diff options
Diffstat (limited to 'net')
71 files changed, 872 insertions, 417 deletions
diff --git a/net/batman-adv/hard-interface.c b/net/batman-adv/hard-interface.c index e7ad295504e4..c5bc60d16e40 100644 --- a/net/batman-adv/hard-interface.c +++ b/net/batman-adv/hard-interface.c @@ -981,7 +981,7 @@ batadv_wifi_net_device_insert(struct net_device *net_dev, u32 wifi_flags) ASSERT_RTNL(); - device_state = kzalloc_obj(*device_state, GFP_KERNEL); + device_state = kzalloc_obj(*device_state); if (!device_state) return -ENOMEM; diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c index 35a1be57e386..d7355c73f93e 100644 --- a/net/bluetooth/hci_core.c +++ b/net/bluetooth/hci_core.c @@ -2632,11 +2632,11 @@ int hci_register_dev(struct hci_dev *hdev) if (error) BT_WARN("register suspend notifier failed error:%d\n", error); - queue_work(hdev->req_workqueue, &hdev->power_on); - idr_init(&hdev->adv_monitors_idr); msft_register(hdev); + queue_work(hdev->req_workqueue, &hdev->power_on); + return id; err_wqueue: diff --git a/net/bluetooth/hci_sync.c b/net/bluetooth/hci_sync.c index ffd7b37e7401..3f121099eb22 100644 --- a/net/bluetooth/hci_sync.c +++ b/net/bluetooth/hci_sync.c @@ -6423,8 +6423,7 @@ static int hci_update_event_filter_sync(struct hci_dev *hdev) goto update_scan; } - accept_list = kmalloc_array(num_entries, sizeof(*accept_list), - GFP_KERNEL); + accept_list = kmalloc_objs(*accept_list, num_entries); if (!accept_list) { hci_dev_unlock(hdev); return -ENOMEM; diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c index ee459dd411f5..644e31160d55 100644 --- a/net/bluetooth/l2cap_core.c +++ b/net/bluetooth/l2cap_core.c @@ -1337,7 +1337,7 @@ static void l2cap_le_connect(struct l2cap_chan *chan) struct l2cap_ecred_conn_data { struct { struct l2cap_ecred_conn_req_hdr req; - __le16 scid[5]; + __le16 scid[L2CAP_ECRED_CONN_SCID_MAX]; } __packed pdu; struct l2cap_chan *chan; struct pid *pid; @@ -1352,7 +1352,7 @@ static void l2cap_ecred_defer_connect(struct l2cap_chan *chan, void *data) if (chan == conn->chan) return; - if (!test_and_clear_bit(FLAG_DEFER_SETUP, &chan->flags)) + if (!test_bit(FLAG_DEFER_SETUP, &chan->flags)) return; pid = chan->ops->get_peer_pid(chan); @@ -1362,9 +1362,16 @@ static void l2cap_ecred_defer_connect(struct l2cap_chan *chan, void *data) chan->mode != L2CAP_MODE_EXT_FLOWCTL || chan->state != BT_CONNECT) return; + if (!test_and_clear_bit(FLAG_DEFER_SETUP, &chan->flags)) + return; + if (test_and_set_bit(FLAG_ECRED_CONN_REQ_SENT, &chan->flags)) return; + /* Unreachable, checked in l2cap_connect (+timer drops it if reached) */ + if (WARN_ON_ONCE(conn->count >= ARRAY_SIZE(conn->pdu.scid))) + return; + l2cap_ecred_init(chan, 0); /* Set the same ident so we can match on the rsp */ @@ -3894,6 +3901,9 @@ static void l2cap_ecred_rsp_defer(struct l2cap_chan *chan, void *data) struct l2cap_ecred_conn_rsp *rsp_flex = container_of(&rsp->pdu.rsp, struct l2cap_ecred_conn_rsp, hdr); + if (chan->mode != L2CAP_MODE_EXT_FLOWCTL) + return; + /* Check if channel for outgoing connection or if it wasn't deferred * since in those cases it must be skipped. */ @@ -3904,6 +3914,10 @@ static void l2cap_ecred_rsp_defer(struct l2cap_chan *chan, void *data) /* Reset ident so only one response is sent */ chan->ident = 0; + /* Unreachable, check in l2cap_ecred_conn_req. If reached, drop rest */ + if (WARN_ON_ONCE(rsp->count >= ARRAY_SIZE(rsp->pdu.scid))) + rsp->pdu.rsp.result = cpu_to_le16(L2CAP_CR_LE_NO_MEM); + /* Include all channels pending with the same ident */ if (!rsp->pdu.rsp.result) rsp_flex->dcid[rsp->count++] = cpu_to_le16(chan->scid); @@ -5063,6 +5077,7 @@ static int l2cap_le_connect_req(struct l2cap_conn *conn, __set_chan_timer(chan, chan->ops->get_sndtimeo(chan)); chan->ident = cmd->ident; + chan->mode = L2CAP_MODE_LE_FLOWCTL; if (test_bit(FLAG_DEFER_SETUP, &chan->flags)) { l2cap_state_change(chan, BT_CONNECT2); @@ -7369,6 +7384,9 @@ int l2cap_chan_connect(struct l2cap_chan *chan, __le16 psm, u16 cid, goto done; } + mutex_lock(&conn->lock); + l2cap_chan_lock(chan); + if (chan->mode == L2CAP_MODE_EXT_FLOWCTL) { struct l2cap_chan_data data; @@ -7376,19 +7394,20 @@ int l2cap_chan_connect(struct l2cap_chan *chan, __le16 psm, u16 cid, data.pid = chan->ops->get_peer_pid(chan); data.count = 1; - l2cap_chan_list(conn, l2cap_chan_by_pid, &data); + __l2cap_chan_list(conn, l2cap_chan_by_pid, &data); + + /* Leave room for non-deferred channel that ends the group. */ + if (test_bit(FLAG_DEFER_SETUP, &chan->flags)) + data.count += 1; /* Check if there isn't too many channels being connected */ if (data.count > L2CAP_ECRED_CONN_SCID_MAX) { hci_conn_drop(hcon); err = -EPROTO; - goto done; + goto chan_unlock; } } - mutex_lock(&conn->lock); - l2cap_chan_lock(chan); - if (cid && __l2cap_get_chan_by_dcid(conn, cid)) { hci_conn_drop(hcon); err = -EBUSY; diff --git a/net/bluetooth/msft.c b/net/bluetooth/msft.c index ded68568e6c9..d9dd722db3eb 100644 --- a/net/bluetooth/msft.c +++ b/net/bluetooth/msft.c @@ -769,8 +769,8 @@ void msft_register(struct hci_dev *hdev) INIT_LIST_HEAD(&msft->handle_map); INIT_LIST_HEAD(&msft->address_filters); - hdev->msft_data = msft; mutex_init(&msft->filter_lock); + hdev->msft_data = msft; } void msft_release(struct hci_dev *hdev) diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c index 3ef5d8bbf552..3e9b10f8abf1 100644 --- a/net/bridge/br_multicast.c +++ b/net/bridge/br_multicast.c @@ -808,7 +808,11 @@ void br_multicast_del_pg(struct net_bridge_mdb_entry *mp, struct hlist_node *tmp; rcu_assign_pointer(*pp, pg->next); - hlist_del_init(&pg->mglist); + /* Keep ->next (held under multicast_lock, freed later by the GC work): + * a port->mglist teardown walk may have latched this node as its next, + * and deleting other groups of the same port must not truncate it. + */ + hlist_del_init_rcu(&pg->mglist); br_multicast_eht_clean_sets(pg); hlist_for_each_entry_safe(ent, tmp, &pg->src_list, node) br_multicast_del_group_src(ent, false); @@ -835,6 +839,13 @@ static void br_multicast_find_del_pg(struct net_bridge *br, struct net_bridge_mdb_entry *mp; struct net_bridge_port_group *p; + /* A teardown walk over port->mglist can reach a group that an earlier + * iteration already deleted as a side effect. It is off mp->ports by + * now, so skip it instead of falling through to the WARN_ON() below. + */ + if (hlist_unhashed(&pg->mglist)) + return; + mp = br_mdb_ip_get(br, &pg->key.addr); if (WARN_ON(!mp)) return; diff --git a/net/ceph/messenger.c b/net/ceph/messenger.c index 9c1b6cf8c36f..212e7797f9e4 100644 --- a/net/ceph/messenger.c +++ b/net/ceph/messenger.c @@ -1003,7 +1003,6 @@ static struct page *ceph_msg_data_iter_next(struct ceph_msg_data_cursor *cursor, * we'll get an iov_iter_get_pages2 variant that doesn't take * page refs. Until then, just put the page ref. */ - VM_BUG_ON_PAGE(!PageWriteback(page) && page_count(page) < 2, page); put_page(page); *length = min_t(size_t, len, cursor->resid); diff --git a/net/core/dev.c b/net/core/dev.c index 38336858c168..290e0f099e6b 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -12703,7 +12703,7 @@ int __dev_change_net_namespace(struct net_device *dev, struct net *net, const char *pat, int new_ifindex, struct netlink_ext_ack *extack) { - struct netdev_name_node *name_node; + struct netdev_name_node *name_node, *tmp; struct net *net_old = dev_net(dev); char new_name[IFNAMSIZ] = {}; int err, new_nsid; @@ -12749,13 +12749,19 @@ int __dev_change_net_namespace(struct net_device *dev, struct net *net, } /* Check that none of the altnames conflicts. */ err = -EEXIST; - netdev_for_each_altname(dev, name_node) { - if (netdev_name_in_use(net, name_node->name)) { - NL_SET_ERR_MSG_FMT(extack, - "An interface with the altname %s exists in the target netns", - name_node->name); - goto out; + netdev_for_each_altname_safe(dev, name_node, tmp) { + if (!netdev_name_in_use(net, name_node->name)) + continue; + + if (!check_net(net_old)) { + __netdev_name_node_alt_destroy(name_node); + continue; } + + NL_SET_ERR_MSG_FMT(extack, + "An interface with the altname %s exists in the target netns", + name_node->name); + goto out; } /* Check that new_ifindex isn't used yet. */ @@ -13210,7 +13216,6 @@ static struct pernet_operations __net_initdata netdev_net_ops = { static void __net_exit default_device_exit_net(struct net *net) { - struct netdev_name_node *name_node, *tmp; struct net_device *dev, *aux; /* * Push all migratable network devices back to the @@ -13234,10 +13239,6 @@ static void __net_exit default_device_exit_net(struct net *net) if (netdev_name_in_use(&init_net, fb_name)) snprintf(fb_name, IFNAMSIZ, "dev%%d"); - netdev_for_each_altname_safe(dev, name_node, tmp) - if (netdev_name_in_use(&init_net, name_node->name)) - __netdev_name_node_alt_destroy(name_node); - err = dev_change_net_namespace(dev, &init_net, fb_name); if (err) { pr_emerg("%s: failed to move %s to init_net: %d\n", diff --git a/net/core/gro_cells.c b/net/core/gro_cells.c index 1b84385c04bd..d8c0a2867120 100644 --- a/net/core/gro_cells.c +++ b/net/core/gro_cells.c @@ -22,6 +22,8 @@ int gro_cells_receive(struct gro_cells *gcells, struct sk_buff *skb) if (unlikely(!(dev->flags & IFF_UP))) goto drop; + skb_unset_transport_header(skb); + if (!gcells->cells || skb_cloned(skb) || netif_elide_gro(dev)) { res = netif_rx(skb); goto unlock; diff --git a/net/core/page_pool.c b/net/core/page_pool.c index 8f8956fb061b..08d7f35cf608 100644 --- a/net/core/page_pool.c +++ b/net/core/page_pool.c @@ -1073,7 +1073,8 @@ netmem_ref page_pool_alloc_frag_netmem(struct page_pool *pool, if (WARN_ON(size > max_size)) return 0; - size = ALIGN(size, dma_get_cache_alignment()); + size = ALIGN(size, max_t(unsigned int, dma_get_cache_alignment(), + __alignof__(struct skb_shared_info))); *offset = pool->frag_offset; if (netmem && *offset + size > max_size) { diff --git a/net/core/sock.c b/net/core/sock.c index 1ad41904db25..fa60b7494c58 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -2494,6 +2494,9 @@ struct sock *sk_clone(const struct sock *sk, const gfp_t priority, #ifdef CONFIG_BPF_SYSCALL RCU_INIT_POINTER(newsk->sk_bpf_storage, NULL); #endif +#if IS_ENABLED(CONFIG_INET_PSP) + RCU_INIT_POINTER(newsk->psp_assoc, NULL); +#endif /* SANITY */ if (likely(newsk->sk_net_refcnt)) { diff --git a/net/devlink/netlink.c b/net/devlink/netlink.c index 300580c1a217..a8eda727bff1 100644 --- a/net/devlink/netlink.c +++ b/net/devlink/netlink.c @@ -251,7 +251,7 @@ devlink_get_parent_from_attrs_lock(struct net *net, struct nlattr **attrs) if (!attrs[DEVLINK_ATTR_PARENT_DEV]) return ERR_PTR(-EINVAL); - tb = kcalloc(maxtype + 1, sizeof(*tb), GFP_KERNEL); + tb = kzalloc_objs(*tb, maxtype + 1); if (!tb) return ERR_PTR(-ENOMEM); diff --git a/net/devlink/param.c b/net/devlink/param.c index 8ca0f3ed646c..95ac9db8c993 100644 --- a/net/devlink/param.c +++ b/net/devlink/param.c @@ -330,13 +330,12 @@ static int devlink_nl_param_fill(struct sk_buff *msg, struct devlink *devlink, int err; int i; - default_value = kcalloc(DEVLINK_PARAM_CMODE_MAX + 1, - sizeof(*default_value), GFP_KERNEL); + default_value = kzalloc_objs(*default_value, + DEVLINK_PARAM_CMODE_MAX + 1); if (!default_value) return -ENOMEM; - param_value = kcalloc(DEVLINK_PARAM_CMODE_MAX + 1, - sizeof(*param_value), GFP_KERNEL); + param_value = kzalloc_objs(*param_value, DEVLINK_PARAM_CMODE_MAX + 1); if (!param_value) { kfree(default_value); return -ENOMEM; diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c index 0483519b7fb0..7a362f2e2c2b 100644 --- a/net/ipv4/fib_semantics.c +++ b/net/ipv4/fib_semantics.c @@ -874,7 +874,7 @@ static void fib_rebalance(struct fib_info *fi) change_nexthops(fi) { int upper_bound; - if (nexthop_nh->fib_nh_flags & RTNH_F_DEAD) { + if (!total || nexthop_nh->fib_nh_flags & RTNH_F_DEAD) { upper_bound = -1; } else if (ip_ignore_linkdown(nexthop_nh->fib_nh_dev) && nexthop_nh->fib_nh_flags & RTNH_F_LINKDOWN) { diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c index b80b8a92f46e..d56355aca797 100644 --- a/net/ipv4/igmp.c +++ b/net/ipv4/igmp.c @@ -188,6 +188,10 @@ static void ip_ma_put(struct ip_mc_list *im) } } +#define pmc_dereference(e, pmc) \ + rcu_dereference_protected(e, lockdep_is_held(&(pmc)->lock) || \ + lockdep_is_held(&(pmc)->interface->mc_tomb_lock)) + #define for_each_pmc_rcu(in_dev, pmc) \ for (pmc = rcu_dereference(in_dev->mc_list); \ pmc != NULL; \ @@ -198,13 +202,28 @@ static void ip_ma_put(struct ip_mc_list *im) pmc != NULL; \ pmc = rtnl_dereference(pmc->next_rcu)) +#define for_each_psf_mclock(pmc, psf) \ + for (psf = pmc_dereference((pmc)->sources, pmc); \ + psf; \ + psf = pmc_dereference(psf->sf_next, pmc)) + +#define for_each_psf_rcu(im, psf) \ + for (psf = rcu_dereference((im)->sources); \ + psf; \ + psf = rcu_dereference(psf->sf_next)) + +#define for_each_psf_tomb(pmc, psf) \ + for (psf = pmc_dereference((pmc)->tomb, pmc); \ + psf; \ + psf = pmc_dereference(psf->sf_next, pmc)) + static void ip_sf_list_clear_all(struct ip_sf_list *psf) { struct ip_sf_list *next; while (psf) { - next = psf->sf_next; - kfree(psf); + next = rcu_dereference_protected(psf->sf_next, 1); + kfree_rcu(psf, rcu); psf = next; } } @@ -349,7 +368,7 @@ igmp_scount(struct ip_mc_list *pmc, int type, int gdeleted, int sdeleted) struct ip_sf_list *psf; int scount = 0; - for (psf = pmc->sources; psf; psf = psf->sf_next) { + for_each_psf_mclock(pmc, psf) { if (!is_in(pmc, psf, type, gdeleted, sdeleted)) continue; scount++; @@ -494,7 +513,8 @@ static struct sk_buff *add_grec(struct sk_buff *skb, struct ip_mc_list *pmc, struct net *net = dev_net(dev); struct igmpv3_report *pih; struct igmpv3_grec *pgr = NULL; - struct ip_sf_list *psf, *psf_next, *psf_prev, **psf_list; + struct ip_sf_list *psf, *psf_next, *psf_prev; + struct ip_sf_list __rcu **psf_list; int scount, stotal, first, isquery, truncate; unsigned int mtu; @@ -517,7 +537,7 @@ static struct sk_buff *add_grec(struct sk_buff *skb, struct ip_mc_list *pmc, psf_list = sdeleted ? &pmc->tomb : &pmc->sources; - if (!