diff options
Diffstat (limited to 'net')
443 files changed, 15439 insertions, 8544 deletions
diff --git a/net/6lowpan/Makefile b/net/6lowpan/Makefile index eb8baa72adc8..c6ffc55ee0d7 100644 --- a/net/6lowpan/Makefile +++ b/net/6lowpan/Makefile @@ -1,6 +1,6 @@ obj-$(CONFIG_6LOWPAN) += 6lowpan.o -6lowpan-y := iphc.o nhc.o +6lowpan-y := core.o iphc.o nhc.o #rfc6282 nhcs obj-$(CONFIG_6LOWPAN_NHC_DEST) += nhc_dest.o diff --git a/net/6lowpan/core.c b/net/6lowpan/core.c new file mode 100644 index 000000000000..ae1896fa45e2 --- /dev/null +++ b/net/6lowpan/core.c @@ -0,0 +1,40 @@ +/* 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. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * Authors: + * (C) 2015 Pengutronix, Alexander Aring <aar@pengutronix.de> + */ + +#include <linux/module.h> + +#include <net/6lowpan.h> + +void lowpan_netdev_setup(struct net_device *dev, enum lowpan_lltypes lltype) +{ + lowpan_priv(dev)->lltype = lltype; +} +EXPORT_SYMBOL(lowpan_netdev_setup); + +static int __init lowpan_module_init(void) +{ + request_module_nowait("ipv6"); + + request_module_nowait("nhc_dest"); + request_module_nowait("nhc_fragment"); + request_module_nowait("nhc_hop"); + request_module_nowait("nhc_ipv6"); + request_module_nowait("nhc_mobility"); + request_module_nowait("nhc_routing"); + request_module_nowait("nhc_udp"); + + return 0; +} +module_init(lowpan_module_init); + +MODULE_LICENSE("GPL"); diff --git a/net/6lowpan/iphc.c b/net/6lowpan/iphc.c index 94a375c04f21..1e0071fdcf72 100644 --- a/net/6lowpan/iphc.c +++ b/net/6lowpan/iphc.c @@ -48,7 +48,6 @@ #include <linux/bitops.h> #include <linux/if_arp.h> -#include <linux/module.h> #include <linux/netdevice.h> #include <net/6lowpan.h> #include <net/ipv6.h> @@ -284,7 +283,7 @@ lowpan_header_decompress(struct sk_buff *skb, struct net_device *dev, if (lowpan_fetch_skb(skb, &tmp, sizeof(tmp))) return -EINVAL; - hdr.flow_lbl[0] = (skb->data[0] & 0x0F) | ((tmp >> 2) & 0x30); + hdr.flow_lbl[0] = (tmp & 0x0F) | ((tmp >> 2) & 0x30); memcpy(&hdr.flow_lbl[1], &skb->data[0], 2); skb_pull(skb, 2); break; @@ -610,19 +609,3 @@ int lowpan_header_compress(struct sk_buff *skb, struct net_device *dev, return 0; } EXPORT_SYMBOL_GPL(lowpan_header_compress); - -static int __init lowpan_module_init(void) -{ - request_module_nowait("nhc_dest"); - request_module_nowait("nhc_fragment"); - request_module_nowait("nhc_hop"); - request_module_nowait("nhc_ipv6"); - request_module_nowait("nhc_mobility"); - request_module_nowait("nhc_routing"); - request_module_nowait("nhc_udp"); - - return 0; -} -module_init(lowpan_module_init); - -MODULE_LICENSE("GPL"); diff --git a/net/8021q/vlan_dev.c b/net/8021q/vlan_dev.c index 01d7ba840df8..fded86508117 100644 --- a/net/8021q/vlan_dev.c +++ b/net/8021q/vlan_dev.c @@ -791,10 +791,9 @@ void vlan_setup(struct net_device *dev) { ether_setup(dev); - dev->priv_flags |= IFF_802_1Q_VLAN; + dev->priv_flags |= IFF_802_1Q_VLAN | IFF_NO_QUEUE; dev->priv_flags &= ~IFF_TX_SKB_SHARING; netif_keep_dst(dev); - dev->tx_queue_len = 0; dev->netdev_ops = &vlan_netdev_ops; dev->destructor = vlan_dev_free; diff --git a/net/9p/trans_rdma.c b/net/9p/trans_rdma.c index 37a78d20c0f6..ba1210253f5e 100644 --- a/net/9p/trans_rdma.c +++ b/net/9p/trans_rdma.c @@ -94,8 +94,6 @@ struct p9_trans_rdma { struct ib_pd *pd; struct ib_qp *qp; struct ib_cq *cq; - struct ib_mr *dma_mr; - u32 lkey; long timeout; int sq_depth; struct semaphore sq_sem; @@ -382,9 +380,6 @@ static void rdma_destroy_trans(struct p9_trans_rdma *rdma) if (!rdma) return; - if (rdma->dma_mr && !IS_ERR(rdma->dma_mr)) - ib_dereg_mr(rdma->dma_mr); - if (rdma->qp && !IS_ERR(rdma->qp)) ib_destroy_qp(rdma->qp); @@ -415,7 +410,7 @@ post_recv(struct p9_client *client, struct p9_rdma_context *c) sge.addr = c->busa; sge.length = client->msize; - sge.lkey = rdma->lkey; + sge.lkey = rdma->pd->local_dma_lkey; wr.next = NULL; c->wc_op = IB_WC_RECV; @@ -506,7 +501,7 @@ dont_need_post_recv: sge.addr = c->busa; sge.length = c->req->tc->size; - sge.lkey = rdma->lkey; + sge.lkey = rdma->pd->local_dma_lkey; wr.next = NULL; c->wc_op = IB_WC_SEND; @@ -647,7 +642,6 @@ rdma_create_trans(struct p9_client *client, const char *addr, char *args) struct p9_trans_rdma *rdma; struct rdma_conn_param conn_param; struct ib_qp_init_attr qp_attr; - struct ib_device_attr devattr; struct ib_cq_init_attr cq_attr = {}; /* Parse the transport specific mount options */ @@ -700,11 +694,6 @@ rdma_create_trans(struct p9_client *client, const char *addr, char *args) if (err || (rdma->state != P9_RDMA_ROUTE_RESOLVED)) goto error; - /* Query the device attributes */ - err = ib_query_device(rdma->cm_id->device, &devattr); - if (err) - goto error; - /* Create the Completion Queue */ cq_attr.cqe = opts.sq_depth + opts.rq_depth + 1; rdma->cq = ib_create_cq(rdma->cm_id->device, cq_comp_handler, @@ -719,17 +708,6 @@ rdma_create_trans(struct p9_client *client, const char *addr, char *args) if (IS_ERR(rdma->pd)) goto error; - /* Cache the DMA lkey in the transport */ - rdma->dma_mr = NULL; - if (devattr.device_cap_flags & IB_DEVICE_LOCAL_DMA_LKEY) - rdma->lkey = rdma->cm_id->device->local_dma_lkey; - else { - rdma->dma_mr = ib_get_dma_mr(rdma->pd, IB_ACCESS_LOCAL_WRITE); - if (IS_ERR(rdma->dma_mr)) - goto error; - rdma->lkey = rdma->dma_mr->lkey; - } - /* Create the Queue Pair */ memset(&qp_attr, 0, sizeof qp_attr); qp_attr.event_handler = qp_event_handler; diff --git a/net/Kconfig b/net/Kconfig index 57a7c5af3175..7021c1bf44d6 100644 --- a/net/Kconfig +++ b/net/Kconfig @@ -374,6 +374,13 @@ source "net/caif/Kconfig" source "net/ceph/Kconfig" source "net/nfc/Kconfig" +config LWTUNNEL + bool "Network light weight tunnels" + ---help--- + This feature provides an infrastructure to support light weight + tunnels like mpls. There is no netdevice associated with a light + weight tunnel endpoint. Tunnel encapsulation parameters are stored + with light weight tunnel state associated with fib routes. endif # if NET diff --git a/net/atm/br2684.c b/net/atm/br2684.c index cc78538d163b..aa0047c5c467 100644 --- a/net/atm/br2684.c +++ b/net/atm/br2684.c @@ -802,13 +802,10 @@ static int br2684_seq_show(struct seq_file *seq, void *v) (brdev->payload == p_bridged) ? "bridged" : "routed", brvcc->copies_failed, brvcc->copies_needed); #ifdef CONFIG_ATM_BR2684_IPFILTER -#define b1(var, byte) ((u8 *) &brvcc->filter.var)[byte] -#define bs(var) b1(var, 0), b1(var, 1), b1(var, 2), b1(var, 3) if (brvcc->filter.netmask != 0) - seq_printf(seq, " filter=%d.%d.%d.%d/" - "%d.%d.%d.%d\n", bs(prefix), bs(netmask)); -#undef bs -#undef b1 + seq_printf(seq, " filter=%pI4/%pI4\n", + &brvcc->filter.prefix, + &brvcc->filter.netmask); #endif /* CONFIG_ATM_BR2684_IPFILTER */ } return 0; diff --git a/net/batman-adv/bat_iv_ogm.c b/net/batman-adv/bat_iv_ogm.c index 753383c2215c..912d9c36fb1c 100644 --- a/net/batman-adv/bat_iv_ogm.c +++ b/net/batman-adv/bat_iv_ogm.c @@ -77,8 +77,7 @@ enum batadv_dup_status { * @lq_index: index to store the value at * @value: value to store in the ring buffer */ -static void batadv_ring_buffer_set(uint8_t lq_recv[], uint8_t *lq_index, - uint8_t value) +static void batadv_ring_buffer_set(u8 lq_recv[], u8 *lq_index, u8 value) { lq_recv[*lq_index] = value; *lq_index = (*lq_index + 1) % BATADV_TQ_GLOBAL_WINDOW_SIZE; @@ -91,12 +90,12 @@ static void batadv_ring_buffer_set(uint8_t lq_recv[], uint8_t *lq_index, * * Returns computed average value. */ -static uint8_t batadv_ring_buffer_avg(const uint8_t lq_recv[]) +static u8 batadv_ring_buffer_avg(const u8 lq_recv[]) { - const uint8_t *ptr; - uint16_t count = 0; - uint16_t i = 0; - uint16_t sum = 0; + const u8 *ptr; + u16 count = 0; + u16 i = 0; + u16 sum = 0; ptr = lq_recv; @@ -113,7 +112,7 @@ static uint8_t batadv_ring_buffer_avg(const uint8_t lq_recv[]) if (count == 0) return 0; - return (uint8_t)(sum / count); + return (u8)(sum / count); } /** @@ -155,14 +154,14 @@ static int batadv_iv_ogm_orig_add_if(struct batadv_orig_node *orig_node, kfree(orig_node->bat_iv.bcast_own); orig_node->bat_iv.bcast_own = data_ptr; - data_ptr = kmalloc_array(max_if_num, sizeof(uint8_t), GFP_ATOMIC); + data_ptr = kmalloc_array(max_if_num, sizeof(u8), GFP_ATOMIC); if (!data_ptr) { kfree(orig_node->bat_iv.bcast_own); goto unlock; } memcpy(data_ptr, orig_node->bat_iv.bcast_own_sum, - (max_if_num - 1) * sizeof(uint8_t)); + (max_if_num - 1) * sizeof(u8)); kfree(orig_node->bat_iv.bcast_own_sum); orig_node->bat_iv.bcast_own_sum = data_ptr; @@ -215,19 +214,19 @@ free_bcast_own: if (max_if_num == 0) goto free_own_sum; - data_ptr = kmalloc_array(max_if_num, sizeof(uint8_t), GFP_ATOMIC); + data_ptr = kmalloc_array(max_if_num, sizeof(u8), GFP_ATOMIC); if (!data_ptr) { kfree(orig_node->bat_iv.bcast_own); goto unlock; } memcpy(data_ptr, orig_node->bat_iv.bcast_own_sum, - del_if_num * sizeof(uint8_t)); + del_if_num * sizeof(u8)); - if_offset = (del_if_num + 1) * sizeof(uint8_t); - memcpy((char *)data_ptr + del_if_num * sizeof(uint8_t), + if_offset = (del_if_num + 1) * sizeof(u8); + memcpy((char *)data_ptr + del_if_num * sizeof(u8), orig_node->bat_iv.bcast_own_sum + if_offset, - (max_if_num - del_if_num) * sizeof(uint8_t)); + (max_if_num - del_if_num) * sizeof(u8)); free_own_sum: kfree(orig_node->bat_iv.bcast_own_sum); @@ -250,7 +249,7 @@ unlock: * If the object does not exists it is created an initialised. */ static struct batadv_orig_node * -batadv_iv_ogm_orig_get(struct batadv_priv *bat_priv, const uint8_t *addr) +batadv_iv_ogm_orig_get(struct batadv_priv *bat_priv, const u8 *addr) { struct batadv_orig_node *orig_node; int size, hash_added; @@ -270,7 +269,7 @@ batadv_iv_ogm_orig_get(struct batadv_priv *bat_priv, const uint8_t *addr) if (!orig_node->bat_iv.bcast_own) goto free_orig_node; - size = bat_priv->num_ifaces * sizeof(uint8_t); + size = bat_priv->num_ifaces * sizeof(u8); orig_node->bat_iv.bcast_own_sum = kzalloc(size, GFP_ATOMIC); if (!orig_node->bat_iv.bcast_own_sum) goto free_orig_node; @@ -293,43 +292,17 @@ free_orig_node: static struct batadv_neigh_node * batadv_iv_ogm_neigh_new(struct batadv_hard_iface *hard_iface, - const uint8_t *neigh_addr, + const u8 *neigh_addr, struct batadv_orig_node *orig_node, struct batadv_orig_node *orig_neigh) { - struct batadv_priv *bat_priv = netdev_priv(hard_iface->soft_iface); - struct batadv_neigh_node *neigh_node, *tmp_neigh_node; + struct batadv_neigh_node *neigh_node; - neigh_node = batadv_neigh_node_new(hard_iface, neigh_addr, orig_node); + neigh_node = batadv_neigh_node_new(orig_node, hard_iface, neigh_addr); if (!neigh_node) goto out; - if (!atomic_inc_not_zero(&hard_iface->refcount)) { - kfree(neigh_node); - neigh_node = NULL; - goto out; - } - neigh_node->orig_node = orig_neigh; - neigh_node->if_incoming = hard_iface; - - spin_lock_bh(&orig_node->neigh_list_lock); - tmp_neigh_node = batadv_neigh_node_get(orig_node, hard_iface, - neigh_addr); - if (!tmp_neigh_node) { - hlist_add_head_rcu(&neigh_node->list, &orig_node->neigh_list); - } else { - kfree(neigh_node); - batadv_hardif_free_ref(hard_iface); - neigh_node = tmp_neigh_node; - } - spin_unlock_bh(&orig_node->neigh_list_lock); - - if (!tmp_neigh_node) - batadv_dbg(BATADV_DBG_BATMAN, bat_priv, - "Creating new neighbor %pM for orig_node %pM on interface %s\n", - neigh_addr, orig_node->orig, - hard_iface->net_dev->name); out: return neigh_node; @@ -339,7 +312,7 @@ static int batadv_iv_ogm_iface_enable(struct batadv_hard_iface *hard_iface) { struct batadv_ogm_packet *batadv_ogm_packet; unsigned char *ogm_buff; - uint32_t random_seqno; + u32 random_seqno; /* randomize initial seqno to avoid collision */ get_random_bytes(&random_seqno, sizeof(random_seqno)); @@ -411,8 +384,7 @@ static unsigned long batadv_iv_ogm_fwd_send_time(void) } /* apply hop penalty for a normal link */ -static uint8_t batadv_hop_penalty(uint8_t tq, - const struct batadv_priv *bat_priv) +static u8 batadv_hop_penalty(u8 tq, const struct batadv_priv *bat_priv) { int hop_penalty = atomic_read(&bat_priv->hop_penalty); int new_tq; @@ -442,11 +414,11 @@ static void batadv_iv_ogm_send_to_if(struct batadv_forw_packet *forw_packet, { struct batadv_priv *bat_priv = netdev_priv(hard_iface->soft_iface); const char *fwd_str; - uint8_t packet_num; - int16_t buff_pos; + u8 packet_num; + s16 buff_pos; struct batadv_ogm_packet *batadv_ogm_packet; struct sk_buff *skb; - uint8_t *packet_pos; + u8 *packet_pos; if (hard_iface->if_status != BATADV_IF_ACTIVE) return; @@ -837,7 +809,7 @@ static void batadv_iv_ogm_forward(struct batadv_orig_node *orig_node, struct batadv_hard_iface *if_outgoing) { struct batadv_priv *bat_priv = netdev_priv(if_incoming->soft_iface); - uint16_t tvlv_len; + u16 tvlv_len; if (batadv_ogm_packet->ttl <= 1) { batadv_dbg(BATADV_DBG_BATMAN, bat_priv, "ttl exceeded\n"); @@ -896,9 +868,9 @@ batadv_iv_ogm_slide_own_bcast_window(struct batadv_hard_iface *hard_iface) struct hlist_head *head; struct batadv_orig_node *orig_node; unsigned long *word; - uint32_t i; + u32 i; size_t word_index; - uint8_t *w; + u8 *w; int if_num; for (i = 0; i < hash->size; i++) { @@ -927,8 +899,8 @@ static void batadv_iv_ogm_schedule(struct batadv_hard_iface *hard_iface) struct batadv_ogm_packet *batadv_ogm_packet; struct batadv_hard_iface *primary_if, *tmp_hard_iface; int *ogm_buff_len = &hard_iface->bat_iv.ogm_buff_len; - uint32_t seqno; - uint16_t tvlv_len = 0; + u32 seqno; + u16 tvlv_len = 0; unsigned long send_time; primary_if = batadv_primary_if_get_selected(bat_priv); @@ -947,7 +919,7 @@ static void batadv_iv_ogm_schedule(struct batadv_hard_iface *hard_iface) batadv_ogm_packet->tvlv_len = htons(tvlv_len); /* change sequence number to network order */ - seqno = (uint32_t)atomic_read(&hard_iface->bat_iv.ogm_seqno); + seqno = (u32)atomic_read(&hard_iface->bat_iv.ogm_seqno); batadv_ogm_packet->seqno = htonl(seqno); atomic_inc(&hard_iface->bat_iv.ogm_seqno); @@ -970,7 +942,7 @@ static void batadv_iv_ogm_schedule(struct batadv_hard_iface *hard_iface) rcu_read_lock(); list_for_each_entry_rcu(tmp_hard_iface, &batadv_hardif_list, list) { if (tmp_hard_iface->soft_iface != hard_iface->soft_iface) - continue; + continue; batadv_iv_ogm_queue_add(bat_priv, *ogm_buff, *ogm_buff_len, hard_iface, tmp_hard_iface, 1, send_time); @@ -1006,13 +978,14 @@ batadv_iv_ogm_orig_update(struct batadv_priv *bat_priv, { struct batadv_neigh_ifinfo *neigh_ifinfo = NULL; struct batadv_neigh_ifinfo *router_ifinfo = NULL; - struct batadv_neigh_node *neigh_node = NULL, *tmp_neigh_node = NULL; + struct batadv_neigh_node *neigh_node = NULL; + struct batadv_neigh_node *tmp_neigh_node = NULL; struct batadv_neigh_node *router = NULL; struct batadv_orig_node *orig_node_tmp; int if_num; - uint8_t sum_orig, sum_neigh; - uint8_t *neigh_addr; - uint8_t tq_avg; + u8 sum_orig, sum_neigh; + u8 *neigh_addr; + u8 tq_avg; batadv_dbg(BATADV_DBG_BATMAN, bat_priv, "update_originator(): Searching and updating originator entry of received packet\n"); @@ -1164,8 +1137,8 @@ static int batadv_iv_ogm_calc_tq(struct batadv_orig_node *orig_node, struct batadv_priv *bat_priv = netdev_priv(if_incoming->soft_iface); struct batadv_neigh_node *neigh_node = NULL, *tmp_neigh_node; struct batadv_neigh_ifinfo *neigh_ifinfo; - uint8_t total_count; - uint8_t orig_eq_count, neigh_rq_count, neigh_rq_inv, tq_own; + u8 total_count; + u8 orig_eq_count, neigh_rq_count, neigh_rq_inv, tq_own; unsigned int neigh_rq_inv_cube, neigh_rq_max_cube; int tq_asym_penalty, inv_asym_penalty, if_num, ret = 0; unsigned int combined_tq; @@ -1311,13 +1284,13 @@ batadv_iv_ogm_update_seqnos(const struct ethhdr *ethhdr, struct batadv_neigh_node *neigh_node; struct batadv_neigh_ifinfo *neigh_ifinfo; int is_dup; - int32_t seq_diff; + s32 seq_diff; int need_update = 0; int set_mark; enum batadv_dup_status ret = BATADV_NO_DUP; - uint32_t seqno = ntohl(batadv_ogm_packet->seqno); - uint8_t *neigh_addr; - uint8_t packet_count; + u32 seqno = ntohl(batadv_ogm_packet->seqno); + u8 *neigh_addr; + u8 packet_count; unsigned long *bitmap; orig_node = batadv_iv_ogm_orig_get(bat_priv, batadv_ogm_packet->orig); @@ -1406,7 +1379,8 @@ batadv_iv_ogm_process_per_outif(const struct sk_buff *skb, int ogm_offset, struct batadv_hard_iface *if_outgoing) { struct batadv_priv *bat_priv = netdev_priv(if_incoming->soft_iface); - struct batadv_neigh_node *router = NULL, *router_router = NULL; + struct batadv_neigh_node *router = NULL; + struct batadv_neigh_node *router_router = NULL; struct batadv_orig_node *orig_neigh_node; struct batadv_orig_ifinfo *orig_ifinfo; struct batadv_neigh_node *orig_neigh_router = NULL; @@ -1418,7 +1392,7 @@ batadv_iv_ogm_process_per_outif(const struct sk_buff *skb, int ogm_offset, bool sameseq, similar_ttl; struct sk_buff *skb_priv; struct ethhdr *ethhdr; - uint8_t *prev_sender; + u8 *prev_sender; int is_bidirect; /* create a private copy of the skb, as some functions change tq value @@ -1600,7 +1574,7 @@ static void batadv_iv_ogm_process(const struct sk_buff *skb, int ogm_offset, struct batadv_orig_node *orig_neigh_node, *orig_node; struct batadv_hard_iface *hard_iface; struct batadv_ogm_packet *ogm_packet; - uint32_t if_incoming_seqno; + u32 if_incoming_seqno; bool has_directlink_flag; struct ethhdr *ethhdr; bool is_my_oldorig = false; @@ -1673,9 +1647,9 @@ static void batadv_iv_ogm_process(const struct sk_buff *skb, int ogm_offset, if (is_my_orig) { unsigned long *word; int offset; - int32_t bit_pos; - int16_t if_num; - uint8_t *weight; + s32 bit_pos; + s16 if_num; + u8 *weight; orig_neigh_node = batadv_iv_ogm_orig_get(bat_priv, ethhdr->h_source); @@ -1751,7 +1725,7 @@ static int batadv_iv_ogm_receive(struct sk_buff *skb, { struct batadv_priv *bat_priv = netdev_priv(if_incoming->soft_iface); struct batadv_ogm_packet *ogm_packet; - uint8_t *packet_pos; + u8 *packet_pos; int ogm_offset; bool ret; @@ -1835,7 +1809,7 @@ static void batadv_iv_ogm_orig_print(struct batadv_priv *bat_priv, unsigned long last_seen_jiffies; struct hlist_head *head; int batman_count = 0; - uint32_t i; + u32 i; seq_printf(seq, " %-15s %s (%s/%i) %17s [%10s]: %20s ...\n", "Originator", "last-seen", "#", BATADV_TQ_MAX_VALUE, @@ -1903,7 +1877,7 @@ static int batadv_iv_ogm_neigh_cmp(struct batadv_neigh_node *neigh1, struct batadv_hard_iface *if_outgoing2) { struct batadv_neigh_ifinfo *neigh1_ifinfo, *neigh2_ifinfo; - uint8_t tq1, tq2; + u8 tq1, tq2; int diff; neigh1_ifinfo = batadv_neigh_ifinfo_get(neigh1, if_outgoing1); @@ -1945,7 +1919,7 @@ batadv_iv_ogm_neigh_is_eob(struct batadv_neigh_node *neigh1, struct batadv_hard_iface *if_outgoing2) { struct batadv_neigh_ifinfo *neigh1_ifinfo, *neigh2_ifinfo; - uint8_t tq1, tq2; + u8 tq1, tq2; bool ret; neigh1_ifinfo = batadv_neigh_ifinfo_get(neigh1, if_outgoing1); diff --git a/net/batman-adv/bitarray.c b/net/batman-adv/bitarray.c index cf68c328345e..25cbc36e997a 100644 --- a/net/batman-adv/bitarray.c +++ b/net/batman-adv/bitarray.c @@ -21,7 +21,7 @@ #include <linux/bitmap.h> /* shift the packet array by n places. */ -static void batadv_bitmap_shift_left(unsigned long *seq_bits, int32_t n) +static void batadv_bitmap_shift_left(unsigned long *seq_bits, s32 n) { if (n <= 0 || n >= BATADV_TQ_LOCAL_WINDOW_SIZE) return; @@ -35,8 +35,8 @@ static void batadv_bitmap_shift_left(unsigned long *seq_bits, int32_t n) * 1 if the window was moved (either new or very old) * 0 if the window was not moved/shifted. */ -int batadv_bit_get_packet(void *priv, unsigned long *seq_bits, - int32_t seq_num_diff, int set_mark) +int batadv_bit_get_packet(void *priv, unsigned long *seq_bits, s32 seq_num_diff, + int set_mark) { struct batadv_priv *bat_priv = priv; diff --git a/net/batman-adv/bitarray.h b/net/batman-adv/bitarray.h index 0c2456225fae..0226b220fe5b 100644 --- a/net/batman-adv/bitarray.h +++ b/net/batman-adv/bitarray.h @@ -28,9 +28,9 @@ * and curr_seqno is within range of last_seqno. Otherwise returns 0. */ static inline int batadv_test_bit(const unsigned long *seq_bits, - uint32_t last_seqno, uint32_t curr_seqno) + u32 last_seqno, u32 curr_seqno) { - int32_t diff; + s32 diff; diff = last_seqno - curr_seqno; if (diff < 0 || diff >= BATADV_TQ_LOCAL_WINDOW_SIZE) @@ -39,7 +39,7 @@ static inline int batadv_test_bit(const unsigned long *seq_bits, } /* turn corresponding bit on, so we can remember that we got the packet */ -static inline void batadv_set_bit(unsigned long *seq_bits, int32_t n) +static inline void batadv_set_bit(unsigned long *seq_bits, s32 n) { /* if too old, just drop it */ if (n < 0 || n >= BATADV_TQ_LOCAL_WINDOW_SIZE) @@ -51,7 +51,7 @@ static inline void batadv_set_bit(unsigned long *seq_bits, int32_t n) /* receive and process one packet, returns 1 if received seq_num is considered * new, 0 if old */ -int batadv_bit_get_packet(void *priv, unsigned long *seq_bits, - int32_t seq_num_diff, int set_mark); +int batadv_bit_get_packet(void *priv, unsigned long *seq_bits, s32 seq_num_diff, + int set_mark); #endif /* _NET_BATMAN_ADV_BITARRAY_H_ */ diff --git a/net/batman-adv/bridge_loop_avoidance.c b/net/batman-adv/bridge_loop_avoidance.c index ba0609292ae7..191a70290dca 100644 --- a/net/batman-adv/bridge_loop_avoidance.c +++ b/net/batman-adv/bridge_loop_avoidance.c @@ -51,7 +51,7 @@ #include "packet.h" #include "translation-table.h" -static const uint8_t batadv_announce_mac[4] = {0x43, 0x05, 0x43, 0x05}; +static const u8 batadv_announce_mac[4] = {0x43, 0x05, 0x43, 0x05}; static void batadv_bla_periodic_work(struct work_struct *work); static void @@ -59,10 +59,10 @@ batadv_bla_send_announce(struct batadv_priv *bat_priv, struct batadv_bla_backbone_gw *backbone_gw); /* return the index of the claim */ -static inline uint32_t batadv_choose_claim(const void *data, uint32_t size) +static inline u32 batadv_choose_claim(const void *data, u32 size) { struct batadv_bla_claim *claim = (struct batadv_bla_claim *)data; - uint32_t hash = 0; + u32 hash = 0; hash = jhash(&claim->addr, sizeof(claim->addr), hash); hash = jhash(&claim->vid, sizeof(claim->vid), hash); @@ -71,11 +71,10 @@ static inline uint32_t batadv_choose_claim(const void *data, uint32_t size) } /* return the index of the backbone gateway */ -static inline uint32_t batadv_choose_backbone_gw(const void *data, - uint32_t size) +static inline u32 batadv_choose_backbone_gw(const void *data, u32 size) { const struct batadv_bla_claim *claim = (struct batadv_bla_claim *)data; - uint32_t hash = 0; + u32 hash = 0; hash = jhash(&claim->addr, sizeof(claim->addr), hash); hash = jhash(&claim->vid, sizeof(claim->vid), hash); @@ -89,7 +88,8 @@ static int batadv_compare_backbone_gw(const struct hlist_node *node, { const void *data1 = container_of(node, struct batadv_bla_backbone_gw, hash_entry); - const struct batadv_bla_backbone_gw *gw1 = data1, *gw2 = data2; + const struct batadv_bla_backbone_gw *gw1 = data1; + const struct batadv_bla_backbone_gw *gw2 = data2; if (!batadv_compare_eth(gw1->orig, gw2->orig)) return 0; @@ -106,7 +106,8 @@ static int batadv_compare_claim(const struct hlist_node *node, { const void *data1 = container_of(node, struct batadv_bla_claim, hash_entry); - const struct batadv_bla_claim *cl1 = data1, *cl2 = data2; + const struct batadv_bla_claim *cl1 = data1; + const struct batadv_bla_claim *cl2 = data2; if (!batadv_compare_eth(cl1->addr, cl2->addr)) return 0; @@ -192,8 +193,8 @@ static struct batadv_bla_claim * Returns claim if found or NULL otherwise. */ static struct batadv_bla_backbone_gw * -batadv_backbone_hash_find(struct batadv_priv *bat_priv, - uint8_t *addr, unsigned short vid) +batadv_backbone_hash_find(struct batadv_priv *bat_priv, u8 *addr, + unsigned short vid) { struct batadv_hashtable *hash = bat_priv->bla.backbone_hash; struct hlist_head *head; @@ -269,14 +270,14 @@ batadv_bla_del_backbone_claims(struct batadv_bla_backbone_gw *backbone_gw) * @vid: the VLAN ID * @claimtype: the type of the claim (CLAIM, UNCLAIM, ANNOUNCE, ...) */ -static void batadv_bla_send_claim(struct batadv_priv *bat_priv, uint8_t *mac, +static void batadv_bla_send_claim(struct batadv_priv *bat_priv, u8 *mac, unsigned short vid, int claimtype) { struct sk_buff *skb; struct ethhdr *ethhdr; struct batadv_hard_iface *primary_if; struct net_device *soft_iface; - uint8_t *hw_src; + u8 *hw_src; struct batadv_bla_claim_dst local_claim_dest; __be32 zeroip = 0; @@ -304,13 +305,13 @@ static void batadv_bla_send_claim(struct batadv_priv *bat_priv, uint8_t *mac, * with XX = claim type * and YY:YY = group id */ - (uint8_t *)&local_claim_dest); + (u8 *)&local_claim_dest); if (!skb) goto out; ethhdr = (struct ethhdr *)skb->data; - hw_src = (uint8_t *)ethhdr + ETH_HLEN + sizeof(struct arphdr); + hw_src = (u8 *)ethhdr + ETH_HLEN + sizeof(struct arphdr); /* now we pretend that the client would have sent this ... */ switch (claimtype) { @@ -383,7 +384,7 @@ out: * be found. */ static struct batadv_bla_backbone_gw * -batadv_bla_get_backbone_gw(struct batadv_priv *bat_priv, uint8_t *orig, +batadv_bla_get_backbone_gw(struct batadv_priv *bat_priv, u8 *orig, unsigned short vid, bool own_backbone) { struct batadv_bla_backbone_gw *entry; @@ -552,7 +553,7 @@ static void batadv_bla_send_request(struct batadv_bla_backbone_gw *backbone_gw) static void batadv_bla_send_announce(struct batadv_priv *bat_priv, struct batadv_bla_backbone_gw *backbone_gw) { - uint8_t mac[ETH_ALEN]; + u8 mac[ETH_ALEN]; __be16 crc; memcpy(mac, batadv_announce_mac, 4); @@ -571,7 +572,7 @@ static void batadv_bla_send_announce(struct batadv_priv *bat_priv, * @backbone_gw: the backbone gateway which claims it */ static void batadv_bla_add_claim(struct batadv_priv *bat_priv, - const uint8_t *mac, const unsigned short vid, + const u8 *mac, const unsigned short vid, struct batadv_bla_backbone_gw *backbone_gw) { struct batadv_bla_claim *claim; @@ -635,7 +636,7 @@ claim_free_ref: * given mac address and vid. */ static void batadv_bla_del_claim(struct batadv_priv *bat_priv, - const uint8_t *mac, const unsigned short vid) + const u8 *mac, const unsigned short vid) { struct batadv_bla_claim search_claim, *claim; @@ -659,12 +660,11 @@ static void batadv_bla_del_claim(struct batadv_priv *bat_priv, } /* check for ANNOUNCE frame, return 1 if handled */ -static int batadv_handle_announce(struct batadv_priv *bat_priv, - uint8_t *an_addr, uint8_t *backbone_addr, - unsigned short vid) +static int batadv_handle_announce(struct batadv_priv *bat_priv, u8 *an_addr, + u8 *backbone_addr, unsigned short vid) { struct batadv_bla_backbone_gw *backbone_gw; - uint16_t crc; + u16 crc; if (memcmp(an_addr, batadv_announce_mac, 4) != 0) return 0; @@ -708,8 +708,8 @@ static int batadv_handle_announce(struct batadv_priv *bat_priv, /* check for REQUEST frame, return 1 if handled */ static int batadv_handle_request(struct batadv_priv *bat_priv, struct batadv_hard_iface *primary_if, - uint8_t *backbone_addr, - struct ethhdr *ethhdr, unsigned short vid) + u8 *backbone_addr, struct ethhdr *ethhdr, + unsigned short vid) { /* check for REQUEST frame */ if (!batadv_compare_eth(backbone_addr, ethhdr->h_dest)) @@ -732,8 +732,8 @@ static int batadv_handle_request(struct batadv_priv *bat_priv, /* check for UNCLAIM frame, return 1 if handled */ static int batadv_handle_unclaim(struct batadv_priv *bat_priv, struct batadv_hard_iface *primary_if, - uint8_t *backbone_addr, - uint8_t *claim_addr, unsigned short vid) + u8 *backbone_addr, u8 *claim_addr, + unsigned short vid) { struct batadv_bla_backbone_gw *backbone_gw; @@ -761,7 +761,7 @@ static int batadv_handle_unclaim(struct batadv_priv *bat_priv, /* check for CLAIM frame, return 1 if handled */ static int batadv_handle_claim(struct batadv_priv *bat_priv, struct batadv_hard_iface *primary_if, - uint8_t *backbone_addr, uint8_t *claim_addr, + u8 *backbone_addr, u8 *claim_addr, unsigned short vid) { struct batadv_bla_backbone_gw *backbone_gw; @@ -805,10 +805,10 @@ static int batadv_handle_claim(struct batadv_priv *bat_priv, */ static int batadv_check_claim_group(struct batadv_priv *bat_priv, struct batadv_hard_iface *primary_if, - uint8_t *hw_src, uint8_t *hw_dst, + u8 *hw_src, u8 *hw_dst, struct ethhdr *ethhdr) { - uint8_t *backbone_addr; + u8 *backbone_addr; struct batadv_orig_node *orig_node; struct batadv_bla_claim_dst *bla_dst, *bla_dst_own; @@ -877,7 +877,7 @@ static int batadv_bla_process_claim(struct batadv_priv *bat_priv, struct sk_buff *skb) { struct batadv_bla_claim_dst *bla_dst, *bla_dst_own; - uint8_t *hw_src, *hw_dst; + u8 *hw_src, *hw_dst; struct vlan_hdr *vhdr, vhdr_buf; struct ethhdr *ethhdr; struct arphdr *arphdr; @@ -923,7 +923,7 @@ static int batadv_bla_process_claim(struct batadv_priv *bat_priv, /* pskb_may_pull() may have modified the pointers, get ethhdr again */ ethhdr = eth_hdr(skb); - arphdr = (struct arphdr *)((uint8_t *)ethhdr + headlen); + arphdr = (struct arphdr *)((u8 *)ethhdr + headlen); /* Check whether the ARP frame carries a valid * IP information @@ -937,7 +937,7 @@ static int batadv_bla_process_claim(struct batadv_priv *bat_priv, if (arphdr->ar_pln != 4) return 0; - hw_src = (uint8_t *)arphdr + sizeof(struct arphdr); + hw_src = (u8 *)arphdr + sizeof(struct arphdr); hw_dst = hw_src + ETH_ALEN + 4; bla_dst = (struct batadv_bla_claim_dst *)hw_dst; bla_dst_own = &bat_priv->bla.claim_dest; @@ -1238,9 +1238,9 @@ static struct lock_class_key batadv_backbone_hash_lock_class_key; int batadv_bla_init(struct batadv_priv *bat_priv) { int i; - uint8_t claim_dest[ETH_ALEN] = {0xff, 0x43, 0x05, 0x00, 0x00, 0x00}; + u8 claim_dest[ETH_ALEN] = {0xff, 0x43, 0x05, 0x00, 0x00, 0x00}; struct batadv_hard_iface *primary_if; - uint16_t crc; + u16 crc; unsigned long entrytime; spin_lock_init(&bat_priv->bla.bcast_duplist_lock); @@ -1368,7 +1368,7 @@ out: * * Returns true if orig is a backbone for this vid, false otherwise. */ -bool batadv_bla_is_backbone_gw_orig(struct batadv_priv *bat_priv, uint8_t *orig, +bool batadv_bla_is_backbone_gw_orig(struct batadv_priv *bat_priv, u8 *orig, unsigned short vid) { struct batadv_hashtable *hash = bat_priv->bla.backbone_hash; @@ -1647,9 +1647,9 @@ int batadv_bla_claim_table_seq_print_text(struct seq_file *seq, void *offset) struct batadv_bla_claim *claim; struct batadv_hard_iface *primary_if; struct hlist_head *head; - uint32_t i; + u32 i; bool is_own; - uint8_t *primary_addr; + u8 *primary_addr; primary_if = batadv_seq_print_text_primary_if_get(seq); if (!primary_if) @@ -1692,9 +1692,9 @@ int batadv_bla_backbone_table_seq_print_text(struct seq_file *seq, void *offset) struct batadv_hard_iface *primary_if; struct hlist_head *head; int secs, msecs; - uint32_t i; + u32 i; bool is_own; - uint8_t *primary_addr; + u8 *primary_addr; primary_if = batadv_seq_print_text_primary_if_get(seq); if (!primary_if) diff --git a/net/batman-adv/bridge_loop_avoidance.h b/net/batman-adv/bridge_loop_avoidance.h index 0282690389ac..025152b34282 100644 --- a/net/batman-adv/bridge_loop_avoidance.h +++ b/net/batman-adv/bridge_loop_avoidance.h @@ -22,9 +22,6 @@ #include <linux/types.h> -struct batadv_hard_iface; -struct batadv_orig_node; -struct batadv_priv; struct seq_file; struct sk_buff; @@ -38,7 +35,7 @@ int batadv_bla_is_backbone_gw(struct sk_buff *skb, int batadv_bla_claim_table_seq_print_text(struct seq_file *seq, void *offset); int batadv_bla_backbone_table_seq_print_text(struct seq_file *seq, void *offset); -bool batadv_bla_is_backbone_gw_orig(struct batadv_priv *bat_priv, uint8_t *orig, +bool batadv_bla_is_backbone_gw_orig(struct batadv_priv *bat_priv, u8 *orig, unsigned short vid); int batadv_bla_check_bcast_duplist(struct batadv_priv *bat_priv, struct sk_buff *skb); @@ -84,8 +81,7 @@ static inline int batadv_bla_backbone_table_seq_print_text(struct seq_file *seq, } static inline bool batadv_bla_is_backbone_gw_orig(struct batadv_priv *bat_priv, - uint8_t *orig, - unsigned short vid) + u8 *orig, unsigned short vid) { return false; } diff --git a/net/batman-adv/debugfs.h b/net/batman-adv/debugfs.h index 187acdc85dfa..80ab8d6f0ab3 100644 --- a/net/batman-adv/debugfs.h +++ b/net/batman-adv/debugfs.h @@ -22,7 +22,6 @@ #include <linux/kconfig.h> -struct batadv_hard_iface; struct net_device; #define BATADV_DEBUGFS_SUBDIR "batman_adv" diff --git a/net/batman-adv/distributed-arp-table.c b/net/batman-adv/distributed-arp-table.c index 6d0b471eede8..83bc1aaf5800 100644 --- a/net/batman-adv/distributed-arp-table.c +++ b/net/batman-adv/distributed-arp-table.c @@ -19,6 +19,7 @@ #include "main.h" #include <linux/atomic.h> +#include <linux/bitops.h> #include <linux/byteorder/generic.h> #include <linux/errno.h> #include <linux/etherdevice.h> @@ -101,7 +102,7 @@ static void __batadv_dat_purge(struct batadv_priv *bat_priv, struct batadv_dat_entry *dat_entry; struct hlist_node *node_tmp; struct hlist_head *head; - uint32_t i; + u32 i; if (!bat_priv->dat.hash) return; @@ -167,11 +168,11 @@ static int batadv_compare_dat(const struct hlist_node *node, const void *data2) * * Returns the value of the hw_src field in the ARP packet. */ -static uint8_t *batadv_arp_hw_src(struct sk_buff *skb, int hdr_size) +static u8 *batadv_arp_hw_src(struct sk_buff *skb, int hdr_size) { - uint8_t *addr; + u8 *addr; - addr = (uint8_t *)(skb->data + hdr_size); + addr = (u8 *)(skb->data + hdr_size); addr += ETH_HLEN + sizeof(struct arphdr); return addr; @@ -196,7 +197,7 @@ static __be32 batadv_arp_ip_src(struct sk_buff *skb, int hdr_size) * * Returns the value of the hw_dst field in the ARP packet. */ -static uint8_t *batadv_arp_hw_dst(struct sk_buff *skb, int hdr_size) +static u8 *batadv_arp_hw_dst(struct sk_buff *skb, int hdr_size) { return batadv_arp_hw_src(skb, hdr_size) + ETH_ALEN + 4; } @@ -220,12 +221,12 @@ static __be32 batadv_arp_ip_dst(struct sk_buff *skb, int hdr_size) * * Returns the selected index in the hash table for the given data. */ -static uint32_t batadv_hash_dat(const void *data, uint32_t size) +static u32 batadv_hash_dat(const void *data, u32 size) { - uint32_t hash = 0; + u32 hash = 0; const struct batadv_dat_entry *dat = data; const unsigned char *key; - uint32_t i; + u32 i; key = (const unsigned char *)&dat->ip; for (i = 0; i < sizeof(dat->ip); i++) { @@ -264,7 +265,7 @@ batadv_dat_entry_hash_find(struct batadv_priv *bat_priv, __be32 ip, struct hlist_head *head; struct batadv_dat_entry to_find, *dat_entry, *dat_entry_tmp = NULL; struct batadv_hashtable *hash = bat_priv->dat.hash; - uint32_t index; + u32 index; if (!hash) return NULL; @@ -299,7 +300,7 @@ batadv_dat_entry_hash_find(struct batadv_priv *bat_priv, __be32 ip, * @vid: VLAN identifier */ static void batadv_dat_entry_add(struct batadv_priv *bat_priv, __be32 ip, - uint8_t *mac_addr, unsigned short vid) + u8 *mac_addr, unsigned short vid) { struct batadv_dat_entry *dat_entry; int hash_added; @@ -356,11 +357,11 @@ out: * @msg: message to print together with the debugging information */ static void batadv_dbg_arp(struct batadv_priv *bat_priv, struct sk_buff *skb, - uint16_t type, int hdr_size, char *msg) + u16 type, int hdr_size, char *msg) { struct batadv_unicast_4addr_packet *unicast_4addr_packet; struct batadv_bcast_packet *bcast_pkt; - uint8_t *orig_addr; + u8 *orig_addr; __be32 ip_src, ip_dst; if (msg) @@ -423,7 +424,7 @@ static void batadv_dbg_arp(struct batadv_priv *bat_priv, struct sk_buff *skb, #else static void batadv_dbg_arp(struct batadv_priv *bat_priv, struct sk_buff *skb, - uint16_t type, int hdr_size, char *msg) + u16 type, int hdr_size, char *msg) { } @@ -453,7 +454,7 @@ static bool batadv_is_orig_node_eligible(struct batadv_dat_candidate *res, int j; /* check if orig node candidate is running DAT */ - if (!(candidate->capabilities & BATADV_ORIG_CAPA_HAS_DAT)) + if (!test_bit(BATADV_ORIG_CAPA_HAS_DAT, &candidate->capabilities)) goto out; /* Check if this node has already been selected... */ @@ -496,7 +497,8 @@ static void batadv_choose_next_candidate(struct batadv_priv *bat_priv, int select, batadv_dat_addr_t ip_key, batadv_dat_addr_t *last_max) { - batadv_dat_addr_t max = 0, tmp_max = 0; + batadv_dat_addr_t max = 0; + batadv_dat_addr_t tmp_max = 0; struct batadv_orig_node *orig_node, *max_orig_node = NULL; struct batadv_hashtable *hash = bat_priv->orig_hash; struct hlist_head *head; @@ -708,14 +710,13 @@ void batadv_dat_status_update(struct net_device *net_dev) */ static void batadv_dat_tvlv_ogm_handler_v1(struct batadv_priv *bat_priv, struct batadv_orig_node *orig, - uint8_t flags, - void *tvlv_value, - uint16_t tvlv_value_len) + u8 flags, + void *tvlv_value, u16 tvlv_value_len) { if (flags & BATADV_TVLV_HANDLER_OGM_CIFNOTFND) - orig->capabilities &= ~BATADV_ORIG_CAPA_HAS_DAT; + clear_bit(BATADV_ORIG_CAPA_HAS_DAT, &orig->capabilities); else - orig->capabilities |= BATADV_ORIG_CAPA_HAS_DAT; + set_bit(BATADV_ORIG_CAPA_HAS_DAT, &orig->capabilities); } /** @@ -786,7 +787,7 @@ int batadv_dat_cache_seq_print_text(struct seq_file *seq, void *offset) struct hlist_head *head; unsigned long last_seen_jiffies; int last_seen_msecs, last_seen_secs, last_seen_mins; - uint32_t i; + u32 i; primary_if = batadv_seq_print_text_primary_if_get(seq); if (!primary_if) @@ -829,14 +830,14 @@ out: * * Returns the ARP type if the skb contains a valid ARP packet, 0 otherwise. */ -static uint16_t batadv_arp_get_type(struct batadv_priv *bat_priv, - struct sk_buff *skb, int hdr_size) +static u16 batadv_arp_get_type(struct batadv_priv *bat_priv, + struct sk_buff *skb, int hdr_size) { struct arphdr *arphdr; struct ethhdr *ethhdr; __be32 ip_src, ip_dst; - uint8_t *hw_src, *hw_dst; - uint16_t type = 0; + u8 *hw_src, *hw_dst; + u16 type = 0; /* pull the ethernet header */ if (unlikely(!pskb_may_pull(skb, hdr_size + ETH_HLEN))) @@ -933,9 +934,9 @@ static unsigned short batadv_dat_get_vid(struct sk_buff *skb, int *hdr_size) bool batadv_dat_snoop_outgoing_arp_request(struct batadv_priv *bat_priv, struct sk_buff *skb) { - uint16_t type = 0; + u16 type = 0; __be32 ip_dst, ip_src; - uint8_t *hw_src; + u8 *hw_src; bool ret = false; struct batadv_dat_entry *dat_entry = NULL; struct sk_buff *skb_new; @@ -1021,9 +1022,9 @@ out: bool batadv_dat_snoop_incoming_arp_request(struct batadv_priv *bat_priv, struct sk_buff *skb, int hdr_size) { - uint16_t type; + u16 type; __be32 ip_src, ip_dst; - uint8_t *hw_src; + u8 *hw_src; struct sk_buff *skb_new; struct batadv_dat_entry *dat_entry = NULL; bool ret = false; @@ -1099,9 +1100,9 @@ out: void batadv_dat_snoop_outgoing_arp_reply(struct batadv_priv *bat_priv, struct sk_buff *skb) { - uint16_t type; + u16 type; __be32 ip_src, ip_dst; - uint8_t *hw_src, *hw_dst; + u8 *hw_src, *hw_dst; int hdr_size = 0; unsigned short vid; @@ -1145,9 +1146,9 @@ void batadv_dat_snoop_outgoing_arp_reply(struct batadv_priv *bat_priv, bool batadv_dat_snoop_incoming_arp_reply(struct batadv_priv *bat_priv, struct sk_buff *skb, int hdr_size) { - uint16_t type; + u16 type; __be32 ip_src, ip_dst; - uint8_t *hw_src, *hw_dst; + u8 *hw_src, *hw_dst; bool dropped = false; unsigned short vid; @@ -1201,7 +1202,7 @@ out: bool batadv_dat_drop_broadcast_packet(struct batadv_priv *bat_priv, struct batadv_forw_packet *forw_packet) { - uint16_t type; + u16 type; __be32 ip_dst; struct batadv_dat_entry *dat_entry = NULL; bool ret = false; diff --git a/net/batman-adv/distributed-arp-table.h b/net/batman-adv/distributed-arp-table.h index 3181507ebc14..26d4a525a798 100644 --- a/net/batman-adv/distributed-arp-table.h +++ b/net/batman-adv/distributed-arp-table.h @@ -54,7 +54,7 @@ bool batadv_dat_drop_broadcast_packet(struct batadv_priv *bat_priv, static inline void batadv_dat_init_orig_node_addr(struct batadv_orig_node *orig_node) { - uint32_t addr; + u32 addr; addr = batadv_choose_orig(orig_node->orig, BATADV_DAT_ADDR_MAX); orig_node->dat_addr = (batadv_dat_addr_t)addr; @@ -69,7 +69,7 @@ static inline void batadv_dat_init_own_addr(struct batadv_priv *bat_priv, struct batadv_hard_iface *primary_if) { - uint32_t addr; + u32 addr; addr = batadv_choose_orig(primary_if->net_dev->dev_addr, BATADV_DAT_ADDR_MAX); @@ -89,7 +89,7 @@ int batadv_dat_cache_seq_print_text(struct seq_file *seq, void *offset); * Updates the ethtool statistics for the received packet if it is a DAT subtype */ static inline void batadv_dat_inc_counter(struct batadv_priv *bat_priv, - uint8_t subtype) + u8 subtype) { switch (subtype) { case BATADV_P_DAT_DHT_GET: @@ -169,7 +169,7 @@ static inline void batadv_dat_free(struct batadv_priv *bat_priv) } static inline void batadv_dat_inc_counter(struct batadv_priv *bat_priv, - uint8_t subtype) + u8 subtype) { } diff --git a/net/batman-adv/fragmentation.c b/net/batman-adv/fragmentation.c index c0f0d01ab244..700c96c82a15 100644 --- a/net/batman-adv/fragmentation.c +++ b/net/batman-adv/fragmentation.c @@ -25,6 +25,7 @@ #include <linux/if_ether.h> #include <linux/jiffies.h> #include <linux/kernel.h> +#include <linux/lockdep.h> #include <linux/netdevice.h> #include <linux/pkt_sched.h> #include <linux/skbuff.h> @@ -66,7 +67,7 @@ void batadv_frag_purge_orig(struct batadv_orig_node *orig_node, bool (*check_cb)(struct batadv_frag_table_entry *)) { struct batadv_frag_table_entry *chain; - uint8_t i; + u8 i; for (i = 0; i < BATADV_FRAG_BUFFER_COUNT; i++) { chain = &orig_node->fragments[i]; @@ -110,8 +111,10 @@ static int batadv_frag_size_limit(void) * without searching for the right position. */ static bool batadv_frag_init_chain(struct batadv_frag_table_entry *chain, - uint16_t seqno) + u16 seqno) { + lockdep_assert_held(&chain->lock); + if (chain->seqno == seqno) return false; @@ -145,8 +148,8 @@ static bool batadv_frag_insert_packet(struct batadv_orig_node *orig_node, struct batadv_frag_list_entry *frag_entry_new = NULL, *frag_entry_curr; struct batadv_frag_list_entry *frag_entry_last = NULL; struct batadv_frag_packet *frag_packet; - uint8_t bucket; - uint16_t seqno, hdr_size = sizeof(struct batadv_frag_packet); + u8 bucket; + u16 seqno, hdr_size = sizeof(struct batadv_frag_packet); bool ret = false; /* Linearize packet to avoid linearizing 16 packets in a row when doing @@ -351,7 +354,7 @@ bool batadv_frag_skb_fwd(struct sk_buff *skb, struct batadv_orig_node *orig_node_dst = NULL; struct batadv_neigh_node *neigh_node = NULL; struct batadv_frag_packet *packet; - uint16_t total_size; + u16 total_size; bool ret = false; packet = (struct batadv_frag_packet *)skb->data; diff --git a/net/batman-adv/gateway_client.c b/net/batman-adv/gateway_client.c index cffa92dd9877..e6c8382c79ba 100644 --- a/net/batman-adv/gateway_client.c +++ b/net/batman-adv/gateway_client.c @@ -27,7 +27,6 @@ #include <linux/in.h> #include <linux/ip.h> #include <linux/ipv6.h> -#include <linux/jiffies.h> #include <linux/kernel.h> #include <linux/list.h> #include <linux/netdevice.h> @@ -153,20 +152,14 @@ 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; - uint32_t max_gw_factor = 0, tmp_gw_factor = 0; - uint32_t gw_divisor; - uint8_t max_tq = 0; - uint8_t tq_avg; + u64 max_gw_factor = 0; + u64 tmp_gw_factor = 0; + u8 max_tq = 0; + u8 tq_avg; struct batadv_orig_node *orig_node; - gw_divisor = BATADV_TQ_LOCAL_WINDOW_SIZE * BATADV_TQ_LOCAL_WINDOW_SIZE; - gw_divisor *= 64; - rcu_read_lock(); hlist_for_each_entry_rcu(gw_node, &bat_priv->gw.list, list) { - if (gw_node->deleted) - continue; - orig_node = gw_node->orig_node; router = batadv_orig_router_get(orig_node, BATADV_IF_DEFAULT); if (!router) @@ -187,7 +180,7 @@ batadv_gw_get_best_gw_node(struct batadv_priv *bat_priv) tmp_gw_factor = tq_avg * tq_avg; tmp_gw_factor *= gw_node->bandwidth_down; tmp_gw_factor *= 100 * 100; - tmp_gw_factor /= gw_divisor; + tmp_gw_factor >>= 18; if ((tmp_gw_factor > max_gw_factor) || ((tmp_gw_factor == max_gw_factor) && @@ -267,7 +260,8 @@ void batadv_gw_check_client_stop(struct batadv_priv *bat_priv) void batadv_gw_election(struct batadv_priv *bat_priv) { - struct batadv_gw_node *curr_gw = NULL, *next_gw = NULL; + struct batadv_gw_node *curr_gw = NULL; + struct batadv_gw_node *next_gw = NULL; struct batadv_neigh_node *router = NULL; struct batadv_neigh_ifinfo *router_ifinfo = NULL; char gw_addr[18] = { '\0' }; @@ -351,8 +345,9 @@ void batadv_gw_check_election(struct batadv_priv *bat_priv, 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, *router_orig = NULL; - uint8_t gw_tq_avg, orig_tq_avg; + struct batadv_neigh_node *router_gw = NULL; + struct batadv_neigh_node *router_orig = NULL; + u8 gw_tq_avg, orig_tq_avg; curr_gw_orig = batadv_gw_get_selected_orig(bat_priv); if (!curr_gw_orig) @@ -474,9 +469,6 @@ batadv_gw_node_get(struct batadv_priv *bat_priv, if (gw_node_tmp->orig_node != orig_node) continue; - if (gw_node_tmp->deleted) - continue; - if (!atomic_inc_not_zero(&gw_node_tmp->refcount)) continue; @@ -526,9 +518,7 @@ void batadv_gw_node_update(struct batadv_priv *bat_priv, gw_node->bandwidth_down = ntohl(gateway->bandwidth_down); gw_node->bandwidth_up = ntohl(gateway->bandwidth_up); - gw_node->deleted = 0; if (ntohl(gateway->bandwidth_down) == 0) { - gw_node->deleted = jiffies; batadv_dbg(BATADV_DBG_BATMAN, bat_priv, "Gateway %pM removed from gateway list\n", orig_node->orig); @@ -536,14 +526,21 @@ void batadv_gw_node_update(struct batadv_priv *bat_priv, /* Note: We don't need a NULL check here, since curr_gw never * gets dereferenced. */ + spin_lock_bh(&bat_priv->gw.list_lock); + hlist_del_init_rcu(&gw_node->list); + spin_unlock_bh(&bat_priv->gw.list_lock); + + batadv_gw_node_free_ref(gw_node); + curr_gw = batadv_gw_get_selected_gw_node(bat_priv); if (gw_node == curr_gw) batadv_gw_reselect(bat_priv); + + if (curr_gw) + batadv_gw_node_free_ref(curr_gw); } out: - if (curr_gw) - batadv_gw_node_free_ref(curr_gw); if (gw_node) batadv_gw_node_free_ref(gw_node); } @@ -559,39 +556,18 @@ void batadv_gw_node_delete(struct batadv_priv *bat_priv, batadv_gw_node_update(bat_priv, orig_node, &gateway); } -void batadv_gw_node_purge(struct batadv_priv *bat_priv) +void batadv_gw_node_free(struct batadv_priv *bat_priv) { - struct batadv_gw_node *gw_node, *curr_gw; + struct batadv_gw_node *gw_node; struct hlist_node *node_tmp; - unsigned long timeout = msecs_to_jiffies(2 * BATADV_PURGE_TIMEOUT); - int do_reselect = 0; - - curr_gw = batadv_gw_get_selected_gw_node(bat_priv); spin_lock_bh(&bat_priv->gw.list_lock); - hlist_for_each_entry_safe(gw_node, node_tmp, &bat_priv->gw.list, list) { - if (((!gw_node->deleted) || - (time_before(jiffies, gw_node->deleted + timeout))) && - atomic_read(&bat_priv->mesh_state) == BATADV_MESH_ACTIVE) - continue; - - if (curr_gw == gw_node) - do_reselect = 1; - - hlist_del_rcu(&gw_node->list); + hlist_del_init_rcu(&gw_node->list); batadv_gw_node_free_ref(gw_node); } - spin_unlock_bh(&bat_priv->gw.list_lock); - - /* gw_reselect() needs to acquire the gw_list_lock */ - if (do_reselect) - batadv_gw_reselect(bat_priv); - - if (curr_gw) - batadv_gw_node_free_ref(curr_gw); } /* fails if orig_node has no router */ @@ -655,9 +631,6 @@ int batadv_gw_client_seq_print_text(struct seq_file *seq, void *offset) rcu_read_lock(); hlist_for_each_entry_rcu(gw_node, &bat_priv->gw.list, list) { - if (gw_node->deleted) - continue; - /* fails if orig_node has no router */ if (batadv_write_buffer_text(bat_priv, seq, gw_node) < 0) continue; @@ -692,7 +665,7 @@ out: */ enum batadv_dhcp_recipient batadv_gw_dhcp_recipient_get(struct sk_buff *skb, unsigned int *header_len, - uint8_t *chaddr) + u8 *chaddr) { enum batadv_dhcp_recipient ret = BATADV_DHCP_NO; struct ethhdr *ethhdr; @@ -702,7 +675,7 @@ batadv_gw_dhcp_recipient_get(struct sk_buff *skb, unsigned int *header_len, struct vlan_ethhdr *vhdr; int chaddr_offset; __be16 proto; - uint8_t *p; + u8 *p; /* check for ethernet header */ if (!pskb_may_pull(skb, *header_len + ETH_HLEN)) @@ -812,13 +785,15 @@ batadv_gw_dhcp_recipient_get(struct sk_buff *skb, unsigned int *header_len, bool batadv_gw_out_of_range(struct batadv_priv *bat_priv, struct sk_buff *skb) { - struct batadv_neigh_node *neigh_curr = NULL, *neigh_old = NULL; + struct batadv_neigh_node *neigh_curr = NULL; + struct batadv_neigh_node *neigh_old = NULL; struct batadv_orig_node *orig_dst_node = NULL; - struct batadv_gw_node *gw_node = NULL, *curr_gw = NULL; + struct batadv_gw_node *gw_node = NULL; + struct batadv_gw_node *curr_gw = NULL; struct batadv_neigh_ifinfo *curr_ifinfo, *old_ifinfo; struct ethhdr *ethhdr = (struct ethhdr *)skb->data; bool out_of_range = false; - uint8_t curr_tq_avg; + u8 curr_tq_avg; unsigned short vid; vid = batadv_get_vid(skb, 0); diff --git a/net/batman-adv/gateway_client.h b/net/batman-adv/gateway_client.h index 89565b451c18..fa9527785ed3 100644 --- a/net/batman-adv/gateway_client.h +++ b/net/batman-adv/gateway_client.h @@ -38,11 +38,11 @@ void batadv_gw_node_update(struct batadv_priv *bat_priv, struct batadv_tvlv_gateway_data *gateway); void batadv_gw_node_delete(struct batadv_priv *bat_priv, struct batadv_orig_node *orig_node); -void batadv_gw_node_purge(struct batadv_priv *bat_priv); +void batadv_gw_node_free(struct batadv_priv *bat_priv); int batadv_gw_client_seq_print_text(struct seq_file *seq, void *offset); 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, - uint8_t *chaddr); + u8 *chaddr); #endif /* _NET_BATMAN_ADV_GATEWAY_CLIENT_H_ */ diff --git a/net/batman-adv/gateway_common.c b/net/batman-adv/gateway_common.c index 39cf44ccebd4..0cb5e6b6f6d4 100644 --- a/net/batman-adv/gateway_common.c +++ b/net/batman-adv/gateway_common.c @@ -19,8 +19,10 @@ #include "main.h" #include <linux/atomic.h> +#include <linux/errno.h> #include <linux/byteorder/generic.h> #include <linux/kernel.h> +#include <linux/math64.h> #include <linux/netdevice.h> #include <linux/stddef.h> #include <linux/string.h> @@ -39,11 +41,11 @@ * Returns false on parse error and true otherwise. */ static bool batadv_parse_gw_bandwidth(struct net_device *net_dev, char *buff, - uint32_t *down, uint32_t *up) + u32 *down, u32 *up) { enum batadv_bandwidth_units bw_unit_type = BATADV_BW_UNIT_KBIT; char *slash_ptr, *tmp_ptr; - long ldown, lup; + u64 ldown, lup; int ret; slash_ptr = strchr(buff, '/'); @@ -61,7 +63,7 @@ static bool batadv_parse_gw_bandwidth(struct net_device *net_dev, char *buff, *tmp_ptr = '\0'; } - ret = kstrtol(buff, 10, &ldown); + ret = kstrtou64(buff, 10, &ldown); if (ret) { batadv_err(net_dev, "Download speed of gateway mode invalid: %s\n", @@ -71,14 +73,31 @@ static bool batadv_parse_gw_bandwidth(struct net_device *net_dev, char *buff, switch (bw_unit_type) { case BATADV_BW_UNIT_MBIT: - *down = ldown * 10; + /* prevent overflow */ + if (U64_MAX / 10 < ldown) { + batadv_err(net_dev, + "Download speed of gateway mode too large: %s\n", + buff); + return false; + } + + ldown *= 10; break; case BATADV_BW_UNIT_KBIT: default: - *down = ldown / 100; + ldown = div_u64(ldown, 100); break; } + if (U32_MAX < ldown) { + batadv_err(net_dev, + "Download speed of gateway mode too large: %s\n", + buff); + return false; + } + + *down = ldown; + /* we also got some upload info */ if (slash_ptr) { bw_unit_type = BATADV_BW_UNIT_KBIT; @@ -94,7 +113,7 @@ static bool batadv_parse_gw_bandwidth(struct net_device *net_dev, char *buff, *tmp_ptr = '\0'; } - ret = kstrtol(slash_ptr + 1, 10, &lup); + ret = kstrtou64(slash_ptr + 1, 10, &lup); if (ret) { batadv_err(net_dev, "Upload speed of gateway mode invalid: %s\n", @@ -104,13 +123,30 @@ static bool batadv_parse_gw_bandwidth(struct net_device *net_dev, char *buff, switch (bw_unit_type) { case BATADV_BW_UNIT_MBIT: - *up = lup * 10; + /* prevent overflow */ + if (U64_MAX / 10 < lup) { + batadv_err(net_dev, + "Upload speed of gateway mode too large: %s\n", + slash_ptr + 1); + return false; + } + + lup *= 10; break; case BATADV_BW_UNIT_KBIT: default: - *up = lup / 100; + lup = div_u64(lup, 100); break; } + + if (U32_MAX < lup) { + batadv_err(net_dev, + "Upload speed of gateway mode too large: %s\n", + slash_ptr + 1); + return false; + } + + *up = lup; } return true; @@ -124,7 +160,7 @@ static bool batadv_parse_gw_bandwidth(struct net_device *net_dev, char *buff, void batadv_gw_tvlv_container_update(struct batadv_priv *bat_priv) { struct batadv_tvlv_gateway_data gw; - uint32_t down, up; + u32 down, up; char gw_mode; gw_mode = atomic_read(&bat_priv->gw_mode); @@ -149,7 +185,10 @@ ssize_t batadv_gw_bandwidth_set(struct net_device *net_dev, char *buff, size_t count) { struct batadv_priv *bat_priv = netdev_priv(net_dev); - uint32_t down_curr, up_curr, down_new = 0, up_new = 0; + u32 down_curr; + u32 up_curr; + u32 down_new = 0; + u32 up_new = 0; bool ret; down_curr = (unsigned int)atomic_read(&bat_priv->gw.bandwidth_down); @@ -157,7 +196,7 @@ ssize_t batadv_gw_bandwidth_set(struct net_device *net_dev, char *buff, ret = batadv_parse_gw_bandwidth(net_dev, buff, &down_new, &up_new); if (!ret) - goto end; + return -EINVAL; if (!down_new) down_new = 1; @@ -181,7 +220,6 @@ ssize_t batadv_gw_bandwidth_set(struct net_device *net_dev, char *buff, atomic_set(&bat_priv->gw.bandwidth_up, up_new); batadv_gw_tvlv_container_update(bat_priv); -end: return count; } @@ -195,9 +233,8 @@ end: */ static void batadv_gw_tvlv_ogm_handler_v1(struct batadv_priv *bat_priv, struct batadv_orig_node *orig, - uint8_t flags, - void *tvlv_value, - uint16_t tvlv_value_len) + u8 flags, + void *tvlv_value, u16 tvlv_value_len) { struct batadv_tvlv_gateway_data gateway, *gateway_ptr; diff --git a/net/batman-adv/gateway_common.h b/net/batman-adv/gateway_common.h index bd5c812cebf4..ab893e318229 100644 --- a/net/batman-adv/gateway_common.h +++ b/net/batman-adv/gateway_common.h @@ -22,7 +22,6 @@ #include <linux/types.h> -struct batadv_priv; struct net_device; enum batadv_gw_modes { diff --git a/net/batman-adv/hard-interface.c b/net/batman-adv/hard-interface.c index f4a15d2e5eaf..f11345e163d7 100644 --- a/net/batman-adv/hard-interface.c +++ b/net/batman-adv/hard-interface.c @@ -252,6 +252,44 @@ static void batadv_check_known_mac_addr(const struct net_device *net_dev) rcu_read_unlock(); } +/** + * batadv_hardif_recalc_extra_skbroom() - Recalculate skbuff extra head/tailroom + * @soft_iface: netdev struct of the mesh interface + */ +static void batadv_hardif_recalc_extra_skbroom(struct net_device *soft_iface) +{ + const struct batadv_hard_iface *hard_iface; + unsigned short lower_header_len = ETH_HLEN; + unsigned short lower_headroom = 0; + unsigned short lower_tailroom = 0; + unsigned short needed_headroom; + + rcu_read_lock(); + list_for_each_entry_rcu(hard_iface, &batadv_hardif_list, list) { + if (hard_iface->if_status == BATADV_IF_NOT_IN_USE) + continue; + + if (hard_iface->soft_iface != soft_iface) + continue; + + lower_header_len = max_t(unsigned short, lower_header_len, + hard_iface->net_dev->hard_header_len); + + lower_headroom = max_t(unsigned short, lower_headroom, + hard_iface->net_dev->needed_headroom); + + lower_tailroom = max_t(unsigned short, lower_tailroom, + hard_iface->net_dev->needed_tailroom); + } + rcu_read_unlock(); + + needed_headroom = lower_headroom + (lower_header_len - ETH_HLEN); + needed_headroom += batadv_max_header_len(); + + soft_iface->needed_headroom = needed_headroom; + soft_iface->needed_tailroom = lower_tailroom; +} + int batadv_hardif_min_mtu(struct net_device *soft_iface) { struct batadv_priv *bat_priv = netdev_priv(soft_iface); @@ -474,6 +512,8 @@ int batadv_hardif_enable_interface(struct batadv_hard_iface *hard_iface, "Not using interface %s (retrying later): interface not active\n", hard_iface->net_dev->name); + batadv_hardif_recalc_extra_skbroom(soft_iface); + /* begin scheduling originator messages on that interface */ batadv_schedule_bat_ogm(hard_iface); @@ -528,6 +568,9 @@ void batadv_hardif_disable_interface(struct batadv_hard_iface *hard_iface, batadv_purge_outstanding_packets(bat_priv, hard_iface); dev_put(hard_iface->soft_iface); + netdev_upper_dev_unlink(hard_iface->net_dev, hard_iface->soft_iface); + batadv_hardif_recalc_extra_skbroom(hard_iface->soft_iface); + /* nobody uses this interface anymore */ if (!bat_priv->num_ifaces) { batadv_gw_check_client_stop(bat_priv); @@ -536,7 +579,6 @@ void batadv_hardif_disable_interface(struct batadv_hard_iface *hard_iface, batadv_softif_destroy_sysfs(hard_iface->soft_iface); } - netdev_upper_dev_unlink(hard_iface->net_dev, hard_iface->soft_iface); hard_iface->soft_iface = NULL; batadv_hardif_free_ref(hard_iface); diff --git a/net/batman-adv/hash.c b/net/batman-adv/hash.c index e89f3146b092..2ea6a18d793f 100644 --- a/net/batman-adv/hash.c +++ b/net/batman-adv/hash.c @@ -25,7 +25,7 @@ /* clears the hash */ static void batadv_hash_init(struct batadv_hashtable *hash) { - uint32_t i; + u32 i; for (i = 0; i < hash->size; i++) { INIT_HLIST_HEAD(&hash->table[i]); @@ -42,7 +42,7 @@ void batadv_hash_destroy(struct batadv_hashtable *hash) } /* allocates and clears the hash */ -struct batadv_hashtable *batadv_hash_new(uint32_t size) +struct batadv_hashtable *batadv_hash_new(u32 size) { struct batadv_hashtable *hash; @@ -73,7 +73,7 @@ free_hash: void batadv_hash_set_lock_class(struct batadv_hashtable *hash, struct lock_class_key *key) { - uint32_t i; + u32 i; for (i = 0; i < hash->size; i++) lockdep_set_class(&hash->list_locks[i], key); diff --git a/net/batman-adv/hash.h b/net/batman-adv/hash.h index 5065f50c9c3c..377626250ac7 100644 --- a/net/batman-adv/hash.h +++ b/net/batman-adv/hash.h @@ -39,17 +39,17 @@ typedef int (*batadv_hashdata_compare_cb)(const struct hlist_node *, * based on the key in the data of the first * argument and the size the second */ -typedef uint32_t (*batadv_hashdata_choose_cb)(const void *, uint32_t); +typedef u32 (*batadv_hashdata_choose_cb)(const void *, u32); typedef void (*batadv_hashdata_free_cb)(struct hlist_node *, void *); struct batadv_hashtable { struct hlist_head *table; /* the hashtable itself with the buckets */ spinlock_t *list_locks; /* spinlock for each hash list entry */ - uint32_t size; /* size of hashtable */ + u32 size; /* size of hashtable */ }; /* allocates and clears the hash */ -struct batadv_hashtable *batadv_hash_new(uint32_t size); +struct batadv_hashtable *batadv_hash_new(u32 size); /* set class key for all locks */ void batadv_hash_set_lock_class(struct batadv_hashtable *hash, @@ -69,7 +69,7 @@ static inline void batadv_hash_delete(struct batadv_hashtable *hash, struct hlist_head *head; struct hlist_node *node, *node_tmp; spinlock_t *list_lock; /* spinlock to protect write access */ - uint32_t i; + u32 i; for (i = 0; i < hash->size; i++) { head = &hash->table[i]; @@ -105,7 +105,7 @@ static inline int batadv_hash_add(struct batadv_hashtable *hash, const void *data, struct hlist_node *data_node) { - uint32_t index; + u32 index; int ret = -1; struct hlist_head *head; struct hlist_node *node; @@ -149,7 +149,7 @@ static inline void *batadv_hash_remove(struct batadv_hashtable *hash, batadv_hashdata_choose_cb choose, void *data) { - uint32_t index; + u32 index; struct hlist_node *node; struct hlist_head *head; void *data_save = NULL; diff --git a/net/batman-adv/icmp_socket.c b/net/batman-adv/icmp_socket.c index 07061bcbaa04..bcabb5e3f4d3 100644 --- a/net/batman-adv/icmp_socket.c +++ b/net/batman-adv/icmp_socket.c @@ -183,7 +183,7 @@ static ssize_t batadv_socket_write(struct file *file, const char __user *buff, struct batadv_orig_node *orig_node = NULL; struct batadv_neigh_node *neigh_node = NULL; size_t packet_len = sizeof(struct batadv_icmp_packet); - uint8_t *addr; + u8 *addr; if (len < sizeof(struct batadv_icmp_header)) { batadv_dbg(BATADV_DBG_BATMAN, bat_priv, @@ -337,8 +337,8 @@ err: } /** - * batadv_socket_receive_packet - schedule an icmp packet to be sent to userspace - * on an icmp socket. + * batadv_socket_receive_packet - schedule an icmp packet to be sent to + * userspace on an icmp socket. * @socket_client: the socket this packet belongs to * @icmph: pointer to the header of the icmp packet * @icmp_len: total length of the icmp packet diff --git a/net/batman-adv/icmp_socket.h b/net/batman-adv/icmp_socket.h index 7de7fce4b48c..e937143f0b10 100644 --- a/net/batman-adv/icmp_socket.h +++ b/net/batman-adv/icmp_socket.h @@ -23,7 +23,6 @@ #include <linux/types.h> struct batadv_icmp_header; -struct batadv_priv; #define BATADV_ICMP_SOCKET "socket" diff --git a/net/batman-adv/main.c b/net/batman-adv/main.c index 8457097f1643..d7f17c1aa4a4 100644 --- a/net/batman-adv/main.c +++ b/net/batman-adv/main.c @@ -30,6 +30,7 @@ #include <linux/ipv6.h> #include <linux/kernel.h> #include <linux/list.h> +#include <linux/lockdep.h> #include <linux/module.h> #include <linux/moduleparam.h> #include <linux/netdevice.h> @@ -148,7 +149,7 @@ int batadv_mesh_init(struct net_device *soft_iface) INIT_HLIST_HEAD(&bat_priv->mcast.want_all_ipv6_list); #endif INIT_LIST_HEAD(&bat_priv->tt.changes_list); - INIT_LIST_HEAD(&bat_priv->tt.req_list); + INIT_HLIST_HEAD(&bat_priv->tt.req_list); INIT_LIST_HEAD(&bat_priv->tt.roam_list); #ifdef CONFIG_BATMAN_ADV_MCAST INIT_HLIST_HEAD(&bat_priv->mcast.mla_list); @@ -198,7 +199,7 @@ void batadv_mesh_free(struct net_device *soft_iface) batadv_purge_outstanding_packets(bat_priv, NULL); - batadv_gw_node_purge(bat_priv); + batadv_gw_node_free(bat_priv); batadv_nc_mesh_free(bat_priv); batadv_dat_free(bat_priv); batadv_bla_free(bat_priv); @@ -234,7 +235,7 @@ void batadv_mesh_free(struct net_device *soft_iface) * * Returns 'true' if the mac address was found, false otherwise. */ -bool batadv_is_my_mac(struct batadv_priv *bat_priv, const uint8_t *addr) +bool batadv_is_my_mac(struct batadv_priv *bat_priv, const u8 *addr) { const struct batadv_hard_iface *hard_iface; bool is_my_mac = false; @@ -387,7 +388,7 @@ int batadv_batman_skb_recv(struct sk_buff *skb, struct net_device *dev, struct batadv_priv *bat_priv; struct batadv_ogm_packet *batadv_ogm_packet; struct batadv_hard_iface *hard_iface; - uint8_t idx; + u8 idx; int ret; hard_iface = container_of(ptype, struct batadv_hard_iface, @@ -496,7 +497,7 @@ static void batadv_recv_handler_init(void) } int -batadv_recv_handler_register(uint8_t packet_type, +batadv_recv_handler_register(u8 packet_type, int (*recv_handler)(struct sk_buff *, struct batadv_hard_iface *)) { @@ -512,7 +513,7 @@ batadv_recv_handler_register(uint8_t packet_type, return 0; } -void batadv_recv_handler_unregister(uint8_t packet_type) +void batadv_recv_handler_unregister(u8 packet_type) { batadv_rx_handler[packet_type] = batadv_recv_unhandled_packet; } @@ -583,7 +584,7 @@ int batadv_algo_seq_print_text(struct seq_file *seq, void *offset) seq_puts(seq, "Available routing algorithms:\n"); hlist_for_each_entry(bat_algo_ops, &batadv_algo_list, list) { - seq_printf(seq, "%s\n", bat_algo_ops->name); + seq_printf(seq, " * %s\n", bat_algo_ops->name); } return 0; @@ -642,8 +643,7 @@ batadv_tvlv_handler_free_ref(struct batadv_tvlv_handler *tvlv_handler) * Returns tvlv handler if found or NULL otherwise. */ static struct batadv_tvlv_handler -*batadv_tvlv_handler_get(struct batadv_priv *bat_priv, - uint8_t type, uint8_t version) +*batadv_tvlv_handler_get(struct batadv_priv *bat_priv, u8 type, u8 version) { struct batadv_tvlv_handler *tvlv_handler_tmp, *tvlv_handler = NULL; @@ -691,8 +691,7 @@ static void batadv_tvlv_container_free_ref(struct batadv_tvlv_container *tvlv) * Returns tvlv container if found or NULL otherwise. */ static struct batadv_tvlv_container -*batadv_tvlv_container_get(struct batadv_priv *bat_priv, - uint8_t type, uint8_t version) +*batadv_tvlv_container_get(struct batadv_priv *bat_priv, u8 type, u8 version) { struct batadv_tvlv_container *tvlv_tmp, *tvlv = NULL; @@ -723,10 +722,10 @@ static struct batadv_tvlv_container * * Returns size of all currently registered tvlv containers in bytes. */ -static uint16_t batadv_tvlv_container_list_size(struct batadv_priv *bat_priv) +static u16 batadv_tvlv_container_list_size(struct batadv_priv *bat_priv) { struct batadv_tvlv_container *tvlv; - uint16_t tvlv_len = 0; + u16 tvlv_len = 0; hlist_for_each_entry(tvlv, &bat_priv->tvlv.container_list, list) { tvlv_len += sizeof(struct batadv_tvlv_hdr); @@ -739,13 +738,17 @@ static uint16_t batadv_tvlv_container_list_size(struct batadv_priv *bat_priv) /** * batadv_tvlv_container_remove - remove tvlv container from the tvlv container * list + * @bat_priv: the bat priv with all the soft interface information * @tvlv: the to be removed tvlv container * * Has to be called with the appropriate locks being acquired * (tvlv.container_list_lock). */ -static void batadv_tvlv_container_remove(struct batadv_tvlv_container *tvlv) +static void batadv_tvlv_container_remove(struct batadv_priv *bat_priv, + struct batadv_tvlv_container *tvlv) { + lockdep_assert_held(&bat_priv->tvlv.handler_list_lock); + if (!tvlv) return; @@ -764,13 +767,13 @@ static void batadv_tvlv_container_remove(struct batadv_tvlv_container *tvlv) * @version: tvlv container type to unregister */ void batadv_tvlv_container_unregister(struct batadv_priv *bat_priv, - uint8_t type, uint8_t version) + u8 type, u8 version) { struct batadv_tvlv_container *tvlv; spin_lock_bh(&bat_priv->tvlv.container_list_lock); tvlv = batadv_tvlv_container_get(bat_priv, type, version); - batadv_tvlv_container_remove(tvlv); + batadv_tvlv_container_remove(bat_priv, tvlv); spin_unlock_bh(&bat_priv->tvlv.container_list_lock); } @@ -787,8 +790,8 @@ void batadv_tvlv_container_unregister(struct batadv_priv *bat_priv, * content is going to replace the old one. */ void batadv_tvlv_container_register(struct batadv_priv *bat_priv, - uint8_t type, uint8_t version, - void *tvlv_value, uint16_t tvlv_value_len) + u8 type, u8 version, + void *tvlv_value, u16 tvlv_value_len) { struct batadv_tvlv_container *tvlv_old, *tvlv_new; @@ -809,7 +812,7 @@ 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(tvlv_old); + batadv_tvlv_container_remove(bat_priv, tvlv_old); hlist_add_head(&tvlv_new->list, &bat_priv->tvlv.container_list); spin_unlock_bh(&bat_priv->tvlv.container_list_lock); } @@ -861,14 +864,13 @@ static bool batadv_tvlv_realloc_packet_buff(unsigned char **packet_buff, * * Returns size of all appended tvlv containers in bytes. */ -uint16_t batadv_tvlv_container_ogm_append(struct batadv_priv *bat_priv, - unsigned char **packet_buff, - int *packet_buff_len, - int packet_min_len) +u16 batadv_tvlv_container_ogm_append(struct batadv_priv *bat_priv, + unsigned char **packet_buff, + int *packet_buff_len, int packet_min_len) { struct batadv_tvlv_container *tvlv; struct batadv_tvlv_hdr *tvlv_hdr; - uint16_t tvlv_value_len; + u16 tvlv_value_len; void *tvlv_value; bool ret; @@ -893,7 +895,7 @@ uint16_t batadv_tvlv_container_ogm_append(struct batadv_priv *bat_priv, tvlv_hdr->len = tvlv->tvlv_hdr.len; tvlv_value = tvlv_hdr + 1; memcpy(tvlv_value, tvlv + 1, ntohs(tvlv->tvlv_hdr.len)); - tvlv_value = (uint8_t *)tvlv_value + ntohs(tvlv->tvlv_hdr.len); + tvlv_value = (u8 *)tvlv_value + ntohs(tvlv->tvlv_hdr.len); } end: @@ -920,8 +922,8 @@ static int batadv_tvlv_call_handler(struct batadv_priv *bat_priv, struct batadv_tvlv_handler *tvlv_handler, bool ogm_source, struct batadv_orig_node *orig_node, - uint8_t *src, uint8_t *dst, - void *tvlv_value, uint16_t tvlv_value_len) + u8 *src, u8 *dst, + void *tvlv_value, u16 tvlv_value_len) { if (!tvlv_handler) return NET_RX_SUCCESS; @@ -972,13 +974,13 @@ static int batadv_tvlv_call_handler(struct batadv_priv *bat_priv, int batadv_tvlv_containers_process(struct batadv_priv *bat_priv, bool ogm_source, struct batadv_orig_node *orig_node, - uint8_t *src, uint8_t *dst, - void *tvlv_value, uint16_t tvlv_value_len) + u8 *src, u8 *dst, + void *tvlv_value, u16 tvlv_value_len) { struct batadv_tvlv_handler *tvlv_handler; struct batadv_tvlv_hdr *tvlv_hdr; - uint16_t tvlv_value_cont_len; - uint8_t cifnotfound = BATADV_TVLV_HANDLER_OGM_CIFNOTFND; + u16 tvlv_value_cont_len; + u8 cifnotfound = BATADV_TVLV_HANDLER_OGM_CIFNOTFND; int ret = NET_RX_SUCCESS; while (tvlv_value_len >= sizeof(*tvlv_hdr)) { @@ -1000,7 +1002,7 @@ int batadv_tvlv_containers_process(struct batadv_priv *bat_priv, tvlv_value_cont_len); if (tvlv_handler) batadv_tvlv_handler_free_ref(tvlv_handler); - tvlv_value = (uint8_t *)tvlv_value + tvlv_value_cont_len; + tvlv_value = (u8 *)tvlv_value + tvlv_value_cont_len; tvlv_value_len -= tvlv_value_cont_len; } @@ -1034,7 +1036,7 @@ void batadv_tvlv_ogm_receive(struct batadv_priv *bat_priv, struct batadv_orig_node *orig_node) { void *tvlv_value; - uint16_t tvlv_value_len; + u16 tvlv_value_len; if (!batadv_ogm_packet) return; @@ -1066,14 +1068,14 @@ void batadv_tvlv_ogm_receive(struct batadv_priv *bat_priv, void batadv_tvlv_handler_register(struct batadv_priv *bat_priv, void (*optr)(struct batadv_priv *bat_priv, struct batadv_orig_node *orig, - uint8_t flags, + u8 flags, void *tvlv_value, - uint16_t tvlv_value_len), + u16 tvlv_value_len), int (*uptr)(struct batadv_priv *bat_priv, - uint8_t *src, uint8_t *dst, + u8 *src, u8 *dst, void *tvlv_value, - uint16_t tvlv_value_len), - uint8_t type, uint8_t version, uint8_t flags) + u16 tvlv_value_len), + u8 type, u8 version, u8 flags) { struct batadv_tvlv_handler *tvlv_handler; @@ -1108,7 +1110,7 @@ void batadv_tvlv_handler_register(struct batadv_priv *bat_priv, * @version: tvlv handler version to be unregistered */ void batadv_tvlv_handler_unregister(struct batadv_priv *bat_priv, - uint8_t type, uint8_t version) + u8 type, u8 version) { struct batadv_tvlv_handler *tvlv_handler; @@ -1134,9 +1136,9 @@ void batadv_tvlv_handler_unregister(struct batadv_priv *bat_priv, * @tvlv_value: tvlv content * @tvlv_value_len: tvlv content length */ -void batadv_tvlv_unicast_send(struct batadv_priv *bat_priv, uint8_t *src, - uint8_t *dst, uint8_t type, uint8_t version, - void *tvlv_value, uint16_t tvlv_value_len) +void batadv_tvlv_unicast_send(struct batadv_priv *bat_priv, u8 *src, + u8 *dst, u8 type, u8 version, + void *tvlv_value, u16 tvlv_value_len) { struct batadv_unicast_tvlv_packet *unicast_tvlv_packet; struct batadv_tvlv_hdr *tvlv_hdr; diff --git a/net/batman-adv/main.h b/net/batman-adv/main.h index 41d27c7872b9..ebd8af0a1eb0 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 "2015.1" +#define BATADV_SOURCE_VERSION "2015.2" #endif /* B.A.T.M.A.N. parameters */ @@ -193,7 +193,7 @@ extern struct workqueue_struct *batadv_event_workqueue; int batadv_mesh_init(struct net_device *soft_iface); void batadv_mesh_free(struct net_device *soft_iface); -bool batadv_is_my_mac(struct batadv_priv *bat_priv, const uint8_t *addr); +bool batadv_is_my_mac(struct batadv_priv *bat_priv, const u8 *addr); struct batadv_hard_iface * batadv_seq_print_text_primary_if_get(struct seq_file *seq); int batadv_max_header_len(void); @@ -202,10 +202,10 @@ int batadv_batman_skb_recv(struct sk_buff *skb, struct net_device *dev, struct packet_type *ptype, struct net_device *orig_dev); int -batadv_recv_handler_register(uint8_t packet_type, +batadv_recv_handler_register(u8 packet_type, int (*recv_handler)(struct sk_buff *, struct batadv_hard_iface *)); -void batadv_recv_handler_unregister(uint8_t packet_type); +void batadv_recv_handler_unregister(u8 packet_type); 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); @@ -304,7 +304,7 @@ static inline bool batadv_has_timed_out(unsigned long timestamp, * they handle overflows/underflows and can correctly check for a * predecessor/successor unless the variable sequence number has grown by * more then 2**(bitwidth(x)-1)-1. - * This means that for a uint8_t with the maximum value 255, it would think: + * This means that for a u8 with the maximum value 255, it would think: * - when adding nothing - it is neither a predecessor nor a successor * - before adding more than 127 to the starting value - it is a predecessor, * - when adding 128 - it is neither a predecessor nor a successor, @@ -327,10 +327,9 @@ static inline void batadv_add_counter(struct batadv_priv *bat_priv, size_t idx, #define batadv_inc_counter(b, i) batadv_add_counter(b, i, 1) /* Sum and return the cpu-local counters for index 'idx' */ -static inline uint64_t batadv_sum_counter(struct batadv_priv *bat_priv, - size_t idx) +static inline u64 batadv_sum_counter(struct batadv_priv *bat_priv, size_t idx) { - uint64_t *counters, sum = 0; + u64 *counters, sum = 0; int cpu; for_each_possible_cpu(cpu) { @@ -348,39 +347,38 @@ static inline uint64_t batadv_sum_counter(struct batadv_priv *bat_priv, #define BATADV_SKB_CB(__skb) ((struct batadv_skb_cb *)&((__skb)->cb[0])) void batadv_tvlv_container_register(struct batadv_priv *bat_priv, - uint8_t type, uint8_t version, - void *tvlv_value, uint16_t tvlv_value_len); -uint16_t batadv_tvlv_container_ogm_append(struct batadv_priv *bat_priv, - unsigned char **packet_buff, - int *packet_buff_len, - int packet_min_len); + u8 type, u8 version, + void *tvlv_value, u16 tvlv_value_len); +u16 batadv_tvlv_container_ogm_append(struct batadv_priv *bat_priv, + unsigned char **packet_buff, + int *packet_buff_len, int packet_min_len); void batadv_tvlv_ogm_receive(struct batadv_priv *bat_priv, struct batadv_ogm_packet *batadv_ogm_packet, struct batadv_orig_node *orig_node); void batadv_tvlv_container_unregister(struct batadv_priv *bat_priv, - uint8_t type, uint8_t version); + u8 type, u8 version); void batadv_tvlv_handler_register(struct batadv_priv *bat_priv, void (*optr)(struct batadv_priv *bat_priv, struct batadv_orig_node *orig, - uint8_t flags, + u8 flags, void *tvlv_value, - uint16_t tvlv_value_len), + u16 tvlv_value_len), int (*uptr)(struct batadv_priv *bat_priv, - uint8_t *src, uint8_t *dst, + u8 *src, u8 *dst, void *tvlv_value, - uint16_t tvlv_value_len), - uint8_t type, uint8_t version, uint8_t flags); + u16 tvlv_value_len), + u8 type, u8 version, u8 flags); void batadv_tvlv_handler_unregister(struct batadv_priv *bat_priv, - uint8_t type, uint8_t version); + u8 type, u8 version); int batadv_tvlv_containers_process(struct batadv_priv *bat_priv, bool ogm_source, struct batadv_orig_node *orig_node, - uint8_t *src, uint8_t *dst, - void *tvlv_buff, uint16_t tvlv_buff_len); -void batadv_tvlv_unicast_send(struct batadv_priv *bat_priv, uint8_t *src, - uint8_t *dst, uint8_t type, uint8_t version, - void *tvlv_value, uint16_t tvlv_value_len); + u8 *src, u8 *dst, + void *tvlv_buff, u16 tvlv_buff_len); +void batadv_tvlv_unicast_send(struct batadv_priv *bat_priv, u8 *src, + u8 *dst, u8 type, u8 version, + void *tvlv_value, u16 tvlv_value_len); unsigned short batadv_get_vid(struct sk_buff *skb, size_t header_len); bool batadv_vlan_ap_isola_get(struct batadv_priv *bat_priv, unsigned short vid); diff --git a/net/batman-adv/multicast.c b/net/batman-adv/multicast.c index 7aa480b7edd0..eb76386f8d4b 100644 --- a/net/batman-adv/multicast.c +++ b/net/batman-adv/multicast.c @@ -19,6 +19,8 @@ #include "main.h" #include <linux/atomic.h> +#include <linux/bitops.h> +#include <linux/bug.h> #include <linux/byteorder/generic.h> #include <linux/errno.h> #include <linux/etherdevice.h> @@ -29,6 +31,7 @@ #include <linux/ip.h> #include <linux/ipv6.h> #include <linux/list.h> +#include <linux/lockdep.h> #include <linux/netdevice.h> #include <linux/rculist.h> #include <linux/rcupdate.h> @@ -87,7 +90,7 @@ static int batadv_mcast_mla_softif_get(struct net_device *dev, * Returns true if the given address is already in the given list. * Otherwise returns false. */ -static bool batadv_mcast_mla_is_duplicate(uint8_t *mcast_addr, +static bool batadv_mcast_mla_is_duplicate(u8 *mcast_addr, struct hlist_head *mcast_list) { struct batadv_hw_addr *mcast_entry; @@ -101,15 +104,19 @@ static bool batadv_mcast_mla_is_duplicate(uint8_t *mcast_addr, /** * batadv_mcast_mla_list_free - free a list of multicast addresses + * @bat_priv: the bat priv with all the soft interface information * @mcast_list: the list to free * * Removes and frees all items in the given mcast_list. */ -static void batadv_mcast_mla_list_free(struct hlist_head *mcast_list) +static void batadv_mcast_mla_list_free(struct batadv_priv *bat_priv, + struct hlist_head *mcast_list) { struct batadv_hw_addr *mcast_entry; struct hlist_node *tmp; + lockdep_assert_held(&bat_priv->tt.commit_lock); + hlist_for_each_entry_safe(mcast_entry, tmp, mcast_list, list) { hlist_del(&mcast_entry->list); kfree(mcast_entry); @@ -132,6 +139,8 @@ static void batadv_mcast_mla_tt_retract(struct batadv_priv *bat_priv, struct batadv_hw_addr *mcast_entry; struct hlist_node *tmp; + lockdep_assert_held(&bat_priv->tt.commit_lock); + hlist_for_each_entry_safe(mcast_entry, tmp, &bat_priv->mcast.mla_list, list) { if (mcast_list && @@ -162,6 +171,8 @@ static void batadv_mcast_mla_tt_add(struct batadv_priv *bat_priv, struct batadv_hw_addr *mcast_entry; struct hlist_node *tmp; + lockdep_assert_held(&bat_priv->tt.commit_lock); + if (!mcast_list) return; @@ -266,7 +277,7 @@ update: batadv_mcast_mla_tt_add(bat_priv, &mcast_list); out: - batadv_mcast_mla_list_free(&mcast_list); + batadv_mcast_mla_list_free(bat_priv, &mcast_list); } /** @@ -588,19 +599,28 @@ batadv_mcast_forw_mode(struct batadv_priv *bat_priv, struct sk_buff *skb, * * If the BATADV_MCAST_WANT_ALL_UNSNOOPABLES flag of this originator, * orig, has toggled then this method updates counter and list accordingly. + * + * Caller needs to hold orig->mcast_handler_lock. */ static void batadv_mcast_want_unsnoop_update(struct batadv_priv *bat_priv, struct batadv_orig_node *orig, - uint8_t mcast_flags) + u8 mcast_flags) { + struct hlist_node *node = &orig->mcast_want_all_unsnoopables_node; + struct hlist_head *head = &bat_priv->mcast.want_all_unsnoopables_list; + + lockdep_assert_held(&orig->mcast_handler_lock); + /* switched from flag unset to set */ if (mcast_flags & BATADV_MCAST_WANT_ALL_UNSNOOPABLES && !(orig->mcast_flags & BATADV_MCAST_WANT_ALL_UNSNOOPABLES)) { atomic_inc(&bat_priv->mcast.num_want_all_unsnoopables); spin_lock_bh(&bat_priv->mcast.want_lists_lock); - hlist_add_head_rcu(&orig->mcast_want_all_unsnoopables_node, - &bat_priv->mcast.want_all_unsnoopables_list); + /* flag checks above + mcast_handler_lock prevents this */ + WARN_ON(!hlist_unhashed(node)); + + hlist_add_head_rcu(node, head); spin_unlock_bh(&bat_priv->mcast.want_lists_lock); /* switched from flag set to unset */ } else if (!(mcast_flags & BATADV_MCAST_WANT_ALL_UNSNOOPABLES) && @@ -608,7 +628,10 @@ static void batadv_mcast_want_unsnoop_update(struct batadv_priv *bat_priv, atomic_dec(&bat_priv->mcast.num_want_all_unsnoopables); spin_lock_bh(&bat_priv->mcast.want_lists_lock); - hlist_del_rcu(&orig->mcast_want_all_unsnoopables_node); + /* flag checks above + mcast_handler_lock prevents this */ + WARN_ON(hlist_unhashed(node)); + + hlist_del_init_rcu(node); spin_unlock_bh(&bat_priv->mcast.want_lists_lock); } } @@ -621,19 +644,28 @@ static void batadv_mcast_want_unsnoop_update(struct batadv_priv *bat_priv, * * If the BATADV_MCAST_WANT_ALL_IPV4 flag of this originator, orig, has * toggled then this method updates counter and list accordingly. + * + * Caller needs to hold orig->mcast_handler_lock. */ static void batadv_mcast_want_ipv4_update(struct batadv_priv *bat_priv, struct batadv_orig_node *orig, - uint8_t mcast_flags) + u8 mcast_flags) { + struct hlist_node *node = &orig->mcast_want_all_ipv4_node; + struct hlist_head *head = &bat_priv->mcast.want_all_ipv4_list; + + lockdep_assert_held(&orig->mcast_handler_lock); + /* switched from flag unset to set */ if (mcast_flags & BATADV_MCAST_WANT_ALL_IPV4 && !