remove most callers of kernel_setsockopt v3
Subsystems (24)
Christoph Hellwig
maintainerHi Dave,
this series removes most callers of the kernel_setsockopt functions, and instead switches their users to small functions that implement setting a sockopt directly using a normal kernel function call with type safety and all the other benefits of not having a function call.
In some cases these functions seem pretty heavy handed as they do a lock_sock even for just setting a single variable, but this mirrors the real setsockopt implementation unlike a few drivers that just set set the fields directly.
Changes since v2:
- drop the separately merged kernel_getopt_removal
- drop the sctp patches, as there is conflicting cleanup going on
- add an additional ACK for the rxrpc changes
Changes since v1:
- use ->getname for sctp sockets in dlm
- add a new ->bind_add struct proto method for dlm/sctp
- switch the ipv6 and remaining sctp helpers to inline function so that the ipv6 and sctp modules are not pulled in by any module that could potentially use ipv6 or sctp connections
- remove arguments to various sock_* helpers that are always used with the same constant arguments
Christoph Hellwig
maintainerPATCH 1/28 net: add sock_set_reuseaddr
Add a helper to directly set the SO_REUSEADDR sockopt from kernel space without going through a fake uaccess.
For this the iscsi target now has to formally depend on inet to avoid a mostly theoretical compile failure. For actual operation it already did depend on having ipv4 or ipv6 support.
--- drivers/infiniband/sw/siw/siw_cm.c | 18 +++++------------- drivers/nvme/target/tcp.c | 8 +------- drivers/target/iscsi/Kconfig | 2 +- drivers/target/iscsi/iscsi_target_login.c | 9 +-------- fs/dlm/lowcomms.c | 6 +----- include/net/sock.h | 2 ++ net/core/sock.c | 8 ++++++++ 7 files changed, 19 insertions(+), 34 deletions(-)
drivers/infiniband/sw/siw/siw_cm.c +5 -13
@@ -1312,17 +1312,14 @@ static void siw_cm_llp_state_change(struct sock *sk)static int kernel_bindconnect (struct socket *s,struct sockaddr *laddr,struct sockaddr *raddr) { -int rv, flags =0 , s_val =1 ; +int rv, flags =0 ;size_t size = laddr->sa_family ==AF_INET ?sizeof (struct sockaddr_in ) :sizeof (struct sockaddr_in6 );/* * Make address available again asap. */ - rv =kernel_setsockopt (s,SOL_SOCKET ,SO_REUSEADDR , (char *)&s_val, -sizeof (s_val)); -if (rv <0 ) -return rv; +sock_set_reuseaddr (s->sk); rv = s->ops->bind (s, laddr, size);if (rv <0 )
@@ -1781,7 +1778,7 @@ int siw_create_listen(struct iw_cm_id *id, int backlog)struct siw_cep *cep =NULL ;struct siw_device *sdev =to_siw_dev (id->device);int addr_family = id->local_addr.ss_family; -int rv =0 , s_val; +int rv =0 ;if (addr_family !=AF_INET && addr_family !=AF_INET6 )return -EAFNOSUPPORT ;
@@ -1793,13 +1790,8 @@ int siw_create_listen(struct iw_cm_id *id, int backlog)/* * Allow binding local port when still in TIME_WAIT from last close. */ - s_val =1 ; - rv =kernel_setsockopt (s,SOL_SOCKET ,SO_REUSEADDR , (char *)&s_val, -sizeof (s_val)); -if (rv) { -siw_dbg (id->device,"setsockopt error: %d\n" , rv); - goto error; - } +sock_set_reuseaddr (s->sk); +if (addr_family ==AF_INET ) {struct sockaddr_in *laddr = &to_sockaddr_in (id->local_addr);
drivers/nvme/target/tcp.c +1 -7
@@ -1632,6 +1632,7 @@ static int nvmet_tcp_add_port(struct nvmet_port *nport) port->sock->sk->sk_user_data = port; port->data_ready = port->sock->sk->sk_data_ready; port->sock->sk->sk_data_ready = nvmet_tcp_listen_data_ready; +sock_set_reuseaddr (port->sock->sk); opt =1 ; ret = kernel_setsockopt(port->sock, IPPROTO_TCP,
@@ -1641,13 +1642,6 @@ static int nvmet_tcp_add_port(struct nvmet_port *nport) goto err_sock; } - ret =kernel_setsockopt (port->sock,SOL_SOCKET ,SO_REUSEADDR , - (char *)&opt,sizeof (opt)); -if (ret) { -pr_err ("failed to set SO_REUSEADDR sock opt %d\n" , ret); - goto err_sock; - } -if (so_priority >0 ) { ret =kernel_setsockopt (port->sock,SOL_SOCKET ,SO_PRIORITY , (char *)&so_priority,sizeof (so_priority));
drivers/target/iscsi/Kconfig +1 -1
@@ -1,7 +1,7 @@ # SPDX-License-Identifier: GPL-2.0-only config ISCSI_TARGET tristate "Linux-iSCSI.org iSCSI Target Mode Stack" - depends on NET + depends on INET select CRYPTO select CRYPTO_CRC32C select CRYPTO_CRC32C_INTEL if X86
drivers/target/iscsi/iscsi_target_login.c +1 -8
@@ -909,14 +909,7 @@ int iscsit_setup_np( } } -/* FIXME: Someone please explain why this is endian-safe */ - ret =kernel_setsockopt (sock,SOL_SOCKET ,SO_REUSEADDR , - (char *)&opt,sizeof (opt)); -if (ret <0 ) { -pr_err ("kernel_setsockopt() for SO_REUSEADDR" -" failed\n" ); - goto fail; - } +sock_set_reuseaddr (sock->sk); ret =kernel_setsockopt (sock,IPPROTO_IP ,IP_FREEBIND , (char *)&opt,sizeof (opt));
fs/dlm/lowcomms.c +1 -5
@@ -1244,12 +1244,8 @@ static struct socket *tcp_create_listen_sock(struct connection *con,kernel_setsockopt (sock,SOL_TCP ,TCP_NODELAY , (char *)&one,sizeof (one)); - result =kernel_setsockopt (sock,SOL_SOCKET ,SO_REUSEADDR , - (char *)&one,sizeof (one)); +sock_set_reuseaddr (sock->sk); -if (result <0 ) { -log_print ("Failed to set SO_REUSEADDR on socket: %d" , result); - }write_lock_bh (&sock->sk->sk_callback_lock); sock->sk->sk_user_data = con;save_listen_callbacks (sock);
include/net/sock.h +2 -0
@@ -2688,4 +2688,6 @@ static inline bool sk_dev_equal_l3scope(struct sock *sk, int dif)void sock_def_readable (struct sock *sk); +void sock_set_reuseaddr (struct sock *sk); +#endif /* _SOCK_H */
net/core/sock.c +8 -0
@@ -712,6 +712,14 @@ bool sk_mc_loop(struct sock *sk) }EXPORT_SYMBOL (sk_mc_loop); +void sock_set_reuseaddr (struct sock *sk) +{ +lock_sock (sk); + sk->sk_reuse =SK_CAN_REUSE ; +release_sock (sk); +} +EXPORT_SYMBOL (sock_set_reuseaddr); +/* * This is meant for all protocols to use and covers goings on * at the socket level. Everything here is generic.
Signature · 1 line
2.26.2
Christoph Hellwig
maintainerPATCH 2/28 net: add sock_no_linger
In reply to Christoph HellwigAdd a helper to directly set the SO_LINGER sockopt from kernel space with onoff set to true and a linger time of 0 without going through a fake uaccess.
--- drivers/nvme/host/tcp.c | 9 +-------- drivers/nvme/target/tcp.c | 6 +----- include/net/sock.h | 1 + net/core/sock.c | 9 +++++++++ net/rds/tcp.h | 1 - net/rds/tcp_connect.c | 2 +- net/rds/tcp_listen.c | 13 +------------ net/sunrpc/svcsock.c | 12 ++---------- 8 files changed, 16 insertions(+), 37 deletions(-)
drivers/nvme/host/tcp.c +1 -8
@@ -1313,7 +1313,6 @@ static int nvme_tcp_alloc_queue(struct nvme_ctrl *nctrl, {struct nvme_tcp_ctrl *ctrl =to_tcp_ctrl (nctrl);struct nvme_tcp_queue *queue = &ctrl->queues[qid]; -struct linger sol = { .l_onoff =1 , .l_linger =0 };int ret, opt, rcv_pdu_size; queue->ctrl = ctrl;
@@ -1361,13 +1360,7 @@ static int nvme_tcp_alloc_queue(struct nvme_ctrl *nctrl,* close. This is done to prevent stale data from being sent should * the network connection be restored before TCP times out. */ - ret =kernel_setsockopt (queue->sock,SOL_SOCKET ,SO_LINGER , - (char *)&sol,sizeof (sol)); -if (ret) { -dev_err (nctrl->device, -"failed to set SO_LINGER sock opt %d\n" , ret); - goto err_sock; - } +sock_no_linger (queue->sock->sk);if (so_priority >0 ) { ret = kernel_setsockopt(queue->sock, SOL_SOCKET, SO_PRIORITY,
drivers/nvme/target/tcp.c +1 -5
@@ -1429,7 +1429,6 @@ static int nvmet_tcp_set_queue_sock(struct nvmet_tcp_queue *queue) {struct socket *sock = queue->sock;struct inet_sock *inet =inet_sk (sock->sk); -struct linger sol = { .l_onoff =1 , .l_linger =0 };int ret; ret = kernel_getsockname(sock,
@@ -1447,10 +1446,7 @@ static int nvmet_tcp_set_queue_sock(struct nvmet_tcp_queue *queue)* close. This is done to prevent stale data from being sent should * the network connection be restored before TCP times out. */ - ret =kernel_setsockopt (sock,SOL_SOCKET ,SO_LINGER , - (char *)&sol,sizeof (sol)); -if (ret) -return ret; +sock_no_linger (sock->sk);if (so_priority >0 ) { ret = kernel_setsockopt(sock, SOL_SOCKET, SO_PRIORITY,
include/net/sock.h +1 -0
@@ -2688,6 +2688,7 @@ static inline bool sk_dev_equal_l3scope(struct sock *sk, int dif)void sock_def_readable (struct sock *sk); +void sock_no_linger (struct sock *sk);void sock_set_reuseaddr (struct sock *sk);#endif /* _SOCK_H */
net/core/sock.c +9 -0
@@ -720,6 +720,15 @@ void sock_set_reuseaddr(struct sock *sk) }EXPORT_SYMBOL (sock_set_reuseaddr); +void sock_no_linger (struct sock *sk) +{ +lock_sock (sk); + sk->sk_lingertime =0 ; +sock_set_flag (sk,SOCK_LINGER ); +release_sock (sk); +} +EXPORT_SYMBOL (sock_no_linger); +/* * This is meant for all protocols to use and covers goings on * at the socket level. Everything here is generic.
net/rds/tcp.h +0 -1
@@ -73,7 +73,6 @@ void rds_tcp_listen_data_ready(struct sock *sk);int rds_tcp_accept_one (struct socket *sock);int rds_tcp_keepalive (struct socket *sock);void *rds_tcp_listen_sock_def_readable (struct net *net); -void rds_tcp_set_linger (struct socket *sock);/* tcp_recv.c */ int rds_tcp_recv_init (void );
net/rds/tcp_connect.c +1 -1
@@ -207,7 +207,7 @@ void rds_tcp_conn_path_shutdown(struct rds_conn_path *cp)if (sock) {if (rds_destroy_pending (cp->cp_conn)) -rds_tcp_set_linger (sock); +sock_no_linger (sock->sk); sock->ops->shutdown (sock,RCV_SHUTDOWN |SEND_SHUTDOWN );lock_sock (sock->sk);rds_tcp_restore_callbacks (sock, tc);/* tc->tc_sock = NULL */
net/rds/tcp_listen.c +1 -12
@@ -111,17 +111,6 @@ struct rds_tcp_connection *rds_tcp_accept_one_path(struct rds_connection *conn)return NULL ; } -void rds_tcp_set_linger (struct socket *sock) -{ -struct linger no_linger = { - .l_onoff =1 , - .l_linger =0 , - }; - -kernel_setsockopt (sock,SOL_SOCKET ,SO_LINGER , - (char *)&no_linger,sizeof (no_linger)); -} -int rds_tcp_accept_one (struct socket *sock) {struct socket *new_sock =NULL ;
@@ -241,7 +230,7 @@ int rds_tcp_accept_one(struct socket *sock)* be pending on it. By setting linger, we achieve the side-effect * of avoiding TIME_WAIT state on new_sock. */ -rds_tcp_set_linger (new_sock); +sock_no_linger (new_sock->sk);kernel_sock_shutdown (new_sock,SHUT_RDWR ); ret =0 ; out:
net/sunrpc/svcsock.c +2 -10
@@ -323,17 +323,9 @@ static int svc_tcp_has_wspace(struct svc_xprt *xprt)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 , - }; + struct svc_sock *svsk = container_of(xprt, struct svc_sock, sk_xprt); - 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)); +sock_no_linger (svsk->sk_sock->sk); }/*
Signature · 1 line
2.26.2
Christoph Hellwig
maintainerPATCH 3/28 net: add sock_set_priority
In reply to Christoph HellwigAdd a helper to directly set the SO_PRIORITY sockopt from kernel space without going through a fake uaccess.