*psf_list) + if (!rcu_access_pointer(*psf_list)) goto empty_source; pih = skb ? igmpv3_report_hdr(skb) : NULL; @@ -533,10 +553,12 @@ static struct sk_buff *add_grec(struct sk_buff *skb, struct ip_mc_list *pmc, } first = 1; psf_prev = NULL; - for (psf = *psf_list; psf; psf = psf_next) { + for (psf = pmc_dereference(*psf_list, pmc); + psf; + psf = psf_next) { __be32 *psrc; - psf_next = psf->sf_next; + psf_next = pmc_dereference(psf->sf_next, pmc); if (!is_in(pmc, psf, type, gdeleted, sdeleted)) { psf_prev = psf; @@ -583,10 +605,12 @@ decrease_sf_crcount: psf->sf_crcount--; if ((sdeleted || gdeleted) && psf->sf_crcount == 0) { if (psf_prev) - psf_prev->sf_next = psf->sf_next; + rcu_assign_pointer(psf_prev->sf_next, + psf_next); else - *psf_list = psf->sf_next; - kfree(psf); + rcu_assign_pointer(*psf_list, + psf_next); + kfree_rcu(psf, rcu); continue; } } @@ -655,28 +679,29 @@ static int igmpv3_send_report(struct in_device *in_dev, struct ip_mc_list *pmc) /* * remove zero-count source records from a source filter list */ -static void igmpv3_clear_zeros(struct ip_sf_list **ppsf) +static void igmpv3_clear_zeros(struct ip_sf_list __rcu **ppsf) { struct ip_sf_list *psf_prev, *psf_next, *psf; psf_prev = NULL; - for (psf = *ppsf; psf; psf = psf_next) { - psf_next = psf->sf_next; + for (psf = rcu_dereference_protected(*ppsf, 1); psf; psf = psf_next) { + psf_next = rcu_dereference_protected(psf->sf_next, 1); if (psf->sf_crcount == 0) { if (psf_prev) - psf_prev->sf_next = psf->sf_next; + rcu_assign_pointer(psf_prev->sf_next, psf_next); else - *ppsf = psf->sf_next; - kfree(psf); - } else + rcu_assign_pointer(*ppsf, psf_next); + kfree_rcu(psf, rcu); + } else { psf_prev = psf; + } } } static void kfree_pmc(struct ip_mc_list *pmc) { - ip_sf_list_clear_all(pmc->sources); - ip_sf_list_clear_all(pmc->tomb); + ip_sf_list_clear_all(rcu_dereference_protected(pmc->sources, 1)); + ip_sf_list_clear_all(rcu_dereference_protected(pmc->tomb, 1)); kfree(pmc); } @@ -710,7 +735,8 @@ static void igmpv3_send_cr(struct in_device *in_dev) igmpv3_clear_zeros(&pmc->sources); } } - if (pmc->crcount == 0 && !pmc->tomb && !pmc->sources) { + if (pmc->crcount == 0 && !rcu_access_pointer(pmc->tomb) && + !rcu_access_pointer(pmc->sources)) { if (pmc_prev) pmc_prev->next = pmc_next; else @@ -896,7 +922,7 @@ static int igmp_xmarksources(struct ip_mc_list *pmc, int nsrcs, __be32 *srcs) int i, scount; scount = 0; - for (psf = pmc->sources; psf; psf = psf->sf_next) { + for_each_psf_mclock(pmc, psf) { if (scount == nsrcs) break; for (i = 0; i < nsrcs; i++) { @@ -927,7 +953,7 @@ static int igmp_marksources(struct ip_mc_list *pmc, int nsrcs, __be32 *srcs) /* mark INCLUDE-mode sources */ scount = 0; - for (psf = pmc->sources; psf; psf = psf->sf_next) { + for_each_psf_mclock(pmc, psf) { if (scount == nsrcs) break; for (i = 0; i < nsrcs; i++) @@ -1228,11 +1254,12 @@ static void igmpv3_add_delrec(struct in_device *in_dev, struct ip_mc_list *im, if (pmc->sfmode == MCAST_INCLUDE) { struct ip_sf_list *psf; + for_each_psf_mclock(im, psf) + psf->sf_crcount = pmc->crcount; pmc->tomb = im->tomb; pmc->sources = im->sources; - im->tomb = im->sources = NULL; - for (psf = pmc->sources; psf; psf = psf->sf_next) - psf->sf_crcount = pmc->crcount; + RCU_INIT_POINTER(im->tomb, NULL); + RCU_INIT_POINTER(im->sources, NULL); } spin_unlock_bh(&im->lock); @@ -1271,9 +1298,18 @@ static void igmpv3_del_delrec(struct in_device *in_dev, struct ip_mc_list *im) if (pmc) { im->interface = pmc->interface; if (im->sfmode == MCAST_INCLUDE) { - swap(im->tomb, pmc->tomb); - swap(im->sources, pmc->sources); - for (psf = im->sources; psf; psf = psf->sf_next) + struct ip_sf_list *sources, *tomb; + + tomb = rcu_replace_pointer(im->tomb, + rcu_dereference_protected(pmc->tomb, 1), + lockdep_is_held(&im->lock)); + rcu_assign_pointer(pmc->tomb, tomb); + + sources = rcu_replace_pointer(im->sources, + rcu_dereference_protected(pmc->sources, 1), + lockdep_is_held(&im->lock)); + rcu_assign_pointer(pmc->sources, sources); + for_each_psf_mclock(im, psf) psf->sf_crcount = in_dev->mr_qrv ?: READ_ONCE(net->ipv4.sysctl_igmp_qrv); } else { @@ -1310,8 +1346,8 @@ static void igmpv3_clear_delrec(struct in_device *in_dev) struct ip_sf_list *psf; spin_lock_bh(&pmc->lock); - psf = pmc->tomb; - pmc->tomb = NULL; + psf = pmc_dereference(pmc->tomb, pmc); + RCU_INIT_POINTER(pmc->tomb, NULL); spin_unlock_bh(&pmc->lock); ip_sf_list_clear_all(psf); } @@ -1990,7 +2026,7 @@ static int ip_mc_del1_src(struct ip_mc_list *pmc, int sfmode, int rv = 0; psf_prev = NULL; - for (psf = pmc->sources; psf; psf = psf->sf_next) { + for_each_psf_mclock(pmc, psf) { if (psf->sf_inaddr == *psfsrc) break; psf_prev = psf; @@ -1999,7 +2035,7 @@ static int ip_mc_del1_src(struct ip_mc_list *pmc, int sfmode, /* source filter not found, or count wrong => bug */ return -ESRCH; } - psf->sf_count[sfmode]--; + WRITE_ONCE(psf->sf_count[sfmode], psf->sf_count[sfmode] - 1); if (psf->sf_count[sfmode] == 0) { ip_rt_multicast_event(pmc->interface); } @@ -2011,19 +2047,28 @@ static int ip_mc_del1_src(struct ip_mc_list *pmc, int sfmode, /* no more filters for this source */ if (psf_prev) - psf_prev->sf_next = psf->sf_next; + rcu_assign_pointer(psf_prev->sf_next, + pmc_dereference(psf->sf_next, pmc)); else - pmc->sources = psf->sf_next; + rcu_assign_pointer(pmc->sources, + pmc_dereference(psf->sf_next, pmc)); #ifdef CONFIG_IP_MULTICAST if (psf->sf_oldin && !IGMP_V1_SEEN(in_dev) && !IGMP_V2_SEEN(in_dev)) { - psf->sf_crcount = in_dev->mr_qrv ?: READ_ONCE(net->ipv4.sysctl_igmp_qrv); - psf->sf_next = pmc->tomb; - pmc->tomb = psf; - rv = 1; - } else + struct ip_sf_list *dpsf = kmalloc_obj(*dpsf, GFP_ATOMIC); + + if (dpsf) { + *dpsf = *psf; + dpsf->sf_crcount = in_dev->mr_qrv ?: + READ_ONCE(net->ipv4.sysctl_igmp_qrv); + rcu_assign_pointer(dpsf->sf_next, + pmc_dereference(pmc->tomb, pmc)); + rcu_assign_pointer(pmc->tomb, dpsf); + rv = 1; + } + } #endif - kfree(psf); + kfree_rcu(psf, rcu); } return rv; } @@ -2060,7 +2105,7 @@ static int ip_mc_del_src(struct in_device *in_dev, __be32 *pmca, int sfmode, err = -EINVAL; if (!pmc->sfcount[sfmode]) goto out_unlock; - pmc->sfcount[sfmode]--; + WRITE_ONCE(pmc->sfcount[sfmode], pmc->sfcount[sfmode] - 1); } err = 0; for (i = 0; i < sfcount; i++) { @@ -2083,7 +2128,7 @@ static int ip_mc_del_src(struct in_device *in_dev, __be32 *pmca, int sfmode, #ifdef CONFIG_IP_MULTICAST pmc->crcount = in_dev->mr_qrv ?: READ_ONCE(net->ipv4.sysctl_igmp_qrv); WRITE_ONCE(in_dev->mr_ifc_count, pmc->crcount); - for (psf = pmc->sources; psf; psf = psf->sf_next) + for_each_psf_mclock(pmc, psf) psf->sf_crcount = 0; igmp_ifc_event(pmc->interface); } else if (sf_setstate(pmc) || changerec) { @@ -2104,7 +2149,7 @@ static int ip_mc_add1_src(struct ip_mc_list *pmc, int sfmode, struct ip_sf_list *psf, *psf_prev; psf_prev = NULL; - for (psf = pmc->sources; psf; psf = psf->sf_next) { + for_each_psf_mclock(pmc, psf) { if (psf->sf_inaddr == *psfsrc) break; psf_prev = psf; @@ -2114,12 +2159,12 @@ static int ip_mc_add1_src(struct ip_mc_list *pmc, int sfmode, if (!psf) return -ENOBUFS; psf->sf_inaddr = *psfsrc; - if (psf_prev) { - psf_prev->sf_next = psf; - } else - pmc->sources = psf; + if (psf_prev) + rcu_assign_pointer(psf_prev->sf_next, psf); + else + rcu_assign_pointer(pmc->sources, psf); } - psf->sf_count[sfmode]++; + WRITE_ONCE(psf->sf_count[sfmode], psf->sf_count[sfmode] + 1); if (psf->sf_count[sfmode] == 1) { ip_rt_multicast_event(pmc->interface); } @@ -2132,13 +2177,15 @@ static void sf_markstate(struct ip_mc_list *pmc) struct ip_sf_list *psf; int mca_xcount = pmc->sfcount[MCAST_EXCLUDE]; - for (psf = pmc->sources; psf; psf = psf->sf_next) + for_each_psf_mclock(pmc, psf) { if (pmc->sfcount[MCAST_EXCLUDE]) { psf->sf_oldin = mca_xcount == psf->sf_count[MCAST_EXCLUDE] && !psf->sf_count[MCAST_INCLUDE]; - } else + } else { psf->sf_oldin = psf->sf_count[MCAST_INCLUDE] != 0; + } + } } static int sf_setstate(struct ip_mc_list *pmc) @@ -2149,27 +2196,31 @@ static int sf_setstate(struct ip_mc_list *pmc) int new_in, rv; rv = 0; - for (psf = pmc->sources; psf; psf = psf->sf_next) { + for_each_psf_mclock(pmc, psf) { if (pmc->sfcount[MCAST_EXCLUDE]) { new_in = mca_xcount == psf->sf_count[MCAST_EXCLUDE] && !psf->sf_count[MCAST_INCLUDE]; - } else + } else { new_in = psf->sf_count[MCAST_INCLUDE] != 0; + } if (new_in) { if (!psf->sf_oldin) { struct ip_sf_list *prev = NULL; - for (dpsf = pmc->tomb; dpsf; dpsf = dpsf->sf_next) { + for_each_psf_tomb(pmc, dpsf) { if (dpsf->sf_inaddr == psf->sf_inaddr) break; prev = dpsf; } if (dpsf) { + struct ip_sf_list *dpsf_next; + + dpsf_next = pmc_dereference(dpsf->sf_next, pmc); if (prev) - prev->sf_next = dpsf->sf_next; + rcu_assign_pointer(prev->sf_next, dpsf_next); else - pmc->tomb = dpsf->sf_next; - kfree(dpsf); + rcu_assign_pointer(pmc->tomb, dpsf_next); + kfree_rcu(dpsf, rcu); } psf->sf_crcount = qrv; rv++; @@ -2181,17 +2232,19 @@ static int sf_setstate(struct ip_mc_list *pmc) * add or update "delete" records if an active filter * is now inactive */ - for (dpsf = pmc->tomb; dpsf; dpsf = dpsf->sf_next) + for_each_psf_tomb(pmc, dpsf) { if (dpsf->sf_inaddr == psf->sf_inaddr) break; + } if (!dpsf) { dpsf = kmalloc_obj(*dpsf, GFP_ATOMIC); if (!dpsf) continue; *dpsf = *psf; /* pmc->lock held by callers */ - dpsf->sf_next = pmc->tomb; - pmc->tomb = dpsf; + rcu_assign_pointer(dpsf->sf_next, + pmc_dereference(pmc->tomb, pmc)); + rcu_assign_pointer(pmc->tomb, dpsf); } dpsf->sf_crcount = qrv; rv++; @@ -2231,7 +2284,7 @@ static int ip_mc_add_src(struct in_device *in_dev, __be32 *pmca, int sfmode, #endif isexclude = pmc->sfmode == MCAST_EXCLUDE; if (!delta) - pmc->sfcount[sfmode]++; + WRITE_ONCE(pmc->sfcount[sfmode], pmc->sfcount[sfmode] + 1); err = 0; for (i = 0; i < sfcount; i++) { err = ip_mc_add1_src(pmc, sfmode, &psfsrc[i]); @@ -2242,7 +2295,7 @@ static int ip_mc_add_src(struct in_device *in_dev, __be32 *pmca, int sfmode, int j; if (!delta) - pmc->sfcount[sfmode]--; + WRITE_ONCE(pmc->sfcount[sfmode], pmc->sfcount[sfmode] - 1); for (j = 0; j < i; j++) (void) ip_mc_del1_src(pmc, sfmode, &psfsrc[j]); } else if (isexclude != (pmc->sfcount[MCAST_EXCLUDE] != 0)) { @@ -2262,7 +2315,7 @@ static int ip_mc_add_src(struct in_device *in_dev, __be32 *pmca, int sfmode, pmc->crcount = in_dev->mr_qrv ?: READ_ONCE(net->ipv4.sysctl_igmp_qrv); WRITE_ONCE(in_dev->mr_ifc_count, pmc->crcount); - for (psf = pmc->sources; psf; psf = psf->sf_next) + for_each_psf_mclock(pmc, psf) psf->sf_crcount = 0; igmp_ifc_event(in_dev); } else if (sf_setstate(pmc)) { @@ -2278,13 +2331,13 @@ static void ip_mc_clear_src(struct ip_mc_list *pmc) struct ip_sf_list *tomb, *sources; spin_lock_bh(&pmc->lock); - tomb = pmc->tomb; - pmc->tomb = NULL; - sources = pmc->sources; - pmc->sources = NULL; + tomb = pmc_dereference(pmc->tomb, pmc); + RCU_INIT_POINTER(pmc->tomb, NULL); + sources = pmc_dereference(pmc->sources, pmc); + RCU_INIT_POINTER(pmc->sources, NULL); pmc->sfmode = MCAST_EXCLUDE; - pmc->sfcount[MCAST_INCLUDE] = 0; - pmc->sfcount[MCAST_EXCLUDE] = 1; + WRITE_ONCE(pmc->sfcount[MCAST_INCLUDE], 0); + WRITE_ONCE(pmc->sfcount[MCAST_EXCLUDE], 1); spin_unlock_bh(&pmc->lock); ip_sf_list_clear_all(tomb); @@ -2866,20 +2919,19 @@ int ip_check_mc_rcu(struct in_device *in_dev, __be32 mc_addr, __be32 src_addr, u rv = 1; } else if (im) { if (src_addr) { - spin_lock_bh(&im->lock); - for (psf = im->sources; psf; psf = psf->sf_next) { + for_each_psf_rcu(im, psf) { if (psf->sf_inaddr == src_addr) break; } if (psf) - rv = psf->sf_count[MCAST_INCLUDE] || - psf->sf_count[MCAST_EXCLUDE] != - im->sfcount[MCAST_EXCLUDE]; + rv = READ_ONCE(psf->sf_count[MCAST_INCLUDE]) || + READ_ONCE(psf->sf_count[MCAST_EXCLUDE]) != + READ_ONCE(im->sfcount[MCAST_EXCLUDE]); else - rv = im->sfcount[MCAST_EXCLUDE] != 0; - spin_unlock_bh(&im->lock); - } else + rv = READ_ONCE(im->sfcount[MCAST_EXCLUDE]) != 0; + } else { rv = 1; /* unspecified source; tentatively allow */ + } } return rv; } @@ -3043,7 +3095,7 @@ static inline struct ip_sf_list *igmp_mcf_get_first(struct seq_file *seq) im = rcu_dereference(idev->mc_list); if (likely(im)) { spin_lock_bh(&im->lock); - psf = im->sources; + psf = pmc_dereference(im->sources, im); if (likely(psf)) { state->im = im; state->idev = idev; @@ -3059,7 +3111,7 @@ static struct ip_sf_list *igmp_mcf_get_next(struct seq_file *seq, struct ip_sf_l { struct igmp_mcf_iter_state *state = igmp_mcf_seq_private(seq); - psf = psf->sf_next; + psf = pmc_dereference(psf->sf_next, state->im); while (!psf) { spin_unlock_bh(&state->im->lock); state->im = state->im->next; @@ -3075,7 +3127,7 @@ static struct ip_sf_list *igmp_mcf_get_next(struct seq_file *seq, struct ip_sf_l state->im = rcu_dereference(state->idev->mc_list); } spin_lock_bh(&state->im->lock); - psf = state->im->sources; + psf = pmc_dereference(state->im->sources, state->im); } out: return psf; diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index b4237d0e994d..1c867a302444 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -3182,8 +3182,7 @@ void __tcp_close(struct sock *sk, long timeout) /* Unread data was tossed, zap the connection. */ NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPABORTONCLOSE); tcp_set_state(sk, TCP_CLOSE); - tcp_send_active_reset(sk, sk->sk_allocation, - SK_RST_REASON_TCP_ABORT_ON_CLOSE); + tcp_send_active_reset(sk, SK_RST_REASON_TCP_ABORT_ON_CLOSE); } else if (sock_flag(sk, SOCK_LINGER) && !sk->sk_lingertime) { /* Check zero linger _after_ checking for unread data. */ sk->sk_prot->disconnect(sk, 0); @@ -3257,7 +3256,7 @@ adjudge_to_death: struct tcp_sock *tp = tcp_sk(sk); if (READ_ONCE(tp->linger2) < 0) { tcp_set_state(sk, TCP_CLOSE); - tcp_send_active_reset(sk, GFP_ATOMIC, + tcp_send_active_reset(sk, SK_RST_REASON_TCP_ABORT_ON_LINGER); __NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPABORTONLINGER); @@ -3276,7 +3275,7 @@ adjudge_to_death: if (sk->sk_state != TCP_CLOSE) { if (tcp_check_oom(sk, 0)) { tcp_set_state(sk, TCP_CLOSE); - tcp_send_active_reset(sk, GFP_ATOMIC, + tcp_send_active_reset(sk, SK_RST_REASON_TCP_ABORT_ON_MEMORY); __NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPABORTONMEMORY); @@ -3377,14 +3376,14 @@ int tcp_disconnect(struct sock *sk, int flags) } else if (unlikely(tp->repair)) { WRITE_ONCE(sk->sk_err, ECONNABORTED); } else if (tcp_need_reset(old_state)) { - tcp_send_active_reset(sk, gfp_any(), SK_RST_REASON_TCP_STATE); + tcp_send_active_reset(sk, SK_RST_REASON_TCP_STATE); WRITE_ONCE(sk->sk_err, ECONNRESET); } else if (tp->snd_nxt != tp->write_seq && (1 << old_state) & (TCPF_CLOSING | TCPF_LAST_ACK)) { /* The last check adjusts for discrepancy of Linux wrt. RFC * states */ - tcp_send_active_reset(sk, gfp_any(), + tcp_send_active_reset(sk, SK_RST_REASON_TCP_DISCONNECT_WITH_DATA); WRITE_ONCE(sk->sk_err, ECONNRESET); } else if (old_state == TCP_SYN_SENT) @@ -4562,9 +4561,11 @@ int do_tcp_getsockopt(struct sock *sk, int level, if (copy_from_sockptr(&len, optlen, sizeof(int))) return -EFAULT; - ca_ops = icsk->icsk_ca_ops; + rcu_read_lock(); + ca_ops = READ_ONCE(icsk->icsk_ca_ops); if (ca_ops && ca_ops->get_info) sz = ca_ops->get_info(sk, ~0U, &attr, &info); + rcu_read_unlock(); len = min_t(unsigned int, len, sz); if (copy_to_sockptr(optlen, &len, sizeof(int))) @@ -4577,16 +4578,24 @@ int do_tcp_getsockopt(struct sock *sk, int level, val = !inet_csk_in_pingpong_mode(sk); break; - case TCP_CONGESTION: + case TCP_CONGESTION: { + char ca_name[TCP_CA_NAME_MAX] = {}; + if (copy_from_sockptr(&len, optlen, sizeof(int))) return -EFAULT; len = min_t(unsigned int, len, TCP_CA_NAME_MAX); if (copy_to_sockptr(optlen, &len, sizeof(int))) return -EFAULT; - if (copy_to_sockptr(optval, icsk->icsk_ca_ops->name, len)) + + rcu_read_lock(); + memcpy(ca_name, READ_ONCE(icsk->icsk_ca_ops)->name, + sizeof(ca_name)); + rcu_read_unlock(); + + if (copy_to_sockptr(optval, ca_name, len)) return -EFAULT; return 0; - + } case TCP_ULP: if (copy_from_sockptr(&len, optlen, sizeof(int))) return -EFAULT; @@ -5147,8 +5156,7 @@ int tcp_abort(struct sock *sk, int err) bh_lock_sock(sk); if (tcp_need_reset(sk->sk_state)) - tcp_send_active_reset(sk, GFP_ATOMIC, - SK_RST_REASON_TCP_STATE); + tcp_send_active_reset(sk, SK_RST_REASON_TCP_STATE); tcp_done_with_error(sk, err); bh_unlock_sock(sk); diff --git a/net/ipv4/tcp_cong.c b/net/ipv4/tcp_cong.c index e9f6c77e0631..8e83ef81fc18 100644 --- a/net/ipv4/tcp_cong.c +++ b/net/ipv4/tcp_cong.c @@ -223,7 +223,7 @@ void tcp_assign_congestion_control(struct sock *sk) ca = rcu_dereference(net->ipv4.tcp_congestion_control); if (unlikely(!bpf_try_module_get(ca, ca->owner))) ca = &tcp_reno; - icsk->icsk_ca_ops = ca; + WRITE_ONCE(icsk->icsk_ca_ops, ca); rcu_read_unlock(); memset(icsk->icsk_ca_priv, 0, sizeof(icsk->icsk_ca_priv)); @@ -253,7 +253,7 @@ static void tcp_reinit_congestion_control(struct sock *sk, struct inet_connection_sock *icsk = inet_csk(sk); tcp_cleanup_congestion_control(sk); - icsk->icsk_ca_ops = ca; + WRITE_ONCE(icsk->icsk_ca_ops, ca); icsk->icsk_ca_setsockopt = 1; memset(icsk->icsk_ca_priv, 0, sizeof(icsk->icsk_ca_priv)); diff --git a/net/ipv4/tcp_dctcp.c b/net/ipv4/tcp_dctcp.c index 274e628e7cf8..5b457f68a581 100644 --- a/net/ipv4/tcp_dctcp.c +++ b/net/ipv4/tcp_dctcp.c @@ -111,7 +111,7 @@ __bpf_kfunc static void dctcp_init(struct sock *sk) /* No ECN support? Fall back to Reno. Also need to clear * ECT from sk since it is set during 3WHS for DCTCP. */ - inet_csk(sk)->icsk_ca_ops = &dctcp_reno; + WRITE_ONCE(inet_csk(sk)->icsk_ca_ops, &dctcp_reno); INET_ECN_dontxmit(sk); } @@ -228,7 +228,7 @@ static size_t dctcp_get_info(struct sock *sk, u32 ext, int *attr, if (ext & (1 << (INET_DIAG_DCTCPINFO - 1)) || ext & (1 << (INET_DIAG_VEGASINFO - 1))) { memset(&info->dctcp, 0, sizeof(info->dctcp)); - if (inet_csk(sk)->icsk_ca_ops != &dctcp_reno) { + if (READ_ONCE(inet_csk(sk)->icsk_ca_ops) != &dctcp_reno) { info->dctcp.dctcp_enabled = 1; info->dctcp.dctcp_ce_state = (u16) ca->ce_state; info->dctcp.dctcp_alpha = ca->dctcp_alpha; diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 9f053eb8b46e..04dbb2babbcd 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -2931,8 +2931,8 @@ static int bpf_iter_tcp_realloc_batch(struct bpf_tcp_iter_state *iter, { union bpf_tcp_iter_batch_item *new_batch; - new_batch = kvmalloc_array(new_batch_sz, sizeof(*new_batch), - flags | __GFP_NOWARN); + new_batch = kvmalloc_objs(*new_batch, new_batch_sz, + flags | __GFP_NOWARN); if (!new_batch) return -ENOMEM; diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index f3fa0b18eda0..0ddfd5af6e58 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -507,7 +507,7 @@ void tcp_ca_openreq_child(struct sock *sk, const struct dst_entry *dst) ca = tcp_ca_find_key(ca_key); if (likely(ca && bpf_try_module_get(ca, ca->owner))) { icsk->icsk_ca_dst_locked = tcp_ca_dst_locked(dst); - icsk->icsk_ca_ops = ca; + WRITE_ONCE(icsk->icsk_ca_ops, ca); ca_got_dst = true; } rcu_read_unlock(); diff --git a/net/ipv4/tcp_offload.c b/net/ipv4/tcp_offload.c index 3b1fdcd3cb29..e74d99ca9fac 100644 --- a/net/ipv4/tcp_offload.c +++ b/net/ipv4/tcp_offload.c @@ -332,6 +332,7 @@ struct sk_buff *tcp_gro_receive(struct list_head *head, struct sk_buff *skb, flush |= skb->ip_summed != p->ip_summed; flush |= skb->csum_level != p->csum_level; flush |= NAPI_GRO_CB(p)->count >= 64; + flush |= NAPI_GRO_CB(p)->is_flist != NAPI_GRO_CB(skb)->is_flist; skb_set_network_header(skb, skb_gro_receive_network_offset(skb)); if (flush || skb_gro_receive_list(p, skb)) @@ -395,12 +396,20 @@ static void tcp4_check_fraglist_gro(struct list_head *head, struct sk_buff *skb, struct net *net; int iif, sdif; - if (likely(!(skb->dev->features & NETIF_F_GRO_FRAGLIST))) - return; - p = tcp_gro_lookup(head, th); if (p) { - NAPI_GRO_CB(skb)->is_flist = NAPI_GRO_CB(p)->is_flist; + /* flist GRO applies to consecutive non-GSO skbs */ + if (!skb_is_gso(skb) || !NAPI_GRO_CB(p)->is_flist) { + NAPI_GRO_CB(skb)->is_flist = NAPI_GRO_CB(p)->is_flist; + return; + } + + /* Fall back to the regular GRO path */ + if (NAPI_GRO_CB(p)->count == 1) + NAPI_GRO_CB(p)->is_flist = 0; + + NAPI_GRO_CB(skb)->is_flist = 0; + return; } @@ -410,7 +419,7 @@ static void tcp4_check_fraglist_gro(struct list_head *head, struct sk_buff *skb, sk = __inet_lookup_established(net, iph->saddr, th->source, iph->daddr, ntohs(th->dest), iif, sdif); - NAPI_GRO_CB(skb)->is_flist = !sk; + NAPI_GRO_CB(skb)->is_flist = !sk && !skb_is_gso(skb); if (sk) sock_gen_put(sk); } @@ -430,7 +439,8 @@ struct sk_buff *tcp4_gro_receive(struct list_head *head, struct sk_buff *skb) if (!th) goto flush; - tcp4_check_fraglist_gro(head, skb, th); + if (unlikely(skb->dev->features & NETIF_F_GRO_FRAGLIST)) + tcp4_check_fraglist_gro(head, skb, th); return tcp_gro_receive(head, skb, th); diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 6f4dca4a4de9..d960e3de7d50 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -3849,9 +3849,9 @@ void tcp_send_fin(struct sock *sk) * was unread data in the receive queue. This behavior is recommended * by RFC 2525, section 2.17. -DaveM */ -void tcp_send_active_reset(struct sock *sk, gfp_t priority, - enum sk_rst_reason reason) +void tcp_send_active_reset(struct sock *sk, enum sk_rst_reason reason) { + gfp_t priority = sk_gfp_mask(sk, GFP_ATOMIC | __GFP_NOWARN); struct sk_buff *skb; TCP_INC_STATS(sock_net(sk), TCP_MIB_OUTRSTS); @@ -4092,7 +4092,7 @@ static void tcp_ca_dst_init(struct sock *sk, const struct dst_entry *dst) if (likely(ca && bpf_try_module_get(ca, ca->owner))) { bpf_module_put(icsk->icsk_ca_ops, icsk->icsk_ca_ops->owner); icsk->icsk_ca_dst_locked = tcp_ca_dst_locked(dst); - icsk->icsk_ca_ops = ca; + WRITE_ONCE(icsk->icsk_ca_ops, ca); } rcu_read_unlock(); } diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c index 1038e7ba9c2e..e56eae4bc341 100644 --- a/net/ipv4/tcp_timer.c +++ b/net/ipv4/tcp_timer.c @@ -126,7 +126,7 @@ static int tcp_out_of_resources(struct sock *sk, bool do_reset) (!tp->snd_wnd && !tp->packets_out)) do_reset = true; if (do_reset) - tcp_send_active_reset(sk, GFP_ATOMIC, + tcp_send_active_reset(sk, SK_RST_REASON_TCP_ABORT_ON_MEMORY); tcp_done(sk); __NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPABORTONMEMORY); @@ -809,7 +809,7 @@ static void tcp_keepalive_timer(struct timer_list *t) goto out; } } - tcp_send_active_reset(sk, GFP_ATOMIC, SK_RST_REASON_TCP_STATE); + tcp_send_active_reset(sk, SK_RST_REASON_TCP_STATE); goto death; } @@ -836,7 +836,7 @@ static void tcp_keepalive_timer(struct timer_list *t) icsk->icsk_probes_out > 0) || (user_timeout == 0 && icsk->icsk_probes_out >= keepalive_probes(tp))) { - tcp_send_active_reset(sk, GFP_ATOMIC, + tcp_send_active_reset(sk, SK_RST_REASON_TCP_KEEPALIVE_TIMEOUT); tcp_write_err(sk); goto out; diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index af9603217444..bb8cfc62cb00 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -900,6 +900,15 @@ out: return sk; } +static void udp_err_update_exception(struct net *net, struct sk_buff *skb, + int type, int code, u32 info) +{ + if (type == ICMP_DEST_UNREACH && code == ICMP_FRAG_NEEDED) + ipv4_update_pmtu(skb, net, info, 0, IPPROTO_UDP); + else if (type == ICMP_REDIRECT) + ipv4_redirect(skb, net, 0, IPPROTO_UDP); +} + /* * This routine is called by the ICMP module when it gets some * sort of error condition. If err < 0 then the socket should @@ -923,6 +932,8 @@ int udp_err(struct sk_buff *skb, u32 info) int harderr; int err; + udp_err_update_exception(net, skb, type, code, info); + uh = (struct udphdr *)(skb->data + (iph->ihl << 2)); sk = __udp4_lib_lookup(net, iph->daddr, uh->dest, iph->saddr, uh->source, skb->dev->ifindex, @@ -2166,10 +2177,10 @@ int __udp_disconnect(struct sock *sk, int flags) */ sk->sk_state = TCP_CLOSE; - inet->inet_daddr = 0; + WRITE_ONCE(inet->inet_daddr, 0); inet->inet_dport = 0; sock_rps_reset_rxhash(sk); - sk->sk_bound_dev_if = 0; + WRITE_ONCE(sk->sk_bound_dev_if, 0); if (!