diff options
Diffstat (limited to 'net')
171 files changed, 2291 insertions, 1251 deletions
diff --git a/net/8021q/vlan_dev.c b/net/8021q/vlan_dev.c index 6f142f0..733ec28 100644 --- a/net/8021q/vlan_dev.c +++ b/net/8021q/vlan_dev.c @@ -493,10 +493,48 @@ static void vlan_dev_change_rx_flags(struct net_device *dev, int change) } } +static int vlan_calculate_locking_subclass(struct net_device *real_dev) +{ + int subclass = 0; + + while (is_vlan_dev(real_dev)) { + subclass++; + real_dev = vlan_dev_priv(real_dev)->real_dev; + } + + return subclass; +} + +static void vlan_dev_mc_sync(struct net_device *to, struct net_device *from) +{ + int err = 0, subclass; + + subclass = vlan_calculate_locking_subclass(to); + + spin_lock_nested(&to->addr_list_lock, subclass); + err = __hw_addr_sync(&to->mc, &from->mc, to->addr_len); + if (!err) + __dev_set_rx_mode(to); + spin_unlock(&to->addr_list_lock); +} + +static void vlan_dev_uc_sync(struct net_device *to, struct net_device *from) +{ + int err = 0, subclass; + + subclass = vlan_calculate_locking_subclass(to); + + spin_lock_nested(&to->addr_list_lock, subclass); + err = __hw_addr_sync(&to->uc, &from->uc, to->addr_len); + if (!err) + __dev_set_rx_mode(to); + spin_unlock(&to->addr_list_lock); +} + static void vlan_dev_set_rx_mode(struct net_device *vlan_dev) { - dev_mc_sync(vlan_dev_priv(vlan_dev)->real_dev, vlan_dev); - dev_uc_sync(vlan_dev_priv(vlan_dev)->real_dev, vlan_dev); + vlan_dev_mc_sync(vlan_dev_priv(vlan_dev)->real_dev, vlan_dev); + vlan_dev_uc_sync(vlan_dev_priv(vlan_dev)->real_dev, vlan_dev); } /* @@ -608,9 +646,7 @@ static int vlan_dev_init(struct net_device *dev) SET_NETDEV_DEVTYPE(dev, &vlan_type); - if (is_vlan_dev(real_dev)) - subclass = 1; - + subclass = vlan_calculate_locking_subclass(dev); vlan_dev_set_lockdep_class(dev, subclass); vlan_dev_priv(dev)->vlan_pcpu_stats = netdev_alloc_pcpu_stats(struct vlan_pcpu_stats); diff --git a/net/9p/client.c b/net/9p/client.c index 9186550..0004cba 100644 --- a/net/9p/client.c +++ b/net/9p/client.c @@ -415,9 +415,17 @@ static void p9_free_req(struct p9_client *c, struct p9_req_t *r) * req: request received * */ -void p9_client_cb(struct p9_client *c, struct p9_req_t *req) +void p9_client_cb(struct p9_client *c, struct p9_req_t *req, int status) { p9_debug(P9_DEBUG_MUX, " tag %d\n", req->tc->tag); + + /* + * This barrier is needed to make sure any change made to req before + * the other thread wakes up will indeed be seen by the waiting side. + */ + smp_wmb(); + req->status = status; + wake_up(req->wq); p9_debug(P9_DEBUG_MUX, "wakeup: %d\n", req->tc->tag); } @@ -655,16 +663,13 @@ static int p9_client_flush(struct p9_client *c, struct p9_req_t *oldreq) if (IS_ERR(req)) return PTR_ERR(req); - /* * if we haven't received a response for oldreq, * remove it from the list */ - if (oldreq->status == REQ_STATUS_FLSH) { - spin_lock(&c->lock); - list_del(&oldreq->req_list); - spin_unlock(&c->lock); - } + if (oldreq->status == REQ_STATUS_SENT) + if (c->trans_mod->cancelled) + c->trans_mod->cancelled(c, oldreq); p9_free_req(c, req); return 0; @@ -751,6 +756,12 @@ again: err = wait_event_interruptible(*req->wq, req->status >= REQ_STATUS_RCVD); + /* + * Make sure our req is coherent with regard to updates in other + * threads - echoes to wmb() in the callback + */ + smp_rmb(); + if ((err == -ERESTARTSYS) && (c->status == Connected) && (type == P9_TFLUSH)) { sigpending = 1; diff --git a/net/9p/trans_fd.c b/net/9p/trans_fd.c index b7bd7f2..80d08f6 100644 --- a/net/9p/trans_fd.c +++ b/net/9p/trans_fd.c @@ -66,20 +66,6 @@ struct p9_fd_opts { int privport; }; -/** - * struct p9_trans_fd - transport state - * @rd: reference to file to read from - * @wr: reference of file to write to - * @conn: connection state reference - * - */ - -struct p9_trans_fd { - struct file *rd; - struct file *wr; - struct p9_conn *conn; -}; - /* * Option Parsing (code inspired by NFS code) * - a little lazy - parse all fd-transport options @@ -159,6 +145,20 @@ struct p9_conn { unsigned long wsched; }; +/** + * struct p9_trans_fd - transport state + * @rd: reference to file to read from + * @wr: reference of file to write to + * @conn: connection state reference + * + */ + +struct p9_trans_fd { + struct file *rd; + struct file *wr; + struct p9_conn conn; +}; + static void p9_poll_workfn(struct work_struct *work); static DEFINE_SPINLOCK(p9_poll_lock); @@ -212,15 +212,9 @@ static void p9_conn_cancel(struct p9_conn *m, int err) m->err = err; list_for_each_entry_safe(req, rtmp, &m->req_list, req_list) { - req->status = REQ_STATUS_ERROR; - if (!req->t_err) - req->t_err = err; list_move(&req->req_list, &cancel_list); } list_for_each_entry_safe(req, rtmp, &m->unsent_req_list, req_list) { - req->status = REQ_STATUS_ERROR; - if (!req->t_err) - req->t_err = err; list_move(&req->req_list, &cancel_list); } spin_unlock_irqrestore(&m->client->lock, flags); @@ -228,7 +222,9 @@ static void p9_conn_cancel(struct p9_conn *m, int err) list_for_each_entry_safe(req, rtmp, &cancel_list, req_list) { p9_debug(P9_DEBUG_ERROR, "call back req %p\n", req); list_del(&req->req_list); - p9_client_cb(m->client, req); + if (!req->t_err) + req->t_err = err; + p9_client_cb(m->client, req, REQ_STATUS_ERROR); } } @@ -302,6 +298,7 @@ static void p9_read_work(struct work_struct *work) { int n, err; struct p9_conn *m; + int status = REQ_STATUS_ERROR; m = container_of(work, struct p9_conn, rq); @@ -348,8 +345,7 @@ static void p9_read_work(struct work_struct *work) "mux %p pkt: size: %d bytes tag: %d\n", m, n, tag); m->req = p9_tag_lookup(m->client, tag); - if (!m->req || (m->req->status != REQ_STATUS_SENT && - m->req->status != REQ_STATUS_FLSH)) { + if (!m->req || (m->req->status != REQ_STATUS_SENT)) { p9_debug(P9_DEBUG_ERROR, "Unexpected packet tag %d\n", tag); err = -EIO; @@ -375,10 +371,10 @@ static void p9_read_work(struct work_struct *work) p9_debug(P9_DEBUG_TRANS, "got new packet\n"); spin_lock(&m->client->lock); if (m->req->status != REQ_STATUS_ERROR) - m->req->status = REQ_STATUS_RCVD; + status = REQ_STATUS_RCVD; list_del(&m->req->req_list); spin_unlock(&m->client->lock); - p9_client_cb(m->client, m->req); + p9_client_cb(m->client, m->req, status); m->rbuf = NULL; m->rpos = 0; m->rsize = 0; @@ -573,21 +569,19 @@ p9_pollwait(struct file *filp, wait_queue_head_t *wait_address, poll_table *p) } /** - * p9_conn_create - allocate and initialize the per-session mux data + * p9_conn_create - initialize the per-session mux data * @client: client instance * * Note: Creates the polling task if this is the first session. */ -static struct p9_conn *p9_conn_create(struct p9_client *client) +static void p9_conn_create(struct p9_client *client) { int n; - struct p9_conn *m; + struct p9_trans_fd *ts = client->trans; + struct p9_conn *m = &ts->conn; p9_debug(P9_DEBUG_TRANS, "client %p msize %d\n", client, client->msize); - m = kzalloc(sizeof(struct p9_conn), GFP_KERNEL); - if (!m) - return ERR_PTR(-ENOMEM); INIT_LIST_HEAD(&m->mux_list); m->client = client; @@ -609,8 +603,6 @@ static struct p9_conn *p9_conn_create(struct p9_client *client) p9_debug(P9_DEBUG_TRANS, "mux %p can write\n", m); set_bit(Wpending, &m->wsched); } - - return m; } /** @@ -669,7 +661,7 @@ static int p9_fd_request(struct p9_client *client, struct p9_req_t *req) { int n; struct p9_trans_fd *ts = client->trans; - struct p9_conn *m = ts->conn; + struct p9_conn *m = &ts->conn; p9_debug(P9_DEBUG_TRANS, "mux %p task %p tcall %p id %d\n", m, current, req->tc, req->tc->id); @@ -704,14 +696,26 @@ static int p9_fd_cancel(struct p9_client *client, struct p9_req_t *req) list_del(&req->req_list); req->status = REQ_STATUS_FLSHD; ret = 0; - } else if (req->status == REQ_STATUS_SENT) - req->status = REQ_STATUS_FLSH; - + } spin_unlock(&client->lock); return ret; } +static int p9_fd_cancelled(struct p9_client *client, struct p9_req_t *req) +{ + p9_debug(P9_DEBUG_TRANS, "client %p req %p\n", client, req); + + /* we haven't received a response for oldreq, + * remove it from the list. + */ + spin_lock(&client->lock); + list_del(&req->req_list); + spin_unlock(&client->lock); + + return 0; +} + /** * parse_opts - parse mount options into p9_fd_opts structure * @params: options string passed from mount @@ -780,7 +784,7 @@ static int parse_opts(char *params, struct p9_fd_opts *opts) static int p9_fd_open(struct p9_client *client, int rfd, int wfd) { - struct p9_trans_fd *ts = kmalloc(sizeof(struct p9_trans_fd), + struct p9_trans_fd *ts = kzalloc(sizeof(struct p9_trans_fd), GFP_KERNEL); if (!ts) return -ENOMEM; @@ -806,9 +810,8 @@ static int p9_socket_open(struct p9_client *client, struct socket *csocket) { struct p9_trans_fd *p; struct file *file; - int ret; - p = kmalloc(sizeof(struct p9_trans_fd), GFP_KERNEL); + p = kzalloc(sizeof(struct p9_trans_fd), GFP_KERNEL); if (!p) return -ENOMEM; @@ -829,20 +832,12 @@ static int p9_socket_open(struct p9_client *client, struct socket *csocket) p->rd->f_flags |= O_NONBLOCK; - p->conn = p9_conn_create(client); - if (IS_ERR(p->conn)) { - ret = PTR_ERR(p->conn); - p->conn = NULL; - kfree(p); - sockfd_put(csocket); - sockfd_put(csocket); - return ret; - } + p9_conn_create(client); return 0; } /** - * p9_mux_destroy - cancels all pending requests and frees mux resources + * p9_mux_destroy - cancels all pending requests of mux * @m: mux to destroy * */ @@ -859,7 +854,6 @@ static void p9_conn_destroy(struct p9_conn *m) p9_conn_cancel(m, -ECONNRESET); m->client = NULL; - kfree(m); } /** @@ -881,7 +875,7 @@ static void p9_fd_close(struct p9_client *client) client->status = Disconnected; - p9_conn_destroy(ts->conn); + p9_conn_destroy(&ts->conn); if (ts->rd) fput(ts->rd); @@ -1033,14 +1027,7 @@ p9_fd_create(struct p9_client *client, const char *addr, char *args) return err; p = (struct p9_trans_fd *) client->trans; - p->conn = p9_conn_create(client); - if (IS_ERR(p->conn)) { - err = PTR_ERR(p->conn); - p->conn = NULL; - fput(p->rd); - fput(p->wr); - return err; - } + p9_conn_create(client); return 0; } @@ -1053,6 +1040,7 @@ static struct p9_trans_module p9_tcp_trans = { .close = p9_fd_close, .request = p9_fd_request, .cancel = p9_fd_cancel, + .cancelled = p9_fd_cancelled, .owner = THIS_MODULE, }; @@ -1064,6 +1052,7 @@ static struct p9_trans_module p9_unix_trans = { .close = p9_fd_close, .request = p9_fd_request, .cancel = p9_fd_cancel, + .cancelled = p9_fd_cancelled, .owner = THIS_MODULE, }; @@ -1075,6 +1064,7 @@ static struct p9_trans_module p9_fd_trans = { .close = p9_fd_close, .request = p9_fd_request, .cancel = p9_fd_cancel, + .cancelled = p9_fd_cancelled, .owner = THIS_MODULE, }; diff --git a/net/9p/trans_rdma.c b/net/9p/trans_rdma.c index 8f68df5..14ad43b 100644 --- a/net/9p/trans_rdma.c +++ b/net/9p/trans_rdma.c @@ -193,6 +193,8 @@ static int parse_opts(char *params, struct p9_rdma_opts *opts) if (!*p) continue; token = match_token(p, tokens, args); + if (token == Opt_err) + continue; r = match_int(&args[0], &option); if (r < 0) { p9_debug(P9_DEBUG_ERROR, @@ -305,8 +307,7 @@ handle_recv(struct p9_client *client, struct p9_trans_rdma *rdma, } req->rc = c->rc; - req->status = REQ_STATUS_RCVD; - p9_client_cb(client, req); + p9_client_cb(client, req, REQ_STATUS_RCVD); return; @@ -511,6 +512,11 @@ dont_need_post_recv: goto send_error; } + /* Mark request as `sent' *before* we actually send it, + * because doing if after could erase the REQ_STATUS_RCVD + * status in case of a very fast reply. + */ + req->status = REQ_STATUS_SENT; err = ib_post_send(rdma->qp, &wr, &bad_wr); if (err) goto send_error; @@ -520,6 +526,7 @@ dont_need_post_recv: /* Handle errors that happened during or while preparing the send: */ send_error: + req->status = REQ_STATUS_ERROR; kfree(c); p9_debug(P9_DEBUG_ERROR, "Error %d in rdma_request()\n", err); @@ -582,12 +589,24 @@ static struct p9_trans_rdma *alloc_rdma(struct p9_rdma_opts *opts) return rdma; } -/* its not clear to me we can do anything after send has been posted */ static int rdma_cancel(struct p9_client *client, struct p9_req_t *req) { + /* Nothing to do here. + * We will take care of it (if we have to) in rdma_cancelled() + */ return 1; } +/* A request has been fully flushed without a reply. + * That means we have posted one buffer in excess. + */ +static int rdma_cancelled(struct p9_client *client, struct p9_req_t *req) +{ + struct p9_trans_rdma *rdma = client->trans; + atomic_inc(&rdma->excess_rc); + return 0; +} + /** * trans_create_rdma - Transport method for creating atransport instance * @client: client instance @@ -721,6 +740,7 @@ static struct p9_trans_module p9_rdma_trans = { .close = rdma_close, .request = rdma_request, .cancel = rdma_cancel, + .cancelled = rdma_cancelled, }; /** diff --git a/net/9p/trans_virtio.c b/net/9p/trans_virtio.c index ac2666c..6940d8f 100644 --- a/net/9p/trans_virtio.c +++ b/net/9p/trans_virtio.c @@ -164,8 +164,7 @@ static void req_done(struct virtqueue *vq) p9_debug(P9_DEBUG_TRANS, ": rc %p\n", rc); p9_debug(P9_DEBUG_TRANS, ": lookup tag %d\n", rc->tag); req = p9_tag_lookup(chan->client, rc->tag); - req->status = REQ_STATUS_RCVD; - p9_client_cb(chan->client, req); + p9_client_cb(chan->client, req, REQ_STATUS_RCVD); } } diff --git a/net/Kconfig b/net/Kconfig index d1f6f96..d92afe4 100644 --- a/net/Kconfig +++ b/net/Kconfig @@ -243,7 +243,7 @@ config XPS default y config CGROUP_NET_PRIO - tristate "Network priority cgroup" + bool "Network priority cgroup" depends on CGROUPS ---help--- Cgroup subsystem for use in assigning processes to network priorities on diff --git a/net/atm/clip.c b/net/atm/clip.c index 8215f7c..ba291ce 100644 --- a/net/atm/clip.c +++ b/net/atm/clip.c @@ -68,7 +68,7 @@ static int to_atmarpd(enum atmarp_ctrl_type type, int itf, __be32 ip) sk = sk_atm(atmarpd); skb_queue_tail(&sk->sk_receive_queue, skb); - sk->sk_data_ready(sk, skb->len); + sk->sk_data_ready(sk); return 0; } diff --git a/net/atm/lec.c b/net/atm/lec.c index 5a2f602..4c5b8ba 100644 --- a/net/atm/lec.c +++ b/net/atm/lec.c @@ -152,7 +152,7 @@ static void lec_handle_bridge(struct sk_buff *skb, struct net_device *dev) atm_force_charge(priv->lecd, skb2->truesize); sk = sk_atm(priv->lecd); skb_queue_tail(&sk->sk_receive_queue, skb2); - sk->sk_data_ready(sk, skb2->len); + sk->sk_data_ready(sk); } } #endif /* defined(CONFIG_BRIDGE) || defined(CONFIG_BRIDGE_MODULE) */ @@ -447,7 +447,7 @@ static int lec_atm_send(struct atm_vcc *vcc, struct sk_buff *skb) atm_force_charge(priv->lecd, skb2->truesize); sk = sk_atm(priv->lecd); skb_queue_tail(&sk->sk_receive_queue, skb2); - sk->sk_data_ready(sk, skb2->len); + sk->sk_data_ready(sk); } } #endif /* defined(CONFIG_BRIDGE) || defined(CONFIG_BRIDGE_MODULE) */ @@ -530,13 +530,13 @@ send_to_lecd(struct lec_priv *priv, atmlec_msg_type type, atm_force_charge(priv->lecd, skb->truesize); sk = sk_atm(priv->lecd); skb_queue_tail(&sk->sk_receive_queue, skb); - sk->sk_data_ready(sk, skb->len); + sk->sk_data_ready(sk); if (data != NULL) { pr_debug("about to send %d bytes of data\n", data->len); atm_force_charge(priv->lecd, data->truesize); skb_queue_tail(&sk->sk_receive_queue, data); - sk->sk_data_ready(sk, skb->len); + sk->sk_data_ready(sk); } return 0; @@ -616,7 +616,7 @@ static void lec_push(struct atm_vcc *vcc, struct sk_buff *skb) pr_debug("%s: To daemon\n", dev->name); skb_queue_tail(&sk->sk_receive_queue, skb); - sk->sk_data_ready(sk, skb->len); + sk->sk_data_ready(sk); } else { /* Data frame, queue to protocol handlers */ struct lec_arp_table *entry; unsigned char *src, *dst; diff --git a/net/atm/mpc.c b/net/atm/mpc.c index 91dc58f..e8e0e7a 100644 --- a/net/atm/mpc.c +++ b/net/atm/mpc.c @@ -706,7 +706,7 @@ static void mpc_push(struct atm_vcc *vcc, struct sk_buff *skb) dprintk("(%s) control packet arrived\n", dev->name); /* Pass control packets to daemon */ skb_queue_tail(&sk->sk_receive_queue, skb); - sk->sk_data_ready(sk, skb->len); + sk->sk_data_ready(sk); return; } @@ -992,7 +992,7 @@ int msg_to_mpoad(struct k_message *mesg, struct mpoa_client *mpc) sk = sk_atm(mpc->mpoad_vcc); skb_queue_tail(&sk->sk_receive_queue, skb); - sk->sk_data_ready(sk, skb->len); + sk->sk_data_ready(sk); return 0; } @@ -1273,7 +1273,7 @@ static void purge_egress_shortcut(struct atm_vcc *vcc, eg_cache_entry *entry) sk = sk_atm(vcc); skb_queue_tail(&sk->sk_receive_queue, skb); - sk->sk_data_ready(sk, skb->len); + sk->sk_data_ready(sk); dprintk("exiting\n"); } diff --git a/net/atm/raw.c b/net/atm/raw.c index b4f7b9f..2e17e97 100644 --- a/net/atm/raw.c +++ b/net/atm/raw.c @@ -25,7 +25,7 @@ static void atm_push_raw(struct atm_vcc *vcc, struct sk_buff *skb) struct sock *sk = sk_atm(vcc); skb_queue_tail(&sk->sk_receive_queue, skb); - sk->sk_data_ready(sk, skb->len); + sk->sk_data_ready(sk); } } diff --git a/net/atm/signaling.c b/net/atm/signaling.c index 4176887..523bce7 100644 --- a/net/atm/signaling.c +++ b/net/atm/signaling.c @@ -51,7 +51,7 @@ static void sigd_put_skb(struct sk_buff *skb) #endif atm_force_charge(sigd, skb->truesize); skb_queue_tail(&sk_atm(sigd)->sk_receive_queue, skb); - sk_atm(sigd)->sk_data_ready(sk_atm(sigd), skb->len); + sk_atm(sigd)->sk_data_ready(sk_atm(sigd)); } static void modify_qos(struct atm_vcc *vcc, struct atmsvc_msg *msg) diff --git a/net/ax25/ax25_in.c b/net/ax25/ax25_in.c index 96f4cab3..7ed8ab7 100644 --- a/net/ax25/ax25_in.c +++ b/net/ax25/ax25_in.c @@ -422,7 +422,7 @@ static int ax25_rcv(struct sk_buff *skb, struct net_device *dev, if (sk) { if (!sock_flag(sk, SOCK_DEAD)) - sk->sk_data_ready(sk, skb->len); + sk->sk_data_ready(sk); sock_put(sk); } else { free: diff --git a/net/batman-adv/bat_iv_ogm.c b/net/batman-adv/bat_iv_ogm.c index b3bd4ec..f04224c 100644 --- a/net/batman-adv/bat_iv_ogm.c +++ b/net/batman-adv/bat_iv_ogm.c @@ -1545,6 +1545,8 @@ out_neigh: if ((orig_neigh_node) && (!is_single_hop_neigh)) batadv_orig_node_free_ref(orig_neigh_node); out: + if (router_ifinfo) + batadv_neigh_ifinfo_free_ref(router_ifinfo); if (router) batadv_neigh_node_free_ref(router); if (router_router) diff --git a/net/batman-adv/originator.c b/net/batman-adv/originator.c index ffd9dfb..1785da3 100644 --- a/net/batman-adv/originator.c +++ b/net/batman-adv/originator.c @@ -501,12 +501,17 @@ batadv_neigh_node_get(const struct batadv_orig_node *orig_node, static void batadv_orig_ifinfo_free_rcu(struct rcu_head *rcu) { struct batadv_orig_ifinfo *orig_ifinfo; + struct batadv_neigh_node *router; orig_ifinfo = container_of(rcu, struct batadv_orig_ifinfo, rcu); if (orig_ifinfo->if_outgoing != BATADV_IF_DEFAULT) batadv_hardif_free_ref_now(orig_ifinfo->if_outgoing); + /* this is the last reference to this object */ + router = rcu_dereference_protected(orig_ifinfo->router, true); + if (router) + batadv_neigh_node_free_ref_now(router); kfree(orig_ifinfo); } @@ -702,6 +707,47 @@ free_orig_node: } /** + * batadv_purge_neigh_ifinfo - purge obsolete ifinfo entries from neighbor + * @bat_priv: the bat priv with all the soft interface information + * @neigh: orig node which is to be checked + */ +static void +batadv_purge_neigh_ifinfo(struct batadv_priv *bat_priv, + struct batadv_neigh_node *neigh) +{ + struct batadv_neigh_ifinfo *neigh_ifinfo; + struct batadv_hard_iface *if_outgoing; + struct hlist_node *node_tmp; + + spin_lock_bh(&neigh->ifinfo_lock); + + /* for all ifinfo objects for this neighinator */ + hlist_for_each_entry_safe(neigh_ifinfo, node_tmp, + &neigh->ifinfo_list, list) { + if_outgoing = neigh_ifinfo->if_outgoing; + + /* always keep the default interface */ + if (if_outgoing == BATADV_IF_DEFAULT) + continue; + + /* don't purge if the interface is not (going) down */ + if ((if_outgoing->if_status != BATADV_IF_INACTIVE) && + (if_outgoing->if_status != BATADV_IF_NOT_IN_USE) && + (if_outgoing->if_status != BATADV_IF_TO_BE_REMOVED)) + continue; + + batadv_dbg(BATADV_DBG_BATMAN, bat_priv, + "neighbor/ifinfo purge: neighbor %pM, iface: %s\n", + neigh->addr, if_outgoing->net_dev->name); + + hlist_del_rcu(&neigh_ifinfo->list); + batadv_neigh_ifinfo_free_ref(neigh_ifinfo); + } + + spin_unlock_bh(&neigh->ifinfo_lock); +} + +/** * batadv_purge_orig_ifinfo - purge obsolete ifinfo entries from originator * @bat_priv: the bat priv with all the soft interface information * @orig_node: orig node which is to be checked @@ -800,6 +846,11 @@ batadv_purge_orig_neighbors(struct batadv_priv *bat_priv, hlist_del_rcu(&neigh_node->list); batadv_neigh_node_free_ref(neigh_node); + } else { + /* only necessary if not the whole neighbor is to be + * deleted, but some interface has been removed. + */ + batadv_purge_neigh_ifinfo(bat_priv, neigh_node); } } @@ -857,7 +908,7 @@ static bool batadv_purge_orig_node(struct batadv_priv *bat_priv, { struct batadv_neigh_node *best_neigh_node; struct batadv_hard_iface *hard_iface; - bool changed; + bool changed_ifinfo, changed_neigh; if (batadv_has_timed_out(orig_node->last_seen, 2 * BATADV_PURGE_TIMEOUT)) { @@ -867,10 +918,10 @@ static bool batadv_purge_orig_node(struct batadv_priv *bat_priv, jiffies_to_msecs(orig_node->last_seen)); return true; } - changed = batadv_purge_orig_ifinfo(bat_priv, orig_node); - changed = changed || batadv_purge_orig_neighbors(bat_priv, orig_node); + changed_ifinfo = batadv_purge_orig_ifinfo(bat_priv, orig_node); + changed_neigh = batadv_purge_orig_neighbors(bat_priv, orig_node); - if (!changed) + if (!changed_ifinfo && !changed_neigh) return false; /* first for NULL ... */ diff --git a/net/bluetooth/hci_conn.c b/net/bluetooth/hci_conn.c index d958e2d..521fd4f 100644 --- a/net/bluetooth/hci_conn.c +++ b/net/bluetooth/hci_conn.c @@ -819,14 +819,17 @@ static int hci_conn_auth(struct hci_conn *conn, __u8 sec_level, __u8 auth_type) if (!test_and_set_bit(HCI_CONN_AUTH_PEND, &conn->flags)) { struct hci_cp_auth_requested cp; - /* encrypt must be pending if auth is also pending */ - set_bit(HCI_CONN_ENCRYPT_PEND, &conn->flags); - cp.handle = cpu_to_le16(conn->handle); hci_send_cmd(conn->hdev, HCI_OP_AUTH_REQUESTED, sizeof(cp), &cp); + + /* If we're already encrypted set the REAUTH_PEND flag, + * otherwise set the ENCRYPT_PEND. + */ if (conn->key_type != 0xff) set_bit(HCI_CONN_REAUTH_PEND, &conn->flags); + else + set_bit(HCI_CONN_ENCRYPT_PEND, &conn->flags); } return 0; diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c index 4977491..15010a2 100644 --- a/net/bluetooth/hci_event.c +++ b/net/bluetooth/hci_event.c @@ -3330,6 +3330,12 @@ static void hci_key_refresh_complete_evt(struct hci_dev *hdev, if (!conn) goto unlock; + /* For BR/EDR the necessary steps are taken through the + * auth_complete event. + */ + if (conn->type != LE_LINK) + goto unlock; + if (!ev->status) conn->sec_level = conn->pending_sec_level; diff --git a/net/bluetooth/l2cap_sock.c b/net/bluetooth/l2cap_sock.c index f59e00c..ef5e5b0 100644 --- a/net/bluetooth/l2cap_sock.c +++ b/net/bluetooth/l2cap_sock.c @@ -1271,7 +1271,7 @@ static void l2cap_sock_teardown_cb(struct l2cap_chan *chan, int err) if (parent) { bt_accept_unlink(sk); - parent->sk_data_ready(parent, 0); + parent->sk_data_ready(parent); } else { sk->sk_state_change(sk); } @@ -1327,7 +1327,7 @@ static void l2cap_sock_ready_cb(struct l2cap_chan *chan) sk->sk_state_change(sk); if (parent) - parent->sk_data_ready(parent, 0); + parent->sk_data_ready(parent); release_sock(sk); } @@ -1340,7 +1340,7 @@ static void l2cap_sock_defer_cb(struct l2cap_chan *chan) parent = bt_sk(sk)->parent; if (parent) - parent->sk_data_ready(parent, 0); + parent->sk_data_ready(parent); release_sock(sk); } diff --git a/net/bluetooth/rfcomm/core.c b/net/bluetooth/rfcomm/core.c index 633ccee..cf620260 100644 --- a/net/bluetooth/rfcomm/core.c +++ b/net/bluetooth/rfcomm/core.c @@ -186,9 +186,9 @@ static void rfcomm_l2state_change(struct sock *sk) rfcomm_schedule(); } -static void rfcomm_l2data_ready(struct sock *sk, int bytes) +static void rfcomm_l2data_ready(struct sock *sk) { - BT_DBG("%p bytes %d", sk, bytes); + BT_DBG("%p", sk); rfcomm_schedule(); } diff --git a/net/bluetooth/rfcomm/sock.c b/net/bluetooth/rfcomm/sock.c index eabd25a..c603a5e 100644 --- a/net/bluetooth/rfcomm/sock.c +++ b/net/bluetooth/rfcomm/sock.c @@ -54,7 +54,7 @@ static void rfcomm_sk_data_ready(struct rfcomm_dlc *d, struct sk_buff *skb) atomic_add(skb->len, &sk->sk_rmem_alloc); skb_queue_tail(&sk->sk_receive_queue, skb); - sk->sk_data_ready(sk, skb->len); + sk->sk_data_ready(sk); if (atomic_read(&sk->sk_rmem_alloc) >= sk->sk_rcvbuf) rfcomm_dlc_throttle(d); @@ -84,7 +84,7 @@ static void rfcomm_sk_state_change(struct rfcomm_dlc *d, int err) sock_set_flag(sk, SOCK_ZAPPED); bt_accept_unlink(sk); } - parent->sk_data_ready(parent, 0); + parent->sk_data_ready(parent); } else { if (d->state == BT_CONNECTED) rfcomm_session_getaddr(d->session, diff --git a/net/bluetooth/sco.c b/net/bluetooth/sco.c index ab1e6fc..c06dbd3 100644 --- a/net/bluetooth/sco.c +++ b/net/bluetooth/sco.c @@ -1024,7 +1024,7 @@ static void sco_conn_ready(struct sco_conn *conn) sk->sk_state = BT_CONNECTED; /* Wake up parent */ - parent->sk_data_ready(parent, 1); + parent->sk_data_ready(parent); bh_unlock_sock(parent); diff --git a/net/bridge/br_input.c b/net/bridge/br_input.c index d0cca3c..7985dea 100644 --- a/net/bridge/br_input.c +++ b/net/bridge/br_input.c @@ -73,7 +73,7 @@ int br_handle_frame_finish(struct sk_buff *skb) goto drop; if (!br_allowed_ingress(p->br, nbp_get_vlan_info(p), skb, &vid)) - goto drop; + goto out; /* insert into forwarding database after filtering to avoid spoofing */ br = p->br; diff --git a/net/bridge/br_netfilter.c b/net/bridge/br_netfilter.c index 80e1b0f..2acf7fa 100644 --- a/net/bridge/br_netfilter.c +++ b/net/bridge/br_netfilter.c @@ -859,12 +859,12 @@ static unsigned int br_nf_forward_arp(const struct nf_hook_ops *ops, return NF_STOLEN; } -#if IS_ENABLED(CONFIG_NF_CONNTRACK_IPV4) +#if IS_ENABLED(CONFIG_NF_DEFRAG_IPV4) static int br_nf_dev_queue_xmit(struct sk_buff *skb) { int ret; - if (skb->nfct != NULL && skb->protocol == htons(ETH_P_IP) && + if (skb->protocol == htons(ETH_P_IP) && skb->len + nf_bridge_mtu_reduction(skb) > skb->dev->mtu && !skb_is_gso(skb)) { if (br_parse_ip_options(skb)) diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c index e74b6d53..e8844d9 100644 --- a/net/bridge/br_netlink.c +++ b/net/bridge/br_netlink.c @@ -445,6 +445,20 @@ static int br_validate(struct nlattr *tb[], struct nlattr *data[]) return 0; } +static int br_dev_newlink(struct net *src_net, struct net_device *dev, + struct nlattr *tb[], struct nlattr *data[]) +{ + struct net_bridge *br = netdev_priv(dev); + + if (tb[IFLA_ADDRESS]) { + spin_lock_bh(&br->lock); + br_stp_change_bridge_id(br, nla_data(tb[IFLA_ADDRESS])); + spin_unlock_bh(&br->lock); + } + + return register_netdevice(dev); +} + static size_t br_get_link_af_size(const struct net_device *dev) { struct net_port_vlans *pv; @@ -473,6 +487,7 @@ struct rtnl_link_ops br_link_ops __read_mostly = { .priv_size = sizeof(struct net_bridge), .setup = br_dev_setup, .validate = br_validate, + .newlink = br_dev_newlink, .dellink = br_dev_delete, }; diff --git a/net/bridge/br_vlan.c b/net/bridge/br_vlan.c index 9151071..4a37161 100644 --- a/net/bridge/br_vlan.c +++ b/net/bridge/br_vlan.c @@ -170,7 +170,7 @@ bool br_allowed_ingress(struct net_bridge *br, struct net_port_vlans *v, * rejected. */ if (!v) - return false; + goto drop; /* If vlan tx offload is disabled on bridge device and frame was * sent from vlan device on the bridge device, it does not have @@ -193,7 +193,7 @@ bool br_allowed_ingress(struct net_bridge *br, struct net_port_vlans *v, * vlan untagged or priority-tagged traffic belongs to. */ if (pvid == VLAN_N_VID) - return false; + goto drop; /* PVID is set on this port. Any untagged or priority-tagged * ingress frame is considered to belong to this vlan. @@ -216,7 +216,8 @@ bool br_allowed_ingress(struct net_bridge *br, struct net_port_vlans *v, /* Frame had a valid vlan tag. See if vlan is allowed */ if (test_bit(*vid, v->vlan_bitmap)) return true; - +drop: + kfree_skb(skb); return false; } diff --git a/net/caif/caif_socket.c b/net/caif/caif_socket.c index d6be3ed..e843709 100644 --- a/net/caif/caif_socket.c +++ b/net/caif/caif_socket.c @@ -124,7 +124,6 @@ static void caif_flow_ctrl(struct sock *sk, int mode) static int caif_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) { int err; - int skb_len; unsigned long flags; struct sk_buff_head *list = &sk->sk_receive_queue; struct caifsock *cf_sk = container_of(sk, struct caifsock, sk); @@ -153,14 +152,13 @@ static int caif_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) * may be freed by other threads of control pulling packets * from the queue. */ - skb_len = skb->len; spin_lock_irqsave(&list->lock, flags); if (!sock_flag(sk, SOCK_DEAD)) __skb_queue_tail(list, skb); spin_unlock_irqrestore(&list->lock, flags); if (!sock_flag(sk, SOCK_DEAD)) - sk->sk_data_ready(sk, skb_len); + sk->sk_data_ready(sk); else kfree_skb(skb); return 0; diff --git a/net/can/gw.c b/net/can/gw.c index ac31891..050a211 100644 --- a/net/can/gw.c +++ b/net/can/gw.c @@ -804,7 +804,7 @@ static int cgw_create_job(struct sk_buff *skb, struct nlmsghdr *nlh) u8 limhops = 0; int err = 0; - if (!capable(CAP_NET_ADMIN)) + if (!netlink_capable(skb, CAP_NET_ADMIN)) return -EPERM; if (nlmsg_len(nlh) < sizeof(*r)) @@ -893,7 +893,7 @@ static int cgw_remove_job(struct sk_buff *skb, struct nlmsghdr *nlh) u8 limhops = 0; int err = 0; - if (!capable(CAP_NET_ADMIN)) + if (!netlink_capable(skb, CAP_NET_ADMIN)) return -EPERM; if (nlmsg_len(nlh) < sizeof(*r)) diff --git a/net/ceph/crush/mapper.c b/net/ceph/crush/mapper.c index b703790..a1ef53c 100644 --- a/net/ceph/crush/mapper.c +++ b/net/ceph/crush/mapper.c @@ -292,10 +292,12 @@ static int is_out(const struct crush_map *map, * @outpos: our position in that vector * @tries: number of