diff options
Diffstat (limited to 'net')
60 files changed, 394 insertions, 464 deletions
diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c index 738871af5efa..670c84b1bfc2 100644 --- a/net/core/net_namespace.c +++ b/net/core/net_namespace.c @@ -1001,22 +1001,18 @@ static int register_pernet_operations(struct list_head *list, int error; if (ops->id) { -again: - error = ida_get_new_above(&net_generic_ids, MIN_PERNET_OPS_ID, ops->id); - if (error < 0) { - if (error == -EAGAIN) { - ida_pre_get(&net_generic_ids, GFP_KERNEL); - goto again; - } + error = ida_alloc_min(&net_generic_ids, MIN_PERNET_OPS_ID, + GFP_KERNEL); + if (error < 0) return error; - } + *ops->id = error; max_gen_ptrs = max(max_gen_ptrs, *ops->id + 1); } error = __register_pernet_operations(list, ops); if (error) { rcu_barrier(); if (ops->id) - ida_remove(&net_generic_ids, *ops->id); + ida_free(&net_generic_ids, *ops->id); } return error; @@ -1027,7 +1023,7 @@ static void unregister_pernet_operations(struct pernet_operations *ops) __unregister_pernet_operations(ops); rcu_barrier(); if (ops->id) - ida_remove(&net_generic_ids, *ops->id); + ida_free(&net_generic_ids, *ops->id); } /** diff --git a/net/dsa/slave.c b/net/dsa/slave.c index 962c4fd338ba..1c45c1d6d241 100644 --- a/net/dsa/slave.c +++ b/net/dsa/slave.c @@ -767,7 +767,6 @@ static int dsa_slave_add_cls_matchall(struct net_device *dev, const struct tc_action *a; struct dsa_port *to_dp; int err = -EOPNOTSUPP; - LIST_HEAD(actions); if (!ds->ops->port_mirror_add) return err; @@ -775,8 +774,7 @@ static int dsa_slave_add_cls_matchall(struct net_device *dev, if (!tcf_exts_has_one_action(cls->exts)) return err; - tcf_exts_to_list(cls->exts, &actions); - a = list_first_entry(&actions, struct tc_action, list); + a = tcf_exts_first_action(cls->exts); if (is_tcf_mirred_egress_mirror(a) && protocol == htons(ETH_P_ALL)) { struct dsa_mall_mirror_tc_entry *mirror; diff --git a/net/ipv4/tcp_bbr.c b/net/ipv4/tcp_bbr.c index 13d34427ca3d..02ff2dde9609 100644 --- a/net/ipv4/tcp_bbr.c +++ b/net/ipv4/tcp_bbr.c @@ -95,11 +95,10 @@ struct bbr { u32 mode:3, /* current bbr_mode in state machine */ prev_ca_state:3, /* CA state on previous ACK */ packet_conservation:1, /* use packet conservation? */ - restore_cwnd:1, /* decided to revert cwnd to old value */ round_start:1, /* start of packet-timed tx->ack round? */ idle_restart:1, /* restarting after idle? */ probe_rtt_round_done:1, /* a BBR_PROBE_RTT round at 4 pkts? */ - unused:12, + unused:13, lt_is_sampling:1, /* taking long-term ("LT") samples now? */ lt_rtt_cnt:7, /* round trips in long-term interval */ lt_use_bw:1; /* use lt_bw as our bw estimate? */ @@ -175,6 +174,8 @@ static const u32 bbr_lt_bw_diff = 4000 / 8; /* If we estimate we're policed, use lt_bw for this many round trips: */ static const u32 bbr_lt_bw_max_rtts = 48; +static void bbr_check_probe_rtt_done(struct sock *sk); + /* Do we estimate that STARTUP filled the pipe? */ static bool bbr_full_bw_reached(const struct sock *sk) { @@ -309,6 +310,8 @@ static void bbr_cwnd_event(struct sock *sk, enum tcp_ca_event event) */ if (bbr->mode == BBR_PROBE_BW) bbr_set_pacing_rate(sk, bbr_bw(sk), BBR_UNIT); + else if (bbr->mode == BBR_PROBE_RTT) + bbr_check_probe_rtt_done(sk); } } @@ -396,17 +399,11 @@ static bool bbr_set_cwnd_to_recover_or_restore( cwnd = tcp_packets_in_flight(tp) + acked; } else if (prev_state >= TCP_CA_Recovery && state < TCP_CA_Recovery) { /* Exiting loss recovery; restore cwnd saved before recovery. */ - bbr->restore_cwnd = 1; + cwnd = max(cwnd, bbr->prior_cwnd); bbr->packet_conservation = 0; } bbr->prev_ca_state = state; - if (bbr->restore_cwnd) { - /* Restore cwnd after exiting loss recovery or PROBE_RTT. */ - cwnd = max(cwnd, bbr->prior_cwnd); - bbr->restore_cwnd = 0; - } - if (bbr->packet_conservation) { *new_cwnd = max(cwnd, tcp_packets_in_flight(tp) + acked); return true; /* yes, using packet conservation */ @@ -423,10 +420,10 @@ static void bbr_set_cwnd(struct sock *sk, const struct rate_sample *rs, { struct tcp_sock *tp = tcp_sk(sk); struct bbr *bbr = inet_csk_ca(sk); - u32 cwnd = 0, target_cwnd = 0; + u32 cwnd = tp->snd_cwnd, target_cwnd = 0; if (!acked) - return; + goto done; /* no packet fully ACKed; just apply caps */ if (bbr_set_cwnd_to_recover_or_restore(sk, rs, acked, &cwnd)) goto done; @@ -748,6 +745,20 @@ static void bbr_check_drain(struct sock *sk, const struct rate_sample *rs) bbr_reset_probe_bw_mode(sk); /* we estimate queue is drained */ } +static void bbr_check_probe_rtt_done(struct sock *sk) +{ + struct tcp_sock *tp = tcp_sk(sk); + struct bbr *bbr = inet_csk_ca(sk); + + if (!(bbr->probe_rtt_done_stamp && + after(tcp_jiffies32, bbr->probe_rtt_done_stamp))) + return; + + bbr->min_rtt_stamp = tcp_jiffies32; /* wait a while until PROBE_RTT */ + tp->snd_cwnd = max(tp->snd_cwnd, bbr->prior_cwnd); + bbr_reset_mode(sk); +} + /* The goal of PROBE_RTT mode is to have BBR flows cooperatively and * periodically drain the bottleneck queue, to converge to measure the true * min_rtt (unloaded propagation delay). This allows the flows to keep queues @@ -806,12 +817,8 @@ static void bbr_update_min_rtt(struct sock *sk, const struct rate_sample *rs) } else if (bbr->probe_rtt_done_stamp) { if (bbr->round_start) bbr->probe_rtt_round_done = 1; - if (bbr->probe_rtt_round_done && - after(tcp_jiffies32, bbr->probe_rtt_done_stamp)) { - bbr->min_rtt_stamp = tcp_jiffies32; - bbr->restore_cwnd = 1; /* snap to prior_cwnd */ - bbr_reset_mode(sk); - } + if (bbr->probe_rtt_round_done) + bbr_check_probe_rtt_done(sk); } } /* Restart after idle ends only once we process a new S/ACK for data */ @@ -862,7 +869,6 @@ static void bbr_init(struct sock *sk) bbr->has_seen_rtt = 0; bbr_init_pacing_rate_from_rtt(sk); - bbr->restore_cwnd = 0; bbr->round_start = 0; bbr->idle_restart = 0; bbr->full_bw_reached = 0; diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 9e041fa5c545..44c09eddbb78 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -2517,6 +2517,12 @@ static int __net_init tcp_sk_init(struct net *net) if (res) goto fail; sock_set_flag(sk, SOCK_USE_WRITE_QUEUE); + + /* Please enforce IP_DF and IPID==0 for RST and + * ACK sent in SYN-RECV and TIME-WAIT state. + */ + inet_sk(sk)->pmtudisc = IP_PMTUDISC_DO; + *per_cpu_ptr(net->ipv4.tcp_sk, cpu) = sk; } diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 2fac4ad74867..d51a8c0b3372 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -2398,7 +2398,7 @@ static void addrconf_add_mroute(struct net_device *dev) ipv6_addr_set(&cfg.fc_dst, htonl(0xFF000000), 0, 0, 0); - ip6_route_add(&cfg, GFP_ATOMIC, NULL); + ip6_route_add(&cfg, GFP_KERNEL, NULL); } static struct inet6_dev *addrconf_add_dev(struct net_device *dev) @@ -3062,7 +3062,7 @@ static void sit_add_v4_addrs(struct inet6_dev *idev) if (addr.s6_addr32[3]) { add_addr(idev, &addr, plen, scope); addrconf_prefix_route(&addr, plen, 0, idev->dev, 0, pflags, - GFP_ATOMIC); + GFP_KERNEL); return; } @@ -3087,7 +3087,7 @@ static void sit_add_v4_addrs(struct inet6_dev *idev) add_addr(idev, &addr, plen, flag); addrconf_prefix_route(&addr, plen, 0, idev->dev, - 0, pflags, GFP_ATOMIC); + 0, pflags, GFP_KERNEL); } } } diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c index d212738e9d10..c861a6d4671d 100644 --- a/net/ipv6/ip6_fib.c +++ b/net/ipv6/ip6_fib.c @@ -198,6 +198,8 @@ void fib6_info_destroy_rcu(struct rcu_head *head) } } + lwtstate_put(f6i->fib6_nh.nh_lwtstate); + if (f6i->fib6_nh.nh_dev) dev_put(f6i->fib6_nh.nh_dev); diff --git a/net/ipv6/ip6_vti.c b/net/ipv6/ip6_vti.c index 38dec9da90d3..5095367c7204 100644 --- a/net/ipv6/ip6_vti.c +++ b/net/ipv6/ip6_vti.c @@ -1094,7 +1094,8 @@ static void __net_exit vti6_destroy_tunnels(struct vti6_net *ip6n, } t = rtnl_dereference(ip6n->tnls_wc[0]); - unregister_netdevice_queue(t->dev, list); + if (t) + unregister_netdevice_queue(t->dev, list); } static int __net_init vti6_init_net(struct net *net) diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 7208c16302f6..c4ea13e8360b 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -956,7 +956,7 @@ static void ip6_rt_init_dst(struct rt6_info *rt, struct fib6_info *ort) rt->dst.error = 0; rt->dst.output = ip6_output; - if (ort->fib6_type == RTN_LOCAL) { + if (ort->fib6_type == RTN_LOCAL || ort->fib6_type == RTN_ANYCAST) { rt->dst.input = ip6_input; } else if (ipv6_addr_type(&ort->fib6_dst.addr) & IPV6_ADDR_MULTICAST) { rt->dst.input = ip6_mc_input; diff --git a/net/ncsi/ncsi-netlink.c b/net/ncsi/ncsi-netlink.c index 82e6edf9c5d9..45f33d6dedf7 100644 --- a/net/ncsi/ncsi-netlink.c +++ b/net/ncsi/ncsi-netlink.c @@ -100,7 +100,7 @@ static int ncsi_write_package_info(struct sk_buff *skb, bool found; int rc; - if (id > ndp->package_num) { + if (id > ndp->package_num - 1) { netdev_info(ndp->ndev.dev, "NCSI: No package