diff options
Diffstat (limited to 'net')
48 files changed, 287 insertions, 155 deletions
diff --git a/net/core/dev.c b/net/core/dev.c index 0766a245816b..9a67003e49db 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -2245,7 +2245,7 @@ void dev_queue_xmit_nit(struct sk_buff *skb, struct net_device *dev) rcu_read_lock(); again: list_for_each_entry_rcu(ptype, ptype_list, list) { - if (ptype->ignore_outgoing) + if (READ_ONCE(ptype->ignore_outgoing)) continue; /* Never send packets back to the socket @@ -6743,6 +6743,8 @@ static int napi_threaded_poll(void *data) void *have; while (!napi_thread_wait(napi)) { + unsigned long last_qs = jiffies; + for (;;) { bool repoll = false; @@ -6767,6 +6769,7 @@ static int napi_threaded_poll(void *data) if (!repoll) break; + rcu_softirq_qs_periodic(last_qs); cond_resched(); } } @@ -11665,11 +11668,12 @@ static void __init net_dev_struct_check(void) /* TXRX read-mostly hotpath */ CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_txrx, lstats); + CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_txrx, state); CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_txrx, flags); CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_txrx, hard_header_len); CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_txrx, features); CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_txrx, ip6_ptr); - CACHELINE_ASSERT_GROUP_SIZE(struct net_device, net_device_read_txrx, 38); + CACHELINE_ASSERT_GROUP_SIZE(struct net_device, net_device_read_txrx, 46); /* RX read-mostly hotpath */ CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_rx, ptype_specific); diff --git a/net/core/sock.c b/net/core/sock.c index 43bf3818c19e..0963689a5950 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -482,7 +482,7 @@ int __sock_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) unsigned long flags; struct sk_buff_head *list = &sk->sk_receive_queue; - if (atomic_read(&sk->sk_rmem_alloc) >= sk->sk_rcvbuf) { + if (atomic_read(&sk->sk_rmem_alloc) >= READ_ONCE(sk->sk_rcvbuf)) { atomic_inc(&sk->sk_drops); trace_sock_rcvqueue_full(sk, skb); return -ENOMEM; @@ -552,7 +552,7 @@ int __sk_receive_skb(struct sock *sk, struct sk_buff *skb, skb->dev = NULL; - if (sk_rcvqueues_full(sk, sk->sk_rcvbuf)) { + if (sk_rcvqueues_full(sk, READ_ONCE(sk->sk_rcvbuf))) { atomic_inc(&sk->sk_drops); goto discard_and_relse; } diff --git a/net/dccp/ccids/Kconfig b/net/dccp/ccids/Kconfig index a3eeb84d16f9..e3d388c33d25 100644 --- a/net/dccp/ccids/Kconfig +++ b/net/dccp/ccids/Kconfig @@ -13,7 +13,7 @@ config IP_DCCP_CCID2_DEBUG config IP_DCCP_CCID3 bool "CCID-3 (TCP-Friendly)" - def_bool y if (IP_DCCP = y || IP_DCCP = m) + default IP_DCCP = y || IP_DCCP = m help CCID-3 denotes TCP-Friendly Rate Control (TFRC), an equation-based rate-controlled congestion control mechanism. TFRC is designed to diff --git a/net/devlink/netlink.c b/net/devlink/netlink.c index 499885c8b9ca..593605c1b1ef 100644 --- a/net/devlink/netlink.c +++ b/net/devlink/netlink.c @@ -193,12 +193,13 @@ devlink_get_from_attrs_lock(struct net *net, struct nlattr **attrs, devname = nla_data(attrs[DEVLINK_ATTR_DEV_NAME]); devlinks_xa_for_each_registered_get(net, index, devlink) { - devl_dev_lock(devlink, dev_lock); - if (devl_is_registered(devlink) && - strcmp(devlink->dev->bus->name, busname) == 0 && - strcmp(dev_name(devlink->dev), devname) == 0) - return devlink; - devl_dev_unlock(devlink, dev_lock); + if (strcmp(devlink->dev->bus->name, busname) == 0 && + strcmp(dev_name(devlink->dev), devname) == 0) { + devl_dev_lock(devlink, dev_lock); + if (devl_is_registered(devlink)) + return devlink; + devl_dev_unlock(devlink, dev_lock); + } devlink_put(devlink); } diff --git a/net/devlink/port.c b/net/devlink/port.c index 4b2d46ccfe48..118d130d2afd 100644 --- a/net/devlink/port.c +++ b/net/devlink/port.c @@ -889,7 +889,7 @@ int devlink_nl_port_new_doit(struct sk_buff *skb, struct genl_info *info) err = -ENOMEM; goto err_out_port_del; } - err = devlink_nl_port_fill(msg, devlink_port, DEVLINK_CMD_NEW, + err = devlink_nl_port_fill(msg, devlink_port, DEVLINK_CMD_PORT_NEW, info->snd_portid, info->snd_seq, 0, NULL); if (WARN_ON_ONCE(err)) goto err_out_msg_free; diff --git a/net/hsr/hsr_framereg.c b/net/hsr/hsr_framereg.c index 6d14d935ee82..26329db09210 100644 --- a/net/hsr/hsr_framereg.c +++ b/net/hsr/hsr_framereg.c @@ -228,6 +228,10 @@ struct hsr_node *hsr_get_node(struct hsr_port *port, struct list_head *node_db, */ if (ethhdr->h_proto == htons(ETH_P_PRP) || ethhdr->h_proto == htons(ETH_P_HSR)) { + /* Check if skb contains hsr_ethhdr */ + if (skb->mac_len < sizeof(struct hsr_ethhdr)) + return NULL; + /* Use the existing sequence_nr from the tag as starting point * for filtering duplicate frames. */ diff --git a/net/hsr/hsr_main.c b/net/hsr/hsr_main.c index cb83c8feb746..9756e657bab9 100644 --- a/net/hsr/hsr_main.c +++ b/net/hsr/hsr_main.c @@ -148,14 +148,21 @@ static struct notifier_block hsr_nb = { static int __init hsr_init(void) { - int res; + int err; BUILD_BUG_ON(sizeof(struct hsr_tag) != HSR_HLEN); - register_netdevice_notifier(&hsr_nb); - res = hsr_netlink_init(); + err = register_netdevice_notifier(&hsr_nb); + if (err) + return err; + + err = hsr_netlink_init(); + if (err) { + unregister_netdevice_notifier(&hsr_nb); + return err; + } - return res; + return 0; } static void __exit hsr_exit(void) diff --git a/net/hsr/hsr_slave.c b/net/hsr/hsr_slave.c index e5742f2a2d52..1b6457f357bd 100644 --- a/net/hsr/hsr_slave.c +++ b/net/hsr/hsr_slave.c @@ -220,7 +220,8 @@ void hsr_del_port(struct hsr_port *port) netdev_update_features(master->dev); dev_set_mtu(master->dev, hsr_get_max_mtu(hsr)); netdev_rx_handler_unregister(port->dev); - dev_set_promiscuity(port->dev, -1); + if (!port->hsr->fwd_offloaded) + dev_set_promiscuity(port->dev, -1); netdev_upper_dev_unlink(port->dev, master->dev); } diff --git