diff options
Diffstat (limited to 'net/smc')
-rw-r--r-- | net/smc/Makefile | 2 | ||||
-rw-r--r-- | net/smc/af_smc.c | 162 | ||||
-rw-r--r-- | net/smc/smc.h | 38 | ||||
-rw-r--r-- | net/smc/smc_core.c | 7 | ||||
-rw-r--r-- | net/smc/smc_inet.c | 159 | ||||
-rw-r--r-- | net/smc/smc_inet.h | 22 |
6 files changed, 316 insertions, 74 deletions
diff --git a/net/smc/Makefile b/net/smc/Makefile index 2c510d543058..60f1c87d5212 100644 --- a/net/smc/Makefile +++ b/net/smc/Makefile @@ -4,6 +4,6 @@ obj-$(CONFIG_SMC) += smc.o obj-$(CONFIG_SMC_DIAG) += smc_diag.o smc-y := af_smc.o smc_pnet.o smc_ib.o smc_clc.o smc_core.o smc_wr.o smc_llc.o smc-y += smc_cdc.o smc_tx.o smc_rx.o smc_close.o smc_ism.o smc_netlink.o smc_stats.o -smc-y += smc_tracepoint.o +smc-y += smc_tracepoint.o smc_inet.o smc-$(CONFIG_SYSCTL) += smc_sysctl.o smc-$(CONFIG_SMC_LO) += smc_loopback.o diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c index c5f98c6b2561..73a875573e7a 100644 --- a/net/smc/af_smc.c +++ b/net/smc/af_smc.c @@ -54,6 +54,7 @@ #include "smc_tracepoint.h" #include "smc_sysctl.h" #include "smc_loopback.h" +#include "smc_inet.h" static DEFINE_MUTEX(smc_server_lgr_pending); /* serialize link group * creation on server @@ -170,15 +171,15 @@ static bool smc_hs_congested(const struct sock *sk) return false; } -static struct smc_hashinfo smc_v4_hashinfo = { +struct smc_hashinfo smc_v4_hashinfo = { .lock = __RW_LOCK_UNLOCKED(smc_v4_hashinfo.lock), }; -static struct smc_hashinfo smc_v6_hashinfo = { +struct smc_hashinfo smc_v6_hashinfo = { .lock = __RW_LOCK_UNLOCKED(smc_v6_hashinfo.lock), }; -static int smc_hash_sk(struct sock *sk) +int smc_hash_sk(struct sock *sk) { struct smc_hashinfo *h = sk->sk_prot->h.smc_hash; struct hlist_head *head; @@ -193,7 +194,7 @@ static int smc_hash_sk(struct sock *sk) return 0; } -static void smc_unhash_sk(struct sock *sk) +void smc_unhash_sk(struct sock *sk) { struct smc_hashinfo *h = sk->sk_prot->h.smc_hash; @@ -207,7 +208,7 @@ static void smc_unhash_sk(struct sock *sk) * work which we didn't do because of user hold the sock_lock in the * BH context */ -static void smc_release_cb(struct sock *sk) +void smc_release_cb(struct sock *sk) { struct smc_sock *smc = smc_sk(sk); @@ -307,7 +308,7 @@ static int __smc_release(struct smc_sock *smc) return rc; } -static int smc_release(struct socket *sock) +int smc_release(struct socket *sock) { struct sock *sk = sock->sk; struct smc_sock *smc; @@ -361,25 +362,15 @@ static void smc_destruct(struct sock *sk) return; } -static struct sock *smc_sock_alloc(struct net *net, struct socket *sock, - int protocol) +void smc_sk_init(struct net *net, struct sock *sk, int protocol) { - struct smc_sock *smc; - struct proto *prot; - struct sock *sk; - - prot = (protocol == SMCPROTO_SMC6) ? &smc_proto6 : &smc_proto; - sk = sk_alloc(net, PF_SMC, GFP_KERNEL, prot, 0); - if (!sk) - return NULL; + struct smc_sock *smc = smc_sk(sk); - sock_init_data(sock, sk); /* sets sk_refcnt to 1 */ sk->sk_state = SMC_INIT; sk->sk_destruct = smc_destruct; sk->sk_protocol = protocol; WRITE_ONCE(sk->sk_sndbuf, 2 * READ_ONCE(net->smc.sysctl_wmem)); WRITE_ONCE(sk->sk_rcvbuf, 2 * READ_ONCE(net->smc.sysctl_rmem)); - smc = smc_sk(sk); INIT_WORK(&smc->tcp_listen_work, smc_tcp_listen_work); INIT_WORK(&smc->connect_work, smc_connect_work); INIT_DELAYED_WORK(&smc->conn.tx_work, smc_tx_work); @@ -389,12 +380,30 @@ static struct sock *smc_sock_alloc(struct net *net, struct socket *sock, sk->sk_prot->hash(sk); mutex_init(&smc->clcsock_release_lock); smc_init_saved_callbacks(smc); + smc->limit_smc_hs = net->smc.limit_smc_hs; + smc->use_fallback = false; /* assume rdma capability first */ + smc->fallback_rsn = 0; +} + +static struct sock *smc_sock_alloc(struct net *net, struct socket *sock, + int protocol) +{ + struct proto *prot; + struct sock *sk; + + prot = (protocol == SMCPROTO_SMC6) ? &smc_proto6 : &smc_proto; + sk = sk_alloc(net, PF_SMC, GFP_KERNEL, prot, 0); + if (!sk) + return NULL; + + sock_init_data(sock, sk); /* sets sk_refcnt to 1 */ + smc_sk_init(net, sk, protocol); return sk; } -static int smc_bind(struct socket *sock, struct sockaddr *uaddr, - int addr_len) +int smc_bind(struct socket *sock, struct sockaddr *uaddr, + int addr_len) { struct sockaddr_in *addr = (struct sockaddr_in *)uaddr; struct sock *sk = sock->sk; @@ -1623,8 +1632,8 @@ out: release_sock(&smc->sk); } -static int smc_connect(struct socket *sock, struct sockaddr *addr, - int alen, int flags) +int smc_connect(struct socket *sock, struct sockaddr *addr, + int alen, int flags) { struct sock *sk = sock->sk; struct smc_sock *smc; @@ -2605,7 +2614,7 @@ out: read_unlock_bh(&listen_clcsock->sk_callback_lock); } -static int smc_listen(struct socket *sock, int backlog) +int smc_listen(struct socket *sock, int backlog) { struct sock *sk = sock->sk; struct smc_sock *smc; @@ -2670,8 +2679,8 @@ out: return rc; } -static int smc_accept(struct socket *sock, struct socket *new_sock, - struct proto_accept_arg *arg) +int smc_accept(struct socket *sock, struct socket *new_sock, + struct proto_accept_arg *arg) { struct sock *sk = sock->sk, *nsk; DECLARE_WAITQUEUE(wait, current); @@ -2740,8 +2749,8 @@ out: return rc; } -static int smc_getname(struct socket *sock, struct sockaddr *addr, - int peer) +int smc_getname(struct socket *sock, struct sockaddr *addr, + int peer) { struct smc_sock *smc; @@ -2754,7 +2763,7 @@ static int smc_getname(struct socket *sock, struct sockaddr *addr, return smc->clcsock->ops->getname(smc->clcsock, addr, peer); } -static int smc_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) +int smc_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) { struct sock *sk = sock->sk; struct smc_sock *smc; @@ -2792,8 +2801,8 @@ out: return rc; } -static int smc_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, - int flags) +int smc_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, + int flags) { struct sock *sk = sock->sk; struct smc_sock *smc; @@ -2842,8 +2851,8 @@ static __poll_t smc_accept_poll(struct sock *parent) return mask; } -static __poll_t smc_poll(struct file *file, struct socket *sock, - poll_table *wait) +__poll_t smc_poll(struct file *file, struct socket *sock, + poll_table *wait) { struct sock *sk = sock->sk; struct smc_sock *smc; @@ -2895,7 +2904,7 @@ static __poll_t smc_poll(struct file *file, struct socket *sock, return mask; } -static int smc_shutdown(struct socket *sock, int how) +int smc_shutdown(struct socket *sock, int how) { struct sock *sk = sock->sk; bool do_shutdown = true; @@ -3035,8 +3044,8 @@ static int __smc_setsockopt(struct socket *sock, int level, int optname, return rc; } -static int smc_setsockopt(struct socket *sock, int level, int optname, - sockptr_t optval, unsigned int optlen) +int smc_setsockopt(struct socket *sock, int level, int optname, + sockptr_t optval, unsigned int optlen) { struct sock *sk = sock->sk; struct smc_sock *smc; @@ -3122,8 +3131,8 @@ out: return rc; } -static int smc_getsockopt(struct socket *sock, int level, int optname, - char __user *optval, int __user *optlen) +int smc_getsockopt(struct socket *sock, int level, int optname, + char __user *optval, int __user *optlen) { struct smc_sock *smc; int rc; @@ -3148,8 +3157,8 @@ static int smc_getsockopt(struct socket *sock, int level, int optname, return rc; } -static int smc_ioctl(struct socket *sock, unsigned int cmd, - unsigned long arg) +int smc_ioctl(struct socket *sock, unsigned int cmd, + unsigned long arg) { union smc_host_cursor cons, urg; struct smc_connection *conn; @@ -3235,9 +3244,9 @@ static int smc_ioctl(struct socket *sock, unsigned int cmd, * Note that subsequent recv() calls have to wait till all splice() processing * completed. */ -static ssize_t smc_splice_read(struct socket *sock, loff_t *ppos, - struct pipe_inode_info *pipe, size_t len, - unsigned int flags) +ssize_t smc_splice_read(struct socket *sock, loff_t *ppos, + struct pipe_inode_info *pipe, size_t len, + unsigned int flags) { struct sock *sk = sock->sk; struct smc_sock *smc; @@ -3303,6 +3312,31 @@ static const struct proto_ops smc_sock_ops = { .splice_read = smc_splice_read, }; +int smc_create_clcsk(struct net *net, struct sock *sk, int family) +{ + struct smc_sock *smc = smc_sk(sk); + int rc; + + rc = sock_create_kern(net, family, SOCK_STREAM, IPPROTO_TCP, + &smc->clcsock); + if (rc) { + sk_common_release(sk); + return rc; + } + + /* smc_clcsock_release() does not wait smc->clcsock->sk's + * destruction; its sk_state might not be TCP_CLOSE after + * smc->sk is close()d, and TCP timers can be fired later, + * which need net ref. + */ + sk = smc->clcsock->sk; + __netns_tracker_free(net, &sk->ns_tracker, false); + sk->sk_net_refcnt = 1; + get_net_track(net, &sk->ns_tracker, GFP_KERNEL); + sock_inuse_add(net, 1); + return 0; +} + static int __smc_create(struct net *net, struct socket *sock, int protocol, int kern, struct socket *clcsock) { @@ -3328,35 +3362,12 @@ static int __smc_create(struct net *net, struct socket *sock, int protocol, /* create internal TCP socket for CLC handshake and fallback */ smc = smc_sk(sk); - smc->use_fallback = false; /* assume rdma capability first */ - smc->fallback_rsn = 0; - - /* default behavior from limit_smc_hs in every net namespace */ - smc->limit_smc_hs = net->smc.limit_smc_hs; rc = 0; - if (!clcsock) { - rc = sock_create_kern(net, family, SOCK_STREAM, IPPROTO_TCP, - &smc->clcsock); - if (rc) { - sk_common_release(sk); - goto out; - } - - /* smc_clcsock_release() does not wait smc->clcsock->sk's - * destruction; its sk_state might not be TCP_CLOSE after - * smc->sk is close()d, and TCP timers can be fired later, - * which need net ref. - */ - sk = smc->clcsock->sk; - __netns_tracker_free(net, &sk->ns_tracker, false); - sk->sk_net_refcnt = 1; - get_net_track(net, &sk->ns_tracker, GFP_KERNEL); - sock_inuse_add(net, 1); - } else { + if (clcsock) smc->clcsock = clcsock; - } - + else + rc = smc_create_clcsk(net, sk, family); out: return rc; } @@ -3565,10 +3576,15 @@ static int __init smc_init(void) pr_err("%s: tcp_ulp_register fails with %d\n", __func__, rc); goto out_lo; } - + rc = smc_inet_init(); + if (rc) { + pr_err("%s: smc_inet_init fails with %d\n", __func__, rc); + goto out_ulp; + } static_branch_enable(&tcp_have_smc); return 0; - +out_ulp: + tcp_unregister_ulp(&smc_ulp_ops); out_lo: smc_loopback_exit(); out_ib: @@ -3605,6 +3621,7 @@ out_pernet_subsys: static void __exit smc_exit(void) { static_branch_disable(&tcp_have_smc); + smc_inet_exit(); tcp_unregister_ulp(&smc_ulp_ops); sock_unregister(PF_SMC); smc_core_exit(); @@ -3632,4 +3649,9 @@ MODULE_DESCRIPTION("smc socket address family"); MODULE_LICENSE("GPL"); MODULE_ALIAS_NETPROTO(PF_SMC); MODULE_ALIAS_TCP_ULP("smc"); +/* 256 for IPPROTO_SMC and 1 for SOCK_STREAM */ +MODULE_ALIAS_NET_PF_PROTO_TYPE(PF_INET, 256, 1); +#if IS_ENABLED(CONFIG_IPV6) +MODULE_ALIAS_NET_PF_PROTO_TYPE(PF_INET6, 256, 1); +#endif /* CONFIG_IPV6 */ MODULE_ALIAS_GENL_FAMILY(SMC_GENL_FAMILY_NAME); diff --git a/net/smc/smc.h b/net/smc/smc.h index 18c8b7870198..34b781e463c4 100644 --- a/net/smc/smc.h +++ b/net/smc/smc.h @@ -34,6 +34,44 @@ extern struct proto smc_proto; extern struct proto smc_proto6; +extern struct smc_hashinfo smc_v4_hashinfo; +extern struct smc_hashinfo smc_v6_hashinfo; + +int smc_hash_sk(struct sock *sk); +void smc_unhash_sk(struct sock *sk); +void smc_release_cb(struct sock *sk); + +int smc_release(struct socket *sock); +int smc_bind(struct socket *sock, struct sockaddr *uaddr, + int addr_len); +int smc_connect(struct socket *sock, struct sockaddr *addr, + int alen, int flags); +int smc_accept(struct socket *sock, struct socket *new_sock, + struct proto_accept_arg *arg); +int smc_getname(struct socket *sock, struct sockaddr *addr, + int peer); +__poll_t smc_poll(struct file *file, struct socket *sock, + poll_table *wait); +int smc_ioctl(struct socket *sock, unsigned int cmd, + unsigned long arg); +int smc_listen(struct socket *sock, int backlog); +int smc_shutdown(struct socket *sock, int how); +int smc_setsockopt(struct socket *sock, int level, int optname, + sockptr_t optval, unsigned int optlen); +int smc_getsockopt(struct socket *sock, int level, int optname, + char __user *optval, int __user *optlen); +int smc_sendmsg(struct socket *sock, struct msghdr *msg, size_t len); +int smc_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, + int flags); +ssize_t smc_splice_read(struct socket *sock, loff_t *ppos, + struct pipe_inode_info *pipe, size_t len, + unsigned int flags); + +/* smc sock initialization */ +void smc_sk_init(struct net *net, struct sock *sk, int protocol); +/* clcsock initialization */ +int smc_create_clcsk(struct net *net, struct sock *sk, int family); + #ifdef ATOMIC64_INIT #define KERNEL_HAS_ATOMIC64 #endif diff --git a/net/smc/smc_core.c b/net/smc/smc_core.c index fafdb97adfad..3b95828d9976 100644 --- a/net/smc/smc_core.c +++ b/net/smc/smc_core.c @@ -2006,7 +2006,7 @@ out: } #define SMCD_DMBE_SIZES 6 /* 0 -> 16KB, 1 -> 32KB, .. 6 -> 1MB */ -#define SMCR_RMBE_SIZES 5 /* 0 -> 16KB, 1 -> 32KB, .. 5 -> 512KB */ +#define SMCR_RMBE_SIZES 15 /* 0 -> 16KB, 1 -> 32KB, .. 15 -> 512MB */ /* convert the RMB size into the compressed notation (minimum 16K, see * SMCD/R_DMBE_SIZES. @@ -2015,7 +2015,6 @@ out: */ static u8 smc_compress_bufsize(int size, bool is_smcd, bool is_rmb) { - const unsigned int max_scat = SG_MAX_SINGLE_ALLOC * PAGE_SIZE; u8 compressed; if (size <= SMC_BUF_MIN_SIZE) @@ -2025,9 +2024,11 @@ static u8 smc_compress_bufsize(int size, bool is_smcd, bool is_rmb) compressed = min_t(u8, ilog2(size) + 1, is_smcd ? SMCD_DMBE_SIZES : SMCR_RMBE_SIZES); +#ifdef CONFIG_ARCH_NO_SG_CHAIN if (!is_smcd && is_rmb) /* RMBs are backed by & limited to max size of scatterlists */ - compressed = min_t(u8, compressed, ilog2(max_scat >> 14)); + compressed = min_t(u8, compressed, ilog2((SG_MAX_SINGLE_ALLOC * PAGE_SIZE) >> 14)); +#endif return compressed; } diff --git a/net/smc/smc_inet.c b/net/smc/smc_inet.c new file mode 100644 index 000000000000..bece346dd8e9 --- /dev/null +++ b/net/smc/smc_inet.c @@ -0,0 +1,159 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Shared Memory Communications over RDMA (SMC-R) and RoCE + * + * Definitions for the IPPROTO_SMC (socket related) + * + * Copyright IBM Corp. 2016, 2018 + * Copyright (c) 2024, Alibaba Inc. + * + * Author: D. Wythe <alibuda@linux.alibaba.com> + */ + +#include <net/protocol.h> +#include <net/sock.h> + +#include "smc_inet.h" +#include "smc.h" + +static int smc_inet_init_sock(struct sock *sk); + +static struct proto smc_inet_prot = { + .name = "INET_SMC", + .owner = THIS_MODULE, + .init = smc_inet_init_sock, + .hash = smc_hash_sk, + .unhash = smc_unhash_sk, + .release_cb = smc_release_cb, + .obj_size = sizeof(struct smc_sock), + .h.smc_hash = &smc_v4_hashinfo, + .slab_flags = SLAB_TYPESAFE_BY_RCU, +}; + +static const struct proto_ops smc_inet_stream_ops = { + .family = PF_INET, + .owner = THIS_MODULE, + .release = smc_release, + .bind = smc_bind, + .connect = smc_connect, + .socketpair = sock_no_socketpair, + .accept = smc_accept, + .getname = smc_getname, + .poll = smc_poll, + .ioctl = smc_ioctl, + .listen = smc_listen, + .shutdown = smc_shutdown, + .setsockopt = smc_setsockopt, + .getsockopt = smc_getsockopt, + .sendmsg = smc_sendmsg, + .recvmsg = smc_recvmsg, + .mmap = sock_no_mmap, + .splice_read = smc_splice_read, +}; + +static struct inet_protosw smc_inet_protosw = { + .type = SOCK_STREAM, + .protocol = IPPROTO_SMC, + .prot = &smc_inet_prot, + .ops = &smc_inet_stream_ops, + .flags = INET_PROTOSW_ICSK, +}; + +#if