with id %u\n", id); return -ENODEV; } @@ -240,7 +240,7 @@ static int ncsi_pkg_info_all_nl(struct sk_buff *skb, return 0; /* done */ hdr = genlmsg_put(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, - &ncsi_genl_family, 0, NCSI_CMD_PKG_INFO); + &ncsi_genl_family, NLM_F_MULTI, NCSI_CMD_PKG_INFO); if (!hdr) { rc = -EMSGSIZE; goto err; diff --git a/net/netfilter/ipvs/Kconfig b/net/netfilter/ipvs/Kconfig index 05dc1b77e466..cad48d07c818 100644 --- a/net/netfilter/ipvs/Kconfig +++ b/net/netfilter/ipvs/Kconfig @@ -296,10 +296,10 @@ config IP_VS_MH_TAB_INDEX stored in a hash table. This table is assigned by a preference list of the positions to each destination until all slots in the table are filled. The index determines the prime for size of - the table as 251, 509, 1021, 2039, 4093, 8191, 16381, 32749, - 65521 or 131071. When using weights to allow destinations to - receive more connections, the table is assigned an amount - proportional to the weights specified. The table needs to be large + the table as 251, 509, 1021, 2039, 4093, 8191, 16381, 32749, + 65521 or 131071. When using weights to allow destinations to + receive more connections, the table is assigned an amount + proportional to the weights specified. The table needs to be large enough to effectively fit all the destinations multiplied by their respective weights. diff --git a/net/netfilter/ipvs/ip_vs_mh.c b/net/netfilter/ipvs/ip_vs_mh.c index 0f795b186eb3..94d9d349ebb0 100644 --- a/net/netfilter/ipvs/ip_vs_mh.c +++ b/net/netfilter/ipvs/ip_vs_mh.c @@ -5,10 +5,10 @@ * */ -/* The mh algorithm is to assign a preference list of all the lookup +/* The mh algorithm is to assign a preference list of all the lookup * table positions to each destination and populate the table with * the most-preferred position of destinations. Then it is to select - * destination with the hash key of source IP address through looking + * destination with the hash key of source IP address through looking * up a the lookup table. * * The algorithm is detailed in: diff --git a/net/rds/tcp.c b/net/rds/tcp.c index 2c7b7c352d3e..b9bbcf3d6c63 100644 --- a/net/rds/tcp.c +++ b/net/rds/tcp.c @@ -37,7 +37,6 @@ #include <net/tcp.h> #include <net/net_namespace.h> #include <net/netns/generic.h> -#include <net/tcp.h> #include <net/addrconf.h> #include "rds.h" diff --git a/net/sched/act_api.c b/net/sched/act_api.c index 229d63c99be2..db83dac1e7f4 100644 --- a/net/sched/act_api.c +++ b/net/sched/act_api.c @@ -300,21 +300,17 @@ int tcf_generic_walker(struct tc_action_net *tn, struct sk_buff *skb, } EXPORT_SYMBOL(tcf_generic_walker); -static bool __tcf_idr_check(struct tc_action_net *tn, u32 index, - struct tc_action **a, int bind) +int tcf_idr_search(struct tc_action_net *tn, struct tc_action **a, u32 index) { struct tcf_idrinfo *idrinfo = tn->idrinfo; struct tc_action *p; spin_lock(&idrinfo->lock); p = idr_find(&idrinfo->action_idr, index); - if (IS_ERR(p)) { + if (IS_ERR(p)) p = NULL; - } else if (p) { + else if (p) refcount_inc(&p->tcfa_refcnt); - if (bind) - atomic_inc(&p->tcfa_bindcnt); - } spin_unlock(&idrinfo->lock); if (p) { @@ -323,23 +319,10 @@ static bool __tcf_idr_check(struct tc_action_net *tn, u32 index, } return false; } - -int tcf_idr_search(struct tc_action_net *tn, struct tc_action **a, u32 index) -{ - return __tcf_idr_check(tn, index, a, 0); -} EXPORT_SYMBOL(tcf_idr_search); -bool tcf_idr_check(struct tc_action_net *tn, u32 index, struct tc_action **a, - int bind) +static int tcf_idr_delete_index(struct tcf_idrinfo *idrinfo, u32 index) { - return __tcf_idr_check(tn, index, a, bind); -} -EXPORT_SYMBOL(tcf_idr_check); - -int tcf_idr_delete_index(struct tc_action_net *tn, u32 index) -{ - struct tcf_idrinfo *idrinfo = tn->idrinfo; struct tc_action *p; int ret = 0; @@ -370,7 +353,6 @@ int tcf_idr_delete_index(struct tc_action_net *tn, u32 index) spin_unlock(&idrinfo->lock); return ret; } -EXPORT_SYMBOL(tcf_idr_delete_index); int tcf_idr_create(struct tc_action_net *tn, u32 index, struct nlattr *est, struct tc_action **a, const struct tc_action_ops *ops, @@ -409,7 +391,6 @@ int tcf_idr_create(struct tc_action_net *tn, u32 index, struct nlattr *est, p->idrinfo = idrinfo; p->ops = ops; - INIT_LIST_HEAD(&p->list); *a = p; return 0; err3: @@ -686,14 +667,18 @@ static int tcf_action_put(struct tc_action *p) return __tcf_action_put(p, false); } +/* Put all actions in this array, skip those NULL's. */ static void tcf_action_put_many(struct tc_action *actions[]) { int i; - for (i = 0; i < TCA_ACT_MAX_PRIO && actions[i]; i++) { + for (i = 0; i < TCA_ACT_MAX_PRIO; i++) { struct tc_action *a = actions[i]; - const struct tc_action_ops *ops = a->ops; + const struct tc_action_ops *ops; + if (!a) + continue; + ops = a->ops; if (tcf_action_put(a)) module_put(ops->owner); } @@ -1175,41 +1160,38 @@ err_out: return err; } -static int tcf_action_delete(struct net *net, struct tc_action *actions[], - int *acts_deleted, struct netlink_ext_ack *extack) +static int tcf_action_delete(struct net *net, struct tc_action *actions[]) { - u32 act_index; - int ret, i; + int i; for (i = 0; i < TCA_ACT_MAX_PRIO && actions[i]; i++) { struct tc_action *a = actions[i]; const struct tc_action_ops *ops = a->ops; - /* Actions can be deleted concurrently so we must save their * type and id to search again after reference is released. */ - act_index = a->tcfa_index; + struct tcf_idrinfo *idrinfo = a->idrinfo; + u32 act_index = a->tcfa_index; if (tcf_action_put(a)) { /* last reference, action was deleted concurrently */ module_put(ops->owner); } else { + int ret; + /* now do the delete */ - ret = ops->delete(net, act_index); - if (ret < 0) { - *acts_deleted = i + 1; + ret = tcf_idr_delete_index(idrinfo, act_index); + if (ret < 0) return ret; - } } + actions[i] = NULL; } - *acts_deleted = i; return 0; } static int tcf_del_notify(struct net *net, struct nlmsghdr *n, struct tc_action *actions[], - int *acts_deleted, u32 portid, size_t attr_size, - struct netlink_ext_ack *extack) + u32 portid, size_t attr_size, struct netlink_ext_ack *extack) { int ret; struct sk_buff *skb; @@ -1227,7 +1209,7 @@ tcf_del_notify(struct net *net, struct nlmsghdr *n, struct tc_action *actions[], } /* now do the delete */ - ret = tcf_action_delete(net, actions, acts_deleted, extack); + ret = tcf_action_delete(net, actions); if (ret < 0) { NL_SET_ERR_MSG(extack, "Failed to delete TC action"); kfree_skb(skb); @@ -1249,8 +1231,7 @@ tca_action_gd(struct net *net, struct nlattr *nla, struct nlmsghdr *n, struct nlattr *tb[TCA_ACT_MAX_PRIO + 1]; struct tc_action *act; size_t attr_size = 0; - struct tc_action *actions[TCA_ACT_MAX_PRIO + 1] = {}; - int acts_deleted = 0; + struct tc_action *actions[TCA_ACT_MAX_PRIO] = {}; ret = nla_parse_nested(tb, TCA_ACT_MAX_PRIO, nla, NULL, extack); if (ret < 0) @@ -1280,14 +1261,13 @@ tca_action_gd(struct net *net, struct nlattr *nla, struct nlmsghdr *n, if (event == RTM_GETACTION) ret = tcf_get_notify(net, portid, n, actions, event, extack); else { /* delete */ - ret = tcf_del_notify(net, n, actions, &acts_deleted, portid, - attr_size, extack); + ret = tcf_del_notify(net, n, actions, portid, attr_size, extack); if (ret) goto err; - return ret; + return 0; } err: - tcf_action_put_many(&actions[acts_deleted]); + tcf_action_put_many(actions); return ret; } diff --git a/net/sched/act_bpf.c b/net/sched/act_bpf.c index d30b23e42436..0c68bc9cf0b4 100644 --- a/net/sched/act_bpf.c +++ b/net/sched/act_bpf.c @@ -395,13 +395,6 @@ static int tcf_bpf_search(struct net *net, struct tc_action **a, u32 index, return tcf_idr_search(tn, a, index); } -static int tcf_bpf_delete(struct net *net, u32 index) -{ - struct tc_action_net *tn = net_generic(net, bpf_net_id); - - return tcf_idr_delete_index(tn, index); -} - static struct tc_action_ops act_bpf_ops __read_mostly = { .kind = "bpf", .type = TCA_ACT_BPF, @@ -412,7 +405,6 @@ static struct tc_action_ops act_bpf_ops __read_mostly = { .init = tcf_bpf_init, .walk = tcf_bpf_walker, .lookup = tcf_bpf_search, - .delete = tcf_bpf_delete, .size = sizeof(struct tcf_bpf), }; diff --git a/net/sched/act_connmark.c b/net/sched/act_connmark.c index 54c0bf54f2ac..6f0f273f1139 100644 --- a/net/sched/act_connmark.c +++ b/net/sched/act_connmark.c @@ -198,13 +198,6 @@ static int tcf_connmark_search(struct net *net, struct tc_action **a, u32 index, return tcf_idr_search(tn, a, index); } -static int tcf_connmark_delete(struct net *net, u32 index) -{ - struct tc_action_net *tn = net_generic(net, connmark_net_id); - - return tcf_idr_delete_index(tn, index); -} - static struct tc_action_ops act_connmark_ops = { .kind = "connmark", .type = TCA_ACT_CONNMARK, @@ -214,7 +207,6 @@ static struct tc_action_ops act_connmark_ops = { .init = tcf_connmark_init, .walk = tcf_connmark_walker, .lookup = tcf_connmark_search, - .delete = tcf_connmark_delete, .size = sizeof(struct tcf_connmark_info), }; diff --git a/net/sched/act_csum.c b/net/sched/act_csum.c index e698d3fe2080..b8a67ae3105a 100644 --- a/net/sched/act_csum.c +++ b/net/sched/act_csum.c @@ -659,13 +659,6 @@ static size_t tcf_csum_get_fill_size(const struct tc_action *act) return nla_total_size(sizeof(struct tc_csum)); } -static int tcf_csum_delete(struct net *net, u32 index) -{ - struct tc_action_net *tn = net_generic(net, csum_net_id); - - return tcf_idr_delete_index(tn, index); -} - static struct tc_action_ops act_csum_ops = { .kind = "csum", .type = TCA_ACT_CSUM, @@ -677,7 +670,6 @@ static struct tc_action_ops act_csum_ops = { .walk = tcf_csum_walker, .lookup = tcf_csum_search, .get_fill_size = tcf_csum_get_fill_size, - .delete = tcf_csum_delete, .size = sizeof(struct tcf_csum), }; diff --git a/net/sched/act_gact.c b/net/sched/act_gact.c index 6a3f25a8ffb3..cd1d9bd32ef9 100644 --- a/net/sched/act_gact.c +++ b/net/sched/act_gact.c @@ -243,13 +243,6 @@ static size_t tcf_gact_get_fill_size(const struct tc_action *act) return sz; } -static int tcf_gact_delete(struct net *net, u32 index) -{ - struct tc_action_net *tn = net_generic(net, gact_net_id); - - return tcf_idr_delete_index(tn, index); -} - static struct tc_action_ops act_gact_ops = { .kind = "gact", .type = TCA_ACT_GACT, @@ -261,7 +254,6 @@ static struct tc_action_ops act_gact_ops = { .walk = tcf_gact_walker, .lookup = tcf_gact_search, .get_fill_size = tcf_gact_get_fill_size, - .delete = tcf_gact_delete, .size = sizeof(struct tcf_gact), }; diff --git a/net/sched/act_ife.c b/net/sched/act_ife.c index d1081bdf1bdb..196430aefe87 100644 --- a/net/sched/act_ife.c +++ b/net/sched/act_ife.c @@ -167,16 +167,16 @@ static struct tcf_meta_ops *find_ife_oplist(u16 metaid) { struct tcf_meta_ops *o; - read_lock_bh(&ife_mod_lock); + read_lock(&ife_mod_lock); list_for_each_entry(o, &ifeoplist, list) { if (o->metaid == metaid) { if (!try_module_get(o->owner)) o = NULL; - read_unlock_bh(&ife_mod_lock); + read_unlock(&ife_mod_lock); return o; } } - read_unlock_bh(&ife_mod_lock); + read_unlock(&ife_mod_lock); return NULL; } @@ -190,12 +190,12 @@ int register_ife_op(struct tcf_meta_ops *mops) !mops->get || !mops->alloc) return -EINVAL; - write_lock_bh(&ife_mod_lock); + write_lock(&ife_mod_lock); list_for_each_entry(m, &ifeoplist, list) { if (m->metaid == mops->metaid || (strcmp(mops->name, m->name) == 0)) { - write_unlock_bh(&ife_mod_lock); + write_unlock(&ife_mod_lock); return -EEXIST; } } @@ -204,7 +204,7 @@ int register_ife_op(struct tcf_meta_ops *mops) mops->release = ife_release_meta_gen; list_add_tail(&mops->list, &ifeoplist); - write_unlock_bh(&ife_mod_lock); + write_unlock(&ife_mod_lock); return 0; } EXPORT_SYMBOL_GPL(unregister_ife_op); @@ -214,7 +214,7 @@ int unregister_ife_op(struct tcf_meta_ops *mops) struct tcf_meta_ops *m; int err = -ENOENT; - write_lock_bh(&ife_mod_lock); + write_lock(&ife_mod_lock); list_for_each_entry(m, &ifeoplist, list) { if (m->metaid == mops->metaid) { list_del(&mops->list); @@ -222,7 +222,7 @@ int unregister_ife_op(struct tcf_meta_ops *mops) break; } } - write_unlock_bh(&ife_mod_lock); + write_unlock(&ife_mod_lock); return err; } @@ -265,11 +265,8 @@ static const char *ife_meta_id2name(u32 metaid) #endif /* called when adding new meta information - * under ife->tcf_lock for existing action */ -static int load_metaops_and_vet(struct tcf_ife_info *ife, u32 metaid, - void *val, int len, bool exists, - bool rtnl_held) +static int load_metaops_and_vet(u32 metaid, void *val, int len, bool rtnl_held) { struct tcf_meta_ops *ops = find_ife_oplist(metaid); int ret = 0; @@ -277,15 +274,11 @@ static int load_metaops_and_vet(struct tcf_ife_info *ife, u32 metaid, if (!ops) { ret = -ENOENT; #ifdef CONFIG_MODULES - if (exists) - spin_unlock_bh(&ife->tcf_lock); if (rtnl_held) rtnl_unlock(); request_module("ife-meta-%s", ife_meta_id2name(metaid)); if (rtnl_held) rtnl_lock(); - if (exists) - spin_lock_bh(&ife->tcf_lock); ops = find_ife_oplist(metaid); #endif } @@ -302,24 +295,17 @@ static int load_metaops_and_vet(struct tcf_ife_info *ife, u32 metaid, } /* called when adding new meta information - * under ife->tcf_lock for existing action */ -static int add_metainfo(struct tcf_ife_info *ife, u32 metaid, void *metaval, - int len, bool atomic) +static int __add_metainfo(const struct tcf_meta_ops *ops, + struct tcf_ife_info *ife, u32 metaid, void *metaval, + int len, bool atomic, bool exists) { struct tcf_meta_info *mi = NULL; - struct tcf_meta_ops *ops = find_ife_oplist(metaid); int ret = 0; - if (!ops) - return -ENOENT; - mi = kzalloc(sizeof(*mi), atomic ? GFP_ATOMIC : GFP_KERNEL); - if (!mi) { - /*put back what find_ife_oplist took */ - module_put(ops->owner); + if (!mi) return -ENOMEM; - } mi->metaid = metaid; mi->ops = ops; @@ -327,29 +313,47 @@ static int add_metainfo(struct tcf_ife_info *ife, u32 metaid, void *metaval, ret = ops->alloc(mi, metaval, atomic ? GFP_ATOMIC : GFP_KERNEL); if (ret != 0) { kfree(mi); - module_put(ops->owner); return ret; } } + if (exists) + spin_lock_bh(&ife->tcf_lock); list_add_tail(&mi->metalist, &ife->metalist); + if (exists) + spin_unlock_bh(&ife->tcf_lock); + + return ret; +} + +static int add_metainfo(struct tcf_ife_info *ife, u32 metaid, void *metaval, + int len, bool exists) +{ + const struct tcf_meta_ops *ops = find_ife_oplist(metaid); + int ret; + if (!ops) + return -ENOENT; + ret = __add_metainfo(ops, ife, metaid, metaval, len, false, exists); + if (ret) + /*put back what find_ife_oplist took */ + module_put(ops->owner); return ret; } -static int use_all_metadata(struct tcf_ife_info *ife) +static int use_all_metadata(struct tcf_ife_info *ife, bool exists) { struct tcf_meta_ops *o; int rc = 0; int installed = 0; - read_lock_bh(&ife_mod_lock); + read_lock(&ife_mod_lock); list_for_each_entry(o, &ifeoplist, list) { - rc = add_metainfo(ife, o->metaid, NULL, 0, true); + rc = __add_metainfo(o, ife, o->metaid, NULL, 0, true, exists); if (rc == 0) installed += 1; } - read_unlock_bh(&ife_mod_lock); + read_unlock(&ife_mod_lock); if (installed) return 0; @@ -422,7 +426,6 @@ static void tcf_ife_cleanup(struct tc_action *a) kfree_rcu(p, rcu); } -/* under ife->tcf_lock for existing action */ static int populate_metalist(struct tcf_ife_info *ife, struct nlattr **tb, bool exists, bool rtnl_held) { @@ -436,8 +439,7 @@ static int populate_metalist(struct tcf_ife_info *ife, struct nlattr **tb, val = nla_data(tb[i]); len = nla_len(tb[i]); - rc = load_metaops_and_vet(ife, i, val, len, exists, - rtnl_held); + rc = load_metaops_and_vet(i, val, len, rtnl_held); if (rc != 0) return rc; @@ -540,8 +542,6 @@ static int tcf_ife_init(struct net *net, struct nlattr *nla, p->eth_type = ife_type; } - if (exists) - spin_lock_bh(&ife->tcf_lock); if (ret == ACT_P_CREATED) INIT_LIST_HEAD(&ife->metalist); @@ -551,10 +551,7 @@ static int tcf_ife_init(struct net *net, struct nlattr *nla, NULL, NULL); if (err) { metadata_parse_err: - if (exists) - spin_unlock_bh(&ife->tcf_lock); tcf_idr_release(*a, bind); - kfree(p); return err; } @@ -569,17 +566,16 @@ metadata_parse_err: * as we can. You better have at least one else we are * going to bail out */ - err = use_all_metadata(ife); + err = use_all_metadata(ife, exists); if (err) { - if (exists) - spin_unlock_bh(&ife->tcf_lock); tcf_idr_release(*a, bind); - kfree(p); return err; } } + if (exists) + spin_lock_bh(&ife->tcf_lock); ife->tcf_action = parm->action; /* protected by tcf_lock when modifying existing action */ rcu_swap_protected(ife->params, p, 1); @@ -853,13 +849,6 @@ static int tcf_ife_search(struct net *net, struct tc_action **a, u32 index, return tcf_idr_search(tn, a, index); } -static int tcf_ife_delete(struct net *net, u32 index) -{ - struct tc_action_net *tn = net_generic(net, ife_net_id); - - return tcf_idr_delete_index(tn, index); -} - static struct tc_action_ops act_ife_ops = { .kind = "ife", .type = TCA_ACT_IFE, @@ -870,7 +859,6 @@ static struct tc_action_ops act_ife_ops = { .init = tcf_ife_init, .walk = tcf_ife_walker, .lookup = tcf_ife_search, - .delete = tcf_ife_delete, .size = sizeof(struct tcf_ife_info), }; diff --git a/net/sched/act_ipt.c b/net/sched/act_ipt.c index 51f235bbeb5b..23273b5303fd 100644 --- a/net/sched/act_ipt.c +++ b/net/sched/act_ipt.c @@ -337,13 +337,6 @@ static int tcf_ipt_search(struct net *net, struct tc_action **a, u32 index, return tcf_idr_search(tn, a, index); } -static int tcf_ipt_delete(struct net *net, u32 index) -{ - struct tc_action_net *tn = net_generic(net, ipt_net_id); - - return tcf_idr_delete_index(tn, index); -} - static struct tc_action_ops act_ipt_ops = { .kind = "ipt", .type = TCA_ACT_IPT, @@ -354,7 +347,6 @@ static struct tc_action_ops act_ipt_ops = { .init = tcf_ipt_init, .walk = tcf_ipt_walker, .lookup = tcf_ipt_search, - .delete = tcf_ipt_delete, .size = sizeof(struct tcf_ipt), }; @@ -395,13 +387,6 @@ static int tcf_xt_search(struct net *net, struct tc_action **a, u32 index, return tcf_idr_search(tn, a, index); } -static int tcf_xt_delete(struct net *net, u32 index) -{ - struct tc_action_net *tn = net_generic(net, xt_net_id); - - return tcf_idr_delete_index(tn, index); -} - static struct tc_action_ops act_xt_ops = { .kind = "xt", .type = TCA_ACT_XT, @@ -412,7 +397,6 @@ static struct tc_action_ops act_xt_ops = { .init = tcf_xt_init, .walk = tcf_xt_walker, .lookup = tcf_xt_search, - .delete = tcf_xt_delete, .size = sizeof(struct tcf_ipt), }; diff --git a/net/sched/act_mirred.c b/net/sched/act_mirred.c index 38fd20f10f67..8bf66d0a6800 100644 --- a/net/sched/act_mirred.c +++ b/net/sched/act_mirred.c @@ -395,13 +395,6 @@ static void tcf_mirred_put_dev(struct net_device *dev) dev_put(dev); } -static int tcf_mirred_delete(struct net *net, u32 index) -{ - struct tc_action_net *tn = net_generic(net, mirred_net_id); - - return tcf_idr_delete_index(tn, index); -} - static struct tc_action_ops act_mirred_ops = { .kind = "mirred", .type = TCA_ACT_MIRRED, @@ -416,7 +409,6 @@ static struct tc_action_ops act_mirred_ops = { .size = sizeof(struct tcf_mirred), .get_dev = tcf_mirred_get_dev, .put_dev = tcf_mirred_put_dev, - .delete = tcf_mirred_delete, }; static __net_init int mirred_init_net(struct net *net) diff --git a/net/sched/act_nat.c b/net/sched/act_nat.c index 822e903bfc25..4313aa102440 100644 --- a/net/sched/act_nat.c +++ b/net/sched/act_nat.c @@ -300,13 +300,6 @@ static int tcf_nat_search(struct net *net, struct tc_action **a, u32 index, return tcf_idr_search(tn, a, index); } -static int tcf_nat_delete(struct net *net, u32 index) -{ - struct tc_action_net *tn = net_generic(net, nat_net_id); - - return tcf_idr_delete_index(tn, index); -} - static struct tc_action_ops act_nat_ops = { .kind = "nat", .type = TCA_ACT_NAT, @@ -316,7 +309,6 @@ static struct tc_action_ops act_nat_ops = { .init = tcf_nat_init, .walk = tcf_nat_walker, .lookup = tcf_nat_search, - .delete = tcf_nat_delete, .size = sizeof(struct tcf_nat), }; diff --git a/net/sched/act_pedit.c b/net/sched/act_pedit.c index 8a7a7cb94e83..107034070019 100644 --- a/net/sched/act_pedit.c +++ b/net/sched/act_pedit.c @@ -460,13 +460,6 @@ static int tcf_pedit_search(struct net *net, struct tc_action **a, u32 index, return tcf_idr_search(tn, a, index); } -static int tcf_pedit_delete(struct net *net, u32 index) -{ - struct tc_action_net *tn = net_generic(net, pedit_net_id); - - return tcf_idr_delete_index(tn, index); -} - static struct tc_action_ops act_pedit_ops = { .kind = "pedit", .type = TCA_ACT_PEDIT, @@ -477,7 +470,6 @@ static struct tc_action_ops act_pedit_ops = { .init = tcf_pedit_init, .walk = tcf_pedit_walker, .lookup = tcf_pedit_search, - .delete = tcf_pedit_delete, .size = sizeof(struct tcf_pedit), }; diff --git a/net/sched/act_police.c b/net/sched/act_police.c index 06f0742db593..5d8bfa878477 100644 --- a/net/sched/act_police.c +++ b/net/sched/act_police.c @@ -320,13 +320,6 @@ static int tcf_police_search(struct net *net, struct tc_action **a, u32 index, return tcf_idr_search(tn, a, index); } -static int tcf_police_delete(struct net *net, u32 index) -{ - struct tc_action_net *tn = net_generic(net, police_net_id); - - return tcf_idr_delete_index(tn, index); -} - MODULE_AUTHOR("Alexey Kuznetsov"); MODULE_DESCRIPTION("Policing actions"); MODULE_LICENSE("GPL"); @@ -340,7 +333,6 @@ static struct tc_action_ops act_police_ops = { .init = tcf_police_init, .walk = tcf_police_walker, .lookup = tcf_police_search, - .delete = tcf_police_delete, .size = sizeof(struct tcf_police), }; diff --git a/net/sched/act_sample.c b/net/sched/act_sample.c index 207b4132d1b0..44e9c00657bc 100644 --- a/net/sched/act_sample.c +++ b/net/sched/act_sample.c @@ -232,13 +232,6 @@ static int tcf_sample_search(struct net *net, struct tc_action **a, u32 index, return tcf_idr_search(tn, a, index); } -static int tcf_sample_delete(struct net *net, u32 index) -{ - struct tc_action_net *tn = net_generic(net, sample_net_id); - - return tcf_idr_delete_index(tn, index); -} - static struct tc_action_ops act_sample_ops = { .kind = "sample", .type = TCA_ACT_SAMPLE, @@ -249,7 +242,6 @@ static struct tc_action_ops act_sample_ops = { .cleanup = tcf_sample_cleanup, .walk = tcf_sample_walker, .lookup = tcf_sample_search, - .delete = tcf_sample_delete, .size = sizeof(struct tcf_sample), }; diff --git a/net/sched/act_simple.c b/net/sched/act_simple.c index e616523ba3c1..52400d49f81f 100644 --- a/net/sched/act_simple.c +++ b/net/sched/act_simple.c @@ -196,13 +196,6 @@ static int tcf_simp_search(struct net *net, struct tc_action **a, u32 index, return tcf_idr_search(tn, a, index); } -static int tcf_simp_delete(struct net *net, u32 index) -{ - struct tc_action_net *tn = net_generic(net, simp_net_id); - - return tcf_idr_delete_index(tn, index); -} - static struct tc_action_ops act_simp_ops = { .kind = "simple", .type = TCA_ACT_SIMP, @@ -213,7 +206,6 @@ static struct tc_action_ops act_simp_ops = { .init = tcf_simp_init, .walk = tcf_simp_walker, .lookup = tcf_simp_search, - .delete = tcf_simp_delete, .size = sizeof(struct tcf_defact), }; diff --git a/net/sched/act_skbedit.c b/net/sched/act_skbedit.c index 926d7bc4a89d..73e44ce2a883 100644 --- a/net/sched/act_skbedit.c +++ b/net/sched/act_skbedit.c @@ -299,13 +299,6 @@ static int tcf_skbedit_search(struct net *net, struct tc_action **a, u32 index, return tcf_idr_search(tn, a, index); } -static int tcf_skbedit_delete(struct net *net, u32 index) -{ - struct tc_action_net *tn = net_generic(net, skbedit_net_id); - - return tcf_idr_delete_index(tn, index); -} - static struct tc_action_ops act_skbedit_ops = { .kind = "skbedit", .type = TCA_ACT_SKBEDIT, @@ -316,7 +309,6 @@ static struct tc_action_ops act_skbedit_ops = { .cleanup = tcf_skbedit_cleanup, .walk = tcf_skbedit_walker, .lookup = tcf_skbedit_search, - .delete = tcf_skbedit_delete, .size = sizeof(struct tcf_skbedit), }; diff --git a/net/sched/act_skbmod.c b/net/sched/act_skbmod.c index d6a1af0c4171..588077fafd6c 100644 --- a/net/sched/act_skbmod.c +++ b/net/sched/act_skbmod.c @@ -259,13 +259,6 @@ static int tcf_skbmod_search(struct net *net, struct tc_action **a, u32 index, return tcf_idr_search(tn, a, index); } -static int tcf_skbmod_delete(struct net *net, u32 index) -{ - struct tc_action_net *tn = net_generic(net, skbmod_net_id); - - return tcf_idr_delete_index(tn, index); -} - static struct tc_action_ops act_skbmod_ops = { .kind = "skbmod", .type = TCA_ACT_SKBMOD, @@ -276,7 +269,6 @@ static struct tc_action_ops act_skbmod_ops = { .cleanup = tcf_skbmod_cleanup, .walk = tcf_skbmod_walker, .lookup = tcf_skbmod_search, - .delete = tcf_skbmod_delete, .size = sizeof(struct tcf_skbmod), }; diff --git a/net/sched/act_tunnel_key.c b/net/sched/act_tunnel_key.c index 8f09cf08d8fe..420759153d5f 100644 --- a/net/sched/act_tunnel_key.c +++ b/net/sched/act_tunnel_key.c @@ -548,13 +548,6 @@ static int tunnel_key_search(struct net *net, struct tc_action **a, u32 index, return tcf_idr_search(tn, a, index); } -static int tunnel_key_delete(struct net *net, u32 index) -{ - struct tc_action_net *tn = net_generic(net, tunnel_key_net_id); - - return tcf_idr_delete_index(tn, index); -} - static struct tc_action_ops act_tunnel_key_ops = { .kind = "tunnel_key", .type = TCA_ACT_TUNNEL_KEY, @@ -565,7 +558,6 @@ static struct tc_action_ops act_tunnel_key_ops = { .cleanup = tunnel_key_release, .walk = tunnel_key_walker, .lookup = tunnel_key_search, - .delete = tunnel_key_delete, .size = sizeof(struct tcf_tunnel_key), }; diff --git a/net/sched/act_vlan.c b/net/sched/act_vlan.c index 209e70ad2c09..033d273afe50 100644 --- a/net/sched/act_vlan.c +++ b/net/sched/act_vlan.c @@ -296,13 +296,6 @@ static int tcf_vlan_search(struct net *net, struct tc_action **a, u32 index, return tcf_idr_search(tn, a, index); } -static int tcf_vlan_delete(struct net *net, u32 index) -{ - struct tc_action_net *tn = net_generic(net, vlan_net_id); - - return tcf_idr_delete_index(tn, index); -} - static struct tc_action_ops act_vlan_ops = { .kind = "vlan", .type = TCA_ACT_VLAN, @@ -313,7 +306,6 @@ static struct tc_action_ops act_vlan_ops = { .cleanup = tcf_vlan_cleanup, .walk = tcf_vlan_walker, .lookup = tcf_vlan_search, - .delete = tcf_vlan_delete, .size = sizeof(struct tcf_vlan), }; diff --git a/net/sched/cls_u32.c b/net/sched/cls_u32.c index d5d2a6dc3921..f218ccf1e2d9 100644 --- a/net/sched/cls_u32.c +++ b/net/sched/cls_u32.c @@ -914,6 +914,7 @@ static int u32_change(struct net *net, struct sk_buff *in_skb, struct nlattr *opt = tca[TCA_OPTIONS]; struct nlattr *tb[TCA_U32_MAX + 1]; u32 htid, flags = 0; + size_t sel_size; int err; #ifdef CONFIG_CLS_U32_PERF size_t