linux/net/sunrpc/svcsock.c

// SPDX-License-Identifier: GPL-2.0-only
/*
 * linux/net/sunrpc/svcsock.c
 *
 * These are the RPC server socket internals.
 *
 * The server scheduling algorithm does not always distribute the load
 * evenly when servicing a single client. May need to modify the
 * svc_xprt_enqueue procedure...
 *
 * TCP support is largely untested and may be a little slow. The problem
 * is that we currently do two separate recvfrom's, one for the 4-byte
 * record length, and the second for the actual record. This could possibly
 * be improved by always reading a minimum size of around 100 bytes and
 * tucking any superfluous bytes away in a temporary store. Still, that
 * leaves write requests out in the rain. An alternative may be to peek at
 * the first skb in the queue, and if it matches the next TCP sequence
 * number, to extract the record marker. Yuck.
 *
 * Copyright (C) 1995, 1996 Olaf Kirch <[email protected]>
 */

#include <linux/kernel.h>
#include <linux/sched.h>
#include <linux/module.h>
#include <linux/errno.h>
#include <linux/fcntl.h>
#include <linux/net.h>
#include <linux/in.h>
#include <linux/inet.h>
#include <linux/udp.h>
#include <linux/tcp.h>
#include <linux/unistd.h>
#include <linux/slab.h>
#include <linux/netdevice.h>
#include <linux/skbuff.h>
#include <linux/file.h>
#include <linux/freezer.h>
#include <linux/bvec.h>

#include <net/sock.h>
#include <net/checksum.h>
#include <net/ip.h>
#include <net/ipv6.h>
#include <net/udp.h>
#include <net/tcp.h>
#include <net/tcp_states.h>
#include <net/tls_prot.h>
#include <net/handshake.h>
#include <linux/uaccess.h>
#include <linux/highmem.h>
#include <asm/ioctls.h>
#include <linux/key.h>

#include <linux/sunrpc/types.h>
#include <linux/sunrpc/clnt.h>
#include <linux/sunrpc/xdr.h>
#include <linux/sunrpc/msg_prot.h>
#include <linux/sunrpc/svcsock.h>
#include <linux/sunrpc/stats.h>
#include <linux/sunrpc/xprt.h>

#include <trace/events/sock.h>
#include <trace/events/sunrpc.h>

#include "socklib.h"
#include "sunrpc.h"

#define RPCDBG_FACILITY …

/* To-do: to avoid tying up an nfsd thread while waiting for a
 * handshake request, the request could instead be deferred.
 */
enum { … };

static struct svc_sock *svc_setup_socket(struct svc_serv *, struct socket *,
					 int flags);
static int		svc_udp_recvfrom(struct svc_rqst *);
static int		svc_udp_sendto(struct svc_rqst *);
static void		svc_sock_detach(struct svc_xprt *);
static void		svc_tcp_sock_detach(struct svc_xprt *);
static void		svc_sock_free(struct svc_xprt *);

static struct svc_xprt *svc_create_socket(struct svc_serv *, int,
					  struct net *, struct sockaddr *,
					  int, int);
#ifdef CONFIG_DEBUG_LOCK_ALLOC
static struct lock_class_key svc_key[2];
static struct lock_class_key svc_slock_key[2];

static void svc_reclassify_socket(struct socket *sock)
{ … }
#else
static void svc_reclassify_socket(struct socket *sock)
{
}
#endif

/**
 * svc_tcp_release_ctxt - Release transport-related resources
 * @xprt: the transport which owned the context
 * @ctxt: the context from rqstp->rq_xprt_ctxt or dr->xprt_ctxt
 *
 */
static void svc_tcp_release_ctxt(struct svc_xprt *xprt, void *ctxt)
{ … }

/**
 * svc_udp_release_ctxt - Release transport-related resources
 * @xprt: the transport which owned the context
 * @ctxt: the context from rqstp->rq_xprt_ctxt or dr->xprt_ctxt
 *
 */
static void svc_udp_release_ctxt(struct svc_xprt *xprt, void *ctxt)
{ … }

svc_pktinfo_u;
#define SVC_PKTINFO_SPACE …

static void svc_set_cmsg_data(struct svc_rqst *rqstp, struct cmsghdr *cmh)
{ … }

static int svc_sock_result_payload(struct svc_rqst *rqstp, unsigned int offset,
				   unsigned int length)
{ … }

/*
 * Report socket names for nfsdfs
 */
static int svc_one_sock_name(struct svc_sock *svsk, char *buf, int remaining)
{ … }

static int
svc_tcp_sock_process_cmsg(struct socket *sock, struct msghdr *msg,
			  struct cmsghdr *cmsg, int ret)
{ … }

static int
svc_tcp_sock_recv_cmsg(struct svc_sock *svsk, struct msghdr *msg)
{ … }