(orig->mcast_flags & BATADV_MCAST_WANT_ALL_IPV4)) { atomic_inc(&bat_priv->mcast.num_want_all_ipv4); spin_lock_bh(&bat_priv->mcast.want_lists_lock); - hlist_add_head_rcu(&orig->mcast_want_all_ipv4_node, - &bat_priv->mcast.want_all_ipv4_list); + /* flag checks above + mcast_handler_lock prevents this */ + WARN_ON(!hlist_unhashed(node)); + + hlist_add_head_rcu(node, head); spin_unlock_bh(&bat_priv->mcast.want_lists_lock); /* switched from flag set to unset */ } else if (!(mcast_flags & BATADV_MCAST_WANT_ALL_IPV4) && @@ -641,7 +673,10 @@ static void batadv_mcast_want_ipv4_update(struct batadv_priv *bat_priv, atomic_dec(&bat_priv->mcast.num_want_all_ipv4); spin_lock_bh(&bat_priv->mcast.want_lists_lock); - hlist_del_rcu(&orig->mcast_want_all_ipv4_node); + /* flag checks above + mcast_handler_lock prevents this */ + WARN_ON(hlist_unhashed(node)); + + hlist_del_init_rcu(node); spin_unlock_bh(&bat_priv->mcast.want_lists_lock); } } @@ -654,19 +689,28 @@ static void batadv_mcast_want_ipv4_update(struct batadv_priv *bat_priv, * * If the BATADV_MCAST_WANT_ALL_IPV6 flag of this originator, orig, has * toggled then this method updates counter and list accordingly. + * + * Caller needs to hold orig->mcast_handler_lock. */ static void batadv_mcast_want_ipv6_update(struct batadv_priv *bat_priv, struct batadv_orig_node *orig, - uint8_t mcast_flags) + u8 mcast_flags) { + struct hlist_node *node = &orig->mcast_want_all_ipv6_node; + struct hlist_head *head = &bat_priv->mcast.want_all_ipv6_list; + + lockdep_assert_held(&orig->mcast_handler_lock); + /* switched from flag unset to set */ if (mcast_flags & BATADV_MCAST_WANT_ALL_IPV6 && !(orig->mcast_flags & BATADV_MCAST_WANT_ALL_IPV6)) { atomic_inc(&bat_priv->mcast.num_want_all_ipv6); spin_lock_bh(&bat_priv->mcast.want_lists_lock); - hlist_add_head_rcu(&orig->mcast_want_all_ipv6_node, - &bat_priv->mcast.want_all_ipv6_list); + /* flag checks above + mcast_handler_lock prevents this */ + WARN_ON(!hlist_unhashed(node)); + + hlist_add_head_rcu(node, head); spin_unlock_bh(&bat_priv->mcast.want_lists_lock); /* switched from flag set to unset */ } else if (!(mcast_flags & BATADV_MCAST_WANT_ALL_IPV6) && @@ -674,7 +718,10 @@ static void batadv_mcast_want_ipv6_update(struct batadv_priv *bat_priv, atomic_dec(&bat_priv->mcast.num_want_all_ipv6); spin_lock_bh(&bat_priv->mcast.want_lists_lock); - hlist_del_rcu(&orig->mcast_want_all_ipv6_node); + /* flag checks above + mcast_handler_lock prevents this */ + WARN_ON(hlist_unhashed(node)); + + hlist_del_init_rcu(node); spin_unlock_bh(&bat_priv->mcast.want_lists_lock); } } @@ -689,47 +736,50 @@ static void batadv_mcast_want_ipv6_update(struct batadv_priv *bat_priv, */ static void batadv_mcast_tvlv_ogm_handler_v1(struct batadv_priv *bat_priv, struct batadv_orig_node *orig, - uint8_t flags, + u8 flags, void *tvlv_value, - uint16_t tvlv_value_len) + u16 tvlv_value_len) { bool orig_mcast_enabled = !(flags & BATADV_TVLV_HANDLER_OGM_CIFNOTFND); - uint8_t mcast_flags = BATADV_NO_FLAGS; + u8 mcast_flags = BATADV_NO_FLAGS; bool orig_initialized; - orig_initialized = orig->capa_initialized & BATADV_ORIG_CAPA_HAS_MCAST; + if (orig_mcast_enabled && tvlv_value && + (tvlv_value_len >= sizeof(mcast_flags))) + mcast_flags = *(u8 *)tvlv_value; + + spin_lock_bh(&orig->mcast_handler_lock); + orig_initialized = test_bit(BATADV_ORIG_CAPA_HAS_MCAST, + &orig->capa_initialized); /* If mcast support is turned on decrease the disabled mcast node * counter only if we had increased it for this node before. If this * is a completely new orig_node no need to decrease the counter. */ if (orig_mcast_enabled && - !(orig->capabilities & BATADV_ORIG_CAPA_HAS_MCAST)) { + !test_bit(BATADV_ORIG_CAPA_HAS_MCAST, &orig->capabilities)) { if (orig_initialized) atomic_dec(&bat_priv->mcast.num_disabled); - orig->capabilities |= BATADV_ORIG_CAPA_HAS_MCAST; + set_bit(BATADV_ORIG_CAPA_HAS_MCAST, &orig->capabilities); /* If mcast support is being switched off or if this is an initial * OGM without mcast support then increase the disabled mcast * node counter. */ } else if (!orig_mcast_enabled && - (orig->capabilities & BATADV_ORIG_CAPA_HAS_MCAST || + (test_bit(BATADV_ORIG_CAPA_HAS_MCAST, &orig->capabilities) || !orig_initialized)) { atomic_inc(&bat_priv->mcast.num_disabled); - orig->capabilities &= ~BATADV_ORIG_CAPA_HAS_MCAST; + clear_bit(BATADV_ORIG_CAPA_HAS_MCAST, &orig->capabilities); } - orig->capa_initialized |= BATADV_ORIG_CAPA_HAS_MCAST; - - if (orig_mcast_enabled && tvlv_value && - (tvlv_value_len >= sizeof(mcast_flags))) - mcast_flags = *(uint8_t *)tvlv_value; + set_bit(BATADV_ORIG_CAPA_HAS_MCAST, &orig->capa_initialized); batadv_mcast_want_unsnoop_update(bat_priv, orig, mcast_flags); batadv_mcast_want_ipv4_update(bat_priv, orig, mcast_flags); batadv_mcast_want_ipv6_update(bat_priv, orig, mcast_flags); orig->mcast_flags = mcast_flags; + spin_unlock_bh(&orig->mcast_handler_lock); } /** @@ -763,11 +813,15 @@ void batadv_mcast_purge_orig(struct batadv_orig_node *orig) { struct batadv_priv *bat_priv = orig->bat_priv; - if (!(orig->capabilities & BATADV_ORIG_CAPA_HAS_MCAST) && - orig->capa_initialized & BATADV_ORIG_CAPA_HAS_MCAST) + spin_lock_bh(&orig->mcast_handler_lock); + + if (!test_bit(BATADV_ORIG_CAPA_HAS_MCAST, &orig->capabilities) && + test_bit(BATADV_ORIG_CAPA_HAS_MCAST, &orig->capa_initialized)) atomic_dec(&bat_priv->mcast.num_disabled); batadv_mcast_want_unsnoop_update(bat_priv, orig, BATADV_NO_FLAGS); batadv_mcast_want_ipv4_update(bat_priv, orig, BATADV_NO_FLAGS); batadv_mcast_want_ipv6_update(bat_priv, orig, BATADV_NO_FLAGS); + + spin_unlock_bh(&orig->mcast_handler_lock); } diff --git a/net/batman-adv/multicast.h b/net/batman-adv/multicast.h index beb6e56c624a..8f3cb04b9f13 100644 --- a/net/batman-adv/multicast.h +++ b/net/batman-adv/multicast.h @@ -20,8 +20,6 @@ #include "main.h" -struct batadv_orig_node; -struct batadv_priv; struct sk_buff; /** diff --git a/net/batman-adv/network-coding.c b/net/batman-adv/network-coding.c index f0a50f31d822..f5276be2c77c 100644 --- a/net/batman-adv/network-coding.c +++ b/net/batman-adv/network-coding.c @@ -19,6 +19,7 @@ #include "main.h" #include <linux/atomic.h> +#include <linux/bitops.h> #include <linux/byteorder/generic.h> #include <linux/compiler.h> #include <linux/debugfs.h> @@ -129,14 +130,13 @@ void batadv_nc_status_update(struct net_device *net_dev) */ static void batadv_nc_tvlv_ogm_handler_v1(struct batadv_priv *bat_priv, struct batadv_orig_node *orig, - uint8_t flags, - void *tvlv_value, - uint16_t tvlv_value_len) + u8 flags, + void *tvlv_value, u16 tvlv_value_len) { if (flags & BATADV_TVLV_HANDLER_OGM_CIFNOTFND) - orig->capabilities &= ~BATADV_ORIG_CAPA_HAS_NC; + clear_bit(BATADV_ORIG_CAPA_HAS_NC, &orig->capabilities); else - orig->capabilities |= BATADV_ORIG_CAPA_HAS_NC; + set_bit(BATADV_ORIG_CAPA_HAS_NC, &orig->capabilities); } /** @@ -381,7 +381,7 @@ static void batadv_nc_purge_orig_hash(struct batadv_priv *bat_priv) struct batadv_hashtable *hash = bat_priv->orig_hash; struct hlist_head *head; struct batadv_orig_node *orig_node; - uint32_t i; + u32 i; if (!hash) return; @@ -417,7 +417,7 @@ static void batadv_nc_purge_paths(struct batadv_priv *bat_priv, struct hlist_node *node_tmp; struct batadv_nc_path *nc_path; spinlock_t *lock; /* Protects lists in hash */ - uint32_t i; + u32 i; for (i = 0; i < hash->size; i++) { head = &hash->table[i]; @@ -477,10 +477,10 @@ static void batadv_nc_hash_key_gen(struct batadv_nc_path *key, const char *src, * * Returns the selected index in the hash table for the given data. */ -static uint32_t batadv_nc_hash_choose(const void *data, uint32_t size) +static u32 batadv_nc_hash_choose(const void *data, u32 size) { const struct batadv_nc_path *nc_path = data; - uint32_t hash = 0; + u32 hash = 0; hash = jhash(&nc_path->prev_hop, sizeof(nc_path->prev_hop), hash); hash = jhash(&nc_path->next_hop, sizeof(nc_path->next_hop), hash); @@ -586,6 +586,8 @@ static bool batadv_nc_sniffed_purge(struct batadv_priv *bat_priv, unsigned long timeout = bat_priv->nc.max_buffer_time; bool res = false; + lockdep_assert_held(&nc_path->packet_list_lock); + /* Packets are added to tail, so the remaining packets did not time * out and we can stop processing the current queue */ @@ -622,6 +624,8 @@ static bool batadv_nc_fwd_flush(struct batadv_priv *bat_priv, { unsigned long timeout = bat_priv->nc.max_fwd_delay; + lockdep_assert_held(&nc_path->packet_list_lock); + /* Packets are added to tail, so the remaining packets did not time * out and we can stop processing the current queue */ @@ -743,8 +747,8 @@ static bool batadv_can_nc_with_orig(struct batadv_priv *bat_priv, struct batadv_ogm_packet *ogm_packet) { struct batadv_orig_ifinfo *orig_ifinfo; - uint32_t last_real_seqno; - uint8_t last_ttl; + u32 last_real_seqno; + u8 last_ttl; orig_ifinfo = batadv_orig_ifinfo_get(orig_node, BATADV_IF_DEFAULT); if (!orig_ifinfo) @@ -872,8 +876,8 @@ free: } /** - * batadv_nc_update_nc_node - updates stored incoming and outgoing nc node structs - * (best called on incoming OGMs) + * batadv_nc_update_nc_node - updates stored incoming and outgoing nc node + * structs (best called on incoming OGMs) * @bat_priv: the bat priv with all the soft interface information * @orig_node: orig node originating the ogm packet * @orig_neigh_node: neighboring orig node from which we received the ogm packet @@ -887,14 +891,15 @@ void batadv_nc_update_nc_node(struct batadv_priv *bat_priv, struct batadv_ogm_packet *ogm_packet, int is_single_hop_neigh) { - struct batadv_nc_node *in_nc_node = NULL, *out_nc_node = NULL; + struct batadv_nc_node *in_nc_node = NULL; + struct batadv_nc_node *out_nc_node = NULL; /* Check if network coding is enabled */ if (!atomic_read(&bat_priv->network_coding)) goto out; /* check if orig node is network coding enabled */ - if (!(orig_node->capabilities & BATADV_ORIG_CAPA_HAS_NC)) + if (!test_bit(BATADV_ORIG_CAPA_HAS_NC, &orig_node->capabilities)) goto out; /* accept ogms from 'good' neighbors and single hop neighbors */ @@ -937,8 +942,8 @@ out: */ static struct batadv_nc_path *batadv_nc_get_path(struct batadv_priv *bat_priv, struct batadv_hashtable *hash, - uint8_t *src, - uint8_t *dst) + u8 *src, + u8 *dst) { int hash_added; struct batadv_nc_path *nc_path, nc_path_key; @@ -990,9 +995,9 @@ static struct batadv_nc_path *batadv_nc_get_path(struct batadv_priv *bat_priv, * selection of a receiver with slightly lower TQ than the other * @tq: to be weighted tq value */ -static uint8_t batadv_nc_random_weight_tq(uint8_t tq) +static u8 batadv_nc_random_weight_tq(u8 tq) { - uint8_t rand_val, rand_tq; + u8 rand_val, rand_tq; get_random_bytes(&rand_val, sizeof(rand_val)); @@ -1037,7 +1042,7 @@ static bool batadv_nc_code_packets(struct batadv_priv *bat_priv, struct batadv_nc_packet *nc_packet, struct batadv_neigh_node *neigh_node) { - uint8_t tq_weighted_neigh, tq_weighted_coding, tq_tmp; + u8 tq_weighted_neigh, tq_weighted_coding, tq_tmp; struct sk_buff *skb_dest, *skb_src; struct batadv_unicast_packet *packet1; struct batadv_unicast_packet *packet2; @@ -1046,7 +1051,7 @@ static bool batadv_nc_code_packets(struct batadv_priv *bat_priv, struct batadv_neigh_node *router_coding = NULL; struct batadv_neigh_ifinfo *router_neigh_ifinfo = NULL; struct batadv_neigh_ifinfo *router_coding_ifinfo = NULL; - uint8_t *first_source, *first_dest, *second_source, *second_dest; + u8 *first_source, *first_dest, *second_source, *second_dest; __be32 packet_id1, packet_id2; size_t count; bool res = false; @@ -1230,8 +1235,7 @@ out: * * Returns true if coding of a decoded packet is allowed. */ -static bool batadv_nc_skb_coding_possible(struct sk_buff *skb, - uint8_t *dst, uint8_t *src) +static bool batadv_nc_skb_coding_possible(struct sk_buff *skb, u8 *dst, u8 *src) { if (BATADV_SKB_CB(skb)->decoded && !batadv_compare_eth(dst, src)) return false; @@ -1254,7 +1258,7 @@ batadv_nc_path_search(struct batadv_priv *bat_priv, struct batadv_nc_node *in_nc_node, struct batadv_nc_node *out_nc_node, struct sk_buff *skb, - uint8_t *eth_dst) + u8 *eth_dst) { struct batadv_nc_path *nc_path, nc_path_key; struct batadv_nc_packet *nc_packet_out = NULL; @@ -1320,8 +1324,8 @@ batadv_nc_path_search(struct batadv_priv *bat_priv, static struct batadv_nc_packet * batadv_nc_skb_src_search(struct batadv_priv *bat_priv, struct sk_buff *skb, - uint8_t *eth_dst, - uint8_t *eth_src, + u8 *eth_dst, + u8 *eth_src, struct batadv_nc_node *in_nc_node) { struct batadv_orig_node *orig_node; @@ -1361,7 +1365,7 @@ batadv_nc_skb_src_search(struct batadv_priv *bat_priv, */ static void batadv_nc_skb_store_before_coding(struct batadv_priv *bat_priv, struct sk_buff *skb, - uint8_t *eth_dst_new) + u8 *eth_dst_new) { struct ethhdr *ethhdr; @@ -1637,7 +1641,7 @@ batadv_nc_skb_decode_packet(struct batadv_priv *bat_priv, struct sk_buff *skb, struct batadv_unicast_packet *unicast_packet; struct batadv_coded_packet coded_packet_tmp; struct ethhdr *ethhdr, ethhdr_tmp; - uint8_t *orig_dest, ttl, ttvn; + u8 *orig_dest, ttl, ttvn; unsigned int coding_len; int err; @@ -1729,7 +1733,7 @@ batadv_nc_find_decoding_packet(struct batadv_priv *bat_priv, struct batadv_hashtable *hash = bat_priv->nc.decoding_hash; struct batadv_nc_packet *tmp_nc_packet, *nc_packet = NULL; struct batadv_nc_path *nc_path, nc_path_key; - uint8_t *dest, *source; + u8 *dest, *source; __be32 packet_id; int index; diff --git a/net/batman-adv/network-coding.h b/net/batman-adv/network-coding.h index 5b79aa8c64c1..8f6d4ad8778a 100644 --- a/net/batman-adv/network-coding.h +++ b/net/batman-adv/network-coding.h @@ -22,11 +22,7 @@ #include <linux/types.h> -struct batadv_nc_node; -struct batadv_neigh_node; struct batadv_ogm_packet; -struct batadv_orig_node; -struct batadv_priv; struct net_device; struct seq_file; struct sk_buff; diff --git a/net/batman-adv/originator.c b/net/batman-adv/originator.c index 018b7495ad84..7486df9ed48d 100644 --- a/net/batman-adv/originator.c +++ b/net/batman-adv/originator.c @@ -26,6 +26,7 @@ #include <linux/list.h> #include <linux/lockdep.h> #include <linux/netdevice.h> +#include <linux/rculist.h> #include <linux/seq_file.h> #include <linux/slab.h> #include <linux/spinlock.h> @@ -70,7 +71,7 @@ batadv_orig_node_vlan_get(struct batadv_orig_node *orig_node, struct batadv_orig_node_vlan *vlan = NULL, *tmp; rcu_read_lock(); - list_for_each_entry_rcu(tmp, &orig_node->vlan_list, list) { + hlist_for_each_entry_rcu(tmp, &orig_node->vlan_list, list) { if (tmp->vid != vid) continue; @@ -118,7 +119,7 @@ batadv_orig_node_vlan_new(struct batadv_orig_node *orig_node, atomic_set(&vlan->refcount, 2); vlan->vid = vid; - list_add_rcu(&vlan->list, &orig_node->vlan_list); + hlist_add_head_rcu(&vlan->list, &orig_node->vlan_list); out: spin_unlock_bh(&orig_node->vlan_list_lock); @@ -442,41 +443,6 @@ out: } /** - * batadv_neigh_node_new - create and init a new neigh_node object - * @hard_iface: the interface where the neighbour is connected to - * @neigh_addr: the mac address of the neighbour interface - * @orig_node: originator object representing the neighbour - * - * Allocates a new neigh_node object and initialises all the generic fields. - * Returns the new object or NULL on failure. - */ -struct batadv_neigh_node * -batadv_neigh_node_new(struct batadv_hard_iface *hard_iface, - const uint8_t *neigh_addr, - struct batadv_orig_node *orig_node) -{ - struct batadv_neigh_node *neigh_node; - - neigh_node = kzalloc(sizeof(*neigh_node), GFP_ATOMIC); - if (!neigh_node) - goto out; - - INIT_HLIST_NODE(&neigh_node->list); - INIT_HLIST_HEAD(&neigh_node->ifinfo_list); - spin_lock_init(&neigh_node->ifinfo_lock); - - ether_addr_copy(neigh_node->addr, neigh_addr); - neigh_node->if_incoming = hard_iface; - neigh_node->orig_node = orig_node; - - /* extra reference for return */ - atomic_set(&neigh_node->refcount, 2); - -out: - return neigh_node; -} - -/** * batadv_neigh_node_get - retrieve a neighbour from the list * @orig_node: originator which the neighbour belongs to * @hard_iface: the interface where this neighbour is connected to @@ -486,10 +452,10 @@ out: * which is connected through the provided hard interface. * Returns NULL if the neighbour is not found. */ -struct batadv_neigh_node * +static struct batadv_neigh_node * batadv_neigh_node_get(const struct batadv_orig_node *orig_node, const struct batadv_hard_iface *hard_iface, - const uint8_t *addr) + const u8 *addr) { struct batadv_neigh_node *tmp_neigh_node, *res = NULL; @@ -513,6 +479,59 @@ batadv_neigh_node_get(const struct batadv_orig_node *orig_node, } /** + * batadv_neigh_node_new - create and init a new neigh_node object + * @orig_node: originator object representing the neighbour + * @hard_iface: the interface where the neighbour is connected to + * @neigh_addr: the mac address of the neighbour interface + * + * Allocates a new neigh_node object and initialises all the generic fields. + * Returns the new object or NULL on failure. + */ +struct batadv_neigh_node * +batadv_neigh_node_new(struct batadv_orig_node *orig_node, + struct batadv_hard_iface *hard_iface, + const u8 *neigh_addr) +{ + struct batadv_neigh_node *neigh_node; + + neigh_node = batadv_neigh_node_get(orig_node, hard_iface, neigh_addr); + if (neigh_node) + goto out; + + neigh_node = kzalloc(sizeof(*neigh_node), GFP_ATOMIC); + if (!neigh_node) + goto out; + + if (!atomic_inc_not_zero(&hard_iface->refcount)) { + kfree(neigh_node); + neigh_node = NULL; + goto out; + } + + INIT_HLIST_NODE(&neigh_node->list); + INIT_HLIST_HEAD(&neigh_node->ifinfo_list); + spin_lock_init(&neigh_node->ifinfo_lock); + + ether_addr_copy(neigh_node->addr, neigh_addr); + neigh_node->if_incoming = hard_iface; + neigh_node->orig_node = orig_node; + + /* extra reference for return */ + atomic_set(&neigh_node->refcount, 2); + + spin_lock_bh(&orig_node->neigh_list_lock); + hlist_add_head_rcu(&neigh_node->list, &orig_node->neigh_list); + spin_unlock_bh(&orig_node->neigh_list_lock); + + batadv_dbg(BATADV_DBG_BATMAN, orig_node->bat_priv, + "Creating new neighbor %pM for orig_node %pM on interface %s\n", + neigh_addr, orig_node->orig, hard_iface->net_dev->name); + +out: + return neigh_node; +} + +/** * batadv_orig_ifinfo_free_rcu - free the orig_ifinfo object * @rcu: rcu pointer of the orig_ifinfo object */ @@ -624,7 +643,7 @@ void batadv_originator_free(struct batadv_priv *bat_priv) struct hlist_head *head; spinlock_t *list_lock; /* spinlock to protect write access */ struct batadv_orig_node *orig_node; - uint32_t i; + u32 i; if (!hash) return; @@ -659,7 +678,7 @@ void batadv_originator_free(struct batadv_priv *bat_priv) * Returns the newly created object or NULL on failure. */ struct batadv_orig_node *batadv_orig_node_new(struct batadv_priv *bat_priv, - const uint8_t *addr) + const u8 *addr) { struct batadv_orig_node *orig_node; struct batadv_orig_node_vlan *vlan; @@ -674,7 +693,7 @@ struct batadv_orig_node *batadv_orig_node_new(struct batadv_priv *bat_priv, return NULL; INIT_HLIST_HEAD(&orig_node->neigh_list); - INIT_LIST_HEAD(&orig_node->vlan_list); + INIT_HLIST_HEAD(&orig_node->vlan_list); INIT_HLIST_HEAD(&orig_node->ifinfo_list); spin_lock_init(&orig_node->bcast_seqno_lock); spin_lock_init(&orig_node->neigh_list_lock); @@ -696,8 +715,13 @@ struct batadv_orig_node *batadv_orig_node_new(struct batadv_priv *bat_priv, orig_node->last_seen = jiffies; reset_time = jiffies - 1 - msecs_to_jiffies(BATADV_RESET_PROTECTION_MS); orig_node->bcast_seqno_reset = reset_time; + #ifdef CONFIG_BATMAN_ADV_MCAST orig_node->mcast_flags = BATADV_NO_FLAGS; + INIT_HLIST_NODE(&orig_node->mcast_want_all_unsnoopables_node); + INIT_HLIST_NODE(&orig_node->mcast_want_all_ipv4_node); + INIT_HLIST_NODE(&orig_node->mcast_want_all_ipv6_node); + spin_lock_init(&orig_node->mcast_handler_lock); #endif /* create a vlan object for the "untagged" LAN */ @@ -976,7 +1000,7 @@ static void _batadv_purge_orig(struct batadv_priv *bat_priv) struct hlist_head *head; spinlock_t *list_lock; /* spinlock to protect write access */ struct batadv_orig_node *orig_node; - uint32_t i; + u32 i; if (!hash) return; @@ -1005,7 +1029,6 @@ static void _batadv_purge_orig(struct batadv_priv *bat_priv) spin_unlock_bh(list_lock); } - batadv_gw_node_purge(bat_priv); batadv_gw_election(bat_priv); } @@ -1110,7 +1133,7 @@ int batadv_orig_hash_add_if(struct batadv_hard_iface *hard_iface, struct batadv_hashtable *hash = bat_priv->orig_hash; struct hlist_head *head; struct batadv_orig_node *orig_node; - uint32_t i; + u32 i; int ret; /* resize all orig nodes because orig_node->bcast_own(_sum) depend on @@ -1147,7 +1170,7 @@ int batadv_orig_hash_del_if(struct batadv_hard_iface *hard_iface, struct batadv_hard_iface *hard_iface_tmp; struct batadv_orig_node *orig_node; struct batadv_algo_ops *bao = bat_priv->bat_algo_ops; - uint32_t i; + u32 i; int ret; /* resize all orig nodes because orig_node->bcast_own(_sum) depend on diff --git a/net/batman-adv/originator.h b/net/batman-adv/originator.h index 79734d302010..fa18f9bf266b 100644 --- a/net/batman-adv/originator.h +++ b/net/batman-adv/originator.h @@ -40,15 +40,11 @@ void batadv_purge_orig_ref(struct batadv_priv *bat_priv); void batadv_orig_node_free_ref(struct batadv_orig_node *orig_node); void batadv_orig_node_free_ref_now(struct batadv_orig_node *orig_node); struct batadv_orig_node *batadv_orig_node_new(struct batadv_priv *bat_priv, - const uint8_t *addr); + const u8 *addr); struct batadv_neigh_node * -batadv_neigh_node_get(const struct batadv_orig_node *orig_node, - const struct batadv_hard_iface *hard_iface, - const uint8_t *addr); -struct batadv_neigh_node * -batadv_neigh_node_new(struct batadv_hard_iface *hard_iface, - const uint8_t *neigh_addr, - struct batadv_orig_node *orig_node); +batadv_neigh_node_new(struct batadv_orig_node *orig_node, + struct batadv_hard_iface *hard_iface, + const u8 *neigh_addr); void batadv_neigh_node_free_ref(struct batadv_neigh_node *neigh_node); struct batadv_neigh_node * batadv_orig_router_get(struct batadv_orig_node *orig_node, @@ -86,9 +82,9 @@ void batadv_orig_node_vlan_free_ref(struct batadv_orig_node_vlan *orig_vlan); /* hashfunction to choose an entry in a hash table of given size * hash algorithm from http://en.wikipedia.org/wiki/Hash_table */ -static inline uint32_t batadv_choose_orig(const void *data, uint32_t size) +static inline u32 batadv_choose_orig(const void *data, u32 size) { - uint32_t hash = 0; + u32 hash = 0; hash = jhash(data, ETH_ALEN, hash); return hash % size; diff --git a/net/batman-adv/packet.h b/net/batman-adv/packet.h index 9e747c08d0bc..11f996b39fef 100644 --- a/net/batman-adv/packet.h +++ b/net/batman-adv/packet.h @@ -197,8 +197,8 @@ enum batadv_tvlv_type { * transport the claim type and the group id */ struct batadv_bla_claim_dst { - uint8_t magic[3]; /* FF:43:05 */ - uint8_t type; /* bla_claimframe */ + u8 magic[3]; /* FF:43:05 */ + u8 type; /* bla_claimframe */ __be16 group; /* group id */ }; @@ -213,16 +213,16 @@ struct batadv_bla_claim_dst { * @tvlv_len: length of tvlv data following the ogm header */ struct batadv_ogm_packet { - uint8_t packet_type; - uint8_t version; - uint8_t ttl; - uint8_t flags; - __be32 seqno; - uint8_t orig[ETH_ALEN]; - uint8_t prev_sender[ETH_ALEN]; - uint8_t reserved; - uint8_t tq; - __be16 tvlv_len; + u8 packet_type; + u8 version; + u8 ttl; + u8 flags; + __be32 seqno; + u8 orig[ETH_ALEN]; + u8 prev_sender[ETH_ALEN]; + u8 reserved; + u8 tq; + __be16 tvlv_len; /* __packed is not needed as the struct size is divisible by 4, * and the largest data type in this struct has a size of 4. */ @@ -246,14 +246,14 @@ struct batadv_ogm_packet { * members are padded the same way as they are in real packets. */ struct batadv_icmp_header { - uint8_t packet_type; - uint8_t version; - uint8_t ttl; - uint8_t msg_type; /* see ICMP message types above */ - uint8_t dst[ETH_ALEN]; - uint8_t orig[ETH_ALEN]; - uint8_t uid; - uint8_t align[3]; + u8 packet_type; + u8 version; + u8 ttl; + u8 msg_type; /* see ICMP message types above */ + u8 dst[ETH_ALEN]; + u8 orig[ETH_ALEN]; + u8 uid; + u8 align[3]; }; /** @@ -269,15 +269,15 @@ struct batadv_icmp_header { * @seqno: ICMP sequence number */ struct batadv_icmp_packet { - uint8_t packet_type; - uint8_t version; - uint8_t ttl; - uint8_t msg_type; /* see ICMP message types above */ - uint8_t dst[ETH_ALEN]; - uint8_t orig[ETH_ALEN]; - uint8_t uid; - uint8_t reserved; - __be16 seqno; + u8 packet_type; + u8 version; + u8 ttl; + u8 msg_type; /* see ICMP message types above */ + u8 dst[ETH_ALEN]; + u8 orig[ETH_ALEN]; + u8 uid; + u8 reserved; + __be16 seqno; }; #define BATADV_RR_LEN 16 @@ -296,16 +296,16 @@ struct batadv_icmp_packet { * @rr: route record array */ struct batadv_icmp_packet_rr { - uint8_t packet_type; - uint8_t version; - uint8_t ttl; - uint8_t msg_type; /* see ICMP message types above */ - uint8_t dst[ETH_ALEN]; - uint8_t orig[ETH_ALEN]; - uint8_t uid; - uint8_t rr_cur; - __be16 seqno; - uint8_t rr[BATADV_RR_LEN][ETH_ALEN]; + u8 packet_type; + u8 version; + u8 ttl; + u8 msg_type; /* see ICMP message types above */ + u8 dst[ETH_ALEN]; + u8 orig[ETH_ALEN]; + u8 uid; + u8 rr_cur; + __be16 seqno; + u8 rr[BATADV_RR_LEN][ETH_ALEN]; }; #define BATADV_ICMP_MAX_PACKET_SIZE sizeof(struct batadv_icmp_packet_rr) @@ -331,11 +331,11 @@ struct batadv_icmp_packet_rr { * @dest: originator destination of the unicast packet */ struct batadv_unicast_packet { - uint8_t packet_type; - uint8_t version; - uint8_t ttl; - uint8_t ttvn; /* destination translation table version number */ - uint8_t dest[ETH_ALEN]; + u8 packet_type; + u8 version; + u8 ttl; + u8 ttvn; /* destination translation table version number */ + u8 dest[ETH_ALEN]; /* "4 bytes boundary + 2 bytes" long to make the payload after the * following ethernet header again 4 bytes boundary aligned */ @@ -349,9 +349,9 @@ struct batadv_unicast_packet { */ struct batadv_unicast_4addr_packet { struct batadv_unicast_packet u; - uint8_t src[ETH_ALEN]; - uint8_t subtype; - uint8_t reserved; + u8 src[ETH_ALEN]; + u8 subtype; + u8 reserved; /* "4 bytes boundary + 2 bytes" long to make the payload after the * following ethernet header again 4 bytes boundary aligned */ @@ -370,22 +370,22 @@ struct batadv_unicast_4addr_packet { * @total_size: size of the merged packet */ struct batadv_frag_packet { - uint8_t packet_type; - uint8_t version; /* batman version field */ - uint8_t ttl; + u8 packet_type; + u8 version; /* batman version field */ + u8 ttl; #if defined(__BIG_ENDIAN_BITFIELD) - uint8_t no:4; - uint8_t reserved:4; + u8 no:4; + u8 reserved:4; #elif defined(__LITTLE_ENDIAN_BITFIELD) - uint8_t reserved:4; - uint8_t no:4; + u8 reserved:4; + u8 no:4; #else #error "unknown bitfield endianness" #endif - uint8_t dest[ETH_ALEN]; - uint8_t orig[ETH_ALEN]; - __be16 seqno; - __be16 total_size; + u8 dest[ETH_ALEN]; + u8 orig[ETH_ALEN]; + __be16 seqno; + __be16 total_size; }; /** @@ -398,12 +398,12 @@ struct batadv_frag_packet { * @orig: originator of the broadcast packet */ struct batadv_bcast_packet { - uint8_t packet_type; - uint8_t version; /* batman version field */ - uint8_t ttl; - uint8_t reserved; - __be32 seqno; - uint8_t orig[ETH_ALEN]; + u8 packet_type; + u8 version; /* batman version field */ + u8 ttl; + u8 reserved; + __be32 seqno; + u8 orig[ETH_ALEN]; /* "4 bytes boundary + 2 bytes" long to make the payload after the * following ethernet header again 4 bytes boundary aligned */ @@ -428,21 +428,21 @@ struct batadv_bcast_packet { * @coded_len: length of network coded part of the payload */ struct batadv_coded_packet { - uint8_t packet_type; - uint8_t version; /* batman version field */ - uint8_t ttl; - uint8_t first_ttvn; - /* uint8_t first_dest[ETH_ALEN]; - saved in mac header destination */ - uint8_t first_source[ETH_ALEN]; - uint8_t first_orig_dest[ETH_ALEN]; - __be32 first_crc; - uint8_t second_ttl; - uint8_t second_ttvn; - uint8_t second_dest[ETH_ALEN]; - uint8_t second_source[ETH_ALEN]; - uint8_t second_orig_dest[ETH_ALEN]; - __be32 second_crc; - __be16 coded_len; + u8 packet_type; + u8 version; /* batman version field */ + u8 ttl; + u8 first_ttvn; + /* u8 first_dest[ETH_ALEN]; - saved in mac header destination */ + u8 first_source[ETH_ALEN]; + u8 first_orig_dest[ETH_ALEN]; + __be32 first_crc; + u8 second_ttl; + u8 second_ttvn; + u8 second_dest[ETH_ALEN]; + u8 second_source[ETH_ALEN]; + u8 second_orig_dest[ETH_ALEN]; + __be32 second_crc; + __be16 coded_len; }; #pragma pack() @@ -459,14 +459,14 @@ struct batadv_coded_packet { * @align: 2 bytes to align the header to a 4 byte boundary */ struct batadv_unicast_tvlv_packet { - uint8_t packet_type; - uint8_t version; /* batman version field */ - uint8_t ttl; - uint8_t reserved; - uint8_t dst[ETH_ALEN]; - uint8_t src[ETH_ALEN]; - __be16 tvlv_len; - uint16_t align; + u8 packet_type; + u8 version; /* batman version field */ + u8 ttl; + u8 reserved; + u8 dst[ETH_ALEN]; + u8 src[ETH_ALEN]; + __be16 tvlv_len; + u16 align; }; /** @@ -476,9 +476,9 @@ struct batadv_unicast_tvlv_packet { * @len: tvlv container length */ struct batadv_tvlv_hdr { - uint8_t type; - uint8_t version; - __be16 len; + u8 type; + u8 version; + __be16 len; }; /** @@ -500,9 +500,9 @@ struct batadv_tvlv_gateway_data { * one batadv_tvlv_tt_vlan_data object per announced vlan */ struct batadv_tvlv_tt_data { - uint8_t flags; - uint8_t ttvn; - __be16 num_vlan; + u8 flags; + u8 ttvn; + __be16 num_vlan; }; /** @@ -513,9 +513,9 @@ struct batadv_tvlv_tt_data { * @reserved: unused, useful for alignment purposes */ struct batadv_tvlv_tt_vlan_data { - __be32 crc; - __be16 vid; - uint16_t reserved; + __be32 crc; + __be16 vid; + u16 reserved; }; /** @@ -527,9 +527,9 @@ struct batadv_tvlv_tt_vlan_data { * @vid: VLAN identifier */ struct batadv_tvlv_tt_change { - uint8_t flags; - uint8_t reserved[3]; - uint8_t addr[ETH_ALEN]; + u8 flags; + u8 reserved[3]; + u8 addr[ETH_ALEN]; __be16 vid; }; @@ -539,7 +539,7 @@ struct batadv_tvlv_tt_change { * @vid: VLAN identifier */ struct batadv_tvlv_roam_adv { - uint8_t client[ETH_ALEN]; + u8 client[ETH_ALEN]; __be16 vid; }; @@ -549,8 +549,8 @@ struct batadv_tvlv_roam_adv { * @reserved: reserved field */ struct batadv_tvlv_mcast_data { - uint8_t flags; - uint8_t reserved[3]; + u8 flags; + u8 reserved[3]; }; #endif /* _NET_BATMAN_ADV_PACKET_H_ */ diff --git a/net/batman-adv/routing.c b/net/batman-adv/routing.c index c360c0cd19c2..8d990b070a2e 100644 --- a/net/batman-adv/routing.c +++ b/net/batman-adv/routing.c @@ -145,7 +145,7 @@ out: * 0 if the packet is to be accepted * 1 if the packet is to be ignored. */ -int batadv_window_protected(struct batadv_priv *bat_priv, int32_t seq_num_diff, +int batadv_window_protected(struct batadv_priv *bat_priv, s32 seq_num_diff, unsigned long *last_reset) { if (seq_num_diff <= -BATADV_TQ_LOCAL_WINDOW_SIZE || @@ -653,19 +653,19 @@ out: static bool batadv_reroute_unicast_packet(struct batadv_priv *bat_priv, struct batadv_unicast_packet *unicast_packet, - uint8_t *dst_addr, unsigned short vid) + u8 *dst_addr, unsigned short vid) { struct batadv_orig_node *orig_node = NULL; struct batadv_hard_iface *primary_if = NULL; bool ret = false; - uint8_t *orig_addr, orig_ttvn; + u8 *orig_addr, orig_ttvn; if (batadv_is_my_client(bat_priv, dst_addr, vid)) { primary_if = batadv_primary_if_get_selected(bat_priv); if (!primary_if) goto out; orig_addr = primary_if->net_dev->dev_addr; - orig_ttvn = (uint8_t)atomic_read(&bat_priv->tt.vn); + orig_ttvn = (u8)atomic_read(&bat_priv->tt.vn); } else { orig_node = batadv_transtable_search(bat_priv, NULL, dst_addr, vid); @@ -676,7 +676,7 @@ batadv_reroute_unicast_packet(struct batadv_priv *bat_priv, goto out; orig_addr = orig_node->orig; - orig_ttvn = (uint8_t)atomic_read(&orig_node->last_ttvn); + orig_ttvn = (u8)atomic_read(&orig_node->last_ttvn); } /* update the packet header */ @@ -698,7 +698,7 @@ static int batadv_check_unicast_ttvn(struct batadv_priv *bat_priv, struct batadv_unicast_packet *unicast_packet; struct batadv_hard_iface *primary_if; struct batadv_orig_node *orig_node; - uint8_t curr_ttvn, old_ttvn; + u8 curr_ttvn, old_ttvn; struct ethhdr *ethhdr; unsigned short vid; int is_old_ttvn; @@ -740,7 +740,7 @@ static int batadv_check_unicast_ttvn(struct batadv_priv *bat_priv, * value is used later to check if the node which sent (or re-routed * last time) the packet had an updated information or not */ - curr_ttvn = (uint8_t)atomic_read(&bat_priv->tt.vn); + curr_ttvn = (u8)atomic_read(&bat_priv->tt.vn); if (!batadv_is_my_mac(bat_priv, unicast_packet->dest)) { orig_node = batadv_orig_hash_find(bat_priv, unicast_packet->dest); @@ -751,7 +751,7 @@ static int batadv_check_unicast_ttvn(struct batadv_priv *bat_priv, if (!orig_node) return 0; - curr_ttvn = (uint8_t)atomic_read(&orig_node->last_ttvn); + curr_ttvn = (u8)atomic_read(&orig_node->last_ttvn); batadv_orig_node_free_ref(orig_node); } @@ -833,7 +833,7 @@ int batadv_recv_unicast_packet(struct sk_buff *skb, struct batadv_priv *bat_priv = netdev_priv(recv_if->soft_iface); struct batadv_unicast_packet *unicast_packet; struct batadv_unicast_4addr_packet *unicast_4addr_packet; - uint8_t *orig_addr; + u8 *orig_addr; struct batadv_orig_node *orig_node = NULL; int check, hdr_size = sizeof(*unicast_packet); bool is4addr; @@ -904,7 +904,7 @@ int batadv_recv_unicast_tvlv(struct sk_buff *skb, struct batadv_priv *bat_priv = netdev_priv(recv_if->soft_iface); struct batadv_unicast_tvlv_packet *unicast_tvlv_packet; unsigned char *tvlv_buff; - uint16_t tvlv_buff_len; + u16 tvlv_buff_len; int hdr_size = sizeof(*unicast_tvlv_packet); int ret = NET_RX_DROP; @@ -1007,8 +1007,8 @@ int batadv_recv_bcast_packet(struct sk_buff *skb, struct ethhdr *ethhdr; int hdr_size = sizeof(*bcast_packet); int ret = NET_RX_DROP; - int32_t seq_diff; - uint32_t seqno; + s32 seq_diff; + u32 seqno; /* drop packet if it has not necessary minimum size */ if (unlikely(!pskb_may_pull(skb, hdr_size))) diff --git a/net/batman-adv/routing.h b/net/batman-adv/routing.h index 6bc29d33abc1..204bbe4952a6 100644 --- a/net/batman-adv/routing.h +++ b/net/batman-adv/routing.h @@ -22,10 +22,6 @@ #include <linux/types.h> -struct batadv_hard_iface; -struct batadv_neigh_node; -struct batadv_orig_node; -struct batadv_priv; struct sk_buff; bool batadv_check_management_packet(struct sk_buff *skb, @@ -55,7 +51,7 @@ struct batadv_neigh_node * batadv_find_router(struct batadv_priv *bat_priv, struct batadv_orig_node *orig_node, struct batadv_hard_iface *recv_if); -int batadv_window_protected(struct batadv_priv *bat_priv, int32_t seq_num_diff, +int batadv_window_protected(struct batadv_priv *bat_priv, s32 seq_num_diff, unsigned long *last_reset); #endif /* _NET_BATMAN_ADV_ROUTING_H_ */ diff --git a/net/batman-adv/send.c b/net/batman-adv/send.c index 0a01992e65ab..f664324805eb 100644 --- a/net/batman-adv/send.c +++ b/net/batman-adv/send.c @@ -54,7 +54,7 @@ static void batadv_send_outstanding_bcast_packet(struct work_struct *work); */ int batadv_send_skb_packet(struct sk_buff *skb, struct batadv_hard_iface *hard_iface, - const uint8_t *dst_addr) + const u8 *dst_addr) { struct batadv_priv *bat_priv = netdev_priv(hard_iface->soft_iface); struct ethhdr *ethhdr; @@ -172,7 +172,7 @@ batadv_send_skb_push_fill_unicast(struct sk_buff *skb, int hdr_size, struct batadv_orig_node *orig_node) { struct batadv_unicast_packet *unicast_packet; - uint8_t ttvn = (uint8_t)atomic_read(&orig_node->last_ttvn); + u8 ttvn = (u8)atomic_read(&orig_node->last_ttvn); if (batadv_skb_head_push(skb, hdr_size) < 0) return false; @@ -343,12 +343,12 @@ out: */ int batadv_send_skb_via_tt_generic(struct batadv_priv *bat_priv, struct sk_buff *skb, int packet_type, - int packet_subtype, uint8_t *dst_hint, + int packet_subtype, u8 *dst_hint, unsigned short vid) { struct ethhdr *ethhdr = (struct ethhdr *)skb->data; struct batadv_orig_node *orig_node; - uint8_t *src, *dst; + u8 *src, *dst; src = ethhdr->h_source; dst = ethhdr->h_dest; @@ -616,7 +616,8 @@ batadv_purge_outstanding_packets(struct batadv_priv *bat_priv, * we delete only packets belonging to the given interface */ if ((hard_iface) && - (forw_packet->if_incoming != hard_iface)) + (forw_packet->if_incoming != hard_iface) && + (forw_packet->if_outgoing != hard_iface)) continue; spin_unlock_bh(&bat_priv->forw_bcast_list_lock); diff --git a/net/batman-adv/send.h b/net/batman-adv/send.h index 0536835fe503..82059f259e46 100644 --- a/net/batman-adv/send.h +++ b/net/batman-adv/send.h @@ -25,15 +25,12 @@ #include "packet.h" -struct batadv_hard_iface; -struct batadv_orig_node; -struct batadv_priv; struct sk_buff; struct work_struct; int batadv_send_skb_packet(struct sk_buff *skb, struct batadv_hard_iface *hard_iface, - const uint8_t *dst_addr); + const u8 *dst_addr); int batadv_send_skb_to_orig(struct sk_buff *skb, struct batadv_orig_node *orig_node, struct batadv_hard_iface *recv_if); @@ -56,7 +53,7 @@ int batadv_send_skb_unicast(struct batadv_priv *bat_priv, unsigned short vid); int batadv_send_skb_via_tt_generic(struct batadv_priv *bat_priv, struct sk_buff *skb, int packet_type, - int packet_subtype, uint8_t *dst_hint, + int packet_subtype, u8 *dst_hint, unsigned short vid); int batadv_send_skb_via_gw(struct batadv_priv *bat_priv, struct sk_buff *skb, unsigned short vid); @@ -75,7 +72,7 @@ int batadv_send_skb_via_gw(struct batadv_priv *bat_priv, struct sk_buff *skb, * Returns NET_XMIT_DROP in case of error or NET_XMIT_SUCCESS otherwise. */ static inline int batadv_send_skb_via_tt(struct batadv_priv *bat_priv, - struct sk_buff *skb, uint8_t *dst_hint, + struct sk_buff *skb, u8 *dst_hint, unsigned short vid) { return batadv_send_skb_via_tt_generic(bat_priv, skb, BATADV_UNICAST, 0, @@ -100,7 +97,7 @@ static inline int batadv_send_skb_via_tt(struct batadv_priv *bat_priv, static inline int batadv_send_skb_via_tt_4addr(struct batadv_priv *bat_priv, struct sk_buff *skb, int packet_subtype, - uint8_t *dst_hint, + u8 *dst_hint, unsigned short vid) { return batadv_send_skb_via_tt_generic(bat_priv, skb, diff --git a/net/batman-adv/soft-interface.c b/net/batman-adv/soft-interface.c index a2fc843c2243..ac4d08de5df4 100644 --- a/net/batman-adv/soft-interface.c +++ b/net/batman-adv/soft-interface.c @@ -131,7 +131,7 @@ static int batadv_interface_set_mac_addr(struct net_device *dev, void *p) struct batadv_priv *bat_priv = netdev_priv(dev); struct batadv_softif_vlan *vlan; struct sockaddr *addr = p; - uint8_t old_addr[ETH_ALEN]; + u8 old_addr[ETH_ALEN]; if (!is_valid_ether_addr(addr->sa_data)) return -EADDRNOTAVAIL; @@ -186,22 +186,23 @@ static int batadv_interface_tx(struct sk_buff *skb, struct batadv_hard_iface *primary_if = NULL; struct batadv_bcast_packet *bcast_packet; __be16 ethertype = htons(ETH_P_BATMAN); - static const uint8_t stp_addr[ETH_ALEN] = {0x01, 0x80, 0xC2, 0x00, - 0x00, 0x00}; - static const uint8_t ectp_addr[ETH_ALEN] = {0xCF, 0x00, 0x00, 0x00, - 0x00, 0x00}; + static const u8 stp_addr[ETH_ALEN] = {0x01, 0x80, 0xC2, 0x00, + 0x00, 0x00}; + static const u8 ectp_addr[ETH_ALEN] = {0xCF, 0x00, 0x00, 0x00, + 0x00, 0x00}; enum batadv_dhcp_recipient dhcp_rcp = BATADV_DHCP_NO; - uint8_t *dst_hint = NULL, chaddr[ETH_ALEN]; + u8 *dst_hint = NULL, chaddr[ETH_ALEN]; struct vlan_ethhdr *vhdr; unsigned int header_len = 0; int data_len = skb->len, ret; unsigned long brd_delay = 1; bool do_bcast = false, client_added; unsigned short vid; - uint32_t seqno; + u32 seqno; int gw_mode; enum batadv_forw_mode forw_mode; struct batadv_orig_node *mcast_single_orig = NULL; + int network_offset = ETH_HLEN; if (atomic_read(&bat_priv->mesh_state) != BATADV_MESH_ACTIVE) goto dropped; @@ -214,14 +215,18 @@ static int batadv_interface_tx(struct sk_buff *skb, case ETH_P_8021Q: vhdr = vlan_eth_hdr(skb); - if (vhdr->h_vlan_encapsulated_proto != ethertype) + if (vhdr->h_vlan_encapsulated_proto != ethertype) { + network_offset += VLAN_HLEN; break; + } /* fall through */ case ETH_P_BATMAN: goto dropped; } + skb_set_network_header(skb, network_offset); + if (batadv_bla_tx(bat_priv, skb, vid)) goto dropped; @@ -745,9 +750,9 @@ static void batadv_softif_destroy_finish(struct work_struct *work) static int batadv_softif_init_late(struct net_device *dev) { struct batadv_priv *bat_priv; - uint32_t random_seqno; + u32 random_seqno; int ret; - size_t cnt_len = sizeof(uint64_t) * BATADV_CNT_NUM; + size_t cnt_len = sizeof(u64) * BATADV_CNT_NUM; batadv_set_lockdep_class(dev); @@ -758,7 +763,7 @@ static int batadv_softif_init_late(struct net_device *dev) /* batadv_interface_stats() needs to be available as soon as * register_netdevice() has been called */ - bat_priv->bat_counters = __alloc_percpu(cnt_len, __alignof__(uint64_t)); + bat_priv->bat_counters = __alloc_percpu(cnt_len, __alignof__(u64)); if (!bat_priv->bat_counters) return -ENOMEM; @@ -936,14 +941,12 @@ static void batadv_softif_init_early(struct net_device *dev) dev->netdev_ops = &batadv_netdev_ops; dev->destructor = batadv_softif_free; dev->features |= NETIF_F_HW_VLAN_CTAG_FILTER; - dev->tx_queue_len = 0; + dev->priv_flags |= IFF_NO_QUEUE; /* can't call min_mtu, because the needed variables * have not been initialized yet */ dev->mtu = ETH_DATA_LEN; - /* reserve more space in the skbuff for our header */ - dev->hard_header_len = batadv_max_header_len(); /* generate random address */ eth_hw_addr_random(dev); @@ -1112,8 +1115,7 @@ static const struct { #endif }; -static void batadv_get_strings(struct net_device *dev, uint32_t stringset, - uint8_t *data) +static void batadv_get_strings(struct net_device *dev, u32 stringset, u8 *data) { if (stringset == ETH_SS_STATS) memcpy(data, batadv_counters_strings, @@ -1121,8 +1123,7 @@ static void batadv_get_strings(struct net_device *dev, uint32_t stringset, } static void batadv_get_ethtool_stats(struct net_device *dev, - struct ethtool_stats *stats, - uint64_t *data) + struct ethtool_stats *stats, u64 *data) { struct batadv_priv *bat_priv = netdev_priv(dev); int i; diff --git a/net/batman-adv/soft-interface.h b/net/batman-adv/soft-interface.h index 578e8a663c30..8e82176f40b1 100644 --- a/net/batman-adv/soft-interface.h +++ b/net/batman-adv/soft-interface.h @@ -22,10 +22,6 @@ #include <net/rtnetlink.h> -struct batadv_hard_iface; -struct batadv_orig_node; -struct batadv_priv; -struct batadv_softif_vlan; struct net_device; struct sk_buff; diff --git a/net/batman-adv/sysfs.c b/net/batman-adv/sysfs.c index d6a312a82c03..9de3c8804ff4 100644 --- a/net/batman-adv/sysfs.c +++ b/net/batman-adv/sysfs.c @@ -457,7 +457,7 @@ static ssize_t batadv_show_gw_bwidth(struct kobject *kobj, struct attribute *attr, char *buff) { struct batadv_priv *bat_priv = batadv_kobj_to_batpriv(kobj); - uint32_t down, up; + u32 down, up; down = atomic_read(&bat_priv->gw.bandwidth_down); up = atomic_read(&bat_priv->gw.bandwidth_up); @@ -512,7 +512,7 @@ static ssize_t batadv_store_isolation_mark(struct kobject *kobj, { struct net_device *net_dev = batadv_kobj_to_netdev(kobj); struct batadv_priv *bat_priv = netdev_priv(net_dev); - uint32_t mark, mask; + u32 mark, mask; char *mask_ptr; /* parse the mask if it has been specified, otherwise assume the mask is diff --git a/net/batman-adv/sysfs.h b/net/batman-adv/sysfs.h index 2294583f7cf9..61974428a7af 100644 --- a/net/batman-adv/sysfs.h +++ b/net/batman-adv/sysfs.h @@ -23,8 +23,6 @@ #include <linux/sysfs.h> #include <linux/types.h> -struct batadv_priv; -struct batadv_softif_vlan; struct kobject; struct net_device; diff --git a/net/batman-adv/translation-table.c b/net/batman-adv/translation-table.c index 5809b39c1922..4228b10c47ea 100644 --- a/net/batman-adv/translation-table.c +++ b/net/batman-adv/translation-table.c @@ -19,6 +19,7 @@ #include "main.h" #include <linux/atomic.h> +#include <linux/bitops.h> #include <linux/bug.h> #include <linux/byteorder/generic.h> #include <linux/compiler.h> @@ -55,7 +56,7 @@ static struct lock_class_key batadv_tt_local_hash_lock_class_key; static struct lock_class_key batadv_tt_global_hash_lock_class_key; -static void batadv_send_roam_adv(struct batadv_priv *bat_priv, uint8_t *client, +static void batadv_send_roam_adv(struct batadv_priv *bat_priv, u8 *client, unsigned short vid, struct batadv_orig_node *orig_node); static void batadv_tt_purge(struct work_struct *work); @@ -84,10 +85,10 @@ static int batadv_compare_tt(const struct hlist_node *node, const void *data2) * Returns the hash index where the object represented by 'data' should be * stored at. */ -static inline uint32_t batadv_choose_tt(const void *data, uint32_t size) +static inline u32 batadv_choose_tt(const void *data, u32 size) { struct batadv_tt_common_entry *tt; - uint32_t hash = 0; + u32 hash = 0; tt = (struct batadv_tt_common_entry *)data; hash = jhash(&tt->addr, ETH_ALEN, hash); @@ -106,12 +107,12 @@ static inline uint32_t batadv_choose_tt(const void *data, uint32_t size) * found, NULL otherwise. */ static struct batadv_tt_common_entry * -batadv_tt_hash_find(struct batadv_hashtable *hash, const uint8_t *addr, +batadv_tt_hash_find(struct batadv_hashtable *hash, const u8 *addr, unsigned short vid) { struct hlist_head *head; struct batadv_tt_common_entry to_search, *tt, *tt_tmp = NULL; - uint32_t index; + u32 index; if (!hash) return NULL; @@ -151,7 +152,7 @@ batadv_tt_hash_find(struct batadv_hashtable *hash, const uint8_t *addr, * found, NULL otherwise. */ static struct batadv_tt_local_entry * -batadv_tt_local_hash_find(struct batadv_priv *bat_priv, const uint8_t *addr, +batadv_tt_local_hash_find(struct batadv_priv *bat_priv, const u8 *addr, unsigned short vid) { struct batadv_tt_common_entry *tt_common_entry; @@ -176,7 +177,7 @@ batadv_tt_local_hash_find(struct batadv_priv *bat_priv, const uint8_t *addr, * is found, NULL otherwise. */ static struct batadv_tt_global_entry * -batadv_tt_global_hash_find(struct batadv_priv *bat_priv, const uint8_t *addr, +batadv_tt_global_hash_find(struct batadv_priv *bat_priv, const u8 *addr, unsigned short vid) { struct batadv_tt_common_entry *tt_common_entry; @@ -222,7 +223,7 @@ batadv_tt_global_entry_free_ref(struct batadv_tt_global_entry *tt_global_entry) * (excluding ourself). */ int batadv_tt_global_hash_count(struct batadv_priv *bat_priv, - const uint8_t *addr, unsigned short vid) + const u8 *addr, unsigned short vid) { struct batadv_tt_global_entry *tt_global_entry; int count; @@ -314,7 +315,7 @@ static void batadv_tt_global_size_mod(struct batadv_orig_node *orig_node, if (atomic_add_return(v, &vlan->tt.num_entries) == 0) { spin_lock_bh(&orig_node->vlan_list_lock); - list_del_rcu(&vlan->list); + hlist_del_init_rcu(&vlan->list); spin_unlock_bh(&orig_node->vlan_list_lock); batadv_orig_node_vlan_free_ref(vlan); } @@ -363,11 +364,11 @@ batadv_tt_orig_list_entry_free_ref(struct batadv_tt_orig_list_entry *orig_entry) */ static void batadv_tt_local_event(struct batadv_priv *bat_priv, struct batadv_tt_local_entry *tt_local_entry, - uint8_t event_flags) + u8 event_flags) { struct batadv_tt_change_node *tt_change_node, *entry, *safe; struct batadv_tt_common_entry *common = &tt_local_entry->common; - uint8_t flags = common->flags | event_flags; + u8 flags = common->flags | event_flags; bool event_removed = false; bool del_op_requested, del_op_entry; @@ -447,7 +448,7 @@ static int batadv_tt_len(int changes_num) * * Returns the number of entries. */ -static uint16_t batadv_tt_entries(uint16_t tt_len) +static u16 batadv_tt_entries(u16 tt_len) { return tt_len / batadv_tt_len(1); } @@ -461,7 +462,8 @@ static uint16_t batadv_tt_entries(uint16_t tt_len) */ static int batadv_tt_local_table_transmit_size(struct batadv_priv *bat_priv) { - uint16_t num_vlan = 0, tt_local_entries = 0; + u16 num_vlan = 0; + u16 tt_local_entries = 0; struct batadv_softif_vlan *vlan; int hdr_size; @@ -524,8 +526,8 @@ static void batadv_tt_global_free(struct batadv_priv *bat_priv, * * Returns true if the client was successfully added, false otherwise. */ -bool batadv_tt_local_add(struct net_device *soft_iface, const uint8_t *addr, - unsigned short vid, int ifindex, uint32_t mark) +bool batadv_tt_local_add(struct net_device *soft_iface, const u8 *addr, + unsigned short vid, int ifindex, u32 mark) { struct batadv_priv *bat_priv = netdev_priv(soft_iface); struct batadv_tt_local_entry *tt_local; @@ -535,9 +537,10 @@ bool batadv_tt_local_add(struct net_device *soft_iface, const uint8_t *addr, struct hlist_head *head; struct batadv_tt_orig_list_entry *orig_entry; int hash_added, table_size, packet_size_max; - bool ret = false, roamed_back = false; - uint8_t remote_flags; - uint32_t match_mark; + bool ret = false; + bool roamed_back = false; + u8 remote_flags; + u32 match_mark; if (ifindex != BATADV_NULL_IFINDEX) in_dev = dev_get_by_index(&init_net, ifindex); @@ -604,7 +607,7 @@ bool batadv_tt_local_add(struct net_device *soft_iface, const uint8_t *addr, batadv_dbg(BATADV_DBG_TT, bat_priv, "Creating new local tt entry: %pM (vid: %d, ttvn: %d)\n", addr, BATADV_PRINT_VID(vid), - (uint8_t)atomic_read(&bat_priv->tt.vn)); + (u8)atomic_read(&bat_priv->tt.vn)); ether_addr_copy(tt_local->common.addr, addr); /* The local entry has to be marked as NEW to avoid to send it in @@ -723,19 +726,22 @@ out: * * Return the size of the allocated buffer or 0 in case of failure. */ -static uint16_t +static u16 batadv_tt_prepare_tvlv_global_data(struct batadv_orig_node *orig_node, struct batadv_tvlv_tt_data **tt_data, struct batadv_tvlv_tt_change **tt_change, - int32_t *tt_len) + s32 *tt_len) { - uint16_t num_vlan = 0, num_entries = 0, change_offset, tvlv_len; + u16 num_vlan = 0; + u16 num_entries = 0; + u16 change_offset; + u16 tvlv_len; struct batadv_tvlv_tt_vlan_data *tt_vlan; struct batadv_orig_node_vlan *vlan; - uint8_t *tt_change_ptr; + u8 *tt_change_ptr; rcu_read_lock(); - list_for_each_entry_rcu(vlan, &orig_node->vlan_list, list) { + hlist_for_each_entry_rcu(vlan, &orig_node->vlan_list, list) { num_vlan++; num_entries += atomic_read(&vlan->tt.num_entries); } @@ -761,14 +767,14 @@ batadv_tt_prepare_tvlv_global_data(struct batadv_orig_node *orig_node, (*tt_data)->num_vlan = htons(num_vlan); tt_vlan = (struct batadv_tvlv_tt_vlan_data *)(*tt_data + 1); - list_for_each_entry_rcu(vlan, &orig_node->vlan_list, list) { + hlist_for_each_entry_rcu(vlan, &orig_node->vlan_list, list) { tt_vlan->vid = htons(vlan->vid); tt_vlan->crc = htonl(vlan->tt.crc); tt_vlan++; } - tt_change_ptr = (uint8_t *)*tt_data + change_offset; + tt_change_ptr = (u8 *)*tt_data + change_offset; *tt_change = (struct batadv_tvlv_tt_change *)tt_change_ptr; out: @@ -794,16 +800,18 @@ out: * * Return the size of the allocated buffer or 0 in case of failure. */ -static uint16_t +static u16 batadv_tt_prepare_tvlv_local_data(struct batadv_priv *bat_priv, struct batadv_tvlv_tt_data **tt_data, struct batadv_tvlv_tt_change **tt_change, - int32_t *tt_len) + s32 *tt_len) { struct batadv_tvlv_tt_vlan_data *tt_vlan; struct batadv_softif_vlan *vlan; - uint16_t num_vlan = 0, num_entries = 0, tvlv_len; - uint8_t *tt_change_ptr; + u16 num_vlan = 0; + u16 num_entries = 0; + u16 tvlv_len; + u8 *tt_change_ptr; int change_offset; rcu_read_lock(); @@ -840,7 +848,7 @@ batadv_tt_prepare_tvlv_local_data(struct batadv_priv *bat_priv, tt_vlan++; } - tt_change_ptr = (uint8_t *)*tt_data + change_offset; + tt_change_ptr = (u8 *)*tt_data + change_offset; *tt_change = (struct batadv_tvlv_tt_change *)tt_change_ptr; out: @@ -859,8 +867,9 @@ static void batadv_tt_tvlv_container_update(struct batadv_priv *bat_priv) struct batadv_tvlv_tt_data *tt_data; struct batadv_tvlv_tt_change *tt_change; int tt_diff_len, tt_change_len = 0; - int tt_diff_entries_num = 0, tt_diff_entries_count = 0; - uint16_t tvlv_len; + int tt_diff_entries_num = 0; + int tt_diff_entries_count = 0; + u16 tvlv_len; tt_diff_entries_num = atomic_read(&bat_priv->tt.local_changes); tt_diff_len = batadv_tt_len(tt_diff_entries_num); @@ -934,12 +943,12 @@ int batadv_tt_local_seq_print_text(struct seq_file *seq, void *offset) struct batadv_softif_vlan *vlan; struct hlist_head *head; unsigned short vid; - uint32_t i; + u32 i; int last_seen_secs; int last_seen_msecs; unsigned long last_seen_jiffies; bool no_purge; - uint16_t np_flag = BATADV_TT_CLIENT_NOPURGE; + u16 np_flag = BATADV_TT_CLIENT_NOPURGE; primary_if = batadv_seq_print_text_primary_if_get(seq); if (!primary_if) @@ -947,7 +956,7 @@ int batadv_tt_local_seq_print_text(struct seq_file *seq, void *offset) seq_printf(seq, "Locally retrieved addresses (from %s) announced via TT (TTVN: %u):\n", - net_dev->name, (uint8_t)atomic_read(&bat_priv->tt.vn)); + net_dev->name, (u8)atomic_read(&bat_priv->tt.vn)); seq_printf(seq, " %-13s %s %-8s %-9s (%-10s)\n", "Client", "VID", "Flags", "Last seen", "CRC"); @@ -1007,7 +1016,7 @@ out: static void batadv_tt_local_set_pending(struct batadv_priv *bat_priv, struct batadv_tt_local_entry *tt_local_entry, - uint16_t flags, const char *message) + u16 flags, const char *message) { batadv_tt_local_event(bat_priv, tt_local_entry, flags); @@ -1033,12 +1042,12 @@ batadv_tt_local_set_pending(struct batadv_priv *bat_priv, * * Returns the flags assigned to the local entry before being deleted */ -uint16_t batadv_tt_local_remove(struct batadv_priv *bat_priv, - const uint8_t *addr, unsigned short vid, - const char *message, bool roaming) +u16 batadv_tt_local_remove(struct batadv_priv *bat_priv, const u8 *addr, + unsigned short vid, const char *message, + bool roaming) { struct batadv_tt_local_entry *tt_local_entry; - uint16_t flags, curr_flags = BATADV_NO_FLAGS; + u16 flags, curr_flags = BATADV_NO_FLAGS; struct batadv_softif_vlan *vlan; void *tt_entry_exists; @@ -1141,7 +1150,7 @@ static void batadv_tt_local_purge(struct batadv_priv *bat_priv, struct batadv_hashtable *hash = bat_priv->tt.local_hash; struct hlist_head *head; spinlock_t *list_lock; /* protects write access to the hash lists */ - uint32_t i; + u32 i; for (i = 0; i < hash->size; i++) { head = &hash->table[i]; @@ -1162,7 +1171,7 @@ static void batadv_tt_local_table_free(struct batadv_priv *bat_priv) struct batadv_softif_vlan *vlan; struct hlist_node *node_tmp; struct hlist_head *head; - uint32_t i; + u32 i; if (!bat_priv->tt.local_hash) return; @@ -1337,15 +1346,14 @@ out: static bool batadv_tt_global_add(struct batadv_priv *bat_priv, struct batadv_orig_node *orig_node, const unsigned char *tt_addr, - unsigned short vid, uint16_t flags, - uint8_t ttvn) + unsigned short vid, u16 flags, u8 ttvn) { struct batadv_tt_global_entry *tt_global_entry; struct batadv_tt_local_entry *tt_local_entry; bool ret = false; int hash_added; struct batadv_tt_common_entry *common; - uint16_t local_flags; + u16 local_flags; /* ignore global entries from backbone nodes */ if (batadv_bla_is_backbone_gw_orig(bat_priv, orig_node->orig, vid)) @@ -1542,8 +1550,8 @@ batadv_tt_global_print_entry(struct batadv_priv *bat_priv, struct batadv_tt_common_entry *tt_common_entry; struct batadv_orig_node_vlan *vlan; struct hlist_head *head; - uint8_t last_ttvn; - uint16_t flags; + u8 last_ttvn; + u16 flags; tt_common_entry = &tt_global_entry->common; flags = tt_common_entry->flags; @@ -1617,7 +1625,7 @@ int batadv_tt_global_seq_print_text(struct seq_file *seq, void *offset) struct batadv_tt_global_entry *tt_global; struct batadv_hard_iface *primary_if; struct hlist_head *head; - uint32_t i; + u32 i; primary_if = batadv_seq_print_text_primary_if_get(seq); if (!primary_if) @@ -1650,20 +1658,28 @@ out: } /** - * batadv_tt_global_del_orig_entry - remove and free an orig_entry + * _batadv_tt_global_del_orig_entry - remove and free an orig_entry * @tt_global_entry: the global entry to remove the orig_entry from * @orig_entry: the orig entry to remove and free * * Remove an orig_entry from its list in the given tt_global_entry and * free this orig_entry afterwards. + * + * Caller must hold tt_global_entry->list_lock and ensure orig_entry->list is + * part of a list. */ static void -batadv_tt_global_del_orig_entry(struct batadv_tt_global_entry *tt_global_entry, - struct batadv_tt_orig_list_entry *orig_entry) +_batadv_tt_global_del_orig_entry(struct batadv_tt_global_entry *tt_global_entry, + struct batadv_tt_orig_list_entry *orig_entry) { + lockdep_assert_held(&tt_global_entry->list_lock); + batadv_tt_global_size_dec(orig_entry->orig_node, tt_global_entry->common.vid); atomic_dec(&tt_global_entry->orig_list_count); + /* requires holding tt_global_entry->list_lock and orig_entry->list + * being part of a list + */ hlist_del_rcu(&orig_entry->list); batadv_tt_orig_list_entry_free_ref(orig_entry); } @@ -1679,7 +1695,7 @@ batadv_tt_global_del_orig_list(struct batadv_tt_global_entry *tt_global_entry) spin_lock_bh(&tt_global_entry->list_lock); head = &tt_global_entry->orig_list; hlist_for_each_entry_safe(orig_entry, safe, head, list) - batadv_tt_global_del_orig_entry(tt_global_entry, orig_entry); + _batadv_tt_global_del_orig_entry(tt_global_entry, orig_entry); spin_unlock_bh(&tt_global_entry->list_lock); } @@ -1714,8 +1730,8 @@ batadv_tt_global_del_orig_node(struct batadv_priv *bat_priv, orig_node->orig, tt_global_entry->common.addr, BATADV_PRINT_VID(vid), message); - batadv_tt_global_del_orig_entry(tt_global_entry, - orig_entry); + _batadv_tt_global_del_orig_entry(tt_global_entry, + orig_entry); } } spin_unlock_bh(&tt_global_entry->list_lock); @@ -1837,12 +1853,12 @@ out: */ void batadv_tt_global_del_orig(struct batadv_priv *bat_priv, struct batadv_orig_node *orig_node, - int32_t match_vid, + s32 match_vid, const char *message) { struct batadv_tt_global_entry *tt_global; struct batadv_tt_common_entry *tt_common_entry; - uint32_t i; + u32 i; struct batadv_hashtable *hash = bat_priv->tt.global_hash; struct hlist_node *safe; struct hlist_head *head; @@ -1882,7 +1898,7 @@ void batadv_tt_global_del_orig(struct batadv_priv *bat_priv, } spin_unlock_bh(list_lock); } - orig_node->capa_initialized &= ~BATADV_ORIG_CAPA_HAS_TT; + clear_bit(BATADV_ORIG_CAPA_HAS_TT, &orig_node->capa_initialized); } static bool batadv_tt_global_to_purge(struct batadv_tt_global_entry *tt_global, @@ -1913,7 +1929,7 @@ static void batadv_tt_global_purge(struct batadv_priv *bat_priv) struct hlist_head *head; struct hlist_node *node_tmp; spinlock_t *list_lock; /* protects write access to the hash lists */ - uint32_t i; + u32 i; char *msg = NULL; struct batadv_tt_common_entry *tt_common; struct batadv_tt_global_entry *tt_global; @@ -1954,7 +1970,7 @@ static void batadv_tt_global_table_free(struct batadv_priv *bat_priv) struct batadv_tt_global_entry *tt_global; struct hlist_node *node_tmp; struct hlist_head *head; - uint32_t i; + u32 i; if (!bat_priv->tt.global_hash) return; @@ -2015,8 +2031,8 @@ _batadv_is_ap_isolated(struct batadv_tt_local_entry *tt_local_entry, * If the two clients are AP isolated the function returns NULL. */ struct batadv_orig_node *batadv_transtable_search(struct batadv_priv *bat_priv, - const uint8_t *src, - const uint8_t *addr, + const u8 *src, + const u8 *addr, unsigned short vid) { struct batadv_tt_local_entry *tt_local_entry = NULL; @@ -2084,16 +2100,16 @@ out: * * Returns the checksum of the global table of a given originator. */ -static uint32_t batadv_tt_global_crc(struct batadv_priv *bat_priv, - struct batadv_orig_node *orig_node, - unsigned short vid) +static u32 batadv_tt_global_crc(struct batadv_priv *bat_priv, + struct batadv_orig_node *orig_node, + unsigned short vid) { struct batadv_hashtable *hash = bat_priv->tt.global_hash; struct batadv_tt_common_entry *tt_common; struct batadv_tt_global_entry *tt_global; struct hlist_head *head; - uint32_t i, crc_tmp, crc = 0; - uint8_t flags; + u32 i, crc_tmp, crc = 0; + u8 flags; __be16 tmp_vid; for (i = 0; i < hash->size; i++) { @@ -2161,14 +2177,14 @@ static uint32_t batadv_tt_global_crc(struct batadv_priv *bat_priv, * * Returns the checksum of the local table */ -static uint32_t batadv_tt_local_crc(struct batadv_priv *bat_priv, - unsigned short vid) +static u32 batadv_tt_local_crc(struct batadv_priv *bat_priv, + unsigned short vid) { struct batadv_hashtable *hash = bat_priv->tt.local_hash; struct batadv_tt_common_entry *tt_common; struct hlist_head *head; - uint32_t i, crc_tmp, crc = 0; - uint8_t flags; + u32 i, crc_tmp, crc = 0; + u8 flags; __be16 tmp_vid; for (i = 0; i < hash->size; i++) { @@ -2210,12 +2226,13 @@ static uint32_t batadv_tt_local_crc(struct batadv_priv *bat_priv, static void batadv_tt_req_list_free(struct batadv_priv *bat_priv) { - struct batadv_tt_req_node *node, *safe; + struct batadv_tt_req_node *node; + struct hlist_node *safe; spin_lock_bh(&bat_priv->tt.req_list_lock); - list_for_each_entry_safe(node, safe, &bat_priv->tt.req_list, list) { - list_del(&node->list); + hlist_for_each_entry_safe(node, safe, &bat_priv->tt.req_list, list) { + hlist_del_init(&node->list); kfree(node); } @@ -2225,7 +2242,7 @@ static void batadv_tt_req_list_free(struct batadv_priv *bat_priv) static void batadv_tt_save_orig_buffer(struct batadv_priv *bat_priv, struct batadv_orig_node *orig_node, const void *tt_buff, - uint16_t tt_buff_len) + u16 tt_buff_len) { /* Replace the old buffer only if I received something in the * last OGM (the OGM could carry no changes) @@ -2245,30 +2262,36 @@ static void batadv_tt_save_orig_buffer(struct batadv_priv *bat_priv, static void batadv_tt_req_purge(struct batadv_priv *bat_priv) { - struct batadv_tt_req_node *node, *safe; + struct batadv_tt_req_node *node; + struct hlist_node *safe; spin_lock_bh(&bat_priv->tt.req_list_lock); - list_for_each_entry_safe(node, safe, &bat_priv->tt.req_list, list) { + hlist_for_each_entry_safe(node, safe, &bat_priv->tt.req_list, list) { if (batadv_has_timed_out(node->issued_at, BATADV_TT_REQUEST_TIMEOUT)) { - list_del(&node->list); + hlist_del_init(&node->list); kfree(node); } } spin_unlock_bh(&bat_priv->tt.req_list_lock); } -/* returns the pointer to the new tt_req_node struct if no request - * has already been issued for this orig_node, NULL otherwise +/** + * batadv_tt_req_node_new - search and possibly create a tt_req_node object + * @bat_priv: the bat priv with all the soft interface information + * @orig_node: orig node this request is being issued for + * + * Returns the pointer to the new tt_req_node struct if no request + * has already been issued for this orig_node, NULL otherwise. */ static struct batadv_tt_req_node * -batadv_new_tt_req_node(struct batadv_priv *bat_priv, +batadv_tt_req_node_new(struct batadv_priv *bat_priv, struct batadv_orig_node *orig_node) { struct batadv_tt_req_node *tt_req_node_tmp, *tt_req_node = NULL; spin_lock_bh(&bat_priv->tt.req_list_lock); - list_for_each_entry(tt_req_node_tmp, &bat_priv->tt.req_list, list) { + hlist_for_each_entry(tt_req_node_tmp, &bat_priv->tt.req_list, list) { if (batadv_compare_eth(tt_req_node_tmp, orig_node) && !batadv_has_timed_out(tt_req_node_tmp->issued_at, BATADV_TT_REQUEST_TIMEOUT)) @@ -2282,7 +2305,7 @@ batadv_new_tt_req_node(struct batadv_priv *bat_priv, ether_addr_copy(tt_req_node->addr, orig_node->orig); tt_req_node->issued_at = jiffies; - list_add(&tt_req_node->list, &bat_priv->tt.req_list); + hlist_add_head(&tt_req_node->list, &bat_priv->tt.req_list); unlock: spin_unlock_bh(&bat_priv->tt.req_list_lock); return tt_req_node; @@ -2334,15 +2357,15 @@ static int batadv_tt_global_valid(const void *entry_ptr, */ static void batadv_tt_tvlv_generate(struct batadv_priv *bat_priv, struct batadv_hashtable *hash, - void *tvlv_buff, uint16_t tt_len, + void *tvlv_buff, u16 tt_len, int (*valid_cb)(const void *, const void *), void *cb_data) { struct batadv_tt_common_entry *tt_common_entry; struct batadv_tvlv_tt_change *tt_change; struct hlist_head *head; - uint16_t tt_tot, tt_num_entries = 0; - uint32_t i; + u16 tt_tot, tt_num_entries = 0; + u32 i; tt_tot = batadv_tt_entries(tt_len); tt_change = (struct batadv_tvlv_tt_change *)tvlv_buff; @@ -2384,11 +2407,11 @@ static void batadv_tt_tvlv_generate(struct batadv_priv *bat_priv, */ static bool batadv_tt_global_check_crc(struct batadv_orig_node *orig_node, struct batadv_tvlv_tt_vlan_data *tt_vlan, - uint16_t num_vlan) + u16 num_vlan) { struct batadv_tvlv_tt_vlan_data *tt_vlan_tmp; struct batadv_orig_node_vlan *vlan; - uint32_t crc; + u32 crc; int i; /* check if each received CRC matches the locally stored one */ @@ -2443,11 +2466,11 @@ static void batadv_tt_global_update_crc(struct batadv_priv *bat_priv, struct batadv_orig_node *orig_node) { struct batadv_orig_node_vlan *vlan; - uint32_t crc; + u32 crc; /* recompute the global CRC for each VLAN */ rcu_read_lock(); - list_for_each_entry_rcu(vlan, &orig_node->vlan_list, list) { + hlist_for_each_entry_rcu(vlan, &orig_node->vlan_list, list) { /* if orig_node is a backbone node for this VLAN, don't compute * the CRC as we ignore all the global entries over it */ @@ -2473,9 +2496,9 @@ static void batadv_tt_global_update_crc(struct batadv_priv *bat_priv, */ static int batadv_send_tt_request(struct batadv_priv *bat_priv, struct batadv_orig_node *dst_orig_node, - uint8_t ttvn, + u8 ttvn, struct batadv_tvlv_tt_vlan_data *tt_vlan, - uint16_t num_vlan, bool full_table) + u16 num_vlan, bool full_table) { struct batadv_tvlv_tt_data *tvlv_tt_data = NULL; struct batadv_tt_req_node *tt_req_node = NULL; @@ -2491,7 +2514,7 @@ static int batadv_send_tt_request(struct batadv_priv *bat_priv, /* The new tt_req will be issued only if I'm not waiting for a * reply from the same orig_node yet */ - tt_req_node = batadv_new_tt_req_node(bat_priv, dst_orig_node); + tt_req_node = batadv_tt_req_node_new(bat_priv, dst_orig_node); if (!tt_req_node) goto out; @@ -2533,7 +2556,8 @@ out: batadv_hardif_free_ref(primary_if); if (ret && tt_req_node) { spin_lock_bh(&bat_priv->tt.req_list_lock); - list_del(&tt_req_node->list); + /* hlist_del_init() verifies tt_req_node still is in the list */ + hlist_del_init(&tt_req_node->list); spin_unlock_bh(&bat_priv->tt.req_list_lock); kfree(tt_req_node); } @@ -2553,7 +2577,7 @@ out: */ static bool batadv_send_other_tt_response(struct batadv_priv *bat_priv, struct batadv_tvlv_tt_data *tt_data, - uint8_t *req_src, uint8_t *req_dst) + u8 *req_src, u8 *req_dst) { struct batadv_orig_node *req_dst_orig_node; struct batadv_orig_node *res_dst_orig_node = NULL; @@ -2561,9 +2585,9 @@ static bool batadv_send_other_tt_response(struct batadv_priv *bat_priv, struct batadv_tvlv_tt_data *tvlv_tt_data = NULL; struct batadv_tvlv_tt_vlan_data *tt_vlan; bool ret = false, full_table; - uint8_t orig_ttvn, req_ttvn; - uint16_t tvlv_len; - int32_t tt_len; + u8 orig_ttvn, req_ttvn; + u16 tvlv_len; + s32 tt_len; batadv_dbg(BATADV_DBG_TT, bat_priv, "Received TT_REQUEST from %pM for ttvn: %u (%pM) [%c]\n", @@ -2579,7 +2603,7 @@ static bool batadv_send_other_tt_response(struct batadv_priv *bat_priv, if (!res_dst_orig_node) goto out; - orig_ttvn = (uint8_t)atomic_read(&req_dst_orig_node->last_ttvn); + orig_ttvn = (u8)atomic_read(&req_dst_orig_node->last_ttvn); req_ttvn = tt_data->ttvn; tt_vlan = (struct batadv_tvlv_tt_vlan_data *)(tt_data + 1); @@ -2685,16 +2709,16 @@ out: */ static bool batadv_send_my_tt_response(struct batadv_priv *bat_priv, struct batadv_tvlv_tt_data *tt_data, - uint8_t *req_src) + u8 *req_src) { struct batadv_tvlv_tt_data *tvlv_tt_data = NULL; struct batadv_hard_iface *primary_if = NULL; struct batadv_tvlv_tt_change *tt_change; struct batadv_orig_node *orig_node; - uint8_t my_ttvn, req_ttvn; - uint16_t tvlv_len; + u8 my_ttvn, req_ttvn; + u16 tvlv_len; bool full_table; - int32_t tt_len; + s32 tt_len; batadv_dbg(BATADV_DBG_TT, bat_priv, "Received TT_REQUEST from %pM for ttvn: %u (me) [%c]\n", @@ -2703,7 +2727,7 @@ static bool batadv_send_my_tt_response(struct batadv_priv *bat_priv, spin_lock_bh(&bat_priv->tt.commit_lock); - my_ttvn = (uint8_t)atomic_read(&bat_priv->tt.vn); + my_ttvn = (u8)atomic_read(&bat_priv->tt.vn); req_ttvn = tt_data->ttvn; orig_node = batadv_orig_hash_find(bat_priv, req_src); @@ -2742,7 +2766,7 @@ static bool batadv_send_my_tt_response(struct batadv_priv *bat_priv, bat_priv->tt.last_changeset_len); spin_unlock_bh(&bat_priv->tt.last_changeset_lock); } else { - req_ttvn = (uint8_t)atomic_read(&bat_priv->tt.vn); + req_ttvn = (u8)atomic_read(&bat_priv->tt.vn); /* allocate the tvlv, put the tt_data and all the tt_vlan_data * in the initial part @@ -2803,7 +2827,7 @@ out: */ static bool batadv_send_tt_response(struct batadv_priv *bat_priv, struct batadv_tvlv_tt_data *tt_data, - uint8_t *req_src, uint8_t *req_dst) + u8 *req_src, u8 *req_dst) { if (batadv_is_my_mac(bat_priv, req_dst)) return batadv_send_my_tt_response(bat_priv, tt_data, req_src); @@ -2814,7 +2838,7 @@ static bool batadv_send_tt_response(struct batadv_priv *bat_priv, static void _batadv_tt_update_changes(struct batadv_priv *bat_priv, struct batadv_orig_node *orig_node, struct batadv_tvlv_tt_change *tt_change, - uint16_t tt_num_changes, uint8_t ttvn) + u16 tt_num_changes, u8 ttvn) { int i; int roams; @@ -2841,13 +2865,13 @@ static void _batadv_tt_update_changes(struct batadv_priv *bat_priv, return; } } - orig_node->capa_initialized |= BATADV_ORIG_CAPA_HAS_TT; + set_bit(BATADV_ORIG_CAPA_HAS_TT, &orig_node->capa_initialized); } static void batadv_tt_fill_gtable(struct batadv_priv *bat_priv, struct batadv_tvlv_tt_change *tt_change, - uint8_t ttvn, uint8_t *resp_src, - uint16_t num_entries) + u8 ttvn, u8 *resp_src, + u16 num_entries) { struct batadv_orig_node *orig_node; @@ -2877,7 +2901,7 @@ out: static void batadv_tt_update_changes(struct batadv_priv *bat_priv, struct batadv_orig_node *orig_node, - uint16_t tt_num_changes, uint8_t ttvn, + u16 tt_num_changes, u8 ttvn, struct batadv_tvlv_tt_change *tt_change) { _batadv_tt_update_changes(bat_priv, orig_node, tt_change, @@ -2896,7 +2920,7 @@ static void batadv_tt_update_changes(struct batadv_priv *bat_priv, * * Returns true if the client is served by this node, false otherwise. */ -bool batadv_is_my_client(struct batadv_priv *bat_priv, const uint8_t *addr, +bool batadv_is_my_client(struct batadv_priv *bat_priv, const u8 *addr, unsigned short vid) { struct batadv_tt_local_entry *tt_local_entry; @@ -2927,13 +2951,14 @@ out: */ static void batadv_handle_tt_response(struct batadv_priv *bat_priv, struct batadv_tvlv_tt_data *tt_data, - uint8_t *resp_src, uint16_t num_entries) + u8 *resp_src, u16 num_entries) { - struct batadv_tt_req_node *node, *safe; + struct batadv_tt_req_node *node; + struct hlist_node *safe; struct batadv_orig_node *orig_node = NULL; struct batadv_tvlv_tt_change *tt_change; - uint8_t *tvlv_ptr = (uint8_t *)tt_data; - uint16_t change_offset; + u8 *tvlv_ptr = (u8 *)tt_data; + u16 change_offset; batadv_dbg(BATADV_DBG_TT, bat_priv, "Received TT_RESPONSE from %pM for ttvn %d t_size: %d [%c]\n", @@ -2967,10 +2992,10 @@ static void batadv_handle_tt_response(struct batadv_priv *bat_priv, /* Delete the tt_req_node from pending tt_requests list */ spin_lock_bh(&bat_priv->tt.req_list_lock); - list_for_each_entry_safe(node, safe, &bat_priv->tt.req_list, list) { + hlist_for_each_entry_safe(node, safe, &bat_priv->tt.req_list, list) { if (!batadv_compare_eth(node->addr, resp_src)) continue; - list_del(&node->list); + hlist_del_init(&node->list); kfree(node); } @@ -3016,8 +3041,7 @@ static void batadv_tt_roam_purge(struct batadv_priv *bat_priv) * * returns true if the ROAMING_ADV can be sent, false otherwise */ -static bool batadv_tt_check_roam_count(struct batadv_priv *bat_priv, - uint8_t *client) +static bool batadv_tt_check_roam_count(struct batadv_priv *bat_priv, u8 *client) { struct batadv_tt_roam_node *tt_roam_node; bool ret = false; @@ -3072,7 +3096,7 @@ unlock: * for this particular roamed client has to be forwarded to the sender of the * roaming message. */ -static void batadv_send_roam_adv(struct batadv_priv *bat_priv, uint8_t *client, +static void batadv_send_roam_adv(struct batadv_priv *bat_priv, u8 *client, unsigned short vid, struct batadv_orig_node *orig_node) { @@ -3150,14 +3174,14 @@ void batadv_tt_free(struct batadv_priv *bat_priv) * @enable: whether to set or unset the flag * @count: whether to increase the TT size by the number of changed entries */ -static void batadv_tt_local_set_flags(struct batadv_priv *bat_priv, - uint16_t flags, bool enable, bool count) +static void batadv_tt_local_set_flags(struct batadv_priv *bat_priv, u16 flags, + bool enable, bool count) { struct batadv_hashtable *hash = bat_priv->tt.local_hash; struct batadv_tt_common_entry *tt_common_entry; - uint16_t changed_num = 0; + u16 changed_num = 0; struct hlist_head *head; - uint32_t i; + u32 i; if (!hash) return; @@ -3199,7 +3223,7 @@ static void batadv_tt_local_purge_pending_clients(struct batadv_priv *bat_priv) struct hlist_node *node_tmp; struct hlist_head *head; spinlock_t *list_lock; /* protects write access to the hash lists */ - uint32_t i; + u32 i; if (!hash) return; @@ -3247,6 +3271,8 @@ static void batadv_tt_local_purge_pending_clients(struct batadv_priv *bat_priv) */ static void batadv_tt_local_commit_changes_nolock(struct batadv_priv *bat_priv) { + lockdep_assert_held(&bat_priv->tt.commit_lock); + /* Update multicast addresses in local translation table */ batadv_mcast_mla_update(bat_priv); @@ -3265,7 +3291,7 @@ static void batadv_tt_local_commit_changes_nolock(struct batadv_priv *bat_priv) atomic_inc(&bat_priv->tt.vn); batadv_dbg(BATADV_DBG_TT, bat_priv, "Local changes committed, updating to ttvn %u\n", - (uint8_t)atomic_read(&bat_priv->tt.vn)); + (u8)atomic_read(&bat_priv->tt.vn)); /* reset the sending counter */ atomic_set(&bat_priv->tt.ogm_append_cnt, BATADV_TT_OGM_APPEND_MAX); @@ -3284,8 +3310,8 @@ void batadv_tt_local_commit_changes(struct batadv_priv *bat_priv) spin_unlock_bh(&bat_priv->tt.commit_lock); } -bool batadv_is_ap_isolated(struct batadv_priv *bat_priv, uint8_t *src, - uint8_t *dst, unsigned short vid) +bool batadv_is_ap_isolated(struct batadv_priv *bat_priv, u8 *src, u8 *dst, + unsigned short vid) { struct batadv_tt_local_entry *tt_local_entry = NULL; struct batadv_tt_global_entry *tt_global_entry = NULL; @@ -3333,17 +3359,18 @@ out: */ static void batadv_tt_update_orig(struct batadv_priv *bat_priv, struct batadv_orig_node *orig_node, - const void *tt_buff, uint16_t tt_num_vlan, + const void *tt_buff, u16 tt_num_vlan, struct batadv_tvlv_tt_change *tt_change, - uint16_t tt_num_changes, uint8_t ttvn) + u16 tt_num_changes, u8 ttvn) { - uint8_t orig_ttvn = (uint8_t)atomic_read(&orig_node->last_ttvn); + u8 orig_ttvn = (u8)atomic_read(&orig_node->last_ttvn); struct batadv_tvlv_tt_vlan_data *tt_vlan; bool full_table = true; bool has_tt_init; tt_vlan = (struct batadv_tvlv_tt_vlan_data *)tt_buff; - has_tt_init = orig_node->capa_initialized & BATADV_ORIG_CAPA_HAS_TT; + has_tt_init = test_bit(BATADV_ORIG_CAPA_HAS_TT, + &orig_node->capa_initialized); /* orig table not initialised AND first diff is in the OGM OR the ttvn * increased by one -> we can apply the attached changes @@ -3415,7 +3442,7 @@ request_table: * deleted later by a DEL or because of timeout */ bool batadv_tt_global_client_is_roaming(struct batadv_priv *bat_priv, - uint8_t *addr, unsigned short vid) + u8 *addr, unsigned short vid) { struct batadv_tt_global_entry *tt_global_entry; bool ret = false; @@ -3441,7 +3468,7 @@ out: * to keep the latter consistent with the node TTVN */ bool batadv_tt_local_client_is_roaming(struct batadv_priv *bat_priv, - uint8_t *addr, unsigned short vid) + u8 *addr, unsigned short vid) { struct batadv_tt_local_entry *tt_local_entry; bool ret = false; @@ -3527,13 +3554,13 @@ void batadv_tt_local_resize_to_mtu(struct net_device *soft_iface) */ static void batadv_tt_tvlv_ogm_handler_v1(struct batadv_priv *bat_priv, struct batadv_orig_node *orig, - uint8_t flags, void *tvlv_value, - uint16_t tvlv_value_len) + u8 flags, void *tvlv_value, + u16 tvlv_value_len) { struct batadv_tvlv_tt_vlan_data *tt_vlan; struct batadv_tvlv_tt_change *tt_change; struct batadv_tvlv_tt_data *tt_data; - uint16_t num_entries, num_vlan; + u16 num_entries, num_vlan; if (tvlv_value_len < sizeof(*tt_data)) return; @@ -3569,12 +3596,12 @@ static void batadv_tt_tvlv_ogm_handler_v1(struct batadv_priv *bat_priv, * otherwise. */ static int batadv_tt_tvlv_unicast_handler_v1(struct batadv_priv *bat_priv, - uint8_t *src, uint8_t *dst, + u8 *src, u8 *dst, void *tvlv_value, - uint16_t tvlv_value_len) + u16 tvlv_value_len) { struct batadv_tvlv_tt_data *tt_data; - uint16_t tt_vlan_len, tt_num_entries; + u16 tt_vlan_len, tt_num_entries; char tt_flag; bool ret; @@ -3650,9 +3677,9 @@ static int batadv_tt_tvlv_unicast_handler_v1(struct batadv_priv *bat_priv, * otherwise. */ static int batadv_roam_tvlv_unicast_handler_v1(struct batadv_priv *bat_priv, - uint8_t *src, uint8_t *dst, + u8 *src, u8 *dst, void *tvlv_value, - uint16_t tvlv_value_len) + u16 tvlv_value_len) { struct batadv_tvlv_roam_adv *roaming_adv; struct batadv_orig_node *orig_node = NULL; @@ -3734,7 +3761,7 @@ int batadv_tt_init(struct batadv_priv *bat_priv) * otherwise */ bool batadv_tt_global_is_isolated(struct batadv_priv *bat_priv, - const uint8_t *addr, unsigned short vid) + const u8 *addr, unsigned short vid) { struct batadv_tt_global_entry *tt; bool ret; diff --git a/net/batman-adv/translation-table.h b/net/batman-adv/translation-table.h index 6acc25d3a925..abd8e116e5fb 100644 --- a/net/batman-adv/translation-table.h +++ b/net/batman-adv/translation-table.h @@ -22,44 +22,41 @@ #include <linux/types.h> -struct batadv_orig_node; -struct batadv_priv; struct net_device; struct seq_file; int batadv_tt_init(struct batadv_priv *bat_priv); -bool batadv_tt_local_add(struct net_device *soft_iface, const uint8_t *addr, - unsigned short vid, int ifindex, uint32_t mark); -uint16_t batadv_tt_local_remove(struct batadv_priv *bat_priv, - const uint8_t *addr, unsigned short vid, - const char *message, bool roaming); +bool batadv_tt_local_add(struct net_device *soft_iface, const u8 *addr, + unsigned short vid, int ifindex, u32 mark); +u16 batadv_tt_local_remove(struct batadv_priv *bat_priv, + const u8 *addr, unsigned short vid, + 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); void batadv_tt_global_del_orig(struct batadv_priv *bat_priv, struct batadv_orig_node *orig_node, - int32_t match_vid, const char *message); + s32 match_vid, const char *message); int batadv_tt_global_hash_count(struct batadv_priv *bat_priv, - const uint8_t *addr, unsigned short vid); + const u8 *addr, unsigned short vid); struct batadv_orig_node *batadv_transtable_search(struct batadv_priv *bat_priv, - const uint8_t *src, - const uint8_t *addr, + const u8 *src, const u8 *addr, unsigned short vid); void batadv_tt_free(struct batadv_priv *bat_priv); -bool batadv_is_my_client(struct batadv_priv *bat_priv, const uint8_t *addr, +bool batadv_is_my_client(struct batadv_priv *bat_priv, const u8 *addr, unsigned short vid); -bool batadv_is_ap_isolated(struct batadv_priv *bat_priv, uint8_t *src, - uint8_t *dst, unsigned short vid); +bool batadv_is_ap_isolated(struct batadv_priv *bat_priv, u8 *src, u8 *dst, + unsigned short vid); void batadv_tt_local_commit_changes(struct batadv_priv *bat_priv); bool batadv_tt_global_client_is_roaming(struct batadv_priv *bat_priv, - uint8_t *addr, unsigned short vid); + u8 *addr, unsigned short vid); bool batadv_tt_local_client_is_roaming(struct batadv_priv *bat_priv, - uint8_t *addr, unsigned short vid); + u8 *addr, unsigned short vid); void batadv_tt_local_resize_to_mtu(struct net_device *soft_iface); bool batadv_tt_add_temporary_global_entry(struct batadv_priv *bat_priv, struct batadv_orig_node *orig_node, const unsigned char *addr, unsigned short vid); bool batadv_tt_global_is_isolated(struct batadv_priv *bat_priv, - const uint8_t *addr, unsigned short vid); + const u8 *addr, unsigned short vid); #endif /* _NET_BATMAN_ADV_TRANSLATION_TABLE_H_ */ diff --git a/net/batman-adv/types.h b/net/batman-adv/types.h index 67d63483618e..d260efd70499 100644 --- a/net/batman-adv/types.h +++ b/net/batman-adv/types.h @@ -44,7 +44,7 @@ struct seq_file; * * *Please be careful: batadv_dat_addr_t must be UNSIGNED* */ -#define batadv_dat_addr_t uint16_t +#define batadv_dat_addr_t u16 #endif /* CONFIG_BATMAN_ADV_DAT */ @@ -103,10 +103,10 @@ struct batadv_hard_iface_bat_iv { */ struct batadv_hard_iface { struct list_head list; - int16_t if_num; + s16 if_num; char if_status; struct net_device *net_dev; - uint8_t num_bcasts; + u8 num_bcasts; struct kobject *hardif_obj; atomic_t refcount; struct packet_type batman_adv_ptype; @@ -132,8 +132,8 @@ struct batadv_orig_ifinfo { struct hlist_node list; struct batadv_hard_iface *if_outgoing; struct batadv_neigh_node __rcu *router; /* rcu protected pointer */ - uint32_t last_real_seqno; - uint8_t last_ttl; + u32 last_real_seqno; + u8 last_ttl; unsigned long batman_seqno_reset; atomic_t refcount; struct rcu_head rcu; @@ -152,9 +152,9 @@ struct batadv_frag_table_entry { struct hlist_head head; spinlock_t lock; /* protects head */ unsigned long timestamp; - uint16_t seqno; - uint16_t size; - uint16_t total_size; + u16 seqno; + u16 size; + u16 total_size; }; /** @@ -166,7 +166,7 @@ struct batadv_frag_table_entry { struct batadv_frag_list_entry { struct hlist_node list; struct sk_buff *skb; - uint8_t no; + u8 no; }; /** @@ -175,7 +175,7 @@ struct batadv_frag_list_entry { * @num_entries: number of TT entries for this VLAN */ struct batadv_vlan_tt { - uint32_t crc; + u32 crc; atomic_t num_entries; }; @@ -190,7 +190,7 @@ struct batadv_vlan_tt { struct batadv_orig_node_vlan { unsigned short vid; struct batadv_vlan_tt tt; - struct list_head list; + struct hlist_node list; atomic_t refcount; struct rcu_head rcu; }; @@ -206,7 +206,7 @@ struct batadv_orig_node_vlan { */ struct batadv_orig_bat_iv { unsigned long *bcast_own; - uint8_t *bcast_own_sum; + u8 *bcast_own_sum; /* ogm_cnt_lock protects: bcast_own, bcast_own_sum, * neigh_node->bat_iv.real_bits & neigh_node->bat_iv.real_packet_count */ @@ -221,6 +221,7 @@ struct batadv_orig_bat_iv { * @batadv_dat_addr_t: address of the orig node in the distributed hash * @last_seen: time when last packet from this node was received * @bcast_seqno_reset: time when the broadcast seqno window was reset + * @mcast_handler_lock: synchronizes mcast-capability and -flag changes * @mcast_flags: multicast flags announced by the orig node * @mcast_want_all_unsnoop_node: a list node for the * mcast.want_all_unsnoopables list @@ -259,7 +260,7 @@ struct batadv_orig_bat_iv { * @bat_iv: B.A.T.M.A.N. IV private structure */ struct batadv_orig_node { - uint8_t orig[ETH_ALEN]; + u8 orig[ETH_ALEN]; struct hlist_head ifinfo_list; struct batadv_orig_ifinfo *last_bonding_candidate; #ifdef CONFIG_BATMAN_ADV_DAT @@ -268,21 +269,23 @@ struct batadv_orig_node { unsigned long last_seen; unsigned long bcast_seqno_reset; #ifdef CONFIG_BATMAN_ADV_MCAST - uint8_t mcast_flags; + /* synchronizes mcast tvlv specific orig changes */ + spinlock_t mcast_handler_lock; + u8 mcast_flags; struct hlist_node mcast_want_all_unsnoopables_node; struct hlist_node mcast_want_all_ipv4_node; struct hlist_node mcast_want_all_ipv6_node; #endif - uint8_t capabilities; - uint8_t capa_initialized; + unsigned long capabilities; + unsigned long capa_initialized; atomic_t last_ttvn; unsigned char *tt_buff; - int16_t tt_buff_len; + s16 tt_buff_len; spinlock_t tt_buff_lock; /* protects tt_buff & tt_buff_len */ /* prevents from changing the table while reading it */ spinlock_t tt_lock; DECLARE_BITMAP(bcast_bits, BATADV_TQ_LOCAL_WINDOW_SIZE); - uint32_t last_bcast_seqno; + u32 last_bcast_seqno; struct hlist_head neigh_list; /* neigh_list_lock protects: neigh_list and router */ spinlock_t neigh_list_lock; @@ -299,7 +302,7 @@ struct batadv_orig_node { spinlock_t out_coding_list_lock; /* Protects out_coding_list */ #endif struct batadv_frag_table_entry fragments[BATADV_FRAG_BUFFER_COUNT]; - struct list_head vlan_list; + struct hlist_head vlan_list; spinlock_t vlan_list_lock; /* protects vlan_list */ struct batadv_orig_bat_iv bat_iv; }; @@ -313,10 +316,10 @@ struct batadv_orig_node { * (= orig node announces a tvlv of type BATADV_TVLV_MCAST) */ enum batadv_orig_capabilities { - BATADV_ORIG_CAPA_HAS_DAT = BIT(0), - BATADV_ORIG_CAPA_HAS_NC = BIT(1), - BATADV_ORIG_CAPA_HAS_TT = BIT(2), - BATADV_ORIG_CAPA_HAS_MCAST = BIT(3), + BATADV_ORIG_CAPA_HAS_DAT, + BATADV_ORIG_CAPA_HAS_NC, + BATADV_ORIG_CAPA_HAS_TT, + BATADV_ORIG_CAPA_HAS_MCAST, }; /** @@ -325,16 +328,14 @@ enum batadv_orig_capabilities { * @orig_node: pointer to corresponding orig node * @bandwidth_down: advertised uplink download bandwidth * @bandwidth_up: advertised uplink upload bandwidth - * @deleted: this struct is scheduled for deletion * @refcount: number of contexts the object is used * @rcu: struct used for freeing in an RCU-safe manner */ struct batadv_gw_node { struct hlist_node list; struct batadv_orig_node *orig_node; - uint32_t bandwidth_down; - uint32_t bandwidth_up; - unsigned long deleted; + u32 bandwidth_down; + u32 bandwidth_up; atomic_t refcount; struct rcu_head rcu; }; @@ -355,7 +356,7 @@ struct batadv_gw_node { struct batadv_neigh_node { struct hlist_node list; struct batadv_orig_node *orig_node; - uint8_t addr[ETH_ALEN]; + u8 addr[ETH_ALEN]; struct hlist_head ifinfo_list; spinlock_t ifinfo_lock; /* protects ifinfo_list and its members */ struct batadv_hard_iface *if_incoming; @@ -375,11 +376,11 @@ struct batadv_neigh_node { * @real_packet_count: counted result of real_bits */ struct batadv_neigh_ifinfo_bat_iv { - uint8_t tq_recv[BATADV_TQ_GLOBAL_WINDOW_SIZE]; - uint8_t tq_index; - uint8_t tq_avg; + u8 tq_recv[BATADV_TQ_GLOBAL_WINDOW_SIZE]; + u8 tq_index; + u8 tq_avg; DECLARE_BITMAP(real_bits, BATADV_TQ_LOCAL_WINDOW_SIZE); - uint8_t real_packet_count; + u8 real_packet_count; }; /** @@ -395,7 +396,7 @@ struct batadv_neigh_ifinfo { struct hlist_node list; struct batadv_hard_iface *if_outgoing; struct batadv_neigh_ifinfo_bat_iv bat_iv; - uint8_t last_ttl; + u8 last_ttl; atomic_t refcount; struct rcu_head rcu; }; @@ -408,7 +409,7 @@ struct batadv_neigh_ifinfo { */ #ifdef CONFIG_BATMAN_ADV_BLA struct batadv_bcast_duplist_entry { - uint8_t orig[ETH_ALEN]; + u8 orig[ETH_ALEN]; __be32 crc; unsigned long entrytime; }; @@ -534,13 +535,13 @@ struct batadv_priv_tt { struct list_head changes_list; struct batadv_hashtable *local_hash; struct batadv_hashtable *global_hash; - struct list_head req_list; + struct hlist_head req_list; struct list_head roam_list; spinlock_t changes_list_lock; /* protects changes */ spinlock_t req_list_lock; /* protects req_list */ spinlock_t roam_list_lock; /* protects roam_list */ unsigned char *last_changeset; - int16_t last_changeset_len; + s16 last_changeset_len; /* protects last_changeset & last_changeset_len */ spinlock_t last_changeset_lock; /* prevents from executing a commit while reading the table */ @@ -660,7 +661,7 @@ struct batadv_priv_mcast { struct hlist_head want_all_unsnoopables_list; struct hlist_head want_all_ipv4_list; struct hlist_head want_all_ipv6_list; - uint8_t flags; + u8 flags; bool enabled; atomic_t num_disabled; atomic_t num_want_all_unsnoopables; @@ -778,7 +779,7 @@ struct batadv_priv { atomic_t mesh_state; struct net_device *soft_iface; struct net_device_stats stats; - uint64_t __percpu *bat_counters; /* Per cpu counters */ + u64 __percpu *bat_counters; /* Per cpu counters */ atomic_t aggregated_ogms; atomic_t bonding; atomic_t fragmentation; @@ -800,8 +801,8 @@ struct batadv_priv { #ifdef CONFIG_BATMAN_ADV_DEBUG atomic_t log_level; #endif - uint32_t isolation_mark; - uint32_t isolation_mark_mask; + u32 isolation_mark; + u32 isolation_mark_mask; atomic_t bcast_seqno; atomic_t bcast_queue_left; atomic_t batman_queue_left; @@ -867,7 +868,7 @@ struct batadv_socket_client { struct batadv_socket_packet { struct list_head list; size_t icmp_len; - uint8_t icmp_packet[BATADV_ICMP_MAX_PACKET_SIZE]; + u8 icmp_packet[BATADV_ICMP_MAX_PACKET_SIZE]; }; /** @@ -888,14 +889,14 @@ struct batadv_socket_packet { */ #ifdef CONFIG_BATMAN_ADV_BLA struct batadv_bla_backbone_gw { - uint8_t orig[ETH_ALEN]; + u8 orig[ETH_ALEN]; unsigned short vid; struct hlist_node hash_entry; struct batadv_priv *bat_priv; unsigned long lasttime; atomic_t wait_periods; atomic_t request_sent; - uint16_t crc; + u16 crc; atomic_t refcount; struct rcu_head rcu; }; @@ -911,7 +912,7 @@ struct batadv_bla_backbone_gw { * @rcu: struct used for freeing in an RCU-safe manner */ struct batadv_bla_claim { - uint8_t addr[ETH_ALEN]; + u8 addr[ETH_ALEN]; unsigned short vid; struct batadv_bla_backbone_gw *backbone_gw; unsigned long lasttime; @@ -933,10 +934,10 @@ struct batadv_bla_claim { * @rcu: struct used for freeing in an RCU-safe manner */ struct batadv_tt_common_entry { - uint8_t addr[ETH_ALEN]; + u8 addr[ETH_ALEN]; unsigned short vid; struct hlist_node hash_entry; - uint16_t flags; + u16 flags; unsigned long added_at; atomic_t refcount; struct rcu_head rcu; @@ -978,7 +979,7 @@ struct batadv_tt_global_entry { */ struct batadv_tt_orig_list_entry { struct batadv_orig_node *orig_node; - uint8_t ttvn; + u8 ttvn; struct hlist_node list; atomic_t refcount; struct rcu_head rcu; @@ -1001,9 +1002,9 @@ struct batadv_tt_change_node { * @list: list node for batadv_priv_tt::req_list */ struct batadv_tt_req_node { - uint8_t addr[ETH_ALEN]; + u8 addr[ETH_ALEN]; unsigned long issued_at; - struct list_head list; + struct hlist_node list; }; /** @@ -1015,7 +1016,7 @@ struct batadv_tt_req_node { * @list: list node for batadv_priv_tt::roam_list */ struct batadv_tt_roam_node { - uint8_t addr[ETH_ALEN]; + u8 addr[ETH_ALEN]; atomic_t counter; unsigned long first_time; struct list_head list; @@ -1032,7 +1033,7 @@ struct batadv_tt_roam_node { */ struct batadv_nc_node { struct list_head list; - uint8_t addr[ETH_ALEN]; + u8 addr[ETH_ALEN]; atomic_t refcount; struct rcu_head rcu; struct batadv_orig_node *orig_node; @@ -1056,8 +1057,8 @@ struct batadv_nc_path { atomic_t refcount; struct list_head packet_list; spinlock_t packet_list_lock; /* Protects packet_list */ - uint8_t next_hop[ETH_ALEN]; - uint8_t prev_hop[ETH_ALEN]; + u8 next_hop[ETH_ALEN]; + u8 prev_hop[ETH_ALEN]; unsigned long last_valid; }; @@ -1109,11 +1110,11 @@ struct batadv_skb_cb { struct batadv_forw_packet { struct hlist_node list; unsigned long send_time; - uint8_t own; + u8 own; struct sk_buff *skb; - uint16_t packet_len; - uint32_t direct_link_flags; - uint8_t num_packets; + u16 packet_len; + u32 direct_link_flags; + u8 num_packets; struct delayed_work delayed_work; struct batadv_hard_iface *if_incoming; struct batadv_hard_iface *if_outgoing; @@ -1188,7 +1189,7 @@ struct batadv_algo_ops { */ struct batadv_dat_entry { __be32 ip; - uint8_t mac_addr[ETH_ALEN]; + u8 mac_addr[ETH_ALEN]; unsigned short vid; unsigned long last_update; struct hlist_node hash_entry; @@ -1250,14 +1251,13 @@ struct batadv_tvlv_handler { struct hlist_node list; void (*ogm_handler)(struct batadv_priv *bat_priv, struct batadv_orig_node *orig, - uint8_t flags, - void *tvlv_value, uint16_t tvlv_value_len); + u8 flags, void *tvlv_value, u16 tvlv_value_len); int (*unicast_handler)(struct batadv_priv *bat_priv, - uint8_t *src, uint8_t *dst, - void *tvlv_value, uint16_t tvlv_value_len); - uint8_t type; - uint8_t version; - uint8_t flags; + u8 *src, u8 *dst, + void *tvlv_value, u16 tvlv_value_len); + u8 type; + u8 version; + u8 flags; atomic_t refcount; struct rcu_head rcu; }; diff --git a/net/bluetooth/6lowpan.c b/net/bluetooth/6lowpan.c index 2fb7b3064904..131e79cde350 100644 --- a/net/bluetooth/6lowpan.c +++ b/net/bluetooth/6lowpan.c @@ -85,7 +85,7 @@ struct lowpan_dev { static inline struct lowpan_dev *lowpan_dev(const struct net_device *netdev) { - return netdev_priv(netdev); + return (struct lowpan_dev *)lowpan_priv(netdev)->priv; } static inline void peer_add(struct lowpan_dev *dev, struct lowpan_peer *peer) @@ -848,8 +848,9 @@ static int setup_netdev(struct l2cap_chan *chan, struct lowpan_dev **dev) struct net_device *netdev; int err = 0; - netdev = alloc_netdev(sizeof(struct lowpan_dev), IFACE_NAME_TEMPLATE, - NET_NAME_UNKNOWN, netdev_setup); + netdev = alloc_netdev(LOWPAN_PRIV_SIZE(sizeof(struct lowpan_dev)), + IFACE_NAME_TEMPLATE, NET_NAME_UNKNOWN, + netdev_setup); if (!netdev) return -ENOMEM; @@ -859,9 +860,24 @@ static int setup_netdev(struct l2cap_chan *chan, struct lowpan_dev **dev) SET_NETDEV_DEV(netdev, &chan->conn->hcon->hdev->dev); SET_NETDEV_DEVTYPE(netdev, &bt_type); + *dev = lowpan_dev(netdev); + (*dev)->netdev = netdev; + (*dev)->hdev = chan->conn->hcon->hdev; + INIT_LIST_HEAD(&(*dev)->peers); + + spin_lock(&devices_lock); + INIT_LIST_HEAD(&(*dev)->list); + list_add_rcu(&(*dev)->list, &bt_6lowpan_devices); + spin_unlock(&devices_lock); + + lowpan_netdev_setup(netdev, LOWPAN_LLTYPE_BTLE); + err = register_netdev(netdev); if (err < 0) { BT_INFO("register_netdev failed %d", err); + spin_lock(&devices_lock); + list_del_rcu(&(*dev)->list); + spin_unlock(&devices_lock); free_netdev(netdev); goto out; } @@ -871,16 +887,6 @@ static int setup_netdev(struct l2cap_chan *chan, struct lowpan_dev **dev) &chan->src, chan->src_type); set_bit(__LINK_STATE_PRESENT, &netdev->state); - *dev = netdev_priv(netdev); - (*dev)->netdev = netdev; - (*dev)->hdev = chan->conn->hcon->hdev; - INIT_LIST_HEAD(&(*dev)->peers); - - spin_lock(&devices_lock); - INIT_LIST_HEAD(&(*dev)->list); - list_add_rcu(&(*dev)->list, &bt_6lowpan_devices); - spin_unlock(&devices_lock); - return 0; out: diff --git a/net/bluetooth/Kconfig b/net/bluetooth/Kconfig index b8c794b87523..95d1a66ba03a 100644 --- a/net/bluetooth/Kconfig +++ b/net/bluetooth/Kconfig @@ -53,6 +53,11 @@ source "net/bluetooth/cmtp/Kconfig" source "net/bluetooth/hidp/Kconfig" +config BT_HS + bool "Bluetooth High Speed (HS) features" + depends on BT_BREDR + default y + config BT_LE bool "Bluetooth Low Energy (LE) features" depends on BT diff --git a/net/bluetooth/Makefile b/net/bluetooth/Makefile index 29c12ae72a66..2b15ae8c1def 100644 --- a/net/bluetooth/Makefile +++ b/net/bluetooth/Makefile @@ -13,9 +13,10 @@ bluetooth_6lowpan-y := 6lowpan.o bluetooth-y := af_bluetooth.o hci_core.o hci_conn.o hci_event.o mgmt.o \ hci_sock.o hci_sysfs.o l2cap_core.o l2cap_sock.o smp.o lib.o \ - a2mp.o amp.o ecc.o hci_request.o mgmt_util.o + ecc.o hci_request.o mgmt_util.o bluetooth-$(CONFIG_BT_BREDR) += sco.o +bluetooth-$(CONFIG_BT_HS) += a2mp.o amp.o bluetooth-$(CONFIG_BT_DEBUGFS) += hci_debugfs.o bluetooth-$(CONFIG_BT_SELFTEST) += selftest.o diff --git a/net/bluetooth/a2mp.c b/net/bluetooth/a2mp.c index 5a04eb1a7e57..5f123c3320a7 100644 --- a/net/bluetooth/a2mp.c +++ b/net/bluetooth/a2mp.c @@ -16,6 +16,7 @@ #include <net/bluetooth/hci_core.h> #include <net/bluetooth/l2cap.h> +#include "hci_request.h" #include "a2mp.h" #include "amp.h" @@ -286,11 +287,21 @@ static int a2mp_change_notify(struct amp_mgr *mgr, struct sk_buff *skb, return 0; } +static void read_local_amp_info_complete(struct hci_dev *hdev, u8 status, + u16 opcode) +{ + BT_DBG("%s status 0x%2.2x", hdev->name, status); + + a2mp_send_getinfo_rsp(hdev); +} + static int a2mp_getinfo_req(struct amp_mgr *mgr, struct sk_buff *skb, struct a2mp_cmd *hdr) { struct a2mp_info_req *req = (void *) skb->data; struct hci_dev *hdev; + struct hci_request hreq; + int err = 0; if (le16_to_cpu(hdr->len) < sizeof(*req)) return -EINVAL; @@ -311,7 +322,11 @@ static int a2mp_getinfo_req(struct amp_mgr *mgr, struct sk_buff *skb, } set_bit(READ_LOC_AMP_INFO, &mgr->state); - hci_send_cmd(hdev, HCI_OP_READ_LOCAL_AMP_INFO, 0, NULL); + hci_req_init(&hreq, hdev); + hci_req_add(&hreq, HCI_OP_READ_LOCAL_AMP_INFO, 0, NULL); + err = hci_req_run(&hreq, read_local_amp_info_complete); + if (err < 0) + a2mp_send_getinfo_rsp(hdev); done: if (hdev) diff --git a/net/bluetooth/a2mp.h b/net/bluetooth/a2mp.h index 296f665adb09..a4ff3ea9b38a 100644 --- a/net/bluetooth/a2mp.h +++ b/net/bluetooth/a2mp.h @@ -130,10 +130,29 @@ struct a2mp_physlink_rsp { #define A2MP_STATUS_SECURITY_VIOLATION 0x06 struct amp_mgr *amp_mgr_get(struct amp_mgr *mgr); + +#if IS_ENABLED(CONFIG_BT_HS) int amp_mgr_put(struct amp_mgr *mgr); struct l2cap_chan *a2mp_channel_create(struct l2cap_conn *conn, struct sk_buff *skb); void a2mp_discover_amp(struct l2cap_chan *chan); +#else +static inline int amp_mgr_put(struct amp_mgr *mgr) +{ + return 0; +} + +static inline struct l2cap_chan *a2mp_channel_create(struct l2cap_conn *conn, + struct sk_buff *skb) +{ + return NULL; +} + +static inline void a2mp_discover_amp(struct l2cap_chan *chan) +{ +} +#endif + void a2mp_send_getinfo_rsp(struct hci_dev *hdev); void a2mp_send_getampassoc_rsp(struct hci_dev *hdev, u8 status); void a2mp_send_create_phy_link_req(struct hci_dev *hdev, u8 status); diff --git a/net/bluetooth/amp.c b/net/bluetooth/amp.c index ee016f039100..e32f34189007 100644 --- a/net/bluetooth/amp.c +++ b/net/bluetooth/amp.c @@ -16,6 +16,7 @@ #include <net/bluetooth/hci_core.h> #include <crypto/hash.h> +#include "hci_request.h" #include "a2mp.h" #include "amp.h" @@ -220,10 +221,49 @@ int phylink_gen_key(struct hci_conn *conn, u8 *data, u8 *len, u8 *type) return hmac_sha256(gamp_key, HCI_AMP_LINK_KEY_SIZE, "802b", 4, data); } +static void read_local_amp_assoc_complete(struct hci_dev *hdev, u8 status, + u16 opcode, struct sk_buff *skb) +{ + struct hci_rp_read_local_amp_assoc *rp = (void *)skb->data; + struct amp_assoc *assoc = &hdev->loc_assoc; + size_t rem_len, frag_len; + + BT_DBG("%s status 0x%2.2x", hdev->name, rp->status); + + if (rp->status) + goto send_rsp; + + frag_len = skb->len - sizeof(*rp); + rem_len = __le16_to_cpu(rp->rem_len); + + if (rem_len > frag_len) { + BT_DBG("frag_len %zu rem_len %zu", frag_len, rem_len); + + memcpy(assoc->data + assoc->offset, rp->frag, frag_len); + assoc->offset += frag_len; + + /* Read other fragments */ + amp_read_loc_assoc_frag(hdev, rp->phy_handle); + + return; + } + + memcpy(assoc->data + assoc->offset, rp->frag, rem_len); + assoc->len = assoc->offset + rem_len; + assoc->offset = 0; + +send_rsp: + /* Send A2MP Rsp when all fragments are received */ + a2mp_send_getampassoc_rsp(hdev, rp->status); + a2mp_send_create_phy_link_req(hdev, rp->status); +} + void amp_read_loc_assoc_frag(struct hci_dev *hdev, u8 phy_handle) { struct hci_cp_read_local_amp_assoc cp; struct amp_assoc *loc_assoc = &hdev->loc_assoc; + struct hci_request req; + int err = 0; BT_DBG("%s handle %d", hdev->name, phy_handle); @@ -231,12 +271,18 @@ void amp_read_loc_assoc_frag(struct hci_dev *hdev, u8 phy_handle) cp.max_len = cpu_to_le16(hdev->amp_assoc_size); cp.len_so_far = cpu_to_le16(loc_assoc->offset); - hci_send_cmd(hdev, HCI_OP_READ_LOCAL_AMP_ASSOC, sizeof(cp), &cp); + hci_req_init(&req, hdev); + hci_req_add(&req, HCI_OP_READ_LOCAL_AMP_ASSOC, sizeof(cp), &cp); + err = hci_req_run_skb(&req, read_local_amp_assoc_complete); + if (err < 0) + a2mp_send_getampassoc_rsp(hdev, A2MP_STATUS_INVALID_CTRL_ID); } void amp_read_loc_assoc(struct hci_dev *hdev, struct amp_mgr *mgr) { struct hci_cp_read_local_amp_assoc cp; + struct hci_request req; + int err = 0; memset(&hdev->loc_assoc, 0, sizeof(struct amp_assoc)); memset(&cp, 0, sizeof(cp)); @@ -244,7 +290,11 @@ void amp_read_loc_assoc(struct hci_dev *hdev, struct amp_mgr *mgr) cp.max_len = cpu_to_le16(hdev->amp_assoc_size); set_bit(READ_LOC_AMP_ASSOC, &mgr->state); - hci_send_cmd(hdev, HCI_OP_READ_LOCAL_AMP_ASSOC, sizeof(cp), &cp); + hci_req_init(&req, hdev); + hci_req_add(&req, HCI_OP_READ_LOCAL_AMP_ASSOC, sizeof(cp), &cp); + hci_req_run_skb(&req, read_local_amp_assoc_complete); + if (err < 0) + a2mp_send_getampassoc_rsp(hdev, A2MP_STATUS_INVALID_CTRL_ID); } void amp_read_loc_assoc_final_data(struct hci_dev *hdev, @@ -252,6 +302,8 @@ void amp_read_loc_assoc_final_data(struct hci_dev *hdev, { struct hci_cp_read_local_amp_assoc cp; struct amp_mgr *mgr = hcon->amp_mgr; + struct hci_request req; + int err = 0; cp.phy_handle = hcon->handle; cp.len_so_far = cpu_to_le16(0); @@ -260,7 +312,25 @@ void amp_read_loc_assoc_final_data(struct hci_dev *hdev, set_bit(READ_LOC_AMP_ASSOC_FINAL, &mgr->state); /* Read Local AMP Assoc final link information data */ - hci_send_cmd(hdev, HCI_OP_READ_LOCAL_AMP_ASSOC, sizeof(cp), &cp); + hci_req_init(&req, hdev); + hci_req_add(&req, HCI_OP_READ_LOCAL_AMP_ASSOC, sizeof(cp), &cp); + hci_req_run_skb(&req, read_local_amp_assoc_complete); + if (err < 0) + a2mp_send_getampassoc_rsp(hdev, A2MP_STATUS_INVALID_CTRL_ID); +} + +static void write_remote_amp_assoc_complete(struct hci_dev *hdev, u8 status, + u16 opcode, struct sk_buff *skb) +{ + struct hci_rp_write_remote_amp_assoc *rp = (void *)skb->data; + + BT_DBG("%s status 0x%2.2x phy_handle 0x%2.2x", + hdev->name, rp->status, rp->phy_handle); + + if (rp->status) + return; + + amp_write_rem_assoc_continue(hdev, rp->phy_handle); } /* Write AMP Assoc data fragments, returns true with last fragment written*/ @@ -270,6 +340,7 @@ static bool amp_write_rem_assoc_frag(struct hci_dev *hdev, struct hci_cp_write_remote_amp_assoc *cp; struct amp_mgr *mgr = hcon->amp_mgr; struct amp_ctrl *ctrl; + struct hci_request req; u16 frag_len, len; ctrl = amp_ctrl_lookup(mgr, hcon->remote_id); @@ -307,7 +378,9 @@ static bool amp_write_rem_assoc_frag(struct hci_dev *hdev, amp_ctrl_put(ctrl); - hci_send_cmd(hdev, HCI_OP_WRITE_REMOTE_AMP_ASSOC, len, cp); + hci_req_init(&req, hdev); + hci_req_add(&req, HCI_OP_WRITE_REMOTE_AMP_ASSOC, len, cp); + hci_req_run_skb(&req, write_remote_amp_assoc_complete); kfree(cp); @@ -344,10 +417,37 @@ void amp_write_remote_assoc(struct hci_dev *hdev, u8 handle) amp_write_rem_assoc_frag(hdev, hcon); } +static void create_phylink_complete(struct hci_dev *hdev, u8 status, + u16 opcode) +{ + struct hci_cp_create_phy_link *cp; + + BT_DBG("%s status 0x%2.2x", hdev->name, status); + + cp = hci_sent_cmd_data(hdev, HCI_OP_CREATE_PHY_LINK); + if (!cp) + return; + + hci_dev_lock(hdev); + + if (status) { + struct hci_conn *hcon; + + hcon = hci_conn_hash_lookup_handle(hdev, cp->phy_handle); + if (hcon) + hci_conn_del(hcon); + } else { + amp_write_remote_assoc(hdev, cp->phy_handle); + } + + hci_dev_unlock(hdev); +} + void amp_create_phylink(struct hci_dev *hdev, struct amp_mgr *mgr, struct hci_conn *hcon) { struct hci_cp_create_phy_link cp; + struct hci_request req; cp.phy_handle = hcon->handle; @@ -360,13 +460,33 @@ void amp_create_phylink(struct hci_dev *hdev, struct amp_mgr *mgr, return; } - hci_send_cmd(hdev, HCI_OP_CREATE_PHY_LINK, sizeof(cp), &cp); + hci_req_init(&req, hdev); + hci_req_add(&req, HCI_OP_CREATE_PHY_LINK, sizeof(cp), &cp); + hci_req_run(&req, create_phylink_complete); +} + +static void accept_phylink_complete(struct hci_dev *hdev, u8 status, + u16 opcode) +{ + struct hci_cp_accept_phy_link *cp; + + BT_DBG("%s status 0x%2.2x", hdev->name, status); + + if (status) + return; + + cp = hci_sent_cmd_data(hdev, HCI_OP_ACCEPT_PHY_LINK); + if (!cp) + return; + + amp_write_remote_assoc(hdev, cp->phy_handle); } void amp_accept_phylink(struct hci_dev *hdev, struct amp_mgr *mgr, struct hci_conn *hcon) { struct hci_cp_accept_phy_link cp; + struct hci_request req; cp.phy_handle = hcon->handle; @@ -379,7 +499,9 @@ void amp_accept_phylink(struct hci_dev *hdev, struct amp_mgr *mgr, return; } - hci_send_cmd(hdev, HCI_OP_ACCEPT_PHY_LINK, sizeof(cp), &cp); + hci_req_init(&req, hdev); + hci_req_add(&req, HCI_OP_ACCEPT_PHY_LINK, sizeof(cp), &cp); + hci_req_run(&req, accept_phylink_complete); } void amp_physical_cfm(struct hci_conn *bredr_hcon, struct hci_conn *hs_hcon) diff --git a/net/bluetooth/amp.h b/net/bluetooth/amp.h index 7ea3db77ba89..8848f8158ae4 100644 --- a/net/bluetooth/amp.h +++ b/net/bluetooth/amp.h @@ -44,6 +44,20 @@ void amp_create_phylink(struct hci_dev *hdev, struct amp_mgr *mgr, struct hci_conn *hcon); void amp_accept_phylink(struct hci_dev *hdev, struct amp_mgr *mgr, struct hci_conn *hcon); + +#if IS_ENABLED(CONFIG_BT_HS) +void amp_create_logical_link(struct l2cap_chan *chan); +void amp_disconnect_logical_link(struct hci_chan *hchan); +#else +static inline void amp_create_logical_link(struct l2cap_chan *chan) +{ +} + +static inline void amp_disconnect_logical_link(struct hci_chan *hchan) +{ +} +#endif + void amp_write_remote_assoc(struct hci_dev *hdev, u8 handle); void amp_write_rem_assoc_continue(struct hci_dev *hdev, u8 handle); void amp_physical_cfm(struct hci_conn *bredr_hcon, struct hci_conn *hs_hcon); diff --git a/net/bluetooth/cmtp/capi.c b/net/bluetooth/cmtp/capi.c index b0c6c6af76ef..9a50338772f3 100644 --- a/net/bluetooth/cmtp/capi.c +++ b/net/bluetooth/cmtp/capi.c @@ -100,9 +100,9 @@ static void cmtp_application_del(struct cmtp_session *session, struct cmtp_appli static struct cmtp_application *cmtp_application_get(struct cmtp_session *session, int pattern, __u16 value) { struct cmtp_application *app; - struct list_head *p, *n; + struct list_head *p; - list_for_each_safe(p, n, &session->applications) { + list_for_each(p, &session->applications) { app = list_entry(p, struct cmtp_application, list); switch (pattern) { case CMTP_MSGNUM: @@ -511,13 +511,13 @@ static int cmtp_proc_show(struct seq_file *m, void *v) struct capi_ctr *ctrl = m->private; struct cmtp_session *session = ctrl->driverdata; struct cmtp_application *app; - struct list_head *p, *n; + struct list_head *p; seq_printf(m, "%s\n\n", cmtp_procinfo(ctrl)); seq_printf(m, "addr %s\n", session->name); seq_printf(m, "ctrl %d\n", session->num); - list_for_each_safe(p, n, &session->applications) { + list_for_each(p, &session->applications) { app = list_entry(p, struct cmtp_application, list); seq_printf(m, "appl %d -> %d\n", app->appl, app->mapping); } diff --git a/net/bluetooth/hci_conn.c b/net/bluetooth/hci_conn.c index 2c48bf0b5afb..b4548c739a64 100644 --- a/net/bluetooth/hci_conn.c +++ b/net/bluetooth/hci_conn.c @@ -64,6 +64,48 @@ static void hci_le_create_connection_cancel(struct hci_conn *conn) hci_send_cmd(conn->hdev, HCI_OP_LE_CREATE_CONN_CANCEL, 0, NULL); } +/* This function requires the caller holds hdev->lock */ +static void hci_connect_le_scan_cleanup(struct hci_conn *conn) +{ + struct hci_conn_params *params; + struct smp_irk *irk; + bdaddr_t *bdaddr; + u8 bdaddr_type; + + bdaddr = &conn->dst; + bdaddr_type = conn->dst_type; + + /* Check if we need to convert to identity address */ + irk = hci_get_irk(conn->hdev, bdaddr, bdaddr_type); + if (irk) { + bdaddr = &irk->bdaddr; + bdaddr_type = irk->addr_type; + } + + params = hci_explicit_connect_lookup(conn->hdev, bdaddr, bdaddr_type); + if (!params) + return; + + /* The connection attempt was doing scan for new RPA, and is + * in scan phase. If params are not associated with any other + * autoconnect action, remove them completely. If they are, just unmark + * them as waiting for connection, by clearing explicit_connect field. + */ + if (params->auto_connect == HCI_AUTO_CONN_EXPLICIT) + hci_conn_params_del(conn->hdev, bdaddr, bdaddr_type); + else + params->explicit_connect = false; +} + +/* This function requires the caller holds hdev->lock */ +static void hci_connect_le_scan_remove(struct hci_conn *conn) +{ + hci_connect_le_scan_cleanup(conn); + + hci_conn_hash_del(conn->hdev, conn); + hci_update_background_scan(conn->hdev); +} + static void hci_acl_create_connection(struct hci_conn *conn) { struct hci_dev *hdev = conn->hdev; @@ -340,8 +382,12 @@ static void hci_conn_timeout(struct work_struct *work) if (conn->out) { if (conn->type == ACL_LINK) hci_acl_create_connection_cancel(conn); - else if (conn->type == LE_LINK) - hci_le_create_connection_cancel(conn); + else if (conn->type == LE_LINK) { + if (test_bit(HCI_CONN_SCANNING, &conn->flags)) + hci_connect_le_scan_remove(conn); + else + hci_le_create_connection_cancel(conn); + } } else if (conn->type == SCO_LINK || conn->type == ESCO_LINK) { hci_reject_sco(conn); } @@ -637,15 +683,18 @@ static void create_le_conn_complete(struct hci_dev *hdev, u8 status, u16 opcode) { struct hci_conn *conn; - if (status == 0) - return; + hci_dev_lock(hdev); + + conn = hci_lookup_le_connect(hdev); + + if (!status) { + hci_connect_le_scan_cleanup(conn); + goto done; + } BT_ERR("HCI request failed to create LE connection: status 0x%2.2x", status); - hci_dev_lock(hdev); - - conn = hci_conn_hash_lookup_state(hdev, LE_LINK, BT_CONNECT); if (!conn) goto done; @@ -685,6 +734,7 @@ static void hci_req_add_le_create_conn(struct hci_request *req, hci_req_add(req, HCI_OP_LE_CREATE_CONN, sizeof(cp), &cp); conn->state = BT_CONNECT; + clear_bit(HCI_CONN_SCANNING, &conn->flags); } static void hci_req_directed_advertising(struct hci_request *req, @@ -728,7 +778,7 @@ struct hci_conn *hci_connect_le(struct hci_dev *hdev, bdaddr_t *dst, u8 role) { struct hci_conn_params *params; - struct hci_conn *conn; + struct hci_conn *conn, *conn_unfinished; struct smp_irk *irk; struct hci_request req; int err; @@ -751,26 +801,29 @@ struct hci_conn *hci_connect_le(struct hci_dev *hdev, bdaddr_t *dst, * and return the object found. */ conn = hci_conn_hash_lookup_ba(hdev, LE_LINK, dst); + conn_unfinished = NULL; if (conn) { - conn->pending_sec_level = sec_level; - goto done; + if (conn->state == BT_CONNECT && + test_bit(HCI_CONN_SCANNING, &conn->flags)) { + BT_DBG("will continue unfinished conn %pMR", dst); + conn_unfinished = conn; + } else { + if (conn->pending_sec_level < sec_level) + conn->pending_sec_level = sec_level; + goto done; + } } /* Since the controller supports only one LE connection attempt at a * time, we return -EBUSY if there is any connection attempt running. */ - conn = hci_conn_hash_lookup_state(hdev, LE_LINK, BT_CONNECT); - if (conn) + if (hci_lookup_le_connect(hdev)) return ERR_PTR(-EBUSY); /* When given an identity address with existing identity * resolving key, the connection needs to be established * to a resolvable random address. * - * This uses the cached random resolvable address from - * a previous scan. When no cached address is available, - * try connecting to the identity address instead. - * * Storing the resolvable random address is required here * to handle connection failures. The address will later * be resolved back into the original identity address @@ -782,15 +835,23 @@ struct hci_conn *hci_connect_le(struct hci_dev *hdev, bdaddr_t *dst, dst_type = ADDR_LE_DEV_RANDOM; } - conn = hci_conn_add(hdev, LE_LINK, dst, role); + if (conn_unfinished) { + conn = conn_unfinished; + bacpy(&conn->dst, dst); + } else { + conn = hci_conn_add(hdev, LE_LINK, dst, role); + } + if (!conn) return ERR_PTR(-ENOMEM); conn->dst_type = dst_type; conn->sec_level = BT_SECURITY_LOW; - conn->pending_sec_level = sec_level; conn->conn_timeout = conn_timeout; + if (!conn_unfinished) + conn->pending_sec_level = sec_level; + hci_req_init(&req, hdev); /* Disable advertising if we're active. For master role @@ -855,6 +916,144 @@ create_conn: } done: + /* If this is continuation of connect started by hci_connect_le_scan, + * it already called hci_conn_hold and calling it again would mess the + * counter. + */ + if (!conn_unfinished) + hci_conn_hold(conn); + + return conn; +} + +static void hci_connect_le_scan_complete(struct hci_dev *hdev, u8 status, + u16 opcode) +{ + struct hci_conn *conn; + + if (!status) + return; + + BT_ERR("Failed to add device to auto conn whitelist: status 0x%2.2x", + status); + + hci_dev_lock(hdev); + + conn = hci_conn_hash_lookup_state(hdev, LE_LINK, BT_CONNECT); + if (conn) + hci_le_conn_failed(conn, status); + + hci_dev_unlock(hdev); +} + +static bool is_connected(struct hci_dev *hdev, bdaddr_t *addr, u8 type) +{ + struct hci_conn *conn; + + conn = hci_conn_hash_lookup_ba(hdev, LE_LINK, addr); + if (!conn) + return false; + + if (conn->dst_type != type) + return false; + + if (conn->state != BT_CONNECTED) + return false; + + return true; +} + +/* This function requires the caller holds hdev->lock */ +static int hci_explicit_conn_params_set(struct hci_request *req, + bdaddr_t *addr, u8 addr_type) +{ + struct hci_dev *hdev = req->hdev; + struct hci_conn_params *params; + + if (is_connected(hdev, addr, addr_type)) + return -EISCONN; + + params = hci_conn_params_add(hdev, addr, addr_type); + if (!params) + return -EIO; + + /* If we created new params, or existing params were marked as disabled, + * mark them to be used just once to connect. + */ + if (params->auto_connect == HCI_AUTO_CONN_DISABLED) { + params->auto_connect = HCI_AUTO_CONN_EXPLICIT; + list_del_init(¶ms->action); + list_add(¶ms->action, &hdev->pend_le_conns); + } + + params->explicit_connect = true; + __hci_update_background_scan(req); + + BT_DBG("addr %pMR (type %u) auto_connect %u", addr, addr_type, + params->auto_connect); + + return 0; +} + +/* This function requires the caller holds hdev->lock */ +struct hci_conn *hci_connect_le_scan(struct hci_dev *hdev, bdaddr_t *dst, + u8 dst_type, u8 sec_level, + u16 conn_timeout, u8 role) +{ + struct hci_conn *conn; + struct hci_request req; + int err; + + /* Let's make sure that le is enabled.*/ + if (!hci_dev_test_flag(hdev, HCI_LE_ENABLED)) { + if (lmp_le_capable(hdev)) + return ERR_PTR(-ECONNREFUSED); + + return ERR_PTR(-EOPNOTSUPP); + } + + /* Some devices send ATT messages as soon as the physical link is + * established. To be able to handle these ATT messages, the user- + * space first establishes the connection and then starts the pairing + * process. + * + * So if a hci_conn object already exists for the following connection + * attempt, we simply update pending_sec_level and auth_type fields + * and return the object found. + */ + conn = hci_conn_hash_lookup_ba(hdev, LE_LINK, dst); + if (conn) { + if (conn->pending_sec_level < sec_level) + conn->pending_sec_level = sec_level; + goto done; + } + + BT_DBG("requesting refresh of dst_addr"); + + conn = hci_conn_add(hdev, LE_LINK, dst, role); + if (!conn) + return ERR_PTR(-ENOMEM); + + hci_req_init(&req, hdev); + + if (hci_explicit_conn_params_set(&req, dst, dst_type) < 0) + return ERR_PTR(-EBUSY); + + conn->state = BT_CONNECT; + set_bit(HCI_CONN_SCANNING, &conn->flags); + + err = hci_req_run(&req, hci_connect_le_scan_complete); + if (err && err != -ENODATA) { + hci_conn_del(conn); + return ERR_PTR(err); + } + + conn->dst_type = dst_type; + conn->sec_level = BT_SECURITY_LOW; + conn->pending_sec_level = sec_level; + conn->conn_timeout = conn_timeout; + +done: hci_conn_hold(conn); return conn; } diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c index 2f8fb33067e1..adcbc74c2432 100644 --- a/net/bluetooth/hci_core.c +++ b/net/bluetooth/hci_core.c @@ -2822,10 +2822,6 @@ struct hci_conn_params *hci_conn_params_lookup(struct hci_dev *hdev, { struct hci_conn_params *params; - /* The conn params list only contains identity addresses */ - if (!hci_is_identity_address(addr, addr_type)) - return NULL; - list_for_each_entry(params, &hdev->le_conn_params, list) { if (bacmp(¶ms->addr, addr) == 0 && params->addr_type == addr_type) { @@ -2842,10 +2838,6 @@ struct hci_conn_params *hci_pend_le_action_lookup(struct list_head *list, { struct hci_conn_params *param; - /* The list only contains identity addresses */ - if (!hci_is_identity_address(addr, addr_type)) - return NULL; - list_for_each_entry(param, list, action) { if (bacmp(¶m->addr, addr) == 0 && param->addr_type == addr_type) @@ -2856,14 +2848,35 @@ struct hci_conn_params *hci_pend_le_action_lookup(struct list_head *list, } /* This function requires the caller holds hdev->lock */ +struct hci_conn_params *hci_explicit_connect_lookup(struct hci_dev *hdev, + bdaddr_t *addr, + u8 addr_type) +{ + struct hci_conn_params *param; + + list_for_each_entry(param, &hdev->pend_le_conns, action) { + if (bacmp(¶m->addr, addr) == 0 && + param->addr_type == addr_type && + param->explicit_connect) + return param; + } + + list_for_each_entry(param, &hdev->pend_le_reports, action) { + if (bacmp(¶m->addr, addr) == 0 && + param->addr_type == addr_type && + param->explicit_connect) + return param; + } + + return NULL; +} + +/* This function requires the caller holds hdev->lock */ struct hci_conn_params *hci_conn_params_add(struct hci_dev *hdev, bdaddr_t *addr, u8 addr_type) { struct hci_conn_params *params; - if (!hci_is_identity_address(addr, addr_type)) - return NULL; - params = hci_conn_params_lookup(hdev, addr, addr_type); if (params) return params; @@ -2927,6 +2940,15 @@ void hci_conn_params_clear_disabled(struct hci_dev *hdev) list_for_each_entry_safe(params, tmp, &hdev->le_conn_params, list) { if (params->auto_connect != HCI_AUTO_CONN_DISABLED) continue; + + /* If trying to estabilish one time connection to disabled + * device, leave the params, but mark them as just once. + */ + if (params->explicit_connect) { + params->auto_connect = HCI_AUTO_CONN_EXPLICIT; + continue; + } + list_del(¶ms->list); kfree(params); } diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c index 32363c2b7f83..186041866315 100644 --- a/net/bluetooth/hci_event.c +++ b/net/bluetooth/hci_event.c @@ -823,7 +823,7 @@ static void hci_cc_read_local_amp_info(struct hci_dev *hdev, BT_DBG("%s status 0x%2.2x", hdev->name, rp->status); if (rp->status) - goto a2mp_rsp; + return; hdev->amp_status = rp->amp_status; hdev->amp_total_bw = __le32_to_cpu(rp->total_bw); @@ -835,46 +835,6 @@ static void hci_cc_read_local_amp_info(struct hci_dev *hdev, hdev->amp_assoc_size = __le16_to_cpu(rp->max_assoc_size); hdev->amp_be_flush_to = __le32_to_cpu(rp->be_flush_to); hdev->amp_max_flush_to = __le32_to_cpu(rp->max_flush_to); - -a2mp_rsp: - a2mp_send_getinfo_rsp(hdev); -} - -static void hci_cc_read_local_amp_assoc(struct hci_dev *hdev, - struct sk_buff *skb) -{ - struct hci_rp_read_local_amp_assoc *rp = (void *) skb->data; - struct amp_assoc *assoc = &hdev->loc_assoc; - size_t rem_len, frag_len; - - BT_DBG("%s status 0x%2.2x", hdev->name, rp->status); - - if (rp->status) - goto a2mp_rsp; - - frag_len = skb->len - sizeof(*rp); - rem_len = __le16_to_cpu(rp->rem_len); - - if (rem_len > frag_len) { - BT_DBG("frag_len %zu rem_len %zu", frag_len, rem_len); - - memcpy(assoc->data + assoc->offset, rp->frag, frag_len); - assoc->offset += frag_len; - - /* Read other fragments */ - amp_read_loc_assoc_frag(hdev, rp->phy_handle); - - return; - } - - memcpy(assoc->data + assoc->offset, rp->frag, rem_len); - assoc->len = assoc->offset + rem_len; - assoc->offset = 0; - -a2mp_rsp: - /* Send A2MP Rsp when all fragments are received */ - a2mp_send_getampassoc_rsp(hdev, rp->status); - a2mp_send_create_phy_link_req(hdev, rp->status); } static void hci_cc_read_inq_rsp_tx_power(struct hci_dev *hdev, @@ -1099,7 +1059,7 @@ static void hci_cc_le_set_adv_enable(struct hci_dev *hdev, struct sk_buff *skb) hci_dev_set_flag(hdev, HCI_LE_ADV); - conn = hci_conn_hash_lookup_state(hdev, LE_LINK, BT_CONNECT); + conn = hci_lookup_le_connect(hdev); if (conn) queue_delayed_work(hdev->workqueue, &conn->le_conn_timeout, @@ -1409,20 +1369,6 @@ static void hci_cc_set_adv_param(struct hci_dev *hdev, struct sk_buff *skb) hci_dev_unlock(hdev); } -static void hci_cc_write_remote_amp_assoc(struct hci_dev *hdev, - struct sk_buff *skb) -{ - struct hci_rp_write_remote_amp_assoc *rp = (void *) skb->data; - - BT_DBG("%s status 0x%2.2x phy_handle 0x%2.2x", - hdev->name, rp->status, rp->phy_handle); - - if (rp->status) - return; - - amp_write_rem_assoc_continue(hdev, rp->phy_handle); -} - static void hci_cc_read_rssi(struct hci_dev *hdev, struct sk_buff *skb) { struct hci_rp_read_rssi *rp = (void *) skb->data; @@ -1944,47 +1890,6 @@ static void hci_cs_disconnect(struct hci_dev *hdev, u8 status) hci_dev_unlock(hdev); } -static void hci_cs_create_phylink(struct hci_dev *hdev, u8 status) -{ - struct hci_cp_create_phy_link *cp; - - BT_DBG("%s status 0x%2.2x", hdev->name, status); - - cp = hci_sent_cmd_data(hdev, HCI_OP_CREATE_PHY_LINK); - if (!cp) - return; - - hci_dev_lock(hdev); - - if (status) { - struct hci_conn *hcon; - - hcon = hci_conn_hash_lookup_handle(hdev, cp->phy_handle); - if (hcon) - hci_conn_del(hcon); - } else { - amp_write_remote_assoc(hdev, cp->phy_handle); - } - - hci_dev_unlock(hdev); -} - -static void hci_cs_accept_phylink(struct hci_dev *hdev, u8 status) -{ - struct hci_cp_accept_phy_link *cp; - - BT_DBG("%s status 0x%2.2x", hdev->name, status); - - if (status) - return; - - cp = hci_sent_cmd_data(hdev, HCI_OP_ACCEPT_PHY_LINK); - if (!cp) - return; - - amp_write_remote_assoc(hdev, cp->phy_handle); -} - static void hci_cs_le_create_conn(struct hci_dev *hdev, u8 status) { struct hci_cp_le_create_conn *cp; @@ -2998,10 +2903,6 @@ static void hci_cmd_complete_evt(struct hci_dev *hdev, struct sk_buff *skb, hci_cc_read_clock(hdev, skb); break; - case HCI_OP_READ_LOCAL_AMP_ASSOC: - hci_cc_read_local_amp_assoc(hdev, skb); - break; - case HCI_OP_READ_INQ_RSP_TX_POWER: hci_cc_read_inq_rsp_tx_power(hdev, skb); break; @@ -3106,10 +3007,6 @@ static void hci_cmd_complete_evt(struct hci_dev *hdev, struct sk_buff *skb, hci_cc_set_adv_param(hdev, skb); break; - case HCI_OP_WRITE_REMOTE_AMP_ASSOC: - hci_cc_write_remote_amp_assoc(hdev, skb); - break; - case HCI_OP_READ_RSSI: hci_cc_read_rssi(hdev, skb); break; @@ -3193,14 +3090,6 @@ static void hci_cmd_status_evt(struct hci_dev *hdev, struct sk_buff *skb, hci_cs_setup_sync_conn(hdev, ev->status); break; - case HCI_OP_CREATE_PHY_LINK: - hci_cs_create_phylink(hdev, ev->status); - break; - - case HCI_OP_ACCEPT_PHY_LINK: - hci_cs_accept_phylink(hdev, ev->status); - break; - case HCI_OP_SNIFF_MODE: hci_cs_sniff_mode(hdev, ev->status); break; @@ -3837,17 +3726,25 @@ static void hci_sync_conn_complete_evt(struct hci_dev *hdev, if (ev->link_type == ESCO_LINK) goto unlock; + /* When the link type in the event indicates SCO connection + * and lookup of the connection object fails, then check + * if an eSCO connection object exists. + * + * The core limits the synchronous connections to either + * SCO or eSCO. The eSCO connection is preferred and tried + * to be setup first and until successfully established, + * the link type will be hinted as eSCO. + */ conn = hci_conn_hash_lookup_ba(hdev, ESCO_LINK, &ev->bdaddr); if (!conn) goto unlock; - - conn->type = SCO_LINK; } switch (ev->status) { case 0x00: conn->handle = __le16_to_cpu(ev->handle); conn->state = BT_CONNECTED; + conn->type = ev->link_type; hci_debugfs_create_conn(conn); hci_conn_add_sysfs(conn); @@ -4399,6 +4296,23 @@ unlock: hci_dev_unlock(hdev); } +#if IS_ENABLED(CONFIG_BT_HS) +static void hci_chan_selected_evt(struct hci_dev *hdev, struct sk_buff *skb) +{ + struct hci_ev_channel_selected *ev = (void *)skb->data; + struct hci_conn *hcon; + + BT_DBG("%s handle 0x%2.2x", hdev->name, ev->phy_handle); + + skb_pull(skb, sizeof(*ev)); + + hcon = hci_conn_hash_lookup_handle(hdev, ev->phy_handle); + if (!hcon) + return; + + amp_read_loc_assoc_final_data(hdev, hcon); +} + static void hci_phy_link_complete_evt(struct hci_dev *hdev, struct sk_buff *skb) { @@ -4522,6 +4436,7 @@ static void hci_disconn_phylink_complete_evt(struct hci_dev *hdev, hci_dev_unlock(hdev); } +#endif static void hci_le_conn_complete_evt(struct hci_dev *hdev, struct sk_buff *skb) { @@ -4540,7 +4455,7 @@ static void hci_le_conn_complete_evt(struct hci_dev *hdev, struct sk_buff *skb) */ hci_dev_clear_flag(hdev, HCI_LE_ADV); - conn = hci_conn_hash_lookup_state(hdev, LE_LINK, BT_CONNECT); + conn = hci_lookup_le_connect(hdev); if (!conn) { conn = hci_conn_add(hdev, LE_LINK, &ev->bdaddr, ev->role); if (!conn) { @@ -4733,42 +4648,49 @@ static struct hci_conn *check_pending_le_conn(struct hci_dev *hdev, /* If we're not connectable only connect devices that we have in * our pend_le_conns list. */ - params = hci_pend_le_action_lookup(&hdev->pend_le_conns, - addr, addr_type); + params = hci_explicit_connect_lookup(hdev, addr, addr_type); + if (!params) return NULL; - switch (params->auto_connect) { - case HCI_AUTO_CONN_DIRECT: - /* Only devices advertising with ADV_DIRECT_IND are - * triggering a connection attempt. This is allowing - * incoming connections from slave devices. - */ - if (adv_type != LE_ADV_DIRECT_IND) + if (!params->explicit_connect) { + switch (params->auto_connect) { + case HCI_AUTO_CONN_DIRECT: + /* Only devices advertising with ADV_DIRECT_IND are + * triggering a connection attempt. This is allowing + * incoming connections from slave devices. + */ + if (adv_type != LE_ADV_DIRECT_IND) + return NULL; + break; + case HCI_AUTO_CONN_ALWAYS: + /* Devices advertising with ADV_IND or ADV_DIRECT_IND + * are triggering a connection attempt. This means + * that incoming connectioms from slave device are + * accepted and also outgoing connections to slave + * devices are established when found. + */ + break; + default: return NULL; - break; - case HCI_AUTO_CONN_ALWAYS: - /* Devices advertising with ADV_IND or ADV_DIRECT_IND - * are triggering a connection attempt. This means - * that incoming connectioms from slave device are - * accepted and also outgoing connections to slave - * devices are established when found. - */ - break; - default: - return NULL; + } } conn = hci_connect_le(hdev, addr, addr_type, BT_SECURITY_LOW, HCI_LE_AUTOCONN_TIMEOUT, HCI_ROLE_MASTER); if (!IS_ERR(conn)) { - /* Store the pointer since we don't really have any + /* If HCI_AUTO_CONN_EXPLICIT is set, conn is already owned + * by higher layer that tried to connect, if no then + * store the pointer since we don't really have any * other owner of the object besides the params that * triggered it. This way we can abort the connection if * the parameters get removed and keep the reference * count consistent once the connection is established. */ - params->conn = hci_conn_get(conn); + + if (!params->explicit_connect) + params->conn = hci_conn_get(conn); + return conn; } @@ -5206,22 +5128,6 @@ static void hci_le_meta_evt(struct hci_dev *hdev, struct sk_buff *skb) } } -static void hci_chan_selected_evt(struct hci_dev *hdev, struct sk_buff *skb) -{ - struct hci_ev_channel_selected *ev = (void *) skb->data; - struct hci_conn *hcon; - - BT_DBG("%s handle 0x%2.2x", hdev->name, ev->phy_handle); - - skb_pull(skb, sizeof(*ev)); - - hcon = hci_conn_hash_lookup_handle(hdev, ev->phy_handle); - if (!hcon) - return; - - amp_read_loc_assoc_final_data(hdev, hcon); -} - static bool hci_get_cmd_complete(struct hci_dev *hdev, u16 opcode, u8 event, struct sk_buff *skb) { @@ -5442,14 +5348,15 @@ void hci_event_packet(struct hci_dev *hdev, struct sk_buff *skb) hci_le_meta_evt(hdev, skb); break; - case HCI_EV_CHANNEL_SELECTED: - hci_chan_selected_evt(hdev, skb); - break; - case HCI_EV_REMOTE_OOB_DATA_REQUEST: hci_remote_oob_data_request_evt(hdev, skb); break; +#if IS_ENABLED(CONFIG_BT_HS) + case HCI_EV_CHANNEL_SELECTED: + hci_chan_selected_evt(hdev, skb); + break; + case HCI_EV_PHY_LINK_COMPLETE: hci_phy_link_complete_evt(hdev, skb); break; @@ -5465,6 +5372,7 @@ void hci_event_packet(struct hci_dev *hdev, struct sk_buff *skb) case HCI_EV_DISCONN_PHY_LINK_COMPLETE: hci_disconn_phylink_complete_evt(hdev, skb); break; +#endif case HCI_EV_NUM_COMP_BLOCKS: hci_num_comp_blocks_evt(hdev, skb); diff --git a/net/bluetooth/hci_request.c b/net/bluetooth/hci_request.c index d6025d6e6d59..b7369220c9ef 100644 --- a/net/bluetooth/hci_request.c +++ b/net/bluetooth/hci_request.c @@ -317,7 +317,7 @@ static void set_random_addr(struct hci_request *req, bdaddr_t *rpa) * address be updated at the next cycle. */ if (hci_dev_test_flag(hdev, HCI_LE_ADV) || - hci_conn_hash_lookup_state(hdev, LE_LINK, BT_CONNECT)) { + hci_lookup_le_connect(hdev)) { BT_DBG("Deferring random address update"); hci_dev_set_flag(hdev, HCI_RPA_EXPIRED); return; @@ -479,7 +479,6 @@ void hci_update_page_scan(struct hci_dev *hdev) void __hci_update_background_scan(struct hci_request *req) { struct hci_dev *hdev = req->hdev; - struct hci_conn *conn; if (!test_bit(HCI_UP, &hdev->flags) || test_bit(HCI_INIT, &hdev->flags) || @@ -529,8 +528,7 @@ void __hci_update_background_scan(struct hci_request *req) * since some controllers are not able to scan and connect at * the same time. */ - conn = hci_conn_hash_lookup_state(hdev, LE_LINK, BT_CONNECT); - if (conn) + if (hci_lookup_le_connect(hdev)) return; /* If controller is currently scanning, we stop it to ensure we diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c index 45fffa413642..7c65ee200c29 100644 --- a/net/bluetooth/l2cap_core.c +++ b/net/bluetooth/l2cap_core.c @@ -7113,8 +7113,10 @@ int l2cap_chan_connect(struct l2cap_chan *chan, __le16 psm, u16 cid, else role = HCI_ROLE_MASTER; - hcon = hci_connect_le(hdev, dst, dst_type, chan->sec_level, - HCI_LE_CONN_TIMEOUT, role); + hcon = hci_connect_le_scan(hdev, dst, dst_type, + chan->sec_level, + HCI_LE_CONN_TIMEOUT, + role); } else { u8 auth_type = l2cap_get_auth_type(chan); hcon = hci_connect_acl(hdev, dst, chan->sec_level, auth_type); diff --git a/net/bluetooth/l2cap_sock.c b/net/bluetooth/l2cap_sock.c index 244287706f91..586b3d580cfc 100644 --- a/net/bluetooth/l2cap_sock.c +++ b/net/bluetooth/l2cap_sock.c @@ -1054,18 +1054,23 @@ static void l2cap_sock_kill(struct sock *sk) sock_put(sk); } -static int __l2cap_wait_ack(struct sock *sk) +static int __l2cap_wait_ack(struct sock *sk, struct l2cap_chan *chan) { - struct l2cap_chan *chan = l2cap_pi(sk)->chan; DECLARE_WAITQUEUE(wait, current); int err = 0; - int timeo = HZ/5; + int timeo = L2CAP_WAIT_ACK_POLL_PERIOD; + /* Timeout to prevent infinite loop */ + unsigned long timeout = jiffies + L2CAP_WAIT_ACK_TIMEOUT; add_wait_queue(sk_sleep(sk), &wait); set_current_state(TASK_INTERRUPTIBLE); - while (chan->unacked_frames > 0 && chan->conn) { + do { + BT_DBG("Waiting for %d ACKs, timeout %04d ms", + chan->unacked_frames, time_after(jiffies, timeout) ? 0 : + jiffies_to_msecs(timeout - jiffies)); + if (!timeo) - timeo = HZ/5; + timeo = L2CAP_WAIT_ACK_POLL_PERIOD; if (signal_pending(current)) { err = sock_intr_errno(timeo); @@ -1080,7 +1085,15 @@ static int __l2cap_wait_ack(struct sock *sk) err = sock_error(sk); if (err) break; - } + + if (time_after(jiffies, timeout)) { + err = -ENOLINK; + break; + } + + } while (chan->unacked_frames > 0 && + chan->state == BT_CONNECTED); + set_current_state(TASK_RUNNING); remove_wait_queue(sk_sleep(sk), &wait); return err; @@ -1098,7 +1111,12 @@ static int l2cap_sock_shutdown(struct socket *sock, int how) if (!sk) return 0; + /* prevent sk structure from being freed whilst unlocked */ + sock_hold(sk); + chan = l2cap_pi(sk)->chan; + /* prevent chan structure from being freed whilst unlocked */ + l2cap_chan_hold(chan); conn = chan->conn; BT_DBG("chan %p state %s", chan, state_to_string(chan->state)); @@ -1110,8 +1128,10 @@ static int l2cap_sock_shutdown(struct socket *sock, int how) lock_sock(sk); if (!sk->sk_shutdown) { - if (chan->mode == L2CAP_MODE_ERTM) - err = __l2cap_wait_ack(sk); + if (chan->mode == L2CAP_MODE_ERTM && + chan->unacked_frames > 0 && + chan->state == BT_CONNECTED) + err = __l2cap_wait_ack(sk, chan); sk->sk_shutdown = SHUTDOWN_MASK; @@ -1134,6 +1154,11 @@ static int l2cap_sock_shutdown(struct socket *sock, int how) if (conn) mutex_unlock(&conn->chan_lock); + l2cap_chan_put(chan); + sock_put(sk); + + BT_DBG("err: %d", err); + return err; } diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c index 92720f3fe573..ccaf5a436d8f 100644 --- a/net/bluetooth/mgmt.c +++ b/net/bluetooth/mgmt.c @@ -3564,9 +3564,10 @@ static int pair_device(struct sock *sk, struct hci_dev *hdev, void *data, */ hci_conn_params_add(hdev, &cp->addr.bdaddr, addr_type); - conn = hci_connect_le(hdev, &cp->addr.bdaddr, addr_type, - sec_level, HCI_LE_CONN_TIMEOUT, - HCI_ROLE_MASTER); + conn = hci_connect_le_scan(hdev, &cp->addr.bdaddr, + addr_type, sec_level, + HCI_LE_CONN_TIMEOUT, + HCI_ROLE_MASTER); } if (IS_ERR(conn)) { @@ -4210,7 +4211,7 @@ static bool trigger_le_scan(struct hci_request *req, u16 interval, u8 *status) /* Don't let discovery abort an outgoing connection attempt * that's using directed advertising. */ - if (hci_conn_hash_lookup_state(hdev, LE_LINK, BT_CONNECT)) { + if (hci_lookup_le_connect(hdev)) { *status = MGMT_STATUS_REJECTED; return false; } @@ -6107,6 +6108,12 @@ static int hci_conn_params_set(struct hci_request *req, bdaddr_t *addr, switch (auto_connect) { case HCI_AUTO_CONN_DISABLED: case HCI_AUTO_CONN_LINK_LOSS: + /* If auto connect is being disabled when we're trying to + * connect to device, keep connecting. + */ + if (params->explicit_connect) + list_add(¶ms->action, &hdev->pend_le_conns); + __hci_update_background_scan(req); break; case HCI_AUTO_CONN_REPORT: @@ -6226,6 +6233,17 @@ static int add_device(struct sock *sk, struct hci_dev *hdev, else auto_conn = HCI_AUTO_CONN_REPORT; + /* Kernel internally uses conn_params with resolvable private + * address, but Add Device allows only identity addresses. + * Make sure it is enforced before calling + * hci_conn_params_lookup. + */ + if (!hci_is_identity_address(&cp->addr.bdaddr, addr_type)) { + err = cmd->cmd_complete(cmd, MGMT_STATUS_INVALID_PARAMS); + mgmt_pending_remove(cmd); + goto unlock; + } + /* If the connection parameters don't exist for this device, * they will be created and configured with defaults. */ @@ -6340,6 +6358,18 @@ static int remove_device(struct sock *sk, struct hci_dev *hdev, else addr_type = ADDR_LE_DEV_RANDOM; + /* Kernel internally uses conn_params with resolvable private + * address, but Remove Device allows only identity addresses. + * Make sure it is enforced before calling + * hci_conn_params_lookup. + */ + if (!hci_is_identity_address(&cp->addr.bdaddr, addr_type)) { + err = cmd->cmd_complete(cmd, + MGMT_STATUS_INVALID_PARAMS); + mgmt_pending_remove(cmd); + goto unlock; + } + params = hci_conn_params_lookup(hdev, &cp->addr.bdaddr, addr_type); if (!params) { diff --git a/net/bluetooth/sco.c b/net/bluetooth/sco.c index 688a040c5626..f315c8d0e43b 100644 --- a/net/bluetooth/sco.c +++ b/net/bluetooth/sco.c @@ -154,13 +154,13 @@ static void sco_chan_del(struct sock *sk, int err) sock_set_flag(sk, SOCK_ZAPPED); } -static int sco_conn_del(struct hci_conn *hcon, int err) +static void sco_conn_del(struct hci_conn *hcon, int err) { struct sco_conn *conn = hcon->sco_data; struct sock *sk; if (!conn) - return 0; + return; BT_DBG("hcon %p conn %p, err %d", hcon, conn, err); @@ -179,7 +179,6 @@ static int sco_conn_del(struct hci_conn *hcon, int err) hcon->sco_data = NULL; kfree(conn); - return 0; } static void __sco_chan_add(struct sco_conn *conn, struct sock *sk, struct sock *parent) diff --git a/net/bridge/br_device.c b/net/bridge/br_device.c index 4ff77a16956c..6ed2feb51e3c 100644 --- a/net/bridge/br_device.c +++ b/net/bridge/br_device.c @@ -339,6 +339,7 @@ static const struct net_device_ops br_netdev_ops = { .ndo_bridge_getlink = br_getlink, .ndo_bridge_setlink = br_setlink, .ndo_bridge_dellink = br_dellink, + .ndo_features_check = passthru_features_check, }; static void br_dev_free(struct net_device *dev) @@ -364,8 +365,7 @@ void br_dev_setup(struct net_device *dev) dev->destructor = br_dev_free; dev->ethtool_ops = &br_ethtool_ops; SET_NETDEV_DEVTYPE(dev, &br_type); - dev->tx_queue_len = 0; - dev->priv_flags = IFF_EBRIDGE; + dev->priv_flags = IFF_EBRIDGE | IFF_NO_QUEUE; dev->features = COMMON_FEATURES | NETIF_F_LLTX | NETIF_F_NETNS_LOCAL | NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_STAG_TX; diff --git a/net/bridge/br_if.c b/net/bridge/br_if.c index a538cb1199a3..45e4757c6fd2 100644 --- a/net/bridge/br_if.c +++ b/net/bridge/br_if.c @@ -281,6 +281,7 @@ void br_dev_delete(struct net_device *dev, struct list_head *head) br_fdb_delete_by_port(br, NULL, 0, 1); br_vlan_flush(br); + br_multicast_dev_del(br); del_timer_sync(&br->gc_timer); br_sysfs_delbr(br->dev); diff --git a/net/bridge/br_mdb.c b/net/bridge/br_mdb.c index c94321955db7..d747275fad18 100644 --- a/net/bridge/br_mdb.c +++ b/net/bridge/br_mdb.c @@ -85,6 +85,7 @@ static int br_mdb_fill_info(struct sk_buff *skb, struct netlink_callback *cb, memset(&e, 0, sizeof(e)); e.ifindex = port->dev->ifindex; e.state = p->state; + e.vid = p->addr.vid; if (p->addr.proto == htons(ETH_P_IP)) e.addr.u.ip4 = p->addr.u.ip4; #if IS_ENABLED(CONFIG_IPV6) @@ -230,7 +231,7 @@ errout: } void br_mdb_notify(struct net_device *dev, struct net_bridge_port *port, - struct br_ip *group, int type) + struct br_ip *group, int type, u8 state) { struct br_mdb_entry entry; @@ -241,9 +242,78 @@ void br_mdb_notify(struct net_device *dev, struct net_bridge_port *port, #if IS_ENABLED(CONFIG_IPV6) entry.addr.u.ip6 = group->u.ip6; #endif + entry.state = state; + entry.vid = group->vid; __br_mdb_notify(dev, &entry, type); } +static int nlmsg_populate_rtr_fill(struct sk_buff *skb, + struct net_device *dev, + int ifindex, u32 pid, + u32 seq, int type, unsigned int flags) +{ + struct br_port_msg *bpm; + struct nlmsghdr *nlh; + struct nlattr *nest; + + nlh = nlmsg_put(skb, pid, seq, type, sizeof(*bpm), NLM_F_MULTI); + if (!nlh) + return -EMSGSIZE; + + bpm = nlmsg_data(nlh); + memset(bpm, 0, sizeof(*bpm)); + bpm->family = AF_BRIDGE; + bpm->ifindex = dev->ifindex; + nest = nla_nest_start(skb, MDBA_ROUTER); + if (!nest) + goto cancel; + + if (nla_put_u32(skb, MDBA_ROUTER_PORT, ifindex)) + goto end; + + nla_nest_end(skb, nest); + nlmsg_end(skb, nlh); + return 0; + +end: + nla_nest_end(skb, nest); +cancel: + nlmsg_cancel(skb, nlh); + return -EMSGSIZE; +} + +static inline size_t rtnl_rtr_nlmsg_size(void) +{ + return NLMSG_ALIGN(sizeof(struct br_port_msg)) + + nla_total_size(sizeof(__u32)); +} + +void br_rtr_notify(struct net_device *dev, struct net_bridge_port *port, + int type) +{ + struct net *net = dev_net(dev); + struct sk_buff *skb; + int err = -ENOBUFS; + int ifindex; + + ifindex = port ? port->dev->ifindex : 0; + skb = nlmsg_new(rtnl_rtr_nlmsg_size(), GFP_ATOMIC); + if (!skb) + goto errout; + + err = nlmsg_populate_rtr_fill(skb, dev, ifindex, 0, 0, type, NTF_SELF); + if (err < 0) { + kfree_skb(skb); + goto errout; + } + + rtnl_notify(skb, net, 0, RTNLGRP_MDB, NULL, GFP_ATOMIC); + return; + +errout: + rtnl_set_sk_err(net, RTNLGRP_MDB, err); +} + static bool is_valid_mdb_entry(struct br_mdb_entry *entry) { if (entry->ifindex == 0) @@ -263,6 +333,8 @@ static bool is_valid_mdb_entry(struct br_mdb_entry *entry) return false; if (entry->state != MDB_PERMANENT && entry->state != MDB_TEMPORARY) return false; + if (entry->vid >= VLAN_VID_MASK) + return false; return true; } @@ -374,6 +446,7 @@ static int __br_mdb_add(struct net *net, struct net_bridge *br, return -EINVAL; memset(&ip, 0, sizeof(ip)); + ip.vid = entry->vid; ip.proto = entry->addr.proto; if (ip.proto == htons(ETH_P_IP)) ip.u.ip4 = entry->addr.u.ip4; @@ -391,8 +464,11 @@ static int __br_mdb_add(struct net *net, struct net_bridge *br, static int br_mdb_add(struct sk_buff *skb, struct nlmsghdr *nlh) { struct net *net = sock_net(skb->sk); + unsigned short vid = VLAN_N_VID; + struct net_device *dev, *pdev; struct br_mdb_entry *entry; - struct net_device *dev; + struct net_bridge_port *p; + struct net_port_vlans *pv; struct net_bridge *br; int err; @@ -402,9 +478,32 @@ static int br_mdb_add(struct sk_buff *skb, struct nlmsghdr *nlh) br = netdev_priv(dev); - err = __br_mdb_add(net, br, entry); - if (!err) - __br_mdb_notify(dev, entry, RTM_NEWMDB); + /* If vlan filtering is enabled and VLAN is not specified + * install mdb entry on all vlans configured on the port. + */ + pdev = __dev_get_by_index(net, entry->ifindex); + if (!pdev) + return -ENODEV; + + p = br_port_get_rtnl(pdev); + if (!p || p->br != br || p->state == BR_STATE_DISABLED) + return -EINVAL; + + pv = nbp_get_vlan_info(p); + if (br_vlan_enabled(br) && pv && entry->vid == 0) { + for_each_set_bit(vid, pv->vlan_bitmap, VLAN_N_VID) { + entry->vid = vid; + err = __br_mdb_add(net, br, entry); + if (err) + break; + __br_mdb_notify(dev, entry, RTM_NEWMDB); + } + } else { + err = __br_mdb_add(net, br, entry); + if (!err) + __br_mdb_notify(dev, entry, RTM_NEWMDB); + } + return err; } @@ -421,6 +520,7 @@ static int __br_mdb_del(struct net_bridge *br, struct br_mdb_entry *entry) return -EINVAL; memset(&ip, 0, sizeof(ip)); + ip.vid = entry->vid; ip.proto = entry->addr.proto; if (ip.proto == htons(ETH_P_IP)) ip.u.ip4 = entry->addr.u.ip4; @@ -465,8 +565,12 @@ unlock: static int br_mdb_del(struct sk_buff *skb, struct nlmsghdr *nlh) { - struct net_device *dev; + struct net *net = sock_net(skb->sk); + unsigned short vid = VLAN_N_VID; + struct net_device *dev, *pdev; struct br_mdb_entry *entry; + struct net_bridge_port *p; + struct net_port_vlans *pv; struct net_bridge *br; int err; @@ -476,9 +580,31 @@ static int br_mdb_del(struct sk_buff *skb, struct nlmsghdr *nlh) br = netdev_priv(dev); - err = __br_mdb_del(br, entry); - if (!err) - __br_mdb_notify(dev, entry, RTM_DELMDB); + /* If vlan filtering is enabled and VLAN is not specified + * delete mdb entry on all vlans configured on the port. + */ + pdev = __dev_get_by_index(net, entry->ifindex); + if (!pdev) + return -ENODEV; + + p = br_port_get_rtnl(pdev); + if (!p || p->br != br || p->state == BR_STATE_DISABLED) + return -EINVAL; + + pv = nbp_get_vlan_info(p); + if (br_vlan_enabled(br) && pv && entry->vid == 0) { + for_each_set_bit(vid, pv->vlan_bitmap, VLAN_N_VID) { + entry->vid = vid; + err = __br_mdb_del(br, entry); + if (!err) + __br_mdb_notify(dev, entry, RTM_DELMDB); + } + } else { + err = __br_mdb_del(br, entry); + if (!err) + __br_mdb_notify(dev, entry, RTM_DELMDB); + } + return err; } diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c index 1285eaf5dc22..66efdc21f548 100644 --- a/net/bridge/br_multicast.c +++ b/net/bridge/br_multicast.c @@ -283,6 +283,8 @@ static void br_multicast_del_pg(struct net_bridge *br, rcu_assign_pointer(*pp, p->next); hlist_del_init(&p->mglist); del_timer(&p->timer); + br_mdb_notify(br->dev, p->port, &pg->addr, RTM_DELMDB, + p->state); call_rcu_bh(&p->rcu, br_multicast_free_pg); if (!mp->ports && !mp->mglist && @@ -704,7 +706,7 @@ static int br_multicast_add_group(struct net_bridge *br, if (unlikely(!p)) goto err; rcu_assign_pointer(*pp, p); - br_mdb_notify(br->dev, port, group, RTM_NEWMDB); + br_mdb_notify(br->dev, port, group, RTM_NEWMDB, MDB_TEMPORARY); found: mod_timer(&p->timer, now + br->multicast_membership_interval); @@ -764,6 +766,7 @@ static void br_multicast_router_expired(unsigned long data) goto out; hlist_del_init_rcu(&port->rlist); + br_rtr_notify(br->dev, port, RTM_DELMDB); out: spin_unlock(&br->multicast_lock); @@ -924,6 +927,15 @@ void br_multicast_add_port(struct net_bridge_port *port) void br_multicast_del_port(struct net_bridge_port *port) { + struct net_bridge *br = port->br; + struct net_bridge_port_group *pg; + struct hlist_node *n; + + /* Take care of the remaining groups, only perm ones should be left */ + spin_lock_bh(&br->multicast_lock); + hlist_for_each_entry_safe(pg, n, &port->mglist, mglist) + br_multicast_del_pg(br, pg); + spin_unlock_bh(&br->multicast_lock); del_timer_sync(&port->multicast_router_timer); } @@ -963,10 +975,13 @@ void br_multicast_disable_port(struct net_bridge_port *port) spin_lock(&br->multicast_lock); hlist_for_each_entry_safe(pg, n, &port->mglist, mglist) - br_multicast_del_pg(br, pg); + if (pg->state == MDB_TEMPORARY) + br_multicast_del_pg(br, pg); - if (!hlist_unhashed(&port->rlist)) + if (!hlist_unhashed(&port->rlist)) { hlist_del_init_rcu(&port->rlist); + br_rtr_notify(br->dev, port, RTM_DELMDB); + } del_timer(&port->multicast_router_timer); del_timer(&port->ip4_own_query.timer); #if IS_ENABLED(CONFIG_IPV6) @@ -1204,6 +1219,7 @@ static void br_multicast_add_router(struct net_bridge *br, hlist_add_behind_rcu(&port->rlist, slot); else hlist_add_head_rcu(&port->rlist, &br->router_list); + br_rtr_notify(br->dev, port, RTM_NEWMDB); } static void br_multicast_mark_router(struct net_bridge *br, @@ -1437,7 +1453,8 @@ br_multicast_leave_group(struct net_bridge *br, hlist_del_init(&p->mglist); del_timer(&p->timer); call_rcu_bh(&p->rcu, br_multicast_free_pg); - br_mdb_notify(br->dev, port, group, RTM_DELMDB); + br_mdb_notify(br->dev, port, group, RTM_DELMDB, + p->state); if (!mp->ports && !mp->mglist && netif_running(br->dev)) @@ -1754,12 +1771,6 @@ void br_multicast_open(struct net_bridge *br) void br_multicast_stop(struct net_bridge *br) { - struct net_bridge_mdb_htable *mdb; - struct net_bridge_mdb_entry *mp; - struct hlist_node *n; - u32 ver; - int i; - del_timer_sync(&br->multicast_router_timer); del_timer_sync(&br->ip4_other_query.timer); del_timer_sync(&br->ip4_own_query.timer); @@ -1767,6 +1778,15 @@ void br_multicast_stop(struct net_bridge *br) del_timer_sync(&br->ip6_other_query.timer); del_timer_sync(&br->ip6_own_query.timer); #endif +} + +void br_multicast_dev_del(struct net_bridge *br) +{ + struct net_bridge_mdb_htable *mdb; + struct net_bridge_mdb_entry *mp; + struct hlist_node *n; + u32 ver; + int i; spin_lock_bh(&br->multicast_lock); mdb = mlock_dereference(br->mdb, br); @@ -1834,8 +1854,10 @@ int br_multicast_set_port_router(struct net_bridge_port *p, unsigned long val) p->multicast_router = val; err = 0; - if (val < 2 && !hlist_unhashed(&p->rlist)) + if (val < 2 && !hlist_unhashed(&p->rlist)) { hlist_del_init_rcu(&p->rlist); + br_rtr_notify(br->dev, p, RTM_DELMDB); + } if (val == 1) break; diff --git a/net/bridge/br_netfilter_hooks.c b/net/bridge/br_netfilter_hooks.c index c8b9bcfe997e..0a6f095bb0c9 100644 --- a/net/bridge/br_netfilter_hooks.c +++ b/net/bridge/br_netfilter_hooks.c @@ -49,9 +49,9 @@ static struct ctl_table_header *brnf_sysctl_header; static int brnf_call_iptables __read_mostly = 1; static int brnf_call_ip6tables __read_mostly = 1; static int brnf_call_arptables __read_mostly = 1; -static int brnf_filter_vlan_tagged __read_mostly = 0; -static int brnf_filter_pppoe_tagged __read_mostly = 0; -static int brnf_pass_vlan_indev __read_mostly = 0; +static int brnf_filter_vlan_tagged __read_mostly; +static int brnf_filter_pppoe_tagged __read_mostly; +static int brnf_pass_vlan_indev __read_mostly; #else #define brnf_call_iptables 1 #define brnf_call_ip6tables 1 @@ -284,7 +284,7 @@ int br_nf_pre_routing_finish_bridge(struct sock *sk, struct sk_buff *skb) nf_bridge->neigh_header, ETH_HLEN-ETH_ALEN); /* tell br_dev_xmit to continue with forwarding */ - nf_bridge->mask |= BRNF_BRIDGED_DNAT; + nf_bridge->bridged_dnat = 1; /* FIXME Need to refragment */ ret = neigh->output(neigh, skb); } @@ -356,7 +356,7 @@ static int br_nf_pre_routing_finish(struct sock *sk, struct sk_buff *skb) skb->pkt_type = PACKET_OTHERHOST; nf_bridge->pkt_otherhost = false; } - nf_bridge->mask &= ~BRNF_NF_BRIDGE_PREROUTING; + nf_bridge->in_prerouting = 0; if (br_nf_ipv4_daddr_was_changed(skb, nf_bridge)) { if ((err = ip_route_input(skb, iph->daddr, iph->saddr, iph->tos, dev))) { struct in_device *in_dev = __in_dev_get_rcu(dev); @@ -444,7 +444,7 @@ struct net_device *setup_pre_routing(struct sk_buff *skb) nf_bridge->pkt_otherhost = true; } - nf_bridge->mask |= BRNF_NF_BRIDGE_PREROUTING; + nf_bridge->in_prerouting = 1; nf_bridge->physindev = skb->dev; skb->dev = brnf_get_logical_dev(skb, skb->dev); @@ -850,10 +850,8 @@ static unsigned int ip_sabotage_in(const struct nf_hook_ops *ops, struct sk_buff *skb, const struct nf_hook_state *state) { - if (skb->nf_bridge && - !(skb->nf_bridge->mask & BRNF_NF_BRIDGE_PREROUTING)) { + if (skb->nf_bridge && !skb->nf_bridge->in_prerouting) return NF_STOP; - } return NF_ACCEPT; } @@ -872,7 +870,7 @@ static void br_nf_pre_routing_finish_bridge_slow(struct sk_buff *skb) struct nf_bridge_info *nf_bridge = nf_bridge_info_get(skb); skb_pull(skb, ETH_HLEN); - nf_bridge->mask &= ~BRNF_BRIDGED_DNAT; + nf_bridge->bridged_dnat = 0; BUILD_BUG_ON(sizeof(nf_bridge->neigh_header) != (ETH_HLEN - ETH_ALEN)); @@ -887,7 +885,7 @@ static void br_nf_pre_routing_finish_bridge_slow(struct sk_buff *skb) static int br_nf_dev_xmit(struct sk_buff *skb) { - if (skb->nf_bridge && (skb->nf_bridge->mask & BRNF_BRIDGED_DNAT)) { + if (skb->nf_bridge && skb->nf_bridge->bridged_dnat) { br_nf_pre_routing_finish_bridge_slow(skb); return 1; } diff --git a/net/bridge/br_netfilter_ipv6.c b/net/bridge/br_netfilter_ipv6.c index 13b7d1e3d185..77383bfe7ea3 100644 --- a/net/bridge/br_netfilter_ipv6.c +++ b/net/bridge/br_netfilter_ipv6.c @@ -174,7 +174,7 @@ static int br_nf_pre_routing_finish_ipv6(struct sock *sk, struct sk_buff *skb) skb->pkt_type = PACKET_OTHERHOST; nf_bridge->pkt_otherhost = false; } - nf_bridge->mask &= ~BRNF_NF_BRIDGE_PREROUTING; + nf_bridge->in_prerouting = 0; if (br_nf_ipv6_daddr_was_changed(skb, nf_bridge)) { skb_dst_drop(skb); v6ops->route_input(skb); diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c index 4d74a0639c4c..ea748c93a07f 100644 --- a/net/bridge/br_netlink.c +++ b/net/bridge/br_netlink.c @@ -16,7 +16,6 @@ #include <net/rtnetlink.h> #include <net/net_namespace.h> #include <net/sock.h> -#include <net/switchdev.h> #include <uapi/linux/if_bridge.h> #include "br_private.h" @@ -166,8 +165,6 @@ static int br_fill_ifvlaninfo_range(struct sk_buff *skb, u16 vid_start, sizeof(vinfo), &vinfo)) goto nla_put_failure; - vinfo.flags &= ~BRIDGE_VLAN_INFO_RANGE_BEGIN; - vinfo.vid = vid_end; vinfo.flags = flags | BRIDGE_VLAN_INFO_RANGE_END; if (nla_put(skb, IFLA_BRIDGE_VLAN_INFO, @@ -675,6 +672,21 @@ static int br_validate(struct nlattr *tb[], struct nlattr *data[]) return -EADDRNOTAVAIL; } + if (!data) + return 0; + +#ifdef CONFIG_BRIDGE_VLAN_FILTERING + if (data[IFLA_BR_VLAN_PROTOCOL]) { + switch (nla_get_be16(data[IFLA_BR_VLAN_PROTOCOL])) { + case htons(ETH_P_8021Q): + case htons(ETH_P_8021AD): + break; + default: + return -EPROTONOSUPPORT; + } + } +#endif + return 0; } @@ -730,6 +742,8 @@ static const struct nla_policy br_policy[IFLA_BR_MAX + 1] = { [IFLA_BR_AGEING_TIME] = { .type = NLA_U32 }, [IFLA_BR_STP_STATE] = { .type = NLA_U32 }, [IFLA_BR_PRIORITY] = { .type = NLA_U16 }, + [IFLA_BR_VLAN_FILTERING] = { .type = NLA_U8 }, + [IFLA_BR_VLAN_PROTOCOL] = { .type = NLA_U16 }, }; static int br_changelink(struct net_device *brdev, struct nlattr *tb[], @@ -777,6 +791,24 @@ static int br_changelink(struct net_device *brdev, struct nlattr *tb[], br_stp_set_bridge_priority(br, priority); } + if (data[IFLA_BR_VLAN_FILTERING]) { + u8 vlan_filter = nla_get_u8(data[IFLA_BR_VLAN_FILTERING]); + + err = __br_vlan_filter_toggle(br, vlan_filter); + if (err) + return err; + } + +#ifdef CONFIG_BRIDGE_VLAN_FILTERING + if (data[IFLA_BR_VLAN_PROTOCOL]) { + __be16 vlan_proto = nla_get_be16(data[IFLA_BR_VLAN_PROTOCOL]); + + err = __br_vlan_set_proto(br, vlan_proto); + if (err) + return err; + } +#endif + return 0; } @@ -788,6 +820,10 @@ static size_t br_get_size(const struct net_device *brdev) nla_total_size(sizeof(u32)) + /* IFLA_BR_AGEING_TIME */ nla_total_size(sizeof(u32)) + /* IFLA_BR_STP_STATE */ nla_total_size(sizeof(u16)) + /* IFLA_BR_PRIORITY */ + nla_total_size(sizeof(u8)) + /* IFLA_BR_VLAN_FILTERING */ +#ifdef CONFIG_BRIDGE_VLAN_FILTERING + nla_total_size(sizeof(__be16)) + /* IFLA_BR_VLAN_PROTOCOL */ +#endif 0; } @@ -800,14 +836,21 @@ static int br_fill_info(struct sk_buff *skb, const struct net_device *brdev) u32 ageing_time = jiffies_to_clock_t(br->ageing_time); u32 stp_enabled = br->stp_enabled; u16 priority = (br->bridge_id.prio[0] << 8) | br->bridge_id.prio[1]; + u8 vlan_enabled = br_vlan_enabled(br); if (nla_put_u32(skb, IFLA_BR_FORWARD_DELAY, forward_delay) || nla_put_u32(skb, IFLA_BR_HELLO_TIME, hello_time) || nla_put_u32(skb, IFLA_BR_MAX_AGE, age_time) || nla_put_u32(skb, IFLA_BR_AGEING_TIME, ageing_time) || nla_put_u32(skb, IFLA_BR_STP_STATE, stp_enabled) || - nla_put_u16(skb, IFLA_BR_PRIORITY, priority)) + nla_put_u16(skb, IFLA_BR_PRIORITY, priority) || + nla_put_u8(skb, IFLA_BR_VLAN_FILTERING, vlan_enabled)) + return -EMSGSIZE; + +#ifdef CONFIG_BRIDGE_VLAN_FILTERING + if (nla_put_be16(skb, IFLA_BR_VLAN_PROTOCOL, br->vlan_proto)) return -EMSGSIZE; +#endif return 0; } @@ -839,7 +882,7 @@ struct rtnl_link_ops br_link_ops __read_mostly = { .kind = "bridge", .priv_size = sizeof(struct net_bridge), .setup = br_dev_setup, - .maxtype = IFLA_BRPORT_MAX, + .maxtype = IFLA_BR_MAX, .policy = br_policy, .validate = br_validate, .newlink = br_dev_newlink, diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h index 8b21146b24a0..213baf7aaa93 100644 --- a/net/bridge/br_private.h +++ b/net/bridge/br_private.h @@ -95,15 +95,15 @@ struct net_bridge_fdb_entry struct hlist_node hlist; struct net_bridge_port *dst; - struct rcu_head rcu; unsigned long updated; unsigned long used; mac_addr addr; + __u16 vlan_id; unsigned char is_local:1, is_static:1, added_by_user:1, added_by_external_learn:1; - __u16 vlan_id; + struct rcu_head rcu; }; struct net_bridge_port_group { @@ -466,6 +466,7 @@ void br_multicast_disable_port(struct net_bridge_port *port); void br_multicast_init(struct net_bridge *br); void br_multicast_open(struct net_bridge *br); void br_multicast_stop(struct net_bridge *br); +void br_multicast_dev_del(struct net_bridge *br); void br_multicast_deliver(struct net_bridge_mdb_entry *mdst, struct sk_buff *skb); void br_multicast_forward(struct net_bridge_mdb_entry *mdst, @@ -488,7 +489,9 @@ br_multicast_new_port_group(struct net_bridge_port *port, struct br_ip *group, void br_mdb_init(void); void br_mdb_uninit(void); void br_mdb_notify(struct net_device *dev, struct net_bridge_port *port, - struct br_ip *group, int type); + struct br_ip *group, int type, u8 state); +void br_rtr_notify(struct net_device *dev, struct net_bridge_port *port, + int type); #define mlock_dereference(X, br) \ rcu_dereference_protected(X, lockdep_is_held(&br->multicast_lock)) @@ -565,6 +568,10 @@ static inline void br_multicast_stop(struct net_bridge *br) { } +static inline void br_multicast_dev_del(struct net_bridge *br) +{ +} + static inline void br_multicast_deliver(struct net_bridge_mdb_entry *mdst, struct sk_buff *skb) { @@ -607,7 +614,9 @@ int br_vlan_delete(struct net_bridge *br, u16 vid); void br_vlan_flush(struct net_bridge *br); bool br_vlan_find(struct net_bridge *br, u16 vid); void br_recalculate_fwd_mask(struct net_bridge *br); +int __br_vlan_filter_toggle(struct net_bridge *br, unsigned long val); int br_vlan_filter_toggle(struct net_bridge *br, unsigned long val); +int __br_vlan_set_proto(struct net_bridge *br, __be16 proto); int br_vlan_set_proto(struct net_bridge *br, unsigned long val); int br_vlan_init(struct net_bridge *br); int br_vlan_set_default_pvid(struct net_bridge *br, unsigned long val); @@ -764,6 +773,12 @@ static inline int br_vlan_enabled(struct net_bridge *br) { return 0; } + +static inline int __br_vlan_filter_toggle(struct net_bridge *br, + unsigned long val) +{ + return -EOPNOTSUPP; +} #endif struct nf_br_ops { diff --git a/net/bridge/br_vlan.c b/net/bridge/br_vlan.c index 0d41f81838ff..5f5a02b49a99 100644 --- a/net/bridge/br_vlan.c +++ b/net/bridge/br_vlan.c @@ -117,10 +117,11 @@ out_filt: return err; } -static void __vlan_vid_del(struct net_device *dev, struct net_bridge *br, - u16 vid) +static int __vlan_vid_del(struct net_device *dev, struct net_bridge *br, + u16 vid) { const struct net_device_ops *ops = dev->netdev_ops; + int err = 0; /* If driver uses VLAN ndo ops, use 8021q to delete vid * on device, otherwise try switchdev ops to delete vid. @@ -137,8 +138,12 @@ static void __vlan_vid_del(struct net_device *dev, struct net_bridge *br, }, }; - switchdev_port_obj_del(dev, &vlan_obj); + err = switchdev_port_obj_del(dev, &vlan_obj); + if (err == -EOPNOTSUPP) + err = 0; } + + return err; } static int __vlan_del(struct net_port_vlans *v, u16 vid) @@ -151,7 +156,11 @@ static int __vlan_del(struct net_port_vlans *v, u16 vid) if (v->port_idx) { struct net_bridge_port *p = v->parent.port; - __vlan_vid_del(p->dev, p->br, vid); + int err; + + err = __vlan_vid_del(p->dev, p->br, vid); + if (err) + return err; } clear_bit(vid, v->vlan_bitmap); @@ -468,41 +477,40 @@ void br_recalculate_fwd_mask(struct net_bridge *br) ~(1u << br->group_addr[5]); } -int br_vlan_filter_toggle(struct net_bridge *br, unsigned long val) +int __br_vlan_filter_toggle(struct net_bridge *br, unsigned long val) { - if (!rtnl_trylock()) - return restart_syscall(); - if (br->vlan_enabled == val) - goto unlock; + return 0; br->vlan_enabled = val; br_manage_promisc(br); recalculate_group_addr(br); br_recalculate_fwd_mask(br); -unlock: + return 0; +} + +int br_vlan_filter_toggle(struct net_bridge *br, unsigned long val) +{ + if (!rtnl_trylock()) + return restart_syscall(); + + __br_vlan_filter_toggle(br, val); rtnl_unlock(); + return 0; } -int br_vlan_set_proto(struct net_bridge *br, unsigned long val) +int __br_vlan_set_proto(struct net_bridge *br, __be16 proto) { int err = 0; struct net_bridge_port *p; struct net_port_vlans *pv; - __be16 proto, oldproto; + __be16 oldproto; u16 vid, errvid; - if (val != ETH_P_8021Q && val != ETH_P_8021AD) - return -EPROTONOSUPPORT; - - if (!rtnl_trylock()) - return restart_syscall(); - - proto = htons(val); if (br->vlan_proto == proto) - goto unlock; + return 0; /* Add VLANs for the new proto to the device filter. */ list_for_each_entry(p, &br->port_list, list) { @@ -533,9 +541,7 @@ int br_vlan_set_proto(struct net_bridge *br, unsigned long val) vlan_vid_del(p->dev, oldproto, vid); } -unlock: - rtnl_unlock(); - return err; + return 0; err_filt: errvid = vid; @@ -551,7 +557,23 @@ err_filt: vlan_vid_del(p->dev, proto, vid); } - goto unlock; + return err; +} + +int br_vlan_set_proto(struct net_bridge *br, unsigned long val) +{ + int err; + + if (val != ETH_P_8021Q && val != ETH_P_8021AD) + return -EPROTONOSUPPORT; + + if (!rtnl_trylock()) + return restart_syscall(); + + err = __br_vlan_set_proto(br, htons(val)); + rtnl_unlock(); + + return err; } static bool vlan_default_pvid(struct net_port_vlans *pv, u16 vid) diff --git a/net/bridge/netfilter/ebtables.c b/net/bridge/netfilter/ebtables.c index 18ca4b24c418..48b6b01295de 100644 --- a/net/bridge/netfilter/ebtables.c +++ b/net/bridge/netfilter/ebtables.c @@ -176,7 +176,7 @@ ebt_basic_match(const struct ebt_entry *e, const struct sk_buff *skb, return 0; } -static inline __pure +static inline struct ebt_entry *ebt_next_entry(const struct ebt_entry *entry) { return (void *)entry + entry->next_offset; diff --git a/net/caif/caif_dev.c b/net/caif/caif_dev.c index edbca468fa73..d730a0f68f46 100644 --- a/net/caif/caif_dev.c +++ b/net/caif/caif_dev.c @@ -177,7 +177,7 @@ static int transmit(struct cflayer *layer, struct cfpkt *pkt) skb->protocol = htons(ETH_P_CAIF); /* Check if we need to handle xoff */ - if (likely(caifd->netdev->tx_queue_len == 0)) + if (likely(caifd->netdev->priv_flags & IFF_NO_QUEUE)) goto noxoff; if (unlikely(caifd->xoff)) diff --git a/net/ceph/ceph_common.c b/net/ceph/ceph_common.c index 3f56eefc2a07..54a00d66509e 100644 --- a/net/ceph/ceph_common.c +++ b/net/ceph/ceph_common.c @@ -518,8 +518,11 @@ int ceph_print_client_options(struct seq_file *m, struct ceph_client *client) struct ceph_options *opt = client->options; size_t pos = m->count; - if (opt->name) - seq_printf(m, "name=%s,", opt->name); + if (opt->name) { + seq_puts(m, "name="); + seq_escape(m, opt->name, ", \t\n\\"); + seq_putc(m, ','); + } if (opt->key) seq_puts(m, "secret=<hidden>,"); diff --git a/net/core/Makefile b/net/core/Makefile index fec0856dd6c0..086b01fbe1bd 100644 --- a/net/core/Makefile +++ b/net/core/Makefile @@ -23,3 +23,4 @@ obj-$(CONFIG_NETWORK_PHY_TIMESTAMPING) += timestamping.o obj-$(CONFIG_NET_PTP_CLASSIFY) += ptp_classifier.o obj-$(CONFIG_CGROUP_NET_PRIO) += netprio_cgroup.o obj-$(CONFIG_CGROUP_NET_CLASSID) += netclassid_cgroup.o +obj-$(CONFIG_LWTUNNEL) += lwtunnel.o diff --git a/net/core/dev.c b/net/core/dev.c index a8e4dd430285..877c84834d81 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -3061,6 +3061,16 @@ 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); @@ -3645,15 +3655,15 @@ static inline struct sk_buff *handle_ing(struct sk_buff *skb, qdisc_skb_cb(skb)->pkt_len = skb->len; skb->tc_verd = SET_TC_AT(skb->tc_verd, AT_INGRESS); - qdisc_bstats_update_cpu(cl->q, skb); + qdisc_bstats_cpu_update(cl->q, skb); - switch (tc_classify(skb, cl, &cl_res)) { + switch (tc_classify(skb, cl, &cl_res, false)) { case TC_ACT_OK: case TC_ACT_RECLASSIFY: skb->tc_index = TC_H_MIN(cl_res.classid); break; case TC_ACT_SHOT: - qdisc_qstats_drop_cpu(cl->q); + qdisc_qstats_cpu_drop(cl->q); case TC_ACT_STOLEN: case TC_ACT_QUEUED: kfree_skb(skb); @@ -4985,7 +4995,7 @@ EXPORT_SYMBOL(netdev_all_upper_get_next_dev_rcu); * Gets the next netdev_adjacent->private from the dev's lower neighbour * list, starting from iter position. The caller must hold either hold the * RTNL lock or its own locking that guarantees that the neighbour lower - * list will remain unchainged. + * list will remain unchanged. */ void *netdev_lower_get_next_private(struct net_device *dev, struct list_head **iter) @@ -5040,7 +5050,7 @@ EXPORT_SYMBOL(netdev_lower_get_next_private_rcu); * Gets the next netdev_adjacent from the dev's lower neighbour * list, starting from iter position. The caller must hold RTNL lock or * its own locking that guarantees that the neighbour lower - * list will remain unchainged. + * list will remain unchanged. */ void *netdev_lower_get_next(struct net_device *dev, struct list_head **iter) { @@ -5301,6 +5311,7 @@ static int __netdev_upper_dev_link(struct net_device *dev, struct net_device *upper_dev, bool master, void *private) { + struct netdev_notifier_changeupper_info changeupper_info; struct netdev_adjacent *i, *j, *to_i, *to_j; int ret = 0; @@ -5319,6 +5330,10 @@ static int __netdev_upper_dev_link(struct net_device *dev, if (master && netdev_master_upper_dev_get(dev)) return -EBUSY; + changeupper_info.upper_dev = upper_dev; + changeupper_info.master = master; + changeupper_info.linking = true; + ret = __netdev_adjacent_dev_link_neighbour(dev, upper_dev, private, master); if (ret) @@ -5357,7 +5372,8 @@ static int __netdev_upper_dev_link(struct net_device *dev, goto rollback_lower_mesh; } - call_netdevice_notifiers(NETDEV_CHANGEUPPER, dev); + call_netdevice_notifiers_info(NETDEV_CHANGEUPPER, dev, + &changeupper_info.info); return 0; rollback_lower_mesh: @@ -5452,9 +5468,14 @@ EXPORT_SYMBOL(netdev_master_upper_dev_link_private); void netdev_upper_dev_unlink(struct net_device *dev, struct net_device *upper_dev) { + struct netdev_notifier_changeupper_info changeupper_info; struct netdev_adjacent *i, *j; ASSERT_RTNL(); + changeupper_info.upper_dev = upper_dev; + changeupper_info.master = netdev_master_upper_dev_get(dev) == upper_dev; + changeupper_info.linking = false; + __netdev_adjacent_dev_unlink_neighbour(dev, upper_dev); /* Here is the tricky part. We must remove all dev's lower @@ -5474,7 +5495,8 @@ void netdev_upper_dev_unlink(struct net_device *dev, list_for_each_entry(i, &upper_dev->all_adj_list.upper, list) __netdev_adjacent_dev_unlink(dev, i->dev); - call_netdevice_notifiers(NETDEV_CHANGEUPPER, dev); + call_netdevice_notifiers_info(NETDEV_CHANGEUPPER, dev, + &changeupper_info.info); } EXPORT_SYMBOL(netdev_upper_dev_unlink); @@ -6075,6 +6097,26 @@ int dev_get_phys_port_name(struct net_device *dev, EXPORT_SYMBOL(dev_get_phys_port_name); /** + * dev_change_proto_down - update protocol port state information + * @dev: device + * @proto_down: new value + * + * This info can be used by switch drivers to set the phys state of the + * port. + */ +int dev_change_proto_down(struct net_device *dev, bool proto_down) +{ + const struct net_device_ops *ops = dev->netdev_ops; + + if (!ops->ndo_change_proto_down) + return -EOPNOTSUPP; + if (!netif_device_present(dev)) + return -ENODEV; + return ops->ndo_change_proto_down(dev, proto_down); +} +EXPORT_SYMBOL(dev_change_proto_down); + +/** * dev_new_index - allocate an ifindex * @net: the applicable net namespace * @@ -6967,6 +7009,9 @@ struct net_device *alloc_netdev_mqs(int sizeof_priv, const char *name, dev->priv_flags = IFF_XMIT_DST_RELEASE | IFF_XMIT_DST_RELEASE_PERM; setup(dev); + if (!dev->tx_queue_len) + dev->priv_flags |= IFF_NO_QUEUE; + dev->num_tx_queues = txqs; dev->real_num_tx_queues = txqs; if (netif_alloc_netdev_queues(dev)) @@ -7639,7 +7684,7 @@ static int __init net_dev_init(void) open_softirq(NET_RX_SOFTIRQ, net_rx_action); hotcpu_notifier(dev_cpu_callback, 0); - dst_init(); + dst_subsys_init(); rc = 0; out: return rc; diff --git a/net/core/dst.c b/net/core/dst.c index 002144bea935..0771c8cb9307 100644 --- a/net/core/dst.c +++ b/net/core/dst.c @@ -20,8 +20,10 @@ #include <net/net_namespace.h> #include <linux/sched.h> #include <linux/prefetch.h> +#include <net/lwtunnel.h> #include <net/dst.h> +#include <net/dst_metadata.h> /* * Theory of operations: @@ -158,19 +160,10 @@ const u32 dst_default_metrics[RTAX_MAX + 1] = { [RTAX_MAX] = 0xdeadbeef, }; - -void *dst_alloc(struct dst_ops *ops, struct net_device *dev, - int initial_ref, int initial_obsolete, unsigned short flags) +void dst_init(struct dst_entry *dst, struct dst_ops *ops, + struct net_device *dev, int initial_ref, int initial_obsolete, + unsigned short flags) { - struct dst_entry *dst; - - if (ops->gc && dst_entries_get_fast(ops) > ops->gc_thresh) { - if (ops->gc(ops)) - return NULL; - } - dst = kmem_cache_alloc(ops->kmem_cachep, GFP_ATOMIC); - if (!dst) - return NULL; dst->child = NULL; dst->dev = dev; if (dev) @@ -192,6 +185,7 @@ void *dst_alloc(struct dst_ops *ops, struct net_device *dev, #ifdef CONFIG_IP_ROUTE_CLASSID dst->tclassid = 0; #endif + dst->lwtstate = NULL; atomic_set(&dst->__refcnt, initial_ref); dst->__use = 0; dst->lastuse = jiffies; @@ -200,6 +194,25 @@ void *dst_alloc(struct dst_ops *ops, struct net_device *dev, dst->next = NULL; if (!