From a6a6fe27bab48f0d09a64b051e7bde432fcae081 Mon Sep 17 00:00:00 2001 From: "D. Wythe" Date: Thu, 10 Feb 2022 17:11:37 +0800 Subject: net/smc: Dynamic control handshake limitation by socket options This patch aims to add dynamic control for SMC handshake limitation for every smc sockets, in production environment, it is possible for the same applications to handle different service types, and may have different opinion on SMC handshake limitation. This patch try socket options to complete it, since we don't have socket option level for SMC yet, which requires us to implement it at the same time. This patch does the following: - add new socket option level: SOL_SMC. - add new SMC socket option: SMC_LIMIT_HS. - provide getter/setter for SMC socket options. Link: https://lore.kernel.org/all/20f504f961e1a803f85d64229ad84260434203bd.1644323503.git.alibuda@linux.alibaba.com/ Signed-off-by: D. Wythe Signed-off-by: David S. Miller --- include/linux/socket.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux/socket.h') diff --git a/include/linux/socket.h b/include/linux/socket.h index 8ef26d89ef49..6f85f5d957ef 100644 --- a/include/linux/socket.h +++ b/include/linux/socket.h @@ -366,6 +366,7 @@ struct ucred { #define SOL_XDP 283 #define SOL_MPTCP 284 #define SOL_MCTP 285 +#define SOL_SMC 286 /* IPX options */ #define IPX_TYPE 1 -- cgit From da214a475f8bd1d3e9e7a19ddfeb4d1617551bab Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Tue, 12 Apr 2022 14:22:39 -0600 Subject: net: add __sys_socket_file() This works like __sys_socket(), except instead of allocating and returning a socket fd, it just returns the file associated with the socket. No fd is installed into the process file table. This is similar to do_accept(), and allows io_uring to use this without instantiating a file descriptor in the process file table. Signed-off-by: Jens Axboe Acked-by: David S. Miller Link: https://lore.kernel.org/r/20220412202240.234207-2-axboe@kernel.dk --- include/linux/socket.h | 1 + net/socket.c | 52 ++++++++++++++++++++++++++++++++++++++++---------- 2 files changed, 43 insertions(+), 10 deletions(-) (limited to 'include/linux/socket.h') diff --git a/include/linux/socket.h b/include/linux/socket.h index 6f85f5d957ef..a1882e1e71d2 100644 --- a/include/linux/socket.h +++ b/include/linux/socket.h @@ -434,6 +434,7 @@ extern struct file *do_accept(struct file *file, unsigned file_flags, extern int __sys_accept4(int fd, struct sockaddr __user *upeer_sockaddr, int __user *upeer_addrlen, int flags); extern int __sys_socket(int family, int type, int protocol); +extern struct file *__sys_socket_file(int family, int type, int protocol); extern int __sys_bind(int fd, struct sockaddr __user *umyaddr, int addrlen); extern int __sys_connect_file(struct file *file, struct sockaddr_storage *addr, int addrlen, int file_flags); diff --git a/net/socket.c b/net/socket.c index 6887840682bb..bb6a1a12fbde 100644 --- a/net/socket.c +++ b/net/socket.c @@ -504,7 +504,7 @@ static int sock_map_fd(struct socket *sock, int flags) struct socket *sock_from_file(struct file *file) { if (file->f_op == &socket_file_ops) - return file->private_data; /* set in sock_map_fd */ + return file->private_data; /* set in sock_alloc_file */ return NULL; } @@ -1538,11 +1538,10 @@ int sock_create_kern(struct net *net, int family, int type, int protocol, struct } EXPORT_SYMBOL(sock_create_kern); -int __sys_socket(int family, int type, int protocol) +static struct socket *__sys_socket_create(int family, int type, int protocol) { - int retval; struct socket *sock; - int flags; + int retval; /* Check the SOCK_* constants for consistency. */ BUILD_BUG_ON(SOCK_CLOEXEC != O_CLOEXEC); @@ -1550,17 +1549,50 @@ int __sys_socket(int family, int type, int protocol) BUILD_BUG_ON(SOCK_CLOEXEC & SOCK_TYPE_MASK); BUILD_BUG_ON(SOCK_NONBLOCK & SOCK_TYPE_MASK); - flags = type & ~SOCK_TYPE_MASK; - if (flags & ~(SOCK_CLOEXEC | SOCK_NONBLOCK)) - return -EINVAL; + if ((type & ~SOCK_TYPE_MASK) & ~(SOCK_CLOEXEC | SOCK_NONBLOCK)) + return ERR_PTR(-EINVAL); type &= SOCK_TYPE_MASK; + retval = sock_create(family, type, protocol, &sock); + if (retval < 0) + return ERR_PTR(retval); + + return sock; +} + +struct file *__sys_socket_file(int family, int type, int protocol) +{ + struct socket *sock; + struct file *file; + int flags; + + sock = __sys_socket_create(family, type, protocol); + if (IS_ERR(sock)) + return ERR_CAST(sock); + + flags = type & ~SOCK_TYPE_MASK; if (SOCK_NONBLOCK != O_NONBLOCK && (flags & SOCK_NONBLOCK)) flags = (flags & ~SOCK_NONBLOCK) | O_NONBLOCK; - retval = sock_create(family, type, protocol, &sock); - if (retval < 0) - return retval; + file = sock_alloc_file(sock, flags, NULL); + if (IS_ERR(file)) + sock_release(sock); + + return file; +} + +int __sys_socket(int family, int type, int protocol) +{ + struct socket *sock; + int flags; + + sock = __sys_socket_create(family, type, protocol); + if (IS_ERR(sock)) + return PTR_ERR(sock); + + flags = type & ~SOCK_TYPE_MASK; + if (SOCK_NONBLOCK != O_NONBLOCK && (flags & SOCK_NONBLOCK)) + flags = (flags & ~SOCK_NONBLOCK) | O_NONBLOCK; return sock_map_fd(sock, flags & (O_CLOEXEC | O_NONBLOCK)); } -- cgit From f94fd25cb0aaf77fd7453f31c5d394a1a68ecf60 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Thu, 28 Apr 2022 18:45:06 -0600 Subject: tcp: pass back data left in socket after receive This is currently done for CMSG_INQ, add an ability to do so via struct msghdr as well and have CMSG_INQ use that too. If the caller sets msghdr->msg_get_inq, then we'll pass back the hint in msghdr->msg_inq. Rearrange struct msghdr a bit so we can add this member while shrinking it at the same time. On a 64-bit build, it was 96 bytes before this change and 88 bytes afterwards. Reviewed-by: Eric Dumazet Signed-off-by: Jens Axboe Link: https://lore.kernel.org/r/650c22ca-cffc-0255-9a05-2413a1e20826@kernel.dk Signed-off-by: Jakub Kicinski --- include/linux/socket.h | 6 +++++- net/ipv4/tcp.c | 16 ++++++++++------ 2 files changed, 15 insertions(+), 7 deletions(-) (limited to 'include/linux/socket.h') diff --git a/include/linux/socket.h b/include/linux/socket.h index 6f85f5d957ef..12085c9a8544 100644 --- a/include/linux/socket.h +++ b/include/linux/socket.h @@ -50,6 +50,9 @@ struct linger { struct msghdr { void *msg_name; /* ptr to socket address structure */ int msg_namelen; /* size of socket address structure */ + + int msg_inq; /* output, data left in socket */ + struct iov_iter msg_iter; /* data */ /* @@ -62,8 +65,9 @@ struct msghdr { void __user *msg_control_user; }; bool msg_control_is_user : 1; - __kernel_size_t msg_controllen; /* ancillary data buffer length */ + bool msg_get_inq : 1;/* return INQ after receive */ unsigned int msg_flags; /* flags on received message */ + __kernel_size_t msg_controllen; /* ancillary data buffer length */ struct kiocb *msg_iocb; /* ptr to iocb for async requests */ }; diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index cf18fbcbf123..bb7ef45408e1 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -2335,8 +2335,10 @@ static int tcp_recvmsg_locked(struct sock *sk, struct msghdr *msg, size_t len, if (sk->sk_state == TCP_LISTEN) goto out; - if (tp->recvmsg_inq) + if (tp->recvmsg_inq) { *cmsg_flags = TCP_CMSG_INQ; + msg->msg_get_inq = 1; + } timeo = sock_rcvtimeo(sk, nonblock); /* Urgent data needs to be handled specially. */ @@ -2559,7 +2561,7 @@ recv_sndq: int tcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int nonblock, int flags, int *addr_len) { - int cmsg_flags = 0, ret, inq; + int cmsg_flags = 0, ret; struct scm_timestamping_internal tss; if (unlikely(flags & MSG_ERRQUEUE)) @@ -2576,12 +2578,14 @@ int tcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int nonblock, release_sock(sk); sk_defer_free_flush(sk); - if (cmsg_flags && ret >= 0) { + if ((cmsg_flags || msg->msg_get_inq) && ret >= 0) { if (cmsg_flags & TCP_CMSG_TS) tcp_recv_timestamp(msg, sk, &tss); - if (cmsg_flags & TCP_CMSG_INQ) { - inq = tcp_inq_hint(sk); - put_cmsg(msg, SOL_TCP, TCP_CM_INQ, sizeof(inq), &inq); + if (msg->msg_get_inq) { + msg->msg_inq = tcp_inq_hint(sk); + if (cmsg_flags & TCP_CMSG_INQ) + put_cmsg(msg, SOL_TCP, TCP_CM_INQ, + sizeof(msg->msg_inq), &msg->msg_inq); } } return ret; -- cgit