diff options
Diffstat (limited to 'net')
211 files changed, 1567 insertions, 1049 deletions
diff --git a/net/8021q/vlan_dev.c b/net/8021q/vlan_dev.c index c8d6a07e23c5..3dd7c972677b 100644 --- a/net/8021q/vlan_dev.c +++ b/net/8021q/vlan_dev.c @@ -503,11 +503,10 @@ static void vlan_dev_set_lockdep_one(struct net_device *dev, lockdep_set_class(&txq->_xmit_lock, &vlan_netdev_xmit_lock_key); } -static void vlan_dev_set_lockdep_class(struct net_device *dev, int subclass) +static void vlan_dev_set_lockdep_class(struct net_device *dev) { - lockdep_set_class_and_subclass(&dev->addr_list_lock, - &vlan_netdev_addr_lock_key, - subclass); + lockdep_set_class(&dev->addr_list_lock, + &vlan_netdev_addr_lock_key); netdev_for_each_tx_queue(dev, vlan_dev_set_lockdep_one, NULL); } @@ -601,7 +600,7 @@ static int vlan_dev_init(struct net_device *dev) SET_NETDEV_DEVTYPE(dev, &vlan_type); - vlan_dev_set_lockdep_class(dev, dev->lower_level); + vlan_dev_set_lockdep_class(dev); vlan->vlan_pcpu_stats = netdev_alloc_pcpu_stats(struct vlan_pcpu_stats); if (!vlan->vlan_pcpu_stats) diff --git a/net/9p/mod.c b/net/9p/mod.c index c1b62428da7b..5126566850bd 100644 --- a/net/9p/mod.c +++ b/net/9p/mod.c @@ -189,3 +189,4 @@ MODULE_AUTHOR("Latchesar Ionkov <lucho@ionkov.net>"); MODULE_AUTHOR("Eric Van Hensbergen <ericvh@gmail.com>"); MODULE_AUTHOR("Ron Minnich <rminnich@lanl.gov>"); MODULE_LICENSE("GPL"); +MODULE_DESCRIPTION("Plan 9 Resource Sharing Support (9P2000)"); diff --git a/net/ax25/af_ax25.c b/net/ax25/af_ax25.c index fd91cd34f25e..dec3f35467c9 100644 --- a/net/ax25/af_ax25.c +++ b/net/ax25/af_ax25.c @@ -1187,7 +1187,10 @@ static int __must_check ax25_connect(struct socket *sock, if (addr_len > sizeof(struct sockaddr_ax25) && fsa->fsa_ax25.sax25_ndigis != 0) { /* Valid number of digipeaters ? */ - if (fsa->fsa_ax25.sax25_ndigis < 1 || fsa->fsa_ax25.sax25_ndigis > AX25_MAX_DIGIS) { + if (fsa->fsa_ax25.sax25_ndigis < 1 || + fsa->fsa_ax25.sax25_ndigis > AX25_MAX_DIGIS || + addr_len < sizeof(struct sockaddr_ax25) + + sizeof(ax25_address) * fsa->fsa_ax25.sax25_ndigis) { err = -EINVAL; goto out_release; } @@ -1507,7 +1510,10 @@ static int ax25_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) struct full_sockaddr_ax25 *fsa = (struct full_sockaddr_ax25 *)usax; /* Valid number of digipeaters ? */ - if (usax->sax25_ndigis < 1 || usax->sax25_ndigis > AX25_MAX_DIGIS) { + if (usax->sax25_ndigis < 1 || + usax->sax25_ndigis > AX25_MAX_DIGIS || + addr_len < sizeof(struct sockaddr_ax25) + + sizeof(ax25_address) * usax->sax25_ndigis) { err = -EINVAL; goto out; } diff --git a/net/bpf/test_run.c b/net/bpf/test_run.c index bfd4ccd80847..b03c469cd01f 100644 --- a/net/bpf/test_run.c +++ b/net/bpf/test_run.c @@ -147,6 +147,20 @@ int noinline bpf_fentry_test6(u64 a, void *b, short c, int d, void *e, u64 f) return a + (long)b + c + d + (long)e + f; } +struct bpf_fentry_test_t { + struct bpf_fentry_test_t *a; +}; + +int noinline bpf_fentry_test7(struct bpf_fentry_test_t *arg) +{ + return (long)arg; +} + +int noinline bpf_fentry_test8(struct bpf_fentry_test_t *arg) +{ + return (long)arg->a; +} + int noinline bpf_modify_return_test(int a, int *b) { *b += 1; @@ -185,6 +199,7 @@ int bpf_prog_test_run_tracing(struct bpf_prog *prog, const union bpf_attr *kattr, union bpf_attr __user *uattr) { + struct bpf_fentry_test_t arg = {}; u16 side_effect = 0, ret = 0; int b = 2, err = -EFAULT; u32 retval = 0; @@ -197,7 +212,9 @@ int bpf_prog_test_run_tracing(struct bpf_prog *prog, bpf_fentry_test3(4, 5, 6) != 15 || bpf_fentry_test4((void *)7, 8, 9, 10) != 34 || bpf_fentry_test5(11, (void *)12, 13, 14, 15) != 65 || - bpf_fentry_test6(16, (void *)17, 18, 19, (void *)20, 21) != 111) + bpf_fentry_test6(16, (void *)17, 18, 19, (void *)20, 21) != 111 || + bpf_fentry_test7((struct bpf_fentry_test_t *)0) != 0 || + bpf_fentry_test8(&arg) != 0) goto out; break; case BPF_MODIFY_RETURN: diff --git a/net/bpfilter/bpfilter_kern.c b/net/bpfilter/bpfilter_kern.c index c0f0990f30b6..1905e01c3aa9 100644 --- a/net/bpfilter/bpfilter_kern.c +++ b/net/bpfilter/bpfilter_kern.c @@ -50,7 +50,7 @@ static int __bpfilter_process_sockopt(struct sock *sk, int optname, req.len = optlen; if (!bpfilter_ops.info.pid) goto out; - n = __kernel_write(bpfilter_ops.info.pipe_to_umh, &req, sizeof(req), + n = kernel_write(bpfilter_ops.info.pipe_to_umh, &req, sizeof(req), &pos); if (n != sizeof(req)) { pr_err("write fail %zd\n", n); diff --git a/net/bridge/br_mrp.c b/net/bridge/br_mrp.c index 24986ec7d38c..90592af9db61 100644 --- a/net/bridge/br_mrp.c +++ b/net/bridge/br_mrp.c @@ -86,7 +86,7 @@ static struct sk_buff *br_mrp_skb_alloc(struct net_bridge_port *p, { struct ethhdr *eth_hdr; struct sk_buff *skb; - u16 *version; + __be16 *version; skb = dev_alloc_skb(MRP_MAX_FRAME_LENGTH); if (!skb) @@ -411,10 +411,16 @@ int br_mrp_set_port_role(struct net_bridge_port *p, if (!mrp) return -EINVAL; - if (role == BR_MRP_PORT_ROLE_PRIMARY) + switch (role) { + case BR_MRP_PORT_ROLE_PRIMARY: rcu_assign_pointer(mrp->p_port, p); - else + break; + case BR_MRP_PORT_ROLE_SECONDARY: rcu_assign_pointer(mrp->s_port, p); + break; + default: + return -EINVAL; + } br_mrp_port_switchdev_set_role(p, role); diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c index 83490bf73a13..4c4a93abde68 100644 --- a/net/bridge/br_multicast.c +++ b/net/bridge/br_multicast.c @@ -1007,7 +1007,7 @@ static int br_ip6_multicast_mld2_report(struct net_bridge *br, nsrcs_offset = len + offsetof(struct mld2_grec, grec_nsrcs); if (skb_transport_offset(skb) + ipv6_transport_len(skb) < - nsrcs_offset + sizeof(_nsrcs)) + nsrcs_offset + sizeof(__nsrcs)) return -EINVAL; _nsrcs = skb_header_pointer(skb, nsrcs_offset, diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h index 7501be4eeba0..e0ea6dbbc97e 100644 --- a/net/bridge/br_private.h +++ b/net/bridge/br_private.h @@ -217,8 +217,8 @@ struct net_bridge_port_group { struct rcu_head rcu; struct timer_list timer; struct br_ip addr; + unsigned char eth_addr[ETH_ALEN] __aligned(2); unsigned char flags; - unsigned char eth_addr[ETH_ALEN]; }; struct net_bridge_mdb_entry { @@ -430,7 +430,7 @@ struct net_bridge { struct hlist_head fdb_list; #if IS_ENABLED(CONFIG_BRIDGE_MRP) - struct list_head __rcu mrp_list; + struct list_head mrp_list; #endif }; diff --git a/net/bridge/br_private_mrp.h b/net/bridge/br_private_mrp.h index 33b255e38ffe..315eb37d89f0 100644 --- a/net/bridge/br_private_mrp.h +++ b/net/bridge/br_private_mrp.h @@ -8,7 +8,7 @@ struct br_mrp { /* list of mrp instances */ - struct list_head __rcu list; + struct list_head list; struct net_bridge_port __rcu *p_port; struct net_bridge_port __rcu *s_port; diff --git a/net/bridge/netfilter/nft_meta_bridge.c b/net/bridge/netfilter/nft_meta_bridge.c index 7c9e92b2f806..8e8ffac037cd 100644 --- a/net/bridge/netfilter/nft_meta_bridge.c +++ b/net/bridge/netfilter/nft_meta_bridge.c @@ -155,3 +155,4 @@ module_exit(nft_meta_bridge_module_exit); MODULE_LICENSE("GPL"); MODULE_AUTHOR("wenxu <wenxu@ucloud.cn>"); MODULE_ALIAS_NFT_AF_EXPR(AF_BRIDGE, "meta"); +MODULE_DESCRIPTION("Support for bridge dedicated meta key"); diff --git a/net/bridge/netfilter/nft_reject_bridge.c b/net/bridge/netfilter/nft_reject_bridge.c index f48cf4cfb80f..deae2c9a0f69 100644 --- a/net/bridge/netfilter/nft_reject_bridge.c +++ b/net/bridge/netfilter/nft_reject_bridge.c @@ -455,3 +455,4 @@ module_exit(nft_reject_bridge_module_exit); MODULE_LICENSE("GPL"); MODULE_AUTHOR("Pablo Neira Ayuso <pablo@netfilter.org>"); MODULE_ALIAS_NFT_AF_EXPR(AF_BRIDGE, "reject"); +MODULE_DESCRIPTION("Reject packets from bridge via nftables"); diff --git a/net/ceph/ceph_common.c b/net/ceph/ceph_common.c index afe0e8184c23..4e7edd707a14 100644 --- a/net/ceph/ceph_common.c +++ b/net/ceph/ceph_common.c @@ -332,6 +332,7 @@ struct ceph_options *ceph_alloc_options(void) opt->mount_timeout = CEPH_MOUNT_TIMEOUT_DEFAULT; opt->osd_idle_ttl = CEPH_OSD_IDLE_TTL_DEFAULT; opt->osd_request_timeout = CEPH_OSD_REQUEST_TIMEOUT_DEFAULT; + opt->read_from_replica = CEPH_READ_FROM_REPLICA_DEFAULT; return opt; } EXPORT_SYMBOL(ceph_alloc_options); @@ -490,16 +491,13 @@ int ceph_parse_param(struct fs_parameter *param, struct ceph_options *opt, case Opt_read_from_replica: switch (result.uint_32) { case Opt_read_from_replica_no: - opt->osd_req_flags &= ~(CEPH_OSD_FLAG_BALANCE_READS | - CEPH_OSD_FLAG_LOCALIZE_READS); + opt->read_from_replica = 0; break; case Opt_read_from_replica_balance: - opt->osd_req_flags |= CEPH_OSD_FLAG_BALANCE_READS; - opt->osd_req_flags &= ~CEPH_OSD_FLAG_LOCALIZE_READS; + opt->read_from_replica = CEPH_OSD_FLAG_BALANCE_READS; break; case Opt_read_from_replica_localize: - opt->osd_req_flags |= CEPH_OSD_FLAG_LOCALIZE_READS; - opt->osd_req_flags &= ~CEPH_OSD_FLAG_BALANCE_READS; + opt->read_from_replica = CEPH_OSD_FLAG_LOCALIZE_READS; break; default: BUG(); @@ -613,9 +611,9 @@ int ceph_print_client_options(struct seq_file *m, struct ceph_client *client, } seq_putc(m, ','); } - if (opt->osd_req_flags & CEPH_OSD_FLAG_BALANCE_READS) { + if (opt->read_from_replica == CEPH_OSD_FLAG_BALANCE_READS) { seq_puts(m, "read_from_replica=balance,"); - } else if (opt->osd_req_flags & CEPH_OSD_FLAG_LOCALIZE_READS) { + } else if (opt->read_from_replica == CEPH_OSD_FLAG_LOCALIZE_READS) { seq_puts(m, "read_from_replica=localize,"); } diff --git a/net/ceph/osd_client.c b/net/ceph/osd_client.c index 4fea3c33af2a..2db8b44e70c2 100644 --- a/net/ceph/osd_client.c +++ b/net/ceph/osd_client.c @@ -445,8 +445,10 @@ static void target_copy(struct ceph_osd_request_target *dest, dest->size = src->size; dest->min_size = src->min_size; dest->sort_bitwise = src->sort_bitwise; + dest->recovery_deletes = src->recovery_deletes; dest->flags = src->flags; + dest->used_replica = src->used_replica; dest->paused = src->paused; dest->epoch = src->epoch; @@ -1117,10 +1119,10 @@ struct ceph_osd_request *ceph_osdc_new_request(struct ceph_osd_client *osdc, truncate_size, truncate_seq); } - req->r_flags = flags; req->r_base_oloc.pool = layout->pool_id; req->r_base_oloc.pool_ns = ceph_try_get_string(layout->pool_ns); ceph_oid_printf(&req->r_base_oid, "%llx.%08llx", vino.ino, objnum); + req->r_flags = flags | osdc->client->options->read_from_replica; req->r_snapid = vino.snap; if (flags & CEPH_OSD_FLAG_WRITE) @@ -2431,14 +2433,11 @@ promote: static void account_request(struct ceph_osd_request *req) { - struct ceph_osd_client *osdc = req->r_osdc; - WARN_ON(req->r_flags & (CEPH_OSD_FLAG_ACK | CEPH_OSD_FLAG_ONDISK)); WARN_ON(!(req->r_flags & (CEPH_OSD_FLAG_READ | CEPH_OSD_FLAG_WRITE))); req->r_flags |= CEPH_OSD_FLAG_ONDISK; - req->r_flags |= osdc->client->options->osd_req_flags; - atomic_inc(&osdc->num_requests); + atomic_inc(&req->r_osdc->num_requests); req->r_start_stamp = jiffies; req->r_start_latency = ktime_get(); diff --git a/net/core/dev.c b/net/core/dev.c index 6bc2388141f6..7a774ebf64e2 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -4192,10 +4192,12 @@ int dev_direct_xmit(struct sk_buff *skb, u16 queue_id) local_bh_disable(); + dev_xmit_recursion_inc(); HARD_TX_LOCK(dev, txq, smp_processor_id()); if (!netif_xmit_frozen_or_drv_stopped(txq)) ret = netdev_start_xmit(skb, dev, txq, false); HARD_TX_UNLOCK(dev, txq); + dev_xmit_recursion_dec(); local_bh_enable(); @@ -5599,7 +5601,7 @@ static void flush_backlog(struct work_struct *work) skb_queue_walk_safe(&sd->input_pkt_queue, skb, tmp) { if (skb->dev->reg_state == NETREG_UNREGISTERING) { __skb_unlink(skb, &sd->input_pkt_queue); - kfree_skb(skb); + dev_kfree_skb_irq(skb); input_queue_head_incr(sd); } } @@ -9547,6 +9549,13 @@ int register_netdevice(struct net_device *dev) rcu_barrier(); dev->reg_state = NETREG_UNREGISTERED; + /* We should put the kobject that hold in + * netdev_unregister_kobject(), otherwise + * the net device cannot be freed when + * driver calls free_netdev(), because the + * kobject is being hold. + */ + kobject_put(&dev->dev.kobj); } /* * Prevent userspace races by waiting until the network diff --git a/net/core/dev_addr_lists.c b/net/core/dev_addr_lists.c index 6393ba930097..54cd568e7c2f 100644 --- a/net/core/dev_addr_lists.c +++ b/net/core/dev_addr_lists.c @@ -690,6 +690,15 @@ void dev_uc_unsync(struct net_device *to, struct net_device *from) if (to->addr_len != from->addr_len) return; + /* netif_addr_lock_bh() uses lockdep subclass 0, this is okay for two + * reasons: + * 1) This is always called without any addr_list_lock, so as the + * outermost one here, it must be 0. + * 2) This is called by some callers after unlinking the upper device, + * so the dev->lower_level becomes 1 again. + * Therefore, the subclass for 'from' is 0, for 'to' is either 1 or + * larger. + */ netif_addr_lock_bh(from); netif_addr_lock_nested(to); __hw_addr_unsync(&to->uc, &from->uc, to->addr_len); @@ -911,6 +920,7 @@ void dev_mc_unsync(struct net_device *to, struct net_device *from) if (to->addr_len != from->addr_len) return; + /* See the above comments inside dev_uc_unsync(). */ netif_addr_lock_bh(from); netif_addr_lock_nested(to); __hw_addr_unsync(&to->mc, &from->mc, to->addr_len); diff --git a/net/core/drop_monitor.c b/net/core/drop_monitor.c index 2ee7bc4c9e03..b09bebeadf0b 100644 --- a/net/core/drop_monitor.c +++ b/net/core/drop_monitor.c @@ -1721,3 +1721,4 @@ module_exit(exit_net_drop_monitor); MODULE_LICENSE("GPL v2"); MODULE_AUTHOR("Neil Horman <nhorman@tuxdriver.com>"); MODULE_ALIAS_GENL_FAMILY("NET_DM"); +MODULE_DESCRIPTION("Monitoring code for network dropped packet alerts"); diff --git a/net/core/filter.c b/net/core/filter.c index 73395384afe2..82e1b5b06167 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -5853,12 +5853,16 @@ BPF_CALL_1(bpf_skb_ecn_set_ce, struct sk_buff *, skb) { unsigned int iphdr_len; - if (skb->protocol == cpu_to_be16(ETH_P_IP)) + switch (skb_protocol(skb, true)) { + case cpu_to_be16(ETH_P_IP): iphdr_len = sizeof(struct iphdr); - else if (skb->protocol == cpu_to_be16(ETH_P_IPV6)) + break; + case cpu_to_be16(ETH_P_IPV6): iphdr_len = sizeof(struct ipv6hdr); - else + break; + default: return 0; + } if (skb_headlen(skb) < iphdr_len) return 0; diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c index d02df0b6d0d9..142a8824f0a8 100644 --- a/net/core/flow_dissector.c +++ b/net/core/flow_dissector.c @@ -70,10 +70,10 @@ void skb_flow_dissector_init(struct flow_dissector *flow_dissector, EXPORT_SYMBOL(skb_flow_dissector_init); #ifdef CONFIG_BPF_SYSCALL -int flow_dissector_bpf_prog_attach(struct net *net, struct bpf_prog *prog) +int flow_dissector_bpf_prog_attach_check(struct net *net, + struct bpf_prog *prog) { enum netns_bpf_attach_type type = NETNS_BPF_FLOW_DISSECTOR; - struct bpf_prog *attached; if (net == &init_net) { /* BPF flow dissector in the root namespace overrides @@ -86,26 +86,17 @@ int flow_dissector_bpf_prog_attach(struct net *net, struct bpf_prog *prog) for_each_net(ns) { if (ns == &init_net) continue; - if (rcu_access_pointer(ns->bpf.progs[type])) + if (rcu_access_pointer(ns->bpf.run_array[type])) return -EEXIST; } } else { /* Make sure root flow dissector is not attached * when attaching to the non-root namespace. */ - if (rcu_access_pointer(init_net.bpf.progs[type])) + if (rcu_access_pointer(init_net.bpf.run_array[type])) return -EEXIST; } - attached = rcu_dereference_protected(net->bpf.progs[type], - lockdep_is_held(&netns_bpf_mutex)); - if (attached == prog) - /* The same program cannot be attached twice */ - return -EINVAL; - - rcu_assign_pointer(net->bpf.progs[type], prog); - if (attached) - bpf_prog_put(attached); return 0; } #endif /* CONFIG_BPF_SYSCALL */ @@ -903,7 +894,6 @@ bool __skb_flow_dissect(const struct net *net, struct flow_dissector_key_addrs *key_addrs; struct flow_dissector_key_tags *key_tags; struct flow_dissector_key_vlan *key_vlan; - struct bpf_prog *attached = NULL; enum flow_dissect_ret fdret; enum flow_dissector_key_id dissector_vlan = FLOW_DISSECTOR_KEY_MAX; bool mpls_el = false; @@ -960,14 +950,14 @@ bool __skb_flow_dissect(const struct net *net, WARN_ON_ONCE(!net); if (net) { enum netns_bpf_attach_type type = NETNS_BPF_FLOW_DISSECTOR; + struct bpf_prog_array *run_array; rcu_read_lock(); - attached = rcu_dereference(init_net.bpf.progs[type]); - - if (!attached) - attached = rcu_dereference(net->bpf.progs[type]); + run_array = rcu_dereference(init_net.bpf.run_array[type]); + if (!run_array) + run_array = rcu_dereference(net->bpf.run_array[type]); - if (attached) { + if (run_array) { struct bpf_flow_keys flow_keys; struct bpf_flow_dissector ctx = { .flow_keys = &flow_keys, @@ -975,6 +965,7 @@ bool __skb_flow_dissect(const struct net *net, .data_end = data + hlen, }; __be16 n_proto = proto; + struct bpf_prog *prog; if (skb) { ctx.skb = skb; @@ -985,7 +976,8 @@ bool __skb_flow_dissect(const struct net *net, n_proto = skb->protocol; } - ret = bpf_flow_dissect(attached, &ctx, n_proto, nhoff, + prog = READ_ONCE(run_array->items[0].prog); + ret = bpf_flow_dissect(prog, &ctx, n_proto, nhoff, hlen, flags); __skb_flow_bpf_to_target(&flow_keys, flow_dissector, target_container); diff --git a/net/core/flow_offload.c b/net/core/flow_offload.c index 0cfc35e6be28..2076219b8ba5 100644 --- a/net/core/flow_offload.c +++ b/net/core/flow_offload.c @@ -4,6 +4,7 @@ #include <net/flow_offload.h> #include <linux/rtnetlink.h> #include <linux/mutex.h> +#include <linux/rhashtable.h> struct flow_rule *flow_rule_alloc(unsigned int num_actions) { @@ -372,14 +373,15 @@ int flow_indr_dev_register(flow_indr_block_bind_cb_t *cb, void *cb_priv) } EXPORT_SYMBOL(flow_indr_dev_register); -static void __flow_block_indr_cleanup(flow_setup_cb_t *setup_cb, void *cb_priv, +static void __flow_block_indr_cleanup(void (*release)(void *cb_priv), + void *cb_priv, struct list_head *cleanup_list) { struct flow_block_cb *this, *next; list_for_each_entry_safe(this, next, &flow_block_indr_list, indr.list) { - if (this->cb == setup_cb && - this->cb_priv == cb_priv) { + if (this->release == release && + this->indr.cb_priv == cb_priv) { list_move(&this->indr.list, cleanup_list); return; } @@ -397,7 +399,7 @@ static void flow_block_indr_notify(struct list_head *cleanup_list) } void flow_indr_dev_unregister(flow_indr_block_bind_cb_t *cb, void *cb_priv, - flow_setup_cb_t *setup_cb) + void (*release)(void *cb_priv)) { struct flow_indr_dev *this, *next, *indr_dev = NULL; LIST_HEAD(cleanup_list); @@ -418,7 +420,7 @@ void flow_indr_dev_unregister(flow_indr_block_bind_cb_t *cb, void *cb_priv, return; } - __flow_block_indr_cleanup(setup_cb, cb_priv, &cleanup_list); + __flow_block_indr_cleanup(release, cb_priv, &cleanup_list); mutex_unlock(&flow_indr_block_lock); flow_block_indr_notify(&cleanup_list); @@ -429,32 +431,37 @@ EXPORT_SYMBOL(flow_indr_dev_unregister); static void flow_block_indr_init(struct flow_block_cb *flow_block, struct flow_block_offload *bo, struct net_device *dev, void *data, + void *cb_priv, void (*cleanup)(struct flow_block_cb *block_cb)) { flow_block->indr.binder_type = bo->binder_type; flow_block->indr.data = data; + flow_block->indr.cb_priv = cb_priv; flow_block->indr.dev = dev; flow_block->indr.cleanup = cleanup; } -static void __flow_block_indr_binding(struct flow_block_offload *bo, - struct net_device *dev, void *data, - void (*cleanup)(struct flow_block_cb *block_cb)) +struct flow_block_cb *flow_indr_block_cb_alloc(flow_setup_cb_t *cb, + void *cb_ident, void *cb_priv, + void (*release)(void *cb_priv), + struct flow_block_offload *bo, + struct net_device *dev, void *data, + void *indr_cb_priv, + void (*cleanup)(struct flow_block_cb *block_cb)) { struct flow_block_cb *block_cb; - list_for_each_entry(block_cb, &bo->cb_list, list) { - switch (bo->command) { - case FLOW_BLOCK_BIND: - flow_block_indr_init(block_cb, bo, dev, data, cleanup); - list_add(&block_cb->indr.list, &flow_block_indr_list); - break; - case FLOW_BLOCK_UNBIND: - list_del(&block_cb->indr.list); - break; - } - } + block_cb = flow_block_cb_alloc(cb, cb_ident, cb_priv, release); + if (IS_ERR(block_cb)) + goto out; + + flow_block_indr_init(block_cb, bo, dev, data, indr_cb_priv, cleanup); + list_add(&block_cb->indr.list, &flow_block_indr_list); + +out: + return block_cb; } +EXPORT_SYMBOL(flow_indr_block_cb_alloc); int flow_indr_dev_setup_offload(struct net_device *dev, enum tc_setup_type type, void *data, @@ -465,9 +472,8 @@ int flow_indr_dev_setup_offload(struct net_device *dev, mutex_lock(&flow_indr_block_lock); list_for_each_entry(this, &flow_block_indr_dev_list, list) - this->cb(dev, this->cb_priv, type, bo); + this->cb(dev, this->cb_priv, type, bo, data, cleanup); - __flow_block_indr_binding(bo, dev, data, cleanup); mutex_unlock(&flow_indr_block_lock); return list_empty(&bo->cb_list) ? -EOPNOTSUPP : 0; diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c index e353b822bb15..7bd6440c63bf 100644 --- a/net/core/net-sysfs.c +++ b/net/core/net-sysfs.c @@ -1108,7 +1108,7 @@ static ssize_t tx_timeout_show(struct netdev_queue *queue, char *buf) trans_timeout = queue->trans_timeout; spin_unlock_irq(&queue->_xmit_lock); - return sprintf(buf, "%lu", trans_timeout); + return sprintf(buf, fmt_ulong, trans_timeout); } static unsigned int get_netdev_queue_index(struct netdev_queue *queue) diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 9aedc15736ad..85a4b0101f76 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -3343,7 +3343,8 @@ replay: */ if (err < 0) { /* If device is not registered at all, free it now */ - if (dev->reg_state == NETREG_UNINITIALIZED) + if (dev->reg_state == NETREG_UNINITIALIZED || + dev->reg_state == NETREG_UNREGISTERED) free_netdev(dev); goto out; } diff --git a/net/core/skmsg.c b/net/core/skmsg.c index 351afbf6bfba..6a32a1fd34f8 100644 --- a/net/core/skmsg.c +++ b/net/core/skmsg.c @@ -683,7 +683,7 @@ static struct sk_psock *sk_psock_from_strp(struct strparser *strp) return container_of(parser, struct sk_psock, parser); } -static void sk_psock_skb_redirect(struct sk_psock *psock, struct sk_buff *skb) +static void sk_psock_skb_redirect(struct sk_buff *skb) { struct sk_psock *psock_other; struct sock *sk_other; @@ -715,12 +715,11 @@ static void sk_psock_skb_redirect(struct sk_psock *psock, struct sk_buff *skb) } } -static void sk_psock_tls_verdict_apply(struct sk_psock *psock, - struct sk_buff *skb, int verdict) +static void sk_psock_tls_verdict_apply(struct sk_buff *skb, int verdict) { switch (verdict) { case __SK_REDIRECT: - sk_psock_skb_redirect(psock, skb); + sk_psock_skb_redirect(skb); break; case __SK_PASS: case __SK_DROP: @@ -741,8 +740,8 @@ int sk_psock_tls_strp_read(struct sk_psock *psock, struct sk_buff *skb) ret = sk_psock_bpf_run(psock, prog, skb); ret = sk_psock_map_verd(ret, tcp_skb_bpf_redirect_fetch(skb)); } + sk_psock_tls_verdict_apply(skb, ret); rcu_read_unlock(); - sk_psock_tls_verdict_apply(psock, skb, ret); return ret; } EXPORT_SYMBOL_GPL(sk_psock_tls_strp_read); @@ -770,7 +769,7 @@ static void sk_psock_verdict_apply(struct sk_psock *psock, } goto out_free; case __SK_REDIRECT: - sk_psock_skb_redirect(psock, skb); + sk_psock_skb_redirect(skb); break; case __SK_DROP: /* fall-through */ @@ -782,11 +781,18 @@ out_free: static void sk_psock_strp_read(struct strparser *strp, struct sk_buff *skb) { - struct sk_psock *psock = sk_psock_from_strp(strp); + struct sk_psock *psock; struct bpf_prog *prog; int ret = __SK_DROP; + struct sock *sk; rcu_read_lock(); + sk = strp->sk; + psock = sk_psock(sk); + if (unlikely(!psock)) { + kfree_skb(skb); + goto out; + } prog = READ_ONCE(psock->progs.skb_verdict); if (likely(prog)) { skb_orphan(skb); @@ -794,8 +800,9 @@ static void sk_psock_strp_read(struct strparser *strp, struct sk_buff *skb) ret = sk_psock_bpf_run(psock, prog, skb); ret = sk_psock_map_verd(ret, tcp_skb_bpf_redirect_fetch(skb)); } - rcu_read_unlock(); sk_psock_verdict_apply(psock, skb, ret); +out: + rcu_read_unlock(); } static int sk_psock_strp_read_done(struct strparser *strp, int err) diff --git a/net/core/sock.c b/net/core/sock.c index 6c4acf1f0220..2e5b7870e5d3 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -718,7 +718,7 @@ bool sk_mc_loop(struct sock *sk) return inet6_sk(sk)->mc_loop; #endif } - WARN_ON(1); + WARN_ON_ONCE(1); return true; } EXPORT_SYMBOL(sk_mc_loop); @@ -1767,6 +1767,7 @@ struct sock *sk_alloc(struct net *net, int family, gfp_t priority, cgroup_sk_alloc(&sk->sk_cgrp_data); sock_update_classid(&sk->sk_cgrp_data); sock_update_netprioidx(&sk->sk_cgrp_data); + sk_tx_queue_clear(sk); } return sk; @@ -1925,7 +1926,7 @@ struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority) /* sk->sk_memcg will be populated at accept() time */ newsk->sk_memcg = NULL; - cgroup_sk_alloc(&newsk->sk_cgrp_data); + cgroup_sk_clone(&newsk->sk_cgrp_data); rcu_read_lock(); filter = rcu_dereference(sk->sk_filter); @@ -1990,6 +1991,7 @@ struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority) */ sk_refcnt_debug_inc(newsk); sk_set_socket(newsk, NULL); + sk_tx_queue_clear(newsk); RCU_INIT_POINTER(newsk->sk_wq, NULL); if (newsk->sk_prot->sockets_allocated) diff --git a/net/core/sock_map.c b/net/core/sock_map.c index 4059f94e9bb5..0971f17e8e54 100644 --- a/net/core/sock_map.c +++ b/net/core/sock_map.c @@ -70,11 +70,49 @@ int sock_map_get_from_fd(const union bpf_attr *attr, struct bpf_prog *prog) struct fd f; int ret; + if (attr->attach_flags || attr->replace_bpf_fd) + return -EINVAL; + f = fdget(ufd); map = __bpf_map_get(f); if (IS_ERR(map)) return PTR_ERR(map); - ret = sock_map_prog_update(map, prog, attr->attach_type); + ret = sock_map_prog_update(map, prog, NULL, attr->attach_type); + fdput(f); + return ret; +} + +int sock_map_prog_detach(const union bpf_attr *attr, enum bpf_prog_type ptype) +{ + u32 ufd = attr->target_fd; + struct bpf_prog *prog; + struct bpf_map *map; + struct fd f; + int ret; + + if (attr->attach_flags || attr->replace_bpf_fd) + return -EINVAL; + + f = fdget(ufd); + map = __bpf_map_get(f); + if (IS_ERR(map)) + return PTR_ERR(map); + + prog = bpf_prog_get(attr->attach_bpf_fd); + if (IS_ERR(prog)) { + ret = PTR_ERR(prog); + goto put_map; + } + + if (prog->type != ptype) { + ret = -EINVAL; + goto put_prog; + } + + ret = sock_map_prog_update(map, NULL, prog, attr->attach_type); +put_prog: + bpf_prog_put(prog); +put_map: fdput(f); return ret; } @@ -1203,27 +1241,32 @@ static struct sk_psock_progs *sock_map_progs(struct bpf_map *map) } int sock_map_prog_update(struct bpf_map *map, struct bpf_prog *prog, - u32 which) + struct bpf_prog *old, u32 which) { struct sk_psock_progs *progs = sock_map_progs(map); + struct bpf_prog **pprog; if (!progs) return -EOPNOTSUPP; switch (which) { case BPF_SK_MSG_VERDICT: - psock_set_prog(&progs->msg_parser, prog); + pprog = &progs->msg_parser; break; case BPF_SK_SKB_STREAM_PARSER: - psock_set_prog(&progs->skb_parser, prog); + pprog = &progs->skb_parser; break; case BPF_SK_SKB_STREAM_VERDICT: - psock_set_prog(&progs->skb_verdict, prog); + pprog = &progs->skb_verdict; break; default: return -EOPNOTSUPP; } + if (old) + return psock_replace_prog(pprog, prog, old); + + psock_set_prog(pprog, prog); return 0; } diff --git a/net/core/sock_reuseport.c b/net/core/sock_reuseport.c index adcb3aea576d..bbdd3c7b6cb5 100644 --- a/net/core/sock_reuseport.c +++ b/net/core/sock_reuseport.c @@ -101,6 +101,7 @@ static struct sock_reuseport *reuseport_grow(struct sock_reuseport *reuse) more_reuse->prog = reuse->prog; more_reuse->reuseport_id = reuse->reuseport_id; more_reuse->bind_inany = reuse->bind_inany; + more_reuse->has_conns = reuse->has_conns; memcpy(more_reuse->socks, reuse->socks, reuse->num_socks * sizeof(struct sock *)); diff --git a/net/core/sysctl_net_core.c b/net/core/sysctl_net_core.c index f93f8ace6c56..6ada114bbcca 100644 --- a/net/core/sysctl_net_core.c +++ b/net/core/sysctl_net_core.c @@ -274,7 +274,7 @@ static int proc_dointvec_minmax_bpf_enable(struct ctl_table *table, int write, ret = proc_dointvec_minmax(&tmp, write, buffer, lenp, ppos); if (write && !ret) { if (jit_enable < 2 || - (jit_enable == 2 && bpf_dump_raw_ok())) { + (jit_enable == 2 && bpf_dump_raw_ok(current_cred()))) { *(int *)table->data = jit_enable; if (jit_enable == 2) pr_warn("bpf_jit_enable = 2 was set! NEVER use this in production, only for JIT debugging!