(flags & DST_NOCOUNT)) dst_entries_add(ops, 1); +} +EXPORT_SYMBOL(dst_init); + +void *dst_alloc(struct dst_ops *ops, struct net_device *dev, + int initial_ref, int initial_obsolete, unsigned short flags) +{ + struct dst_entry *dst; + + if (ops->gc && dst_entries_get_fast(ops) > ops->gc_thresh) { + if (ops->gc(ops)) + return NULL; + } + + dst = kmem_cache_alloc(ops->kmem_cachep, GFP_ATOMIC); + if (!dst) + return NULL; + + dst_init(dst, ops, dev, initial_ref, initial_obsolete, flags); + return dst; } EXPORT_SYMBOL(dst_alloc); @@ -248,7 +261,13 @@ again: dst->ops->destroy(dst); if (dst->dev) dev_put(dst->dev); - kmem_cache_free(dst->ops->kmem_cachep, dst); + + lwtstate_put(dst->lwtstate); + + if (dst->flags & DST_METADATA) + kfree(dst); + else + kmem_cache_free(dst->ops->kmem_cachep, dst); dst = child; if (dst) { @@ -329,6 +348,69 @@ void __dst_destroy_metrics_generic(struct dst_entry *dst, unsigned long old) } EXPORT_SYMBOL(__dst_destroy_metrics_generic); +static struct dst_ops md_dst_ops = { + .family = AF_UNSPEC, +}; + +static int dst_md_discard_sk(struct sock *sk, struct sk_buff *skb) +{ + WARN_ONCE(1, "Attempting to call output on metadata dst\n"); + kfree_skb(skb); + return 0; +} + +static int dst_md_discard(struct sk_buff *skb) +{ + WARN_ONCE(1, "Attempting to call input on metadata dst\n"); + kfree_skb(skb); + return 0; +} + +static void __metadata_dst_init(struct metadata_dst *md_dst, u8 optslen) +{ + struct dst_entry *dst; + + dst = &md_dst->dst; + dst_init(dst, &md_dst_ops, NULL, 1, DST_OBSOLETE_NONE, + DST_METADATA | DST_NOCACHE | DST_NOCOUNT); + + dst->input = dst_md_discard; + dst->output = dst_md_discard_sk; + + memset(dst + 1, 0, sizeof(*md_dst) + optslen - sizeof(*dst)); +} + +struct metadata_dst *metadata_dst_alloc(u8 optslen, gfp_t flags) +{ + struct metadata_dst *md_dst; + + md_dst = kmalloc(sizeof(*md_dst) + optslen, flags); + if (!md_dst) + return NULL; + + __metadata_dst_init(md_dst, optslen); + + return md_dst; +} +EXPORT_SYMBOL_GPL(metadata_dst_alloc); + +struct metadata_dst __percpu *metadata_dst_alloc_percpu(u8 optslen, gfp_t flags) +{ + int cpu; + struct metadata_dst __percpu *md_dst; + + md_dst = __alloc_percpu_gfp(sizeof(struct metadata_dst) + optslen, + __alignof__(struct metadata_dst), flags); + if (!md_dst) + return NULL; + + for_each_possible_cpu(cpu) + __metadata_dst_init(per_cpu_ptr(md_dst, cpu), optslen); + + return md_dst; +} +EXPORT_SYMBOL_GPL(metadata_dst_alloc_percpu); + /* Dirty hack. We did it in 2.2 (in __dst_free), * we have _very_ good reasons not to repeat * this mistake in 2.3, but we have no choice @@ -393,7 +475,7 @@ static struct notifier_block dst_dev_notifier = { .priority = -10, /* must be called after other network notifiers */ }; -void __init dst_init(void) +void __init dst_subsys_init(void) { register_netdevice_notifier(&dst_dev_notifier); } diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c index 9a12668f7d62..bf77e3639ce0 100644 --- a/net/core/fib_rules.c +++ b/net/core/fib_rules.c @@ -16,6 +16,7 @@ #include <net/net_namespace.h> #include <net/sock.h> #include <net/fib_rules.h> +#include <net/ip_tunnels.h> int fib_default_rule_add(struct fib_rules_ops *ops, u32 pref, u32 table, u32 flags) @@ -43,7 +44,7 @@ int fib_default_rule_add(struct fib_rules_ops *ops, } EXPORT_SYMBOL(fib_default_rule_add); -u32 fib_default_rule_pref(struct fib_rules_ops *ops) +static u32 fib_default_rule_pref(struct fib_rules_ops *ops) { struct list_head *pos; struct fib_rule *rule; @@ -59,7 +60,6 @@ u32 fib_default_rule_pref(struct fib_rules_ops *ops) return 0; } -EXPORT_SYMBOL(fib_default_rule_pref); static void notify_rule_change(int event, struct fib_rule *rule, struct fib_rules_ops *ops, struct nlmsghdr *nlh, @@ -186,6 +186,9 @@ static int fib_rule_match(struct fib_rule *rule, struct fib_rules_ops *ops, if ((rule->mark ^ fl->flowi_mark) & rule->mark_mask) goto out; + if (rule->tun_id && (rule->tun_id != fl->flowi_tun_key.tun_id)) + goto out; + ret = ops->match(rule, fl, flags); out: return (rule->flags & FIB_RULE_INVERT) ? !ret : ret; @@ -295,8 +298,8 @@ static int fib_nl_newrule(struct sk_buff *skb, struct nlmsghdr* nlh) } rule->fr_net = net; - if (tb[FRA_PRIORITY]) - rule->pref = nla_get_u32(tb[FRA_PRIORITY]); + rule->pref = tb[FRA_PRIORITY] ? nla_get_u32(tb[FRA_PRIORITY]) + : fib_default_rule_pref(ops); if (tb[FRA_IIFNAME]) { struct net_device *dev; @@ -330,6 +333,9 @@ static int fib_nl_newrule(struct sk_buff *skb, struct nlmsghdr* nlh) if (tb[FRA_FWMASK]) rule->mark_mask = nla_get_u32(tb[FRA_FWMASK]); + if (tb[FRA_TUN_ID]) + rule->tun_id = nla_get_be64(tb[FRA_TUN_ID]); + rule->action = frh->action; rule->flags = frh->flags; rule->table = frh_get_table(frh, tb); @@ -343,9 +349,6 @@ static int fib_nl_newrule(struct sk_buff *skb, struct nlmsghdr* nlh) else rule->suppress_ifgroup = -1; - if (!tb[FRA_PRIORITY] && ops->default_pref) - rule->pref = ops->default_pref(ops); - err = -EINVAL; if (tb[FRA_GOTO]) { if (rule->action != FR_ACT_GOTO) @@ -407,6 +410,9 @@ static int fib_nl_newrule(struct sk_buff *skb, struct nlmsghdr* nlh) if (unresolved) ops->unresolved_rules++; + if (rule->tun_id) + ip_tunnel_need_metadata(); + notify_rule_change(RTM_NEWRULE, rule, ops, nlh, NETLINK_CB(skb).portid); flush_route_cache(ops); rules_ops_put(ops); @@ -473,6 +479,10 @@ static int fib_nl_delrule(struct sk_buff *skb, struct nlmsghdr* nlh) (rule->mark_mask != nla_get_u32(tb[FRA_FWMASK]))) continue; + if (tb[FRA_TUN_ID] && + (rule->tun_id != nla_get_be64(tb[FRA_TUN_ID]))) + continue; + if (!ops->compare(rule, frh, tb)) continue; @@ -487,6 +497,9 @@ static int fib_nl_delrule(struct sk_buff *skb, struct nlmsghdr* nlh) goto errout; } + if (rule->tun_id) + ip_tunnel_unneed_metadata(); + list_del_rcu(&rule->list); if (rule->action == FR_ACT_GOTO) { @@ -535,7 +548,8 @@ static inline size_t fib_rule_nlmsg_size(struct fib_rules_ops *ops, + nla_total_size(4) /* FRA_SUPPRESS_PREFIXLEN */ + nla_total_size(4) /* FRA_SUPPRESS_IFGROUP */ + nla_total_size(4) /* FRA_FWMARK */ - + nla_total_size(4); /* FRA_FWMASK */ + + nla_total_size(4) /* FRA_FWMASK */ + + nla_total_size(8); /* FRA_TUN_ID */ if (ops->nlmsg_payload) payload += ops->nlmsg_payload(rule); @@ -591,7 +605,9 @@ static int fib_nl_fill_rule(struct sk_buff *skb, struct fib_rule *rule, ((rule->mark_mask || rule->mark) && nla_put_u32(skb, FRA_FWMASK, rule->mark_mask)) || (rule->target && - nla_put_u32(skb, FRA_GOTO, rule->target))) + nla_put_u32(skb, FRA_GOTO, rule->target)) || + (rule->tun_id && + nla_put_be64(skb, FRA_TUN_ID, rule->tun_id))) goto nla_put_failure; if (rule->suppress_ifgroup != -1) { diff --git a/net/core/filter.c b/net/core/filter.c index be3098fb65e4..13079f03902e 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -47,6 +47,8 @@ #include <linux/if_vlan.h> #include <linux/bpf.h> #include <net/sch_generic.h> +#include <net/cls_cgroup.h> +#include <net/dst_metadata.h> /** * sk_filter - run a packet through a socket filter @@ -1122,6 +1124,7 @@ int bpf_prog_create_from_user(struct bpf_prog **pfp, struct sock_fprog *fprog, *pfp = fp; return 0; } +EXPORT_SYMBOL_GPL(bpf_prog_create_from_user); void bpf_prog_destroy(struct bpf_prog *fp) { @@ -1346,7 +1349,7 @@ const struct bpf_func_proto bpf_l3_csum_replace_proto = { 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; - u32 is_pseudo = BPF_IS_PSEUDO_HEADER(flags); + bool is_pseudo = !!BPF_IS_PSEUDO_HEADER(flags); int offset = (int) r2; __sum16 sum, *ptr; @@ -1424,6 +1427,139 @@ const struct bpf_func_proto bpf_clone_redirect_proto = { .arg3_type = ARG_ANYTHING, }; +static u64 bpf_get_cgroup_classid(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5) +{ + return task_get_classid((struct sk_buff *) (unsigned long) r1); +} + +static const struct bpf_func_proto bpf_get_cgroup_classid_proto = { + .func = bpf_get_cgroup_classid, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_CTX, +}; + +static u64 bpf_skb_vlan_push(u64 r1, u64 r2, u64 vlan_tci, u64 r4, u64 r5) +{ + struct sk_buff *skb = (struct sk_buff *) (long) r1; + __be16 vlan_proto = (__force __be16) r2; + + if (unlikely(vlan_proto != htons(ETH_P_8021Q) && + vlan_proto != htons(ETH_P_8021AD))) + vlan_proto = htons(ETH_P_8021Q); + + return skb_vlan_push(skb, vlan_proto, vlan_tci); +} + +const struct bpf_func_proto bpf_skb_vlan_push_proto = { + .func = bpf_skb_vlan_push, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_CTX, + .arg2_type = ARG_ANYTHING, + .arg3_type = ARG_ANYTHING, +}; +EXPORT_SYMBOL_GPL(bpf_skb_vlan_push_proto); + +static u64 bpf_skb_vlan_pop(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5) +{ + struct sk_buff *skb = (struct sk_buff *) (long) r1; + + return skb_vlan_pop(skb); +} + +const struct bpf_func_proto bpf_skb_vlan_pop_proto = { + .func = bpf_skb_vlan_pop, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_CTX, +}; +EXPORT_SYMBOL_GPL(bpf_skb_vlan_pop_proto); + +bool bpf_helper_changes_skb_data(void *func) +{ + if (func == bpf_skb_vlan_push) + return true; + if (func == bpf_skb_vlan_pop) + return true; + return false; +} + +static u64 bpf_skb_get_tunnel_key(u64 r1, u64 r2, u64 size, u64 flags, u64 r5) +{ + struct sk_buff *skb = (struct sk_buff *) (long) r1; + struct bpf_tunnel_key *to = (struct bpf_tunnel_key *) (long) r2; + struct ip_tunnel_info *info = skb_tunnel_info(skb); + + if (unlikely(size != sizeof(struct bpf_tunnel_key) || flags || !info)) + return -EINVAL; + if (ip_tunnel_info_af(info) != AF_INET) + return -EINVAL; + + to->tunnel_id = be64_to_cpu(info->key.tun_id); + to->remote_ipv4 = be32_to_cpu(info->key.u.ipv4.src); + + return 0; +} + +const struct bpf_func_proto bpf_skb_get_tunnel_key_proto = { + .func = bpf_skb_get_tunnel_key, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_CTX, + .arg2_type = ARG_PTR_TO_STACK, + .arg3_type = ARG_CONST_STACK_SIZE, + .arg4_type = ARG_ANYTHING, +}; + +static struct metadata_dst __percpu *md_dst; + +static u64 bpf_skb_set_tunnel_key(u64 r1, u64 r2, u64 size, u64 flags, u64 r5) +{ + struct sk_buff *skb = (struct sk_buff *) (long) r1; + struct bpf_tunnel_key *from = (struct bpf_tunnel_key *) (long) r2; + struct metadata_dst *md = this_cpu_ptr(md_dst); + struct ip_tunnel_info *info; + + if (unlikely(size != sizeof(struct bpf_tunnel_key) || flags)) + return -EINVAL; + + skb_dst_drop(skb); + dst_hold((struct dst_entry *) md); + skb_dst_set(skb, (struct dst_entry *) md); + + info = &md->u.tun_info; + info->mode = IP_TUNNEL_INFO_TX; + info->key.tun_flags = TUNNEL_KEY; + info->key.tun_id = cpu_to_be64(from->tunnel_id); + info->key.u.ipv4.dst = cpu_to_be32(from->remote_ipv4); + + return 0; +} + +const struct bpf_func_proto bpf_skb_set_tunnel_key_proto = { + .func = bpf_skb_set_tunnel_key, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_CTX, + .arg2_type = ARG_PTR_TO_STACK, + .arg3_type = ARG_CONST_STACK_SIZE, + .arg4_type = ARG_ANYTHING, +}; + +static const struct bpf_func_proto *bpf_get_skb_set_tunnel_key_proto(void) +{ + if (!md_dst) { + /* race is not possible, since it's called from + * verifier that is holding verifier mutex + */ + md_dst = metadata_dst_alloc_percpu(0, GFP_KERNEL); + if (!md_dst) + return NULL; + } + return &bpf_skb_set_tunnel_key_proto; +} + static const struct bpf_func_proto * sk_filter_func_proto(enum bpf_func_id func_id) { @@ -1461,6 +1597,16 @@ tc_cls_act_func_proto(enum bpf_func_id func_id) return &bpf_l4_csum_replace_proto; case BPF_FUNC_clone_redirect: return &bpf_clone_redirect_proto; + case BPF_FUNC_get_cgroup_classid: + return &bpf_get_cgroup_classid_proto; + case BPF_FUNC_skb_vlan_push: + return &bpf_skb_vlan_push_proto; + case BPF_FUNC_skb_vlan_pop: + return &bpf_skb_vlan_pop_proto; + case BPF_FUNC_skb_get_tunnel_key: + return &bpf_skb_get_tunnel_key_proto; + case BPF_FUNC_skb_set_tunnel_key: + return bpf_get_skb_set_tunnel_key_proto(); default: return sk_filter_func_proto(func_id); } @@ -1569,6 +1715,13 @@ static u32 bpf_net_convert_ctx_access(enum bpf_access_type type, int dst_reg, offsetof(struct net_device, ifindex)); break; + case offsetof(struct __sk_buff, hash): + BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, hash) != 4); + + *insn++ = BPF_LDX_MEM(BPF_W, dst_reg, src_reg, + offsetof(struct sk_buff, hash)); + break; + case offsetof(struct __sk_buff, mark): BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, mark) != 4); diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c index 2a834c6179b9..d79699c9d1b9 100644 --- a/net/core/flow_dissector.c +++ b/net/core/flow_dissector.c @@ -19,14 +19,14 @@ #include <net/flow_dissector.h> #include <scsi/fc/fc_fcoe.h> -static bool skb_flow_dissector_uses_key(struct flow_dissector *flow_dissector, - enum flow_dissector_key_id key_id) +static bool dissector_uses_key(const struct flow_dissector *flow_dissector, + enum flow_dissector_key_id key_id) { return flow_dissector->used_keys & (1 << key_id); } -static void skb_flow_dissector_set_key(struct flow_dissector *flow_dissector, - enum flow_dissector_key_id key_id) +static void dissector_set_key(struct flow_dissector *flow_dissector, + enum flow_dissector_key_id key_id) { flow_dissector->used_keys |= (1 << key_id); } @@ -51,20 +51,20 @@ void skb_flow_dissector_init(struct flow_dissector *flow_dissector, * boundaries of unsigned short. */ BUG_ON(key->offset > USHRT_MAX); - BUG_ON(skb_flow_dissector_uses_key(flow_dissector, - key->key_id)); + BUG_ON(dissector_uses_key(flow_dissector, + key->key_id)); - skb_flow_dissector_set_key(flow_dissector, key->key_id); + dissector_set_key(flow_dissector, key->key_id); flow_dissector->offset[key->key_id] = key->offset; } /* Ensure that the dissector always includes control and basic key. * That way we are able to avoid handling lack of these in fast path. */ - BUG_ON(!skb_flow_dissector_uses_key(flow_dissector, - FLOW_DISSECTOR_KEY_CONTROL)); - BUG_ON(!skb_flow_dissector_uses_key(flow_dissector, - FLOW_DISSECTOR_KEY_BASIC)); + BUG_ON(!dissector_uses_key(flow_dissector, + FLOW_DISSECTOR_KEY_CONTROL)); + BUG_ON(!dissector_uses_key(flow_dissector, + FLOW_DISSECTOR_KEY_BASIC)); } EXPORT_SYMBOL(skb_flow_dissector_init); @@ -121,7 +121,8 @@ EXPORT_SYMBOL(__skb_flow_get_ports); bool __skb_flow_dissect(const struct sk_buff *skb, struct flow_dissector *flow_dissector, void *target_container, - void *data, __be16 proto, int nhoff, int hlen) + void *data, __be16 proto, int nhoff, int hlen, + unsigned int flags) { struct flow_dissector_key_control *key_control; struct flow_dissector_key_basic *key_basic; @@ -130,6 +131,7 @@ bool __skb_flow_dissect(const struct sk_buff *skb, struct flow_dissector_key_tags *key_tags; struct flow_dissector_key_keyid *key_keyid; u8 ip_proto = 0; + bool ret = false; if (!data) { data = skb->data; @@ -152,8 +154,8 @@ bool __skb_flow_dissect(const struct sk_buff *skb, FLOW_DISSECTOR_KEY_BASIC, target_container); - if (skb_flow_dissector_uses_key(flow_dissector, - FLOW_DISSECTOR_KEY_ETH_ADDRS)) { + if (dissector_uses_key(flow_dissector, + FLOW_DISSECTOR_KEY_ETH_ADDRS)) { struct ethhdr *eth = eth_hdr(skb); struct flow_dissector_key_eth_addrs *key_eth_addrs; @@ -171,15 +173,13 @@ again: ip: iph = __skb_header_pointer(skb, nhoff, sizeof(_iph), data, hlen, &_iph); if (!iph || iph->ihl < 5) - return false; + goto out_bad; nhoff += iph->ihl * 4; ip_proto = iph->protocol; - if (ip_is_fragment(iph)) - ip_proto = 0; - if (!skb_flow_dissector_uses_key(flow_dissector, - FLOW_DISSECTOR_KEY_IPV4_ADDRS)) + if (!dissector_uses_key(flow_dissector, + FLOW_DISSECTOR_KEY_IPV4_ADDRS)) break; key_addrs = skb_flow_dissector_target(flow_dissector, @@ -187,6 +187,22 @@ ip: memcpy(&key_addrs->v4addrs, &iph->saddr, sizeof(key_addrs->v4addrs)); key_control->addr_type = FLOW_DISSECTOR_KEY_IPV4_ADDRS; + + if (ip_is_fragment(iph)) { + key_control->flags |= FLOW_DIS_IS_FRAGMENT; + + if (iph->frag_off & htons(IP_OFFSET)) { + goto out_good; + } else { + key_control->flags |= FLOW_DIS_FIRST_FRAG; + if (!(flags & FLOW_DISSECTOR_F_PARSE_1ST_FRAG)) + goto out_good; + } + } + + if (flags & FLOW_DISSECTOR_F_STOP_AT_L3) + goto out_good; + break; } case htons(ETH_P_IPV6): { @@ -197,13 +213,13 @@ ip: ipv6: iph = __skb_header_pointer(skb, nhoff, sizeof(_iph), data, hlen, &_iph); if (!iph) - return false; + goto out_bad; ip_proto = iph->nexthdr; nhoff += sizeof(struct ipv6hdr); - if (skb_flow_dissector_uses_key(flow_dissector, - FLOW_DISSECTOR_KEY_IPV6_ADDRS)) { + if (dissector_uses_key(flow_dissector, + FLOW_DISSECTOR_KEY_IPV6_ADDRS)) { struct flow_dissector_key_ipv6_addrs *key_ipv6_addrs; key_ipv6_addrs = skb_flow_dissector_target(flow_dissector, @@ -216,15 +232,20 @@ ipv6: flow_label = ip6_flowlabel(iph); if (flow_label) { - if (skb_flow_dissector_uses_key(flow_dissector, - FLOW_DISSECTOR_KEY_FLOW_LABEL)) { + if (dissector_uses_key(flow_dissector, + FLOW_DISSECTOR_KEY_FLOW_LABEL)) { key_tags = skb_flow_dissector_target(flow_dissector, FLOW_DISSECTOR_KEY_FLOW_LABEL, target_container); key_tags->flow_label = ntohl(flow_label); } + if (flags & FLOW_DISSECTOR_F_STOP_AT_FLOW_LABEL) + goto out_good; } + if (flags & FLOW_DISSECTOR_F_STOP_AT_L3) + goto out_good; + break; } case htons(ETH_P_8021AD): @@ -234,10 +255,10 @@ ipv6: vlan = __skb_header_pointer(skb, nhoff, sizeof(_vlan), data, hlen, &_vlan); if (!vlan) - return false; + goto out_bad; - if (skb_flow_dissector_uses_key(flow_dissector, - FLOW_DISSECTOR_KEY_VLANID)) { + if (dissector_uses_key(flow_dissector, + FLOW_DISSECTOR_KEY_VLANID)) { key_tags = skb_flow_dissector_target(flow_dissector, FLOW_DISSECTOR_KEY_VLANID, target_container); @@ -256,7 +277,7 @@ ipv6: } *hdr, _hdr; hdr = __skb_header_pointer(skb, nhoff, sizeof(_hdr), data, hlen, &_hdr); if (!hdr) - return false; + goto out_bad; proto = hdr->proto; nhoff += PPPOE_SES_HLEN; switch (proto) { @@ -265,7 +286,7 @@ ipv6: case htons(PPP_IPV6): goto ipv6; default: - return false; + goto out_bad; } } case htons(ETH_P_TIPC): { @@ -275,19 +296,17 @@ ipv6: } *hdr, _hdr; hdr = __skb_header_pointer(skb, nhoff, sizeof(_hdr), data, hlen, &_hdr); if (!hdr) - return false; - key_basic->n_proto = proto; - key_control->thoff = (u16)nhoff; + goto out_bad; - if (skb_flow_dissector_uses_key(flow_dissector, - FLOW_DISSECTOR_KEY_TIPC_ADDRS)) { + if (dissector_uses_key(flow_dissector, + FLOW_DISSECTOR_KEY_TIPC_ADDRS)) { key_addrs = skb_flow_dissector_target(flow_dissector, FLOW_DISSECTOR_KEY_TIPC_ADDRS, target_container); key_addrs->tipcaddrs.srcnode = hdr->srcnode; key_control->addr_type = FLOW_DISSECTOR_KEY_TIPC_ADDRS; } - return true; + goto out_good; } case htons(ETH_P_MPLS_UC): @@ -297,12 +316,12 @@ mpls: hdr = __skb_header_pointer(skb, nhoff, sizeof(_hdr), data, hlen, &_hdr); if (!hdr) - return false; + goto out_bad; if ((ntohl(hdr[0].entry) & MPLS_LS_LABEL_MASK) >> MPLS_LS_LABEL_SHIFT == MPLS_LABEL_ENTROPY) { - if (skb_flow_dissector_uses_key(flow_dissector, - FLOW_DISSECTOR_KEY_MPLS_ENTROPY)) { + if (dissector_uses_key(flow_dissector, + FLOW_DISSECTOR_KEY_MPLS_ENTROPY)) { key_keyid = skb_flow_dissector_target(flow_dissector, FLOW_DISSECTOR_KEY_MPLS_ENTROPY, target_container); @@ -310,21 +329,17 @@ mpls: htonl(MPLS_LS_LABEL_MASK); } - key_basic->n_proto = proto; - key_basic->ip_proto = ip_proto; - key_control->thoff = (u16)nhoff; - - return true; + goto out_good; } - return true; + goto out_good; } case htons(ETH_P_FCOE): key_control->thoff = (u16)(nhoff + FCOE_HEADER_LEN); /* fall through */ default: - return false; + goto out_bad; } ip_proto_again: @@ -337,7 +352,7 @@ ip_proto_again: hdr = __skb_header_pointer(skb, nhoff, sizeof(_hdr), data, hlen, &_hdr); if (!hdr) - return false; + goto out_bad; /* * Only look inside GRE if version zero and no * routing @@ -357,10 +372,10 @@ ip_proto_again: data, hlen, &_keyid); if (!keyid) - return false; + goto out_bad; - if (skb_flow_dissector_uses_key(flow_dissector, - FLOW_DISSECTOR_KEY_GRE_KEYID)) { + if (dissector_uses_key(flow_dissector, + FLOW_DISSECTOR_KEY_GRE_KEYID)) { key_keyid = skb_flow_dissector_target(flow_dissector, FLOW_DISSECTOR_KEY_GRE_KEYID, target_container); @@ -378,10 +393,15 @@ ip_proto_again: sizeof(_eth), data, hlen, &_eth); if (!eth) - return false; + goto out_bad; proto = eth->h_proto; nhoff += sizeof(*eth); } + + key_control->flags |= FLOW_DIS_ENCAPSULATION; + if (flags & FLOW_DISSECTOR_F_STOP_AT_ENCAP) + goto out_good; + goto again; } case NEXTHDR_HOP: @@ -395,18 +415,53 @@ ip_proto_again: opthdr = __skb_header_pointer(skb, nhoff, sizeof(_opthdr), data, hlen, &_opthdr); if (!opthdr) - return false; + goto out_bad; ip_proto = opthdr[0]; nhoff += (opthdr[1] + 1) << 3; goto ip_proto_again; } + case NEXTHDR_FRAGMENT: { + struct frag_hdr _fh, *fh; + + if (proto != htons(ETH_P_IPV6)) + break; + + fh = __skb_header_pointer(skb, nhoff, sizeof(_fh), + data, hlen, &_fh); + + if (!fh) + goto out_bad; + + key_control->flags |= FLOW_DIS_IS_FRAGMENT; + + nhoff += sizeof(_fh); + + if (!(fh->frag_off & htons(IP6_OFFSET))) { + key_control->flags |= FLOW_DIS_FIRST_FRAG; + if (flags & FLOW_DISSECTOR_F_PARSE_1ST_FRAG) { + ip_proto = fh->nexthdr; + goto ip_proto_again; + } + } + goto out_good; + } case IPPROTO_IPIP: proto = htons(ETH_P_IP); + + key_control->flags |= FLOW_DIS_ENCAPSULATION; + if (flags & FLOW_DISSECTOR_F_STOP_AT_ENCAP) + goto out_good; + goto ip; case IPPROTO_IPV6: proto = htons(ETH_P_IPV6); + + key_control->flags |= FLOW_DIS_ENCAPSULATION; + if (flags & FLOW_DISSECTOR_F_STOP_AT_ENCAP) + goto out_good; + goto ipv6; case IPPROTO_MPLS: proto = htons(ETH_P_MPLS_UC); @@ -415,12 +470,8 @@ ip_proto_again: break; } - key_basic->n_proto = proto; - key_basic->ip_proto = ip_proto; - key_control->thoff = (u16)nhoff; - - if (skb_flow_dissector_uses_key(flow_dissector, - FLOW_DISSECTOR_KEY_PORTS)) { + if (dissector_uses_key(flow_dissector, + FLOW_DISSECTOR_KEY_PORTS)) { key_ports = skb_flow_dissector_target(flow_dissector, FLOW_DISSECTOR_KEY_PORTS, target_container); @@ -428,7 +479,15 @@ ip_proto_again: data, hlen); } - return true; +out_good: + ret = true; + +out_bad: + key_basic->n_proto = proto; + key_basic->ip_proto = ip_proto; + key_control->thoff = (u16)nhoff; + + return ret; } EXPORT_SYMBOL(__skb_flow_dissect); @@ -438,18 +497,21 @@ static __always_inline void __flow_hash_secret_init(void) net_get_random_once(&hashrnd, sizeof(hashrnd)); } -static __always_inline u32 __flow_hash_words(u32 *words, u32 length, u32 keyval) +static __always_inline u32 __flow_hash_words(const u32 *words, u32 length, + u32 keyval) { return jhash2(words, length, keyval); } -static inline void *flow_keys_hash_start(struct flow_keys *flow) +static inline const u32 *flow_keys_hash_start(const struct flow_keys *flow) { + const void *p = flow; + BUILD_BUG_ON(FLOW_KEYS_HASH_OFFSET % sizeof(u32)); - return (void *)flow + FLOW_KEYS_HASH_OFFSET; + return (const u32 *)(p + FLOW_KEYS_HASH_OFFSET); } -static inline size_t flow_keys_hash_length(struct flow_keys *flow) +static inline size_t flow_keys_hash_length(const struct flow_keys *flow) { size_t diff = FLOW_KEYS_HASH_OFFSET + sizeof(flow->addrs); BUILD_BUG_ON((sizeof(*flow) - FLOW_KEYS_HASH_OFFSET) % sizeof(u32)); @@ -539,7 +601,7 @@ static inline u32 __flow_hash_from_keys(struct flow_keys *keys, u32 keyval) __flow_hash_consistentify(keys); - hash = __flow_hash_words((u32 *)flow_keys_hash_start(keys), + hash = __flow_hash_words(flow_keys_hash_start(keys), flow_keys_hash_length(keys), keyval); if (!hash) hash = 1; @@ -557,8 +619,8 @@ EXPORT_SYMBOL(flow_hash_from_keys); static inline u32 ___skb_get_hash(const struct sk_buff *skb, struct flow_keys *keys, u32 keyval) { - if (!skb_flow_dissect_flow_keys(skb, keys)) - return 0; + skb_flow_dissect_flow_keys(skb, keys, + FLOW_DISSECTOR_F_STOP_AT_FLOW_LABEL); return __flow_hash_from_keys(keys, keyval); } @@ -602,17 +664,11 @@ EXPORT_SYMBOL(make_flow_keys_digest); void __skb_get_hash(struct sk_buff *skb) { struct flow_keys keys; - u32 hash; __flow_hash_secret_init(); - hash = ___skb_get_hash(skb, &keys, hashrnd); - if (!hash) - return; - if (keys.ports.ports) - skb->l4_hash = 1; - skb->sw_hash = 1; - skb->hash = hash; + __skb_set_sw_hash(skb, ___skb_get_hash(skb, &keys, hashrnd), + flow_keys_have_l4(&keys)); } EXPORT_SYMBOL(__skb_get_hash); @@ -624,6 +680,51 @@ __u32 skb_get_hash_perturb(const struct sk_buff *skb, u32 perturb) } EXPORT_SYMBOL(skb_get_hash_perturb); +__u32 __skb_get_hash_flowi6(struct sk_buff *skb, const struct flowi6 *fl6) +{ + struct flow_keys keys; + + memset(&keys, 0, sizeof(keys)); + + memcpy(&keys.addrs.v6addrs.src, &fl6->saddr, + sizeof(keys.addrs.v6addrs.src)); + memcpy(&keys.addrs.v6addrs.dst, &fl6->daddr, + sizeof(keys.addrs.v6addrs.dst)); + keys.control.addr_type = FLOW_DISSECTOR_KEY_IPV6_ADDRS; + keys.ports.src = fl6->fl6_sport; + keys.ports.dst = fl6->fl6_dport; + keys.keyid.keyid = fl6->fl6_gre_key; + keys.tags.flow_label = (__force u32)fl6->flowlabel; + keys.basic.ip_proto = fl6->flowi6_proto; + + __skb_set_sw_hash(skb, flow_hash_from_keys(&keys), + flow_keys_have_l4(&keys)); + + return skb->hash; +} +EXPORT_SYMBOL(__skb_get_hash_flowi6); + +__u32 __skb_get_hash_flowi4(struct sk_buff *skb, const struct flowi4 *fl4) +{ + struct flow_keys keys; + + memset(&keys, 0, sizeof(keys)); + + keys.addrs.v4addrs.src = fl4->saddr; + keys.addrs.v4addrs.dst = fl4->daddr; + keys.control.addr_type = FLOW_DISSECTOR_KEY_IPV4_ADDRS; + keys.ports.src = fl4->fl4_sport; + keys.ports.dst = fl4->fl4_dport; + keys.keyid.keyid = fl4->fl4_gre_key; + keys.basic.ip_proto = fl4->flowi4_proto; + + __skb_set_sw_hash(skb, flow_hash_from_keys(&keys), + flow_keys_have_l4(&keys)); + + return skb->hash; +} +EXPORT_SYMBOL(__skb_get_hash_flowi4); + u32 __skb_get_poff(const struct sk_buff *skb, void *data, const struct flow_keys *keys, int hlen) { @@ -683,12 +784,47 @@ u32 skb_get_poff(const struct sk_buff *skb) { struct flow_keys keys; - if (!skb_flow_dissect_flow_keys(skb, &keys)) + if (!skb_flow_dissect_flow_keys(skb, &keys, 0)) return 0; return __skb_get_poff(skb, skb->data, &keys, skb_headlen(skb)); } +__u32 __get_hash_from_flowi6(const struct flowi6 *fl6, struct flow_keys *keys) +{ + memset(keys, 0, sizeof(*keys)); + + memcpy(&keys->addrs.v6addrs.src, &fl6->saddr, + sizeof(keys->addrs.v6addrs.src)); + memcpy(&keys->addrs.v6addrs.dst, &fl6->daddr, + sizeof(keys->addrs.v6addrs.dst)); + keys->control.addr_type = FLOW_DISSECTOR_KEY_IPV6_ADDRS; + keys->ports.src = fl6->fl6_sport; + keys->ports.dst = fl6->fl6_dport; + keys->keyid.keyid = fl6->fl6_gre_key; + keys->tags.flow_label = (__force u32)fl6->flowlabel; + keys->basic.ip_proto = fl6->flowi6_proto; + + return flow_hash_from_keys(keys); +} +EXPORT_SYMBOL(__get_hash_from_flowi6); + +__u32 __get_hash_from_flowi4(const struct flowi4 *fl4, struct flow_keys *keys) +{ + memset(keys, 0, sizeof(*keys)); + + keys->addrs.v4addrs.src = fl4->saddr; + keys->addrs.v4addrs.dst = fl4->daddr; + keys->control.addr_type = FLOW_DISSECTOR_KEY_IPV4_ADDRS; + keys->ports.src = fl4->fl4_sport; + keys->ports.dst = fl4->fl4_dport; + keys->keyid.keyid = fl4->fl4_gre_key; + keys->basic.ip_proto = fl4->flowi4_proto; + + return flow_hash_from_keys(keys); +} +EXPORT_SYMBOL(__get_hash_from_flowi4); + static const struct flow_dissector_key flow_keys_dissector_keys[] = { { .key_id = FLOW_DISSECTOR_KEY_CONTROL, diff --git a/net/core/lwtunnel.c b/net/core/lwtunnel.c new file mode 100644 index 000000000000..dfb1a9ca0835 --- /dev/null +++ b/net/core/lwtunnel.c @@ -0,0 +1,249 @@ +/* + * lwtunnel Infrastructure for light weight tunnels like mpls + * + * Authors: Roopa Prabhu, <roopa@cumulusnetworks.com> + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + * + */ + +#include <linux/capability.h> +#include <linux/module.h> +#include <linux/types.h> +#include <linux/kernel.h> +#include <linux/slab.h> +#include <linux/uaccess.h> +#include <linux/skbuff.h> +#include <linux/netdevice.h> +#include <linux/lwtunnel.h> +#include <linux/in.h> +#include <linux/init.h> +#include <linux/err.h> + +#include <net/lwtunnel.h> +#include <net/rtnetlink.h> +#include <net/ip6_fib.h> + +struct lwtunnel_state *lwtunnel_state_alloc(int encap_len) +{ + struct lwtunnel_state *lws; + + lws = kzalloc(sizeof(*lws) + encap_len, GFP_ATOMIC); + + return lws; +} +EXPORT_SYMBOL(lwtunnel_state_alloc); + +static const struct lwtunnel_encap_ops __rcu * + lwtun_encaps[LWTUNNEL_ENCAP_MAX + 1] __read_mostly; + +int lwtunnel_encap_add_ops(const struct lwtunnel_encap_ops *ops, + unsigned int num) +{ + if (num > LWTUNNEL_ENCAP_MAX) + return -ERANGE; + + return !cmpxchg((const struct lwtunnel_encap_ops **) + &lwtun_encaps[num], + NULL, ops) ? 0 : -1; +} +EXPORT_SYMBOL(lwtunnel_encap_add_ops); + +int lwtunnel_encap_del_ops(const struct lwtunnel_encap_ops *ops, + unsigned int encap_type) +{ + int ret; + + if (encap_type == LWTUNNEL_ENCAP_NONE || + encap_type > LWTUNNEL_ENCAP_MAX) + return -ERANGE; + + ret = (cmpxchg((const struct lwtunnel_encap_ops **) + &lwtun_encaps[encap_type], + ops, NULL) == ops) ? 0 : -1; + + synchronize_net(); + + return ret; +} +EXPORT_SYMBOL(lwtunnel_encap_del_ops); + +int lwtunnel_build_state(struct net_device *dev, u16 encap_type, + struct nlattr *encap, unsigned int family, + const void *cfg, struct lwtunnel_state **lws) +{ + const struct lwtunnel_encap_ops *ops; + int ret = -EINVAL; + + if (encap_type == LWTUNNEL_ENCAP_NONE || + encap_type > LWTUNNEL_ENCAP_MAX) + return ret; + + ret = -EOPNOTSUPP; + rcu_read_lock(); + ops = rcu_dereference(lwtun_encaps[encap_type]); + if (likely(ops && ops->build_state)) + ret = ops->build_state(dev, encap, family, cfg, lws); + rcu_read_unlock(); + + return ret; +} +EXPORT_SYMBOL(lwtunnel_build_state); + +int lwtunnel_fill_encap(struct sk_buff *skb, struct lwtunnel_state *lwtstate) +{ + const struct lwtunnel_encap_ops *ops; + struct nlattr *nest; + int ret = -EINVAL; + + if (!lwtstate) + return 0; + + if (lwtstate->type == LWTUNNEL_ENCAP_NONE || + lwtstate->type > LWTUNNEL_ENCAP_MAX) + return 0; + + ret = -EOPNOTSUPP; + nest = nla_nest_start(skb, RTA_ENCAP); + rcu_read_lock(); + ops = rcu_dereference(lwtun_encaps[lwtstate->type]); + if (likely(ops && ops->fill_encap)) + ret = ops->fill_encap(skb, lwtstate); + rcu_read_unlock(); + + if (ret) + goto nla_put_failure; + nla_nest_end(skb, nest); + ret = nla_put_u16(skb, RTA_ENCAP_TYPE, lwtstate->type); + if (ret) + goto nla_put_failure; + + return 0; + +nla_put_failure: + nla_nest_cancel(skb, nest); + + return (ret == -EOPNOTSUPP ? 0 : ret); +} +EXPORT_SYMBOL(lwtunnel_fill_encap); + +int lwtunnel_get_encap_size(struct lwtunnel_state *lwtstate) +{ + const struct lwtunnel_encap_ops *ops; + int ret = 0; + + if (!lwtstate) + return 0; + + if (lwtstate->type == LWTUNNEL_ENCAP_NONE || + lwtstate->type > LWTUNNEL_ENCAP_MAX) + return 0; + + rcu_read_lock(); + ops = rcu_dereference(lwtun_encaps[lwtstate->type]); + if (likely(ops && ops->get_encap_size)) + ret = nla_total_size(ops->get_encap_size(lwtstate)); + rcu_read_unlock(); + + return ret; +} +EXPORT_SYMBOL(lwtunnel_get_encap_size); + +int lwtunnel_cmp_encap(struct lwtunnel_state *a, struct lwtunnel_state *b) +{ + const struct lwtunnel_encap_ops *ops; + int ret = 0; + + if (!a && !b) + return 0; + + if (!a || !b) + return 1; + + if (a->type != b->type) + return 1; + + if (a->type == LWTUNNEL_ENCAP_NONE || + a->type > LWTUNNEL_ENCAP_MAX) + return 0; + + rcu_read_lock(); + ops = rcu_dereference(lwtun_encaps[a->type]); + if (likely(ops && ops->cmp_encap)) + ret = ops->cmp_encap(a, b); + rcu_read_unlock(); + + return ret; +} +EXPORT_SYMBOL(lwtunnel_cmp_encap); + +int lwtunnel_output(struct sock *sk, 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->output)) + ret = ops->output(sk, skb); + rcu_read_unlock(); + + if (ret == -EOPNOTSUPP) + goto drop; + + return ret; + +drop: + kfree_skb(skb); + + return ret; +} +EXPORT_SYMBOL(lwtunnel_output); + +int lwtunnel_input(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->input)) + ret = ops->input(skb); + rcu_read_unlock(); + + if (ret == -EOPNOTSUPP) + goto drop; + + return ret; + +drop: + kfree_skb(skb); + + return ret; +} +EXPORT_SYMBOL(lwtunnel_input); diff --git a/net/core/neighbour.c b/net/core/neighbour.c index 84195dacb8b6..2b515ba7e94f 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -274,8 +274,12 @@ static struct neighbour *neigh_alloc(struct neigh_table *tbl, struct net_device (entries >= tbl->gc_thresh2 && time_after(now, tbl->last_flush + 5 * HZ))) { if (!neigh_forced_gc(tbl) && - entries >= tbl->gc_thresh3) + entries >= tbl->gc_thresh3) { + net_info_ratelimited("%s: neighbor table overflow!\n", + tbl->id); + NEIGH_CACHE_STAT_INC(tbl, table_fulls); goto out_entries; + } } n = kzalloc(tbl->entry_size + dev->neigh_priv_len, GFP_ATOMIC); @@ -1849,6 +1853,7 @@ static int neightbl_fill_info(struct sk_buff *skb, struct neigh_table *tbl, ndst.ndts_rcv_probes_ucast += st->rcv_probes_ucast; ndst.ndts_periodic_gc_runs += st->periodic_gc_runs; ndst.ndts_forced_gc_runs += st->forced_gc_runs; + ndst.ndts_table_fulls += st->table_fulls; } if (nla_put(skb, NDTA_STATS, sizeof(ndst), &ndst)) @@ -2717,12 +2722,12 @@ static int neigh_stat_seq_show(struct seq_file *seq, void *v) struct neigh_statistics *st = v; if (v == SEQ_START_TOKEN) { - seq_printf(seq, "entries allocs destroys hash_grows lookups hits res_failed rcv_probes_mcast rcv_probes_ucast periodic_gc_runs forced_gc_runs unresolved_discards\n"); + seq_printf(seq, "entries allocs destroys hash_grows lookups hits res_failed rcv_probes_mcast rcv_probes_ucast periodic_gc_runs forced_gc_runs unresolved_discards table_fulls\n"); return 0; } seq_printf(seq, "%08x %08lx %08lx %08lx %08lx %08lx %08lx " - "%08lx %08lx %08lx %08lx %08lx\n", + "%08lx %08lx %08lx %08lx %08lx %08lx\n", atomic_read(&tbl->entries), st->allocs, @@ -2739,7 +2744,8 @@ static int neigh_stat_seq_show(struct seq_file *seq, void *v) st->periodic_gc_runs, st->forced_gc_runs, - st->unres_discards + st->unres_discards, + st->table_fulls ); return 0; diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c index 18b34d771ed4..b279077c3089 100644 --- a/net/core/net-sysfs.c +++ b/net/core/net-sysfs.c @@ -404,6 +404,19 @@ static ssize_t group_store(struct device *dev, struct device_attribute *attr, NETDEVICE_SHOW(group, fmt_dec); static DEVICE_ATTR(netdev_group, S_IRUGO | S_IWUSR, group_show, group_store); +static int change_proto_down(struct net_device *dev, unsigned long proto_down) +{ + return dev_change_proto_down(dev, (bool) proto_down); +} + +static ssize_t proto_down_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t len) +{ + return netdev_store(dev, attr, buf, len, change_proto_down); +} +NETDEVICE_SHOW_RW(proto_down, fmt_dec); + static ssize_t phys_port_id_show(struct device *dev, struct device_attribute *attr, char *buf) { @@ -501,6 +514,7 @@ static struct attribute *net_class_attrs[] = { &dev_attr_phys_port_id.attr, &dev_attr_phys_port_name.attr, &dev_attr_phys_switch_id.attr, + &dev_attr_proto_down.attr, NULL, }; ATTRIBUTE_GROUPS(net_class); @@ -675,7 +689,7 @@ static ssize_t store_rps_map(struct netdev_rx_queue *queue, struct rps_map *old_map, *map; cpumask_var_t mask; int err, cpu, i; - static DEFINE_SPINLOCK(rps_map_lock); + static DEFINE_MUTEX(rps_map_mutex); if (!capable(CAP_NET_ADMIN)) return -EPERM; @@ -708,18 +722,21 @@ static ssize_t store_rps_map(struct netdev_rx_queue *queue, map = NULL; } - spin_lock(&rps_map_lock); + mutex_lock(&rps_map_mutex); old_map = rcu_dereference_protected(queue->rps_map, - lockdep_is_held(&rps_map_lock)); + mutex_is_locked(&rps_map_mutex)); rcu_assign_pointer(queue->rps_map, map); - spin_unlock(&rps_map_lock); if (map) static_key_slow_inc(&rps_needed); - if (old_map) { - kfree_rcu(old_map, rcu); + if (old_map) static_key_slow_dec(&rps_needed); - } + + mutex_unlock(&rps_map_mutex); + + if (old_map) + kfree_rcu(old_map, rcu); + free_cpumask_var(mask); return len; } diff --git a/net/core/net-traces.c b/net/core/net-traces.c index ba3c0120786c..adef015b2f41 100644 --- a/net/core/net-traces.c +++ b/net/core/net-traces.c @@ -31,6 +31,7 @@ #include <trace/events/napi.h> #include <trace/events/sock.h> #include <trace/events/udp.h> +#include <trace/events/fib.h> EXPORT_TRACEPOINT_SYMBOL_GPL(kfree_skb); diff --git a/net/core/netpoll.c b/net/core/netpoll.c index c126a878c47c..6aa3db8dfc3b 100644 --- a/net/core/netpoll.c +++ b/net/core/netpoll.c @@ -380,6 +380,8 @@ void netpoll_send_udp(struct netpoll *np, const char *msg, int len) static atomic_t ip_ident; struct ipv6hdr *ip6h; + WARN_ON_ONCE(!irqs_disabled()); + udp_len = len + sizeof(*udph); if (np->ipv6) ip_len = udp_len + sizeof(*ip6h); diff --git a/net/core/pktgen.c b/net/core/pktgen.c index 1cbd209192ea..de8d5cc5eb24 100644 --- a/net/core/pktgen.c +++ b/net/core/pktgen.c @@ -273,7 +273,6 @@ struct pktgen_dev { /* runtime counters relating to clone_skb */ - __u64 allocated_skbs; __u32 clone_count; int last_ok; /* Was last skb sent? * Or a failed transmit of some sort? @@ -2279,7 +2278,7 @@ static void spin(struct pktgen_dev *pkt_dev, ktime_t spin_until) static inline void set_pkt_overhead(struct pktgen_dev *pkt_dev) { - pkt_dev->pkt_overhead = 0; + pkt_dev->pkt_overhead = LL_RESERVED_SPACE(pkt_dev->odev); pkt_dev->pkt_overhead += pkt_dev->nr_labels*sizeof(u32); pkt_dev->pkt_overhead += VLAN_TAG_SIZE(pkt_dev); pkt_dev->pkt_overhead += SVLAN_TAG_SIZE(pkt_dev); @@ -2788,6 +2787,7 @@ static struct sk_buff *pktgen_alloc_skb(struct net_device *dev, } else { skb = __netdev_alloc_skb(dev, size, GFP_NOWAIT); } + skb_reserve(skb, LL_RESERVED_SPACE(dev)); return skb; } @@ -3397,7 +3397,6 @@ static void pktgen_xmit(struct pktgen_dev *pkt_dev) return; } pkt_dev->last_pkt_size = pkt_dev->skb->len; - pkt_dev->allocated_skbs++; pkt_dev->clone_count = 0; /* reset counter */ } diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index dc004b1e1f85..a466821d1441 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -678,6 +678,12 @@ int rtnetlink_put_metrics(struct sk_buff *skb, u32 *metrics) continue; if (nla_put_string(skb, i + 1, name)) goto nla_put_failure; + } else if (i == RTAX_FEATURES - 1) { + u32 user_features = metrics[i] & RTAX_FEATURE_MASK; + + BUILD_BUG_ON(RTAX_FEATURE_MASK & DST_FEATURE_MASK); + if (nla_put_u32(skb, i + 1, user_features)) + goto nla_put_failure; } else { if (nla_put_u32(skb, i + 1, metrics[i])) goto nla_put_failure; @@ -896,7 +902,9 @@ static noinline size_t if_nlmsg_size(const struct net_device *dev, + rtnl_link_get_size(dev) /* IFLA_LINKINFO */ + rtnl_link_get_af_size(dev) /* IFLA_AF_SPEC */ + nla_total_size(MAX_PHYS_ITEM_ID_LEN) /* IFLA_PHYS_PORT_ID */ - + nla_total_size(MAX_PHYS_ITEM_ID_LEN); /* IFLA_PHYS_SWITCH_ID */ + + nla_total_size(MAX_PHYS_ITEM_ID_LEN) /* IFLA_PHYS_SWITCH_ID */ + + nla_total_size(1); /* IFLA_PROTO_DOWN */ + } static int rtnl_vf_ports_fill(struct sk_buff *skb, struct net_device *dev) @@ -1082,7 +1090,8 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev, (dev->ifalias && nla_put_string(skb, IFLA_IFALIAS, dev->ifalias)) || nla_put_u32(skb, IFLA_CARRIER_CHANGES, - atomic_read(&dev->carrier_changes))) + atomic_read(&dev->carrier_changes)) || + nla_put_u8(skb, IFLA_PROTO_DOWN, dev->proto_down)) goto nla_put_failure; if (1) { @@ -1319,6 +1328,7 @@ static const struct nla_policy ifla_policy[IFLA_MAX+1] = { [IFLA_CARRIER_CHANGES] = { .type = NLA_U32 }, /* ignored */ [IFLA_PHYS_SWITCH_ID] = { .type = NLA_BINARY, .len = MAX_PHYS_ITEM_ID_LEN }, [IFLA_LINK_NETNSID] = { .type = NLA_S32 }, + [IFLA_PROTO_DOWN] = { .type = NLA_U8 }, }; static const struct nla_policy ifla_info_policy[IFLA_INFO_MAX+1] = { @@ -1861,6 +1871,14 @@ static int do_setlink(const struct sk_buff *skb, } err = 0; + if (tb[IFLA_PROTO_DOWN]) { + err = dev_change_proto_down(dev, + nla_get_u8(tb[IFLA_PROTO_DOWN])); + if (err) + goto errout; + status |= DO_SETLINK_NOTIFY; + } + errout: if (status & DO_SETLINK_MODIFIED) { if (status & DO_SETLINK_NOTIFY) @@ -1951,16 +1969,30 @@ static int rtnl_group_dellink(const struct net *net, int group) return 0; } +int rtnl_delete_link(struct net_device *dev) +{ + const struct rtnl_link_ops *ops; + LIST_HEAD(list_kill); + + ops = dev->rtnl_link_ops; + if (!ops || !ops->dellink) + return -EOPNOTSUPP; + + ops->dellink(dev, &list_kill); + unregister_netdevice_many(&list_kill); + + return 0; +} +EXPORT_SYMBOL_GPL(rtnl_delete_link); + static int rtnl_dellink(struct sk_buff *skb, struct nlmsghdr *nlh) { struct net *net = sock_net(skb->sk); - const struct rtnl_link_ops *ops; struct net_device *dev; struct ifinfomsg *ifm; char ifname[IFNAMSIZ]; struct nlattr *tb[IFLA_MAX+1]; int err; - LIST_HEAD(list_kill); err = nlmsg_parse(nlh, sizeof(*ifm), tb, IFLA_MAX, ifla_policy); if (err < 0) @@ -1982,13 +2014,7 @@ static int rtnl_dellink(struct sk_buff *skb, struct nlmsghdr *nlh) if (!dev) return -ENODEV; - ops = dev->rtnl_link_ops; - if (!ops || !ops->dellink) - return -EOPNOTSUPP; - - ops->dellink(dev, &list_kill); - unregister_netdevice_many(&list_kill); - return 0; + return rtnl_delete_link(dev); } int rtnl_configure_link(struct net_device *dev, const struct ifinfomsg *ifm) diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 7b84330e5d30..dad4dd37e2aa 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -392,7 +392,7 @@ EXPORT_SYMBOL(napi_alloc_frag); /** * __netdev_alloc_skb - allocate an skbuff for rx on a specific device * @dev: network device to receive on - * @length: length to allocate + * @len: length to allocate * @gfp_mask: get_free_pages mask, passed to alloc_skb * * Allocate a new &sk_buff and assign it a usage count of one. The @@ -461,7 +461,7 @@ EXPORT_SYMBOL(__netdev_alloc_skb); /** * __napi_alloc_skb - allocate skbuff for rx in a specific NAPI instance * @napi: napi instance this buffer was allocated for - * @length: length to allocate + * @len: length to allocate * @gfp_mask: get_free_pages mask, passed to alloc_skb and alloc_pages * * Allocate a new sk_buff for use in NAPI receive. This buffer will diff --git a/net/core/sock.c b/net/core/sock.c index 193901d09757..ca2984afe16e 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -2078,7 +2078,7 @@ suppress_allocation: EXPORT_SYMBOL(__sk_mem_schedule); /** - * __sk_reclaim - reclaim memory_allocated + * __sk_mem_reclaim - reclaim memory_allocated * @sk: socket * @amount: number of bytes (rounded down to a SK_MEM_QUANTUM multiple) */ diff --git a/net/core/sock_diag.c b/net/core/sock_diag.c index d79866c5f8bc..817622f3dbb7 100644 --- a/net/core/sock_diag.c +++ b/net/core/sock_diag.c @@ -90,6 +90,9 @@ int sock_diag_put_filterinfo(bool may_report_filterinfo, struct sock *sk, goto out; fprog = filter->prog->orig_prog; + if (!fprog) + goto out; + flen = bpf_classic_proglen(fprog); attr = nla_reserve(skb, attrtype, flen); diff --git a/net/core/timestamping.c b/net/core/timestamping.c index 43d3dd62fcc8..42689d5c468c 100644 --- a/net/core/timestamping.c +++ b/net/core/timestamping.c @@ -60,11 +60,15 @@ bool skb_defer_rx_timestamp(struct sk_buff *skb) struct phy_device *phydev; unsigned int type; + if (!skb->dev || !skb->dev->phydev || !skb->dev->phydev->drv) + return false; + if (skb_headroom(skb) < ETH_HLEN) return false; + __skb_push(skb, ETH_HLEN); - type = classify(skb); + type = ptp_classify_raw(skb); __skb_pull(skb, ETH_HLEN); diff --git a/net/core/utils.c b/net/core/utils.c index a7732a068043..3dffce953c39 100644 --- a/net/core/utils.c +++ b/net/core/utils.c @@ -301,7 +301,7 @@ out: EXPORT_SYMBOL(in6_pton); void inet_proto_csum_replace4(__sum16 *sum, struct sk_buff *skb, - __be32 from, __be32 to, int pseudohdr) + __be32 from, __be32 to, bool pseudohdr) { if (skb->ip_summed != CHECKSUM_PARTIAL) { csum_replace4(sum, from, to); @@ -318,7 +318,7 @@ EXPORT_SYMBOL(inet_proto_csum_replace4); void inet_proto_csum_replace16(__sum16 *sum, struct sk_buff *skb, const __be32 *from, const __be32 *to, - int pseudohdr) + bool pseudohdr) { __be32 diff[] = { ~from[0], ~from[1], ~from[2], ~from[3], @@ -336,6 +336,19 @@ void inet_proto_csum_replace16(__sum16 *sum, struct sk_buff *skb, } EXPORT_SYMBOL(inet_proto_csum_replace16); +void inet_proto_csum_replace_by_diff(__sum16 *sum, struct sk_buff *skb, + __wsum diff, bool pseudohdr) +{ + if (skb->ip_summed != CHECKSUM_PARTIAL) { + *sum = csum_fold(csum_add(diff, ~csum_unfold(*sum))); + if (skb->ip_summed == CHECKSUM_COMPLETE && pseudohdr) + skb->csum = ~csum_add(diff, ~skb->csum); + } else if (pseudohdr) { + *sum = ~csum_fold(csum_add(diff, csum_unfold(*sum))); + } +} +EXPORT_SYMBOL(inet_proto_csum_replace_by_diff); + struct __net_random_once_work { struct work_struct work; struct static_key *key; diff --git a/net/decnet/dn_rules.c b/net/decnet/dn_rules.c index 9d66a0f72f90..295bbd6a56f2 100644 --- a/net/decnet/dn_rules.c +++ b/net/decnet/dn_rules.c @@ -229,7 +229,6 @@ static const struct fib_rules_ops __net_initconst dn_fib_rules_ops_template = { .configure = dn_fib_rule_configure, .compare = dn_fib_rule_compare, .fill = dn_fib_rule_fill, - .default_pref = fib_default_rule_pref, .flush_cache = dn_fib_rule_flush_cache, .nlgroup = RTNLGRP_DECnet_RULE, .policy = dn_fib_rule_policy, diff --git a/net/dsa/dsa.c b/net/dsa/dsa.c index b445d492c115..76e3800765f8 100644 --- a/net/dsa/dsa.c +++ b/net/dsa/dsa.c @@ -176,6 +176,41 @@ __ATTRIBUTE_GROUPS(dsa_hwmon); #endif /* CONFIG_NET_DSA_HWMON */ /* basic switch operations **************************************************/ +static int dsa_cpu_dsa_setup(struct dsa_switch *ds, struct net_device *master) +{ + struct dsa_chip_data *cd = ds->pd; + struct device_node *port_dn; + struct phy_device *phydev; + int ret, port, mode; + + for (port = 0; port < DSA_MAX_PORTS; port++) { + if (!(dsa_is_cpu_port(ds, port) || dsa_is_dsa_port(ds, port))) + continue; + + port_dn = cd->port_dn[port]; + if (of_phy_is_fixed_link(port_dn)) { + ret = of_phy_register_fixed_link(port_dn); + if (ret) { + netdev_err(master, + "failed to register fixed PHY\n"); + return ret; + } + phydev = of_phy_find_device(port_dn); + + mode = of_get_phy_mode(port_dn); + if (mode < 0) + mode = PHY_INTERFACE_MODE_NA; + phydev->interface = mode; + + genphy_config_init(phydev); + genphy_read_status(phydev); + if (ds->drv->adjust_link) + ds->drv->adjust_link(ds, port, phydev); + } + } + return 0; +} + static int dsa_switch_setup_one(struct dsa_switch *ds, struct device *parent) { struct dsa_switch_driver *drv = ds->drv; @@ -297,6 +332,14 @@ static int dsa_switch_setup_one(struct dsa_switch *ds, struct device *parent) } } + /* Perform configuration of the CPU and DSA ports */ + ret = dsa_cpu_dsa_setup(ds, dst->master_netdev); + if (ret < 0) { + netdev_err(dst->master_netdev, "[%d] : can't configure CPU and DSA ports\n", + index); + ret = 0; + } + #ifdef CONFIG_NET_DSA_HWMON /* If the switch provides a temperature sensor, * register with hardware monitoring subsystem. @@ -554,6 +597,31 @@ static int dsa_of_setup_routing_table(struct dsa_platform_data *pd, return 0; } +static int dsa_of_probe_links(struct dsa_platform_data *pd, + struct dsa_chip_data *cd, + int chip_index, int port_index, + struct device_node *port, + const char *port_name) +{ + struct device_node *link; + int link_index; + int ret; + + for (link_index = 0;; link_index++) { + link = of_parse_phandle(port, "link", link_index); + if (!link) + break; + + if (!strcmp(port_name, "dsa") && pd->nr_chips > 1) { + ret = dsa_of_setup_routing_table(pd, cd, chip_index, + port_index, link); + if (ret) + return ret; + } + } + return 0; +} + static void dsa_of_free_platform_data(struct dsa_platform_data *pd) { int i; @@ -573,8 +641,8 @@ static void dsa_of_free_platform_data(struct dsa_platform_data *pd) static int dsa_of_probe(struct device *dev) { struct device_node *np = dev->of_node; - struct device_node *child, *mdio, *ethernet, *port, *link; - struct mii_bus *mdio_bus; + struct device_node *child, *mdio, *ethernet, *port; + struct mii_bus *mdio_bus, *mdio_bus_switch; struct net_device *ethernet_dev; struct dsa_platform_data *pd; struct dsa_chip_data *cd; @@ -636,6 +704,16 @@ static int dsa_of_probe(struct device *dev) if (!of_property_read_u32(child, "eeprom-length", &eeprom_len)) cd->eeprom_len = eeprom_len; + mdio = of_parse_phandle(child, "mii-bus", 0); + if (mdio) { + mdio_bus_switch = of_mdio_find_bus(mdio); + if (!mdio_bus_switch) { + ret = -EPROBE_DEFER; + goto out_free_chip; + } + cd->host_dev = &mdio_bus_switch->dev; + } + for_each_available_child_of_node(child, port) { port_reg = of_get_property(port, "reg", NULL); if (!port_reg) @@ -658,15 +736,10 @@ static int dsa_of_probe(struct device *dev) goto out_free_chip; } - link = of_parse_phandle(port, "link", 0); - - if (!strcmp(port_name, "dsa") && link && - pd->nr_chips > 1) { - ret = dsa_of_setup_routing_table(pd, cd, - chip_index, port_index, link); - if (ret) - goto out_free_chip; - } + ret = dsa_of_probe_links(pd, cd, chip_index, + port_index, port, port_name); + if (ret) + goto out_free_chip; } } diff --git a/net/dsa/dsa_priv.h b/net/dsa/dsa_priv.h index d5f1f9b862ea..311796c809af 100644 --- a/net/dsa/dsa_priv.h +++ b/net/dsa/dsa_priv.h @@ -13,9 +13,10 @@ #include <linux/phy.h> #include <linux/netdevice.h> +#include <linux/netpoll.h> struct dsa_device_ops { - netdev_tx_t (*xmit)(struct sk_buff *skb, struct net_device *dev); + struct sk_buff *(*xmit)(struct sk_buff *skb, struct net_device *dev); int (*rcv)(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt, struct net_device *orig_dev); }; @@ -26,7 +27,7 @@ struct dsa_slave_priv { * switch port. */ struct net_device *dev; - netdev_tx_t (*xmit)(struct sk_buff *skb, + struct sk_buff * (*xmit)(struct sk_buff *skb, struct net_device *dev); /* @@ -47,6 +48,9 @@ struct dsa_slave_priv { int old_duplex; struct net_device *bridge_dev; +#ifdef CONFIG_NET_POLL_CONTROLLER + struct netpoll *netpoll; +#endif }; /* dsa.c */ diff --git a/net/dsa/slave.c b/net/dsa/slave.c index 35c47ddd04f0..cce97385f743 100644 --- a/net/dsa/slave.c +++ b/net/dsa/slave.c @@ -18,6 +18,7 @@ #include <net/rtnetlink.h> #include <net/switchdev.h> #include <linux/if_bridge.h> +#include <linux/netpoll.h> #include "dsa_priv.h" /* slave mii_bus handling ***************************************************/ @@ -199,103 +200,212 @@ out: return 0; } -static int dsa_slave_fdb_add(struct ndmsg *ndm, struct nlattr *tb[], - struct net_device *dev, - const unsigned char *addr, u16 vid, u16 nlm_flags) +static int dsa_bridge_check_vlan_range(struct dsa_switch *ds, + const struct net_device *bridge, + u16 vid_begin, u16 vid_end) { + struct dsa_slave_priv *p; + struct net_device *dev, *vlan_br; + DECLARE_BITMAP(members, DSA_MAX_PORTS); + DECLARE_BITMAP(untagged, DSA_MAX_PORTS); + u16 vid; + int member, err; + + if (!ds->drv->vlan_getnext || !vid_begin) + return -EOPNOTSUPP; + + vid = vid_begin - 1; + + do { + err = ds->drv->vlan_getnext(ds, &vid, members, untagged); + if (err) + break; + + if (vid > vid_end) + break; + + member = find_first_bit(members, DSA_MAX_PORTS); + if (member == DSA_MAX_PORTS) + continue; + + dev = ds->ports[member]; + p = netdev_priv(dev); + vlan_br = p->bridge_dev; + if (vlan_br == bridge) + continue; + + netdev_dbg(vlan_br, "hardware VLAN %d already in use\n", vid); + return -EOPNOTSUPP; + } while (vid < vid_end); + + return err == -ENOENT ? 0 : err; +} + +static int dsa_slave_port_vlan_add(struct net_device *dev, + struct switchdev_obj *obj) +{ + struct switchdev_obj_vlan *vlan = &obj->u.vlan; struct dsa_slave_priv *p = netdev_priv(dev); struct dsa_switch *ds = p->parent; - int ret = -EOPNOTSUPP; + u16 vid; + int err; - if (ds->drv->fdb_add) - ret = ds->drv->fdb_add(ds, p->port, addr, vid); + switch (obj->trans) { + case SWITCHDEV_TRANS_PREPARE: + if (!ds->drv->port_vlan_add || !ds->drv->port_pvid_set) + return -EOPNOTSUPP; - return ret; + /* If the requested port doesn't belong to the same bridge as + * the VLAN members, fallback to software VLAN (hopefully). + */ + err = dsa_bridge_check_vlan_range(ds, p->bridge_dev, + vlan->vid_begin, + vlan->vid_end); + if (err) + return err; + break; + case SWITCHDEV_TRANS_COMMIT: + for (vid = vlan->vid_begin; vid <= vlan->vid_end; ++vid) { + err = ds->drv->port_vlan_add(ds, p->port, vid, + vlan->flags & + BRIDGE_VLAN_INFO_UNTAGGED); + if (!err && vlan->flags & BRIDGE_VLAN_INFO_PVID) + err = ds->drv->port_pvid_set(ds, p->port, vid); + if (err) + return err; + } + break; + default: + return -EOPNOTSUPP; + } + + return 0; } -static int dsa_slave_fdb_del(struct ndmsg *ndm, struct nlattr *tb[], - struct net_device *dev, - const unsigned char *addr, u16 vid) +static int dsa_slave_port_vlan_del(struct net_device *dev, + struct switchdev_obj *obj) { + struct switchdev_obj_vlan *vlan = &obj->u.vlan; struct dsa_slave_priv *p = netdev_priv(dev); struct dsa_switch *ds = p->parent; - int ret = -EOPNOTSUPP; + u16 vid; + int err; - if (ds->drv->fdb_del) - ret = ds->drv->fdb_del(ds, p->port, addr, vid); + if (!ds->drv->port_vlan_del) + return -EOPNOTSUPP; - return ret; + for (vid = vlan->vid_begin; vid <= vlan->vid_end; ++vid) { + err = ds->drv->port_vlan_del(ds, p->port, vid); + if (err) + return err; + } + + return 0; } -static int dsa_slave_fill_info(struct net_device *dev, struct sk_buff *skb, - const unsigned char *addr, u16 vid, - bool is_static, - u32 portid, u32 seq, int type, - unsigned int flags) +static int dsa_slave_port_vlan_dump(struct net_device *dev, + struct switchdev_obj *obj) { - struct nlmsghdr *nlh; - struct ndmsg *ndm; + struct switchdev_obj_vlan *vlan = &obj->u.vlan; + struct dsa_slave_priv *p = netdev_priv(dev); + struct dsa_switch *ds = p->parent; + DECLARE_BITMAP(members, DSA_MAX_PORTS); + DECLARE_BITMAP(untagged, DSA_MAX_PORTS); + u16 pvid, vid = 0; + int err; - nlh = nlmsg_put(skb, portid, seq, type, sizeof(*ndm), flags); - if (!nlh) - return -EMSGSIZE; + if (!ds->drv->vlan_getnext || !ds->drv->port_pvid_get) + return -EOPNOTSUPP; - ndm = nlmsg_data(nlh); - ndm->ndm_family = AF_BRIDGE; - ndm->ndm_pad1 = 0; - ndm->ndm_pad2 = 0; - ndm->ndm_flags = NTF_EXT_LEARNED; - ndm->ndm_type = 0; - ndm->ndm_ifindex = dev->ifindex; - ndm->ndm_state = is_static ? NUD_NOARP : NUD_REACHABLE; + err = ds->drv->port_pvid_get(ds, p->port, &pvid); + if (err) + return err; - if (nla_put(skb, NDA_LLADDR, ETH_ALEN, addr)) - goto nla_put_failure; + for (;;) { + err = ds->drv->vlan_getnext(ds, &vid, members, untagged); + if (err) + break; - if (vid && nla_put_u16(skb, NDA_VLAN, vid)) - goto nla_put_failure; + if (!test_bit(p->port, members)) + continue; - nlmsg_end(skb, nlh); - return 0; + memset(vlan, 0, sizeof(*vlan)); + vlan->vid_begin = vlan->vid_end = vid; + + if (vid == pvid) + vlan->flags |= BRIDGE_VLAN_INFO_PVID; + + if (test_bit(p->port, untagged)) + vlan->flags |= BRIDGE_VLAN_INFO_UNTAGGED; + + err = obj->cb(dev, obj); + if (err) + break; + } + + return err == -ENOENT ? 0 : err; +} -nla_put_failure: - nlmsg_cancel(skb, nlh); - return -EMSGSIZE; +static int dsa_slave_port_fdb_add(struct net_device *dev, + struct switchdev_obj *obj) +{ + struct switchdev_obj_fdb *fdb = &obj->u.fdb; + struct dsa_slave_priv *p = netdev_priv(dev); + struct dsa_switch *ds = p->parent; + int ret = -EOPNOTSUPP; + + if (obj->trans == SWITCHDEV_TRANS_PREPARE) + ret = ds->drv->port_fdb_add ? 0 : -EOPNOTSUPP; + else if (obj->trans == SWITCHDEV_TRANS_COMMIT) + ret = ds->drv->port_fdb_add(ds, p->port, fdb->addr, fdb->vid); + + return ret; } -/* Dump information about entries, in response to GETNEIGH */ -static int dsa_slave_fdb_dump(struct sk_buff *skb, struct netlink_callback *cb, - struct net_device *dev, - struct net_device *filter_dev, int idx) +static int dsa_slave_port_fdb_del(struct net_device *dev, + struct switchdev_obj *obj) +{ + struct switchdev_obj_fdb *fdb = &obj->u.fdb; + struct dsa_slave_priv *p = netdev_priv(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->addr, fdb->vid); + + return ret; +} + +static int dsa_slave_port_fdb_dump(struct net_device *dev, + struct switchdev_obj *obj) { struct dsa_slave_priv *p = netdev_priv(dev); struct dsa_switch *ds = p->parent; unsigned char addr[ETH_ALEN] = { 0 }; + u16 vid = 0; int ret; - if (!ds->drv->fdb_getnext) + if (!ds->drv->port_fdb_getnext) return -EOPNOTSUPP; - for (; ; idx++) { + for (;;) { bool is_static; - ret = ds->drv->fdb_getnext(ds, p->port, addr, &is_static); + ret = ds->drv->port_fdb_getnext(ds, p->port, addr, &vid, + &is_static); if (ret < 0) break; - if (idx < cb->args[0]) - continue; + obj->u.fdb.addr = addr; + obj->u.fdb.vid = vid; + obj->u.fdb.ndm_state = is_static ? NUD_NOARP : NUD_REACHABLE; - ret = dsa_slave_fill_info(dev, skb, addr, 0, - is_static, - NETLINK_CB(cb->skb).portid, - cb->nlh->nlmsg_seq, - RTM_NEWNEIGH, NLM_F_MULTI); + ret = obj->cb(dev, obj); if (ret < 0) break; } - return idx; + return ret == -ENOENT ? 0 : ret; } static int dsa_slave_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) @@ -363,6 +473,71 @@ static int dsa_slave_port_attr_set(struct net_device *dev, return ret; } +static int dsa_slave_port_obj_add(struct net_device *dev, + struct switchdev_obj *obj) +{ + int err; + + /* For the prepare phase, ensure the full set of changes is feasable in + * one go in order to signal a failure properly. If an operation is not + * supported, return -EOPNOTSUPP. + */ + + switch (obj->id) { + case SWITCHDEV_OBJ_PORT_FDB: + err = dsa_slave_port_fdb_add(dev, obj); + break; + case SWITCHDEV_OBJ_PORT_VLAN: + err = dsa_slave_port_vlan_add(dev, obj); + break; + default: + err = -EOPNOTSUPP; + break; + } + + return err; +} + +static int dsa_slave_port_obj_del(struct net_device *dev, + struct switchdev_obj *obj) +{ + int err; + + switch (obj->id) { + case SWITCHDEV_OBJ_PORT_FDB: + err = dsa_slave_port_fdb_del(dev, obj); + break; + case SWITCHDEV_OBJ_PORT_VLAN: + err = dsa_slave_port_vlan_del(dev, obj); + break; + default: + err = -EOPNOTSUPP; + break; + } + + return err; +} + +static int dsa_slave_port_obj_dump(struct net_device *dev, + struct switchdev_obj *obj) +{ + int err; + + switch (obj->id) { + case SWITCHDEV_OBJ_PORT_FDB: + err = dsa_slave_port_fdb_dump(dev, obj); + break; + case SWITCHDEV_OBJ_PORT_VLAN: + err = dsa_slave_port_vlan_dump(dev, obj); + break; + default: + err = -EOPNOTSUPP; + break; + } + + return err; +} + static int dsa_slave_bridge_port_join(struct net_device *dev, struct net_device *br) { @@ -418,24 +593,53 @@ static int dsa_slave_port_attr_get(struct net_device *dev, return 0; } -static netdev_tx_t dsa_slave_xmit(struct sk_buff *skb, struct net_device *dev) +static inline netdev_tx_t dsa_netpoll_send_skb(struct dsa_slave_priv *p, + struct sk_buff *skb) { - struct dsa_slave_priv *p = netdev_priv(dev); - - return p->xmit(skb, dev); +#ifdef CONFIG_NET_POLL_CONTROLLER + if (p->netpoll) + netpoll_send_skb(p->netpoll, skb); +#else + BUG(); +#endif + return NETDEV_TX_OK; } -static netdev_tx_t dsa_slave_notag_xmit(struct sk_buff *skb, - struct net_device *dev) +static netdev_tx_t dsa_slave_xmit(struct sk_buff *skb, struct net_device *dev) { struct dsa_slave_priv *p = netdev_priv(dev); + struct sk_buff *nskb; + + dev->stats.tx_packets++; + dev->stats.tx_bytes += skb->len; + + /* Transmit function may have to reallocate the original SKB */ + nskb = p->xmit(skb, dev); + if (!nskb) + return NETDEV_TX_OK; - skb->dev = p->parent->dst->master_netdev; - dev_queue_xmit(skb); + /* SKB for netpoll still need to be mangled with the protocol-specific + * tag to be successfully transmitted + */ + if (unlikely(netpoll_tx_running(dev))) + return dsa_netpoll_send_skb(p, nskb); + + /* Queue the SKB for transmission on the parent interface, but + * do not modify its EtherType + */ + nskb->dev = p->parent->dst->master_netdev; + dev_queue_xmit(nskb); return NETDEV_TX_OK; } +static struct sk_buff *dsa_slave_notag_xmit(struct sk_buff *skb, + struct net_device *dev) +{ + /* Just return the original SKB */ + return skb; +} + /* ethtool operations *******************************************************/ static int @@ -665,6 +869,49 @@ static int dsa_slave_get_eee(struct net_device *dev, struct ethtool_eee *e) return ret; } +#ifdef CONFIG_NET_POLL_CONTROLLER +static int dsa_slave_netpoll_setup(struct net_device *dev, + struct netpoll_info *ni) +{ + struct dsa_slave_priv *p = netdev_priv(dev); + struct dsa_switch *ds = p->parent; + struct net_device *master = ds->dst->master_netdev; + struct netpoll *netpoll; + int err = 0; + + netpoll = kzalloc(sizeof(*netpoll), GFP_KERNEL); + if (!netpoll) + return -ENOMEM; + + err = __netpoll_setup(netpoll, master); + if (err) { + kfree(netpoll); + goto out; + } + + p->netpoll = netpoll; +out: + return err; +} + +static void dsa_slave_netpoll_cleanup(struct net_device *dev) +{ + struct dsa_slave_priv *p = netdev_priv(dev); + struct netpoll *netpoll = p->netpoll; + + if (!netpoll) + return; + + p->netpoll = NULL; + + __netpoll_free_async(netpoll); +} + +static void dsa_slave_poll_controller(struct net_device *dev) +{ +} +#endif + static const struct ethtool_ops dsa_slave_ethtool_ops = { .get_settings = dsa_slave_get_settings, .set_settings = dsa_slave_set_settings, @@ -692,16 +939,27 @@ static const struct net_device_ops dsa_slave_netdev_ops = { .ndo_change_rx_flags = dsa_slave_change_rx_flags, .ndo_set_rx_mode = dsa_slave_set_rx_mode, .ndo_set_mac_address = dsa_slave_set_mac_address, - .ndo_fdb_add = dsa_slave_fdb_add, - .ndo_fdb_del = dsa_slave_fdb_del, - .ndo_fdb_dump = dsa_slave_fdb_dump, + .ndo_fdb_add = switchdev_port_fdb_add, + .ndo_fdb_del = switchdev_port_fdb_del, + .ndo_fdb_dump = switchdev_port_fdb_dump, .ndo_do_ioctl = dsa_slave_ioctl, .ndo_get_iflink = dsa_slave_get_iflink, +#ifdef CONFIG_NET_POLL_CONTROLLER + .ndo_netpoll_setup = dsa_slave_netpoll_setup, + .ndo_netpoll_cleanup = dsa_slave_netpoll_cleanup, + .ndo_poll_controller = dsa_slave_poll_controller, +#endif + .ndo_bridge_getlink = switchdev_port_bridge_getlink, + .ndo_bridge_setlink = switchdev_port_bridge_setlink, + .ndo_bridge_dellink = switchdev_port_bridge_dellink, }; static const struct switchdev_ops dsa_slave_switchdev_ops = { .switchdev_port_attr_get = dsa_slave_port_attr_get, .switchdev_port_attr_set = dsa_slave_port_attr_set, + .switchdev_port_obj_add = dsa_slave_port_obj_add, + .switchdev_port_obj_del = dsa_slave_port_obj_del, + .switchdev_port_obj_dump = dsa_slave_port_obj_dump, }; static void dsa_slave_adjust_link(struct net_device *dev) @@ -889,7 +1147,7 @@ int dsa_slave_create(struct dsa_switch *ds, struct device *parent, slave_dev->features = master->vlan_features; slave_dev->ethtool_ops = &dsa_slave_ethtool_ops; eth_hw_addr_inherit(slave_dev, master); - slave_dev->tx_queue_len = 0; + slave_dev->priv_flags |= IFF_NO_QUEUE; slave_dev->netdev_ops = &dsa_slave_netdev_ops; slave_dev->switchdev_ops = &dsa_slave_switchdev_ops; diff --git a/net/dsa/tag_brcm.c b/net/dsa/tag_brcm.c index 83d3572cdb20..e2aadb73111d 100644 --- a/net/dsa/tag_brcm.c +++ b/net/dsa/tag_brcm.c @@ -58,14 +58,11 @@ #define BRCM_EG_TC_MASK 0x7 #define BRCM_EG_PID_MASK 0x1f -static netdev_tx_t brcm_tag_xmit(struct sk_buff *skb, struct net_device *dev) +static struct sk_buff *brcm_tag_xmit(struct sk_buff *skb, struct net_device *dev) { struct dsa_slave_priv *p = netdev_priv(dev); u8 *brcm_tag; - dev->stats.tx_packets++; - dev->stats.tx_bytes += skb->len; - if (skb_cow_head(skb, BRCM_TAG_LEN) < 0) goto out_free; @@ -87,17 +84,11 @@ static netdev_tx_t brcm_tag_xmit(struct sk_buff *skb, struct net_device *dev) brcm_tag[2] = BRCM_IG_DSTMAP2_MASK; brcm_tag[3] = (1 << p->port) & BRCM_IG_DSTMAP1_MASK; - /* Queue the SKB for transmission on the parent interface, but - * do not modify its EtherType - */ - skb->dev = p->parent->dst->master_netdev; - dev_queue_xmit(skb); - - return NETDEV_TX_OK; + return skb; out_free: kfree_skb(skb); - return NETDEV_TX_OK; + return NULL; } static int brcm_tag_rcv(struct sk_buff *skb, struct net_device *dev, diff --git a/net/dsa/tag_dsa.c b/net/dsa/tag_dsa.c index 2dab27063273..aa780e4ac0bd 100644 --- a/net/dsa/tag_dsa.c +++ b/net/dsa/tag_dsa.c @@ -15,14 +15,11 @@ #define DSA_HLEN 4 -static netdev_tx_t dsa_xmit(struct sk_buff *skb, struct net_device *dev) +static struct sk_buff *dsa_xmit(struct sk_buff *skb, struct net_device *dev) { struct dsa_slave_priv *p = netdev_priv(dev); u8 *dsa_header; - dev->stats.tx_packets++; - dev->stats.tx_bytes += skb->len; - /* * Convert the outermost 802.1q tag to a DSA tag for tagged * packets, or insert a DSA tag between the addresses and @@ -63,14 +60,11 @@ static netdev_tx_t dsa_xmit(struct sk_buff *skb, struct net_device *dev) dsa_header[3] = 0x00; } - skb->dev = p->parent->dst->master_netdev; - dev_queue_xmit(skb); - - return NETDEV_TX_OK; + return skb; out_free: kfree_skb(skb); - return NETDEV_TX_OK; + return NULL; } static int dsa_rcv(struct sk_buff *skb, struct net_device *dev, diff --git a/net/dsa/tag_edsa.c b/net/dsa/tag_edsa.c index 9aeda596f7ec..2288c8098c42 100644 --- a/net/dsa/tag_edsa.c +++ b/net/dsa/tag_edsa.c @@ -16,14 +16,11 @@ #define DSA_HLEN 4 #define EDSA_HLEN 8 -static netdev_tx_t edsa_xmit(struct sk_buff *skb, struct net_device *dev) +static struct sk_buff *edsa_xmit(struct sk_buff *skb, struct net_device *dev) { struct dsa_slave_priv *p = netdev_priv(dev); u8 *edsa_header; - dev->stats.tx_packets++; - dev->stats.tx_bytes += skb->len; - /* * Convert the outermost 802.1q tag to a DSA tag and prepend * a DSA ethertype field is the packet is tagged, or insert @@ -76,14 +73,11 @@ static netdev_tx_t edsa_xmit(struct sk_buff *skb, struct net_device *dev) edsa_header[7] = 0x00; } - skb->dev = p->parent->dst->master_netdev; - dev_queue_xmit(skb); - - return NETDEV_TX_OK; + return skb; out_free: kfree_skb(skb); - return NETDEV_TX_OK; + return NULL; } static int edsa_rcv(struct sk_buff *skb, struct net_device *dev, diff --git a/net/dsa/tag_trailer.c b/net/dsa/tag_trailer.c index e268f9db8893..d25efc93d8f1 100644 --- a/net/dsa/tag_trailer.c +++ b/net/dsa/tag_trailer.c @@ -13,16 +13,13 @@ #include <linux/slab.h> #include "dsa_priv.h" -static netdev_tx_t trailer_xmit(struct sk_buff *skb, struct net_device *dev) +static struct sk_buff *trailer_xmit(struct sk_buff *skb, struct net_device *dev) { struct dsa_slave_priv *p = netdev_priv(dev); struct sk_buff *nskb; int padlen; u8 *trailer; - dev->stats.tx_packets++; - dev->stats.tx_bytes += skb->len; - /* * We have to make sure that the trailer ends up as the very * last 4 bytes of the packet. This means that we have to pad @@ -36,7 +33,7 @@ static netdev_tx_t trailer_xmit(struct sk_buff *skb, struct net_device *dev) nskb = alloc_skb(NET_IP_ALIGN + skb->len + padlen + 4, GFP_ATOMIC); if (nskb == NULL) { kfree_skb(skb); - return NETDEV_TX_OK; + return NULL; } skb_reserve(nskb, NET_IP_ALIGN); @@ -57,10 +54,7 @@ static netdev_tx_t trailer_xmit(struct sk_buff *skb, struct net_device *dev) trailer[2] = 0x10; trailer[3] = 0x00; - nskb->dev = p->parent->dst->master_netdev; - dev_queue_xmit(nskb); - - return NETDEV_TX_OK; + return nskb; } static int trailer_rcv(struct sk_buff *skb, struct net_device *dev, diff --git a/net/ethernet/eth.c b/net/ethernet/eth.c index 77e0f0e7a88e..d850fdc828f9 100644 --- a/net/ethernet/eth.c +++ b/net/ethernet/eth.c @@ -114,7 +114,7 @@ int eth_header(struct sk_buff *skb, struct net_device *dev, EXPORT_SYMBOL(eth_header); /** - * eth_get_headlen - determine the the length of header for an ethernet frame + * eth_get_headlen - determine the length of header for an ethernet frame * @data: pointer to start of frame * @len: total length of frame * @@ -132,7 +132,7 @@ u32 eth_get_headlen(void *data, unsigned int len) /* parse any remaining L2/L3 headers, check for L4 */ if (!skb_flow_dissect_flow_keys_buf(&keys, data, eth->h_proto, - sizeof(*eth), len)) + sizeof(*eth), len, 0)) return max_t(u32, keys.control.thoff, sizeof(*eth)); /* parse for any L4 headers */ diff --git a/net/hsr/hsr_device.c b/net/hsr/hsr_device.c index 44d27469ae55..35a9788bb3ae 100644 --- a/net/hsr/hsr_device.c +++ b/net/hsr/hsr_device.c @@ -392,7 +392,7 @@ void hsr_dev_setup(struct net_device *dev) dev->header_ops = &hsr_header_ops; dev->netdev_ops = &hsr_device_ops; SET_NETDEV_DEVTYPE(dev, &hsr_type); - dev->tx_queue_len = 0; + dev->priv_flags |= IFF_NO_QUEUE; dev->destructor = hsr_dev_destroy; diff --git a/net/ieee802154/6lowpan/6lowpan_i.h b/net/ieee802154/6lowpan/6lowpan_i.h index e50f69da78eb..ea339fa94c27 100644 --- a/net/ieee802154/6lowpan/6lowpan_i.h +++ b/net/ieee802154/6lowpan/6lowpan_i.h @@ -5,6 +5,7 @@ #include <net/ieee802154_netdev.h> #include <net/inet_frag.h> +#include <net/6lowpan.h> struct lowpan_create_arg { u16 tag; @@ -37,26 +38,18 @@ static inline u32 ieee802154_addr_hash(const struct ieee802154_addr *a) } } -struct lowpan_dev_record { - struct net_device *ldev; - struct list_head list; -}; - /* private device info */ struct lowpan_dev_info { struct net_device *real_dev; /* real WPAN device ptr */ - struct mutex dev_list_mtx; /* mutex for list ops */ u16 fragment_tag; }; static inline struct lowpan_dev_info *lowpan_dev_info(const struct net_device *dev) { - return netdev_priv(dev); + return (struct lowpan_dev_info *)lowpan_priv(dev)->priv; } -extern struct list_head lowpan_devices; - int lowpan_frag_rcv(struct sk_buff *skb, const u8 frag_type); void lowpan_net_frag_exit(void); int lowpan_net_frag_init(void); diff --git a/net/ieee802154/6lowpan/core.c b/net/ieee802154/6lowpan/core.c index f20a387a1011..953b1c49f5d1 100644 --- a/net/ieee802154/6lowpan/core.c +++ b/net/ieee802154/6lowpan/core.c @@ -52,8 +52,7 @@ #include "6lowpan_i.h" -LIST_HEAD(lowpan_devices); -static int lowpan_open_count; +static int open_count; static struct header_ops lowpan_header_ops = { .create = lowpan_header_create, @@ -91,7 +90,7 @@ static void lowpan_setup(struct net_device *dev) dev->hard_header_len = 2 + 1 + 20 + 14; dev->needed_tailroom = 2; /* FCS */ dev->mtu = IPV6_MIN_MTU; - dev->tx_queue_len = 0; + dev->priv_flags |= IFF_NO_QUEUE; dev->flags = IFF_BROADCAST | IFF_MULTICAST; dev->watchdog_timeo = 0; @@ -114,7 +113,6 @@ static int lowpan_newlink(struct net *src_net, struct net_device *dev, struct nlattr *tb[], struct nlattr *data[]) { struct net_device *real_dev; - struct lowpan_dev_record *entry; int ret; ASSERT_RTNL(); @@ -133,67 +131,52 @@ static int lowpan_newlink(struct net *src_net, struct net_device *dev, return -EINVAL; } - lowpan_dev_info(dev)->real_dev = real_dev; - mutex_init(&lowpan_dev_info(dev)->dev_list_mtx); - - entry = kzalloc(sizeof(*entry), GFP_KERNEL); - if (!entry) { + if (real_dev->ieee802154_ptr->lowpan_dev) { dev_put(real_dev); - lowpan_dev_info(dev)->real_dev = NULL; - return -ENOMEM; + return -EBUSY; } - entry->ldev = dev; - + lowpan_dev_info(dev)->real_dev = real_dev; /* Set the lowpan hardware address to the wpan hardware address. */ memcpy(dev->dev_addr, real_dev->dev_addr, IEEE802154_ADDR_LEN); - mutex_lock(&lowpan_dev_info(dev)->dev_list_mtx); - INIT_LIST_HEAD(&entry->list); - list_add_tail(&entry->list, &lowpan_devices); - mutex_unlock(&lowpan_dev_info(dev)->dev_list_mtx); + lowpan_netdev_setup(dev, LOWPAN_LLTYPE_IEEE802154); ret = register_netdevice(dev); - if (ret >= 0) { - if (!lowpan_open_count) - lowpan_rx_init(); - lowpan_open_count++; + if (ret < 0) { + dev_put(real_dev); + return ret; } - return ret; + real_dev->ieee802154_ptr->lowpan_dev = dev; + if (!open_count) + lowpan_rx_init(); + + open_count++; + + return 0; } static void lowpan_dellink(struct net_device *dev, struct list_head *head) { struct lowpan_dev_info *lowpan_dev = lowpan_dev_info(dev); struct net_device *real_dev = lowpan_dev->real_dev; - struct lowpan_dev_record *entry, *tmp; ASSERT_RTNL(); - lowpan_open_count--; - if (!lowpan_open_count) - lowpan_rx_exit(); - - mutex_lock(&lowpan_dev_info(dev)->dev_list_mtx); - list_for_each_entry_safe(entry, tmp, &lowpan_devices, list) { - if (entry->ldev == dev) { - list_del(&entry->list); - kfree(entry); - } - } - mutex_unlock(&lowpan_dev_info(dev)->dev_list_mtx); + open_count--; - mutex_destroy(&lowpan_dev_info(dev)->dev_list_mtx); - - unregister_netdevice_queue(dev, head); + if (!open_count) + lowpan_rx_exit(); + real_dev->ieee802154_ptr->lowpan_dev = NULL; + unregister_netdevice(dev); dev_put(real_dev); } static struct rtnl_link_ops lowpan_link_ops __read_mostly = { .kind = "lowpan", - .priv_size = sizeof(struct lowpan_dev_info), + .priv_size = LOWPAN_PRIV_SIZE(sizeof(struct lowpan_dev_info)), .setup = lowpan_setup, .newlink = lowpan_newlink, .dellink = lowpan_dellink, @@ -214,19 +197,21 @@ static int lowpan_device_event(struct notifier_block *unused, unsigned long event, void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); - LIST_HEAD(del_list); - struct lowpan_dev_record *entry, *tmp; if (dev->type != ARPHRD_IEEE802154) goto out; - if (event == NETDEV_UNREGISTER) { - list_for_each_entry_safe(entry, tmp, &lowpan_devices, list) { - if (lowpan_dev_info(entry->ldev)->real_dev == dev) - lowpan_dellink(entry->ldev, &del_list); - } - - unregister_netdevice_many(&del_list); + switch (event) { + case NETDEV_UNREGISTER: + /* Check if wpan interface is unregistered that we + * also delete possible lowpan interfaces which belongs + * to the wpan interface. + */ + if (dev->ieee802154_ptr && dev->ieee802154_ptr->lowpan_dev) + lowpan_dellink(dev->ieee802154_ptr->lowpan_dev, NULL); + break; + default: + break; } out: diff --git a/net/ieee802154/6lowpan/rx.c b/net/ieee802154/6lowpan/rx.c index 4be1d289ab2d..12e10201d263 100644 --- a/net/ieee802154/6lowpan/rx.c +++ b/net/ieee802154/6lowpan/rx.c @@ -15,36 +15,14 @@ #include "6lowpan_i.h" -static int lowpan_give_skb_to_devices(struct sk_buff *skb, - struct net_device *dev) +static int lowpan_give_skb_to_device(struct sk_buff *skb, + struct net_device *dev) { - struct lowpan_dev_record *entry; - struct sk_buff *skb_cp; - int stat = NET_RX_SUCCESS; - + skb->dev = dev->ieee802154_ptr->lowpan_dev; skb->protocol = htons(ETH_P_IPV6); skb->pkt_type = PACKET_HOST; - rcu_read_lock(); - list_for_each_entry_rcu(entry, &lowpan_devices, list) - if (lowpan_dev_info(entry->ldev)->real_dev == skb->dev) { - skb_cp = skb_copy(skb, GFP_ATOMIC); - if (!skb_cp) { - kfree_skb(skb); - rcu_read_unlock(); - return NET_RX_DROP; - } - - skb_cp->dev = entry->ldev; - stat = netif_rx(skb_cp); - if (stat == NET_RX_DROP) - break; - } - rcu_read_unlock(); - - consume_skb(skb); - - return stat; + return netif_rx(skb); } static int @@ -89,6 +67,10 @@ static int lowpan_rcv(struct sk_buff *skb, struct net_device *dev, struct ieee802154_hdr hdr; int ret; + if (dev->type != ARPHRD_IEEE802154 || + !dev->ieee802154_ptr->lowpan_dev) + goto drop; + skb = skb_share_check(skb, GFP_ATOMIC); if (!skb) goto drop; @@ -99,9 +81,6 @@ static int lowpan_rcv(struct sk_buff *skb, struct net_device *dev, if (skb->pkt_type == PACKET_OTHERHOST) goto drop_skb; - if (dev->type != ARPHRD_IEEE802154) - goto drop_skb; - if (ieee802154_hdr_peek_addrs(skb, &hdr) < 0) goto drop_skb; @@ -109,7 +88,7 @@ static int lowpan_rcv(struct sk_buff *skb, struct net_device *dev, if (skb->data[0] == LOWPAN_DISPATCH_IPV6) { /* Pull off the 1-byte of 6lowpan header. */ skb_pull(skb, 1); - return lowpan_give_skb_to_devices(skb, NULL); + return lowpan_give_skb_to_device(skb, dev); } else { switch (skb->data[0] & 0xe0) { case LOWPAN_DISPATCH_IPHC: /* ipv6 datagram */ @@ -117,7 +96,7 @@ static int lowpan_rcv(struct sk_buff *skb, struct net_device *dev, if (ret < 0) goto drop_skb; - return lowpan_give_skb_to_devices(skb, NULL); + return lowpan_give_skb_to_device(skb, dev); case LOWPAN_DISPATCH_FRAG1: /* first fragment header */ ret = lowpan_frag_rcv(skb, LOWPAN_DISPATCH_FRAG1); if (ret == 1) { @@ -125,7 +104,7 @@ static int lowpan_rcv(struct sk_buff *skb, struct net_device *dev, if (ret < 0) goto drop_skb; - return lowpan_give_skb_to_devices(skb, NULL); + return lowpan_give_skb_to_device(skb, dev); } else if (ret == -1) { return NET_RX_DROP; } else { @@ -138,7 +117,7 @@ static int lowpan_rcv(struct sk_buff *skb, struct net_device *dev, if (ret < 0) goto drop_skb; - return lowpan_give_skb_to_devices(skb, NULL); + return lowpan_give_skb_to_device(skb, dev); } else if (ret == -1) { return NET_RX_DROP; } else { diff --git a/net/ieee802154/6lowpan/tx.c b/net/ieee802154/6lowpan/tx.c index 2597abbf7f4b..f6263fc12340 100644 --- a/net/ieee802154/6lowpan/tx.c +++ b/net/ieee802154/6lowpan/tx.c @@ -112,7 +112,7 @@ lowpan_xmit_fragment(struct sk_buff *skb, const struct ieee802154_hdr *wpan_hdr, frag = lowpan_alloc_frag(skb, frag_hdrlen + len, wpan_hdr); if (IS_ERR(frag)) - return -PTR_ERR(frag); + return PTR_ERR(frag); memcpy(skb_put(frag, frag_hdrlen), frag_hdr, frag_hdrlen); memcpy(skb_put(frag, len), skb_network_header(skb) + offset, len); @@ -224,7 +224,7 @@ static int lowpan_header(struct sk_buff *skb, struct net_device *dev) } else { da.mode = IEEE802154_ADDR_LONG; da.extended_addr = ieee802154_devaddr_from_raw(daddr); - cb->ackreq = wpan_dev->frame_retries >= 0; + cb->ackreq = wpan_dev->ackreq; } return dev_hard_header(skb, lowpan_dev_info(dev)->real_dev, diff --git a/net/ieee802154/nl802154.c b/net/ieee802154/nl802154.c index 68f24016860c..3f89c0abdab1 100644 --- a/net/ieee802154/nl802154.c +++ b/net/ieee802154/nl802154.c @@ -230,6 +230,8 @@ static const struct nla_policy nl802154_policy[NL802154_ATTR_MAX+1] = { [NL802154_ATTR_WPAN_PHY_CAPS] = { .type = NLA_NESTED }, [NL802154_ATTR_SUPPORTED_COMMANDS] = { .type = NLA_NESTED }, + + [NL802154_ATTR_ACKREQ_DEFAULT] = { .type = NLA_U8 }, }; /* message building helper */ @@ -458,6 +460,7 @@ static int nl802154_send_wpan_phy(struct cfg802154_registered_device *rdev, CMD(set_max_csma_backoffs, SET_MAX_CSMA_BACKOFFS); CMD(set_max_frame_retries, SET_MAX_FRAME_RETRIES); CMD(set_lbt_mode, SET_LBT_MODE); + CMD(set_ackreq_default, SET_ACKREQ_DEFAULT); if (rdev->wpan_phy.flags & WPAN_PHY_FLAG_TXPOWER) CMD(set_tx_power, SET_TX_POWER); @@ -656,6 +659,10 @@ nl802154_send_iface(struct sk_buff *msg, u32 portid, u32 seq, int flags, if (nla_put_u8(msg, NL802154_ATTR_LBT_MODE, wpan_dev->lbt)) goto nla_put_failure; + /* ackreq default behaviour */ + if (nla_put_u8(msg, NL802154_ATTR_ACKREQ_DEFAULT, wpan_dev->ackreq)) + goto nla_put_failure; + genlmsg_end(msg, hdr); return 0; @@ -1027,7 +1034,7 @@ static int nl802154_set_lbt_mode(struct sk_buff *skb, struct genl_info *info) struct cfg802154_registered_device *rdev = info->user_ptr[0]; struct net_device *dev = info->user_ptr[1]; struct wpan_dev *wpan_dev = dev->ieee802154_ptr; - bool mode; + int mode; if (netif_running(dev)) return -EBUSY; @@ -1035,13 +1042,39 @@ static int nl802154_set_lbt_mode(struct sk_buff *skb, struct genl_info *info) if (!info->attrs[NL802154_ATTR_LBT_MODE]) return -EINVAL; - mode = !!nla_get_u8(info->attrs[NL802154_ATTR_LBT_MODE]); + mode = nla_get_u8(info->attrs[NL802154_ATTR_LBT_MODE]); + + if (mode != 0 && mode != 1) + return -EINVAL; + if (!wpan_phy_supported_bool(mode, rdev->wpan_phy.supported.lbt)) return -EINVAL; return rdev_set_lbt_mode(rdev, wpan_dev, mode); } +static int +nl802154_set_ackreq_default(struct sk_buff *skb, struct genl_info *info) +{ + struct cfg802154_registered_device *rdev = info->user_ptr[0]; + struct net_device *dev = info->user_ptr[1]; + struct wpan_dev *wpan_dev = dev->ieee802154_ptr; + int ackreq; + + if (netif_running(dev)) + return -EBUSY; + + if (!info->attrs[NL802154_ATTR_ACKREQ_DEFAULT]) + return -EINVAL; + + ackreq = nla_get_u8(info->attrs[NL802154_ATTR_ACKREQ_DEFAULT]); + + if (ackreq != 0 && ackreq != 1) + return -EINVAL; + + return rdev_set_ackreq_default(rdev, wpan_dev, ackreq); +} + #define NL802154_FLAG_NEED_WPAN_PHY 0x01 #define NL802154_FLAG_NEED_NETDEV 0x02 #define NL802154_FLAG_NEED_RTNL 0x04 @@ -1248,6 +1281,14 @@ static const struct genl_ops nl802154_ops[] = { .internal_flags = NL802154_FLAG_NEED_NETDEV | NL802154_FLAG_NEED_RTNL, }, + { + .cmd = NL802154_CMD_SET_ACKREQ_DEFAULT, + .doit = nl802154_set_ackreq_default, + .policy = nl802154_policy, + .flags = GENL_ADMIN_PERM, + .internal_flags = NL802154_FLAG_NEED_NETDEV | + NL802154_FLAG_NEED_RTNL, + }, }; /* initialisation/exit functions */ diff --git a/net/ieee802154/rdev-ops.h b/net/ieee802154/rdev-ops.h index b2155a123f6c..03b357501cc5 100644 --- a/net/ieee802154/rdev-ops.h +++ b/net/ieee802154/rdev-ops.h @@ -24,6 +24,26 @@ rdev_del_virtual_intf_deprecated(struct cfg802154_registered_device *rdev, } static inline int +rdev_suspend(struct cfg802154_registered_device *rdev) +{ + int ret; + trace_802154_rdev_suspend(&rdev->wpan_phy); + ret = rdev->ops->suspend(&rdev->wpan_phy); + trace_802154_rdev_return_int(&rdev->wpan_phy, ret); + return ret; +} + +static inline int +rdev_resume(struct cfg802154_registered_device *rdev) +{ + int ret; + trace_802154_rdev_resume(&rdev->wpan_phy); + ret = rdev->ops->resume(&rdev->wpan_phy); + trace_802154_rdev_return_int(&rdev->wpan_phy, ret); + return ret; +} + +static inline int rdev_add_virtual_intf(struct cfg802154_registered_device *rdev, char *name, unsigned char name_assign_type, enum nl802154_iftype type, __le64 extended_addr) @@ -175,4 +195,17 @@ rdev_set_lbt_mode(struct cfg802154_registered_device *rdev, return ret; } +static inline int +rdev_set_ackreq_default(struct cfg802154_registered_device *rdev, + struct wpan_dev *wpan_dev, bool ackreq) +{ + int ret; + + trace_802154_rdev_set_ackreq_default(&rdev->wpan_phy, wpan_dev, + ackreq); + ret = rdev->ops->set_ackreq_default(&rdev->wpan_phy, wpan_dev, ackreq); + trace_802154_rdev_return_int(&rdev->wpan_phy, ret); + return ret; +} + #endif /* __CFG802154_RDEV_OPS */ diff --git a/net/ieee802154/sysfs.c b/net/ieee802154/sysfs.c index 133b4280660c..bd88525b041e 100644 --- a/net/ieee802154/sysfs.c +++ b/net/ieee802154/sysfs.c @@ -14,11 +14,13 @@ */ #include <linux/device.h> +#include <linux/rtnetlink.h> #include <net/cfg802154.h> #include "core.h" #include "sysfs.h" +#include "rdev-ops.h" static inline struct cfg802154_registered_device * dev_to_rdev(struct device *dev) @@ -62,10 +64,46 @@ static struct attribute *pmib_attrs[] = { }; ATTRIBUTE_GROUPS(pmib); +#ifdef CONFIG_PM_SLEEP +static int wpan_phy_suspend(struct device *dev) +{ + struct cfg802154_registered_device *rdev = dev_to_rdev(dev); + int ret = 0; + + if (rdev->ops->suspend) { + rtnl_lock(); + ret = rdev_suspend(rdev); + rtnl_unlock(); + } + + return ret; +} + +static int wpan_phy_resume(struct device *dev) +{ + struct cfg802154_registered_device *rdev = dev_to_rdev(dev); + int ret = 0; + + if (rdev->ops->resume) { + rtnl_lock(); + ret = rdev_resume(rdev); + rtnl_unlock(); + } + + return ret; +} + +static SIMPLE_DEV_PM_OPS(wpan_phy_pm_ops, wpan_phy_suspend, wpan_phy_resume); +#define WPAN_PHY_PM_OPS (&wpan_phy_pm_ops) +#else +#define WPAN_PHY_PM_OPS NULL +#endif + struct class wpan_phy_class = { .name = "ieee802154", .dev_release = wpan_phy_release, .dev_groups = pmib_groups, + .pm = WPAN_PHY_PM_OPS, }; int wpan_phy_sysfs_init(void) diff --git a/net/ieee802154/trace.h b/net/ieee802154/trace.h index 9b5f0eb36696..9a471e41ec73 100644 --- a/net/ieee802154/trace.h +++ b/net/ieee802154/trace.h @@ -40,6 +40,28 @@ * rdev->ops traces * *************************************************************/ +DECLARE_EVENT_CLASS(wpan_phy_only_evt, + TP_PROTO(struct wpan_phy *wpan_phy), + TP_ARGS(wpan_phy), + TP_STRUCT__entry( + WPAN_PHY_ENTRY + ), + TP_fast_assign( + WPAN_PHY_ASSIGN; + ), + TP_printk(WPAN_PHY_PR_FMT, WPAN_PHY_PR_ARG) +); + +DEFINE_EVENT(wpan_phy_only_evt, 802154_rdev_suspend, + TP_PROTO(struct wpan_phy *wpan_phy), + TP_ARGS(wpan_phy) +); + +DEFINE_EVENT(wpan_phy_only_evt, 802154_rdev_resume, + TP_PROTO(struct wpan_phy *wpan_phy), + TP_ARGS(wpan_phy) +); + TRACE_EVENT(802154_rdev_add_virtual_intf, TP_PROTO(struct wpan_phy *wpan_phy, char *name, enum nl802154_iftype type, __le64 extended_addr), @@ -253,6 +275,25 @@ TRACE_EVENT(802154_rdev_set_lbt_mode, WPAN_DEV_PR_ARG, BOOL_TO_STR(__entry->mode)) ); +TRACE_EVENT(802154_rdev_set_ackreq_default, + TP_PROTO(struct wpan_phy *wpan_phy, struct wpan_dev *wpan_dev, + bool ackreq), + TP_ARGS(wpan_phy, wpan_dev, ackreq), + TP_STRUCT__entry( + WPAN_PHY_ENTRY + WPAN_DEV_ENTRY + __field(bool, ackreq) + ), + TP_fast_assign( + WPAN_PHY_ASSIGN; + WPAN_DEV_ASSIGN; + __entry->ackreq = ackreq; + ), + TP_printk(WPAN_PHY_PR_FMT ", " WPAN_DEV_PR_FMT + ", ackreq default: %s", WPAN_PHY_PR_ARG, + WPAN_DEV_PR_ARG, BOOL_TO_STR(__entry->ackreq)) +); + TRACE_EVENT(802154_rdev_return_int, TP_PROTO(struct wpan_phy *wpan_phy, int ret), TP_ARGS(wpan_phy, ret), diff --git a/net/ipv4/Kconfig b/net/ipv4/Kconfig index 6fb3c90ad726..416dfa004cfb 100644 --- a/net/ipv4/Kconfig +++ b/net/ipv4/Kconfig @@ -331,20 +331,6 @@ config NET_FOU_IP_TUNNELS When this option is enabled IP tunnels can be configured to use FOU or GUE encapsulation. -config GENEVE_CORE - tristate "Generic Network Virtualization Encapsulation library" - depends on INET - select NET_UDP_TUNNEL - ---help--- - This allows one to create Geneve virtual interfaces that provide - Layer 2 Networks over Layer 3 Networks. Geneve is often used - to tunnel virtual network infrastructure in virtualized environments. - For more information see: - http://tools.ietf.org/html/draft-gross-geneve-01 - - To compile this driver as a module, choose M here: the module - - config INET_AH tristate "IP: AH transformation" select XFRM_ALGO diff --git a/net/ipv4/Makefile b/net/ipv4/Makefile index efc43f300b8c..89aacb630a53 100644 --- a/net/ipv4/Makefile +++ b/net/ipv4/Makefile @@ -57,7 +57,6 @@ obj-$(CONFIG_TCP_CONG_YEAH) += tcp_yeah.o obj-$(CONFIG_TCP_CONG_ILLINOIS) += tcp_illinois.o obj-$(CONFIG_MEMCG_KMEM) += tcp_memcontrol.o obj-$(CONFIG_NETLABEL) += cipso_ipv4.o -obj-$(CONFIG_GENEVE_CORE) += geneve_core.o obj-$(CONFIG_XFRM) += xfrm4_policy.o xfrm4_state.o xfrm4_input.o \ xfrm4_output.o xfrm4_protocol.o diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index 9532ee87151f..1d0c3adb6f34 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -112,12 +112,14 @@ #include <net/raw.h> #include <net/icmp.h> #include <net/inet_common.h> +#include <net/ip_tunnels.h> #include <net/xfrm.h> #include <net/net_namespace.h> #include <net/secure_seq.h> #ifdef CONFIG_IP_MROUTE #include <linux/mroute.h> #endif +#include <net/vrf.h> /* The inetsw table contains everything that inet_create needs to @@ -426,6 +428,7 @@ int inet_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) struct net *net = sock_net(sk); unsigned short snum; int chk_addr_ret; + u32 tb_id = RT_TABLE_LOCAL; int err; /* If the socket has its own bind function then use it. (RAW) */ @@ -447,7 +450,8 @@ int inet_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) goto out; } - chk_addr_ret = inet_addr_type(net, addr->sin_addr.s_addr); + tb_id = vrf_dev_table_ifindex(net, sk->sk_bound_dev_if) ? : tb_id; + chk_addr_ret = inet_addr_type_table(net, addr->sin_addr.s_addr, tb_id); /* Not specified by any standard per-se, however it breaks too * many applications when removed. It is unfortunate since @@ -1448,38 +1452,51 @@ int inet_ctl_sock_create(struct sock **sk, unsigned short family, } EXPORT_SYMBOL_GPL(inet_ctl_sock_create); +u64 snmp_get_cpu_field(void __percpu *mib, int cpu, int offt) +{ + return *(((unsigned long *)per_cpu_ptr(mib, cpu)) + offt); +} +EXPORT_SYMBOL_GPL(snmp_get_cpu_field); + unsigned long snmp_fold_field(void __percpu *mib, int offt) { unsigned long res = 0; int i; for_each_possible_cpu(i) - res += *(((unsigned long *) per_cpu_ptr(mib, i)) + offt); + res += snmp_get_cpu_field(mib, i, offt); return res; } EXPORT_SYMBOL_GPL(snmp_fold_field); #if BITS_PER_LONG==32 +u64 snmp_get_cpu_field64(void __percpu *mib, int cpu, int offt, + size_t syncp_offset) +{ + void *bhptr; + struct u64_stats_sync *syncp; + u64 v; + unsigned int start; + + bhptr = per_cpu_ptr(mib, cpu); + syncp = (struct u64_stats_sync *)(bhptr + syncp_offset); + do { + start = u64_stats_fetch_begin_irq(syncp); + v = *(((u64 *)bhptr) + offt); + } while (u64_stats_fetch_retry_irq(syncp, start)); + + return v; +} +EXPORT_SYMBOL_GPL(snmp_get_cpu_field64); + u64 snmp_fold_field64(void __percpu *mib, int offt, size_t syncp_offset) { u64 res = 0; int cpu; for_each_possible_cpu(cpu) { - void *bhptr; - struct u64_stats_sync *syncp; - u64 v; - unsigned int start; - - bhptr = per_cpu_ptr(mib, cpu); - syncp = (struct u64_stats_sync *)(bhptr + syncp_offset); - do { - start = u64_stats_fetch_begin_irq(syncp); - v = *(((u64 *) bhptr) + offt); - } while (u64_stats_fetch_retry_irq(syncp, start)); - - res += v; + res += snmp_get_cpu_field64(mib, cpu, offt, syncp_offset); } return res; } @@ -1780,6 +1797,8 @@ static int __init inet_init(void) dev_add_pack(&ip_packet_type); + ip_tunnel_core_init(); + rc = 0; out: return rc; diff --git a/net/ipv4/ah4.c b/net/ipv4/ah4.c index ac9a32ec3ee4..f2a71025a770 100644 --- a/net/ipv4/ah4.c +++ b/net/ipv4/ah4.c @@ -360,8 +360,10 @@ static int ah_input(struct xfrm_state *x, struct sk_buff *skb) work_iph = ah_alloc_tmp(ahash, nfrags + sglists, ihl + ahp->icv_trunc_len + seqhi_len); - if (!work_iph) + if (!work_iph) { + err = -ENOMEM; goto out; + } seqhi = (__be32 *)((char *)work_iph + ihl); auth_data = ah_tmp_auth(seqhi, seqhi_len); diff --git a/net/ipv4/arp.c b/net/ipv4/arp.c index 6c8b1fbafce8..30409b75e925 100644 --- a/net/ipv4/arp.c +++ b/net/ipv4/arp.c @@ -233,7 +233,7 @@ static int arp_constructor(struct neighbour *neigh) return -EINVAL; } - neigh->type = inet_addr_type(dev_net(dev), addr); + neigh->type = inet_addr_type_dev_table(dev_net(dev), dev, addr); parms = in_dev->arp_parms; __neigh_parms_put(neigh->parms); @@ -291,6 +291,40 @@ static void arp_error_report(struct neighbour *neigh, struct sk_buff *skb) kfree_skb(skb); } +/* Create and send an arp packet. */ +static void arp_send_dst(int type, int ptype, __be32 dest_ip, + struct net_device *dev, __be32 src_ip, + const unsigned char *dest_hw, + const unsigned char *src_hw, + const unsigned char *target_hw, struct sk_buff *oskb) +{ + struct sk_buff *skb; + + /* arp on this interface. */ + if (dev->flags & IFF_NOARP) + return; + + skb = arp_create(type, ptype, dest_ip, dev, src_ip, + dest_hw, src_hw, target_hw); + if (!skb) + return; + + if (oskb) + skb_dst_copy(skb, oskb); + + arp_xmit(skb); +} + +void arp_send(int type, int ptype, __be32 dest_ip, + struct net_device *dev, __be32 src_ip, + const unsigned char *dest_hw, const unsigned char *src_hw, + const unsigned char *target_hw) +{ + arp_send_dst(type, ptype, dest_ip, dev, src_ip, dest_hw, src_hw, + target_hw, NULL); +} +EXPORT_SYMBOL(arp_send); + static void arp_solicit(struct neighbour *neigh, struct sk_buff *skb) { __be32 saddr = 0; @@ -309,7 +343,7 @@ static void arp_solicit(struct neighbour *neigh, struct sk_buff *skb) switch (IN_DEV_ARP_ANNOUNCE(in_dev)) { default: case 0: /* By default announce any local IP */ - if (skb && inet_addr_type(dev_net(dev), + if (skb && inet_addr_type_dev_table(dev_net(dev), dev, ip_hdr(skb)->saddr) == RTN_LOCAL) saddr = ip_hdr(skb)->saddr; break; @@ -317,7 +351,8 @@ static void arp_solicit(struct neighbour *neigh, struct sk_buff *skb) if (!skb) break; saddr = ip_hdr(skb)->saddr; - if (inet_addr_type(dev_net(dev), saddr) == RTN_LOCAL) { + if (inet_addr_type_dev_table(dev_net(dev), dev, + saddr) == RTN_LOCAL) { /* saddr should be known to target */ if (inet_addr_onlink(in_dev, target, saddr)) break; @@ -346,8 +381,9 @@ static void arp_solicit(struct neighbour *neigh, struct sk_buff *skb) } } - arp_send(ARPOP_REQUEST, ETH_P_ARP, target, dev, saddr, - dst_hw, dev->dev_addr, NULL); + arp_send_dst(ARPOP_REQUEST, ETH_P_ARP, target, dev, saddr, + dst_hw, dev->dev_addr, NULL, + dev->priv_flags & IFF_XMIT_DST_RELEASE ? NULL : skb); } static int arp_ignore(struct in_device *in_dev, __be32 sip, __be32 tip) @@ -597,32 +633,6 @@ void arp_xmit(struct sk_buff *skb) EXPORT_SYMBOL(arp_xmit); /* - * Create and send an arp packet. - */ -void arp_send(int type, int ptype, __be32 dest_ip, - struct net_device *dev, __be32 src_ip, - const unsigned char *dest_hw, const unsigned char *src_hw, - const unsigned char *target_hw) -{ - struct sk_buff *skb; - - /* - * No arp on this interface. - */ - - if (dev->flags&IFF_NOARP) - return; - - skb = arp_create(type, ptype, dest_ip, dev, src_ip, - dest_hw, src_hw, target_hw); - if (!skb) - return; - - arp_xmit(skb); -} -EXPORT_SYMBOL(arp_send); - -/* * Process an arp request. */ @@ -742,7 +752,7 @@ static int arp_process(struct sock *sk, struct sk_buff *skb) /* Special case: IPv4 duplicate address detection packet (RFC2131) */ if (sip == 0) { if (arp->ar_op == htons(ARPOP_REQUEST) && - inet_addr_type(net, tip) == RTN_LOCAL && + inet_addr_type_dev_table(net, dev, tip) == RTN_LOCAL && !arp_ignore(in_dev, sip, tip)) arp_send(ARPOP_REPLY, ETH_P_ARP, sip, dev, tip, sha, dev->dev_addr, sha); @@ -802,16 +812,18 @@ static int arp_process(struct sock *sk, struct sk_buff *skb) n = __neigh_lookup(&arp_tbl, &sip, dev, 0); if (IN_DEV_ARP_ACCEPT(in_dev)) { + unsigned int addr_type = inet_addr_type_dev_table(net, dev, sip); + /* Unsolicited ARP is not accepted by default. It is possible, that this option should be enabled for some devices (strip is candidate) */ is_garp = arp->ar_op == htons(ARPOP_REQUEST) && tip == sip && - inet_addr_type(net, sip) == RTN_UNICAST; + addr_type == RTN_UNICAST; if (!n && ((arp->ar_op == htons(ARPOP_REPLY) && - inet_addr_type(net, sip) == RTN_UNICAST) || is_garp)) + addr_type == RTN_UNICAST) || is_garp)) n = __neigh_lookup(&arp_tbl, &sip, dev, 1); } diff --git a/net/ipv4/datagram.c b/net/ipv4/datagram.c index 574fad9cca05..f915abff1350 100644 --- a/net/ipv4/datagram.c +++ b/net/ipv4/datagram.c @@ -74,7 +74,7 @@ int __ip4_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len inet->inet_daddr = fl4->daddr; inet->inet_dport = usin->sin_port; sk->sk_state = TCP_ESTABLISHED; - inet_set_txhash(sk); + sk_set_txhash(sk); inet->inet_id = jiffies; sk_dst_set(sk, &rt->dst); diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c index 6bbc54940eb4..6fcbd215cdbc 100644 --- a/net/ipv4/fib_frontend.c +++ b/net/ipv4/fib_frontend.c @@ -45,6 +45,8 @@ #include <net/ip_fib.h> #include <net/rtnetlink.h> #include <net/xfrm.h> +#include <net/vrf.h> +#include <trace/events/fib.h> #ifndef CONFIG_IP_MULTIPLE_TABLES @@ -211,12 +213,12 @@ void fib_flush_external(struct net *net) */ static inline unsigned int __inet_dev_addr_type(struct net *net, const struct net_device *dev, - __be32 addr) + __be32 addr, u32 tb_id) { struct flowi4 fl4 = { .daddr = addr }; struct fib_result res; unsigned int ret = RTN_BROADCAST; - struct fib_table *local_table; + struct fib_table *table; if (ipv4_is_zeronet(addr) || ipv4_is_lbcast(addr)) return RTN_BROADCAST; @@ -225,10 +227,10 @@ static inline unsigned int __inet_dev_addr_type(struct net *net, rcu_read_lock(); - local_table = fib_get_table(net, RT_TABLE_LOCAL); - if (local_table) { + table = fib_get_table(net, tb_id); + if (table) { ret = RTN_UNICAST; - if (!fib_table_lookup(local_table, &fl4, &res, FIB_LOOKUP_NOREF)) { + if (!fib_table_lookup(table, &fl4, &res, FIB_LOOKUP_NOREF)) { if (!dev || dev == res.fi->fib_dev) ret = res.type; } @@ -238,19 +240,40 @@ static inline unsigned int __inet_dev_addr_type(struct net *net, return ret; } +unsigned int inet_addr_type_table(struct net *net, __be32 addr, u32 tb_id) +{ + return __inet_dev_addr_type(net, NULL, addr, tb_id); +} +EXPORT_SYMBOL(inet_addr_type_table); + unsigned int inet_addr_type(struct net *net, __be32 addr) { - return __inet_dev_addr_type(net, NULL, addr); + return __inet_dev_addr_type(net, NULL, addr, RT_TABLE_LOCAL); } EXPORT_SYMBOL(inet_addr_type); unsigned int inet_dev_addr_type(struct net *net, const struct net_device *dev, __be32 addr) { - return __inet_dev_addr_type(net, dev, addr); + u32 rt_table = vrf_dev_table(dev) ? : RT_TABLE_LOCAL; + + return __inet_dev_addr_type(net, dev, addr, rt_table); } EXPORT_SYMBOL(inet_dev_addr_type); +/* inet_addr_type with dev == NULL but using the table from a dev + * if one is associated + */ +unsigned int inet_addr_type_dev_table(struct net *net, + const struct net_device *dev, + __be32 addr) +{ + u32 rt_table = vrf_dev_table(dev) ? : RT_TABLE_LOCAL; + + return __inet_dev_addr_type(net, NULL, addr, rt_table); +} +EXPORT_SYMBOL(inet_addr_type_dev_table); + __be32 fib_compute_spec_dst(struct sk_buff *skb) { struct net_device *dev = skb->dev; @@ -280,6 +303,7 @@ __be32 fib_compute_spec_dst(struct sk_buff *skb) fl4.flowi4_tos = RT_TOS(ip_hdr(skb)->tos); fl4.flowi4_scope = scope; fl4.flowi4_mark = IN_DEV_SRC_VMARK(in_dev) ? skb->mark : 0; + fl4.flowi4_tun_key.tun_id = 0; if (!fib_lookup(net, &fl4, &res, 0)) return FIB_RES_PREFSRC(net, res); } else { @@ -308,16 +332,21 @@ static int __fib_validate_source(struct sk_buff *skb, __be32 src, __be32 dst, bool dev_match; fl4.flowi4_oif = 0; - fl4.flowi4_iif = oif ? : LOOPBACK_IFINDEX; + fl4.flowi4_iif = vrf_master_ifindex_rcu(dev); + if (!fl4.flowi4_iif) + fl4.flowi4_iif = oif ? : LOOPBACK_IFINDEX; fl4.daddr = src; fl4.saddr = dst; fl4.flowi4_tos = tos; fl4.flowi4_scope = RT_SCOPE_UNIVERSE; + fl4.flowi4_tun_key.tun_id = 0; no_addr = idev->ifa_list == NULL; fl4.flowi4_mark = IN_DEV_SRC_VMARK(idev) ? skb->mark : 0; + trace_fib_validate_source(dev, &fl4); + net = dev_net(dev); if (fib_lookup(net, &fl4, &res, 0)) goto last_resort; @@ -337,6 +366,9 @@ static int __fib_validate_source(struct sk_buff *skb, __be32 src, __be32 dst, if (nh->nh_dev == dev) { dev_match = true; break; + } else if (vrf_master_ifindex_rcu(nh->nh_dev) == dev->ifindex) { + dev_match = true; + break; } } #else @@ -494,9 +526,12 @@ static int rtentry_to_fib_config(struct net *net, int cmd, struct rtentry *rt, addr = sk_extract_addr(&rt->rt_gateway); if (rt->rt_gateway.sa_family == AF_INET && addr) { + unsigned int addr_type; + cfg->fc_gw = addr; + addr_type = inet_addr_type_table(net, addr, cfg->fc_table); if (rt->rt_flags & RTF_GATEWAY && - inet_addr_type(net, addr) == RTN_UNICAST) + addr_type == RTN_UNICAST) cfg->fc_scope = RT_SCOPE_UNIVERSE; } @@ -591,6 +626,8 @@ const struct nla_policy rtm_ipv4_policy[RTA_MAX + 1] = { [RTA_METRICS] = { .type = NLA_NESTED }, [RTA_MULTIPATH] = { .len = sizeof(struct rtnexthop) }, [RTA_FLOW] = { .type = NLA_U32 }, + [RTA_ENCAP_TYPE] = { .type = NLA_U16 }, + [RTA_ENCAP] = { .type = NLA_NESTED }, }; static int rtm_to_fib_config(struct net *net, struct sk_buff *skb, @@ -656,6 +693,12 @@ static int rtm_to_fib_config(struct net *net, struct sk_buff *skb, case RTA_TABLE: cfg->fc_table = nla_get_u32(attr); break; + case RTA_ENCAP: + cfg->fc_encap = attr; + break; + case RTA_ENCAP_TYPE: + cfg->fc_encap_type = nla_get_u16(attr); + break; } } @@ -760,6 +803,7 @@ out: static void fib_magic(int cmd, int type, __be32 dst, int dst_len, struct in_ifaddr *ifa) { struct net *net = dev_net(ifa->ifa_dev->dev); + u32 tb_id = vrf_dev_table_rtnl(ifa->ifa_dev->dev); struct fib_table *tb; struct fib_config cfg = { .fc_protocol = RTPROT_KERNEL, @@ -774,11 +818,10 @@ static void fib_magic(int cmd, int type, __be32 dst, int dst_len, struct in_ifad }, }; - if (type == RTN_UNICAST) - tb = fib_new_table(net, RT_TABLE_MAIN); - else - tb = fib_new_table(net, RT_TABLE_LOCAL); + if (!tb_id) + tb_id = (type == RTN_UNICAST) ? RT_TABLE_MAIN : RT_TABLE_LOCAL; + tb = fib_new_table(net, tb_id); if (!tb) return; @@ -960,11 +1003,14 @@ void fib_del_ifaddr(struct in_ifaddr *ifa, struct in_ifaddr *iprim) fib_magic(RTM_DELROUTE, RTN_BROADCAST, any, 32, prim); } if (!(ok & LOCAL_OK)) { + unsigned int addr_type; + fib_magic(RTM_DELROUTE, RTN_LOCAL, ifa->ifa_local, 32, prim); /* Check, that this local address finally disappeared. */ - if (gone && - inet_addr_type(dev_net(dev), ifa->ifa_local) != RTN_LOCAL) { + addr_type = inet_addr_type_dev_table(dev_net(dev), dev, + ifa->ifa_local); + if (gone && addr_type != RTN_LOCAL) { /* And the last, but not the least thing. * We must flush stray FIB entries. * diff --git a/net/ipv4/fib_rules.c b/net/ipv4/fib_rules.c index 18123d50f576..f2bda9e89c61 100644 --- a/net/ipv4/fib_rules.c +++ b/net/ipv4/fib_rules.c @@ -318,7 +318,6 @@ static const struct fib_rules_ops __net_initconst fib4_rules_ops_template = { .delete = fib4_rule_delete, .compare = fib4_rule_compare, .fill = fib4_rule_fill, - .default_pref = fib_default_rule_pref, .nlmsg_payload = fib4_rule_nlmsg_payload, .flush_cache = fib4_rule_flush_cache, .nlgroup = RTNLGRP_IPV4_RULE, diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c index 3a06586b170c..064bd3caaa4f 100644 --- a/net/ipv4/fib_semantics.c +++ b/net/ipv4/fib_semantics.c @@ -42,6 +42,7 @@ #include <net/ip_fib.h> #include <net/netlink.h> #include <net/nexthop.h> +#include <net/lwtunnel.h> #include "fib_lookup.h" @@ -208,6 +209,7 @@ static void free_fib_info_rcu(struct rcu_head *head) change_nexthops(fi) { if (nexthop_nh->nh_dev) dev_put(nexthop_nh->nh_dev); + lwtstate_put(nexthop_nh->nh_lwtstate); free_nh_exceptions(nexthop_nh); rt_fibinfo_free_cpus(nexthop_nh->nh_pcpu_rth_output); rt_fibinfo_free(&nexthop_nh->nh_rth_input); @@ -266,6 +268,7 @@ static inline int nh_comp(const struct fib_info *fi, const struct fib_info *ofi) #ifdef CONFIG_IP_ROUTE_CLASSID nh->nh_tclassid != onh->nh_tclassid || #endif + lwtunnel_cmp_encap(nh->nh_lwtstate, onh->nh_lwtstate) || ((nh->nh_flags ^ onh->nh_flags) & ~RTNH_COMPARE_MASK)) return -1; onh++; @@ -366,6 +369,7 @@ static inline size_t fib_nlmsg_size(struct fib_info *fi) payload += nla_total_size((RTAX_MAX * nla_total_size(4))); if (fi->fib_nhs) { + size_t nh_encapsize = 0; /* Also handles the special case fib_nhs == 1 */ /* each nexthop is packed in an attribute */ @@ -374,8 +378,21 @@ static inline size_t fib_nlmsg_size(struct fib_info *fi) /* may contain flow and gateway attribute */ nhsize += 2 * nla_total_size(4); + /* grab encap info */ + for_nexthops(fi) { + if (nh->nh_lwtstate) { + /* RTA_ENCAP_TYPE */ + nh_encapsize += lwtunnel_get_encap_size( + nh->nh_lwtstate); + /* RTA_ENCAP */ + nh_encapsize += nla_total_size(2); + } + } endfor_nexthops(fi); + /* all nexthops are packed in a nested attribute */ - payload += nla_total_size(fi->fib_nhs * nhsize); + payload += nla_total_size((fi->fib_nhs * nhsize) + + nh_encapsize); + } return payload; @@ -421,13 +438,15 @@ static int fib_detect_death(struct fib_info *fi, int order, if (n) { state = n->nud_state; neigh_release(n); + } else { + return 0; } if (state == NUD_REACHABLE) return 0; if ((state & NUD_VALID) && order != dflt) return 0; if ((state & NUD_VALID) || - (*last_idx < 0 && order > dflt)) { + (*last_idx < 0 && order > dflt && state != NUD_INCOMPLETE)) { *last_resort = fi; *last_idx = order; } @@ -452,6 +471,9 @@ static int fib_count_nexthops(struct rtnexthop *rtnh, int remaining) static int fib_get_nhs(struct fib_info *fi, struct rtnexthop *rtnh, int remaining, struct fib_config *cfg) { + struct net *net = cfg->fc_nlinfo.nl_net; + int ret; + change_nexthops(fi) { int attrlen; @@ -475,18 +497,70 @@ static int fib_get_nhs(struct fib_info *fi, struct rtnexthop *rtnh, if (nexthop_nh->nh_tclassid) fi->fib_net->ipv4.fib_num_tclassid_users++; #endif + nla = nla_find(attrs, attrlen, RTA_ENCAP); + if (nla) { + struct lwtunnel_state *lwtstate; + struct net_device *dev = NULL; + struct nlattr *nla_entype; + + nla_entype = nla_find(attrs, attrlen, + RTA_ENCAP_TYPE); + if (!nla_entype) + goto err_inval; + if (cfg->fc_oif) + dev = __dev_get_by_index(net, cfg->fc_oif); + ret = lwtunnel_build_state(dev, nla_get_u16( + nla_entype), + nla, AF_INET, cfg, + &lwtstate); + if (ret) + goto errout; + nexthop_nh->nh_lwtstate = + lwtstate_get(lwtstate); + } } rtnh = rtnh_next(rtnh, &remaining); } endfor_nexthops(fi); return 0; + +err_inval: + ret = -EINVAL; + +errout: + return ret; } #endif +static int fib_encap_match(struct net *net, u16 encap_type, + struct nlattr *encap, + int oif, const struct fib_nh *nh, + const struct fib_config *cfg) +{ + struct lwtunnel_state *lwtstate; + struct net_device *dev = NULL; + int ret, result = 0; + + if (encap_type == LWTUNNEL_ENCAP_NONE) + return 0; + + if (oif) + dev = __dev_get_by_index(net, oif); + ret = lwtunnel_build_state(dev, encap_type, encap, + AF_INET, cfg, &lwtstate); + if (!ret) { + result = lwtunnel_cmp_encap(lwtstate, nh->nh_lwtstate); + lwtstate_free(lwtstate); + } + + return result; +} + int fib_nh_match(struct fib_config *cfg, struct fib_info *fi) { + struct net *net = cfg->fc_nlinfo.nl_net; #ifdef CONFIG_IP_ROUTE_MULTIPATH struct rtnexthop *rtnh; int remaining; @@ -496,6 +570,12 @@ int fib_nh_match(struct fib_config *cfg, struct fib_info *fi) return 1; if (cfg->fc_oif || cfg->fc_gw) { + if (cfg->fc_encap) { + if (fib_encap_match(net, cfg->fc_encap_type, + cfg->fc_encap, cfg->fc_oif, + fi->fib_nh, cfg)) + return 1; + } if ((!cfg->fc_oif || cfg->fc_oif == fi->fib_nh->nh_oif) && (!cfg->fc_gw || cfg->fc_gw == fi->fib_nh->nh_gw)) return 0; @@ -585,7 +665,7 @@ int fib_nh_match(struct fib_config *cfg, struct fib_info *fi) static int fib_check_nh(struct fib_config *cfg, struct fib_info *fi, struct fib_nh *nh) { - int err; + int err = 0; struct net *net; struct net_device *dev; @@ -594,16 +674,18 @@ static int fib_check_nh(struct fib_config *cfg, struct fib_info *fi, struct fib_result res; if (nh->nh_flags & RTNH_F_ONLINK) { + unsigned int addr_type; if (cfg->fc_scope >= RT_SCOPE_LINK) return -EINVAL; - if (inet_addr_type(net, nh->nh_gw) != RTN_UNICAST) - return -EINVAL; dev = __dev_get_by_index(net, nh->nh_oif); if (!dev) return -ENODEV; if (!(dev->flags & IFF_UP)) return -ENETDOWN; + addr_type = inet_addr_type_dev_table(net, dev, nh->nh_gw); + if (addr_type != RTN_UNICAST) + return -EINVAL; if (!netif_carrier_ok(dev)) nh->nh_flags |= RTNH_F_LINKDOWN; nh->nh_dev = dev; @@ -613,6 +695,7 @@ static int fib_check_nh(struct fib_config *cfg, struct fib_info *fi, } rcu_read_lock(); { + struct fib_table *tbl = NULL; struct flowi4 fl4 = { .daddr = nh->nh_gw, .flowi4_scope = cfg->fc_scope + 1, @@ -623,8 +706,24 @@ static int fib_check_nh(struct fib_config *cfg, struct fib_info *fi, /* It is not necessary, but requires a bit of thinking */ if (fl4.flowi4_scope < RT_SCOPE_LINK) fl4.flowi4_scope = RT_SCOPE_LINK; - err = fib_lookup(net, &fl4, &res, - FIB_LOOKUP_IGNORE_LINKSTATE); + + if (cfg->fc_table) + tbl = fib_get_table(net, cfg->fc_table); + + if (tbl) + err = fib_table_lookup(tbl, &fl4, &res, + FIB_LOOKUP_IGNORE_LINKSTATE | + FIB_LOOKUP_NOREF); + + /* on error or if no table given do full lookup. This + * is needed for example when nexthops are in the local + * table rather than the given table + */ + if (!tbl || err) { + err = fib_lookup(net, &fl4, &res, + FIB_LOOKUP_IGNORE_LINKSTATE); + } + if (err) { rcu_read_unlock(); return err; @@ -760,6 +859,67 @@ __be32 fib_info_update_nh_saddr(struct net *net, struct fib_nh *nh) return nh->nh_saddr; } +static bool fib_valid_prefsrc(struct fib_config *cfg, __be32 fib_prefsrc) +{ + if (cfg->fc_type != RTN_LOCAL || !cfg->fc_dst || + fib_prefsrc != cfg->fc_dst) { + u32 tb_id = cfg->fc_table; + + if (tb_id == RT_TABLE_MAIN) + tb_id = RT_TABLE_LOCAL; + + if (inet_addr_type_table(cfg->fc_nlinfo.nl_net, + fib_prefsrc, tb_id) != RTN_LOCAL) { + return false; + } + } + return true; +} + +static int +fib_convert_metrics(struct fib_info *fi, const struct fib_config *cfg) +{ + bool ecn_ca = false; + struct nlattr *nla; + int remaining; + + if (!cfg->fc_mx) + return 0; + + nla_for_each_attr(nla, cfg->fc_mx, cfg->fc_mx_len, remaining) { + int type = nla_type(nla); + u32 val; + + if (!type) + continue; + if (type > RTAX_MAX) + return -EINVAL; + + if (type == RTAX_CC_ALGO) { + char tmp[TCP_CA_NAME_MAX]; + + nla_strlcpy(tmp, nla, sizeof(tmp)); + val = tcp_ca_get_key_by_name(tmp, &ecn_ca); + if (val == TCP_CA_UNSPEC) + return -EINVAL; + } else { + val = nla_get_u32(nla); + } + if (type == RTAX_ADVMSS && val > 65535 - 40) + val = 65535 - 40; + if (type == RTAX_MTU && val > 65535 - 15) + val = 65535 - 15; + if (type == RTAX_FEATURES && (val & ~RTAX_FEATURE_MASK)) + return -EINVAL; + fi->fib_metrics[type - 1] = val; + } + + if (ecn_ca) + fi->fib_metrics[RTAX_FEATURES - 1] |= DST_FEATURE_ECN_CA; + + return 0; +} + struct fib_info *fib_create_info(struct fib_config *cfg) { int err; @@ -832,36 +992,9 @@ struct fib_info *fib_create_info(struct fib_config *cfg) goto failure; } endfor_nexthops(fi) - if (cfg->fc_mx) { - struct nlattr *nla; - int remaining; - - nla_for_each_attr(nla, cfg->fc_mx, cfg->fc_mx_len, remaining) { - int type = nla_type(nla); - - if (type) { - u32 val; - - if (type > RTAX_MAX) - goto err_inval; - if (type == RTAX_CC_ALGO) { - char tmp[TCP_CA_NAME_MAX]; - - nla_strlcpy(tmp, nla, sizeof(tmp)); - val = tcp_ca_get_key_by_name(tmp); - if (val == TCP_CA_UNSPEC) - goto err_inval; - } else { - val = nla_get_u32(nla); - } - if (type == RTAX_ADVMSS && val > 65535 - 40) - val = 65535 - 40; - if (type == RTAX_MTU && val > 65535 - 15) - val = 65535 - 15; - fi->fib_metrics[type - 1] = val; - } - } - } + err = fib_convert_metrics(fi, cfg); + if (err) + goto failure; if (cfg->fc_mp) { #ifdef CONFIG_IP_ROUTE_MULTIPATH @@ -882,6 +1015,22 @@ struct fib_info *fib_create_info(struct fib_config *cfg) } else { struct fib_nh *nh = fi->fib_nh; + if (cfg->fc_encap) { + struct lwtunnel_state *lwtstate; + struct net_device *dev = NULL; + + if (cfg->fc_encap_type == LWTUNNEL_ENCAP_NONE) + goto err_inval; + if (cfg->fc_oif) + dev = __dev_get_by_index(net, cfg->fc_oif); + err = lwtunnel_build_state(dev, cfg->fc_encap_type, + cfg->fc_encap, AF_INET, cfg, + &lwtstate); + if (err) + goto failure; + + nh->nh_lwtstate = lwtstate_get(lwtstate); + } nh->nh_oif = cfg->fc_oif; nh->nh_gw = cfg->fc_gw; nh->nh_flags = cfg->fc_flags; @@ -940,12 +1089,8 @@ struct fib_info *fib_create_info(struct fib_config *cfg) fi->fib_flags |= RTNH_F_LINKDOWN; } - if (fi->fib_prefsrc) { - if (cfg->fc_type != RTN_LOCAL || !cfg->fc_dst || - fi->fib_prefsrc != cfg->fc_dst) - if (inet_addr_type(net, fi->fib_prefsrc) != RTN_LOCAL) - goto err_inval; - } + if (fi->fib_prefsrc && !fib_valid_prefsrc(cfg, fi->fib_prefsrc)) + goto err_inval; change_nexthops(fi) { fib_info_update_nh_saddr(net, nexthop_nh); @@ -1055,6 +1200,8 @@ int fib_dump_info(struct sk_buff *skb, u32 portid, u32 seq, int event, nla_put_u32(skb, RTA_FLOW, fi->fib_nh[0].nh_tclassid)) goto nla_put_failure; #endif + if (fi->fib_nh->nh_lwtstate) + lwtunnel_fill_encap(skb, fi->fib_nh->nh_lwtstate); } #ifdef CONFIG_IP_ROUTE_MULTIPATH if (fi->fib_nhs > 1) { @@ -1090,6 +1237,8 @@ int fib_dump_info(struct sk_buff *skb, u32 portid, u32 seq, int event, nla_put_u32(skb, RTA_FLOW, nh->nh_tclassid)) goto nla_put_failure; #endif + if (nh->nh_lwtstate) + lwtunnel_fill_encap(skb, nh->nh_lwtstate); /* length of rtnetlink header + attributes */ rtnh->rtnh_len = nlmsg_get_pos(skb) - (void *) rtnh; } endfor_nexthops(fi); diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c index b0c6258ffb79..26d6ffb6d23c 100644 --- a/net/ipv4/fib_trie.c +++ b/net/ipv4/fib_trie.c @@ -81,6 +81,7 @@ #include <net/sock.h> #include <net/ip_fib.h> #include <net/switchdev.h> +#include <trace/events/fib.h> #include "fib_lookup.h" #define MAX_STAT_DEPTH 32 @@ -1278,6 +1279,8 @@ int fib_table_lookup(struct fib_table *tb, const struct flowi4 *flp, unsigned long index; t_key cindex; + trace_fib_table_lookup(tb->tb_id, flp); + pn = t->kv; cindex = 0; @@ -1423,8 +1426,11 @@ found: nh->nh_flags & RTNH_F_LINKDOWN && !(fib_flags & FIB_LOOKUP_IGNORE_LINKSTATE)) continue; - if (flp->flowi4_oif && flp->flowi4_oif != nh->nh_oif) - continue; + if (!(flp->flowi4_flags & FLOWI_FLAG_VRFSRC)) { + if (flp->flowi4_oif && + flp->flowi4_oif != nh->nh_oif) + continue; + } if (!(fib_flags & FIB_LOOKUP_NOREF)) atomic_inc(&fi->fib_clntref); @@ -1439,6 +1445,8 @@ found: #ifdef CONFIG_IP_FIB_TRIE_STATS this_cpu_inc(stats->semantic_match_passed); #endif + trace_fib_table_lookup_nh(nh); + return err; } } diff --git a/net/ipv4/fou.c b/net/ipv4/fou.c index 34968cd5c146..e0fcbbbcfe54 100644 --- a/net/ipv4/fou.c +++ b/net/ipv4/fou.c @@ -79,7 +79,11 @@ static struct guehdr *gue_remcsum(struct sk_buff *skb, struct guehdr *guehdr, __be16 *pd = data; size_t start = ntohs(pd[0]); size_t offset = ntohs(pd[1]); - size_t plen = hdrlen + max_t(size_t, offset + sizeof(u16), start); + size_t plen = sizeof(struct udphdr) + hdrlen + + max_t(size_t, offset + sizeof(u16), start); + + if (skb->remcsum_offload) + return guehdr; if (!pskb_may_pull(skb, plen)) return NULL; @@ -221,29 +225,21 @@ out_unlock: static struct guehdr *gue_gro_remcsum(struct sk_buff *skb, unsigned int off, struct guehdr *guehdr, void *data, - size_t hdrlen, u8 ipproto, - struct gro_remcsum *grc, bool nopartial) + size_t hdrlen, struct gro_remcsum *grc, + bool nopartial) { __be16 *pd = data; size_t start = ntohs(pd[0]); size_t offset = ntohs(pd[1]); - size_t plen = hdrlen + max_t(size_t, offset + sizeof(u16), start); if (skb->remcsum_offload) - return NULL; + return guehdr; if (!NAPI_GRO_CB(skb)->csum_valid) return NULL; - /* Pull checksum that will be written */ - if (skb_gro_header_hard(skb, off + plen)) { - guehdr = skb_gro_header_slow(skb, off + plen, off); - if (!guehdr) - return NULL; - } - - skb_gro_remcsum_process(skb, (void *)guehdr + hdrlen, - start, offset, grc, nopartial); + guehdr = skb_gro_remcsum_process(skb, (void *)guehdr, off, hdrlen, + start, offset, grc, nopartial); skb->remcsum_offload = 1; @@ -307,10 +303,10 @@ static struct sk_buff **gue_gro_receive(struct sk_buff **head, if (flags & GUE_PFLAG_REMCSUM) { guehdr = gue_gro_remcsum(skb, off, guehdr, - data + doffset, hdrlen, - guehdr->proto_ctype, &grc, + data + doffset, hdrlen, &grc, !!(fou->flags & FOU_F_REMCSUM_NOPARTIAL)); + if (!guehdr) goto out; @@ -351,7 +347,7 @@ static struct sk_buff **gue_gro_receive(struct sk_buff **head, rcu_read_lock(); offloads = NAPI_GRO_CB(skb)->is_ipv6 ? inet6_offloads : inet_offloads; ops = rcu_dereference(offloads[guehdr->proto_ctype]); - if (WARN_ON(!ops || !ops->callbacks.gro_receive)) + if (WARN_ON_ONCE(!ops || !ops->callbacks.gro_receive)) goto out_unlock; pp = ops->callbacks.gro_receive(head, skb); @@ -570,7 +566,7 @@ static int parse_nl_config(struct genl_info *info, if (info->attrs[FOU_ATTR_AF]) { u8 family = nla_get_u8(info->attrs[FOU_ATTR_AF]); - if (family != AF_INET && family != AF_INET6) + if (family != AF_INET) return -EINVAL; cfg->udp_config.family = family; diff --git a/net/ipv4/geneve_core.c b/net/ipv4/geneve_core.c deleted file mode 100644 index 311a4ba6950a..000000000000 --- a/net/ipv4/geneve_core.c +++ /dev/null @@ -1,447 +0,0 @@ -/* - * Geneve: Generic Network Virtualization Encapsulation - * - * Copyright (c) 2014 Nicira, Inc. - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version - * 2 of the License, or (at your option) any later version. - */ - -#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt - -#include <linux/kernel.h> -#include <linux/types.h> -#include <linux/module.h> -#include <linux/errno.h> -#include <linux/slab.h> -#include <linux/skbuff.h> -#include <linux/list.h> -#include <linux/netdevice.h> -#include <linux/in.h> -#include <linux/ip.h> -#include <linux/udp.h> -#include <linux/igmp.h> -#include <linux/etherdevice.h> -#include <linux/if_ether.h> -#include <linux/if_vlan.h> -#include <linux/ethtool.h> -#include <linux/mutex.h> -#include <net/arp.h> -#include <net/ndisc.h> -#include <net/ip.h> -#include <net/ip_tunnels.h> -#include <net/icmp.h> -#include <net/udp.h> -#include <net/rtnetlink.h> -#include <net/route.h> -#include <net/dsfield.h> -#include <net/inet_ecn.h> -#include <net/net_namespace.h> -#include <net/netns/generic.h> -#include <net/geneve.h> -#include <net/protocol.h> -#include <net/udp_tunnel.h> -#if IS_ENABLED(CONFIG_IPV6) -#include <net/ipv6.h> -#include <net/addrconf.h> -#include <net/ip6_tunnel.h> -#include <net/ip6_checksum.h> -#endif - -/* Protects sock_list and refcounts. */ -static DEFINE_MUTEX(geneve_mutex); - -/* per-network namespace private data for this module */ -struct geneve_net { - struct list_head sock_list; -}; - -static int geneve_net_id; - -static struct geneve_sock *geneve_find_sock(struct net *net, - sa_family_t family, __be16 port) -{ - struct geneve_net *gn = net_generic(net, geneve_net_id); - struct geneve_sock *gs; - - list_for_each_entry(gs, &gn->sock_list, list) { - if (inet_sk(gs->sock->sk)->inet_sport == port && - inet_sk(gs->sock->sk)->sk.sk_family == family) - return gs; - } - - return NULL; -} - -static void geneve_build_header(struct genevehdr *geneveh, - __be16 tun_flags, u8 vni[3], - u8 options_len, u8 *options) -{ - geneveh->ver = GENEVE_VER; - geneveh->opt_len = options_len / 4; - geneveh->oam = !!(tun_flags & TUNNEL_OAM); - geneveh->critical = !!(tun_flags & TUNNEL_CRIT_OPT); - geneveh->rsvd1 = 0; - memcpy(geneveh->vni, vni, 3); - geneveh->proto_type = htons(ETH_P_TEB); - geneveh->rsvd2 = 0; - - memcpy(geneveh->options, options, options_len); -} - -/* Transmit a fully formatted Geneve frame. - * - * When calling this function. The skb->data should point - * to the geneve header which is fully formed. - * - * This function will add other UDP tunnel headers. - */ -int geneve_xmit_skb(struct geneve_sock *gs, struct rtable *rt, - struct sk_buff *skb, __be32 src, __be32 dst, __u8 tos, - __u8 ttl, __be16 df, __be16 src_port, __be16 dst_port, - __be16 tun_flags, u8 vni[3], u8 opt_len, u8 *opt, - bool csum, bool xnet) -{ - struct genevehdr *gnvh; - int min_headroom; - int err; - - min_headroom = LL_RESERVED_SPACE(rt->dst.dev) + rt->dst.header_len - + GENEVE_BASE_HLEN + opt_len + sizeof(struct iphdr) - + (skb_vlan_tag_present(skb) ? VLAN_HLEN : 0); - - err = skb_cow_head(skb, min_headroom); - if (unlikely(err)) { - kfree_skb(skb); - return err; - } - - skb = vlan_hwaccel_push_inside(skb); - if (unlikely(!skb)) - return -ENOMEM; - - skb = udp_tunnel_handle_offloads(skb, csum); - if (IS_ERR(skb)) - return PTR_ERR(skb); - - gnvh = (struct genevehdr *)__skb_push(skb, sizeof(*gnvh) + opt_len); - geneve_build_header(gnvh, tun_flags, vni, opt_len, opt); - - skb_set_inner_protocol(skb, htons(ETH_P_TEB)); - - return udp_tunnel_xmit_skb(rt, gs->sock->sk, skb, src, dst, - tos, ttl, df, src_port, dst_port, xnet, - !csum); -} -EXPORT_SYMBOL_GPL(geneve_xmit_skb); - -static int geneve_hlen(struct genevehdr *gh) -{ - return sizeof(*gh) + gh->opt_len * 4; -} - -static struct sk_buff **geneve_gro_receive(struct sk_buff **head, - struct sk_buff *skb, - struct udp_offload *uoff) -{ - struct sk_buff *p, **pp = NULL; - struct genevehdr *gh, *gh2; - unsigned int hlen, gh_len, off_gnv; - const struct packet_offload *ptype; - __be16 type; - int flush = 1; - - off_gnv = skb_gro_offset(skb); - hlen = off_gnv + sizeof(*gh); - gh = skb_gro_header_fast(skb, off_gnv); - if (skb_gro_header_hard(skb, hlen)) { - gh = skb_gro_header_slow(skb, hlen, off_gnv); - if (unlikely(!gh)) - goto out; - } - - if (gh->ver != GENEVE_VER || gh->oam) - goto out; - gh_len = geneve_hlen(gh); - - hlen = off_gnv + gh_len; - if (skb_gro_header_hard(skb, hlen)) { - gh = skb_gro_header_slow(skb, hlen, off_gnv); - if (unlikely(!gh)) - goto out; - } - - flush = 0; - - for (p = *head; p; p = p->next) { - if (!NAPI_GRO_CB(p)->same_flow) - continue; - - gh2 = (struct genevehdr *)(p->data + off_gnv); - if (gh->opt_len != gh2->opt_len || - memcmp(gh, gh2, gh_len)) { - NAPI_GRO_CB(p)->same_flow = 0; - continue; - } - } - - type = gh->proto_type; - - rcu_read_lock(); - ptype = gro_find_receive_by_type(type); - if (!ptype) { - flush = 1; - goto out_unlock; - } - - skb_gro_pull(skb, gh_len); - skb_gro_postpull_rcsum(skb, gh, gh_len); - pp = ptype->callbacks.gro_receive(head, skb); - -out_unlock: - rcu_read_unlock(); -out: - NAPI_GRO_CB(skb)->flush |= flush; - - return pp; -} - -static int geneve_gro_complete(struct sk_buff *skb, int nhoff, - struct udp_offload *uoff) -{ - struct genevehdr *gh; - struct packet_offload *ptype; - __be16 type; - int gh_len; - int err = -ENOSYS; - - udp_tunnel_gro_complete(skb, nhoff); - - gh = (struct genevehdr *)(skb->data + nhoff); - gh_len = geneve_hlen(gh); - type = gh->proto_type; - - rcu_read_lock(); - ptype = gro_find_complete_by_type(type); - if (ptype) - err = ptype->callbacks.gro_complete(skb, nhoff + gh_len); - - rcu_read_unlock(); - return err; -} - -static void geneve_notify_add_rx_port(struct geneve_sock *gs) -{ - struct sock *sk = gs->sock->sk; - sa_family_t sa_family = sk->sk_family; - int err; - - if (sa_family == AF_INET) { - err = udp_add_offload(&gs->udp_offloads); - if (err) - pr_warn("geneve: udp_add_offload failed with status %d\n", - err); - } -} - -static void geneve_notify_del_rx_port(struct geneve_sock *gs) -{ - struct sock *sk = gs->sock->sk; - sa_family_t sa_family = sk->sk_family; - - if (sa_family == AF_INET) - udp_del_offload(&gs->udp_offloads); -} - -/* Callback from net/ipv4/udp.c to receive packets */ -static int geneve_udp_encap_recv(struct sock *sk, struct sk_buff *skb) -{ - struct genevehdr *geneveh; - struct geneve_sock *gs; - int opts_len; - - /* Need Geneve and inner Ethernet header to be present */ - if (unlikely(!pskb_may_pull(skb, GENEVE_BASE_HLEN))) - goto error; - - /* Return packets with reserved bits set */ - geneveh = geneve_hdr(skb); - - if (unlikely(geneveh->ver != GENEVE_VER)) - goto error; - - if (unlikely(geneveh->proto_type != htons(ETH_P_TEB))) - goto error; - - opts_len = geneveh->opt_len * 4; - if (iptunnel_pull_header(skb, GENEVE_BASE_HLEN + opts_len, - htons(ETH_P_TEB))) - goto drop; - - gs = rcu_dereference_sk_user_data(sk); - if (!gs) - goto drop; - - gs->rcv(gs, skb); - return 0; - -drop: - /* Consume bad packet */ - kfree_skb(skb); - return 0; - -error: - /* Let the UDP layer deal with the skb */ - return 1; -} - -static struct socket *geneve_create_sock(struct net *net, bool ipv6, - __be16 port) -{ - struct socket *sock; - struct udp_port_cfg udp_conf; - int err; - - memset(&udp_conf, 0, sizeof(udp_conf)); - - if (ipv6) { - udp_conf.family = AF_INET6; - } else { - udp_conf.family = AF_INET; - udp_conf.local_ip.s_addr = htonl(INADDR_ANY); - } - - udp_conf.local_udp_port = port; - - /* Open UDP socket */ - err = udp_sock_create(net, &udp_conf, &sock); - if (err < 0) - return ERR_PTR(err); - - return sock; -} - -/* Create new listen socket if needed */ -static struct geneve_sock *geneve_socket_create(struct net *net, __be16 port, - geneve_rcv_t *rcv, void *data, - bool ipv6) -{ - struct geneve_net *gn = net_generic(net, geneve_net_id); - struct geneve_sock *gs; - struct socket *sock; - struct udp_tunnel_sock_cfg tunnel_cfg; - - gs = kzalloc(sizeof(*gs), GFP_KERNEL); - if (!gs) - return ERR_PTR(-ENOMEM); - - sock = geneve_create_sock(net, ipv6, port); - if (IS_ERR(sock)) { - kfree(gs); - return ERR_CAST(sock); - } - - gs->sock = sock; - gs->refcnt = 1; - gs->rcv = rcv; - gs->rcv_data = data; - - /* Initialize the geneve udp offloads structure */ - gs->udp_offloads.port = port; - gs->udp_offloads.callbacks.gro_receive = geneve_gro_receive; - gs->udp_offloads.callbacks.gro_complete = geneve_gro_complete; - geneve_notify_add_rx_port(gs); - - /* Mark socket as an encapsulation socket */ - tunnel_cfg.sk_user_data = gs; - tunnel_cfg.encap_type = 1; - tunnel_cfg.encap_rcv = geneve_udp_encap_recv; - tunnel_cfg.encap_destroy = NULL; - setup_udp_tunnel_sock(net, sock, &tunnel_cfg); - - list_add(&gs->list, &gn->sock_list); - - return gs; -} - -struct geneve_sock *geneve_sock_add(struct net *net, __be16 port, - geneve_rcv_t *rcv, void *data, - bool no_share, bool ipv6) -{ - struct geneve_sock *gs; - - mutex_lock(&geneve_mutex); - - gs = geneve_find_sock(net, ipv6 ? AF_INET6 : AF_INET, port); - if (gs) { - if (!no_share && gs->rcv == rcv) - gs->refcnt++; - else - gs = ERR_PTR(-EBUSY); - } else { - gs = geneve_socket_create(net, port, rcv, data, ipv6); - } - - mutex_unlock(&geneve_mutex); - - return gs; -} -EXPORT_SYMBOL_GPL(geneve_sock_add); - -void geneve_sock_release(struct geneve_sock *gs) -{ - mutex_lock(&geneve_mutex); - - if (--gs->refcnt) - goto unlock; - - list_del(&gs->list); - geneve_notify_del_rx_port(gs); - udp_tunnel_sock_release(gs->sock); - kfree_rcu(gs, rcu); - -unlock: - mutex_unlock(&geneve_mutex); -} -EXPORT_SYMBOL_GPL(geneve_sock_release); - -static __net_init int geneve_init_net(struct net *net) -{ - struct geneve_net *gn = net_generic(net, geneve_net_id); - - INIT_LIST_HEAD(&gn->sock_list); - - return 0; -} - -static struct pernet_operations geneve_net_ops = { - .init = geneve_init_net, - .id = &geneve_net_id, - .size = sizeof(struct geneve_net), -}; - -static int __init geneve_init_module(void) -{ - int rc; - - rc = register_pernet_subsys(&geneve_net_ops); - if (rc) - return rc; - - pr_info("Geneve core logic\n"); - - return 0; -} -module_init(geneve_init_module); - -static void __exit geneve_cleanup_module(void) -{ - unregister_pernet_subsys(&geneve_net_ops); -} -module_exit(geneve_cleanup_module); - -MODULE_LICENSE("GPL"); -MODULE_AUTHOR("Jesse Gross <jesse@nicira.com>"); -MODULE_DESCRIPTION("Driver library for GENEVE encapsulated traffic"); diff --git a/net/ipv4/gre_demux.c b/net/ipv4/gre_demux.c index 4a7b5b2a1ce3..d9c552a721fc 100644 --- a/net/ipv4/gre_demux.c +++ b/net/ipv4/gre_demux.c @@ -31,7 +31,6 @@ #include <net/xfrm.h> static const struct gre_protocol __rcu *gre_proto[GREPROTO_MAX] __read_mostly; -static struct gre_cisco_protocol __rcu *gre_cisco_proto_list[GRE_IP_PROTO_MAX]; int gre_add_protocol(const struct gre_protocol *proto, u8 version) { @@ -61,197 +60,6 @@ int gre_del_protocol(const struct gre_protocol *proto, u8 version) } EXPORT_SYMBOL_GPL(gre_del_protocol); -void gre_build_header(struct sk_buff *skb, const struct tnl_ptk_info *tpi, - int hdr_len) -{ - struct gre_base_hdr *greh; - - skb_push(skb, hdr_len); - - skb_reset_transport_header(skb); - greh = (struct gre_base_hdr *)skb->data; - greh->flags = tnl_flags_to_gre_flags(tpi->flags); - greh->protocol = tpi->proto; - - if (tpi->flags&(TUNNEL_KEY|TUNNEL_CSUM|TUNNEL_SEQ)) { - __be32 *ptr = (__be32 *)(((u8 *)greh) + hdr_len - 4); - - if (tpi->flags&TUNNEL_SEQ) { - *ptr = tpi->seq; - ptr--; - } - if (tpi->flags&TUNNEL_KEY) { - *ptr = tpi->key; - ptr--; - } - if (tpi->flags&TUNNEL_CSUM && - !(skb_shinfo(skb)->gso_type & - (SKB_GSO_GRE|SKB_GSO_GRE_CSUM))) { - *ptr = 0; - *(__sum16 *)ptr = csum_fold(skb_checksum(skb, 0, - skb->len, 0)); - } - } -} -EXPORT_SYMBOL_GPL(gre_build_header); - -static int parse_gre_header(struct sk_buff *skb, struct tnl_ptk_info *tpi, - bool *csum_err) -{ - const struct gre_base_hdr *greh; - __be32 *options; - int hdr_len; - - if (unlikely(!pskb_may_pull(skb, sizeof(struct gre_base_hdr)))) - return -EINVAL; - - greh = (struct gre_base_hdr *)skb_transport_header(skb); - if (unlikely(greh->flags & (GRE_VERSION | GRE_ROUTING))) - return -EINVAL; - - tpi->flags = gre_flags_to_tnl_flags(greh->flags); - hdr_len = ip_gre_calc_hlen(tpi->flags); - - if (!pskb_may_pull(skb, hdr_len)) - return -EINVAL; - - greh = (struct gre_base_hdr *)skb_transport_header(skb); - tpi->proto = greh->protocol; - - options = (__be32 *)(greh + 1); - if (greh->flags & GRE_CSUM) { - if (skb_checksum_simple_validate(skb)) { - *csum_err = true; - return -EINVAL; - } - - skb_checksum_try_convert(skb, IPPROTO_GRE, 0, - null_compute_pseudo); - - options++; - } - - if (greh->flags & GRE_KEY) { - tpi->key = *options; - options++; - } else - tpi->key = 0; - - if (unlikely(greh->flags & GRE_SEQ)) { - tpi->seq = *options; - options++; - } else - tpi->seq = 0; - - /* WCCP version 1 and 2 protocol decoding. - * - Change protocol to IP - * - When dealing with WCCPv2, Skip extra 4 bytes in GRE header - */ - if (greh->flags == 0 && tpi->proto == htons(ETH_P_WCCP)) { - tpi->proto = htons(ETH_P_IP); - if ((*(u8 *)options & 0xF0) != 0x40) { - hdr_len += 4; - if (!pskb_may_pull(skb, hdr_len)) - return -EINVAL; - } - } - - return iptunnel_pull_header(skb, hdr_len, tpi->proto); -} - -static int gre_cisco_rcv(struct sk_buff *skb) -{ - struct tnl_ptk_info tpi; - int i; - bool csum_err = false; - -#ifdef CONFIG_NET_IPGRE_BROADCAST - if (ipv4_is_multicast(ip_hdr(skb)->daddr)) { - /* Looped back packet, drop it! */ - if (rt_is_output_route(skb_rtable(skb))) - goto drop; - } -#endif - - if (parse_gre_header(skb, &tpi, &csum_err) < 0) - goto drop; - - rcu_read_lock(); - for (i = 0; i < GRE_IP_PROTO_MAX; i++) { - struct gre_cisco_protocol *proto; - int ret; - - proto = rcu_dereference(gre_cisco_proto_list[i]); - if (!proto) - continue; - ret = proto->handler(skb, &tpi); - if (ret == PACKET_RCVD) { - rcu_read_unlock(); - return 0; - } - } - rcu_read_unlock(); - - icmp_send(skb, ICMP_DEST_UNREACH, ICMP_PORT_UNREACH, 0); -drop: - kfree_skb(skb); - return 0; -} - -static void gre_cisco_err(struct sk_buff *skb, u32 info) -{ - /* All the routers (except for Linux) return only - * 8 bytes of packet payload. It means, that precise relaying of - * ICMP in the real Internet is absolutely infeasible. - * - * Moreover, Cisco "wise men" put GRE key to the third word - * in GRE header. It makes impossible maintaining even soft - * state for keyed - * GRE tunnels with enabled checksum. Tell them "thank you". - * - * Well, I wonder, rfc1812 was written by Cisco employee, - * what the hell these idiots break standards established - * by themselves??? - */ - - const int type = icmp_hdr(skb)->type; - const int code = icmp_hdr(skb)->code; - struct tnl_ptk_info tpi; - bool csum_err = false; - int i; - - if (parse_gre_header(skb, &tpi, &csum_err)) { - if (!csum_err) /* ignore csum errors. */ - return; - } - - if (type == ICMP_DEST_UNREACH && code == ICMP_FRAG_NEEDED) { - ipv4_update_pmtu(skb, dev_net(skb->dev), info, - skb->dev->ifindex, 0, IPPROTO_GRE, 0); - return; - } - if (type == ICMP_REDIRECT) { - ipv4_redirect(skb, dev_net(skb->dev), skb->dev->ifindex, 0, - IPPROTO_GRE, 0); - return; - } - - rcu_read_lock(); - for (i = 0; i < GRE_IP_PROTO_MAX; i++) { - struct gre_cisco_protocol *proto; - - proto = rcu_dereference(gre_cisco_proto_list[i]); - if (!proto) - continue; - - if (proto->err_handler(skb, info, &tpi) == PACKET_RCVD) - goto out; - - } -out: - rcu_read_unlock(); -} - static int gre_rcv(struct sk_buff *skb) { const struct gre_protocol *proto; @@ -302,60 +110,19 @@ static const struct net_protocol net_gre_protocol = { .netns_ok = 1, }; -static const struct gre_protocol ipgre_protocol = { - .handler = gre_cisco_rcv, - .err_handler = gre_cisco_err, -}; - -int gre_cisco_register(struct gre_cisco_protocol *newp) -{ - struct gre_cisco_protocol **proto = (struct gre_cisco_protocol **) - &gre_cisco_proto_list[newp->priority]; - - return (cmpxchg(proto, NULL, newp) == NULL) ? 0 : -EBUSY; -} -EXPORT_SYMBOL_GPL(gre_cisco_register); - -int gre_cisco_unregister(struct gre_cisco_protocol *del_proto) -{ - struct gre_cisco_protocol **proto = (struct gre_cisco_protocol **) - &gre_cisco_proto_list[del_proto->priority]; - int ret; - - ret = (cmpxchg(proto, del_proto, NULL) == del_proto) ? 0 : -EINVAL; - - if (ret) - return ret; - - synchronize_net(); - return 0; -} -EXPORT_SYMBOL_GPL(gre_cisco_unregister); - static int __init gre_init(void) { pr_info("GRE over IPv4 demultiplexor driver\n"); if (inet_add_protocol(&net_gre_protocol, IPPROTO_GRE) < 0) { pr_err("can't add protocol\n"); - goto err; - } - - if (gre_add_protocol(&ipgre_protocol, GREPROTO_CISCO) < 0) { - pr_info("%s: can't add ipgre handler\n", __func__); - goto err_gre; + return -EAGAIN; } - return 0; -err_gre: - inet_del_protocol(&net_gre_protocol, IPPROTO_GRE); -err: - return -EAGAIN; } static void __exit gre_exit(void) { - gre_del_protocol(&ipgre_protocol, GREPROTO_CISCO); inet_del_protocol(&net_gre_protocol, IPPROTO_GRE); } diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c index f5203fba6236..79fe05befcae 100644 --- a/net/ipv4/icmp.c +++ b/net/ipv4/icmp.c @@ -96,6 +96,7 @@ #include <net/xfrm.h> #include <net/inet_common.h> #include <net/ip_fib.h> +#include <net/vrf.h> /* * Build xmit assembly blocks @@ -308,9 +309,10 @@ static bool icmpv4_xrlim_allow(struct net *net, struct rtable *rt, rc = false; if (icmp_global_allow()) { + int vif = vrf_master_ifindex(dst->dev); struct inet_peer *peer; - peer = inet_getpeer_v4(net->ipv4.peers, fl4->daddr, 1); + peer = inet_getpeer_v4(net->ipv4.peers, fl4->daddr, vif, 1); rc = inet_peer_xrlim_allow(peer, net->ipv4.sysctl_icmp_ratelimit); if (peer) @@ -425,6 +427,7 @@ static void icmp_reply(struct icmp_bxm *icmp_param, struct sk_buff *skb) fl4.flowi4_mark = mark; fl4.flowi4_tos = RT_TOS(ip_hdr(skb)->tos); fl4.flowi4_proto = IPPROTO_ICMP; + fl4.flowi4_oif = vrf_master_ifindex(skb->dev) ? : skb->dev->ifindex; security_skb_classify_flow(skb, flowi4_to_flowi(&fl4)); rt = ip_route_output_key(net, &fl4); if (IS_ERR(rt)) @@ -458,6 +461,8 @@ static struct rtable *icmp_route_lookup(struct net *net, fl4->flowi4_proto = IPPROTO_ICMP; fl4->fl4_icmp_type = type; fl4->fl4_icmp_code = code; + fl4->flowi4_oif = vrf_master_ifindex(skb_in->dev) ? : skb_in->dev->ifindex; + security_skb_classify_flow(skb_in, flowi4_to_flowi(fl4)); rt = __ip_route_output_key(net, fl4); if (IS_ERR(rt)) @@ -480,7 +485,8 @@ static struct rtable *icmp_route_lookup(struct net *net, if (err) goto relookup_failed; - if (inet_addr_type(net, fl4_dec.saddr) == RTN_LOCAL) { + if (inet_addr_type_dev_table(net, skb_in->dev, + fl4_dec.saddr) == RTN_LOCAL) { rt2 = __ip_route_output_key(net, &fl4_dec); if (IS_ERR(rt2)) err = PTR_ERR(rt2); @@ -496,6 +502,7 @@ static struct rtable *icmp_route_lookup(struct net *net, } /* Ugh! */ orefdst = skb_in->_skb_refdst; /* save old refdst */ + skb_dst_set(skb_in, NULL); err = ip_route_input(skb_in, fl4_dec.daddr, fl4_dec.saddr, RT_TOS(tos), rt2->dst.dev); @@ -828,7 +835,7 @@ static bool icmp_unreach(struct sk_buff *skb) */ if (!net->ipv4.sysctl_icmp_ignore_bogus_error_responses && - inet_addr_type(net, iph->daddr) == RTN_BROADCAST) { + inet_addr_type_dev_table(net, skb->dev, iph->daddr) == RTN_BROADCAST) { net_warn_ratelimited("%pI4 sent an invalid ICMP type %u, code %u error to a broadcast: %pI4 on %s\n", &ip_hdr(skb)->saddr, icmph->type, icmph->code, diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c index 9fdfd9deac11..d38b8b61eaee 100644 --- a/net/ipv4/igmp.c +++ b/net/ipv4/igmp.c @@ -110,6 +110,9 @@ #define IP_MAX_MEMBERSHIPS 20 #define IP_MAX_MSF 10 +/* IGMP reports for link-local multicast groups are enabled by default */ +int sysctl_igmp_llm_reports __read_mostly = 1; + #ifdef CONFIG_IP_MULTICAST /* Parameter names and values are taken from igmp-v2-06 draft */ @@ -437,6 +440,8 @@ static struct sk_buff *add_grec(struct sk_buff *skb, struct ip_mc_list *pmc, if (pmc->multiaddr == IGMP_ALL_HOSTS) return skb; + if (ipv4_is_local_multicast(pmc->multiaddr) && !sysctl_igmp_llm_reports) + return skb; isquery = type == IGMPV3_MODE_IS_INCLUDE || type == IGMPV3_MODE_IS_EXCLUDE; @@ -545,6 +550,9 @@ static int igmpv3_send_report(struct in_device *in_dev, struct ip_mc_list *pmc) for_each_pmc_rcu(in_dev, pmc) { if (pmc->multiaddr == IGMP_ALL_HOSTS) continue; + if (ipv4_is_local_multicast(pmc->multiaddr) && + !sysctl_igmp_llm_reports) + continue; spin_lock_bh(&pmc->lock); if (pmc->sfcount[MCAST_EXCLUDE]) type = IGMPV3_MODE_IS_EXCLUDE; @@ -678,7 +686,11 @@ static int igmp_send_report(struct in_device *in_dev, struct ip_mc_list *pmc, if (type == IGMPV3_HOST_MEMBERSHIP_REPORT) return igmpv3_send_report(in_dev, pmc); - else if (type == IGMP_HOST_LEAVE_MESSAGE) + + if (ipv4_is_local_multicast(group) && !sysctl_igmp_llm_reports) + return 0; + + if (type == IGMP_HOST_LEAVE_MESSAGE) dst = IGMP_ALL_ROUTER; else dst = group; @@ -851,6 +863,8 @@ static bool igmp_heard_report(struct in_device *in_dev, __be32 group) if (group == IGMP_ALL_HOSTS) return false; + if (ipv4_is_local_multicast(group) && !sysctl_igmp_llm_reports) + return false; rcu_read_lock(); for_each_pmc_rcu(in_dev, im) { @@ -957,6 +971,9 @@ static bool igmp_heard_query(struct in_device *in_dev, struct sk_buff *skb, continue; if (im->multiaddr == IGMP_ALL_HOSTS) continue; + if (ipv4_is_local_multicast(im->multiaddr) && + !sysctl_igmp_llm_reports) + continue; spin_lock_bh(&im->lock); if (im->tm_running) im->gsquery = im->gsquery && mark; @@ -1181,6 +1198,8 @@ static void igmp_group_dropped(struct ip_mc_list *im) #ifdef CONFIG_IP_MULTICAST if (im->multiaddr == IGMP_ALL_HOSTS) return; + if (ipv4_is_local_multicast(im->multiaddr) && !sysctl_igmp_llm_reports) + return; reporter = im->reporter; igmp_stop_timer(im); @@ -1213,6 +1232,8 @@ static void igmp_group_added(struct ip_mc_list *im) #ifdef CONFIG_IP_MULTICAST if (im->multiaddr == IGMP_ALL_HOSTS) return; + if (ipv4_is_local_multicast(im->multiaddr) && !sysctl_igmp_llm_reports) + return; if (in_dev->dead) return; @@ -1518,6 +1539,9 @@ static void ip_mc_rejoin_groups(struct in_device *in_dev) for_each_pmc_rtnl(in_dev, im) { if (im->multiaddr == IGMP_ALL_HOSTS) continue; + if (ipv4_is_local_multicast(im->multiaddr) && + !sysctl_igmp_llm_reports) + continue; /* a failover is happening and switches * must be notified immediately diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c index 0cb9165421d4..89120196a949 100644 --- a/net/ipv4/inet_hashtables.c +++ b/net/ipv4/inet_hashtables.c @@ -343,7 +343,6 @@ static int __inet_check_established(struct inet_timewait_death_row *death_row, struct sock *sk2; const struct hlist_nulls_node *node; struct inet_timewait_sock *tw = NULL; - int twrefcnt = 0; spin_lock(lock); @@ -371,21 +370,17 @@ static int __inet_check_established(struct inet_timewait_death_row *death_row, WARN_ON(!sk_unhashed(sk)); __sk_nulls_add_node_rcu(sk, &head->chain); if (tw) { - twrefcnt = inet_twsk_unhash(tw); + sk_nulls_del_node_init_rcu((struct sock *)tw); NET_INC_STATS_BH(net, LINUX_MIB_TIMEWAITRECYCLED); } spin_unlock(lock); - if (twrefcnt) - inet_twsk_put(tw); sock_prot_inuse_add(sock_net(sk), sk->sk_prot, 1); if (twp) { *twp = tw; } else if (tw) { /* Silly. Should hash-dance instead... */ - inet_twsk_deschedule(tw); - - inet_twsk_put(tw); + inet_twsk_deschedule_put(tw); } return 0; @@ -403,13 +398,12 @@ static u32 inet_sk_port_offset(const struct sock *sk) inet->inet_dport); } -int __inet_hash_nolisten(struct sock *sk, struct inet_timewait_sock *tw) +void __inet_hash_nolisten(struct sock *sk, struct sock *osk) { struct inet_hashinfo *hashinfo = sk->sk_prot->h.hashinfo; struct hlist_nulls_head *list; struct inet_ehash_bucket *head; spinlock_t *lock; - int twrefcnt = 0; WARN_ON(!sk_unhashed(sk)); @@ -420,23 +414,22 @@ int __inet_hash_nolisten(struct sock *sk, struct inet_timewait_sock *tw) spin_lock(lock); __sk_nulls_add_node_rcu(sk, list); - if (tw) { - WARN_ON(sk->sk_hash != tw->tw_hash); - twrefcnt = inet_twsk_unhash(tw); + if (osk) { + WARN_ON(sk->sk_hash != osk->sk_hash); + sk_nulls_del_node_init_rcu(osk); } spin_unlock(lock); sock_prot_inuse_add(sock_net(sk), sk->sk_prot, 1); - return twrefcnt; } EXPORT_SYMBOL_GPL(__inet_hash_nolisten); -int __inet_hash(struct sock *sk, struct inet_timewait_sock *tw) +void __inet_hash(struct sock *sk, struct sock *osk) { struct inet_hashinfo *hashinfo = sk->sk_prot->h.hashinfo; struct inet_listen_hashbucket *ilb; if (sk->sk_state != TCP_LISTEN) - return __inet_hash_nolisten(sk, tw); + return __inet_hash_nolisten(sk, osk); WARN_ON(!sk_unhashed(sk)); ilb = &hashinfo->listening_hash[inet_sk_listen_hashfn(sk)]; @@ -445,7 +438,6 @@ int __inet_hash(struct sock *sk, struct inet_timewait_sock *tw) __sk_nulls_add_node_rcu(sk, &ilb->head); sock_prot_inuse_add(sock_net(sk), sk->sk_prot, 1); spin_unlock(&ilb->lock); - return 0; } EXPORT_SYMBOL(__inet_hash); @@ -492,7 +484,6 @@ int __inet_hash_connect(struct inet_timewait_death_row *death_row, struct inet_bind_bucket *tb; int ret; struct net *net = sock_net(sk); - int twrefcnt = 1; if (!snum) { int i, remaining, low, high, port; @@ -560,19 +551,14 @@ ok: inet_bind_hash(sk, tb, port); if (sk_unhashed(sk)) { inet_sk(sk)->inet_sport = htons(port); - twrefcnt += __inet_hash_nolisten(sk, tw); + __inet_hash_nolisten(sk, (struct sock *)tw); } if (tw) - twrefcnt += inet_twsk_bind_unhash(tw, hinfo); + inet_twsk_bind_unhash(tw, hinfo); spin_unlock(&head->lock); - if (tw) { - inet_twsk_deschedule(tw); - while (twrefcnt) { - twrefcnt--; - inet_twsk_put(tw); - } - } + if (tw) + inet_twsk_deschedule_put(tw); ret = 0; goto out; diff --git a/net/ipv4/inet_timewait_sock.c b/net/ipv4/inet_timewait_sock.c index 2ffbd16b79e0..ae22cc24fbe8 100644 --- a/net/ipv4/inet_timewait_sock.c +++ b/net/ipv4/inet_timewait_sock.c @@ -18,28 +18,6 @@ /** - * inet_twsk_unhash - unhash a timewait socket from established hash - * @tw: timewait socket - * - * unhash a timewait socket from established hash, if hashed. - * ehash lock must be held by caller. - * Returns 1 if caller should call inet_twsk_put() after lock release. - */ -int inet_twsk_unhash(struct inet_timewait_sock *tw) -{ - if (hlist_nulls_unhashed(&tw->tw_node)) - return 0; - - hlist_nulls_del_rcu(&tw->tw_node); - sk_nulls_node_init(&tw->tw_node); - /* - * We cannot call inet_twsk_put() ourself under lock, - * caller must call it for us. - */ - return 1; -} - -/** * inet_twsk_bind_unhash - unhash a timewait socket from bind hash * @tw: timewait socket * @hashinfo: hashinfo pointer @@ -48,35 +26,29 @@ int inet_twsk_unhash(struct inet_timewait_sock *tw) * bind hash lock must be held by caller. * Returns 1 if caller should call inet_twsk_put() after lock release. */ -int inet_twsk_bind_unhash(struct inet_timewait_sock *tw, +void inet_twsk_bind_unhash(struct inet_timewait_sock *tw, struct inet_hashinfo *hashinfo) { struct inet_bind_bucket *tb = tw->tw_tb; if (!tb) - return 0; + return; __hlist_del(&tw->tw_bind_node); tw->tw_tb = NULL; inet_bind_bucket_destroy(hashinfo->bind_bucket_cachep, tb); - /* - * We cannot call inet_twsk_put() ourself under lock, - * caller must call it for us. - */ - return 1; + __sock_put((struct sock *)tw); } /* Must be called with locally disabled BHs. */ static void inet_twsk_kill(struct inet_timewait_sock *tw) { struct inet_hashinfo *hashinfo = tw->tw_dr->hashinfo; - struct inet_bind_hashbucket *bhead; - int refcnt; - /* Unlink from established hashes. */ spinlock_t *lock = inet_ehash_lockp(hashinfo, tw->tw_hash); + struct inet_bind_hashbucket *bhead; spin_lock(lock); - refcnt = inet_twsk_unhash(tw); + sk_nulls_del_node_init_rcu((struct sock *)tw); spin_unlock(lock); /* Disassociate with bind bucket. */ @@ -84,11 +56,9 @@ static void inet_twsk_kill(struct inet_timewait_sock *tw) hashinfo->bhash_size)]; spin_lock(&bhead->lock); - refcnt += inet_twsk_bind_unhash(tw, hashinfo); + inet_twsk_bind_unhash(tw, hashinfo); spin_unlock(&bhead->lock); - BUG_ON(refcnt >= atomic_read(&tw->tw_refcnt)); - atomic_sub(refcnt, &tw->tw_refcnt); atomic_dec(&tw->tw_dr->tw_count); inet_twsk_put(tw); } @@ -235,13 +205,17 @@ EXPORT_SYMBOL_GPL(inet_twsk_alloc); * tcp_input.c to verify this. */ -/* This is for handling early-kills of TIME_WAIT sockets. */ -void inet_twsk_deschedule(struct inet_timewait_sock *tw) +/* This is for handling early-kills of TIME_WAIT sockets. + * Warning : consume reference. + * Caller should not access tw anymore. + */ +void inet_twsk_deschedule_put(struct inet_timewait_sock *tw) { if (del_timer_sync(&tw->tw_timer)) inet_twsk_kill(tw); + inet_twsk_put(tw); } -EXPORT_SYMBOL(inet_twsk_deschedule); +EXPORT_SYMBOL(inet_twsk_deschedule_put); void inet_twsk_schedule(struct inet_timewait_sock *tw, const int timeo) { @@ -311,9 +285,8 @@ restart: rcu_read_unlock(); local_bh_disable(); - inet_twsk_deschedule(tw); + inet_twsk_deschedule_put(tw); local_bh_enable(); - inet_twsk_put(tw); goto restart_rcu; } /* If the nulls value we got at the end of this lookup is diff --git a/net/ipv4/inetpeer.c b/net/ipv4/inetpeer.c index 241afd743d2c..86fa45809540 100644 --- a/net/ipv4/inetpeer.c +++ b/net/ipv4/inetpeer.c @@ -157,22 +157,6 @@ void __init inet_initpeers(void) INIT_DEFERRABLE_WORK(&gc_work, inetpeer_gc_worker); } -static int addr_compare(const struct inetpeer_addr *a, - const struct inetpeer_addr *b) -{ - int i, n = (a->family == AF_INET ? 