEC) && c->ifi6)
> -		tcp_sock_init6(c, ns, addr, ifname, port);
> +		tcp_sock_init6(c, addr, ifname, port);
> +}
> +
> +/**
> + * tcp_ns_sock_init4() - Init socket to listen for outbound IPv4 connections
> + * @c:		Execution context
> + * @port:	Port, host order
> + */
> +static void tcp_ns_sock_init4(const struct ctx *c, in_port_t port)
> +{
> +	in_port_t idx = port + c->tcp.fwd_out.delta[port];

Move after declaration of 'loopback'.

> +	union tcp_epoll_ref tref = { .tcp.listen = 1, .tcp.outbound = 1,
> +				     .tcp.splice = 1, .tcp.index = idx };
> +	struct in_addr loopback = { htonl(INADDR_LOOPBACK) };
> +	int s;
> +
> +	assert(c->mode == MODE_PASTA);
> +
> +	s = sock_l4(c, AF_INET, IPPROTO_TCP, &loopback, NULL, port, tref.u32);
> +	if (s >= 0)
> +		tcp_sock_set_bufsize(c, s);
> +	else
> +		s = -1;
> +
> +	if (c->tcp.fwd_out.mode == FWD_AUTO)
> +		tcp_sock_ns[port][V4] = s;
>  }
>  
>  /**
> - * tcp_sock_init_ns() - Bind sockets in namespace for outbound connections
> + * tcp_ns_sock_init6() - Init socket to listen for outbound IPv6 connections
> + * @c:		Execution context
> + * @port:	Port, host order
> + */
> +static void tcp_ns_sock_init6(const struct ctx *c, in_port_t port)
> +{
> +	in_port_t idx = port + c->tcp.fwd_out.delta[port];
> +	union tcp_epoll_ref tref = { .tcp.listen = 1, .tcp.outbound = 1,
> +				     .tcp.splice = 1, .tcp.v6 = 1,
> +				     .tcp.index = idx};

Missing whitespace between 'idx' and };

