linux/net/sunrpc/svcsock.c

1520 lines
38 KiB
C
Raw Normal View History

/*
* 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>
nfsd41: sunrpc: Added rpc server-side backchannel handling When the call direction is a reply, copy the xid and call direction into the req->rq_private_buf.head[0].iov_base otherwise rpc_verify_header returns rpc_garbage. Signed-off-by: Rahul Iyer <iyer@netapp.com> Signed-off-by: Mike Sager <sager@netapp.com> Signed-off-by: Marc Eshel <eshel@almaden.ibm.com> Signed-off-by: Benny Halevy <bhalevy@panasas.com> Signed-off-by: Ricardo Labiaga <Ricardo.Labiaga@netapp.com> Signed-off-by: Andy Adamson <andros@netapp.com> Signed-off-by: Benny Halevy <bhalevy@panasas.com> [get rid of CONFIG_NFSD_V4_1] [sunrpc: refactoring of svc_tcp_recvfrom] [nfsd41: sunrpc: create common send routine for the fore and the back channels] [nfsd41: sunrpc: Use free_page() to free server backchannel pages] [nfsd41: sunrpc: Document server backchannel locking] [nfsd41: sunrpc: remove bc_connect_worker()] [nfsd41: sunrpc: Define xprt_server_backchannel()[ [nfsd41: sunrpc: remove bc_close and bc_init_auto_disconnect dummy functions] [nfsd41: sunrpc: eliminate unneeded switch statement in xs_setup_tcp()] [nfsd41: sunrpc: Don't auto close the server backchannel connection] [nfsd41: sunrpc: Remove unused functions] Signed-off-by: Alexandros Batsakis <batsakis@netapp.com> Signed-off-by: Ricardo Labiaga <Ricardo.Labiaga@netapp.com> Signed-off-by: Benny Halevy <bhalevy@panasas.com> [nfsd41: change bc_sock to bc_xprt] [nfsd41: sunrpc: move struct rpc_buffer def into a common header file] [nfsd41: sunrpc: use rpc_sleep in bc_send_request so not to block on mutex] [removed cosmetic changes] Signed-off-by: Benny Halevy <bhalevy@panasas.com> [sunrpc: add new xprt class for nfsv4.1 backchannel] [sunrpc: v2.1 change handling of auto_close and init_auto_disconnect operations for the nfsv4.1 backchannel] Signed-off-by: Alexandros Batsakis <batsakis@netapp.com> [reverted more cosmetic leftovers] [got rid of xprt_server_backchannel] [separated "nfsd41: sunrpc: add new xprt class for nfsv4.1 backchannel"] Signed-off-by: Benny Halevy <bhalevy@panasas.com> Cc: Trond Myklebust <trond.myklebust@netapp.com> [sunrpc: change idle timeout value for the backchannel] Signed-off-by: Alexandros Batsakis <batsakis@netapp.com> Signed-off-by: Benny Halevy <bhalevy@panasas.com> Acked-by: Trond Myklebust <trond.myklebust@netapp.com> Signed-off-by: J. Bruce Fields <bfields@citi.umich.edu>
2009-09-10 22:32:28 +08:00
#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;
}
}
/*
nfsd41: sunrpc: Added rpc server-side backchannel handling When the call direction is a reply, copy the xid and call direction into the req->rq_private_buf.head[0].iov_base otherwise rpc_verify_header returns rpc_garbage. Signed-off-by: Rahul Iyer <iyer@netapp.com> Signed-off-by: Mike Sager <sager@netapp.com> Signed-off-by: Marc Eshel <eshel@almaden.ibm.com> Signed-off-by: Benny Halevy <bhalevy@panasas.com> Signed-off-by: Ricardo Labiaga <Ricardo.Labiaga@netapp.com> Signed-off-by: Andy Adamson <andros@netapp.com> Signed-off-by: Benny Halevy <bhalevy@panasas.com> [get rid of CONFIG_NFSD_V4_1] [sunrpc: refactoring of svc_tcp_recvfrom] [nfsd41: sunrpc: create common send routine for the fore and the back channels] [nfsd41: sunrpc: Use free_page() to free server backchannel pages] [nfsd41: sunrpc: Document server backchannel locking] [nfsd41: sunrpc: remove bc_connect_worker()] [nfsd41: sunrpc: Define xprt_server_backchannel()[ [nfsd41: sunrpc: remove bc_close and bc_init_auto_disconnect dummy functions] [nfsd41: sunrpc: eliminate unneeded switch statement in xs_setup_tcp()] [nfsd41: sunrpc: Don't auto close the server backchannel connection] [nfsd41: sunrpc: Remove unused functions] Signed-off-by: Alexandros Batsakis <batsakis@netapp.com> Signed-off-by: Ricardo Labiaga <Ricardo.Labiaga@netapp.com> Signed-off-by: Benny Halevy <bhalevy@panasas.com> [nfsd41: change bc_sock to bc_xprt] [nfsd41: sunrpc: move struct rpc_buffer def into a common header file] [nfsd41: sunrpc: use rpc_sleep in bc_send_request so not to block on mutex] [removed cosmetic changes] Signed-off-by: Benny Halevy <bhalevy@panasas.com> [sunrpc: add new xprt class for nfsv4.1 backchannel] [sunrpc: v2.1 change handling of auto_close and init_auto_disconnect operations for the nfsv4.1 backchannel] Signed-off-by: Alexandros Batsakis <batsakis@netapp.com> [reverted more cosmetic leftovers] [got rid of xprt_server_backchannel] [separated "nfsd41: sunrpc: add new xprt class for nfsv4.1 backchannel"] Signed-off-by: Benny Halevy <bhalevy@panasas.com> Cc: Trond Myklebust <trond.myklebust@netapp.com> [sunrpc: change idle timeout value for the backchannel] Signed-off-by: Alexandros Batsakis <batsakis@netapp.com> Signed-off-by: Benny Halevy <bhalevy@panasas.com> Acked-by: Trond Myklebust <trond.myklebust@netapp.com> Signed-off-by: J. Bruce Fields <bfields@citi.umich.edu>
2009-09-10 22:32:28 +08:00
* send routine intended to be shared by the fore- and back-channel
*/
nfsd41: sunrpc: Added rpc server-side backchannel handling When the call direction is a reply, copy the xid and call direction into the req->rq_private_buf.head[0].iov_base otherwise rpc_verify_header returns rpc_garbage. Signed-off-by: Rahul Iyer <iyer@netapp.com> Signed-off-by: Mike Sager <sager@netapp.com> Signed-off-by: Marc Eshel <eshel@almaden.ibm.com> Signed-off-by: Benny Halevy <bhalevy@panasas.com> Signed-off-by: Ricardo Labiaga <Ricardo.Labiaga@netapp.com> Signed-off-by: Andy Adamson <andros@netapp.com> Signed-off-by: Benny Halevy <bhalevy@panasas.com> [get rid of CONFIG_NFSD_V4_1] [sunrpc: refactoring of svc_tcp_recvfrom] [nfsd41: sunrpc: create common send routine for the fore and the back channels] [nfsd41: sunrpc: Use free_page() to free server backchannel pages] [nfsd41: sunrpc: Document server backchannel locking] [nfsd41: sunrpc: remove bc_connect_worker()] [nfsd41: sunrpc: Define xprt_server_backchannel()[ [nfsd41: sunrpc: remove bc_close and bc_init_auto_disconnect dummy functions] [nfsd41: sunrpc: eliminate unneeded switch statement in xs_setup_tcp()] [nfsd41: sunrpc: Don't auto close the server backchannel connection] [nfsd41: sunrpc: Remove unused functions] Signed-off-by: Alexandros Batsakis <batsakis@netapp.com> Signed-off-by: Ricardo Labiaga <Ricardo.Labiaga@netapp.com> Signed-off-by: Benny Halevy <bhalevy@panasas.com> [nfsd41: change bc_sock to bc_xprt] [nfsd41: sunrpc: move struct rpc_buffer def into a common header file] [nfsd41: sunrpc: use rpc_sleep in bc_send_request so not to block on mutex] [removed cosmetic changes] Signed-off-by: Benny Halevy <bhalevy@panasas.com> [sunrpc: add new xprt class for nfsv4.1 backchannel] [sunrpc: v2.1 change handling of auto_close and init_auto_disconnect operations for the nfsv4.1 backchannel] Signed-off-by: Alexandros Batsakis <batsakis@netapp.com> [reverted more cosmetic leftovers] [got rid of xprt_server_backchannel] [separated "nfsd41: sunrpc: add new xprt class for nfsv4.1 backchannel"] Signed-off-by: Benny Halevy <bhalevy@panasas.com> Cc: Trond Myklebust <trond.myklebust@netapp.com> [sunrpc: change idle timeout value for the backchannel] Signed-off-by: Alexandros Batsakis <batsakis@netapp.com> Signed-off-by: Benny Halevy <bhalevy@panasas.com> Acked-by: Trond Myklebust <trond.myklebust@netapp.com> Signed-off-by: J. Bruce Fields <bfields@citi.umich.edu>
2009-09-10 22:32:28 +08:00
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;
nfsd41: sunrpc: Added rpc server-side backchannel handling When the call direction is a reply, copy the xid and call direction into the req->rq_private_buf.head[0].iov_base otherwise rpc_verify_header returns rpc_garbage. Signed-off-by: Rahul Iyer <iyer@netapp.com> Signed-off-by: Mike Sager <sager@netapp.com> Signed-off-by: Marc Eshel <eshel@almaden.ibm.com> Signed-off-by: Benny Halevy <bhalevy@panasas.com> Signed-off-by: Ricardo Labiaga <Ricardo.Labiaga@netapp.com> Signed-off-by: Andy Adamson <andros@netapp.com> Signed-off-by: Benny Halevy <bhalevy@panasas.com> [get rid of CONFIG_NFSD_V4_1] [sunrpc: refactoring of svc_tcp_recvfrom] [nfsd41: sunrpc: create common send routine for the fore and the back channels] [nfsd41: sunrpc: Use free_page() to free server backchannel pages] [nfsd41: sunrpc: Document server backchannel locking] [nfsd41: sunrpc: remove bc_connect_worker()] [nfsd41: sunrpc: Define xprt_server_backchannel()[ [nfsd41: sunrpc: remove bc_close and bc_init_auto_disconnect dummy functions] [nfsd41: sunrpc: eliminate unneeded switch statement in xs_setup_tcp()] [nfsd41: sunrpc: Don't auto close the server backchannel connection] [nfsd41: sunrpc: Remove unused functions] Signed-off-by: Alexandros Batsakis <batsakis@netapp.com> Signed-off-by: Ricardo Labiaga <Ricardo.Labiaga@netapp.com> Signed-off-by: Benny Halevy <bhalevy@panasas.com> [nfsd41: change bc_sock to bc_xprt] [nfsd41: sunrpc: move struct rpc_buffer def into a common header file] [nfsd41: sunrpc: use rpc_sleep in bc_send_request so not to block on mutex] [removed cosmetic changes] Signed-off-by: Benny Halevy <bhalevy@panasas.com> [sunrpc: add new xprt class for nfsv4.1 backchannel] [sunrpc: v2.1 change handling of auto_close and init_auto_disconnect operations for the nfsv4.1 backchannel] Signed-off-by: Alexandros Batsakis <batsakis@netapp.com> [reverted more cosmetic leftovers] [got rid of xprt_server_backchannel] [separated "nfsd41: sunrpc: add new xprt class for nfsv4.1 backchannel"] Signed-off-by: Benny Halevy <bhalevy@panasas.com> Cc: Trond Myklebust <trond.myklebust@netapp.com> [sunrpc: change idle timeout value for the backchannel] Signed-off-by: Alexandros Batsakis <batsakis@netapp.com> Signed-off-by: Benny Halevy <bhalevy@panasas.com> Acked-by: Trond Myklebust <trond.myklebust@netapp.com> Signed-off-by: J. Bruce Fields <bfields@citi.umich.edu>
2009-09-10 22:32:28 +08:00
int slen;
int len = 0;
slen = xdr->len;
/* send head */
if (slen == xdr->head[0].iov_len)
flags = 0;
nfsd41: sunrpc: Added rpc server-side backchannel handling When the call direction is a reply, copy the xid and call direction into the req->rq_private_buf.head[0].iov_base otherwise rpc_verify_header returns rpc_garbage. Signed-off-by: Rahul Iyer <iyer@netapp.com> Signed-off-by: Mike Sager <sager@netapp.com> Signed-off-by: Marc Eshel <eshel@almaden.ibm.com> Signed-off-by: Benny Halevy <bhalevy@panasas.com> Signed-off-by: Ricardo Labiaga <Ricardo.Labiaga@netapp.com> Signed-off-by: Andy Adamson <andros@netapp.com> Signed-off-by: Benny Halevy <bhalevy@panasas.com> [get rid of CONFIG_NFSD_V4_1] [sunrpc: refactoring of svc_tcp_recvfrom] [nfsd41: sunrpc: create common send routine for the fore and the back channels] [nfsd41: sunrpc: Use free_page() to free server backchannel pages] [nfsd41: sunrpc: Document server backchannel locking] [nfsd41: sunrpc: remove bc_connect_worker()] [nfsd41: sunrpc: Define xprt_server_backchannel()[ [nfsd41: sunrpc: remove bc_close and bc_init_auto_disconnect dummy functions] [nfsd41: sunrpc: eliminate unneeded switch statement in xs_setup_tcp()] [nfsd41: sunrpc: Don't auto close the server backchannel connection] [nfsd41: sunrpc: Remove unused functions] Signed-off-by: Alexandros Batsakis <batsakis@netapp.com> Signed-off-by: Ricardo Labiaga <Ricardo.Labiaga@netapp.com> Signed-off-by: Benny Halevy <bhalevy@panasas.com> [nfsd41: change bc_sock to bc_xprt] [nfsd41: sunrpc: move struct rpc_buffer def into a common header file] [nfsd41: sunrpc: use rpc_sleep in bc_send_request so not to block on mutex] [removed cosmetic changes] Signed-off-by: Benny Halevy <bhalevy@panasas.com> [sunrpc: add new xprt class for nfsv4.1 backchannel] [sunrpc: v2.1 change handling of auto_close and init_auto_disconnect operations for the nfsv4.1 backchannel] Signed-off-by: Alexandros Batsakis <batsakis@netapp.com> [reverted more cosmetic leftovers] [got rid of xprt_server_backchannel] [separated "nfsd41: sunrpc: add new xprt class for nfsv4.1 backchannel"] Signed-off-by: Benny Halevy <bhalevy@panasas.com> Cc: Trond Myklebust <trond.myklebust@netapp.com> [sunrpc: change idle timeout value for the backchannel] Signed-off-by: Alexandros Batsakis <batsakis@netapp.com> Signed-off-by: Benny Halevy <bhalevy@panasas.com> Acked-by: Trond Myklebust <trond.myklebust@netapp.com> Signed-off-by: J. Bruce Fields <bfields@citi.umich.edu>
2009-09-10 22:32:28 +08:00
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++;
}
nfsd41: sunrpc: Added rpc server-side backchannel handling When the call direction is a reply, copy the xid and call direction into the req->rq_private_buf.head[0].iov_base otherwise rpc_verify_header returns rpc_garbage. Signed-off-by: Rahul Iyer <iyer@netapp.com> Signed-off-by: Mike Sager <sager@netapp.com> Signed-off-by: Marc Eshel <eshel@almaden.ibm.com> Signed-off-by: Benny Halevy <bhalevy@panasas.com> Signed-off-by: Ricardo Labiaga <Ricardo.Labiaga@netapp.com> Signed-off-by: Andy Adamson <andros@netapp.com> Signed-off-by: Benny Halevy <bhalevy@panasas.com> [get rid of CONFIG_NFSD_V4_1] [sunrpc: refactoring of svc_tcp_recvfrom] [nfsd41: sunrpc: create common send routine for the fore and the back channels] [nfsd41: sunrpc: Use free_page() to free server backchannel pages] [nfsd41: sunrpc: Document server backchannel locking] [nfsd41: sunrpc: remove bc_connect_worker()] [nfsd41: sunrpc: Define xprt_server_backchannel()[ [nfsd41: sunrpc: remove bc_close and bc_init_auto_disconnect dummy functions] [nfsd41: sunrpc: eliminate unneeded switch statement in xs_setup_tcp()] [nfsd41: sunrpc: Don't auto close the server backchannel connection] [nfsd41: sunrpc: Remove unused functions] Signed-off-by: Alexandros Batsakis <batsakis@netapp.com> Signed-off-by: Ricardo Labiaga <Ricardo.Labiaga@netapp.com> Signed-off-by: Benny Halevy <bhalevy@panasas.com> [nfsd41: change bc_sock to bc_xprt] [nfsd41: sunrpc: move struct rpc_buffer def into a common header file] [nfsd41: sunrpc: use rpc_sleep in bc_send_request so not to block on mutex] [removed cosmetic changes] Signed-off-by: Benny Halevy <bhalevy@panasas.com> [sunrpc: add new xprt class for nfsv4.1 backchannel] [sunrpc: v2.1 change handling of auto_close and init_auto_disconnect operations for the nfsv4.1 backchannel] Signed-off-by: Alexandros Batsakis <batsakis@netapp.com> [reverted more cosmetic leftovers] [got rid of xprt_server_backchannel] [separated "nfsd41: sunrpc: add new xprt class for nfsv4.1 backchannel"] Signed-off-by: Benny Halevy <bhalevy@panasas.com> Cc: Trond Myklebust <trond.myklebust@netapp.com> [sunrpc: change idle timeout value for the backchannel] Signed-off-by: Alexandros Batsakis <batsakis@netapp.com> Signed-off-by: Benny Halevy <bhalevy@panasas.com> Acked-by: Trond Myklebust <trond.myklebust@netapp.com> Signed-off-by: J. Bruce Fields <bfields@citi.umich.edu>
2009-09-10 22:32:28 +08:00
/* send tail */
if (xdr->tail[0].iov_len) {
nfsd41: sunrpc: Added rpc server-side backchannel handling When the call direction is a reply, copy the xid and call direction into the req->rq_private_buf.head[0].iov_base otherwise rpc_verify_header returns rpc_garbage. Signed-off-by: Rahul Iyer <iyer@netapp.com> Signed-off-by: Mike Sager <sager@netapp.com> Signed-off-by: Marc Eshel <eshel@almaden.ibm.com> Signed-off-by: Benny Halevy <bhalevy@panasas.com> Signed-off-by: Ricardo Labiaga <Ricardo.Labiaga@netapp.com> Signed-off-by: Andy Adamson <andros@netapp.com> Signed-off-by: Benny Halevy <bhalevy@panasas.com> [get rid of CONFIG_NFSD_V4_1] [sunrpc: refactoring of svc_tcp_recvfrom] [nfsd41: sunrpc: create common send routine for the fore and the back channels] [nfsd41: sunrpc: Use free_page() to free server backchannel pages] [nfsd41: sunrpc: Document server backchannel locking] [nfsd41: sunrpc: remove bc_connect_worker()] [nfsd41: sunrpc: Define xprt_server_backchannel()[ [nfsd41: sunrpc: remove bc_close and bc_init_auto_disconnect dummy functions] [nfsd41: sunrpc: eliminate unneeded switch statement in xs_setup_tcp()] [nfsd41: sunrpc: Don't auto close the server backchannel connection] [nfsd41: sunrpc: Remove unused functions] Signed-off-by: Alexandros Batsakis <batsakis@netapp.com> Signed-off-by: Ricardo Labiaga <Ricardo.Labiaga@netapp.com> Signed-off-by: Benny Halevy <bhalevy@panasas.com> [nfsd41: change bc_sock to bc_xprt] [nfsd41: sunrpc: move struct rpc_buffer def into a common header file] [nfsd41: sunrpc: use rpc_sleep in bc_send_request so not to block on mutex] [removed cosmetic changes] Signed-off-by: Benny Halevy <bhalevy@panasas.com> [sunrpc: add new xprt class for nfsv4.1 backchannel] [sunrpc: v2.1 change handling of auto_close and init_auto_disconnect operations for the nfsv4.1 backchannel] Signed-off-by: Alexandros Batsakis <batsakis@netapp.com> [reverted more cosmetic leftovers] [got rid of xprt_server_backchannel] [separated "nfsd41: sunrpc: add new xprt class for nfsv4.1 backchannel"] Signed-off-by: Benny Halevy <bhalevy@panasas.com> Cc: Trond Myklebust <trond.myklebust@netapp.com> [sunrpc: change idle timeout value for the backchannel] Signed-off-by: Alexandros Batsakis <batsakis@netapp.com> Signed-off-by: Benny Halevy <bhalevy@panasas.com> Acked-by: Trond Myklebust <trond.myklebust@netapp.com> Signed-off-by: J. Bruce Fields <bfields@citi.umich.edu>
2009-09-10 22:32:28 +08:00
result = kernel_sendpage(sock, tailpage, tailoffset,
xdr->tail[0].iov_len, 0);
if (result > 0)
len += result;
}
nfsd41: sunrpc: Added rpc server-side backchannel handling When the call direction is a reply, copy the xid and call direction into the req->rq_private_buf.head[0].iov_base otherwise rpc_verify_header returns rpc_garbage. Signed-off-by: Rahul Iyer <iyer@netapp.com> Signed-off-by: Mike Sager <sager@netapp.com> Signed-off-by: Marc Eshel <eshel@almaden.ibm.com> Signed-off-by: Benny Halevy <bhalevy@panasas.com> Signed-off-by: Ricardo Labiaga <Ricardo.Labiaga@netapp.com> Signed-off-by: Andy Adamson <andros@netapp.com> Signed-off-by: Benny Halevy <bhalevy@panasas.com> [get rid of CONFIG_NFSD_V4_1] [sunrpc: refactoring of svc_tcp_recvfrom] [nfsd41: sunrpc: create common send routine for the fore and the back channels] [nfsd41: sunrpc: Use free_page() to free server backchannel pages] [nfsd41: sunrpc: Document server backchannel locking] [nfsd41: sunrpc: remove bc_connect_worker()] [nfsd41: sunrpc: Define xprt_server_backchannel()[ [nfsd41: sunrpc: remove bc_close and bc_init_auto_disconnect dummy functions] [nfsd41: sunrpc: eliminate unneeded switch statement in xs_setup_tcp()] [nfsd41: sunrpc: Don't auto close the server backchannel connection] [nfsd41: sunrpc: Remove unused functions] Signed-off-by: Alexandros Batsakis <batsakis@netapp.com> Signed-off-by: Ricardo Labiaga <Ricardo.Labiaga@netapp.com> Signed-off-by: Benny Halevy <bhalevy@panasas.com> [nfsd41: change bc_sock to bc_xprt] [nfsd41: sunrpc: move struct rpc_buffer def into a common header file] [nfsd41: sunrpc: use rpc_sleep in bc_send_request so not to block on mutex] [removed cosmetic changes] Signed-off-by: Benny Halevy <bhalevy@panasas.com> [sunrpc: add new xprt class for nfsv4.1 backchannel] [sunrpc: v2.1 change handling of auto_close and init_auto_disconnect operations for the nfsv4.1 backchannel] Signed-off-by: Alexandros Batsakis <batsakis@netapp.com> [reverted more cosmetic leftovers] [got rid of xprt_server_backchannel] [separated "nfsd41: sunrpc: add new xprt class for nfsv4.1 backchannel"] Signed-off-by: Benny Halevy <bhalevy@panasas.com> Cc: Trond Myklebust <trond.myklebust@netapp.com> [sunrpc: change idle timeout value for the backchannel] Signed-off-by: Alexandros Batsakis <batsakis@netapp.com> Signed-off-by: Benny Halevy <bhalevy@panasas.com> Acked-by: Trond Myklebust <trond.myklebust@netapp.com> Signed-off-by: J. Bruce Fields <bfields@citi.umich.edu>
2009-09-10 22:32:28 +08:00
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)
nfsd41: sunrpc: Added rpc server-side backchannel handling When the call direction is a reply, copy the xid and call direction into the req->rq_private_buf.head[0].iov_base otherwise rpc_verify_header returns rpc_garbage. Signed-off-by: Rahul Iyer <iyer@netapp.com> Signed-off-by: Mike Sager <sager@netapp.com> Signed-off-by: Marc Eshel <eshel@almaden.ibm.com> Signed-off-by: Benny Halevy <bhalevy@panasas.com> Signed-off-by: Ricardo Labiaga <Ricardo.Labiaga@netapp.com> Signed-off-by: Andy Adamson <andros@netapp.com> Signed-off-by: Benny Halevy <bhalevy@panasas.com> [get rid of CONFIG_NFSD_V4_1] [sunrpc: refactoring of svc_tcp_recvfrom] [nfsd41: sunrpc: create common send routine for the fore and the back channels] [nfsd41: sunrpc: Use free_page() to free server backchannel pages] [nfsd41: sunrpc: Document server backchannel locking] [nfsd41: sunrpc: remove bc_connect_worker()] [nfsd41: sunrpc: Define xprt_server_backchannel()[ [nfsd41: sunrpc: remove bc_close and bc_init_auto_disconnect dummy functions] [nfsd41: sunrpc: eliminate unneeded switch statement in xs_setup_tcp()] [nfsd41: sunrpc: Don't auto close the server backchannel connection] [nfsd41: sunrpc: Remove unused functions] Signed-off-by: Alexandros Batsakis <batsakis@netapp.com> Signed-off-by: Ricardo Labiaga <Ricardo.Labiaga@netapp.com> Signed-off-by: Benny Halevy <bhalevy@panasas.com> [nfsd41: change bc_sock to bc_xprt] [nfsd41: sunrpc: move struct rpc_buffer def into a common header file] [nfsd41: sunrpc: use rpc_sleep in bc_send_request so not to block on mutex] [removed cosmetic changes] Signed-off-by: Benny Halevy <bhalevy@panasas.com> [sunrpc: add new xprt class for nfsv4.1 backchannel] [sunrpc: v2.1 change handling of auto_close and init_auto_disconnect operations for the nfsv4.1 backchannel] Signed-off-by: Alexandros Batsakis <batsakis@netapp.com> [reverted more cosmetic leftovers] [got rid of xprt_server_backchannel] [separated "nfsd41: sunrpc: add new xprt class for nfsv4.1 backchannel"] Signed-off-by: Benny Halevy <bhalevy@panasas.com> Cc: Trond Myklebust <trond.myklebust@netapp.com> [sunrpc: change idle timeout value for the backchannel] Signed-off-by: Alexandros Batsakis <batsakis@netapp.com> Signed-off-by: Benny Halevy <bhalevy@panasas.com> Acked-by: Trond Myklebust <trond.myklebust@netapp.com> Signed-off-by: J. Bruce Fields <bfields@citi.umich.edu>
2009-09-10 22:32:28 +08:00
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_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;
}
/*
* Generic recvfrom routine.
