diff options
Diffstat (limited to 'net')
219 files changed, 10619 insertions, 3023 deletions
diff --git a/net/8021q/vlan.c b/net/8021q/vlan.c index 82a116ba590e..8de138d3306b 100644 --- a/net/8021q/vlan.c +++ b/net/8021q/vlan.c @@ -169,7 +169,7 @@ int register_vlan_dev(struct net_device *dev) if (err < 0) goto out_uninit_mvrp; - vlan->nest_level = dev_get_nest_level(real_dev, is_vlan_dev) + 1; + vlan->nest_level = dev_get_nest_level(real_dev) + 1; err = register_netdevice(dev); if (err < 0) goto out_uninit_mvrp; diff --git a/net/9p/trans_virtio.c b/net/9p/trans_virtio.c index 4acb1d5417aa..f24b25c25106 100644 --- a/net/9p/trans_virtio.c +++ b/net/9p/trans_virtio.c @@ -507,8 +507,8 @@ err_out: /* wakeup anybody waiting for slots to pin pages */ wake_up(&vp_wq); } - kfree(in_pages); - kfree(out_pages); + kvfree(in_pages); + kvfree(out_pages); return err; } diff --git a/net/Kconfig b/net/Kconfig index c2cdbce629bd..7b6cd340b72b 100644 --- a/net/Kconfig +++ b/net/Kconfig @@ -369,6 +369,7 @@ source "net/irda/Kconfig" source "net/bluetooth/Kconfig" source "net/rxrpc/Kconfig" source "net/kcm/Kconfig" +source "net/strparser/Kconfig" config FIB_RULES bool diff --git a/net/Makefile b/net/Makefile index 9bd20bb86cc6..4cafaa2b4667 100644 --- a/net/Makefile +++ b/net/Makefile @@ -35,6 +35,7 @@ obj-$(CONFIG_BT) += bluetooth/ obj-$(CONFIG_SUNRPC) += sunrpc/ obj-$(CONFIG_AF_RXRPC) += rxrpc/ obj-$(CONFIG_AF_KCM) += kcm/ +obj-$(CONFIG_STREAM_PARSER) += strparser/ obj-$(CONFIG_ATM) += atm/ obj-$(CONFIG_L2TP) += l2tp/ obj-$(CONFIG_DECNET) += decnet/ diff --git a/net/atm/mpc.c b/net/atm/mpc.c index 0e982222d425..3b3b1a292ec8 100644 --- a/net/atm/mpc.c +++ b/net/atm/mpc.c @@ -1007,7 +1007,7 @@ static int mpoa_event_listener(struct notifier_block *mpoa_notifier, if (!net_eq(dev_net(dev), &init_net)) return NOTIFY_DONE; - if (dev->name == NULL || strncmp(dev->name, "lec", 3)) + if (strncmp(dev->name, "lec", 3)) return NOTIFY_DONE; /* we are only interested in lec:s */ switch (event) { diff --git a/net/batman-adv/Kconfig b/net/batman-adv/Kconfig index 833bb145ba3c..f20742cbae6d 100644 --- a/net/batman-adv/Kconfig +++ b/net/batman-adv/Kconfig @@ -73,10 +73,21 @@ config BATMAN_ADV_MCAST reduce the air overhead while improving the reliability of multicast messages. -config BATMAN_ADV_DEBUG - bool "B.A.T.M.A.N. debugging" +config BATMAN_ADV_DEBUGFS + bool "batman-adv debugfs entries" depends on BATMAN_ADV depends on DEBUG_FS + default y + help + Enable this to export routing related debug tables via debugfs. + The information for each soft-interface and used hard-interface can be + found under batman_adv/ + + If unsure, say Y. + +config BATMAN_ADV_DEBUG + bool "B.A.T.M.A.N. debugging" + depends on BATMAN_ADV_DEBUGFS help This is an option for use by developers; most people should say N here. This enables compilation of support for diff --git a/net/batman-adv/Makefile b/net/batman-adv/Makefile index a83fc6c58d19..f724d3c98a81 100644 --- a/net/batman-adv/Makefile +++ b/net/batman-adv/Makefile @@ -24,14 +24,14 @@ batman-adv-$(CONFIG_BATMAN_ADV_BATMAN_V) += bat_v_elp.o batman-adv-$(CONFIG_BATMAN_ADV_BATMAN_V) += bat_v_ogm.o batman-adv-y += bitarray.o batman-adv-$(CONFIG_BATMAN_ADV_BLA) += bridge_loop_avoidance.o -batman-adv-$(CONFIG_DEBUG_FS) += debugfs.o +batman-adv-$(CONFIG_BATMAN_ADV_DEBUGFS) += debugfs.o batman-adv-$(CONFIG_BATMAN_ADV_DAT) += distributed-arp-table.o batman-adv-y += fragmentation.o batman-adv-y += gateway_client.o batman-adv-y += gateway_common.o batman-adv-y += hard-interface.o batman-adv-y += hash.o -batman-adv-y += icmp_socket.o +batman-adv-$(CONFIG_BATMAN_ADV_DEBUGFS) += icmp_socket.o batman-adv-$(CONFIG_BATMAN_ADV_DEBUG) += log.o batman-adv-y += main.o batman-adv-$(CONFIG_BATMAN_ADV_MCAST) += multicast.o diff --git a/net/batman-adv/bat_algo.c b/net/batman-adv/bat_algo.c index 81dbbf569bd4..623d04302aa2 100644 --- a/net/batman-adv/bat_algo.c +++ b/net/batman-adv/bat_algo.c @@ -20,12 +20,18 @@ #include <linux/errno.h> #include <linux/list.h> #include <linux/moduleparam.h> +#include <linux/netlink.h> #include <linux/printk.h> #include <linux/seq_file.h> +#include <linux/skbuff.h> #include <linux/stddef.h> #include <linux/string.h> +#include <net/genetlink.h> +#include <net/netlink.h> +#include <uapi/linux/batman_adv.h> #include "bat_algo.h" +#include "netlink.h" char batadv_routing_algo[20] = "BATMAN_IV"; static struct hlist_head batadv_algo_list; @@ -95,6 +101,7 @@ int batadv_algo_select(struct batadv_priv *bat_priv, char *name) return 0; } +#ifdef CONFIG_BATMAN_ADV_DEBUGFS int batadv_algo_seq_print_text(struct seq_file *seq, void *offset) { struct batadv_algo_ops *bat_algo_ops; @@ -107,6 +114,7 @@ int batadv_algo_seq_print_text(struct seq_file *seq, void *offset) return 0; } +#endif static int batadv_param_set_ra(const char *val, const struct kernel_param *kp) { @@ -138,3 +146,65 @@ static struct kparam_string batadv_param_string_ra = { module_param_cb(routing_algo, &batadv_param_ops_ra, &batadv_param_string_ra, 0644); + +/** + * batadv_algo_dump_entry - fill in information about one supported routing + * algorithm + * @msg: netlink message to be sent back + * @portid: Port to reply to + * @seq: Sequence number of message + * @bat_algo_ops: Algorithm to be dumped + * + * Return: Error number, or 0 on success + */ +static int batadv_algo_dump_entry(struct sk_buff *msg, u32 portid, u32 seq, + struct batadv_algo_ops *bat_algo_ops) +{ + void *hdr; + + hdr = genlmsg_put(msg, portid, seq, &batadv_netlink_family, + NLM_F_MULTI, BATADV_CMD_GET_ROUTING_ALGOS); + if (!hdr) + return -EMSGSIZE; + + if (nla_put_string(msg, BATADV_ATTR_ALGO_NAME, bat_algo_ops->name)) + goto nla_put_failure; + + genlmsg_end(msg, hdr); + return 0; + + nla_put_failure: + genlmsg_cancel(msg, hdr); + return -EMSGSIZE; +} + +/** + * batadv_algo_dump - fill in information about supported routing + * algorithms + * @msg: netlink message to be sent back + * @cb: Parameters to the netlink request + * + * Return: Length of reply message. + */ +int batadv_algo_dump(struct sk_buff *msg, struct netlink_callback *cb) +{ + int portid = NETLINK_CB(cb->skb).portid; + struct batadv_algo_ops *bat_algo_ops; + int skip = cb->args[0]; + int i = 0; + + hlist_for_each_entry(bat_algo_ops, &batadv_algo_list, list) { + if (i++ < skip) + continue; + + if (batadv_algo_dump_entry(msg, portid, cb->nlh->nlmsg_seq, + bat_algo_ops)) { + i--; + break; + } + } + + cb->args[0] = i; + + return msg->len; +} diff --git a/net/batman-adv/bat_algo.h b/net/batman-adv/bat_algo.h index 860d773dd8fa..3b5b69cdd12b 100644 --- a/net/batman-adv/bat_algo.h +++ b/net/batman-adv/bat_algo.h @@ -22,7 +22,9 @@ #include <linux/types.h> +struct netlink_callback; struct seq_file; +struct sk_buff; extern char batadv_routing_algo[]; extern struct list_head batadv_hardif_list; @@ -31,5 +33,6 @@ void batadv_algo_init(void); int batadv_algo_register(struct batadv_algo_ops *bat_algo_ops); int batadv_algo_select(struct batadv_priv *bat_priv, char *name); int batadv_algo_seq_print_text(struct seq_file *seq, void *offset); +int batadv_algo_dump(struct sk_buff *msg, struct netlink_callback *cb); #endif /* _NET_BATMAN_ADV_BAT_ALGO_H_ */ diff --git a/net/batman-adv/bat_iv_ogm.c b/net/batman-adv/bat_iv_ogm.c index 19b0abd6c640..e2d18d0b1f06 100644 --- a/net/batman-adv/bat_iv_ogm.c +++ b/net/batman-adv/bat_iv_ogm.c @@ -35,6 +35,7 @@ #include <linux/list.h> #include <linux/lockdep.h> #include <linux/netdevice.h> +#include <linux/netlink.h> #include <linux/pkt_sched.h> #include <linux/printk.h> #include <linux/random.h> @@ -48,12 +49,17 @@ #include <linux/string.h> #include <linux/types.h> #include <linux/workqueue.h> +#include <net/genetlink.h> +#include <net/netlink.h> +#include <uapi/linux/batman_adv.h> #include "bat_algo.h" #include "bitarray.h" +#include "gateway_client.h" #include "hard-interface.h" #include "hash.h" #include "log.h" +#include "netlink.h" #include "network-coding.h" #include "originator.h" #include "packet.h" @@ -318,17 +324,18 @@ batadv_iv_ogm_orig_get(struct batadv_priv *bat_priv, const u8 *addr) if (!orig_node->bat_iv.bcast_own_sum) goto free_orig_node; + kref_get(&orig_node->refcount); hash_added = batadv_hash_add(bat_priv->orig_hash, batadv_compare_orig, batadv_choose_orig, orig_node, &orig_node->hash_entry); if (hash_added != 0) - goto free_orig_node; + goto free_orig_node_hash; return orig_node; -free_orig_node: - /* free twice, as batadv_orig_node_new sets refcount to 2 */ +free_orig_node_hash: batadv_orig_node_put(orig_node); +free_orig_node: batadv_orig_node_put(orig_node); return NULL; @@ -528,36 +535,25 @@ static void batadv_iv_ogm_send_to_if(struct batadv_forw_packet *forw_packet, static void batadv_iv_ogm_emit(struct batadv_forw_packet *forw_packet) { struct net_device *soft_iface; - struct batadv_priv *bat_priv; - struct batadv_hard_iface *primary_if = NULL; if (!forw_packet->if_incoming) { pr_err("Error - can't forward packet: incoming iface not specified\n"); - goto out; + return; } soft_iface = forw_packet->if_incoming->soft_iface; - bat_priv = netdev_priv(soft_iface); if (WARN_ON(!forw_packet->if_outgoing)) - goto out; + return; if (WARN_ON(forw_packet->if_outgoing->soft_iface != soft_iface)) - goto out; + return; if (forw_packet->if_incoming->if_status != BATADV_IF_ACTIVE) - goto out; - - primary_if = batadv_primary_if_get_selected(bat_priv); - if (!primary_if) - goto out; + return; /* only for one specific outgoing interface */ batadv_iv_ogm_send_to_if(forw_packet, forw_packet->if_outgoing); - -out: - if (primary_if) - batadv_hardif_put(primary_if); } /** @@ -685,19 +681,12 @@ static void batadv_iv_ogm_aggregate_new(const unsigned char *packet_buff, struct batadv_forw_packet *forw_packet_aggr; unsigned char *skb_buff; unsigned int skb_size; + atomic_t *queue_left = own_packet ? NULL : &bat_priv->batman_queue_left; - /* own packet should always be scheduled */ - if (!own_packet) { - if (!batadv_atomic_dec_not_zero(&bat_priv->batman_queue_left)) { - batadv_dbg(BATADV_DBG_BATMAN, bat_priv, - "batman packet queue full\n"); - return; - } - } - - forw_packet_aggr = kmalloc(sizeof(*forw_packet_aggr), GFP_ATOMIC); + forw_packet_aggr = batadv_forw_packet_alloc(if_incoming, if_outgoing, + queue_left, bat_priv); if (!forw_packet_aggr) - goto out_nomem; + return; if (atomic_read(&bat_priv->aggregated_ogms) && packet_len < BATADV_MAX_AGGREGATION_BYTES) @@ -708,8 +697,11 @@ static void batadv_iv_ogm_aggregate_new(const unsigned char *packet_buff, skb_size += ETH_HLEN; forw_packet_aggr->skb = netdev_alloc_skb_ip_align(NULL, skb_size); - if (!forw_packet_aggr->skb) - goto out_free_forw_packet; + if (!forw_packet_aggr->skb) { + batadv_forw_packet_free(forw_packet_aggr); + return; + } + forw_packet_aggr->skb->priority = TC_PRIO_CONTROL; skb_reserve(forw_packet_aggr->skb, ETH_HLEN); @@ -717,12 +709,7 @@ static void batadv_iv_ogm_aggregate_new(const unsigned char *packet_buff, forw_packet_aggr->packet_len = packet_len; memcpy(skb_buff, packet_buff, packet_len); - kref_get(&if_incoming->refcount); - kref_get(&if_outgoing->refcount); forw_packet_aggr->own = own_packet; - forw_packet_aggr->if_incoming = if_incoming; - forw_packet_aggr->if_outgoing = if_outgoing; - forw_packet_aggr->num_packets = 0; forw_packet_aggr->direct_link_flags = BATADV_NO_FLAGS; forw_packet_aggr->send_time = send_time; @@ -741,13 +728,6 @@ static void batadv_iv_ogm_aggregate_new(const unsigned char *packet_buff, queue_delayed_work(batadv_event_workqueue, &forw_packet_aggr->delayed_work, send_time - jiffies); - - return; -out_free_forw_packet: - kfree(forw_packet_aggr); -out_nomem: - if (!own_packet) - atomic_inc(&bat_priv->batman_queue_left); } /* aggregate a new packet into the existing ogm packet */ @@ -1830,10 +1810,6 @@ static void batadv_iv_send_outstanding_bat_ogm_packet(struct work_struct *work) batadv_iv_ogm_schedule(forw_packet->if_incoming); out: - /* don't count own packet */ - if (!forw_packet->own) - atomic_inc(&bat_priv->batman_queue_left); - batadv_forw_packet_free(forw_packet); } @@ -1879,6 +1855,7 @@ static int batadv_iv_ogm_receive(struct sk_buff *skb, return NET_RX_SUCCESS; } +#ifdef CONFIG_BATMAN_ADV_DEBUGFS /** * batadv_iv_ogm_orig_print_neigh - print neighbors for the originator table * @orig_node: the orig_node for which the neighbors are printed @@ -1976,8 +1953,239 @@ next: if (batman_count == 0) seq_puts(seq, "No batman nodes in range ...\n"); } +#endif + +/** + * batadv_iv_ogm_neigh_get_tq_avg - Get the TQ average for a neighbour on a + * given outgoing interface. + * @neigh_node: Neighbour of interest + * @if_outgoing: Outgoing interface of interest + * @tq_avg: Pointer of where to store the TQ average + * + * Return: False if no average TQ available, otherwise true. + */ +static bool +batadv_iv_ogm_neigh_get_tq_avg(struct batadv_neigh_node *neigh_node, + struct batadv_hard_iface *if_outgoing, + u8 *tq_avg) +{ + struct batadv_neigh_ifinfo *n_ifinfo; + + n_ifinfo = batadv_neigh_ifinfo_get(neigh_node, if_outgoing); + if (!n_ifinfo) + return false; + + *tq_avg = n_ifinfo->bat_iv.tq_avg; + batadv_neigh_ifinfo_put(n_ifinfo); + + return true; +} + +/** + * batadv_iv_ogm_orig_dump_subentry - Dump an originator subentry into a + * message + * @msg: Netlink message to dump into + * @portid: Port making netlink request + * @seq: Sequence number of netlink message + * @bat_priv: The bat priv with all the soft interface information + * @if_outgoing: Limit dump to entries with this outgoing interface + * @orig_node: Originator to dump + * @neigh_node: Single hops neighbour + * @best: Is the best originator + * + * Return: Error code, or 0 on success + */ +static int +batadv_iv_ogm_orig_dump_subentry(struct sk_buff *msg, u32 portid, u32 seq, + struct batadv_priv *bat_priv, + struct batadv_hard_iface *if_outgoing, + struct batadv_orig_node *orig_node, + struct batadv_neigh_node *neigh_node, + bool best) +{ + void *hdr; + u8 tq_avg; + unsigned int last_seen_msecs; + + last_seen_msecs = jiffies_to_msecs(jiffies - orig_node->last_seen); + + if (!batadv_iv_ogm_neigh_get_tq_avg(neigh_node, if_outgoing, &tq_avg)) + return 0; + + if (if_outgoing != BATADV_IF_DEFAULT && + if_outgoing != neigh_node->if_incoming) + return 0; + + hdr = genlmsg_put(msg, portid, seq, &batadv_netlink_family, + NLM_F_MULTI, BATADV_CMD_GET_ORIGINATORS); + if (!hdr) + return -ENOBUFS; + + if (nla_put(msg, BATADV_ATTR_ORIG_ADDRESS, ETH_ALEN, + orig_node->orig) || + nla_put(msg, BATADV_ATTR_NEIGH_ADDRESS, ETH_ALEN, + neigh_node->addr) || + nla_put_u32(msg, BATADV_ATTR_HARD_IFINDEX, + neigh_node->if_incoming->net_dev->ifindex) || + nla_put_u8(msg, BATADV_ATTR_TQ, tq_avg) || + nla_put_u32(msg, BATADV_ATTR_LAST_SEEN_MSECS, + last_seen_msecs)) + goto nla_put_failure; + + if (best && nla_put_flag(msg, BATADV_ATTR_FLAG_BEST)) + goto nla_put_failure; + + genlmsg_end(msg, hdr); + return 0; + + nla_put_failure: + genlmsg_cancel(msg, hdr); + return -EMSGSIZE; +} + +/** + * batadv_iv_ogm_orig_dump_entry - Dump an originator entry into a message + * @msg: Netlink message to dump into + * @portid: Port making netlink request + * @seq: Sequence number of netlink message + * @bat_priv: The bat priv with all the soft interface information + * @if_outgoing: Limit dump to entries with this outgoing interface + * @orig_node: Originator to dump + * @sub_s: Number of sub entries to skip + * + * This function assumes the caller holds rcu_read_lock(). + * + * Return: Error code, or 0 on success + */ +static int +batadv_iv_ogm_orig_dump_entry(struct sk_buff *msg, u32 portid, u32 seq, + struct batadv_priv *bat_priv, + struct batadv_hard_iface *if_outgoing, + struct batadv_orig_node *orig_node, int *sub_s) +{ + struct batadv_neigh_node *neigh_node_best; + struct batadv_neigh_node *neigh_node; + int sub = 0; + bool best; + u8 tq_avg_best; + + neigh_node_best = batadv_orig_router_get(orig_node, if_outgoing); + if (!neigh_node_best) + goto out; + + if (!batadv_iv_ogm_neigh_get_tq_avg(neigh_node_best, if_outgoing, + &tq_avg_best)) + goto out; + + if (tq_avg_best == 0) + goto out; + + hlist_for_each_entry_rcu(neigh_node, &orig_node->neigh_list, list) { + if (sub++ < *sub_s) + continue; + + best = (neigh_node == neigh_node_best); + + if (batadv_iv_ogm_orig_dump_subentry(msg, portid, seq, + bat_priv, if_outgoing, + orig_node, neigh_node, + best)) { + batadv_neigh_node_put(neigh_node_best); + + *sub_s = sub - 1; + return -EMSGSIZE; + } + } + + out: + if (neigh_node_best) + batadv_neigh_node_put(neigh_node_best); + + *sub_s = 0; + return 0; +} /** + * batadv_iv_ogm_orig_dump_bucket - Dump an originator bucket into a + * message + * @msg: Netlink message to dump into + * @portid: Port making netlink request + * @seq: Sequence number of netlink message + * @bat_priv: The bat priv with all the soft interface information + * @if_outgoing: Limit dump to entries with this outgoing interface + * @head: Bucket to be dumped + * @idx_s: Number of entries to be skipped + * @sub: Number of sub entries to be skipped + * + * Return: Error code, or 0 on success + */ +static int +batadv_iv_ogm_orig_dump_bucket(struct sk_buff *msg, u32 portid, u32 seq, + struct batadv_priv *bat_priv, + struct batadv_hard_iface *if_outgoing, + struct hlist_head *head, int *idx_s, int *sub) +{ + struct batadv_orig_node *orig_node; + int idx = 0; + + rcu_read_lock(); + hlist_for_each_entry_rcu(orig_node, head, hash_entry) { + if (idx++ < *idx_s) + continue; + + if (batadv_iv_ogm_orig_dump_entry(msg, portid, seq, bat_priv, + if_outgoing, orig_node, + sub)) { + rcu_read_unlock(); + *idx_s = idx - 1; + return -EMSGSIZE; + } + } + rcu_read_unlock(); + + *idx_s = 0; + *sub = 0; + return 0; +} + +/** + * batadv_iv_ogm_orig_dump - Dump the originators into a message + * @msg: Netlink message to dump into + * @cb: Control block containing additional options + * @bat_priv: The bat priv with all the soft interface information + * @if_outgoing: Limit dump to entries with this outgoing interface + */ +static void +batadv_iv_ogm_orig_dump(struct sk_buff *msg, struct netlink_callback *cb, + struct batadv_priv *bat_priv, + struct batadv_hard_iface *if_outgoing) +{ + struct batadv_hashtable *hash = bat_priv->orig_hash; + struct hlist_head *head; + int bucket = cb->args[0]; + int idx = cb->args[1]; + int sub = cb->args[2]; + int portid = NETLINK_CB(cb->skb).portid; + + while (bucket < hash->size) { + head = &hash->table[bucket]; + + if (batadv_iv_ogm_orig_dump_bucket(msg, portid, + cb->nlh->nlmsg_seq, + bat_priv, if_outgoing, head, + &idx, &sub)) + break; + + bucket++; + } + + cb->args[0] = bucket; + cb->args[1] = idx; + cb->args[2] = sub; +} + +#ifdef CONFIG_BATMAN_ADV_DEBUGFS +/** * batadv_iv_hardif_neigh_print - print a single hop neighbour node * @seq: neighbour table seq_file struct * @hardif_neigh: hardif neighbour information @@ -2027,37 +2235,43 @@ static void batadv_iv_neigh_print(struct batadv_priv *bat_priv, if (batman_count == 0) seq_puts(seq, "No batman nodes in range ...\n"); } +#endif /** - * batadv_iv_ogm_neigh_cmp - compare the metrics of two neighbors + * batadv_iv_ogm_neigh_diff - calculate tq difference of two neighbors * @neigh1: the first neighbor object of the comparison * @if_outgoing1: outgoing interface for the first neighbor * @neigh2: the second neighbor object of the comparison * @if_outgoing2: outgoing interface for the second neighbor + * @diff: pointer to integer receiving the calculated difference * - * Return: a value less, equal to or greater than 0 if the metric via neigh1 is - * lower, the same as or higher than the metric via neigh2 + * The content of *@diff is only valid when this function returns true. + * It is less, equal to or greater than 0 if the metric via neigh1 is lower, + * the same as or higher than the metric via neigh2 + * + * Return: true when the difference could be calculated, false otherwise */ -static int batadv_iv_ogm_neigh_cmp(struct batadv_neigh_node *neigh1, - struct batadv_hard_iface *if_outgoing1, - struct batadv_neigh_node *neigh2, - struct batadv_hard_iface *if_outgoing2) +static bool batadv_iv_ogm_neigh_diff(struct batadv_neigh_node *neigh1, + struct batadv_hard_iface *if_outgoing1, + struct batadv_neigh_node *neigh2, + struct batadv_hard_iface *if_outgoing2, + int *diff) { struct batadv_neigh_ifinfo *neigh1_ifinfo, *neigh2_ifinfo; u8 tq1, tq2; - int diff; + bool ret = true; neigh1_ifinfo = batadv_neigh_ifinfo_get(neigh1, if_outgoing1); neigh2_ifinfo = batadv_neigh_ifinfo_get(neigh2, if_outgoing2); if (!neigh1_ifinfo || !neigh2_ifinfo) { - diff = 0; + ret = false; goto out; } tq1 = neigh1_ifinfo->bat_iv.tq_avg; tq2 = neigh2_ifinfo->bat_iv.tq_avg; - diff = tq1 - tq2; + *diff = (int)tq1 - (int)tq2; out: if (neigh1_ifinfo) @@ -2065,6 +2279,162 @@ out: if (neigh2_ifinfo) batadv_neigh_ifinfo_put(neigh2_ifinfo); + return ret; +} + +/** + * batadv_iv_ogm_neigh_dump_neigh - Dump a neighbour into a netlink message + * @msg: Netlink message to dump into + * @portid: Port making netlink request + * @seq: Sequence number of netlink message + * @hardif_neigh: Neighbour to be dumped + * + * Return: Error code, or 0 on success + */ +static int +batadv_iv_ogm_neigh_dump_neigh(struct sk_buff *msg, u32 portid, u32 seq, + struct batadv_hardif_neigh_node *hardif_neigh) +{ + void *hdr; + unsigned int last_seen_msecs; + + last_seen_msecs = jiffies_to_msecs(jiffies - hardif_neigh->last_seen); + + hdr = genlmsg_put(msg, portid, seq, &batadv_netlink_family, + NLM_F_MULTI, BATADV_CMD_GET_NEIGHBORS); + if (!hdr) + return -ENOBUFS; + + if (nla_put(msg, BATADV_ATTR_NEIGH_ADDRESS, ETH_ALEN, + hardif_neigh->addr) || + nla_put_u32(msg, BATADV_ATTR_HARD_IFINDEX, + hardif_neigh->if_incoming->net_dev->ifindex) || + nla_put_u32(msg, BATADV_ATTR_LAST_SEEN_MSECS, + last_seen_msecs)) + goto nla_put_failure; + + genlmsg_end(msg, hdr); + return 0; + + nla_put_failure: + genlmsg_cancel(msg, hdr); + return -EMSGSIZE; +} + +/** + * batadv_iv_ogm_neigh_dump_hardif - Dump the neighbours of a hard interface + * into a message + * @msg: Netlink message to dump into + * @portid: Port making netlink request + * @seq: Sequence number of netlink message + * @bat_priv: The bat priv with all the soft interface information + * @hard_iface: Hard interface to dump the neighbours for + * @idx_s: Number of entries to skip + * + * This function assumes the caller holds rcu_read_lock(). + * + * Return: Error code, or 0 on success + */ +static int +batadv_iv_ogm_neigh_dump_hardif(struct sk_buff *msg, u32 portid, u32 seq, + struct batadv_priv *bat_priv, + struct batadv_hard_iface *hard_iface, + int *idx_s) +{ + struct batadv_hardif_neigh_node *hardif_neigh; + int idx = 0; + + hlist_for_each_entry_rcu(hardif_neigh, + &hard_iface->neigh_list, list) { + if (idx++ < *idx_s) + continue; + + if (batadv_iv_ogm_neigh_dump_neigh(msg, portid, seq, + hardif_neigh)) { + *idx_s = idx - 1; + return -EMSGSIZE; + } + } + + *idx_s = 0; + return 0; +} + +/** + * batadv_iv_ogm_neigh_dump - Dump the neighbours into a message + * @msg: Netlink message to dump into + * @cb: Control block containing additional options + * @bat_priv: The bat priv with all the soft interface information + * @single_hardif: Limit dump to this hard interfaace + */ +static void +batadv_iv_ogm_neigh_dump(struct sk_buff *msg, struct netlink_callback *cb, + struct batadv_priv *bat_priv, + struct batadv_hard_iface *single_hardif) +{ + struct batadv_hard_iface *hard_iface; + int i_hardif = 0; + int i_hardif_s = cb->args[0]; + int idx = cb->args[1]; + int portid = NETLINK_CB(cb->skb).portid; + + rcu_read_lock(); + if (single_hardif) { + if (i_hardif_s == 0) { + if (batadv_iv_ogm_neigh_dump_hardif(msg, portid, + cb->nlh->nlmsg_seq, + bat_priv, + single_hardif, + &idx) == 0) + i_hardif++; + } + } else { + list_for_each_entry_rcu(hard_iface, &batadv_hardif_list, + list) { + if (hard_iface->soft_iface != bat_priv->soft_iface) + continue; + + if (i_hardif++ < i_hardif_s) + continue; + + if (batadv_iv_ogm_neigh_dump_hardif(msg, portid, + cb->nlh->nlmsg_seq, + bat_priv, + hard_iface, &idx)) { + i_hardif--; + break; + } + } + } + rcu_read_unlock(); + + cb->args[0] = i_hardif; + cb->args[1] = idx; +} + +/** + * batadv_iv_ogm_neigh_cmp - compare the metrics of two neighbors + * @neigh1: the first neighbor object of the comparison + * @if_outgoing1: outgoing interface for the first neighbor + * @neigh2: the second neighbor object of the comparison + * @if_outgoing2: outgoing interface for the second neighbor + * + * Return: a value less, equal to or greater than 0 if the metric via neigh1 is + * lower, the same as or higher than the metric via neigh2 + */ +static int batadv_iv_ogm_neigh_cmp(struct batadv_neigh_node *neigh1, + struct batadv_hard_iface *if_outgoing1, + struct batadv_neigh_node *neigh2, + struct batadv_hard_iface *if_outgoing2) +{ + bool ret; + int diff; + + ret = batadv_iv_ogm_neigh_diff(neigh1, if_outgoing1, neigh2, + if_outgoing2, &diff); + if (!ret) + return 0; + return diff; } @@ -2085,36 +2455,341 @@ batadv_iv_ogm_neigh_is_sob(struct batadv_neigh_node *neigh1, struct batadv_neigh_node *neigh2, struct batadv_hard_iface *if_outgoing2) { - struct batadv_neigh_ifinfo *neigh1_ifinfo, *neigh2_ifinfo; - u8 tq1, tq2; bool ret; + int diff; - neigh1_ifinfo = batadv_neigh_ifinfo_get(neigh1, if_outgoing1); - neigh2_ifinfo = batadv_neigh_ifinfo_get(neigh2, if_outgoing2); + ret = batadv_iv_ogm_neigh_diff(neigh1, if_outgoing1, neigh2, + if_outgoing2, &diff); + if (!ret) + return false; - /* we can't say that the metric is better */ - if (!neigh1_ifinfo || !neigh2_ifinfo) { - ret = false; + ret = diff > -BATADV_TQ_SIMILARITY_THRESHOLD; + return ret; +} + +static void batadv_iv_iface_activate(struct batadv_hard_iface *hard_iface) +{ + /* begin scheduling originator messages on that interface */ + batadv_iv_ogm_schedule(hard_iface); +} + +static struct batadv_gw_node * +batadv_iv_gw_get_best_gw_node(struct batadv_priv *bat_priv) +{ + struct batadv_neigh_node *router; + struct batadv_neigh_ifinfo *router_ifinfo; + struct batadv_gw_node *gw_node, *curr_gw = NULL; + u64 max_gw_factor = 0; + u64 tmp_gw_factor = 0; + u8 max_tq = 0; + u8 tq_avg; + struct batadv_orig_node *orig_node; + + rcu_read_lock(); + hlist_for_each_entry_rcu(gw_node, &bat_priv->gw.list, list) { + orig_node = gw_node->orig_node; + router = batadv_orig_router_get(orig_node, BATADV_IF_DEFAULT); + if (!router) + continue; + + router_ifinfo = batadv_neigh_ifinfo_get(router, + BATADV_IF_DEFAULT); + if (!router_ifinfo) + goto next; + + if (!kref_get_unless_zero(&gw_node->refcount)) + goto next; + + tq_avg = router_ifinfo->bat_iv.tq_avg; + + switch (atomic_read(&bat_priv->gw.sel_class)) { + case 1: /* fast connection */ + tmp_gw_factor = tq_avg * tq_avg; + tmp_gw_factor *= gw_node->bandwidth_down; + tmp_gw_factor *= 100 * 100; + tmp_gw_factor >>= 18; + + if ((tmp_gw_factor > max_gw_factor) || + ((tmp_gw_factor == max_gw_factor) && + (tq_avg > max_tq))) { + if (curr_gw) + batadv_gw_node_put(curr_gw); + curr_gw = gw_node; + kref_get(&curr_gw->refcount); + } + break; + + default: /* 2: stable connection (use best statistic) + * 3: fast-switch (use best statistic but change as + * soon as a better gateway appears) + * XX: late-switch (use best statistic but change as + * soon as a better gateway appears which has + * $routing_class more tq points) + */ + if (tq_avg > max_tq) { + if (curr_gw) + batadv_gw_node_put(curr_gw); + curr_gw = gw_node; + kref_get(&curr_gw->refcount); + } + break; + } + + if (tq_avg > max_tq) + max_tq = tq_avg; + + if (tmp_gw_factor > max_gw_factor) + max_gw_factor = tmp_gw_factor; + + batadv_gw_node_put(gw_node); + +next: + batadv_neigh_node_put(router); + if (router_ifinfo) + batadv_neigh_ifinfo_put(router_ifinfo); + } + rcu_read_unlock(); + + return curr_gw; +} + +static bool batadv_iv_gw_is_eligible(struct batadv_priv *bat_priv, + struct batadv_orig_node *curr_gw_orig, + struct batadv_orig_node *orig_node) +{ + struct batadv_neigh_ifinfo *router_orig_ifinfo = NULL; + struct batadv_neigh_ifinfo *router_gw_ifinfo = NULL; + struct batadv_neigh_node *router_gw = NULL; + struct batadv_neigh_node *router_orig = NULL; + u8 gw_tq_avg, orig_tq_avg; + bool ret = false; + + /* dynamic re-election is performed only on fast or late switch */ + if (atomic_read(&bat_priv->gw.sel_class) <= 2) + return false; + + router_gw = batadv_orig_router_get(curr_gw_orig, BATADV_IF_DEFAULT); + if (!router_gw) { + ret = true; goto out; } - tq1 = neigh1_ifinfo->bat_iv.tq_avg; - tq2 = neigh2_ifinfo->bat_iv.tq_avg; - ret = (tq1 - tq2) > -BATADV_TQ_SIMILARITY_THRESHOLD; + router_gw_ifinfo = batadv_neigh_ifinfo_get(router_gw, + BATADV_IF_DEFAULT); + if (!router_gw_ifinfo) { + ret = true; + goto out; + } + + router_orig = batadv_orig_router_get(orig_node, BATADV_IF_DEFAULT); + if (!router_orig) + goto out; + + router_orig_ifinfo = batadv_neigh_ifinfo_get(router_orig, + BATADV_IF_DEFAULT); + if (!router_orig_ifinfo) + goto out; + + gw_tq_avg = router_gw_ifinfo->bat_iv.tq_avg; + orig_tq_avg = router_orig_ifinfo->bat_iv.tq_avg; + + /* the TQ value has to be better */ + if (orig_tq_avg < gw_tq_avg) + goto out; + /* if the routing class is greater than 3 the value tells us how much + * greater the TQ value of the new gateway must be + */ + if ((atomic_read(&bat_priv->gw.sel_class) > 3) && + (orig_tq_avg - gw_tq_avg < atomic_read(&bat_priv->gw.sel_class))) + goto out; + + batadv_dbg(BATADV_DBG_BATMAN, bat_priv, + "Restarting gateway selection: better gateway found (tq curr: %i, tq new: %i)\n", + gw_tq_avg, orig_tq_avg); + + ret = true; out: - if (neigh1_ifinfo) - batadv_neigh_ifinfo_put(neigh1_ifinfo); - if (neigh2_ifinfo) - batadv_neigh_ifinfo_put(neigh2_ifinfo); + if (router_gw_ifinfo) + batadv_neigh_ifinfo_put(router_gw_ifinfo); + if (router_orig_ifinfo) + batadv_neigh_ifinfo_put(router_orig_ifinfo); + if (router_gw) + batadv_neigh_node_put(router_gw); + if (router_orig) + batadv_neigh_node_put(router_orig); return ret; } -static void batadv_iv_iface_activate(struct batadv_hard_iface *hard_iface) +#ifdef CONFIG_BATMAN_ADV_DEBUGFS +/* fails if orig_node has no router */ +static int batadv_iv_gw_write_buffer_text(struct batadv_priv *bat_priv, + struct seq_file *seq, + const struct batadv_gw_node *gw_node) { - /* begin scheduling originator messages on that interface */ - batadv_iv_ogm_schedule(hard_iface); + struct batadv_gw_node *curr_gw; + struct batadv_neigh_node *router; + struct batadv_neigh_ifinfo *router_ifinfo = NULL; + int ret = -1; + + router = batadv_orig_router_get(gw_node->orig_node, BATADV_IF_DEFAULT); + if (!router) + goto out; + + router_ifinfo = batadv_neigh_ifinfo_get(router, BATADV_IF_DEFAULT); + if (!router_ifinfo) + goto out; + + curr_gw = batadv_gw_get_selected_gw_node(bat_priv); + + seq_printf(seq, "%s %pM (%3i) %pM [%10s]: %u.%u/%u.%u MBit\n", + (curr_gw == gw_node ? "=>" : " "), + gw_node->orig_node->orig, + router_ifinfo->bat_iv.tq_avg, router->addr, + router->if_incoming->net_dev->name, + gw_node->bandwidth_down / 10, + gw_node->bandwidth_down % 10, + gw_node->bandwidth_up / 10, + gw_node->bandwidth_up % 10); + ret = seq_has_overflowed(seq) ? -1 : 0; + + if (curr_gw) + batadv_gw_node_put(curr_gw); +out: + if (router_ifinfo) + batadv_neigh_ifinfo_put(router_ifinfo); + if (router) + batadv_neigh_node_put(router); + return ret; +} + +static void batadv_iv_gw_print(struct batadv_priv *bat_priv, + struct seq_file *seq) +{ + struct batadv_gw_node *gw_node; + int gw_count = 0; + + seq_puts(seq, + " Gateway (#/255) Nexthop [outgoingIF]: advertised uplink bandwidth\n"); + + rcu_read_lock(); + hlist_for_each_entry_rcu(gw_node, &bat_priv->gw.list, list) { + /* fails if orig_node has no router */ + if (batadv_iv_gw_write_buffer_text(bat_priv, seq, gw_node) < 0) + continue; + + gw_count++; + } + rcu_read_unlock(); + + if (gw_count == 0) + seq_puts(seq, "No gateways in range ...\n"); +} +#endif + +/** + * batadv_iv_gw_dump_entry - Dump a gateway into a message + * @msg: Netlink message to dump into + * @portid: Port making netlink request + * @seq: Sequence number of netlink message + * @bat_priv: The bat priv with all the soft interface information + * @gw_node: Gateway to be dumped + * + * Return: Error code, or 0 on success + */ +static int batadv_iv_gw_dump_entry(struct sk_buff *msg, u32 portid, u32 seq, + struct batadv_priv *bat_priv, + struct batadv_gw_node *gw_node) +{ + struct batadv_neigh_ifinfo *router_ifinfo = NULL; + struct batadv_neigh_node *router; + struct batadv_gw_node *curr_gw; + int ret = -EINVAL; + void *hdr; + + router = batadv_orig_router_get(gw_node->orig_node, BATADV_IF_DEFAULT); + if (!router) + goto out; + + router_ifinfo = batadv_neigh_ifinfo_get(router, BATADV_IF_DEFAULT); + if (!router_ifinfo) + goto out; + + curr_gw = batadv_gw_get_selected_gw_node(bat_priv); + + hdr = genlmsg_put(msg, portid, seq, &batadv_netlink_family, + NLM_F_MULTI, BATADV_CMD_GET_GATEWAYS); + if (!hdr) { + ret = -ENOBUFS; + goto out; + } + + ret = -EMSGSIZE; + + if (curr_gw == gw_node) + if (nla_put_flag(msg, BATADV_ATTR_FLAG_BEST)) { + genlmsg_cancel(msg, hdr); + goto out; + } + + if (nla_put(msg, BATADV_ATTR_ORIG_ADDRESS, ETH_ALEN, + gw_node->orig_node->orig) || + nla_put_u8(msg, BATADV_ATTR_TQ, router_ifinfo->bat_iv.tq_avg) || + nla_put(msg, BATADV_ATTR_ROUTER, ETH_ALEN, + router->addr) || + nla_put_string(msg, BATADV_ATTR_HARD_IFNAME, + router->if_incoming->net_dev->name) || + nla_put_u32(msg, BATADV_ATTR_BANDWIDTH_DOWN, + gw_node->bandwidth_down) || + nla_put_u32(msg, BATADV_ATTR_BANDWIDTH_UP, + gw_node->bandwidth_up)) { + genlmsg_cancel(msg, hdr); + goto out; + } + + genlmsg_end(msg, hdr); + ret = 0; + +out: + if (router_ifinfo) + batadv_neigh_ifinfo_put(router_ifinfo); + if (router) + batadv_neigh_node_put(router); + return ret; +} + +/** + * batadv_iv_gw_dump - Dump gateways into a message + * @msg: Netlink message to dump into + * @cb: Control block containing additional options + * @bat_priv: The bat priv with all the soft interface information + */ +static void batadv_iv_gw_dump(struct sk_buff *msg, struct netlink_callback *cb, + struct batadv_priv *bat_priv) +{ + int portid = NETLINK_CB(cb->skb).portid; + struct batadv_gw_node *gw_node; + int idx_skip = cb->args[0]; + int idx = 0; + + rcu_read_lock(); + hlist_for_each_entry_rcu(gw_node, &bat_priv->gw.list, list) { + if (idx++ < idx_skip) + continue; + + if (batadv_iv_gw_dump_entry(msg, portid, cb->nlh->nlmsg_seq, + bat_priv, gw_node)) { + idx_skip = idx - 1; + goto unlock; + } + } + + idx_skip = idx; +unlock: + rcu_read_unlock(); + + cb->args[0] = idx_skip; } static struct batadv_algo_ops batadv_batman_iv __read_mostly = { @@ -2129,14 +2804,28 @@ static struct batadv_algo_ops batadv_batman_iv __read_mostly = { .neigh = { .cmp = batadv_iv_ogm_neigh_cmp, .is_similar_or_better = batadv_iv_ogm_neigh_is_sob, +#ifdef CONFIG_BATMAN_ADV_DEBUGFS .print = batadv_iv_neigh_print, +#endif + .dump = batadv_iv_ogm_neigh_dump, }, .orig = { +#ifdef CONFIG_BATMAN_ADV_DEBUGFS .print = batadv_iv_ogm_orig_print, +#endif + .dump = batadv_iv_ogm_orig_dump, .free = batadv_iv_ogm_orig_free, .add_if = batadv_iv_ogm_orig_add_if, .del_if = batadv_iv_ogm_orig_del_if, }, + .gw = { + .get_best_gw_node = batadv_iv_gw_get_best_gw_node, + .is_eligible = batadv_iv_gw_is_eligible, +#ifdef CONFIG_BATMAN_ADV_DEBUGFS + .print = batadv_iv_gw_print, +#endif + .dump = batadv_iv_gw_dump, + }, }; int __init batadv_iv_init(void) diff --git a/net/batman-adv/bat_v.c b/net/batman-adv/bat_v.c index 0366cbf5e444..e79f6f01182e 100644 --- a/net/batman-adv/bat_v.c +++ b/net/batman-adv/bat_v.c @@ -21,24 +21,38 @@ #include <linux/atomic.h> #include <linux/bug.h> #include <linux/cache.h> +#include <linux/errno.h> +#include <linux/if_ether.h> #include <linux/init.h> #include <linux/jiffies.h> +#include <linux/kernel.h> +#include <linux/kref.h> #include <linux/netdevice.h> +#include <linux/netlink.h> #include <linux/rculist.h> #include <linux/rcupdate.h> #include <linux/seq_file.h> #include <linux/stddef.h> #include <linux/types.h> #include <linux/workqueue.h> +#include <net/genetlink.h> +#include <net/netlink.h> +#include <uapi/linux/batman_adv.h> #include "bat_algo.h" #include "bat_v_elp.h" #include "bat_v_ogm.h" +#include "gateway_client.h" +#include "gateway_common.h" #include "hard-interface.h" #include "hash.h" +#include "log.h" +#include "netlink.h" #include "originator.h" #include "packet.h" +struct sk_buff; + static void batadv_v_iface_activate(struct batadv_hard_iface *hard_iface) { struct batadv_priv *bat_priv = netdev_priv(hard_iface->soft_iface); @@ -115,6 +129,7 @@ batadv_v_hardif_neigh_init(struct batadv_hardif_neigh_node *hardif_neigh) batadv_v_elp_throughput_metric_update); } +#ifdef CONFIG_BATMAN_ADV_DEBUGFS /** * batadv_v_orig_print_neigh - print neighbors for the originator table * @orig_node: the orig_node for which the neighbors are printed @@ -198,8 +213,142 @@ static void batadv_v_neigh_print(struct batadv_priv *bat_priv, if (batman_count == 0) seq_puts(seq, "No batman nodes in range ...\n"); } +#endif + +/** + * batadv_v_neigh_dump_neigh - Dump a neighbour into a message + * @msg: Netlink message to dump into + * @portid: Port making netlink request + * @seq: Sequence number of netlink message + * @hardif_neigh: Neighbour to dump + * + * Return: Error code, or 0 on success + */ +static int +batadv_v_neigh_dump_neigh(struct sk_buff *msg, u32 portid, u32 seq, + struct batadv_hardif_neigh_node *hardif_neigh) +{ + void *hdr; + unsigned int last_seen_msecs; + u32 throughput; + + last_seen_msecs = jiffies_to_msecs(jiffies - hardif_neigh->last_seen); + throughput = ewma_throughput_read(&hardif_neigh->bat_v.throughput); + throughput = throughput * 100; + + hdr = genlmsg_put(msg, portid, seq, &batadv_netlink_family, NLM_F_MULTI, + BATADV_CMD_GET_NEIGHBORS); + if (!hdr) + return -ENOBUFS; + + if (nla_put(msg, BATADV_ATTR_NEIGH_ADDRESS, ETH_ALEN, + hardif_neigh->addr) || + nla_put_u32(msg, BATADV_ATTR_HARD_IFINDEX, + hardif_neigh->if_incoming->net_dev->ifindex) || + nla_put_u32(msg, BATADV_ATTR_LAST_SEEN_MSECS, + last_seen_msecs) || + nla_put_u32(msg, BATADV_ATTR_THROUGHPUT, throughput)) + goto nla_put_failure; + + genlmsg_end(msg, hdr); + return 0; + + nla_put_failure: + genlmsg_cancel(msg, hdr); + return -EMSGSIZE; +} /** + * batadv_v_neigh_dump_hardif - Dump the neighbours of a hard interface into + * a message + * @msg: Netlink message to dump into + * @portid: Port making netlink request + * @seq: Sequence number of netlink message + * @bat_priv: The bat priv with all the soft interface information + * @hard_iface: The hard interface to be dumped + * @idx_s: Entries to be skipped + * + * This function assumes the caller holds rcu_read_lock(). + * + * Return: Error code, or 0 on success + */ +static int +batadv_v_neigh_dump_hardif(struct sk_buff *msg, u32 portid, u32 seq, + struct batadv_priv *bat_priv, + struct batadv_hard_iface *hard_iface, + int *idx_s) +{ + struct batadv_hardif_neigh_node *hardif_neigh; + int idx = 0; + + hlist_for_each_entry_rcu(hardif_neigh, + &hard_iface->neigh_list, list) { + if (idx++ < *idx_s) + continue; + + if (batadv_v_neigh_dump_neigh(msg, portid, seq, hardif_neigh)) { + *idx_s = idx - 1; + return -EMSGSIZE; + } + } + + *idx_s = 0; + return 0; +} + +/** + * batadv_v_neigh_dump - Dump the neighbours of a hard interface into a + * message + * @msg: Netlink message to dump into + * @cb: Control block containing additional options + * @bat_priv: The bat priv with all the soft interface information + * @single_hardif: Limit dumping to this hard interface + */ +static void +batadv_v_neigh_dump(struct sk_buff *msg, struct netlink_callback *cb, + struct batadv_priv *bat_priv, + struct batadv_hard_iface *single_hardif) +{ + struct batadv_hard_iface *hard_iface; + int i_hardif = 0; + int i_hardif_s = cb->args[0]; + int idx = cb->args[1]; + int portid = NETLINK_CB(cb->skb).portid; + + rcu_read_lock(); + if (single_hardif) { + if (i_hardif_s == 0) { + if (batadv_v_neigh_dump_hardif(msg, portid, + cb->nlh->nlmsg_seq, + bat_priv, single_hardif, + &idx) == 0) + i_hardif++; + } + } else { + list_for_each_entry_rcu(hard_iface, &batadv_hardif_list, list) { + if (hard_iface->soft_iface != bat_priv->soft_iface) + continue; + + if (i_hardif++ < i_hardif_s) + continue; + + if (batadv_v_neigh_dump_hardif(msg, portid, + cb->nlh->nlmsg_seq, + bat_priv, hard_iface, + &idx)) { + i_hardif--; + break; + } + } + } + rcu_read_unlock(); + + cb->args[0] = i_hardif; + cb->args[1] = idx; +} + +#ifdef CONFIG_BATMAN_ADV_DEBUGFS +/** * batadv_v_orig_print - print the originator table * @bat_priv: the bat priv with all the soft interface information * @seq: debugfs table seq_file struct @@ -265,6 +414,205 @@ next: if (batman_count == 0) seq_puts(seq, "No batman nodes in range ...\n"); } +#endif + +/** + * batadv_v_orig_dump_subentry - Dump an originator subentry into a + * message + * @msg: Netlink message to dump into + * @portid: Port making netlink request + * @seq: Sequence number of netlink message + * @bat_priv: The bat priv with all the soft interface information + * @if_outgoing: Limit dump to entries with this outgoing interface + * @orig_node: Originator to dump + * @neigh_node: Single hops neighbour + * @best: Is the best originator + * + * Return: Error code, or 0 on success + */ +static int +batadv_v_orig_dump_subentry(struct sk_buff *msg, u32 portid, u32 seq, + struct batadv_priv *bat_priv, + struct batadv_hard_iface *if_outgoing, + struct batadv_orig_node *orig_node, + struct batadv_neigh_node *neigh_node, + bool best) +{ + struct batadv_neigh_ifinfo *n_ifinfo; + unsigned int last_seen_msecs; + u32 throughput; + void *hdr; + + n_ifinfo = batadv_neigh_ifinfo_get(neigh_node, if_outgoing); + if (!n_ifinfo) + return 0; + + throughput = n_ifinfo->bat_v.throughput * 100; + + batadv_neigh_ifinfo_put(n_ifinfo); + + last_seen_msecs = jiffies_to_msecs(jiffies - orig_node->last_seen); + + if (if_outgoing != BATADV_IF_DEFAULT && + if_outgoing != neigh_node->if_incoming) + return 0; + + hdr = genlmsg_put(msg, portid, seq, &batadv_netlink_family, NLM_F_MULTI, + BATADV_CMD_GET_ORIGINATORS); + if (!hdr) + return -ENOBUFS; + + if (nla_put(msg, BATADV_ATTR_ORIG_ADDRESS, ETH_ALEN, orig_node->orig) || + nla_put(msg, BATADV_ATTR_NEIGH_ADDRESS, ETH_ALEN, + neigh_node->addr) || + nla_put_u32(msg, BATADV_ATTR_HARD_IFINDEX, + neigh_node->if_incoming->net_dev->ifindex) || + nla_put_u32(msg, BATADV_ATTR_THROUGHPUT, throughput) || + nla_put_u32(msg, BATADV_ATTR_LAST_SEEN_MSECS, + last_seen_msecs)) + goto nla_put_failure; + + if (best && nla_put_flag(msg, BATADV_ATTR_FLAG_BEST)) + goto nla_put_failure; + + genlmsg_end(msg, hdr); + return 0; + + nla_put_failure: + genlmsg_cancel(msg, hdr); + return -EMSGSIZE; +} + +/** + * batadv_v_orig_dump_entry - Dump an originator entry into a message + * @msg: Netlink message to dump into + * @portid: Port making netlink request + * @seq: Sequence number of netlink message + * @bat_priv: The bat priv with all the soft interface information + * @if_outgoing: Limit dump to entries with this outgoing interface + * @orig_node: Originator to dump + * @sub_s: Number of sub entries to skip + * + * This function assumes the caller holds rcu_read_lock(). + * + * Return: Error code, or 0 on success + */ +static int +batadv_v_orig_dump_entry(struct sk_buff *msg, u32 portid, u32 seq, + struct batadv_priv *bat_priv, + struct batadv_hard_iface *if_outgoing, + struct batadv_orig_node *orig_node, int *sub_s) +{ + struct batadv_neigh_node *neigh_node_best; + struct batadv_neigh_node *neigh_node; + int sub = 0; + bool best; + + neigh_node_best = batadv_orig_router_get(orig_node, if_outgoing); + if (!neigh_node_best) + goto out; + + hlist_for_each_entry_rcu(neigh_node, &orig_node->neigh_list, list) { + if (sub++ < *sub_s) + continue; + + best = (neigh_node == neigh_node_best); + + if (batadv_v_orig_dump_subentry(msg, portid, seq, bat_priv, + if_outgoing, orig_node, + neigh_node, best)) { + batadv_neigh_node_put(neigh_node_best); + + *sub_s = sub - 1; + return -EMSGSIZE; + } + } + + out: + if (neigh_node_best) + batadv_neigh_node_put(neigh_node_best); + + *sub_s = 0; + return 0; +} + +/** + * batadv_v_orig_dump_bucket - Dump an originator bucket into a + * message + * @msg: Netlink message to dump into + * @portid: Port making netlink request + * @seq: Sequence number of netlink message + * @bat_priv: The bat priv with all the soft interface information + * @if_outgoing: Limit dump to entries with this outgoing interface + * @head: Bucket to be dumped + * @idx_s: Number of entries to be skipped + * @sub: Number of sub entries to be skipped + * + * Return: Error code, or 0 on success + */ +static int +batadv_v_orig_dump_bucket(struct sk_buff *msg, u32 portid, u32 seq, + struct batadv_priv *bat_priv, + struct batadv_hard_iface *if_outgoing, + struct hlist_head *head, int *idx_s, int *sub) +{ + struct batadv_orig_node *orig_node; + int idx = 0; + + rcu_read_lock(); + hlist_for_each_entry_rcu(orig_node, head, hash_entry) { + if (idx++ < *idx_s) + continue; + + if (batadv_v_orig_dump_entry(msg, portid, seq, bat_priv, + if_outgoing, orig_node, sub)) { + rcu_read_unlock(); + *idx_s = idx - 1; + return -EMSGSIZE; + } + } + rcu_read_unlock(); + + *idx_s = 0; + *sub = 0; + return 0; +} + +/** + * batadv_v_orig_dump - Dump the originators into a message + * @msg: Netlink message to dump into + * @cb: Control block containing additional options + * @bat_priv: The bat priv with all the soft interface information + * @if_outgoing: Limit dump to entries with this outgoing interface + */ +static void +batadv_v_orig_dump(struct sk_buff *msg, struct netlink_callback *cb, + struct batadv_priv *bat_priv, + struct batadv_hard_iface *if_outgoing) +{ + struct batadv_hashtable *hash = bat_priv->orig_hash; + struct hlist_head *head; + int bucket = cb->args[0]; + int idx = cb->args[1]; + int sub = cb->args[2]; + int portid = NETLINK_CB(cb->skb).portid; + + while (bucket < hash->size) { + head = &hash->table[bucket]; + + if (batadv_v_orig_dump_bucket(msg, portid, + cb->nlh->nlmsg_seq, + bat_priv, if_outgoing, head, &idx, + &sub)) + break; + + bucket++; + } + + cb->args[0] = bucket; + cb->args[1] = idx; + cb->args[2] = sub; +} static int batadv_v_neigh_cmp(struct batadv_neigh_node *neigh1, struct batadv_hard_iface *if_outgoing1, @@ -320,6 +668,365 @@ err_ifinfo1: return ret; } +static ssize_t batadv_v_store_sel_class(struct batadv_priv *bat_priv, + char *buff, size_t count) +{ + u32 old_class, class; + + if (!batadv_parse_throughput(bat_priv->soft_iface, buff, + "B.A.T.M.A.N. V GW selection class", + &class)) + return -EINVAL; + + old_class = atomic_read(&bat_priv->gw.sel_class); + atomic_set(&bat_priv->gw.sel_class, class); + + if (old_class != class) + batadv_gw_reselect(bat_priv); + + return count; +} + +static ssize_t batadv_v_show_sel_class(struct batadv_priv *bat_priv, char *buff) +{ + u32 class = atomic_read(&bat_priv->gw.sel_class); + + return sprintf(buff, "%u.%u MBit\n", class / 10, class % 10); +} + +/** + * batadv_v_gw_throughput_get - retrieve the GW-bandwidth for a given GW + * @gw_node: the GW to retrieve the metric for + * @bw: the pointer where the metric will be stored. The metric is computed as + * the minimum between the GW advertised throughput and the path throughput to + * it in the mesh + * + * Return: 0 on success, -1 on failure + */ +static int batadv_v_gw_throughput_get(struct batadv_gw_node *gw_node, u32 *bw) +{ + struct batadv_neigh_ifinfo *router_ifinfo = NULL; + struct batadv_orig_node *orig_node; + struct batadv_neigh_node *router; + int ret = -1; + + orig_node = gw_node->orig_node; + router = batadv_orig_router_get(orig_node, BATADV_IF_DEFAULT); + if (!router) + goto out; + + router_ifinfo = batadv_neigh_ifinfo_get(router, BATADV_IF_DEFAULT); + if (!router_ifinfo) + goto out; + + /* the GW metric is computed as the minimum between the path throughput + * to reach the GW itself and the advertised bandwidth. + * This gives us an approximation of the effective throughput that the + * client can expect via this particular GW node + */ + *bw = router_ifinfo->bat_v.throughput; + *bw = min_t(u32, *bw, gw_node->bandwidth_down); + + ret = 0; +out: + if (router) + batadv_neigh_node_put(router); + if (router_ifinfo) + batadv_neigh_ifinfo_put(router_ifinfo); + + return ret; +} + +/** + * batadv_v_gw_get_best_gw_node - retrieve the best GW node + * @bat_priv: the bat priv with all the soft interface information + * + * Return: the GW node having the best GW-metric, NULL if no GW is known + */ +static struct batadv_gw_node * +batadv_v_gw_get_best_gw_node(struct batadv_priv *bat_priv) +{ + struct batadv_gw_node *gw_node, *curr_gw = NULL; + u32 max_bw = 0, bw; + + rcu_read_lock(); + hlist_for_each_entry_rcu(gw_node, &bat_priv->gw.list, list) { + if (!kref_get_unless_zero(&gw_node->refcount)) + continue; + + if (batadv_v_gw_throughput_get(gw_node, &bw) < 0) + goto next; + + if (curr_gw && (bw <= max_bw)) + goto next; + + if (curr_gw) + batadv_gw_node_put(curr_gw); + + curr_gw = gw_node; + kref_get(&curr_gw->refcount); + max_bw = bw; + +next: + batadv_gw_node_put(gw_node); + } + rcu_read_unlock(); + + return curr_gw; +} + +/** + * batadv_v_gw_is_eligible - check if a originator would be selected as GW + * @bat_priv: the bat priv with all the soft interface information + * @curr_gw_orig: originator representing the currently selected GW + * @orig_node: the originator representing the new candidate + * + * Return: true if orig_node can be selected as current GW, false otherwise + */ +static bool batadv_v_gw_is_eligible(struct batadv_priv *bat_priv, + struct batadv_orig_node *curr_gw_orig, + struct batadv_orig_node *orig_node) +{ + struct batadv_gw_node *curr_gw = NULL, *orig_gw = NULL; + u32 gw_throughput, orig_throughput, threshold; + bool ret = false; + + threshold = atomic_read(&bat_priv->gw.sel_class); + + curr_gw = batadv_gw_node_get(bat_priv, curr_gw_orig); + if (!curr_gw) { + ret = true; + goto out; + } + + if (batadv_v_gw_throughput_get(curr_gw, &gw_throughput) < 0) { + ret = true; + goto out; + } + + orig_gw = batadv_gw_node_get(bat_priv, orig_node); + if (!orig_node) + goto out; + + if (batadv_v_gw_throughput_get(orig_gw, &orig_throughput) < 0) + goto out; + + if (orig_throughput < gw_throughput) + goto out; + + if ((orig_throughput - gw_throughput) < threshold) + goto out; + + batadv_dbg(BATADV_DBG_BATMAN, bat_priv, + "Restarting gateway selection: better gateway found (throughput curr: %u, throughput new: %u)\n", + gw_throughput, orig_throughput); + + ret = true; +out: + if (curr_gw) + batadv_gw_node_put(curr_gw); + if (orig_gw) + batadv_gw_node_put(orig_gw); + + return ret; +} + +#ifdef CONFIG_BATMAN_ADV_DEBUGFS +/* fails if orig_node has no router */ +static int batadv_v_gw_write_buffer_text(struct batadv_priv *bat_priv, + struct seq_file *seq, + const struct batadv_gw_node *gw_node) +{ + struct batadv_gw_node *curr_gw; + struct batadv_neigh_node *router; + struct batadv_neigh_ifinfo *router_ifinfo = NULL; + int ret = -1; + + router = batadv_orig_router_get(gw_node->orig_node, BATADV_IF_DEFAULT); + if (!router) + goto out; + + router_ifinfo = batadv_neigh_ifinfo_get(router, BATADV_IF_DEFAULT); + if (!router_ifinfo) + goto out; + + curr_gw = batadv_gw_get_selected_gw_node(bat_priv); + + seq_printf(seq, "%s %pM (%9u.%1u) %pM [%10s]: %u.%u/%u.%u MBit\n", + (curr_gw == gw_node ? "=>" : " "), + gw_node->orig_node->orig, + router_ifinfo->bat_v.throughput / 10, + router_ifinfo->bat_v.throughput % 10, router->addr, + router->if_incoming->net_dev->name, + gw_node->bandwidth_down / 10, + gw_node->bandwidth_down % 10, + gw_node->bandwidth_up / 10, + gw_node->bandwidth_up % 10); + ret = seq_has_overflowed(seq) ? -1 : 0; + + if (curr_gw) + batadv_gw_node_put(curr_gw); +out: + if (router_ifinfo) + batadv_neigh_ifinfo_put(router_ifinfo); + if (router) + batadv_neigh_node_put(router); + return ret; +} + +/** + * batadv_v_gw_print - print the gateway list + * @bat_priv: the bat priv with all the soft interface information + * @seq: gateway table seq_file struct + */ +static void batadv_v_gw_print(struct batadv_priv *bat_priv, + struct seq_file *seq) +{ + struct batadv_gw_node *gw_node; + int gw_count = 0; + + seq_puts(seq, + " Gateway ( throughput) Nexthop [outgoingIF]: advertised uplink bandwidth\n"); + + rcu_read_lock(); + hlist_for_each_entry_rcu(gw_node, &bat_priv->gw.list, list) { + /* fails if orig_node has no router */ + if (batadv_v_gw_write_buffer_text(bat_priv, seq, gw_node) < 0) + continue; + + gw_count++; + } + rcu_read_unlock(); + + if (gw_count == 0) + seq_puts(seq, "No gateways in range ...\n"); +} +#endif + +/** + * batadv_v_gw_dump_entry - Dump a gateway into a message + * @msg: Netlink message to dump into + * @portid: Port making netlink request + * @seq: Sequence number of netlink message + * @bat_priv: The bat priv with all the soft interface information + * @gw_node: Gateway to be dumped + * + * Return: Error code, or 0 on success + */ +static int batadv_v_gw_dump_entry(struct sk_buff *msg, u32 portid, u32 seq, + struct batadv_priv *bat_priv, + struct batadv_gw_node *gw_node) +{ + struct batadv_neigh_ifinfo *router_ifinfo = NULL; + struct batadv_neigh_node *router; + struct batadv_gw_node *curr_gw; + int ret = -EINVAL; + void *hdr; + + router = batadv_orig_router_get(gw_node->orig_node, BATADV_IF_DEFAULT); + if (!router) + goto out; + + router_ifinfo = batadv_neigh_ifinfo_get(router, BATADV_IF_DEFAULT); + if (!router_ifinfo) + goto out; + + curr_gw = batadv_gw_get_selected_gw_node(bat_priv); + + hdr = genlmsg_put(msg, portid, seq, &batadv_netlink_family, + NLM_F_MULTI, BATADV_CMD_GET_GATEWAYS); + if (!hdr) { + ret = -ENOBUFS; + goto out; + } + + ret = -EMSGSIZE; + + if (curr_gw == gw_node) { + if (nla_put_flag(msg, BATADV_ATTR_FLAG_BEST)) { + genlmsg_cancel(msg, hdr); + goto out; + } + } + + if (nla_put(msg, BATADV_ATTR_ORIG_ADDRESS, ETH_ALEN, + gw_node->orig_node->orig)) { + genlmsg_cancel(msg, hdr); + goto out; + } + + if (nla_put_u32(msg, BATADV_ATTR_THROUGHPUT, + router_ifinfo->bat_v.throughput)) { + genlmsg_cancel(msg, hdr); + goto out; + } + + if (nla_put(msg, BATADV_ATTR_ROUTER, ETH_ALEN, router->addr)) { + genlmsg_cancel(msg, hdr); + goto out; + } + + if (nla_put_string(msg, BATADV_ATTR_HARD_IFNAME, + router->if_incoming->net_dev->name)) { + genlmsg_cancel(msg, hdr); + goto out; + } + + if (nla_put_u32(msg, BATADV_ATTR_BANDWIDTH_DOWN, + gw_node->bandwidth_down)) { + genlmsg_cancel(msg, hdr); + goto out; + } + + if (nla_put_u32(msg, BATADV_ATTR_BANDWIDTH_UP, gw_node->bandwidth_up)) { + genlmsg_cancel(msg, hdr); + goto out; + } + + genlmsg_end(msg, hdr); + ret = 0; + +out: + if (router_ifinfo) + batadv_neigh_ifinfo_put(router_ifinfo); + if (router) + batadv_neigh_node_put(router); + return ret; +} + +/** + * batadv_v_gw_dump - Dump gateways into a message + * @msg: Netlink message to dump into + * @cb: Control block containing additional options + * @bat_priv: The bat priv with all the soft interface information + */ +static void batadv_v_gw_dump(struct sk_buff *msg, struct netlink_callback *cb, + struct batadv_priv *bat_priv) +{ + int portid = NETLINK_CB(cb->skb).portid; + struct batadv_gw_node *gw_node; + int idx_skip = cb->args[0]; + int idx = 0; + + rcu_read_lock(); + hlist_for_each_entry_rcu(gw_node, &bat_priv->gw.list, list) { + if (idx++ < idx_skip) + continue; + + if (batadv_v_gw_dump_entry(msg, portid, cb->nlh->nlmsg_seq, + bat_priv, gw_node)) { + idx_skip = idx - 1; + goto unlock; + } + } + + idx_skip = idx; +unlock: + rcu_read_unlock(); + + cb->args[0] = idx_skip; +} + static struct batadv_algo_ops batadv_batman_v __read_mostly = { .name = "BATMAN_V", .iface = { @@ -333,10 +1040,26 @@ static struct batadv_algo_ops batadv_batman_v __read_mostly = { .hardif_init = batadv_v_hardif_neigh_init, .cmp = batadv_v_neigh_cmp, .is_similar_or_better = batadv_v_neigh_is_sob, +#ifdef CONFIG_BATMAN_ADV_DEBUGFS .print = batadv_v_neigh_print, +#endif + .dump = batadv_v_neigh_dump, }, .orig = { +#ifdef CONFIG_BATMAN_ADV_DEBUGFS .print = batadv_v_orig_print, +#endif + .dump = batadv_v_orig_dump, + }, + .gw = { + .store_sel_class = batadv_v_store_sel_class, + .show_sel_class = batadv_v_show_sel_class, + .get_best_gw_node = batadv_v_gw_get_best_gw_node, + .is_eligible = batadv_v_gw_is_eligible, +#ifdef CONFIG_BATMAN_ADV_DEBUGFS + .print = batadv_v_gw_print, +#endif + .dump = batadv_v_gw_dump, }, }; @@ -363,7 +1086,16 @@ void batadv_v_hardif_init(struct batadv_hard_iface *hard_iface) */ int batadv_v_mesh_init(struct batadv_priv *bat_priv) { - return batadv_v_ogm_init(bat_priv); + int ret = 0; + + ret = batadv_v_ogm_init(bat_priv); + if (ret < 0) + return ret; + + /* set default throughput difference threshold to 5Mbps */ + atomic_set(&bat_priv->gw.sel_class, 50); + + return 0; } /** diff --git a/net/batman-adv/bat_v_ogm.c b/net/batman-adv/bat_v_ogm.c index 6fbba4eb0617..1aeeadca620c 100644 --- a/net/batman-adv/bat_v_ogm.c +++ b/net/batman-adv/bat_v_ogm.c @@ -73,13 +73,12 @@ struct batadv_orig_node *batadv_v_ogm_orig_get(struct batadv_priv *bat_priv, if (!orig_node) return NULL; + kref_get(&orig_node->refcount); hash_added = batadv_hash_add(bat_priv->orig_hash, batadv_compare_orig, batadv_choose_orig, orig_node, &orig_node->hash_entry); if (hash_added != 0) { - /* orig_node->refcounter is initialised to 2 by - * batadv_orig_node_new() - */ + /* remove refcnt for newly created orig_node and hash entry */ batadv_orig_node_put(orig_node); batadv_orig_node_put(orig_node); orig_node = NULL; diff --git a/net/batman-adv/bridge_loop_avoidance.c b/net/batman-adv/bridge_loop_avoidance.c index ad2ffe16d29f..e7f690b571ea 100644 --- a/net/batman-adv/bridge_loop_avoidance.c +++ b/net/batman-adv/bridge_loop_avoidance.c @@ -35,6 +35,7 @@ #include <linux/list.h> #include <linux/lockdep.h> #include <linux/netdevice.h> +#include <linux/netlink.h> #include <linux/rculist.h> #include <linux/rcupdate.h> #include <linux/seq_file.h> @@ -45,12 +46,18 @@ #include <linux/string.h> #include <linux/workqueue.h> #include <net/arp.h> +#include <net/genetlink.h> +#include <net/netlink.h> +#include <net/sock.h> +#include <uapi/linux/batman_adv.h> #include "hard-interface.h" #include "hash.h" #include "log.h" +#include "netlink.h" #include "originator.h" #include "packet.h" +#include "soft-interface.h" #include "sysfs.h" #include "translation-table.h" @@ -519,11 +526,9 @@ batadv_bla_get_backbone_gw(struct batadv_priv *bat_priv, u8 *orig, atomic_set(&entry->wait_periods, 0); ether_addr_copy(entry->orig, orig); INIT_WORK(&entry->report_work, batadv_bla_loopdetect_report); - - /* one for the hash, one for returning */ kref_init(&entry->refcount); - kref_get(&entry->refcount); + kref_get(&entry->refcount); hash_added = batadv_hash_add(bat_priv->bla.backbone_hash, batadv_compare_backbone_gw, batadv_choose_backbone_gw, entry, @@ -711,12 +716,13 @@ static void batadv_bla_add_claim(struct batadv_priv *bat_priv, claim->lasttime = jiffies; kref_get(&backbone_gw->refcount); claim->backbone_gw = backbone_gw; - kref_init(&claim->refcount); - kref_get(&claim->refcount); + batadv_dbg(BATADV_DBG_BLA, bat_priv, "bla_add_claim(): adding new entry %pM, vid %d to hash ...\n", mac, BATADV_PRINT_VID(vid)); + + kref_get(&claim->refcount); hash_added = batadv_hash_add(bat_priv->bla.claim_hash, batadv_compare_claim, batadv_choose_claim, claim, @@ -1148,7 +1154,7 @@ static bool batadv_bla_process_claim(struct batadv_priv *bat_priv, /* Let the loopdetect frames on the mesh in any case. */ if (bla_dst->type == BATADV_CLAIM_TYPE_LOOPDETECT) - return 0; + return false; /* check if it is a claim frame. */ ret = batadv_check_claim_group(bat_priv, primary_if, hw_src, hw_dst, @@ -1990,6 +1996,7 @@ out: return ret; } +#ifdef CONFIG_BATMAN_ADV_DEBUGFS /** * batadv_bla_claim_table_seq_print_text - print the claim table in a seq file * @seq: seq file to print on @@ -2050,8 +2057,172 @@ out: batadv_hardif_put(primary_if); return 0; } +#endif + +/** + * batadv_bla_claim_dump_entry - dump one entry of the claim table + * to a netlink socket + * @msg: buffer for the message + * @portid: netlink port + * @seq: Sequence number of netlink message + * @primary_if: primary interface + * @claim: entry to dump + * + * Return: 0 or error code. + */ +static int +batadv_bla_claim_dump_entry(struct sk_buff *msg, u32 portid, u32 seq, + struct batadv_hard_iface *primary_if, + struct batadv_bla_claim *claim) +{ + u8 *primary_addr = primary_if->net_dev->dev_addr; + u16 backbone_crc; + bool is_own; + void *hdr; + int ret = -EINVAL; + + hdr = genlmsg_put(msg, portid, seq, &batadv_netlink_family, + NLM_F_MULTI, BATADV_CMD_GET_BLA_CLAIM); + if (!hdr) { + ret = -ENOBUFS; + goto out; + } + + is_own = batadv_compare_eth(claim->backbone_gw->orig, + primary_addr); + + spin_lock_bh(&claim->backbone_gw->crc_lock); + backbone_crc = claim->backbone_gw->crc; + spin_unlock_bh(&claim->backbone_gw->crc_lock); + + if (is_own) + if (nla_put_flag(msg, BATADV_ATTR_BLA_OWN)) { + genlmsg_cancel(msg, hdr); + goto out; + } + + if (nla_put(msg, BATADV_ATTR_BLA_ADDRESS, ETH_ALEN, claim->addr) || + nla_put_u16(msg, BATADV_ATTR_BLA_VID, claim->vid) || + nla_put(msg, BATADV_ATTR_BLA_BACKBONE, ETH_ALEN, + claim->backbone_gw->orig) || + nla_put_u16(msg, BATADV_ATTR_BLA_CRC, + backbone_crc)) { + genlmsg_cancel(msg, hdr); + goto out; + } + + genlmsg_end(msg, hdr); + ret = 0; + +out: + return ret; +} + +/** + * batadv_bla_claim_dump_bucket - dump one bucket of the claim table + * to a netlink socket + * @msg: buffer for the message + * @portid: netlink port + * @seq: Sequence number of netlink message + * @primary_if: primary interface + * @head: bucket to dump + * @idx_skip: How many entries to skip + * + * Return: always 0. + */ +static int +batadv_bla_claim_dump_bucket(struct sk_buff *msg, u32 portid, u32 seq, + struct batadv_hard_iface *primary_if, + struct hlist_head *head, int *idx_skip) +{ + struct batadv_bla_claim *claim; + int idx = 0; + + rcu_read_lock(); + hlist_for_each_entry_rcu(claim, head, hash_entry) { + if (idx++ < *idx_skip) + continue; + if (batadv_bla_claim_dump_entry(msg, portid, seq, + primary_if, claim)) { + *idx_skip = idx - 1; + goto unlock; + } + } + + *idx_skip = idx; +unlock: + rcu_read_unlock(); + return 0; +} /** + * batadv_bla_claim_dump - dump claim table to a netlink socket + * @msg: buffer for the message + * @cb: callback structure containing arguments + * + * Return: message length. + */ +int batadv_bla_claim_dump(struct sk_buff *msg, struct netlink_callback *cb) +{ + struct batadv_hard_iface *primary_if = NULL; + int portid = NETLINK_CB(cb->skb).portid; + struct net *net = sock_net(cb->skb->sk); + struct net_device *soft_iface; + struct batadv_hashtable *hash; + struct batadv_priv *bat_priv; + int bucket = cb->args[0]; + struct hlist_head *head; + int idx = cb->args[1]; + int ifindex; + int ret = 0; + + ifindex = batadv_netlink_get_ifindex(cb->nlh, + BATADV_ATTR_MESH_IFINDEX); + if (!ifindex) + return -EINVAL; + + soft_iface = dev_get_by_index(net, ifindex); + if (!soft_iface || !batadv_softif_is_valid(soft_iface)) { + ret = -ENODEV; + goto out; + } + + bat_priv = netdev_priv(soft_iface); + hash = bat_priv->bla.claim_hash; + + primary_if = batadv_primary_if_get_selected(bat_priv); + if (!primary_if || primary_if->if_status != BATADV_IF_ACTIVE) { + ret = -ENOENT; + goto out; + } + + while (bucket < hash->size) { + head = &hash->table[bucket]; + + if (batadv_bla_claim_dump_bucket(msg, portid, + cb->nlh->nlmsg_seq, + primary_if, head, &idx)) + break; + bucket++; + } + + cb->args[0] = bucket; + cb->args[1] = idx; + + ret = msg->len; + +out: + if (primary_if) + batadv_hardif_put(primary_if); + + if (soft_iface) + dev_put(soft_iface); + + return ret; +} + +#ifdef CONFIG_BATMAN_ADV_DEBUGFS +/** * batadv_bla_backbone_table_seq_print_text - print the backbone table in a seq * file * @seq: seq file to print on @@ -2114,3 +2285,168 @@ out: batadv_hardif_put(primary_if); return 0; } +#endif + +/** + * batadv_bla_backbone_dump_entry - dump one entry of the backbone table + * to a netlink socket + * @msg: buffer for the message + * @portid: netlink port + * @seq: Sequence number of netlink message + * @primary_if: primary interface + * @backbone_gw: entry to dump + * + * Return: 0 or error code. + */ +static int +batadv_bla_backbone_dump_entry(struct sk_buff *msg, u32 portid, u32 seq, + struct batadv_hard_iface *primary_if, + struct batadv_bla_backbone_gw *backbone_gw) +{ + u8 *primary_addr = primary_if->net_dev->dev_addr; + u16 backbone_crc; + bool is_own; + int msecs; + void *hdr; + int ret = -EINVAL; + + hdr = genlmsg_put(msg, portid, seq, &batadv_netlink_family, + NLM_F_MULTI, BATADV_CMD_GET_BLA_BACKBONE); + if (!hdr) { + ret = -ENOBUFS; + goto out; + } + + is_own = batadv_compare_eth(backbone_gw->orig, primary_addr); + + spin_lock_bh(&backbone_gw->crc_lock); + backbone_crc = backbone_gw->crc; + spin_unlock_bh(&backbone_gw->crc_lock); + + msecs = jiffies_to_msecs(jiffies - backbone_gw->lasttime); + + if (is_own) + if (nla_put_flag(msg, BATADV_ATTR_BLA_OWN)) { + genlmsg_cancel(msg, hdr); + goto out; + } + + if (nla_put(msg, BATADV_ATTR_BLA_BACKBONE, ETH_ALEN, + backbone_gw->orig) || + nla_put_u16(msg, BATADV_ATTR_BLA_VID, backbone_gw->vid) || + nla_put_u16(msg, BATADV_ATTR_BLA_CRC, + backbone_crc) || + nla_put_u32(msg, BATADV_ATTR_LAST_SEEN_MSECS, msecs)) { + genlmsg_cancel(msg, hdr); + goto out; + } + + genlmsg_end(msg, hdr); + ret = 0; + +out: + return ret; +} + +/** + * batadv_bla_backbone_dump_bucket - dump one bucket of the backbone table + * to a netlink socket + * @msg: buffer for the message + * @portid: netlink port + * @seq: Sequence number of netlink message + * @primary_if: primary interface + * @head: bucket to dump + * @idx_skip: How many entries to skip + * + * Return: always 0. + */ +static int +batadv_bla_backbone_dump_bucket(struct sk_buff *msg, u32 portid, u32 seq, + struct batadv_hard_iface *primary_if, + struct hlist_head *head, int *idx_skip) +{ + struct batadv_bla_backbone_gw *backbone_gw; + int idx = 0; + + rcu_read_lock(); + hlist_for_each_entry_rcu(backbone_gw, head, hash_entry) { + if (idx++ < *idx_skip) + continue; + if (batadv_bla_backbone_dump_entry(msg, portid, seq, + primary_if, backbone_gw)) { + *idx_skip = idx - 1; + goto unlock; + } + } + + *idx_skip = idx; +unlock: + rcu_read_unlock(); + return 0; +} + +/** + * batadv_bla_backbone_dump - dump backbone table to a netlink socket + * @msg: buffer for the message + * @cb: callback structure containing arguments + * + * Return: message length. + */ +int batadv_bla_backbone_dump(struct sk_buff *msg, struct netlink_callback *cb) +{ + struct batadv_hard_iface *primary_if = NULL; + int portid = NETLINK_CB(cb->skb).portid; + struct net *net = sock_net(cb->skb->sk); + struct net_device *soft_iface; + struct batadv_hashtable *hash; + struct batadv_priv *bat_priv; + int bucket = cb->args[0]; + struct hlist_head *head; + int idx = cb->args[1]; + int ifindex; + int ret = 0; + + ifindex = batadv_netlink_get_ifindex(cb->nlh, + BATADV_ATTR_MESH_IFINDEX); + if (!ifindex) + return -EINVAL; + + soft_iface = dev_get_by_index(net, ifindex); + if (!soft_iface || !batadv_softif_is_valid(soft_iface)) { + ret = -ENODEV; + goto out; + } + + bat_priv = netdev_priv(soft_iface); + hash = bat_priv->bla.backbone_hash; + + primary_if = batadv_primary_if_get_selected(bat_priv); + if (!primary_if || primary_if->if_status != BATADV_IF_ACTIVE) { + ret = -ENOENT; + goto out; + } + + while (bucket < hash->size) { + head = &hash->table[bucket]; + + if (batadv_bla_backbone_dump_bucket(msg, portid, + cb->nlh->nlmsg_seq, + primary_if, head, &idx)) + break; + bucket++; + } + + cb->args[0] = bucket; + cb->args[1] = idx; + + ret = msg->len; + +out: + if (primary_if) + batadv_hardif_put(primary_if); + + if (soft_iface) + dev_put(soft_iface); + + return ret; +} diff --git a/net/batman-adv/bridge_loop_avoidance.h b/net/batman-adv/bridge_loop_avoidance.h index 0f01daeb359e..1ae93e46fb98 100644 --- a/net/batman-adv/bridge_loop_avoidance.h +++ b/net/batman-adv/bridge_loop_avoidance.h @@ -23,6 +23,7 @@ #include <linux/types.h> struct net_device; +struct netlink_callback; struct seq_file; struct sk_buff; @@ -35,8 +36,10 @@ bool batadv_bla_is_backbone_gw(struct sk_buff *skb, struct batadv_orig_node *orig_node, int hdr_size); int batadv_bla_claim_table_seq_print_text(struct seq_file *seq, void *offset); +int batadv_bla_claim_dump(struct sk_buff *msg, struct netlink_callback *cb); int batadv_bla_backbone_table_seq_print_text(struct seq_file *seq, void *offset); +int batadv_bla_backbone_dump(struct sk_buff *msg, struct netlink_callback *cb); bool batadv_bla_is_backbone_gw_orig(struct batadv_priv *bat_priv, u8 *orig, unsigned short vid); bool batadv_bla_check_bcast_duplist(struct batadv_priv *bat_priv, @@ -47,7 +50,7 @@ void batadv_bla_update_orig_address(struct batadv_priv *bat_priv, void batadv_bla_status_update(struct net_device *net_dev); int batadv_bla_init(struct batadv_priv *bat_priv); void batadv_bla_free(struct batadv_priv *bat_priv); - +int batadv_bla_claim_dump(struct sk_buff *msg, struct netlink_callback *cb); #define BATADV_BLA_CRC_INIT 0 #else /* ifdef CONFIG_BATMAN_ADV_BLA */ @@ -112,6 +115,18 @@ static inline void batadv_bla_free(struct batadv_priv *bat_priv) { } +static inline int batadv_bla_claim_dump(struct sk_buff *msg, + struct netlink_callback *cb) +{ + return -EOPNOTSUPP; +} + +static inline int batadv_bla_backbone_dump(struct sk_buff *msg, + struct netlink_callback *cb) +{ + return -EOPNOTSUPP; +} + #endif /* ifdef CONFIG_BATMAN_ADV_BLA */ #endif /* ifndef _NET_BATMAN_ADV_BLA_H_ */ diff --git a/net/batman-adv/debugfs.c b/net/batman-adv/debugfs.c index 1d68b6e63b96..b4ffba7dd583 100644 --- a/net/batman-adv/debugfs.c +++ b/net/batman-adv/debugfs.c @@ -31,6 +31,7 @@ #include <linux/stddef.h> #include <linux/stringify.h> #include <linux/sysfs.h> +#include <net/net_namespace.h> #include "bat_algo.h" #include "bridge_loop_avoidance.h" @@ -305,12 +306,16 @@ void batadv_debugfs_destroy(void) */ int batadv_debugfs_add_hardif(struct batadv_hard_iface *hard_iface) { + struct net *net = dev_net(hard_iface->net_dev); struct batadv_debuginfo **bat_debug; struct dentry *file; if (!batadv_debugfs) goto out; + if (net != &init_net) + return 0; + hard_iface->debug_dir = debugfs_create_dir(hard_iface->net_dev->name, batadv_debugfs); if (!hard_iface->debug_dir) @@ -341,6 +346,11 @@ out: */ void batadv_debugfs_del_hardif(struct batadv_hard_iface *hard_iface) { + struct net *net = dev_net(hard_iface->net_dev); + + if (net != &init_net) + return; + if (batadv_debugfs) { debugfs_remove_recursive(hard_iface->debug_dir); hard_iface->debug_dir = NULL; @@ -351,11 +361,15 @@ int batadv_debugfs_add_meshif(struct net_device *dev) { struct batadv_priv *bat_priv = netdev_priv(dev); struct batadv_debuginfo **bat_debug; + struct net *net = dev_net(dev); struct dentry *file; if (!batadv_debugfs) goto out; + if (net != &init_net) + return 0; + bat_priv->debug_dir = debugfs_create_dir(dev->name, batadv_debugfs); if (!bat_priv->debug_dir) goto out; @@ -392,6 +406,10 @@ out: void batadv_debugfs_del_meshif(struct net_device *dev) { struct batadv_priv *bat_priv = netdev_priv(dev); + struct net *net = dev_net(dev); + + if (net != &init_net) + return; batadv_debug_log_cleanup(bat_priv); diff --git a/net/batman-adv/debugfs.h b/net/batman-adv/debugfs.h index 1ab4e2e63afc..c68ff3dcb926 100644 --- a/net/batman-adv/debugfs.h +++ b/net/batman-adv/debugfs.h @@ -26,7 +26,7 @@ struct net_device; #define BATADV_DEBUGFS_SUBDIR "batman_adv" -#if IS_ENABLED(CONFIG_DEBUG_FS) +#if IS_ENABLED(CONFIG_BATMAN_ADV_DEBUGFS) void batadv_debugfs_init(void); void batadv_debugfs_destroy(void); diff --git a/net/batman-adv/distributed-arp-table.c b/net/batman-adv/distributed-arp-table.c index b1cc8bfe11ac..e257efdc5d03 100644 --- a/net/batman-adv/distributed-arp-table.c +++ b/net/batman-adv/distributed-arp-table.c @@ -343,8 +343,8 @@ static void batadv_dat_entry_add(struct batadv_priv *bat_priv, __be32 ip, ether_addr_copy(dat_entry->mac_addr, mac_addr); dat_entry->last_update = jiffies; kref_init(&dat_entry->refcount); - kref_get(&dat_entry->refcount); + kref_get(&dat_entry->refcount); hash_added = batadv_hash_add(bat_priv->dat.hash, batadv_compare_dat, batadv_hash_dat, dat_entry, &dat_entry->hash_entry); @@ -795,6 +795,7 @@ void batadv_dat_free(struct batadv_priv *bat_priv) batadv_dat_hash_free(bat_priv); } +#ifdef CONFIG_BATMAN_ADV_DEBUGFS /** * batadv_dat_cache_seq_print_text - print the local DAT hash table * @seq: seq file to print on @@ -846,6 +847,7 @@ out: batadv_hardif_put(primary_if); return 0; } +#endif /** * batadv_arp_get_type - parse an ARP packet and gets the type diff --git a/net/batman-adv/gateway_client.c b/net/batman-adv/gateway_client.c index 63a805d3f96e..de055d64debe 100644 --- a/net/batman-adv/gateway_client.c +++ b/net/batman-adv/gateway_client.c @@ -20,6 +20,7 @@ #include <linux/atomic.h> #include <linux/byteorder/generic.h> +#include <linux/errno.h> #include <linux/etherdevice.h> #include <linux/fs.h> #include <linux/if_ether.h> @@ -31,6 +32,7 @@ #include <linux/kref.h> #include <linux/list.h> #include <linux/netdevice.h> +#include <linux/netlink.h> #include <linux/rculist.h> #include <linux/rcupdate.h> #include <linux/seq_file.h> @@ -39,13 +41,17 @@ #include <linux/spinlock.h> #include <linux/stddef.h> #include <linux/udp.h> +#include <net/sock.h> +#include <uapi/linux/batman_adv.h> #include "gateway_common.h" #include "hard-interface.h" #include "log.h" +#include "netlink.h" #include "originator.h" #include "packet.h" #include "routing.h" +#include "soft-interface.h" #include "sysfs.h" #include "translation-table.h" @@ -80,12 +86,12 @@ static void batadv_gw_node_release(struct kref *ref) * batadv_gw_node_put - decrement the gw_node refcounter and possibly release it * @gw_node: gateway node to free */ -static void batadv_gw_node_put(struct batadv_gw_node *gw_node) +void batadv_gw_node_put(struct batadv_gw_node *gw_node) { kref_put(&gw_node->refcount, batadv_gw_node_release); } -static struct batadv_gw_node * +struct batadv_gw_node * batadv_gw_get_selected_gw_node(struct batadv_priv *bat_priv) { struct batadv_gw_node *gw_node; @@ -164,86 +170,6 @@ void batadv_gw_reselect(struct batadv_priv *bat_priv) atomic_set(&bat_priv->gw.reselect, 1); } -static struct batadv_gw_node * -batadv_gw_get_best_gw_node(struct batadv_priv *bat_priv) -{ - struct batadv_neigh_node *router; - struct batadv_neigh_ifinfo *router_ifinfo; - struct batadv_gw_node *gw_node, *curr_gw = NULL; - u64 max_gw_factor = 0; - u64 tmp_gw_factor = 0; - u8 max_tq = 0; - u8 tq_avg; - struct batadv_orig_node *orig_node; - - rcu_read_lock(); - hlist_for_each_entry_rcu(gw_node, &bat_priv->gw.list, list) { - orig_node = gw_node->orig_node; - router = batadv_orig_router_get(orig_node, BATADV_IF_DEFAULT); - if (!router) - continue; - - router_ifinfo = batadv_neigh_ifinfo_get(router, - BATADV_IF_DEFAULT); - if (!router_ifinfo) - goto next; - - if (!kref_get_unless_zero(&gw_node->refcount)) - goto next; - - tq_avg = router_ifinfo->bat_iv.tq_avg; - - switch (atomic_read(&bat_priv->gw.sel_class)) { - case 1: /* fast connection */ - tmp_gw_factor = tq_avg * tq_avg; - tmp_gw_factor *= gw_node->bandwidth_down; - tmp_gw_factor *= 100 * 100; - tmp_gw_factor >>= 18; - - if ((tmp_gw_factor > max_gw_factor) || - ((tmp_gw_factor == max_gw_factor) && - (tq_avg > max_tq))) { - if (curr_gw) - batadv_gw_node_put(curr_gw); - curr_gw = gw_node; - kref_get(&curr_gw->refcount); - } - break; - - default: /* 2: stable connection (use best statistic) - * 3: fast-switch (use best statistic but change as - * soon as a better gateway appears) - * XX: late-switch (use best statistic but change as - * soon as a better gateway appears which has - * $routing_class more tq points) - */ - if (tq_avg > max_tq) { - if (curr_gw) - batadv_gw_node_put(curr_gw); - curr_gw = gw_node; - kref_get(&curr_gw->refcount); - } - break; - } - - if (tq_avg > max_tq) - max_tq = tq_avg; - - if (tmp_gw_factor > max_gw_factor) - max_gw_factor = tmp_gw_factor; - - batadv_gw_node_put(gw_node); - -next: - batadv_neigh_node_put(router); - if (router_ifinfo) - batadv_neigh_ifinfo_put(router_ifinfo); - } - rcu_read_unlock(); - - return curr_gw; -} - /** * batadv_gw_check_client_stop - check if client mode has been switched off * @bat_priv: the bat priv with all the soft interface information @@ -287,12 +213,19 @@ void batadv_gw_election(struct batadv_priv *bat_priv) if (atomic_read(&bat_priv->gw.mode) != BATADV_GW_MODE_CLIENT) goto out; + if (!bat_priv->algo_ops->gw.get_best_gw_node) + goto out; + curr_gw = batadv_gw_get_selected_gw_node(bat_priv); if (!batadv_atomic_dec_not_zero(&bat_priv->gw.reselect) && curr_gw) goto out; - next_gw = batadv_gw_get_best_gw_node(bat_priv); + /* if gw.reselect is set to 1 it means that a previous call to + * gw.is_eligible() said that we have a new best GW, therefore it can + * now be picked from the list and selected + */ + next_gw = bat_priv->algo_ops->gw.get_best_gw_node(bat_priv); if (curr_gw == next_gw) goto out; @@ -360,70 +293,31 @@ out: void batadv_gw_check_election(struct batadv_priv *bat_priv, struct batadv_orig_node *orig_node) { - struct batadv_neigh_ifinfo *router_orig_tq = NULL; - struct batadv_neigh_ifinfo *router_gw_tq = NULL; struct batadv_orig_node *curr_gw_orig; - struct batadv_neigh_node *router_gw = NULL; - struct batadv_neigh_node *router_orig = NULL; - u8 gw_tq_avg, orig_tq_avg; + + /* abort immediately if the routing algorithm does not support gateway + * election + */ + if (!bat_priv->algo_ops->gw.is_eligible) + return; curr_gw_orig = batadv_gw_get_selected_orig(bat_priv); if (!curr_gw_orig) goto reselect; - router_gw = batadv_orig_router_get(curr_gw_orig, BATADV_IF_DEFAULT); - if (!router_gw) - goto reselect; - - router_gw_tq = batadv_neigh_ifinfo_get(router_gw, - BATADV_IF_DEFAULT); - if (!router_gw_tq) - goto reselect; - /* this node already is the gateway */ if (curr_gw_orig == orig_node) goto out; - router_orig = batadv_orig_router_get(orig_node, BATADV_IF_DEFAULT); - if (!router_orig) + if (!bat_priv->algo_ops->gw.is_eligible(bat_priv, curr_gw_orig, + orig_node)) goto out; - router_orig_tq = batadv_neigh_ifinfo_get(router_orig, - BATADV_IF_DEFAULT); - if (!router_orig_tq) - goto out; - - gw_tq_avg = router_gw_tq->bat_iv.tq_avg; - orig_tq_avg = router_orig_tq->bat_iv.tq_avg; - - /* the TQ value has to be better */ - if (orig_tq_avg < gw_tq_avg) - goto out; - - /* if the routing class is greater than 3 the value tells us how much - * greater the TQ value of the new gateway must be - */ - if ((atomic_read(&bat_priv->gw.sel_class) > 3) && - (orig_tq_avg - gw_tq_avg < atomic_read(&bat_priv->gw.sel_class))) - goto out; - - batadv_dbg(BATADV_DBG_BATMAN, bat_priv, - "Restarting gateway selection: better gateway found (tq curr: %i, tq new: %i)\n", - gw_tq_avg, orig_tq_avg); - reselect: batadv_gw_reselect(bat_priv); out: if (curr_gw_orig) batadv_orig_node_put(curr_gw_orig); - if (router_gw) - batadv_neigh_node_put(router_gw); - if (router_orig) - batadv_neigh_node_put(router_orig); - if (router_gw_tq) - batadv_neigh_ifinfo_put(router_gw_tq); - if (router_orig_tq) - batadv_neigh_ifinfo_put(router_orig_tq); } /** @@ -445,14 +339,15 @@ static void batadv_gw_node_add(struct batadv_priv *bat_priv, if (!gw_node) return; - kref_get(&orig_node->refcount); + kref_init(&gw_node->refcount); INIT_HLIST_NODE(&gw_node->list); + kref_get(&orig_node->refcount); gw_node->orig_node = orig_node; gw_node->bandwidth_down = ntohl(gateway->bandwidth_down); gw_node->bandwidth_up = ntohl(gateway->bandwidth_up); - kref_init(&gw_node->refcount); spin_lock_bh(&bat_priv->gw.list_lock); + kref_get(&gw_node->refcount); hlist_add_head_rcu(&gw_node->list, &bat_priv->gw.list); spin_unlock_bh(&bat_priv->gw.list_lock); @@ -463,6 +358,9 @@ static void batadv_gw_node_add(struct batadv_priv *bat_priv, ntohl(gateway->bandwidth_down) % 10, ntohl(gateway->bandwidth_up) / 10, ntohl(gateway->bandwidth_up) % 10); + + /* don't return reference to new gw_node */ + batadv_gw_node_put(gw_node); } /** @@ -472,9 +370,8 @@ static void batadv_gw_node_add(struct batadv_priv *bat_priv, * * Return: gateway node if found or NULL otherwise. */ -static struct batadv_gw_node * -batadv_gw_node_get(struct batadv_priv *bat_priv, - struct batadv_orig_node *orig_node) +struct batadv_gw_node *batadv_gw_node_get(struct batadv_priv *bat_priv, + struct batadv_orig_node *orig_node) { struct batadv_gw_node *gw_node_tmp, *gw_node = NULL; @@ -585,81 +482,87 @@ void batadv_gw_node_free(struct batadv_priv *bat_priv) spin_unlock_bh(&bat_priv->gw.list_lock); } -/* fails if orig_node has no router */ -static int batadv_write_buffer_text(struct batadv_priv *bat_priv, - struct seq_file *seq, - const struct batadv_gw_node *gw_node) +#ifdef CONFIG_BATMAN_ADV_DEBUGFS +int batadv_gw_client_seq_print_text(struct seq_file *seq, void *offset) { - struct batadv_gw_node *curr_gw; - struct batadv_neigh_node *router; - struct batadv_neigh_ifinfo *router_ifinfo = NULL; - int ret = -1; + struct net_device *net_dev = (struct net_device *)seq->private; + struct batadv_priv *bat_priv = netdev_priv(net_dev); + struct batadv_hard_iface *primary_if; - router = batadv_orig_router_get(gw_node->orig_node, BATADV_IF_DEFAULT); - if (!router) - goto out; + primary_if = batadv_seq_print_text_primary_if_get(seq); + if (!primary_if) + return 0; - router_ifinfo = batadv_neigh_ifinfo_get(router, BATADV_IF_DEFAULT); - if (!router_ifinfo) - goto out; + seq_printf(seq, "[B.A.T.M.A.N. adv %s, MainIF/MAC: %s/%pM (%s %s)]\n", + BATADV_SOURCE_VERSION, primary_if->net_dev->name, + primary_if->net_dev->dev_addr, net_dev->name, + bat_priv->algo_ops->name); - curr_gw = batadv_gw_get_selected_gw_node(bat_priv); + batadv_hardif_put(primary_if); - seq_printf(seq, "%s %pM (%3i) %pM [%10s]: %u.%u/%u.