a/net/ipv4/esp4.c b/net/ipv4/esp4.c index 4dd9e5040672..d33d12421814 100644 --- a/net/ipv4/esp4.c +++ b/net/ipv4/esp4.c @@ -95,7 +95,7 @@ static inline struct scatterlist *esp_req_sg(struct crypto_aead *aead, __alignof__(struct scatterlist)); } -static void esp_ssg_unref(struct xfrm_state *x, void *tmp) +static void esp_ssg_unref(struct xfrm_state *x, void *tmp, struct sk_buff *skb) { struct crypto_aead *aead = x->data; int extralen = 0; @@ -114,7 +114,7 @@ static void esp_ssg_unref(struct xfrm_state *x, void *tmp) */ if (req->src != req->dst) for (sg = sg_next(req->src); sg; sg = sg_next(sg)) - put_page(sg_page(sg)); + skb_page_unref(skb, sg_page(sg), false); } #ifdef CONFIG_INET_ESPINTCP @@ -260,7 +260,7 @@ static void esp_output_done(void *data, int err) } tmp = ESP_SKB_CB(skb)->tmp; - esp_ssg_unref(x, tmp); + esp_ssg_unref(x, tmp, skb); kfree(tmp); if (xo && (xo->flags & XFRM_DEV_RESUME)) { @@ -639,7 +639,7 @@ int esp_output_tail(struct xfrm_state *x, struct sk_buff *skb, struct esp_info * } if (sg != dsg) - esp_ssg_unref(x, tmp); + esp_ssg_unref(x, tmp, skb); if (!err && x->encap && x->encap->encap_type == TCP_ENCAP_ESPINTCP) err = esp_output_tail_tcp(x, skb); diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index 7d8090f109ef..c038e28e2f1e 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -771,6 +771,20 @@ void inet_csk_clear_xmit_timers(struct sock *sk) } EXPORT_SYMBOL(inet_csk_clear_xmit_timers); +void inet_csk_clear_xmit_timers_sync(struct sock *sk) +{ + struct inet_connection_sock *icsk = inet_csk(sk); + + /* ongoing timer handlers need to acquire socket lock. */ + sock_not_owned_by_me(sk); + + icsk->icsk_pending = icsk->icsk_ack.pending = 0; + + sk_stop_timer_sync(sk, &icsk->icsk_retransmit_timer); + sk_stop_timer_sync(sk, &icsk->icsk_delack_timer); + sk_stop_timer_sync(sk, &sk->sk_timer); +} + void inet_csk_delete_keepalive_timer(struct sock *sk) { sk_stop_timer(sk, &sk->sk_timer); diff --git a/net/ipv4/inet_fragment.c b/net/ipv4/inet_fragment.c index 7072fc0783ef..c88c9034d630 100644 --- a/net/ipv4/inet_fragment.c +++ b/net/ipv4/inet_fragment.c @@ -24,6 +24,8 @@ #include <net/ip.h> #include <net/ipv6.h> +#include "../core/sock_destructor.h" + /* Use skb->cb to track consecutive/adjacent fragments coming at * the end of the queue. Nodes in the rb-tree queue will * contain "runs" of one or more adjacent fragments. @@ -39,6 +41,7 @@ struct ipfrag_skb_cb { }; struct sk_buff *next_frag; int frag_run_len; + int ip_defrag_offset; }; #define FRAG_CB(skb) ((struct ipfrag_skb_cb *)((skb)->cb)) @@ -396,12 +399,12 @@ int inet_frag_queue_insert(struct inet_frag_queue *q, struct sk_buff *skb, */ if (!last) fragrun_create(q, skb); /* First fragment. */ - else if (last->ip_defrag_offset + last->len < end) { + else if (FRAG_CB(last)->ip_defrag_offset + last->len < end) { /* This is the common case: skb goes to the end. */ /* Detect and discard overlaps. */ - if (offset < last->ip_defrag_offset + last->len) + if (offset < FRAG_CB(last)->ip_defrag_offset + last->len) return IPFRAG_OVERLAP; - if (offset == last->ip_defrag_offset + last->len) + if (offset == FRAG_CB(last)->ip_defrag_offset + last->len) fragrun_append_to_last(q, skb); else fragrun_create(q, skb); @@ -418,13 +421,13 @@ int inet_frag_queue_insert(struct inet_frag_queue *q, struct sk_buff *skb, parent = *rbn; curr = rb_to_skb(parent); - curr_run_end = curr->ip_defrag_offset + + curr_run_end = FRAG_CB(curr)->ip_defrag_offset + FRAG_CB(curr)->frag_run_len; - if (end <= curr->ip_defrag_offset) + if (end <= FRAG_CB(curr)->ip_defrag_offset) rbn = &parent->rb_left; else if (offset >= curr_run_end) rbn = &parent->rb_right; - else if (offset >= curr->ip_defrag_offset && + else if (offset >= FRAG_CB(curr)->ip_defrag_offset && end <= curr_run_end) return IPFRAG_DUP; else @@ -438,7 +441,7 @@ int inet_frag_queue_insert(struct inet_frag_queue *q, struct sk_buff *skb, rb_insert_color(&skb->rbnode, &q->rb_fragments); } - skb->ip_defrag_offset = offset; + FRAG_CB(skb)->ip_defrag_offset = offset; return IPFRAG_OK; } @@ -448,13 +451,28 @@ void *inet_frag_reasm_prepare(struct inet_frag_queue *q, struct sk_buff *skb, struct sk_buff *parent) { struct sk_buff *fp, *head = skb_rb_first(&q->rb_fragments); - struct sk_buff **nextp; + void (*destructor)(struct sk_buff *); + unsigned int orig_truesize = 0; + struct sk_buff **nextp = NULL; + struct sock *sk = skb->sk; int delta; + if (sk && is_skb_wmem(skb)) { + /* TX: skb->sk might have been passed as argument to + * dst->output and must remain valid until tx completes. + * + * Move sk to reassembled skb and fix up wmem accounting. + */ + orig_truesize = skb->truesize; + destructor = skb->destructor; + } + if (head != skb) { fp = skb_clone(skb, GFP_ATOMIC); - if (!fp) - return NULL; + if (!fp) { + head = skb; + goto out_restore_sk; + } FRAG_CB(fp)->next_frag = FRAG_CB(skb)->next_frag; if (RB_EMPTY_NODE(&skb->rbnode)) FRAG_CB(parent)->next_frag = fp; @@ -463,6 +481,12 @@ void *inet_frag_reasm_prepare(struct inet_frag_queue *q, struct sk_buff *skb, &q->rb_fragments); if (q->fragments_tail == skb) q->fragments_tail = fp; + + if (orig_truesize) { + /* prevent skb_morph from releasing sk */ + skb->sk = NULL; + skb->destructor = NULL; + } skb_morph(skb, head); FRAG_CB(skb)->next_frag = FRAG_CB(head)->next_frag; rb_replace_node(&head->rbnode, &skb->rbnode, @@ -470,13 +494,13 @@ void *inet_frag_reasm_prepare(struct inet_frag_queue *q, struct sk_buff *skb, consume_skb(head); head = skb; } - WARN_ON(head->ip_defrag_offset != 0); + WARN_ON(FRAG_CB(head)->ip_defrag_offset != 0); delta = -head->truesize; /* Head of list must not be cloned. */ if (skb_unclone(head, GFP_ATOMIC)) - return NULL; + goto out_restore_sk; delta += head->truesize; if (delta) @@ -492,7 +516,7 @@ void *inet_frag_reasm_prepare(struct inet_frag_queue *q, struct sk_buff *skb, clone = alloc_skb(0, GFP_ATOMIC); if (!clone) - return NULL; + goto out_restore_sk; skb_shinfo(clone)->frag_list = skb_shinfo(head)->frag_list; skb_frag_list_init(head); for (i = 0; i < skb_shinfo(head)->nr_frags; i++) @@ -509,6 +533,21 @@ void *inet_frag_reasm_prepare(struct inet_frag_queue *q, struct sk_buff *skb, nextp = &skb_shinfo(head)->frag_list; } +out_restore_sk: + if (orig_truesize) { + int ts_delta = head->truesize - orig_truesize; + + /* if this reassembled skb is fragmented later, + * fraglist skbs will get skb->sk assigned from head->sk, + * and each frag skb will be released via sock_wfree. + * + * Update sk_wmem_alloc. + */ + head->sk = sk; + head->destructor = destructor; + refcount_add(ts_delta, &sk->sk_wmem_alloc); + } + return nextp; } EXPORT_SYMBOL(inet_frag_reasm_prepare); @@ -516,6 +555,8 @@ EXPORT_SYMBOL(inet_frag_reasm_prepare); void inet_frag_reasm_finish(struct inet_frag_queue *q, struct sk_buff *head, void *reasm_data, bool try_coalesce) { + struct sock *sk = is_skb_wmem(head) ? head->sk : NULL; + const unsigned int head_truesize = head->truesize; struct sk_buff **nextp = reasm_data; struct rb_node *rbn; struct sk_buff *fp; @@ -579,6 +620,9 @@ void inet_frag_reasm_finish(struct inet_frag_queue *q, struct sk_buff *head, head->prev = NULL; head->tstamp = q->stamp; head->mono_delivery_time = q->mono_delivery_time; + + if (sk) + refcount_add(sum_truesize - head_truesize, &sk->sk_wmem_alloc); } EXPORT_SYMBOL(inet_frag_reasm_finish); diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c index 7498af320164..cf88eca5f1b4 100644 --- a/net/ipv4/inet_hashtables.c +++ b/net/ipv4/inet_hashtables.c @@ -1135,7 +1135,7 @@ error: sock_prot_inuse_add(net, sk->sk_prot, -1); spin_lock(lock); - sk_nulls_del_node_init_rcu(sk); + __sk_nulls_del_node_init_rcu(sk); spin_unlock(lock); sk->sk_hash = 0; diff --git a/net/ipv4/inet_timewait_sock.c b/net/ipv4/inet_timewait_sock.c index 5befa4de5b24..e8de45d34d56 100644 --- a/net/ipv4/inet_timewait_sock.c +++ b/net/ipv4/inet_timewait_sock.c @@ -263,12 +263,12 @@ void __inet_twsk_schedule(struct inet_timewait_sock *tw, int timeo, bool rearm) } EXPORT_SYMBOL_GPL(__inet_twsk_schedule); +/* Remove all non full sockets (TIME_WAIT and NEW_SYN_RECV) for dead netns */ void inet_twsk_purge(struct inet_hashinfo *hashinfo, int family) { - struct inet_timewait_sock *tw; - struct sock *sk; struct hlist_nulls_node *node; unsigned int slot; + struct sock *sk; for (slot = 0; slot <= hashinfo->ehash_mask; slot++) { struct inet_ehash_bucket *head = &hashinfo->ehash[slot]; @@ -277,38 +277,35 @@ restart_rcu: rcu_read_lock(); restart: sk_nulls_for_each_rcu(sk, node, &head->chain) { - if (sk->sk_state != TCP_TIME_WAIT) { - /* A kernel listener socket might not hold refcnt for net, - * so reqsk_timer_handler() could be fired after net is - * freed. Userspace listener and reqsk never exist here. - */ - if (unlikely(sk->sk_state == TCP_NEW_SYN_RECV && - hashinfo->pernet)) { - struct request_sock *req = inet_reqsk(sk); - - inet_csk_reqsk_queue_drop_and_put(req->rsk_listener, req); - } + int state = inet_sk_state_load(sk); + if ((1 << state) & ~(TCPF_TIME_WAIT | + TCPF_NEW_SYN_RECV)) continue; - } - tw = inet_twsk(sk); - if ((tw->tw_family != family) || - refcount_read(&twsk_net(tw)->ns.count)) + if (sk->sk_family != family || + refcount_read(&sock_net(sk)->ns.count)) continue; - if (unlikely(!refcount_inc_not_zero(&tw->tw_refcnt))) + if (unlikely(!refcount_inc_not_zero(&sk->sk_refcnt))) continue; - if (unlikely((tw->tw_family != family) || - refcount_read(&twsk_net(tw)->ns.count))) { - inet_twsk_put(tw); + if (unlikely(sk->sk_family != family || + refcount_read(&sock_net(sk)->ns.count))) { + sock_gen_put(sk); goto restart; } rcu_read_unlock(); local_bh_disable(); - inet_twsk_deschedule_put(tw); + if (state == TCP_TIME_WAIT) { + inet_twsk_deschedule_put(inet_twsk(sk)); + } else { + struct request_sock *req = inet_reqsk(sk); + + inet_csk_reqsk_queue_drop_and_put(req->rsk_listener, + req); + } local_bh_enable(); goto restart_rcu; } diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c index a4941f53b523..fb947d1613fe 100644 --- a/net/ipv4/ip_fragment.c +++ b/net/ipv4/ip_fragment.c @@ -384,6 +384,7 @@ static int ip_frag_queue(struct ipq *qp, struct sk_buff *skb) } skb_dst_drop(skb); + skb_orphan(skb); return -EINPROGRESS; insert_error: @@ -487,7 +488,6 @@ int ip_defrag(struct net *net, struct sk_buff *skb, u32 user) struct ipq *qp; __IP_INC_STATS(net, IPSTATS_MIB_REASMREQDS); - skb_orphan(skb); /* Lookup (or create) queue header */ qp = ip_find(net, ip_hdr(skb), user, vif); diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index 33f93dc730a3..1fe794967211 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -1458,7 +1458,6 @@ struct sk_buff *__ip_make_skb(struct sock *sk, skb->priority = (cork->tos != -1) ? cork->priority: READ_ONCE(sk->sk_priority); skb->mark = cork->mark; skb->tstamp = cork->transmit_time; - skb->mono_delivery_time = !!skb->tstamp; /* * Steal rt from cork.dst to avoid a pair of atomic_inc/atomic_dec * on dst refcount diff --git a/net/ipv4/netfilter/Kconfig b/net/ipv4/netfilter/Kconfig index 8f6e950163a7..1b991b889506 100644 --- a/net/ipv4/netfilter/Kconfig +++ b/net/ipv4/netfilter/Kconfig @@ -329,6 +329,7 @@ config NFT_COMPAT_ARP config IP_NF_ARPFILTER tristate "arptables-legacy packet filtering support" select IP_NF_ARPTABLES + select NETFILTER_FAMILY_ARP depends on NETFILTER_XTABLES help ARP packet filtering defines a table `filter', which has a series of diff --git a/net/ipv4/nexthop.c b/net/ipv4/nexthop.c index 74928a9d1aa4..535856b0f0ed 100644 --- a/net/ipv4/nexthop.c +++ b/net/ipv4/nexthop.c @@ -768,8 +768,10 @@ static int nh_grp_hw_stats_update(struct nexthop *nh, bool *hw_stats_used) struct net *net = nh->net; int err; - if (nexthop_notifiers_is_empty(net)) + if (nexthop_notifiers_is_empty(net)) { + *hw_stats_used = false; return 