path: root/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 <okir@monad.swb.de>
 */

#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 <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 <linux/uaccess.h>
#include <linux/highmem.h>
#include <asm/ioctls.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/sunrpc.h>

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

#define RPCDBG_FACILITY	RPCDBG_SVCXPRT


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)
{
	struct sock *sk = sock->sk;

	if (WARN_ON_ONCE(!sock_allow_reclassification(sk)))
		return;

	switch (sk->sk_family) {
	case AF_INET:
		sock_lock_init_class_and_name(sk, "slock-AF_INET-NFSD",
					      &svc_slock_key[0],
					      "sk_xprt.xpt_lock-AF_INET-NFSD",
					      &svc_key[0]);
		break;

	case AF_INET6:
		sock_lock_init_class_and_name(sk, "slock-AF_INET6-NFSD",
					      &svc_slock_key[1],
					      "sk_xprt.xpt_lock-AF_INET6-NFSD",
					      &svc_key[1]);
		break;

	default:
		BUG();
	}
}
#else
static void svc_reclassify_socket(struct socket *sock)
{
}
#endif

/**
 * svc_tcp_release_rqst - Release transport-related resources
 * @rqstp: request structure with resources to be released
 *
 */
static void svc_tcp_release_rqst(struct svc_rqst *rqstp)
{
	struct sk_buff *skb = rqstp->rq_xprt_ctxt;

	if (skb) {
		struct svc_sock *svsk =
			container_of(rqstp->rq_xprt, struct svc_sock, sk_xprt);

		rqstp->rq_xprt_ctxt = NULL;
		skb_free_datagram_locked(svsk->sk_sk, skb);
	}
}

/**
 * svc_udp_release_rqst - Release transport-related resources
 * @rqstp: request structure with resources to be released
 *
 */
static void svc_udp_release_rqst(struct svc_rqst *rqstp)
{
	struct sk_buff *skb = rqstp->rq_xprt_ctxt;

	if (skb) {
		rqstp->rq_xprt_ctxt = NULL;
		consume_skb(skb);
	}
}

union svc_pktinfo_u {
	struct in_pktinfo pkti;
	struct in6_pktinfo pkti6;
};
#define SVC_PKTINFO_SPACE \
	CMSG_SPACE(sizeof(union svc_pktinfo_u))

static void svc_set_cmsg_data(struct svc_rqst *rqstp, struct cmsghdr *cmh)
{
	struct svc_sock *svsk =
		container_of(rqstp->rq_xprt, struct svc_sock, sk_xprt);
	switch (svsk->sk_sk->sk_family) {
	case AF_INET: {
			struct in_pktinfo *pki = CMSG_DATA(cmh);

			cmh->cmsg_level = SOL_IP;
			cmh->cmsg_type = IP_PKTINFO;
			pki->ipi_ifindex = 0;
			pki->ipi_spec_dst.s_addr =
				 svc_daddr_in(rqstp)->sin_addr.s_addr;
			cmh->cmsg_len = CMSG_LEN(sizeof(*pki));
		}
		break;

	case AF_INET6: {
			struct in6_pktinfo *pki = CMSG_DATA(cmh);
			struct sockaddr_in6 *daddr = svc_daddr_in6(rqstp);

			cmh->cmsg_level = SOL_IPV6;
			cmh->cmsg_type = IPV6_PKTINFO;
			pki->ipi6_ifindex = daddr->sin6_scope_id;
			pki->ipi6_addr = daddr->sin6_addr;
			cmh->cmsg_len = CMSG_LEN(sizeof(*pki));
		}
		break;
	}
}

static int svc_sock_result_payload(struct svc_rqst *rqstp, unsigned int offset,
				   unsigned int length)
{
	return 0;
}

/*
 * Report socket names for nfsdfs
 */
static int svc_one_sock_name(struct svc_sock *svsk, char *buf, int remaining)
{
	const struct sock *sk = svsk->sk_sk;
	const char *proto_name = sk->sk_protocol == IPPROTO_UDP ?
							"udp" : "tcp";
	int len;

	switch (sk->sk_family) {
	case PF_INET:
		len = snprintf(buf, remaining, "ipv4 %s %pI4 %d\n",
				proto_name,
				&inet_sk(sk)->inet_rcv_saddr,
				inet_sk(sk)->inet_num);
		break;
#if IS_ENABLED(CONFIG_IPV6)
	case PF_INET6:
		len = snprintf(buf, remaining, "ipv6 %s %pI6 %d\n",
				proto_name,
				&sk->sk_v6_rcv_saddr,
				inet_sk(sk)->inet_num);
		break;
#endif
	default:
		len = snprintf(buf, remaining, "*unknown-%d*\n",
				sk->sk_family);
	}

	if (len >= remaining) {
		*buf = '\0';
		return -ENAMETOOLONG;
	}
	return len;
}

#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)
{
	struct svc_sock *svsk =
		container_of(rqstp->rq_xprt, struct svc_sock, sk_xprt);
	struct bio_vec *bvec = rqstp->rq_bvec;
	struct msghdr msg = { NULL };
	unsigned int i;
	ssize_t len;
	size_t t;

	rqstp->rq_xprt_hlen = 0;

	clear_bit(XPT_DATA, &svsk->sk_xprt.xpt_flags);

	for (i = 0, t = 0; t < buflen; i++, t += PAGE_SIZE) {
		bvec[i].bv_page = rqstp->rq_pages[i];
		bvec[i].bv_len = PAGE_SIZE;
		bvec[i].bv_offset = 0;
	}
	rqstp->rq_respages = &rqstp->rq_pages[i];
	rqstp->rq_next_page = rqstp->rq_respages + 1;

	iov_iter_bvec(&msg.msg_iter, READ, bvec, i, buflen);
	if (seek) {
		iov_iter_advance(&msg.msg_iter, seek);
		buflen -= seek;
	}
	len = sock_recvmsg(svsk->sk_sock, &msg, MSG_DONTWAIT);
	if (len > 0)
		svc_flush_bvec(bvec, len, seek);

	/* If we read a full record, then assume there may be more
	 * data to read (stream based sockets only!)
	 */
	if (len == buflen)
		set_bit(XPT_DATA, &svsk->sk_xprt.xpt_flags);

	return len;
}

/*
 * Set socket snd and rcv buffer lengths
 */
static void svc_sock_setbufsize(struct svc_sock *svsk, unsigned int nreqs)
{
	unsigned int max_mesg = svsk->sk_xprt.xpt_server->sv_max_mesg;
	struct socket *sock = svsk->sk_sock;

	nreqs = min(nreqs, INT_MAX / 2 / max_mesg);

	lock_sock(sock->sk);
	sock->sk->sk_sndbuf = nreqs * max_mesg * 2;
	sock->sk->sk_rcvbuf = nreqs * max_mesg * 2;
	sock->sk->sk_write_space(sock->sk);
	release_sock(sock-