> +	int s;
> +
> +	assert(c->mode == MODE_PASTA);
> +
> +	s = sock_l4(c, AF_INET6, IPPROTO_TCP, &in6addr_loopback, NULL, port,
> +		    tref.u32);
> +	if (s >= 0)
> +		tcp_sock_set_bufsize(c, s);
> +	else
> +		s = -1;
> +
> +	if (c->tcp.fwd_out.mode == FWD_AUTO)
> +		tcp_sock_ns[port][V6] = s;
> +}
> +
> +/**
> + * tcp_ns_sock_init() - Init socket to listen for spliced outbound connections
> + * @c:		Execution context
> + * @port:	Port, host order
> + */
> +void tcp_ns_sock_init(const struct ctx *c, in_port_t port)
> +{
> +	if (c->ifi4)
> +		tcp_ns_sock_init4(c, port);
> +	if (c->ifi6)
> +		tcp_ns_sock_init6(c, port);
> +}
> +
> +/**
> + * tcp_ns_socks_init() - Bind sockets in namespace for outbound connections
>   * @arg:	Execution context
>   *
>   * Return: 0
>   */
> -static int tcp_sock_init_ns(void *arg)
> +static int tcp_ns_socks_init(void *arg)
>  {
>  	struct ctx *c = (struct ctx *)arg;
>  	unsigned port;
> @@ -3149,7 +3194,7 @@ static int tcp_sock_init_ns(void *arg)
>  		if (!bitmap_isset(c->tcp.fwd_out.map, port))
>  			continue;
>  
> -		tcp_sock_init(c, 1, AF_UNSPEC, NULL, NULL, port);
> +		tcp_ns_sock_init(c, port);
>  	}
>  
>  	return 0;
> @@ -3279,7 +3324,7 @@ int tcp_init(struct ctx *c)
>  	if (c->mode == MODE_PASTA) {
>  		tcp_splice_init(c);
>  
> -		NS_CALL(tcp_sock_init_ns, c);
> +		NS_CALL(tcp_ns_socks_init, c);
>  
>  		refill_arg.ns = 1;
>  		NS_CALL(tcp_sock_refill, &refill_arg);
> @@ -3364,8 +3409,7 @@ static int tcp_port_rebind(void *arg)
>  
>  			if ((a->c->ifi4 && tcp_sock_ns[port][V4] == -1) ||
>  			    (a->c->ifi6 && tcp_sock_ns[port][V6] == -1))
> -				tcp_sock_init(a->c, 1, AF_UNSPEC, NULL, NULL,
> -					      port);
> +				tcp_ns_sock_init(a->c, port);
>  		}
>  	} else {
>  		for (port = 0; port < NUM_PORTS; port++) {
> @@ -3398,7 +3442,7 @@ static int tcp_port_rebind(void *arg)
>  
>  			if ((a->c->ifi4 && tcp_sock_init_ext[port][V4] == -1) ||
>  			    (a->c->ifi6 && tcp_sock_init_ext[port][V6] == -1))
> -				tcp_sock_init(a->c, 0, AF_UNSPEC, NULL, NULL,
> +				tcp_sock_init(a->c, AF_UNSPEC, NULL, NULL,
>  					      port);
>  		}
>  	}
> diff --git a/tcp.h b/tcp.h
> index 49738ef..f4ed298 100644
> --- a/tcp.h
> +++ b/tcp.h
> @@ -19,8 +19,8 @@ void tcp_sock_handler(struct ctx *c, union epoll_ref ref, uint32_t events,
>  		      const struct timespec *now);
>  int tcp_tap_handler(struct ctx *c, int af, const void *addr,
>  		    const struct pool *p, const struct timespec *now);
> -void tcp_sock_init(const struct ctx *c, int ns, sa_family_t af,
> -		   const void *addr, const char *ifname, in_port_t port);
> +void tcp_sock_init(const struct ctx *c, sa_family_t af, const void *addr,
> +		   const char *ifname, in_port_t port);
>  int tcp_init(struct ctx *c);
>  void tcp_timer(struct ctx *c, const struct timespec *ts);
>  void tcp_defer_handler(struct ctx *c);


  reply	other threads:[~2022-11-16 23:53 UTC|newest]