\n"); diff --git a/net/core/xdp.c b/net/core/xdp.c index 90f44f382115..3c45f99e26d5 100644 --- a/net/core/xdp.c +++ b/net/core/xdp.c @@ -462,6 +462,7 @@ struct xdp_frame *xdp_convert_zc_to_xdp_frame(struct xdp_buff *xdp) xdpf->len = totsize - metasize; xdpf->headroom = 0; xdpf->metasize = metasize; + xdpf->frame_sz = PAGE_SIZE; xdpf->mem.type = MEM_TYPE_PAGE_ORDER0; xsk_buff_free(xdp); diff --git a/net/dsa/tag_edsa.c b/net/dsa/tag_edsa.c index e8eaa804ccb9..d6200ff98200 100644 --- a/net/dsa/tag_edsa.c +++ b/net/dsa/tag_edsa.c @@ -13,6 +13,16 @@ #define DSA_HLEN 4 #define EDSA_HLEN 8 +#define FRAME_TYPE_TO_CPU 0x00 +#define FRAME_TYPE_FORWARD 0x03 + +#define TO_CPU_CODE_MGMT_TRAP 0x00 +#define TO_CPU_CODE_FRAME2REG 0x01 +#define TO_CPU_CODE_IGMP_MLD_TRAP 0x02 +#define TO_CPU_CODE_POLICY_TRAP 0x03 +#define TO_CPU_CODE_ARP_MIRROR 0x04 +#define TO_CPU_CODE_POLICY_MIRROR 0x05 + static struct sk_buff *edsa_xmit(struct sk_buff *skb, struct net_device *dev) { struct dsa_port *dp = dsa_slave_to_port(dev); @@ -77,6 +87,8 @@ static struct sk_buff *edsa_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt) { u8 *edsa_header; + int frame_type; + int code; int source_device; int source_port; @@ -91,8 +103,29 @@ static struct sk_buff *edsa_rcv(struct sk_buff *skb, struct net_device *dev, /* * Check that frame type is either TO_CPU or FORWARD. */ - if ((edsa_header[0] & 0xc0) != 0x00 && (edsa_header[0] & 0xc0) != 0xc0) + frame_type = edsa_header[0] >> 6; + + switch (frame_type) { + case FRAME_TYPE_TO_CPU: + code = (edsa_header[1] & 0x6) | ((edsa_header[2] >> 4) & 1); + + /* + * Mark the frame to never egress on any port of the same switch + * unless it's a trapped IGMP/MLD packet, in which case the + * bridge might want to forward it. + */ + if (code != TO_CPU_CODE_IGMP_MLD_TRAP) + skb->offload_fwd_mark = 1; + + break; + + case FRAME_TYPE_FORWARD: + skb->offload_fwd_mark = 1; + break; + + default: return NULL; + } /* * Determine source device and port. @@ -156,8 +189,6 @@ static struct sk_buff *edsa_rcv(struct sk_buff *skb, struct net_device *dev, 2 * ETH_ALEN); } - skb->offload_fwd_mark = 1; - return skb; } diff --git a/net/ethtool/cabletest.c b/net/ethtool/cabletest.c index 7b7a0456c15c..7194956aa09e 100644 --- a/net/ethtool/cabletest.c +++ b/net/ethtool/cabletest.c @@ -234,6 +234,14 @@ static int ethnl_act_cable_test_tdr_cfg(const struct nlattr *nest, struct nlattr *tb[ETHTOOL_A_CABLE_TEST_TDR_CFG_MAX + 1]; int ret; + cfg->first = 100; + cfg->step = 100; + cfg->last = MAX_CABLE_LENGTH_CM; + cfg->pair = PHY_PAIR_ALL; + + if (!nest) + return 0; + ret = nla_parse_nested(tb, ETHTOOL_A_CABLE_TEST_TDR_CFG_MAX, nest, cable_test_tdr_act_cfg_policy, info->extack); if (ret < 0) @@ -242,17 +250,12 @@ static int ethnl_act_cable_test_tdr_cfg(const struct nlattr *nest, if (tb[ETHTOOL_A_CABLE_TEST_TDR_CFG_FIRST]) cfg->first = nla_get_u32( tb[ETHTOOL_A_CABLE_TEST_TDR_CFG_FIRST]); - else - cfg->first = 100; + if (tb[ETHTOOL_A_CABLE_TEST_TDR_CFG_LAST]) cfg->last = nla_get_u32(tb[ETHTOOL_A_CABLE_TEST_TDR_CFG_LAST]); - else - cfg->last = MAX_CABLE_LENGTH_CM; if (tb[ETHTOOL_A_CABLE_TEST_TDR_CFG_STEP]) cfg->step = nla_get_u32(tb[ETHTOOL_A_CABLE_TEST_TDR_CFG_STEP]); - else - cfg->step = 100; if (tb[ETHTOOL_A_CABLE_TEST_TDR_CFG_PAIR]) { cfg->pair = nla_get_u8(tb[ETHTOOL_A_CABLE_TEST_TDR_CFG_PAIR]); @@ -263,8 +266,6 @@ static int ethnl_act_cable_test_tdr_cfg(const struct nlattr *nest, "invalid pair parameter"); return -EINVAL; } - } else { - cfg->pair = PHY_PAIR_ALL; } if (cfg->first > MAX_CABLE_LENGTH_CM) { diff --git a/net/ethtool/common.c b/net/ethtool/common.c index 423e640e3876..aaecfc916a4d 100644 --- a/net/ethtool/common.c +++ b/net/ethtool/common.c @@ -40,9 +40,11 @@ const char netdev_features_strings[NETDEV_FEATURE_COUNT][ETH_GSTRING_LEN] = { [NETIF_F_GSO_UDP_TUNNEL_BIT] = "tx-udp_tnl-segmentation", [NETIF_F_GSO_UDP_TUNNEL_CSUM_BIT] = "tx-udp_tnl-csum-segmentation", [NETIF_F_GSO_PARTIAL_BIT] = "tx-gso-partial", + [NETIF_F_GSO_TUNNEL_REMCSUM_BIT] = "tx-tunnel-remcsum-segmentation", [NETIF_F_GSO_SCTP_BIT] = "tx-sctp-segmentation", [NETIF_F_GSO_ESP_BIT] = "tx-esp-segmentation", [NETIF_F_GSO_UDP_L4_BIT] = "tx-udp-segmentation", + [NETIF_F_GSO_FRAGLIST_BIT] = "tx-gso-list", [NETIF_F_FCOE_CRC_BIT] = "tx-checksum-fcoe-crc", [NETIF_F_SCTP_CRC_BIT] = "tx-checksum-sctp", diff --git a/net/ethtool/ioctl.c b/net/ethtool/ioctl.c index b5df90c981c2..21d5fc0f6bb3 100644 --- a/net/ethtool/ioctl.c +++ b/net/ethtool/ioctl.c @@ -2978,7 +2978,7 @@ ethtool_rx_flow_rule_create(const struct ethtool_rx_flow_spec_input *input) sizeof(match->mask.ipv6.dst)); } if (memcmp(v6_m_spec->ip6src, &zero_addr, sizeof(zero_addr)) || - memcmp(v6_m_spec->ip6src, &zero_addr, sizeof(zero_addr))) { + memcmp(v6_m_spec->ip6dst, &zero_addr, sizeof(zero_addr))) { match->dissector.used_keys |= BIT(FLOW_DISSECTOR_KEY_IPV6_ADDRS); match->dissector.offset[FLOW_DISSECTOR_KEY_IPV6_ADDRS] = diff --git a/net/ethtool/linkstate.c b/net/ethtool/linkstate.c index 7f47ba89054e..afe5ac8a0f00 100644 --- a/net/ethtool/linkstate.c +++ b/net/ethtool/linkstate.c @@ -78,19 +78,18 @@ static int linkstate_prepare_data(const struct ethnl_req_info *req_base, ret = linkstate_get_sqi(dev); if (ret < 0 && ret != -EOPNOTSUPP) - return ret; - + goto out; data->sqi = ret; ret = linkstate_get_sqi_max(dev); if (ret < 0 && ret != -EOPNOTSUPP) - return ret; - + goto out; data->sqi_max = ret; + ret = 0; +out: ethnl_ops_complete(dev); - - return 0; + return ret; } static int linkstate_reply_size(const struct ethnl_req_info *req_base, diff --git a/net/ethtool/netlink.c b/net/ethtool/netlink.c index 88fd07f47040..dd8a1c1dc07d 100644 --- a/net/ethtool/netlink.c +++ b/net/ethtool/netlink.c @@ -376,10 +376,17 @@ err_dev: } static int ethnl_default_dump_one(struct sk_buff *skb, struct net_device *dev, - const struct ethnl_dump_ctx *ctx) + const struct ethnl_dump_ctx *ctx, + struct netlink_callback *cb) { + void *ehdr; int ret; + ehdr = genlmsg_put(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, + ðtool_genl_family, 0, ctx->ops->reply_cmd); + if (!ehdr) + return -EMSGSIZE; + ethnl_init_reply_data(ctx->reply_data, ctx->ops, dev); rtnl_lock(); ret = ctx->ops->prepare_data(ctx->req_info, ctx->reply_data, NULL); @@ -395,6 +402,10 @@ out: if (ctx->ops->cleanup_data) ctx->ops->cleanup_data(ctx->reply_data); ctx->reply_data->dev = NULL; + if (ret < 0) + genlmsg_cancel(skb, ehdr); + else + genlmsg_end(skb, ehdr); return ret; } @@ -411,7 +422,6 @@ static int ethnl_default_dumpit(struct sk_buff *skb, int s_idx = ctx->pos_idx; int h, idx = 0; int ret = 0; - void *ehdr; rtnl_lock(); for (h = ctx->pos_hash; h < NETDEV_HASHENTRIES; h++, s_idx = 0) { @@ -431,26 +441,15 @@ restart_chain: dev_hold(dev); rtnl_unlock(); - ehdr = genlmsg_put(skb, NETLINK_CB(cb->skb).portid, - cb->nlh->nlmsg_seq, - ðtool_genl_family, 0, - ctx->ops->reply_cmd); - if (!ehdr) { - dev_put(dev); - ret = -EMSGSIZE; - goto out; - } - ret = ethnl_default_dump_one(skb, dev, ctx); + ret = ethnl_default_dump_one(skb, dev, ctx, cb); dev_put(dev); if (ret < 0) { - genlmsg_cancel(skb, ehdr); if (ret == -EOPNOTSUPP) goto lock_and_cont; if (likely(skb->len)) ret = skb->len; goto out; } - genlmsg_end(skb, ehdr); lock_and_cont: rtnl_lock(); if (net->dev_base_seq != seq) { diff --git a/net/hsr/hsr_device.c b/net/hsr/hsr_device.c index cd99f548e440..a6f4e9f65b14 100644 --- a/net/hsr/hsr_device.c +++ b/net/hsr/hsr_device.c @@ -339,7 +339,7 @@ static void hsr_announce(struct timer_list *t) rcu_read_unlock(); } -static void hsr_del_ports(struct hsr_priv *hsr) +void hsr_del_ports(struct hsr_priv *hsr) { struct hsr_port *port; @@ -356,31 +356,12 @@ static void hsr_del_ports(struct hsr_priv *hsr) hsr_del_port(port); } -/* This has to be called after all the readers are gone. - * Otherwise we would have to check the return value of - * hsr_port_get_hsr(). - */ -static void hsr_dev_destroy(struct net_device *hsr_dev) -{ - struct hsr_priv *hsr = netdev_priv(hsr_dev); - - hsr_debugfs_term(hsr); - hsr_del_ports(hsr); - - del_timer_sync(&hsr->prune_timer); - del_timer_sync(&hsr->announce_timer); - - hsr_del_self_node(hsr); - hsr_del_nodes(&hsr->node_db); -} - static const struct net_device_ops hsr_device_ops = { .ndo_change_mtu = hsr_dev_change_mtu, .ndo_open = hsr_dev_open, .ndo_stop = hsr_dev_close, .ndo_start_xmit = hsr_dev_xmit, .ndo_fix_features = hsr_fix_features, - .ndo_uninit = hsr_dev_destroy, }; static struct device_type hsr_type = { @@ -434,6 +415,7 @@ int hsr_dev_finalize(struct net_device *hsr_dev, struct net_device *slave[2], unsigned char multicast_spec, u8 protocol_version, struct netlink_ext_ack *extack) { + bool unregister = false; struct hsr_priv *hsr; int res; @@ -485,25 +467,27 @@ int hsr_dev_finalize(struct net_device *hsr_dev, struct net_device *slave[2], if (res) goto err_unregister; + unregister = true; + res = hsr_add_port(hsr, slave[0], HSR_PT_SLAVE_A, extack); if (res) - goto err_add_slaves; + goto err_unregister; res = hsr_add_port(hsr, slave[1], HSR_PT_SLAVE_B, extack); if (res) - goto err_add_slaves; + goto err_unregister; hsr_debugfs_init(hsr, hsr_dev); mod_timer(&hsr->prune_timer, jiffies + msecs_to_jiffies(PRUNE_PERIOD)); return 0; -err_add_slaves: - unregister_netdevice(hsr_dev); err_unregister: hsr_del_ports(hsr); err_add_master: hsr_del_self_node(hsr); + if (unregister) + unregister_netdevice(hsr_dev); return res; } diff --git a/net/hsr/hsr_device.h b/net/hsr/hsr_device.h index a099d7de7e79..b8f9262ed101 100644 --- a/net/hsr/hsr_device.h +++ b/net/hsr/hsr_device.h @@ -11,6 +11,7 @@ #include <linux/netdevice.h> #include "hsr_main.h" +void hsr_del_ports(struct hsr_priv *hsr); void hsr_dev_setup(struct net_device *dev); int hsr_dev_finalize(struct net_device *hsr_dev, struct net_device *slave[2], unsigned char multicast_spec, u8 protocol_version, @@ -18,5 +19,4 @@ int hsr_dev_finalize(struct net_device *hsr_dev, struct net_device *slave[2], void hsr_check_carrier_and_operstate(struct hsr_priv *hsr); bool is_hsr_master(struct net_device *dev); int hsr_get_max_mtu(struct hsr_priv *hsr); - #endif /* __HSR_DEVICE_H */ diff --git a/net/hsr/hsr_forward.c b/net/hsr/hsr_forward.c index ed13760463de..1ea17752fffc 100644 --- a/net/hsr/hsr_forward.c +++ b/net/hsr/hsr_forward.c @@ -120,13 +120,18 @@ static struct sk_buff *frame_get_stripped_skb(struct hsr_frame_info *frame, return skb_clone(frame->skb_std, GFP_ATOMIC); } -static void hsr_fill_tag(struct sk_buff *skb, struct hsr_frame_info *frame, - struct hsr_port *port, u8 proto_version) +static struct sk_buff *hsr_fill_tag(struct sk_buff *skb, + struct hsr_frame_info *frame, + struct hsr_port *port, u8 proto_version) { struct hsr_ethhdr *hsr_ethhdr; int lane_id; int lsdu_size; + /* pad to minimum packet size which is 60 + 6 (HSR tag) */ + if (skb_put_padto(skb, ETH_ZLEN + HSR_HLEN)) + return NULL; + if (port->type == HSR_PT_SLAVE_A) lane_id = 0; else @@ -144,6 +149,8 @@ static void hsr_fill_tag(struct sk_buff *skb, struct hsr_frame_info *frame, hsr_ethhdr->hsr_tag.encap_proto = hsr_ethhdr->ethhdr.h_proto; hsr_ethhdr->ethhdr.h_proto = htons(proto_version ? ETH_P_HSR : ETH_P_PRP); + + return skb; } static struct sk_buff *create_tagged_skb(struct sk_buff *skb_o, @@ -172,9 +179,10 @@ static struct sk_buff *create_tagged_skb(struct sk_buff *skb_o, memmove(dst, src, movelen); skb_reset_mac_header(skb); - hsr_fill_tag(skb, frame, port, port->hsr->prot_version); - - return skb; + /* skb_put_padto free skb on error and hsr_fill_tag returns NULL in + * that case + */ + return hsr_fill_tag(skb, frame, port, port->hsr->prot_version); } /* If the original frame was an HSR tagged frame, just clone it to be sent diff --git a/net/hsr/hsr_framereg.c b/net/hsr/hsr_framereg.c index 03b891904314..530de24b1fb5 100644 --- a/net/hsr/hsr_framereg.c +++ b/net/hsr/hsr_framereg.c @@ -325,7 +325,8 @@ void hsr_addr_subst_dest(struct hsr_node *node_src, struct sk_buff *skb, if (port->type != node_dst->addr_B_port) return; - ether_addr_copy(eth_hdr(skb)->h_dest, node_dst->macaddress_B); + if (is_valid_ether_addr(node_dst->macaddress_B)) + ether_addr_copy(eth_hdr(skb)->h_dest, node_dst->macaddress_B); } void hsr_register_frame_in(struct hsr_node *node, struct hsr_port *port, diff --git a/net/hsr/hsr_main.c b/net/hsr/hsr_main.c index e2564de67603..144da15f0a81 100644 --- a/net/hsr/hsr_main.c +++ b/net/hsr/hsr_main.c @@ -6,6 +6,7 @@ */ #include <linux/netdevice.h> +#include <net/rtnetlink.h> #include <linux/rculist.h> #include <linux/timer.h> #include <linux/etherdevice.h> @@ -100,8 +101,10 @@ static int hsr_netdev_notify(struct notifier_block *nb, unsigned long event, master = hsr_port_get_hsr(port->hsr, HSR_PT_MASTER); hsr_del_port(port); if (hsr_slave_empty(master->hsr)) { - unregister_netdevice_queue(master->dev, - &list_kill); + const struct rtnl_link_ops *ops; + + ops = master->dev->rtnl_link_ops; + ops->dellink(master->dev, &list_kill); unregister_netdevice_many(&list_kill); } } @@ -144,9 +147,9 @@ static int __init hsr_init(void) static void __exit hsr_exit(void) { - unregister_netdevice_notifier(&hsr_nb); hsr_netlink_exit(); hsr_debugfs_remove_root(); + unregister_netdevice_notifier(&hsr_nb); } module_init(hsr_init); diff --git a/net/hsr/hsr_netlink.c b/net/hsr/hsr_netlink.c index 1decb25f6764..6e14b7d22639 100644 --- a/net/hsr/hsr_netlink.c +++ b/net/hsr/hsr_netlink.c @@ -83,6 +83,22 @@ static int hsr_newlink(struct net *src_net, struct net_device *dev, return hsr_dev_finalize(dev, link, multicast_spec, hsr_version, extack); } +static void hsr_dellink(struct net_device *dev, struct list_head *head) +{ + struct hsr_priv *hsr = netdev_priv(dev); + + del_timer_sync(&hsr->prune_timer); + del_timer_sync(&hsr->announce_timer); + + hsr_debugfs_term(hsr); + hsr_del_ports(hsr); + + hsr_del_self_node(hsr); + hsr_del_nodes(&hsr->node_db); + + unregister_netdevice_queue(dev, head); +} + static int hsr_fill_info(struct sk_buff *skb, const struct net_device *dev) { struct hsr_priv *hsr = netdev_priv(dev); @@ -118,6 +134,7 @@ static struct rtnl_link_ops hsr_link_ops __read_mostly = { .priv_size = sizeof(struct hsr_priv), .setup = hsr_dev_setup, .newlink = hsr_newlink, + .dellink = hsr_dellink, .fill_info = hsr_fill_info, }; diff --git a/net/ipv4/Kconfig b/net/ipv4/Kconfig index 6ecbb0ced177..e64e59b536d3 100644 --- a/net/ipv4/Kconfig +++ b/net/ipv4/Kconfig @@ -340,29 +340,31 @@ config NET_FOU_IP_TUNNELS config INET_AH tristate "IP: AH transformation" - select XFRM_ALGO - select CRYPTO - select CRYPTO_HMAC - select CRYPTO_MD5 - select CRYPTO_SHA1 + select XFRM_AH help - Support for IPsec AH. + Support for IPsec AH (Authentication Header). + + AH can be used with various authentication algorithms. Besides + enabling AH support itself, this option enables the generic + implementations of the algorithms that RFC 8221 lists as MUST be + implemented. If you need any other algorithms, you'll need to enable + them in the crypto API. You should also enable accelerated + implementations of any needed algorithms when available. If unsure, say Y. config INET_ESP tristate "IP: ESP transformation" - select XFRM_ALGO - select CRYPTO - select CRYPTO_AUTHENC - select CRYPTO_HMAC - select CRYPTO_MD5 - select CRYPTO_CBC - select CRYPTO_SHA1 - select CRYPTO_DES - select CRYPTO_ECHAINIV + select XFRM_ESP help - Support for IPsec ESP. + Support for IPsec ESP (Encapsulating Security Payload). + + ESP can be used with various encryption and authentication algorithms. + Besides enabling ESP support itself, this option enables the generic + implementations of the algorithms that RFC 8221 lists as MUST be + implemented. If you need any other algorithms, you'll need to enable + them in the crypto API. You should also enable accelerated + implementations of any needed algorithms when available. If unsure, say Y. diff --git a/net/ipv4/esp4_offload.c b/net/ipv4/esp4_offload.c index d14133eac476..5bda5aeda579 100644 --- a/net/ipv4/esp4_offload.c +++ b/net/ipv4/esp4_offload.c @@ -361,3 +361,4 @@ module_exit(esp4_offload_exit); MODULE_LICENSE("GPL"); MODULE_AUTHOR("Steffen Klassert <steffen.klassert@secunet.com>"); MODULE_ALIAS_XFRM_OFFLOAD_TYPE(AF_INET, XFRM_PROTO_ESP); +MODULE_DESCRIPTION("IPV4 GSO/GRO offload support"); diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c index e53871e4a097..1f75dc686b6b 100644 --- a/net/ipv4/fib_semantics.c +++ b/net/ipv4/fib_semantics.c @@ -1109,7 +1109,7 @@ static int fib_check_nh_v4_gw(struct net *net, struct fib_nh *nh, u32 table, if (fl4.flowi4_scope < RT_SCOPE_LINK) fl4.flowi4_scope = RT_SCOPE_LINK; - if (table) + if (table && table != RT_TABLE_MAIN) tbl = fib_get_table(net, table); if (tbl) diff --git a/net/ipv4/fou.c b/net/ipv4/fou.c index dcc79ff54b41..abd083415f89 100644 --- a/net/ipv4/fou.c +++ b/net/ipv4/fou.c @@ -1304,3 +1304,4 @@ module_init(fou_init); module_exit(fou_fini); MODULE_AUTHOR("Tom Herbert <therbert@google.com>"); MODULE_LICENSE("GPL"); +MODULE_DESCRIPTION("Foo over UDP"); diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c index 956a806649f7..e30515f89802 100644 --- a/net/ipv4/icmp.c +++ b/net/ipv4/icmp.c @@ -427,7 +427,7 @@ static void icmp_reply(struct icmp_bxm *icmp_param, struct sk_buff *skb) ipcm_init(&ipc); inet->tos = ip_hdr(skb)->tos; - sk->sk_mark = mark; + ipc.sockc.mark = mark; daddr = ipc.addr = ip_hdr(skb)->saddr; saddr = fib_compute_spec_dst(skb); @@ -710,10 +710,10 @@ void __icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info, icmp_param.skb = skb_in; icmp_param.offset = skb_network_offset(skb_in); inet_sk(sk)->tos = tos; - sk->sk_mark = mark; ipcm_init(&ipc); ipc.addr = iph->saddr; ipc.opt = &icmp_param.replyopts.opt; + ipc.sockc.mark = mark; rt = icmp_route_lookup(net, &fl4, skb_in, iph, saddr, tos, mark, type, code, &icmp_param); diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index 090d3097ee15..17206677d503 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -1702,7 +1702,7 @@ void ip_send_unicast_reply(struct sock *sk, struct sk_buff *skb, sk->sk_protocol = ip_hdr(skb)->protocol; sk->sk_bound_dev_if = arg->bound_dev_if; sk->sk_sndbuf = sysctl_wmem_default; - sk->sk_mark = fl4.flowi4_mark; + ipc.sockc.mark = fl4.flowi4_mark; err = ip_append_data(sk, &fl4, ip_reply_glue_bits, arg->iov->iov_base, len, 0, &ipc, &rt, MSG_DONTWAIT); if (unlikely(err)) { diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c index f4f1d11eab50..0c1f36404471 100644 --- a/net/ipv4/ip_tunnel.c +++ b/net/ipv4/ip_tunnel.c @@ -85,9 +85,10 @@ struct ip_tunnel *ip_tunnel_lookup(struct ip_tunnel_net *itn, __be32 remote, __be32 local, __be32 key) { - unsigned int hash; struct ip_tunnel *t, *cand = NULL; struct hlist_head *head; + struct net_device *ndev; + unsigned int hash; hash = ip_tunnel_hash(key, remote); head = &itn->tunnels[hash]; @@ -162,8 +163,9 @@ struct ip_tunnel *ip_tunnel_lookup(struct ip_tunnel_net *itn, if (t && t->dev->flags & IFF_UP) return t; - if (itn->fb_tunnel_dev && itn->fb_tunnel_dev->flags & IFF_UP) - return netdev_priv(itn->fb_tunnel_dev); + ndev = READ_ONCE(itn->fb_tunnel_dev); + if (ndev && ndev->flags & IFF_UP) + return netdev_priv(ndev); return NULL; } @@ -1259,9 +1261,9 @@ void ip_tunnel_uninit(struct net_device *dev) struct ip_tunnel_net *itn; itn = net_generic(net, tunnel->ip_tnl_net_id); - /* fb_tunnel_dev will be unregisted in net-exit call. */ - if (itn->fb_tunnel_dev != dev) - ip_tunnel_del(itn, netdev_priv(dev)); + ip_tunnel_del(itn, netdev_priv(dev)); + if (itn->fb_tunnel_dev == dev) + WRITE_ONCE(itn->fb_tunnel_dev, NULL); dst_cache_reset(&tunnel->dst_cache); } diff --git a/net/ipv4/ip_tunnel_core.c b/net/ipv4/ip_tunnel_core.c index 181b7a2a0247..f8b419e2475c 100644 --- a/net/ipv4/ip_tunnel_core.c +++ b/net/ipv4/ip_tunnel_core.c @@ -844,3 +844,21 @@ void ip_tunnel_unneed_metadata(void) static_branch_dec(&ip_tunnel_metadata_cnt); } EXPORT_SYMBOL_GPL(ip_tunnel_unneed_metadata); + +/* Returns either the correct skb->protocol value, or 0 if invalid. */ +__be16 ip_tunnel_parse_protocol(const struct sk_buff *skb) +{ + if (skb_network_header(skb) >= skb->head && + (skb_network_header(skb) + sizeof(struct iphdr)) <= skb_tail_pointer(skb) && + ip_hdr(skb)->version == 4) + return htons(ETH_P_IP); + if (skb_network_header(skb) >= skb->head && + (skb_network_header(skb) + sizeof(struct ipv6hdr)) <= skb_tail_pointer(skb) && + ipv6_hdr(skb)->version == 6) + return htons(ETH_P_IPV6); + return 0; +} +EXPORT_SYMBOL(ip_tunnel_parse_protocol); + +const struct header_ops ip_tunnel_header_ops = { .parse_protocol = ip_tunnel_parse_protocol }; +EXPORT_SYMBOL(ip_tunnel_header_ops); diff --git a/net/ipv4/ip_vti.c b/net/ipv4/ip_vti.c index 1d9c8cff5ac3..460ca1099e8a 100644 --- a/net/ipv4/ip_vti.c +++ b/net/ipv4/ip_vti.c @@ -441,6 +441,7 @@ static const struct net_device_ops vti_netdev_ops = { static void vti_tunnel_setup(struct net_device *dev) { dev->netdev_ops = &vti_netdev_ops; + dev->header_ops = &ip_tunnel_header_ops; dev->type = ARPHRD_TUNNEL; ip_tunnel_setup(dev, vti_net_id); } diff --git a/net/ipv4/ipip.c b/net/ipv4/ipip.c index 40fea52c8277..75d35e76bec2 100644 --- a/net/ipv4/ipip.c +++ b/net/ipv4/ipip.c @@ -361,6 +361,7 @@ static const struct net_device_ops ipip_netdev_ops = { static void ipip_tunnel_setup(struct net_device *dev) { dev->netdev_ops = &ipip_netdev_ops; + dev->header_ops = &ip_tunnel_header_ops; dev->type = ARPHRD_TUNNEL; dev->flags = IFF_NOARP; diff --git a/net/ipv4/netfilter/ip_tables.c b/net/ipv4/netfilter/ip_tables.c index c2670eaa74e6..5bf9fa06aee0 100644 --- a/net/ipv4/netfilter/ip_tables.c +++ b/net/ipv4/netfilter/ip_tables.c @@ -1797,11 +1797,22 @@ out_free: return ret; } +void ipt_unregister_table_pre_exit(struct net *net, struct xt_table *table, + const struct nf_hook_ops *ops) +{ + nf_unregister_net_hooks(net, ops, hweight32(table->valid_hooks)); +} + +void ipt_unregister_table_exit(struct net *net, struct xt_table *table) +{ + __ipt_unregister_table(net, table); +} + void ipt_unregister_table(struct net *net, struct xt_table *table, const struct nf_hook_ops *ops) { if (ops) - nf_unregister_net_hooks(net, ops, hweight32(table->valid_hooks)); + ipt_unregister_table_pre_exit(net, table, ops); __ipt_unregister_table(net, table); } @@ -1958,6 +1969,8 @@ static void __exit ip_tables_fini(void) EXPORT_SYMBOL(ipt_register_table); EXPORT_SYMBOL(ipt_unregister_table); +EXPORT_SYMBOL(ipt_unregister_table_pre_exit); +EXPORT_SYMBOL(ipt_unregister_table_exit); EXPORT_SYMBOL(ipt_do_table); module_init(ip_tables_init); module_exit(ip_tables_fini); diff --git a/net/ipv4/netfilter/ipt_SYNPROXY.c b/net/ipv4/netfilter/ipt_SYNPROXY.c index 748dc3ce58d3..f2984c7eef40 100644 --- a/net/ipv4/netfilter/ipt_SYNPROXY.c +++ b/net/ipv4/netfilter/ipt_SYNPROXY.c @@ -118,3 +118,4 @@ module_exit(synproxy_tg4_exit); MODULE_LICENSE("GPL"); MODULE_AUTHOR("Patrick McHardy <kaber@trash.net>"); +MODULE_DESCRIPTION("Intercept TCP connections and establish them using syncookies"); diff --git a/net/ipv4/netfilter/iptable_filter.c b/net/ipv4/netfilter/iptable_filter.c index 9d54b4017e50..8f7bc1ee7453 100644 --- a/net/ipv4/netfilter/iptable_filter.c +++ b/net/ipv4/netfilter/iptable_filter.c @@ -72,16 +72,24 @@ static int __net_init iptable_filter_net_init(struct net *net) return 0; } +static void __net_exit iptable_filter_net_pre_exit(struct net *net) +{ + if (net->ipv4.iptable_filter) + ipt_unregister_table_pre_exit(net, net->ipv4.iptable_filter, + filter_ops); +} + static void __net_exit iptable_filter_net_exit(struct net *net) { if (!net->ipv4.iptable_filter) return; - ipt_unregister_table(net, net->ipv4.iptable_filter, filter_ops); + ipt_unregister_table_exit(net, net->ipv4.iptable_filter); net->ipv4.iptable_filter = NULL; } static struct pernet_operations iptable_filter_net_ops = { .init = iptable_filter_net_init, + .pre_exit = iptable_filter_net_pre_exit, .exit = iptable_filter_net_exit, }; diff --git a/net/ipv4/netfilter/iptable_mangle.c b/net/ipv4/netfilter/iptable_mangle.c index bb9266ea3785..f703a717ab1d 100644 --- a/net/ipv4/netfilter/iptable_mangle.c +++ b/net/ipv4/netfilter/iptable_mangle.c @@ -100,15 +100,23 @@ static int __net_init iptable_mangle_table_init(struct net *net) return ret; } +static void __net_exit iptable_mangle_net_pre_exit(struct net *net) +{ + if (net->ipv4.iptable_mangle) + ipt_unregister_table_pre_exit(net, net->ipv4.iptable_mangle, + mangle_ops); +} + static void __net_exit iptable_mangle_net_exit(struct net *net) { if (!net->ipv4.iptable_mangle) return; - ipt_unregister_table(net, net->ipv4.iptable_mangle, mangle_ops); + ipt_unregister_table_exit(net, net->ipv4.iptable_mangle); net->ipv4.iptable_mangle = NULL; } static struct pernet_operations iptable_mangle_net_ops = { + .pre_exit = iptable_mangle_net_pre_exit, .exit = iptable_mangle_net_exit, }; diff --git a/net/ipv4/netfilter/iptable_nat.c b/net/ipv4/netfilter/iptable_nat.c index ad33687b7444..b0143b109f25 100644 --- a/net/ipv4/netfilter/iptable_nat.c +++ b/net/ipv4/netfilter/iptable_nat.c @@ -113,16 +113,22 @@ static int __net_init iptable_nat_table_init(struct net *net) return ret; } +static void __net_exit iptable_nat_net_pre_exit(struct net *net) +{ + if (net->ipv4.nat_table) + ipt_nat_unregister_lookups(net); +} + static void __net_exit iptable_nat_net_exit(struct net *net) { if (!net->ipv4.nat_table) return; - ipt_nat_unregister_lookups(net); - ipt_unregister_table(net, net->ipv4.nat_table, NULL); + ipt_unregister_table_exit(net, net->ipv4.nat_table); net->ipv4.nat_table = NULL; } static struct pernet_operations iptable_nat_net_ops = { + .pre_exit = iptable_nat_net_pre_exit, .exit = iptable_nat_net_exit, }; diff --git a/net/ipv4/netfilter/iptable_raw.c b/net/ipv4/netfilter/iptable_raw.c index 69697eb4bfc6..9abfe6bf2cb9 100644 --- a/net/ipv4/netfilter/iptable_raw.c +++ b/net/ipv4/netfilter/iptable_raw.c @@ -67,15 +67,23 @@ static int __net_init iptable_raw_table_init(struct net *net) return ret; } +static void __net_exit iptable_raw_net_pre_exit(struct net *net) +{ + if (net->ipv4.iptable_raw) + ipt_unregister_table_pre_exit(net, net->ipv4.iptable_raw, + rawtable_ops); +} + static void __net_exit iptable_raw_net_exit(struct net *net) { if (!net->ipv4.iptable_raw) return; - ipt_unregister_table(net, net->ipv4.iptable_raw, rawtable_ops); + ipt_unregister_table_exit(net, net->ipv4.iptable_raw); net->ipv4.iptable_raw = NULL; } static struct pernet_operations iptable_raw_net_ops = { + .pre_exit = iptable_raw_net_pre_exit, .exit = iptable_raw_net_exit, }; diff --git a/net/ipv4/netfilter/iptable_security.c b/net/ipv4/netfilter/iptable_security.c index ac633c1db97e..415c1975d770 100644 --- a/net/ipv4/netfilter/iptable_security.c +++ b/net/ipv4/netfilter/iptable_security.c @@ -62,16 +62,23 @@ static int __net_init iptable_security_table_init(struct net *net) return ret; } +static void __net_exit iptable_security_net_pre_exit(struct net *net) +{ + if (net->ipv4.iptable_security) + ipt_unregister_table_pre_exit(net, net->ipv4.iptable_security, + sectbl_ops); +} + static void __net_exit iptable_security_net_exit(struct net *net) { if (!net->ipv4.iptable_security) return; - - ipt_unregister_table(net, net->ipv4.iptable_security, sectbl_ops); + ipt_unregister_table_exit(net, net->ipv4.iptable_security); net->ipv4.iptable_security = NULL; } static struct pernet_operations iptable_security_net_ops = { + .pre_exit = iptable_security_net_pre_exit, .exit = iptable_security_net_exit, }; diff --git a/net/ipv4/netfilter/nf_flow_table_ipv4.c b/net/ipv4/netfilter/nf_flow_table_ipv4.c index e32e41b99f0f..aba65fe90345 100644 --- a/net/ipv4/netfilter/nf_flow_table_ipv4.c +++ b/net/ipv4/netfilter/nf_flow_table_ipv4.c @@ -34,3 +34,4 @@ module_exit(nf_flow_ipv4_module_exit); MODULE_LICENSE("GPL"); MODULE_AUTHOR("Pablo Neira Ayuso <pablo@netfilter.org>"); MODULE_ALIAS_NF_FLOWTABLE(AF_INET); +MODULE_DESCRIPTION("Netfilter flow table support"); diff --git a/net/ipv4/netfilter/nft_dup_ipv4.c b/net/ipv4/netfilter/nft_dup_ipv4.c index abf89b972094..bcdb37f86a94 100644 --- a/net/ipv4/netfilter/nft_dup_ipv4.c +++ b/net/ipv4/netfilter/nft_dup_ipv4.c @@ -107,3 +107,4 @@ module_exit(nft_dup_ipv4_module_exit); MODULE_LICENSE("GPL"); MODULE_AUTHOR("Pablo Neira Ayuso <pablo@netfilter.org>"); MODULE_ALIAS_NFT_AF_EXPR(AF_INET, "dup"); +MODULE_DESCRIPTION("IPv4 nftables packet duplication support"); diff --git a/net/ipv4/netfilter/nft_fib_ipv4.c b/net/ipv4/netfilter/nft_fib_ipv4.c index ce294113dbcd..03df986217b7 100644 --- a/net/ipv4/netfilter/nft_fib_ipv4.c +++ b/net/ipv4/netfilter/nft_fib_ipv4.c @@ -210,3 +210,4 @@ module_exit(nft_fib4_module_exit); MODULE_LICENSE("GPL"); MODULE_AUTHOR("Florian Westphal <fw@strlen.de>"); MODULE_ALIAS_NFT_AF_EXPR(2, "fib"); +MODULE_DESCRIPTION("nftables fib / ip route lookup support"); diff --git a/net/ipv4/netfilter/nft_reject_ipv4.c b/net/ipv4/netfilter/nft_reject_ipv4.c index 7e6fd5cde50f..e408f813f5d8 100644 --- a/net/ipv4/netfilter/nft_reject_ipv4.c +++ b/net/ipv4/netfilter/nft_reject_ipv4.c @@ -71,3 +71,4 @@ module_exit(nft_reject_ipv4_module_exit); MODULE_LICENSE("GPL"); MODULE_AUTHOR("Patrick McHardy <kaber@trash.net>"); MODULE_ALIAS_NFT_AF_EXPR(AF_INET, "reject"); +MODULE_DESCRIPTION("IPv4 packet rejection for nftables"); diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c index 535427292194..df6fbefe44d4 100644 --- a/net/ipv4/ping.c +++ b/net/ipv4/ping.c @@ -786,6 +786,9 @@ static int ping_v4_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) inet_sk_flowi_flags(sk), faddr, saddr, 0, 0, sk->sk_uid); + fl4.fl4_icmp_type = user_icmph.type; + fl4.fl4_icmp_code = user_icmph.code; + security_sk_classify_flow(sk, flowi4_to_flowi(&fl4)); rt = ip_route_output_flow(net, &fl4, sk); if (IS_ERR(rt)) { diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 1d7076b78e63..a01efa062f6b 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -2027,7 +2027,7 @@ int ip_route_use_hint(struct sk_buff *skb, __be32 daddr, __be32 saddr, const struct sk_buff *hint) { struct in_device *in_dev = __in_dev_get_rcu(dev); - struct rtable *rt = (struct rtable *)hint; + struct rtable *rt = skb_rtable(hint); struct net *net = dev_net(dev); int err = -EINVAL; u32 tag = 0; diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 810cc164f795..6f0caf9a866d 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -2691,6 +2691,9 @@ int tcp_disconnect(struct sock *sk, int flags) tp->window_clamp = 0; tp->delivered = 0; tp->delivered_ce = 0; + if (icsk->icsk_ca_ops->release) + icsk->icsk_ca_ops->release(sk); + memset(icsk->icsk_ca_priv, 0, sizeof(icsk->icsk_ca_priv)); tcp_set_ca_state(sk, TCP_CA_Open); tp->is_sack_reneg = 0; tcp_clear_retrans(tp); @@ -3246,10 +3249,7 @@ static int do_tcp_setsockopt(struct sock *sk, int level, #ifdef CONFIG_TCP_MD5SIG case TCP_MD5SIG: case TCP_MD5SIG_EXT: - if ((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN)) - err = tp->af_specific->md5_parse(sk, optname, optval, optlen); - else - err = -EINVAL; + err = tp->af_specific->md5_parse(sk, optname, optval, optlen); break; #endif case TCP_USER_TIMEOUT: @@ -4033,11 +4033,14 @@ EXPORT_SYMBOL(tcp_md5_hash_skb_data); int tcp_md5_hash_key(struct tcp_md5sig_pool *hp, const struct tcp_md5sig_key *key) { + u8 keylen = READ_ONCE(key->keylen); /* paired with WRITE_ONCE() in tcp_md5_do_add */ struct scatterlist sg; - sg_init_one(&sg, key->key, key->keylen); - ahash_request_set_crypt(hp->md5_req, &sg, NULL, key->keylen); - return crypto_ahash_update(hp->md5_req); + sg_init_one(&sg, key->key, keylen); + ahash_request_set_crypt(hp->md5_req, &sg, NULL, keylen); + + /* We use data_race() because tcp_md5_do_add() might change key->key under us */ + return data_race(crypto_ahash_update(hp->md5_req)); } EXPORT_SYMBOL(tcp_md5_hash_key); diff --git a/net/ipv4/tcp_cong.c b/net/ipv4/tcp_cong.c index 3172e31987be..62878cf26d9c 100644 --- a/net/ipv4/tcp_cong.c +++ b/net/ipv4/tcp_cong.c @@ -197,7 +197,7 @@ static void tcp_reinit_congestion_control(struct sock *sk, icsk->icsk_ca_setsockopt = 1; memset(icsk->icsk_ca_priv, 0, sizeof(icsk->icsk_ca_priv)); - if (sk->sk_state != TCP_CLOSE) + if (!