#if ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE
static void svc_flush_bvec(const struct bio_vec *bvec, size_t size, size_t seek)
{
	struct bvec_iter bi = {
		.bi_size	= size + seek,
	};
	struct bio_vec bv;

	bvec_iter_advance(bvec, &bi, seek & PAGE_MASK);
	for_each_bvec(bv, bvec, bi, bi)
		flush_dcache_page(bv.bv_page);
}
#else
static inline void svc_flush_bvec(const struct bio_vec *bvec, size_t size,
				  size_t seek)
{ … }
#endif

/*
 * Read from @rqstp's transport socket. The incoming message fills whole
 * pages in @rqstp's rq_pages array until the last page of the message
 * has been received into a partial page.
 */
static ssize_t svc_tcp_read_msg(struct svc_rqst *rqstp, size_t buflen,
				size_t seek)
{ … }

/*
 * Set socket snd and rcv buffer lengths
 */
static void svc_sock_setbufsize(struct svc_sock *svsk, unsigned int nreqs)
{ … }

static void svc_sock_secure_port(struct svc_rqst *rqstp)
{ … }

/*
 * INET callback when data has been received on the socket.
 */
static void svc_data_ready(struct sock *sk)
{ … }

/*
 * INET callback when space is newly available on the socket.
 */
static void svc_write_space(struct sock *sk)
{ … }

static int svc_tcp_has_wspace(struct svc_xprt *xprt)
{ … }

static void svc_tcp_kill_temp_xprt(struct svc_xprt *xprt)
{ … }

/**
 * svc_tcp_handshake_done - Handshake completion handler
 * @data: address of xprt to wake
 * @status: status of handshake
 * @peerid: serial number of key containing the remote peer's identity
 *
 * If a security policy is specified as an export option, we don't
 * have a specific export here to check. So we set a "TLS session
 * is present" flag on the xprt and let an upper layer enforce local
 * security policy.
 */
static void svc_tcp_handshake_done(void *data, int status, key_serial_t peerid)
{ … }

/**
 * svc_tcp_handshake - Perform a transport-layer security handshake
 * @xprt: connected transport endpoint
 *
 */
static void svc_tcp_handshake(struct svc_xprt *xprt)
{ … }

/*
 * See net/ipv6/ip_sockglue.c : ip_cmsg_recv_pktinfo
 */
static int svc_udp_get_dest_address4(struct svc_rqst *rqstp,
				     struct cmsghdr *cmh)
{ … }

/*
 * See net/ipv6/datagram.c : ip6_datagram_recv_ctl
 */
static int svc_udp_get_dest_address6(struct svc_rqst *rqstp,
				     struct cmsghdr *cmh)
{ … }

/*
 * Copy the UDP datagram's destination address to the rqstp structure.
 * The 'destination' address in this case is the address to which the
 * peer sent the datagram, i.e. our local address. For multihomed
 * hosts, this can change from msg to msg. Note that only the IP
 * address changes, the port number should remain the same.
 */
static int svc_udp_get_dest_address(struct svc_rqst *rqstp,
				    struct cmsghdr *cmh)
{ … }

/**
 * svc_udp_recvfrom - Receive a datagram from a UDP socket.
 * @rqstp: request structure into which to receive an RPC Call
 *
 * Called in a loop when XPT_DATA has been set.
 *
 * Returns:
 *   On success, the number of bytes in a received RPC Call, or
 *   %0 if a complete RPC Call message was not ready to return
 */
static int svc_udp_recvfrom(struct svc_rqst *rqstp)
{ … }

/**
 * svc_udp_sendto - Send out a reply on a UDP socket
 * @rqstp: completed svc_rqst
 *
 * xpt_mutex ensures @rqstp's whole message is written to the socket
 * without interruption.
 *
 * Returns the number of bytes sent, or a negative errno.
 */
static int svc_udp_sendto(struct svc_rqst *rqstp)
{ … }

static int svc_udp_has_wspace(struct svc_xprt *xprt)
{ … }

static struct svc_xprt *svc_udp_accept(struct svc_xprt *xprt)
{ … }

static void svc_udp_kill_temp_xprt(struct svc_xprt *xprt)
{ … }

static struct svc_xprt *svc_udp_create(struct svc_serv *serv,
				       struct net *net,
				       struct sockaddr *sa, int salen,
				       int flags)
{ … }

static const struct svc_xprt_ops svc_udp_ops = …;

static struct svc_xprt_class svc_udp_class = …;

static void svc_udp_init(struct svc_sock *svsk, struct svc_serv *serv)
{ … }

/*
 * A data_ready event on a listening socket means there's a connection
 * pending. Do not use state_change as a substitute for it.
 */
static void svc_tcp_listen_data_ready(struct sock *sk)
{ … }