attempts to make * @recurse_tries: number of attempts to have recursive chooseleaf make - * @local_tries: localized retries - * @local_fallback_tries: localized fallback retries + * @local_retries: localized retries + * @local_fallback_retries: localized fallback retries * @recurse_to_leaf: true if we want one device under each item of given type (chooseleaf instead of choose) + * @vary_r: pass r to recursive calls * @out2: second output vector for leaf items (if @recurse_to_leaf) + * @parent_r: r value passed from the parent */ static int crush_choose_firstn(const struct crush_map *map, struct crush_bucket *bucket, @@ -304,10 +306,12 @@ static int crush_choose_firstn(const struct crush_map *map, int *out, int outpos, unsigned int tries, unsigned int recurse_tries, - unsigned int local_tries, - unsigned int local_fallback_tries, + unsigned int local_retries, + unsigned int local_fallback_retries, int recurse_to_leaf, - int *out2) + unsigned int vary_r, + int *out2, + int parent_r) { int rep; unsigned int ftotal, flocal; @@ -319,8 +323,11 @@ static int crush_choose_firstn(const struct crush_map *map, int itemtype; int collide, reject; - dprintk("CHOOSE%s bucket %d x %d outpos %d numrep %d\n", recurse_to_leaf ? "_LEAF" : "", - bucket->id, x, outpos, numrep); + dprintk("CHOOSE%s bucket %d x %d outpos %d numrep %d tries %d recurse_tries %d local_retries %d local_fallback_retries %d parent_r %d\n", + recurse_to_leaf ? "_LEAF" : "", + bucket->id, x, outpos, numrep, + tries, recurse_tries, local_retries, local_fallback_retries, + parent_r); for (rep = outpos; rep < numrep; rep++) { /* keep trying until we get a non-out, non-colliding item */ @@ -335,7 +342,7 @@ static int crush_choose_firstn(const struct crush_map *map, do { collide = 0; retry_bucket = 0; - r = rep; + r = rep + parent_r; /* r' = r + f_total */ r += ftotal; @@ -344,9 +351,9 @@ static int crush_choose_firstn(const struct crush_map *map, reject = 1; goto reject; } - if (local_fallback_tries > 0 && + if (local_fallback_retries > 0 && flocal >= (in->size>>1) && - flocal > local_fallback_tries) + flocal > local_fallback_retries) item = bucket_perm_choose(in, x, r); else item = crush_bucket_choose(in, x, r); @@ -387,16 +394,23 @@ static int crush_choose_firstn(const struct crush_map *map, reject = 0; if (!collide && recurse_to_leaf) { if (item < 0) { + int sub_r; + if (vary_r) + sub_r = r >> (vary_r-1); + else + sub_r = 0; if (crush_choose_firstn(map, map->buckets[-1-item], weight, weight_max, x, outpos+1, 0, out2, outpos, recurse_tries, 0, - local_tries, - local_fallback_tries, + local_retries, + local_fallback_retries, 0, - NULL) <= outpos) + vary_r, + NULL, + sub_r) <= outpos) /* didn't get leaf */ reject = 1; } else { @@ -420,14 +434,14 @@ reject: ftotal++; flocal++; - if (collide && flocal <= local_tries) + if (collide && flocal <= local_retries) /* retry locally a few times */ retry_bucket = 1; - else if (local_fallback_tries > 0 && - flocal <= in->size + local_fallback_tries) + else if (local_fallback_retries > 0 && + flocal <= in->size + local_fallback_retries) /* exhaustive bucket search */ retry_bucket = 1; - else if (ftotal <= tries) + else if (ftotal < tries) /* then retry descent */ retry_descent = 1; else @@ -640,10 +654,20 @@ int crush_do_rule(const struct crush_map *map, __u32 step; int i, j; int numrep; - int choose_tries = map->choose_total_tries; - int choose_local_tries = map->choose_local_tries; - int choose_local_fallback_tries = map->choose_local_fallback_tries; + /* + * the original choose_total_tries value was off by one (it + * counted "retries" and not "tries"). add one. + */ + int choose_tries = map->choose_total_tries + 1; int choose_leaf_tries = 0; + /* + * the local tries values were counted as "retries", though, + * and need no adjustment + */ + int choose_local_retries = map->choose_local_tries; + int choose_local_fallback_retries = map->choose_local_fallback_tries; + + int vary_r = map->chooseleaf_vary_r; if ((__u32)ruleno >= map->max_rules) { dprintk(" bad ruleno %d\n", ruleno); @@ -676,13 +700,18 @@ int crush_do_rule(const struct crush_map *map, break; case CRUSH_RULE_SET_CHOOSE_LOCAL_TRIES: - if (curstep->arg1 > 0) - choose_local_tries = curstep->arg1; + if (curstep->arg1 >= 0) + choose_local_retries = curstep->arg1; break; case CRUSH_RULE_SET_CHOOSE_LOCAL_FALLBACK_TRIES: - if (curstep->arg1 > 0) - choose_local_fallback_tries = curstep->arg1; + if (curstep->arg1 >= 0) + choose_local_fallback_retries = curstep->arg1; + break; + + case CRUSH_RULE_SET_CHOOSELEAF_VARY_R: + if (curstep->arg1 >= 0) + vary_r = curstep->arg1; break; case CRUSH_RULE_CHOOSELEAF_FIRSTN: @@ -734,10 +763,12 @@ int crush_do_rule(const struct crush_map *map, o+osize, j, choose_tries, recurse_tries, - choose_local_tries, - choose_local_fallback_tries, + choose_local_retries, + choose_local_fallback_retries, recurse_to_leaf, - c+osize); + vary_r, + c+osize, + 0); } else { crush_choose_indep( map, diff --git a/net/ceph/debugfs.c b/net/ceph/debugfs.c index 258a382..10421a4 100644 --- a/net/ceph/debugfs.c +++ b/net/ceph/debugfs.c @@ -53,34 +53,55 @@ static int osdmap_show(struct seq_file *s, void *p) { int i; struct ceph_client *client = s->private; + struct ceph_osdmap *map = client->osdc.osdmap; struct rb_node *n; - if (client->osdc.osdmap == NULL) + if (map == NULL) return 0; - seq_printf(s, "epoch %d\n", client->osdc.osdmap->epoch); + + seq_printf(s, "epoch %d\n", map->epoch); seq_printf(s, "flags%s%s\n", - (client->osdc.osdmap->flags & CEPH_OSDMAP_NEARFULL) ? - " NEARFULL" : "", - (client->osdc.osdmap->flags & CEPH_OSDMAP_FULL) ? - " FULL" : ""); - for (n = rb_first(&client->osdc.osdmap->pg_pools); n; n = rb_next(n)) { + (map->flags & CEPH_OSDMAP_NEARFULL) ? " NEARFULL" : "", + (map->flags & CEPH_OSDMAP_FULL) ? " FULL" : ""); + + for (n = rb_first(&map->pg_pools); n; n = rb_next(n)) { struct ceph_pg_pool_info *pool = rb_entry(n, struct ceph_pg_pool_info, node); - seq_printf(s, "pg_pool %llu pg_num %d / %d\n", - (unsigned long long)pool->id, pool->pg_num, - pool->pg_num_mask); + + seq_printf(s, "pool %lld pg_num %u (%d) read_tier %lld write_tier %lld\n", + pool->id, pool->pg_num, pool->pg_num_mask, + pool->read_tier, pool->write_tier); } - for (i = 0; i < client->osdc.osdmap->max_osd; i++) { - struct ceph_entity_addr *addr = - &client->osdc.osdmap->osd_addr[i]; - int state = client->osdc.osdmap->osd_state[i]; + for (i = 0; i < map->max_osd; i++) { + struct ceph_entity_addr *addr = &map->osd_addr[i]; + int state = map->osd_state[i]; char sb[64]; - seq_printf(s, "\tosd%d\t%s\t%3d%%\t(%s)\n", + seq_printf(s, "osd%d\t%s\t%3d%%\t(%s)\t%3d%%\n", i, ceph_pr_addr(&addr->in_addr), - ((client->osdc.osdmap->osd_weight[i]*100) >> 16), - ceph_osdmap_state_str(sb, sizeof(sb), state)); + ((map->osd_weight[i]*100) >> 16), + ceph_osdmap_state_str(sb, sizeof(sb), state), + ((ceph_get_primary_affinity(map, i)*100) >> 16)); + } + for (n = rb_first(&map->pg_temp); n; n = rb_next(n)) { + struct ceph_pg_mapping *pg = + rb_entry(n, struct ceph_pg_mapping, node); + + seq_printf(s, "pg_temp %llu.%x [", pg->pgid.pool, + pg->pgid.seed); + for (i = 0; i < pg->pg_temp.len; i++) + seq_printf(s, "%s%d", (i == 0 ? "" : ","), + pg->pg_temp.osds[i]); + seq_printf(s, "]\n"); } + for (n = rb_first(&map->primary_temp); n; n = rb_next(n)) { + struct ceph_pg_mapping *pg = + rb_entry(n, struct ceph_pg_mapping, node); + + seq_printf(s, "primary_temp %llu.%x %d\n", pg->pgid.pool, + pg->pgid.seed, pg->primary_temp.osd); + } + return 0; } diff --git a/net/ceph/messenger.c b/net/ceph/messenger.c index 30efc5c..dac7f9b 100644 --- a/net/ceph/messenger.c +++ b/net/ceph/messenger.c @@ -383,7 +383,7 @@ static void con_sock_state_closed(struct ceph_connection *con) */ /* data available on socket, or listen socket received a connect */ -static void ceph_sock_data_ready(struct sock *sk, int count_unused) +static void ceph_sock_data_ready(struct sock *sk) { struct ceph_connection *con = sk->sk_user_data; if (atomic_read(&con->msgr->stopping)) { @@ -919,6 +919,9 @@ static bool ceph_msg_data_pages_advance(struct ceph_msg_data_cursor *cursor, if (!bytes || cursor->page_offset) return false; /* more bytes to process in the current page */ + if (!cursor->resid) + return false; /* no more data */ + /* Move on to the next page; offset is already at 0 */ BUG_ON(cursor->page_index >= cursor->page_count); @@ -1004,6 +1007,9 @@ static bool ceph_msg_data_pagelist_advance(struct ceph_msg_data_cursor *cursor, if (!bytes || cursor->offset & ~PAGE_MASK) return false; /* more bytes to process in the current page */ + if (!cursor->resid) + return false; /* no more data */ + /* Move on to the next page */ BUG_ON(list_is_last(&cursor->page->lru, &pagelist->head)); diff --git a/net/ceph/osd_client.c b/net/ceph/osd_client.c index 82750f9..b0dfce7 100644 --- a/net/ceph/osd_client.c +++ b/net/ceph/osd_client.c @@ -436,6 +436,7 @@ static bool osd_req_opcode_valid(u16 opcode) case CEPH_OSD_OP_OMAPCLEAR: case CEPH_OSD_OP_OMAPRMKEYS: case CEPH_OSD_OP_OMAP_CMP: + case CEPH_OSD_OP_SETALLOCHINT: case CEPH_OSD_OP_CLONERANGE: case CEPH_OSD_OP_ASSERT_SRC_VERSION: case CEPH_OSD_OP_SRC_CMPXATTR: @@ -591,6 +592,26 @@ void osd_req_op_watch_init(struct ceph_osd_request *osd_req, } EXPORT_SYMBOL(osd_req_op_watch_init); +void osd_req_op_alloc_hint_init(struct ceph_osd_request *osd_req, + unsigned int which, + u64 expected_object_size, + u64 expected_write_size) +{ + struct ceph_osd_req_op *op = _osd_req_op_init(osd_req, which, + CEPH_OSD_OP_SETALLOCHINT); + + op->alloc_hint.expected_object_size = expected_object_size; + op->alloc_hint.expected_write_size = expected_write_size; + + /* + * CEPH_OSD_OP_SETALLOCHINT op is advisory and therefore deemed + * not worth a feature bit. Set FAILOK per-op flag to make + * sure older osds don't trip over an unsupported opcode. + */ + op->flags |= CEPH_OSD_OP_FLAG_FAILOK; +} +EXPORT_SYMBOL(osd_req_op_alloc_hint_init); + static void ceph_osdc_msg_data_add(struct ceph_msg *msg, struct ceph_osd_data *osd_data) { @@ -681,6 +702,12 @@ static u64 osd_req_encode_op(struct ceph_osd_request *req, dst->watch.ver = cpu_to_le64(src->watch.ver); dst->watch.flag = src->watch.flag; break; + case CEPH_OSD_OP_SETALLOCHINT: + dst->alloc_hint.expected_object_size = + cpu_to_le64(src->alloc_hint.expected_object_size); + dst->alloc_hint.expected_write_size = + cpu_to_le64(src->alloc_hint.expected_write_size); + break; default: pr_err("unsupported osd opcode %s\n", ceph_osd_op_name(src->op)); @@ -688,7 +715,9 @@ static u64 osd_req_encode_op(struct ceph_osd_request *req, return 0; } + dst->op = cpu_to_le16(src->op); + dst->flags = cpu_to_le32(src->flags); dst->payload_len = cpu_to_le32(src->payload_len); return request_data_len; @@ -1304,7 +1333,7 @@ static int __map_request(struct ceph_osd_client *osdc, { struct ceph_pg pgid; int acting[CEPH_PG_MAX_SIZE]; - int o = -1, num = 0; + int num, o; int err; bool was_paused; @@ -1317,11 +1346,9 @@ static int __map_request(struct ceph_osd_client *osdc, } req->r_pgid = pgid; - err = ceph_calc_pg_acting(osdc->osdmap, pgid, acting); - if (err > 0) { - o = acting[0]; - num = err; - } + num = ceph_calc_pg_acting(osdc->osdmap, pgid, acting, &o); + if (num < 0) + num = 0; was_paused = req->r_paused; req->r_paused = __req_should_be_paused(osdc, req); @@ -2033,7 +2060,7 @@ void ceph_osdc_handle_map(struct ceph_osd_client *osdc, struct ceph_msg *msg) int skipped_map = 0; dout("taking full map %u len %d\n", epoch, maplen); - newmap = osdmap_decode(&p, p+maplen); + newmap = ceph_osdmap_decode(&p, p+maplen); if (IS_ERR(newmap)) { err = PTR_ERR(newmap); goto bad; diff --git a/net/ceph/osdmap.c b/net/ceph/osdmap.c index aade4a5..8b8a5a2 100644 --- a/net/ceph/osdmap.c +++ b/net/ceph/osdmap.c @@ -343,7 +343,7 @@ bad: /* * rbtree of pg_mapping for handling pg_temp (explicit mapping of pgid - * to a set of osds) + * to a set of osds) and primary_temp (explicit primary setting) */ static int pgid_cmp(struct ceph_pg l, struct ceph_pg r) { @@ -506,7 +506,7 @@ static void __remove_pg_pool(struct rb_root *root, struct ceph_pg_pool_info *pi) kfree(pi); } -static int __decode_pool(void **p, void *end, struct ceph_pg_pool_info *pi) +static int decode_pool(void **p, void *end, struct ceph_pg_pool_info *pi) { u8 ev, cv; unsigned len, num; @@ -587,7 +587,7 @@ bad: return -EINVAL; } -static int __decode_pool_names(void **p, void *end, struct ceph_osdmap *map) +static int decode_pool_names(void **p, void *end, struct ceph_osdmap *map) { struct ceph_pg_pool_info *pi; u32 num, len; @@ -633,6 +633,13 @@ void ceph_osdmap_destroy(struct ceph_osdmap *map) rb_erase(&pg->node, &map->pg_temp); kfree(pg); } + while (!RB_EMPTY_ROOT(&map->primary_temp)) { + struct ceph_pg_mapping *pg = + rb_entry(rb_first(&map->primary_temp), + struct ceph_pg_mapping, node); + rb_erase(&pg->node, &map->primary_temp); + kfree(pg); + } while (!RB_EMPTY_ROOT(&map->pg_pools)) { struct ceph_pg_pool_info *pi = rb_entry(rb_first(&map->pg_pools), @@ -642,186 +649,516 @@ void ceph_osdmap_destroy(struct ceph_osdmap *map) kfree(map->osd_state); kfree(map->osd_weight); kfree(map->osd_addr); + kfree(map->osd_primary_affinity); kfree(map); } /* - * adjust max osd value. reallocate arrays. + * Adjust max_osd value, (re)allocate arrays. + * + * The new elements are properly initialized. */ static int osdmap_set_max_osd(struct ceph_osdmap *map, int max) { u8 *state; - struct ceph_entity_addr *addr; u32 *weight; + struct ceph_entity_addr *addr; + int i; - state = kcalloc(max, sizeof(*state), GFP_NOFS); - addr = kcalloc(max, sizeof(*addr), GFP_NOFS); - weight = kcalloc(max, sizeof(*weight), GFP_NOFS); - if (state == NULL || addr == NULL || weight == NULL) { + state = krealloc(map->osd_state, max*sizeof(*state), GFP_NOFS); + weight = krealloc(map->osd_weight, max*sizeof(*weight), GFP_NOFS); + addr = krealloc(map->osd_addr, max*sizeof(*addr), GFP_NOFS); + if (!state || !weight || !addr) { kfree(state); - kfree(addr); kfree(weight); + kfree(addr); + return -ENOMEM; } - /* copy old? */ - if (map->osd_state) { - memcpy(state, map->osd_state, map->max_osd*sizeof(*state)); - memcpy(addr, map->osd_addr, map->max_osd*sizeof(*addr)); - memcpy(weight, map->osd_weight, map->max_osd*sizeof(*weight)); - kfree(map->osd_state); - kfree(map->osd_addr); - kfree(map->osd_weight); + for (i = map->max_osd; i < max; i++) { + state[i] = 0; + weight[i] = CEPH_OSD_OUT; + memset(addr + i, 0, sizeof(*addr)); } map->osd_state = state; map->osd_weight = weight; map->osd_addr = addr; + + if (map->osd_primary_affinity) { + u32 *affinity; + + affinity = krealloc(map->osd_primary_affinity, + max*sizeof(*affinity), GFP_NOFS); + if (!affinity) + return -ENOMEM; + + for (i = map->max_osd; i < max; i++) + affinity[i] = CEPH_OSD_DEFAULT_PRIMARY_AFFINITY; + + map->osd_primary_affinity = affinity; + } + map->max_osd = max; + return 0; } +#define OSDMAP_WRAPPER_COMPAT_VER 7 +#define OSDMAP_CLIENT_DATA_COMPAT_VER 1 + /* - * decode a full map. + * Return 0 or error. On success, *v is set to 0 for old (v6) osdmaps, + * to struct_v of the client_data section for new (v7 and above) + * osdmaps. */ -struct ceph_osdmap *osdmap_decode(void **p, void *end) +static int get_osdmap_client_data_v(void **p, void *end, + const char *prefix, u8 *v) { - struct ceph_osdmap *map; - u16 version; - u32 len, max, i; - int err = -EINVAL; - void *start = *p; - struct ceph_pg_pool_info *pi; + u8 struct_v; + + ceph_decode_8_safe(p, end, struct_v, e_inval); + if (struct_v >= 7) { + u8 struct_compat; + + ceph_decode_8_safe(p, end, struct_compat, e_inval); + if (struct_compat > OSDMAP_WRAPPER_COMPAT_VER) { + pr_warning("got v %d cv %d > %d of %s ceph_osdmap\n", + struct_v, struct_compat, + OSDMAP_WRAPPER_COMPAT_VER, prefix); + return -EINVAL; + } + *p += 4; /* ignore wrapper struct_len */ + + ceph_decode_8_safe(p, end, struct_v, e_inval); + ceph_decode_8_safe(p, end, struct_compat, e_inval); + if (struct_compat > OSDMAP_CLIENT_DATA_COMPAT_VER) { + pr_warning("got v %d cv %d > %d of %s ceph_osdmap client data\n", + struct_v, struct_compat, + OSDMAP_CLIENT_DATA_COMPAT_VER, prefix); + return -EINVAL; + } + *p += 4; /* ignore client data struct_len */ + } else { + u16 version; + + *p -= 1; + ceph_decode_16_safe(p, end, version, e_inval); + if (version < 6) { + pr_warning("got v %d < 6 of %s ceph_osdmap\n", version, + prefix); + return -EINVAL; + } - dout("osdmap_decode %p to %p len %d\n", *p, end, (int)(end - *p)); + /* old osdmap enconding */ + struct_v = 0; + } - map = kzalloc(sizeof(*map), GFP_NOFS); - if (map == NULL) - return ERR_PTR(-ENOMEM); - map->pg_temp = RB_ROOT; + *v = struct_v; + return 0; - ceph_decode_16_safe(p, end, version, bad); - if (version > 6) { - pr_warning("got unknown v %d > 6 of osdmap\n", version); - goto bad; +e_inval: + return -EINVAL; +} + +static int __decode_pools(void **p, void *end, struct ceph_osdmap *map, + bool incremental) +{ + u32 n; + + ceph_decode_32_safe(p, end, n, e_inval); + while (n--) { + struct ceph_pg_pool_info *pi; + u64 pool; + int ret; + + ceph_decode_64_safe(p, end, pool, e_inval); + + pi = __lookup_pg_pool(&map->pg_pools, pool); + if (!incremental || !pi) { + pi = kzalloc(sizeof(*pi), GFP_NOFS); + if (!pi) + return -ENOMEM; + + pi->id = pool; + + ret = __insert_pg_pool(&map->pg_pools, pi); + if (ret) { + kfree(pi); + return ret; + } + } + + ret = decode_pool(p, end, pi); + if (ret) + return ret; } - if (version < 6) { - pr_warning("got old v %d < 6 of osdmap\n", version); - goto bad; + + return 0; + +e_inval: + return -EINVAL; +} + +static int decode_pools(void **p, void *end, struct ceph_osdmap *map) +{ + return __decode_pools(p, end, map, false); +} + +static int decode_new_pools(void **p, void *end, struct ceph_osdmap *map) +{ + return __decode_pools(p, end, map, true); +} + +static int __decode_pg_temp(void **p, void *end, struct ceph_osdmap *map, + bool incremental) +{ + u32 n; + + ceph_decode_32_safe(p, end, n, e_inval); + while (n--) { + struct ceph_pg pgid; + u32 len, i; + int ret; + + ret = ceph_decode_pgid(p, end, &pgid); + if (ret) + return ret; + + ceph_decode_32_safe(p, end, len, e_inval); + + ret = __remove_pg_mapping(&map->pg_temp, pgid); + BUG_ON(!incremental && ret != -ENOENT); + + if (!incremental || len > 0) { + struct ceph_pg_mapping *pg; + + ceph_decode_need(p, end, len*sizeof(u32), e_inval); + + if (len > (UINT_MAX - sizeof(*pg)) / sizeof(u32)) + return -EINVAL; + + pg = kzalloc(sizeof(*pg) + len*sizeof(u32), GFP_NOFS); + if (!pg) + return -ENOMEM; + + pg->pgid = pgid; + pg->pg_temp.len = len; + for (i = 0; i < len; i++) + pg->pg_temp.osds[i] = ceph_decode_32(p); + + ret = __insert_pg_mapping(pg, &map->pg_temp); + if (ret) { + kfree(pg); + return ret; + } + } } - ceph_decode_need(p, end, 2*sizeof(u64)+6*sizeof(u32), bad); + return 0; + +e_inval: + return -EINVAL; +} + +static int decode_pg_temp(void **p, void *end, struct ceph_osdmap *map) +{ + return __decode_pg_temp(p, end, map, false); +} + +static int decode_new_pg_temp(void **p, void *end, struct ceph_osdmap *map) +{ + return __decode_pg_temp(p, end, map, true); +} + +static int __decode_primary_temp(void **p, void *end, struct ceph_osdmap *map, + bool incremental) +{ + u32 n; + + ceph_decode_32_safe(p, end, n, e_inval); + while (n--) { + struct ceph_pg pgid; + u32 osd; + int ret; + + ret = ceph_decode_pgid(p, end, &pgid); + if (ret) + return ret; + + ceph_decode_32_safe(p, end, osd, e_inval); + + ret = __remove_pg_mapping(&map->primary_temp, pgid); + BUG_ON(!incremental && ret != -ENOENT); + + if (!incremental || osd != (u32)-1) { + struct ceph_pg_mapping *pg; + + pg = kzalloc(sizeof(*pg), GFP_NOFS); + if (!pg) + return -ENOMEM; + + pg->pgid = pgid; + pg->primary_temp.osd = osd; + + ret = __insert_pg_mapping(pg, &map->primary_temp); + if (ret) { + kfree(pg); + return ret; + } + } + } + + return 0; + +e_inval: + return -EINVAL; +} + +static int decode_primary_temp(void **p, void *end, struct ceph_osdmap *map) +{ + return __decode_primary_temp(p, end, map, false); +} + +static int decode_new_primary_temp(void **p, void *end, + struct ceph_osdmap *map) +{ + return __decode_primary_temp(p, end, map, true); +} + +u32 ceph_get_primary_affinity(struct ceph_osdmap *map, int osd) +{ + BUG_ON(osd >= map->max_osd); + + if (!map->osd_primary_affinity) + return CEPH_OSD_DEFAULT_PRIMARY_AFFINITY; + + return map->osd_primary_affinity[osd]; +} + +static int set_primary_affinity(struct ceph_osdmap *map, int osd, u32 aff) +{ + BUG_ON(osd >= map->max_osd); + + if (!map->osd_primary_affinity) { + int i; + + map->osd_primary_affinity = kmalloc(map->max_osd*sizeof(u32), + GFP_NOFS); + if (!map->osd_primary_affinity) + return -ENOMEM; + + for (i = 0; i < map->max_osd; i++) + map->osd_primary_affinity[i] = + CEPH_OSD_DEFAULT_PRIMARY_AFFINITY; + } + + map->osd_primary_affinity[osd] = aff; + + return 0; +} + +static int decode_primary_affinity(void **p, void *end, + struct ceph_osdmap *map) +{ + u32 len, i; + + ceph_decode_32_safe(p, end, len, e_inval); + if (len == 0) { + kfree(map->osd_primary_affinity); + map->osd_primary_affinity = NULL; + return 0; + } + if (len != map->max_osd) + goto e_inval; + + ceph_decode_need(p, end, map->max_osd*sizeof(u32), e_inval); + + for (i = 0; i < map->max_osd; i++) { + int ret; + + ret = set_primary_affinity(map, i, ceph_decode_32(p)); + if (ret) + return ret; + } + + return 0; + +e_inval: + return -EINVAL; +} + +static int decode_new_primary_affinity(void **p, void *end, + struct ceph_osdmap *map) +{ + u32 n; + + ceph_decode_32_safe(p, end, n, e_inval); + while (n--) { + u32 osd, aff; + int ret; + + ceph_decode_32_safe(p, end, osd, e_inval); + ceph_decode_32_safe(p, end, aff, e_inval); + + ret = set_primary_affinity(map, osd, aff); + if (ret) + return ret; + + pr_info("osd%d primary-affinity 0x%x\n", osd, aff); + } + + return 0; + +e_inval: + return -EINVAL; +} + +/* + * decode a full map. + */ +static int osdmap_decode(void **p, void *end, struct ceph_osdmap *map) +{ + u8 struct_v; + u32 epoch = 0; + void *start = *p; + u32 max; + u32 len, i; + int err; + + dout("%s %p to %p len %d\n", __func__, *p, end, (int)(end - *p)); + + err = get_osdmap_client_data_v(p, end, "full", &struct_v); + if (err) + goto bad; + + /* fsid, epoch, created, modified */ + ceph_decode_need(p, end, sizeof(map->fsid) + sizeof(u32) + + sizeof(map->created) + sizeof(map->modified), e_inval); ceph_decode_copy(p, &map->fsid, sizeof(map->fsid)); - map->epoch = ceph_decode_32(p); + epoch = map->epoch = ceph_decode_32(p); ceph_decode_copy(p, &map->created, sizeof(map->created)); ceph_decode_copy(p, &map->modified, sizeof(map->modified)); - ceph_decode_32_safe(p, end, max, bad); - while (max--) { - ceph_decode_need(p, end, 8 + 2, bad); - err = -ENOMEM; - pi = kzalloc(sizeof(*pi), GFP_NOFS); - if (!pi) - goto bad; - pi->id = ceph_decode_64(p); - err = __decode_pool(p, end, pi); - if (err < 0) { - kfree(pi); - goto bad; - } - __insert_pg_pool(&map->pg_pools, pi); - } + /* pools */ + err = decode_pools(p, end, map); + if (err) + goto bad; - err = __decode_pool_names(p, end, map); - if (err < 0) { - dout("fail to decode pool names"); + /* pool_name */ + err = decode_pool_names(p, end, map); + if (err) goto bad; - } - ceph_decode_32_safe(p, end, map->pool_max, bad); + ceph_decode_32_safe(p, end, map->pool_max, e_inval); - ceph_decode_32_safe(p, end, map->flags, bad); + ceph_decode_32_safe(p, end, map->flags, e_inval); - max = ceph_decode_32(p); + /* max_osd */ + ceph_decode_32_safe(p, end, max, e_inval); /* (re)alloc osd arrays */ err = osdmap_set_max_osd(map, max); - if (err < 0) + if (err) goto bad; - dout("osdmap_decode max_osd = %d\n", map->max_osd); - /* osds */ - err = -EINVAL; + /* osd_state, osd_weight, osd_addrs->client_addr */ ceph_decode_need(p, end, 3*sizeof(u32) + map->max_osd*(1 + sizeof(*map->osd_weight) + - sizeof(*map->osd_addr)), bad); - *p += 4; /* skip length field (should match max) */ + sizeof(*map->osd_addr)), e_inval); + + if (ceph_decode_32(p) != map->max_osd) + goto e_inval; + ceph_decode_copy(p, map->osd_state, map->max_osd); - *p += 4; /* skip length field (should match max) */ + if (ceph_decode_32(p) != map->max_osd) + goto e_inval; + for (i = 0; i < map->max_osd; i++) map->osd_weight[i] = ceph_decode_32(p); - *p += 4; /* skip length field (should match max) */ + if (ceph_decode_32(p) != map->max_osd) + goto e_inval; + ceph_decode_copy(p, map->osd_addr, map->max_osd*sizeof(*map->osd_addr)); for (i = 0; i < map->max_osd; i++) ceph_decode_addr(&map->osd_addr[i]); /* pg_temp */ - ceph_decode_32_safe(p, end, len, bad); - for (i = 0; i < len; i++) { - int n, j; - struct ceph_pg pgid; - struct ceph_pg_mapping *pg; + err = decode_pg_temp(p, end, map); + if (err) + goto bad; - err = ceph_decode_pgid(p, end, &pgid); + /* primary_temp */ + if (struct_v >= 1) { + err = decode_primary_temp(p, end, map); if (err) goto bad; - ceph_decode_need(p, end, sizeof(u32), bad); - n = ceph_decode_32(p); - err = -EINVAL; - if (n > (UINT_MAX - sizeof(*pg)) / sizeof(u32)) - goto bad; - ceph_decode_need(p, end, n * sizeof(u32), bad); - err = -ENOMEM; - pg = kmalloc(sizeof(*pg) + n*sizeof(u32), GFP_NOFS); - if (!pg) - goto bad; - pg->pgid = pgid; - pg->len = n; - for (j = 0; j < n; j++) - pg->osds[j] = ceph_decode_32(p); + } - err = __insert_pg_mapping(pg, &map->pg_temp); + /* primary_affinity */ + if (struct_v >= 2) { + err = decode_primary_affinity(p, end, map); if (err) goto bad; - dout(" added pg_temp %lld.%x len %d\n", pgid.pool, pgid.seed, - len); + } else { + /* XXX can this happen? */ + kfree(map->osd_primary_affinity); + map->osd_primary_affinity = NULL; } /* crush */ - ceph_decode_32_safe(p, end, len, bad); - dout("osdmap_decode crush len %d from off 0x%x\n", len, - (int)(*p - start)); - ceph_decode_need(p, end, len, bad); - map->crush = crush_decode(*p, end); - *p += len; + ceph_decode_32_safe(p, end, len, e_inval); + map->crush = crush_decode(*p, min(*p + len, end)); if (IS_ERR(map->crush)) { err = PTR_ERR(map->crush); map->crush = NULL; goto bad; } + *p += len; - /* ignore the rest of the map */ + /* ignore the rest */ *p = end; - dout("osdmap_decode done %p %p\n", *p, end); - return map; + dout("full osdmap epoch %d max_osd %d\n", map->epoch, map->max_osd); + return 0; +e_inval: + err = -EINVAL; bad: - dout("osdmap_decode fail err %d\n", err); - ceph_osdmap_destroy(map); - return ERR_PTR(err); + pr_err("corrupt full osdmap (%d) epoch %d off %d (%p of %p-%p)\n", + err, epoch, (int)(*p - start), *p, start, end); + print_hex_dump(KERN_DEBUG, "osdmap: ", + DUMP_PREFIX_OFFSET, 16, 1, + start, end - start, true); + return err; +} + +/* + * Allocate and decode a full map. + */ +struct ceph_osdmap *ceph_osdmap_decode(void **p, void *end) +{ + struct ceph_osdmap *map; + int ret; + + map = kzalloc(sizeof(*map), GFP_NOFS); + if (!map) + return ERR_PTR(-ENOMEM); + + map->pg_temp = RB_ROOT; + map->primary_temp = RB_ROOT; + mutex_init(&map->crush_scratch_mutex); + + ret = osdmap_decode(p, end, map); + if (ret) { + ceph_osdmap_destroy(map); + return ERR_PTR(ret); + } + + return map; } /* @@ -840,17 +1177,18 @@ struct ceph_osdmap *osdmap_apply_incremental(void **p, void *end, __s64 new_pool_max; __s32 new_flags, max; void *start = *p; - int err = -EINVAL; - u16 version; + int err; + u8 struct_v; + + dout("%s %p to %p len %d\n", __func__, *p, end, (int)(end - *p)); - ceph_decode_16_safe(p, end, version, bad); - if (version != 6) { - pr_warning("got unknown v %d != 6 of inc osdmap\n", version); + err = get_osdmap_client_data_v(p, end, "inc", &struct_v); + if (err) goto bad; - } - ceph_decode_need(p, end, sizeof(fsid)+sizeof(modified)+2*sizeof(u32), - bad); + /* fsid, epoch, modified, new_pool_max, new_flags */ + ceph_decode_need(p, end, sizeof(fsid) + sizeof(u32) + sizeof(modified) + + sizeof(u64) + sizeof(u32), e_inval); ceph_decode_copy(p, &fsid, sizeof(fsid)); epoch = ceph_decode_32(p); BUG_ON(epoch != map->epoch+1); @@ -859,21 +1197,22 @@ struct ceph_osdmap *osdmap_apply_incremental(void **p, void *end, new_flags = ceph_decode_32(p); /* full map? */ - ceph_decode_32_safe(p, end, len, bad); + ceph_decode_32_safe(p, end, len, e_inval); if (len > 0) { dout("apply_incremental full map len %d, %p to %p\n", len, *p, end); - return osdmap_decode(p, min(*p+len, end)); + return ceph_osdmap_decode(p, min(*p+len, end)); } /* new crush? */ - ceph_decode_32_safe(p, end, len, bad); + ceph_decode_32_safe(p, end, len, e_inval); if (len > 0) { - dout("apply_incremental new crush map len %d, %p to %p\n", - len, *p, end); newcrush = crush_decode(*p, min(*p+len, end)); - if (IS_ERR(newcrush)) - return ERR_CAST(newcrush); + if (IS_ERR(newcrush)) { + err = PTR_ERR(newcrush); + newcrush = NULL; + goto bad; + } *p += len; } @@ -883,13 +1222,11 @@ struct ceph_osdmap *osdmap_apply_incremental(void **p, void *end, if (new_pool_max >= 0) map->pool_max = new_pool_max; - ceph_decode_need(p, end, 5*sizeof(u32), bad); - /* new max? */ - max = ceph_decode_32(p); + ceph_decode_32_safe(p, end, max, e_inval); if (max >= 0) { err = osdmap_set_max_osd(map, max); - if (err < 0) + if (err) goto bad; } @@ -902,51 +1239,34 @@ struct ceph_osdmap *osdmap_apply_incremental(void **p, void *end, newcrush = NULL; } - /* new_pool */ - ceph_decode_32_safe(p, end, len, bad); - while (len--) { - struct ceph_pg_pool_info *pi; + /* new_pools */ + err = decode_new_pools(p, end, map); + if (err) + goto bad; - ceph_decode_64_safe(p, end, pool, bad); - pi = __lookup_pg_pool(&map->pg_pools, pool); - if (!pi) { - pi = kzalloc(sizeof(*pi), GFP_NOFS); - if (!pi) { - err = -ENOMEM; - goto bad; - } - pi->id = pool; - __insert_pg_pool(&map->pg_pools, pi); - } - err = __decode_pool(p, end, pi); - if (err < 0) - goto bad; - } - if (version >= 5) { - err = __decode_pool_names(p, end, map); - if (err < 0) - goto bad; - } + /* new_pool_names */ + err = decode_pool_names(p, end, map); + if (err) + goto bad; /* old_pool */ - ceph_decode_32_safe(p, end, len, bad); + ceph_decode_32_safe(p, end, len, e_inval); while (len--) { struct ceph_pg_pool_info *pi; - ceph_decode_64_safe(p, end, pool, bad); + ceph_decode_64_safe(p, end, pool, e_inval); pi = __lookup_pg_pool(&map->pg_pools, pool); if (pi) __remove_pg_pool(&map->pg_pools, pi); } /* new_up */ - err = -EINVAL; - ceph_decode_32_safe(p, end, len, bad); + ceph_decode_32_safe(p, end, len, e_inval); while (len--) { u32 osd; struct ceph_entity_addr addr; - ceph_decode_32_safe(p, end, osd, bad); - ceph_decode_copy_safe(p, end, &addr, sizeof(addr), bad); + ceph_decode_32_safe(p, end, osd, e_inval); + ceph_decode_copy_safe(p, end, &addr, sizeof(addr), e_inval); ceph_decode_addr(&addr); pr_info("osd%d up\n", osd); BUG_ON(osd >= map->max_osd); @@ -955,11 +1275,11 @@ struct ceph_osdmap *osdmap_apply_incremental(void **p, void *end, } /* new_state */ - ceph_decode_32_safe(p, end, len, bad); + ceph_decode_32_safe(p, end, len, e_inval); while (len--) { u32 osd; u8 xorstate; - ceph_decode_32_safe(p, end, osd, bad); + ceph_decode_32_safe(p, end, osd, e_inval); xorstate = **(u8 **)p; (*p)++; /* clean flag */ if (xorstate == 0) @@ -971,10 +1291,10 @@ struct ceph_osdmap *osdmap_apply_incremental(void **p, void *end, } /* new_weight */ - ceph_decode_32_safe(p, end, len, bad); + ceph_decode_32_safe(p, end, len, e_inval); while (len--) { u32 osd, off; - ceph_decode_need(p, end, sizeof(u32)*2, bad); + ceph_decode_need(p, end, sizeof(u32)*2, e_inval); osd = ceph_decode_32(p); off = ceph_decode_32(p); pr_info("osd%d weight 0x%x %s\n", osd, off, @@ -985,56 +1305,35 @@ struct ceph_osdmap *osdmap_apply_incremental(void **p, void *end, } /* new_pg_temp */ - ceph_decode_32_safe(p, end, len, bad); - while (len--) { - struct ceph_pg_mapping *pg; - int j; - struct ceph_pg pgid; - u32 pglen; + err = decode_new_pg_temp(p, end, map); + if (err) + goto bad; - err = ceph_decode_pgid(p, end, &pgid); + /* new_primary_temp */ + if (struct_v >= 1) { + err = decode_new_primary_temp(p, end, map); if (err) goto bad; - ceph_decode_need(p, end, sizeof(u32), bad); - pglen = ceph_decode_32(p); - if (pglen) { - ceph_decode_need(p, end, pglen*sizeof(u32), bad); - - /* removing existing (if any) */ - (void) __remove_pg_mapping(&map->pg_temp, pgid); + } - /* insert */ - err = -EINVAL; - if (pglen > (UINT_MAX - sizeof(*pg)) / sizeof(u32)) - goto bad; - err = -ENOMEM; - pg = kmalloc(sizeof(*pg) + sizeof(u32)*pglen, GFP_NOFS); - if (!pg) - goto bad; - pg->pgid = pgid; - pg->len = pglen; - for (j = 0; j < pglen; j++) - pg->osds[j] = ceph_decode_32(p); - err = __insert_pg_mapping(pg, &map->pg_temp); - if (err) { - kfree(pg); - goto bad; - } - dout(" added pg_temp %lld.