((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN))) tcp_init_congestion_control(sk); } diff --git a/net/ipv4/tcp_cubic.c b/net/ipv4/tcp_cubic.c index 8f8eefd3a3ce..c7bf5b26bf0c 100644 --- a/net/ipv4/tcp_cubic.c +++ b/net/ipv4/tcp_cubic.c @@ -432,10 +432,9 @@ static void hystart_update(struct sock *sk, u32 delay) if (hystart_detect & HYSTART_DELAY) { /* obtain the minimum delay of more than sampling packets */ + if (ca->curr_rtt > delay) + ca->curr_rtt = delay; if (ca->sample_cnt < HYSTART_MIN_SAMPLES) { - if (ca->curr_rtt > delay) - ca->curr_rtt = delay; - ca->sample_cnt++; } else { if (ca->curr_rtt > ca->delay_min + diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 83330a6cb242..518f04355fbf 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -261,7 +261,8 @@ static void tcp_ecn_accept_cwr(struct sock *sk, const struct sk_buff *skb) * cwnd may be very low (even just 1 packet), so we should ACK * immediately. */ - inet_csk(sk)->icsk_ack.pending |= ICSK_ACK_NOW; + if (TCP_SKB_CB(skb)->seq != TCP_SKB_CB(skb)->end_seq) + inet_csk(sk)->icsk_ack.pending |= ICSK_ACK_NOW; } } @@ -3487,10 +3488,8 @@ static void tcp_replace_ts_recent(struct tcp_sock *tp, u32 seq) } } -/* This routine deals with acks during a TLP episode. - * We mark the end of a TLP episode on receiving TLP dupack or when - * ack is after tlp_high_seq. - * Ref: loss detection algorithm in draft-dukkipati-tcpm-tcp-loss-probe. +/* This routine deals with acks during a TLP episode and ends an episode by + * resetting tlp_high_seq. Ref: TLP algorithm in draft-ietf-tcpm-rack */ static void tcp_process_tlp_ack(struct sock *sk, u32 ack, int flag) { @@ -3499,7 +3498,10 @@ static void tcp_process_tlp_ack(struct sock *sk, u32 ack, int flag) if (before(ack, tp->tlp_high_seq)) return; - if (flag & FLAG_DSACKING_ACK) { + if (!tp->tlp_retrans) { + /* TLP of new data has been acknowledged */ + tp->tlp_high_seq = 0; + } else if (flag & FLAG_DSACKING_ACK) { /* This DSACK means original and TLP probe arrived; no loss */ tp->tlp_high_seq = 0; } else if (after(ack, tp->tlp_high_seq)) { @@ -3665,6 +3667,15 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag) tcp_in_ack_event(sk, ack_ev_flags); } + /* This is a deviation from RFC3168 since it states that: + * "When the TCP data sender is ready to set the CWR bit after reducing + * the congestion window, it SHOULD set the CWR bit only on the first + * new data packet that it transmits." + * We accept CWR on pure ACKs to be more robust + * with widely-deployed TCP implementations that do this. + */ + tcp_ecn_accept_cwr(sk, skb); + /* We passed data and got it acked, remove any soft error * log. Something worked... */ @@ -4572,6 +4583,7 @@ static void tcp_data_queue_ofo(struct sock *sk, struct sk_buff *skb) if (unlikely(tcp_try_rmem_schedule(sk, skb, skb->truesize))) { NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPOFODROP); + sk->sk_data_ready(sk); tcp_drop(sk, skb); return; } @@ -4605,7 +4617,11 @@ static void tcp_data_queue_ofo(struct sock *sk, struct sk_buff *skb) if (tcp_ooo_try_coalesce(sk, tp->ooo_last_skb, skb, &fragstolen)) { coalesce_done: - tcp_grow_window(sk, skb); + /* For non sack flows, do not grow window to force DUPACK + * and trigger fast retransmit. + */ + if (tcp_is_sack(tp)) + tcp_grow_window(sk, skb); kfree_skb_partial(skb, fragstolen); skb = NULL; goto add_sack; @@ -4689,7 +4705,11 @@ add_sack: tcp_sack_new_ofo_skb(sk, seq, end_seq); end: if (skb) { - tcp_grow_window(sk, skb); + /* For non sack flows, do not grow window to force DUPACK + * and trigger fast retransmit. + */ + if (tcp_is_sack(tp)) + tcp_grow_window(sk, skb); skb_condense(skb); skb_set_owner_r(skb, sk); } @@ -4792,8 +4812,6 @@ static void tcp_data_queue(struct sock *sk, struct sk_buff *skb) skb_dst_drop(skb); __skb_pull(skb, tcp_hdr(skb)->doff * 4); - tcp_ecn_accept_cwr(sk, skb); - tp->rx_opt.dsack = 0; /* Queue data for delivery to the user. @@ -4812,6 +4830,7 @@ queue_and_out: sk_forced_mem_schedule(sk, skb->truesize); else if (tcp_try_rmem_schedule(sk, skb, skb->truesize)) { NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPRCVQDROP); + sk->sk_data_ready(sk); goto drop; } diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index ad6435ba6d72..04bfcbbfee83 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -1111,9 +1111,21 @@ int tcp_md5_do_add(struct sock *sk, const union tcp_md5_addr *addr, key = tcp_md5_do_lookup_exact(sk, addr, family, prefixlen, l3index); if (key) { - /* Pre-existing entry - just update that one. */ - memcpy(key->key, newkey, newkeylen); - key->keylen = newkeylen; + /* Pre-existing entry - just update that one. + * Note that the key might be used concurrently. + * data_race() is telling kcsan that we do not care of + * key mismatches, since changing MD5 key on live flows + * can lead to packet drops. + */ + data_race(memcpy(key->key, newkey, newkeylen)); + + /* Pairs with READ_ONCE() in tcp_md5_hash_key(). + * Also note that a reader could catch new key->keylen value + * but old key->key[], this is the reason we use __GFP_ZERO + * at sock_kmalloc() time below these lines. + */ + WRITE_ONCE(key->keylen, newkeylen); + return 0; } @@ -1129,7 +1141,7 @@ int tcp_md5_do_add(struct sock *sk, const union tcp_md5_addr *addr, rcu_assign_pointer(tp->md5sig_info, md5sig); } - key = sock_kmalloc(sk, sizeof(*key), gfp); + key = sock_kmalloc(sk, sizeof(*key), gfp | __GFP_ZERO); if (!key) return -ENOMEM; if (!tcp_alloc_md5sig_pool()) { diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index a50e1990a845..0bc05d68cd74 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -700,7 +700,8 @@ static unsigned int tcp_synack_options(const struct sock *sk, unsigned int mss, struct sk_buff *skb, struct tcp_out_options *opts, const struct tcp_md5sig_key *md5, - struct tcp_fastopen_cookie *foc) + struct tcp_fastopen_cookie *foc, + enum tcp_synack_type synack_type) { struct inet_request_sock *ireq = inet_rsk(req); unsigned int remaining = MAX_TCP_OPTION_SPACE; @@ -715,7 +716,8 @@ static unsigned int tcp_synack_options(const struct sock *sk, * rather than TS in order to fit in better with old, * buggy kernels, but that was deemed to be unnecessary. */ - ireq->tstamp_ok &= !ireq->sack_ok; + if (synack_type != TCP_SYNACK_COOKIE) + ireq->tstamp_ok &= !ireq->sack_ok; } #endif @@ -2622,6 +2624,11 @@ void tcp_send_loss_probe(struct sock *sk) int pcount; int mss = tcp_current_mss(sk); + /* At most one outstanding TLP */ + if (tp->tlp_high_seq) + goto rearm_timer; + + tp->tlp_retrans = 0; skb = tcp_send_head(sk); if (skb && tcp_snd_wnd_test(tp, skb, mss)) { pcount = tp->packets_out; @@ -2639,10 +2646,6 @@ void tcp_send_loss_probe(struct sock *sk) return; } - /* At most one outstanding TLP retransmission. */ - if (tp->tlp_high_seq) - goto rearm_timer; - if (skb_still_in_host_queue(sk, skb)) goto rearm_timer; @@ -2664,10 +2667,12 @@ void tcp_send_loss_probe(struct sock *sk) if (__tcp_retransmit_skb(sk, skb, 1)) goto rearm_timer; + tp->tlp_retrans = 1; + +probe_sent: /* Record snd_nxt for loss detection. */ tp->tlp_high_seq = tp->snd_nxt; -probe_sent: NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPLOSSPROBES); /* Reset s.t. tcp_rearm_rto will restart timer from now */ inet_csk(sk)->icsk_pending = 0; @@ -3394,7 +3399,7 @@ struct sk_buff *tcp_make_synack(const struct sock *sk, struct dst_entry *dst, #endif skb_set_hash(skb, tcp_rsk(req)->txhash, PKT_HASH_TYPE_L4); tcp_header_size = tcp_synack_options(sk, req, mss, skb, &opts, md5, - foc) + sizeof(*th); + foc, synack_type) + sizeof(*th); skb_push(skb, tcp_header_size); skb_reset_transport_header(skb); diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 1b7ebbcae497..4077d589b72e 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -416,7 +416,7 @@ static struct sock *udp4_lib_lookup2(struct net *net, struct udp_hslot *hslot2, struct sk_buff *skb) { - struct sock *sk, *result; + struct sock *sk, *result, *reuseport_result; int score, badness; u32 hash = 0; @@ -426,17 +426,20 @@ static struct sock *udp4_lib_lookup2(struct net *net, score = compute_score(sk, net, saddr, sport, daddr, hnum, dif, sdif); if (score > badness) { + reuseport_result = NULL; + if (sk->sk_reuseport && sk->sk_state != TCP_ESTABLISHED) { hash = udp_ehashfn(net, daddr, hnum, saddr, sport); - result = reuseport_select_sock(sk, hash, skb, - sizeof(struct udphdr)); - if (result && !reuseport_has_conns(sk, false)) - return result; + reuseport_result = reuseport_select_sock(sk, hash, skb, + sizeof(struct udphdr)); + if (reuseport_result && !reuseport_has_conns(sk, false)) + return reuseport_result; } + + result = reuseport_result ? : sk; badness = score; - result = sk; } } return result; @@ -2051,7 +2054,7 @@ static int udp_queue_rcv_one_skb(struct sock *sk, struct sk_buff *skb) /* * UDP-Lite specific tests, ignored on UDP sockets */ - if ((is_udplite & UDPLITE_RECV_CC) && UDP_SKB_CB(skb)->partial_cov) { + if ((up->pcflag & UDPLITE_RECV_CC) && UDP_SKB_CB(skb)->partial_cov) { /* * MIB statistics other than incrementing the error count are diff --git a/net/ipv6/Kconfig b/net/ipv6/Kconfig index 992cf45fb4f6..f4f19e89af5e 100644 --- a/net/ipv6/Kconfig +++ b/net/ipv6/Kconfig @@ -49,29 +49,31 @@ config IPV6_OPTIMISTIC_DAD config INET6_AH tristate "IPv6: AH transformation" - select XFRM_ALGO - select CRYPTO - select CRYPTO_HMAC - select CRYPTO_MD5 - select CRYPTO_SHA1 + select XFRM_AH help - Support for IPsec AH. + Support for IPsec AH (Authentication Header). + + AH can be used with various authentication algorithms. Besides + enabling AH support itself, this option enables the generic + implementations of the algorithms that RFC 8221 lists as MUST be + implemented. If you need any other algorithms, you'll need to enable + them in the crypto API. You should also enable accelerated + implementations of any needed algorithms when available. If unsure, say Y. config INET6_ESP tristate "IPv6: ESP transformation" - select XFRM_ALGO - select CRYPTO - select CRYPTO_AUTHENC - select CRYPTO_HMAC - select CRYPTO_MD5 - select CRYPTO_CBC - select CRYPTO_SHA1 - select CRYPTO_DES - select CRYPTO_ECHAINIV + select XFRM_ESP help - Support for IPsec ESP. + Support for IPsec ESP (Encapsulating Security Payload). + + ESP can be used with various encryption and authentication algorithms. + Besides enabling ESP support itself, this option enables the generic + implementations of the algorithms that RFC 8221 lists as MUST be + implemented. If you need any other algorithms, you'll need to enable + them in the crypto API. You should also enable accelerated + implementations of any needed algorithms when available. If unsure, say Y. diff --git a/net/ipv6/esp6_offload.c b/net/ipv6/esp6_offload.c index 55addea1948f..1ca516fb30e1 100644 --- a/net/ipv6/esp6_offload.c +++ b/net/ipv6/esp6_offload.c @@ -395,3 +395,4 @@ module_exit(esp6_offload_exit); MODULE_LICENSE("GPL"); MODULE_AUTHOR("Steffen Klassert <steffen.klassert@secunet.com>"); MODULE_ALIAS_XFRM_OFFLOAD_TYPE(AF_INET6, XFRM_PROTO_ESP); +MODULE_DESCRIPTION("IPV6 GSO/GRO offload support"); diff --git a/net/ipv6/fou6.c b/net/ipv6/fou6.c index 091f94184dc1..430518ae26fa 100644 --- a/net/ipv6/fou6.c +++ b/net/ipv6/fou6.c @@ -224,3 +224,4 @@ module_init(fou6_init); module_exit(fou6_fini); MODULE_AUTHOR("Tom Herbert <therbert@google.com>"); MODULE_LICENSE("GPL"); +MODULE_DESCRIPTION("Foo over UDP (IPv6)"); diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c index fc5000370030..9df8737ae0d3 100644 --- a/net/ipv6/icmp.c +++ b/net/ipv6/icmp.c @@ -566,7 +566,6 @@ static void icmp6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info, fl6.mp_hash = rt6_multipath_hash(net, &fl6, skb, NULL); security_skb_classify_flow(skb, flowi6_to_flowi(&fl6)); - sk->sk_mark = mark; np = inet6_sk(sk); if (!icmpv6_xrlim_allow(sk, type, &fl6)) @@ -583,6 +582,7 @@ static void icmp6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info, fl6.flowi6_oif = np->ucast_oif; ipcm6_init_sk(&ipc6, np); + ipc6.sockc.mark = mark; fl6.flowlabel = ip6_make_flowinfo(ipc6.tclass, fl6.flowlabel); dst = icmpv6_route_lookup(net, skb, sk, &fl6); @@ -751,7 +751,6 @@ static void icmpv6_echo_reply(struct sk_buff *skb) sk = icmpv6_xmit_lock(net); if (!sk) goto out_bh_enable; - sk->sk_mark = mark; np = inet6_sk(sk); if (!fl6.flowi6_oif && ipv6_addr_is_multicast(&fl6.daddr)) @@ -779,6 +778,7 @@ static void icmpv6_echo_reply(struct sk_buff *skb) ipcm6_init_sk(&ipc6, np); ipc6.hlimit = ip6_sk_dst_hoplimit(np, &fl6, dst); ipc6.tclass = ipv6_get_dsfield(ipv6_hdr(skb)); + ipc6.sockc.mark = mark; if (ip6_append_data(sk, icmpv6_getfrag, &msg, skb->len + sizeof(struct icmp6hdr), diff --git a/net/ipv6/ila/ila_main.c b/net/ipv6/ila/ila_main.c index 257d2b681246..36c58aa257e8 100644 --- a/net/ipv6/ila/ila_main.c +++ b/net/ipv6/ila/ila_main.c @@ -120,3 +120,4 @@ module_init(ila_init); module_exit(ila_fini); MODULE_AUTHOR("Tom Herbert <tom@herbertland.com>"); MODULE_LICENSE("GPL"); +MODULE_DESCRIPTION("IPv6: Identifier Locator Addressing (ILA)"); diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c index 781ca8c07a0d..3a57fb9ce049 100644 --- a/net/ipv6/ip6_gre.c +++ b/net/ipv6/ip6_gre.c @@ -127,6 +127,7 @@ static struct ip6_tnl *ip6gre_tunnel_lookup(struct net_device *dev, gre_proto == htons(ETH_P_ERSPAN2)) ? ARPHRD_ETHER : ARPHRD_IP6GRE; int score, cand_score = 4; + struct net_device *ndev; for_each_ip_tunnel_rcu(t, ign->tunnels_r_l[h0 ^ h1]) { if (!ipv6_addr_equal(local, &t->parms.laddr) || @@ -238,9 +239,9 @@ static struct ip6_tnl *ip6gre_tunnel_lookup(struct net_device *dev, if (t && t->dev->flags & IFF_UP) return t; - dev = ign->fb_tunnel_dev; - if (dev && dev->flags & IFF_UP) - return netdev_priv(dev); + ndev = READ_ONCE(ign->fb_tunnel_dev); + if (ndev && ndev->flags & IFF_UP) + return netdev_priv(ndev); return NULL; } @@ -413,6 +414,8 @@ static void ip6gre_tunnel_uninit(struct net_device *dev) ip6gre_tunnel_unlink_md(ign, t); ip6gre_tunnel_unlink(ign, t); + if (ign->fb_tunnel_dev == dev) + WRITE_ONCE(ign->fb_tunnel_dev, NULL); dst_cache_reset(&t->dst_cache); dev_put(dev); } @@ -1559,17 +1562,18 @@ static void ip6gre_destroy_tunnels(struct net *net, struct list_head *head) static int __net_init ip6gre_init_net(struct net *net) { struct ip6gre_net *ign = net_generic(net, ip6gre_net_id); + struct net_device *ndev; int err; if (!net_has_fallback_tunnels(net)) return 0; - ign->fb_tunnel_dev = alloc_netdev(sizeof(struct ip6_tnl), "ip6gre0", - NET_NAME_UNKNOWN, - ip6gre_tunnel_setup); - if (!ign->fb_tunnel_dev) { + ndev = alloc_netdev(sizeof(struct ip6_tnl), "ip6gre0", + NET_NAME_UNKNOWN, ip6gre_tunnel_setup); + if (!ndev) { err = -ENOMEM; goto err_alloc_dev; } + ign->fb_tunnel_dev = ndev; dev_net_set(ign->fb_tunnel_dev, net); /* FB netdevice is special: we have one, and only one per netns. * Allowing to move it to another netns is clearly unsafe. @@ -1589,7 +1593,7 @@ static int __net_init ip6gre_init_net(struct net *net) return 0; err_reg_dev: - free_netdev(ign->fb_tunnel_dev); + free_netdev(ndev); err_alloc_dev: return err; } diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c index 821d96c720b9..a18c378ca5f4 100644 --- a/net/ipv6/ip6_tunnel.c +++ b/net/ipv6/ip6_tunnel.c @@ -1846,6 +1846,7 @@ static const struct net_device_ops ip6_tnl_netdev_ops = { static void ip6_tnl_dev_setup(struct net_device *dev) { dev->netdev_ops = &ip6_tnl_netdev_ops; + dev->header_ops = &ip_tunnel_header_ops; dev->needs_free_netdev = true; dev->priv_destructor = ip6_dev_free; diff --git a/net/ipv6/ip6_vti.c b/net/ipv6/ip6_vti.c index 1147f647b9a0..0d964160a9dd 100644 --- a/net/ipv6/ip6_vti.c +++ b/net/ipv6/ip6_vti.c @@ -905,6 +905,7 @@ static const struct net_device_ops vti6_netdev_ops = { static void vti6_dev_setup(struct net_device *dev) { dev->netdev_ops = &vti6_netdev_ops; + dev->header_ops = &ip_tunnel_header_ops; dev->needs_free_netdev = true; dev->priv_destructor = vti6_dev_free; diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c index 7e12d2114158..8cd2782a31e4 100644 --- a/net/ipv6/mcast.c +++ b/net/ipv6/mcast.c @@ -2615,6 +2615,7 @@ void ipv6_mc_destroy_dev(struct inet6_dev *idev) idev->mc_list = i->next; write_unlock_bh(&idev->lock); + ip6_mc_clear_src(i); ma_put(i); write_lock_bh(&idev->lock); } diff --git a/net/ipv6/netfilter/ip6_tables.c b/net/ipv6/netfilter/ip6_tables.c index e27393498ecb..e96a431549bc 100644 --- a/net/ipv6/netfilter/ip6_tables.c +++ b/net/ipv6/netfilter/ip6_tables.c @@ -1807,11 +1807,22 @@ out_free: return ret; } +void ip6t_unregister_table_pre_exit(struct net *net, struct xt_table *table, + const struct nf_hook_ops *ops) +{ + nf_unregister_net_hooks(net, ops, hweight32(table->valid_hooks)); +} + +void ip6t_unregister_table_exit(struct net *net, struct xt_table *table) +{ + __ip6t_unregister_table(net, table); +} + void ip6t_unregister_table(struct net *net, struct xt_table *table, const struct nf_hook_ops *ops) { if (ops) - nf_unregister_net_hooks(net, ops, hweight32(table->valid_hooks)); + ip6t_unregister_table_pre_exit(net, table, ops); __ip6t_unregister_table(net, table); } @@ -1969,6 +1980,8 @@ static void __exit ip6_tables_fini(void) EXPORT_SYMBOL(ip6t_register_table); EXPORT_SYMBOL(ip6t_unregister_table); +EXPORT_SYMBOL(ip6t_unregister_table_pre_exit); +EXPORT_SYMBOL(ip6t_unregister_table_exit); EXPORT_SYMBOL(ip6t_do_table); module_init(ip6_tables_init); diff --git a/net/ipv6/netfilter/ip6t_SYNPROXY.c b/net/ipv6/netfilter/ip6t_SYNPROXY.c index fd1f52a21bf1..d51d0c3e5fe9 100644 --- a/net/ipv6/netfilter/ip6t_SYNPROXY.c +++ b/net/ipv6/netfilter/ip6t_SYNPROXY.c @@ -121,3 +121,4 @@ module_exit(synproxy_tg6_exit); MODULE_LICENSE("GPL"); MODULE_AUTHOR("Patrick McHardy <kaber@trash.net>"); +MODULE_DESCRIPTION("Intercept IPv6 TCP connections and establish them using syncookies"); diff --git a/net/ipv6/netfilter/ip6table_filter.c b/net/ipv6/netfilter/ip6table_filter.c index 32667f5d5a33..88337b51ffbf 100644 --- a/net/ipv6/netfilter/ip6table_filter.c +++ b/net/ipv6/netfilter/ip6table_filter.c @@ -73,16 +73,24 @@ static int __net_init ip6table_filter_net_init(struct net *net) return 0; } +static void __net_exit ip6table_filter_net_pre_exit(struct net *net) +{ + if (net->ipv6.ip6table_filter) + ip6t_unregister_table_pre_exit(net, net->ipv6.ip6table_filter, + filter_ops); +} + static void __net_exit ip6table_filter_net_exit(struct net *net) { if (!net->ipv6.ip6table_filter) return; - ip6t_unregister_table(net, net->ipv6.ip6table_filter, filter_ops); + ip6t_unregister_table_exit(net, net->ipv6.ip6table_filter); net->ipv6.ip6table_filter = NULL; } static struct pernet_operations ip6table_filter_net_ops = { .init = ip6table_filter_net_init, + .pre_exit = ip6table_filter_net_pre_exit, .exit = ip6table_filter_net_exit, }; diff --git a/net/ipv6/netfilter/ip6table_mangle.c b/net/ipv6/netfilter/ip6table_mangle.c index 070afb97fa2b..1a2748611e00 100644 --- a/net/ipv6/netfilter/ip6table_mangle.c +++ b/net/ipv6/netfilter/ip6table_mangle.c @@ -93,16 +93,24 @@ static int __net_init ip6table_mangle_table_init(struct net *net) return ret; } +static void __net_exit ip6table_mangle_net_pre_exit(struct net *net) +{ + if (net->ipv6.ip6table_mangle) + ip6t_unregister_table_pre_exit(net, net->ipv6.ip6table_mangle, + mangle_ops); +} + static void __net_exit ip6table_mangle_net_exit(struct net *net) { if (!net->ipv6.ip6table_mangle) return; - ip6t_unregister_table(net, net->ipv6.ip6table_mangle, mangle_ops); + ip6t_unregister_table_exit(net, net->ipv6.ip6table_mangle); net->ipv6.ip6table_mangle = NULL; } static struct pernet_operations ip6table_mangle_net_ops = { + .pre_exit = ip6table_mangle_net_pre_exit, .exit = ip6table_mangle_net_exit, }; diff --git a/net/ipv6/netfilter/ip6table_nat.c b/net/ipv6/netfilter/ip6table_nat.c index 0f4875952efc..0a23265e3caa 100644 --- a/net/ipv6/netfilter/ip6table_nat.c +++ b/net/ipv6/netfilter/ip6table_nat.c @@ -114,16 +114,22 @@ static int __net_init ip6table_nat_table_init(struct net *net) return ret; } +static void __net_exit ip6table_nat_net_pre_exit(struct net *net) +{ + if (net->ipv6.ip6table_nat) + ip6t_nat_unregister_lookups(net); +} + static void __net_exit ip6table_nat_net_exit(struct net *net) { if (!net->ipv6.ip6table_nat) return; - ip6t_nat_unregister_lookups(net); - ip6t_unregister_table(net, net->ipv6.ip6table_nat, NULL); + ip6t_unregister_table_exit(net, net->ipv6.ip6table_nat); net->ipv6.ip6table_nat = NULL; } static struct pernet_operations ip6table_nat_net_ops = { + .pre_exit = ip6table_nat_net_pre_exit, .exit = ip6table_nat_net_exit, }; diff --git a/net/ipv6/netfilter/ip6table_raw.c b/net/ipv6/netfilter/ip6table_raw.c index a22100b1cf2c..8f9e742226f7 100644 --- a/net/ipv6/netfilter/ip6table_raw.c +++ b/net/ipv6/netfilter/ip6table_raw.c @@ -66,15 +66,23 @@ static int __net_init ip6table_raw_table_init(struct net *net) return ret; } +static void __net_exit ip6table_raw_net_pre_exit(struct net *net) +{ + if (net->ipv6.ip6table_raw) + ip6t_unregister_table_pre_exit(net, net->ipv6.ip6table_raw, + rawtable_ops); +} + static void __net_exit ip6table_raw_net_exit(struct net *net) { if (!net->ipv6.ip6table_raw) return; - ip6t_unregister_table(net, net->ipv6.ip6table_raw, rawtable_ops); + ip6t_unregister_table_exit(net, net->ipv6.ip6table_raw); net->ipv6.ip6table_raw = NULL; } static struct pernet_operations ip6table_raw_net_ops = { + .pre_exit = ip6table_raw_net_pre_exit, .exit = ip6table_raw_net_exit, }; diff --git a/net/ipv6/netfilter/ip6table_security.c b/net/ipv6/netfilter/ip6table_security.c index a74335fe2bd9..5e8c48fed032 100644 --- a/net/ipv6/netfilter/ip6table_security.c +++ b/net/ipv6/netfilter/ip6table_security.c @@ -61,15 +61,23 @@ static int __net_init ip6table_security_table_init(struct net *net) return ret; } +static void __net_exit ip6table_security_net_pre_exit(struct net *net) +{ + if (net->ipv6.ip6table_security) + ip6t_unregister_table_pre_exit(net, net->ipv6.ip6table_security, + sectbl_ops); +} + static void __net_exit ip6table_security_net_exit(struct net *net) { if (!net->ipv6.ip6table_security) return; - ip6t_unregister_table(net, net->ipv6.ip6table_security, sectbl_ops); + ip6t_unregister_table_exit(net, net->ipv6.ip6table_security); net->ipv6.ip6table_security = NULL; } static struct pernet_operations ip6table_security_net_ops = { + .pre_exit = ip6table_security_net_pre_exit, .exit = ip6table_security_net_exit, }; diff --git a/net/ipv6/netfilter/nf_flow_table_ipv6.c b/net/ipv6/netfilter/nf_flow_table_ipv6.c index a8566ee12e83..667b8af2546a 100644 --- a/net/ipv6/netfilter/nf_flow_table_ipv6.c +++ b/net/ipv6/netfilter/nf_flow_table_ipv6.c @@ -35,3 +35,4 @@ module_exit(nf_flow_ipv6_module_exit); MODULE_LICENSE("GPL"); MODULE_AUTHOR("Pablo Neira Ayuso <pablo@netfilter.org>"); MODULE_ALIAS_NF_FLOWTABLE(AF_INET6); +MODULE_DESCRIPTION("Netfilter flow table IPv6 module"); diff --git a/net/ipv6/netfilter/nft_dup_ipv6.c b/net/ipv6/netfilter/nft_dup_ipv6.c index 2af32200507d..8b5193efb1f1 100644 --- a/net/ipv6/netfilter/nft_dup_ipv6.c +++ b/net/ipv6/netfilter/nft_dup_ipv6.c @@ -105,3 +105,4 @@ module_exit(nft_dup_ipv6_module_exit); MODULE_LICENSE("GPL"); MODULE_AUTHOR("Pablo Neira Ayuso <pablo@netfilter.org>"); MODULE_ALIAS_NFT_AF_EXPR(AF_INET6, "dup"); +MODULE_DESCRIPTION("IPv6 nftables packet duplication support"); diff --git a/net/ipv6/netfilter/nft_fib_ipv6.c b/net/ipv6/netfilter/nft_fib_ipv6.c index 7ece86afd079..e204163c7036 100644 --- a/net/ipv6/netfilter/nft_fib_ipv6.c +++ b/net/ipv6/netfilter/nft_fib_ipv6.c @@ -255,3 +255,4 @@ module_exit(nft_fib6_module_exit); MODULE_LICENSE("GPL"); MODULE_AUTHOR("Florian Westphal <fw@strlen.de>"); MODULE_ALIAS_NFT_AF_EXPR(10, "fib"); +MODULE_DESCRIPTION("nftables fib / ipv6 route lookup support"); diff --git a/net/ipv6/netfilter/nft_reject_ipv6.c b/net/ipv6/netfilter/nft_reject_ipv6.c index 680a28ce29fd..c1098a1968e1 100644 --- a/net/ipv6/netfilter/nft_reject_ipv6.c +++ b/net/ipv6/netfilter/nft_reject_ipv6.c @@ -72,3 +72,4 @@ module_exit(nft_reject_ipv6_module_exit); MODULE_LICENSE("GPL"); MODULE_AUTHOR("Patrick McHardy <kaber@trash.net>"); MODULE_ALIAS_NFT_AF_EXPR(AF_INET6, "reject"); +MODULE_DESCRIPTION("IPv6 packet rejection for nftables"); diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 82cbb46a2a4f..f3279810d765 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -431,9 +431,12 @@ void fib6_select_path(const struct net *net, struct fib6_result *res, struct fib6_info *sibling, *next_sibling; struct fib6_info *match = res->f6i; - if ((!match->fib6_nsiblings && !match->nh) || have_oif_match) + if (!match->nh && (!match->fib6_nsiblings || have_oif_match)) goto out; + if (match->nh && have_oif_match && res->nh) + return; + /* We might have already computed the hash for ICMPv6 errors. In such * case it will always be non-zero. Otherwise now is the time to do it. */ @@ -3402,7 +3405,7 @@ static bool fib6_is_reject(u32 flags, struct net_device *dev, int addr_type) if ((flags & RTF_REJECT) || (dev && (dev->flags & IFF_LOOPBACK) && !(addr_type & IPV6_ADDR_LOOPBACK) && - !(flags & RTF_LOCAL))) + !(flags & (RTF_ANYCAST | RTF_LOCAL)))) return true; return false; diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c index 1fbb4dfbb191..5e2c34c0ac97 100644 --- a/net/ipv6/sit.c +++ b/net/ipv6/sit.c @@ -1421,6 +1421,7 @@ static void ipip6_tunnel_setup(struct net_device *dev) int t_hlen = tunnel->hlen + sizeof(struct iphdr); dev->netdev_ops = &ipip6_netdev_ops; + dev->header_ops = &ip_tunnel_header_ops; dev->needs_free_netdev = true; dev->priv_destructor = ipip6_dev_free; diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 7d4151747340..a8d74f44056a 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -148,7 +148,7 @@ static struct sock *udp6_lib_lookup2(struct net *net, int dif, int sdif, struct udp_hslot *hslot2, struct sk_buff *skb) { - struct sock *sk, *result; + struct sock *sk, *result, *reuseport_result; int score, badness; u32 hash = 0; @@ -158,17 +158,20 @@ static struct sock *udp6_lib_lookup2(struct net *net, score = compute_score(sk, net, saddr, sport, daddr, hnum, dif, sdif); if (score > badness) { + reuseport_result = NULL; + if (sk->sk_reuseport && sk->sk_state != TCP_ESTABLISHED) { hash = udp6_ehashfn(net, daddr, hnum, saddr, sport); - result = reuseport_select_sock(sk, hash, skb, - sizeof(struct udphdr)); - if (result && !reuseport_has_conns(sk, false)) - return result; + reuseport_result = reuseport_select_sock(sk, hash, skb, + sizeof(struct udphdr)); + if (reuseport_result && !reuseport_has_conns(sk, false)) + return reuseport_result; } - result = sk; + + result = reuseport_result ? : sk; badness = score; } } @@ -643,7 +646,7 @@ static int udpv6_queue_rcv_one_skb(struct sock *sk, struct sk_buff *skb) /* * UDP-Lite specific tests, ignored on UDP sockets (see net/ipv4/udp.c). */ - if ((is_udplite & UDPLITE_RECV_CC) && UDP_SKB_CB(skb)->partial_cov) { + if ((up->pcflag & UDPLITE_RECV_CC) && UDP_SKB_CB(skb)->partial_cov) { if (up->pcrlen == 0) { /* full coverage was set */ net_dbg_ratelimited("UDPLITE6: partial coverage %d while full coverage %d requested\n", diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c index 6d7ef78c88af..6434d17e6e8e 100644 --- a/net/l2tp/l2tp_core.c +++ b/net/l2tp/l2tp_core.c @@ -1028,6 +1028,7 @@ static void l2tp_xmit_core(struct l2tp_session *session, struct sk_buff *skb, /* Queue the packet to IP for output */ skb->ignore_df = 1; + skb_dst_drop(skb); #if IS_ENABLED(CONFIG_IPV6) if (l2tp_sk_is_v6(tunnel->sock)) error = inet6_csk_xmit(tunnel->sock, skb, NULL); @@ -1099,10 +1100,6 @@ int l2tp_xmit_skb(struct l2tp_session *session, struct sk_buff *skb, int hdr_len goto out_unlock; } - /* Get routing info from the tunnel socket */ - skb_dst_drop(skb); - skb_dst_set(skb, sk_dst_check(sk, 0)); - inet = inet_sk(sk); fl = &inet->cork.fl; switch (tunnel->encap) { diff --git a/net/llc/af_llc.c b/net/llc/af_llc.c index 54fb8d452a7b..6e53e43c1907 100644 --- a/net/llc/af_llc.c +++ b/net/llc/af_llc.c @@ -273,6 +273,10 @@ static int llc_ui_autobind(struct socket *sock, struct sockaddr_llc *addr) if (!sock_flag(sk, SOCK_ZAPPED)) goto out; + if (!addr->sllc_arphrd) + addr->sllc_arphrd = ARPHRD_ETHER; + if (addr->sllc_arphrd != ARPHRD_ETHER) + goto out; rc = -ENODEV; if (sk->sk_bound_dev_if) { llc->dev = dev_get_by_index(&init_net, sk->sk_bound_dev_if); @@ -328,7 +332,9 @@ static int llc_ui_bind(struct socket *sock, struct sockaddr *uaddr, int addrlen) if (unlikely(!sock_flag(sk, SOCK_ZAPPED) || addrlen != sizeof(*addr))) goto out; rc = -EAFNOSUPPORT; - if (unlikely(addr->sllc_family != AF_LLC)) + if (!addr->sllc_arphrd) + addr->sllc_arphrd = ARPHRD_ETHER; + if (unlikely(addr->sllc_family != AF_LLC || addr->sllc_arphrd != ARPHRD_ETHER)) goto out; dprintk("%s: binding %02X\n", __func__, addr->sllc_sap); rc = -ENODEV; @@ -336,8 +342,6 @@ static int llc_ui_bind(struct socket *sock, struct sockaddr *uaddr, int addrlen) if (sk->sk_bound_dev_if) { llc->dev = dev_get_by_index_rcu(&init_net, sk->sk_bound_dev_if); if (llc->dev) { - if (!addr->sllc_arphrd) - addr->sllc_arphrd = llc->dev->type; if (is_zero_ether_addr(addr->sllc_mac)) memcpy(addr->sllc_mac, llc->dev->dev_addr, IFHWADDRLEN); diff --git a/net/mac80211/mesh_hwmp.c b/net/mac80211/mesh_hwmp.c index aa5150929996..02cde0fd08fe 100644 --- a/net/mac80211/mesh_hwmp.c +++ b/net/mac80211/mesh_hwmp.c @@ -1105,11 +1105,8 @@ void mesh_path_start_discovery(struct ieee80211_sub_if_data *sdata) ttl, lifetime, 0, ifmsh->preq_id++, sdata); spin_lock_bh(&mpath->state_lock); - if (mpath->flags & MESH_PATH_DELETED) { - spin_unlock_bh(&mpath->state_lock); - goto enddiscovery; - } - mod_timer(&mpath->timer, jiffies + mpath->discovery_timeout); + if (!