0; + } err = nh_notifier_grp_hw_stats_init(&info, nh); if (err) diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c index 42ac434cfcfa..dcb11f22cbf2 100644 --- a/net/ipv4/raw.c +++ b/net/ipv4/raw.c @@ -357,10 +357,10 @@ static int raw_send_hdrinc(struct sock *sk, struct flowi4 *fl4, goto error; skb_reserve(skb, hlen); + skb->protocol = htons(ETH_P_IP); skb->priority = READ_ONCE(sk->sk_priority); skb->mark = sockc->mark; skb->tstamp = sockc->transmit_time; - skb->mono_delivery_time = !!skb->tstamp; skb_dst_set(skb, &rt->dst); *rtp = NULL; diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c index 7972ad3d7c73..500f665f98cb 100644 --- a/net/ipv4/syncookies.c +++ b/net/ipv4/syncookies.c @@ -474,6 +474,9 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb) ireq->wscale_ok, &rcv_wscale, dst_metric(&rt->dst, RTAX_INITRWND)); + /* req->syncookie is set true only if ACK is validated + * by BPF kfunc, then, rcv_wscale is already configured. + */ if (!req->syncookie) ireq->rcv_wscale = rcv_wscale; ireq->ecn_ok &= cookie_ecn_ok(net, &rt->dst); diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index d20b62d52171..e767721b3a58 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -2931,6 +2931,8 @@ void tcp_close(struct sock *sk, long timeout) lock_sock(sk); __tcp_close(sk, timeout); release_sock(sk); + if (!sk->sk_net_refcnt) + inet_csk_clear_xmit_timers_sync(sk); sock_put(sk); } EXPORT_SYMBOL(tcp_close); diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index 52040b0e2616..f0761f060a83 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -398,10 +398,6 @@ void tcp_twsk_purge(struct list_head *net_exit_list, int family) /* Even if tw_refcount == 1, we must clean up kernel reqsk */ inet_twsk_purge(net->ipv4.tcp_death_row.hashinfo, family); } else if (!purged_once) { - /* The last refcount is decremented in tcp_sk_exit_batch() */ - if (refcount_read(&net->ipv4.tcp_death_row.tw_refcount) == 1) - continue; - inet_twsk_purge(&tcp_hashinfo, family); purged_once = true; } diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 247bd4d8ee45..92db9b474f2b 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -5416,10 +5416,11 @@ static int inet6_dump_addr(struct sk_buff *skb, struct netlink_callback *cb, err = 0; if (fillargs.ifindex) { - err = -ENODEV; dev = dev_get_by_index_rcu(tgt_net, fillargs.ifindex); - if (!dev) + if (!dev) { + err = -ENODEV; goto done; + } idev = __in6_dev_get(dev); if (idev) err = in6_dump_addrs(idev, skb, cb, diff --git a/net/ipv6/esp6.c b/net/ipv6/esp6.c index 6e6efe026cdc..7371886d4f9f 100644 --- a/net/ipv6/esp6.c +++ b/net/ipv6/esp6.c @@ -112,7 +112,7 @@ static inline struct scatterlist *esp_req_sg(struct crypto_aead *aead, __alignof__(struct scatterlist)); } -static void esp_ssg_unref(struct xfrm_state *x, void *tmp) +static void esp_ssg_unref(struct xfrm_state *x, void *tmp, struct sk_buff *skb) { struct crypto_aead *aead = x->data; int extralen = 0; @@ -131,7 +131,7 @@ static void esp_ssg_unref(struct xfrm_state *x, void *tmp) */ if (req->src != req->dst) for (sg = sg_next(req->src); sg; sg = sg_next(sg)) - put_page(sg_page(sg)); + skb_page_unref(skb, sg_page(sg), false); } #ifdef CONFIG_INET6_ESPINTCP @@ -294,7 +294,7 @@ static void esp_output_done(void *data, int err) } tmp = ESP_SKB_CB(skb)->tmp; - esp_ssg_unref(x, tmp); + esp_ssg_unref(x, tmp, skb); kfree(tmp); esp_output_encap_csum(skb); @@ -677,7 +677,7 @@ int esp6_output_tail(struct xfrm_state *x, struct sk_buff *skb, struct esp_info } if (sg != dsg) - esp_ssg_unref(x, tmp); + esp_ssg_unref(x, tmp, skb); if (!err && x->encap && x->encap->encap_type == TCP_ENCAP_ESPINTCP) err = esp_output_tail_tcp(x, skb); diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index 02eeca5492cd..b9dd3a66e423 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -1925,7 +1925,7 @@ struct sk_buff *__ip6_make_skb(struct sock *sk, skb->priority = READ_ONCE(sk->sk_priority); skb->mark = cork->base.mark; skb->tstamp = cork->base.transmit_time; - skb->mono_delivery_time = !!skb->tstamp; + ip6_cork_steal_dst(skb, cork); IP6_INC_STATS(net, rt->rt6i_idev, IPSTATS_MIB_OUTREQUESTS); if (proto == IPPROTO_ICMPV6) { diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c index 1a51a44571c3..d0dcbaca1994 100644 --- a/net/ipv6/netfilter/nf_conntrack_reasm.c +++ b/net/ipv6/netfilter/nf_conntrack_reasm.c @@ -294,6 +294,7 @@ static int nf_ct_frag6_queue(struct frag_queue *fq, struct sk_buff *skb, } skb_dst_drop(skb); + skb_orphan(skb); return -EINPROGRESS; insert_error: @@ -469,7 +470,6 @@ int nf_ct_frag6_gather(struct net *net, struct sk_buff *skb, u32 user) hdr = ipv6_hdr(skb); fhdr = (struct frag_hdr *)skb_transport_header(skb); - skb_orphan(skb); fq = fq_find(net, fhdr->identification, user, hdr, skb->dev ? skb->dev->ifindex : 0); if (fq == NULL) { diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c index ca49e6617afa..0d896ca7b589 100644 --- a/net/ipv6/raw.c +++ b/net/ipv6/raw.c @@ -622,7 +622,7 @@ static int rawv6_send_hdrinc(struct sock *sk, struct msghdr *msg, int length, skb->priority = READ_ONCE(sk->sk_priority); skb->mark = sockc->mark; skb->tstamp = sockc->transmit_time; - skb->mono_delivery_time = !!skb->tstamp; + skb_put(skb, length); skb_reset_network_header(skb); iph = ipv6_hdr(skb); diff --git a/net/ipv6/syncookies.c b/net/ipv6/syncookies.c index 8bad0a44a0a6..6d8286c299c9 100644 --- a/net/ipv6/syncookies.c +++ b/net/ipv6/syncookies.c @@ -258,6 +258,9 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb) ireq->wscale_ok, &rcv_wscale, dst_metric(dst, RTAX_INITRWND)); + /* req->syncookie is set true only if ACK is validated + * by BPF kfunc, then, rcv_wscale is already configured. + */ if (!req->syncookie) ireq->rcv_wscale = rcv_wscale; ireq->ecn_ok &= cookie_ecn_ok(net, dst); diff --git a/net/iucv/af_iucv.c b/net/iucv/af_iucv.c index 4aa1c72e6c49..7c8c3adcac6e 100644 --- a/net/iucv/af_iucv.c +++ b/net/iucv/af_iucv.c @@ -1060,12 +1060,12 @@ static int iucv_sock_sendmsg(struct socket *sock, struct msghdr *msg, int i; /* skip iucv_array lying in the headroom */ - iba[0].address = (u32)virt_to_phys(skb->data); + iba[0].address = virt_to_dma32(skb->data); iba[0].length = (u32)skb_headlen(skb); for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { skb_frag_t *frag = &skb_shinfo(skb)->frags[i]; - iba[i + 1].address = (u32)virt_to_phys(skb_frag_address(frag)); + iba[i + 1].address = virt_to_dma32(skb_frag_address(frag)); iba[i + 1].length = (u32)skb_frag_size(frag); } err = pr_iucv->message_send(iucv->path, &txmsg, @@ -1161,12 +1161,12 @@ static void iucv_process_message(struct sock *sk, struct sk_buff *skb, struct iucv_array *iba = (struct iucv_array *)skb->head; int i; - iba[0].address = (u32)virt_to_phys(skb->data); + iba[0].address = virt_to_dma32(skb->data); iba[0].length = (u32)skb_headlen(skb); for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { skb_frag_t *frag = &skb_shinfo(skb)->frags[i]; - iba[i + 1].address = (u32)virt_to_phys(skb_frag_address(frag)); + iba[i + 1].address = virt_to_dma32(skb_frag_address(frag)); iba[i + 1].length = (u32)skb_frag_size(frag); } rc = pr_iucv->message_receive(path, msg, diff --git a/net/iucv/iucv.c b/net/iucv/iucv.c index 4d8ee3607b53..a4ab615ca3e3 100644 --- a/net/iucv/iucv.c +++ b/net/iucv/iucv.c @@ -210,7 +210,7 @@ struct iucv_cmd_dpl { u8 iprmmsg[8]; u32 ipsrccls; u32 ipmsgtag; - u32 ipbfadr2; + dma32_t ipbfadr2; u32 ipbfln2f; u32 res; } __attribute__ ((packed,aligned(8))); @@ -226,11 +226,11 @@ struct iucv_cmd_db { u8 iprcode; u32 ipmsgid; u32 iptrgcls; - u32 ipbfadr1; + dma32_t ipbfadr1; u32 ipbfln1f; u32 ipsrccls; u32 ipmsgtag; - u32 ipbfadr2; + dma32_t ipbfadr2; u32 ipbfln2f; u32 res; } __attribute__ ((packed,aligned(8))); @@ -432,7 +432,7 @@ static void iucv_declare_cpu(void *data) /* Declare interrupt buffer. */ parm = iucv_param_irq[cpu]; memset(parm, 0, sizeof(union iucv_param)); - parm->db.ipbfadr1 = virt_to_phys(iucv_irq_data[cpu]); + parm->db.ipbfadr1 = virt_to_dma32(iucv_irq_data[cpu]); rc = iucv_call_b2f0(IUCV_DECLARE_BUFFER, parm); if (rc) { char *err = "Unknown"; @@ -1081,8 +1081,7 @@ static int iucv_message_receive_iprmdata(struct iucv_path *path, size = (size < 8) ? size : 8; for (array = buffer; size > 0; array++) { copy = min_t(size_t, size, array->length); - memcpy((u8 *)(addr_t) array->address, - rmmsg, copy); + memcpy(dma32_to_virt(array->address), rmmsg, copy); rmmsg += copy; size -= copy; } @@ -1124,7 +1123,7 @@ int __iucv_message_receive(struct iucv_path *path, struct iucv_message *msg, parm = iucv_param[smp_processor_id()]; memset(parm, 0, sizeof(union iucv_param)); - parm->db.ipbfadr1 = (u32)virt_to_phys(buffer); + parm->db.ipbfadr1 = virt_to_dma32(buffer); parm->db.ipbfln1f = (u32) size; parm->db.ipmsgid = msg->id; parm->db.ippathid = path->pathid; @@ -1242,7 +1241,7 @@ int iucv_message_reply(struct iucv_path *path, struct iucv_message *msg, parm->dpl.iptrgcls = msg->class; memcpy(parm->dpl.iprmmsg, reply, min_t(size_t, size, 8)); } else { - parm->db.ipbfadr1 = (u32)virt_to_phys(reply); + parm->db.ipbfadr1 = virt_to_dma32(reply); parm->db.ipbfln1f = (u32) size; parm->db.ippathid = path->pathid; parm->db.ipflags1 = flags; @@ -1294,7 +1293,7 @@ int __iucv_message_send(struct iucv_path *path, struct iucv_message *msg, parm->dpl.ipmsgtag = msg->tag; memcpy(parm->dpl.iprmmsg, buffer, 8); } else { - parm->db.ipbfadr1 = (u32)virt_to_phys(buffer); + parm->db.ipbfadr1 = virt_to_dma32(buffer); parm->db.ipbfln1f = (u32) size; parm->db.ippathid = path->pathid; parm->db.ipflags1 = flags | IUCV_IPNORPY; @@ -1379,7 +1378,7 @@ int iucv_message_send2way(struct iucv_path *path, struct iucv_message *msg, parm->dpl.iptrgcls = msg->class; parm->dpl.ipsrccls = srccls; parm->dpl.ipmsgtag = msg->tag; - parm->dpl.ipbfadr2 = (u32)virt_to_phys(answer); + parm->dpl.ipbfadr2 = virt_to_dma32(answer); parm->dpl.ipbfln2f = (u32) asize; memcpy(parm->dpl.iprmmsg, buffer, 8); } else { @@ -1388,9 +1387,9 @@ int iucv_message_send2way(struct iucv_path *path, struct iucv_message *msg, parm->db.iptrgcls = msg->class; parm->db.ipsrccls = srccls; parm->db.ipmsgtag = msg->tag; - parm->db.ipbfadr1 = (u32)virt_to_phys(buffer); + parm->db.ipbfadr1 = virt_to_dma32(buffer); parm->db.ipbfln1f = (u32) size; - parm->db.ipbfadr2 = (u32)virt_to_phys(answer); + parm->db.ipbfadr2 = virt_to_dma32(answer); parm->db.ipbfln2f = (u32) asize; } rc = iucv_call_b2f0(IUCV_SEND, parm); diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c index f03452dc716d..f67c1d021812 100644 --- a/net/mac80211/cfg.c +++ b/net/mac80211/cfg.c @@ -2199,15 +2199,14 @@ static int ieee80211_change_station(struct wiphy *wiphy, } if (sta->sdata->vif.type == NL80211_IFTYPE_AP_VLAN && - sta->sdata->u.vlan.sta) { - ieee80211_clear_fast_rx(sta); + sta->sdata->u.vlan.sta) RCU_INIT_POINTER(sta->sdata->u.vlan.sta, NULL); - } if (test_sta_flag(sta, WLAN_STA_AUTHORIZED)) ieee80211_vif_dec_num_mcast(sta->sdata); sta->sdata = vlansdata; + ieee80211_check_fast_rx(sta); ieee80211_check_fast_xmit(sta); if (test_sta_flag(sta, WLAN_STA_AUTHORIZED)) { diff --git a/net/mac80211/debug.h b/net/mac80211/debug.h index 49da401c5340..35a8ba25fa57 100644 --- a/net/mac80211/debug.h +++ b/net/mac80211/debug.h @@ -158,7 +158,7 @@ do { \ _sdata_dbg(print, sdata, "[link %d] " fmt, \ link_id, ##__VA_ARGS__); \ else \ - _sdata_dbg(1, sdata, fmt, ##__VA_ARGS__); \ + _sdata_dbg(print, sdata, fmt, ##__VA_ARGS__); \ } while (0) #define link_dbg(link, fmt, ...) \ _link_id_dbg(1, (link)->sdata, (link)->link_id, \ diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h index b6fead612b66..bd507d6b65e3 100644 --- a/net/mac80211/ieee80211_i.h +++ b/net/mac80211/ieee80211_i.h @@ -131,7 +131,7 @@ struct ieee80211_bss { }; /** - * enum ieee80211_corrupt_data_flags - BSS data corruption flags + * enum ieee80211_bss_corrupt_data_flags - BSS data corruption flags * @IEEE80211_BSS_CORRUPT_BEACON: last beacon frame received was corrupted * @IEEE80211_BSS_CORRUPT_PROBE_RESP: last probe response received was corrupted * @@ -144,7 +144,7 @@ enum ieee80211_bss_corrupt_data_flags { }; /** - * enum ieee80211_valid_data_flags - BSS valid data flags + * enum ieee80211_bss_valid_data_flags - BSS valid data flags * @IEEE80211_BSS_VALID_WMM: WMM/UAPSD data was gathered from non-corrupt IE * @IEEE80211_BSS_VALID_RATES: Supported rates were gathered from non-corrupt IE * @IEEE80211_BSS_VALID_ERP: ERP flag was gathered from non-corrupt IE diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c index 47a2cba8313f..96b70006b7fc 100644 --- a/net/mac80211/mlme.c +++ b/net/mac80211/mlme.c @@ -5874,6 +5874,15 @@ static int ieee80211_ttlm_set_links(struct ieee80211_sub_if_data *sdata, } if (sdata->vif.active_links != active_links) { + /* usable links are affected when active_links are changed, + * so notify the driver about the status change + */ + changed |= BSS_CHANGED_MLD_VALID_LINKS; + active_links &= sdata->vif.active_links; + if (!active_links) + active_links = + BIT(__ffs(sdata->vif.valid_links & + ~dormant_links)); ret = ieee80211_set_active_links(&sdata->vif, active_links); if (ret) { sdata_info(sdata, "Failed to set TTLM active links\n"); @@ -5888,7 +5897,6 @@ static int ieee80211_ttlm_set_links(struct ieee80211_sub_if_data *sdata, goto out; } - changed |= BSS_CHANGED_MLD_VALID_LINKS; sdata->vif.suspended_links = suspended_links; if (sdata->vif.suspended_links) changed |= BSS_CHANGED_MLD_TTLM; @@ -7652,7 +7660,7 @@ static int ieee80211_prep_connection(struct ieee80211_sub_if_data *sdata, sdata_info(sdata, "failed to insert STA entry for the AP (error %d)\n", err); - goto out_err; + goto out_release_chan; } } else WARN_ON_ONCE(!ether_addr_equal(link->u.mgd.bssid, cbss->bssid)); @@ -7663,8 +7671,9 @@ static int ieee80211_prep_connection(struct ieee80211_sub_if_data *sdata, return 0; +out_release_chan: + ieee80211_link_release_channel(link); out_err: - ieee80211_link_release_channel(&sdata->deflink); ieee80211_vif_set_links(sdata, 0, 0); return err; } diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index e93f905e60b6..fd86f2720c9e 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -1200,6 +1200,25 @@ static void nf_tables_table_disable(struct net *net, struct nft_table *table) __NFT_TABLE_F_WAS_AWAKEN | \ __NFT_TABLE_F_WAS_ORPHAN) +static bool nft_table_pending_update(const struct nft_ctx *ctx) +{ + struct nftables_pernet *nft_net = nft_pernet(ctx->net); + struct nft_trans *trans; + + if (ctx->table->flags & __NFT_TABLE_F_UPDATE) + return true; + + list_for_each_entry(trans, &nft_net->commit_list, list) { + if ((trans->msg_type == NFT_MSG_NEWCHAIN || + trans->msg_type == NFT_MSG_DELCHAIN) && + trans->ctx.table == ctx->table && + nft_trans_chain_update(trans)) + return true; + } + + return false; +} + static int nf_tables_updtable(struct nft_ctx *ctx) { struct nft_trans *trans; @@ -1213,7 +1232,7 @@ static int nf_tables_updtable(struct nft_ctx *ctx) if (flags & ~NFT_TABLE_F_MASK) return -EOPNOTSUPP; - if (flags == ctx->table->flags) + if (flags == (ctx->table->flags & NFT_TABLE_F_MASK)) return 0; if ((nft_table_has_owner(ctx->table) && @@ -1226,7 +1245,7 @@ static int nf_tables_updtable(struct nft_ctx *ctx) return -EOPNOTSUPP; /* No dormant off/on/off/on games in single transaction */ - if (ctx->table->flags & __NFT_TABLE_F_UPDATE) + if (nft_table_pending_update(ctx)) return -EINVAL; trans = nft_trans_alloc(ctx, NFT_MSG_NEWTABLE, @@ -2631,17 +2650,11 @@ static int nf_tables_updchain(struct nft_ctx *ctx, u8 genmask, u8 policy, } } - if (nla[NFTA_CHAIN_COUNTERS]) { - if (!nft_is_base_chain(chain)) { - err = -EOPNOTSUPP; - goto err_hooks; - } - - stats = nft_stats_alloc(nla[NFTA_CHAIN_COUNTERS]); - if (IS_ERR(stats)) { - err = PTR_ERR(stats); - goto err_hooks; - } + if (table->flags & __NFT_TABLE_F_UPDATE && + !list_empty(&hook.list)) { + NL_SET_BAD_ATTR(extack, attr); + err = -EOPNOTSUPP; + goto err_hooks; } if (!(table->flags & NFT_TABLE_F_DORMANT) && @@ -2658,6 +2671,20 @@ static int nf_tables_updchain(struct nft_ctx *ctx, u8 genmask, u8 policy, } unregister = true; + + if (nla[NFTA_CHAIN_COUNTERS]) { + if (!nft_is_base_chain(chain)) { + err = -EOPNOTSUPP; + goto err_hooks; + } + + stats = nft_stats_alloc(nla[NFTA_CHAIN_COUNTERS]); + if (IS_ERR(stats)) { + err = PTR_ERR(stats); + goto err_hooks; + } + } + err = -ENOMEM; trans = nft_trans_alloc(ctx, NFT_MSG_NEWCHAIN, sizeof(struct nft_trans_chain)); @@ -2859,6 +2886,9 @@ static int nft_delchain_hook(struct nft_ctx *ctx, struct nft_trans *trans; int err; + if (ctx->table->flags & __NFT_TABLE_F_UPDATE) + return -EOPNOTSUPP; + err = nft_chain_parse_hook(ctx->net, basechain, nla, &chain_hook, ctx->family, chain->flags, extack); if (err < 0) @@ -2943,7 +2973,8 @@ static int nf_tables_delchain(struct sk_buff *skb, const struct nfnl_info *info, nft_ctx_init(&ctx, net, skb, info->nlh, family, table, chain, nla); if (nla[NFTA_CHAIN_HOOK]) { - if (chain->flags & NFT_CHAIN_HW_OFFLOAD) + if (NFNL_MSG_TYPE(info->nlh->nlmsg_type) == NFT_MSG_DESTROYCHAIN || + chain->flags & NFT_CHAIN_HW_OFFLOAD) return -EOPNOTSUPP; if (nft_is_base_chain(chain)) { @@ -10181,9 +10212,11 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb) if (nft_trans_chain_update(trans)) { nf_tables_chain_notify(&trans->ctx, NFT_MSG_DELCHAIN, &nft_trans_chain_hooks(trans)); - nft_netdev_unregister_hooks(net, - &nft_trans_chain_hooks(trans), - true); + if (!(trans->ctx.table->flags & NFT_TABLE_F_DORMANT)) { + nft_netdev_unregister_hooks(net, + &nft_trans_chain_hooks(trans), + true); + } } else { nft_chain_del(trans->ctx.chain); nf_tables_chain_notify(&trans->ctx, NFT_MSG_DELCHAIN, @@ -10459,9 +10492,11 @@ static int __nf_tables_abort(struct net *net, enum nfnl_abort_action action) break; case NFT_MSG_NEWCHAIN: if (nft_trans_chain_update(trans)) { - nft_netdev_unregister_hooks(net, - &nft_trans_chain_hooks(trans), - true); + if (!