--- drivers/nvme/host/tcp.c | 12 ++---------- drivers/nvme/target/tcp.c | 18 ++++-------------- include/net/sock.h | 1 + net/core/sock.c | 8 ++++++++ 4 files changed, 15 insertions(+), 24 deletions(-)
drivers/nvme/host/tcp.c +2 -10
@@ -1362,16 +1362,8 @@ static int nvme_tcp_alloc_queue(struct nvme_ctrl *nctrl,*/ sock_no_linger (queue->sock->sk); -if (so_priority >0 ) { - ret =kernel_setsockopt (queue->sock,SOL_SOCKET ,SO_PRIORITY , - (char *)&so_priority,sizeof (so_priority)); -if (ret) { -dev_err (ctrl->ctrl.device, -"failed to set SO_PRIORITY sock opt, ret %d\n" , - ret); - goto err_sock; - } - } +if (so_priority >0 ) +sock_set_priority (queue->sock->sk, so_priority);/* Set socket type of service */ if (nctrl->opts->tos >=0 ) {
drivers/nvme/target/tcp.c +4 -14
@@ -1448,12 +1448,8 @@ static int nvmet_tcp_set_queue_sock(struct nvmet_tcp_queue *queue)*/ sock_no_linger (sock->sk); -if (so_priority >0 ) { - ret =kernel_setsockopt (sock,SOL_SOCKET ,SO_PRIORITY , - (char *)&so_priority,sizeof (so_priority)); -if (ret) -return ret; - } +if (so_priority >0 ) +sock_set_priority (sock->sk, so_priority);/* Set socket type of service */ if (inet->rcv_tos >0 ) {
@@ -1638,14 +1634,8 @@ static int nvmet_tcp_add_port(struct nvmet_port *nport) goto err_sock; } -if (so_priority >0 ) { - ret =kernel_setsockopt (port->sock,SOL_SOCKET ,SO_PRIORITY , - (char *)&so_priority,sizeof (so_priority)); -if (ret) { -pr_err ("failed to set SO_PRIORITY sock opt %d\n" , ret); - goto err_sock; - } - } +if (so_priority >0 ) +sock_set_priority (port->sock->sk, so_priority); ret =kernel_bind (port->sock, (struct sockaddr *)&port->addr,sizeof (port->addr));
include/net/sock.h +1 -0
@@ -2689,6 +2689,7 @@ static inline bool sk_dev_equal_l3scope(struct sock *sk, int dif)void sock_def_readable (struct sock *sk);void sock_no_linger (struct sock *sk); +void sock_set_priority (struct sock *sk,u32 priority);void sock_set_reuseaddr (struct sock *sk);#endif /* _SOCK_H */
net/core/sock.c +8 -0
@@ -729,6 +729,14 @@ void sock_no_linger(struct sock *sk) }EXPORT_SYMBOL (sock_no_linger); +void sock_set_priority (struct sock *sk,u32 priority) +{ +lock_sock (sk); + sk->sk_priority = priority; +release_sock (sk); +} +EXPORT_SYMBOL (sock_set_priority); +/* * This is meant for all protocols to use and covers goings on * at the socket level. Everything here is generic.
Signature · 1 line
2.26.2
Christoph Hellwig
maintainerPATCH 4/28 net: add sock_set_sndtimeo
In reply to Christoph HellwigAdd a helper to directly set the SO_SNDTIMEO_NEW sockopt from kernel space without going through a fake uaccess. The interface is simplified to only pass the seconds value, as that is the only thing needed at the moment.
--- fs/dlm/lowcomms.c | 8 ++------ include/net/sock.h | 1 + net/core/sock.c | 11 +++++++++++ 3 files changed, 14 insertions(+), 6 deletions(-)
fs/dlm/lowcomms.c +2 -6
@@ -1035,7 +1035,6 @@ static void sctp_connect_to_sock(struct connection *con)int result;int addr_len;struct socket *sock; -struct __kernel_sock_timeval tv = { .tv_sec =5 , .tv_usec =0 };if (con->nodeid ==0 ) {log_print ("attempt to connect sock 0 foiled" );
@@ -1087,13 +1086,10 @@ static void sctp_connect_to_sock(struct connection *con)* since O_NONBLOCK argument in connect() function does not work here, * then, we should restore the default value of this attribute. */ -kernel_setsockopt (sock,SOL_SOCKET ,SO_SNDTIMEO_NEW , (char *)&tv, -sizeof (tv)); +sock_set_sndtimeo (sock->sk,5 ); result = sock->ops->connect (sock, (struct sockaddr *)&daddr, addr_len,0 ); -memset (&tv,0 ,sizeof (tv)); -kernel_setsockopt (sock,SOL_SOCKET ,SO_SNDTIMEO_NEW , (char *)&tv, -sizeof (tv)); +sock_set_sndtimeo (sock->sk,0 );if (result == -EINPROGRESS ) result =0 ;
include/net/sock.h +1 -0
@@ -2691,5 +2691,6 @@ void sock_def_readable(struct sock *sk);void sock_no_linger (struct sock *sk);void sock_set_priority (struct sock *sk,u32 priority);void sock_set_reuseaddr (struct sock *sk); +void sock_set_sndtimeo (struct sock *sk,s64 secs);#endif /* _SOCK_H */
net/core/sock.c +11 -0
@@ -737,6 +737,17 @@ void sock_set_priority(struct sock *sk, u32 priority) }EXPORT_SYMBOL (sock_set_priority); +void sock_set_sndtimeo (struct sock *sk,s64 secs) +{ +lock_sock (sk); +if (secs && secs <MAX_SCHEDULE_TIMEOUT /HZ -1 ) + sk->sk_sndtimeo = secs *HZ ; +else + sk->sk_sndtimeo =MAX_SCHEDULE_TIMEOUT ; +release_sock (sk); +} +EXPORT_SYMBOL (sock_set_sndtimeo); +/* * This is meant for all protocols to use and covers goings on * at the socket level. Everything here is generic.
Signature · 1 line
2.26.2
Christoph Hellwig
maintainerPATCH 5/28 net: add sock_bindtoindex
In reply to Christoph HellwigAdd a helper to directly set the SO_BINDTOIFINDEX sockopt from kernel space without going through a fake uaccess.
--- include/net/sock.h | 1 + net/core/sock.c | 21 +++++++++++++++------ net/ipv4/udp_tunnel.c | 4 +--- net/ipv6/ip6_udp_tunnel.c | 4 +--- 4 files changed, 18 insertions(+), 12 deletions(-)
include/net/sock.h +1 -0
@@ -2688,6 +2688,7 @@ static inline bool sk_dev_equal_l3scope(struct sock *sk, int dif)void sock_def_readable (struct sock *sk); +int sock_bindtoindex (struct sock *sk,int ifindex);void sock_no_linger (struct sock *sk);void sock_set_priority (struct sock *sk,u32 priority);void sock_set_reuseaddr (struct sock *sk);
net/core/sock.c +15 -6
@@ -566,7 +566,7 @@ struct dst_entry *sk_dst_check(struct sock *sk, u32 cookie) }EXPORT_SYMBOL (sk_dst_check); -static int sock_setbindtodevice_locked (struct sock *sk,int ifindex) +static int sock_bindtoindex_locked (struct sock *sk,int ifindex) {int ret = -ENOPROTOOPT ;#ifdef CONFIG_NETDEVICES
@@ -594,6 +594,18 @@ static int sock_setbindtodevice_locked(struct sock *sk, int ifindex)return ret; } +int sock_bindtoindex (struct sock *sk,int ifindex) +{ +int ret; + +lock_sock (sk); + ret =sock_bindtoindex_locked (sk, ifindex); +release_sock (sk); + +return ret; +} +EXPORT_SYMBOL (sock_bindtoindex); +static int sock_setbindtodevice (struct sock *sk,char __user *optval,int optlen) {
@@ -634,10 +646,7 @@ static int sock_setbindtodevice(struct sock *sk, char __user *optval, goto out; } -lock_sock (sk); - ret =sock_setbindtodevice_locked (sk, index); -release_sock (sk); - +return sock_bindtoindex (sk, index); out:#endif
@@ -1216,7 +1225,7 @@ int sock_setsockopt(struct socket *sock, int level, int optname,break ;case SO_BINDTOIFINDEX : - ret =sock_setbindtodevice_locked (sk, val); + ret =sock_bindtoindex_locked (sk, val);break ;default :
net/ipv4/udp_tunnel.c +1 -3
@@ -22,9 +22,7 @@ int udp_sock_create4(struct net *net, struct udp_port_cfg *cfg, goto error;if (cfg->bind_ifindex) { - err =kernel_setsockopt (sock,SOL_SOCKET ,SO_BINDTOIFINDEX , - (void *)&cfg->bind_ifindex, -sizeof (cfg->bind_ifindex)); + err =sock_bindtoindex (sock->sk, cfg->bind_ifindex);if (err <0 ) goto error; }
net/ipv6/ip6_udp_tunnel.c +1 -3
@@ -33,9 +33,7 @@ int udp_sock_create6(struct net *net, struct udp_port_cfg *cfg, goto error; }if (cfg->bind_ifindex) { - err =kernel_setsockopt (sock,SOL_SOCKET ,SO_BINDTOIFINDEX , - (void *)&cfg->bind_ifindex, -sizeof (cfg->bind_ifindex)); + err =sock_bindtoindex (sock->sk, cfg->bind_ifindex);if (err <0 ) goto error; }
Signature · 1 line
2.26.2
Christoph Hellwig
maintainerPATCH 6/28 net: add sock_enable_timestamps
In reply to Christoph HellwigAdd a helper to directly enable timestamps instead of setting the SO_TIMESTAMP* sockopts from kernel space and going through a fake uaccess.
--- include/net/sock.h | 1 + net/core/sock.c | 47 +++++++++++++++++++++++++--------------- net/rxrpc/local_object.c | 8 +------ 3 files changed, 31 insertions(+), 25 deletions(-)
include/net/sock.h +1 -0
@@ -2689,6 +2689,7 @@ static inline bool sk_dev_equal_l3scope(struct sock *sk, int dif)void sock_def_readable (struct sock *sk);int sock_bindtoindex (struct sock *sk,int ifindex); +void sock_enable_timestamps (struct sock *sk);void sock_no_linger (struct sock *sk);void sock_set_priority (struct sock *sk,u32 priority);void sock_set_reuseaddr (struct sock *sk);
net/core/sock.c +29 -18
63 lines not on this page · raw message
net/rxrpc/local_object.c +1 -7
@@ -189,13 +189,7 @@ static int rxrpc_open_socket(struct rxrpc_local *local, struct net *net) }/* We want receive timestamps. */ - opt =1 ; - ret =kernel_setsockopt (local->socket,SOL_SOCKET ,SO_TIMESTAMPNS_OLD , - (char *)&opt,sizeof (opt)); -if (ret <0 ) { -_debug ("setsockopt failed" ); - goto error; - } +sock_enable_timestamps (local->socket->sk);break ;default :
Signature · 1 line
2.26.2
Christoph Hellwig
maintainerPATCH 7/28 net: add sock_set_keepalive
In reply to Christoph HellwigAdd a helper to directly set the SO_KEEPALIVE sockopt from kernel space without going through a fake uaccess.
--- fs/dlm/lowcomms.c | 6 +----- include/net/sock.h | 1 + net/core/sock.c | 10 ++++++++++ net/rds/tcp_listen.c | 6 +----- net/sunrpc/xprtsock.c | 4 +--- 5 files changed, 14 insertions(+), 13 deletions(-)
fs/dlm/lowcomms.c +1 -5
@@ -1259,11 +1259,7 @@ static struct socket *tcp_create_listen_sock(struct connection *con, con->sock =NULL ; goto create_out; } - result =kernel_setsockopt (sock,SOL_SOCKET ,SO_KEEPALIVE , - (char *)&one,sizeof (one)); -if (result <0 ) { -log_print ("Set keepalive failed: %d" , result); - } +sock_set_keepalive (sock->sk); result = sock->ops->listen (sock,5 );if (result <0 ) {
include/net/sock.h +1 -0
@@ -2691,6 +2691,7 @@ void sock_def_readable(struct sock *sk);int sock_bindtoindex (struct sock *sk,int ifindex);void sock_enable_timestamps (struct sock *sk);void sock_no_linger (struct sock *sk); +void sock_set_keepalive (struct sock *sk);void sock_set_priority (struct sock *sk,u32 priority);void sock_set_reuseaddr (struct sock *sk);void sock_set_sndtimeo (struct sock *sk,s64 secs);
net/core/sock.c +10 -0
@@ -779,6 +779,16 @@ void sock_enable_timestamps(struct sock *sk) }EXPORT_SYMBOL (sock_enable_timestamps); +void sock_set_keepalive (struct sock *sk) +{ +lock_sock (sk); +if (sk->sk_prot->keepalive) + sk->sk_prot->keepalive (sk, true); +sock_valbool_flag (sk,SOCK_KEEPOPEN , true); +release_sock (sk); +} +EXPORT_SYMBOL (sock_set_keepalive); +/* * This is meant for all protocols to use and covers goings on * at the socket level. Everything here is generic.
net/rds/tcp_listen.c +1 -5
@@ -43,13 +43,9 @@ int rds_tcp_keepalive(struct socket *sock)/* values below based on xs_udp_default_timeout */ int keepidle =5 ;/* send a probe 'keepidle' secs after last data */ int keepcnt =5 ;/* number of unack'ed probes before declaring dead */ -int keepalive =1 ;int ret =0 ; - ret =kernel_setsockopt (sock,SOL_SOCKET ,SO_KEEPALIVE , - (char *)&keepalive,sizeof (keepalive)); -if (ret <0 ) - goto bail; +sock_set_keepalive (sock->sk); ret =kernel_setsockopt (sock,IPPROTO_TCP ,TCP_KEEPCNT , (char *)&keepcnt,sizeof (keepcnt));
net/sunrpc/xprtsock.c +1 -3
@@ -2110,7 +2110,6 @@ static void xs_tcp_set_socket_timeouts(struct rpc_xprt *xprt, struct sock_xprt *transport = container_of(xprt, struct sock_xprt, xprt);unsigned int keepidle;unsigned int keepcnt; -unsigned int opt_on =1 ;unsigned int timeo;spin_lock (&xprt->transport_lock);
@@ -2122,8 +2121,7 @@ static void xs_tcp_set_socket_timeouts(struct rpc_xprt *xprt,spin_unlock (&xprt->transport_lock);/* TCP Keepalive options */ -kernel_setsockopt (sock,SOL_SOCKET ,SO_KEEPALIVE , - (char *)&opt_on,sizeof (opt_on)); +sock_set_keepalive (sock->sk);kernel_setsockopt (sock,SOL_TCP ,TCP_KEEPIDLE , (char *)&keepidle,sizeof (keepidle)); kernel_setsockopt(sock, SOL_TCP, TCP_KEEPINTVL,
Signature · 1 line
2.26.2
Christoph Hellwig
maintainerPATCH 8/28 net: add sock_set_rcvbuf
In reply to Christoph HellwigAdd a helper to directly set the SO_RCVBUFFORCE sockopt from kernel space without going through a fake uaccess.
