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 <asm/ioctls.h>
#include <trace/events/skb.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 "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

/*
 * Release an skbuff after use
 */
static void svc_release_skb(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;

		dprintk("svc: service %p, releasing skb %p\n", rqstp, skb);
		skb_free_datagram_locked(svsk->sk_sk, skb);
	}
}

static void svc_release_udp_skb(struct svc_rqst *rqstp)
{
	struct sk_buff *skb = rqstp->rq_xprt_ctxt;

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

		dprintk("svc: service %p, releasing skb %p\n", rqstp, skb);
		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;
	}
}

/*
 * send routine intended to be shared by the fore- and back-channel
 */
int svc_send_common(struct socket *sock, struct xdr_buf *xdr,
		    struct page *headpage, unsigned long headoffset,
		    struct page *tailpage, unsigned long tailoffset)
{
	int		result;
	int		size;
	struct page	**ppage = xdr->pages;
	size_t		base = xdr->page_base;
	unsigned int	pglen = xdr->page_len;
	unsigned int	flags = MSG_MORE | MSG_SENDPAGE_NOTLAST;
	int		slen;
	int		len = 0;

	slen = xdr->len;

	/* send head */
	if (slen == xdr->head[0].iov_len)
		flags = 0;
	len = kernel_sendpage(sock, headpage, headoffset,
				  xdr->head[0].iov_len, flags);
	if (len != xdr->head[0].iov_len)
		goto out;
	slen -= xdr->head[0].iov_len;
	if (slen == 0)
		goto out;

	/* send page data */
	size = PAGE_SIZE - base < pglen ? PAGE_SIZE - base : pglen;
	while (pglen > 0) {
		if (slen == size)
			flags = 0;
		result = kernel_sendpage(sock, *ppage, base, size, flags);
		if (result > 0)
			len += result;
		if (result != size)
			goto out;
		slen -= size;
		pglen -= size;
		size = PAGE_SIZE < pglen ? PAGE_SIZE : pglen;
		base = 0;
		ppage++;
	}

	/* send tail */
	if (xdr->tail[0].iov_len) {
		result = kernel_sendpage(sock, tailpage, tailoffset,
				   xdr->tail[0].iov_len, 0);
		if (result > 0)
			len += result;
	}

out:
	return len;
}


/*
 * Generic sendto routine
 */
static int svc_sendto(struct svc_rqst *rqstp, struct xdr_buf *xdr)
{
	struct svc_sock	*svsk =
		container_of(rqstp->rq_xprt, struct svc_sock, sk_xprt);
	struct socket	*sock = svsk->sk_sock;
	union {
		struct cmsghdr	hdr;
		long		all[SVC_PKTINFO_SPACE / sizeof(long)];
	} buffer;
	struct cmsghdr *cmh = &buffer.hdr;
	int		len = 0;
	unsigned long tailoff;
	unsigned long headoff;
	RPC_IFDEBUG(char buf[RPC_MAX_ADDRBUFLEN]);

	if (rqstp->rq_prot == IPPROTO_UDP) {
		struct msghdr msg = {
			.msg_name	= &rqstp->rq_addr,
			.msg_namelen	= rqstp->rq_addrlen,
			.msg_control	= cmh,
			.msg_controllen	= sizeof(buffer),
			.msg_flags	= MSG_MORE,
		};

		svc_set_cmsg_data(rqstp, cmh);

		if (sock_sendmsg(sock, &msg) < 0)
			goto out;
	}

	tailoff = ((unsigned long)xdr->tail[0].iov_base) & (PAGE_SIZE-1);
	headoff = 0;
	len = svc_send_common(sock, xdr, rqstp->rq_respages[0], headoff,
			       rqstp->rq_respages[0], tailoff);

out:
	dprintk("svc: socket %p sendto([%p %zu... ], %d) = %d (addr %s)\n",
		svsk, xdr->head[0].iov_base, xdr->head[0].iov_len,
		xdr->len, len, svc_print_addr(rqstp, buf, sizeof(buf)));

	return len;
}

/*
 * 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_ENAB