size; @@ -1076,8 +1077,13 @@ static int u32_change(struct net *net, struct sk_buff *in_skb, } s = nla_data(tb[TCA_U32_SEL]); + sel_size = struct_size(s, keys, s->nkeys); + if (nla_len(tb[TCA_U32_SEL]) < sel_size) { + err = -EINVAL; + goto erridr; + } - n = kzalloc(sizeof(*n) + s->nkeys*sizeof(struct tc_u32_key), GFP_KERNEL); + n = kzalloc(offsetof(typeof(*n), sel) + sel_size, GFP_KERNEL); if (n == NULL) { err = -ENOBUFS; goto erridr; @@ -1092,7 +1098,7 @@ static int u32_change(struct net *net, struct sk_buff *in_skb, } #endif - memcpy(&n->sel, s, sizeof(*s) + s->nkeys*sizeof(struct tc_u32_key)); + memcpy(&n->sel, s, sel_size); RCU_INIT_POINTER(n->ht_up, ht); n->handle = handle; n->fshift = s->hmask ? ffs(ntohl(s->hmask)) - 1 : 0; diff --git a/net/sched/sch_cake.c b/net/sched/sch_cake.c index 35fc7252187c..c07c30b916d5 100644 --- a/net/sched/sch_cake.c +++ b/net/sched/sch_cake.c @@ -64,7 +64,6 @@ #include <linux/vmalloc.h> #include <linux/reciprocal_div.h> #include <net/netlink.h> -#include <linux/version.h> #include <linux/if_vlan.h> #include <net/pkt_sched.h> #include <net/pkt_cls.h> @@ -621,15 +620,20 @@ static bool cake_ddst(int flow_mode) } static u32 cake_hash(struct cake_tin_data *q, const struct sk_buff *skb, - int flow_mode) + int flow_mode, u16 flow_override, u16 host_override) { - u32 flow_hash = 0, srchost_hash, dsthost_hash; + u32 flow_hash = 0, srchost_hash = 0, dsthost_hash = 0; u16 reduced_hash, srchost_idx, dsthost_idx; struct flow_keys keys, host_keys; if (unlikely(flow_mode == CAKE_FLOW_NONE)) return 0; + /* If both overrides are set we can skip packet dissection entirely */ + if ((flow_override || !(flow_mode & CAKE_FLOW_FLOWS)) && + (host_override || !(flow_mode & CAKE_FLOW_HOSTS))) + goto skip_hash; + skb_flow_dissect_flow_keys(skb, &keys, FLOW_DISSECTOR_F_STOP_AT_FLOW_LABEL); @@ -676,6 +680,14 @@ static u32 cake_hash(struct cake_tin_data *q, const struct sk_buff *skb, if (flow_mode & CAKE_FLOW_FLOWS) flow_hash = flow_hash_from_keys(&keys); +skip_hash: + if (flow_override) + flow_hash = flow_override - 1; + if (host_override) { + dsthost_hash = host_override - 1; + srchost_hash = host_override - 1; + } + if (!(flow_mode & CAKE_FLOW_FLOWS)) { if (flow_mode & CAKE_FLOW_SRC_IP) flow_hash ^= srchost_hash; @@ -1571,7 +1583,7 @@ static u32 cake_classify(struct Qdisc *sch, struct cake_tin_data **t, struct cake_sched_data *q = qdisc_priv(sch); struct tcf_proto *filter; struct tcf_result res; - u32 flow = 0; + u16 flow = 0, host = 0; int result; filter = rcu_dereference_bh(q->filter_list); @@ -1595,10 +1607,12 @@ static u32 cake_classify(struct Qdisc *sch, struct cake_tin_data **t, #endif if (TC_H_MIN(res.classid) <= CAKE_QUEUES) flow = TC_H_MIN(res.classid); + if (TC_H_MAJ(res.classid) <= (CAKE_QUEUES << 16)) + host = TC_H_MAJ(res.classid) >> 16; } hash: *t = cake_select_tin(sch, skb); - return flow ?: cake_hash(*t, skb, flow_mode) + 1; + return cake_hash(*t, skb, flow_mode, flow, host) + 1; } static void cake_reconfigure(struct Qdisc *sch); diff --git a/net/smc/smc_ib.c b/net/smc/smc_ib.c index 9bb5274a244e..e519ef29c0ff 100644 --- a/net/smc/smc_ib.c +++ b/net/smc/smc_ib.c @@ -145,17 +145,21 @@ out: static int smc_ib_fill_mac(struct smc_ib_device *smcibdev, u8 ibport) { - struct ib_gid_attr gattr; - union ib_gid gid; - int rc; + const struct ib_gid_attr *attr; + int rc = 0; - rc = ib_query_gid(smcibdev->ibdev, ibport, 0, &gid, &gattr); - if (rc || !gattr.ndev) + attr = rdma_get_gid_attr(smcibdev->ibdev, ibport, 0); + if (IS_ERR(attr)) return -ENODEV; - memcpy(smcibdev->mac[ibport - 1], gattr.ndev->dev_addr, ETH_ALEN); - dev_put(gattr.ndev); - return 0; + if (attr->ndev) + memcpy(smcibdev->mac[ibport - 1], attr->ndev->dev_addr, + ETH_ALEN); + else + rc = -ENODEV; + + rdma_put_gid_attr(attr); + return rc; } /* Create an identifier unique for this instance of SMC-R. @@ -180,29 +184,27 @@ bool smc_ib_port_active(struct smc_ib_device *smcibdev, u8 ibport) int smc_ib_determine_gid(struct smc_ib_device *smcibdev, u8 ibport, unsigned short vlan_id, u8 gid[], u8 *sgid_index) { - struct ib_gid_attr gattr; - union ib_gid _gid; + const struct ib_gid_attr *attr; int i; for (i = 0; i < smcibdev->pattr[ibport - 1].gid_tbl_len; i++) { - memset(&_gid, 0, SMC_GID_SIZE); - memset(&gattr, 0, sizeof(gattr)); - if (ib_query_gid(smcibdev->ibdev, ibport, i, &_gid, &gattr)) + attr = rdma_get_gid_attr(smcibdev->ibdev, ibport, i); + if (IS_ERR(attr)) continue; - if (!gattr.ndev) - continue; - if (((!vlan_id && !is_vlan_dev(gattr.ndev)) || - (vlan_id && is_vlan_dev(gattr.ndev) && - vlan_dev_vlan_id(gattr.ndev) == vlan_id)) && - gattr.gid_type == IB_GID_TYPE_IB) { + + if (attr->ndev && + ((!vlan_id && !is_vlan_dev(attr->ndev)) || + (vlan_id && is_vlan_dev(attr->ndev) && + vlan_dev_vlan_id(attr->ndev) == vlan_id)) && + attr->gid_type == IB_GID_TYPE_ROCE) { if (gid) - memcpy(gid, &_gid, SMC_GID_SIZE); + memcpy(gid, &attr->gid, SMC_GID_SIZE); if (sgid_index) - *sgid_index = i; - dev_put(gattr.ndev); + *sgid_index = attr->index; + rdma_put_gid_attr(attr); return 0; } - dev_put(gattr.ndev); + rdma_put_gid_attr(attr); } return -ENODEV; } diff --git a/net/sunrpc/auth.c b/net/sunrpc/auth.c index d2623b9f23d6..305ecea92170 100644 --- a/net/sunrpc/auth.c +++ b/net/sunrpc/auth.c @@ -50,7 +50,7 @@ static int param_set_hashtbl_sz(const char *val, const struct kernel_param *kp) if (!val) goto out_inval; ret = kstrtoul(val, 0, &num); - if (ret == -EINVAL) + if (ret) goto out_inval; nbits = fls(num - 1); if (nbits > MAX_HASHTABLE_BITS || nbits < 2) @@ -253,7 +253,7 @@ rpcauth_list_flavors(rpc_authflavor_t *array, int size) EXPORT_SYMBOL_GPL(rpcauth_list_flavors); struct rpc_auth * -rpcauth_create(struct rpc_auth_create_args *args, struct rpc_clnt *clnt) +rpcauth_create(const struct rpc_auth_create_args *args, struct rpc_clnt *clnt) { struct rpc_auth *auth; const struct rpc_authops *ops; diff --git a/net/sunrpc/auth_gss/auth_gss.c b/net/sunrpc/auth_gss/auth_gss.c index 0fc397fae42b..21c0aa0a0d1d 100644 --- a/net/sunrpc/auth_gss/auth_gss.c +++ b/net/sunrpc/auth_gss/auth_gss.c @@ -284,7 +284,12 @@ err: return p; } -#define UPCALL_BUF_LEN 128 +/* XXX: Need some documentation about why UPCALL_BUF_LEN is so small. + * Is user space expecting no more than UPCALL_BUF_LEN bytes? + * Note that there are now _two_ NI_MAXHOST sized data items + * being passed in this string. + */ +#define UPCALL_BUF_LEN 256 struct gss_upcall_msg { refcount_t count; @@ -456,18 +461,44 @@ static int gss_encode_v1_msg(struct gss_upcall_msg *gss_msg, buflen -= len; p += len; gss_msg->msg.len = len; + + /* + * target= is a full service principal that names the remote + * identity that we are authenticating to. + */ if (target_name) { len = scnprintf(p, buflen, "target=%s ", target_name); buflen -= len; p += len; gss_msg->msg.len += len; } - if (service_name != NULL) { - len = scnprintf(p, buflen, "service=%s ", service_name); + + /* + * gssd uses service= and srchost= to select a matching key from + * the system's keytab to use as the source principal. + * + * service= is the service name part of the source principal, + * or "*" (meaning choose any). + * + * srchost= is the hostname part of the source principal. When + * not provided, gssd uses the local hostname. + */ + if (service_name) { + char *c = strchr(service_name, '@'); + + if (!c) + len = scnprintf(p, buflen, "service=%s ", + service_name); + else + len = scnprintf(p, buflen, + "service=%.*s srchost=%s ", + (int)(c - service_name), + service_name, c + 1); buflen -= len; p += len; gss_msg->msg.len += len; } + if (mech->gm_upcall_enctypes) { len = scnprintf(p, buflen, "enctypes=%s ", mech->gm_upcall_enctypes); @@ -985,7 +1016,7 @@ static void gss_pipe_free(struct gss_pipe *p) * parameters based on the input flavor (which must be a pseudoflavor) */ static struct gss_auth * -gss_create_new(struct rpc_auth_create_args *args, struct rpc_clnt *clnt) +gss_create_new(const struct rpc_auth_create_args *args, struct rpc_clnt *clnt) { rpc_authflavor_t flavor = args->pseudoflavor; struct gss_auth *gss_auth; @@ -1132,7 +1163,7 @@ gss_destroy(struct rpc_auth *auth) * (which is guaranteed to last as long as any of its descendants). */ static struct gss_auth * -gss_auth_find_or_add_hashed(struct rpc_auth_create_args *args, +gss_auth_find_or_add_hashed(const struct rpc_auth_create_args *args, struct rpc_clnt *clnt, struct gss_auth *new) { @@ -1169,7 +1200,8 @@ out: } static struct gss_auth * -gss_create_hashed(struct rpc_auth_create_args *args, struct rpc_clnt *clnt) +gss_create_hashed(const struct rpc_auth_create_args *args, + struct rpc_clnt *clnt) { struct gss_auth *gss_auth; struct gss_auth *new; @@ -1188,7 +1220,7 @@ out: } static struct rpc_auth * -gss_create(struct rpc_auth_create_args *args, struct rpc_clnt *clnt) +gss_create(const