*/
static ssize_t svc_recvfrom(struct svc_rqst *rqstp, struct kvec *iov,
unsigned int nr, size_t buflen, unsigned int base)
{
struct svc_sock *svsk =
container_of(rqstp->rq_xprt, struct svc_sock, sk_xprt);
struct msghdr msg = { NULL };
ssize_t len;
rqstp->rq_xprt_hlen = 0;
clear_bit(XPT_DATA, &svsk->sk_xprt.xpt_flags);
iov_iter_kvec(&msg.msg_iter, READ, iov, nr, buflen);
if (base != 0) {
iov_iter_advance(&msg.msg_iter, base);
buflen -= base;
}
len = sock_recvmsg(svsk->sk_sock, &msg, MSG_DONTWAIT);
/* 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);
dprintk("svc: socket %p recvfrom(%p, %zu) = %zd\n",
svsk, iov[0].iov_base, iov[0].iov_len, len);
return len;
}
/*
* Set socket snd and rcv buffer lengths
*/
static void svc_sock_setbufsize(struct socket *sock, unsigned int snd,
unsigned int rcv)
{
lock_sock(sock->sk);
sock->sk->sk_sndbuf = snd * 2;
sock->sk->sk_rcvbuf = rcv * 2;
sock->sk->sk_write_space(sock->sk);
release_sock(sock->sk);
}
static void svc_sock_secure_port(struct svc_rqst *rqstp)
{
if (svc_port_is_privileged(svc_addr(rqstp)))
set_bit(RQ_SECURE, &rqstp->rq_flags);
else
clear_bit(RQ_SECURE, &rqstp->rq_flags);
}
/*
* INET callback when data has been received on the socket.
*/
static void svc_data_ready(struct sock *sk)
{
struct svc_sock *svsk = (struct svc_sock *)sk->sk_user_data;
if (svsk) {
dprintk("svc: socket %p(inet %p), busy=%d\n",
svsk, sk,
test_bit(XPT_BUSY, &svsk->sk_xprt.xpt_flags));
net: sunrpc: svcsock: fix NULL-pointer exception While running nfs/connectathon tests kernel NULL-pointer exception has been observed due to races in svcsock.c. Race is appear when kernel accepts connection by kernel_accept (which creates new socket) and start queuing ingress packets to new socket. This happens in ksoftirq context which could run concurrently on a different core while new socket setup is not done yet. The fix is to re-order socket user data init sequence and add write/read barrier calls to be sure that we got proper values for callback pointers before actually calling them. Test results: nfs/connectathon reports '0' failed tests for about 200+ iterations. Crash log: ---<-snip->--- [ 6708.638984] Unable to handle kernel NULL pointer dereference at virtual address 00000000 [ 6708.647093] pgd = ffff0000094e0000 [ 6708.650497] [00000000] *pgd=0000010ffff90003, *pud=0000010ffff90003, *pmd=0000010ffff80003, *pte=0000000000000000 [ 6708.660761] Internal error: Oops: 86000005 [#1] SMP [ 6708.665630] Modules linked in: nfsv3 nfnetlink_queue nfnetlink_log nfnetlink rpcsec_gss_krb5 nfsv4 dns_resolver nfs fscache overlay xt_CONNSECMARK xt_SECMARK xt_conntrack iptable_security ip_tables ah4 xfrm4_mode_transport sctp tun binfmt_misc ext4 jbd2 mbcache loop tcp_diag udp_diag inet_diag rpcrdma ib_isert iscsi_target_mod ib_iser rdma_cm iw_cm libiscsi scsi_transport_iscsi ib_srpt target_core_mod ib_srp scsi_transport_srp ib_ipoib ib_ucm ib_uverbs ib_umad ib_cm ib_core nls_koi8_u nls_cp932 ts_kmp nf_conntrack_ipv4 nf_defrag_ipv4 nf_conntrack vfat fat ghash_ce sha2_ce sha1_ce cavium_rng_vf i2c_thunderx sg thunderx_edac i2c_smbus edac_core cavium_rng nfsd auth_rpcgss nfs_acl lockd grace sunrpc xfs libcrc32c nicvf nicpf ast i2c_algo_bit drm_kms_helper syscopyarea sysfillrect sysimgblt fb_sys_fops [ 6708.736446] ttm drm i2c_core thunder_bgx thunder_xcv mdio_thunder mdio_cavium dm_mirror dm_region_hash dm_log dm_mod [last unloaded: stap_3c300909c5b3f46dcacd49aab3334af_87021] [ 6708.752275] CPU: 84 PID: 0 Comm: swapper/84 Tainted: G W OE 4.11.0-4.el7.aarch64 #1 [ 6708.760787] Hardware name: www.cavium.com CRB-2S/CRB-2S, BIOS 0.3 Mar 13 2017 [ 6708.767910] task: ffff810006842e80 task.stack: ffff81000689c000 [ 6708.773822] PC is at 0x0 [ 6708.776739] LR is at svc_data_ready+0x38/0x88 [sunrpc] [ 6708.781866] pc : [<0000000000000000>] lr : [<ffff0000029d7378>] pstate: 60000145 [ 6708.789248] sp : ffff810ffbad3900 [ 6708.792551] x29: ffff810ffbad3900 x28: ffff000008c73d58 [ 6708.797853] x27: 0000000000000000 x26: ffff81000bbe1e00 [ 6708.803156] x25: 0000000000000020 x24: ffff800f7410bf28 [ 6708.808458] x23: ffff000008c63000 x22: ffff000008c63000 [ 6708.813760] x21: ffff800f7410bf28 x20: ffff81000bbe1e00 [ 6708.819063] x19: ffff810012412400 x18: 00000000d82a9df2 [ 6708.824365] x17: 0000000000000000 x16: 0000000000000000 [ 6708.829667] x15: 0000000000000000 x14: 0000000000000001 [ 6708.834969] x13: 0000000000000000 x12: 722e736f622e676e [ 6708.840271] x11: 00000000f814dd99 x10: 0000000000000000 [ 6708.845573] x9 : 7374687225000000 x8 : 0000000000000000 [ 6708.850875] x7 : 0000000000000000 x6 : 0000000000000000 [ 6708.856177] x5 : 0000000000000028 x4 : 0000000000000000 [ 6708.861479] x3 : 0000000000000000 x2 : 00000000e5000000 [ 6708.866781] x1 : 0000000000000000 x0 : ffff81000bbe1e00 [ 6708.872084] [ 6708.873565] Process swapper/84 (pid: 0, stack limit = 0xffff81000689c000) [ 6708.880341] Stack: (0xffff810ffbad3900 to 0xffff8100068a0000) [ 6708.886075] Call trace: [ 6708.888513] Exception stack(0xffff810ffbad3710 to 0xffff810ffbad3840) [ 6708.894942] 3700: ffff810012412400 0001000000000000 [ 6708.902759] 3720: ffff810ffbad3900 0000000000000000 0000000060000145 ffff800f79300000 [ 6708.910577] 3740: ffff000009274d00 00000000000003ea 0000000000000015 ffff000008c63000 [ 6708.918395] 3760: ffff810ffbad3830 ffff800f79300000 000000000000004d 0000000000000000 [ 6708.926212] 3780: ffff810ffbad3890 ffff0000080f88dc ffff800f79300000 000000000000004d [ 6708.934030] 37a0: ffff800f7930093c ffff000008c63000 0000000000000000 0000000000000140 [ 6708.941848] 37c0: ffff000008c2c000 0000000000040b00 ffff81000bbe1e00 0000000000000000 [ 6708.949665] 37e0: 00000000e5000000 0000000000000000 0000000000000000 0000000000000028 [ 6708.957483] 3800: 0000000000000000 0000000000000000 0000000000000000 7374687225000000 [ 6708.965300] 3820: 0000000000000000 00000000f814dd99 722e736f622e676e 0000000000000000 [ 6708.973117] [< (null)>] (null) [ 6708.977824] [<ffff0000086f9fa4>] tcp_data_queue+0x754/0xc5c [ 6708.983386] [<ffff0000086fa64c>] tcp_rcv_established+0x1a0/0x67c [ 6708.989384] [<ffff000008704120>] tcp_v4_do_rcv+0x15c/0x22c [ 6708.994858] [<ffff000008707418>] tcp_v4_rcv+0xaf0/0xb58 [ 6709.000077] [<ffff0000086df784>] ip_local_deliver_finish+0x10c/0x254 [ 6709.006419] [<ffff0000086dfea4>] ip_local_deliver+0xf0/0xfc [ 6709.011980] [<ffff0000086dfad4>] ip_rcv_finish+0x208/0x3a4 [ 6709.017454] [<ffff0000086e018c>] ip_rcv+0x2dc/0x3c8 [ 6709.022328] [<ffff000008692fc8>] __netif_receive_skb_core+0x2f8/0xa0c [ 6709.028758] [<ffff000008696068>] __netif_receive_skb+0x38/0x84 [ 6709.034580] [<ffff00000869611c>] netif_receive_skb_internal+0x68/0xdc [ 6709.041010] [<ffff000008696bc0>] napi_gro_receive+0xcc/0x1a8 [ 6709.046690] [<ffff0000014b0fc4>] nicvf_cq_intr_handler+0x59c/0x730 [nicvf] [ 6709.053559] [<ffff0000014b1380>] nicvf_poll+0x38/0xb8 [nicvf] [ 6709.059295] [<ffff000008697a6c>] net_rx_action+0x2f8/0x464 [ 6709.064771] [<ffff000008081824>] __do_softirq+0x11c/0x308 [ 6709.070164] [<ffff0000080d14e4>] irq_exit+0x12c/0x174 [ 6709.075206] [<ffff00000813101c>] __handle_domain_irq+0x78/0xc4 [ 6709.081027] [<ffff000008081608>] gic_handle_irq+0x94/0x190 [ 6709.086501] Exception stack(0xffff81000689fdf0 to 0xffff81000689ff20) [ 6709.092929] fde0: 0000810ff2ec0000 ffff000008c10000 [ 6709.100747] fe00: ffff000008c70ef4 0000000000000001 0000000000000000 ffff810ffbad9b18 [ 6709.108565] fe20: ffff810ffbad9c70 ffff8100169d3800 ffff810006843ab0 ffff81000689fe80 [ 6709.116382] fe40: 0000000000000bd0 0000ffffdf979cd0 183f5913da192500 0000ffff8a254ce4 [ 6709.124200] fe60: 0000ffff8a254b78 0000aaab10339808 0000000000000000 0000ffff8a0c2a50 [ 6709.132018] fe80: 0000ffffdf979b10 ffff000008d6d450 ffff000008c10000 ffff000008d6d000 [ 6709.139836] fea0: 0000000000000054 ffff000008cd3dbc 0000000000000000 0000000000000000 [ 6709.147653] fec0: 0000000000000000 0000000000000000 0000000000000000 ffff81000689ff20 [ 6709.155471] fee0: ffff000008085240 ffff81000689ff20 ffff000008085244 0000000060000145 [ 6709.163289] ff00: ffff81000689ff10 ffff00000813f1e4 ffffffffffffffff ffff00000813f238 [ 6709.171107] [<ffff000008082eb4>] el1_irq+0xb4/0x140 [ 6709.175976] [<ffff000008085244>] arch_cpu_idle+0x44/0x11c [ 6709.181368] [<ffff0000087bf3b8>] default_idle_call+0x20/0x30 [ 6709.187020] [<ffff000008116d50>] do_idle+0x158/0x1e4 [ 6709.191973] [<ffff000008116ff4>] cpu_startup_entry+0x2c/0x30 [ 6709.197624] [<ffff00000808e7cc>] secondary_start_kernel+0x13c/0x160 [ 6709.203878] [<0000000001bc71c4>] 0x1bc71c4 [ 6709.207967] Code: bad PC value [ 6709.211061] SMP: stopping secondary CPUs [ 6709.218830] Starting crashdump kernel... [ 6709.222749] Bye! ---<-snip>--- Signed-off-by: Vadim Lomovtsev <vlomovts@redhat.com> Reviewed-by: Jeff Layton <jlayton@redhat.com> Cc: stable@vger.kernel.org Signed-off-by: J. Bruce Fields <bfields@redhat.com>
2017-08-21 19:23:07 +08:00
/* Refer to svc_setup_socket() for details. */
rmb();
svsk->sk_odata(sk);
if (!test_and_set_bit(XPT_DATA, &svsk->sk_xprt.xpt_flags))
svc_xprt_enqueue(&svsk->sk_xprt);
}
}
/*
* INET callback when space is newly available on the socket.
*/
static void svc_write_space(struct sock *sk)
{
struct svc_sock *svsk = (struct svc_sock *)(sk->sk_user_data);
if (svsk) {
dprintk("svc: socket %p(inet %p), write_space busy=%d\n",
svsk, sk, test_bit(XPT_BUSY, &svsk->sk_xprt.xpt_flags));
net: sunrpc: svcsock: fix NULL-pointer exception While running nfs/connectathon tests kernel NULL-pointer exception has been observed due to races in svcsock.c. Race is appear when kernel accepts connection by kernel_accept (which creates new socket) and start queuing ingress packets to new socket. This happens in ksoftirq context which could run concurrently on a different core while new socket setup is not done yet. The fix is to re-order socket user data init sequence and add write/read barrier calls to be sure that we got proper values for callback pointers before actually calling them. Test results: nfs/connectathon reports '0' failed tests for about 200+ iterations. Crash log: ---<-snip->--- [ 6708.638984] Unable to handle kernel NULL pointer dereference at virtual address 00000000 [ 6708.647093] pgd = ffff0000094e0000 [ 6708.650497] [00000000] *pgd=0000010ffff90003, *pud=0000010ffff90003, *pmd=0000010ffff80003, *pte=0000000000000000 [ 6708.660761] Internal error: Oops: 86000005 [#1] SMP [ 6708.665630] Modules linked in: nfsv3 nfnetlink_queue nfnetlink_log nfnetlink rpcsec_gss_krb5 nfsv4 dns_resolver nfs fscache overlay xt_CONNSECMARK xt_SECMARK xt_conntrack iptable_security ip_tables ah4 xfrm4_mode_transport sctp tun binfmt_misc ext4 jbd2 mbcache loop tcp_diag udp_diag inet_diag rpcrdma ib_isert iscsi_target_mod ib_iser rdma_cm iw_cm libiscsi scsi_transport_iscsi ib_srpt target_core_mod ib_srp scsi_transport_srp ib_ipoib ib_ucm ib_uverbs ib_umad ib_cm ib_core nls_koi8_u nls_cp932 ts_kmp nf_conntrack_ipv4 nf_defrag_ipv4 nf_conntrack vfat fat ghash_ce sha2_ce sha1_ce cavium_rng_vf i2c_thunderx sg thunderx_edac i2c_smbus edac_core cavium_rng nfsd auth_rpcgss nfs_acl lockd grace sunrpc xfs libcrc32c nicvf nicpf ast i2c_algo_bit drm_kms_helper syscopyarea sysfillrect sysimgblt fb_sys_fops [ 6708.736446] ttm drm i2c_core thunder_bgx thunder_xcv mdio_thunder mdio_cavium dm_mirror dm_region_hash dm_log dm_mod [last unloaded: stap_3c300909c5b3f46dcacd49aab3334af_87021] [ 6708.752275] CPU: 84 PID: 0 Comm: swapper/84 Tainted: G W OE 4.11.0-4.el7.aarch64 #1 [ 6708.760787] Hardware name: www.cavium.com CRB-2S/CRB-2S, BIOS 0.3 Mar 13 2017 [ 6708.767910] task: ffff810006842e80 task.stack: ffff81000689c000 [ 6708.773822] PC is at 0x0 [ 6708.776739] LR is at svc_data_ready+0x38/0x88 [sunrpc] [ 6708.781866] pc : [<0000000000000000>] lr : [<ffff0000029d7378>] pstate: 60000145 [ 6708.789248] sp : ffff810ffbad3900 [ 6708.792551] x29: ffff810ffbad3900 x28: ffff000008c73d58 [ 6708.797853] x27: 0000000000000000 x26: ffff81000bbe1e00 [ 6708.803156] x25: 0000000000000020 x24: ffff800f7410bf28 [ 6708.808458] x23: ffff000008c63000 x22: ffff000008c63000 [ 6708.813760] x21: ffff800f7410bf28 x20: ffff81000bbe1e00 [ 6708.819063] x19: ffff810012412400 x18: 00000000d82a9df2 [ 6708.824365] x17: 0000000000000000 x16: 0000000000000000 [ 6708.829667] x15: 0000000000000000 x14: 0000000000000001 [ 6708.834969] x13: 0000000000000000 x12: 722e736f622e676e [ 6708.840271] x11: 00000000f814dd99 x10: 0000000000000000 [ 6708.845573] x9 : 7374687225000000 x8 : 0000000000000000 [ 6708.850875] x7 : 0000000000000000 x6 : 0000000000000000 [ 6708.856177] x5 : 0000000000000028 x4 : 0000000000000000 [ 6708.861479] x3 : 0000000000000000 x2 : 00000000e5000000 [ 6708.866781] x1 : 0000000000000000 x0 : ffff81000bbe1e00 [ 6708.872084] [ 6708.873565] Process swapper/84 (pid: 0, stack limit = 0xffff81000689c000) [ 6708.880341] Stack: (0xffff810ffbad3900 to 0xffff8100068a0000) [ 6708.886075] Call trace: [ 6708.888513] Exception stack(0xffff810ffbad3710 to 0xffff810ffbad3840) [ 6708.894942] 3700: ffff810012412400 0001000000000000 [ 6708.902759] 3720: ffff810ffbad3900 0000000000000000 0000000060000145 ffff800f79300000 [ 6708.910577] 3740: ffff000009274d00 00000000000003ea 0000000000000015 ffff000008c63000 [ 6708.918395] 3760: ffff810ffbad3830 ffff800f79300000 000000000000004d 0000000000000000 [ 6708.926212] 3780: ffff810ffbad3890 ffff0000080f88dc ffff800f79300000 000000000000004d [ 6708.934030] 37a0: ffff800f7930093c ffff000008c63000 0000000000000000 0000000000000140 [ 6708.941848] 37c0: ffff000008c2c000 0000000000040b00 ffff81000bbe1e00 0000000000000000 [ 6708.949665] 37e0: 00000000e5000000 0000000000000000 0000000000000000 0000000000000028 [ 6708.957483] 3800: 0000000000000000 0000000000000000 0000000000000000 7374687225000000 [ 6708.965300] 3820: 0000000000000000 00000000f814dd99 722e736f622e676e 0000000000000000 [ 6708.973117] [< (null)>] (null) [ 6708.977824] [<ffff0000086f9fa4>] tcp_data_queue+0x754/0xc5c [ 6708.983386] [<ffff0000086fa64c>] tcp_rcv_established+0x1a0/0x67c [ 6708.989384] [<ffff000008704120>] tcp_v4_do_rcv+0x15c/0x22c [ 6708.994858] [<ffff000008707418>] tcp_v4_rcv+0xaf0/0xb58 [ 6709.000077] [<ffff0000086df784>] ip_local_deliver_finish+0x10c/0x254 [ 6709.006419] [<ffff0000086dfea4>] ip_local_deliver+0xf0/0xfc [ 6709.011980] [<ffff0000086dfad4>] ip_rcv_finish+0x208/0x3a4 [ 6709.017454] [<ffff0000086e018c>] ip_rcv+0x2dc/0x3c8 [ 6709.022328] [<ffff000008692fc8>] __netif_receive_skb_core+0x2f8/0xa0c [ 6709.028758] [<ffff000008696068>] __netif_receive_skb+0x38/0x84 [ 6709.034580] [<ffff00000869611c>] netif_receive_skb_internal+0x68/0xdc [ 6709.041010] [<ffff000008696bc0>] napi_gro_receive+0xcc/0x1a8 [ 6709.046690] [<ffff0000014b0fc4>] nicvf_cq_intr_handler+0x59c/0x730 [nicvf] [ 6709.053559] [<ffff0000014b1380>] nicvf_poll+0x38/0xb8 [nicvf] [ 6709.059295] [<ffff000008697a6c>] net_rx_action+0x2f8/0x464 [ 6709.064771] [<ffff000008081824>] __do_softirq+0x11c/0x308 [ 6709.070164] [<ffff0000080d14e4>] irq_exit+0x12c/0x174 [ 6709.075206] [<ffff00000813101c>] __handle_domain_irq+0x78/0xc4 [ 6709.081027] [<ffff000008081608>] gic_handle_irq+0x94/0x190 [ 6709.086501] Exception stack(0xffff81000689fdf0 to 0xffff81000689ff20) [ 6709.092929] fde0: 0000810ff2ec0000 ffff000008c10000 [ 6709.100747] fe00: ffff000008c70ef4 0000000000000001 0000000000000000 ffff810ffbad9b18 [ 6709.108565] fe20: ffff810ffbad9c70 ffff8100169d3800 ffff810006843ab0 ffff81000689fe80 [ 6709.116382] fe40: 0000000000000bd0 0000ffffdf979cd0 183f5913da192500 0000ffff8a254ce4 [ 6709.124200] fe60: 0000ffff8a254b78 0000aaab10339808 0000000000000000 0000ffff8a0c2a50 [ 6709.132018] fe80: 0000ffffdf979b10 ffff000008d6d450 ffff000008c10000 ffff000008d6d000 [ 6709.139836] fea0: 0000000000000054 ffff000008cd3dbc 0000000000000000 0000000000000000 [ 6709.147653] fec0: 0000000000000000 0000000000000000 0000000000000000 ffff81000689ff20 [ 6709.155471] fee0: ffff000008085240 ffff81000689ff20 ffff000008085244 0000000060000145 [ 6709.163289] ff00: ffff81000689ff10 ffff00000813f1e4 ffffffffffffffff ffff00000813f238 [ 6709.171107] [<ffff000008082eb4>] el1_irq+0xb4/0x140 [ 6709.175976] [<ffff000008085244>] arch_cpu_idle+0x44/0x11c [ 6709.181368] [<ffff0000087bf3b8>] default_idle_call+0x20/0x30 [ 6709.187020] [<ffff000008116d50>] do_idle+0x158/0x1e4 [ 6709.191973] [<ffff000008116ff4>] cpu_startup_entry+0x2c/0x30 [ 6709.197624] [<ffff00000808e7cc>] secondary_start_kernel+0x13c/0x160 [ 6709.203878] [<0000000001bc71c4>] 0x1bc71c4 [ 6709.207967] Code: bad PC value [ 6709.211061] SMP: stopping secondary CPUs [ 6709.218830] Starting crashdump kernel... [ 6709.222749] Bye! ---<-snip>--- Signed-off-by: Vadim Lomovtsev <vlomovts@redhat.com> Reviewed-by: Jeff Layton <jlayton@redhat.com> Cc: stable@vger.kernel.org Signed-off-by: J. Bruce Fields <bfields@redhat.com>
2017-08-21 19:23:07 +08:00
/* Refer to svc_setup_socket() for details. */
rmb();
svsk->sk_owspace(sk);
svc_xprt_enqueue(&svsk->sk_xprt);
}
}
static int svc_tcp_has_wspace(struct svc_xprt *xprt)
{
struct svc_sock *svsk = container_of(xprt, struct svc_sock, sk_xprt);
if (test_bit(XPT_LISTENER, &xprt->xpt_flags))
return 1;
return !test_bit(SOCK_NOSPACE, &svsk->sk_sock->flags);
}
sunrpc: svc_age_temp_xprts_now should not call setsockopt non-tcp transports This fixes the following panic that can occur with NFSoRDMA. general protection fault: 0000 [#1] SMP Modules linked in: rpcrdma ib_isert iscsi_target_mod ib_iser libiscsi scsi_transport_iscsi ib_srpt target_core_mod ib_srp scsi_transport_srp scsi_tgt ib_ipoib rdma_ucm ib_ucm ib_uverbs ib_umad rdma_cm ib_cm iw_cm mlx5_ib ib_core intel_powerclamp coretemp kvm_intel kvm sg ioatdma ipmi_devintf ipmi_ssif dcdbas iTCO_wdt iTCO_vendor_support pcspkr irqbypass sb_edac shpchp dca crc32_pclmul ghash_clmulni_intel edac_core lpc_ich aesni_intel lrw gf128mul glue_helper ablk_helper mei_me mei ipmi_si cryptd wmi ipmi_msghandler acpi_pad acpi_power_meter nfsd auth_rpcgss nfs_acl lockd grace sunrpc ip_tables xfs libcrc32c sd_mod crc_t10dif crct10dif_generic mgag200 i2c_algo_bit drm_kms_helper syscopyarea sysfillrect sysimgblt ahci fb_sys_fops ttm libahci mlx5_core tg3 crct10dif_pclmul drm crct10dif_common ptp i2c_core libata crc32c_intel pps_core fjes dm_mirror dm_region_hash dm_log dm_mod CPU: 1 PID: 120 Comm: kworker/1:1 Not tainted 3.10.0-514.el7.x86_64 #1 Hardware name: Dell Inc. PowerEdge R320/0KM5PX, BIOS 2.4.2 01/29/2015 Workqueue: events check_lifetime task: ffff88031f506dd0 ti: ffff88031f584000 task.ti: ffff88031f584000 RIP: 0010:[<ffffffff8168d847>] [<ffffffff8168d847>] _raw_spin_lock_bh+0x17/0x50 RSP: 0018:ffff88031f587ba8 EFLAGS: 00010206 RAX: 0000000000020000 RBX: 20041fac02080072 RCX: ffff88031f587fd8 RDX: 0000000000000000 RSI: 0000000000000000 RDI: 20041fac02080072 RBP: ffff88031f587bb0 R08: 0000000000000008 R09: ffffffff8155be77 R10: ffff880322a59b00 R11: ffffea000bf39f00 R12: 20041fac02080072 R13: 000000000000000d R14: ffff8800c4fbd800 R15: 0000000000000001 FS: 0000000000000000(0000) GS:ffff880322a40000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007f3c52d4547e CR3: 00000000019ba000 CR4: 00000000001407e0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000ffff0ff0 DR7: 0000000000000400 Stack: 20041fac02080002 ffff88031f587bd0 ffffffff81557830 20041fac02080002 ffff88031f587c78 ffff88031f587c40 ffffffff8155ae08 000000010157df32 0000000800000001 ffff88031f587c20 ffffffff81096acb ffffffff81aa37d0 Call Trace: [<ffffffff81557830>] lock_sock_nested+0x20/0x50 [<ffffffff8155ae08>] sock_setsockopt+0x78/0x940 [<ffffffff81096acb>] ? lock_timer_base.isra.33+0x2b/0x50 [<ffffffff8155397d>] kernel_setsockopt+0x4d/0x50 [<ffffffffa0386284>] svc_age_temp_xprts_now+0x174/0x1e0 [sunrpc] [<ffffffffa03b681d>] nfsd_inetaddr_event+0x9d/0xd0 [nfsd] [<ffffffff81691ebc>] notifier_call_chain+0x4c/0x70 [<ffffffff810b687d>] __blocking_notifier_call_chain+0x4d/0x70 [<ffffffff810b68b6>] blocking_notifier_call_chain+0x16/0x20 [<ffffffff815e8538>] __inet_del_ifa+0x168/0x2d0 [<ffffffff815e8cef>] check_lifetime+0x25f/0x270 [<ffffffff810a7f3b>] process_one_work+0x17b/0x470 [<ffffffff810a8d76>] worker_thread+0x126/0x410 [<ffffffff810a8c50>] ? rescuer_thread+0x460/0x460 [<ffffffff810b052f>] kthread+0xcf/0xe0 [<ffffffff810b0460>] ? kthread_create_on_node+0x140/0x140 [<ffffffff81696418>] ret_from_fork+0x58/0x90 [<ffffffff810b0460>] ? kthread_create_on_node+0x140/0x140 Code: ca 75 f1 5d c3 0f 1f 80 00 00 00 00 eb d9 66 0f 1f 44 00 00 0f 1f 44 00 00 55 48 89 e5 53 48 89 fb e8 7e 04 a0 ff b8 00 00 02 00 <f0> 0f c1 03 89 c2 c1 ea 10 66 39 c2 75 03 5b 5d c3 83 e2 fe 0f RIP [<ffffffff8168d847>] _raw_spin_lock_bh+0x17/0x50 RSP <ffff88031f587ba8> Signed-off-by: Scott Mayhew <smayhew@redhat.com> Fixes: c3d4879e ("sunrpc: Add a function to close temporary transports immediately") Reviewed-by: Chuck Lever <chuck.lever@oracle.com> Signed-off-by: J. Bruce Fields <bfields@redhat.com>