(mpath->flags & MESH_PATH_DELETED)) + mod_timer(&mpath->timer, jiffies + mpath->discovery_timeout); spin_unlock_bh(&mpath->state_lock); enddiscovery: diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c index a88ab6fb16f2..5c5af4b5fc08 100644 --- a/net/mac80211/rx.c +++ b/net/mac80211/rx.c @@ -2396,6 +2396,7 @@ static int ieee80211_802_1x_port_control(struct ieee80211_rx_data *rx) static int ieee80211_drop_unencrypted(struct ieee80211_rx_data *rx, __le16 fc) { + struct ieee80211_hdr *hdr = (void *)rx->skb->data; struct sk_buff *skb = rx->skb; struct ieee80211_rx_status *status = IEEE80211_SKB_RXCB(skb); @@ -2406,6 +2407,31 @@ static int ieee80211_drop_unencrypted(struct ieee80211_rx_data *rx, __le16 fc) if (status->flag & RX_FLAG_DECRYPTED) return 0; + /* check mesh EAPOL frames first */ + if (unlikely(rx->sta && ieee80211_vif_is_mesh(&rx->sdata->vif) && + ieee80211_is_data(fc))) { + struct ieee80211s_hdr *mesh_hdr; + u16 hdr_len = ieee80211_hdrlen(fc); + u16 ethertype_offset; + __be16 ethertype; + + if (!ether_addr_equal(hdr->addr1, rx->sdata->vif.addr)) + goto drop_check; + + /* make sure fixed part of mesh header is there, also checks skb len */ + if (!pskb_may_pull(rx->skb, hdr_len + 6)) + goto drop_check; + + mesh_hdr = (struct ieee80211s_hdr *)(skb->data + hdr_len); + ethertype_offset = hdr_len + ieee80211_get_mesh_hdrlen(mesh_hdr) + + sizeof(rfc1042_header); + + if (skb_copy_bits(rx->skb, ethertype_offset, ðertype, 2) == 0 && + ethertype == rx->sdata->control_port_protocol) + return 0; + } + +drop_check: /* Drop unencrypted frames if key is set. */ if (unlikely(!ieee80211_has_protected(fc) && !ieee80211_is_any_nullfunc(fc) && diff --git a/net/mac80211/status.c b/net/mac80211/status.c index 7b1bacac39c6..cbc40b358ba2 100644 --- a/net/mac80211/status.c +++ b/net/mac80211/status.c @@ -639,11 +639,23 @@ static void ieee80211_report_ack_skb(struct ieee80211_local *local, u64 cookie = IEEE80211_SKB_CB(skb)->ack.cookie; struct ieee80211_sub_if_data *sdata; struct ieee80211_hdr *hdr = (void *)skb->data; + __be16 ethertype = 0; + + if (skb->len >= ETH_HLEN && skb->protocol == cpu_to_be16(ETH_P_802_3)) + skb_copy_bits(skb, 2 * ETH_ALEN, ðertype, ETH_TLEN); rcu_read_lock(); sdata = ieee80211_sdata_from_skb(local, skb); if (sdata) { - if (ieee80211_is_any_nullfunc(hdr->frame_control)) + if (ethertype == sdata->control_port_protocol || + ethertype == cpu_to_be16(ETH_P_PREAUTH)) + cfg80211_control_port_tx_status(&sdata->wdev, + cookie, + skb->data, + skb->len, + acked, + GFP_ATOMIC); + else if (ieee80211_is_any_nullfunc(hdr->frame_control)) cfg80211_probe_status(sdata->dev, hdr->addr1, cookie, acked, info->status.ack_signal, @@ -654,12 +666,8 @@ static void ieee80211_report_ack_skb(struct ieee80211_local *local, skb->data, skb->len, acked, GFP_ATOMIC); else - cfg80211_control_port_tx_status(&sdata->wdev, - cookie, - skb->data, - skb->len, - acked, - GFP_ATOMIC); + pr_warn("Unknown status report in ack skb\n"); + } rcu_read_unlock(); diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c index e9ce658141f5..1a2941e5244f 100644 --- a/net/mac80211/tx.c +++ b/net/mac80211/tx.c @@ -3996,6 +3996,9 @@ void __ieee80211_subif_start_xmit(struct sk_buff *skb, skb_list_walk_safe(skb, skb, next) { skb_mark_not_on_list(skb); + if (skb->protocol == sdata->control_port_protocol) + ctrl_flags |= IEEE80211_TX_CTRL_SKIP_MPATH_LOOKUP; + skb = ieee80211_build_hdr(sdata, skb, info_flags, sta, ctrl_flags, cookie); if (IS_ERR(skb)) { @@ -4206,7 +4209,7 @@ static void ieee80211_8023_xmit(struct ieee80211_sub_if_data *sdata, (!sta || !test_sta_flag(sta, WLAN_STA_TDLS_PEER))) ra = sdata->u.mgd.bssid; - if (!is_valid_ether_addr(ra)) + if (is_zero_ether_addr(ra)) goto out_free; multicast = is_multicast_ether_addr(ra); @@ -5371,7 +5374,8 @@ int ieee80211_tx_control_port(struct wiphy *wiphy, struct net_device *dev, return -EINVAL; if (proto == sdata->control_port_protocol) - ctrl_flags |= IEEE80211_TX_CTRL_PORT_CTRL_PROTO; + ctrl_flags |= IEEE80211_TX_CTRL_PORT_CTRL_PROTO | + IEEE80211_TX_CTRL_SKIP_MPATH_LOOKUP; if (unencrypted) flags |= IEEE80211_TX_INTFL_DONT_ENCRYPT; diff --git a/net/mptcp/options.c b/net/mptcp/options.c index 490b92534afc..8f940be42f98 100644 --- a/net/mptcp/options.c +++ b/net/mptcp/options.c @@ -336,9 +336,7 @@ bool mptcp_syn_options(struct sock *sk, const struct sk_buff *skb, */ subflow->snd_isn = TCP_SKB_CB(skb)->end_seq; if (subflow->request_mptcp) { - pr_debug("local_key=%llu", subflow->local_key); opts->suboptions = OPTION_MPTCP_MPC_SYN; - opts->sndr_key = subflow->local_key; *size = TCPOLEN_MPTCP_MPC_SYN; return true; } else if (subflow->request_join) { @@ -451,9 +449,9 @@ static bool mptcp_established_options_mp(struct sock *sk, struct sk_buff *skb, } static void mptcp_write_data_fin(struct mptcp_subflow_context *subflow, - struct mptcp_ext *ext) + struct sk_buff *skb, struct mptcp_ext *ext) { - if (!ext->use_map) { + if (!ext->use_map || !skb->len) { /* RFC6824 requires a DSS mapping with specific values * if DATA_FIN is set but no data payload is mapped */ @@ -505,7 +503,7 @@ static bool mptcp_established_options_dss(struct sock *sk, struct sk_buff *skb, opts->ext_copy = *mpext; if (skb && tcp_fin && subflow->data_fin_tx_enable) - mptcp_write_data_fin(subflow, &opts->ext_copy); + mptcp_write_data_fin(subflow, skb, &opts->ext_copy); ret = true; } diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h index 809687d3f410..c6eeaf3e8dcb 100644 --- a/net/mptcp/protocol.h +++ b/net/mptcp/protocol.h @@ -135,8 +135,6 @@ static inline __be32 mptcp_option(u8 subopt, u8 len, u8 nib, u8 field) ((nib & 0xF) << 8) | field); } -#define MPTCP_PM_MAX_ADDR 4 - struct mptcp_addr_info { sa_family_t family; __be16 port; @@ -234,10 +232,7 @@ static inline struct mptcp_data_frag *mptcp_rtx_head(const struct sock *sk) { struct mptcp_sock *msk = mptcp_sk(sk); - if (list_empty(&msk->rtx_queue)) - return NULL; - - return list_first_entry(&msk->rtx_queue, struct mptcp_data_frag, list); + return list_first_entry_or_null(&msk->rtx_queue, struct mptcp_data_frag, list); } struct mptcp_subflow_request_sock { @@ -254,6 +249,7 @@ struct mptcp_subflow_request_sock { u64 thmac; u32 local_nonce; u32 remote_nonce; + struct mptcp_sock *msk; }; static inline struct mptcp_subflow_request_sock * diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c index bf132575040d..3838a0b3a21f 100644 --- a/net/mptcp/subflow.c +++ b/net/mptcp/subflow.c @@ -69,6 +69,9 @@ static void subflow_req_destructor(struct request_sock *req) pr_debug("subflow_req=%p", subflow_req); + if (subflow_req->msk) + sock_put((struct sock *)subflow_req->msk); + if (subflow_req->mp_capable) mptcp_token_destroy_request(subflow_req->token); tcp_request_sock_ops.destructor(req); @@ -86,8 +89,8 @@ static void subflow_generate_hmac(u64 key1, u64 key2, u32 nonce1, u32 nonce2, } /* validate received token and create truncated hmac and nonce for SYN-ACK */ -static bool subflow_token_join_request(struct request_sock *req, - const struct sk_buff *skb) +static struct mptcp_sock *subflow_token_join_request(struct request_sock *req, + const struct sk_buff *skb) { struct mptcp_subflow_request_sock *subflow_req = mptcp_subflow_rsk(req); u8 hmac[SHA256_DIGEST_SIZE]; @@ -97,13 +100,13 @@ static bool subflow_token_join_request(struct request_sock *req, msk = mptcp_token_get_sock(subflow_req->token); if (!msk) { SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_JOINNOTOKEN); - return false; + return NULL; } local_id = mptcp_pm_get_local_id(msk, (struct sock_common *)req); if (local_id < 0) { sock_put((struct sock *)msk); - return false; + return NULL; } subflow_req->local_id = local_id; @@ -114,9 +117,7 @@ static bool subflow_token_join_request(struct request_sock *req, subflow_req->remote_nonce, hmac); subflow_req->thmac = get_unaligned_be64(hmac); - - sock_put((struct sock *)msk); - return true; + return msk; } static void subflow_init_req(struct request_sock *req, @@ -133,6 +134,7 @@ static void subflow_init_req(struct request_sock *req, subflow_req->mp_capable = 0; subflow_req->mp_join = 0; + subflow_req->msk = NULL; #ifdef CONFIG_TCP_MD5SIG /* no MPTCP if MD5SIG is enabled on this socket or we may run out of @@ -166,12 +168,9 @@ static void subflow_init_req(struct request_sock *req, subflow_req->remote_id = mp_opt.join_id; subflow_req->token = mp_opt.token; subflow_req->remote_nonce = mp_opt.nonce; - pr_debug("token=%u, remote_nonce=%u", subflow_req->token, - subflow_req->remote_nonce); - if (!subflow_token_join_request(req, skb)) { - subflow_req->mp_join = 0; - // @@ need to trigger RST - } + subflow_req->msk = subflow_token_join_request(req, skb); + pr_debug("token=%u, remote_nonce=%u msk=%p", subflow_req->token, + subflow_req->remote_nonce, subflow_req->msk); } } @@ -354,10 +353,9 @@ static bool subflow_hmac_valid(const struct request_sock *req, const struct mptcp_subflow_request_sock *subflow_req; u8 hmac[SHA256_DIGEST_SIZE]; struct mptcp_sock *msk; - bool ret; subflow_req = mptcp_subflow_rsk(req); - msk = mptcp_token_get_sock(subflow_req->token); + msk = subflow_req->msk; if (!msk) return false; @@ -365,12 +363,7 @@ static bool subflow_hmac_valid(const struct request_sock *req, subflow_req->remote_nonce, subflow_req->local_nonce, hmac); - ret = true; - if (crypto_memneq(hmac, mp_opt->hmac, MPTCPOPT_HMAC_LEN)) - ret = false; - - sock_put((struct sock *)msk); - return ret; + return !crypto_memneq(hmac, mp_opt->hmac, MPTCPOPT_HMAC_LEN); } static void mptcp_sock_destruct(struct sock *sk) @@ -438,22 +431,25 @@ static struct sock *subflow_syn_recv_sock(const struct sock *sk, struct mptcp_subflow_context *listener = mptcp_subflow_ctx(sk); struct mptcp_subflow_request_sock *subflow_req; struct mptcp_options_received mp_opt; - bool fallback_is_fatal = false; + bool fallback, fallback_is_fatal; struct sock *new_msk = NULL; - bool fallback = false; struct sock *child; pr_debug("listener=%p, req=%p, conn=%p", listener, req, listener->conn); - /* we need later a valid 'mp_capable' value even when options are not - * parsed + /* After child creation we must look for 'mp_capable' even when options + * are not parsed */ mp_opt.mp_capable = 0; - if (tcp_rsk(req)->is_mptcp == 0) + + /* hopefully temporary handling for MP_JOIN+syncookie */ + subflow_req = mptcp_subflow_rsk(req); + fallback_is_fatal = subflow_req->mp_join; + fallback = !tcp_rsk(req)->is_mptcp; + if (fallback) goto create_child; /* if the sk is MP_CAPABLE, we try to fetch the client key */ - subflow_req = mptcp_subflow_rsk(req); if (subflow_req->mp_capable) { if (TCP_SKB_CB(skb)->seq != subflow_req->ssn_offset + 1) { /* here we can receive and accept an in-window, @@ -474,12 +470,11 @@ create_msk: if (!new_msk) fallback = true; } else if (subflow_req->mp_join) { - fallback_is_fatal = true; mptcp_get_options(skb, &mp_opt); if (!mp_opt.mp_join || !subflow_hmac_valid(req, &mp_opt)) { SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_JOINACKMAC); - return NULL; + fallback = true; } } @@ -522,10 +517,12 @@ create_child: } else if (ctx->mp_join) { struct mptcp_sock *owner; - owner = mptcp_token_get_sock(ctx->token); + owner = subflow_req->msk; if (!owner) goto dispose_child; + /* move the msk reference ownership to the subflow */ + subflow_req->msk = NULL; ctx->conn = (struct sock *)owner; if (!mptcp_finish_join(child)) goto dispose_child; @@ -1053,8 +1050,10 @@ int mptcp_subflow_create_socket(struct sock *sk, struct socket **new_sock) err = tcp_set_ulp(sf->sk, "mptcp"); release_sock(sf->sk); - if (err) + if (err) { + sock_release(sf); return err; + } /* the newly created socket really belongs to the owning MPTCP master * socket, even if for additional subflows the allocation is performed diff --git a/net/netfilter/ipset/ip_set_bitmap_ip.c b/net/netfilter/ipset/ip_set_bitmap_ip.c index 486959f70cf3..a8ce04a4bb72 100644 --- a/net/netfilter/ipset/ip_set_bitmap_ip.c +++ b/net/netfilter/ipset/ip_set_bitmap_ip.c @@ -326,7 +326,7 @@ bitmap_ip_create(struct net *net, struct ip_set *set, struct nlattr *tb[], set->variant = &bitmap_ip; if (!init_map_ip(set, map, first_ip, last_ip, elements, hosts, netmask)) { - kfree(map); + ip_set_free(map); return -ENOMEM; } if (tb[IPSET_ATTR_TIMEOUT]) { diff --git a/net/netfilter/ipset/ip_set_bitmap_ipmac.c b/net/netfilter/ipset/ip_set_bitmap_ipmac.c index 2310a316e0af..2c625e0f49ec 100644 --- a/net/netfilter/ipset/ip_set_bitmap_ipmac.c +++ b/net/netfilter/ipset/ip_set_bitmap_ipmac.c @@ -363,7 +363,7 @@ bitmap_ipmac_create(struct net *net, struct ip_set *set, struct nlattr *tb[], map->memsize = BITS_TO_LONGS(elements) * sizeof(unsigned long); set->variant = &bitmap_ipmac; if (!init_map_ipmac(set, map, first_ip, last_ip, elements)) { - kfree(map); + ip_set_free(map); return -ENOMEM; } if (tb[IPSET_ATTR_TIMEOUT]) { diff --git a/net/netfilter/ipset/ip_set_bitmap_port.c b/net/netfilter/ipset/ip_set_bitmap_port.c index e56ced66f202..7138e080def4 100644 --- a/net/netfilter/ipset/ip_set_bitmap_port.c +++ b/net/netfilter/ipset/ip_set_bitmap_port.c @@ -274,7 +274,7 @@ bitmap_port_create(struct net *net, struct ip_set *set, struct nlattr *tb[], map->memsize = BITS_TO_LONGS(elements) * sizeof(unsigned long); set->variant = &bitmap_port; if (!init_map_port(set, map, first_port, last_port)) { - kfree(map); + ip_set_free(map); return -ENOMEM; } if (tb[IPSET_ATTR_TIMEOUT]) { diff --git a/net/netfilter/ipset/ip_set_core.c b/net/netfilter/ipset/ip_set_core.c index 340cb955af25..56621d6bfd29 100644 --- a/net/netfilter/ipset/ip_set_core.c +++ b/net/netfilter/ipset/ip_set_core.c @@ -460,6 +460,8 @@ ip_set_elem_len(struct ip_set *set, struct nlattr *tb[], size_t len, for (id = 0; id < IPSET_EXT_ID_MAX; id++) { if (!add_extension(id, cadt_flags, tb)) continue; + if (align < ip_set_extensions[id].align) + align = ip_set_extensions[id].align; len = ALIGN(len, ip_set_extensions[id].align); set->offset[id] = len; set->extensions |= ip_set_extensions[id].type; diff --git a/net/netfilter/ipset/ip_set_hash_gen.h b/net/netfilter/ipset/ip_set_hash_gen.h index 1ee43752d6d3..521e970be402 100644 --- a/net/netfilter/ipset/ip_set_hash_gen.h +++ b/net/netfilter/ipset/ip_set_hash_gen.h @@ -682,7 +682,7 @@ retry: } t->hregion = ip_set_alloc(ahash_sizeof_regions(htable_bits)); if (!t->hregion) { - kfree(t); + ip_set_free(t); ret = -ENOMEM; goto out; } @@ -1533,7 +1533,7 @@ IPSET_TOKEN(HTYPE, _create)(struct net *net, struct ip_set *set, } t->hregion = ip_set_alloc(ahash_sizeof_regions(hbits)); if (!t->hregion) { - kfree(t); + ip_set_free(t); kfree(h); return -ENOMEM; } diff --git a/net/netfilter/ipvs/ip_vs_sync.c b/net/netfilter/ipvs/ip_vs_sync.c index 605e0f68f8bd..2b8abbfe018c 100644 --- a/net/netfilter/ipvs/ip_vs_sync.c +++ b/net/netfilter/ipvs/ip_vs_sync.c @@ -1717,6 +1717,8 @@ static int sync_thread_backup(void *data) { struct ip_vs_sync_thread_data *tinfo = data; struct netns_ipvs *ipvs = tinfo->ipvs; + struct sock *sk = tinfo->sock->sk; + struct udp_sock *up = udp_sk(sk); int len; pr_info("sync thread started: state = BACKUP, mcast_ifn = %s, " @@ -1724,12 +1726,14 @@ static int sync_thread_backup(void *data) ipvs->bcfg.mcast_ifn, ipvs->bcfg.syncid, tinfo->id); while (!kthread_should_stop()) { - wait_event_interruptible(*sk_sleep(tinfo->sock->sk), - !skb_queue_empty(&tinfo->sock->sk->sk_receive_queue) - || kthread_should_stop()); + wait_event_interruptible(*sk_sleep(sk), + !skb_queue_empty_lockless(&sk->sk_receive_queue) || + !skb_queue_empty_lockless(&up->reader_queue) || + kthread_should_stop()); /* do we have data now? */ - while (!skb_queue_empty(&(tinfo->sock->sk->sk_receive_queue))) { + while (!skb_queue_empty_lockless(&sk->sk_receive_queue) || + !skb_queue_empty_lockless(&up->reader_queue)) { len = ip_vs_receive(tinfo->sock, tinfo->buf, ipvs->bcfg.sync_maxlen); if (len <= 0) { diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index 79cd9dde457b..f33d72c5b06e 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -2158,6 +2158,8 @@ static int nf_conntrack_update(struct net *net, struct sk_buff *skb) err = __nf_conntrack_update(net, skb, ct, ctinfo); if (err < 0) return err; + + ct = nf_ct_get(skb, &ctinfo); } return nf_confirm_cthelper(skb, ct, ctinfo); diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c index d7bd8b1f27d5..832eabecfbdd 100644 --- a/net/netfilter/nf_conntrack_netlink.c +++ b/net/netfilter/nf_conntrack_netlink.c @@ -939,7 +939,8 @@ ctnetlink_alloc_filter(const struct nlattr * const cda[], u8 family) filter->mark.mask = 0xffffffff; } } else if (cda[CTA_MARK_MASK]) { - return ERR_PTR(-EINVAL); + err = -EINVAL; + goto err_filter; } #endif if (!cda[CTA_FILTER]) @@ -947,15 +948,17 @@ ctnetlink_alloc_filter(const struct nlattr * const cda[], u8 family) err = ctnetlink_parse_zone(cda[CTA_ZONE], &filter->zone); if (err < 0) - return ERR_PTR(err); + goto err_filter; err = ctnetlink_parse_filter(cda[CTA_FILTER], filter); if (err < 0) - return ERR_PTR(err); + goto err_filter; if (filter->orig_flags) { - if (!cda[CTA_TUPLE_ORIG]) - return ERR_PTR(-EINVAL); + if (!cda[CTA_TUPLE_ORIG]) { + err = -EINVAL; + goto err_filter; + } err = ctnetlink_parse_tuple_filter(cda, &filter->orig, CTA_TUPLE_ORIG, @@ -963,23 +966,32 @@ ctnetlink_alloc_filter(const struct nlattr * const cda[], u8 family) &filter->zone, filter->orig_flags); if (err < 0) - return ERR_PTR(err); + goto err_filter; } if (filter->reply_flags) { - if (!cda[CTA_TUPLE_REPLY]) - return ERR_PTR(-EINVAL); + if (!cda[CTA_TUPLE_REPLY]) { + err = -EINVAL; + goto err_filter; + } err = ctnetlink_parse_tuple_filter(cda, &filter->reply, CTA_TUPLE_REPLY, filter->family, &filter->zone, filter->orig_flags); - if (err < 0) - return ERR_PTR(err); + if (err < 0) { + err = -EINVAL; + goto err_filter; + } } return filter; + +err_filter: + kfree(filter); + + return ERR_PTR(err); } static bool ctnetlink_needs_filter(u8 family, const struct nlattr * const *cda) diff --git a/net/netfilter/nf_dup_netdev.c b/net/netfilter/nf_dup_netdev.c index f108a76925dd..2b01a151eaa8 100644 --- a/net/netfilter/nf_dup_netdev.c +++ b/net/netfilter/nf_dup_netdev.c @@ -73,3 +73,4 @@ EXPORT_SYMBOL_GPL(nft_fwd_dup_netdev_offload); MODULE_LICENSE("GPL"); MODULE_AUTHOR("Pablo Neira Ayuso <pablo@netfilter.org>"); +MODULE_DESCRIPTION("Netfilter packet duplication support"); diff --git a/net/netfilter/nf_flow_table_core.c b/net/netfilter/nf_flow_table_core.c index 6a3034f84ab6..b1eb5272b379 100644 --- a/net/netfilter/nf_flow_table_core.c +++ b/net/netfilter/nf_flow_table_core.c @@ -387,51 +387,6 @@ static void nf_flow_offload_work_gc(struct work_struct *work) queue_delayed_work(system_power_efficient_wq, &flow_table->gc_work, HZ); } -int nf_flow_table_offload_add_cb(struct nf_flowtable *flow_table, - flow_setup_cb_t *cb, void *cb_priv) -{ - struct flow_block *block = &flow_table->flow_block; - struct flow_block_cb *block_cb; - int err = 0; - - down_write(&flow_table->flow_block_lock); - block_cb = flow_block_cb_lookup(block, cb, cb_priv); - if (block_cb) { - err = -EEXIST; - goto unlock; - } - - block_cb = flow_block_cb_alloc(cb, cb_priv, cb_priv, NULL); - if (IS_ERR(block_cb)) { - err = PTR_ERR(block_cb); - goto unlock; - } - - list_add_tail(&block_cb->list, &block->cb_list); - -unlock: - up_write(&flow_table->flow_block_lock); - return err; -} -EXPORT_SYMBOL_GPL(nf_flow_table_offload_add_cb); - -void nf_flow_table_offload_del_cb(struct nf_flowtable *flow_table, - flow_setup_cb_t *cb, void *cb_priv) -{ - struct flow_block *block = &flow_table->flow_block; - struct flow_block_cb *block_cb; - - down_write(&flow_table->flow_block_lock); - block_cb = flow_block_cb_lookup(block, cb, cb_priv); - if (block_cb) { - list_del(&block_cb->list); - flow_block_cb_free(block_cb); - } else { - WARN_ON(true); - } - up_write(&flow_table->flow_block_lock); -} -EXPORT_SYMBOL_GPL(nf_flow_table_offload_del_cb); static int nf_flow_nat_port_tcp(struct sk_buff *skb, unsigned int thoff, __be16 port, __be16 new_port) @@ -639,3 +594,4 @@ module_exit(nf_flow_table_module_exit); MODULE_LICENSE("GPL"); MODULE_AUTHOR("Pablo Neira Ayuso <pablo@netfilter.org>"); +MODULE_DESCRIPTION("Netfilter flow table module"); diff --git a/net/netfilter/nf_flow_table_inet.c b/net/netfilter/nf_flow_table_inet.c index 88bedf1ff1ae..bc4126d8ef65 100644 --- a/net/netfilter/nf_flow_table_inet.c +++ b/net/netfilter/nf_flow_table_inet.c @@ -72,3 +72,4 @@ module_exit(nf_flow_inet_module_exit); MODULE_LICENSE("GPL"); MODULE_AUTHOR("Pablo Neira Ayuso <pablo@netfilter.org>"); MODULE_ALIAS_NF_FLOWTABLE(1); /* NFPROTO_INET */ +MODULE_DESCRIPTION("Netfilter flow table mixed IPv4/IPv6 module"); diff --git a/net/netfilter/nf_flow_table_offload.c b/net/netfilter/nf_flow_table_offload.c index 62651e6683f6..5fff1e040168 100644 --- a/net/netfilter/nf_flow_table_offload.c +++ b/net/netfilter/nf_flow_table_offload.c @@ -950,6 +950,7 @@ static void nf_flow_table_indr_cleanup(struct flow_block_cb *block_cb) nf_flow_table_gc_cleanup(flowtable, dev); down_write(&flowtable->flow_block_lock); list_del(&block_cb->list); + list_del(&block_cb->driver_list); flow_block_cb_free(block_cb); up_write(&flowtable->flow_block_lock); } diff --git a/net/netfilter/nf_synproxy_core.c b/net/netfilter/nf_synproxy_core.c index b9cbe1e2453e..ebcdc8e54476 100644 --- a/net/netfilter/nf_synproxy_core.c +++ b/net/netfilter/nf_synproxy_core.c @@ -1237,3 +1237,4 @@ EXPORT_SYMBOL_GPL(nf_synproxy_ipv6_fini); MODULE_LICENSE("GPL"); MODULE_AUTHOR("Patrick McHardy <kaber@trash.net>"); +MODULE_DESCRIPTION("nftables SYNPROXY expression support"); diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 073aa1051d43..88325b264737 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -188,24 +188,6 @@ static void nft_netdev_unregister_hooks(struct net *net, nf_unregister_net_hook(net, &hook->ops); } -static int nft_register_basechain_hooks(struct net *net, int family, - struct nft_base_chain *basechain) -{ - if (family == NFPROTO_NETDEV) - return nft_netdev_register_hooks(net, &basechain->hook_list); - - return nf_register_net_hook(net, &basechain->ops); -} - -static void nft_unregister_basechain_hooks(struct net *net, int family, - struct nft_base_chain *basechain) -{ - if (family == NFPROTO_NETDEV) - nft_netdev_unregister_hooks(net, &basechain->hook_list); - else - nf_unregister_net_hook(net, &basechain->ops); -} - static int nf_tables_register_hook(struct net *net, const struct nft_table *table, struct nft_chain *chain) @@ -223,7 +205,10 @@ static int nf_tables_register_hook(struct net *net, if (basechain->type->ops_register) return basechain->type->ops_register(net, ops); - return nft_register_basechain_hooks(net, table->family, basechain); + if (table->family == NFPROTO_NETDEV) + return nft_netdev_register_hooks(net, &basechain->hook_list); + + return nf_register_net_hook(net, &basechain->ops); } static void nf_tables_unregister_hook(struct net *net, @@ -242,7 +227,10 @@ static void nf_tables_unregister_hook(struct net *net, if (basechain->type->ops_unregister) return basechain->type->ops_unregister(net, ops); - nft_unregister_basechain_hooks(net, table->family, basechain); + if (table->family == NFPROTO_NETDEV) + nft_netdev_unregister_hooks(net, &basechain->hook_list); + else + nf_unregister_net_hook(net, &basechain->ops); } static int nft_trans_table_add(struct nft_ctx *ctx, int msg_type) @@ -832,8 +820,7 @@ static void nft_table_disable(struct net *net, struct nft_table *table, u32 cnt) if (cnt && i++ == cnt) break; - nft_unregister_basechain_hooks(net, table->family, - nft_base_chain(chain)); + nf_tables_unregister_hook(net, table, chain); } } @@ -848,8 +835,7 @@ static int nf_tables_table_enable(struct net *net, struct nft_table *table) if (!nft_is_base_chain(chain)) continue; - err = nft_register_basechain_hooks(net, table->family, - nft_base_chain(chain)); + err = nf_tables_register_hook(net, table, chain); if (err < 0) goto err_register_hooks; @@ -894,11 +880,12 @@ static int nf_tables_updtable(struct nft_ctx *ctx) nft_trans_table_enable(trans) = false; } else if (!(flags & NFT_TABLE_F_DORMANT) && ctx->table->flags & NFT_TABLE_F_DORMANT) { + ctx->table->flags &= ~NFT_TABLE_F_DORMANT; ret = nf_tables_table_enable(ctx->net, ctx->table); - if (ret >= 0) { - ctx->table->flags &= ~NFT_TABLE_F_DORMANT; + if (ret >= 0) nft_trans_table_enable(trans) = true; - } + else + ctx->table->flags |= NFT_TABLE_F_DORMANT; } if (ret < 0) goto err; @@ -6550,12 +6537,22 @@ err1: return err; } +static void nft_flowtable_hook_release(struct nft_flowtable_hook *flowtable_hook) +{ + struct nft_hook *this, *next; + + list_for_each_entry_safe(this, next, &flowtable_hook->list, list) { + list_del(&this->list); + kfree(this); + } +} + static int nft_delflowtable_hook(struct nft_ctx *ctx, struct nft_flowtable *flowtable) { const struct nlattr * const *nla = ctx->nla; struct nft_flowtable_hook flowtable_hook; - struct nft_hook *this, *next, *hook; + struct nft_hook *this, *hook; struct nft_trans *trans; int err; @@ -6564,33 +6561,40 @@ static int nft_delflowtable_hook(struct nft_ctx *ctx, if (err < 0) return err; - list_for_each_entry_safe(this, next, &flowtable_hook.list, list) { + list_for_each_entry(this, &flowtable_hook.list, list) { hook = nft_hook_list_find(&flowtable->hook_list, this); if (!hook) { err = -ENOENT; goto err_flowtable_del_hook; } hook->inactive = true; - list_del(&this->list); - kfree(this); } trans = nft_trans_alloc(ctx, NFT_MSG_DELFLOWTABLE, sizeof(struct nft_trans_flowtable)); - if (!trans) - return -ENOMEM; + if (!trans) { + err = -ENOMEM; + goto err_flowtable_del_hook; + } nft_trans_flowtable(trans) = flowtable; nft_trans_flowtable_update(trans) = true; INIT_LIST_HEAD(&nft_trans_flowtable_hooks(trans)); + nft_flowtable_hook_release(&flowtable_hook); list_add_tail(&trans->list, &ctx->net->nft.commit_list); return 0; err_flowtable_del_hook: - list_for_each_entry(hook, &flowtable_hook.list, list) + list_for_each_entry(this, &flowtable_hook.list, list) { + hook = nft_hook_list_find(&flowtable->hook_list, this); + if (!hook) + break; + hook->inactive = false; + } + nft_flowtable_hook_release(&flowtable_hook); return err; } diff --git a/net/netfilter/nf_tables_offload.c b/net/netfilter/nf_tables_offload.c index 185fc82c99aa..c7cf1cde46de 100644 --- a/net/netfilter/nf_tables_offload.c +++ b/net/netfilter/nf_tables_offload.c @@ -296,6 +296,7 @@ static void nft_indr_block_cleanup(struct flow_block_cb *block_cb) nft_flow_block_offload_init(&bo, dev_net(dev), FLOW_BLOCK_UNBIND, basechain, &extack); mutex_lock(&net->nft.commit_mutex); + list_del(&block_cb->driver_list); list_move(&block_cb->list, &bo.cb_list); nft_flow_offload_unbind(&bo, basechain); mutex_unlock(&net->nft.commit_mutex); diff --git a/net/netfilter/nfnetlink.c b/net/netfilter/nfnetlink.c index 99127e2d95a8..5f24edf95830 100644 --- a/net/netfilter/nfnetlink.c +++ b/net/netfilter/nfnetlink.c @@ -33,6 +33,7 @@ MODULE_LICENSE("GPL"); MODULE_AUTHOR("Harald Welte <laforge@netfilter.org>"); MODULE_ALIAS_NET_PF_PROTO(PF_NETLINK, NETLINK_NETFILTER); +MODULE_DESCRIPTION("Netfilter messages via netlink socket"); #define nfnl_dereference_protected(id) \ rcu_dereference_protected(table[(id)].subsys, \ diff --git a/net/netfilter/nft_compat.c b/net/netfilter/nft_compat.c index f9adca62ccb3..aa1a066cb74b 100644 --- a/net/netfilter/nft_compat.c +++ b/net/netfilter/nft_compat.c @@ -902,3 +902,4 @@ MODULE_LICENSE("GPL"); MODULE_AUTHOR("Pablo Neira Ayuso <pablo@netfilter.org>"); MODULE_ALIAS_NFT_EXPR("match"); MODULE_ALIAS_NFT_EXPR("target"); +MODULE_DESCRIPTION("x_tables over nftables support"); diff --git a/net/netfilter/nft_connlimit.c b/net/netfilter/nft_connlimit.c index 69d6173f91e2..7d0761fad37e 100644 --- a/net/netfilter/nft_connlimit.c +++ b/net/netfilter/nft_connlimit.c @@ -280,3 +280,4 @@ MODULE_LICENSE("GPL"); MODULE_AUTHOR("Pablo Neira Ayuso"); MODULE_ALIAS_NFT_EXPR("connlimit"); MODULE_ALIAS_NFT_OBJ(NFT_OBJECT_CONNLIMIT); +MODULE_DESCRIPTION("nftables connlimit rule support"); diff --git a/net/netfilter/nft_counter.c b/net/netfilter/nft_counter.c index f6d4d0fa23a6..85ed461ec24e 100644 --- a/net/netfilter/nft_counter.c +++ b/net/netfilter/nft_counter.c @@ -303,3 +303,4 @@ MODULE_LICENSE("GPL"); MODULE_AUTHOR("Patrick McHardy <kaber@trash.net>"); MODULE_ALIAS_NFT_EXPR("counter"); MODULE_ALIAS_NFT_OBJ(NFT_OBJECT_COUNTER); +MODULE_DESCRIPTION("nftables counter rule support"); diff --git a/net/netfilter/nft_ct.c b/net/netfilter/nft_ct.c index faea72c2df32..77258af1fce0 100644 --- a/net/netfilter/nft_ct.c +++ b/net/netfilter/nft_ct.c @@ -1345,3 +1345,4 @@ MODULE_ALIAS_NFT_EXPR("notrack"); MODULE_ALIAS_NFT_OBJ(NFT_OBJECT_CT_HELPER); MODULE_ALIAS_NFT_OBJ(NFT_OBJECT_CT_TIMEOUT); MODULE_ALIAS_NFT_OBJ(NFT_OBJECT_CT_EXPECT); +MODULE_DESCRIPTION("Netfilter nf_tables conntrack module"); diff --git a/net/netfilter/nft_dup_netdev.c b/net/netfilter/nft_dup_netdev.c index c2e78c160fd7..40788b3f1071 100644 --- a/net/netfilter/nft_dup_netdev.c +++ b/net/netfilter/nft_dup_netdev.c @@ -102,3 +102,4 @@ module_exit(nft_dup_netdev_module_exit); MODULE_LICENSE("GPL"); MODULE_AUTHOR("Pablo Neira Ayuso <pablo@netfilter.org>"); MODULE_ALIAS_NFT_AF_EXPR(5, "dup"); +MODULE_DESCRIPTION("nftables netdev packet duplication support"); diff --git a/net/netfilter/nft_fib_inet.c b/net/netfilter/nft_fib_inet.c index 465432e0531b..a88d44e163d1 100644 --- a/net/netfilter/nft_fib_inet.c +++ b/net/netfilter/nft_fib_inet.c @@ -76,3 +76,4 @@ module_exit(nft_fib_inet_module_exit); MODULE_LICENSE("GPL"); MODULE_AUTHOR("Florian Westphal <fw@strlen.de>"); MODULE_ALIAS_NFT_AF_EXPR(1, "fib"); +MODULE_DESCRIPTION("nftables fib inet support"); diff --git a/net/netfilter/nft_fib_netdev.c b/net/netfilter/nft_fib_netdev.c index a2e726ae7f07..3f3478abd845 100644 --- a/net/netfilter/nft_fib_netdev.c +++ b/net/netfilter/nft_fib_netdev.c @@ -85,3 +85,4 @@ module_exit(nft_fib_netdev_module_exit); MODULE_LICENSE("GPL"); MODULE_AUTHOR("Pablo M. Bermudo Garay <pablombg@gmail.com>"); MODULE_ALIAS_NFT_AF_EXPR(5, "fib"); +MODULE_DESCRIPTION("nftables netdev fib lookups support"); diff --git a/net/netfilter/nft_flow_offload.c b/net/netfilter/nft_flow_offload.c index b70b48996801..3b9b97aa4b32 100644 --- a/net/netfilter/nft_flow_offload.c +++ b/net/netfilter/nft_flow_offload.c @@ -286,3 +286,4 @@ module_exit(nft_flow_offload_module_exit); MODULE_LICENSE("GPL"); MODULE_AUTHOR("Pablo Neira Ayuso <pablo@netfilter.org>"); MODULE_ALIAS_NFT_EXPR("flow_offload"); +MODULE_DESCRIPTION("nftables hardware flow offload module"); diff --git a/net/netfilter/nft_hash.c b/net/netfilter/nft_hash.c index b836d550b919..96371d878e7e 100644 --- a/net/netfilter/nft_hash.c +++ b/net/netfilter/nft_hash.c @@ -248,3 +248,4 @@ module_exit(nft_hash_module_exit); MODULE_LICENSE("GPL"); MODULE_AUTHOR("Laura Garcia <nevola@gmail.com>"); MODULE_ALIAS_NFT_EXPR("hash"); +MODULE_DESCRIPTION("Netfilter nftables hash module"); diff --git a/net/netfilter/nft_limit.c b/net/netfilter/nft_limit.c index 35b67d7e3694..0e2c315c3b5e 100644 --- a/net/netfilter/nft_limit.c +++ b/net/netfilter/nft_limit.c @@ -372,3 +372,4 @@ MODULE_LICENSE("GPL"); MODULE_AUTHOR("Patrick McHardy <kaber@trash.net>"); MODULE_ALIAS_NFT_EXPR("limit"); MODULE_ALIAS_NFT_OBJ(NFT_OBJECT_LIMIT); +MODULE_DESCRIPTION("nftables limit expression support"); diff --git a/net/netfilter/nft_log.c b/net/netfilter/nft_log.c index fe4831f2258f..57899454a530 100644 --- a/net/netfilter/nft_log.c +++ b/net/netfilter/nft_log.c @@ -298,3 +298,4 @@ module_exit(nft_log_module_exit); MODULE_LICENSE("GPL"); MODULE_AUTHOR("Patrick McHardy <kaber@trash.net>"); MODULE_ALIAS_NFT_EXPR("log"); +MODULE_DESCRIPTION("Netfilter nf_tables log module"); diff --git a/net/netfilter/nft_masq.c b/net/netfilter/nft_masq.c index bc9fd98c5d6d..71390b727040 100644 --- a/net/netfilter/nft_masq.c +++ b/net/netfilter/nft_masq.c @@ -305,3 +305,4 @@ module_exit(nft_masq_module_exit); MODULE_LICENSE("GPL"); MODULE_AUTHOR("Arturo Borrero Gonzalez <arturo@debian.org>"); MODULE_ALIAS_NFT_EXPR("masq"); +MODULE_DESCRIPTION("Netfilter nftables masquerade expression support"); diff --git a/net/netfilter/nft_nat.c b/net/netfilter/nft_nat.c index 23a7bfd10521..4bcf33b049c4 100644 --- a/net/netfilter/nft_nat.c +++ b/net/netfilter/nft_nat.c @@ -402,3 +402,4 @@ module_exit(nft_nat_module_exit); MODULE_LICENSE("GPL"); MODULE_AUTHOR("Tomasz Bursztyka <tomasz.bursztyka@linux.intel.com>"); MODULE_ALIAS_NFT_EXPR("nat"); +MODULE_DESCRIPTION("Network Address Translation support"); diff --git a/net/netfilter/nft_numgen.c b/net/netfilter/nft_numgen.c index 48edb9d5f012..f1fc824f9737 100644 --- a/net/netfilter/nft_numgen.c +++ b/net/netfilter/nft_numgen.c @@ -217,3 +217,4 @@ module_exit(nft_ng_module_exit); MODULE_LICENSE("GPL"); MODULE_AUTHOR("Laura Garcia <nevola@gmail.com>"); MODULE_ALIAS_NFT_EXPR("numgen"); +MODULE_DESCRIPTION("nftables number generator module"); diff --git a/net/netfilter/nft_objref.c b/net/netfilter/nft_objref.c index bfd18d2b65a2..5f9207a9f485 100644 --- a/net/netfilter/nft_objref.c +++ b/net/netfilter/nft_objref.c @@ -252,3 +252,4 @@ module_exit(nft_objref_module_exit); MODULE_LICENSE("GPL"); MODULE_AUTHOR("Pablo Neira Ayuso <pablo@netfilter.org>"); MODULE_ALIAS_NFT_EXPR("objref"); +MODULE_DESCRIPTION("nftables stateful object reference module"); diff --git a/net/netfilter/nft_osf.c b/net/netfilter/nft_osf.c index b42247aa48a9..c261d57a666a 100644 --- a/net/netfilter/nft_osf.c +++ b/net/netfilter/nft_osf.c @@ -149,3 +149,4 @@ module_exit(nft_osf_module_exit); MODULE_LICENSE("GPL"); MODULE_AUTHOR("Fernando Fernandez <ffmancera@riseup.net>"); MODULE_ALIAS_NFT_EXPR("osf"); +MODULE_DESCRIPTION("nftables passive OS fingerprint support"); diff --git a/net/netfilter/nft_queue.c b/net/netfilter/nft_queue.c index 5ece0a6aa8c3..23265d757acb 100644 --- a/net/netfilter/nft_queue.c +++ b/net/netfilter/nft_queue.c @@ -216,3 +216,4 @@ module_exit(nft_queue_module_exit); MODULE_LICENSE("GPL"); MODULE_AUTHOR("Eric Leblond <eric@regit.org>"); MODULE_ALIAS_NFT_EXPR("queue"); +MODULE_DESCRIPTION("Netfilter nftables queue module"); diff --git a/net/netfilter/nft_quota.c b/net/netfilter/nft_quota.c index 4413690591f2..0363f533a42b 100644 --- a/net/netfilter/nft_quota.c +++ b/net/netfilter/nft_quota.c @@ -254,3 +254,4 @@ MODULE_LICENSE("GPL"); MODULE_AUTHOR("Pablo Neira Ayuso <pablo@netfilter.org>"); MODULE_ALIAS_NFT_EXPR("quota"); MODULE_ALIAS_NFT_OBJ(NFT_OBJECT_QUOTA); +MODULE_DESCRIPTION("Netfilter nftables quota module"); diff --git a/net/netfilter/nft_redir.c b/net/netfilter/nft_redir.c index 5b779171565c..2056051c0af0 100644 --- a/net/netfilter/nft_redir.c +++ b/net/netfilter/nft_redir.c @@ -292,3 +292,4 @@ module_exit(nft_redir_module_exit); MODULE_LICENSE("GPL"); MODULE_AUTHOR("Arturo Borrero Gonzalez <arturo@debian.org>"); MODULE_ALIAS_NFT_EXPR("redir"); +MODULE_DESCRIPTION("Netfilter nftables redirect support"); diff --git a/net/netfilter/nft_reject.c b/net/netfilter/nft_reject.c index 00f865fb80ca..86eafbb0fdd0 100644 --- a/net/netfilter/nft_reject.c +++ b/net/netfilter/nft_reject.c @@ -119,3 +119,4 @@ EXPORT_SYMBOL_GPL(nft_reject_icmpv6_code); MODULE_LICENSE("GPL"); MODULE_AUTHOR("Patrick McHardy <kaber@trash.net>"); +MODULE_DESCRIPTION("Netfilter x_tables over nftables module"); diff --git a/net/netfilter/nft_reject_inet.c b/net/netfilter/nft_reject_inet.c index f41f414b72d1..cf8f2646e93c 100644 --- a/net/netfilter/nft_reject_inet.c +++ b/net/netfilter/nft_reject_inet.c @@ -149,3 +149,4 @@ module_exit(nft_reject_inet_module_exit); MODULE_LICENSE("GPL"); MODULE_AUTHOR("Patrick McHardy <kaber@trash.net>"); MODULE_ALIAS_NFT_AF_EXPR(1, "reject"); +MODULE_DESCRIPTION("Netfilter nftables reject inet support"); diff --git a/net/netfilter/nft_set_pipapo.c b/net/netfilter/nft_set_pipapo.c index 8b5acc6910fd..8c04388296b0 100644 --- a/net/netfilter/nft_set_pipapo.c +++ b/net/netfilter/nft_set_pipapo.c @@ -1242,7 +1242,9 @@ static int nft_pipapo_insert(const struct net *net, const struct nft_set *set, end += NFT_PIPAPO_GROUPS_PADDED_SIZE(f); } - if (!*this_cpu_ptr(m->scratch) || bsize_max > m->bsize_max) { + if (!*get_cpu_ptr(m->scratch) || bsize_max > m->bsize_max) { + put_cpu_ptr(m->scratch); + err = pipapo_realloc_scratch(m, bsize_max); if (err) return err; @@ -1250,6 +1252,8 @@ static int nft_pipapo_insert(const struct net *net, const struct nft_set *set, this_cpu_write(nft_pipapo_scratch_index, false); m->bsize_max = bsize_max; + } else { + put_cpu_ptr(m->scratch); } *ext2 = &e->ext; diff --git a/net/netfilter/nft_set_rbtree.c b/net/netfilter/nft_set_rbtree.c index 62f416bc0579..b6aad3fc46c3 100644 --- a/net/netfilter/nft_set_rbtree.c +++ b/net/netfilter/nft_set_rbtree.c @@ -271,12 +271,14 @@ static int __nft_rbtree_insert(const struct net *net, const struct nft_set *set, if (nft_rbtree_interval_start(new)) { if (nft_rbtree_interval_end(rbe) && - nft_set_elem_active(&rbe->ext, genmask)) + nft_set_elem_active(&rbe->ext, genmask) && + !nft_set_elem_expired(&rbe->ext)) overlap = false; } else { overlap = nft_rbtree_interval_end(rbe) && nft_set_elem_active(&rbe->ext, - genmask); + genmask) && + !nft_set_elem_expired(&rbe->ext); } } else if (d > 0) { p = &parent->rb_right; @@ -284,9 +286,11 @@ static int __nft_rbtree_insert(const struct net *net, const struct nft_set *set, if (nft_rbtree_interval_end(new)) { overlap = nft_rbtree_interval_end(rbe) && nft_set_elem_active(&rbe->ext, - genmask); + genmask) && + !nft_set_elem_expired(&rbe->ext); } else if (nft_rbtree_interval_end(rbe) && - nft_set_elem_active(&rbe->ext, genmask)) { + nft_set_elem_active(&rbe->ext, genmask) && + !nft_set_elem_expired(&rbe->ext)) { overlap = true; } } else { @@ -294,15 +298,18 @@ static int __nft_rbtree_insert(const struct net *net, const struct nft_set *set, nft_rbtree_interval_start(new)) { p = &parent->rb_left; - if (nft_set_elem_active(&rbe->ext, genmask)) + if (nft_set_elem_active(&rbe->ext, genmask) && + !nft_set_elem_expired(&rbe->ext)) overlap = false; } else if (nft_rbtree_interval_start(rbe) && nft_rbtree_interval_end(new)) { p = &parent->rb_right; - if (nft_set_elem_active(&rbe->ext, genmask)) + if (nft_set_elem_active(&rbe->ext, genmask) && + !nft_set_elem_expired(&rbe->ext)) overlap = false; - } else if (nft_set_elem_active(&rbe->ext, genmask)) { + } else if (nft_set_elem_active(&rbe->ext, genmask) && + !nft_set_elem_expired(&rbe->ext)) { *ext = &rbe->ext; return -EEXIST; } else { diff --git a/net/netfilter/nft_synproxy.c b/net/netfilter/nft_synproxy.c index e2c1fc608841..4fda8b3f1762 100644 --- a/net/netfilter/nft_synproxy.c +++ b/net/netfilter/nft_synproxy.c @@ -388,3 +388,4 @@ MODULE_LICENSE("GPL"); MODULE_AUTHOR("Fernando Fernandez <ffmancera@riseup.net>"); MODULE_ALIAS_NFT_EXPR("synproxy"); MODULE_ALIAS_NFT_OBJ(NFT_OBJECT_SYNPROXY); +MODULE_DESCRIPTION("nftables SYNPROXY expression support"); diff --git a/net/netfilter/nft_tunnel.c b/net/netfilter/nft_tunnel.c index 30be5787fbde..d3eb953d0333 100644 --- a/net/netfilter/nft_tunnel.c +++ b/net/netfilter/nft_tunnel.c @@ -719,3 +719,4 @@ MODULE_LICENSE("GPL"); MODULE_AUTHOR("Pablo Neira Ayuso <pablo@netfilter.org>"); MODULE_ALIAS_NFT_EXPR("tunnel"); MODULE_ALIAS_NFT_OBJ(NFT_OBJECT_TUNNEL); +MODULE_DESCRIPTION("nftables tunnel expression support"); diff --git a/net/netfilter/xt_nat.c b/net/netfilter/xt_nat.c index a8e5f6c8db7a..b4f7bbc3f3ca 100644 --- a/net/netfilter/xt_nat.c +++ b/net/netfilter/xt_nat.c @@ -244,3 +244,4 @@ MODULE_ALIAS("ipt_SNAT"); MODULE_ALIAS("ipt_DNAT"); MODULE_ALIAS("ip6t_SNAT"); MODULE_ALIAS("ip6t_DNAT"); +MODULE_DESCRIPTION("SNAT and DNAT targets support"); diff --git a/net/netlink/genetlink.c b/net/netlink/genetlink.c index 55ee680e9db1..9395ee8a868d 100644 --- a/net/netlink/genetlink.c +++ b/net/netlink/genetlink.c @@ -351,22 +351,11 @@ int genl_register_family(struct genl_family *family) start = end = GENL_ID_VFS_DQUOT; } - if (family->maxattr && !family->parallel_ops) { - family->attrbuf = kmalloc_array(family->maxattr + 1, - sizeof(struct nlattr *), - GFP_KERNEL); - if (family->attrbuf == NULL) { - err = -ENOMEM; - goto errout_locked; - } - } else - family->attrbuf = NULL; - family->id = idr_alloc_cyclic(&genl_fam_idr, family, start, end + 1, GFP_KERNEL); if (family->id < 0) { err = family->id; - goto errout_free; + goto errout_locked; } err = genl_validate_assign_mc_groups(family); @@ -385,8 +374,6 @@ int genl_register_family(struct genl_family *family) errout_remove: idr_remove(&genl_fam_idr, family->id); -errout_free: - kfree(family->attrbuf); errout_locked: genl_unlock_all(); return err; @@ -419,8 +406,6 @@ int genl_unregister_family(const struct genl_family *family) atomic_read(&genl_sk_destructing_cnt) == 0); genl_unlock(); - kfree(family->attrbuf); - genl_ctrl_event(CTRL_CMD_DELFAMILY, family, NULL, 0); return 0; @@ -485,30 +470,23 @@ genl_family_rcv_msg_attrs_parse(const struct genl_family *family, if (!family->maxattr) return NULL; - if (family->parallel_ops) { - attrbuf = kmalloc_array(family->maxattr + 1, - sizeof(struct nlattr *), GFP_KERNEL); - if (!attrbuf) - return ERR_PTR(-ENOMEM); - } else { - attrbuf = family->attrbuf; - } + attrbuf = kmalloc_array(family->maxattr + 1, + sizeof(struct nlattr *), GFP_KERNEL); + if (!attrbuf) + return ERR_PTR(-ENOMEM); err = __nlmsg_parse(nlh, hdrlen, attrbuf, family->maxattr, family->policy, validate, extack); if (err) { - if (family->parallel_ops) - kfree(attrbuf); + kfree(attrbuf); return ERR_PTR(err); } return attrbuf; } -static void genl_family_rcv_msg_attrs_free(const struct genl_family *family, - struct nlattr **attrbuf) +static void genl_family_rcv_msg_attrs_free(struct nlattr **attrbuf) { - if (family->parallel_ops) - kfree(attrbuf); + kfree(attrbuf); } struct genl_start_context { @@ -542,7 +520,7 @@ static int genl_start(struct netlink_callback *cb) no_attrs: info = genl_dumpit_info_alloc(); if (!info) { - genl_family_rcv_msg_attrs_free(ctx->family, attrs); + genl_family_rcv_msg_attrs_free(attrs); return -ENOMEM; } info->family = ctx->family; @@ -559,7 +537,7 @@ no_attrs: } if (rc) { - genl_family_rcv_msg_attrs_free(info->family, info->attrs); + genl_family_rcv_msg_attrs_free(info->attrs); genl_dumpit_info_free(info); cb->data = NULL; } @@ -588,7 +566,7 @@ static int genl_lock_done(struct netlink_callback *cb) rc = ops->done(cb); genl_unlock(); } - genl_family_rcv_msg_attrs_free(info->family, info->attrs); + genl_family_rcv_msg_attrs_free(info->attrs); genl_dumpit_info_free(info); return rc; } @@ -601,7 +579,7 @@ static int genl_parallel_done(struct netlink_callback *cb) if (ops->done) rc = ops->done(cb); - genl_family_rcv_msg_attrs_free(info->family, info->attrs); + genl_family_rcv_msg_attrs_free(info->attrs); genl_dumpit_info_free(info); return rc; } @@ -694,7 +672,7 @@ static int genl_family_rcv_msg_doit(const struct genl_family *family, family->post_doit(ops, skb, &info); out: - genl_family_rcv_msg_attrs_free(family, attrbuf); + genl_family_rcv_msg_attrs_free(attrbuf); return err; } @@ -1166,60 +1144,11 @@ static struct genl_family genl_ctrl __ro_after_init = { .netnsok = true, }; -static int genl_bind(struct net *net, int group) -{ - struct genl_family *f; - int err = -ENOENT; - unsigned int id; - - down_read(&cb_lock); - - idr_for_each_entry(&genl_fam_idr, f, id) { - if (group >= f->mcgrp_offset && - group < f->mcgrp_offset + f->n_mcgrps) { - int fam_grp = group - f->mcgrp_offset; - - if (!f->netnsok && net != &init_net) - err = -ENOENT; - else if (f->mcast_bind) - err = f->mcast_bind(net, fam_grp); - else - err = 0; - break; - } - } - up_read(&cb_lock); - - return err; -} - -static void genl_unbind(struct net *net, int group) -{ - struct genl_family *f; - unsigned int id; - - down_read(&cb_lock); - - idr_for_each_entry(&genl_fam_idr, f, id) { - if (group >= f->mcgrp_offset && - group < f->mcgrp_offset + f->n_mcgrps) { - int fam_grp = group - f->mcgrp_offset; - - if (f->mcast_unbind) - f->mcast_unbind(net, fam_grp); - break; - } - } - up_read(&cb_lock); -} - static int __net_init genl_pernet_init(struct net *net) { struct netlink_kernel_cfg cfg = { .input = genl_rcv, .flags = NL_CFG_F_NONROOT_RECV, - .bind = genl_bind, - .unbind = genl_unbind, }; /* we'll bump the group number right afterwards */ diff --git a/net/nfc/nci/core.c b/net/nfc/nci/core.c index 7cd524884304..78ea8c94dcba 100644 --- a/net/nfc/nci/core.c +++ b/net/nfc/nci/core.c @@ -1228,10 +1228,13 @@ int nci_register_device(struct nci_dev *ndev) rc = nfc_register_device(ndev->nfc_dev); if (rc) - goto destroy_rx_wq_exit; + goto destroy_tx_wq_exit; goto exit; +destroy_tx_wq_exit: + destroy_workqueue(ndev->tx_wq); + destroy_rx_wq_exit: destroy_workqueue(ndev->rx_wq); diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c index fc0efd8833c8..2611657f40ca 100644 --- a/net/openvswitch/actions.c +++ b/net/openvswitch/actions.c @@ -1169,9 +1169,10 @@ static int execute_check_pkt_len(struct datapath *dp, struct sk_buff *skb, struct sw_flow_key *key, const struct nlattr *attr, bool last) { + struct ovs_skb_cb *ovs_cb = OVS_CB(skb); const struct nlattr *actions, *cpl_arg; + int len, max_len, rem = nla_len(attr); const struct check_pkt_len_arg *arg; - int rem = nla_len(attr); bool clone_flow_key; /* The first netlink attribute in 'attr' is always @@ -1180,7 +1181,11 @@ static int execute_check_pkt_len(struct datapath *dp, struct sk_buff *skb, cpl_arg = nla_data(attr); arg = nla_data(cpl_arg); - if (skb->len <= arg->pkt_len) { + len = ovs_cb->mru ? ovs_cb->mru + skb->mac_len : skb->len; + max_len = arg->pkt_len; + + if ((skb_is_gso(skb) && skb_gso_validate_mac_len(skb, max_len)) || + len <= max_len) { /* Second netlink attribute in 'attr' is always * 'OVS_CHECK_PKT_LEN_ATTR_ACTIONS_IF_LESS_EQUAL'. */ diff --git a/net/qrtr/qrtr.c b/net/qrtr/qrtr.c index 2d8d6131bc5f..300a104b9a0f 100644 --- a/net/qrtr/qrtr.c +++ b/net/qrtr/qrtr.c @@ -166,6 +166,7 @@ static void __qrtr_node_release(struct kref *kref) { struct qrtr_node *node = container_of(kref, struct qrtr_node, ref); struct radix_tree_iter iter; + struct qrtr_tx_flow *flow; unsigned long flags; void __rcu **slot; @@ -181,8 +182,9 @@ static void __qrtr_node_release(struct kref *kref) /* Free tx flow counters */ radix_tree_for_each_slot(slot, &node->qrtr_tx_flow, &iter, 0) { + flow = *slot; radix_tree_iter_delete(&node->qrtr_tx_flow, &iter, slot); - kfree(*slot); + kfree(flow); } kfree(node); } @@ -427,7 +429,7 @@ int qrtr_endpoint_post(struct qrtr_endpoint *ep, const void *data, size_t len) unsigned int ver; size_t hdrlen; - if (len & 3) + if (len == 0 || len & 3) return -EINVAL; skb = netdev_alloc_skb(NULL, len); @@ -441,6 +443,8 @@ int qrtr_endpoint_post(struct qrtr_endpoint *ep, const void *data, size_t len) switch (ver) { case QRTR_PROTO_VER_1: + if (len < sizeof(*v1)) + goto err; v1 = data; hdrlen = sizeof(*v1); @@ -454,6 +458,8 @@ int qrtr_endpoint_post(struct qrtr_endpoint *ep, const void *data, size_t len) size = le32_to_cpu(v1->size); break; case QRTR_PROTO_VER_2: + if (len < sizeof(*v2)) + goto err; v2 = data; hdrlen = sizeof(*v2) + v2->optlen; @@ -1174,6 +1180,7 @@ static int qrtr_release(struct socket *sock) sk->sk_state_change(sk); sock_set_flag(sk, SOCK_DEAD); + sock_orphan(sk); sock->sk = NULL; if (!sock_flag(sk, SOCK_ZAPPED)) diff --git a/net/rds/connection.c b/net/rds/connection.c index ed7f2133acc2..f2fcab182095 100644 --- a/net/rds/connection.c +++ b/net/rds/connection.c @@ -905,6 +905,17 @@ void rds_conn_path_connect_if_down(struct rds_conn_path *cp) } EXPORT_SYMBOL_GPL(rds_conn_path_connect_if_down); +/* Check connectivity of all paths + */ +void rds_check_all_paths(struct rds_connection *conn) +{ + int i = 0; + + do { + rds_conn_path_connect_if_down(&conn->c_path[i]); + } while (++i < conn->c_npaths); +} + void rds_conn_connect_if_down(struct rds_connection *conn) { WARN_ON(conn->c_trans->t_mp_capable); diff --git a/net/rds/ib.h b/net/rds/ib.h index 5ae069d39eab..8dfff43cf07f 100644 --- a/net/rds/ib.h +++ b/net/rds/ib.h @@ -264,7 +264,13 @@ struct rds_ib_device { int *vector_load; }; -#define ibdev_to_node(ibdev) dev_to_node((ibdev)->dev.parent) +static inline int ibdev_to_node(struct ib_device *ibdev) +{ + struct device *parent; + + parent = ibdev->dev.parent; + return parent ? dev_to_node(parent) : NUMA_NO_NODE; +} #define rdsibdev_to_node(rdsibdev) ibdev_to_node(rdsibdev->dev) /* bits for i_ack_flags */ diff --git a/net/rds/rds.h b/net/rds/rds.h index 6019b0c004a9..106e862996b9 100644 --- a/net/rds/rds.h +++ b/net/rds/rds.h @@ -778,6 +778,7 @@ void rds_conn_drop(struct rds_connection *conn); void rds_conn_path_drop(struct rds_conn_path *cpath, bool destroy); void rds_conn_connect_if_down(struct rds_connection *conn); void rds_conn_path_connect_if_down(struct rds_conn_path *cp); +void rds_check_all_paths(struct rds_connection *conn); void rds_for_each_conn_info(struct socket *sock, unsigned int len, struct rds_info_iterator *iter, struct rds_info_lengths *lens, @@ -823,6 +824,12 @@ rds_conn_path_up(struct rds_conn_path *cp) } static inline int +rds_conn_path_down(struct rds_conn_path *cp) +{ + return atomic_read(&cp->cp_state) == RDS_CONN_DOWN; +} + +static inline int rds_conn_up(struct rds_connection *conn) { WARN_ON(conn->c_trans->t_mp_capable); diff --git a/net/rds/send.c b/net/rds/send.c index 68e2bdb08fd0..9a529a01cdc6 100644 --- a/net/rds/send.c +++ b/net/rds/send.c @@ -1340,7 +1340,8 @@ int rds_sendmsg(struct socket *sock, struct msghdr *msg, size_t payload_len) goto out; } - rds_conn_path_connect_if_down(cpath); + if (rds_conn_path_down(cpath)) + rds_check_all_paths(conn); ret = rds_cong_wait(conn->c_fcong, dport, nonblock, rs); if (ret) { diff --git a/net/rds/transport.c b/net/rds/transport.c index 46f709a4b577..f8001ec80867 100644 --- a/net/rds/transport.c +++ b/net/rds/transport.c @@ -38,6 +38,12 @@ #include "rds.h" #include "loop.h" +static char * const rds_trans_modules[] = { + [RDS_TRANS_IB] = "rds_rdma", + [RDS_TRANS_GAP] = NULL, + [RDS_TRANS_TCP] = "rds_tcp", +}; + static struct rds_transport *transports[RDS_TRANS_COUNT]; static DECLARE_RWSEM(rds_trans_sem); @@ -110,18 +116,20 @@ struct rds_transport *rds_trans_get(int t_type) { struct rds_transport *ret = NULL; struct rds_transport *trans; - unsigned int i; down_read(&rds_trans_sem); - for (i = 0; i < RDS_TRANS_COUNT; i++) { - trans = transports[i]; - - if (trans && trans->t_type == t_type && - (!trans->t_owner || try_module_get(trans->t_owner))) { - ret = trans; - break; - } + trans = transports[t_type]; + if (!trans) { + up_read(&rds_trans_sem); + if (rds_trans_modules[t_type]) + request_module(rds_trans_modules[t_type]); + down_read(&rds_trans_sem); + trans = transports[t_type]; } + if (trans && trans->t_type == t_type && + (!trans->t_owner || try_module_get(trans->t_owner))) + ret = trans; + up_read(&rds_trans_sem); return ret; diff --git a/net/rxrpc/call_accept.c b/net/rxrpc/call_accept.c index b7611cc159e5..032ed76c0166 100644 --- a/net/rxrpc/call_accept.c +++ b/net/rxrpc/call_accept.c @@ -22,6 +22,11 @@ #include <net/ip.h> #include "ar-internal.h" +static void rxrpc_dummy_notify(struct sock *sk, struct rxrpc_call *call, + unsigned long user_call_ID) +{ +} + /* * Preallocate a single service call, connection and peer and, if possible, * give them a user ID and attach the user's side of the ID to them. @@ -228,6 +233,8 @@ void rxrpc_discard_prealloc(struct rxrpc_sock *rx) if (rx->discard_new_call) { _debug("discard %lx", call->user_call_ID); rx->discard_new_call(call, call->user_call_ID); + if (call->notify_rx) + call->notify_rx = rxrpc_dummy_notify; rxrpc_put_call(call, rxrpc_call_put_kernel); } rxrpc_call_completed(call); diff --git a/net/rxrpc/call_event.c b/net/rxrpc/call_event.c index aa1c8eee6557..6be2672a65ea 100644 --- a/net/rxrpc/call_event.c +++ b/net/rxrpc/call_event.c @@ -253,7 +253,7 @@ static void rxrpc_resend(struct rxrpc_call *call, unsigned long now_j) * confuse things */ annotation &= ~RXRPC_TX_ANNO_MASK; - annotation |= RXRPC_TX_ANNO_RESENT; + annotation |= RXRPC_TX_ANNO_UNACK | RXRPC_TX_ANNO_RESENT; call->rxtx_annotations[ix] = annotation; skb = call->rxtx_buffer[ix]; diff --git a/net/rxrpc/input.c b/net/rxrpc/input.c index 299ac98e9754..767579328a06 100644 --- a/net/rxrpc/input.c +++ b/net/rxrpc/input.c @@ -722,13 +722,12 @@ static void rxrpc_input_ackinfo(struct rxrpc_call *call, struct sk_buff *skb, ntohl(ackinfo->rxMTU), ntohl(ackinfo->maxMTU), rwind, ntohl(ackinfo->jumbo_max)); + if (rwind > RXRPC_RXTX_BUFF_SIZE - 1) + rwind = RXRPC_RXTX_BUFF_SIZE - 1; if (call->tx_winsize != rwind) { - if (rwind > RXRPC_RXTX_BUFF_SIZE - 1) - rwind = RXRPC_RXTX_BUFF_SIZE - 1; if (rwind > call->tx_winsize) wake = true; - trace_rxrpc_rx_rwind_change(call, sp->hdr.serial, - ntohl(ackinfo->rwind), wake); + trace_rxrpc_rx_rwind_change(call, sp->hdr.serial, rwind, wake); call->tx_winsize = rwind; } diff --git a/net/rxrpc/recvmsg.c b/net/rxrpc/recvmsg.c index 2989742a4aa1..490b1927215c 100644 --- a/net/rxrpc/recvmsg.c +++ b/net/rxrpc/recvmsg.c @@ -543,7 +543,7 @@ try_again: list_empty(&rx->recvmsg_q) && rx->sk.sk_state != RXRPC_SERVER_LISTENING) { release_sock(&rx->sk); - return -ENODATA; + return -EAGAIN; } if (list_empty(&rx->recvmsg_q)) { diff --git a/net/rxrpc/sendmsg.c b/net/rxrpc/sendmsg.c index 1304b8608f56..03a30d014bb6 100644 --- a/net/rxrpc/sendmsg.c +++ b/net/rxrpc/sendmsg.c @@ -304,7 +304,7 @@ static int rxrpc_send_data(struct rxrpc_sock *rx, /* this should be in poll */ sk_clear_bit(SOCKWQ_ASYNC_NOSPACE, sk); - if (sk->sk_err || (sk->sk_shutdown & SEND_SHUTDOWN)) + if (sk->sk_shutdown & SEND_SHUTDOWN) return -EPIPE; more = msg->msg_flags & MSG_MORE; diff --git a/net/sched/act_connmark.c b/net/sched/act_connmark.c index 43a243081e7d..f901421b0634 100644 --- a/net/sched/act_connmark.c +++ b/net/sched/act_connmark.c @@ -43,17 +43,20 @@ static int tcf_connmark_act(struct sk_buff *skb, const struct tc_action *a, tcf_lastuse_update(&ca->tcf_tm); bstats_update(&ca->tcf_bstats, skb); - if (skb->protocol == htons(ETH_P_IP)) { + switch (skb_protocol(skb, true)) { + case htons(ETH_P_IP): if (skb->len < sizeof(struct iphdr)) goto out; proto = NFPROTO_IPV4; - } else if (skb->protocol == htons(ETH_P_IPV6)) { + break; + case htons(ETH_P_IPV6): if (skb->len < sizeof(struct ipv6hdr)) goto out; proto = NFPROTO_IPV6; - } else { + break; + default: goto out; } diff --git a/net/sched/act_csum.c b/net/sched/act_csum.c index cb8608f0a77a..c60674cf25c4 100644 --- a/net/sched/act_csum.c +++ b/net/sched/act_csum.c @@ -587,7 +587,7 @@ static int tcf_csum_act(struct sk_buff *skb, const struct tc_action *a, goto drop; update_flags = params->update_flags; - protocol = tc_skb_protocol(skb); + protocol = skb_protocol(skb, false); again: switch (protocol) { case cpu_to_be16(ETH_P_IP): diff --git a/net/sched/act_ct.c b/net/sched/act_ct.c index e29f0f45d688..5928efb6449c 100644 --- a/net/sched/act_ct.c +++ b/net/sched/act_ct.c @@ -624,7 +624,7 @@ static u8 tcf_ct_skb_nf_family(struct sk_buff *skb) { u8 family = NFPROTO_UNSPEC; - switch (skb->protocol) { + switch (skb_protocol(skb, true)) { case htons(ETH_P_IP): family = NFPROTO_IPV4; break; @@ -673,9 +673,10 @@ static int tcf_ct_ipv6_is_fragment(struct sk_buff *skb, bool *frag) } static int tcf_ct_handle_fragments(struct net *net, struct sk_buff *skb, - u8 family, u16 zone) + u8 family, u16 zone, bool *defrag) { enum ip_conntrack_info ctinfo; + struct qdisc_skb_cb cb; struct nf_conn *ct; int err = 0; bool frag; @@ -693,6 +694,7 @@ static int tcf_ct_handle_fragments(struct net *net, struct sk_buff *skb, return err; skb_get(skb); + cb = *qdisc_skb_cb(skb); if (family == NFPROTO_IPV4) { enum ip_defrag_users user = IP_DEFRAG_CONNTRACK_IN + zone; @@ -703,6 +705,9 @@ static int tcf_ct_handle_fragments(struct net *net, struct sk_buff *skb, local_bh_enable(); if (err && err != -EINPROGRESS) goto out_free; + + if (!err) + *defrag = true; } else { /* NFPROTO_IPV6 */ #if IS_ENABLED(CONFIG_NF_DEFRAG_IPV6) enum ip6_defrag_users user = IP6_DEFRAG_CONNTRACK_IN + zone; @@ -711,12 +716,16 @@ static int tcf_ct_handle_fragments(struct net *net, struct sk_buff *skb, err = nf_ct_frag6_gather(net, skb, user); if (err && err != -EINPROGRESS) goto out_free; + + if (!err) + *defrag = true; #else err = -EOPNOTSUPP; goto out_free; #endif } + *qdisc_skb_cb(skb) = cb; skb_clear_hash(skb); skb->ignore_df = 1; return err; @@ -748,6 +757,7 @@ static int ct_nat_execute(struct sk_buff *skb, struct nf_conn *ct, const struct nf_nat_range2 *range, enum nf_nat_manip_type maniptype) { + __be16 proto = skb_protocol(skb, true); int hooknum, err = NF_ACCEPT; /* See HOOK2MANIP(). */ @@ -759,14 +769,13 @@ static int ct_nat_execute(struct sk_buff *skb, struct nf_conn *ct, switch (ctinfo) { case IP_CT_RELATED: case IP_CT_RELATED_REPLY: - if (skb->protocol == htons(ETH_P_IP) && + if (proto == htons(ETH_P_IP) && ip_hdr(skb)->protocol == IPPROTO_ICMP) { if (!nf_nat_icmp_reply_translation(skb, ct, ctinfo, hooknum)) err = NF_DROP; goto out; - } else if (IS_ENABLED(CONFIG_IPV6) && - skb->protocol == htons(ETH_P_IPV6)) { + } else if (IS_ENABLED(CONFIG_IPV6) && proto == htons(ETH_P_IPV6)) { __be16 frag_off; u8 nexthdr = ipv6_hdr(skb)->nexthdr; int hdrlen = ipv6_skip_exthdr(skb, @@ -914,6 +923,7 @@ static int tcf_ct_act(struct sk_buff *skb, const struct tc_action *a, int nh_ofs, err, retval; struct tcf_ct_params *p; bool skip_add = false; + bool defrag = false; struct nf_conn *ct; u8 family; @@ -925,6 +935,8 @@ static int tcf_ct_act(struct sk_buff *skb, const struct tc_action *a, force = p->ct_action & TCA_CT_ACT_FORCE; tmpl = p->tmpl; + tcf_lastuse_update(&c->tcf_tm); + if (clear) { ct = nf_ct_get(skb, &ctinfo); if (ct) { @@ -944,7 +956,7 @@ static int tcf_ct_act(struct sk_buff *skb, const struct tc_action *a, */ nh_ofs = skb_network_offset(skb); skb_pull_rcsum(skb, nh_ofs); - err = tcf_ct_handle_fragments(net, skb, family, p->zone); + err = tcf_ct_handle_fragments(net, skb, family, p->zone, &defrag); if (err == -EINPROGRESS) { retval = TC_ACT_STOLEN; goto out; @@ -1012,6 +1024,8 @@ out_push: out: tcf_action_update_bstats(&c->common, skb); + if (defrag) + qdisc_skb_cb(skb)->pkt_len = skb->len; return retval; drop: @@ -1543,17 +1557,6 @@ static void __exit ct_cleanup_module(void) destroy_workqueue(act_ct_wq); } -void tcf_ct_flow_table_restore_skb(struct sk_buff *skb, unsigned long cookie) -{ - enum ip_conntrack_info ctinfo = cookie & NFCT_INFOMASK; - struct nf_conn *ct; - - ct = (struct nf_conn *)(cookie & NFCT_PTRMASK); - nf_conntrack_get(&ct->ct_general); - nf_ct_set(skb, ct, ctinfo); -} -EXPORT_SYMBOL_GPL(tcf_ct_flow_table_restore_skb); - module_init(ct_init_module); module_exit(ct_cleanup_module); MODULE_AUTHOR("Paul Blakey <paulb@mellanox.com>"); @@ -1561,4 +1564,3 @@ MODULE_AUTHOR("Yossi Kuperman <yossiku@mellanox.com>"); MODULE_AUTHOR("Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>"); MODULE_DESCRIPTION("Connection tracking action"); MODULE_LICENSE("GPL v2"); - diff --git a/net/sched/act_ctinfo.c b/net/sched/act_ctinfo.c index 19649623493b..b5042f3ea079 100644 --- a/net/sched/act_ctinfo.c +++ b/net/sched/act_ctinfo.c @@ -96,19 +96,22 @@ static int tcf_ctinfo_act(struct sk_buff *skb, const struct tc_action *a, action = READ_ONCE(ca->tcf_action); wlen = skb_network_offset(skb); - if (tc_skb_protocol(skb) == htons(ETH_P_IP)) { + switch (skb_protocol(skb, true)) { + case htons(ETH_P_IP): wlen += sizeof(struct iphdr); if (!pskb_may_pull(skb, wlen)) goto out; proto = NFPROTO_IPV4; - } else if (tc_skb_protocol(skb) == htons(ETH_P_IPV6)) { + break; + case htons(ETH_P_IPV6): wlen += sizeof(struct ipv6hdr); if (!pskb_may_pull(skb, wlen)) goto out; proto = NFPROTO_IPV6; - } else { + break; + default: goto out; } diff --git a/net/sched/act_gate.c b/net/sched/act_gate.c index 9c628591f452..323ae7f6315d 100644 --- a/net/sched/act_gate.c +++ b/net/sched/act_gate.c @@ -32,7 +32,7 @@ static ktime_t gate_get_time(struct tcf_gate *gact) return KTIME_MAX; } -static int gate_get_start_time(struct tcf_gate *gact, ktime_t *start) +static void gate_get_start_time(struct tcf_gate *gact, ktime_t *start) { struct tcf_gate_params *param = &gact->param; ktime_t now, base, cycle; @@ -43,18 +43,13 @@ static int gate_get_start_time(struct tcf_gate *gact, ktime_t *start) if (ktime_after(base, now)) { *start = base; - return 0; + return; } cycle = param->tcfg_cycletime; - /* cycle time should not be zero */ - if (!cycle) - return -EFAULT; - n = div64_u64(ktime_sub_ns(now, base), cycle); *start = ktime_add_ns(base, (n + 1) * cycle); - return 0; } static void gate_start_timer(struct tcf_gate *gact, ktime_t start) @@ -277,6 +272,27 @@ release_list: return err; } +static void gate_setup_timer(struct tcf_gate *gact, u64 basetime, + enum tk_offsets tko, s32 clockid, + bool do_init) +{ + if (!do_init) { + if (basetime == gact->param.tcfg_basetime && + tko == gact->tk_offset && + clockid == gact->param.tcfg_clockid) + return; + + spin_unlock_bh(&gact->tcf_lock); + hrtimer_cancel(&gact->hitimer); + spin_lock_bh(&gact->tcf_lock); + } + gact->param.tcfg_basetime = basetime; + gact->param.tcfg_clockid = clockid; + gact->tk_offset = tko; + hrtimer_init(&gact->hitimer, clockid, HRTIMER_MODE_ABS_SOFT); + gact->hitimer.function = gate_timer_func; +} + static int tcf_gate_init(struct net *net, struct nlattr *nla, struct nlattr *est, struct tc_action **a, int ovr, int bind, bool rtnl_held, @@ -287,12 +303,12 @@ static int tcf_gate_init(struct net *net, struct nlattr *nla, enum tk_offsets tk_offset = TK_OFFS_TAI; struct nlattr *tb[TCA_GATE_MAX + 1]; struct tcf_chain *goto_ch = NULL; + u64 cycletime = 0, basetime = 0; struct tcf_gate_params *p; s32 clockid = CLOCK_TAI; struct tcf_gate *gact; struct tc_gate *parm; int ret = 0, err; - u64 basetime = 0; u32 gflags = 0; s32 prio = -1; ktime_t start; @@ -308,6 +324,27 @@ static int tcf_gate_init(struct net *net, struct nlattr *nla, if (!tb[TCA_GATE_PARMS]) return -EINVAL; + if (tb[TCA_GATE_CLOCKID]) { + clockid = nla_get_s32(tb[TCA_GATE_CLOCKID]); + switch (clockid) { + case CLOCK_REALTIME: + tk_offset = TK_OFFS_REAL; + break; + case CLOCK_MONOTONIC: + tk_offset = TK_OFFS_MAX; + break; + case CLOCK_BOOTTIME: + tk_offset = TK_OFFS_BOOT; + break; + case CLOCK_TAI: + tk_offset = TK_OFFS_TAI; + break; + default: + NL_SET_ERR_MSG(extack, "Invalid 'clockid'"); + return -EINVAL; + } + } + parm = nla_data(tb[TCA_GATE_PARMS]); index = parm->index; @@ -331,10 +368,6 @@ static int tcf_gate_init(struct net *net, struct nlattr *nla, tcf_idr_release(*a, bind); return -EEXIST; } - if (ret == ACT_P_CREATED) { - to_gate(*a)->param.tcfg_clockid = -1; - INIT_LIST_HEAD(&(to_gate(*a)->param.entries)); - } if (tb[TCA_GATE_PRIORITY]) prio = nla_get_s32(tb[TCA_GATE_PRIORITY]); @@ -345,41 +378,19 @@ static int tcf_gate_init(struct net *net, struct nlattr *nla, if (tb[TCA_GATE_FLAGS]) gflags = nla_get_u32(tb[TCA_GATE_FLAGS]); - if (tb[TCA_GATE_CLOCKID]) { - clockid = nla_get_s32(tb[TCA_GATE_CLOCKID]); - switch (clockid) { - case CLOCK_REALTIME: - tk_offset = TK_OFFS_REAL; - break; - case CLOCK_MONOTONIC: - tk_offset = TK_OFFS_MAX; - break; - case CLOCK_BOOTTIME: - tk_offset = TK_OFFS_BOOT; - break; - case CLOCK_TAI: - tk_offset = TK_OFFS_TAI; - break; - default: - NL_SET_ERR_MSG(extack, "Invalid 'clockid'"); - goto release_idr; - } - } + gact = to_gate(*a); + if (ret == ACT_P_CREATED) + INIT_LIST_HEAD(&gact->param.entries); err = tcf_action_check_ctrlact(parm->action, tp, &goto_ch, extack); if (err < 0) goto release_idr; - gact = to_gate(*a); - spin_lock_bh(&gact->tcf_lock); p = &gact->param; - if (tb[TCA_GATE_CYCLE_TIME]) { - p->tcfg_cycletime = nla_get_u64(tb[TCA_GATE_CYCLE_TIME]); - if (!p->tcfg_cycletime_ext) - goto chain_put; - } + if (tb[TCA_GATE_CYCLE_TIME]) + cycletime = nla_get_u64(tb[TCA_GATE_CYCLE_TIME]); if (tb[TCA_GATE_ENTRY_LIST]) { err = parse_gate_list(tb[TCA_GATE_ENTRY_LIST], p, extack); @@ -387,35 +398,29 @@ static int tcf_gate_init(struct net *net, struct nlattr *nla, goto chain_put; } - if (!p->tcfg_cycletime) { + if (!cycletime) { struct tcfg_gate_entry *entry; ktime_t cycle = 0; list_for_each_entry(entry, &p->entries, list) cycle = ktime_add_ns(cycle, entry->interval); - p->tcfg_cycletime = cycle; + cycletime = cycle; + if (!cycletime) { + err = -EINVAL; + goto chain_put; + } } + p->tcfg_cycletime = cycletime; if (tb[TCA_GATE_CYCLE_TIME_EXT]) p->tcfg_cycletime_ext = nla_get_u64(tb[TCA_GATE_CYCLE_TIME_EXT]); + gate_setup_timer(gact, basetime, tk_offset, clockid, + ret == ACT_P_CREATED); p->tcfg_priority = prio; - p->tcfg_basetime = basetime; - p->tcfg_clockid = clockid; p->tcfg_flags = gflags; - - gact->tk_offset = tk_offset; - hrtimer_init(&gact->hitimer, clockid, HRTIMER_MODE_ABS_SOFT); - gact->hitimer.function = gate_timer_func; - - err = gate_get_start_time(gact, &start); - if (err < 0) { - NL_SET_ERR_MSG(extack, - "Internal error: failed get start time"); - release_entry_list(&p->entries); - goto chain_put; - } + gate_get_start_time(gact, &start); gact->current_close_time = start; gact->current_gate_status = GATE_ACT_GATE_OPEN | GATE_ACT_PENDING; @@ -443,6 +448,13 @@ chain_put: if (goto_ch) tcf_chain_put_by_act(goto_ch); release_idr: + /* action is not inserted in any list: it's safe to init hitimer + * without taking tcf_lock. + */ + if (ret == ACT_P_CREATED) + gate_setup_timer(gact, gact->param.tcfg_basetime, + gact->tk_offset, gact->param.tcfg_clockid, + true); tcf_idr_release(*a, bind); return err; } @@ -453,9 +465,7 @@ static void tcf_gate_cleanup(struct tc_action *a) struct tcf_gate_params *p; p = &gact->param; - if (p->tcfg_clockid != -1) - hrtimer_cancel(&gact->hitimer); - + hrtimer_cancel(&gact->hitimer); release_entry_list(&p->entries); } diff --git a/net/sched/act_mpls.c b/net/sched/act_mpls.c index be3f215cd027..8118e2640979 100644 --- a/net/sched/act_mpls.c +++ b/net/sched/act_mpls.c @@ -82,7 +82,7 @@ static int tcf_mpls_act(struct sk_buff *skb, const struct tc_action *a, goto drop; break; case TCA_MPLS_ACT_PUSH: - new_lse = tcf_mpls_get_lse(NULL, p, !eth_p_mpls(skb->protocol)); + new_lse = tcf_mpls_get_lse(NULL, p, !eth_p_mpls(skb_protocol(skb, true))); if (skb_mpls_push(skb, new_lse, p->tcfm_proto, mac_len, skb->dev && skb->dev->type == ARPHRD_ETHER)) goto drop; diff --git a/net/sched/act_skbedit.c b/net/sched/act_skbedit.c index b125b2be4467..b2b3faa57294 100644 --- a/net/sched/act_skbedit.c +++ b/net/sched/act_skbedit.c @@ -41,7 +41,7 @@ static int tcf_skbedit_act(struct sk_buff *skb, const struct tc_action *a, if (params->flags & SKBEDIT_F_INHERITDSFIELD) { int wlen = skb_network_offset(skb); - switch (tc_skb_protocol(skb)) { + switch (skb_protocol(skb, true)) { case htons(ETH_P_IP): wlen += sizeof(struct iphdr); if (!pskb_may_pull(skb, wlen)) diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index a00a203b2ef5..4619cb3cb0a8 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -20,7 +20,6 @@ #include <linux/kmod.h> #include <linux/slab.h> #include <linux/idr.h> -#include <linux/rhashtable.h> #include <linux/jhash.h> #include <linux/rculist.h> #include <net/net_namespace.h> @@ -652,6 +651,7 @@ static void tc_block_indr_cleanup(struct flow_block_cb *block_cb) &block->flow_block, tcf_block_shared(block), &extack); down_write(&block->cb_lock); + list_del(&block_cb->driver_list); list_move(&block_cb->list, &bo.cb_list); up_write(&block->cb_lock); rtnl_lock(); @@ -671,25 +671,29 @@ static int tcf_block_offload_cmd(struct tcf_block *block, struct netlink_ext_ack *extack) { struct flow_block_offload bo = {}; - int err; tcf_block_offload_init(&bo, dev, command, ei->binder_type, &block->flow_block, tcf_block_shared(block), extack); - if (dev->netdev_ops->ndo_setup_tc) + if (dev->netdev_ops->ndo_setup_tc) { + int err; + err = dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_BLOCK, &bo); - else - err = flow_indr_dev_setup_offload(dev, TC_SETUP_BLOCK, block, - &bo, tc_block_indr_cleanup); + if (err < 0) { + if (err != -EOPNOTSUPP) + NL_SET_ERR_MSG(extack, "Driver ndo_setup_tc failed"); + return err; + } - if (err < 0) { - if (err != -EOPNOTSUPP) - NL_SET_ERR_MSG(extack, "Driver ndo_setup_tc failed"); - return err; + return tcf_block_setup(block, &bo); } - return tcf_block_setup(block, &bo); + flow_indr_dev_setup_offload(dev, TC_SETUP_BLOCK, block, &bo, + tc_block_indr_cleanup); + tcf_block_setup(block, &bo); + + return -EOPNOTSUPP; } static int tcf_block_offload_bind(struct tcf_block *block, struct Qdisc *q, @@ -1533,7 +1537,7 @@ static inline int __tcf_classify(struct sk_buff *skb, reclassify: #endif for (; tp; tp = rcu_dereference_bh(tp->next)) { - __be16 protocol = tc_skb_protocol(skb); + __be16 protocol = skb_protocol(skb, false); int err; if (tp->protocol != protocol && diff --git a/net/sched/cls_flow.c b/net/sched/cls_flow.c index 80ae7b9fa90a..ab53a93b2f2b 100644 --- a/net/sched/cls_flow.c +++ b/net/sched/cls_flow.c @@ -80,7 +80,7 @@ static u32 flow_get_dst(const struct sk_buff *skb, const struct flow_keys *flow) if (dst) return ntohl(dst); - return addr_fold(skb_dst(skb)) ^ (__force u16) tc_skb_protocol(skb); + return addr_fold(skb_dst(skb)) ^ (__force u16)skb_protocol(skb, true); } static u32 flow_get_proto(const struct sk_buff *skb, @@ -104,7 +104,7 @@ static u32 flow_get_proto_dst(const struct sk_buff *skb, if (flow->ports.ports) return ntohs(flow->ports.dst); - return addr_fold(skb_dst(skb)) ^ (__force u16) tc_skb_protocol(skb); + return addr_fold(skb_dst(skb)) ^ (__force u16)skb_protocol(skb, true); } static u32 flow_get_iif(const struct sk_buff *skb) @@ -151,7 +151,7 @@ static u32 flow_get_nfct(const struct sk_buff *skb) static u32 flow_get_nfct_src(const struct sk_buff *skb, const struct flow_keys *flow) { - switch (tc_skb_protocol(skb)) { + switch (skb_protocol(skb, true)) { case htons(ETH_P_IP): return ntohl(CTTUPLE(skb, src.u3.ip)); case htons(ETH_P_IPV6): @@ -164,7 +164,7 @@ fallback: static u32 flow_get_nfct_dst(const struct sk_buff *skb, const struct flow_keys *flow) { - switch (tc_skb_protocol(skb)) { + switch (skb_protocol(skb, true)) { case htons(ETH_P_IP): return ntohl(CTTUPLE(skb, dst.u3.ip)); case htons(ETH_P_IPV6): diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c index b2da37286082..e30bd969fc48 100644 --- a/net/sched/cls_flower.c +++ b/net/sched/cls_flower.c @@ -313,7 +313,7 @@ static int fl_classify(struct sk_buff *skb, const struct tcf_proto *tp, /* skb_flow_dissect() does not set n_proto in case an unknown * protocol, so do it rather here. */ - skb_key.basic.n_proto = skb->protocol; + skb_key.basic.n_proto = skb_protocol(skb, false); skb_flow_dissect_tunnel_info(skb, &mask->dissector, &skb_key); skb_flow_dissect_ct(skb, &mask->dissector, &skb_key, fl_ct_info_to_flower_map, diff --git a/net/sched/em_ipset.c b/net/sched/em_ipset.c index df00566d327d..c95cf86fb431 100644 --- a/net/sched/em_ipset.c +++ b/net/sched/em_ipset.c @@ -59,7 +59,7 @@ static int em_ipset_match(struct sk_buff *skb, struct tcf_ematch *em, }; int ret, network_offset; - switch (tc_skb_protocol(skb)) { + switch (skb_protocol(skb, true)) { case htons(ETH_P_IP): state.pf = NFPROTO_IPV4; if (!pskb_network_may_pull(skb, sizeof(struct iphdr))) diff --git a/net/sched/em_ipt.c b/net/sched/em_ipt.c index 18755d29fd15..3650117da47f 100644 --- a/net/sched/em_ipt.c +++ b/net/sched/em_ipt.c @@ -212,7 +212,7 @@ static int em_ipt_match(struct sk_buff *skb, struct tcf_ematch *em, struct nf_hook_state state; int ret; - switch (tc_skb_protocol(skb)) { + switch (skb_protocol(skb, true)) { case htons(ETH_P_IP): if (!pskb_network_may_pull(skb, sizeof(struct iphdr))) return 0; diff --git a/net/sched/em_meta.c b/net/sched/em_meta.c index d99966a55c84..46254968d390 100644 --- a/net/sched/em_meta.c +++ b/net/sched/em_meta.c @@ -195,7 +195,7 @@ META_COLLECTOR(int_priority) META_COLLECTOR(int_protocol) { /* Let userspace take care of the byte ordering */ - dst->value = tc_skb_protocol(skb); + dst->value = skb_protocol(skb, false); } META_COLLECTOR(int_pkttype) diff --git a/net/sched/sch_atm.c b/net/sched/sch_atm.c index ee12ca9f55b4..1c281cc81f57 100644 --- a/net/sched/sch_atm.c +++ b/net/sched/sch_atm.c @@ -553,16 +553,16 @@ static int atm_tc_init(struct Qdisc *sch, struct nlattr *opt, if (!p->link.q) p->link.q = &noop_qdisc; pr_debug("atm_tc_init: link (%p) qdisc %p\n", &p->link, p->link.q); + p->link.vcc = NULL; + p->link.sock = NULL; + p->link.common.classid = sch->handle; + p->link.ref = 1; err = tcf_block_get(&p->link.block, &p->link.filter_list, sch, extack); if (err) return err; - p->link.vcc = NULL; - p->link.sock = NULL; - p->link.common.classid = sch->handle; - p->link.ref = 1; tasklet_init(&p->task, sch_atm_dequeue, (unsigned long)sch); return 0; } diff --git a/net/sched/sch_cake.c b/net/sched/sch_cake.c index 60f8ae578819..ebaeec1e5c82 100644 --- a/net/sched/sch_cake.c +++ b/net/sched/sch_cake.c @@ -592,7 +592,7 @@ static bool cake_update_flowkeys(struct flow_keys *keys, bool rev = !skb->_nfct, upd = false; __be32 ip; - if (tc_skb_protocol(skb) != htons(ETH_P_IP)) + if (skb_protocol(skb, true) != htons(ETH_P_IP)) return false; if (!nf_ct_get_tuple_skb(&tuple, skb)) @@ -1551,32 +1551,51 @@ static unsigned int cake_drop(struct Qdisc *sch, struct sk_buff **to_free) return idx + (tin << 16); } -static u8 cake_handle_diffserv(struct sk_buff *skb, u16 wash) +static u8 cake_handle_diffserv(struct sk_buff *skb, bool wash) { - int wlen = skb_network_offset(skb); + const int offset = skb_network_offset(skb); + u16 *buf, buf_; u8 dscp; - switch (tc_skb_protocol(skb)) { + switch (skb_protocol(skb, true)) { case htons(ETH_P_IP): - wlen += sizeof(struct iphdr); - if (!pskb_may_pull(skb, wlen) || - skb_try_make_writable(skb, wlen)) + buf = skb_header_pointer(skb, offset, sizeof(buf_), &buf_); + if (unlikely(!buf)) return 0; - dscp = ipv4_get_dsfield(ip_hdr(skb)) >> 2; - if (wash && dscp) + /* ToS is in the second byte of iphdr */ + dscp = ipv4_get_dsfield((struct iphdr *)buf) >> 2; + + if (wash && dscp) { + const int wlen = offset + sizeof(struct iphdr); + + if (!pskb_may_pull(skb, wlen) || + skb_try_make_writable(skb, wlen)) + return 0; + ipv4_change_dsfield(ip_hdr(skb), INET_ECN_MASK, 0); + } + return dscp; case htons(ETH_P_IPV6): - wlen += sizeof(struct ipv6hdr); - if (!pskb_may_pull(skb, wlen) || - skb_try_make_writable(skb, wlen)) + buf = skb_header_pointer(skb, offset, sizeof(buf_), &buf_); + if (unlikely(!buf)) return 0; - dscp = ipv6_get_dsfield(ipv6_hdr(skb)) >> 2; - if (wash && dscp) + /* Traffic class is in the first and second bytes of ipv6hdr */ + dscp = ipv6_get_dsfield((struct ipv6hdr *)buf) >> 2; + + if (wash && dscp) { + const int wlen = offset + sizeof(struct ipv6hdr); + + if (!pskb_may_pull(skb, wlen) || + skb_try_make_writable(skb, wlen)) + return 0; + ipv6_change_dsfield(ipv6_hdr(skb), INET_ECN_MASK, 0); + } + return dscp; case htons(ETH_P_ARP): @@ -1593,14 +1612,17 @@ static struct cake_tin_data *cake_select_tin(struct Qdisc *sch, { struct cake_sched_data *q = qdisc_priv(sch); u32 tin, mark; + bool wash; u8 dscp; /* Tin selection: Default to diffserv-based selection, allow overriding - * using firewall marks or skb->priority. + * using firewall marks or skb->priority. Call DSCP parsing early if + * wash is enabled, otherwise defer to below to skip unneeded parsing. */ - dscp = cake_handle_diffserv(skb, - q->rate_flags & CAKE_FLAG_WASH); mark = (skb->mark & q->fwmark_mask) >> q->fwmark_shft; + wash = !!(q->rate_flags & CAKE_FLAG_WASH); + if (wash) + dscp = cake_handle_diffserv(skb, wash); if (q->tin_mode == CAKE_DIFFSERV_BESTEFFORT) tin = 0; @@ -1614,6 +1636,8 @@ static struct cake_tin_data *cake_select_tin(struct Qdisc *sch, tin = q->tin_order[TC_H_MIN(skb->priority) - 1]; else { + if (!wash) + dscp = cake_handle_diffserv(skb, wash); tin = q->tin_index[dscp]; if (unlikely(tin >= q->tin_cnt)) @@ -2691,7 +2715,7 @@ static int cake_init(struct Qdisc *sch, struct nlattr *opt, qdisc_watchdog_init(&q->watchdog, sch); if (opt) { - int err = cake_change(sch, opt, extack); + err = cake_change(sch, opt, extack); if (err) return err; @@ -3008,7 +3032,7 @@ static int cake_dump_class_stats(struct Qdisc *sch, unsigned long cl, PUT_STAT_S32(BLUE_TIMER_US, ktime_to_us( ktime_sub(now, - flow->cvars.blue_timer))); + flow->cvars.blue_timer))); } if (flow->cvars.dropping) { PUT_STAT_S32(DROP_NEXT_US, diff --git a/net/sched/sch_dsmark.c b/net/sched/sch_dsmark.c index 05605b30bef3..2b88710994d7 100644 --- a/net/sched/sch_dsmark.c +++ b/net/sched/sch_dsmark.c @@ -210,7 +210,7 @@ static int dsmark_enqueue(struct sk_buff *skb, struct Qdisc *sch, if (p->set_tc_index) { int wlen = skb_network_offset(skb); - switch (tc_skb_protocol(skb)) { + switch (skb_protocol(skb, true)) { case htons(ETH_P_IP): wlen += sizeof(struct iphdr); if (!pskb_may_pull(skb, wlen) || @@ -303,7 +303,7 @@ static struct sk_buff *dsmark_dequeue(struct Qdisc *sch) index = skb->tc_index & (p->indices - 1); pr_debug("index %d->%d\n", skb->tc_index, index); - switch (tc_skb_protocol(skb)) { + switch (skb_protocol(skb, true)) { case htons(ETH_P_IP): ipv4_change_dsfield(ip_hdr(skb), p->mv[index].mask, p->mv[index].value); @@ -320,7 +320,7 @@ static struct sk_buff *dsmark_dequeue(struct Qdisc *sch) */ if (p->mv[index].mask != 0xff || p->mv[index].value) pr_warn("%s: unsupported protocol %d\n", - __func__, ntohs(tc_skb_protocol(skb))); + __func__, ntohs(skb_protocol(skb, true))); break; } diff --git a/net/sched/sch_fq.c b/net/sched/sch_fq.c index 8f06a808c59a..2fb76fc0cc31 100644 --- a/net/sched/sch_fq.c +++ b/net/sched/sch_fq.c @@ -1075,3 +1075,4 @@ module_init(fq_module_init) module_exit(fq_module_exit) MODULE_AUTHOR("Eric Dumazet"); MODULE_LICENSE("GPL"); +MODULE_DESCRIPTION("Fair Queue Packet Scheduler"); diff --git a/net/sched/sch_fq_codel.c b/net/sched/sch_fq_codel.c index 436160be9c18..459a784056c0 100644 --- a/net/sched/sch_fq_codel.c +++ b/net/sched/sch_fq_codel.c @@ -721,3 +721,4 @@ module_init(fq_codel_module_init) module_exit(fq_codel_module_exit) MODULE_AUTHOR("Eric Dumazet"); MODULE_LICENSE("GPL"); +MODULE_DESCRIPTION("Fair Queue CoDel discipline"); diff --git a/net/sched/sch_hhf.c b/net/sched/sch_hhf.c index be35f03b657b..420ede875322 100644 --- a/net/sched/sch_hhf.c +++ b/net/sched/sch_hhf.c @@ -721,3 +721,4 @@ module_exit(hhf_module_exit) MODULE_AUTHOR("Terry Lam"); MODULE_AUTHOR("Nandita Dukkipati"); MODULE_LICENSE("GPL"); +MODULE_DESCRIPTION("Heavy-Hitter Filter (HHF)"); diff --git a/net/sched/sch_teql.c b/net/sched/sch_teql.c index 689ef6f3ded8..2f1f0a378408 100644 --- a/net/sched/sch_teql.c +++ b/net/sched/sch_teql.c @@ -239,7 +239,7 @@ __teql_resolve(struct sk_buff *skb, struct sk_buff *skb_res, char haddr[MAX_ADDR_LEN]; neigh_ha_snapshot(haddr, n, dev); - err = dev_hard_header(skb, dev, ntohs(tc_skb_protocol(skb)), + err = dev_hard_header(skb, dev, ntohs(skb_protocol(skb, false)), haddr, NULL, skb->len); if (err < 0) diff --git a/net/sctp/associola.c b/net/sctp/associola.c index 72315137d7e7..8d735461fa19 100644 --- a/net/sctp/associola.c +++ b/net/sctp/associola.c @@ -1565,12 +1565,15 @@ void sctp_assoc_rwnd_decrease(struct sctp_association *asoc, unsigned int len) int sctp_assoc_set_bind_addr_from_ep(struct sctp_association *asoc, enum sctp_scope scope, gfp_t gfp) { + struct sock *sk = asoc->base.sk; int flags; /* Use scoping rules to determine the subset of addresses from * the endpoint. */ - flags = (PF_INET6 == asoc->base.sk->sk_family) ? SCTP_ADDR6_ALLOWED : 0; + flags = (PF_INET6 == sk->sk_family) ? SCTP_ADDR6_ALLOWED : 0; + if (!inet_v6_ipv6only(sk)) + flags |= SCTP_ADDR4_ALLOWED; if (asoc->peer.ipv4_address) flags |= SCTP_ADDR4_PEERSUPP; if (asoc->peer.ipv6_address) diff --git a/net/sctp/bind_addr.c b/net/sctp/bind_addr.c index 53bc61537f44..701c5a4e441d 100644 --- a/net/sctp/bind_addr.c +++ b/net/sctp/bind_addr.c @@ -461,6 +461,7 @@ static int sctp_copy_one_addr(struct net *net, struct sctp_bind_addr *dest, * well as the remote peer. */ if ((((AF_INET == addr->sa.sa_family) && + (flags & SCTP_ADDR4_ALLOWED) && (flags & SCTP_ADDR4_PEERSUPP))) || (((AF_INET6 == addr->sa.sa_family) && (flags & SCTP_ADDR6_ALLOWED) && diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c index 092d1afdee0d..cde29f3c7fb3 100644 --- a/net/sctp/protocol.c +++ b/net/sctp/protocol.c @@ -148,7 +148,8 @@ int sctp_copy_local_addr_list(struct net *net, struct sctp_bind_addr *bp, * sock as well as the remote peer. */ if (addr->a.sa.sa_family == AF_INET && - !(copy_flags & SCTP_ADDR4_PEERSUPP)) + (!(copy_flags & SCTP_ADDR4_ALLOWED) || + !(copy_flags & SCTP_ADDR4_PEERSUPP))) continue; if (addr->a.sa.sa_family == AF_INET6 && (!(copy_flags & SCTP_ADDR6_ALLOWED) || diff --git a/net/sctp/stream.c b/net/sctp/stream.c index 67f7e71f9129..bda2536dd740 100644 --- a/net/sctp/stream.c +++ b/net/sctp/stream.c @@ -22,17 +22,11 @@ #include <net/sctp/sm.h> #include <net/sctp/stream_sched.h> -/* Migrates chunks from stream queues to new stream queues if needed, - * but not across associations. Also, removes those chunks to streams - * higher than the new max. - */ -static void sctp_stream_outq_migrate(struct sctp_stream *stream, - struct sctp_stream *new, __u16 outcnt) +static void sctp_stream_shrink_out(struct sctp_stream *stream, __u16 outcnt) { struct sctp_association *asoc; struct sctp_chunk *ch, *temp; struct sctp_outq *outq; - int i; asoc = container_of(stream, struct sctp_association, stream); outq = &asoc->outqueue; @@ -56,6 +50,19 @@ static void sctp_stream_outq_migrate(struct sctp_stream *stream, sctp_chunk_free(ch); } +} + +/* Migrates chunks from stream queues to new stream queues if needed, + * but not across associations. Also, removes those chunks to streams + * higher than the new max. + */ +static void sctp_stream_outq_migrate(struct sctp_stream *stream, + struct sctp_stream *new, __u16 outcnt) +{ + int i; + + if (stream->outcnt > outcnt) + sctp_stream_shrink_out(stream, outcnt); if (new) { /* Here we actually move the old ext stuff into the new @@ -1037,11 +1044,13 @@ struct sctp_chunk *sctp_process_strreset_resp( nums = ntohs(addstrm->number_of_streams); number = stream->outcnt - nums; - if (result == SCTP_STRRESET_PERFORMED) + if (result == SCTP_STRRESET_PERFORMED) { for (i = number; i < stream->outcnt; i++) SCTP_SO(stream, i)->state = SCTP_STREAM_OPEN; - else + } else { + sctp_stream_shrink_out(stream, number); stream->outcnt = number; + } *evp = sctp_ulpevent_make_stream_change_event(asoc, flags, 0, nums, GFP_ATOMIC); diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c index 903321543838..1163d51196da 100644 --- a/net/smc/af_smc.c +++ b/net/smc/af_smc.c @@ -126,8 +126,10 @@ EXPORT_SYMBOL_GPL(smc_proto6); static void smc_restore_fallback_changes(struct smc_sock *smc) { - smc->clcsock->file->private_data = smc->sk.sk_socket; - smc->clcsock->file = NULL; + if (smc->clcsock->file) { /* non-accepted sockets have no file yet */ + smc->clcsock->file->private_data = smc->sk.sk_socket; + smc->clcsock->file = NULL; + } } static int __smc_release(struct smc_sock *smc) @@ -352,7 +354,7 @@ static int smcr_lgr_reg_rmbs(struct smc_link *link, */ mutex_lock(&lgr->llc_conf_mutex); for (i = 0; i < SMC_LINKS_PER_LGR_MAX; i++) { - if (lgr->lnk[i].state != SMC_LNK_ACTIVE) + if (!smc_link_active(&lgr->lnk[i])) continue; rc = smcr_link_reg_rmb(&lgr->lnk[i], rmb_desc); if (rc) @@ -632,7 +634,9 @@ static int smc_connect_rdma(struct smc_sock *smc, for (i = 0; i < SMC_LINKS_PER_LGR_MAX; i++) { struct smc_link *l = &smc->conn.lgr->lnk[i]; - if (l->peer_qpn == ntoh24(aclc->qpn)) { + if (l->peer_qpn == ntoh24(aclc->qpn) && + !memcmp(l->peer_gid, &aclc->lcl.gid, SMC_GID_SIZE) && + !memcmp(l->peer_mac, &aclc->lcl.mac, sizeof(l->peer_mac))) { link = l; break; } diff --git a/net/smc/smc_cdc.c b/net/smc/smc_cdc.c index a47e8855e045..ce468ff62a19 100644 --- a/net/smc/smc_cdc.c +++ b/net/smc/smc_cdc.c @@ -66,9 +66,13 @@ int smc_cdc_get_free_slot(struct smc_connection *conn, rc = smc_wr_tx_get_free_slot(link, smc_cdc_tx_handler, wr_buf, wr_rdma_buf, (struct smc_wr_tx_pend_priv **)pend); - if (conn->killed) + if (conn->killed) { /* abnormal termination */ + if (!rc) + smc_wr_tx_put_slot(link, + (struct smc_wr_tx_pend_priv *)pend); rc = -EPIPE; + } return rc; } diff --git a/net/smc/smc_clc.c b/net/smc/smc_clc.c index d5627df24215..779f4142a11d 100644 --- a/net/smc/smc_clc.c +++ b/net/smc/smc_clc.c @@ -27,6 +27,7 @@ #define SMCR_CLC_ACCEPT_CONFIRM_LEN 68 #define SMCD_CLC_ACCEPT_CONFIRM_LEN 48 +#define SMC_CLC_RECV_BUF_LEN 100 /* eye catcher "SMCR" EBCDIC for CLC messages */ static const char SMC_EYECATCHER[4] = {'\xe2', '\xd4', '\xc3', '\xd9'}; @@ -36,7 +37,7 @@ static const char SMCD_EYECATCHER[4] = {'\xe2', '\xd4', '\xc3', '\xc4'}; /* check if received message has a correct header length and contains valid * heading and trailing eyecatchers */ -static bool smc_clc_msg_hdr_valid(struct smc_clc_msg_hdr *clcm) +static bool smc_clc_msg_hdr_valid(struct smc_clc_msg_hdr *clcm, bool check_trl) { struct smc_clc_msg_proposal_prefix *pclc_prfx; struct smc_clc_msg_accept_confirm *clc; @@ -49,12 +50,9 @@ static bool smc_clc_msg_hdr_valid(struct smc_clc_msg_hdr *clcm) return false; switch (clcm->type) { case SMC_CLC_PROPOSAL: - if (clcm->path != SMC_TYPE_R && clcm->path != SMC_TYPE_D && - clcm->path != SMC_TYPE_B) - return false; pclc = (struct smc_clc_msg_proposal *)clcm; pclc_prfx = smc_clc_proposal_get_prefix(pclc); - if (ntohs(pclc->hdr.length) != + if (ntohs(pclc->hdr.length) < sizeof(*pclc) + ntohs(pclc->iparea_offset) + sizeof(*pclc_prfx) + pclc_prfx->ipv6_prefixes_cnt * @@ -86,7 +84,8 @@ static bool smc_clc_msg_hdr_valid(struct smc_clc_msg_hdr *clcm) default: return false; } - if (memcmp(trl->eyecatcher, SMC_EYECATCHER, sizeof(SMC_EYECATCHER)) && + if (check_trl && + memcmp(trl->eyecatcher, SMC_EYECATCHER, sizeof(SMC_EYECATCHER)) && memcmp(trl->eyecatcher, SMCD_EYECATCHER, sizeof(SMCD_EYECATCHER))) return false; return true; @@ -276,7 +275,8 @@ int smc_clc_wait_msg(struct smc_sock *smc, void *buf, int buflen, struct msghdr msg = {NULL, 0}; int reason_code = 0; struct kvec vec = {buf, buflen}; - int len, datlen; + int len, datlen, recvlen; + bool check_trl = true; int krflags; /* peek the first few bytes to determine length of data to receive @@ -320,10 +320,7 @@ int smc_clc_wait_msg(struct smc_sock *smc, void *buf, int buflen, } datlen = ntohs(clcm->length); if ((len < sizeof(struct smc_clc_msg_hdr)) || - (datlen > buflen) || - (clcm->version != SMC_CLC_V1) || - (clcm->path != SMC_TYPE_R && clcm->path != SMC_TYPE_D && - clcm->path != SMC_TYPE_B) || + (clcm->version < SMC_CLC_V1) || ((clcm->type != SMC_CLC_DECLINE) && (clcm->type != expected_type))) { smc->sk.sk_err = EPROTO; @@ -331,16 +328,38 @@ int smc_clc_wait_msg(struct smc_sock *smc, void *buf, int buflen, goto out; } + if (clcm->type == SMC_CLC_PROPOSAL && clcm->path == SMC_TYPE_N) + reason_code = SMC_CLC_DECL_VERSMISMAT; /* just V2 offered */ + /* receive the complete CLC message */ memset(&msg, 0, sizeof(struct msghdr)); - iov_iter_kvec(&msg.msg_iter, READ, &vec, 1, datlen); + if (datlen > buflen) { + check_trl = false; + recvlen = buflen; + } else { + recvlen = datlen; + } + iov_iter_kvec(&msg.msg_iter, READ, &vec, 1, recvlen); krflags = MSG_WAITALL; len = sock_recvmsg(smc->clcsock, &msg, krflags); - if (len < datlen || !smc_clc_msg_hdr_valid(clcm)) { + if (len < recvlen || !smc_clc_msg_hdr_valid(clcm, check_trl)) { smc->sk.sk_err = EPROTO; reason_code = -EPROTO; goto out; } + datlen -= len; + while (datlen) { + u8 tmp[SMC_CLC_RECV_BUF_LEN]; + + vec.iov_base = &tmp; + vec.iov_len = SMC_CLC_RECV_BUF_LEN; + /* receive remaining proposal message */ + recvlen = datlen > SMC_CLC_RECV_BUF_LEN ? + SMC_CLC_RECV_BUF_LEN : datlen; + iov_iter_kvec(&msg.msg_iter, READ, &vec, 1, recvlen); + len = sock_recvmsg(smc->clcsock, &msg, krflags); + datlen -= len; + } if (clcm->type == SMC_CLC_DECLINE) { struct smc_clc_msg_decline *dclc; diff --git a/net/smc/smc_clc.h b/net/smc/smc_clc.h index 465876701b75..76c2b150d040 100644 --- a/net/smc/smc_clc.h +++ b/net/smc/smc_clc.h @@ -25,6 +25,7 @@ #define SMC_CLC_V1 0x1 /* SMC version */ #define SMC_TYPE_R 0 /* SMC-R only */ #define SMC_TYPE_D 1 /* SMC-D only */ +#define SMC_TYPE_N 2 /* neither SMC-R nor SMC-D */ #define SMC_TYPE_B 3 /* SMC-R and SMC-D */ #define CLC_WAIT_TIME (6 * HZ) /* max. wait time on clcsock */ #define CLC_WAIT_TIME_SHORT HZ /* short wait time on clcsock */ @@ -46,6 +47,7 @@ #define SMC_CLC_DECL_ISMVLANERR 0x03090000 /* err to reg vlan id on ism dev */ #define SMC_CLC_DECL_NOACTLINK 0x030a0000 /* no active smc-r link in lgr */ #define SMC_CLC_DECL_NOSRVLINK 0x030b0000 /* SMC-R link from srv not found */ +#define SMC_CLC_DECL_VERSMISMAT 0x030c0000 /* SMC version mismatch */ #define SMC_CLC_DECL_SYNCERR 0x04000000 /* synchronization error */ #define SMC_CLC_DECL_PEERDECL 0x05000000 /* peer declined during handshake */ #define