%x len %d\n", pgid.pool, - pgid.seed, pglen); - } else { - /* remove */ - __remove_pg_mapping(&map->pg_temp, pgid); - } + /* new_primary_affinity */ + if (struct_v >= 2) { + err = decode_new_primary_affinity(p, end, map); + if (err) + goto bad; } /* ignore the rest */ *p = end; + + dout("inc osdmap epoch %d max_osd %d\n", map->epoch, map->max_osd); return map; +e_inval: + err = -EINVAL; bad: - pr_err("corrupt inc osdmap epoch %d off %d (%p of %p-%p)\n", - epoch, (int)(*p - start), *p, start, end); + pr_err("corrupt inc osdmap (%d) epoch %d off %d (%p of %p-%p)\n", + err, epoch, (int)(*p - start), *p, start, end); print_hex_dump(KERN_DEBUG, "osdmap: ", DUMP_PREFIX_OFFSET, 16, 1, start, end - start, true); @@ -1142,61 +1441,250 @@ int ceph_oloc_oid_to_pg(struct ceph_osdmap *osdmap, } EXPORT_SYMBOL(ceph_oloc_oid_to_pg); -static int crush_do_rule_ary(const struct crush_map *map, int ruleno, int x, - int *result, int result_max, - const __u32 *weight, int weight_max) +static int do_crush(struct ceph_osdmap *map, int ruleno, int x, + int *result, int result_max, + const __u32 *weight, int weight_max) { - int scratch[result_max * 3]; + int r; + + BUG_ON(result_max > CEPH_PG_MAX_SIZE); - return crush_do_rule(map, ruleno, x, result, result_max, - weight, weight_max, scratch); + mutex_lock(&map->crush_scratch_mutex); + r = crush_do_rule(map->crush, ruleno, x, result, result_max, + weight, weight_max, map->crush_scratch_ary); + mutex_unlock(&map->crush_scratch_mutex); + + return r; } /* - * Calculate raw osd vector for the given pgid. Return pointer to osd - * array, or NULL on failure. + * Calculate raw (crush) set for given pgid. + * + * Return raw set length, or error. */ -static int *calc_pg_raw(struct ceph_osdmap *osdmap, struct ceph_pg pgid, - int *osds, int *num) +static int pg_to_raw_osds(struct ceph_osdmap *osdmap, + struct ceph_pg_pool_info *pool, + struct ceph_pg pgid, u32 pps, int *osds) { - struct ceph_pg_mapping *pg; - struct ceph_pg_pool_info *pool; int ruleno; - int r; - u32 pps; + int len; - pool = __lookup_pg_pool(&osdmap->pg_pools, pgid.pool); - if (!pool) - return NULL; + /* crush */ + ruleno = crush_find_rule(osdmap->crush, pool->crush_ruleset, + pool->type, pool->size); + if (ruleno < 0) { + pr_err("no crush rule: pool %lld ruleset %d type %d size %d\n", + pgid.pool, pool->crush_ruleset, pool->type, + pool->size); + return -ENOENT; + } - /* pg_temp? */ + len = do_crush(osdmap, ruleno, pps, osds, + min_t(int, pool->size, CEPH_PG_MAX_SIZE), + osdmap->osd_weight, osdmap->max_osd); + if (len < 0) { + pr_err("error %d from crush rule %d: pool %lld ruleset %d type %d size %d\n", + len, ruleno, pgid.pool, pool->crush_ruleset, + pool->type, pool->size); + return len; + } + + return len; +} + +/* + * Given raw set, calculate up set and up primary. + * + * Return up set length. *primary is set to up primary osd id, or -1 + * if up set is empty. + */ +static int raw_to_up_osds(struct ceph_osdmap *osdmap, + struct ceph_pg_pool_info *pool, + int *osds, int len, int *primary) +{ + int up_primary = -1; + int i; + + if (ceph_can_shift_osds(pool)) { + int removed = 0; + + for (i = 0; i < len; i++) { + if (ceph_osd_is_down(osdmap, osds[i])) { + removed++; + continue; + } + if (removed) + osds[i - removed] = osds[i]; + } + + len -= removed; + if (len > 0) + up_primary = osds[0]; + } else { + for (i = len - 1; i >= 0; i--) { + if (ceph_osd_is_down(osdmap, osds[i])) + osds[i] = CRUSH_ITEM_NONE; + else + up_primary = osds[i]; + } + } + + *primary = up_primary; + return len; +} + +static void apply_primary_affinity(struct ceph_osdmap *osdmap, u32 pps, + struct ceph_pg_pool_info *pool, + int *osds, int len, int *primary) +{ + int i; + int pos = -1; + + /* + * Do we have any non-default primary_affinity values for these + * osds? + */ + if (!osdmap->osd_primary_affinity) + return; + + for (i = 0; i < len; i++) { + int osd = osds[i]; + + if (osd != CRUSH_ITEM_NONE && + osdmap->osd_primary_affinity[osd] != + CEPH_OSD_DEFAULT_PRIMARY_AFFINITY) { + break; + } + } + if (i == len) + return; + + /* + * Pick the primary. Feed both the seed (for the pg) and the + * osd into the hash/rng so that a proportional fraction of an + * osd's pgs get rejected as primary. + */ + for (i = 0; i < len; i++) { + int osd = osds[i]; + u32 aff; + + if (osd == CRUSH_ITEM_NONE) + continue; + + aff = osdmap->osd_primary_affinity[osd]; + if (aff < CEPH_OSD_MAX_PRIMARY_AFFINITY && + (crush_hash32_2(CRUSH_HASH_RJENKINS1, + pps, osd) >> 16) >= aff) { + /* + * We chose not to use this primary. Note it + * anyway as a fallback in case we don't pick + * anyone else, but keep looking. + */ + if (pos < 0) + pos = i; + } else { + pos = i; + break; + } + } + if (pos < 0) + return; + + *primary = osds[pos]; + + if (ceph_can_shift_osds(pool) && pos > 0) { + /* move the new primary to the front */ + for (i = pos; i > 0; i--) + osds[i] = osds[i - 1]; + osds[0] = *primary; + } +} + +/* + * Given up set, apply pg_temp and primary_temp mappings. + * + * Return acting set length. *primary is set to acting primary osd id, + * or -1 if acting set is empty. + */ +static int apply_temps(struct ceph_osdmap *osdmap, + struct ceph_pg_pool_info *pool, struct ceph_pg pgid, + int *osds, int len, int *primary) +{ + struct ceph_pg_mapping *pg; + int temp_len; + int temp_primary; + int i; + + /* raw_pg -> pg */ pgid.seed = ceph_stable_mod(pgid.seed, pool->pg_num, pool->pg_num_mask); + + /* pg_temp? */ pg = __lookup_pg_mapping(&osdmap->pg_temp, pgid); if (pg) { - *num = pg->len; - return pg->osds; + temp_len = 0; + temp_primary = -1; + + for (i = 0; i < pg->pg_temp.len; i++) { + if (ceph_osd_is_down(osdmap, pg->pg_temp.osds[i])) { + if (ceph_can_shift_osds(pool)) + continue; + else + osds[temp_len++] = CRUSH_ITEM_NONE; + } else { + osds[temp_len++] = pg->pg_temp.osds[i]; + } + } + + /* apply pg_temp's primary */ + for (i = 0; i < temp_len; i++) { + if (osds[i] != CRUSH_ITEM_NONE) { + temp_primary = osds[i]; + break; + } + } + } else { + temp_len = len; + temp_primary = *primary; } - /* crush */ - ruleno = crush_find_rule(osdmap->crush, pool->crush_ruleset, - pool->type, pool->size); - if (ruleno < 0) { - pr_err("no crush rule pool %lld ruleset %d type %d size %d\n", - pgid.pool, pool->crush_ruleset, pool->type, - pool->size); - return NULL; + /* primary_temp? */ + pg = __lookup_pg_mapping(&osdmap->primary_temp, pgid); + if (pg) + temp_primary = pg->primary_temp.osd; + + *primary = temp_primary; + return temp_len; +} + +/* + * Calculate acting set for given pgid. + * + * Return acting set length, or error. *primary is set to acting + * primary osd id, or -1 if acting set is empty or on error. + */ +int ceph_calc_pg_acting(struct ceph_osdmap *osdmap, struct ceph_pg pgid, + int *osds, int *primary) +{ + struct ceph_pg_pool_info *pool; + u32 pps; + int len; + + pool = __lookup_pg_pool(&osdmap->pg_pools, pgid.pool); + if (!pool) { + *primary = -1; + return -ENOENT; } if (pool->flags & CEPH_POOL_FLAG_HASHPSPOOL) { - /* hash pool id and seed sothat pool PGs do not overlap */ + /* hash pool id and seed so that pool PGs do not overlap */ pps = crush_hash32_2(CRUSH_HASH_RJENKINS1, ceph_stable_mod(pgid.seed, pool->pgp_num, pool->pgp_num_mask), pgid.pool); } else { /* - * legacy ehavior: add ps and pool together. this is + * legacy behavior: add ps and pool together. this is * not a great approach because the PGs from each pool * will overlap on top of each other: 0.5 == 1.4 == * 2.3 == ... @@ -1205,38 +1693,20 @@ static int *calc_pg_raw(struct ceph_osdmap *osdmap, struct ceph_pg pgid, pool->pgp_num_mask) + (unsigned)pgid.pool; } - r = crush_do_rule_ary(osdmap->crush, ruleno, pps, - osds, min_t(int, pool->size, *num), - osdmap->osd_weight, osdmap->max_osd); - if (r < 0) { - pr_err("error %d from crush rule: pool %lld ruleset %d type %d" - " size %d\n", r, pgid.pool, pool->crush_ruleset, - pool->type, pool->size); - return NULL; + + len = pg_to_raw_osds(osdmap, pool, pgid, pps, osds); + if (len < 0) { + *primary = -1; + return len; } - *num = r; - return osds; -} -/* - * Return acting set for given pgid. - */ -int ceph_calc_pg_acting(struct ceph_osdmap *osdmap, struct ceph_pg pgid, - int *acting) -{ - int rawosds[CEPH_PG_MAX_SIZE], *osds; - int i, o, num = CEPH_PG_MAX_SIZE; + len = raw_to_up_osds(osdmap, pool, osds, len, primary); - osds = calc_pg_raw(osdmap, pgid, rawosds, &num); - if (!osds) - return -1; + apply_primary_affinity(osdmap, pps, pool, osds, len, primary); - /* primary is first up osd */ - o = 0; - for (i = 0; i < num; i++) - if (ceph_osd_is_up(osdmap, osds[i])) - acting[o++] = osds[i]; - return o; + len = apply_temps(osdmap, pool, pgid, osds, len, primary); + + return len; } /* @@ -1244,17 +1714,11 @@ int ceph_calc_pg_acting(struct ceph_osdmap *osdmap, struct ceph_pg pgid, */ int ceph_calc_pg_primary(struct ceph_osdmap *osdmap, struct ceph_pg pgid) { - int rawosds[CEPH_PG_MAX_SIZE], *osds; - int i, num = CEPH_PG_MAX_SIZE; + int osds[CEPH_PG_MAX_SIZE]; + int primary; - osds = calc_pg_raw(osdmap, pgid, rawosds, &num); - if (!osds) - return -1; + ceph_calc_pg_acting(osdmap, pgid, osds, &primary); - /* primary is first up osd */ - for (i = 0; i < num; i++) - if (ceph_osd_is_up(osdmap, osds[i])) - return osds[i]; - return -1; + return primary; } EXPORT_SYMBOL(ceph_calc_pg_primary); diff --git a/net/core/dev.c b/net/core/dev.c index 5777018..6da649b 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -2284,7 +2284,7 @@ EXPORT_SYMBOL(skb_checksum_help); __be16 skb_network_protocol(struct sk_buff *skb, int *depth) { __be16 type = skb->protocol; - int vlan_depth = ETH_HLEN; + int vlan_depth = skb->mac_len; /* Tunnel gso handlers can set protocol to ethernet. */ if (type == htons(ETH_P_TEB)) { @@ -2418,7 +2418,7 @@ EXPORT_SYMBOL(netdev_rx_csum_fault); * 2. No high memory really exists on this machine. */ -static int illegal_highdma(const struct net_device *dev, struct sk_buff *skb) +static int illegal_highdma(struct net_device *dev, struct sk_buff *skb) { #ifdef CONFIG_HIGHMEM int i; @@ -2493,38 +2493,36 @@ static int dev_gso_segment(struct sk_buff *skb, netdev_features_t features) } static netdev_features_t harmonize_features(struct sk_buff *skb, - const struct net_device *dev, - netdev_features_t features) + netdev_features_t features) { int tmp; if (skb->ip_summed != CHECKSUM_NONE && !can_checksum_protocol(features, skb_network_protocol(skb, &tmp))) { features &= ~NETIF_F_ALL_CSUM; - } else if (illegal_highdma(dev, skb)) { + } else if (illegal_highdma(skb->dev, skb)) { features &= ~NETIF_F_SG; } return features; } -netdev_features_t netif_skb_dev_features(struct sk_buff *skb, - const struct net_device *dev) +netdev_features_t netif_skb_features(struct sk_buff *skb) { __be16 protocol = skb->protocol; - netdev_features_t features = dev->features; + netdev_features_t features = skb->dev->features; - if (skb_shinfo(skb)->gso_segs > dev->gso_max_segs) + if (skb_shinfo(skb)->gso_segs > skb->dev->gso_max_segs) features &= ~NETIF_F_GSO_MASK; if (protocol == htons(ETH_P_8021Q) || protocol == htons(ETH_P_8021AD)) { struct vlan_ethhdr *veh = (struct vlan_ethhdr *)skb->data; protocol = veh->h_vlan_encapsulated_proto; } else if (!vlan_tx_tag_present(skb)) { - return harmonize_features(skb, dev, features); + return harmonize_features(skb, features); } - features &= (dev->vlan_features | NETIF_F_HW_VLAN_CTAG_TX | + features &= (skb->dev->vlan_features | NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_STAG_TX); if (protocol == htons(ETH_P_8021Q) || protocol == htons(ETH_P_8021AD)) @@ -2532,9 +2530,9 @@ netdev_features_t netif_skb_dev_features(struct sk_buff *skb, NETIF_F_GEN_CSUM | NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_STAG_TX; - return harmonize_features(skb, dev, features); + return harmonize_features(skb, features); } -EXPORT_SYMBOL(netif_skb_dev_features); +EXPORT_SYMBOL(netif_skb_features); int dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev, struct netdev_queue *txq) @@ -4589,8 +4587,7 @@ void *netdev_lower_get_next_private(struct net_device *dev, if (&lower->list == &dev->adj_list.lower) return NULL; - if (iter) - *iter = lower->list.next; + *iter = lower->list.next; return lower->private; } @@ -4618,8 +4615,7 @@ void *netdev_lower_get_next_private_rcu(struct net_device *dev, if (&lower->list == &dev->adj_list.lower) return NULL; - if (iter) - *iter = &lower->list; + *iter = &lower->list; return lower->private; } @@ -5240,6 +5236,7 @@ void __dev_set_rx_mode(struct net_device *dev) if (ops->ndo_set_rx_mode) ops->ndo_set_rx_mode(dev); } +EXPORT_SYMBOL(__dev_set_rx_mode); void dev_set_rx_mode(struct net_device *dev) { @@ -5544,7 +5541,7 @@ static int dev_new_index(struct net *net) /* Delayed registration/unregisteration */ static LIST_HEAD(net_todo_list); -static DECLARE_WAIT_QUEUE_HEAD(netdev_unregistering_wq); +DECLARE_WAIT_QUEUE_HEAD(netdev_unregistering_wq); static void net_set_todo(struct net_device *dev) { diff --git a/net/core/dst.c b/net/core/dst.c index ca4231e..80d6286 100644 --- a/net/core/dst.c +++ b/net/core/dst.c @@ -142,12 +142,12 @@ loop: mutex_unlock(&dst_gc_mutex); } -int dst_discard(struct sk_buff *skb) +int dst_discard_sk(struct sock *sk, struct sk_buff *skb) { kfree_skb(skb); return 0; } -EXPORT_SYMBOL(dst_discard); +EXPORT_SYMBOL(dst_discard_sk); const u32 dst_default_metrics[RTAX_MAX + 1] = { /* This initializer is needed to force linker to place this variable @@ -184,7 +184,7 @@ void *dst_alloc(struct dst_ops *ops, struct net_device *dev, dst->xfrm = NULL; #endif dst->input = dst_discard; - dst->output = dst_discard; + dst->output = dst_discard_sk; dst->error = 0; dst->obsolete = initial_obsolete; dst->header_len = 0; @@ -209,8 +209,10 @@ static void ___dst_free(struct dst_entry *dst) /* The first case (dev==NULL) is required, when protocol module is unloaded. */ - if (dst->dev == NULL || !(dst->dev->flags&IFF_UP)) - dst->input = dst->output = dst_discard; + if (dst->dev == NULL || !(dst->dev->flags&IFF_UP)) { + dst->input = dst_discard; + dst->output = dst_discard_sk; + } dst->obsolete = DST_OBSOLETE_DEAD; } @@ -361,7 +363,8 @@ static void dst_ifdown(struct dst_entry *dst, struct net_device *dev, return; if (!unregister) { - dst->input = dst->output = dst_discard; + dst->input = dst_discard; + dst->output = dst_discard_sk; } else { dst->dev = dev_net(dst->dev)->loopback_dev; dev_hold(dst->dev); diff --git a/net/core/filter.c b/net/core/filter.c index 765556b..9d79ca0 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -122,6 +122,13 @@ noinline u64 __bpf_call_base(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5) return 0; } +/* Register mappings for user programs. */ +#define A_REG 0 +#define X_REG 7 +#define TMP_REG 8 +#define ARG2_REG 2 +#define ARG3_REG 3 + /** * __sk_run_filter - run a filter on a given context * @ctx: buffer to run the filter on @@ -242,6 +249,8 @@ unsigned int __sk_run_filter(void *ctx, const struct sock_filter_int *insn) regs[FP_REG] = (u64) (unsigned long) &stack[ARRAY_SIZE(stack)]; regs[ARG1_REG] = (u64) (unsigned long) ctx; + regs[A_REG] = 0; + regs[X_REG] = 0; select_insn: goto *jumptable[insn->code]; @@ -295,43 +304,43 @@ select_insn: (*(s64 *) &A) >>= K; CONT; BPF_ALU64_BPF_MOD_BPF_X: + if (unlikely(X == 0)) + return 0; tmp = A; - if (X) - A = do_div(tmp, X); + A = do_div(tmp, X); CONT; BPF_ALU_BPF_MOD_BPF_X: + if (unlikely(X == 0)) + return 0; tmp = (u32) A; - if (X) - A = do_div(tmp, (u32) X); + A = do_div(tmp, (u32) X); CONT; BPF_ALU64_BPF_MOD_BPF_K: tmp = A; - if (K) - A = do_div(tmp, K); + A = do_div(tmp, K); CONT; BPF_ALU_BPF_MOD_BPF_K: tmp = (u32) A; - if (K) - A = do_div(tmp, (u32) K); + A = do_div(tmp, (u32) K); CONT; BPF_ALU64_BPF_DIV_BPF_X: - if (X) - do_div(A, X); + if (unlikely(X == 0)) + return 0; + do_div(A, X); CONT; BPF_ALU_BPF_DIV_BPF_X: + if (unlikely(X == 0)) + return 0; tmp = (u32) A; - if (X) - do_div(tmp, (u32) X); + do_div(tmp, (u32) X); A = (u32) tmp; CONT; BPF_ALU64_BPF_DIV_BPF_K: - if (K) - do_div(A, K); + do_div(A, K); CONT; BPF_ALU_BPF_DIV_BPF_K: tmp = (u32) A; - if (K) - do_div(tmp, (u32) K); + do_div(tmp, (u32) K); A = (u32) tmp; CONT; BPF_ALU_BPF_END_BPF_TO_BE: @@ -600,6 +609,9 @@ static u64 __skb_get_nlattr(u64 ctx, u64 A, u64 X, u64 r4, u64 r5) if (skb_is_nonlinear(skb)) return 0; + if (skb->len < sizeof(struct nlattr)) + return 0; + if (A > skb->len - sizeof(struct nlattr)) return 0; @@ -618,11 +630,14 @@ static u64 __skb_get_nlattr_nest(u64 ctx, u64 A, u64 X, u64 r4, u64 r5) if (skb_is_nonlinear(skb)) return 0; + if (skb->len < sizeof(struct nlattr)) + return 0; + if (A > skb->len - sizeof(struct nlattr)) return 0; nla = (struct nlattr *) &skb->data[A]; - if (nla->nla_len > A - skb->len) + if (nla->nla_len > skb->len - A) return 0; nla = nla_find_nested(nla, X); @@ -637,13 +652,6 @@ static u64 __get_raw_cpu_id(u64 ctx, u64 A, u64 X, u64 r4, u64 r5) return raw_smp_processor_id(); } -/* Register mappings for user programs. */ -#define A_REG 0 -#define X_REG 7 -#define TMP_REG 8 -#define ARG2_REG 2 -#define ARG3_REG 3 - static bool convert_bpf_extensions(struct sock_filter *fp, struct sock_filter_int **insnp) { @@ -1737,7 +1745,6 @@ void sk_decode_filter(struct sock_filter *filt, struct sock_filter *to) [BPF_S_ANC_RXHASH] = BPF_LD|BPF_B|BPF_ABS, [BPF_S_ANC_CPU] = BPF_LD|BPF_B|BPF_ABS, [BPF_S_ANC_ALU_XOR_X] = BPF_LD|BPF_B|BPF_ABS, - [BPF_S_ANC_SECCOMP_LD_W] = BPF_LD|BPF_B|BPF_ABS, [BPF_S_ANC_VLAN_TAG] = BPF_LD|BPF_B|BPF_ABS, [BPF_S_ANC_VLAN_TAG_PRESENT] = BPF_LD|BPF_B|BPF_ABS, [BPF_S_ANC_PAY_OFFSET] = BPF_LD|BPF_B|BPF_ABS, diff --git a/net/core/flow.c b/net/core/flow.c index 31cfb36..a0348fd 100644 --- a/net/core/flow.c +++ b/net/core/flow.c @@ -455,6 +455,8 @@ int flow_cache_init(struct net *net) if (!fc->percpu) return -ENOMEM; + cpu_notifier_register_begin(); + for_each_online_cpu(i) { if (flow_cache_cpu_prepare(fc, i)) goto err; @@ -462,7 +464,9 @@ int flow_cache_init(struct net *net) fc->hotcpu_notifier = (struct notifier_block){ .notifier_call = flow_cache_cpu, }; - register_hotcpu_notifier(&fc->hotcpu_notifier); + __register_hotcpu_notifier(&fc->hotcpu_notifier); + + cpu_notifier_register_done(); setup_timer(&fc->rnd_timer, flow_cache_new_hashrnd, (unsigned long) fc); @@ -478,6 +482,8 @@ err: fcp->hash_table = NULL; } + cpu_notifier_register_done(); + free_percpu(fc->percpu); fc->percpu = NULL; diff --git a/net/core/neighbour.c b/net/core/neighbour.c index 8f8a96e..32d872e 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -1248,8 +1248,8 @@ void __neigh_set_probe_once(struct neighbour *neigh) neigh->updated = jiffies; if (!(neigh->nud_state & NUD_FAILED)) return; - neigh->nud_state = NUD_PROBE; - atomic_set(&neigh->probes, NEIGH_VAR(neigh->parms, UCAST_PROBES)); + neigh->nud_state = NUD_INCOMPLETE; + atomic_set(&neigh->probes, neigh_max_probes(neigh)); neigh_add_timer(neigh, jiffies + NEIGH_VAR(neigh->parms, RETRANS_TIME)); } diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c index 81d3a9a..7c8ffd9 100644 --- a/net/core/net_namespace.c +++ b/net/core/net_namespace.c @@ -24,7 +24,7 @@ static LIST_HEAD(pernet_list); static struct list_head *first_device = &pernet_list; -static DEFINE_MUTEX(net_mutex); +DEFINE_MUTEX(net_mutex); LIST_HEAD(net_namespace_list); EXPORT_SYMBOL_GPL(net_namespace_list); diff --git a/net/core/netclassid_cgroup.c b/net/core/netclassid_cgroup.c index 719efd5..22931e1 100644 --- a/net/core/netclassid_cgroup.c +++ b/net/core/netclassid_cgroup.c @@ -23,7 +23,7 @@ static inline struct cgroup_cls_state *css_cls_state(struct cgroup_subsys_state struct cgroup_cls_state *task_cls_state(struct task_struct *p) { - return css_cls_state(task_css(p, net_cls_subsys_id)); + return css_cls_state(task_css(p, net_cls_cgrp_id)); } EXPORT_SYMBOL_GPL(task_cls_state); @@ -73,7 +73,7 @@ static void cgrp_attach(struct cgroup_subsys_state *css, void *v = (void *)(unsigned long)cs->classid; struct task_struct *p; - cgroup_taskset_for_each(p, css, tset) { + cgroup_taskset_for_each(p, tset) { task_lock(p); iterate_fd(p->files, 0, update_classid, v); task_unlock(p); @@ -102,19 +102,10 @@ static struct cftype ss_files[] = { { } /* terminate */ }; -struct cgroup_subsys net_cls_subsys = { - .name = "net_cls", +struct cgroup_subsys net_cls_cgrp_subsys = { .css_alloc = cgrp_css_alloc, .css_online = cgrp_css_online, .css_free = cgrp_css_free, .attach = cgrp_attach, - .subsys_id = net_cls_subsys_id, .base_cftypes = ss_files, - .module = THIS_MODULE, }; - -static int __init init_netclassid_cgroup(void) -{ - return cgroup_load_subsys(&net_cls_subsys); -} -__initcall(init_netclassid_cgroup); diff --git a/net/core/netprio_cgroup.c b/net/core/netprio_cgroup.c index 9043cae..3825f66 100644 --- a/net/core/netprio_cgroup.c +++ b/net/core/netprio_cgroup.c @@ -186,7 +186,7 @@ static int read_priomap(struct seq_file *sf, void *v) } static int write_priomap(struct cgroup_subsys_state *css, struct cftype *cft, - const char *buffer) + char *buffer) { char devname[IFNAMSIZ + 1]; struct net_device *dev; @@ -224,7 +224,7 @@ static void net_prio_attach(struct cgroup_subsys_state *css, struct task_struct *p; void *v = (void *)(unsigned long)css->cgroup->id; - cgroup_taskset_for_each(p, css, tset) { + cgroup_taskset_for_each(p, tset) { task_lock(p); iterate_fd(p->files, 0, update_netprio, v); task_unlock(p); @@ -244,15 +244,12 @@ static struct cftype ss_files[] = { { } /* terminate */ }; -struct cgroup_subsys net_prio_subsys = { - .name = "net_prio", +struct cgroup_subsys net_prio_cgrp_subsys = { .css_alloc = cgrp_css_alloc, .css_online = cgrp_css_online, .css_free = cgrp_css_free, .attach = net_prio_attach, - .subsys_id = net_prio_subsys_id, .base_cftypes = ss_files, - .module = THIS_MODULE, }; static int netprio_device_event(struct notifier_block *unused, @@ -283,37 +280,9 @@ static struct notifier_block netprio_device_notifier = { static int __init init_cgroup_netprio(void) { - int ret; - - ret = cgroup_load_subsys(&net_prio_subsys); - if (ret) - goto out; - register_netdevice_notifier(&netprio_device_notifier); - -out: - return ret; -} - -static void __exit exit_cgroup_netprio(void) -{ - struct netprio_map *old; - struct net_device *dev; - - unregister_netdevice_notifier(&netprio_device_notifier); - - cgroup_unload_subsys(&net_prio_subsys); - - rtnl_lock(); - for_each_netdev(&init_net, dev) { - old = rtnl_dereference(dev->priomap); - RCU_INIT_POINTER(dev->priomap, NULL); - if (old) - kfree_rcu(old, rcu); - } - rtnl_unlock(); + return 0; } -module_init(init_cgroup_netprio); -module_exit(exit_cgroup_netprio); +subsys_initcall(init_cgroup_netprio); MODULE_LICENSE("GPL v2"); diff --git a/net/core/pktgen.c b/net/core/pktgen.c index d0dac57..0304f98 100644 --- a/net/core/pktgen.c +++ b/net/core/pktgen.c @@ -3338,9 +3338,11 @@ static void pktgen_xmit(struct pktgen_dev *pkt_dev) queue_map = skb_get_queue_mapping(pkt_dev->skb); txq = netdev_get_tx_queue(odev, queue_map); - __netif_tx_lock_bh(txq); + local_bh_disable(); - if (unlikely(netif_xmit_frozen_or_stopped(txq))) { + HARD_TX_LOCK(odev, txq, smp_processor_id()); + + if (unlikely(netif_xmit_frozen_or_drv_stopped(txq))) { ret = NETDEV_TX_BUSY; pkt_dev->last_ok = 0; goto unlock; @@ -3374,7 +3376,9 @@ static void pktgen_xmit(struct pktgen_dev *pkt_dev) pkt_dev->last_ok = 0; } unlock: - __netif_tx_unlock_bh(txq); + HARD_TX_UNLOCK(odev, txq); + + local_bh_enable(); /* If pkt_dev->count is zero, then run forever */ if ((pkt_dev->count != 0) && (pkt_dev->sofar >= pkt_dev->count)) { diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index d4ff417..2d8d8fc 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -353,15 +353,46 @@ void __rtnl_link_unregister(struct rtnl_link_ops *ops) } EXPORT_SYMBOL_GPL(__rtnl_link_unregister); +/* Return with the rtnl_lock held when there are no network + * devices unregistering in any network namespace. + */ +static void rtnl_lock_unregistering_all(void) +{ + struct net *net; + bool unregistering; + DEFINE_WAIT(wait); + + for (;;) { + prepare_to_wait(&netdev_unregistering_wq, &wait, + TASK_UNINTERRUPTIBLE); + unregistering = false; + rtnl_lock(); + for_each_net(net) { + if (net->dev_unreg_count > 0) { + unregistering = true; + break; + } + } + if (!unregistering) + break; + __rtnl_unlock(); + schedule(); + } + finish_wait(&netdev_unregistering_wq, &wait); +} + /** * rtnl_link_unregister - Unregister rtnl_link_ops from rtnetlink. * @ops: struct rtnl_link_ops * to unregister */ void rtnl_link_unregister(struct rtnl_link_ops *ops) { - rtnl_lock(); + /* Close the race with cleanup_net() */ + mutex_lock(&net_mutex); + rtnl_lock_unregistering_all(); __rtnl_link_unregister(ops); rtnl_unlock(); + mutex_unlock(&net_mutex); } EXPORT_SYMBOL_GPL(rtnl_link_unregister); @@ -774,7 +805,8 @@ static inline int rtnl_vfinfo_size(const struct net_device *dev, return 0; } -static size_t rtnl_port_size(const struct net_device *dev) +static size_t rtnl_port_size(const struct net_device *dev, + u32 ext_filter_mask) { size_t port_size = nla_total_size(4) /* PORT_VF */ + nla_total_size(PORT_PROFILE_MAX) /* PORT_PROFILE */ @@ -790,7 +822,8 @@ static size_t rtnl_port_size(const struct net_device *dev) size_t port_self_size = nla_total_size(sizeof(struct nlattr)) + port_size; - if (!dev->netdev_ops->ndo_get_vf_port || !dev->dev.parent) + if (!dev->netdev_ops->ndo_get_vf_port || !dev->dev.parent || + !(ext_filter_mask & RTEXT_FILTER_VF)) return 0; if (dev_num_vf(dev->dev.parent)) return port_self_size + vf_ports_size + @@ -826,7 +859,7 @@ static noinline size_t if_nlmsg_size(const struct net_device *dev, + nla_total_size(ext_filter_mask & RTEXT_FILTER_VF ? 4 : 0) /* IFLA_NUM_VF */ + rtnl_vfinfo_size(dev, ext_filter_mask) /* IFLA_VFINFO_LIST */ - + rtnl_port_size(dev) /* IFLA_VF_PORTS + IFLA_PORT_SELF */ + + rtnl_port_size(dev, ext_filter_mask) /* IFLA_VF_PORTS + IFLA_PORT_SELF */ + rtnl_link_get_size(dev) /* IFLA_LINKINFO */ + rtnl_link_get_af_size(dev) /* IFLA_AF_SPEC */ + nla_total_size(MAX_PHYS_PORT_ID_LEN); /* IFLA_PHYS_PORT_ID */ @@ -888,11 +921,13 @@ static int rtnl_port_self_fill(struct sk_buff *skb, struct net_device *dev) return 0; } -static int rtnl_port_fill(struct sk_buff *skb, struct net_device *dev) +static int rtnl_port_fill(struct sk_buff *skb, struct net_device *dev, + u32 ext_filter_mask) { int err; - if (!dev->netdev_ops->ndo_get_vf_port || !dev->dev.parent) + if (!dev->netdev_ops->ndo_get_vf_port || !dev->dev.parent || + !