2016-11-12 02:16:22 +08:00
static void svc_tcp_kill_temp_xprt(struct svc_xprt *xprt)
{
struct svc_sock *svsk;
struct socket *sock;
struct linger no_linger = {
.l_onoff = 1,
.l_linger = 0,
};
svsk = container_of(xprt, struct svc_sock, sk_xprt);
sock = svsk->sk_sock;
kernel_setsockopt(sock, SOL_SOCKET, SO_LINGER,
(char *)&no_linger, sizeof(no_linger));
}
/*
* See net/ipv6/ip_sockglue.c : ip_cmsg_recv_pktinfo
*/
static int svc_udp_get_dest_address4(struct svc_rqst *rqstp,
struct cmsghdr *cmh)
{
struct in_pktinfo *pki = CMSG_DATA(cmh);
struct sockaddr_in *daddr = svc_daddr_in(rqstp);
if (cmh->cmsg_type != IP_PKTINFO)
return 0;
daddr->sin_family = AF_INET;
daddr->sin_addr.s_addr = pki->ipi_spec_dst.s_addr;
return 1;
}
/*
* See net/ipv6/datagram.c : ip6_datagram_recv_ctl
*/
static int svc_udp_get_dest_address6(struct svc_rqst *rqstp,
struct cmsghdr *cmh)
{
struct in6_pktinfo *pki = CMSG_DATA(cmh);
struct sockaddr_in6 *daddr = svc_daddr_in6(rqstp);
if (cmh->cmsg_type != IPV6_PKTINFO)
return 0;
daddr->sin6_family = AF_INET6;
daddr->sin6_addr = pki->ipi6_addr;
daddr->sin6_scope_id = pki->ipi6_ifindex;
return 1;
}
svc: Move the sockaddr information to svc_xprt This patch moves the transport sockaddr to the svc_xprt structure. Convenience functions are added to set and get the local and remote addresses of a transport from the transport provider as well as determine the length of a sockaddr. A transport is responsible for setting the xpt_local and xpt_remote addresses in the svc_xprt structure as part of transport creation and xpo_accept processing. This cannot be done in a generic way and in fact varies between TCP, UDP and RDMA. A set of xpo_ functions (e.g. getlocalname, getremotename) could have been added but this would have resulted in additional caching and copying of the addresses around. Note that the xpt_local address should also be set on listening endpoints; for TCP/RDMA this is done as part of endpoint creation. For connected transports like TCP and RDMA, the addresses never change and can be set once and copied into the rqstp structure for each request. For UDP, however, the local and remote addresses may change for each request. In this case, the address information is obtained from the UDP recvmsg info and copied into the rqstp structure from there. A svc_xprt_local_port function was also added that returns the local port given a transport. This is used by svc_create_xprt when returning the port associated with a newly created transport, and later when creating a generic find transport service to check if a service is already listening on a given port. Signed-off-by: Tom Tucker <tom@opengridcomputing.com> Acked-by: Neil Brown <neilb@suse.de> Reviewed-by: Chuck Lever <chuck.lever@oracle.com> Reviewed-by: Greg Banks <gnb@sgi.com> Signed-off-by: J. Bruce Fields <bfields@citi.umich.edu>
2007-12-31 11:08:12 +08:00
/*
* 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)
{
switch (cmh->cmsg_level) {
case SOL_IP:
return svc_udp_get_dest_address4(rqstp, cmh);
case SOL_IPV6:
return svc_udp_get_dest_address6(rqstp, cmh);
}
return 0;
}
/*
* Receive a datagram from a UDP socket.
*/
static int svc_udp_recvfrom(struct svc_rqst *rqstp)
{
struct svc_sock *svsk =
container_of(rqstp->rq_xprt, struct svc_sock, sk_xprt);
struct svc_serv *serv = svsk->sk_xprt.xpt_server;
struct sk_buff *skb;
union {
struct cmsghdr hdr;
long all[SVC_PKTINFO_SPACE / sizeof(long)];
} buffer;
struct cmsghdr *cmh = &buffer.hdr;
struct msghdr msg = {
.msg_name = svc_addr(rqstp),
.msg_control = cmh,
.msg_controllen = sizeof(buffer),
.msg_flags = MSG_DONTWAIT,
};
size_t len;
int err;
if (test_and_clear_bit(XPT_CHNGBUF, &svsk->sk_xprt.xpt_flags))
/* udp sockets need large rcvbuf as all pending
* requests are still in that buffer. sndbuf must
* also be large enough that there is enough space
* for one reply per thread. We count all threads
* rather than threads in a particular pool, which
* provides an upper bound on the number of threads
* which will access the socket.
*/
svc_sock_setbufsize(svsk->sk_sock,
(serv->sv_nrthreads+3) * serv->sv_max_mesg,
(serv->sv_nrthreads+3) * serv->sv_max_mesg);
clear_bit(XPT_DATA, &svsk->sk_xprt.xpt_flags);
skb = NULL;
err = kernel_recvmsg(svsk->sk_sock, &msg, NULL,
0, 0, MSG_PEEK | MSG_DONTWAIT);
if (err >= 0)
skb = skb_recv_udp(svsk->sk_sk, 0, 1, &err);
if (skb == NULL) {
if (err != -EAGAIN) {
/* possibly an icmp error */
dprintk("svc: recvfrom returned error %d\n", -err);
set_bit(XPT_DATA, &svsk->sk_xprt.xpt_flags);
}
return 0;
}
svc: Move the sockaddr information to svc_xprt This patch moves the transport sockaddr to the svc_xprt structure. Convenience functions are added to set and get the local and remote addresses of a transport from the transport provider as well as determine the length of a sockaddr. A transport is responsible for setting the xpt_local and xpt_remote addresses in the svc_xprt structure as part of transport creation and xpo_accept processing. This cannot be done in a generic way and in fact varies between TCP, UDP and RDMA. A set of xpo_ functions (e.g. getlocalname, getremotename) could have been added but this would have resulted in additional caching and copying of the addresses around. Note that the xpt_local address should also be set on listening endpoints; for TCP/RDMA this is done as part of endpoint creation. For connected transports like TCP and RDMA, the addresses never change and can be set once and copied into the rqstp structure for each request. For UDP, however, the local and remote addresses may change for each request. In this case, the address information is obtained from the UDP recvmsg info and copied into the rqstp structure from there. A svc_xprt_local_port function was also added that returns the local port given a transport. This is used by svc_create_xprt when returning the port associated with a newly created transport, and later when creating a generic find transport service to check if a service is already listening on a given port. Signed-off-by: Tom Tucker <tom@opengridcomputing.com> Acked-by: Neil Brown <neilb@suse.de> Reviewed-by: Chuck Lever <chuck.lever@oracle.com> Reviewed-by: Greg Banks <gnb@sgi.com> Signed-off-by: J. Bruce Fields <bfields@citi.umich.edu>
2007-12-31 11:08:12 +08:00
len = svc_addr_len(svc_addr(rqstp));
rqstp->rq_addrlen = len;
if (skb->tstamp == 0) {
skb->tstamp = ktime_get_real();
/* Don't enable netstamp, sunrpc doesn't
need that much accuracy */
}
sock_write_timestamp(svsk->sk_sk, skb->tstamp);
set_bit(XPT_DATA, &svsk->sk_xprt.xpt_flags); /* there may be more data... */
len = skb->len;
rqstp->rq_arg.len = len;
rqstp->rq_prot = IPPROTO_UDP;
if (!svc_udp_get_dest_address(rqstp, cmh)) {
net_warn_ratelimited("svc: received unknown control message %d/%d; dropping RPC reply datagram\n",
cmh->cmsg_level, cmh->cmsg_type);
goto out_free;
}
rqstp->rq_daddrlen = svc_addr_len(svc_daddr(rqstp));
if (skb_is_nonlinear(skb)) {
/* we have to copy */
local_bh_disable();
if (csum_partial_copy_to_xdr(&rqstp->rq_arg, skb)) {
local_bh_enable();
/* checksum error */
goto out_free;
}
local_bh_enable();
consume_skb(skb);
} else {
/* we can use it in-place */
rqstp->rq_arg.head[0].iov_base = skb->data;
rqstp->rq_arg.head[0].iov_len = len;
if (skb_checksum_complete(skb))
goto out_free;
rqstp->rq_xprt_ctxt = skb;
}
rqstp->rq_arg.page_base = 0;
if (len <= rqstp->rq_arg.head[0].iov_len) {
rqstp->rq_arg.head[0].iov_len = len;
rqstp->rq_arg.page_len = 0;
rqstp->rq_respages = rqstp->rq_pages+1;
} else {
rqstp->rq_arg.page_len = len - rqstp->rq_arg.head[0].iov_len;
rqstp->rq_respages = rqstp->rq_pages + 1 +
DIV_ROUND_UP(rqstp->rq_arg.page_len, PAGE_SIZE);
}
rqstp->rq_next_page = rqstp->rq_respages+1;
if (serv->sv_stats)
serv->sv_stats->netudpcnt++;
return len;
out_free:
kfree_skb(skb);
return 0;
}
static int
svc_udp_sendto(struct svc_rqst *rqstp)
{
int error;
error = svc_sendto(rqstp, &rqstp->rq_res);
if (error == -ECONNREFUSED)
/* ICMP error on earlier request. */
error = svc_sendto(rqstp, &rqstp->rq_res);
return error;
}
static int svc_udp_has_wspace(struct svc_xprt *xprt)
{
struct svc_sock *svsk = container_of(xprt, struct svc_sock, sk_xprt);
struct svc_serv *serv = xprt->xpt_server;
unsigned long required;
/*
* Set the SOCK_NOSPACE flag before checking the available
* sock space.
*/
set_bit(SOCK_NOSPACE, &svsk->sk_sock->flags);
required = atomic_read(&svsk->sk_xprt.xpt_reserved) + serv->sv_max_mesg;
if (required*2 > sock_wspace(svsk->sk_sk))
return 0;
clear_bit(SOCK_NOSPACE, &svsk->sk_sock->flags);
return 1;
}
static struct svc_xprt *svc_udp_accept(struct svc_xprt *xprt)
{
BUG();
return NULL;
}
sunrpc: svc_age_temp_xprts_now should not call setsockopt non-tcp transports This fixes the following panic that can occur with NFSoRDMA. general protection fault: 0000 [#1] SMP Modules linked in: rpcrdma ib_isert iscsi_target_mod ib_iser libiscsi scsi_transport_iscsi ib_srpt target_core_mod ib_srp scsi_transport_srp scsi_tgt ib_ipoib rdma_ucm ib_ucm ib_uverbs ib_umad rdma_cm ib_cm iw_cm mlx5_ib ib_core intel_powerclamp coretemp kvm_intel kvm sg ioatdma ipmi_devintf ipmi_ssif dcdbas iTCO_wdt iTCO_vendor_support pcspkr irqbypass sb_edac shpchp dca crc32_pclmul ghash_clmulni_intel edac_core lpc_ich aesni_intel lrw gf128mul glue_helper ablk_helper mei_me mei ipmi_si cryptd wmi ipmi_msghandler acpi_pad acpi_power_meter nfsd auth_rpcgss nfs_acl lockd grace sunrpc ip_tables xfs libcrc32c sd_mod crc_t10dif crct10dif_generic mgag200 i2c_algo_bit drm_kms_helper syscopyarea sysfillrect sysimgblt ahci fb_sys_fops ttm libahci mlx5_core tg3 crct10dif_pclmul drm crct10dif_common ptp i2c_core libata crc32c_intel pps_core fjes dm_mirror dm_region_hash dm_log dm_mod CPU: 1 PID: 120 Comm: kworker/1:1 Not tainted 3.10.0-514.el7.x86_64 #1 Hardware name: Dell Inc. PowerEdge R320/0KM5PX, BIOS 2.4.2 01/29/2015 Workqueue: events check_lifetime task: ffff88031f506dd0 ti: ffff88031f584000 task.ti: ffff88031f584000 RIP: 0010:[<ffffffff8168d847>] [<ffffffff8168d847>] _raw_spin_lock_bh+0x17/0x50 RSP: 0018:ffff88031f587ba8 EFLAGS: 00010206 RAX: 0000000000020000 RBX: 20041fac02080072 RCX: ffff88031f587fd8 RDX: 0000000000000000 RSI: 0000000000000000 RDI: 20041fac02080072 RBP: ffff88031f587bb0 R08: 0000000000000008 R09: ffffffff8155be77 R10: ffff880322a59b00 R11: ffffea000bf39f00 R12: 20041fac02080072 R13: 000000000000000d R14: ffff8800c4fbd800 R15: 0000000000000001 FS: 0000000000000000(0000) GS:ffff880322a40000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007f3c52d4547e CR3: 00000000019ba000 CR4: 00000000001407e0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000ffff0ff0 DR7: 0000000000000400 Stack: 20041fac02080002 ffff88031f587bd0 ffffffff81557830 20041fac02080002 ffff88031f587c78 ffff88031f587c40 ffffffff8155ae08 000000010157df32 0000000800000001 ffff88031f587c20 ffffffff81096acb ffffffff81aa37d0 Call Trace: [<ffffffff81557830>] lock_sock_nested+0x20/0x50 [<ffffffff8155ae08>] sock_setsockopt+0x78/0x940 [<ffffffff81096acb>] ? lock_timer_base.isra.33+0x2b/0x50 [<ffffffff8155397d>] kernel_setsockopt+0x4d/0x50 [<ffffffffa0386284>] svc_age_temp_xprts_now+0x174/0x1e0 [sunrpc] [<ffffffffa03b681d>] nfsd_inetaddr_event+0x9d/0xd0 [nfsd] [<ffffffff81691ebc>] notifier_call_chain+0x4c/0x70 [<ffffffff810b687d>] __blocking_notifier_call_chain+0x4d/0x70 [<ffffffff810b68b6>] blocking_notifier_call_chain+0x16/0x20 [<ffffffff815e8538>] __inet_del_ifa+0x168/0x2d0 [<ffffffff815e8cef>] check_lifetime+0x25f/0x270 [<ffffffff810a7f3b>] process_one_work+0x17b/0x470 [<ffffffff810a8d76>] worker_thread+0x126/0x410 [<ffffffff810a8c50>] ? rescuer_thread+0x460/0x460 [<ffffffff810b052f>] kthread+0xcf/0xe0 [<ffffffff810b0460>] ? kthread_create_on_node+0x140/0x140 [<ffffffff81696418>] ret_from_fork+0x58/0x90 [<ffffffff810b0460>] ? kthread_create_on_node+0x140/0x140 Code: ca 75 f1 5d c3 0f 1f 80 00 00 00 00 eb d9 66 0f 1f 44 00 00 0f 1f 44 00 00 55 48 89 e5 53 48 89 fb e8 7e 04 a0 ff b8 00 00 02 00 <f0> 0f c1 03 89 c2 c1 ea 10 66 39 c2 75 03 5b 5d c3 83 e2 fe 0f RIP [<ffffffff8168d847>] _raw_spin_lock_bh+0x17/0x50 RSP <ffff88031f587ba8> Signed-off-by: Scott Mayhew <smayhew@redhat.com> Fixes: c3d4879e ("sunrpc: Add a function to close temporary transports immediately") Reviewed-by: Chuck Lever <chuck.lever@oracle.com> Signed-off-by: J. Bruce Fields <bfields@redhat.com>
2016-11-12 02:16:22 +08:00
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)
{
return svc_create_socket(serv, IPPROTO_UDP, net, sa, salen, flags);
}
static const struct svc_xprt_ops svc_udp_ops = {
.xpo_create = svc_udp_create,
.xpo_recvfrom = svc_udp_recvfrom,
.xpo_sendto = svc_udp_sendto,
.xpo_release_rqst = svc_release_udp_skb,
.xpo_detach = svc_sock_detach,
.xpo_free = svc_sock_free,
.xpo_has_wspace = svc_udp_has_wspace,
.xpo_accept = svc_udp_accept,
.xpo_secure_port = svc_sock_secure_port,
sunrpc: svc_age_temp_xprts_now should not call setsockopt non-tcp transports This fixes the following panic that can occur with NFSoRDMA. general protection fault: 0000 [#1] SMP Modules linked in: rpcrdma ib_isert iscsi_target_mod ib_iser libiscsi scsi_transport_iscsi ib_srpt target_core_mod ib_srp scsi_transport_srp scsi_tgt ib_ipoib rdma_ucm ib_ucm ib_uverbs ib_umad rdma_cm ib_cm iw_cm mlx5_ib ib_core intel_powerclamp coretemp kvm_intel kvm sg ioatdma ipmi_devintf ipmi_ssif dcdbas iTCO_wdt iTCO_vendor_support pcspkr irqbypass sb_edac shpchp dca crc32_pclmul ghash_clmulni_intel edac_core lpc_ich aesni_intel lrw gf128mul glue_helper ablk_helper mei_me mei ipmi_si cryptd wmi ipmi_msghandler acpi_pad acpi_power_meter nfsd auth_rpcgss nfs_acl lockd grace sunrpc ip_tables xfs libcrc32c sd_mod crc_t10dif crct10dif_generic mgag200 i2c_algo_bit drm_kms_helper syscopyarea sysfillrect sysimgblt ahci fb_sys_fops ttm libahci mlx5_core tg3 crct10dif_pclmul drm crct10dif_common ptp i2c_core libata crc32c_intel pps_core fjes dm_mirror dm_region_hash dm_log dm_mod CPU: 1 PID: 120 Comm: kworker/1:1 Not tainted 3.10.0-514.el7.x86_64 #1 Hardware name: Dell Inc. PowerEdge R320/0KM5PX, BIOS 2.4.2 01/29/2015 Workqueue: events check_lifetime task: ffff88031f506dd0 ti: ffff88031f584000 task.ti: ffff88031f584000 RIP: 0010:[<ffffffff8168d847>] [<ffffffff8168d847>] _raw_spin_lock_bh+0x17/0x50 RSP: 0018:ffff88031f587ba8 EFLAGS: 00010206 RAX: 0000000000020000 RBX: 20041fac02080072 RCX: ffff88031f587fd8 RDX: 0000000000000000 RSI: 0000000000000000 RDI: 20041fac02080072 RBP: ffff88031f587bb0 R08: 0000000000000008 R09: ffffffff8155be77 R10: ffff880322a59b00 R11: ffffea000bf39f00 R12: 20041fac02080072 R13: 000000000000000d R14: ffff8800c4fbd800 R15: 0000000000000001 FS: 0000000000000000(0000) GS:ffff880322a40000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007f3c52d4547e CR3: 00000000019ba000 CR4: 00000000001407e0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000ffff0ff0 DR7: 0000000000000400 Stack: 20041fac02080002 ffff88031f587bd0 ffffffff81557830 20041fac02080002 ffff88031f587c78 ffff88031f587c40 ffffffff8155ae08 000000010157df32 0000000800000001 ffff88031f587c20 ffffffff81096acb ffffffff81aa37d0 Call Trace: [<ffffffff81557830>] lock_sock_nested+0x20/0x50 [<ffffffff8155ae08>] sock_setsockopt+0x78/0x940 [<ffffffff81096acb>] ? lock_timer_base.isra.33+0x2b/0x50 [<ffffffff8155397d>] kernel_setsockopt+0x4d/0x50 [<ffffffffa0386284>] svc_age_temp_xprts_now+0x174/0x1e0 [sunrpc] [<ffffffffa03b681d>] nfsd_inetaddr_event+0x9d/0xd0 [nfsd] [<ffffffff81691ebc>] notifier_call_chain+0x4c/0x70 [<ffffffff810b687d>] __blocking_notifier_call_chain+0x4d/0x70 [<ffffffff810b68b6>] blocking_notifier_call_chain+0x16/0x20 [<ffffffff815e8538>] __inet_del_ifa+0x168/0x2d0 [<ffffffff815e8cef>] check_lifetime+0x25f/0x270 [<ffffffff810a7f3b>] process_one_work+0x17b/0x470 [<ffffffff810a8d76>] worker_thread+0x126/0x410 [<ffffffff810a8c50>] ? rescuer_thread+0x460/0x460 [<ffffffff810b052f>] kthread+0xcf/0xe0 [<ffffffff810b0460>] ? kthread_create_on_node+0x140/0x140 [<ffffffff81696418>] ret_from_fork+0x58/0x90 [<ffffffff810b0460>] ? kthread_create_on_node+0x140/0x140 Code: ca 75 f1 5d c3 0f 1f 80 00 00 00 00 eb d9 66 0f 1f 44 00 00 0f 1f 44 00 00 55 48 89 e5 53 48 89 fb e8 7e 04 a0 ff b8 00 00 02 00 <f0> 0f c1 03 89 c2 c1 ea 10 66 39 c2 75 03 5b 5d c3 83 e2 fe 0f RIP [<ffffffff8168d847>] _raw_spin_lock_bh+0x17/0x50 RSP <ffff88031f587ba8> Signed-off-by: Scott Mayhew <smayhew@redhat.com> Fixes: c3d4879e ("sunrpc: Add a function to close temporary transports immediately") Reviewed-by: Chuck Lever <chuck.lever@oracle.com> Signed-off-by: J. Bruce Fields <bfields@redhat.com>
2016-11-12 02:16:22 +08:00
.xpo_kill_temp_xprt = svc_udp_kill_temp_xprt,
};
static struct svc_xprt_class svc_udp_class = {
.xcl_name = "udp",
.xcl_owner = THIS_MODULE,
.xcl_ops = &svc_udp_ops,
.xcl_max_payload = RPCSVC_MAXPAYLOAD_UDP,
.xcl_ident = XPRT_TRANSPORT_UDP,
};
static void svc_udp_init(struct svc_sock *svsk, struct svc_serv *serv)
{
int err, level, optname, one = 1;
svc_xprt_init(sock_net(svsk->sk_sock->sk), &svc_udp_class,
&svsk->sk_xprt, serv);
clear_bit(XPT_CACHE_AUTH, &svsk->sk_xprt.xpt_flags);
svsk->sk_sk->sk_data_ready = svc_data_ready;
svsk->sk_sk->sk_write_space = svc_write_space;
/* initialise setting must have enough space to
* receive and respond to one request.