Thread overview: 57+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2022-11-16  4:41 [PATCH 00/32] Use dual stack sockets to listen for inbound TCP connections David Gibson
2022-11-16  4:41 ` [PATCH 01/32] clang-tidy: Suppress warning about assignments in if statements David Gibson
2022-11-16 23:10   ` Stefano Brivio
2022-11-17  1:20     ` David Gibson
2022-11-16  4:41 ` [PATCH 02/32] style: Minor corrections to function comments David Gibson
2022-11-16 23:11   ` Stefano Brivio
2022-11-17  1:21     ` David Gibson
2022-11-16  4:41 ` [PATCH 03/32] tcp_splice: #include tcp_splice.h in tcp_splice.c David Gibson
2022-11-16  4:41 ` [PATCH 04/32] tcp: Remove unused TCP_MAX_SOCKS constant David Gibson
2022-11-16  4:41 ` [PATCH 05/32] tcp: Better helpers for converting between connection pointer and index David Gibson
2022-11-16 23:11   ` Stefano Brivio
2022-11-17  1:24     ` David Gibson
2022-11-16  4:41 ` [PATCH 06/32] tcp_splice: Helpers for converting from index to/from tcp_splice_conn David Gibson
2022-11-16  4:41 ` [PATCH 07/32] tcp: Move connection state structures into a shared header David Gibson
2022-11-16  4:41 ` [PATCH 08/32] tcp: Add connection union type David Gibson
2022-11-16  4:41 ` [PATCH 09/32] tcp: Improved helpers to update connections after moving David Gibson
2022-11-16  4:41 ` [PATCH 10/32] tcp: Unify spliced and non-spliced connection tables David Gibson
2022-11-16  4:41 ` [PATCH 11/32] tcp: Unify tcp_defer_handler and tcp_splice_defer_handler() David Gibson
2022-11-16  4:41 ` [PATCH 12/32] tcp: Partially unify tcp_timer() and tcp_splice_timer() David Gibson
2022-11-16  4:41 ` [PATCH 13/32] tcp: Unify the IN_EPOLL flag David Gibson
2022-11-16  4:41 ` [PATCH 14/32] tcp: Separate helpers to create ns listening sockets David Gibson
2022-11-16 23:51   ` Stefano Brivio [this message]
2022-11-17  1:32     ` David Gibson
2022-11-16  4:41 ` [PATCH 15/32] tcp: Unify part of spliced and non-spliced conn_from_sock path David Gibson
2022-11-16 23:53   ` Stefano Brivio
2022-11-17  1:37     ` David Gibson
2022-11-17  7:30       ` Stefano Brivio
2022-11-17  8:58         ` David Gibson
2022-11-16  4:41 ` [PATCH 16/32] tcp: Use the same sockets to listen for spliced and non-spliced connections David Gibson
2022-11-16 23:54   ` Stefano Brivio
2022-11-17  1:43     ` David Gibson
2022-11-16  4:41 ` [PATCH 17/32] tcp: Remove splice from tcp_epoll_ref David Gibson
2022-11-16  4:41 ` [PATCH 18/32] tcp: Don't store hash bucket in connection structures David Gibson
2022-11-16  4:41 ` [PATCH 19/32] inany: Helper functions for handling addresses which could be IPv4 or IPv6 David Gibson
2022-11-16 23:54   ` Stefano Brivio
2022-11-17  1:48     ` David Gibson
2022-11-16  4:42 ` [PATCH 20/32] tcp: Hash IPv4 and IPv4-mapped-IPv6 addresses the same David Gibson
2022-11-16  4:42 ` [PATCH 21/32] tcp: Take tcp_hash_insert() address from struct tcp_conn David Gibson
2022-11-16  4:42 ` [PATCH 22/32] tcp: Simplify tcp_hash_match() to take an inany_addr David Gibson
2022-11-16  4:42 ` [PATCH 23/32] tcp: Unify initial sequence number calculation for IPv4 and IPv6 David Gibson
2022-11-16  4:42 ` [PATCH 24/32] tcp: Have tcp_seq_init() take its parameters from struct tcp_conn David Gibson
2022-11-16  4:42 ` [PATCH 25/32] tcp: Fix small errors in tcp_seq_init() time handling David Gibson
2022-11-16  4:42 ` [PATCH 26/32] tcp: Remove v6 flag from tcp_epoll_ref David Gibson
2022-11-17  0:15   ` Stefano Brivio
2022-11-17  1:50     ` David Gibson
2022-11-16  4:42 ` [PATCH 27/32] tcp: NAT IPv4-mapped IPv6 addresses like IPv4 addresses David Gibson
2022-11-17  0:15   ` Stefano Brivio
2022-11-17  2:00     ` David Gibson
2022-11-16  4:42 ` [PATCH 28/32] tcp_splice: Allow splicing of connections from IPv4-mapped loopback David Gibson
2022-11-17  0:15   ` Stefano Brivio
2022-11-17  2:05     ` David Gibson
2022-11-16  4:42 ` [PATCH 29/32] tcp: Consolidate tcp_sock_init[46] David Gibson
2022-11-16  4:42 ` [PATCH 30/32] util: Allow sock_l4() to open dual stack sockets David Gibson
2022-11-16  4:42 ` [PATCH 31/32] util: Always return -1 on error in sock_l4() David Gibson
2022-11-16  4:42 ` [PATCH 32/32] tcp: Use dual stack sockets for port forwarding when possible David Gibson
2022-11-17  0:15   ` Stefano Brivio
2022-11-17  2:08     ` David Gibson

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20221117005138.17007cb1@elisabeth \
    --to=sbrivio@redhat.com \
    --cc=david@gibson.dropbear.id.au \
    --cc=passt-dev@passt.top \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
Code repositories for project(s) associated with this public inbox

	https://passt.top/passt

This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for IMAP folder(s).