--- fs/dlm/lowcomms.c | 7 +----- include/net/sock.h | 1 + net/core/sock.c | 59 +++++++++++++++++++++++++--------------------- 3 files changed, 34 insertions(+), 33 deletions(-)
fs/dlm/lowcomms.c +1 -6
@@ -1297,7 +1297,6 @@ static int sctp_listen_for_all(void)struct socket *sock =NULL ;int result = -EINVAL ;struct connection *con =nodeid2con (0 ,GFP_NOFS ); -int bufsize =NEEDED_RMEM ;int one =1 ;if (!con)
@@ -1312,11 +1311,7 @@ static int sctp_listen_for_all(void) goto out; } - result =kernel_setsockopt (sock,SOL_SOCKET ,SO_RCVBUFFORCE , - (char *)&bufsize,sizeof (bufsize)); -if (result) -log_print ("Error increasing buffer space on socket %d" , result); - +sock_set_rcvbuf (sock->sk,NEEDED_RMEM ); result =kernel_setsockopt (sock,SOL_SCTP ,SCTP_NODELAY , (char *)&one,sizeof (one));if (result <0 )
include/net/sock.h +1 -0
@@ -2693,6 +2693,7 @@ void sock_enable_timestamps(struct sock *sk);void sock_no_linger (struct sock *sk);void sock_set_keepalive (struct sock *sk);void sock_set_priority (struct sock *sk,u32 priority); +void sock_set_rcvbuf (struct sock *sk,int val);void sock_set_reuseaddr (struct sock *sk);void sock_set_sndtimeo (struct sock *sk,s64 secs);
net/core/sock.c +32 -27
77 lines not on this page · raw message
Signature · 1 line
2.26.2
Christoph Hellwig
maintainerPATCH 9/28 net: add sock_set_reuseport
In reply to Christoph HellwigAdd a helper to directly set the SO_REUSEPORT sockopt from kernel space without going through a fake uaccess.
--- include/net/sock.h | 1 + net/core/sock.c | 8 ++++++++ net/sunrpc/xprtsock.c | 17 +---------------- 3 files changed, 10 insertions(+), 16 deletions(-)
include/net/sock.h +1 -0
@@ -2695,6 +2695,7 @@ void sock_set_keepalive(struct sock *sk);void sock_set_priority (struct sock *sk,u32 priority);void sock_set_rcvbuf (struct sock *sk,int val);void sock_set_reuseaddr (struct sock *sk); +void sock_set_reuseport (struct sock *sk);void sock_set_sndtimeo (struct sock *sk,s64 secs);#endif /* _SOCK_H */
net/core/sock.c +8 -0
@@ -729,6 +729,14 @@ void sock_set_reuseaddr(struct sock *sk) }EXPORT_SYMBOL (sock_set_reuseaddr); +void sock_set_reuseport (struct sock *sk) +{ +lock_sock (sk); + sk->sk_reuseport = true; +release_sock (sk); +} +EXPORT_SYMBOL (sock_set_reuseport); +void sock_no_linger (struct sock *sk) {lock_sock (sk);
net/sunrpc/xprtsock.c +1 -16
@@ -1594,21 +1594,6 @@ static int xs_get_random_port(void)return rand + min; } -/** -* xs_set_reuseaddr_port - set the socket's port and address reuse options -* @sock: socket -* -* Note that this function has to be called on all sockets that share the -* same port, and it must be called before binding. -*/ -static void xs_sock_set_reuseport (struct socket *sock) -{ -int opt =1 ; - -kernel_setsockopt (sock,SOL_SOCKET ,SO_REUSEPORT , - (char *)&opt,sizeof (opt)); -} -static unsigned short xs_sock_getport (struct socket *sock) {struct sockaddr_storage buf;
@@ -1801,7 +1786,7 @@ static struct socket *xs_create_sock(struct rpc_xprt *xprt,xs_reclassify_socket (family, sock);if (reuseport) -xs_sock_set_reuseport (sock); +sock_set_reuseport (sock->sk); err =xs_bind (transport, sock);if (err) {
Signature · 1 line
2.26.2
Christoph Hellwig
maintainerPATCH 10/28 tcp: add tcp_sock_set_cork
In reply to Christoph HellwigAdd a helper to directly set the TCP_CORK sockopt from kernel space without going through a fake uaccess. Cleanup the callers to avoid pointless wrappers now that this is a simple function call.
--- drivers/block/drbd/drbd_int.h | 14 -------- drivers/block/drbd/drbd_receiver.c | 4 +-- drivers/block/drbd/drbd_worker.c | 6 ++-- fs/cifs/transport.c | 8 ++--- include/linux/tcp.h | 2 ++ net/ipv4/tcp.c | 51 +++++++++++++++++++----------- net/rds/tcp_send.c | 9 ++---- 7 files changed, 43 insertions(+), 51 deletions(-)
drivers/block/drbd/drbd_int.h +0 -14
@@ -1570,20 +1570,6 @@ extern void drbd_set_recv_tcq(struct drbd_device *device, int tcq_enabled);extern void _drbd_clear_done_ee (struct drbd_device *device,struct list_head *to_be_freed);extern int drbd_connected (struct drbd_peer_device *); -static inline void drbd_tcp_cork (struct socket *sock) -{ -int val =1 ; - (void )kernel_setsockopt (sock,SOL_TCP ,TCP_CORK , - (char *)&val,sizeof (val)); -} - -static inline void drbd_tcp_uncork (struct socket *sock) -{ -int val =0 ; - (void )kernel_setsockopt (sock,SOL_TCP ,TCP_CORK , - (char *)&val,sizeof (val)); -} -static inline void drbd_tcp_nodelay (struct socket *sock) {int val =1 ;
drivers/block/drbd/drbd_receiver.c +2 -2
@@ -6162,7 +6162,7 @@ void drbd_send_acks_wf(struct work_struct *ws)rcu_read_unlock ();if (tcp_cork) -drbd_tcp_cork (connection->meta.socket); +tcp_sock_set_cork (connection->meta.socket->sk, true); err =drbd_finish_peer_reqs (device);kref_put (&device->kref, drbd_destroy_device);
@@ -6175,7 +6175,7 @@ void drbd_send_acks_wf(struct work_struct *ws) }if (tcp_cork) -drbd_tcp_uncork (connection->meta.socket); +tcp_sock_set_cork (connection->meta.socket->sk, false);return ; }
drivers/block/drbd/drbd_worker.c +3 -3
@@ -2098,7 +2098,7 @@ static void wait_for_work(struct drbd_connection *connection, struct list_head *if (uncork) {mutex_lock (&connection->data.mutex);if (connection->data.socket) -drbd_tcp_uncork (connection->data.socket); +tcp_sock_set_cork (connection->data.socket->sk, false);mutex_unlock (&connection->data.mutex); }
@@ -2153,9 +2153,9 @@ static void wait_for_work(struct drbd_connection *connection, struct list_head *mutex_lock (&connection->data.mutex);if (connection->data.socket) {if (cork) -drbd_tcp_cork (connection->data.socket); +tcp_sock_set_cork (connection->data.socket->sk, true);else if (!uncork) -drbd_tcp_uncork (connection->data.socket); +tcp_sock_set_cork (connection->data.socket->sk, false); }mutex_unlock (&connection->data.mutex); }
fs/cifs/transport.c +2 -6
@@ -325,7 +325,6 @@ __smb_send_rqst(struct TCP_Server_Info *server, int num_rqst,size_t total_len =0 , sent, size;struct socket *ssocket = server->ssocket;struct msghdr smb_msg; -int val =1 ;__be32 rfc1002_marker;if (cifs_rdma_enabled (server)) {
@@ -345,8 +344,7 @@ __smb_send_rqst(struct TCP_Server_Info *server, int num_rqst, }/* cork the socket */ -kernel_setsockopt (ssocket,SOL_TCP ,TCP_CORK , - (char *)&val,sizeof (val)); +tcp_sock_set_cork (ssocket->sk, true);for (j =0 ; j < num_rqst; j++) send_length +=smb_rqst_len (server, &rqst[j]);
@@ -435,9 +433,7 @@ __smb_send_rqst(struct TCP_Server_Info *server, int num_rqst, }/* uncork it */ - val =0 ; -kernel_setsockopt (ssocket,SOL_TCP ,TCP_CORK , - (char *)&val,sizeof (val)); +tcp_sock_set_cork (ssocket->sk, false);if ((total_len >0 ) && (total_len != send_length)) { cifs_dbg(FYI, "partial send (wanted=%u sent=%zu): terminating session\n",
include/linux/tcp.h +2 -0
@@ -497,4 +497,6 @@ static inline u16 tcp_mss_clamp(const struct tcp_sock *tp, u16 mss)int tcp_skb_shift (struct sk_buff *to,struct sk_buff *from,int pcount,int shiftlen); +void tcp_sock_set_cork (struct sock *sk,bool on); +#endif /* _LINUX_TCP_H */
net/ipv4/tcp.c +32 -19
63 lines not on this page · raw message
net/rds/tcp_send.c +2 -7
@@ -38,23 +38,18 @@#include "rds.h" #include "tcp.h" -static void rds_tcp_cork (struct socket *sock,int val) -{ -kernel_setsockopt (sock,SOL_TCP ,TCP_CORK , (void *)&val,sizeof (val)); -} -void rds_tcp_xmit_path_prepare (struct rds_conn_path *cp) {struct rds_tcp_connection *tc = cp->cp_transport_data; -rds_tcp_cork (tc->t_sock,1 ); +tcp_sock_set_cork (tc->t_sock->sk, true); }void rds_tcp_xmit_path_complete (struct rds_conn_path *cp) {struct rds_tcp_connection *tc = cp->cp_transport_data; -rds_tcp_cork (tc->t_sock,0 ); +tcp_sock_set_cork (tc->t_sock->sk, false); }/* the core send_sem serializes this with other xmit and shutdown */
Signature · 1 line
2.26.2
Christoph Hellwig
maintainerPATCH 11/28 tcp: add tcp_sock_set_nodelay
In reply to Christoph HellwigAdd a helper to directly set the TCP_NODELAY sockopt from kernel space without going through a fake uaccess. Cleanup the callers to avoid pointless wrappers now that this is a simple function call.