IS_ENABLED(CONFIG_IPV6) +static struct proto smc_inet6_prot = { + .name = "INET6_SMC", + .owner = THIS_MODULE, + .init = smc_inet_init_sock, + .hash = smc_hash_sk, + .unhash = smc_unhash_sk, + .release_cb = smc_release_cb, + .obj_size = sizeof(struct smc_sock), + .h.smc_hash = &smc_v6_hashinfo, + .slab_flags = SLAB_TYPESAFE_BY_RCU, +}; + +static const struct proto_ops smc_inet6_stream_ops = { + .family = PF_INET6, + .owner = THIS_MODULE, + .release = smc_release, + .bind = smc_bind, + .connect = smc_connect, + .socketpair = sock_no_socketpair, + .accept = smc_accept, + .getname = smc_getname, + .poll = smc_poll, + .ioctl = smc_ioctl, + .listen = smc_listen, + .shutdown = smc_shutdown, + .setsockopt = smc_setsockopt, + .getsockopt = smc_getsockopt, + .sendmsg = smc_sendmsg, + .recvmsg = smc_recvmsg, + .mmap = sock_no_mmap, + .splice_read = smc_splice_read, +}; + +static struct inet_protosw smc_inet6_protosw = { + .type = SOCK_STREAM, + .protocol = IPPROTO_SMC, + .prot = &smc_inet6_prot, + .ops = &smc_inet6_stream_ops, + .flags = INET_PROTOSW_ICSK, +}; +#endif /* CONFIG_IPV6 */ + +static int smc_inet_init_sock(struct sock *sk) +{ + struct net *net = sock_net(sk); + + /* init common smc sock */ + smc_sk_init(net, sk, IPPROTO_SMC); + /* create clcsock */ + return smc_create_clcsk(net, sk, sk->sk_family); +} + +int __init smc_inet_init(void) +{ + int rc; + + rc = proto_register(&smc_inet_prot, 1); + if (rc) { + pr_err("%s: proto_register smc_inet_prot fails with %d\n", + __func__, rc); + return rc; + } + /* no return value */ + inet_register_protosw(&smc_inet_protosw); + +#if IS_ENABLED(CONFIG_IPV6) + rc = proto_register(&smc_inet6_prot, 1); + if (rc) { + pr_err("%s: proto_register smc_inet6_prot fails with %d\n", + __func__, rc); + goto out_inet6_prot; + } + rc = inet6_register_protosw(&smc_inet6_protosw); + if (rc) { + pr_err("%s: inet6_register_protosw smc_inet6_protosw fails with %d\n", + __func__, rc); + goto out_inet6_protosw; + } + return rc; +out_inet6_protosw: + proto_unregister(&smc_inet6_prot); +out_inet6_prot: + inet_unregister_protosw(&smc_inet_protosw); + proto_unregister(&smc_inet_prot); +#endif /* CONFIG_IPV6 */ + return rc; +} + +void smc_inet_exit(void) +{ +#if IS_ENABLED(CONFIG_IPV6) + inet6_unregister_protosw(&smc_inet6_protosw); + proto_unregister(&smc_inet6_prot); +#endif /* CONFIG_IPV6 */ + inet_unregister_protosw(&smc_inet_protosw); + proto_unregister(&smc_inet_prot); +} diff --git a/net/smc/smc_inet.h b/net/smc/smc_inet.h new file mode 100644 index 000000000000..a489c8a2b8ef --- /dev/null +++ b/net/smc/smc_inet.h @@ -0,0 +1,22 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Shared Memory Communications over RDMA (SMC-R) and RoCE + * + * Definitions for the IPPROTO_SMC (socket related) + + * Copyright IBM Corp. 2016 + * Copyright (c) 2024, Alibaba Inc. + * + * Author: D. Wythe <alibuda@linux.alibaba.com> + */ +#ifndef __INET_SMC +#define __INET_SMC + +/* Initialize protocol registration on IPPROTO_SMC, + * @return 0 on success + */ +int smc_inet_init(void); + +void smc_inet_exit(void); + +#endif /* __INET_SMC */ |