(ext_filter_mask & RTEXT_FILTER_VF)) return 0; err = rtnl_port_self_fill(skb, dev); @@ -1079,7 +1114,7 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev, nla_nest_end(skb, vfinfo); } - if (rtnl_port_fill(skb, dev)) + if (rtnl_port_fill(skb, dev, ext_filter_mask)) goto nla_put_failure; if (dev->rtnl_link_ops || rtnl_have_link_slave_info(dev)) { @@ -1198,6 +1233,7 @@ static int rtnl_dump_ifinfo(struct sk_buff *skb, struct netlink_callback *cb) struct hlist_head *head; struct nlattr *tb[IFLA_MAX+1]; u32 ext_filter_mask = 0; + int err; s_h = cb->args[0]; s_idx = cb->args[1]; @@ -1218,11 +1254,17 @@ static int rtnl_dump_ifinfo(struct sk_buff *skb, struct netlink_callback *cb) hlist_for_each_entry_rcu(dev, head, index_hlist) { if (idx < s_idx) goto cont; - if (rtnl_fill_ifinfo(skb, dev, RTM_NEWLINK, - NETLINK_CB(cb->skb).portid, - cb->nlh->nlmsg_seq, 0, - NLM_F_MULTI, - ext_filter_mask) <= 0) + err = rtnl_fill_ifinfo(skb, dev, RTM_NEWLINK, + NETLINK_CB(cb->skb).portid, + cb->nlh->nlmsg_seq, 0, + NLM_F_MULTI, + ext_filter_mask); + /* If we ran out of room on the first message, + * we're in trouble + */ + WARN_ON((err == -EMSGSIZE) && (skb->len == 0)); + + if (err <= 0) goto out; nl_dump_check_consistent(cb, nlmsg_hdr(skb)); @@ -1395,7 +1437,8 @@ static int do_set_master(struct net_device *dev, int ifindex) return 0; } -static int do_setlink(struct net_device *dev, struct ifinfomsg *ifm, +static int do_setlink(const struct sk_buff *skb, + struct net_device *dev, struct ifinfomsg *ifm, struct nlattr **tb, char *ifname, int modified) { const struct net_device_ops *ops = dev->netdev_ops; @@ -1407,7 +1450,7 @@ static int do_setlink(struct net_device *dev, struct ifinfomsg *ifm, err = PTR_ERR(net); goto errout; } - if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) { + if (!netlink_ns_capable(skb, net->user_ns, CAP_NET_ADMIN)) { err = -EPERM; goto errout; } @@ -1661,7 +1704,7 @@ static int rtnl_setlink(struct sk_buff *skb, struct nlmsghdr *nlh) if (err < 0) goto errout; - err = do_setlink(dev, ifm, tb, ifname, 0); + err = do_setlink(skb, dev, ifm, tb, ifname, 0); errout: return err; } @@ -1778,7 +1821,8 @@ err: } EXPORT_SYMBOL(rtnl_create_link); -static int rtnl_group_changelink(struct net *net, int group, +static int rtnl_group_changelink(const struct sk_buff *skb, + struct net *net, int group, struct ifinfomsg *ifm, struct nlattr **tb) { @@ -1787,7 +1831,7 @@ static int rtnl_group_changelink(struct net *net, int group, for_each_netdev(net, dev) { if (dev->group == group) { - err = do_setlink(dev, ifm, tb, NULL, 0); + err = do_setlink(skb, dev, ifm, tb, NULL, 0); if (err < 0) return err; } @@ -1929,12 +1973,12 @@ replay: modified = 1; } - return do_setlink(dev, ifm, tb, ifname, modified); + return do_setlink(skb, dev, ifm, tb, ifname, modified); } if (!(nlh->nlmsg_flags & NLM_F_CREATE)) { if (ifm->ifi_index == 0 && tb[IFLA_GROUP]) - return rtnl_group_changelink(net, + return rtnl_group_changelink(skb, net, nla_get_u32(tb[IFLA_GROUP]), ifm, tb); return -ENODEV; @@ -2321,7 +2365,7 @@ static int rtnl_fdb_del(struct sk_buff *skb, struct nlmsghdr *nlh) int err = -EINVAL; __u8 *addr; - if (!capable(CAP_NET_ADMIN)) + if (!netlink_capable(skb, CAP_NET_ADMIN)) return -EPERM; err = nlmsg_parse(nlh, sizeof(*ndm), tb, NDA_MAX, NULL); @@ -2773,7 +2817,7 @@ static int rtnetlink_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh) sz_idx = type>>2; kind = type&3; - if (kind != 2 && !ns_capable(net->user_ns, CAP_NET_ADMIN)) + if (kind != 2 && !netlink_net_capable(skb, CAP_NET_ADMIN)) return -EPERM; if (kind == 2 && nlh->nlmsg_flags&NLM_F_DUMP) { diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 30c7d35..1b62343 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -3458,8 +3458,6 @@ static void sock_rmem_free(struct sk_buff *skb) */ int sock_queue_err_skb(struct sock *sk, struct sk_buff *skb) { - int len = skb->len; - if (atomic_read(&sk->sk_rmem_alloc) + skb->truesize >= (unsigned int)sk->sk_rcvbuf) return -ENOMEM; @@ -3474,7 +3472,7 @@ int sock_queue_err_skb(struct sock *sk, struct sk_buff *skb) skb_queue_tail(&sk->sk_error_queue, skb); if (!sock_flag(sk, SOCK_DEAD)) - sk->sk_data_ready(sk, len); + sk->sk_data_ready(sk); return 0; } EXPORT_SYMBOL(sock_queue_err_skb); @@ -3937,12 +3935,14 @@ EXPORT_SYMBOL_GPL(skb_scrub_packet); unsigned int skb_gso_transport_seglen(const struct sk_buff *skb) { const struct skb_shared_info *shinfo = skb_shinfo(skb); - unsigned int hdr_len; if (likely(shinfo->gso_type & (SKB_GSO_TCPV4 | SKB_GSO_TCPV6))) - hdr_len = tcp_hdrlen(skb); - else - hdr_len = sizeof(struct udphdr); - return hdr_len + shinfo->gso_size; + return tcp_hdrlen(skb) + shinfo->gso_size; + + /* UFO sets gso_size to the size of the fragmentation + * payload, i.e. the size of the L4 (UDP) header is already + * accounted for. + */ + return shinfo->gso_size; } EXPORT_SYMBOL_GPL(skb_gso_transport_seglen); diff --git a/net/core/sock.c b/net/core/sock.c index c0fc6bd..664ee42 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -145,6 +145,55 @@ static DEFINE_MUTEX(proto_list_mutex); static LIST_HEAD(proto_list); +/** + * sk_ns_capable - General socket capability test + * @sk: Socket to use a capability on or through + * @user_ns: The user namespace of the capability to use + * @cap: The capability to use + * + * Test to see if the opener of the socket had when the socket was + * created and the current process has the capability @cap in the user + * namespace @user_ns. + */ +bool sk_ns_capable(const struct sock *sk, + struct user_namespace *user_ns, int cap) +{ + return file_ns_capable(sk->sk_socket->file, user_ns, cap) && + ns_capable(user_ns, cap); +} +EXPORT_SYMBOL(sk_ns_capable); + +/** + * sk_capable - Socket global capability test + * @sk: Socket to use a capability on or through + * @cap: The global capbility to use + * + * Test to see if the opener of the socket had when the socket was + * created and the current process has the capability @cap in all user + * namespaces. + */ +bool sk_capable(const struct sock *sk, int cap) +{ + return sk_ns_capable(sk, &init_user_ns, cap); +} +EXPORT_SYMBOL(sk_capable); + +/** + * sk_net_capable - Network namespace socket capability test + * @sk: Socket to use a capability on or through + * @cap: The capability to use + * + * Test to see if the opener of the socket had when the socke was created + * and the current process has the capability @cap over the network namespace + * the socket is a member of. + */ +bool sk_net_capable(const struct sock *sk, int cap) +{ + return sk_ns_capable(sk, sock_net(sk)->user_ns, cap); +} +EXPORT_SYMBOL(sk_net_capable); + + #ifdef CONFIG_MEMCG_KMEM int mem_cgroup_sockets_init(struct mem_cgroup *memcg, struct cgroup_subsys *ss) { @@ -428,7 +477,7 @@ int sock_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) spin_unlock_irqrestore(&list->lock, flags); if (!sock_flag(sk, SOCK_DEAD)) - sk->sk_data_ready(sk, skb_len); + sk->sk_data_ready(sk); return 0; } EXPORT_SYMBOL(sock_queue_rcv_skb); @@ -2196,7 +2245,7 @@ static void sock_def_error_report(struct sock *sk) rcu_read_unlock(); } -static void sock_def_readable(struct sock *sk, int len) +static void sock_def_readable(struct sock *sk) { struct socket_wq *wq; diff --git a/net/core/sock_diag.c b/net/core/sock_diag.c index d7af188..a4216a4 100644 --- a/net/core/sock_diag.c +++ b/net/core/sock_diag.c @@ -49,7 +49,7 @@ int sock_diag_put_meminfo(struct sock *sk, struct sk_buff *skb, int attrtype) } EXPORT_SYMBOL_GPL(sock_diag_put_meminfo); -int sock_diag_put_filterinfo(struct user_namespace *user_ns, struct sock *sk, +int sock_diag_put_filterinfo(bool may_report_filterinfo, struct sock *sk, struct sk_buff *skb, int attrtype) { struct sock_fprog_kern *fprog; @@ -58,7 +58,7 @@ int sock_diag_put_filterinfo(struct user_namespace *user_ns, struct sock *sk, unsigned int flen; int err = 0; - if (!ns_capable(user_ns, CAP_NET_ADMIN)) { + if (!may_report_filterinfo) { nla_reserve(skb, attrtype, 0); return 0; } diff --git a/net/core/utils.c b/net/core/utils.c index 2f737bf..eed3433 100644 --- a/net/core/utils.c +++ b/net/core/utils.c @@ -348,8 +348,8 @@ static void __net_random_once_deferred(struct work_struct *w) { struct __net_random_once_work *work = container_of(w, struct __net_random_once_work, work); - if (!static_key_enabled(work->key)) - static_key_slow_inc(work->key); + BUG_ON(!static_key_enabled(work->key)); + static_key_slow_dec(work->key); kfree(work); } @@ -367,7 +367,7 @@ static void __net_random_once_disable_jump(struct static_key *key) } bool __net_get_random_once(void *buf, int nbytes, bool *done, - struct static_key *done_key) + struct static_key *once_key) { static DEFINE_SPINLOCK(lock); unsigned long flags; @@ -382,7 +382,7 @@ bool __net_get_random_once(void *buf, int nbytes, bool *done, *done = true; spin_unlock_irqrestore(&lock, flags); - __net_random_once_disable_jump(done_key); + __net_random_once_disable_jump(once_key); return true; } diff --git a/net/dcb/dcbnl.c b/net/dcb/dcbnl.c index 5536444..f8b98d8 100644 --- a/net/dcb/dcbnl.c +++ b/net/dcb/dcbnl.c @@ -1669,7 +1669,7 @@ static int dcb_doit(struct sk_buff *skb, struct nlmsghdr *nlh) struct nlmsghdr *reply_nlh = NULL; const struct reply_func *fn; - if ((nlh->nlmsg_type == RTM_SETDCB) && !capable(CAP_NET_ADMIN)) + if ((nlh->nlmsg_type == RTM_SETDCB) && !netlink_capable(skb, CAP_NET_ADMIN)) return -EPERM; ret = nlmsg_parse(nlh, sizeof(*dcb), tb, DCB_ATTR_MAX, diff --git a/net/dccp/input.c b/net/dccp/input.c index 14cdafa..3c8ec7d 100644 --- a/net/dccp/input.c +++ b/net/dccp/input.c @@ -28,7 +28,7 @@ static void dccp_enqueue_skb(struct sock *sk, struct sk_buff *skb) __skb_pull(skb, dccp_hdr(skb)->dccph_doff * 4); __skb_queue_tail(&sk->sk_receive_queue, skb); skb_set_owner_r(skb, sk); - sk->sk_data_ready(sk, 0); + sk->sk_data_ready(sk); } static void dccp_fin(struct sock *sk, struct sk_buff *skb) diff --git a/net/dccp/minisocks.c b/net/dccp/minisocks.c index 9e2f78b..c69eb9c 100644 --- a/net/dccp/minisocks.c +++ b/net/dccp/minisocks.c @@ -237,7 +237,7 @@ int dccp_child_process(struct sock *parent, struct sock *child, /* Wakeup parent, send SIGIO */ if (state == DCCP_RESPOND && child->sk_state != state) - parent->sk_data_ready(parent, 0); + parent->sk_data_ready(parent); } else { /* Alas, it is possible again, because we do lookup * in main socket hash table and lock on listening diff --git a/net/dccp/output.c b/net/dccp/output.c index 8876078..0248e8a 100644 --- a/net/dccp/output.c +++ b/net/dccp/output.c @@ -138,7 +138,7 @@ static int dccp_transmit_skb(struct sock *sk, struct sk_buff *skb) DCCP_INC_STATS(DCCP_MIB_OUTSEGS); - err = icsk->icsk_af_ops->queue_xmit(skb, &inet->cork.fl); + err = icsk->icsk_af_ops->queue_xmit(sk, skb, &inet->cork.fl); return net_xmit_eval(err); } return -ENOBUFS; diff --git a/net/decnet/dn_dev.c b/net/decnet/dn_dev.c index a603823..3b726f3 100644 --- a/net/decnet/dn_dev.c +++ b/net/decnet/dn_dev.c @@ -574,7 +574,7 @@ static int dn_nl_deladdr(struct sk_buff *skb, struct nlmsghdr *nlh) struct dn_ifaddr __rcu **ifap; int err = -EINVAL; - if (!capable(CAP_NET_ADMIN)) + if (!netlink_capable(skb, CAP_NET_ADMIN)) return -EPERM; if (!net_eq(net, &init_net)) @@ -618,7 +618,7 @@ static int dn_nl_newaddr(struct sk_buff *skb, struct nlmsghdr *nlh) struct dn_ifaddr *ifa; int err; - if (!capable(CAP_NET_ADMIN)) + if (!netlink_capable(skb, CAP_NET_ADMIN)) return -EPERM; if (!net_eq(net, &init_net)) diff --git a/net/decnet/dn_fib.c b/net/decnet/dn_fib.c index 57dc159..d332aef 100644 --- a/net/decnet/dn_fib.c +++ b/net/decnet/dn_fib.c @@ -505,7 +505,7 @@ static int dn_fib_rtm_delroute(struct sk_buff *skb, struct nlmsghdr *nlh) struct nlattr *attrs[RTA_MAX+1]; int err; - if (!capable(CAP_NET_ADMIN)) + if (!netlink_capable(skb, CAP_NET_ADMIN)) return -EPERM; if (!net_eq(net, &init_net)) @@ -530,7 +530,7 @@ static int dn_fib_rtm_newroute(struct sk_buff *skb, struct nlmsghdr *nlh) struct nlattr *attrs[RTA_MAX+1]; int err; - if (!capable(CAP_NET_ADMIN)) + if (!netlink_capable(skb, CAP_NET_ADMIN)) return -EPERM; if (!net_eq(net, &init_net)) diff --git a/net/decnet/dn_nsp_in.c b/net/decnet/dn_nsp_in.c index c344163..fe5f014 100644 --- a/net/decnet/dn_nsp_in.c +++ b/net/decnet/dn_nsp_in.c @@ -585,7 +585,6 @@ out: static __inline__ int dn_queue_skb(struct sock *sk, struct sk_buff *skb, int sig, struct sk_buff_head *queue) { int err; - int skb_len; /* Cast skb->rcvbuf to unsigned... It's pointless, but reduces number of warnings when compiling with -W --ANK @@ -600,12 +599,11 @@ static __inline__ int dn_queue_skb(struct sock *sk, struct sk_buff *skb, int sig if (err) goto out; - skb_len = skb->len; skb_set_owner_r(skb, sk); skb_queue_tail(queue, skb); if (!sock_flag(sk, SOCK_DEAD)) - sk->sk_data_ready(sk, skb_len); + sk->sk_data_ready(sk); out: return err; } diff --git a/net/decnet/dn_route.c b/net/decnet/dn_route.c index ce0cbbf..daccc4a 100644 --- a/net/decnet/dn_route.c +++ b/net/decnet/dn_route.c @@ -752,7 +752,7 @@ static int dn_to_neigh_output(struct sk_buff *skb) return n->output(n, skb); } -static int dn_output(struct sk_buff *skb) +static int dn_output(struct sock *sk, struct sk_buff *skb) { struct dst_entry *dst = skb_dst(skb); struct dn_route *rt = (struct dn_route *)dst; @@ -838,6 +838,18 @@ drop: * Used to catch bugs. This should never normally get * called. */ +static int dn_rt_bug_sk(struct sock *sk, struct sk_buff *skb) +{ + struct dn_skb_cb *cb = DN_SKB_CB(skb); + + net_dbg_ratelimited("dn_rt_bug: skb from:%04x to:%04x\n", + le16_to_cpu(cb->src), le16_to_cpu(cb->dst)); + + kfree_skb(skb); + + return NET_RX_DROP; +} + static int dn_rt_bug(struct sk_buff *skb) { struct dn_skb_cb *cb = DN_SKB_CB(skb); @@ -1463,7 +1475,7 @@ make_route: rt->n = neigh; rt->dst.lastuse = jiffies; - rt->dst.output = dn_rt_bug; + rt->dst.output = dn_rt_bug_sk; switch (res.type) { case RTN_UNICAST: rt->dst.input = dn_forward; diff --git a/net/decnet/netfilter/dn_rtmsg.c b/net/decnet/netfilter/dn_rtmsg.c index e83015c..e4d9560 100644 --- a/net/decnet/netfilter/dn_rtmsg.c +++ b/net/decnet/netfilter/dn_rtmsg.c @@ -107,7 +107,7 @@ static inline void dnrmg_receive_user_skb(struct sk_buff *skb) if (nlh->nlmsg_len < sizeof(*nlh) || skb->len < nlh->nlmsg_len) return; - if (!capable(CAP_NET_ADMIN)) + if (!netlink_capable(skb, CAP_NET_ADMIN)) RCV_SKB_FAIL(-EPERM); /* Eventually we might send routing messages too */ diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index 8c54870..6d6dd34 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -1650,6 +1650,39 @@ static int __init init_ipv4_mibs(void) return register_pernet_subsys(&ipv4_mib_ops); } +static __net_init int inet_init_net(struct net *net) +{ + /* + * Set defaults for local port range + */ + seqlock_init(&net->ipv4.ip_local_ports.lock); + net->ipv4.ip_local_ports.range[0] = 32768; + net->ipv4.ip_local_ports.range[1] = 61000; + + seqlock_init(&net->ipv4.ping_group_range.lock); + /* + * Sane defaults - nobody may create ping sockets. + * Boot scripts should set this to distro-specific group. + */ + net->ipv4.ping_group_range.range[0] = make_kgid(&init_user_ns, 1); + net->ipv4.ping_group_range.range[1] = make_kgid(&init_user_ns, 0); + return 0; +} + +static __net_exit void inet_exit_net(struct net *net) +{ +} + +static __net_initdata struct pernet_operations af_inet_ops = { + .init = inet_init_net, + .exit = inet_exit_net, +}; + +static int __init init_inet_pernet_ops(void) +{ + return register_pernet_subsys(&af_inet_ops); +} + static int ipv4_proc_init(void); /* @@ -1794,6 +1827,9 @@ static int __init inet_init(void) if (ip_mr_init()) pr_crit("%s: Cannot init ipv4 mroute\n", __func__); #endif + + if (init_inet_pernet_ops()) + pr_crit("%s: Cannot init ipv4 inet pernet ops\n", __func__); /* * Initialise per-cpu ipv4 mibs */ diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c index 1a629f8..255aa99 100644 --- a/net/ipv4/fib_frontend.c +++ b/net/ipv4/fib_frontend.c @@ -250,7 +250,7 @@ static int __fib_validate_source(struct sk_buff *skb, __be32 src, __be32 dst, bool dev_match; fl4.flowi4_oif = 0; - fl4.flowi4_iif = oif; + fl4.flowi4_iif = oif ? : LOOPBACK_IFINDEX; fl4.daddr = src; fl4.saddr = dst; fl4.flowi4_tos = tos; diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c index b53f0bf..b10cd43a 100644 --- a/net/ipv4/fib_semantics.c +++ b/net/ipv4/fib_semantics.c @@ -631,6 +631,7 @@ static int fib_check_nh(struct fib_config *cfg, struct fib_info *fi, .daddr = nh->nh_gw, .flowi4_scope = cfg->fc_scope + 1, .flowi4_oif = nh->nh_oif, + .flowi4_iif = LOOPBACK_IFINDEX, }; /* It is not necessary, but requires a bit of thinking */ @@ -820,13 +821,13 @@ struct fib_info *fib_create_info(struct fib_config *cfg) fi = kzalloc(sizeof(*fi)+nhs*sizeof(struct fib_nh), GFP_KERNEL); if (fi == NULL) goto failure; + fib_info_cnt++; if (cfg->fc_mx) { fi->fib_metrics = kzalloc(sizeof(u32) * RTAX_MAX, GFP_KERNEL); if (!fi->fib_metrics) goto failure; } else fi->fib_metrics = (u32 *) dst_default_metrics; - fib_info_cnt++; fi->fib_net = hold_net(net); fi->fib_protocol = cfg->fc_protocol; diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index 0d1e2cb..a56b8e6 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -37,11 +37,11 @@ void inet_get_local_port_range(struct net *net, int *low, int *high) unsigned int seq; do { - seq = read_seqbegin(&net->ipv4.sysctl_local_ports.lock); + seq = read_seqbegin(&net->ipv4.ip_local_ports.lock); - *low = net->ipv4.sysctl_local_ports.range[0]; - *high = net->ipv4.sysctl_local_ports.range[1]; - } while (read_seqretry(&net->ipv4.sysctl_local_ports.lock, seq)); + *low = net->ipv4.ip_local_ports.range[0]; + *high = net->ipv4.ip_local_ports.range[1]; + } while (read_seqretry(&net->ipv4.ip_local_ports.lock, seq)); } EXPORT_SYMBOL(inet_get_local_port_range); diff --git a/net/ipv4/ip_forward.c b/net/ipv4/ip_forward.c index be8abe7..6f111e4 100644 --- a/net/ipv4/ip_forward.c +++ b/net/ipv4/ip_forward.c @@ -42,12 +42,12 @@ static bool ip_may_fragment(const struct sk_buff *skb) { return unlikely((ip_hdr(skb)->frag_off & htons(IP_DF)) == 0) || - !skb->local_df; + skb->local_df; } static bool ip_exceeds_mtu(const struct sk_buff *skb, unsigned int mtu) { - if (skb->len <= mtu || skb->local_df) + if (skb->len <= mtu) return false; if (skb_is_gso(skb) && skb_gso_network_seglen(skb) <= mtu) @@ -56,53 +56,6 @@ static bool ip_exceeds_mtu(const struct sk_buff *skb, unsigned int mtu) return true; } -static bool ip_gso_exceeds_dst_mtu(const struct sk_buff *skb) -{ - unsigned int mtu; - - if (skb->local_df || !skb_is_gso(skb)) - return false; - - mtu = ip_dst_mtu_maybe_forward(skb_dst(skb), true); - - /* if seglen > mtu, do software segmentation for IP fragmentation on - * output. DF bit cannot be set since ip_forward would have sent - * icmp error. - */ - return skb_gso_network_seglen(skb) > mtu; -} - -/* called if GSO skb needs to be fragmented on forward */ -static int ip_forward_finish_gso(struct sk_buff *skb) -{ - struct dst_entry *dst = skb_dst(skb); - netdev_features_t features; - struct sk_buff *segs; - int ret = 0; - - features = netif_skb_dev_features(skb, dst->dev); - segs = skb_gso_segment(skb, features & ~NETIF_F_GSO_MASK); - if (IS_ERR(segs)) { - kfree_skb(skb); - return -ENOMEM; - } - - consume_skb(skb); - - do { - struct sk_buff *nskb = segs->next; - int err; - - segs->next = NULL; - err = dst_output(segs); - - if (err && ret == 0) - ret = err; - segs = nskb; - } while (segs); - - return ret; -} static int ip_forward_finish(struct sk_buff *skb) { @@ -114,9 +67,6 @@ static int ip_forward_finish(struct sk_buff *skb) if (unlikely(opt->optlen)) ip_forward_options(skb); - if (ip_gso_exceeds_dst_mtu(skb)) - return ip_forward_finish_gso(skb); - return dst_output(skb); } diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c index c10a3ce..ed32313 100644 --- a/net/ipv4/ip_fragment.c +++ b/net/ipv4/ip_fragment.c @@ -232,8 +232,9 @@ static void ip_expire(unsigned long arg) * "Fragment Reassembly Timeout" message, per RFC792. */ if (qp->user == IP_DEFRAG_AF_PACKET || - (qp->user == IP_DEFRAG_CONNTRACK_IN && - skb_rtable(head)->rt_type != RTN_LOCAL)) + ((qp->user >= IP_DEFRAG_CONNTRACK_IN) && + (qp->user <= __IP_DEFRAG_CONNTRACK_IN_END) && + (skb_rtable(head)->rt_type != RTN_LOCAL))) goto out_rcu_unlock; diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index ec4f762..94213c8 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -463,6 +463,7 @@ static const struct net_device_ops ipgre_netdev_ops = { static void ipgre_tunnel_setup(struct net_device *dev) { dev->netdev_ops = &ipgre_netdev_ops; + dev->type = ARPHRD_IPGRE; ip_tunnel_setup(dev, ipgre_net_id); } @@ -501,7 +502,6 @@ static int ipgre_tunnel_init(struct net_device *dev) memcpy(dev->dev_addr, &iph->saddr, 4); memcpy(dev->broadcast, &iph->daddr, 4); - dev->type = ARPHRD_IPGRE; dev->flags = IFF_NOARP; dev->priv_flags &= ~IFF_XMIT_DST_RELEASE; dev->addr_len = 4; diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index 1a0755f..a52f501 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -101,17 +101,17 @@ int __ip_local_out(struct sk_buff *skb) skb_dst(skb)->dev, dst_output); } -int ip_local_out(struct sk_buff *skb) +int ip_local_out_sk(struct sock *sk, struct sk_buff *skb) { int err; err = __ip_local_out(skb); if (likely(err == 1)) - err = dst_output(skb); + err = dst_output_sk(sk, skb); return err; } -EXPORT_SYMBOL_GPL(ip_local_out); +EXPORT_SYMBOL_GPL(ip_local_out_sk); static inline int ip_select_ttl(struct inet_sock *inet, struct dst_entry *dst) { @@ -211,6 +211,48 @@ static inline int ip_finish_output2(struct sk_buff *skb) return -EINVAL; } +static int ip_finish_output_gso(struct sk_buff *skb) +{ + netdev_features_t features; + struct sk_buff *segs; + int ret = 0; + + /* common case: locally created skb or seglen is <= mtu */ + if (((IPCB(skb)->flags & IPSKB_FORWARDED) == 0) || + skb_gso_network_seglen(skb) <= ip_skb_dst_mtu(skb)) + return ip_finish_output2(skb); + + /* Slowpath - GSO segment length is exceeding the dst MTU. + * + * This can happen in two cases: + * 1) TCP GRO packet, DF bit not set + * 2) skb arrived via virtio-net, we thus get TSO/GSO skbs directly + * from host network stack. + */ + features = netif_skb_features(skb); + segs = skb_gso_segment(skb, features & ~NETIF_F_GSO_MASK); + if (IS_ERR(segs)) { + kfree_skb(skb); + return -ENOMEM; + } + + consume_skb(skb); + + do { + struct sk_buff *nskb = segs->next; + int err; + + segs->next = NULL; + err = ip_fragment(segs, ip_finish_output2); + + if (err && ret == 0) + ret = err; + segs = nskb; + } while (segs); + + return ret; +} + static int ip_finish_output(struct sk_buff *skb) { #if defined(CONFIG_NETFILTER) && defined(CONFIG_XFRM) @@ -220,15 +262,17 @@ static int ip_finish_output(struct sk_buff *skb) return dst_output(skb); } #endif - if (skb->len > ip_skb_dst_mtu(skb) && !skb_is_gso(skb)) + if (skb_is_gso(skb)) + return ip_finish_output_gso(skb); + + if (skb->len > ip_skb_dst_mtu(skb)) return ip_fragment(skb, ip_finish_output2); - else - return ip_finish_output2(skb); + + return ip_finish_output2(skb); } -int ip_mc_output(struct sk_buff *skb) +int ip_mc_output(struct sock *sk, struct sk_buff *skb) { - struct sock *sk = skb->sk; struct rtable *rt = skb_rtable(skb); struct net_device *dev = rt->dst.dev; @@ -287,7 +331,7 @@ int ip_mc_output(struct sk_buff *skb) !(IPCB(skb)->flags & IPSKB_REROUTED)); } -int ip_output(struct sk_buff *skb) +int ip_output(struct sock *sk, struct sk_buff *skb) { struct net_device *dev = skb_dst(skb)->dev; @@ -315,9 +359,9 @@ static void ip_copy_addrs(struct iphdr *iph, const struct flowi4 *fl4) sizeof(fl4->saddr) + sizeof(fl4->daddr)); } -int ip_queue_xmit(struct sk_buff *skb, struct flowi *fl) +/* Note: skb->sk can be different from sk, in case of tunnels */ +int ip_queue_xmit(struct sock *sk, struct sk_buff *skb, struct flowi *fl) { - struct sock *sk = skb->sk; struct inet_sock *inet = inet_sk(sk); struct ip_options_rcu *inet_opt; struct flowi4 *fl4; @@ -389,6 +433,7 @@ packet_routed: ip_select_ident_more(skb, &rt->dst, sk, (skb_shinfo(skb)->gso_segs ?: 1) - 1); + /* TODO : should we use skb->sk here instead of sk ? */ skb->priority = sk->sk_priority; skb->mark = sk->sk_mark; diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c index e77381d..b3f8597 100644 --- a/net/ipv4/ip_tunnel.c +++ b/net/ipv4/ip_tunnel.c @@ -442,6 +442,8 @@ int ip_tunnel_rcv(struct ip_tunnel *tunnel, struct sk_buff *skb, tunnel->i_seqno = ntohl(tpi->seq) + 1; } + skb_reset_network_header(skb); + err = IP_ECN_decapsulate(iph, skb); if (unlikely(err)) { if (log_ecn_error) @@ -670,7 +672,7 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev, return; } - err = iptunnel_xmit(rt, skb, fl4.saddr, fl4.daddr, protocol, + err = iptunnel_xmit(skb->sk, rt, skb, fl4.saddr, fl4.daddr, protocol, tos, ttl, df, !net_eq(tunnel->net, dev_net(dev))); iptunnel_xmit_stats(err, &dev->stats, dev->tstats); @@ -722,19 +724,18 @@ static void ip_tunnel_update(struct ip_tunnel_net *itn, int ip_tunnel_ioctl(struct net_device *dev, struct ip_tunnel_parm *p, int cmd) { int err = 0; - struct ip_tunnel *t; - struct net *net = dev_net(dev); - struct ip_tunnel *tunnel = netdev_priv(dev); - struct ip_tunnel_net *itn = net_generic(net, tunnel->ip_tnl_net_id); + struct ip_tunnel *t = netdev_priv(dev); + struct net *net = t->net; + struct ip_tunnel_net *itn = net_generic(net, t->ip_tnl_net_id); BUG_ON(!itn->fb_tunnel_dev); switch (cmd) { case SIOCGETTUNNEL: - t = NULL; - if (dev == itn->fb_tunnel_dev) + if (dev == itn->fb_tunnel_dev) { t = ip_tunnel_find(itn, p, itn->fb_tunnel_dev->type); - if (t == NULL) - t = netdev_priv(dev); + if (t == NULL) + t = netdev_priv(dev); + } memcpy(p, &t->parms, sizeof(*p)); break; diff --git a/net/ipv4/ip_tunnel_core.c b/net/ipv4/ip_tunnel_core.c index e0c2b1d..bcf206c 100644 --- a/net/ipv4/ip_tunnel_core.c +++ b/net/ipv4/ip_tunnel_core.c @@ -46,7 +46,7 @@ #include <net/netns/generic.h> #include <net/rtnetlink.h> -int iptunnel_xmit(struct rtable *rt, struct sk_buff *skb, +int iptunnel_xmit(struct sock *sk, struct rtable *rt, struct sk_buff *skb, __be32 src, __be32 dst, __u8 proto, __u8 tos, __u8 ttl, __be16 df, bool xnet) { @@ -76,7 +76,7 @@ int iptunnel_xmit(struct rtable *rt, struct sk_buff *skb, iph->ttl = ttl; __ip_select_ident(iph, &rt->dst, (skb_shinfo(skb)->gso_segs ?: 1) - 1); - err = ip_local_out(skb); + err = ip_local_out_sk(sk, skb); if (unlikely(net_xmit_eval(err))) pkt_len = 0; return pkt_len; diff --git a/net/ipv4/ip_vti.c b/net/ipv4/ip_vti.c index d3f64d7..13ef00f 100644 --- a/net/ipv4/ip_vti.c +++ b/net/ipv4/ip_vti.c @@ -340,6 +340,7 @@ static const struct net_device_ops vti_netdev_ops = { static void vti_tunnel_setup(struct net_device *dev) { dev->netdev_ops = &vti_netdev_ops; + dev->type = ARPHRD_TUNNEL; ip_tunnel_setup(dev, vti_net_id); } @@ -351,7 +352,7 @@ static int vti_tunnel_init(struct net_device *dev) memcpy(dev->dev_addr, &iph->saddr, 4); memcpy(dev->broadcast, &iph->daddr, 4); - dev->type = ARPHRD_TUNNEL; + dev->hard_header_len = LL_MAX_HEADER + sizeof(struct iphdr); dev->mtu = ETH_DATA_LEN; dev->flags = IFF_NOARP; dev->iflink = 0; diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c index 28863570..d84dc8d 100644 --- a/net/ipv4/ipmr.c +++ b/net/ipv4/ipmr.c @@ -455,7 +455,7 @@ static netdev_tx_t reg_vif_xmit(struct sk_buff *skb, struct net_device *dev) struct mr_table *mrt; struct flowi4 fl4 = { .flowi4_oif = dev->ifindex, - .flowi4_iif = skb->skb_iif, + .flowi4_iif = skb->skb_iif ? : LOOPBACK_IFINDEX, .flowi4_mark = skb->mark, }; int err; diff --git a/net/ipv4/netfilter/ipt_rpfilter.c b/net/ipv4/netfilter/ipt_rpfilter.c index c49dcd0..4bfaedf 100644 --- a/net/ipv4/netfilter/ipt_rpfilter.c +++ b/net/ipv4/netfilter/ipt_rpfilter.c @@ -89,11 +89,8 @@ static bool rpfilter_mt(const struct sk_buff *skb, struct xt_action_param *par) if (ipv4_is_multicast(iph->daddr)) { if (ipv4_is_zeronet(iph->saddr)) return ipv4_is_local_multicast(iph->daddr) ^ invert; - flow.flowi4_iif = 0; - } else { - flow.flowi4_iif = LOOPBACK_IFINDEX; } - + flow.flowi4_iif = LOOPBACK_IFINDEX; flow.daddr = iph->saddr; flow.saddr = rpfilter_get_saddr(iph->daddr); flow.flowi4_oif = 0; diff --git a/net/ipv4/netfilter/nf_defrag_ipv4.c b/net/ipv4/netfilter/nf_defrag_ipv4.c index 12e13bd..f40f321 100644 --- a/net/ipv4/netfilter/nf_defrag_ipv4.c +++ b/net/ipv4/netfilter/nf_defrag_ipv4.c @@ -22,7 +22,6 @@ #endif #include <net/netfilter/nf_conntrack_zones.h> -/* Returns new sk_buff, or NULL */ static int nf_ct_ipv4_gather_frags(struct sk_buff *skb, u_int32_t user) { int err; @@ -33,8 +32,10 @@ static int nf_ct_ipv4_gather_frags(struct sk_buff *skb, u_int32_t user) err = ip_defrag(skb, user); local_bh_enable(); - if (!err) + if (!err) { ip_send_check(ip_hdr(skb)); + skb->local_df = 1; + } return err; } diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c index f4b19e5..044a0dd 100644 --- a/net/ipv4/ping.c +++ b/net/ipv4/ping.c @@ -236,15 +236,15 @@ exit: static void inet_get_ping_group_range_net(struct net *net, kgid_t *low, kgid_t *high) { - kgid_t *data = net->ipv4.sysctl_ping_group_range; + kgid_t *data = net->ipv4.ping_group_range.range; unsigned int seq; do { - seq = read_seqbegin(&net->ipv4.sysctl_local_ports.lock); + seq = read_seqbegin(&net->ipv4.ping_group_range.lock); *low = data[0]; *high = data[1]; - } while (read_seqretry(&net->ipv4.sysctl_local_ports.lock, seq)); + } while (read_seqretry(&net->ipv4.ping_group_range.lock, seq)); } @@ -252,26 +252,33 @@ int ping_init_sock(struct sock *sk) { struct net *net = sock_net(sk); kgid_t group = current_egid(); - struct group_info *group_info = get_current_groups(); - int i, j, count = group_info->ngroups; + struct group_info *group_info; + int i, j, count; kgid_t low, high; + int ret = 0; inet_get_ping_group_range_net(net, &low, &high); if (gid_lte(low, group) && gid_lte(group, high)) return 0; + group_info = get_current_groups(); + count = group_info->ngroups; for (i = 0; i < group_info->nblocks; i++) { int cp_count = min_t(int, NGROUPS_PER_BLOCK, count); for (j = 0; j < cp_count; j++) { kgid_t gid = group_info->blocks[i][j]; if (gid_lte(low, gid) && gid_lte(gid, high)) - return 0; + goto out_release_group; } count -= cp_count; } - return -EACCES; + ret = -EACCES; + +out_release_group: + put_group_info(group_info); + return ret; } EXPORT_SYMBOL_GPL(ping_init_sock); diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 1be9e99..db1e0da 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -188,7 +188,7 @@ const __u8 ip_tos2prio[16] = { EXPORT_SYMBOL(ip_tos2prio); static DEFINE_PER_CPU(struct rt_cache_stat, rt_cache_stat); -#define RT_CACHE_STAT_INC(field) __this_cpu_inc(rt_cache_stat.field) +#define RT_CACHE_STAT_INC(field) raw_cpu_inc(rt_cache_stat.field) #ifdef CONFIG_PROC_FS static void *rt_cache_seq_start(struct seq_file *seq, loff_t *pos) @@ -1129,7 +1129,7 @@ static void ipv4_link_failure(struct sk_buff *skb) dst_set_expires(&rt->dst, 0); } -static int ip_rt_bug(struct sk_buff *skb) +static int ip_rt_bug(struct sock *sk, struct sk_buff *skb) { pr_debug("%s: %pI4 -> %pI4, %s\n", __func__, &ip_hdr(skb)->saddr, &ip_hdr(skb)->daddr, @@ -1700,8 +1700,7 @@ static int ip_route_input_slow(struct sk_buff *skb, __be32 daddr, __be32 saddr, if (res.type == RTN_LOCAL) { err = fib_validate_source(skb, saddr, daddr, tos, - LOOPBACK_IFINDEX, - dev, in_dev, &itag); + 0, dev, in_dev, &itag); if (err < 0) goto martian_source_keep_err; goto local_input; @@ -2218,7 +2217,7 @@ struct dst_entry *ipv4_blackhole_route(struct net *net, struct dst_entry *dst_or new->__use = 1; new->input = dst_discard; - new->output = dst_discard; + new->output = dst_discard_sk; new->dev = ort->dst.dev; if (new->dev) @@ -2357,7 +2356,7 @@ static int rt_fill_info(struct net *net, __be32 dst, __be32 src, } } else #endif - if (nla_put_u32(skb, RTA_IIF, rt->rt_iif)) + if (nla_put_u32(skb, RTA_IIF, skb->dev->ifindex)) goto nla_put_failure; } diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c index 44eba05..5cde8f2 100644 --- a/net/ipv4/sysctl_net_ipv4.c +++ b/net/ipv4/sysctl_net_ipv4.c @@ -45,10 +45,10 @@ static int ip_ping_group_range_max[] = { GID_T_MAX, GID_T_MAX }; /* Update system visible IP port range */ static void set_local_port_range(struct net *net, int range[2]) { - write_seqlock(&net->ipv4.sysctl_local_ports.lock); - net->ipv4.sysctl_local_ports.range[0] = range[0]; - net->ipv4.sysctl_local_ports.range[1] = range[1]; - write_sequnlock(&net->ipv4.sysctl_local_ports.lock); + write_seqlock(&net->ipv4.ip_local_ports.lock); + net->ipv4.ip_local_ports.range[0] = range[0]; + net->ipv4.ip_local_ports.range[1] = range[1]; + write_sequnlock(&net->ipv4.ip_local_ports.lock); } /* Validate changes from /proc interface. */ @@ -57,7 +57,7 @@ static int ipv4_local_port_range(struct ctl_table *table, int write, size_t *lenp, loff_t *ppos) { struct net *net = - container_of(table->data, struct net, ipv4.sysctl_local_ports.range); + container_of(table->data, struct net, ipv4.ip_local_ports.range); int ret; int range[2]; struct ctl_table tmp = { @@ -87,14 +87,14 @@ static void inet_get_ping_group_range_table(struct ctl_table *table, kgid_t *low { kgid_t *data = table->data; struct net *net = - container_of(table->data, struct net, ipv4.sysctl_ping_group_range); + container_of(table->data, struct net, ipv4.ping_group_range.range); unsigned int seq; do { - seq = read_seqbegin(&net->ipv4.sysctl_local_ports.lock); + seq = read_seqbegin(&net->ipv4.ip_local_ports.lock); *low = data[0]; *high = data[1]; - } while (read_seqretry(&net->ipv4.sysctl_local_ports.lock, seq)); + } while (read_seqretry(&net->ipv4.ip_local_ports.lock, seq)); } /* Update system visible IP port range */ @@ -102,11 +102,11 @@ static void set_ping_group_range(struct ctl_table *table, kgid_t low, kgid_t hig { kgid_t *data = table->data; struct net *net = - container_of(table->data, struct net, ipv4.sysctl_ping_group_range); - write_seqlock(&net->ipv4.sysctl_local_ports.lock); + container_of(table->data, struct net, ipv4.ping_group_range.range); + write_seqlock(&net->ipv4.ip_local_ports.lock); data[0] = low; data[1] = high; - write_sequnlock(&net->ipv4.sysctl_local_ports.lock); + write_sequnlock(&net->ipv4.ip_local_ports.lock); } /* Validate changes from /proc interface. */ @@ -805,7 +805,7 @@ static struct ctl_table ipv4_net_table[] = { }, { .procname = "ping_group_range", - .data = &init_net.ipv4.sysctl_ping_group_range, + .data = &init_net.ipv4.ping_group_range.range, .maxlen = sizeof(gid_t)*2, .mode = 0644, .proc_handler = ipv4_ping_group_range, @@ -819,8 +819,8 @@ static struct ctl_table ipv4_net_table[] = { }, { .procname = "ip_local_port_range", - .maxlen = sizeof(init_net.ipv4.sysctl_local_ports.range), - .data = &init_net.ipv4.sysctl_local_ports.range, + .maxlen = sizeof(init_net.ipv4.ip_local_ports.range), + .data = &init_net.ipv4.ip_local_ports.range, .mode = 0644, .proc_handler = ipv4_local_port_range, }, @@ -858,20 +858,6 @@ static __net_init int ipv4_sysctl_init_net(struct net *net) table[i].data += (void *)net - (void *)&init_net; } - /* - * Sane defaults - nobody may create ping sockets. - * Boot scripts should set this to distro-specific group. - */ - net->ipv4.sysctl_ping_group_range[0] = make_kgid(&init_user_ns, 1); - net->ipv4.sysctl_ping_group_range[1] = make_kgid(&init_user_ns, 0); - - /* - * Set defaults for local port range - */ - seqlock_init(&net->ipv4.sysctl_local_ports.lock); - net->ipv4.sysctl_local_ports.range[0] = 32768; - net->ipv4.sysctl_local_ports.range[1] = 61000; - net->ipv4.ipv4_hdr = register_net_sysctl(net, "net/ipv4", table); if (net->ipv4.ipv4_hdr == NULL) goto err_reg; diff --git a/net/ipv4/tcp_cubic.c b/net/ipv4/tcp_cubic.c index 8bf2245..b4f1b29 100644 --- a/net/ipv4/tcp_cubic.c +++ b/net/ipv4/tcp_cubic.c @@ -409,7 +409,7 @@ static void bictcp_acked(struct sock *sk, u32 cnt, s32 rtt_us) ratio -= ca->delayed_ack >> ACK_RATIO_SHIFT; ratio += cnt; - ca->delayed_ack = min(ratio, ACK_RATIO_LIMIT); + ca->delayed_ack = clamp(ratio, 1U, ACK_RATIO_LIMIT); } /* Some calls are for duplicates without timetamps */ diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index e1661f4..d6b46eb 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -4413,7 +4413,7 @@ queue_and_out: if (eaten > 0) kfree_skb_partial(skb, fragstolen); if (!sock_flag(sk, SOCK_DEAD)) - sk->sk_data_ready(sk, 0); + sk->sk_data_ready(sk); return; } @@ -4914,7 +4914,7 @@ static void tcp_urg(struct sock *sk, struct sk_buff *skb, const struct tcphdr *t BUG(); tp->urg_data = TCP_URG_VALID | tmp; if (!sock_flag(sk, SOCK_DEAD)) - sk->sk_data_ready(sk, 0); + sk->sk_data_ready(sk); } } } @@ -5000,11 +5000,11 @@ static bool tcp_dma_try_early_copy(struct sock *sk, struct sk_buff *skb, (tcp_flag_word(tcp_hdr(skb)) & TCP_FLAG_PSH) || (atomic_read(&sk->sk_rmem_alloc) > (sk->sk_rcvbuf >> 1))) { tp->ucopy.wakeup = 1; - sk->sk_data_ready(sk, 0); + sk->sk_data_ready(sk); } } else if (chunk > 0) { tp->ucopy.wakeup = 1; - sk->sk_data_ready(sk, 0); + sk->sk_data_ready(sk); } out: return copied_early; @@ -5275,7 +5275,7 @@ no_ack: #endif if (eaten) kfree_skb_partial(skb, fragstolen); - sk->sk_data_ready(sk, 0); + sk->sk_data_ready(sk); return; } } diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 6379894..438f3b9 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -1434,7 +1434,7 @@ static int tcp_v4_conn_req_fastopen(struct sock *sk, tp->rcv_nxt = TCP_SKB_CB(skb)->end_seq; tp->syn_data_acked = 1; } - sk->sk_data_ready(sk, 0); + sk->sk_data_ready(sk); bh_unlock_sock(child); sock_put(child); WARN_ON(req->sk == NULL); diff --git a/net/ipv4/tcp_memcontrol.c b/net/ipv4/tcp_memcontrol.c index f7e522c..d4f015a 100644 --- a/net/ipv4/tcp_memcontrol.c +++ b/net/ipv4/tcp_memcontrol.c @@ -103,7 +103,7 @@ static int tcp_update_limit(struct mem_cgroup *memcg, u64 val) } static int tcp_cgroup_write(struct cgroup_subsys_state *css, struct cftype *cft, - const char *buffer) + char *buffer) { struct mem_cgroup *memcg = mem_cgroup_from_css(css); unsigned long long val; @@ -219,7 +219,7 @@ static struct cftype tcp_files[] = { static int __init tcp_memcontrol_init(void) { - WARN_ON(cgroup_add_cftypes(&mem_cgroup_subsys, tcp_files)); + WARN_ON(cgroup_add_cftypes(&memory_cgrp_subsys, tcp_files)); return 0; } __initcall(tcp_memcontrol_init); diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index ca788ad..05c1b15 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -745,7 +745,7 @@ int tcp_child_process(struct sock *parent, struct sock *child, skb->len); /* Wakeup parent, send SIGIO */ if (state == TCP_SYN_RECV && child->sk_state != state) - parent->sk_data_ready(parent, 0); + parent->sk_data_ready(parent); } else { /* Alas, it is possible again, because we do lookup * in main socket hash table and lock on listening diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 699fb10..12d6016 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -981,7 +981,7 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it, TCP_ADD_STATS(sock_net(sk), TCP_MIB_OUTSEGS, tcp_skb_pcount(skb)); - err = icsk->icsk_af_ops->queue_xmit(skb, &inet->cork.fl); + err = icsk->icsk_af_ops->queue_xmit(sk, skb, &inet->cork.fl); if (likely(err <= 0)) return err; @@ -2441,8 +2441,14 @@ int __tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb) err = tcp_transmit_skb(sk, skb, 1, GFP_ATOMIC); } - if (likely(!err)) + if (likely(!err)) { TCP_SKB_CB(skb)->sacked |= TCPCB_EVER_RETRANS; + /* Update global TCP statistics. */ + TCP_INC_STATS(sock_net(sk), TCP_MIB_RETRANSSEGS); + if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_SYN) + NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPSYNRETRANS); + tp->total_retrans++; + } return err; } @@ -2452,12 +2458,6 @@ int tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb) int err = __tcp_retransmit_skb(sk, skb); if (err == 0) { - /* Update global TCP statistics. */ - TCP_INC_STATS(sock_net(sk), TCP_MIB_RETRANSSEGS); - if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_SYN) - NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPSYNRETRANS); - tp->total_retrans++; - #if FASTRETRANS_DEBUG > 0 if (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_RETRANS) { net_dbg_ratelimited("retrans_out leaked\n"); diff --git a/net/ipv4/xfrm4_output.c b/net/ipv4/xfrm4_output.c index f3800bf..186a8ec 100644 --- a/net/ipv4/xfrm4_output.c +++ b/net/ipv4/xfrm4_output.c @@ -94,7 +94,7 @@ static int __xfrm4_output(struct sk_buff *skb) return x->outer_mode->afinfo->output_finish(skb); } -int xfrm4_output(struct sk_buff *skb) +int xfrm4_output(struct sock *sk, struct sk_buff *skb) { return NF_HOOK_COND(NFPROTO_IPV4, NF_INET_POST_ROUTING, skb, NULL, skb_dst(skb)->dev, __xfrm4_output, diff --git a/net/ipv6/inet6_connection_sock.c b/net/ipv6/inet6_connection_sock.c index c913818..d4ade34 100644 --- a/net/ipv6/inet6_connection_sock.c +++ b/net/ipv6/inet6_connection_sock.c @@ -224,9 +224,8 @@ static struct dst_entry *inet6_csk_route_socket(struct sock *sk, return dst; } -int inet6_csk_xmit(struct sk_buff *skb, struct flowi *fl_unused) +int inet6_csk_xmit(struct sock *sk, struct sk_buff *skb, struct flowi *fl_unused) { - struct sock *sk = skb->sk; struct ipv6_pinfo *np = inet6_sk(sk); struct flowi6 fl6; struct dst_entry *dst; diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c index 34e0ded..87891f5 100644 --- a/net/ipv6/ip6_fib.c +++ b/net/ipv6/ip6_fib.c @@ -1459,7 +1459,7 @@ static int fib6_walk_continue(struct fib6_walker_t *w) if (w->skip) { w->skip--; - continue; + goto skip; } err = w->func(w); @@ -1469,6 +1469,7 @@ static int fib6_walk_continue(struct fib6_walker_t *w) w->count++; continue; } +skip: w->state = FWS_U; case FWS_U: if (fn == w->root) diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c index c98338b..9d92146 100644 --- a/net/ipv6/ip6_gre.c +++ b/net/ipv6/ip6_gre.c @@ -1559,6 +1559,15 @@ static int ip6gre_changelink(struct net_device *dev, struct nlattr *tb[], return 0; } +static void ip6gre_dellink(struct net_device *dev, struct list_head *head) +{ + struct net *net = dev_net(dev); + struct ip6gre_net *ign = net_generic(net, ip6gre_net_id); + + if (dev != ign->fb_tunnel_dev) + unregister_netdevice_queue(dev, head); +} + static size_t ip6gre_get_size(const struct net_device *dev) { return @@ -1636,6 +1645,7 @@ static struct rtnl_link_ops ip6gre_link_ops __read_mostly = { .validate = ip6gre_tunnel_validate, .newlink = ip6gre_newlink, .changelink = ip6gre_changelink, + .dellink = ip6gre_dellink, .get_size = ip6gre_get_size, .fill_info = ip6gre_fill_info, }; diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index 3284d61..fbf1156 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -132,7 +132,7 @@ static int ip6_finish_output(struct sk_buff *skb) return ip6_finish_output2(skb); } -int ip6_output(struct sk_buff *skb) +int ip6_output(struct sock *sk, struct sk_buff *skb) { struct net_device *dev = skb_dst(skb)->dev; struct inet6_dev *idev = ip6_dst_idev(skb_dst(skb)); @@ -344,12 +344,16 @@ static unsigned int ip6_dst_mtu_forward(const struct dst_entry *dst) static bool ip6_pkt_too_big(const struct sk_buff *skb, unsigned int mtu) { - if (skb->len <= mtu || skb->local_df) + if (skb->len <= mtu) return false; + /* ipv6 conntrack defrag sets max_frag_size + local_df */ if (IP6CB(skb)->frag_max_size && IP6CB(skb)->frag_max_size > mtu) return true; + if (skb->local_df) + return false; + if (skb_is_gso(skb) && skb_gso_network_seglen(skb) <= mtu) return false; @@ -1225,7 +1229,7 @@ int ip6_append_data(struct sock *sk, int getfrag(void *from, char *to, unsigned int maxnonfragsize, headersize; headersize = sizeof(struct ipv6hdr) + - (opt ? opt->tot_len : 0) + + (opt ? opt->opt_flen + opt->opt_nflen : 0) + (dst_allfrag(&rt->dst) ? sizeof(struct frag_hdr) : 0) + rt->rt6i_nfheader_len; diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c index e1df691..f6a66bb 100644 --- a/net/ipv6/ip6_tunnel.c +++ b/net/ipv6/ip6_tunnel.c @@ -1340,8 +1340,8 @@ ip6_tnl_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) int err = 0; struct ip6_tnl_parm p; struct __ip6_tnl_parm p1; - struct ip6_tnl *t = NULL; - struct net *net = dev_net(dev); + struct ip6_tnl *t = netdev_priv(dev); + struct net *net = t->net; struct ip6_tnl_net *ip6n = net_generic(net, ip6_tnl_net_id); switch (cmd) { @@ -1353,11 +1353,11 @@ ip6_tnl_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) } ip6_tnl_parm_from_user(&p1, &p); t = ip6_tnl_locate(net, &p1, 0); + if (t == NULL) + t = netdev_priv(dev); } else { memset(&p, 0, sizeof(p)); } - if (t == NULL) - t = netdev_priv(dev); ip6_tnl_parm_to_user(&p, &t->parms); if (copy_to_user(ifr->ifr_ifru.ifru_data, &p, sizeof (p))) { err = -EFAULT; @@ -1557,7 +1557,7 @@ static int ip6_tnl_validate(struct nlattr *tb[], struct nlattr *data[]) { u8 proto; - if (!data) + if (!data || !data[IFLA_IPTUN_PROTO]) return 0; proto = nla_get_u8(data[IFLA_IPTUN_PROTO]); diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c index 8737400..8250474 100644 --- a/net/ipv6/ip6mr.c +++ b/net/ipv6/ip6mr.c @@ -700,7 +700,7 @@ static netdev_tx_t reg_vif_xmit(struct sk_buff *skb, struct mr6_table *mrt; struct flowi6 fl6 = { .flowi6_oif = dev->ifindex, - .flowi6_iif = skb->skb_iif, + .flowi6_iif = skb->skb_iif ? : LOOPBACK_IFINDEX, .flowi6_mark = skb->mark, }; int err; @@ -1633,7 +1633,7 @@ struct sock *mroute6_socket(struct net *net, struct sk_buff *skb) { struct mr6_table *mrt; struct flowi6 fl6 = { - .flowi6_iif = skb->skb_iif, + .flowi6_iif = skb->skb_iif ? : LOOPBACK_IFINDEX, .flowi6_oif = skb->dev->ifindex, .flowi6_mark = skb->mark, }; diff --git a/net/ipv6/netfilter.c b/net/ipv6/netfilter.c index 95f3f1d..d38e6a8 100644 --- a/net/ipv6/netfilter.c +++ b/net/ipv6/netfilter.c @@ -30,13 +30,15 @@ int ip6_route_me_harder(struct sk_buff *skb) .daddr = iph->daddr, .saddr = iph->saddr, }; + int err; dst = ip6_route_output(net, skb->sk, &fl6); - if (dst->error) { + err = dst->error; + if (err) { IP6_INC_STATS(net, ip6_dst_idev(dst), IPSTATS_MIB_OUTNOROUTES); LIMIT_NETDEBUG(KERN_DEBUG "ip6_route_me_harder: No more route.\n"); dst_release(dst); - return dst->error; + return err; } /* Drop old route. */ diff --git a/net/ipv6/netfilter/ip6t_rpfilter.c b/net/ipv6/netfilter/ip6t_rpfilter.c index e0983f3..790e0c6 100644 --- a/net/ipv6/netfilter/ip6t_rpfilter.c +++ b/net/ipv6/netfilter/ip6t_rpfilter.c @@ -33,6 +33,7 @@ static bool rpfilter_lookup_reverse6(const struct sk_buff *skb, struct ipv6hdr *iph = ipv6_hdr(skb); bool ret = false; struct flowi6 fl6 = { + .flowi6_iif = LOOPBACK_IFINDEX, .flowlabel = (* (__be32 *) iph) & IPV6_FLOWINFO_MASK, .flowi6_proto = iph->nexthdr, .daddr = iph->saddr, diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 5015c50..004fffb 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -84,9 +84,9 @@ static void ip6_dst_ifdown(struct dst_entry *, static int ip6_dst_gc(struct dst_ops *ops); static int ip6_pkt_discard(struct sk_buff *skb); -static int ip6_pkt_discard_out(struct sk_buff *skb); +static int ip6_pkt_discard_out(struct sock *sk, struct sk_buff *skb); static int ip6_pkt_prohibit(struct sk_buff *skb); -static int ip6_pkt_prohibit_out(struct sk_buff *skb); +static int ip6_pkt_prohibit_out(struct sock *sk, struct sk_buff *skb); static void ip6_link_failure(struct sk_buff *skb); static void ip6_rt_update_pmtu(struct dst_entry *dst, struct sock *sk, struct sk_buff *skb, u32 mtu); @@ -290,7 +290,7 @@ static const struct rt6_info ip6_blk_hole_entry_template = { .obsolete = DST_OBSOLETE_FORCE_CHK, .error = -EINVAL, .input = dst_discard, - .output = dst_discard, + .output = dst_discard_sk, }, .rt6i_flags = (RTF_REJECT | RTF_NONEXTHOP), .rt6i_protocol = RTPROT_KERNEL, @@ -1058,7 +1058,7 @@ struct dst_entry *ip6_blackhole_route(struct net *net, struct dst_entry *dst_ori new->__use = 1; new->input = dst_discard; - new->output = dst_discard; + new->output = dst_discard_sk; if (dst_metrics_read_only(&ort->dst)) new->_metrics = ort->dst._metrics; @@ -1273,6 +1273,7 @@ void ip6_redirect(struct sk_buff *skb, struct net *net, int oif, u32 mark) struct flowi6 fl6; memset(&fl6, 0, sizeof(fl6)); + fl6.flowi6_iif = LOOPBACK_IFINDEX; fl6.flowi6_oif = oif; fl6.flowi6_mark = mark; fl6.daddr = iph->daddr; @@ -1294,6 +1295,7 @@ void ip6_redirect_no_header(struct sk_buff *skb, struct net *net, int oif, struct flowi6 fl6; memset(&fl6, 0, sizeof(fl6)); + fl6.flowi6_iif = LOOPBACK_IFINDEX; fl6.flowi6_oif = oif; fl6.flowi6_mark = mark; fl6.daddr = msg->dest; @@ -1338,7 +1340,7 @@ static unsigned int ip6_mtu(const struct dst_entry *dst) unsigned int mtu = dst_metric_raw(dst, RTAX_MTU); if (mtu) - return mtu; + goto out; mtu = IPV6_MIN_MTU; @@ -1348,7 +1350,8 @@ static unsigned int ip6_mtu(const struct dst_entry *dst) mtu = idev->cnf.mtu6; rcu_read_unlock(); - return mtu; +out: + return min_t(unsigned int, mtu, IP6_MAX_MTU); } static struct dst_entry *icmp6_dst_gc_list; @@ -1576,7 +1579,7 @@ int ip6_route_add(struct fib6_config *cfg) switch (cfg->fc_type) { case RTN_BLACKHOLE: rt->dst.error = -EINVAL; - rt->dst.output = dst_discard; + rt->dst.output = dst_discard_sk; rt->dst.input = dst_discard; break; case RTN_PROHIBIT: @@ -2128,7 +2131,7 @@ static int ip6_pkt_discard(struct sk_buff *skb) return ip6_pkt_drop(skb, ICMPV6_NOROUTE, IPSTATS_MIB_INNOROUTES); } -static int ip6_pkt_discard_out(struct sk_buff *skb) +static int ip6_pkt_discard_out(struct sock *sk, struct sk_buff *skb) { skb->dev = skb_dst(skb)->dev; return ip6_pkt_drop(skb, ICMPV6_NOROUTE, IPSTATS_MIB_OUTNOROUTES); @@ -2139,7 +2142,7 @@ static int ip6_pkt_prohibit(struct sk_buff *skb) return ip6_pkt_drop(skb, ICMPV6_ADM_PROHIBITED, IPSTATS_MIB_INNOROUTES); } -static int ip6_pkt_prohibit_out(struct sk_buff *skb) +static int ip6_pkt_prohibit_out(struct sock *sk, struct sk_buff *skb) { skb->dev = skb_dst(skb)->dev; return ip6_pkt_drop(skb, ICMPV6_ADM_PROHIBITED, IPSTATS_MIB_OUTNOROUTES); diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c index 1693c8d..e5a453c 100644 --- a/net/ipv6/sit.c +++ b/net/ipv6/sit.c @@ -974,8 +974,9 @@ static netdev_tx_t ipip6_tunnel_xmit(struct sk_buff *skb, goto out; } - err = iptunnel_xmit(rt, skb, fl4.saddr, fl4.daddr, IPPROTO_IPV6, tos, - ttl, df, !net_eq(tunnel->net, dev_net(dev))); + err = iptunnel_xmit(skb->sk, rt, skb, fl4.saddr, fl4.daddr, + IPPROTO_IPV6, tos, ttl, df, + !net_eq(tunnel->net, dev_net(dev))); iptunnel_xmit_stats(err, &dev->stats, dev->tstats); return NETDEV_TX_OK; @@ -1126,8 +1127,8 @@ ipip6_tunnel_ioctl (struct net_device *dev, struct ifreq *ifr, int cmd) int err = 0; struct ip_tunnel_parm p; struct ip_tunnel_prl prl; - struct ip_tunnel *t; - struct net *net = dev_net(dev); + struct ip_tunnel *t = netdev_priv(dev); + struct net *net = t->net; struct sit_net *sitn = net_generic(net, sit_net_id); #ifdef CONFIG_IPV6_SIT_6RD struct ip_tunnel_6rd ip6rd; @@ -1138,16 +1139,15 @@ ipip6_tunnel_ioctl (struct net_device *dev, struct ifreq *ifr, int cmd) #ifdef CONFIG_IPV6_SIT_6RD case SIOCGET6RD: #endif - t = NULL; if (dev == sitn->fb_tunnel_dev) { if (copy_from_user(&p, ifr->ifr_ifru.ifru_data, sizeof(p))) { err = -EFAULT; break; } t = ipip6_tunnel_locate(net, &p, 0); + if (t == NULL) + t = netdev_priv(dev); } - if (t == NULL) - t = netdev_priv(dev); err = -EFAULT; if (cmd == SIOCGETTUNNEL) { @@ -1243,9 +1243,6 @@ ipip6_tunnel_ioctl (struct net_device *dev, struct ifreq *ifr, int cmd) err = -EINVAL; if (dev == sitn->fb_tunnel_dev) goto done; - err = -ENOENT; - if (!(t = netdev_priv(dev))) - goto done; err = ipip6_tunnel_get_prl(t, ifr->ifr_ifru.ifru_data); break; @@ -1261,9 +1258,6 @@ ipip6_tunnel_ioctl (struct net_device *dev, struct ifreq *ifr, int cmd) err = -EFAULT; if (copy_from_user(&prl, ifr->ifr_ifru.ifru_data, sizeof(prl))) goto done; - err = -ENOENT; - if (!(t = netdev_priv(dev))) - goto done; switch (cmd) { case SIOCDELPRL: @@ -1291,8 +1285,6 @@ ipip6_tunnel_ioctl (struct net_device *dev, struct ifreq *ifr, int cmd) sizeof(ip6rd))) goto done; - t = netdev_priv(dev); - if (cmd != SIOCDEL6RD) { err = ipip6_tunnel_update_6rd(t, &ip6rd); if (err < 0) diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 5ca56ce..e289830 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -798,7 +798,7 @@ static void tcp_v6_send_response(struct sk_buff *skb, u32 seq, u32 ack, u32 win, __tcp_v6_send_check(buff, &fl6.saddr, &fl6.daddr); fl6.flowi6_proto = IPPROTO_TCP; - if (rt6_need_strict(&fl6.daddr) || !oif) + if (rt6_need_strict(&fl6.daddr) && !oif) fl6.flowi6_oif = inet6_iif(skb); else fl6.flowi6_oif = oif; diff --git a/net/ipv6/xfrm6_output.c b/net/ipv6/xfrm6_output.c index ba62433..b930d08 100644 --- a/net/ipv6/xfrm6_output.c +++ b/net/ipv6/xfrm6_output.c @@ -166,7 +166,7 @@ static int __xfrm6_output(struct sk_buff *skb) return x->outer_mode->afinfo->output_finish(skb); } -int xfrm6_output(struct sk_buff *skb) +int xfrm6_output(struct sock *sk, struct sk_buff *skb) { return NF_HOOK_COND(NFPROTO_IPV6, NF_INET_POST_ROUTING, skb, NULL, skb_dst(skb)->dev, __xfrm6_output, diff --git a/net/iucv/af_iucv.c b/net/iucv/af_iucv.c index a5e0311..8c9d730 100644 --- a/net/iucv/af_iucv.c +++ b/net/iucv/af_iucv.c @@ -1757,7 +1757,7 @@ static int iucv_callback_connreq(struct iucv_path *path, /* Wake up accept */ nsk->sk_state = IUCV_CONNECTED; - sk->sk_data_ready(sk, 1); + sk->sk_data_ready(sk); err = 0; fail: bh_unlock_sock(sk); @@ -1830,7 +1830,7 @@ static void iucv_callback_txdone(struct iucv_path *path, spin_lock_irqsave(&list->lock, flags); while (list_skb != (struct sk_buff *)list) { - if (msg->tag != IUCV_SKB_CB(list_skb)->tag) { + if (msg->tag == IUCV_SKB_CB(list_skb)->tag) { this = list_skb; break; } @@ -1968,7 +1968,7 @@ static int afiucv_hs_callback_syn(struct sock *sk, struct sk_buff *skb) if (!err) { iucv_accept_enqueue(sk, nsk); nsk->sk_state = IUCV_CONNECTED; - sk->sk_data_ready(sk, 1); + sk->sk_data_ready(sk); } else iucv_sock_kill(nsk); bh_unlock_sock(sk); diff --git a/net/iucv/iucv.c b/net/iucv/iucv.c index cd5b8ec..da78793 100644 --- a/net/iucv/iucv.c +++ b/net/iucv/iucv.c @@ -621,6 +621,42 @@ static void iucv_disable(void) put_online_cpus(); } +static void free_iucv_data(int cpu) +{ + kfree(iucv_param_irq[cpu]); + iucv_param_irq[cpu] = NULL; + kfree(iucv_param[cpu]); + iucv_param[cpu] = NULL; + kfree(iucv_irq_data[cpu]); + iucv_irq_data[cpu] = NULL; +} + +static int alloc_iucv_data(int cpu) +{ + /* Note: GFP_DMA used to get memory below 2G */ + iucv_irq_data[cpu] = kmalloc_node(sizeof(struct iucv_irq_data), + GFP_KERNEL|GFP_DMA, cpu_to_node(cpu)); + if (!iucv_irq_data[cpu]) + goto out_free; + + /* Allocate parameter blocks. */ + iucv_param[cpu] = kmalloc_node(sizeof(union iucv_param), + GFP_KERNEL|GFP_DMA, cpu_to_node(cpu)); + if (!iucv_param[cpu]) + goto out_free; + + iucv_param_irq[cpu] = kmalloc_node(sizeof(union iucv_param), + GFP_KERNEL|GFP_DMA, cpu_to_node(cpu)); + if (!iucv_param_irq[cpu]) + goto out_free; + + return 0; + +out_free: + free_iucv_data(cpu); + return -ENOMEM; +} + static int iucv_cpu_notify(struct notifier_block *self, unsigned long action, void *hcpu) { @@ -630,38 +666,14 @@ static int iucv_cpu_notify(struct notifier_block *self, switch (action) { case CPU_UP_PREPARE: case CPU_UP_PREPARE_FROZEN: - iucv_irq_data[cpu] = kmalloc_node(sizeof(struct iucv_irq_data), - GFP_KERNEL|GFP_DMA, cpu_to_node(cpu)); - if (!iucv_irq_data[cpu]) - return notifier_from_errno(-ENOMEM); - - iucv_param[cpu] = kmalloc_node(sizeof(union iucv_param), - GFP_KERNEL|GFP_DMA, cpu_to_node(cpu)); - if (!iucv_param[cpu]) { - kfree(iucv_irq_data[cpu]); - iucv_irq_data[cpu] = NULL; + if (alloc_iucv_data(cpu)) return notifier_from_errno(-ENOMEM); - } - iucv_param_irq[cpu] = kmalloc_node(sizeof(union iucv_param), - GFP_KERNEL|GFP_DMA, cpu_to_node(cpu)); - if (!iucv_param_irq[cpu]) { - kfree(iucv_param[cpu]); - iucv_param[cpu] = NULL; - kfree(iucv_irq_data[cpu]); - iucv_irq_data[cpu] = NULL; - return notifier_from_errno(-ENOMEM); - } break; case CPU_UP_CANCELED: case CPU_UP_CANCELED_FROZEN: case CPU_DEAD: case CPU_DEAD_FROZEN: - kfree(iucv_param_irq[cpu]); - iucv_param_irq[cpu] = NULL; - kfree(iucv_param[cpu]); - iucv_param[cpu] = NULL; - kfree(iucv_irq_data[cpu]); - iucv_irq_data[cpu] = NULL; + free_iucv_data(cpu); break; case CPU_ONLINE: case CPU_ONLINE_FROZEN: @@ -2016,7 +2028,7 @@ static int __init iucv_init(void) rc = iucv_query_maxconn(); if (rc) goto out_ctl; - rc = register_external_interrupt(0x4000, iucv_external_interrupt); + rc = register_external_irq(EXT_IRQ_IUCV, iucv_external_interrupt); if (rc) goto out_ctl; iucv_root = root_device_register("iucv"); @@ -2025,33 +2037,20 @@ static int __init iucv_init(void) goto out_int; } - for_each_online_cpu(cpu) { - /* Note: GFP_DMA used to get memory below 2G */ - iucv_irq_data[cpu] = kmalloc_node(sizeof(struct iucv_irq_data), - GFP_KERNEL|GFP_DMA, cpu_to_node(cpu)); - if (!iucv_irq_data[cpu]) { - rc = -ENOMEM; - goto out_free; - } + cpu_notifier_register_begin(); - /* Allocate parameter blocks. */ - iucv_param[cpu] = kmalloc_node(sizeof(union iucv_param), - GFP_KERNEL|GFP_DMA, cpu_to_node(cpu)); - if (!iucv_param[cpu]) { - rc = -ENOMEM; - goto out_free; - } - iucv_param_irq[cpu] = kmalloc_node(sizeof(union iucv_param), - GFP_KERNEL|GFP_DMA, cpu_to_node(cpu)); - if (!iucv_param_irq[cpu]) { + for_each_online_cpu(cpu) { + if (alloc_iucv_data(cpu)) { rc = -ENOMEM; goto out_free; } - } - rc = register_hotcpu_notifier(&iucv_cpu_notifier); + rc = __register_hotcpu_notifier(&iucv_cpu_notifier); if (rc) goto out_free; + + cpu_notifier_register_done(); + rc = register_reboot_notifier(&iucv_reboot_notifier); if (rc) goto out_cpu; @@ -2069,19 +2068,17 @@ static int __init iucv_init(void) out_reboot: unregister_reboot_notifier(&iucv_reboot_notifier); out_cpu: - unregister_hotcpu_notifier(&iucv_cpu_notifier); + cpu_notifier_register_begin(); + __unregister_hotcpu_notifier(&iucv_cpu_notifier); out_free: - for_each_possible_cpu(cpu) { - kfree(iucv_param_irq[cpu]); - iucv_param_irq[cpu] = NULL; - kfree(iucv_param[cpu]); - iucv_param[cpu] = NULL; - kfree(iucv_irq_data[cpu]); - iucv_irq_data[cpu] = NULL; - } + for_each_possible_cpu(cpu) + free_iucv_data(cpu); + + cpu_notifier_register_done(); + root_device_unregister(iucv_root); out_int: - unregister_external_interrupt(0x4000, iucv_external_interrupt); + unregister_external_irq(EXT_IRQ_IUCV, iucv_external_interrupt); out_ctl: ctl_clear_bit(0, 1); out: @@ -2105,18 +2102,14 @@ static void __exit iucv_exit(void) kfree(p); spin_unlock_irq(&iucv_queue_lock); unregister_reboot_notifier(&iucv_reboot_notifier); - unregister_hotcpu_notifier(&iucv_cpu_notifier); - for_each_possible_cpu(cpu) { - kfree(iucv_param_irq[cpu]); - iucv_param_irq[cpu] = NULL; - kfree(iucv_param[cpu]); - iucv_param[cpu] = NULL; - kfree(iucv_irq_data[cpu]); - iucv_irq_data[cpu] = NULL; - } + cpu_notifier_register_begin(); + __unregister_hotcpu_notifier(&iucv_cpu_notifier); + for_each_possible_cpu(cpu) + free_iucv_data(cpu); + cpu_notifier_register_done(); root_device_unregister(iucv_root); bus_unregister(&iucv_bus); - unregister_external_interrupt(0x4000, iucv_external_interrupt); + unregister_external_irq(EXT_IRQ_IUCV, iucv_external_interrupt); } subsys_initcall(iucv_init); diff --git a/net/key/af_key.c b/net/key/af_key.c index e72589a..f3c8307 100644 --- a/net/key/af_key.c +++ b/net/key/af_key.c @@ -205,7 +205,7 @@ static int pfkey_broadcast_one(struct sk_buff *skb, struct sk_buff **skb2, if (atomic_read(&sk->sk_rmem_alloc) <= sk->sk_rcvbuf) { skb_set_owner_r(*skb2, sk); skb_queue_tail(&sk->sk_receive_queue, *skb2); - sk->sk_data_ready(sk, (*skb2)->len); + sk->sk_data_ready(sk); *skb2 = NULL; err = 0; } diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c index 47f7a54..a4e37d7 100644 --- a/net/l2tp/l2tp_core.c +++ b/net/l2tp/l2tp_core.c @@ -1131,10 +1131,10 @@ static int l2tp_xmit_core(struct l2tp_session *session, struct sk_buff *skb, skb->local_df = 1; #if IS_ENABLED(CONFIG_IPV6) if (tunnel->sock->sk_family == PF_INET6 && !tunnel->v4mapped) - error = inet6_csk_xmit(skb, NULL); + error = inet6_csk_xmit(tunnel->sock, skb, NULL); else #endif - error = ip_queue_xmit(skb, fl); + error = ip_queue_xmit(tunnel->sock, skb, fl); /* Update stats */ if (error >= 0) { diff --git a/net/l2tp/l2tp_ip.c b/net/l2tp/l2tp_ip.c index 0b44d85..3397fe6 100644 --- a/net/l2tp/l2tp_ip.c +++ b/net/l2tp/l2tp_ip.c @@ -487,7 +487,7 @@ static int l2tp_ip_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *m xmit: /* Queue the packet to IP for output */ - rc = ip_queue_xmit(skb, &inet->cork.fl); + rc = ip_queue_xmit(sk, skb, &inet->cork.fl); rcu_read_unlock(); error: diff --git a/net/l2tp/l2tp_ppp.c b/net/l2tp/l2tp_ppp.c index d276e2d..950909f 100644 --- a/net/l2tp/l2tp_ppp.c +++ b/net/l2tp/l2tp_ppp.c @@ -753,9 +753,9 @@ static int pppol2tp_connect(struct socket *sock, struct sockaddr *uservaddr, session->deref = pppol2tp_session_sock_put; /* If PMTU discovery was enabled, use the MTU that was discovered */ - dst = sk_dst_get(sk); + dst = sk_dst_get(tunnel->sock); if (dst != NULL) { - u32 pmtu = dst_mtu(__sk_dst_get(sk)); + u32 pmtu = dst_mtu(__sk_dst_get(tunnel->sock)); if (pmtu != 0) session->mtu = session->mru = pmtu - PPPOL2TP_HEADER_OVERHEAD; diff --git a/net/mac80211/chan.c b/net/mac80211/chan.c index bd1fd8e..75b5dd2 100644 --- a/net/mac80211/chan.c +++ b/net/mac80211/chan.c @@ -249,7 +249,7 @@ ieee80211_new_chanctx(struct ieee80211_local *local, if (!local->use_chanctx) { local->_oper_chandef = *chandef; - ieee80211_hw_config(local, 0); + ieee80211_hw_config(local, IEEE80211_CONF_CHANGE_CHANNEL); } else { err = drv_add_chanctx(local, ctx); if (err) { @@ -286,7 +286,7 @@ static void ieee80211_free_chanctx(struct ieee80211_local *local, check_single_channel = true; local->hw.conf.radar_enabled = false; - ieee80211_hw_config(local, 0); + ieee80211_hw_config(local, IEEE80211_CONF_CHANGE_CHANNEL); } else { drv_remove_chanctx(local, ctx); } @@ -492,6 +492,13 @@ void ieee80211_recalc_smps_chanctx(struct ieee80211_local *local, rx_chains_static = max(rx_chains_static, needed_static); rx_chains_dynamic = max(rx_chains_dynamic, needed_dynamic); } + + /* Disable SMPS for the monitor interface */ + sdata = rcu_dereference(local->monitor_sdata); + if (sdata && + rcu_access_pointer(sdata->vif.chanctx_conf) == &chanctx->conf) + rx_chains_dynamic = rx_chains_static = local->rx_chains; + rcu_read_unlock(); if (!local->use_chanctx) { diff --git a/net/mac80211/main.c b/net/mac80211/main.c index b055f6a5..4c1bf61 100644 --- a/net/mac80211/main.c +++ b/net/mac80211/main.c @@ -148,6 +148,8 @@ static u32 ieee80211_hw_conf_chan(struct ieee80211_local *local) list_for_each_entry_rcu(sdata, &local->interfaces, list) { if (!rcu_access_pointer(sdata->vif.chanctx_conf)) continue; + if (sdata->vif.type == NL80211_IFTYPE_AP_VLAN) + continue; power = min(power, sdata->vif.bss_conf.txpower); } rcu_read_unlock(); @@ -199,7 +201,7 @@ void ieee80211_bss_info_change_notify(struct ieee80211_sub_if_data *sdata, { struct ieee80211_local *local = sdata->local; - if (!changed) + if (!changed || sdata->vif.type == NL80211_IFTYPE_AP_VLAN) return; drv_bss_info_changed(local, sdata, &sdata->vif.bss_conf, changed); diff --git a/net/mac80211/offchannel.c b/net/mac80211/offchannel.c index 0c2a294..6fb3855 100644 --- a/net/mac80211/offchannel.c +++ b/net/mac80211/offchannel.c @@ -355,6 +355,7 @@ void ieee80211_sw_roc_work(struct work_struct *work) struct ieee80211_roc_work *dep; /* start this ROC */ + ieee80211_offchannel_stop_vifs(local); /* switch channel etc */ ieee80211_recalc_idle(local); diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c index 216c45b..2b608b2 100644 --- a/net/mac80211/rx.c +++ b/net/mac80211/rx.c @@ -1231,7 +1231,8 @@ ieee80211_rx_h_sta_process(struct ieee80211_rx_data *rx) if (ether_addr_equal(bssid, rx->sdata->u.ibss.bssid) && test_sta_flag(sta, WLAN_STA_AUTHORIZED)) { sta->last_rx = jiffies; - if (ieee80211_is_data(hdr->frame_control)) { + if (ieee80211_is_data(hdr->frame_control) && + !is_multicast_ether_addr(hdr->addr1)) { sta->last_rx_rate_idx = status->rate_idx; sta->last_rx_rate_flag = status->flag; sta->last_rx_rate_vht_flag = status->vht_flag; diff --git a/net/mac80211/sta_info.c b/net/mac80211/sta_info.c index 137a192..847d92f 100644 --- a/net/mac80211/sta_info.c +++ b/net/mac80211/sta_info.c @@ -1148,7 +1148,8 @@ void ieee80211_sta_ps_deliver_wakeup(struct sta_info *sta) atomic_dec(&ps->num_sta_ps); /* This station just woke up and isn't aware of our SMPS state */ - if (!ieee80211_smps_is_restrictive(sta->known_smps_mode, + if (!ieee80211_vif_is_mesh(&sdata->vif) && + !ieee80211_smps_is_restrictive(sta->known_smps_mode, sdata->smps_mode) && sta->known_smps_mode != sdata->bss->req_smps && sta_info_tx_streams(sta) != 1) { diff --git a/net/mac80211/status.c b/net/mac80211/status.c index e6e574a..60cb7a6 100644 --- a/net/mac80211/status.c +++ b/net/mac80211/status.c @@ -314,10 +314,9 @@ ieee80211_add_tx_radiotap_header(struct ieee80211_local *local, !is_multicast_ether_addr(hdr->addr1)) txflags |= IEEE80211_RADIOTAP_F_TX_FAIL; - if ((info->status.rates[0].flags & IEEE80211_TX_RC_USE_RTS_CTS) || - (info->status.rates[0].flags & IEEE80211_TX_RC_USE_CTS_PROTECT)) + if (info->status.rates[0].flags & IEEE80211_TX_RC_USE_CTS_PROTECT) txflags |= IEEE80211_RADIOTAP_F_TX_CTS; - else if (info->status.rates[0].flags & IEEE80211_TX_RC_USE_RTS_CTS) + if (info->status.rates[0].flags & IEEE80211_TX_RC_USE_RTS_CTS) txflags |= IEEE80211_RADIOTAP_F_TX_RTS; put_unaligned_le16(txflags, pos); @@ -618,6 +617,7 @@ void ieee80211_tx_status(struct ieee80211_hw *hw, struct sk_buff *skb) sta, true, acked); if ((local->hw.flags & IEEE80211_HW_HAS_RATE_CONTROL) && + (ieee80211_is_data(hdr->frame_control)) && (rates_idx != -1)) sta->last_tx_rate = info->status.rates[rates_idx]; diff --git a/net/mac80211/util.c b/net/mac80211/util.c index 275c94f..3c36583 100644 --- a/net/mac80211/util.c +++ b/net/mac80211/util.c @@ -1780,7 +1780,7 @@ int ieee80211_reconfig(struct ieee80211_local *local) mutex_unlock(&local->mtx); if (sched_scan_stopped) - cfg80211_sched_scan_stopped(local->hw.wiphy); + cfg80211_sched_scan_stopped_rtnl(local->hw.wiphy); /* * If this is for hw restart things are still running. diff --git a/net/mac802154/mib.c b/net/mac802154/mib.c index 153bd1d..f0991f2 100644 --- a/net/mac802154/mib.c +++ b/net/mac802154/mib.c @@ -26,7 +26,6 @@ #include <net/mac802154.h> #include <net/ieee802154_netdev.h> #include <net/wpan-phy.h> -#include <net/ieee802154_netdev.h> #include "mac802154.h" diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index 6dba48e..75421f2 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -1795,6 +1795,7 @@ int nf_conntrack_init_net(struct net *net) int cpu; atomic_set(&net->ct.count, 0); + seqcount_init(&net->ct.generation); net->ct.pcpu_lists = alloc_percpu(struct ct_pcpu); if (!net->ct.pcpu_lists) diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c index ccc46fa..5857963 100644 --- a/net/netfilter/nf_conntrack_netlink.c +++ b/net/netfilter/nf_conntrack_netlink.c @@ -1336,6 +1336,9 @@ ctnetlink_setup_nat(struct nf_conn *ct, const struct nlattr * const cda[]) #ifdef CONFIG_NF_NAT_NEEDED int ret; + if (!cda[CTA_NAT_DST] && !cda[CTA_NAT_SRC]) + return 0; + ret = ctnetlink_parse_nat_setup(ct, NF_NAT_MANIP_DST, cda[CTA_NAT_DST]); if (ret < 0) diff --git a/net/netfilter/nf_conntrack_pptp.c b/net/netfilter/nf_conntrack_pptp.c index 7bd03de..825c3e3 100644 --- a/net/netfilter/nf_conntrack_pptp.c +++ b/net/netfilter/nf_conntrack_pptp.c @@ -605,32 +605,14 @@ static struct nf_conntrack_helper pptp __read_mostly = { .expect_policy = &pptp_exp_policy, }; -static void nf_conntrack_pptp_net_exit(struct net *net) -{ - nf_ct_gre_keymap_flush(net); -} - -static struct pernet_operations nf_conntrack_pptp_net_ops = { - .exit = nf_conntrack_pptp_net_exit, -}; - static int __init nf_conntrack_pptp_init(void) { - int rv; - - rv = nf_conntrack_helper_register(&pptp); - if (rv < 0) - return rv; - rv = register_pernet_subsys(&nf_conntrack_pptp_net_ops); - if (rv < 0) - nf_conntrack_helper_unregister(&pptp); - return rv; + return nf_conntrack_helper_register(&pptp); } static void __exit nf_conntrack_pptp_fini(void) { nf_conntrack_helper_unregister(&pptp); - unregister_pernet_subsys(&nf_conntrack_pptp_net_ops); } module_init(nf_conntrack_pptp_init); diff --git a/net/netfilter/nf_conntrack_proto_gre.c b/net/netfilter/nf_conntrack_proto_gre.c index 9d9c0da..d566573 100644 --- a/net/netfilter/nf_conntrack_proto_gre.c +++ b/net/netfilter/nf_conntrack_proto_gre.c @@ -66,7 +66,7 @@ static inline struct netns_proto_gre *gre_pernet(struct net *net) return net_generic(net, proto_gre_net_id); } -void nf_ct_gre_keymap_flush(struct net *net) +static void nf_ct_gre_keymap_flush(struct net *net) { struct netns_proto_gre *net_gre = gre_pernet(net); struct nf_ct_gre_keymap *km, *tmp; @@ -78,7 +78,6 @@ void nf_ct_gre_keymap_flush(struct net *net) } write_unlock_bh(&net_gre->keymap_lock); } -EXPORT_SYMBOL(nf_ct_gre_keymap_flush); static inline int gre_key_cmpfn(const struct nf_ct_gre_keymap *km, const struct nf_conntrack_tuple *t) diff --git a/net/netfilter/nf_tables_core.c b/net/netfilter/nf_tables_core.c index 90998a6..8041053 100644 --- a/net/netfilter/nf_tables_core.c +++ b/net/netfilter/nf_tables_core.c @@ -25,9 +25,8 @@ static void nft_cmp_fast_eval(const struct nft_expr *expr, struct nft_data data[NFT_REG_MAX + 1]) { const struct nft_cmp_fast_expr *priv = nft_expr_priv(expr); - u32 mask; + u32 mask = nft_cmp_fast_mask(priv->len); - mask = ~0U >> (sizeof(priv->data) * BITS_PER_BYTE - priv->len); if ((data[priv->sreg].data[0] & mask) == priv->data) return; data[NFT_REG_VERDICT].verdict = NFT_BREAK; diff --git a/net/netfilter/nfnetlink.c b/net/netfilter/nfnetlink.c index e8138da..23ef77c 100644 --- a/net/netfilter/nfnetlink.c +++ b/net/netfilter/nfnetlink.c @@ -256,15 +256,15 @@ replay: #endif { nfnl_unlock(subsys_id); - kfree_skb(nskb); - return netlink_ack(skb, nlh, -EOPNOTSUPP); + netlink_ack(skb, nlh, -EOPNOTSUPP); + return kfree_skb(nskb); } } if (!ss->commit || !ss->abort) { nfnl_unlock(subsys_id); - kfree_skb(nskb); - return netlink_ack(skb, nlh, -EOPNOTSUPP); + netlink_ack(skb, nlh, -EOPNOTSUPP); + return kfree_skb(skb); } while (skb->len >= nlmsg_total_size(0)) { @@ -368,14 +368,13 @@ done: static void nfnetlink_rcv(struct sk_buff *skb) { struct nlmsghdr *nlh = nlmsg_hdr(skb); - struct net *net = sock_net(skb->sk); int msglen; if (nlh->nlmsg_len < NLMSG_HDRLEN || skb->len < nlh->nlmsg_len) return; - if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) { + if (!netlink_net_capable(skb, CAP_NET_ADMIN)) { netlink_ack(skb, nlh, -EPERM); return; } diff --git a/net/netfilter/nft_cmp.c b/net/netfilter/nft_cmp.c index 954925d..e2b3f51 100644 --- a/net/netfilter/nft_cmp.c +++ b/net/netfilter/nft_cmp.c @@ -128,7 +128,7 @@ static int nft_cmp_fast_init(const struct nft_ctx *ctx, BUG_ON(err < 0); desc.len *= BITS_PER_BYTE; - mask = ~0U >> (sizeof(priv->data) * BITS_PER_BYTE - desc.len); + mask = nft_cmp_fast_mask(desc.len); priv->data = data.data[0] & mask; priv->len = desc.len; return 0; diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index c2d585c..81dca96 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -1360,7 +1360,72 @@ retry: return err; } -static inline int netlink_capable(const struct socket *sock, unsigned int flag) +/** + * __netlink_ns_capable - General netlink message capability test + * @nsp: NETLINK_CB of the socket buffer holding a netlink command from userspace. + * @user_ns: The user namespace of the capability to use + * @cap: The capability to use + * + * Test to see if the opener of the socket we received the message + * from had when the netlink socket was created and the sender of the + * message has has the capability @cap in the user namespace @user_ns. + */ +bool __netlink_ns_capable(const struct netlink_skb_parms *nsp, + struct user_namespace *user_ns, int cap) +{ + return sk_ns_capable(nsp->sk, user_ns, cap); +} +EXPORT_SYMBOL(__netlink_ns_capable); + +/** + * netlink_ns_capable - General netlink message capability test + * @skb: socket buffer holding a netlink command from userspace + * @user_ns: The user namespace of the capability to use + * @cap: The capability to use + * + * Test to see if the opener of the socket we received the message + * from had when the netlink socket was created and the sender of the + * message has has the capability @cap in the user namespace @user_ns. + */ +bool netlink_ns_capable(const struct sk_buff *skb, + struct user_namespace *user_ns, int cap) +{ + return __netlink_ns_capable(&NETLINK_CB(skb), user_ns, cap); +} +EXPORT_SYMBOL(netlink_ns_capable); + +/** + * netlink_capable - Netlink global message capability test + * @skb: socket buffer holding a netlink command from userspace + * @cap: The capability to use + * + * Test to see if the opener of the socket we received the message + * from had when the netlink socket was created and the sender of the + * message has has the capability @cap in all user namespaces. + */ +bool netlink_capable(const struct sk_buff *skb, int cap) +{ + return netlink_ns_capable(skb, &init_user_ns, cap); +} +EXPORT_SYMBOL(netlink_capable); + +/** + * netlink_net_capable - Netlink network namespace message capability test + * @skb: socket buffer holding a netlink command from userspace + * @cap: The capability to use + * + * Test to see if the opener of the socket we received the message + * from had when the netlink socket was created and the sender of the + * message has has the capability @cap over the network namespace of + * the socket we received the message from. + */ +bool netlink_net_capable(const struct sk_buff *skb, int cap) +{ + return netlink_ns_capable(skb, sock_net(skb->sk)->user_ns, cap); +} +EXPORT_SYMBOL(netlink_net_capable); + +static inline int netlink_allowed(const struct socket *sock, unsigned int flag) { return (nl_table[sock->sk->sk_protocol].flags & flag) || ns_capable(sock_net(sock->sk)->user_ns, CAP_NET_ADMIN); @@ -1428,7 +1493,7 @@ static int netlink_bind(struct socket *sock, struct sockaddr *addr, /* Only superuser is allowed to listen multicasts */ if (nladdr->nl_groups) { - if (!netlink_capable(sock, NL_CFG_F_NONROOT_RECV)) + if (!netlink_allowed(sock, NL_CFG_F_NONROOT_RECV)) return -EPERM; err = netlink_realloc_groups(sk); if (err) @@ -1490,7 +1555,7 @@ static int netlink_connect(struct socket *sock, struct sockaddr *addr, return -EINVAL; if ((nladdr->nl_groups || nladdr->nl_pid) && - !netlink_capable(sock, NL_CFG_F_NONROOT_SEND)) + !netlink_allowed(sock, NL_CFG_F_NONROOT_SEND)) return -EPERM; if (!nlk->portid) @@ -1653,7 +1718,7 @@ static int __netlink_sendskb(struct sock *sk, struct sk_buff *skb) else #endif /* CONFIG_NETLINK_MMAP */ skb_queue_tail(&sk->sk_receive_queue, skb); - sk->sk_data_ready(sk, len); + sk->sk_data_ready(sk); return len; } @@ -2096,7 +2161,7 @@ static int netlink_setsockopt(struct socket *sock, int level, int optname, break; case NETLINK_ADD_MEMBERSHIP: case NETLINK_DROP_MEMBERSHIP: { - if (!netlink_capable(sock, NL_CFG_F_NONROOT_RECV)) + if (!netlink_allowed(sock, NL_CFG_F_NONROOT_RECV)) return -EPERM; err = netlink_realloc_groups(sk); if (err) @@ -2247,7 +2312,7 @@ static int netlink_sendmsg(struct kiocb *kiocb, struct socket *sock, dst_group = ffs(addr->nl_groups); err = -EPERM; if ((dst_group || dst_portid) && - !netlink_capable(sock, NL_CFG_F_NONROOT_SEND)) + !netlink_allowed(sock, NL_CFG_F_NONROOT_SEND)) goto out; } else { dst_portid = nlk->dst_portid; @@ -2394,7 +2459,7 @@ out: return err ? : copied; } -static void netlink_data_ready(struct sock *sk, int len) +static void netlink_data_ready(struct sock *sk) { BUG(); } diff --git a/net/netlink/genetlink.c b/net/netlink/genetlink.c index b1dcdb9..a3ba3ca 100644 --- a/net/netlink/genetlink.c +++ b/net/netlink/genetlink.c @@ -561,7 +561,7 @@ static int genl_family_rcv_msg(struct genl_family *family, return -EOPNOTSUPP; if ((ops->flags & GENL_ADMIN_PERM) && - !capable(CAP_NET_ADMIN)) + !netlink_capable(skb, CAP_NET_ADMIN)) return -EPERM; if ((nlh->nlmsg_flags & NLM_F_DUMP) == NLM_F_DUMP) { diff --git a/net/netrom/af_netrom.c b/net/netrom/af_netrom.c index b74aa07..ede50d1 100644 --- a/net/netrom/af_netrom.c +++ b/net/netrom/af_netrom.c @@ -1011,7 +1011,7 @@ int nr_rx_frame(struct sk_buff *skb, struct net_device *dev) skb_queue_head(&sk->sk_receive_queue, skb); if (!sock_flag(sk, SOCK_DEAD)) - sk->sk_data_ready(sk, skb->len); + sk->sk_data_ready(sk); bh_unlock_sock(sk); diff --git a/net/nfc/llcp_core.c b/net/nfc/llcp_core.c index b486f12..b467195 100644 --- a/net/nfc/llcp_core.c +++ b/net/nfc/llcp_core.c @@ -976,7 +976,7 @@ static void nfc_llcp_recv_connect(struct nfc_llcp_local *local, new_sk->sk_state = LLCP_CONNECTED; /* Wake the listening processes */ - parent->sk_data_ready(parent, 0); + parent->sk_data_ready(parent); /* Send CC */ nfc_llcp_send_cc(new_sock); diff --git a/net/openvswitch/vport-gre.c b/net/openvswitch/vport-gre.c index a3d6951..ebb6e24 100644 --- a/net/openvswitch/vport-gre.c +++ b/net/openvswitch/vport-gre.c @@ -174,7 +174,7 @@ static int gre_tnl_send(struct vport *vport, struct sk_buff *skb) skb->local_df = 1; - return iptunnel_xmit(rt, skb, fl.saddr, + return iptunnel_xmit(skb->sk, rt, skb, fl.saddr, OVS_CB(skb)->tun_key->ipv4_dst, IPPROTO_GRE, OVS_CB(skb)->tun_key->ipv4_tos, OVS_CB(skb)->tun_key->ipv4_ttl, df, false); diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index 72e0c71..b85c67c 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -1848,7 +1848,7 @@ static int packet_rcv(struct sk_buff *skb, struct net_device *dev, skb->dropcount = atomic_read(&sk->sk_drops); __skb_queue_tail(&sk->sk_receive_queue, skb); spin_unlock(&sk->sk_receive_queue.lock); - sk->sk_data_ready(sk, skb->len); + sk->sk_data_ready(sk); return 0; drop_n_acct: @@ -2054,7 +2054,7 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev, else prb_clear_blk_fill_status(&po->rx_ring); - sk->sk_data_ready(sk, 0); + sk->sk_data_ready(sk); drop_n_restore: if (skb_head != skb->data && skb_shared(skb)) { @@ -2069,7 +2069,7 @@ ring_is_full: po->stats.stats1.tp_drops++; spin_unlock(&sk->sk_receive_queue.lock); - sk->sk_data_ready(sk, 0); + sk->sk_data_ready(sk); kfree_skb(copy_skb); goto drop_n_restore; } diff --git a/net/packet/diag.c b/net/packet/diag.c index 533ce4f..92f2c71 100644 --- a/net/packet/diag.c +++ b/net/packet/diag.c @@ -128,6 +128,7 @@ static int pdiag_put_fanout(struct packet_sock *po, struct sk_buff *nlskb) static int sk_diag_fill(struct sock *sk, struct sk_buff *skb, struct packet_diag_req *req, + bool may_report_filterinfo, struct user_namespace *user_ns, u32 portid, u32 seq, u32 flags, int sk_ino) { @@ -172,7 +173,8 @@ static int sk_diag_fill(struct sock *sk, struct sk_buff *skb, goto out_nlmsg_trim; if ((req->pdiag_show & PACKET_SHOW_FILTER) && - sock_diag_put_filterinfo(user_ns, sk, skb, PACKET_DIAG_FILTER)) + sock_diag_put_filterinfo(may_report_filterinfo, sk, skb, + PACKET_DIAG_FILTER)) goto out_nlmsg_trim; return nlmsg_end(skb, nlh); @@ -188,9 +190,11 @@ static int packet_diag_dump(struct sk_buff *skb, struct netlink_callback *cb) struct packet_diag_req *req; struct net *net; struct sock *sk; + bool may_report_filterinfo; net = sock_net(skb->sk); req = nlmsg_data(cb->nlh); + may_report_filterinfo = netlink_net_capable(cb->skb, CAP_NET_ADMIN); mutex_lock(&net->packet.sklist_lock); sk_for_each(sk, &net->packet.sklist) { @@ -200,6 +204,7 @@ static int packet_diag_dump(struct sk_buff *skb, struct netlink_callback *cb) goto next; if (sk_diag_fill(sk, skb, req, + may_report_filterinfo, sk_user_ns(NETLINK_CB(cb->skb).sk), NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, NLM_F_MULTI, diff --git a/net/phonet/pep-gprs.c b/net/phonet/pep-gprs.c index a2fba7e..66dc65e 100644 --- a/net/phonet/pep-gprs.c +++ b/net/phonet/pep-gprs.c @@ -37,7 +37,7 @@ struct gprs_dev { struct sock *sk; void (*old_state_change)(struct sock *); - void (*old_data_ready)(struct sock *, int); + void (*old_data_ready)(struct sock *); void (*old_write_space)(struct sock *); struct net_device *dev; @@ -146,7 +146,7 @@ drop: return err; } -static void gprs_data_ready(struct sock *sk, int len) +static void gprs_data_ready(struct sock *sk) { struct gprs_dev *gp = sk->sk_user_data; struct sk_buff *skb; diff --git a/net/phonet/pep.c b/net/phonet/pep.c index e774117..70a547e 100644 --- a/net/phonet/pep.c +++ b/net/phonet/pep.c @@ -462,10 +462,9 @@ out: queue: skb->dev = NULL; skb_set_owner_r(skb, sk); - err = skb->len; skb_queue_tail(queue, skb); if (!sock_flag(sk, SOCK_DEAD)) - sk->sk_data_ready(sk, err); + sk->sk_data_ready(sk); return NET_RX_SUCCESS; } @@ -587,10 +586,9 @@ static int pipe_handler_do_rcv(struct sock *sk, struct sk_buff *skb) pn->rx_credits--; skb->dev = NULL; skb_set_owner_r(skb, sk); - err = skb->len; skb_queue_tail(&sk->sk_receive_queue, skb); if (!sock_flag(sk, SOCK_DEAD)) - sk->sk_data_ready(sk, err); + sk->sk_data_ready(sk); return NET_RX_SUCCESS; case PNS_PEP_CONNECT_RESP: @@ -698,7 +696,7 @@ static int pep_do_rcv(struct sock *sk, struct sk_buff *skb) skb_queue_head(&sk->sk_receive_queue, skb); sk_acceptq_added(sk); if (!sock_flag(sk, SOCK_DEAD)) - sk->sk_data_ready(sk, 0); + sk->sk_data_ready(sk); return NET_RX_SUCCESS; case PNS_PEP_DISCONNECT_REQ: diff --git a/net/phonet/pn_netlink.c b/net/phonet/pn_netlink.c index dc15f43..b64151a 100644 --- a/net/phonet/pn_netlink.c +++ b/net/phonet/pn_netlink.c @@ -70,10 +70,10 @@ static int addr_doit(struct sk_buff *skb, struct nlmsghdr *nlh) int err; u8 pnaddr; - if (!capable(CAP_NET_ADMIN)) + if (!netlink_capable(skb, CAP_NET_ADMIN)) return -EPERM; - if (!capable(CAP_SYS_ADMIN)) + if (!netlink_capable(skb, CAP_SYS_ADMIN)) return -EPERM; ASSERT_RTNL(); @@ -233,10 +233,10 @@ static int route_doit(struct sk_buff *skb, struct nlmsghdr *nlh) int err; u8 dst; - if (!capable(CAP_NET_ADMIN)) + if (!netlink_capable(skb, CAP_NET_ADMIN)) return -EPERM; - if (!capable(CAP_SYS_ADMIN)) + if (!netlink_capable(skb, CAP_SYS_ADMIN)) return -EPERM; ASSERT_RTNL(); diff --git a/net/rds/tcp.h b/net/rds/tcp.h index 9cf2927..6563749 100644 --- a/net/rds/tcp.h +++ b/net/rds/tcp.h @@ -61,12 +61,12 @@ void rds_tcp_state_change(struct sock *sk); /* tcp_listen.c */ int rds_tcp_listen_init(void); void rds_tcp_listen_stop(void); -void rds_tcp_listen_data_ready(struct sock *sk, int bytes); +void rds_tcp_listen_data_ready(struct sock *sk); /* tcp_recv.c */ int rds_tcp_recv_init(void); void rds_tcp_recv_exit(void); -void rds_tcp_data_ready(struct sock *sk, int bytes); +void rds_tcp_data_ready(struct sock *sk); int rds_tcp_recv(struct rds_connection *conn); void rds_tcp_inc_free(struct rds_incoming *inc); int rds_tcp_inc_copy_to_user(struct rds_incoming *inc, struct iovec *iov, diff --git a/net/rds/tcp_listen.c b/net/rds/tcp_listen.c index 7787537..4e638f8 100644 --- a/net/rds/tcp_listen.c +++ b/net/rds/tcp_listen.c @@ -108,9 +108,9 @@ static void rds_tcp_accept_worker(struct work_struct *work) cond_resched(); } -void rds_tcp_listen_data_ready(struct sock *sk, int bytes) +void rds_tcp_listen_data_ready(struct sock *sk) { - void (*ready)(struct sock *sk, int bytes); + void (*ready)(struct sock *sk); rdsdebug("listen data ready sk %p\n", sk); @@ -132,7 +132,7 @@ void rds_tcp_listen_data_ready(struct sock *sk, int bytes) out: read_unlock(&sk->sk_callback_lock); - ready(sk, bytes); + ready(sk); } int rds_tcp_listen_init(void) diff --git a/net/rds/tcp_recv.c b/net/rds/tcp_recv.c index 4fac4f2..9ae6e0a 100644 --- a/net/rds/tcp_recv.c +++ b/net/rds/tcp_recv.c @@ -314,13 +314,13 @@ int rds_tcp_recv(struct rds_connection *conn) return ret; } -void rds_tcp_data_ready(struct sock *sk, int bytes) +void rds_tcp_data_ready(struct sock *sk) { - void (*ready)(struct sock *sk, int bytes); + void (*ready)(struct sock *sk); struct rds_connection *conn; struct rds_tcp_connection *tc; - rdsdebug("data ready sk %p bytes %d\n", sk, bytes); + rdsdebug("data ready sk %p\n", sk); read_lock(&sk->sk_callback_lock); conn = sk->sk_user_data; @@ -337,7 +337,7 @@ void rds_tcp_data_ready(struct sock *sk, int bytes) queue_delayed_work(rds_wq, &conn->c_recv_w, 0); out: read_unlock(&sk->sk_callback_lock); - ready(sk, bytes); + ready(sk); } int rds_tcp_recv_init(void) diff --git a/net/rose/af_rose.c b/net/rose/af_rose.c index c2cca2e..8451c8c 100644 --- a/net/rose/af_rose.c +++ b/net/rose/af_rose.c @@ -1041,7 +1041,7 @@ int rose_rx_call_request(struct sk_buff *skb, struct net_device *dev, struct ros rose_start_heartbeat(make); if (!sock_flag(sk, SOCK_DEAD)) - sk->sk_data_ready(sk, skb->len); + sk->sk_data_ready(sk); return 1; } diff --git a/net/rxrpc/ar-input.c b/net/rxrpc/ar-input.c index 7374264..63b21e5 100644 --- a/net/rxrpc/ar-input.c +++ b/net/rxrpc/ar-input.c @@ -113,7 +113,7 @@ int rxrpc_queue_rcv_skb(struct rxrpc_call *call, struct sk_buff *skb, spin_unlock_bh(&sk->sk_receive_queue.lock); if (!sock_flag(sk, SOCK_DEAD)) - sk->sk_data_ready(sk, skb_len); + sk->sk_data_ready(sk); } skb = NULL; } else { @@ -632,14 +632,14 @@ cant_find_conn: * handle data received on the local endpoint * - may be called in interrupt context */ -void rxrpc_data_ready(struct sock *sk, int count) +void rxrpc_data_ready(struct sock *sk) { struct rxrpc_skb_priv *sp; struct rxrpc_local *local; struct sk_buff *skb; int ret; - _enter("%p, %d", sk, count); + _enter("%p", sk); ASSERT(!irqs_disabled()); diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h index c831d44..ba9fd36 100644 --- a/net/rxrpc/ar-internal.h +++ b/net/rxrpc/ar-internal.h @@ -518,7 +518,7 @@ void rxrpc_UDP_error_handler(struct work_struct *); */ extern const char *rxrpc_pkts[]; -void rxrpc_data_ready(struct sock *, int); +void rxrpc_data_ready(struct sock *); int rxrpc_queue_rcv_skb(struct rxrpc_call *, struct sk_buff *, bool, bool); void rxrpc_fast_process_packet(struct rxrpc_call *, struct sk_buff *); diff --git a/net/sched/act_api.c b/net/sched/act_api.c index 8a5ba5a..648778a 100644 --- a/net/sched/act_api.c +++ b/net/sched/act_api.c @@ -948,7 +948,7 @@ static int tc_ctl_action(struct sk_buff *skb, struct nlmsghdr *n) u32 portid = skb ? NETLINK_CB(skb).portid : 0; int ret = 0, ovr = 0; - if ((n->nlmsg_type != RTM_GETACTION) && !capable(CAP_NET_ADMIN)) + if ((n->nlmsg_type != RTM_GETACTION) && !netlink_capable(skb, CAP_NET_ADMIN)) return -EPERM; ret = nlmsg_parse(n, sizeof(struct tcamsg), tca, TCA_ACT_MAX, NULL); diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index 29a30a1..bdbdb1a 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -134,7 +134,7 @@ static int tc_ctl_tfilter(struct sk_buff *skb, struct nlmsghdr *n) int err; int tp_created = 0; - if ((n->nlmsg_type != RTM_GETTFILTER) && !capable(CAP_NET_ADMIN)) + if ((n->nlmsg_type != RTM_GETTFILTER) && !netlink_capable(skb, CAP_NET_ADMIN)) return -EPERM; replay: diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c index a0b84e0..4007690 100644 --- a/net/sched/sch_api.c +++ b/net/sched/sch_api.c @@ -1084,7 +1084,7 @@ static int tc_get_qdisc(struct sk_buff *skb, struct nlmsghdr *n) struct Qdisc *p = NULL; int err; - if ((n->nlmsg_type != RTM_GETQDISC) && !capable(CAP_NET_ADMIN)) + if ((n->nlmsg_type != RTM_GETQDISC) && !netlink_capable(skb, CAP_NET_ADMIN)) return -EPERM; err = nlmsg_parse(n, sizeof(*tcm), tca, TCA_MAX, NULL); @@ -1151,7 +1151,7 @@ static int tc_modify_qdisc(struct sk_buff *skb, struct nlmsghdr *n) struct Qdisc *q, *p; int err; - if (!capable(CAP_NET_ADMIN)) + if (!netlink_capable(skb, CAP_NET_ADMIN)) return -EPERM; replay: @@ -1490,7 +1490,7 @@ static int tc_ctl_tclass(struct sk_buff *skb, struct nlmsghdr *n) u32 qid; int err; - if ((n->nlmsg_type != RTM_GETTCLASS) && !capable(CAP_NET_ADMIN)) + if ((n->nlmsg_type != RTM_GETTCLASS) && !netlink_capable(skb, CAP_NET_ADMIN)) return -EPERM; err = nlmsg_parse(n, sizeof(*tcm), tca, TCA_MAX, NULL); diff --git a/net/sched/sch_hhf.c b/net/sched/sch_hhf.c index edee03d..6e957c3 100644 --- a/net/sched/sch_hhf.c +++ b/net/sched/sch_hhf.c @@ -553,11 +553,6 @@ static int hhf_change(struct Qdisc *sch, struct nlattr *opt) if (err < 0) return err; - sch_tree_lock(sch); - - if (tb[TCA_HHF_BACKLOG_LIMIT]) - sch->limit = nla_get_u32(tb[TCA_HHF_BACKLOG_LIMIT]); - if (tb[TCA_HHF_QUANTUM]) new_quantum = nla_get_u32(tb[TCA_HHF_QUANTUM]); @@ -567,6 +562,12 @@ static int hhf_change(struct Qdisc *sch, struct nlattr *opt) non_hh_quantum = (u64)new_quantum * new_hhf_non_hh_weight; if (non_hh_quantum > INT_MAX) return -EINVAL; + + sch_tree_lock(sch); + + if (tb[TCA_HHF_BACKLOG_LIMIT]) + sch->limit = nla_get_u32(tb[TCA_HHF_BACKLOG_LIMIT]); + q->quantum = new_quantum; q->hhf_non_hh_weight = new_hhf_non_hh_weight; diff --git a/net/sctp/associola.c b/net/sctp/associola.c index 4f6d6f9..39579c3 100644 --- a/net/sctp/associola.c +++ b/net/sctp/associola.c @@ -1395,35 +1395,44 @@ static inline bool sctp_peer_needs_update(struct sctp_association *asoc) return false; } -/* Update asoc's rwnd for the approximated state in the buffer, - * and check whether SACK needs to be sent. - */ -void sctp_assoc_rwnd_update(struct sctp_association *asoc, bool update_peer) +/* Increase asoc's rwnd by len and send any window update SACK if needed. */ +void sctp_assoc_rwnd_increase(struct sctp_association *asoc, unsigned int len) { - int rx_count; struct sctp_chunk *sack; struct timer_list *timer; - if (asoc->ep->rcvbuf_policy) - rx_count = atomic_read(&asoc->rmem_alloc); - else - rx_count = atomic_read(&asoc->base.sk->sk_rmem_alloc); + if (asoc->rwnd_over) { + if (asoc->rwnd_over >= len) { + asoc->rwnd_over -= len; + } else { + asoc->rwnd += (len - asoc->rwnd_over); + asoc->rwnd_over = 0; + } + } else { + asoc->rwnd += len; + } - if ((asoc->base.sk->sk_rcvbuf - rx_count) > 0) - asoc->rwnd = (asoc->base.sk->sk_rcvbuf - rx_count) >> 1; - else - asoc->rwnd = 0; + /* If we had window pressure, start recovering it + * once our rwnd had reached the accumulated pressure + * threshold. The idea is to recover slowly, but up + * to the initial advertised window. + */ + if (asoc->rwnd_press && asoc->rwnd >= asoc->rwnd_press) { + int change = min(asoc->pathmtu, asoc->rwnd_press); + asoc->rwnd += change; + asoc->rwnd_press -= change; + } - pr_debug("%s: asoc:%p rwnd=%u, rx_count=%d, sk_rcvbuf=%d\n", - __func__, asoc, asoc->rwnd, rx_count, - asoc->base.sk->sk_rcvbuf); + pr_debug("%s: asoc:%p rwnd increased by %d to (%u, %u) - %u\n", + __func__, asoc, len, asoc->rwnd, asoc->rwnd_over, + asoc->a_rwnd); /* Send a window update SACK if the rwnd has increased by at least the * minimum of the association's PMTU and half of the receive buffer. * The algorithm used is similar to the one described in * Section 4.2.3.3 of RFC 1122. */ - if (update_peer && sctp_peer_needs_update(asoc)) { + if (sctp_peer_needs_update(asoc)) { asoc->a_rwnd = asoc->rwnd; pr_debug("%s: sending window update SACK- asoc:%p rwnd:%u " @@ -1445,6 +1454,45 @@ void sctp_assoc_rwnd_update(struct sctp_association *asoc, bool update_peer) } } +/* Decrease asoc's rwnd by len. */ +void sctp_assoc_rwnd_decrease(struct sctp_association *asoc, unsigned int len) +{ + int rx_count; + int over = 0; + + if (unlikely(!asoc->rwnd || asoc->rwnd_over)) + pr_debug("%s: association:%p has asoc->rwnd:%u, " + "asoc->rwnd_over:%u!