--- drivers/block/drbd/drbd_int.h | 7 ---- drivers/block/drbd/drbd_main.c | 2 +- drivers/block/drbd/drbd_receiver.c | 4 +-- drivers/infiniband/sw/siw/siw_cm.c | 24 +++----------- drivers/nvme/host/tcp.c | 9 +----- drivers/nvme/target/tcp.c | 12 ++----- drivers/target/iscsi/iscsi_target_login.c | 15 ++------- fs/cifs/connect.c | 10 ++---- fs/dlm/lowcomms.c | 8 ++--- fs/ocfs2/cluster/tcp.c | 20 ++---------- include/linux/tcp.h | 1 + net/ceph/messenger.c | 11 ++----- net/ipv4/tcp.c | 39 +++++++++++++++-------- net/rds/tcp.c | 11 +------ net/rds/tcp.h | 1 - net/rds/tcp_listen.c | 2 +- 16 files changed, 49 insertions(+), 127 deletions(-)
drivers/block/drbd/drbd_int.h +0 -7
@@ -1570,13 +1570,6 @@ extern void drbd_set_recv_tcq(struct drbd_device *device, int tcq_enabled);extern void _drbd_clear_done_ee (struct drbd_device *device,struct list_head *to_be_freed);extern int drbd_connected (struct drbd_peer_device *); -static inline void drbd_tcp_nodelay (struct socket *sock) -{ -int val =1 ; - (void )kernel_setsockopt (sock,SOL_TCP ,TCP_NODELAY , - (char *)&val,sizeof (val)); -} -static inline void drbd_tcp_quickack (struct socket *sock) {int val =2 ;
drivers/block/drbd/drbd_main.c +1 -1
@@ -660,7 +660,7 @@ static int __send_command(struct drbd_connection *connection, int vnr,/* DRBD protocol "pings" are latency critical. * This is supposed to trigger tcp_push_pending_frames() */ if (!err && (cmd ==P_PING || cmd ==P_PING_ACK )) -drbd_tcp_nodelay (sock->socket); +tcp_sock_set_nodelay (sock->socket->sk);return err; }
drivers/block/drbd/drbd_receiver.c +2 -2
@@ -1051,8 +1051,8 @@ static int conn_connect(struct drbd_connection *connection)/* we don't want delays. * we use TCP_CORK where appropriate, though */ -drbd_tcp_nodelay (sock.socket); -drbd_tcp_nodelay (msock.socket); +tcp_sock_set_nodelay (sock.socket->sk); +tcp_sock_set_nodelay (msock.socket->sk); connection->data.socket = sock.socket; connection->meta.socket = msock.socket;
drivers/infiniband/sw/siw/siw_cm.c +4 -20
@@ -947,16 +947,8 @@ static void siw_accept_newconn(struct siw_cep *cep)siw_cep_get (new_cep); new_s->sk->sk_user_data = new_cep; -if (siw_tcp_nagle == false) { -int val =1 ; - - rv =kernel_setsockopt (new_s,SOL_TCP ,TCP_NODELAY , - (char *)&val,sizeof (val)); -if (rv) { -siw_dbg_cep (cep,"setsockopt NODELAY error: %d\n" , rv); - goto error; - } - } +if (siw_tcp_nagle == false) +tcp_sock_set_nodelay (new_s->sk); new_cep->state =SIW_EPSTATE_AWAIT_MPAREQ ; rv =siw_cm_queue_work (new_cep,SIW_CM_WORK_MPATIMEOUT );
@@ -1386,16 +1378,8 @@ int siw_connect(struct iw_cm_id *id, struct iw_cm_conn_param *params)siw_dbg_qp (qp,"kernel_bindconnect: error %d\n" , rv); goto error; } -if (siw_tcp_nagle == false) { -int val =1 ; - - rv =kernel_setsockopt (s,SOL_TCP ,TCP_NODELAY , (char *)&val, -sizeof (val)); -if (rv) { -siw_dbg_qp (qp,"setsockopt NODELAY error: %d\n" , rv); - goto error; - } - } +if (siw_tcp_nagle == false) +tcp_sock_set_nodelay (s->sk); cep =siw_cep_alloc (sdev);if (!cep) { rv = -ENOMEM ;
drivers/nvme/host/tcp.c +1 -8
@@ -1346,14 +1346,7 @@ static int nvme_tcp_alloc_queue(struct nvme_ctrl *nctrl, }/* Set TCP no delay */ - opt =1 ; - ret =kernel_setsockopt (queue->sock,IPPROTO_TCP , -TCP_NODELAY , (char *)&opt,sizeof (opt)); -if (ret) { -dev_err (nctrl->device, -"failed to set TCP_NODELAY sock opt %d\n" , ret); - goto err_sock; - } +tcp_sock_set_nodelay (queue->sock->sk);/* * Cleanup whatever is sitting in the TCP transmit queue on socket
drivers/nvme/target/tcp.c +2 -10
@@ -1580,7 +1580,7 @@ static int nvmet_tcp_add_port(struct nvmet_port *nport) {struct nvmet_tcp_port *port;__kernel_sa_family_t af; -int opt, ret; +int ret; port =kzalloc (sizeof (*port),GFP_KERNEL );if (!port)
@@ -1625,15 +1625,7 @@ static int nvmet_tcp_add_port(struct nvmet_port *nport) port->data_ready = port->sock->sk->sk_data_ready; port->sock->sk->sk_data_ready = nvmet_tcp_listen_data_ready;sock_set_reuseaddr (port->sock->sk); - - opt =1 ; - ret =kernel_setsockopt (port->sock,IPPROTO_TCP , -TCP_NODELAY , (char *)&opt,sizeof (opt)); -if (ret) { -pr_err ("failed to set TCP_NODELAY sock opt %d\n" , ret); - goto err_sock; - } - +tcp_sock_set_nodelay (port->sock->sk);if (so_priority >0 )sock_set_priority (port->sock->sk, so_priority);
drivers/target/iscsi/iscsi_target_login.c +3 -12
@@ -897,20 +897,11 @@ int iscsit_setup_np(/* * Set SO_REUSEADDR, and disable Nagel Algorithm with TCP_NODELAY. */ -/* FIXME: Someone please explain why this is endian-safe */ - opt =1 ; -if (np->np_network_transport ==ISCSI_TCP ) { - ret =kernel_setsockopt (sock,IPPROTO_TCP ,TCP_NODELAY , - (char *)&opt,sizeof (opt)); -if (ret <0 ) { -pr_err ("kernel_setsockopt() for TCP_NODELAY" -" failed: %d\n" , ret); - goto fail; - } - } - +if (np->np_network_transport ==ISCSI_TCP ) +tcp_sock_set_nodelay (sock->sk);sock_set_reuseaddr (sock->sk); + opt =1 ; ret =kernel_setsockopt (sock,IPPROTO_IP ,IP_FREEBIND , (char *)&opt,sizeof (opt));if (ret <0 ) {
fs/cifs/connect.c +2 -8
@@ -3929,14 +3929,8 @@ generic_ip_connect(struct TCP_Server_Info *server) socket->sk->sk_rcvbuf =140 *1024 ; } -if (server->tcp_nodelay) { -int val =1 ; - rc =kernel_setsockopt (socket,SOL_TCP ,TCP_NODELAY , - (char *)&val,sizeof (val)); -if (rc) -cifs_dbg (FYI ,"set TCP_NODELAY socket option error %d\n" , - rc); - } +if (server->tcp_nodelay) +tcp_sock_set_nodelay (socket->sk); cifs_dbg(FYI, "sndbuf %d rcvbuf %d rcvtimeo 0x%lx\n", socket->sk->sk_sndbuf,
fs/dlm/lowcomms.c +2 -6
@@ -1128,7 +1128,6 @@ static void tcp_connect_to_sock(struct connection *con)struct sockaddr_storage saddr, src_addr;int addr_len;struct socket *sock =NULL ; -int one =1 ;int result;if (con->nodeid ==0 ) {
@@ -1177,8 +1176,7 @@ static void tcp_connect_to_sock(struct connection *con)log_print ("connecting to %d" , con->nodeid);/* Turn off Nagle's algorithm */ -kernel_setsockopt (sock,SOL_TCP ,TCP_NODELAY , (char *)&one, -sizeof (one)); +tcp_sock_set_nodelay (sock->sk); result = sock->ops->connect (sock, (struct sockaddr *)&saddr, addr_len,O_NONBLOCK );
@@ -1220,7 +1218,6 @@ static struct socket *tcp_create_listen_sock(struct connection *con, {struct socket *sock =NULL ;int result =0 ; -int one =1 ;int addr_len;if (dlm_local_addr[0 ]->ss_family ==AF_INET )
@@ -1237,8 +1234,7 @@ static struct socket *tcp_create_listen_sock(struct connection *con, }/* Turn off Nagle's algorithm */ -kernel_setsockopt (sock,SOL_TCP ,TCP_NODELAY , (char *)&one, -sizeof (one)); +tcp_sock_set_nodelay (sock->sk);sock_set_reuseaddr (sock->sk);
fs/ocfs2/cluster/tcp.c +2 -18
@@ -1441,14 +1441,6 @@ static void o2net_rx_until_empty(struct work_struct *work)sc_put (sc); } -static int o2net_set_nodelay (struct socket *sock) -{ -int val =1 ; - -return kernel_setsockopt (sock,SOL_TCP ,TCP_NODELAY , - (void *)&val,sizeof (val)); -} -static int o2net_set_usertimeout (struct socket *sock) {int user_timeout =O2NET_TCP_USER_TIMEOUT ;
@@ -1636,11 +1628,7 @@ static void o2net_start_connect(struct work_struct *work) goto out; } - ret =o2net_set_nodelay (sc->sc_sock); -if (ret) { -mlog (ML_ERROR ,"setting TCP_NODELAY failed with %d\n" , ret); - goto out; - } +tcp_sock_set_nodelay (sc->sc_sock->sk); ret =o2net_set_usertimeout (sock);if (ret) {
@@ -1832,11 +1820,7 @@ static int o2net_accept_one(struct socket *sock, int *more) *more =1 ; new_sock->sk->sk_allocation =GFP_ATOMIC ; - ret =o2net_set_nodelay (new_sock); -if (ret) { -mlog (ML_ERROR ,"setting TCP_NODELAY failed with %d\n" , ret); - goto out; - } +tcp_sock_set_nodelay (new_sock->sk); ret =o2net_set_usertimeout (new_sock);if (ret) {
include/linux/tcp.h +1 -0
@@ -498,5 +498,6 @@ int tcp_skb_shift(struct sk_buff *to, struct sk_buff *from, int pcount, int shiftlen);void tcp_sock_set_cork (struct sock *sk,bool on); +void tcp_sock_set_nodelay (struct sock *sk);#endif /* _LINUX_TCP_H */
net/ceph/messenger.c +2 -9
@@ -490,15 +490,8 @@ static int ceph_tcp_connect(struct ceph_connection *con)return ret; } -if (ceph_test_opt (from_msgr (con->msgr),TCP_NODELAY )) { -int optval =1 ; - - ret =kernel_setsockopt (sock,SOL_TCP ,TCP_NODELAY , - (char *)&optval,sizeof (optval)); -if (ret) -pr_err ("kernel_setsockopt(TCP_NODELAY) failed: %d" , - ret); - } +if (ceph_test_opt (from_msgr (con->msgr),TCP_NODELAY )) +tcp_sock_set_nodelay (sock->sk); con->sock = sock;return 0 ;
net/ipv4/tcp.c +25 -14
@@ -2832,6 +2832,30 @@ void tcp_sock_set_cork(struct sock *sk, bool on) }EXPORT_SYMBOL (tcp_sock_set_cork); +/* TCP_NODELAY is weaker than TCP_CORK, so that this option on corked socket is +* remembered, but it is not activated until cork is cleared. +* +* However, when TCP_NODELAY is set we make an explicit push, which overrides +* even TCP_CORK for currently queued segments. +*/ +static void __tcp_sock_set_nodelay (struct sock *sk,bool on) +{ +if (on) { +tcp_sk (sk)->nonagle |=TCP_NAGLE_OFF |TCP_NAGLE_PUSH ; +tcp_push_pending_frames (sk); + }else { +tcp_sk (sk)->nonagle &= ~TCP_NAGLE_OFF ; + } +} + +void tcp_sock_set_nodelay (struct sock *sk) +{ +lock_sock (sk); +__tcp_sock_set_nodelay (sk, true); +release_sock (sk); +} +EXPORT_SYMBOL (tcp_sock_set_nodelay); +/* * Socket option code for TCP. */
@@ -2929,20 +2953,7 @@ static int do_tcp_setsockopt(struct sock *sk, int level,break ;case TCP_NODELAY : -if (val) { -/* TCP_NODELAY is weaker than TCP_CORK, so that -* this option on corked socket is remembered, but -* it is not activated until cork is cleared. -* -* However, when TCP_NODELAY is set we make -* an explicit push, which overrides even TCP_CORK -* for currently queued segments. -*/ - tp->nonagle |=TCP_NAGLE_OFF |TCP_NAGLE_PUSH ; -tcp_push_pending_frames (sk); - }else { - tp->nonagle &= ~TCP_NAGLE_OFF ; - } +__tcp_sock_set_nodelay (sk, val);break ;case TCP_THIN_LINEAR_TIMEOUTS :
net/rds/tcp.c +1 -10
@@ -89,15 +89,6 @@ static struct ctl_table rds_tcp_sysctl_table[] = { { } }; -/* doing it this way avoids calling tcp_sk() */ -void rds_tcp_nonagle (struct socket *sock) -{ -int val =1 ; - -kernel_setsockopt (sock,SOL_TCP ,TCP_NODELAY , (void *)&val, -sizeof (val)); -} -u32 rds_tcp_write_seq (struct rds_tcp_connection *tc) {/* seq# of the last byte of data in tcp send buffer */
@@ -502,7 +493,7 @@ void rds_tcp_tune(struct socket *sock)struct net *net =sock_net (sk);struct rds_tcp_net *rtn =net_generic (net, rds_tcp_netid); -rds_tcp_nonagle (sock); +tcp_sock_set_nodelay (sock->sk);lock_sock (sk);if (rtn->sndbuf_size >0 ) { sk->sk_sndbuf = rtn->sndbuf_size;
net/rds/tcp.h +0 -1
@@ -50,7 +50,6 @@ struct rds_tcp_statistics {/* tcp.c */ void rds_tcp_tune (struct socket *sock); -void rds_tcp_nonagle (struct socket *sock);void rds_tcp_set_callbacks (struct socket *sock,struct rds_conn_path *cp);void rds_tcp_reset_callbacks (struct socket *sock,struct rds_conn_path *cp); void rds_tcp_restore_callbacks(struct socket *sock,
net/rds/tcp_listen.c +1 -1
@@ -288,7 +288,7 @@ struct socket *rds_tcp_listen_init(struct net *net, bool isv6) } sock->sk->sk_reuse =SK_CAN_REUSE ; -rds_tcp_nonagle (sock); +tcp_sock_set_nodelay (sock->sk);write_lock_bh (&sock->sk->sk_callback_lock); sock->sk->sk_user_data = sock->sk->sk_data_ready;
Signature · 1 line
2.26.2
Christoph Hellwig
maintainerPATCH 12/28 tcp: add tcp_sock_set_quickack
In reply to Christoph HellwigAdd a helper to directly set the TCP_QUICKACK sockopt from kernel space without going through a fake uaccess. Cleanup the callers to avoid pointless wrappers now that this is a simple function call.