* svc_udp_recvfrom will re-adjust if necessary
*/
svc_sock_setbufsize(svsk->sk_sock,
3 * svsk->sk_xprt.xpt_server->sv_max_mesg,
3 * svsk->sk_xprt.xpt_server->sv_max_mesg);
/* data might have come in before data_ready set up */
set_bit(XPT_DATA, &svsk->sk_xprt.xpt_flags);
set_bit(XPT_CHNGBUF, &svsk->sk_xprt.xpt_flags);
/* make sure we get destination address info */
switch (svsk->sk_sk->sk_family) {
case AF_INET:
level = SOL_IP;
optname = IP_PKTINFO;
break;
case AF_INET6:
level = SOL_IPV6;
optname = IPV6_RECVPKTINFO;
break;
default:
BUG();
}
err = kernel_setsockopt(svsk->sk_sock, level, optname,
(char *)&one, sizeof(one));
dprintk("svc: kernel_setsockopt returned %d\n", err);
}
/*
* 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)
{
struct svc_sock *svsk = (struct svc_sock *)sk->sk_user_data;
dprintk("svc: socket %p TCP (listen) state change %d\n",
sk, sk->sk_state);
net: sunrpc: svcsock: fix NULL-pointer exception While running nfs/connectathon tests kernel NULL-pointer exception has been observed due to races in svcsock.c. Race is appear when kernel accepts connection by kernel_accept (which creates new socket) and start queuing ingress packets to new socket. This happens in ksoftirq context which could run concurrently on a different core while new socket setup is not done yet. The fix is to re-order socket user data init sequence and add write/read barrier calls to be sure that we got proper values for callback pointers before actually calling them. Test results: nfs/connectathon reports '0' failed tests for about 200+ iterations. Crash log: ---<-snip->--- [ 6708.638984] Unable to handle kernel NULL pointer dereference at virtual address 00000000 [ 6708.647093] pgd = ffff0000094e0000 [ 6708.650497] [00000000] *pgd=0000010ffff90003, *pud=0000010ffff90003, *pmd=0000010ffff80003, *pte=0000000000000000 [ 6708.660761] Internal error: Oops: 86000005 [#1] SMP [ 6708.665630] Modules linked in: nfsv3 nfnetlink_queue nfnetlink_log nfnetlink rpcsec_gss_krb5 nfsv4 dns_resolver nfs fscache overlay xt_CONNSECMARK xt_SECMARK xt_conntrack iptable_security ip_tables ah4 xfrm4_mode_transport sctp tun binfmt_misc ext4 jbd2 mbcache loop tcp_diag udp_diag inet_diag rpcrdma ib_isert iscsi_target_mod ib_iser rdma_cm iw_cm libiscsi scsi_transport_iscsi ib_srpt target_core_mod ib_srp scsi_transport_srp ib_ipoib ib_ucm ib_uverbs ib_umad ib_cm ib_core nls_koi8_u nls_cp932 ts_kmp nf_conntrack_ipv4 nf_defrag_ipv4 nf_conntrack vfat fat ghash_ce sha2_ce sha1_ce cavium_rng_vf i2c_thunderx sg thunderx_edac i2c_smbus edac_core cavium_rng nfsd auth_rpcgss nfs_acl lockd grace sunrpc xfs libcrc32c nicvf nicpf ast i2c_algo_bit drm_kms_helper syscopyarea sysfillrect sysimgblt fb_sys_fops [ 6708.736446] ttm drm i2c_core thunder_bgx thunder_xcv mdio_thunder mdio_cavium dm_mirror dm_region_hash dm_log dm_mod [last unloaded: stap_3c300909c5b3f46dcacd49aab3334af_87021] [ 6708.752275] CPU: 84 PID: 0 Comm: swapper/84 Tainted: G W OE 4.11.0-4.el7.aarch64 #1 [ 6708.760787] Hardware name: www.cavium.com CRB-2S/CRB-2S, BIOS 0.3 Mar 13 2017 [ 6708.767910] task: ffff810006842e80 task.stack: ffff81000689c000 [ 6708.773822] PC is at 0x0 [ 6708.776739] LR is at svc_data_ready+0x38/0x88 [sunrpc] [ 6708.781866] pc : [<0000000000000000>] lr : [<ffff0000029d7378>] pstate: 60000145 [ 6708.789248] sp : ffff810ffbad3900 [ 6708.792551] x29: ffff810ffbad3900 x28: ffff000008c73d58 [ 6708.797853] x27: 0000000000000000 x26: ffff81000bbe1e00 [ 6708.803156] x25: 0000000000000020 x24: ffff800f7410bf28 [ 6708.808458] x23: ffff000008c63000 x22: ffff000008c63000 [ 6708.813760] x21: ffff800f7410bf28 x20: ffff81000bbe1e00 [ 6708.819063] x19: ffff810012412400 x18: 00000000d82a9df2 [ 6708.824365] x17: 0000000000000000 x16: 0000000000000000 [ 6708.829667] x15: 0000000000000000 x14: 0000000000000001 [ 6708.834969] x13: 0000000000000000 x12: 722e736f622e676e [ 6708.840271] x11: 00000000f814dd99 x10: 0000000000000000 [ 6708.845573] x9 : 7374687225000000 x8 : 0000000000000000 [ 6708.850875] x7 : 0000000000000000 x6 : 0000000000000000 [ 6708.856177] x5 : 0000000000000028 x4 : 0000000000000000 [ 6708.861479] x3 : 0000000000000000 x2 : 00000000e5000000 [ 6708.866781] x1 : 0000000000000000 x0 : ffff81000bbe1e00 [ 6708.872084] [ 6708.873565] Process swapper/84 (pid: 0, stack limit = 0xffff81000689c000) [ 6708.880341] Stack: (0xffff810ffbad3900 to 0xffff8100068a0000) [ 6708.886075] Call trace: [ 6708.888513] Exception stack(0xffff810ffbad3710 to 0xffff810ffbad3840) [ 6708.894942] 3700: ffff810012412400 0001000000000000 [ 6708.902759] 3720: ffff810ffbad3900 0000000000000000 0000000060000145 ffff800f79300000 [ 6708.910577] 3740: ffff000009274d00 00000000000003ea 0000000000000015 ffff000008c63000 [ 6708.918395] 3760: ffff810ffbad3830 ffff800f79300000 000000000000004d 0000000000000000 [ 6708.926212] 3780: ffff810ffbad3890 ffff0000080f88dc ffff800f79300000 000000000000004d [ 6708.934030] 37a0: ffff800f7930093c ffff000008c63000 0000000000000000 0000000000000140 [ 6708.941848] 37c0: ffff000008c2c000 0000000000040b00 ffff81000bbe1e00 0000000000000000 [ 6708.949665] 37e0: 00000000e5000000 0000000000000000 0000000000000000 0000000000000028 [ 6708.957483] 3800: 0000000000000000 0000000000000000 0000000000000000 7374687225000000 [ 6708.965300] 3820: 0000000000000000 00000000f814dd99 722e736f622e676e 0000000000000000 [ 6708.973117] [< (null)>] (null) [ 6708.977824] [<ffff0000086f9fa4>] tcp_data_queue+0x754/0xc5c [ 6708.983386] [<ffff0000086fa64c>] tcp_rcv_established+0x1a0/0x67c [ 6708.989384] [<ffff000008704120>] tcp_v4_do_rcv+0x15c/0x22c [ 6708.994858] [<ffff000008707418>] tcp_v4_rcv+0xaf0/0xb58 [ 6709.000077] [<ffff0000086df784>] ip_local_deliver_finish+0x10c/0x254 [ 6709.006419] [<ffff0000086dfea4>] ip_local_deliver+0xf0/0xfc [ 6709.011980] [<ffff0000086dfad4>] ip_rcv_finish+0x208/0x3a4 [ 6709.017454] [<ffff0000086e018c>] ip_rcv+0x2dc/0x3c8 [ 6709.022328] [<ffff000008692fc8>] __netif_receive_skb_core+0x2f8/0xa0c [ 6709.028758] [<ffff000008696068>] __netif_receive_skb+0x38/0x84 [ 6709.034580] [<ffff00000869611c>] netif_receive_skb_internal+0x68/0xdc [ 6709.041010] [<ffff000008696bc0>] napi_gro_receive+0xcc/0x1a8 [ 6709.046690] [<ffff0000014b0fc4>] nicvf_cq_intr_handler+0x59c/0x730 [nicvf] [ 6709.053559] [<ffff0000014b1380>] nicvf_poll+0x38/0xb8 [nicvf] [ 6709.059295] [<ffff000008697a6c>] net_rx_action+0x2f8/0x464 [ 6709.064771] [<ffff000008081824>] __do_softirq+0x11c/0x308 [ 6709.070164] [<ffff0000080d14e4>] irq_exit+0x12c/0x174 [ 6709.075206] [<ffff00000813101c>] __handle_domain_irq+0x78/0xc4 [ 6709.081027] [<ffff000008081608>] gic_handle_irq+0x94/0x190 [ 6709.086501] Exception stack(0xffff81000689fdf0 to 0xffff81000689ff20) [ 6709.092929] fde0: 0000810ff2ec0000 ffff000008c10000 [ 6709.100747] fe00: ffff000008c70ef4 0000000000000001 0000000000000000 ffff810ffbad9b18 [ 6709.108565] fe20: ffff810ffbad9c70 ffff8100169d3800 ffff810006843ab0 ffff81000689fe80 [ 6709.116382] fe40: 0000000000000bd0 0000ffffdf979cd0 183f5913da192500 0000ffff8a254ce4 [ 6709.124200] fe60: 0000ffff8a254b78 0000aaab10339808 0000000000000000 0000ffff8a0c2a50 [ 6709.132018] fe80: 0000ffffdf979b10 ffff000008d6d450 ffff000008c10000 ffff000008d6d000 [ 6709.139836] fea0: 0000000000000054 ffff000008cd3dbc 0000000000000000 0000000000000000 [ 6709.147653] fec0: 0000000000000000 0000000000000000 0000000000000000 ffff81000689ff20 [ 6709.155471] fee0: ffff000008085240 ffff81000689ff20 ffff000008085244 0000000060000145 [ 6709.163289] ff00: ffff81000689ff10 ffff00000813f1e4 ffffffffffffffff ffff00000813f238 [ 6709.171107] [<ffff000008082eb4>] el1_irq+0xb4/0x140 [ 6709.175976] [<ffff000008085244>] arch_cpu_idle+0x44/0x11c [ 6709.181368] [<ffff0000087bf3b8>] default_idle_call+0x20/0x30 [ 6709.187020] [<ffff000008116d50>] do_idle+0x158/0x1e4 [ 6709.191973] [<ffff000008116ff4>] cpu_startup_entry+0x2c/0x30 [ 6709.197624] [<ffff00000808e7cc>] secondary_start_kernel+0x13c/0x160 [ 6709.203878] [<0000000001bc71c4>] 0x1bc71c4 [ 6709.207967] Code: bad PC value [ 6709.211061] SMP: stopping secondary CPUs [ 6709.218830] Starting crashdump kernel... [ 6709.222749] Bye! ---<-snip>--- Signed-off-by: Vadim Lomovtsev <vlomovts@redhat.com> Reviewed-by: Jeff Layton <jlayton@redhat.com> Cc: stable@vger.kernel.org Signed-off-by: J. Bruce Fields <bfields@redhat.com>
2017-08-21 19:23:07 +08:00
if (svsk) {
/* Refer to svc_setup_socket() for details. */
rmb();
svsk->sk_odata(sk);
net: sunrpc: svcsock: fix NULL-pointer exception While running nfs/connectathon tests kernel NULL-pointer exception has been observed due to races in svcsock.c. Race is appear when kernel accepts connection by kernel_accept (which creates new socket) and start queuing ingress packets to new socket. This happens in ksoftirq context which could run concurrently on a different core while new socket setup is not done yet. The fix is to re-order socket user data init sequence and add write/read barrier calls to be sure that we got proper values for callback pointers before actually calling them. Test results: nfs/connectathon reports '0' failed tests for about 200+ iterations. Crash log: ---<-snip->--- [ 6708.638984] Unable to handle kernel NULL pointer dereference at virtual address 00000000 [ 6708.647093] pgd = ffff0000094e0000 [ 6708.650497] [00000000] *pgd=0000010ffff90003, *pud=0000010ffff90003, *pmd=0000010ffff80003, *pte=0000000000000000 [ 6708.660761] Internal error: Oops: 86000005 [#1] SMP [ 6708.665630] Modules linked in: nfsv3 nfnetlink_queue nfnetlink_log nfnetlink rpcsec_gss_krb5 nfsv4 dns_resolver nfs fscache overlay xt_CONNSECMARK xt_SECMARK xt_conntrack iptable_security ip_tables ah4 xfrm4_mode_transport sctp tun binfmt_misc ext4 jbd2 mbcache loop tcp_diag udp_diag inet_diag rpcrdma ib_isert iscsi_target_mod ib_iser rdma_cm iw_cm libiscsi scsi_transport_iscsi ib_srpt target_core_mod ib_srp scsi_transport_srp ib_ipoib ib_ucm ib_uverbs ib_umad ib_cm ib_core nls_koi8_u nls_cp932 ts_kmp nf_conntrack_ipv4 nf_defrag_ipv4 nf_conntrack vfat fat ghash_ce sha2_ce sha1_ce cavium_rng_vf i2c_thunderx sg thunderx_edac i2c_smbus edac_core cavium_rng nfsd auth_rpcgss nfs_acl lockd grace sunrpc xfs libcrc32c nicvf nicpf ast i2c_algo_bit drm_kms_helper syscopyarea sysfillrect sysimgblt fb_sys_fops [ 6708.736446] ttm drm i2c_core thunder_bgx thunder_xcv mdio_thunder mdio_cavium dm_mirror dm_region_hash dm_log dm_mod [last unloaded: stap_3c300909c5b3f46dcacd49aab3334af_87021] [ 6708.752275] CPU: 84 PID: 0 Comm: swapper/84 Tainted: G W OE 4.11.0-4.el7.aarch64 #1 [ 6708.760787] Hardware name: www.cavium.com CRB-2S/CRB-2S, BIOS 0.3 Mar 13 2017 [ 6708.767910] task: ffff810006842e80 task.stack: ffff81000689c000 [ 6708.773822] PC is at 0x0 [ 6708.776739] LR is at svc_data_ready+0x38/0x88 [sunrpc] [ 6708.781866] pc : [<0000000000000000>] lr : [<ffff0000029d7378>] pstate: 60000145 [ 6708.789248] sp : ffff810ffbad3900 [ 6708.792551] x29: ffff810ffbad3900 x28: ffff000008c73d58 [ 6708.797853] x27: 0000000000000000 x26: ffff81000bbe1e00 [ 6708.803156] x25: 0000000000000020 x24: ffff800f7410bf28 [ 6708.808458] x23: ffff000008c63000 x22: ffff000008c63000 [ 6708.813760] x21: ffff800f7410bf28 x20: ffff81000bbe1e00 [ 6708.819063] x19: ffff810012412400 x18: 00000000d82a9df2 [ 6708.824365] x17: 0000000000000000 x16: 0000000000000000 [ 6708.829667] x15: 0000000000000000 x14: 0000000000000001 [ 6708.834969] x13: 0000000000000000 x12: 722e736f622e676e [ 6708.840271] x11: 00000000f814dd99 x10: 0000000000000000 [ 6708.845573] x9 : 7374687225000000 x8 : 0000000000000000 [ 6708.850875] x7 : 0000000000000000 x6 : 0000000000000000 [ 6708.856177] x5 : 0000000000000028 x4 : 0000000000000000 [ 6708.861479] x3 : 0000000000000000 x2 : 00000000e5000000 [ 6708.866781] x1 : 0000000000000000 x0 : ffff81000bbe1e00 [ 6708.872084] [ 6708.873565] Process swapper/84 (pid: 0, stack limit = 0xffff81000689c000) [ 6708.880341] Stack: (0xffff810ffbad3900 to 0xffff8100068a0000) [ 6708.886075] Call trace: [ 6708.888513] Exception stack(0xffff810ffbad3710 to 0xffff810ffbad3840) [ 6708.894942] 3700: ffff810012412400 0001000000000000 [ 6708.902759] 3720: ffff810ffbad3900 0000000000000000 0000000060000145 ffff800f79300000 [ 6708.910577] 3740: ffff000009274d00 00000000000003ea 0000000000000015 ffff000008c63000 [ 6708.918395] 3760: ffff810ffbad3830 ffff800f79300000 000000000000004d 0000000000000000 [ 6708.926212] 3780: ffff810ffbad3890 ffff0000080f88dc ffff800f79300000 000000000000004d [ 6708.934030] 37a0: ffff800f7930093c ffff000008c63000 0000000000000000 0000000000000140 [ 6708.941848] 37c0: ffff000008c2c000 0000000000040b00 ffff81000bbe1e00 0000000000000000 [ 6708.949665] 37e0: 00000000e5000000 0000000000000000 0000000000000000 0000000000000028 [ 6708.957483] 3800: 0000000000000000 0000000000000000 0000000000000000 7374687225000000 [ 6708.965300] 3820: 0000000000000000 00000000f814dd99 722e736f622e676e 0000000000000000 [ 6708.973117] [< (null)>] (null) [ 6708.977824] [<ffff0000086f9fa4>] tcp_data_queue+0x754/0xc5c [ 6708.983386] [<ffff0000086fa64c>] tcp_rcv_established+0x1a0/0x67c [ 6708.989384] [<ffff000008704120>] tcp_v4_do_rcv+0x15c/0x22c [ 6708.994858] [<ffff000008707418>] tcp_v4_rcv+0xaf0/0xb58 [ 6709.000077] [<ffff0000086df784>] ip_local_deliver_finish+0x10c/0x254 [ 6709.006419] [<ffff0000086dfea4>] ip_local_deliver+0xf0/0xfc [ 6709.011980] [<ffff0000086dfad4>] ip_rcv_finish+0x208/0x3a4 [ 6709.017454] [<ffff0000086e018c>] ip_rcv+0x2dc/0x3c8 [ 6709.022328] [<ffff000008692fc8>] __netif_receive_skb_core+0x2f8/0xa0c [ 6709.028758] [<ffff000008696068>] __netif_receive_skb+0x38/0x84 [ 6709.034580] [<ffff00000869611c>] netif_receive_skb_internal+0x68/0xdc [ 6709.041010] [<ffff000008696bc0>] napi_gro_receive+0xcc/0x1a8 [ 6709.046690] [<ffff0000014b0fc4>] nicvf_cq_intr_handler+0x59c/0x730 [nicvf] [ 6709.053559] [<ffff0000014b1380>] nicvf_poll+0x38/0xb8 [nicvf] [ 6709.059295] [<ffff000008697a6c>] net_rx_action+0x2f8/0x464 [ 6709.064771] [<ffff000008081824>] __do_softirq+0x11c/0x308 [ 6709.070164] [<ffff0000080d14e4>] irq_exit+0x12c/0x174 [ 6709.075206] [<ffff00000813101c>] __handle_domain_irq+0x78/0xc4 [ 6709.081027] [<ffff000008081608>] gic_handle_irq+0x94/0x190 [ 6709.086501] Exception stack(0xffff81000689fdf0 to 0xffff81000689ff20) [ 6709.092929] fde0: 0000810ff2ec0000 ffff000008c10000 [ 6709.100747] fe00: ffff000008c70ef4 0000000000000001 0000000000000000 ffff810ffbad9b18 [ 6709.108565] fe20: ffff810ffbad9c70 ffff8100169d3800 ffff810006843ab0 ffff81000689fe80 [ 6709.116382] fe40: 0000000000000bd0 0000ffffdf979cd0 183f5913da192500 0000ffff8a254ce4 [ 6709.124200] fe60: 0000ffff8a254b78 0000aaab10339808 0000000000000000 0000ffff8a0c2a50 [ 6709.132018] fe80: 0000ffffdf979b10 ffff000008d6d450 ffff000008c10000 ffff000008d6d000 [ 6709.139836] fea0: 0000000000000054 ffff000008cd3dbc 0000000000000000 0000000000000000 [ 6709.147653] fec0: 0000000000000000 0000000000000000 0000000000000000 ffff81000689ff20 [ 6709.155471] fee0: ffff000008085240 ffff81000689ff20 ffff000008085244 0000000060000145 [ 6709.163289] ff00: ffff81000689ff10 ffff00000813f1e4 ffffffffffffffff ffff00000813f238 [ 6709.171107] [<ffff000008082eb4>] el1_irq+0xb4/0x140 [ 6709.175976] [<ffff000008085244>] arch_cpu_idle+0x44/0x11c [ 6709.181368] [<ffff0000087bf3b8>] default_idle_call+0x20/0x30 [ 6709.187020] [<ffff000008116d50>] do_idle+0x158/0x1e4 [ 6709.191973] [<ffff000008116ff4>] cpu_startup_entry+0x2c/0x30 [ 6709.197624] [<ffff00000808e7cc>] secondary_start_kernel+0x13c/0x160 [ 6709.203878] [<0000000001bc71c4>] 0x1bc71c4 [ 6709.207967] Code: bad PC value [ 6709.211061] SMP: stopping secondary CPUs [ 6709.218830] Starting crashdump kernel... [ 6709.222749] Bye! ---<-snip>--- Signed-off-by: Vadim Lomovtsev <vlomovts@redhat.com> Reviewed-by: Jeff Layton <jlayton@redhat.com> Cc: stable@vger.kernel.org Signed-off-by: J. Bruce Fields <bfields@redhat.com>
2017-08-21 19:23:07 +08:00
}
/*
* This callback may called twice when a new connection
* is established as a child socket inherits everything
* from a parent LISTEN socket.