\n", __func__, asoc, + asoc->rwnd, asoc->rwnd_over); + + if (asoc->ep->rcvbuf_policy) + rx_count = atomic_read(&asoc->rmem_alloc); + else + rx_count = atomic_read(&asoc->base.sk->sk_rmem_alloc); + + /* If we've reached or overflowed our receive buffer, announce + * a 0 rwnd if rwnd would still be positive. Store the + * the potential pressure overflow so that the window can be restored + * back to original value. + */ + if (rx_count >= asoc->base.sk->sk_rcvbuf) + over = 1; + + if (asoc->rwnd >= len) { + asoc->rwnd -= len; + if (over) { + asoc->rwnd_press += asoc->rwnd; + asoc->rwnd = 0; + } + } else { + asoc->rwnd_over = len - asoc->rwnd; + asoc->rwnd = 0; + } + + pr_debug("%s: asoc:%p rwnd decreased by %d to (%u, %u, %u)\n", + __func__, asoc, len, asoc->rwnd, asoc->rwnd_over, + asoc->rwnd_press); +} /* Build the bind address list for the association based on info from the * local endpoint and the remote peer. diff --git a/net/sctp/auth.c b/net/sctp/auth.c index 683c7d1..0e85291 100644 --- a/net/sctp/auth.c +++ b/net/sctp/auth.c @@ -386,14 +386,13 @@ nomem: */ int sctp_auth_asoc_init_active_key(struct sctp_association *asoc, gfp_t gfp) { - struct net *net = sock_net(asoc->base.sk); struct sctp_auth_bytes *secret; struct sctp_shared_key *ep_key; /* If we don't support AUTH, or peer is not capable * we don't need to do anything. */ - if (!net->sctp.auth_enable || !asoc->peer.auth_capable) + if (!asoc->ep->auth_enable || !asoc->peer.auth_capable) return 0; /* If the key_id is non-zero and we couldn't find an @@ -440,16 +439,16 @@ struct sctp_shared_key *sctp_auth_get_shkey( */ int sctp_auth_init_hmacs(struct sctp_endpoint *ep, gfp_t gfp) { - struct net *net = sock_net(ep->base.sk); struct crypto_hash *tfm = NULL; __u16 id; - /* if the transforms are already allocted, we are done */ - if (!net->sctp.auth_enable) { + /* If AUTH extension is disabled, we are done */ + if (!ep->auth_enable) { ep->auth_hmacs = NULL; return 0; } + /* If the transforms are already allocated, we are done */ if (ep->auth_hmacs) return 0; @@ -665,12 +664,10 @@ static int __sctp_auth_cid(sctp_cid_t chunk, struct sctp_chunks_param *param) /* Check if peer requested that this chunk is authenticated */ int sctp_auth_send_cid(sctp_cid_t chunk, const struct sctp_association *asoc) { - struct net *net; if (!asoc) return 0; - net = sock_net(asoc->base.sk); - if (!net->sctp.auth_enable || !asoc->peer.auth_capable) + if (!asoc->ep->auth_enable || !asoc->peer.auth_capable) return 0; return __sctp_auth_cid(chunk, asoc->peer.peer_chunks); @@ -679,12 +676,10 @@ int sctp_auth_send_cid(sctp_cid_t chunk, const struct sctp_association *asoc) /* Check if we requested that peer authenticate this chunk. */ int sctp_auth_recv_cid(sctp_cid_t chunk, const struct sctp_association *asoc) { - struct net *net; if (!asoc) return 0; - net = sock_net(asoc->base.sk); - if (!net->sctp.auth_enable) + if (!asoc->ep->auth_enable) return 0; return __sctp_auth_cid(chunk, diff --git a/net/sctp/endpointola.c b/net/sctp/endpointola.c index 8e5fdea..3d9f429 100644 --- a/net/sctp/endpointola.c +++ b/net/sctp/endpointola.c @@ -68,7 +68,8 @@ static struct sctp_endpoint *sctp_endpoint_init(struct sctp_endpoint *ep, if (!ep->digest) return NULL; - if (net->sctp.auth_enable) { + ep->auth_enable = net->sctp.auth_enable; + if (ep->auth_enable) { /* Allocate space for HMACS and CHUNKS authentication * variables. There are arrays that we encode directly * into parameters to make the rest of the operations easier. diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c index 4e1d0fc..44cbb54 100644 --- a/net/sctp/protocol.c +++ b/net/sctp/protocol.c @@ -491,8 +491,13 @@ static void sctp_v4_get_dst(struct sctp_transport *t, union sctp_addr *saddr, continue; if ((laddr->state == SCTP_ADDR_SRC) && (AF_INET == laddr->a.sa.sa_family)) { - fl4->saddr = laddr->a.v4.sin_addr.s_addr; fl4->fl4_sport = laddr->a.v4.sin_port; + flowi4_update_output(fl4, + asoc->base.sk->sk_bound_dev_if, + RT_CONN_FLAGS(asoc->base.sk), + daddr->v4.sin_addr.s_addr, + laddr->a.v4.sin_addr.s_addr); + rt = ip_route_output_key(sock_net(sk), fl4); if (!IS_ERR(rt)) { dst = &rt->dst; @@ -957,7 +962,7 @@ static inline int sctp_v4_xmit(struct sk_buff *skb, SCTP_INC_STATS(sock_net(&inet->sk), SCTP_MIB_OUTSCTPPACKS); - return ip_queue_xmit(skb, &transport->fl); + return ip_queue_xmit(&inet->sk, skb, &transport->fl); } static struct sctp_af sctp_af_inet; diff --git a/net/sctp/sm_make_chunk.c b/net/sctp/sm_make_chunk.c index 3a1767e..fee5552 100644 --- a/net/sctp/sm_make_chunk.c +++ b/net/sctp/sm_make_chunk.c @@ -219,6 +219,7 @@ struct sctp_chunk *sctp_make_init(const struct sctp_association *asoc, gfp_t gfp, int vparam_len) { struct net *net = sock_net(asoc->base.sk); + struct sctp_endpoint *ep = asoc->ep; sctp_inithdr_t init; union sctp_params addrs; size_t chunksize; @@ -278,7 +279,7 @@ struct sctp_chunk *sctp_make_init(const struct sctp_association *asoc, chunksize += vparam_len; /* Account for AUTH related parameters */ - if (net->sctp.auth_enable) { + if (ep->auth_enable) { /* Add random parameter length*/ chunksize += sizeof(asoc->c.auth_random); @@ -363,7 +364,7 @@ struct sctp_chunk *sctp_make_init(const struct sctp_association *asoc, } /* Add SCTP-AUTH chunks to the parameter list */ - if (net->sctp.auth_enable) { + if (ep->auth_enable) { sctp_addto_chunk(retval, sizeof(asoc->c.auth_random), asoc->c.auth_random); if (auth_hmacs) @@ -2010,7 +2011,7 @@ static void sctp_process_ext_param(struct sctp_association *asoc, /* if the peer reports AUTH, assume that he * supports AUTH. */ - if (net->sctp.auth_enable) + if (asoc->ep->auth_enable) asoc->peer.auth_capable = 1; break; case SCTP_CID_ASCONF: @@ -2102,6 +2103,7 @@ static sctp_ierror_t sctp_process_unk_param(const struct sctp_association *asoc, * SCTP_IERROR_NO_ERROR - continue with the chunk */ static sctp_ierror_t sctp_verify_param(struct net *net, + const struct sctp_endpoint *ep, const struct sctp_association *asoc, union sctp_params param, sctp_cid_t cid, @@ -2152,7 +2154,7 @@ static sctp_ierror_t sctp_verify_param(struct net *net, goto fallthrough; case SCTP_PARAM_RANDOM: - if (!net->sctp.auth_enable) + if (!ep->auth_enable) goto fallthrough; /* SCTP-AUTH: Secion 6.1 @@ -2169,7 +2171,7 @@ static sctp_ierror_t sctp_verify_param(struct net *net, break; case SCTP_PARAM_CHUNKS: - if (!net->sctp.auth_enable) + if (!ep->auth_enable) goto fallthrough; /* SCTP-AUTH: Section 3.2 @@ -2185,7 +2187,7 @@ static sctp_ierror_t sctp_verify_param(struct net *net, break; case SCTP_PARAM_HMAC_ALGO: - if (!net->sctp.auth_enable) + if (!ep->auth_enable) goto fallthrough; hmacs = (struct sctp_hmac_algo_param *)param.p; @@ -2220,10 +2222,9 @@ fallthrough: } /* Verify the INIT packet before we process it. */ -int sctp_verify_init(struct net *net, const struct sctp_association *asoc, - sctp_cid_t cid, - sctp_init_chunk_t *peer_init, - struct sctp_chunk *chunk, +int sctp_verify_init(struct net *net, const struct sctp_endpoint *ep, + const struct sctp_association *asoc, sctp_cid_t cid, + sctp_init_chunk_t *peer_init, struct sctp_chunk *chunk, struct sctp_chunk **errp) { union sctp_params param; @@ -2264,8 +2265,8 @@ int sctp_verify_init(struct net *net, const struct sctp_association *asoc, /* Verify all the variable length parameters */ sctp_walk_params(param, peer_init, init_hdr.params) { - - result = sctp_verify_param(net, asoc, param, cid, chunk, errp); + result = sctp_verify_param(net, ep, asoc, param, cid, + chunk, errp); switch (result) { case SCTP_IERROR_ABORT: case SCTP_IERROR_NOMEM: @@ -2497,6 +2498,7 @@ static int sctp_process_param(struct sctp_association *asoc, struct sctp_af *af; union sctp_addr_param *addr_param; struct sctp_transport *t; + struct sctp_endpoint *ep = asoc->ep; /* We maintain all INIT parameters in network byte order all the * time. This allows us to not worry about whether the parameters @@ -2636,7 +2638,7 @@ do_addr_param: goto fall_through; case SCTP_PARAM_RANDOM: - if (!net->sctp.auth_enable) + if (!ep->auth_enable) goto fall_through; /* Save peer's random parameter */ @@ -2649,7 +2651,7 @@ do_addr_param: break; case SCTP_PARAM_HMAC_ALGO: - if (!net->sctp.auth_enable) + if (!ep->auth_enable) goto fall_through; /* Save peer's HMAC list */ @@ -2665,7 +2667,7 @@ do_addr_param: break; case SCTP_PARAM_CHUNKS: - if (!net->sctp.auth_enable) + if (!ep->auth_enable) goto fall_through; asoc->peer.peer_chunks = kmemdup(param.p, diff --git a/net/sctp/sm_sideeffect.c b/net/sctp/sm_sideeffect.c index 5d6883f..fef2acd 100644 --- a/net/sctp/sm_sideeffect.c +++ b/net/sctp/sm_sideeffect.c @@ -496,11 +496,10 @@ static void sctp_do_8_2_transport_strike(sctp_cmd_seq_t *commands, /* If the transport error count is greater than the pf_retrans * threshold, and less than pathmaxrtx, and if the current state - * is not SCTP_UNCONFIRMED, then mark this transport as Partially - * Failed, see SCTP Quick Failover Draft, section 5.1 + * is SCTP_ACTIVE, then mark this transport as Partially Failed, + * see SCTP Quick Failover Draft, section 5.1 */ - if ((transport->state != SCTP_PF) && - (transport->state != SCTP_UNCONFIRMED) && + if ((transport->state == SCTP_ACTIVE) && (asoc->pf_retrans < transport->pathmaxrxt) && (transport->error_count > asoc->pf_retrans)) { diff --git a/net/sctp/sm_statefuns.c b/net/sctp/sm_statefuns.c index 01e0024..5170a1f 100644 --- a/net/sctp/sm_statefuns.c +++ b/net/sctp/sm_statefuns.c @@ -357,7 +357,7 @@ sctp_disposition_t sctp_sf_do_5_1B_init(struct net *net, /* Verify the INIT chunk before processing it. */ err_chunk = NULL; - if (!sctp_verify_init(net, asoc, chunk->chunk_hdr->type, + if (!sctp_verify_init(net, ep, asoc, chunk->chunk_hdr->type, (sctp_init_chunk_t *)chunk->chunk_hdr, chunk, &err_chunk)) { /* This chunk contains fatal error. It is to be discarded. @@ -524,7 +524,7 @@ sctp_disposition_t sctp_sf_do_5_1C_ack(struct net *net, /* Verify the INIT chunk before processing it. */ err_chunk = NULL; - if (!sctp_verify_init(net, asoc, chunk->chunk_hdr->type, + if (!sctp_verify_init(net, ep, asoc, chunk->chunk_hdr->type, (sctp_init_chunk_t *)chunk->chunk_hdr, chunk, &err_chunk)) { @@ -1430,7 +1430,7 @@ static sctp_disposition_t sctp_sf_do_unexpected_init( /* Verify the INIT chunk before processing it. */ err_chunk = NULL; - if (!sctp_verify_init(net, asoc, chunk->chunk_hdr->type, + if (!sctp_verify_init(net, ep, asoc, chunk->chunk_hdr->type, (sctp_init_chunk_t *)chunk->chunk_hdr, chunk, &err_chunk)) { /* This chunk contains fatal error. It is to be discarded. @@ -6178,7 +6178,7 @@ static int sctp_eat_data(const struct sctp_association *asoc, * PMTU. In cases, such as loopback, this might be a rather * large spill over. */ - if ((!chunk->data_accepted) && (!asoc->rwnd || + if ((!chunk->data_accepted) && (!asoc->rwnd || asoc->rwnd_over || (datalen > asoc->rwnd + asoc->frag_point))) { /* If this is the next TSN, consider reneging to make diff --git a/net/sctp/socket.c b/net/sctp/socket.c index 981aaf8..fee06b9 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -2115,6 +2115,12 @@ static int sctp_recvmsg(struct kiocb *iocb, struct sock *sk, sctp_skb_pull(skb, copied); skb_queue_head(&sk->sk_receive_queue, skb); + /* When only partial message is copied to the user, increase + * rwnd by that amount. If all the data in the skb is read, + * rwnd is updated when the event is freed. + */ + if (!sctp_ulpevent_is_notification(event)) + sctp_assoc_rwnd_increase(event->asoc, copied); goto out; } else if ((event->msg_flags & MSG_NOTIFICATION) || (event->msg_flags & MSG_EOR)) @@ -3315,10 +3321,10 @@ static int sctp_setsockopt_auth_chunk(struct sock *sk, char __user *optval, unsigned int optlen) { - struct net *net = sock_net(sk); + struct sctp_endpoint *ep = sctp_sk(sk)->ep; struct sctp_authchunk val; - if (!net->sctp.auth_enable) + if (!ep->auth_enable) return -EACCES; if (optlen != sizeof(struct sctp_authchunk)) @@ -3335,7 +3341,7 @@ static int sctp_setsockopt_auth_chunk(struct sock *sk, } /* add this chunk id to the endpoint */ - return sctp_auth_ep_add_chunkid(sctp_sk(sk)->ep, val.sauth_chunk); + return sctp_auth_ep_add_chunkid(ep, val.sauth_chunk); } /* @@ -3348,12 +3354,12 @@ static int sctp_setsockopt_hmac_ident(struct sock *sk, char __user *optval, unsigned int optlen) { - struct net *net = sock_net(sk); + struct sctp_endpoint *ep = sctp_sk(sk)->ep; struct sctp_hmacalgo *hmacs; u32 idents; int err; - if (!net->sctp.auth_enable) + if (!ep->auth_enable) return -EACCES; if (optlen < sizeof(struct sctp_hmacalgo)) @@ -3370,7 +3376,7 @@ static int sctp_setsockopt_hmac_ident(struct sock *sk, goto out; } - err = sctp_auth_ep_set_hmacs(sctp_sk(sk)->ep, hmacs); + err = sctp_auth_ep_set_hmacs(ep, hmacs); out: kfree(hmacs); return err; @@ -3386,12 +3392,12 @@ static int sctp_setsockopt_auth_key(struct sock *sk, char __user *optval, unsigned int optlen) { - struct net *net = sock_net(sk); + struct sctp_endpoint *ep = sctp_sk(sk)->ep; struct sctp_authkey *authkey; struct sctp_association *asoc; int ret; - if (!net->sctp.auth_enable) + if (!ep->auth_enable) return -EACCES; if (optlen <= sizeof(struct sctp_authkey)) @@ -3412,7 +3418,7 @@ static int sctp_setsockopt_auth_key(struct sock *sk, goto out; } - ret = sctp_auth_set_key(sctp_sk(sk)->ep, asoc, authkey); + ret = sctp_auth_set_key(ep, asoc, authkey); out: kzfree(authkey); return ret; @@ -3428,11 +3434,11 @@ static int sctp_setsockopt_active_key(struct sock *sk, char __user *optval, unsigned int optlen) { - struct net *net = sock_net(sk); + struct sctp_endpoint *ep = sctp_sk(sk)->ep; struct sctp_authkeyid val; struct sctp_association *asoc; - if (!net->sctp.auth_enable) + if (!ep->auth_enable) return -EACCES; if (optlen != sizeof(struct sctp_authkeyid)) @@ -3444,8 +3450,7 @@ static int sctp_setsockopt_active_key(struct sock *sk, if (!asoc && val.scact_assoc_id && sctp_style(sk, UDP)) return -EINVAL; - return sctp_auth_set_active_key(sctp_sk(sk)->ep, asoc, - val.scact_keynumber); + return sctp_auth_set_active_key(ep, asoc, val.scact_keynumber); } /* @@ -3457,11 +3462,11 @@ static int sctp_setsockopt_del_key(struct sock *sk, char __user *optval, unsigned int optlen) { - struct net *net = sock_net(sk); + struct sctp_endpoint *ep = sctp_sk(sk)->ep; struct sctp_authkeyid val; struct sctp_association *asoc; - if (!net->sctp.auth_enable) + if (!ep->auth_enable) return -EACCES; if (optlen != sizeof(struct sctp_authkeyid)) @@ -3473,8 +3478,7 @@ static int sctp_setsockopt_del_key(struct sock *sk, if (!asoc && val.scact_assoc_id && sctp_style(sk, UDP)) return -EINVAL; - return sctp_auth_del_key_id(sctp_sk(sk)->ep, asoc, - val.scact_keynumber); + return sctp_auth_del_key_id(ep, asoc, val.scact_keynumber); } @@ -5381,16 +5385,16 @@ static int sctp_getsockopt_maxburst(struct sock *sk, int len, static int sctp_getsockopt_hmac_ident(struct sock *sk, int len, char __user *optval, int __user *optlen) { - struct net *net = sock_net(sk); + struct sctp_endpoint *ep = sctp_sk(sk)->ep; struct sctp_hmacalgo __user *p = (void __user *)optval; struct sctp_hmac_algo_param *hmacs; __u16 data_len = 0; u32 num_idents; - if (!net->sctp.auth_enable) + if (!ep->auth_enable) return -EACCES; - hmacs = sctp_sk(sk)->ep->auth_hmacs_list; + hmacs = ep->auth_hmacs_list; data_len = ntohs(hmacs->param_hdr.length) - sizeof(sctp_paramhdr_t); if (len < sizeof(struct sctp_hmacalgo) + data_len) @@ -5411,11 +5415,11 @@ static int sctp_getsockopt_hmac_ident(struct sock *sk, int len, static int sctp_getsockopt_active_key(struct sock *sk, int len, char __user *optval, int __user *optlen) { - struct net *net = sock_net(sk); + struct sctp_endpoint *ep = sctp_sk(sk)->ep; struct sctp_authkeyid val; struct sctp_association *asoc; - if (!net->sctp.auth_enable) + if (!ep->auth_enable) return -EACCES; if (len < sizeof(struct sctp_authkeyid)) @@ -5430,7 +5434,7 @@ static int sctp_getsockopt_active_key(struct sock *sk, int len, if (asoc) val.scact_keynumber = asoc->active_key_id; else - val.scact_keynumber = sctp_sk(sk)->ep->active_key_id; + val.scact_keynumber = ep->active_key_id; len = sizeof(struct sctp_authkeyid); if (put_user(len, optlen)) @@ -5444,7 +5448,7 @@ static int sctp_getsockopt_active_key(struct sock *sk, int len, static int sctp_getsockopt_peer_auth_chunks(struct sock *sk, int len, char __user *optval, int __user *optlen) { - struct net *net = sock_net(sk); + struct sctp_endpoint *ep = sctp_sk(sk)->ep; struct sctp_authchunks __user *p = (void __user *)optval; struct sctp_authchunks val; struct sctp_association *asoc; @@ -5452,7 +5456,7 @@ static int sctp_getsockopt_peer_auth_chunks(struct sock *sk, int len, u32 num_chunks = 0; char __user *to; - if (!net->sctp.auth_enable) + if (!ep->auth_enable) return -EACCES; if (len < sizeof(struct sctp_authchunks)) @@ -5489,7 +5493,7 @@ num: static int sctp_getsockopt_local_auth_chunks(struct sock *sk, int len, char __user *optval, int __user *optlen) { - struct net *net = sock_net(sk); + struct sctp_endpoint *ep = sctp_sk(sk)->ep; struct sctp_authchunks __user *p = (void __user *)optval; struct sctp_authchunks val; struct sctp_association *asoc; @@ -5497,7 +5501,7 @@ static int sctp_getsockopt_local_auth_chunks(struct sock *sk, int len, u32 num_chunks = 0; char __user *to; - if (!net->sctp.auth_enable) + if (!ep->auth_enable) return -EACCES; if (len < sizeof(struct sctp_authchunks)) @@ -5514,7 +5518,7 @@ static int sctp_getsockopt_local_auth_chunks(struct sock *sk, int len, if (asoc) ch = (struct sctp_chunks_param *)asoc->c.auth_chunks; else - ch = sctp_sk(sk)->ep->auth_chunk_list; + ch = ep->auth_chunk_list; if (!ch) goto num; @@ -6593,6 +6597,46 @@ static void __sctp_write_space(struct sctp_association *asoc) } } +static void sctp_wake_up_waiters(struct sock *sk, + struct sctp_association *asoc) +{ + struct sctp_association *tmp = asoc; + + /* We do accounting for the sndbuf space per association, + * so we only need to wake our own association. + */ + if (asoc->ep->sndbuf_policy) + return __sctp_write_space(asoc); + + /* If association goes down and is just flushing its + * outq, then just normally notify others. + */ + if (asoc->base.dead) + return sctp_write_space(sk); + + /* Accounting for the sndbuf space is per socket, so we + * need to wake up others, try to be fair and in case of + * other associations, let them have a go first instead + * of just doing a sctp_write_space() call. + * + * Note that we reach sctp_wake_up_waiters() only when + * associations free up queued chunks, thus we are under + * lock and the list of associations on a socket is + * guaranteed not to change. + */ + for (tmp = list_next_entry(tmp, asocs); 1; + tmp = list_next_entry(tmp, asocs)) { + /* Manually skip the head element. */ + if (&tmp->asocs == &((sctp_sk(sk))->ep->asocs)) + continue; + /* Wake up association. */ + __sctp_write_space(tmp); + /* We've reached the end. */ + if (tmp == asoc) + break; + } +} + /* Do accounting for the sndbuf space. * Decrement the used sndbuf space of the corresponding association by the * data size which was just transmitted(freed). @@ -6620,7 +6664,7 @@ static void sctp_wfree(struct sk_buff *skb) sk_mem_uncharge(sk, skb->truesize); sock_wfree(skb); - __sctp_write_space(asoc); + sctp_wake_up_waiters(sk, asoc); sctp_association_put(asoc); } @@ -6705,7 +6749,7 @@ do_nonblock: goto out; } -void sctp_data_ready(struct sock *sk, int len) +void sctp_data_ready(struct sock *sk) { struct socket_wq *wq; diff --git a/net/sctp/sysctl.c b/net/sctp/sysctl.c index 35c8923..c82fdc1 100644 --- a/net/sctp/sysctl.c +++ b/net/sctp/sysctl.c @@ -64,6 +64,9 @@ static int proc_sctp_do_rto_min(struct ctl_table *ctl, int write, static int proc_sctp_do_rto_max(struct ctl_table *ctl, int write, void __user *buffer, size_t *lenp, loff_t *ppos); +static int proc_sctp_do_auth(struct ctl_table *ctl, int write, + void __user *buffer, size_t *lenp, + loff_t *ppos); static struct ctl_table sctp_table[] = { { @@ -266,7 +269,7 @@ static struct ctl_table sctp_net_table[] = { .data = &init_net.sctp.auth_enable, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = proc_dointvec, + .proc_handler = proc_sctp_do_auth, }, { .procname = "addr_scope_policy", @@ -400,6 +403,37 @@ static int proc_sctp_do_rto_max(struct ctl_table *ctl, int write, return ret; } +static int proc_sctp_do_auth(struct ctl_table *ctl, int write, + void __user *buffer, size_t *lenp, + loff_t *ppos) +{ + struct net *net = current->nsproxy->net_ns; + struct ctl_table tbl; + int new_value, ret; + + memset(&tbl, 0, sizeof(struct ctl_table)); + tbl.maxlen = sizeof(unsigned int); + + if (write) + tbl.data = &new_value; + else + tbl.data = &net->sctp.auth_enable; + + ret = proc_dointvec(&tbl, write, buffer, lenp, ppos); + + if (write) { + struct sock *sk = net->sctp.ctl_sock; + + net->sctp.auth_enable = new_value; + /* Update the value in the control socket */ + lock_sock(sk); + sctp_sk(sk)->ep->auth_enable = new_value; + release_sock(sk); + } + + return ret; +} + int sctp_sysctl_net_register(struct net *net) { struct ctl_table *table = sctp_net_table; diff --git a/net/sctp/ulpevent.c b/net/sctp/ulpevent.c index 8d198ae..85c6465 100644 --- a/net/sctp/ulpevent.c +++ b/net/sctp/ulpevent.c @@ -989,7 +989,7 @@ static void sctp_ulpevent_receive_data(struct sctp_ulpevent *event, skb = sctp_event2skb(event); /* Set the owner and charge rwnd for bytes received. */ sctp_ulpevent_set_owner(event, asoc); - sctp_assoc_rwnd_update(asoc, false); + sctp_assoc_rwnd_decrease(asoc, skb_headlen(skb)); if (!skb->data_len) return; @@ -1011,7 +1011,6 @@ static void sctp_ulpevent_release_data(struct sctp_ulpevent *event) { struct sk_buff *skb, *frag; unsigned int len; - struct sctp_association *asoc; /* Current stack structures assume that the rcv buffer is * per socket. For UDP style sockets this is not true as @@ -1036,11 +1035,8 @@ static void sctp_ulpevent_release_data(struct sctp_ulpevent *event) } done: - asoc = event->asoc; - sctp_association_hold(asoc); + sctp_assoc_rwnd_increase(event->asoc, len); sctp_ulpevent_release_owner(event); - sctp_assoc_rwnd_update(asoc, true); - sctp_association_put(asoc); } static void sctp_ulpevent_release_frag_data(struct sctp_ulpevent *event) diff --git a/net/sctp/ulpqueue.c b/net/sctp/ulpqueue.c index 5dc9411..7144eb6 100644 --- a/net/sctp/ulpqueue.c +++ b/net/sctp/ulpqueue.c @@ -259,7 +259,7 @@ int sctp_ulpq_tail_event(struct sctp_ulpq *ulpq, struct sctp_ulpevent *event) sctp_ulpq_clear_pd(ulpq); if (queue == &sk->sk_receive_queue) - sk->sk_data_ready(sk, 0); + sk->sk_data_ready(sk); return 1; out_free: @@ -1135,5 +1135,5 @@ void sctp_ulpq_abort_pd(struct sctp_ulpq *ulpq, gfp_t gfp) /* If there is data waiting, send it up the socket now. */ if (sctp_ulpq_clear_pd(ulpq) || ev) - sk->sk_data_ready(sk, 0); + sk->sk_data_ready(sk); } diff --git a/net/socket.c b/net/socket.c index 1b1e7e6..abf56b2 100644 --- a/net/socket.c +++ b/net/socket.c @@ -1880,8 +1880,8 @@ out: * Receive a datagram from a socket. */ -asmlinkage long sys_recv(int fd, void __user *ubuf, size_t size, - unsigned int flags) +SYSCALL_DEFINE4(recv, int, fd, void __user *, ubuf, size_t, size, + unsigned int, flags) { return sys_recvfrom(fd, ubuf, size, flags, NULL, NULL); } diff --git a/net/sunrpc/Kconfig b/net/sunrpc/Kconfig index 241b54f..0754d0f 100644 --- a/net/sunrpc/Kconfig +++ b/net/sunrpc/Kconfig @@ -9,19 +9,6 @@ config SUNRPC_BACKCHANNEL bool depends on SUNRPC -config SUNRPC_XPRT_RDMA - tristate - depends on SUNRPC && INFINIBAND && INFINIBAND_ADDR_TRANS - default SUNRPC && INFINIBAND - help - This option allows the NFS client and server to support - an RDMA-enabled transport. - - To compile RPC client RDMA transport support as a module, - choose M here: the module will be called xprtrdma. - - If unsure, say N. - config SUNRPC_SWAP bool depends on SUNRPC @@ -57,3 +44,29 @@ config SUNRPC_DEBUG but makes troubleshooting NFS issues significantly harder. If unsure, say Y. + +config SUNRPC_XPRT_RDMA_CLIENT + tristate "RPC over RDMA Client Support" + depends on SUNRPC && INFINIBAND && INFINIBAND_ADDR_TRANS + default SUNRPC && INFINIBAND + help + This option allows the NFS client to support an RDMA-enabled + transport. + + To compile RPC client RDMA transport support as a module, + choose M here: the module will be called xprtrdma. + + If unsure, say N. + +config SUNRPC_XPRT_RDMA_SERVER + tristate "RPC over RDMA Server Support" + depends on SUNRPC && INFINIBAND && INFINIBAND_ADDR_TRANS + default SUNRPC && INFINIBAND + help + This option allows the NFS server to support an RDMA-enabled + transport. + + To compile RPC server RDMA transport support as a module, + choose M here: the module will be called svcrdma. + + If unsure, say N. diff --git a/net/sunrpc/Makefile b/net/sunrpc/Makefile index 8209a04..e5a7a1c 100644 --- a/net/sunrpc/Makefile +++ b/net/sunrpc/Makefile @@ -5,7 +5,8 @@ obj-$(CONFIG_SUNRPC) += sunrpc.o obj-$(CONFIG_SUNRPC_GSS) += auth_gss/ -obj-$(CONFIG_SUNRPC_XPRT_RDMA) += xprtrdma/ + +obj-y += xprtrdma/ sunrpc-y := clnt.o xprt.o socklib.o xprtsock.o sched.o \ auth.o auth_null.o auth_unix.o auth_generic.o \ diff --git a/net/sunrpc/backchannel_rqst.c b/net/sunrpc/backchannel_rqst.c index e860d4f..3513d55 100644 --- a/net/sunrpc/backchannel_rqst.c +++ b/net/sunrpc/backchannel_rqst.c @@ -212,39 +212,23 @@ out: } EXPORT_SYMBOL_GPL(xprt_destroy_backchannel); -/* - * One or more rpc_rqst structure have been preallocated during the - * backchannel setup. Buffer space for the send and private XDR buffers - * has been preallocated as well. Use xprt_alloc_bc_request to allocate - * to this request. Use xprt_free_bc_request to return it. - * - * We know that we're called in soft interrupt context, grab the spin_lock - * since there is no need to grab the bottom half spin_lock. - * - * Return an available rpc_rqst, otherwise NULL if non are available. - */ -struct rpc_rqst *xprt_alloc_bc_request(struct rpc_xprt *xprt) +static struct rpc_rqst *xprt_alloc_bc_request(struct rpc_xprt *xprt, __be32 xid) { - struct rpc_rqst *req; + struct rpc_rqst *req = NULL; dprintk("RPC: allocate a backchannel request\n"); - spin_lock(&xprt->bc_pa_lock); - if (!list_empty(&xprt->bc_pa_list)) { - req = list_first_entry(&xprt->bc_pa_list, struct rpc_rqst, - rq_bc_pa_list); - list_del(&req->rq_bc_pa_list); - } else { - req = NULL; - } - spin_unlock(&xprt->bc_pa_lock); + if (list_empty(&xprt->bc_pa_list)) + goto not_found; - if (req != NULL) { - set_bit(RPC_BC_PA_IN_USE, &req->rq_bc_pa_state); - req->rq_reply_bytes_recvd = 0; - req->rq_bytes_sent = 0; - memcpy(&req->rq_private_buf, &req->rq_rcv_buf, + req = list_first_entry(&xprt->bc_pa_list, struct rpc_rqst, + rq_bc_pa_list); + req->rq_reply_bytes_recvd = 0; + req->rq_bytes_sent = 0; + memcpy(&req->rq_private_buf, &req->rq_rcv_buf, sizeof(req->rq_private_buf)); - } + req->rq_xid = xid; + req->rq_connect_cookie = xprt->connect_cookie; +not_found: dprintk("RPC: backchannel req=%p\n", req); return req; } @@ -259,6 +243,7 @@ void xprt_free_bc_request(struct rpc_rqst *req) dprintk("RPC: free backchannel req=%p\n", req); + req->rq_connect_cookie = xprt->connect_cookie - 1; smp_mb__before_clear_bit(); WARN_ON_ONCE(!test_bit(RPC_BC_PA_IN_USE, &req->rq_bc_pa_state)); clear_bit(RPC_BC_PA_IN_USE, &req->rq_bc_pa_state); @@ -281,7 +266,57 @@ void xprt_free_bc_request(struct rpc_rqst *req) * may be reused by a new callback request. */ spin_lock_bh(&xprt->bc_pa_lock); - list_add(&req->rq_bc_pa_list, &xprt->bc_pa_list); + list_add_tail(&req->rq_bc_pa_list, &xprt->bc_pa_list); spin_unlock_bh(&xprt->bc_pa_lock); } +/* + * One or more rpc_rqst structure have been preallocated during the + * backchannel setup. Buffer space for the send and private XDR buffers + * has been preallocated as well. Use xprt_alloc_bc_request to allocate + * to this request. Use xprt_free_bc_request to return it. + * + * We know that we're called in soft interrupt context, grab the spin_lock + * since there is no need to grab the bottom half spin_lock. + * + * Return an available rpc_rqst, otherwise NULL if non are available. + */ +struct rpc_rqst *xprt_lookup_bc_request(struct rpc_xprt *xprt, __be32 xid) +{ + struct rpc_rqst *req; + + spin_lock(&xprt->bc_pa_lock); + list_for_each_entry(req, &xprt->bc_pa_list, rq_bc_pa_list) { + if (req->rq_connect_cookie != xprt->connect_cookie) + continue; + if (req->rq_xid == xid) + goto found; + } + req = xprt_alloc_bc_request(xprt, xid); +found: + spin_unlock(&xprt->bc_pa_lock); + return req; +} + +/* + * Add callback request to callback list. The callback + * service sleeps on the sv_cb_waitq waiting for new + * requests. Wake it up after adding enqueing the + * request. + */ +void xprt_complete_bc_request(struct rpc_rqst *req, uint32_t copied) +{ + struct rpc_xprt *xprt = req->rq_xprt; + struct svc_serv *bc_serv = xprt->bc_serv; + + req->rq_private_buf.len = copied; + set_bit(RPC_BC_PA_IN_USE, &req->rq_bc_pa_state); + + dprintk("RPC: add callback request to list\n"); + spin_lock(&bc_serv->sv_cb_lock); + list_del(&req->rq_bc_pa_list); + list_add(&req->rq_bc_list, &bc_serv->sv_cb_list); + wake_up(&bc_serv->sv_cb_waitq); + spin_unlock(&bc_serv->sv_cb_lock); +} + diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c index 0edada9..2e6ab10 100644 --- a/net/sunrpc/clnt.c +++ b/net/sunrpc/clnt.c @@ -438,6 +438,38 @@ out_no_rpciod: return ERR_PTR(err); } +struct rpc_clnt *rpc_create_xprt(struct rpc_create_args *args, + struct rpc_xprt *xprt) +{ + struct rpc_clnt *clnt = NULL; + + clnt = rpc_new_client(args, xprt, NULL); + if (IS_ERR(clnt)) + return clnt; + + if (!