%u MBit\n", - (curr_gw == gw_node ? "=>" : " "), - gw_node->orig_node->orig, - router_ifinfo->bat_iv.tq_avg, router->addr, - router->if_incoming->net_dev->name, - gw_node->bandwidth_down / 10, - gw_node->bandwidth_down % 10, - gw_node->bandwidth_up / 10, - gw_node->bandwidth_up % 10); - ret = seq_has_overflowed(seq) ? -1 : 0; + if (!bat_priv->algo_ops->gw.print) { + seq_puts(seq, + "No printing function for this routing protocol\n"); + return 0; + } - if (curr_gw) - batadv_gw_node_put(curr_gw); -out: - if (router_ifinfo) - batadv_neigh_ifinfo_put(router_ifinfo); - if (router) - batadv_neigh_node_put(router); - return ret; + bat_priv->algo_ops->gw.print(bat_priv, seq); + + return 0; } +#endif -int batadv_gw_client_seq_print_text(struct seq_file *seq, void *offset) +/** + * batadv_gw_dump - Dump gateways into a message + * @msg: Netlink message to dump into + * @cb: Control block containing additional options + * + * Return: Error code, or length of message + */ +int batadv_gw_dump(struct sk_buff *msg, struct netlink_callback *cb) { - struct net_device *net_dev = (struct net_device *)seq->private; - struct batadv_priv *bat_priv = netdev_priv(net_dev); - struct batadv_hard_iface *primary_if; - struct batadv_gw_node *gw_node; - int gw_count = 0; - - primary_if = batadv_seq_print_text_primary_if_get(seq); - if (!primary_if) + struct batadv_hard_iface *primary_if = NULL; + struct net *net = sock_net(cb->skb->sk); + struct net_device *soft_iface; + struct batadv_priv *bat_priv; + int ifindex; + int ret; + + ifindex = batadv_netlink_get_ifindex(cb->nlh, + BATADV_ATTR_MESH_IFINDEX); + if (!ifindex) + return -EINVAL; + + soft_iface = dev_get_by_index(net, ifindex); + if (!soft_iface || !batadv_softif_is_valid(soft_iface)) { + ret = -ENODEV; goto out; + } - seq_printf(seq, - " Gateway (#/255) Nexthop [outgoingIF]: advertised uplink bandwidth ... [B.A.T.M.A.N. adv %s, MainIF/MAC: %s/%pM (%s)]\n", - BATADV_SOURCE_VERSION, primary_if->net_dev->name, - primary_if->net_dev->dev_addr, net_dev->name); + bat_priv = netdev_priv(soft_iface); - rcu_read_lock(); - hlist_for_each_entry_rcu(gw_node, &bat_priv->gw.list, list) { - /* fails if orig_node has no router */ - if (batadv_write_buffer_text(bat_priv, seq, gw_node) < 0) - continue; + primary_if = batadv_primary_if_get_selected(bat_priv); + if (!primary_if || primary_if->if_status != BATADV_IF_ACTIVE) { + ret = -ENOENT; + goto out; + } - gw_count++; + if (!bat_priv->algo_ops->gw.dump) { + ret = -EOPNOTSUPP; + goto out; } - rcu_read_unlock(); - if (gw_count == 0) - seq_puts(seq, "No gateways in range ...\n"); + bat_priv->algo_ops->gw.dump(msg, cb, bat_priv); + + ret = msg->len; out: if (primary_if) batadv_hardif_put(primary_if); - return 0; + if (soft_iface) + dev_put(soft_iface); + + return ret; } /** diff --git a/net/batman-adv/gateway_client.h b/net/batman-adv/gateway_client.h index 582dd8c413c8..859166d03561 100644 --- a/net/batman-adv/gateway_client.h +++ b/net/batman-adv/gateway_client.h @@ -23,6 +23,7 @@ #include <linux/types.h> struct batadv_tvlv_gateway_data; +struct netlink_callback; struct seq_file; struct sk_buff; @@ -39,10 +40,16 @@ void batadv_gw_node_update(struct batadv_priv *bat_priv, void batadv_gw_node_delete(struct batadv_priv *bat_priv, struct batadv_orig_node *orig_node); void batadv_gw_node_free(struct batadv_priv *bat_priv); +void batadv_gw_node_put(struct batadv_gw_node *gw_node); +struct batadv_gw_node * +batadv_gw_get_selected_gw_node(struct batadv_priv *bat_priv); int batadv_gw_client_seq_print_text(struct seq_file *seq, void *offset); +int batadv_gw_dump(struct sk_buff *msg, struct netlink_callback *cb); bool batadv_gw_out_of_range(struct batadv_priv *bat_priv, struct sk_buff *skb); enum batadv_dhcp_recipient batadv_gw_dhcp_recipient_get(struct sk_buff *skb, unsigned int *header_len, u8 *chaddr); +struct batadv_gw_node *batadv_gw_node_get(struct batadv_priv *bat_priv, + struct batadv_orig_node *orig_node); #endif /* _NET_BATMAN_ADV_GATEWAY_CLIENT_H_ */ diff --git a/net/batman-adv/gateway_common.c b/net/batman-adv/gateway_common.c index d7bc6a87bcc9..21184810d89f 100644 --- a/net/batman-adv/gateway_common.c +++ b/net/batman-adv/gateway_common.c @@ -241,10 +241,9 @@ static void batadv_gw_tvlv_ogm_handler_v1(struct batadv_priv *bat_priv, batadv_gw_node_update(bat_priv, orig, &gateway); - /* restart gateway selection if fast or late switching was enabled */ + /* restart gateway selection */ if ((gateway.bandwidth_down != 0) && - (atomic_read(&bat_priv->gw.mode) == BATADV_GW_MODE_CLIENT) && - (atomic_read(&bat_priv->gw.sel_class) > 2)) + (atomic_read(&bat_priv->gw.mode) == BATADV_GW_MODE_CLIENT)) batadv_gw_check_election(bat_priv, orig); } diff --git a/net/batman-adv/hard-interface.c b/net/batman-adv/hard-interface.c index 1f9080840566..08ce36147c4c 100644 --- a/net/batman-adv/hard-interface.c +++ b/net/batman-adv/hard-interface.c @@ -35,7 +35,8 @@ #include <linux/rtnetlink.h> #include <linux/slab.h> #include <linux/spinlock.h> -#include <linux/workqueue.h> +#include <net/net_namespace.h> +#include <net/rtnetlink.h> #include "bat_v.h" #include "bridge_loop_avoidance.h" @@ -85,25 +86,55 @@ out: } /** + * batadv_getlink_net - return link net namespace (of use fallback) + * @netdev: net_device to check + * @fallback_net: return in case get_link_net is not available for @netdev + * + * Return: result of rtnl_link_ops->get_link_net or @fallback_net + */ +static const struct net *batadv_getlink_net(const struct net_device *netdev, + const struct net *fallback_net) +{ + if (!netdev->rtnl_link_ops) + return fallback_net; + + if (!netdev->rtnl_link_ops->get_link_net) + return fallback_net; + + return netdev->rtnl_link_ops->get_link_net(netdev); +} + +/** * batadv_mutual_parents - check if two devices are each others parent - * @dev1: 1st net_device - * @dev2: 2nd net_device + * @dev1: 1st net dev + * @net1: 1st devices netns + * @dev2: 2nd net dev + * @net2: 2nd devices netns * * veth devices come in pairs and each is the parent of the other! * * Return: true if the devices are each others parent, otherwise false */ static bool batadv_mutual_parents(const struct net_device *dev1, - const struct net_device *dev2) + const struct net *net1, + const struct net_device *dev2, + const struct net *net2) { int dev1_parent_iflink = dev_get_iflink(dev1); int dev2_parent_iflink = dev_get_iflink(dev2); + const struct net *dev1_parent_net; + const struct net *dev2_parent_net; + + dev1_parent_net = batadv_getlink_net(dev1, net1); + dev2_parent_net = batadv_getlink_net(dev2, net2); if (!dev1_parent_iflink || !dev2_parent_iflink) return false; return (dev1_parent_iflink == dev2->ifindex) && - (dev2_parent_iflink == dev1->ifindex); + (dev2_parent_iflink == dev1->ifindex) && + net_eq(dev1_parent_net, net2) && + net_eq(dev2_parent_net, net1); } /** @@ -121,8 +152,9 @@ static bool batadv_mutual_parents(const struct net_device *dev1, */ static bool batadv_is_on_batman_iface(const struct net_device *net_dev) { - struct net_device *parent_dev; struct net *net = dev_net(net_dev); + struct net_device *parent_dev; + const struct net *parent_net; bool ret; /* check if this is a batman-adv mesh interface */ @@ -134,13 +166,16 @@ static bool batadv_is_on_batman_iface(const struct net_device *net_dev) dev_get_iflink(net_dev) == net_dev->ifindex) return false; + parent_net = batadv_getlink_net(net_dev, net); + /* recurse over the parent device */ - parent_dev = __dev_get_by_index(net, dev_get_iflink(net_dev)); + parent_dev = __dev_get_by_index((struct net *)parent_net, + dev_get_iflink(net_dev)); /* if we got a NULL parent_dev there is something broken.. */ if (WARN(!parent_dev, "Cannot find parent device")) return false; - if (batadv_mutual_parents(net_dev, parent_dev)) + if (batadv_mutual_parents(net_dev, net, parent_dev, parent_net)) return false; ret = batadv_is_on_batman_iface(parent_dev); @@ -625,25 +660,6 @@ out: batadv_hardif_put(primary_if); } -/** - * batadv_hardif_remove_interface_finish - cleans up the remains of a hardif - * @work: work queue item - * - * Free the parts of the hard interface which can not be removed under - * rtnl lock (to prevent deadlock situations). - */ -static void batadv_hardif_remove_interface_finish(struct work_struct *work) -{ - struct batadv_hard_iface *hard_iface; - - hard_iface = container_of(work, struct batadv_hard_iface, - cleanup_work); - - batadv_debugfs_del_hardif(hard_iface); - batadv_sysfs_del_hardif(&hard_iface->hardif_obj); - batadv_hardif_put(hard_iface); -} - static struct batadv_hard_iface * batadv_hardif_add_interface(struct net_device *net_dev) { @@ -676,10 +692,9 @@ batadv_hardif_add_interface(struct net_device *net_dev) INIT_LIST_HEAD(&hard_iface->list); INIT_HLIST_HEAD(&hard_iface->neigh_list); - INIT_WORK(&hard_iface->cleanup_work, - batadv_hardif_remove_interface_finish); spin_lock_init(&hard_iface->neigh_list_lock); + kref_init(&hard_iface->refcount); hard_iface->num_bcasts = BATADV_NUM_BCASTS_DEFAULT; if (batadv_is_wifi_netdev(net_dev)) @@ -687,11 +702,8 @@ batadv_hardif_add_interface(struct net_device *net_dev) batadv_v_hardif_init(hard_iface); - /* extra reference for return */ - kref_init(&hard_iface->refcount); - kref_get(&hard_iface->refcount); - batadv_check_known_mac_addr(hard_iface->net_dev); + kref_get(&hard_iface->refcount); list_add_tail_rcu(&hard_iface->list, &batadv_hardif_list); return hard_iface; @@ -713,13 +725,15 @@ static void batadv_hardif_remove_interface(struct batadv_hard_iface *hard_iface) /* first deactivate interface */ if (hard_iface->if_status != BATADV_IF_NOT_IN_USE) batadv_hardif_disable_interface(hard_iface, - BATADV_IF_CLEANUP_AUTO); + BATADV_IF_CLEANUP_KEEP); if (hard_iface->if_status != BATADV_IF_NOT_IN_USE) return; hard_iface->if_status = BATADV_IF_TO_BE_REMOVED; - queue_work(batadv_event_workqueue, &hard_iface->cleanup_work); + batadv_debugfs_del_hardif(hard_iface); + batadv_sysfs_del_hardif(&hard_iface->hardif_obj); + batadv_hardif_put(hard_iface); } void batadv_hardif_remove_interfaces(void) diff --git a/net/batman-adv/icmp_socket.h b/net/batman-adv/icmp_socket.h index 618d5de06f20..e44a7da51431 100644 --- a/net/batman-adv/icmp_socket.h +++ b/net/batman-adv/icmp_socket.h @@ -26,9 +26,25 @@ struct batadv_icmp_header; #define BATADV_ICMP_SOCKET "socket" -void batadv_socket_init(void); int batadv_socket_setup(struct batadv_priv *bat_priv); + +#ifdef CONFIG_BATMAN_ADV_DEBUGFS + +void batadv_socket_init(void); void batadv_socket_receive_packet(struct batadv_icmp_header *icmph, size_t icmp_len); +#else + +static inline void batadv_socket_init(void) +{ +} + +static inline void +batadv_socket_receive_packet(struct batadv_icmp_header *icmph, size_t icmp_len) +{ +} + +#endif + #endif /* _NET_BATMAN_ADV_ICMP_SOCKET_H_ */ diff --git a/net/batman-adv/main.c b/net/batman-adv/main.c index fe4c5e29f96b..2c017ab47557 100644 --- a/net/batman-adv/main.c +++ b/net/batman-adv/main.c @@ -82,6 +82,12 @@ static void batadv_recv_handler_init(void); static int __init batadv_init(void) { + int ret; + + ret = batadv_tt_cache_init(); + if (ret < 0) + return ret; + INIT_LIST_HEAD(&batadv_hardif_list); batadv_algo_init(); @@ -93,9 +99,8 @@ static int __init batadv_init(void) batadv_tp_meter_init(); batadv_event_workqueue = create_singlethread_workqueue("bat_events"); - if (!batadv_event_workqueue) - return -ENOMEM; + goto err_create_wq; batadv_socket_init(); batadv_debugfs_init(); @@ -108,6 +113,11 @@ static int __init batadv_init(void) BATADV_SOURCE_VERSION, BATADV_COMPAT_VERSION); return 0; + +err_create_wq: + batadv_tt_cache_destroy(); + + return -ENOMEM; } static void __exit batadv_exit(void) @@ -123,6 +133,8 @@ static void __exit batadv_exit(void) batadv_event_workqueue = NULL; rcu_barrier(); + + batadv_tt_cache_destroy(); } int batadv_mesh_init(struct net_device *soft_iface) @@ -270,6 +282,7 @@ bool batadv_is_my_mac(struct batadv_priv *bat_priv, const u8 *addr) return is_my_mac; } +#ifdef CONFIG_BATMAN_ADV_DEBUGFS /** * batadv_seq_print_text_primary_if_get - called from debugfs table printing * function that requires the primary interface @@ -305,6 +318,7 @@ batadv_seq_print_text_primary_if_get(struct seq_file *seq) out: return primary_if; } +#endif /** * batadv_max_header_len - calculate maximum encapsulation overhead for a @@ -638,3 +652,4 @@ MODULE_AUTHOR(BATADV_DRIVER_AUTHOR); MODULE_DESCRIPTION(BATADV_DRIVER_DESC); MODULE_SUPPORTED_DEVICE(BATADV_DRIVER_DEVICE); MODULE_VERSION(BATADV_SOURCE_VERSION); +MODULE_ALIAS_RTNL_LINK("batadv"); diff --git a/net/batman-adv/main.h b/net/batman-adv/main.h index 06a860845434..09af21e27639 100644 --- a/net/batman-adv/main.h +++ b/net/batman-adv/main.h @@ -24,7 +24,7 @@ #define BATADV_DRIVER_DEVICE "batman-adv" #ifndef BATADV_SOURCE_VERSION -#define BATADV_SOURCE_VERSION "2016.3" +#define BATADV_SOURCE_VERSION "2016.4" #endif /* B.A.T.M.A.N. parameters */ diff --git a/net/batman-adv/multicast.c b/net/batman-adv/multicast.c index cc915073a753..13661f43386f 100644 --- a/net/batman-adv/multicast.c +++ b/net/batman-adv/multicast.c @@ -528,7 +528,7 @@ update: } return !(mcast_data.flags & - (BATADV_MCAST_WANT_ALL_IPV4 + BATADV_MCAST_WANT_ALL_IPV6)); + (BATADV_MCAST_WANT_ALL_IPV4 | BATADV_MCAST_WANT_ALL_IPV6)); } /** @@ -1134,6 +1134,7 @@ void batadv_mcast_init(struct batadv_priv *bat_priv) BATADV_TVLV_HANDLER_OGM_CIFNOTFND); } +#ifdef CONFIG_BATMAN_ADV_DEBUGFS /** * batadv_mcast_flags_print_header - print own mcast flags to debugfs table * @bat_priv: the bat priv with all the soft interface information @@ -1234,6 +1235,7 @@ int batadv_mcast_flags_seq_print_text(struct seq_file *seq, void *offset) return 0; } +#endif /** * batadv_mcast_free - free the multicast optimizations structures diff --git a/net/batman-adv/netlink.c b/net/batman-adv/netlink.c index 231f8eaf075b..64cb6acbe0a6 100644 --- a/net/batman-adv/netlink.c +++ b/net/batman-adv/netlink.c @@ -18,6 +18,8 @@ #include "netlink.h" #include "main.h" +#include <linux/atomic.h> +#include <linux/byteorder/generic.h> #include <linux/errno.h> #include <linux/fs.h> #include <linux/genetlink.h> @@ -26,24 +28,33 @@ #include <linux/netdevice.h> #include <linux/netlink.h> #include <linux/printk.h> +#include <linux/rculist.h> +#include <linux/rcupdate.h> +#include <linux/skbuff.h> #include <linux/stddef.h> #include <linux/types.h> #include <net/genetlink.h> #include <net/netlink.h> +#include <net/sock.h> #include <uapi/linux/batman_adv.h> +#include "bat_algo.h" +#include "bridge_loop_avoidance.h" +#include "gateway_client.h" #include "hard-interface.h" +#include "originator.h" +#include "packet.h" #include "soft-interface.h" #include "tp_meter.h" +#include "translation-table.h" -struct sk_buff; - -static struct genl_family batadv_netlink_family = { +struct genl_family batadv_netlink_family = { .id = GENL_ID_GENERATE, .hdrsize = 0, .name = BATADV_NL_NAME, .version = 1, .maxattr = BATADV_ATTR_MAX, + .netnsok = true, }; /* multicast groups */ @@ -51,11 +62,11 @@ enum batadv_netlink_multicast_groups { BATADV_NL_MCGRP_TPMETER, }; -static struct genl_multicast_group batadv_netlink_mcgrps[] = { +static const struct genl_multicast_group batadv_netlink_mcgrps[] = { [BATADV_NL_MCGRP_TPMETER] = { .name = BATADV_NL_MCAST_GROUP_TPMETER }, }; -static struct nla_policy batadv_netlink_policy[NUM_BATADV_ATTR] = { +static const struct nla_policy batadv_netlink_policy[NUM_BATADV_ATTR] = { [BATADV_ATTR_VERSION] = { .type = NLA_STRING }, [BATADV_ATTR_ALGO_NAME] = { .type = NLA_STRING }, [BATADV_ATTR_MESH_IFINDEX] = { .type = NLA_U32 }, @@ -69,9 +80,44 @@ static struct nla_policy batadv_netlink_policy[NUM_BATADV_ATTR] = { [BATADV_ATTR_TPMETER_TEST_TIME] = { .type = NLA_U32 }, [BATADV_ATTR_TPMETER_BYTES] = { .type = NLA_U64 }, [BATADV_ATTR_TPMETER_COOKIE] = { .type = NLA_U32 }, + [BATADV_ATTR_ACTIVE] = { .type = NLA_FLAG }, + [BATADV_ATTR_TT_ADDRESS] = { .len = ETH_ALEN }, + [BATADV_ATTR_TT_TTVN] = { .type = NLA_U8 }, + [BATADV_ATTR_TT_LAST_TTVN] = { .type = NLA_U8 }, + [BATADV_ATTR_TT_CRC32] = { .type = NLA_U32 }, + [BATADV_ATTR_TT_VID] = { .type = NLA_U16 }, + [BATADV_ATTR_TT_FLAGS] = { .type = NLA_U32 }, + [BATADV_ATTR_FLAG_BEST] = { .type = NLA_FLAG }, + [BATADV_ATTR_LAST_SEEN_MSECS] = { .type = NLA_U32 }, + [BATADV_ATTR_NEIGH_ADDRESS] = { .len = ETH_ALEN }, + [BATADV_ATTR_TQ] = { .type = NLA_U8 }, + [BATADV_ATTR_THROUGHPUT] = { .type = NLA_U32 }, + [BATADV_ATTR_BANDWIDTH_UP] = { .type = NLA_U32 }, + [BATADV_ATTR_BANDWIDTH_DOWN] = { .type = NLA_U32 }, + [BATADV_ATTR_ROUTER] = { .len = ETH_ALEN }, + [BATADV_ATTR_BLA_OWN] = { .type = NLA_FLAG }, + [BATADV_ATTR_BLA_ADDRESS] = { .len = ETH_ALEN }, + [BATADV_ATTR_BLA_VID] = { .type = NLA_U16 }, + [BATADV_ATTR_BLA_BACKBONE] = { .len = ETH_ALEN }, + [BATADV_ATTR_BLA_CRC] = { .type = NLA_U16 }, }; /** + * batadv_netlink_get_ifindex - Extract an interface index from a message + * @nlh: Message header + * @attrtype: Attribute which holds an interface index + * + * Return: interface index, or 0. + */ +int +batadv_netlink_get_ifindex(const struct nlmsghdr *nlh, int attrtype) +{ + struct nlattr *attr = nlmsg_find_attr(nlh, GENL_HDRLEN, attrtype); + + return attr ? nla_get_u32(attr) : 0; +} + +/** * batadv_netlink_mesh_info_put - fill in generic information about mesh * interface * @msg: netlink message to be sent back @@ -93,8 +139,16 @@ batadv_netlink_mesh_info_put(struct sk_buff *msg, struct net_device *soft_iface) nla_put_u32(msg, BATADV_ATTR_MESH_IFINDEX, soft_iface->ifindex) || nla_put_string(msg, BATADV_ATTR_MESH_IFNAME, soft_iface->name) || nla_put(msg, BATADV_ATTR_MESH_ADDRESS, ETH_ALEN, - soft_iface->dev_addr)) + soft_iface->dev_addr) || + nla_put_u8(msg, BATADV_ATTR_TT_TTVN, + (u8)atomic_read(&bat_priv->tt.vn))) + goto out; + +#ifdef CONFIG_BATMAN_ADV_BLA + if (nla_put_u16(msg, BATADV_ATTR_BLA_CRC, + ntohs(bat_priv->bla.claim_dest.group))) goto out; +#endif primary_if = batadv_primary_if_get_selected(bat_priv); if (primary_if && primary_if->if_status == BATADV_IF_ACTIVE) { @@ -380,6 +434,106 @@ out: return ret; } +/** + * batadv_netlink_dump_hardif_entry - Dump one hard interface into a message + * @msg: Netlink message to dump into + * @portid: Port making netlink request + * @seq: Sequence number of netlink message + * @hard_iface: Hard interface to dump + * + * Return: error code, or 0 on success + */ +static int +batadv_netlink_dump_hardif_entry(struct sk_buff *msg, u32 portid, u32 seq, + struct batadv_hard_iface *hard_iface) +{ + struct net_device *net_dev = hard_iface->net_dev; + void *hdr; + + hdr = genlmsg_put(msg, portid, seq, &batadv_netlink_family, NLM_F_MULTI, + BATADV_CMD_GET_HARDIFS); + if (!hdr) + return -EMSGSIZE; + + if (nla_put_u32(msg, BATADV_ATTR_HARD_IFINDEX, + net_dev->ifindex) || + nla_put_string(msg, BATADV_ATTR_HARD_IFNAME, + net_dev->name) || + nla_put(msg, BATADV_ATTR_HARD_ADDRESS, ETH_ALEN, + net_dev->dev_addr)) + goto nla_put_failure; + + if (hard_iface->if_status == BATADV_IF_ACTIVE) { + if (nla_put_flag(msg, BATADV_ATTR_ACTIVE)) + goto nla_put_failure; + } + + genlmsg_end(msg, hdr); + return 0; + + nla_put_failure: + genlmsg_cancel(msg, hdr); + return -EMSGSIZE; +} + +/** + * batadv_netlink_dump_hardifs - Dump all hard interface into a messages + * @msg: Netlink message to dump into + * @cb: Parameters from query + * + * Return: error code, or length of reply message on success + */ +static int +batadv_netlink_dump_hardifs(struct sk_buff *msg, struct netlink_callback *cb) +{ + struct net *net = sock_net(cb->skb->sk); + struct net_device *soft_iface; + struct batadv_hard_iface *hard_iface; + int ifindex; + int portid = NETLINK_CB(cb->skb).portid; + int seq = cb->nlh->nlmsg_seq; + int skip = cb->args[0]; + int i = 0; + + ifindex = batadv_netlink_get_ifindex(cb->nlh, + BATADV_ATTR_MESH_IFINDEX); + if (!ifindex) + return -EINVAL; + + soft_iface = dev_get_by_index(net, ifindex); + if (!soft_iface) + return -ENODEV; + + if (!batadv_softif_is_valid(soft_iface)) { + dev_put(soft_iface); + return -ENODEV; + } + + rcu_read_lock(); + + list_for_each_entry_rcu(hard_iface, &batadv_hardif_list, list) { + if (hard_iface->soft_iface != soft_iface) + continue; + + if (i++ < skip) + continue; + + if (batadv_netlink_dump_hardif_entry(msg, portid, seq, + hard_iface)) { + i--; + break; + } + } + + rcu_read_unlock(); + + dev_put(soft_iface); + + cb->args[0] = i; + + return msg->len; +} + static struct genl_ops batadv_netlink_ops[] = { { .cmd = BATADV_CMD_GET_MESH_INFO, @@ -399,6 +553,61 @@ static struct genl_ops batadv_netlink_ops[] = { .policy = batadv_netlink_policy, .doit = batadv_netlink_tp_meter_cancel, }, + { + .cmd = BATADV_CMD_GET_ROUTING_ALGOS, + .flags = GENL_ADMIN_PERM, + .policy = batadv_netlink_policy, + .dumpit = batadv_algo_dump, + }, + { + .cmd = BATADV_CMD_GET_HARDIFS, + .flags = GENL_ADMIN_PERM, + .policy = batadv_netlink_policy, + .dumpit = batadv_netlink_dump_hardifs, + }, + { + .cmd = BATADV_CMD_GET_TRANSTABLE_LOCAL, + .flags = GENL_ADMIN_PERM, + .policy = batadv_netlink_policy, + .dumpit = batadv_tt_local_dump, + }, + { + .cmd = BATADV_CMD_GET_TRANSTABLE_GLOBAL, + .flags = GENL_ADMIN_PERM, + .policy = batadv_netlink_policy, + .dumpit = batadv_tt_global_dump, + }, + { + .cmd = BATADV_CMD_GET_ORIGINATORS, + .flags = GENL_ADMIN_PERM, + .policy = batadv_netlink_policy, + .dumpit = batadv_orig_dump, + }, + { + .cmd = BATADV_CMD_GET_NEIGHBORS, + .flags = GENL_ADMIN_PERM, + .policy = batadv_netlink_policy, + .dumpit = batadv_hardif_neigh_dump, + }, + { + .cmd = BATADV_CMD_GET_GATEWAYS, + .flags = GENL_ADMIN_PERM, + .policy = batadv_netlink_policy, + .dumpit = batadv_gw_dump, + }, + { + .cmd = BATADV_CMD_GET_BLA_CLAIM, + .flags = GENL_ADMIN_PERM, + .policy = batadv_netlink_policy, + .dumpit = batadv_bla_claim_dump, + }, + { + .cmd = BATADV_CMD_GET_BLA_BACKBONE, + .flags = GENL_ADMIN_PERM, + .policy = batadv_netlink_policy, + .dumpit = batadv_bla_backbone_dump, + }, + }; /** diff --git a/net/batman-adv/netlink.h b/net/batman-adv/netlink.h index 945653ab58c6..52eb16281aba 100644 --- a/net/batman-adv/netlink.h +++ b/net/batman-adv/netlink.h @@ -21,12 +21,18 @@ #include "main.h" #include <linux/types.h> +#include <net/genetlink.h> + +struct nlmsghdr; void batadv_netlink_register(void); void batadv_netlink_unregister(void); +int batadv_netlink_get_ifindex(const struct nlmsghdr *nlh, int attrtype); int batadv_netlink_tpmeter_notify(struct batadv_priv *bat_priv, const u8 *dst, u8 result, u32 test_time, u64 total_bytes, u32 cookie); +extern struct genl_family batadv_netlink_family; + #endif /* _NET_BATMAN_ADV_NETLINK_H_ */ diff --git a/net/batman-adv/network-coding.c b/net/batman-adv/network-coding.c index 293ef4ffd4e1..e3baf697a35c 100644 --- a/net/batman-adv/network-coding.c +++ b/net/batman-adv/network-coding.c @@ -856,14 +856,12 @@ batadv_nc_get_nc_node(struct batadv_priv *bat_priv, if (!nc_node) return NULL; - kref_get(&orig_neigh_node->refcount); - /* Initialize nc_node */ INIT_LIST_HEAD(&nc_node->list); + kref_init(&nc_node->refcount); ether_addr_copy(nc_node->addr, orig_node->orig); + kref_get(&orig_neigh_node->refcount); nc_node->orig_node = orig_neigh_node; - kref_init(&nc_node->refcount); - kref_get(&nc_node->refcount); /* Select ingoing or outgoing coding node */ if (in_coding) { @@ -879,6 +877,7 @@ batadv_nc_get_nc_node(struct batadv_priv *bat_priv, /* Add nc_node to orig_node */ spin_lock_bh(lock); + kref_get(&nc_node->refcount); list_add_tail_rcu(&nc_node->list, list); spin_unlock_bh(lock); @@ -979,7 +978,6 @@ static struct batadv_nc_path *batadv_nc_get_path(struct batadv_priv *bat_priv, INIT_LIST_HEAD(&nc_path->packet_list); spin_lock_init(&nc_path->packet_list_lock); kref_init(&nc_path->refcount); - kref_get(&nc_path->refcount); nc_path->last_valid = jiffies; ether_addr_copy(nc_path->next_hop, dst); ether_addr_copy(nc_path->prev_hop, src); @@ -989,6 +987,7 @@ static struct batadv_nc_path *batadv_nc_get_path(struct batadv_priv *bat_priv, nc_path->next_hop); /* Add nc_path to hash table */ + kref_get(&nc_path->refcount); hash_added = batadv_hash_add(hash, batadv_nc_hash_compare, batadv_nc_hash_choose, &nc_path_key, &nc_path->hash_entry); @@ -1882,6 +1881,7 @@ void batadv_nc_mesh_free(struct batadv_priv *bat_priv) batadv_hash_destroy(bat_priv->nc.decoding_hash); } +#ifdef CONFIG_BATMAN_ADV_DEBUGFS /** * batadv_nc_nodes_seq_print_text - print the nc node information * @seq: seq file to print on @@ -1981,3 +1981,4 @@ int batadv_nc_init_debugfs(struct batadv_priv *bat_priv) out: return -ENOMEM; } +#endif diff --git a/net/batman-adv/originator.c b/net/batman-adv/originator.c index 3940b5d24421..5f3bfc41aeb1 100644 --- a/net/batman-adv/originator.c +++ b/net/batman-adv/originator.c @@ -28,11 +28,15 @@ #include <linux/list.h> #include <linux/lockdep.h> #include <linux/netdevice.h> +#include <linux/netlink.h> #include <linux/rculist.h> #include <linux/seq_file.h> +#include <linux/skbuff.h> #include <linux/slab.h> #include <linux/spinlock.h> #include <linux/workqueue.h> +#include <net/sock.h> +#include <uapi/linux/batman_adv.h> #include "bat_algo.h" #include "distributed-arp-table.h" @@ -42,8 +46,10 @@ #include "hash.h" #include "log.h" #include "multicast.h" +#include "netlink.h" #include "network-coding.h" #include "routing.h" +#include "soft-interface.h" #include "translation-table.h" /* hash class keys */ @@ -127,9 +133,9 @@ batadv_orig_node_vlan_new(struct batadv_orig_node *orig_node, goto out; kref_init(&vlan->refcount); - kref_get(&vlan->refcount); vlan->vid = vid; + kref_get(&vlan->refcount); hlist_add_head_rcu(&vlan->list, &orig_node->vlan_list); out: @@ -380,6 +386,7 @@ batadv_orig_ifinfo_new(struct batadv_orig_node *orig_node, orig_ifinfo->if_outgoing = if_outgoing; INIT_HLIST_NODE(&orig_ifinfo->list); kref_init(&orig_ifinfo->refcount); + kref_get(&orig_ifinfo->refcount); hlist_add_head_rcu(&orig_ifinfo->list, &orig_node->ifinfo_list); @@ -453,9 +460,9 @@ batadv_neigh_ifinfo_new(struct batadv_neigh_node *neigh, INIT_HLIST_NODE(&neigh_ifinfo->list); kref_init(&neigh_ifinfo->refcount); - kref_get(&neigh_ifinfo->refcount); neigh_ifinfo->if_outgoing = if_outgoing; + kref_get(&neigh_ifinfo->refcount); hlist_add_head_rcu(&neigh_ifinfo->list, &neigh->ifinfo_list); out: @@ -647,8 +654,8 @@ batadv_neigh_node_create(struct batadv_orig_node *orig_node, /* extra reference for return */ kref_init(&neigh_node->refcount); - kref_get(&neigh_node->refcount); + kref_get(&neigh_node->refcount); hlist_add_head_rcu(&neigh_node->list, &orig_node->neigh_list); batadv_dbg(BATADV_DBG_BATMAN, orig_node->bat_priv, @@ -686,6 +693,7 @@ batadv_neigh_node_get_or_create(struct batadv_orig_node *orig_node, return batadv_neigh_node_create(orig_node, hard_iface, neigh_addr); } +#ifdef CONFIG_BATMAN_ADV_DEBUGFS /** * batadv_hardif_neigh_seq_print_text - print the single hop neighbour list * @seq: neighbour table seq_file struct @@ -719,6 +727,84 @@ int batadv_hardif_neigh_seq_print_text(struct seq_file *seq, void *offset) bat_priv->algo_ops->neigh.print(bat_priv, seq); return 0; } +#endif + +/** + * batadv_hardif_neigh_dump - Dump to netlink the neighbor infos for a specific + * outgoing interface + * @msg: message to dump into + * @cb: parameters for the dump + * + * Return: 0 or error value + */ +int batadv_hardif_neigh_dump(struct sk_buff *msg, struct netlink_callback *cb) +{ + struct net *net = sock_net(cb->skb->sk); + struct net_device *soft_iface; + struct net_device *hard_iface = NULL; + struct batadv_hard_iface *hardif = BATADV_IF_DEFAULT; + struct batadv_priv *bat_priv; + struct batadv_hard_iface *primary_if = NULL; + int ret; + int ifindex, hard_ifindex; + + ifindex = batadv_netlink_get_ifindex(cb->nlh, BATADV_ATTR_MESH_IFINDEX); + if (!ifindex) + return -EINVAL; + + soft_iface = dev_get_by_index(net, ifindex); + if (!soft_iface || !batadv_softif_is_valid(soft_iface)) { + ret = -ENODEV; + goto out; + } + + bat_priv = netdev_priv(soft_iface); + + primary_if = batadv_primary_if_get_selected(bat_priv); + if (!primary_if || primary_if->if_status != BATADV_IF_ACTIVE) { + ret = -ENOENT; + goto out; + } + + hard_ifindex = batadv_netlink_get_ifindex(cb->nlh, + BATADV_ATTR_HARD_IFINDEX); + if (hard_ifindex) { + hard_iface = dev_get_by_index(net, hard_ifindex); + if (hard_iface) + hardif = batadv_hardif_get_by_netdev(hard_iface); + + if (!hardif) { + ret = -ENODEV; + goto out; + } + + if (hardif->soft_iface != soft_iface) { + ret = -ENOENT; + goto out; + } + } + + if (!bat_priv->algo_ops->neigh.dump) { + ret = -EOPNOTSUPP; + goto out; + } + + bat_priv->algo_ops->neigh.dump(msg, cb, bat_priv, hardif); + + ret = msg->len; + + out: + if (hardif) + batadv_hardif_put(hardif); + if (hard_iface) + dev_put(hard_iface); + if (primary_if) + batadv_hardif_put(primary_if); + if (soft_iface) + dev_put(soft_iface); + + return ret; +} /** * batadv_orig_ifinfo_release - release orig_ifinfo from lists and queue for @@ -905,7 +991,6 @@ struct batadv_orig_node *batadv_orig_node_new(struct batadv_priv *bat_priv, /* extra reference for return */ kref_init(&orig_node->refcount); - kref_get(&orig_node->refcount); orig_node->bat_priv = bat_priv; ether_addr_copy(orig_node->orig, addr); @@ -1256,6 +1341,7 @@ void batadv_purge_orig_ref(struct batadv_priv *bat_priv) _batadv_purge_orig(bat_priv); } +#ifdef CONFIG_BATMAN_ADV_DEBUGFS int batadv_orig_seq_print_text(struct seq_file *seq, void *offset) { struct net_device *net_dev = (struct net_device *)seq->private; @@ -1329,6 +1415,84 @@ out: batadv_hardif_put(hard_iface); return 0; } +#endif + +/** + * batadv_orig_dump - Dump to netlink the originator infos for a specific + * outgoing interface + * @msg: message to dump into + * @cb: parameters for the dump + * + * Return: 0 or error value + */ +int batadv_orig_dump(struct sk_buff *msg, struct netlink_callback *cb) +{ + struct net *net = sock_net(cb->skb->sk); + struct net_device *soft_iface; + struct net_device *hard_iface = NULL; + struct batadv_hard_iface *hardif = BATADV_IF_DEFAULT; + struct batadv_priv *bat_priv; + struct batadv_hard_iface *primary_if = NULL; + int ret; + int ifindex, hard_ifindex; + + ifindex = batadv_netlink_get_ifindex(cb->nlh, BATADV_ATTR_MESH_IFINDEX); + if (!ifindex) + return -EINVAL; + + soft_iface = dev_get_by_index(net, ifindex); + if (!soft_iface || !batadv_softif_is_valid(soft_iface)) { + ret = -ENODEV; + goto out; + } + + bat_priv = netdev_priv(soft_iface); + + primary_if = batadv_primary_if_get_selected(bat_priv); + if (!primary_if || primary_if->if_status != BATADV_IF_ACTIVE) { + ret = -ENOENT; + goto out; + } + + hard_ifindex = batadv_netlink_get_ifindex(cb->nlh, + BATADV_ATTR_HARD_IFINDEX); + if (hard_ifindex) { + hard_iface = dev_get_by_index(net, hard_ifindex); + if (hard_iface) + hardif = batadv_hardif_get_by_netdev(hard_iface); + + if (!hardif) { + ret = -ENODEV; + goto out; + } + + if (hardif->soft_iface != soft_iface) { + ret = -ENOENT; + goto out; + } + } + + if (!bat_priv->algo_ops->orig.dump) { + ret = -EOPNOTSUPP; + goto out; + } + + bat_priv->algo_ops->orig.dump(msg, cb, bat_priv, hardif); + + ret = msg->len; + + out: + if (hardif) + batadv_hardif_put(hardif); + if (hard_iface) + dev_put(hard_iface); + if (primary_if) + batadv_hardif_put(primary_if); + if (soft_iface) + dev_put(soft_iface); + + return ret; +} int batadv_orig_hash_add_if(struct batadv_hard_iface *hard_iface, int max_if_num) diff --git a/net/batman-adv/originator.h b/net/batman-adv/originator.h index 566306bf05dc..ebc56183f358 100644 --- a/net/batman-adv/originator.h +++ b/net/batman-adv/originator.h @@ -31,7 +31,9 @@ #include "hash.h" +struct netlink_callback; struct seq_file; +struct sk_buff; bool batadv_compare_orig(const struct hlist_node *node, const void *data2); int batadv_originator_init(struct batadv_priv *bat_priv); @@ -61,6 +63,7 @@ batadv_neigh_ifinfo_get(struct batadv_neigh_node *neigh, struct batadv_hard_iface *if_outgoing); void batadv_neigh_ifinfo_put(struct batadv_neigh_ifinfo *neigh_ifinfo); +int batadv_hardif_neigh_dump(struct sk_buff *msg, struct netlink_callback *cb); int batadv_hardif_neigh_seq_print_text(struct seq_file *seq, void *offset); struct batadv_orig_ifinfo * @@ -72,6 +75,7 @@ batadv_orig_ifinfo_new(struct batadv_orig_node *orig_node, void batadv_orig_ifinfo_put(struct batadv_orig_ifinfo *orig_ifinfo); int batadv_orig_seq_print_text(struct seq_file *seq, void *offset); +int batadv_orig_dump(struct sk_buff *msg, struct netlink_callback *cb); int batadv_orig_hardif_seq_print_text(struct seq_file *seq, void *offset); int batadv_orig_hash_add_if(struct batadv_hard_iface *hard_iface, int max_if_num); diff --git a/net/batman-adv/packet.h b/net/batman-adv/packet.h index 6b011ff64dd8..6afc0b86950e 100644 --- a/net/batman-adv/packet.h +++ b/net/batman-adv/packet.h @@ -129,42 +129,6 @@ enum batadv_tt_data_flags { }; /** - * enum batadv_tt_client_flags - TT client specific flags - * @BATADV_TT_CLIENT_DEL: the client has to be deleted from the table - * @BATADV_TT_CLIENT_ROAM: the client roamed to/from another node and the new - * update telling its new real location has not been received/sent yet - * @BATADV_TT_CLIENT_WIFI: this client is connected through a wifi interface. - * This information is used by the "AP Isolation" feature - * @BATADV_TT_CLIENT_ISOLA: this client is considered "isolated". This - * information is used by the Extended Isolation feature - * @BATADV_TT_CLIENT_NOPURGE: this client should never be removed from the table - * @BATADV_TT_CLIENT_NEW: this client has been added to the local table but has - * not been announced yet - * @BATADV_TT_CLIENT_PENDING: this client is marked for removal but it is kept - * in the table for one more originator interval for consistency purposes - * @BATADV_TT_CLIENT_TEMP: this global client has been detected to be part of - * the network but no nnode has already announced it - * - * Bits from 0 to 7 are called _remote flags_ because they are sent on the wire. - * Bits from 8 to 15 are called _local flags_ because they are used for local - * computations only. - * - * Bits from 4 to 7 - a subset of remote flags - are ensured to be in sync with - * the other nodes in the network. To achieve this goal these flags are included - * in the TT CRC computation. - */ -enum batadv_tt_client_flags { - BATADV_TT_CLIENT_DEL = BIT(0), - BATADV_TT_CLIENT_ROAM = BIT(1), - BATADV_TT_CLIENT_WIFI = BIT(4), - BATADV_TT_CLIENT_ISOLA = BIT(5), - BATADV_TT_CLIENT_NOPURGE = BIT(8), - BATADV_TT_CLIENT_NEW = BIT(9), - BATADV_TT_CLIENT_PENDING = BIT(10), - BATADV_TT_CLIENT_TEMP = BIT(11), -}; - -/** * enum batadv_vlan_flags - flags for the four MSB of any vlan ID field * @BATADV_VLAN_HAS_TAG: whether the field contains a valid vlan tag or not */ diff --git a/net/batman-adv/routing.c b/net/batman-adv/routing.c index 7602c001e92b..610f2c45edcd 100644 --- a/net/batman-adv/routing.c +++ b/net/batman-adv/routing.c @@ -74,11 +74,23 @@ static void _batadv_update_route(struct batadv_priv *bat_priv, if (!orig_ifinfo) return; - rcu_read_lock(); - curr_router = rcu_dereference(orig_ifinfo->router); - if (curr_router && !kref_get_unless_zero(&curr_router->refcount)) - curr_router = NULL; - rcu_read_unlock(); + spin_lock_bh(&orig_node->neigh_list_lock); + /* curr_router used earlier may not be the current orig_ifinfo->router + * anymore because it was dereferenced outside of the neigh_list_lock + * protected region. After the new best neighbor has replace the current + * best neighbor the reference counter needs to decrease. Consequently, + * the code needs to ensure the curr_router variable contains a pointer + * to the replaced best neighbor. + */ + curr_router = rcu_dereference_protected(orig_ifinfo->router, true); + + /* increase refcount of new best neighbor */ + if (neigh_node) + kref_get(&neigh_node->refcount); + + rcu_assign_pointer(orig_ifinfo->router, neigh_node); + spin_unlock_bh(&orig_node->neigh_list_lock); + batadv_orig_ifinfo_put(orig_ifinfo); /* route deleted */ if ((curr_router) && (!neigh_node)) { @@ -100,27 +112,6 @@ static void _batadv_update_route(struct batadv_priv *bat_priv, curr_router->addr); } - if (curr_router) - batadv_neigh_node_put(curr_router); - - spin_lock_bh(&orig_node->neigh_list_lock); - /* curr_router used earlier may not be the current orig_ifinfo->router - * anymore because it was dereferenced outside of the neigh_list_lock - * protected region. After the new best neighbor has replace the current - * best neighbor the reference counter needs to decrease. Consequently, - * the code needs to ensure the curr_router variable contains a pointer - * to the replaced best neighbor. - */ - curr_router = rcu_dereference_protected(orig_ifinfo->router, true); - - /* increase refcount of new best neighbor */ - if (neigh_node) - kref_get(&neigh_node->refcount); - - rcu_assign_pointer(orig_ifinfo->router, neigh_node); - spin_unlock_bh(&orig_node->neigh_list_lock); - batadv_orig_ifinfo_put(orig_ifinfo); - /* decrease refcount of previous best neighbor */ if (curr_router) batadv_neigh_node_put(curr_router); diff --git a/net/batman-adv/send.c b/net/batman-adv/send.c index 6191159484df..8d4e1f578574 100644 --- a/net/batman-adv/send.c +++ b/net/batman-adv/send.c @@ -315,8 +315,7 @@ out: * * Wrap the given skb into a batman-adv unicast or unicast-4addr header * depending on whether BATADV_UNICAST or BATADV_UNICAST_4ADDR was supplied - * as packet_type. Then send this frame to the given orig_node and release a - * reference to this orig_node. + * as packet_type. Then send this frame to the given orig_node. * * Return: NET_XMIT_DROP in case of error or NET_XMIT_SUCCESS otherwise. */ @@ -370,8 +369,6 @@ int batadv_send_skb_unicast(struct batadv_priv *bat_priv, ret = NET_XMIT_SUCCESS; out: - if (orig_node) - batadv_orig_node_put(orig_node); if (ret == NET_XMIT_DROP) kfree_skb(skb); return ret; @@ -403,6 +400,7 @@ int batadv_send_skb_via_tt_generic(struct batadv_priv *bat_priv, struct ethhdr *ethhdr = (struct ethhdr *)skb->data; struct batadv_orig_node *orig_node; u8 *src, *dst; + int ret; src = ethhdr->h_source; dst = ethhdr->h_dest; @@ -414,8 +412,13 @@ int batadv_send_skb_via_tt_generic(struct batadv_priv *bat_priv, } orig_node = batadv_transtable_search(bat_priv, src, dst, vid); - return batadv_send_skb_unicast(bat_priv, skb, packet_type, - packet_subtype, orig_node, vid); + ret = batadv_send_skb_unicast(bat_priv, skb, packet_type, + packet_subtype, orig_node, vid); + + if (orig_node) + batadv_orig_node_put(orig_node); + + return ret; } /** @@ -433,12 +436,25 @@ int batadv_send_skb_via_gw(struct batadv_priv *bat_priv, struct sk_buff *skb, unsigned short vid) { struct batadv_orig_node *orig_node; + int ret; orig_node = batadv_gw_get_selected_orig(bat_priv); - return batadv_send_skb_unicast(bat_priv, skb, BATADV_UNICAST_4ADDR, - BATADV_P_DATA, orig_node, vid); + ret = batadv_send_skb_unicast(bat_priv, skb, BATADV_UNICAST_4ADDR, + BATADV_P_DATA, orig_node, vid); + + if (orig_node) + batadv_orig_node_put(orig_node); + + return ret; } +/** + * batadv_forw_packet_free - free a forwarding packet + * @forw_packet: The packet to free + * + * This frees a forwarding packet and releases any resources it might + * have claimed. + */ void batadv_forw_packet_free(struct batadv_forw_packet *forw_packet) { kfree_skb(forw_packet->skb); @@ -446,9 +462,73 @@ void batadv_forw_packet_free(struct batadv_forw_packet *forw_packet) batadv_hardif_put(forw_packet->if_incoming); if (forw_packet->if_outgoing) batadv_hardif_put(forw_packet->if_outgoing); + if (forw_packet->queue_left) + atomic_inc(forw_packet->queue_left); kfree(forw_packet); } +/** + * batadv_forw_packet_alloc - allocate a forwarding packet + * @if_incoming: The (optional) if_incoming to be grabbed + * @if_outgoing: The (optional) if_outgoing to be grabbed + * @queue_left: The (optional) queue counter to decrease + * @bat_priv: The bat_priv for the mesh of this forw_packet + * + * Allocates a forwarding packet and tries to get a reference to the + * (optional) if_incoming, if_outgoing and queue_left. If queue_left + * is NULL then bat_priv is optional, too. + * + * Return: An allocated forwarding packet on success, NULL otherwise. + */ +struct batadv_forw_packet * +batadv_forw_packet_alloc(struct batadv_hard_iface *if_incoming, + struct batadv_hard_iface *if_outgoing, + atomic_t *queue_left, + struct batadv_priv *bat_priv) +{ + struct batadv_forw_packet *forw_packet; + const char *qname; + + if (queue_left && !batadv_atomic_dec_not_zero(queue_left)) { + qname = "unknown"; + + if (queue_left == &bat_priv->bcast_queue_left) + qname = "bcast"; + + if (queue_left == &bat_priv->batman_queue_left) + qname = "batman"; + + batadv_dbg(BATADV_DBG_BATMAN, bat_priv, + "%s queue is full\n", qname); + + return NULL; + } + + forw_packet = kmalloc(sizeof(*forw_packet), GFP_ATOMIC); + if (!forw_packet) + goto err; + + if (if_incoming) + kref_get(&if_incoming->refcount); + + if (if_outgoing) + kref_get(&if_outgoing->refcount); + + forw_packet->skb = NULL; + forw_packet->queue_left = queue_left; + forw_packet->if_incoming = if_incoming; + forw_packet->if_outgoing = if_outgoing; + forw_packet->num_packets = 0; + + return forw_packet; + +err: + if (queue_left) + atomic_inc(queue_left); + + return NULL; +} + static void _batadv_add_bcast_packet_to_list(struct batadv_priv *bat_priv, struct batadv_forw_packet *forw_packet, @@ -487,24 +567,20 @@ int batadv_add_bcast_packet_to_list(struct batadv_priv *bat_priv, struct batadv_bcast_packet *bcast_packet; struct sk_buff *newskb; - if (!batadv_atomic_dec_not_zero(&bat_priv->bcast_queue_left)) { - batadv_dbg(BATADV_DBG_BATMAN, bat_priv, - "bcast packet queue full\n"); - goto out; - } - primary_if = batadv_primary_if_get_selected(bat_priv); if (!primary_if) - goto out_and_inc; - - forw_packet = kmalloc(sizeof(*forw_packet), GFP_ATOMIC); + goto err; + forw_packet = batadv_forw_packet_alloc(primary_if, NULL, + &bat_priv->bcast_queue_left, + bat_priv); + batadv_hardif_put(primary_if); if (!forw_packet) - goto out_and_inc; + goto err; newskb = skb_copy(skb, GFP_ATOMIC); if (!newskb) - goto packet_free; + goto err_packet_free; /* as we have a copy now, it is safe to decrease the TTL */ bcast_packet = (struct batadv_bcast_packet *)newskb->data; @@ -513,11 +589,6 @@ int batadv_add_bcast_packet_to_list(struct batadv_priv *bat_priv, skb_reset_mac_header(newskb); forw_packet->skb = newskb; - forw_packet->if_incoming = primary_if; - forw_packet->if_outgoing = NULL; - - /* how often did we send the bcast packet ? */ - forw_packet->num_packets = 0; INIT_DELAYED_WORK(&forw_packet->delayed_work, batadv_send_outstanding_bcast_packet); @@ -525,13 +596,9 @@ int batadv_add_bcast_packet_to_list(struct batadv_priv *bat_priv, _batadv_add_bcast_packet_to_list(bat_priv, forw_packet, delay); return NETDEV_TX_OK; -packet_free: - kfree(forw_packet); -out_and_inc: - atomic_inc(&bat_priv->bcast_queue_left); -out: - if (primary_if) - batadv_hardif_put(primary_if); +err_packet_free: + batadv_forw_packet_free(forw_packet); +err: return NETDEV_TX_BUSY; } @@ -592,7 +659,6 @@ static void batadv_send_outstanding_bcast_packet(struct work_struct *work) out: batadv_forw_packet_free(forw_packet); - atomic_inc(&bat_priv->bcast_queue_left); } void @@ -633,9 +699,6 @@ batadv_purge_outstanding_packets(struct batadv_priv *bat_priv, if (pending) { hlist_del(&forw_packet->list); - if (!forw_packet->own) - atomic_inc(&bat_priv->bcast_queue_left); - batadv_forw_packet_free(forw_packet); } } @@ -663,9 +726,6 @@ batadv_purge_outstanding_packets(struct batadv_priv *bat_priv, if (pending) { hlist_del(&forw_packet->list); - if (!forw_packet->own) - atomic_inc(&bat_priv->batman_queue_left); - batadv_forw_packet_free(forw_packet); } } diff --git a/net/batman-adv/send.h b/net/batman-adv/send.h index 7cecb7563b45..999f78683d9e 100644 --- a/net/batman-adv/send.h +++ b/net/batman-adv/send.h @@ -28,6 +28,12 @@ struct sk_buff; void batadv_forw_packet_free(struct batadv_forw_packet *forw_packet); +struct batadv_forw_packet * +batadv_forw_packet_alloc(struct batadv_hard_iface *if_incoming, + struct batadv_hard_iface *if_outgoing, + atomic_t *queue_left, + struct batadv_priv *bat_priv); + int batadv_send_skb_to_orig(struct sk_buff *skb, struct batadv_orig_node *orig_node, struct batadv_hard_iface *recv_if); diff --git a/net/batman-adv/soft-interface.c b/net/batman-adv/soft-interface.c index 7527c0652dd5..49e16b6e0ba3 100644 --- a/net/batman-adv/soft-interface.c +++ b/net/batman-adv/soft-interface.c @@ -39,6 +39,7 @@ #include <linux/random.h> #include <linux/rculist.h> #include <linux/rcupdate.h> +#include <linux/rtnetlink.h> #include <linux/skbuff.h> #include <linux/slab.h> #include <linux/socket.h> @@ -46,7 +47,6 @@ #include <linux/stddef.h> #include <linux/string.h> #include <linux/types.h> -#include <linux/workqueue.h> #include "bat_algo.h" #include "bridge_loop_avoidance.h" @@ -57,6 +57,7 @@ #include "hard-interface.h" #include "multicast.h" #include "network-coding.h" +#include "originator.h" #include "packet.h" #include "send.h" #include "sysfs.h" @@ -377,6 +378,8 @@ dropped: dropped_freed: batadv_inc_counter(bat_priv, BATADV_CNT_TX_DROPPED); end: + if (mcast_single_orig) + batadv_orig_node_put(mcast_single_orig); if (primary_if) batadv_hardif_put(primary_if); return NETDEV_TX_OK; @@ -591,6 +594,7 @@ int batadv_softif_create_vlan(struct batadv_priv *bat_priv, unsigned short vid) } spin_lock_bh(&bat_priv->softif_vlan_list_lock); + kref_get(&vlan->refcount); hlist_add_head_rcu(&vlan->list, &bat_priv->softif_vlan_list); spin_unlock_bh(&bat_priv->softif_vlan_list_lock); @@ -601,6 +605,9 @@ int batadv_softif_create_vlan(struct batadv_priv *bat_priv, unsigned short vid) bat_priv->soft_iface->dev_addr, vid, BATADV_NULL_IFINDEX, BATADV_NO_MARK); + /* don't return reference to new softif_vlan */ + batadv_softif_vlan_put(vlan); + return 0; } @@ -747,34 +754,6 @@ static void batadv_set_lockdep_class(struct net_device *dev) } /** - * batadv_softif_destroy_finish - cleans up the remains of a softif - * @work: work queue item - * - * Free the parts of the soft interface which can not be removed under - * rtnl lock (to prevent deadlock situations). - */ -static void batadv_softif_destroy_finish(struct work_struct *work) -{ - struct batadv_softif_vlan *vlan; - struct batadv_priv *bat_priv; - struct net_device *soft_iface; - - bat_priv = container_of(work, struct batadv_priv, - cleanup_work); - soft_iface = bat_priv->soft_iface; - - /* destroy the "untagged" VLAN */ - vlan = batadv_softif_vlan_get(bat_priv, BATADV_NO_FLAGS); - if (vlan) { - batadv_softif_destroy_vlan(bat_priv, vlan); - batadv_softif_vlan_put(vlan); - } - - batadv_sysfs_del_meshif(soft_iface); - unregister_netdev(soft_iface); -} - -/** * batadv_softif_init_late - late stage initialization of soft interface * @dev: registered network device to modify * @@ -791,7 +770,6 @@ static int batadv_softif_init_late(struct net_device *dev) bat_priv = netdev_priv(dev); bat_priv->soft_iface = dev; - INIT_WORK(&bat_priv->cleanup_work, batadv_softif_destroy_finish); /* batadv_interface_stats() needs to be available as soon as * register_netdevice() has been called @@ -1028,8 +1006,19 @@ struct net_device *batadv_softif_create(struct net *net, const char *name) void batadv_softif_destroy_sysfs(struct net_device *soft_iface) { struct batadv_priv *bat_priv = netdev_priv(soft_iface); + struct batadv_softif_vlan *vlan; - queue_work(batadv_event_workqueue, &bat_priv->cleanup_work); + ASSERT_RTNL(); + + /* destroy the "untagged" VLAN */ + vlan = batadv_softif_vlan_get(bat_priv, BATADV_NO_FLAGS); + if (vlan) { + batadv_softif_destroy_vlan(bat_priv, vlan); + batadv_softif_vlan_put(vlan); + } + + batadv_sysfs_del_meshif(soft_iface); + unregister_netdevice(soft_iface); } /** diff --git a/net/batman-adv/sysfs.c b/net/batman-adv/sysfs.c index fe9ca94ddee2..02d96f224c60 100644 --- a/net/batman-adv/sysfs.c +++ b/net/batman-adv/sysfs.c @@ -37,6 +37,7 @@ #include <linux/stddef.h> #include <linux/string.h> #include <linux/stringify.h> +#include <linux/workqueue.h> #include "bridge_loop_avoidance.h" #include "distributed-arp-table.h" @@ -428,6 +429,13 @@ static ssize_t batadv_show_gw_mode(struct kobject *kobj, struct attribute *attr, struct batadv_priv *bat_priv = batadv_kobj_to_batpriv(kobj); int bytes_written; + /* GW mode is not available if the routing algorithm in use does not + * implement the GW API + */ + if (!bat_priv->algo_ops->gw.get_best_gw_node || + !bat_priv->algo_ops->gw.is_eligible) + return -ENOENT; + switch (atomic_read(&bat_priv->gw.mode)) { case BATADV_GW_MODE_CLIENT: bytes_written = sprintf(buff, "%s\n", @@ -455,6 +463,13 @@ static ssize_t batadv_store_gw_mode(struct kobject *kobj, char *curr_gw_mode_str; int gw_mode_tmp = -1; + /* toggling GW mode is allowed only if the routing algorithm in use + * provides the GW API + */ + if (!bat_priv->algo_ops->gw.get_best_gw_node || + !bat_priv->algo_ops->gw.is_eligible) + return -EINVAL; + if (buff[count - 1] == '\n') buff[count - 1] = '\0'; @@ -514,6 +529,50 @@ static ssize_t batadv_store_gw_mode(struct kobject *kobj, return count; } +static ssize_t batadv_show_gw_sel_class(struct kobject *kobj, + struct attribute *attr, char *buff) +{ + struct batadv_priv *bat_priv = batadv_kobj_to_batpriv(kobj); + + /* GW selection class is not available if the routing algorithm in use + * does not implement the GW API + */ + if (!bat_priv->algo_ops->gw.get_best_gw_node || + !bat_priv->algo_ops->gw.is_eligible) + return -ENOENT; + + if (bat_priv->algo_ops->gw.show_sel_class) + return bat_priv->algo_ops->gw.show_sel_class(bat_priv, buff); + + return sprintf(buff, "%i\n", atomic_read(&bat_priv->gw.sel_class)); +} + +static ssize_t batadv_store_gw_sel_class(struct kobject *kobj, + struct attribute *attr, char *buff, + size_t count) +{ + struct batadv_priv *bat_priv = batadv_kobj_to_batpriv(kobj); + + /* setting the GW selection class is allowed only if the routing + * algorithm in use implements the GW API + */ + if (!bat_priv->algo_ops->gw.get_best_gw_node || + !bat_priv->algo_ops->gw.is_eligible) + return -EINVAL; + + if (buff[count - 1] == '\n') + buff[count - 1] = '\0'; + + if (bat_priv->algo_ops->gw.store_sel_class) + return bat_priv->algo_ops->gw.store_sel_class(bat_priv, buff, + count); + + return __batadv_store_uint_attr(buff, count, 1, BATADV_TQ_MAX_VALUE, + batadv_post_gw_reselect, attr, + &bat_priv->gw.sel_class, + bat_priv->soft_iface); +} + static ssize_t batadv_show_gw_bwidth(struct kobject *kobj, struct attribute *attr, char *buff) { @@ -625,8 +684,8 @@ BATADV_ATTR_SIF_UINT(orig_interval, orig_interval, S_IRUGO | S_IWUSR, 2 * BATADV_JITTER, INT_MAX, NULL); BATADV_ATTR_SIF_UINT(hop_penalty, hop_penalty, S_IRUGO | S_IWUSR, 0, BATADV_TQ_MAX_VALUE, NULL); -BATADV_ATTR_SIF_UINT(gw_sel_class, gw.sel_class, S_IRUGO | S_IWUSR, 1, - BATADV_TQ_MAX_VALUE, batadv_post_gw_reselect); +static BATADV_ATTR(gw_sel_class, S_IRUGO | S_IWUSR, batadv_show_gw_sel_class, + batadv_store_gw_sel_class); static BATADV_ATTR(gw_bandwidth, S_IRUGO | S_IWUSR, batadv_show_gw_bwidth, batadv_store_gw_bwidth); #ifdef CONFIG_BATMAN_ADV_MCAST @@ -712,6 +771,8 @@ rem_attr: for (bat_attr = batadv_mesh_attrs; *bat_attr; ++bat_attr) sysfs_remove_file(bat_priv->mesh_obj, &((*bat_attr)->attr)); + kobject_uevent(bat_priv->mesh_obj, KOBJ_REMOVE); + kobject_del(bat_priv->mesh_obj); kobject_put(bat_priv->mesh_obj); bat_priv->mesh_obj = NULL; out: @@ -726,6 +787,8 @@ void batadv_sysfs_del_meshif(struct net_device *dev) for (bat_attr = batadv_mesh_attrs; *bat_attr; ++bat_attr) sysfs_remove_file(bat_priv->mesh_obj, &((*bat_attr)->attr)); + kobject_uevent(bat_priv->mesh_obj, KOBJ_REMOVE); + kobject_del(bat_priv->mesh_obj); kobject_put(bat_priv->mesh_obj); bat_priv->mesh_obj = NULL; } @@ -781,6 +844,10 @@ rem_attr: for (bat_attr = batadv_vlan_attrs; *bat_attr; ++bat_attr) sysfs_remove_file(vlan->kobj, &((*bat_attr)->attr)); + if (vlan->kobj != bat_priv->mesh_obj) { + kobject_uevent(vlan->kobj, KOBJ_REMOVE); + kobject_del(vlan->kobj); + } kobject_put(vlan->kobj); vlan->kobj = NULL; out: @@ -800,6 +867,10 @@ void batadv_sysfs_del_vlan(struct batadv_priv *bat_priv, for (bat_attr = batadv_vlan_attrs; *bat_attr; ++bat_attr) sysfs_remove_file(vlan->kobj, &((*bat_attr)->attr)); + if (vlan->kobj != bat_priv->mesh_obj) { + kobject_uevent(vlan->kobj, KOBJ_REMOVE); + kobject_del(vlan->kobj); + } kobject_put(vlan->kobj); vlan->kobj = NULL; } @@ -828,31 +899,31 @@ static ssize_t batadv_show_mesh_iface(struct kobject *kobj, return length; } -static ssize_t batadv_store_mesh_iface(struct kobject *kobj, - struct attribute *attr, char *buff, - size_t count) +/** + * batadv_store_mesh_iface_finish - store new hardif mesh_iface state + * @net_dev: netdevice to add/remove to/from batman-adv soft-interface + * @ifname: name of soft-interface to modify + * + * Changes the parts of the hard+soft interface which can not be modified under + * sysfs lock (to prevent deadlock situations). + * + * Return: 0 on success, 0 < on failure + */ +static int batadv_store_mesh_iface_finish(struct net_device *net_dev, + char ifname[IFNAMSIZ]) { - struct net_device *net_dev = batadv_kobj_to_netdev(kobj); struct net *net = dev_net(net_dev); struct batadv_hard_iface *hard_iface; - int status_tmp = -1; - int ret = count; + int status_tmp; + int ret = 0; + + ASSERT_RTNL(); hard_iface = batadv_hardif_get_by_netdev(net_dev); if (!hard_iface) - return count; - - if (buff[count - 1] == '\n') - buff[count - 1] = '\0'; - - if (strlen(buff) >= IFNAMSIZ) { - pr_err("Invalid parameter for 'mesh_iface' setting received: interface name too long '%s'\n", - buff); - batadv_hardif_put(hard_iface); - return -EINVAL; - } + return 0; - if (strncmp(buff, "none", 4) == 0) + if (strncmp(ifname, "none", 4) == 0) status_tmp = BATADV_IF_NOT_IN_USE; else status_tmp = BATADV_IF_I_WANT_YOU; @@ -861,15 +932,13 @@ static ssize_t batadv_store_mesh_iface(struct kobject *kobj, goto out; if ((hard_iface->soft_iface) && - (strncmp(hard_iface->soft_iface->name, buff, IFNAMSIZ) == 0)) + (strncmp(hard_iface->soft_iface->name, ifname, IFNAMSIZ) == 0)) goto out; - rtnl_lock(); - if (status_tmp == BATADV_IF_NOT_IN_USE) { batadv_hardif_disable_interface(hard_iface, BATADV_IF_CLEANUP_AUTO); - goto unlock; + goto out; } /* if the interface already is in use */ @@ -877,15 +946,71 @@ static ssize_t batadv_store_mesh_iface(struct kobject *kobj, batadv_hardif_disable_interface(hard_iface, BATADV_IF_CLEANUP_AUTO); - ret = batadv_hardif_enable_interface(hard_iface, net, buff); - -unlock: - rtnl_unlock(); + ret = batadv_hardif_enable_interface(hard_iface, net, ifname); out: batadv_hardif_put(hard_iface); return ret; } +/** + * batadv_store_mesh_iface_work - store new hardif mesh_iface state + * @work: work queue item + * + * Changes the parts of the hard+soft interface which can not be modified under + * sysfs lock (to prevent deadlock situations). + */ +static void batadv_store_mesh_iface_work(struct work_struct *work) +{ + struct batadv_store_mesh_work *store_work; + int ret; + + store_work = container_of(work, struct batadv_store_mesh_work, work); + + rtnl_lock(); + ret = batadv_store_mesh_iface_finish(store_work->net_dev, + store_work->soft_iface_name); + rtnl_unlock(); + + if (ret < 0) + pr_err("Failed to store new mesh_iface state %s for %s: %d\n", + store_work->soft_iface_name, store_work->net_dev->name, + ret); + + dev_put(store_work->net_dev); + kfree(store_work); +} + +static ssize_t batadv_store_mesh_iface(struct kobject *kobj, + struct attribute *attr, char *buff, + size_t count) +{ + struct net_device *net_dev = batadv_kobj_to_netdev(kobj); + struct batadv_store_mesh_work *store_work; + + if (buff[count - 1] == '\n') + buff[count - 1] = '\0'; + + if (strlen(buff) >= IFNAMSIZ) { + pr_err("Invalid parameter for 'mesh_iface' setting received: interface name too long '%s'\n", + buff); + return -EINVAL; + } + + store_work = kmalloc(sizeof(*store_work), GFP_KERNEL); + if (!store_work) + return -ENOMEM; + + dev_hold(net_dev); + INIT_WORK(&store_work->work, batadv_store_mesh_iface_work); + store_work->net_dev = net_dev; + strlcpy(store_work->soft_iface_name, buff, + sizeof(store_work->soft_iface_name)); + + queue_work(batadv_event_workqueue, &store_work->work); + + return count; +} + static ssize_t batadv_show_iface_status(struct kobject *kobj, struct attribute *attr, char *buff) { @@ -1048,6 +1173,8 @@ out: void batadv_sysfs_del_hardif(struct kobject **hardif_obj) { + kobject_uevent(*hardif_obj, KOBJ_REMOVE); + kobject_del(*hardif_obj); kobject_put(*hardif_obj); *hardif_obj = NULL; } diff --git a/net/batman-adv/translation-table.c b/net/batman-adv/translation-table.c index 7e6df7a4964a..7f663092f6de 100644 --- a/net/batman-adv/translation-table.c +++ b/net/batman-adv/translation-table.c @@ -22,12 +22,14 @@ #include <linux/bitops.h> #include <linux/bug.h> #include <linux/byteorder/generic.h> +#include <linux/cache.h> #include <linux/compiler.h> #include <linux/crc32c.h> #include <linux/errno.h> #include <linux/etherdevice.h> #include <linux/fs.h> #include <linux/if_ether.h> +#include <linux/init.h> #include <linux/jhash.h> #include <linux/jiffies.h> #include <linux/kernel.h> @@ -35,25 +37,39 @@ #include <linux/list.h> #include <linux/lockdep.h> #include <linux/netdevice.h> +#include <linux/netlink.h> #include <linux/rculist.h> #include <linux/rcupdate.h> #include <linux/seq_file.h> +#include <linux/skbuff.h> #include <linux/slab.h> #include <linux/spinlock.h> #include <linux/stddef.h> #include <linux/string.h> #include <linux/workqueue.h> +#include <net/genetlink.h> +#include <net/netlink.h> +#include <net/sock.h> +#include <uapi/linux/batman_adv.h> #include "bridge_loop_avoidance.h" #include "hard-interface.h" #include "hash.h" #include "log.h" #include "multicast.h" +#include "netlink.h" #include "originator.h" #include "packet.h" #include "soft-interface.h" #include "tvlv.h" +static struct kmem_cache *batadv_tl_cache __read_mostly; +static struct kmem_cache *batadv_tg_cache __read_mostly; +static struct kmem_cache *batadv_tt_orig_cache __read_mostly; +static struct kmem_cache *batadv_tt_change_cache __read_mostly; +static struct kmem_cache *batadv_tt_req_cache __read_mostly; +static struct kmem_cache *batadv_tt_roam_cache __read_mostly; + /* hash class keys */ static struct lock_class_key batadv_tt_local_hash_lock_class_key; static struct lock_class_key batadv_tt_global_hash_lock_class_key; @@ -205,6 +221,20 @@ batadv_tt_global_hash_find(struct batadv_priv *bat_priv, const u8 *addr, } /** + * batadv_tt_local_entry_free_rcu - free the tt_local_entry + * @rcu: rcu pointer of the tt_local_entry + */ +static void batadv_tt_local_entry_free_rcu(struct rcu_head *rcu) +{ + struct batadv_tt_local_entry *tt_local_entry; + + tt_local_entry = container_of(rcu, struct batadv_tt_local_entry, + common.rcu); + + kmem_cache_free(batadv_tl_cache, tt_local_entry); +} + +/** * batadv_tt_local_entry_release - release tt_local_entry from lists and queue * for free after rcu grace period * @ref: kref pointer of the nc_node @@ -218,7 +248,7 @@ static void batadv_tt_local_entry_release(struct kref *ref) batadv_softif_vlan_put(tt_local_entry->vlan); - kfree_rcu(tt_local_entry, common.rcu); + call_rcu(&tt_local_entry->common.rcu, batadv_tt_local_entry_free_rcu); } /** @@ -234,6 +264,20 @@ batadv_tt_local_entry_put(struct batadv_tt_local_entry *tt_local_entry) } /** + * batadv_tt_global_entry_free_rcu - free the tt_global_entry + * @rcu: rcu pointer of the tt_global_entry + */ +static void batadv_tt_global_entry_free_rcu(struct rcu_head *rcu) +{ + struct batadv_tt_global_entry *tt_global_entry; + + tt_global_entry = container_of(rcu, struct batadv_tt_global_entry, + common.rcu); + + kmem_cache_free(batadv_tg_cache, tt_global_entry); +} + +/** * batadv_tt_global_entry_release - release tt_global_entry from lists and queue * for free after rcu grace period * @ref: kref pointer of the nc_node @@ -246,7 +290,8 @@ static void batadv_tt_global_entry_release(struct kref *ref) common.refcount); batadv_tt_global_del_orig_list(tt_global_entry); - kfree_rcu(tt_global_entry, common.rcu); + + call_rcu(&tt_global_entry->common.rcu, batadv_tt_global_entry_free_rcu); } /** @@ -384,6 +429,19 @@ static void batadv_tt_global_size_dec(struct batadv_orig_node *orig_node, } /** + * batadv_tt_orig_list_entry_free_rcu - free the orig_entry + * @rcu: rcu pointer of the orig_entry + */ +static void batadv_tt_orig_list_entry_free_rcu(struct rcu_head *rcu) +{ + struct batadv_tt_orig_list_entry *orig_entry; + + orig_entry = container_of(rcu, struct batadv_tt_orig_list_entry, rcu); + + kmem_cache_free(batadv_tt_orig_cache, orig_entry); +} + +/** * batadv_tt_orig_list_entry_release - release tt orig entry from lists and * queue for free after rcu grace period * @ref: kref pointer of the tt orig entry @@ -396,7 +454,7 @@ static void batadv_tt_orig_list_entry_release(struct kref *ref) refcount); batadv_orig_node_put(orig_entry->orig_node); - kfree_rcu(orig_entry, rcu); + call_rcu(&orig_entry->rcu, batadv_tt_orig_list_entry_free_rcu); } /** @@ -426,7 +484,7 @@ static void batadv_tt_local_event(struct batadv_priv *bat_priv, bool event_removed = false; bool del_op_requested, del_op_entry; - tt_change_node = kmalloc(sizeof(*tt_change_node), GFP_ATOMIC); + tt_change_node = kmem_cache_alloc(batadv_tt_change_cache, GFP_ATOMIC); if (!tt_change_node) return; @@ -467,8 +525,8 @@ static void batadv_tt_local_event(struct batadv_priv *bat_priv, continue; del: list_del(&entry->list); - kfree(entry); - kfree(tt_change_node); + kmem_cache_free(batadv_tt_change_cache, entry); + kmem_cache_free(batadv_tt_change_cache, tt_change_node); event_removed = true; goto unlock; } @@ -646,7 +704,7 @@ bool batadv_tt_local_add(struct net_device *soft_iface, const u8 *addr, goto out; } - tt_local = kmalloc(sizeof(*tt_local), GFP_ATOMIC); + tt_local = kmem_cache_alloc(batadv_tl_cache, GFP_ATOMIC); if (!tt_local) goto out; @@ -656,7 +714,7 @@ bool batadv_tt_local_add(struct net_device *soft_iface, const u8 *addr, net_ratelimited_function(batadv_info, soft_iface, "adding TT local entry %pM to non-existent VLAN %d\n", addr, BATADV_PRINT_VID(vid)); - kfree(tt_local); + kmem_cache_free(batadv_tl_cache, tt_local); tt_local = NULL; goto out; } @@ -676,7 +734,6 @@ bool batadv_tt_local_add(struct net_device *soft_iface, const u8 *addr, if (batadv_is_wifi_netdev(in_dev)) tt_local->common.flags |= BATADV_TT_CLIENT_WIFI; kref_init(&tt_local->common.refcount); - kref_get(&tt_local->common.refcount); tt_local->last_seen = jiffies; tt_local->common.added_at = tt_local->last_seen; tt_local->vlan = vlan; @@ -688,6 +745,7 @@ bool batadv_tt_local_add(struct net_device *soft_iface, const u8 *addr, is_multicast_ether_addr(addr)) tt_local->common.flags |= BATADV_TT_CLIENT_NOPURGE; + kref_get(&tt_local->common.refcount); hash_added = batadv_hash_add(bat_priv->tt.local_hash, batadv_compare_tt, batadv_choose_tt, &tt_local->common, &tt_local->common.hash_entry); @@ -959,7 +1017,7 @@ static void batadv_tt_tvlv_container_update(struct batadv_priv *bat_priv) tt_diff_entries_count++; } list_del(&entry->list); - kfree(entry); + kmem_cache_free(batadv_tt_change_cache, entry); } spin_unlock_bh(&bat_priv->tt.changes_list_lock); @@ -989,6 +1047,7 @@ container_register: kfree(tt_data); } +#ifdef CONFIG_BATMAN_ADV_DEBUGFS int batadv_tt_local_seq_print_text(struct seq_file *seq, void *offset) { struct net_device *net_dev = (struct net_device *)seq->private; @@ -1056,6 +1115,165 @@ out: batadv_hardif_put(primary_if); return 0; } +#endif + +/** + * batadv_tt_local_dump_entry - Dump one TT local entry into a message + * @msg :Netlink message to dump into + * @portid: Port making netlink request + * @seq: Sequence number of netlink message + * @bat_priv: The bat priv with all the soft interface information + * @common: tt local & tt global common data + * + * Return: Error code, or 0 on success + */ +static int +batadv_tt_local_dump_entry(struct sk_buff *msg, u32 portid, u32 seq, + struct batadv_priv *bat_priv, + struct batadv_tt_common_entry *common) +{ + void *hdr; + struct batadv_softif_vlan *vlan; + struct batadv_tt_local_entry *local; + unsigned int last_seen_msecs; + u32 crc; + + local = container_of(common, struct batadv_tt_local_entry, common); + last_seen_msecs = jiffies_to_msecs(jiffies - local->last_seen); + + vlan = batadv_softif_vlan_get(bat_priv, common->vid); + if (!vlan) + return 0; + + crc = vlan->tt.crc; + + batadv_softif_vlan_put(vlan); + + hdr = genlmsg_put(msg, portid, seq, &batadv_netlink_family, + NLM_F_MULTI, + BATADV_CMD_GET_TRANSTABLE_LOCAL); + if (!hdr) + return -ENOBUFS; + + if (nla_put(msg, BATADV_ATTR_TT_ADDRESS, ETH_ALEN, common->addr) || + nla_put_u32(msg, BATADV_ATTR_TT_CRC32, crc) || + nla_put_u16(msg, BATADV_ATTR_TT_VID, common->vid) || + nla_put_u32(msg, BATADV_ATTR_TT_FLAGS, common->flags)) + goto nla_put_failure; + + if (!(common->flags & BATADV_TT_CLIENT_NOPURGE) && + nla_put_u32(msg, BATADV_ATTR_LAST_SEEN_MSECS, last_seen_msecs)) + goto nla_put_failure; + + genlmsg_end(msg, hdr); + return 0; + + nla_put_failure: + genlmsg_cancel(msg, hdr); + return -EMSGSIZE; +} + +/** + * batadv_tt_local_dump_bucket - Dump one TT local bucket into a message + * @msg: Netlink message to dump into + * @portid: Port making netlink request + * @seq: Sequence number of netlink message + * @bat_priv: The bat priv with all the soft interface information + * @head: Pointer to the list containing the local tt entries + * @idx_s: Number of entries to skip + * + * Return: Error code, or 0 on success + */ +static int +batadv_tt_local_dump_bucket(struct sk_buff *msg, u32 portid, u32 seq, + struct batadv_priv *bat_priv, + struct hlist_head *head, int *idx_s) +{ + struct batadv_tt_common_entry *common; + int idx = 0; + + rcu_read_lock(); + hlist_for_each_entry_rcu(common, head, hash_entry) { + if (idx++ < *idx_s) + continue; + + if (batadv_tt_local_dump_entry(msg, portid, seq, bat_priv, + common)) { + rcu_read_unlock(); + *idx_s = idx - 1; + return -EMSGSIZE; + } + } + rcu_read_unlock(); + + *idx_s = 0; + return 0; +} + +/** + * batadv_tt_local_dump - Dump TT local entries into a message + * @msg: Netlink message to dump into + * @cb: Parameters from query + * + * Return: Error code, or 0 on success + */ +int batadv_tt_local_dump(struct sk_buff *msg, struct netlink_callback *cb) +{ + struct net *net = sock_net(cb->skb->sk); + struct net_device *soft_iface; + struct batadv_priv *bat_priv; + struct batadv_hard_iface *primary_if = NULL; + struct batadv_hashtable *hash; + struct hlist_head *head; + int ret; + int ifindex; + int bucket = cb->args[0]; + int idx = cb->args[1]; + int portid = NETLINK_CB(cb->skb).portid; + + ifindex = batadv_netlink_get_ifindex(cb->nlh, BATADV_ATTR_MESH_IFINDEX); + if (!ifindex) + return -EINVAL; + + soft_iface = dev_get_by_index(net, ifindex); + if (!soft_iface || !batadv_softif_is_valid(soft_iface)) { + ret = -ENODEV; + goto out; + } + + bat_priv = netdev_priv(soft_iface); + + primary_if = batadv_primary_if_get_selected(bat_priv); + if (!primary_if || primary_if->if_status != BATADV_IF_ACTIVE) { + ret = -ENOENT; + goto out; + } + + hash = bat_priv->tt.local_hash; + + while (bucket < hash->size) { + head = &hash->table[bucket]; + + if (batadv_tt_local_dump_bucket(msg, portid, cb->nlh->nlmsg_seq, + bat_priv, head, &idx)) + break; + + bucket++; + } + + ret = msg->len; + + out: + if (primary_if) + batadv_hardif_put(primary_if); + if (soft_iface) + dev_put(soft_iface); + + cb->args[0] = bucket; + cb->args[1] = idx; + + return ret; +} static void batadv_tt_local_set_pending(struct batadv_priv *bat_priv, @@ -1259,7 +1477,7 @@ static void batadv_tt_changes_list_free(struct batadv_priv *bat_priv) list_for_each_entry_safe(entry, safe, &bat_priv->tt.changes_list, list) { list_del(&entry->list); - kfree(entry); + kmem_cache_free(batadv_tt_change_cache, entry); } atomic_set(&bat_priv->tt.local_changes, 0); @@ -1341,7 +1559,7 @@ batadv_tt_global_orig_entry_add(struct batadv_tt_global_entry *tt_global, goto out; } - orig_entry = kzalloc(sizeof(*orig_entry), GFP_ATOMIC); + orig_entry = kmem_cache_zalloc(batadv_tt_orig_cache, GFP_ATOMIC); if (!orig_entry) goto out; @@ -1351,9 +1569,9 @@ batadv_tt_global_orig_entry_add(struct batadv_tt_global_entry *tt_global, orig_entry->orig_node = orig_node; orig_entry->ttvn = ttvn; kref_init(&orig_entry->refcount); - kref_get(&orig_entry->refcount); spin_lock_bh(&tt_global->list_lock); + kref_get(&orig_entry->refcount); hlist_add_head_rcu(&orig_entry->list, &tt_global->orig_list); spin_unlock_bh(&tt_global->list_lock); @@ -1411,7 +1629,8 @@ static bool batadv_tt_global_add(struct batadv_priv *bat_priv, goto out; if (!tt_global_entry) { - tt_global_entry = kzalloc(sizeof(*tt_global_entry), GFP_ATOMIC); + tt_global_entry = kmem_cache_zalloc(batadv_tg_cache, + GFP_ATOMIC); if (!tt_global_entry) goto out; @@ -1428,13 +1647,13 @@ static bool batadv_tt_global_add(struct batadv_priv *bat_priv, if (flags & BATADV_TT_CLIENT_ROAM) tt_global_entry->roam_at = jiffies; kref_init(&common->refcount); - kref_get(&common->refcount); common->added_at = jiffies; INIT_HLIST_HEAD(&tt_global_entry->orig_list); atomic_set(&tt_global_entry->orig_list_count, 0); spin_lock_init(&tt_global_entry->list_lock); + kref_get(&common->refcount); hash_added = batadv_hash_add(bat_priv->tt.global_hash, batadv_compare_tt, batadv_choose_tt, common, @@ -1579,6 +1798,7 @@ batadv_transtable_best_orig(struct batadv_priv *bat_priv, return best_entry; } +#ifdef CONFIG_BATMAN_ADV_DEBUGFS /** * batadv_tt_global_print_entry - print all orig nodes who announce the address * for this global entry @@ -1702,6 +1922,219 @@ out: batadv_hardif_put(primary_if); return 0; } +#endif + +/** + * batadv_tt_global_dump_subentry - Dump all TT local entries into a message + * @msg: Netlink message to dump into + * @portid: Port making netlink request + * @seq: Sequence number of netlink message + * @common: tt local & tt global common data + * @orig: Originator node announcing a non-mesh client + * @best: Is the best originator for the TT entry + * + * Return: Error code, or 0 on success + */ +static int +batadv_tt_global_dump_subentry(struct sk_buff *msg, u32 portid, u32 seq, + struct batadv_tt_common_entry *common, + struct batadv_tt_orig_list_entry *orig, + bool best) +{ + void *hdr; + struct batadv_orig_node_vlan *vlan; + u8 last_ttvn; + u32 crc; + + vlan = batadv_orig_node_vlan_get(orig->orig_node, + common->vid); + if (!vlan) + return 0; + + crc = vlan->tt.crc; + + batadv_orig_node_vlan_put(vlan); + + hdr = genlmsg_put(msg, portid, seq, &batadv_netlink_family, + NLM_F_MULTI, + BATADV_CMD_GET_TRANSTABLE_GLOBAL); + if (!hdr) + return -ENOBUFS; + + last_ttvn = atomic_read(&orig->orig_node->last_ttvn); + + if (nla_put(msg, BATADV_ATTR_TT_ADDRESS, ETH_ALEN, common->addr) || + nla_put(msg, BATADV_ATTR_ORIG_ADDRESS, ETH_ALEN, + orig->orig_node->orig) || + nla_put_u8(msg, BATADV_ATTR_TT_TTVN, orig->ttvn) || + nla_put_u8(msg, BATADV_ATTR_TT_LAST_TTVN, last_ttvn) || + nla_put_u32(msg, BATADV_ATTR_TT_CRC32, crc) || + nla_put_u16(msg, BATADV_ATTR_TT_VID, common->vid) || + nla_put_u32(msg, BATADV_ATTR_TT_FLAGS, common->flags)) + goto nla_put_failure; + + if (best && nla_put_flag(msg, BATADV_ATTR_FLAG_BEST)) + goto nla_put_failure; + + genlmsg_end(msg, hdr); + return 0; + + nla_put_failure: + genlmsg_cancel(msg, hdr); + return -EMSGSIZE; +} + +/** + * batadv_tt_global_dump_entry - Dump one TT global entry into a message + * @msg: Netlink message to dump into + * @portid: Port making netlink request + * @seq: Sequence number of netlink message + * @bat_priv: The bat priv with all the soft interface information + * @common: tt local & tt global common data + * @sub_s: Number of entries to skip + * + * This function assumes the caller holds rcu_read_lock(). + * + * Return: Error code, or 0 on success + */ +static int +batadv_tt_global_dump_entry(struct sk_buff *msg, u32 portid, u32 seq, + struct batadv_priv *bat_priv, + struct batadv_tt_common_entry *common, int *sub_s) +{ + struct batadv_tt_orig_list_entry *orig_entry, *best_entry; + struct batadv_tt_global_entry *global; + struct hlist_head *head; + int sub = 0; + bool best; + + global = container_of(common, struct batadv_tt_global_entry, common); + best_entry = batadv_transtable_best_orig(bat_priv, global); + head = &global->orig_list; + + hlist_for_each_entry_rcu(orig_entry, head, list) { + if (sub++ < *sub_s) + continue; + + best = (orig_entry == best_entry); + + if (batadv_tt_global_dump_subentry(msg, portid, seq, common, + orig_entry, best)) { + *sub_s = sub - 1; + return -EMSGSIZE; + } + } + + *sub_s = 0; + return 0; +} + +/** + * batadv_tt_global_dump_bucket - Dump one TT local bucket into a message + * @msg: Netlink message to dump into + * @portid: Port making netlink request + * @seq: Sequence number of netlink message + * @bat_priv: The bat priv with all the soft interface information + * @head: Pointer to the list containing the global tt entries + * @idx_s: Number of entries to skip + * @sub: Number of entries to skip + * + * Return: Error code, or 0 on success + */ +static int +batadv_tt_global_dump_bucket(struct sk_buff *msg, u32 portid, u32 seq, + struct batadv_priv *bat_priv, + struct hlist_head *head, int *idx_s, int *sub) +{ + struct batadv_tt_common_entry *common; + int idx = 0; + + rcu_read_lock(); + hlist_for_each_entry_rcu(common, head, hash_entry) { + if (idx++ < *idx_s) + continue; + + if (batadv_tt_global_dump_entry(msg, portid, seq, bat_priv, + common, sub)) { + rcu_read_unlock(); + *idx_s = idx - 1; + return -EMSGSIZE; + } + } + rcu_read_unlock(); + + *idx_s = 0; + *sub = 0; + return 0; +} + +/** + * batadv_tt_global_dump - Dump TT global entries into a message + * @msg: Netlink message to dump into + * @cb: Parameters from query + * + * Return: Error code, or length of message on success + */ +int batadv_tt_global_dump(struct sk_buff *msg, struct netlink_callback *cb) +{ + struct net *net = sock_net(cb->skb->sk); + struct net_device *soft_iface; + struct batadv_priv *bat_priv; + struct batadv_hard_iface *primary_if = NULL; + struct batadv_hashtable *hash; + struct hlist_head *head; + int ret; + int ifindex; + int bucket = cb->args[0]; + int idx = cb->args[1]; + int sub = cb->args[2]; + int portid = NETLINK_CB(cb->skb).portid; + + ifindex = batadv_netlink_get_ifindex(cb->nlh, BATADV_ATTR_MESH_IFINDEX); + if (!ifindex) + return -EINVAL; + + soft_iface = dev_get_by_index(net, ifindex); + if (!soft_iface || !batadv_softif_is_valid(soft_iface)) { + ret = -ENODEV; + goto out; + } + + bat_priv = netdev_priv(soft_iface); + + primary_if = batadv_primary_if_get_selected(bat_priv); + if (!primary_if || primary_if->if_status != BATADV_IF_ACTIVE) { + ret = -ENOENT; + goto out; + } + + hash = bat_priv->tt.global_hash; + + while (bucket < hash->size) { + head = &hash->table[bucket]; + + if (batadv_tt_global_dump_bucket(msg, portid, + cb->nlh->nlmsg_seq, bat_priv, + head, &idx, &sub)) + break; + + bucket++; + } + + ret = msg->len; + + out: + if (primary_if) + batadv_hardif_put(primary_if); + if (soft_iface) + dev_put(soft_iface); + + cb->args[0] = bucket; + cb->args[1] = idx; + cb->args[2] = sub; + + return ret; +} /** * _batadv_tt_global_del_orig_entry - remove and free an orig_entry @@ -2280,7 +2713,7 @@ static void batadv_tt_req_node_release(struct kref *ref) tt_req_node = container_of(ref, struct batadv_tt_req_node, refcount); - kfree(tt_req_node); + kmem_cache_free(batadv_tt_req_cache, tt_req_node); } /** @@ -2367,7 +2800,7 @@ batadv_tt_req_node_new(struct batadv_priv *bat_priv, goto unlock; } - tt_req_node = kmalloc(sizeof(*tt_req_node), GFP_ATOMIC); + tt_req_node = kmem_cache_alloc(batadv_tt_req_cache, GFP_ATOMIC); if (!tt_req_node) goto unlock; @@ -3104,7 +3537,7 @@ static void batadv_tt_roam_list_free(struct batadv_priv *bat_priv) list_for_each_entry_safe(node, safe, &bat_priv->tt.roam_list, list) { list_del(&node->list); - kfree(node); + kmem_cache_free(batadv_tt_roam_cache, node); } spin_unlock_bh(&bat_priv->tt.roam_list_lock); @@ -3121,7 +3554,7 @@ static void batadv_tt_roam_purge(struct batadv_priv *bat_priv) continue; list_del(&node->list); - kfree(node); + kmem_cache_free(batadv_tt_roam_cache, node); } spin_unlock_bh(&bat_priv->tt.roam_list_lock); } @@ -3162,7 +3595,8 @@ static bool batadv_tt_check_roam_count(struct batadv_priv *bat_priv, u8 *client) } if (!ret) { - tt_roam_node = kmalloc(sizeof(*tt_roam_node), GFP_ATOMIC); + tt_roam_node = kmem_cache_alloc(batadv_tt_roam_cache, + GFP_ATOMIC); if (!tt_roam_node) goto unlock; @@ -3865,3 +4299,85 @@ bool batadv_tt_global_is_isolated(struct batadv_priv *bat_priv, return ret; } + +/** + * batadv_tt_cache_init - Initialize tt memory object cache + * + * Return: 0 on success or negative error number in case of failure. + */ +int __init batadv_tt_cache_init(void) +{ + size_t tl_size = sizeof(struct batadv_tt_local_entry); + size_t tg_size = sizeof(struct batadv_tt_global_entry); + size_t tt_orig_size = sizeof(struct batadv_tt_orig_list_entry); + size_t tt_change_size = sizeof(struct batadv_tt_change_node); + size_t tt_req_size = sizeof(struct batadv_tt_req_node); + size_t tt_roam_size = sizeof(struct batadv_tt_roam_node); + + batadv_tl_cache = kmem_cache_create("batadv_tl_cache", tl_size, 0, + SLAB_HWCACHE_ALIGN, NULL); + if (!batadv_tl_cache) + return -ENOMEM; + + batadv_tg_cache = kmem_cache_create("batadv_tg_cache", tg_size, 0, + SLAB_HWCACHE_ALIGN, NULL); + if (!batadv_tg_cache) + goto err_tt_tl_destroy; + + batadv_tt_orig_cache = kmem_cache_create("batadv_tt_orig_cache", + tt_orig_size, 0, + SLAB_HWCACHE_ALIGN, NULL); + if (!batadv_tt_orig_cache) + goto err_tt_tg_destroy; + + batadv_tt_change_cache = kmem_cache_create("batadv_tt_change_cache", + tt_change_size, 0, + SLAB_HWCACHE_ALIGN, NULL); + if (!batadv_tt_change_cache) + goto err_tt_orig_destroy; + + batadv_tt_req_cache = kmem_cache_create("batadv_tt_req_cache", + tt_req_size, 0, + SLAB_HWCACHE_ALIGN, NULL); + if (!batadv_tt_req_cache) + goto err_tt_change_destroy; + + batadv_tt_roam_cache = kmem_cache_create("batadv_tt_roam_cache", + tt_roam_size, 0, + SLAB_HWCACHE_ALIGN, NULL); + if (!batadv_tt_roam_cache) + goto err_tt_req_destroy; + + return 0; + +err_tt_req_destroy: + kmem_cache_destroy(batadv_tt_req_cache); + batadv_tt_req_cache = NULL; +err_tt_change_destroy: + kmem_cache_destroy(batadv_tt_change_cache); + batadv_tt_change_cache = NULL; +err_tt_orig_destroy: + kmem_cache_destroy(batadv_tt_orig_cache); + batadv_tt_orig_cache = NULL; +err_tt_tg_destroy: + kmem_cache_destroy(batadv_tg_cache); + batadv_tg_cache = NULL; +err_tt_tl_destroy: + kmem_cache_destroy(batadv_tl_cache); + batadv_tl_cache = NULL; + + return -ENOMEM; +} + +/** + * batadv_tt_cache_destroy - Destroy tt memory object cache + */ +void batadv_tt_cache_destroy(void) +{ + kmem_cache_destroy(batadv_tl_cache); + kmem_cache_destroy(batadv_tg_cache); + kmem_cache_destroy(batadv_tt_orig_cache); + kmem_cache_destroy(batadv_tt_change_cache); + kmem_cache_destroy(batadv_tt_req_cache); + kmem_cache_destroy(batadv_tt_roam_cache); +} diff --git a/net/batman-adv/translation-table.h b/net/batman-adv/translation-table.h index 7c7e2c006bfe..783fdba84db2 100644 --- a/net/batman-adv/translation-table.h +++ b/net/batman-adv/translation-table.h @@ -22,8 +22,10 @@ #include <linux/types.h> +struct netlink_callback; struct net_device; struct seq_file; +struct sk_buff; int batadv_tt_init(struct batadv_priv *bat_priv); bool batadv_tt_local_add(struct net_device *soft_iface, const u8 *addr, @@ -33,6 +35,8 @@ u16 batadv_tt_local_remove(struct batadv_priv *bat_priv, const char *message, bool roaming); int batadv_tt_local_seq_print_text(struct seq_file *seq, void *offset); int batadv_tt_global_seq_print_text(struct seq_file *seq, void *offset); +int batadv_tt_local_dump(struct sk_buff *msg, struct netlink_callback *cb); +int batadv_tt_global_dump(struct sk_buff *msg, struct netlink_callback *cb); void batadv_tt_global_del_orig(struct batadv_priv *bat_priv, struct batadv_orig_node *orig_node, s32 match_vid, const char *message); @@ -59,4 +63,7 @@ bool batadv_tt_add_temporary_global_entry(struct batadv_priv *bat_priv, bool batadv_tt_global_is_isolated(struct batadv_priv *bat_priv, const u8 *addr, unsigned short vid); +int batadv_tt_cache_init(void); +void batadv_tt_cache_destroy(void); + #endif /* _NET_BATMAN_ADV_TRANSLATION_TABLE_H_ */ diff --git a/net/batman-adv/tvlv.c b/net/batman-adv/tvlv.c index 3d1cf0fb112d..77654f055f24 100644 --- a/net/batman-adv/tvlv.c +++ b/net/batman-adv/tvlv.c @@ -257,8 +257,13 @@ void batadv_tvlv_container_register(struct batadv_priv *bat_priv, spin_lock_bh(&bat_priv->tvlv.container_list_lock); tvlv_old = batadv_tvlv_container_get(bat_priv, type, version); batadv_tvlv_container_remove(bat_priv, tvlv_old); + + kref_get(&tvlv_new->refcount); hlist_add_head(&tvlv_new->list, &bat_priv->tvlv.container_list); spin_unlock_bh(&bat_priv->tvlv.container_list_lock); + + /* don't return reference to new tvlv_container */ + batadv_tvlv_container_put(tvlv_new); } /** @@ -542,8 +547,12 @@ void batadv_tvlv_handler_register(struct batadv_priv *bat_priv, INIT_HLIST_NODE(&tvlv_handler->list); spin_lock_bh(&bat_priv->tvlv.handler_list_lock); + kref_get(&tvlv_handler->refcount); hlist_add_head_rcu(&tvlv_handler->list, &bat_priv->tvlv.handler_list); spin_unlock_bh(&bat_priv->tvlv.handler_list_lock); + + /* don't return reference to new tvlv_handler */ + batadv_tvlv_handler_put(tvlv_handler); } /** diff --git a/net/batman-adv/types.h b/net/batman-adv/types.h index a64522c3b45d..b3dd1a381aad 100644 --- a/net/batman-adv/types.h +++ b/net/batman-adv/types.h @@ -28,6 +28,7 @@ #include <linux/if_ether.h> #include <linux/kref.h> #include <linux/netdevice.h> +#include <linux/netlink.h> #include <linux/sched.h> /* for linux/wait.h */ #include <linux/spinlock.h> #include <linux/types.h> @@ -132,7 +133,6 @@ struct batadv_hard_iface_bat_v { * @rcu: struct used for freeing in an RCU-safe manner * @bat_iv: per hard-interface B.A.T.M.A.N. IV data * @bat_v: per hard-interface B.A.T.M.A.N. V data - * @cleanup_work: work queue callback item for hard-interface deinit * @debug_dir: dentry for nc subdir in batman-adv directory in debugfs * @neigh_list: list of unique single hop neighbors via this interface * @neigh_list_lock: lock protecting neigh_list @@ -152,7 +152,6 @@ struct batadv_hard_iface { #ifdef CONFIG_BATMAN_ADV_BATMAN_V struct batadv_hard_iface_bat_v bat_v; #endif - struct work_struct cleanup_work; struct dentry *debug_dir; struct hlist_head neigh_list; /* neigh_list_lock protects: neigh_list */ @@ -1015,7 +1014,6 @@ struct batadv_priv_bat_v { * @forw_bcast_list_lock: lock protecting forw_bcast_list * @tp_list_lock: spinlock protecting @tp_list * @orig_work: work queue callback item for orig node purging - * @cleanup_work: work queue callback item for soft-interface deinit * @primary_if: one of the hard-interfaces assigned to this mesh interface * becomes the primary interface * @algo_ops: routing algorithm used by this mesh interface @@ -1074,7 +1072,6 @@ struct batadv_priv { spinlock_t tp_list_lock; /* protects tp_list */ atomic_t tp_num; struct delayed_work orig_work; - struct work_struct cleanup_work; struct batadv_hard_iface __rcu *primary_if; /* rcu protected pointer */ struct batadv_algo_ops *algo_ops; struct hlist_head softif_vlan_list; @@ -1379,6 +1376,7 @@ struct batadv_skb_cb { * locally generated packet * @if_outgoing: packet where the packet should be sent to, or NULL if * unspecified + * @queue_left: The queue (counter) this packet was applied to */ struct batadv_forw_packet { struct hlist_node list; @@ -1391,11 +1389,13 @@ struct batadv_forw_packet { struct delayed_work delayed_work; struct batadv_hard_iface *if_incoming; struct batadv_hard_iface *if_outgoing; + atomic_t *queue_left; }; /** * struct batadv_algo_iface_ops - mesh algorithm callbacks (interface specific) * @activate: start routing mechanisms when hard-interface is brought up + * (optional) * @enable: init routing info when hard-interface is enabled * @disable: de-init routing info when hard-interface is disabled * @update_mac: (re-)init mac addresses of the protocol information @@ -1413,11 +1413,13 @@ struct batadv_algo_iface_ops { /** * struct batadv_algo_neigh_ops - mesh algorithm callbacks (neighbour specific) * @hardif_init: called on creation of single hop entry + * (optional) * @cmp: compare the metrics of two neighbors for their respective outgoing * interfaces * @is_similar_or_better: check if neigh1 is equally similar or better than * neigh2 for their respective outgoing interface from the metric prospective * @print: print the single hop neighbor list (optional) + * @dump: dump neighbors to a netlink socket (optional) */ struct batadv_algo_neigh_ops { void (*hardif_init)(struct batadv_hardif_neigh_node *neigh); @@ -1429,26 +1431,64 @@ struct batadv_algo_neigh_ops { struct batadv_hard_iface *if_outgoing1, struct batadv_neigh_node *neigh2, struct batadv_hard_iface *if_outgoing2); +#ifdef CONFIG_BATMAN_ADV_DEBUGFS void (*print)(struct batadv_priv *priv, struct seq_file *seq); +#endif + void (*dump)(struct sk_buff *msg, struct netlink_callback *cb, + struct batadv_priv *priv, + struct batadv_hard_iface *hard_iface); }; /** * struct batadv_algo_orig_ops - mesh algorithm callbacks (originator specific) * @free: free the resources allocated by the routing algorithm for an orig_node - * object + * object (optional) * @add_if: ask the routing algorithm to apply the needed changes to the - * orig_node due to a new hard-interface being added into the mesh + * orig_node due to a new hard-interface being added into the mesh (optional) * @del_if: ask the routing algorithm to apply the needed changes to the - * orig_node due to an hard-interface being removed from the mesh + * orig_node due to an hard-interface being removed from the mesh (optional) * @print: print the originator table (optional) + * @dump: dump originators to a netlink socket (optional) */ struct batadv_algo_orig_ops { void (*free)(struct batadv_orig_node *orig_node); int (*add_if)(struct batadv_orig_node *orig_node, int max_if_num); int (*del_if)(struct batadv_orig_node *orig_node, int max_if_num, int del_if_num); +#ifdef CONFIG_BATMAN_ADV_DEBUGFS void (*print)(struct batadv_priv *priv, struct seq_file *seq, struct batadv_hard_iface *hard_iface); +#endif + void (*dump)(struct sk_buff *msg, struct netlink_callback *cb, + struct batadv_priv *priv, + struct batadv_hard_iface *hard_iface); +}; + +/** + * struct batadv_algo_gw_ops - mesh algorithm callbacks (GW specific) + * @store_sel_class: parse and stores a new GW selection class (optional) + * @show_sel_class: prints the current GW selection class (optional) + * @get_best_gw_node: select the best GW from the list of available nodes + * (optional) + * @is_eligible: check if a newly discovered GW is a potential candidate for + * the election as best GW (optional) + * @print: print the gateway table (optional) + * @dump: dump gateways to a netlink socket (optional) + */ +struct batadv_algo_gw_ops { + ssize_t (*store_sel_class)(struct batadv_priv *bat_priv, char *buff, + size_t count); + ssize_t (*show_sel_class)(struct batadv_priv *bat_priv, char *buff); + struct batadv_gw_node *(*get_best_gw_node) + (struct batadv_priv *bat_priv); + bool (*is_eligible)(struct batadv_priv *bat_priv, + struct batadv_orig_node *curr_gw_orig, + struct batadv_orig_node *orig_node); +#ifdef CONFIG_BATMAN_ADV_DEBUGFS + void (*print)(struct batadv_priv *bat_priv, struct seq_file *seq); +#endif + void (*dump)(struct sk_buff *msg, struct netlink_callback *cb, + struct batadv_priv *priv); }; /** @@ -1458,6 +1498,7 @@ struct batadv_algo_orig_ops { * @iface: callbacks related to interface handling * @neigh: callbacks related to neighbors handling * @orig: callbacks related to originators handling + * @gw: callbacks related to GW mode */ struct batadv_algo_ops { struct hlist_node list; @@ -1465,6 +1506,7 @@ struct batadv_algo_ops { struct batadv_algo_iface_ops iface; struct batadv_algo_neigh_ops neigh; struct batadv_algo_orig_ops orig; + struct batadv_algo_gw_ops gw; }; /** @@ -1564,4 +1606,17 @@ enum batadv_tvlv_handler_flags { BATADV_TVLV_HANDLER_OGM_CALLED = BIT(2), }; +/** + * struct batadv_store_mesh_work - Work queue item to detach add/del interface + * from sysfs locks + * @net_dev: netdevice to add/remove to/from batman-adv soft-interface + * @soft_iface_name: name of soft-interface to modify + * @work: work queue item + */ +struct batadv_store_mesh_work { + struct net_device *net_dev; + char soft_iface_name[IFNAMSIZ]; + struct work_struct work; +}; + #endif /* _NET_BATMAN_ADV_TYPES_H_ */ diff --git a/net/bluetooth/af_bluetooth.c b/net/bluetooth/af_bluetooth.c index ece45e0683fd..0b5f729d08d2 100644 --- a/net/bluetooth/af_bluetooth.c +++ b/net/bluetooth/af_bluetooth.c @@ -250,7 +250,7 @@ int bt_sock_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, skb_free_datagram(sk, skb); - if (msg->msg_flags & MSG_TRUNC) + if (flags & MSG_TRUNC) copied = skblen; return err ? : copied; diff --git a/net/bluetooth/hci_request.c b/net/bluetooth/hci_request.c index c045b3c54768..b0e23dfc5c34 100644 --- a/net/bluetooth/hci_request.c +++ b/net/bluetooth/hci_request.c @@ -262,6 +262,8 @@ int __hci_req_sync(struct hci_dev *hdev, int (*func)(struct hci_request *req, break; } + kfree_skb(hdev->req_skb); + hdev->req_skb = NULL; hdev->req_status = hdev->req_result = 0; BT_DBG("%s end: err %d", hdev->name, err); diff --git a/net/bluetooth/hci_sock.c b/net/bluetooth/hci_sock.c index 6ef8a01a9ad4..96f04b7b9556 100644 --- a/net/bluetooth/hci_sock.c +++ b/net/bluetooth/hci_sock.c @@ -1091,7 +1091,7 @@ static int hci_sock_recvmsg(struct socket *sock, struct msghdr *msg, skb_free_datagram(sk, skb); - if (msg->msg_flags & MSG_TRUNC) + if (flags & MSG_TRUNC) copied = skblen; return err ? : copied; diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c index 54ceb1f2cc9a..d4cad29b033f 100644 --- a/net/bluetooth/l2cap_core.c +++ b/net/bluetooth/l2cap_core.c @@ -32,6 +32,7 @@ #include <linux/debugfs.h> #include <linux/crc16.h> +#include <linux/filter.h> #include <net/bluetooth/bluetooth.h> #include <net/bluetooth/hci_core.h> @@ -5835,6 +5836,9 @@ static int l2cap_reassemble_sdu(struct l2cap_chan *chan, struct sk_buff *skb, if (chan->sdu) break; + if (!pskb_may_pull(skb, L2CAP_SDULEN_SIZE)) + break; + chan->sdu_len = get_unaligned_le16(skb->data); skb_pull(skb, L2CAP_SDULEN_SIZE); @@ -6610,6 +6614,10 @@ static int l2cap_data_rcv(struct l2cap_chan *chan, struct sk_buff *skb) goto drop; } + if ((chan->mode == L2CAP_MODE_ERTM || + chan->mode == L2CAP_MODE_STREAMING) && sk_filter(chan->data, skb)) + goto drop; + if (!control->sframe) { int err; diff --git a/net/bluetooth/l2cap_sock.c b/net/bluetooth/l2cap_sock.c index 1842141baedb..a8ba752732c9 100644 --- a/net/bluetooth/l2cap_sock.c +++ b/net/bluetooth/l2cap_sock.c @@ -1019,7 +1019,7 @@ static int l2cap_sock_recvmsg(struct socket *sock, struct msghdr *msg, goto done; if (pi->rx_busy_skb) { - if (!sock_queue_rcv_skb(sk, pi->rx_busy_skb)) + if (!