(sk->sk_userlocks & SOCK_BINDADDR_LOCK)) { inet_reset_saddr(sk); if (sk->sk_prot->rehash && diff --git a/net/ipv6/exthdrs.c b/net/ipv6/exthdrs.c index 51941ad656a3..09a4552f7f08 100644 --- a/net/ipv6/exthdrs.c +++ b/net/ipv6/exthdrs.c @@ -445,7 +445,7 @@ looped_back: hdr->segments_left--; addr = hdr->segments + hdr->segments_left; - skb_push(skb, sizeof(struct ipv6hdr)); + skb_push(skb, -skb_network_offset(skb)); if (skb->ip_summed == CHECKSUM_COMPLETE) seg6_update_csum(skb); @@ -469,7 +469,7 @@ looped_back: } ipv6_hdr(skb)->hop_limit--; - skb_pull(skb, sizeof(struct ipv6hdr)); + skb_pull(skb, skb_transport_offset(skb)); goto looped_back; } diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c index 69c51f1a5bf0..8ebda0b6a78b 100644 --- a/net/ipv6/ip6_gre.c +++ b/net/ipv6/ip6_gre.c @@ -878,6 +878,7 @@ static int ip6gre_xmit_other(struct sk_buff *skb, struct net_device *dev) static netdev_tx_t ip6gre_tunnel_xmit(struct sk_buff *skb, struct net_device *dev) { + struct ip_tunnel_info *tun_info = NULL; struct ip6_tnl *t = netdev_priv(dev); __be16 payload_protocol; int ret; @@ -888,6 +889,9 @@ static netdev_tx_t ip6gre_tunnel_xmit(struct sk_buff *skb, if (!ip6_tnl_xmit_ctl(t, &t->parms.laddr, &t->parms.raddr)) goto tx_err; + if (t->parms.collect_md) + tun_info = skb_tunnel_info_txcheck(skb); + payload_protocol = skb_protocol(skb, true); switch (payload_protocol) { case htons(ETH_P_IP): @@ -907,7 +911,7 @@ static netdev_tx_t ip6gre_tunnel_xmit(struct sk_buff *skb, return NETDEV_TX_OK; tx_err: - if (!t->parms.collect_md || !IS_ERR(skb_tunnel_info_txcheck(skb))) + if (!IS_ERR(tun_info)) DEV_STATS_INC(dev, tx_errors); DEV_STATS_INC(dev, tx_dropped); kfree_skb(skb); diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c index aaba4c2aae23..ecef55f26189 100644 --- a/net/ipv6/mcast.c +++ b/net/ipv6/mcast.c @@ -240,7 +240,8 @@ static int __ipv6_sock_mc_join(struct sock *sk, int ifindex, return err; } - mc_lst->next = np->ipv6_mc_list; + rcu_assign_pointer(mc_lst->next, + sock_dereference(np->ipv6_mc_list, sk)); rcu_assign_pointer(np->ipv6_mc_list, mc_lst); return 0; @@ -300,7 +301,8 @@ int ipv6_sock_mc_drop(struct sock *sk, int ifindex, const struct in6_addr *addr) lnk = &mc_lst->next) { if ((ifindex == 0 || mc_lst->ifindex == ifindex) && ipv6_addr_equal(&mc_lst->addr, addr)) { - *lnk = mc_lst->next; + rcu_assign_pointer(*lnk, + sock_dereference(mc_lst->next, sk)); __ipv6_sock_mc_drop(sk, mc_lst); return 0; } @@ -333,7 +335,8 @@ void __ipv6_sock_mc_close(struct sock *sk) struct ipv6_mc_socklist *mc_lst; while ((mc_lst = sock_dereference(np->ipv6_mc_list, sk)) != NULL) { - np->ipv6_mc_list = mc_lst->next; + rcu_assign_pointer(np->ipv6_mc_list, + sock_dereference(mc_lst->next, sk)); __ipv6_sock_mc_drop(sk, mc_lst); } } @@ -355,12 +358,12 @@ int ip6_mc_source(int add, int omode, struct sock *sk, { struct ipv6_pinfo *inet6 = inet6_sk(sk); struct in6_addr *source, *group; + struct ip6_sf_socklist *newpsl, *psl; struct net *net = sock_net(sk); struct ipv6_mc_socklist *pmc; - struct ip6_sf_socklist *psl; struct inet6_dev *idev; int leavegroup = 0; - int i, j, rv; + int i, j; int err; source = &((struct sockaddr_in6 *)&pgsr->gsr_source)->sin6_addr; @@ -409,13 +412,11 @@ int ip6_mc_source(int add, int omode, struct sock *sk, if (!add) { if (!psl) goto done; /* err = -EADDRNOTAVAIL */ - rv = !0; for (i = 0; i < psl->sl_count; i++) { - rv = !ipv6_addr_equal(&psl->sl_addr[i], source); - if (rv == 0) + if (ipv6_addr_equal(&psl->sl_addr[i], source)) break; } - if (rv) /* source not found */ + if (i == psl->sl_count) /* source not found */ goto done; /* err = -EADDRNOTAVAIL */ /* special case - (INCLUDE, empty) == LEAVE_GROUP */ @@ -424,58 +425,74 @@ int ip6_mc_source(int add, int omode, struct sock *sk, goto done; } + atomic_sub(struct_size(psl, sl_addr, psl->sl_max), + &sk->sk_omem_alloc); + + if (psl->sl_count == 1) { + newpsl = NULL; + } else { + newpsl = sock_kmalloc(sk, struct_size(newpsl, sl_addr, + psl->sl_count - 1), + GFP_KERNEL); + if (!newpsl) { + atomic_add(struct_size(psl, sl_addr, psl->sl_max), + &sk->sk_omem_alloc); + err = -ENOBUFS; + goto done; + } + newpsl->sl_max = psl->sl_count - 1; + newpsl->sl_count = psl->sl_count - 1; + for (j = 0; j < i; j++) + newpsl->sl_addr[j] = psl->sl_addr[j]; + for (j = i + 1; j < psl->sl_count; j++) + newpsl->sl_addr[j - 1] = psl->sl_addr[j]; + } + /* update the interface filter */ ip6_mc_del_src(idev, group, omode, 1, source, 1); - for (j = i+1; j < psl->sl_count; j++) - psl->sl_addr[j-1] = psl->sl_addr[j]; - psl->sl_count--; + rcu_assign_pointer(pmc->sflist, newpsl); + kfree_rcu(psl, rcu); err = 0; goto done; } /* else, add a new source to the filter */ - if (psl && psl->sl_count >= sysctl_mld_max_msf) { + if (psl && psl->sl_count >= READ_ONCE(sysctl_mld_max_msf)) { err = -ENOBUFS; goto done; } - if (!psl || psl->sl_count == psl->sl_max) { - struct ip6_sf_socklist *newpsl; - int count = IP6_SFBLOCK; - - if (psl) - count += psl->sl_max; - newpsl = sock_kmalloc(sk, struct_size(newpsl, sl_addr, count), - GFP_KERNEL); - if (!newpsl) { - err = -ENOBUFS; - goto done; - } - newpsl->sl_max = count; - newpsl->sl_count = count - IP6_SFBLOCK; - if (psl) { - for (i = 0; i < psl->sl_count; i++) - newpsl->sl_addr[i] = psl->sl_addr[i]; - atomic_sub(struct_size(psl, sl_addr, psl->sl_max), - &sk->sk_omem_alloc); + if (psl) { + for (i = 0; i < psl->sl_count; i++) { + if (ipv6_addr_equal(&psl->sl_addr[i], source)) + goto done; /* err = -EADDRNOTAVAIL */ } - rcu_assign_pointer(pmc->sflist, newpsl); - kfree_rcu(psl, rcu); - psl = newpsl; } - rv = 1; /* > 0 for insert logic below if sl_count is 0 */ - for (i = 0; i < psl->sl_count; i++) { - rv = !ipv6_addr_equal(&psl->sl_addr[i], source); - if (rv == 0) /* There is an error in the address. */ - goto done; + + i = psl ? psl->sl_count + 1 : 1; + newpsl = sock_kmalloc(sk, struct_size(newpsl, sl_addr, i), + GFP_KERNEL); + if (!newpsl) { + err = -ENOBUFS; + goto done; } - for (j = psl->sl_count-1; j >= i; j--) - psl->sl_addr[j+1] = psl->sl_addr[j]; - psl->sl_addr[i] = *source; - psl->sl_count++; - err = 0; + newpsl->sl_max = i; + newpsl->sl_count = i; + if (psl) { + for (j = 0; j < psl->sl_count; j++) + newpsl->sl_addr[j] = psl->sl_addr[j]; + } + newpsl->sl_addr[i - 1] = *source; + /* update the interface list */ ip6_mc_add_src(idev, group, omode, 1, source, 1); + + if (psl) + atomic_sub(struct_size(psl, sl_addr, psl->sl_max), + &sk->sk_omem_alloc); + rcu_assign_pointer(pmc->sflist, newpsl); + kfree_rcu(psl, rcu); + err = 0; done: mutex_unlock(&idev->mc_lock); in6_dev_put(idev); @@ -784,9 +801,11 @@ static void mld_del_delrec(struct inet6_dev *idev, struct ifmcaddr6 *im) if (!pmc) return; if (pmc_prev) - rcu_assign_pointer(pmc_prev->next, pmc->next); + rcu_assign_pointer(pmc_prev->next, + mc_dereference(pmc->next, idev)); else - rcu_assign_pointer(idev->mc_tomb, pmc->next); + rcu_assign_pointer(idev->mc_tomb, + mc_dereference(pmc->next, idev)); im->idev = pmc->idev; if (im->mca_sfmode == MCAST_INCLUDE) { @@ -966,7 +985,7 @@ static int __ipv6_dev_mc_inc(struct net_device *dev, return -ENOMEM; } - rcu_assign_pointer(mc->next, idev->mc_list); + rcu_assign_pointer(mc->next, mc_dereference(idev->mc_list, idev)); rcu_assign_pointer(idev->mc_list, mc); mld_del_delrec(idev, mc); @@ -1000,7 +1019,8 @@ int __ipv6_dev_mc_dec(struct inet6_dev *idev, const struct in6_addr *addr) WRITE_ONCE(ma->mca_users, new_users); if (new_users == 0) { - *map = ma->next; + rcu_assign_pointer(*map, + mc_dereference(ma->next, idev)); igmp6_group_dropped(ma); inet6_ifmcaddr_notify(idev->dev, ma, @@ -2351,14 +2371,18 @@ static int ip6_mc_del1_src(struct ifmcaddr6 *pmc, int sfmode, if (psf->sf_oldin && !(pmc->mca_flags & MAF_NOREPORT) && !mld_in_v1_mode(idev)) { - psf->sf_crcount = idev->mc_qrv; - rcu_assign_pointer(psf->sf_next, - mc_dereference(pmc->mca_tomb, idev)); - rcu_assign_pointer(pmc->mca_tomb, psf); - rv = 1; - } else { - kfree_rcu(psf, rcu); + struct ip6_sf_list *dpsf = kmalloc_obj(*dpsf); + + if (dpsf) { + *dpsf = *psf; + dpsf->sf_crcount = idev->mc_qrv; + rcu_assign_pointer(dpsf->sf_next, + mc_dereference(pmc->mca_tomb, idev)); + rcu_assign_pointer(pmc->mca_tomb, dpsf); + rv = 1; + } } + kfree_rcu(psf, rcu); } return rv; } @@ -2621,7 +2645,7 @@ static void ip6_mc_clear_src(struct ifmcaddr6 *pmc) static void igmp6_join_group(struct ifmcaddr6 *ma) { - unsigned long delay; + unsigned long delay, interval; mc_assert_locked(ma->idev); @@ -2630,13 +2654,17 @@ static void igmp6_join_group(struct ifmcaddr6 *ma) igmp6_send(&ma->mca_addr, ma->idev->dev, ICMPV6_MGM_REPORT); - delay = get_random_u32_below(unsolicited_report_interval(ma->idev)); + interval = unsolicited_report_interval(ma->idev); + delay = interval; if (cancel_delayed_work(&ma->mca_work)) { refcount_dec(&ma->mca_refcnt); delay = ma->mca_work.timer.expires - jiffies; } + if (delay >= interval) + delay = get_random_u32_below(interval); + if (!mod_delayed_work(mld_wq, &ma->mca_work, delay)) refcount_inc(&ma->mca_refcnt); WRITE_ONCE(ma->mca_flags, ma->mca_flags | @@ -3001,7 +3029,7 @@ static int igmp6_mc_seq_show(struct seq_file *seq, void *v) struct ifmcaddr6 *im = (struct ifmcaddr6 *)v; struct igmp6_mc_iter_state *state = igmp6_mc_seq_private(seq); unsigned int mca_flags = READ_ONCE(im->mca_flags); - unsigned long expires = READ_ONCE(im->mca_work.timer.expires); + long delta = READ_ONCE(im->mca_work.timer.expires) - jiffies; seq_printf(seq, "%-4d %-15s %pi6 %5d %08X %ld\n", @@ -3009,7 +3037,7 @@ static int igmp6_mc_seq_show(struct seq_file *seq, void *v) &im->mca_addr, READ_ONCE(im->mca_users), mca_flags, (mca_flags & MAF_TIMER_RUNNING) ? - jiffies_to_clock_t(expires - jiffies) : 0); + jiffies_delta_to_clock_t(delta) : 0); return 0; } diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 6a40c5074543..9658939511e0 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -3255,7 +3255,7 @@ void ip6_redirect_no_header(struct sk_buff *skb, struct net *net, int oif) void ip6_sk_redirect(struct sk_buff *skb, struct sock *sk) { - ip6_redirect(skb, sock_net(sk), sk->sk_bound_dev_if, + ip6_redirect(skb, sock_net(sk), skb->dev->ifindex, READ_ONCE(sk->sk_mark), sk_uid(sk)); } diff --git a/net/ipv6/tcpv6_offload.c b/net/ipv6/tcpv6_offload.c index f2a659cd6183..eec3778855eb 100644 --- a/net/ipv6/tcpv6_offload.c +++ b/net/ipv6/tcpv6_offload.c @@ -26,7 +26,18 @@ static void tcp6_check_fraglist_gro(struct list_head *head, struct sk_buff *skb, p = tcp_gro_lookup(head, th); if (p) { - NAPI_GRO_CB(skb)->is_flist = NAPI_GRO_CB(p)->is_flist; + /* flist GRO applies to consecutive non-GSO skbs */ + if (!skb_is_gso(skb) || !NAPI_GRO_CB(p)->is_flist) { + NAPI_GRO_CB(skb)->is_flist = NAPI_GRO_CB(p)->is_flist; + return; + } + + /* Fall back to the regular GRO path */ + if (NAPI_GRO_CB(p)->count == 1) + NAPI_GRO_CB(p)->is_flist = 0; + + NAPI_GRO_CB(skb)->is_flist = 0; + return; } @@ -36,7 +47,7 @@ static void tcp6_check_fraglist_gro(struct list_head *head, struct sk_buff *skb, sk = __inet6_lookup_established(net, &hdr->saddr, th->source, &hdr->daddr, ntohs(th->dest), iif, sdif); - NAPI_GRO_CB(skb)->is_flist = !sk; + NAPI_GRO_CB(skb)->is_flist = !sk && !skb_is_gso(skb); if (sk) sock_gen_put(sk); #endif /* IS_ENABLED(CONFIG_IPV6) */ diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index fd875908ac0c..93478d1ad576 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -690,6 +690,17 @@ out: return sk; } +static void udpv6_err_update_exception(struct net *net, struct sk_buff *skb, + u8 type, __be32 info) +{ + if (type == ICMPV6_PKT_TOOBIG) + ip6_update_pmtu(skb, net, info, skb->dev->ifindex, 0, + sock_net_uid(net, NULL)); + else if (type == NDISC_REDIRECT) + ip6_redirect(skb, net, skb->dev->ifindex, 0, + sock_net_uid(net, NULL)); +} + static int udpv6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, u8 type, u8 code, int offset, __be32 info) { @@ -703,6 +714,8 @@ static int udpv6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, int harderr; int err; + udpv6_err_update_exception(net, skb, type, info); + daddr = seg6_get_daddr(skb, opt) ? : &hdr->daddr; saddr = &hdr->saddr; sk = __udp6_lib_lookup(net, daddr, uh->dest, saddr, uh->source, diff --git a/net/iucv/af_iucv.c b/net/iucv/af_iucv.c index 4e5cc9da6e06..db261ecd19af 100644 --- a/net/iucv/af_iucv.c +++ b/net/iucv/af_iucv.c @@ -210,12 +210,6 @@ static int afiucv_hs_send(struct iucv_message *imsg, struct sock *sock, phs_hdr->flags = flags; if (flags == AF_IUCV_FLAG_SYN) phs_hdr->window = iucv->msglimit; - else if ((flags == AF_IUCV_FLAG_WIN) || !flags) { - confirm_recv = atomic_read(&iucv->msg_recv); - phs_hdr->window = confirm_recv; - if (confirm_recv) - phs_hdr->flags = phs_hdr->flags | AF_IUCV_FLAG_WIN; - } memcpy(phs_hdr->destUserID, iucv->dst_user_id, 8); memcpy(phs_hdr->destAppName, iucv->dst_name, 8); memcpy(phs_hdr->srcUserID, iucv->src_user_id, 8); @@ -250,13 +244,22 @@ static int afiucv_hs_send(struct iucv_message *imsg, struct sock *sock, } skb->protocol = cpu_to_be16(ETH_P_AF_IUCV); + /* Claim the receive credit here, not while building the header: every + * way this frame can be dropped has now been ruled out, so the window + * is zeroed only for as long as the transmit itself takes. + */ + if (flags == AF_IUCV_FLAG_WIN || !flags) { + confirm_recv = atomic_xchg(&iucv->msg_recv, 0); + phs_hdr->window = confirm_recv; + if (confirm_recv) + phs_hdr->flags = phs_hdr->flags | AF_IUCV_FLAG_WIN; + } + atomic_inc(&iucv->skbs_in_xmit); err = dev_queue_xmit(skb); if (net_xmit_eval(err)) { atomic_dec(&iucv->skbs_in_xmit); - } else { - atomic_sub(confirm_recv, &iucv->msg_recv); - WARN_ON(atomic_read(&iucv->msg_recv) < 0); + atomic_add(confirm_recv, &iucv->msg_recv); } return net_xmit_eval(err); @@ -1241,6 +1244,7 @@ static int iucv_sock_recvmsg(struct socket *sock, struct msghdr *msg, struct iucv_sock *iucv = iucv_sk(sk); unsigned int copied, rlen; struct sk_buff *skb, *rskb, *cskb; + bool send_win = false; int err = 0; u32 offset; @@ -1331,16 +1335,20 @@ static int iucv_sock_recvmsg(struct socket *sock, struct msghdr *msg, if (skb_queue_empty(&iucv->backlog_skb_q)) { if (!list_empty(&iucv->message_q.list)) iucv_process_message_q(sk); - if (atomic_read(&iucv->msg_recv) >= - iucv->msglimit / 2) { - err = iucv_send_ctrl(sk, AF_IUCV_FLAG_WIN); - if (err) { - sk->sk_state = IUCV_DISCONN; - sk->sk_state_change(sk); - } - } + if (iucv->transport == AF_IUCV_TRANS_HIPER && + atomic_read(&iucv->msg_recv) >= + iucv->msglimit / 2) + send_win = true; } spin_unlock_bh(&iucv->message_q.lock); + + if (send_win) { + err = iucv_send_ctrl(sk, AF_IUCV_FLAG_WIN); + if (err) { + sk->sk_state = IUCV_DISCONN; + sk->sk_state_change(sk); + } + } } done: diff --git a/net/mac80211/nan.c b/net/mac80211/nan.c index 19e08661be43..c7769da9617b 100644 --- a/net/mac80211/nan.c +++ b/net/mac80211/nan.c @@ -659,8 +659,7 @@ int ieee80211_nan_set_peer_sched(struct ieee80211_sub_if_data *sdata, if (!sta) return -ENOENT; - new_sched = kzalloc(struct_size(new_sched, channels, sched->n_channels), - GFP_KERNEL); + new_sched = kzalloc_flex(*new_sched, channels, sched->n_channels); if (!new_sched) return -ENOMEM; diff --git a/net/mac802154/ieee802154_i.h b/net/mac802154/ieee802154_i.h index 8f2bff268392..c53aa293a222 100644 --- a/net/mac802154/ieee802154_i.h +++ b/net/mac802154/ieee802154_i.h @@ -76,7 +76,12 @@ struct ieee802154_local { struct work_struct rx_mac_cmd_work; /* Association */ - struct ieee802154_pan_device *assoc_dev; + /* assoc_lock protects assoc_dev_extended_addr, assoc_addr, + * assoc_status, the assoc_done reinit/complete pairing and the + * IEEE802154_IS_ASSOCIATING bit in @ongoing. + */ + spinlock_t assoc_lock; + __le64 assoc_dev_extended_addr; struct completion assoc_done; __le16 assoc_addr; u8 assoc_status; diff --git a/net/mac802154/main.c b/net/mac802154/main.c index ea1efef3572a..63e89bd586e3 100644 --- a/net/mac802154/main.c +++ b/net/mac802154/main.c @@ -104,6 +104,7 @@ ieee802154_alloc_hw(size_t priv_data_len, const struct ieee802154_ops *ops) INIT_WORK(&local->rx_mac_cmd_work, mac802154_rx_mac_cmd_worker); init_completion(&local->assoc_done); + spin_lock_init(&local->assoc_lock); /* init supported flags with 802.15.4 default ranges */ phy->supported.max_minbe = 8; diff --git a/net/mac802154/scan.c b/net/mac802154/scan.c index 005338f89b75..dd156c01ac49 100644 --- a/net/mac802154/scan.c +++ b/net/mac802154/scan.c @@ -536,7 +536,9 @@ int mac802154_perform_association(struct ieee802154_sub_if_data *sdata, struct ieee802154_association_req_frame frame = {}; struct ieee802154_local *local = sdata->local; struct wpan_dev *wpan_dev = &sdata->wpan_dev; + __le16 resp_short_addr; struct sk_buff *skb; + u8 resp_status; int ret; frame.mhr.fc.type = IEEE802154_FC_TYPE_MAC_CMD; @@ -578,9 +580,11 @@ int mac802154_perform_association(struct ieee802154_sub_if_data *sdata, return ret; } - local->assoc_dev = coord; + spin_lock(&local->assoc_lock); reinit_completion(&local->assoc_done); + local->assoc_dev_extended_addr = coord->extended_addr; set_bit(IEEE802154_IS_ASSOCIATING, &local->ongoing); + spin_unlock(&local->assoc_lock); ret = ieee802154_mlme_tx_one_locked(local, sdata, skb); if (ret) { @@ -599,25 +603,37 @@ int mac802154_perform_association(struct ieee802154_sub_if_data *sdata, goto clear_assoc; } - if (local->assoc_status != IEEE802154_ASSOCIATION_SUCCESSFUL) { - if (local->assoc_status == IEEE802154_PAN_AT_CAPACITY) + /* The association is complete: mac802154_process_association_resp() + * cleared the associating bit before waking us, so a second (e.g. + * malicious) ASSOC RESP can no longer pass the recheck and overwrite + * the result. Snapshot assoc_status/assoc_addr under the lock. + */ + spin_lock(&local->assoc_lock); + resp_status = local->assoc_status; + resp_short_addr = local->assoc_addr; + spin_unlock(&local->assoc_lock); + + if (resp_status != IEEE802154_ASSOCIATION_SUCCESSFUL) { + if (resp_status == IEEE802154_PAN_AT_CAPACITY) ret = -ERANGE; else ret = -EPERM; dev_warn(&sdata->dev->dev, "Negative ASSOC RESP received from %8phC: %s\n", &ceaddr, - local->assoc_status == IEEE802154_PAN_AT_CAPACITY ? + resp_status == IEEE802154_PAN_AT_CAPACITY ? "PAN at capacity" : "access denied"); - goto clear_assoc; + return ret; } - ret = 0; - *short_addr = local->assoc_addr; + *short_addr = resp_short_addr; + + return 0; clear_assoc: + spin_lock(&local->assoc_lock); clear_bit(IEEE802154_IS_ASSOCIATING, &local->ongoing); - local->assoc_dev = NULL; + spin_unlock(&local->assoc_lock); return ret; } @@ -639,19 +655,28 @@ int mac802154_process_association_resp(struct ieee802154_sub_if_data *sdata, dest->mode != IEEE802154_EXTENDED_ADDRESSING)) return -EINVAL; - if (unlikely(dest->extended_addr != wpan_dev->extended_addr || - src->extended_addr != local->assoc_dev->extended_addr)) + spin_lock(&local->assoc_lock); + if (unlikely(!test_bit(IEEE802154_IS_ASSOCIATING, &local->ongoing) || + dest->extended_addr != wpan_dev->extended_addr || + src->extended_addr != local->assoc_dev_extended_addr)) { + spin_unlock(&local->assoc_lock); return -ENODEV; + } memcpy(&resp_pl, skb->data, sizeof(resp_pl)); local->assoc_addr = resp_pl.short_addr; local->assoc_status = resp_pl.status; + /* Clear the associating bit before waking the waiter: once the result + * is saved, any subsequent (e.g. malicious) ASSOC RESP must fail the + * test_bit() recheck above and can no longer overwrite the result. + */ + clear_bit(IEEE802154_IS_ASSOCIATING, &local->ongoing); + complete(&local->assoc_done); + spin_unlock(&local->assoc_lock); dev_dbg(&skb->dev->dev, "ASSOC RESP 0x%x received from %8phC, getting short address %04x\n", - local->assoc_status, &deaddr, local->assoc_addr); - - complete(&local->assoc_done); + resp_pl.status, &deaddr, resp_pl.short_addr); return 0; } diff --git a/net/mctp/test/route-test.c b/net/mctp/test/route-test.c index c92e3abb40d7..f05f75bf93e0 100644 --- a/net/mctp/test/route-test.c +++ b/net/mctp/test/route-test.c @@ -193,7 +193,7 @@ static void __mctp_route_test_init(struct kunit *test, if (netid != MCTP_NET_ANY) WRITE_ONCE(dev->mdev->net, netid); - dev->mdev->addrs = kmalloc_objs(u8, 1, GFP_KERNEL); + dev->mdev->addrs = kmalloc_objs(u8, 1); dev->mdev->num_addrs = 1; dev->mdev->addrs[0] = 8; diff --git a/net/mctp/test/utils.c b/net/mctp/test/utils.c index 6eef8d485c25..6b131084a249 100644 --- a/net/mctp/test/utils.c +++ b/net/mctp/test/utils.c @@ -88,7 +88,7 @@ struct mctp_test_dev *mctp_test_create_dev_with_addr(mctp_eid_t addr) if (!dev) return NULL; - dev->mdev->addrs = kmalloc_objs(u8, 1, GFP_KERNEL); + dev->mdev->addrs = kmalloc_objs(u8, 1); if (!dev->mdev->addrs) { mctp_test_destroy_dev(dev); return NULL; diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index b474d03620a7..e1f08f71cdb1 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -3109,8 +3109,7 @@ static void mptcp_do_fastclose(struct sock *sk) */ inet_csk(ssk)->icsk_ack.rcv_mss = TCP_MIN_MSS; - tcp_send_active_reset(ssk, ssk->sk_allocation, - SK_RST_REASON_TCP_ABORT_ON_CLOSE); + tcp_send_active_reset(ssk, SK_RST_REASON_TCP_ABORT_ON_CLOSE); unlock: release_sock(ssk); } diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h index 06a107d4e839..87ccb84e9927 100644 --- a/net/mptcp/protocol.h +++ b/net/mptcp/protocol.h @@ -690,7 +690,7 @@ mptcp_send_active_reset_reason(struct sock *sk) enum sk_rst_reason reason; reason = sk_rst_convert_mptcp_reason(subflow->reset_reason); - tcp_send_active_reset(sk, GFP_ATOMIC, reason); + tcp_send_active_reset(sk, reason); } /* Made the fwd mem carried by the given skb available to the msk, diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 765a92fa90d6..31fbd5a28937 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -3215,7 +3215,7 @@ static int nft_trans_delhook(struct nft_hook *hook, { struct nft_trans_hook *trans_hook; - trans_hook = kmalloc_obj(*trans_hook, GFP_KERNEL); + trans_hook = kmalloc_obj(*trans_hook); if (!trans_hook) return -ENOMEM; diff --git a/net/netfilter/nfnetlink_cttimeout.c b/net/netfilter/nfnetlink_cttimeout.c index 66c2016f6049..f43bf768b31c 100644 --- a/net/netfilter/nfnetlink_cttimeout.c +++ b/net/netfilter/nfnetlink_cttimeout.c @@ -150,7 +150,7 @@ static int cttimeout_new_timeout(struct sk_buff *skb, goto err_proto_put; } - timeout = kzalloc(sizeof(*timeout), GFP_KERNEL); + timeout = kzalloc_obj(*timeout); if (timeout == NULL) { ret = -ENOMEM; goto err_proto_put; diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index b22cda322136..76bde7906d49 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -2675,7 +2675,8 @@ static int tpacket_parse_header(struct packet_sock *po, void *frame, int size_max, void **data) { union tpacket_uhdr ph; - int tp_len, off; + u32 tp_len; + int off; ph.raw = frame; @@ -2695,7 +2696,7 @@ static int tpacket_parse_header(struct packet_sock *po, void *frame, break; } if (unlikely(tp_len > size_max)) { - pr_err("packet size is too long (%d > %d)\n", tp_len, size_max); + pr_err("packet size is too long (%u > %d)\n", tp_len, size_max); return -EMSGSIZE; } diff --git a/net/qrtr/af_qrtr.c b/net/qrtr/af_qrtr.c index a30fa56e6aa3..78347c937af7 100644 --- a/net/qrtr/af_qrtr.c +++ b/net/qrtr/af_qrtr.c @@ -9,6 +9,7 @@ #include <linux/termios.h> /* For TIOCINQ/OUTQ */ #include <linux/spinlock.h> #include <linux/wait.h> +#include <linux/workqueue.h> #include <net/sock.h> @@ -120,8 +121,10 @@ static DEFINE_XARRAY_ALLOC(qrtr_ports); * @nid: node id * @qrtr_tx_flow: xarray of qrtr_tx_flow, keyed by node << 32 | port * @qrtr_tx_lock: lock for qrtr_tx_flow inserts + * @hello_sent: hello packet send successful * @rx_queue: receive queue * @item: list item for broadcast list + * @say_hello: delayed work for sending hello packet */ struct qrtr_node { struct mutex ep_lock; @@ -132,8 +135,11 @@ struct qrtr_node { struct xarray qrtr_tx_flow; struct mutex qrtr_tx_lock; /* for qrtr_tx_flow */ + bool hello_sent; + struct sk_buff_head rx_queue; struct list_head item; + struct delayed_work say_hello; }; /** @@ -187,6 +193,8 @@ static void __qrtr_node_release(struct kref *kref) list_del(&node->item); mutex_unlock(&qrtr_node_lock); + cancel_delayed_work_sync(&node->say_hello); + skb_queue_purge(&node->rx_queue); /* Free tx flow counters */ @@ -341,6 +349,14 @@ static int qrtr_node_enqueue(struct qrtr_node *node, struct sk_buff *skb, size_t len = skb->len; int rc, confirm_rx; + mutex_lock(&node->ep_lock); + if (!node->hello_sent && type != QRTR_TYPE_HELLO) { + mutex_unlock(&node->ep_lock); + kfree_skb(skb); + return -EAGAIN; + } + mutex_unlock(&node->ep_lock); + confirm_rx = qrtr_tx_wait(node, to->sq_node, to->sq_port, type); if (confirm_rx < 0) { kfree_skb(skb); @@ -353,7 +369,7 @@ static int qrtr_node_enqueue(struct qrtr_node *node, struct sk_buff *skb, hdr->src_node_id = cpu_to_le32(from->sq_node); hdr->src_port_id = cpu_to_le32(from->sq_port); if (to->sq_port == QRTR_PORT_CTRL) { - hdr->dst_node_id = cpu_to_le32(node->nid); + hdr->dst_node_id = cpu_to_le32(READ_ONCE(node->nid)); hdr->dst_port_id = cpu_to_le32(QRTR_PORT_CTRL); } else { hdr->dst_node_id = cpu_to_le32(to->sq_node); @@ -372,6 +388,8 @@ static int qrtr_node_enqueue(struct qrtr_node *node, struct sk_buff *skb, rc = node->ep->xmit(node->ep, skb); else kfree_skb(skb); + if (!rc && type == QRTR_TYPE_HELLO) + node->hello_sent = true; mutex_unlock(&node->ep_lock); } /* Need to ensure that a subsequent message carries the otherwise lost @@ -379,6 +397,9 @@ static int qrtr_node_enqueue(struct qrtr_node *node, struct sk_buff *skb, if (rc && confirm_rx) qrtr_tx_flow_failed(node, to->sq_node, to->sq_port); + if (rc == -EAGAIN && type == QRTR_TYPE_HELLO) + schedule_delayed_work(&node->say_hello, msecs_to_jiffies(100)); + return rc; } @@ -416,7 +437,7 @@ static void qrtr_node_assign(struct qrtr_node *node, unsigned int nid) spin_lock_irqsave(&qrtr_nodes_lock, flags); radix_tree_insert(&qrtr_nodes, nid, node); if (node->nid == QRTR_EP_NID_AUTO) - node->nid = nid; + WRITE_ONCE(node->nid, nid); spin_unlock_irqrestore(&qrtr_nodes_lock, flags); } @@ -570,6 +591,38 @@ static struct sk_buff *qrtr_alloc_ctrl_packet(struct qrtr_ctrl_pkt **pkt, return skb; } +static void qrtr_hello_work(struct work_struct *work) +{ + struct sockaddr_qrtr from = {AF_QIPCRTR, 0, QRTR_PORT_CTRL}; + struct sockaddr_qrtr to = {AF_QIPCRTR, 0, QRTR_PORT_CTRL}; + struct qrtr_ctrl_pkt *pkt; + struct qrtr_node *node; + struct qrtr_sock *ctrl; + struct sk_buff *skb; + + node = container_of(to_delayed_work(work), struct qrtr_node, say_hello); + + /* NS must be bound before we can send; retry with backoff if not ready */ + ctrl = qrtr_port_lookup(QRTR_PORT_CTRL); + if (!ctrl) { + schedule_delayed_work(&node->say_hello, msecs_to_jiffies(100)); + return; + } + + skb = qrtr_alloc_ctrl_packet(&pkt, GFP_KERNEL); + if (!skb) { + qrtr_port_put(ctrl); + schedule_delayed_work(&node->say_hello, msecs_to_jiffies(100)); + return; + } + + pkt->cmd = cpu_to_le32(QRTR_TYPE_HELLO); + from.sq_node = qrtr_local_nid; + to.sq_node = node->nid; + qrtr_node_enqueue(node, skb, QRTR_TYPE_HELLO, &from, &to); + qrtr_port_put(ctrl); +} + /** * qrtr_endpoint_register() - register a new endpoint * @ep: endpoint to register @@ -595,6 +648,9 @@ int qrtr_endpoint_register(struct qrtr_endpoint *ep, unsigned int