(args->flags & RPC_CLNT_CREATE_NOPING)) { + int err = rpc_ping(clnt); + if (err != 0) { + rpc_shutdown_client(clnt); + return ERR_PTR(err); + } + } + + clnt->cl_softrtry = 1; + if (args->flags & RPC_CLNT_CREATE_HARDRTRY) + clnt->cl_softrtry = 0; + + if (args->flags & RPC_CLNT_CREATE_AUTOBIND) + clnt->cl_autobind = 1; + if (args->flags & RPC_CLNT_CREATE_DISCRTRY) + clnt->cl_discrtry = 1; + if (!(args->flags & RPC_CLNT_CREATE_QUIET)) + clnt->cl_chatty = 1; + + return clnt; +} +EXPORT_SYMBOL_GPL(rpc_create_xprt); + /** * rpc_create - create an RPC client and transport with one call * @args: rpc_clnt create argument structure @@ -451,7 +483,6 @@ out_no_rpciod: struct rpc_clnt *rpc_create(struct rpc_create_args *args) { struct rpc_xprt *xprt; - struct rpc_clnt *clnt; struct xprt_create xprtargs = { .net = args->net, .ident = args->protocol, @@ -515,30 +546,7 @@ struct rpc_clnt *rpc_create(struct rpc_create_args *args) if (args->flags & RPC_CLNT_CREATE_NONPRIVPORT) xprt->resvport = 0; - clnt = rpc_new_client(args, xprt, NULL); - if (IS_ERR(clnt)) - return clnt; - - if (!(args->flags & RPC_CLNT_CREATE_NOPING)) { - int err = rpc_ping(clnt); - if (err != 0) { - rpc_shutdown_client(clnt); - return ERR_PTR(err); - } - } - - clnt->cl_softrtry = 1; - if (args->flags & RPC_CLNT_CREATE_HARDRTRY) - clnt->cl_softrtry = 0; - - if (args->flags & RPC_CLNT_CREATE_AUTOBIND) - clnt->cl_autobind = 1; - if (args->flags & RPC_CLNT_CREATE_DISCRTRY) - clnt->cl_discrtry = 1; - if (!(args->flags & RPC_CLNT_CREATE_QUIET)) - clnt->cl_chatty = 1; - - return clnt; + return rpc_create_xprt(args, xprt); } EXPORT_SYMBOL_GPL(rpc_create); @@ -1363,6 +1371,7 @@ rpc_restart_call_prepare(struct rpc_task *task) if (RPC_ASSASSINATED(task)) return 0; task->tk_action = call_start; + task->tk_status = 0; if (task->tk_ops->rpc_call_prepare != NULL) task->tk_action = rpc_prepare_task; return 1; @@ -1379,6 +1388,7 @@ rpc_restart_call(struct rpc_task *task) if (RPC_ASSASSINATED(task)) return 0; task->tk_action = call_start; + task->tk_status = 0; return 1; } EXPORT_SYMBOL_GPL(rpc_restart_call); @@ -1728,9 +1738,7 @@ call_bind_status(struct rpc_task *task) case -EPROTONOSUPPORT: dprintk("RPC: %5u remote rpcbind version unavailable, retrying\n", task->tk_pid); - task->tk_status = 0; - task->tk_action = call_bind; - return; + goto retry_timeout; case -ECONNREFUSED: /* connection problems */ case -ECONNRESET: case -ECONNABORTED: @@ -1756,6 +1764,7 @@ call_bind_status(struct rpc_task *task) return; retry_timeout: + task->tk_status = 0; task->tk_action = call_timeout; } @@ -1798,21 +1807,19 @@ call_connect_status(struct rpc_task *task) trace_rpc_connect_status(task, status); task->tk_status = 0; switch (status) { - /* if soft mounted, test if we've timed out */ - case -ETIMEDOUT: - task->tk_action = call_timeout; - return; case -ECONNREFUSED: case -ECONNRESET: case -ECONNABORTED: case -ENETUNREACH: case -EHOSTUNREACH: - /* retry with existing socket, after a delay */ - rpc_delay(task, 3*HZ); if (RPC_IS_SOFTCONN(task)) break; + /* retry with existing socket, after a delay */ + rpc_delay(task, 3*HZ); case -EAGAIN: - task->tk_action = call_bind; + /* Check for timeouts before looping back to call_bind */ + case -ETIMEDOUT: + task->tk_action = call_timeout; return; case 0: clnt->cl_stats->netreconn++; @@ -2007,6 +2014,10 @@ call_status(struct rpc_task *task) case -EHOSTDOWN: case -EHOSTUNREACH: case -ENETUNREACH: + if (RPC_IS_SOFTCONN(task)) { + rpc_exit(task, status); + break; + } /* * Delay any retries for 3 seconds, then handle as if it * were a timeout. diff --git a/net/sunrpc/sched.c b/net/sunrpc/sched.c index ff3cc4b..25578af 100644 --- a/net/sunrpc/sched.c +++ b/net/sunrpc/sched.c @@ -637,7 +637,8 @@ static void __rpc_queue_timer_fn(unsigned long ptr) static void __rpc_atrun(struct rpc_task *task) { - task->tk_status = 0; + if (task->tk_status == -ETIMEDOUT) + task->tk_status = 0; } /* diff --git a/net/sunrpc/svcsock.c b/net/sunrpc/svcsock.c index b6e59f0..43bcb46 100644 --- a/net/sunrpc/svcsock.c +++ b/net/sunrpc/svcsock.c @@ -60,7 +60,7 @@ static struct svc_sock *svc_setup_socket(struct svc_serv *, struct socket *, int flags); -static void svc_udp_data_ready(struct sock *, int); +static void svc_udp_data_ready(struct sock *); static int svc_udp_recvfrom(struct svc_rqst *); static int svc_udp_sendto(struct svc_rqst *); static void svc_sock_detach(struct svc_xprt *); @@ -403,14 +403,14 @@ static void svc_sock_setbufsize(struct socket *sock, unsigned int snd, /* * INET callback when data has been received on the socket. */ -static void svc_udp_data_ready(struct sock *sk, int count) +static void svc_udp_data_ready(struct sock *sk) { struct svc_sock *svsk = (struct svc_sock *)sk->sk_user_data; wait_queue_head_t *wq = sk_sleep(sk); if (svsk) { - dprintk("svc: socket %p(inet %p), count=%d, busy=%d\n", - svsk, sk, count, + dprintk("svc: socket %p(inet %p), busy=%d\n", + svsk, sk, test_bit(XPT_BUSY, &svsk->sk_xprt.xpt_flags)); set_bit(XPT_DATA, &svsk->sk_xprt.xpt_flags); svc_xprt_enqueue(&svsk->sk_xprt); @@ -731,7 +731,7 @@ static void svc_udp_init(struct svc_sock *svsk, struct svc_serv *serv) * A data_ready event on a listening socket means there's a connection * pending. Do not use state_change as a substitute for it. */ -static void svc_tcp_listen_data_ready(struct sock *sk, int count_unused) +static void svc_tcp_listen_data_ready(struct sock *sk) { struct svc_sock *svsk = (struct svc_sock *)sk->sk_user_data; wait_queue_head_t *wq; @@ -783,7 +783,7 @@ static void svc_tcp_state_change(struct sock *sk) wake_up_interruptible_all(wq); } -static void svc_tcp_data_ready(struct sock *sk, int count) +static void svc_tcp_data_ready(struct sock *sk) { struct svc_sock *svsk = (struct svc_sock *)sk->sk_user_data; wait_queue_head_t *wq = sk_sleep(sk); @@ -1397,6 +1397,22 @@ static struct svc_sock *svc_setup_socket(struct svc_serv *serv, return svsk; } +bool svc_alien_sock(struct net *net, int fd) +{ + int err; + struct socket *sock = sockfd_lookup(fd, &err); + bool ret = false; + + if (!sock) + goto out; + if (sock_net(sock->sk) != net) + ret = true; + sockfd_put(sock); +out: + return ret; +} +EXPORT_SYMBOL_GPL(svc_alien_sock); + /** * svc_addsock - add a listener socket to an RPC service * @serv: pointer to RPC service to which to add a new listener diff --git a/net/sunrpc/xdr.c b/net/sunrpc/xdr.c index 1504bb1..dd97ba3 100644 --- a/net/sunrpc/xdr.c +++ b/net/sunrpc/xdr.c @@ -833,8 +833,20 @@ xdr_buf_from_iov(struct kvec *iov, struct xdr_buf *buf) } EXPORT_SYMBOL_GPL(xdr_buf_from_iov); -/* Sets subbuf to the portion of buf of length len beginning base bytes - * from the start of buf. Returns -1 if base of length are out of bounds. */ +/** + * xdr_buf_subsegment - set subbuf to a portion of buf + * @buf: an xdr buffer + * @subbuf: the result buffer + * @base: beginning of range in bytes + * @len: length of range in bytes + * + * sets @subbuf to an xdr buffer representing the portion of @buf of + * length @len starting at offset @base. + * + * @buf and @subbuf may be pointers to the same struct xdr_buf. + * + * Returns -1 if base of length are out of bounds. + */ int xdr_buf_subsegment(struct xdr_buf *buf, struct xdr_buf *subbuf, unsigned int base, unsigned int len) @@ -847,9 +859,8 @@ xdr_buf_subsegment(struct xdr_buf *buf, struct xdr_buf *subbuf, len -= subbuf->head[0].iov_len; base = 0; } else { - subbuf->head[0].iov_base = NULL; - subbuf->head[0].iov_len = 0; base -= buf->head[0].iov_len; + subbuf->head[0].iov_len = 0; } if (base < buf->page_len) { @@ -871,9 +882,8 @@ xdr_buf_subsegment(struct xdr_buf *buf, struct xdr_buf *subbuf, len -= subbuf->tail[0].iov_len; base = 0; } else { - subbuf->tail[0].iov_base = NULL; - subbuf->tail[0].iov_len = 0; base -= buf->tail[0].iov_len; + subbuf->tail[0].iov_len = 0; } if (base || len) diff --git a/net/sunrpc/xprt.c b/net/sunrpc/xprt.c index 7d4df99..d173f79 100644 --- a/net/sunrpc/xprt.c +++ b/net/sunrpc/xprt.c @@ -1383,15 +1383,3 @@ void xprt_put(struct rpc_xprt *xprt) if (atomic_dec_and_test(&xprt->count)) xprt_destroy(xprt); } - -/** - * xprt_get - return a reference to an RPC transport. - * @xprt: pointer to the transport - * - */ -struct rpc_xprt *xprt_get(struct rpc_xprt *xprt) -{ - if (atomic_inc_not_zero(&xprt->count)) - return xprt; - return NULL; -} diff --git a/net/sunrpc/xprtrdma/Makefile b/net/sunrpc/xprtrdma/Makefile index 5a8f268..da5136f 100644 --- a/net/sunrpc/xprtrdma/Makefile +++ b/net/sunrpc/xprtrdma/Makefile @@ -1,8 +1,8 @@ -obj-$(CONFIG_SUNRPC_XPRT_RDMA) += xprtrdma.o +obj-$(CONFIG_SUNRPC_XPRT_RDMA_CLIENT) += xprtrdma.o xprtrdma-y := transport.o rpc_rdma.o verbs.o -obj-$(CONFIG_SUNRPC_XPRT_RDMA) += svcrdma.o +obj-$(CONFIG_SUNRPC_XPRT_RDMA_SERVER) += svcrdma.o svcrdma-y := svc_rdma.o svc_rdma_transport.o \ svc_rdma_marshal.o svc_rdma_sendto.o svc_rdma_recvfrom.o diff --git a/net/sunrpc/xprtrdma/rpc_rdma.c b/net/sunrpc/xprtrdma/rpc_rdma.c index e03725b..96ead52 100644 --- a/net/sunrpc/xprtrdma/rpc_rdma.c +++ b/net/sunrpc/xprtrdma/rpc_rdma.c @@ -649,9 +649,7 @@ rpcrdma_inline_fixup(struct rpc_rqst *rqst, char *srcp, int copy_len, int pad) break; page_base = 0; } - rqst->rq_rcv_buf.page_len = olen - copy_len; - } else - rqst->rq_rcv_buf.page_len = 0; + } if (copy_len && rqst->rq_rcv_buf.tail[0].iov_len) { curlen = copy_len; diff --git a/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c b/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c index 0ce7552..8d904e4 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c +++ b/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c @@ -90,6 +90,7 @@ static void rdma_build_arg_xdr(struct svc_rqst *rqstp, sge_no++; } rqstp->rq_respages = &rqstp->rq_pages[sge_no]; + rqstp->rq_next_page = rqstp->rq_respages + 1; /* We should never run out of SGE because the limit is defined to * support the max allowed RPC data length @@ -169,6 +170,7 @@ static int map_read_chunks(struct svcxprt_rdma *xprt, */ head->arg.pages[page_no] = rqstp->rq_arg.pages[page_no]; rqstp->rq_respages = &rqstp->rq_arg.pages[page_no+1]; + rqstp->rq_next_page = rqstp->rq_respages + 1; byte_count -= sge_bytes; ch_bytes -= sge_bytes; @@ -276,6 +278,7 @@ static int fast_reg_read_chunks(struct svcxprt_rdma *xprt, /* rq_respages points one past arg pages */ rqstp->rq_respages = &rqstp->rq_arg.pages[page_no]; + rqstp->rq_next_page = rqstp->rq_respages + 1; /* Create the reply and chunk maps */ offset = 0; @@ -520,13 +523,6 @@ next_sge: for (ch_no = 0; &rqstp->rq_pages[ch_no] < rqstp->rq_respages; ch_no++) rqstp->rq_pages[ch_no] = NULL; - /* - * Detach res pages. If svc_release sees any it will attempt to - * put them. - */ - while (rqstp->rq_next_page != rqstp->rq_respages) - *(--rqstp->rq_next_page) = NULL; - return err; } @@ -550,7 +546,7 @@ static int rdma_read_complete(struct svc_rqst *rqstp, /* rq_respages starts after the last arg page */ rqstp->rq_respages = &rqstp->rq_arg.pages[page_no]; - rqstp->rq_next_page = &rqstp->rq_arg.pages[page_no]; + rqstp->rq_next_page = rqstp->rq_respages + 1; /* Rebuild rq_arg head and tail. */ rqstp->rq_arg.head[0] = head->arg.head[0]; diff --git a/net/sunrpc/xprtrdma/svc_rdma_sendto.c b/net/sunrpc/xprtrdma/svc_rdma_sendto.c index c1d124d..7e024a5 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_sendto.c +++ b/net/sunrpc/xprtrdma/svc_rdma_sendto.c @@ -265,6 +265,7 @@ static dma_addr_t dma_map_xdr(struct svcxprt_rdma *xprt, xdr_off -= xdr->head[0].iov_len; if (xdr_off < xdr->page_len) { /* This offset is in the page list */ + xdr_off += xdr->page_base; page = xdr->pages[xdr_off >> PAGE_SHIFT]; xdr_off &= ~PAGE_MASK; } else { @@ -625,6 +626,7 @@ static int send_reply(struct svcxprt_rdma *rdma, if (page_no+1 >= sge_no) ctxt->sge[page_no+1].length = 0; } + rqstp->rq_next_page = rqstp->rq_respages + 1; BUG_ON(sge_no > rdma->sc_max_sge); memset(&send_wr, 0, sizeof send_wr); ctxt->wr_op = IB_WR_SEND; diff --git a/net/sunrpc/xprtrdma/svc_rdma_transport.c b/net/sunrpc/xprtrdma/svc_rdma_transport.c index 62e4f9b..25688fa 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_transport.c +++ b/net/sunrpc/xprtrdma/svc_rdma_transport.c @@ -477,8 +477,7 @@ struct page *svc_rdma_get_page(void) while ((page = alloc_page(GFP_KERNEL)) == NULL) { /* If we can't get memory, wait a bit and try again */ - printk(KERN_INFO "svcrdma: out of memory...retrying in 1000 " - "jiffies.\n"); + printk(KERN_INFO "svcrdma: out of memory...retrying in 1s\n"); schedule_timeout_uninterruptible(msecs_to_jiffies(1000)); } return page; diff --git a/net/sunrpc/xprtrdma/transport.c b/net/sunrpc/xprtrdma/transport.c index 285dc08..1eb9c46 100644 --- a/net/sunrpc/xprtrdma/transport.c +++ b/net/sunrpc/xprtrdma/transport.c @@ -733,7 +733,7 @@ static void __exit xprt_rdma_cleanup(void) { int rc; - dprintk(KERN_INFO "RPCRDMA Module Removed, deregister RPC RDMA transport\n"); + dprintk("RPCRDMA Module Removed, deregister RPC RDMA transport\n"); #ifdef RPC_DEBUG if (sunrpc_table_header) { unregister_sysctl_table(sunrpc_table_header); @@ -755,14 +755,14 @@ static int __init xprt_rdma_init(void) if (rc) return rc; - dprintk(KERN_INFO "RPCRDMA Module Init, register RPC RDMA transport\n"); + dprintk("RPCRDMA Module Init, register RPC RDMA transport\n"); - dprintk(KERN_INFO "Defaults:\n"); - dprintk(KERN_INFO "\tSlots %d\n" + dprintk("Defaults:\n"); + dprintk("\tSlots %d\n" "\tMaxInlineRead %d\n\tMaxInlineWrite %d\n", xprt_rdma_slot_table_entries, xprt_rdma_max_inline_read, xprt_rdma_max_inline_write); - dprintk(KERN_INFO "\tPadding %d\n\tMemreg %d\n", + dprintk("\tPadding %d\n\tMemreg %d\n", xprt_rdma_inline_write_padding, xprt_rdma_memreg_strategy); #ifdef RPC_DEBUG diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c index 0addefc..25a3dcf 100644 --- a/net/sunrpc/xprtsock.c +++ b/net/sunrpc/xprtsock.c @@ -254,7 +254,7 @@ struct sock_xprt { /* * Saved socket callback addresses */ - void (*old_data_ready)(struct sock *, int); + void (*old_data_ready)(struct sock *); void (*old_state_change)(struct sock *); void (*old_write_space)(struct sock *); void (*old_error_report)(struct sock *); @@ -909,6 +909,12 @@ static void xs_tcp_close(struct rpc_xprt *xprt) xs_tcp_shutdown(xprt); } +static void xs_xprt_free(struct rpc_xprt *xprt) +{ + xs_free_peer_addresses(xprt); + xprt_free(xprt); +} + /** * xs_destroy - prepare to shutdown a transport * @xprt: doomed transport @@ -919,8 +925,7 @@ static void xs_destroy(struct rpc_xprt *xprt) dprintk("RPC: xs_destroy xprt %p\n", xprt); xs_close(xprt); - xs_free_peer_addresses(xprt); - xprt_free(xprt); + xs_xprt_free(xprt); module_put(THIS_MODULE); } @@ -946,7 +951,7 @@ static int xs_local_copy_to_xdr(struct xdr_buf *xdr, struct sk_buff *skb) * * Currently this assumes we can read the whole reply in a single gulp. */ -static void xs_local_data_ready(struct sock *sk, int len) +static void xs_local_data_ready(struct sock *sk) { struct rpc_task *task; struct rpc_xprt *xprt; @@ -1009,7 +1014,7 @@ static void xs_local_data_ready(struct sock *sk, int len) * @len: how much data to read * */ -static void xs_udp_data_ready(struct sock *sk, int len) +static void xs_udp_data_ready(struct sock *sk) { struct rpc_task *task; struct rpc_xprt *xprt; @@ -1306,41 +1311,29 @@ static inline int xs_tcp_read_reply(struct rpc_xprt *xprt, * If we're unable to obtain the rpc_rqst we schedule the closing of the * connection and return -1. */ -static inline int xs_tcp_read_callback(struct rpc_xprt *xprt, +static int xs_tcp_read_callback(struct rpc_xprt *xprt, struct xdr_skb_reader *desc) { struct sock_xprt *transport = container_of(xprt, struct sock_xprt, xprt); struct rpc_rqst *req; - req = xprt_alloc_bc_request(xprt); + /* Look up and lock the request corresponding to the given XID */ + spin_lock(&xprt->transport_lock); + req = xprt_lookup_bc_request(xprt, transport->tcp_xid); if (req == NULL) { + spin_unlock(&xprt->transport_lock); printk(KERN_WARNING "Callback slot table overflowed\n"); xprt_force_disconnect(xprt); return -1; } - req->rq_xid = transport->tcp_xid; dprintk("RPC: read callback XID %08x\n", ntohl(req->rq_xid)); xs_tcp_read_common(xprt, desc, req); - if (!(transport->tcp_flags & TCP_RCV_COPY_DATA)) { - struct svc_serv *bc_serv = xprt->bc_serv; - - /* - * Add callback request to callback list. The callback - * service sleeps on the sv_cb_waitq waiting for new - * requests. Wake it up after adding enqueing the - * request. - */ - dprintk("RPC: add callback request to list\n"); - spin_lock(&bc_serv->sv_cb_lock); - list_add(&req->rq_bc_list, &bc_serv->sv_cb_list); - spin_unlock(&bc_serv->sv_cb_lock); - wake_up(&bc_serv->sv_cb_waitq); - } - - req->rq_private_buf.len = transport->tcp_copied; + if (!(transport->tcp_flags & TCP_RCV_COPY_DATA)) + xprt_complete_bc_request(req, transport->tcp_copied); + spin_unlock(&xprt->transport_lock); return 0; } @@ -1444,7 +1437,7 @@ static int xs_tcp_data_recv(read_descriptor_t *rd_desc, struct sk_buff *skb, uns * @bytes: how much data to read * */ -static void xs_tcp_data_ready(struct sock *sk, int bytes) +static void xs_tcp_data_ready(struct sock *sk) { struct rpc_xprt *xprt; read_descriptor_t rd_desc; @@ -2544,6 +2537,10 @@ static void bc_close(struct rpc_xprt *xprt) static void bc_destroy(struct rpc_xprt *xprt) { + dprintk("RPC: bc_destroy xprt %p\n", xprt); + + xs_xprt_free(xprt); + module_put(THIS_MODULE); } static struct rpc_xprt_ops xs_local_ops = { @@ -2744,7 +2741,7 @@ static struct rpc_xprt *xs_setup_local(struct xprt_create *args) return xprt; ret = ERR_PTR(-EINVAL); out_err: - xprt_free(xprt); + xs_xprt_free(xprt); return ret; } @@ -2822,7 +2819,7 @@ static struct rpc_xprt *xs_setup_udp(struct xprt_create *args) return xprt; ret = ERR_PTR(-EINVAL); out_err: - xprt_free(xprt); + xs_xprt_free(xprt); return ret; } @@ -2897,12 +2894,11 @@ static struct rpc_xprt *xs_setup_tcp(struct xprt_create *args) xprt->address_strings[RPC_DISPLAY_ADDR], xprt->address_strings[RPC_DISPLAY_PROTO]); - if (try_module_get(THIS_MODULE)) return xprt; ret = ERR_PTR(-EINVAL); out_err: - xprt_free(xprt); + xs_xprt_free(xprt); return ret; } @@ -2919,15 +2915,6 @@ static struct rpc_xprt *xs_setup_bc_tcp(struct xprt_create *args) struct svc_sock *bc_sock; struct rpc_xprt *ret; - if (args->bc_xprt->xpt_bc_xprt) { - /* - * This server connection already has a backchannel - * transport; we can't create a new one, as we wouldn't - * be able to match replies based on xid any more. So, - * reuse the already-existing one: - */ - return args->bc_xprt->xpt_bc_xprt; - } xprt = xs_setup_xprt(args, xprt_tcp_slot_table_entries, xprt_tcp_slot_table_entries); if (IS_ERR(xprt)) @@ -2985,13 +2972,14 @@ static struct rpc_xprt *xs_setup_bc_tcp(struct xprt_create *args) */ xprt_set_connected(xprt); - if (try_module_get(THIS_MODULE)) return xprt; + + args->bc_xprt->xpt_bc_xprt = NULL; xprt_put(xprt); ret = ERR_PTR(-EINVAL); out_err: - xprt_free(xprt); + xs_xprt_free(xprt); return ret; } diff --git a/net/tipc/netlink.c b/net/tipc/netlink.c index 3aaf73d..ad844d3 100644 --- a/net/tipc/netlink.c +++ b/net/tipc/netlink.c @@ -47,7 +47,7 @@ static int handle_cmd(struct sk_buff *skb, struct genl_info *info) int hdr_space = nlmsg_total_size(GENL_HDRLEN + TIPC_GENL_HDRLEN); u16 cmd; - if ((req_userhdr->cmd & 0xC000) && (!capable(CAP_NET_ADMIN))) + if ((req_userhdr->cmd & 0xC000) && (!netlink_capable(skb, CAP_NET_ADMIN))) cmd = TIPC_CMD_NOT_NET_ADMIN; else cmd = req_userhdr->cmd; diff --git a/net/tipc/server.c b/net/tipc/server.c index 646a930..a538a02 100644 --- a/net/tipc/server.c +++ b/net/tipc/server.c @@ -119,7 +119,7 @@ static struct tipc_conn *tipc_conn_lookup(struct tipc_server *s, int conid) return con; } -static void sock_data_ready(struct sock *sk, int unused) +static void sock_data_ready(struct sock *sk) { struct tipc_conn *con; @@ -297,7 +297,7 @@ static int tipc_accept_from_sock(struct tipc_conn *con) newcon->usr_data = s->tipc_conn_new(newcon->conid); /* Wake up receive process in case of 'SYN+' message */ - newsock->sk->sk_data_ready(newsock->sk, 0); + newsock->sk->sk_data_ready(newsock->sk); return ret; } diff --git a/net/tipc/socket.c b/net/tipc/socket.c index 29b7f26..3c02569 100644 --- a/net/tipc/socket.c +++ b/net/tipc/socket.c @@ -45,7 +45,7 @@ #define CONN_TIMEOUT_DEFAULT 8000 /* default connect timeout = 8s */ static int backlog_rcv(struct sock *sk, struct sk_buff *skb); -static void tipc_data_ready(struct sock *sk, int len); +static void tipc_data_ready(struct sock *sk); static void tipc_write_space(struct sock *sk); static int tipc_release(struct socket *sock); static int tipc_accept(struct socket *sock, struct socket *new_sock, int flags); @@ -301,7 +301,6 @@ static int tipc_release(struct socket *sock) struct tipc_sock *tsk; struct tipc_port *port; struct sk_buff *buf; - int res; /* * Exit if socket isn't fully initialized (occurs when a failed accept() @@ -349,7 +348,7 @@ static int tipc_release(struct socket *sock) sock_put(sk); sock->sk = NULL; - return res; + return 0; } /** @@ -1249,7 +1248,7 @@ static void tipc_write_space(struct sock *sk) * @sk: socket * @len: the length of messages */ -static void tipc_data_ready(struct sock *sk, int len) +static void tipc_data_ready(struct sock *sk) { struct socket_wq *wq; @@ -1411,7 +1410,7 @@ static u32 filter_rcv(struct sock *sk, struct sk_buff *buf) __skb_queue_tail(&sk->sk_receive_queue, buf); skb_set_owner_r(buf, sk); - sk->sk_data_ready(sk, 0); + sk->sk_data_ready(sk); return TIPC_OK; } diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index 94404f1..bb7e8ba 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -1217,7 +1217,7 @@ restart: __skb_queue_tail(&other->sk_receive_queue, skb); spin_unlock(&other->sk_receive_queue.lock); unix_state_unlock(other); - other->sk_data_ready(other, 0); + other->sk_data_ready(other); sock_put(other); return 0; @@ -1600,7 +1600,7 @@ restart: if (max_level > unix_sk(other)->recursion_level) unix_sk(other)->recursion_level = max_level; unix_state_unlock(other); - other->sk_data_ready(other, len); + other->sk_data_ready(other); sock_put(other); scm_destroy(siocb->scm); return len; @@ -1706,7 +1706,7 @@ static int unix_stream_sendmsg(struct kiocb *kiocb, struct socket *sock, if (max_level > unix_sk(other)->recursion_level) unix_sk(other)->recursion_level = max_level; unix_state_unlock(other); - other->sk_data_ready(other, size); + other->sk_data_ready(other); sent += size; } diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c index 5adfd94..85d232b 100644 --- a/net/vmw_vsock/af_vsock.c +++ b/net/vmw_vsock/af_vsock.c @@ -1925,9 +1925,23 @@ static struct miscdevice vsock_device = { .fops = &vsock_device_ops, }; -static int __vsock_core_init(void) +int __vsock_core_init(const struct vsock_transport *t, struct module *owner) { - int err; + int err = mutex_lock_interruptible(&vsock_register_mutex); + + if (err) + return err; + + if (transport) { + err = -EBUSY; + goto err_busy; + } + + /* Transport must be the owner of the protocol so that it can't + * unload while there are open sockets. + */ + vsock_proto.owner = owner; + transport = t; vsock_init_tables(); @@ -1951,36 +1965,19 @@ static int __vsock_core_init(void) goto err_unregister_proto; } + mutex_unlock(&vsock_register_mutex); return 0; err_unregister_proto: proto_unregister(&vsock_proto); err_misc_deregister: misc_deregister(&vsock_device); - return err; -} - -int vsock_core_init(const struct vsock_transport *t) -{ - int retval = mutex_lock_interruptible(&vsock_register_mutex); - if (retval) - return retval; - - if (transport) { - retval = -EBUSY; - goto out; - } - - transport = t; - retval = __vsock_core_init(); - if (retval) - transport = NULL; - -out: + transport = NULL; +err_busy: mutex_unlock(&vsock_register_mutex); - return retval; + return err; } -EXPORT_SYMBOL_GPL(vsock_core_init); +EXPORT_SYMBOL_GPL(__vsock_core_init); void vsock_core_exit(void) { @@ -2000,5 +1997,5 @@ EXPORT_SYMBOL_GPL(vsock_core_exit); MODULE_AUTHOR("VMware, Inc."); MODULE_DESCRIPTION("VMware Virtual Socket Family"); -MODULE_VERSION("1.0.0.0-k"); +MODULE_VERSION("1.0.1.0-k"); MODULE_LICENSE("GPL v2"); diff --git a/net/vmw_vsock/vmci_transport_notify.c b/net/vmw_vsock/vmci_transport_notify.c index 9a73074..9b7f207 100644 --- a/net/vmw_vsock/vmci_transport_notify.c +++ b/net/vmw_vsock/vmci_transport_notify.c @@ -315,7 +315,7 @@ vmci_transport_handle_wrote(struct sock *sk, struct vsock_sock *vsk = vsock_sk(sk); PKT_FIELD(vsk, sent_waiting_read) = false; #endif - sk->sk_data_ready(sk, 0); + sk->sk_data_ready(sk); } static void vmci_transport_notify_pkt_socket_init(struct sock *sk) diff --git a/net/vmw_vsock/vmci_transport_notify_qstate.c b/net/vmw_vsock/vmci_transport_notify_qstate.c index 622bd7a..dc9c792 100644 --- a/net/vmw_vsock/vmci_transport_notify_qstate.c +++ b/net/vmw_vsock/vmci_transport_notify_qstate.c @@ -92,7 +92,7 @@ vmci_transport_handle_wrote(struct sock *sk, bool bottom_half, struct sockaddr_vm *dst, struct sockaddr_vm *src) { - sk->sk_data_ready(sk, 0); + sk->sk_data_ready(sk); } static void vsock_block_update_write_window(struct sock *sk) @@ -290,7 +290,7 @@ vmci_transport_notify_pkt_recv_post_dequeue( /* See the comment in * vmci_transport_notify_pkt_send_post_enqueue(). */ - sk->sk_data_ready(sk, 0); + sk->sk_data_ready(sk); } return err; diff --git a/net/wireless/scan.c b/net/wireless/scan.c index 7d09a71..88f108e 100644 --- a/net/wireless/scan.c +++ b/net/wireless/scan.c @@ -284,14 +284,22 @@ void cfg80211_sched_scan_results(struct wiphy *wiphy) } EXPORT_SYMBOL(cfg80211_sched_scan_results); -void cfg80211_sched_scan_stopped(struct wiphy *wiphy) +void cfg80211_sched_scan_stopped_rtnl(struct wiphy *wiphy) { struct cfg80211_registered_device *rdev = wiphy_to_dev(wiphy); + ASSERT_RTNL(); + trace_cfg80211_sched_scan_stopped(wiphy); - rtnl_lock(); __cfg80211_stop_sched_scan(rdev, true); +} +EXPORT_SYMBOL(cfg80211_sched_scan_stopped_rtnl); + +void cfg80211_sched_scan_stopped(struct wiphy *wiphy) +{ + rtnl_lock(); + cfg80211_sched_scan_stopped_rtnl(wiphy); rtnl_unlock(); } EXPORT_SYMBOL(cfg80211_sched_scan_stopped); diff --git a/net/wireless/sme.c b/net/wireless/sme.c index acdcb4a8..3546a77 100644 --- a/net/wireless/sme.c +++ b/net/wireless/sme.c @@ -234,7 +234,6 @@ void cfg80211_conn_work(struct work_struct *work) NULL, 0, NULL, 0, WLAN_STATUS_UNSPECIFIED_FAILURE, false, NULL); - cfg80211_sme_free(wdev); } wdev_unlock(wdev); } @@ -648,6 +647,7 @@ void __cfg80211_connect_result(struct net_device *dev, const u8 *bssid, cfg80211_unhold_bss(bss_from_pub(bss)); cfg80211_put_bss(wdev->wiphy, bss); } + cfg80211_sme_free(wdev); return; } diff --git a/net/x25/af_x25.c b/net/x25/af_x25.c index 6177479..5ad4418 100644 --- a/net/x25/af_x25.c +++ b/net/x25/af_x25.c @@ -1064,7 +1064,7 @@ int x25_rx_call_request(struct sk_buff *skb, struct x25_neigh *nb, x25_start_heartbeat(make); if (!sock_flag(sk, SOCK_DEAD)) - sk->sk_data_ready(sk, skb->len); + sk->sk_data_ready(sk); rc = 1; sock_put(sk); out: diff --git a/net/x25/x25_in.c b/net/x25/x25_in.c index d1b0dc7..7ac5009 100644 --- a/net/x25/x25_in.c +++ b/net/x25/x25_in.c @@ -79,7 +79,7 @@ static int x25_queue_rx_frame(struct sock *sk, struct sk_buff *skb, int more) skb_set_owner_r(skbn, sk); skb_queue_tail(&sk->sk_receive_queue, skbn); if (!sock_flag(sk, SOCK_DEAD)) - sk->sk_data_ready(sk, skbn->len); + sk->sk_data_ready(sk); return 0; } diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index f02f511..c08fbd1 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -1842,7 +1842,7 @@ purge_queue: xfrm_pol_put(pol); } -static int xdst_queue_output(struct sk_buff *skb) +static int xdst_queue_output(struct sock *sk, struct sk_buff *skb) { unsigned long sched_next; struct dst_entry *dst = skb_dst(skb); diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c index 8f131c1..51398ae 100644 --- a/net/xfrm/xfrm_user.c +++ b/net/xfrm/xfrm_user.c @@ -2377,7 +2377,7 @@ static int xfrm_user_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh) link = &xfrm_dispatch[type]; /* All operations require privileges, even GET */ - if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) + if (!netlink_net_capable(skb, CAP_NET_ADMIN)) return -EPERM; if ((type == (XFRM_MSG_GETSA - XFRM_MSG_BASE) || |