1 : 4); - - for (i = 0; i < n; i++) { - if (a->addr.a6[i] == b->addr.a6[i]) - continue; - if ((__force u32)a->addr.a6[i] < (__force u32)b->addr.a6[i]) - return -1; - return 1; - } - - return 0; -} - #define rcu_deref_locked(X, BASE) \ rcu_dereference_protected(X, lockdep_is_held(&(BASE)->lock.lock)) @@ -188,7 +172,7 @@ static int addr_compare(const struct inetpeer_addr *a, *stackptr++ = &_base->root; \ for (u = rcu_deref_locked(_base->root, _base); \ u != peer_avl_empty;) { \ - int cmp = addr_compare(_daddr, &u->daddr); \ + int cmp = inetpeer_addr_cmp(_daddr, &u->daddr); \ if (cmp == 0) \ break; \ if (cmp == -1) \ @@ -215,7 +199,7 @@ static struct inet_peer *lookup_rcu(const struct inetpeer_addr *daddr, int count = 0; while (u != peer_avl_empty) { - int cmp = addr_compare(daddr, &u->daddr); + int cmp = inetpeer_addr_cmp(daddr, &u->daddr); if (cmp == 0) { /* Before taking a reference, check if this entry was * deleted (refcnt=-1) diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c index 921138f6c97c..fa7f15305f9a 100644 --- a/net/ipv4/ip_fragment.c +++ b/net/ipv4/ip_fragment.c @@ -48,6 +48,7 @@ #include <linux/inet.h> #include <linux/netfilter_ipv4.h> #include <net/inet_ecn.h> +#include <net/vrf.h> /* NOTE. Logic of IP defragmentation is parallel to corresponding IPv6 * code now. If you change something here, _PLEASE_ update ipv6/reassembly.c @@ -77,6 +78,7 @@ struct ipq { u8 ecn; /* RFC3168 support */ u16 max_df_size; /* largest frag with DF set seen */ int iif; + int vif; /* VRF device index */ unsigned int rid; struct inet_peer *peer; }; @@ -99,6 +101,7 @@ static int ip_frag_reasm(struct ipq *qp, struct sk_buff *prev, struct ip4_create_arg { struct iphdr *iph; u32 user; + int vif; }; static unsigned int ipqhashfn(__be16 id, __be32 saddr, __be32 daddr, u8 prot) @@ -127,7 +130,8 @@ static bool ip4_frag_match(const struct inet_frag_queue *q, const void *a) qp->saddr == arg->iph->saddr && qp->daddr == arg->iph->daddr && qp->protocol == arg->iph->protocol && - qp->user == arg->user; + qp->user == arg->user && + qp->vif == arg->vif; } static void ip4_frag_init(struct inet_frag_queue *q, const void *a) @@ -144,9 +148,11 @@ static void ip4_frag_init(struct inet_frag_queue *q, const void *a) qp->ecn = ip4_frag_ecn(arg->iph->tos); qp->saddr = arg->iph->saddr; qp->daddr = arg->iph->daddr; + qp->vif = arg->vif; qp->user = arg->user; qp->peer = sysctl_ipfrag_max_dist ? - inet_getpeer_v4(net->ipv4.peers, arg->iph->saddr, 1) : NULL; + inet_getpeer_v4(net->ipv4.peers, arg->iph->saddr, arg->vif, 1) : + NULL; } static void ip4_frag_free(struct inet_frag_queue *q) @@ -244,7 +250,8 @@ out: /* Find the correct entry in the "incomplete datagrams" queue for * this IP datagram, and create new one, if nothing is found. */ -static struct ipq *ip_find(struct net *net, struct iphdr *iph, u32 user) +static struct ipq *ip_find(struct net *net, struct iphdr *iph, + u32 user, int vif) { struct inet_frag_queue *q; struct ip4_create_arg arg; @@ -252,6 +259,7 @@ static struct ipq *ip_find(struct net *net, struct iphdr *iph, u32 user) arg.iph = iph; arg.user = user; + arg.vif = vif; hash = ipqhashfn(iph->id, iph->saddr, iph->daddr, iph->protocol); @@ -522,7 +530,6 @@ static int ip_frag_reasm(struct ipq *qp, struct sk_buff *prev, int len; int ihlen; int err; - int sum_truesize; u8 ecn; ipq_kill(qp); @@ -590,32 +597,19 @@ static int ip_frag_reasm(struct ipq *qp, struct sk_buff *prev, add_frag_mem_limit(qp->q.net, clone->truesize); } + skb_shinfo(head)->frag_list = head->next; skb_push(head, head->data - skb_network_header(head)); - sum_truesize = head->truesize; - for (fp = head->next; fp;) { - bool headstolen; - int delta; - struct sk_buff *next = fp->next; - - sum_truesize += fp->truesize; + for (fp=head->next; fp; fp = fp->next) { + head->data_len += fp->len; + head->len += fp->len; if (head->ip_summed != fp->ip_summed) head->ip_summed = CHECKSUM_NONE; else if (head->ip_summed == CHECKSUM_COMPLETE) head->csum = csum_add(head->csum, fp->csum); - - if (skb_try_coalesce(head, fp, &headstolen, &delta)) { - kfree_skb_partial(fp, headstolen); - } else { - if (!skb_shinfo(head)->frag_list) - skb_shinfo(head)->frag_list = fp; - head->data_len += fp->len; - head->len += fp->len; - head->truesize += fp->truesize; - } - fp = next; + head->truesize += fp->truesize; } - sub_frag_mem_limit(qp->q.net, sum_truesize); + sub_frag_mem_limit(qp->q.net, head->truesize); head->next = NULL; head->dev = dev; @@ -662,14 +656,15 @@ out_fail: /* Process an incoming IP datagram fragment. */ int ip_defrag(struct sk_buff *skb, u32 user) { + struct net_device *dev = skb->dev ? : skb_dst(skb)->dev; + int vif = vrf_master_ifindex_rcu(dev); + struct net *net = dev_net(dev); struct ipq *qp; - struct net *net; - net = skb->dev ? dev_net(skb->dev) : dev_net(skb_dst(skb)->dev); IP_INC_STATS_BH(net, IPSTATS_MIB_REASMREQDS); /* Lookup (or create) queue header */ - qp = ip_find(net, ip_hdr(skb), user); + qp = ip_find(net, ip_hdr(skb), user, vif); if (qp) { int ret; diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index 5fd706473c73..bd0679d90519 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -25,6 +25,7 @@ #include <linux/udp.h> #include <linux/if_arp.h> #include <linux/mroute.h> +#include <linux/if_vlan.h> #include <linux/init.h> #include <linux/in6.h> #include <linux/inetdevice.h> @@ -47,6 +48,7 @@ #include <net/netns/generic.h> #include <net/rtnetlink.h> #include <net/gre.h> +#include <net/dst_metadata.h> #if IS_ENABLED(CONFIG_IPV6) #include <net/ipv6.h> @@ -121,8 +123,127 @@ static int ipgre_tunnel_init(struct net_device *dev); static int ipgre_net_id __read_mostly; static int gre_tap_net_id __read_mostly; -static int ipgre_err(struct sk_buff *skb, u32 info, - const struct tnl_ptk_info *tpi) +static int ip_gre_calc_hlen(__be16 o_flags) +{ + int addend = 4; + + if (o_flags & TUNNEL_CSUM) + addend += 4; + if (o_flags & TUNNEL_KEY) + addend += 4; + if (o_flags & TUNNEL_SEQ) + addend += 4; + return addend; +} + +static __be16 gre_flags_to_tnl_flags(__be16 flags) +{ + __be16 tflags = 0; + + if (flags & GRE_CSUM) + tflags |= TUNNEL_CSUM; + if (flags & GRE_ROUTING) + tflags |= TUNNEL_ROUTING; + if (flags & GRE_KEY) + tflags |= TUNNEL_KEY; + if (flags & GRE_SEQ) + tflags |= TUNNEL_SEQ; + if (flags & GRE_STRICT) + tflags |= TUNNEL_STRICT; + if (flags & GRE_REC) + tflags |= TUNNEL_REC; + if (flags & GRE_VERSION) + tflags |= TUNNEL_VERSION; + + return tflags; +} + +static __be16 tnl_flags_to_gre_flags(__be16 tflags) +{ + __be16 flags = 0; + + if (tflags & TUNNEL_CSUM) + flags |= GRE_CSUM; + if (tflags & TUNNEL_ROUTING) + flags |= GRE_ROUTING; + if (tflags & TUNNEL_KEY) + flags |= GRE_KEY; + if (tflags & TUNNEL_SEQ) + flags |= GRE_SEQ; + if (tflags & TUNNEL_STRICT) + flags |= GRE_STRICT; + if (tflags & TUNNEL_REC) + flags |= GRE_REC; + if (tflags & TUNNEL_VERSION) + flags |= GRE_VERSION; + + return flags; +} + +static int parse_gre_header(struct sk_buff *skb, struct tnl_ptk_info *tpi, + bool *csum_err) +{ + const struct gre_base_hdr *greh; + __be32 *options; + int hdr_len; + + if (unlikely(!pskb_may_pull(skb, sizeof(struct gre_base_hdr)))) + return -EINVAL; + + greh = (struct gre_base_hdr *)skb_transport_header(skb); + if (unlikely(greh->flags & (GRE_VERSION | GRE_ROUTING))) + return -EINVAL; + + tpi->flags = gre_flags_to_tnl_flags(greh->flags); + hdr_len = ip_gre_calc_hlen(tpi->flags); + + if (!pskb_may_pull(skb, hdr_len)) + return -EINVAL; + + greh = (struct gre_base_hdr *)skb_transport_header(skb); + tpi->proto = greh->protocol; + + options = (__be32 *)(greh + 1); + if (greh->flags & GRE_CSUM) { + if (skb_checksum_simple_validate(skb)) { + *csum_err = true; + return -EINVAL; + } + + skb_checksum_try_convert(skb, IPPROTO_GRE, 0, + null_compute_pseudo); + options++; + } + + if (greh->flags & GRE_KEY) { + tpi->key = *options; + options++; + } else { + tpi->key = 0; + } + if (unlikely(greh->flags & GRE_SEQ)) { + tpi->seq = *options; + options++; + } else { + tpi->seq = 0; + } + /* WCCP version 1 and 2 protocol decoding. + * - Change protocol to IP + * - When dealing with WCCPv2, Skip extra 4 bytes in GRE header + */ + if (greh->flags == 0 && tpi->proto == htons(ETH_P_WCCP)) { + tpi->proto = htons(ETH_P_IP); + if ((*(u8 *)options & 0xF0) != 0x40) { + hdr_len += 4; + if (!pskb_may_pull(skb, hdr_len)) + return -EINVAL; + } + } + return iptunnel_pull_header(skb, hdr_len, tpi->proto); +} + +static void ipgre_err(struct sk_buff *skb, u32 info, + const struct tnl_ptk_info *tpi) { /* All the routers (except for Linux) return only @@ -148,14 +269,14 @@ static int ipgre_err(struct sk_buff *skb, u32 info, switch (type) { default: case ICMP_PARAMETERPROB: - return PACKET_RCVD; + return; case ICMP_DEST_UNREACH: switch (code) { case ICMP_SR_FAILED: case ICMP_PORT_UNREACH: /* Impossible event. */ - return PACKET_RCVD; + return; default: /* All others are translated to HOST_UNREACH. rfc2003 contains "deep thoughts" about NET_UNREACH, @@ -164,9 +285,10 @@ static int ipgre_err(struct sk_buff *skb, u32 info, break; } break; + case ICMP_TIME_EXCEEDED: if (code != ICMP_EXC_TTL) - return PACKET_RCVD; + return; break; case ICMP_REDIRECT: @@ -183,26 +305,85 @@ static int ipgre_err(struct sk_buff *skb, u32 info, iph->daddr, iph->saddr, tpi->key); if (!t) - return PACKET_REJECT; + return; if (t->parms.iph.daddr == 0 || ipv4_is_multicast(t->parms.iph.daddr)) - return PACKET_RCVD; + return; if (t->parms.iph.ttl == 0 && type == ICMP_TIME_EXCEEDED) - return PACKET_RCVD; + return; if (time_before(jiffies, t->err_time + IPTUNNEL_ERR_TIMEO)) t->err_count++; else t->err_count = 1; t->err_time = jiffies; - return PACKET_RCVD; +} + +static void gre_err(struct sk_buff *skb, u32 info) +{ + /* All the routers (except for Linux) return only + * 8 bytes of packet payload. It means, that precise relaying of + * ICMP in the real Internet is absolutely infeasible. + * + * Moreover, Cisco "wise men" put GRE key to the third word + * in GRE header. It makes impossible maintaining even soft + * state for keyed + * GRE tunnels with enabled checksum. Tell them "thank you". + * + * Well, I wonder, rfc1812 was written by Cisco employee, + * what the hell these idiots break standards established + * by themselves??? + */ + + const int type = icmp_hdr(skb)->type; + const int code = icmp_hdr(skb)->code; + struct tnl_ptk_info tpi; + bool csum_err = false; + + if (parse_gre_header(skb, &tpi, &csum_err)) { + if (!csum_err) /* ignore csum errors. */ + return; + } + + if (type == ICMP_DEST_UNREACH && code == ICMP_FRAG_NEEDED) { + ipv4_update_pmtu(skb, dev_net(skb->dev), info, + skb->dev->ifindex, 0, IPPROTO_GRE, 0); + return; + } + if (type == ICMP_REDIRECT) { + ipv4_redirect(skb, dev_net(skb->dev), skb->dev->ifindex, 0, + IPPROTO_GRE, 0); + return; + } + + ipgre_err(skb, info, &tpi); +} + +static __be64 key_to_tunnel_id(__be32 key) +{ +#ifdef __BIG_ENDIAN + return (__force __be64)((__force u32)key); +#else + return (__force __be64)((__force u64)key << 32); +#endif +} + +/* Returns the least-significant 32 bits of a __be64. */ +static __be32 tunnel_id_to_key(__be64 x) +{ +#ifdef __BIG_ENDIAN + return (__force __be32)x; +#else + return (__force __be32)((__force u64)x >> 32); +#endif } static int ipgre_rcv(struct sk_buff *skb, const struct tnl_ptk_info *tpi) { struct net *net = dev_net(skb->dev); + struct metadata_dst *tun_dst = NULL; struct ip_tunnel_net *itn; const struct iphdr *iph; struct ip_tunnel *tunnel; @@ -218,40 +399,184 @@ static int ipgre_rcv(struct sk_buff *skb, const struct tnl_ptk_info *tpi) if (tunnel) { skb_pop_mac_header(skb); - ip_tunnel_rcv(tunnel, skb, tpi, log_ecn_error); + if (tunnel->collect_md) { + __be16 flags; + __be64 tun_id; + + flags = tpi->flags & (TUNNEL_CSUM | TUNNEL_KEY); + tun_id = key_to_tunnel_id(tpi->key); + tun_dst = ip_tun_rx_dst(skb, flags, tun_id, 0); + if (!tun_dst) + return PACKET_REJECT; + } + + ip_tunnel_rcv(tunnel, skb, tpi, tun_dst, log_ecn_error); return PACKET_RCVD; } return PACKET_REJECT; } +static int gre_rcv(struct sk_buff *skb) +{ + struct tnl_ptk_info tpi; + bool csum_err = false; + +#ifdef CONFIG_NET_IPGRE_BROADCAST + if (ipv4_is_multicast(ip_hdr(skb)->daddr)) { + /* Looped back packet, drop it! */ + if (rt_is_output_route(skb_rtable(skb))) + goto drop; + } +#endif + + if (parse_gre_header(skb, &tpi, &csum_err) < 0) + goto drop; + + if (ipgre_rcv(skb, &tpi) == PACKET_RCVD) + return 0; + + icmp_send(skb, ICMP_DEST_UNREACH, ICMP_PORT_UNREACH, 0); +drop: + kfree_skb(skb); + return 0; +} + +static void build_header(struct sk_buff *skb, int hdr_len, __be16 flags, + __be16 proto, __be32 key, __be32 seq) +{ + struct gre_base_hdr *greh; + + skb_push(skb, hdr_len); + + skb_reset_transport_header(skb); + greh = (struct gre_base_hdr *)skb->data; + greh->flags = tnl_flags_to_gre_flags(flags); + greh->protocol = proto; + + if (flags & (TUNNEL_KEY | TUNNEL_CSUM | TUNNEL_SEQ)) { + __be32 *ptr = (__be32 *)(((u8 *)greh) + hdr_len - 4); + + if (flags & TUNNEL_SEQ) { + *ptr = seq; + ptr--; + } + if (flags & TUNNEL_KEY) { + *ptr = key; + ptr--; + } + if (flags & TUNNEL_CSUM && + !(skb_shinfo(skb)->gso_type & + (SKB_GSO_GRE | SKB_GSO_GRE_CSUM))) { + *ptr = 0; + *(__sum16 *)ptr = csum_fold(skb_checksum(skb, 0, + skb->len, 0)); + } + } +} + static void __gre_xmit(struct sk_buff *skb, struct net_device *dev, const struct iphdr *tnl_params, __be16 proto) { struct ip_tunnel *tunnel = netdev_priv(dev); - struct tnl_ptk_info tpi; - tpi.flags = tunnel->parms.o_flags; - tpi.proto = proto; - tpi.key = tunnel->parms.o_key; if (tunnel->parms.o_flags & TUNNEL_SEQ) tunnel->o_seqno++; - tpi.seq = htonl(tunnel->o_seqno); /* Push GRE header. */ - gre_build_header(skb, &tpi, tunnel->tun_hlen); - - skb_set_inner_protocol(skb, tpi.proto); + build_header(skb, tunnel->tun_hlen, 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); } +static struct sk_buff *gre_handle_offloads(struct sk_buff *skb, + bool csum) +{ + return iptunnel_handle_offloads(skb, csum, + csum ? SKB_GSO_GRE_CSUM : SKB_GSO_GRE); +} + +static void gre_fb_xmit(struct sk_buff *skb, struct net_device *dev) +{ + struct ip_tunnel_info *tun_info; + struct net *net = dev_net(dev); + const struct ip_tunnel_key *key; + struct flowi4 fl; + struct rtable *rt; + int min_headroom; + int tunnel_hlen; + __be16 df, flags; + int err; + + tun_info = skb_tunnel_info(skb); + if (unlikely(!tun_info || !(tun_info->mode & IP_TUNNEL_INFO_TX) || + ip_tunnel_info_af(tun_info) != AF_INET)) + goto err_free_skb; + + key = &tun_info->key; + memset(&fl, 0, sizeof(fl)); + fl.daddr = key->u.ipv4.dst; + fl.saddr = key->u.ipv4.src; + fl.flowi4_tos = RT_TOS(key->tos); + fl.flowi4_mark = skb->mark; + fl.flowi4_proto = IPPROTO_GRE; + + rt = ip_route_output_key(net, &fl); + if (IS_ERR(rt)) + goto err_free_skb; + + tunnel_hlen = ip_gre_calc_hlen(key->tun_flags); + + min_headroom = LL_RESERVED_SPACE(rt->dst.dev) + rt->dst.header_len + + tunnel_hlen + sizeof(struct iphdr); + if (skb_headroom(skb) < min_headroom || skb_header_cloned(skb)) { + int head_delta = SKB_DATA_ALIGN(min_headroom - + skb_headroom(skb) + + 16); + err = pskb_expand_head(skb, max_t(int, head_delta, 0), + 0, GFP_ATOMIC); + if (unlikely(err)) + goto err_free_rt; + } + + /* Push Tunnel header. */ + skb = gre_handle_offloads(skb, !!(tun_info->key.tun_flags & TUNNEL_CSUM)); + if (IS_ERR(skb)) { + skb = NULL; + goto err_free_rt; + } + + flags = tun_info->key.tun_flags & (TUNNEL_CSUM | TUNNEL_KEY); + build_header(skb, tunnel_hlen, flags, htons(ETH_P_TEB), + tunnel_id_to_key(tun_info->key.tun_id), 0); + + df = key->tun_flags & TUNNEL_DONT_FRAGMENT ? htons(IP_DF) : 0; + err = iptunnel_xmit(skb->sk, rt, skb, fl.saddr, + key->u.ipv4.dst, IPPROTO_GRE, + key->tos, key->ttl, df, false); + iptunnel_xmit_stats(err, &dev->stats, dev->tstats); + return; + +err_free_rt: + ip_rt_put(rt); +err_free_skb: + kfree_skb(skb); + dev->stats.tx_dropped++; +} + static netdev_tx_t ipgre_xmit(struct sk_buff *skb, struct net_device *dev) { struct ip_tunnel *tunnel = netdev_priv(dev); const struct iphdr *tnl_params; + if (tunnel->collect_md) { + gre_fb_xmit(skb, dev); + return NETDEV_TX_OK; + } + if (dev->header_ops) { /* Need space for new headers */ if (skb_cow_head(skb, dev->needed_headroom - @@ -277,7 +602,6 @@ static netdev_tx_t ipgre_xmit(struct sk_buff *skb, goto out; __gre_xmit(skb, dev, tnl_params, skb->protocol); - return NETDEV_TX_OK; free_skb: @@ -292,6 +616,11 @@ static netdev_tx_t gre_tap_xmit(struct sk_buff *skb, { struct ip_tunnel *tunnel = netdev_priv(dev); + if (tunnel->collect_md) { + gre_fb_xmit(skb, dev); + return NETDEV_TX_OK; + } + skb = gre_handle_offloads(skb, !!(tunnel->parms.o_flags&TUNNEL_CSUM)); if (IS_ERR(skb)) goto out; @@ -300,7 +629,6 @@ static netdev_tx_t gre_tap_xmit(struct sk_buff *skb, goto free_skb; __gre_xmit(skb, dev, &tunnel->parms.iph, htons(ETH_P_TEB)); - return NETDEV_TX_OK; free_skb: @@ -530,10 +858,9 @@ static int ipgre_tunnel_init(struct net_device *dev) return ip_tunnel_init(dev); } -static struct gre_cisco_protocol ipgre_protocol = { - .handler = ipgre_rcv, - .err_handler = ipgre_err, - .priority = 0, +static const struct gre_protocol ipgre_protocol = { + .handler = gre_rcv, + .err_handler = gre_err, }; static int __net_init ipgre_init_net(struct net *net) @@ -596,8 +923,10 @@ out: return ipgre_tunnel_validate(tb, data); } -static void ipgre_netlink_parms(struct nlattr *data[], struct nlattr *tb[], - struct ip_tunnel_parm *parms) +static void ipgre_netlink_parms(struct net_device *dev, + struct nlattr *data[], + struct nlattr *tb[], + struct ip_tunnel_parm *parms) { memset(parms, 0, sizeof(*parms)); @@ -635,6 +964,12 @@ static void ipgre_netlink_parms(struct nlattr *data[], struct nlattr *tb[], if (!data[IFLA_GRE_PMTUDISC] || nla_get_u8(data[IFLA_GRE_PMTUDISC])) parms->iph.frag_off = htons(IP_DF); + + if (data[IFLA_GRE_COLLECT_METADATA]) { + struct ip_tunnel *t = netdev_priv(dev); + + t->collect_md = true; + } } /* This function returns true when ENCAP attributes are present in the nl msg */ @@ -712,7 +1047,7 @@ static int ipgre_newlink(struct net *src_net, struct net_device *dev, return err; } - ipgre_netlink_parms(data, tb, &p); + ipgre_netlink_parms(dev, data, tb, &p); return ip_tunnel_newlink(dev, tb, &p); } @@ -730,7 +1065,7 @@ static int ipgre_changelink(struct net_device *dev, struct nlattr *tb[], return err; } - ipgre_netlink_parms(data, tb, &p); + ipgre_netlink_parms(dev, data, tb, &p); return ip_tunnel_changelink(dev, tb, &p); } @@ -765,6 +1100,8 @@ static size_t ipgre_get_size(const struct net_device *dev) nla_total_size(2) + /* IFLA_GRE_ENCAP_DPORT */ nla_total_size(2) + + /* IFLA_GRE_COLLECT_METADATA */ + nla_total_size(0) + 0; } @@ -796,6 +1133,11 @@ static int ipgre_fill_info(struct sk_buff *skb, const struct net_device *dev) t->encap.flags)) goto nla_put_failure; + if (t->collect_md) { + if (nla_put_flag(skb, IFLA_GRE_COLLECT_METADATA)) + goto nla_put_failure; + } + return 0; nla_put_failure: @@ -817,6 +1159,7 @@ static const struct nla_policy ipgre_policy[IFLA_GRE_MAX + 1] = { [IFLA_GRE_ENCAP_FLAGS] = { .type = NLA_U16 }, [IFLA_GRE_ENCAP_SPORT] = { .type = NLA_U16 }, [IFLA_GRE_ENCAP_DPORT] = { .type = NLA_U16 }, + [IFLA_GRE_COLLECT_METADATA] = { .type = NLA_FLAG }, }; static struct rtnl_link_ops ipgre_link_ops __read_mostly = { @@ -849,9 +1192,38 @@ static struct rtnl_link_ops ipgre_tap_ops __read_mostly = { .get_link_net = ip_tunnel_get_link_net, }; +struct net_device *gretap_fb_dev_create(struct net *net, const char *name, + u8 name_assign_type) +{ + struct nlattr *tb[IFLA_MAX + 1]; + struct net_device *dev; + struct ip_tunnel *t; + int err; + + memset(&tb, 0, sizeof(tb)); + + dev = rtnl_create_link(net, name, name_assign_type, + &ipgre_tap_ops, tb); + if (IS_ERR(dev)) + return dev; + + /* Configure flow based GRE device. */ + t = netdev_priv(dev); + t->collect_md = true; + + err = ipgre_newlink(net, dev, tb, NULL); + if (err < 0) + goto out; + return dev; +out: + free_netdev(dev); + return ERR_PTR(err); +} +EXPORT_SYMBOL_GPL(gretap_fb_dev_create); + static int __net_init ipgre_tap_init_net(struct net *net) { - return ip_tunnel_init_net(net, gre_tap_net_id, &ipgre_tap_ops, NULL); + return ip_tunnel_init_net(net, gre_tap_net_id, &ipgre_tap_ops, "gretap0"); } static void __net_exit ipgre_tap_exit_net(struct net *net) @@ -881,7 +1253,7 @@ static int __init ipgre_init(void) if (err < 0) goto pnet_tap_faied; - err = gre_cisco_register(&ipgre_protocol); + err = gre_add_protocol(&ipgre_protocol, GREPROTO_CISCO); if (err < 0) { pr_info("%s: can't add protocol\n", __func__); goto add_proto_failed; @@ -900,7 +1272,7 @@ static int __init ipgre_init(void) tap_ops_failed: rtnl_link_unregister(&ipgre_link_ops); rtnl_link_failed: - gre_cisco_unregister(&ipgre_protocol); + gre_del_protocol(&ipgre_protocol, GREPROTO_CISCO); add_proto_failed: unregister_pernet_device(&ipgre_tap_net_ops); pnet_tap_faied: @@ -912,7 +1284,7 @@ static void __exit ipgre_fini(void) { rtnl_link_unregister(&ipgre_tap_ops); rtnl_link_unregister(&ipgre_link_ops); - gre_cisco_unregister(&ipgre_protocol); + gre_del_protocol(&ipgre_protocol, GREPROTO_CISCO); unregister_pernet_device(&ipgre_tap_net_ops); unregister_pernet_device(&ipgre_net_ops); } diff --git a/net/ipv4/ip_input.c b/net/ipv4/ip_input.c index 2db4c8773c1b..f4fc8a77aaa7 100644 --- a/net/ipv4/ip_input.c +++ b/net/ipv4/ip_input.c @@ -146,6 +146,7 @@ #include <net/xfrm.h> #include <linux/mroute.h> #include <linux/netlink.h> +#include <net/dst_metadata.h> /* * Process Router Attention IP option (RFC 2113) @@ -331,7 +332,7 @@ static int ip_rcv_finish(struct sock *sk, struct sk_buff *skb) * Initialise the virtual path cache for the packet. It describes * how the packet travels inside Linux networking. */ - if (!skb_dst(skb)) { + if (!skb_valid_dst(skb)) { int err = ip_route_input_noref(skb, iph->daddr, iph->saddr, iph->tos, skb->dev); if (unlikely(err)) { diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index 6bf89a6312bc..0138fada0951 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -1542,6 +1542,7 @@ void ip_send_unicast_reply(struct sock *sk, struct sk_buff *skb, struct net *net = sock_net(sk); struct sk_buff *nskb; int err; + int oif; if (__ip_options_echo(&replyopts.opt.opt, skb, sopt)) return; @@ -1559,7 +1560,11 @@ void ip_send_unicast_reply(struct sock *sk, struct sk_buff *skb, daddr = replyopts.opt.opt.faddr; } - flowi4_init_output(&fl4, arg->bound_dev_if, + oif = arg->bound_dev_if; + if (!oif && netif_index_is_vrf(net, skb->skb_iif)) + oif = skb->skb_iif; + + flowi4_init_output(&fl4, oif, IP4_REPLY_MARK(net, skb->mark), RT_TOS(arg->tos), RT_SCOPE_UNIVERSE, ip_hdr(skb)->protocol, diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c index 626d9e56a6bd..cbb51f3fac06 100644 --- a/net/ipv4/ip_tunnel.c +++ b/net/ipv4/ip_tunnel.c @@ -230,10 +230,13 @@ skip_key_lookup: if (cand) return cand; + t = rcu_dereference(itn->collect_md_tun); + if (t) + return t; + if (itn->fb_tunnel_dev && itn->fb_tunnel_dev->flags & IFF_UP) return netdev_priv(itn->fb_tunnel_dev); - return NULL; } EXPORT_SYMBOL_GPL(ip_tunnel_lookup); @@ -261,11 +264,15 @@ static void ip_tunnel_add(struct ip_tunnel_net *itn, struct ip_tunnel *t) { struct hlist_head *head = ip_bucket(itn, &t->parms); + if (t->collect_md) + rcu_assign_pointer(itn->collect_md_tun, t); hlist_add_head_rcu(&t->hash_node, head); } -static void ip_tunnel_del(struct ip_tunnel *t) +static void ip_tunnel_del(struct ip_tunnel_net *itn, struct ip_tunnel *t) { + if (t->collect_md) + rcu_assign_pointer(itn->collect_md_tun, NULL); hlist_del_init_rcu(&t->hash_node); } @@ -419,7 +426,8 @@ static struct ip_tunnel *ip_tunnel_create(struct net *net, } int ip_tunnel_rcv(struct ip_tunnel *tunnel, struct sk_buff *skb, - const struct tnl_ptk_info *tpi, bool log_ecn_error) + const struct tnl_ptk_info *tpi, struct metadata_dst *tun_dst, + bool log_ecn_error) { struct pcpu_sw_netstats *tstats; const struct iphdr *iph = ip_hdr(skb); @@ -478,6 +486,9 @@ int ip_tunnel_rcv(struct ip_tunnel *tunnel, struct sk_buff *skb, skb->dev = tunnel->dev; } + if (tun_dst) + skb_dst_set(skb, (struct dst_entry *)tun_dst); + gro_cells_receive(&tunnel->gro_cells, skb); return 0; @@ -806,7 +817,7 @@ static void ip_tunnel_update(struct ip_tunnel_net *itn, struct ip_tunnel_parm *p, bool set_mtu) { - ip_tunnel_del(t); + ip_tunnel_del(itn, t); t->parms.iph.saddr = p->iph.saddr; t->parms.iph.daddr = p->iph.daddr; t->parms.i_key = p->i_key; @@ -967,7 +978,7 @@ void ip_tunnel_dellink(struct net_device *dev, struct list_head *head) itn = net_generic(tunnel->net, tunnel->ip_tnl_net_id); if (itn->fb_tunnel_dev != dev) { - ip_tunnel_del(netdev_priv(dev)); + ip_tunnel_del(itn, netdev_priv(dev)); unregister_netdevice_queue(dev, head); } } @@ -1072,8 +1083,13 @@ int ip_tunnel_newlink(struct net_device *dev, struct nlattr *tb[], nt = netdev_priv(dev); itn = net_generic(net, nt->ip_tnl_net_id); - if (ip_tunnel_find(itn, p, dev->type)) - return -EEXIST; + if (nt->collect_md) { + if (rtnl_dereference(itn->collect_md_tun)) + return -EEXIST; + } else { + if (ip_tunnel_find(itn, p, dev->type)) + return -EEXIST; + } nt->net = net; nt->parms = *p; @@ -1089,7 +1105,6 @@ int ip_tunnel_newlink(struct net_device *dev, struct nlattr *tb[], dev->mtu = mtu; ip_tunnel_add(itn, nt); - out: return err; } @@ -1163,6 +1178,10 @@ int ip_tunnel_init(struct net_device *dev) iph->version = 4; iph->ihl = 5; + if (tunnel->collect_md) { + dev->features |= NETIF_F_NETNS_LOCAL; + netif_keep_dst(dev); + } return 0; } EXPORT_SYMBOL_GPL(ip_tunnel_init); @@ -1176,7 +1195,7 @@ void ip_tunnel_uninit(struct net_device *dev) itn = net_generic(net, tunnel->ip_tnl_net_id); /* fb_tunnel_dev will be unregisted in net-exit call. */ if (itn->fb_tunnel_dev != dev) - ip_tunnel_del(netdev_priv(dev)); + ip_tunnel_del(itn, netdev_priv(dev)); ip_tunnel_dst_reset_all(tunnel); } diff --git a/net/ipv4/ip_tunnel_core.c b/net/ipv4/ip_tunnel_core.c index 6a51a71a6c67..29ed6c5a5185 100644 --- a/net/ipv4/ip_tunnel_core.c +++ b/net/ipv4/ip_tunnel_core.c @@ -32,6 +32,7 @@ #include <linux/etherdevice.h> #include <linux/if_ether.h> #include <linux/if_vlan.h> +#include <linux/static_key.h> #include <net/ip.h> #include <net/icmp.h> @@ -190,3 +191,232 @@ struct rtnl_link_stats64 *ip_tunnel_get_stats64(struct net_device *dev, return tot; } EXPORT_SYMBOL_GPL(ip_tunnel_get_stats64); + +static const struct nla_policy ip_tun_policy[LWTUNNEL_IP_MAX + 1] = { + [LWTUNNEL_IP_ID] = { .type = NLA_U64 }, + [LWTUNNEL_IP_DST] = { .type = NLA_U32 }, + [LWTUNNEL_IP_SRC] = { .type = NLA_U32 }, + [LWTUNNEL_IP_TTL] = { .type = NLA_U8 }, + [LWTUNNEL_IP_TOS] = { .type = NLA_U8 }, + [LWTUNNEL_IP_SPORT] = { .type = NLA_U16 }, + [LWTUNNEL_IP_DPORT] = { .type = NLA_U16 }, + [LWTUNNEL_IP_FLAGS] = { .type = NLA_U16 }, +}; + +static int ip_tun_build_state(struct net_device *dev, struct nlattr *attr, + unsigned int family, const void *cfg, + struct lwtunnel_state **ts) +{ + struct ip_tunnel_info *tun_info; + struct lwtunnel_state *new_state; + struct nlattr *tb[LWTUNNEL_IP_MAX + 1]; + int err; + + err = nla_parse_nested(tb, LWTUNNEL_IP_MAX, attr, ip_tun_policy); + if (err < 0) + return err; + + new_state = lwtunnel_state_alloc(sizeof(*tun_info)); + if (!new_state) + return -ENOMEM; + + new_state->type = LWTUNNEL_ENCAP_IP; + + tun_info = lwt_tun_info(new_state); + + if (tb[LWTUNNEL_IP_ID]) + tun_info->key.tun_id = nla_get_u64(tb[LWTUNNEL_IP_ID]); + + if (tb[LWTUNNEL_IP_DST]) + tun_info->key.u.ipv4.dst = nla_get_be32(tb[LWTUNNEL_IP_DST]); + + if (tb[LWTUNNEL_IP_SRC]) + tun_info->key.u.ipv4.src = nla_get_be32(tb[LWTUNNEL_IP_SRC]); + + if (tb[LWTUNNEL_IP_TTL]) + tun_info->key.ttl = nla_get_u8(tb[LWTUNNEL_IP_TTL]); + + if (tb[LWTUNNEL_IP_TOS]) + tun_info->key.tos = nla_get_u8(tb[LWTUNNEL_IP_TOS]); + + if (tb[LWTUNNEL_IP_SPORT]) + tun_info->key.tp_src = nla_get_be16(tb[LWTUNNEL_IP_SPORT]); + + if (tb[LWTUNNEL_IP_DPORT]) + tun_info->key.tp_dst = nla_get_be16(tb[LWTUNNEL_IP_DPORT]); + + if (tb[LWTUNNEL_IP_FLAGS]) + tun_info->key.tun_flags = nla_get_u16(tb[LWTUNNEL_IP_FLAGS]); + + tun_info->mode = IP_TUNNEL_INFO_TX; + tun_info->options_len = 0; + + *ts = new_state; + + return 0; +} + +static int ip_tun_fill_encap_info(struct sk_buff *skb, + struct lwtunnel_state *lwtstate) +{ + struct ip_tunnel_info *tun_info = lwt_tun_info(lwtstate); + + if (nla_put_u64(skb, LWTUNNEL_IP_ID, tun_info->key.tun_id) || + nla_put_be32(skb, LWTUNNEL_IP_DST, tun_info->key.u.ipv4.dst) || + nla_put_be32(skb, LWTUNNEL_IP_SRC, tun_info->key.u.ipv4.src) || + nla_put_u8(skb, LWTUNNEL_IP_TOS, tun_info->key.tos) || + nla_put_u8(skb, LWTUNNEL_IP_TTL, tun_info->key.ttl) || + nla_put_u16(skb, LWTUNNEL_IP_SPORT, tun_info->key.tp_src) || + nla_put_u16(skb, LWTUNNEL_IP_DPORT, tun_info->key.tp_dst) || + nla_put_u16(skb, LWTUNNEL_IP_FLAGS, tun_info->key.tun_flags)) + return -ENOMEM; + + return 0; +} + +static int ip_tun_encap_nlsize(struct lwtunnel_state *lwtstate) +{ + return nla_total_size(8) /* LWTUNNEL_IP_ID */ + + nla_total_size(4) /* LWTUNNEL_IP_DST */ + + nla_total_size(4) /* LWTUNNEL_IP_SRC */ + + nla_total_size(1) /* LWTUNNEL_IP_TOS */ + + nla_total_size(1) /* LWTUNNEL_IP_TTL */ + + nla_total_size(2) /* LWTUNNEL_IP_SPORT */ + + nla_total_size(2) /* LWTUNNEL_IP_DPORT */ + + nla_total_size(2); /* LWTUNNEL_IP_FLAGS */ +} + +static int ip_tun_cmp_encap(struct lwtunnel_state *a, struct lwtunnel_state *b) +{ + return memcmp(lwt_tun_info(a), lwt_tun_info(b), + sizeof(struct ip_tunnel_info)); +} + +static const struct lwtunnel_encap_ops ip_tun_lwt_ops = { + .build_state = ip_tun_build_state, + .fill_encap = ip_tun_fill_encap_info, + .get_encap_size = ip_tun_encap_nlsize, + .cmp_encap = ip_tun_cmp_encap, +}; + +static const struct nla_policy ip6_tun_policy[LWTUNNEL_IP6_MAX + 1] = { + [LWTUNNEL_IP6_ID] = { .type = NLA_U64 }, + [LWTUNNEL_IP6_DST] = { .len = sizeof(struct in6_addr) }, + [LWTUNNEL_IP6_SRC] = { .len = sizeof(struct in6_addr) }, + [LWTUNNEL_IP6_HOPLIMIT] = { .type = NLA_U8 }, + [LWTUNNEL_IP6_TC] = { .type = NLA_U8 }, + [LWTUNNEL_IP6_SPORT] = { .type = NLA_U16 }, + [LWTUNNEL_IP6_DPORT] = { .type = NLA_U16 }, + [LWTUNNEL_IP6_FLAGS] = { .type = NLA_U16 }, +}; + +static int ip6_tun_build_state(struct net_device *dev, struct nlattr *attr, + unsigned int family, const void *cfg, + struct lwtunnel_state **ts) +{ + struct ip_tunnel_info *tun_info; + struct lwtunnel_state *new_state; + struct nlattr *tb[LWTUNNEL_IP6_MAX + 1]; + int err; + + err = nla_parse_nested(tb, LWTUNNEL_IP6_MAX, attr, ip6_tun_policy); + if (err < 0) + return err; + + new_state = lwtunnel_state_alloc(sizeof(*tun_info)); + if (!new_state) + return -ENOMEM; + + new_state->type = LWTUNNEL_ENCAP_IP6; + + tun_info = lwt_tun_info(new_state); + + if (tb[LWTUNNEL_IP6_ID]) + tun_info->key.tun_id = nla_get_u64(tb[LWTUNNEL_IP6_ID]); + + if (tb[LWTUNNEL_IP6_DST]) + tun_info->key.u.ipv6.dst = nla_get_in6_addr(tb[LWTUNNEL_IP6_DST]); + + if (tb[LWTUNNEL_IP6_SRC]) + tun_info->key.u.ipv6.src = nla_get_in6_addr(tb[LWTUNNEL_IP6_SRC]); + + if (tb[LWTUNNEL_IP6_HOPLIMIT]) + tun_info->key.ttl = nla_get_u8(tb[LWTUNNEL_IP6_HOPLIMIT]); + + if (tb[LWTUNNEL_IP6_TC]) + tun_info->key.tos = nla_get_u8(tb[LWTUNNEL_IP6_TC]); + + if (tb[LWTUNNEL_IP6_SPORT]) + tun_info->key.tp_src = nla_get_be16(tb[LWTUNNEL_IP6_SPORT]); + + if (tb[LWTUNNEL_IP6_DPORT]) + tun_info->key.tp_dst = nla_get_be16(tb[LWTUNNEL_IP6_DPORT]); + + if (tb[LWTUNNEL_IP6_FLAGS]) + tun_info->key.tun_flags = nla_get_u16(tb[LWTUNNEL_IP6_FLAGS]); + + tun_info->mode = IP_TUNNEL_INFO_TX | IP_TUNNEL_INFO_IPV6; + tun_info->options_len = 0; + + *ts = new_state; + + return 0; +} + +static int ip6_tun_fill_encap_info(struct sk_buff *skb, + struct lwtunnel_state *lwtstate) +{ + struct ip_tunnel_info *tun_info = lwt_tun_info(lwtstate); + + if (nla_put_u64(skb, LWTUNNEL_IP6_ID, tun_info->key.tun_id) || + nla_put_in6_addr(skb, LWTUNNEL_IP6_DST, &tun_info->key.u.ipv6.dst) || + nla_put_in6_addr(skb, LWTUNNEL_IP6_SRC, &tun_info->key.u.ipv6.src) || + nla_put_u8(skb, LWTUNNEL_IP6_HOPLIMIT, tun_info->key.tos) || + nla_put_u8(skb, LWTUNNEL_IP6_TC, tun_info->key.ttl) || + nla_put_u16(skb, LWTUNNEL_IP6_SPORT, tun_info->key.tp_src) || + nla_put_u16(skb, LWTUNNEL_IP6_DPORT, tun_info->key.tp_dst) || + nla_put_u16(skb, LWTUNNEL_IP6_FLAGS, tun_info->key.tun_flags)) + return -ENOMEM; + + return 0; +} + +static int ip6_tun_encap_nlsize(struct lwtunnel_state *lwtstate) +{ + return nla_total_size(8) /* LWTUNNEL_IP6_ID */ + + nla_total_size(16) /* LWTUNNEL_IP6_DST */ + + nla_total_size(16) /* LWTUNNEL_IP6_SRC */ + + nla_total_size(1) /* LWTUNNEL_IP6_HOPLIMIT */ + + nla_total_size(1) /* LWTUNNEL_IP6_TC */ + + nla_total_size(2) /* LWTUNNEL_IP6_SPORT */ + + nla_total_size(2) /* LWTUNNEL_IP6_DPORT */ + + nla_total_size(2); /* LWTUNNEL_IP6_FLAGS */ +} + +static const struct lwtunnel_encap_ops ip6_tun_lwt_ops = { + .build_state = ip6_tun_build_state, + .fill_encap = ip6_tun_fill_encap_info, + .get_encap_size = ip6_tun_encap_nlsize, + .cmp_encap = ip_tun_cmp_encap, +}; + +void __init ip_tunnel_core_init(void) +{ + lwtunnel_encap_add_ops(&ip_tun_lwt_ops, LWTUNNEL_ENCAP_IP); + lwtunnel_encap_add_ops(&ip6_tun_lwt_ops, LWTUNNEL_ENCAP_IP6); +} + +struct static_key ip_tunnel_metadata_cnt = STATIC_KEY_INIT_FALSE; +EXPORT_SYMBOL(ip_tunnel_metadata_cnt); + +void ip_tunnel_need_metadata(void) +{ + static_key_slow_inc(&ip_tunnel_metadata_cnt); +} +EXPORT_SYMBOL_GPL(ip_tunnel_need_metadata); + +void ip_tunnel_unneed_metadata(void) +{ + static_key_slow_dec(&ip_tunnel_metadata_cnt); +} +EXPORT_SYMBOL_GPL(ip_tunnel_unneed_metadata); diff --git a/net/ipv4/ipconfig.c b/net/ipv4/ipconfig.c index 8e7328c6a390..ed4ef09c2136 100644 --- a/net/ipv4/ipconfig.c +++ b/net/ipv4/ipconfig.c @@ -94,7 +94,7 @@ /* Define the timeout for waiting for a DHCP/BOOTP/RARP reply */ #define CONF_OPEN_RETRIES 2 /* (Re)open devices twice */ #define CONF_SEND_RETRIES 6 /* Send six requests per open */ -#define CONF_INTER_TIMEOUT (HZ/2) /* Inter-device timeout: 1/2 second */ +#define CONF_INTER_TIMEOUT (HZ) /* Inter-device timeout: 1 second */ #define CONF_BASE_TIMEOUT (HZ*2) /* Initial timeout: 2 seconds */ #define CONF_TIMEOUT_RANDOM (HZ) /* Maximum amount of randomization */ #define CONF_TIMEOUT_MULT *7/4 /* Rate of timeout growth */ diff --git a/net/ipv4/ipip.c b/net/ipv4/ipip.c index 254238daf58b..f34c31defafe 100644 --- a/net/ipv4/ipip.c +++ b/net/ipv4/ipip.c @@ -198,7 +198,7 @@ static int ipip_rcv(struct sk_buff *skb) goto drop; if (iptunnel_pull_header(skb, 0, tpi.proto)) goto drop; - return ip_tunnel_rcv(tunnel, skb, &tpi, log_ecn_error); + return ip_tunnel_rcv(tunnel, skb, &tpi, NULL, log_ecn_error); } return -1; diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c index 3a2c0162c3ba..866ee89f5254 100644 --- a/net/ipv4/ipmr.c +++ b/net/ipv4/ipmr.c @@ -233,7 +233,6 @@ static const struct fib_rules_ops __net_initconst ipmr_rules_ops_template = { .match = ipmr_rule_match, .configure = ipmr_rule_configure, .compare = ipmr_rule_compare, - .default_pref = fib_default_rule_pref, .fill = ipmr_rule_fill, .nlgroup = RTNLGRP_IPV4_RULE, .policy = ipmr_rule_policy, diff --git a/net/ipv4/netfilter/Kconfig b/net/ipv4/netfilter/Kconfig index 2199a5db25e6..690d27d3f2f9 100644 --- a/net/ipv4/netfilter/Kconfig +++ b/net/ipv4/netfilter/Kconfig @@ -58,6 +58,12 @@ config NFT_REJECT_IPV4 default NFT_REJECT tristate +config NFT_DUP_IPV4 + tristate "IPv4 nf_tables packet duplication support" + select NF_DUP_IPV4 + help + This module enables IPv4 packet duplication support for nf_tables. + endif # NF_TABLES_IPV4 config NF_TABLES_ARP @@ -67,6 +73,12 @@ config NF_TABLES_ARP endif # NF_TABLES +config NF_DUP_IPV4 + tristate "Netfilter IPv4 packet duplication to alternate destination" + help + This option enables the nf_dup_ipv4 core, which duplicates an IPv4 + packet to be rerouted to another destination. + config NF_LOG_ARP tristate "ARP packet logging" default m if NETFILTER_ADVANCED=n diff --git a/net/ipv4/netfilter/Makefile b/net/ipv4/netfilter/Makefile index 7fe6c703528f..87b073da14c9 100644 --- a/net/ipv4/netfilter/Makefile +++ b/net/ipv4/netfilter/Makefile @@ -41,6 +41,7 @@ obj-$(CONFIG_NFT_CHAIN_NAT_IPV4) += nft_chain_nat_ipv4.o obj-$(CONFIG_NFT_REJECT_IPV4) += nft_reject_ipv4.o obj-$(CONFIG_NFT_MASQ_IPV4) += nft_masq_ipv4.o obj-$(CONFIG_NFT_REDIR_IPV4) += nft_redir_ipv4.o +obj-$(CONFIG_NFT_DUP_IPV4) += nft_dup_ipv4.o obj-$(CONFIG_NF_TABLES_ARP) += nf_tables_arp.o # generic IP tables @@ -70,3 +71,5 @@ obj-$(CONFIG_IP_NF_ARP_MANGLE) += arpt_mangle.o # just filtering instance of ARP tables for now obj-$(CONFIG_IP_NF_ARPFILTER) += arptable_filter.o + +obj-$(CONFIG_NF_DUP_IPV4) += nf_dup_ipv4.o diff --git a/net/ipv4/netfilter/arp_tables.c b/net/ipv4/netfilter/arp_tables.c index 92305a1a021a..8f87fc38ccde 100644 --- a/net/ipv4/netfilter/arp_tables.c +++ b/net/ipv4/netfilter/arp_tables.c @@ -240,7 +240,7 @@ get_entry(const void *base, unsigned int offset) return (struct arpt_entry *)(base + offset); } -static inline __pure +static inline struct arpt_entry *arpt_next_entry(const struct arpt_entry *entry) { return (void *)entry + entry->next_offset; @@ -280,6 +280,9 @@ unsigned int arpt_do_table(struct sk_buff *skb, table_base = private->entries; jumpstack = (struct arpt_entry **)private->jumpstack[cpu]; + /* No TEE support for arptables, so no need to switch to alternate + * stack. All targets that reenter must return absolute verdicts. + */ e = get_entry(table_base, private->hook_entry[hook]); acpar.in = state->in; @@ -325,11 +328,6 @@ unsigned int arpt_do_table(struct sk_buff *skb, } if (table_base + v != arpt_next_entry(e)) { - - if (stackidx >= private->stacksize) { - verdict = NF_DROP; - break; - } jumpstack[stackidx++] = e; } @@ -337,9 +335,6 @@ unsigned int arpt_do_table(struct sk_buff *skb, continue; } - /* Targets which reenter must return - * abs. verdicts - */ acpar.target = t->u.kernel.target; acpar.targinfo = t->data; verdict = t->u.kernel.target->target(skb, &acpar); diff --git a/net/ipv4/netfilter/ip_tables.c b/net/ipv4/netfilter/ip_tables.c index 6c72fbb7b49e..b0a86e73451c 100644 --- a/net/ipv4/netfilter/ip_tables.c +++ b/net/ipv4/netfilter/ip_tables.c @@ -276,7 +276,7 @@ static void trace_packet(const struct sk_buff *skb, } #endif -static inline __pure +static inline struct ipt_entry *ipt_next_entry(const struct ipt_entry *entry) { return (void *)entry + entry->next_offset; @@ -296,12 +296,13 @@ ipt_do_table(struct sk_buff *skb, const char *indev, *outdev; const void *table_base; struct ipt_entry *e, **jumpstack; - unsigned int *stackptr, origptr, cpu; + unsigned int stackidx, cpu; const struct xt_table_info *private; struct xt_action_param acpar; unsigned int addend; /* Initialization */ + stackidx = 0; ip = ip_hdr(skb); indev = state->in ? state->in->name : nulldevname; outdev = state->out ? state->out->name : nulldevname; @@ -331,13 +332,21 @@ ipt_do_table(struct sk_buff *skb, smp_read_barrier_depends(); table_base = private->entries; jumpstack = (struct ipt_entry **)private->jumpstack[cpu]; - stackptr = per_cpu_ptr(private->stackptr, cpu); - origptr = *stackptr; + + /* Switch to alternate jumpstack if we're being invoked via TEE. + * TEE issues XT_CONTINUE verdict on original skb so we must not + * clobber the jumpstack. + * + * For recursion via REJECT or SYNPROXY the stack will be clobbered + * but it is no problem since absolute verdict is issued by these. + */ + if (static_key_false(&xt_tee_enabled)) + jumpstack += private->stacksize * __this_cpu_read(nf_skb_duplicated); e = get_entry(table_base, private->hook_entry[hook]); - pr_debug("Entering %s(hook %u); sp at %u (UF %p)\n", - table->name, hook, origptr, + pr_debug("Entering %s(hook %u), UF %p\n", + table->name, hook, get_entry(table_base, private->underflow[hook])); do { @@ -383,28 +392,24 @@ ipt_do_table(struct sk_buff *skb, verdict = (unsigned int)(-v) - 1; break; } - if (*stackptr <= origptr) { + if (stackidx == 0) { e = get_entry(table_base, private->underflow[hook]); pr_debug("Underflow (this is normal) " "to %p\n", e); } else { - e = jumpstack[--*stackptr]; + e = jumpstack[--stackidx]; pr_debug("Pulled %p out from pos %u\n", - e, *stackptr); + e, stackidx); e = ipt_next_entry(e); } continue; } if (table_base + v != ipt_next_entry(e) && !(e->ip.flags & IPT_F_GOTO)) { - if (*stackptr >= private->stacksize) { - verdict = NF_DROP; - break; - } - jumpstack[(*stackptr)++] = e; + jumpstack[stackidx++] = e; pr_debug("Pushed %p into pos %u\n", - e, *stackptr - 1); + e, stackidx - 1); } e = get_entry(table_base, v); @@ -423,9 +428,8 @@ ipt_do_table(struct sk_buff *skb, /* Verdict */ break; } while (!acpar.hotdrop); - pr_debug("Exiting %s; resetting sp from %u to %u\n", - __func__, *stackptr, origptr); - *stackptr = origptr; + pr_debug("Exiting %s; sp at %u\n", __func__, stackidx); + xt_write_recseq_end(addend); local_bh_enable(); diff --git a/net/ipv4/netfilter/ipt_ECN.c b/net/ipv4/netfilter/ipt_ECN.c index 4bf3dc49ad1e..270765236f5e 100644 --- a/net/ipv4/netfilter/ipt_ECN.c +++ b/net/ipv4/netfilter/ipt_ECN.c @@ -72,7 +72,7 @@ set_ect_tcp(struct sk_buff *skb, const struct ipt_ECN_info *einfo) tcph->cwr = einfo->proto.tcp.cwr; inet_proto_csum_replace2(&tcph->check, skb, - oldval, ((__be16 *)tcph)[6], 0); + oldval, ((__be16 *)tcph)[6], false); return true; } diff --git a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c index 30ad9554b5e9..8a2caaf3940b 100644 --- a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c +++ b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c @@ -280,7 +280,7 @@ getorigdst(struct sock *sk, int optval, void __user *user, int *len) return -EINVAL; } - h = nf_conntrack_find_get(sock_net(sk), NF_CT_DEFAULT_ZONE, &tuple); + h = nf_conntrack_find_get(sock_net(sk), &nf_ct_zone_dflt, &tuple); if (h) { struct sockaddr_in sin; struct nf_conn *ct = nf_ct_tuplehash_to_ctrack(h); diff --git a/net/ipv4/netfilter/nf_conntrack_proto_icmp.c b/net/ipv4/netfilter/nf_conntrack_proto_icmp.c index 80d5554b9a88..cdde3ec496e9 100644 --- a/net/ipv4/netfilter/nf_conntrack_proto_icmp.c +++ b/net/ipv4/netfilter/nf_conntrack_proto_icmp.c @@ -134,9 +134,11 @@ icmp_error_message(struct net *net, struct nf_conn *tmpl, struct sk_buff *skb, struct nf_conntrack_tuple innertuple, origtuple; const struct nf_conntrack_l4proto *innerproto; const struct nf_conntrack_tuple_hash *h; - u16 zone = tmpl ? nf_ct_zone(tmpl) : NF_CT_DEFAULT_ZONE; + const struct nf_conntrack_zone *zone; + struct nf_conntrack_zone tmp; NF_CT_ASSERT(skb->nfct == NULL); + zone = nf_ct_zone_tmpl(tmpl, skb, &tmp); /* Are they talking about one of our connections? */ if (!nf_ct_get_tuplepr(skb, diff --git a/net/ipv4/netfilter/nf_defrag_ipv4.c b/net/ipv4/netfilter/nf_defrag_ipv4.c index c88b7d434718..9306ec4fab41 100644 --- a/net/ipv4/netfilter/nf_defrag_ipv4.c +++ b/net/ipv4/netfilter/nf_defrag_ipv4.c @@ -43,22 +43,22 @@ static int nf_ct_ipv4_gather_frags(struct sk_buff *skb, u_int32_t user) static enum ip_defrag_users nf_ct_defrag_user(unsigned int hooknum, struct sk_buff *skb) { - u16 zone = NF_CT_DEFAULT_ZONE; - + u16 zone_id = NF_CT_DEFAULT_ZONE_ID; #if IS_ENABLED(CONFIG_NF_CONNTRACK) - if (skb->nfct) - zone = nf_ct_zone((struct nf_conn *)skb->nfct); -#endif + if (skb->nfct) { + enum ip_conntrack_info ctinfo; + const struct nf_conn *ct = nf_ct_get(skb, &ctinfo); -#if IS_ENABLED(CONFIG_BRIDGE_NETFILTER) - if (skb->nf_bridge && - skb->nf_bridge->mask & BRNF_NF_BRIDGE_PREROUTING) - return IP_DEFRAG_CONNTRACK_BRIDGE_IN + zone; + zone_id = nf_ct_zone_id(nf_ct_zone(ct), CTINFO2DIR(ctinfo)); + } #endif + if (nf_bridge_in_prerouting(skb)) + return IP_DEFRAG_CONNTRACK_BRIDGE_IN + zone_id; + if (hooknum == NF_INET_PRE_ROUTING) - return IP_DEFRAG_CONNTRACK_IN + zone; + return IP_DEFRAG_CONNTRACK_IN + zone_id; else - return IP_DEFRAG_CONNTRACK_OUT + zone; + return IP_DEFRAG_CONNTRACK_OUT + zone_id; } static unsigned int ipv4_conntrack_defrag(const struct nf_hook_ops *ops, diff --git a/net/ipv4/netfilter/nf_dup_ipv4.c b/net/ipv4/netfilter/nf_dup_ipv4.c new file mode 100644 index 000000000000..2d79e6e8d934 --- /dev/null +++ b/net/ipv4/netfilter/nf_dup_ipv4.c @@ -0,0 +1,121 @@ +/* + * (C) 2007 by Sebastian Claßen <sebastian.classen@freenet.ag> + * (C) 2007-2010 by Jan Engelhardt <jengelh@medozas.de> + * + * Extracted from xt_TEE.c + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License version 2 or later, as + * published by the Free Software Foundation. + */ +#include <linux/ip.h> +#include <linux/module.h> +#include <linux/percpu.h> +#include <linux/route.h> +#include <linux/skbuff.h> +#include <linux/netfilter.h> +#include <net/checksum.h> +#include <net/icmp.h> +#include <net/ip.h> +#include <net/route.h> +#include <net/netfilter/ipv4/nf_dup_ipv4.h> +#if IS_ENABLED(CONFIG_NF_CONNTRACK) +#include <net/netfilter/nf_conntrack.h> +#endif + +static struct net *pick_net(struct sk_buff *skb) +{ +#ifdef CONFIG_NET_NS + const struct dst_entry *dst; + + if (skb->dev != NULL) + return dev_net(skb->dev); + dst = skb_dst(skb); + if (dst != NULL && dst->dev != NULL) + return dev_net(dst->dev); +#endif + return &init_net; +} + +static bool nf_dup_ipv4_route(struct sk_buff *skb, const struct in_addr *gw, + int oif) +{ + const struct iphdr *iph = ip_hdr(skb); + struct net *net = pick_net(skb); + struct rtable *rt; + struct flowi4 fl4; + + memset(&fl4, 0, sizeof(fl4)); + if (oif != -1) + fl4.flowi4_oif = oif; + + fl4.daddr = gw->s_addr; + fl4.flowi4_tos = RT_TOS(iph->tos); + fl4.flowi4_scope = RT_SCOPE_UNIVERSE; + fl4.flowi4_flags = FLOWI_FLAG_KNOWN_NH; + rt = ip_route_output_key(net, &fl4); + if (IS_ERR(rt)) + return false; + + skb_dst_drop(skb); + skb_dst_set(skb, &rt->dst); + skb->dev = rt->dst.dev; + skb->protocol = htons(ETH_P_IP); + + return true; +} + +void nf_dup_ipv4(struct sk_buff *skb, unsigned int hooknum, + const struct in_addr *gw, int oif) +{ + struct iphdr *iph; + + if (this_cpu_read(nf_skb_duplicated)) + return; + /* + * Copy the skb, and route the copy. Will later return %XT_CONTINUE for + * the original skb, which should continue on its way as if nothing has + * happened. The copy should be independently delivered to the gateway. + */ + skb = pskb_copy(skb, GFP_ATOMIC); + if (skb == NULL) + return; + +#if IS_ENABLED(CONFIG_NF_CONNTRACK) + /* Avoid counting cloned packets towards the original connection. */ + nf_conntrack_put(skb->nfct); + skb->nfct = &nf_ct_untracked_get()->ct_general; + skb->nfctinfo = IP_CT_NEW; + nf_conntrack_get(skb->nfct); +#endif + /* + * If we are in PREROUTING/INPUT, the checksum must be recalculated + * since the length could have changed as a result of defragmentation. + * + * We also decrease the TTL to mitigate potential loops between two + * hosts. + * + * Set %IP_DF so that the original source is notified of a potentially + * decreased MTU on the clone route. IPv6 does this too. + */ + iph = ip_hdr(skb); + iph->frag_off |= htons(IP_DF); + if (hooknum == NF_INET_PRE_ROUTING || + hooknum == NF_INET_LOCAL_IN) + --iph->ttl; + ip_send_check(iph); + + if (nf_dup_ipv4_route(skb, gw, oif)) { + __this_cpu_write(nf_skb_duplicated, true); + ip_local_out(skb); + __this_cpu_write(nf_skb_duplicated, false); + } else { + kfree_skb(skb); + } +} +EXPORT_SYMBOL_GPL(nf_dup_ipv4); + +MODULE_AUTHOR("Sebastian Claßen <sebastian.classen@freenet.ag>"); +MODULE_AUTHOR("Jan Engelhardt <jengelh@medozas.de>"); +MODULE_DESCRIPTION("nf_dup_ipv4: Duplicate IPv4 packet"); +MODULE_LICENSE("GPL"); diff --git a/net/ipv4/netfilter/nf_nat_l3proto_ipv4.c b/net/ipv4/netfilter/nf_nat_l3proto_ipv4.c index e59cc05c09e9..22f4579b0c2a 100644 --- a/net/ipv4/netfilter/nf_nat_l3proto_ipv4.c +++ b/net/ipv4/netfilter/nf_nat_l3proto_ipv4.c @@ -120,7 +120,7 @@ static void nf_nat_ipv4_csum_update(struct sk_buff *skb, oldip = iph->daddr; newip = t->dst.u3.ip; } - inet_proto_csum_replace4(check, skb, oldip, newip, 1); + inet_proto_csum_replace4(check, skb, oldip, newip, true); } static void nf_nat_ipv4_csum_recalc(struct sk_buff *skb, @@ -151,7 +151,7 @@ static void nf_nat_ipv4_csum_recalc(struct sk_buff *skb, } } else inet_proto_csum_replace2(check, skb, - htons(oldlen), htons(datalen), 1); + htons(oldlen), htons(datalen), true); } #if IS_ENABLED(CONFIG_NF_CT_NETLINK) diff --git a/net/ipv4/netfilter/nf_nat_proto_icmp.c b/net/ipv4/netfilter/nf_nat_proto_icmp.c index 4557b4ab8342..7b98baa13ede 100644 --- a/net/ipv4/netfilter/nf_nat_proto_icmp.c +++ b/net/ipv4/netfilter/nf_nat_proto_icmp.c @@ -67,7 +67,7 @@ icmp_manip_pkt(struct sk_buff *skb, hdr = (struct icmphdr *)(skb->data + hdroff); inet_proto_csum_replace2(&hdr->checksum, skb, - hdr->un.echo.id, tuple->src.u.icmp.id, 0); + hdr->un.echo.id, tuple->src.u.icmp.id, false); hdr->un.echo.id = tuple->src.u.icmp.id; return true; } diff --git a/net/ipv4/netfilter/nft_dup_ipv4.c b/net/ipv4/netfilter/nft_dup_ipv4.c new file mode 100644 index 000000000000..b45932d43b69 --- /dev/null +++ b/net/ipv4/netfilter/nft_dup_ipv4.c @@ -0,0 +1,110 @@ +/* + * Copyright (c) 2015 Pablo Neira Ayuso <pablo@netfilter.org> + * + * 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/kernel.h> +#include <linux/init.h> +#include <linux/module.h> +#include <linux/netlink.h> +#include <linux/netfilter.h> +#include <linux/netfilter/nf_tables.h> +#include <net/netfilter/nf_tables.h> +#include <net/netfilter/ipv4/nf_dup_ipv4.h> + +struct nft_dup_ipv4 { + enum nft_registers sreg_addr:8; + enum nft_registers sreg_dev:8; +}; + +static void nft_dup_ipv4_eval(const struct nft_expr *expr, + struct nft_regs *regs, + const struct nft_pktinfo *pkt) +{ + struct nft_dup_ipv4 *priv = nft_expr_priv(expr); + struct in_addr gw = { + .s_addr = (__force __be32)regs->data[priv->sreg_addr], + }; + int oif = regs->data[priv->sreg_dev]; + + nf_dup_ipv4(pkt->skb, pkt->ops->hooknum, &gw, oif); +} + +static int nft_dup_ipv4_init(const struct nft_ctx *ctx, + const struct nft_expr *expr, + const struct nlattr * const tb[]) +{ + struct nft_dup_ipv4 *priv = nft_expr_priv(expr); + int err; + + if (tb[NFTA_DUP_SREG_ADDR] == NULL) + return -EINVAL; + + priv->sreg_addr = nft_parse_register(tb[NFTA_DUP_SREG_ADDR]); + err = nft_validate_register_load(priv->sreg_addr, sizeof(struct in_addr)); + if (err < 0) + return err; + + if (tb[NFTA_DUP_SREG_DEV] != NULL) { + priv->sreg_dev = nft_parse_register(tb[NFTA_DUP_SREG_DEV]); + return nft_validate_register_load(priv->sreg_dev, sizeof(int)); + } + return 0; +} + +static int nft_dup_ipv4_dump(struct sk_buff *skb, const struct nft_expr *expr) +{ + struct nft_dup_ipv4 *priv = nft_expr_priv(expr); + + if (nft_dump_register(skb, NFTA_DUP_SREG_ADDR, priv->sreg_addr) || + nft_dump_register(skb, NFTA_DUP_SREG_DEV, priv->sreg_dev)) + goto nla_put_failure; + + return 0; + +nla_put_failure: + return -1; +} + +static struct nft_expr_type nft_dup_ipv4_type; +static const struct nft_expr_ops nft_dup_ipv4_ops = { + .type = &nft_dup_ipv4_type, + .size = NFT_EXPR_SIZE(sizeof(struct nft_dup_ipv4)), + .eval = nft_dup_ipv4_eval, + .init = nft_dup_ipv4_init, + .dump = nft_dup_ipv4_dump, +}; + +static const struct nla_policy nft_dup_ipv4_policy[NFTA_DUP_MAX + 1] = { + [NFTA_DUP_SREG_ADDR] = { .type = NLA_U32 }, + [NFTA_DUP_SREG_DEV] = { .type = NLA_U32 }, +}; + +static struct nft_expr_type nft_dup_ipv4_type __read_mostly = { + .family = NFPROTO_IPV4, + .name = "dup", + .ops = &nft_dup_ipv4_ops, + .policy = nft_dup_ipv4_policy, + .maxattr = NFTA_DUP_MAX, + .owner = THIS_MODULE, +}; + +static int __init nft_dup_ipv4_module_init(void) +{ + return nft_register_expr(&nft_dup_ipv4_type); +} + +static void __exit nft_dup_ipv4_module_exit(void) +{ + nft_unregister_expr(&nft_dup_ipv4_type); +} + +module_init(nft_dup_ipv4_module_init); +module_exit(nft_dup_ipv4_module_exit); + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Pablo Neira Ayuso <pablo@netfilter.org>"); +MODULE_ALIAS_NFT_AF_EXPR(AF_INET, "dup"); diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c index 05ff44b758df..e89094ab5ddb 100644 --- a/net/ipv4/ping.c +++ b/net/ipv4/ping.c @@ -363,7 +363,8 @@ static int ping_check_bind_addr(struct sock *sk, struct inet_sock *isk, scoped); rcu_read_unlock(); - if (!(isk->freebind || isk->transparent || has_addr || + if (!(net->ipv6.sysctl.ip_nonlocal_bind || + isk->freebind || isk->transparent || has_addr || addr_type == IPV6_ADDR_ANY)) return -EADDRNOTAVAIL; diff --git a/net/ipv4/proc.c b/net/ipv4/proc.c index da5d483e236a..3abd9d7a3adf 100644 --- a/net/ipv4/proc.c +++ b/net/ipv4/proc.c @@ -300,6 +300,8 @@ static const struct snmp_mib snmp4_net_list[] = { SNMP_MIB_ITEM("TCPACKSkippedChallenge", LINUX_MIB_TCPACKSKIPPEDCHALLENGE), SNMP_MIB_ITEM("TCPWinProbe", LINUX_MIB_TCPWINPROBE), SNMP_MIB_ITEM("TCPKeepAlive", LINUX_MIB_TCPKEEPALIVE), + SNMP_MIB_ITEM("TCPMTUPFail", LINUX_MIB_TCPMTUPFAIL), + SNMP_MIB_ITEM("TCPMTUPSuccess", LINUX_MIB_TCPMTUPSUCCESS), SNMP_MIB_SENTINEL }; diff --git a/net/ipv4/route.c b/net/ipv4/route.c index e681b852ced1..5f4a5565ad8b 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -91,6 +91,7 @@ #include <linux/slab.h> #include <linux/jhash.h> #include <net/dst.h> +#include <net/dst_metadata.h> #include <net/net_namespace.h> #include <net/protocol.h> #include <net/ip.h> @@ -102,6 +103,7 @@ #include <net/tcp.h> #include <net/icmp.h> #include <net/xfrm.h> +#include <net/lwtunnel.h> #include <net/netevent.h> #include <net/rtnetlink.h> #ifdef CONFIG_SYSCTL @@ -109,6 +111,8 @@ #include <linux/kmemleak.h> #endif #include <net/secure_seq.h> +#include <net/ip_tunnels.h> +#include <net/vrf.h> #define RT_FL_TOS(oldflp4) \ ((oldflp4)->flowi4_tos & (IPTOS_RT_MASK | RTO_ONLINK)) @@ -834,6 +838,7 @@ void ip_rt_send_redirect(struct sk_buff *skb) struct inet_peer *peer; struct net *net; int log_martians; + int vif; rcu_read_lock(); in_dev = __in_dev_get_rcu(rt->dst.dev); @@ -842,10 +847,11 @@ void ip_rt_send_redirect(struct sk_buff *skb) return; } log_martians = IN_DEV_LOG_MARTIANS(in_dev); + vif = vrf_master_ifindex_rcu(rt->dst.dev); rcu_read_unlock(); net = dev_net(rt->dst.dev); - peer = inet_getpeer_v4(net->ipv4.peers, ip_hdr(skb)->saddr, 1); + peer = inet_getpeer_v4(net->ipv4.peers, ip_hdr(skb)->saddr, vif, 1); if (!peer) { icmp_send(skb, ICMP_REDIRECT, ICMP_REDIR_HOST, rt_nexthop(rt, ip_hdr(skb)->daddr)); @@ -934,7 +940,8 @@ static int ip_error(struct sk_buff *skb) break; } - peer = inet_getpeer_v4(net->ipv4.peers, ip_hdr(skb)->saddr, 1); + peer = inet_getpeer_v4(net->ipv4.peers, ip_hdr(skb)->saddr, + vrf_master_ifindex(skb->dev), 1); send = true; if (peer) { @@ -1403,6 +1410,7 @@ static void rt_set_nexthop(struct rtable *rt, __be32 daddr, #ifdef CONFIG_IP_ROUTE_CLASSID rt->dst.tclassid = nh->nh_tclassid; #endif + rt->dst.lwtstate = lwtstate_get(nh->nh_lwtstate); if (unlikely(fnhe)) cached = rt_bind_exception(rt, fnhe, daddr); else if (!(rt->dst.flags & DST_NOCACHE)) @@ -1546,7 +1554,6 @@ static int __mkroute_input(struct sk_buff *skb, struct rtable *rth; int err; struct in_device *out_dev; - unsigned int flags = 0; bool do_cache; u32 itag = 0; @@ -1610,7 +1617,7 @@ static int __mkroute_input(struct sk_buff *skb, } rth->rt_genid = rt_genid_ipv4(dev_net(rth->dst.dev)); - rth->rt_flags = flags; + rth->rt_flags = 0; rth->rt_type = res->type; rth->rt_is_input = 1; rth->rt_iif = 0; @@ -1624,6 +1631,14 @@ static int __mkroute_input(struct sk_buff *skb, rth->dst.output = ip_output; rt_set_nexthop(rth, daddr, res, fnhe, res->fi, res->type, itag); + if (lwtunnel_output_redirect(rth->dst.lwtstate)) { + rth->dst.lwtstate->orig_output = rth->dst.output; + rth->dst.output = lwtunnel_output; + } + if (lwtunnel_input_redirect(rth->dst.lwtstate)) { + rth->dst.lwtstate->orig_input = rth->dst.input; + rth->dst.input = lwtunnel_input; + } skb_dst_set(skb, &rth->dst); out: err = 0; @@ -1662,6 +1677,7 @@ static int ip_route_input_slow(struct sk_buff *skb, __be32 daddr, __be32 saddr, { struct fib_result res; struct in_device *in_dev = __in_dev_get_rcu(dev); + struct ip_tunnel_info *tun_info; struct flowi4 fl4; unsigned int flags = 0; u32 itag = 0; @@ -1679,6 +1695,13 @@ static int ip_route_input_slow(struct sk_buff *skb, __be32 daddr, __be32 saddr, by fib_lookup. */ + tun_info = skb_tunnel_info(skb); + if (tun_info && !(tun_info->mode & IP_TUNNEL_INFO_TX)) + fl4.flowi4_tun_key.tun_id = tun_info->key.tun_id; + else + fl4.flowi4_tun_key.tun_id = 0; + skb_dst_drop(skb); + if (ipv4_is_multicast(saddr) || ipv4_is_lbcast(saddr)) goto martian_source; @@ -1710,7 +1733,7 @@ static int ip_route_input_slow(struct sk_buff *skb, __be32 daddr, __be32 saddr, * Now we are ready to route packet. */ fl4.flowi4_oif = 0; - fl4.flowi4_iif = dev->ifindex; + fl4.flowi4_iif = vrf_master_ifindex_rcu(dev) ? : dev->ifindex; fl4.flowi4_mark = skb->mark; fl4.flowi4_tos = tos; fl4.flowi4_scope = RT_SCOPE_UNIVERSE; @@ -1792,6 +1815,7 @@ local_input: rth->rt_gateway = 0; rth->rt_uses_gateway = 0; INIT_LIST_HEAD(&rth->rt_uncached); + RT_CACHE_STAT_INC(in_slow_tot); if (res.type == RTN_UNREACHABLE) { rth->dst.input= ip_error; @@ -1981,7 +2005,6 @@ add: rth->rt_gateway = 0; rth->rt_uses_gateway = 0; INIT_LIST_HEAD(&rth->rt_uncached); - RT_CACHE_STAT_INC(out_slow_tot); if (flags & RTCF_LOCAL) @@ -2004,6 +2027,8 @@ add: } rt_set_nexthop(rth, fl4->daddr, res, fnhe, fi, type, 0); + if (lwtunnel_output_redirect(rth->dst.lwtstate)) + rth->dst.output = lwtunnel_output; return rth; } @@ -2110,6 +2135,11 @@ struct rtable *__ip_route_output_key(struct net *net, struct flowi4 *fl4) fl4->saddr = inet_select_addr(dev_out, 0, RT_SCOPE_HOST); } + if (netif_is_vrf(dev_out) && + !(fl4->flowi4_flags & FLOWI_FLAG_VRFSRC)) { + rth = vrf_dev_get_rth(dev_out); + goto out; + } } if (!fl4->daddr) { @@ -2261,7 +2291,6 @@ struct dst_entry *ipv4_blackhole_route(struct net *net, struct dst_entry *dst_or rt->rt_uses_gateway = ort->rt_uses_gateway; INIT_LIST_HEAD(&rt->rt_uncached); - dst_free(new); } diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c index 0330ab2e2b63..894da3a70aff 100644 --- a/net/ipv4/sysctl_net_ipv4.c +++ b/net/ipv4/sysctl_net_ipv4.c @@ -29,6 +29,7 @@ static int zero; static int one = 1; static int four = 4; +static int thousand = 1000; static int gso_max_segs = GSO_MAX_SEGS; static int tcp_retr1_max = 255; static int ip_local_port_range_min[] = { 1, 1 }; @@ -712,6 +713,24 @@ static struct ctl_table ipv4_table[] = { .extra2 = &gso_max_segs, }, { + .procname = "tcp_pacing_ss_ratio", + .data = &sysctl_tcp_pacing_ss_ratio, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = &zero, + .extra2 = &thousand, + }, + { + .procname = "tcp_pacing_ca_ratio", + .data = &sysctl_tcp_pacing_ca_ratio, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = &zero, + .extra2 = &thousand, + }, + { .procname = "tcp_autocorking", .data = &sysctl_tcp_autocorking, .maxlen = sizeof(int), @@ -910,6 +929,13 @@ static struct ctl_table ipv4_net_table[] = { .mode = 0644, .proc_handler = proc_dointvec, }, + { + .procname = "igmp_link_local_mcast_reports", + .data = &sysctl_igmp_llm_reports, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec + }, { } }; diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 45534a5ab430..b8b8fa184f75 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -627,6 +627,8 @@ static void skb_entail(struct sock *sk, struct sk_buff *skb) sk_mem_charge(sk, skb->truesize); if (tp->nonagle & TCP_NAGLE_PUSH) tp->nonagle &= ~TCP_NAGLE_PUSH; + + tcp_slow_start_after_idle_check(sk); } static inline void tcp_mark_urg(struct tcp_sock *tp, int flags) diff --git a/net/ipv4/tcp_bic.c b/net/ipv4/tcp_bic.c index c037644eafb7..fd1405d37c14 100644 --- a/net/ipv4/tcp_bic.c +++ b/net/ipv4/tcp_bic.c @@ -146,7 +146,7 @@ static void bictcp_cong_avoid(struct sock *sk, u32 ack, u32 acked) if (!tcp_is_cwnd_limited(sk)) return; - if (tp->snd_cwnd <= tp->snd_ssthresh) + if (tcp_in_slow_start(tp)) tcp_slow_start(tp, acked); else { bictcp_update(ca, tp->snd_cwnd); diff --git a/net/ipv4/tcp_cdg.c b/net/ipv4/tcp_cdg.c index 8c6fd3d5e40f..167b6a3e1b98 100644 --- a/net/ipv4/tcp_cdg.c +++ b/net/ipv4/tcp_cdg.c @@ -264,7 +264,7 @@ static void tcp_cdg_cong_avoid(struct sock *sk, u32 ack, u32 acked) u32 prior_snd_cwnd; u32 incr; - if (tp->snd_cwnd < tp->snd_ssthresh && hystart_detect) + if (tcp_in_slow_start(tp) && hystart_detect) tcp_cdg_hystart_update(sk); if (after(ack, ca->rtt_seq) && ca->rtt.v64) { diff --git a/net/ipv4/tcp_cong.c b/net/ipv4/tcp_cong.c index 84be008c945c..93c4dc3ab23f 100644 --- a/net/ipv4/tcp_cong.c +++ b/net/ipv4/tcp_cong.c @@ -114,16 +114,19 @@ void tcp_unregister_congestion_control(struct tcp_congestion_ops *ca) } EXPORT_SYMBOL_GPL(tcp_unregister_congestion_control); -u32 tcp_ca_get_key_by_name(const char *name) +u32 tcp_ca_get_key_by_name(const char *name, bool *ecn_ca) { const struct tcp_congestion_ops *ca; - u32 key; + u32 key = TCP_CA_UNSPEC; might_sleep(); rcu_read_lock(); ca = __tcp_ca_find_autoload(name); - key = ca ? ca->key : TCP_CA_UNSPEC; + if (ca) { + key = ca->key; + *ecn_ca = ca->flags & TCP_CONG_NEEDS_ECN; + } rcu_read_unlock(); return key; @@ -365,10 +368,8 @@ int tcp_set_congestion_control(struct sock *sk, const char *name) */ u32 tcp_slow_start(struct tcp_sock *tp, u32 acked) { - u32 cwnd = tp->snd_cwnd + acked; + u32 cwnd = min(tp->snd_cwnd + acked, tp->snd_ssthresh); - if (cwnd > tp->snd_ssthresh) - cwnd = tp->snd_ssthresh + 1; acked -= cwnd - tp->snd_cwnd; tp->snd_cwnd = min(cwnd, tp->snd_cwnd_clamp); @@ -413,7 +414,7 @@ void tcp_reno_cong_avoid(struct sock *sk, u32 ack, u32 acked) return; /* In "safe" area, increase. */ - if (tp->snd_cwnd <= tp->snd_ssthresh) { + if (tcp_in_slow_start(tp)) { acked = tcp_slow_start(tp, acked); if (!acked) return; diff --git a/net/ipv4/tcp_cubic.c b/net/ipv4/tcp_cubic.c index 06d3d665a9fd..c6ded6b2a79f 100644 --- a/net/ipv4/tcp_cubic.c +++ b/net/ipv4/tcp_cubic.c @@ -151,6 +151,21 @@ static void bictcp_init(struct sock *sk) tcp_sk(sk)->snd_ssthresh = initial_ssthresh; } +static void bictcp_cwnd_event(struct sock *sk, enum tcp_ca_event event) +{ + if (event == CA_EVENT_TX_START) { + s32 delta = tcp_time_stamp - tcp_sk(sk)->lsndtime; + struct bictcp *ca = inet_csk_ca(sk); + + /* We were application limited (idle) for a while. + * Shift epoch_start to keep cwnd growth to cubic curve. + */ + if (ca->epoch_start && delta > 0) + ca->epoch_start += delta; + return; + } +} + /* calculate the cubic root of x using a table lookup followed by one * Newton-Raphson iteration. * Avg err ~= 0.195% @@ -320,7 +335,7 @@ static void bictcp_cong_avoid(struct sock *sk, u32 ack, u32 acked) if (!tcp_is_cwnd_limited(sk)) return; - if (tp->snd_cwnd <= tp->snd_ssthresh) { + if (tcp_in_slow_start(tp)) { if (hystart && after(ack, ca->end_seq)) bictcp_hystart_reset(sk); acked = tcp_slow_start(tp, acked); @@ -439,7 +454,7 @@ static void bictcp_acked(struct sock *sk, u32 cnt, s32 rtt_us) ca->delay_min = delay; /* hystart triggers when cwnd is larger than some threshold */ - if (hystart && tp->snd_cwnd <= tp->snd_ssthresh && + if (hystart && tcp_in_slow_start(tp) && tp->snd_cwnd >= hystart_low_window) hystart_update(sk, delay); } @@ -450,6 +465,7 @@ static struct tcp_congestion_ops cubictcp __read_mostly = { .cong_avoid = bictcp_cong_avoid, .set_state = bictcp_state, .undo_cwnd = bictcp_undo_cwnd, + .cwnd_event = bictcp_cwnd_event, .pkts_acked = bictcp_acked, .owner = THIS_MODULE, .name = "cubic", diff --git a/net/ipv4/tcp_highspeed.c b/net/ipv4/tcp_highspeed.c index 882c08aae2f5..db7842495a64 100644 --- a/net/ipv4/tcp_highspeed.c +++ b/net/ipv4/tcp_highspeed.c @@ -116,7 +116,7 @@ static void hstcp_cong_avoid(struct sock *sk, u32 ack, u32 acked) if (!tcp_is_cwnd_limited(sk)) return; - if (tp->snd_cwnd <= tp->snd_ssthresh) + if (tcp_in_slow_start(tp)) tcp_slow_start(tp, acked); else { /* Update AIMD parameters. diff --git a/net/ipv4/tcp_htcp.c b/net/ipv4/tcp_htcp.c index 58469fff6c18..82f0d9ed60f5 100644 --- a/net/ipv4/tcp_htcp.c +++ b/net/ipv4/tcp_htcp.c @@ -236,7 +236,7 @@ static void htcp_cong_avoid(struct sock *sk, u32 ack, u32 acked) if (!tcp_is_cwnd_limited(sk)) return; - if (tp->snd_cwnd <= tp->snd_ssthresh) + if (tcp_in_slow_start(tp)) tcp_slow_start(tp, acked); else { /* In dangerous area, increase slowly. diff --git a/net/ipv4/tcp_hybla.c b/net/ipv4/tcp_hybla.c index f963b274f2b0..083831e359df 100644 --- a/net/ipv4/tcp_hybla.c +++ b/net/ipv4/tcp_hybla.c @@ -112,7 +112,7 @@ static void hybla_cong_avoid(struct sock *sk, u32 ack, u32 acked) rho_fractions = ca->rho_3ls - (ca->rho << 3); - if (tp->snd_cwnd < tp->snd_ssthresh) { + if (tcp_in_slow_start(tp)) { /* * slow start * INC = 2^RHO - 1 diff --git a/net/ipv4/tcp_illinois.c b/net/ipv4/tcp_illinois.c index f71002e4db0b..2ab9bbb6faff 100644 --- a/net/ipv4/tcp_illinois.c +++ b/net/ipv4/tcp_illinois.c @@ -268,7 +268,7 @@ static void tcp_illinois_cong_avoid(struct sock *sk, u32 ack, u32 acked) return; /* In slow start */ - if (tp->snd_cwnd <= tp->snd_ssthresh) + if (tcp_in_slow_start(tp)) tcp_slow_start(tp, acked); else { diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 728f5b3d3c64..a8f515bb19c4 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -109,6 +109,7 @@ int sysctl_tcp_invalid_ratelimit __read_mostly = HZ/2; #define FLAG_SYN_ACKED 0x10 /* This ACK acknowledged SYN. */ #define FLAG_DATA_SACKED 0x20 /* New SACK. */ #define FLAG_ECE 0x40 /* ECE in this ACK */ +#define FLAG_LOST_RETRANS 0x80 /* This ACK marks some retransmission lost */ #define FLAG_SLOWPATH 0x100 /* Do not skip RFC checks for window update.*/ #define FLAG_ORIG_SACK_ACKED 0x200 /* Never retransmitted data are (s)acked */ #define FLAG_SND_UNA_ADVANCED 0x400 /* Snd_una was changed (!= FLAG_DATA_ACKED) */ @@ -196,11 +197,13 @@ static void tcp_enter_quickack_mode(struct sock *sk) * and the session is not interactive. */ -static inline bool tcp_in_quickack_mode(const struct sock *sk) +static bool tcp_in_quickack_mode(struct sock *sk) { const struct inet_connection_sock *icsk = inet_csk(sk); + const struct dst_entry *dst = __sk_dst_get(sk); - return icsk->icsk_ack.quick && !icsk->icsk_ack.pingpong; + return (dst && dst_metric(dst, RTAX_QUICKACK)) || + (icsk->icsk_ack.quick && !icsk->icsk_ack.pingpong); } static void tcp_ecn_queue_cwr(struct tcp_sock *tp) @@ -750,13 +753,29 @@ static void tcp_rtt_estimator(struct sock *sk, long mrtt_us) * TCP pacing, to smooth the burst on large writes when packets * in flight is significantly lower than cwnd (or rwin) */ +int sysctl_tcp_pacing_ss_ratio __read_mostly = 200; +int sysctl_tcp_pacing_ca_ratio __read_mostly = 120; + static void tcp_update_pacing_rate(struct sock *sk) { const struct tcp_sock *tp = tcp_sk(sk); u64 rate; /* set sk_pacing_rate to 200 % of current rate (mss * cwnd / srtt) */ - rate = (u64)tp->mss_cache * 2 * (USEC_PER_SEC << 3); + rate = (u64)tp->mss_cache * ((USEC_PER_SEC / 100) << 3); + + /* current rate is (cwnd * mss) / srtt + * In Slow Start [1], set sk_pacing_rate to 200 % the current rate. + * In Congestion Avoidance phase, set it to 120 % the current rate. + * + * [1] : Normal Slow Start condition is (tp->snd_cwnd < tp->snd_ssthresh) + * If snd_cwnd >= (tp->snd_ssthresh / 2), we are approaching + * end of slow start and should slow down. + */ + if (tp->snd_cwnd < tp->snd_ssthresh / 2) + rate *= sysctl_tcp_pacing_ss_ratio; + else + rate *= sysctl_tcp_pacing_ca_ratio; rate *= max(tp->snd_cwnd, tp->packets_out); @@ -1037,7 +1056,7 @@ static bool tcp_is_sackblock_valid(struct tcp_sock *tp, bool is_dsack, * highest SACK block). Also calculate the lowest snd_nxt among the remaining * retransmitted skbs to avoid some costly processing per ACKs. */ -static void tcp_mark_lost_retrans(struct sock *sk) +static void tcp_mark_lost_retrans(struct sock *sk, int *flag) { const struct inet_connection_sock *icsk = inet_csk(sk); struct tcp_sock *tp = tcp_sk(sk); @@ -1078,7 +1097,7 @@ static void tcp_mark_lost_retrans(struct sock *sk) if (after(received_upto, ack_seq)) { TCP_SKB_CB(skb)->sacked &= ~TCPCB_SACKED_RETRANS; tp->retrans_out -= tcp_skb_pcount(skb); - + *flag |= FLAG_LOST_RETRANS; tcp_skb_mark_lost_uncond_verify(tp, skb); NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPLOSTRETRANSMIT); } else { @@ -1818,7 +1837,7 @@ advance_sp: ((inet_csk(sk)->icsk_ca_state != TCP_CA_Loss) || tp->undo_marker)) tcp_update_reordering(sk, tp->fackets_out - state->reord, 0); - tcp_mark_lost_retrans(sk); + tcp_mark_lost_retrans(sk, &state->flag); tcp_verify_left_out(tp); out: @@ -2474,15 +2493,14 @@ static bool tcp_try_undo_loss(struct sock *sk, bool frto_undo) return false; } -/* The cwnd reduction in CWR and Recovery use the PRR algorithm - * https://datatracker.ietf.org/doc/draft-ietf-tcpm-proportional-rate-reduction/ +/* The cwnd reduction in CWR and Recovery uses the PRR algorithm in RFC 6937. * It computes the number of packets to send (sndcnt) based on packets newly * delivered: * 1) If the packets in flight is larger than ssthresh, PRR spreads the * cwnd reductions across a full RTT. - * 2) If packets in flight is lower than ssthresh (such as due to excess - * losses and/or application stalls), do not perform any further cwnd - * reductions, but instead slow start up to ssthresh. + * 2) Otherwise PRR uses packet conservation to send as much as delivered. + * But when the retransmits are acked without further losses, PRR + * slow starts cwnd up to ssthresh to speed up the recovery. */ static void tcp_init_cwnd_reduction(struct sock *sk) { @@ -2499,7 +2517,7 @@ static void tcp_init_cwnd_reduction(struct sock *sk) } static void tcp_cwnd_reduction(struct sock *sk, const int prior_unsacked, - int fast_rexmit) + int fast_rexmit, int flag) { struct tcp_sock *tp = tcp_sk(sk); int sndcnt = 0; @@ -2508,16 +2526,18 @@ static void tcp_cwnd_reduction(struct sock *sk, const int prior_unsacked, (tp->packets_out - tp->sacked_out); tp->prr_delivered += newly_acked_sacked; - if (tcp_packets_in_flight(tp) > tp->snd_ssthresh) { + if (delta < 0) { u64 dividend = (u64)tp->snd_ssthresh * tp->prr_delivered + tp->prior_cwnd - 1; sndcnt = div_u64(dividend, tp->prior_cwnd) - tp->prr_out; - } else { + } else if ((flag & FLAG_RETRANS_DATA_ACKED) && + !(flag & FLAG_LOST_RETRANS)) { sndcnt = min_t(int, delta, max_t(int, tp->prr_delivered - tp->prr_out, newly_acked_sacked) + 1); + } else { + sndcnt = min(delta, newly_acked_sacked); } - sndcnt = max(sndcnt, (fast_rexmit ? 1 : 0)); tp->snd_cwnd = tcp_packets_in_flight(tp) + sndcnt; } @@ -2578,7 +2598,7 @@ static void tcp_try_to_open(struct sock *sk, int flag, const int prior_unsacked) if (inet_csk(sk)->icsk_ca_state != TCP_CA_CWR) { tcp_try_keep_open(sk); } else { - tcp_cwnd_reduction(sk, prior_unsacked, 0); + tcp_cwnd_reduction(sk, prior_unsacked, 0, flag); } } @@ -2588,6 +2608,7 @@ static void tcp_mtup_probe_failed(struct sock *sk) icsk->icsk_mtup.search_high = icsk->icsk_mtup.probe_size - 1; icsk->icsk_mtup.probe_size = 0; + NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPMTUPFAIL); } static void tcp_mtup_probe_success(struct sock *sk) @@ -2607,6 +2628,7 @@ static void tcp_mtup_probe_success(struct sock *sk) icsk->icsk_mtup.search_low = icsk->icsk_mtup.probe_size; icsk->icsk_mtup.probe_size = 0; tcp_sync_mss(sk, icsk->icsk_pmtu_cookie); + NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPMTUPSUCCESS); } /* Do a simple retransmit without using the backoff mechanisms in @@ -2675,7 +2697,7 @@ static void tcp_enter_recovery(struct sock *sk, bool ece_ack) tp->prior_ssthresh = 0; tcp_init_undo(tp); - if (inet_csk(sk)->icsk_ca_state < TCP_CA_CWR) { + if (!tcp_in_cwnd_reduction(sk)) { if (!ece_ack) tp->prior_ssthresh = tcp_current_ssthresh(sk); tcp_init_cwnd_reduction(sk); @@ -2735,7 +2757,7 @@ static void tcp_process_loss(struct sock *sk, int flag, bool is_dupack) /* Undo during fast recovery after partial ACK. */ static bool tcp_try_undo_partial(struct sock *sk, const int acked, - const int prior_unsacked) + const int prior_unsacked, int flag) { struct tcp_sock *tp = tcp_sk(sk); @@ -2751,7 +2773,7 @@ static bool tcp_try_undo_partial(struct sock *sk, const int acked, * mark more packets lost or retransmit more. */ if (tp->retrans_out) { - tcp_cwnd_reduction(sk, prior_unsacked, 0); + tcp_cwnd_reduction(sk, prior_unsacked, 0, flag); return true; } @@ -2838,7 +2860,7 @@ static void tcp_fastretrans_alert(struct sock *sk, const int acked, if (tcp_is_reno(tp) && is_dupack) tcp_add_reno_sack(sk); } else { - if (tcp_try_undo_partial(sk, acked, prior_unsacked)) + if (tcp_try_undo_partial(sk, acked, prior_unsacked, flag)) return; /* Partial ACK arrived. Force fast retransmit. */ do_lost = tcp_is_reno(tp) || @@ -2851,9 +2873,10 @@ static void tcp_fastretrans_alert(struct sock *sk, const int acked, break; case TCP_CA_Loss: tcp_process_loss(sk, flag, is_dupack); - if (icsk->icsk_ca_state != TCP_CA_Open) + if (icsk->icsk_ca_state != TCP_CA_Open && + !(flag & FLAG_LOST_RETRANS)) return; - /* Fall through to processing in Open state. */ + /* Change state if cwnd is undone or retransmits are lost */ default: if (tcp_is_reno(tp)) { if (flag & FLAG_SND_UNA_ADVANCED) @@ -2888,7 +2911,7 @@ static void tcp_fastretrans_alert(struct sock *sk, const int acked, if (do_lost) tcp_update_scoreboard(sk, fast_rexmit); - tcp_cwnd_reduction(sk, prior_unsacked, fast_rexmit); + tcp_cwnd_reduction(sk, prior_unsacked, fast_rexmit, flag); tcp_xmit_retransmit_queue(sk); } @@ -3325,6 +3348,9 @@ static int tcp_ack_update_window(struct sock *sk, const struct sk_buff *skb, u32 tp->pred_flags = 0; tcp_fast_path_check(sk); + if (tcp_send_head(sk)) + tcp_slow_start_after_idle_check(sk); + if (nwin > tp->max_window) { tp->max_window = nwin; tcp_sync_mss(sk, inet_csk(sk)->icsk_pmtu_cookie); @@ -3562,10 +3588,6 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag) &sack_state); acked -= tp->packets_out; - /* Advance cwnd if state allows */ - if (tcp_may_raise_cwnd(sk, flag)) - tcp_cong_avoid(sk, ack, acked); - if (tcp_ack_is_dubious(sk, flag)) { is_dupack = !(flag & (FLAG_SND_UNA_ADVANCED | FLAG_NOT_DUP)); tcp_fastretrans_alert(sk, acked, prior_unsacked, @@ -3574,6 +3596,10 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag) if (tp->tlp_high_seq) tcp_process_tlp_ack(sk, ack, flag); + /* Advance cwnd if state allows */ + if (tcp_may_raise_cwnd(sk, flag)) + tcp_cong_avoid(sk, ack, acked); + if ((flag & FLAG_FORWARD_PROGRESS) || !(flag & FLAG_NOT_DUP)) { struct dst_entry *dst = __sk_dst_get(sk); if (dst) @@ -3947,7 +3973,6 @@ void tcp_reset(struct sock *sk) static void tcp_fin(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); - const struct dst_entry *dst; inet_csk_schedule_ack(sk); @@ -3959,9 +3984,7 @@ static void tcp_fin(struct sock *sk) case TCP_ESTABLISHED: /* Move to CLOSE_WAIT */ tcp_set_state(sk, TCP_CLOSE_WAIT); - dst = __sk_dst_get(sk); - if (!dst || !dst_metric(dst, RTAX_QUICKACK)) - inet_csk(sk)->icsk_ack.pingpong = 1; + inet_csk(sk)->icsk_ack.pingpong = 1; break; case TCP_CLOSE_WAIT: @@ -5980,14 +6003,17 @@ static void tcp_ecn_create_request(struct request_sock *req, const struct net *net = sock_net(listen_sk); bool th_ecn = th->ece && th->cwr; bool ect, ecn_ok; + u32 ecn_ok_dst; if (!th_ecn) return; ect = !INET_ECN_is_not_ect(TCP_SKB_CB(skb)->ip_dsfield); - ecn_ok = net->ipv4.sysctl_tcp_ecn || dst_feature(dst, RTAX_FEATURE_ECN); + ecn_ok_dst = dst_feature(dst, DST_FEATURE_ECN_MASK); + ecn_ok = net->ipv4.sysctl_tcp_ecn || ecn_ok_dst; - if ((!ect && ecn_ok) || tcp_ca_needs_ecn(listen_sk)) + if ((!ect && ecn_ok) || tcp_ca_needs_ecn(listen_sk) || + (ecn_ok_dst & DST_FEATURE_ECN_CA)) inet_rsk(req)->ecn_ok = 1; } diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 0ea2e1c5d395..93898e093d4e 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -222,7 +222,7 @@ int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) if (err) goto failure; - inet_set_txhash(sk); + sk_set_txhash(sk); rt = ip_route_newports(fl4, rt, orig_sport, orig_dport, inet->inet_sport, inet->inet_dport, sk); @@ -1277,7 +1277,7 @@ struct sock *tcp_v4_syn_recv_sock(struct sock *sk, struct sk_buff *skb, newinet->mc_ttl = ip_hdr(skb)->ttl; newinet->rcv_tos = ip_hdr(skb)->tos; inet_csk(newsk)->icsk_ext_hdr_len = 0; - inet_set_txhash(newsk); + sk_set_txhash(newsk); if (inet_opt) inet_csk(newsk)->icsk_ext_hdr_len = inet_opt->opt.optlen; newinet->inet_id = newtp->write_seq ^ jiffies; @@ -1683,8 +1683,7 @@ do_time_wait: iph->daddr, th->dest, inet_iif(skb)); if (sk2) { - inet_twsk_deschedule(inet_twsk(sk)); - inet_twsk_put(inet_twsk(sk)); + inet_twsk_deschedule_put(inet_twsk(sk)); sk = sk2; goto process; } diff --git a/net/ipv4/tcp_metrics.c b/net/ipv4/tcp_metrics.c index a51d63a43e33..c8cbc2b4b792 100644 --- a/net/ipv4/tcp_metrics.c +++ b/net/ipv4/tcp_metrics.c @@ -81,11 +81,7 @@ static void tcp_metric_set(struct tcp_metrics_block *tm, static bool addr_same(const struct inetpeer_addr *a, const struct inetpeer_addr *b) { - if (a->family != b->family) - return false; - if (a->family == AF_INET) - return a->addr.a4 == b->addr.a4; - return ipv6_addr_equal(&a->addr.in6, &b->addr.in6); + return inetpeer_addr_cmp(a, b) == 0; } struct tcpm_hash_bucket { @@ -247,14 +243,14 @@ static struct tcp_metrics_block *__tcp_get_metrics_req(struct request_sock *req, daddr.family = req->rsk_ops->family; switch (daddr.family) { case AF_INET: - saddr.addr.a4 = inet_rsk(req)->ir_loc_addr; - daddr.addr.a4 = inet_rsk(req)->ir_rmt_addr; - hash = (__force unsigned int) daddr.addr.a4; + inetpeer_set_addr_v4(&saddr, inet_rsk(req)->ir_loc_addr); + inetpeer_set_addr_v4(&daddr, inet_rsk(req)->ir_rmt_addr); + hash = ipv4_addr_hash(inet_rsk(req)->ir_rmt_addr); break; #if IS_ENABLED(CONFIG_IPV6) case AF_INET6: - saddr.addr.in6 = inet_rsk(req)->ir_v6_loc_addr; - daddr.addr.in6 = inet_rsk(req)->ir_v6_rmt_addr; + inetpeer_set_addr_v6(&saddr, &inet_rsk(req)->ir_v6_loc_addr); + inetpeer_set_addr_v6(&daddr, &inet_rsk(req)->ir_v6_rmt_addr); hash = ipv6_addr_hash(&inet_rsk(req)->ir_v6_rmt_addr); break; #endif @@ -285,25 +281,19 @@ static struct tcp_metrics_block *__tcp_get_metrics_tw(struct inet_timewait_sock struct net *net; if (tw->tw_family == AF_INET) { - saddr.family = AF_INET; - saddr.addr.a4 = tw->tw_rcv_saddr; - daddr.family = AF_INET; - daddr.addr.a4 = tw->tw_daddr; - hash = (__force unsigned int) daddr.addr.a4; + inetpeer_set_addr_v4(&saddr, tw->tw_rcv_saddr); + inetpeer_set_addr_v4(&daddr, tw->tw_daddr); + hash = ipv4_addr_hash(tw->tw_daddr); } #if IS_ENABLED(CONFIG_IPV6) else if (tw->tw_family == AF_INET6) { if (ipv6_addr_v4mapped(&tw->tw_v6_daddr)) { - saddr.family = AF_INET; - saddr.addr.a4 = tw->tw_rcv_saddr; - daddr.family = AF_INET; - daddr.addr.a4 = tw->tw_daddr; - hash = (__force unsigned int) daddr.addr.a4; + inetpeer_set_addr_v4(&saddr, tw->tw_rcv_saddr); + inetpeer_set_addr_v4(&daddr, tw->tw_daddr); + hash = ipv4_addr_hash(tw->tw_daddr); } else { - saddr.family = AF_INET6; - saddr.addr.in6 = tw->tw_v6_rcv_saddr; - daddr.family = AF_INET6; - daddr.addr.in6 = tw->tw_v6_daddr; + inetpeer_set_addr_v6(&saddr, &tw->tw_v6_rcv_saddr); + inetpeer_set_addr_v6(&daddr, &tw->tw_v6_daddr); hash = ipv6_addr_hash(&tw->tw_v6_daddr); } } @@ -335,25 +325,19 @@ static struct tcp_metrics_block *tcp_get_metrics(struct sock *sk, struct net *net; if (sk->sk_family == AF_INET) { - saddr.family = AF_INET; - saddr.addr.a4 = inet_sk(sk)->inet_saddr; - daddr.family = AF_INET; - daddr.addr.a4 = inet_sk(sk)->inet_daddr; - hash = (__force unsigned int) daddr.addr.a4; + inetpeer_set_addr_v4(&saddr, inet_sk(sk)->inet_saddr); + inetpeer_set_addr_v4(&daddr, inet_sk(sk)->inet_daddr); + hash = ipv4_addr_hash(inet_sk(sk)->inet_daddr); } #if IS_ENABLED(CONFIG_IPV6) else if (sk->sk_family == AF_INET6) { if (ipv6_addr_v4mapped(&sk->sk_v6_daddr)) { - saddr.family = AF_INET; - saddr.addr.a4 = inet_sk(sk)->inet_saddr; - daddr.family = AF_INET; - daddr.addr.a4 = inet_sk(sk)->inet_daddr; - hash = (__force unsigned int) daddr.addr.a4; + inetpeer_set_addr_v4(&saddr, inet_sk(sk)->inet_saddr); + inetpeer_set_addr_v4(&daddr, inet_sk(sk)->inet_daddr); + hash = ipv4_addr_hash(inet_sk(sk)->inet_daddr); } else { - saddr.family = AF_INET6; - saddr.addr.in6 = sk->sk_v6_rcv_saddr; - daddr.family = AF_INET6; - daddr.addr.in6 = sk->sk_v6_daddr; + inetpeer_set_addr_v6(&saddr, &sk->sk_v6_rcv_saddr); + inetpeer_set_addr_v6(&daddr, &sk->sk_v6_daddr); hash = ipv6_addr_hash(&sk->sk_v6_daddr); } } @@ -461,7 +445,7 @@ void tcp_update_metrics(struct sock *sk) tcp_metric_set(tm, TCP_METRIC_CWND, tp->snd_cwnd); } - } else if (tp->snd_cwnd > tp->snd_ssthresh && + } else if (!tcp_in_slow_start(tp) && icsk->icsk_ca_state == TCP_CA_Open) { /* Cong. avoidance phase, cwnd is reliable. */ if (!tcp_metric_locked(tm, TCP_METRIC_SSTHRESH)) @@ -796,18 +780,18 @@ static int tcp_metrics_fill_info(struct sk_buff *msg, switch (tm->tcpm_daddr.family) { case AF_INET: if (nla_put_in_addr(msg, TCP_METRICS_ATTR_ADDR_IPV4, - tm->tcpm_daddr.addr.a4) < 0) + inetpeer_get_addr_v4(&tm->tcpm_daddr)) < 0) goto nla_put_failure; if (nla_put_in_addr(msg, TCP_METRICS_ATTR_SADDR_IPV4, - tm->tcpm_saddr.addr.a4) < 0) + inetpeer_get_addr_v4(&tm->tcpm_saddr)) < 0) goto nla_put_failure; break; case AF_INET6: if (nla_put_in6_addr(msg, TCP_METRICS_ATTR_ADDR_IPV6, - &tm->tcpm_daddr.addr.in6) < 0) + inetpeer_get_addr_v6(&tm->tcpm_daddr)) < 0) goto nla_put_failure; if (nla_put_in6_addr(msg, TCP_METRICS_ATTR_SADDR_IPV6, - &tm->tcpm_saddr.addr.in6) < 0) + inetpeer_get_addr_v6(&tm->tcpm_saddr)) < 0) goto nla_put_failure; break; default: @@ -956,20 +940,21 @@ static int __parse_nl_addr(struct genl_info *info, struct inetpeer_addr *addr, a = info->attrs[v4]; if (a) { - addr->family = AF_INET; - addr->addr.a4 = nla_get_in_addr(a); + inetpeer_set_addr_v4(addr, nla_get_in_addr(a)); if (hash) - *hash = (__force unsigned int) addr->addr.a4; + *hash = ipv4_addr_hash(inetpeer_get_addr_v4(addr)); return 0; } a = info->attrs[v6]; if (a) { + struct in6_addr in6; + if (nla_len(a) != sizeof(struct in6_addr)) return -EINVAL; - addr->family = AF_INET6; - addr->addr.in6 = nla_get_in6_addr(a); + in6 = nla_get_in6_addr(a); + inetpeer_set_addr_v6(addr, &in6); if (hash) - *hash = ipv6_addr_hash(&addr->addr.in6); + *hash = ipv6_addr_hash(inetpeer_get_addr_v6(addr)); return 0; } return optional ? 1 : -EAFNOSUPPORT; diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index 4bc00cb79e60..6d8795b066ac 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -147,8 +147,7 @@ tcp_timewait_state_process(struct inet_timewait_sock *tw, struct sk_buff *skb, if (!th->fin || TCP_SKB_CB(skb)->end_seq != tcptw->tw_rcv_nxt + 1) { kill_with_rst: - inet_twsk_deschedule(tw); - inet_twsk_put(tw); + inet_twsk_deschedule_put(tw); return TCP_TW_RST; } @@ -198,8 +197,7 @@ kill_with_rst: */ if (sysctl_tcp_rfc1337 == 0) { kill: - inet_twsk_deschedule(tw); - inet_twsk_put(tw); + inet_twsk_deschedule_put(tw); return TCP_TW_SUCCESS; } } diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index b1c218df2c85..f9a8a12b62ee 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -137,12 +137,12 @@ static __u16 tcp_advertise_mss(struct sock *sk) } /* RFC2861. Reset CWND after idle period longer RTO to "restart window". - * This is the first part of cwnd validation mechanism. */ -static void tcp_cwnd_restart(struct sock *sk, const struct dst_entry *dst) + * This is the first part of cwnd validation mechanism. + */ +void tcp_cwnd_restart(struct sock *sk, s32 delta) { struct tcp_sock *tp = tcp_sk(sk); - s32 delta = tcp_time_stamp - tp->lsndtime; - u32 restart_cwnd = tcp_init_cwnd(tp, dst); + u32 restart_cwnd = tcp_init_cwnd(tp, __sk_dst_get(sk)); u32 cwnd = tp->snd_cwnd; tcp_ca_event(sk, CA_EVENT_CWND_RESTART); @@ -163,20 +163,17 @@ static void tcp_event_data_sent(struct tcp_sock *tp, { struct inet_connection_sock *icsk = inet_csk(sk); const u32 now = tcp_time_stamp; - const struct dst_entry *dst = __sk_dst_get(sk); - if (sysctl_tcp_slow_start_after_idle && - (!tp->packets_out && (s32)(now - tp->lsndtime) > icsk->icsk_rto)) - tcp_cwnd_restart(sk, __sk_dst_get(sk)); + if (tcp_packets_in_flight(tp) == 0) + tcp_ca_event(sk, CA_EVENT_TX_START); tp->lsndtime = now; /* If it is a reply for ato after last received * packet, enter pingpong mode. */ - if ((u32)(now - icsk->icsk_ack.lrcvtime) < icsk->icsk_ack.ato && - (!dst || !dst_metric(dst, RTAX_QUICKACK))) - icsk->icsk_ack.pingpong = 1; + if ((u32)(now - icsk->icsk_ack.lrcvtime) < icsk->icsk_ack.ato) + icsk->icsk_ack.pingpong = 1; } /* Account for an ACK we sent. */ @@ -946,9 +943,6 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it, &md5); tcp_header_size = tcp_options_size + sizeof(struct tcphdr); - if (tcp_packets_in_flight(tp) == 0) - tcp_ca_event(sk, CA_EVENT_TX_START); - /* if no packet is in qdisc/device queue, then allow XPS to select * another queue. We can be called from tcp_tsq_handler() * which holds one reference to sk_wmem_alloc. @@ -1776,7 +1770,7 @@ static bool tcp_tso_should_defer(struct sock *sk, struct sk_buff *skb, if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN) goto send_now; - if (!