SMC_CLC_DECL_INTERR 0x09990000 /* internal error */ diff --git a/net/smc/smc_core.c b/net/smc/smc_core.c index 7964a21e5e6f..f82a2e599917 100644 --- a/net/smc/smc_core.c +++ b/net/smc/smc_core.c @@ -15,6 +15,7 @@ #include <linux/workqueue.h> #include <linux/wait.h> #include <linux/reboot.h> +#include <linux/mutex.h> #include <net/tcp.h> #include <net/sock.h> #include <rdma/ib_verbs.h> @@ -44,18 +45,10 @@ static struct smc_lgr_list smc_lgr_list = { /* established link groups */ static atomic_t lgr_cnt = ATOMIC_INIT(0); /* number of existing link groups */ static DECLARE_WAIT_QUEUE_HEAD(lgrs_deleted); -struct smc_ib_up_work { - struct work_struct work; - struct smc_link_group *lgr; - struct smc_ib_device *smcibdev; - u8 ibport; -}; - static void smc_buf_free(struct smc_link_group *lgr, bool is_rmb, struct smc_buf_desc *buf_desc); static void __smc_lgr_terminate(struct smc_link_group *lgr, bool soft); -static void smc_link_up_work(struct work_struct *work); static void smc_link_down_work(struct work_struct *work); /* return head of link group list and its lock for a given link group */ @@ -247,7 +240,8 @@ static void smcr_lgr_link_deactivate_all(struct smc_link_group *lgr) if (smc_link_usable(lnk)) lnk->state = SMC_LNK_INACTIVE; } - wake_up_interruptible_all(&lgr->llc_waiter); + wake_up_all(&lgr->llc_msg_waiter); + wake_up_all(&lgr->llc_flow_waiter); } static void smc_lgr_free(struct smc_link_group *lgr); @@ -324,7 +318,6 @@ int smcr_link_init(struct smc_link_group *lgr, struct smc_link *lnk, get_device(&ini->ib_dev->ibdev->dev); atomic_inc(&ini->ib_dev->lnk_cnt); - lnk->state = SMC_LNK_ACTIVATING; lnk->link_id = smcr_next_link_id(lgr); lnk->lgr = lgr; lnk->link_idx = link_idx; @@ -360,6 +353,7 @@ int smcr_link_init(struct smc_link_group *lgr, struct smc_link *lnk, rc = smc_wr_create_link(lnk); if (rc) goto destroy_qp; + lnk->state = SMC_LNK_ACTIVATING; return 0; destroy_qp: @@ -450,7 +444,7 @@ static int smc_lgr_create(struct smc_sock *smc, struct smc_init_info *ini) } smc->conn.lgr = lgr; spin_lock_bh(lgr_lock); - list_add(&lgr->list, lgr_list); + list_add_tail(&lgr->list, lgr_list); spin_unlock_bh(lgr_lock); return 0; @@ -548,8 +542,7 @@ struct smc_link *smc_switch_conns(struct smc_link_group *lgr, smc_wr_wakeup_tx_wait(from_lnk); for (i = 0; i < SMC_LINKS_PER_LGR_MAX; i++) { - if (lgr->lnk[i].state != SMC_LNK_ACTIVE || - i == from_lnk->link_idx) + if (!smc_link_active(&lgr->lnk[i]) || i == from_lnk->link_idx) continue; if (is_dev_err && from_lnk->smcibdev == lgr->lnk[i].smcibdev && from_lnk->ibport == lgr->lnk[i].ibport) { @@ -1104,66 +1097,23 @@ static void smc_conn_abort_work(struct work_struct *work) sock_put(&smc->sk); /* sock_hold done by schedulers of abort_work */ } -/* link is up - establish alternate link if applicable */ -static void smcr_link_up(struct smc_link_group *lgr, - struct smc_ib_device *smcibdev, u8 ibport) -{ - struct smc_link *link = NULL; - - if (list_empty(&lgr->list) || - lgr->type == SMC_LGR_SYMMETRIC || - lgr->type == SMC_LGR_ASYMMETRIC_PEER) - return; - - if (lgr->role == SMC_SERV) { - /* trigger local add link processing */ - link = smc_llc_usable_link(lgr); - if (!link) - return; - smc_llc_srv_add_link_local(link); - } else { - /* invite server to start add link processing */ - u8 gid[SMC_GID_SIZE]; - - if (smc_ib_determine_gid(smcibdev, ibport, lgr->vlan_id, gid, - NULL)) - return; - if (lgr->llc_flow_lcl.type != SMC_LLC_FLOW_NONE) { - /* some other llc task is ongoing */ - wait_event_interruptible_timeout(lgr->llc_waiter, - (lgr->llc_flow_lcl.type == SMC_LLC_FLOW_NONE), - SMC_LLC_WAIT_TIME); - } - if (list_empty(&lgr->list) || - !smc_ib_port_active(smcibdev, ibport)) - return; /* lgr or device no longer active */ - link = smc_llc_usable_link(lgr); - if (!link) - return; - smc_llc_send_add_link(link, smcibdev->mac[ibport - 1], gid, - NULL, SMC_LLC_REQ); - } -} - void smcr_port_add(struct smc_ib_device *smcibdev, u8 ibport) { - struct smc_ib_up_work *ib_work; struct smc_link_group *lgr, *n; list_for_each_entry_safe(lgr, n, &smc_lgr_list.list, list) { + struct smc_link *link; + if (strncmp(smcibdev->pnetid[ibport - 1], lgr->pnet_id, SMC_MAX_PNETID_LEN) || lgr->type == SMC_LGR_SYMMETRIC || lgr->type == SMC_LGR_ASYMMETRIC_PEER) continue; - ib_work = kmalloc(sizeof(*ib_work), GFP_KERNEL); - if (!ib_work) - continue; - INIT_WORK(&ib_work->work, smc_link_up_work); - ib_work->lgr = lgr; - ib_work->smcibdev = smcibdev; - ib_work->ibport = ibport; - schedule_work(&ib_work->work); + + /* trigger local add link processing */ + link = smc_llc_usable_link(lgr); + if (link) + smc_llc_add_link_local(link); } } @@ -1195,13 +1145,19 @@ static void smcr_link_down(struct smc_link *lnk) if (lgr->llc_flow_lcl.type != SMC_LLC_FLOW_NONE) { /* another llc task is ongoing */ mutex_unlock(&lgr->llc_conf_mutex); - wait_event_interruptible_timeout(lgr->llc_waiter, - (lgr->llc_flow_lcl.type == SMC_LLC_FLOW_NONE), + wait_event_timeout(lgr->llc_flow_waiter, + (list_empty(&lgr->list) || + lgr->llc_flow_lcl.type == SMC_LLC_FLOW_NONE), SMC_LLC_WAIT_TIME); mutex_lock(&lgr->llc_conf_mutex); } - smc_llc_send_delete_link(to_lnk, del_link_id, SMC_LLC_REQ, true, - SMC_LLC_DEL_LOST_PATH); + if (!list_empty(&lgr->list)) { + smc_llc_send_delete_link(to_lnk, del_link_id, + SMC_LLC_REQ, true, + SMC_LLC_DEL_LOST_PATH); + smcr_link_clear(lnk, true); + } + wake_up(&lgr->llc_flow_waiter); /* wake up next waiter */ } } @@ -1240,20 +1196,6 @@ void smcr_port_err(struct smc_ib_device *smcibdev, u8 ibport) } } -static void smc_link_up_work(struct work_struct *work) -{ - struct smc_ib_up_work *ib_work = container_of(work, - struct smc_ib_up_work, - work); - struct smc_link_group *lgr = ib_work->lgr; - - if (list_empty(&lgr->list)) - goto out; - smcr_link_up(lgr, ib_work->smcibdev, ib_work->ibport); -out: - kfree(ib_work); -} - static void smc_link_down_work(struct work_struct *work) { struct smc_link *link = container_of(work, struct smc_link, @@ -1262,7 +1204,7 @@ static void smc_link_down_work(struct work_struct *work) if (list_empty(&lgr->list)) return; - wake_up_interruptible_all(&lgr->llc_waiter); + wake_up_all(&lgr->llc_msg_waiter); mutex_lock(&lgr->llc_conf_mutex); smcr_link_down(link); mutex_unlock(&lgr->llc_conf_mutex); @@ -1326,7 +1268,7 @@ static bool smcr_lgr_match(struct smc_link_group *lgr, return false; for (i = 0; i < SMC_LINKS_PER_LGR_MAX; i++) { - if (lgr->lnk[i].state != SMC_LNK_ACTIVE) + if (!smc_link_active(&lgr->lnk[i])) continue; if ((lgr->role == SMC_SERV || lgr->lnk[i].peer_qpn == clcqpn) && !memcmp(lgr->lnk[i].peer_gid, &lcl->gid, SMC_GID_SIZE) && @@ -1369,7 +1311,7 @@ int smc_conn_create(struct smc_sock *smc, struct smc_init_info *ini) smcr_lgr_match(lgr, ini->ib_lcl, role, ini->ib_clcqpn)) && !lgr->sync_err && lgr->vlan_id == ini->vlan_id && - (role == SMC_CLNT || + (role == SMC_CLNT || ini->is_smcd || lgr->conns_num < SMC_RMBS_PER_LGR_MAX)) { /* link group found */ ini->cln_first_contact = SMC_REUSE_CONTACT; @@ -1774,14 +1716,14 @@ static int __smc_buf_create(struct smc_sock *smc, bool is_smcd, bool is_rmb) void smc_sndbuf_sync_sg_for_cpu(struct smc_connection *conn) { - if (!conn->lgr || conn->lgr->is_smcd || !smc_link_usable(conn->lnk)) + if (!conn->lgr || conn->lgr->is_smcd || !smc_link_active(conn->lnk)) return; smc_ib_sync_sg_for_cpu(conn->lnk, conn->sndbuf_desc, DMA_TO_DEVICE); } void smc_sndbuf_sync_sg_for_device(struct smc_connection *conn) { - if (!conn->lgr || conn->lgr->is_smcd || !smc_link_usable(conn->lnk)) + if (!conn->lgr || conn->lgr->is_smcd || !smc_link_active(conn->lnk)) return; smc_ib_sync_sg_for_device(conn->lnk, conn->sndbuf_desc, DMA_TO_DEVICE); } @@ -1793,7 +1735,7 @@ void smc_rmb_sync_sg_for_cpu(struct smc_connection *conn) if (!conn->lgr || conn->lgr->is_smcd) return; for (i = 0; i < SMC_LINKS_PER_LGR_MAX; i++) { - if (!smc_link_usable(&conn->lgr->lnk[i])) + if (!smc_link_active(&conn->lgr->lnk[i])) continue; smc_ib_sync_sg_for_cpu(&conn->lgr->lnk[i], conn->rmb_desc, DMA_FROM_DEVICE); @@ -1807,7 +1749,7 @@ void smc_rmb_sync_sg_for_device(struct smc_connection *conn) if (!conn->lgr || conn->lgr->is_smcd) return; for (i = 0; i < SMC_LINKS_PER_LGR_MAX; i++) { - if (!smc_link_usable(&conn->lgr->lnk[i])) + if (!smc_link_active(&conn->lgr->lnk[i])) continue; smc_ib_sync_sg_for_device(&conn->lgr->lnk[i], conn->rmb_desc, DMA_FROM_DEVICE); @@ -1830,8 +1772,12 @@ int smc_buf_create(struct smc_sock *smc, bool is_smcd) return rc; /* create rmb */ rc = __smc_buf_create(smc, is_smcd, true); - if (rc) + if (rc) { + mutex_lock(&smc->conn.lgr->sndbufs_lock); + list_del(&smc->conn.sndbuf_desc->list); + mutex_unlock(&smc->conn.lgr->sndbufs_lock); smc_buf_free(smc->conn.lgr, false, smc->conn.sndbuf_desc); + } return rc; } @@ -1955,20 +1901,20 @@ static void smc_core_going_away(void) struct smc_ib_device *smcibdev; struct smcd_dev *smcd; - spin_lock(&smc_ib_devices.lock); + mutex_lock(&smc_ib_devices.mutex); list_for_each_entry(smcibdev, &smc_ib_devices.list, list) { int i; for (i = 0; i < SMC_MAX_PORTS; i++) set_bit(i, smcibdev->ports_going_away); } - spin_unlock(&smc_ib_devices.lock); + mutex_unlock(&smc_ib_devices.mutex); - spin_lock(&smcd_dev_list.lock); + mutex_lock(&smcd_dev_list.mutex); list_for_each_entry(smcd, &smcd_dev_list.list, list) { smcd->going_away = 1; } - spin_unlock(&smcd_dev_list.lock); + mutex_unlock(&smcd_dev_list.mutex); } /* Clean up all SMC link groups */ @@ -1980,10 +1926,10 @@ static void smc_lgrs_shutdown(void) smc_smcr_terminate_all(NULL); - spin_lock(&smcd_dev_list.lock); + mutex_lock(&smcd_dev_list.mutex); list_for_each_entry(smcd, &smcd_dev_list.list, list) smc_smcd_terminate_all(smcd); - spin_unlock(&smcd_dev_list.lock); + mutex_unlock(&smcd_dev_list.mutex); } static int smc_core_reboot_event(struct notifier_block *this, diff --git a/net/smc/smc_core.h b/net/smc/smc_core.h index 86d160f0d187..1c4d5439d0ff 100644 --- a/net/smc/smc_core.h +++ b/net/smc/smc_core.h @@ -262,8 +262,10 @@ struct smc_link_group { struct work_struct llc_del_link_work; struct work_struct llc_event_work; /* llc event worker */ - wait_queue_head_t llc_waiter; + wait_queue_head_t llc_flow_waiter; /* w4 next llc event */ + wait_queue_head_t llc_msg_waiter; + /* w4 next llc msg */ struct smc_llc_flow llc_flow_lcl; /* llc local control field */ struct smc_llc_flow llc_flow_rmt; @@ -347,6 +349,11 @@ static inline bool smc_link_usable(struct smc_link *lnk) return true; } +static inline bool smc_link_active(struct smc_link *lnk) +{ + return lnk->state == SMC_LNK_ACTIVE; +} + struct smc_sock; struct smc_clc_msg_accept_confirm; struct smc_clc_msg_local; diff --git a/net/smc/smc_ib.c b/net/smc/smc_ib.c index 562a52d01ad1..1c314dbdc7fa 100644 --- a/net/smc/smc_ib.c +++ b/net/smc/smc_ib.c @@ -16,6 +16,7 @@ #include <linux/workqueue.h> #include <linux/scatterlist.h> #include <linux/wait.h> +#include <linux/mutex.h> #include <rdma/ib_verbs.h> #include <rdma/ib_cache.h> @@ -33,7 +34,7 @@ #define SMC_QP_RNR_RETRY 7 /* 7: infinite */ struct smc_ib_devices smc_ib_devices = { /* smc-registered ib devices */ - .lock = __SPIN_LOCK_UNLOCKED(smc_ib_devices.lock), + .mutex = __MUTEX_INITIALIZER(smc_ib_devices.mutex), .list = LIST_HEAD_INIT(smc_ib_devices.list), }; @@ -505,6 +506,10 @@ long smc_ib_setup_per_ibdev(struct smc_ib_device *smcibdev) int cqe_size_order, smc_order; long rc; + mutex_lock(&smcibdev->mutex); + rc = 0; + if (smcibdev->initialized) + goto out; /* the calculated number of cq entries fits to mlx5 cq allocation */ cqe_size_order = cache_line_size() == 128 ? 7 : 6; smc_order = MAX_ORDER - cqe_size_order - 1; @@ -516,7 +521,7 @@ long smc_ib_setup_per_ibdev(struct smc_ib_device *smcibdev) rc = PTR_ERR_OR_ZERO(smcibdev->roce_cq_send); if (IS_ERR(smcibdev->roce_cq_send)) { smcibdev->roce_cq_send = NULL; - return rc; + goto out; } smcibdev->roce_cq_recv = ib_create_cq(smcibdev->ibdev, smc_wr_rx_cq_handler, NULL, @@ -528,21 +533,26 @@ long smc_ib_setup_per_ibdev(struct smc_ib_device *smcibdev) } smc_wr_add_dev(smcibdev); smcibdev->initialized = 1; - return rc; + goto out; err: ib_destroy_cq(smcibdev->roce_cq_send); +out: + mutex_unlock(&smcibdev->mutex); return rc; } static void smc_ib_cleanup_per_ibdev(struct smc_ib_device *smcibdev) { + mutex_lock(&smcibdev->mutex); if (!smcibdev->initialized) - return; + goto out; smcibdev->initialized = 0; ib_destroy_cq(smcibdev->roce_cq_recv); ib_destroy_cq(smcibdev->roce_cq_send); smc_wr_remove_dev(smcibdev); +out: + mutex_unlock(&smcibdev->mutex); } static struct ib_client smc_ib_client; @@ -565,9 +575,10 @@ static int smc_ib_add_dev(struct ib_device *ibdev) INIT_WORK(&smcibdev->port_event_work, smc_ib_port_event_work); atomic_set(&smcibdev->lnk_cnt, 0); init_waitqueue_head(&smcibdev->lnks_deleted); - spin_lock(&smc_ib_devices.lock); + mutex_init(&smcibdev->mutex); + mutex_lock(&smc_ib_devices.mutex); list_add_tail(&smcibdev->list, &smc_ib_devices.list); - spin_unlock(&smc_ib_devices.lock); + mutex_unlock(&smc_ib_devices.mutex); ib_set_client_data(ibdev, &smc_ib_client, smcibdev); INIT_IB_EVENT_HANDLER(&smcibdev->event_handler, smcibdev->ibdev, smc_ib_global_event_handler); @@ -602,9 +613,9 @@ static void smc_ib_remove_dev(struct ib_device *ibdev, void *client_data) { struct smc_ib_device *smcibdev = client_data; - spin_lock(&smc_ib_devices.lock); + mutex_lock(&smc_ib_devices.mutex); list_del_init(&smcibdev->list); /* remove from smc_ib_devices */ - spin_unlock(&smc_ib_devices.lock); + mutex_unlock(&smc_ib_devices.mutex); pr_warn_ratelimited("smc: removing ib device %s\n", smcibdev->ibdev->name); smc_smcr_terminate_all(smcibdev); diff --git a/net/smc/smc_ib.h b/net/smc/smc_ib.h index e6a696ae15f3..2ce481187dd0 100644 --- a/net/smc/smc_ib.h +++ b/net/smc/smc_ib.h @@ -14,6 +14,7 @@ #include <linux/interrupt.h> #include <linux/if_ether.h> +#include <linux/mutex.h> #include <linux/wait.h> #include <rdma/ib_verbs.h> #include <net/smc.h> @@ -25,7 +26,7 @@ struct smc_ib_devices { /* list of smc ib devices definition */ struct list_head list; - spinlock_t lock; /* protects list of smc ib devices */ + struct mutex mutex; /* protects list of smc ib devices */ }; extern struct smc_ib_devices smc_ib_devices; /* list of smc ib devices */ @@ -51,6 +52,7 @@ struct smc_ib_device { /* ib-device infos for smc */ DECLARE_BITMAP(ports_going_away, SMC_MAX_PORTS); atomic_t lnk_cnt; /* number of links on ibdev */ wait_queue_head_t lnks_deleted; /* wait 4 removal of all links*/ + struct mutex mutex; /* protect dev setup+cleanup */ }; struct smc_buf_desc; diff --git a/net/smc/smc_ism.c b/net/smc/smc_ism.c index 91f85fc09fb8..998c525de785 100644 --- a/net/smc/smc_ism.c +++ b/net/smc/smc_ism.c @@ -7,6 +7,7 @@ */ #include <linux/spinlock.h> +#include <linux/mutex.h> #include <linux/slab.h> #include <asm/page.h> @@ -17,7 +18,7 @@ struct smcd_dev_list smcd_dev_list = { .list = LIST_HEAD_INIT(smcd_dev_list.list), - .lock = __SPIN_LOCK_UNLOCKED(smcd_dev_list.lock) + .mutex = __MUTEX_INITIALIZER(smcd_dev_list.mutex) }; /* Test if an ISM communication is possible. */ @@ -317,9 +318,9 @@ EXPORT_SYMBOL_GPL(smcd_alloc_dev); int smcd_register_dev(struct smcd_dev *smcd) { - spin_lock(&smcd_dev_list.lock); + mutex_lock(&smcd_dev_list.mutex); list_add_tail(&smcd->list, &smcd_dev_list.list); - spin_unlock(&smcd_dev_list.lock); + mutex_unlock(&smcd_dev_list.mutex); pr_warn_ratelimited("smc: adding smcd device %s with pnetid %.16s%s\n", dev_name(&smcd->dev), smcd->pnetid, @@ -333,9 +334,9 @@ void smcd_unregister_dev(struct smcd_dev *smcd) { pr_warn_ratelimited("smc: removing smcd device %s\n", dev_name(&smcd->dev)); - spin_lock(&smcd_dev_list.lock); + mutex_lock(&smcd_dev_list.mutex); list_del_init(&smcd->list); - spin_unlock(&smcd_dev_list.lock); + mutex_unlock(&smcd_dev_list.mutex); smcd->going_away = 1; smc_smcd_terminate_all(smcd); flush_workqueue(smcd->event_wq); diff --git a/net/smc/smc_ism.h b/net/smc/smc_ism.h index 4da946cbfa29..81cc4537efd3 100644 --- a/net/smc/smc_ism.h +++ b/net/smc/smc_ism.h @@ -10,12 +10,13 @@ #define SMCD_ISM_H #include <linux/uio.h> +#include <linux/mutex.h> #include "smc.h" struct smcd_dev_list { /* List of SMCD devices */ struct list_head list; - spinlock_t lock; /* Protects list of devices */ + struct mutex mutex; /* Protects list of devices */ }; extern struct smcd_dev_list smcd_dev_list; /* list of smcd devices */ diff --git a/net/smc/smc_llc.c b/net/smc/smc_llc.c index 391237b601fe..df5b0a6ea848 100644 --- a/net/smc/smc_llc.c +++ b/net/smc/smc_llc.c @@ -186,6 +186,26 @@ static inline void smc_llc_flow_qentry_set(struct smc_llc_flow *flow, flow->qentry = qentry; } +static void smc_llc_flow_parallel(struct smc_link_group *lgr, u8 flow_type, + struct smc_llc_qentry *qentry) +{ + u8 msg_type = qentry->msg.raw.hdr.common.type; + + if ((msg_type == SMC_LLC_ADD_LINK || msg_type == SMC_LLC_DELETE_LINK) && + flow_type != msg_type && !lgr->delayed_event) { + lgr->delayed_event = qentry; + return; + } + /* drop parallel or already-in-progress llc requests */ + if (flow_type != msg_type) + pr_warn_once("smc: SMC-R lg %*phN dropped parallel " + "LLC msg: msg %d flow %d role %d\n", + SMC_LGR_ID_SIZE, &lgr->id, + qentry->msg.raw.hdr.common.type, + flow_type, lgr->role); + kfree(qentry); +} + /* try to start a new llc flow, initiated by an incoming llc msg */ static bool smc_llc_flow_start(struct smc_llc_flow *flow, struct smc_llc_qentry *qentry) @@ -195,14 +215,7 @@ static bool smc_llc_flow_start(struct smc_llc_flow *flow, spin_lock_bh(&lgr->llc_flow_lock); if (flow->type) { /* a flow is already active */ - if ((qentry->msg.raw.hdr.common.type == SMC_LLC_ADD_LINK || - qentry->msg.raw.hdr.common.type == SMC_LLC_DELETE_LINK) && - !lgr->delayed_event) { - lgr->delayed_event = qentry; - } else { - /* forget this llc request */ - kfree(qentry); - } + smc_llc_flow_parallel(lgr, flow->type, qentry); spin_unlock_bh(&lgr->llc_flow_lock); return false; } @@ -222,8 +235,8 @@ static bool smc_llc_flow_start(struct smc_llc_flow *flow, } if (qentry == lgr->delayed_event) lgr->delayed_event = NULL; - spin_unlock_bh(&lgr->llc_flow_lock); smc_llc_flow_qentry_set(flow, qentry); + spin_unlock_bh(&lgr->llc_flow_lock); return true; } @@ -251,11 +264,11 @@ again: return 0; } spin_unlock_bh(&lgr->llc_flow_lock); - rc = wait_event_interruptible_timeout(lgr->llc_waiter, - (lgr->llc_flow_lcl.type == SMC_LLC_FLOW_NONE && - (lgr->llc_flow_rmt.type == SMC_LLC_FLOW_NONE || - lgr->llc_flow_rmt.type == allowed_remote)), - SMC_LLC_WAIT_TIME); + rc = wait_event_timeout(lgr->llc_flow_waiter, (list_empty(&lgr->list) || + (lgr->llc_flow_lcl.type == SMC_LLC_FLOW_NONE && + (lgr->llc_flow_rmt.type == SMC_LLC_FLOW_NONE || + lgr->llc_flow_rmt.type == allowed_remote))), + SMC_LLC_WAIT_TIME * 10); if (!rc) return -ETIMEDOUT; goto again; @@ -272,7 +285,7 @@ void smc_llc_flow_stop(struct smc_link_group *lgr, struct smc_llc_flow *flow) flow == &lgr->llc_flow_lcl) schedule_work(&lgr->llc_event_work); else - wake_up_interruptible(&lgr->llc_waiter); + wake_up(&lgr->llc_flow_waiter); } /* lnk is optional and used for early wakeup when link goes down, useful in @@ -283,26 +296,32 @@ struct smc_llc_qentry *smc_llc_wait(struct smc_link_group *lgr, int time_out, u8 exp_msg) { struct smc_llc_flow *flow = &lgr->llc_flow_lcl; + u8 rcv_msg; - wait_event_interruptible_timeout(lgr->llc_waiter, - (flow->qentry || - (lnk && !smc_link_usable(lnk)) || - list_empty(&lgr->list)), - time_out); + wait_event_timeout(lgr->llc_msg_waiter, + (flow->qentry || + (lnk && !smc_link_usable(lnk)) || + list_empty(&lgr->list)), + time_out); if (!flow->qentry || (lnk && !smc_link_usable(lnk)) || list_empty(&lgr->list)) { smc_llc_flow_qentry_del(flow); goto out; } - if (exp_msg && flow->qentry->msg.raw.hdr.common.type != exp_msg) { + rcv_msg = flow->qentry->msg.raw.hdr.common.type; + if (exp_msg && rcv_msg != exp_msg) { if (exp_msg == SMC_LLC_ADD_LINK && - flow->qentry->msg.raw.hdr.common.type == - SMC_LLC_DELETE_LINK) { + rcv_msg == SMC_LLC_DELETE_LINK) { /* flow_start will delay the unexpected msg */ smc_llc_flow_start(&lgr->llc_flow_lcl, smc_llc_flow_qentry_clr(flow)); return NULL; } + pr_warn_once("smc: SMC-R lg %*phN dropped unexpected LLC msg: " + "msg %d exp %d flow %d role %d flags %x\n", + SMC_LGR_ID_SIZE, &lgr->id, rcv_msg, exp_msg, + flow->type, lgr->role, + flow->qentry->msg.raw.hdr.flags); smc_llc_flow_qentry_del(flow); } out: @@ -409,7 +428,7 @@ static int smc_llc_send_confirm_rkey(struct smc_link *send_link, rtok_ix = 1; for (i = 0; i < SMC_LINKS_PER_LGR_MAX; i++) { link = &send_link->lgr->lnk[i]; - if (link->state == SMC_LNK_ACTIVE && link != send_link) { + if (smc_link_active(link) && link != send_link) { rkeyllc->rtoken[rtok_ix].link_id = link->link_id; rkeyllc->rtoken[rtok_ix].rmb_key = htonl(rmb_desc->mr_rx[link->link_idx]->rkey); @@ -876,6 +895,36 @@ out: return rc; } +/* as an SMC client, invite server to start the add_link processing */ +static void smc_llc_cli_add_link_invite(struct smc_link *link, + struct smc_llc_qentry *qentry) +{ + struct smc_link_group *lgr = smc_get_lgr(link); + struct smc_init_info ini; + + if (lgr->type == SMC_LGR_SYMMETRIC || + lgr->type == SMC_LGR_ASYMMETRIC_PEER) + goto out; + + ini.vlan_id = lgr->vlan_id; + smc_pnet_find_alt_roce(lgr, &ini, link->smcibdev); + if (!ini.ib_dev) + goto out; + + smc_llc_send_add_link(link, ini.ib_dev->mac[ini.ib_port - 1], + ini.ib_gid, NULL, SMC_LLC_REQ); +out: + kfree(qentry); +} + +static bool smc_llc_is_local_add_link(union smc_llc_msg *llc) +{ + if (llc->raw.hdr.common.type == SMC_LLC_ADD_LINK && + !llc->add_link.qp_mtu && !llc->add_link.link_num) + return true; + return false; +} + static void smc_llc_process_cli_add_link(struct smc_link_group *lgr) { struct smc_llc_qentry *qentry; @@ -883,7 +932,10 @@ static void smc_llc_process_cli_add_link(struct smc_link_group *lgr) qentry = smc_llc_flow_qentry_clr(&lgr->llc_flow_lcl); mutex_lock(&lgr->llc_conf_mutex); - smc_llc_cli_add_link(qentry->link, qentry); + if (smc_llc_is_local_add_link(&qentry->msg)) + smc_llc_cli_add_link_invite(qentry->link, qentry); + else + smc_llc_cli_add_link(qentry->link, qentry); mutex_unlock(&lgr->llc_conf_mutex); } @@ -892,7 +944,7 @@ static int smc_llc_active_link_count(struct smc_link_group *lgr) int i, link_count = 0; for (i = 0; i < SMC_LINKS_PER_LGR_MAX; i++) { - if (!smc_link_usable(&lgr->lnk[i])) + if (!smc_link_active(&lgr->lnk[i])) continue; link_count++; } @@ -1032,12 +1084,14 @@ static int smc_llc_srv_conf_link(struct smc_link *link, if (rc) return -ENOLINK; /* receive CONFIRM LINK response over the RoCE fabric */ - qentry = smc_llc_wait(lgr, link, SMC_LLC_WAIT_FIRST_TIME, - SMC_LLC_CONFIRM_LINK); - if (!qentry) { + qentry = smc_llc_wait(lgr, link, SMC_LLC_WAIT_FIRST_TIME, 0); + if (!qentry || + qentry->msg.raw.hdr.common.type != SMC_LLC_CONFIRM_LINK) { /* send DELETE LINK */ smc_llc_send_delete_link(link, link_new->link_id, SMC_LLC_REQ, false, SMC_LLC_DEL_LOST_PATH); + if (qentry) + smc_llc_flow_qentry_del(&lgr->llc_flow_lcl); return -ENOLINK; } smc_llc_save_peer_uid(qentry); @@ -1139,14 +1193,14 @@ static void smc_llc_process_srv_add_link(struct smc_link_group *lgr) mutex_unlock(&lgr->llc_conf_mutex); } -/* enqueue a local add_link req to trigger a new add_link flow, only as SERV */ -void smc_llc_srv_add_link_local(struct smc_link *link) +/* enqueue a local add_link req to trigger a new add_link flow */ +void smc_llc_add_link_local(struct smc_link *link) { struct smc_llc_msg_add_link add_llc = {0}; add_llc.hd.length = sizeof(add_llc); add_llc.hd.common.type = SMC_LLC_ADD_LINK; - /* no dev and port needed, we as server ignore client data anyway */ + /* no dev and port needed */ smc_llc_enqueue(link, (union smc_llc_msg *)&add_llc); } @@ -1222,8 +1276,8 @@ static void smc_llc_process_cli_delete_link(struct smc_link_group *lgr) smc_llc_send_message(lnk, &qentry->msg); /* response */ if (smc_link_downing(&lnk_del->state)) { - smc_switch_conns(lgr, lnk_del, false); - smc_wr_tx_wait_no_pending_sends(lnk_del); + if (smc_switch_conns(lgr, lnk_del, false)) + smc_wr_tx_wait_no_pending_sends(lnk_del); } smcr_link_clear(lnk_del, true); @@ -1297,8 +1351,8 @@ static void smc_llc_process_srv_delete_link(struct smc_link_group *lgr) goto out; /* asymmetric link already deleted */ if (smc_link_downing(&lnk_del->state)) { - smc_switch_conns(lgr, lnk_del, false); - smc_wr_tx_wait_no_pending_sends(lnk_del); + if (smc_switch_conns(lgr, lnk_del, false)) + smc_wr_tx_wait_no_pending_sends(lnk_del); } if (!list_empty(&lgr->list)) { /* qentry is either a request from peer (send it back to @@ -1326,7 +1380,7 @@ static void smc_llc_process_srv_delete_link(struct smc_link_group *lgr) if (lgr->type == SMC_LGR_SINGLE && !list_empty(&lgr->list)) { /* trigger setup of asymm alt link */ - smc_llc_srv_add_link_local(lnk); + smc_llc_add_link_local(lnk); } out: mutex_unlock(&lgr->llc_conf_mutex); @@ -1455,11 +1509,22 @@ static void smc_llc_event_handler(struct smc_llc_qentry *qentry) if (list_empty(&lgr->list)) goto out; /* lgr is terminating */ if (lgr->role == SMC_CLNT) { - if (lgr->llc_flow_lcl.type == SMC_LLC_FLOW_ADD_LINK) { + if (smc_llc_is_local_add_link(llc)) { + if (lgr->llc_flow_lcl.type == + SMC_LLC_FLOW_ADD_LINK) + break; /* add_link in progress */ + if (smc_llc_flow_start(&lgr->llc_flow_lcl, + qentry)) { + schedule_work(&lgr->llc_add_link_work); + } + return; + } + if (lgr->llc_flow_lcl.type == SMC_LLC_FLOW_ADD_LINK && + !lgr->llc_flow_lcl.qentry) { /* a flow is waiting for this message */ smc_llc_flow_qentry_set(&lgr->llc_flow_lcl, qentry); - wake_up_interruptible(&lgr->llc_waiter); + wake_up(&lgr->llc_msg_waiter); } else if (smc_llc_flow_start(&lgr->llc_flow_lcl, qentry)) { schedule_work(&lgr->llc_add_link_work); @@ -1474,33 +1539,18 @@ static void smc_llc_event_handler(struct smc_llc_qentry *qentry) if (lgr->llc_flow_lcl.type != SMC_LLC_FLOW_NONE) { /* a flow is waiting for this message */ smc_llc_flow_qentry_set(&lgr->llc_flow_lcl, qentry); - wake_up_interruptible(&lgr->llc_waiter); + wake_up(&lgr->llc_msg_waiter); return; } break; case SMC_LLC_DELETE_LINK: - if (lgr->role == SMC_CLNT) { - /* server requests to delete this link, send response */ - if (lgr->llc_flow_lcl.type != SMC_LLC_FLOW_NONE) { - /* DEL LINK REQ during ADD LINK SEQ */ - smc_llc_flow_qentry_set(&lgr->llc_flow_lcl, - qentry); - wake_up_interruptible(&lgr->llc_waiter); - } else if (smc_llc_flow_start(&lgr->llc_flow_lcl, - qentry)) { - schedule_work(&lgr->llc_del_link_work); - } - } else { - if (lgr->llc_flow_lcl.type == SMC_LLC_FLOW_ADD_LINK && - !lgr->llc_flow_lcl.qentry) { - /* DEL LINK REQ during ADD LINK SEQ */ - smc_llc_flow_qentry_set(&lgr->llc_flow_lcl, - qentry); - wake_up_interruptible(&lgr->llc_waiter); - } else if (smc_llc_flow_start(&lgr->llc_flow_lcl, - qentry)) { - schedule_work(&lgr->llc_del_link_work); - } + if (lgr->llc_flow_lcl.type == SMC_LLC_FLOW_ADD_LINK && + !lgr->llc_flow_lcl.qentry) { + /* DEL LINK REQ during ADD LINK SEQ */ + smc_llc_flow_qentry_set(&lgr->llc_flow_lcl, qentry); + wake_up(&lgr->llc_msg_waiter); + } else if (smc_llc_flow_start(&lgr->llc_flow_lcl, qentry)) { + schedule_work(&lgr->llc_del_link_work); } return; case SMC_LLC_CONFIRM_RKEY: @@ -1566,23 +1616,30 @@ again: static void smc_llc_rx_response(struct smc_link *link, struct smc_llc_qentry *qentry) { + enum smc_llc_flowtype flowtype = link->lgr->llc_flow_lcl.type; + struct smc_llc_flow *flow = &link->lgr->llc_flow_lcl; u8 llc_type = qentry->msg.raw.hdr.common.type; switch (llc_type) { case SMC_LLC_TEST_LINK: - if (link->state == SMC_LNK_ACTIVE) + if (smc_link_active(link)) complete(&link->llc_testlink_resp); break; case SMC_LLC_ADD_LINK: - case SMC_LLC_DELETE_LINK: - case SMC_LLC_CONFIRM_LINK: case SMC_LLC_ADD_LINK_CONT: + case SMC_LLC_CONFIRM_LINK: + if (flowtype != SMC_LLC_FLOW_ADD_LINK || flow->qentry) + break; /* drop out-of-flow response */ + goto assign; + case SMC_LLC_DELETE_LINK: + if (flowtype != SMC_LLC_FLOW_DEL_LINK || flow->qentry) + break; /* drop out-of-flow response */ + goto assign; case SMC_LLC_CONFIRM_RKEY: case SMC_LLC_DELETE_RKEY: - /* assign responses to the local flow, we requested them */ - smc_llc_flow_qentry_set(&link->lgr->llc_flow_lcl, qentry); - wake_up_interruptible(&link->lgr->llc_waiter); - return; + if (flowtype != SMC_LLC_FLOW_RKEY || flow->qentry) + break; /* drop out-of-flow response */ + goto assign; case SMC_LLC_CONFIRM_RKEY_CONT: /* not used because max links is 3 */ break; @@ -1591,6 +1648,11 @@ static void smc_llc_rx_response(struct smc_link *link, break; } kfree(qentry); + return; +assign: + /* assign responses to the local flow, we requested them */ + smc_llc_flow_qentry_set(&link->lgr->llc_flow_lcl, qentry); + wake_up(&link->lgr->llc_msg_waiter); } static void smc_llc_enqueue(struct smc_link *link, union smc_llc_msg *llc) @@ -1616,7 +1678,7 @@ static void smc_llc_enqueue(struct smc_link *link, union smc_llc_msg *llc) spin_lock_irqsave(&lgr->llc_event_q_lock, flags); list_add_tail(&qentry->list, &lgr->llc_event_q); spin_unlock_irqrestore(&lgr->llc_event_q_lock, flags); - schedule_work(&link->lgr->llc_event_work); + schedule_work(&lgr->llc_event_work); } /* copy received msg and add it to the event queue */ @@ -1644,7 +1706,7 @@ static void smc_llc_testlink_work(struct work_struct *work) u8 user_data[16] = { 0 }; int rc; - if (link->state != SMC_LNK_ACTIVE) + if (!smc_link_active(link)) return; /* don't reschedule worker */ expire_time = link->wr_rx_tstamp + link->llc_testlink_time; if (time_is_after_jiffies(expire_time)) { @@ -1656,7 +1718,7 @@ static void smc_llc_testlink_work(struct work_struct *work) /* receive TEST LINK response over RoCE fabric */ rc = wait_for_completion_interruptible_timeout(&link->llc_testlink_resp, SMC_LLC_WAIT_TIME); - if (link->state != SMC_LNK_ACTIVE) + if (!smc_link_active(link)) return; /* link state changed */ if (rc <= 0) { smcr_link_down_cond_sched(link); @@ -1677,7 +1739,8 @@ void smc_llc_lgr_init(struct smc_link_group *lgr, struct smc_sock *smc) INIT_LIST_HEAD(&lgr->llc_event_q); spin_lock_init(&lgr->llc_event_q_lock); spin_lock_init(&lgr->llc_flow_lock); - init_waitqueue_head(&lgr->llc_waiter); + init_waitqueue_head(&lgr->llc_flow_waiter); + init_waitqueue_head(&lgr->llc_msg_waiter); mutex_init(&lgr->llc_conf_mutex); lgr->llc_testlink_time = net->ipv4.sysctl_tcp_keepalive_time; } @@ -1686,7 +1749,8 @@ void smc_llc_lgr_init(struct smc_link_group *lgr, struct smc_sock *smc) void smc_llc_lgr_clear(struct smc_link_group *lgr) { smc_llc_event_flush(lgr); - wake_up_interruptible_all(&lgr->llc_waiter); + wake_up_all(&lgr->llc_flow_waiter); + wake_up_all(&lgr->llc_msg_waiter); cancel_work_sync(&lgr->llc_event_work); cancel_work_sync(&lgr->llc_add_link_work); cancel_work_sync(&lgr->llc_del_link_work); diff --git a/net/smc/smc_llc.h b/net/smc/smc_llc.h index a5d2fe3eea61..cc00a2ec4e92 100644 --- a/net/smc/smc_llc.h +++ b/net/smc/smc_llc.h @@ -103,7 +103,7 @@ void smc_llc_send_link_delete_all(struct smc_link_group *lgr, bool ord, u32 rsn); int smc_llc_cli_add_link(struct smc_link *link, struct smc_llc_qentry *qentry); int smc_llc_srv_add_link(struct smc_link *link); -void smc_llc_srv_add_link_local(struct smc_link *link); +void smc_llc_add_link_local(struct smc_link *link); int smc_llc_init(void) __init; #endif /* SMC_LLC_H */ diff --git a/net/smc/smc_pnet.c b/net/smc/smc_pnet.c index 014d91b9778e..30e5fac7034e 100644 --- a/net/smc/smc_pnet.c +++ b/net/smc/smc_pnet.c @@ -12,6 +12,7 @@ #include <linux/module.h> #include <linux/list.h> #include <linux/ctype.h> +#include <linux/mutex.h> #include <net/netlink.h> #include <net/genetlink.h> @@ -129,7 +130,7 @@ static int smc_pnet_remove_by_pnetid(struct net *net, char *pnet_name) return rc; /* remove ib devices */ - spin_lock(&smc_ib_devices.lock); + mutex_lock(&smc_ib_devices.mutex); list_for_each_entry(ibdev, &smc_ib_devices.list, list) { for (ibport = 0; ibport < SMC_MAX_PORTS; ibport++) { if (ibdev->pnetid_by_user[ibport] && @@ -149,9 +150,9 @@ static int smc_pnet_remove_by_pnetid(struct net *net, char *pnet_name) } } } - spin_unlock(&smc_ib_devices.lock); + mutex_unlock(&smc_ib_devices.mutex); /* remove smcd devices */ - spin_lock(&smcd_dev_list.lock); + mutex_lock(&smcd_dev_list.mutex); list_for_each_entry(smcd_dev, &smcd_dev_list.list, list) { if (smcd_dev->pnetid_by_user && (!pnet_name || @@ -165,7 +166,7 @@ static int smc_pnet_remove_by_pnetid(struct net *net, char *pnet_name) rc = 0; } } - spin_unlock(&smcd_dev_list.lock); + mutex_unlock(&smcd_dev_list.mutex); return rc; } @@ -240,14 +241,14 @@ static bool smc_pnet_apply_ib(struct smc_ib_device *ib_dev, u8 ib_port, u8 pnet_null[SMC_MAX_PNETID_LEN] = {0}; bool applied = false; - spin_lock(&smc_ib_devices.lock); + mutex_lock(&smc_ib_devices.mutex); if (smc_pnet_match(ib_dev->pnetid[ib_port - 1], pnet_null)) { memcpy(ib_dev->pnetid[ib_port - 1], pnet_name, SMC_MAX_PNETID_LEN); ib_dev->pnetid_by_user[ib_port - 1] = true; applied = true; } - spin_unlock(&smc_ib_devices.lock); + mutex_unlock(&smc_ib_devices.mutex); return applied; } @@ -258,13 +259,13 @@ static bool smc_pnet_apply_smcd(struct smcd_dev *smcd_dev, char *pnet_name) u8 pnet_null[SMC_MAX_PNETID_LEN] = {0}; bool applied = false; - spin_lock(&smcd_dev_list.lock); + mutex_lock(&smcd_dev_list.mutex); if (smc_pnet_match(smcd_dev->pnetid, pnet_null)) { memcpy(smcd_dev->pnetid, pnet_name, SMC_MAX_PNETID_LEN); smcd_dev->pnetid_by_user = true; applied = true; } - spin_unlock(&smcd_dev_list.lock); + mutex_unlock(&smcd_dev_list.mutex); return applied; } @@ -300,7 +301,7 @@ static struct smc_ib_device *smc_pnet_find_ib(char *ib_name) { struct smc_ib_device *ibdev; - spin_lock(&smc_ib_devices.lock); + mutex_lock(&smc_ib_devices.mutex); list_for_each_entry(ibdev, &smc_ib_devices.list, list) { if (!strncmp(ibdev->ibdev->name, ib_name, sizeof(ibdev->ibdev->name)) || @@ -311,7 +312,7 @@ static struct smc_ib_device *smc_pnet_find_ib(char *ib_name) } ibdev = NULL; out: - spin_unlock(&smc_ib_devices.lock); + mutex_unlock(&smc_ib_devices.mutex); return ibdev; } @@ -320,7 +321,7 @@ static struct smcd_dev *smc_pnet_find_smcd(char *smcd_name) { struct smcd_dev *smcd_dev; - spin_lock(&smcd_dev_list.lock); + mutex_lock(&smcd_dev_list.mutex); list_for_each_entry(smcd_dev, &smcd_dev_list.list, list) { if (!strncmp(dev_name(&smcd_dev->dev), smcd_name, IB_DEVICE_NAME_MAX - 1)) @@ -328,7 +329,7 @@ static struct smcd_dev *smc_pnet_find_smcd(char *smcd_name) } smcd_dev = NULL; out: - spin_unlock(&smcd_dev_list.lock); + mutex_unlock(&smcd_dev_list.mutex); return smcd_dev; } @@ -825,7 +826,7 @@ static void _smc_pnet_find_roce_by_pnetid(u8 *pnet_id, int i; ini->ib_dev = NULL; - spin_lock(&smc_ib_devices.lock); + mutex_lock(&smc_ib_devices.mutex); list_for_each_entry(ibdev, &smc_ib_devices.list, list) { if (ibdev == known_dev) continue; @@ -844,7 +845,7 @@ static void _smc_pnet_find_roce_by_pnetid(u8 *pnet_id, } } out: - spin_unlock(&smc_ib_devices.lock); + mutex_unlock(&smc_ib_devices.mutex); } /* find alternate roce device with same pnet_id and vlan_id */ @@ -863,7 +864,7 @@ static void smc_pnet_find_rdma_dev(struct net_device *netdev, { struct smc_ib_device *ibdev; - spin_lock(&smc_ib_devices.lock); + mutex_lock(&smc_ib_devices.mutex); list_for_each_entry(ibdev, &smc_ib_devices.list, list) { struct net_device *ndev; int i; @@ -888,7 +889,7 @@ static void smc_pnet_find_rdma_dev(struct net_device *netdev, } } } - spin_unlock(&smc_ib_devices.lock); + mutex_unlock(&smc_ib_devices.mutex); } /* Determine the corresponding IB device port based on the hardware PNETID. @@ -924,7 +925,7 @@ static void smc_pnet_find_ism_by_pnetid(struct net_device *ndev, smc_pnet_find_ndev_pnetid_by_table(ndev, ndev_pnetid)) return; /* pnetid could not be determined */ - spin_lock(&smcd_dev_list.lock); + mutex_lock(&smcd_dev_list.mutex); list_for_each_entry(ismdev, &smcd_dev_list.list, list) { if (smc_pnet_match(ismdev->pnetid, ndev_pnetid) && !ismdev->going_away) { @@ -932,7 +933,7 @@ static void smc_pnet_find_ism_by_pnetid(struct net_device *ndev, break; } } - spin_unlock(&smcd_dev_list.lock); + mutex_unlock(&smcd_dev_list.mutex); } /* PNET table analysis for a given sock: diff --git a/net/smc/smc_wr.c b/net/smc/smc_wr.c index 7239ba9b99dc..1e23cdd41eb1 100644 --- a/net/smc/smc_wr.c +++ b/net/smc/smc_wr.c @@ -169,6 +169,8 @@ void smc_wr_tx_cq_handler(struct ib_cq *ib_cq, void *cq_context) static inline int smc_wr_tx_get_free_slot_index(struct smc_link *link, u32 *idx) { *idx = link->wr_tx_cnt; + if (!smc_link_usable(link)) + return -ENOLINK; for_each_clear_bit(*idx, link->wr_tx_mask, link->wr_tx_cnt) { if (!test_and_set_bit(*idx, link->wr_tx_mask)) return 0; @@ -560,15 +562,15 @@ void smc_wr_free_link(struct smc_link *lnk) { struct ib_device *ibdev; + if (!lnk->smcibdev) + return; + ibdev = lnk->smcibdev->ibdev; + if (smc_wr_tx_wait_no_pending_sends(lnk)) memset(lnk->wr_tx_mask, 0, BITS_TO_LONGS(SMC_WR_BUF_CNT) * sizeof(*lnk->wr_tx_mask)); - if (!lnk->smcibdev) - return; - ibdev = lnk->smcibdev->ibdev; - if (lnk->wr_rx_dma_addr) { ib_dma_unmap_single(ibdev, lnk->wr_rx_dma_addr, SMC_WR_BUF_SIZE * lnk->wr_rx_cnt, diff --git a/net/sunrpc/rpc_pipe.c b/net/sunrpc/rpc_pipe.c index 39e14d5edaf1..e9d0953522f0 100644 --- a/net/sunrpc/rpc_pipe.c +++ b/net/sunrpc/rpc_pipe.c @@ -1317,6 +1317,7 @@ rpc_gssd_dummy_populate(struct dentry *root, struct rpc_pipe *pipe_data) q.len = strlen(gssd_dummy_clnt_dir[0].name); clnt_dentry = d_hash_and_lookup(gssd_dentry, &q); if (!clnt_dentry) { + __rpc_depopulate(gssd_dentry, gssd_dummy_clnt_dir, 0, 1); pipe_dentry = ERR_PTR(-ENOENT); goto out; } diff --git a/net/sunrpc/svcsock.c b/net/sunrpc/svcsock.c index 5c4ec9386f81..c537272f9c7e 100644 --- a/net/sunrpc/svcsock.c +++ b/net/sunrpc/svcsock.c @@ -44,6 +44,7 @@ #include <net/tcp.h> #include <net/tcp_states.h> #include <linux/uaccess.h> +#include <linux/highmem.h> #include <asm/ioctls.h> #include <linux/sunrpc/types.h> diff --git a/net/sunrpc/xdr.c b/net/sunrpc/xdr.c index 6f7d82fb1eb0..be11d672b5b9 100644 --- a/net/sunrpc/xdr.c +++ b/net/sunrpc/xdr.c @@ -1118,6 +1118,7 @@ xdr_buf_subsegment(struct xdr_buf *buf, struct xdr_buf *subbuf, base = 0; } else { base -= buf->head[0].iov_len; + subbuf->head[0].iov_base = buf->head[0].iov_base; subbuf->head[0].iov_len = 0; } @@ -1130,6 +1131,8 @@ xdr_buf_subsegment(struct xdr_buf *buf, struct xdr_buf *subbuf, base = 0; } else { base -= buf->page_len; + subbuf->pages = buf->pages; + subbuf->page_base = 0; subbuf->page_len = 0; } @@ -1141,6 +1144,7 @@ xdr_buf_subsegment(struct xdr_buf *buf, struct xdr_buf *subbuf, base = 0; } else { base -= buf->tail[0].iov_len; + subbuf->tail[0].iov_base = buf->tail[0].iov_base; subbuf->tail[0].iov_len = 0; } diff --git a/net/sunrpc/xprtrdma/frwr_ops.c b/net/sunrpc/xprtrdma/frwr_ops.c index ef997880e17a..b647562a26dd 100644 --- a/net/sunrpc/xprtrdma/frwr_ops.c +++ b/net/sunrpc/xprtrdma/frwr_ops.c @@ -367,7 +367,7 @@ static void frwr_wc_fastreg(struct ib_cq *cq, struct ib_wc *wc) trace_xprtrdma_wc_fastreg(wc, frwr); /* The MR will get recycled when the associated req is retransmitted */ - rpcrdma_flush_disconnect(cq, wc); + rpcrdma_flush_disconnect(cq->cq_context, wc); } /** @@ -452,7 +452,7 @@ static void frwr_wc_localinv(struct ib_cq *cq, struct ib_wc *wc) trace_xprtrdma_wc_li(wc, frwr); __frwr_release_mr(wc, mr); - rpcrdma_flush_disconnect(cq, wc); + rpcrdma_flush_disconnect(cq->cq_context, wc); } /** @@ -474,7 +474,7 @@ static void frwr_wc_localinv_wake(struct ib_cq *cq, struct ib_wc *wc) __frwr_release_mr(wc, mr); complete(&frwr->fr_linv_done); - rpcrdma_flush_disconnect(cq, wc); + rpcrdma_flush_disconnect(cq->cq_context, wc); } /** @@ -582,7 +582,7 @@ static void frwr_wc_localinv_done(struct ib_cq *cq, struct ib_wc *wc) smp_rmb(); rpcrdma_complete_rqst(rep); - rpcrdma_flush_disconnect(cq, wc); + rpcrdma_flush_disconnect(cq->cq_context, wc); } /** diff --git a/net/sunrpc/xprtrdma/rpc_rdma.c b/net/sunrpc/xprtrdma/rpc_rdma.c index 2081c8fbfa48..453bacc99907 100644 --- a/net/sunrpc/xprtrdma/rpc_rdma.c +++ b/net/sunrpc/xprtrdma/rpc_rdma.c @@ -71,7 +71,7 @@ static unsigned int rpcrdma_max_call_header_size(unsigned int maxsegs) size = RPCRDMA_HDRLEN_MIN; /* Maximum Read list size */ - size = maxsegs * rpcrdma_readchunk_maxsz * sizeof(__be32); + size += maxsegs * rpcrdma_readchunk_maxsz * sizeof(__be32); /* Minimal Read chunk size */ size += sizeof(__be32); /* segment count */ @@ -94,7 +94,7 @@ static unsigned int rpcrdma_max_reply_header_size(unsigned int maxsegs) size = RPCRDMA_HDRLEN_MIN; /* Maximum Write list size */ - size = sizeof(__be32); /* segment count */ + size += sizeof(__be32); /* segment count */ size += maxsegs * rpcrdma_segment_maxsz * sizeof(__be32); size += sizeof(__be32); /* list discriminator */ @@ -1349,8 +1349,7 @@ rpcrdma_decode_error(struct rpcrdma_xprt *r_xprt, struct rpcrdma_rep *rep, be32_to_cpup(p), be32_to_cpu(rep->rr_xid)); } - r_xprt->rx_stats.bad_reply_count++; - return -EREMOTEIO; + return -EIO; } /* Perform XID lookup, reconstruction of the RPC reply, and @@ -1387,13 +1386,11 @@ out: spin_unlock(&xprt->queue_lock); return; -/* If the incoming reply terminated a pending RPC, the next - * RPC call will post a replacement receive buffer as it is - * being marshaled. - */ out_badheader: trace_xprtrdma_reply_hdr(rep); r_xprt->rx_stats.bad_reply_count++; + rqst->rq_task->tk_status = status; + status = 0; goto out; } diff --git a/net/sunrpc/xprtrdma/transport.c b/net/sunrpc/xprtrdma/transport.c index 0c4af7f5e241..053c8ab1265a 100644 --- a/net/sunrpc/xprtrdma/transport.c +++ b/net/sunrpc/xprtrdma/transport.c @@ -242,13 +242,18 @@ xprt_rdma_connect_worker(struct work_struct *work) rc = rpcrdma_xprt_connect(r_xprt); xprt_clear_connecting(xprt); - if (r_xprt->rx_ep && r_xprt->rx_ep->re_connect_status > 0) { + if (!rc) { xprt->connect_cookie++; xprt->stat.connect_count++; xprt->stat.connect_time += (long)jiffies - xprt->stat.connect_start; xprt_set_connected(xprt); rc = -EAGAIN; + } else { + /* Force a call to xprt_rdma_close to clean up */ + spin_lock(&xprt->transport_lock); + set_bit(XPRT_CLOSE_WAIT, &xprt->state); + spin_unlock(&xprt->transport_lock); } xprt_wake_pending_tasks(xprt, rc); } diff --git a/net/sunrpc/xprtrdma/verbs.c b/net/sunrpc/xprtrdma/verbs.c index 2ae348377806..75c646743df3 100644 --- a/net/sunrpc/xprtrdma/verbs.c +++ b/net/sunrpc/xprtrdma/verbs.c @@ -84,7 +84,8 @@ static void rpcrdma_rep_destroy(struct rpcrdma_rep *rep); static void rpcrdma_reps_unmap(struct rpcrdma_xprt *r_xprt); static void rpcrdma_mrs_create(struct rpcrdma_xprt *r_xprt); static void rpcrdma_mrs_destroy(struct rpcrdma_xprt *r_xprt); -static int rpcrdma_ep_destroy(struct rpcrdma_ep *ep); +static void rpcrdma_ep_get(struct rpcrdma_ep *ep); +static int rpcrdma_ep_put(struct rpcrdma_ep *ep); static struct rpcrdma_regbuf * rpcrdma_regbuf_alloc(size_t size, enum dma_data_direction direction, gfp_t flags); @@ -97,7 +98,8 @@ static void rpcrdma_regbuf_free(struct rpcrdma_regbuf *rb); */ static void rpcrdma_xprt_drain(struct rpcrdma_xprt *r_xprt) { - struct rdma_cm_id *id = r_xprt->rx_ep->re_id; + struct rpcrdma_ep *ep = r_xprt->rx_ep; + struct rdma_cm_id *id = ep->re_id; /* Flush Receives, then wait for deferred Reply work * to complete. @@ -108,6 +110,8 @@ static void rpcrdma_xprt_drain(struct rpcrdma_xprt *r_xprt) * local invalidations. */ ib_drain_sq(id->qp); + + rpcrdma_ep_put(ep); } /** @@ -126,23 +130,27 @@ static void rpcrdma_qp_event_handler(struct ib_event *event, void *context) trace_xprtrdma_qp_event(ep, event); } +/* Ensure xprt_force_disconnect() is invoked exactly once when a + * connection is closed or lost. (The important thing is it needs + * to be invoked "at least" once). + */ +static void rpcrdma_force_disconnect(struct rpcrdma_ep *ep) +{ + if (atomic_add_unless(&ep->re_force_disconnect, 1, 1)) + xprt_force_disconnect(ep->re_xprt); +} + /** * rpcrdma_flush_disconnect - Disconnect on flushed completion - * @cq: completion queue + * @r_xprt: transport to disconnect * @wc: work completion entry * * Must be called in process context. */ -void rpcrdma_flush_disconnect(struct ib_cq *cq, struct ib_wc *wc) +void rpcrdma_flush_disconnect(struct rpcrdma_xprt *r_xprt, struct ib_wc *wc) { - struct rpcrdma_xprt *r_xprt = cq->cq_context; - struct rpc_xprt *xprt = &r_xprt->rx_xprt; - - if (wc->status != IB_WC_SUCCESS && - r_xprt->rx_ep->re_connect_status == 1) { - r_xprt->rx_ep->re_connect_status = -ECONNABORTED; - xprt_force_disconnect(xprt); - } + if (wc->status != IB_WC_SUCCESS) + rpcrdma_force_disconnect(r_xprt->rx_ep); } /** @@ -156,11 +164,12 @@ static void rpcrdma_wc_send(struct ib_cq *cq, struct ib_wc *wc) struct ib_cqe *cqe = wc->wr_cqe; struct rpcrdma_sendctx *sc = container_of(cqe, struct rpcrdma_sendctx, sc_cqe); + struct rpcrdma_xprt *r_xprt = cq->cq_context; /* WARNING: Only wr_cqe and status are reliable at this point */ trace_xprtrdma_wc_send(sc, wc); - rpcrdma_sendctx_put_locked((struct rpcrdma_xprt *)cq->cq_context, sc); - rpcrdma_flush_disconnect(cq, wc); + rpcrdma_sendctx_put_locked(r_xprt, sc); + rpcrdma_flush_disconnect(r_xprt, wc); } /** @@ -195,7 +204,7 @@ static void rpcrdma_wc_receive(struct ib_cq *cq, struct ib_wc *wc) return; out_flushed: - rpcrdma_flush_disconnect(cq, wc); + rpcrdma_flush_disconnect(r_xprt, wc); rpcrdma_rep_destroy(rep); } @@ -239,7 +248,6 @@ rpcrdma_cm_event_handler(struct rdma_cm_id *id, struct rdma_cm_event *event) { struct sockaddr *sap = (struct sockaddr *)&id->route.addr.dst_addr; struct rpcrdma_ep *ep = id->context; - struct rpc_xprt *xprt = ep->re_xprt; might_sleep(); @@ -263,10 +271,9 @@ rpcrdma_cm_event_handler(struct rdma_cm_id *id, struct rdma_cm_event *event) /* fall through */ case RDMA_CM_EVENT_ADDR_CHANGE: ep->re_connect_status = -ENODEV; - xprt_force_disconnect(xprt); goto disconnected; case RDMA_CM_EVENT_ESTABLISHED: - kref_get(&ep->re_kref); + rpcrdma_ep_get(ep); ep->re_connect_status = 1; rpcrdma_update_cm_private(ep, &event->param.conn); trace_xprtrdma_inline_thresh(ep); @@ -274,22 +281,24 @@ rpcrdma_cm_event_handler(struct rdma_cm_id *id, struct rdma_cm_event *event) break; case RDMA_CM_EVENT_CONNECT_ERROR: ep->re_connect_status = -ENOTCONN; - goto disconnected; + goto wake_connect_worker; case RDMA_CM_EVENT_UNREACHABLE: ep->re_connect_status = -ENETUNREACH; - goto disconnected; + goto wake_connect_worker; case RDMA_CM_EVENT_REJECTED: dprintk("rpcrdma: connection to %pISpc rejected: %s\n", sap, rdma_reject_msg(id, event->status)); ep->re_connect_status = -ECONNREFUSED; if (event->status == IB_CM_REJ_STALE_CONN) - ep->re_connect_status = -EAGAIN; - goto disconnected; + ep->re_connect_status = -ENOTCONN; +wake_connect_worker: + wake_up_all(&ep->re_connect_wait); + return 0; case RDMA_CM_EVENT_DISCONNECTED: ep->re_connect_status = -ECONNABORTED; disconnected: - xprt_force_disconnect(xprt); - return rpcrdma_ep_destroy(ep); + rpcrdma_force_disconnect(ep); + return rpcrdma_ep_put(ep); default: break; } @@ -345,7 +354,7 @@ out: return ERR_PTR(rc); } -static void rpcrdma_ep_put(struct kref *kref) +static void rpcrdma_ep_destroy(struct kref *kref) { struct rpcrdma_ep *ep = container_of(kref, struct rpcrdma_ep, re_kref); @@ -369,13 +378,18 @@ static void rpcrdma_ep_put(struct kref *kref) module_put(THIS_MODULE); } +static noinline void rpcrdma_ep_get(struct rpcrdma_ep *ep) +{ + kref_get(&ep->re_kref); +} + /* Returns: * %0 if @ep still has a positive kref count, or * %1 if @ep was destroyed successfully. */ -static int rpcrdma_ep_destroy(struct rpcrdma_ep *ep) +static noinline int rpcrdma_ep_put(struct rpcrdma_ep *ep) { - return kref_put(&ep->re_kref, rpcrdma_ep_put); + return kref_put(&ep->re_kref, rpcrdma_ep_destroy); } static int rpcrdma_ep_create(struct rpcrdma_xprt *r_xprt) @@ -388,14 +402,14 @@ static int rpcrdma_ep_create(struct rpcrdma_xprt *r_xprt) ep = kzalloc(sizeof(*ep), GFP_NOFS); if (!ep) - return -EAGAIN; + return -ENOTCONN; ep->re_xprt = &r_xprt->rx_xprt; kref_init(&ep->re_kref); id = rpcrdma_create_id(r_xprt, ep); if (IS_ERR(id)) { - rc = PTR_ERR(id); - goto out_free; + kfree(ep); + return PTR_ERR(id); } __module_get(THIS_MODULE); device = id->device; @@ -492,11 +506,8 @@ static int rpcrdma_ep_create(struct rpcrdma_xprt *r_xprt) return 0; out_destroy: - rpcrdma_ep_destroy(ep); + rpcrdma_ep_put(ep); rdma_destroy_id(id); -out_free: - kfree(ep); - r_xprt->rx_ep = NULL; return rc; } @@ -512,22 +523,19 @@ int rpcrdma_xprt_connect(struct rpcrdma_xprt *r_xprt) struct rpcrdma_ep *ep; int rc; -retry: - rpcrdma_xprt_disconnect(r_xprt); rc = rpcrdma_ep_create(r_xprt); if (rc) return rc; ep = r_xprt->rx_ep; - ep->re_connect_status = 0; xprt_clear_connected(xprt); - rpcrdma_reset_cwnd(r_xprt); - rpcrdma_post_recvs(r_xprt, true); - rc = rpcrdma_sendctxs_create(r_xprt); - if (rc) - goto out; + /* Bump the ep's reference count while there are + * outstanding Receives. + */ + rpcrdma_ep_get(ep); + rpcrdma_post_recvs(r_xprt, true); rc = rdma_connect(ep->re_id, &ep->re_remote_cma); if (rc) @@ -538,22 +546,24 @@ retry: wait_event_interruptible(ep->re_connect_wait, ep->re_connect_status != 0); if (ep->re_connect_status <= 0) { - if (ep->re_connect_status == -EAGAIN) - goto retry; rc = ep->re_connect_status; goto out; } + rc = rpcrdma_sendctxs_create(r_xprt); + if (rc) { + rc = -ENOTCONN; + goto out; + } + rc = rpcrdma_reqs_setup(r_xprt); if (rc) { - rpcrdma_xprt_disconnect(r_xprt); + rc = -ENOTCONN; goto out; } rpcrdma_mrs_create(r_xprt); out: - if (rc) - ep->re_connect_status = rc; trace_xprtrdma_connect(r_xprt, rc); return rc; } @@ -587,7 +597,7 @@ void rpcrdma_xprt_disconnect(struct rpcrdma_xprt *r_xprt) rpcrdma_mrs_destroy(r_xprt); rpcrdma_sendctxs_destroy(r_xprt); - if (rpcrdma_ep_destroy(ep)) + if (rpcrdma_ep_put(ep)) rdma_destroy_id(id); r_xprt->rx_ep = NULL; diff --git a/net/sunrpc/xprtrdma/xprt_rdma.h b/net/sunrpc/xprtrdma/xprt_rdma.h index 0a16fdb09b2c..43974ef39a50 100644 --- a/net/sunrpc/xprtrdma/xprt_rdma.h +++ b/net/sunrpc/xprtrdma/xprt_rdma.h @@ -82,6 +82,7 @@ struct rpcrdma_ep { unsigned int re_max_inline_recv; int re_async_rc; int re_connect_status; + atomic_t re_force_disconnect; struct ib_qp_init_attr re_attr; wait_queue_head_t re_connect_wait; struct rpc_xprt *re_xprt; @@ -446,7 +447,7 @@ extern unsigned int xprt_rdma_memreg_strategy; /* * Endpoint calls - xprtrdma/verbs.c */ -void rpcrdma_flush_disconnect(struct ib_cq *cq, struct ib_wc *wc); +void rpcrdma_flush_disconnect(struct rpcrdma_xprt *r_xprt, struct ib_wc *wc); int rpcrdma_xprt_connect(struct rpcrdma_xprt *r_xprt); void rpcrdma_xprt_disconnect(struct rpcrdma_xprt *r_xprt); diff --git a/net/tipc/link.c b/net/tipc/link.c index ee3b8d0576b8..d40f8e5b7683 100644 --- a/net/tipc/link.c +++ b/net/tipc/link.c @@ -827,11 +827,11 @@ int tipc_link_timeout(struct tipc_link *l, struct sk_buff_head *xmitq) state |= l->bc_rcvlink->rcv_unacked; state |= l->rcv_unacked; state |= !skb_queue_empty(&l->transmq); - state |= !skb_queue_empty(&l->deferdq); probe = mstate->probing; probe |= l->silent_intv_cnt; if (probe || mstate->monitoring) l->silent_intv_cnt++; + probe |= !skb_queue_empty(&l->deferdq); if (l->snd_nxt == l->checkpoint) { tipc_link_update_cwin(l, 0, 0); probe = true; @@ -921,6 +921,21 @@ static void link_prepare_wakeup(struct tipc_link *l) } +/** + * tipc_link_set_skb_retransmit_time - set the time at which retransmission of + * the given skb should be next attempted + * @skb: skb to set a future retransmission time for + * @l: link the skb will be transmitted on + */ +static void tipc_link_set_skb_retransmit_time(struct sk_buff *skb, + struct tipc_link *l) +{ + if (link_is_bc_sndlink(l)) + TIPC_SKB_CB(skb)->nxt_retr = TIPC_BC_RETR_LIM; + else + TIPC_SKB_CB(skb)->nxt_retr = TIPC_UC_RETR_TIME; +} + void tipc_link_reset(struct tipc_link *l) { struct sk_buff_head list; @@ -1036,9 +1051,7 @@ int tipc_link_xmit(struct tipc_link *l, struct sk_buff_head *list, return -ENOBUFS; } __skb_queue_tail(transmq, skb); - /* next retransmit attempt */ - if (link_is_bc_sndlink(l)) - TIPC_SKB_CB(skb)->nxt_retr = TIPC_BC_RETR_LIM; + tipc_link_set_skb_retransmit_time(skb, l); __skb_queue_tail(xmitq, _skb); TIPC_SKB_CB(skb)->ackers = l->ackers; l->rcv_unacked = 0; @@ -1139,9 +1152,7 @@ static void tipc_link_advance_backlog(struct tipc_link *l, if (unlikely(skb == l->backlog[imp].target_bskb)) l->backlog[imp].target_bskb = NULL; __skb_queue_tail(&l->transmq, skb); - /* next retransmit attempt */ - if (link_is_bc_sndlink(l)) - TIPC_SKB_CB(skb)->nxt_retr = TIPC_BC_RETR_LIM; + tipc_link_set_skb_retransmit_time(skb, l); __skb_queue_tail(xmitq, _skb); TIPC_SKB_CB(skb)->ackers = l->ackers; @@ -1584,8 +1595,7 @@ release: /* retransmit skb if unrestricted*/ if (time_before(jiffies, TIPC_SKB_CB(skb)->nxt_retr)) continue; - TIPC_SKB_CB(skb)->nxt_retr = (is_uc) ? - TIPC_UC_RETR_TIME : TIPC_BC_RETR_LIM; + tipc_link_set_skb_retransmit_time(skb, l); _skb = pskb_copy(skb, GFP_ATOMIC); if (!_skb) continue; diff --git a/net/vmw_vsock/virtio_transport.c b/net/vmw_vsock/virtio_transport.c index dfbaf6bd8b1c..2700a63ab095 100644 --- a/net/vmw_vsock/virtio_transport.c +++ b/net/vmw_vsock/virtio_transport.c @@ -22,7 +22,7 @@ #include <net/af_vsock.h> static struct workqueue_struct *virtio_vsock_workqueue; -static struct virtio_vsock *the_virtio_vsock; +static struct virtio_vsock __rcu *the_virtio_vsock; static DEFINE_MUTEX(the_virtio_vsock_mutex); /* protects the_virtio_vsock */ struct virtio_vsock { diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 263ae395ad44..0e07fb8585fb 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -5016,7 +5016,8 @@ static int nl80211_start_ap(struct sk_buff *skb, struct genl_info *info) err = nl80211_parse_he_obss_pd( info->attrs[NL80211_ATTR_HE_OBSS_PD], ¶ms.he_obss_pd); - goto out; + if (err) + goto out; } if (info->attrs[NL80211_ATTR_HE_BSS_COLOR]) { @@ -5024,7 +5025,7 @@ static int nl80211_start_ap(struct sk_buff *skb, struct genl_info *info) info->attrs[NL80211_ATTR_HE_BSS_COLOR], ¶ms.he_bss_color); if (err) - return err; + goto out; } nl80211_calculate_ap_params(¶ms); diff --git a/net/xdp/xsk_buff_pool.c b/net/xdp/xsk_buff_pool.c index 540ed75e4482..08b80669f649 100644 --- a/net/xdp/xsk_buff_pool.c +++ b/net/xdp/xsk_buff_pool.c @@ -2,9 +2,6 @@ #include <net/xsk_buff_pool.h> #include <net/xdp_sock.h> -#include <linux/dma-direct.h> -#include <linux/dma-noncoherent.h> -#include <linux/swiotlb.h> #include "xsk_queue.h" @@ -55,7 +52,6 @@ struct xsk_buff_pool *xp_create(struct page **pages, u32 nr_pages, u32 chunks, pool->free_heads_cnt = chunks; pool->headroom = headroom; pool->chunk_size = chunk_size; - pool->cheap_dma = true; pool->unaligned = unaligned; pool->frame_len = chunk_size - headroom - XDP_PACKET_HEADROOM; INIT_LIST_HEAD(&pool->free_list); @@ -125,48 +121,6 @@ static void xp_check_dma_contiguity(struct xsk_buff_pool *pool) } } -static bool __maybe_unused xp_check_swiotlb_dma(struct xsk_buff_pool *pool) -{ -#if defined(CONFIG_SWIOTLB) - phys_addr_t paddr; - u32 i; - - for (i = 0; i < pool->dma_pages_cnt; i++) { - paddr = dma_to_phys(pool->dev, pool->dma_pages[i]); - if (is_swiotlb_buffer(paddr)) - return false; - } -#endif - return true; -} - -static bool xp_check_cheap_dma(struct xsk_buff_pool *pool) -{ -#if defined(CONFIG_HAS_DMA) - const struct dma_map_ops *ops = get_dma_ops(pool->dev); - - if (ops) { - return !ops->sync_single_for_cpu && - !ops->sync_single_for_device; - } - - if (!dma_is_direct(ops)) - return false; - - if (!xp_check_swiotlb_dma(pool)) - return false; - - if (!dev_is_dma_coherent(pool->dev)) { -#if defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU) || \ - defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU_ALL) || \ - defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_DEVICE) - return false; -#endif - } -#endif - return true; -} - int xp_dma_map(struct xsk_buff_pool *pool, struct device *dev, unsigned long attrs, struct page **pages, u32 nr_pages) { @@ -180,6 +134,7 @@ int xp_dma_map(struct xsk_buff_pool *pool, struct device *dev, pool->dev = dev; pool->dma_pages_cnt = nr_pages; + pool->dma_need_sync = false; for (i = 0; i < pool->dma_pages_cnt; i++) { dma = dma_map_page_attrs(dev, pages[i], 0, PAGE_SIZE, @@ -188,14 +143,13 @@ int xp_dma_map(struct xsk_buff_pool *pool, struct device *dev, xp_dma_unmap(pool, attrs); return -ENOMEM; } + if (dma_need_sync(dev, dma)) + pool->dma_need_sync = true; pool->dma_pages[i] = dma; } if (pool->unaligned) xp_check_dma_contiguity(pool); - - pool->dev = dev; - pool->cheap_dma = xp_check_cheap_dma(pool); return 0; } EXPORT_SYMBOL(xp_dma_map); @@ -280,7 +234,7 @@ struct xdp_buff *xp_alloc(struct xsk_buff_pool *pool) xskb->xdp.data = xskb->xdp.data_hard_start + XDP_PACKET_HEADROOM; xskb->xdp.data_meta = xskb->xdp.data; - if (!pool->cheap_dma) { + if (pool->dma_need_sync) { dma_sync_single_range_for_device(pool->dev, xskb->dma, 0, pool->frame_len, DMA_BIDIRECTIONAL); diff --git a/net/xfrm/Kconfig b/net/xfrm/Kconfig index b5d4a1ef04b9..5b9a5ab48111 100644 --- a/net/xfrm/Kconfig +++ b/net/xfrm/Kconfig @@ -67,6 +67,30 @@ config XFRM_STATISTICS If unsure, say N. +# This option selects XFRM_ALGO along with the AH authentication algorithms that +# RFC 8221 lists as MUST be implemented. +config XFRM_AH + tristate + select XFRM_ALGO + select CRYPTO + select CRYPTO_HMAC + select CRYPTO_SHA256 + +# This option selects XFRM_ALGO along with the ESP encryption and authentication +# algorithms that RFC 8221 lists as MUST be implemented. +config XFRM_ESP + tristate + select XFRM_ALGO + select CRYPTO + select CRYPTO_AES + select CRYPTO_AUTHENC + select CRYPTO_CBC + select CRYPTO_ECHAINIV + select CRYPTO_GCM + select CRYPTO_HMAC + select CRYPTO_SEQIV + select CRYPTO_SHA256 + config XFRM_IPCOMP tristate select XFRM_ALGO diff --git a/net/xfrm/xfrm_device.c b/net/xfrm/xfrm_device.c index f50d1f97cf8e..626096bd0d29 100644 --- a/net/xfrm/xfrm_device.c +++ b/net/xfrm/xfrm_device.c @@ -108,7 +108,7 @@ struct sk_buff *validate_xmit_xfrm(struct sk_buff *skb, netdev_features_t featur struct xfrm_offload *xo = xfrm_offload(skb); struct sec_path *sp; - if (!xo) + if (!xo || (xo->flags & XFRM_XMIT)) return skb; if (!(features & NETIF_F_HW_ESP)) @@ -129,6 +129,8 @@ struct sk_buff *validate_xmit_xfrm(struct sk_buff *skb, netdev_features_t featur return skb; } + xo->flags |= XFRM_XMIT; + if (skb_is_gso(skb)) { struct net_device *dev = skb->dev; diff --git a/net/xfrm/xfrm_interface.c b/net/xfrm/xfrm_interface.c index c407ecbc5d46..b615729812e5 100644 --- a/net/xfrm/xfrm_interface.c +++ b/net/xfrm/xfrm_interface.c @@ -37,6 +37,7 @@ #include <net/ip.h> #include <net/ipv6.h> #include <net/ip6_route.h> +#include <net/ip_tunnels.h> #include <net/addrconf.h> #include <net/xfrm.h> #include <net/net_namespace.h> @@ -581,6 +582,7 @@ static const struct net_device_ops xfrmi_netdev_ops = { static void xfrmi_dev_setup(struct net_device *dev) { dev->netdev_ops = &xfrmi_netdev_ops; + dev->header_ops = &ip_tunnel_header_ops; dev->type = ARPHRD_NONE; dev->mtu = ETH_DATA_LEN; dev->min_mtu = ETH_MIN_MTU; diff --git a/net/xfrm/xfrm_output.c b/net/xfrm/xfrm_output.c index e4c23f69f69f..a7ab19353313 100644 --- a/net/xfrm/xfrm_output.c +++ b/net/xfrm/xfrm_output.c @@ -574,16 +574,12 @@ int xfrm_output(struct sock *sk, struct sk_buff *skb) switch (x->outer_mode.family) { case AF_INET: memset(IPCB(skb), 0, sizeof(*IPCB(skb))); -#ifdef CONFIG_NETFILTER IPCB(skb)->flags |= IPSKB_XFRM_TRANSFORMED; -#endif break; case AF_INET6: memset(IP6CB(skb), 0, sizeof(*IP6CB(skb))); -#ifdef CONFIG_NETFILTER IP6CB(skb)->flags |= IP6SKB_XFRM_TRANSFORMED; -#endif break; } |