__sock_queue_rcv_skb(sk, pi->rx_busy_skb)) pi->rx_busy_skb = NULL; else goto done; @@ -1270,7 +1270,17 @@ static int l2cap_sock_recv_cb(struct l2cap_chan *chan, struct sk_buff *skb) goto done; } - err = sock_queue_rcv_skb(sk, skb); + if (chan->mode != L2CAP_MODE_ERTM && + chan->mode != L2CAP_MODE_STREAMING) { + /* Even if no filter is attached, we could potentially + * get errors from security modules, etc. + */ + err = sk_filter(sk, skb); + if (err) + goto done; + } + + err = __sock_queue_rcv_skb(sk, skb); /* For ERTM, handle one skb that doesn't fit into the recv * buffer. This is important to do because the data frames diff --git a/net/bridge/Makefile b/net/bridge/Makefile index a1cda5d4718d..0aefc011b668 100644 --- a/net/bridge/Makefile +++ b/net/bridge/Makefile @@ -20,4 +20,6 @@ bridge-$(CONFIG_BRIDGE_IGMP_SNOOPING) += br_multicast.o br_mdb.o bridge-$(CONFIG_BRIDGE_VLAN_FILTERING) += br_vlan.o +bridge-$(CONFIG_NET_SWITCHDEV) += br_switchdev.o + obj-$(CONFIG_NETFILTER) += netfilter/ diff --git a/net/bridge/br_device.c b/net/bridge/br_device.c index 09f26940aba5..89a687f3c0a3 100644 --- a/net/bridge/br_device.c +++ b/net/bridge/br_device.c @@ -62,10 +62,10 @@ netdev_tx_t br_dev_xmit(struct sk_buff *skb, struct net_device *dev) goto out; if (is_broadcast_ether_addr(dest)) { - br_flood(br, skb, false, false, true); + br_flood(br, skb, BR_PKT_BROADCAST, false, true); } else if (is_multicast_ether_addr(dest)) { if (unlikely(netpoll_tx_running(dev))) { - br_flood(br, skb, false, false, true); + br_flood(br, skb, BR_PKT_MULTICAST, false, true); goto out; } if (br_multicast_rcv(br, NULL, skb, vid)) { @@ -78,11 +78,11 @@ netdev_tx_t br_dev_xmit(struct sk_buff *skb, struct net_device *dev) br_multicast_querier_exists(br, eth_hdr(skb))) br_multicast_flood(mdst, skb, false, true); else - br_flood(br, skb, false, false, true); + br_flood(br, skb, BR_PKT_MULTICAST, false, true); } else if ((dst = __br_fdb_get(br, dest, vid)) != NULL) { br_forward(dst->dst, skb, false, true); } else { - br_flood(br, skb, true, false, true); + br_flood(br, skb, BR_PKT_UNICAST, false, true); } out: rcu_read_unlock(); diff --git a/net/bridge/br_fdb.c b/net/bridge/br_fdb.c index c18080ad4085..6b43c8c88f19 100644 --- a/net/bridge/br_fdb.c +++ b/net/bridge/br_fdb.c @@ -267,7 +267,7 @@ void br_fdb_change_mac_address(struct net_bridge *br, const u8 *newaddr) /* If old entry was unassociated with any port, then delete it. */ f = __br_fdb_get(br, br->dev->dev_addr, 0); - if (f && f->is_local && !f->dst) + if (f && f->is_local && !f->dst && !f->added_by_user) fdb_delete_local(br, NULL, f); fdb_insert(br, NULL, newaddr, 0); @@ -282,7 +282,7 @@ void br_fdb_change_mac_address(struct net_bridge *br, const u8 *newaddr) if (!br_vlan_should_use(v)) continue; f = __br_fdb_get(br, br->dev->dev_addr, v->vid); - if (f && f->is_local && !f->dst) + if (f && f->is_local && !f->dst && !f->added_by_user) fdb_delete_local(br, NULL, f); fdb_insert(br, NULL, newaddr, v->vid); } @@ -710,24 +710,27 @@ int br_fdb_dump(struct sk_buff *skb, struct netlink_callback *cb, struct net_device *dev, struct net_device *filter_dev, - int idx) + int *idx) { struct net_bridge *br = netdev_priv(dev); + int err = 0; int i; if (!(dev->priv_flags & IFF_EBRIDGE)) goto out; - if (!filter_dev) - idx = ndo_dflt_fdb_dump(skb, cb, dev, NULL, idx); + if (!filter_dev) { + err = ndo_dflt_fdb_dump(skb, cb, dev, NULL, idx); + if (err < 0) + goto out; + } for (i = 0; i < BR_HASH_SIZE; i++) { struct net_bridge_fdb_entry *f; hlist_for_each_entry_rcu(f, &br->hash[i], hlist) { - int err; - if (idx < cb->args[0]) + if (*idx < cb->args[2]) goto skip; if (filter_dev && @@ -750,34 +753,37 @@ int br_fdb_dump(struct sk_buff *skb, cb->nlh->nlmsg_seq, RTM_NEWNEIGH, NLM_F_MULTI); - if (err < 0) { - cb->args[1] = err; - break; - } + if (err < 0) + goto out; skip: - ++idx; + *idx += 1; } } out: - return idx; + return err; } /* Update (create or replace) forwarding database entry */ -static int fdb_add_entry(struct net_bridge_port *source, const __u8 *addr, - __u16 state, __u16 flags, __u16 vid) +static int fdb_add_entry(struct net_bridge *br, struct net_bridge_port *source, + const __u8 *addr, __u16 state, __u16 flags, __u16 vid) { - struct net_bridge *br = source->br; struct hlist_head *head = &br->hash[br_mac_hash(addr, vid)]; struct net_bridge_fdb_entry *fdb; bool modified = false; /* If the port cannot learn allow only local and static entries */ - if (!(state & NUD_PERMANENT) && !(state & NUD_NOARP) && + if (source && !(state & NUD_PERMANENT) && !(state & NUD_NOARP) && !(source->state == BR_STATE_LEARNING || source->state == BR_STATE_FORWARDING)) return -EPERM; + if (!source && !(state & NUD_PERMANENT)) { + pr_info("bridge: RTM_NEWNEIGH %s without NUD_PERMANENT\n", + br->dev->name); + return -EINVAL; + } + fdb = fdb_find(head, addr, vid); if (fdb == NULL) { if (!(flags & NLM_F_CREATE)) @@ -832,22 +838,28 @@ static int fdb_add_entry(struct net_bridge_port *source, const __u8 *addr, return 0; } -static int __br_fdb_add(struct ndmsg *ndm, struct net_bridge_port *p, - const unsigned char *addr, u16 nlh_flags, u16 vid) +static int __br_fdb_add(struct ndmsg *ndm, struct net_bridge *br, + struct net_bridge_port *p, const unsigned char *addr, + u16 nlh_flags, u16 vid) { int err = 0; if (ndm->ndm_flags & NTF_USE) { + if (!p) { + pr_info("bridge: RTM_NEWNEIGH %s with NTF_USE is not supported\n", + br->dev->name); + return -EINVAL; + } local_bh_disable(); rcu_read_lock(); - br_fdb_update(p->br, p, addr, vid, true); + br_fdb_update(br, p, addr, vid, true); rcu_read_unlock(); local_bh_enable(); } else { - spin_lock_bh(&p->br->hash_lock); - err = fdb_add_entry(p, addr, ndm->ndm_state, + spin_lock_bh(&br->hash_lock); + err = fdb_add_entry(br, p, addr, ndm->ndm_state, nlh_flags, vid); - spin_unlock_bh(&p->br->hash_lock); + spin_unlock_bh(&br->hash_lock); } return err; @@ -884,6 +896,7 @@ int br_fdb_add(struct ndmsg *ndm, struct nlattr *tb[], dev->name); return -EINVAL; } + br = p->br; vg = nbp_vlan_group(p); } @@ -895,15 +908,9 @@ int br_fdb_add(struct ndmsg *ndm, struct nlattr *tb[], } /* VID was specified, so use it. */ - if (dev->priv_flags & IFF_EBRIDGE) - err = br_fdb_insert(br, NULL, addr, vid); - else - err = __br_fdb_add(ndm, p, addr, nlh_flags, vid); + err = __br_fdb_add(ndm, br, p, addr, nlh_flags, vid); } else { - if (dev->priv_flags & IFF_EBRIDGE) - err = br_fdb_insert(br, NULL, addr, 0); - else - err = __br_fdb_add(ndm, p, addr, nlh_flags, 0); + err = __br_fdb_add(ndm, br, p, addr, nlh_flags, 0); if (err || !vg || !vg->num_vlans) goto out; @@ -914,11 +921,7 @@ int br_fdb_add(struct ndmsg *ndm, struct nlattr *tb[], list_for_each_entry(v, &vg->vlan_list, vlist) { if (!br_vlan_should_use(v)) continue; - if (dev->priv_flags & IFF_EBRIDGE) - err = br_fdb_insert(br, NULL, addr, v->vid); - else - err = __br_fdb_add(ndm, p, addr, nlh_flags, - v->vid); + err = __br_fdb_add(ndm, br, p, addr, nlh_flags, v->vid); if (err) goto out; } diff --git a/net/bridge/br_forward.c b/net/bridge/br_forward.c index 63a83d8d7da3..7cb41aee4c82 100644 --- a/net/bridge/br_forward.c +++ b/net/bridge/br_forward.c @@ -29,7 +29,8 @@ static inline int should_deliver(const struct net_bridge_port *p, vg = nbp_vlan_group_rcu(p); return ((p->flags & BR_HAIRPIN_MODE) || skb->dev != p->dev) && - br_allowed_egress(vg, skb) && p->state == BR_STATE_FORWARDING; + br_allowed_egress(vg, skb) && p->state == BR_STATE_FORWARDING && + nbp_switchdev_allowed_egress(p, skb); } int br_dev_queue_push_xmit(struct net *net, struct sock *sk, struct sk_buff *skb) @@ -175,7 +176,7 @@ out: /* called under rcu_read_lock */ void br_flood(struct net_bridge *br, struct sk_buff *skb, - bool unicast, bool local_rcv, bool local_orig) + enum br_pkt_type pkt_type, bool local_rcv, bool local_orig) { u8 igmp_type = br_multicast_igmp_type(skb); struct net_bridge_port *prev = NULL; @@ -183,7 +184,10 @@ void br_flood(struct net_bridge *br, struct sk_buff *skb, list_for_each_entry_rcu(p, &br->port_list, list) { /* Do not flood unicast traffic to ports that turn it off */ - if (unicast && !(p->flags & BR_FLOOD)) + if (pkt_type == BR_PKT_UNICAST && !(p->flags & BR_FLOOD)) + continue; + if (pkt_type == BR_PKT_MULTICAST && + !(p->flags & BR_MCAST_FLOOD)) continue; /* Do not flood to ports that enable proxy ARP */ diff --git a/net/bridge/br_if.c b/net/bridge/br_if.c index f2fede05d32c..ed0dd3340084 100644 --- a/net/bridge/br_if.c +++ b/net/bridge/br_if.c @@ -362,7 +362,7 @@ static struct net_bridge_port *new_nbp(struct net_bridge *br, p->path_cost = port_cost(dev); p->priority = 0x8000 >> BR_PORT_BITS; p->port_no = index; - p->flags = BR_LEARNING | BR_FLOOD; + p->flags = BR_LEARNING | BR_FLOOD | BR_MCAST_FLOOD; br_init_port(p); br_set_state(p, BR_STATE_DISABLED); br_stp_port_timer_init(p); @@ -545,6 +545,10 @@ int br_add_if(struct net_bridge *br, struct net_device *dev) if (err) goto err5; + err = nbp_switchdev_mark_set(p); + if (err) + goto err6; + dev_disable_lro(dev); list_add_rcu(&p->list, &br->port_list); @@ -566,7 +570,7 @@ int br_add_if(struct net_bridge *br, struct net_device *dev) err = nbp_vlan_init(p); if (err) { netdev_err(dev, "failed to initialize vlan filtering on this port\n"); - goto err6; + goto err7; } spin_lock_bh(&br->lock); @@ -589,12 +593,12 @@ int br_add_if(struct net_bridge *br, struct net_device *dev) return 0; -err6: +err7: list_del_rcu(&p->list); br_fdb_delete_by_port(br, p, 0, 1); nbp_update_port_count(br); +err6: netdev_upper_dev_unlink(dev, br->dev); - err5: dev->priv_flags &= ~IFF_BRIDGE_PORT; netdev_rx_handler_unregister(dev); diff --git a/net/bridge/br_input.c b/net/bridge/br_input.c index 8e486203d133..8a4368461fb0 100644 --- a/net/bridge/br_input.c +++ b/net/bridge/br_input.c @@ -131,11 +131,12 @@ static void br_do_proxy_arp(struct sk_buff *skb, struct net_bridge *br, /* note: already called with rcu_read_lock */ int br_handle_frame_finish(struct net *net, struct sock *sk, struct sk_buff *skb) { - bool local_rcv = false, mcast_hit = false, unicast = true; struct net_bridge_port *p = br_port_get_rcu(skb->dev); const unsigned char *dest = eth_hdr(skb)->h_dest; + enum br_pkt_type pkt_type = BR_PKT_UNICAST; struct net_bridge_fdb_entry *dst = NULL; struct net_bridge_mdb_entry *mdst; + bool local_rcv, mcast_hit = false; struct net_bridge *br; u16 vid = 0; @@ -145,29 +146,36 @@ int br_handle_frame_finish(struct net *net, struct sock *sk, struct sk_buff *skb if (!br_allowed_ingress(p->br, nbp_vlan_group_rcu(p), skb, &vid)) goto out; + nbp_switchdev_frame_mark(p, skb); + /* insert into forwarding database after filtering to avoid spoofing */ br = p->br; if (p->flags & BR_LEARNING) br_fdb_update(br, p, eth_hdr(skb)->h_source, vid, false); - if (!is_broadcast_ether_addr(dest) && is_multicast_ether_addr(dest) && - br_multicast_rcv(br, p, skb, vid)) - goto drop; + local_rcv = !!(br->dev->flags & IFF_PROMISC); + if (is_multicast_ether_addr(dest)) { + /* by definition the broadcast is also a multicast address */ + if (is_broadcast_ether_addr(dest)) { + pkt_type = BR_PKT_BROADCAST; + local_rcv = true; + } else { + pkt_type = BR_PKT_MULTICAST; + if (br_multicast_rcv(br, p, skb, vid)) + goto drop; + } + } if (p->state == BR_STATE_LEARNING) goto drop; BR_INPUT_SKB_CB(skb)->brdev = br->dev; - local_rcv = !!(br->dev->flags & IFF_PROMISC); - if (IS_ENABLED(CONFIG_INET) && skb->protocol == htons(ETH_P_ARP)) br_do_proxy_arp(skb, br, vid, p); - if (is_broadcast_ether_addr(dest)) { - local_rcv = true; - unicast = false; - } else if (is_multicast_ether_addr(dest)) { + switch (pkt_type) { + case BR_PKT_MULTICAST: mdst = br_mdb_get(br, skb, vid); if ((mdst || BR_INPUT_SKB_CB_MROUTERS_ONLY(skb)) && br_multicast_querier_exists(br, eth_hdr(skb))) { @@ -181,18 +189,22 @@ int br_handle_frame_finish(struct net *net, struct sock *sk, struct sk_buff *skb local_rcv = true; br->dev->stats.multicast++; } - unicast = false; - } else if ((dst = __br_fdb_get(br, dest, vid)) && dst->is_local) { - /* Do not forward the packet since it's local. */ - return br_pass_frame_up(skb); + break; + case BR_PKT_UNICAST: + dst = __br_fdb_get(br, dest, vid); + default: + break; } if (dst) { + if (dst->is_local) + return br_pass_frame_up(skb); + dst->used = jiffies; br_forward(dst->dst, skb, local_rcv, false); } else { if (!mcast_hit) - br_flood(br, skb, unicast, local_rcv, false); + br_flood(br, skb, pkt_type, local_rcv, false); else br_multicast_flood(mdst, skb, local_rcv, false); } diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c index f2a29e467e78..e99037c6f7b7 100644 --- a/net/bridge/br_netlink.c +++ b/net/bridge/br_netlink.c @@ -169,10 +169,15 @@ static int br_port_fill_attrs(struct sk_buff *skb, nla_put_u32(skb, IFLA_BRPORT_COST, p->path_cost) || nla_put_u8(skb, IFLA_BRPORT_MODE, mode) || nla_put_u8(skb, IFLA_BRPORT_GUARD, !!(p->flags & BR_BPDU_GUARD)) || - nla_put_u8(skb, IFLA_BRPORT_PROTECT, !!(p->flags & BR_ROOT_BLOCK)) || - nla_put_u8(skb, IFLA_BRPORT_FAST_LEAVE, !!(p->flags & BR_MULTICAST_FAST_LEAVE)) || + nla_put_u8(skb, IFLA_BRPORT_PROTECT, + !!(p->flags & BR_ROOT_BLOCK)) || + nla_put_u8(skb, IFLA_BRPORT_FAST_LEAVE, + !!(p->flags & BR_MULTICAST_FAST_LEAVE)) || nla_put_u8(skb, IFLA_BRPORT_LEARNING, !!(p->flags & BR_LEARNING)) || - nla_put_u8(skb, IFLA_BRPORT_UNICAST_FLOOD, !!(p->flags & BR_FLOOD)) || + nla_put_u8(skb, IFLA_BRPORT_UNICAST_FLOOD, + !!(p->flags & BR_FLOOD)) || + nla_put_u8(skb, IFLA_BRPORT_MCAST_FLOOD, + !!(p->flags & BR_MCAST_FLOOD)) || nla_put_u8(skb, IFLA_BRPORT_PROXYARP, !!(p->flags & BR_PROXYARP)) || nla_put_u8(skb, IFLA_BRPORT_PROXYARP_WIFI, !!(p->flags & BR_PROXYARP_WIFI)) || @@ -630,6 +635,7 @@ static int br_setport(struct net_bridge_port *p, struct nlattr *tb[]) br_set_port_flag(p, tb, IFLA_BRPORT_PROTECT, BR_ROOT_BLOCK); br_set_port_flag(p, tb, IFLA_BRPORT_LEARNING, BR_LEARNING); br_set_port_flag(p, tb, IFLA_BRPORT_UNICAST_FLOOD, BR_FLOOD); + br_set_port_flag(p, tb, IFLA_BRPORT_MCAST_FLOOD, BR_MCAST_FLOOD); br_set_port_flag(p, tb, IFLA_BRPORT_PROXYARP, BR_PROXYARP); br_set_port_flag(p, tb, IFLA_BRPORT_PROXYARP_WIFI, BR_PROXYARP_WIFI); @@ -1245,14 +1251,30 @@ static int br_fill_info(struct sk_buff *skb, const struct net_device *brdev) return 0; } -static size_t bridge_get_linkxstats_size(const struct net_device *dev) +static size_t br_get_linkxstats_size(const struct net_device *dev, int attr) { - struct net_bridge *br = netdev_priv(dev); + struct net_bridge_port *p = NULL; struct net_bridge_vlan_group *vg; struct net_bridge_vlan *v; + struct net_bridge *br; int numvls = 0; - vg = br_vlan_group(br); + switch (attr) { + case IFLA_STATS_LINK_XSTATS: + br = netdev_priv(dev); + vg = br_vlan_group(br); + break; + case IFLA_STATS_LINK_XSTATS_SLAVE: + p = br_port_get_rtnl(dev); + if (!p) + return 0; + br = p->br; + vg = nbp_vlan_group(p); + break; + default: + return 0; + } + if (vg) { /* we need to count all, even placeholder entries */ list_for_each_entry(v, &vg->vlan_list, vlist) @@ -1264,45 +1286,42 @@ static size_t bridge_get_linkxstats_size(const struct net_device *dev) nla_total_size(0); } -static size_t brport_get_linkxstats_size(const struct net_device *dev) -{ - return nla_total_size(sizeof(struct br_mcast_stats)) + - nla_total_size(0); -} - -static size_t br_get_linkxstats_size(const struct net_device *dev, int attr) +static int br_fill_linkxstats(struct sk_buff *skb, + const struct net_device *dev, + int *prividx, int attr) { - size_t retsize = 0; + struct nlattr *nla __maybe_unused; + struct net_bridge_port *p = NULL; + struct net_bridge_vlan_group *vg; + struct net_bridge_vlan *v; + struct net_bridge *br; + struct nlattr *nest; + int vl_idx = 0; switch (attr) { case IFLA_STATS_LINK_XSTATS: - retsize = bridge_get_linkxstats_size(dev); + br = netdev_priv(dev); + vg = br_vlan_group(br); break; case IFLA_STATS_LINK_XSTATS_SLAVE: - retsize = brport_get_linkxstats_size(dev); + p = br_port_get_rtnl(dev); + if (!p) + return 0; + br = p->br; + vg = nbp_vlan_group(p); break; + default: + return -EINVAL; } - return retsize; -} - -static int bridge_fill_linkxstats(struct sk_buff *skb, - const struct net_device *dev, - int *prividx) -{ - struct net_bridge *br = netdev_priv(dev); - struct nlattr *nla __maybe_unused; - struct net_bridge_vlan_group *vg; - struct net_bridge_vlan *v; - struct nlattr *nest; - int vl_idx = 0; - nest = nla_nest_start(skb, LINK_XSTATS_TYPE_BRIDGE); if (!nest) return -EMSGSIZE; - vg = br_vlan_group(br); if (vg) { + u16 pvid; + + pvid = br_get_pvid(vg); list_for_each_entry(v, &vg->vlan_list, vlist) { struct bridge_vlan_xstats vxi; struct br_vlan_stats stats; @@ -1311,6 +1330,9 @@ static int bridge_fill_linkxstats(struct sk_buff *skb, continue; memset(&vxi, 0, sizeof(vxi)); vxi.vid = v->vid; + vxi.flags = v->flags; + if (v->vid == pvid) + vxi.flags |= BRIDGE_VLAN_INFO_PVID; br_vlan_get_stats(v, &stats); vxi.rx_bytes = stats.rx_bytes; vxi.rx_packets = stats.rx_packets; @@ -1329,7 +1351,7 @@ static int bridge_fill_linkxstats(struct sk_buff *skb, BRIDGE_XSTATS_PAD); if (!nla) goto nla_put_failure; - br_multicast_get_stats(br, NULL, nla_data(nla)); + br_multicast_get_stats(br, p, nla_data(nla)); } #endif nla_nest_end(skb, nest); @@ -1344,52 +1366,6 @@ nla_put_failure: return -EMSGSIZE; } -static int brport_fill_linkxstats(struct sk_buff *skb, - const struct net_device *dev, - int *prividx) -{ - struct net_bridge_port *p = br_port_get_rtnl(dev); - struct nlattr *nla __maybe_unused; - struct nlattr *nest; - - if (!p) - return 0; - - nest = nla_nest_start(skb, LINK_XSTATS_TYPE_BRIDGE); - if (!nest) - return -EMSGSIZE; -#ifdef CONFIG_BRIDGE_IGMP_SNOOPING - nla = nla_reserve_64bit(skb, BRIDGE_XSTATS_MCAST, - sizeof(struct br_mcast_stats), - BRIDGE_XSTATS_PAD); - if (!nla) { - nla_nest_end(skb, nest); - return -EMSGSIZE; - } - br_multicast_get_stats(p->br, p, nla_data(nla)); -#endif - nla_nest_end(skb, nest); - - return 0; -} - -static int br_fill_linkxstats(struct sk_buff *skb, const struct net_device *dev, - int *prividx, int attr) -{ - int ret = -EINVAL; - - switch (attr) { - case IFLA_STATS_LINK_XSTATS: - ret = bridge_fill_linkxstats(skb, dev, prividx); - break; - case IFLA_STATS_LINK_XSTATS_SLAVE: - ret = brport_fill_linkxstats(skb, dev, prividx); - break; - } - - return ret; -} - static struct rtnl_af_ops br_af_ops __read_mostly = { .family = AF_BRIDGE, .get_link_af_size = br_get_link_af_size_filtered, diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h index aac2a6e6b008..1b63177e0ccd 100644 --- a/net/bridge/br_private.h +++ b/net/bridge/br_private.h @@ -251,6 +251,9 @@ struct net_bridge_port #ifdef CONFIG_BRIDGE_VLAN_FILTERING struct net_bridge_vlan_group __rcu *vlgrp; #endif +#ifdef CONFIG_NET_SWITCHDEV + int offload_fwd_mark; +#endif }; #define br_auto_port(p) ((p)->flags & BR_AUTO_MASK) @@ -359,6 +362,11 @@ struct net_bridge struct timer_list gc_timer; struct kobject *ifobj; u32 auto_cnt; + +#ifdef CONFIG_NET_SWITCHDEV + int offload_fwd_mark; +#endif + #ifdef CONFIG_BRIDGE_VLAN_FILTERING struct net_bridge_vlan_group __rcu *vlgrp; u8 vlan_enabled; @@ -381,6 +389,10 @@ struct br_input_skb_cb { #ifdef CONFIG_BRIDGE_VLAN_FILTERING bool vlan_filtered; #endif + +#ifdef CONFIG_NET_SWITCHDEV + int offload_fwd_mark; +#endif }; #define BR_INPUT_SKB_CB(__skb) ((struct br_input_skb_cb *)(__skb)->cb) @@ -496,7 +508,7 @@ int br_fdb_delete(struct ndmsg *ndm, struct nlattr *tb[], int br_fdb_add(struct ndmsg *nlh, struct nlattr *tb[], struct net_device *dev, const unsigned char *addr, u16 vid, u16 nlh_flags); int br_fdb_dump(struct sk_buff *skb, struct netlink_callback *cb, - struct net_device *dev, struct net_device *fdev, int idx); + struct net_device *dev, struct net_device *fdev, int *idx); int br_fdb_sync_static(struct net_bridge *br, struct net_bridge_port *p); void br_fdb_unsync_static(struct net_bridge *br, struct net_bridge_port *p); int br_fdb_external_learn_add(struct net_bridge *br, struct net_bridge_port *p, @@ -505,12 +517,17 @@ int br_fdb_external_learn_del(struct net_bridge *br, struct net_bridge_port *p, const unsigned char *addr, u16 vid); /* br_forward.c */ +enum br_pkt_type { + BR_PKT_UNICAST, + BR_PKT_MULTICAST, + BR_PKT_BROADCAST +}; int br_dev_queue_push_xmit(struct net *net, struct sock *sk, struct sk_buff *skb); void br_forward(const struct net_bridge_port *to, struct sk_buff *skb, bool local_rcv, bool local_orig); int br_forward_finish(struct net *net, struct sock *sk, struct sk_buff *skb); void br_flood(struct net_bridge *br, struct sk_buff *skb, - bool unicast, bool local_rcv, bool local_orig); + enum br_pkt_type pkt_type, bool local_rcv, bool local_orig); /* br_if.c */ void br_port_carrier_check(struct net_bridge_port *p); @@ -1034,4 +1051,29 @@ static inline int br_sysfs_addbr(struct net_device *dev) { return 0; } static inline void br_sysfs_delbr(struct net_device *dev) { return; } #endif /* CONFIG_SYSFS */ +/* br_switchdev.c */ +#ifdef CONFIG_NET_SWITCHDEV +int nbp_switchdev_mark_set(struct net_bridge_port *p); +void nbp_switchdev_frame_mark(const struct net_bridge_port *p, + struct sk_buff *skb); +bool nbp_switchdev_allowed_egress(const struct net_bridge_port *p, + const struct sk_buff *skb); +#else +static inline int nbp_switchdev_mark_set(struct net_bridge_port *p) +{ + return 0; +} + +static inline void nbp_switchdev_frame_mark(const struct net_bridge_port *p, + struct sk_buff *skb) +{ +} + +static inline bool nbp_switchdev_allowed_egress(const struct net_bridge_port *p, + const struct sk_buff *skb) +{ + return true; +} +#endif /* CONFIG_NET_SWITCHDEV */ + #endif diff --git a/net/bridge/br_switchdev.c b/net/bridge/br_switchdev.c new file mode 100644 index 000000000000..f4097b900de1 --- /dev/null +++ b/net/bridge/br_switchdev.c @@ -0,0 +1,57 @@ +#include <linux/kernel.h> +#include <linux/list.h> +#include <linux/netdevice.h> +#include <linux/rtnetlink.h> +#include <linux/skbuff.h> +#include <net/switchdev.h> + +#include "br_private.h" + +static int br_switchdev_mark_get(struct net_bridge *br, struct net_device *dev) +{ + struct net_bridge_port *p; + + /* dev is yet to be added to the port list. */ + list_for_each_entry(p, &br->port_list, list) { + if (switchdev_port_same_parent_id(dev, p->dev)) + return p->offload_fwd_mark; + } + + return ++br->offload_fwd_mark; +} + +int nbp_switchdev_mark_set(struct net_bridge_port *p) +{ + struct switchdev_attr attr = { + .orig_dev = p->dev, + .id = SWITCHDEV_ATTR_ID_PORT_PARENT_ID, + }; + int err; + + ASSERT_RTNL(); + + err = switchdev_port_attr_get(p->dev, &attr); + if (err) { + if (err == -EOPNOTSUPP) + return 0; + return err; + } + + p->offload_fwd_mark = br_switchdev_mark_get(p->br, p->dev); + + return 0; +} + +void nbp_switchdev_frame_mark(const struct net_bridge_port *p, + struct sk_buff *skb) +{ + if (skb->offload_fwd_mark && !WARN_ON_ONCE(!p->offload_fwd_mark)) + BR_INPUT_SKB_CB(skb)->offload_fwd_mark = p->offload_fwd_mark; +} + +bool nbp_switchdev_allowed_egress(const struct net_bridge_port *p, + const struct sk_buff *skb) +{ + return !skb->offload_fwd_mark || + BR_INPUT_SKB_CB(skb)->offload_fwd_mark != p->offload_fwd_mark; +} diff --git a/net/bridge/br_sysfs_if.c b/net/bridge/br_sysfs_if.c index 1e04d4d44273..e657258e1f2c 100644 --- a/net/bridge/br_sysfs_if.c +++ b/net/bridge/br_sysfs_if.c @@ -171,6 +171,7 @@ BRPORT_ATTR_FLAG(learning, BR_LEARNING); BRPORT_ATTR_FLAG(unicast_flood, BR_FLOOD); BRPORT_ATTR_FLAG(proxyarp, BR_PROXYARP); BRPORT_ATTR_FLAG(proxyarp_wifi, BR_PROXYARP_WIFI); +BRPORT_ATTR_FLAG(multicast_flood, BR_MCAST_FLOOD); #ifdef CONFIG_BRIDGE_IGMP_SNOOPING static ssize_t show_multicast_router(struct net_bridge_port *p, char *buf) diff --git a/net/ceph/mon_client.c b/net/ceph/mon_client.c index c83326c5ba58..ef34a02719d7 100644 --- a/net/ceph/mon_client.c +++ b/net/ceph/mon_client.c @@ -574,7 +574,7 @@ static void complete_generic_request(struct ceph_mon_generic_request *req) put_generic_request(req); } -void cancel_generic_request(struct ceph_mon_generic_request *req) +static void cancel_generic_request(struct ceph_mon_generic_request *req) { struct ceph_mon_client *monc = req->monc; struct ceph_mon_generic_request *lookup_req; diff --git a/net/ceph/osd_client.c b/net/ceph/osd_client.c index b5ec09612ff7..a97e7b506612 100644 --- a/net/ceph/osd_client.c +++ b/net/ceph/osd_client.c @@ -4220,7 +4220,7 @@ static struct ceph_msg *alloc_msg_with_page_vector(struct ceph_msg_header *hdr) pages = ceph_alloc_page_vector(calc_pages_for(0, data_len), GFP_NOIO); - if (!pages) { + if (IS_ERR(pages)) { ceph_msg_put(m); return NULL; } diff --git a/net/ceph/string_table.c b/net/ceph/string_table.c index ca53c8319209..22fb96efcf34 100644 --- a/net/ceph/string_table.c +++ b/net/ceph/string_table.c @@ -84,12 +84,6 @@ retry: } EXPORT_SYMBOL(ceph_find_or_create_string); -static void ceph_free_string(struct rcu_head *head) -{ - struct ceph_string *cs = container_of(head, struct ceph_string, rcu); - kfree(cs); -} - void ceph_release_string(struct kref *ref) { struct ceph_string *cs = container_of(ref, struct ceph_string, kref); @@ -101,7 +95,7 @@ void ceph_release_string(struct kref *ref) } spin_unlock(&string_tree_lock); - call_rcu(&cs->rcu, ceph_free_string); + kfree_rcu(cs, rcu); } EXPORT_SYMBOL(ceph_release_string); diff --git a/net/core/dev.c b/net/core/dev.c index 936ea0054f57..34b5322bc081 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -3355,16 +3355,6 @@ static int __dev_queue_xmit(struct sk_buff *skb, void *accel_priv) else skb_dst_force(skb); -#ifdef CONFIG_NET_SWITCHDEV - /* Don't forward if offload device already forwarded */ - if (skb->offload_fwd_mark && - skb->offload_fwd_mark == dev->offload_fwd_mark) { - consume_skb(skb); - rc = NET_XMIT_SUCCESS; - goto out; - } -#endif - txq = netdev_pick_tx(dev, skb, accel_priv); q = rcu_dereference_bh(txq->qdisc); @@ -4292,32 +4282,53 @@ int netif_receive_skb(struct sk_buff *skb) } EXPORT_SYMBOL(netif_receive_skb); -/* Network device is going away, flush any packets still pending - * Called with irqs disabled. - */ -static void flush_backlog(void *arg) +DEFINE_PER_CPU(struct work_struct, flush_works); + +/* Network device is going away, flush any packets still pending */ +static void flush_backlog(struct work_struct *work) { - struct net_device *dev = arg; - struct softnet_data *sd = this_cpu_ptr(&softnet_data); struct sk_buff *skb, *tmp; + struct softnet_data *sd; + local_bh_disable(); + sd = this_cpu_ptr(&softnet_data); + + local_irq_disable(); rps_lock(sd); skb_queue_walk_safe(&sd->input_pkt_queue, skb, tmp) { - if (skb->dev == dev) { + if (skb->dev->reg_state == NETREG_UNREGISTERING) { __skb_unlink(skb, &sd->input_pkt_queue); kfree_skb(skb); input_queue_head_incr(sd); } } rps_unlock(sd); + local_irq_enable(); skb_queue_walk_safe(&sd->process_queue, skb, tmp) { - if (skb->dev == dev) { + if (skb->dev->reg_state == NETREG_UNREGISTERING) { __skb_unlink(skb, &sd->process_queue); kfree_skb(skb); input_queue_head_incr(sd); } } + local_bh_enable(); +} + +static void flush_all_backlogs(void) +{ + unsigned int cpu; + + get_online_cpus(); + + for_each_online_cpu(cpu) + queue_work_on(cpu, system_highpri_wq, + per_cpu_ptr(&flush_works, cpu)); + + for_each_online_cpu(cpu) + flush_work(per_cpu_ptr(&flush_works, cpu)); + + put_online_cpus(); } static int napi_gro_complete(struct sk_buff *skb) @@ -4805,8 +4816,9 @@ static bool sd_has_rps_ipi_waiting(struct softnet_data *sd) static int process_backlog(struct napi_struct *napi, int quota) { - int work = 0; struct softnet_data *sd = container_of(napi, struct softnet_data, backlog); + bool again = true; + int work = 0; /* Check if we have pending ipi, its better to send them now, * not waiting net_rx_action() end. @@ -4817,23 +4829,20 @@ static int process_backlog(struct napi_struct *napi, int quota) } napi->weight = weight_p; - local_irq_disable(); - while (1) { + while (again) { struct sk_buff *skb; while ((skb = __skb_dequeue(&sd->process_queue))) { rcu_read_lock(); - local_irq_enable(); __netif_receive_skb(skb); rcu_read_unlock(); - local_irq_disable(); input_queue_head_incr(sd); - if (++work >= quota) { - local_irq_enable(); + if (++work >= quota) return work; - } + } + local_irq_disable(); rps_lock(sd); if (skb_queue_empty(&sd->input_pkt_queue)) { /* @@ -4845,16 +4854,14 @@ static int process_backlog(struct napi_struct *napi, int quota) * and we dont need an smp_mb() memory barrier. */ napi->state = 0; - rps_unlock(sd); - - break; + again = false; + } else { + skb_queue_splice_tail_init(&sd->input_pkt_queue, + &sd->process_queue); } - - skb_queue_splice_tail_init(&sd->input_pkt_queue, - &sd->process_queue); rps_unlock(sd); + local_irq_enable(); } - local_irq_enable(); return work; } @@ -6045,8 +6052,7 @@ void *netdev_lower_dev_get_private(struct net_device *dev, EXPORT_SYMBOL(netdev_lower_dev_get_private); -int dev_get_nest_level(struct net_device *dev, - bool (*type_check)(const struct net_device *dev)) +int dev_get_nest_level(struct net_device *dev) { struct net_device *lower = NULL; struct list_head *iter; @@ -6056,15 +6062,12 @@ int dev_get_nest_level(struct net_device *dev, ASSERT_RTNL(); netdev_for_each_lower_dev(dev, lower, iter) { - nest = dev_get_nest_level(lower, type_check); + nest = dev_get_nest_level(lower); if (max_nest < nest) max_nest = nest; } - if (type_check(dev)) - max_nest++; - - return max_nest; + return max_nest + 1; } EXPORT_SYMBOL(dev_get_nest_level); @@ -6711,8 +6714,8 @@ static void rollback_registered_many(struct list_head *head) unlist_netdevice(dev); dev->reg_state = NETREG_UNREGISTERING; - on_each_cpu(flush_backlog, dev, 1); } + flush_all_backlogs(); synchronize_net(); @@ -8277,8 +8280,11 @@ static int __init net_dev_init(void) */ for_each_possible_cpu(i) { + struct work_struct *flush = per_cpu_ptr(&flush_works, i); struct softnet_data *sd = &per_cpu(softnet_data, i); + INIT_WORK(flush, flush_backlog); + skb_queue_head_init(&sd->input_pkt_queue); skb_queue_head_init(&sd->process_queue); INIT_LIST_HEAD(&sd->poll_list); diff --git a/net/core/drop_monitor.c b/net/core/drop_monitor.c index d6b3b579560d..72cfb0c61125 100644 --- a/net/core/drop_monitor.c +++ b/net/core/drop_monitor.c @@ -105,7 +105,7 @@ static struct sk_buff *reset_per_cpu_data(struct per_cpu_dm_data *data) return skb; } -static struct genl_multicast_group dropmon_mcgrps[] = { +static const struct genl_multicast_group dropmon_mcgrps[] = { { .name = "events", }, }; diff --git a/net/core/filter.c b/net/core/filter.c index b5add4ef0d1d..a83766be1ad2 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -1350,18 +1350,18 @@ struct bpf_scratchpad { static DEFINE_PER_CPU(struct bpf_scratchpad, bpf_sp); +static inline int __bpf_try_make_writable(struct sk_buff *skb, + unsigned int write_len) +{ + return skb_ensure_writable(skb, write_len); +} + static inline int bpf_try_make_writable(struct sk_buff *skb, unsigned int write_len) { - int err; + int err = __bpf_try_make_writable(skb, write_len); - if (!skb_cloned(skb)) - return 0; - if (skb_clone_writable(skb, write_len)) - return 0; - err = pskb_expand_head(skb, 0, 0, GFP_ATOMIC); - if (!err) - bpf_compute_data_end(skb); + bpf_compute_data_end(skb); return err; } @@ -1379,42 +1379,25 @@ static inline void bpf_pull_mac_rcsum(struct sk_buff *skb) static u64 bpf_skb_store_bytes(u64 r1, u64 r2, u64 r3, u64 r4, u64 flags) { - struct bpf_scratchpad *sp = this_cpu_ptr(&bpf_sp); struct sk_buff *skb = (struct sk_buff *) (long) r1; - int offset = (int) r2; + unsigned int offset = (unsigned int) r2; void *from = (void *) (long) r3; unsigned int len = (unsigned int) r4; void *ptr; if (unlikely(flags & ~(BPF_F_RECOMPUTE_CSUM | BPF_F_INVALIDATE_HASH))) return -EINVAL; - - /* bpf verifier guarantees that: - * 'from' pointer points to bpf program stack - * 'len' bytes of it were initialized - * 'len' > 0 - * 'skb' is a valid pointer to 'struct sk_buff' - * - * so check for invalid 'offset' and too large 'len' - */ - if (unlikely((u32) offset > 0xffff || len > sizeof(sp->buff))) + if (unlikely(offset > 0xffff)) return -EFAULT; if (unlikely(bpf_try_make_writable(skb, offset + len))) return -EFAULT; - ptr = skb_header_pointer(skb, offset, len, sp->buff); - if (unlikely(!ptr)) - return -EFAULT; - + ptr = skb->data + offset; if (flags & BPF_F_RECOMPUTE_CSUM) __skb_postpull_rcsum(skb, ptr, len, offset); memcpy(ptr, from, len); - if (ptr == sp->buff) - /* skb_store_bits cannot return -EFAULT here */ - skb_store_bits(skb, offset, ptr, len); - if (flags & BPF_F_RECOMPUTE_CSUM) __skb_postpush_rcsum(skb, ptr, len, offset); if (flags & BPF_F_INVALIDATE_HASH) @@ -1437,12 +1420,12 @@ static const struct bpf_func_proto bpf_skb_store_bytes_proto = { static u64 bpf_skb_load_bytes(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5) { const struct sk_buff *skb = (const struct sk_buff *)(unsigned long) r1; - int offset = (int) r2; + unsigned int offset = (unsigned int) r2; void *to = (void *)(unsigned long) r3; unsigned int len = (unsigned int) r4; void *ptr; - if (unlikely((u32) offset > 0xffff)) + if (unlikely(offset > 0xffff)) goto err_clear; ptr = skb_header_pointer(skb, offset, len, to); @@ -1470,20 +1453,17 @@ static const struct bpf_func_proto bpf_skb_load_bytes_proto = { static u64 bpf_l3_csum_replace(u64 r1, u64 r2, u64 from, u64 to, u64 flags) { struct sk_buff *skb = (struct sk_buff *) (long) r1; - int offset = (int) r2; - __sum16 sum, *ptr; + unsigned int offset = (unsigned int) r2; + __sum16 *ptr; if (unlikely(flags & ~(BPF_F_HDR_FIELD_MASK))) return -EINVAL; - if (unlikely((u32) offset > 0xffff)) + if (unlikely(offset > 0xffff || offset & 1)) return -EFAULT; - if (unlikely(bpf_try_make_writable(skb, offset + sizeof(sum)))) - return -EFAULT; - - ptr = skb_header_pointer(skb, offset, sizeof(sum), &sum); - if (unlikely(!ptr)) + if (unlikely(bpf_try_make_writable(skb, offset + sizeof(*ptr)))) return -EFAULT; + ptr = (__sum16 *)(skb->data + offset); switch (flags & BPF_F_HDR_FIELD_MASK) { case 0: if (unlikely(from != 0)) @@ -1501,10 +1481,6 @@ static u64 bpf_l3_csum_replace(u64 r1, u64 r2, u64 from, u64 to, u64 flags) return -EINVAL; } - if (ptr == &sum) - /* skb_store_bits guaranteed to not return -EFAULT here */ - skb_store_bits(skb, offset, ptr, sizeof(sum)); - return 0; } @@ -1524,20 +1500,18 @@ static u64 bpf_l4_csum_replace(u64 r1, u64 r2, u64 from, u64 to, u64 flags) struct sk_buff *skb = (struct sk_buff *) (long) r1; bool is_pseudo = flags & BPF_F_PSEUDO_HDR; bool is_mmzero = flags & BPF_F_MARK_MANGLED_0; - int offset = (int) r2; - __sum16 sum, *ptr; + unsigned int offset = (unsigned int) r2; + __sum16 *ptr; if (unlikely(flags & ~(BPF_F_MARK_MANGLED_0 | BPF_F_PSEUDO_HDR | BPF_F_HDR_FIELD_MASK))) return -EINVAL; - if (unlikely((u32) offset > 0xffff)) + if (unlikely(offset > 0xffff || offset & 1)) return -EFAULT; - if (unlikely(bpf_try_make_writable(skb, offset + sizeof(sum)))) + if (unlikely(bpf_try_make_writable(skb, offset + sizeof(*ptr)))) return -EFAULT; - ptr = skb_header_pointer(skb, offset, sizeof(sum), &sum); - if (unlikely(!ptr)) - return -EFAULT; + ptr = (__sum16 *)(skb->data + offset); if (is_mmzero && !*ptr) return 0; @@ -1560,10 +1534,6 @@ static u64 bpf_l4_csum_replace(u64 r1, u64 r2, u64 from, u64 to, u64 flags) if (is_mmzero && !*ptr) *ptr = CSUM_MANGLED_0; - if (ptr == &sum) - /* skb_store_bits guaranteed to not return -EFAULT here */ - skb_store_bits(skb, offset, ptr, sizeof(sum)); - return 0; } @@ -2010,8 +1980,8 @@ static u64 bpf_skb_change_type(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5) u32 pkt_type = r2; /* We only allow a restricted subset to be changed for now. */ - if (unlikely(skb->pkt_type > PACKET_OTHERHOST || - pkt_type > PACKET_OTHERHOST)) + if (unlikely(!skb_pkt_type_ok(skb->pkt_type) || + !skb_pkt_type_ok(pkt_type))) return -EINVAL; skb->pkt_type = pkt_type; @@ -2026,6 +1996,92 @@ static const struct bpf_func_proto bpf_skb_change_type_proto = { .arg2_type = ARG_ANYTHING, }; +static u32 __bpf_skb_min_len(const struct sk_buff *skb) +{ + u32 min_len = skb_network_offset(skb); + + if (skb_transport_header_was_set(skb)) + min_len = skb_transport_offset(skb); + if (skb->ip_summed == CHECKSUM_PARTIAL) + min_len = skb_checksum_start_offset(skb) + + skb->csum_offset + sizeof(__sum16); + return min_len; +} + +static u32 __bpf_skb_max_len(const struct sk_buff *skb) +{ + return skb->dev ? skb->dev->mtu + skb->dev->hard_header_len : + 65536; +} + +static int bpf_skb_grow_rcsum(struct sk_buff *skb, unsigned int new_len) +{ + unsigned int old_len = skb->len; + int ret; + + ret = __skb_grow_rcsum(skb, new_len); + if (!ret) + memset(skb->data + old_len, 0, new_len - old_len); + return ret; +} + +static int bpf_skb_trim_rcsum(struct sk_buff *skb, unsigned int new_len) +{ + return __skb_trim_rcsum(skb, new_len); +} + +static u64 bpf_skb_change_tail(u64 r1, u64 r2, u64 flags, u64 r4, u64 r5) +{ + struct sk_buff *skb = (struct sk_buff *)(long) r1; + u32 max_len = __bpf_skb_max_len(skb); + u32 min_len = __bpf_skb_min_len(skb); + u32 new_len = (u32) r2; + int ret; + + if (unlikely(flags || new_len > max_len || new_len < min_len)) + return -EINVAL; + if (skb->encapsulation) + return -ENOTSUPP; + + /* The basic idea of this helper is that it's performing the + * needed work to either grow or trim an skb, and eBPF program + * rewrites the rest via helpers like bpf_skb_store_bytes(), + * bpf_lX_csum_replace() and others rather than passing a raw + * buffer here. This one is a slow path helper and intended + * for replies with control messages. + * + * Like in bpf_skb_change_proto(), we want to keep this rather + * minimal and without protocol specifics so that we are able + * to separate concerns as in bpf_skb_store_bytes() should only + * be the one responsible for writing buffers. + * + * It's really expected to be a slow path operation here for + * control message replies, so we're implicitly linearizing, + * uncloning and drop offloads from the skb by this. + */ + ret = __bpf_try_make_writable(skb, skb->len); + if (!ret) { + if (new_len > skb->len) + ret = bpf_skb_grow_rcsum(skb, new_len); + else if (new_len < skb->len) + ret = bpf_skb_trim_rcsum(skb, new_len); + if (!ret && skb_is_gso(skb)) + skb_gso_reset(skb); + } + + bpf_compute_data_end(skb); + return ret; +} + +static const struct bpf_func_proto bpf_skb_change_tail_proto = { + .func = bpf_skb_change_tail, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_CTX, + .arg2_type = ARG_ANYTHING, + .arg3_type = ARG_ANYTHING, +}; + bool bpf_helper_changes_skb_data(void *func) { if (func == bpf_skb_vlan_push) @@ -2036,6 +2092,8 @@ bool bpf_helper_changes_skb_data(void *func) return true; if (func == bpf_skb_change_proto) return true; + if (func == bpf_skb_change_tail) + return true; if (func == bpf_l3_csum_replace) return true; if (func == bpf_l4_csum_replace) @@ -2316,8 +2374,7 @@ bpf_get_skb_set_tunnel_proto(enum bpf_func_id which) } } -#ifdef CONFIG_SOCK_CGROUP_DATA -static u64 bpf_skb_in_cgroup(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5) +static u64 bpf_skb_under_cgroup(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5) { struct sk_buff *skb = (struct sk_buff *)(long)r1; struct bpf_map *map = (struct bpf_map *)(long)r2; @@ -2337,18 +2394,52 @@ static u64 bpf_skb_in_cgroup(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5) if (unlikely(!cgrp)) return -EAGAIN; - return cgroup_is_descendant(sock_cgroup_ptr(&sk->sk_cgrp_data), cgrp); + return sk_under_cgroup_hierarchy(sk, cgrp); } -static const struct bpf_func_proto bpf_skb_in_cgroup_proto = { - .func = bpf_skb_in_cgroup, +static const struct bpf_func_proto bpf_skb_under_cgroup_proto = { + .func = bpf_skb_under_cgroup, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_CONST_MAP_PTR, .arg3_type = ARG_ANYTHING, }; -#endif + +static unsigned long bpf_xdp_copy(void *dst_buff, const void *src_buff, + unsigned long off, unsigned long len) +{ + memcpy(dst_buff, src_buff + off, len); + return 0; +} + +static u64 bpf_xdp_event_output(u64 r1, u64 r2, u64 flags, u64 r4, + u64 meta_size) +{ + struct xdp_buff *xdp = (struct xdp_buff *)(long) r1; + struct bpf_map *map = (struct bpf_map *)(long) r2; + u64 xdp_size = (flags & BPF_F_CTXLEN_MASK) >> 32; + void *meta = (void *)(long) r4; + + if (unlikely(flags & ~(BPF_F_CTXLEN_MASK | BPF_F_INDEX_MASK))) + return -EINVAL; + if (unlikely(xdp_size > (unsigned long)(xdp->data_end - xdp->data))) + return -EFAULT; + + return bpf_event_output(map, flags, meta, meta_size, xdp, xdp_size, + bpf_xdp_copy); +} + +static const struct bpf_func_proto bpf_xdp_event_output_proto = { + .func = bpf_xdp_event_output, + .gpl_only = true, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_CTX, + .arg2_type = ARG_CONST_MAP_PTR, + .arg3_type = ARG_ANYTHING, + .arg4_type = ARG_PTR_TO_STACK, + .arg5_type = ARG_CONST_STACK_SIZE, +}; static const struct bpf_func_proto * sk_filter_func_proto(enum bpf_func_id func_id) @@ -2402,6 +2493,8 @@ tc_cls_act_func_proto(enum bpf_func_id func_id) return &bpf_skb_change_proto_proto; case BPF_FUNC_skb_change_type: return &bpf_skb_change_type_proto; + case BPF_FUNC_skb_change_tail: + return &bpf_skb_change_tail_proto; case BPF_FUNC_skb_get_tunnel_key: return &bpf_skb_get_tunnel_key_proto; case BPF_FUNC_skb_set_tunnel_key: @@ -2420,10 +2513,8 @@ tc_cls_act_func_proto(enum bpf_func_id func_id) return &bpf_skb_event_output_proto; case BPF_FUNC_get_smp_processor_id: return &bpf_get_smp_processor_id_proto; -#ifdef CONFIG_SOCK_CGROUP_DATA - case BPF_FUNC_skb_in_cgroup: - return &bpf_skb_in_cgroup_proto; -#endif + case BPF_FUNC_skb_under_cgroup: + return &bpf_skb_under_cgroup_proto; default: return sk_filter_func_proto(func_id); } @@ -2432,7 +2523,12 @@ tc_cls_act_func_proto(enum bpf_func_id func_id) static const struct bpf_func_proto * xdp_func_proto(enum bpf_func_id func_id) { - return sk_filter_func_proto(func_id); + switch (func_id) { + case BPF_FUNC_perf_event_output: + return &bpf_xdp_event_output_proto; + default: + return sk_filter_func_proto(func_id); + } } static bool __is_valid_access(int off, int size, enum bpf_access_type type) diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c index 91028ae2fb01..a2879c0f6c4c 100644 --- a/net/core/flow_dissector.c +++ b/net/core/flow_dissector.c @@ -118,13 +118,16 @@ bool __skb_flow_dissect(const struct sk_buff *skb, struct flow_dissector_key_addrs *key_addrs; struct flow_dissector_key_ports *key_ports; struct flow_dissector_key_tags *key_tags; + struct flow_dissector_key_vlan *key_vlan; struct flow_dissector_key_keyid *key_keyid; + bool skip_vlan = false; u8 ip_proto = 0; bool ret = false; if (!data) { data = skb->data; - proto = skb->protocol; + proto = skb_vlan_tag_present(skb) ? + skb->vlan_proto : skb->protocol; nhoff = skb_network_offset(skb); hlen = skb_headlen(skb); } @@ -243,23 +246,45 @@ ipv6: case htons(ETH_P_8021AD): case htons(ETH_P_8021Q): { const struct vlan_hdr *vlan; - struct vlan_hdr _vlan; - vlan = __skb_header_pointer(skb, nhoff, sizeof(_vlan), data, hlen, &_vlan); - if (!vlan) - goto out_bad; + if (skb_vlan_tag_present(skb)) + proto = skb->protocol; + + if (!skb_vlan_tag_present(skb) || + proto == cpu_to_be16(ETH_P_8021Q) || + proto == cpu_to_be16(ETH_P_8021AD)) { + struct vlan_hdr _vlan; + + vlan = __skb_header_pointer(skb, nhoff, sizeof(_vlan), + data, hlen, &_vlan); + if (!vlan) + goto out_bad; + proto = vlan->h_vlan_encapsulated_proto; + nhoff += sizeof(*vlan); + if (skip_vlan) + goto again; + } + skip_vlan = true; if (dissector_uses_key(flow_dissector, - FLOW_DISSECTOR_KEY_VLANID)) { - key_tags = skb_flow_dissector_target(flow_dissector, - FLOW_DISSECTOR_KEY_VLANID, + FLOW_DISSECTOR_KEY_VLAN)) { + key_vlan = skb_flow_dissector_target(flow_dissector, + FLOW_DISSECTOR_KEY_VLAN, target_container); - key_tags->vlan_id = skb_vlan_tag_get_id(skb); + if (skb_vlan_tag_present(skb)) { + key_vlan->vlan_id = skb_vlan_tag_get_id(skb); + key_vlan->vlan_priority = + (skb_vlan_tag_get_prio(skb) >> VLAN_PRIO_SHIFT); + } else { + key_vlan->vlan_id = ntohs(vlan->h_vlan_TCI) & + VLAN_VID_MASK; + key_vlan->vlan_priority = + (ntohs(vlan->h_vlan_TCI) & + VLAN_PRIO_MASK) >> VLAN_PRIO_SHIFT; + } } - proto = vlan->h_vlan_encapsulated_proto; - nhoff += sizeof(*vlan); goto again; } case htons(ETH_P_PPP_SES): { @@ -917,8 +942,8 @@ static const struct flow_dissector_key flow_keys_dissector_keys[] = { .offset = offsetof(struct flow_keys, ports), }, { - .key_id = FLOW_DISSECTOR_KEY_VLANID, - .offset = offsetof(struct flow_keys, tags), + .key_id = FLOW_DISSECTOR_KEY_VLAN, + .offset = offsetof(struct flow_keys, vlan), }, { .key_id = FLOW_DISSECTOR_KEY_FLOW_LABEL, diff --git a/net/core/lwtunnel.c b/net/core/lwtunnel.c index 669ecc9f884e..e5f84c26ba1a 100644 --- a/net/core/lwtunnel.c +++ b/net/core/lwtunnel.c @@ -251,6 +251,41 @@ drop: } EXPORT_SYMBOL(lwtunnel_output); +int lwtunnel_xmit(struct sk_buff *skb) +{ + struct dst_entry *dst = skb_dst(skb); + const struct lwtunnel_encap_ops *ops; + struct lwtunnel_state *lwtstate; + int ret = -EINVAL; + + if (!dst) + goto drop; + + lwtstate = dst->lwtstate; + + if (lwtstate->type == LWTUNNEL_ENCAP_NONE || + lwtstate->type > LWTUNNEL_ENCAP_MAX) + return 0; + + ret = -EOPNOTSUPP; + rcu_read_lock(); + ops = rcu_dereference(lwtun_encaps[lwtstate->type]); + if (likely(ops && ops->xmit)) + ret = ops->xmit(skb); + rcu_read_unlock(); + + if (ret == -EOPNOTSUPP) + goto drop; + + return ret; + +drop: + kfree_skb(skb); + + return ret; +} +EXPORT_SYMBOL(lwtunnel_xmit); + int lwtunnel_input(struct sk_buff *skb) { struct dst_entry *dst = skb_dst(skb); diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c index 2c2eb1b629b1..42bdda0e616b 100644 --- a/net/core/net_namespace.c +++ b/net/core/net_namespace.c @@ -37,6 +37,8 @@ struct net init_net = { }; EXPORT_SYMBOL(init_net); +static bool init_net_initialized; + #define INITIAL_NET_GEN_PTRS 13 /* +1 for len +2 for rcu_head */ static unsigned int max_gen_ptrs = INITIAL_NET_GEN_PTRS; @@ -213,31 +215,29 @@ static void rtnl_net_notifyid(struct net *net, int cmd, int id); */ int peernet2id_alloc(struct net *net, struct net *peer) { - unsigned long flags; bool alloc; int id; - spin_lock_irqsave(&net->nsid_lock, flags); + spin_lock_bh(&net->nsid_lock); alloc = atomic_read(&peer->count) == 0 ? false : true; id = __peernet2id_alloc(net, peer, &alloc); - spin_unlock_irqrestore(&net->nsid_lock, flags); + spin_unlock_bh(&net->nsid_lock); if (alloc && id >= 0) rtnl_net_notifyid(net, RTM_NEWNSID, id); return id; } -EXPORT_SYMBOL(peernet2id_alloc); /* This function returns, if assigned, the id of a peer netns. */ int peernet2id(struct net *net, struct net *peer) { - unsigned long flags; int id; - spin_lock_irqsave(&net->nsid_lock, flags); + spin_lock_bh(&net->nsid_lock); id = __peernet2id(net, peer); - spin_unlock_irqrestore(&net->nsid_lock, flags); + spin_unlock_bh(&net->nsid_lock); return id; } +EXPORT_SYMBOL(peernet2id); /* This function returns true is the peer netns has an id assigned into the * current netns. @@ -249,18 +249,17 @@ bool peernet_has_id(struct net *net, struct net *peer) struct net *get_net_ns_by_id(struct net *net, int id) { - unsigned long flags; struct net *peer; if (id < 0) return NULL; rcu_read_lock(); - spin_lock_irqsave(&net->nsid_lock, flags); + spin_lock_bh(&net->nsid_lock); peer = idr_find(&net->netns_ids, id); if (peer) get_net(peer); - spin_unlock_irqrestore(&net->nsid_lock, flags); + spin_unlock_bh(&net->nsid_lock); rcu_read_unlock(); return peer; @@ -404,17 +403,17 @@ static void cleanup_net(struct work_struct *work) for_each_net(tmp) { int id; - spin_lock_irq(&tmp->nsid_lock); + spin_lock_bh(&tmp->nsid_lock); id = __peernet2id(tmp, net); if (id >= 0) idr_remove(&tmp->netns_ids, id); - spin_unlock_irq(&tmp->nsid_lock); + spin_unlock_bh(&tmp->nsid_lock); if (id >= 0) rtnl_net_notifyid(tmp, RTM_DELNSID, id); } - spin_lock_irq(&net->nsid_lock); + spin_lock_bh(&net->nsid_lock); idr_destroy(&net->netns_ids); - spin_unlock_irq(&net->nsid_lock); + spin_unlock_bh(&net->nsid_lock); } rtnl_unlock(); @@ -531,7 +530,7 @@ static struct pernet_operations __net_initdata net_ns_ops = { .exit = net_ns_net_exit, }; -static struct nla_policy rtnl_net_policy[NETNSA_MAX + 1] = { +static const struct nla_policy rtnl_net_policy[NETNSA_MAX + 1] = { [NETNSA_NONE] = { .type = NLA_UNSPEC }, [NETNSA_NSID] = { .type = NLA_S32 }, [NETNSA_PID] = { .type = NLA_U32 }, @@ -542,7 +541,6 @@ static int rtnl_net_newid(struct sk_buff *skb, struct nlmsghdr *nlh) { struct net *net = sock_net(skb->sk); struct nlattr *tb[NETNSA_MAX + 1]; - unsigned long flags; struct net *peer; int nsid, err; @@ -563,15 +561,15 @@ static int rtnl_net_newid(struct sk_buff *skb, struct nlmsghdr *nlh) if (IS_ERR(peer)) return PTR_ERR(peer); - spin_lock_irqsave(&net->nsid_lock, flags); + spin_lock_bh(&net->nsid_lock); if (__peernet2id(net, peer) >= 0) { - spin_unlock_irqrestore(&net->nsid_lock, flags); + spin_unlock_bh(&net->nsid_lock); err = -EEXIST; goto out; } err = alloc_netid(net, peer, nsid); - spin_unlock_irqrestore(&net->nsid_lock, flags); + spin_unlock_bh(&net->nsid_lock); if (err >= 0) { rtnl_net_notifyid(net, RTM_NEWNSID, err); err = 0; @@ -693,11 +691,10 @@ static int rtnl_net_dumpid(struct sk_buff *skb, struct netlink_callback *cb) .idx = 0, .s_idx = cb->args[0], }; - unsigned long flags; - spin_lock_irqsave(&net->nsid_lock, flags); + spin_lock_bh(&net->nsid_lock); idr_for_each(&net->netns_ids, rtnl_net_dumpid_one, &net_cb); - spin_unlock_irqrestore(&net->nsid_lock, flags); + spin_unlock_bh(&net->nsid_lock); cb->args[0] = net_cb.idx; return skb->len; @@ -750,6 +747,8 @@ static int __init net_ns_init(void) if (setup_net(&init_net, &init_user_ns)) panic("Could not setup the initial network namespace"); + init_net_initialized = true; + rtnl_lock(); list_add_tail_rcu(&init_net.list, &net_namespace_list); rtnl_unlock(); @@ -811,15 +810,24 @@ static void __unregister_pernet_operations(struct pernet_operations *ops) static int __register_pernet_operations(struct list_head *list, struct pernet_operations *ops) { + if (!init_net_initialized) { + list_add_tail(&ops->list, list); + return 0; + } + return ops_init(ops, &init_net); } static void __unregister_pernet_operations(struct pernet_operations *ops) { - LIST_HEAD(net_exit_list); - list_add(&init_net.exit_list, &net_exit_list); - ops_exit_list(ops, &net_exit_list); - ops_free_list(ops, &net_exit_list); + if (!init_net_initialized) { + list_del(&ops->list); + } else { + LIST_HEAD(net_exit_list); + list_add(&init_net.exit_list, &net_exit_list); + ops_exit_list(ops, &net_exit_list); + ops_free_list(ops, &net_exit_list); + } } #endif /* CONFIG_NET_NS */ diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 189cc78c77eb..1dfca1c3f8f5 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -704,6 +704,8 @@ int rtnetlink_put_metrics(struct sk_buff *skb, u32 *metrics) } else if (i == RTAX_FEATURES - 1) { u32 user_features = metrics[i] & RTAX_FEATURE_MASK; + if (!user_features) + continue; BUILD_BUG_ON(RTAX_FEATURE_MASK & DST_FEATURE_MASK); if (nla_put_u32(skb, i + 1, user_features)) goto nla_put_failure; @@ -3066,7 +3068,7 @@ static int nlmsg_populate_fdb(struct sk_buff *skb, seq = cb->nlh->nlmsg_seq; list_for_each_entry(ha, &list->list, list) { - if (*idx < cb->args[0]) + if (*idx < cb->args[2]) goto skip; err = nlmsg_populate_fdb_fill(skb, dev, ha->addr, 0, @@ -3093,19 +3095,18 @@ int ndo_dflt_fdb_dump(struct sk_buff *skb, struct netlink_callback *cb, struct net_device *dev, struct net_device *filter_dev, - int idx) + int *idx) { int err; netif_addr_lock_bh(dev); - err = nlmsg_populate_fdb(skb, cb, dev, &idx, &dev->uc); + err = nlmsg_populate_fdb(skb, cb, dev, idx, &dev->uc); if (err) goto out; - nlmsg_populate_fdb(skb, cb, dev, &idx, &dev->mc); + nlmsg_populate_fdb(skb, cb, dev, idx, &dev->mc); out: netif_addr_unlock_bh(dev); - cb->args[1] = err; - return idx; + return err; } EXPORT_SYMBOL(ndo_dflt_fdb_dump); @@ -3118,9 +3119,13 @@ static int rtnl_fdb_dump(struct sk_buff *skb, struct netlink_callback *cb) const struct net_device_ops *cops = NULL; struct ifinfomsg *ifm = nlmsg_data(cb->nlh); struct net *net = sock_net(skb->sk); + struct hlist_head *head; int brport_idx = 0; int br_idx = 0; - int idx = 0; + int h, s_h; + int idx = 0, s_idx; + int err = 0; + int fidx = 0; if (nlmsg_parse(cb->nlh, sizeof(struct ifinfomsg), tb, IFLA_MAX, ifla_policy) == 0) { @@ -3138,49 +3143,71 @@ static int rtnl_fdb_dump(struct sk_buff *skb, struct netlink_callback *cb) ops = br_dev->netdev_ops; } - cb->args[1] = 0; - for_each_netdev(net, dev) { - if (brport_idx && (dev->ifindex != brport_idx)) - continue; + s_h = cb->args[0]; + s_idx = cb->args[1]; - if (!br_idx) { /* user did not specify a specific bridge */ - if (dev->priv_flags & IFF_BRIDGE_PORT) { - br_dev = netdev_master_upper_dev_get(dev); - cops = br_dev->netdev_ops; - } + for (h = s_h; h < NETDEV_HASHENTRIES; h++, s_idx = 0) { + idx = 0; + head = &net->dev_index_head[h]; + hlist_for_each_entry(dev, head, index_hlist) { - } else { - if (dev != br_dev && - !(dev->priv_flags & IFF_BRIDGE_PORT)) + if (brport_idx && (dev->ifindex != brport_idx)) continue; - if (br_dev != netdev_master_upper_dev_get(dev) && - !(dev->priv_flags & IFF_EBRIDGE)) - continue; + if (!br_idx) { /* user did not specify a specific bridge */ + if (dev->priv_flags & IFF_BRIDGE_PORT) { + br_dev = netdev_master_upper_dev_get(dev); + cops = br_dev->netdev_ops; + } + } else { + if (dev != br_dev && + !(dev->priv_flags & IFF_BRIDGE_PORT)) + continue; - cops = ops; - } + if (br_dev != netdev_master_upper_dev_get(dev) && + !(dev->priv_flags & IFF_EBRIDGE)) + continue; + cops = ops; + } - if (dev->priv_flags & IFF_BRIDGE_PORT) { - if (cops && cops->ndo_fdb_dump) - idx = cops->ndo_fdb_dump(skb, cb, br_dev, dev, - idx); - } - if (cb->args[1] == -EMSGSIZE) - break; + if (idx < s_idx) + goto cont; - if (dev->netdev_ops->ndo_fdb_dump) - idx = dev->netdev_ops->ndo_fdb_dump(skb, cb, dev, NULL, - idx); - else - idx = ndo_dflt_fdb_dump(skb, cb, dev, NULL, idx); - if (cb->args[1] == -EMSGSIZE) - break; + if (dev->priv_flags & IFF_BRIDGE_PORT) { + if (cops && cops->ndo_fdb_dump) { + err = cops->ndo_fdb_dump(skb, cb, + br_dev, dev, + &fidx); + if (err == -EMSGSIZE) + goto out; + } + } - cops = NULL; + if (dev->netdev_ops->ndo_fdb_dump) + err = dev->netdev_ops->ndo_fdb_dump(skb, cb, + dev, NULL, + &fidx); + else + err = ndo_dflt_fdb_dump(skb, cb, dev, NULL, + &fidx); + if (err == -EMSGSIZE) + goto out; + + cops = NULL; + + /* reset fdb offset to 0 for rest of the interfaces */ + cb->args[2] = 0; + fidx = 0; +cont: + idx++; + } } - cb->args[0] = idx; +out: + cb->args[0] = h; + cb->args[1] = idx; + cb->args[2] = fidx; + return skb->len; } diff --git a/net/core/sock.c b/net/core/sock.c index 25dab8b60223..51a730485649 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -1315,24 +1315,6 @@ static void sock_copy(struct sock *nsk, const struct sock *osk) #endif } -void sk_prot_clear_portaddr_nulls(struct sock *sk, int size) -{ - unsigned long nulls1, nulls2; - - nulls1 = offsetof(struct sock, __sk_common.skc_node.next); - nulls2 = offsetof(struct sock, __sk_common.skc_portaddr_node.next); - if (nulls1 > nulls2) - swap(nulls1, nulls2); - - if (nulls1 != 0) - memset((char *)sk, 0, nulls1); - memset((char *)sk + nulls1 + sizeof(void *), 0, - nulls2 - nulls1 - sizeof(void *)); - memset((char *)sk + nulls2 + sizeof(void *), 0, - size - nulls2 - sizeof(void *)); -} -EXPORT_SYMBOL(sk_prot_clear_portaddr_nulls); - static struct sock *sk_prot_alloc(struct proto *prot, gfp_t priority, int family) { @@ -1344,12 +1326,8 @@ static struct sock *sk_prot_alloc(struct proto *prot, gfp_t priority, sk = kmem_cache_alloc(slab, priority & ~__GFP_ZERO); if (!sk) return sk; - if (priority & __GFP_ZERO) { - if (prot->clear_sk) - prot->clear_sk(sk, prot->obj_size); - else - sk_prot_clear_nulls(sk, prot->obj_size); - } + if (priority & __GFP_ZERO) + sk_prot_clear_nulls(sk, prot->obj_size); } else sk = kmalloc(prot->obj_size, priority); diff --git a/net/dsa/dsa.c b/net/dsa/dsa.c index 7e68bc6bc853..d8d267e9a872 100644 --- a/net/dsa/dsa.c +++ b/net/dsa/dsa.c @@ -61,27 +61,27 @@ const struct dsa_device_ops *dsa_device_ops[DSA_TAG_LAST] = { static DEFINE_MUTEX(dsa_switch_drivers_mutex); static LIST_HEAD(dsa_switch_drivers); -void register_switch_driver(struct dsa_switch_driver *drv) +void register_switch_driver(struct dsa_switch_ops *ops) { mutex_lock(&dsa_switch_drivers_mutex); - list_add_tail(&drv->list, &dsa_switch_drivers); + list_add_tail(&ops->list, &dsa_switch_drivers); mutex_unlock(&dsa_switch_drivers_mutex); } EXPORT_SYMBOL_GPL(register_switch_driver); -void unregister_switch_driver(struct dsa_switch_driver *drv) +void unregister_switch_driver(struct dsa_switch_ops *ops) { mutex_lock(&dsa_switch_drivers_mutex); - list_del_init(&drv->list); + list_del_init(&ops->list); mutex_unlock(&dsa_switch_drivers_mutex); } EXPORT_SYMBOL_GPL(unregister_switch_driver); -static struct dsa_switch_driver * +static struct dsa_switch_ops * dsa_switch_probe(struct device *parent, struct device *host_dev, int sw_addr, const char **_name, void **priv) { - struct dsa_switch_driver *ret; + struct dsa_switch_ops *ret; struct list_head *list; const char *name; @@ -90,13 +90,13 @@ dsa_switch_probe(struct device *parent, struct device *host_dev, int sw_addr, mutex_lock(&dsa_switch_drivers_mutex); list_for_each(list, &dsa_switch_drivers) { - struct dsa_switch_driver *drv; + struct dsa_switch_ops *ops; - drv = list_entry(list, struct dsa_switch_driver, list); + ops = list_entry(list, struct dsa_switch_ops, list); - name = drv->probe(parent, host_dev, sw_addr, priv); + name = ops->probe(parent, host_dev, sw_addr, priv); if (name != NULL) { - ret = drv; + ret = ops; break; } } @@ -117,7 +117,7 @@ static ssize_t temp1_input_show(struct device *dev, struct dsa_switch *ds = dev_get_drvdata(dev); int temp, ret; - ret = ds->drv->get_temp(ds, &temp); + ret = ds->ops->get_temp(ds, &temp); if (ret < 0) return ret; @@ -131,7 +131,7 @@ static ssize_t temp1_max_show(struct device *dev, struct dsa_switch *ds = dev_get_drvdata(dev); int temp, ret; - ret = ds->drv->get_temp_limit(ds, &temp); + ret = ds->ops->get_temp_limit(ds, &temp); if (ret < 0) return ret; @@ -149,7 +149,7 @@ static ssize_t temp1_max_store(struct device *dev, if (ret < 0) return ret; - ret = ds->drv->set_temp_limit(ds, DIV_ROUND_CLOSEST(temp, 1000)); + ret = ds->ops->set_temp_limit(ds, DIV_ROUND_CLOSEST(temp, 1000)); if (ret < 0) return ret; @@ -164,7 +164,7 @@ static ssize_t temp1_max_alarm_show(struct device *dev, bool alarm; int ret; - ret = ds->drv->get_temp_alarm(ds, &alarm); + ret = ds->ops->get_temp_alarm(ds, &alarm); if (ret < 0) return ret; @@ -184,15 +184,15 @@ static umode_t dsa_hwmon_attrs_visible(struct kobject *kobj, { struct device *dev = container_of(kobj, struct device, kobj); struct dsa_switch *ds = dev_get_drvdata(dev); - struct dsa_switch_driver *drv = ds->drv; + struct dsa_switch_ops *ops = ds->ops; umode_t mode = attr->mode; if (index == 1) { - if (!drv->get_temp_limit) + if (!ops->get_temp_limit) mode = 0; - else if (!drv->set_temp_limit) + else if (!ops->set_temp_limit) mode &= ~S_IWUSR; - } else if (index == 2 && !drv->get_temp_alarm) { + } else if (index == 2 && !ops->get_temp_alarm) { mode = 0; } return mode; @@ -228,8 +228,8 @@ int dsa_cpu_dsa_setup(struct dsa_switch *ds, struct device *dev, genphy_config_init(phydev); genphy_read_status(phydev); - if (ds->drv->adjust_link) - ds->drv->adjust_link(ds, port, phydev); + if (ds->ops->adjust_link) + ds->ops->adjust_link(ds, port, phydev); } return 0; @@ -303,7 +303,7 @@ void dsa_cpu_port_ethtool_restore(struct dsa_switch *ds) static int dsa_switch_setup_one(struct dsa_switch *ds, struct device *parent) { - struct dsa_switch_driver *drv = ds->drv; + struct dsa_switch_ops *ops = ds->ops; struct dsa_switch_tree *dst = ds->dst; struct dsa_chip_data *cd = ds->cd; bool valid_name_found = false; @@ -354,7 +354,10 @@ static int dsa_switch_setup_one(struct dsa_switch *ds, struct device *parent) * switch. */ if (dst->cpu_switch == index) { - dst->tag_ops = dsa_resolve_tag_protocol(drv->tag_protocol); + enum dsa_tag_protocol tag_protocol; + + tag_protocol = ops->get_tag_protocol(ds); + dst->tag_ops = dsa_resolve_tag_protocol(tag_protocol); if (IS_ERR(dst->tag_ops)) { ret = PTR_ERR(dst->tag_ops); goto out; @@ -368,15 +371,15 @@ static int dsa_switch_setup_one(struct dsa_switch *ds, struct device *parent) /* * Do basic register setup. */ - ret = drv->setup(ds); + ret = ops->setup(ds); if (ret < 0) goto out; - ret = drv->set_addr(ds, dst->master_netdev->dev_addr); + ret = ops->set_addr(ds, dst->master_netdev->dev_addr); if (ret < 0) goto out; - if (!ds->slave_mii_bus && drv->phy_read) { + if (!ds->slave_mii_bus && ops->phy_read) { ds->slave_mii_bus = devm_mdiobus_alloc(parent); if (!ds->slave_mii_bus) { ret = -ENOMEM; @@ -423,7 +426,7 @@ static int dsa_switch_setup_one(struct dsa_switch *ds, struct device *parent) * register with hardware monitoring subsystem. * Treat registration error as non-fatal and ignore it. */ - if (drv->get_temp) { + if (ops->get_temp) { const char *netname = netdev_name(dst->master_netdev); char hname[IFNAMSIZ + 1]; int i, j; @@ -454,7 +457,7 @@ dsa_switch_setup(struct dsa_switch_tree *dst, int index, struct device *parent, struct device *host_dev) { struct dsa_chip_data *cd = dst->pd->chip + index; - struct dsa_switch_driver *drv; + struct dsa_switch_ops *ops; struct dsa_switch *ds; int ret; const char *name; @@ -463,8 +466,8 @@ dsa_switch_setup(struct dsa_switch_tree *dst, int index, /* * Probe for switch model. */ - drv = dsa_switch_probe(parent, host_dev, cd->sw_addr, &name, &priv); - if (drv == NULL) { + ops = dsa_switch_probe(parent, host_dev, cd->sw_addr, &name, &priv); + if (!ops) { netdev_err(dst->master_netdev, "[%d]: could not detect attached switch\n", index); return ERR_PTR(-EINVAL); @@ -483,7 +486,7 @@ dsa_switch_setup(struct dsa_switch_tree *dst, int index, ds->dst = dst; ds->index = index; ds->cd = cd; - ds->drv = drv; + ds->ops = ops; ds->priv = priv; ds->dev = parent; @@ -538,12 +541,12 @@ static void dsa_switch_destroy(struct dsa_switch *ds) ds->dsa_port_mask |= ~(1 << port); } - if (ds->slave_mii_bus && ds->drv->phy_read) + if (ds->slave_mii_bus && ds->ops->phy_read) mdiobus_unregister(ds->slave_mii_bus); } #ifdef CONFIG_PM_SLEEP -static int dsa_switch_suspend(struct dsa_switch *ds) +int dsa_switch_suspend(struct dsa_switch *ds) { int i, ret = 0; @@ -557,18 +560,19 @@ static int dsa_switch_suspend(struct dsa_switch *ds) return ret; } - if (ds->drv->suspend) - ret = ds->drv->suspend(ds); + if (ds->ops->suspend) + ret = ds->ops->suspend(ds); return ret; } +EXPORT_SYMBOL_GPL(dsa_switch_suspend); -static int dsa_switch_resume(struct dsa_switch *ds) +int dsa_switch_resume(struct dsa_switch *ds) { int i, ret = 0; - if (ds->drv->resume) - ret = ds->drv->resume(ds); + if (ds->ops->resume) + ret = ds->ops->resume(ds); if (ret) return ret; @@ -585,6 +589,7 @@ static int dsa_switch_resume(struct dsa_switch *ds) return 0; } +EXPORT_SYMBOL_GPL(dsa_switch_resume); #endif /* platform driver init and cleanup *****************************************/ @@ -1086,7 +1091,6 @@ static int dsa_resume(struct device *d) static SIMPLE_DEV_PM_OPS(dsa_pm_ops, dsa_suspend, dsa_resume); static const struct of_device_id dsa_of_match_table[] = { - { .compatible = "brcm,bcm7445-switch-v4.0" }, { .compatible = "marvell,dsa", }, {} }; diff --git a/net/dsa/dsa2.c b/net/dsa/dsa2.c index f30bad9678f0..8278385dcd21 100644 --- a/net/dsa/dsa2.c +++ b/net/dsa/dsa2.c @@ -294,25 +294,25 @@ static int dsa_ds_apply(struct dsa_switch_tree *dst, struct dsa_switch *ds) int err; /* Initialize ds->phys_mii_mask before registering the slave MDIO bus - * driver and before drv->setup() has run, since the switch drivers and + * driver and before ops->setup() has run, since the switch drivers and * the slave MDIO bus driver rely on these values for probing PHY * devices or not */ ds->phys_mii_mask = ds->enabled_port_mask; - err = ds->drv->setup(ds); + err = ds->ops->setup(ds); if (err < 0) return err; - err = ds->drv->set_addr(ds, dst->master_netdev->dev_addr); + err = ds->ops->set_addr(ds, dst->master_netdev->dev_addr); if (err < 0) return err; - err = ds->drv->set_addr(ds, dst->master_netdev->dev_addr); + err = ds->ops->set_addr(ds, dst->master_netdev->dev_addr); if (err < 0) return err; - if (!ds->slave_mii_bus && ds->drv->phy_read) { + if (!ds->slave_mii_bus && ds->ops->phy_read) { ds->slave_mii_bus = devm_mdiobus_alloc(ds->dev); if (!ds->slave_mii_bus) return -ENOMEM; @@ -374,7 +374,7 @@ static void dsa_ds_unapply(struct dsa_switch_tree *dst, struct dsa_switch *ds) dsa_user_port_unapply(port, index, ds); } - if (ds->slave_mii_bus && ds->drv->phy_read) + if (ds->slave_mii_bus && ds->ops->phy_read) mdiobus_unregister(ds->slave_mii_bus); } @@ -443,6 +443,7 @@ static int dsa_cpu_parse(struct device_node *port, u32 index, struct dsa_switch_tree *dst, struct dsa_switch *ds) { + enum dsa_tag_protocol tag_protocol; struct net_device *ethernet_dev; struct device_node *ethernet; @@ -465,7 +466,8 @@ static int dsa_cpu_parse(struct device_node *port, u32 index, dst->cpu_port = index; } - dst->tag_ops = dsa_resolve_tag_protocol(ds->drv->tag_protocol); + tag_protocol = ds->ops->get_tag_protocol(ds); + dst->tag_ops = dsa_resolve_tag_protocol(tag_protocol); if (IS_ERR(dst->tag_ops)) { dev_warn(ds->dev, "No tagger for this switch\n"); return PTR_ERR(dst->tag_ops); @@ -541,7 +543,7 @@ static int dsa_parse_ports_dn(struct device_node *ports, struct dsa_switch *ds) ds->ports[reg].dn = port; - /* Initialize enabled_port_mask now for drv->setup() + /* Initialize enabled_port_mask now for ops->setup() * to have access to a correct value, just like what * net/dsa/dsa.c::dsa_switch_setup_one does. */ diff --git a/net/dsa/slave.c b/net/dsa/slave.c index fc9196745225..9ecbe787f102 100644 --- a/net/dsa/slave.c +++ b/net/dsa/slave.c @@ -28,7 +28,7 @@ static int dsa_slave_phy_read(struct mii_bus *bus, int addr, int reg) struct dsa_switch *ds = bus->priv; if (ds->phys_mii_mask & (1 << addr)) - return ds->drv->phy_read(ds, addr, reg); + return ds->ops->phy_read(ds, addr, reg); return 0xffff; } @@ -38,7 +38,7 @@ static int dsa_slave_phy_write(struct mii_bus *bus, int addr, int reg, u16 val) struct dsa_switch *ds = bus->priv; if (ds->phys_mii_mask & (1 << addr)) - return ds->drv->phy_write(ds, addr, reg, val); + return ds->ops->phy_write(ds, addr, reg, val); return 0; } @@ -98,14 +98,14 @@ static int dsa_slave_open(struct net_device *dev) goto clear_allmulti; } - if (ds->drv->port_enable) { - err = ds->drv->port_enable(ds, p->port, p->phy); + if (ds->ops->port_enable) { + err = ds->ops->port_enable(ds, p->port, p->phy); if (err) goto clear_promisc; } - if (ds->drv->port_stp_state_set) - ds->drv->port_stp_state_set(ds, p->port, stp_state); + if (ds->ops->port_stp_state_set) + ds->ops->port_stp_state_set(ds, p->port, stp_state); if (p->phy) phy_start(p->phy); @@ -144,11 +144,11 @@ static int dsa_slave_close(struct net_device *dev) if (!ether_addr_equal(dev->dev_addr, master->dev_addr)) dev_uc_del(master, dev->dev_addr); - if (ds->drv->port_disable) - ds->drv->port_disable(ds, p->port, p->phy); + if (ds->ops->port_disable) + ds->ops->port_disable(ds, p->port, p->phy); - if (ds->drv->port_stp_state_set) - ds->drv->port_stp_state_set(ds, p->port, BR_STATE_DISABLED); + if (ds->ops->port_stp_state_set) + ds->ops->port_stp_state_set(ds, p->port, BR_STATE_DISABLED); return 0; } @@ -209,13 +209,13 @@ static int dsa_slave_port_vlan_add(struct net_device *dev, struct dsa_switch *ds = p->parent; if (switchdev_trans_ph_prepare(trans)) { - if (!ds->drv->port_vlan_prepare || !ds->drv->port_vlan_add) + if (!ds->ops->port_vlan_prepare || !ds->ops->port_vlan_add) return -EOPNOTSUPP; - return ds->drv->port_vlan_prepare(ds, p->port, vlan, trans); + return ds->ops->port_vlan_prepare(ds, p->port, vlan, trans); } - ds->drv->port_vlan_add(ds, p->port, vlan, trans); + ds->ops->port_vlan_add(ds, p->port, vlan, trans); return 0; } @@ -226,10 +226,10 @@ static int dsa_slave_port_vlan_del(struct net_device *dev, struct dsa_slave_priv *p = netdev_priv(dev); struct dsa_switch *ds = p->parent; - if (!ds->drv->port_vlan_del) + if (!ds->ops->port_vlan_del) return -EOPNOTSUPP; - return ds->drv->port_vlan_del(ds, p->port, vlan); + return ds->ops->port_vlan_del(ds, p->port, vlan); } static int dsa_slave_port_vlan_dump(struct net_device *dev, @@ -239,8 +239,8 @@ static int dsa_slave_port_vlan_dump(struct net_device *dev, struct dsa_slave_priv *p = netdev_priv(dev); struct dsa_switch *ds = p->parent; - if (ds->drv->port_vlan_dump) - return ds->drv->port_vlan_dump(ds, p->port, vlan, cb); + if (ds->ops->port_vlan_dump) + return ds->ops->port_vlan_dump(ds, p->port, vlan, cb); return -EOPNOTSUPP; } @@ -253,13 +253,13 @@ static int dsa_slave_port_fdb_add(struct net_device *dev, struct dsa_switch *ds = p->parent; if (switchdev_trans_ph_prepare(trans)) { - if (!ds->drv->port_fdb_prepare || !ds->drv->port_fdb_add) + if (!ds->ops->port_fdb_prepare || !ds->ops->port_fdb_add) return -EOPNOTSUPP; - return ds->drv->port_fdb_prepare(ds, p->port, fdb, trans); + return ds->ops->port_fdb_prepare(ds, p->port, fdb, trans); } - ds->drv->port_fdb_add(ds, p->port, fdb, trans); + ds->ops->port_fdb_add(ds, p->port, fdb, trans); return 0; } @@ -271,8 +271,8 @@ static int dsa_slave_port_fdb_del(struct net_device *dev, struct dsa_switch *ds = p->parent; int ret = -EOPNOTSUPP; - if (ds->drv->port_fdb_del) - ret = ds->drv->port_fdb_del(ds, p->port, fdb); + if (ds->ops->port_fdb_del) + ret = ds->ops->port_fdb_del(ds, p->port, fdb); return ret; } @@ -284,8 +284,52 @@ static int dsa_slave_port_fdb_dump(struct net_device *dev, struct dsa_slave_priv *p = netdev_priv(dev); struct dsa_switch *ds = p->parent; - if (ds->drv->port_fdb_dump) - return ds->drv->port_fdb_dump(ds, p->port, fdb, cb); + if (ds->ops->port_fdb_dump) + return ds->ops->port_fdb_dump(ds, p->port, fdb, cb); + + return -EOPNOTSUPP; +} + +static int dsa_slave_port_mdb_add(struct net_device *dev, + const struct switchdev_obj_port_mdb *mdb, + struct switchdev_trans *trans) +{ + struct dsa_slave_priv *p = netdev_priv(dev); + struct dsa_switch *ds = p->parent; + + if (switchdev_trans_ph_prepare(trans)) { + if (!ds->ops->port_mdb_prepare || !ds->ops->port_mdb_add) + return -EOPNOTSUPP; + + return ds->ops->port_mdb_prepare(ds, p->port, mdb, trans); + } + + ds->ops->port_mdb_add(ds, p->port, mdb, trans); + + return 0; +} + +static int dsa_slave_port_mdb_del(struct net_device *dev, + const struct switchdev_obj_port_mdb *mdb) +{ + struct dsa_slave_priv *p = netdev_priv(dev); + struct dsa_switch *ds = p->parent; + + if (ds->ops->port_mdb_del) + return ds->ops->port_mdb_del(ds, p->port, mdb); + + return -EOPNOTSUPP; +} + +static int dsa_slave_port_mdb_dump(struct net_device *dev, + struct switchdev_obj_port_mdb *mdb, + switchdev_obj_dump_cb_t *cb) +{ + struct dsa_slave_priv *p = netdev_priv(dev); + struct dsa_switch *ds = p->parent; + + if (ds->ops->port_mdb_dump) + return ds->ops->port_mdb_dump(ds, p->port, mdb, cb); return -EOPNOTSUPP; } @@ -308,9 +352,9 @@ static int dsa_slave_stp_state_set(struct net_device *dev, struct dsa_switch *ds = p->parent; if (switchdev_trans_ph_prepare(trans)) - return ds->drv->port_stp_state_set ? 0 : -EOPNOTSUPP; + return ds->ops->port_stp_state_set ? 0 : -EOPNOTSUPP; - ds->drv->port_stp_state_set(ds, p->port, attr->u.stp_state); + ds->ops->port_stp_state_set(ds, p->port, attr->u.stp_state); return 0; } @@ -326,8 +370,8 @@ static int dsa_slave_vlan_filtering(struct net_device *dev, if (switchdev_trans_ph_prepare(trans)) return 0; - if (ds->drv->port_vlan_filtering) - return ds->drv->port_vlan_filtering(ds, p->port, + if (ds->ops->port_vlan_filtering) + return ds->ops->port_vlan_filtering(ds, p->port, attr->u.vlan_filtering); return 0; @@ -365,8 +409,8 @@ static int dsa_slave_ageing_time(struct net_device *dev, ds->ports[p->port].ageing_time = ageing_time; ageing_time = dsa_fastest_ageing_time(ds, ageing_time); - if (ds->drv->set_ageing_time) - return ds->drv->set_ageing_time(ds, ageing_time); + if (ds->ops->set_ageing_time) + return ds->ops->set_ageing_time(ds, ageing_time); return 0; } @@ -412,6 +456,10 @@ static int dsa_slave_port_obj_add(struct net_device *dev, SWITCHDEV_OBJ_PORT_FDB(obj), trans); break; + case SWITCHDEV_OBJ_ID_PORT_MDB: + err = dsa_slave_port_mdb_add(dev, SWITCHDEV_OBJ_PORT_MDB(obj), + trans); + break; case SWITCHDEV_OBJ_ID_PORT_VLAN: err = dsa_slave_port_vlan_add(dev, SWITCHDEV_OBJ_PORT_VLAN(obj), @@ -435,6 +483,9 @@ static int dsa_slave_port_obj_del(struct net_device *dev, err = dsa_slave_port_fdb_del(dev, SWITCHDEV_OBJ_PORT_FDB(obj)); break; + case SWITCHDEV_OBJ_ID_PORT_MDB: + err = dsa_slave_port_mdb_del(dev, SWITCHDEV_OBJ_PORT_MDB(obj)); + break; case SWITCHDEV_OBJ_ID_PORT_VLAN: err = dsa_slave_port_vlan_del(dev, SWITCHDEV_OBJ_PORT_VLAN(obj)); @@ -459,6 +510,10 @@ static int dsa_slave_port_obj_dump(struct net_device *dev, SWITCHDEV_OBJ_PORT_FDB(obj), cb); break; + case SWITCHDEV_OBJ_ID_PORT_MDB: + err = dsa_slave_port_mdb_dump(dev, SWITCHDEV_OBJ_PORT_MDB(obj), + cb); + break; case SWITCHDEV_OBJ_ID_PORT_VLAN: err = dsa_slave_port_vlan_dump(dev, SWITCHDEV_OBJ_PORT_VLAN(obj), @@ -481,8 +536,8 @@ static int dsa_slave_bridge_port_join(struct net_device *dev, p->bridge_dev = br; - if (ds->drv->port_bridge_join) - ret = ds->drv->port_bridge_join(ds, p->port, br); + if (ds->ops->port_bridge_join) + ret = ds->ops->port_bridge_join(ds, p->port, br); return ret == -EOPNOTSUPP ? 