* 1) data_ready method of the parent socket will be called
* when one of child sockets become ESTABLISHED.
* 2) data_ready method of the child socket may be called
* when it receives data before the socket is accepted.
* In case of 2, we should ignore it silently.
*/
if (sk->sk_state == TCP_LISTEN) {
if (svsk) {
set_bit(XPT_CONN, &svsk->sk_xprt.xpt_flags);
svc_xprt_enqueue(&svsk->sk_xprt);
} else
printk("svc: socket %p: no user data\n", sk);
}
}
/*
* A state change on a connected socket means it's dying or dead.
*/
static void svc_tcp_state_change(struct sock *sk)
{
struct svc_sock *svsk = (struct svc_sock *)sk->sk_user_data;
dprintk("svc: socket %p TCP (connected) state change %d (svsk %p)\n",
sk, sk->sk_state, sk->sk_user_data);
if (!svsk)
printk("svc: socket %p: no user data\n", sk);
else {
net: sunrpc: svcsock: fix NULL-pointer exception While running nfs/connectathon tests kernel NULL-pointer exception has been observed due to races in svcsock.c. Race is appear when kernel accepts connection by kernel_accept (which creates new socket) and start queuing ingress packets to new socket. This happens in ksoftirq context which could run concurrently on a different core while new socket setup is not done yet. The fix is to re-order socket user data init sequence and add write/read barrier calls to be sure that we got proper values for callback pointers before actually calling them. Test results: nfs/connectathon reports '0' failed tests for about 200+ iterations. Crash log: ---<-snip->--- [ 6708.638984] Unable to handle kernel NULL pointer dereference at virtual address 00000000 [ 6708.647093] pgd = ffff0000094e0000 [ 6708.650497] [00000000] *pgd=0000010ffff90003, *pud=0000010ffff90003, *pmd=0000010ffff80003, *pte=0000000000000000 [ 6708.660761] Internal error: Oops: 86000005 [#1] SMP [ 6708.665630] Modules linked in: nfsv3 nfnetlink_queue nfnetlink_log nfnetlink rpcsec_gss_krb5 nfsv4 dns_resolver nfs fscache overlay xt_CONNSECMARK xt_SECMARK xt_conntrack iptable_security ip_tables ah4 xfrm4_mode_transport sctp tun binfmt_misc ext4 jbd2 mbcache loop tcp_diag udp_diag inet_diag rpcrdma ib_isert iscsi_target_mod ib_iser rdma_cm iw_cm libiscsi scsi_transport_iscsi ib_srpt target_core_mod ib_srp scsi_transport_srp ib_ipoib ib_ucm ib_uverbs ib_umad ib_cm ib_core nls_koi8_u nls_cp932 ts_kmp nf_conntrack_ipv4 nf_defrag_ipv4 nf_conntrack vfat fat ghash_ce sha2_ce sha1_ce cavium_rng_vf i2c_thunderx sg thunderx_edac i2c_smbus edac_core cavium_rng nfsd auth_rpcgss nfs_acl lockd grace sunrpc xfs libcrc32c nicvf nicpf ast i2c_algo_bit drm_kms_helper syscopyarea sysfillrect sysimgblt fb_sys_fops [ 6708.736446] ttm drm i2c_core thunder_bgx thunder_xcv mdio_thunder mdio_cavium dm_mirror dm_region_hash dm_log dm_mod [last unloaded: stap_3c300909c5b3f46dcacd49aab3334af_87021] [ 6708.752275] CPU: 84 PID: 0 Comm: swapper/84 Tainted: G W OE 4.11.0-4.el7.aarch64 #1 [ 6708.760787] Hardware name: www.cavium.com CRB-2S/CRB-2S, BIOS 0.3 Mar 13 2017 [ 6708.767910] task: ffff810006842e80 task.stack: ffff81000689c000 [ 6708.773822] PC is at 0x0 [ 6708.776739] LR is at svc_data_ready+0x38/0x88 [sunrpc] [ 6708.781866] pc : [<0000000000000000>] lr : [<ffff0000029d7378>] pstate: 60000145 [ 6708.789248] sp : ffff810ffbad3900 [ 6708.792551] x29: ffff810ffbad3900 x28: ffff000008c73d58 [ 6708.797853] x27: 0000000000000000 x26: ffff81000bbe1e00 [ 6708.803156] x25: 0000000000000020 x24: ffff800f7410bf28 [ 6708.808458] x23: ffff000008c63000 x22: ffff000008c63000 [ 6708.813760] x21: ffff800f7410bf28 x20: ffff81000bbe1e00 [ 6708.819063] x19: ffff810012412400 x18: 00000000d82a9df2 [ 6708.824365] x17: 0000000000000000 x16: 0000000000000000 [ 6708.829667] x15: 0000000000000000 x14: 0000000000000001 [ 6708.834969] x13: 0000000000000000 x12: 722e736f622e676e [ 6708.840271] x11: 00000000f814dd99 x10: 0000000000000000 [ 6708.845573] x9 : 7374687225000000 x8 : 0000000000000000 [ 6708.850875] x7 : 0000000000000000 x6 : 0000000000000000 [ 6708.856177] x5 : 0000000000000028 x4 : 0000000000000000 [ 6708.861479] x3 : 0000000000000000 x2 : 00000000e5000000 [ 6708.866781] x1 : 0000000000000000 x0 : ffff81000bbe1e00 [ 6708.872084] [ 6708.873565] Process swapper/84 (pid: 0, stack limit = 0xffff81000689c000) [ 6708.880341] Stack: (0xffff810ffbad3900 to 0xffff8100068a0000) [ 6708.886075] Call trace: [ 6708.888513] Exception stack(0xffff810ffbad3710 to 0xffff810ffbad3840) [ 6708.894942] 3700: ffff810012412400 0001000000000000 [ 6708.902759] 3720: ffff810ffbad3900 0000000000000000 0000000060000145 ffff800f79300000 [ 6708.910577] 3740: ffff000009274d00 00000000000003ea 0000000000000015 ffff000008c63000 [ 6708.918395] 3760: ffff810ffbad3830 ffff800f79300000 000000000000004d 0000000000000000 [ 6708.926212] 3780: ffff810ffbad3890 ffff0000080f88dc ffff800f79300000 000000000000004d [ 6708.934030] 37a0: ffff800f7930093c ffff000008c63000 0000000000000000 0000000000000140 [ 6708.941848] 37c0: ffff000008c2c000 0000000000040b00 ffff81000bbe1e00 0000000000000000 [ 6708.949665] 37e0: 00000000e5000000 0000000000000000 0000000000000000 0000000000000028 [ 6708.957483] 3800: 0000000000000000 0000000000000000 0000000000000000 7374687225000000 [ 6708.965300] 3820: 0000000000000000 00000000f814dd99 722e736f622e676e 0000000000000000 [ 6708.973117] [< (null)>] (null) [ 6708.977824] [<ffff0000086f9fa4>] tcp_data_queue+0x754/0xc5c [ 6708.983386] [<ffff0000086fa64c>] tcp_rcv_established+0x1a0/0x67c [ 6708.989384] [<ffff000008704120>] tcp_v4_do_rcv+0x15c/0x22c [ 6708.994858] [<ffff000008707418>] tcp_v4_rcv+0xaf0/0xb58 [ 6709.000077] [<ffff0000086df784>] ip_local_deliver_finish+0x10c/0x254 [ 6709.006419] [<ffff0000086dfea4>] ip_local_deliver+0xf0/0xfc [ 6709.011980] [<ffff0000086dfad4>] ip_rcv_finish+0x208/0x3a4 [ 6709.017454] [<ffff0000086e018c>] ip_rcv+0x2dc/0x3c8 [ 6709.022328] [<ffff000008692fc8>] __netif_receive_skb_core+0x2f8/0xa0c [ 6709.028758] [<ffff000008696068>] __netif_receive_skb+0x38/0x84 [ 6709.034580] [<ffff00000869611c>] netif_receive_skb_internal+0x68/0xdc [ 6709.041010] [<ffff000008696bc0>] napi_gro_receive+0xcc/0x1a8 [ 6709.046690] [<ffff0000014b0fc4>] nicvf_cq_intr_handler+0x59c/0x730 [nicvf] [ 6709.053559] [<ffff0000014b1380>] nicvf_poll+0x38/0xb8 [nicvf] [ 6709.059295] [<ffff000008697a6c>] net_rx_action+0x2f8/0x464 [ 6709.064771] [<ffff000008081824>] __do_softirq+0x11c/0x308 [ 6709.070164] [<ffff0000080d14e4>] irq_exit+0x12c/0x174 [ 6709.075206] [<ffff00000813101c>] __handle_domain_irq+0x78/0xc4 [ 6709.081027] [<ffff000008081608>] gic_handle_irq+0x94/0x190 [ 6709.086501] Exception stack(0xffff81000689fdf0 to 0xffff81000689ff20) [ 6709.092929] fde0: 0000810ff2ec0000 ffff000008c10000 [ 6709.100747] fe00: ffff000008c70ef4 0000000000000001 0000000000000000 ffff810ffbad9b18 [ 6709.108565] fe20: ffff810ffbad9c70 ffff8100169d3800 ffff810006843ab0 ffff81000689fe80 [ 6709.116382] fe40: 0000000000000bd0 0000ffffdf979cd0 183f5913da192500 0000ffff8a254ce4 [ 6709.124200] fe60: 0000ffff8a254b78 0000aaab10339808 0000000000000000 0000ffff8a0c2a50 [ 6709.132018] fe80: 0000ffffdf979b10 ffff000008d6d450 ffff000008c10000 ffff000008d6d000 [ 6709.139836] fea0: 0000000000000054 ffff000008cd3dbc 0000000000000000 0000000000000000 [ 6709.147653] fec0: 0000000000000000 0000000000000000 0000000000000000 ffff81000689ff20 [ 6709.155471] fee0: ffff000008085240 ffff81000689ff20 ffff000008085244 0000000060000145 [ 6709.163289] ff00: ffff81000689ff10 ffff00000813f1e4 ffffffffffffffff ffff00000813f238 [ 6709.171107] [<ffff000008082eb4>] el1_irq+0xb4/0x140 [ 6709.175976] [<ffff000008085244>] arch_cpu_idle+0x44/0x11c [ 6709.181368] [<ffff0000087bf3b8>] default_idle_call+0x20/0x30 [ 6709.187020] [<ffff000008116d50>] do_idle+0x158/0x1e4 [ 6709.191973] [<ffff000008116ff4>] cpu_startup_entry+0x2c/0x30 [ 6709.197624] [<ffff00000808e7cc>] secondary_start_kernel+0x13c/0x160 [ 6709.203878] [<0000000001bc71c4>] 0x1bc71c4 [ 6709.207967] Code: bad PC value [ 6709.211061] SMP: stopping secondary CPUs [ 6709.218830] Starting crashdump kernel... [ 6709.222749] Bye! ---<-snip>--- Signed-off-by: Vadim Lomovtsev <vlomovts@redhat.com> Reviewed-by: Jeff Layton <jlayton@redhat.com> Cc: stable@vger.kernel.org Signed-off-by: J. Bruce Fields <bfields@redhat.com>
2017-08-21 19:23:07 +08:00
/* Refer to svc_setup_socket() for details. */
rmb();
svsk->sk_ostate(sk);
SUNRPC: accept() may return sockets that are still in SYN_RECV We're seeing traces of the following form: [10952.396347] svc: transport ffff88042ba4a 000 dequeued, inuse=2 [10952.396351] svc: tcp_accept ffff88042ba4 a000 sock ffff88042a6e4c80 [10952.396362] nfsd: connect from 10.2.6.1, port=187 [10952.396364] svc: svc_setup_socket ffff8800b99bcf00 [10952.396368] setting up TCP socket for reading [10952.396370] svc: svc_setup_socket created ffff8803eb10a000 (inet ffff88042b75b800) [10952.396373] svc: transport ffff8803eb10a000 put into queue [10952.396375] svc: transport ffff88042ba4a000 put into queue [10952.396377] svc: server ffff8800bb0ec000 waiting for data (to = 3600000) [10952.396380] svc: transport ffff8803eb10a000 dequeued, inuse=2 [10952.396381] svc_recv: found XPT_CLOSE [10952.396397] svc: svc_delete_xprt(ffff8803eb10a000) [10952.396398] svc: svc_tcp_sock_detach(ffff8803eb10a000) [10952.396399] svc: svc_sock_detach(ffff8803eb10a000) [10952.396412] svc: svc_sock_free(ffff8803eb10a000) i.e. an immediate close of the socket after initialisation. The culprit appears to be the test at the end of svc_tcp_init, which checks if the newly created socket is in the TCP_ESTABLISHED state, and immediately closes it if not. The evidence appears to suggest that the socket might still be in the SYN_RECV state at this time. The fix is to check for both states, and then to add a check in svc_tcp_state_change() to ensure we don't close the socket when it transitions into TCP_ESTABLISHED. Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com> Signed-off-by: J. Bruce Fields <bfields@redhat.com>
2016-07-26 21:51:19 +08:00
if (sk->sk_state != TCP_ESTABLISHED) {
set_bit(XPT_CLOSE, &svsk->sk_xprt.xpt_flags);
svc_xprt_enqueue(&svsk->sk_xprt);
}
}
}
/*
* Accept a TCP connection
*/
static struct svc_xprt *svc_tcp_accept(struct svc_xprt *xprt)
{
struct svc_sock *svsk = container_of(xprt, struct svc_sock, sk_xprt);
struct sockaddr_storage addr;
struct sockaddr *sin = (struct sockaddr *) &addr;
struct svc_serv *serv = svsk->sk_xprt.xpt_server;
struct socket *sock = svsk->sk_sock;
struct socket *newsock;
struct svc_sock *newsvsk;
int err, slen;
RPC_IFDEBUG(char buf[RPC_MAX_ADDRBUFLEN]);
dprintk("svc: tcp_accept %p sock %p\n", svsk, sock);
if (!sock)
return NULL;
clear_bit(XPT_CONN, &svsk->sk_xprt.xpt_flags);
err = kernel_accept(sock, &newsock, O_NONBLOCK);
if (err < 0) {
if (err == -ENOMEM)
printk(KERN_WARNING "%s: no more sockets!\n",
serv->sv_name);
else if (err != -EAGAIN)
net_warn_ratelimited("%s: accept failed (err %d)!\n",
serv->sv_name, -err);
return NULL;
}
set_bit(XPT_CONN, &svsk->sk_xprt.xpt_flags);
net: make getname() functions return length rather than use int* parameter Changes since v1: Added changes in these files: drivers/infiniband/hw/usnic/usnic_transport.c drivers/staging/lustre/lnet/lnet/lib-socket.c drivers/target/iscsi/iscsi_target_login.c drivers/vhost/net.c fs/dlm/lowcomms.c fs/ocfs2/cluster/tcp.c security/tomoyo/network.c Before: All these functions either return a negative error indicator, or store length of sockaddr into "int *socklen" parameter and return zero on success. "int *socklen" parameter is awkward. For example, if caller does not care, it still needs to provide on-stack storage for the value it does not need. None of the many FOO_getname() functions of various protocols ever used old value of *socklen. They always just overwrite it. This change drops this parameter, and makes all these functions, on success, return length of sockaddr. It's always >= 0 and can be differentiated from an error. Tests in callers are changed from "if (err)" to "if (err < 0)", where needed. rpc_sockname() lost "int buflen" parameter, since its only use was to be passed to kernel_getsockname() as &buflen and subsequently not used in any way. Userspace API is not changed. text data bss dec hex filename 30108430 2633624 873672 33615726 200ef6e vmlinux.before.o 30108109 2633612 873672 33615393 200ee21 vmlinux.o Signed-off-by: Denys Vlasenko <dvlasenk@redhat.com> CC: David S. Miller <davem@davemloft.net> CC: linux-kernel@vger.kernel.org CC: netdev@vger.kernel.org CC: linux-bluetooth@vger.kernel.org CC: linux-decnet-user@lists.sourceforge.net CC: linux-wireless@vger.kernel.org CC: linux-rdma@vger.kernel.org CC: linux-sctp@vger.kernel.org CC: linux-nfs@vger.kernel.org CC: linux-x25@vger.kernel.org Signed-off-by: David S. Miller <davem@davemloft.net>
2018-02-13 03:00:20 +08:00
err = kernel_getpeername(newsock, sin);
if (err < 0) {
net_warn_ratelimited("%s: peername failed (err %d)!\n",
serv->sv_name, -err);
goto failed; /* aborted connection or whatever */
}
net: make getname() functions return length rather than use int* parameter Changes since v1: Added changes in these files: drivers/infiniband/hw/usnic/usnic_transport.c drivers/staging/lustre/lnet/lnet/lib-socket.c drivers/target/iscsi/iscsi_target_login.c drivers/vhost/net.c fs/dlm/lowcomms.c fs/ocfs2/cluster/tcp.c security/tomoyo/network.c Before: All these functions either return a negative error indicator, or store length of sockaddr into "int *socklen" parameter and return zero on success. "int *socklen" parameter is awkward. For example, if caller does not care, it still needs to provide on-stack storage for the value it does not need. None of the many FOO_getname() functions of various protocols ever used old value of *socklen. They always just overwrite it. This change drops this parameter, and makes all these functions, on success, return length of sockaddr. It's always >= 0 and can be differentiated from an error. Tests in callers are changed from "if (err)" to "if (err < 0)", where needed. rpc_sockname() lost "int buflen" parameter, since its only use was to be passed to kernel_getsockname() as &buflen and subsequently not used in any way. Userspace API is not changed. text data bss dec hex filename 30108430 2633624 873672 33615726 200ef6e vmlinux.before.o 30108109 2633612 873672 33615393 200ee21 vmlinux.o Signed-off-by: Denys Vlasenko <dvlasenk@redhat.com> CC: David S. Miller <davem@davemloft.net> CC: linux-kernel@vger.kernel.org CC: netdev@vger.kernel.org CC: linux-bluetooth@vger.kernel.org CC: linux-decnet-user@lists.sourceforge.net CC: linux-wireless@vger.kernel.org CC: linux-rdma@vger.kernel.org CC: linux-sctp@vger.kernel.org CC: linux-nfs@vger.kernel.org CC: linux-x25@vger.kernel.org Signed-off-by: David S. Miller <davem@davemloft.net>
2018-02-13 03:00:20 +08:00
slen = err;
/* Ideally, we would want to reject connections from unauthorized
* hosts here, but when we get encryption, the IP of the host won't
* tell us anything. For now just warn about unpriv connections.