nid) node->nid = QRTR_EP_NID_AUTO; node->ep = ep; + node->hello_sent = false; + INIT_DELAYED_WORK(&node->say_hello, qrtr_hello_work); + xa_init(&node->qrtr_tx_flow); mutex_init(&node->qrtr_tx_lock); @@ -605,6 +661,9 @@ int qrtr_endpoint_register(struct qrtr_endpoint *ep, unsigned int nid) mutex_unlock(&qrtr_node_lock); ep->node = node; + /* Initiate HELLO handshake from the core layer */ + schedule_delayed_work(&node->say_hello, 0); + return 0; } EXPORT_SYMBOL_GPL(qrtr_endpoint_register); @@ -879,6 +938,9 @@ static int qrtr_bcast_enqueue(struct qrtr_node *node, struct sk_buff *skb, mutex_lock(&qrtr_node_lock); list_for_each_entry(node, &qrtr_all_nodes, item) { + /* Skip nodes with no assigned node ID yet. */ + if (READ_ONCE(node->nid) == QRTR_EP_NID_AUTO) + continue; skbn = pskb_copy(skb, GFP_KERNEL); if (!skbn) break; diff --git a/net/qrtr/ns.c b/net/qrtr/ns.c index c5e7e01db249..bcb090ee79d4 100644 --- a/net/qrtr/ns.c +++ b/net/qrtr/ns.c @@ -212,6 +212,7 @@ static void lookup_notify(struct sockaddr_qrtr *to, struct qrtr_server *srv, pr_err("failed to send lookup notification\n"); } +/* Announce the list of servers registered on the local node */ static int announce_servers(struct sockaddr_qrtr *sq) { struct qrtr_server *srv; @@ -326,38 +327,8 @@ static int server_del(struct qrtr_node *node, unsigned int port, bool bcast) return 0; } -static int say_hello(struct sockaddr_qrtr *dest) -{ - struct qrtr_ctrl_pkt pkt; - struct msghdr msg = { }; - struct kvec iv; - int ret; - - iv.iov_base = &pkt; - iv.iov_len = sizeof(pkt); - - memset(&pkt, 0, sizeof(pkt)); - pkt.cmd = cpu_to_le32(QRTR_TYPE_HELLO); - - msg.msg_name = (struct sockaddr *)dest; - msg.msg_namelen = sizeof(*dest); - - ret = kernel_sendmsg(qrtr_ns.sock, &msg, &iv, 1, sizeof(pkt)); - if (ret < 0) - pr_err("failed to send hello msg\n"); - - return ret; -} - -/* Announce the list of servers registered on the local node */ static int ctrl_cmd_hello(struct sockaddr_qrtr *sq) { - int ret; - - ret = say_hello(sq); - if (ret < 0) - return ret; - return announce_servers(sq); } @@ -774,10 +745,6 @@ int qrtr_ns_init(void) qrtr_ns.bcast_sq.sq_node = QRTR_NODE_BCAST; qrtr_ns.bcast_sq.sq_port = QRTR_PORT_CTRL; - ret = say_hello(&qrtr_ns.bcast_sq); - if (ret < 0) - goto err_wq; - /* As the qrtr ns socket owner and creator is the same module, we have * to decrease the qrtr module reference count to guarantee that it * remains zero after the ns socket is created, otherwise, executing diff --git a/net/rds/connection.c b/net/rds/connection.c index 7c8ab8e973e1..b6c4beb50eaf 100644 --- a/net/rds/connection.c +++ b/net/rds/connection.c @@ -106,10 +106,12 @@ static struct rds_connection *rds_conn_lookup(struct net *net, } /* - * This is called by transports as they're bringing down a connection. - * It clears partial message state so that the transport can start sending - * and receiving over this connection again in the future. It is up to - * the transport to have serialized this call with its send and recv. + * This is called by rds_conn_shutdown() once the transport has brought + * a path down. It clears partial message state so that the transport + * can start sending and receiving over this path again in the future. + * The caller owns RDS_IN_XMIT and RDS_RECV_REFILL across this call, + * which is what serializes it against the send and receive-refill + * paths. */ static void rds_conn_path_reset(struct rds_conn_path *cp) { @@ -120,7 +122,16 @@ static void rds_conn_path_reset(struct rds_conn_path *cp) rds_stats_inc(s_conn_reset); rds_send_path_reset(cp); - cp->cp_flags = 0; + + /* Clear the bits the reset is responsible for individually: a + * blanket cp_flags = 0 is a plain store that can clobber a + * concurrent atomic read-modify-write on the same word. + * RDS_IN_XMIT and RDS_RECV_REFILL are held as locks by the + * caller, rds_conn_shutdown(), which releases them once the + * teardown is complete. + */ + clear_bit(RDS_LL_SEND_FULL, &cp->cp_flags); + clear_bit(RDS_RECONNECT_PENDING, &cp->cp_flags); /* Do not clear next_rx_seq here, else we cannot distinguish * retransmitted packets from new packets, and will hand all @@ -406,28 +417,70 @@ void rds_conn_shutdown(struct rds_conn_path *cp) } mutex_unlock(&cp->cp_cm_lock); + /* Quiesce the transmit and receive-refill paths by + * acquiring their bit locks, not merely waiting for + * them to be released: with a plain wait, either path + * can re-take its lock the instant after we sample it + * clear and then run concurrently with the transport + * shutdown and the path reset below. Holding both + * locks across the teardown makes that structurally + * impossible. + */ wait_event(cp->cp_waitq, - !test_bit(RDS_IN_XMIT, &cp->cp_flags)); + !test_and_set_bit_lock(RDS_IN_XMIT, &cp->cp_flags)); wait_event(cp->cp_waitq, - !test_bit(RDS_RECV_REFILL, &cp->cp_flags)); + !test_and_set_bit(RDS_RECV_REFILL, &cp->cp_flags)); conn->c_trans->conn_path_shutdown(cp); rds_conn_path_reset(cp); + /* Release the two locks and wake any waiter (e.g. + * rds_tcp_reset_callbacks()) that blocked on them while + * we held them. The unlock orders the transport's ring + * re-initialization and the path reset above before + * either bit is seen clear. rds_conn_path_reset() leaves + * both bits alone: ownership ends here, not inside the + * reset. + */ + clear_bit_unlock(RDS_IN_XMIT, &cp->cp_flags); + clear_bit_unlock(RDS_RECV_REFILL, &cp->cp_flags); + wake_up_all(&cp->cp_waitq); + if (!rds_conn_path_transition(cp, RDS_CONN_DISCONNECTING, - RDS_CONN_DOWN) && - !rds_conn_path_transition(cp, RDS_CONN_ERROR, RDS_CONN_DOWN)) { - /* This can happen - eg when we're in the middle of tearing - * down the connection, and someone unloads the rds module. - * Quite reproducible with loopback connections. - * Mostly harmless. + /* The path was dropped again while we tore it + * down: by a socket state-change callback in + * irq context on receipt of a FIN, or by an + * accept that claimed the path just before a + * drop put it back to RDS_CONN_ERROR and then + * installed a fresh socket on it. Unless a + * pending destroy suppressed it, the drop also + * queued another shutdown pass, and that pass + * must run, because it is what tears down + * whatever attached to the path after the + * transport shutdown above sampled its state. + * Consuming the RDS_CONN_ERROR here would turn + * that pass into a no-op: leave the state + * alone, and let the pass finish the job. * - * Note that this also happens with rds-tcp because - * we could have triggered rds_conn_path_drop in irq - * mode from rds_tcp_state change on the receipt of - * a FIN, thus we need to recheck for RDS_CONN_ERROR - * here. + * Quiesce the reconnect timer before bailing + * out, though. When a pending destroy did + * suppress the queue, no later pass runs, and + * rds_conn_path_destroy() is about to flush + * cp_down_w and free the path: it must not + * find cp_conn_w still armed. A successor + * pass, when there is one, re-arms the + * reconnect from its own tail. + */ + cancel_delayed_work_sync(&cp->cp_conn_w); + clear_bit(RDS_RECONNECT_PENDING, &cp->cp_flags); + + if (rds_conn_path_state(cp) == RDS_CONN_ERROR) + return; + /* No current cp_state writer leaves a + * DISCONNECTING path in any state but + * RDS_CONN_ERROR; report loudly if one ever + * does. */ rds_conn_path_error(cp, "%s: failed to transition " "to state DOWN, current state " diff --git a/net/rds/ib_recv.c b/net/rds/ib_recv.c index 357128d34a54..bd6cb3ffaa57 100644 --- a/net/rds/ib_recv.c +++ b/net/rds/ib_recv.c @@ -363,15 +363,14 @@ static int acquire_refill(struct rds_connection *conn) static void release_refill(struct rds_connection *conn) { - clear_bit(RDS_RECV_REFILL, &conn->c_flags); - smp_mb__after_atomic(); + clear_bit_unlock(RDS_RECV_REFILL, &conn->c_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 * the system-wide hashed waitqueue buckets in the fast path only to * almost never find waiters. */ - if (waitqueue_active(&conn->c_waitq)) + if (wq_has_sleeper(&conn->c_waitq)) wake_up_all(&conn->c_waitq); } @@ -392,7 +391,9 @@ void rds_ib_recv_refill(struct rds_connection *conn, int prefill, gfp_t gfp) /* the goal here is to just make sure that someone, somewhere * is posting buffers. If we can't get the refill lock, - * let them do their thing + * let them do their thing. The holder may also be + * rds_conn_shutdown() tearing the path down, in which case + * there is nothing to post. */ if (!acquire_refill(conn)) return; diff --git a/net/rds/info.c b/net/rds/info.c index 31e7ad108459..a57f81a05c87 100644 --- a/net/rds/info.c +++ b/net/rds/info.c @@ -205,7 +205,7 @@ int rds_info_getsockopt(struct socket *sock, int optname, sockopt_t *opt) * iterator code to allocate and hand it back. */ npages = iov_iter_npages(&opt->iter_out, INT_MAX); - pages = kvmalloc_array(npages, sizeof(*pages), GFP_KERNEL); + pages = kvmalloc_objs(*pages, npages); if (!pages) { ret = -ENOMEM; goto out; diff --git a/net/rds/send.c b/net/rds/send.c index 15a1b97f13e7..1afa981e5c06 100644 --- a/net/rds/send.c +++ b/net/rds/send.c @@ -114,8 +114,13 @@ static void release_in_xmit(struct rds_conn_path *cp) * hot path and finding waiters is very rare. We don't want to walk * the system-wide hashed waitqueue buckets in the fast path only to * almost never find waiters. + * + * wq_has_sleeper() supplies the full barrier that orders the wait + * queue read after the bit clear; clear_bit_unlock() alone is only + * a release and would let this check read a stale empty queue, + * losing the wake-up. */ - if (waitqueue_active(&cp->cp_waitq)) + if (wq_has_sleeper(&cp->cp_waitq)) wake_up_all(&cp->cp_waitq); } @@ -239,8 +244,11 @@ restart: WRITE_ONCE(cp->cp_send_gen, send_gen); /* - * rds_conn_shutdown() sets the conn state and then tests RDS_IN_XMIT, - * we do the opposite to avoid races. + * rds_conn_shutdown() sets the conn state and then acquires + * RDS_IN_XMIT; we take the lock first and then check the state. + * Ownership is decided by the atomic RMW on the cp_flags word: + * if the teardown won the bit we back off here, and if we won + * it the teardown waits until we release it. */ if (!rds_conn_path_up(cp)) { release_in_xmit(cp); diff --git a/net/rds/tcp.c b/net/rds/tcp.c index b263634ac750..774a71f88d37 100644 --- a/net/rds/tcp.c +++ b/net/rds/tcp.c @@ -115,46 +115,90 @@ void rds_tcp_restore_callbacks(struct socket *sock, } /* - * rds_tcp_reset_callbacks() switches the to the new sock and - * returns the existing tc->t_sock. + * rds_tcp_reset_callbacks() switches a path to a new socket and + * releases the old one it finds in tc->t_sock, resolving a duelling + * SYN. * - * The only functions that set tc->t_sock are rds_tcp_set_callbacks - * and rds_tcp_reset_callbacks. Send and receive trust that - * it is set. The absence of RDS_CONN_UP bit protects those paths - * from being called while it isn't set. + * tc->t_sock is set by rds_tcp_set_callbacks() and cleared by + * rds_tcp_restore_callbacks(). Four paths write it: the active + * connect in rds_tcp_conn_path_connect(), which sets it and clears it + * again on failure; the accept path in rds_tcp_accept_one(), which + * sets it for a path with no socket yet; the teardown in + * rds_tcp_conn_path_shutdown(), which clears it; and the swap done + * here, which does both. The connect and accept paths are serialized + * against each other by t_conn_path_lock. Send and receive trust + * that it is set: the absence of RDS_CONN_UP protects those paths + * from being called while it isn't, and the swap done here runs under + * RDS_IN_XMIT so that it cannot interleave with a sender already + * inside rds_send_xmit(). */ void rds_tcp_reset_callbacks(struct socket *sock, struct rds_conn_path *cp) { struct rds_tcp_connection *tc = cp->cp_transport_data; - struct socket *osock = tc->t_sock; - - if (!osock) - goto newsock; + struct socket *osock; /* Need to resolve a duelling SYN between peers. * We have an outstanding SYN to this peer, which may * potentially have transitioned to the RDS_CONN_UP state, * so we must quiesce any send threads before resetting - * cp_transport_data. We quiesce these threads by setting - * cp_state to something other than RDS_CONN_UP, and then - * waiting for any existing threads in rds_send_xmit to - * complete release_in_xmit(). (Subsequent threads entering - * rds_send_xmit() will bail on !rds_conn_up(). + * cp_transport_data. Setting cp_state to something other + * than RDS_CONN_UP stops new senders, and owning RDS_IN_XMIT + * excludes any thread already inside rds_send_xmit() - or a + * teardown in rds_conn_shutdown(), which holds the same lock + * for the duration of the transport shutdown - for the whole + * socket swap and the rds_send_path_reset() below. * - * However an incoming syn-ack at this point would end up - * marking the conn as RDS_CONN_UP, and would again permit - * rds_send_xmi() threads through, so ideally we would - * synchronize on RDS_CONN_UP after lock_sock(), but cannot - * do