0 : ret; } @@ -493,16 +548,16 @@ static void dsa_slave_bridge_port_leave(struct net_device *dev) struct dsa_switch *ds = p->parent; - if (ds->drv->port_bridge_leave) - ds->drv->port_bridge_leave(ds, p->port); + if (ds->ops->port_bridge_leave) + ds->ops->port_bridge_leave(ds, p->port); p->bridge_dev = NULL; /* Port left the bridge, put in BR_STATE_DISABLED by the bridge layer, * so allow it to be in BR_STATE_FORWARDING to be kept functional */ - if (ds->drv->port_stp_state_set) - ds->drv->port_stp_state_set(ds, p->port, BR_STATE_FORWARDING); + if (ds->ops->port_stp_state_set) + ds->ops->port_stp_state_set(ds, p->port, BR_STATE_FORWARDING); } static int dsa_slave_port_attr_get(struct net_device *dev, @@ -605,8 +660,8 @@ static int dsa_slave_get_regs_len(struct net_device *dev) struct dsa_slave_priv *p = netdev_priv(dev); struct dsa_switch *ds = p->parent; - if (ds->drv->get_regs_len) - return ds->drv->get_regs_len(ds, p->port); + if (ds->ops->get_regs_len) + return ds->ops->get_regs_len(ds, p->port); return -EOPNOTSUPP; } @@ -617,8 +672,8 @@ dsa_slave_get_regs(struct net_device *dev, struct ethtool_regs *regs, void *_p) struct dsa_slave_priv *p = netdev_priv(dev); struct dsa_switch *ds = p->parent; - if (ds->drv->get_regs) - ds->drv->get_regs(ds, p->port, regs, _p); + if (ds->ops->get_regs) + ds->ops->get_regs(ds, p->port, regs, _p); } static int dsa_slave_nway_reset(struct net_device *dev) @@ -651,8 +706,8 @@ static int dsa_slave_get_eeprom_len(struct net_device *dev) if (ds->cd && ds->cd->eeprom_len) return ds->cd->eeprom_len; - if (ds->drv->get_eeprom_len) - return ds->drv->get_eeprom_len(ds); + if (ds->ops->get_eeprom_len) + return ds->ops->get_eeprom_len(ds); return 0; } @@ -663,8 +718,8 @@ static int dsa_slave_get_eeprom(struct net_device *dev, struct dsa_slave_priv *p = netdev_priv(dev); struct dsa_switch *ds = p->parent; - if (ds->drv->get_eeprom) - return ds->drv->get_eeprom(ds, eeprom, data); + if (ds->ops->get_eeprom) + return ds->ops->get_eeprom(ds, eeprom, data); return -EOPNOTSUPP; } @@ -675,8 +730,8 @@ static int dsa_slave_set_eeprom(struct net_device *dev, struct dsa_slave_priv *p = netdev_priv(dev); struct dsa_switch *ds = p->parent; - if (ds->drv->set_eeprom) - return ds->drv->set_eeprom(ds, eeprom, data); + if (ds->ops->set_eeprom) + return ds->ops->set_eeprom(ds, eeprom, data); return -EOPNOTSUPP; } @@ -694,8 +749,8 @@ static void dsa_slave_get_strings(struct net_device *dev, strncpy(data + len, "tx_bytes", len); strncpy(data + 2 * len, "rx_packets", len); strncpy(data + 3 * len, "rx_bytes", len); - if (ds->drv->get_strings != NULL) - ds->drv->get_strings(ds, p->port, data + 4 * len); + if (ds->ops->get_strings) + ds->ops->get_strings(ds, p->port, data + 4 * len); } } @@ -714,8 +769,8 @@ static void dsa_cpu_port_get_ethtool_stats(struct net_device *dev, dst->master_ethtool_ops.get_ethtool_stats(dev, stats, data); } - if (ds->drv->get_ethtool_stats) - ds->drv->get_ethtool_stats(ds, cpu_port, data + count); + if (ds->ops->get_ethtool_stats) + ds->ops->get_ethtool_stats(ds, cpu_port, data + count); } static int dsa_cpu_port_get_sset_count(struct net_device *dev, int sset) @@ -727,8 +782,8 @@ static int dsa_cpu_port_get_sset_count(struct net_device *dev, int sset) if (dst->master_ethtool_ops.get_sset_count) count += dst->master_ethtool_ops.get_sset_count(dev, sset); - if (sset == ETH_SS_STATS && ds->drv->get_sset_count) - count += ds->drv->get_sset_count(ds); + if (sset == ETH_SS_STATS && ds->ops->get_sset_count) + count += ds->ops->get_sset_count(ds); return count; } @@ -755,14 +810,14 @@ static void dsa_cpu_port_get_strings(struct net_device *dev, dst->master_ethtool_ops.get_strings(dev, stringset, data); } - if (stringset == ETH_SS_STATS && ds->drv->get_strings) { + if (stringset == ETH_SS_STATS && ds->ops->get_strings) { ndata = data + mcount * len; /* This function copies ETH_GSTRINGS_LEN bytes, we will mangle * the output after to prepend our CPU port prefix we * constructed earlier */ - ds->drv->get_strings(ds, cpu_port, ndata); - count = ds->drv->get_sset_count(ds); + ds->ops->get_strings(ds, cpu_port, ndata); + count = ds->ops->get_sset_count(ds); for (i = 0; i < count; i++) { memmove(ndata + (i * len + sizeof(pfx)), ndata + i * len, len - sizeof(pfx)); @@ -782,8 +837,8 @@ static void dsa_slave_get_ethtool_stats(struct net_device *dev, data[1] = dev->stats.tx_bytes; data[2] = dev->stats.rx_packets; data[3] = dev->stats.rx_bytes; - if (ds->drv->get_ethtool_stats != NULL) - ds->drv->get_ethtool_stats(ds, p->port, data + 4); + if (ds->ops->get_ethtool_stats) + ds->ops->get_ethtool_stats(ds, p->port, data + 4); } static int dsa_slave_get_sset_count(struct net_device *dev, int sset) @@ -795,8 +850,8 @@ static int dsa_slave_get_sset_count(struct net_device *dev, int sset) int count; count = 4; - if (ds->drv->get_sset_count != NULL) - count += ds->drv->get_sset_count(ds); + if (ds->ops->get_sset_count) + count += ds->ops->get_sset_count(ds); return count; } @@ -809,8 +864,8 @@ static void dsa_slave_get_wol(struct net_device *dev, struct ethtool_wolinfo *w) struct dsa_slave_priv *p = netdev_priv(dev); struct dsa_switch *ds = p->parent; - if (ds->drv->get_wol) - ds->drv->get_wol(ds, p->port, w); + if (ds->ops->get_wol) + ds->ops->get_wol(ds, p->port, w); } static int dsa_slave_set_wol(struct net_device *dev, struct ethtool_wolinfo *w) @@ -819,8 +874,8 @@ static int dsa_slave_set_wol(struct net_device *dev, struct ethtool_wolinfo *w) struct dsa_switch *ds = p->parent; int ret = -EOPNOTSUPP; - if (ds->drv->set_wol) - ret = ds->drv->set_wol(ds, p->port, w); + if (ds->ops->set_wol) + ret = ds->ops->set_wol(ds, p->port, w); return ret; } @@ -831,10 +886,10 @@ static int dsa_slave_set_eee(struct net_device *dev, struct ethtool_eee *e) struct dsa_switch *ds = p->parent; int ret; - if (!ds->drv->set_eee) + if (!ds->ops->set_eee) return -EOPNOTSUPP; - ret = ds->drv->set_eee(ds, p->port, p->phy, e); + ret = ds->ops->set_eee(ds, p->port, p->phy, e); if (ret) return ret; @@ -850,10 +905,10 @@ static int dsa_slave_get_eee(struct net_device *dev, struct ethtool_eee *e) struct dsa_switch *ds = p->parent; int ret; - if (!ds->drv->get_eee) + if (!ds->ops->get_eee) return -EOPNOTSUPP; - ret = ds->drv->get_eee(ds, p->port, e); + ret = ds->ops->get_eee(ds, p->port, e); if (ret) return ret; @@ -988,8 +1043,8 @@ static void dsa_slave_adjust_link(struct net_device *dev) p->old_pause = p->phy->pause; } - if (ds->drv->adjust_link && status_changed) - ds->drv->adjust_link(ds, p->port, p->phy); + if (ds->ops->adjust_link && status_changed) + ds->ops->adjust_link(ds, p->port, p->phy); if (status_changed) phy_print_status(p->phy); @@ -1004,8 +1059,8 @@ static int dsa_slave_fixed_link_update(struct net_device *dev, if (dev) { p = netdev_priv(dev); ds = p->parent; - if (ds->drv->fixed_link_update) - ds->drv->fixed_link_update(ds, p->port, status); + if (ds->ops->fixed_link_update) + ds->ops->fixed_link_update(ds, p->port, status); } return 0; @@ -1062,8 +1117,8 @@ static int dsa_slave_phy_setup(struct dsa_slave_priv *p, phy_dn = port_dn; } - if (ds->drv->get_phy_flags) - phy_flags = ds->drv->get_phy_flags(ds, p->port); + if (ds->ops->get_phy_flags) + phy_flags = ds->ops->get_phy_flags(ds, p->port); if (phy_dn) { int phy_id = of_mdio_parse_addr(&slave_dev->dev, phy_dn); diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index 55513e654d79..e94b47be0019 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -211,24 +211,19 @@ int inet_listen(struct socket *sock, int backlog) * we can only allow the backlog to be adjusted. */ if (old_state != TCP_LISTEN) { - /* Check special setups for testing purpose to enable TFO w/o - * requiring TCP_FASTOPEN sockopt. + /* Enable TFO w/o requiring TCP_FASTOPEN socket option. * Note that only TCP sockets (SOCK_STREAM) will reach here. - * Also fastopenq may already been allocated because this - * socket was in TCP_LISTEN state previously but was - * shutdown() (rather than close()). + * Also fastopen backlog may already been set via the option + * because the socket was in TCP_LISTEN state previously but + * was shutdown() rather than close(). */ - if ((sysctl_tcp_fastopen & TFO_SERVER_ENABLE) != 0 && + if ((sysctl_tcp_fastopen & TFO_SERVER_WO_SOCKOPT1) && + (sysctl_tcp_fastopen & TFO_SERVER_ENABLE) && !inet_csk(sk)->icsk_accept_queue.fastopenq.max_qlen) { - if ((sysctl_tcp_fastopen & TFO_SERVER_WO_SOCKOPT1) != 0) - fastopen_queue_tune(sk, backlog); - else if ((sysctl_tcp_fastopen & - TFO_SERVER_WO_SOCKOPT2) != 0) - fastopen_queue_tune(sk, - ((uint)sysctl_tcp_fastopen) >> 16); - + fastopen_queue_tune(sk, backlog); tcp_fastopen_init_key_once(true); } + err = inet_csk_listen_start(sk, backlog); if (err) goto out; @@ -921,6 +916,8 @@ const struct proto_ops inet_stream_ops = { .mmap = sock_no_mmap, .sendpage = inet_sendpage, .splice_read = tcp_splice_read, + .read_sock = tcp_read_sock, + .peek_len = tcp_peek_len, #ifdef CONFIG_COMPAT .compat_setsockopt = compat_sock_common_setsockopt, .compat_getsockopt = compat_sock_common_getsockopt, diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c index 539fa264e67d..8066ccc48a17 100644 --- a/net/ipv4/fib_semantics.c +++ b/net/ipv4/fib_semantics.c @@ -1576,7 +1576,8 @@ static bool fib_good_nh(const struct fib_nh *nh) rcu_read_lock_bh(); - n = __ipv4_neigh_lookup_noref(nh->nh_dev, nh->nh_gw); + n = __ipv4_neigh_lookup_noref(nh->nh_dev, + (__force u32)nh->nh_gw); if (n) state = n->nud_state; diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c index febca0f1008c..e2ffc2a5c7db 100644 --- a/net/ipv4/fib_trie.c +++ b/net/ipv4/fib_trie.c @@ -249,7 +249,7 @@ static inline unsigned long get_index(t_key key, struct key_vector *kv) * index into the parent's child array. That is, they will be used to find * 'n' among tp's children. * - * The bits from (n->pos + n->bits) to (tn->pos - 1) - "S" - are skipped bits + * The bits from (n->pos + n->bits) to (tp->pos - 1) - "S" - are skipped bits * for the node n. * * All the bits we have seen so far are significant to the node n. The rest @@ -258,7 +258,7 @@ static inline unsigned long get_index(t_key key, struct key_vector *kv) * The bits from (n->pos) to (n->pos + n->bits - 1) - "C" - are the index into * n's child array, and will of course be different for each child. * - * The rest of the bits, from 0 to (n->pos + n->bits), are completely unknown + * The rest of the bits, from 0 to (n->pos -1) - "u" - are completely unknown * at this point. */ diff --git a/net/ipv4/fou.c b/net/ipv4/fou.c index 321d57f825ce..cf50f7e2b012 100644 --- a/net/ipv4/fou.c +++ b/net/ipv4/fou.c @@ -631,7 +631,7 @@ static struct genl_family fou_nl_family = { .netnsok = true, }; -static struct nla_policy fou_nl_policy[FOU_ATTR_MAX + 1] = { +static const struct nla_policy fou_nl_policy[FOU_ATTR_MAX + 1] = { [FOU_ATTR_PORT] = { .type = NLA_U16, }, [FOU_ATTR_AF] = { .type = NLA_U8, }, [FOU_ATTR_IPPROTO] = { .type = NLA_U8, }, diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c index 38c2c47fe0e8..abfbe492ebfe 100644 --- a/net/ipv4/inet_diag.c +++ b/net/ipv4/inet_diag.c @@ -45,6 +45,7 @@ struct inet_diag_entry { u16 family; u16 userlocks; u32 ifindex; + u32 mark; }; static DEFINE_MUTEX(inet_diag_table_mutex); @@ -580,6 +581,14 @@ static int inet_diag_bc_run(const struct nlattr *_bc, yes = 0; break; } + case INET_DIAG_BC_MARK_COND: { + struct inet_diag_markcond *cond; + + cond = (struct inet_diag_markcond *)(op + 1); + if ((entry->mark & cond->mask) != cond->mark) + yes = 0; + break; + } } if (yes) { @@ -624,6 +633,12 @@ int inet_diag_bc_sk(const struct nlattr *bc, struct sock *sk) entry.dport = ntohs(inet->inet_dport); entry.ifindex = sk->sk_bound_dev_if; entry.userlocks = sk_fullsock(sk) ? sk->sk_userlocks : 0; + if (sk_fullsock(sk)) + entry.mark = sk->sk_mark; + else if (sk->sk_state == TCP_NEW_SYN_RECV) + entry.mark = inet_rsk(inet_reqsk(sk))->ir_mark; + else + entry.mark = 0; return inet_diag_bc_run(bc, &entry); } @@ -706,10 +721,25 @@ static bool valid_port_comparison(const struct inet_diag_bc_op *op, return true; } -static int inet_diag_bc_audit(const void *bytecode, int bytecode_len) +static bool valid_markcond(const struct inet_diag_bc_op *op, int len, + int *min_len) +{ + *min_len += sizeof(struct inet_diag_markcond); + return len >= *min_len; +} + +static int inet_diag_bc_audit(const struct nlattr *attr, + const struct sk_buff *skb) { - const void *bc = bytecode; - int len = bytecode_len; + bool net_admin = netlink_net_capable(skb, CAP_NET_ADMIN); + const void *bytecode, *bc; + int bytecode_len, len; + + if (!attr || nla_len(attr) < sizeof(struct inet_diag_bc_op)) + return -EINVAL; + + bytecode = bc = nla_data(attr); + len = bytecode_len = nla_len(attr); while (len > 0) { int min_len = sizeof(struct inet_diag_bc_op); @@ -732,6 +762,12 @@ static int inet_diag_bc_audit(const void *bytecode, int bytecode_len) if (!valid_port_comparison(bc, len, &min_len)) return -EINVAL; break; + case INET_DIAG_BC_MARK_COND: + if (!net_admin) + return -EPERM; + if (!valid_markcond(bc, len, &min_len)) + return -EINVAL; + break; case INET_DIAG_BC_AUTO: case INET_DIAG_BC_JMP: case INET_DIAG_BC_NOP: @@ -1020,13 +1056,13 @@ static int inet_diag_rcv_msg_compat(struct sk_buff *skb, struct nlmsghdr *nlh) if (nlh->nlmsg_flags & NLM_F_DUMP) { if (nlmsg_attrlen(nlh, hdrlen)) { struct nlattr *attr; + int err; attr = nlmsg_find_attr(nlh, hdrlen, INET_DIAG_REQ_BYTECODE); - if (!attr || - nla_len(attr) < sizeof(struct inet_diag_bc_op) || - inet_diag_bc_audit(nla_data(attr), nla_len(attr))) - return -EINVAL; + err = inet_diag_bc_audit(attr, skb); + if (err) + return err; } { struct netlink_dump_control c = { @@ -1051,13 +1087,13 @@ static int inet_diag_handler_cmd(struct sk_buff *skb, struct nlmsghdr *h) h->nlmsg_flags & NLM_F_DUMP) { if (nlmsg_attrlen(h, hdrlen)) { struct nlattr *attr; + int err; attr = nlmsg_find_attr(h, hdrlen, INET_DIAG_REQ_BYTECODE); - if (!attr || - nla_len(attr) < sizeof(struct inet_diag_bc_op) || - inet_diag_bc_audit(nla_data(attr), nla_len(attr))) - return -EINVAL; + err = inet_diag_bc_audit(attr, skb); + if (err) + return err; } { struct netlink_dump_control c = { diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index 5b1481be0282..113cc43df789 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -370,7 +370,6 @@ static void __gre_xmit(struct sk_buff *skb, struct net_device *dev, tunnel->parms.o_flags, proto, tunnel->parms.o_key, htonl(tunnel->o_seqno)); - skb_set_inner_protocol(skb, proto); ip_tunnel_xmit(skb, dev, tnl_params, tnl_params->protocol); } diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index dde37fb340bf..65569274efb8 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -73,6 +73,7 @@ #include <net/icmp.h> #include <net/checksum.h> #include <net/inetpeer.h> +#include <net/lwtunnel.h> #include <linux/igmp.h> #include <linux/netfilter_ipv4.h> #include <linux/netfilter_bridge.h> @@ -197,6 +198,13 @@ static int ip_finish_output2(struct net *net, struct sock *sk, struct sk_buff *s skb = skb2; } + if (lwtunnel_xmit_redirect(dst->lwtstate)) { + int res = lwtunnel_xmit(skb); + + if (res < 0 || res == LWTUNNEL_XMIT_DONE) + return res; + } + rcu_read_lock_bh(); nexthop = (__force u32) rt_nexthop(rt, ip_hdr(skb)->daddr); neigh = __ipv4_neigh_lookup_noref(dev, nexthop); diff --git a/net/ipv4/ip_tunnel_core.c b/net/ipv4/ip_tunnel_core.c index 9d847c302551..0f227db0e9ac 100644 --- a/net/ipv4/ip_tunnel_core.c +++ b/net/ipv4/ip_tunnel_core.c @@ -73,9 +73,11 @@ void iptunnel_xmit(struct sock *sk, struct rtable *rt, struct sk_buff *skb, skb_dst_set(skb, &rt->dst); memset(IPCB(skb), 0, sizeof(*IPCB(skb))); - if (skb_iif && proto == IPPROTO_UDP) { - /* Arrived from an ingress interface and got udp encapuslated. - * The encapsulated network segment length may exceed dst mtu. + if (skb_iif && !(df & htons(IP_DF))) { + /* Arrived from an ingress interface, got encapsulated, with + * fragmentation of encapulating frames allowed. + * If skb is gso, the resulting encapsulated network segments + * may exceed dst mtu. * Allow IP Fragmentation of segments. */ IPCB(skb)->flags |= IPSKB_FRAG_SEGS; diff --git a/net/ipv4/ip_vti.c b/net/ipv4/ip_vti.c index a917903d5e97..cc701fa70b12 100644 --- a/net/ipv4/ip_vti.c +++ b/net/ipv4/ip_vti.c @@ -557,6 +557,33 @@ static struct rtnl_link_ops vti_link_ops __read_mostly = { .get_link_net = ip_tunnel_get_link_net, }; +static bool is_vti_tunnel(const struct net_device *dev) +{ + return dev->netdev_ops == &vti_netdev_ops; +} + +static int vti_device_event(struct notifier_block *unused, + unsigned long event, void *ptr) +{ + struct net_device *dev = netdev_notifier_info_to_dev(ptr); + struct ip_tunnel *tunnel = netdev_priv(dev); + + if (!is_vti_tunnel(dev)) + return NOTIFY_DONE; + + switch (event) { + case NETDEV_DOWN: + if (!net_eq(tunnel->net, dev_net(dev))) + xfrm_garbage_collect(tunnel->net); + break; + } + return NOTIFY_DONE; +} + +static struct notifier_block vti_notifier_block __read_mostly = { + .notifier_call = vti_device_event, +}; + static int __init vti_init(void) { const char *msg; @@ -564,6 +591,8 @@ static int __init vti_init(void) pr_info("IPv4 over IPsec tunneling driver\n"); + register_netdevice_notifier(&vti_notifier_block); + msg = "tunnel device"; err = register_pernet_device(&vti_net_ops); if (err < 0) @@ -596,6 +625,7 @@ xfrm_proto_ah_failed: xfrm_proto_esp_failed: unregister_pernet_device(&vti_net_ops); pernet_dev_failed: + unregister_netdevice_notifier(&vti_notifier_block); pr_err("vti init: failed to register %s\n", msg); return err; } @@ -607,6 +637,7 @@ static void __exit vti_fini(void) xfrm4_protocol_deregister(&vti_ah4_protocol, IPPROTO_AH); xfrm4_protocol_deregister(&vti_esp4_protocol, IPPROTO_ESP); unregister_pernet_device(&vti_net_ops); + unregister_netdevice_notifier(&vti_notifier_block); } module_init(vti_init); diff --git a/net/ipv4/ipconfig.c b/net/ipv4/ipconfig.c index 66c2fe602810..071a785c65eb 100644 --- a/net/ipv4/ipconfig.c +++ b/net/ipv4/ipconfig.c @@ -306,7 +306,7 @@ static void __init ic_close_devs(void) while ((d = next)) { next = d->next; dev = d->dev; - if (dev != ic_dev->dev && !netdev_uses_dsa(dev)) { + if ((!ic_dev || dev != ic_dev->dev) && !netdev_uses_dsa(dev)) { pr_debug("IP-Config: Downing %s\n", dev->name); dev_change_flags(dev, d->flags); } @@ -1530,12 +1530,14 @@ static int __init ip_auto_config(void) * Close all network devices except the device we've * autoconfigured and set up routes. */ - ic_close_devs(); if (ic_setup_if() < 0 || ic_setup_routes() < 0) - return -1; + err = -1; + else + err = 0; + ic_close_devs(); - return 0; + return err; } late_initcall(ip_auto_config); diff --git a/net/ipv4/proc.c b/net/ipv4/proc.c index 9f665b63a927..1ed015e4bc79 100644 --- a/net/ipv4/proc.c +++ b/net/ipv4/proc.c @@ -257,6 +257,7 @@ static const struct snmp_mib snmp4_net_list[] = { SNMP_MIB_ITEM("TCPSpuriousRTOs", LINUX_MIB_TCPSPURIOUSRTOS), SNMP_MIB_ITEM("TCPMD5NotFound", LINUX_MIB_TCPMD5NOTFOUND), SNMP_MIB_ITEM("TCPMD5Unexpected", LINUX_MIB_TCPMD5UNEXPECTED), + SNMP_MIB_ITEM("TCPMD5Failure", LINUX_MIB_TCPMD5FAILURE), SNMP_MIB_ITEM("TCPSackShifted", LINUX_MIB_SACKSHIFTED), SNMP_MIB_ITEM("TCPSackMerged", LINUX_MIB_SACKMERGED), SNMP_MIB_ITEM("TCPSackShiftFallback", LINUX_MIB_SACKSHIFTFALLBACK), diff --git a/net/ipv4/route.c b/net/ipv4/route.c index a1f2830d8110..3e992783c1d0 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -1246,7 +1246,9 @@ static unsigned int ipv4_mtu(const struct dst_entry *dst) mtu = 576; } - return min_t(unsigned int, mtu, IP_MAX_MTU); + mtu = min_t(unsigned int, mtu, IP_MAX_MTU); + + return mtu - lwtunnel_headroom(dst->lwtstate, mtu); } static struct fib_nh_exception *find_exception(struct fib_nh *nh, __be32 daddr) diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 032a96d78c99..77311a92275c 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -1570,6 +1570,12 @@ int tcp_read_sock(struct sock *sk, read_descriptor_t *desc, } EXPORT_SYMBOL(tcp_read_sock); +int tcp_peek_len(struct socket *sock) +{ + return tcp_inq(sock->sk); +} +EXPORT_SYMBOL(tcp_peek_len); + /* * This routine copies from a sock struct into the user buffer. * @@ -3092,23 +3098,6 @@ struct tcp_md5sig_pool *tcp_get_md5sig_pool(void) } EXPORT_SYMBOL(tcp_get_md5sig_pool); -int tcp_md5_hash_header(struct tcp_md5sig_pool *hp, - const struct tcphdr *th) -{ - struct scatterlist sg; - struct tcphdr hdr; - - /* We are not allowed to change tcphdr, make a local copy */ - memcpy(&hdr, th, sizeof(hdr)); - hdr.check = 0; - - /* options aren't included in the hash */ - sg_init_one(&sg, &hdr, sizeof(hdr)); - ahash_request_set_crypt(hp->md5_req, &sg, NULL, sizeof(hdr)); - return crypto_ahash_update(hp->md5_req); -} -EXPORT_SYMBOL(tcp_md5_hash_header); - int tcp_md5_hash_skb_data(struct tcp_md5sig_pool *hp, const struct sk_buff *skb, unsigned int header_len) { @@ -3193,7 +3182,6 @@ int tcp_abort(struct sock *sk, int err) local_bh_enable(); return 0; } - sock_gen_put(sk); return -EOPNOTSUPP; } @@ -3222,7 +3210,6 @@ int tcp_abort(struct sock *sk, int err) bh_unlock_sock(sk); local_bh_enable(); release_sock(sk); - sock_put(sk); return 0; } EXPORT_SYMBOL_GPL(tcp_abort); diff --git a/net/ipv4/tcp_diag.c b/net/ipv4/tcp_diag.c index 4d610934fb39..a748c74aa8b7 100644 --- a/net/ipv4/tcp_diag.c +++ b/net/ipv4/tcp_diag.c @@ -54,11 +54,16 @@ static int tcp_diag_destroy(struct sk_buff *in_skb, { struct net *net = sock_net(in_skb->sk); struct sock *sk = inet_diag_find_one_icsk(net, &tcp_hashinfo, req); + int err; if (IS_ERR(sk)) return PTR_ERR(sk); - return sock_diag_destroy(sk, ECONNABORTED); + err = sock_diag_destroy(sk, ECONNABORTED); + + sock_gen_put(sk); + + return err; } #endif diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 3ebf45b38bc3..8cd02c0b056c 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -4392,12 +4392,9 @@ static int tcp_try_rmem_schedule(struct sock *sk, struct sk_buff *skb, if (tcp_prune_queue(sk) < 0) return -1; - if (!sk_rmem_schedule(sk, skb, size)) { + while (!sk_rmem_schedule(sk, skb, size)) { if (!tcp_prune_ofo_queue(sk)) return -1; - - if (!sk_rmem_schedule(sk, skb, size)) - return -1; } } return 0; @@ -4874,29 +4871,41 @@ static void tcp_collapse_ofo_queue(struct sock *sk) } /* - * Purge the out-of-order queue. - * Return true if queue was pruned. + * Clean the out-of-order queue to make room. + * We drop high sequences packets to : + * 1) Let a chance for holes to be filled. + * 2) not add too big latencies if thousands of packets sit there. + * (But if application shrinks SO_RCVBUF, we could still end up + * freeing whole queue here) + * + * Return true if queue has shrunk. */ static bool tcp_prune_ofo_queue(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); - bool res = false; + struct sk_buff *skb; - if (!skb_queue_empty(&tp->out_of_order_queue)) { - NET_INC_STATS(sock_net(sk), LINUX_MIB_OFOPRUNED); - __skb_queue_purge(&tp->out_of_order_queue); + if (skb_queue_empty(&tp->out_of_order_queue)) + return false; - /* Reset SACK state. A conforming SACK implementation will - * do the same at a timeout based retransmit. When a connection - * is in a sad state like this, we care only about integrity - * of the connection not performance. - */ - if (tp->rx_opt.sack_ok) - tcp_sack_reset(&tp->rx_opt); + NET_INC_STATS(sock_net(sk), LINUX_MIB_OFOPRUNED); + + while ((skb = __skb_dequeue_tail(&tp->out_of_order_queue)) != NULL) { + tcp_drop(sk, skb); sk_mem_reclaim(sk); - res = true; + if (atomic_read(&sk->sk_rmem_alloc) <= sk->sk_rcvbuf && + !tcp_under_memory_pressure(sk)) + break; } - return res; + + /* Reset SACK state. A conforming SACK implementation will + * do the same at a timeout based retransmit. When a connection + * is in a sad state like this, we care only about integrity + * of the connection not performance. + */ + if (tp->rx_opt.sack_ok) + tcp_sack_reset(&tp->rx_opt); + return true; } /* Reduce allocated memory if we can, trying to get diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 32b048e524d6..a75bf48d7950 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -814,8 +814,14 @@ static void tcp_v4_reqsk_send_ack(const struct sock *sk, struct sk_buff *skb, u32 seq = (sk->sk_state == TCP_LISTEN) ? tcp_rsk(req)->snt_isn + 1 : tcp_sk(sk)->snd_nxt; + /* RFC 7323 2.3 + * The window field (SEG.WND) of every outgoing segment, with the + * exception of <SYN> segments, MUST be right-shifted by + * Rcv.Wind.Shift bits: + */ tcp_v4_send_ack(sock_net(sk), skb, seq, - tcp_rsk(req)->rcv_nxt, req->rsk_rcv_wnd, + tcp_rsk(req)->rcv_nxt, + req->rsk_rcv_wnd >> inet_rsk(req)->rcv_wscale, tcp_time_stamp, req->ts_recent, 0, @@ -1169,6 +1175,7 @@ static bool tcp_v4_inbound_md5_hash(const struct sock *sk, NULL, skb); if (genhash || memcmp(hash_location, newhash, 16) != 0) { + NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPMD5FAILURE); net_info_ratelimited("MD5 Hash failed for (%pI4, %d)->(%pI4, %d)%s\n", &iph->saddr, ntohs(th->source), &iph->daddr, ntohs(th->dest), @@ -1531,6 +1538,34 @@ bool tcp_prequeue(struct sock *sk, struct sk_buff *skb) } EXPORT_SYMBOL(tcp_prequeue); +bool tcp_add_backlog(struct sock *sk, struct sk_buff *skb) +{ + u32 limit = sk->sk_rcvbuf + sk->sk_sndbuf; + + /* Only socket owner can try to collapse/prune rx queues + * to reduce memory overhead, so add a little headroom here. + * Few sockets backlog are possibly concurrently non empty. + */ + limit += 64*1024; + + /* In case all data was pulled from skb frags (in __pskb_pull_tail()), + * we can fix skb->truesize to its real value to avoid future drops. + * This is valid because skb is not yet charged to the socket. + * It has been noticed pure SACK packets were sometimes dropped + * (if cooked by drivers without copybreak feature). + */ + if (!skb->data_len) + skb->truesize = SKB_TRUESIZE(skb_end_offset(skb)); + + if (unlikely(sk_add_backlog(sk, skb, limit))) { + bh_unlock_sock(sk); + __NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPBACKLOGDROP); + return true; + } + return false; +} +EXPORT_SYMBOL(tcp_add_backlog); + /* * From tcp_input.c */ @@ -1602,6 +1637,7 @@ process: sk = req->rsk_listener; if (unlikely(tcp_v4_inbound_md5_hash(sk, skb))) { + sk_drops_add(sk, skb); reqsk_put(req); goto discard_it; } @@ -1660,10 +1696,7 @@ process: if (!sock_owned_by_user(sk)) { if (!tcp_prequeue(sk, skb)) ret = tcp_v4_do_rcv(sk, skb); - } else if (unlikely(sk_add_backlog(sk, skb, - sk->sk_rcvbuf + sk->sk_sndbuf))) { - bh_unlock_sock(sk); - __NET_INC_STATS(net, LINUX_MIB_TCPBACKLOGDROP); + } else if (tcp_add_backlog(sk, skb)) { goto discard_and_relse; } bh_unlock_sock(sk); diff --git a/net/ipv4/tcp_metrics.c b/net/ipv4/tcp_metrics.c index b617826e2477..bf1f3b2b29d1 100644 --- a/net/ipv4/tcp_metrics.c +++ b/net/ipv4/tcp_metrics.c @@ -751,7 +751,7 @@ static struct genl_family tcp_metrics_nl_family = { .netnsok = true, }; -static struct nla_policy tcp_metrics_nl_policy[TCP_METRICS_ATTR_MAX + 1] = { +static const struct nla_policy tcp_metrics_nl_policy[TCP_METRICS_ATTR_MAX + 1] = { [TCP_METRICS_ATTR_ADDR_IPV4] = { .type = NLA_U32, }, [TCP_METRICS_ATTR_ADDR_IPV6] = { .type = NLA_BINARY, .len = sizeof(struct in6_addr), }, diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index bdaef7fd6e47..8b45794eb6b2 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -2776,7 +2776,7 @@ void tcp_xmit_retransmit_queue(struct sock *sk) max_segs = tcp_tso_autosize(sk, tcp_current_mss(sk)); tcp_for_write_queue_from(skb, sk) { - __u8 sacked = TCP_SKB_CB(skb)->sacked; + __u8 sacked; int segs; if (skb == tcp_send_head(sk)) @@ -2788,6 +2788,7 @@ void tcp_xmit_retransmit_queue(struct sock *sk) segs = tp->snd_cwnd - tcp_packets_in_flight(tp); if (segs <= 0) return; + sacked = TCP_SKB_CB(skb)->sacked; /* In case tcp_shift_skb_data() have aggregated large skbs, * we need to make sure not sending too bigs TSO packets */ diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index e61f7cd65d08..058c31286ce1 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -114,6 +114,7 @@ #include <net/busy_poll.h> #include "udp_impl.h" #include <net/sock_reuseport.h> +#include <net/addrconf.h> struct udp_table udp_table __read_mostly; EXPORT_SYMBOL(udp_table); @@ -1182,13 +1183,13 @@ out: * @sk: socket * * Drops all bad checksum frames, until a valid one is found. - * Returns the length of found skb, or 0 if none is found. + * Returns the length of found skb, or -1 if none is found. */ -static unsigned int first_packet_length(struct sock *sk) +static int first_packet_length(struct sock *sk) { struct sk_buff_head list_kill, *rcvq = &sk->sk_receive_queue; struct sk_buff *skb; - unsigned int res; + int res; __skb_queue_head_init(&list_kill); @@ -1203,7 +1204,7 @@ static unsigned int first_packet_length(struct sock *sk) __skb_unlink(skb, rcvq); __skb_queue_tail(&list_kill, skb); } - res = skb ? skb->len : 0; + res = skb ? skb->len : -1; spin_unlock_bh(&rcvq->lock); if (!skb_queue_empty(&list_kill)) { @@ -1232,7 +1233,7 @@ int udp_ioctl(struct sock *sk, int cmd, unsigned long arg) case SIOCINQ: { - unsigned int amount = first_packet_length(sk); + int amount = max_t(int, 0, first_packet_length(sk)); return put_user(amount, (int __user *)arg); } @@ -2184,7 +2185,7 @@ unsigned int udp_poll(struct file *file, struct socket *sock, poll_table *wait) /* Check for false positives due to checksum errors */ if ((mask & POLLRDNORM) && !(file->f_flags & O_NONBLOCK) && - !(sk->sk_shutdown & RCV_SHUTDOWN) && !first_packet_length(sk)) + !(sk->sk_shutdown & RCV_SHUTDOWN) && first_packet_length(sk) == -1) mask &= ~(POLLIN | POLLRDNORM); return mask; @@ -2192,6 +2193,20 @@ unsigned int udp_poll(struct file *file, struct socket *sock, poll_table *wait) } EXPORT_SYMBOL(udp_poll); +int udp_abort(struct sock *sk, int err) +{ + lock_sock(sk); + + sk->sk_err = err; + sk->sk_error_report(sk); + udp_disconnect(sk, 0); + + release_sock(sk); + + return 0; +} +EXPORT_SYMBOL_GPL(udp_abort); + struct proto udp_prot = { .name = "UDP", .owner = THIS_MODULE, @@ -2216,13 +2231,12 @@ struct proto udp_prot = { .sysctl_wmem = &sysctl_udp_wmem_min, .sysctl_rmem = &sysctl_udp_rmem_min, .obj_size = sizeof(struct udp_sock), - .slab_flags = SLAB_DESTROY_BY_RCU, .h.udp_table = &udp_table, #ifdef CONFIG_COMPAT .compat_setsockopt = compat_udp_setsockopt, .compat_getsockopt = compat_udp_getsockopt, #endif - .clear_sk = sk_prot_clear_portaddr_nulls, + .diag_destroy = udp_abort, }; EXPORT_SYMBOL(udp_prot); diff --git a/net/ipv4/udp_diag.c b/net/ipv4/udp_diag.c index 3d5ccf4b1412..8a9f6e535caa 100644 --- a/net/ipv4/udp_diag.c +++ b/net/ipv4/udp_diag.c @@ -165,12 +165,88 @@ static void udp_diag_get_info(struct sock *sk, struct inet_diag_msg *r, r->idiag_wqueue = sk_wmem_alloc_get(sk); } +#ifdef CONFIG_INET_DIAG_DESTROY +static int __udp_diag_destroy(struct sk_buff *in_skb, + const struct inet_diag_req_v2 *req, + struct udp_table *tbl) +{ + struct net *net = sock_net(in_skb->sk); + struct sock *sk; + int err; + + rcu_read_lock(); + + if (req->sdiag_family == AF_INET) + sk = __udp4_lib_lookup(net, + req->id.idiag_dst[0], req->id.idiag_dport, + req->id.idiag_src[0], req->id.idiag_sport, + req->id.idiag_if, tbl, NULL); +#if IS_ENABLED(CONFIG_IPV6) + else if (req->sdiag_family == AF_INET6) { + if (ipv6_addr_v4mapped((struct in6_addr *)req->id.idiag_dst) && + ipv6_addr_v4mapped((struct in6_addr *)req->id.idiag_src)) + sk = __udp4_lib_lookup(net, + req->id.idiag_dst[0], req->id.idiag_dport, + req->id.idiag_src[0], req->id.idiag_sport, + req->id.idiag_if, tbl, NULL); + + else + sk = __udp6_lib_lookup(net, + (struct in6_addr *)req->id.idiag_dst, + req->id.idiag_dport, + (struct in6_addr *)req->id.idiag_src, + req->id.idiag_sport, + req->id.idiag_if, tbl, NULL); + } +#endif + else { + rcu_read_unlock(); + return -EINVAL; + } + + if (sk && !atomic_inc_not_zero(&sk->sk_refcnt)) + sk = NULL; + + rcu_read_unlock(); + + if (!sk) + return -ENOENT; + + if (sock_diag_check_cookie(sk, req->id.idiag_cookie)) { + sock_put(sk); + return -ENOENT; + } + + err = sock_diag_destroy(sk, ECONNABORTED); + + sock_put(sk); + + return err; +} + +static int udp_diag_destroy(struct sk_buff *in_skb, + const struct inet_diag_req_v2 *req) +{ + return __udp_diag_destroy(in_skb, req, &udp_table); +} + +static int udplite_diag_destroy(struct sk_buff *in_skb, + const struct inet_diag_req_v2 *req) +{ + return __udp_diag_destroy(in_skb, req, &udplite_table); +} + +#endif + static const struct inet_diag_handler udp_diag_handler = { .dump = udp_diag_dump, .dump_one = udp_diag_dump_one, .idiag_get_info = udp_diag_get_info, .idiag_type = IPPROTO_UDP, .idiag_info_size = 0, +#ifdef CONFIG_INET_DIAG_DESTROY + .destroy = udp_diag_destroy, +#endif }; static void udplite_diag_dump(struct sk_buff *skb, struct netlink_callback *cb, @@ -192,6 +268,9 @@ static const struct inet_diag_handler udplite_diag_handler = { .idiag_get_info = udp_diag_get_info, .idiag_type = IPPROTO_UDPLITE, .idiag_info_size = 0, +#ifdef CONFIG_INET_DIAG_DESTROY + .destroy = udplite_diag_destroy, +#endif }; static int __init udp_diag_init(void) diff --git a/net/ipv4/udplite.c b/net/ipv4/udplite.c index 3b3efbda48e1..af817158d830 100644 --- a/net/ipv4/udplite.c +++ b/net/ipv4/udplite.c @@ -55,13 +55,11 @@ struct proto udplite_prot = { .unhash = udp_lib_unhash, .get_port = udp_v4_get_port, .obj_size = sizeof(struct udp_sock), - .slab_flags = SLAB_DESTROY_BY_RCU, .h.udp_table = &udplite_table, #ifdef CONFIG_COMPAT .compat_setsockopt = compat_udp_setsockopt, .compat_getsockopt = compat_udp_getsockopt, #endif - .clear_sk = sk_prot_clear_portaddr_nulls, }; EXPORT_SYMBOL(udplite_prot); diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index ab3e796596b1..f418d2eaeddd 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -1872,7 +1872,6 @@ static int addrconf_dad_end(struct inet6_ifaddr *ifp) void addrconf_dad_failure(struct inet6_ifaddr *ifp) { - struct in6_addr addr; struct inet6_dev *idev = ifp->idev; struct net *net = dev_net(ifp->idev->dev); @@ -1934,18 +1933,6 @@ void addrconf_dad_failure(struct inet6_ifaddr *ifp) in6_ifa_put(ifp2); lock_errdad: spin_lock_bh(&ifp->lock); - } else if (idev->cnf.accept_dad > 1 && !idev->cnf.disable_ipv6) { - addr.s6_addr32[0] = htonl(0xfe800000); - addr.s6_addr32[1] = 0; - - if (!ipv6_generate_eui64(addr.s6_addr + 8, idev->dev) && - ipv6_addr_equal(&ifp->addr, &addr)) { - /* DAD failed for link-local based on MAC address */ - idev->cnf.disable_ipv6 = 1; - - pr_info("%s: IPv6 being disabled!\n", - ifp->idev->dev->name); - } } errdad: @@ -3543,7 +3530,7 @@ static int addrconf_ifdown(struct net_device *dev, int how) /* combine the user config with event to determine if permanent * addresses are to be removed from address hash table */ - keep_addr = !(how || _keep_addr <= 0); + keep_addr = !(how || _keep_addr <= 0 || idev->cnf.disable_ipv6); /* Step 2: clear hash table */ for (i = 0; i < IN6_ADDR_HSIZE; i++) { @@ -3599,7 +3586,7 @@ restart: /* re-combine the user config with event to determine if permanent * addresses are to be removed from the interface list */ - keep_addr = (!how && _keep_addr > 0); + keep_addr = (!how && _keep_addr > 0 && !idev->cnf.disable_ipv6); INIT_LIST_HEAD(&del_list); list_for_each_entry_safe(ifa, tmp, &idev->addr_list, if_list) { @@ -3821,6 +3808,7 @@ static void addrconf_dad_work(struct work_struct *w) dad_work); struct inet6_dev *idev = ifp->idev; struct in6_addr mcaddr; + bool disable_ipv6 = false; enum { DAD_PROCESS, @@ -3837,6 +3825,24 @@ static void addrconf_dad_work(struct work_struct *w) } else if (ifp->state == INET6_IFADDR_STATE_ERRDAD) { action = DAD_ABORT; ifp->state = INET6_IFADDR_STATE_POSTDAD; + + if (idev->cnf.accept_dad > 1 && !idev->cnf.disable_ipv6 && + !(ifp->flags & IFA_F_STABLE_PRIVACY)) { + struct in6_addr addr; + + addr.s6_addr32[0] = htonl(0xfe800000); + addr.s6_addr32[1] = 0; + + if (!ipv6_generate_eui64(addr.s6_addr + 8, idev->dev) && + ipv6_addr_equal(&ifp->addr, &addr)) { + /* DAD failed for link-local based on MAC */ + idev->cnf.disable_ipv6 = 1; + + pr_info("%s: IPv6 being disabled!\n", + ifp->idev->dev->name); + disable_ipv6 = true; + } + } } spin_unlock_bh(&ifp->lock); @@ -3845,6 +3851,8 @@ static void addrconf_dad_work(struct work_struct *w) goto out; } else if (action == DAD_ABORT) { addrconf_dad_stop(ifp, 1); + if (disable_ipv6) + addrconf_ifdown(idev->dev, 0); goto out; } diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c index b454055ba625..46ad699937fd 100644 --- a/net/ipv6/af_inet6.c +++ b/net/ipv6/af_inet6.c @@ -545,6 +545,8 @@ const struct proto_ops inet6_stream_ops = { .mmap = sock_no_mmap, .sendpage = inet_sendpage, .splice_read = tcp_splice_read, + .read_sock = tcp_read_sock, + .peek_len = tcp_peek_len, #ifdef CONFIG_COMPAT .compat_setsockopt = compat_sock_common_setsockopt, .compat_getsockopt = compat_sock_common_getsockopt, diff --git a/net/ipv6/calipso.c b/net/ipv6/calipso.c index c53b92c617c5..37ac9de713c6 100644 --- a/net/ipv6/calipso.c +++ b/net/ipv6/calipso.c @@ -952,8 +952,10 @@ calipso_opt_insert(struct ipv6_opt_hdr *hop, memcpy(new, hop, start); ret_val = calipso_genopt((unsigned char *)new, start, buf_len, doi_def, secattr); - if (ret_val < 0) + if (ret_val < 0) { + kfree(new); return ERR_PTR(ret_val); + } buf_len = start + ret_val; /* At this point buf_len aligns to 4n, so (buf_len & 4) pads to 8n */ diff --git a/net/ipv6/ila/ila_common.c b/net/ipv6/ila/ila_common.c index ec9efbcdad35..aba0998ddbfb 100644 --- a/net/ipv6/ila/ila_common.c +++ b/net/ipv6/ila/ila_common.c @@ -172,6 +172,5 @@ static void __exit ila_fini(void) module_init(ila_init); module_exit(ila_fini); -MODULE_ALIAS_RTNL_LWT(ILA); MODULE_AUTHOR("Tom Herbert <tom@herbertland.com>"); MODULE_LICENSE("GPL"); diff --git a/net/ipv6/ila/ila_lwt.c b/net/ipv6/ila/ila_lwt.c index c8314c6b6154..e50c27a93e17 100644 --- a/net/ipv6/ila/ila_lwt.c +++ b/net/ipv6/ila/ila_lwt.c @@ -51,7 +51,7 @@ drop: return -EINVAL; } -static struct nla_policy ila_nl_policy[ILA_ATTR_MAX + 1] = { +static const struct nla_policy ila_nl_policy[ILA_ATTR_MAX + 1] = { [ILA_ATTR_LOCATOR] = { .type = NLA_U64, }, [ILA_ATTR_CSUM_MODE] = { .type = NLA_U8, }, }; diff --git a/net/ipv6/ila/ila_xlat.c b/net/ipv6/ila/ila_xlat.c index e6eca5fdf4c9..e604013dd814 100644 --- a/net/ipv6/ila/ila_xlat.c +++ b/net/ipv6/ila/ila_xlat.c @@ -128,7 +128,7 @@ static struct genl_family ila_nl_family = { .parallel_ops = true, }; -static struct nla_policy ila_nl_policy[ILA_ATTR_MAX + 1] = { +static const struct nla_policy ila_nl_policy[ILA_ATTR_MAX + 1] = { [ILA_ATTR_LOCATOR] = { .type = NLA_U64, }, [ILA_ATTR_LOCATOR_MATCH] = { .type = NLA_U64, }, [ILA_ATTR_IFINDEX] = { .type = NLA_U32, }, diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c index b375b5addb76..397e1ed3daa3 100644 --- a/net/ipv6/ip6_gre.c +++ b/net/ipv6/ip6_gre.c @@ -519,8 +519,6 @@ static netdev_tx_t __gre6_xmit(struct sk_buff *skb, gre_build_header(skb, tunnel->tun_hlen, tunnel->parms.o_flags, protocol, tunnel->parms.o_key, htonl(tunnel->o_seqno)); - skb_set_inner_protocol(skb, protocol); - return ip6_tnl_xmit(skb, dev, dsfield, fl6, encap_limit, pmtu, NEXTHDR_GRE); } diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index 1dfc402d9ad1..993fd9666f1b 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -56,6 +56,7 @@ #include <net/checksum.h> #include <linux/mroute6.h> #include <net/l3mdev.h> +#include <net/lwtunnel.h> static int ip6_finish_output2(struct net *net, struct sock *sk, struct sk_buff *skb) { @@ -104,6 +105,13 @@ static int ip6_finish_output2(struct net *net, struct sock *sk, struct sk_buff * } } + if (lwtunnel_xmit_redirect(dst->lwtstate)) { + int res = lwtunnel_xmit(skb); + + if (res < 0 || res == LWTUNNEL_XMIT_DONE) + return res; + } + rcu_read_lock_bh(); nexthop = rt6_nexthop((struct rt6_info *)dst, &ipv6_hdr(skb)->daddr); neigh = __ipv6_neigh_lookup_noref(dst->dev, nexthop); diff --git a/net/ipv6/ping.c b/net/ipv6/ping.c index fed40d1ec29b..0900352c924c 100644 --- a/net/ipv6/ping.c +++ b/net/ipv6/ping.c @@ -55,7 +55,7 @@ static int ping_v6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) struct icmp6hdr user_icmph; int addr_type; struct in6_addr *daddr; - int iif = 0; + int oif = 0; struct flowi6 fl6; int err; struct dst_entry *dst; @@ -78,25 +78,30 @@ static int ping_v6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) if (u->sin6_family != AF_INET6) { return -EAFNOSUPPORT; } - if (sk->sk_bound_dev_if && - sk->sk_bound_dev_if != u->sin6_scope_id) { - return -EINVAL; - } daddr = &(u->sin6_addr); - iif = u->sin6_scope_id; + if (__ipv6_addr_needs_scope_id(ipv6_addr_type(daddr))) + oif = u->sin6_scope_id; } else { if (sk->sk_state != TCP_ESTABLISHED) return -EDESTADDRREQ; daddr = &sk->sk_v6_daddr; } - if (!iif) - iif = sk->sk_bound_dev_if; + if (!oif) + oif = sk->sk_bound_dev_if; + + if (!oif) + oif = np->sticky_pktinfo.ipi6_ifindex; + + if (!oif && ipv6_addr_is_multicast(daddr)) + oif = np->mcast_oif; + else if (!oif) + oif = np->ucast_oif; addr_type = ipv6_addr_type(daddr); - if (__ipv6_addr_needs_scope_id(addr_type) && !iif) - return -EINVAL; - if (addr_type & IPV6_ADDR_MAPPED) + if ((__ipv6_addr_needs_scope_id(addr_type) && !oif) || + (addr_type & IPV6_ADDR_MAPPED) || + (oif && sk->sk_bound_dev_if && oif != sk->sk_bound_dev_if)) return -EINVAL; /* TODO: use ip6_datagram_send_ctl to get options from cmsg */ @@ -106,16 +111,12 @@ static int ping_v6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) fl6.flowi6_proto = IPPROTO_ICMPV6; fl6.saddr = np->saddr; fl6.daddr = *daddr; + fl6.flowi6_oif = oif; fl6.flowi6_mark = sk->sk_mark; fl6.fl6_icmp_type = user_icmph.icmp6_type; fl6.fl6_icmp_code = user_icmph.icmp6_code; security_sk_classify_flow(sk, flowi6_to_flowi(&fl6)); - if (!fl6.flowi6_oif && ipv6_addr_is_multicast(&fl6.daddr)) - fl6.flowi6_oif = np->mcast_oif; - else if (!fl6.flowi6_oif) - fl6.flowi6_oif = np->ucast_oif; - ipc6.tclass = np->tclass; fl6.flowlabel = ip6_make_flowinfo(ipc6.tclass, fl6.flowlabel); diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 49817555449e..09d43ff11a8d 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -1604,7 +1604,9 @@ static unsigned int ip6_mtu(const struct dst_entry *dst) rcu_read_unlock(); out: - return min_t(unsigned int, mtu, IP6_MAX_MTU); + mtu = min_t(unsigned int, mtu, IP6_MAX_MTU); + + return mtu - lwtunnel_headroom(dst->lwtstate, mtu); } static struct dst_entry *icmp6_dst_gc_list; diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c index 696edeeff8bc..b1cdf8009d29 100644 --- a/net/ipv6/sit.c +++ b/net/ipv6/sit.c @@ -1126,7 +1126,7 @@ static int ipip6_tunnel_update_6rd(struct ip_tunnel *t, } #endif -bool ipip6_valid_ip_proto(u8 ipproto) +static bool ipip6_valid_ip_proto(u8 ipproto) { return ipproto == IPPROTO_IPV6 || ipproto == IPPROTO_IPIP || diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 33df8b8575cc..04529a3d42cb 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -671,6 +671,7 @@ static bool tcp_v6_inbound_md5_hash(const struct sock *sk, NULL, skb); if (genhash || memcmp(hash_location, newhash, 16) != 0) { + NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPMD5FAILURE); net_info_ratelimited("MD5 Hash %s for [%pI6c]:%u->[%pI6c]:%u\n", genhash ? "failed" : "mismatch", &ip6h->saddr, ntohs(th->source), @@ -944,9 +945,15 @@ static void tcp_v6_reqsk_send_ack(const struct sock *sk, struct sk_buff *skb, /* sk->sk_state == TCP_LISTEN -> for regular TCP_SYN_RECV * sk->sk_state == TCP_SYN_RECV -> for Fast Open. */ + /* RFC 7323 2.3 + * The window field (SEG.WND) of every outgoing segment, with the + * exception of <SYN> segments, MUST be right-shifted by + * Rcv.Wind.Shift bits: + */ tcp_v6_send_ack(sk, skb, (sk->sk_state == TCP_LISTEN) ? tcp_rsk(req)->snt_isn + 1 : tcp_sk(sk)->snd_nxt, - tcp_rsk(req)->rcv_nxt, req->rsk_rcv_wnd, + tcp_rsk(req)->rcv_nxt, + req->rsk_rcv_wnd >> inet_rsk(req)->rcv_wscale, tcp_time_stamp, req->ts_recent, sk->sk_bound_dev_if, tcp_v6_md5_do_lookup(sk, &ipv6_hdr(skb)->daddr), 0, 0); @@ -1409,6 +1416,7 @@ process: sk = req->rsk_listener; tcp_v6_fill_cb(skb, hdr, th); if (tcp_v6_inbound_md5_hash(sk, skb)) { + sk_drops_add(sk, skb); reqsk_put(req); goto discard_it; } @@ -1465,10 +1473,7 @@ process: if (!sock_owned_by_user(sk)) { if (!tcp_prequeue(sk, skb)) ret = tcp_v6_do_rcv(sk, skb); - } else if (unlikely(sk_add_backlog(sk, skb, - sk->sk_rcvbuf + sk->sk_sndbuf))) { - bh_unlock_sock(sk); - __NET_INC_STATS(net, LINUX_MIB_TCPBACKLOGDROP); + } else if (tcp_add_backlog(sk, skb)) { goto discard_and_relse; } bh_unlock_sock(sk); @@ -1862,17 +1867,6 @@ void tcp6_proc_exit(struct net *net) } #endif -static void tcp_v6_clear_sk(struct sock *sk, int size) -{ - struct inet_sock *inet = inet_sk(sk); - - /* we do not want to clear pinet6 field, because of RCU lookups */ - sk_prot_clear_nulls(sk, offsetof(struct inet_sock, pinet6)); - - size -= offsetof(struct inet_sock, pinet6) + sizeof(inet->pinet6); - memset(&inet->pinet6 + 1, 0, size); -} - struct proto tcpv6_prot = { .name = "TCPv6", .owner = THIS_MODULE, @@ -1914,7 +1908,6 @@ struct proto tcpv6_prot = { .compat_setsockopt = compat_tcp_setsockopt, .compat_getsockopt = compat_tcp_getsockopt, #endif - .clear_sk = tcp_v6_clear_sk, .diag_destroy = tcp_abort, }; diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 81e2f98b958d..9aa7c1c7a9ce 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -1424,17 +1424,6 @@ void udp6_proc_exit(struct net *net) } #endif /* CONFIG_PROC_FS */ -void udp_v6_clear_sk(struct sock *sk, int size) -{ - struct inet_sock *inet = inet_sk(sk); - - /* we do not want to clear pinet6 field, because of RCU lookups */ - sk_prot_clear_portaddr_nulls(sk, offsetof(struct inet_sock, pinet6)); - - size -= offsetof(struct inet_sock, pinet6) + sizeof(inet->pinet6); - memset(&inet->pinet6 + 1, 0, size); -} - /* ------------------------------------------------------------------------ */ struct proto udpv6_prot = { @@ -1460,13 +1449,12 @@ struct proto udpv6_prot = { .sysctl_wmem = &sysctl_udp_wmem_min, .sysctl_rmem = &sysctl_udp_rmem_min, .obj_size = sizeof(struct udp6_sock), - .slab_flags = SLAB_DESTROY_BY_RCU, .h.udp_table = &udp_table, #ifdef CONFIG_COMPAT .compat_setsockopt = compat_udpv6_setsockopt, .compat_getsockopt = compat_udpv6_getsockopt, #endif - .clear_sk = udp_v6_clear_sk, + .diag_destroy = udp_abort, }; static struct inet_protosw udpv6_protosw = { diff --git a/net/ipv6/udp_impl.h b/net/ipv6/udp_impl.h index 0682c031ccdc..f6eb1ab34f4b 100644 --- a/net/ipv6/udp_impl.h +++ b/net/ipv6/udp_impl.h @@ -29,8 +29,6 @@ int udpv6_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int noblock, int udpv6_queue_rcv_skb(struct sock *sk, struct sk_buff *skb); void udpv6_destroy_sock(struct sock *sk); -void udp_v6_clear_sk(struct sock *sk, int size); - #ifdef CONFIG_PROC_FS int udp6_seq_show(struct seq_file *seq, void *v); #endif diff --git a/net/ipv6/udplite.c b/net/ipv6/udplite.c index 9cf097e206e9..47d0d2b87106 100644 --- a/net/ipv6/udplite.c +++ b/net/ipv6/udplite.c @@ -50,13 +50,11 @@ struct proto udplitev6_prot = { .unhash = udp_lib_unhash, .get_port = udp_v6_get_port, .obj_size = sizeof(struct udp6_sock), - .slab_flags = SLAB_DESTROY_BY_RCU, .h.udp_table = &udplite_table, #ifdef CONFIG_COMPAT .compat_setsockopt = compat_udpv6_setsockopt, .compat_getsockopt = compat_udpv6_getsockopt, #endif - .clear_sk = udp_v6_clear_sk, }; static struct inet_protosw udplite6_protosw = { diff --git a/net/irda/af_irda.c b/net/irda/af_irda.c index 8d2f7c9b491d..db639690c205 100644 --- a/net/irda/af_irda.c +++ b/net/irda/af_irda.c @@ -845,9 +845,6 @@ static int irda_accept(struct socket *sock, struct socket *newsock, int flags) if (sock->state != SS_UNCONNECTED) goto out; - if ((sk = sock->sk) == NULL) - goto out; - err = -EOPNOTSUPP; if ((sk->sk_type != SOCK_STREAM) && (sk->sk_type != SOCK_SEQPACKET) && (sk->sk_type != SOCK_DGRAM)) diff --git a/net/irda/iriap.c b/net/irda/iriap.c index 4a7ae32afa09..1138eaf5c682 100644 --- a/net/irda/iriap.c +++ b/net/irda/iriap.c @@ -185,8 +185,12 @@ struct iriap_cb *iriap_open(__u8 slsap_sel, int mode, void *priv, self->magic = IAS_MAGIC; self->mode = mode; - if (mode == IAS_CLIENT) - iriap_register_lsap(self, slsap_sel, mode); + if (mode == IAS_CLIENT) { + if (iriap_register_lsap(self, slsap_sel, mode)) { + kfree(self); + return NULL; + } + } self->confirm = callback; self->priv = priv; diff --git a/net/kcm/Kconfig b/net/kcm/Kconfig index 5db94d940ecc..87fca36e6c47 100644 --- a/net/kcm/Kconfig +++ b/net/kcm/Kconfig @@ -3,6 +3,7 @@ config AF_KCM tristate "KCM sockets" depends on INET select BPF_SYSCALL + select STREAM_PARSER ---help--- KCM (Kernel Connection Multiplexor) sockets provide a method for multiplexing messages of a message based application diff --git a/net/kcm/kcmproc.c b/net/kcm/kcmproc.c index 16c2e03bd388..bf75c9231cca 100644 --- a/net/kcm/kcmproc.c +++ b/net/kcm/kcmproc.c @@ -155,8 +155,8 @@ static void kcm_format_psock(struct kcm_psock *psock, struct seq_file *seq, seq_printf(seq, " psock-%-5u %-10llu %-16llu %-10llu %-16llu %-8d %-8d %-8d %-8d ", psock->index, - psock->stats.rx_msgs, - psock->stats.rx_bytes, + psock->strp.stats.rx_msgs, + psock->strp.stats.rx_bytes, psock->stats.tx_msgs, psock->stats.tx_bytes, psock->sk->sk_receive_queue.qlen, @@ -170,14 +170,27 @@ static void kcm_format_psock(struct kcm_psock *psock, struct seq_file *seq, if (psock->tx_stopped) seq_puts(seq, "TxStop "); - if (psock->rx_stopped) + if (psock->strp.rx_stopped) seq_puts(seq, "RxStop "); if (psock->tx_kcm) seq_printf(seq, "Rsvd-%d ", psock->tx_kcm->index); - if (psock->ready_rx_msg) - seq_puts(seq, "RdyRx "); + if (!psock->strp.rx_paused && !psock->ready_rx_msg) { + if (psock->sk->sk_receive_queue.qlen) { + if (psock->strp.rx_need_bytes) + seq_printf(seq, "RxWait=%u ", + psock->strp.rx_need_bytes); + else + seq_printf(seq, "RxWait "); + } + } else { + if (psock->strp.rx_paused) + seq_puts(seq, "RxPause "); + + if (psock->ready_rx_msg) + seq_puts(seq, "RdyRx "); + } seq_puts(seq, "\n"); } @@ -275,6 +288,7 @@ static int kcm_stats_seq_show(struct seq_file *seq, void *v) { struct kcm_psock_stats psock_stats; struct kcm_mux_stats mux_stats; + struct strp_aggr_stats strp_stats; struct kcm_mux *mux; struct kcm_psock *psock; struct net *net = seq->private; @@ -282,20 +296,28 @@ static int kcm_stats_seq_show(struct seq_file *seq, void *v) memset(&mux_stats, 0, sizeof(mux_stats)); memset(&psock_stats, 0, sizeof(psock_stats)); + memset(&strp_stats, 0, sizeof(strp_stats)); mutex_lock(&knet->mutex); aggregate_mux_stats(&knet->aggregate_mux_stats, &mux_stats); aggregate_psock_stats(&knet->aggregate_psock_stats, &psock_stats); + aggregate_strp_stats(&knet->aggregate_strp_stats, + &strp_stats); list_for_each_entry_rcu(mux, &knet->mux_list, kcm_mux_list) { spin_lock_bh(&mux->lock); aggregate_mux_stats(&mux->stats, &mux_stats); aggregate_psock_stats(&mux->aggregate_psock_stats, &psock_stats); - list_for_each_entry(psock, &mux->psocks, psock_list) + aggregate_strp_stats(&mux->aggregate_strp_stats, + &strp_stats); + list_for_each_entry(psock, &mux->psocks, psock_list) { aggregate_psock_stats(&psock->stats, &psock_stats); + save_strp_stats(&psock->strp, &strp_stats); + } + spin_unlock_bh(&mux->lock); } @@ -328,7 +350,7 @@ static int kcm_stats_seq_show(struct seq_file *seq, void *v) mux_stats.rx_ready_drops); seq_printf(seq, - "%-8s %-10s %-16s %-10s %-16s %-10s %-10s %-10s %-10s %-10s %-10s %-10s %-10s %-10s\n", + "%-8s %-10s %-16s %-10s %-16s %-10s %-10s %-10s %-10s %-10s %-10s %-10s %-10s %-10s %-10s %-10s\n", "Psock", "RX-Msgs", "RX-Bytes", @@ -337,6 +359,8 @@ static int kcm_stats_seq_show(struct seq_file *seq, void *v) "Reserved", "Unreserved", "RX-Aborts", + "RX-Intr", + "RX-Unrecov", "RX-MemFail", "RX-NeedMor", "RX-BadLen", @@ -345,20 +369,22 @@ static int kcm_stats_seq_show(struct seq_file *seq, void *v) "TX-Aborts"); seq_printf(seq, - "%-8s %-10llu %-16llu %-10llu %-16llu %-10llu %-10llu %-10u %-10u %-10u %-10u %-10u %-10u %-10u\n", + "%-8s %-10llu %-16llu %-10llu %-16llu %-10llu %-10llu %-10u %-10u %-10u %-10u %-10u %-10u %-10u %-10u %-10u\n", "", - psock_stats.rx_msgs, - psock_stats.rx_bytes, + strp_stats.rx_msgs, + strp_stats.rx_bytes, psock_stats.tx_msgs, psock_stats.tx_bytes, psock_stats.reserved, psock_stats.unreserved, - psock_stats.rx_aborts, - psock_stats.rx_mem_fail, - psock_stats.rx_need_more_hdr, - psock_stats.rx_bad_hdr_len, - psock_stats.rx_msg_too_big, - psock_stats.rx_msg_timeouts, + strp_stats.rx_aborts, + strp_stats.rx_interrupted, + strp_stats.rx_unrecov_intr, + strp_stats.rx_mem_fail, + strp_stats.rx_need_more_hdr, + strp_stats.rx_bad_hdr_len, + strp_stats.rx_msg_too_big, + strp_stats.rx_msg_timeouts, psock_stats.tx_aborts); return 0; diff --git a/net/kcm/kcmsock.c b/net/kcm/kcmsock.c index cb39e05b166c..2632ac748371 100644 --- a/net/kcm/kcmsock.c +++ b/net/kcm/kcmsock.c @@ -1,3 +1,13 @@ +/* + * Kernel Connection Multiplexor + * + * Copyright (c) 2016 Tom Herbert <tom@herbertland.com> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 + * as published by the Free Software Foundation. + */ + #include <linux/bpf.h> #include <linux/errno.h> #include <linux/errqueue.h> @@ -16,7 +26,6 @@ #include <net/kcm.h> #include <net/netns/generic.h> #include <net/sock.h> -#include <net/tcp.h> #include <uapi/linux/kcm.h> unsigned int kcm_net_id; @@ -35,38 +44,12 @@ static inline struct kcm_tx_msg *kcm_tx_msg(struct sk_buff *skb) return (struct kcm_tx_msg *)skb->cb; } -static inline struct kcm_rx_msg *kcm_rx_msg(struct sk_buff *skb) -{ - return (struct kcm_rx_msg *)((void *)skb->cb + - offsetof(struct qdisc_skb_cb, data)); -} - static void report_csk_error(struct sock *csk, int err) { csk->sk_err = EPIPE; csk->sk_error_report(csk); } -/* Callback lock held */ -static void kcm_abort_rx_psock(struct kcm_psock *psock, int err, - struct sk_buff *skb) -{ - struct sock *csk = psock->sk; - - /* Unrecoverable error in receive */ - - del_timer(&psock->rx_msg_timer); - - if (psock->rx_stopped) - return; - - psock->rx_stopped = 1; - KCM_STATS_INCR(psock->stats.rx_aborts); - - /* Report an error on the lower socket */ - report_csk_error(csk, err); -} - static void kcm_abort_tx_psock(struct kcm_psock *psock, int err, bool wakeup_kcm) { @@ -109,12 +92,13 @@ static void kcm_abort_tx_psock(struct kcm_psock *psock, int err, static void kcm_update_rx_mux_stats(struct kcm_mux *mux, struct kcm_psock *psock) { - KCM_STATS_ADD(mux->stats.rx_bytes, - psock->stats.rx_bytes - psock->saved_rx_bytes); + STRP_STATS_ADD(mux->stats.rx_bytes, + psock->strp.stats.rx_bytes - + psock->saved_rx_bytes); mux->stats.rx_msgs += - psock->stats.rx_msgs - psock->saved_rx_msgs; - psock->saved_rx_msgs = psock->stats.rx_msgs; - psock->saved_rx_bytes = psock->stats.rx_bytes; + psock->strp.stats.rx_msgs - psock->saved_rx_msgs; + psock->saved_rx_msgs = psock->strp.stats.rx_msgs; + psock->saved_rx_bytes = psock->strp.stats.rx_bytes; } static void kcm_update_tx_mux_stats(struct kcm_mux *mux, @@ -167,11 +151,11 @@ static void kcm_rcv_ready(struct kcm_sock *kcm) */ list_del(&psock->psock_ready_list); psock->ready_rx_msg = NULL; - /* Commit clearing of ready_rx_msg for queuing work */ smp_mb(); - queue_work(kcm_wq, &psock->rx_work); + strp_unpause(&psock->strp); + strp_check_rcv(&psock->strp); } /* Buffer limit is okay now, add to ready list */ @@ -285,6 +269,7 @@ static struct kcm_sock *reserve_rx_kcm(struct kcm_psock *psock, if (list_empty(&mux->kcm_rx_waiters)) { psock->ready_rx_msg = head; + strp_pause(&psock->strp); list_add_tail(&psock->psock_ready_list, &mux->psocks_ready); spin_unlock_bh(&mux->rx_lock); @@ -353,346 +338,60 @@ static void unreserve_rx_kcm(struct kcm_psock *psock, spin_unlock_bh(&mux->rx_lock); } -static void kcm_start_rx_timer(struct kcm_psock *psock) -{ - if (psock->sk->sk_rcvtimeo) - mod_timer(&psock->rx_msg_timer, psock->sk->sk_rcvtimeo); -} - -/* Macro to invoke filter function. */ -#define KCM_RUN_FILTER(prog, ctx) \ - (*prog->bpf_func)(ctx, prog->insnsi) - -/* Lower socket lock held */ -static int kcm_tcp_recv(read_descriptor_t *desc, struct sk_buff *orig_skb, - unsigned int orig_offset, size_t orig_len) -{ - struct kcm_psock *psock = (struct kcm_psock *)desc->arg.data; - struct kcm_rx_msg *rxm; - struct kcm_sock *kcm; - struct sk_buff *head, *skb; - size_t eaten = 0, cand_len; - ssize_t extra; - int err; - bool cloned_orig = false; - - if (psock->ready_rx_msg) - return 0; - - head = psock->rx_skb_head; - if (head) { - /* Message already in progress */ - - rxm = kcm_rx_msg(head); - if (unlikely(rxm->early_eaten)) { - /* Already some number of bytes on the receive sock - * data saved in rx_skb_head, just indicate they - * are consumed. - */ - eaten = orig_len <= rxm->early_eaten ? - orig_len : rxm->early_eaten; - rxm->early_eaten -= eaten; - - return eaten; - } - - if (unlikely(orig_offset)) { - /* Getting data with a non-zero offset when a message is - * in progress is not expected. If it does happen, we - * need to clone and pull since we can't deal with - * offsets in the skbs for a message expect in the head. - */ - orig_skb = skb_clone(orig_skb, GFP_ATOMIC); - if (!orig_skb) { - KCM_STATS_INCR(psock->stats.rx_mem_fail); - desc->error = -ENOMEM; - return 0; - } - if (!pskb_pull(orig_skb, orig_offset)) { - KCM_STATS_INCR(psock->stats.rx_mem_fail); - kfree_skb(orig_skb); - desc->error = -ENOMEM; - return 0; - } - cloned_orig = true; - orig_offset = 0; - } - - if (!psock->rx_skb_nextp) { - /* We are going to append to the frags_list of head. - * Need to unshare the frag_list. - */ - err = skb_unclone(head, GFP_ATOMIC); - if (err) { - KCM_STATS_INCR(psock->stats.rx_mem_fail); - desc->error = err; - return 0; - } - - if (unlikely(skb_shinfo(head)->frag_list)) { - /* We can't append to an sk_buff that already - * has a frag_list. We create a new head, point - * the frag_list of that to the old head, and - * then are able to use the old head->next for - * appending to the message. - */ - if (WARN_ON(head->next)) { - desc->error = -EINVAL; - return 0; - } - - skb = alloc_skb(0, GFP_ATOMIC); - if (!skb) { - KCM_STATS_INCR(psock->stats.rx_mem_fail); - desc->error = -ENOMEM; - return 0; - } - skb->len = head->len; - skb->data_len = head->len; - skb->truesize = head->truesize; - *kcm_rx_msg(skb) = *kcm_rx_msg(head); - psock->rx_skb_nextp = &head->next; - skb_shinfo(skb)->frag_list = head; - psock->rx_skb_head = skb; - head = skb; - } else { - psock->rx_skb_nextp = - &skb_shinfo(head)->frag_list; - } - } - } - - while (eaten < orig_len) { - /* Always clone since we will consume something */ - skb = skb_clone(orig_skb, GFP_ATOMIC); - if (!skb) { - KCM_STATS_INCR(psock->stats.rx_mem_fail); - desc->error = -ENOMEM; - break; - } - - cand_len = orig_len - eaten; - - head = psock->rx_skb_head; - if (!head) { - head = skb; - psock->rx_skb_head = head; - /* Will set rx_skb_nextp on next packet if needed */ - psock->rx_skb_nextp = NULL; - rxm = kcm_rx_msg(head); - memset(rxm, 0, sizeof(*rxm)); - rxm->offset = orig_offset + eaten; - } else { - /* Unclone since we may be appending to an skb that we - * already share a frag_list with. - */ - err = skb_unclone(skb, GFP_ATOMIC); - if (err) { - KCM_STATS_INCR(psock->stats.rx_mem_fail); - desc->error = err; - break; - } - - rxm = kcm_rx_msg(head); - *psock->rx_skb_nextp = skb; - psock->rx_skb_nextp = &skb->next; - head->data_len += skb->len; - head->len += skb->len; - head->truesize += skb->truesize; - } - - if (!rxm->full_len) { - ssize_t len; - - len = KCM_RUN_FILTER(psock->bpf_prog, head); - - if (!len) { - /* Need more header to determine length */ - if (!rxm->accum_len) { - /* Start RX timer for new message */ - kcm_start_rx_timer(psock); - } - rxm->accum_len += cand_len; - eaten += cand_len; - KCM_STATS_INCR(psock->stats.rx_need_more_hdr); - WARN_ON(eaten != orig_len); - break; - } else if (len > psock->sk->sk_rcvbuf) { - /* Message length exceeds maximum allowed */ - KCM_STATS_INCR(psock->stats.rx_msg_too_big); - desc->error = -EMSGSIZE; - psock->rx_skb_head = NULL; - kcm_abort_rx_psock(psock, EMSGSIZE, head); - break; - } else if (len <= (ssize_t)head->len - - skb->len - rxm->offset) { - /* Length must be into new skb (and also - * greater than zero) - */ - KCM_STATS_INCR(psock->stats.rx_bad_hdr_len); - desc->error = -EPROTO; - psock->rx_skb_head = NULL; - kcm_abort_rx_psock(psock, EPROTO, head); - break; - } - - rxm->full_len = len; - } - - extra = (ssize_t)(rxm->accum_len + cand_len) - rxm->full_len; - - if (extra < 0) { - /* Message not complete yet. */ - if (rxm->full_len - rxm->accum_len > - tcp_inq(psock->sk)) { - /* Don't have the whole messages in the socket - * buffer. Set psock->rx_need_bytes to wait for - * the rest of the message. Also, set "early - * eaten" since we've already buffered the skb - * but don't consume yet per tcp_read_sock. - */ - - if (!rxm->accum_len) { - /* Start RX timer for new message */ - kcm_start_rx_timer(psock); - } - - psock->rx_need_bytes = rxm->full_len - - rxm->accum_len; - rxm->accum_len += cand_len; - rxm->early_eaten = cand_len; - KCM_STATS_ADD(psock->stats.rx_bytes, cand_len); - desc->count = 0; /* Stop reading socket */ - break; - } - rxm->accum_len += cand_len; - eaten += cand_len; - WARN_ON(eaten != orig_len); - break; - } - - /* Positive extra indicates ore bytes than needed for the - * message - */ - - WARN_ON(extra > cand_len); - - eaten += (cand_len - extra); - - /* Hurray, we have a new message! */ - del_timer(&psock->rx_msg_timer); - psock->rx_skb_head = NULL; - KCM_STATS_INCR(psock->stats.rx_msgs); - -try_queue: - kcm = reserve_rx_kcm(psock, head); - if (!kcm) { - /* Unable to reserve a KCM, message is held in psock. */ - break; - } - - if (kcm_queue_rcv_skb(&kcm->sk, head)) { - /* Should mean socket buffer full */ - unreserve_rx_kcm(psock, false); - goto try_queue; - } - } - - if (cloned_orig) - kfree_skb(orig_skb); - - KCM_STATS_ADD(psock->stats.rx_bytes, eaten); - - return eaten; -} - -/* Called with lock held on lower socket */ -static int psock_tcp_read_sock(struct kcm_psock *psock) -{ - read_descriptor_t desc; - - desc.arg.data = psock; - desc.error = 0; - desc.count = 1; /* give more than one skb per call */ - - /* sk should be locked here, so okay to do tcp_read_sock */ - tcp_read_sock(psock->sk, &desc, kcm_tcp_recv); - - unreserve_rx_kcm(psock, true); - - return desc.error; -} - /* Lower sock lock held */ -static void psock_tcp_data_ready(struct sock *sk) +static void psock_data_ready(struct sock *sk) { struct kcm_psock *psock; read_lock_bh(&sk->sk_callback_lock); psock = (struct kcm_psock *)sk->sk_user_data; - if (unlikely(!psock || psock->rx_stopped)) - goto out; + if (likely(psock)) + strp_data_ready(&psock->strp); - if (psock->ready_rx_msg) - goto out; - - if (psock->rx_need_bytes) { - if (tcp_inq(sk) >= psock->rx_need_bytes) - psock->rx_need_bytes = 0; - else - goto out; - } - - if (psock_tcp_read_sock(psock) == -ENOMEM) - queue_delayed_work(kcm_wq, &psock->rx_delayed_work, 0); - -out: read_unlock_bh(&sk->sk_callback_lock); } -static void do_psock_rx_work(struct kcm_psock *psock) +/* Called with lower sock held */ +static void kcm_rcv_strparser(struct strparser *strp, struct sk_buff *skb) { - read_descriptor_t rd_desc; - struct sock *csk = psock->sk; - - /* We need the read lock to synchronize with psock_tcp_data_ready. We - * need the socket lock for calling tcp_read_sock. - */ - lock_sock(csk); - read_lock_bh(&csk->sk_callback_lock); - - if (unlikely(csk->sk_user_data != psock)) - goto out; - - if (unlikely(psock->rx_stopped)) - goto out; - - if (psock->ready_rx_msg) - goto out; - - rd_desc.arg.data = psock; + struct kcm_psock *psock = container_of(strp, struct kcm_psock, strp); + struct kcm_sock *kcm; - if (psock_tcp_read_sock(psock) == -ENOMEM) - queue_delayed_work(kcm_wq, &psock->rx_delayed_work, 0); +try_queue: + kcm = reserve_rx_kcm(psock, skb); + if (!kcm) { + /* Unable to reserve a KCM, message is held in psock and strp + * is paused. + */ + return; + } -out: - read_unlock_bh(&csk->sk_callback_lock); - release_sock(csk); + if (kcm_queue_rcv_skb(&kcm->sk, skb)) { + /* Should mean socket buffer full */ + unreserve_rx_kcm(psock, false); + goto try_queue; + } } -static void psock_rx_work(struct work_struct *w) +static int kcm_parse_func_strparser(struct strparser *strp, struct sk_buff *skb) { - do_psock_rx_work(container_of(w, struct kcm_psock, rx_work)); + struct kcm_psock *psock = container_of(strp, struct kcm_psock, strp); + struct bpf_prog *prog = psock->bpf_prog; + + return (*prog->bpf_func)(skb, prog->insnsi); } -static void psock_rx_delayed_work(struct work_struct *w) +static int kcm_read_sock_done(struct strparser *strp, int err) { - do_psock_rx_work(container_of(w, struct kcm_psock, - rx_delayed_work.work)); + struct kcm_psock *psock = container_of(strp, struct kcm_psock, strp); + + unreserve_rx_kcm(psock, true); + + return err; } -static void psock_tcp_state_change(struct sock *sk) +static void psock_state_change(struct sock *sk) { /* TCP only does a POLLIN for a half close. Do a POLLHUP here * since application will normally not poll with POLLIN @@ -702,7 +401,7 @@ static void psock_tcp_state_change(struct sock *sk) report_csk_error(sk, EPIPE); } -static void psock_tcp_write_space(struct sock *sk) +static void psock_write_space(struct sock *sk) { struct kcm_psock *psock; struct kcm_mux *mux; @@ -713,14 +412,13 @@ static void psock_tcp_write_space(struct sock *sk) psock = (struct kcm_psock *)sk->sk_user_data; if (unlikely(!psock)) goto out; - mux = psock->mux; spin_lock_bh(&mux->lock); /* Check if the socket is reserved so someone is waiting for sending. */ kcm = psock->tx_kcm; - if (kcm) + if (kcm && !unlikely(kcm->tx_stopped)) queue_work(kcm_wq, &kcm->tx_work); spin_unlock_bh(&mux->lock); @@ -1411,7 +1109,7 @@ static int kcm_recvmsg(struct socket *sock, struct msghdr *msg, struct kcm_sock *kcm = kcm_sk(sk); int err = 0; long timeo; - struct kcm_rx_msg *rxm; + struct strp_rx_msg *rxm; int copied = 0; struct sk_buff *skb; @@ -1425,7 +1123,7 @@ static int kcm_recvmsg(struct socket *sock, struct msghdr *msg, /* Okay, have a message on the receive queue */ - rxm = kcm_rx_msg(skb); + rxm = strp_rx_msg(skb); if (len > rxm->full_len) len = rxm->full_len; @@ -1481,7 +1179,7 @@ static ssize_t kcm_splice_read(struct socket *sock, loff_t *ppos, struct sock *sk = sock->sk; struct kcm_sock *kcm = kcm_sk(sk); long timeo; - struct kcm_rx_msg *rxm; + struct strp_rx_msg *rxm; int err = 0; ssize_t copied; struct sk_buff *skb; @@ -1498,7 +1196,7 @@ static ssize_t kcm_splice_read(struct socket *sock, loff_t *ppos, /* Okay, have a message on the receive queue */ - rxm = kcm_rx_msg(skb); + rxm = strp_rx_msg(skb); if (len > rxm->full_len) len = rxm->full_len; @@ -1674,15 +1372,6 @@ static void init_kcm_sock(struct kcm_sock *kcm, struct kcm_mux *mux) spin_unlock_bh(&mux->rx_lock); } -static void kcm_rx_msg_timeout(unsigned long arg) -{ - struct kcm_psock *psock = (struct kcm_psock *)arg; - - /* Message assembly timed out */ - KCM_STATS_INCR(psock->stats.rx_msg_timeouts); - kcm_abort_rx_psock(psock, ETIMEDOUT, NULL); -} - static int kcm_attach(struct socket *sock, struct socket *csock, struct bpf_prog *prog) { @@ -1692,19 +1381,13 @@ static int kcm_attach(struct socket *sock, struct socket *csock, struct kcm_psock *psock = NULL, *tpsock; struct list_head *head; int index = 0; - - if (csock->ops->family != PF_INET && - csock->ops->family != PF_INET6) - return -EINVAL; + struct strp_callbacks cb; + int err; csk = csock->sk; if (!csk) return -EINVAL; - /* Only support TCP for now */ - if (csk->sk_protocol != IPPROTO_TCP) - return -EINVAL; - psock = kmem_cache_zalloc(kcm_psockp, GFP_KERNEL); if (!psock) return -ENOMEM; @@ -1713,11 +1396,16 @@ static int kcm_attach(struct socket *sock, struct socket *csock, psock->sk = csk; psock->bpf_prog = prog; - setup_timer(&psock->rx_msg_timer, kcm_rx_msg_timeout, - (unsigned long)psock); + cb.rcv_msg = kcm_rcv_strparser; + cb.abort_parser = NULL; + cb.parse_msg = kcm_parse_func_strparser; + cb.read_sock_done = kcm_read_sock_done; - INIT_WORK(&psock->rx_work, psock_rx_work); - INIT_DELAYED_WORK(&psock->rx_delayed_work, psock_rx_delayed_work); + err = strp_init(&psock->strp, csk, &cb); + if (err) { + kmem_cache_free(kcm_psockp, psock); + return err; + } sock_hold(csk); @@ -1726,9 +1414,9 @@ static int kcm_attach(struct socket *sock, struct socket *csock, psock->save_write_space = csk->sk_write_space; psock->save_state_change = csk->sk_state_change; csk->sk_user_data = psock; - csk->sk_data_ready = psock_tcp_data_ready; - csk->sk_write_space = psock_tcp_write_space; - csk->sk_state_change = psock_tcp_state_change; + csk->sk_data_ready = psock_data_ready; + csk->sk_write_space = psock_write_space; + csk->sk_state_change = psock_state_change; write_unlock_bh(&csk->sk_callback_lock); /* Finished initialization, now add the psock to the MUX. */ @@ -1750,7 +1438,7 @@ static int kcm_attach(struct socket *sock, struct socket *csock, spin_unlock_bh(&mux->lock); /* Schedule RX work in case there are already bytes queued */ - queue_work(kcm_wq, &psock->rx_work); + strp_check_rcv(&psock->strp); return 0; } @@ -1790,6 +1478,8 @@ static void kcm_unattach(struct kcm_psock *psock) struct sock *csk = psock->sk; struct kcm_mux *mux = psock->mux; + lock_sock(csk); + /* Stop getting callbacks from TCP socket. After this there should * be no way to reserve a kcm for this psock. */ @@ -1798,7 +1488,7 @@ static void kcm_unattach(struct kcm_psock *psock) csk->sk_data_ready = psock->save_data_ready; csk->sk_write_space = psock->save_write_space; csk->sk_state_change = psock->save_state_change; - psock->rx_stopped = 1; + strp_stop(&psock->strp); if (WARN_ON(psock->rx_kcm)) { write_unlock_bh(&csk->sk_callback_lock); @@ -1821,18 +1511,17 @@ static void kcm_unattach(struct kcm_psock *psock) write_unlock_bh(&csk->sk_callback_lock); - del_timer_sync(&psock->rx_msg_timer); - cancel_work_sync(&psock->rx_work); - cancel_delayed_work_sync(&psock->rx_delayed_work); + /* Call strp_done without sock lock */ + release_sock(csk); + strp_done(&psock->strp); + lock_sock(csk); bpf_prog_put(psock->bpf_prog); - kfree_skb(psock->rx_skb_head); - psock->rx_skb_head = NULL; - spin_lock_bh(&mux->lock); aggregate_psock_stats(&psock->stats, &mux->aggregate_psock_stats); + save_strp_stats(&psock->strp, &mux->aggregate_strp_stats); KCM_STATS_INCR(mux->stats.psock_unattach); @@ -1875,6 +1564,8 @@ no_reserved: fput(csk->sk_socket->file); kmem_cache_free(kcm_psockp, psock); } + + release_sock(csk); } static int kcm_unattach_ioctl(struct socket *sock, struct kcm_unattach *info) @@ -1915,6 +1606,7 @@ static int kcm_unattach_ioctl(struct socket *sock, struct kcm_unattach *info) spin_unlock_bh(&mux->lock); + /* Lower socket lock should already be held */ kcm_unattach(psock); err = 0; @@ -2072,6 +1764,8 @@ static void release_mux(struct kcm_mux *mux) aggregate_mux_stats(&mux->stats, &knet->aggregate_mux_stats); aggregate_psock_stats(&mux->aggregate_psock_stats, &knet->aggregate_psock_stats); + aggregate_strp_stats(&mux->aggregate_strp_stats, + &knet->aggregate_strp_stats); list_del_rcu(&mux->kcm_mux_list); knet->count--; mutex_unlock(&knet->mutex); @@ -2151,6 +1845,13 @@ static int kcm_release(struct socket *sock) * it will just return. */ __skb_queue_purge(&sk->sk_write_queue); + + /* Set tx_stopped. This is checked when psock is bound to a kcm and we + * get a writespace callback. This prevents further work being queued + * from the callback (unbinding the psock occurs after canceling work. + */ + kcm->tx_stopped = 1; + release_sock(sk); spin_lock_bh(&mux->lock); diff --git a/net/l2tp/l2tp_netlink.c b/net/l2tp/l2tp_netlink.c index 1d02e8d20e56..bf3117771822 100644 --- a/net/l2tp/l2tp_netlink.c +++ b/net/l2tp/l2tp_netlink.c @@ -867,7 +867,7 @@ out: return skb->len; } -static struct nla_policy l2tp_nl_policy[L2TP_ATTR_MAX + 1] = { +static const struct nla_policy l2tp_nl_policy[L2TP_ATTR_MAX + 1] = { [L2TP_ATTR_NONE] = { .type = NLA_UNSPEC, }, [L2TP_ATTR_PW_TYPE] = { .type = NLA_U16, }, [L2TP_ATTR_ENCAP_TYPE] = { .type = NLA_U16, }, diff --git a/net/l2tp/l2tp_ppp.c b/net/l2tp/l2tp_ppp.c index d9560aa2dba3..34eff77982cf 100644 --- a/net/l2tp/l2tp_ppp.c +++ b/net/l2tp/l2tp_ppp.c @@ -177,7 +177,7 @@ static int pppol2tp_recv_payload_hook(struct sk_buff *skb) if (!pskb_may_pull(skb, 2)) return 1; - if ((skb->data[0] == 0xff) && (skb->data[1] == 0x03)) + if ((skb->data[0] == PPP_ALLSTATIONS) && (skb->data[1] == PPP_UI)) skb_pull(skb, 2); return 0; @@ -282,7 +282,6 @@ static void pppol2tp_session_sock_put(struct l2tp_session *session) static int pppol2tp_sendmsg(struct socket *sock, struct msghdr *m, size_t total_len) { - static const unsigned char ppph[2] = { 0xff, 0x03 }; struct sock *sk = sock->sk; struct sk_buff *skb; int error; @@ -312,7 +311,7 @@ static int pppol2tp_sendmsg(struct socket *sock, struct msghdr *m, error = -ENOMEM; skb = sock_wmalloc(sk, NET_SKB_PAD + sizeof(struct iphdr) + uhlen + session->hdr_len + - sizeof(ppph) + total_len, + 2 + total_len, /* 2 bytes for PPP_ALLSTATIONS & PPP_UI */ 0, GFP_KERNEL); if (!skb) goto error_put_sess_tun; @@ -325,8 +324,8 @@ static int pppol2tp_sendmsg(struct socket *sock, struct msghdr *m, skb_reserve(skb, uhlen); /* Add PPP header */ - skb->data[0] = ppph[0]; - skb->data[1] = ppph[1]; + skb->data[0] = PPP_ALLSTATIONS; + skb->data[1] = PPP_UI; skb_put(skb, 2); /* Copy user data into skb */ @@ -369,7 +368,6 @@ error: */ static int pppol2tp_xmit(struct ppp_channel *chan, struct sk_buff *skb) { - static const u8 ppph[2] = { 0xff, 0x03 }; struct sock *sk = (struct sock *) chan->private; struct sock *sk_tun; struct l2tp_session *session; @@ -398,14 +396,14 @@ static int pppol2tp_xmit(struct ppp_channel *chan, struct sk_buff *skb) sizeof(struct iphdr) + /* IP header */ uhlen + /* UDP header (if L2TP_ENCAPTYPE_UDP) */ session->hdr_len + /* L2TP header */ - sizeof(ppph); /* PPP header */ + 2; /* 2 bytes for PPP_ALLSTATIONS & PPP_UI */ if (skb_cow_head(skb, headroom)) goto abort_put_sess_tun; /* Setup PPP header */ - __skb_push(skb, sizeof(ppph)); - skb->data[0] = ppph[0]; - skb->data[1] = ppph[1]; + __skb_push(skb, 2); + skb->data[0] = PPP_ALLSTATIONS; + skb->data[1] = PPP_UI; local_bh_disable(); l2tp_xmit_skb(session, skb, session->hdr_len); @@ -440,7 +438,7 @@ static void pppol2tp_session_close(struct l2tp_session *session) BUG_ON(session->magic != L2TP_SESSION_MAGIC); if (sock) { - inet_shutdown(sock, 2); + inet_shutdown(sock, SEND_SHUTDOWN); /* Don't let the session go away before our socket does */ l2tp_session_inc_refcount(session); } @@ -856,7 +854,7 @@ static int pppol2tp_getname(struct socket *sock, struct sockaddr *uaddr, error = -ENOTCONN; if (sk == NULL) goto end; - if (sk->sk_state != PPPOX_CONNECTED) + if (!