((1 << icsk->icsk_ca_state) & (TCPF_CA_Open | TCPF_CA_CWR))) + if (icsk->icsk_ca_state >= TCP_CA_Recovery) goto send_now; /* Avoid bursty behavior by allowing defer @@ -2151,7 +2145,7 @@ repair: tcp_cwnd_validate(sk, is_cwnd_limited); return false; } - return (push_one == 2) || (!tp->packets_out && tcp_send_head(sk)); + return !tp->packets_out && tcp_send_head(sk); } bool tcp_schedule_loss_probe(struct sock *sk) @@ -2228,7 +2222,7 @@ static bool skb_still_in_host_queue(const struct sock *sk, return false; } -/* When probe timeout (PTO) fires, send a new segment if one exists, else +/* When probe timeout (PTO) fires, try send a new segment if possible, else * retransmit the last segment. */ void tcp_send_loss_probe(struct sock *sk) @@ -2237,11 +2231,19 @@ void tcp_send_loss_probe(struct sock *sk) struct sk_buff *skb; int pcount; int mss = tcp_current_mss(sk); - int err = -1; - if (tcp_send_head(sk)) { - err = tcp_write_xmit(sk, mss, TCP_NAGLE_OFF, 2, GFP_ATOMIC); - goto rearm_timer; + skb = tcp_send_head(sk); + if (skb) { + if (tcp_snd_wnd_test(tp, skb, mss)) { + pcount = tp->packets_out; + tcp_write_xmit(sk, mss, TCP_NAGLE_OFF, 2, GFP_ATOMIC); + if (tp->packets_out > pcount) + goto probe_sent; + goto rearm_timer; + } + skb = tcp_write_queue_prev(sk, skb); + } else { + skb = tcp_write_queue_tail(sk); } /* At most one outstanding TLP retransmission. */ @@ -2249,7 +2251,6 @@ void tcp_send_loss_probe(struct sock *sk) goto rearm_timer; /* Retransmit last segment. */ - skb = tcp_write_queue_tail(sk); if (WARN_ON(!skb)) goto rearm_timer; @@ -2264,26 +2265,24 @@ void tcp_send_loss_probe(struct sock *sk) if (unlikely(tcp_fragment(sk, skb, (pcount - 1) * mss, mss, GFP_ATOMIC))) goto rearm_timer; - skb = tcp_write_queue_tail(sk); + skb = tcp_write_queue_next(sk, skb); } if (WARN_ON(!skb || !tcp_skb_pcount(skb))) goto rearm_timer; - err = __tcp_retransmit_skb(sk, skb); + if (__tcp_retransmit_skb(sk, skb)) + goto rearm_timer; /* Record snd_nxt for loss detection. */ - if (likely(!err)) - tp->tlp_high_seq = tp->snd_nxt; + tp->tlp_high_seq = tp->snd_nxt; +probe_sent: + NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPLOSSPROBES); + /* Reset s.t. tcp_rearm_rto will restart timer from now */ + inet_csk(sk)->icsk_pending = 0; rearm_timer: - inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS, - inet_csk(sk)->icsk_rto, - TCP_RTO_MAX); - - if (likely(!err)) - NET_INC_STATS_BH(sock_net(sk), - LINUX_MIB_TCPLOSSPROBES); + tcp_rearm_rto(sk); } /* Push out any pending frames which were held back due to diff --git a/net/ipv4/tcp_scalable.c b/net/ipv4/tcp_scalable.c index 333bcb2415ff..bf5ea9e9bbc1 100644 --- a/net/ipv4/tcp_scalable.c +++ b/net/ipv4/tcp_scalable.c @@ -22,7 +22,7 @@ static void tcp_scalable_cong_avoid(struct sock *sk, u32 ack, u32 acked) if (!tcp_is_cwnd_limited(sk)) return; - if (tp->snd_cwnd <= tp->snd_ssthresh) + if (tcp_in_slow_start(tp)) tcp_slow_start(tp, acked); else tcp_cong_avoid_ai(tp, min(tp->snd_cwnd, TCP_SCALABLE_AI_CNT), diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c index 5b752f58a900..7149ebc820c7 100644 --- a/net/ipv4/tcp_timer.c +++ b/net/ipv4/tcp_timer.c @@ -649,4 +649,3 @@ void tcp_init_xmit_timers(struct sock *sk) inet_csk_init_xmit_timers(sk, &tcp_write_timer, &tcp_delack_timer, &tcp_keepalive_timer); } -EXPORT_SYMBOL(tcp_init_xmit_timers); diff --git a/net/ipv4/tcp_vegas.c b/net/ipv4/tcp_vegas.c index a6cea1d5e20d..13951c4087d4 100644 --- a/net/ipv4/tcp_vegas.c +++ b/net/ipv4/tcp_vegas.c @@ -225,7 +225,7 @@ static void tcp_vegas_cong_avoid(struct sock *sk, u32 ack, u32 acked) */ diff = tp->snd_cwnd * (rtt-vegas->baseRTT) / vegas->baseRTT; - if (diff > gamma && tp->snd_cwnd <= tp->snd_ssthresh) { + if (diff > gamma && tcp_in_slow_start(tp)) { /* Going too fast. Time to slow down * and switch to congestion avoidance. */ @@ -240,7 +240,7 @@ static void tcp_vegas_cong_avoid(struct sock *sk, u32 ack, u32 acked) tp->snd_cwnd = min(tp->snd_cwnd, (u32)target_cwnd+1); tp->snd_ssthresh = tcp_vegas_ssthresh(tp); - } else if (tp->snd_cwnd <= tp->snd_ssthresh) { + } else if (tcp_in_slow_start(tp)) { /* Slow start. */ tcp_slow_start(tp, acked); } else { @@ -281,7 +281,7 @@ static void tcp_vegas_cong_avoid(struct sock *sk, u32 ack, u32 acked) vegas->minRTT = 0x7fffffff; } /* Use normal slow start */ - else if (tp->snd_cwnd <= tp->snd_ssthresh) + else if (tcp_in_slow_start(tp)) tcp_slow_start(tp, acked); } diff --git a/net/ipv4/tcp_veno.c b/net/ipv4/tcp_veno.c index 112151eeee45..0d094b995cd9 100644 --- a/net/ipv4/tcp_veno.c +++ b/net/ipv4/tcp_veno.c @@ -150,7 +150,7 @@ static void tcp_veno_cong_avoid(struct sock *sk, u32 ack, u32 acked) veno->diff = (tp->snd_cwnd << V_PARAM_SHIFT) - target_cwnd; - if (tp->snd_cwnd <= tp->snd_ssthresh) { + if (tcp_in_slow_start(tp)) { /* Slow start. */ tcp_slow_start(tp, acked); } else { diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 1b8c5ba7d5f7..c0a15e7f359f 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -1013,11 +1013,31 @@ int udp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) if (!rt) { struct net *net = sock_net(sk); + __u8 flow_flags = inet_sk_flowi_flags(sk); fl4 = &fl4_stack; + + /* unconnected socket. If output device is enslaved to a VRF + * device lookup source address from VRF table. This mimics + * behavior of ip_route_connect{_init}. + */ + if (netif_index_is_vrf(net, ipc.oif)) { + flowi4_init_output(fl4, ipc.oif, sk->sk_mark, tos, + RT_SCOPE_UNIVERSE, sk->sk_protocol, + (flow_flags | FLOWI_FLAG_VRFSRC), + faddr, saddr, dport, + inet->inet_sport); + + rt = ip_route_output_flow(net, fl4, sk); + if (!IS_ERR(rt)) { + saddr = fl4->saddr; + ip_rt_put(rt); + } + } + flowi4_init_output(fl4, ipc.oif, sk->sk_mark, tos, RT_SCOPE_UNIVERSE, sk->sk_protocol, - inet_sk_flowi_flags(sk), + flow_flags, faddr, saddr, dport, inet->inet_sport); security_sk_classify_flow(sk, flowi4_to_flowi(fl4)); diff --git a/net/ipv4/udp_tunnel.c b/net/ipv4/udp_tunnel.c index 933ea903f7b8..aba428626b52 100644 --- a/net/ipv4/udp_tunnel.c +++ b/net/ipv4/udp_tunnel.c @@ -4,9 +4,10 @@ #include <linux/udp.h> #include <linux/types.h> #include <linux/kernel.h> +#include <net/dst_metadata.h> +#include <net/net_namespace.h> #include <net/udp.h> #include <net/udp_tunnel.h> -#include <net/net_namespace.h> int udp_sock_create4(struct net *net, struct udp_port_cfg *cfg, struct socket **sockp) @@ -103,4 +104,26 @@ void udp_tunnel_sock_release(struct socket *sock) } EXPORT_SYMBOL_GPL(udp_tunnel_sock_release); +struct metadata_dst *udp_tun_rx_dst(struct sk_buff *skb, unsigned short family, + __be16 flags, __be64 tunnel_id, int md_size) +{ + struct metadata_dst *tun_dst; + struct ip_tunnel_info *info; + + if (family == AF_INET) + tun_dst = ip_tun_rx_dst(skb, flags, tunnel_id, md_size); + else + tun_dst = ipv6_tun_rx_dst(skb, flags, tunnel_id, md_size); + if (!tun_dst) + return NULL; + + info = &tun_dst->u.tun_info; + info->key.tp_src = udp_hdr(skb)->source; + info->key.tp_dst = udp_hdr(skb)->dest; + if (udp_hdr(skb)->check) + info->key.tun_flags |= TUNNEL_CSUM; + return tun_dst; +} +EXPORT_SYMBOL_GPL(udp_tun_rx_dst); + MODULE_LICENSE("GPL"); diff --git a/net/ipv4/xfrm4_policy.c b/net/ipv4/xfrm4_policy.c index bff69746e05f..bb919b28619f 100644 --- a/net/ipv4/xfrm4_policy.c +++ b/net/ipv4/xfrm4_policy.c @@ -15,11 +15,12 @@ #include <net/dst.h> #include <net/xfrm.h> #include <net/ip.h> +#include <net/vrf.h> static struct xfrm_policy_afinfo xfrm4_policy_afinfo; static struct dst_entry *__xfrm4_dst_lookup(struct net *net, struct flowi4 *fl4, - int tos, + int tos, int oif, const xfrm_address_t *saddr, const xfrm_address_t *daddr) { @@ -28,6 +29,7 @@ static struct dst_entry *__xfrm4_dst_lookup(struct net *net, struct flowi4 *fl4, memset(fl4, 0, sizeof(*fl4)); fl4->daddr = daddr->a4; fl4->flowi4_tos = tos; + fl4->flowi4_oif = oif; if (saddr) fl4->saddr = saddr->a4; @@ -38,22 +40,22 @@ static struct dst_entry *__xfrm4_dst_lookup(struct net *net, struct flowi4 *fl4, return ERR_CAST(rt); } -static struct dst_entry *xfrm4_dst_lookup(struct net *net, int tos, +static struct dst_entry *xfrm4_dst_lookup(struct net *net, int tos, int oif, const xfrm_address_t *saddr, const xfrm_address_t *daddr) { struct flowi4 fl4; - return __xfrm4_dst_lookup(net, &fl4, tos, saddr, daddr); + return __xfrm4_dst_lookup(net, &fl4, tos, oif, saddr, daddr); } -static int xfrm4_get_saddr(struct net *net, +static int xfrm4_get_saddr(struct net *net, int oif, xfrm_address_t *saddr, xfrm_address_t *daddr) { struct dst_entry *dst; struct flowi4 fl4; - dst = __xfrm4_dst_lookup(net, &fl4, 0, NULL, daddr); + dst = __xfrm4_dst_lookup(net, &fl4, 0, oif, NULL, daddr); if (IS_ERR(dst)) return -EHOSTUNREACH; @@ -106,8 +108,10 @@ _decode_session4(struct sk_buff *skb, struct flowi *fl, int reverse) struct flowi4 *fl4 = &fl->u.ip4; int oif = 0; - if (skb_dst(skb)) - oif = skb_dst(skb)->dev->ifindex; + if (skb_dst(skb)) { + oif = vrf_master_ifindex(skb_dst(skb)->dev) ? + : skb_dst(skb)->dev->ifindex; + } memset(fl4, 0, sizeof(struct flowi4)); fl4->flowi4_mark = skb->mark; diff --git a/net/ipv6/Kconfig b/net/ipv6/Kconfig index 438a73aa777c..983bb999738c 100644 --- a/net/ipv6/Kconfig +++ b/net/ipv6/Kconfig @@ -5,16 +5,15 @@ # IPv6 as module will cause a CRASH if you try to unload it menuconfig IPV6 tristate "The IPv6 protocol" - default m + default y ---help--- - This is complemental support for the IP version 6. - You will still be able to do traditional IPv4 networking as well. + Support for IP version 6 (IPv6). For general information about IPv6, see <https://en.wikipedia.org/wiki/IPv6>. - For Linux IPv6 development information, see <http://www.linux-ipv6.org>. - For specific information about IPv6 under Linux, read the HOWTO at - <http://www.bieringer.de/linux/IPv6/>. + For specific information about IPv6 under Linux, see + Documentation/networking/ipv6.txt and read the HOWTO at + <http://www.tldp.org/HOWTO/Linux+IPv6-HOWTO/> To compile this protocol support as a module, choose M here: the module will be called ipv6. @@ -93,6 +92,25 @@ config IPV6_MIP6 If unsure, say N. +config IPV6_ILA + tristate "IPv6: Identifier Locator Addressing (ILA)" + select LWTUNNEL + ---help--- + Support for IPv6 Identifier Locator Addressing (ILA). + + ILA is a mechanism to do network virtualization without + encapsulation. The basic concept of ILA is that we split an + IPv6 address into a 64 bit locator and 64 bit identifier. The + identifier is the identity of an entity in communication + ("who") and the locator expresses the location of the + entity ("where"). + + ILA can be configured using the "encap ila" option with + "ip -6 route" command. ILA is described in + https://tools.ietf.org/html/draft-herbert-nvo3-ila-00. + + If unsure, say N. + config INET6_XFRM_TUNNEL tristate select INET6_TUNNEL diff --git a/net/ipv6/Makefile b/net/ipv6/Makefile index 0f3f1999719a..2c900c7b7eb1 100644 --- a/net/ipv6/Makefile +++ b/net/ipv6/Makefile @@ -34,6 +34,7 @@ obj-$(CONFIG_INET6_XFRM_MODE_TUNNEL) += xfrm6_mode_tunnel.o obj-$(CONFIG_INET6_XFRM_MODE_ROUTEOPTIMIZATION) += xfrm6_mode_ro.o obj-$(CONFIG_INET6_XFRM_MODE_BEET) += xfrm6_mode_beet.o obj-$(CONFIG_IPV6_MIP6) += mip6.o +obj-$(CONFIG_IPV6_ILA) += ila.o obj-$(CONFIG_NETFILTER) += netfilter/ obj-$(CONFIG_IPV6_VTI) += ip6_vti.o diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 21c2c818df3b..030fefdc9aed 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -195,6 +195,7 @@ static struct ipv6_devconf ipv6_devconf __read_mostly = { .max_addresses = IPV6_MAX_ADDRESSES, .accept_ra_defrtr = 1, .accept_ra_from_local = 0, + .accept_ra_min_hop_limit= 1, .accept_ra_pinfo = 1, #ifdef CONFIG_IPV6_ROUTER_PREF .accept_ra_rtr_pref = 1, @@ -211,7 +212,9 @@ static struct ipv6_devconf ipv6_devconf __read_mostly = { .accept_ra_mtu = 1, .stable_secret = { .initialized = false, - } + }, + .use_oif_addrs_only = 0, + .ignore_routes_with_linkdown = 0, }; static struct ipv6_devconf ipv6_devconf_dflt __read_mostly = { @@ -236,6 +239,7 @@ static struct ipv6_devconf ipv6_devconf_dflt __read_mostly = { .max_addresses = IPV6_MAX_ADDRESSES, .accept_ra_defrtr = 1, .accept_ra_from_local = 0, + .accept_ra_min_hop_limit= 1, .accept_ra_pinfo = 1, #ifdef CONFIG_IPV6_ROUTER_PREF .accept_ra_rtr_pref = 1, @@ -253,6 +257,8 @@ static struct ipv6_devconf ipv6_devconf_dflt __read_mostly = { .stable_secret = { .initialized = false, }, + .use_oif_addrs_only = 0, + .ignore_routes_with_linkdown = 0, }; /* Check if a valid qdisc is available */ @@ -468,6 +474,9 @@ static int inet6_netconf_msgsize_devconf(int type) if (type == -1 || type == NETCONFA_PROXY_NEIGH) size += nla_total_size(4); + if (type == -1 || type == NETCONFA_IGNORE_ROUTES_WITH_LINKDOWN) + size += nla_total_size(4); + return size; } @@ -504,6 +513,11 @@ static int inet6_netconf_fill_devconf(struct sk_buff *skb, int ifindex, nla_put_s32(skb, NETCONFA_PROXY_NEIGH, devconf->proxy_ndp) < 0) goto nla_put_failure; + if ((type == -1 || type == NETCONFA_IGNORE_ROUTES_WITH_LINKDOWN) && + nla_put_s32(skb, NETCONFA_IGNORE_ROUTES_WITH_LINKDOWN, + devconf->ignore_routes_with_linkdown) < 0) + goto nla_put_failure; + nlmsg_end(skb, nlh); return 0; @@ -540,6 +554,7 @@ static const struct nla_policy devconf_ipv6_policy[NETCONFA_MAX+1] = { [NETCONFA_IFINDEX] = { .len = sizeof(int) }, [NETCONFA_FORWARDING] = { .len = sizeof(int) }, [NETCONFA_PROXY_NEIGH] = { .len = sizeof(int) }, + [NETCONFA_IGNORE_ROUTES_WITH_LINKDOWN] = { .len = sizeof(int) }, }; static int inet6_netconf_get_devconf(struct sk_buff *in_skb, @@ -762,6 +777,63 @@ static int addrconf_fixup_forwarding(struct ctl_table *table, int *p, int newf) rt6_purge_dflt_routers(net); return 1; } + +static void addrconf_linkdown_change(struct net *net, __s32 newf) +{ + struct net_device *dev; + struct inet6_dev *idev; + + for_each_netdev(net, dev) { + idev = __in6_dev_get(dev); + if (idev) { + int changed = (!idev->cnf.ignore_routes_with_linkdown) ^ (!newf); + + idev->cnf.ignore_routes_with_linkdown = newf; + if (changed) + inet6_netconf_notify_devconf(dev_net(dev), + NETCONFA_IGNORE_ROUTES_WITH_LINKDOWN, + dev->ifindex, + &idev->cnf); + } + } +} + +static int addrconf_fixup_linkdown(struct ctl_table *table, int *p, int newf) +{ + struct net *net; + int old; + + if (!rtnl_trylock()) + return restart_syscall(); + + net = (struct net *)table->extra2; + old = *p; + *p = newf; + + if (p == &net->ipv6.devconf_dflt->ignore_routes_with_linkdown) { + if ((!newf) ^ (!old)) + inet6_netconf_notify_devconf(net, + NETCONFA_IGNORE_ROUTES_WITH_LINKDOWN, + NETCONFA_IFINDEX_DEFAULT, + net->ipv6.devconf_dflt); + rtnl_unlock(); + return 0; + } + + if (p == &net->ipv6.devconf_all->ignore_routes_with_linkdown) { + net->ipv6.devconf_dflt->ignore_routes_with_linkdown = newf; + addrconf_linkdown_change(net, newf); + if ((!newf) ^ (!old)) + inet6_netconf_notify_devconf(net, + NETCONFA_IGNORE_ROUTES_WITH_LINKDOWN, + NETCONFA_IFINDEX_ALL, + net->ipv6.devconf_all); + } + rtnl_unlock(); + + return 1; +} + #endif /* Nobody refers to this ifaddr, destroy it */ @@ -1358,15 +1430,96 @@ out: return ret; } +static int __ipv6_dev_get_saddr(struct net *net, + struct ipv6_saddr_dst *dst, + struct inet6_dev *idev, + struct ipv6_saddr_score *scores, + int hiscore_idx) +{ + struct ipv6_saddr_score *score = &scores[1 - hiscore_idx], *hiscore = &scores[hiscore_idx]; + + read_lock_bh(&idev->lock); + list_for_each_entry(score->ifa, &idev->addr_list, if_list) { + int i; + + /* + * - Tentative Address (RFC2462 section 5.4) + * - A tentative address is not considered + * "assigned to an interface" in the traditional + * sense, unless it is also flagged as optimistic. + * - Candidate Source Address (section 4) + * - In any case, anycast addresses, multicast + * addresses, and the unspecified address MUST + * NOT be included in a candidate set. + */ + if ((score->ifa->flags & IFA_F_TENTATIVE) && + (!(score->ifa->flags & IFA_F_OPTIMISTIC))) + continue; + + score->addr_type = __ipv6_addr_type(&score->ifa->addr); + + if (unlikely(score->addr_type == IPV6_ADDR_ANY || + score->addr_type & IPV6_ADDR_MULTICAST)) { + net_dbg_ratelimited("ADDRCONF: unspecified / multicast address assigned as unicast address on %s", + idev->dev->name); + continue; + } + + score->rule = -1; + bitmap_zero(score->scorebits, IPV6_SADDR_RULE_MAX); + + for (i = 0; i < IPV6_SADDR_RULE_MAX; i++) { + int minihiscore, miniscore; + + minihiscore = ipv6_get_saddr_eval(net, hiscore, dst, i); + miniscore = ipv6_get_saddr_eval(net, score, dst, i); + + if (minihiscore > miniscore) { + if (i == IPV6_SADDR_RULE_SCOPE && + score->scopedist > 0) { + /* + * special case: + * each remaining entry + * has too small (not enough) + * scope, because ifa entries + * are sorted by their scope + * values. + */ + goto out; + } + break; + } else if (minihiscore < miniscore) { + if (hiscore->ifa) + in6_ifa_put(hiscore->ifa); + + in6_ifa_hold(score->ifa); + + swap(hiscore, score); + hiscore_idx = 1 - hiscore_idx; + + /* restore our iterator */ + score->ifa = hiscore->ifa; + + break; + } + } + } +out: + read_unlock_bh(&idev->lock); + return hiscore_idx; +} + int ipv6_dev_get_saddr(struct net *net, const struct net_device *dst_dev, const struct in6_addr *daddr, unsigned int prefs, struct in6_addr *saddr) { - struct ipv6_saddr_score scores[2], - *score = &scores[0], *hiscore = &scores[1]; + struct ipv6_saddr_score scores[2], *hiscore; struct ipv6_saddr_dst dst; + struct inet6_dev *idev; struct net_device *dev; int dst_type; + bool use_oif_addr = false; + int hiscore_idx = 0; dst_type = __ipv6_addr_type(daddr); dst.addr = daddr; @@ -1375,105 +1528,50 @@ int ipv6_dev_get_saddr(struct net *net, const struct net_device *dst_dev, dst.label = ipv6_addr_label(net, daddr, dst_type, dst.ifindex); dst.prefs = prefs; - hiscore->rule = -1; - hiscore->ifa = NULL; + scores[hiscore_idx].rule = -1; + scores[hiscore_idx].ifa = NULL; rcu_read_lock(); - for_each_netdev_rcu(net, dev) { - struct inet6_dev *idev; - - /* Candidate Source Address (section 4) - * - multicast and link-local destination address, - * the set of candidate source address MUST only - * include addresses assigned to interfaces - * belonging to the same link as the outgoing - * interface. - * (- For site-local destination addresses, the - * set of candidate source addresses MUST only - * include addresses assigned to interfaces - * belonging to the same site as the outgoing - * interface.) - */ - if (((dst_type & IPV6_ADDR_MULTICAST) || - dst.scope <= IPV6_ADDR_SCOPE_LINKLOCAL) && - dst.ifindex && dev->ifindex != dst.ifindex) - continue; - - idev = __in6_dev_get(dev); - if (!idev) - continue; - - read_lock_bh(&idev->lock); - list_for_each_entry(score->ifa, &idev->addr_list, if_list) { - int i; - - /* - * - Tentative Address (RFC2462 section 5.4) - * - A tentative address is not considered - * "assigned to an interface" in the traditional - * sense, unless it is also flagged as optimistic. - * - Candidate Source Address (section 4) - * - In any case, anycast addresses, multicast - * addresses, and the unspecified address MUST - * NOT be included in a candidate set. - */ - if ((score->ifa->flags & IFA_F_TENTATIVE) && - (!(score->ifa->flags & IFA_F_OPTIMISTIC))) - continue; - - score->addr_type = __ipv6_addr_type(&score->ifa->addr); + /* Candidate Source Address (section 4) + * - multicast and link-local destination address, + * the set of candidate source address MUST only + * include addresses assigned to interfaces + * belonging to the same link as the outgoing + * interface. + * (- For site-local destination addresses, the + * set of candidate source addresses MUST only + * include addresses assigned to interfaces + * belonging to the same site as the outgoing + * interface.) + * - "It is RECOMMENDED that the candidate source addresses + * be the set of unicast addresses assigned to the + * interface that will be used to send to the destination + * (the 'outgoing' interface)." (RFC 6724) + */ + if (dst_dev) { + idev = __in6_dev_get(dst_dev); + if ((dst_type & IPV6_ADDR_MULTICAST) || + dst.scope <= IPV6_ADDR_SCOPE_LINKLOCAL || + (idev && idev->cnf.use_oif_addrs_only)) { + use_oif_addr = true; + } + } - if (unlikely(score->addr_type == IPV6_ADDR_ANY || - score->addr_type & IPV6_ADDR_MULTICAST)) { - net_dbg_ratelimited("ADDRCONF: unspecified / multicast address assigned as unicast address on %s", - dev->name); + if (use_oif_addr) { + if (idev) + hiscore_idx = __ipv6_dev_get_saddr(net, &dst, idev, scores, hiscore_idx); + } else { + for_each_netdev_rcu(net, dev) { + idev = __in6_dev_get(dev); + if (!idev) continue; - } - - score->rule = -1; - bitmap_zero(score->scorebits, IPV6_SADDR_RULE_MAX); - - for (i = 0; i < IPV6_SADDR_RULE_MAX; i++) { - int minihiscore, miniscore; - - minihiscore = ipv6_get_saddr_eval(net, hiscore, &dst, i); - miniscore = ipv6_get_saddr_eval(net, score, &dst, i); - - if (minihiscore > miniscore) { - if (i == IPV6_SADDR_RULE_SCOPE && - score->scopedist > 0) { - /* - * special case: - * each remaining entry - * has too small (not enough) - * scope, because ifa entries - * are sorted by their scope - * values. - */ - goto try_nextdev; - } - break; - } else if (minihiscore < miniscore) { - if (hiscore->ifa) - in6_ifa_put(hiscore->ifa); - - in6_ifa_hold(score->ifa); - - swap(hiscore, score); - - /* restore our iterator */ - score->ifa = hiscore->ifa; - - break; - } - } + hiscore_idx = __ipv6_dev_get_saddr(net, &dst, idev, scores, hiscore_idx); } -try_nextdev: - read_unlock_bh(&idev->lock); } rcu_read_unlock(); + hiscore = &scores[hiscore_idx]; if (!hiscore->ifa) return -EADDRNOTAVAIL; @@ -1845,37 +1943,6 @@ static void addrconf_leave_anycast(struct inet6_ifaddr *ifp) __ipv6_dev_ac_dec(ifp->idev, &addr); } -static int addrconf_ifid_eui48(u8 *eui, struct net_device *dev) -{ - if (dev->addr_len != ETH_ALEN) - return -1; - memcpy(eui, dev->dev_addr, 3); - memcpy(eui + 5, dev->dev_addr + 3, 3); - - /* - * The zSeries OSA network cards can be shared among various - * OS instances, but the OSA cards have only one MAC address. - * This leads to duplicate address conflicts in conjunction - * with IPv6 if more than one instance uses the same card. - * - * The driver for these cards can deliver a unique 16-bit - * identifier for each instance sharing the same card. It is - * placed instead of 0xFFFE in the interface identifier. The - * "u" bit of the interface identifier is not inverted in this - * case. Hence the resulting interface identifier has local - * scope according to RFC2373. - */ - if (dev->dev_id) { - eui[3] = (dev->dev_id >> 8) & 0xFF; - eui[4] = dev->dev_id & 0xFF; - } else { - eui[3] = 0xFF; - eui[4] = 0xFE; - eui[0] ^= 2; - } - return 0; -} - static int addrconf_ifid_eui64(u8 *eui, struct net_device *dev) { if (dev->addr_len != IEEE802154_ADDR_LEN) @@ -3558,7 +3625,7 @@ static void addrconf_dad_work(struct work_struct *w) /* send a neighbour solicitation for our addr */ addrconf_addr_solict_mult(&ifp->addr, &mcaddr); - ndisc_send_ns(ifp->idev->dev, NULL, &ifp->addr, &mcaddr, &in6addr_any); + ndisc_send_ns(ifp->idev->dev, NULL, &ifp->addr, &mcaddr, &in6addr_any, NULL); out: in6_ifa_put(ifp); rtnl_unlock(); @@ -4560,6 +4627,7 @@ static inline void ipv6_store_devconf(struct ipv6_devconf *cnf, array[DEVCONF_MAX_DESYNC_FACTOR] = cnf->max_desync_factor; array[DEVCONF_MAX_ADDRESSES] = cnf->max_addresses; array[DEVCONF_ACCEPT_RA_DEFRTR] = cnf->accept_ra_defrtr; + array[DEVCONF_ACCEPT_RA_MIN_HOP_LIMIT] = cnf->accept_ra_min_hop_limit; array[DEVCONF_ACCEPT_RA_PINFO] = cnf->accept_ra_pinfo; #ifdef CONFIG_IPV6_ROUTER_PREF array[DEVCONF_ACCEPT_RA_RTR_PREF] = cnf->accept_ra_rtr_pref; @@ -4585,7 +4653,9 @@ static inline void ipv6_store_devconf(struct ipv6_devconf *cnf, array[DEVCONF_SUPPRESS_FRAG_NDISC] = cnf->suppress_frag_ndisc; array[DEVCONF_ACCEPT_RA_FROM_LOCAL] = cnf->accept_ra_from_local; array[DEVCONF_ACCEPT_RA_MTU] = cnf->accept_ra_mtu; + array[DEVCONF_IGNORE_ROUTES_WITH_LINKDOWN] = cnf->ignore_routes_with_linkdown; /* we omit DEVCONF_STABLE_SECRET for now */ + array[DEVCONF_USE_OIF_ADDRS_ONLY] = cnf->use_oif_addrs_only; } static inline size_t inet6_ifla6_size(void) @@ -4605,6 +4675,7 @@ static inline size_t inet6_if_nlmsg_size(void) + nla_total_size(MAX_ADDR_LEN) /* IFLA_ADDRESS */ + nla_total_size(4) /* IFLA_MTU */ + nla_total_size(4) /* IFLA_LINK */ + + nla_total_size(1) /* IFLA_OPERSTATE */ + nla_total_size(inet6_ifla6_size()); /* IFLA_PROTINFO */ } @@ -4624,18 +4695,24 @@ static inline void __snmp6_fill_statsdev(u64 *stats, atomic_long_t *mib, } static inline void __snmp6_fill_stats64(u64 *stats, void __percpu *mib, - int items, int bytes, size_t syncpoff) + int bytes, size_t syncpoff) { - int i; - int pad = bytes - sizeof(u64) * items; + int i, c; + u64 buff[IPSTATS_MIB_MAX]; + int pad = bytes - sizeof(u64) * IPSTATS_MIB_MAX; + BUG_ON(pad < 0); - /* Use put_unaligned() because stats may not be aligned for u64. */ - put_unaligned(items, &stats[0]); - for (i = 1; i < items; i++) - put_unaligned(snmp_fold_field64(mib, i, syncpoff), &stats[i]); + memset(buff, 0, sizeof(buff)); + buff[0] = IPSTATS_MIB_MAX; - memset(&stats[items], 0, pad); + for_each_possible_cpu(c) { + for (i = 1; i < IPSTATS_MIB_MAX; i++) + buff[i] += snmp_get_cpu_field64(mib, c, i, syncpoff); + } + + memcpy(stats, buff, IPSTATS_MIB_MAX * sizeof(u64)); + memset(&stats[IPSTATS_MIB_MAX], 0, pad); } static void snmp6_fill_stats(u64 *stats, struct inet6_dev *idev, int attrtype, @@ -4643,8 +4720,8 @@ static void snmp6_fill_stats(u64 *stats, struct inet6_dev *idev, int attrtype, { switch (attrtype) { case IFLA_INET6_STATS: - __snmp6_fill_stats64(stats, idev->stats.ipv6, - IPSTATS_MIB_MAX, bytes, offsetof(struct ipstats_mib, syncp)); + __snmp6_fill_stats64(stats, idev->stats.ipv6, bytes, + offsetof(struct ipstats_mib, syncp)); break; case IFLA_INET6_ICMP6STATS: __snmp6_fill_statsdev(stats, idev->stats.icmpv6dev->mibs, ICMP6_MIB_MAX, bytes); @@ -4861,7 +4938,9 @@ static int inet6_fill_ifinfo(struct sk_buff *skb, struct inet6_dev *idev, nla_put(skb, IFLA_ADDRESS, dev->addr_len, dev->dev_addr)) || nla_put_u32(skb, IFLA_MTU, dev->mtu) || (dev->ifindex != dev_get_iflink(dev) && - nla_put_u32(skb, IFLA_LINK, dev_get_iflink(dev)))) + nla_put_u32(skb, IFLA_LINK, dev_get_iflink(dev))) || + nla_put_u8(skb, IFLA_OPERSTATE, + netif_running(dev) ? dev->operstate : IF_OPER_DOWN)) goto nla_put_failure; protoinfo = nla_nest_start(skb, IFLA_PROTINFO); if (!protoinfo) @@ -5306,6 +5385,34 @@ out: return err; } +static +int addrconf_sysctl_ignore_routes_with_linkdown(struct ctl_table *ctl, + int write, + void __user *buffer, + size_t *lenp, + loff_t *ppos) +{ + int *valp = ctl->data; + int val = *valp; + loff_t pos = *ppos; + struct ctl_table lctl; + int ret; + + /* ctl->data points to idev->cnf.ignore_routes_when_linkdown + * we should not modify it until we get the rtnl lock. + */ + lctl = *ctl; + lctl.data = &val; + + ret = proc_dointvec(&lctl, write, buffer, lenp, ppos); + + if (write) + ret = addrconf_fixup_linkdown(ctl, valp, val); + if (ret) + *ppos = pos; + return ret; +} + static struct addrconf_sysctl_table { struct ctl_table_header *sysctl_header; @@ -5456,6 +5563,13 @@ static struct addrconf_sysctl_table .proc_handler = proc_dointvec, }, { + .procname = "accept_ra_min_hop_limit", + .data = &ipv6_devconf.accept_ra_min_hop_limit, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec, + }, + { .procname = "accept_ra_pinfo", .data = &ipv6_devconf.accept_ra_pinfo, .maxlen = sizeof(int), @@ -5585,6 +5699,20 @@ static struct addrconf_sysctl_table .proc_handler = addrconf_sysctl_stable_secret, }, { + .procname = "use_oif_addrs_only", + .data = &ipv6_devconf.use_oif_addrs_only, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec, + }, + { + .procname = "ignore_routes_with_linkdown", + .data = &ipv6_devconf.ignore_routes_with_linkdown, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = addrconf_sysctl_ignore_routes_with_linkdown, + }, + { /* sentinel */ } }, diff --git a/net/ipv6/addrconf_core.c b/net/ipv6/addrconf_core.c index ca09bf49ac68..bfa941fc1165 100644 --- a/net/ipv6/addrconf_core.c +++ b/net/ipv6/addrconf_core.c @@ -107,7 +107,16 @@ int inet6addr_notifier_call_chain(unsigned long val, void *v) } EXPORT_SYMBOL(inet6addr_notifier_call_chain); -const struct ipv6_stub *ipv6_stub __read_mostly; +static int eafnosupport_ipv6_dst_lookup(struct net *net, struct sock *u1, + struct dst_entry **u2, + struct flowi6 *u3) +{ + return -EAFNOSUPPORT; +} + +const struct ipv6_stub *ipv6_stub __read_mostly = &(struct ipv6_stub) { + .ipv6_dst_lookup = eafnosupport_ipv6_dst_lookup, +}; EXPORT_SYMBOL_GPL(ipv6_stub); /* IPv6 Wildcard Address and Loopback Address defined by RFC2553 */ diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c index 7de52b65173f..44bb66bde0e2 100644 --- a/net/ipv6/af_inet6.c +++ b/net/ipv6/af_inet6.c @@ -197,6 +197,7 @@ lookup_protocol: np->mcast_hops = IPV6_DEFAULT_MCASTHOPS; np->mc_loop = 1; np->pmtudisc = IPV6_PMTUDISC_WANT; + np->autoflowlabel = ip6_default_np_autolabel(sock_net(sk)); sk->sk_ipv6only = net->ipv6.sysctl.bindv6only; /* Init the ipv4 part of the socket since we can have sockets @@ -342,7 +343,8 @@ int inet6_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) */ v4addr = LOOPBACK4_IPV6; if (!(addr_type & IPV6_ADDR_MULTICAST)) { - if (!(inet->freebind || inet->transparent) && + if (!net->ipv6.sysctl.ip_nonlocal_bind && + !(inet->freebind || inet->transparent) && !ipv6_chk_addr(net, &addr->sin6_addr, dev, 0)) { err = -EADDRNOTAVAIL; @@ -679,8 +681,8 @@ bool ipv6_opt_accepted(const struct sock *sk, const struct sk_buff *skb, const struct ipv6_pinfo *np = inet6_sk(sk); if (np->rxopt.all) { - if ((opt->hop && (np->rxopt.bits.hopopts || - np->rxopt.bits.ohopopts)) || + if (((opt->flags & IP6SKB_HOPBYHOP) && + (np->rxopt.bits.hopopts || np->rxopt.bits.ohopopts)) || (ip6_flowinfo((struct ipv6hdr *) skb_network_header(skb)) && np->rxopt.bits.rxflow) || (opt->srcrt && (np->rxopt.bits.srcrt || @@ -766,10 +768,10 @@ static int __net_init inet6_net_init(struct net *net) net->ipv6.sysctl.bindv6only = 0; net->ipv6.sysctl.icmpv6_time = 1*HZ; net->ipv6.sysctl.flowlabel_consistency = 1; - net->ipv6.sysctl.auto_flowlabels = 0; + net->ipv6.sysctl.auto_flowlabels = IP6_DEFAULT_AUTO_FLOW_LABELS; net->ipv6.sysctl.idgen_retries = 3; net->ipv6.sysctl.idgen_delay = 1 * HZ; - net->ipv6.sysctl.flowlabel_state_ranges = 1; + net->ipv6.sysctl.flowlabel_state_ranges = 0; atomic_set(&net->ipv6.fib6_sernum, 1); err = ipv6_init_mibs(net); diff --git a/net/ipv6/ah6.c b/net/ipv6/ah6.c index ed7d4e3f9c10..0630a4d5daaa 100644 --- a/net/ipv6/ah6.c +++ b/net/ipv6/ah6.c @@ -577,8 +577,10 @@ static int ah6_input(struct xfrm_state *x, struct sk_buff *skb) work_iph = ah_alloc_tmp(ahash, nfrags + sglists, hdr_len + ahp->icv_trunc_len + seqhi_len); - if (!work_iph) + if (!work_iph) { + err = -ENOMEM; goto out; + } auth_data = ah_tmp_auth((u8 *)work_iph, hdr_len); seqhi = (__be32 *)(auth_data + ahp->icv_trunc_len); diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c index b10a88986a98..9aadd57808a5 100644 --- a/net/ipv6/datagram.c +++ b/net/ipv6/datagram.c @@ -199,7 +199,7 @@ ipv4_connected: NULL); sk->sk_state = TCP_ESTABLISHED; - ip6_set_txhash(sk); + sk_set_txhash(sk); out: fl6_sock_release(flowlabel); return err; @@ -568,8 +568,8 @@ void ip6_datagram_recv_specific_ctl(struct sock *sk, struct msghdr *msg, } /* HbH is allowed only once */ - if (np->rxopt.bits.hopopts && opt->hop) { - u8 *ptr = nh + opt->hop; + if (np->rxopt.bits.hopopts && (opt->flags & IP6SKB_HOPBYHOP)) { + u8 *ptr = nh + sizeof(struct ipv6hdr); put_cmsg(msg, SOL_IPV6, IPV6_HOPOPTS, (ptr[1]+1)<<3, ptr); } @@ -630,8 +630,8 @@ void ip6_datagram_recv_specific_ctl(struct sock *sk, struct msghdr *msg, int hlim = ipv6_hdr(skb)->hop_limit; put_cmsg(msg, SOL_IPV6, IPV6_2292HOPLIMIT, sizeof(hlim), &hlim); } - if (np->rxopt.bits.ohopopts && opt->hop) { - u8 *ptr = nh + opt->hop; + if (np->rxopt.bits.ohopopts && (opt->flags & IP6SKB_HOPBYHOP)) { + u8 *ptr = nh + sizeof(struct ipv6hdr); put_cmsg(msg, SOL_IPV6, IPV6_2292HOPOPTS, (ptr[1]+1)<<3, ptr); } if (np->rxopt.bits.odstopts && opt->dst0) { diff --git a/net/ipv6/exthdrs.c b/net/ipv6/exthdrs.c index a7bbbe45570b..ce203b0402be 100644 --- a/net/ipv6/exthdrs.c +++ b/net/ipv6/exthdrs.c @@ -632,7 +632,7 @@ int ipv6_parse_hopopts(struct sk_buff *skb) return -1; } - opt->hop = sizeof(struct ipv6hdr); + opt->flags |= IP6SKB_HOPBYHOP; if (ip6_parse_tlv(tlvprochopopt_lst, skb)) { skb->transport_header += (skb_transport_header(skb)[1] + 1) << 3; opt = IP6CB(skb); diff --git a/net/ipv6/exthdrs_offload.c b/net/ipv6/exthdrs_offload.c index 447a7fbd1bb6..f5e2ba1c18bf 100644 --- a/net/ipv6/exthdrs_offload.c +++ b/net/ipv6/exthdrs_offload.c @@ -36,6 +36,6 @@ out: return ret; out_rt: - inet_del_offload(&rthdr_offload, IPPROTO_ROUTING); + inet6_del_offload(&rthdr_offload, IPPROTO_ROUTING); goto out; } diff --git a/net/ipv6/fib6_rules.c b/net/ipv6/fib6_rules.c index 2367a16eae58..9f777ec59a59 100644 --- a/net/ipv6/fib6_rules.c +++ b/net/ipv6/fib6_rules.c @@ -258,11 +258,6 @@ nla_put_failure: return -ENOBUFS; } -static u32 fib6_rule_default_pref(struct fib_rules_ops *ops) -{ - return 0x3FFF; -} - static size_t fib6_rule_nlmsg_payload(struct fib_rule *rule) { return nla_total_size(16) /* dst */ @@ -279,7 +274,6 @@ static const struct fib_rules_ops __net_initconst fib6_rules_ops_template = { .configure = fib6_rule_configure, .compare = fib6_rule_compare, .fill = fib6_rule_fill, - .default_pref = fib6_rule_default_pref, .nlmsg_payload = fib6_rule_nlmsg_payload, .nlgroup = RTNLGRP_IPV6_RULE, .policy = fib6_rule_policy, diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c index 713d7434c911..6c2b2132c8d3 100644 --- a/net/ipv6/icmp.c +++ b/net/ipv6/icmp.c @@ -329,7 +329,7 @@ static struct dst_entry *icmpv6_route_lookup(struct net *net, struct flowi6 fl2; int err; - err = ip6_dst_lookup(sk, &dst, fl6); + err = ip6_dst_lookup(net, sk, &dst, fl6); if (err) return ERR_PTR(err); @@ -361,7 +361,7 @@ static struct dst_entry *icmpv6_route_lookup(struct net *net, if (err) goto relookup_failed; - err = ip6_dst_lookup(sk, &dst2, &fl2); + err = ip6_dst_lookup(net, sk, &dst2, &fl2); if (err) goto relookup_failed; @@ -591,7 +591,7 @@ static void icmpv6_echo_reply(struct sk_buff *skb) else if (!fl6.flowi6_oif) fl6.flowi6_oif = np->ucast_oif; - err = ip6_dst_lookup(sk, &dst, &fl6); + err = ip6_dst_lookup(net, sk, &dst, &fl6); if (err) goto out; dst = xfrm_lookup(net, dst, flowi6_to_flowi(&fl6), sk, 0); diff --git a/net/ipv6/ila.c b/net/ipv6/ila.c new file mode 100644 index 000000000000..678d2df4b8d9 --- /dev/null +++ b/net/ipv6/ila.c @@ -0,0 +1,229 @@ +#include <linux/errno.h> +#include <linux/ip.h> +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/skbuff.h> +#include <linux/socket.h> +#include <linux/types.h> +#include <net/checksum.h> +#include <net/ip.h> +#include <net/ip6_fib.h> +#include <net/lwtunnel.h> +#include <net/protocol.h> +#include <uapi/linux/ila.h> + +struct ila_params { + __be64 locator; + __be64 locator_match; + __wsum csum_diff; +}; + +static inline struct ila_params *ila_params_lwtunnel( + struct lwtunnel_state *lwstate) +{ + return (struct ila_params *)lwstate->data; +} + +static inline __wsum compute_csum_diff8(const __be32 *from, const __be32 *to) +{ + __be32 diff[] = { + ~from[0], ~from[1], to[0], to[1], + }; + + return csum_partial(diff, sizeof(diff), 0); +} + +static inline __wsum get_csum_diff(struct ipv6hdr *ip6h, struct ila_params *p) +{ + if (*(__be64 *)&ip6h->daddr == p->locator_match) + return p->csum_diff; + else + return compute_csum_diff8((__be32 *)&ip6h->daddr, + (__be32 *)&p->locator); +} + +static void update_ipv6_locator(struct sk_buff *skb, struct ila_params *p) +{ + __wsum diff; + struct ipv6hdr *ip6h = ipv6_hdr(skb); + size_t nhoff = sizeof(struct ipv6hdr); + + /* First update checksum */ + switch (ip6h->nexthdr) { + case NEXTHDR_TCP: + if (likely(pskb_may_pull(skb, nhoff + sizeof(struct tcphdr)))) { + struct tcphdr *th = (struct tcphdr *) + (skb_network_header(skb) + nhoff); + + diff = get_csum_diff(ip6h, p); + inet_proto_csum_replace_by_diff(&th->check, skb, + diff, true); + } + break; + case NEXTHDR_UDP: + if (likely(pskb_may_pull(skb, nhoff + sizeof(struct udphdr)))) { + struct udphdr *uh = (struct udphdr *) + (skb_network_header(skb) + nhoff); + + if (uh->check || skb->ip_summed == CHECKSUM_PARTIAL) { + diff = get_csum_diff(ip6h, p); + inet_proto_csum_replace_by_diff(&uh->check, skb, + diff, true); + if (!uh->check) + uh->check = CSUM_MANGLED_0; + } + } + break; + case NEXTHDR_ICMP: + if (likely(pskb_may_pull(skb, + nhoff + sizeof(struct icmp6hdr)))) { + struct icmp6hdr *ih = (struct icmp6hdr *) + (skb_network_header(skb) + nhoff); + + diff = get_csum_diff(ip6h, p); + inet_proto_csum_replace_by_diff(&ih->icmp6_cksum, skb, + diff, true); + } + break; + } + + /* Now change destination address */ + *(__be64 *)&ip6h->daddr = p->locator; +} + +static int ila_output(struct sock *sk, struct sk_buff *skb) +{ + struct dst_entry *dst = skb_dst(skb); + + if (skb->protocol != htons(ETH_P_IPV6)) + goto drop; + + update_ipv6_locator(skb, ila_params_lwtunnel(dst->lwtstate)); + + return dst->lwtstate->orig_output(sk, skb); + +drop: + kfree_skb(skb); + return -EINVAL; +} + +static int ila_input(struct sk_buff *skb) +{ + struct dst_entry *dst = skb_dst(skb); + + if (skb->protocol != htons(ETH_P_IPV6)) + goto drop; + + update_ipv6_locator(skb, ila_params_lwtunnel(dst->lwtstate)); + + return dst->lwtstate->orig_input(skb); + +drop: + kfree_skb(skb); + return -EINVAL; +} + +static struct nla_policy ila_nl_policy[ILA_ATTR_MAX + 1] = { + [ILA_ATTR_LOCATOR] = { .type = NLA_U64, }, +}; + +static int ila_build_state(struct net_device *dev, struct nlattr *nla, + unsigned int family, const void *cfg, + struct lwtunnel_state **ts) +{ + struct ila_params *p; + struct nlattr *tb[ILA_ATTR_MAX + 1]; + size_t encap_len = sizeof(*p); + struct lwtunnel_state *newts; + const struct fib6_config *cfg6 = cfg; + int ret; + + if (family != AF_INET6) + return -EINVAL; + + ret = nla_parse_nested(tb, ILA_ATTR_MAX, nla, + ila_nl_policy); + if (ret < 0) + return ret; + + if (!tb[ILA_ATTR_LOCATOR]) + return -EINVAL; + + newts = lwtunnel_state_alloc(encap_len); + if (!newts) + return -ENOMEM; + + newts->len = encap_len; + p = ila_params_lwtunnel(newts); + + p->locator = (__force __be64)nla_get_u64(tb[ILA_ATTR_LOCATOR]); + + if (cfg6->fc_dst_len > sizeof(__be64)) { + /* Precompute checksum difference for translation since we + * know both the old locator and the new one. + */ + p->locator_match = *(__be64 *)&cfg6->fc_dst; + p->csum_diff = compute_csum_diff8( + (__be32 *)&p->locator_match, (__be32 *)&p->locator); + } + + newts->type = LWTUNNEL_ENCAP_ILA; + newts->flags |= LWTUNNEL_STATE_OUTPUT_REDIRECT | + LWTUNNEL_STATE_INPUT_REDIRECT; + + *ts = newts; + + return 0; +} + +static int ila_fill_encap_info(struct sk_buff *skb, + struct lwtunnel_state *lwtstate) +{ + struct ila_params *p = ila_params_lwtunnel(lwtstate); + + if (nla_put_u64(skb, ILA_ATTR_LOCATOR, (__force u64)p->locator)) + goto nla_put_failure; + + return 0; + +nla_put_failure: + return -EMSGSIZE; +} + +static int ila_encap_nlsize(struct lwtunnel_state *lwtstate) +{ + /* No encapsulation overhead */ + return 0; +} + +static int ila_encap_cmp(struct lwtunnel_state *a, struct lwtunnel_state *b) +{ + struct ila_params *a_p = ila_params_lwtunnel(a); + struct ila_params *b_p = ila_params_lwtunnel(b); + + return (a_p->locator != b_p->locator); +} + +static const struct lwtunnel_encap_ops ila_encap_ops = { + .build_state = ila_build_state, + .output = ila_output, + .input = ila_input, + .fill_encap = ila_fill_encap_info, + .get_encap_size = ila_encap_nlsize, + .cmp_encap = ila_encap_cmp, +}; + +static int __init ila_init(void) +{ + return lwtunnel_encap_add_ops(&ila_encap_ops, LWTUNNEL_ENCAP_ILA); +} + +static void __exit ila_fini(void) +{ + lwtunnel_encap_del_ops(&ila_encap_ops, LWTUNNEL_ENCAP_ILA); +} + +module_init(ila_init); +module_exit(ila_fini); +MODULE_AUTHOR("Tom Herbert <tom@herbertland.com>"); +MODULE_LICENSE("GPL"); diff --git a/net/ipv6/inet6_hashtables.c b/net/ipv6/inet6_hashtables.c index b4fd96de97e6..6ac8dad0138a 100644 --- a/net/ipv6/inet6_hashtables.c +++ b/net/ipv6/inet6_hashtables.c @@ -207,7 +207,6 @@ static int __inet6_check_established(struct inet_timewait_death_row *death_row, struct sock *sk2; const struct hlist_nulls_node *node; struct inet_timewait_sock *tw = NULL; - int twrefcnt = 0; spin_lock(lock); @@ -234,21 +233,17 @@ static int __inet6_check_established(struct inet_timewait_death_row *death_row, WARN_ON(!sk_unhashed(sk)); __sk_nulls_add_node_rcu(sk, &head->chain); if (tw) { - twrefcnt = inet_twsk_unhash(tw); + sk_nulls_del_node_init_rcu((struct sock *)tw); NET_INC_STATS_BH(net, LINUX_MIB_TIMEWAITRECYCLED); } spin_unlock(lock); - if (twrefcnt) - inet_twsk_put(tw); sock_prot_inuse_add(sock_net(sk), sk->sk_prot, 1); if (twp) { *twp = tw; } else if (tw) { /* Silly. Should hash-dance instead... */ - inet_twsk_deschedule(tw); - - inet_twsk_put(tw); + inet_twsk_deschedule_put(tw); } return 0; diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c index 548c6237b1e7..418d9823692b 100644 --- a/net/ipv6/ip6_fib.c +++ b/net/ipv6/ip6_fib.c @@ -32,6 +32,7 @@ #include <net/ipv6.h> #include <net/ndisc.h> #include <net/addrconf.h> +#include <net/lwtunnel.h> #include <net/ip6_fib.h> #include <net/ip6_route.h> diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c index 69f4f689f06a..4038c694ec03 100644 --- a/net/ipv6/ip6_gre.c +++ b/net/ipv6/ip6_gre.c @@ -729,7 +729,7 @@ static netdev_tx_t ip6gre_xmit2(struct sk_buff *skb, */ ipv6h = ipv6_hdr(skb); ip6_flow_hdr(ipv6h, INET_ECN_encapsulate(0, dsfield), - ip6_make_flowlabel(net, skb, fl6->flowlabel, false)); + ip6_make_flowlabel(net, skb, fl6->flowlabel, true, fl6)); ipv6h->hop_limit = tunnel->parms.hop_limit; ipv6h->nexthdr = proto; ipv6h->saddr = fl6->saddr; @@ -1183,7 +1183,8 @@ static int ip6gre_header(struct sk_buff *skb, struct net_device *dev, ip6_flow_hdr(ipv6h, 0, ip6_make_flowlabel(dev_net(dev), skb, - t->fl.u.ip6.flowlabel, false)); + t->fl.u.ip6.flowlabel, true, + &t->fl.u.ip6)); ipv6h->hop_limit = t->parms.hop_limit; ipv6h->nexthdr = NEXTHDR_GRE; ipv6h->saddr = t->parms.laddr; diff --git a/net/ipv6/ip6_input.c b/net/ipv6/ip6_input.c index 57990c929cd8..adba03ac7ce9 100644 --- a/net/ipv6/ip6_input.c +++ b/net/ipv6/ip6_input.c @@ -45,6 +45,7 @@ #include <net/addrconf.h> #include <net/xfrm.h> #include <net/inet_ecn.h> +#include <net/dst_metadata.h> int ip6_rcv_finish(struct sock *sk, struct sk_buff *skb) { @@ -55,7 +56,7 @@ int ip6_rcv_finish(struct sock *sk, struct sk_buff *skb) if (ipprot && ipprot->early_demux) ipprot->early_demux(skb); } - if (!skb_dst(skb)) + if (!skb_valid_dst(skb)) ip6_route_input(skb); return dst_input(skb); @@ -98,7 +99,7 @@ int ipv6_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt * arrived via the sending interface (ethX), because of the * nature of scoping architecture. --yoshfuji */ - IP6CB(skb)->iif = skb_dst(skb) ? ip6_dst_idev(skb_dst(skb))->dev->ifindex : dev->ifindex; + IP6CB(skb)->iif = skb_valid_dst(skb) ? ip6_dst_idev(skb_dst(skb))->dev->ifindex : dev->ifindex; if (unlikely(!pskb_may_pull(skb, sizeof(*hdr)))) goto err; diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index d5f7716662db..26ea47930740 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -207,7 +207,7 @@ int ip6_xmit(struct sock *sk, struct sk_buff *skb, struct flowi6 *fl6, hlimit = ip6_dst_hoplimit(dst); ip6_flow_hdr(hdr, tclass, ip6_make_flowlabel(net, skb, fl6->flowlabel, - np->autoflowlabel)); + np->autoflowlabel, fl6)); hdr->payload_len = htons(seg_len); hdr->nexthdr = proto; @@ -881,10 +881,9 @@ out: return dst; } -static int ip6_dst_lookup_tail(struct sock *sk, +static int ip6_dst_lookup_tail(struct net *net, struct sock *sk, struct dst_entry **dst, struct flowi6 *fl6) { - struct net *net = sock_net(sk); #ifdef CONFIG_IPV6_OPTIMISTIC_DAD struct neighbour *n; struct rt6_info *rt; @@ -994,10 +993,11 @@ out_err_release: * * It returns zero on success, or a standard errno code on error. */ -int ip6_dst_lookup(struct sock *sk, struct dst_entry **dst, struct flowi6 *fl6) +int ip6_dst_lookup(struct net *net, struct sock *sk, struct dst_entry **dst, + struct flowi6 *fl6) { *dst = NULL; - return ip6_dst_lookup_tail(sk, dst, fl6); + return ip6_dst_lookup_tail(net, sk, dst, fl6); } EXPORT_SYMBOL_GPL(ip6_dst_lookup); @@ -1018,11 +1018,13 @@ struct dst_entry *ip6_dst_lookup_flow(struct sock *sk, struct flowi6 *fl6, struct dst_entry *dst = NULL; int err; - err = ip6_dst_lookup_tail(sk, &dst, fl6); + err = ip6_dst_lookup_tail(sock_net(sk), sk, &dst, fl6); if (err) return ERR_PTR(err); if (final_dst) fl6->daddr = *final_dst; + if (!fl6->flowi6_oif) + fl6->flowi6_oif = dst->dev->ifindex; return xfrm_lookup_route(sock_net(sk), dst, flowi6_to_flowi(fl6), sk, 0); } @@ -1050,7 +1052,7 @@ struct dst_entry *ip6_sk_dst_lookup_flow(struct sock *sk, struct flowi6 *fl6, dst = ip6_sk_dst_check(sk, dst, fl6); - err = ip6_dst_lookup_tail(sk, &dst, fl6); + err = ip6_dst_lookup_tail(sock_net(sk), sk, &dst, fl6); if (err) return ERR_PTR(err); if (final_dst) @@ -1647,7 +1649,7 @@ struct sk_buff *__ip6_make_skb(struct sock *sk, ip6_flow_hdr(hdr, v6_cork->tclass, ip6_make_flowlabel(net, skb, fl6->flowlabel, - np->autoflowlabel)); + np->autoflowlabel, fl6)); hdr->hop_limit = v6_cork->hop_limit; hdr->nexthdr = proto; hdr->saddr = fl6->saddr; diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c index 2e67b660118b..b0ab420612bc 100644 --- a/net/ipv6/ip6_tunnel.c +++ b/net/ipv6/ip6_tunnel.c @@ -1095,7 +1095,7 @@ static int ip6_tnl_xmit2(struct sk_buff *skb, skb_reset_network_header(skb); ipv6h = ipv6_hdr(skb); ip6_flow_hdr(ipv6h, INET_ECN_encapsulate(0, dsfield), - ip6_make_flowlabel(net, skb, fl6->flowlabel, false)); + ip6_make_flowlabel(net, skb, fl6->flowlabel, true, fl6)); ipv6h->hop_limit = t->parms.hop_limit; ipv6h->nexthdr = proto; ipv6h->saddr = fl6->saddr; diff --git a/net/ipv6/ip6_udp_tunnel.c b/net/ipv6/ip6_udp_tunnel.c index e1a1136bda7c..14dacf1df529 100644 --- a/net/ipv6/ip6_udp_tunnel.c +++ b/net/ipv6/ip6_udp_tunnel.c @@ -23,6 +23,15 @@ int udp_sock_create6(struct net *net, struct udp_port_cfg *cfg, if (err < 0) goto error; + if (cfg->ipv6_v6only) { + int val = 1; + + err = kernel_setsockopt(sock, IPPROTO_IPV6, IPV6_V6ONLY, + (char *) &val, sizeof(val)); + if (err < 0) + goto error; + } + udp6_addr.sin6_family = AF_INET6; memcpy(&udp6_addr.sin6_addr, &cfg->local_ip6, sizeof(udp6_addr.sin6_addr)); diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c index 74ceb73c1c9a..0e004cc42a22 100644 --- a/net/ipv6/ip6mr.c +++ b/net/ipv6/ip6mr.c @@ -217,7 +217,6 @@ static const struct fib_rules_ops __net_initconst ip6mr_rules_ops_template = { .match = ip6mr_rule_match, .configure = ip6mr_rule_configure, .compare = ip6mr_rule_compare, - .default_pref = fib_default_rule_pref, .fill = ip6mr_rule_fill, .nlgroup = RTNLGRP_IPV6_RULE, .policy = ip6mr_rule_policy, @@ -550,7 +549,7 @@ static void ipmr_mfc_seq_stop(struct seq_file *seq, void *v) if (it->cache == &mrt->mfc6_unres_queue) spin_unlock_bh(&mfc_unres_lock); - else if (it->cache == mrt->mfc6_cache_array) + else if (it->cache == &mrt->mfc6_cache_array[it->ct]) read_unlock(&mrt_lock); } diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c index c53331cfed95..64a71354b069 100644 --- a/net/ipv6/ndisc.c +++ b/net/ipv6/ndisc.c @@ -553,7 +553,8 @@ static void ndisc_send_unsol_na(struct net_device *dev) void ndisc_send_ns(struct net_device *dev, struct neighbour *neigh, const struct in6_addr *solicit, - const struct in6_addr *daddr, const struct in6_addr *saddr) + const struct in6_addr *daddr, const struct in6_addr *saddr, + struct sk_buff *oskb) { struct sk_buff *skb; struct in6_addr addr_buf; @@ -589,6 +590,9 @@ void ndisc_send_ns(struct net_device *dev, struct neighbour *neigh, ndisc_fill_addr_option(skb, ND_OPT_SOURCE_LL_ADDR, dev->dev_addr); + if (!(dev->priv_flags & IFF_XMIT_DST_RELEASE) && oskb) + skb_dst_copy(skb, oskb); + ndisc_send_skb(skb, daddr, saddr); } @@ -675,12 +679,12 @@ static void ndisc_solicit(struct neighbour *neigh, struct sk_buff *skb) "%s: trying to ucast probe in NUD_INVALID: %pI6\n", __func__, target); } - ndisc_send_ns(dev, neigh, target, target, saddr); + ndisc_send_ns(dev, neigh, target, target, saddr, skb); } else if ((probes -= NEIGH_VAR(neigh->parms, APP_PROBES)) < 0) { neigh_app_ns(neigh); } else { addrconf_addr_solict_mult(target, &mcaddr); - ndisc_send_ns(dev, NULL, target, &mcaddr, saddr); + ndisc_send_ns(dev, NULL, target, &mcaddr, saddr, skb); } } @@ -1074,6 +1078,8 @@ static void ndisc_router_discovery(struct sk_buff *skb) struct ndisc_options ndopts; int optlen; unsigned int pref = 0; + __u32 old_if_flags; + bool send_ifinfo_notify = false; __u8 *opt = (__u8 *)(ra_msg + 1); @@ -1144,6 +1150,7 @@ static void ndisc_router_discovery(struct sk_buff *skb) * Remember the managed/otherconf flags from most recently * received RA message (RFC 2462) -- yoshfuji */ + old_if_flags = in6_dev->if_flags; in6_dev->if_flags = (in6_dev->if_flags & ~(IF_RA_MANAGED | IF_RA_OTHERCONF)) | (ra_msg->icmph.icmp6_addrconf_managed ? @@ -1151,6 +1158,9 @@ static void ndisc_router_discovery(struct sk_buff *skb) (ra_msg->icmph.icmp6_addrconf_other ? IF_RA_OTHERCONF : 0); + if (old_if_flags != in6_dev->if_flags) + send_ifinfo_notify = true; + if (!in6_dev->cnf.accept_ra_defrtr) { ND_PRINTK(2, info, "RA: %s, defrtr is false for dev: %s\n", @@ -1225,18 +1235,16 @@ static void ndisc_router_discovery(struct sk_buff *skb) if (rt) rt6_set_expires(rt, jiffies + (HZ * lifetime)); - if (ra_msg->icmph.icmp6_hop_limit) { - /* Only set hop_limit on the interface if it is higher than - * the current hop_limit. - */ - if (in6_dev->cnf.hop_limit < ra_msg->icmph.icmp6_hop_limit) { + if (in6_dev->cnf.accept_ra_min_hop_limit < 256 && + ra_msg->icmph.icmp6_hop_limit) { + if (in6_dev->cnf.accept_ra_min_hop_limit <= ra_msg->icmph.icmp6_hop_limit) { in6_dev->cnf.hop_limit = ra_msg->icmph.icmp6_hop_limit; + if (rt) + dst_metric_set(&rt->dst, RTAX_HOPLIMIT, + ra_msg->icmph.icmp6_hop_limit); } else { - ND_PRINTK(2, warn, "RA: Got route advertisement with lower hop_limit than current\n"); + ND_PRINTK(2, warn, "RA: Got route advertisement with lower hop_limit than minimum\n"); } - if (rt) - dst_metric_set(&rt->dst, RTAX_HOPLIMIT, - ra_msg->icmph.icmp6_hop_limit); } skip_defrtr: @@ -1254,7 +1262,7 @@ skip_defrtr: rtime = HZ/10; NEIGH_VAR_SET(in6_dev->nd_parms, RETRANS_TIME, rtime); in6_dev->tstamp = jiffies; - inet6_ifinfo_notify(RTM_NEWLINK, in6_dev); + send_ifinfo_notify = true; } rtime = ntohl(ra_msg->reachable_time); @@ -1271,11 +1279,17 @@ skip_defrtr: GC_STALETIME, 3 * rtime); in6_dev->nd_parms->reachable_time = neigh_rand_reach_time(rtime); in6_dev->tstamp = jiffies; - inet6_ifinfo_notify(RTM_NEWLINK, in6_dev); + send_ifinfo_notify = true; } } } + /* + * Send a notify if RA changed managed/otherconf flags or timer settings + */ + if (send_ifinfo_notify) + inet6_ifinfo_notify(RTM_NEWLINK, in6_dev); + skip_linkparms: /* diff --git a/net/ipv6/netfilter/Kconfig b/net/ipv6/netfilter/Kconfig index b552cf0d6198..96833e4b3193 100644 --- a/net/ipv6/netfilter/Kconfig +++ b/net/ipv6/netfilter/Kconfig @@ -47,9 +47,21 @@ config NFT_REJECT_IPV6 default NFT_REJECT tristate +config NFT_DUP_IPV6 + tristate "IPv6 nf_tables packet duplication support" + select NF_DUP_IPV6 + help + This module enables IPv6 packet duplication support for nf_tables. + endif # NF_TABLES_IPV6 endif # NF_TABLES +config NF_DUP_IPV6 + tristate "Netfilter IPv6 packet duplication to alternate destination" + help + This option enables the nf_dup_ipv6 core, which duplicates an IPv6 + packet to be rerouted to another destination. + config NF_REJECT_IPV6 tristate "IPv6 packet rejection" default m if NETFILTER_ADVANCED=n diff --git a/net/ipv6/netfilter/Makefile b/net/ipv6/netfilter/Makefile index c36e0a5490de..b4f7d0b4e2af 100644 --- a/net/ipv6/netfilter/Makefile +++ b/net/ipv6/netfilter/Makefile @@ -30,6 +30,8 @@ obj-$(CONFIG_NF_LOG_IPV6) += nf_log_ipv6.o # reject obj-$(CONFIG_NF_REJECT_IPV6) += nf_reject_ipv6.o +obj-$(CONFIG_NF_DUP_IPV6) += nf_dup_ipv6.o + # nf_tables obj-$(CONFIG_NF_TABLES_IPV6) += nf_tables_ipv6.o obj-$(CONFIG_NFT_CHAIN_ROUTE_IPV6) += nft_chain_route_ipv6.o @@ -37,6 +39,7 @@ obj-$(CONFIG_NFT_CHAIN_NAT_IPV6) += nft_chain_nat_ipv6.o obj-$(CONFIG_NFT_REJECT_IPV6) += nft_reject_ipv6.o obj-$(CONFIG_NFT_MASQ_IPV6) += nft_masq_ipv6.o obj-$(CONFIG_NFT_REDIR_IPV6) += nft_redir_ipv6.o +obj-$(CONFIG_NFT_DUP_IPV6) += nft_dup_ipv6.o # matches obj-$(CONFIG_IP6_NF_MATCH_AH) += ip6t_ah.o diff --git a/net/ipv6/netfilter/ip6_tables.c b/net/ipv6/netfilter/ip6_tables.c index 3c35ced39b42..0771991ed812 100644 --- a/net/ipv6/netfilter/ip6_tables.c +++ b/net/ipv6/netfilter/ip6_tables.c @@ -305,7 +305,7 @@ static void trace_packet(const struct sk_buff *skb, } #endif -static inline __pure struct ip6t_entry * +static inline struct ip6t_entry * ip6t_next_entry(const struct ip6t_entry *entry) { return (void *)entry + entry->next_offset; @@ -324,12 +324,13 @@ ip6t_do_table(struct sk_buff *skb, const char *indev, *outdev; const void *table_base; struct ip6t_entry *e, **jumpstack; - unsigned int *stackptr, origptr, cpu; + unsigned int stackidx, cpu; const struct xt_table_info *private; struct xt_action_param acpar; unsigned int addend; /* Initialization */ + stackidx = 0; indev = state->in ? state->in->name : nulldevname; outdev = state->out ? state->out->name : nulldevname; /* We handle fragments by dealing with the first fragment as @@ -357,8 +358,16 @@ ip6t_do_table(struct sk_buff *skb, cpu = smp_processor_id(); table_base = private->entries; jumpstack = (struct ip6t_entry **)private->jumpstack[cpu]; - stackptr = per_cpu_ptr(private->stackptr, cpu); - origptr = *stackptr; + + /* Switch to alternate jumpstack if we're being invoked via TEE. + * TEE issues XT_CONTINUE verdict on original skb so we must not + * clobber the jumpstack. + * + * For recursion via REJECT or SYNPROXY the stack will be clobbered + * but it is no problem since absolute verdict is issued by these. + */ + if (static_key_false(&xt_tee_enabled)) + jumpstack += private->stacksize * __this_cpu_read(nf_skb_duplicated); e = get_entry(table_base, private->hook_entry[hook]); @@ -406,20 +415,16 @@ ip6t_do_table(struct sk_buff *skb, verdict = (unsigned int)(-v) - 1; break; } - if (*stackptr <= origptr) + if (stackidx == 0) e = get_entry(table_base, private->underflow[hook]); else - e = ip6t_next_entry(jumpstack[--*stackptr]); + e = ip6t_next_entry(jumpstack[--stackidx]); continue; } if (table_base + v != ip6t_next_entry(e) && !(e->ipv6.flags & IP6T_F_GOTO)) { - if (*stackptr >= private->stacksize) { - verdict = NF_DROP; - break; - } - jumpstack[(*stackptr)++] = e; + jumpstack[stackidx++] = e; } e = get_entry(table_base, v); @@ -437,8 +442,6 @@ ip6t_do_table(struct sk_buff *skb, break; } while (!acpar.hotdrop); - *stackptr = origptr; - xt_write_recseq_end(addend); local_bh_enable(); diff --git a/net/ipv6/netfilter/ip6t_REJECT.c b/net/ipv6/netfilter/ip6t_REJECT.c index 12331efd49cf..0ed841a3fa33 100644 --- a/net/ipv6/netfilter/ip6t_REJECT.c +++ b/net/ipv6/netfilter/ip6t_REJECT.c @@ -35,14 +35,12 @@ MODULE_AUTHOR("Yasuyuki KOZAKAI <yasuyuki.kozakai@toshiba.co.jp>"); MODULE_DESCRIPTION("Xtables: packet \"rejection\" target for IPv6"); MODULE_LICENSE("GPL"); - static unsigned int reject_tg6(struct sk_buff *skb, const struct xt_action_param *par) { const struct ip6t_reject_info *reject = par->targinfo; struct net *net = dev_net((par->in != NULL) ? par->in : par->out); - pr_debug("%s: medium point\n", __func__); switch (reject->with) { case IP6T_ICMP6_NO_ROUTE: nf_send_unreach6(net, skb, ICMPV6_NOROUTE, par->hooknum); @@ -65,8 +63,11 @@ reject_tg6(struct sk_buff *skb, const struct xt_action_param *par) case IP6T_TCP_RESET: nf_send_reset6(net, skb, par->hooknum); break; - default: - net_info_ratelimited("case %u not handled yet\n", reject->with); + case IP6T_ICMP6_POLICY_FAIL: + nf_send_unreach6(net, skb, ICMPV6_POLICY_FAIL, par->hooknum); + break; + case IP6T_ICMP6_REJECT_ROUTE: + nf_send_unreach6(net, skb, ICMPV6_REJECT_ROUTE, par->hooknum); break; } diff --git a/net/ipv6/netfilter/ip6t_SYNPROXY.c b/net/ipv6/netfilter/ip6t_SYNPROXY.c index ebbb754c2111..1e4bf99ed16e 100644 --- a/net/ipv6/netfilter/ip6t_SYNPROXY.c +++ b/net/ipv6/netfilter/ip6t_SYNPROXY.c @@ -237,7 +237,7 @@ synproxy_send_client_ack(const struct synproxy_net *snet, nth->ack_seq = th->ack_seq; tcp_flag_word(nth) = TCP_FLAG_ACK; nth->doff = tcp_hdr_size / 4; - nth->window = ntohs(htons(th->window) >> opts->wscale); + nth->window = htons(ntohs(th->window) >> opts->wscale); nth->check = 0; nth->urg_ptr = 0; diff --git a/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c b/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c index 4ba0c34c627b..7302900c321a 100644 --- a/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c +++ b/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c @@ -251,7 +251,7 @@ ipv6_getorigdst(struct sock *sk, int optval, void __user *user, int *len) if (*len < 0 || (unsigned int) *len < sizeof(sin6)) return -EINVAL; - h = nf_conntrack_find_get(sock_net(sk), NF_CT_DEFAULT_ZONE, &tuple); + h = nf_conntrack_find_get(sock_net(sk), &nf_ct_zone_dflt, &tuple); if (!h) { pr_debug("IP6T_SO_ORIGINAL_DST: Can't find %pI6c/%u-%pI6c/%u.\n", &tuple.src.u3.ip6, ntohs(tuple.src.u.tcp.port), diff --git a/net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c b/net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c index 90388d606483..0e6fae103d33 100644 --- a/net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c +++ b/net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c @@ -150,7 +150,7 @@ icmpv6_error_message(struct net *net, struct nf_conn *tmpl, struct nf_conntrack_tuple intuple, origtuple; const struct nf_conntrack_tuple_hash *h; const struct nf_conntrack_l4proto *inproto; - u16 zone = tmpl ? nf_ct_zone(tmpl) : NF_CT_DEFAULT_ZONE; + struct nf_conntrack_zone tmp; NF_CT_ASSERT(skb->nfct == NULL); @@ -177,7 +177,8 @@ icmpv6_error_message(struct net *net, struct nf_conn *tmpl, *ctinfo = IP_CT_RELATED; - h = nf_conntrack_find_get(net, zone, &intuple); + h = nf_conntrack_find_get(net, nf_ct_zone_tmpl(tmpl, skb, &tmp), + &intuple); if (!h) { pr_debug("icmpv6_error: no match\n"); return -NF_ACCEPT; diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c index 6d02498172c1..701cd2bae0a9 100644 --- a/net/ipv6/netfilter/nf_conntrack_reasm.c +++ b/net/ipv6/netfilter/nf_conntrack_reasm.c @@ -633,6 +633,7 @@ ret_orig: kfree_skb(clone); return skb; } +EXPORT_SYMBOL_GPL(nf_ct_frag6_gather); void nf_ct_frag6_consume_orig(struct sk_buff *skb) { diff --git a/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c b/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c index a45db0b4785c..6d9c0b3d5b8c 100644 --- a/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c +++ b/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c @@ -33,23 +33,22 @@ static enum ip6_defrag_users nf_ct6_defrag_user(unsigned int hooknum, struct sk_buff *skb) { - u16 zone = NF_CT_DEFAULT_ZONE; - + u16 zone_id = NF_CT_DEFAULT_ZONE_ID; #if IS_ENABLED(CONFIG_NF_CONNTRACK) - if (skb->nfct) - zone = nf_ct_zone((struct nf_conn *)skb->nfct); -#endif + if (skb->nfct) { + enum ip_conntrack_info ctinfo; + const struct nf_conn *ct = nf_ct_get(skb, &ctinfo); -#if IS_ENABLED(CONFIG_BRIDGE_NETFILTER) - if (skb->nf_bridge && - skb->nf_bridge->mask & BRNF_NF_BRIDGE_PREROUTING) - return IP6_DEFRAG_CONNTRACK_BRIDGE_IN + zone; + zone_id = nf_ct_zone_id(nf_ct_zone(ct), CTINFO2DIR(ctinfo)); + } #endif + if (nf_bridge_in_prerouting(skb)) + return IP6_DEFRAG_CONNTRACK_BRIDGE_IN + zone_id; + if (hooknum == NF_INET_PRE_ROUTING) - return IP6_DEFRAG_CONNTRACK_IN + zone; + return IP6_DEFRAG_CONNTRACK_IN + zone_id; else - return IP6_DEFRAG_CONNTRACK_OUT + zone; - + return IP6_DEFRAG_CONNTRACK_OUT + zone_id; } static unsigned int ipv6_defrag(const struct nf_hook_ops *ops, diff --git a/net/ipv6/netfilter/nf_dup_ipv6.c b/net/ipv6/netfilter/nf_dup_ipv6.c new file mode 100644 index 000000000000..c8ab626556a0 --- /dev/null +++ b/net/ipv6/netfilter/nf_dup_ipv6.c @@ -0,0 +1,97 @@ +/* + * (C) 2007 by Sebastian Claßen <sebastian.classen@freenet.ag> + * (C) 2007-2010 by Jan Engelhardt <jengelh@medozas.de> + * + * Extracted from xt_TEE.c + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License version 2 or later, as + * published by the Free Software Foundation. + */ +#include <linux/module.h> +#include <linux/percpu.h> +#include <linux/skbuff.h> +#include <linux/netfilter.h> +#include <net/ipv6.h> +#include <net/ip6_route.h> +#include <net/netfilter/ipv6/nf_dup_ipv6.h> +#if IS_ENABLED(CONFIG_NF_CONNTRACK) +#include <net/netfilter/nf_conntrack.h> +#endif + +static struct net *pick_net(struct sk_buff *skb) +{ +#ifdef CONFIG_NET_NS + const struct dst_entry *dst; + + if (skb->dev != NULL) + return dev_net(skb->dev); + dst = skb_dst(skb); + if (dst != NULL && dst->dev != NULL) + return dev_net(dst->dev); +#endif + return &init_net; +} + +static bool nf_dup_ipv6_route(struct sk_buff *skb, const struct in6_addr *gw, + int oif) +{ + const struct ipv6hdr *iph = ipv6_hdr(skb); + struct net *net = pick_net(skb); + struct dst_entry *dst; + struct flowi6 fl6; + + memset(&fl6, 0, sizeof(fl6)); + if (oif != -1) + fl6.flowi6_oif = oif; + + fl6.daddr = *gw; + fl6.flowlabel = (__force __be32)(((iph->flow_lbl[0] & 0xF) << 16) | + (iph->flow_lbl[1] << 8) | iph->flow_lbl[2]); + dst = ip6_route_output(net, NULL, &fl6); + if (dst->error) { + dst_release(dst); + return false; + } + skb_dst_drop(skb); + skb_dst_set(skb, dst); + skb->dev = dst->dev; + skb->protocol = htons(ETH_P_IPV6); + + return true; +} + +void nf_dup_ipv6(struct sk_buff *skb, unsigned int hooknum, + const struct in6_addr *gw, int oif) +{ + if (this_cpu_read(nf_skb_duplicated)) + return; + skb = pskb_copy(skb, GFP_ATOMIC); + if (skb == NULL) + return; + +#if IS_ENABLED(CONFIG_NF_CONNTRACK) + nf_conntrack_put(skb->nfct); + skb->nfct = &nf_ct_untracked_get()->ct_general; + skb->nfctinfo = IP_CT_NEW; + nf_conntrack_get(skb->nfct); +#endif + if (hooknum == NF_INET_PRE_ROUTING || + hooknum == NF_INET_LOCAL_IN) { + struct ipv6hdr *iph = ipv6_hdr(skb); + --iph->hop_limit; + } + if (nf_dup_ipv6_route(skb, gw, oif)) { + __this_cpu_write(nf_skb_duplicated, true); + ip6_local_out(skb); + __this_cpu_write(nf_skb_duplicated, false); + } else { + kfree_skb(skb); + } +} +EXPORT_SYMBOL_GPL(nf_dup_ipv6); + +MODULE_AUTHOR("Sebastian Claßen <sebastian.classen@freenet.ag>"); +MODULE_AUTHOR("Jan Engelhardt <jengelh@medozas.de>"); +MODULE_DESCRIPTION("nf_dup_ipv6: IPv6 packet duplication"); +MODULE_LICENSE("GPL"); diff --git a/net/ipv6/netfilter/nf_nat_l3proto_ipv6.c b/net/ipv6/netfilter/nf_nat_l3proto_ipv6.c index e76900e0aa92..70fbaed49edb 100644 --- a/net/ipv6/netfilter/nf_nat_l3proto_ipv6.c +++ b/net/ipv6/netfilter/nf_nat_l3proto_ipv6.c @@ -124,7 +124,7 @@ static void nf_nat_ipv6_csum_update(struct sk_buff *skb, newip = &t->dst.u3.in6; } inet_proto_csum_replace16(check, skb, oldip->s6_addr32, - newip->s6_addr32, 1); + newip->s6_addr32, true); } static void nf_nat_ipv6_csum_recalc(struct sk_buff *skb, @@ -155,7 +155,7 @@ static void nf_nat_ipv6_csum_recalc(struct sk_buff *skb, } } else inet_proto_csum_replace2(check, skb, - htons(oldlen), htons(datalen), 1); + htons(oldlen), htons(datalen), true); } #if IS_ENABLED(CONFIG_NF_CT_NETLINK) diff --git a/net/ipv6/netfilter/nf_nat_proto_icmpv6.c b/net/ipv6/netfilter/nf_nat_proto_icmpv6.c index 2205e8eeeacf..57593b00c5b4 100644 --- a/net/ipv6/netfilter/nf_nat_proto_icmpv6.c +++ b/net/ipv6/netfilter/nf_nat_proto_icmpv6.c @@ -73,7 +73,7 @@ icmpv6_manip_pkt(struct sk_buff *skb, hdr->icmp6_type == ICMPV6_ECHO_REPLY) { inet_proto_csum_replace2(&hdr->icmp6_cksum, skb, hdr->icmp6_identifier, - tuple->src.u.icmp.id, 0); + tuple->src.u.icmp.id, false); hdr->icmp6_identifier = tuple->src.u.icmp.id; } return true; diff --git a/net/ipv6/netfilter/nft_dup_ipv6.c b/net/ipv6/netfilter/nft_dup_ipv6.c new file mode 100644 index 000000000000..0eaa4f65fdea --- /dev/null +++ b/net/ipv6/netfilter/nft_dup_ipv6.c @@ -0,0 +1,108 @@ +/* + * Copyright (c) 2015 Pablo Neira Ayuso <pablo@netfilter.org> + * + * 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/kernel.h> +#include <linux/init.h> +#include <linux/module.h> +#include <linux/netlink.h> +#include <linux/netfilter.h> +#include <linux/netfilter/nf_tables.h> +#include <net/netfilter/nf_tables.h> +#include <net/netfilter/ipv6/nf_dup_ipv6.h> + +struct nft_dup_ipv6 { + enum nft_registers sreg_addr:8; + enum nft_registers sreg_dev:8; +}; + +static void nft_dup_ipv6_eval(const struct nft_expr *expr, + struct nft_regs *regs, + const struct nft_pktinfo *pkt) +{ + struct nft_dup_ipv6 *priv = nft_expr_priv(expr); + struct in6_addr *gw = (struct in6_addr *)®s->data[priv->sreg_addr]; + int oif = regs->data[priv->sreg_dev]; + + nf_dup_ipv6(pkt->skb, pkt->ops->hooknum, gw, oif); +} + +static int nft_dup_ipv6_init(const struct nft_ctx *ctx, + const struct nft_expr *expr, + const struct nlattr * const tb[]) +{ + struct nft_dup_ipv6 *priv = nft_expr_priv(expr); + int err; + + if (tb[NFTA_DUP_SREG_ADDR] == NULL) + return -EINVAL; + + priv->sreg_addr = nft_parse_register(tb[NFTA_DUP_SREG_ADDR]); + err = nft_validate_register_load(priv->sreg_addr, sizeof(struct in6_addr)); + if (err < 0) + return err; + + if (tb[NFTA_DUP_SREG_DEV] != NULL) { + priv->sreg_dev = nft_parse_register(tb[NFTA_DUP_SREG_DEV]); + return nft_validate_register_load(priv->sreg_dev, sizeof(int)); + } + return 0; +} + +static int nft_dup_ipv6_dump(struct sk_buff *skb, const struct nft_expr *expr) +{ + struct nft_dup_ipv6 *priv = nft_expr_priv(expr); + + if (nft_dump_register(skb, NFTA_DUP_SREG_ADDR, priv->sreg_addr) || + nft_dump_register(skb, NFTA_DUP_SREG_DEV, priv->sreg_dev)) + goto nla_put_failure; + + return 0; + +nla_put_failure: + return -1; +} + +static struct nft_expr_type nft_dup_ipv6_type; +static const struct nft_expr_ops nft_dup_ipv6_ops = { + .type = &nft_dup_ipv6_type, + .size = NFT_EXPR_SIZE(sizeof(struct nft_dup_ipv6)), + .eval = nft_dup_ipv6_eval, + .init = nft_dup_ipv6_init, + .dump = nft_dup_ipv6_dump, +}; + +static const struct nla_policy nft_dup_ipv6_policy[NFTA_DUP_MAX + 1] = { + [NFTA_DUP_SREG_ADDR] = { .type = NLA_U32 }, + [NFTA_DUP_SREG_DEV] = { .type = NLA_U32 }, +}; + +static struct nft_expr_type nft_dup_ipv6_type __read_mostly = { + .family = NFPROTO_IPV6, + .name = "dup", + .ops = &nft_dup_ipv6_ops, + .policy = nft_dup_ipv6_policy, + .maxattr = NFTA_DUP_MAX, + .owner = THIS_MODULE, +}; + +static int __init nft_dup_ipv6_module_init(void) +{ + return nft_register_expr(&nft_dup_ipv6_type); +} + +static void __exit nft_dup_ipv6_module_exit(void) +{ + nft_unregister_expr(&nft_dup_ipv6_type); +} + +module_init(nft_dup_ipv6_module_init); +module_exit(nft_dup_ipv6_module_exit); + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Pablo Neira Ayuso <pablo@netfilter.org>"); +MODULE_ALIAS_NFT_AF_EXPR(AF_INET6, "dup"); diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c index ca4700cb26c4..fdbada1569a3 100644 --- a/net/ipv6/raw.c +++ b/net/ipv6/raw.c @@ -295,7 +295,8 @@ static int rawv6_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len) * unspecified and mapped address have a v4 equivalent. */ v4addr = LOOPBACK4_IPV6; - if (!(addr_type & IPV6_ADDR_MULTICAST)) { + if (!(addr_type & IPV6_ADDR_MULTICAST) && + !sock_net(sk)->ipv6.sysctl.ip_nonlocal_bind) { err = -EADDRNOTAVAIL; if (!ipv6_chk_addr(sock_net(sk), &addr->sin6_addr, dev, 0)) { diff --git a/net/ipv6/route.c b/net/ipv6/route.c index d15586490cec..53617d715188 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -54,10 +54,13 @@ #include <net/tcp.h> #include <linux/rtnetlink.h> #include <net/dst.h> +#include <net/dst_metadata.h> #include <net/xfrm.h> #include <net/netevent.h> #include <net/netlink.h> #include <net/nexthop.h> +#include <net/lwtunnel.h> +#include <net/ip_tunnels.h> #include <asm/uaccess.h> @@ -535,13 +538,14 @@ static void rt6_probe_deferred(struct work_struct *w) container_of(w, struct __rt6_probe_work, work); addrconf_addr_solict_mult(&work->target, &mcaddr); - ndisc_send_ns(work->dev, NULL, &work->target, &mcaddr, NULL); + ndisc_send_ns(work->dev, NULL, &work->target, &mcaddr, NULL, NULL); dev_put(work->dev); kfree(work); } static void rt6_probe(struct rt6_info *rt) { + struct __rt6_probe_work *work; struct neighbour *neigh; /* * Okay, this does not seem to be appropriate @@ -556,34 +560,33 @@ static void rt6_probe(struct rt6_info *rt) rcu_read_lock_bh(); neigh = __ipv6_neigh_lookup_noref(rt->dst.dev, &rt->rt6i_gateway); if (neigh) { - write_lock(&neigh->lock); if (neigh->nud_state & NUD_VALID) goto out; - } - - if (!neigh || - time_after(jiffies, neigh->updated + rt->rt6i_idev->cnf.rtr_probe_interval)) { - struct __rt6_probe_work *work; + work = NULL; + write_lock(&neigh->lock); + if (!(neigh->nud_state & NUD_VALID) && + time_after(jiffies, + neigh->updated + + rt->rt6i_idev->cnf.rtr_probe_interval)) { + work = kmalloc(sizeof(*work), GFP_ATOMIC); + if (work) + __neigh_set_probe_once(neigh); + } + write_unlock(&neigh->lock); + } else { work = kmalloc(sizeof(*work), GFP_ATOMIC); + } - if (neigh && work) - __neigh_set_probe_once(neigh); - - if (neigh) - write_unlock(&neigh->lock); + if (work) { + INIT_WORK(&work->work, rt6_probe_deferred); + work->target = rt->rt6i_gateway; + dev_hold(rt->dst.dev); + work->dev = rt->dst.dev; + schedule_work(&work->work); + } - if (work) { - INIT_WORK(&work->work, rt6_probe_deferred); - work->target = rt->rt6i_gateway; - dev_hold(rt->dst.dev); - work->dev = rt->dst.dev; - schedule_work(&work->work); - } - } else { out: - write_unlock(&neigh->lock); - } rcu_read_unlock_bh(); } #else @@ -662,6 +665,12 @@ static struct rt6_info *find_match(struct rt6_info *rt, int oif, int strict, { int m; bool match_do_rr = false; + struct inet6_dev *idev = rt->rt6i_idev; + struct net_device *dev = rt->dst.dev; + + if (dev && !netif_carrier_ok(dev) && + idev->cnf.ignore_routes_with_linkdown) + goto out; if (rt6_check_expired(rt)) goto out; @@ -1154,6 +1163,7 @@ void ip6_route_input(struct sk_buff *skb) const struct ipv6hdr *iph = ipv6_hdr(skb); struct net *net = dev_net(skb->dev); int flags = RT6_LOOKUP_F_HAS_SADDR; + struct ip_tunnel_info *tun_info; struct flowi6 fl6 = { .flowi6_iif = skb->dev->ifindex, .daddr = iph->daddr, @@ -1163,6 +1173,10 @@ void ip6_route_input(struct sk_buff *skb) .flowi6_proto = iph->nexthdr, }; + tun_info = skb_tunnel_info(skb); + if (tun_info && !