that: waiting on !RDS_IN_XMIT after lock_sock() may - * end up deadlocking with tcp_sendmsg(), and the RDS_IN_XMIT - * would not get set. As a result, we set c_state to - * RDS_CONN_RESETTTING, to ensure that rds_tcp_state_change - * cannot mark rds_conn_path_up() in the window before lock_sock() + * An incoming syn-ack at this point would end up marking the + * conn as RDS_CONN_UP, and would again permit rds_send_xmit() + * threads through, so ideally we would synchronize on + * RDS_CONN_UP after lock_sock(), but cannot do that: acquiring + * RDS_IN_XMIT after lock_sock() may end up deadlocking with + * tcp_sendmsg(), which takes the socket lock while holding + * RDS_IN_XMIT. As a result, we set c_state to + * RDS_CONN_RESETTING, to ensure that rds_tcp_state_change + * cannot mark rds_conn_path_up() in the window before + * lock_sock(). + * + * Only make that transition if the path is still connecting + * (or already resetting from an earlier duel). A path in any + * other state - typically RDS_CONN_DISCONNECTING or + * RDS_CONN_ERROR with a shutdown in flight - is dropped + * instead. That still replaces its state, with RDS_CONN_ERROR, + * and, unless a pending destroy is about to reap the whole + * connection anyway, queues one more shutdown pass. A shutdown + * already in flight leaves that RDS_CONN_ERROR alone when it + * finishes; the queued pass then completes the transition to + * RDS_CONN_DOWN and tears down anything that attached to the + * path in the meantime. + */ + if (!rds_conn_path_transition(cp, RDS_CONN_CONNECTING, + RDS_CONN_RESETTING) && + !rds_conn_path_transition(cp, RDS_CONN_RESETTING, + RDS_CONN_RESETTING)) + rds_conn_path_drop(cp, 0); + wait_event(cp->cp_waitq, + !test_and_set_bit_lock(RDS_IN_XMIT, &cp->cp_flags)); + + /* Read t_sock only while owning RDS_IN_XMIT, never before the + * wait: the teardown in rds_conn_shutdown() releases the old + * socket and clears t_sock, so a pointer sampled earlier can + * be stale by the time we wake up. The teardown holds the + * same lock while it does so, so what we read here cannot + * change under us until we release it. + */ + osock = tc->t_sock; + if (!osock) + goto newsock; + + /* reset receive side state for rds_tcp_data_recv() for osock. + * + * The sync cancels while owning RDS_IN_XMIT rely on cp_wq + * being ordered: a teardown blocked on the bit occupies + * cp_wq's only execution slot, so cp_send_w and cp_recv_w are + * pending at most and the cancels never flush. Nothing here + * may flush or wait on cp_wq itself. */ - atomic_set(&cp->cp_state, RDS_CONN_RESETTING); - wait_event(cp->cp_waitq, !test_bit(RDS_IN_XMIT, &cp->cp_flags)); - /* reset receive side state for rds_tcp_data_recv() for osock */ cancel_delayed_work_sync(&cp->cp_send_w); cancel_delayed_work_sync(&cp->cp_recv_w); lock_sock(osock->sk); @@ -172,6 +216,9 @@ newsock: lock_sock(sock->sk); rds_tcp_set_callbacks(sock, cp); release_sock(sock->sk); + + clear_bit_unlock(RDS_IN_XMIT, &cp->cp_flags); + wake_up_all(&cp->cp_waitq); } /* Add tc to rds_tcp_tc_list and set tc->t_sock. See comments diff --git a/net/rds/tcp_listen.c b/net/rds/tcp_listen.c index a3db9b057084..13fa60c1985b 100644 --- a/net/rds/tcp_listen.c +++ b/net/rds/tcp_listen.c @@ -295,7 +295,11 @@ int rds_tcp_accept_one(struct rds_tcp_net *rtn) if (rs_tcp->t_sock) { /* Duelling SYN has been handled in rds_tcp_accept_one() */ rds_tcp_reset_callbacks(new_sock, cp); - /* rds_connect_path_complete() marks RDS_CONN_UP */ + /* rds_connect_path_complete() marks RDS_CONN_UP, or, + * if a concurrent shutdown won the duel, drops the + * path again and the pass that drop queues reaps the + * socket installed above. + */ rds_connect_path_complete(cp, RDS_CONN_RESETTING); } else { rds_tcp_set_callbacks(new_sock, cp); diff --git a/net/rxrpc/key.c b/net/rxrpc/key.c index a0aa78d89289..cbd26da44951 100644 --- a/net/rxrpc/key.c +++ b/net/rxrpc/key.c @@ -210,7 +210,7 @@ static int rxrpc_preparse_xdr_yfs_rxgk(struct key_preparsed_payload *prep, if (!token) goto nomem; - token->rxgk = kzalloc(struct_size_t(struct rxgk_key, _key, raw_keylen), GFP_KERNEL); + token->rxgk = kzalloc_flex(struct rxgk_key, _key, raw_keylen); if (!token->rxgk) goto nomem_token; diff --git a/net/sched/act_api.c b/net/sched/act_api.c index b4415d358c91..37eced84dfa5 100644 --- a/net/sched/act_api.c +++ b/net/sched/act_api.c @@ -443,12 +443,21 @@ static size_t tcf_action_shared_attrs_size(const struct tc_action *act) + nla_total_size(IFNAMSIZ) /* TCA_ACT_KIND */ + cookie_len /* TCA_ACT_COOKIE */ + nla_total_size(sizeof(struct nla_bitfield32)) /* TCA_ACT_HW_STATS */ + /* TCA_ACT_USED_HW_STATS */ + + nla_total_size(sizeof(struct nla_bitfield32)) + + nla_total_size(sizeof(u32)) /* TCA_ACT_IN_HW_COUNT */ + nla_total_size(0) /* TCA_ACT_STATS nested */ + nla_total_size(sizeof(struct nla_bitfield32)) /* TCA_ACT_FLAGS */ /* TCA_STATS_BASIC */ + nla_total_size_64bit(sizeof(struct gnet_stats_basic)) - /* TCA_STATS_PKT64 */ - + nla_total_size_64bit(sizeof(u64)) + /* TCA_STATS_BASIC_HW */ + + nla_total_size_64bit(sizeof(struct gnet_stats_basic)) + /* TCA_STATS_PKT64, emitted by both of the basic copies above */ + + 2 * nla_total_size_64bit(sizeof(u64)) + /* TCA_STATS_RATE_EST */ + + nla_total_size_64bit(sizeof(struct gnet_stats_rate_est)) + /* TCA_STATS_RATE_EST64 */ + + nla_total_size_64bit(sizeof(struct gnet_stats_rate_est64)) /* TCA_STATS_QUEUE */ + nla_total_size_64bit(sizeof(struct gnet_stats_queue)) + nla_total_size(0) /* TCA_ACT_OPTIONS nested */ @@ -1688,12 +1697,12 @@ out_nlmsg_trim: static int tcf_get_notify(struct net *net, u32 portid, struct nlmsghdr *n, - struct tc_action *actions[], int event, + struct tc_action *actions[], size_t attr_size, int event, struct netlink_ext_ack *extack) { struct sk_buff *skb; - skb = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL); + skb = alloc_skb(max(attr_size, NLMSG_GOODSIZE), GFP_KERNEL); if (!skb) return -ENOBUFS; if (tca_get_fill(skb, actions, portid, n->nlmsg_seq, 0, event, @@ -1858,11 +1867,13 @@ static int tcf_action_delete(struct net *net, struct tc_action *actions[]) static struct sk_buff *tcf_reoffload_del_notify_msg(struct net *net, struct tc_action *action) { - size_t attr_size = tcf_action_fill_size(action); struct tc_action *actions[TCA_ACT_MAX_PRIO] = { [0] = action, }; struct sk_buff *skb; + size_t attr_size; + + attr_size = tcf_action_full_attrs_size(tcf_action_fill_size(action)); skb = alloc_skb(max(attr_size, NLMSG_GOODSIZE), GFP_KERNEL); if (!skb) @@ -1879,15 +1890,18 @@ static struct sk_buff *tcf_reoffload_del_notify_msg(struct net *net, static int tcf_reoffload_del_notify(struct net *net, struct tc_action *action) { const struct tc_action_ops *ops = action->ops; - struct sk_buff *skb; + struct sk_buff *skb = NULL; int ret; - if (!rtnl_notify_needed(net, 0, RTNLGRP_TC)) { - skb = NULL; - } else { + if (rtnl_notify_needed(net, 0, RTNLGRP_TC)) { skb = tcf_reoffload_del_notify_msg(net, action); + /* The action has already lost its hardware instance and is + * skip_sw, so it must be released whether or not the + * notification can be built. Drop the notification rather + * than leave an action behind that processes no packets. + */ if (IS_ERR(skb)) - return PTR_ERR(skb); + skb = NULL; } ret = tcf_idr_release_unsafe(action); @@ -2044,7 +2058,8 @@ tca_action_gd(struct net *net, struct nlattr *nla, struct nlmsghdr *n, attr_size = tcf_action_full_attrs_size(attr_size); if (event == RTM_GETACTION) - ret = tcf_get_notify(net, portid, n, actions, event, extack); + ret = tcf_get_notify(net, portid, n, actions, attr_size, event, + extack); else { /* delete */ ret = tcf_del_notify(net, n, actions, portid, attr_size, extack); if (ret) diff --git a/net/sched/act_gate.c b/net/sched/act_gate.c index fdbfcaa3e2ab..5d228a402204 100644 --- a/net/sched/act_gate.c +++ b/net/sched/act_gate.c @@ -240,7 +240,7 @@ static int tcf_gate_copy_entries(struct tcf_gate_params *dst, list_for_each_entry(entry, &src->entries, list) { struct tcfg_gate_entry *new; - new = kzalloc(sizeof(*new), GFP_ATOMIC); + new = kzalloc_obj(*new, GFP_ATOMIC); if (!new) { NL_SET_ERR_MSG(extack, "Not enough memory for entry"); return -ENOMEM; @@ -415,7 +415,7 @@ static int tcf_gate_init(struct net *net, struct nlattr *nla, if (err < 0) goto release_idr; - p = kzalloc(sizeof(*p), GFP_KERNEL); + p = kzalloc_obj(*p); if (!p) { err = -ENOMEM; goto chain_put; diff --git a/net/sched/act_tunnel_key.c b/net/sched/act_tunnel_key.c index ff401ace4f3d..503834853306 100644 --- a/net/sched/act_tunnel_key.c +++ b/net/sched/act_tunnel_key.c @@ -526,7 +526,7 @@ static int tunnel_key_init(struct net *net, struct nlattr *nla, } t = to_tunnel_key(*a); - params_new = kzalloc(sizeof(*params_new), GFP_KERNEL); + params_new = kzalloc_obj(*params_new); if (unlikely(!params_new)) { NL_SET_ERR_MSG(extack, "Cannot allocate tunnel key parameters"); ret = -ENOMEM; diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c index 0e275b58151c..1cefea571efd 100644 --- a/net/sched/cls_flower.c +++ b/net/sched/cls_flower.c @@ -1703,6 +1703,11 @@ static int fl_set_enc_opt(struct nlattr **tb, struct fl_flow_key *key, return -EINVAL; } nla_opt_msk = nla_next(nla_opt_msk, &msk_depth); + + if (msk_depth && !nla_ok(nla_opt_msk, msk_depth)) { + NL_SET_ERR_MSG(extack, "A mask attribute is invalid"); + return -EINVAL; + } } return 0; diff --git a/net/sched/cls_u32.c b/net/sched/cls_u32.c index ac6d0fa5a40e..a3e65c8cf29e 100644 --- a/net/sched/cls_u32.c +++ b/net/sched/cls_u32.c @@ -370,6 +370,10 @@ static int u32_init(struct tcf_proto *tp) refcount_set(&root_ht->refcnt, 1); root_ht->handle = tp_c ? gen_new_htid(tp_c, root_ht) : id2handle(0); + if (root_ht->handle == 0) { + kfree(root_ht); + return -ENOMEM; + } root_ht->prio = tp->prio; root_ht->is_root = true; idr_init(&root_ht->handle_idr); @@ -695,21 +699,33 @@ out: return ret; } -static u32 gen_new_kid(struct tc_u_hnode *ht, u32 htid) +static u32 gen_new_kid(struct tc_u_hnode *ht, u32 htid, int *err) { u32 index = htid | 0x800; u32 max = htid | 0xFFF; + *err = 0; + if (idr_alloc_u32(&ht->handle_idr, NULL, &index, max, GFP_KERNEL)) { index = htid + 1; - if (idr_alloc_u32(&ht->handle_idr, NULL, &index, max, - GFP_KERNEL)) - index = max; + *err = idr_alloc_u32(&ht->handle_idr, NULL, &index, max, + GFP_KERNEL); + if (*err) + return 0; } return index; } +static int u32_kid_extack(int err, struct netlink_ext_ack *extack) +{ + if (err == -ENOSPC) + NL_SET_ERR_MSG_MOD(extack, "Hash table node ID pool exhausted"); + else + NL_SET_ERR_MSG_MOD(extack, "Failed to allocate node ID"); + return err; +} + static const struct nla_policy u32_policy[TCA_U32_MAX + 1] = { [TCA_U32_CLASSID] = { .type = NLA_U32 }, [TCA_U32_HASH] = { .type = NLA_U32 }, @@ -1079,7 +1095,9 @@ static int u32_change(struct net *net, struct sk_buff *in_skb, * handle which is used to uniquely identify the match entry. */ if (!TC_U32_NODE(handle)) { - handle = gen_new_kid(ht, htid); + handle = gen_new_kid(ht, htid, &err); + if (err) + return u32_kid_extack(err, extack); } else { handle = htid | TC_U32_NODE(handle); err = idr_alloc_u32(&ht->handle_idr, NULL, &handle, @@ -1091,7 +1109,9 @@ static int u32_change(struct net *net, struct sk_buff *in_skb, /* The user did not give us a handle; lets just generate one * from the table's pool of nodeids. */ - handle = gen_new_kid(ht, htid); + handle = gen_new_kid(ht, htid, &err); + if (err) + return u32_kid_extack(err, extack); } if (tb[TCA_U32_SEL] == NULL) { diff --git a/net/sctp/inqueue.c b/net/sctp/inqueue.c index 5f988b3a8814..d666cec6b194 100644 --- a/net/sctp/inqueue.c +++ b/net/sctp/inqueue.c @@ -212,8 +212,10 @@ new_skb: chunk->chunk_end = ((__u8 *)ch) + SCTP_PAD4(ntohs(ch->length)); skb_pull(chunk->skb, sizeof(*ch)); chunk->subh.v = NULL; /* Subheader is no longer valid. */ - - if (chunk->chunk_end + sizeof(*ch) <= skb_tail_pointer(chunk->skb)) { + if (unlikely(ntohs(ch->length) < sizeof(*ch))) { + chunk->pdiscard = 1; + } else if (chunk->chunk_end + sizeof(*ch) <= + skb_tail_pointer(chunk->skb)) { /* This is not a singleton */ chunk->singleton = 0; } else if (chunk->chunk_end > skb_tail_pointer(chunk->skb)) { diff --git a/net/sctp/sm_make_chunk.c b/net/sctp/sm_make_chunk.c index 236e25abc7a4..84a4c97d0f75 100644 --- a/net/sctp/sm_make_chunk.c +++ b/net/sctp/sm_make_chunk.c @@ -3215,6 +3215,9 @@ bool sctp_verify_asconf(const struct sctp_association *asoc, *errp = param.p; switch (param.p->type) { case SCTP_PARAM_ERR_CAUSE: + if (length < sizeof(struct sctp_addip_param) + + sizeof(struct sctp_errhdr)) + return false; break; case SCTP_PARAM_IPV4_ADDRESS: if (length != sizeof(struct sctp_ipv4addr_param)) @@ -3448,20 +3451,15 @@ static __be16 sctp_get_asconf_response(struct sctp_chunk *asconf_ack, case SCTP_PARAM_ERR_CAUSE: length = sizeof(*asconf_ack_param); err_param = (void *)asconf_ack_param + length; - asconf_ack_len -= length; - if (asconf_ack_len > 0) - return err_param->cause; - else - return SCTP_ERROR_INV_PARAM; - break; + return err_param->cause; default: return SCTP_ERROR_INV_PARAM; } } length = ntohs(asconf_ack_param->param_hdr.length); - asconf_ack_param = (void *)asconf_ack_param + length; - asconf_ack_len -= length; + asconf_ack_param = (void *)asconf_ack_param + SCTP_PAD4(length); + asconf_ack_len -= SCTP_PAD4(length); } return err_code; diff --git a/net/sctp/sm_sideeffect.c b/net/sctp/sm_sideeffect.c index 94716406d602..0d99b7e8c082 100644 --- a/net/sctp/sm_sideeffect.c +++ b/net/sctp/sm_sideeffect.c @@ -1545,17 +1545,8 @@ static int sctp_cmd_interpreter(enum sctp_event_type event_type, timeout = asoc->timeouts[cmd->obj.to]; BUG_ON(!timeout); - /* - * SCTP has a hard time with timer starts. Because we process - * timer starts as side effects, it can be hard to tell if we - * have already started a timer or not, which leads to BUG - * halts when we call add_timer. So here, instead of just starting - * a timer, if the timer is already started, and just mod - * the timer with the shorter of the two expiration times - */ - if (!timer_pending(timer)) + if (!timer_reduce(timer, jiffies + timeout)) sctp_association_hold(asoc); - timer_reduce(timer, jiffies + timeout); break; case SCTP_CMD_TIMER_RESTART: diff --git a/net/sunrpc/auth_gss/gss_krb5_crypto.c b/net/sunrpc/auth_gss/gss_krb5_crypto.c index cf461ebcdde5..09a7c97e87da 100644 --- a/net/sunrpc/auth_gss/gss_krb5_crypto.c +++ b/net/sunrpc/auth_gss/gss_krb5_crypto.c @@ -282,9 +282,8 @@ int gss_krb5_mic_build_sg(const struct xdr_buf *body, unsigned int overflow_nents = nsg - XDR_BUF_TO_SG_NENTS + 1; - *sg_overflow = kmalloc_array(overflow_nents, - sizeof(**sg_overflow), - GFP_NOFS); + *sg_overflow = kmalloc_objs(**sg_overflow, overflow_nents, + GFP_NOFS); if (!