(sk->sk_state & PPPOX_CONNECTED)) goto end; error = -EBADF; diff --git a/net/mac80211/driver-ops.h b/net/mac80211/driver-ops.h index ba5fc1f01e53..42a41ae405ba 100644 --- a/net/mac80211/driver-ops.h +++ b/net/mac80211/driver-ops.h @@ -1088,13 +1088,13 @@ static inline void drv_leave_ibss(struct ieee80211_local *local, } static inline u32 drv_get_expected_throughput(struct ieee80211_local *local, - struct ieee80211_sta *sta) + struct sta_info *sta) { u32 ret = 0; - trace_drv_get_expected_throughput(sta); - if (local->ops->get_expected_throughput) - ret = local->ops->get_expected_throughput(&local->hw, sta); + trace_drv_get_expected_throughput(&sta->sta); + if (local->ops->get_expected_throughput && sta->uploaded) + ret = local->ops->get_expected_throughput(&local->hw, &sta->sta); trace_drv_return_u32(local, ret); return ret; diff --git a/net/mac80211/mesh_hwmp.c b/net/mac80211/mesh_hwmp.c index 8f9c3bde835f..fa7d37cf0351 100644 --- a/net/mac80211/mesh_hwmp.c +++ b/net/mac80211/mesh_hwmp.c @@ -326,22 +326,33 @@ static u32 airtime_link_metric_get(struct ieee80211_local *local, u32 tx_time, estimated_retx; u64 result; - if (sta->mesh->fail_avg >= 100) - return MAX_METRIC; + /* Try to get rate based on HW/SW RC algorithm. + * Rate is returned in units of Kbps, correct this + * to comply with airtime calculation units + * Round up in case we get rate < 100Kbps + */ + rate = DIV_ROUND_UP(sta_get_expected_throughput(sta), 100); - sta_set_rate_info_tx(sta, &sta->tx_stats.last_rate, &rinfo); - rate = cfg80211_calculate_bitrate(&rinfo); - if (WARN_ON(!rate)) - return MAX_METRIC; + if (rate) { + err = 0; + } else { + if (sta->mesh->fail_avg >= 100) + return MAX_METRIC; - err = (sta->mesh->fail_avg << ARITH_SHIFT) / 100; + sta_set_rate_info_tx(sta, &sta->tx_stats.last_rate, &rinfo); + rate = cfg80211_calculate_bitrate(&rinfo); + if (WARN_ON(!rate)) + return MAX_METRIC; + + err = (sta->mesh->fail_avg << ARITH_SHIFT) / 100; + } /* bitrate is in units of 100 Kbps, while we need rate in units of * 1Mbps. This will be corrected on tx_time computation. */ tx_time = (device_constant + 10 * test_frame_len / rate); estimated_retx = ((1 << (2 * ARITH_SHIFT)) / (s_unit - err)); - result = (tx_time * estimated_retx) >> (2 * ARITH_SHIFT) ; + result = (tx_time * estimated_retx) >> (2 * ARITH_SHIFT); return (u32)result; } diff --git a/net/mac80211/sta_info.c b/net/mac80211/sta_info.c index 76b737dcc36f..19f14c907d74 100644 --- a/net/mac80211/sta_info.c +++ b/net/mac80211/sta_info.c @@ -2279,11 +2279,7 @@ void sta_set_sinfo(struct sta_info *sta, struct station_info *sinfo) if (test_sta_flag(sta, WLAN_STA_TDLS_PEER)) sinfo->sta_flags.set |= BIT(NL80211_STA_FLAG_TDLS_PEER); - /* check if the driver has a SW RC implementation */ - if (ref && ref->ops->get_expected_throughput) - thr = ref->ops->get_expected_throughput(sta->rate_ctrl_priv); - else - thr = drv_get_expected_throughput(local, &sta->sta); + thr = sta_get_expected_throughput(sta); if (thr != 0) { sinfo->filled |= BIT(NL80211_STA_INFO_EXPECTED_THROUGHPUT); @@ -2291,6 +2287,25 @@ void sta_set_sinfo(struct sta_info *sta, struct station_info *sinfo) } } +u32 sta_get_expected_throughput(struct sta_info *sta) +{ + struct ieee80211_sub_if_data *sdata = sta->sdata; + struct ieee80211_local *local = sdata->local; + struct rate_control_ref *ref = NULL; + u32 thr = 0; + + if (test_sta_flag(sta, WLAN_STA_RATE_CONTROL)) + ref = local->rate_ctrl; + + /* check if the driver has a SW RC implementation */ + if (ref && ref->ops->get_expected_throughput) + thr = ref->ops->get_expected_throughput(sta->rate_ctrl_priv); + else + thr = drv_get_expected_throughput(local, sta); + + return thr; +} + unsigned long ieee80211_sta_last_active(struct sta_info *sta) { struct ieee80211_sta_rx_stats *stats = sta_get_last_rx_stats(sta); diff --git a/net/mac80211/sta_info.h b/net/mac80211/sta_info.h index 78b0ef32dddd..0556be3e3628 100644 --- a/net/mac80211/sta_info.h +++ b/net/mac80211/sta_info.h @@ -712,6 +712,8 @@ void sta_set_rate_info_tx(struct sta_info *sta, struct rate_info *rinfo); void sta_set_sinfo(struct sta_info *sta, struct station_info *sinfo); +u32 sta_get_expected_throughput(struct sta_info *sta); + void ieee80211_sta_expire(struct ieee80211_sub_if_data *sdata, unsigned long exp_time); u8 sta_info_tx_streams(struct sta_info *sta); diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c index 502396694f47..1d0746dfea57 100644 --- a/net/mac80211/tx.c +++ b/net/mac80211/tx.c @@ -2334,7 +2334,6 @@ static struct sk_buff *ieee80211_build_hdr(struct ieee80211_sub_if_data *sdata, struct mesh_path __maybe_unused *mppath = NULL, *mpath = NULL; const u8 *encaps_data; int encaps_len, skip_header_bytes; - int nh_pos, h_pos; bool wme_sta = false, authorized = false; bool tdls_peer; bool multicast; @@ -2640,13 +2639,7 @@ static struct sk_buff *ieee80211_build_hdr(struct ieee80211_sub_if_data *sdata, encaps_len = 0; } - nh_pos = skb_network_header(skb) - skb->data; - h_pos = skb_transport_header(skb) - skb->data; - skb_pull(skb, skip_header_bytes); - nh_pos -= skip_header_bytes; - h_pos -= skip_header_bytes; - head_need = hdrlen + encaps_len + meshhdrlen - skb_headroom(skb); /* @@ -2672,18 +2665,12 @@ static struct sk_buff *ieee80211_build_hdr(struct ieee80211_sub_if_data *sdata, } } - if (encaps_data) { + if (encaps_data) memcpy(skb_push(skb, encaps_len), encaps_data, encaps_len); - nh_pos += encaps_len; - h_pos += encaps_len; - } #ifdef CONFIG_MAC80211_MESH - if (meshhdrlen > 0) { + if (meshhdrlen > 0) memcpy(skb_push(skb, meshhdrlen), &mesh_hdr, meshhdrlen); - nh_pos += meshhdrlen; - h_pos += meshhdrlen; - } #endif if (ieee80211_is_data_qos(fc)) { @@ -2699,15 +2686,7 @@ static struct sk_buff *ieee80211_build_hdr(struct ieee80211_sub_if_data *sdata, } else memcpy(skb_push(skb, hdrlen), &hdr, hdrlen); - nh_pos += hdrlen; - h_pos += hdrlen; - - /* Update skb pointers to various headers since this modified frame - * is going to go through Linux networking code that may potentially - * need things like pointer to IP header. */ skb_reset_mac_header(skb); - skb_set_network_header(skb, nh_pos); - skb_set_transport_header(skb, h_pos); info = IEEE80211_SKB_CB(skb); memset(info, 0, sizeof(*info)); @@ -4390,9 +4369,6 @@ void __ieee80211_tx_skb_tid_band(struct ieee80211_sub_if_data *sdata, int ac = ieee802_1d_to_ac[tid & 7]; skb_reset_mac_header(skb); - skb_reset_network_header(skb); - skb_reset_transport_header(skb); - skb_set_queue_mapping(skb, ac); skb->priority = tid; diff --git a/net/mpls/af_mpls.c b/net/mpls/af_mpls.c index 5c161e7759b5..0e4334cbde17 100644 --- a/net/mpls/af_mpls.c +++ b/net/mpls/af_mpls.c @@ -961,9 +961,6 @@ static void mpls_ifdown(struct net_device *dev, int event) RCU_INIT_POINTER(nh->nh_dev, NULL); } endfor_nexthops(rt); } - - - return; } static void mpls_ifup(struct net_device *dev, unsigned int nh_flags) @@ -997,8 +994,6 @@ static void mpls_ifup(struct net_device *dev, unsigned int nh_flags) ACCESS_ONCE(rt->rt_nhn_alive) = alive; } - - return; } static int mpls_dev_notify(struct notifier_block *this, unsigned long event, diff --git a/net/mpls/mpls_gso.c b/net/mpls/mpls_gso.c index 2055e57ed1c3..b4da6d8e8632 100644 --- a/net/mpls/mpls_gso.c +++ b/net/mpls/mpls_gso.c @@ -23,32 +23,50 @@ static struct sk_buff *mpls_gso_segment(struct sk_buff *skb, netdev_features_t features) { struct sk_buff *segs = ERR_PTR(-EINVAL); + u16 mac_offset = skb->mac_header; netdev_features_t mpls_features; + u16 mac_len = skb->mac_len; __be16 mpls_protocol; + unsigned int mpls_hlen; + + skb_reset_network_header(skb); + mpls_hlen = skb_inner_network_header(skb) - skb_network_header(skb); + if (unlikely(!pskb_may_pull(skb, mpls_hlen))) + goto out; /* Setup inner SKB. */ mpls_protocol = skb->protocol; skb->protocol = skb->inner_protocol; - /* Push back the mac header that skb_mac_gso_segment() has pulled. - * It will be re-pulled by the call to skb_mac_gso_segment() below - */ - __skb_push(skb, skb->mac_len); + __skb_pull(skb, mpls_hlen); + + skb->mac_len = 0; + skb_reset_mac_header(skb); /* Segment inner packet. */ mpls_features = skb->dev->mpls_features & features; segs = skb_mac_gso_segment(skb, mpls_features); + if (IS_ERR_OR_NULL(segs)) { + skb_gso_error_unwind(skb, mpls_protocol, mpls_hlen, mac_offset, + mac_len); + goto out; + } + skb = segs; + + mpls_hlen += mac_len; + do { + skb->mac_len = mac_len; + skb->protocol = mpls_protocol; + skb_reset_inner_network_header(skb); - /* Restore outer protocol. */ - skb->protocol = mpls_protocol; + __skb_push(skb, mpls_hlen); - /* Re-pull the mac header that the call to skb_mac_gso_segment() - * above pulled. It will be re-pushed after returning - * skb_mac_gso_segment(), an indirect caller of this function. - */ - __skb_pull(skb, skb->data - skb_mac_header(skb)); + skb_reset_mac_header(skb); + skb_set_network_header(skb, mac_len); + } while ((skb = skb->next)); +out: return segs; } diff --git a/net/mpls/mpls_iptunnel.c b/net/mpls/mpls_iptunnel.c index 644a8da6d4bd..cf52cf30ac4b 100644 --- a/net/mpls/mpls_iptunnel.c +++ b/net/mpls/mpls_iptunnel.c @@ -37,7 +37,7 @@ static unsigned int mpls_encap_size(struct mpls_iptunnel_encap *en) return en->labels * sizeof(struct mpls_shim_hdr); } -static int mpls_output(struct net *net, struct sock *sk, struct sk_buff *skb) +static int mpls_xmit(struct sk_buff *skb) { struct mpls_iptunnel_encap *tun_encap_info; struct mpls_shim_hdr *hdr; @@ -90,7 +90,11 @@ static int mpls_output(struct net *net, struct sock *sk, struct sk_buff *skb) if (skb_cow(skb, hh_len + new_header_size)) goto drop; + skb_set_inner_protocol(skb, skb->protocol); + skb_reset_inner_network_header(skb); + skb_push(skb, new_header_size); + skb_reset_network_header(skb); skb->dev = out_dev; @@ -115,7 +119,7 @@ static int mpls_output(struct net *net, struct sock *sk, struct sk_buff *skb) net_dbg_ratelimited("%s: packet transmission failed: %d\n", __func__, err); - return 0; + return LWTUNNEL_XMIT_DONE; drop: kfree_skb(skb); @@ -153,7 +157,8 @@ static int mpls_build_state(struct net_device *dev, struct nlattr *nla, if (ret) goto errout; newts->type = LWTUNNEL_ENCAP_MPLS; - newts->flags |= LWTUNNEL_STATE_OUTPUT_REDIRECT; + newts->flags |= LWTUNNEL_STATE_XMIT_REDIRECT; + newts->headroom = mpls_encap_size(tun_encap_info); *ts = newts; @@ -209,7 +214,7 @@ static int mpls_encap_cmp(struct lwtunnel_state *a, struct lwtunnel_state *b) static const struct lwtunnel_encap_ops mpls_iptun_ops = { .build_state = mpls_build_state, - .output = mpls_output, + .xmit = mpls_xmit, .fill_encap = mpls_fill_encap_info, .get_encap_size = mpls_encap_nlsize, .cmp_encap = mpls_encap_cmp, diff --git a/net/netfilter/nf_conntrack_expect.c b/net/netfilter/nf_conntrack_expect.c index 9e3693128313..f8dbacf66795 100644 --- a/net/netfilter/nf_conntrack_expect.c +++ b/net/netfilter/nf_conntrack_expect.c @@ -574,7 +574,7 @@ static int exp_seq_show(struct seq_file *s, void *v) helper = rcu_dereference(nfct_help(expect->master)->helper); if (helper) { seq_printf(s, "%s%s", expect->flags ? " " : "", helper->name); - if (helper->expect_policy[expect->class].name) + if (helper->expect_policy[expect->class].name[0]) seq_printf(s, "/%s", helper->expect_policy[expect->class].name); } diff --git a/net/netfilter/nf_conntrack_h323_main.c b/net/netfilter/nf_conntrack_h323_main.c index bb77a97961bf..5c0db5c64734 100644 --- a/net/netfilter/nf_conntrack_h323_main.c +++ b/net/netfilter/nf_conntrack_h323_main.c @@ -1473,7 +1473,8 @@ static int process_rcf(struct sk_buff *skb, struct nf_conn *ct, "timeout to %u seconds for", info->timeout); nf_ct_dump_tuple(&exp->tuple); - mod_timer(&exp->timeout, jiffies + info->timeout * HZ); + mod_timer_pending(&exp->timeout, + jiffies + info->timeout * HZ); } spin_unlock_bh(&nf_conntrack_expect_lock); } diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c index dedbe4b33f38..c052b712c49f 100644 --- a/net/netfilter/nf_conntrack_netlink.c +++ b/net/netfilter/nf_conntrack_netlink.c @@ -1910,6 +1910,8 @@ static int ctnetlink_new_conntrack(struct net *net, struct sock *ctnl, if (!cda[CTA_TUPLE_ORIG] || !cda[CTA_TUPLE_REPLY]) return -EINVAL; + if (otuple.dst.protonum != rtuple.dst.protonum) + return -EINVAL; ct = ctnetlink_create_conntrack(net, &zone, cda, &otuple, &rtuple, u3); @@ -2378,12 +2380,8 @@ ctnetlink_glue_attach_expect(const struct nlattr *attr, struct nf_conn *ct, return PTR_ERR(exp); err = nf_ct_expect_related_report(exp, portid, report); - if (err < 0) { - nf_ct_expect_put(exp); - return err; - } - - return 0; + nf_ct_expect_put(exp); + return err; } static void ctnetlink_glue_seqadj(struct sk_buff *skb, struct nf_conn *ct, diff --git a/net/netfilter/nf_conntrack_sip.c b/net/netfilter/nf_conntrack_sip.c index 8d9db9d4702b..7d77217de6a3 100644 --- a/net/netfilter/nf_conntrack_sip.c +++ b/net/netfilter/nf_conntrack_sip.c @@ -1383,7 +1383,7 @@ static int process_sip_response(struct sk_buff *skb, unsigned int protoff, return NF_DROP; } cseq = simple_strtoul(*dptr + matchoff, NULL, 10); - if (!cseq) { + if (!cseq && *(*dptr + matchoff) != '0') { nf_ct_helper_log(skb, ct, "cannot get cseq"); return NF_DROP; } @@ -1446,7 +1446,7 @@ static int process_sip_request(struct sk_buff *skb, unsigned int protoff, return NF_DROP; } cseq = simple_strtoul(*dptr + matchoff, NULL, 10); - if (!cseq) { + if (!cseq && *(*dptr + matchoff) != '0') { nf_ct_helper_log(skb, ct, "cannot get cseq"); return NF_DROP; } diff --git a/net/netfilter/nf_conntrack_standalone.c b/net/netfilter/nf_conntrack_standalone.c index 4e7becde4357..3d9a316a3c77 100644 --- a/net/netfilter/nf_conntrack_standalone.c +++ b/net/netfilter/nf_conntrack_standalone.c @@ -205,6 +205,7 @@ static int ct_seq_show(struct seq_file *s, void *v) struct nf_conn *ct = nf_ct_tuplehash_to_ctrack(hash); const struct nf_conntrack_l3proto *l3proto; const struct nf_conntrack_l4proto *l4proto; + struct net *net = seq_file_net(s); int ret = 0; NF_CT_ASSERT(ct); @@ -215,6 +216,9 @@ static int ct_seq_show(struct seq_file *s, void *v) if (NF_CT_DIRECTION(hash)) goto release; + if (!net_eq(nf_ct_net(ct), net)) + goto release; + l3proto = __nf_ct_l3proto_find(nf_ct_l3num(ct)); NF_CT_ASSERT(l3proto); l4proto = __nf_ct_l4proto_find(nf_ct_l3num(ct), nf_ct_protonum(ct)); diff --git a/net/netfilter/nfnetlink_acct.c b/net/netfilter/nfnetlink_acct.c index 1b4de4bd6958..70eb2f6a3b01 100644 --- a/net/netfilter/nfnetlink_acct.c +++ b/net/netfilter/nfnetlink_acct.c @@ -326,14 +326,14 @@ static int nfnl_acct_try_del(struct nf_acct *cur) { int ret = 0; - /* we want to avoid races with nfnl_acct_find_get. */ - if (atomic_dec_and_test(&cur->refcnt)) { + /* We want to avoid races with nfnl_acct_put. So only when the current + * refcnt is 1, we decrease it to 0. + */ + if (atomic_cmpxchg(&cur->refcnt, 1, 0) == 1) { /* We are protected by nfnl mutex. */ list_del_rcu(&cur->head); kfree_rcu(cur, rcu_head); } else { - /* still in use, restore reference counter. */ - atomic_inc(&cur->refcnt); ret = -EBUSY; } return ret; @@ -443,7 +443,7 @@ void nfnl_acct_update(const struct sk_buff *skb, struct nf_acct *nfacct) } EXPORT_SYMBOL_GPL(nfnl_acct_update); -static void nfnl_overquota_report(struct nf_acct *nfacct) +static void nfnl_overquota_report(struct net *net, struct nf_acct *nfacct) { int ret; struct sk_buff *skb; @@ -458,11 +458,12 @@ static void nfnl_overquota_report(struct nf_acct *nfacct) kfree_skb(skb); return; } - netlink_broadcast(init_net.nfnl, skb, 0, NFNLGRP_ACCT_QUOTA, + netlink_broadcast(net->nfnl, skb, 0, NFNLGRP_ACCT_QUOTA, GFP_ATOMIC); } -int nfnl_acct_overquota(const struct sk_buff *skb, struct nf_acct *nfacct) +int nfnl_acct_overquota(struct net *net, const struct sk_buff *skb, + struct nf_acct *nfacct) { u64 now; u64 *quota; @@ -480,7 +481,7 @@ int nfnl_acct_overquota(const struct sk_buff *skb, struct nf_acct *nfacct) if (now >= *quota && !test_and_set_bit(NFACCT_OVERQUOTA_BIT, &nfacct->flags)) { - nfnl_overquota_report(nfacct); + nfnl_overquota_report(net, nfacct); } return ret; diff --git a/net/netfilter/nfnetlink_cttimeout.c b/net/netfilter/nfnetlink_cttimeout.c index 4cdcd969b64c..68216cdc7083 100644 --- a/net/netfilter/nfnetlink_cttimeout.c +++ b/net/netfilter/nfnetlink_cttimeout.c @@ -330,16 +330,16 @@ static int ctnl_timeout_try_del(struct net *net, struct ctnl_timeout *timeout) { int ret = 0; - /* we want to avoid races with nf_ct_timeout_find_get. */ - if (atomic_dec_and_test(&timeout->refcnt)) { + /* We want to avoid races with ctnl_timeout_put. So only when the + * current refcnt is 1, we decrease it to 0. + */ + if (atomic_cmpxchg(&timeout->refcnt, 1, 0) == 1) { /* We are protected by nfnl mutex. */ list_del_rcu(&timeout->head); nf_ct_l4proto_put(timeout->l4proto); ctnl_untimeout(net, timeout); kfree_rcu(timeout, rcu_head); } else { - /* still in use, restore reference counter. */ - atomic_inc(&timeout->refcnt); ret = -EBUSY; } return ret; @@ -543,7 +543,9 @@ err: static void ctnl_timeout_put(struct ctnl_timeout *timeout) { - atomic_dec(&timeout->refcnt); + if (atomic_dec_and_test(&timeout->refcnt)) + kfree_rcu(timeout, rcu_head); + module_put(THIS_MODULE); } #endif /* CONFIG_NF_CONNTRACK_TIMEOUT */ @@ -591,7 +593,9 @@ static void __net_exit cttimeout_net_exit(struct net *net) list_for_each_entry_safe(cur, tmp, &net->nfct_timeout_list, head) { list_del_rcu(&cur->head); nf_ct_l4proto_put(cur->l4proto); - kfree_rcu(cur, rcu_head); + + if (atomic_dec_and_test(&cur->refcnt)) + kfree_rcu(cur, rcu_head); } } diff --git a/net/netfilter/nfnetlink_log.c b/net/netfilter/nfnetlink_log.c index cbcfdfb586a6..6577db524ef6 100644 --- a/net/netfilter/nfnetlink_log.c +++ b/net/netfilter/nfnetlink_log.c @@ -1147,6 +1147,7 @@ MODULE_ALIAS_NFNL_SUBSYS(NFNL_SUBSYS_ULOG); MODULE_ALIAS_NF_LOGGER(AF_INET, 1); MODULE_ALIAS_NF_LOGGER(AF_INET6, 1); MODULE_ALIAS_NF_LOGGER(AF_BRIDGE, 1); +MODULE_ALIAS_NF_LOGGER(3, 1); /* NFPROTO_ARP */ module_init(nfnetlink_log_init); module_exit(nfnetlink_log_fini); diff --git a/net/netfilter/nfnetlink_queue.c b/net/netfilter/nfnetlink_queue.c index 5d36a0926b4a..f49f45081acb 100644 --- a/net/netfilter/nfnetlink_queue.c +++ b/net/netfilter/nfnetlink_queue.c @@ -1145,10 +1145,8 @@ static int nfqnl_recv_verdict(struct net *net, struct sock *ctnl, struct nfnl_queue_net *q = nfnl_queue_pernet(net); int err; - queue = instance_lookup(q, queue_num); - if (!queue) - queue = verdict_instance_lookup(q, queue_num, - NETLINK_CB(skb).portid); + queue = verdict_instance_lookup(q, queue_num, + NETLINK_CB(skb).portid); if (IS_ERR(queue)) return PTR_ERR(queue); diff --git a/net/netfilter/nft_exthdr.c b/net/netfilter/nft_exthdr.c index ba7aed13e174..82c264e40278 100644 --- a/net/netfilter/nft_exthdr.c +++ b/net/netfilter/nft_exthdr.c @@ -59,6 +59,7 @@ static int nft_exthdr_init(const struct nft_ctx *ctx, const struct nlattr * const tb[]) { struct nft_exthdr *priv = nft_expr_priv(expr); + u32 offset, len; if (tb[NFTA_EXTHDR_DREG] == NULL || tb[NFTA_EXTHDR_TYPE] == NULL || @@ -66,9 +67,15 @@ static int nft_exthdr_init(const struct nft_ctx *ctx, tb[NFTA_EXTHDR_LEN] == NULL) return -EINVAL; + offset = ntohl(nla_get_be32(tb[NFTA_EXTHDR_OFFSET])); + len = ntohl(nla_get_be32(tb[NFTA_EXTHDR_LEN])); + + if (offset > U8_MAX || len > U8_MAX) + return -ERANGE; + priv->type = nla_get_u8(tb[NFTA_EXTHDR_TYPE]); - priv->offset = ntohl(nla_get_be32(tb[NFTA_EXTHDR_OFFSET])); - priv->len = ntohl(nla_get_be32(tb[NFTA_EXTHDR_LEN])); + priv->offset = offset; + priv->len = len; priv->dreg = nft_parse_register(tb[NFTA_EXTHDR_DREG]); return nft_validate_register_store(ctx, priv->dreg, NULL, diff --git a/net/netfilter/nft_set_rbtree.c b/net/netfilter/nft_set_rbtree.c index 038682d48261..38b5bda242f8 100644 --- a/net/netfilter/nft_set_rbtree.c +++ b/net/netfilter/nft_set_rbtree.c @@ -70,7 +70,6 @@ static bool nft_rbtree_lookup(const struct net *net, const struct nft_set *set, } else if (d > 0) parent = parent->rb_right; else { -found: if (!nft_set_elem_active(&rbe->ext, genmask)) { parent = parent->rb_left; continue; @@ -84,9 +83,12 @@ found: } } - if (set->flags & NFT_SET_INTERVAL && interval != NULL) { - rbe = interval; - goto found; + if (set->flags & NFT_SET_INTERVAL && interval != NULL && + nft_set_elem_active(&interval->ext, genmask) && + !nft_rbtree_interval_end(interval)) { + spin_unlock_bh(&nft_rbtree_lock); + *ext = &interval->ext; + return true; } out: spin_unlock_bh(&nft_rbtree_lock); diff --git a/net/netfilter/xt_TPROXY.c b/net/netfilter/xt_TPROXY.c index 7f4414d26a66..663c4c3c9072 100644 --- a/net/netfilter/xt_TPROXY.c +++ b/net/netfilter/xt_TPROXY.c @@ -127,6 +127,8 @@ nf_tproxy_get_sock_v4(struct net *net, struct sk_buff *skb, void *hp, daddr, dport, in->ifindex); + if (sk && !atomic_inc_not_zero(&sk->sk_refcnt)) + sk = NULL; /* NOTE: we return listeners even if bound to * 0.0.0.0, those are filtered out in * xt_socket, since xt_TPROXY needs 0 bound @@ -195,6 +197,8 @@ nf_tproxy_get_sock_v6(struct net *net, struct sk_buff *skb, int thoff, void *hp, daddr, ntohs(dport), in->ifindex); + if (sk && !atomic_inc_not_zero(&sk->sk_refcnt)) + sk = NULL; /* NOTE: we return listeners even if bound to * 0.0.0.0, those are filtered out in * xt_socket, since xt_TPROXY needs 0 bound diff --git a/net/netfilter/xt_nfacct.c b/net/netfilter/xt_nfacct.c index 3048a7e3a90a..cf327593852a 100644 --- a/net/netfilter/xt_nfacct.c +++ b/net/netfilter/xt_nfacct.c @@ -26,7 +26,7 @@ static bool nfacct_mt(const struct sk_buff *skb, struct xt_action_param *par) nfnl_acct_update(skb, info->nfacct); - overquota = nfnl_acct_overquota(skb, info->nfacct); + overquota = nfnl_acct_overquota(par->net, skb, info->nfacct); return overquota == NFACCT_UNDERQUOTA ? false : true; } diff --git a/net/netlink/diag.c b/net/netlink/diag.c index 8dd836a8dd60..3e3e2534478a 100644 --- a/net/netlink/diag.c +++ b/net/netlink/diag.c @@ -63,43 +63,75 @@ out_nlmsg_trim: static int __netlink_diag_dump(struct sk_buff *skb, struct netlink_callback *cb, int protocol, int s_num) { + struct rhashtable_iter *hti = (void *)cb->args[2]; struct netlink_table *tbl = &nl_table[protocol]; - struct rhashtable *ht = &tbl->hash; - const struct bucket_table *htbl = rht_dereference_rcu(ht->tbl, ht); struct net *net = sock_net(skb->sk); struct netlink_diag_req *req; struct netlink_sock *nlsk; struct sock *sk; - int ret = 0, num = 0, i; + int num = 2; + int ret = 0; req = nlmsg_data(cb->nlh); - for (i = 0; i < htbl->size; i++) { - struct rhash_head *pos; + if (s_num > 1) + goto mc_list; - rht_for_each_entry_rcu(nlsk, pos, htbl, i, node) { - sk = (struct sock *)nlsk; + num--; - if (!net_eq(sock_net(sk), net)) - continue; - if (num < s_num) { - num++; + if (!hti) { + hti = kmalloc(sizeof(*hti), GFP_KERNEL); + if (!hti) + return -ENOMEM; + + cb->args[2] = (long)hti; + } + + if (!s_num) + rhashtable_walk_enter(&tbl->hash, hti); + + ret = rhashtable_walk_start(hti); + if (ret == -EAGAIN) + ret = 0; + if (ret) + goto stop; + + while ((nlsk = rhashtable_walk_next(hti))) { + if (IS_ERR(nlsk)) { + ret = PTR_ERR(nlsk); + if (ret == -EAGAIN) { + ret = 0; continue; } + break; + } - if (sk_diag_fill(sk, skb, req, - NETLINK_CB(cb->skb).portid, - cb->nlh->nlmsg_seq, - NLM_F_MULTI, - sock_i_ino(sk)) < 0) { - ret = 1; - goto done; - } + sk = (struct sock *)nlsk; - num++; + if (!net_eq(sock_net(sk), net)) + continue; + + if (sk_diag_fill(sk, skb, req, + NETLINK_CB(cb->skb).portid, + cb->nlh->nlmsg_seq, + NLM_F_MULTI, + sock_i_ino(sk)) < 0) { + ret = 1; + break; } } +stop: + rhashtable_walk_stop(hti); + if (ret) + goto done; + + rhashtable_walk_exit(hti); + cb->args[2] = 0; + num++; + +mc_list: + read_lock(&nl_table_lock); sk_for_each_bound(sk, &tbl->mc_list) { if (sk_hashed(sk)) continue; @@ -116,13 +148,14 @@ static int __netlink_diag_dump(struct sk_buff *skb, struct netlink_callback *cb, NLM_F_MULTI, sock_i_ino(sk)) < 0) { ret = 1; - goto done; + break; } num++; } + read_unlock(&nl_table_lock); + done: cb->args[0] = num; - cb->args[1] = protocol; return ret; } @@ -131,20 +164,20 @@ static int netlink_diag_dump(struct sk_buff *skb, struct netlink_callback *cb) { struct netlink_diag_req *req; int s_num = cb->args[0]; + int err = 0; req = nlmsg_data(cb->nlh); - rcu_read_lock(); - read_lock(&nl_table_lock); - if (req->sdiag_protocol == NDIAG_PROTO_ALL) { int i; for (i = cb->args[1]; i < MAX_LINKS; i++) { - if (__netlink_diag_dump(skb, cb, i, s_num)) + err = __netlink_diag_dump(skb, cb, i, s_num); + if (err) break; s_num = 0; } + cb->args[1] = i; } else { if (req->sdiag_protocol >= MAX_LINKS) { read_unlock(&nl_table_lock); @@ -152,13 +185,22 @@ static int netlink_diag_dump(struct sk_buff *skb, struct netlink_callback *cb) return -ENOENT; } - __netlink_diag_dump(skb, cb, req->sdiag_protocol, s_num); + err = __netlink_diag_dump(skb, cb, req->sdiag_protocol, s_num); } - read_unlock(&nl_table_lock); - rcu_read_unlock(); + return err < 0 ? err : skb->len; +} + +static int netlink_diag_dump_done(struct netlink_callback *cb) +{ + struct rhashtable_iter *hti = (void *)cb->args[2]; + + if (cb->args[0] == 1) + rhashtable_walk_exit(hti); - return skb->len; + kfree(hti); + + return 0; } static int netlink_diag_handler_dump(struct sk_buff *skb, struct nlmsghdr *h) @@ -172,6 +214,7 @@ static int netlink_diag_handler_dump(struct sk_buff *skb, struct nlmsghdr *h) if (h->nlmsg_flags & NLM_F_DUMP) { struct netlink_dump_control c = { .dump = netlink_diag_dump, + .done = netlink_diag_dump_done, }; return netlink_dump_start(net->diag_nlsk, skb, h, &c); } else diff --git a/net/netlink/genetlink.c b/net/netlink/genetlink.c index a09132a69869..23cc12639ba7 100644 --- a/net/netlink/genetlink.c +++ b/net/netlink/genetlink.c @@ -977,7 +977,7 @@ static int genl_ctrl_event(int event, struct genl_family *family, return 0; } -static struct genl_ops genl_ctrl_ops[] = { +static const struct genl_ops genl_ctrl_ops[] = { { .cmd = CTRL_CMD_GETFAMILY, .doit = ctrl_getfamily, @@ -986,7 +986,7 @@ static struct genl_ops genl_ctrl_ops[] = { }, }; -static struct genl_multicast_group genl_ctrl_groups[] = { +static const struct genl_multicast_group genl_ctrl_groups[] = { { .name = "notify", }, }; diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c index 1ecbd7715f6d..ca91fc33f8a9 100644 --- a/net/openvswitch/actions.c +++ b/net/openvswitch/actions.c @@ -162,10 +162,16 @@ static int push_mpls(struct sk_buff *skb, struct sw_flow_key *key, if (skb_cow_head(skb, MPLS_HLEN) < 0) return -ENOMEM; + if (!skb->inner_protocol) { + skb_set_inner_network_header(skb, skb->mac_len); + skb_set_inner_protocol(skb, skb->protocol); + } + skb_push(skb, MPLS_HLEN); memmove(skb_mac_header(skb) - MPLS_HLEN, skb_mac_header(skb), skb->mac_len); skb_reset_mac_header(skb); + skb_set_network_header(skb, skb->mac_len); new_mpls_lse = (__be32 *)skb_mpls_header(skb); *new_mpls_lse = mpls->mpls_lse; @@ -173,8 +179,6 @@ static int push_mpls(struct sk_buff *skb, struct sw_flow_key *key, skb_postpush_rcsum(skb, new_mpls_lse, MPLS_HLEN); update_ethertype(skb, eth_hdr(skb), mpls->mpls_ethertype); - if (!skb->inner_protocol) - skb_set_inner_protocol(skb, skb->protocol); skb->protocol = mpls->mpls_ethertype; invalidate_flow_key(key); @@ -198,6 +202,7 @@ static int pop_mpls(struct sk_buff *skb, struct sw_flow_key *key, __skb_pull(skb, MPLS_HLEN); skb_reset_mac_header(skb); + skb_set_network_header(skb, skb->mac_len); /* skb_mpls_header() is used to locate the ethertype * field correctly in the presence of VLAN tags. diff --git a/net/openvswitch/conntrack.c b/net/openvswitch/conntrack.c index e054a748ff25..31045ef44a82 100644 --- a/net/openvswitch/conntrack.c +++ b/net/openvswitch/conntrack.c @@ -1367,7 +1367,7 @@ static void __ovs_ct_free_action(struct ovs_conntrack_info *ct_info) if (ct_info->helper) module_put(ct_info->helper->me); if (ct_info->ct) - nf_ct_put(ct_info->ct); + nf_ct_tmpl_free(ct_info->ct); } void ovs_ct_init(struct net *net) diff --git a/net/openvswitch/vport-geneve.c b/net/openvswitch/vport-geneve.c index 1a1fcec88695..5aaf3babfc3f 100644 --- a/net/openvswitch/vport-geneve.c +++ b/net/openvswitch/vport-geneve.c @@ -93,7 +93,14 @@ static struct vport *geneve_tnl_create(const struct vport_parms *parms) return ERR_CAST(dev); } - dev_change_flags(dev, dev->flags | IFF_UP); + err = dev_change_flags(dev, dev->flags | IFF_UP); + if (err < 0) { + rtnl_delete_link(dev); + rtnl_unlock(); + ovs_vport_free(vport); + goto error; + } + rtnl_unlock(); return vport; error: diff --git a/net/openvswitch/vport-gre.c b/net/openvswitch/vport-gre.c index 7f8897f33a67..0e72d95b0e8f 100644 --- a/net/openvswitch/vport-gre.c +++ b/net/openvswitch/vport-gre.c @@ -54,6 +54,7 @@ static struct vport *gre_tnl_create(const struct vport_parms *parms) struct net *net = ovs_dp_get_net(parms->dp); struct net_device *dev; struct vport *vport; + int err; vport = ovs_vport_alloc(0, &ovs_gre_vport_ops, parms); if (IS_ERR(vport)) @@ -67,9 +68,15 @@ static struct vport *gre_tnl_create(const struct vport_parms *parms) return ERR_CAST(dev); } - dev_change_flags(dev, dev->flags | IFF_UP); - rtnl_unlock(); + err = dev_change_flags(dev, dev->flags | IFF_UP); + if (err < 0) { + rtnl_delete_link(dev); + rtnl_unlock(); + ovs_vport_free(vport); + return ERR_PTR(err); + } + rtnl_unlock(); return vport; } diff --git a/net/openvswitch/vport-vxlan.c b/net/openvswitch/vport-vxlan.c index 5eb7694348b5..7eb955e453e6 100644 --- a/net/openvswitch/vport-vxlan.c +++ b/net/openvswitch/vport-vxlan.c @@ -130,7 +130,14 @@ static struct vport *vxlan_tnl_create(const struct vport_parms *parms) return ERR_CAST(dev); } - dev_change_flags(dev, dev->flags | IFF_UP); + err = dev_change_flags(dev, dev->flags | IFF_UP); + if (err < 0) { + rtnl_delete_link(dev); + rtnl_unlock(); + ovs_vport_free(vport); + goto error; + } + rtnl_unlock(); return vport; error: diff --git a/net/rxrpc/af_rxrpc.c b/net/rxrpc/af_rxrpc.c index 88effadd4b16..32d544995dda 100644 --- a/net/rxrpc/af_rxrpc.c +++ b/net/rxrpc/af_rxrpc.c @@ -22,6 +22,7 @@ #include <net/net_namespace.h> #include <net/sock.h> #include <net/af_rxrpc.h> +#define CREATE_TRACE_POINTS #include "ar-internal.h" MODULE_DESCRIPTION("RxRPC network protocol"); @@ -230,6 +231,8 @@ static int rxrpc_listen(struct socket *sock, int backlog) * @srx: The address of the peer to contact * @key: The security context to use (defaults to socket setting) * @user_call_ID: The ID to use + * @gfp: The allocation constraints + * @notify_rx: Where to send notifications instead of socket queue * * Allow a kernel service to begin a call on the nominated socket. This just * sets up all the internal tracking structures and allocates connection and @@ -242,7 +245,8 @@ struct rxrpc_call *rxrpc_kernel_begin_call(struct socket *sock, struct sockaddr_rxrpc *srx, struct key *key, unsigned long user_call_ID, - gfp_t gfp) + gfp_t gfp, + rxrpc_notify_rx_t notify_rx) { struct rxrpc_conn_parameters cp; struct rxrpc_call *call; @@ -269,6 +273,8 @@ struct rxrpc_call *rxrpc_kernel_begin_call(struct socket *sock, cp.exclusive = false; cp.service_id = srx->srx_service; call = rxrpc_new_client_call(rx, &cp, srx, user_call_ID, gfp); + if (!IS_ERR(call)) + call->notify_rx = notify_rx; release_sock(&rx->sk); _leave(" = %p", call); @@ -278,40 +284,37 @@ EXPORT_SYMBOL(rxrpc_kernel_begin_call); /** * rxrpc_kernel_end_call - Allow a kernel service to end a call it was using + * @sock: The socket the call is on * @call: The call to end * * Allow a kernel service to end a call it was using. The call must be * complete before this is called (the call should be aborted if necessary). */ -void rxrpc_kernel_end_call(struct rxrpc_call *call) +void rxrpc_kernel_end_call(struct socket *sock, struct rxrpc_call *call) { _enter("%d{%d}", call->debug_id, atomic_read(&call->usage)); - rxrpc_remove_user_ID(call->socket, call); + rxrpc_remove_user_ID(rxrpc_sk(sock->sk), call); + rxrpc_purge_queue(&call->knlrecv_queue); rxrpc_put_call(call); } EXPORT_SYMBOL(rxrpc_kernel_end_call); /** - * rxrpc_kernel_intercept_rx_messages - Intercept received RxRPC messages + * rxrpc_kernel_new_call_notification - Get notifications of new calls * @sock: The socket to intercept received messages on - * @interceptor: The function to pass the messages to + * @notify_new_call: Function to be called when new calls appear * - * Allow a kernel service to intercept messages heading for the Rx queue on an - * RxRPC socket. They get passed to the specified function instead. - * @interceptor should free the socket buffers it is given. @interceptor is - * called with the socket receive queue spinlock held and softirqs disabled - - * this ensures that the messages will be delivered in the right order. + * Allow a kernel service to be given notifications about new calls. */ -void rxrpc_kernel_intercept_rx_messages(struct socket *sock, - rxrpc_interceptor_t interceptor) +void rxrpc_kernel_new_call_notification( + struct socket *sock, + rxrpc_notify_new_call_t notify_new_call) { struct rxrpc_sock *rx = rxrpc_sk(sock->sk); - _enter(""); - rx->interceptor = interceptor; + rx->notify_new_call = notify_new_call; } - -EXPORT_SYMBOL(rxrpc_kernel_intercept_rx_messages); +EXPORT_SYMBOL(rxrpc_kernel_new_call_notification); /* * connect an RxRPC socket diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h index ff83fb1ddd47..4e86d248dc5e 100644 --- a/net/rxrpc/ar-internal.h +++ b/net/rxrpc/ar-internal.h @@ -40,6 +40,20 @@ struct rxrpc_crypt { struct rxrpc_connection; /* + * Mark applied to socket buffers. + */ +enum rxrpc_skb_mark { + RXRPC_SKB_MARK_DATA, /* data message */ + RXRPC_SKB_MARK_FINAL_ACK, /* final ACK received message */ + RXRPC_SKB_MARK_BUSY, /* server busy message */ + RXRPC_SKB_MARK_REMOTE_ABORT, /* remote abort message */ + RXRPC_SKB_MARK_LOCAL_ABORT, /* local abort message */ + RXRPC_SKB_MARK_NET_ERROR, /* network error message */ + RXRPC_SKB_MARK_LOCAL_ERROR, /* local error message */ + RXRPC_SKB_MARK_NEW_CALL, /* local error message */ +}; + +/* * sk_state for RxRPC sockets */ enum { @@ -57,7 +71,7 @@ enum { struct rxrpc_sock { /* WARNING: sk has to be the first member */ struct sock sk; - rxrpc_interceptor_t interceptor; /* kernel service Rx interceptor function */ + rxrpc_notify_new_call_t notify_new_call; /* Func to notify of new call */ struct rxrpc_local *local; /* local endpoint */ struct list_head listen_link; /* link in the local endpoint's listen list */ struct list_head secureq; /* calls awaiting connection security clearance */ @@ -255,6 +269,9 @@ enum rxrpc_conn_flag { RXRPC_CONN_HAS_IDR, /* Has a client conn ID assigned */ RXRPC_CONN_IN_SERVICE_CONNS, /* Conn is in peer->service_conns */ RXRPC_CONN_IN_CLIENT_CONNS, /* Conn is in local->client_conns */ + RXRPC_CONN_EXPOSED, /* Conn has extra ref for exposure */ + RXRPC_CONN_DONT_REUSE, /* Don't reuse this connection */ + RXRPC_CONN_COUNTED, /* Counted by rxrpc_nr_client_conns */ }; /* @@ -265,6 +282,17 @@ enum rxrpc_conn_event { }; /* + * The connection cache state. + */ +enum rxrpc_conn_cache_state { + RXRPC_CONN_CLIENT_INACTIVE, /* Conn is not yet listed */ + RXRPC_CONN_CLIENT_WAITING, /* Conn is on wait list, waiting for capacity */ + RXRPC_CONN_CLIENT_ACTIVE, /* Conn is on active list, doing calls */ + RXRPC_CONN_CLIENT_CULLED, /* Conn is culled and delisted, doing calls */ + RXRPC_CONN_CLIENT_IDLE, /* Conn is on idle list, doing mostly nothing */ +}; + +/* * The connection protocol state. */ enum rxrpc_conn_proto_state { @@ -275,7 +303,6 @@ enum rxrpc_conn_proto_state { RXRPC_CONN_SERVICE, /* Service secured connection */ RXRPC_CONN_REMOTELY_ABORTED, /* Conn aborted by peer */ RXRPC_CONN_LOCALLY_ABORTED, /* Conn aborted locally */ - RXRPC_CONN_NETWORK_ERROR, /* Conn terminated by network error */ RXRPC_CONN__NR_STATES }; @@ -288,23 +315,33 @@ struct rxrpc_connection { struct rxrpc_conn_proto proto; struct rxrpc_conn_parameters params; - spinlock_t channel_lock; + atomic_t usage; + struct rcu_head rcu; + struct list_head cache_link; + spinlock_t channel_lock; + unsigned char active_chans; /* Mask of active channels */ +#define RXRPC_ACTIVE_CHANS_MASK ((1 << RXRPC_MAXCALLS) - 1) + struct list_head waiting_calls; /* Calls waiting for channels */ struct rxrpc_channel { struct rxrpc_call __rcu *call; /* Active call */ u32 call_id; /* ID of current call */ u32 call_counter; /* Call ID counter */ u32 last_call; /* ID of last call */ - u32 last_result; /* Result of last call (0/abort) */ + u8 last_type; /* Type of last packet */ + u16 last_service_id; + union { + u32 last_seq; + u32 last_abort; + }; } channels[RXRPC_MAXCALLS]; - wait_queue_head_t channel_wq; /* queue to wait for channel to become available */ - struct rcu_head rcu; struct work_struct processor; /* connection event processor */ union { struct rb_node client_node; /* Node in local->client_conns */ struct rb_node service_node; /* Node in peer->service_conns */ }; + struct list_head proc_link; /* link in procfs list */ struct list_head link; /* link in master connection list */ struct sk_buff_head rx_queue; /* received conn-level packets */ const struct rxrpc_security *security; /* applied security module */ @@ -313,17 +350,15 @@ struct rxrpc_connection { struct rxrpc_crypt csum_iv; /* packet checksum base */ unsigned long flags; unsigned long events; - unsigned long put_time; /* Time at which last put */ + unsigned long idle_timestamp; /* Time at which last became idle */ spinlock_t state_lock; /* state-change lock */ - atomic_t usage; + enum rxrpc_conn_cache_state cache_state : 8; enum rxrpc_conn_proto_state state : 8; /* current state of connection */ u32 local_abort; /* local abort code */ u32 remote_abort; /* remote abort code */ - int error; /* local error incurred */ int debug_id; /* debug ID for printks */ atomic_t serial; /* packet serial number counter */ - atomic_t hi_serial; /* highest serial number received */ - atomic_t avail_chans; /* number of channels available */ + unsigned int hi_serial; /* highest serial number received */ u8 size_align; /* data size alignment (for security) */ u8 header_size; /* rxrpc + security header size */ u8 security_size; /* security header size */ @@ -341,10 +376,12 @@ enum rxrpc_call_flag { RXRPC_CALL_RCVD_LAST, /* all packets received */ RXRPC_CALL_RUN_RTIMER, /* Tx resend timer started */ RXRPC_CALL_TX_SOFT_ACK, /* sent some soft ACKs */ - RXRPC_CALL_PROC_BUSY, /* the processor is busy */ RXRPC_CALL_INIT_ACCEPT, /* acceptance was initiated */ RXRPC_CALL_HAS_USERID, /* has a user ID attached */ RXRPC_CALL_EXPECT_OOS, /* expect out of sequence packets */ + RXRPC_CALL_IS_SERVICE, /* Call is service call */ + RXRPC_CALL_EXPOSED, /* The call was exposed to the world */ + RXRPC_CALL_RX_NO_MORE, /* Don't indicate MSG_MORE from recvmsg() */ }; /* @@ -386,13 +423,22 @@ enum rxrpc_call_state { RXRPC_CALL_SERVER_ACK_REQUEST, /* - server pending ACK of request */ RXRPC_CALL_SERVER_SEND_REPLY, /* - server sending reply */ RXRPC_CALL_SERVER_AWAIT_ACK, /* - server awaiting final ACK */ - RXRPC_CALL_COMPLETE, /* - call completed */ + RXRPC_CALL_COMPLETE, /* - call complete */ + RXRPC_CALL_DEAD, /* - call is dead */ + NR__RXRPC_CALL_STATES +}; + +/* + * Call completion condition (state == RXRPC_CALL_COMPLETE). + */ +enum rxrpc_call_completion { + RXRPC_CALL_SUCCEEDED, /* - Normal termination */ RXRPC_CALL_SERVER_BUSY, /* - call rejected by busy server */ RXRPC_CALL_REMOTELY_ABORTED, /* - call aborted by peer */ RXRPC_CALL_LOCALLY_ABORTED, /* - call aborted locally on error or close */ + RXRPC_CALL_LOCAL_ERROR, /* - call failed due to local error */ RXRPC_CALL_NETWORK_ERROR, /* - call terminated by network error */ - RXRPC_CALL_DEAD, /* - call is dead */ - NR__RXRPC_CALL_STATES + NR__RXRPC_CALL_COMPLETIONS }; /* @@ -402,6 +448,7 @@ enum rxrpc_call_state { struct rxrpc_call { struct rcu_head rcu; struct rxrpc_connection *conn; /* connection carrying call */ + struct rxrpc_peer *peer; /* Peer record for remote address */ struct rxrpc_sock *socket; /* socket responsible */ struct timer_list lifetimer; /* lifetime remaining on call */ struct timer_list deadspan; /* reap timer for re-ACK'ing, etc */ @@ -409,14 +456,17 @@ struct rxrpc_call { struct timer_list resend_timer; /* Tx resend timer */ struct work_struct destroyer; /* call destroyer */ struct work_struct processor; /* packet processor and ACK generator */ + rxrpc_notify_rx_t notify_rx; /* kernel service Rx notification function */ struct list_head link; /* link in master call list */ + struct list_head chan_wait_link; /* Link in conn->waiting_calls */ struct hlist_node error_link; /* link in error distribution list */ struct list_head accept_link; /* calls awaiting acceptance */ struct rb_node sock_node; /* node in socket call tree */ struct sk_buff_head rx_queue; /* received packets */ struct sk_buff_head rx_oos_queue; /* packets received out of sequence */ + struct sk_buff_head knlrecv_queue; /* Queue for kernel_recv [TODO: replace this] */ struct sk_buff *tx_pending; /* Tx socket buffer being filled */ - wait_queue_head_t tx_waitq; /* wait for Tx window space to become available */ + wait_queue_head_t waitq; /* Wait queue for channel or Tx */ __be32 crypto_buf[2]; /* Temporary packet crypto buffer */ unsigned long user_call_ID; /* user-defined call ID */ unsigned long creation_jif; /* time of call creation */ @@ -424,16 +474,17 @@ struct rxrpc_call { unsigned long events; spinlock_t lock; rwlock_t state_lock; /* lock for state transition */ + u32 abort_code; /* Local/remote abort code */ + int error; /* Local error incurred */ + enum rxrpc_call_state state : 8; /* current state of call */ + enum rxrpc_call_completion completion : 8; /* Call completion condition */ atomic_t usage; atomic_t skb_count; /* Outstanding packets on this call */ atomic_t sequence; /* Tx data packet sequence counter */ - u32 local_abort; /* local abort code */ - u32 remote_abort; /* remote abort code */ - int error_report; /* Network error (ICMP/local transport) */ - int error; /* Local error incurred */ - enum rxrpc_call_state state : 8; /* current state of call */ + u16 service_id; /* service ID */ + u32 call_id; /* call ID on connection */ + u32 cid; /* connection ID plus channel index */ int debug_id; /* debug ID for printks */ - u8 channel; /* connection channel occupied by this call */ /* transmission-phase ACK management */ u8 acks_head; /* offset into window of first entry */ @@ -455,34 +506,16 @@ struct rxrpc_call { rxrpc_seq_t ackr_win_top; /* top of ACK window (rx_data_eaten is bottom) */ rxrpc_seq_t ackr_prev_seq; /* previous sequence number received */ u8 ackr_reason; /* reason to ACK */ + u16 ackr_skew; /* skew on packet being ACK'd */ rxrpc_serial_t ackr_serial; /* serial of packet being ACK'd */ atomic_t ackr_not_idle; /* number of packets in Rx queue */ /* received packet records, 1 bit per record */ #define RXRPC_ACKR_WINDOW_ASZ DIV_ROUND_UP(RXRPC_MAXACKS, BITS_PER_LONG) unsigned long ackr_window[RXRPC_ACKR_WINDOW_ASZ + 1]; - - u8 in_clientflag; /* Copy of conn->in_clientflag */ - struct rxrpc_local *local; /* Local endpoint. */ - u32 call_id; /* call ID on connection */ - u32 cid; /* connection ID plus channel index */ - u32 epoch; /* epoch of this connection */ - u16 service_id; /* service ID */ }; -/* - * locally abort an RxRPC call - */ -static inline void rxrpc_abort_call(struct rxrpc_call *call, u32 abort_code) -{ - write_lock_bh(&call->state_lock); - if (call->state < RXRPC_CALL_COMPLETE) { - call->local_abort = abort_code; - call->state = RXRPC_CALL_LOCALLY_ABORTED; - set_bit(RXRPC_CALL_EV_ABORT, &call->events); - } - write_unlock_bh(&call->state_lock); -} +#include <trace/events/rxrpc.h> /* * af_rxrpc.c @@ -496,19 +529,22 @@ extern struct workqueue_struct *rxrpc_workqueue; * call_accept.c */ void rxrpc_accept_incoming_calls(struct rxrpc_local *); -struct rxrpc_call *rxrpc_accept_call(struct rxrpc_sock *, unsigned long); +struct rxrpc_call *rxrpc_accept_call(struct rxrpc_sock *, unsigned long, + rxrpc_notify_rx_t); int rxrpc_reject_call(struct rxrpc_sock *); /* * call_event.c */ -void __rxrpc_propose_ACK(struct rxrpc_call *, u8, u32, bool); -void rxrpc_propose_ACK(struct rxrpc_call *, u8, u32, bool); +void __rxrpc_propose_ACK(struct rxrpc_call *, u8, u16, u32, bool); +void rxrpc_propose_ACK(struct rxrpc_call *, u8, u16, u32, bool); void rxrpc_process_call(struct work_struct *); /* * call_object.c */ +extern const char *const rxrpc_call_states[]; +extern const char *const rxrpc_call_completions[]; extern unsigned int rxrpc_max_call_lifetime; extern unsigned int rxrpc_dead_call_expiry; extern struct kmem_cache *rxrpc_call_jar; @@ -525,18 +561,111 @@ struct rxrpc_call *rxrpc_incoming_call(struct rxrpc_sock *, struct sk_buff *); void rxrpc_release_call(struct rxrpc_call *); void rxrpc_release_calls_on_socket(struct rxrpc_sock *); -void __rxrpc_put_call(struct rxrpc_call *); +void rxrpc_see_call(struct rxrpc_call *); +void rxrpc_get_call(struct rxrpc_call *); +void rxrpc_put_call(struct rxrpc_call *); +void rxrpc_get_call_for_skb(struct rxrpc_call *, struct sk_buff *); +void rxrpc_put_call_for_skb(struct rxrpc_call *, struct sk_buff *); void __exit rxrpc_destroy_all_calls(void); +static inline bool rxrpc_is_service_call(const struct rxrpc_call *call) +{ + return test_bit(RXRPC_CALL_IS_SERVICE, &call->flags); +} + +static inline bool rxrpc_is_client_call(const struct rxrpc_call *call) +{ + return !rxrpc_is_service_call(call); +} + +/* + * Transition a call to the complete state. + */ +static inline bool __rxrpc_set_call_completion(struct rxrpc_call *call, + enum rxrpc_call_completion compl, + u32 abort_code, + int error) +{ + if (call->state < RXRPC_CALL_COMPLETE) { + call->abort_code = abort_code; + call->error = error; + call->completion = compl, + call->state = RXRPC_CALL_COMPLETE; + return true; + } + return false; +} + +static inline bool rxrpc_set_call_completion(struct rxrpc_call *call, + enum rxrpc_call_completion compl, + u32 abort_code, + int error) +{ + int ret; + + write_lock_bh(&call->state_lock); + ret = __rxrpc_set_call_completion(call, compl, abort_code, error); + write_unlock_bh(&call->state_lock); + return ret; +} + +/* + * Record that a call successfully completed. + */ +static inline void __rxrpc_call_completed(struct rxrpc_call *call) +{ + __rxrpc_set_call_completion(call, RXRPC_CALL_SUCCEEDED, 0, 0); +} + +static inline void rxrpc_call_completed(struct rxrpc_call *call) +{ + write_lock_bh(&call->state_lock); + __rxrpc_call_completed(call); + write_unlock_bh(&call->state_lock); +} + +/* + * Record that a call is locally aborted. + */ +static inline bool __rxrpc_abort_call(struct rxrpc_call *call, + u32 abort_code, int error) +{ + if (__rxrpc_set_call_completion(call, + RXRPC_CALL_LOCALLY_ABORTED, + abort_code, error)) { + set_bit(RXRPC_CALL_EV_ABORT, &call->events); + return true; + } + return false; +} + +static inline bool rxrpc_abort_call(struct rxrpc_call *call, + u32 abort_code, int error) +{ + bool ret; + + write_lock_bh(&call->state_lock); + ret = __rxrpc_abort_call(call, abort_code, error); + write_unlock_bh(&call->state_lock); + return ret; +} + /* * conn_client.c */ +extern unsigned int rxrpc_max_client_connections; +extern unsigned int rxrpc_reap_client_connections; +extern unsigned int rxrpc_conn_idle_client_expiry; +extern unsigned int rxrpc_conn_idle_client_fast_expiry; extern struct idr rxrpc_client_conn_ids; void rxrpc_destroy_client_conn_ids(void); int rxrpc_connect_call(struct rxrpc_call *, struct rxrpc_conn_parameters *, struct sockaddr_rxrpc *, gfp_t); -void rxrpc_unpublish_client_conn(struct rxrpc_connection *); +void rxrpc_expose_client_call(struct rxrpc_call *); +void rxrpc_disconnect_client_call(struct rxrpc_call *); +void rxrpc_put_client_conn(struct rxrpc_connection *); +void __exit rxrpc_destroy_all_client_connections(void); /* * conn_event.c @@ -550,15 +679,17 @@ void rxrpc_reject_packets(struct rxrpc_local *); */ extern unsigned int rxrpc_connection_expiry; extern struct list_head rxrpc_connections; +extern struct list_head rxrpc_connection_proc_list; extern rwlock_t rxrpc_connection_lock; int rxrpc_extract_addr_from_skb(struct sockaddr_rxrpc *, struct sk_buff *); struct rxrpc_connection *rxrpc_alloc_connection(gfp_t); struct rxrpc_connection *rxrpc_find_connection_rcu(struct rxrpc_local *, struct sk_buff *); -void __rxrpc_disconnect_call(struct rxrpc_call *); +void __rxrpc_disconnect_call(struct rxrpc_connection *, struct rxrpc_call *); void rxrpc_disconnect_call(struct rxrpc_call *); -void rxrpc_put_connection(struct rxrpc_connection *); +void rxrpc_kill_connection(struct rxrpc_connection *); +void __rxrpc_put_connection(struct rxrpc_connection *); void __exit rxrpc_destroy_all_connections(void); static inline bool rxrpc_conn_is_client(const struct rxrpc_connection *conn) @@ -582,6 +713,21 @@ struct rxrpc_connection *rxrpc_get_connection_maybe(struct rxrpc_connection *con return atomic_inc_not_zero(&conn->usage) ? conn : NULL; } +static inline void rxrpc_put_connection(struct rxrpc_connection *conn) +{ + if (!conn) + return; + + if (rxrpc_conn_is_client(conn)) { + if (atomic_dec_and_test(&conn->usage)) + rxrpc_put_client_conn(conn); + } else { + if (atomic_dec_return(&conn->usage) == 1) + __rxrpc_put_connection(conn); + } +} + + static inline bool rxrpc_queue_conn(struct rxrpc_connection *conn) { if (!rxrpc_get_connection_maybe(conn)) @@ -697,9 +843,10 @@ struct rxrpc_peer *rxrpc_lookup_peer(struct rxrpc_local *, struct sockaddr_rxrpc *, gfp_t); struct rxrpc_peer *rxrpc_alloc_peer(struct rxrpc_local *, gfp_t); -static inline void rxrpc_get_peer(struct rxrpc_peer *peer) +static inline struct rxrpc_peer *rxrpc_get_peer(struct rxrpc_peer *peer) { atomic_inc(&peer->usage); + return peer; } static inline @@ -718,7 +865,6 @@ static inline void rxrpc_put_peer(struct rxrpc_peer *peer) /* * proc.c */ -extern const char *const rxrpc_call_states[]; extern const struct file_operations rxrpc_call_seq_fops; extern const struct file_operations rxrpc_connection_seq_fops; @@ -746,7 +892,13 @@ int rxrpc_init_server_conn_security(struct rxrpc_connection *); /* * skbuff.c */ +void rxrpc_kernel_data_consumed(struct rxrpc_call *, struct sk_buff *); void rxrpc_packet_destructor(struct sk_buff *); +void rxrpc_new_skb(struct sk_buff *); +void rxrpc_see_skb(struct sk_buff *); +void rxrpc_get_skb(struct sk_buff *); +void rxrpc_free_skb(struct sk_buff *); +void rxrpc_purge_queue(struct sk_buff_head *); /* * sysctl.c @@ -893,54 +1045,3 @@ do { \ } while (0) #endif /* __KDEBUGALL */ - -/* - * socket buffer accounting / leak finding - */ -static inline void __rxrpc_new_skb(struct sk_buff *skb, const char *fn) -{ - //_net("new skb %p %s [%d]", skb, fn, atomic_read(&rxrpc_n_skbs)); - //atomic_inc(&rxrpc_n_skbs); -} - -#define rxrpc_new_skb(skb) __rxrpc_new_skb((skb), __func__) - -static inline void __rxrpc_kill_skb(struct sk_buff *skb, const char *fn) -{ - //_net("kill skb %p %s [%d]", skb, fn, atomic_read(&rxrpc_n_skbs)); - //atomic_dec(&rxrpc_n_skbs); -} - -#define rxrpc_kill_skb(skb) __rxrpc_kill_skb((skb), __func__) - -static inline void __rxrpc_free_skb(struct sk_buff *skb, const char *fn) -{ - if (skb) { - CHECK_SLAB_OKAY(&skb->users); - //_net("free skb %p %s [%d]", - // skb, fn, atomic_read(&rxrpc_n_skbs)); - //atomic_dec(&rxrpc_n_skbs); - kfree_skb(skb); - } -} - -#define rxrpc_free_skb(skb) __rxrpc_free_skb((skb), __func__) - -static inline void rxrpc_purge_queue(struct sk_buff_head *list) -{ - struct sk_buff *skb; - while ((skb = skb_dequeue((list))) != NULL) - rxrpc_free_skb(skb); -} - -#define rxrpc_get_call(CALL) \ -do { \ - CHECK_SLAB_OKAY(&(CALL)->usage); \ - if (atomic_inc_return(&(CALL)->usage) == 1) \ - BUG(); \ -} while (0) - -#define rxrpc_put_call(CALL) \ -do { \ - __rxrpc_put_call(CALL); \ -} while (0) diff --git a/net/rxrpc/call_accept.c b/net/rxrpc/call_accept.c index 9bae21e66d65..68a439e30df1 100644 --- a/net/rxrpc/call_accept.c +++ b/net/rxrpc/call_accept.c @@ -129,8 +129,7 @@ static int rxrpc_accept_incoming_call(struct rxrpc_local *local, _debug("conn ready"); call->state = RXRPC_CALL_SERVER_ACCEPTING; list_add_tail(&call->accept_link, &rx->acceptq); - rxrpc_get_call(call); - atomic_inc(&call->skb_count); + rxrpc_get_call_for_skb(call, notification); nsp = rxrpc_skb(notification); nsp->call = call; @@ -203,6 +202,7 @@ void rxrpc_accept_incoming_calls(struct rxrpc_local *local) _net("incoming call skb %p", skb); + rxrpc_see_skb(skb); sp = rxrpc_skb(skb); /* Set up a response packet header in case we need it */ @@ -286,7 +286,8 @@ security_mismatch: * - assign the user call ID to the call at the front of the queue */ struct rxrpc_call *rxrpc_accept_call(struct rxrpc_sock *rx, - unsigned long user_call_ID) + unsigned long user_call_ID, + rxrpc_notify_rx_t notify_rx) { struct rxrpc_call *call; struct rb_node *parent, **pp; @@ -322,18 +323,15 @@ struct rxrpc_call *rxrpc_accept_call(struct rxrpc_sock *rx, call = list_entry(rx->acceptq.next, struct rxrpc_call, accept_link); list_del_init(&call->accept_link); sk_acceptq_removed(&rx->sk); + rxrpc_see_call(call); write_lock_bh(&call->state_lock); switch (call->state) { case RXRPC_CALL_SERVER_ACCEPTING: call->state = RXRPC_CALL_SERVER_RECV_REQUEST; break; - case RXRPC_CALL_REMOTELY_ABORTED: - case RXRPC_CALL_LOCALLY_ABORTED: - ret = -ECONNABORTED; - goto out_release; - case RXRPC_CALL_NETWORK_ERROR: - ret = call->conn->error; + case RXRPC_CALL_COMPLETE: + ret = call->error; goto out_release; case RXRPC_CALL_DEAD: ret = -ETIME; @@ -343,6 +341,7 @@ struct rxrpc_call *rxrpc_accept_call(struct rxrpc_sock *rx, } /* formalise the acceptance */ + call->notify_rx = notify_rx; call->user_call_ID = user_call_ID; rb_link_node(&call->sock_node, parent, pp); rb_insert_color(&call->sock_node, &rx->calls); @@ -398,21 +397,19 @@ int rxrpc_reject_call(struct rxrpc_sock *rx) call = list_entry(rx->acceptq.next, struct rxrpc_call, accept_link); list_del_init(&call->accept_link); sk_acceptq_removed(&rx->sk); + rxrpc_see_call(call); write_lock_bh(&call->state_lock); switch (call->state) { case RXRPC_CALL_SERVER_ACCEPTING: - call->state = RXRPC_CALL_SERVER_BUSY; + __rxrpc_set_call_completion(call, RXRPC_CALL_SERVER_BUSY, + 0, ECONNABORTED); if (test_and_set_bit(RXRPC_CALL_EV_REJECT_BUSY, &call->events)) rxrpc_queue_call(call); ret = 0; goto out_release; - case RXRPC_CALL_REMOTELY_ABORTED: - case RXRPC_CALL_LOCALLY_ABORTED: - ret = -ECONNABORTED; - goto out_release; - case RXRPC_CALL_NETWORK_ERROR: - ret = call->conn->error; + case RXRPC_CALL_COMPLETE: + ret = call->error; goto out_release; case RXRPC_CALL_DEAD: ret = -ETIME; @@ -442,17 +439,20 @@ out: * rxrpc_kernel_accept_call - Allow a kernel service to accept an incoming call * @sock: The socket on which the impending call is waiting * @user_call_ID: The tag to attach to the call + * @notify_rx: Where to send notifications instead of socket queue * * Allow a kernel service to accept an incoming call, assuming the incoming - * call is still valid. + * call is still valid. The caller should immediately trigger their own + * notification as there must be data waiting. */ struct rxrpc_call *rxrpc_kernel_accept_call(struct socket *sock, - unsigned long user_call_ID) + unsigned long user_call_ID, + rxrpc_notify_rx_t notify_rx) { struct rxrpc_call *call; _enter(",%lx", user_call_ID); - call = rxrpc_accept_call(rxrpc_sk(sock->sk), user_call_ID); + call = rxrpc_accept_call(rxrpc_sk(sock->sk), user_call_ID, notify_rx); _leave(" = %p", call); return call; } diff --git a/net/rxrpc/call_event.c b/net/rxrpc/call_event.c index f5e99163a09e..de72de662044 100644 --- a/net/rxrpc/call_event.c +++ b/net/rxrpc/call_event.c @@ -25,7 +25,7 @@ * propose an ACK be sent */ void __rxrpc_propose_ACK(struct rxrpc_call *call, u8 ack_reason, - u32 serial, bool immediate) + u16 skew, u32 serial, bool immediate) { unsigned long expiry; s8 prior = rxrpc_ack_priority[ack_reason]; @@ -44,8 +44,10 @@ void __rxrpc_propose_ACK(struct rxrpc_call *call, u8 ack_reason, /* update DELAY, IDLE, REQUESTED and PING_RESPONSE ACK serial * numbers */ if (prior == rxrpc_ack_priority[call->ackr_reason]) { - if (prior <= 4) + if (prior <= 4) { + call->ackr_skew = skew; call->ackr_serial = serial; + } if (immediate) goto cancel_timer; return; @@ -93,7 +95,7 @@ cancel_timer: _debug("cancel timer %%%u", serial); try_to_del_timer_sync(&call->ack_timer); read_lock_bh(&call->state_lock); - if (call->state <= RXRPC_CALL_COMPLETE && + if (call->state < RXRPC_CALL_COMPLETE && !test_and_set_bit(RXRPC_CALL_EV_ACK, &call->events)) rxrpc_queue_call(call); read_unlock_bh(&call->state_lock); @@ -103,13 +105,13 @@ cancel_timer: * propose an ACK be sent, locking the call structure */ void rxrpc_propose_ACK(struct rxrpc_call *call, u8 ack_reason, - u32 serial, bool immediate) + u16 skew, u32 serial, bool immediate) { s8 prior = rxrpc_ack_priority[ack_reason]; if (prior > rxrpc_ack_priority[call->ackr_reason]) { spin_lock_bh(&call->lock); - __rxrpc_propose_ACK(call, ack_reason, serial, immediate); + __rxrpc_propose_ACK(call, ack_reason, skew, serial, immediate); spin_unlock_bh(&call->lock); } } @@ -121,7 +123,7 @@ static void rxrpc_set_resend(struct rxrpc_call *call, u8 resend, unsigned long resend_at) { read_lock_bh(&call->state_lock); - if (call->state >= RXRPC_CALL_COMPLETE) + if (call->state == RXRPC_CALL_COMPLETE) resend = 0; if (resend & 1) { @@ -191,6 +193,8 @@ static void rxrpc_resend(struct rxrpc_call *call) stop = true; sp->resend_at = jiffies + 3; } else { + if (rxrpc_is_client_call(call)) + rxrpc_expose_client_call(call); sp->resend_at = jiffies + rxrpc_resend_timeout; } @@ -226,7 +230,7 @@ static void rxrpc_resend_timer(struct rxrpc_call *call) _enter("%d,%d,%d", call->acks_tail, call->acks_unacked, call->acks_head); - if (call->state >= RXRPC_CALL_COMPLETE) + if (call->state == RXRPC_CALL_COMPLETE) return; resend = 0; @@ -376,7 +380,7 @@ static void rxrpc_rotate_tx_window(struct rxrpc_call *call, u32 hard) call->acks_hard++; } - wake_up(&call->tx_waitq); + wake_up(&call->waitq); } /* @@ -407,6 +411,7 @@ static int rxrpc_drain_rx_oos_queue(struct rxrpc_call *call) skb = skb_dequeue(&call->rx_oos_queue); if (skb) { + rxrpc_see_skb(skb); sp = rxrpc_skb(skb); _debug("drain OOS packet %d [%d]", @@ -427,6 +432,7 @@ static int rxrpc_drain_rx_oos_queue(struct rxrpc_call *call) /* find out what the next packet is */ skb = skb_peek(&call->rx_oos_queue); + rxrpc_see_skb(skb); if (skb) call->rx_first_oos = rxrpc_skb(skb)->hdr.seq; else @@ -459,8 +465,7 @@ static void rxrpc_insert_oos_packet(struct rxrpc_call *call, skb->destructor = rxrpc_packet_destructor; ASSERTCMP(sp->call, ==, NULL); sp->call = call; - rxrpc_get_call(call); - atomic_inc(&call->skb_count); + rxrpc_get_call_for_skb(call, skb); /* insert into the buffer in sequence order */ spin_lock_bh(&call->lock); @@ -546,7 +551,7 @@ static void rxrpc_extract_ackinfo(struct rxrpc_call *call, struct sk_buff *skb, mtu = min(ntohl(ackinfo.rxMTU), ntohl(ackinfo.maxMTU)); - peer = call->conn->params.peer; + peer = call->peer; if (mtu < peer->maxdata) { spin_lock_bh(&peer->lock); peer->maxdata = mtu; @@ -576,6 +581,7 @@ process_further: if (!skb) return -EAGAIN; + rxrpc_see_skb(skb); _net("deferred skb %p", skb); sp = rxrpc_skb(skb); @@ -625,7 +631,7 @@ process_further: if (ack.reason == RXRPC_ACK_PING) { _proto("Rx ACK %%%u PING Request", latest); rxrpc_propose_ACK(call, RXRPC_ACK_PING_RESPONSE, - sp->hdr.serial, true); + skb->priority, sp->hdr.serial, true); } /* discard any out-of-order or duplicate ACKs */ @@ -704,7 +710,7 @@ all_acked: break; case RXRPC_CALL_SERVER_AWAIT_ACK: _debug("srv complete"); - call->state = RXRPC_CALL_COMPLETE; + __rxrpc_call_completed(call); post_ACK = true; break; case RXRPC_CALL_CLIENT_SEND_REQUEST: @@ -734,8 +740,7 @@ all_acked: _debug("post ACK"); skb->mark = RXRPC_SKB_MARK_FINAL_ACK; sp->call = call; - rxrpc_get_call(call); - atomic_inc(&call->skb_count); + rxrpc_get_call_for_skb(call, skb); spin_lock_bh(&call->lock); if (rxrpc_queue_rcv_skb(call, skb, true, true) < 0) BUG(); @@ -794,8 +799,7 @@ static int rxrpc_post_message(struct rxrpc_call *call, u32 mark, u32 error, memset(sp, 0, sizeof(*sp)); sp->error = error; sp->call = call; - rxrpc_get_call(call); - atomic_inc(&call->skb_count); + rxrpc_get_call_for_skb(call, skb); spin_lock_bh(&call->lock); ret = rxrpc_queue_rcv_skb(call, skb, true, fatal); @@ -827,20 +831,20 @@ void rxrpc_process_call(struct work_struct *work) u32 serial, abort_code = RX_PROTOCOL_ERROR; u8 *acks = NULL; + rxrpc_see_call(call); + //printk("\n--------------------\n"); _enter("{%d,%s,%lx} [%lu]", call->debug_id, rxrpc_call_states[call->state], call->events, (jiffies - call->creation_jif) / (HZ / 10)); - if (test_and_set_bit(RXRPC_CALL_PROC_BUSY, &call->flags)) { - _debug("XXXXXXXXXXXXX RUNNING ON MULTIPLE CPUS XXXXXXXXXXXXX"); - return; - } + if (!call->conn) + goto skip_msg_init; /* there's a good chance we're going to have to send a message, so set * one up in advance */ - msg.msg_name = &call->conn->params.peer->srx.transport; - msg.msg_namelen = call->conn->params.peer->srx.transport_len; + msg.msg_name = &call->peer->srx.transport; + msg.msg_namelen = call->peer->srx.transport_len; msg.msg_control = NULL; msg.msg_controllen = 0; msg.msg_flags = 0; @@ -859,6 +863,7 @@ void rxrpc_process_call(struct work_struct *work) memset(iov, 0, sizeof(iov)); iov[0].iov_base = &whdr; iov[0].iov_len = sizeof(whdr); +skip_msg_init: /* deal with events of a final nature */ if (test_bit(RXRPC_CALL_EV_RCVD_ERROR, &call->events)) { @@ -869,24 +874,22 @@ void rxrpc_process_call(struct work_struct *work) clear_bit(RXRPC_CALL_EV_REJECT_BUSY, &call->events); clear_bit(RXRPC_CALL_EV_ABORT, &call->events); - error = call->error_report; - if (error < RXRPC_LOCAL_ERROR_OFFSET) { + if (call->completion == RXRPC_CALL_NETWORK_ERROR) { mark = RXRPC_SKB_MARK_NET_ERROR; _debug("post net error %d", error); } else { mark = RXRPC_SKB_MARK_LOCAL_ERROR; - error -= RXRPC_LOCAL_ERROR_OFFSET; _debug("post net local error %d", error); } - if (rxrpc_post_message(call, mark, error, true) < 0) + if (rxrpc_post_message(call, mark, call->error, true) < 0) goto no_mem; clear_bit(RXRPC_CALL_EV_RCVD_ERROR, &call->events); goto kill_ACKs; } if (test_bit(RXRPC_CALL_EV_CONN_ABORT, &call->events)) { - ASSERTCMP(call->state, >, RXRPC_CALL_COMPLETE); + ASSERTCMP(call->state, ==, RXRPC_CALL_COMPLETE); clear_bit(RXRPC_CALL_EV_REJECT_BUSY, &call->events); clear_bit(RXRPC_CALL_EV_ABORT, &call->events); @@ -894,7 +897,7 @@ void rxrpc_process_call(struct work_struct *work) _debug("post conn abort"); if (rxrpc_post_message(call, RXRPC_SKB_MARK_LOCAL_ERROR, - call->conn->error, true) < 0) + call->error, true) < 0) goto no_mem; clear_bit(RXRPC_CALL_EV_CONN_ABORT, &call->events); goto kill_ACKs; @@ -907,13 +910,13 @@ void rxrpc_process_call(struct work_struct *work) } if (test_bit(RXRPC_CALL_EV_ABORT, &call->events)) { - ASSERTCMP(call->state, >, RXRPC_CALL_COMPLETE); + ASSERTCMP(call->state, ==, RXRPC_CALL_COMPLETE); if (rxrpc_post_message(call, RXRPC_SKB_MARK_LOCAL_ERROR, - ECONNABORTED, true) < 0) + call->error, true) < 0) goto no_mem; whdr.type = RXRPC_PACKET_TYPE_ABORT; - data = htonl(call->local_abort); + data = htonl(call->abort_code); iov[1].iov_base = &data; iov[1].iov_len = sizeof(data); genbit = RXRPC_CALL_EV_ABORT; @@ -973,13 +976,7 @@ void rxrpc_process_call(struct work_struct *work) } if (test_bit(RXRPC_CALL_EV_LIFE_TIMER, &call->events)) { - write_lock_bh(&call->state_lock); - if (call->state <= RXRPC_CALL_COMPLETE) { - call->state = RXRPC_CALL_LOCALLY_ABORTED; - call->local_abort = RX_CALL_TIMEOUT; - set_bit(RXRPC_CALL_EV_ABORT, &call->events); - } - write_unlock_bh(&call->state_lock); + rxrpc_abort_call(call, RX_CALL_TIMEOUT, ETIME); _debug("post timeout"); if (rxrpc_post_message(call, RXRPC_SKB_MARK_LOCAL_ERROR, @@ -992,7 +989,8 @@ void rxrpc_process_call(struct work_struct *work) /* deal with assorted inbound messages */ if (!skb_queue_empty(&call->rx_queue)) { - switch (rxrpc_process_rx_queue(call, &abort_code)) { + ret = rxrpc_process_rx_queue(call, &abort_code); + switch (ret) { case 0: case -EAGAIN: break; @@ -1001,7 +999,7 @@ void rxrpc_process_call(struct work_struct *work) case -EKEYEXPIRED: case -EKEYREJECTED: case -EPROTO: - rxrpc_abort_call(call, abort_code); + rxrpc_abort_call(call, abort_code, -ret); goto kill_ACKs; } } @@ -1151,11 +1149,10 @@ void rxrpc_process_call(struct work_struct *work) goto maybe_reschedule; send_ACK_with_skew: - ack.maxSkew = htons(atomic_read(&call->conn->hi_serial) - - ntohl(ack.serial)); + ack.maxSkew = htons(call->ackr_skew); send_ACK: - mtu = call->conn->params.peer->if_mtu; - mtu -= call->conn->params.peer->hdrsize; + mtu = call->peer->if_mtu; + mtu -= call->peer->hdrsize; ackinfo.maxMTU = htonl(mtu); ackinfo.rwind = htonl(rxrpc_rx_window_size); @@ -1227,10 +1224,7 @@ send_message_2: goto kill_ACKs; case RXRPC_CALL_EV_ACK_FINAL: - write_lock_bh(&call->state_lock); - if (call->state == RXRPC_CALL_CLIENT_FINAL_ACK) - call->state = RXRPC_CALL_COMPLETE; - write_unlock_bh(&call->state_lock); + rxrpc_call_completed(call); goto kill_ACKs; default: @@ -1242,7 +1236,8 @@ send_message_2: case RXRPC_CALL_SERVER_ACK_REQUEST: _debug("start ACK timer"); rxrpc_propose_ACK(call, RXRPC_ACK_DELAY, - call->ackr_serial, false); + call->ackr_skew, call->ackr_serial, + false); default: break; } @@ -1277,7 +1272,6 @@ maybe_reschedule: } error: - clear_bit(RXRPC_CALL_PROC_BUSY, &call->flags); kfree(acks); /* because we don't want two CPUs both processing the work item for one diff --git a/net/rxrpc/call_object.c b/net/rxrpc/call_object.c index c47f14fc5e88..516d8ea82f02 100644 --- a/net/rxrpc/call_object.c +++ b/net/rxrpc/call_object.c @@ -30,7 +30,7 @@ unsigned int rxrpc_max_call_lifetime = 60 * HZ; unsigned int rxrpc_dead_call_expiry = 2 * HZ; const char *const rxrpc_call_states[NR__RXRPC_CALL_STATES] = { - [RXRPC_CALL_UNINITIALISED] = "Uninit", + [RXRPC_CALL_UNINITIALISED] = "Uninit ", [RXRPC_CALL_CLIENT_AWAIT_CONN] = "ClWtConn", [RXRPC_CALL_CLIENT_SEND_REQUEST] = "ClSndReq", [RXRPC_CALL_CLIENT_AWAIT_REPLY] = "ClAwtRpl", @@ -43,11 +43,16 @@ const char *const rxrpc_call_states[NR__RXRPC_CALL_STATES] = { [RXRPC_CALL_SERVER_SEND_REPLY] = "SvSndRpl", [RXRPC_CALL_SERVER_AWAIT_ACK] = "SvAwtACK", [RXRPC_CALL_COMPLETE] = "Complete", + [RXRPC_CALL_DEAD] = "Dead ", +}; + +const char *const rxrpc_call_completions[NR__RXRPC_CALL_COMPLETIONS] = { + [RXRPC_CALL_SUCCEEDED] = "Complete", [RXRPC_CALL_SERVER_BUSY] = "SvBusy ", [RXRPC_CALL_REMOTELY_ABORTED] = "RmtAbort", [RXRPC_CALL_LOCALLY_ABORTED] = "LocAbort", + [RXRPC_CALL_LOCAL_ERROR] = "LocError", [RXRPC_CALL_NETWORK_ERROR] = "NetError", - [RXRPC_CALL_DEAD] = "Dead ", }; struct kmem_cache *rxrpc_call_jar; @@ -127,10 +132,12 @@ static struct rxrpc_call *rxrpc_alloc_call(gfp_t gfp) INIT_WORK(&call->destroyer, &rxrpc_destroy_call); INIT_WORK(&call->processor, &rxrpc_process_call); INIT_LIST_HEAD(&call->link); + INIT_LIST_HEAD(&call->chan_wait_link); INIT_LIST_HEAD(&call->accept_link); skb_queue_head_init(&call->rx_queue); skb_queue_head_init(&call->rx_oos_queue); - init_waitqueue_head(&call->tx_waitq); + skb_queue_head_init(&call->knlrecv_queue); + init_waitqueue_head(&call->waitq); spin_lock_init(&call->lock); rwlock_init(&call->state_lock); atomic_set(&call->usage, 1); @@ -167,10 +174,7 @@ static struct rxrpc_call *rxrpc_alloc_client_call(struct rxrpc_sock *rx, sock_hold(&rx->sk); call->socket = rx; call->rx_data_post = 1; - - call->local = rx->local; call->service_id = srx->srx_service; - call->in_clientflag = 0; _leave(" = %p", call); return call; @@ -216,6 +220,7 @@ struct rxrpc_call *rxrpc_new_client_call(struct rxrpc_sock *rx, { struct rxrpc_call *call, *xcall; struct rb_node *parent, **pp; + const void *here = __builtin_return_address(0); int ret; _enter("%p,%lx", rx, user_call_ID); @@ -226,6 +231,9 @@ struct rxrpc_call *rxrpc_new_client_call(struct rxrpc_sock *rx, return call; } + trace_rxrpc_call(call, 0, atomic_read(&call->usage), 0, here, + (const void *)user_call_ID); + /* Publish the call, even though it is incompletely set up as yet */ call->user_call_ID = user_call_ID; __set_bit(RXRPC_CALL_HAS_USERID, &call->flags); @@ -275,6 +283,7 @@ error: list_del_init(&call->link); write_unlock_bh(&rxrpc_call_lock); + set_bit(RXRPC_CALL_RELEASED, &call->flags); call->state = RXRPC_CALL_DEAD; rxrpc_put_call(call); _leave(" = %d", ret); @@ -287,6 +296,7 @@ error: */ found_user_ID_now_present: write_unlock(&rx->call_lock); + set_bit(RXRPC_CALL_RELEASED, &call->flags); call->state = RXRPC_CALL_DEAD; rxrpc_put_call(call); _leave(" = -EEXIST [%p]", call); @@ -303,6 +313,7 @@ struct rxrpc_call *rxrpc_incoming_call(struct rxrpc_sock *rx, { struct rxrpc_skb_priv *sp = rxrpc_skb(skb); struct rxrpc_call *call, *candidate; + const void *here = __builtin_return_address(0); u32 call_id, chan; _enter(",%d", conn->debug_id); @@ -313,14 +324,18 @@ struct rxrpc_call *rxrpc_incoming_call(struct rxrpc_sock *rx, if (!candidate) return ERR_PTR(-EBUSY); + trace_rxrpc_call(candidate, 1, atomic_read(&candidate->usage), + 0, here, NULL); + chan = sp->hdr.cid & RXRPC_CHANNELMASK; candidate->socket = rx; candidate->conn = conn; + candidate->peer = conn->params.peer; candidate->cid = sp->hdr.cid; candidate->call_id = sp->hdr.callNumber; - candidate->channel = chan; candidate->rx_data_post = 0; candidate->state = RXRPC_CALL_SERVER_ACCEPTING; + candidate->flags |= (1 << RXRPC_CALL_IS_SERVICE); if (conn->security_ix > 0) candidate->state = RXRPC_CALL_SERVER_SECURING; @@ -330,7 +345,7 @@ struct rxrpc_call *rxrpc_incoming_call(struct rxrpc_sock *rx, call = rcu_dereference_protected(conn->channels[chan].call, lockdep_is_held(&conn->channel_lock)); - _debug("channel[%u] is %p", candidate->channel, call); + _debug("channel[%u] is %p", candidate->cid & RXRPC_CHANNELMASK, call); if (call && call->call_id == sp->hdr.callNumber) { /* already set; must've been a duplicate packet */ _debug("extant call [%d]", call->state); @@ -357,8 +372,8 @@ struct rxrpc_call *rxrpc_incoming_call(struct rxrpc_sock *rx, _debug("CALL: %u { %s }", call->debug_id, rxrpc_call_states[call->state]); - if (call->state >= RXRPC_CALL_COMPLETE) { - __rxrpc_disconnect_call(call); + if (call->state == RXRPC_CALL_COMPLETE) { + __rxrpc_disconnect_call(conn, call); } else { spin_unlock(&conn->channel_lock); kmem_cache_free(rxrpc_call_jar, candidate); @@ -385,6 +400,7 @@ struct rxrpc_call *rxrpc_incoming_call(struct rxrpc_sock *rx, rcu_assign_pointer(conn->channels[chan].call, call); sock_hold(&rx->sk); rxrpc_get_connection(conn); + rxrpc_get_peer(call->peer); spin_unlock(&conn->channel_lock); spin_lock(&conn->params.peer->lock); @@ -395,10 +411,7 @@ struct rxrpc_call *rxrpc_incoming_call(struct rxrpc_sock *rx, list_add_tail(&call->link, &rxrpc_calls); write_unlock_bh(&rxrpc_call_lock); - call->local = conn->params.local; - call->epoch = conn->proto.epoch; call->service_id = conn->params.service_id; - call->in_clientflag = RXRPC_CLIENT_INITIATED; _net("CALL incoming %d on CONN %d", call->debug_id, call->conn->debug_id); @@ -427,6 +440,44 @@ old_call: } /* + * Note the re-emergence of a call. + */ +void rxrpc_see_call(struct rxrpc_call *call) +{ + const void *here = __builtin_return_address(0); + if (call) { + int n = atomic_read(&call->usage); + int m = atomic_read(&call->skb_count); + + trace_rxrpc_call(call, 2, n, m, here, 0); + } +} + +/* + * Note the addition of a ref on a call. + */ +void rxrpc_get_call(struct rxrpc_call *call) +{ + const void *here = __builtin_return_address(0); + int n = atomic_inc_return(&call->usage); + int m = atomic_read(&call->skb_count); + + trace_rxrpc_call(call, 3, n, m, here, 0); +} + +/* + * Note the addition of a ref on a call for a socket buffer. + */ +void rxrpc_get_call_for_skb(struct rxrpc_call *call, struct sk_buff *skb) +{ + const void *here = __builtin_return_address(0); + int n = atomic_inc_return(&call->usage); + int m = atomic_inc_return(&call->skb_count); + + trace_rxrpc_call(call, 4, n, m, here, skb); +} + +/* * detach a call from a socket and set up for release */ void rxrpc_release_call(struct rxrpc_call *call) @@ -439,6 +490,8 @@ void rxrpc_release_call(struct rxrpc_call *call) atomic_read(&call->ackr_not_idle), call->rx_first_oos); + rxrpc_see_call(call); + spin_lock_bh(&call->lock); if (test_and_set_bit(RXRPC_CALL_RELEASED, &call->flags)) BUG(); @@ -473,8 +526,7 @@ void rxrpc_release_call(struct rxrpc_call *call) if (call->state < RXRPC_CALL_COMPLETE && call->state != RXRPC_CALL_CLIENT_FINAL_ACK) { _debug("+++ ABORTING STATE %d +++\n", call->state); - call->state = RXRPC_CALL_LOCALLY_ABORTED; - call->local_abort = RX_CALL_DEAD; + __rxrpc_abort_call(call, RX_CALL_DEAD, ECONNRESET); } write_unlock_bh(&call->state_lock); @@ -493,6 +545,7 @@ void rxrpc_release_call(struct rxrpc_call *call) (skb = skb_dequeue(&call->rx_oos_queue))) { spin_unlock_bh(&call->lock); + sp = rxrpc_skb(skb); _debug("- zap %s %%%u #%u", rxrpc_pkts[sp->hdr.type], sp->hdr.serial, sp->hdr.seq); @@ -500,8 +553,6 @@ void rxrpc_release_call(struct rxrpc_call *call) spin_lock_bh(&call->lock); } spin_unlock_bh(&call->lock); - - ASSERTCMP(call->state, !=, RXRPC_CALL_COMPLETE); } del_timer_sync(&call->resend_timer); @@ -522,6 +573,7 @@ static void rxrpc_dead_call_expired(unsigned long _call) _enter("{%d}", call->debug_id); + rxrpc_see_call(call); write_lock_bh(&call->state_lock); call->state = RXRPC_CALL_DEAD; write_unlock_bh(&call->state_lock); @@ -536,22 +588,16 @@ static void rxrpc_mark_call_released(struct rxrpc_call *call) { bool sched; + rxrpc_see_call(call); write_lock(&call->state_lock); if (call->state < RXRPC_CALL_DEAD) { - sched = false; - if (call->state < RXRPC_CALL_COMPLETE) { - _debug("abort call %p", call); - call->state = RXRPC_CALL_LOCALLY_ABORTED; - call->local_abort = RX_CALL_DEAD; - if (!test_and_set_bit(RXRPC_CALL_EV_ABORT, &call->events)) - sched = true; - } + sched = __rxrpc_abort_call(call, RX_CALL_DEAD, ECONNRESET); if (!test_and_set_bit(RXRPC_CALL_EV_RELEASE, &call->events)) sched = true; - if (sched) - rxrpc_queue_call(call); } write_unlock(&call->state_lock); + if (sched) + rxrpc_queue_call(call); } /* @@ -566,12 +612,6 @@ void rxrpc_release_calls_on_socket(struct rxrpc_sock *rx) read_lock_bh(&rx->call_lock); - /* mark all the calls as no longer wanting incoming packets */ - for (p = rb_first(&rx->calls); p; p = rb_next(p)) { - call = rb_entry(p, struct rxrpc_call, sock_node); - rxrpc_mark_call_released(call); - } - /* kill the not-yet-accepted incoming calls */ list_for_each_entry(call, &rx->secureq, accept_link) { rxrpc_mark_call_released(call); @@ -581,6 +621,12 @@ void rxrpc_release_calls_on_socket(struct rxrpc_sock *rx) rxrpc_mark_call_released(call); } + /* mark all the calls as no longer wanting incoming packets */ + for (p = rb_first(&rx->calls); p; p = rb_next(p)) { + call = rb_entry(p, struct rxrpc_call, sock_node); + rxrpc_mark_call_released(call); + } + read_unlock_bh(&rx->call_lock); _leave(""); } @@ -588,21 +634,43 @@ void rxrpc_release_calls_on_socket(struct rxrpc_sock *rx) /* * release a call */ -void __rxrpc_put_call(struct rxrpc_call *call) +void rxrpc_put_call(struct rxrpc_call *call) { - ASSERT(call != NULL); + const void *here = __builtin_return_address(0); + int n, m; - _enter("%p{u=%d}", call, atomic_read(&call->usage)); + ASSERT(call != NULL); - ASSERTCMP(atomic_read(&call->usage), >, 0); + n = atomic_dec_return(&call->usage); + m = atomic_read(&call->skb_count); + trace_rxrpc_call(call, 5, n, m, here, NULL); + ASSERTCMP(n, >=, 0); + if (n == 0) { + _debug("call %d dead", call->debug_id); + WARN_ON(m != 0); + ASSERTCMP(call->state, ==, RXRPC_CALL_DEAD); + rxrpc_queue_work(&call->destroyer); + } +} - if (atomic_dec_and_test(&call->usage)) { +/* + * Release a call ref held by a socket buffer. + */ +void rxrpc_put_call_for_skb(struct rxrpc_call *call, struct sk_buff *skb) +{ + const void *here = __builtin_return_address(0); + int n, m; + + n = atomic_dec_return(&call->usage); + m = atomic_dec_return(&call->skb_count); + trace_rxrpc_call(call, 6, n, m, here, skb); + ASSERTCMP(n, >=, 0); + if (n == 0) { _debug("call %d dead", call->debug_id); - WARN_ON(atomic_read(&call->skb_count) != 0); + WARN_ON(m != 0); ASSERTCMP(call->state, ==, RXRPC_CALL_DEAD); rxrpc_queue_work(&call->destroyer); } - _leave(""); } /* @@ -613,6 +681,8 @@ static void rxrpc_rcu_destroy_call(struct rcu_head *rcu) struct rxrpc_call *call = container_of(rcu, struct rxrpc_call, rcu); rxrpc_purge_queue(&call->rx_queue); + rxrpc_purge_queue(&call->knlrecv_queue); + rxrpc_put_peer(call->peer); kmem_cache_free(rxrpc_call_jar, call); } @@ -667,6 +737,7 @@ static void rxrpc_cleanup_call(struct rxrpc_call *call) rxrpc_purge_queue(&call->rx_queue); ASSERT(skb_queue_empty(&call->rx_oos_queue)); + rxrpc_purge_queue(&call->knlrecv_queue); sock_put(&call->socket->sk); call_rcu(&call->rcu, rxrpc_rcu_destroy_call); } @@ -679,8 +750,8 @@ static void rxrpc_destroy_call(struct work_struct *work) struct rxrpc_call *call = container_of(work, struct rxrpc_call, destroyer); - _enter("%p{%d,%d,%p}", - call, atomic_read(&call->usage), call->channel, call->conn); + _enter("%p{%d,%x,%p}", + call, atomic_read(&call->usage), call->cid, call->conn); ASSERTCMP(call->state, ==, RXRPC_CALL_DEAD); @@ -707,6 +778,7 @@ void __exit rxrpc_destroy_all_calls(void) call = list_entry(rxrpc_calls.next, struct rxrpc_call, link); _debug("Zapping call %p", call); + rxrpc_see_call(call); list_del_init(&call->link); switch (atomic_read(&call->usage)) { @@ -748,16 +820,14 @@ static void rxrpc_call_life_expired(unsigned long _call) { struct rxrpc_call *call = (struct rxrpc_call *) _call; + _enter("{%d}", call->debug_id); + + rxrpc_see_call(call); if (call->state >= RXRPC_CALL_COMPLETE) return; - _enter("{%d}", call->debug_id); - read_lock_bh(&call->state_lock); - if (call->state < RXRPC_CALL_COMPLETE) { - set_bit(RXRPC_CALL_EV_LIFE_TIMER, &call->events); - rxrpc_queue_call(call); - } - read_unlock_bh(&call->state_lock); + set_bit(RXRPC_CALL_EV_LIFE_TIMER, &call->events); + rxrpc_queue_call(call); } /* @@ -770,6 +840,7 @@ static void rxrpc_resend_time_expired(unsigned long _call) _enter("{%d}", call->debug_id); + rxrpc_see_call(call); if (call->state >= RXRPC_CALL_COMPLETE) return; @@ -787,12 +858,10 @@ static void rxrpc_ack_time_expired(unsigned long _call) _enter("{%d}", call->debug_id); + rxrpc_see_call(call); if (call->state >= RXRPC_CALL_COMPLETE) return; - read_lock_bh(&call->state_lock); - if (call->state < RXRPC_CALL_COMPLETE && - !test_and_set_bit(RXRPC_CALL_EV_ACK, &call->events)) + if (!test_and_set_bit(RXRPC_CALL_EV_ACK, &call->events)) rxrpc_queue_call(call); - read_unlock_bh(&call->state_lock); } diff --git a/net/rxrpc/conn_client.c b/net/rxrpc/conn_client.c index 9e91f27b0d0f..4b213bc0f554 100644 --- a/net/rxrpc/conn_client.c +++ b/net/rxrpc/conn_client.c @@ -7,6 +7,68 @@ * modify it under the terms of the GNU General Public Licence * as published by the Free Software Foundation; either version * 2 of the Licence, or (at your option) any later version. + * + * + * Client connections need to be cached for a little while after they've made a + * call so as to handle retransmitted DATA packets in case the server didn't + * receive the final ACK or terminating ABORT we sent it. + * + * Client connections can be in one of a number of cache states: + * + * (1) INACTIVE - The connection is not held in any list and may not have been + * exposed to the world. If it has been previously exposed, it was + * discarded from the idle list after expiring. + * + * (2) WAITING - The connection is waiting for the number of client conns to + * drop below the maximum capacity. Calls may be in progress upon it from + * when it was active and got culled. + * + * The connection is on the rxrpc_waiting_client_conns list which is kept + * in to-be-granted order. Culled conns with waiters go to the back of + * the queue just like new conns. + * + * (3) ACTIVE - The connection has at least one call in progress upon it, it + * may freely grant available channels to new calls and calls may be + * waiting on it for channels to become available. + * + * The connection is on the rxrpc_active_client_conns list which is kept + * in activation order for culling purposes. + * + * rxrpc_nr_active_client_conns is held incremented also. + * + * (4) CULLED - The connection got summarily culled to try and free up + * capacity. Calls currently in progress on the connection are allowed to + * continue, but new calls will have to wait. There can be no waiters in + * this state - the conn would have to go to the WAITING state instead. + * + * (5) IDLE - The connection has no calls in progress upon it and must have + * been exposed to the world (ie. the EXPOSED flag must be set). When it + * expires, the EXPOSED flag is cleared and the connection transitions to + * the INACTIVE state. + * + * The connection is on the rxrpc_idle_client_conns list which is kept in + * order of how soon they'll expire. + * + * There are flags of relevance to the cache: + * + * (1) EXPOSED - The connection ID got exposed to the world. If this flag is + * set, an extra ref is added to the connection preventing it from being + * reaped when it has no calls outstanding. This flag is cleared and the + * ref dropped when a conn is discarded from the idle list. + * + * This allows us to move terminal call state retransmission to the + * connection and to discard the call immediately we think it is done + * with. It also give us a chance to reuse the connection. + * + * (2) DONT_REUSE - The connection should be discarded as soon as possible and + * should not be reused. This is set when an exclusive connection is used + * or a call ID counter overflows. + * + * The caching state may only be changed if the cache lock is held. + * + * There are two idle client connection expiry durations. If the total number + * of connections is below the reap threshold, we use the normal duration; if + * it's above, we use the fast duration. */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt @@ -16,22 +78,37 @@ #include <linux/timer.h> #include "ar-internal.h" +__read_mostly unsigned int rxrpc_max_client_connections = 1000; +__read_mostly unsigned int rxrpc_reap_client_connections = 900; +__read_mostly unsigned int rxrpc_conn_idle_client_expiry = 2 * 60 * HZ; +__read_mostly unsigned int rxrpc_conn_idle_client_fast_expiry = 2 * HZ; + +static unsigned int rxrpc_nr_client_conns; +static unsigned int rxrpc_nr_active_client_conns; +static __read_mostly bool rxrpc_kill_all_client_conns; + +static DEFINE_SPINLOCK(rxrpc_client_conn_cache_lock); +static DEFINE_SPINLOCK(rxrpc_client_conn_discard_mutex); +static LIST_HEAD(rxrpc_waiting_client_conns); +static LIST_HEAD(rxrpc_active_client_conns); +static LIST_HEAD(rxrpc_idle_client_conns); + /* * We use machine-unique IDs for our client connections. */ DEFINE_IDR(rxrpc_client_conn_ids); static DEFINE_SPINLOCK(rxrpc_conn_id_lock); +static void rxrpc_cull_active_client_conns(void); +static void rxrpc_discard_expired_client_conns(struct work_struct *); + +static DECLARE_DELAYED_WORK(rxrpc_client_conn_reap, + rxrpc_discard_expired_client_conns); + /* * Get a connection ID and epoch for a client connection from the global pool. * The connection struct pointer is then recorded in the idr radix tree. The * epoch is changed if this wraps. - * - * TODO: The IDR tree gets very expensive on memory if the connection IDs are - * widely scattered throughout the number space, so we shall need to retire - * connections that have, say, an ID more than four times the maximum number of - * client conns away from the current allocation point to try and keep the IDs - * concentrated. We will also need to retire connections from an old epoch. */ static int rxrpc_get_client_connection_id(struct rxrpc_connection *conn, gfp_t gfp) @@ -114,8 +191,7 @@ void rxrpc_destroy_client_conn_ids(void) } /* - * Allocate a client connection. The caller must take care to clear any - * padding bytes in *cp. + * Allocate a client connection. */ static struct rxrpc_connection * rxrpc_alloc_client_connection(struct rxrpc_conn_parameters *cp, gfp_t gfp) @@ -131,6 +207,10 @@ rxrpc_alloc_client_connection(struct rxrpc_conn_parameters *cp, gfp_t gfp) return ERR_PTR(-ENOMEM); } + atomic_set(&conn->usage, 1); + if (conn->params.exclusive) + __set_bit(RXRPC_CONN_DONT_REUSE, &conn->flags); + conn->params = *cp; conn->out_clientflag = RXRPC_CLIENT_INITIATED; conn->state = RXRPC_CONN_CLIENT; @@ -148,7 +228,7 @@ rxrpc_alloc_client_connection(struct rxrpc_conn_parameters *cp, gfp_t gfp) goto error_2; write_lock(&rxrpc_connection_lock); - list_add_tail(&conn->link, &rxrpc_connections); + list_add_tail(&conn->proc_link, &rxrpc_connection_proc_list); write_unlock(&rxrpc_connection_lock); /* We steal the caller's peer ref. */ @@ -170,32 +250,68 @@ error_0: } /* - * find a connection for a call - * - called in process context with IRQs enabled + * Determine if a connection may be reused. */ -int rxrpc_connect_call(struct rxrpc_call *call, - struct rxrpc_conn_parameters *cp, - struct sockaddr_rxrpc *srx, - gfp_t gfp) +static bool rxrpc_may_reuse_conn(struct rxrpc_connection *conn) +{ + int id_cursor, id, distance, limit; + + if (test_bit(RXRPC_CONN_DONT_REUSE, &conn->flags)) + goto dont_reuse; + + if (conn->proto.epoch != rxrpc_epoch) + goto mark_dont_reuse; + + /* The IDR tree gets very expensive on memory if the connection IDs are + * widely scattered throughout the number space, so we shall want to + * kill off connections that, say, have an ID more than about four + * times the maximum number of client conns away from the current + * allocation point to try and keep the IDs concentrated. + */ + id_cursor = READ_ONCE(rxrpc_client_conn_ids.cur); + id = conn->proto.cid >> RXRPC_CIDSHIFT; + distance = id - id_cursor; + if (distance < 0) + distance = -distance; + limit = round_up(rxrpc_max_client_connections, IDR_SIZE) * 4; + if (distance > limit) + goto mark_dont_reuse; + + return true; + +mark_dont_reuse: + set_bit(RXRPC_CONN_DONT_REUSE, &conn->flags); +dont_reuse: + return false; +} + +/* + * Create or find a client connection to use for a call. + * + * If we return with a connection, the call will be on its waiting list. It's + * left to the caller to assign a channel and wake up the call. + */ +static int rxrpc_get_client_conn(struct rxrpc_call *call, + struct rxrpc_conn_parameters *cp, + struct sockaddr_rxrpc *srx, + gfp_t gfp) { struct rxrpc_connection *conn, *candidate = NULL; struct rxrpc_local *local = cp->local; struct rb_node *p, **pp, *parent; long diff; - int chan; - - DECLARE_WAITQUEUE(myself, current); + int ret = -ENOMEM; _enter("{%d,%lx},", call->debug_id, call->user_call_ID); cp->peer = rxrpc_lookup_peer(cp->local, srx, gfp); if (!cp->peer) - return -ENOMEM; + goto error; + /* If the connection is not meant to be exclusive, search the available + * connections to see if the connection we want to use already exists. + */ if (!cp->exclusive) { - /* Search for a existing client connection unless this is going - * to be a connection that's used exclusively for a single call. - */ _debug("search 1"); spin_lock(&local->client_conns_lock); p = local->client_conns.rb_node; @@ -206,39 +322,55 @@ int rxrpc_connect_call(struct rxrpc_call *call, diff = (cmp(peer) ?: cmp(key) ?: cmp(security_level)); - if (diff < 0) +#undef cmp + if (diff < 0) { p = p->rb_left; - else if (diff > 0) + } else if (diff > 0) { p = p->rb_right; - else - goto found_extant_conn; + } else { + if (rxrpc_may_reuse_conn(conn) && + rxrpc_get_connection_maybe(conn)) + goto found_extant_conn; + /* The connection needs replacing. It's better + * to effect that when we have something to + * replace it with so that we don't have to + * rebalance the tree twice. + */ + break; + } } spin_unlock(&local->client_conns_lock); } - /* We didn't find a connection or we want an exclusive one. */ - _debug("get new conn"); + /* There wasn't a connection yet or we need an exclusive connection. + * We need to create a candidate and then potentially redo the search + * in case we're racing with another thread also trying to connect on a + * shareable connection. + */ + _debug("new conn"); candidate = rxrpc_alloc_client_connection(cp, gfp); - if (!candidate) { - _leave(" = -ENOMEM"); - return -ENOMEM; + if (IS_ERR(candidate)) { + ret = PTR_ERR(candidate); + goto error_peer; } + /* Add the call to the new connection's waiting list in case we're + * going to have to wait for the connection to come live. It's our + * connection, so we want first dibs on the channel slots. We would + * normally have to take channel_lock but we do this before anyone else + * can see the connection. + */ + list_add_tail(&call->chan_wait_link, &candidate->waiting_calls); + if (cp->exclusive) { - /* Assign the call on an exclusive connection to channel 0 and - * don't add the connection to the endpoint's shareable conn - * lookup tree. - */ - _debug("exclusive chan 0"); - conn = candidate; - atomic_set(&conn->avail_chans, RXRPC_MAXCALLS - 1); - spin_lock(&conn->channel_lock); - chan = 0; - goto found_channel; + call->conn = candidate; + _leave(" = 0 [exclusive %d]", candidate->debug_id); + return 0; } - /* We need to redo the search before attempting to add a new connection - * lest we race with someone else adding a conflicting instance. + /* Publish the new connection for userspace to find. We need to redo + * the search before doing this lest we race with someone else adding a + * conflicting instance. */ _debug("search 2"); spin_lock(&local->client_conns_lock); @@ -249,124 +381,673 @@ int rxrpc_connect_call(struct rxrpc_call *call, parent = *pp; conn = rb_entry(parent, struct rxrpc_connection, client_node); +#define cmp(X) ((long)conn->params.X - (long)candidate->params.X) diff = (cmp(peer) ?: cmp(key) ?: cmp(security_level)); - if (diff < 0) +#undef cmp + if (diff < 0) { pp = &(*pp)->rb_left; - else if (diff > 0) + } else if (diff > 0) { pp = &(*pp)->rb_right; - else - goto found_extant_conn; + } else { + if (rxrpc_may_reuse_conn(conn) && + rxrpc_get_connection_maybe(conn)) + goto found_extant_conn; + /* The old connection is from an outdated epoch. */ + _debug("replace conn"); + clear_bit(RXRPC_CONN_IN_CLIENT_CONNS, &conn->flags); + rb_replace_node(&conn->client_node, + &candidate->client_node, + &local->client_conns); + goto candidate_published; + } } - /* The second search also failed; simply add the new connection with - * the new call in channel 0. Note that we need to take the channel - * lock before dropping the client conn lock. - */ _debug("new conn"); - set_bit(RXRPC_CONN_IN_CLIENT_CONNS, &candidate->flags); rb_link_node(&candidate->client_node, parent, pp); rb_insert_color(&candidate->client_node, &local->client_conns); -attached: - conn = candidate; - candidate = NULL; - atomic_set(&conn->avail_chans, RXRPC_MAXCALLS - 1); - spin_lock(&conn->channel_lock); +candidate_published: + set_bit(RXRPC_CONN_IN_CLIENT_CONNS, &candidate->flags); + call->conn = candidate; spin_unlock(&local->client_conns_lock); - chan = 0; + _leave(" = 0 [new %d]", candidate->debug_id); + return 0; -found_channel: - _debug("found chan"); - call->conn = conn; - call->channel = chan; - call->epoch = conn->proto.epoch; - call->cid = conn->proto.cid | chan; - call->call_id = ++conn->channels[chan].call_counter; - conn->channels[chan].call_id = call->call_id; - rcu_assign_pointer(conn->channels[chan].call, call); + /* We come here if we found a suitable connection already in existence. + * Discard any candidate we may have allocated, and try to get a + * channel on this one. + */ +found_extant_conn: + _debug("found conn"); + spin_unlock(&local->client_conns_lock); - _net("CONNECT call %d on conn %d", call->debug_id, conn->debug_id); + rxrpc_put_connection(candidate); + candidate = NULL; + spin_lock(&conn->channel_lock); + call->conn = conn; + list_add(&call->chan_wait_link, &conn->waiting_calls); spin_unlock(&conn->channel_lock); + _leave(" = 0 [extant %d]", conn->debug_id); + return 0; + +error_peer: rxrpc_put_peer(cp->peer); cp->peer = NULL; - _leave(" = %p {u=%d}", conn, atomic_read(&conn->usage)); - return 0; +error: + _leave(" = %d", ret); + return ret; +} - /* We found a potentially suitable connection already in existence. If - * we can reuse it (ie. its usage count hasn't been reduced to 0 by the - * reaper), discard any candidate we may have allocated, and try to get - * a channel on this one, otherwise we have to replace it. - */ -found_extant_conn: - _debug("found conn"); - if (!rxrpc_get_connection_maybe(conn)) { - set_bit(RXRPC_CONN_IN_CLIENT_CONNS, &candidate->flags); - rb_replace_node(&conn->client_node, - &candidate->client_node, - &local->client_conns); - clear_bit(RXRPC_CONN_IN_CLIENT_CONNS, &conn->flags); - goto attached; +/* + * Activate a connection. + */ +static void rxrpc_activate_conn(struct rxrpc_connection *conn) +{ + conn->cache_state = RXRPC_CONN_CLIENT_ACTIVE; + rxrpc_nr_active_client_conns++; + list_move_tail(&conn->cache_link, &rxrpc_active_client_conns); +} + +/* + * Attempt to animate a connection for a new call. + * + * If it's not exclusive, the connection is in the endpoint tree, and we're in + * the conn's list of those waiting to grab a channel. There is, however, a + * limit on the number of live connections allowed at any one time, so we may + * have to wait for capacity to become available. + * + * Note that a connection on the waiting queue might *also* have active + * channels if it has been culled to make space and then re-requested by a new + * call. + */ +static void rxrpc_animate_client_conn(struct rxrpc_connection *conn) +{ + unsigned int nr_conns; + + _enter("%d,%d", conn->debug_id, conn->cache_state); + + if (conn->cache_state == RXRPC_CONN_CLIENT_ACTIVE) + goto out; + + spin_lock(&rxrpc_client_conn_cache_lock); + + nr_conns = rxrpc_nr_client_conns; + if (!test_and_set_bit(RXRPC_CONN_COUNTED, &conn->flags)) + rxrpc_nr_client_conns = nr_conns + 1; + + switch (conn->cache_state) { + case RXRPC_CONN_CLIENT_ACTIVE: + case RXRPC_CONN_CLIENT_WAITING: + break; + + case RXRPC_CONN_CLIENT_INACTIVE: + case RXRPC_CONN_CLIENT_CULLED: + case RXRPC_CONN_CLIENT_IDLE: + if (nr_conns >= rxrpc_max_client_connections) + goto wait_for_capacity; + goto activate_conn; + + default: + BUG(); } - spin_unlock(&local->client_conns_lock); +out_unlock: + spin_unlock(&rxrpc_client_conn_cache_lock); +out: + _leave(" [%d]", conn->cache_state); + return; - rxrpc_put_connection(candidate); +activate_conn: + _debug("activate"); + rxrpc_activate_conn(conn); + goto out_unlock; + +wait_for_capacity: + _debug("wait"); + conn->cache_state = RXRPC_CONN_CLIENT_WAITING; + list_move_tail(&conn->cache_link, &rxrpc_waiting_client_conns); + goto out_unlock; +} + +/* + * Deactivate a channel. + */ +static void rxrpc_deactivate_one_channel(struct rxrpc_connection *conn, + unsigned int channel) +{ + struct rxrpc_channel *chan = &conn->channels[channel]; + + rcu_assign_pointer(chan->call, NULL); + conn->active_chans &= ~(1 << channel); +} + +/* + * Assign a channel to the call at the front of the queue and wake the call up. + * We don't increment the callNumber counter until this number has been exposed + * to the world. + */ +static void rxrpc_activate_one_channel(struct rxrpc_connection *conn, + unsigned int channel) +{ + struct rxrpc_channel *chan = &conn->channels[channel]; + struct rxrpc_call *call = list_entry(conn->waiting_calls.next, + struct rxrpc_call, chan_wait_link); + u32 call_id = chan->call_counter + 1; + + rxrpc_see_call(call); + list_del_init(&call->chan_wait_link); + conn->active_chans |= 1 << channel; + call->peer = rxrpc_get_peer(conn->params.peer); + call->cid = conn->proto.cid | channel; + call->call_id = call_id; + + _net("CONNECT call %08x:%08x as call %d on conn %d", + call->cid, call->call_id, call->debug_id, conn->debug_id); + + /* Paired with the read barrier in rxrpc_wait_for_channel(). This + * orders cid and epoch in the connection wrt to call_id without the + * need to take the channel_lock. + * + * We provisionally assign a callNumber at this point, but we don't + * confirm it until the call is about to be exposed. + * + * TODO: Pair with a barrier in the data_ready handler when that looks + * at the call ID through a connection channel. + */ + smp_wmb(); + chan->call_id = call_id; + rcu_assign_pointer(chan->call, call); + wake_up(&call->waitq); +} + +/* + * Assign channels and callNumbers to waiting calls. + */ +static void rxrpc_activate_channels(struct rxrpc_connection *conn) +{ + unsigned char mask; + + _enter("%d", conn->debug_id); + + if (conn->cache_state != RXRPC_CONN_CLIENT_ACTIVE || + conn->active_chans == RXRPC_ACTIVE_CHANS_MASK) + return; + + spin_lock(&conn->channel_lock); + + while (!list_empty(&conn->waiting_calls) && + (mask = ~conn->active_chans, + mask &= RXRPC_ACTIVE_CHANS_MASK, + mask != 0)) + rxrpc_activate_one_channel(conn, __ffs(mask)); + + spin_unlock(&conn->channel_lock); + _leave(""); +} + +/* + * Wait for a callNumber and a channel to be granted to a call. + */ +static int rxrpc_wait_for_channel(struct rxrpc_call *call, gfp_t gfp) +{ + int ret = 0; + + _enter("%d", call->debug_id); + + if (!call->call_id) { + DECLARE_WAITQUEUE(myself, current); - if (!atomic_add_unless(&conn->avail_chans, -1, 0)) { if (!gfpflags_allow_blocking(gfp)) { - rxrpc_put_connection(conn); - _leave(" = -EAGAIN"); - return -EAGAIN; + ret = -EAGAIN; + goto out; } - add_wait_queue(&conn->channel_wq, &myself); + add_wait_queue_exclusive(&call->waitq, &myself); for (;;) { set_current_state(TASK_INTERRUPTIBLE); - if (atomic_add_unless(&conn->avail_chans, -1, 0)) + if (call->call_id) break; - if (signal_pending(current)) - goto interrupted; + if (signal_pending(current)) { + ret = -ERESTARTSYS; + break; + } schedule(); } - remove_wait_queue(&conn->channel_wq, &myself); + remove_wait_queue(&call->waitq, &myself); __set_current_state(TASK_RUNNING); } - /* The connection allegedly now has a free channel and we can now - * attach the call to it. - */ + /* Paired with the write barrier in rxrpc_activate_one_channel(). */ + smp_rmb(); + +out: + _leave(" = %d", ret); + return ret; +} + +/* + * find a connection for a call + * - called in process context with IRQs enabled + */ +int rxrpc_connect_call(struct rxrpc_call *call, + struct rxrpc_conn_parameters *cp, + struct sockaddr_rxrpc *srx, + gfp_t gfp) +{ + int ret; + + _enter("{%d,%lx},", call->debug_id, call->user_call_ID); + + rxrpc_discard_expired_client_conns(NULL); + rxrpc_cull_active_client_conns(); + + ret = rxrpc_get_client_conn(call, cp, srx, gfp); + if (ret < 0) + return ret; + + rxrpc_animate_client_conn(call->conn); + rxrpc_activate_channels(call->conn); + + ret = rxrpc_wait_for_channel(call, gfp); + if (ret < 0) + rxrpc_disconnect_client_call(call); + + _leave(" = %d", ret); + return ret; +} + +/* + * Note that a connection is about to be exposed to the world. Once it is + * exposed, we maintain an extra ref on it that stops it from being summarily + * discarded before it's (a) had a chance to deal with retransmission and (b) + * had a chance at re-use (the per-connection security negotiation is + * expensive). + */ +static void rxrpc_expose_client_conn(struct rxrpc_connection *conn) +{ + if (!test_and_set_bit(RXRPC_CONN_EXPOSED, &conn->flags)) + rxrpc_get_connection(conn); +} + +/* + * Note that a call, and thus a connection, is about to be exposed to the + * world. + */ +void rxrpc_expose_client_call(struct rxrpc_call *call) +{ + struct rxrpc_connection *conn = call->conn; + struct rxrpc_channel *chan = + &conn->channels[call->cid & RXRPC_CHANNELMASK]; + + if (!test_and_set_bit(RXRPC_CALL_EXPOSED, &call->flags)) { + /* Mark the call ID as being used. If the callNumber counter + * exceeds ~2 billion, we kill the connection after its + * outstanding calls have finished so that the counter doesn't + * wrap. + */ + chan->call_counter++; + if (chan->call_counter >= INT_MAX) + set_bit(RXRPC_CONN_DONT_REUSE, &conn->flags); + rxrpc_expose_client_conn(conn); + } +} + +/* + * Disconnect a client call. + */ +void rxrpc_disconnect_client_call(struct rxrpc_call *call) +{ + unsigned int channel = call->cid & RXRPC_CHANNELMASK; + struct rxrpc_connection *conn = call->conn; + struct rxrpc_channel *chan = &conn->channels[channel]; + + call->conn = NULL; + spin_lock(&conn->channel_lock); - for (chan = 0; chan < RXRPC_MAXCALLS; chan++) - if (!conn->channels[chan].call) - goto found_channel; - BUG(); + /* Calls that have never actually been assigned a channel can simply be + * discarded. If the conn didn't get used either, it will follow + * immediately unless someone else grabs it in the meantime. + */ + if (!list_empty(&call->chan_wait_link)) { + _debug("call is waiting"); + ASSERTCMP(call->call_id, ==, 0); + ASSERT(!test_bit(RXRPC_CALL_EXPOSED, &call->flags)); + list_del_init(&call->chan_wait_link); + + /* We must deactivate or idle the connection if it's now + * waiting for nothing. + */ + spin_lock(&rxrpc_client_conn_cache_lock); + if (conn->cache_state == RXRPC_CONN_CLIENT_WAITING && + list_empty(&conn->waiting_calls) && + !conn->active_chans) + goto idle_connection; + goto out; + } + + ASSERTCMP(rcu_access_pointer(chan->call), ==, call); + ASSERTCMP(atomic_read(&conn->usage), >=, 2); + + /* If a client call was exposed to the world, we save the result for + * retransmission. + * + * We use a barrier here so that the call number and abort code can be + * read without needing to take a lock. + * + * TODO: Make the incoming packet handler check this and handle + * terminal retransmission without requiring access to the call. + */ + if (test_bit(RXRPC_CALL_EXPOSED, &call->flags)) { + _debug("exposed %u,%u", call->call_id, call->abort_code); + __rxrpc_disconnect_call(conn, call); + } + + /* See if we can pass the channel directly to another call. */ + if (conn->cache_state == RXRPC_CONN_CLIENT_ACTIVE && + !list_empty(&conn->waiting_calls)) { + _debug("pass chan"); + rxrpc_activate_one_channel(conn, channel); + goto out_2; + } + + /* Things are more complex and we need the cache lock. We might be + * able to simply idle the conn or it might now be lurking on the wait + * list. It might even get moved back to the active list whilst we're + * waiting for the lock. + */ + spin_lock(&rxrpc_client_conn_cache_lock); + + switch (conn->cache_state) { + case RXRPC_CONN_CLIENT_ACTIVE: + if (list_empty(&conn->waiting_calls)) { + rxrpc_deactivate_one_channel(conn, channel); + if (!conn->active_chans) { + rxrpc_nr_active_client_conns--; + goto idle_connection; + } + goto out; + } + + _debug("pass chan 2"); + rxrpc_activate_one_channel(conn, channel); + goto out; + + case RXRPC_CONN_CLIENT_CULLED: + rxrpc_deactivate_one_channel(conn, channel); + ASSERT(list_empty(&conn->waiting_calls)); + if (!conn->active_chans) + goto idle_connection; + goto out; + + case RXRPC_CONN_CLIENT_WAITING: + rxrpc_deactivate_one_channel(conn, channel); + goto out; + + default: + BUG(); + } -interrupted: - remove_wait_queue(&conn->channel_wq, &myself); - __set_current_state(TASK_RUNNING); +out: + spin_unlock(&rxrpc_client_conn_cache_lock); +out_2: + spin_unlock(&conn->channel_lock); rxrpc_put_connection(conn); - rxrpc_put_peer(cp->peer); - cp->peer = NULL; - _leave(" = -ERESTARTSYS"); - return -ERESTARTSYS; + _leave(""); + return; + +idle_connection: + /* As no channels remain active, the connection gets deactivated + * immediately or moved to the idle list for a short while. + */ + if (test_bit(RXRPC_CONN_EXPOSED, &conn->flags)) { + _debug("make idle"); + conn->idle_timestamp = jiffies; + conn->cache_state = RXRPC_CONN_CLIENT_IDLE; + list_move_tail(&conn->cache_link, &rxrpc_idle_client_conns); + if (rxrpc_idle_client_conns.next == &conn->cache_link && + !rxrpc_kill_all_client_conns) + queue_delayed_work(rxrpc_workqueue, + &rxrpc_client_conn_reap, + rxrpc_conn_idle_client_expiry); + } else { + _debug("make inactive"); + conn->cache_state = RXRPC_CONN_CLIENT_INACTIVE; + list_del_init(&conn->cache_link); + } + goto out; } /* - * Remove a client connection from the local endpoint's tree, thereby removing - * it as a target for reuse for new client calls. + * Clean up a dead client connection. */ -void rxrpc_unpublish_client_conn(struct rxrpc_connection *conn) +static struct rxrpc_connection * +rxrpc_put_one_client_conn(struct rxrpc_connection *conn) { + struct rxrpc_connection *next; struct rxrpc_local *local = conn->params.local; + unsigned int nr_conns; - spin_lock(&local->client_conns_lock); - if (test_and_clear_bit(RXRPC_CONN_IN_CLIENT_CONNS, &conn->flags)) - rb_erase(&conn->client_node, &local->client_conns); - spin_unlock(&local->client_conns_lock); + if (test_bit(RXRPC_CONN_IN_CLIENT_CONNS, &conn->flags)) { + spin_lock(&local->client_conns_lock); + if (test_and_clear_bit(RXRPC_CONN_IN_CLIENT_CONNS, + &conn->flags)) + rb_erase(&conn->client_node, &local->client_conns); + spin_unlock(&local->client_conns_lock); + } rxrpc_put_client_connection_id(conn); + + ASSERTCMP(conn->cache_state, ==, RXRPC_CONN_CLIENT_INACTIVE); + + if (!test_bit(RXRPC_CONN_COUNTED, &conn->flags)) + return NULL; + + spin_lock(&rxrpc_client_conn_cache_lock); + nr_conns = --rxrpc_nr_client_conns; + + next = NULL; + if (nr_conns < rxrpc_max_client_connections && + !list_empty(&rxrpc_waiting_client_conns)) { + next = list_entry(rxrpc_waiting_client_conns.next, + struct rxrpc_connection, cache_link); + rxrpc_get_connection(next); + rxrpc_activate_conn(next); + } + + spin_unlock(&rxrpc_client_conn_cache_lock); + rxrpc_kill_connection(conn); + + if (next) + rxrpc_activate_channels(next); + + /* We need to get rid of the temporary ref we took upon next, but we + * can't call rxrpc_put_connection() recursively. + */ + return next; +} + +/* + * Clean up a dead client connections. + */ +void rxrpc_put_client_conn(struct rxrpc_connection *conn) +{ + struct rxrpc_connection *next; + + do { + _enter("%p{u=%d,d=%d}", + conn, atomic_read(&conn->usage), conn->debug_id); + + next = rxrpc_put_one_client_conn(conn); + + if (!next) + break; + conn = next; + } while (atomic_dec_and_test(&conn->usage)); + + _leave(""); +} + +/* + * Kill the longest-active client connections to make room for new ones. + */ +static void rxrpc_cull_active_client_conns(void) +{ + struct rxrpc_connection *conn; + unsigned int nr_conns = rxrpc_nr_client_conns; + unsigned int nr_active, limit; + + _enter(""); + + ASSERTCMP(nr_conns, >=, 0); + if (nr_conns < rxrpc_max_client_connections) { + _leave(" [ok]"); + return; + } + limit = rxrpc_reap_client_connections; + + spin_lock(&rxrpc_client_conn_cache_lock); + nr_active = rxrpc_nr_active_client_conns; + + while (nr_active > limit) { + ASSERT(!list_empty(&rxrpc_active_client_conns)); + conn = list_entry(rxrpc_active_client_conns.next, + struct rxrpc_connection, cache_link); + ASSERTCMP(conn->cache_state, ==, RXRPC_CONN_CLIENT_ACTIVE); + + if (list_empty(&conn->waiting_calls)) { + conn->cache_state = RXRPC_CONN_CLIENT_CULLED; + list_del_init(&conn->cache_link); + } else { + conn->cache_state = RXRPC_CONN_CLIENT_WAITING; + list_move_tail(&conn->cache_link, + &rxrpc_waiting_client_conns); + } + + nr_active--; + } + + rxrpc_nr_active_client_conns = nr_active; + spin_unlock(&rxrpc_client_conn_cache_lock); + ASSERTCMP(nr_active, >=, 0); + _leave(" [culled]"); +} + +/* + * Discard expired client connections from the idle list. Each conn in the + * idle list has been exposed and holds an extra ref because of that. + * + * This may be called from conn setup or from a work item so cannot be + * considered non-reentrant. + */ +static void rxrpc_discard_expired_client_conns(struct work_struct *work) +{ + struct rxrpc_connection *conn; + unsigned long expiry, conn_expires_at, now; + unsigned int nr_conns; + bool did_discard = false; + + _enter("%c", work ? 'w' : 'n'); + + if (list_empty(&rxrpc_idle_client_conns)) { + _leave(" [empty]"); + return; + } + + /* Don't double up on the discarding */ + if (!spin_trylock(&rxrpc_client_conn_discard_mutex)) { + _leave(" [already]"); + return; + } + + /* We keep an estimate of what the number of conns ought to be after + * we've discarded some so that we don't overdo the discarding. + */ + nr_conns = rxrpc_nr_client_conns; + +next: + spin_lock(&rxrpc_client_conn_cache_lock); + + if (list_empty(&rxrpc_idle_client_conns)) + goto out; + + conn = list_entry(rxrpc_idle_client_conns.next, + struct rxrpc_connection, cache_link); + ASSERT(test_bit(RXRPC_CONN_EXPOSED, &conn->flags)); + + if (!rxrpc_kill_all_client_conns) { + /* If the number of connections is over the reap limit, we + * expedite discard by reducing the expiry timeout. We must, + * however, have at least a short grace period to be able to do + * final-ACK or ABORT retransmission. + */ + expiry = rxrpc_conn_idle_client_expiry; + if (nr_conns > rxrpc_reap_client_connections) + expiry = rxrpc_conn_idle_client_fast_expiry; + + conn_expires_at = conn->idle_timestamp + expiry; + + now = READ_ONCE(jiffies); + if (time_after(conn_expires_at, now)) + goto not_yet_expired; + } + + _debug("discard conn %d", conn->debug_id); + if (!test_and_clear_bit(RXRPC_CONN_EXPOSED, &conn->flags)) + BUG(); + conn->cache_state = RXRPC_CONN_CLIENT_INACTIVE; + list_del_init(&conn->cache_link); + + spin_unlock(&rxrpc_client_conn_cache_lock); + + /* When we cleared the EXPOSED flag, we took on responsibility for the + * reference that that had on the usage count. We deal with that here. + * If someone re-sets the flag and re-gets the ref, that's fine. + */ + rxrpc_put_connection(conn); + did_discard = true; + nr_conns--; + goto next; + +not_yet_expired: + /* The connection at the front of the queue hasn't yet expired, so + * schedule the work item for that point if we discarded something. + * + * We don't worry if the work item is already scheduled - it can look + * after rescheduling itself at a later time. We could cancel it, but + * then things get messier. + */ + _debug("not yet"); + if (!rxrpc_kill_all_client_conns) + queue_delayed_work(rxrpc_workqueue, + &rxrpc_client_conn_reap, + conn_expires_at - now); + +out: + spin_unlock(&rxrpc_client_conn_cache_lock); + spin_unlock(&rxrpc_client_conn_discard_mutex); + _leave(""); +} + +/* + * Preemptively destroy all the client connection records rather than waiting + * for them to time out + */ +void __exit rxrpc_destroy_all_client_connections(void) +{ + _enter(""); + + spin_lock(&rxrpc_client_conn_cache_lock); + rxrpc_kill_all_client_conns = true; + spin_unlock(&rxrpc_client_conn_cache_lock); + + cancel_delayed_work(&rxrpc_client_conn_reap); + + if (!queue_delayed_work(rxrpc_workqueue, &rxrpc_client_conn_reap, 0)) + _debug("destroy: queue failed"); + + _leave(""); } diff --git a/net/rxrpc/conn_event.c b/net/rxrpc/conn_event.c index cee0f35bc1cf..9db90f4f768d 100644 --- a/net/rxrpc/conn_event.c +++ b/net/rxrpc/conn_event.c @@ -25,35 +25,149 @@ #include "ar-internal.h" /* + * Retransmit terminal ACK or ABORT of the previous call. + */ +static void rxrpc_conn_retransmit_call(struct rxrpc_connection *conn, + struct sk_buff *skb) +{ + struct rxrpc_skb_priv *sp = rxrpc_skb(skb); + struct rxrpc_channel *chan; + struct msghdr msg; + struct kvec iov; + struct { + struct rxrpc_wire_header whdr; + union { + struct { + __be32 code; + } abort; + struct { + struct rxrpc_ackpacket ack; + u8 padding[3]; + struct rxrpc_ackinfo info; + }; + }; + } __attribute__((packed)) pkt; + size_t len; + u32 serial, mtu, call_id; + + _enter("%d", conn->debug_id); + + chan = &conn->channels[sp->hdr.cid & RXRPC_CHANNELMASK]; + + /* If the last call got moved on whilst we were waiting to run, just + * ignore this packet. + */ + call_id = READ_ONCE(chan->last_call); + /* Sync with __rxrpc_disconnect_call() */ + smp_rmb(); + if (call_id != sp->hdr.callNumber) + return; + + msg.msg_name = &conn->params.peer->srx.transport; + msg.msg_namelen = conn->params.peer->srx.transport_len; + msg.msg_control = NULL; + msg.msg_controllen = 0; + msg.msg_flags = 0; + + pkt.whdr.epoch = htonl(sp->hdr.epoch); + pkt.whdr.cid = htonl(sp->hdr.cid); + pkt.whdr.callNumber = htonl(sp->hdr.callNumber); + pkt.whdr.seq = 0; + pkt.whdr.type = chan->last_type; + pkt.whdr.flags = conn->out_clientflag; + pkt.whdr.userStatus = 0; + pkt.whdr.securityIndex = conn->security_ix; + pkt.whdr._rsvd = 0; + pkt.whdr.serviceId = htons(chan->last_service_id); + + len = sizeof(pkt.whdr); + switch (chan->last_type) { + case RXRPC_PACKET_TYPE_ABORT: + pkt.abort.code = htonl(chan->last_abort); + len += sizeof(pkt.abort); + break; + + case RXRPC_PACKET_TYPE_ACK: + mtu = conn->params.peer->if_mtu; + mtu -= conn->params.peer->hdrsize; + pkt.ack.bufferSpace = 0; + pkt.ack.maxSkew = htons(skb->priority); + pkt.ack.firstPacket = htonl(chan->last_seq); + pkt.ack.previousPacket = htonl(chan->last_seq - 1); + pkt.ack.serial = htonl(sp->hdr.serial); + pkt.ack.reason = RXRPC_ACK_DUPLICATE; + pkt.ack.nAcks = 0; + pkt.info.rxMTU = htonl(rxrpc_rx_mtu); + pkt.info.maxMTU = htonl(mtu); + pkt.info.rwind = htonl(rxrpc_rx_window_size); + pkt.info.jumbo_max = htonl(rxrpc_rx_jumbo_max); + len += sizeof(pkt.ack) + sizeof(pkt.info); + break; + } + + /* Resync with __rxrpc_disconnect_call() and check that the last call + * didn't get advanced whilst we were filling out the packets. + */ + smp_rmb(); + if (READ_ONCE(chan->last_call) != call_id) + return; + + iov.iov_base = &pkt; + iov.iov_len = len; + + serial = atomic_inc_return(&conn->serial); + pkt.whdr.serial = htonl(serial); + + switch (chan->last_type) { + case RXRPC_PACKET_TYPE_ABORT: + _proto("Tx ABORT %%%u { %d } [re]", serial, conn->local_abort); + break; + case RXRPC_PACKET_TYPE_ACK: + _proto("Tx ACK %%%u [re]", serial); + break; + } + + kernel_sendmsg(conn->params.local->socket, &msg, &iov, 1, len); + _leave(""); + return; +} + +/* * pass a connection-level abort onto all calls on that connection */ -static void rxrpc_abort_calls(struct rxrpc_connection *conn, int state, - u32 abort_code) +static void rxrpc_abort_calls(struct rxrpc_connection *conn, + enum rxrpc_call_completion compl, + u32 abort_code, int error) { struct rxrpc_call *call; - int i; + bool queue; + int i, bit; _enter("{%d},%x", conn->debug_id, abort_code); + if (compl == RXRPC_CALL_LOCALLY_ABORTED) + bit = RXRPC_CALL_EV_CONN_ABORT; + else + bit = RXRPC_CALL_EV_RCVD_ABORT; + spin_lock(&conn->channel_lock); for (i = 0; i < RXRPC_MAXCALLS; i++) { call = rcu_dereference_protected( conn->channels[i].call, lockdep_is_held(&conn->channel_lock)); - write_lock_bh(&call->state_lock); - if (call->state <= RXRPC_CALL_COMPLETE) { - call->state = state; - if (state == RXRPC_CALL_LOCALLY_ABORTED) { - call->local_abort = conn->local_abort; - set_bit(RXRPC_CALL_EV_CONN_ABORT, &call->events); - } else { - call->remote_abort = conn->remote_abort; - set_bit(RXRPC_CALL_EV_RCVD_ABORT, &call->events); + if (call) { + rxrpc_see_call(call); + write_lock_bh(&call->state_lock); + if (rxrpc_set_call_completion(call, compl, abort_code, + error)) { + set_bit(bit, &call->events); + queue = true; } - rxrpc_queue_call(call); + write_unlock_bh(&call->state_lock); + if (queue) + rxrpc_queue_call(call); } - write_unlock_bh(&call->state_lock); } spin_unlock(&conn->channel_lock); @@ -78,17 +192,16 @@ static int rxrpc_abort_connection(struct rxrpc_connection *conn, /* generate a connection-level abort */ spin_lock_bh(&conn->state_lock); - if (conn->state < RXRPC_CONN_REMOTELY_ABORTED) { - conn->state = RXRPC_CONN_LOCALLY_ABORTED; - conn->error = error; - spin_unlock_bh(&conn->state_lock); - } else { + if (conn->state >= RXRPC_CONN_REMOTELY_ABORTED) { spin_unlock_bh(&conn->state_lock); _leave(" = 0 [already dead]"); return 0; } - rxrpc_abort_calls(conn, RXRPC_CALL_LOCALLY_ABORTED, abort_code); + conn->state = RXRPC_CONN_LOCALLY_ABORTED; + spin_unlock_bh(&conn->state_lock); + + rxrpc_abort_calls(conn, RXRPC_CALL_LOCALLY_ABORTED, abort_code, error); msg.msg_name = &conn->params.peer->srx.transport; msg.msg_namelen = conn->params.peer->srx.transport_len; @@ -166,6 +279,11 @@ static int rxrpc_process_event(struct rxrpc_connection *conn, _enter("{%d},{%u,%%%u},", conn->debug_id, sp->hdr.type, sp->hdr.serial); switch (sp->hdr.type) { + case RXRPC_PACKET_TYPE_DATA: + case RXRPC_PACKET_TYPE_ACK: + rxrpc_conn_retransmit_call(conn, skb); + return 0; + case RXRPC_PACKET_TYPE_ABORT: if (skb_copy_bits(skb, 0, &wtmp, sizeof(wtmp)) < 0) return -EPROTO; @@ -173,7 +291,7 @@ static int rxrpc_process_event(struct rxrpc_connection *conn, _proto("Rx ABORT %%%u { ac=%d }", sp->hdr.serial, abort_code); conn->state = RXRPC_CONN_REMOTELY_ABORTED; - rxrpc_abort_calls(conn, RXRPC_CALL_REMOTELY_ABORTED, + rxrpc_abort_calls(conn, 0, RXRPC_CALL_REMOTELY_ABORTED, abort_code); return -ECONNABORTED; @@ -277,6 +395,7 @@ void rxrpc_process_connection(struct work_struct *work) /* go through the conn-level event packets, releasing the ref on this * connection that each one has when we've finished with it */ while ((skb = skb_dequeue(&conn->rx_queue))) { + rxrpc_see_skb(skb); ret = rxrpc_process_event(conn, skb, &abort_code); switch (ret) { case -EPROTO: @@ -365,6 +484,7 @@ void rxrpc_reject_packets(struct rxrpc_local *local) whdr.type = RXRPC_PACKET_TYPE_ABORT; while ((skb = skb_dequeue(&local->reject_queue))) { + rxrpc_see_skb(skb); sp = rxrpc_skb(skb); switch (sa.sa.sa_family) { case AF_INET: diff --git a/net/rxrpc/conn_object.c b/net/rxrpc/conn_object.c index 896d84493a05..9c6685b97e70 100644 --- a/net/rxrpc/conn_object.c +++ b/net/rxrpc/conn_object.c @@ -1,6 +1,6 @@ -/* RxRPC virtual connection handler +/* RxRPC virtual connection handler, common bits. * - * Copyright (C) 2007 Red Hat, Inc. All Rights Reserved. + * Copyright (C) 2007, 2016 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) * * This program is free software; you can redistribute it and/or @@ -15,8 +15,6 @@ #include <linux/slab.h> #include <linux/net.h> #include <linux/skbuff.h> -#include <net/sock.h> -#include <net/af_rxrpc.h> #include "ar-internal.h" /* @@ -27,9 +25,12 @@ unsigned int rxrpc_connection_expiry = 10 * 60; static void rxrpc_connection_reaper(struct work_struct *work); LIST_HEAD(rxrpc_connections); +LIST_HEAD(rxrpc_connection_proc_list); DEFINE_RWLOCK(rxrpc_connection_lock); static DECLARE_DELAYED_WORK(rxrpc_connection_reap, rxrpc_connection_reaper); +static void rxrpc_destroy_connection(struct rcu_head *); + /* * allocate a new connection */ @@ -41,21 +42,19 @@ struct rxrpc_connection *rxrpc_alloc_connection(gfp_t gfp) conn = kzalloc(sizeof(struct rxrpc_connection), gfp); if (conn) { + INIT_LIST_HEAD(&conn->cache_link); spin_lock_init(&conn->channel_lock); - init_waitqueue_head(&conn->channel_wq); + INIT_LIST_HEAD(&conn->waiting_calls); INIT_WORK(&conn->processor, &rxrpc_process_connection); + INIT_LIST_HEAD(&conn->proc_link); INIT_LIST_HEAD(&conn->link); skb_queue_head_init(&conn->rx_queue); conn->security = &rxrpc_no_security; spin_lock_init(&conn->state_lock); - /* We maintain an extra ref on the connection whilst it is - * on the rxrpc_connections list. - */ - atomic_set(&conn->usage, 2); conn->debug_id = atomic_inc_return(&rxrpc_debug_id); - atomic_set(&conn->avail_chans, RXRPC_MAXCALLS); conn->size_align = 4; conn->header_size = sizeof(struct rxrpc_wire_header); + conn->idle_timestamp = jiffies; } _leave(" = %p{%d}", conn, conn ? conn->debug_id : 0); @@ -153,25 +152,32 @@ not_found: * terminates. The caller must hold the channel_lock and must release the * call's ref on the connection. */ -void __rxrpc_disconnect_call(struct rxrpc_call *call) +void __rxrpc_disconnect_call(struct rxrpc_connection *conn, + struct rxrpc_call *call) { - struct rxrpc_connection *conn = call->conn; - struct rxrpc_channel *chan = &conn->channels[call->channel]; + struct rxrpc_channel *chan = + &conn->channels[call->cid & RXRPC_CHANNELMASK]; - _enter("%d,%d", conn->debug_id, call->channel); + _enter("%d,%x", conn->debug_id, call->cid); if (rcu_access_pointer(chan->call) == call) { /* Save the result of the call so that we can repeat it if necessary * through the channel, whilst disposing of the actual call record. */ - chan->last_result = call->local_abort; + chan->last_service_id = call->service_id; + if (call->abort_code) { + chan->last_abort = call->abort_code; + chan->last_type = RXRPC_PACKET_TYPE_ABORT; + } else { + chan->last_seq = call->rx_data_eaten; + chan->last_type = RXRPC_PACKET_TYPE_ACK; + } + /* Sync with rxrpc_conn_retransmit(). */ smp_wmb(); chan->last_call = chan->call_id; chan->call_id = chan->call_counter; rcu_assign_pointer(chan->call, NULL); - atomic_inc(&conn->avail_chans); - wake_up(&conn->channel_wq); } _leave(""); @@ -185,34 +191,52 @@ void rxrpc_disconnect_call(struct rxrpc_call *call) { struct rxrpc_connection *conn = call->conn; + if (rxrpc_is_client_call(call)) + return rxrpc_disconnect_client_call(call); + spin_lock(&conn->channel_lock); - __rxrpc_disconnect_call(call); + __rxrpc_disconnect_call(conn, call); spin_unlock(&conn->channel_lock); call->conn = NULL; + conn->idle_timestamp = jiffies; rxrpc_put_connection(conn); } /* - * release a virtual connection + * Kill off a connection. */ -void rxrpc_put_connection(struct rxrpc_connection *conn) +void rxrpc_kill_connection(struct rxrpc_connection *conn) { - if (!conn) - return; + ASSERT(!rcu_access_pointer(conn->channels[0].call) && + !rcu_access_pointer(conn->channels[1].call) && + !rcu_access_pointer(conn->channels[2].call) && + !rcu_access_pointer(conn->channels[3].call)); + ASSERT(list_empty(&conn->cache_link)); - _enter("%p{u=%d,d=%d}", - conn, atomic_read(&conn->usage), conn->debug_id); + write_lock(&rxrpc_connection_lock); + list_del_init(&conn->proc_link); + write_unlock(&rxrpc_connection_lock); - ASSERTCMP(atomic_read(&conn->usage), >, 1); + /* Drain the Rx queue. Note that even though we've unpublished, an + * incoming packet could still be being added to our Rx queue, so we + * will need to drain it again in the RCU cleanup handler. + */ + rxrpc_purge_queue(&conn->rx_queue); - conn->put_time = ktime_get_seconds(); - if (atomic_dec_return(&conn->usage) == 1) { - _debug("zombie"); - rxrpc_queue_delayed_work(&rxrpc_connection_reap, 0); - } + /* Leave final destruction to RCU. The connection processor work item + * must carry a ref on the connection to prevent us getting here whilst + * it is queued or running. + */ + call_rcu(&conn->rcu, rxrpc_destroy_connection); +} - _leave(""); +/* + * release a virtual connection + */ +void __rxrpc_put_connection(struct rxrpc_connection *conn) +{ + rxrpc_queue_delayed_work(&rxrpc_connection_reap, 0); } /* @@ -242,19 +266,19 @@ static void rxrpc_destroy_connection(struct rcu_head *rcu) } /* - * reap dead connections + * reap dead service connections */ static void rxrpc_connection_reaper(struct work_struct *work) { struct rxrpc_connection *conn, *_p; - unsigned long reap_older_than, earliest, put_time, now; + unsigned long reap_older_than, earliest, idle_timestamp, now; LIST_HEAD(graveyard); _enter(""); - now = ktime_get_seconds(); - reap_older_than = now - rxrpc_connection_expiry; + now = jiffies; + reap_older_than = now - rxrpc_connection_expiry * HZ; earliest = ULONG_MAX; write_lock(&rxrpc_connection_lock); @@ -263,10 +287,14 @@ static void rxrpc_connection_reaper(struct work_struct *work) if (likely(atomic_read(&conn->usage) > 1)) continue; - put_time = READ_ONCE(conn->put_time); - if (time_after(put_time, reap_older_than)) { - if (time_before(put_time, earliest)) - earliest = put_time; + idle_timestamp = READ_ONCE(conn->idle_timestamp); + _debug("reap CONN %d { u=%d,t=%ld }", + conn->debug_id, atomic_read(&conn->usage), + (long)reap_older_than - (long)idle_timestamp); + + if (time_after(idle_timestamp, reap_older_than)) { + if (time_before(idle_timestamp, earliest)) + earliest = idle_timestamp; continue; } @@ -277,7 +305,7 @@ static void rxrpc_connection_reaper(struct work_struct *work) continue; if (rxrpc_conn_is_client(conn)) - rxrpc_unpublish_client_conn(conn); + BUG(); else rxrpc_unpublish_service_conn(conn); @@ -287,9 +315,9 @@ static void rxrpc_connection_reaper(struct work_struct *work) if (earliest != ULONG_MAX) { _debug("reschedule reaper %ld", (long) earliest - now); - ASSERTCMP(earliest, >, now); + ASSERT(time_after(earliest, now)); rxrpc_queue_delayed_work(&rxrpc_connection_reap, - (earliest - now) * HZ); + earliest - now); } while (!list_empty(&graveyard)) { @@ -298,16 +326,15 @@ static void rxrpc_connection_reaper(struct work_struct *work) list_del_init(&conn->link); ASSERTCMP(atomic_read(&conn->usage), ==, 0); - skb_queue_purge(&conn->rx_queue); - call_rcu(&conn->rcu, rxrpc_destroy_connection); + rxrpc_kill_connection(conn); } _leave(""); } /* - * preemptively destroy all the connection records rather than waiting for them - * to time out + * preemptively destroy all the service connection records rather than + * waiting for them to time out */ void __exit rxrpc_destroy_all_connections(void) { @@ -316,6 +343,8 @@ void __exit rxrpc_destroy_all_connections(void) _enter(""); + rxrpc_destroy_all_client_connections(); + rxrpc_connection_expiry = 0; cancel_delayed_work(&rxrpc_connection_reap); rxrpc_queue_delayed_work(&rxrpc_connection_reap, 0); @@ -330,6 +359,8 @@ void __exit rxrpc_destroy_all_connections(void) write_unlock(&rxrpc_connection_lock); BUG_ON(leak); + ASSERT(list_empty(&rxrpc_connection_proc_list)); + /* Make sure the local and peer records pinned by any dying connections * are released. */ diff --git a/net/rxrpc/conn_service.c b/net/rxrpc/conn_service.c index fd9027ccba8f..316a92107fee 100644 --- a/net/rxrpc/conn_service.c +++ b/net/rxrpc/conn_service.c @@ -185,8 +185,14 @@ struct rxrpc_connection *rxrpc_incoming_connection(struct rxrpc_local *local, rxrpc_get_local(local); + /* We maintain an extra ref on the connection whilst it is on + * the rxrpc_connections list. + */ + atomic_set(&conn->usage, 2); + write_lock(&rxrpc_connection_lock); list_add_tail(&conn->link, &rxrpc_connections); + list_add_tail(&conn->proc_link, &rxrpc_connection_proc_list); write_unlock(&rxrpc_connection_lock); /* Make the connection a target for incoming packets. */ diff --git a/net/rxrpc/input.c b/net/rxrpc/input.c index 9e0f58edcd01..72f016cfaaf5 100644 --- a/net/rxrpc/input.c +++ b/net/rxrpc/input.c @@ -90,9 +90,15 @@ int rxrpc_queue_rcv_skb(struct rxrpc_call *call, struct sk_buff *skb, } /* allow interception by a kernel service */ - if (rx->interceptor) { - rx->interceptor(sk, call->user_call_ID, skb); + if (skb->mark == RXRPC_SKB_MARK_NEW_CALL && + rx->notify_new_call) { spin_unlock_bh(&sk->sk_receive_queue.lock); + skb_queue_tail(&call->knlrecv_queue, skb); + rx->notify_new_call(&rx->sk); + } else if (call->notify_rx) { + spin_unlock_bh(&sk->sk_receive_queue.lock); + skb_queue_tail(&call->knlrecv_queue, skb); + call->notify_rx(&rx->sk, call, call->user_call_ID); } else { _net("post skb %p", skb); __skb_queue_tail(&sk->sk_receive_queue, skb); @@ -124,11 +130,17 @@ static int rxrpc_fast_process_data(struct rxrpc_call *call, struct rxrpc_skb_priv *sp; bool terminal; int ret, ackbit, ack; + u32 serial; + u16 skew; + u8 flags; _enter("{%u,%u},,{%u}", call->rx_data_post, call->rx_first_oos, seq); sp = rxrpc_skb(skb); ASSERTCMP(sp->call, ==, NULL); + flags = sp->hdr.flags; + serial = sp->hdr.serial; + skew = skb->priority; spin_lock(&call->lock); @@ -190,10 +202,9 @@ static int rxrpc_fast_process_data(struct rxrpc_call *call, goto enqueue_packet; sp->call = call; - rxrpc_get_call(call); - atomic_inc(&call->skb_count); - terminal = ((sp->hdr.flags & RXRPC_LAST_PACKET) && - !(sp->hdr.flags & RXRPC_CLIENT_INITIATED)); + rxrpc_get_call_for_skb(call, skb); + terminal = ((flags & RXRPC_LAST_PACKET) && + !(flags & RXRPC_CLIENT_INITIATED)); ret = rxrpc_queue_rcv_skb(call, skb, false, terminal); if (ret < 0) { if (ret == -ENOMEM || ret == -ENOBUFS) { @@ -205,12 +216,13 @@ static int rxrpc_fast_process_data(struct rxrpc_call *call, } skb = NULL; + sp = NULL; _debug("post #%u", seq); ASSERTCMP(call->rx_data_post, ==, seq); call->rx_data_post++; - if (sp->hdr.flags & RXRPC_LAST_PACKET) + if (flags & RXRPC_LAST_PACKET) set_bit(RXRPC_CALL_RCVD_LAST, &call->flags); /* if we've reached an out of sequence packet then we need to drain @@ -226,7 +238,7 @@ static int rxrpc_fast_process_data(struct rxrpc_call *call, spin_unlock(&call->lock); atomic_inc(&call->ackr_not_idle); - rxrpc_propose_ACK(call, RXRPC_ACK_DELAY, sp->hdr.serial, false); + rxrpc_propose_ACK(call, RXRPC_ACK_DELAY, skew, serial, false); _leave(" = 0 [posted]"); return 0; @@ -239,7 +251,7 @@ out: discard_and_ack: _debug("discard and ACK packet %p", skb); - __rxrpc_propose_ACK(call, ack, sp->hdr.serial, true); + __rxrpc_propose_ACK(call, ack, skew, serial, true); discard: spin_unlock(&call->lock); rxrpc_free_skb(skb); @@ -247,7 +259,7 @@ discard: return 0; enqueue_and_ack: - __rxrpc_propose_ACK(call, ack, sp->hdr.serial, true); + __rxrpc_propose_ACK(call, ack, skew, serial, true); enqueue_packet: _net("defer skb %p", skb); spin_unlock(&call->lock); @@ -299,7 +311,7 @@ void rxrpc_fast_process_packet(struct rxrpc_call *call, struct sk_buff *skb) { struct rxrpc_skb_priv *sp = rxrpc_skb(skb); __be32 wtmp; - u32 hi_serial, abort_code; + u32 abort_code; _enter("%p,%p", call, skb); @@ -316,18 +328,12 @@ void rxrpc_fast_process_packet(struct rxrpc_call *call, struct sk_buff *skb) } #endif - /* track the latest serial number on this connection for ACK packet - * information */ - hi_serial = atomic_read(&call->conn->hi_serial); - while (sp->hdr.serial > hi_serial) - hi_serial = atomic_cmpxchg(&call->conn->hi_serial, hi_serial, - sp->hdr.serial); - /* request ACK generation for any ACK or DATA packet that requests * it */ if (sp->hdr.flags & RXRPC_REQUEST_ACK) { _proto("ACK Requested on %%%u", sp->hdr.serial); - rxrpc_propose_ACK(call, RXRPC_ACK_REQUESTED, sp->hdr.serial, false); + rxrpc_propose_ACK(call, RXRPC_ACK_REQUESTED, + skb->priority, sp->hdr.serial, false); } switch (sp->hdr.type) { @@ -340,14 +346,13 @@ void rxrpc_fast_process_packet(struct rxrpc_call *call, struct sk_buff *skb) abort_code = ntohl(wtmp); _proto("Rx ABORT %%%u { %x }", sp->hdr.serial, abort_code); - write_lock_bh(&call->state_lock); - if (call->state < RXRPC_CALL_COMPLETE) { - call->state = RXRPC_CALL_REMOTELY_ABORTED; - call->remote_abort = abort_code; + if (__rxrpc_set_call_completion(call, + RXRPC_CALL_REMOTELY_ABORTED, + abort_code, ECONNABORTED)) { set_bit(RXRPC_CALL_EV_RCVD_ABORT, &call->events); rxrpc_queue_call(call); } - goto free_packet_unlock; + goto free_packet; case RXRPC_PACKET_TYPE_BUSY: _proto("Rx BUSY %%%u", sp->hdr.serial); @@ -358,7 +363,9 @@ void rxrpc_fast_process_packet(struct rxrpc_call *call, struct sk_buff *skb) write_lock_bh(&call->state_lock); switch (call->state) { case RXRPC_CALL_CLIENT_SEND_REQUEST: - call->state = RXRPC_CALL_SERVER_BUSY; + __rxrpc_set_call_completion(call, + RXRPC_CALL_SERVER_BUSY, + 0, EBUSY); set_bit(RXRPC_CALL_EV_RCVD_BUSY, &call->events); rxrpc_queue_call(call); case RXRPC_CALL_SERVER_BUSY: @@ -414,12 +421,8 @@ protocol_error: _debug("protocol error"); write_lock_bh(&call->state_lock); protocol_error_locked: - if (call->state <= RXRPC_CALL_COMPLETE) { - call->state = RXRPC_CALL_LOCALLY_ABORTED; - call->local_abort = RX_PROTOCOL_ERROR; - set_bit(RXRPC_CALL_EV_ABORT, &call->events); + if (__rxrpc_abort_call(call, RX_PROTOCOL_ERROR, EPROTO)) rxrpc_queue_call(call); - } free_packet_unlock: write_unlock_bh(&call->state_lock); free_packet: @@ -485,14 +488,8 @@ protocol_error: _debug("protocol error"); rxrpc_free_skb(part); rxrpc_free_skb(jumbo); - write_lock_bh(&call->state_lock); - if (call->state <= RXRPC_CALL_COMPLETE) { - call->state = RXRPC_CALL_LOCALLY_ABORTED; - call->local_abort = RX_PROTOCOL_ERROR; - set_bit(RXRPC_CALL_EV_ABORT, &call->events); + if (rxrpc_abort_call(call, RX_PROTOCOL_ERROR, EPROTO)) rxrpc_queue_call(call); - } - write_unlock_bh(&call->state_lock); _leave(""); } @@ -513,26 +510,28 @@ static void rxrpc_post_packet_to_call(struct rxrpc_call *call, read_lock(&call->state_lock); switch (call->state) { - case RXRPC_CALL_LOCALLY_ABORTED: - if (!test_and_set_bit(RXRPC_CALL_EV_ABORT, &call->events)) { - rxrpc_queue_call(call); - goto free_unlock; - } - case RXRPC_CALL_REMOTELY_ABORTED: - case RXRPC_CALL_NETWORK_ERROR: case RXRPC_CALL_DEAD: goto dead_call; + case RXRPC_CALL_COMPLETE: - case RXRPC_CALL_CLIENT_FINAL_ACK: - /* complete server call */ - if (rxrpc_conn_is_service(call->conn)) + switch (call->completion) { + case RXRPC_CALL_LOCALLY_ABORTED: + if (!test_and_set_bit(RXRPC_CALL_EV_ABORT, + &call->events)) { + rxrpc_queue_call(call); + goto free_unlock; + } + default: goto dead_call; - /* resend last packet of a completed call */ - _debug("final ack again"); - rxrpc_get_call(call); - set_bit(RXRPC_CALL_EV_ACK_FINAL, &call->events); - rxrpc_queue_call(call); - goto free_unlock; + case RXRPC_CALL_SUCCEEDED: + if (rxrpc_conn_is_service(call->conn)) + goto dead_call; + goto resend_final_ack; + } + + case RXRPC_CALL_CLIENT_FINAL_ACK: + goto resend_final_ack; + default: break; } @@ -549,6 +548,13 @@ static void rxrpc_post_packet_to_call(struct rxrpc_call *call, rxrpc_put_call(call); goto done; +resend_final_ack: + _debug("final ack again"); + rxrpc_get_call(call); + set_bit(RXRPC_CALL_EV_ACK_FINAL, &call->events); + rxrpc_queue_call(call); + goto free_unlock; + dead_call: if (sp->hdr.type != RXRPC_PACKET_TYPE_ABORT) { skb->priority = RX_CALL_DEAD; @@ -565,15 +571,16 @@ done: /* * post connection-level events to the connection - * - this includes challenges, responses and some aborts + * - this includes challenges, responses, some aborts and call terminal packet + * retransmission. */ -static bool rxrpc_post_packet_to_conn(struct rxrpc_connection *conn, +static void rxrpc_post_packet_to_conn(struct rxrpc_connection *conn, struct sk_buff *skb) { _enter("%p,%p", conn, skb); skb_queue_tail(&conn->rx_queue, skb); - return rxrpc_queue_conn(conn); + rxrpc_queue_conn(conn); } /* @@ -632,7 +639,7 @@ void rxrpc_data_ready(struct sock *sk) struct rxrpc_skb_priv *sp; struct rxrpc_local *local = sk->sk_user_data; struct sk_buff *skb; - int ret; + int ret, skew; _enter("%p", sk); @@ -694,28 +701,66 @@ void rxrpc_data_ready(struct sock *sk) rcu_read_lock(); -retry_find_conn: conn = rxrpc_find_connection_rcu(local, skb); - if (!conn) + if (!conn) { + skb->priority = 0; goto cant_route_call; + } + + /* Note the serial number skew here */ + skew = (int)sp->hdr.serial - (int)conn->hi_serial; + if (skew >= 0) { + if (skew > 0) + conn->hi_serial = sp->hdr.serial; + skb->priority = 0; + } else { + skew = -skew; + skb->priority = min(skew, 65535); + } if (sp->hdr.callNumber == 0) { /* Connection-level packet */ _debug("CONN %p {%d}", conn, conn->debug_id); - if (!rxrpc_post_packet_to_conn(conn, skb)) - goto retry_find_conn; + rxrpc_post_packet_to_conn(conn, skb); + goto out_unlock; } else { /* Call-bound packets are routed by connection channel. */ unsigned int channel = sp->hdr.cid & RXRPC_CHANNELMASK; struct rxrpc_channel *chan = &conn->channels[channel]; - struct rxrpc_call *call = rcu_dereference(chan->call); + struct rxrpc_call *call; + + /* Ignore really old calls */ + if (sp->hdr.callNumber < chan->last_call) + goto discard_unlock; + + if (sp->hdr.callNumber == chan->last_call) { + /* For the previous service call, if completed + * successfully, we discard all further packets. + */ + if (rxrpc_conn_is_service(conn) && + (chan->last_type == RXRPC_PACKET_TYPE_ACK || + sp->hdr.type == RXRPC_PACKET_TYPE_ABORT)) + goto discard_unlock; + + /* But otherwise we need to retransmit the final packet + * from data cached in the connection record. + */ + rxrpc_post_packet_to_conn(conn, skb); + goto out_unlock; + } + call = rcu_dereference(chan->call); if (!call || atomic_read(&call->usage) == 0) goto cant_route_call; + rxrpc_see_call(call); rxrpc_post_packet_to_call(call, skb); + goto out_unlock; } +discard_unlock: + rxrpc_free_skb(skb); +out_unlock: rcu_read_unlock(); out: return; @@ -741,6 +786,8 @@ cant_route_call: if (sp->hdr.type != RXRPC_PACKET_TYPE_ABORT) { _debug("reject type %d",sp->hdr.type); rxrpc_reject_packet(local, skb); + } else { + rxrpc_free_skb(skb); } _leave(" [no call]"); return; diff --git a/net/rxrpc/local_event.c b/net/rxrpc/local_event.c index 31a3f86ef2f6..bcc6593b4cdb 100644 --- a/net/rxrpc/local_event.c +++ b/net/rxrpc/local_event.c @@ -93,6 +93,7 @@ void rxrpc_process_local_events(struct rxrpc_local *local) if (skb) { struct rxrpc_skb_priv *sp = rxrpc_skb(skb); + rxrpc_see_skb(skb); _debug("{%d},{%u}", local->debug_id, sp->hdr.type); switch (sp->hdr.type) { diff --git a/net/rxrpc/output.c b/net/rxrpc/output.c index f4bda06b7d2d..817ae801e769 100644 --- a/net/rxrpc/output.c +++ b/net/rxrpc/output.c @@ -115,12 +115,12 @@ static int rxrpc_sendmsg_cmsg(struct msghdr *msg, */ static void rxrpc_send_abort(struct rxrpc_call *call, u32 abort_code) { + if (call->state >= RXRPC_CALL_COMPLETE) + return; + write_lock_bh(&call->state_lock); - if (call->state <= RXRPC_CALL_COMPLETE) { - call->state = RXRPC_CALL_LOCALLY_ABORTED; - call->local_abort = abort_code; - set_bit(RXRPC_CALL_EV_ABORT, &call->events); + if (__rxrpc_abort_call(call, abort_code, ECONNABORTED)) { del_timer_sync(&call->resend_timer); del_timer_sync(&call->ack_timer); clear_bit(RXRPC_CALL_EV_RESEND_TIMER, &call->events); @@ -190,7 +190,7 @@ int rxrpc_do_sendmsg(struct rxrpc_sock *rx, struct msghdr *msg, size_t len) if (cmd == RXRPC_CMD_ACCEPT) { if (rx->sk.sk_state != RXRPC_SERVER_LISTENING) return -EINVAL; - call = rxrpc_accept_call(rx, user_call_ID); + call = rxrpc_accept_call(rx, user_call_ID, NULL); if (IS_ERR(call)) return PTR_ERR(call); rxrpc_put_call(call); @@ -207,22 +207,23 @@ int rxrpc_do_sendmsg(struct rxrpc_sock *rx, struct msghdr *msg, size_t len) return PTR_ERR(call); } + rxrpc_see_call(call); _debug("CALL %d USR %lx ST %d on CONN %p", call->debug_id, call->user_call_ID, call->state, call->conn); if (call->state >= RXRPC_CALL_COMPLETE) { /* it's too late for this call */ - ret = -ECONNRESET; + ret = -ESHUTDOWN; } else if (cmd == RXRPC_CMD_SEND_ABORT) { rxrpc_send_abort(call, abort_code); ret = 0; } else if (cmd != RXRPC_CMD_SEND_DATA) { ret = -EINVAL; - } else if (!call->in_clientflag && + } else if (rxrpc_is_client_call(call) && call->state != RXRPC_CALL_CLIENT_SEND_REQUEST) { /* request phase complete for this client call */ ret = -EPROTO; - } else if (call->in_clientflag && + } else if (rxrpc_is_service_call(call) && call->state != RXRPC_CALL_SERVER_ACK_REQUEST && call->state != RXRPC_CALL_SERVER_SEND_REPLY) { /* Reply phase not begun or not complete for service call. */ @@ -238,6 +239,7 @@ int rxrpc_do_sendmsg(struct rxrpc_sock *rx, struct msghdr *msg, size_t len) /** * rxrpc_kernel_send_data - Allow a kernel service to send data on a call + * @sock: The socket the call is on * @call: The call to send data through * @msg: The data to send * @len: The amount of data to send @@ -247,8 +249,8 @@ int rxrpc_do_sendmsg(struct rxrpc_sock *rx, struct msghdr *msg, size_t len) * nor should an address be supplied. MSG_MORE should be flagged if there's * more data to come, otherwise this data will end the transmission phase. */ -int rxrpc_kernel_send_data(struct rxrpc_call *call, struct msghdr *msg, - size_t len) +int rxrpc_kernel_send_data(struct socket *sock, struct rxrpc_call *call, + struct msghdr *msg, size_t len) { int ret; @@ -257,7 +259,7 @@ int rxrpc_kernel_send_data(struct rxrpc_call *call, struct msghdr *msg, ASSERTCMP(msg->msg_name, ==, NULL); ASSERTCMP(msg->msg_control, ==, NULL); - lock_sock(&call->socket->sk); + lock_sock(sock->sk); _debug("CALL %d USR %lx ST %d on CONN %p", call->debug_id, call->user_call_ID, call->state, call->conn); @@ -269,36 +271,36 @@ int rxrpc_kernel_send_data(struct rxrpc_call *call, struct msghdr *msg, call->state != RXRPC_CALL_SERVER_SEND_REPLY) { ret = -EPROTO; /* request phase complete for this client call */ } else { - ret = rxrpc_send_data(call->socket, call, msg, len); + ret = rxrpc_send_data(rxrpc_sk(sock->sk), call, msg, len); } - release_sock(&call->socket->sk); + release_sock(sock->sk); _leave(" = %d", ret); return ret; } - EXPORT_SYMBOL(rxrpc_kernel_send_data); /** * rxrpc_kernel_abort_call - Allow a kernel service to abort a call + * @sock: The socket the call is on * @call: The call to be aborted * @abort_code: The abort code to stick into the ABORT packet * * Allow a kernel service to abort a call, if it's still in an abortable state. */ -void rxrpc_kernel_abort_call(struct rxrpc_call *call, u32 abort_code) +void rxrpc_kernel_abort_call(struct socket *sock, struct rxrpc_call *call, + u32 abort_code) { _enter("{%d},%d", call->debug_id, abort_code); - lock_sock(&call->socket->sk); + lock_sock(sock->sk); _debug("CALL %d USR %lx ST %d on CONN %p", call->debug_id, call->user_call_ID, call->state, call->conn); - if (call->state < RXRPC_CALL_COMPLETE) - rxrpc_send_abort(call, abort_code); + rxrpc_send_abort(call, abort_code); - release_sock(&call->socket->sk); + release_sock(sock->sk); _leave(""); } @@ -390,7 +392,7 @@ static int rxrpc_wait_for_tx_window(struct rxrpc_sock *rx, call->acks_winsz), *timeo); - add_wait_queue(&call->tx_waitq, &myself); + add_wait_queue(&call->waitq, &myself); for (;;) { set_current_state(TASK_INTERRUPTIBLE); @@ -408,7 +410,7 @@ static int rxrpc_wait_for_tx_window(struct rxrpc_sock *rx, lock_sock(&rx->sk); } - remove_wait_queue(&call->tx_waitq, &myself); + remove_wait_queue(&call->waitq, &myself); set_current_state(TASK_RUNNING); _leave(" = %d", ret); return ret; @@ -482,6 +484,8 @@ static void rxrpc_queue_packet(struct rxrpc_call *call, struct sk_buff *skb, if (try_to_del_timer_sync(&call->ack_timer) >= 0) { /* the packet may be freed by rxrpc_process_call() before this * returns */ + if (rxrpc_is_client_call(call)) + rxrpc_expose_client_call(call); ret = rxrpc_send_data_packet(call->conn, skb); _net("sent skb %p", skb); } else { @@ -548,6 +552,7 @@ static int rxrpc_send_data(struct rxrpc_sock *rx, skb = call->tx_pending; call->tx_pending = NULL; + rxrpc_see_skb(skb); copied = 0; do { @@ -637,8 +642,8 @@ static int rxrpc_send_data(struct rxrpc_sock *rx, /* check for the far side aborting the call or a network error * occurring */ - if (call->state > RXRPC_CALL_COMPLETE) - goto call_aborted; + if (call->state == RXRPC_CALL_COMPLETE) + goto call_terminated; /* add the packet to the send queue if it's now full */ if (sp->remain <= 0 || @@ -699,15 +704,9 @@ out: _leave(" = %d", ret); return ret; -call_aborted: +call_terminated: rxrpc_free_skb(skb); - if (call->state == RXRPC_CALL_NETWORK_ERROR) - ret = call->error_report < RXRPC_LOCAL_ERROR_OFFSET ? - call->error_report : - call->error_report - RXRPC_LOCAL_ERROR_OFFSET; - else - ret = -ECONNABORTED; - _leave(" = %d", ret); + _leave(" = %d", -call->error); return ret; maybe_error: diff --git a/net/rxrpc/peer_event.c b/net/rxrpc/peer_event.c index 8940674b5e08..27b9ecad007e 100644 --- a/net/rxrpc/peer_event.c +++ b/net/rxrpc/peer_event.c @@ -248,13 +248,21 @@ void rxrpc_peer_error_distributor(struct work_struct *work) struct rxrpc_peer *peer = container_of(work, struct rxrpc_peer, error_distributor); struct rxrpc_call *call; - int error_report; + enum rxrpc_call_completion compl; + bool queue; + int error; _enter(""); - error_report = READ_ONCE(peer->error_report); + error = READ_ONCE(peer->error_report); + if (error < RXRPC_LOCAL_ERROR_OFFSET) { + compl = RXRPC_CALL_NETWORK_ERROR; + } else { + compl = RXRPC_CALL_LOCAL_ERROR; + error -= RXRPC_LOCAL_ERROR_OFFSET; + } - _debug("ISSUE ERROR %d", error_report); + _debug("ISSUE ERROR %s %d", rxrpc_call_completions[compl], error); spin_lock_bh(&peer->lock); @@ -262,16 +270,17 @@ void rxrpc_peer_error_distributor(struct work_struct *work) call = hlist_entry(peer->error_targets.first, struct rxrpc_call, error_link); hlist_del_init(&call->error_link); + rxrpc_see_call(call); + queue = false; write_lock(&call->state_lock); - if (call->state != RXRPC_CALL_COMPLETE && - call->state < RXRPC_CALL_NETWORK_ERROR) { - call->error_report = error_report; - call->state = RXRPC_CALL_NETWORK_ERROR; + if (__rxrpc_set_call_completion(call, compl, 0, error)) { set_bit(RXRPC_CALL_EV_RCVD_ERROR, &call->events); - rxrpc_queue_call(call); + queue = true; } write_unlock(&call->state_lock); + if (queue) + rxrpc_queue_call(call); } spin_unlock_bh(&peer->lock); diff --git a/net/rxrpc/peer_object.c b/net/rxrpc/peer_object.c index 538e9831c699..aebc73ac16dc 100644 --- a/net/rxrpc/peer_object.c +++ b/net/rxrpc/peer_object.c @@ -313,3 +313,18 @@ void __rxrpc_put_peer(struct rxrpc_peer *peer) kfree_rcu(peer, rcu); } + +/** + * rxrpc_kernel_get_peer - Get the peer address of a call + * @sock: The socket on which the call is in progress. + * @call: The call to query + * @_srx: Where to place the result + * + * Get the address of the remote peer in a call. + */ +void rxrpc_kernel_get_peer(struct socket *sock, struct rxrpc_call *call, + struct sockaddr_rxrpc *_srx) +{ + *_srx = call->peer->srx; +} +EXPORT_SYMBOL(rxrpc_kernel_get_peer); diff --git a/net/rxrpc/proc.c b/net/rxrpc/proc.c index ced5f07444e5..82c64055449d 100644 --- a/net/rxrpc/proc.c +++ b/net/rxrpc/proc.c @@ -22,7 +22,6 @@ static const char *const rxrpc_conn_states[RXRPC_CONN__NR_STATES] = { [RXRPC_CONN_SERVICE] = "SvSecure", [RXRPC_CONN_REMOTELY_ABORTED] = "RmtAbort", [RXRPC_CONN_LOCALLY_ABORTED] = "LocAbort", - [RXRPC_CONN_NETWORK_ERROR] = "NetError", }; /* @@ -46,7 +45,9 @@ static void rxrpc_call_seq_stop(struct seq_file *seq, void *v) static int rxrpc_call_seq_show(struct seq_file *seq, void *v) { - struct rxrpc_connection *conn; + struct rxrpc_local *local; + struct rxrpc_sock *rx; + struct rxrpc_peer *peer; struct rxrpc_call *call; char lbuff[4 + 4 + 4 + 4 + 5 + 1], rbuff[4 + 4 + 4 + 4 + 5 + 1]; @@ -60,15 +61,24 @@ static int rxrpc_call_seq_show(struct seq_file *seq, void *v) call = list_entry(v, struct rxrpc_call, link); - sprintf(lbuff, "%pI4:%u", - &call->local->srx.transport.sin.sin_addr, - ntohs(call->local->srx.transport.sin.sin_port)); + rx = READ_ONCE(call->socket); + if (rx) { + local = READ_ONCE(rx->local); + if (local) + sprintf(lbuff, "%pI4:%u", + &local->srx.transport.sin.sin_addr, + ntohs(local->srx.transport.sin.sin_port)); + else + strcpy(lbuff, "no_local"); + } else { + strcpy(lbuff, "no_socket"); + } - conn = call->conn; - if (conn) + peer = call->peer; + if (peer) sprintf(rbuff, "%pI4:%u", - &conn->params.peer->srx.transport.sin.sin_addr, - ntohs(conn->params.peer->srx.transport.sin.sin_port)); + &peer->srx.transport.sin.sin_addr, + ntohs(peer->srx.transport.sin.sin_port)); else strcpy(rbuff, "no_connection"); @@ -80,10 +90,10 @@ static int rxrpc_call_seq_show(struct seq_file *seq, void *v) call->service_id, call->cid, call->call_id, - call->in_clientflag ? "Svc" : "Clt", + rxrpc_is_service_call(call) ? "Svc" : "Clt", atomic_read(&call->usage), rxrpc_call_states[call->state], - call->remote_abort ?: call->local_abort, + call->abort_code, call->user_call_ID); return 0; @@ -115,13 +125,13 @@ const struct file_operations rxrpc_call_seq_fops = { static void *rxrpc_connection_seq_start(struct seq_file *seq, loff_t *_pos) { read_lock(&rxrpc_connection_lock); - return seq_list_start_head(&rxrpc_connections, *_pos); + return seq_list_start_head(&rxrpc_connection_proc_list, *_pos); } static void *rxrpc_connection_seq_next(struct seq_file *seq, void *v, loff_t *pos) { - return seq_list_next(v, &rxrpc_connections, pos); + return seq_list_next(v, &rxrpc_connection_proc_list, pos); } static void rxrpc_connection_seq_stop(struct seq_file *seq, void *v) @@ -134,7 +144,7 @@ static int rxrpc_connection_seq_show(struct seq_file *seq, void *v) struct rxrpc_connection *conn; char lbuff[4 + 4 + 4 + 4 + 5 + 1], rbuff[4 + 4 + 4 + 4 + 5 + 1]; - if (v == &rxrpc_connections) { + if (v == &rxrpc_connection_proc_list) { seq_puts(seq, "Proto Local Remote " " SvID ConnID End Use State Key " @@ -143,7 +153,7 @@ static int rxrpc_connection_seq_show(struct seq_file *seq, void *v) return 0; } - conn = list_entry(v, struct rxrpc_connection, link); + conn = list_entry(v, struct rxrpc_connection, proc_link); sprintf(lbuff, "%pI4:%u", &conn->params.local->srx.transport.sin.sin_addr, @@ -165,7 +175,7 @@ static int rxrpc_connection_seq_show(struct seq_file *seq, void *v) rxrpc_conn_states[conn->state], key_serial(conn->params.key), atomic_read(&conn->serial), - atomic_read(&conn->hi_serial)); + conn->hi_serial); return 0; } diff --git a/net/rxrpc/recvmsg.c b/net/rxrpc/recvmsg.c index 9ed66d533002..0ab7b334bab1 100644 --- a/net/rxrpc/recvmsg.c +++ b/net/rxrpc/recvmsg.c @@ -111,9 +111,11 @@ int rxrpc_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, } peek_next_packet: + rxrpc_see_skb(skb); sp = rxrpc_skb(skb); call = sp->call; ASSERT(call != NULL); + rxrpc_see_call(call); _debug("next pkt %s", rxrpc_pkts[sp->hdr.type]); @@ -293,12 +295,17 @@ receive_non_data_message: ret = put_cmsg(msg, SOL_RXRPC, RXRPC_BUSY, 0, &abort_code); break; case RXRPC_SKB_MARK_REMOTE_ABORT: - abort_code = call->remote_abort; + abort_code = call->abort_code; ret = put_cmsg(msg, SOL_RXRPC, RXRPC_ABORT, 4, &abort_code); break; case RXRPC_SKB_MARK_LOCAL_ABORT: - abort_code = call->local_abort; + abort_code = call->abort_code; ret = put_cmsg(msg, SOL_RXRPC, RXRPC_ABORT, 4, &abort_code); + if (call->error) { + abort_code = call->error; + ret = put_cmsg(msg, SOL_RXRPC, RXRPC_LOCAL_ERROR, 4, + &abort_code); + } break; case RXRPC_SKB_MARK_NET_ERROR: _debug("RECV NET ERROR %d", sp->error); @@ -362,56 +369,178 @@ wait_error: } -/** - * rxrpc_kernel_is_data_last - Determine if data message is last one - * @skb: Message holding data +/* + * Deliver messages to a call. This keeps processing packets until the buffer + * is filled and we find either more DATA (returns 0) or the end of the DATA + * (returns 1). If more packets are required, it returns -EAGAIN. * - * Determine if data message is last one for the parent call. + * TODO: Note that this is hacked in at the moment and will be replaced. */ -bool rxrpc_kernel_is_data_last(struct sk_buff *skb) +static int temp_deliver_data(struct socket *sock, struct rxrpc_call *call, + struct iov_iter *iter, size_t size, + size_t *_offset) { - struct rxrpc_skb_priv *sp = rxrpc_skb(skb); + struct rxrpc_skb_priv *sp; + struct sk_buff *skb; + size_t remain; + int ret, copy; + + _enter("%d", call->debug_id); + +next: + local_bh_disable(); + skb = skb_dequeue(&call->knlrecv_queue); + local_bh_enable(); + if (!skb) { + if (test_bit(RXRPC_CALL_RX_NO_MORE, &call->flags)) + return 1; + _leave(" = -EAGAIN [empty]"); + return -EAGAIN; + } - ASSERTCMP(skb->mark, ==, RXRPC_SKB_MARK_DATA); + sp = rxrpc_skb(skb); + _debug("dequeued %p %u/%zu", skb, sp->offset, size); - return sp->hdr.flags & RXRPC_LAST_PACKET; -} + switch (skb->mark) { + case RXRPC_SKB_MARK_DATA: + remain = size - *_offset; + if (remain > 0) { + copy = skb->len - sp->offset; + if (copy > remain) + copy = remain; + ret = skb_copy_datagram_iter(skb, sp->offset, iter, + copy); + if (ret < 0) + goto requeue_and_leave; -EXPORT_SYMBOL(rxrpc_kernel_is_data_last); + /* handle piecemeal consumption of data packets */ + sp->offset += copy; + *_offset += copy; + } -/** - * rxrpc_kernel_get_abort_code - Get the abort code from an RxRPC abort message - * @skb: Message indicating an abort - * - * Get the abort code from an RxRPC abort message. - */ -u32 rxrpc_kernel_get_abort_code(struct sk_buff *skb) -{ - struct rxrpc_skb_priv *sp = rxrpc_skb(skb); + if (sp->offset < skb->len) + goto partially_used_skb; + + /* We consumed the whole packet */ + ASSERTCMP(sp->offset, ==, skb->len); + if (sp->hdr.flags & RXRPC_LAST_PACKET) + set_bit(RXRPC_CALL_RX_NO_MORE, &call->flags); + rxrpc_kernel_data_consumed(call, skb); + rxrpc_free_skb(skb); + goto next; - switch (skb->mark) { - case RXRPC_SKB_MARK_REMOTE_ABORT: - return sp->call->remote_abort; - case RXRPC_SKB_MARK_LOCAL_ABORT: - return sp->call->local_abort; default: - BUG(); + rxrpc_free_skb(skb); + goto next; } -} -EXPORT_SYMBOL(rxrpc_kernel_get_abort_code); +partially_used_skb: + ASSERTCMP(*_offset, ==, size); + ret = 0; +requeue_and_leave: + skb_queue_head(&call->knlrecv_queue, skb); + return ret; +} /** - * rxrpc_kernel_get_error - Get the error number from an RxRPC error message - * @skb: Message indicating an error + * rxrpc_kernel_recv_data - Allow a kernel service to receive data/info + * @sock: The socket that the call exists on + * @call: The call to send data through + * @buf: The buffer to receive into + * @size: The size of the buffer, including data already read + * @_offset: The running offset into the buffer. + * @want_more: True if more data is expected to be read + * @_abort: Where the abort code is stored if -ECONNABORTED is returned + * + * Allow a kernel service to receive data and pick up information about the + * state of a call. Returns 0 if got what was asked for and there's more + * available, 1 if we got what was asked for and we're at the end of the data + * and -EAGAIN if we need more data. + * + * Note that we may return -EAGAIN to drain empty packets at the end of the + * data, even if we've already copied over the requested data. * - * Get the error number from an RxRPC error message. + * This function adds the amount it transfers to *_offset, so this should be + * precleared as appropriate. Note that the amount remaining in the buffer is + * taken to be size - *_offset. + * + * *_abort should also be initialised to 0. */ -int rxrpc_kernel_get_error_number(struct sk_buff *skb) +int rxrpc_kernel_recv_data(struct socket *sock, struct rxrpc_call *call, + void *buf, size_t size, size_t *_offset, + bool want_more, u32 *_abort) { - struct rxrpc_skb_priv *sp = rxrpc_skb(skb); + struct iov_iter iter; + struct kvec iov; + int ret; - return sp->error; -} + _enter("{%d,%s},%zu,%d", + call->debug_id, rxrpc_call_states[call->state], size, want_more); + + ASSERTCMP(*_offset, <=, size); + ASSERTCMP(call->state, !=, RXRPC_CALL_SERVER_ACCEPTING); -EXPORT_SYMBOL(rxrpc_kernel_get_error_number); + iov.iov_base = buf + *_offset; + iov.iov_len = size - *_offset; + iov_iter_kvec(&iter, ITER_KVEC | READ, &iov, 1, size - *_offset); + + lock_sock(sock->sk); + + switch (call->state) { + case RXRPC_CALL_CLIENT_RECV_REPLY: + case RXRPC_CALL_SERVER_RECV_REQUEST: + case RXRPC_CALL_SERVER_ACK_REQUEST: + ret = temp_deliver_data(sock, call, &iter, size, _offset); + if (ret < 0) + goto out; + + /* We can only reach here with a partially full buffer if we + * have reached the end of the data. We must otherwise have a + * full buffer or have been given -EAGAIN. + */ + if (ret == 1) { + if (*_offset < size) + goto short_data; + if (!want_more) + goto read_phase_complete; + ret = 0; + goto out; + } + + if (!want_more) + goto excess_data; + goto out; + + case RXRPC_CALL_COMPLETE: + goto call_complete; + + default: + *_offset = 0; + ret = -EINPROGRESS; + goto out; + } + +read_phase_complete: + ret = 1; +out: + release_sock(sock->sk); + _leave(" = %d [%zu,%d]", ret, *_offset, *_abort); + return ret; + +short_data: + ret = -EBADMSG; + goto out; +excess_data: + ret = -EMSGSIZE; + goto out; +call_complete: + *_abort = call->abort_code; + ret = call->error; + if (call->completion == RXRPC_CALL_SUCCEEDED) { + ret = 1; + if (size > 0) + ret = -ECONNRESET; + } + goto out; +} +EXPORT_SYMBOL(rxrpc_kernel_recv_data); diff --git a/net/rxrpc/rxkad.c b/net/rxrpc/rxkad.c index 63afa9e9cc08..89f475febfd7 100644 --- a/net/rxrpc/rxkad.c +++ b/net/rxrpc/rxkad.c @@ -275,7 +275,7 @@ static int rxkad_secure_packet(struct rxrpc_call *call, memcpy(&iv, call->conn->csum_iv.x, sizeof(iv)); /* calculate the security checksum */ - x = call->channel << (32 - RXRPC_CIDSHIFT); + x = (call->cid & RXRPC_CHANNELMASK) << (32 - RXRPC_CIDSHIFT); x |= sp->hdr.seq & 0x3fffffff; call->crypto_buf[0] = htonl(sp->hdr.callNumber); call->crypto_buf[1] = htonl(x); @@ -507,7 +507,7 @@ static int rxkad_verify_packet(struct rxrpc_call *call, memcpy(&iv, call->conn->csum_iv.x, sizeof(iv)); /* validate the security checksum */ - x = call->channel << (32 - RXRPC_CIDSHIFT); + x = (call->cid & RXRPC_CHANNELMASK) << (32 - RXRPC_CIDSHIFT); x |= sp->hdr.seq & 0x3fffffff; call->crypto_buf[0] = htonl(call->call_id); call->crypto_buf[1] = htonl(x); diff --git a/net/rxrpc/skbuff.c b/net/rxrpc/skbuff.c index 06c51d4b622d..9752f8b1fdd0 100644 --- a/net/rxrpc/skbuff.c +++ b/net/rxrpc/skbuff.c @@ -53,9 +53,9 @@ static void rxrpc_request_final_ACK(struct rxrpc_call *call) /* * drop the bottom ACK off of the call ACK window and advance the window */ -static void rxrpc_hard_ACK_data(struct rxrpc_call *call, - struct rxrpc_skb_priv *sp) +static void rxrpc_hard_ACK_data(struct rxrpc_call *call, struct sk_buff *skb) { + struct rxrpc_skb_priv *sp = rxrpc_skb(skb); int loop; u32 seq; @@ -91,8 +91,8 @@ static void rxrpc_hard_ACK_data(struct rxrpc_call *call, * its Tx bufferage. */ _debug("send Rx idle ACK"); - __rxrpc_propose_ACK(call, RXRPC_ACK_IDLE, sp->hdr.serial, - false); + __rxrpc_propose_ACK(call, RXRPC_ACK_IDLE, + skb->priority, sp->hdr.serial, false); } spin_unlock_bh(&call->lock); @@ -125,9 +125,8 @@ void rxrpc_kernel_data_consumed(struct rxrpc_call *call, struct sk_buff *skb) ASSERTCMP(sp->hdr.seq, >, call->rx_data_eaten); call->rx_data_recv = sp->hdr.seq; - rxrpc_hard_ACK_data(call, sp); + rxrpc_hard_ACK_data(call, skb); } -EXPORT_SYMBOL(rxrpc_kernel_data_consumed); /* * Destroy a packet that has an RxRPC control buffer @@ -140,9 +139,7 @@ void rxrpc_packet_destructor(struct sk_buff *skb) _enter("%p{%p}", skb, call); if (call) { - if (atomic_dec_return(&call->skb_count) < 0) - BUG(); - rxrpc_put_call(call); + rxrpc_put_call_for_skb(call, skb); sp->call = NULL; } @@ -163,3 +160,65 @@ void rxrpc_kernel_free_skb(struct sk_buff *skb) rxrpc_free_skb(skb); } EXPORT_SYMBOL(rxrpc_kernel_free_skb); + +/* + * Note the existence of a new-to-us socket buffer (allocated or dequeued). + */ +void rxrpc_new_skb(struct sk_buff *skb) +{ + const void *here = __builtin_return_address(0); + int n = atomic_inc_return(&rxrpc_n_skbs); + trace_rxrpc_skb(skb, 0, atomic_read(&skb->users), n, here); +} + +/* + * Note the re-emergence of a socket buffer from a queue or buffer. + */ +void rxrpc_see_skb(struct sk_buff *skb) +{ + const void *here = __builtin_return_address(0); + if (skb) { + int n = atomic_read(&rxrpc_n_skbs); + trace_rxrpc_skb(skb, 1, atomic_read(&skb->users), n, here); + } +} + +/* + * Note the addition of a ref on a socket buffer. + */ +void rxrpc_get_skb(struct sk_buff *skb) +{ + const void *here = __builtin_return_address(0); + int n = atomic_inc_return(&rxrpc_n_skbs); + trace_rxrpc_skb(skb, 2, atomic_read(&skb->users), n, here); + skb_get(skb); +} + +/* + * Note the destruction of a socket buffer. + */ +void rxrpc_free_skb(struct sk_buff *skb) +{ + const void *here = __builtin_return_address(0); + if (skb) { + int n; + CHECK_SLAB_OKAY(&skb->users); + n = atomic_dec_return(&rxrpc_n_skbs); + trace_rxrpc_skb(skb, 3, atomic_read(&skb->users), n, here); + kfree_skb(skb); + } +} + +/* + * Clear a queue of socket buffers. + */ +void rxrpc_purge_queue(struct sk_buff_head *list) +{ + const void *here = __builtin_return_address(0); + struct sk_buff *skb; + while ((skb = skb_dequeue((list))) != NULL) { + int n = atomic_dec_return(&rxrpc_n_skbs); + trace_rxrpc_skb(skb, 4, atomic_read(&skb->users), n, here); + kfree_skb(skb); + } +} diff --git a/net/rxrpc/sysctl.c b/net/rxrpc/sysctl.c index 03ad08774d4e..dc380af8a81e 100644 --- a/net/rxrpc/sysctl.c +++ b/net/rxrpc/sysctl.c @@ -62,6 +62,22 @@ static struct ctl_table rxrpc_sysctl_table[] = { .proc_handler = proc_dointvec_ms_jiffies, .extra1 = (void *)&one, }, + { + .procname = "idle_conn_expiry", + .data = &rxrpc_conn_idle_client_expiry, + .maxlen = sizeof(unsigned int), + .mode = 0644, + .proc_handler = proc_dointvec_ms_jiffies, + .extra1 = (void *)&one, + }, + { + .procname = "idle_conn_fast_expiry", + .data = &rxrpc_conn_idle_client_fast_expiry, + .maxlen = sizeof(unsigned int), + .mode = 0644, + .proc_handler = proc_dointvec_ms_jiffies, + .extra1 = (void *)&one, + }, /* Values measured in seconds but used in jiffies */ { @@ -81,17 +97,24 @@ static struct ctl_table rxrpc_sysctl_table[] = { .extra1 = (void *)&one, }, - /* Values measured in seconds */ + /* Non-time values */ + { + .procname = "max_client_conns", + .data = &rxrpc_max_client_connections, + .maxlen = sizeof(unsigned int), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = (void *)&rxrpc_reap_client_connections, + }, { - .procname = "connection_expiry", - .data = &rxrpc_connection_expiry, + .procname = "reap_client_conns", + .data = &rxrpc_reap_client_connections, .maxlen = sizeof(unsigned int), .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = (void *)&one, + .extra2 = (void *)&rxrpc_max_client_connections, }, - - /* Non-time values */ { .procname = "max_backlog", .data = &rxrpc_max_backlog, diff --git a/net/sched/act_api.c b/net/sched/act_api.c index e4a5f2607ffa..d09d0687594b 100644 --- a/net/sched/act_api.c +++ b/net/sched/act_api.c @@ -64,7 +64,6 @@ int __tcf_hash_release(struct tc_action *p, bool bind, bool strict) if (p->tcfa_bindcnt <= 0 && p->tcfa_refcnt <= 0) { if (p->ops->cleanup) p->ops->cleanup(p, bind); - list_del(&p->list); tcf_hash_destroy(p->hinfo, p); ret = ACT_P_DELETED; } @@ -421,18 +420,19 @@ static struct tc_action_ops *tc_lookup_action(struct nlattr *kind) return res; } -int tcf_action_exec(struct sk_buff *skb, const struct list_head *actions, - struct tcf_result *res) +int tcf_action_exec(struct sk_buff *skb, struct tc_action **actions, + int nr_actions, struct tcf_result *res) { - const struct tc_action *a; - int ret = -1; + int ret = -1, i; if (skb->tc_verd & TC_NCLS) { skb->tc_verd = CLR_TC_NCLS(skb->tc_verd); ret = TC_ACT_OK; goto exec_done; } - list_for_each_entry(a, actions, list) { + for (i = 0; i < nr_actions; i++) { + const struct tc_action *a = actions[i]; + repeat: ret = a->ops->act(skb, a, res); if (ret == TC_ACT_REPEAT) @@ -754,16 +754,6 @@ err_out: return ERR_PTR(err); } -static void cleanup_a(struct list_head *actions) -{ - struct tc_action *a, *tmp; - - list_for_each_entry_safe(a, tmp, actions, list) { - list_del(&a->list); - kfree(a); - } -} - static int tca_action_flush(struct net *net, struct nlattr *nla, struct nlmsghdr *n, u32 portid) { @@ -905,7 +895,7 @@ tca_action_gd(struct net *net, struct nlattr *nla, struct nlmsghdr *n, return ret; } err: - cleanup_a(&actions); + tcf_action_destroy(&actions, 0); return ret; } @@ -942,15 +932,9 @@ tcf_action_add(struct net *net, struct nlattr *nla, struct nlmsghdr *n, ret = tcf_action_init(net, nla, NULL, NULL, ovr, 0, &actions); if (ret) - goto done; + return ret; - /* dump then free all the actions after update; inserted policy - * stays intact - */ - ret = tcf_add_notify(net, n, &actions, portid); - cleanup_a(&actions); -done: - return ret; + return tcf_add_notify(net, n, &actions, portid); } static int tc_ctl_action(struct sk_buff *skb, struct nlmsghdr *n) diff --git a/net/sched/act_ife.c b/net/sched/act_ife.c index 141a06eeb1e5..e87cd81315e1 100644 --- a/net/sched/act_ife.c +++ b/net/sched/act_ife.c @@ -53,7 +53,7 @@ int ife_tlv_meta_encode(void *skbdata, u16 attrtype, u16 dlen, const void *dval) u32 *tlv = (u32 *)(skbdata); u16 totlen = nla_total_size(dlen); /*alignment + hdr */ char *dptr = (char *)tlv + NLA_HDRLEN; - u32 htlv = attrtype << 16 | totlen; + u32 htlv = attrtype << 16 | dlen; *tlv = htonl(htlv); memset(dptr, 0, totlen - NLA_HDRLEN); @@ -135,7 +135,7 @@ EXPORT_SYMBOL_GPL(ife_release_meta_gen); int ife_validate_meta_u32(void *val, int len) { - if (len == 4) + if (len == sizeof(u32)) return 0; return -EINVAL; @@ -144,8 +144,8 @@ EXPORT_SYMBOL_GPL(ife_validate_meta_u32); int ife_validate_meta_u16(void *val, int len) { - /* length will include padding */ - if (len == NLA_ALIGN(2)) + /* length will not include padding */ + if (len == sizeof(u16)) return 0; return -EINVAL; @@ -652,12 +652,14 @@ static int tcf_ife_decode(struct sk_buff *skb, const struct tc_action *a, u8 *tlvdata = (u8 *)tlv; u16 mtype = tlv->type; u16 mlen = tlv->len; + u16 alen; mtype = ntohs(mtype); mlen = ntohs(mlen); + alen = NLA_ALIGN(mlen); - if (find_decode_metaid(skb, ife, mtype, (mlen - 4), - (void *)(tlvdata + 4))) { + if (find_decode_metaid(skb, ife, mtype, (mlen - NLA_HDRLEN), + (void *)(tlvdata + NLA_HDRLEN))) { /* abuse overlimits to count when we receive metadata * but dont have an ops for it */ @@ -666,8 +668,8 @@ static int tcf_ife_decode(struct sk_buff *skb, const struct tc_action *a, ife->tcf_qstats.overlimits++; } - tlvdata += mlen; - ifehdrln -= mlen; + tlvdata += alen; + ifehdrln -= alen; tlv = (struct meta_tlvhdr *)tlvdata; } diff --git a/net/sched/act_police.c b/net/sched/act_police.c index b3c7e975fc9e..8a3be1d99775 100644 --- a/net/sched/act_police.c +++ b/net/sched/act_police.c @@ -63,49 +63,8 @@ static int tcf_act_police_walker(struct net *net, struct sk_buff *skb, const struct tc_action_ops *ops) { struct tc_action_net *tn = net_generic(net, police_net_id); - struct tcf_hashinfo *hinfo = tn->hinfo; - int err = 0, index = -1, i = 0, s_i = 0, n_i = 0; - struct nlattr *nest; - - spin_lock_bh(&hinfo->lock); - - s_i = cb->args[0]; - - for (i = 0; i < (POL_TAB_MASK + 1); i++) { - struct hlist_head *head; - struct tc_action *p; - - head = &hinfo->htab[tcf_hash(i, POL_TAB_MASK)]; - - hlist_for_each_entry_rcu(p, head, tcfa_head) { - index++; - if (index < s_i) - continue; - nest = nla_nest_start(skb, index); - if (nest == NULL) - goto nla_put_failure; - if (type == RTM_DELACTION) - err = tcf_action_dump_1(skb, p, 0, 1); - else - err = tcf_action_dump_1(skb, p, 0, 0); - if (err < 0) { - index--; - nla_nest_cancel(skb, nest); - goto done; - } - nla_nest_end(skb, nest); - n_i++; - } - } -done: - spin_unlock_bh(&hinfo->lock); - if (n_i) - cb->args[0] += n_i; - return n_i; -nla_put_failure: - nla_nest_cancel(skb, nest); - goto done; + return tcf_generic_walker(tn, skb, cb, type, ops); } static const struct nla_policy police_policy[TCA_POLICE_MAX + 1] = { @@ -125,6 +84,7 @@ static int tcf_act_police_init(struct net *net, struct nlattr *nla, struct tcf_police *police; struct qdisc_rate_table *R_tab = NULL, *P_tab = NULL; struct tc_action_net *tn = net_generic(net, police_net_id); + bool exists = false; int size; if (nla == NULL) @@ -139,24 +99,24 @@ static int tcf_act_police_init(struct net *net, struct nlattr *nla, size = nla_len(tb[TCA_POLICE_TBF]); if (size != sizeof(*parm) && size != sizeof(struct tc_police_compat)) return -EINVAL; + parm = nla_data(tb[TCA_POLICE_TBF]); + exists = tcf_hash_check(tn, parm->index, a, bind); + if (exists && bind) + return 0; - if (parm->index) { - if (tcf_hash_check(tn, parm->index, a, bind)) { - if (ovr) - goto override; - /* not replacing */ - return -EEXIST; - } - } else { + if (!exists) { ret = tcf_hash_create(tn, parm->index, NULL, a, &act_police_ops, bind, false); if (ret) return ret; ret = ACT_P_CREATED; + } else { + tcf_hash_release(*a, bind); + if (!ovr) + return -EEXIST; } -override: police = to_police(*a); if (parm->rate.rate) { err = -ENOMEM; diff --git a/net/sched/act_vlan.c b/net/sched/act_vlan.c index 691409de3e1a..59a8d3150ae2 100644 --- a/net/sched/act_vlan.c +++ b/net/sched/act_vlan.c @@ -43,7 +43,8 @@ static int tcf_vlan(struct sk_buff *skb, const struct tc_action *a, goto drop; break; case TCA_VLAN_ACT_PUSH: - err = skb_vlan_push(skb, v->tcfv_push_proto, v->tcfv_push_vid); + err = skb_vlan_push(skb, v->tcfv_push_proto, v->tcfv_push_vid | + (v->tcfv_push_prio << VLAN_PRIO_SHIFT)); if (err) goto drop; break; @@ -65,6 +66,7 @@ static const struct nla_policy vlan_policy[TCA_VLAN_MAX + 1] = { [TCA_VLAN_PARMS] = { .len = sizeof(struct tc_vlan) }, [TCA_VLAN_PUSH_VLAN_ID] = { .type = NLA_U16 }, [TCA_VLAN_PUSH_VLAN_PROTOCOL] = { .type = NLA_U16 }, + [TCA_VLAN_PUSH_VLAN_PRIORITY] = { .type = NLA_U8 }, }; static int tcf_vlan_init(struct net *net, struct nlattr *nla, @@ -78,6 +80,7 @@ static int tcf_vlan_init(struct net *net, struct nlattr *nla, int action; __be16 push_vid = 0; __be16 push_proto = 0; + u8 push_prio = 0; bool exists = false; int ret = 0, err; @@ -123,6 +126,9 @@ static int tcf_vlan_init(struct net *net, struct nlattr *nla, } else { push_proto = htons(ETH_P_8021Q); } + + if (tb[TCA_VLAN_PUSH_VLAN_PRIORITY]) + push_prio = nla_get_u8(tb[TCA_VLAN_PUSH_VLAN_PRIORITY]); break; default: if (exists) @@ -150,6 +156,7 @@ static int tcf_vlan_init(struct net *net, struct nlattr *nla, v->tcfv_action = action; v->tcfv_push_vid = push_vid; + v->tcfv_push_prio = push_prio; v->tcfv_push_proto = push_proto; v->tcf_action = parm->action; @@ -181,7 +188,9 @@ static int tcf_vlan_dump(struct sk_buff *skb, struct tc_action *a, if (v->tcfv_action == TCA_VLAN_ACT_PUSH && (nla_put_u16(skb, TCA_VLAN_PUSH_VLAN_ID, v->tcfv_push_vid) || nla_put_be16(skb, TCA_VLAN_PUSH_VLAN_PROTOCOL, - v->tcfv_push_proto))) + v->tcfv_push_proto) || + (nla_put_u8(skb, TCA_VLAN_PUSH_VLAN_PRIORITY, + v->tcfv_push_prio)))) goto nla_put_failure; tcf_tm_dump(&t, &v->tcf_tm); diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index 843a716a4303..a7c5645373af 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -541,8 +541,12 @@ out: void tcf_exts_destroy(struct tcf_exts *exts) { #ifdef CONFIG_NET_CLS_ACT - tcf_action_destroy(&exts->actions, TCA_ACT_UNBIND); - INIT_LIST_HEAD(&exts->actions); + LIST_HEAD(actions); + + tcf_exts_to_list(exts, &actions); + tcf_action_destroy(&actions, TCA_ACT_UNBIND); + kfree(exts->actions); + exts->nr_actions = 0; #endif } EXPORT_SYMBOL(tcf_exts_destroy); @@ -554,7 +558,6 @@ int tcf_exts_validate(struct net *net, struct tcf_proto *tp, struct nlattr **tb, { struct tc_action *act; - INIT_LIST_HEAD(&exts->actions); if (exts->police && tb[exts->police]) { act = tcf_action_init_1(net, tb[exts->police], rate_tlv, "police", ovr, @@ -563,14 +566,20 @@ int tcf_exts_validate(struct net *net, struct tcf_proto *tp, struct nlattr **tb, return PTR_ERR(act); act->type = exts->type = TCA_OLD_COMPAT; - list_add(&act->list, &exts->actions); + exts->actions[0] = act; + exts->nr_actions = 1; } else if (exts->action && tb[exts->action]) { - int err; + LIST_HEAD(actions); + int err, i = 0; + err = tcf_action_init(net, tb[exts->action], rate_tlv, NULL, ovr, - TCA_ACT_BIND, &exts->actions); + TCA_ACT_BIND, &actions); if (err) return err; + list_for_each_entry(act, &actions, list) + exts->actions[i++] = act; + exts->nr_actions = i; } } #else @@ -587,37 +596,49 @@ void tcf_exts_change(struct tcf_proto *tp, struct tcf_exts *dst, struct tcf_exts *src) { #ifdef CONFIG_NET_CLS_ACT - LIST_HEAD(tmp); + struct tcf_exts old = *dst; + tcf_tree_lock(tp); - list_splice_init(&dst->actions, &tmp); - list_splice(&src->actions, &dst->actions); + dst->nr_actions = src->nr_actions; + dst->actions = src->actions; dst->type = src->type; tcf_tree_unlock(tp); - tcf_action_destroy(&tmp, TCA_ACT_UNBIND); + + tcf_exts_destroy(&old); #endif } EXPORT_SYMBOL(tcf_exts_change); -#define tcf_exts_first_act(ext) \ - list_first_entry_or_null(&(exts)->actions, \ - struct tc_action, list) +#ifdef CONFIG_NET_CLS_ACT +static struct tc_action *tcf_exts_first_act(struct tcf_exts *exts) +{ + if (exts->nr_actions == 0) + return NULL; + else + return exts->actions[0]; +} +#endif int tcf_exts_dump(struct sk_buff *skb, struct tcf_exts *exts) { #ifdef CONFIG_NET_CLS_ACT struct nlattr *nest; - if (exts->action && !list_empty(&exts->actions)) { + if (exts->action && exts->nr_actions) { /* * again for backward compatible mode - we want * to work with both old and new modes of entering * tc data even if iproute2 was newer - jhs */ if (exts->type != TCA_OLD_COMPAT) { + LIST_HEAD(actions); + nest = nla_nest_start(skb, exts->action); if (nest == NULL) goto nla_put_failure; - if (tcf_action_dump(skb, &exts->actions, 0, 0) < 0) + + tcf_exts_to_list(exts, &actions); + if (tcf_action_dump(skb, &actions, 0, 0) < 0) goto nla_put_failure; nla_nest_end(skb, nest); } else if (exts->police) { diff --git a/net/sched/cls_basic.c b/net/sched/cls_basic.c index 0b8c3ace671f..eb219b78cd49 100644 --- a/net/sched/cls_basic.c +++ b/net/sched/cls_basic.c @@ -138,10 +138,12 @@ static int basic_set_parms(struct net *net, struct tcf_proto *tp, struct tcf_exts e; struct tcf_ematch_tree t; - tcf_exts_init(&e, TCA_BASIC_ACT, TCA_BASIC_POLICE); - err = tcf_exts_validate(net, tp, tb, est, &e, ovr); + err = tcf_exts_init(&e, TCA_BASIC_ACT, TCA_BASIC_POLICE); if (err < 0) return err; + err = tcf_exts_validate(net, tp, tb, est, &e, ovr); + if (err < 0) + goto errout; err = tcf_em_tree_validate(tp, tb[TCA_BASIC_EMATCHES], &t); if (err < 0) @@ -189,7 +191,10 @@ static int basic_change(struct net *net, struct sk_buff *in_skb, if (!fnew) return -ENOBUFS; - tcf_exts_init(&fnew->exts, TCA_BASIC_ACT, TCA_BASIC_POLICE); + err = tcf_exts_init(&fnew->exts, TCA_BASIC_ACT, TCA_BASIC_POLICE); + if (err < 0) + goto errout; + err = -EINVAL; if (handle) { fnew->handle = handle; @@ -226,6 +231,7 @@ static int basic_change(struct net *net, struct sk_buff *in_skb, return 0; errout: + tcf_exts_destroy(&fnew->exts); kfree(fnew); return err; } diff --git a/net/sched/cls_bpf.c b/net/sched/cls_bpf.c index c3002c2c68bb..4742f415ee5b 100644 --- a/net/sched/cls_bpf.c +++ b/net/sched/cls_bpf.c @@ -311,17 +311,19 @@ static int cls_bpf_modify_existing(struct net *net, struct tcf_proto *tp, if ((!is_bpf && !is_ebpf) || (is_bpf && is_ebpf)) return -EINVAL; - tcf_exts_init(&exts, TCA_BPF_ACT, TCA_BPF_POLICE); - ret = tcf_exts_validate(net, tp, tb, est, &exts, ovr); + ret = tcf_exts_init(&exts, TCA_BPF_ACT, TCA_BPF_POLICE); if (ret < 0) return ret; + ret = tcf_exts_validate(net, tp, tb, est, &exts, ovr); + if (ret < 0) + goto errout; if (tb[TCA_BPF_FLAGS]) { u32 bpf_flags = nla_get_u32(tb[TCA_BPF_FLAGS]); if (bpf_flags & ~TCA_BPF_FLAG_ACT_DIRECT) { - tcf_exts_destroy(&exts); - return -EINVAL; + ret = -EINVAL; + goto errout; } have_exts = bpf_flags & TCA_BPF_FLAG_ACT_DIRECT; @@ -331,10 +333,8 @@ static int cls_bpf_modify_existing(struct net *net, struct tcf_proto *tp, ret = is_bpf ? cls_bpf_prog_from_ops(tb, prog) : cls_bpf_prog_from_efd(tb, prog, tp); - if (ret < 0) { - tcf_exts_destroy(&exts); - return ret; - } + if (ret < 0) + goto errout; if (tb[TCA_BPF_CLASSID]) { prog->res.classid = nla_get_u32(tb[TCA_BPF_CLASSID]); @@ -343,6 +343,10 @@ static int cls_bpf_modify_existing(struct net *net, struct tcf_proto *tp, tcf_exts_change(tp, &prog->exts, &exts); return 0; + +errout: + tcf_exts_destroy(&exts); + return ret; } static u32 cls_bpf_grab_new_handle(struct tcf_proto *tp, @@ -388,7 +392,9 @@ static int cls_bpf_change(struct net *net, struct sk_buff *in_skb, if (!prog) return -ENOBUFS; - tcf_exts_init(&prog->exts, TCA_BPF_ACT, TCA_BPF_POLICE); + ret = tcf_exts_init(&prog->exts, TCA_BPF_ACT, TCA_BPF_POLICE); + if (ret < 0) + goto errout; if (oldprog) { if (handle && oldprog->handle != handle) { @@ -420,9 +426,10 @@ static int cls_bpf_change(struct net *net, struct sk_buff *in_skb, *arg = (unsigned long) prog; return 0; + errout: + tcf_exts_destroy(&prog->exts); kfree(prog); - return ret; } diff --git a/net/sched/cls_cgroup.c b/net/sched/cls_cgroup.c index 4c85bd3a750c..85233c470035 100644 --- a/net/sched/cls_cgroup.c +++ b/net/sched/cls_cgroup.c @@ -93,7 +93,9 @@ static int cls_cgroup_change(struct net *net, struct sk_buff *in_skb, if (!new) return -ENOBUFS; - tcf_exts_init(&new->exts, TCA_CGROUP_ACT, TCA_CGROUP_POLICE); + err = tcf_exts_init(&new->exts, TCA_CGROUP_ACT, TCA_CGROUP_POLICE); + if (err < 0) + goto errout; new->handle = handle; new->tp = tp; err = nla_parse_nested(tb, TCA_CGROUP_MAX, tca[TCA_OPTIONS], @@ -101,10 +103,14 @@ static int cls_cgroup_change(struct net *net, struct sk_buff *in_skb, if (err < 0) goto errout; - tcf_exts_init(&e, TCA_CGROUP_ACT, TCA_CGROUP_POLICE); - err = tcf_exts_validate(net, tp, tb, tca[TCA_RATE], &e, ovr); + err = tcf_exts_init(&e, TCA_CGROUP_ACT, TCA_CGROUP_POLICE); if (err < 0) goto errout; + err = tcf_exts_validate(net, tp, tb, tca[TCA_RATE], &e, ovr); + if (err < 0) { + tcf_exts_destroy(&e); + goto errout; + } err = tcf_em_tree_validate(tp, tb[TCA_CGROUP_EMATCHES], &t); if (err < 0) { @@ -120,6 +126,7 @@ static int cls_cgroup_change(struct net *net, struct sk_buff *in_skb, call_rcu(&head->rcu, cls_cgroup_destroy_rcu); return 0; errout: + tcf_exts_destroy(&new->exts); kfree(new); return err; } diff --git a/net/sched/cls_flow.c b/net/sched/cls_flow.c index fbfec6a18839..2c1ae549edbf 100644 --- a/net/sched/cls_flow.c +++ b/net/sched/cls_flow.c @@ -418,10 +418,12 @@ static int flow_change(struct net *net, struct sk_buff *in_skb, return -EOPNOTSUPP; } - tcf_exts_init(&e, TCA_FLOW_ACT, TCA_FLOW_POLICE); + err = tcf_exts_init(&e, TCA_FLOW_ACT, TCA_FLOW_POLICE); + if (err < 0) + goto err1; err = tcf_exts_validate(net, tp, tb, tca[TCA_RATE], &e, ovr); if (err < 0) - return err; + goto err1; err = tcf_em_tree_validate(tp, tb[TCA_FLOW_EMATCHES], &t); if (err < 0) @@ -432,13 +434,15 @@ static int flow_change(struct net *net, struct sk_buff *in_skb, if (!fnew) goto err2; - tcf_exts_init(&fnew->exts, TCA_FLOW_ACT, TCA_FLOW_POLICE); + err = tcf_exts_init(&fnew->exts, TCA_FLOW_ACT, TCA_FLOW_POLICE); + if (err < 0) + goto err3; fold = (struct flow_filter *)*arg; if (fold) { err = -EINVAL; if (fold->handle != handle && handle) - goto err2; + goto err3; /* Copy fold into fnew */ fnew->tp = fold->tp; @@ -458,31 +462,31 @@ static int flow_change(struct net *net, struct sk_buff *in_skb, if (tb[TCA_FLOW_MODE]) mode = nla_get_u32(tb[TCA_FLOW_MODE]); if (mode != FLOW_MODE_HASH && nkeys > 1) - goto err2; + goto err3; if (mode == FLOW_MODE_HASH) perturb_period = fold->perturb_period; if (tb[TCA_FLOW_PERTURB]) { if (mode != FLOW_MODE_HASH) - goto err2; + goto err3; perturb_period = nla_get_u32(tb[TCA_FLOW_PERTURB]) * HZ; } } else { err = -EINVAL; if (!handle) - goto err2; + goto err3; if (!tb[TCA_FLOW_KEYS]) - goto err2; + goto err3; mode = FLOW_MODE_MAP; if (tb[TCA_FLOW_MODE]) mode = nla_get_u32(tb[TCA_FLOW_MODE]); if (mode != FLOW_MODE_HASH && nkeys > 1) - goto err2; + goto err3; if (tb[TCA_FLOW_PERTURB]) { if (mode != FLOW_MODE_HASH) - goto err2; + goto err3; perturb_period = nla_get_u32(tb[TCA_FLOW_PERTURB]) * HZ; } @@ -542,6 +546,8 @@ static int flow_change(struct net *net, struct sk_buff *in_skb, call_rcu(&fold->rcu, flow_destroy_filter); return 0; +err3: + tcf_exts_destroy(&fnew->exts); err2: tcf_em_tree_destroy(&t); kfree(fnew); diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c index 5060801a2f6d..cf9ad5b50889 100644 --- a/net/sched/cls_flower.c +++ b/net/sched/cls_flower.c @@ -28,6 +28,7 @@ struct fl_flow_key { struct flow_dissector_key_control control; struct flow_dissector_key_basic basic; struct flow_dissector_key_eth_addrs eth; + struct flow_dissector_key_vlan vlan; struct flow_dissector_key_addrs ipaddrs; union { struct flow_dissector_key_ipv4_addrs ipv4; @@ -293,6 +294,10 @@ static const struct nla_policy fl_policy[TCA_FLOWER_MAX + 1] = { [TCA_FLOWER_KEY_TCP_DST] = { .type = NLA_U16 }, [TCA_FLOWER_KEY_UDP_SRC] = { .type = NLA_U16 }, [TCA_FLOWER_KEY_UDP_DST] = { .type = NLA_U16 }, + [TCA_FLOWER_KEY_VLAN_ID] = { .type = NLA_U16 }, + [TCA_FLOWER_KEY_VLAN_PRIO] = { .type = NLA_U8 }, + [TCA_FLOWER_KEY_VLAN_ETH_TYPE] = { .type = NLA_U16 }, + }; static void fl_set_key_val(struct nlattr **tb, @@ -308,9 +313,29 @@ static void fl_set_key_val(struct nlattr **tb, memcpy(mask, nla_data(tb[mask_type]), len); } +static void fl_set_key_vlan(struct nlattr **tb, + struct flow_dissector_key_vlan *key_val, + struct flow_dissector_key_vlan *key_mask) +{ +#define VLAN_PRIORITY_MASK 0x7 + + if (tb[TCA_FLOWER_KEY_VLAN_ID]) { + key_val->vlan_id = + nla_get_u16(tb[TCA_FLOWER_KEY_VLAN_ID]) & VLAN_VID_MASK; + key_mask->vlan_id = VLAN_VID_MASK; + } + if (tb[TCA_FLOWER_KEY_VLAN_PRIO]) { + key_val->vlan_priority = + nla_get_u8(tb[TCA_FLOWER_KEY_VLAN_PRIO]) & + VLAN_PRIORITY_MASK; + key_mask->vlan_priority = VLAN_PRIORITY_MASK; + } +} + static int fl_set_key(struct net *net, struct nlattr **tb, struct fl_flow_key *key, struct fl_flow_key *mask) { + __be16 ethertype; #ifdef CONFIG_NET_CLS_IND if (tb[TCA_FLOWER_INDEV]) { int err = tcf_change_indev(net, tb[TCA_FLOWER_INDEV]); @@ -328,9 +353,20 @@ static int fl_set_key(struct net *net, struct nlattr **tb, mask->eth.src, TCA_FLOWER_KEY_ETH_SRC_MASK, sizeof(key->eth.src)); - fl_set_key_val(tb, &key->basic.n_proto, TCA_FLOWER_KEY_ETH_TYPE, - &mask->basic.n_proto, TCA_FLOWER_UNSPEC, - sizeof(key->basic.n_proto)); + if (tb[TCA_FLOWER_KEY_ETH_TYPE]) { + ethertype = nla_get_be16(tb[TCA_FLOWER_KEY_ETH_TYPE]); + + if (ethertype == htons(ETH_P_8021Q)) { + fl_set_key_vlan(tb, &key->vlan, &mask->vlan); + fl_set_key_val(tb, &key->basic.n_proto, + TCA_FLOWER_KEY_VLAN_ETH_TYPE, + &mask->basic.n_proto, TCA_FLOWER_UNSPEC, + sizeof(key->basic.n_proto)); + } else { + key->basic.n_proto = ethertype; + mask->basic.n_proto = cpu_to_be16(~0); + } + } if (key->basic.n_proto == htons(ETH_P_IP) || key->basic.n_proto == htons(ETH_P_IPV6)) { @@ -404,12 +440,10 @@ static int fl_init_hashtable(struct cls_fl_head *head, #define FL_KEY_MEMBER_OFFSET(member) offsetof(struct fl_flow_key, member) #define FL_KEY_MEMBER_SIZE(member) (sizeof(((struct fl_flow_key *) 0)->member)) -#define FL_KEY_MEMBER_END_OFFSET(member) \ - (FL_KEY_MEMBER_OFFSET(member) + FL_KEY_MEMBER_SIZE(member)) -#define FL_KEY_IN_RANGE(mask, member) \ - (FL_KEY_MEMBER_OFFSET(member) <= (mask)->range.end && \ - FL_KEY_MEMBER_END_OFFSET(member) >= (mask)->range.start) +#define FL_KEY_IS_MASKED(mask, member) \ + memchr_inv(((char *)mask) + FL_KEY_MEMBER_OFFSET(member), \ + 0, FL_KEY_MEMBER_SIZE(member)) \ #define FL_KEY_SET(keys, cnt, id, member) \ do { \ @@ -418,9 +452,9 @@ static int fl_init_hashtable(struct cls_fl_head *head, cnt++; \ } while(0); -#define FL_KEY_SET_IF_IN_RANGE(mask, keys, cnt, id, member) \ +#define FL_KEY_SET_IF_MASKED(mask, keys, cnt, id, member) \ do { \ - if (FL_KEY_IN_RANGE(mask, member)) \ + if (FL_KEY_IS_MASKED(mask, member)) \ FL_KEY_SET(keys, cnt, id, member); \ } while(0); @@ -432,14 +466,16 @@ static void fl_init_dissector(struct cls_fl_head *head, FL_KEY_SET(keys, cnt, FLOW_DISSECTOR_KEY_CONTROL, control); FL_KEY_SET(keys, cnt, FLOW_DISSECTOR_KEY_BASIC, basic); - FL_KEY_SET_IF_IN_RANGE(mask, keys, cnt, - FLOW_DISSECTOR_KEY_ETH_ADDRS, eth); - FL_KEY_SET_IF_IN_RANGE(mask, keys, cnt, - FLOW_DISSECTOR_KEY_IPV4_ADDRS, ipv4); - FL_KEY_SET_IF_IN_RANGE(mask, keys, cnt, - FLOW_DISSECTOR_KEY_IPV6_ADDRS, ipv6); - FL_KEY_SET_IF_IN_RANGE(mask, keys, cnt, - FLOW_DISSECTOR_KEY_PORTS, tp); + FL_KEY_SET_IF_MASKED(&mask->key, keys, cnt, + FLOW_DISSECTOR_KEY_ETH_ADDRS, eth); + FL_KEY_SET_IF_MASKED(&mask->key, keys, cnt, + FLOW_DISSECTOR_KEY_IPV4_ADDRS, ipv4); + FL_KEY_SET_IF_MASKED(&mask->key, keys, cnt, + FLOW_DISSECTOR_KEY_IPV6_ADDRS, ipv6); + FL_KEY_SET_IF_MASKED(&mask->key, keys, cnt, + FLOW_DISSECTOR_KEY_PORTS, tp); + FL_KEY_SET_IF_MASKED(&mask->key, keys, cnt, + FLOW_DISSECTOR_KEY_VLAN, vlan); skb_flow_dissector_init(&head->dissector, keys, cnt); } @@ -478,10 +514,12 @@ static int fl_set_parms(struct net *net, struct tcf_proto *tp, struct tcf_exts e; int err; - tcf_exts_init(&e, TCA_FLOWER_ACT, 0); - err = tcf_exts_validate(net, tp, tb, est, &e, ovr); + err = tcf_exts_init(&e, TCA_FLOWER_ACT, 0); if (err < 0) return err; + err = tcf_exts_validate(net, tp, tb, est, &e, ovr); + if (err < 0) + goto errout; if (tb[TCA_FLOWER_CLASSID]) { f->res.classid = nla_get_u32(tb[TCA_FLOWER_CLASSID]); @@ -550,7 +588,9 @@ static int fl_change(struct net *net, struct sk_buff *in_skb, if (!fnew) return -ENOBUFS; - tcf_exts_init(&fnew->exts, TCA_FLOWER_ACT, 0); + err = tcf_exts_init(&fnew->exts, TCA_FLOWER_ACT, 0); + if (err < 0) + goto errout; if (!handle) { handle = fl_grab_new_handle(tp, head); @@ -614,6 +654,7 @@ static int fl_change(struct net *net, struct sk_buff *in_skb, return 0; errout: + tcf_exts_destroy(&fnew->exts); kfree(fnew); return err; } @@ -668,6 +709,29 @@ static int fl_dump_key_val(struct sk_buff *skb, return 0; } +static int fl_dump_key_vlan(struct sk_buff *skb, + struct flow_dissector_key_vlan *vlan_key, + struct flow_dissector_key_vlan *vlan_mask) +{ + int err; + + if (!memchr_inv(vlan_mask, 0, sizeof(*vlan_mask))) + return 0; + if (vlan_mask->vlan_id) { + err = nla_put_u16(skb, TCA_FLOWER_KEY_VLAN_ID, + vlan_key->vlan_id); + if (err) + return err; + } + if (vlan_mask->vlan_priority) { + err = nla_put_u8(skb, TCA_FLOWER_KEY_VLAN_PRIO, + vlan_key->vlan_priority); + if (err) + return err; + } + return 0; +} + static int fl_dump(struct net *net, struct tcf_proto *tp, unsigned long fh, struct sk_buff *skb, struct tcmsg *t) { @@ -712,6 +776,10 @@ static int fl_dump(struct net *net, struct tcf_proto *tp, unsigned long fh, &mask->basic.n_proto, TCA_FLOWER_UNSPEC, sizeof(key->basic.n_proto))) goto nla_put_failure; + + if (fl_dump_key_vlan(skb, &key->vlan, &mask->vlan)) + goto nla_put_failure; + if ((key->basic.n_proto == htons(ETH_P_IP) || key->basic.n_proto == htons(ETH_P_IPV6)) && fl_dump_key_val(skb, &key->basic.ip_proto, TCA_FLOWER_KEY_IP_PROTO, diff --git a/net/sched/cls_fw.c b/net/sched/cls_fw.c index f23a3b68bba6..cc0bda945800 100644 --- a/net/sched/cls_fw.c +++ b/net/sched/cls_fw.c @@ -195,10 +195,12 @@ fw_change_attrs(struct net *net, struct tcf_proto *tp, struct fw_filter *f, u32 mask; int err; - tcf_exts_init(&e, TCA_FW_ACT, TCA_FW_POLICE); - err = tcf_exts_validate(net, tp, tb, tca[TCA_RATE], &e, ovr); + err = tcf_exts_init(&e, TCA_FW_ACT, TCA_FW_POLICE); if (err < 0) return err; + err = tcf_exts_validate(net, tp, tb, tca[TCA_RATE], &e, ovr); + if (err < 0) + goto errout; if (tb[TCA_FW_CLASSID]) { f->res.classid = nla_get_u32(tb[TCA_FW_CLASSID]); @@ -270,10 +272,15 @@ static int fw_change(struct net *net, struct sk_buff *in_skb, #endif /* CONFIG_NET_CLS_IND */ fnew->tp = f->tp; - tcf_exts_init(&fnew->exts, TCA_FW_ACT, TCA_FW_POLICE); + err = tcf_exts_init(&fnew->exts, TCA_FW_ACT, TCA_FW_POLICE); + if (err < 0) { + kfree(fnew); + return err; + } err = fw_change_attrs(net, tp, fnew, tb, tca, base, ovr); if (err < 0) { + tcf_exts_destroy(&fnew->exts); kfree(fnew); return err; } @@ -313,7 +320,9 @@ static int fw_change(struct net *net, struct sk_buff *in_skb, if (f == NULL) return -ENOBUFS; - tcf_exts_init(&f->exts, TCA_FW_ACT, TCA_FW_POLICE); + err = tcf_exts_init(&f->exts, TCA_FW_ACT, TCA_FW_POLICE); + if (err < 0) + goto errout; f->id = handle; f->tp = tp; @@ -328,6 +337,7 @@ static int fw_change(struct net *net, struct sk_buff *in_skb, return 0; errout: + tcf_exts_destroy(&f->exts); kfree(f); return err; } diff --git a/net/sched/cls_route.c b/net/sched/cls_route.c index 08a3b0a6f5ab..c91e65d81a48 100644 --- a/net/sched/cls_route.c +++ b/net/sched/cls_route.c @@ -383,17 +383,19 @@ static int route4_set_parms(struct net *net, struct tcf_proto *tp, struct nlattr **tb, struct nlattr *est, int new, bool ovr) { - int err; u32 id = 0, to = 0, nhandle = 0x8000; struct route4_filter *fp; unsigned int h1; struct route4_bucket *b; struct tcf_exts e; + int err; - tcf_exts_init(&e, TCA_ROUTE4_ACT, TCA_ROUTE4_POLICE); - err = tcf_exts_validate(net, tp, tb, est, &e, ovr); + err = tcf_exts_init(&e, TCA_ROUTE4_ACT, TCA_ROUTE4_POLICE); if (err < 0) return err; + err = tcf_exts_validate(net, tp, tb, est, &e, ovr); + if (err < 0) + goto errout; err = -EINVAL; if (tb[TCA_ROUTE4_TO]) { @@ -503,7 +505,10 @@ static int route4_change(struct net *net, struct sk_buff *in_skb, if (!f) goto errout; - tcf_exts_init(&f->exts, TCA_ROUTE4_ACT, TCA_ROUTE4_POLICE); + err = tcf_exts_init(&f->exts, TCA_ROUTE4_ACT, TCA_ROUTE4_POLICE); + if (err < 0) + goto errout; + if (fold) { f->id = fold->id; f->iif = fold->iif; @@ -557,6 +562,7 @@ static int route4_change(struct net *net, struct sk_buff *in_skb, return 0; errout: + tcf_exts_destroy(&f->exts); kfree(f); return err; } diff --git a/net/sched/cls_rsvp.h b/net/sched/cls_rsvp.h index f9c9fc075fe6..4f05a19fb073 100644 --- a/net/sched/cls_rsvp.h +++ b/net/sched/cls_rsvp.h @@ -487,10 +487,12 @@ static int rsvp_change(struct net *net, struct sk_buff *in_skb, if (err < 0) return err; - tcf_exts_init(&e, TCA_RSVP_ACT, TCA_RSVP_POLICE); - err = tcf_exts_validate(net, tp, tb, tca[TCA_RATE], &e, ovr); + err = tcf_exts_init(&e, TCA_RSVP_ACT, TCA_RSVP_POLICE); if (err < 0) return err; + err = tcf_exts_validate(net, tp, tb, tca[TCA_RATE], &e, ovr); + if (err < 0) + goto errout2; f = (struct rsvp_filter *)*arg; if (f) { @@ -506,7 +508,11 @@ static int rsvp_change(struct net *net, struct sk_buff *in_skb, goto errout2; } - tcf_exts_init(&n->exts, TCA_RSVP_ACT, TCA_RSVP_POLICE); + err = tcf_exts_init(&n->exts, TCA_RSVP_ACT, TCA_RSVP_POLICE); + if (err < 0) { + kfree(n); + goto errout2; + } if (tb[TCA_RSVP_CLASSID]) { n->res.classid = nla_get_u32(tb[TCA_RSVP_CLASSID]); @@ -530,7 +536,9 @@ static int rsvp_change(struct net *net, struct sk_buff *in_skb, if (f == NULL) goto errout2; - tcf_exts_init(&f->exts, TCA_RSVP_ACT, TCA_RSVP_POLICE); + err = tcf_exts_init(&f->exts, TCA_RSVP_ACT, TCA_RSVP_POLICE); + if (err < 0) + goto errout; h2 = 16; if (tb[TCA_RSVP_SRC]) { memcpy(f->src, nla_data(tb[TCA_RSVP_SRC]), sizeof(f->src)); @@ -627,6 +635,7 @@ insert: goto insert; errout: + tcf_exts_destroy(&f->exts); kfree(f); errout2: tcf_exts_destroy(&e); diff --git a/net/sched/cls_tcindex.c b/net/sched/cls_tcindex.c index 944c8ff45055..d9500709831f 100644 --- a/net/sched/cls_tcindex.c +++ b/net/sched/cls_tcindex.c @@ -219,10 +219,10 @@ static const struct nla_policy tcindex_policy[TCA_TCINDEX_MAX + 1] = { [TCA_TCINDEX_CLASSID] = { .type = NLA_U32 }, }; -static void tcindex_filter_result_init(struct tcindex_filter_result *r) +static int tcindex_filter_result_init(struct tcindex_filter_result *r) { memset(r, 0, sizeof(*r)); - tcf_exts_init(&r->exts, TCA_TCINDEX_ACT, TCA_TCINDEX_POLICE); + return tcf_exts_init(&r->exts, TCA_TCINDEX_ACT, TCA_TCINDEX_POLICE); } static void __tcindex_partial_destroy(struct rcu_head *head) @@ -233,23 +233,57 @@ static void __tcindex_partial_destroy(struct rcu_head *head) kfree(p); } +static void tcindex_free_perfect_hash(struct tcindex_data *cp) +{ + int i; + + for (i = 0; i < cp->hash; i++) + tcf_exts_destroy(&cp->perfect[i].exts); + kfree(cp->perfect); +} + +static int tcindex_alloc_perfect_hash(struct tcindex_data *cp) +{ + int i, err = 0; + + cp->perfect = kcalloc(cp->hash, sizeof(struct tcindex_filter_result), + GFP_KERNEL); + if (!cp->perfect) + return -ENOMEM; + + for (i = 0; i < cp->hash; i++) { + err = tcf_exts_init(&cp->perfect[i].exts, + TCA_TCINDEX_ACT, TCA_TCINDEX_POLICE); + if (err < 0) + goto errout; + } + + return 0; + +errout: + tcindex_free_perfect_hash(cp); + return err; +} + static int tcindex_set_parms(struct net *net, struct tcf_proto *tp, unsigned long base, u32 handle, struct tcindex_data *p, struct tcindex_filter_result *r, struct nlattr **tb, struct nlattr *est, bool ovr) { - int err, balloc = 0; struct tcindex_filter_result new_filter_result, *old_r = r; struct tcindex_filter_result cr; - struct tcindex_data *cp, *oldp; + struct tcindex_data *cp = NULL, *oldp; struct tcindex_filter *f = NULL; /* make gcc behave */ + int err, balloc = 0; struct tcf_exts e; - tcf_exts_init(&e, TCA_TCINDEX_ACT, TCA_TCINDEX_POLICE); - err = tcf_exts_validate(net, tp, tb, est, &e, ovr); + err = tcf_exts_init(&e, TCA_TCINDEX_ACT, TCA_TCINDEX_POLICE); if (err < 0) return err; + err = tcf_exts_validate(net, tp, tb, est, &e, ovr); + if (err < 0) + goto errout; err = -ENOMEM; /* tcindex_data attributes must look atomic to classifier/lookup so @@ -270,19 +304,20 @@ tcindex_set_parms(struct net *net, struct tcf_proto *tp, unsigned long base, if (p->perfect) { int i; - cp->perfect = kmemdup(p->perfect, - sizeof(*r) * cp->hash, GFP_KERNEL); - if (!cp->perfect) + if (tcindex_alloc_perfect_hash(cp) < 0) goto errout; for (i = 0; i < cp->hash; i++) - tcf_exts_init(&cp->perfect[i].exts, - TCA_TCINDEX_ACT, TCA_TCINDEX_POLICE); + cp->perfect[i].res = p->perfect[i].res; balloc = 1; } cp->h = p->h; - tcindex_filter_result_init(&new_filter_result); - tcindex_filter_result_init(&cr); + err = tcindex_filter_result_init(&new_filter_result); + if (err < 0) + goto errout1; + err = tcindex_filter_result_init(&cr); + if (err < 0) + goto errout1; if (old_r) cr.res = r->res; @@ -338,15 +373,8 @@ tcindex_set_parms(struct net *net, struct tcf_proto *tp, unsigned long base, err = -ENOMEM; if (!cp->perfect && !cp->h) { if (valid_perfect_hash(cp)) { - int i; - - cp->perfect = kcalloc(cp->hash, sizeof(*r), GFP_KERNEL); - if (!cp->perfect) + if (tcindex_alloc_perfect_hash(cp) < 0) goto errout_alloc; - for (i = 0; i < cp->hash; i++) - tcf_exts_init(&cp->perfect[i].exts, - TCA_TCINDEX_ACT, - TCA_TCINDEX_POLICE); balloc = 1; } else { struct tcindex_filter __rcu **hash; @@ -373,8 +401,12 @@ tcindex_set_parms(struct net *net, struct tcf_proto *tp, unsigned long base, if (!f) goto errout_alloc; f->key = handle; - tcindex_filter_result_init(&f->result); f->next = NULL; + err = tcindex_filter_result_init(&f->result); + if (err < 0) { + kfree(f); + goto errout_alloc; + } } if (tb[TCA_TCINDEX_CLASSID]) { @@ -387,8 +419,13 @@ tcindex_set_parms(struct net *net, struct tcf_proto *tp, unsigned long base, else tcf_exts_change(tp, &cr.exts, &e); - if (old_r && old_r != r) - tcindex_filter_result_init(old_r); + if (old_r && old_r != r) { + err = tcindex_filter_result_init(old_r); + if (err < 0) { + kfree(f); + goto errout_alloc; + } + } oldp = p; r->res = cr.res; @@ -415,9 +452,12 @@ tcindex_set_parms(struct net *net, struct tcf_proto *tp, unsigned long base, errout_alloc: if (balloc == 1) - kfree(cp->perfect); + tcindex_free_perfect_hash(cp); else if (balloc == 2) kfree(cp->h); +errout1: + tcf_exts_destroy(&cr.exts); + tcf_exts_destroy(&new_filter_result.exts); errout: kfree(cp); tcf_exts_destroy(&e); diff --git a/net/sched/cls_u32.c b/net/sched/cls_u32.c index ffe593efe930..a29263a9d8c1 100644 --- a/net/sched/cls_u32.c +++ b/net/sched/cls_u32.c @@ -709,13 +709,15 @@ static int u32_set_parms(struct net *net, struct tcf_proto *tp, struct tc_u_knode *n, struct nlattr **tb, struct nlattr *est, bool ovr) { - int err; struct tcf_exts e; + int err; - tcf_exts_init(&e, TCA_U32_ACT, TCA_U32_POLICE); - err = tcf_exts_validate(net, tp, tb, est, &e, ovr); + err = tcf_exts_init(&e, TCA_U32_ACT, TCA_U32_POLICE); if (err < 0) return err; + err = tcf_exts_validate(net, tp, tb, est, &e, ovr); + if (err < 0) + goto errout; err = -EINVAL; if (tb[TCA_U32_LINK]) { @@ -833,7 +835,10 @@ static struct tc_u_knode *u32_init_knode(struct tcf_proto *tp, new->tp = tp; memcpy(&new->sel, s, sizeof(*s) + s->nkeys*sizeof(struct tc_u32_key)); - tcf_exts_init(&new->exts, TCA_U32_ACT, TCA_U32_POLICE); + if (tcf_exts_init(&new->exts, TCA_U32_ACT, TCA_U32_POLICE)) { + kfree(new); + return NULL; + } return new; } @@ -985,9 +990,12 @@ static int u32_change(struct net *net, struct sk_buff *in_skb, n->handle = handle; n->fshift = s->hmask ? ffs(ntohl(s->hmask)) - 1 : 0; n->flags = flags; - tcf_exts_init(&n->exts, TCA_U32_ACT, TCA_U32_POLICE); n->tp = tp; + err = tcf_exts_init(&n->exts, TCA_U32_ACT, TCA_U32_POLICE); + if (err < 0) + goto errout; + #ifdef CONFIG_CLS_U32_MARK n->pcpu_success = alloc_percpu(u32); if (!n->pcpu_success) { @@ -1028,9 +1036,10 @@ static int u32_change(struct net *net, struct sk_buff *in_skb, errhw: #ifdef CONFIG_CLS_U32_MARK free_percpu(n->pcpu_success); -errout: #endif +errout: + tcf_exts_destroy(&n->exts); #ifdef CONFIG_CLS_U32_PERF free_percpu(n->pf); #endif diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c index 25aada7b095c..d677b3484d81 100644 --- a/net/sched/sch_api.c +++ b/net/sched/sch_api.c @@ -260,6 +260,9 @@ static struct Qdisc *qdisc_match_from_root(struct Qdisc *root, u32 handle) { struct Qdisc *q; + if (!qdisc_dev(root)) + return (root->handle == handle ? root : NULL); + if (!(root->flags & TCQ_F_BUILTIN) && root->handle == handle) return root; @@ -1432,7 +1435,7 @@ err_out: static int tc_dump_qdisc_root(struct Qdisc *root, struct sk_buff *skb, struct netlink_callback *cb, - int *q_idx_p, int s_q_idx) + int *q_idx_p, int s_q_idx, bool recur) { int ret = 0, q_idx = *q_idx_p; struct Qdisc *q; @@ -1451,6 +1454,16 @@ static int tc_dump_qdisc_root(struct Qdisc *root, struct sk_buff *skb, goto done; q_idx++; } + + /* If dumping singletons, there is no qdisc_dev(root) and the singleton + * itself has already been dumped. + * + * If we've already dumped the top-level (ingress) qdisc above and the global + * qdisc hashtable, we don't want to hit it again + */ + if (!qdisc_dev(root) || !recur) + goto out; + hash_for_each(qdisc_dev(root)->qdisc_hash, b, q, hash) { if (q_idx < s_q_idx) { q_idx++; @@ -1492,13 +1505,13 @@ static int tc_dump_qdisc(struct sk_buff *skb, struct netlink_callback *cb) s_q_idx = 0; q_idx = 0; - if (tc_dump_qdisc_root(dev->qdisc, skb, cb, &q_idx, s_q_idx) < 0) + if (tc_dump_qdisc_root(dev->qdisc, skb, cb, &q_idx, s_q_idx, true) < 0) goto done; dev_queue = dev_ingress_queue(dev); if (dev_queue && tc_dump_qdisc_root(dev_queue->qdisc_sleeping, skb, cb, - &q_idx, s_q_idx) < 0) + &q_idx, s_q_idx, false) < 0) goto done; cont: @@ -1775,6 +1788,9 @@ static int tc_dump_tclass_root(struct Qdisc *root, struct sk_buff *skb, if (tc_dump_tclass_qdisc(root, skb, tcm, cb, t_p, s_t) < 0) return -1; + if (!qdisc_dev(root)) + return 0; + hash_for_each(qdisc_dev(root)->qdisc_hash, b, q, hash) { if (tc_dump_tclass_qdisc(q, skb, tcm, cb, t_p, s_t) < 0) return -1; diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c index 18faecc3f13e..0d21b567ff27 100644 --- a/net/sched/sch_generic.c +++ b/net/sched/sch_generic.c @@ -641,18 +641,19 @@ struct Qdisc *qdisc_create_dflt(struct netdev_queue *dev_queue, struct Qdisc *sch; if (!try_module_get(ops->owner)) - goto errout; + return NULL; sch = qdisc_alloc(dev_queue, ops); - if (IS_ERR(sch)) - goto errout; + if (IS_ERR(sch)) { + module_put(ops->owner); + return NULL; + } sch->parent = parentid; if (!ops->init || ops->init(sch, NULL) == 0) return sch; qdisc_destroy(sch); -errout: return NULL; } EXPORT_SYMBOL(qdisc_create_dflt); diff --git a/net/sctp/input.c b/net/sctp/input.c index c182db7d691f..69444d32ecda 100644 --- a/net/sctp/input.c +++ b/net/sctp/input.c @@ -119,7 +119,13 @@ int sctp_rcv(struct sk_buff *skb) skb_transport_offset(skb)) goto discard_it; - if (!pskb_may_pull(skb, sizeof(struct sctphdr))) + /* If the packet is fragmented and we need to do crc checking, + * it's better to just linearize it otherwise crc computing + * takes longer. + */ + if ((!(skb_shinfo(skb)->gso_type & SKB_GSO_SCTP) && + skb_linearize(skb)) || + !pskb_may_pull(skb, sizeof(struct sctphdr))) goto discard_it; /* Pull up the IP header. */ @@ -1177,9 +1183,6 @@ static struct sctp_association *__sctp_rcv_lookup_harder(struct net *net, if ((skb_shinfo(skb)->gso_type & SKB_GSO_SCTP) == SKB_GSO_SCTP) return NULL; - if (skb_linearize(skb)) - return NULL; - ch = (sctp_chunkhdr_t *) skb->data; /* The code below will attempt to walk the chunk and extract diff --git a/net/sctp/inqueue.c b/net/sctp/inqueue.c index c30ddb0f3190..6437aa97cfd7 100644 --- a/net/sctp/inqueue.c +++ b/net/sctp/inqueue.c @@ -170,19 +170,6 @@ next_chunk: chunk = list_entry(entry, struct sctp_chunk, list); - /* Linearize if it's not GSO */ - if ((skb_shinfo(chunk->skb)->gso_type & SKB_GSO_SCTP) != SKB_GSO_SCTP && - skb_is_nonlinear(chunk->skb)) { - if (skb_linearize(chunk->skb)) { - __SCTP_INC_STATS(dev_net(chunk->skb->dev), SCTP_MIB_IN_PKT_DISCARDS); - sctp_chunk_free(chunk); - goto next_chunk; - } - - /* Update sctp_hdr as it probably changed */ - chunk->sctp_hdr = sctp_hdr(chunk->skb); - } - if ((skb_shinfo(chunk->skb)->gso_type & SKB_GSO_SCTP) == SKB_GSO_SCTP) { /* GSO-marked skbs but without frags, handle * them normally diff --git a/net/sctp/proc.c b/net/sctp/proc.c index 4cb5aedfe3ee..ef8ba77a5bea 100644 --- a/net/sctp/proc.c +++ b/net/sctp/proc.c @@ -293,6 +293,7 @@ static void *sctp_transport_seq_start(struct seq_file *seq, loff_t *pos) return ERR_PTR(err); } + iter->start_fail = 0; return sctp_transport_get_idx(seq_file_net(seq), &iter->hti, *pos); } diff --git a/net/sctp/sctp_diag.c b/net/sctp/sctp_diag.c index bb691538adc8..f3508aa75815 100644 --- a/net/sctp/sctp_diag.c +++ b/net/sctp/sctp_diag.c @@ -424,11 +424,13 @@ static int sctp_diag_dump_one(struct sk_buff *in_skb, paddr.v4.sin_family = AF_INET; } else { laddr.v6.sin6_port = req->id.idiag_sport; - memcpy(&laddr.v6.sin6_addr, req->id.idiag_src, 64); + memcpy(&laddr.v6.sin6_addr, req->id.idiag_src, + sizeof(laddr.v6.sin6_addr)); laddr.v6.sin6_family = AF_INET6; paddr.v6.sin6_port = req->id.idiag_dport; - memcpy(&paddr.v6.sin6_addr, req->id.idiag_dst, 64); + memcpy(&paddr.v6.sin6_addr, req->id.idiag_dst, + sizeof(paddr.v6.sin6_addr)); paddr.v6.sin6_family = AF_INET6; } diff --git a/net/strparser/Kconfig b/net/strparser/Kconfig new file mode 100644 index 000000000000..6cff3f6d0c3a --- /dev/null +++ b/net/strparser/Kconfig @@ -0,0 +1,4 @@ + +config STREAM_PARSER + tristate + default n diff --git a/net/strparser/Makefile b/net/strparser/Makefile new file mode 100644 index 000000000000..858a126ebaa0 --- /dev/null +++ b/net/strparser/Makefile @@ -0,0 +1 @@ +obj-$(CONFIG_STREAM_PARSER) += strparser.o diff --git a/net/strparser/strparser.c b/net/strparser/strparser.c new file mode 100644 index 000000000000..5c7549b5b92c --- /dev/null +++ b/net/strparser/strparser.c @@ -0,0 +1,510 @@ +/* + * Stream Parser + * + * Copyright (c) 2016 Tom Herbert <tom@herbertland.com> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 + * as published by the Free Software Foundation. + */ + +#include <linux/bpf.h> +#include <linux/errno.h> +#include <linux/errqueue.h> +#include <linux/file.h> +#include <linux/in.h> +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/net.h> +#include <linux/netdevice.h> +#include <linux/poll.h> +#include <linux/rculist.h> +#include <linux/skbuff.h> +#include <linux/socket.h> +#include <linux/uaccess.h> +#include <linux/workqueue.h> +#include <net/strparser.h> +#include <net/netns/generic.h> +#include <net/sock.h> + +static struct workqueue_struct *strp_wq; + +struct _strp_rx_msg { + /* Internal cb structure. struct strp_rx_msg must be first for passing + * to upper layer. + */ + struct strp_rx_msg strp; + int accum_len; + int early_eaten; +}; + +static inline struct _strp_rx_msg *_strp_rx_msg(struct sk_buff *skb) +{ + return (struct _strp_rx_msg *)((void *)skb->cb + + offsetof(struct qdisc_skb_cb, data)); +} + +/* Lower lock held */ +static void strp_abort_rx_strp(struct strparser *strp, int err) +{ + struct sock *csk = strp->sk; + + /* Unrecoverable error in receive */ + + del_timer(&strp->rx_msg_timer); + + if (strp->rx_stopped) + return; + + strp->rx_stopped = 1; + + /* Report an error on the lower socket */ + csk->sk_err = err; + csk->sk_error_report(csk); +} + +static void strp_start_rx_timer(struct strparser *strp) +{ + if (strp->sk->sk_rcvtimeo) + mod_timer(&strp->rx_msg_timer, strp->sk->sk_rcvtimeo); +} + +/* Lower lock held */ +static void strp_parser_err(struct strparser *strp, int err, + read_descriptor_t *desc) +{ + desc->error = err; + kfree_skb(strp->rx_skb_head); + strp->rx_skb_head = NULL; + strp->cb.abort_parser(strp, err); +} + +static inline int strp_peek_len(struct strparser *strp) +{ + struct socket *sock = strp->sk->sk_socket; + + return sock->ops->peek_len(sock); +} + +/* Lower socket lock held */ +static int strp_recv(read_descriptor_t *desc, struct sk_buff *orig_skb, + unsigned int orig_offset, size_t orig_len) +{ + struct strparser *strp = (struct strparser *)desc->arg.data; + struct _strp_rx_msg *rxm; + struct sk_buff *head, *skb; + size_t eaten = 0, cand_len; + ssize_t extra; + int err; + bool cloned_orig = false; + + if (strp->rx_paused) + return 0; + + head = strp->rx_skb_head; + if (head) { + /* Message already in progress */ + + rxm = _strp_rx_msg(head); + if (unlikely(rxm->early_eaten)) { + /* Already some number of bytes on the receive sock + * data saved in rx_skb_head, just indicate they + * are consumed. + */ + eaten = orig_len <= rxm->early_eaten ? + orig_len : rxm->early_eaten; + rxm->early_eaten -= eaten; + + return eaten; + } + + if (unlikely(orig_offset)) { + /* Getting data with a non-zero offset when a message is + * in progress is not expected. If it does happen, we + * need to clone and pull since we can't deal with + * offsets in the skbs for a message expect in the head. + */ + orig_skb = skb_clone(orig_skb, GFP_ATOMIC); + if (!orig_skb) { + STRP_STATS_INCR(strp->stats.rx_mem_fail); + desc->error = -ENOMEM; + return 0; + } + if (!pskb_pull(orig_skb, orig_offset)) { + STRP_STATS_INCR(strp->stats.rx_mem_fail); + kfree_skb(orig_skb); + desc->error = -ENOMEM; + return 0; + } + cloned_orig = true; + orig_offset = 0; + } + + if (!strp->rx_skb_nextp) { + /* We are going to append to the frags_list of head. + * Need to unshare the frag_list. + */ + err = skb_unclone(head, GFP_ATOMIC); + if (err) { + STRP_STATS_INCR(strp->stats.rx_mem_fail); + desc->error = err; + return 0; + } + + if (unlikely(skb_shinfo(head)->frag_list)) { + /* We can't append to an sk_buff that already + * has a frag_list. We create a new head, point + * the frag_list of that to the old head, and + * then are able to use the old head->next for + * appending to the message. + */ + if (WARN_ON(head->next)) { + desc->error = -EINVAL; + return 0; + } + + skb = alloc_skb(0, GFP_ATOMIC); + if (!skb) { + STRP_STATS_INCR(strp->stats.rx_mem_fail); + desc->error = -ENOMEM; + return 0; + } + skb->len = head->len; + skb->data_len = head->len; + skb->truesize = head->truesize; + *_strp_rx_msg(skb) = *_strp_rx_msg(head); + strp->rx_skb_nextp = &head->next; + skb_shinfo(skb)->frag_list = head; + strp->rx_skb_head = skb; + head = skb; + } else { + strp->rx_skb_nextp = + &skb_shinfo(head)->frag_list; + } + } + } + + while (eaten < orig_len) { + /* Always clone since we will consume something */ + skb = skb_clone(orig_skb, GFP_ATOMIC); + if (!skb) { + STRP_STATS_INCR(strp->stats.rx_mem_fail); + desc->error = -ENOMEM; + break; + } + + cand_len = orig_len - eaten; + + head = strp->rx_skb_head; + if (!head) { + head = skb; + strp->rx_skb_head = head; + /* Will set rx_skb_nextp on next packet if needed */ + strp->rx_skb_nextp = NULL; + rxm = _strp_rx_msg(head); + memset(rxm, 0, sizeof(*rxm)); + rxm->strp.offset = orig_offset + eaten; + } else { + /* Unclone since we may be appending to an skb that we + * already share a frag_list with. + */ + err = skb_unclone(skb, GFP_ATOMIC); + if (err) { + STRP_STATS_INCR(strp->stats.rx_mem_fail); + desc->error = err; + break; + } + + rxm = _strp_rx_msg(head); + *strp->rx_skb_nextp = skb; + strp->rx_skb_nextp = &skb->next; + head->data_len += skb->len; + head->len += skb->len; + head->truesize += skb->truesize; + } + + if (!rxm->strp.full_len) { + ssize_t len; + + len = (*strp->cb.parse_msg)(strp, head); + + if (!len) { + /* Need more header to determine length */ + if (!rxm->accum_len) { + /* Start RX timer for new message */ + strp_start_rx_timer(strp); + } + rxm->accum_len += cand_len; + eaten += cand_len; + STRP_STATS_INCR(strp->stats.rx_need_more_hdr); + WARN_ON(eaten != orig_len); + break; + } else if (len < 0) { + if (len == -ESTRPIPE && rxm->accum_len) { + len = -ENODATA; + strp->rx_unrecov_intr = 1; + } else { + strp->rx_interrupted = 1; + } + strp_parser_err(strp, err, desc); + break; + } else if (len > strp->sk->sk_rcvbuf) { + /* Message length exceeds maximum allowed */ + STRP_STATS_INCR(strp->stats.rx_msg_too_big); + strp_parser_err(strp, -EMSGSIZE, desc); + break; + } else if (len <= (ssize_t)head->len - + skb->len - rxm->strp.offset) { + /* Length must be into new skb (and also + * greater than zero) + */ + STRP_STATS_INCR(strp->stats.rx_bad_hdr_len); + strp_parser_err(strp, -EPROTO, desc); + break; + } + + rxm->strp.full_len = len; + } + + extra = (ssize_t)(rxm->accum_len + cand_len) - + rxm->strp.full_len; + + if (extra < 0) { + /* Message not complete yet. */ + if (rxm->strp.full_len - rxm->accum_len > + strp_peek_len(strp)) { + /* Don't have the whole messages in the socket + * buffer. Set strp->rx_need_bytes to wait for + * the rest of the message. Also, set "early + * eaten" since we've already buffered the skb + * but don't consume yet per strp_read_sock. + */ + + if (!rxm->accum_len) { + /* Start RX timer for new message */ + strp_start_rx_timer(strp); + } + + strp->rx_need_bytes = rxm->strp.full_len - + rxm->accum_len; + rxm->accum_len += cand_len; + rxm->early_eaten = cand_len; + STRP_STATS_ADD(strp->stats.rx_bytes, cand_len); + desc->count = 0; /* Stop reading socket */ + break; + } + rxm->accum_len += cand_len; + eaten += cand_len; + WARN_ON(eaten != orig_len); + break; + } + + /* Positive extra indicates ore bytes than needed for the + * message + */ + + WARN_ON(extra > cand_len); + + eaten += (cand_len - extra); + + /* Hurray, we have a new message! */ + del_timer(&strp->rx_msg_timer); + strp->rx_skb_head = NULL; + STRP_STATS_INCR(strp->stats.rx_msgs); + + /* Give skb to upper layer */ + strp->cb.rcv_msg(strp, head); + + if (unlikely(strp->rx_paused)) { + /* Upper layer paused strp */ + break; + } + } + + if (cloned_orig) + kfree_skb(orig_skb); + + STRP_STATS_ADD(strp->stats.rx_bytes, eaten); + + return eaten; +} + +static int default_read_sock_done(struct strparser *strp, int err) +{ + return err; +} + +/* Called with lock held on lower socket */ +static int strp_read_sock(struct strparser *strp) +{ + struct socket *sock = strp->sk->sk_socket; + read_descriptor_t desc; + + desc.arg.data = strp; + desc.error = 0; + desc.count = 1; /* give more than one skb per call */ + + /* sk should be locked here, so okay to do read_sock */ + sock->ops->read_sock(strp->sk, &desc, strp_recv); + + desc.error = strp->cb.read_sock_done(strp, desc.error); + + return desc.error; +} + +/* Lower sock lock held */ +void strp_data_ready(struct strparser *strp) +{ + if (unlikely(strp->rx_stopped)) + return; + + /* This check is needed to synchronize with do_strp_rx_work. + * do_strp_rx_work acquires a process lock (lock_sock) whereas + * the lock held here is bh_lock_sock. The two locks can be + * held by different threads at the same time, but bh_lock_sock + * allows a thread in BH context to safely check if the process + * lock is held. In this case, if the lock is held, queue work. + */ + if (sock_owned_by_user(strp->sk)) { + queue_work(strp_wq, &strp->rx_work); + return; + } + + if (strp->rx_paused) + return; + + if (strp->rx_need_bytes) { + if (strp_peek_len(strp) >= strp->rx_need_bytes) + strp->rx_need_bytes = 0; + else + return; + } + + if (strp_read_sock(strp) == -ENOMEM) + queue_work(strp_wq, &strp->rx_work); +} +EXPORT_SYMBOL_GPL(strp_data_ready); + +static void do_strp_rx_work(struct strparser *strp) +{ + read_descriptor_t rd_desc; + struct sock *csk = strp->sk; + + /* We need the read lock to synchronize with strp_data_ready. We + * need the socket lock for calling strp_read_sock. + */ + lock_sock(csk); + + if (unlikely(strp->rx_stopped)) + goto out; + + if (strp->rx_paused) + goto out; + + rd_desc.arg.data = strp; + + if (strp_read_sock(strp) == -ENOMEM) + queue_work(strp_wq, &strp->rx_work); + +out: + release_sock(csk); +} + +static void strp_rx_work(struct work_struct *w) +{ + do_strp_rx_work(container_of(w, struct strparser, rx_work)); +} + +static void strp_rx_msg_timeout(unsigned long arg) +{ + struct strparser *strp = (struct strparser *)arg; + + /* Message assembly timed out */ + STRP_STATS_INCR(strp->stats.rx_msg_timeouts); + lock_sock(strp->sk); + strp->cb.abort_parser(strp, ETIMEDOUT); + release_sock(strp->sk); +} + +int strp_init(struct strparser *strp, struct sock *csk, + struct strp_callbacks *cb) +{ + struct socket *sock = csk->sk_socket; + + if (!cb || !cb->rcv_msg || !cb->parse_msg) + return -EINVAL; + + if (!sock->ops->read_sock || !sock->ops->peek_len) + return -EAFNOSUPPORT; + + memset(strp, 0, sizeof(*strp)); + + strp->sk = csk; + + setup_timer(&strp->rx_msg_timer, strp_rx_msg_timeout, + (unsigned long)strp); + + INIT_WORK(&strp->rx_work, strp_rx_work); + + strp->cb.rcv_msg = cb->rcv_msg; + strp->cb.parse_msg = cb->parse_msg; + strp->cb.read_sock_done = cb->read_sock_done ? : default_read_sock_done; + strp->cb.abort_parser = cb->abort_parser ? : strp_abort_rx_strp; + + return 0; +} +EXPORT_SYMBOL_GPL(strp_init); + +void strp_unpause(struct strparser *strp) +{ + strp->rx_paused = 0; + + /* Sync setting rx_paused with RX work */ + smp_mb(); + + queue_work(strp_wq, &strp->rx_work); +} +EXPORT_SYMBOL_GPL(strp_unpause); + +/* strp must already be stopped so that strp_recv will no longer be called. + * Note that strp_done is not called with the lower socket held. + */ +void strp_done(struct strparser *strp) +{ + WARN_ON(!strp->rx_stopped); + + del_timer_sync(&strp->rx_msg_timer); + cancel_work_sync(&strp->rx_work); + + if (strp->rx_skb_head) { + kfree_skb(strp->rx_skb_head); + strp->rx_skb_head = NULL; + } +} +EXPORT_SYMBOL_GPL(strp_done); + +void strp_stop(struct strparser *strp) +{ + strp->rx_stopped = 1; +} +EXPORT_SYMBOL_GPL(strp_stop); + +void strp_check_rcv(struct strparser *strp) +{ + queue_work(strp_wq, &strp->rx_work); +} +EXPORT_SYMBOL_GPL(strp_check_rcv); + +static int __init strp_mod_init(void) +{ + strp_wq = create_singlethread_workqueue("kstrp"); + + return 0; +} + +static void __exit strp_mod_exit(void) +{ +} +module_init(strp_mod_init); +module_exit(strp_mod_exit); +MODULE_LICENSE("GPL"); diff --git a/net/sunrpc/auth_gss/auth_gss.c b/net/sunrpc/auth_gss/auth_gss.c index 23c8e7c39656..976c7812bbd5 100644 --- a/net/sunrpc/auth_gss/auth_gss.c +++ b/net/sunrpc/auth_gss/auth_gss.c @@ -340,12 +340,14 @@ gss_release_msg(struct gss_upcall_msg *gss_msg) } static struct gss_upcall_msg * -__gss_find_upcall(struct rpc_pipe *pipe, kuid_t uid) +__gss_find_upcall(struct rpc_pipe *pipe, kuid_t uid, const struct gss_auth *auth) { struct gss_upcall_msg *pos; list_for_each_entry(pos, &pipe->in_downcall, list) { if (!uid_eq(pos->uid, uid)) continue; + if (auth && pos->auth->service != auth->service) + continue; atomic_inc(&pos->count); dprintk("RPC: %s found msg %p\n", __func__, pos); return pos; @@ -365,7 +367,7 @@ gss_add_msg(struct gss_upcall_msg *gss_msg) struct gss_upcall_msg *old; spin_lock(&pipe->lock); - old = __gss_find_upcall(pipe, gss_msg->uid); + old = __gss_find_upcall(pipe, gss_msg->uid, gss_msg->auth); if (old == NULL) { atomic_inc(&gss_msg->count); list_add(&gss_msg->list, &pipe->in_downcall); @@ -714,7 +716,7 @@ gss_pipe_downcall(struct file *filp, const char __user *src, size_t mlen) err = -ENOENT; /* Find a matching upcall */ spin_lock(&pipe->lock); - gss_msg = __gss_find_upcall(pipe, uid); + gss_msg = __gss_find_upcall(pipe, uid, NULL); if (gss_msg == NULL) { spin_unlock(&pipe->lock); goto err_put_ctx; diff --git a/net/sunrpc/auth_gss/svcauth_gss.c b/net/sunrpc/auth_gss/svcauth_gss.c index e085f5ae1548..1d281816f2bf 100644 --- a/net/sunrpc/auth_gss/svcauth_gss.c +++ b/net/sunrpc/auth_gss/svcauth_gss.c @@ -1230,8 +1230,9 @@ static int svcauth_gss_proxy_init(struct svc_rqst *rqstp, if (status) goto out; - dprintk("RPC: svcauth_gss: gss major status = %d\n", - ud.major_status); + dprintk("RPC: svcauth_gss: gss major status = %d " + "minor status = %d\n", + ud.major_status, ud.minor_status); switch (ud.major_status) { case GSS_S_CONTINUE_NEEDED: diff --git a/net/sunrpc/cache.c b/net/sunrpc/cache.c index 553bf95f7003..4d8e11f94a35 100644 --- a/net/sunrpc/cache.c +++ b/net/sunrpc/cache.c @@ -362,7 +362,7 @@ void sunrpc_destroy_cache_detail(struct cache_detail *cd) cache_purge(cd); spin_lock(&cache_list_lock); write_lock(&cd->hash_lock); - if (cd->entries || atomic_read(&cd->inuse)) { + if (cd->entries) { write_unlock(&cd->hash_lock); spin_unlock(&cache_list_lock); goto out; diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c index cb49898a5a58..7f79fb7dc6a0 100644 --- a/net/sunrpc/clnt.c +++ b/net/sunrpc/clnt.c @@ -2638,6 +2638,7 @@ int rpc_clnt_add_xprt(struct rpc_clnt *clnt, { struct rpc_xprt_switch *xps; struct rpc_xprt *xprt; + unsigned long reconnect_timeout; unsigned char resvport; int ret = 0; @@ -2649,6 +2650,7 @@ int rpc_clnt_add_xprt(struct rpc_clnt *clnt, return -EAGAIN; } resvport = xprt->resvport; + reconnect_timeout = xprt->max_reconnect_timeout; rcu_read_unlock(); xprt = xprt_create_transport(xprtargs); @@ -2657,6 +2659,7 @@ int rpc_clnt_add_xprt(struct rpc_clnt *clnt, goto out_put_switch; } xprt->resvport = resvport; + xprt->max_reconnect_timeout = reconnect_timeout; rpc_xprt_switch_set_roundrobin(xps); if (setup) { @@ -2673,6 +2676,27 @@ out_put_switch: } EXPORT_SYMBOL_GPL(rpc_clnt_add_xprt); +static int +rpc_xprt_cap_max_reconnect_timeout(struct rpc_clnt *clnt, + struct rpc_xprt *xprt, + void *data) +{ + unsigned long timeout = *((unsigned long *)data); + + if (timeout < xprt->max_reconnect_timeout) + xprt->max_reconnect_timeout = timeout; + return 0; +} + +void +rpc_cap_max_reconnect_timeout(struct rpc_clnt *clnt, unsigned long timeo) +{ + rpc_clnt_iterate_for_each_xprt(clnt, + rpc_xprt_cap_max_reconnect_timeout, + &timeo); +} +EXPORT_SYMBOL_GPL(rpc_cap_max_reconnect_timeout); + #if IS_ENABLED(CONFIG_SUNRPC_DEBUG) static void rpc_show_header(void) { diff --git a/net/sunrpc/svc_xprt.c b/net/sunrpc/svc_xprt.c index 4f01f63102ee..c3f652395a80 100644 --- a/net/sunrpc/svc_xprt.c +++ b/net/sunrpc/svc_xprt.c @@ -21,6 +21,10 @@ #define RPCDBG_FACILITY RPCDBG_SVCXPRT +static unsigned int svc_rpc_per_connection_limit __read_mostly; +module_param(svc_rpc_per_connection_limit, uint, 0644); + + static struct svc_deferred_req *svc_deferred_dequeue(struct svc_xprt *xprt); static int svc_deferred_recv(struct svc_rqst *rqstp); static struct cache_deferred_req *svc_defer(struct cache_req *req); @@ -329,12 +333,45 @@ char *svc_print_addr(struct svc_rqst *rqstp, char *buf, size_t len) } EXPORT_SYMBOL_GPL(svc_print_addr); +static bool svc_xprt_slots_in_range(struct svc_xprt *xprt) +{ + unsigned int limit = svc_rpc_per_connection_limit; + int nrqsts = atomic_read(&xprt->xpt_nr_rqsts); + + return limit == 0 || (nrqsts >= 0 && nrqsts < limit); +} + +static bool svc_xprt_reserve_slot(struct svc_rqst *rqstp, struct svc_xprt *xprt) +{ + if (!test_bit(RQ_DATA, &rqstp->rq_flags)) { + if (!svc_xprt_slots_in_range(xprt)) + return false; + atomic_inc(&xprt->xpt_nr_rqsts); + set_bit(RQ_DATA, &rqstp->rq_flags); + } + return true; +} + +static void svc_xprt_release_slot(struct svc_rqst *rqstp) +{ + struct svc_xprt *xprt = rqstp->rq_xprt; + if (test_and_clear_bit(RQ_DATA, &rqstp->rq_flags)) { + atomic_dec(&xprt->xpt_nr_rqsts); + svc_xprt_enqueue(xprt); + } +} + static bool svc_xprt_has_something_to_do(struct svc_xprt *xprt) { if (xprt->xpt_flags & ((1<<XPT_CONN)|(1<<XPT_CLOSE))) return true; - if (xprt->xpt_flags & ((1<<XPT_DATA)|(1<<XPT_DEFERRED))) - return xprt->xpt_ops->xpo_has_wspace(xprt); + if (xprt->xpt_flags & ((1<<XPT_DATA)|(1<<XPT_DEFERRED))) { + if (xprt->xpt_ops->xpo_has_wspace(xprt) && + svc_xprt_slots_in_range(xprt)) + return true; + trace_svc_xprt_no_write_space(xprt); + return false; + } return false; } @@ -480,8 +517,6 @@ void svc_reserve(struct svc_rqst *rqstp, int space) atomic_sub((rqstp->rq_reserved - space), &xprt->xpt_reserved); rqstp->rq_reserved = space; - if (xprt->xpt_ops->xpo_adjust_wspace) - xprt->xpt_ops->xpo_adjust_wspace(xprt); svc_xprt_enqueue(xprt); } } @@ -512,8 +547,8 @@ static void svc_xprt_release(struct svc_rqst *rqstp) rqstp->rq_res.head[0].iov_len = 0; svc_reserve(rqstp, 0); + svc_xprt_release_slot(rqstp); rqstp->rq_xprt = NULL; - svc_xprt_put(xprt); } @@ -781,7 +816,7 @@ static int svc_handle_xprt(struct svc_rqst *rqstp, struct svc_xprt *xprt) svc_add_new_temp_xprt(serv, newxpt); else module_put(xprt->xpt_class->xcl_owner); - } else { + } else if (svc_xprt_reserve_slot(rqstp, xprt)) { /* XPT_DATA|XPT_DEFERRED case: */ dprintk("svc: server %p, pool %u, transport %p, inuse=%d\n", rqstp, rqstp->rq_pool->sp_id, xprt, @@ -871,6 +906,7 @@ EXPORT_SYMBOL_GPL(svc_recv); */ void svc_drop(struct svc_rqst *rqstp) { + trace_svc_drop(rqstp); dprintk("svc: xprt %p dropped request\n", rqstp->rq_xprt); svc_xprt_release(rqstp); } @@ -1148,6 +1184,7 @@ static void svc_revisit(struct cache_deferred_req *dreq, int too_many) spin_unlock(&xprt->xpt_lock); dprintk("revisit canceled\n"); svc_xprt_put(xprt); + trace_svc_drop_deferred(dr); kfree(dr); return; } @@ -1205,6 +1242,7 @@ static struct cache_deferred_req *svc_defer(struct cache_req *req) set_bit(RQ_DROPME, &rqstp->rq_flags); dr->handle.revisit = svc_revisit; + trace_svc_defer(rqstp); return &dr->handle; } @@ -1245,6 +1283,7 @@ static struct svc_deferred_req *svc_deferred_dequeue(struct svc_xprt *xprt) struct svc_deferred_req, handle.recent); list_del_init(&dr->handle.recent); + trace_svc_revisit_deferred(dr); } else clear_bit(XPT_DEFERRED, &xprt->xpt_flags); spin_unlock(&xprt->xpt_lock); diff --git a/net/sunrpc/svcsock.c b/net/sunrpc/svcsock.c index dadfec66dbd8..57625f64efd5 100644 --- a/net/sunrpc/svcsock.c +++ b/net/sunrpc/svcsock.c @@ -60,7 +60,6 @@ static struct svc_sock *svc_setup_socket(struct svc_serv *, struct socket *, int flags); -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 *); @@ -398,48 +397,21 @@ static int svc_sock_secure_port(struct svc_rqst *rqstp) return svc_port_is_privileged(svc_addr(rqstp)); } -static bool sunrpc_waitqueue_active(wait_queue_head_t *wq) -{ - if (!wq) - return false; - /* - * There should normally be a memory * barrier here--see - * wq_has_sleeper(). - * - * It appears that isn't currently necessary, though, basically - * because callers all appear to have sufficient memory barriers - * between the time the relevant change is made and the - * time they call these callbacks. - * - * The nfsd code itself doesn't actually explicitly wait on - * these waitqueues, but it may wait on them for example in - * sendpage() or sendmsg() calls. (And those may be the only - * places, since it it uses nonblocking reads.) - * - * Maybe we should add the memory barriers anyway, but these are - * hot paths so we'd need to be convinced there's no sigificant - * penalty. - */ - return waitqueue_active(wq); -} - /* * INET callback when data has been received on the socket. */ -static void svc_udp_data_ready(struct sock *sk) +static void svc_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), 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); + svsk->sk_odata(sk); + if (!test_and_set_bit(XPT_DATA, &svsk->sk_xprt.xpt_flags)) + svc_xprt_enqueue(&svsk->sk_xprt); } - if (sunrpc_waitqueue_active(wq)) - wake_up_interruptible(wq); } /* @@ -448,56 +420,22 @@ static void svc_udp_data_ready(struct sock *sk) static void svc_write_space(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), write_space busy=%d\n", svsk, sk, test_bit(XPT_BUSY, &svsk->sk_xprt.xpt_flags)); + svsk->sk_owspace(sk); svc_xprt_enqueue(&svsk->sk_xprt); } - - if (sunrpc_waitqueue_active(wq)) { - dprintk("RPC svc_write_space: someone sleeping on %p\n", - svsk); - wake_up_interruptible(wq); - } } static int svc_tcp_has_wspace(struct svc_xprt *xprt) { - struct svc_sock *svsk = container_of(xprt, struct svc_sock, sk_xprt); - struct svc_serv *serv = svsk->sk_xprt.xpt_server; - int required; + struct svc_sock *svsk = container_of(xprt, struct svc_sock, sk_xprt); if (test_bit(XPT_LISTENER, &xprt->xpt_flags)) return 1; - required = atomic_read(&xprt->xpt_reserved) + serv->sv_max_mesg; - if (sk_stream_wspace(svsk->sk_sk) >= required || - (sk_stream_min_wspace(svsk->sk_sk) == 0 && - atomic_read(&xprt->xpt_reserved) == 0)) - return 1; - set_bit(SOCK_NOSPACE, &svsk->sk_sock->flags); - return 0; -} - -static void svc_tcp_write_space(struct sock *sk) -{ - struct svc_sock *svsk = (struct svc_sock *)(sk->sk_user_data); - struct socket *sock = sk->sk_socket; - - if (!sk_stream_is_writeable(sk) || !sock) - return; - if (!svsk || svc_tcp_has_wspace(&svsk->sk_xprt)) - clear_bit(SOCK_NOSPACE, &sock->flags); - svc_write_space(sk); -} - -static void svc_tcp_adjust_wspace(struct svc_xprt *xprt) -{ - struct svc_sock *svsk = container_of(xprt, struct svc_sock, sk_xprt); - - if (svc_tcp_has_wspace(xprt)) - clear_bit(SOCK_NOSPACE, &svsk->sk_sock->flags); + return !test_bit(SOCK_NOSPACE, &svsk->sk_sock->flags); } /* @@ -746,7 +684,7 @@ static void svc_udp_init(struct svc_sock *svsk, struct svc_serv *serv) svc_xprt_init(sock_net(svsk->sk_sock->sk), &svc_udp_class, &svsk->sk_xprt, serv); clear_bit(XPT_CACHE_AUTH, &svsk->sk_xprt.xpt_flags); - svsk->sk_sk->sk_data_ready = svc_udp_data_ready; + svsk->sk_sk->sk_data_ready = svc_data_ready; svsk->sk_sk->sk_write_space = svc_write_space; /* initialise setting must have enough space to @@ -786,11 +724,12 @@ static void svc_udp_init(struct svc_sock *svsk, struct svc_serv *serv) 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; dprintk("svc: socket %p TCP (listen) state change %d\n", sk, sk->sk_state); + if (svsk) + svsk->sk_odata(sk); /* * This callback may called twice when a new connection * is established as a child socket inherits everything @@ -808,10 +747,6 @@ static void svc_tcp_listen_data_ready(struct sock *sk) } else printk("svc: socket %p: no user data\n", sk); } - - wq = sk_sleep(sk); - if (sunrpc_waitqueue_active(wq)) - wake_up_interruptible_all(wq); } /* @@ -820,7 +755,6 @@ static void svc_tcp_listen_data_ready(struct sock *sk) static void svc_tcp_state_change(struct sock *sk) { struct svc_sock *svsk = (struct svc_sock *)sk->sk_user_data; - wait_queue_head_t *wq = sk_sleep(sk); dprintk("svc: socket %p TCP (connected) state change %d (svsk %p)\n", sk, sk->sk_state, sk->sk_user_data); @@ -828,26 +762,12 @@ static void svc_tcp_state_change(struct sock *sk) if (!svsk) printk("svc: socket %p: no user data\n", sk); else { - set_bit(XPT_CLOSE, &svsk->sk_xprt.xpt_flags); - svc_xprt_enqueue(&svsk->sk_xprt); - } - if (sunrpc_waitqueue_active(wq)) - wake_up_interruptible_all(wq); -} - -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); - - dprintk("svc: socket %p TCP data ready (svsk %p)\n", - sk, sk->sk_user_data); - if (svsk) { - set_bit(XPT_DATA, &svsk->sk_xprt.xpt_flags); - svc_xprt_enqueue(&svsk->sk_xprt); + svsk->sk_ostate(sk); + if (sk->sk_state != TCP_ESTABLISHED) { + set_bit(XPT_CLOSE, &svsk->sk_xprt.xpt_flags); + svc_xprt_enqueue(&svsk->sk_xprt); + } } - if (sunrpc_waitqueue_active(wq)) - wake_up_interruptible(wq); } /* @@ -901,6 +821,11 @@ static struct svc_xprt *svc_tcp_accept(struct svc_xprt *xprt) dprintk("%s: connect from %s\n", serv->sv_name, __svc_print_addr(sin, buf, sizeof(buf))); + /* Reset the inherited callbacks before calling svc_setup_socket */ + newsock->sk->sk_state_change = svsk->sk_ostate; + newsock->sk->sk_data_ready = svsk->sk_odata; + newsock->sk->sk_write_space = svsk->sk_owspace; + /* make sure that a write doesn't block forever when * low on memory */ @@ -1317,7 +1242,6 @@ static struct svc_xprt_ops svc_tcp_ops = { .xpo_has_wspace = svc_tcp_has_wspace, .xpo_accept = svc_tcp_accept, .xpo_secure_port = svc_sock_secure_port, - .xpo_adjust_wspace = svc_tcp_adjust_wspace, }; static struct svc_xprt_class svc_tcp_class = { @@ -1357,8 +1281,8 @@ static void svc_tcp_init(struct svc_sock *svsk, struct svc_serv *serv) } else { dprintk("setting up TCP socket for reading\n"); sk->sk_state_change = svc_tcp_state_change; - sk->sk_data_ready = svc_tcp_data_ready; - sk->sk_write_space = svc_tcp_write_space; + sk->sk_data_ready = svc_data_ready; + sk->sk_write_space = svc_write_space; svsk->sk_reclen = 0; svsk->sk_tcplen = 0; @@ -1368,8 +1292,13 @@ static void svc_tcp_init(struct svc_sock *svsk, struct svc_serv *serv) tcp_sk(sk)->nonagle |= TCP_NAGLE_OFF; set_bit(XPT_DATA, &svsk->sk_xprt.xpt_flags); - if (sk->sk_state != TCP_ESTABLISHED) + switch (sk->sk_state) { + case TCP_SYN_RECV: + case TCP_ESTABLISHED: + break; + default: set_bit(XPT_CLOSE, &svsk->sk_xprt.xpt_flags); + } } } @@ -1428,17 +1357,14 @@ static struct svc_sock *svc_setup_socket(struct svc_serv *serv, /* Initialize the socket */ if (sock->type == SOCK_DGRAM) svc_udp_init(svsk, serv); - else { - /* initialise setting must have enough space to - * receive and respond to one request. - */ - svc_sock_setbufsize(svsk->sk_sock, 4 * serv->sv_max_mesg, - 4 * serv->sv_max_mesg); + else svc_tcp_init(svsk, serv); - } - dprintk("svc: svc_setup_socket created %p (inet %p)\n", - svsk, svsk->sk_sk); + dprintk("svc: svc_setup_socket created %p (inet %p), " + "listen %d close %d\n", + svsk, svsk->sk_sk, + test_bit(XPT_LISTENER, &svsk->sk_xprt.xpt_flags), + test_bit(XPT_CLOSE, &svsk->sk_xprt.xpt_flags)); return svsk; } @@ -1606,18 +1532,16 @@ static void svc_sock_detach(struct svc_xprt *xprt) { struct svc_sock *svsk = container_of(xprt, struct svc_sock, sk_xprt); struct sock *sk = svsk->sk_sk; - wait_queue_head_t *wq; dprintk("svc: svc_sock_detach(%p)\n", svsk); /* put back the old socket callbacks */ + lock_sock(sk); sk->sk_state_change = svsk->sk_ostate; sk->sk_data_ready = svsk->sk_odata; sk->sk_write_space = svsk->sk_owspace; - - wq = sk_sleep(sk); - if (sunrpc_waitqueue_active(wq)) - wake_up_interruptible(wq); + sk->sk_user_data = NULL; + release_sock(sk); } /* diff --git a/net/sunrpc/xprt.c b/net/sunrpc/xprt.c index 8313960cac52..ea244b29138b 100644 --- a/net/sunrpc/xprt.c +++ b/net/sunrpc/xprt.c @@ -680,6 +680,20 @@ out: spin_unlock_bh(&xprt->transport_lock); } +static bool +xprt_has_timer(const struct rpc_xprt *xprt) +{ + return xprt->idle_timeout != 0; +} + +static void +xprt_schedule_autodisconnect(struct rpc_xprt *xprt) + __must_hold(&xprt->transport_lock) +{ + if (list_empty(&xprt->recv) && xprt_has_timer(xprt)) + mod_timer(&xprt->timer, xprt->last_used + xprt->idle_timeout); +} + static void xprt_init_autodisconnect(unsigned long data) { @@ -688,6 +702,8 @@ xprt_init_autodisconnect(unsigned long data) spin_lock(&xprt->transport_lock); if (!list_empty(&xprt->recv)) goto out_abort; + /* Reset xprt->last_used to avoid connect/autodisconnect cycling */ + xprt->last_used = jiffies; if (test_and_set_bit(XPRT_LOCKED, &xprt->state)) goto out_abort; spin_unlock(&xprt->transport_lock); @@ -725,6 +741,7 @@ void xprt_unlock_connect(struct rpc_xprt *xprt, void *cookie) goto out; xprt->snd_task =NULL; xprt->ops->release_xprt(xprt, NULL); + xprt_schedule_autodisconnect(xprt); out: spin_unlock_bh(&xprt->transport_lock); wake_up_bit(&xprt->state, XPRT_LOCKED); @@ -888,11 +905,6 @@ static void xprt_timer(struct rpc_task *task) spin_unlock_bh(&xprt->transport_lock); } -static inline int xprt_has_timer(struct rpc_xprt *xprt) -{ - return xprt->idle_timeout != 0; -} - /** * xprt_prepare_transmit - reserve the transport before sending a request * @task: RPC task about to send a request @@ -1280,9 +1292,7 @@ void xprt_release(struct rpc_task *task) if (!list_empty(&req->rq_list)) list_del(&req->rq_list); xprt->last_used = jiffies; - if (list_empty(&xprt->recv) && xprt_has_timer(xprt)) - mod_timer(&xprt->timer, - xprt->last_used + xprt->idle_timeout); + xprt_schedule_autodisconnect(xprt); spin_unlock_bh(&xprt->transport_lock); if (req->rq_buffer) xprt->ops->buf_free(req->rq_buffer); diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c index 111767ab124a..8ede3bc52481 100644 --- a/net/sunrpc/xprtsock.c +++ b/net/sunrpc/xprtsock.c @@ -177,7 +177,6 @@ static struct ctl_table sunrpc_table[] = { * increase over time if the server is down or not responding. */ #define XS_TCP_INIT_REEST_TO (3U * HZ) -#define XS_TCP_MAX_REEST_TO (5U * 60 * HZ) /* * TCP idle timeout; client drops the transport socket if it is idle @@ -2173,6 +2172,8 @@ static void xs_udp_finish_connecting(struct rpc_xprt *xprt, struct socket *sock) write_unlock_bh(&sk->sk_callback_lock); } xs_udp_do_set_buffer_size(xprt); + + xprt->stat.connect_start = jiffies; } static void xs_udp_setup_socket(struct work_struct *work) @@ -2236,6 +2237,7 @@ static int xs_tcp_finish_connecting(struct rpc_xprt *xprt, struct socket *sock) unsigned int keepcnt = xprt->timeout->to_retries + 1; unsigned int opt_on = 1; unsigned int timeo; + unsigned int addr_pref = IPV6_PREFER_SRC_PUBLIC; /* TCP Keepalive options */ kernel_setsockopt(sock, SOL_SOCKET, SO_KEEPALIVE, @@ -2247,6 +2249,16 @@ static int xs_tcp_finish_connecting(struct rpc_xprt *xprt, struct socket *sock) kernel_setsockopt(sock, SOL_TCP, TCP_KEEPCNT, (char *)&keepcnt, sizeof(keepcnt)); + /* Avoid temporary address, they are bad for long-lived + * connections such as NFS mounts. + * RFC4941, section 3.6 suggests that: + * Individual applications, which have specific + * knowledge about the normal duration of connections, + * MAY override this as appropriate. + */ + kernel_setsockopt(sock, SOL_IPV6, IPV6_ADDR_PREFERENCES, + (char *)&addr_pref, sizeof(addr_pref)); + /* TCP user timeout (see RFC5482) */ timeo = jiffies_to_msecs(xprt->timeout->to_initval) * (xprt->timeout->to_retries + 1); @@ -2295,6 +2307,10 @@ static int xs_tcp_finish_connecting(struct rpc_xprt *xprt, struct socket *sock) /* SYN_SENT! */ if (xprt->reestablish_timeout < XS_TCP_INIT_REEST_TO) xprt->reestablish_timeout = XS_TCP_INIT_REEST_TO; + break; + case -EADDRNOTAVAIL: + /* Source port number is unavailable. Try a new one! */ + transport->srcport = 0; } out: return ret; @@ -2369,6 +2385,25 @@ out: xprt_wake_pending_tasks(xprt, status); } +static unsigned long xs_reconnect_delay(const struct rpc_xprt *xprt) +{ + unsigned long start, now = jiffies; + + start = xprt->stat.connect_start + xprt->reestablish_timeout; + if (time_after(start, now)) + return start - now; + return 0; +} + +static void xs_reconnect_backoff(struct rpc_xprt *xprt) +{ + xprt->reestablish_timeout <<= 1; + if (xprt->reestablish_timeout > xprt->max_reconnect_timeout) + xprt->reestablish_timeout = xprt->max_reconnect_timeout; + if (xprt->reestablish_timeout < XS_TCP_INIT_REEST_TO) + xprt->reestablish_timeout = XS_TCP_INIT_REEST_TO; +} + /** * xs_connect - connect a socket to a remote endpoint * @xprt: pointer to transport structure @@ -2386,6 +2421,7 @@ out: static void xs_connect(struct rpc_xprt *xprt, struct rpc_task *task) { struct sock_xprt *transport = container_of(xprt, struct sock_xprt, xprt); + unsigned long delay = 0; WARN_ON_ONCE(!xprt_lock_connect(xprt, task, transport)); @@ -2397,19 +2433,15 @@ static void xs_connect(struct rpc_xprt *xprt, struct rpc_task *task) /* Start by resetting any existing state */ xs_reset_transport(transport); - queue_delayed_work(xprtiod_workqueue, - &transport->connect_worker, - xprt->reestablish_timeout); - xprt->reestablish_timeout <<= 1; - if (xprt->reestablish_timeout < XS_TCP_INIT_REEST_TO) - xprt->reestablish_timeout = XS_TCP_INIT_REEST_TO; - if (xprt->reestablish_timeout > XS_TCP_MAX_REEST_TO) - xprt->reestablish_timeout = XS_TCP_MAX_REEST_TO; - } else { + delay = xs_reconnect_delay(xprt); + xs_reconnect_backoff(xprt); + + } else dprintk("RPC: xs_connect scheduled xprt %p\n", xprt); - queue_delayed_work(xprtiod_workqueue, - &transport->connect_worker, 0); - } + + queue_delayed_work(xprtiod_workqueue, + &transport->connect_worker, + delay); } /** @@ -2961,6 +2993,8 @@ static struct rpc_xprt *xs_setup_tcp(struct xprt_create *args) xprt->ops = &xs_tcp_ops; xprt->timeout = &xs_tcp_default_timeout; + xprt->max_reconnect_timeout = xprt->timeout->to_maxval; + INIT_WORK(&transport->recv_worker, xs_tcp_data_receive_workfn); INIT_DELAYED_WORK(&transport->connect_worker, xs_tcp_setup_socket); diff --git a/net/switchdev/switchdev.c b/net/switchdev/switchdev.c index a5fc9dd24aa9..10b819308439 100644 --- a/net/switchdev/switchdev.c +++ b/net/switchdev/switchdev.c @@ -1042,7 +1042,7 @@ static int switchdev_port_fdb_dump_cb(struct switchdev_obj *obj) struct nlmsghdr *nlh; struct ndmsg *ndm; - if (dump->idx < dump->cb->args[0]) + if (dump->idx < dump->cb->args[2]) goto skip; nlh = nlmsg_put(dump->skb, portid, seq, RTM_NEWNEIGH, @@ -1089,7 +1089,7 @@ nla_put_failure: */ int switchdev_port_fdb_dump(struct sk_buff *skb, struct netlink_callback *cb, struct net_device *dev, - struct net_device *filter_dev, int idx) + struct net_device *filter_dev, int *idx) { struct switchdev_fdb_dump dump = { .fdb.obj.orig_dev = dev, @@ -1097,14 +1097,14 @@ int switchdev_port_fdb_dump(struct sk_buff *skb, struct netlink_callback *cb, .dev = dev, .skb = skb, .cb = cb, - .idx = idx, + .idx = *idx, }; int err; err = switchdev_port_obj_dump(dev, &dump.fdb.obj, switchdev_port_fdb_dump_cb); - cb->args[1] = err; - return dump.idx; + *idx = dump.idx; + return err; } EXPORT_SYMBOL_GPL(switchdev_port_fdb_dump); @@ -1292,12 +1292,10 @@ bool switchdev_port_same_parent_id(struct net_device *a, struct switchdev_attr a_attr = { .orig_dev = a, .id = SWITCHDEV_ATTR_ID_PORT_PARENT_ID, - .flags = SWITCHDEV_F_NO_RECURSE, }; struct switchdev_attr b_attr = { .orig_dev = b, .id = SWITCHDEV_ATTR_ID_PORT_PARENT_ID, - .flags = SWITCHDEV_F_NO_RECURSE, }; if (switchdev_port_attr_get(a, &a_attr) || @@ -1306,89 +1304,4 @@ bool switchdev_port_same_parent_id(struct net_device *a, return netdev_phys_item_id_same(&a_attr.u.ppid, &b_attr.u.ppid); } - -static u32 switchdev_port_fwd_mark_get(struct net_device *dev, - struct net_device *group_dev) -{ - struct net_device *lower_dev; - struct list_head *iter; - - netdev_for_each_lower_dev(group_dev, lower_dev, iter) { - if (lower_dev == dev) - continue; - if (switchdev_port_same_parent_id(dev, lower_dev)) - return lower_dev->offload_fwd_mark; - return switchdev_port_fwd_mark_get(dev, lower_dev); - } - - return dev->ifindex; -} EXPORT_SYMBOL_GPL(switchdev_port_same_parent_id); - -static void switchdev_port_fwd_mark_reset(struct net_device *group_dev, - u32 old_mark, u32 *reset_mark) -{ - struct net_device *lower_dev; - struct list_head *iter; - - netdev_for_each_lower_dev(group_dev, lower_dev, iter) { - if (lower_dev->offload_fwd_mark == old_mark) { - if (!*reset_mark) - *reset_mark = lower_dev->ifindex; - lower_dev->offload_fwd_mark = *reset_mark; - } - switchdev_port_fwd_mark_reset(lower_dev, old_mark, reset_mark); - } -} - -/** - * switchdev_port_fwd_mark_set - Set port offload forwarding mark - * - * @dev: port device - * @group_dev: containing device - * @joining: true if dev is joining group; false if leaving group - * - * An ungrouped port's offload mark is just its ifindex. A grouped - * port's (member of a bridge, for example) offload mark is the ifindex - * of one of the ports in the group with the same parent (switch) ID. - * Ports on the same device in the same group will have the same mark. - * - * Example: - * - * br0 ifindex=9 - * sw1p1 ifindex=2 mark=2 - * sw1p2 ifindex=3 mark=2 - * sw2p1 ifindex=4 mark=5 - * sw2p2 ifindex=5 mark=5 - * - * If sw2p2 leaves the bridge, we'll have: - * - * br0 ifindex=9 - * sw1p1 ifindex=2 mark=2 - * sw1p2 ifindex=3 mark=2 - * sw2p1 ifindex=4 mark=4 - * sw2p2 ifindex=5 mark=5 - */ -void switchdev_port_fwd_mark_set(struct net_device *dev, - struct net_device *group_dev, - bool joining) -{ - u32 mark = dev->ifindex; - u32 reset_mark = 0; - - if (group_dev) { - ASSERT_RTNL(); - if (joining) - mark = switchdev_port_fwd_mark_get(dev, group_dev); - else if (dev->offload_fwd_mark == mark) - /* Ohoh, this port was the mark reference port, - * but it's leaving the group, so reset the - * mark for the remaining ports in the group. - */ - switchdev_port_fwd_mark_reset(group_dev, mark, - &reset_mark); - } - - dev->offload_fwd_mark = mark; -} -EXPORT_SYMBOL_GPL(switchdev_port_fwd_mark_set); diff --git a/net/sysctl_net.c b/net/sysctl_net.c index 46a71c701e7c..5bc1a3d57401 100644 --- a/net/sysctl_net.c +++ b/net/sysctl_net.c @@ -42,26 +42,37 @@ static int net_ctl_permissions(struct ctl_table_header *head, struct ctl_table *table) { struct net *net = container_of(head->set, struct net, sysctls); - kuid_t root_uid = make_kuid(net->user_ns, 0); - kgid_t root_gid = make_kgid(net->user_ns, 0); /* Allow network administrator to have same access as root. */ - if (ns_capable_noaudit(net->user_ns, CAP_NET_ADMIN) || - uid_eq(root_uid, current_euid())) { + if (ns_capable(net->user_ns, CAP_NET_ADMIN)) { int mode = (table->mode >> 6) & 7; return (mode << 6) | (mode << 3) | mode; } - /* Allow netns root group to have the same access as the root group */ - if (in_egroup_p(root_gid)) { - int mode = (table->mode >> 3) & 7; - return (mode << 3) | mode; - } + return table->mode; } +static void net_ctl_set_ownership(struct ctl_table_header *head, + struct ctl_table *table, + kuid_t *uid, kgid_t *gid) +{ + struct net *net = container_of(head->set, struct net, sysctls); + kuid_t ns_root_uid; + kgid_t ns_root_gid; + + ns_root_uid = make_kuid(net->user_ns, 0); + if (uid_valid(ns_root_uid)) + *uid = ns_root_uid; + + ns_root_gid = make_kgid(net->user_ns, 0); + if (gid_valid(ns_root_gid)) + *gid = ns_root_gid; +} + static struct ctl_table_root net_sysctl_root = { .lookup = net_ctl_header_lookup, .permissions = net_ctl_permissions, + .set_ownership = net_ctl_set_ownership, }; static int __net_init sysctl_net_init(struct net *net) diff --git a/net/tipc/bcast.c b/net/tipc/bcast.c index ae469b37d852..753f774cb46f 100644 --- a/net/tipc/bcast.c +++ b/net/tipc/bcast.c @@ -269,18 +269,19 @@ void tipc_bcast_ack_rcv(struct net *net, struct tipc_link *l, u32 acked) * * RCU is locked, no other locks set */ -void tipc_bcast_sync_rcv(struct net *net, struct tipc_link *l, - struct tipc_msg *hdr) +int tipc_bcast_sync_rcv(struct net *net, struct tipc_link *l, + struct tipc_msg *hdr) { struct sk_buff_head *inputq = &tipc_bc_base(net)->inputq; struct sk_buff_head xmitq; + int rc = 0; __skb_queue_head_init(&xmitq); tipc_bcast_lock(net); if (msg_type(hdr) == STATE_MSG) { tipc_link_bc_ack_rcv(l, msg_bcast_ack(hdr), &xmitq); - tipc_link_bc_sync_rcv(l, hdr, &xmitq); + rc = tipc_link_bc_sync_rcv(l, hdr, &xmitq); } else { tipc_link_bc_init_rcv(l, hdr); } @@ -291,6 +292,7 @@ void tipc_bcast_sync_rcv(struct net *net, struct tipc_link *l, /* Any socket wakeup messages ? */ if (!skb_queue_empty(inputq)) tipc_sk_rcv(net, inputq); + return rc; } /* tipc_bcast_add_peer - add a peer node to broadcast link and bearer diff --git a/net/tipc/bcast.h b/net/tipc/bcast.h index d5e79b3767fd..5ffe34472ccd 100644 --- a/net/tipc/bcast.h +++ b/net/tipc/bcast.h @@ -56,8 +56,8 @@ int tipc_bcast_get_mtu(struct net *net); int tipc_bcast_xmit(struct net *net, struct sk_buff_head *list); int tipc_bcast_rcv(struct net *net, struct tipc_link *l, struct sk_buff *skb); void tipc_bcast_ack_rcv(struct net *net, struct tipc_link *l, u32 acked); -void tipc_bcast_sync_rcv(struct net *net, struct tipc_link *l, - struct tipc_msg *hdr); +int tipc_bcast_sync_rcv(struct net *net, struct tipc_link *l, + struct tipc_msg *hdr); int tipc_nl_add_bc_link(struct net *net, struct tipc_nl_msg *msg); int tipc_nl_bc_link_set(struct net *net, struct nlattr *attrs[]); int tipc_bclink_reset_stats(struct net *net); diff --git a/net/tipc/bearer.c b/net/tipc/bearer.c index 65b1bbf133bd..975dbeb60ab0 100644 --- a/net/tipc/bearer.c +++ b/net/tipc/bearer.c @@ -42,6 +42,7 @@ #include "monitor.h" #include "bcast.h" #include "netlink.h" +#include "udp_media.h" #define MAX_ADDR_STR 60 @@ -56,6 +57,13 @@ static struct tipc_media * const media_info_array[] = { NULL }; +static struct tipc_bearer *bearer_get(struct net *net, int bearer_id) +{ + struct tipc_net *tn = tipc_net(net); + + return rcu_dereference_rtnl(tn->bearer_list[bearer_id]); +} + static void bearer_disable(struct net *net, struct tipc_bearer *b); /** @@ -323,6 +331,7 @@ restart: b->domain = disc_domain; b->net_plane = bearer_id + 'A'; b->priority = priority; + test_and_set_bit_lock(0, &b->up); res = tipc_disc_create(net, b, &b->bcast_addr, &skb); if (res) { @@ -360,15 +369,24 @@ static int tipc_reset_bearer(struct net *net, struct tipc_bearer *b) */ void tipc_bearer_reset_all(struct net *net) { - struct tipc_net *tn = tipc_net(net); struct tipc_bearer *b; int i; for (i = 0; i < MAX_BEARERS; i++) { - b = rcu_dereference_rtnl(tn->bearer_list[i]); + b = bearer_get(net, i); + if (b) + clear_bit_unlock(0, &b->up); + } + for (i = 0; i < MAX_BEARERS; i++) { + b = bearer_get(net, i); if (b) tipc_reset_bearer(net, b); } + for (i = 0; i < MAX_BEARERS; i++) { + b = bearer_get(net, i); + if (b) + test_and_set_bit_lock(0, &b->up); + } } /** @@ -382,8 +400,9 @@ static void bearer_disable(struct net *net, struct tipc_bearer *b) int bearer_id = b->identity; pr_info("Disabling bearer <%s>\n", b->name); - b->media->disable_media(b); + clear_bit_unlock(0, &b->up); tipc_node_delete_links(net, bearer_id); + b->media->disable_media(b); RCU_INIT_POINTER(b->media_ptr, NULL); if (b->link_req) tipc_disc_delete(b->link_req); @@ -440,22 +459,16 @@ int tipc_l2_send_msg(struct net *net, struct sk_buff *skb, { struct net_device *dev; int delta; - void *tipc_ptr; dev = (struct net_device *)rcu_dereference_rtnl(b->media_ptr); if (!dev) return 0; - /* Send RESET message even if bearer is detached from device */ - tipc_ptr = rcu_dereference_rtnl(dev->tipc_ptr); - if (unlikely(!tipc_ptr && !msg_is_reset(buf_msg(skb)))) - goto drop; - - delta = dev->hard_header_len - skb_headroom(skb); - if ((delta > 0) && - pskb_expand_head(skb, SKB_DATA_ALIGN(delta), 0, GFP_ATOMIC)) - goto drop; - + delta = SKB_DATA_ALIGN(dev->hard_header_len - skb_headroom(skb)); + if ((delta > 0) && pskb_expand_head(skb, delta, 0, GFP_ATOMIC)) { + kfree_skb(skb); + return 0; + } skb_reset_network_header(skb); skb->dev = dev; skb->protocol = htons(ETH_P_TIPC); @@ -463,9 +476,6 @@ int tipc_l2_send_msg(struct net *net, struct sk_buff *skb, dev->dev_addr, skb->len); dev_queue_xmit(skb); return 0; -drop: - kfree_skb(skb); - return 0; } int tipc_bearer_mtu(struct net *net, u32 bearer_id) @@ -487,12 +497,12 @@ void tipc_bearer_xmit_skb(struct net *net, u32 bearer_id, struct sk_buff *skb, struct tipc_media_addr *dest) { - struct tipc_net *tn = tipc_net(net); + struct tipc_msg *hdr = buf_msg(skb); struct tipc_bearer *b; rcu_read_lock(); - b = rcu_dereference_rtnl(tn->bearer_list[bearer_id]); - if (likely(b)) + b = bearer_get(net, bearer_id); + if (likely(b && (test_bit(0, &b->up) || msg_is_reset(hdr)))) b->media->send_msg(net, skb, b, dest); else kfree_skb(skb); @@ -505,7 +515,6 @@ void tipc_bearer_xmit(struct net *net, u32 bearer_id, struct sk_buff_head *xmitq, struct tipc_media_addr *dst) { - struct tipc_net *tn = net_generic(net, tipc_net_id); struct tipc_bearer *b; struct sk_buff *skb, *tmp; @@ -513,12 +522,15 @@ void tipc_bearer_xmit(struct net *net, u32 bearer_id, return; rcu_read_lock(); - b = rcu_dereference_rtnl(tn->bearer_list[bearer_id]); + b = bearer_get(net, bearer_id); if (unlikely(!b)) __skb_queue_purge(xmitq); skb_queue_walk_safe(xmitq, skb, tmp) { __skb_dequeue(xmitq); - b->media->send_msg(net, skb, b, dst); + if (likely(test_bit(0, &b->up) || msg_is_reset(buf_msg(skb)))) + b->media->send_msg(net, skb, b, dst); + else + kfree_skb(skb); } rcu_read_unlock(); } @@ -535,8 +547,8 @@ void tipc_bearer_bc_xmit(struct net *net, u32 bearer_id, struct tipc_msg *hdr; rcu_read_lock(); - b = rcu_dereference_rtnl(tn->bearer_list[bearer_id]); - if (unlikely(!b)) + b = bearer_get(net, bearer_id); + if (unlikely(!b || !test_bit(0, &b->up))) __skb_queue_purge(xmitq); skb_queue_walk_safe(xmitq, skb, tmp) { hdr = buf_msg(skb); @@ -566,7 +578,8 @@ static int tipc_l2_rcv_msg(struct sk_buff *skb, struct net_device *dev, rcu_read_lock(); b = rcu_dereference_rtnl(dev->tipc_ptr); - if (likely(b && (skb->pkt_type <= PACKET_BROADCAST))) { + if (likely(b && test_bit(0, &b->up) && + (skb->pkt_type <= PACKET_BROADCAST))) { skb->next = NULL; tipc_rcv(dev_net(dev), skb, b); rcu_read_unlock(); @@ -591,18 +604,9 @@ static int tipc_l2_device_event(struct notifier_block *nb, unsigned long evt, { struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct net *net = dev_net(dev); - struct tipc_net *tn = tipc_net(net); struct tipc_bearer *b; - int i; b = rtnl_dereference(dev->tipc_ptr); - if (!b) { - for (i = 0; i < MAX_BEARERS; b = NULL, i++) { - b = rtnl_dereference(tn->bearer_list[i]); - if (b && (b->media_ptr == dev)) - break; - } - } if (!b) return NOTIFY_DONE; @@ -613,11 +617,10 @@ static int tipc_l2_device_event(struct notifier_block *nb, unsigned long evt, if (netif_carrier_ok(dev)) break; case NETDEV_UP: - rcu_assign_pointer(dev->tipc_ptr, b); + test_and_set_bit_lock(0, &b->up); break; case NETDEV_GOING_DOWN: - RCU_INIT_POINTER(dev->tipc_ptr, NULL); - synchronize_net(); + clear_bit_unlock(0, &b->up); tipc_reset_bearer(net, b); break; case NETDEV_CHANGEMTU: @@ -709,6 +712,14 @@ static int __tipc_nl_add_bearer(struct tipc_nl_msg *msg, goto prop_msg_full; nla_nest_end(msg->skb, prop); + +#ifdef CONFIG_TIPC_MEDIA_UDP + if (bearer->media->type_id == TIPC_MEDIA_TYPE_UDP) { + if (tipc_udp_nl_add_bearer_data(msg, bearer)) + goto attr_msg_full; + } +#endif + nla_nest_end(msg->skb, attrs); genlmsg_end(msg->skb, hdr); @@ -895,6 +906,49 @@ int tipc_nl_bearer_enable(struct sk_buff *skb, struct genl_info *info) return 0; } +int tipc_nl_bearer_add(struct sk_buff *skb, struct genl_info *info) +{ + int err; + char *name; + struct tipc_bearer *b; + struct nlattr *attrs[TIPC_NLA_BEARER_MAX + 1]; + struct net *net = sock_net(skb->sk); + + if (!info->attrs[TIPC_NLA_BEARER]) + return -EINVAL; + + err = nla_parse_nested(attrs, TIPC_NLA_BEARER_MAX, + info->attrs[TIPC_NLA_BEARER], + tipc_nl_bearer_policy); + if (err) + return err; + + if (!attrs[TIPC_NLA_BEARER_NAME]) + return -EINVAL; + name = nla_data(attrs[TIPC_NLA_BEARER_NAME]); + + rtnl_lock(); + b = tipc_bearer_find(net, name); + if (!b) { + rtnl_unlock(); + return -EINVAL; + } + +#ifdef CONFIG_TIPC_MEDIA_UDP + if (attrs[TIPC_NLA_BEARER_UDP_OPTS]) { + err = tipc_udp_nl_bearer_add(b, + attrs[TIPC_NLA_BEARER_UDP_OPTS]); + if (err) { + rtnl_unlock(); + return err; + } + } +#endif + rtnl_unlock(); + + return 0; +} + int tipc_nl_bearer_set(struct sk_buff *skb, struct genl_info *info) { int err; diff --git a/net/tipc/bearer.h b/net/tipc/bearer.h index 43757f1f9cb3..78892e2f53e3 100644 --- a/net/tipc/bearer.h +++ b/net/tipc/bearer.h @@ -150,6 +150,7 @@ struct tipc_bearer { u32 identity; struct tipc_link_req *link_req; char net_plane; + unsigned long up; }; struct tipc_bearer_names { @@ -180,6 +181,7 @@ int tipc_nl_bearer_enable(struct sk_buff *skb, struct genl_info *info); int tipc_nl_bearer_dump(struct sk_buff *skb, struct netlink_callback *cb); int tipc_nl_bearer_get(struct sk_buff *skb, struct genl_info *info); int tipc_nl_bearer_set(struct sk_buff *skb, struct genl_info *info); +int tipc_nl_bearer_add(struct sk_buff *skb, struct genl_info *info); int tipc_nl_media_dump(struct sk_buff *skb, struct netlink_callback *cb); int tipc_nl_media_get(struct sk_buff *skb, struct genl_info *info); diff --git a/net/tipc/link.c b/net/tipc/link.c index 877d94f34814..b36e16cdc945 100644 --- a/net/tipc/link.c +++ b/net/tipc/link.c @@ -181,7 +181,10 @@ struct tipc_link { u16 acked; struct tipc_link *bc_rcvlink; struct tipc_link *bc_sndlink; - int nack_state; + unsigned long prev_retr; + u16 prev_from; + u16 prev_to; + u8 nack_state; bool bc_peer_is_up; /* Statistics */ @@ -202,6 +205,8 @@ enum { BC_NACK_SND_SUPPRESS, }; +#define TIPC_BC_RETR_LIMIT 10 /* [ms] */ + /* * Interval between NACKs when packets arrive out of order */ @@ -237,8 +242,8 @@ static void tipc_link_build_proto_msg(struct tipc_link *l, int mtyp, bool probe, u16 rcvgap, int tolerance, int priority, struct sk_buff_head *xmitq); static void link_print(struct tipc_link *l, const char *str); -static void tipc_link_build_nack_msg(struct tipc_link *l, - struct sk_buff_head *xmitq); +static int tipc_link_build_nack_msg(struct tipc_link *l, + struct sk_buff_head *xmitq); static void tipc_link_build_bc_init_msg(struct tipc_link *l, struct sk_buff_head *xmitq); static bool tipc_link_release_pkts(struct tipc_link *l, u16 to); @@ -367,6 +372,18 @@ int tipc_link_bc_peers(struct tipc_link *l) return l->ackers; } +u16 link_bc_rcv_gap(struct tipc_link *l) +{ + struct sk_buff *skb = skb_peek(&l->deferdq); + u16 gap = 0; + + if (more(l->snd_nxt, l->rcv_nxt)) + gap = l->snd_nxt - l->rcv_nxt; + if (skb) + gap = buf_seqno(skb) - l->rcv_nxt; + return gap; +} + void tipc_link_set_mtu(struct tipc_link *l, int mtu) { l->mtu = mtu; @@ -807,7 +824,7 @@ void link_prepare_wakeup(struct tipc_link *l) skb_queue_walk_safe(&l->wakeupq, skb, tmp) { imp = TIPC_SKB_CB(skb)->chain_imp; - lim = l->window + l->backlog[imp].limit; + lim = l->backlog[imp].limit; pnd[imp] += TIPC_SKB_CB(skb)->chain_sz; if ((pnd[imp] + l->backlog[imp].len) >= lim) break; @@ -873,9 +890,11 @@ int tipc_link_xmit(struct tipc_link *l, struct sk_buff_head *list, struct sk_buff *skb, *_skb, *bskb; /* Match msg importance against this and all higher backlog limits: */ - for (i = imp; i <= TIPC_SYSTEM_IMPORTANCE; i++) { - if (unlikely(l->backlog[i].len >= l->backlog[i].limit)) - return link_schedule_user(l, list); + if (!skb_queue_empty(backlogq)) { + for (i = imp; i <= TIPC_SYSTEM_IMPORTANCE; i++) { + if (unlikely(l->backlog[i].len >= l->backlog[i].limit)) + return link_schedule_user(l, list); + } } if (unlikely(msg_size(hdr) > mtu)) { skb_queue_purge(list); @@ -1133,7 +1152,10 @@ int tipc_link_build_state_msg(struct tipc_link *l, struct sk_buff_head *xmitq) if (((l->rcv_nxt ^ tipc_own_addr(l->net)) & 0xf) != 0xf) return 0; l->rcv_unacked = 0; - return TIPC_LINK_SND_BC_ACK; + + /* Use snd_nxt to store peer's snd_nxt in broadcast rcv link */ + l->snd_nxt = l->rcv_nxt; + return TIPC_LINK_SND_STATE; } /* Unicast ACK */ @@ -1162,17 +1184,26 @@ void tipc_link_build_reset_msg(struct tipc_link *l, struct sk_buff_head *xmitq) } /* tipc_link_build_nack_msg: prepare link nack message for transmission + * Note that sending of broadcast NACK is coordinated among nodes, to + * reduce the risk of NACK storms towards the sender */ -static void tipc_link_build_nack_msg(struct tipc_link *l, - struct sk_buff_head *xmitq) +static int tipc_link_build_nack_msg(struct tipc_link *l, + struct sk_buff_head *xmitq) { u32 def_cnt = ++l->stats.deferred_recv; + int match1, match2; - if (link_is_bc_rcvlink(l)) - return; + if (link_is_bc_rcvlink(l)) { + match1 = def_cnt & 0xf; + match2 = tipc_own_addr(l->net) & 0xf; + if (match1 == match2) + return TIPC_LINK_SND_STATE; + return 0; + } if ((skb_queue_len(&l->deferdq) == 1) || !