struct rpc_auth_create_args *args, struct rpc_clnt *clnt) { struct gss_auth *gss_auth; struct rpc_xprt_switch *xps = rcu_access_pointer(clnt->cl_xpi.xpi_xpswitch); @@ -1571,7 +1603,7 @@ static int gss_cred_is_negative_entry(struct rpc_cred *cred) if (test_bit(RPCAUTH_CRED_NEGATIVE, &cred->cr_flags)) { unsigned long now = jiffies; unsigned long begin, expire; - struct gss_cred *gss_cred; + struct gss_cred *gss_cred; gss_cred = container_of(cred, struct gss_cred, gc_base); begin = gss_cred->gc_upcall_timestamp; diff --git a/net/sunrpc/auth_gss/gss_generic_token.c b/net/sunrpc/auth_gss/gss_generic_token.c index 254defe446a7..fe97f3106536 100644 --- a/net/sunrpc/auth_gss/gss_generic_token.c +++ b/net/sunrpc/auth_gss/gss_generic_token.c @@ -231,4 +231,3 @@ g_verify_token_header(struct xdr_netobj *mech, int *body_size, } EXPORT_SYMBOL_GPL(g_verify_token_header); - diff --git a/net/sunrpc/auth_gss/gss_krb5_crypto.c b/net/sunrpc/auth_gss/gss_krb5_crypto.c index 8654494b4d0a..0220e1ca5280 100644 --- a/net/sunrpc/auth_gss/gss_krb5_crypto.c +++ b/net/sunrpc/auth_gss/gss_krb5_crypto.c @@ -169,7 +169,7 @@ make_checksum_hmac_md5(struct krb5_ctx *kctx, char *header, int hdrlen, struct scatterlist sg[1]; int err = -1; u8 *checksumdata; - u8 rc4salt[4]; + u8 *rc4salt; struct crypto_ahash *md5; struct crypto_ahash *hmac_md5; struct ahash_request *req; @@ -183,14 +183,18 @@ make_checksum_hmac_md5(struct krb5_ctx *kctx, char *header, int hdrlen, return GSS_S_FAILURE; } + rc4salt = kmalloc_array(4, sizeof(*rc4salt), GFP_NOFS); + if (!rc4salt) + return GSS_S_FAILURE; + if (arcfour_hmac_md5_usage_to_salt(usage, rc4salt)) { dprintk("%s: invalid usage value %u\n", __func__, usage); - return GSS_S_FAILURE; + goto out_free_rc4salt; } checksumdata = kmalloc(GSS_KRB5_MAX_CKSUM_LEN, GFP_NOFS); if (!checksumdata) - return GSS_S_FAILURE; + goto out_free_rc4salt; md5 = crypto_alloc_ahash("md5", 0, CRYPTO_ALG_ASYNC); if (IS_ERR(md5)) @@ -258,6 +262,8 @@ out_free_md5: crypto_free_ahash(md5); out_free_cksum: kfree(checksumdata); +out_free_rc4salt: + kfree(rc4salt); return err ? GSS_S_FAILURE : 0; } @@ -373,7 +379,6 @@ make_checksum_v2(struct krb5_ctx *kctx, char *header, int hdrlen, struct scatterlist sg[1]; int err = -1; u8 *checksumdata; - unsigned int checksumlen; if (kctx->gk5e->keyed_cksum == 0) { dprintk("%s: expected keyed hash for %s\n", @@ -393,7 +398,6 @@ make_checksum_v2(struct krb5_ctx *kctx, char *header, int hdrlen, tfm = crypto_alloc_ahash(kctx->gk5e->cksum_name, 0, CRYPTO_ALG_ASYNC); if (IS_ERR(tfm)) goto out_free_cksum; - checksumlen = crypto_ahash_digestsize(tfm); req = ahash_request_alloc(tfm, GFP_NOFS); if (!req) @@ -1077,4 +1081,3 @@ out_err: dprintk("%s: returning %d\n", __func__, err); return err; } - diff --git a/net/sunrpc/auth_gss/gss_krb5_keys.c b/net/sunrpc/auth_gss/gss_krb5_keys.c index 870133146026..f7fe2d2b851f 100644 --- a/net/sunrpc/auth_gss/gss_krb5_keys.c +++ b/net/sunrpc/auth_gss/gss_krb5_keys.c @@ -324,4 +324,3 @@ u32 gss_krb5_aes_make_key(const struct gss_krb5_enctype *gk5e, err_out: return ret; } - diff --git a/net/sunrpc/auth_gss/gss_krb5_seal.c b/net/sunrpc/auth_gss/gss_krb5_seal.c index 94a2b3f082a8..eaad9bc7a0bd 100644 --- a/net/sunrpc/auth_gss/gss_krb5_seal.c +++ b/net/sunrpc/auth_gss/gss_krb5_seal.c @@ -229,4 +229,3 @@ gss_get_mic_kerberos(struct gss_ctx *gss_ctx, struct xdr_buf *text, return gss_get_mic_v2(ctx, text, token); } } - diff --git a/net/sunrpc/auth_gss/gss_krb5_unseal.c b/net/sunrpc/auth_gss/gss_krb5_unseal.c index b601a73cc9db..ef2b25b86d2f 100644 --- a/net/sunrpc/auth_gss/gss_krb5_unseal.c +++ b/net/sunrpc/auth_gss/gss_krb5_unseal.c @@ -225,4 +225,3 @@ gss_verify_mic_kerberos(struct gss_ctx *gss_ctx, return gss_verify_mic_v2(ctx, message_buffer, read_token); } } - diff --git a/net/sunrpc/auth_gss/gss_krb5_wrap.c b/net/sunrpc/auth_gss/gss_krb5_wrap.c index a737c2da0837..39a2e672900b 100644 --- a/net/sunrpc/auth_gss/gss_krb5_wrap.c +++ b/net/sunrpc/auth_gss/gss_krb5_wrap.c @@ -440,7 +440,6 @@ static u32 gss_wrap_kerberos_v2(struct krb5_ctx *kctx, u32 offset, struct xdr_buf *buf, struct page **pages) { - int blocksize; u8 *ptr, *plainhdr; s32 now; u8 flags = 0x00; @@ -473,7 +472,6 @@ gss_wrap_kerberos_v2(struct krb5_ctx *kctx, u32 offset, *ptr++ = 0xff; be16ptr = (__be16 *)ptr; - blocksize = crypto_skcipher_blocksize(kctx->acceptor_enc); *be16ptr++ = 0; /* "inner" token header always uses 0 for RRC */ *be16ptr++ = 0; @@ -623,4 +621,3 @@ gss_unwrap_kerberos(struct gss_ctx *gctx, int offset, struct xdr_buf *buf) return gss_unwrap_kerberos_v2(kctx, offset, buf); } } - diff --git a/net/sunrpc/auth_gss/gss_rpc_upcall.c b/net/sunrpc/auth_gss/gss_rpc_upcall.c index 1c7c49dbf8ba..73dcda060335 100644 --- a/net/sunrpc/auth_gss/gss_rpc_upcall.c +++ b/net/sunrpc/auth_gss/gss_rpc_upcall.c @@ -234,6 +234,35 @@ static int gssp_alloc_receive_pages(struct gssx_arg_accept_sec_context *arg) return 0; } +static char *gssp_stringify(struct xdr_netobj *netobj) +{ + return kstrndup(netobj->data, netobj->len, GFP_KERNEL); +} + +static void gssp_hostbased_service(char **principal) +{ + char *c; + + if (!*principal) + return; + + /* terminate and remove realm part */ + c = strchr(*principal, '@'); + if (c) { + *c = '\0'; + + /* change service-hostname delimiter */ + c = strchr(*principal, '/'); + if (c) + *c = '@'; + } + if (!c) { + /* not a service principal */ + kfree(*principal); + *principal = NULL; + } +} + /* * Public functions */ @@ -262,6 +291,7 @@ int gssp_accept_sec_context_upcall(struct net *net, */ .exported_context_token.len = GSSX_max_output_handle_sz, .mech.len = GSS_OID_MAX_LEN, + .targ_name.display_name.len = GSSX_max_princ_sz, .src_name.display_name.len = GSSX_max_princ_sz }; struct gssx_res_accept_sec_context res = { @@ -275,6 +305,7 @@ int gssp_accept_sec_context_upcall(struct net *net, .rpc_cred = NULL, /* FIXME ? */ }; struct xdr_netobj client_name = { 0 , NULL }; + struct xdr_netobj target_name = { 0, NULL }; int ret; if (data->in_handle.len != 0) @@ -285,8 +316,6 @@ int gssp_accept_sec_context_upcall(struct net *net, if (ret) return ret; - /* use nfs/ for targ_name ? */ - ret = gssp_call(net, &msg); gssp_free_receive_pages(&arg); @@ -304,6 +333,7 @@ int gssp_accept_sec_context_upcall(struct net *net, kfree(rctxh.mech.data); } client_name = rctxh.src_name.display_name; + target_name = rctxh.targ_name.display_name; } if (res.options.count == 1) { @@ -325,32 +355,22 @@ int gssp_accept_sec_context_upcall(struct net *net, } /* convert to GSS_NT_HOSTBASED_SERVICE form and set into creds */ - if (data->found_creds && client_name.data != NULL) { - char *c; - - data->creds.cr_raw_principal = kstrndup(client_name.data, - client_name.len, GFP_KERNEL); - - data->creds.cr_principal = kstrndup(client_name.data, - client_name.len, GFP_KERNEL); - if (data->creds.cr_principal) { - /* terminate and remove realm part */ - c = strchr(data->creds.cr_principal, '@'); - if (c) { - *c = '\0'; - - /* change service-hostname delimiter */ - c = strchr(data->creds.cr_principal, '/'); - if (c) *c = '@'; - } - if (!c) { - /* not a service principal */ - kfree(data->creds.cr_principal); - data->creds.cr_principal = NULL; - } + if (data->found_creds) { + if (client_name.data) { + data->creds.cr_raw_principal = + gssp_stringify(&client_name); + data->creds.cr_principal = + gssp_stringify(&client_name); + gssp_hostbased_service(&data->creds.cr_principal); + } + if (target_name.data) { + data->creds.cr_targ_princ = + gssp_stringify(&target_name); + gssp_hostbased_service(&data->creds.cr_targ_princ); } } kfree(client_name.data); + kfree(target_name.data); return ret; } diff --git a/net/sunrpc/auth_gss/svcauth_gss.c b/net/sunrpc/auth_gss/svcauth_gss.c index 5089dbb96d58..860f2a1bbb67 100644 --- a/net/sunrpc/auth_gss/svcauth_gss.c +++ b/net/sunrpc/auth_gss/svcauth_gss.c @@ -1389,7 +1389,7 @@ static void destroy_use_gss_proxy_proc_entry(struct net *net) struct sunrpc_net *sn = net_generic(net, sunrpc_net_id); if (sn->use_gssp_proc) { - remove_proc_entry("use-gss-proxy", sn->proc_net_rpc); + remove_proc_entry("use-gss-proxy", sn->proc_net_rpc); clear_gssp_clnt(sn); } } diff --git a/net/sunrpc/auth_null.c b/net/sunrpc/auth_null.c index 75d72e109a04..4b48228ee8c7 100644 --- a/net/sunrpc/auth_null.c +++ b/net/sunrpc/auth_null.c @@ -19,7 +19,7 @@ static struct rpc_auth null_auth; static struct rpc_cred null_cred; static struct rpc_auth * -nul_create(struct rpc_auth_create_args *args, struct rpc_clnt *clnt) +nul_create(const struct rpc_auth_create_args *args, struct rpc_clnt *clnt) { atomic_inc(&null_auth.au_count); return &null_auth; diff --git a/net/sunrpc/auth_unix.c b/net/sunrpc/auth_unix.c index dafd6b870ba3..185e56d4f9ae 100644 --- a/net/sunrpc/auth_unix.c +++ b/net/sunrpc/auth_unix.c @@ -30,7 +30,7 @@ static struct