*sg_overflow) return -ENOMEM; diff --git a/net/sunrpc/svcauth_unix.c b/net/sunrpc/svcauth_unix.c index aebd97e7f66c..31a1bc60a5f6 100644 --- a/net/sunrpc/svcauth_unix.c +++ b/net/sunrpc/svcauth_unix.c @@ -625,7 +625,7 @@ int sunrpc_nl_unix_gid_get_reqs_dumpit(struct sk_buff *skb, if (!cnt) return 0; - items = kcalloc(cnt, sizeof(*items), GFP_KERNEL); + items = kzalloc_objs(*items, cnt); seqnos = kcalloc(cnt, sizeof(*seqnos), GFP_KERNEL); if (!items || !seqnos) { ret = -ENOMEM; @@ -1326,7 +1326,7 @@ int sunrpc_nl_ip_map_get_reqs_dumpit(struct sk_buff *skb, if (!cnt) return 0; - items = kcalloc(cnt, sizeof(*items), GFP_KERNEL); + items = kzalloc_objs(*items, cnt); seqnos = kcalloc(cnt, sizeof(*seqnos), GFP_KERNEL); if (!items || !seqnos) { ret = -ENOMEM; diff --git a/net/sunrpc/xdr.c b/net/sunrpc/xdr.c index cb2ef428651f..c42fd338c607 100644 --- a/net/sunrpc/xdr.c +++ b/net/sunrpc/xdr.c @@ -371,8 +371,7 @@ int xdr_buf_to_sg_alloc(const struct xdr_buf *buf, unsigned int offset, unsigned int overflow_nents = nsg - sg_head_nents + 1; struct scatterlist *overflow; - overflow = kmalloc_array(overflow_nents, sizeof(*overflow), - gfp); + overflow = kmalloc_objs(*overflow, overflow_nents, gfp); if (!overflow) return -ENOMEM; diff --git a/net/tipc/link.c b/net/tipc/link.c index 49dfc098d89b..6427c69f8929 100644 --- a/net/tipc/link.c +++ b/net/tipc/link.c @@ -504,7 +504,7 @@ bool tipc_link_create(struct net *net, char *if_name, int bearer_id, snprintf(l->name, sizeof(l->name), "%s:%s-%s:unknown", self_str, if_name, peer_str); - strcpy(l->if_name, if_name); + strscpy(l->if_name, if_name); l->addr = peer; l->peer_caps = peer_caps; l->net = net; @@ -574,7 +574,7 @@ bool tipc_link_bc_create(struct net *net, u32 ownnode, u32 peer, u8 *peer_id, snprintf(l->name, sizeof(l->name), "%s:%s", tipc_bclink_name, peer_str); } else { - strcpy(l->name, tipc_bclink_name); + strscpy(l->name, tipc_bclink_name); } trace_tipc_link_reset(l, TIPC_DUMP_ALL, "bclink created!"); tipc_link_reset(l); @@ -1898,7 +1898,7 @@ static void tipc_link_build_proto_msg(struct tipc_link *l, int mtyp, bool probe, msg_set_dest_session(hdr, l->peer_session); } msg_set_max_pkt(hdr, l->advertised_mtu); - strcpy(data, l->if_name); + memcpy(data, l->if_name, TIPC_MAX_IF_NAME); msg_set_size(hdr, INT_H_SIZE + TIPC_MAX_IF_NAME); skb_trim(skb, INT_H_SIZE + TIPC_MAX_IF_NAME); } diff --git a/net/tipc/name_table.c b/net/tipc/name_table.c index 253c72d1366e..6fda36ab1766 100644 --- a/net/tipc/name_table.c +++ b/net/tipc/name_table.c @@ -763,21 +763,40 @@ struct publication *tipc_nametbl_publish(struct net *net, struct tipc_uaddr *ua, struct tipc_socket_addr *sk, u32 key) { struct name_table *nt = tipc_name_table(net); + u32 max_user_pub = TIPC_MAX_PUBL - 1; struct tipc_net *tn = tipc_net(net); struct publication *p = NULL; struct sk_buff *skb = NULL; + bool protocol_type = false; u32 rc_dests; + if (ua->sr.type == TIPC_NODE_STATE || ua->sr.type == TIPC_LINK_STATE || + ua->sr.type == TIPC_TOP_SRV) + protocol_type = true; + spin_lock_bh(&tn->nametbl_lock); + if (protocol_type) + goto insert; - if (nt->local_publ_count >= TIPC_MAX_PUBL) { - pr_warn("Bind failed, max limit %u reached\n", TIPC_MAX_PUBL); + /* Reserve one entry for node state service type because it has cluster + * scope and it is distributed in bulk. So, the maximum number of user's + * publications is (TIPC_MAX_PUBL - 1). + */ + if (nt->local_publ_count >= max_user_pub) { + pr_warn("Bind failed, max limit %u reached\n", max_user_pub); goto exit; } +insert: p = tipc_nametbl_insert_publ(net, ua, sk, key); if (p) { - nt->local_publ_count++; + /* Not count node state, link state and topology server types + * so that maximum nt->local_publ_count does not prevent + * protocol service types from being inserted into the name + * table. + */ + if (!protocol_type) + nt->local_publ_count++; skb = tipc_named_publish(net, p); } rc_dests = nt->rc_dests; @@ -810,7 +829,10 @@ void tipc_nametbl_withdraw(struct net *net, struct tipc_uaddr *ua, p = tipc_nametbl_remove_publ(net, ua, sk, key); if (p) { - nt->local_publ_count--; + if (p->sr.type != TIPC_NODE_STATE && + p->sr.type != TIPC_LINK_STATE && + p->sr.type != TIPC_TOP_SRV) + nt->local_publ_count--; skb = tipc_named_withdraw(net, p); list_del_init(&p->binding_sock); kfree_rcu(p, rcu); diff --git a/net/tipc/node.c b/net/tipc/node.c index 683a136e53ef..bd91378b7540 100644 --- a/net/tipc/node.c +++ b/net/tipc/node.c @@ -1333,7 +1333,9 @@ static void tipc_node_reset_links(struct tipc_node *n) pr_warn("Resetting all links to %x\n", n->addr); + tipc_node_write_lock(n); trace_tipc_node_reset_links(n, true, " "); + tipc_node_write_unlock_fast(n); for (i = 0; i < MAX_BEARERS; i++) { tipc_node_link_down(n, i, false); } diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index 13f9926bf205..79c3921c583c 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -3667,8 +3667,8 @@ static int bpf_iter_unix_realloc_batch(struct bpf_unix_iter_state *iter, { struct sock **new_batch; - new_batch = kvmalloc_array(new_batch_sz, sizeof(*new_batch), - GFP_USER | __GFP_NOWARN); + new_batch = kvmalloc_objs(*new_batch, new_batch_sz, + GFP_USER | __GFP_NOWARN); if (!new_batch) return -ENOMEM; diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c index a33b2a2d381d..f840498b58af 100644 --- a/net/vmw_vsock/af_vsock.c +++ b/net/vmw_vsock/af_vsock.c @@ -438,6 +438,38 @@ struct sock *vsock_find_connected_socket(struct sockaddr_vm *src, } EXPORT_SYMBOL_GPL(vsock_find_connected_socket); +/** + * vsock_check_source - validate a packet source against a socket peer + * @vsk: socket receiving the packet + * @transport: transport receiving the packet + * @src: source address from the packet + * + * Return: true if the packet arrived on the socket's assigned transport and + * its source matches the stored peer. Loopback packets are generated + * internally and always use the local CID as their source, including + * connections using a valid CID alias. + * + * The caller must hold the socket lock and must not call this for listening + * sockets, which accept packets from any source and have no assigned + * transport. + */ +bool vsock_check_source(const struct vsock_sock *vsk, + const struct vsock_transport *transport, + const struct sockaddr_vm *src) +{ + if (vsk->transport != transport) + return false; + + if (src->svm_port != vsk->remote_addr.svm_port) + return false; + + if (src->svm_cid == vsk->remote_addr.svm_cid) + return true; + + return transport->get_local_cid() == VMADDR_CID_LOCAL; +} +EXPORT_SYMBOL_GPL(vsock_check_source); + void vsock_remove_sock(struct vsock_sock *vsk) { /* Transport reassignment must not remove the binding. */ diff --git a/net/vmw_vsock/virtio_transport_common.c b/net/vmw_vsock/virtio_transport_common.c index 88df82364f77..f225f53ed4ba 100644 --- a/net/vmw_vsock/virtio_transport_common.c +++ b/net/vmw_vsock/virtio_transport_common.c @@ -1836,7 +1836,8 @@ void virtio_transport_recv_pkt(struct virtio_transport *t, * lock_sock (note: listener sockets are not assigned to any transport) */ if (sock_flag(sk, SOCK_DONE) || - (sk->sk_state != TCP_LISTEN && vsk->transport != &t->transport)) { + (sk->sk_state != TCP_LISTEN && + !vsock_check_source(vsk, &t->transport, &src))) { (void)virtio_transport_reset_no_sock(t, skb, net); release_sock(sk); sock_put(sk); diff --git a/net/vmw_vsock/vmci_transport.c b/net/vmw_vsock/vmci_transport.c index 1c4ee039c166..1f186e8f8364 100644 --- a/net/vmw_vsock/vmci_transport.c +++ b/net/vmw_vsock/vmci_transport.c @@ -680,11 +680,13 @@ static int vmci_transport_recv_stream_cb(void *data, struct vmci_datagram *dg) struct vmci_transport_packet *pkt; struct vsock_sock *vsk; bool bh_process_pkt; + bool drop_pkt; int err; sk = NULL; err = VMCI_SUCCESS; bh_process_pkt = false; + drop_pkt = false; /* Ignore incoming packets from resources that aren't vsock * implementations. @@ -765,17 +767,29 @@ static int vmci_transport_recv_stream_cb(void *data, struct vmci_datagram *dg) bh_lock_sock(sk); if (!sock_owned_by_user(sk)) { - /* The local context ID may be out of date, update it. */ - vsk->local_addr.svm_cid = dst.svm_cid; + if (sk->sk_state != TCP_LISTEN && + !vsock_check_source(vsk, &vmci_transport, &src)) { + drop_pkt = true; + err = VMCI_ERROR_NO_ACCESS; + } else { + /* The local context ID may be out of date, update it. */ + vsk->local_addr.svm_cid = dst.svm_cid; - if (sk->sk_state == TCP_ESTABLISHED) - vmci_trans(vsk)->notify_ops->handle_notify_pkt( - sk, pkt, true, &dst, &src, - &bh_process_pkt); + if (sk->sk_state == TCP_ESTABLISHED) + vmci_trans(vsk)->notify_ops->handle_notify_pkt(sk, pkt, true, + &dst, &src, + &bh_process_pkt); + } } bh_unlock_sock(sk); + if (drop_pkt) { + if (vmci_transport_send_reset_bh(&dst, &src, pkt) < 0) + pr_err("unable to send reset\n"); + goto out; + } + if (!bh_process_pkt) { struct vmci_transport_recv_pkt_info *recv_pkt_info; @@ -900,6 +914,7 @@ static void vmci_transport_recv_pkt_work(struct work_struct *work) { struct vmci_transport_recv_pkt_info *recv_pkt_info; struct vmci_transport_packet *pkt; + struct sockaddr_vm src; struct sock *sk; recv_pkt_info = @@ -908,6 +923,12 @@ static void vmci_transport_recv_pkt_work(struct work_struct *work) pkt = &recv_pkt_info->pkt; lock_sock(sk); + vsock_addr_init(&src, pkt->dg.src.context, pkt->src_port); + if (sk->sk_state != TCP_LISTEN && + !vsock_check_source(vsock_sk(sk), &vmci_transport, &src)) { + vmci_transport_reply_reset(pkt); + goto out; + } /* The local context ID may be out of date. */ vsock_sk(sk)->local_addr.svm_cid = pkt->dg.dst.context; @@ -937,6 +958,7 @@ static void vmci_transport_recv_pkt_work(struct work_struct *work) break; } +out: release_sock(sk); kfree(recv_pkt_info); /* Release reference obtained in the stream callback when we fetched diff --git a/net/wireless/core.c b/net/wireless/core.c index d13310fef691..3032993ba5dc 100644 --- a/net/wireless/core.c +++ b/net/wireless/core.c @@ -311,9 +311,8 @@ int cfg80211_nan_set_local_schedule(struct cfg80211_registered_device *rdev, if (!sched->n_channels) return 0; - wdev->u.nan.chandefs = kcalloc(sched->n_channels, - sizeof(*wdev->u.nan.chandefs), - GFP_KERNEL); + wdev->u.nan.chandefs = kzalloc_objs(*wdev->u.nan.chandefs, + sched->n_channels); if (!wdev->u.nan.chandefs) return -ENOMEM; diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 44f2bad08670..899b6374c550 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -17330,8 +17330,7 @@ static int nl80211_parse_nan_channel(struct cfg80211_registered_device *rdev, u8 n_rx_nss; int ret; - channel_parsed = kcalloc(NL80211_ATTR_MAX + 1, sizeof(*channel_parsed), - GFP_KERNEL); + channel_parsed = kzalloc_objs(*channel_parsed, NL80211_ATTR_MAX + 1); if (!channel_parsed) return -ENOMEM; @@ -17554,8 +17553,7 @@ static int nl80211_nan_set_peer_sched(struct sk_buff *skb, } if (n_channels) { - nan_channels = kcalloc(n_channels, sizeof(*nan_channels), - GFP_KERNEL); + nan_channels = kzalloc_objs(*nan_channels, n_channels); if (!nan_channels) return -ENOMEM; } @@ -17693,8 +17691,7 @@ static int nl80211_nan_set_local_sched(struct sk_buff *skb, info->nlhdr, GENL_HDRLEN, rem) n_channels++; - sched = kzalloc(struct_size(sched, nan_channels, n_channels), - GFP_KERNEL); + sched = kzalloc_flex(*sched, nan_channels, n_channels); if (!sched) return -ENOMEM; |