(def_cnt % TIPC_NACK_INTV)) tipc_link_build_proto_msg(l, STATE_MSG, 0, 0, 0, 0, xmitq); + return 0; } /* tipc_link_rcv - process TIPC packets/messages arriving from off-node @@ -1223,7 +1254,7 @@ int tipc_link_rcv(struct tipc_link *l, struct sk_buff *skb, /* Defer delivery if sequence gap */ if (unlikely(seqno != rcv_nxt)) { __tipc_skb_queue_sorted(defq, seqno, skb); - tipc_link_build_nack_msg(l, xmitq); + rc |= tipc_link_build_nack_msg(l, xmitq); break; } @@ -1234,7 +1265,7 @@ int tipc_link_rcv(struct tipc_link *l, struct sk_buff *skb, rc |= tipc_link_input(l, skb, l->inputq); if (unlikely(++l->rcv_unacked >= TIPC_MIN_LINK_WIN)) rc |= tipc_link_build_state_msg(l, xmitq); - if (unlikely(rc & ~TIPC_LINK_SND_BC_ACK)) + if (unlikely(rc & ~TIPC_LINK_SND_STATE)) break; } while ((skb = __skb_dequeue(defq))); @@ -1248,10 +1279,11 @@ static void tipc_link_build_proto_msg(struct tipc_link *l, int mtyp, bool probe, u16 rcvgap, int tolerance, int priority, struct sk_buff_head *xmitq) { + struct tipc_link *bcl = l->bc_rcvlink; struct sk_buff *skb; struct tipc_msg *hdr; struct sk_buff_head *dfq = &l->deferdq; - bool node_up = link_is_up(l->bc_rcvlink); + bool node_up = link_is_up(bcl); struct tipc_mon_state *mstate = &l->mon_state; int dlen = 0; void *data; @@ -1279,7 +1311,7 @@ static void tipc_link_build_proto_msg(struct tipc_link *l, int mtyp, bool probe, msg_set_net_plane(hdr, l->net_plane); msg_set_next_sent(hdr, l->snd_nxt); msg_set_ack(hdr, l->rcv_nxt - 1); - msg_set_bcast_ack(hdr, l->bc_rcvlink->rcv_nxt - 1); + msg_set_bcast_ack(hdr, bcl->rcv_nxt - 1); msg_set_last_bcast(hdr, l->bc_sndlink->snd_nxt - 1); msg_set_link_tolerance(hdr, tolerance); msg_set_linkprio(hdr, priority); @@ -1289,6 +1321,7 @@ static void tipc_link_build_proto_msg(struct tipc_link *l, int mtyp, bool probe, if (mtyp == STATE_MSG) { msg_set_seq_gap(hdr, rcvgap); + msg_set_bc_gap(hdr, link_bc_rcv_gap(bcl)); msg_set_probe(hdr, probe); tipc_mon_prep(l->net, data, &dlen, mstate, l->bearer_id); msg_set_size(hdr, INT_H_SIZE + dlen); @@ -1571,51 +1604,107 @@ void tipc_link_bc_init_rcv(struct tipc_link *l, struct tipc_msg *hdr) l->rcv_nxt = peers_snd_nxt; } +/* link_bc_retr eval()- check if the indicated range can be retransmitted now + * - Adjust permitted range if there is overlap with previous retransmission + */ +static bool link_bc_retr_eval(struct tipc_link *l, u16 *from, u16 *to) +{ + unsigned long elapsed = jiffies_to_msecs(jiffies - l->prev_retr); + + if (less(*to, *from)) + return false; + + /* New retransmission request */ + if ((elapsed > TIPC_BC_RETR_LIMIT) || + less(*to, l->prev_from) || more(*from, l->prev_to)) { + l->prev_from = *from; + l->prev_to = *to; + l->prev_retr = jiffies; + return true; + } + + /* Inside range of previous retransmit */ + if (!less(*from, l->prev_from) && !more(*to, l->prev_to)) + return false; + + /* Fully or partially outside previous range => exclude overlap */ + if (less(*from, l->prev_from)) { + *to = l->prev_from - 1; + l->prev_from = *from; + } + if (more(*to, l->prev_to)) { + *from = l->prev_to + 1; + l->prev_to = *to; + } + l->prev_retr = jiffies; + return true; +} + /* tipc_link_bc_sync_rcv - update rcv link according to peer's send state */ -void tipc_link_bc_sync_rcv(struct tipc_link *l, struct tipc_msg *hdr, - struct sk_buff_head *xmitq) +int tipc_link_bc_sync_rcv(struct tipc_link *l, struct tipc_msg *hdr, + struct sk_buff_head *xmitq) { + struct tipc_link *snd_l = l->bc_sndlink; u16 peers_snd_nxt = msg_bc_snd_nxt(hdr); + u16 from = msg_bcast_ack(hdr) + 1; + u16 to = from + msg_bc_gap(hdr) - 1; + int rc = 0; if (!link_is_up(l)) - return; + return rc; if (!msg_peer_node_is_up(hdr)) - return; + return rc; /* Open when peer ackowledges our bcast init msg (pkt #1) */ if (msg_ack(hdr)) l->bc_peer_is_up = true; if (!l->bc_peer_is_up) - return; + return rc; + + l->stats.recv_nacks++; /* Ignore if peers_snd_nxt goes beyond receive window */ if (more(peers_snd_nxt, l->rcv_nxt + l->window)) - return; + return rc; + + if (link_bc_retr_eval(snd_l, &from, &to)) + rc = tipc_link_retrans(snd_l, from, to, xmitq); + + l->snd_nxt = peers_snd_nxt; + if (link_bc_rcv_gap(l)) + rc |= TIPC_LINK_SND_STATE; + + /* Return now if sender supports nack via STATE messages */ + if (l->peer_caps & TIPC_BCAST_STATE_NACK) + return rc; + + /* Otherwise, be backwards compatible */ if (!more(peers_snd_nxt, l->rcv_nxt)) { l->nack_state = BC_NACK_SND_CONDITIONAL; - return; + return 0; } /* Don't NACK if one was recently sent or peeked */ if (l->nack_state == BC_NACK_SND_SUPPRESS) { l->nack_state = BC_NACK_SND_UNCONDITIONAL; - return; + return 0; } /* Conditionally delay NACK sending until next synch rcv */ if (l->nack_state == BC_NACK_SND_CONDITIONAL) { l->nack_state = BC_NACK_SND_UNCONDITIONAL; if ((peers_snd_nxt - l->rcv_nxt) < TIPC_MIN_LINK_WIN) - return; + return 0; } /* Send NACK now but suppress next one */ tipc_link_build_bc_proto_msg(l, true, peers_snd_nxt, xmitq); l->nack_state = BC_NACK_SND_SUPPRESS; + return 0; } void tipc_link_bc_ack_rcv(struct tipc_link *l, u16 acked, @@ -1652,6 +1741,8 @@ void tipc_link_bc_ack_rcv(struct tipc_link *l, u16 acked, } /* tipc_link_bc_nack_rcv(): receive broadcast nack message + * This function is here for backwards compatibility, since + * no BCAST_PROTOCOL/STATE messages occur from TIPC v2.5. */ int tipc_link_bc_nack_rcv(struct tipc_link *l, struct sk_buff *skb, struct sk_buff_head *xmitq) @@ -1692,10 +1783,10 @@ void tipc_link_set_queue_limits(struct tipc_link *l, u32 win) int max_bulk = TIPC_MAX_PUBLICATIONS / (l->mtu / ITEM_SIZE); l->window = win; - l->backlog[TIPC_LOW_IMPORTANCE].limit = win / 2; - l->backlog[TIPC_MEDIUM_IMPORTANCE].limit = win; - l->backlog[TIPC_HIGH_IMPORTANCE].limit = win / 2 * 3; - l->backlog[TIPC_CRITICAL_IMPORTANCE].limit = win * 2; + l->backlog[TIPC_LOW_IMPORTANCE].limit = max_t(u16, 50, win); + l->backlog[TIPC_MEDIUM_IMPORTANCE].limit = max_t(u16, 100, win * 2); + l->backlog[TIPC_HIGH_IMPORTANCE].limit = max_t(u16, 150, win * 3); + l->backlog[TIPC_CRITICAL_IMPORTANCE].limit = max_t(u16, 200, win * 4); l->backlog[TIPC_SYSTEM_IMPORTANCE].limit = max_bulk; } diff --git a/net/tipc/link.h b/net/tipc/link.h index d7e9d42fcb2d..d1bd1787a768 100644 --- a/net/tipc/link.h +++ b/net/tipc/link.h @@ -63,7 +63,7 @@ enum { enum { TIPC_LINK_UP_EVT = 1, TIPC_LINK_DOWN_EVT = (1 << 1), - TIPC_LINK_SND_BC_ACK = (1 << 2) + TIPC_LINK_SND_STATE = (1 << 2) }; /* Starting value for maximum packet size negotiation on unicast links @@ -138,8 +138,8 @@ void tipc_link_bc_ack_rcv(struct tipc_link *l, u16 acked, void tipc_link_build_bc_sync_msg(struct tipc_link *l, struct sk_buff_head *xmitq); void tipc_link_bc_init_rcv(struct tipc_link *l, struct tipc_msg *hdr); -void tipc_link_bc_sync_rcv(struct tipc_link *l, struct tipc_msg *hdr, - struct sk_buff_head *xmitq); +int tipc_link_bc_sync_rcv(struct tipc_link *l, struct tipc_msg *hdr, + struct sk_buff_head *xmitq); int tipc_link_bc_nack_rcv(struct tipc_link *l, struct sk_buff *skb, struct sk_buff_head *xmitq); #endif diff --git a/net/tipc/monitor.c b/net/tipc/monitor.c index b62caa1c770c..ed97a5876ebe 100644 --- a/net/tipc/monitor.c +++ b/net/tipc/monitor.c @@ -728,12 +728,13 @@ int tipc_nl_add_monitor_peer(struct net *net, struct tipc_nl_msg *msg, u32 bearer_id, u32 *prev_node) { struct tipc_monitor *mon = tipc_monitor(net, bearer_id); - struct tipc_peer *peer = mon->self; + struct tipc_peer *peer; if (!mon) return -EINVAL; read_lock_bh(&mon->lock); + peer = mon->self; do { if (*prev_node) { if (peer->addr == *prev_node) diff --git a/net/tipc/msg.h b/net/tipc/msg.h index 7cf52fb39bee..c3832cdf2278 100644 --- a/net/tipc/msg.h +++ b/net/tipc/msg.h @@ -719,6 +719,16 @@ static inline char *msg_media_addr(struct tipc_msg *m) return (char *)&m->hdr[TIPC_MEDIA_INFO_OFFSET]; } +static inline u32 msg_bc_gap(struct tipc_msg *m) +{ + return msg_bits(m, 8, 0, 0x3ff); +} + +static inline void msg_set_bc_gap(struct tipc_msg *m, u32 n) +{ + msg_set_bits(m, 8, 0, 0x3ff, n); +} + /* * Word 9 */ diff --git a/net/tipc/net.h b/net/tipc/net.h index 77a7a118911d..c7c254902873 100644 --- a/net/tipc/net.h +++ b/net/tipc/net.h @@ -39,6 +39,8 @@ #include <net/genetlink.h> +extern const struct nla_policy tipc_nl_net_policy[]; + int tipc_net_start(struct net *net, u32 addr); void tipc_net_stop(struct net *net); diff --git a/net/tipc/netlink.c b/net/tipc/netlink.c index a84daec0afe9..3200059d14b2 100644 --- a/net/tipc/netlink.c +++ b/net/tipc/netlink.c @@ -41,6 +41,7 @@ #include "link.h" #include "node.h" #include "net.h" +#include "udp_media.h" #include <net/genetlink.h> static const struct nla_policy tipc_nl_policy[TIPC_NLA_MAX + 1] = { @@ -161,6 +162,11 @@ static const struct genl_ops tipc_genl_v2_ops[] = { .policy = tipc_nl_policy, }, { + .cmd = TIPC_NL_BEARER_ADD, + .doit = tipc_nl_bearer_add, + .policy = tipc_nl_policy, + }, + { .cmd = TIPC_NL_BEARER_SET, .doit = tipc_nl_bearer_set, .policy = tipc_nl_policy, @@ -238,6 +244,18 @@ static const struct genl_ops tipc_genl_v2_ops[] = { .dumpit = tipc_nl_node_dump_monitor_peer, .policy = tipc_nl_policy, }, + { + .cmd = TIPC_NL_PEER_REMOVE, + .doit = tipc_nl_peer_rm, + .policy = tipc_nl_policy, + }, +#ifdef CONFIG_TIPC_MEDIA_UDP + { + .cmd = TIPC_NL_UDP_GET_REMOTEIP, + .dumpit = tipc_udp_nl_dump_remoteip, + .policy = tipc_nl_policy, + }, +#endif }; int tipc_nlmsg_parse(const struct nlmsghdr *nlh, struct nlattr ***attr) diff --git a/net/tipc/node.c b/net/tipc/node.c index 21974191e425..7ef14e2d2356 100644 --- a/net/tipc/node.c +++ b/net/tipc/node.c @@ -1262,6 +1262,34 @@ void tipc_node_broadcast(struct net *net, struct sk_buff *skb) kfree_skb(skb); } +static void tipc_node_bc_sync_rcv(struct tipc_node *n, struct tipc_msg *hdr, + int bearer_id, struct sk_buff_head *xmitq) +{ + struct tipc_link *ucl; + int rc; + + rc = tipc_bcast_sync_rcv(n->net, n->bc_entry.link, hdr); + + if (rc & TIPC_LINK_DOWN_EVT) { + tipc_bearer_reset_all(n->net); + return; + } + + if (!(rc & TIPC_LINK_SND_STATE)) + return; + + /* If probe message, a STATE response will be sent anyway */ + if (msg_probe(hdr)) + return; + + /* Produce a STATE message carrying broadcast NACK */ + tipc_node_read_lock(n); + ucl = n->links[bearer_id].link; + if (ucl) + tipc_link_build_state_msg(ucl, xmitq); + tipc_node_read_unlock(n); +} + /** * tipc_node_bc_rcv - process TIPC broadcast packet arriving from off-node * @net: the applicable net namespace @@ -1298,7 +1326,7 @@ static void tipc_node_bc_rcv(struct net *net, struct sk_buff *skb, int bearer_id rc = tipc_bcast_rcv(net, be->link, skb); /* Broadcast ACKs are sent on a unicast link */ - if (rc & TIPC_LINK_SND_BC_ACK) { + if (rc & TIPC_LINK_SND_STATE) { tipc_node_read_lock(n); tipc_link_build_state_msg(le->link, &xmitq); tipc_node_read_unlock(n); @@ -1505,7 +1533,7 @@ void tipc_rcv(struct net *net, struct sk_buff *skb, struct tipc_bearer *b) /* Ensure broadcast reception is in synch with peer's send state */ if (unlikely(usr == LINK_PROTOCOL)) - tipc_bcast_sync_rcv(net, n->bc_entry.link, hdr); + tipc_node_bc_sync_rcv(n, hdr, bearer_id, &xmitq); else if (unlikely(tipc_link_acked(n->bc_entry.link) != bc_ack)) tipc_bcast_ack_rcv(net, n->bc_entry.link, bc_ack); @@ -1553,6 +1581,69 @@ discard: kfree_skb(skb); } +int tipc_nl_peer_rm(struct sk_buff *skb, struct genl_info *info) +{ + struct net *net = sock_net(skb->sk); + struct tipc_net *tn = net_generic(net, tipc_net_id); + struct nlattr *attrs[TIPC_NLA_NET_MAX + 1]; + struct tipc_node *peer; + u32 addr; + int err; + int i; + + /* We identify the peer by its net */ + if (!info->attrs[TIPC_NLA_NET]) + return -EINVAL; + + err = nla_parse_nested(attrs, TIPC_NLA_NET_MAX, + info->attrs[TIPC_NLA_NET], + tipc_nl_net_policy); + if (err) + return err; + + if (!attrs[TIPC_NLA_NET_ADDR]) + return -EINVAL; + + addr = nla_get_u32(attrs[TIPC_NLA_NET_ADDR]); + + if (in_own_node(net, addr)) + return -ENOTSUPP; + + spin_lock_bh(&tn->node_list_lock); + peer = tipc_node_find(net, addr); + if (!peer) { + spin_unlock_bh(&tn->node_list_lock); + return -ENXIO; + } + + tipc_node_write_lock(peer); + if (peer->state != SELF_DOWN_PEER_DOWN && + peer->state != SELF_DOWN_PEER_LEAVING) { + tipc_node_write_unlock(peer); + err = -EBUSY; + goto err_out; + } + + for (i = 0; i < MAX_BEARERS; i++) { + struct tipc_link_entry *le = &peer->links[i]; + + if (le->link) { + kfree(le->link); + le->link = NULL; + peer->link_cnt--; + } + } + tipc_node_write_unlock(peer); + tipc_node_delete(peer); + + err = 0; +err_out: + tipc_node_put(peer); + spin_unlock_bh(&tn->node_list_lock); + + return err; +} + int tipc_nl_node_dump(struct sk_buff *skb, struct netlink_callback *cb) { int err; diff --git a/net/tipc/node.h b/net/tipc/node.h index d69fdfcc0ec9..39ef54c1f2ad 100644 --- a/net/tipc/node.h +++ b/net/tipc/node.h @@ -1,7 +1,7 @@ /* * net/tipc/node.h: Include file for TIPC node management routines * - * Copyright (c) 2000-2006, 2014-2015, Ericsson AB + * Copyright (c) 2000-2006, 2014-2016, Ericsson AB * Copyright (c) 2005, 2010-2014, Wind River Systems * All rights reserved. * @@ -45,11 +45,14 @@ /* Optional capabilities supported by this code version */ enum { - TIPC_BCAST_SYNCH = (1 << 1), - TIPC_BLOCK_FLOWCTL = (2 << 1) + TIPC_BCAST_SYNCH = (1 << 1), + TIPC_BCAST_STATE_NACK = (1 << 2), + TIPC_BLOCK_FLOWCTL = (1 << 3) }; -#define TIPC_NODE_CAPABILITIES (TIPC_BCAST_SYNCH | TIPC_BLOCK_FLOWCTL) +#define TIPC_NODE_CAPABILITIES (TIPC_BCAST_SYNCH | \ + TIPC_BCAST_STATE_NACK | \ + TIPC_BLOCK_FLOWCTL) #define INVALID_BEARER_ID -1 void tipc_node_stop(struct net *net); @@ -77,6 +80,7 @@ int tipc_nl_node_dump_link(struct sk_buff *skb, struct netlink_callback *cb); int tipc_nl_node_reset_link_stats(struct sk_buff *skb, struct genl_info *info); int tipc_nl_node_get_link(struct sk_buff *skb, struct genl_info *info); int tipc_nl_node_set_link(struct sk_buff *skb, struct genl_info *info); +int tipc_nl_peer_rm(struct sk_buff *skb, struct genl_info *info); int tipc_nl_node_set_monitor(struct sk_buff *skb, struct genl_info *info); int tipc_nl_node_get_monitor(struct sk_buff *skb, struct genl_info *info); diff --git a/net/tipc/socket.c b/net/tipc/socket.c index c49b8df438cb..f9f5f3c3dab5 100644 --- a/net/tipc/socket.c +++ b/net/tipc/socket.c @@ -2180,7 +2180,8 @@ restart: TIPC_CONN_MSG, SHORT_H_SIZE, 0, dnode, onode, dport, oport, TIPC_CONN_SHUTDOWN); - tipc_node_xmit_skb(net, skb, dnode, tsk->portid); + if (skb) + tipc_node_xmit_skb(net, skb, dnode, tsk->portid); } tsk->connected = 0; sock->state = SS_DISCONNECTING; diff --git a/net/tipc/udp_media.c b/net/tipc/udp_media.c index b016c011970b..dd274687a53d 100644 --- a/net/tipc/udp_media.c +++ b/net/tipc/udp_media.c @@ -49,6 +49,7 @@ #include "core.h" #include "bearer.h" #include "netlink.h" +#include "msg.h" /* IANA assigned UDP port */ #define UDP_PORT_DEFAULT 6118 @@ -70,6 +71,13 @@ struct udp_media_addr { }; }; +/* struct udp_replicast - container for UDP remote addresses */ +struct udp_replicast { + struct udp_media_addr addr; + struct rcu_head rcu; + struct list_head list; +}; + /** * struct udp_bearer - ip/udp bearer data structure * @bearer: associated generic tipc bearer @@ -82,8 +90,20 @@ struct udp_bearer { struct socket *ubsock; u32 ifindex; struct work_struct work; + struct udp_replicast rcast; }; +static int tipc_udp_is_mcast_addr(struct udp_media_addr *addr) +{ + if (ntohs(addr->proto) == ETH_P_IP) + return ipv4_is_multicast(addr->ipv4.s_addr); +#if IS_ENABLED(CONFIG_IPV6) + else + return ipv6_addr_is_multicast(&addr->ipv6); +#endif + return 0; +} + /* udp_media_addr_set - convert a ip/udp address to a TIPC media address */ static void tipc_udp_media_addr_set(struct tipc_media_addr *addr, struct udp_media_addr *ua) @@ -91,15 +111,9 @@ static void tipc_udp_media_addr_set(struct tipc_media_addr *addr, memset(addr, 0, sizeof(struct tipc_media_addr)); addr->media_id = TIPC_MEDIA_TYPE_UDP; memcpy(addr->value, ua, sizeof(struct udp_media_addr)); - if (ntohs(ua->proto) == ETH_P_IP) { - if (ipv4_is_multicast(ua->ipv4.s_addr)) - addr->broadcast = 1; - } else if (ntohs(ua->proto) == ETH_P_IPV6) { - if (ipv6_addr_type(&ua->ipv6) & IPV6_ADDR_MULTICAST) - addr->broadcast = 1; - } else { - pr_err("Invalid UDP media address\n"); - } + + if (tipc_udp_is_mcast_addr(ua)) + addr->broadcast = 1; } /* tipc_udp_addr2str - convert ip/udp address to string */ @@ -140,28 +154,13 @@ static int tipc_udp_addr2msg(char *msg, struct tipc_media_addr *a) } /* tipc_send_msg - enqueue a send request */ -static int tipc_udp_send_msg(struct net *net, struct sk_buff *skb, - struct tipc_bearer *b, - struct tipc_media_addr *dest) +static int tipc_udp_xmit(struct net *net, struct sk_buff *skb, + struct udp_bearer *ub, struct udp_media_addr *src, + struct udp_media_addr *dst) { int ttl, err = 0; - struct udp_bearer *ub; - struct udp_media_addr *dst = (struct udp_media_addr *)&dest->value; - struct udp_media_addr *src = (struct udp_media_addr *)&b->addr.value; struct rtable *rt; - if (skb_headroom(skb) < UDP_MIN_HEADROOM) { - err = pskb_expand_head(skb, UDP_MIN_HEADROOM, 0, GFP_ATOMIC); - if (err) - goto tx_error; - } - - skb_set_inner_protocol(skb, htons(ETH_P_TIPC)); - ub = rcu_dereference_rtnl(b->media_ptr); - if (!ub) { - err = -ENODEV; - goto tx_error; - } if (dst->proto == htons(ETH_P_IP)) { struct flowi4 fl = { .daddr = dst->ipv4.s_addr, @@ -207,29 +206,178 @@ tx_error: return err; } +static int tipc_udp_send_msg(struct net *net, struct sk_buff *skb, + struct tipc_bearer *b, + struct tipc_media_addr *addr) +{ + struct udp_media_addr *src = (struct udp_media_addr *)&b->addr.value; + struct udp_media_addr *dst = (struct udp_media_addr *)&addr->value; + struct udp_replicast *rcast; + struct udp_bearer *ub; + int err = 0; + + if (skb_headroom(skb) < UDP_MIN_HEADROOM) { + err = pskb_expand_head(skb, UDP_MIN_HEADROOM, 0, GFP_ATOMIC); + if (err) + goto out; + } + + skb_set_inner_protocol(skb, htons(ETH_P_TIPC)); + ub = rcu_dereference_rtnl(b->media_ptr); + if (!ub) { + err = -ENODEV; + goto out; + } + + if (!addr->broadcast || list_empty(&ub->rcast.list)) + return tipc_udp_xmit(net, skb, ub, src, dst); + + /* Replicast, send an skb to each configured IP address */ + list_for_each_entry_rcu(rcast, &ub->rcast.list, list) { + struct sk_buff *_skb; + + _skb = pskb_copy(skb, GFP_ATOMIC); + if (!_skb) { + err = -ENOMEM; + goto out; + } + + err = tipc_udp_xmit(net, _skb, ub, src, &rcast->addr); + if (err) { + kfree_skb(_skb); + goto out; + } + } + err = 0; +out: + kfree_skb(skb); + return err; +} + +static bool tipc_udp_is_known_peer(struct tipc_bearer *b, + struct udp_media_addr *addr) +{ + struct udp_replicast *rcast, *tmp; + struct udp_bearer *ub; + + ub = rcu_dereference_rtnl(b->media_ptr); + if (!ub) { + pr_err_ratelimited("UDP bearer instance not found\n"); + return false; + } + + list_for_each_entry_safe(rcast, tmp, &ub->rcast.list, list) { + if (!memcmp(&rcast->addr, addr, sizeof(struct udp_media_addr))) + return true; + } + + return false; +} + +static int tipc_udp_rcast_add(struct tipc_bearer *b, + struct udp_media_addr *addr) +{ + struct udp_replicast *rcast; + struct udp_bearer *ub; + + ub = rcu_dereference_rtnl(b->media_ptr); + if (!ub) + return -ENODEV; + + rcast = kmalloc(sizeof(*rcast), GFP_ATOMIC); + if (!rcast) + return -ENOMEM; + + memcpy(&rcast->addr, addr, sizeof(struct udp_media_addr)); + + if (ntohs(addr->proto) == ETH_P_IP) + pr_info("New replicast peer: %pI4\n", &rcast->addr.ipv4); +#if IS_ENABLED(CONFIG_IPV6) + else if (ntohs(addr->proto) == ETH_P_IPV6) + pr_info("New replicast peer: %pI6\n", &rcast->addr.ipv6); +#endif + + list_add_rcu(&rcast->list, &ub->rcast.list); + return 0; +} + +static int tipc_udp_rcast_disc(struct tipc_bearer *b, struct sk_buff *skb) +{ + struct udp_media_addr src = {0}; + struct udp_media_addr *dst; + + dst = (struct udp_media_addr *)&b->bcast_addr.value; + if (tipc_udp_is_mcast_addr(dst)) + return 0; + + src.port = udp_hdr(skb)->source; + + if (ip_hdr(skb)->version == 4) { + struct iphdr *iphdr = ip_hdr(skb); + + src.proto = htons(ETH_P_IP); + src.ipv4.s_addr = iphdr->saddr; + if (ipv4_is_multicast(iphdr->daddr)) + return 0; +#if IS_ENABLED(CONFIG_IPV6) + } else if (ip_hdr(skb)->version == 6) { + struct ipv6hdr *iphdr = ipv6_hdr(skb); + + src.proto = htons(ETH_P_IPV6); + src.ipv6 = iphdr->saddr; + if (ipv6_addr_is_multicast(&iphdr->daddr)) + return 0; +#endif + } else { + return 0; + } + + if (likely(tipc_udp_is_known_peer(b, &src))) + return 0; + + return tipc_udp_rcast_add(b, &src); +} + /* tipc_udp_recv - read data from bearer socket */ static int tipc_udp_recv(struct sock *sk, struct sk_buff *skb) { struct udp_bearer *ub; struct tipc_bearer *b; + struct tipc_msg *hdr; + int err; ub = rcu_dereference_sk_user_data(sk); if (!ub) { pr_err_ratelimited("Failed to get UDP bearer reference"); - kfree_skb(skb); - return 0; + goto out; } - skb_pull(skb, sizeof(struct udphdr)); + hdr = buf_msg(skb); + rcu_read_lock(); b = rcu_dereference_rtnl(ub->bearer); + if (!b) + goto rcu_out; - if (b) { + if (b && test_bit(0, &b->up)) { tipc_rcv(sock_net(sk), skb, b); rcu_read_unlock(); return 0; } + + if (unlikely(msg_user(hdr) == LINK_CONFIG)) { + err = tipc_udp_rcast_disc(b, skb); + if (err) + goto rcu_out; + } + + tipc_rcv(sock_net(sk), skb, b); rcu_read_unlock(); + return 0; + +rcu_out: + rcu_read_unlock(); +out: kfree_skb(skb); return 0; } @@ -241,15 +389,11 @@ static int enable_mcast(struct udp_bearer *ub, struct udp_media_addr *remote) struct sock *sk = ub->ubsock->sk; if (ntohs(remote->proto) == ETH_P_IP) { - if (!ipv4_is_multicast(remote->ipv4.s_addr)) - return 0; mreqn.imr_multiaddr = remote->ipv4; mreqn.imr_ifindex = ub->ifindex; err = ip_mc_join_group(sk, &mreqn); #if IS_ENABLED(CONFIG_IPV6) } else { - if (!ipv6_addr_is_multicast(&remote->ipv6)) - return 0; err = ipv6_stub->ipv6_sock_mc_join(sk, ub->ifindex, &remote->ipv6); #endif @@ -257,75 +401,234 @@ static int enable_mcast(struct udp_bearer *ub, struct udp_media_addr *remote) return err; } -/** - * parse_options - build local/remote addresses from configuration - * @attrs: netlink config data - * @ub: UDP bearer instance - * @local: local bearer IP address/port - * @remote: peer or multicast IP/port - */ -static int parse_options(struct nlattr *attrs[], struct udp_bearer *ub, - struct udp_media_addr *local, - struct udp_media_addr *remote) +static int __tipc_nl_add_udp_addr(struct sk_buff *skb, + struct udp_media_addr *addr, int nla_t) { - struct nlattr *opts[TIPC_NLA_UDP_MAX + 1]; - struct sockaddr_storage sa_local, sa_remote; + if (ntohs(addr->proto) == ETH_P_IP) { + struct sockaddr_in ip4; - if (!attrs[TIPC_NLA_BEARER_UDP_OPTS]) - goto err; - if (nla_parse_nested(opts, TIPC_NLA_UDP_MAX, - attrs[TIPC_NLA_BEARER_UDP_OPTS], - tipc_nl_udp_policy)) - goto err; - if (opts[TIPC_NLA_UDP_LOCAL] && opts[TIPC_NLA_UDP_REMOTE]) { - nla_memcpy(&sa_local, opts[TIPC_NLA_UDP_LOCAL], - sizeof(sa_local)); - nla_memcpy(&sa_remote, opts[TIPC_NLA_UDP_REMOTE], - sizeof(sa_remote)); + ip4.sin_family = AF_INET; + ip4.sin_port = addr->port; + ip4.sin_addr.s_addr = addr->ipv4.s_addr; + if (nla_put(skb, nla_t, sizeof(ip4), &ip4)) + return -EMSGSIZE; + +#if IS_ENABLED(CONFIG_IPV6) + } else if (ntohs(addr->proto) == ETH_P_IPV6) { + struct sockaddr_in6 ip6; + + ip6.sin6_family = AF_INET6; + ip6.sin6_port = addr->port; + memcpy(&ip6.sin6_addr, &addr->ipv6, sizeof(struct in6_addr)); + if (nla_put(skb, nla_t, sizeof(ip6), &ip6)) + return -EMSGSIZE; +#endif + } + + return 0; +} + +int tipc_udp_nl_dump_remoteip(struct sk_buff *skb, struct netlink_callback *cb) +{ + u32 bid = cb->args[0]; + u32 skip_cnt = cb->args[1]; + u32 portid = NETLINK_CB(cb->skb).portid; + struct udp_replicast *rcast, *tmp; + struct tipc_bearer *b; + struct udp_bearer *ub; + void *hdr; + int err; + int i; + + if (!bid && !skip_cnt) { + struct net *net = sock_net(skb->sk); + struct nlattr *battrs[TIPC_NLA_BEARER_MAX + 1]; + struct nlattr **attrs; + char *bname; + + err = tipc_nlmsg_parse(cb->nlh, &attrs); + if (err) + return err; + + if (!attrs[TIPC_NLA_BEARER]) + return -EINVAL; + + err = nla_parse_nested(battrs, TIPC_NLA_BEARER_MAX, + attrs[TIPC_NLA_BEARER], + tipc_nl_bearer_policy); + if (err) + return err; + + if (!battrs[TIPC_NLA_BEARER_NAME]) + return -EINVAL; + + bname = nla_data(battrs[TIPC_NLA_BEARER_NAME]); + + rtnl_lock(); + b = tipc_bearer_find(net, bname); + if (!b) { + rtnl_unlock(); + return -EINVAL; + } + bid = b->identity; } else { -err: - pr_err("Invalid UDP bearer configuration"); + struct net *net = sock_net(skb->sk); + struct tipc_net *tn = net_generic(net, tipc_net_id); + + rtnl_lock(); + b = rtnl_dereference(tn->bearer_list[bid]); + if (!b) { + rtnl_unlock(); + return -EINVAL; + } + } + + ub = rcu_dereference_rtnl(b->media_ptr); + if (!ub) { + rtnl_unlock(); return -EINVAL; } - if ((sa_local.ss_family & sa_remote.ss_family) == AF_INET) { - struct sockaddr_in *ip4; - - ip4 = (struct sockaddr_in *)&sa_local; - local->proto = htons(ETH_P_IP); - local->port = ip4->sin_port; - local->ipv4.s_addr = ip4->sin_addr.s_addr; - - ip4 = (struct sockaddr_in *)&sa_remote; - remote->proto = htons(ETH_P_IP); - remote->port = ip4->sin_port; - remote->ipv4.s_addr = ip4->sin_addr.s_addr; + + i = 0; + list_for_each_entry_safe(rcast, tmp, &ub->rcast.list, list) { + if (i < skip_cnt) + goto count; + + hdr = genlmsg_put(skb, portid, cb->nlh->nlmsg_seq, + &tipc_genl_family, NLM_F_MULTI, + TIPC_NL_BEARER_GET); + if (!hdr) + goto done; + + err = __tipc_nl_add_udp_addr(skb, &rcast->addr, + TIPC_NLA_UDP_REMOTE); + if (err) { + genlmsg_cancel(skb, hdr); + goto done; + } + genlmsg_end(skb, hdr); +count: + i++; + } +done: + rtnl_unlock(); + cb->args[0] = bid; + cb->args[1] = i; + + return skb->len; +} + +int tipc_udp_nl_add_bearer_data(struct tipc_nl_msg *msg, struct tipc_bearer *b) +{ + struct udp_media_addr *src = (struct udp_media_addr *)&b->addr.value; + struct udp_media_addr *dst; + struct udp_bearer *ub; + struct nlattr *nest; + + ub = rcu_dereference_rtnl(b->media_ptr); + if (!ub) + return -ENODEV; + + nest = nla_nest_start(msg->skb, TIPC_NLA_BEARER_UDP_OPTS); + if (!nest) + goto msg_full; + + if (__tipc_nl_add_udp_addr(msg->skb, src, TIPC_NLA_UDP_LOCAL)) + goto msg_full; + + dst = (struct udp_media_addr *)&b->bcast_addr.value; + if (__tipc_nl_add_udp_addr(msg->skb, dst, TIPC_NLA_UDP_REMOTE)) + goto msg_full; + + if (!list_empty(&ub->rcast.list)) { + if (nla_put_flag(msg->skb, TIPC_NLA_UDP_MULTI_REMOTEIP)) + goto msg_full; + } + + nla_nest_end(msg->skb, nest); + return 0; +msg_full: + nla_nest_cancel(msg->skb, nest); + return -EMSGSIZE; +} + +/** + * tipc_parse_udp_addr - build udp media address from netlink data + * @nlattr: netlink attribute containing sockaddr storage aligned address + * @addr: tipc media address to fill with address, port and protocol type + * @scope_id: IPv6 scope id pointer, not NULL indicates it's required + */ + +static int tipc_parse_udp_addr(struct nlattr *nla, struct udp_media_addr *addr, + u32 *scope_id) +{ + struct sockaddr_storage sa; + + nla_memcpy(&sa, nla, sizeof(sa)); + if (sa.ss_family == AF_INET) { + struct sockaddr_in *ip4 = (struct sockaddr_in *)&sa; + + addr->proto = htons(ETH_P_IP); + addr->port = ip4->sin_port; + addr->ipv4.s_addr = ip4->sin_addr.s_addr; return 0; #if IS_ENABLED(CONFIG_IPV6) - } else if ((sa_local.ss_family & sa_remote.ss_family) == AF_INET6) { - int atype; - struct sockaddr_in6 *ip6; + } else if (sa.ss_family == AF_INET6) { + struct sockaddr_in6 *ip6 = (struct sockaddr_in6 *)&sa; - ip6 = (struct sockaddr_in6 *)&sa_local; - atype = ipv6_addr_type(&ip6->sin6_addr); - if (__ipv6_addr_needs_scope_id(atype) && !ip6->sin6_scope_id) - return -EINVAL; + addr->proto = htons(ETH_P_IPV6); + addr->port = ip6->sin6_port; + memcpy(&addr->ipv6, &ip6->sin6_addr, sizeof(struct in6_addr)); + + /* Scope ID is only interesting for local addresses */ + if (scope_id) { + int atype; - local->proto = htons(ETH_P_IPV6); - local->port = ip6->sin6_port; - memcpy(&local->ipv6, &ip6->sin6_addr, sizeof(struct in6_addr)); - ub->ifindex = ip6->sin6_scope_id; + atype = ipv6_addr_type(&ip6->sin6_addr); + if (__ipv6_addr_needs_scope_id(atype) && + !ip6->sin6_scope_id) { + return -EINVAL; + } + + *scope_id = ip6->sin6_scope_id ? : 0; + } - ip6 = (struct sockaddr_in6 *)&sa_remote; - remote->proto = htons(ETH_P_IPV6); - remote->port = ip6->sin6_port; - memcpy(&remote->ipv6, &ip6->sin6_addr, sizeof(struct in6_addr)); return 0; #endif } return -EADDRNOTAVAIL; } +int tipc_udp_nl_bearer_add(struct tipc_bearer *b, struct nlattr *attr) +{ + int err; + struct udp_media_addr addr = {0}; + struct nlattr *opts[TIPC_NLA_UDP_MAX + 1]; + struct udp_media_addr *dst; + + if (nla_parse_nested(opts, TIPC_NLA_UDP_MAX, attr, tipc_nl_udp_policy)) + return -EINVAL; + + if (!opts[TIPC_NLA_UDP_REMOTE]) + return -EINVAL; + + err = tipc_parse_udp_addr(opts[TIPC_NLA_UDP_REMOTE], &addr, NULL); + if (err) + return err; + + dst = (struct udp_media_addr *)&b->bcast_addr.value; + if (tipc_udp_is_mcast_addr(dst)) { + pr_err("Can't add remote ip to TIPC UDP multicast bearer\n"); + return -EINVAL; + } + + if (tipc_udp_is_known_peer(b, &addr)) + return 0; + + return tipc_udp_rcast_add(b, &addr); +} + /** * tipc_udp_enable - callback to create a new udp bearer instance * @net: network namespace @@ -340,18 +643,37 @@ static int tipc_udp_enable(struct net *net, struct tipc_bearer *b, { int err = -EINVAL; struct udp_bearer *ub; - struct udp_media_addr *remote; + struct udp_media_addr remote = {0}; struct udp_media_addr local = {0}; struct udp_port_cfg udp_conf = {0}; struct udp_tunnel_sock_cfg tuncfg = {NULL}; + struct nlattr *opts[TIPC_NLA_UDP_MAX + 1]; ub = kzalloc(sizeof(*ub), GFP_ATOMIC); if (!ub) return -ENOMEM; - remote = (struct udp_media_addr *)&b->bcast_addr.value; - memset(remote, 0, sizeof(struct udp_media_addr)); - err = parse_options(attrs, ub, &local, remote); + INIT_LIST_HEAD(&ub->rcast.list); + + if (!attrs[TIPC_NLA_BEARER_UDP_OPTS]) + goto err; + + if (nla_parse_nested(opts, TIPC_NLA_UDP_MAX, + attrs[TIPC_NLA_BEARER_UDP_OPTS], + tipc_nl_udp_policy)) + goto err; + + if (!opts[TIPC_NLA_UDP_LOCAL] || !opts[TIPC_NLA_UDP_REMOTE]) { + pr_err("Invalid UDP bearer configuration"); + return -EINVAL; + } + + err = tipc_parse_udp_addr(opts[TIPC_NLA_UDP_LOCAL], &local, + &ub->ifindex); + if (err) + goto err; + + err = tipc_parse_udp_addr(opts[TIPC_NLA_UDP_REMOTE], &remote, NULL); if (err) goto err; @@ -396,10 +718,22 @@ static int tipc_udp_enable(struct net *net, struct tipc_bearer *b, tuncfg.encap_destroy = NULL; setup_udp_tunnel_sock(net, ub->ubsock, &tuncfg); - if (enable_mcast(ub, remote)) + /** + * The bcast media address port is used for all peers and the ip + * is used if it's a multicast address. + */ + memcpy(&b->bcast_addr.value, &remote, sizeof(remote)); + if (tipc_udp_is_mcast_addr(&remote)) + err = enable_mcast(ub, &remote); + else + err = tipc_udp_rcast_add(b, &remote); + if (err) goto err; + return 0; err: + if (ub->ubsock) + udp_tunnel_sock_release(ub->ubsock); kfree(ub); return err; } @@ -408,6 +742,12 @@ err: static void cleanup_bearer(struct work_struct *work) { struct udp_bearer *ub = container_of(work, struct udp_bearer, work); + struct udp_replicast *rcast, *tmp; + + list_for_each_entry_safe(rcast, tmp, &ub->rcast.list, list) { + list_del_rcu(&rcast->list); + kfree_rcu(rcast, rcu); + } if (ub->ubsock) udp_tunnel_sock_release(ub->ubsock); diff --git a/net/tipc/udp_media.h b/net/tipc/udp_media.h new file mode 100644 index 000000000000..281bbae87726 --- /dev/null +++ b/net/tipc/udp_media.h @@ -0,0 +1,46 @@ +/* + * net/tipc/udp_media.h: Include file for UDP bearer media + * + * Copyright (c) 1996-2006, 2013-2016, Ericsson AB + * Copyright (c) 2005, 2010-2011, Wind River Systems + * All rights reserved. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions are met: + * + * 1. Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * 2. Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in the + * documentation and/or other materials provided with the distribution. + * 3. Neither the names of the copyright holders nor the names of its + * contributors may be used to endorse or promote products derived from + * this software without specific prior written permission. + * + * Alternatively, this software may be distributed under the terms of the + * GNU General Public License ("GPL") version 2 as published by the Free + * Software Foundation. + * + * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" + * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE + * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE + * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE + * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR + * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF + * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS + * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN + * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) + * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE + * POSSIBILITY OF SUCH DAMAGE. + */ + +#ifdef CONFIG_TIPC_MEDIA_UDP +#ifndef _TIPC_UDP_MEDIA_H +#define _TIPC_UDP_MEDIA_H + +int tipc_udp_nl_bearer_add(struct tipc_bearer *b, struct nlattr *attr); +int tipc_udp_nl_add_bearer_data(struct tipc_nl_msg *msg, struct tipc_bearer *b); +int tipc_udp_nl_dump_remoteip(struct sk_buff *skb, struct netlink_callback *cb); + +#endif +#endif diff --git a/net/vmw_vsock/Kconfig b/net/vmw_vsock/Kconfig index 14810abedc2e..8831e7c42167 100644 --- a/net/vmw_vsock/Kconfig +++ b/net/vmw_vsock/Kconfig @@ -26,3 +26,23 @@ config VMWARE_VMCI_VSOCKETS To compile this driver as a module, choose M here: the module will be called vmw_vsock_vmci_transport. If unsure, say N. + +config VIRTIO_VSOCKETS + tristate "virtio transport for Virtual Sockets" + depends on VSOCKETS && VIRTIO + select VIRTIO_VSOCKETS_COMMON + help + This module implements a virtio transport for Virtual Sockets. + + Enable this transport if your Virtual Machine host supports Virtual + Sockets over virtio. + + To compile this driver as a module, choose M here: the module will be + called vmw_vsock_virtio_transport. If unsure, say N. + +config VIRTIO_VSOCKETS_COMMON + tristate + help + This option is selected by any driver which needs to access + the virtio_vsock. The module will be called + vmw_vsock_virtio_transport_common. diff --git a/net/vmw_vsock/Makefile b/net/vmw_vsock/Makefile index 2ce52d70f224..bc27c70e0e59 100644 --- a/net/vmw_vsock/Makefile +++ b/net/vmw_vsock/Makefile @@ -1,7 +1,13 @@ obj-$(CONFIG_VSOCKETS) += vsock.o obj-$(CONFIG_VMWARE_VMCI_VSOCKETS) += vmw_vsock_vmci_transport.o +obj-$(CONFIG_VIRTIO_VSOCKETS) += vmw_vsock_virtio_transport.o +obj-$(CONFIG_VIRTIO_VSOCKETS_COMMON) += vmw_vsock_virtio_transport_common.o vsock-y += af_vsock.o vsock_addr.o vmw_vsock_vmci_transport-y += vmci_transport.o vmci_transport_notify.o \ vmci_transport_notify_qstate.o + +vmw_vsock_virtio_transport-y += virtio_transport.o + +vmw_vsock_virtio_transport_common-y += virtio_transport_common.o diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c index b96ac918e0ba..17dbbe64cd73 100644 --- a/net/vmw_vsock/af_vsock.c +++ b/net/vmw_vsock/af_vsock.c @@ -344,6 +344,16 @@ static bool vsock_in_connected_table(struct vsock_sock *vsk) return ret; } +void vsock_remove_sock(struct vsock_sock *vsk) +{ + if (vsock_in_bound_table(vsk)) + vsock_remove_bound(vsk); + + if (vsock_in_connected_table(vsk)) + vsock_remove_connected(vsk); +} +EXPORT_SYMBOL_GPL(vsock_remove_sock); + void vsock_for_each_connected_socket(void (*fn)(struct sock *sk)) { int i; @@ -660,12 +670,6 @@ static void __vsock_release(struct sock *sk) vsk = vsock_sk(sk); pending = NULL; /* Compiler warning. */ - if (vsock_in_bound_table(vsk)) - vsock_remove_bound(vsk); - - if (vsock_in_connected_table(vsk)) - vsock_remove_connected(vsk); - transport->release(vsk); lock_sock(sk); @@ -1995,6 +1999,15 @@ void vsock_core_exit(void) } EXPORT_SYMBOL_GPL(vsock_core_exit); +const struct vsock_transport *vsock_core_get_transport(void) +{ + /* vsock_register_mutex not taken since only the transport uses this + * function and only while registered. + */ + return transport; +} +EXPORT_SYMBOL_GPL(vsock_core_get_transport); + MODULE_AUTHOR("VMware, Inc."); MODULE_DESCRIPTION("VMware Virtual Socket Family"); MODULE_VERSION("1.0.1.0-k"); diff --git a/net/vmw_vsock/virtio_transport.c b/net/vmw_vsock/virtio_transport.c new file mode 100644 index 000000000000..936d7eee62d0 --- /dev/null +++ b/net/vmw_vsock/virtio_transport.c @@ -0,0 +1,620 @@ +/* + * virtio transport for vsock + * + * Copyright (C) 2013-2015 Red Hat, Inc. + * Author: Asias He <asias@redhat.com> + * Stefan Hajnoczi <stefanha@redhat.com> + * + * Some of the code is take from Gerd Hoffmann <kraxel@redhat.com>'s + * early virtio-vsock proof-of-concept bits. + * + * This work is licensed under the terms of the GNU GPL, version 2. + */ +#include <linux/spinlock.h> +#include <linux/module.h> +#include <linux/list.h> +#include <linux/atomic.h> +#include <linux/virtio.h> +#include <linux/virtio_ids.h> +#include <linux/virtio_config.h> +#include <linux/virtio_vsock.h> +#include <net/sock.h> +#include <linux/mutex.h> +#include <net/af_vsock.h> + +static struct workqueue_struct *virtio_vsock_workqueue; +static struct virtio_vsock *the_virtio_vsock; +static DEFINE_MUTEX(the_virtio_vsock_mutex); /* protects the_virtio_vsock */ + +struct virtio_vsock { + struct virtio_device *vdev; + struct virtqueue *vqs[VSOCK_VQ_MAX]; + + /* Virtqueue processing is deferred to a workqueue */ + struct work_struct tx_work; + struct work_struct rx_work; + struct work_struct event_work; + + /* The following fields are protected by tx_lock. vqs[VSOCK_VQ_TX] + * must be accessed with tx_lock held. + */ + struct mutex tx_lock; + + struct work_struct send_pkt_work; + spinlock_t send_pkt_list_lock; + struct list_head send_pkt_list; + + atomic_t queued_replies; + + /* The following fields are protected by rx_lock. vqs[VSOCK_VQ_RX] + * must be accessed with rx_lock held. + */ + struct mutex rx_lock; + int rx_buf_nr; + int rx_buf_max_nr; + + /* The following fields are protected by event_lock. + * vqs[VSOCK_VQ_EVENT] must be accessed with event_lock held. + */ + struct mutex event_lock; + struct virtio_vsock_event event_list[8]; + + u32 guest_cid; +}; + +static struct virtio_vsock *virtio_vsock_get(void) +{ + return the_virtio_vsock; +} + +static u32 virtio_transport_get_local_cid(void) +{ + struct virtio_vsock *vsock = virtio_vsock_get(); + + return vsock->guest_cid; +} + +static void +virtio_transport_send_pkt_work(struct work_struct *work) +{ + struct virtio_vsock *vsock = + container_of(work, struct virtio_vsock, send_pkt_work); + struct virtqueue *vq; + bool added = false; + bool restart_rx = false; + + mutex_lock(&vsock->tx_lock); + + vq = vsock->vqs[VSOCK_VQ_TX]; + + for (;;) { + struct virtio_vsock_pkt *pkt; + struct scatterlist hdr, buf, *sgs[2]; + int ret, in_sg = 0, out_sg = 0; + bool reply; + + spin_lock_bh(&vsock->send_pkt_list_lock); + if (list_empty(&vsock->send_pkt_list)) { + spin_unlock_bh(&vsock->send_pkt_list_lock); + break; + } + + pkt = list_first_entry(&vsock->send_pkt_list, + struct virtio_vsock_pkt, list); + list_del_init(&pkt->list); + spin_unlock_bh(&vsock->send_pkt_list_lock); + + reply = pkt->reply; + + sg_init_one(&hdr, &pkt->hdr, sizeof(pkt->hdr)); + sgs[out_sg++] = &hdr; + if (pkt->buf) { + sg_init_one(&buf, pkt->buf, pkt->len); + sgs[out_sg++] = &buf; + } + + ret = virtqueue_add_sgs(vq, sgs, out_sg, in_sg, pkt, GFP_KERNEL); + /* Usually this means that there is no more space available in + * the vq + */ + if (ret < 0) { + spin_lock_bh(&vsock->send_pkt_list_lock); + list_add(&pkt->list, &vsock->send_pkt_list); + spin_unlock_bh(&vsock->send_pkt_list_lock); + break; + } + + if (reply) { + struct virtqueue *rx_vq = vsock->vqs[VSOCK_VQ_RX]; + int val; + + val = atomic_dec_return(&vsock->queued_replies); + + /* Do we now have resources to resume rx processing? */ + if (val + 1 == virtqueue_get_vring_size(rx_vq)) + restart_rx = true; + } + + added = true; + } + + if (added) + virtqueue_kick(vq); + + mutex_unlock(&vsock->tx_lock); + + if (restart_rx) + queue_work(virtio_vsock_workqueue, &vsock->rx_work); +} + +static int +virtio_transport_send_pkt(struct virtio_vsock_pkt *pkt) +{ + struct virtio_vsock *vsock; + int len = pkt->len; + + vsock = virtio_vsock_get(); + if (!vsock) { + virtio_transport_free_pkt(pkt); + return -ENODEV; + } + + if (pkt->reply) + atomic_inc(&vsock->queued_replies); + + spin_lock_bh(&vsock->send_pkt_list_lock); + list_add_tail(&pkt->list, &vsock->send_pkt_list); + spin_unlock_bh(&vsock->send_pkt_list_lock); + + queue_work(virtio_vsock_workqueue, &vsock->send_pkt_work); + return len; +} + +static void virtio_vsock_rx_fill(struct virtio_vsock *vsock) +{ + int buf_len = VIRTIO_VSOCK_DEFAULT_RX_BUF_SIZE; + struct virtio_vsock_pkt *pkt; + struct scatterlist hdr, buf, *sgs[2]; + struct virtqueue *vq; + int ret; + + vq = vsock->vqs[VSOCK_VQ_RX]; + + do { + pkt = kzalloc(sizeof(*pkt), GFP_KERNEL); + if (!pkt) + break; + + pkt->buf = kmalloc(buf_len, GFP_KERNEL); + if (!pkt->buf) { + virtio_transport_free_pkt(pkt); + break; + } + + pkt->len = buf_len; + + sg_init_one(&hdr, &pkt->hdr, sizeof(pkt->hdr)); + sgs[0] = &hdr; + + sg_init_one(&buf, pkt->buf, buf_len); + sgs[1] = &buf; + ret = virtqueue_add_sgs(vq, sgs, 0, 2, pkt, GFP_KERNEL); + if (ret) { + virtio_transport_free_pkt(pkt); + break; + } + vsock->rx_buf_nr++; + } while (vq->num_free); + if (vsock->rx_buf_nr > vsock->rx_buf_max_nr) + vsock->rx_buf_max_nr = vsock->rx_buf_nr; + virtqueue_kick(vq); +} + +static void virtio_transport_tx_work(struct work_struct *work) +{ + struct virtio_vsock *vsock = + container_of(work, struct virtio_vsock, tx_work); + struct virtqueue *vq; + bool added = false; + + vq = vsock->vqs[VSOCK_VQ_TX]; + mutex_lock(&vsock->tx_lock); + do { + struct virtio_vsock_pkt *pkt; + unsigned int len; + + virtqueue_disable_cb(vq); + while ((pkt = virtqueue_get_buf(vq, &len)) != NULL) { + virtio_transport_free_pkt(pkt); + added = true; + } + } while (!virtqueue_enable_cb(vq)); + mutex_unlock(&vsock->tx_lock); + + if (added) + queue_work(virtio_vsock_workqueue, &vsock->send_pkt_work); +} + +/* Is there space left for replies to rx packets? */ +static bool virtio_transport_more_replies(struct virtio_vsock *vsock) +{ + struct virtqueue *vq = vsock->vqs[VSOCK_VQ_RX]; + int val; + + smp_rmb(); /* paired with atomic_inc() and atomic_dec_return() */ + val = atomic_read(&vsock->queued_replies); + + return val < virtqueue_get_vring_size(vq); +} + +static void virtio_transport_rx_work(struct work_struct *work) +{ + struct virtio_vsock *vsock = + container_of(work, struct virtio_vsock, rx_work); + struct virtqueue *vq; + + vq = vsock->vqs[VSOCK_VQ_RX]; + + mutex_lock(&vsock->rx_lock); + + do { + virtqueue_disable_cb(vq); + for (;;) { + struct virtio_vsock_pkt *pkt; + unsigned int len; + + if (!virtio_transport_more_replies(vsock)) { + /* Stop rx until the device processes already + * pending replies. Leave rx virtqueue + * callbacks disabled. + */ + goto out; + } + + pkt = virtqueue_get_buf(vq, &len); + if (!pkt) { + break; + } + + vsock->rx_buf_nr--; + + /* Drop short/long packets */ + if (unlikely(len < sizeof(pkt->hdr) || + len > sizeof(pkt->hdr) + pkt->len)) { + virtio_transport_free_pkt(pkt); + continue; + } + + pkt->len = len - sizeof(pkt->hdr); + virtio_transport_recv_pkt(pkt); + } + } while (!virtqueue_enable_cb(vq)); + +out: + if (vsock->rx_buf_nr < vsock->rx_buf_max_nr / 2) + virtio_vsock_rx_fill(vsock); + mutex_unlock(&vsock->rx_lock); +} + +/* event_lock must be held */ +static int virtio_vsock_event_fill_one(struct virtio_vsock *vsock, + struct virtio_vsock_event *event) +{ + struct scatterlist sg; + struct virtqueue *vq; + + vq = vsock->vqs[VSOCK_VQ_EVENT]; + + sg_init_one(&sg, event, sizeof(*event)); + + return virtqueue_add_inbuf(vq, &sg, 1, event, GFP_KERNEL); +} + +/* event_lock must be held */ +static void virtio_vsock_event_fill(struct virtio_vsock *vsock) +{ + size_t i; + + for (i = 0; i < ARRAY_SIZE(vsock->event_list); i++) { + struct virtio_vsock_event *event = &vsock->event_list[i]; + + virtio_vsock_event_fill_one(vsock, event); + } + + virtqueue_kick(vsock->vqs[VSOCK_VQ_EVENT]); +} + +static void virtio_vsock_reset_sock(struct sock *sk) +{ + lock_sock(sk); + sk->sk_state = SS_UNCONNECTED; + sk->sk_err = ECONNRESET; + sk->sk_error_report(sk); + release_sock(sk); +} + +static void virtio_vsock_update_guest_cid(struct virtio_vsock *vsock) +{ + struct virtio_device *vdev = vsock->vdev; + u64 guest_cid; + + vdev->config->get(vdev, offsetof(struct virtio_vsock_config, guest_cid), + &guest_cid, sizeof(guest_cid)); + vsock->guest_cid = le64_to_cpu(guest_cid); +} + +/* event_lock must be held */ +static void virtio_vsock_event_handle(struct virtio_vsock *vsock, + struct virtio_vsock_event *event) +{ + switch (le32_to_cpu(event->id)) { + case VIRTIO_VSOCK_EVENT_TRANSPORT_RESET: + virtio_vsock_update_guest_cid(vsock); + vsock_for_each_connected_socket(virtio_vsock_reset_sock); + break; + } +} + +static void virtio_transport_event_work(struct work_struct *work) +{ + struct virtio_vsock *vsock = + container_of(work, struct virtio_vsock, event_work); + struct virtqueue *vq; + + vq = vsock->vqs[VSOCK_VQ_EVENT]; + + mutex_lock(&vsock->event_lock); + + do { + struct virtio_vsock_event *event; + unsigned int len; + + virtqueue_disable_cb(vq); + while ((event = virtqueue_get_buf(vq, &len)) != NULL) { + if (len == sizeof(*event)) + virtio_vsock_event_handle(vsock, event); + + virtio_vsock_event_fill_one(vsock, event); + } + } while (!virtqueue_enable_cb(vq)); + + virtqueue_kick(vsock->vqs[VSOCK_VQ_EVENT]); + + mutex_unlock(&vsock->event_lock); +} + +static void virtio_vsock_event_done(struct virtqueue *vq) +{ + struct virtio_vsock *vsock = vq->vdev->priv; + + if (!vsock) + return; + queue_work(virtio_vsock_workqueue, &vsock->event_work); +} + +static void virtio_vsock_tx_done(struct virtqueue *vq) +{ + struct virtio_vsock *vsock = vq->vdev->priv; + + if (!vsock) + return; + queue_work(virtio_vsock_workqueue, &vsock->tx_work); +} + +static void virtio_vsock_rx_done(struct virtqueue *vq) +{ + struct virtio_vsock *vsock = vq->vdev->priv; + + if (!vsock) + return; + queue_work(virtio_vsock_workqueue, &vsock->rx_work); +} + +static struct virtio_transport virtio_transport = { + .transport = { + .get_local_cid = virtio_transport_get_local_cid, + + .init = virtio_transport_do_socket_init, + .destruct = virtio_transport_destruct, + .release = virtio_transport_release, + .connect = virtio_transport_connect, + .shutdown = virtio_transport_shutdown, + + .dgram_bind = virtio_transport_dgram_bind, + .dgram_dequeue = virtio_transport_dgram_dequeue, + .dgram_enqueue = virtio_transport_dgram_enqueue, + .dgram_allow = virtio_transport_dgram_allow, + + .stream_dequeue = virtio_transport_stream_dequeue, + .stream_enqueue = virtio_transport_stream_enqueue, + .stream_has_data = virtio_transport_stream_has_data, + .stream_has_space = virtio_transport_stream_has_space, + .stream_rcvhiwat = virtio_transport_stream_rcvhiwat, + .stream_is_active = virtio_transport_stream_is_active, + .stream_allow = virtio_transport_stream_allow, + + .notify_poll_in = virtio_transport_notify_poll_in, + .notify_poll_out = virtio_transport_notify_poll_out, + .notify_recv_init = virtio_transport_notify_recv_init, + .notify_recv_pre_block = virtio_transport_notify_recv_pre_block, + .notify_recv_pre_dequeue = virtio_transport_notify_recv_pre_dequeue, + .notify_recv_post_dequeue = virtio_transport_notify_recv_post_dequeue, + .notify_send_init = virtio_transport_notify_send_init, + .notify_send_pre_block = virtio_transport_notify_send_pre_block, + .notify_send_pre_enqueue = virtio_transport_notify_send_pre_enqueue, + .notify_send_post_enqueue = virtio_transport_notify_send_post_enqueue, + + .set_buffer_size = virtio_transport_set_buffer_size, + .set_min_buffer_size = virtio_transport_set_min_buffer_size, + .set_max_buffer_size = virtio_transport_set_max_buffer_size, + .get_buffer_size = virtio_transport_get_buffer_size, + .get_min_buffer_size = virtio_transport_get_min_buffer_size, + .get_max_buffer_size = virtio_transport_get_max_buffer_size, + }, + + .send_pkt = virtio_transport_send_pkt, +}; + +static int virtio_vsock_probe(struct virtio_device *vdev) +{ + vq_callback_t *callbacks[] = { + virtio_vsock_rx_done, + virtio_vsock_tx_done, + virtio_vsock_event_done, + }; + static const char * const names[] = { + "rx", + "tx", + "event", + }; + struct virtio_vsock *vsock = NULL; + int ret; + + ret = mutex_lock_interruptible(&the_virtio_vsock_mutex); + if (ret) + return ret; + + /* Only one virtio-vsock device per guest is supported */ + if (the_virtio_vsock) { + ret = -EBUSY; + goto out; + } + + vsock = kzalloc(sizeof(*vsock), GFP_KERNEL); + if (!vsock) { + ret = -ENOMEM; + goto out; + } + + vsock->vdev = vdev; + + ret = vsock->vdev->config->find_vqs(vsock->vdev, VSOCK_VQ_MAX, + vsock->vqs, callbacks, names); + if (ret < 0) + goto out; + + virtio_vsock_update_guest_cid(vsock); + + ret = vsock_core_init(&virtio_transport.transport); + if (ret < 0) + goto out_vqs; + + vsock->rx_buf_nr = 0; + vsock->rx_buf_max_nr = 0; + atomic_set(&vsock->queued_replies, 0); + + vdev->priv = vsock; + the_virtio_vsock = vsock; + mutex_init(&vsock->tx_lock); + mutex_init(&vsock->rx_lock); + mutex_init(&vsock->event_lock); + spin_lock_init(&vsock->send_pkt_list_lock); + INIT_LIST_HEAD(&vsock->send_pkt_list); + INIT_WORK(&vsock->rx_work, virtio_transport_rx_work); + INIT_WORK(&vsock->tx_work, virtio_transport_tx_work); + INIT_WORK(&vsock->event_work, virtio_transport_event_work); + INIT_WORK(&vsock->send_pkt_work, virtio_transport_send_pkt_work); + + mutex_lock(&vsock->rx_lock); + virtio_vsock_rx_fill(vsock); + mutex_unlock(&vsock->rx_lock); + + mutex_lock(&vsock->event_lock); + virtio_vsock_event_fill(vsock); + mutex_unlock(&vsock->event_lock); + + mutex_unlock(&the_virtio_vsock_mutex); + return 0; + +out_vqs: + vsock->vdev->config->del_vqs(vsock->vdev); +out: + kfree(vsock); + mutex_unlock(&the_virtio_vsock_mutex); + return ret; +} + +static void virtio_vsock_remove(struct virtio_device *vdev) +{ + struct virtio_vsock *vsock = vdev->priv; + struct virtio_vsock_pkt *pkt; + + flush_work(&vsock->rx_work); + flush_work(&vsock->tx_work); + flush_work(&vsock->event_work); + flush_work(&vsock->send_pkt_work); + + vdev->config->reset(vdev); + + mutex_lock(&vsock->rx_lock); + while ((pkt = virtqueue_detach_unused_buf(vsock->vqs[VSOCK_VQ_RX]))) + virtio_transport_free_pkt(pkt); + mutex_unlock(&vsock->rx_lock); + + mutex_lock(&vsock->tx_lock); + while ((pkt = virtqueue_detach_unused_buf(vsock->vqs[VSOCK_VQ_TX]))) + virtio_transport_free_pkt(pkt); + mutex_unlock(&vsock->tx_lock); + + spin_lock_bh(&vsock->send_pkt_list_lock); + while (!list_empty(&vsock->send_pkt_list)) { + pkt = list_first_entry(&vsock->send_pkt_list, + struct virtio_vsock_pkt, list); + list_del(&pkt->list); + virtio_transport_free_pkt(pkt); + } + spin_unlock_bh(&vsock->send_pkt_list_lock); + + mutex_lock(&the_virtio_vsock_mutex); + the_virtio_vsock = NULL; + vsock_core_exit(); + mutex_unlock(&the_virtio_vsock_mutex); + + vdev->config->del_vqs(vdev); + + kfree(vsock); +} + +static struct virtio_device_id id_table[] = { + { VIRTIO_ID_VSOCK, VIRTIO_DEV_ANY_ID }, + { 0 }, +}; + +static unsigned int features[] = { +}; + +static struct virtio_driver virtio_vsock_driver = { + .feature_table = features, + .feature_table_size = ARRAY_SIZE(features), + .driver.name = KBUILD_MODNAME, + .driver.owner = THIS_MODULE, + .id_table = id_table, + .probe = virtio_vsock_probe, + .remove = virtio_vsock_remove, +}; + +static int __init virtio_vsock_init(void) +{ + int ret; + + virtio_vsock_workqueue = alloc_workqueue("virtio_vsock", 0, 0); + if (!virtio_vsock_workqueue) + return -ENOMEM; + ret = register_virtio_driver(&virtio_vsock_driver); + if (ret) + destroy_workqueue(virtio_vsock_workqueue); + return ret; +} + +static void __exit virtio_vsock_exit(void) +{ + unregister_virtio_driver(&virtio_vsock_driver); + destroy_workqueue(virtio_vsock_workqueue); +} + +module_init(virtio_vsock_init); +module_exit(virtio_vsock_exit); +MODULE_LICENSE("GPL v2"); +MODULE_AUTHOR("Asias He"); +MODULE_DESCRIPTION("virtio transport for vsock"); +MODULE_DEVICE_TABLE(virtio, id_table); diff --git a/net/vmw_vsock/virtio_transport_common.c b/net/vmw_vsock/virtio_transport_common.c new file mode 100644 index 000000000000..a53b3a16b4f1 --- /dev/null +++ b/net/vmw_vsock/virtio_transport_common.c @@ -0,0 +1,992 @@ +/* + * common code for virtio vsock + * + * Copyright (C) 2013-2015 Red Hat, Inc. + * Author: Asias He <asias@redhat.com> + * Stefan Hajnoczi <stefanha@redhat.com> + * + * This work is licensed under the terms of the GNU GPL, version 2. + */ +#include <linux/spinlock.h> +#include <linux/module.h> +#include <linux/ctype.h> +#include <linux/list.h> +#include <linux/virtio.h> +#include <linux/virtio_ids.h> +#include <linux/virtio_config.h> +#include <linux/virtio_vsock.h> + +#include <net/sock.h> +#include <net/af_vsock.h> + +#define CREATE_TRACE_POINTS +#include <trace/events/vsock_virtio_transport_common.h> + +/* How long to wait for graceful shutdown of a connection */ +#define VSOCK_CLOSE_TIMEOUT (8 * HZ) + +static const struct virtio_transport *virtio_transport_get_ops(void) +{ + const struct vsock_transport *t = vsock_core_get_transport(); + + return container_of(t, struct virtio_transport, transport); +} + +struct virtio_vsock_pkt * +virtio_transport_alloc_pkt(struct virtio_vsock_pkt_info *info, + size_t len, + u32 src_cid, + u32 src_port, + u32 dst_cid, + u32 dst_port) +{ + struct virtio_vsock_pkt *pkt; + int err; + + pkt = kzalloc(sizeof(*pkt), GFP_KERNEL); + if (!pkt) + return NULL; + + pkt->hdr.type = cpu_to_le16(info->type); + pkt->hdr.op = cpu_to_le16(info->op); + pkt->hdr.src_cid = cpu_to_le64(src_cid); + pkt->hdr.dst_cid = cpu_to_le64(dst_cid); + pkt->hdr.src_port = cpu_to_le32(src_port); + pkt->hdr.dst_port = cpu_to_le32(dst_port); + pkt->hdr.flags = cpu_to_le32(info->flags); + pkt->len = len; + pkt->hdr.len = cpu_to_le32(len); + pkt->reply = info->reply; + + if (info->msg && len > 0) { + pkt->buf = kmalloc(len, GFP_KERNEL); + if (!pkt->buf) + goto out_pkt; + err = memcpy_from_msg(pkt->buf, info->msg, len); + if (err) + goto out; + } + + trace_virtio_transport_alloc_pkt(src_cid, src_port, + dst_cid, dst_port, + len, + info->type, + info->op, + info->flags); + + return pkt; + +out: + kfree(pkt->buf); +out_pkt: + kfree(pkt); + return NULL; +} +EXPORT_SYMBOL_GPL(virtio_transport_alloc_pkt); + +static int virtio_transport_send_pkt_info(struct vsock_sock *vsk, + struct virtio_vsock_pkt_info *info) +{ + u32 src_cid, src_port, dst_cid, dst_port; + struct virtio_vsock_sock *vvs; + struct virtio_vsock_pkt *pkt; + u32 pkt_len = info->pkt_len; + + src_cid = vm_sockets_get_local_cid(); + src_port = vsk->local_addr.svm_port; + if (!info->remote_cid) { + dst_cid = vsk->remote_addr.svm_cid; + dst_port = vsk->remote_addr.svm_port; + } else { + dst_cid = info->remote_cid; + dst_port = info->remote_port; + } + + vvs = vsk->trans; + + /* we can send less than pkt_len bytes */ + if (pkt_len > VIRTIO_VSOCK_DEFAULT_RX_BUF_SIZE) + pkt_len = VIRTIO_VSOCK_DEFAULT_RX_BUF_SIZE; + + /* virtio_transport_get_credit might return less than pkt_len credit */ + pkt_len = virtio_transport_get_credit(vvs, pkt_len); + + /* Do not send zero length OP_RW pkt */ + if (pkt_len == 0 && info->op == VIRTIO_VSOCK_OP_RW) + return pkt_len; + + pkt = virtio_transport_alloc_pkt(info, pkt_len, + src_cid, src_port, + dst_cid, dst_port); + if (!pkt) { + virtio_transport_put_credit(vvs, pkt_len); + return -ENOMEM; + } + + virtio_transport_inc_tx_pkt(vvs, pkt); + + return virtio_transport_get_ops()->send_pkt(pkt); +} + +static void virtio_transport_inc_rx_pkt(struct virtio_vsock_sock *vvs, + struct virtio_vsock_pkt *pkt) +{ + vvs->rx_bytes += pkt->len; +} + +static void virtio_transport_dec_rx_pkt(struct virtio_vsock_sock *vvs, + struct virtio_vsock_pkt *pkt) +{ + vvs->rx_bytes -= pkt->len; + vvs->fwd_cnt += pkt->len; +} + +void virtio_transport_inc_tx_pkt(struct virtio_vsock_sock *vvs, struct virtio_vsock_pkt *pkt) +{ + spin_lock_bh(&vvs->tx_lock); + pkt->hdr.fwd_cnt = cpu_to_le32(vvs->fwd_cnt); + pkt->hdr.buf_alloc = cpu_to_le32(vvs->buf_alloc); + spin_unlock_bh(&vvs->tx_lock); +} +EXPORT_SYMBOL_GPL(virtio_transport_inc_tx_pkt); + +u32 virtio_transport_get_credit(struct virtio_vsock_sock *vvs, u32 credit) +{ + u32 ret; + + spin_lock_bh(&vvs->tx_lock); + ret = vvs->peer_buf_alloc - (vvs->tx_cnt - vvs->peer_fwd_cnt); + if (ret > credit) + ret = credit; + vvs->tx_cnt += ret; + spin_unlock_bh(&vvs->tx_lock); + + return ret; +} +EXPORT_SYMBOL_GPL(virtio_transport_get_credit); + +void virtio_transport_put_credit(struct virtio_vsock_sock *vvs, u32 credit) +{ + spin_lock_bh(&vvs->tx_lock); + vvs->tx_cnt -= credit; + spin_unlock_bh(&vvs->tx_lock); +} +EXPORT_SYMBOL_GPL(virtio_transport_put_credit); + +static int virtio_transport_send_credit_update(struct vsock_sock *vsk, + int type, + struct virtio_vsock_hdr *hdr) +{ + struct virtio_vsock_pkt_info info = { + .op = VIRTIO_VSOCK_OP_CREDIT_UPDATE, + .type = type, + }; + + return virtio_transport_send_pkt_info(vsk, &info); +} + +static ssize_t +virtio_transport_stream_do_dequeue(struct vsock_sock *vsk, + struct msghdr *msg, + size_t len) +{ + struct virtio_vsock_sock *vvs = vsk->trans; + struct virtio_vsock_pkt *pkt; + size_t bytes, total = 0; + int err = -EFAULT; + + spin_lock_bh(&vvs->rx_lock); + while (total < len && !list_empty(&vvs->rx_queue)) { + pkt = list_first_entry(&vvs->rx_queue, + struct virtio_vsock_pkt, list); + + bytes = len - total; + if (bytes > pkt->len - pkt->off) + bytes = pkt->len - pkt->off; + + /* sk_lock is held by caller so no one else can dequeue. + * Unlock rx_lock since memcpy_to_msg() may sleep. + */ + spin_unlock_bh(&vvs->rx_lock); + + err = memcpy_to_msg(msg, pkt->buf + pkt->off, bytes); + if (err) + goto out; + + spin_lock_bh(&vvs->rx_lock); + + total += bytes; + pkt->off += bytes; + if (pkt->off == pkt->len) { + virtio_transport_dec_rx_pkt(vvs, pkt); + list_del(&pkt->list); + virtio_transport_free_pkt(pkt); + } + } + spin_unlock_bh(&vvs->rx_lock); + + /* Send a credit pkt to peer */ + virtio_transport_send_credit_update(vsk, VIRTIO_VSOCK_TYPE_STREAM, + NULL); + + return total; + +out: + if (total) + err = total; + return err; +} + +ssize_t +virtio_transport_stream_dequeue(struct vsock_sock *vsk, + struct msghdr *msg, + size_t len, int flags) +{ + if (flags & MSG_PEEK) + return -EOPNOTSUPP; + + return virtio_transport_stream_do_dequeue(vsk, msg, len); +} +EXPORT_SYMBOL_GPL(virtio_transport_stream_dequeue); + +int +virtio_transport_dgram_dequeue(struct vsock_sock *vsk, + struct msghdr *msg, + size_t len, int flags) +{ + return -EOPNOTSUPP; +} +EXPORT_SYMBOL_GPL(virtio_transport_dgram_dequeue); + +s64 virtio_transport_stream_has_data(struct vsock_sock *vsk) +{ + struct virtio_vsock_sock *vvs = vsk->trans; + s64 bytes; + + spin_lock_bh(&vvs->rx_lock); + bytes = vvs->rx_bytes; + spin_unlock_bh(&vvs->rx_lock); + + return bytes; +} +EXPORT_SYMBOL_GPL(virtio_transport_stream_has_data); + +static s64 virtio_transport_has_space(struct vsock_sock *vsk) +{ + struct virtio_vsock_sock *vvs = vsk->trans; + s64 bytes; + + bytes = vvs->peer_buf_alloc - (vvs->tx_cnt - vvs->peer_fwd_cnt); + if (bytes < 0) + bytes = 0; + + return bytes; +} + +s64 virtio_transport_stream_has_space(struct vsock_sock *vsk) +{ + struct virtio_vsock_sock *vvs = vsk->trans; + s64 bytes; + + spin_lock_bh(&vvs->tx_lock); + bytes = virtio_transport_has_space(vsk); + spin_unlock_bh(&vvs->tx_lock); + + return bytes; +} +EXPORT_SYMBOL_GPL(virtio_transport_stream_has_space); + +int virtio_transport_do_socket_init(struct vsock_sock *vsk, + struct vsock_sock *psk) +{ + struct virtio_vsock_sock *vvs; + + vvs = kzalloc(sizeof(*vvs), GFP_KERNEL); + if (!vvs) + return -ENOMEM; + + vsk->trans = vvs; + vvs->vsk = vsk; + if (psk) { + struct virtio_vsock_sock *ptrans = psk->trans; + + vvs->buf_size = ptrans->buf_size; + vvs->buf_size_min = ptrans->buf_size_min; + vvs->buf_size_max = ptrans->buf_size_max; + vvs->peer_buf_alloc = ptrans->peer_buf_alloc; + } else { + vvs->buf_size = VIRTIO_VSOCK_DEFAULT_BUF_SIZE; + vvs->buf_size_min = VIRTIO_VSOCK_DEFAULT_MIN_BUF_SIZE; + vvs->buf_size_max = VIRTIO_VSOCK_DEFAULT_MAX_BUF_SIZE; + } + + vvs->buf_alloc = vvs->buf_size; + + spin_lock_init(&vvs->rx_lock); + spin_lock_init(&vvs->tx_lock); + INIT_LIST_HEAD(&vvs->rx_queue); + + return 0; +} +EXPORT_SYMBOL_GPL(virtio_transport_do_socket_init); + +u64 virtio_transport_get_buffer_size(struct vsock_sock *vsk) +{ + struct virtio_vsock_sock *vvs = vsk->trans; + + return vvs->buf_size; +} +EXPORT_SYMBOL_GPL(virtio_transport_get_buffer_size); + +u64 virtio_transport_get_min_buffer_size(struct vsock_sock *vsk) +{ + struct virtio_vsock_sock *vvs = vsk->trans; + + return vvs->buf_size_min; +} +EXPORT_SYMBOL_GPL(virtio_transport_get_min_buffer_size); + +u64 virtio_transport_get_max_buffer_size(struct vsock_sock *vsk) +{ + struct virtio_vsock_sock *vvs = vsk->trans; + + return vvs->buf_size_max; +} +EXPORT_SYMBOL_GPL(virtio_transport_get_max_buffer_size); + +void virtio_transport_set_buffer_size(struct vsock_sock *vsk, u64 val) +{ + struct virtio_vsock_sock *vvs = vsk->trans; + + if (val > VIRTIO_VSOCK_MAX_BUF_SIZE) + val = VIRTIO_VSOCK_MAX_BUF_SIZE; + if (val < vvs->buf_size_min) + vvs->buf_size_min = val; + if (val > vvs->buf_size_max) + vvs->buf_size_max = val; + vvs->buf_size = val; + vvs->buf_alloc = val; +} +EXPORT_SYMBOL_GPL(virtio_transport_set_buffer_size); + +void virtio_transport_set_min_buffer_size(struct vsock_sock *vsk, u64 val) +{ + struct virtio_vsock_sock *vvs = vsk->trans; + + if (val > VIRTIO_VSOCK_MAX_BUF_SIZE) + val = VIRTIO_VSOCK_MAX_BUF_SIZE; + if (val > vvs->buf_size) + vvs->buf_size = val; + vvs->buf_size_min = val; +} +EXPORT_SYMBOL_GPL(virtio_transport_set_min_buffer_size); + +void virtio_transport_set_max_buffer_size(struct vsock_sock *vsk, u64 val) +{ + struct virtio_vsock_sock *vvs = vsk->trans; + + if (val > VIRTIO_VSOCK_MAX_BUF_SIZE) + val = VIRTIO_VSOCK_MAX_BUF_SIZE; + if (val < vvs->buf_size) + vvs->buf_size = val; + vvs->buf_size_max = val; +} +EXPORT_SYMBOL_GPL(virtio_transport_set_max_buffer_size); + +int +virtio_transport_notify_poll_in(struct vsock_sock *vsk, + size_t target, + bool *data_ready_now) +{ + if (vsock_stream_has_data(vsk)) + *data_ready_now = true; + else + *data_ready_now = false; + + return 0; +} +EXPORT_SYMBOL_GPL(virtio_transport_notify_poll_in); + +int +virtio_transport_notify_poll_out(struct vsock_sock *vsk, + size_t target, + bool *space_avail_now) +{ + s64 free_space; + + free_space = vsock_stream_has_space(vsk); + if (free_space > 0) + *space_avail_now = true; + else if (free_space == 0) + *space_avail_now = false; + + return 0; +} +EXPORT_SYMBOL_GPL(virtio_transport_notify_poll_out); + +int virtio_transport_notify_recv_init(struct vsock_sock *vsk, + size_t target, struct vsock_transport_recv_notify_data *data) +{ + return 0; +} +EXPORT_SYMBOL_GPL(virtio_transport_notify_recv_init); + +int virtio_transport_notify_recv_pre_block(struct vsock_sock *vsk, + size_t target, struct vsock_transport_recv_notify_data *data) +{ + return 0; +} +EXPORT_SYMBOL_GPL(virtio_transport_notify_recv_pre_block); + +int virtio_transport_notify_recv_pre_dequeue(struct vsock_sock *vsk, + size_t target, struct vsock_transport_recv_notify_data *data) +{ + return 0; +} +EXPORT_SYMBOL_GPL(virtio_transport_notify_recv_pre_dequeue); + +int virtio_transport_notify_recv_post_dequeue(struct vsock_sock *vsk, + size_t target, ssize_t copied, bool data_read, + struct vsock_transport_recv_notify_data *data) +{ + return 0; +} +EXPORT_SYMBOL_GPL(virtio_transport_notify_recv_post_dequeue); + +int virtio_transport_notify_send_init(struct vsock_sock *vsk, + struct vsock_transport_send_notify_data *data) +{ + return 0; +} +EXPORT_SYMBOL_GPL(virtio_transport_notify_send_init); + +int virtio_transport_notify_send_pre_block(struct vsock_sock *vsk, + struct vsock_transport_send_notify_data *data) +{ + return 0; +} +EXPORT_SYMBOL_GPL(virtio_transport_notify_send_pre_block); + +int virtio_transport_notify_send_pre_enqueue(struct vsock_sock *vsk, + struct vsock_transport_send_notify_data *data) +{ + return 0; +} +EXPORT_SYMBOL_GPL(virtio_transport_notify_send_pre_enqueue); + +int virtio_transport_notify_send_post_enqueue(struct vsock_sock *vsk, + ssize_t written, struct vsock_transport_send_notify_data *data) +{ + return 0; +} +EXPORT_SYMBOL_GPL(virtio_transport_notify_send_post_enqueue); + +u64 virtio_transport_stream_rcvhiwat(struct vsock_sock *vsk) +{ + struct virtio_vsock_sock *vvs = vsk->trans; + + return vvs->buf_size; +} +EXPORT_SYMBOL_GPL(virtio_transport_stream_rcvhiwat); + +bool virtio_transport_stream_is_active(struct vsock_sock *vsk) +{ + return true; +} +EXPORT_SYMBOL_GPL(virtio_transport_stream_is_active); + +bool virtio_transport_stream_allow(u32 cid, u32 port) +{ + return true; +} +EXPORT_SYMBOL_GPL(virtio_transport_stream_allow); + +int virtio_transport_dgram_bind(struct vsock_sock *vsk, + struct sockaddr_vm *addr) +{ + return -EOPNOTSUPP; +} +EXPORT_SYMBOL_GPL(virtio_transport_dgram_bind); + +bool virtio_transport_dgram_allow(u32 cid, u32 port) +{ + return false; +} +EXPORT_SYMBOL_GPL(virtio_transport_dgram_allow); + +int virtio_transport_connect(struct vsock_sock *vsk) +{ + struct virtio_vsock_pkt_info info = { + .op = VIRTIO_VSOCK_OP_REQUEST, + .type = VIRTIO_VSOCK_TYPE_STREAM, + }; + + return virtio_transport_send_pkt_info(vsk, &info); +} +EXPORT_SYMBOL_GPL(virtio_transport_connect); + +int virtio_transport_shutdown(struct vsock_sock *vsk, int mode) +{ + struct virtio_vsock_pkt_info info = { + .op = VIRTIO_VSOCK_OP_SHUTDOWN, + .type = VIRTIO_VSOCK_TYPE_STREAM, + .flags = (mode & RCV_SHUTDOWN ? + VIRTIO_VSOCK_SHUTDOWN_RCV : 0) | + (mode & SEND_SHUTDOWN ? + VIRTIO_VSOCK_SHUTDOWN_SEND : 0), + }; + + return virtio_transport_send_pkt_info(vsk, &info); +} +EXPORT_SYMBOL_GPL(virtio_transport_shutdown); + +int +virtio_transport_dgram_enqueue(struct vsock_sock *vsk, + struct sockaddr_vm *remote_addr, + struct msghdr *msg, + size_t dgram_len) +{ + return -EOPNOTSUPP; +} +EXPORT_SYMBOL_GPL(virtio_transport_dgram_enqueue); + +ssize_t +virtio_transport_stream_enqueue(struct vsock_sock *vsk, + struct msghdr *msg, + size_t len) +{ + struct virtio_vsock_pkt_info info = { + .op = VIRTIO_VSOCK_OP_RW, + .type = VIRTIO_VSOCK_TYPE_STREAM, + .msg = msg, + .pkt_len = len, + }; + + return virtio_transport_send_pkt_info(vsk, &info); +} +EXPORT_SYMBOL_GPL(virtio_transport_stream_enqueue); + +void virtio_transport_destruct(struct vsock_sock *vsk) +{ + struct virtio_vsock_sock *vvs = vsk->trans; + + kfree(vvs); +} +EXPORT_SYMBOL_GPL(virtio_transport_destruct); + +static int virtio_transport_reset(struct vsock_sock *vsk, + struct virtio_vsock_pkt *pkt) +{ + struct virtio_vsock_pkt_info info = { + .op = VIRTIO_VSOCK_OP_RST, + .type = VIRTIO_VSOCK_TYPE_STREAM, + .reply = !!pkt, + }; + + /* Send RST only if the original pkt is not a RST pkt */ + if (pkt && le16_to_cpu(pkt->hdr.op) == VIRTIO_VSOCK_OP_RST) + return 0; + + return virtio_transport_send_pkt_info(vsk, &info); +} + +/* Normally packets are associated with a socket. There may be no socket if an + * attempt was made to connect to a socket that does not exist. + */ +static int virtio_transport_reset_no_sock(struct virtio_vsock_pkt *pkt) +{ + struct virtio_vsock_pkt_info info = { + .op = VIRTIO_VSOCK_OP_RST, + .type = le16_to_cpu(pkt->hdr.type), + .reply = true, + }; + + /* Send RST only if the original pkt is not a RST pkt */ + if (le16_to_cpu(pkt->hdr.op) == VIRTIO_VSOCK_OP_RST) + return 0; + + pkt = virtio_transport_alloc_pkt(&info, 0, + le32_to_cpu(pkt->hdr.dst_cid), + le32_to_cpu(pkt->hdr.dst_port), + le32_to_cpu(pkt->hdr.src_cid), + le32_to_cpu(pkt->hdr.src_port)); + if (!pkt) + return -ENOMEM; + + return virtio_transport_get_ops()->send_pkt(pkt); +} + +static void virtio_transport_wait_close(struct sock *sk, long timeout) +{ + if (timeout) { + DEFINE_WAIT(wait); + + do { + prepare_to_wait(sk_sleep(sk), &wait, + TASK_INTERRUPTIBLE); + if (sk_wait_event(sk, &timeout, + sock_flag(sk, SOCK_DONE))) + break; + } while (!signal_pending(current) && timeout); + + finish_wait(sk_sleep(sk), &wait); + } +} + +static void virtio_transport_do_close(struct vsock_sock *vsk, + bool cancel_timeout) +{ + struct sock *sk = sk_vsock(vsk); + + sock_set_flag(sk, SOCK_DONE); + vsk->peer_shutdown = SHUTDOWN_MASK; + if (vsock_stream_has_data(vsk) <= 0) + sk->sk_state = SS_DISCONNECTING; + sk->sk_state_change(sk); + + if (vsk->close_work_scheduled && + (!cancel_timeout || cancel_delayed_work(&vsk->close_work))) { + vsk->close_work_scheduled = false; + + vsock_remove_sock(vsk); + + /* Release refcnt obtained when we scheduled the timeout */ + sock_put(sk); + } +} + +static void virtio_transport_close_timeout(struct work_struct *work) +{ + struct vsock_sock *vsk = + container_of(work, struct vsock_sock, close_work.work); + struct sock *sk = sk_vsock(vsk); + + sock_hold(sk); + lock_sock(sk); + + if (!sock_flag(sk, SOCK_DONE)) { + (void)virtio_transport_reset(vsk, NULL); + + virtio_transport_do_close(vsk, false); + } + + vsk->close_work_scheduled = false; + + release_sock(sk); + sock_put(sk); +} + +/* User context, vsk->sk is locked */ +static bool virtio_transport_close(struct vsock_sock *vsk) +{ + struct sock *sk = &vsk->sk; + + if (!(sk->sk_state == SS_CONNECTED || + sk->sk_state == SS_DISCONNECTING)) + return true; + + /* Already received SHUTDOWN from peer, reply with RST */ + if ((vsk->peer_shutdown & SHUTDOWN_MASK) == SHUTDOWN_MASK) { + (void)virtio_transport_reset(vsk, NULL); + return true; + } + + if ((sk->sk_shutdown & SHUTDOWN_MASK) != SHUTDOWN_MASK) + (void)virtio_transport_shutdown(vsk, SHUTDOWN_MASK); + + if (sock_flag(sk, SOCK_LINGER) && !(current->flags & PF_EXITING)) + virtio_transport_wait_close(sk, sk->sk_lingertime); + + if (sock_flag(sk, SOCK_DONE)) { + return true; + } + + sock_hold(sk); + INIT_DELAYED_WORK(&vsk->close_work, + virtio_transport_close_timeout); + vsk->close_work_scheduled = true; + schedule_delayed_work(&vsk->close_work, VSOCK_CLOSE_TIMEOUT); + return false; +} + +void virtio_transport_release(struct vsock_sock *vsk) +{ + struct sock *sk = &vsk->sk; + bool remove_sock = true; + + lock_sock(sk); + if (sk->sk_type == SOCK_STREAM) + remove_sock = virtio_transport_close(vsk); + release_sock(sk); + + if (remove_sock) + vsock_remove_sock(vsk); +} +EXPORT_SYMBOL_GPL(virtio_transport_release); + +static int +virtio_transport_recv_connecting(struct sock *sk, + struct virtio_vsock_pkt *pkt) +{ + struct vsock_sock *vsk = vsock_sk(sk); + int err; + int skerr; + + switch (le16_to_cpu(pkt->hdr.op)) { + case VIRTIO_VSOCK_OP_RESPONSE: + sk->sk_state = SS_CONNECTED; + sk->sk_socket->state = SS_CONNECTED; + vsock_insert_connected(vsk); + sk->sk_state_change(sk); + break; + case VIRTIO_VSOCK_OP_INVALID: + break; + case VIRTIO_VSOCK_OP_RST: + skerr = ECONNRESET; + err = 0; + goto destroy; + default: + skerr = EPROTO; + err = -EINVAL; + goto destroy; + } + return 0; + +destroy: + virtio_transport_reset(vsk, pkt); + sk->sk_state = SS_UNCONNECTED; + sk->sk_err = skerr; + sk->sk_error_report(sk); + return err; +} + +static int +virtio_transport_recv_connected(struct sock *sk, + struct virtio_vsock_pkt *pkt) +{ + struct vsock_sock *vsk = vsock_sk(sk); + struct virtio_vsock_sock *vvs = vsk->trans; + int err = 0; + + switch (le16_to_cpu(pkt->hdr.op)) { + case VIRTIO_VSOCK_OP_RW: + pkt->len = le32_to_cpu(pkt->hdr.len); + pkt->off = 0; + + spin_lock_bh(&vvs->rx_lock); + virtio_transport_inc_rx_pkt(vvs, pkt); + list_add_tail(&pkt->list, &vvs->rx_queue); + spin_unlock_bh(&vvs->rx_lock); + + sk->sk_data_ready(sk); + return err; + case VIRTIO_VSOCK_OP_CREDIT_UPDATE: + sk->sk_write_space(sk); + break; + case VIRTIO_VSOCK_OP_SHUTDOWN: + if (le32_to_cpu(pkt->hdr.flags) & VIRTIO_VSOCK_SHUTDOWN_RCV) + vsk->peer_shutdown |= RCV_SHUTDOWN; + if (le32_to_cpu(pkt->hdr.flags) & VIRTIO_VSOCK_SHUTDOWN_SEND) + vsk->peer_shutdown |= SEND_SHUTDOWN; + if (vsk->peer_shutdown == SHUTDOWN_MASK && + vsock_stream_has_data(vsk) <= 0) + sk->sk_state = SS_DISCONNECTING; + if (le32_to_cpu(pkt->hdr.flags)) + sk->sk_state_change(sk); + break; + case VIRTIO_VSOCK_OP_RST: + virtio_transport_do_close(vsk, true); + break; + default: + err = -EINVAL; + break; + } + + virtio_transport_free_pkt(pkt); + return err; +} + +static void +virtio_transport_recv_disconnecting(struct sock *sk, + struct virtio_vsock_pkt *pkt) +{ + struct vsock_sock *vsk = vsock_sk(sk); + + if (le16_to_cpu(pkt->hdr.op) == VIRTIO_VSOCK_OP_RST) + virtio_transport_do_close(vsk, true); +} + +static int +virtio_transport_send_response(struct vsock_sock *vsk, + struct virtio_vsock_pkt *pkt) +{ + struct virtio_vsock_pkt_info info = { + .op = VIRTIO_VSOCK_OP_RESPONSE, + .type = VIRTIO_VSOCK_TYPE_STREAM, + .remote_cid = le32_to_cpu(pkt->hdr.src_cid), + .remote_port = le32_to_cpu(pkt->hdr.src_port), + .reply = true, + }; + + return virtio_transport_send_pkt_info(vsk, &info); +} + +/* Handle server socket */ +static int +virtio_transport_recv_listen(struct sock *sk, struct virtio_vsock_pkt *pkt) +{ + struct vsock_sock *vsk = vsock_sk(sk); + struct vsock_sock *vchild; + struct sock *child; + + if (le16_to_cpu(pkt->hdr.op) != VIRTIO_VSOCK_OP_REQUEST) { + virtio_transport_reset(vsk, pkt); + return -EINVAL; + } + + if (sk_acceptq_is_full(sk)) { + virtio_transport_reset(vsk, pkt); + return -ENOMEM; + } + + child = __vsock_create(sock_net(sk), NULL, sk, GFP_KERNEL, + sk->sk_type, 0); + if (!child) { + virtio_transport_reset(vsk, pkt); + return -ENOMEM; + } + + sk->sk_ack_backlog++; + + lock_sock_nested(child, SINGLE_DEPTH_NESTING); + + child->sk_state = SS_CONNECTED; + + vchild = vsock_sk(child); + vsock_addr_init(&vchild->local_addr, le32_to_cpu(pkt->hdr.dst_cid), + le32_to_cpu(pkt->hdr.dst_port)); + vsock_addr_init(&vchild->remote_addr, le32_to_cpu(pkt->hdr.src_cid), + le32_to_cpu(pkt->hdr.src_port)); + + vsock_insert_connected(vchild); + vsock_enqueue_accept(sk, child); + virtio_transport_send_response(vchild, pkt); + + release_sock(child); + + sk->sk_data_ready(sk); + return 0; +} + +static bool virtio_transport_space_update(struct sock *sk, + struct virtio_vsock_pkt *pkt) +{ + struct vsock_sock *vsk = vsock_sk(sk); + struct virtio_vsock_sock *vvs = vsk->trans; + bool space_available; + + /* buf_alloc and fwd_cnt is always included in the hdr */ + spin_lock_bh(&vvs->tx_lock); + vvs->peer_buf_alloc = le32_to_cpu(pkt->hdr.buf_alloc); + vvs->peer_fwd_cnt = le32_to_cpu(pkt->hdr.fwd_cnt); + space_available = virtio_transport_has_space(vsk); + spin_unlock_bh(&vvs->tx_lock); + return space_available; +} + +/* We are under the virtio-vsock's vsock->rx_lock or vhost-vsock's vq->mutex + * lock. + */ +void virtio_transport_recv_pkt(struct virtio_vsock_pkt *pkt) +{ + struct sockaddr_vm src, dst; + struct vsock_sock *vsk; + struct sock *sk; + bool space_available; + + vsock_addr_init(&src, le32_to_cpu(pkt->hdr.src_cid), + le32_to_cpu(pkt->hdr.src_port)); + vsock_addr_init(&dst, le32_to_cpu(pkt->hdr.dst_cid), + le32_to_cpu(pkt->hdr.dst_port)); + + trace_virtio_transport_recv_pkt(src.svm_cid, src.svm_port, + dst.svm_cid, dst.svm_port, + le32_to_cpu(pkt->hdr.len), + le16_to_cpu(pkt->hdr.type), + le16_to_cpu(pkt->hdr.op), + le32_to_cpu(pkt->hdr.flags), + le32_to_cpu(pkt->hdr.buf_alloc), + le32_to_cpu(pkt->hdr.fwd_cnt)); + + if (le16_to_cpu(pkt->hdr.type) != VIRTIO_VSOCK_TYPE_STREAM) { + (void)virtio_transport_reset_no_sock(pkt); + goto free_pkt; + } + + /* The socket must be in connected or bound table + * otherwise send reset back + */ + sk = vsock_find_connected_socket(&src, &dst); + if (!sk) { + sk = vsock_find_bound_socket(&dst); + if (!sk) { + (void)virtio_transport_reset_no_sock(pkt); + goto free_pkt; + } + } + + vsk = vsock_sk(sk); + + space_available = virtio_transport_space_update(sk, pkt); + + lock_sock(sk); + + /* Update CID in case it has changed after a transport reset event */ + vsk->local_addr.svm_cid = dst.svm_cid; + + if (space_available) + sk->sk_write_space(sk); + + switch (sk->sk_state) { + case VSOCK_SS_LISTEN: + virtio_transport_recv_listen(sk, pkt); + virtio_transport_free_pkt(pkt); + break; + case SS_CONNECTING: + virtio_transport_recv_connecting(sk, pkt); + virtio_transport_free_pkt(pkt); + break; + case SS_CONNECTED: + virtio_transport_recv_connected(sk, pkt); + break; + case SS_DISCONNECTING: + virtio_transport_recv_disconnecting(sk, pkt); + virtio_transport_free_pkt(pkt); + break; + default: + virtio_transport_free_pkt(pkt); + break; + } + release_sock(sk); + + /* Release refcnt obtained when we fetched this socket out of the + * bound or connected list. + */ + sock_put(sk); + return; + +free_pkt: + virtio_transport_free_pkt(pkt); +} +EXPORT_SYMBOL_GPL(virtio_transport_recv_pkt); + +void virtio_transport_free_pkt(struct virtio_vsock_pkt *pkt) +{ + kfree(pkt->buf); + kfree(pkt); +} +EXPORT_SYMBOL_GPL(virtio_transport_free_pkt); + +MODULE_LICENSE("GPL v2"); +MODULE_AUTHOR("Asias He"); +MODULE_DESCRIPTION("common code for virtio vsock"); diff --git a/net/vmw_vsock/vmci_transport.c b/net/vmw_vsock/vmci_transport.c index 4120b7a538be..4be4fbbc0b50 100644 --- a/net/vmw_vsock/vmci_transport.c +++ b/net/vmw_vsock/vmci_transport.c @@ -1644,6 +1644,8 @@ static void vmci_transport_destruct(struct vsock_sock *vsk) static void vmci_transport_release(struct vsock_sock *vsk) { + vsock_remove_sock(vsk); + if (!vmci_handle_is_invalid(vmci_trans(vsk)->dg_handle)) { vmci_datagram_destroy_handle(vmci_trans(vsk)->dg_handle); vmci_trans(vsk)->dg_handle = VMCI_INVALID_HANDLE; diff --git a/net/wireless/chan.c b/net/wireless/chan.c index bb3d64ee68aa..0f506220a3bd 100644 --- a/net/wireless/chan.c +++ b/net/wireless/chan.c @@ -716,7 +716,7 @@ static bool cfg80211_ir_permissive_chan(struct wiphy *wiphy, ASSERT_RTNL(); - if (!config_enabled(CONFIG_CFG80211_REG_RELAX_NO_IR) || + if (!IS_ENABLED(CONFIG_CFG80211_REG_RELAX_NO_IR) || !(wiphy->regulatory_flags & REGULATORY_ENABLE_RELAX_NO_IR)) return false; diff --git a/net/wireless/core.c b/net/wireless/core.c index 7645e97362c0..2029b49a1df3 100644 --- a/net/wireless/core.c +++ b/net/wireless/core.c @@ -906,6 +906,8 @@ void cfg80211_unregister_wdev(struct wireless_dev *wdev) if (WARN_ON(wdev->netdev)) return; + nl80211_notify_iface(rdev, wdev, NL80211_CMD_DEL_INTERFACE); + list_del_rcu(&wdev->list); rdev->devlist_generation++; @@ -1079,6 +1081,8 @@ static int cfg80211_netdev_notifier_call(struct notifier_block *nb, wdev->iftype == NL80211_IFTYPE_P2P_CLIENT || wdev->iftype == NL80211_IFTYPE_ADHOC) && !wdev->use_4addr) dev->priv_flags |= IFF_DONT_BRIDGE; + + nl80211_notify_iface(rdev, wdev, NL80211_CMD_NEW_INTERFACE); break; case NETDEV_GOING_DOWN: cfg80211_leave(rdev, wdev); @@ -1157,6 +1161,8 @@ static int cfg80211_netdev_notifier_call(struct notifier_block *nb, * remove and clean it up. */ if (!list_empty(&wdev->list)) { + nl80211_notify_iface(rdev, wdev, + NL80211_CMD_DEL_INTERFACE); sysfs_remove_link(&dev->dev.kobj, "phy80211"); list_del_rcu(&wdev->list); rdev->devlist_generation++; diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index f02653a08993..499785778983 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -2751,7 +2751,7 @@ static int nl80211_new_interface(struct sk_buff *skb, struct genl_info *info) struct cfg80211_registered_device *rdev = info->user_ptr[0]; struct vif_params params; struct wireless_dev *wdev; - struct sk_buff *msg, *event; + struct sk_buff *msg; int err; enum nl80211_iftype type = NL80211_IFTYPE_UNSPECIFIED; u32 flags; @@ -2855,20 +2855,15 @@ static int nl80211_new_interface(struct sk_buff *skb, struct genl_info *info) return -ENOBUFS; } - event = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); - if (event) { - if (nl80211_send_iface(event, 0, 0, 0, - rdev, wdev, false) < 0) { - nlmsg_free(event); - goto out; - } - - genlmsg_multicast_netns(&nl80211_fam, wiphy_net(&rdev->wiphy), - event, 0, NL80211_MCGRP_CONFIG, - GFP_KERNEL); - } + /* + * For wdevs which have no associated netdev object (e.g. of type + * NL80211_IFTYPE_P2P_DEVICE), emit the NEW_INTERFACE event here. + * For all other types, the event will be generated from the + * netdev notifier + */ + if (!wdev->netdev) + nl80211_notify_iface(rdev, wdev, NL80211_CMD_NEW_INTERFACE); -out: return genlmsg_reply(msg, info); } @@ -2876,18 +2871,10 @@ static int nl80211_del_interface(struct sk_buff *skb, struct genl_info *info) { struct cfg80211_registered_device *rdev = info->user_ptr[0]; struct wireless_dev *wdev = info->user_ptr[1]; - struct sk_buff *msg; - int status; if (!rdev->ops->del_virtual_intf) return -EOPNOTSUPP; - msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); - if (msg && nl80211_send_iface(msg, 0, 0, 0, rdev, wdev, true) < 0) { - nlmsg_free(msg); - msg = NULL; - } - /* * If we remove a wireless device without a netdev then clear * user_ptr[1] so that nl80211_post_doit won't dereference it @@ -2898,15 +2885,7 @@ static int nl80211_del_interface(struct sk_buff *skb, struct genl_info *info) if (!wdev->netdev) info->user_ptr[1] = NULL; - status = rdev_del_virtual_intf(rdev, wdev); - if (status >= 0 && msg) - genlmsg_multicast_netns(&nl80211_fam, wiphy_net(&rdev->wiphy), - msg, 0, NL80211_MCGRP_CONFIG, - GFP_KERNEL); - else - nlmsg_free(msg); - - return status; + return rdev_del_virtual_intf(rdev, wdev); } static int nl80211_set_noack_map(struct sk_buff *skb, struct genl_info *info) @@ -5374,6 +5353,18 @@ static int nl80211_check_s32(const struct nlattr *nla, s32 min, s32 max, s32 *ou return 0; } +static int nl80211_check_power_mode(const struct nlattr *nla, + enum nl80211_mesh_power_mode min, + enum nl80211_mesh_power_mode max, + enum nl80211_mesh_power_mode *out) +{ + u32 val = nla_get_u32(nla); + if (val < min || val > max) + return -EINVAL; + *out = val; + return 0; +} + static int nl80211_parse_mesh_config(struct genl_info *info, struct mesh_config *cfg, u32 *mask_out) @@ -5518,7 +5509,7 @@ do { \ NL80211_MESH_POWER_ACTIVE, NL80211_MESH_POWER_MAX, mask, NL80211_MESHCONF_POWER_MODE, - nl80211_check_u32); + nl80211_check_power_mode); FILL_IN_MESH_PARAM_IF_SET(tb, cfg, dot11MeshAwakeWindowDuration, 0, 65535, mask, NL80211_MESHCONF_AWAKE_WINDOW, nl80211_check_u16); @@ -7773,12 +7764,13 @@ static int nl80211_join_ibss(struct sk_buff *skb, struct genl_info *info) ibss.beacon_interval = 100; - if (info->attrs[NL80211_ATTR_BEACON_INTERVAL]) { + if (info->attrs[NL80211_ATTR_BEACON_INTERVAL]) ibss.beacon_interval = nla_get_u32(info->attrs[NL80211_ATTR_BEACON_INTERVAL]); - if (ibss.beacon_interval < 1 || ibss.beacon_interval > 10000) - return -EINVAL; - } + + err = cfg80211_validate_beacon_int(rdev, ibss.beacon_interval); + if (err) + return err; if (!rdev->ops->join_ibss) return -EOPNOTSUPP; @@ -9252,9 +9244,10 @@ static int nl80211_join_mesh(struct sk_buff *skb, struct genl_info *info) if (info->attrs[NL80211_ATTR_BEACON_INTERVAL]) { setup.beacon_interval = nla_get_u32(info->attrs[NL80211_ATTR_BEACON_INTERVAL]); - if (setup.beacon_interval < 10 || - setup.beacon_interval > 10000) - return -EINVAL; + + err = cfg80211_validate_beacon_int(rdev, setup.beacon_interval); + if (err) + return err; } if (info->attrs[NL80211_ATTR_DTIM_PERIOD]) { @@ -11847,6 +11840,29 @@ void nl80211_notify_wiphy(struct cfg80211_registered_device *rdev, NL80211_MCGRP_CONFIG, GFP_KERNEL); } +void nl80211_notify_iface(struct cfg80211_registered_device *rdev, + struct wireless_dev *wdev, + enum nl80211_commands cmd) +{ + struct sk_buff *msg; + + WARN_ON(cmd != NL80211_CMD_NEW_INTERFACE && + cmd != NL80211_CMD_DEL_INTERFACE); + + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (!msg) + return; + + if (nl80211_send_iface(msg, 0, 0, 0, rdev, wdev, + cmd == NL80211_CMD_DEL_INTERFACE) < 0) { + nlmsg_free(msg); + return; + } + + genlmsg_multicast_netns(&nl80211_fam, wiphy_net(&rdev->wiphy), msg, 0, + NL80211_MCGRP_CONFIG, GFP_KERNEL); +} + static int nl80211_add_scan_req(struct sk_buff *msg, struct cfg80211_registered_device *rdev) { diff --git a/net/wireless/nl80211.h b/net/wireless/nl80211.h index a63f402b10b7..7e3821d7fcc5 100644 --- a/net/wireless/nl80211.h +++ b/net/wireless/nl80211.h @@ -7,6 +7,9 @@ int nl80211_init(void); void nl80211_exit(void); void nl80211_notify_wiphy(struct cfg80211_registered_device *rdev, enum nl80211_commands cmd); +void nl80211_notify_iface(struct cfg80211_registered_device *rdev, + struct wireless_dev *wdev, + enum nl80211_commands cmd); void nl80211_send_scan_start(struct cfg80211_registered_device *rdev, struct wireless_dev *wdev); struct sk_buff *nl80211_build_scan_msg(struct cfg80211_registered_device *rdev, diff --git a/net/wireless/util.c b/net/wireless/util.c index b7d1592bd5b8..0675f513e7b9 100644 --- a/net/wireless/util.c +++ b/net/wireless/util.c @@ -1559,7 +1559,7 @@ int cfg80211_validate_beacon_int(struct cfg80211_registered_device *rdev, struct wireless_dev *wdev; int res = 0; - if (!beacon_int) + if (beacon_int < 10 || beacon_int > 10000) return -EINVAL; list_for_each_entry(wdev, &rdev->wiphy.wdev_list, list) { |