--- drivers/block/drbd/drbd_int.h | 7 ------ drivers/block/drbd/drbd_receiver.c | 5 ++-- include/linux/tcp.h | 1 + net/ipv4/tcp.c | 39 ++++++++++++++++++++---------- 4 files changed, 29 insertions(+), 23 deletions(-)
drivers/block/drbd/drbd_int.h +0 -7
@@ -1570,13 +1570,6 @@ extern void drbd_set_recv_tcq(struct drbd_device *device, int tcq_enabled);extern void _drbd_clear_done_ee (struct drbd_device *device,struct list_head *to_be_freed);extern int drbd_connected (struct drbd_peer_device *); -static inline void drbd_tcp_quickack (struct socket *sock) -{ -int val =2 ; - (void )kernel_setsockopt (sock,SOL_TCP ,TCP_QUICKACK , - (char *)&val,sizeof (val)); -} -/* sets the number of 512 byte sectors of our virtual device */ void drbd_set_my_capacity (struct drbd_device *device,sector_t size);
drivers/block/drbd/drbd_receiver.c +2 -3
@@ -1223,7 +1223,7 @@ static int drbd_recv_header_maybe_unplug(struct drbd_connection *connection, str* quickly as possible, and let remote TCP know what we have * received so far. */ if (err == -EAGAIN ) { -drbd_tcp_quickack (connection->data.socket); +tcp_sock_set_quickack (connection->data.socket->sk,2 );drbd_unplug_all_devices (connection); }if (err >0 ) {
@@ -4959,8 +4959,7 @@ static int receive_UnplugRemote(struct drbd_connection *connection, struct packe {/* Make sure we've acked all the TCP data associated * with the data requests being unplugged */ -drbd_tcp_quickack (connection->data.socket); - +tcp_sock_set_quickack (connection->data.socket->sk,2 );return 0 ; }
include/linux/tcp.h +1 -0
@@ -499,5 +499,6 @@ int tcp_skb_shift(struct sk_buff *to, struct sk_buff *from, int pcount,void tcp_sock_set_cork (struct sock *sk,bool on);void tcp_sock_set_nodelay (struct sock *sk); +void tcp_sock_set_quickack (struct sock *sk,int val);#endif /* _LINUX_TCP_H */
net/ipv4/tcp.c +26 -13
@@ -2856,6 +2856,31 @@ void tcp_sock_set_nodelay(struct sock *sk) }EXPORT_SYMBOL (tcp_sock_set_nodelay); +static void __tcp_sock_set_quickack (struct sock *sk,int val) +{ +if (!val) { +inet_csk_enter_pingpong_mode (sk); +return ; + } + +inet_csk_exit_pingpong_mode (sk); +if ((1 << sk->sk_state) & (TCPF_ESTABLISHED |TCPF_CLOSE_WAIT ) && +inet_csk_ack_scheduled (sk)) { +inet_csk (sk)->icsk_ack.pending |=ICSK_ACK_PUSHED ; +tcp_cleanup_rbuf (sk,1 ); +if (!(val &1 )) +inet_csk_enter_pingpong_mode (sk); + } +} + +void tcp_sock_set_quickack (struct sock *sk,int val) +{ +lock_sock (sk); +__tcp_sock_set_quickack (sk, val); +release_sock (sk); +} +EXPORT_SYMBOL (tcp_sock_set_quickack); +/* * Socket option code for TCP. */
@@ -3096,19 +3121,7 @@ static int do_tcp_setsockopt(struct sock *sk, int level,break ;case TCP_QUICKACK : -if (!val) { -inet_csk_enter_pingpong_mode (sk); - }else { -inet_csk_exit_pingpong_mode (sk); -if ((1 << sk->sk_state) & - (TCPF_ESTABLISHED |TCPF_CLOSE_WAIT ) && -inet_csk_ack_scheduled (sk)) { - icsk->icsk_ack.pending |=ICSK_ACK_PUSHED ; -tcp_cleanup_rbuf (sk,1 ); -if (!(val &1 )) -inet_csk_enter_pingpong_mode (sk); - } - } +__tcp_sock_set_quickack (sk, val);break ;#ifdef CONFIG_TCP_MD5SIG
Signature · 1 line
2.26.2
Christoph Hellwig
maintainerPATCH 13/28 tcp: add tcp_sock_set_syncnt
In reply to Christoph HellwigAdd a helper to directly set the TCP_SYNCNT sockopt from kernel space without going through a fake uaccess.
--- drivers/nvme/host/tcp.c | 9 +-------- include/linux/tcp.h | 1 + net/ipv4/tcp.c | 12 ++++++++++++ 3 files changed, 14 insertions(+), 8 deletions(-)
drivers/nvme/host/tcp.c +1 -8
@@ -1336,14 +1336,7 @@ static int nvme_tcp_alloc_queue(struct nvme_ctrl *nctrl, }/* Single syn retry */ - opt =1 ; - ret =kernel_setsockopt (queue->sock,IPPROTO_TCP ,TCP_SYNCNT , - (char *)&opt,sizeof (opt)); -if (ret) { -dev_err (nctrl->device, -"failed to set TCP_SYNCNT sock opt %d\n" , ret); - goto err_sock; - } +tcp_sock_set_syncnt (queue->sock->sk,1 );/* Set TCP no delay */ tcp_sock_set_nodelay (queue->sock->sk);
include/linux/tcp.h +1 -0
@@ -500,5 +500,6 @@ int tcp_skb_shift(struct sk_buff *to, struct sk_buff *from, int pcount,void tcp_sock_set_cork (struct sock *sk,bool on);void tcp_sock_set_nodelay (struct sock *sk);void tcp_sock_set_quickack (struct sock *sk,int val); +int tcp_sock_set_syncnt (struct sock *sk,int val);#endif /* _LINUX_TCP_H */
net/ipv4/tcp.c +12 -0
@@ -2881,6 +2881,18 @@ void tcp_sock_set_quickack(struct sock *sk, int val) }EXPORT_SYMBOL (tcp_sock_set_quickack); +int tcp_sock_set_syncnt (struct sock *sk,int val) +{ +if (val <1 || val >MAX_TCP_SYNCNT ) +return -EINVAL ; + +lock_sock (sk); +inet_csk (sk)->icsk_syn_retries = val; +release_sock (sk); +return 0 ; +} +EXPORT_SYMBOL (tcp_sock_set_syncnt); +/* * Socket option code for TCP. */
Signature · 1 line
2.26.2
Christoph Hellwig
maintainerPATCH 14/28 tcp: add tcp_sock_set_user_timeout
In reply to Christoph HellwigAdd a helper to directly set the TCP_USER_TIMEOUT sockopt from kernel space without going through a fake uaccess.
--- fs/ocfs2/cluster/tcp.c | 22 ++-------------------- include/linux/tcp.h | 1 + net/ipv4/tcp.c | 8 ++++++++ net/sunrpc/xprtsock.c | 3 +-- 4 files changed, 12 insertions(+), 22 deletions(-)
fs/ocfs2/cluster/tcp.c +2 -20
@@ -1441,14 +1441,6 @@ static void o2net_rx_until_empty(struct work_struct *work)sc_put (sc); } -static int o2net_set_usertimeout (struct socket *sock) -{ -int user_timeout =O2NET_TCP_USER_TIMEOUT ; - -return kernel_setsockopt (sock,SOL_TCP ,TCP_USER_TIMEOUT , - (void *)&user_timeout,sizeof (user_timeout)); -} -static void o2net_initialize_handshake (void ) { o2net_hand->o2hb_heartbeat_timeout_ms = cpu_to_be32(
@@ -1629,12 +1621,7 @@ static void o2net_start_connect(struct work_struct *work) }tcp_sock_set_nodelay (sc->sc_sock->sk); - - ret =o2net_set_usertimeout (sock); -if (ret) { -mlog (ML_ERROR ,"set TCP_USER_TIMEOUT failed with %d\n" , ret); - goto out; - } +tcp_sock_set_user_timeout (sock->sk,O2NET_TCP_USER_TIMEOUT );o2net_register_callbacks (sc->sc_sock->sk, sc);
@@ -1821,12 +1808,7 @@ static int o2net_accept_one(struct socket *sock, int *more) new_sock->sk->sk_allocation =GFP_ATOMIC ;tcp_sock_set_nodelay (new_sock->sk); - - ret =o2net_set_usertimeout (new_sock); -if (ret) { -mlog (ML_ERROR ,"set TCP_USER_TIMEOUT failed with %d\n" , ret); - goto out; - } +tcp_sock_set_user_timeout (new_sock->sk,O2NET_TCP_USER_TIMEOUT ); ret = new_sock->ops->getname (new_sock, (struct sockaddr *) &sin,1 );if (ret <0 )
include/linux/tcp.h +1 -0
@@ -501,5 +501,6 @@ void tcp_sock_set_cork(struct sock *sk, bool on);void tcp_sock_set_nodelay (struct sock *sk);void tcp_sock_set_quickack (struct sock *sk,int val);int tcp_sock_set_syncnt (struct sock *sk,int val); +void tcp_sock_set_user_timeout (struct sock *sk,u32 val);#endif /* _LINUX_TCP_H */
net/ipv4/tcp.c +8 -0
@@ -2893,6 +2893,14 @@ int tcp_sock_set_syncnt(struct sock *sk, int val) }EXPORT_SYMBOL (tcp_sock_set_syncnt); +void tcp_sock_set_user_timeout (struct sock *sk,u32 val) +{ +lock_sock (sk); +inet_csk (sk)->icsk_user_timeout = val; +release_sock (sk); +} +EXPORT_SYMBOL (tcp_sock_set_user_timeout); +/* * Socket option code for TCP. */
net/sunrpc/xprtsock.c +1 -2
@@ -2115,8 +2115,7 @@ static void xs_tcp_set_socket_timeouts(struct rpc_xprt *xprt, (char *)&keepcnt, sizeof(keepcnt));/* TCP user timeout (see RFC5482) */ -kernel_setsockopt (sock,SOL_TCP ,TCP_USER_TIMEOUT , - (char *)&timeo,sizeof (timeo)); +tcp_sock_set_user_timeout (sock->sk, timeo); } static void xs_tcp_set_connect_timeout(struct rpc_xprt *xprt,
Signature · 1 line
2.26.2
Christoph Hellwig
maintainerPATCH 15/28 tcp: add tcp_sock_set_keepidle
In reply to Christoph HellwigAdd a helper to directly set the TCP_KEEP_IDLE sockopt from kernel space without going through a fake uaccess.
--- include/linux/tcp.h | 1 + net/ipv4/tcp.c | 49 ++++++++++++++++++++++++++++++------------- net/rds/tcp_listen.c | 5 +---- net/sunrpc/xprtsock.c | 3 +-- 4 files changed, 37 insertions(+), 21 deletions(-)
include/linux/tcp.h +1 -0
@@ -498,6 +498,7 @@ int tcp_skb_shift(struct sk_buff *to, struct sk_buff *from, int pcount, int shiftlen);void tcp_sock_set_cork (struct sock *sk,bool on); +int tcp_sock_set_keepidle (struct sock *sk,int val);void tcp_sock_set_nodelay (struct sock *sk);void tcp_sock_set_quickack (struct sock *sk,int val);int tcp_sock_set_syncnt (struct sock *sk,int val);
net/ipv4/tcp.c +34 -15
61 lines not on this page · raw message
net/rds/tcp_listen.c +1 -4
@@ -52,10 +52,7 @@ int rds_tcp_keepalive(struct socket *sock)if (ret <0 ) goto bail; - ret =kernel_setsockopt (sock,IPPROTO_TCP ,TCP_KEEPIDLE , - (char *)&keepidle,sizeof (keepidle)); -if (ret <0 ) - goto bail; +tcp_sock_set_keepidle (sock->sk, keepidle);/* KEEPINTVL is the interval between successive probes. We follow * the model in xs_tcp_finish_connecting() and re-use keepidle.
net/sunrpc/xprtsock.c +1 -2
@@ -2107,8 +2107,7 @@ static void xs_tcp_set_socket_timeouts(struct rpc_xprt *xprt,/* TCP Keepalive options */ sock_set_keepalive (sock->sk); -kernel_setsockopt (sock,SOL_TCP ,TCP_KEEPIDLE , - (char *)&keepidle,sizeof (keepidle)); +tcp_sock_set_keepidle (sock->sk, keepidle);kernel_setsockopt (sock,SOL_TCP ,TCP_KEEPINTVL , (char *)&keepidle,sizeof (keepidle)); kernel_setsockopt(sock, SOL_TCP, TCP_KEEPCNT,
Signature · 1 line
2.26.2
Christoph Hellwig
maintainerPATCH 16/28 tcp: add tcp_sock_set_keepintvl
In reply to Christoph HellwigAdd a helper to directly set the TCP_KEEPINTVL sockopt from kernel space without going through a fake uaccess.