*/
if (!svc_port_is_privileged(sin)) {
dprintk("%s: connect from unprivileged port: %s\n",
serv->sv_name,
__svc_print_addr(sin, buf, sizeof(buf)));
}
dprintk("%s: connect from %s\n", serv->sv_name,
__svc_print_addr(sin, buf, sizeof(buf)));
/* Reset the inherited callbacks before calling svc_setup_socket */
newsock->sk->sk_state_change = svsk->sk_ostate;
newsock->sk->sk_data_ready = svsk->sk_odata;
newsock->sk->sk_write_space = svsk->sk_owspace;
/* make sure that a write doesn't block forever when
* low on memory
*/
newsock->sk->sk_sndtimeo = HZ*30;
newsvsk = svc_setup_socket(serv, newsock,
(SVC_SOCK_ANONYMOUS | SVC_SOCK_TEMPORARY));
if (IS_ERR(newsvsk))
goto failed;
svc: Move the sockaddr information to svc_xprt This patch moves the transport sockaddr to the svc_xprt structure. Convenience functions are added to set and get the local and remote addresses of a transport from the transport provider as well as determine the length of a sockaddr. A transport is responsible for setting the xpt_local and xpt_remote addresses in the svc_xprt structure as part of transport creation and xpo_accept processing. This cannot be done in a generic way and in fact varies between TCP, UDP and RDMA. A set of xpo_ functions (e.g. getlocalname, getremotename) could have been added but this would have resulted in additional caching and copying of the addresses around. Note that the xpt_local address should also be set on listening endpoints; for TCP/RDMA this is done as part of endpoint creation. For connected transports like TCP and RDMA, the addresses never change and can be set once and copied into the rqstp structure for each request. For UDP, however, the local and remote addresses may change for each request. In this case, the address information is obtained from the UDP recvmsg info and copied into the rqstp structure from there. A svc_xprt_local_port function was also added that returns the local port given a transport. This is used by svc_create_xprt when returning the port associated with a newly created transport, and later when creating a generic find transport service to check if a service is already listening on a given port. Signed-off-by: Tom Tucker <tom@opengridcomputing.com> Acked-by: Neil Brown <neilb@suse.de> Reviewed-by: Chuck Lever <chuck.lever@oracle.com> Reviewed-by: Greg Banks <gnb@sgi.com> Signed-off-by: J. Bruce Fields <bfields@citi.umich.edu>
2007-12-31 11:08:12 +08:00
svc_xprt_set_remote(&newsvsk->sk_xprt, sin, slen);
net: make getname() functions return length rather than use int* parameter Changes since v1: Added changes in these files: drivers/infiniband/hw/usnic/usnic_transport.c drivers/staging/lustre/lnet/lnet/lib-socket.c drivers/target/iscsi/iscsi_target_login.c drivers/vhost/net.c fs/dlm/lowcomms.c fs/ocfs2/cluster/tcp.c security/tomoyo/network.c Before: All these functions either return a negative error indicator, or store length of sockaddr into "int *socklen" parameter and return zero on success. "int *socklen" parameter is awkward. For example, if caller does not care, it still needs to provide on-stack storage for the value it does not need. None of the many FOO_getname() functions of various protocols ever used old value of *socklen. They always just overwrite it. This change drops this parameter, and makes all these functions, on success, return length of sockaddr. It's always >= 0 and can be differentiated from an error. Tests in callers are changed from "if (err)" to "if (err < 0)", where needed. rpc_sockname() lost "int buflen" parameter, since its only use was to be passed to kernel_getsockname() as &buflen and subsequently not used in any way. Userspace API is not changed. text data bss dec hex filename 30108430 2633624 873672 33615726 200ef6e vmlinux.before.o 30108109 2633612 873672 33615393 200ee21 vmlinux.o Signed-off-by: Denys Vlasenko <dvlasenk@redhat.com> CC: David S. Miller <davem@davemloft.net> CC: linux-kernel@vger.kernel.org CC: netdev@vger.kernel.org CC: linux-bluetooth@vger.kernel.org CC: linux-decnet-user@lists.sourceforge.net CC: linux-wireless@vger.kernel.org CC: linux-rdma@vger.kernel.org CC: linux-sctp@vger.kernel.org CC: linux-nfs@vger.kernel.org CC: linux-x25@vger.kernel.org Signed-off-by: David S. Miller <davem@davemloft.net>
2018-02-13 03:00:20 +08:00
err = kernel_getsockname(newsock, sin);
slen = err;
if (unlikely(err < 0)) {
dprintk("svc_tcp_accept: kernel_getsockname error %d\n", -err);
slen = offsetof(struct sockaddr, sa_data);
}
svc: Move the sockaddr information to svc_xprt This patch moves the transport sockaddr to the svc_xprt structure. Convenience functions are added to set and get the local and remote addresses of a transport from the transport provider as well as determine the length of a sockaddr. A transport is responsible for setting the xpt_local and xpt_remote addresses in the svc_xprt structure as part of transport creation and xpo_accept processing. This cannot be done in a generic way and in fact varies between TCP, UDP and RDMA. A set of xpo_ functions (e.g. getlocalname, getremotename) could have been added but this would have resulted in additional caching and copying of the addresses around. Note that the xpt_local address should also be set on listening endpoints; for TCP/RDMA this is done as part of endpoint creation. For connected transports like TCP and RDMA, the addresses never change and can be set once and copied into the rqstp structure for each request. For UDP, however, the local and remote addresses may change for each request. In this case, the address information is obtained from the UDP recvmsg info and copied into the rqstp structure from there. A svc_xprt_local_port function was also added that returns the local port given a transport. This is used by svc_create_xprt when returning the port associated with a newly created transport, and later when creating a generic find transport service to check if a service is already listening on a given port. Signed-off-by: Tom Tucker <tom@opengridcomputing.com> Acked-by: Neil Brown <neilb@suse.de> Reviewed-by: Chuck Lever <chuck.lever@oracle.com> Reviewed-by: Greg Banks <gnb@sgi.com> Signed-off-by: J. Bruce Fields <bfields@citi.umich.edu>
2007-12-31 11:08:12 +08:00
svc_xprt_set_local(&newsvsk->sk_xprt, sin, slen);
if (sock_is_loopback(newsock->sk))
set_bit(XPT_LOCAL, &newsvsk->sk_xprt.xpt_flags);
else
clear_bit(XPT_LOCAL, &newsvsk->sk_xprt.xpt_flags);
if (serv->sv_stats)
serv->sv_stats->nettcpconn++;
return &newsvsk->sk_xprt;
failed:
sock_release(newsock);
return NULL;
}
static unsigned int svc_tcp_restore_pages(struct svc_sock *svsk, struct svc_rqst *rqstp)
{
unsigned int i, len, npages;
if (svsk->sk_datalen == 0)
return 0;
len = svsk->sk_datalen;
npages = (len + PAGE_SIZE - 1) >> PAGE_SHIFT;
for (i = 0; i < npages; i++) {
if (rqstp->rq_pages[i] != NULL)
put_page(rqstp->rq_pages[i]);
BUG_ON(svsk->sk_pages[i] == NULL);
rqstp->rq_pages[i] = svsk->sk_pages[i];
svsk->sk_pages[i] = NULL;
}
rqstp->rq_arg.head[0].iov_base = page_address(rqstp->rq_pages[0]);
return len;
}
static void svc_tcp_save_pages(struct svc_sock *svsk, struct svc_rqst *rqstp)
{
unsigned int i, len, npages;
if (svsk->sk_datalen == 0)
return;
len = svsk->sk_datalen;
npages = (len + PAGE_SIZE - 1) >> PAGE_SHIFT;
for (i = 0; i < npages; i++) {
svsk->sk_pages[i] = rqstp->rq_pages[i];
rqstp->rq_pages[i] = NULL;
}
}
static void svc_tcp_clear_pages(struct svc_sock *svsk)
{
unsigned int i, len, npages;
if (svsk->sk_datalen == 0)
goto out;
len = svsk->sk_datalen;
npages = (len + PAGE_SIZE - 1) >> PAGE_SHIFT;
for (i = 0; i < npages; i++) {
if (svsk->sk_pages[i] == NULL) {
WARN_ON_ONCE(1);
continue;
}
put_page(svsk->sk_pages[i]);
svsk->sk_pages[i] = NULL;
}
out:
svsk->sk_tcplen = 0;
svsk->sk_datalen = 0;
}
/*
* Receive fragment record header.
* If we haven't gotten the record length yet, get the next four bytes.
*/
static int svc_tcp_recv_record(struct svc_sock *svsk, struct svc_rqst *rqstp)
{
struct svc_serv *serv = svsk->sk_xprt.xpt_server;
unsigned int want;
int len;
if (svsk->sk_tcplen < sizeof(rpc_fraghdr)) {
struct kvec iov;
want = sizeof(rpc_fraghdr) - svsk->sk_tcplen;
iov.iov_base = ((char *) &svsk->sk_reclen) + svsk->sk_tcplen;
iov.iov_len = want;
len = svc_recvfrom(rqstp, &iov, 1, want, 0);
if (len < 0)
goto error;
svsk->sk_tcplen += len;
if (len < want) {
dprintk("svc: short recvfrom while reading record "
"length (%d of %d)\n", len, want);
return -EAGAIN;
}
dprintk("svc: TCP record, %d bytes\n", svc_sock_reclen(svsk));
if (svc_sock_reclen(svsk) + svsk->sk_datalen >
serv->sv_max_mesg) {
net_notice_ratelimited("RPC: fragment too large: %d\n",
svc_sock_reclen(svsk));
goto err_delete;
}
}
return svc_sock_reclen(svsk);
error:
dprintk("RPC: TCP recv_record got %d\n", len);
return len;
err_delete:
set_bit(XPT_CLOSE, &svsk->sk_xprt.xpt_flags);
return -EAGAIN;
}
static int receive_cb_reply(struct svc_sock *svsk, struct svc_rqst *rqstp)
nfsd41: sunrpc: Added rpc server-side backchannel handling When the call direction is a reply, copy the xid and call direction into the req->rq_private_buf.head[0].iov_base otherwise rpc_verify_header returns rpc_garbage. Signed-off-by: Rahul Iyer <iyer@netapp.com> Signed-off-by: Mike Sager <sager@netapp.com> Signed-off-by: Marc Eshel <eshel@almaden.ibm.com> Signed-off-by: Benny Halevy <bhalevy@panasas.com> Signed-off-by: Ricardo Labiaga <Ricardo.Labiaga@netapp.com> Signed-off-by: Andy Adamson <andros@netapp.com> Signed-off-by: Benny Halevy <bhalevy@panasas.com> [get rid of CONFIG_NFSD_V4_1] [sunrpc: refactoring of svc_tcp_recvfrom] [nfsd41: sunrpc: create common send routine for the fore and the back channels] [nfsd41: sunrpc: Use free_page() to free server backchannel pages] [nfsd41: sunrpc: Document server backchannel locking] [nfsd41: sunrpc: remove bc_connect_worker()] [nfsd41: sunrpc: Define xprt_server_backchannel()[ [nfsd41: sunrpc: remove bc_close and bc_init_auto_disconnect dummy functions] [nfsd41: sunrpc: eliminate unneeded switch statement in xs_setup_tcp()] [nfsd41: sunrpc: Don't auto close the server backchannel connection] [nfsd41: sunrpc: Remove unused functions] Signed-off-by: Alexandros Batsakis <batsakis@netapp.com> Signed-off-by: Ricardo Labiaga <Ricardo.Labiaga@netapp.com> Signed-off-by: Benny Halevy <bhalevy@panasas.com> [nfsd41: change bc_sock to bc_xprt] [nfsd41: sunrpc: move struct rpc_buffer def into a common header file] [nfsd41: sunrpc: use rpc_sleep in bc_send_request so not to block on mutex] [removed cosmetic changes] Signed-off-by: Benny Halevy <bhalevy@panasas.com> [sunrpc: add new xprt class for nfsv4.1 backchannel] [sunrpc: v2.1 change handling of auto_close and init_auto_disconnect operations for the nfsv4.1 backchannel] Signed-off-by: Alexandros Batsakis <batsakis@netapp.com> [reverted more cosmetic leftovers] [got rid of xprt_server_backchannel] [separated "nfsd41: sunrpc: add new xprt class for nfsv4.1 backchannel"] Signed-off-by: Benny Halevy <bhalevy@panasas.com> Cc: Trond Myklebust <trond.myklebust@netapp.com> [sunrpc: change idle timeout value for the backchannel] Signed-off-by: Alexandros Batsakis <batsakis@netapp.com> Signed-off-by: Benny Halevy <bhalevy@panasas.com> Acked-by: Trond Myklebust <trond.myklebust@netapp.com> Signed-off-by: J. Bruce Fields <bfields@citi.umich.edu>
2009-09-10 22:32:28 +08:00
{
struct rpc_xprt *bc_xprt = svsk->sk_xprt.xpt_bc_xprt;
nfsd41: sunrpc: Added rpc server-side backchannel handling When the call direction is a reply, copy the xid and call direction into the req->rq_private_buf.head[0].iov_base otherwise rpc_verify_header returns rpc_garbage. Signed-off-by: Rahul Iyer <iyer@netapp.com> Signed-off-by: Mike Sager <sager@netapp.com> Signed-off-by: Marc Eshel <eshel@almaden.ibm.com> Signed-off-by: Benny Halevy <bhalevy@panasas.com> Signed-off-by: Ricardo Labiaga <Ricardo.Labiaga@netapp.com> Signed-off-by: Andy Adamson <andros@netapp.com> Signed-off-by: Benny Halevy <bhalevy@panasas.com> [get rid of CONFIG_NFSD_V4_1] [sunrpc: refactoring of svc_tcp_recvfrom] [nfsd41: sunrpc: create common send routine for the fore and the back channels] [nfsd41: sunrpc: Use free_page() to free server backchannel pages] [nfsd41: sunrpc: Document server backchannel locking] [nfsd41: sunrpc: remove bc_connect_worker()] [nfsd41: sunrpc: Define xprt_server_backchannel()[ [nfsd41: sunrpc: remove bc_close and bc_init_auto_disconnect dummy functions] [nfsd41: sunrpc: eliminate unneeded switch statement in xs_setup_tcp()] [nfsd41: sunrpc: Don't auto close the server backchannel connection] [nfsd41: sunrpc: Remove unused functions] Signed-off-by: Alexandros Batsakis <batsakis@netapp.com> Signed-off-by: Ricardo Labiaga <Ricardo.Labiaga@netapp.com> Signed-off-by: Benny Halevy <bhalevy@panasas.com> [nfsd41: change bc_sock to bc_xprt] [nfsd41: sunrpc: move struct rpc_buffer def into a common header file] [nfsd41: sunrpc: use rpc_sleep in bc_send_request so not to block on mutex] [removed cosmetic changes] Signed-off-by: Benny Halevy <bhalevy@panasas.com> [sunrpc: add new xprt class for nfsv4.1 backchannel] [sunrpc: v2.1 change handling of auto_close and init_auto_disconnect operations for the nfsv4.1 backchannel] Signed-off-by: Alexandros Batsakis <batsakis@netapp.com> [reverted more cosmetic leftovers] [got rid of xprt_server_backchannel] [separated "nfsd41: sunrpc: add new xprt class for nfsv4.1 backchannel"] Signed-off-by: Benny Halevy <bhalevy@panasas.com> Cc: Trond Myklebust <trond.myklebust@netapp.com> [sunrpc: change idle timeout value for the backchannel] Signed-off-by: Alexandros Batsakis <batsakis@netapp.com> Signed-off-by: Benny Halevy <bhalevy@panasas.com> Acked-by: Trond Myklebust <trond.myklebust@netapp.com> Signed-off-by: J. Bruce Fields <bfields@citi.umich.edu>
2009-09-10 22:32:28 +08:00
struct rpc_rqst *req = NULL;
struct kvec *src, *dst;
__be32 *p = (__be32 *)rqstp->rq_arg.head[0].iov_base;
__be32 xid;
__be32 calldir;
nfsd41: sunrpc: Added rpc server-side backchannel handling When the call direction is a reply, copy the xid and call direction into the req->rq_private_buf.head[0].iov_base otherwise rpc_verify_header returns rpc_garbage. Signed-off-by: Rahul Iyer <iyer@netapp.com> Signed-off-by: Mike Sager <sager@netapp.com> Signed-off-by: Marc Eshel <eshel@almaden.ibm.com> Signed-off-by: Benny Halevy <bhalevy@panasas.com> Signed-off-by: Ricardo Labiaga <Ricardo.Labiaga@netapp.com> Signed-off-by: Andy Adamson <andros@netapp.com> Signed-off-by: Benny Halevy <bhalevy@panasas.com> [get rid of CONFIG_NFSD_V4_1] [sunrpc: refactoring of svc_tcp_recvfrom] [nfsd41: sunrpc: create common send routine for the fore and the back channels] [nfsd41: sunrpc: Use free_page() to free server backchannel pages] [nfsd41: sunrpc: Document server backchannel locking] [nfsd41: sunrpc: remove bc_connect_worker()] [nfsd41: sunrpc: Define xprt_server_backchannel()[ [nfsd41: sunrpc: remove bc_close and bc_init_auto_disconnect dummy functions] [nfsd41: sunrpc: eliminate unneeded switch statement in xs_setup_tcp()] [nfsd41: sunrpc: Don't auto close the server backchannel connection] [nfsd41: sunrpc: Remove unused functions] Signed-off-by: Alexandros Batsakis <batsakis@netapp.com> Signed-off-by: Ricardo Labiaga <Ricardo.Labiaga@netapp.com> Signed-off-by: Benny Halevy <bhalevy@panasas.com> [nfsd41: change bc_sock to bc_xprt] [nfsd41: sunrpc: move struct rpc_buffer def into a common header file] [nfsd41: sunrpc: use rpc_sleep in bc_send_request so not to block on mutex] [removed cosmetic changes] Signed-off-by: Benny Halevy <bhalevy@panasas.com> [sunrpc: add new xprt class for nfsv4.1 backchannel] [sunrpc: v2.1 change handling of auto_close and init_auto_disconnect operations for the nfsv4.1 backchannel] Signed-off-by: Alexandros Batsakis <batsakis@netapp.com> [reverted more cosmetic leftovers] [got rid of xprt_server_backchannel] [separated "nfsd41: sunrpc: add new xprt class for nfsv4.1 backchannel"] Signed-off-by: Benny Halevy <bhalevy@panasas.com> Cc: Trond Myklebust <trond.myklebust@netapp.com> [sunrpc: change idle timeout value for the backchannel] Signed-off-by: Alexandros Batsakis <batsakis@netapp.com> Signed-off-by: Benny Halevy <bhalevy@panasas.com> Acked-by: Trond Myklebust <trond.myklebust@netapp.com> Signed-off-by: J. Bruce Fields <bfields@citi.umich.edu>
2009-09-10 22:32:28 +08:00
xid = *p++;
calldir = *p;
if (!bc_xprt)
return -EAGAIN;
spin_lock(&bc_xprt->queue_lock);
req = xprt_lookup_rqst(bc_xprt, xid);
if (!req)
goto unlock_notfound;
memcpy(&req->rq_private_buf, &req->rq_rcv_buf, sizeof(struct xdr_buf));
/*
* XXX!: cheating for now! Only copying HEAD.
* But we know this is good enough for now (in fact, for any
* callback reply in the forseeable future).
*/
dst = &req->rq_private_buf.head[0];
src = &rqstp->rq_arg.head[0];
if (dst->iov_len < src->iov_len)
goto unlock_eagain; /* whatever; just giving up. */
memcpy(dst->iov_base, src->iov_base, src->iov_len);
xprt_complete_rqst(req->rq_task, rqstp->rq_arg.len);
rqstp->rq_arg.len = 0;
spin_unlock(&bc_xprt->queue_lock);
return 0;
unlock_notfound:
printk(KERN_NOTICE
"%s: Got unrecognized reply: "
"calldir 0x%x xpt_bc_xprt %p xid %08x\n",
__func__, ntohl(calldir),
bc_xprt, ntohl(xid));
unlock_eagain:
spin_unlock(&bc_xprt->queue_lock);
return -EAGAIN;
}
static int copy_pages_to_kvecs(struct kvec *vec, struct page **pages, int len)
{
int i = 0;
int t = 0;
while (t < len) {
vec[i].iov_base = page_address(pages[i]);
vec[i].iov_len = PAGE_SIZE;
i++;
t += PAGE_SIZE;
}
return i;
nfsd41: sunrpc: Added rpc server-side backchannel handling When the call direction is a reply, copy the xid and call direction into the req->rq_private_buf.head[0].iov_base otherwise rpc_verify_header returns rpc_garbage. Signed-off-by: Rahul Iyer <iyer@netapp.com> Signed-off-by: Mike Sager <sager@netapp.com> Signed-off-by: Marc Eshel <eshel@almaden.ibm.com> Signed-off-by: Benny Halevy <bhalevy@panasas.com> Signed-off-by: Ricardo Labiaga <Ricardo.Labiaga@netapp.com> Signed-off-by: Andy Adamson <andros@netapp.com> Signed-off-by: Benny Halevy <bhalevy@panasas.com> [get rid of CONFIG_NFSD_V4_1] [sunrpc: refactoring of svc_tcp_recvfrom] [nfsd41: sunrpc: create common send routine for the fore and the back channels] [nfsd41: sunrpc: Use free_page() to free server backchannel pages] [nfsd41: sunrpc: Document server backchannel locking] [nfsd41: sunrpc: remove bc_connect_worker()] [nfsd41: sunrpc: Define xprt_server_backchannel()[ [nfsd41: sunrpc: remove bc_close and bc_init_auto_disconnect dummy functions] [nfsd41: sunrpc: eliminate unneeded switch statement in xs_setup_tcp()] [nfsd41: sunrpc: Don't auto close the server backchannel connection] [nfsd41: sunrpc: Remove unused functions] Signed-off-by: Alexandros Batsakis <batsakis@netapp.com> Signed-off-by: Ricardo Labiaga <Ricardo.Labiaga@netapp.com> Signed-off-by: Benny Halevy <bhalevy@panasas.com> [nfsd41: change bc_sock to bc_xprt] [nfsd41: sunrpc: move struct rpc_buffer def into a common header file] [nfsd41: sunrpc: use rpc_sleep in bc_send_request so not to block on mutex] [removed cosmetic changes] Signed-off-by: Benny Halevy <bhalevy@panasas.com> [sunrpc: add new xprt class for nfsv4.1 backchannel] [sunrpc: v2.1 change handling of auto_close and init_auto_disconnect operations for the nfsv4.1 backchannel] Signed-off-by: Alexandros Batsakis <batsakis@netapp.com> [reverted more cosmetic leftovers] [got rid of xprt_server_backchannel] [separated "nfsd41: sunrpc: add new xprt class for nfsv4.1 backchannel"] Signed-off-by: Benny Halevy <bhalevy@panasas.com> Cc: Trond Myklebust <trond.myklebust@netapp.com> [sunrpc: change idle timeout value for the backchannel] Signed-off-by: Alexandros Batsakis <batsakis@netapp.com> Signed-off-by: Benny Halevy <bhalevy@panasas.com> Acked-by: Trond Myklebust <trond.myklebust@netapp.com> Signed-off-by: J. Bruce Fields <bfields@citi.umich.edu>
2009-09-10 22:32:28 +08:00
}
static void svc_tcp_fragment_received(struct svc_sock *svsk)
{
/* If we have more data, signal svc_xprt_enqueue() to try again */
dprintk("svc: TCP %s record (%d bytes)\n",
svc_sock_final_rec(svsk) ? "final" : "nonfinal",
svc_sock_reclen(svsk));
svsk->sk_tcplen = 0;
svsk->sk_reclen = 0;
}
/*
* Receive data from a TCP socket.