/*
 * A state change on a connected socket means it's dying or dead.
 */
static void svc_tcp_state_change(struct sock *sk)
{ … }

/*
 * Accept a TCP connection
 */
static struct svc_xprt *svc_tcp_accept(struct svc_xprt *xprt)
{ … }

static size_t svc_tcp_restore_pages(struct svc_sock *svsk,
				    struct svc_rqst *rqstp)
{ … }

static void svc_tcp_save_pages(struct svc_sock *svsk, struct svc_rqst *rqstp)
{ … }

static void svc_tcp_clear_pages(struct svc_sock *svsk)
{ … }

/*
 * Receive fragment record header into sk_marker.
 */
static ssize_t svc_tcp_read_marker(struct svc_sock *svsk,
				   struct svc_rqst *rqstp)
{ … }

static int receive_cb_reply(struct svc_sock *svsk, struct svc_rqst *rqstp)
{ … }

static void svc_tcp_fragment_received(struct svc_sock *svsk)
{ … }

/**
 * svc_tcp_recvfrom - Receive data from a TCP socket
 * @rqstp: request structure into which to receive an RPC Call
 *
 * Called in a loop when XPT_DATA has been set.
 *
 * Read the 4-byte stream record marker, then use the record length
 * in that marker to set up exactly the resources needed to receive
 * the next RPC message into @rqstp.
 *
 * Returns:
 *   On success, the number of bytes in a received RPC Call, or
 *   %0 if a complete RPC Call message was not ready to return
 *
 * The zero return case handles partial receives and callback Replies.
 * The state of a partial receive is preserved in the svc_sock for
 * the next call to svc_tcp_recvfrom.
 */
static int svc_tcp_recvfrom(struct svc_rqst *rqstp)
{ … }

/*
 * MSG_SPLICE_PAGES is used exclusively to reduce the number of
 * copy operations in this path. Therefore the caller must ensure
 * that the pages backing @xdr are unchanging.
 */
static int svc_tcp_sendmsg(struct svc_sock *svsk, struct svc_rqst *rqstp,
			   rpc_fraghdr marker, unsigned int *sentp)
{ … }

/**
 * svc_tcp_sendto - Send out a reply on a TCP socket
 * @rqstp: completed svc_rqst
 *
 * xpt_mutex ensures @rqstp's whole message is written to the socket
 * without interruption.
 *
 * Returns the number of bytes sent, or a negative errno.
 */
static int svc_tcp_sendto(struct svc_rqst *rqstp)
{ … }

static struct svc_xprt *svc_tcp_create(struct svc_serv *serv,
				       struct net *net,
				       struct sockaddr *sa, int salen,
				       int flags)
{ … }

static const struct svc_xprt_ops svc_tcp_ops = …;

static struct svc_xprt_class svc_tcp_class = …;

void svc_init_xprt_sock(void)
{ … }

void svc_cleanup_xprt_sock(void)
{ … }

static void svc_tcp_init(struct svc_sock *svsk, struct svc_serv *serv)
{ … }

void svc_sock_update_bufs(struct svc_serv *serv)
{ … }
EXPORT_SYMBOL_GPL(…);

/*
 * Initialize socket for RPC use and create svc_sock struct
 */
static struct svc_sock *svc_setup_socket(struct svc_serv *serv,
						struct socket *sock,
						int flags)
{ … }

/**
 * svc_addsock - add a listener socket to an RPC service
 * @serv: pointer to RPC service to which to add a new listener
 * @net: caller's network namespace
 * @fd: file descriptor of the new listener
 * @name_return: pointer to buffer to fill in with name of listener
 * @len: size of the buffer
 * @cred: credential
 *
 * Fills in socket name and returns positive length of name if successful.
 * Name is terminated with '\n'.  On error, returns a negative errno
 * value.
 */
int svc_addsock(struct svc_serv *serv, struct net *net, const int fd,
		char *name_return, const size_t len, const struct cred *cred)
{ … }
EXPORT_SYMBOL_GPL(…);

/*
 * Create socket for RPC service.
 */
static struct svc_xprt *svc_create_socket(struct svc_serv *serv,
					  int protocol,
					  struct net *net,
					  struct sockaddr *sin, int len,
					  int flags)
{ … }

/*
 * Detach the svc_sock from the socket so that no
 * more callbacks occur.
 */
static void svc_sock_detach(struct svc_xprt *xprt)
{ … }

/*
 * Disconnect the socket, and reset the callbacks
 */
static void svc_tcp_sock_detach(struct svc_xprt *xprt)
{ … }

/*
 * Free the svc_sock's socket resources and the svc_sock itself.
 */
static void svc_sock_free(struct svc_xprt *xprt)
{ … }