--- include/linux/tcp.h | 1 + net/ipv4/tcp.c | 12 ++++++++++++ net/rds/tcp_listen.c | 4 +--- net/sunrpc/xprtsock.c | 3 +-- 4 files changed, 15 insertions(+), 5 deletions(-)
include/linux/tcp.h +1 -0
@@ -499,6 +499,7 @@ int tcp_skb_shift(struct sk_buff *to, struct sk_buff *from, int pcount,void tcp_sock_set_cork (struct sock *sk,bool on);int tcp_sock_set_keepidle (struct sock *sk,int val); +int tcp_sock_set_keepintvl (struct sock *sk,int val);void tcp_sock_set_nodelay (struct sock *sk);void tcp_sock_set_quickack (struct sock *sk,int val);int tcp_sock_set_syncnt (struct sock *sk,int val);
net/ipv4/tcp.c +12 -0
@@ -2934,6 +2934,18 @@ int tcp_sock_set_keepidle(struct sock *sk, int val) }EXPORT_SYMBOL (tcp_sock_set_keepidle); +int tcp_sock_set_keepintvl (struct sock *sk,int val) +{ +if (val <1 || val >MAX_TCP_KEEPINTVL ) +return -EINVAL ; + +lock_sock (sk); +tcp_sk (sk)->keepalive_intvl = val *HZ ; +release_sock (sk); +return 0 ; +} +EXPORT_SYMBOL (tcp_sock_set_keepintvl); +/* * Socket option code for TCP. */
net/rds/tcp_listen.c +1 -3
@@ -53,12 +53,10 @@ int rds_tcp_keepalive(struct socket *sock) goto bail;tcp_sock_set_keepidle (sock->sk, keepidle); -/* KEEPINTVL is the interval between successive probes. We follow * the model in xs_tcp_finish_connecting() and re-use keepidle. */ - ret =kernel_setsockopt (sock,IPPROTO_TCP ,TCP_KEEPINTVL , - (char *)&keepidle,sizeof (keepidle)); +tcp_sock_set_keepintvl (sock->sk, keepidle); bail:return ret; }
net/sunrpc/xprtsock.c +1 -2
@@ -2108,8 +2108,7 @@ static void xs_tcp_set_socket_timeouts(struct rpc_xprt *xprt,/* TCP Keepalive options */ sock_set_keepalive (sock->sk);tcp_sock_set_keepidle (sock->sk, keepidle); -kernel_setsockopt (sock,SOL_TCP ,TCP_KEEPINTVL , - (char *)&keepidle,sizeof (keepidle)); +tcp_sock_set_keepintvl (sock->sk, keepidle);kernel_setsockopt (sock,SOL_TCP ,TCP_KEEPCNT , (char *)&keepcnt,sizeof (keepcnt));
Signature · 1 line
2.26.2
Christoph Hellwig
maintainerPATCH 17/28 tcp: add tcp_sock_set_keepcnt
In reply to Christoph HellwigAdd a helper to directly set the TCP_KEEPCNT sockopt from kernel space without going through a fake uaccess.
--- include/linux/tcp.h | 1 + net/ipv4/tcp.c | 12 ++++++++++++ net/rds/tcp.h | 2 +- net/rds/tcp_listen.c | 17 +++-------------- net/sunrpc/xprtsock.c | 3 +-- 5 files changed, 18 insertions(+), 17 deletions(-)
include/linux/tcp.h +1 -0
@@ -498,6 +498,7 @@ int tcp_skb_shift(struct sk_buff *to, struct sk_buff *from, int pcount, int shiftlen);void tcp_sock_set_cork (struct sock *sk,bool on); +int tcp_sock_set_keepcnt (struct sock *sk,int val);int tcp_sock_set_keepidle (struct sock *sk,int val);int tcp_sock_set_keepintvl (struct sock *sk,int val);void tcp_sock_set_nodelay (struct sock *sk);
net/ipv4/tcp.c +12 -0
@@ -2946,6 +2946,18 @@ int tcp_sock_set_keepintvl(struct sock *sk, int val) }EXPORT_SYMBOL (tcp_sock_set_keepintvl); +int tcp_sock_set_keepcnt (struct sock *sk,int val) +{ +if (val <1 || val >MAX_TCP_KEEPCNT ) +return -EINVAL ; + +lock_sock (sk); +tcp_sk (sk)->keepalive_probes = val; +release_sock (sk); +return 0 ; +} +EXPORT_SYMBOL (tcp_sock_set_keepcnt); +/* * Socket option code for TCP. */
net/rds/tcp.h +1 -1
@@ -70,7 +70,7 @@ struct socket *rds_tcp_listen_init(struct net *net, bool isv6);void rds_tcp_listen_stop (struct socket *sock,struct work_struct *acceptor);void rds_tcp_listen_data_ready (struct sock *sk);int rds_tcp_accept_one (struct socket *sock); -int rds_tcp_keepalive (struct socket *sock); +void rds_tcp_keepalive (struct socket *sock);void *rds_tcp_listen_sock_def_readable (struct net *net);/* tcp_recv.c */
net/rds/tcp_listen.c +3 -14
@@ -38,27 +38,19 @@#include "rds.h" #include "tcp.h" -int rds_tcp_keepalive (struct socket *sock) +void rds_tcp_keepalive (struct socket *sock) {/* values below based on xs_udp_default_timeout */ int keepidle =5 ;/* send a probe 'keepidle' secs after last data */ int keepcnt =5 ;/* number of unack'ed probes before declaring dead */ -int ret =0 ;sock_set_keepalive (sock->sk); - - ret =kernel_setsockopt (sock,IPPROTO_TCP ,TCP_KEEPCNT , - (char *)&keepcnt,sizeof (keepcnt)); -if (ret <0 ) - goto bail; - +tcp_sock_set_keepcnt (sock->sk, keepcnt);tcp_sock_set_keepidle (sock->sk, keepidle);/* KEEPINTVL is the interval between successive probes. We follow * the model in xs_tcp_finish_connecting() and re-use keepidle. */ tcp_sock_set_keepintvl (sock->sk, keepidle); -bail: -return ret; }/* rds_tcp_accept_one_path(): if accepting on cp_index > 0, make sure the
@@ -140,10 +132,7 @@ int rds_tcp_accept_one(struct socket *sock) new_sock->ops = sock->ops;__module_get (new_sock->ops->owner); - ret =rds_tcp_keepalive (new_sock); -if (ret <0 ) - goto out; - +rds_tcp_keepalive (new_sock);rds_tcp_tune (new_sock); inet =inet_sk (new_sock->sk);
net/sunrpc/xprtsock.c +1 -2
@@ -2109,8 +2109,7 @@ static void xs_tcp_set_socket_timeouts(struct rpc_xprt *xprt,sock_set_keepalive (sock->sk);tcp_sock_set_keepidle (sock->sk, keepidle);tcp_sock_set_keepintvl (sock->sk, keepidle); -kernel_setsockopt (sock,SOL_TCP ,TCP_KEEPCNT , - (char *)&keepcnt,sizeof (keepcnt)); +tcp_sock_set_keepcnt (sock->sk, keepcnt);/* TCP user timeout (see RFC5482) */ tcp_sock_set_user_timeout (sock->sk, timeo);
Signature · 1 line
2.26.2
Christoph Hellwig
maintainerPATCH 18/28 ipv4: add ip_sock_set_tos
In reply to Christoph HellwigAdd a helper to directly set the IP_TOS sockopt from kernel space without going through a fake uaccess.
--- drivers/nvme/host/tcp.c | 14 +++----------- drivers/nvme/target/tcp.c | 10 ++-------- include/net/ip.h | 2 ++ net/ipv4/ip_sockglue.c | 30 +++++++++++++++++++++--------- 4 files changed, 28 insertions(+), 28 deletions(-)
drivers/nvme/host/tcp.c +3 -11
@@ -1313,7 +1313,7 @@ static int nvme_tcp_alloc_queue(struct nvme_ctrl *nctrl, {struct nvme_tcp_ctrl *ctrl =to_tcp_ctrl (nctrl);struct nvme_tcp_queue *queue = &ctrl->queues[qid]; -int ret, opt, rcv_pdu_size; +int ret, rcv_pdu_size; queue->ctrl = ctrl;INIT_LIST_HEAD (&queue->send_list);
@@ -1352,16 +1352,8 @@ static int nvme_tcp_alloc_queue(struct nvme_ctrl *nctrl,sock_set_priority (queue->sock->sk, so_priority);/* Set socket type of service */ -if (nctrl->opts->tos >=0 ) { - opt = nctrl->opts->tos; - ret =kernel_setsockopt (queue->sock,SOL_IP ,IP_TOS , - (char *)&opt,sizeof (opt)); -if (ret) { -dev_err (nctrl->device, -"failed to set IP_TOS sock opt %d\n" , ret); - goto err_sock; - } - } +if (nctrl->opts->tos >=0 ) +ip_sock_set_tos (queue->sock->sk, nctrl->opts->tos); queue->sock->sk->sk_allocation =GFP_ATOMIC ;nvme_tcp_set_queue_io_cpu (queue);
drivers/nvme/target/tcp.c +2 -8
@@ -1452,14 +1452,8 @@ static int nvmet_tcp_set_queue_sock(struct nvmet_tcp_queue *queue)sock_set_priority (sock->sk, so_priority);/* Set socket type of service */ -if (inet->rcv_tos >0 ) { -int tos = inet->rcv_tos; - - ret =kernel_setsockopt (sock,SOL_IP ,IP_TOS , - (char *)&tos,sizeof (tos)); -if (ret) -return ret; - } +if (inet->rcv_tos >0 ) +ip_sock_set_tos (sock->sk, inet->rcv_tos);write_lock_bh (&sock->sk->sk_callback_lock); sock->sk->sk_user_data = queue;
include/net/ip.h +2 -0
@@ -765,4 +765,6 @@ static inline bool inetdev_valid_mtu(unsigned int mtu) return likely(mtu >= IPV4_MIN_MTU); } +void ip_sock_set_tos (struct sock *sk,int val); +#endif /* _IP_H */
net/ipv4/ip_sockglue.c +21 -9
@@ -560,6 +560,26 @@ int ip_recv_error(struct sock *sk, struct msghdr *msg, int len, int *addr_len)return err; } +static void __ip_sock_set_tos (struct sock *sk,int val) +{ +if (sk->sk_type ==SOCK_STREAM ) { + val &= ~INET_ECN_MASK ; + val |=inet_sk (sk)->tos &INET_ECN_MASK ; + } +if (inet_sk (sk)->tos != val) { +inet_sk (sk)->tos = val; + sk->sk_priority =rt_tos2priority (val); +sk_dst_reset (sk); + } +} + +void ip_sock_set_tos (struct sock *sk,int val) +{ +lock_sock (sk); +__ip_sock_set_tos (sk, val); +release_sock (sk); +} +EXPORT_SYMBOL (ip_sock_set_tos);/* * Socket option code for IP. This is the end of the line after any
@@ -823,15 +843,7 @@ static int do_ip_setsockopt(struct sock *sk, int level, inet->cmsg_flags &= ~IP_CMSG_RECVFRAGSIZE ;break ;case IP_TOS :/* This sets both TOS and Precedence */ -if (sk->sk_type ==SOCK_STREAM ) { - val &= ~INET_ECN_MASK ; - val |= inet->tos &INET_ECN_MASK ; - } -if (inet->tos != val) { - inet->tos = val; - sk->sk_priority =rt_tos2priority (val); -sk_dst_reset (sk); - } +__ip_sock_set_tos (sk, val);break ;case IP_TTL :if (optlen <1 )
Signature · 1 line
2.26.2
Christoph Hellwig
maintainerPATCH 19/28 ipv4: add ip_sock_set_freebind
In reply to Christoph HellwigAdd a helper to directly set the IP_FREEBIND sockopt from kernel space without going through a fake uaccess.
--- drivers/target/iscsi/iscsi_target_login.c | 13 +++---------- include/net/ip.h | 1 + net/ipv4/ip_sockglue.c | 8 ++++++++ 3 files changed, 12 insertions(+), 10 deletions(-)
drivers/target/iscsi/iscsi_target_login.c +3 -10
@@ -15,6 +15,7 @@#include <linux/sched/signal.h> #include <linux/idr.h> #include <linux/tcp.h> /* TCP_NODELAY */ +#include <net/ip.h> #include <net/ipv6.h> /* ipv6_addr_v4mapped() */ #include <scsi/iscsi_proto.h> #include <target/target_core_base.h>
@@ -855,7 +856,7 @@ int iscsit_setup_np( struct sockaddr_storage *sockaddr) {struct socket *sock =NULL ; -int backlog =ISCSIT_TCP_BACKLOG , ret, opt =0 , len; +int backlog =ISCSIT_TCP_BACKLOG , ret, len;switch (np->np_network_transport) {case ISCSI_TCP :
@@ -900,15 +901,7 @@ int iscsit_setup_np(if (np->np_network_transport ==ISCSI_TCP )tcp_sock_set_nodelay (sock->sk);sock_set_reuseaddr (sock->sk); - - opt =1 ; - ret =kernel_setsockopt (sock,IPPROTO_IP ,IP_FREEBIND , - (char *)&opt,sizeof (opt)); -if (ret <0 ) { -pr_err ("kernel_setsockopt() for IP_FREEBIND" -" failed\n" ); - goto fail; - } +ip_sock_set_freebind (sock->sk); ret =kernel_bind (sock, (struct sockaddr *)&np->np_sockaddr, len);if (ret <0 ) {
include/net/ip.h +1 -0
@@ -765,6 +765,7 @@ static inline bool inetdev_valid_mtu(unsigned int mtu) return likely(mtu >= IPV4_MIN_MTU); } +void ip_sock_set_freebind (struct sock *sk);void ip_sock_set_tos (struct sock *sk,int val);#endif /* _IP_H */
net/ipv4/ip_sockglue.c +8 -0
@@ -581,6 +581,14 @@ void ip_sock_set_tos(struct sock *sk, int val) }EXPORT_SYMBOL (ip_sock_set_tos); +void ip_sock_set_freebind (struct sock *sk) +{ +lock_sock (sk); +inet_sk (sk)->freebind = true; +release_sock (sk); +} +EXPORT_SYMBOL (ip_sock_set_freebind); +/* * Socket option code for IP. This is the end of the line after any * TCP,UDP etc options on an IP socket.