(trans->ctx.table->flags & NFT_TABLE_F_DORMANT)) { + nft_netdev_unregister_hooks(net, + &nft_trans_chain_hooks(trans), + true); + } free_percpu(nft_trans_chain_stats(trans)); kfree(nft_trans_chain_name(trans)); nft_trans_destroy(trans); diff --git a/net/netfilter/nft_set_pipapo.c b/net/netfilter/nft_set_pipapo.c index c0ceea068936..df8de5090246 100644 --- a/net/netfilter/nft_set_pipapo.c +++ b/net/netfilter/nft_set_pipapo.c @@ -2329,8 +2329,6 @@ static void nft_pipapo_destroy(const struct nft_ctx *ctx, if (m) { rcu_barrier(); - nft_set_pipapo_match_destroy(ctx, set, m); - for_each_possible_cpu(cpu) pipapo_free_scratch(m, cpu); free_percpu(m->scratch); @@ -2342,8 +2340,7 @@ static void nft_pipapo_destroy(const struct nft_ctx *ctx, if (priv->clone) { m = priv->clone; - if (priv->dirty) - nft_set_pipapo_match_destroy(ctx, set, m); + nft_set_pipapo_match_destroy(ctx, set, m); for_each_possible_cpu(cpu) pipapo_free_scratch(priv->clone, cpu); diff --git a/net/nfc/nci/core.c b/net/nfc/nci/core.c index cdad47b140fa..0d26c8ec9993 100644 --- a/net/nfc/nci/core.c +++ b/net/nfc/nci/core.c @@ -1516,6 +1516,11 @@ static void nci_rx_work(struct work_struct *work) nfc_send_to_raw_sock(ndev->nfc_dev, skb, RAW_PAYLOAD_NCI, NFC_DIRECTION_RX); + if (!nci_plen(skb->data)) { + kfree_skb(skb); + break; + } + /* Process frame */ switch (nci_mt(skb->data)) { case NCI_MT_RSP_PKT: diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index 61270826b9ac..18f616f487ea 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -2057,7 +2057,7 @@ retry: skb->priority = READ_ONCE(sk->sk_priority); skb->mark = READ_ONCE(sk->sk_mark); skb->tstamp = sockc.transmit_time; - skb->mono_delivery_time = !!skb->tstamp; + skb_setup_tx_timestamp(skb, sockc.tsflags); if (unlikely(extra_len == 4)) @@ -2586,7 +2586,6 @@ static int tpacket_fill_skb(struct packet_sock *po, struct sk_buff *skb, skb->priority = READ_ONCE(po->sk.sk_priority); skb->mark = READ_ONCE(po->sk.sk_mark); skb->tstamp = sockc->transmit_time; - skb->mono_delivery_time = !!skb->tstamp; skb_setup_tx_timestamp(skb, sockc->tsflags); skb_zcopy_set_nouarg(skb, ph.raw); @@ -3065,7 +3064,6 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len) skb->priority = READ_ONCE(sk->sk_priority); skb->mark = sockc.mark; skb->tstamp = sockc.transmit_time; - skb->mono_delivery_time = !!skb->tstamp; if (unlikely(extra_len == 4)) skb->no_fcs = 1; @@ -4000,7 +3998,7 @@ packet_setsockopt(struct socket *sock, int level, int optname, sockptr_t optval, if (val < 0 || val > 1) return -EINVAL; - po->prot_hook.ignore_outgoing = !!val; + WRITE_ONCE(po->prot_hook.ignore_outgoing, !!val); return 0; } case PACKET_TX_HAS_OFF: @@ -4134,7 +4132,7 @@ static int packet_getsockopt(struct socket *sock, int level, int optname, 0); break; case PACKET_IGNORE_OUTGOING: - val = po->prot_hook.ignore_outgoing; + val = READ_ONCE(po->prot_hook.ignore_outgoing); break; case PACKET_ROLLOVER_STATS: if (!po->rollover) diff --git a/net/rds/send.c b/net/rds/send.c index 2899def23865..09a280110654 100644 --- a/net/rds/send.c +++ b/net/rds/send.c @@ -103,13 +103,12 @@ EXPORT_SYMBOL_GPL(rds_send_path_reset); static int acquire_in_xmit(struct rds_conn_path *cp) { - return test_and_set_bit(RDS_IN_XMIT, &cp->cp_flags) == 0; + return test_and_set_bit_lock(RDS_IN_XMIT, &cp->cp_flags) == 0; } static void release_in_xmit(struct rds_conn_path *cp) { - clear_bit(RDS_IN_XMIT, &cp->cp_flags); - smp_mb__after_atomic(); + clear_bit_unlock(RDS_IN_XMIT, &cp->cp_flags); /* * We don't use wait_on_bit()/wake_up_bit() because our waking is in a * hot path and finding waiters is very rare. We don't want to walk diff --git a/net/rxrpc/sendmsg.c b/net/rxrpc/sendmsg.c index 6f765768c49c..894b8fa68e5e 100644 --- a/net/rxrpc/sendmsg.c +++ b/net/rxrpc/sendmsg.c @@ -349,8 +349,8 @@ reload: */ remain = more ? INT_MAX : msg_data_left(msg); txb = call->conn->security->alloc_txbuf(call, remain, sk->sk_allocation); - if (IS_ERR(txb)) { - ret = PTR_ERR(txb); + if (!txb) { + ret = -ENOMEM; goto maybe_error; } } diff --git a/net/rxrpc/txbuf.c b/net/rxrpc/txbuf.c index b2a82ab756c2..e0679658d9de 100644 --- a/net/rxrpc/txbuf.c +++ b/net/rxrpc/txbuf.c @@ -33,8 +33,8 @@ struct rxrpc_txbuf *rxrpc_alloc_data_txbuf(struct rxrpc_call *call, size_t data_ total = hoff + sizeof(*whdr) + data_size; mutex_lock(&call->conn->tx_data_alloc_lock); - buf = page_frag_alloc_align(&call->conn->tx_data_alloc, total, gfp, - ~(data_align - 1) & ~(L1_CACHE_BYTES - 1)); + buf = __page_frag_alloc_align(&call->conn->tx_data_alloc, total, gfp, + ~(data_align - 1) & ~(L1_CACHE_BYTES - 1)); mutex_unlock(&call->conn->tx_data_alloc_lock); if (!buf) { kfree(txb); diff --git a/net/sched/sch_fq_pie.c b/net/sched/sch_fq_pie.c index 5b595773e59b..358cf304f4c9 100644 --- a/net/sched/sch_fq_pie.c +++ b/net/sched/sch_fq_pie.c @@ -10,6 +10,7 @@ */ #include <linux/jhash.h> +#include <linux/module.h> #include <linux/sizes.h> #include <linux/vmalloc.h> #include <net/pkt_cls.h> @@ -563,6 +564,7 @@ static struct Qdisc_ops fq_pie_qdisc_ops __read_mostly = { .dump_stats = fq_pie_dump_stats, .owner = THIS_MODULE, }; +MODULE_ALIAS_NET_SCH("fq_pie"); static int __init fq_pie_module_init(void) { diff --git a/net/sched/sch_taprio.c b/net/sched/sch_taprio.c index c5de70efdc86..a0d54b422186 100644 --- a/net/sched/sch_taprio.c +++ b/net/sched/sch_taprio.c @@ -997,7 +997,8 @@ static const struct nla_policy entry_policy[TCA_TAPRIO_SCHED_ENTRY_MAX + 1] = { }; static const struct nla_policy taprio_tc_policy[TCA_TAPRIO_TC_ENTRY_MAX + 1] = { - [TCA_TAPRIO_TC_ENTRY_INDEX] = { .type = NLA_U32 }, + [TCA_TAPRIO_TC_ENTRY_INDEX] = NLA_POLICY_MAX(NLA_U32, + TC_QOPT_MAX_QUEUE), [TCA_TAPRIO_TC_ENTRY_MAX_SDU] = { .type = NLA_U32 }, [TCA_TAPRIO_TC_ENTRY_FP] = NLA_POLICY_RANGE(NLA_U32, TC_FP_EXPRESS, diff --git a/net/socket.c b/net/socket.c index 7e9c8fc9a5b4..e5f3af49a8b6 100644 --- a/net/socket.c +++ b/net/socket.c @@ -2600,9 +2600,9 @@ out: return err; } -int sendmsg_copy_msghdr(struct msghdr *msg, - struct user_msghdr __user *umsg, unsigned flags, - struct iovec **iov) +static int sendmsg_copy_msghdr(struct msghdr *msg, + struct user_msghdr __user *umsg, unsigned flags, + struct iovec **iov) { int err; @@ -2753,10 +2753,10 @@ SYSCALL_DEFINE4(sendmmsg, int, fd, struct mmsghdr __user *, mmsg, return __sys_sendmmsg(fd, mmsg, vlen, flags, true); } -int recvmsg_copy_msghdr(struct msghdr *msg, - struct user_msghdr __user *umsg, unsigned flags, - struct sockaddr __user **uaddr, - struct iovec **iov) +static int recvmsg_copy_msghdr(struct msghdr *msg, + struct user_msghdr __user *umsg, unsigned flags, + struct sockaddr __user **uaddr, + struct iovec **iov) { ssize_t err; diff --git a/net/sunrpc/auth_gss/gss_krb5_crypto.c b/net/sunrpc/auth_gss/gss_krb5_crypto.c index b2c1b683a88e..d2b02710ab07 100644 --- a/net/sunrpc/auth_gss/gss_krb5_crypto.c +++ b/net/sunrpc/auth_gss/gss_krb5_crypto.c @@ -921,8 +921,6 @@ out_err: * Caller provides the truncation length of the output token (h) in * cksumout.len. * - * Note that for RPCSEC, the "initial cipher state" is always all zeroes. - * * Return values: * %GSS_S_COMPLETE: Digest computed, @cksumout filled in * %GSS_S_FAILURE: Call failed @@ -933,19 +931,22 @@ u32 krb5_etm_checksum(struct crypto_sync_skcipher *cipher, int body_offset, struct xdr_netobj *cksumout) { unsigned int ivsize = crypto_sync_skcipher_ivsize(cipher); - static const u8 iv[GSS_KRB5_MAX_BLOCKSIZE]; struct ahash_request *req; struct scatterlist sg[1]; + u8 *iv, *checksumdata; int err = -ENOMEM; - u8 *checksumdata; checksumdata = kmalloc(crypto_ahash_digestsize(tfm), GFP_KERNEL); if (!checksumdata) return GSS_S_FAILURE; + /* For RPCSEC, the "initial cipher state" is always all zeroes. */ + iv = kzalloc(ivsize, GFP_KERNEL); + if (!iv) + goto out_free_mem; req = ahash_request_alloc(tfm, GFP_KERNEL); if (!req) - goto out_free_cksumdata; + goto out_free_mem; ahash_request_set_callback(req, CRYPTO_TFM_REQ_MAY_SLEEP, NULL, NULL); err = crypto_ahash_init(req); if (err) @@ -969,7 +970,8 @@ u32 krb5_etm_checksum(struct crypto_sync_skcipher *cipher, out_free_ahash: ahash_request_free(req); -out_free_cksumdata: +out_free_mem: + kfree(iv); kfree_sensitive(checksumdata); return err ? GSS_S_FAILURE : GSS_S_COMPLETE; } diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c index 211f57164cb6..b783231668c6 100644 --- a/net/tls/tls_sw.c +++ b/net/tls/tls_sw.c @@ -1976,10 +1976,10 @@ int tls_sw_recvmsg(struct sock *sk, if (unlikely(flags & MSG_ERRQUEUE)) return sock_recv_errqueue(sk, msg, len, SOL_IP, IP_RECVERR); - psock = sk_psock_get(sk); err = tls_rx_reader_lock(sk, ctx, flags & MSG_DONTWAIT); if (err < 0) return err; + psock = sk_psock_get(sk); bpf_strp_enabled = sk_psock_strp_enabled(psock); /* If crypto failed the connection is broken */ @@ -2152,12 +2152,15 @@ recv_end: } /* Drain records from the rx_list & copy if required */ - if (is_peek || is_kvec) + if (is_peek) err = process_rx_list(ctx, msg, &control, copied + peeked, decrypted - peeked, is_peek, NULL); else err = process_rx_list(ctx, msg, &control, 0, async_copy_bytes, is_peek, NULL); + + /* we could have copied less than we wanted, and possibly nothing */ + decrypted += max(err, 0) - async_copy_bytes; } copied += decrypted; diff --git a/net/wireless/trace.h b/net/wireless/trace.h index e039e66ab377..cbbf347c6b2e 100644 --- a/net/wireless/trace.h +++ b/net/wireless/trace.h @@ -1024,7 +1024,7 @@ TRACE_EVENT(rdev_get_mpp, TRACE_EVENT(rdev_dump_mpp, TP_PROTO(struct wiphy *wiphy, struct net_device *netdev, int _idx, u8 *dst, u8 *mpp), - TP_ARGS(wiphy, netdev, _idx, mpp, dst), + TP_ARGS(wiphy, netdev, _idx, dst, mpp), TP_STRUCT__entry( WIPHY_ENTRY NETDEV_ENTRY diff --git a/net/wireless/wext-core.c b/net/wireless/wext-core.c index a161c64d1765..838ad6541a17 100644 --- a/net/wireless/wext-core.c +++ b/net/wireless/wext-core.c @@ -4,6 +4,7 @@ * Authors : Jean Tourrilhes - HPL - <jt@hpl.hp.com> * Copyright (c) 1997-2007 Jean Tourrilhes, All Rights Reserved. * Copyright 2009 Johannes Berg <johannes@sipsolutions.net> + * Copyright (C) 2024 Intel Corporation * * (As all part of the Linux kernel, this file is GPL) */ @@ -662,7 +663,8 @@ struct iw_statistics *get_wireless_stats(struct net_device *dev) dev->ieee80211_ptr->wiphy->wext && dev->ieee80211_ptr->wiphy->wext->get_wireless_stats) { wireless_warn_cfg80211_wext(); - if (dev->ieee80211_ptr->wiphy->flags & WIPHY_FLAG_SUPPORTS_MLO) + if (dev->ieee80211_ptr->wiphy->flags & (WIPHY_FLAG_SUPPORTS_MLO | + WIPHY_FLAG_DISABLE_WEXT)) return NULL; return dev->ieee80211_ptr->wiphy->wext->get_wireless_stats(dev); } @@ -704,7 +706,8 @@ static iw_handler get_handler(struct net_device *dev, unsigned int cmd) #ifdef CONFIG_CFG80211_WEXT if (dev->ieee80211_ptr && dev->ieee80211_ptr->wiphy) { wireless_warn_cfg80211_wext(); - if (dev->ieee80211_ptr->wiphy->flags & WIPHY_FLAG_SUPPORTS_MLO) + if (dev->ieee80211_ptr->wiphy->flags & (WIPHY_FLAG_SUPPORTS_MLO | + WIPHY_FLAG_DISABLE_WEXT)) return NULL; handlers = dev->ieee80211_ptr->wiphy->wext; } diff --git a/net/xfrm/xfrm_device.c b/net/xfrm/xfrm_device.c index 653e51ae3964..6346690d5c69 100644 --- a/net/xfrm/xfrm_device.c +++ b/net/xfrm/xfrm_device.c @@ -407,7 +407,8 @@ bool xfrm_dev_offload_ok(struct sk_buff *skb, struct xfrm_state *x) struct xfrm_dst *xdst = (struct xfrm_dst *)dst; struct net_device *dev = x->xso.dev; - if (!x->type_offload) + if (!x->type_offload || + (x->xso.type == XFRM_DEV_OFFLOAD_UNSPECIFIED && x->encap)) return false; if (x->xso.type == XFRM_DEV_OFFLOAD_PACKET || |