rpc_auth unix_auth; static const struct rpc_credops unix_credops; static struct rpc_auth * -unx_create(struct rpc_auth_create_args *args, struct rpc_clnt *clnt) +unx_create(const struct rpc_auth_create_args *args, struct rpc_clnt *clnt) { dprintk("RPC: creating UNIX authenticator for client %p\n", clnt); diff --git a/net/sunrpc/backchannel_rqst.c b/net/sunrpc/backchannel_rqst.c index c2c68a15b59d..3c15a99b9700 100644 --- a/net/sunrpc/backchannel_rqst.c +++ b/net/sunrpc/backchannel_rqst.c @@ -362,4 +362,3 @@ void xprt_complete_bc_request(struct rpc_rqst *req, uint32_t copied) wake_up(&bc_serv->sv_cb_waitq); spin_unlock(&bc_serv->sv_cb_lock); } - diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c index d839c33ae7d9..8ea2f5fadd96 100644 --- a/net/sunrpc/clnt.c +++ b/net/sunrpc/clnt.c @@ -892,7 +892,7 @@ rpc_free_client(struct rpc_clnt *clnt) /* * Free an RPC client */ -static struct rpc_clnt * +static struct rpc_clnt * rpc_free_auth(struct rpc_clnt *clnt) { if (clnt->cl_auth == NULL) @@ -965,10 +965,20 @@ out: } EXPORT_SYMBOL_GPL(rpc_bind_new_program); +void rpc_task_release_transport(struct rpc_task *task) +{ + struct rpc_xprt *xprt = task->tk_xprt; + + if (xprt) { + task->tk_xprt = NULL; + xprt_put(xprt); + } +} +EXPORT_SYMBOL_GPL(rpc_task_release_transport); + void rpc_task_release_client(struct rpc_task *task) { struct rpc_clnt *clnt = task->tk_client; - struct rpc_xprt *xprt = task->tk_xprt; if (clnt != NULL) { /* Remove from client task list */ @@ -979,12 +989,14 @@ void rpc_task_release_client(struct rpc_task *task) rpc_release_client(clnt); } + rpc_task_release_transport(task); +} - if (xprt != NULL) { - task->tk_xprt = NULL; - - xprt_put(xprt); - } +static +void rpc_task_set_transport(struct rpc_task *task, struct rpc_clnt *clnt) +{ + if (!task->tk_xprt) + task->tk_xprt = xprt_iter_get_next(&clnt->cl_xpi); } static @@ -992,8 +1004,7 @@ void rpc_task_set_client(struct rpc_task *task, struct rpc_clnt *clnt) { if (clnt != NULL) { - if (task->tk_xprt == NULL) - task->tk_xprt = xprt_iter_get_next(&clnt->cl_xpi); + rpc_task_set_transport(task, clnt); task->tk_client = clnt; atomic_inc(&clnt->cl_count); if (clnt->cl_softrtry) @@ -1512,6 +1523,7 @@ call_start(struct rpc_task *task) clnt->cl_program->version[clnt->cl_vers]->counts[idx]++; clnt->cl_stats->rpccnt++; task->tk_action = call_reserve; + rpc_task_set_transport(task, clnt); } /* diff --git a/net/sunrpc/rpcb_clnt.c b/net/sunrpc/rpcb_clnt.c index c526f8fb37c9..c7872bc13860 100644 --- a/net/sunrpc/rpcb_clnt.c +++ b/net/sunrpc/rpcb_clnt.c @@ -213,7 +213,7 @@ static void rpcb_set_local(struct net *net, struct rpc_clnt *clnt, sn->rpcb_local_clnt = clnt; sn->rpcb_local_clnt4 = clnt4; sn->rpcb_is_af_local = is_af_local ? 1 : 0; - smp_wmb(); + smp_wmb(); sn->rpcb_users = 1; dprintk("RPC: created new rpcb local clients (rpcb_local_clnt: " "%p, rpcb_local_clnt4: %p) for net %x%s\n", diff --git a/net/sunrpc/stats.c b/net/sunrpc/stats.c index f68aa46c9dd7..71166b393732 100644 --- a/net/sunrpc/stats.c +++ b/net/sunrpc/stats.c @@ -208,13 +208,39 @@ static void _print_name(struct seq_file *seq, unsigned int op, seq_printf(seq, "\t%12u: ", op); } -void rpc_print_iostats(struct seq_file *seq, struct rpc_clnt *clnt) +static void _add_rpc_iostats(struct rpc_iostats *a, struct rpc_iostats *b) +{ + a->om_ops += b->om_ops; + a->om_ntrans += b->om_ntrans; + a->om_timeouts += b->om_timeouts; + a->om_bytes_sent += b->om_bytes_sent; + a->om_bytes_recv += b->om_bytes_recv; + a->om_queue = ktime_add(a->om_queue, b->om_queue); + a->om_rtt = ktime_add(a->om_rtt, b->om_rtt); + a->om_execute = ktime_add(a->om_execute, b->om_execute); +} + +static void _print_rpc_iostats(struct seq_file *seq, struct rpc_iostats *stats, + int op, const struct rpc_procinfo *procs) +{ + _print_name(seq, op, procs); + seq_printf(seq, "%lu %lu %lu %Lu %Lu %Lu %Lu %Lu\n", + stats->om_ops, + stats->om_ntrans, + stats->om_timeouts, + stats->om_bytes_sent, + stats->om_bytes_recv, + ktime_to_ms(stats->om_queue), + ktime_to_ms(stats->om_rtt), + ktime_to_ms(stats->om_execute)); +} + +void rpc_clnt_show_stats(struct seq_file *seq, struct rpc_clnt *clnt) { - struct rpc_iostats *stats = clnt->cl_metrics; struct rpc_xprt *xprt; unsigned int op, maxproc = clnt->cl_maxproc; - if (!stats) + if (!clnt->cl_metrics) return; seq_printf(seq, "\tRPC iostats version: %s ", RPC_IOSTATS_VERS); @@ -229,20 +255,18 @@ void rpc_print_iostats(struct seq_file *seq, struct rpc_clnt *clnt) seq_printf(seq, "\tper-op statistics\n"); for (op = 0; op < maxproc; op++) { - struct rpc_iostats *metrics = &stats[op]; - _print_name(seq, op, clnt->cl_procinfo); - seq_printf(seq, "%lu %lu %lu %Lu %Lu %Lu %Lu %Lu\n", - metrics->om_ops, - metrics->om_ntrans, - metrics->om_timeouts, - metrics->om_bytes_sent, - metrics->om_bytes_recv, - ktime_to_ms(metrics->om_queue), - ktime_to_ms(metrics->om_rtt), - ktime_to_ms(metrics->om_execute)); + struct rpc_iostats stats = {}; + struct rpc_clnt *next = clnt; + do { + _add_rpc_iostats(&stats, &next->cl_metrics[op]); + if (next == next->cl_parent) + break; + next = next->cl_parent; + } while (next); + _print_rpc_iostats(seq, &stats, op, clnt->cl_procinfo); } } -EXPORT_SYMBOL_GPL(rpc_print_iostats); +EXPORT_SYMBOL_GPL(rpc_clnt_show_stats); /* * Register/unregister RPC proc files @@ -310,4 +334,3 @@ void rpc_proc_exit(struct net *net) dprintk("RPC: unregistering /proc/net/rpc\n"); remove_proc_entry("rpc", net->proc_net); } - diff --git a/net/sunrpc/sunrpc.h b/net/sunrpc/sunrpc.h index 09a0315ea77b..c9bacb3c930f 100644 --- a/net/sunrpc/sunrpc.h +++ b/net/sunrpc/sunrpc.h @@ -57,4 +57,3 @@ int svc_send_common(struct socket *sock, struct xdr_buf *xdr, int rpc_clients_notifier_register(void); void rpc_clients_notifier_unregister(void); #endif /* _NET_SUNRPC_SUNRPC_H */ - diff --git a/net/sunrpc/svc.c b/net/sunrpc/svc.c index 30a4226baf03..d13e05f1a990 100644 --- a/net/sunrpc/svc.c +++ b/net/sunrpc/svc.c @@ -1537,16 +1537,16 @@ EXPORT_SYMBOL_GPL(svc_max_payload); /** * svc_fill_write_vector - Construct data argument for VFS write call * @rqstp: svc_rqst to operate on + * @pages: list of pages containing data payload * @first: buffer containing first section of write payload * @total: total number of bytes of write payload * - * Returns the number of elements populated in the data argument array. + * Fills in rqstp::rq_vec, and returns the number of elements. */ -unsigned int svc_fill_write_vector(struct svc_rqst *rqstp, struct kvec *first, - size_t total) +unsigned int svc_fill_write_vector(struct svc_rqst *rqstp, struct page **pages, + struct kvec *first, size_t total) { struct kvec *vec = rqstp->rq_vec; - struct page **pages; unsigned int i; /* Some types of transport can present the write payload @@ -1560,14 +1560,11 @@ unsigned int svc_fill_write_vector(struct svc_rqst *rqstp, struct kvec *first, ++i; } - WARN_ON_ONCE(rqstp->rq_arg.page_base != 0); - pages = rqstp->rq_arg.pages; while (total) { vec[i].iov_base = page_address(*pages); vec[i].iov_len = min_t(size_t, total, PAGE_SIZE); total -= vec[i].iov_len; ++i; - ++pages; } @@ -1580,65 +1577,48 @@ EXPORT_SYMBOL_GPL(svc_fill_write_vector); * svc_fill_symlink_pathname - Construct pathname argument for VFS symlink call * @rqstp: svc_rqst to operate on * @first: buffer containing first section of pathname + * @p: buffer containing remaining section of pathname * @total: total length of the pathname argument * - * Returns pointer to a NUL-terminated string, or an ERR_PTR. The buffer is - * released automatically when @rqstp is recycled. + * The VFS symlink API demands a NUL-terminated pathname in mapped memory. + * Returns pointer to a NUL-terminated string, or an ERR_PTR. Caller must free + * the returned string. */ char *svc_fill_symlink_pathname(struct svc_rqst *rqstp, struct kvec *first, - size_t total) + void *p, size_t total) { - struct xdr_buf *arg = &rqstp->rq_arg; - struct page **pages; - char *result; - - /* VFS API demands a NUL-terminated pathname. This function - * uses a page from @rqstp as the pathname buffer, to enable - * direct placement. Thus the total buffer size is PAGE_SIZE. - * Space in this buffer for NUL-termination requires that we - * cap the size of the returned symlink pathname just a - * little early. - */ - if (total > PAGE_SIZE - 1) - return ERR_PTR(-ENAMETOOLONG); + size_t len, remaining; + char *result, *dst; - /* Some types of transport can present the pathname entirely - * in rq_arg.pages. If not, then copy the pathname into one - * page. - */ - pages = arg->pages; - WARN_ON_ONCE(arg->page_base != 0); - if (first->iov_base == 0) { - result = page_address(*pages); - result[total] = '\0'; - } else { - size_t len, remaining; - char *dst; + result = kmalloc(total + 1, GFP_KERNEL); + if (!result) + return ERR_PTR(-ESERVERFAULT); - result = page_address(*(rqstp->rq_next_page++)); - dst = result; - remaining = total; + dst = result; + remaining = total; - len = min_t(size_t, total, first->iov_len); + len = min_t(size_t, total, first->iov_len); + if (len) { memcpy(dst, first->iov_base, len); dst += len; remaining -= len; + } - /* No more than one page left */ - if (remaining) { - len = min_t(size_t, remaining, PAGE_SIZE); - memcpy(dst, page_address(*pages), len); - dst += len; - } - - *dst = '\0'; + if (remaining) { + len = min_t(size_t, remaining, PAGE_SIZE); + memcpy(dst, p, len); + dst += len; } - /* Sanity check: we don't allow the pathname argument to + *dst = '\0'; + + /* Sanity check: Linux doesn't allow the pathname argument to * contain a NUL byte. */ - if (strlen(result) != total) + if (strlen(result) != total) { + kfree(result); return ERR_PTR(-EINVAL); + } return result; } EXPORT_SYMBOL_GPL(svc_fill_symlink_pathname); diff --git a/net/sunrpc/xprt.c b/net/sunrpc/xprt.c index 3fabf9f6a0f9..a8db2e3f8904 100644 --- a/net/sunrpc/xprt.c +++ b/net/sunrpc/xprt.c @@ -880,7 +880,7 @@ static void xprt_wait_on_pinned_rqst(struct rpc_rqst *req) __must_hold(&req->rq_xprt->recv_lock) { struct rpc_task *task = req->rq_task; - + if (task && test_bit(RPC_TASK_MSG_RECV, &task->tk_runstate)) { spin_unlock(&req->rq_xprt->recv_lock); set_bit(RPC_TASK_MSG_RECV_WAIT, &task->tk_runstate); diff --git a/net/sunrpc/xprtrdma/svc_rdma.c b/net/sunrpc/xprtrdma/svc_rdma.c index 357ba90c382d..134bef6a451e 100644 --- a/net/sunrpc/xprtrdma/svc_rdma.c +++ b/net/sunrpc/xprtrdma/svc_rdma.c @@ -94,7 +94,6 @@ static int read_reset_stat(struct ctl_table *table, int write, atomic_set(stat, 0); else { char str_buf[32]; - char *data; int len = snprintf(str_buf, 32, "%d\n", atomic_read(stat)); if (len >= 32) return -EFAULT; @@ -103,7 +102,6 @@ static int read_reset_stat(struct ctl_table *table, int write, *lenp = 0; return 0; } - data = &str_buf[*ppos]; len -= *ppos; if (len > *lenp) len = *lenp; diff --git a/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c b/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c index 2ef75e885411..b24d5b8f2fee 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c +++ b/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c @@ -365,9 +365,6 @@ static void svc_rdma_build_arg_xdr(struct svc_rqst *rqstp, arg->page_base = 0; arg->buflen = ctxt->rc_byte_len; arg->len = ctxt->rc_byte_len; - - rqstp->rq_respages = &rqstp->rq_pages[0]; - rqstp->rq_next_page = rqstp->rq_respages + 1; } /* This accommodates the largest possible Write chunk, @@ -729,6 +726,12 @@ int svc_rdma_recvfrom(struct svc_rqst *rqstp) svc_rdma_build_arg_xdr(rqstp, ctxt); + /* Prevent svc_xprt_release from releasing pages in rq_pages + * if we return 0 or an error. + */ + rqstp->rq_respages = rqstp->rq_pages; + rqstp->rq_next_page = rqstp->rq_respages; + p = (__be32 *)rqstp->rq_arg.head[0].iov_base; ret = svc_rdma_xdr_decode_req(&rqstp->rq_arg); if (ret < 0) diff --git a/net/sunrpc/xprtrdma/svc_rdma_rw.c b/net/sunrpc/xprtrdma/svc_rdma_rw.c index 04cb3363172a..dc1951759a8e 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_rw.c +++ b/net/sunrpc/xprtrdma/svc_rdma_rw.c @@ -680,6 +680,7 @@ static int svc_rdma_build_read_chunk(struct svc_rqst *rqstp, struct svc_rdma_read_info *info, __be32 *p) { + unsigned int i; int ret; ret = -EINVAL; @@ -702,6 +703,12 @@ static int svc_rdma_build_read_chunk(struct svc_rqst *rqstp, info->ri_chunklen += rs_length; } + /* Pages under I/O have been copied to head->rc_pages. + * Prevent their premature release by svc_xprt_release() . + */ + for (i = 0; i < info->ri_readctxt->rc_page_count; i++) + rqstp->rq_pages[i] = NULL; + return ret; } @@ -817,7 +824,6 @@ int svc_rdma_recv_read_chunk(struct svcxprt_rdma *rdma, struct svc_rqst *rqstp, struct svc_rdma_recv_ctxt *head, __be32 *p) { struct svc_rdma_read_info *info; - struct page **page; int ret; /* The request (with page list) is constructed in @@ -844,27 +850,15 @@ int svc_rdma_recv_read_chunk(struct svcxprt_rdma *rdma, struct svc_rqst *rqstp, ret = svc_rdma_build_normal_read_chunk(rqstp, info, p); else ret = svc_rdma_build_pz_read_chunk(rqstp, info, p); - - /* Mark the start of the pages that can be used for the reply */ - if (info->ri_pageoff > 0) - info->ri_pageno++; - rqstp->rq_respages = &rqstp->rq_pages[info->ri_pageno]; - rqstp->rq_next_page = rqstp->rq_respages + 1; - if (ret < 0) - goto out; + goto out_err; ret = svc_rdma_post_chunk_ctxt(&info->ri_cc); - -out: - /* Read sink pages have been moved from rqstp->rq_pages to - * head->rc_arg.pages. Force svc_recv to refill those slots - * in rq_pages. - */ - for (page = rqstp->rq_pages; page < rqstp->rq_respages; page++) - *page = NULL; - if (ret < 0) - svc_rdma_read_info_free(info); + goto out_err; + return 0; + +out_err: + svc_rdma_read_info_free(info); return ret; } diff --git a/net/sunrpc/xprtrdma/svc_rdma_sendto.c b/net/sunrpc/xprtrdma/svc_rdma_sendto.c index ffef0c508f1a..8602a5f1b515 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_sendto.c +++ b/net/sunrpc/xprtrdma/svc_rdma_sendto.c @@ -656,7 +656,9 @@ static void svc_rdma_save_io_pages(struct svc_rqst *rqstp, ctxt->sc_pages[i] = rqstp->rq_respages[i]; rqstp->rq_respages[i] = NULL; } - rqstp->rq_next_page = rqstp->rq_respages + 1; + + /* Prevent svc_xprt_release from releasing pages in rq_pages */ + rqstp->rq_next_page = rqstp->rq_respages; } /* Prepare the portion of the RPC Reply that will be transmitted diff --git a/net/sunrpc/xprtrdma/svc_rdma_transport.c b/net/sunrpc/xprtrdma/svc_rdma_transport.c index 547b2cdf1427..2848cafd4a17 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_transport.c +++ b/net/sunrpc/xprtrdma/svc_rdma_transport.c @@ -296,7 +296,6 @@ static int rdma_listen_handler(struct rdma_cm_id *cma_id, struct rdma_cm_event *event) { struct sockaddr *sap = (struct sockaddr *)&cma_id->route.addr.src_addr; - int ret = 0; trace_svcrdma_cm_event(event, sap); @@ -315,7 +314,7 @@ static int rdma_listen_handler(struct rdma_cm_id *cma_id, break; } - return ret; + return 0; } static int rdma_cma_handler(struct rdma_cm_id *cma_id, diff --git a/net/sunrpc/xprtrdma/verbs.c b/net/sunrpc/xprtrdma/verbs.c index 5efeba08918b..956a5ea47b58 100644 --- a/net/sunrpc/xprtrdma/verbs.c +++ b/net/sunrpc/xprtrdma/verbs.c @@ -280,7 +280,6 @@ rpcrdma_conn_upcall(struct rdma_cm_id *id, struct rdma_cm_event *event) ++xprt->rx_xprt.connect_cookie; connstate = -ECONNABORTED; connected: - xprt->rx_buf.rb_credits = 1; ep->rep_connected = connstate; rpcrdma_conn_func(ep); wake_up_all(&ep->rep_connect_wait); @@ -755,6 +754,7 @@ retry: } ep->rep_connected = 0; + rpcrdma_post_recvs(r_xprt, true); rc = rdma_connect(ia->ri_id, &ep->rep_remote_cma); if (rc) { @@ -773,8 +773,6 @@ retry: dprintk("RPC: %s: connected\n", __func__); - rpcrdma_post_recvs(r_xprt, true); - out: if (rc) ep->rep_connected = rc; @@ -1171,6 +1169,7 @@ rpcrdma_buffer_create(struct rpcrdma_xprt *r_xprt) list_add(&req->rl_list, &buf->rb_send_bufs); } + buf->rb_credits = 1; buf->rb_posted_receives = 0; INIT_LIST_HEAD(&buf->rb_recv_bufs); diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c index 9e1c5024aba9..6b7539c0466e 100644 --- a/net/sunrpc/xprtsock.c +++ b/net/sunrpc/xprtsock.c @@ -3375,4 +3375,3 @@ module_param_named(tcp_max_slot_table_entries, xprt_max_tcp_slot_table_entries, max_slot_table_size, 0644); module_param_named(udp_slot_table_entries, xprt_udp_slot_table_entries, slot_table_size, 0644); - diff --git a/net/tls/tls_main.c b/net/tls/tls_main.c index 93c0c225ab34..180b6640e531 100644 --- a/net/tls/tls_main.c +++ b/net/tls/tls_main.c @@ -213,9 +213,14 @@ static void tls_write_space(struct sock *sk) { struct tls_context *ctx = tls_get_ctx(sk); - /* We are already sending pages, ignore notification */ - if (ctx->in_tcp_sendpages) + /* If in_tcp_sendpages call lower protocol write space handler + * to ensure we wake up any waiting operations there. For example + * if do_tcp_sendpages where to call sk_wait_event. + */ + if (ctx->in_tcp_sendpages) { + ctx->sk_write_space(sk); return; + } if (!sk->sk_write_pending && tls_is_pending_closed_record(ctx)) { gfp_t sk_allocation = sk->sk_allocation; diff --git a/net/xdp/xdp_umem.c b/net/xdp/xdp_umem.c index 911ca6d3cb5a..bfe2dbea480b 100644 --- a/net/xdp/xdp_umem.c +++ b/net/xdp/xdp_umem.c @@ -74,14 +74,14 @@ int xdp_umem_assign_dev(struct xdp_umem *umem, struct net_device *dev, return 0; if (!dev->netdev_ops->ndo_bpf || !dev->netdev_ops->ndo_xsk_async_xmit) - return force_zc ? -ENOTSUPP : 0; /* fail or fallback */ + return force_zc ? -EOPNOTSUPP : 0; /* fail or fallback */ bpf.command = XDP_QUERY_XSK_UMEM; rtnl_lock(); err = xdp_umem_query(dev, queue_id); if (err) { - err = err < 0 ? -ENOTSUPP : -EBUSY; + err = err < 0 ? -EOPNOTSUPP : -EBUSY; goto err_rtnl_unlock; } |