Signature · 1 line
2.26.2
Christoph Hellwig
maintainerPATCH 20/28 ipv4: add ip_sock_set_recverr
In reply to Christoph HellwigAdd a helper to directly set the IP_RECVERR sockopt from kernel space without going through a fake uaccess.
--- include/net/ip.h | 1 + net/ipv4/ip_sockglue.c | 8 ++++++++ net/rxrpc/local_object.c | 8 +------- 3 files changed, 10 insertions(+), 7 deletions(-)
include/net/ip.h +1 -0
@@ -766,6 +766,7 @@ static inline bool inetdev_valid_mtu(unsigned int mtu) }void ip_sock_set_freebind (struct sock *sk); +void ip_sock_set_recverr (struct sock *sk);void ip_sock_set_tos (struct sock *sk,int val);#endif /* _IP_H */
net/ipv4/ip_sockglue.c +8 -0
@@ -589,6 +589,14 @@ void ip_sock_set_freebind(struct sock *sk) }EXPORT_SYMBOL (ip_sock_set_freebind); +void ip_sock_set_recverr (struct sock *sk) +{ +lock_sock (sk); +inet_sk (sk)->recverr = true; +release_sock (sk); +} +EXPORT_SYMBOL (ip_sock_set_recverr); +/* * Socket option code for IP. This is the end of the line after any * TCP,UDP etc options on an IP socket.
net/rxrpc/local_object.c +1 -7
@@ -171,13 +171,7 @@ static int rxrpc_open_socket(struct rxrpc_local *local, struct net *net)/* Fall through */ case AF_INET :/* we want to receive ICMP errors */ - opt =1 ; - ret =kernel_setsockopt (local->socket,SOL_IP ,IP_RECVERR , - (char *) &opt,sizeof (opt)); -if (ret <0 ) { -_debug ("setsockopt failed" ); - goto error; - } +ip_sock_set_recverr (local->socket->sk);/* we want to set the don't fragment bit */ opt =IP_PMTUDISC_DO ;
Signature · 1 line
2.26.2
Christoph Hellwig
maintainerPATCH 21/28 ipv4: add ip_sock_set_mtu_discover
In reply to Christoph HellwigAdd a helper to directly set the IP_MTU_DISCOVER sockopt from kernel space without going through a fake uaccess.
--- include/net/ip.h | 1 + net/ipv4/ip_sockglue.c | 11 +++++++++++ net/rxrpc/local_object.c | 8 +------- net/rxrpc/output.c | 14 +++++--------- 4 files changed, 18 insertions(+), 16 deletions(-)
include/net/ip.h +1 -0
@@ -766,6 +766,7 @@ static inline bool inetdev_valid_mtu(unsigned int mtu) }void ip_sock_set_freebind (struct sock *sk); +int ip_sock_set_mtu_discover (struct sock *sk,int val);void ip_sock_set_recverr (struct sock *sk);void ip_sock_set_tos (struct sock *sk,int val);
net/ipv4/ip_sockglue.c +11 -0
@@ -597,6 +597,17 @@ void ip_sock_set_recverr(struct sock *sk) }EXPORT_SYMBOL (ip_sock_set_recverr); +int ip_sock_set_mtu_discover (struct sock *sk,int val) +{ +if (val <IP_PMTUDISC_DONT || val >IP_PMTUDISC_OMIT ) +return -EINVAL ; +lock_sock (sk); +inet_sk (sk)->pmtudisc = val; +release_sock (sk); +return 0 ; +} +EXPORT_SYMBOL (ip_sock_set_mtu_discover); +/* * Socket option code for IP. This is the end of the line after any * TCP,UDP etc options on an IP socket.
net/rxrpc/local_object.c +1 -7
@@ -174,13 +174,7 @@ static int rxrpc_open_socket(struct rxrpc_local *local, struct net *net)ip_sock_set_recverr (local->socket->sk);/* we want to set the don't fragment bit */ - opt =IP_PMTUDISC_DO ; - ret =kernel_setsockopt (local->socket,SOL_IP ,IP_MTU_DISCOVER , - (char *) &opt,sizeof (opt)); -if (ret <0 ) { -_debug ("setsockopt failed" ); - goto error; - } +ip_sock_set_mtu_discover (local->socket->sk,IP_PMTUDISC_DO );/* We want receive timestamps. */ sock_enable_timestamps (local->socket->sk);
net/rxrpc/output.c +5 -9
@@ -321,7 +321,7 @@ int rxrpc_send_data_packet(struct rxrpc_call *call, struct sk_buff *skb,struct kvec iov[2 ];rxrpc_serial_t serial;size_t len; -int ret, opt; +int ret;_enter (",{%d}" , skb->len);
@@ -473,18 +473,14 @@ int rxrpc_send_data_packet(struct rxrpc_call *call, struct sk_buff *skb,switch (conn->params.local->srx.transport.family) {case AF_INET6 :case AF_INET : - opt =IP_PMTUDISC_DONT ; -kernel_setsockopt (conn->params.local->socket, -SOL_IP ,IP_MTU_DISCOVER , - (char *)&opt,sizeof (opt)); +ip_sock_set_mtu_discover (conn->params.local->socket->sk, +IP_PMTUDISC_DONT ); ret =kernel_sendmsg (conn->params.local->socket, &msg, iov,2 , len); conn->params.peer->last_tx_at =ktime_get_seconds (); - opt =IP_PMTUDISC_DO ; -kernel_setsockopt (conn->params.local->socket, -SOL_IP ,IP_MTU_DISCOVER , - (char *)&opt,sizeof (opt)); +ip_sock_set_mtu_discover (conn->params.local->socket->sk, +IP_PMTUDISC_DO );break ;default :
Signature · 1 line
2.26.2
Christoph Hellwig
maintainerPATCH 22/28 ipv4: add ip_sock_set_pktinfo
In reply to Christoph HellwigAdd a helper to directly set the IP_PKTINFO sockopt from kernel space without going through a fake uaccess.
--- include/net/ip.h | 1 + net/ipv4/ip_sockglue.c | 8 ++++++++ net/sunrpc/svcsock.c | 5 ++--- 3 files changed, 11 insertions(+), 3 deletions(-)
include/net/ip.h +1 -0
@@ -767,6 +767,7 @@ static inline bool inetdev_valid_mtu(unsigned int mtu)void ip_sock_set_freebind (struct sock *sk);int ip_sock_set_mtu_discover (struct sock *sk,int val); +void ip_sock_set_pktinfo (struct sock *sk);void ip_sock_set_recverr (struct sock *sk);void ip_sock_set_tos (struct sock *sk,int val);
net/ipv4/ip_sockglue.c +8 -0
@@ -608,6 +608,14 @@ int ip_sock_set_mtu_discover(struct sock *sk, int val) }EXPORT_SYMBOL (ip_sock_set_mtu_discover); +void ip_sock_set_pktinfo (struct sock *sk) +{ +lock_sock (sk); +inet_sk (sk)->cmsg_flags |=IP_CMSG_PKTINFO ; +release_sock (sk); +} +EXPORT_SYMBOL (ip_sock_set_pktinfo); +/* * Socket option code for IP. This is the end of the line after any * TCP,UDP etc options on an IP socket.
net/sunrpc/svcsock.c +2 -3
@@ -616,9 +616,8 @@ static void svc_udp_init(struct svc_sock *svsk, struct svc_serv *serv)/* make sure we get destination address info */ switch (svsk->sk_sk->sk_family) {case AF_INET : - level =SOL_IP ; - optname =IP_PKTINFO ; -break ; +ip_sock_set_pktinfo (svsk->sk_sock->sk); +return ;case AF_INET6 : level =SOL_IPV6 ; optname =IPV6_RECVPKTINFO ;
Signature · 1 line
2.26.2
Christoph Hellwig
maintainerPATCH 23/28 ipv6: add ip6_sock_set_v6only
In reply to Christoph HellwigAdd a helper to directly set the IPV6_V6ONLY sockopt from kernel space without going through a fake uaccess.
--- include/net/ipv6.h | 11 +++++++++++ net/ipv6/ip6_udp_tunnel.c | 5 +---- net/sunrpc/svcsock.c | 6 +----- 3 files changed, 13 insertions(+), 9 deletions(-)
include/net/ipv6.h +11 -0
@@ -1177,4 +1177,15 @@ int ipv6_sock_mc_join_ssm(struct sock *sk, int ifindex, const struct in6_addr *addr, unsigned int mode);int ipv6_sock_mc_drop (struct sock *sk,int ifindex,const struct in6_addr *addr); + +static inline int ip6_sock_set_v6only (struct sock *sk) +{ +if (inet_sk (sk)->inet_num) +return -EINVAL ; +lock_sock (sk); + sk->sk_ipv6only = true; +release_sock (sk); +return 0 ; +} +#endif /* _NET_IPV6_H */
net/ipv6/ip6_udp_tunnel.c +1 -4
@@ -25,10 +25,7 @@ int udp_sock_create6(struct net *net, struct udp_port_cfg *cfg, goto error;if (cfg->ipv6_v6only) { -int val =1 ; - - err =kernel_setsockopt (sock,IPPROTO_IPV6 ,IPV6_V6ONLY , - (char *) &val,sizeof (val)); + err =ip6_sock_set_v6only (sock->sk);if (err <0 ) goto error; }
net/sunrpc/svcsock.c +1 -5
@@ -1328,7 +1328,6 @@ static struct svc_xprt *svc_create_socket(struct svc_serv *serv,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",
@@ -1364,11 +1363,8 @@ static struct svc_xprt *svc_create_socket(struct svc_serv *serv,* 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)); - +ip6_sock_set_v6only (sock->sk);if (type ==SOCK_STREAM ) sock->sk->sk_reuse =SK_CAN_REUSE ;/* allow address reuse */ error =kernel_bind (sock, sin, len);
Signature · 1 line
2.26.2
Christoph Hellwig
maintainerPATCH 24/28 ipv6: add ip6_sock_set_recverr
In reply to Christoph HellwigAdd a helper to directly set the IPV6_RECVERR sockopt from kernel space without going through a fake uaccess.
--- include/net/ipv6.h | 7 +++++++ net/rxrpc/local_object.c | 10 ++-------- 2 files changed, 9 insertions(+), 8 deletions(-)
include/net/ipv6.h +7 -0
@@ -1188,4 +1188,11 @@ static inline int ip6_sock_set_v6only(struct sock *sk) return 0; } +static inline void ip6_sock_set_recverr (struct sock *sk) +{ +lock_sock (sk); +inet6_sk (sk)->recverr = true; +release_sock (sk); +} +#endif /* _NET_IPV6_H */
net/rxrpc/local_object.c +2 -8
@@ -107,7 +107,7 @@ static struct rxrpc_local *rxrpc_alloc_local(struct rxrpc_net *rxnet,static int rxrpc_open_socket (struct rxrpc_local *local,struct net *net) {struct sock *usk; -int ret, opt; +int ret;_enter ("%p{%d,%d}" , local, local->srx.transport_type, local->srx.transport.family);
@@ -157,13 +157,7 @@ static int rxrpc_open_socket(struct rxrpc_local *local, struct net *net)switch (local->srx.transport.family) {case AF_INET6 :/* we want to receive ICMPv6 errors */ - opt =1 ; - ret =kernel_setsockopt (local->socket,SOL_IPV6 ,IPV6_RECVERR , - (char *) &opt,sizeof (opt)); -if (ret <0 ) { -_debug ("setsockopt failed" ); - goto error; - } +ip6_sock_set_recverr (local->socket->sk);/* Fall through and set IPv4 options too otherwise we don't get * errors from IPv4 packets sent through the IPv6 socket.
Signature · 1 line
2.26.2
Christoph Hellwig
maintainerPATCH 25/28 ipv6: add ip6_sock_set_addr_preferences
In reply to Christoph HellwigAdd a helper to directly set the IPV6_ADD_PREFERENCES sockopt from kernel space without going through a fake uaccess.