*/
static int svc_tcp_recvfrom(struct svc_rqst *rqstp)
{
struct svc_sock *svsk =
container_of(rqstp->rq_xprt, struct svc_sock, sk_xprt);
struct svc_serv *serv = svsk->sk_xprt.xpt_server;
int len;
struct kvec *vec;
unsigned int want, base;
__be32 *p;
__be32 calldir;
int pnum;
dprintk("svc: tcp_recv %p data %d conn %d close %d\n",
svsk, test_bit(XPT_DATA, &svsk->sk_xprt.xpt_flags),
test_bit(XPT_CONN, &svsk->sk_xprt.xpt_flags),
test_bit(XPT_CLOSE, &svsk->sk_xprt.xpt_flags));
len = svc_tcp_recv_record(svsk, rqstp);
if (len < 0)
goto error;
base = svc_tcp_restore_pages(svsk, rqstp);
want = svc_sock_reclen(svsk) - (svsk->sk_tcplen - sizeof(rpc_fraghdr));
vec = rqstp->rq_vec;
nfsd41: sunrpc: Added rpc server-side backchannel handling When the call direction is a reply, copy the xid and call direction into the req->rq_private_buf.head[0].iov_base otherwise rpc_verify_header returns rpc_garbage. Signed-off-by: Rahul Iyer <iyer@netapp.com> Signed-off-by: Mike Sager <sager@netapp.com> Signed-off-by: Marc Eshel <eshel@almaden.ibm.com> Signed-off-by: Benny Halevy <bhalevy@panasas.com> Signed-off-by: Ricardo Labiaga <Ricardo.Labiaga@netapp.com> Signed-off-by: Andy Adamson <andros@netapp.com> Signed-off-by: Benny Halevy <bhalevy@panasas.com> [get rid of CONFIG_NFSD_V4_1] [sunrpc: refactoring of svc_tcp_recvfrom] [nfsd41: sunrpc: create common send routine for the fore and the back channels] [nfsd41: sunrpc: Use free_page() to free server backchannel pages] [nfsd41: sunrpc: Document server backchannel locking] [nfsd41: sunrpc: remove bc_connect_worker()] [nfsd41: sunrpc: Define xprt_server_backchannel()[ [nfsd41: sunrpc: remove bc_close and bc_init_auto_disconnect dummy functions] [nfsd41: sunrpc: eliminate unneeded switch statement in xs_setup_tcp()] [nfsd41: sunrpc: Don't auto close the server backchannel connection] [nfsd41: sunrpc: Remove unused functions] Signed-off-by: Alexandros Batsakis <batsakis@netapp.com> Signed-off-by: Ricardo Labiaga <Ricardo.Labiaga@netapp.com> Signed-off-by: Benny Halevy <bhalevy@panasas.com> [nfsd41: change bc_sock to bc_xprt] [nfsd41: sunrpc: move struct rpc_buffer def into a common header file] [nfsd41: sunrpc: use rpc_sleep in bc_send_request so not to block on mutex] [removed cosmetic changes] Signed-off-by: Benny Halevy <bhalevy@panasas.com> [sunrpc: add new xprt class for nfsv4.1 backchannel] [sunrpc: v2.1 change handling of auto_close and init_auto_disconnect operations for the nfsv4.1 backchannel] Signed-off-by: Alexandros Batsakis <batsakis@netapp.com> [reverted more cosmetic leftovers] [got rid of xprt_server_backchannel] [separated "nfsd41: sunrpc: add new xprt class for nfsv4.1 backchannel"] Signed-off-by: Benny Halevy <bhalevy@panasas.com> Cc: Trond Myklebust <trond.myklebust@netapp.com> [sunrpc: change idle timeout value for the backchannel] Signed-off-by: Alexandros Batsakis <batsakis@netapp.com> Signed-off-by: Benny Halevy <bhalevy@panasas.com> Acked-by: Trond Myklebust <trond.myklebust@netapp.com> Signed-off-by: J. Bruce Fields <bfields@citi.umich.edu>
2009-09-10 22:32:28 +08:00
pnum = copy_pages_to_kvecs(&vec[0], &rqstp->rq_pages[0], base + want);
rqstp->rq_respages = &rqstp->rq_pages[pnum];
rqstp->rq_next_page = rqstp->rq_respages + 1;
/* Now receive data */
len = svc_recvfrom(rqstp, vec, pnum, base + want, base);
if (len >= 0) {
svsk->sk_tcplen += len;
svsk->sk_datalen += len;
}
if (len != want || !svc_sock_final_rec(svsk)) {
svc_tcp_save_pages(svsk, rqstp);
if (len < 0 && len != -EAGAIN)
goto err_delete;
if (len == want)
svc_tcp_fragment_received(svsk);
else
dprintk("svc: incomplete TCP record (%d of %d)\n",
(int)(svsk->sk_tcplen - sizeof(rpc_fraghdr)),
svc_sock_reclen(svsk));
goto err_noclose;
}
if (svsk->sk_datalen < 8) {
svsk->sk_datalen = 0;
goto err_delete; /* client is nuts. */
}
rqstp->rq_arg.len = svsk->sk_datalen;
rqstp->rq_arg.page_base = 0;
if (rqstp->rq_arg.len <= rqstp->rq_arg.head[0].iov_len) {
rqstp->rq_arg.head[0].iov_len = rqstp->rq_arg.len;
rqstp->rq_arg.page_len = 0;
} else
rqstp->rq_arg.page_len = rqstp->rq_arg.len - rqstp->rq_arg.head[0].iov_len;
rqstp->rq_xprt_ctxt = NULL;
rqstp->rq_prot = IPPROTO_TCP;
if (test_bit(XPT_LOCAL, &svsk->sk_xprt.xpt_flags))
set_bit(RQ_LOCAL, &rqstp->rq_flags);
else
clear_bit(RQ_LOCAL, &rqstp->rq_flags);
p = (__be32 *)rqstp->rq_arg.head[0].iov_base;
calldir = p[1];
if (calldir)
len = receive_cb_reply(svsk, rqstp);
/* Reset TCP read info */
svsk->sk_datalen = 0;
svc_tcp_fragment_received(svsk);
if (len < 0)
goto error;
svc: Move the sockaddr information to svc_xprt This patch moves the transport sockaddr to the svc_xprt structure. Convenience functions are added to set and get the local and remote addresses of a transport from the transport provider as well as determine the length of a sockaddr. A transport is responsible for setting the xpt_local and xpt_remote addresses in the svc_xprt structure as part of transport creation and xpo_accept processing. This cannot be done in a generic way and in fact varies between TCP, UDP and RDMA. A set of xpo_ functions (e.g. getlocalname, getremotename) could have been added but this would have resulted in additional caching and copying of the addresses around. Note that the xpt_local address should also be set on listening endpoints; for TCP/RDMA this is done as part of endpoint creation. For connected transports like TCP and RDMA, the addresses never change and can be set once and copied into the rqstp structure for each request. For UDP, however, the local and remote addresses may change for each request. In this case, the address information is obtained from the UDP recvmsg info and copied into the rqstp structure from there. A svc_xprt_local_port function was also added that returns the local port given a transport. This is used by svc_create_xprt when returning the port associated with a newly created transport, and later when creating a generic find transport service to check if a service is already listening on a given port. Signed-off-by: Tom Tucker <tom@opengridcomputing.com> Acked-by: Neil Brown <neilb@suse.de> Reviewed-by: Chuck Lever <chuck.lever@oracle.com> Reviewed-by: Greg Banks <gnb@sgi.com> Signed-off-by: J. Bruce Fields <bfields@citi.umich.edu>
2007-12-31 11:08:12 +08:00
svc_xprt_copy_addrs(rqstp, &svsk->sk_xprt);
if (serv->sv_stats)
serv->sv_stats->nettcpcnt++;
return rqstp->rq_arg.len;
error:
if (len != -EAGAIN)
goto err_delete;
dprintk("RPC: TCP recvfrom got EAGAIN\n");
return 0;
err_delete:
printk(KERN_NOTICE "%s: recvfrom returned errno %d\n",
svsk->sk_xprt.xpt_server->sv_name, -len);
set_bit(XPT_CLOSE, &svsk->sk_xprt.xpt_flags);
err_noclose:
return 0; /* record not complete */
}
/*
* Send out data on TCP socket.
*/
static int svc_tcp_sendto(struct svc_rqst *rqstp)
{
struct xdr_buf *xbufp = &rqstp->rq_res;
int sent;
__be32 reclen;
/* Set up the first element of the reply kvec.
* Any other kvecs that may be in use have been taken
* care of by the server implementation itself.
*/
reclen = htonl(0x80000000|((xbufp->len ) - 4));
memcpy(xbufp->head[0].iov_base, &reclen, 4);
sent = svc_sendto(rqstp, &rqstp->rq_res);
if (sent != xbufp->len) {
printk(KERN_NOTICE
"rpc-srv/tcp: %s: %s %d when sending %d bytes "
"- shutting down socket\n",
rqstp->rq_xprt->xpt_server->sv_name,
(sent<0)?"got error":"sent only",
sent, xbufp->len);
set_bit(XPT_CLOSE, &rqstp->rq_xprt->xpt_flags);
svc_xprt_enqueue(rqstp->rq_xprt);
sent = -EAGAIN;
}
return sent;
}
static struct svc_xprt *svc_tcp_create(struct svc_serv *serv,
struct net *net,
struct sockaddr *sa, int salen,
int flags)
{
return svc_create_socket(serv, IPPROTO_TCP, net, sa, salen, flags);
}
static const struct svc_xprt_ops svc_tcp_ops = {
.xpo_create = svc_tcp_create,
.xpo_recvfrom = svc_tcp_recvfrom,
.xpo_sendto = svc_tcp_sendto,
.xpo_release_rqst = svc_release_skb,
.xpo_detach = svc_tcp_sock_detach,
.xpo_free = svc_sock_free,
.xpo_has_wspace = svc_tcp_has_wspace,
.xpo_accept = svc_tcp_accept,
.xpo_secure_port = svc_sock_secure_port,
sunrpc: svc_age_temp_xprts_now should not call setsockopt non-tcp transports This fixes the following panic that can occur with NFSoRDMA. general protection fault: 0000 [#1] SMP Modules linked in: rpcrdma ib_isert iscsi_target_mod ib_iser libiscsi scsi_transport_iscsi ib_srpt target_core_mod ib_srp scsi_transport_srp scsi_tgt ib_ipoib rdma_ucm ib_ucm ib_uverbs ib_umad rdma_cm ib_cm iw_cm mlx5_ib ib_core intel_powerclamp coretemp kvm_intel kvm sg ioatdma ipmi_devintf ipmi_ssif dcdbas iTCO_wdt iTCO_vendor_support pcspkr irqbypass sb_edac shpchp dca crc32_pclmul ghash_clmulni_intel edac_core lpc_ich aesni_intel lrw gf128mul glue_helper ablk_helper mei_me mei ipmi_si cryptd wmi ipmi_msghandler acpi_pad acpi_power_meter nfsd auth_rpcgss nfs_acl lockd grace sunrpc ip_tables xfs libcrc32c sd_mod crc_t10dif crct10dif_generic mgag200 i2c_algo_bit drm_kms_helper syscopyarea sysfillrect sysimgblt ahci fb_sys_fops ttm libahci mlx5_core tg3 crct10dif_pclmul drm crct10dif_common ptp i2c_core libata crc32c_intel pps_core fjes dm_mirror dm_region_hash dm_log dm_mod CPU: 1 PID: 120 Comm: kworker/1:1 Not tainted 3.10.0-514.el7.x86_64 #1 Hardware name: Dell Inc. PowerEdge R320/0KM5PX, BIOS 2.4.2 01/29/2015 Workqueue: events check_lifetime task: ffff88031f506dd0 ti: ffff88031f584000 task.ti: ffff88031f584000 RIP: 0010:[<ffffffff8168d847>] [<ffffffff8168d847>] _raw_spin_lock_bh+0x17/0x50 RSP: 0018:ffff88031f587ba8 EFLAGS: 00010206 RAX: 0000000000020000 RBX: 20041fac02080072 RCX: ffff88031f587fd8 RDX: 0000000000000000 RSI: 0000000000000000 RDI: 20041fac02080072 RBP: ffff88031f587bb0 R08: 0000000000000008 R09: ffffffff8155be77 R10: ffff880322a59b00 R11: ffffea000bf39f00 R12: 20041fac02080072 R13: 000000000000000d R14: ffff8800c4fbd800 R15: 0000000000000001 FS: 0000000000000000(0000) GS:ffff880322a40000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007f3c52d4547e CR3: 00000000019ba000 CR4: 00000000001407e0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000ffff0ff0 DR7: 0000000000000400 Stack: 20041fac02080002 ffff88031f587bd0 ffffffff81557830 20041fac02080002 ffff88031f587c78 ffff88031f587c40 ffffffff8155ae08 000000010157df32 0000000800000001 ffff88031f587c20 ffffffff81096acb ffffffff81aa37d0 Call Trace: [<ffffffff81557830>] lock_sock_nested+0x20/0x50 [<ffffffff8155ae08>] sock_setsockopt+0x78/0x940 [<ffffffff81096acb>] ? lock_timer_base.isra.33+0x2b/0x50 [<ffffffff8155397d>] kernel_setsockopt+0x4d/0x50 [<ffffffffa0386284>] svc_age_temp_xprts_now+0x174/0x1e0 [sunrpc] [<ffffffffa03b681d>] nfsd_inetaddr_event+0x9d/0xd0 [nfsd] [<ffffffff81691ebc>] notifier_call_chain+0x4c/0x70 [<ffffffff810b687d>] __blocking_notifier_call_chain+0x4d/0x70 [<ffffffff810b68b6>] blocking_notifier_call_chain+0x16/0x20 [<ffffffff815e8538>] __inet_del_ifa+0x168/0x2d0 [<ffffffff815e8cef>] check_lifetime+0x25f/0x270 [<ffffffff810a7f3b>] process_one_work+0x17b/0x470 [<ffffffff810a8d76>] worker_thread+0x126/0x410 [<ffffffff810a8c50>] ? rescuer_thread+0x460/0x460 [<ffffffff810b052f>] kthread+0xcf/0xe0 [<ffffffff810b0460>] ? kthread_create_on_node+0x140/0x140 [<ffffffff81696418>] ret_from_fork+0x58/0x90 [<ffffffff810b0460>] ? kthread_create_on_node+0x140/0x140 Code: ca 75 f1 5d c3 0f 1f 80 00 00 00 00 eb d9 66 0f 1f 44 00 00 0f 1f 44 00 00 55 48 89 e5 53 48 89 fb e8 7e 04 a0 ff b8 00 00 02 00 <f0> 0f c1 03 89 c2 c1 ea 10 66 39 c2 75 03 5b 5d c3 83 e2 fe 0f RIP [<ffffffff8168d847>] _raw_spin_lock_bh+0x17/0x50 RSP <ffff88031f587ba8> Signed-off-by: Scott Mayhew <smayhew@redhat.com> Fixes: c3d4879e ("sunrpc: Add a function to close temporary transports immediately") Reviewed-by: Chuck Lever <chuck.lever@oracle.com> Signed-off-by: J. Bruce Fields <bfields@redhat.com>
2016-11-12 02:16:22 +08:00
.xpo_kill_temp_xprt = svc_tcp_kill_temp_xprt,
};
static struct svc_xprt_class svc_tcp_class = {
.xcl_name = "tcp",
.xcl_owner = THIS_MODULE,
.xcl_ops = &svc_tcp_ops,
.xcl_max_payload = RPCSVC_MAXPAYLOAD_TCP,
.xcl_ident = XPRT_TRANSPORT_TCP,
};
void svc_init_xprt_sock(void)
{
svc_reg_xprt_class(&svc_tcp_class);
svc_reg_xprt_class(&svc_udp_class);
}
void svc_cleanup_xprt_sock(void)
{
svc_unreg_xprt_class(&svc_tcp_class);
svc_unreg_xprt_class(&svc_udp_class);
}
static void svc_tcp_init(struct svc_sock *svsk, struct svc_serv *serv)
{
struct sock *sk = svsk->sk_sk;
svc_xprt_init(sock_net(svsk->sk_sock->sk), &svc_tcp_class,
&svsk->sk_xprt, serv);
set_bit(XPT_CACHE_AUTH, &svsk->sk_xprt.xpt_flags);
set_bit(XPT_CONG_CTRL, &svsk->sk_xprt.xpt_flags);
if (sk->sk_state == TCP_LISTEN) {
dprintk("setting up TCP socket for listening\n");
strcpy(svsk->sk_xprt.xpt_remotebuf, "listener");
set_bit(XPT_LISTENER, &svsk->sk_xprt.xpt_flags);
sk->sk_data_ready = svc_tcp_listen_data_ready;
set_bit(XPT_CONN, &svsk->sk_xprt.xpt_flags);
} else {
dprintk("setting up TCP socket for reading\n");
sk->sk_state_change = svc_tcp_state_change;
sk->sk_data_ready = svc_data_ready;
sk->sk_write_space = svc_write_space;
svsk->sk_reclen = 0;
svsk->sk_tcplen = 0;
svsk->sk_datalen = 0;
memset(&svsk->sk_pages[0], 0, sizeof(svsk->sk_pages));
tcp_sk(sk)->nonagle |= TCP_NAGLE_OFF;
set_bit(XPT_DATA, &svsk->sk_xprt.xpt_flags);
SUNRPC: accept() may return sockets that are still in SYN_RECV We're seeing traces of the following form: [10952.396347] svc: transport ffff88042ba4a 000 dequeued, inuse=2 [10952.396351] svc: tcp_accept ffff88042ba4 a000 sock ffff88042a6e4c80 [10952.396362] nfsd: connect from 10.2.6.1, port=187 [10952.396364] svc: svc_setup_socket ffff8800b99bcf00 [10952.396368] setting up TCP socket for reading [10952.396370] svc: svc_setup_socket created ffff8803eb10a000 (inet ffff88042b75b800) [10952.396373] svc: transport ffff8803eb10a000 put into queue [10952.396375] svc: transport ffff88042ba4a000 put into queue [10952.396377] svc: server ffff8800bb0ec000 waiting for data (to = 3600000) [10952.396380] svc: transport ffff8803eb10a000 dequeued, inuse=2 [10952.396381] svc_recv: found XPT_CLOSE [10952.396397] svc: svc_delete_xprt(ffff8803eb10a000) [10952.396398] svc: svc_tcp_sock_detach(ffff8803eb10a000) [10952.396399] svc: svc_sock_detach(ffff8803eb10a000) [10952.396412] svc: svc_sock_free(ffff8803eb10a000) i.e. an immediate close of the socket after initialisation. The culprit appears to be the test at the end of svc_tcp_init, which checks if the newly created socket is in the TCP_ESTABLISHED state, and immediately closes it if not. The evidence appears to suggest that the socket might still be in the SYN_RECV state at this time. The fix is to check for both states, and then to add a check in svc_tcp_state_change() to ensure we don't close the socket when it transitions into TCP_ESTABLISHED. Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com> Signed-off-by: J. Bruce Fields <bfields@redhat.com>
2016-07-26 21:51:19 +08:00
switch (sk->sk_state) {
case TCP_SYN_RECV:
case TCP_ESTABLISHED:
break;
default:
set_bit(XPT_CLOSE, &svsk->sk_xprt.xpt_flags);
SUNRPC: accept() may return sockets that are still in SYN_RECV We're seeing traces of the following form: [10952.396347] svc: transport ffff88042ba4a 000 dequeued, inuse=2 [10952.396351] svc: tcp_accept ffff88042ba4 a000 sock ffff88042a6e4c80 [10952.396362] nfsd: connect from 10.2.6.1, port=187 [10952.396364] svc: svc_setup_socket ffff8800b99bcf00 [10952.396368] setting up TCP socket for reading [10952.396370] svc: svc_setup_socket created ffff8803eb10a000 (inet ffff88042b75b800) [10952.396373] svc: transport ffff8803eb10a000 put into queue [10952.396375] svc: transport ffff88042ba4a000 put into queue [10952.396377] svc: server ffff8800bb0ec000 waiting for data (to = 3600000) [10952.396380] svc: transport ffff8803eb10a000 dequeued, inuse=2 [10952.396381] svc_recv: found XPT_CLOSE [10952.396397] svc: svc_delete_xprt(ffff8803eb10a000) [10952.396398] svc: svc_tcp_sock_detach(ffff8803eb10a000) [10952.396399] svc: svc_sock_detach(ffff8803eb10a000) [10952.396412] svc: svc_sock_free(ffff8803eb10a000) i.e. an immediate close of the socket after initialisation. The culprit appears to be the test at the end of svc_tcp_init, which checks if the newly created socket is in the TCP_ESTABLISHED state, and immediately closes it if not. The evidence appears to suggest that the socket might still be in the SYN_RECV state at this time. The fix is to check for both states, and then to add a check in svc_tcp_state_change() to ensure we don't close the socket when it transitions into TCP_ESTABLISHED. Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com> Signed-off-by: J. Bruce Fields <bfields@redhat.com>
2016-07-26 21:51:19 +08:00
}
}
}
void svc_sock_update_bufs(struct svc_serv *serv)
{
/*
* The number of server threads has changed. Update
* rcvbuf and sndbuf accordingly on all sockets
*/
struct svc_sock *svsk;
spin_lock_bh(&serv->sv_lock);
list_for_each_entry(svsk, &serv->sv_permsocks, sk_xprt.xpt_list)
set_bit(XPT_CHNGBUF, &svsk->sk_xprt.xpt_flags);
spin_unlock_bh(&serv->sv_lock);
}
EXPORT_SYMBOL_GPL(svc_sock_update_bufs);
/*
* 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)
{
struct svc_sock *svsk;
struct sock *inet;
int pmap_register = !(flags & SVC_SOCK_ANONYMOUS);
int err = 0;
dprintk("svc: svc_setup_socket %p\n", sock);
svsk = kzalloc(sizeof(*svsk), GFP_KERNEL);
if (!svsk)
return ERR_PTR(-ENOMEM);
inet = sock->sk;
/* Register socket with portmapper */
if (pmap_register)
err = svc_register(serv, sock_net(sock->sk), inet->sk_family,
inet->sk_protocol,
ntohs(inet_sk(inet)->inet_sport));
if (err < 0) {
kfree(svsk);
return ERR_PTR(err);
}
svsk->sk_sock = sock;
svsk->sk_sk = inet;
svsk->sk_ostate = inet->sk_state_change;
svsk->sk_odata = inet->sk_data_ready;
svsk->sk_owspace = inet->sk_write_space;