--- include/net/ipv6.h | 67 ++++++++++++++++++++++++++++++++++++++++ net/ipv6/ipv6_sockglue.c | 59 +---------------------------------- net/sunrpc/xprtsock.c | 7 +++-- 3 files changed, 72 insertions(+), 61 deletions(-)
include/net/ipv6.h +67 -0
@@ -1195,4 +1195,71 @@ static inline void ip6_sock_set_recverr(struct sock *sk)release_sock (sk); } +static inline int __ip6_sock_set_addr_preferences (struct sock *sk,int val) +{ +unsigned int pref =0 ; +unsigned int prefmask = ~0 ; + +/* check PUBLIC/TMP/PUBTMP_DEFAULT conflicts */ +switch (val & (IPV6_PREFER_SRC_PUBLIC | +IPV6_PREFER_SRC_TMP | +IPV6_PREFER_SRC_PUBTMP_DEFAULT )) { +case IPV6_PREFER_SRC_PUBLIC : + pref |=IPV6_PREFER_SRC_PUBLIC ; + prefmask &= ~(IPV6_PREFER_SRC_PUBLIC | +IPV6_PREFER_SRC_TMP ); +break ; +case IPV6_PREFER_SRC_TMP : + pref |=IPV6_PREFER_SRC_TMP ; + prefmask &= ~(IPV6_PREFER_SRC_PUBLIC | +IPV6_PREFER_SRC_TMP ); +break ; +case IPV6_PREFER_SRC_PUBTMP_DEFAULT : + prefmask &= ~(IPV6_PREFER_SRC_PUBLIC | +IPV6_PREFER_SRC_TMP ); +break ; +case 0 : +break ; +default : +return -EINVAL ; + } + +/* check HOME/COA conflicts */ +switch (val & (IPV6_PREFER_SRC_HOME |IPV6_PREFER_SRC_COA )) { +case IPV6_PREFER_SRC_HOME : + prefmask &= ~IPV6_PREFER_SRC_COA ; +break ; +case IPV6_PREFER_SRC_COA : + pref |=IPV6_PREFER_SRC_COA ; +break ; +case 0 : +break ; +default : +return -EINVAL ; + } + +/* check CGA/NONCGA conflicts */ +switch (val & (IPV6_PREFER_SRC_CGA |IPV6_PREFER_SRC_NONCGA )) { +case IPV6_PREFER_SRC_CGA : +case IPV6_PREFER_SRC_NONCGA : +case 0 : +break ; +default : +return -EINVAL ; + } + +inet6_sk (sk)->srcprefs = (inet6_sk (sk)->srcprefs & prefmask) | pref; +return 0 ; +} + +static inline int ip6_sock_set_addr_preferences (struct sock *sk,bool val) +{ +int ret; + +lock_sock (sk); + ret =__ip6_sock_set_addr_preferences (sk, val); +release_sock (sk); +return ret; +} +#endif /* _NET_IPV6_H */
net/ipv6/ipv6_sockglue.c +1 -58
68 lines not on this page · raw message
net/sunrpc/xprtsock.c +4 -3
@@ -2150,7 +2150,6 @@ static int xs_tcp_finish_connecting(struct rpc_xprt *xprt, struct socket *sock)if (!transport->inet) {struct sock *sk = sock->sk; -unsigned int addr_pref =IPV6_PREFER_SRC_PUBLIC ;/* Avoid temporary address, they are bad for long-lived * connections such as NFS mounts.
@@ -2159,8 +2158,10 @@ static int xs_tcp_finish_connecting(struct rpc_xprt *xprt, struct socket *sock)* knowledge about the normal duration of connections, * MAY override this as appropriate. */ -kernel_setsockopt (sock,SOL_IPV6 ,IPV6_ADDR_PREFERENCES , - (char *)&addr_pref,sizeof (addr_pref)); +if (xs_addr (xprt)->sa_family ==PF_INET6 ) { +ip6_sock_set_addr_preferences (sk, +IPV6_PREFER_SRC_PUBLIC ); + }xs_tcp_set_socket_timeouts (xprt, sock);
Signature · 1 line
2.26.2
Christoph Hellwig
maintainerPATCH 26/28 ipv6: add ip6_sock_set_recvpktinfo
In reply to Christoph HellwigAdd a helper to directly set the IPV6_RECVPKTINFO sockopt from kernel space without going through a fake uaccess.
--- include/net/ipv6.h | 7 +++++++ net/sunrpc/svcsock.c | 10 ++-------- 2 files changed, 9 insertions(+), 8 deletions(-)
include/net/ipv6.h +7 -0
@@ -1262,4 +1262,11 @@ static inline int ip6_sock_set_addr_preferences(struct sock *sk, bool val) return ret; } +static inline void ip6_sock_set_recvpktinfo (struct sock *sk) +{ +lock_sock (sk); +inet6_sk (sk)->rxopt.bits.rxinfo = true; +release_sock (sk); +} +#endif /* _NET_IPV6_H */
net/sunrpc/svcsock.c +2 -8
@@ -595,8 +595,6 @@ static struct svc_xprt_class svc_udp_class = {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);
@@ -617,17 +615,13 @@ static void svc_udp_init(struct svc_sock *svsk, struct svc_serv *serv)switch (svsk->sk_sk->sk_family) {case AF_INET :ip_sock_set_pktinfo (svsk->sk_sock->sk); -return ; +break ;case AF_INET6 : - level =SOL_IPV6 ; - optname =IPV6_RECVPKTINFO ; +ip6_sock_set_recvpktinfo (svsk->sk_sock->sk);break ;default :BUG (); } - err =kernel_setsockopt (svsk->sk_sock, level, optname, - (char *)&one,sizeof (one)); -dprintk ("svc: kernel_setsockopt returned %d\n" , err); }/*
Signature · 1 line
2.26.2
Christoph Hellwig
maintainerPATCH 27/28 rxrpc: add rxrpc_sock_set_min_security_level
In reply to Christoph HellwigAdd a helper to directly set the RXRPC_MIN_SECURITY_LEVEL sockopt from kernel space without going through a fake uaccess.
Thanks to David Howells for the documentation updates.
--- Documentation/networking/rxrpc.rst | 13 +++++++++++-- fs/afs/rxrpc.c | 6 ++---- include/net/af_rxrpc.h | 2 ++ net/rxrpc/af_rxrpc.c | 13 +++++++++++++ 4 files changed, 28 insertions(+), 6 deletions(-)
Documentation/networking/rxrpc.rst +11 -2
@@ -477,7 +477,7 @@ AF_RXRPC sockets support a few socket options at the SOL_RXRPC level: Encrypted checksum plus packet padded and first eight bytes of packet encrypted - which includes the actual packet length. - (c) RXRPC_SECURITY_ENCRYPTED + (c) RXRPC_SECURITY_ENCRYPT Encrypted checksum plus entire packet padded and encrypted, including actual packet length.
@@ -578,7 +578,7 @@ A client would issue an operation by: This issues a request_key() to get the key representing the security context. The minimum security level can be set:: - unsigned int sec = RXRPC_SECURITY_ENCRYPTED; + unsigned int sec = RXRPC_SECURITY_ENCRYPT; setsockopt(client, SOL_RXRPC, RXRPC_MIN_SECURITY_LEVEL, &sec, sizeof(sec));
@@ -1090,6 +1090,15 @@ The kernel interface functions are as follows: jiffies). In the event of the timeout occurring, the call will be aborted and -ETIME or -ETIMEDOUT will be returned. + (#) Apply the RXRPC_MIN_SECURITY_LEVEL sockopt to a socket from within in the + kernel:: + + int rxrpc_sock_set_min_security_level(struct sock *sk, + unsigned int val); + + This specifies the minimum security level required for calls on this + socket. + Configurable Parameters =======================
fs/afs/rxrpc.c +2 -4
@@ -37,7 +37,6 @@ int afs_open_socket(struct afs_net *net) {struct sockaddr_rxrpc srx;struct socket *socket; -unsigned int min_level;int ret;_enter ("" );
@@ -57,9 +56,8 @@ int afs_open_socket(struct afs_net *net) srx.transport.sin6.sin6_family =AF_INET6 ; srx.transport.sin6.sin6_port =htons (AFS_CM_PORT ); - min_level =RXRPC_SECURITY_ENCRYPT ; - ret =kernel_setsockopt (socket,SOL_RXRPC ,RXRPC_MIN_SECURITY_LEVEL , - (void *)&min_level,sizeof (min_level)); + ret =rxrpc_sock_set_min_security_level (socket->sk, +RXRPC_SECURITY_ENCRYPT );if (ret <0 ) goto error_2;
include/net/af_rxrpc.h +2 -0
@@ -72,4 +72,6 @@ bool rxrpc_kernel_call_is_complete(struct rxrpc_call *);void rxrpc_kernel_set_max_life (struct socket *,struct rxrpc_call *,unsigned long ); +int rxrpc_sock_set_min_security_level (struct sock *sk,unsigned int val); +#endif /* _NET_RXRPC_H */
net/rxrpc/af_rxrpc.c +13 -0
@@ -571,6 +571,19 @@ static int rxrpc_sendmsg(struct socket *sock, struct msghdr *m, size_t len)return ret; } +int rxrpc_sock_set_min_security_level (struct sock *sk,unsigned int val) +{ +if (sk->sk_state !=RXRPC_UNBOUND ) +return -EISCONN ; +if (val >RXRPC_SECURITY_MAX ) +return -EINVAL ; +lock_sock (sk); +rxrpc_sk (sk)->min_sec_level = val; +release_sock (sk); +return 0 ; +} +EXPORT_SYMBOL (rxrpc_sock_set_min_security_level); +/* * set RxRPC socket options */
Signature · 1 line
2.26.2
Christoph Hellwig
maintainerPATCH 28/28 tipc: call tsk_set_importance from tipc_topsrv_create_listener
In reply to Christoph HellwigAvoid using kernel_setsockopt for the TIPC_IMPORTANCE option when we can just use the internal helper. The only change needed is to pass a struct sock instead of tipc_sock, which is private to socket.c
--- net/tipc/socket.c | 18 +++++++++--------- net/tipc/socket.h | 2 ++ net/tipc/topsrv.c | 6 +++--- 3 files changed, 14 insertions(+), 12 deletions(-)
net/tipc/socket.c +9 -9
@@ -196,17 +196,17 @@ static int tsk_importance(struct tipc_sock *tsk)return msg_importance (&tsk->phdr); } -static int tsk_set_importance (struct tipc_sock *tsk,int imp) +static struct tipc_sock *tipc_sk (const struct sock *sk) { -if (imp >TIPC_CRITICAL_IMPORTANCE ) -return -EINVAL ; -msg_set_importance (&tsk->phdr, (u32 )imp); -return 0 ; + return container_of(sk, struct tipc_sock, sk); } -static struct tipc_sock *tipc_sk (const struct sock *sk) +int tsk_set_importance (struct sock *sk,int imp) { - return container_of(sk, struct tipc_sock, sk); +if (imp >TIPC_CRITICAL_IMPORTANCE ) +return -EINVAL ; +msg_set_importance (&tipc_sk (sk)->phdr, (u32 )imp); +return 0 ; }static bool tsk_conn_cong (struct tipc_sock *tsk)
@@ -2721,7 +2721,7 @@ static int tipc_accept(struct socket *sock, struct socket *new_sock, int flags,/* Connect new socket to it's peer */ tipc_sk_finish_conn (new_tsock,msg_origport (msg),msg_orignode (msg)); -tsk_set_importance (new_tsock,msg_importance (msg)); +tsk_set_importance (new_sk,msg_importance (msg));if (msg_named (msg)) { new_tsock->conn_type =msg_nametype (msg); new_tsock->conn_instance =msg_nameinst (msg);
@@ -3139,7 +3139,7 @@ static int tipc_setsockopt(struct socket *sock, int lvl, int opt,switch (opt) {case TIPC_IMPORTANCE : - res =tsk_set_importance (tsk, value); + res =tsk_set_importance (sk, value);break ;case TIPC_SRC_DROPPABLE :if (sock->type !=SOCK_STREAM )
net/tipc/socket.h +2 -0
@@ -75,4 +75,6 @@ u32 tipc_sock_get_portid(struct sock *sk);bool tipc_sk_overlimit1 (struct sock *sk,struct sk_buff *skb);bool tipc_sk_overlimit2 (struct sock *sk,struct sk_buff *skb); +int tsk_set_importance (struct sock *sk,int imp); +#endif
net/tipc/topsrv.c +3 -3
@@ -497,7 +497,6 @@ static void tipc_topsrv_listener_data_ready(struct sock *sk)static int tipc_topsrv_create_listener (struct tipc_topsrv *srv) { -int imp =TIPC_CRITICAL_IMPORTANCE ;struct socket *lsock =NULL ;struct sockaddr_tipc saddr;struct sock *sk;
@@ -514,8 +513,9 @@ static int tipc_topsrv_create_listener(struct tipc_topsrv *srv) sk->sk_user_data = srv;write_unlock_bh (&sk->sk_callback_lock); - rc =kernel_setsockopt (lsock,SOL_TIPC ,TIPC_IMPORTANCE , - (char *)&imp,sizeof (imp)); +lock_sock (sk); + rc =tsk_set_importance (sk,TIPC_CRITICAL_IMPORTANCE ); +release_sock (sk);if (rc <0 ) goto err;
Signature · 1 line
2.26.2
David Miller
maintainerFrom: Christoph Hellwig <[email protected]>
Date: Thu, 28 May 2020 07:12:08 +0200
Quoted 9 lines
this series removes most callers of the
kernel_setsockoptfunctions, and instead switches their users to small functions that implement setting a sockopt directly using a normal kernel function call with type safety and all the other benefits of not having a function call.In some cases these functions seem pretty heavy handed as they do a
lock_sockeven for just setting a single variable, but this mirrors the real setsockopt implementation unlike a few drivers that just set set the fields directly.
...
Series applied, thanks Christoph.