net: sunrpc: svcsock: fix NULL-pointer exception While running nfs/connectathon tests kernel NULL-pointer exception has been observed due to races in svcsock.c. Race is appear when kernel accepts connection by kernel_accept (which creates new socket) and start queuing ingress packets to new socket. This happens in ksoftirq context which could run concurrently on a different core while new socket setup is not done yet. The fix is to re-order socket user data init sequence and add write/read barrier calls to be sure that we got proper values for callback pointers before actually calling them. Test results: nfs/connectathon reports '0' failed tests for about 200+ iterations. Crash log: ---<-snip->--- [ 6708.638984] Unable to handle kernel NULL pointer dereference at virtual address 00000000 [ 6708.647093] pgd = ffff0000094e0000 [ 6708.650497] [00000000] *pgd=0000010ffff90003, *pud=0000010ffff90003, *pmd=0000010ffff80003, *pte=0000000000000000 [ 6708.660761] Internal error: Oops: 86000005 [#1] SMP [ 6708.665630] Modules linked in: nfsv3 nfnetlink_queue nfnetlink_log nfnetlink rpcsec_gss_krb5 nfsv4 dns_resolver nfs fscache overlay xt_CONNSECMARK xt_SECMARK xt_conntrack iptable_security ip_tables ah4 xfrm4_mode_transport sctp tun binfmt_misc ext4 jbd2 mbcache loop tcp_diag udp_diag inet_diag rpcrdma ib_isert iscsi_target_mod ib_iser rdma_cm iw_cm libiscsi scsi_transport_iscsi ib_srpt target_core_mod ib_srp scsi_transport_srp ib_ipoib ib_ucm ib_uverbs ib_umad ib_cm ib_core nls_koi8_u nls_cp932 ts_kmp nf_conntrack_ipv4 nf_defrag_ipv4 nf_conntrack vfat fat ghash_ce sha2_ce sha1_ce cavium_rng_vf i2c_thunderx sg thunderx_edac i2c_smbus edac_core cavium_rng nfsd auth_rpcgss nfs_acl lockd grace sunrpc xfs libcrc32c nicvf nicpf ast i2c_algo_bit drm_kms_helper syscopyarea sysfillrect sysimgblt fb_sys_fops [ 6708.736446] ttm drm i2c_core thunder_bgx thunder_xcv mdio_thunder mdio_cavium dm_mirror dm_region_hash dm_log dm_mod [last unloaded: stap_3c300909c5b3f46dcacd49aab3334af_87021] [ 6708.752275] CPU: 84 PID: 0 Comm: swapper/84 Tainted: G W OE 4.11.0-4.el7.aarch64 #1 [ 6708.760787] Hardware name: www.cavium.com CRB-2S/CRB-2S, BIOS 0.3 Mar 13 2017 [ 6708.767910] task: ffff810006842e80 task.stack: ffff81000689c000 [ 6708.773822] PC is at 0x0 [ 6708.776739] LR is at svc_data_ready+0x38/0x88 [sunrpc] [ 6708.781866] pc : [<0000000000000000>] lr : [<ffff0000029d7378>] pstate: 60000145 [ 6708.789248] sp : ffff810ffbad3900 [ 6708.792551] x29: ffff810ffbad3900 x28: ffff000008c73d58 [ 6708.797853] x27: 0000000000000000 x26: ffff81000bbe1e00 [ 6708.803156] x25: 0000000000000020 x24: ffff800f7410bf28 [ 6708.808458] x23: ffff000008c63000 x22: ffff000008c63000 [ 6708.813760] x21: ffff800f7410bf28 x20: ffff81000bbe1e00 [ 6708.819063] x19: ffff810012412400 x18: 00000000d82a9df2 [ 6708.824365] x17: 0000000000000000 x16: 0000000000000000 [ 6708.829667] x15: 0000000000000000 x14: 0000000000000001 [ 6708.834969] x13: 0000000000000000 x12: 722e736f622e676e [ 6708.840271] x11: 00000000f814dd99 x10: 0000000000000000 [ 6708.845573] x9 : 7374687225000000 x8 : 0000000000000000 [ 6708.850875] x7 : 0000000000000000 x6 : 0000000000000000 [ 6708.856177] x5 : 0000000000000028 x4 : 0000000000000000 [ 6708.861479] x3 : 0000000000000000 x2 : 00000000e5000000 [ 6708.866781] x1 : 0000000000000000 x0 : ffff81000bbe1e00 [ 6708.872084] [ 6708.873565] Process swapper/84 (pid: 0, stack limit = 0xffff81000689c000) [ 6708.880341] Stack: (0xffff810ffbad3900 to 0xffff8100068a0000) [ 6708.886075] Call trace: [ 6708.888513] Exception stack(0xffff810ffbad3710 to 0xffff810ffbad3840) [ 6708.894942] 3700: ffff810012412400 0001000000000000 [ 6708.902759] 3720: ffff810ffbad3900 0000000000000000 0000000060000145 ffff800f79300000 [ 6708.910577] 3740: ffff000009274d00 00000000000003ea 0000000000000015 ffff000008c63000 [ 6708.918395] 3760: ffff810ffbad3830 ffff800f79300000 000000000000004d 0000000000000000 [ 6708.926212] 3780: ffff810ffbad3890 ffff0000080f88dc ffff800f79300000 000000000000004d [ 6708.934030] 37a0: ffff800f7930093c ffff000008c63000 0000000000000000 0000000000000140 [ 6708.941848] 37c0: ffff000008c2c000 0000000000040b00 ffff81000bbe1e00 0000000000000000 [ 6708.949665] 37e0: 00000000e5000000 0000000000000000 0000000000000000 0000000000000028 [ 6708.957483] 3800: 0000000000000000 0000000000000000 0000000000000000 7374687225000000 [ 6708.965300] 3820: 0000000000000000 00000000f814dd99 722e736f622e676e 0000000000000000 [ 6708.973117] [< (null)>] (null) [ 6708.977824] [<ffff0000086f9fa4>] tcp_data_queue+0x754/0xc5c [ 6708.983386] [<ffff0000086fa64c>] tcp_rcv_established+0x1a0/0x67c [ 6708.989384] [<ffff000008704120>] tcp_v4_do_rcv+0x15c/0x22c [ 6708.994858] [<ffff000008707418>] tcp_v4_rcv+0xaf0/0xb58 [ 6709.000077] [<ffff0000086df784>] ip_local_deliver_finish+0x10c/0x254 [ 6709.006419] [<ffff0000086dfea4>] ip_local_deliver+0xf0/0xfc [ 6709.011980] [<ffff0000086dfad4>] ip_rcv_finish+0x208/0x3a4 [ 6709.017454] [<ffff0000086e018c>] ip_rcv+0x2dc/0x3c8 [ 6709.022328] [<ffff000008692fc8>] __netif_receive_skb_core+0x2f8/0xa0c [ 6709.028758] [<ffff000008696068>] __netif_receive_skb+0x38/0x84 [ 6709.034580] [<ffff00000869611c>] netif_receive_skb_internal+0x68/0xdc [ 6709.041010] [<ffff000008696bc0>] napi_gro_receive+0xcc/0x1a8 [ 6709.046690] [<ffff0000014b0fc4>] nicvf_cq_intr_handler+0x59c/0x730 [nicvf] [ 6709.053559] [<ffff0000014b1380>] nicvf_poll+0x38/0xb8 [nicvf] [ 6709.059295] [<ffff000008697a6c>] net_rx_action+0x2f8/0x464 [ 6709.064771] [<ffff000008081824>] __do_softirq+0x11c/0x308 [ 6709.070164] [<ffff0000080d14e4>] irq_exit+0x12c/0x174 [ 6709.075206] [<ffff00000813101c>] __handle_domain_irq+0x78/0xc4 [ 6709.081027] [<ffff000008081608>] gic_handle_irq+0x94/0x190 [ 6709.086501] Exception stack(0xffff81000689fdf0 to 0xffff81000689ff20) [ 6709.092929] fde0: 0000810ff2ec0000 ffff000008c10000 [ 6709.100747] fe00: ffff000008c70ef4 0000000000000001 0000000000000000 ffff810ffbad9b18 [ 6709.108565] fe20: ffff810ffbad9c70 ffff8100169d3800 ffff810006843ab0 ffff81000689fe80 [ 6709.116382] fe40: 0000000000000bd0 0000ffffdf979cd0 183f5913da192500 0000ffff8a254ce4 [ 6709.124200] fe60: 0000ffff8a254b78 0000aaab10339808 0000000000000000 0000ffff8a0c2a50 [ 6709.132018] fe80: 0000ffffdf979b10 ffff000008d6d450 ffff000008c10000 ffff000008d6d000 [ 6709.139836] fea0: 0000000000000054 ffff000008cd3dbc 0000000000000000 0000000000000000 [ 6709.147653] fec0: 0000000000000000 0000000000000000 0000000000000000 ffff81000689ff20 [ 6709.155471] fee0: ffff000008085240 ffff81000689ff20 ffff000008085244 0000000060000145 [ 6709.163289] ff00: ffff81000689ff10 ffff00000813f1e4 ffffffffffffffff ffff00000813f238 [ 6709.171107] [<ffff000008082eb4>] el1_irq+0xb4/0x140 [ 6709.175976] [<ffff000008085244>] arch_cpu_idle+0x44/0x11c [ 6709.181368] [<ffff0000087bf3b8>] default_idle_call+0x20/0x30 [ 6709.187020] [<ffff000008116d50>] do_idle+0x158/0x1e4 [ 6709.191973] [<ffff000008116ff4>] cpu_startup_entry+0x2c/0x30 [ 6709.197624] [<ffff00000808e7cc>] secondary_start_kernel+0x13c/0x160 [ 6709.203878] [<0000000001bc71c4>] 0x1bc71c4 [ 6709.207967] Code: bad PC value [ 6709.211061] SMP: stopping secondary CPUs [ 6709.218830] Starting crashdump kernel... [ 6709.222749] Bye! ---<-snip>--- Signed-off-by: Vadim Lomovtsev <vlomovts@redhat.com> Reviewed-by: Jeff Layton <jlayton@redhat.com> Cc: stable@vger.kernel.org Signed-off-by: J. Bruce Fields <bfields@redhat.com>
2017-08-21 19:23:07 +08:00
/*
* This barrier is necessary in order to prevent race condition
* with svc_data_ready(), svc_listen_data_ready() and others
* when calling callbacks above.
*/
wmb();
inet->sk_user_data = svsk;
/* Initialize the socket */
if (sock->type == SOCK_DGRAM)
svc_udp_init(svsk, serv);
else
svc_tcp_init(svsk, serv);
dprintk("svc: svc_setup_socket created %p (inet %p), "
"listen %d close %d\n",
svsk, svsk->sk_sk,
test_bit(XPT_LISTENER, &svsk->sk_xprt.xpt_flags),
test_bit(XPT_CLOSE, &svsk->sk_xprt.xpt_flags));
return svsk;
}
bool svc_alien_sock(struct net *net, int fd)
{
int err;
struct socket *sock = sockfd_lookup(fd, &err);
bool ret = false;
if (!sock)
goto out;
if (sock_net(sock->sk) != net)
ret = true;
sockfd_put(sock);
out:
return ret;
}
EXPORT_SYMBOL_GPL(svc_alien_sock);
/**
* svc_addsock - add a listener socket to an RPC service
* @serv: pointer to RPC service to which to add a new listener
* @fd: file descriptor of the new listener
* @name_return: pointer to buffer to fill in with name of listener
* @len: size of the buffer
*
* 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, const int fd, char *name_return,
const size_t len)
{
int err = 0;
struct socket *so = sockfd_lookup(fd, &err);
struct svc_sock *svsk = NULL;
struct sockaddr_storage addr;
struct sockaddr *sin = (struct sockaddr *)&addr;
int salen;
if (!so)
return err;
err = -EAFNOSUPPORT;
if ((so->sk->sk_family != PF_INET) && (so->sk->sk_family != PF_INET6))
goto out;
err = -EPROTONOSUPPORT;
if (so->sk->sk_protocol != IPPROTO_TCP &&
so->sk->sk_protocol != IPPROTO_UDP)
goto out;
err = -EISCONN;
if (so->state > SS_UNCONNECTED)
goto out;
err = -ENOENT;
if (!try_module_get(THIS_MODULE))
goto out;
svsk = svc_setup_socket(serv, so, SVC_SOCK_DEFAULTS);
if (IS_ERR(svsk)) {
module_put(THIS_MODULE);
err = PTR_ERR(svsk);
goto out;
}
net: make getname() functions return length rather than use int* parameter Changes since v1: Added changes in these files: drivers/infiniband/hw/usnic/usnic_transport.c drivers/staging/lustre/lnet/lnet/lib-socket.c drivers/target/iscsi/iscsi_target_login.c drivers/vhost/net.c fs/dlm/lowcomms.c fs/ocfs2/cluster/tcp.c security/tomoyo/network.c Before: All these functions either return a negative error indicator, or store length of sockaddr into "int *socklen" parameter and return zero on success. "int *socklen" parameter is awkward. For example, if caller does not care, it still needs to provide on-stack storage for the value it does not need. None of the many FOO_getname() functions of various protocols ever used old value of *socklen. They always just overwrite it. This change drops this parameter, and makes all these functions, on success, return length of sockaddr. It's always >= 0 and can be differentiated from an error. Tests in callers are changed from "if (err)" to "if (err < 0)", where needed. rpc_sockname() lost "int buflen" parameter, since its only use was to be passed to kernel_getsockname() as &buflen and subsequently not used in any way. Userspace API is not changed. text data bss dec hex filename 30108430 2633624 873672 33615726 200ef6e vmlinux.before.o 30108109 2633612 873672 33615393 200ee21 vmlinux.o Signed-off-by: Denys Vlasenko <dvlasenk@redhat.com> CC: David S. Miller <davem@davemloft.net> CC: linux-kernel@vger.kernel.org CC: netdev@vger.kernel.org CC: linux-bluetooth@vger.kernel.org CC: linux-decnet-user@lists.sourceforge.net CC: linux-wireless@vger.kernel.org CC: linux-rdma@vger.kernel.org CC: linux-sctp@vger.kernel.org CC: linux-nfs@vger.kernel.org CC: linux-x25@vger.kernel.org Signed-off-by: David S. Miller <davem@davemloft.net>
2018-02-13 03:00:20 +08:00
salen = kernel_getsockname(svsk->sk_sock, sin);
if (salen >= 0)
svc_xprt_set_local(&svsk->sk_xprt, sin, salen);
svc_add_new_perm_xprt(serv, &svsk->sk_xprt);
return svc_one_sock_name(svsk, name_return, len);
out:
sockfd_put(so);
return err;
}
EXPORT_SYMBOL_GPL(svc_addsock);
/*
* 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)
{
struct svc_sock *svsk;
struct socket *sock;
int error;
int type;
svc: Move the sockaddr information to svc_xprt This patch moves the transport sockaddr to the svc_xprt structure. Convenience functions are added to set and get the local and remote addresses of a transport from the transport provider as well as determine the length of a sockaddr. A transport is responsible for setting the xpt_local and xpt_remote addresses in the svc_xprt structure as part of transport creation and xpo_accept processing. This cannot be done in a generic way and in fact varies between TCP, UDP and RDMA. A set of xpo_ functions (e.g. getlocalname, getremotename) could have been added but this would have resulted in additional caching and copying of the addresses around. Note that the xpt_local address should also be set on listening endpoints; for TCP/RDMA this is done as part of endpoint creation. For connected transports like TCP and RDMA, the addresses never change and can be set once and copied into the rqstp structure for each request. For UDP, however, the local and remote addresses may change for each request. In this case, the address information is obtained from the UDP recvmsg info and copied into the rqstp structure from there. A svc_xprt_local_port function was also added that returns the local port given a transport. This is used by svc_create_xprt when returning the port associated with a newly created transport, and later when creating a generic find transport service to check if a service is already listening on a given port. Signed-off-by: Tom Tucker <tom@opengridcomputing.com> Acked-by: Neil Brown <neilb@suse.de> Reviewed-by: Chuck Lever <chuck.lever@oracle.com> Reviewed-by: Greg Banks <gnb@sgi.com> Signed-off-by: J. Bruce Fields <bfields@citi.umich.edu>
2007-12-31 11:08:12 +08:00
struct sockaddr_storage addr;
struct sockaddr *newsin = (struct sockaddr *)&addr;
int newlen;
int family;
int val;
RPC_IFDEBUG(char buf[RPC_MAX_ADDRBUFLEN]);
dprintk("svc: svc_create_socket(%s, %d, %s)\n",
serv->sv_program->pg_name, protocol,
__svc_print_addr(sin, buf, sizeof(buf)));
if (protocol != IPPROTO_UDP && protocol != IPPROTO_TCP) {
printk(KERN_WARNING "svc: only UDP and TCP "
"sockets supported\n");
return ERR_PTR(-EINVAL);
}
type = (protocol == IPPROTO_UDP)? SOCK_DGRAM : SOCK_STREAM;
switch (sin->sa_family) {
case AF_INET6:
family = PF_INET6;
break;
case AF_INET:
family = PF_INET;
break;
default:
return ERR_PTR(-EINVAL);
}
error = __sock_create(net, family, type, protocol, &sock, 1);
if (error < 0)
return ERR_PTR(error);
svc_reclassify_socket(sock);
/*
* If this is an PF_INET6 listener, we want to avoid
* getting requests from IPv4 remotes. Those should
* be shunted to a PF_INET listener via rpcbind.
*/
val = 1;
if (family == PF_INET6)
kernel_setsockopt(sock, SOL_IPV6, IPV6_V6ONLY,
(char *)&val, sizeof(val));
if (type == SOCK_STREAM)
sock->sk->sk_reuse = SK_CAN_REUSE; /* allow address reuse */
error = kernel_bind(sock, sin, len);
if (error < 0)
goto bummer;
net: make getname() functions return length rather than use int* parameter Changes since v1: Added changes in these files: drivers/infiniband/hw/usnic/usnic_transport.c drivers/staging/lustre/lnet/lnet/lib-socket.c drivers/target/iscsi/iscsi_target_login.c drivers/vhost/net.c fs/dlm/lowcomms.c fs/ocfs2/cluster/tcp.c security/tomoyo/network.c Before: All these functions either return a negative error indicator, or store length of sockaddr into "int *socklen" parameter and return zero on success. "int *socklen" parameter is awkward. For example, if caller does not care, it still needs to provide on-stack storage for the value it does not need. None of the many FOO_getname() functions of various protocols ever used old value of *socklen. They always just overwrite it. This change drops this parameter, and makes all these functions, on success, return length of sockaddr. It's always >= 0 and can be differentiated from an error. Tests in callers are changed from "if (err)" to "if (err < 0)", where needed. rpc_sockname() lost "int buflen" parameter, since its only use was to be passed to kernel_getsockname() as &buflen and subsequently not used in any way. Userspace API is not changed. text data bss dec hex filename 30108430 2633624 873672 33615726 200ef6e vmlinux.before.o 30108109 2633612 873672 33615393 200ee21 vmlinux.o Signed-off-by: Denys Vlasenko <dvlasenk@redhat.com> CC: David S. Miller <davem@davemloft.net> CC: linux-kernel@vger.kernel.org CC: netdev@vger.kernel.org CC: linux-bluetooth@vger.kernel.org CC: linux-decnet-user@lists.sourceforge.net CC: linux-wireless@vger.kernel.org CC: linux-rdma@vger.kernel.org CC: linux-sctp@vger.kernel.org CC: linux-nfs@vger.kernel.org CC: linux-x25@vger.kernel.org Signed-off-by: David S. Miller <davem@davemloft.net>
2018-02-13 03:00:20 +08:00
error = kernel_getsockname(sock, newsin);
svc: Move the sockaddr information to svc_xprt This patch moves the transport sockaddr to the svc_xprt structure. Convenience functions are added to set and get the local and remote addresses of a transport from the transport provider as well as determine the length of a sockaddr. A transport is responsible for setting the xpt_local and xpt_remote addresses in the svc_xprt structure as part of transport creation and xpo_accept processing. This cannot be done in a generic way and in fact varies between TCP, UDP and RDMA. A set of xpo_ functions (e.g. getlocalname, getremotename) could have been added but this would have resulted in additional caching and copying of the addresses around. Note that the xpt_local address should also be set on listening endpoints; for TCP/RDMA this is done as part of endpoint creation. For connected transports like TCP and RDMA, the addresses never change and can be set once and copied into the rqstp structure for each request. For UDP, however, the local and remote addresses may change for each request. In this case, the address information is obtained from the UDP recvmsg info and copied into the rqstp structure from there. A svc_xprt_local_port function was also added that returns the local port given a transport. This is used by svc_create_xprt when returning the port associated with a newly created transport, and later when creating a generic find transport service to check if a service is already listening on a given port. Signed-off-by: Tom Tucker <tom@opengridcomputing.com> Acked-by: Neil Brown <neilb@suse.de> Reviewed-by: Chuck Lever <chuck.lever@oracle.com> Reviewed-by: Greg Banks <gnb@sgi.com> Signed-off-by: J. Bruce Fields <bfields@citi.umich.edu>
2007-12-31 11:08:12 +08:00
if (error < 0)
goto bummer;
net: make getname() functions return length rather than use int* parameter Changes since v1: Added changes in these files: drivers/infiniband/hw/usnic/usnic_transport.c drivers/staging/lustre/lnet/lnet/lib-socket.c drivers/target/iscsi/iscsi_target_login.c drivers/vhost/net.c fs/dlm/lowcomms.c fs/ocfs2/cluster/tcp.c security/tomoyo/network.c Before: All these functions either return a negative error indicator, or store length of sockaddr into "int *socklen" parameter and return zero on success. "int *socklen" parameter is awkward. For example, if caller does not care, it still needs to provide on-stack storage for the value it does not need. None of the many FOO_getname() functions of various protocols ever used old value of *socklen. They always just overwrite it. This change drops this parameter, and makes all these functions, on success, return length of sockaddr. It's always >= 0 and can be differentiated from an error. Tests in callers are changed from "if (err)" to "if (err < 0)", where needed. rpc_sockname() lost "int buflen" parameter, since its only use was to be passed to kernel_getsockname() as &buflen and subsequently not used in any way. Userspace API is not changed. text data bss dec hex filename 30108430 2633624 873672 33615726 200ef6e vmlinux.before.o 30108109 2633612 873672 33615393 200ee21 vmlinux.o Signed-off-by: Denys Vlasenko <dvlasenk@redhat.com> CC: David S. Miller <davem@davemloft.net> CC: linux-kernel@vger.kernel.org CC: netdev@vger.kernel.org CC: linux-bluetooth@vger.kernel.org CC: linux-decnet-user@lists.sourceforge.net CC: linux-wireless@vger.kernel.org CC: linux-rdma@vger.kernel.org CC: linux-sctp@vger.kernel.org CC: linux-nfs@vger.kernel.org CC: linux-x25@vger.kernel.org Signed-off-by: David S. Miller <davem@davemloft.net>
2018-02-13 03:00:20 +08:00
newlen = error;
svc: Move the sockaddr information to svc_xprt This patch moves the transport sockaddr to the svc_xprt structure. Convenience functions are added to set and get the local and remote addresses of a transport from the transport provider as well as determine the length of a sockaddr. A transport is responsible for setting the xpt_local and xpt_remote addresses in the svc_xprt structure as part of transport creation and xpo_accept processing. This cannot be done in a generic way and in fact varies between TCP, UDP and RDMA. A set of xpo_ functions (e.g. getlocalname, getremotename) could have been added but this would have resulted in additional caching and copying of the addresses around. Note that the xpt_local address should also be set on listening endpoints; for TCP/RDMA this is done as part of endpoint creation. For connected transports like TCP and RDMA, the addresses never change and can be set once and copied into the rqstp structure for each request. For UDP, however, the local and remote addresses may change for each request. In this case, the address information is obtained from the UDP recvmsg info and copied into the rqstp structure from there. A svc_xprt_local_port function was also added that returns the local port given a transport. This is used by svc_create_xprt when returning the port associated with a newly created transport, and later when creating a generic find transport service to check if a service is already listening on a given port. Signed-off-by: Tom Tucker <tom@opengridcomputing.com> Acked-by: Neil Brown <neilb@suse.de> Reviewed-by: Chuck Lever <chuck.lever@oracle.com> Reviewed-by: Greg Banks <gnb@sgi.com> Signed-off-by: J. Bruce Fields <bfields@citi.umich.edu>
2007-12-31 11:08:12 +08:00
if (protocol == IPPROTO_TCP) {
if ((error = kernel_listen(sock, 64)) < 0)
goto bummer;
}
svsk = svc_setup_socket(serv, sock, flags);
if (IS_ERR(svsk)) {
error = PTR_ERR(svsk);
goto bummer;
}
svc_xprt_set_local(&svsk->sk_xprt, newsin, newlen);
return (struct svc_xprt *)svsk;
bummer:
dprintk("svc: svc_create_socket error = %d\n", -error);
sock_release(sock);
return ERR_PTR(error);
}
/*
* Detach the svc_sock from the socket so that no
* more callbacks occur.
*/
static void svc_sock_detach(struct svc_xprt *xprt)
{
struct svc_sock *svsk = container_of(xprt, struct svc_sock, sk_xprt);
struct sock *sk = svsk->sk_sk;
dprintk("svc: svc_sock_detach(%p)\n", svsk);
/* put back the old socket callbacks */
lock_sock(sk);
sk->sk_state_change = svsk->sk_ostate;
sk->sk_data_ready = svsk->sk_odata;
sk->sk_write_space = svsk->sk_owspace;
sk->sk_user_data = NULL;
release_sock(sk);
}
/*
* Disconnect the socket, and reset the callbacks
*/
static void svc_tcp_sock_detach(struct svc_xprt *xprt)
{
struct svc_sock *svsk = container_of(xprt, struct svc_sock, sk_xprt);
dprintk("svc: svc_tcp_sock_detach(%p)\n", svsk);
svc_sock_detach(xprt);
if (!test_bit(XPT_LISTENER, &xprt->xpt_flags)) {
svc_tcp_clear_pages(svsk);
kernel_sock_shutdown(svsk->sk_sock, SHUT_RDWR);
}
}
/*
* Free the svc_sock's socket resources and the svc_sock itself.
*/
static void svc_sock_free(struct svc_xprt *xprt)
{
struct svc_sock *svsk = container_of(xprt, struct svc_sock, sk_xprt);
dprintk("svc: svc_sock_free(%p)\n", svsk);
if (svsk->sk_sock->file)
sockfd_put(svsk->sk_sock);
else
sock_release(svsk->sk_sock);
kfree(svsk);
}