(tun_info->mode & IP_TUNNEL_INFO_TX)) + fl6.flowi6_tun_key.tun_id = tun_info->key.tun_id; + skb_dst_drop(skb); skb_dst_set(skb, ip6_route_input_lookup(net, skb->dev, &fl6, flags)); } @@ -1684,6 +1698,7 @@ out: static int ip6_convert_metrics(struct mx6_config *mxc, const struct fib6_config *cfg) { + bool ecn_ca = false; struct nlattr *nla; int remaining; u32 *mp; @@ -1697,37 +1712,43 @@ static int ip6_convert_metrics(struct mx6_config *mxc, nla_for_each_attr(nla, cfg->fc_mx, cfg->fc_mx_len, remaining) { int type = nla_type(nla); + u32 val; - if (type) { - u32 val; + if (!type) + continue; + if (unlikely(type > RTAX_MAX)) + goto err; + + if (type == RTAX_CC_ALGO) { + char tmp[TCP_CA_NAME_MAX]; - if (unlikely(type > RTAX_MAX)) + nla_strlcpy(tmp, nla, sizeof(tmp)); + val = tcp_ca_get_key_by_name(tmp, &ecn_ca); + if (val == TCP_CA_UNSPEC) goto err; - if (type == RTAX_CC_ALGO) { - char tmp[TCP_CA_NAME_MAX]; + } else { + val = nla_get_u32(nla); + } + if (type == RTAX_FEATURES && (val & ~RTAX_FEATURE_MASK)) + goto err; - nla_strlcpy(tmp, nla, sizeof(tmp)); - val = tcp_ca_get_key_by_name(tmp); - if (val == TCP_CA_UNSPEC) - goto err; - } else { - val = nla_get_u32(nla); - } + mp[type - 1] = val; + __set_bit(type - 1, mxc->mx_valid); + } - mp[type - 1] = val; - __set_bit(type - 1, mxc->mx_valid); - } + if (ecn_ca) { + __set_bit(RTAX_FEATURES - 1, mxc->mx_valid); + mp[RTAX_FEATURES - 1] |= DST_FEATURE_ECN_CA; } mxc->mx = mp; - return 0; err: kfree(mp); return -EINVAL; } -int ip6_route_add(struct fib6_config *cfg) +int ip6_route_info_create(struct fib6_config *cfg, struct rt6_info **rt_ret) { int err; struct net *net = cfg->fc_nlinfo.nl_net; @@ -1735,7 +1756,6 @@ int ip6_route_add(struct fib6_config *cfg) struct net_device *dev = NULL; struct inet6_dev *idev = NULL; struct fib6_table *table; - struct mx6_config mxc = { .mx = NULL, }; int addr_type; if (cfg->fc_dst_len > 128 || cfg->fc_src_len > 128) @@ -1801,6 +1821,25 @@ int ip6_route_add(struct fib6_config *cfg) rt->dst.output = ip6_output; + if (cfg->fc_encap) { + struct lwtunnel_state *lwtstate; + + err = lwtunnel_build_state(dev, cfg->fc_encap_type, + cfg->fc_encap, AF_INET6, cfg, + &lwtstate); + if (err) + goto out; + rt->dst.lwtstate = lwtstate_get(lwtstate); + if (lwtunnel_output_redirect(rt->dst.lwtstate)) { + rt->dst.lwtstate->orig_output = rt->dst.output; + rt->dst.output = lwtunnel_output; + } + if (lwtunnel_input_redirect(rt->dst.lwtstate)) { + rt->dst.lwtstate->orig_input = rt->dst.input; + rt->dst.input = lwtunnel_input; + } + } + ipv6_addr_prefix(&rt->rt6i_dst.addr, &cfg->fc_dst, cfg->fc_dst_len); rt->rt6i_dst.plen = cfg->fc_dst_len; if (rt->rt6i_dst.plen == 128) @@ -1941,6 +1980,32 @@ install_route: cfg->fc_nlinfo.nl_net = dev_net(dev); + *rt_ret = rt; + + return 0; +out: + if (dev) + dev_put(dev); + if (idev) + in6_dev_put(idev); + if (rt) + dst_free(&rt->dst); + + *rt_ret = NULL; + + return err; +} + +int ip6_route_add(struct fib6_config *cfg) +{ + struct mx6_config mxc = { .mx = NULL, }; + struct rt6_info *rt = NULL; + int err; + + err = ip6_route_info_create(cfg, &rt); + if (err) + goto out; + err = ip6_convert_metrics(&mxc, cfg); if (err) goto out; @@ -1948,14 +2013,12 @@ install_route: err = __ip6_ins_rt(rt, &cfg->fc_nlinfo, &mxc); kfree(mxc.mx); + return err; out: - if (dev) - dev_put(dev); - if (idev) - in6_dev_put(idev); if (rt) dst_free(&rt->dst); + return err; } @@ -2180,6 +2243,7 @@ static void ip6_rt_copy_init(struct rt6_info *rt, struct rt6_info *ort) #endif rt->rt6i_prefsrc = ort->rt6i_prefsrc; rt->rt6i_table = ort->rt6i_table; + rt->dst.lwtstate = lwtstate_get(ort->dst.lwtstate); } #ifdef CONFIG_IPV6_ROUTE_INFO @@ -2628,6 +2692,8 @@ static const struct nla_policy rtm_ipv6_policy[RTA_MAX+1] = { [RTA_METRICS] = { .type = NLA_NESTED }, [RTA_MULTIPATH] = { .len = sizeof(struct rtnexthop) }, [RTA_PREF] = { .type = NLA_U8 }, + [RTA_ENCAP_TYPE] = { .type = NLA_U16 }, + [RTA_ENCAP] = { .type = NLA_NESTED }, }; static int rtm_to_fib6_config(struct sk_buff *skb, struct nlmsghdr *nlh, @@ -2722,24 +2788,89 @@ static int rtm_to_fib6_config(struct sk_buff *skb, struct nlmsghdr *nlh, cfg->fc_flags |= RTF_PREF(pref); } + if (tb[RTA_ENCAP]) + cfg->fc_encap = tb[RTA_ENCAP]; + + if (tb[RTA_ENCAP_TYPE]) + cfg->fc_encap_type = nla_get_u16(tb[RTA_ENCAP_TYPE]); + err = 0; errout: return err; } -static int ip6_route_multipath(struct fib6_config *cfg, int add) +struct rt6_nh { + struct rt6_info *rt6_info; + struct fib6_config r_cfg; + struct mx6_config mxc; + struct list_head next; +}; + +static void ip6_print_replace_route_err(struct list_head *rt6_nh_list) +{ + struct rt6_nh *nh; + + list_for_each_entry(nh, rt6_nh_list, next) { + pr_warn("IPV6: multipath route replace failed (check consistency of installed routes): %pI6 nexthop %pI6 ifi %d\n", + &nh->r_cfg.fc_dst, &nh->r_cfg.fc_gateway, + nh->r_cfg.fc_ifindex); + } +} + +static int ip6_route_info_append(struct list_head *rt6_nh_list, + struct rt6_info *rt, struct fib6_config *r_cfg) +{ + struct rt6_nh *nh; + struct rt6_info *rtnh; + int err = -EEXIST; + + list_for_each_entry(nh, rt6_nh_list, next) { + /* check if rt6_info already exists */ + rtnh = nh->rt6_info; + + if (rtnh->dst.dev == rt->dst.dev && + rtnh->rt6i_idev == rt->rt6i_idev && + ipv6_addr_equal(&rtnh->rt6i_gateway, + &rt->rt6i_gateway)) + return err; + } + + nh = kzalloc(sizeof(*nh), GFP_KERNEL); + if (!nh) + return -ENOMEM; + nh->rt6_info = rt; + err = ip6_convert_metrics(&nh->mxc, r_cfg); + if (err) { + kfree(nh); + return err; + } + memcpy(&nh->r_cfg, r_cfg, sizeof(*r_cfg)); + list_add_tail(&nh->next, rt6_nh_list); + + return 0; +} + +static int ip6_route_multipath_add(struct fib6_config *cfg) { struct fib6_config r_cfg; struct rtnexthop *rtnh; + struct rt6_info *rt; + struct rt6_nh *err_nh; + struct rt6_nh *nh, *nh_safe; int remaining; int attrlen; - int err = 0, last_err = 0; + int err = 1; + int nhn = 0; + int replace = (cfg->fc_nlinfo.nlh && + (cfg->fc_nlinfo.nlh->nlmsg_flags & NLM_F_REPLACE)); + LIST_HEAD(rt6_nh_list); remaining = cfg->fc_mp_len; -beginning: rtnh = (struct rtnexthop *)cfg->fc_mp; - /* Parse a Multipath Entry */ + /* Parse a Multipath Entry and build a list (rt6_nh_list) of + * rt6_info structs per nexthop + */ while (rtnh_ok(rtnh, remaining)) { memcpy(&r_cfg, cfg, sizeof(*cfg)); if (rtnh->rtnh_ifindex) @@ -2754,23 +2885,37 @@ beginning: r_cfg.fc_gateway = nla_get_in6_addr(nla); r_cfg.fc_flags |= RTF_GATEWAY; } + r_cfg.fc_encap = nla_find(attrs, attrlen, RTA_ENCAP); + nla = nla_find(attrs, attrlen, RTA_ENCAP_TYPE); + if (nla) + r_cfg.fc_encap_type = nla_get_u16(nla); } - err = add ? ip6_route_add(&r_cfg) : ip6_route_del(&r_cfg); + + err = ip6_route_info_create(&r_cfg, &rt); + if (err) + goto cleanup; + + err = ip6_route_info_append(&rt6_nh_list, rt, &r_cfg); if (err) { - last_err = err; - /* If we are trying to remove a route, do not stop the - * loop when ip6_route_del() fails (because next hop is - * already gone), we should try to remove all next hops. - */ - if (add) { - /* If add fails, we should try to delete all - * next hops that have been already added. - */ - add = 0; - remaining = cfg->fc_mp_len - remaining; - goto beginning; - } + dst_free(&rt->dst); + goto cleanup; + } + + rtnh = rtnh_next(rtnh, &remaining); + } + + err_nh = NULL; + list_for_each_entry(nh, &rt6_nh_list, next) { + err = __ip6_ins_rt(nh->rt6_info, &cfg->fc_nlinfo, &nh->mxc); + /* nh->rt6_info is used or freed at this point, reset to NULL*/ + nh->rt6_info = NULL; + if (err) { + if (replace && nhn) + ip6_print_replace_route_err(&rt6_nh_list); + err_nh = nh; + goto add_errout; } + /* Because each route is added like a single route we remove * these flags after the first nexthop: if there is a collision, * we have already failed to add the first nexthop: @@ -2780,6 +2925,62 @@ beginning: */ cfg->fc_nlinfo.nlh->nlmsg_flags &= ~(NLM_F_EXCL | NLM_F_REPLACE); + nhn++; + } + + goto cleanup; + +add_errout: + /* Delete routes that were already added */ + list_for_each_entry(nh, &rt6_nh_list, next) { + if (err_nh == nh) + break; + ip6_route_del(&nh->r_cfg); + } + +cleanup: + list_for_each_entry_safe(nh, nh_safe, &rt6_nh_list, next) { + if (nh->rt6_info) + dst_free(&nh->rt6_info->dst); + kfree(nh->mxc.mx); + list_del(&nh->next); + kfree(nh); + } + + return err; +} + +static int ip6_route_multipath_del(struct fib6_config *cfg) +{ + struct fib6_config r_cfg; + struct rtnexthop *rtnh; + int remaining; + int attrlen; + int err = 1, last_err = 0; + + remaining = cfg->fc_mp_len; + rtnh = (struct rtnexthop *)cfg->fc_mp; + + /* Parse a Multipath Entry */ + while (rtnh_ok(rtnh, remaining)) { + memcpy(&r_cfg, cfg, sizeof(*cfg)); + if (rtnh->rtnh_ifindex) + r_cfg.fc_ifindex = rtnh->rtnh_ifindex; + + attrlen = rtnh_attrlen(rtnh); + if (attrlen > 0) { + struct nlattr *nla, *attrs = rtnh_attrs(rtnh); + + nla = nla_find(attrs, attrlen, RTA_GATEWAY); + if (nla) { + nla_memcpy(&r_cfg.fc_gateway, nla, 16); + r_cfg.fc_flags |= RTF_GATEWAY; + } + } + err = ip6_route_del(&r_cfg); + if (err) + last_err = err; + rtnh = rtnh_next(rtnh, &remaining); } @@ -2796,7 +2997,7 @@ static int inet6_rtm_delroute(struct sk_buff *skb, struct nlmsghdr *nlh) return err; if (cfg.fc_mp) - return ip6_route_multipath(&cfg, 0); + return ip6_route_multipath_del(&cfg); else return ip6_route_del(&cfg); } @@ -2811,12 +3012,12 @@ static int inet6_rtm_newroute(struct sk_buff *skb, struct nlmsghdr *nlh) return err; if (cfg.fc_mp) - return ip6_route_multipath(&cfg, 1); + return ip6_route_multipath_add(&cfg); else return ip6_route_add(&cfg); } -static inline size_t rt6_nlmsg_size(void) +static inline size_t rt6_nlmsg_size(struct rt6_info *rt) { return NLMSG_ALIGN(sizeof(struct rtmsg)) + nla_total_size(16) /* RTA_SRC */ @@ -2830,7 +3031,8 @@ static inline size_t rt6_nlmsg_size(void) + RTAX_MAX * nla_total_size(4) /* RTA_METRICS */ + nla_total_size(sizeof(struct rta_cacheinfo)) + nla_total_size(TCP_CA_NAME_MAX) /* RTAX_CC_ALGO */ - + nla_total_size(1); /* RTA_PREF */ + + nla_total_size(1) /* RTA_PREF */ + + lwtunnel_get_encap_size(rt->dst.lwtstate); } static int rt6_fill_node(struct net *net, @@ -2891,6 +3093,11 @@ static int rt6_fill_node(struct net *net, else rtm->rtm_type = RTN_UNICAST; rtm->rtm_flags = 0; + if (!netif_carrier_ok(rt->dst.dev)) { + rtm->rtm_flags |= RTNH_F_LINKDOWN; + if (rt->rt6i_idev->cnf.ignore_routes_with_linkdown) + rtm->rtm_flags |= RTNH_F_DEAD; + } rtm->rtm_scope = RT_SCOPE_UNIVERSE; rtm->rtm_protocol = rt->rt6i_protocol; if (rt->rt6i_flags & RTF_DYNAMIC) @@ -2978,6 +3185,8 @@ static int rt6_fill_node(struct net *net, if (nla_put_u8(skb, RTA_PREF, IPV6_EXTRACT_PREF(rt->rt6i_flags))) goto nla_put_failure; + lwtunnel_fill_encap(skb, rt->dst.lwtstate); + nlmsg_end(skb, nlh); return 0; @@ -3104,7 +3313,7 @@ void inet6_rt_notify(int event, struct rt6_info *rt, struct nl_info *info) err = -ENOBUFS; seq = info->nlh ? info->nlh->nlmsg_seq : 0; - skb = nlmsg_new(rt6_nlmsg_size(), gfp_any()); + skb = nlmsg_new(rt6_nlmsg_size(rt), gfp_any()); if (!skb) goto errout; diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c index ac35a28599be..94428fd85b2f 100644 --- a/net/ipv6/sit.c +++ b/net/ipv6/sit.c @@ -742,7 +742,7 @@ static int ipip_rcv(struct sk_buff *skb) goto drop; if (iptunnel_pull_header(skb, 0, tpi.proto)) goto drop; - return ip_tunnel_rcv(tunnel, skb, &tpi, log_ecn_error); + return ip_tunnel_rcv(tunnel, skb, &tpi, NULL, log_ecn_error); } return 1; diff --git a/net/ipv6/sysctl_net_ipv6.c b/net/ipv6/sysctl_net_ipv6.c index 4e705add4f18..45243bbe5253 100644 --- a/net/ipv6/sysctl_net_ipv6.c +++ b/net/ipv6/sysctl_net_ipv6.c @@ -17,6 +17,9 @@ #include <net/inet_frag.h> static int one = 1; +static int auto_flowlabels_min; +static int auto_flowlabels_max = IP6_AUTO_FLOW_LABEL_MAX; + static struct ctl_table ipv6_table_template[] = { { @@ -45,7 +48,9 @@ static struct ctl_table ipv6_table_template[] = { .data = &init_net.ipv6.sysctl.auto_flowlabels, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = proc_dointvec + .proc_handler = proc_dointvec_minmax, + .extra1 = &auto_flowlabels_min, + .extra2 = &auto_flowlabels_max }, { .procname = "fwmark_reflect", @@ -75,6 +80,13 @@ static struct ctl_table ipv6_table_template[] = { .mode = 0644, .proc_handler = proc_dointvec }, + { + .procname = "ip_nonlocal_bind", + .data = &init_net.ipv6.sysctl.ip_nonlocal_bind, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec + }, { } }; @@ -117,6 +129,7 @@ static int __net_init ipv6_sysctl_net_init(struct net *net) ipv6_table[5].data = &net->ipv6.sysctl.idgen_retries; ipv6_table[6].data = &net->ipv6.sysctl.idgen_delay; ipv6_table[7].data = &net->ipv6.sysctl.flowlabel_state_ranges; + ipv6_table[8].data = &net->ipv6.sysctl.ip_nonlocal_bind; ipv6_route_table = ipv6_route_sysctl_init(net); if (!ipv6_route_table) diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 7a6cea5e4274..97d9314ea361 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -276,7 +276,7 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr, if (err) goto late_failure; - ip6_set_txhash(sk); + sk_set_txhash(sk); if (!tp->write_seq && likely(!tp->repair)) tp->write_seq = secure_tcpv6_sequence_number(np->saddr.s6_addr32, @@ -1090,7 +1090,7 @@ static struct sock *tcp_v6_syn_recv_sock(struct sock *sk, struct sk_buff *skb, newsk->sk_v6_rcv_saddr = ireq->ir_v6_loc_addr; newsk->sk_bound_dev_if = ireq->ir_iif; - ip6_set_txhash(newsk); + sk_set_txhash(newsk); /* Now IPv6 options... @@ -1481,8 +1481,7 @@ do_time_wait: ntohs(th->dest), tcp_v6_iif(skb)); if (sk2) { struct inet_timewait_sock *tw = inet_twsk(sk); - inet_twsk_deschedule(tw); - inet_twsk_put(tw); + inet_twsk_deschedule_put(tw); sk = sk2; tcp_v6_restore_cb(skb); goto process; diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index e51fc3eee6db..0aba654f5b91 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -1496,7 +1496,8 @@ int __net_init udp6_proc_init(struct net *net) return udp_proc_register(net, &udp6_seq_afinfo); } -void udp6_proc_exit(struct net *net) { +void udp6_proc_exit(struct net *net) +{ udp_proc_unregister(net, &udp6_seq_afinfo); } #endif /* CONFIG_PROC_FS */ diff --git a/net/ipv6/xfrm6_mode_tunnel.c b/net/ipv6/xfrm6_mode_tunnel.c index 901ef6f8addc..f7fbdbabe50e 100644 --- a/net/ipv6/xfrm6_mode_tunnel.c +++ b/net/ipv6/xfrm6_mode_tunnel.c @@ -20,10 +20,9 @@ static inline void ipip6_ecn_decapsulate(struct sk_buff *skb) { - const struct ipv6hdr *outer_iph = ipv6_hdr(skb); struct ipv6hdr *inner_iph = ipipv6_hdr(skb); - if (INET_ECN_is_ce(ipv6_get_dsfield(outer_iph))) + if (INET_ECN_is_ce(XFRM_MODE_SKB_CB(skb)->tos)) IP6_ECN_set_ce(inner_iph); } diff --git a/net/ipv6/xfrm6_policy.c b/net/ipv6/xfrm6_policy.c index ed0583c1b9fc..30caa289c5db 100644 --- a/net/ipv6/xfrm6_policy.c +++ b/net/ipv6/xfrm6_policy.c @@ -20,13 +20,14 @@ #include <net/ip.h> #include <net/ipv6.h> #include <net/ip6_route.h> +#include <net/vrf.h> #if IS_ENABLED(CONFIG_IPV6_MIP6) #include <net/mip6.h> #endif static struct xfrm_policy_afinfo xfrm6_policy_afinfo; -static struct dst_entry *xfrm6_dst_lookup(struct net *net, int tos, +static struct dst_entry *xfrm6_dst_lookup(struct net *net, int tos, int oif, const xfrm_address_t *saddr, const xfrm_address_t *daddr) { @@ -35,6 +36,7 @@ static struct dst_entry *xfrm6_dst_lookup(struct net *net, int tos, int err; memset(&fl6, 0, sizeof(fl6)); + fl6.flowi6_oif = oif; memcpy(&fl6.daddr, daddr, sizeof(fl6.daddr)); if (saddr) memcpy(&fl6.saddr, saddr, sizeof(fl6.saddr)); @@ -50,13 +52,13 @@ static struct dst_entry *xfrm6_dst_lookup(struct net *net, int tos, return dst; } -static int xfrm6_get_saddr(struct net *net, +static int xfrm6_get_saddr(struct net *net, int oif, xfrm_address_t *saddr, xfrm_address_t *daddr) { struct dst_entry *dst; struct net_device *dev; - dst = xfrm6_dst_lookup(net, 0, NULL, daddr); + dst = xfrm6_dst_lookup(net, 0, oif, NULL, daddr); if (IS_ERR(dst)) return -EHOSTUNREACH; @@ -130,8 +132,10 @@ _decode_session6(struct sk_buff *skb, struct flowi *fl, int reverse) nexthdr = nh[nhoff]; - if (skb_dst(skb)) - oif = skb_dst(skb)->dev->ifindex; + if (skb_dst(skb)) { + oif = vrf_master_ifindex(skb_dst(skb)->dev) ? + : skb_dst(skb)->dev->ifindex; + } memset(fl6, 0, sizeof(struct flowi6)); fl6->flowi6_mark = skb->mark; diff --git a/net/mac80211/Kconfig b/net/mac80211/Kconfig index 086de496a4c1..3891cbd2adea 100644 --- a/net/mac80211/Kconfig +++ b/net/mac80211/Kconfig @@ -7,7 +7,6 @@ config MAC80211 select CRYPTO_CCM select CRYPTO_GCM select CRC32 - select AVERAGE ---help--- This option enables the hardware independent IEEE 802.11 networking stack. diff --git a/net/mac80211/Makefile b/net/mac80211/Makefile index 3275f01881be..783e891b7525 100644 --- a/net/mac80211/Makefile +++ b/net/mac80211/Makefile @@ -3,6 +3,7 @@ obj-$(CONFIG_MAC80211) += mac80211.o # mac80211 objects mac80211-y := \ main.o status.o \ + driver-ops.o \ sta_info.o \ wep.o \ wpa.o \ diff --git a/net/mac80211/aes_cmac.c b/net/mac80211/aes_cmac.c index 4192806be3d3..bdf0790d89cc 100644 --- a/net/mac80211/aes_cmac.c +++ b/net/mac80211/aes_cmac.c @@ -145,20 +145,3 @@ void ieee80211_aes_cmac_key_free(struct crypto_cipher *tfm) { crypto_free_cipher(tfm); } - -void ieee80211_aes_cmac_calculate_k1_k2(struct ieee80211_key_conf *keyconf, - u8 *k1, u8 *k2) -{ - u8 l[AES_BLOCK_SIZE] = {}; - struct ieee80211_key *key = - container_of(keyconf, struct ieee80211_key, conf); - - crypto_cipher_encrypt_one(key->u.aes_cmac.tfm, l, l); - - memcpy(k1, l, AES_BLOCK_SIZE); - gf_mulx(k1); - - memcpy(k2, k1, AES_BLOCK_SIZE); - gf_mulx(k2); -} -EXPORT_SYMBOL(ieee80211_aes_cmac_calculate_k1_k2); diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c index bf7023f6c327..17b1fe961c5d 100644 --- a/net/mac80211/cfg.c +++ b/net/mac80211/cfg.c @@ -1019,6 +1019,65 @@ static int sta_apply_auth_flags(struct ieee80211_local *local, return 0; } +static void sta_apply_mesh_params(struct ieee80211_local *local, + struct sta_info *sta, + struct station_parameters *params) +{ +#ifdef CONFIG_MAC80211_MESH + struct ieee80211_sub_if_data *sdata = sta->sdata; + u32 changed = 0; + + if (params->sta_modify_mask & STATION_PARAM_APPLY_PLINK_STATE) { + switch (params->plink_state) { + case NL80211_PLINK_ESTAB: + if (sta->mesh->plink_state != NL80211_PLINK_ESTAB) + changed = mesh_plink_inc_estab_count(sdata); + sta->mesh->plink_state = params->plink_state; + + ieee80211_mps_sta_status_update(sta); + changed |= ieee80211_mps_set_sta_local_pm(sta, + sdata->u.mesh.mshcfg.power_mode); + break; + case NL80211_PLINK_LISTEN: + case NL80211_PLINK_BLOCKED: + case NL80211_PLINK_OPN_SNT: + case NL80211_PLINK_OPN_RCVD: + case NL80211_PLINK_CNF_RCVD: + case NL80211_PLINK_HOLDING: + if (sta->mesh->plink_state == NL80211_PLINK_ESTAB) + changed = mesh_plink_dec_estab_count(sdata); + sta->mesh->plink_state = params->plink_state; + + ieee80211_mps_sta_status_update(sta); + changed |= ieee80211_mps_set_sta_local_pm(sta, + NL80211_MESH_POWER_UNKNOWN); + break; + default: + /* nothing */ + break; + } + } + + switch (params->plink_action) { + case NL80211_PLINK_ACTION_NO_ACTION: + /* nothing */ + break; + case NL80211_PLINK_ACTION_OPEN: + changed |= mesh_plink_open(sta); + break; + case NL80211_PLINK_ACTION_BLOCK: + changed |= mesh_plink_block(sta); + break; + } + + if (params->local_pm) + changed |= ieee80211_mps_set_sta_local_pm(sta, + params->local_pm); + + ieee80211_mbss_info_change_notify(sdata, changed); +#endif +} + static int sta_apply_parameters(struct ieee80211_local *local, struct sta_info *sta, struct station_parameters *params) @@ -1076,7 +1135,6 @@ static int sta_apply_parameters(struct ieee80211_local *local, } if (mask & BIT(NL80211_STA_FLAG_MFP)) { - sta->sta.mfp = !!(set & BIT(NL80211_STA_FLAG_MFP)); if (set & BIT(NL80211_STA_FLAG_MFP)) set_sta_flag(sta, WLAN_STA_MFP); else @@ -1097,6 +1155,12 @@ static int sta_apply_parameters(struct ieee80211_local *local, params->ext_capab[3] & WLAN_EXT_CAPA4_TDLS_CHAN_SWITCH) set_sta_flag(sta, WLAN_STA_TDLS_CHAN_SWITCH); + if (test_sta_flag(sta, WLAN_STA_TDLS_PEER) && + ieee80211_hw_check(&local->hw, TDLS_WIDER_BW) && + params->ext_capab_len >= 8 && + params->ext_capab[7] & WLAN_EXT_CAPA8_TDLS_WIDE_BW_ENABLED) + set_sta_flag(sta, WLAN_STA_TDLS_WIDER_BW); + if (params->sta_modify_mask & STATION_PARAM_APPLY_UAPSD) { sta->sta.uapsd_queues = params->uapsd_queues; sta->sta.max_sp = params->max_sp; @@ -1144,62 +1208,8 @@ static int sta_apply_parameters(struct ieee80211_local *local, band, false); } - if (ieee80211_vif_is_mesh(&sdata->vif)) { -#ifdef CONFIG_MAC80211_MESH - u32 changed = 0; - - if (params->sta_modify_mask & STATION_PARAM_APPLY_PLINK_STATE) { - switch (params->plink_state) { - case NL80211_PLINK_ESTAB: - if (sta->plink_state != NL80211_PLINK_ESTAB) - changed = mesh_plink_inc_estab_count( - sdata); - sta->plink_state = params->plink_state; - - ieee80211_mps_sta_status_update(sta); - changed |= ieee80211_mps_set_sta_local_pm(sta, - sdata->u.mesh.mshcfg.power_mode); - break; - case NL80211_PLINK_LISTEN: - case NL80211_PLINK_BLOCKED: - case NL80211_PLINK_OPN_SNT: - case NL80211_PLINK_OPN_RCVD: - case NL80211_PLINK_CNF_RCVD: - case NL80211_PLINK_HOLDING: - if (sta->plink_state == NL80211_PLINK_ESTAB) - changed = mesh_plink_dec_estab_count( - sdata); - sta->plink_state = params->plink_state; - - ieee80211_mps_sta_status_update(sta); - changed |= ieee80211_mps_set_sta_local_pm(sta, - NL80211_MESH_POWER_UNKNOWN); - break; - default: - /* nothing */ - break; - } - } - - switch (params->plink_action) { - case NL80211_PLINK_ACTION_NO_ACTION: - /* nothing */ - break; - case NL80211_PLINK_ACTION_OPEN: - changed |= mesh_plink_open(sta); - break; - case NL80211_PLINK_ACTION_BLOCK: - changed |= mesh_plink_block(sta); - break; - } - - if (params->local_pm) - changed |= - ieee80211_mps_set_sta_local_pm(sta, - params->local_pm); - ieee80211_mbss_info_change_notify(sdata, changed); -#endif - } + if (ieee80211_vif_is_mesh(&sdata->vif)) + sta_apply_mesh_params(local, sta, params); /* set the STA state after all sta info from usermode has been set */ if (test_sta_flag(sta, WLAN_STA_TDLS_PEER)) { @@ -2358,6 +2368,8 @@ int __ieee80211_request_smps_mgd(struct ieee80211_sub_if_data *sdata, const u8 *ap; enum ieee80211_smps_mode old_req; int err; + struct sta_info *sta; + bool tdls_peer_found = false; lockdep_assert_held(&sdata->wdev.mtx); @@ -2382,11 +2394,22 @@ int __ieee80211_request_smps_mgd(struct ieee80211_sub_if_data *sdata, ap = sdata->u.mgd.associated->bssid; + rcu_read_lock(); + list_for_each_entry_rcu(sta, &sdata->local->sta_list, list) { + if (!sta->sta.tdls || sta->sdata != sdata || !sta->uploaded || + !test_sta_flag(sta, WLAN_STA_AUTHORIZED)) + continue; + + tdls_peer_found = true; + break; + } + rcu_read_unlock(); + if (smps_mode == IEEE80211_SMPS_AUTOMATIC) { - if (sdata->u.mgd.powersave) - smps_mode = IEEE80211_SMPS_DYNAMIC; - else + if (tdls_peer_found || !sdata->u.mgd.powersave) smps_mode = IEEE80211_SMPS_OFF; + else + smps_mode = IEEE80211_SMPS_DYNAMIC; } /* send SM PS frame to AP */ @@ -2394,6 +2417,8 @@ int __ieee80211_request_smps_mgd(struct ieee80211_sub_if_data *sdata, ap, ap); if (err) sdata->u.mgd.req_smps = old_req; + else if (smps_mode != IEEE80211_SMPS_OFF && tdls_peer_found) + ieee80211_teardown_tdls_peers(sdata); return err; } @@ -2443,6 +2468,10 @@ static int ieee80211_set_cqm_rssi_config(struct wiphy *wiphy, rssi_hyst == bss_conf->cqm_rssi_hyst) return 0; + if (sdata->vif.driver_flags & IEEE80211_VIF_BEACON_FILTER && + !(sdata->vif.driver_flags & IEEE80211_VIF_SUPPORTS_CQM_RSSI)) + return -EOPNOTSUPP; + bss_conf->cqm_rssi_thold = rssi_thold; bss_conf->cqm_rssi_hyst = rssi_hyst; @@ -2479,16 +2508,26 @@ static int ieee80211_set_bitrate_mask(struct wiphy *wiphy, sdata->rc_rateidx_mask[i] = mask->control[i].legacy; memcpy(sdata->rc_rateidx_mcs_mask[i], mask->control[i].ht_mcs, sizeof(mask->control[i].ht_mcs)); + memcpy(sdata->rc_rateidx_vht_mcs_mask[i], + mask->control[i].vht_mcs, + sizeof(mask->control[i].vht_mcs)); sdata->rc_has_mcs_mask[i] = false; + sdata->rc_has_vht_mcs_mask[i] = false; if (!sband) continue; - for (j = 0; j < IEEE80211_HT_MCS_MASK_LEN; j++) - if (~sdata->rc_rateidx_mcs_mask[i][j]) { + for (j = 0; j < IEEE80211_HT_MCS_MASK_LEN; j++) { + if (~sdata->rc_rateidx_mcs_mask[i][j]) sdata->rc_has_mcs_mask[i] = true; + + if (~sdata->rc_rateidx_vht_mcs_mask[i][j]) + sdata->rc_has_vht_mcs_mask[i] = true; + + if (sdata->rc_has_mcs_mask[i] && + sdata->rc_has_vht_mcs_mask[i]) break; - } + } } return 0; diff --git a/net/mac80211/chan.c b/net/mac80211/chan.c index f01c18a3160e..1d1b9b7bdefe 100644 --- a/net/mac80211/chan.c +++ b/net/mac80211/chan.c @@ -190,7 +190,7 @@ ieee80211_find_reservation_chanctx(struct ieee80211_local *local, return NULL; } -static enum nl80211_chan_width ieee80211_get_sta_bw(struct ieee80211_sta *sta) +enum nl80211_chan_width ieee80211_get_sta_bw(struct ieee80211_sta *sta) { switch (sta->bandwidth) { case IEEE80211_STA_RX_BW_20: @@ -264,9 +264,17 @@ ieee80211_get_chanctx_max_required_bw(struct ieee80211_local *local, case NL80211_IFTYPE_AP_VLAN: width = ieee80211_get_max_required_bw(sdata); break; + case NL80211_IFTYPE_STATION: + /* + * The ap's sta->bandwidth is not set yet at this + * point, so take the width from the chandef, but + * account also for TDLS peers + */ + width = max(vif->bss_conf.chandef.width, + ieee80211_get_max_required_bw(sdata)); + break; case NL80211_IFTYPE_P2P_DEVICE: continue; - case NL80211_IFTYPE_STATION: case NL80211_IFTYPE_ADHOC: case NL80211_IFTYPE_WDS: case NL80211_IFTYPE_MESH_POINT: @@ -554,12 +562,13 @@ static void ieee80211_free_chanctx(struct ieee80211_local *local, kfree_rcu(ctx, rcu_head); } -static void ieee80211_recalc_chanctx_chantype(struct ieee80211_local *local, - struct ieee80211_chanctx *ctx) +void ieee80211_recalc_chanctx_chantype(struct ieee80211_local *local, + struct ieee80211_chanctx *ctx) { struct ieee80211_chanctx_conf *conf = &ctx->conf; struct ieee80211_sub_if_data *sdata; const struct cfg80211_chan_def *compat = NULL; + struct sta_info *sta; lockdep_assert_held(&local->chanctx_mtx); @@ -581,6 +590,20 @@ static void ieee80211_recalc_chanctx_chantype(struct ieee80211_local *local, if (WARN_ON_ONCE(!compat)) break; } + + /* TDLS peers can sometimes affect the chandef width */ + list_for_each_entry_rcu(sta, &local->sta_list, list) { + if (!sta->uploaded || + !test_sta_flag(sta, WLAN_STA_TDLS_WIDER_BW) || + !test_sta_flag(sta, WLAN_STA_AUTHORIZED) || + !sta->tdls_chandef.chan) + continue; + + compat = cfg80211_chandef_compatible(&sta->tdls_chandef, + compat); + if (WARN_ON_ONCE(!compat)) + break; + } rcu_read_unlock(); if (!compat) diff --git a/net/mac80211/debugfs.c b/net/mac80211/debugfs.c index 3ea8b7de9633..ced6bf3be8d6 100644 --- a/net/mac80211/debugfs.c +++ b/net/mac80211/debugfs.c @@ -122,6 +122,7 @@ static const char *hw_flag_names[NUM_IEEE80211_HW_FLAGS + 1] = { FLAG(CHANCTX_STA_CSA), FLAG(SUPPORTS_CLONED_SKBS), FLAG(SINGLE_SCAN_ON_ALL_BANDS), + FLAG(TDLS_WIDER_BW), /* keep last for the build bug below */ (void *)0x1 @@ -277,7 +278,6 @@ void debugfs_hw_add(struct ieee80211_local *local) DEBUGFS_STATS_ADD(rx_handlers_queued); DEBUGFS_STATS_ADD(rx_handlers_drop_nullfunc); DEBUGFS_STATS_ADD(rx_handlers_drop_defrag); - DEBUGFS_STATS_ADD(rx_handlers_drop_short); DEBUGFS_STATS_ADD(tx_expand_skb_head); DEBUGFS_STATS_ADD(tx_expand_skb_head_cloned); DEBUGFS_STATS_ADD(rx_expand_skb_head_defrag); diff --git a/net/mac80211/debugfs_key.c b/net/mac80211/debugfs_key.c index e82bf1e9d7a8..702ca122c498 100644 --- a/net/mac80211/debugfs_key.c +++ b/net/mac80211/debugfs_key.c @@ -57,7 +57,6 @@ KEY_CONF_FILE(keylen, D); KEY_CONF_FILE(keyidx, D); KEY_CONF_FILE(hw_key_idx, D); KEY_FILE(flags, X); -KEY_FILE(tx_rx_count, D); KEY_READ(ifindex, sdata->name, "%s\n"); KEY_OPS(ifindex); @@ -310,7 +309,6 @@ void ieee80211_debugfs_key_add(struct ieee80211_key *key) DEBUGFS_ADD(flags); DEBUGFS_ADD(keyidx); DEBUGFS_ADD(hw_key_idx); - DEBUGFS_ADD(tx_rx_count); DEBUGFS_ADD(algorithm); DEBUGFS_ADD(tx_spec); DEBUGFS_ADD(rx_spec); diff --git a/net/mac80211/debugfs_netdev.c b/net/mac80211/debugfs_netdev.c index c09c0131bfa2..1021e87c051f 100644 --- a/net/mac80211/debugfs_netdev.c +++ b/net/mac80211/debugfs_netdev.c @@ -186,6 +186,38 @@ IEEE80211_IF_FILE(rc_rateidx_mcs_mask_2ghz, IEEE80211_IF_FILE(rc_rateidx_mcs_mask_5ghz, rc_rateidx_mcs_mask[IEEE80211_BAND_5GHZ], HEXARRAY); +static ssize_t ieee80211_if_fmt_rc_rateidx_vht_mcs_mask_2ghz( + const struct ieee80211_sub_if_data *sdata, + char *buf, int buflen) +{ + int i, len = 0; + const u16 *mask = sdata->rc_rateidx_vht_mcs_mask[IEEE80211_BAND_2GHZ]; + + for (i = 0; i < NL80211_VHT_NSS_MAX; i++) + len += scnprintf(buf + len, buflen - len, "%04x ", mask[i]); + len += scnprintf(buf + len, buflen - len, "\n"); + + return len; +} + +IEEE80211_IF_FILE_R(rc_rateidx_vht_mcs_mask_2ghz); + +static ssize_t ieee80211_if_fmt_rc_rateidx_vht_mcs_mask_5ghz( + const struct ieee80211_sub_if_data *sdata, + char *buf, int buflen) +{ + int i, len = 0; + const u16 *mask = sdata->rc_rateidx_vht_mcs_mask[IEEE80211_BAND_5GHZ]; + + for (i = 0; i < NL80211_VHT_NSS_MAX; i++) + len += scnprintf(buf + len, buflen - len, "%04x ", mask[i]); + len += scnprintf(buf + len, buflen - len, "\n"); + + return len; +} + +IEEE80211_IF_FILE_R(rc_rateidx_vht_mcs_mask_5ghz); + IEEE80211_IF_FILE(flags, flags, HEX); IEEE80211_IF_FILE(state, state, LHEX); IEEE80211_IF_FILE(txpower, vif.bss_conf.txpower, DEC); @@ -565,6 +597,8 @@ static void add_common_files(struct ieee80211_sub_if_data *sdata) DEBUGFS_ADD(rc_rateidx_mask_5ghz); DEBUGFS_ADD(rc_rateidx_mcs_mask_2ghz); DEBUGFS_ADD(rc_rateidx_mcs_mask_5ghz); + DEBUGFS_ADD(rc_rateidx_vht_mcs_mask_2ghz); + DEBUGFS_ADD(rc_rateidx_vht_mcs_mask_5ghz); DEBUGFS_ADD(hw_queues); } diff --git a/net/mac80211/driver-ops.c b/net/mac80211/driver-ops.c new file mode 100644 index 000000000000..267c3b1ca047 --- /dev/null +++ b/net/mac80211/driver-ops.c @@ -0,0 +1,41 @@ +/* + * 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 <net/mac80211.h> +#include "ieee80211_i.h" +#include "trace.h" +#include "driver-ops.h" + +__must_check +int drv_sta_state(struct ieee80211_local *local, + struct ieee80211_sub_if_data *sdata, + struct sta_info *sta, + enum ieee80211_sta_state old_state, + enum ieee80211_sta_state new_state) +{ + int ret = 0; + + might_sleep(); + + sdata = get_bss_sdata(sdata); + if (!check_sdata_in_driver(sdata)) + return -EIO; + + trace_drv_sta_state(local, sdata, &sta->sta, old_state, new_state); + if (local->ops->sta_state) { + ret = local->ops->sta_state(&local->hw, &sdata->vif, &sta->sta, + old_state, new_state); + } else if (old_state == IEEE80211_STA_AUTH && + new_state == IEEE80211_STA_ASSOC) { + ret = drv_sta_add(local, sdata, &sta->sta); + if (ret == 0) + sta->uploaded = true; + } else if (old_state == IEEE80211_STA_ASSOC && + new_state == IEEE80211_STA_AUTH) { + drv_sta_remove(local, sdata, &sta->sta); + } + trace_drv_return_int(local, ret); + return ret; +} diff --git a/net/mac80211/driver-ops.h b/net/mac80211/driver-ops.h index 32a2e707e222..02d91332d7dd 100644 --- a/net/mac80211/driver-ops.h +++ b/net/mac80211/driver-ops.h @@ -573,37 +573,12 @@ static inline void drv_sta_pre_rcu_remove(struct ieee80211_local *local, trace_drv_return_void(local); } -static inline __must_check +__must_check int drv_sta_state(struct ieee80211_local *local, struct ieee80211_sub_if_data *sdata, struct sta_info *sta, enum ieee80211_sta_state old_state, - enum ieee80211_sta_state new_state) -{ - int ret = 0; - - might_sleep(); - - sdata = get_bss_sdata(sdata); - if (!check_sdata_in_driver(sdata)) - return -EIO; - - trace_drv_sta_state(local, sdata, &sta->sta, old_state, new_state); - if (local->ops->sta_state) { - ret = local->ops->sta_state(&local->hw, &sdata->vif, &sta->sta, - old_state, new_state); - } else if (old_state == IEEE80211_STA_AUTH && - new_state == IEEE80211_STA_ASSOC) { - ret = drv_sta_add(local, sdata, &sta->sta); - if (ret == 0) - sta->uploaded = true; - } else if (old_state == IEEE80211_STA_ASSOC && - new_state == IEEE80211_STA_AUTH) { - drv_sta_remove(local, sdata, &sta->sta); - } - trace_drv_return_int(local, ret); - return ret; -} + enum ieee80211_sta_state new_state); static inline void drv_sta_rc_update(struct ieee80211_local *local, struct ieee80211_sub_if_data *sdata, diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h index b12f61507f9f..6e52659f923f 100644 --- a/net/mac80211/ieee80211_i.h +++ b/net/mac80211/ieee80211_i.h @@ -84,13 +84,13 @@ struct ieee80211_local; #define IEEE80211_DEAUTH_FRAME_LEN (24 /* hdr */ + 2 /* reason */) struct ieee80211_fragment_entry { - unsigned long first_frag_time; - unsigned int seq; - unsigned int rx_queue; - unsigned int last_frag; - unsigned int extra_len; struct sk_buff_head skb_list; - int ccmp; /* Whether fragments were encrypted with CCMP */ + unsigned long first_frag_time; + u16 seq; + u16 extra_len; + u16 last_frag; + u8 rx_queue; + bool ccmp; /* Whether fragments were encrypted with CCMP */ u8 last_pn[6]; /* PN of the last fragment if CCMP was used */ }; @@ -181,7 +181,6 @@ typedef unsigned __bitwise__ ieee80211_rx_result; /** * enum ieee80211_packet_rx_flags - packet RX flags - * @IEEE80211_RX_FRAGMENTED: fragmented frame * @IEEE80211_RX_AMSDU: a-MSDU packet * @IEEE80211_RX_MALFORMED_ACTION_FRM: action frame is malformed * @IEEE80211_RX_DEFERRED_RELEASE: frame was subjected to receive reordering @@ -190,7 +189,6 @@ typedef unsigned __bitwise__ ieee80211_rx_result; * @rx_flags field of &struct ieee80211_rx_status. */ enum ieee80211_packet_rx_flags { - IEEE80211_RX_FRAGMENTED = BIT(2), IEEE80211_RX_AMSDU = BIT(3), IEEE80211_RX_MALFORMED_ACTION_FRM = BIT(4), IEEE80211_RX_DEFERRED_RELEASE = BIT(5), @@ -202,8 +200,6 @@ enum ieee80211_packet_rx_flags { * @IEEE80211_RX_CMNTR: received on cooked monitor already * @IEEE80211_RX_BEACON_REPORTED: This frame was already reported * to cfg80211_report_obss_beacon(). - * @IEEE80211_RX_REORDER_TIMER: this frame is released by the - * reorder buffer timeout timer, not the normal RX path * * These flags are used across handling multiple interfaces * for a single frame. @@ -211,10 +207,10 @@ enum ieee80211_packet_rx_flags { enum ieee80211_rx_flags { IEEE80211_RX_CMNTR = BIT(0), IEEE80211_RX_BEACON_REPORTED = BIT(1), - IEEE80211_RX_REORDER_TIMER = BIT(2), }; struct ieee80211_rx_data { + struct napi_struct *napi; struct sk_buff *skb; struct ieee80211_local *local; struct ieee80211_sub_if_data *sdata; @@ -725,6 +721,7 @@ struct ieee80211_if_mesh { * back to wireless media and to the local net stack. * @IEEE80211_SDATA_DISCONNECT_RESUME: Disconnect after resume. * @IEEE80211_SDATA_IN_DRIVER: indicates interface was added to driver + * @IEEE80211_SDATA_MU_MIMO_OWNER: indicates interface owns MU-MIMO capability */ enum ieee80211_sub_if_data_flags { IEEE80211_SDATA_ALLMULTI = BIT(0), @@ -732,6 +729,7 @@ enum ieee80211_sub_if_data_flags { IEEE80211_SDATA_DONT_BRIDGE_PACKETS = BIT(3), IEEE80211_SDATA_DISCONNECT_RESUME = BIT(4), IEEE80211_SDATA_IN_DRIVER = BIT(5), + IEEE80211_SDATA_MU_MIMO_OWNER = BIT(6), }; /** @@ -903,6 +901,9 @@ struct ieee80211_sub_if_data { bool rc_has_mcs_mask[IEEE80211_NUM_BANDS]; u8 rc_rateidx_mcs_mask[IEEE80211_NUM_BANDS][IEEE80211_HT_MCS_MASK_LEN]; + bool rc_has_vht_mcs_mask[IEEE80211_NUM_BANDS]; + u16 rc_rateidx_vht_mcs_mask[IEEE80211_NUM_BANDS][NL80211_VHT_NSS_MAX]; + union { struct ieee80211_if_ap ap; struct ieee80211_if_wds wds; @@ -1010,7 +1011,6 @@ enum sdata_queue_type { IEEE80211_SDATA_QUEUE_AGG_STOP = 2, IEEE80211_SDATA_QUEUE_RX_AGG_START = 3, IEEE80211_SDATA_QUEUE_RX_AGG_STOP = 4, - IEEE80211_SDATA_QUEUE_TDLS_CHSW = 5, }; enum { @@ -1286,7 +1286,6 @@ struct ieee80211_local { unsigned int rx_handlers_queued; unsigned int rx_handlers_drop_nullfunc; unsigned int rx_handlers_drop_defrag; - unsigned int rx_handlers_drop_short; unsigned int tx_expand_skb_head; unsigned int tx_expand_skb_head_cloned; unsigned int rx_expand_skb_head_defrag; @@ -1348,14 +1347,16 @@ struct ieee80211_local { struct ieee80211_sub_if_data __rcu *p2p_sdata; - struct napi_struct *napi; - /* virtual monitor interface */ struct ieee80211_sub_if_data __rcu *monitor_sdata; struct cfg80211_chan_def monitor_chandef; /* extended capabilities provided by mac80211 */ u8 ext_capa[8]; + + /* TDLS channel switch */ + struct work_struct tdls_chsw_work; + struct sk_buff_head skb_queue_tdls_chsw; }; static inline struct ieee80211_sub_if_data * @@ -1715,6 +1716,8 @@ void ieee80211_vht_handle_opmode(struct ieee80211_sub_if_data *sdata, enum ieee80211_band band, bool nss_only); void ieee80211_apply_vhtcap_overrides(struct ieee80211_sub_if_data *sdata, struct ieee80211_sta_vht_cap *vht_cap); +void ieee80211_get_vht_mask_from_cap(__le16 vht_cap, + u16 vht_mask[NL80211_VHT_NSS_MAX]); /* Spectrum management */ void ieee80211_process_measurement_req(struct ieee80211_sub_if_data *sdata, @@ -1763,8 +1766,6 @@ static inline int __ieee80211_resume(struct ieee80211_hw *hw) /* utility functions/constants */ extern const void *const mac80211_wiphy_privid; /* for wiphy privid */ -u8 *ieee80211_get_bssid(struct ieee80211_hdr *hdr, size_t len, - enum nl80211_iftype type); int ieee80211_frame_duration(enum ieee80211_band band, size_t len, int rate, int erp, int short_preamble, int shift); @@ -2042,6 +2043,9 @@ int ieee80211_check_combinations(struct ieee80211_sub_if_data *sdata, enum ieee80211_chanctx_mode chanmode, u8 radar_detect); int ieee80211_max_num_channels(struct ieee80211_local *local); +enum nl80211_chan_width ieee80211_get_sta_bw(struct ieee80211_sta *sta); +void ieee80211_recalc_chanctx_chantype(struct ieee80211_local *local, + struct ieee80211_chanctx *ctx); /* TDLS */ int ieee80211_tdls_mgmt(struct wiphy *wiphy, struct net_device *dev, @@ -2058,8 +2062,8 @@ int ieee80211_tdls_channel_switch(struct wiphy *wiphy, struct net_device *dev, void ieee80211_tdls_cancel_channel_switch(struct wiphy *wiphy, struct net_device *dev, const u8 *addr); -void ieee80211_process_tdls_channel_switch(struct ieee80211_sub_if_data *sdata, - struct sk_buff *skb); +void ieee80211_teardown_tdls_peers(struct ieee80211_sub_if_data *sdata); +void ieee80211_tdls_chsw_work(struct work_struct *wk); extern const struct ethtool_ops ieee80211_ethtool_ops; diff --git a/net/mac80211/iface.c b/net/mac80211/iface.c index 553ac6dd4867..6964fc6a8ea2 100644 --- a/net/mac80211/iface.c +++ b/net/mac80211/iface.c @@ -1242,8 +1242,6 @@ static void ieee80211_iface_work(struct work_struct *work) WLAN_BACK_RECIPIENT, 0, false); mutex_unlock(&local->sta_mtx); - } else if (skb->pkt_type == IEEE80211_SDATA_QUEUE_TDLS_CHSW) { - ieee80211_process_tdls_channel_switch(sdata, skb); } else if (ieee80211_is_action(mgmt->frame_control) && mgmt->u.action.category == WLAN_CATEGORY_BACK) { int len = skb->len; @@ -1790,13 +1788,23 @@ int ieee80211_if_add(struct ieee80211_local *local, const char *name, sband = local->hw.wiphy->bands[i]; sdata->rc_rateidx_mask[i] = sband ? (1 << sband->n_bitrates) - 1 : 0; - if (sband) + if (sband) { + __le16 cap; + u16 *vht_rate_mask; + memcpy(sdata->rc_rateidx_mcs_mask[i], sband->ht_cap.mcs.rx_mask, sizeof(sdata->rc_rateidx_mcs_mask[i])); - else + + cap = sband->vht_cap.vht_mcs.rx_mcs_map; + vht_rate_mask = sdata->rc_rateidx_vht_mcs_mask[i]; + ieee80211_get_vht_mask_from_cap(cap, vht_rate_mask); + } else { memset(sdata->rc_rateidx_mcs_mask[i], 0, sizeof(sdata->rc_rateidx_mcs_mask[i])); + memset(sdata->rc_rateidx_vht_mcs_mask[i], 0, + sizeof(sdata->rc_rateidx_vht_mcs_mask[i])); + } } ieee80211_set_default_queues(sdata); diff --git a/net/mac80211/key.c b/net/mac80211/key.c index b22df3a79a41..44388d6a1d8e 100644 --- a/net/mac80211/key.c +++ b/net/mac80211/key.c @@ -336,7 +336,6 @@ static void ieee80211_key_replace(struct ieee80211_sub_if_data *sdata, ieee80211_check_fast_xmit(sta); } else { rcu_assign_pointer(sta->gtk[idx], new); - sta->gtk_idx = idx; } } else { defunikey = old && diff --git a/net/mac80211/key.h b/net/mac80211/key.h index 3f4f9eaac140..9951ef06323e 100644 --- a/net/mac80211/key.h +++ b/net/mac80211/key.h @@ -115,9 +115,6 @@ struct ieee80211_key { } gen; } u; - /* number of times this key has been used */ - int tx_rx_count; - #ifdef CONFIG_MAC80211_DEBUGFS struct { struct dentry *stalink; diff --git a/net/mac80211/main.c b/net/mac80211/main.c index 3c63468b4dfb..ff79a13d231d 100644 --- a/net/mac80211/main.c +++ b/net/mac80211/main.c @@ -629,6 +629,8 @@ struct ieee80211_hw *ieee80211_alloc_hw_nm(size_t priv_data_len, INIT_WORK(&local->sched_scan_stopped_work, ieee80211_sched_scan_stopped_work); + INIT_WORK(&local->tdls_chsw_work, ieee80211_tdls_chsw_work); + spin_lock_init(&local->ack_status_lock); idr_init(&local->ack_status_frames); @@ -645,6 +647,7 @@ struct ieee80211_hw *ieee80211_alloc_hw_nm(size_t priv_data_len, skb_queue_head_init(&local->skb_queue); skb_queue_head_init(&local->skb_queue_unreliable); + skb_queue_head_init(&local->skb_queue_tdls_chsw); ieee80211_alloc_led_names(local); @@ -1132,18 +1135,6 @@ int ieee80211_register_hw(struct ieee80211_hw *hw) } EXPORT_SYMBOL(ieee80211_register_hw); -void ieee80211_napi_add(struct ieee80211_hw *hw, struct napi_struct *napi, - struct net_device *napi_dev, - int (*poll)(struct napi_struct *, int), - int weight) -{ - struct ieee80211_local *local = hw_to_local(hw); - - netif_napi_add(napi_dev, napi, poll, weight); - local->napi = napi; -} -EXPORT_SYMBOL_GPL(ieee80211_napi_add); - void ieee80211_unregister_hw(struct ieee80211_hw *hw) { struct ieee80211_local *local = hw_to_local(hw); @@ -1173,6 +1164,7 @@ void ieee80211_unregister_hw(struct ieee80211_hw *hw) cancel_work_sync(&local->restart_work); cancel_work_sync(&local->reconfig_filter); + cancel_work_sync(&local->tdls_chsw_work); flush_work(&local->sched_scan_stopped_work); ieee80211_clear_tx_pending(local); @@ -1183,6 +1175,7 @@ void ieee80211_unregister_hw(struct ieee80211_hw *hw) wiphy_warn(local->hw.wiphy, "skb_queue not empty\n"); skb_queue_purge(&local->skb_queue); skb_queue_purge(&local->skb_queue_unreliable); + skb_queue_purge(&local->skb_queue_tdls_chsw); destroy_workqueue(local->workqueue); wiphy_unregister(local->hw.wiphy); diff --git a/net/mac80211/mesh.c b/net/mac80211/mesh.c index 817098add1d6..e06a5ca7c9a9 100644 --- a/net/mac80211/mesh.c +++ b/net/mac80211/mesh.c @@ -158,7 +158,7 @@ void mesh_sta_cleanup(struct sta_info *sta) changed = mesh_accept_plinks_update(sdata); if (!sdata->u.mesh.user_mpm) { changed |= mesh_plink_deactivate(sta); - del_timer_sync(&sta->plink_timer); + del_timer_sync(&sta->mesh->plink_timer); } if (changed) diff --git a/net/mac80211/mesh_hwmp.c b/net/mac80211/mesh_hwmp.c index 085edc1d056b..d80e0a4c16cf 100644 --- a/net/mac80211/mesh_hwmp.c +++ b/net/mac80211/mesh_hwmp.c @@ -19,15 +19,6 @@ #define MAX_PREQ_QUEUE_LEN 64 -/* Destination only */ -#define MP_F_DO 0x1 -/* Reply and forward */ -#define MP_F_RF 0x2 -/* Unknown Sequence Number */ -#define MP_F_USN 0x01 -/* Reason code Present */ -#define MP_F_RCODE 0x02 - static void mesh_queue_preq(struct mesh_path *, u8); static inline u32 u32_field_get(const u8 *preq_elem, int offset, bool ae) @@ -79,6 +70,12 @@ static inline u16 u16_field_get(const u8 *preq_elem, int offset, bool ae) #define MSEC_TO_TU(x) (x*1000/1024) #define SN_GT(x, y) ((s32)(y - x) < 0) #define SN_LT(x, y) ((s32)(x - y) < 0) +#define MAX_SANE_SN_DELTA 32 + +static inline u32 SN_DELTA(u32 x, u32 y) +{ + return x >= y ? x - y : y - x; +} #define net_traversal_jiffies(s) \ msecs_to_jiffies(s->u.mesh.mshcfg.dot11MeshHWMPnetDiameterTraversalTime) @@ -279,15 +276,10 @@ int mesh_path_error_tx(struct ieee80211_sub_if_data *sdata, *pos++ = ttl; /* number of destinations */ *pos++ = 1; - /* - * flags bit, bit 1 is unset if we know the sequence number and - * bit 2 is set if we have a reason code + /* Flags field has AE bit only as defined in + * sec 8.4.2.117 IEEE802.11-2012 */ *pos = 0; - if (!target_sn) - *pos |= MP_F_USN; - if (target_rcode) - *pos |= MP_F_RCODE; pos++; memcpy(pos, target, ETH_ALEN); pos += ETH_ALEN; @@ -316,8 +308,9 @@ void ieee80211s_update_metric(struct ieee80211_local *local, failed = !(txinfo->flags & IEEE80211_TX_STAT_ACK); /* moving average, scaled to 100 */ - sta->fail_avg = ((80 * sta->fail_avg + 5) / 100 + 20 * failed); - if (sta->fail_avg > 95) + sta->mesh->fail_avg = + ((80 * sta->mesh->fail_avg + 5) / 100 + 20 * failed); + if (sta->mesh->fail_avg > 95) mesh_plink_broken(sta); } @@ -333,7 +326,7 @@ static u32 airtime_link_metric_get(struct ieee80211_local *local, u32 tx_time, estimated_retx; u64 result; - if (sta->fail_avg >= 100) + if (sta->mesh->fail_avg >= 100) return MAX_METRIC; sta_set_rate_info_tx(sta, &sta->last_tx_rate, &rinfo); @@ -341,7 +334,7 @@ static u32 airtime_link_metric_get(struct ieee80211_local *local, if (WARN_ON(!rate)) return MAX_METRIC; - err = (sta->fail_avg << ARITH_SHIFT) / 100; + 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. @@ -441,6 +434,26 @@ static u32 hwmp_route_info_get(struct ieee80211_sub_if_data *sdata, process = false; fresh_info = false; } + } else if (!(mpath->flags & MESH_PATH_ACTIVE)) { + bool have_sn, newer_sn, bounced; + + have_sn = mpath->flags & MESH_PATH_SN_VALID; + newer_sn = have_sn && SN_GT(orig_sn, mpath->sn); + bounced = have_sn && + (SN_DELTA(orig_sn, mpath->sn) > + MAX_SANE_SN_DELTA); + + if (!have_sn || newer_sn) { + /* if SN is newer than what we had + * then we can take it */; + } else if (bounced) { + /* if SN is way different than what + * we had then assume the other side + * rebooted or restarted */; + } else { + process = false; + fresh_info = false; + } } } else { mpath = mesh_path_add(sdata, orig_addr); @@ -570,15 +583,13 @@ static void hwmp_preq_frame_process(struct ieee80211_sub_if_data *sdata, SN_LT(mpath->sn, target_sn)) { mpath->sn = target_sn; mpath->flags |= MESH_PATH_SN_VALID; - } else if ((!(target_flags & MP_F_DO)) && + } else if ((!(target_flags & IEEE80211_PREQ_TO_FLAG)) && (mpath->flags & MESH_PATH_ACTIVE)) { reply = true; target_metric = mpath->metric; target_sn = mpath->sn; - if (target_flags & MP_F_RF) - target_flags |= MP_F_DO; - else - forward = false; + /* Case E2 of sec 13.10.9.3 IEEE 802.11-2012*/ + target_flags |= IEEE80211_PREQ_TO_FLAG; } } rcu_read_unlock(); @@ -736,9 +747,12 @@ static void hwmp_perr_frame_process(struct ieee80211_sub_if_data *sdata, if (mpath->flags & MESH_PATH_ACTIVE && ether_addr_equal(ta, sta->sta.addr) && (!(mpath->flags & MESH_PATH_SN_VALID) || - SN_GT(target_sn, mpath->sn))) { + SN_GT(target_sn, mpath->sn) || target_sn == 0)) { mpath->flags &= ~MESH_PATH_ACTIVE; - mpath->sn = target_sn; + if (target_sn != 0) + mpath->sn = target_sn; + else + mpath->sn += 1; spin_unlock_bh(&mpath->state_lock); if (!ifmsh->mshcfg.dot11MeshForwarding) goto endperr; @@ -862,7 +876,7 @@ void mesh_rx_path_sel_frame(struct ieee80211_sub_if_data *sdata, rcu_read_lock(); sta = sta_info_get(sdata, mgmt->sa); - if (!sta || sta->plink_state != NL80211_PLINK_ESTAB) { + if (!sta || sta->mesh->plink_state != NL80211_PLINK_ESTAB) { rcu_read_unlock(); return; } @@ -974,7 +988,7 @@ void mesh_path_start_discovery(struct ieee80211_sub_if_data *sdata) struct ieee80211_if_mesh *ifmsh = &sdata->u.mesh; struct mesh_preq_queue *preq_node; struct mesh_path *mpath; - u8 ttl, target_flags; + u8 ttl, target_flags = 0; const u8 *da; u32 lifetime; @@ -1033,9 +1047,9 @@ void mesh_path_start_discovery(struct ieee80211_sub_if_data *sdata) } if (preq_node->flags & PREQ_Q_F_REFRESH) - target_flags = MP_F_DO; + target_flags |= IEEE80211_PREQ_TO_FLAG; else - target_flags = MP_F_RF; + target_flags &= ~IEEE80211_PREQ_TO_FLAG; spin_unlock_bh(&mpath->state_lock); da = (mpath->is_root) ? mpath->rann_snd_addr : broadcast_addr; @@ -1176,7 +1190,9 @@ void mesh_path_timer(unsigned long data) spin_unlock_bh(&mpath->state_lock); mesh_queue_preq(mpath, 0); } else { - mpath->flags = 0; + mpath->flags &= ~(MESH_PATH_RESOLVING | + MESH_PATH_RESOLVED | + MESH_PATH_REQ_QUEUED); mpath->exp_time = jiffies; spin_unlock_bh(&mpath->state_lock); if (!mpath->is_gate && mesh_gate_num(sdata) > 0) { diff --git a/net/mac80211/mesh_plink.c b/net/mac80211/mesh_plink.c index 3b59099413fb..58384642e03c 100644 --- a/net/mac80211/mesh_plink.c +++ b/net/mac80211/mesh_plink.c @@ -13,10 +13,11 @@ #include "rate.h" #include "mesh.h" +#define PLINK_CNF_AID(mgmt) ((mgmt)->u.action.u.self_prot.variable + 2) #define PLINK_GET_LLID(p) (p + 2) #define PLINK_GET_PLID(p) (p + 4) -#define mod_plink_timer(s, t) (mod_timer(&s->plink_timer, \ +#define mod_plink_timer(s, t) (mod_timer(&s->mesh->plink_timer, \ jiffies + msecs_to_jiffies(t))) enum plink_event { @@ -53,18 +54,13 @@ static const char * const mplevents[] = { [CLS_IGNR] = "CLS_IGNR" }; -static int mesh_plink_frame_tx(struct ieee80211_sub_if_data *sdata, - enum ieee80211_self_protected_actioncode action, - u8 *da, u16 llid, u16 plid, u16 reason); - - /* We only need a valid sta if user configured a minimum rssi_threshold. */ static bool rssi_threshold_check(struct ieee80211_sub_if_data *sdata, struct sta_info *sta) { s32 rssi_threshold = sdata->u.mesh.mshcfg.rssi_threshold; return rssi_threshold == 0 || - (sta && (s8) -ewma_read(&sta->avg_signal) > rssi_threshold); + (sta && (s8) -ewma_signal_read(&sta->avg_signal) > rssi_threshold); } /** @@ -72,14 +68,14 @@ static bool rssi_threshold_check(struct ieee80211_sub_if_data *sdata, * * @sta: mesh peer link to restart * - * Locking: this function must be called holding sta->plink_lock + * Locking: this function must be called holding sta->mesh->plink_lock */ static inline void mesh_plink_fsm_restart(struct sta_info *sta) { - lockdep_assert_held(&sta->plink_lock); - sta->plink_state = NL80211_PLINK_LISTEN; - sta->llid = sta->plid = sta->reason = 0; - sta->plink_retries = 0; + lockdep_assert_held(&sta->mesh->plink_lock); + sta->mesh->plink_state = NL80211_PLINK_LISTEN; + sta->mesh->llid = sta->mesh->plid = sta->mesh->reason = 0; + sta->mesh->plink_retries = 0; } /* @@ -119,7 +115,7 @@ static u32 mesh_set_short_slot_time(struct ieee80211_sub_if_data *sdata) rcu_read_lock(); list_for_each_entry_rcu(sta, &local->sta_list, list) { if (sdata != sta->sdata || - sta->plink_state != NL80211_PLINK_ESTAB) + sta->mesh->plink_state != NL80211_PLINK_ESTAB) continue; short_slot = false; @@ -169,7 +165,7 @@ static u32 mesh_set_ht_prot_mode(struct ieee80211_sub_if_data *sdata) rcu_read_lock(); list_for_each_entry_rcu(sta, &local->sta_list, list) { if (sdata != sta->sdata || - sta->plink_state != NL80211_PLINK_ESTAB) + sta->mesh->plink_state != NL80211_PLINK_ESTAB) continue; if (sta->sta.bandwidth > IEEE80211_STA_RX_BW_20) @@ -204,59 +200,8 @@ static u32 mesh_set_ht_prot_mode(struct ieee80211_sub_if_data *sdata) return BSS_CHANGED_HT; } -/** - * __mesh_plink_deactivate - deactivate mesh peer link - * - * @sta: mesh peer link to deactivate - * - * All mesh paths with this peer as next hop will be flushed - * Returns beacon changed flag if the beacon content changed. - * - * Locking: the caller must hold sta->plink_lock - */ -static u32 __mesh_plink_deactivate(struct sta_info *sta) -{ - struct ieee80211_sub_if_data *sdata = sta->sdata; - u32 changed = 0; - - lockdep_assert_held(&sta->plink_lock); - - if (sta->plink_state == NL80211_PLINK_ESTAB) - changed = mesh_plink_dec_estab_count(sdata); - sta->plink_state = NL80211_PLINK_BLOCKED; - mesh_path_flush_by_nexthop(sta); - - ieee80211_mps_sta_status_update(sta); - changed |= ieee80211_mps_set_sta_local_pm(sta, - NL80211_MESH_POWER_UNKNOWN); - - return changed; -} - -/** - * mesh_plink_deactivate - deactivate mesh peer link - * - * @sta: mesh peer link to deactivate - * - * All mesh paths with this peer as next hop will be flushed - */ -u32 mesh_plink_deactivate(struct sta_info *sta) -{ - struct ieee80211_sub_if_data *sdata = sta->sdata; - u32 changed; - - spin_lock_bh(&sta->plink_lock); - changed = __mesh_plink_deactivate(sta); - sta->reason = WLAN_REASON_MESH_PEER_CANCELED; - mesh_plink_frame_tx(sdata, WLAN_SP_MESH_PEERING_CLOSE, - sta->sta.addr, sta->llid, sta->plid, - sta->reason); - spin_unlock_bh(&sta->plink_lock); - - return changed; -} - static int mesh_plink_frame_tx(struct ieee80211_sub_if_data *sdata, + struct sta_info *sta, enum ieee80211_self_protected_actioncode action, u8 *da, u16 llid, u16 plid, u16 reason) { @@ -306,7 +251,7 @@ static int mesh_plink_frame_tx(struct ieee80211_sub_if_data *sdata, if (action == WLAN_SP_MESH_PEERING_CONFIRM) { /* AID */ pos = skb_put(skb, 2); - put_unaligned_le16(plid, pos); + put_unaligned_le16(sta->sta.aid, pos); } if (ieee80211_add_srates_ie(sdata, skb, true, band) || ieee80211_add_ext_srates_ie(sdata, skb, true, band) || @@ -375,6 +320,58 @@ free: return err; } +/** + * __mesh_plink_deactivate - deactivate mesh peer link + * + * @sta: mesh peer link to deactivate + * + * All mesh paths with this peer as next hop will be flushed + * Returns beacon changed flag if the beacon content changed. + * + * Locking: the caller must hold sta->mesh->plink_lock + */ +static u32 __mesh_plink_deactivate(struct sta_info *sta) +{ + struct ieee80211_sub_if_data *sdata = sta->sdata; + u32 changed = 0; + + lockdep_assert_held(&sta->mesh->plink_lock); + + if (sta->mesh->plink_state == NL80211_PLINK_ESTAB) + changed = mesh_plink_dec_estab_count(sdata); + sta->mesh->plink_state = NL80211_PLINK_BLOCKED; + mesh_path_flush_by_nexthop(sta); + + ieee80211_mps_sta_status_update(sta); + changed |= ieee80211_mps_set_sta_local_pm(sta, + NL80211_MESH_POWER_UNKNOWN); + + return changed; +} + +/** + * mesh_plink_deactivate - deactivate mesh peer link + * + * @sta: mesh peer link to deactivate + * + * All mesh paths with this peer as next hop will be flushed + */ +u32 mesh_plink_deactivate(struct sta_info *sta) +{ + struct ieee80211_sub_if_data *sdata = sta->sdata; + u32 changed; + + spin_lock_bh(&sta->mesh->plink_lock); + changed = __mesh_plink_deactivate(sta); + sta->mesh->reason = WLAN_REASON_MESH_PEER_CANCELED; + mesh_plink_frame_tx(sdata, sta, WLAN_SP_MESH_PEERING_CLOSE, + sta->sta.addr, sta->mesh->llid, sta->mesh->plid, + sta->mesh->reason); + spin_unlock_bh(&sta->mesh->plink_lock); + + return changed; +} + static void mesh_sta_info_init(struct ieee80211_sub_if_data *sdata, struct sta_info *sta, struct ieee802_11_elems *elems, bool insert) @@ -388,13 +385,14 @@ static void mesh_sta_info_init(struct ieee80211_sub_if_data *sdata, sband = local->hw.wiphy->bands[band]; rates = ieee80211_sta_get_rates(sdata, elems, band, &basic_rates); - spin_lock_bh(&sta->plink_lock); + spin_lock_bh(&sta->mesh->plink_lock); sta->last_rx = jiffies; /* rates and capabilities don't change during peering */ - if (sta->plink_state == NL80211_PLINK_ESTAB && sta->processed_beacon) + if (sta->mesh->plink_state == NL80211_PLINK_ESTAB && + sta->mesh->processed_beacon) goto out; - sta->processed_beacon = true; + sta->mesh->processed_beacon = true; if (sta->sta.supp_rates[band] != rates) changed |= IEEE80211_RC_SUPP_RATES_CHANGED; @@ -421,23 +419,57 @@ static void mesh_sta_info_init(struct ieee80211_sub_if_data *sdata, else rate_control_rate_update(local, sband, sta, changed); out: - spin_unlock_bh(&sta->plink_lock); + spin_unlock_bh(&sta->mesh->plink_lock); +} + +static int mesh_allocate_aid(struct ieee80211_sub_if_data *sdata) +{ + struct sta_info *sta; + unsigned long *aid_map; + int aid; + + aid_map = kcalloc(BITS_TO_LONGS(IEEE80211_MAX_AID + 1), + sizeof(*aid_map), GFP_KERNEL); + if (!aid_map) + return -ENOMEM; + + /* reserve aid 0 for mcast indication */ + __set_bit(0, aid_map); + + rcu_read_lock(); + list_for_each_entry_rcu(sta, &sdata->local->sta_list, list) + __set_bit(sta->sta.aid, aid_map); + rcu_read_unlock(); + + aid = find_first_zero_bit(aid_map, IEEE80211_MAX_AID + 1); + kfree(aid_map); + + if (aid > IEEE80211_MAX_AID) + return -ENOBUFS; + + return aid; } static struct sta_info * __mesh_sta_info_alloc(struct ieee80211_sub_if_data *sdata, u8 *hw_addr) { struct sta_info *sta; + int aid; if (sdata->local->num_sta >= MESH_MAX_PLINKS) return NULL; + aid = mesh_allocate_aid(sdata); + if (aid < 0) + return NULL; + sta = sta_info_alloc(sdata, hw_addr, GFP_KERNEL); if (!sta) return NULL; - sta->plink_state = NL80211_PLINK_LISTEN; + sta->mesh->plink_state = NL80211_PLINK_LISTEN; sta->sta.wme = true; + sta->sta.aid = aid; sta_info_pre_move_state(sta, IEEE80211_STA_AUTH); sta_info_pre_move_state(sta, IEEE80211_STA_ASSOC); @@ -524,7 +556,7 @@ void mesh_neighbour_update(struct ieee80211_sub_if_data *sdata, goto out; if (mesh_peer_accepts_plinks(elems) && - sta->plink_state == NL80211_PLINK_LISTEN && + sta->mesh->plink_state == NL80211_PLINK_LISTEN && sdata->u.mesh.accepting_plinks && sdata->u.mesh.mshcfg.auto_open_plinks && rssi_threshold_check(sdata, sta)) @@ -554,52 +586,52 @@ static void mesh_plink_timer(unsigned long data) if (sta->sdata->local->quiescing) return; - spin_lock_bh(&sta->plink_lock); + spin_lock_bh(&sta->mesh->plink_lock); /* If a timer fires just before a state transition on another CPU, * we may have already extended the timeout and changed state by the * time we've acquired the lock and arrived here. In that case, * skip this timer and wait for the new one. */ - if (time_before(jiffies, sta->plink_timer.expires)) { + if (time_before(jiffies, sta->mesh->plink_timer.expires)) { mpl_dbg(sta->sdata, "Ignoring timer for %pM in state %s (timer adjusted)", - sta->sta.addr, mplstates[sta->plink_state]); - spin_unlock_bh(&sta->plink_lock); + sta->sta.addr, mplstates[sta->mesh->plink_state]); + spin_unlock_bh(&sta->mesh->plink_lock); return; } /* del_timer() and handler may race when entering these states */ - if (sta->plink_state == NL80211_PLINK_LISTEN || - sta->plink_state == NL80211_PLINK_ESTAB) { + if (sta->mesh->plink_state == NL80211_PLINK_LISTEN || + sta->mesh->plink_state == NL80211_PLINK_ESTAB) { mpl_dbg(sta->sdata, "Ignoring timer for %pM in state %s (timer deleted)", - sta->sta.addr, mplstates[sta->plink_state]); - spin_unlock_bh(&sta->plink_lock); + sta->sta.addr, mplstates[sta->mesh->plink_state]); + spin_unlock_bh(&sta->mesh->plink_lock); return; } mpl_dbg(sta->sdata, "Mesh plink timer for %pM fired on state %s\n", - sta->sta.addr, mplstates[sta->plink_state]); + sta->sta.addr, mplstates[sta->mesh->plink_state]); sdata = sta->sdata; mshcfg = &sdata->u.mesh.mshcfg; - switch (sta->plink_state) { + switch (sta->mesh->plink_state) { case NL80211_PLINK_OPN_RCVD: case NL80211_PLINK_OPN_SNT: /* retry timer */ - if (sta->plink_retries < mshcfg->dot11MeshMaxRetries) { + if (sta->mesh->plink_retries < mshcfg->dot11MeshMaxRetries) { u32 rand; mpl_dbg(sta->sdata, "Mesh plink for %pM (retry, timeout): %d %d\n", - sta->sta.addr, sta->plink_retries, - sta->plink_timeout); + sta->sta.addr, sta->mesh->plink_retries, + sta->mesh->plink_timeout); get_random_bytes(&rand, sizeof(u32)); - sta->plink_timeout = sta->plink_timeout + - rand % sta->plink_timeout; - ++sta->plink_retries; - mod_plink_timer(sta, sta->plink_timeout); + sta->mesh->plink_timeout = sta->mesh->plink_timeout + + rand % sta->mesh->plink_timeout; + ++sta->mesh->plink_retries; + mod_plink_timer(sta, sta->mesh->plink_timeout); action = WLAN_SP_MESH_PEERING_OPEN; break; } @@ -609,31 +641,31 @@ static void mesh_plink_timer(unsigned long data) /* confirm timer */ if (!reason) reason = WLAN_REASON_MESH_CONFIRM_TIMEOUT; - sta->plink_state = NL80211_PLINK_HOLDING; + sta->mesh->plink_state = NL80211_PLINK_HOLDING; mod_plink_timer(sta, mshcfg->dot11MeshHoldingTimeout); action = WLAN_SP_MESH_PEERING_CLOSE; break; case NL80211_PLINK_HOLDING: /* holding timer */ - del_timer(&sta->plink_timer); + del_timer(&sta->mesh->plink_timer); mesh_plink_fsm_restart(sta); break; default: break; } - spin_unlock_bh(&sta->plink_lock); + spin_unlock_bh(&sta->mesh->plink_lock); if (action) - mesh_plink_frame_tx(sdata, action, sta->sta.addr, - sta->llid, sta->plid, reason); + mesh_plink_frame_tx(sdata, sta, action, sta->sta.addr, + sta->mesh->llid, sta->mesh->plid, reason); } static inline void mesh_plink_timer_set(struct sta_info *sta, u32 timeout) { - sta->plink_timer.expires = jiffies + msecs_to_jiffies(timeout); - sta->plink_timer.data = (unsigned long) sta; - sta->plink_timer.function = mesh_plink_timer; - sta->plink_timeout = timeout; - add_timer(&sta->plink_timer); + sta->mesh->plink_timer.expires = jiffies + msecs_to_jiffies(timeout); + sta->mesh->plink_timer.data = (unsigned long) sta; + sta->mesh->plink_timer.function = mesh_plink_timer; + sta->mesh->plink_timeout = timeout; + add_timer(&sta->mesh->plink_timer); } static bool llid_in_use(struct ieee80211_sub_if_data *sdata, @@ -645,7 +677,7 @@ static bool llid_in_use(struct ieee80211_sub_if_data *sdata, rcu_read_lock(); list_for_each_entry_rcu(sta, &local->sta_list, list) { - if (!memcmp(&sta->llid, &llid, sizeof(llid))) { + if (!memcmp(&sta->mesh->llid, &llid, sizeof(llid))) { in_use = true; break; } @@ -661,8 +693,6 @@ static u16 mesh_get_new_llid(struct ieee80211_sub_if_data *sdata) do { get_random_bytes(&llid, sizeof(llid)); - /* for mesh PS we still only have the AID range for TIM bits */ - llid = (llid % IEEE80211_MAX_AID) + 1; } while (llid_in_use(sdata, llid)); return llid; @@ -676,16 +706,16 @@ u32 mesh_plink_open(struct sta_info *sta) if (!test_sta_flag(sta, WLAN_STA_AUTH)) return 0; - spin_lock_bh(&sta->plink_lock); - sta->llid = mesh_get_new_llid(sdata); - if (sta->plink_state != NL80211_PLINK_LISTEN && - sta->plink_state != NL80211_PLINK_BLOCKED) { - spin_unlock_bh(&sta->plink_lock); + spin_lock_bh(&sta->mesh->plink_lock); + sta->mesh->llid = mesh_get_new_llid(sdata); + if (sta->mesh->plink_state != NL80211_PLINK_LISTEN && + sta->mesh->plink_state != NL80211_PLINK_BLOCKED) { + spin_unlock_bh(&sta->mesh->plink_lock); return 0; } - sta->plink_state = NL80211_PLINK_OPN_SNT; + sta->mesh->plink_state = NL80211_PLINK_OPN_SNT; mesh_plink_timer_set(sta, sdata->u.mesh.mshcfg.dot11MeshRetryTimeout); - spin_unlock_bh(&sta->plink_lock); + spin_unlock_bh(&sta->mesh->plink_lock); mpl_dbg(sdata, "Mesh plink: starting establishment with %pM\n", sta->sta.addr); @@ -693,8 +723,8 @@ u32 mesh_plink_open(struct sta_info *sta) /* set the non-peer mode to active during peering */ changed = ieee80211_mps_local_status_update(sdata); - mesh_plink_frame_tx(sdata, WLAN_SP_MESH_PEERING_OPEN, - sta->sta.addr, sta->llid, 0, 0); + mesh_plink_frame_tx(sdata, sta, WLAN_SP_MESH_PEERING_OPEN, + sta->sta.addr, sta->mesh->llid, 0, 0); return changed; } @@ -702,10 +732,10 @@ u32 mesh_plink_block(struct sta_info *sta) { u32 changed; - spin_lock_bh(&sta->plink_lock); + spin_lock_bh(&sta->mesh->plink_lock); changed = __mesh_plink_deactivate(sta); - sta->plink_state = NL80211_PLINK_BLOCKED; - spin_unlock_bh(&sta->plink_lock); + sta->mesh->plink_state = NL80211_PLINK_BLOCKED; + spin_unlock_bh(&sta->mesh->plink_lock); return changed; } @@ -715,12 +745,11 @@ static void mesh_plink_close(struct ieee80211_sub_if_data *sdata, enum plink_event event) { struct mesh_config *mshcfg = &sdata->u.mesh.mshcfg; - u16 reason = (event == CLS_ACPT) ? WLAN_REASON_MESH_CLOSE : WLAN_REASON_MESH_CONFIG; - sta->reason = reason; - sta->plink_state = NL80211_PLINK_HOLDING; + sta->mesh->reason = reason; + sta->mesh->plink_state = NL80211_PLINK_HOLDING; mod_plink_timer(sta, mshcfg->dot11MeshHoldingTimeout); } @@ -730,8 +759,8 @@ static u32 mesh_plink_establish(struct ieee80211_sub_if_data *sdata, struct mesh_config *mshcfg = &sdata->u.mesh.mshcfg; u32 changed = 0; - del_timer(&sta->plink_timer); - sta->plink_state = NL80211_PLINK_ESTAB; + del_timer(&sta->mesh->plink_timer); + sta->mesh->plink_state = NL80211_PLINK_ESTAB; changed |= mesh_plink_inc_estab_count(sdata); changed |= mesh_set_ht_prot_mode(sdata); changed |= mesh_set_short_slot_time(sdata); @@ -758,18 +787,18 @@ static u32 mesh_plink_fsm(struct ieee80211_sub_if_data *sdata, u32 changed = 0; mpl_dbg(sdata, "peer %pM in state %s got event %s\n", sta->sta.addr, - mplstates[sta->plink_state], mplevents[event]); + mplstates[sta->mesh->plink_state], mplevents[event]); - spin_lock_bh(&sta->plink_lock); - switch (sta->plink_state) { + spin_lock_bh(&sta->mesh->plink_lock); + switch (sta->mesh->plink_state) { case NL80211_PLINK_LISTEN: switch (event) { case CLS_ACPT: mesh_plink_fsm_restart(sta); break; case OPN_ACPT: - sta->plink_state = NL80211_PLINK_OPN_RCVD; - sta->llid = mesh_get_new_llid(sdata); + sta->mesh->plink_state = NL80211_PLINK_OPN_RCVD; + sta->mesh->llid = mesh_get_new_llid(sdata); mesh_plink_timer_set(sta, mshcfg->dot11MeshRetryTimeout); @@ -791,11 +820,11 @@ static u32 mesh_plink_fsm(struct ieee80211_sub_if_data *sdata, break; case OPN_ACPT: /* retry timer is left untouched */ - sta->plink_state = NL80211_PLINK_OPN_RCVD; + sta->mesh->plink_state = NL80211_PLINK_OPN_RCVD; action = WLAN_SP_MESH_PEERING_CONFIRM; break; case CNF_ACPT: - sta->plink_state = NL80211_PLINK_CNF_RCVD; + sta->mesh->plink_state = NL80211_PLINK_CNF_RCVD; mod_plink_timer(sta, mshcfg->dot11MeshConfirmTimeout); break; default: @@ -855,7 +884,7 @@ static u32 mesh_plink_fsm(struct ieee80211_sub_if_data *sdata, case NL80211_PLINK_HOLDING: switch (event) { case CLS_ACPT: - del_timer(&sta->plink_timer); + del_timer(&sta->mesh->plink_timer); mesh_plink_fsm_restart(sta); break; case OPN_ACPT: @@ -874,17 +903,18 @@ static u32 mesh_plink_fsm(struct ieee80211_sub_if_data *sdata, */ break; } - spin_unlock_bh(&sta->plink_lock); + spin_unlock_bh(&sta->mesh->plink_lock); if (action) { - mesh_plink_frame_tx(sdata, action, sta->sta.addr, - sta->llid, sta->plid, sta->reason); + mesh_plink_frame_tx(sdata, sta, action, sta->sta.addr, + sta->mesh->llid, sta->mesh->plid, + sta->mesh->reason); /* also send confirm in open case */ if (action == WLAN_SP_MESH_PEERING_OPEN) { - mesh_plink_frame_tx(sdata, + mesh_plink_frame_tx(sdata, sta, WLAN_SP_MESH_PEERING_CONFIRM, - sta->sta.addr, sta->llid, - sta->plid, 0); + sta->sta.addr, sta->mesh->llid, + sta->mesh->plid, 0); } } @@ -939,7 +969,7 @@ mesh_plink_get_event(struct ieee80211_sub_if_data *sdata, mpl_dbg(sdata, "Mesh plink: Action frame from non-authed peer\n"); goto out; } - if (sta->plink_state == NL80211_PLINK_BLOCKED) + if (sta->mesh->plink_state == NL80211_PLINK_BLOCKED) goto out; } @@ -954,7 +984,7 @@ mesh_plink_get_event(struct ieee80211_sub_if_data *sdata, if (!matches_local) event = OPN_RJCT; if (!mesh_plink_free_count(sdata) || - (sta->plid && sta->plid != plid)) + (sta->mesh->plid && sta->mesh->plid != plid)) event = OPN_IGNR; else event = OPN_ACPT; @@ -963,14 +993,14 @@ mesh_plink_get_event(struct ieee80211_sub_if_data *sdata, if (!matches_local) event = CNF_RJCT; if (!mesh_plink_free_count(sdata) || - sta->llid != llid || - (sta->plid && sta->plid != plid)) + sta->mesh->llid != llid || + (sta->mesh->plid && sta->mesh->plid != plid)) event = CNF_IGNR; else event = CNF_ACPT; break; case WLAN_SP_MESH_PEERING_CLOSE: - if (sta->plink_state == NL80211_PLINK_ESTAB) + if (sta->mesh->plink_state == NL80211_PLINK_ESTAB) /* Do not check for llid or plid. This does not * follow the standard but since multiple plinks * per sta are not supported, it is necessary in @@ -981,9 +1011,9 @@ mesh_plink_get_event(struct ieee80211_sub_if_data *sdata, * restarted. */ event = CLS_ACPT; - else if (sta->plid != plid) + else if (sta->mesh->plid != plid) event = CLS_IGNR; - else if (ie_len == 8 && sta->llid != llid) + else if (ie_len == 8 && sta->mesh->llid != llid) event = CLS_IGNR; else event = CLS_ACPT; @@ -1070,9 +1100,9 @@ mesh_process_plink_frame(struct ieee80211_sub_if_data *sdata, mpl_dbg(sdata, "Mesh plink: failed to init peer!\n"); goto unlock_rcu; } - sta->plid = plid; + sta->mesh->plid = plid; } else if (!sta && event == OPN_RJCT) { - mesh_plink_frame_tx(sdata, WLAN_SP_MESH_PEERING_CLOSE, + mesh_plink_frame_tx(sdata, NULL, WLAN_SP_MESH_PEERING_CLOSE, mgmt->sa, 0, plid, WLAN_REASON_MESH_CONFIG); goto unlock_rcu; @@ -1081,9 +1111,13 @@ mesh_process_plink_frame(struct ieee80211_sub_if_data *sdata, goto unlock_rcu; } - /* 802.11-2012 13.3.7.2 - update plid on CNF if not set */ - if (!sta->plid && event == CNF_ACPT) - sta->plid = plid; + if (event == CNF_ACPT) { + /* 802.11-2012 13.3.7.2 - update plid on CNF if not set */ + if (!sta->mesh->plid) + sta->mesh->plid = plid; + + sta->mesh->aid = get_unaligned_le16(PLINK_CNF_AID(mgmt)); + } changed |= mesh_plink_fsm(sdata, sta, event); diff --git a/net/mac80211/mesh_ps.c b/net/mac80211/mesh_ps.c index ad8b377b4b9f..90a268abea17 100644 --- a/net/mac80211/mesh_ps.c +++ b/net/mac80211/mesh_ps.c @@ -92,16 +92,16 @@ u32 ieee80211_mps_local_status_update(struct ieee80211_sub_if_data *sdata) if (sdata != sta->sdata) continue; - switch (sta->plink_state) { + switch (sta->mesh->plink_state) { case NL80211_PLINK_OPN_SNT: case NL80211_PLINK_OPN_RCVD: case NL80211_PLINK_CNF_RCVD: peering = true; break; case NL80211_PLINK_ESTAB: - if (sta->local_pm == NL80211_MESH_POWER_LIGHT_SLEEP) + if (sta->mesh->local_pm == NL80211_MESH_POWER_LIGHT_SLEEP) light_sleep_cnt++; - else if (sta->local_pm == NL80211_MESH_POWER_DEEP_SLEEP) + else if (sta->mesh->local_pm == NL80211_MESH_POWER_DEEP_SLEEP) deep_sleep_cnt++; break; default: @@ -153,19 +153,19 @@ u32 ieee80211_mps_set_sta_local_pm(struct sta_info *sta, { struct ieee80211_sub_if_data *sdata = sta->sdata; - if (sta->local_pm == pm) + if (sta->mesh->local_pm == pm) return 0; mps_dbg(sdata, "local STA operates in mode %d with %pM\n", pm, sta->sta.addr); - sta->local_pm = pm; + sta->mesh->local_pm = pm; /* * announce peer-specific power mode transition * (see IEEE802.11-2012 13.14.3.2 and 13.14.3.3) */ - if (sta->plink_state == NL80211_PLINK_ESTAB) + if (sta->mesh->plink_state == NL80211_PLINK_ESTAB) mps_qos_null_tx(sta); return ieee80211_mps_local_status_update(sdata); @@ -197,8 +197,8 @@ void ieee80211_mps_set_frame_flags(struct ieee80211_sub_if_data *sdata, if (is_unicast_ether_addr(hdr->addr1) && ieee80211_is_data_qos(hdr->frame_control) && - sta->plink_state == NL80211_PLINK_ESTAB) - pm = sta->local_pm; + sta->mesh->plink_state == NL80211_PLINK_ESTAB) + pm = sta->mesh->local_pm; else pm = sdata->u.mesh.nonpeer_pm; @@ -241,16 +241,16 @@ void ieee80211_mps_sta_status_update(struct sta_info *sta) * use peer-specific power mode if peering is established and the * peer's power mode is known */ - if (sta->plink_state == NL80211_PLINK_ESTAB && - sta->peer_pm != NL80211_MESH_POWER_UNKNOWN) - pm = sta->peer_pm; + if (sta->mesh->plink_state == NL80211_PLINK_ESTAB && + sta->mesh->peer_pm != NL80211_MESH_POWER_UNKNOWN) + pm = sta->mesh->peer_pm; else - pm = sta->nonpeer_pm; + pm = sta->mesh->nonpeer_pm; do_buffer = (pm != NL80211_MESH_POWER_ACTIVE); /* clear the MPSP flags for non-peers or active STA */ - if (sta->plink_state != NL80211_PLINK_ESTAB) { + if (sta->mesh->plink_state != NL80211_PLINK_ESTAB) { clear_sta_flag(sta, WLAN_STA_MPSP_OWNER); clear_sta_flag(sta, WLAN_STA_MPSP_RECIPIENT); } else if (!do_buffer) { @@ -296,13 +296,13 @@ static void mps_set_sta_peer_pm(struct sta_info *sta, pm = NL80211_MESH_POWER_ACTIVE; } - if (sta->peer_pm == pm) + if (sta->mesh->peer_pm == pm) return; mps_dbg(sta->sdata, "STA %pM enters mode %d\n", sta->sta.addr, pm); - sta->peer_pm = pm; + sta->mesh->peer_pm = pm; ieee80211_mps_sta_status_update(sta); } @@ -317,13 +317,13 @@ static void mps_set_sta_nonpeer_pm(struct sta_info *sta, else pm = NL80211_MESH_POWER_ACTIVE; - if (sta->nonpeer_pm == pm) + if (sta->mesh->nonpeer_pm == pm) return; mps_dbg(sta->sdata, "STA %pM sets non-peer mode to %d\n", sta->sta.addr, pm); - sta->nonpeer_pm = pm; + sta->mesh->nonpeer_pm = pm; ieee80211_mps_sta_status_update(sta); } @@ -552,7 +552,7 @@ void ieee80211_mpsp_trigger_process(u8 *qc, struct sta_info *sta, } else { if (eosp) clear_sta_flag(sta, WLAN_STA_MPSP_RECIPIENT); - else if (sta->local_pm != NL80211_MESH_POWER_ACTIVE) + else if (sta->mesh->local_pm != NL80211_MESH_POWER_ACTIVE) set_sta_flag(sta, WLAN_STA_MPSP_RECIPIENT); if (rspi && !test_and_set_sta_flag(sta, WLAN_STA_MPSP_OWNER)) @@ -577,9 +577,9 @@ void ieee80211_mps_frame_release(struct sta_info *sta, int ac, buffer_local = 0; bool has_buffered = false; - if (sta->plink_state == NL80211_PLINK_ESTAB) + if (sta->mesh->plink_state == NL80211_PLINK_ESTAB) has_buffered = ieee80211_check_tim(elems->tim, elems->tim_len, - sta->llid); + sta->mesh->aid); if (has_buffered) mps_dbg(sta->sdata, "%pM indicates buffered frames\n", @@ -598,7 +598,7 @@ void ieee80211_mps_frame_release(struct sta_info *sta, if (!has_buffered && !buffer_local) return; - if (sta->plink_state == NL80211_PLINK_ESTAB) + if (sta->mesh->plink_state == NL80211_PLINK_ESTAB) mpsp_trigger_send(sta, has_buffered, !buffer_local); else mps_frame_deliver(sta, 1); diff --git a/net/mac80211/mesh_sync.c b/net/mac80211/mesh_sync.c index 09625d6205c3..64bc22ad9496 100644 --- a/net/mac80211/mesh_sync.c +++ b/net/mac80211/mesh_sync.c @@ -127,14 +127,14 @@ static void mesh_sync_offset_rx_bcn_presp(struct ieee80211_sub_if_data *sdata, /* Timing offset calculation (see 13.13.2.2.2) */ t_t = le64_to_cpu(mgmt->u.beacon.timestamp); - sta->t_offset = t_t - t_r; + sta->mesh->t_offset = t_t - t_r; if (test_sta_flag(sta, WLAN_STA_TOFFSET_KNOWN)) { - s64 t_clockdrift = sta->t_offset_setpoint - sta->t_offset; + s64 t_clockdrift = sta->mesh->t_offset_setpoint - sta->mesh->t_offset; msync_dbg(sdata, - "STA %pM : sta->t_offset=%lld, sta->t_offset_setpoint=%lld, t_clockdrift=%lld\n", - sta->sta.addr, (long long) sta->t_offset, - (long long) sta->t_offset_setpoint, + "STA %pM : t_offset=%lld, t_offset_setpoint=%lld, t_clockdrift=%lld\n", + sta->sta.addr, (long long) sta->mesh->t_offset, + (long long) sta->mesh->t_offset_setpoint, (long long) t_clockdrift); if (t_clockdrift > TOFFSET_MAXIMUM_ADJUSTMENT || @@ -152,12 +152,12 @@ static void mesh_sync_offset_rx_bcn_presp(struct ieee80211_sub_if_data *sdata, ifmsh->sync_offset_clockdrift_max = t_clockdrift; spin_unlock_bh(&ifmsh->sync_offset_lock); } else { - sta->t_offset_setpoint = sta->t_offset - TOFFSET_SET_MARGIN; + sta->mesh->t_offset_setpoint = sta->mesh->t_offset - TOFFSET_SET_MARGIN; set_sta_flag(sta, WLAN_STA_TOFFSET_KNOWN); msync_dbg(sdata, - "STA %pM : offset was invalid, sta->t_offset=%lld\n", + "STA %pM : offset was invalid, t_offset=%lld\n", sta->sta.addr, - (long long) sta->t_offset); + (long long) sta->mesh->t_offset); } no_sync: diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c index 9b2cc278ac2a..cd7e55e08a23 100644 --- a/net/mac80211/mlme.c +++ b/net/mac80211/mlme.c @@ -6,6 +6,7 @@ * Copyright 2006-2007 Jiri Benc <jbenc@suse.cz> * Copyright 2007, Michael Wu <flamingice@sourmilk.net> * Copyright 2013-2014 Intel Mobile Communications GmbH + * Copyright (C) 2015 Intel Deutschland GmbH * * 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 @@ -538,11 +539,16 @@ static void ieee80211_add_ht_ie(struct ieee80211_sub_if_data *sdata, ieee80211_ie_build_ht_cap(pos, &ht_cap, cap); } +/* This function determines vht capability flags for the association + * and builds the IE. + * Note - the function may set the owner of the MU-MIMO capability + */ static void ieee80211_add_vht_ie(struct ieee80211_sub_if_data *sdata, struct sk_buff *skb, struct ieee80211_supported_band *sband, struct ieee80211_vht_cap *ap_vht_cap) { + struct ieee80211_local *local = sdata->local; u8 *pos; u32 cap; struct ieee80211_sta_vht_cap vht_cap; @@ -576,7 +582,34 @@ static void ieee80211_add_vht_ie(struct ieee80211_sub_if_data *sdata, */ if (!(ap_vht_cap->vht_cap_info & cpu_to_le32(IEEE80211_VHT_CAP_SU_BEAMFORMER_CAPABLE))) - cap &= ~IEEE80211_VHT_CAP_SU_BEAMFORMEE_CAPABLE; + cap &= ~(IEEE80211_VHT_CAP_SU_BEAMFORMEE_CAPABLE | + IEEE80211_VHT_CAP_MU_BEAMFORMEE_CAPABLE); + else if (!(ap_vht_cap->vht_cap_info & + cpu_to_le32(IEEE80211_VHT_CAP_MU_BEAMFORMER_CAPABLE))) + cap &= ~IEEE80211_VHT_CAP_MU_BEAMFORMEE_CAPABLE; + + /* + * If some other vif is using the MU-MIMO capablity we cannot associate + * using MU-MIMO - this will lead to contradictions in the group-id + * mechanism. + * Ownership is defined since association request, in order to avoid + * simultaneous associations with MU-MIMO. + */ + if (cap & IEEE80211_VHT_CAP_MU_BEAMFORMEE_CAPABLE) { + bool disable_mu_mimo = false; + struct ieee80211_sub_if_data *other; + + list_for_each_entry_rcu(other, &local->interfaces, list) { + if (other->flags & IEEE80211_SDATA_MU_MIMO_OWNER) { + disable_mu_mimo = true; + break; + } + } + if (disable_mu_mimo) + cap &= ~IEEE80211_VHT_CAP_MU_BEAMFORMEE_CAPABLE; + else + sdata->flags |= IEEE80211_SDATA_MU_MIMO_OWNER; + } mask = IEEE80211_VHT_CAP_BEAMFORMEE_STS_MASK; @@ -1096,24 +1129,6 @@ static void ieee80211_chswitch_timer(unsigned long data) ieee80211_queue_work(&sdata->local->hw, &sdata->u.mgd.chswitch_work); } -static void ieee80211_teardown_tdls_peers(struct ieee80211_sub_if_data *sdata) -{ - struct sta_info *sta; - u16 reason = WLAN_REASON_TDLS_TEARDOWN_UNSPECIFIED; - - rcu_read_lock(); - list_for_each_entry_rcu(sta, &sdata->local->sta_list, list) { - if (!sta->sta.tdls || sta->sdata != sdata || !sta->uploaded || - !test_sta_flag(sta, WLAN_STA_AUTHORIZED)) - continue; - - ieee80211_tdls_oper_request(&sdata->vif, sta->sta.addr, - NL80211_TDLS_TEARDOWN, reason, - GFP_ATOMIC); - } - rcu_read_unlock(); -} - static void ieee80211_sta_process_chanswitch(struct ieee80211_sub_if_data *sdata, u64 timestamp, u32 device_timestamp, @@ -2076,6 +2091,7 @@ static void ieee80211_set_disassoc(struct ieee80211_sub_if_data *sdata, memset(&ifmgd->ht_capa_mask, 0, sizeof(ifmgd->ht_capa_mask)); memset(&ifmgd->vht_capa, 0, sizeof(ifmgd->vht_capa)); memset(&ifmgd->vht_capa_mask, 0, sizeof(ifmgd->vht_capa_mask)); + sdata->flags &= ~IEEE80211_SDATA_MU_MIMO_OWNER; sdata->ap_power_level = IEEE80211_UNSET_POWER_LEVEL; @@ -2538,6 +2554,7 @@ static void ieee80211_destroy_assoc_data(struct ieee80211_sub_if_data *sdata, eth_zero_addr(sdata->u.mgd.bssid); ieee80211_bss_info_change_notify(sdata, BSS_CHANGED_BSSID); sdata->u.mgd.flags = 0; + sdata->flags &= ~IEEE80211_SDATA_MU_MIMO_OWNER; mutex_lock(&sdata->local->mtx); ieee80211_vif_release_channel(sdata); mutex_unlock(&sdata->local->mtx); @@ -3034,12 +3051,8 @@ static bool ieee80211_assoc_success(struct ieee80211_sub_if_data *sdata, rate_control_rate_init(sta); - if (ifmgd->flags & IEEE80211_STA_MFP_ENABLED) { + if (ifmgd->flags & IEEE80211_STA_MFP_ENABLED) set_sta_flag(sta, WLAN_STA_MFP); - sta->sta.mfp = true; - } else { - sta->sta.mfp = false; - } sta->sta.wme = elems.wmm_param && local->hw.queues >= IEEE80211_NUM_ACS; @@ -4254,6 +4267,8 @@ static int ieee80211_prep_channel(struct ieee80211_sub_if_data *sdata, struct ieee80211_supported_band *sband; struct cfg80211_chan_def chandef; int ret; + u32 i; + bool have_80mhz; sband = local->hw.wiphy->bands[cbss->channel->band]; @@ -4304,6 +4319,20 @@ static int ieee80211_prep_channel(struct ieee80211_sub_if_data *sdata, } } + /* Allow VHT if at least one channel on the sband supports 80 MHz */ + have_80mhz = false; + for (i = 0; i < sband->n_channels; i++) { + if (sband->channels[i].flags & (IEEE80211_CHAN_DISABLED | + IEEE80211_CHAN_NO_80MHZ)) + continue; + + have_80mhz = true; + break; + } + + if (!have_80mhz) + ifmgd->flags |= IEEE80211_STA_DISABLE_VHT; + ifmgd->flags |= ieee80211_determine_chantype(sdata, sband, cbss->channel, ht_cap, ht_oper, vht_oper, diff --git a/net/mac80211/ocb.c b/net/mac80211/ocb.c index 358d5f9d8207..573b81a1fb2d 100644 --- a/net/mac80211/ocb.c +++ b/net/mac80211/ocb.c @@ -179,7 +179,7 @@ int ieee80211_ocb_join(struct ieee80211_sub_if_data *sdata, { struct ieee80211_local *local = sdata->local; struct ieee80211_if_ocb *ifocb = &sdata->u.ocb; - u32 changed = BSS_CHANGED_OCB; + u32 changed = BSS_CHANGED_OCB | BSS_CHANGED_BSSID; int err; if (ifocb->joined == true) diff --git a/net/mac80211/rate.c b/net/mac80211/rate.c index fda33f961d83..9ce8883d5f44 100644 --- a/net/mac80211/rate.c +++ b/net/mac80211/rate.c @@ -29,6 +29,65 @@ module_param(ieee80211_default_rc_algo, charp, 0644); MODULE_PARM_DESC(ieee80211_default_rc_algo, "Default rate control algorithm for mac80211 to use"); +void rate_control_rate_init(struct sta_info *sta) +{ + struct ieee80211_local *local = sta->sdata->local; + struct rate_control_ref *ref = sta->rate_ctrl; + struct ieee80211_sta *ista = &sta->sta; + void *priv_sta = sta->rate_ctrl_priv; + struct ieee80211_supported_band *sband; + struct ieee80211_chanctx_conf *chanctx_conf; + + ieee80211_sta_set_rx_nss(sta); + + if (!ref) + return; + + rcu_read_lock(); + + chanctx_conf = rcu_dereference(sta->sdata->vif.chanctx_conf); + if (WARN_ON(!chanctx_conf)) { + rcu_read_unlock(); + return; + } + + sband = local->hw.wiphy->bands[chanctx_conf->def.chan->band]; + + spin_lock_bh(&sta->rate_ctrl_lock); + ref->ops->rate_init(ref->priv, sband, &chanctx_conf->def, ista, + priv_sta); + spin_unlock_bh(&sta->rate_ctrl_lock); + rcu_read_unlock(); + set_sta_flag(sta, WLAN_STA_RATE_CONTROL); +} + +void rate_control_rate_update(struct ieee80211_local *local, + struct ieee80211_supported_band *sband, + struct sta_info *sta, u32 changed) +{ + struct rate_control_ref *ref = local->rate_ctrl; + struct ieee80211_sta *ista = &sta->sta; + void *priv_sta = sta->rate_ctrl_priv; + struct ieee80211_chanctx_conf *chanctx_conf; + + if (ref && ref->ops->rate_update) { + rcu_read_lock(); + + chanctx_conf = rcu_dereference(sta->sdata->vif.chanctx_conf); + if (WARN_ON(!chanctx_conf)) { + rcu_read_unlock(); + return; + } + + spin_lock_bh(&sta->rate_ctrl_lock); + ref->ops->rate_update(ref->priv, sband, &chanctx_conf->def, + ista, priv_sta, changed); + spin_unlock_bh(&sta->rate_ctrl_lock); + rcu_read_unlock(); + } + drv_sta_rc_update(local, sta->sdata, &sta->sta, changed); +} + int ieee80211_rate_control_register(const struct rate_control_ops *ops) { struct rate_control_alg *alg; @@ -294,39 +353,37 @@ bool rate_control_send_low(struct ieee80211_sta *pubsta, } EXPORT_SYMBOL(rate_control_send_low); -static bool rate_idx_match_legacy_mask(struct ieee80211_tx_rate *rate, - int n_bitrates, u32 mask) +static bool rate_idx_match_legacy_mask(s8 *rate_idx, int n_bitrates, u32 mask) { int j; /* See whether the selected rate or anything below it is allowed. */ - for (j = rate->idx; j >= 0; j--) { + for (j = *rate_idx; j >= 0; j--) { if (mask & (1 << j)) { /* Okay, found a suitable rate. Use it. */ - rate->idx = j; + *rate_idx = j; return true; } } /* Try to find a higher rate that would be allowed */ - for (j = rate->idx + 1; j < n_bitrates; j++) { + for (j = *rate_idx + 1; j < n_bitrates; j++) { if (mask & (1 << j)) { /* Okay, found a suitable rate. Use it. */ - rate->idx = j; + *rate_idx = j; return true; } } return false; } -static bool rate_idx_match_mcs_mask(struct ieee80211_tx_rate *rate, - u8 mcs_mask[IEEE80211_HT_MCS_MASK_LEN]) +static bool rate_idx_match_mcs_mask(s8 *rate_idx, u8 *mcs_mask) { int i, j; int ridx, rbit; - ridx = rate->idx / 8; - rbit = rate->idx % 8; + ridx = *rate_idx / 8; + rbit = *rate_idx % 8; /* sanity check */ if (ridx < 0 || ridx >= IEEE80211_HT_MCS_MASK_LEN) @@ -336,20 +393,20 @@ static bool rate_idx_match_mcs_mask(struct ieee80211_tx_rate *rate, for (i = ridx; i >= 0; i--) { for (j = rbit; j >= 0; j--) if (mcs_mask[i] & BIT(j)) { - rate->idx = i * 8 + j; + *rate_idx = i * 8 + j; return true; } rbit = 7; } /* Try to find a higher rate that would be allowed */ - ridx = (rate->idx + 1) / 8; - rbit = (rate->idx + 1) % 8; + ridx = (*rate_idx + 1) / 8; + rbit = (*rate_idx + 1) % 8; for (i = ridx; i < IEEE80211_HT_MCS_MASK_LEN; i++) { for (j = rbit; j < 8; j++) if (mcs_mask[i] & BIT(j)) { - rate->idx = i * 8 + j; + *rate_idx = i * 8 + j; return true; } rbit = 0; @@ -357,37 +414,93 @@ static bool rate_idx_match_mcs_mask(struct ieee80211_tx_rate *rate, return false; } +static bool rate_idx_match_vht_mcs_mask(s8 *rate_idx, u16 *vht_mask) +{ + int i, j; + int ridx, rbit; + + ridx = *rate_idx >> 4; + rbit = *rate_idx & 0xf; + + if (ridx < 0 || ridx >= NL80211_VHT_NSS_MAX) + return false; + + /* See whether the selected rate or anything below it is allowed. */ + for (i = ridx; i >= 0; i--) { + for (j = rbit; j >= 0; j--) { + if (vht_mask[i] & BIT(j)) { + *rate_idx = (i << 4) | j; + return true; + } + } + rbit = 15; + } + + /* Try to find a higher rate that would be allowed */ + ridx = (*rate_idx + 1) >> 4; + rbit = (*rate_idx + 1) & 0xf; + for (i = ridx; i < NL80211_VHT_NSS_MAX; i++) { + for (j = rbit; j < 16; j++) { + if (vht_mask[i] & BIT(j)) { + *rate_idx = (i << 4) | j; + return true; + } + } + rbit = 0; + } + return false; +} -static void rate_idx_match_mask(struct ieee80211_tx_rate *rate, +static void rate_idx_match_mask(s8 *rate_idx, u16 *rate_flags, struct ieee80211_supported_band *sband, enum nl80211_chan_width chan_width, u32 mask, - u8 mcs_mask[IEEE80211_HT_MCS_MASK_LEN]) + u8 mcs_mask[IEEE80211_HT_MCS_MASK_LEN], + u16 vht_mask[NL80211_VHT_NSS_MAX]) { - struct ieee80211_tx_rate alt_rate; + if (*rate_flags & IEEE80211_TX_RC_VHT_MCS) { + /* handle VHT rates */ + if (rate_idx_match_vht_mcs_mask(rate_idx, vht_mask)) + return; + + *rate_idx = 0; + /* keep protection flags */ + *rate_flags &= (IEEE80211_TX_RC_USE_RTS_CTS | + IEEE80211_TX_RC_USE_CTS_PROTECT | + IEEE80211_TX_RC_USE_SHORT_PREAMBLE); + + *rate_flags |= IEEE80211_TX_RC_MCS; + if (chan_width == NL80211_CHAN_WIDTH_40) + *rate_flags |= IEEE80211_TX_RC_40_MHZ_WIDTH; - /* handle HT rates */ - if (rate->flags & IEEE80211_TX_RC_MCS) { - if (rate_idx_match_mcs_mask(rate, mcs_mask)) + if (rate_idx_match_mcs_mask(rate_idx, mcs_mask)) return; /* also try the legacy rates. */ - alt_rate.idx = 0; + *rate_flags &= ~(IEEE80211_TX_RC_MCS | + IEEE80211_TX_RC_40_MHZ_WIDTH); + if (rate_idx_match_legacy_mask(rate_idx, sband->n_bitrates, + mask)) + return; + } else if (*rate_flags & IEEE80211_TX_RC_MCS) { + /* handle HT rates */ + if (rate_idx_match_mcs_mask(rate_idx, mcs_mask)) + return; + + /* also try the legacy rates. */ + *rate_idx = 0; /* keep protection flags */ - alt_rate.flags = rate->flags & - (IEEE80211_TX_RC_USE_RTS_CTS | - IEEE80211_TX_RC_USE_CTS_PROTECT | - IEEE80211_TX_RC_USE_SHORT_PREAMBLE); - alt_rate.count = rate->count; - if (rate_idx_match_legacy_mask(&alt_rate, - sband->n_bitrates, mask)) { - *rate = alt_rate; + *rate_flags &= (IEEE80211_TX_RC_USE_RTS_CTS | + IEEE80211_TX_RC_USE_CTS_PROTECT | + IEEE80211_TX_RC_USE_SHORT_PREAMBLE); + if (rate_idx_match_legacy_mask(rate_idx, sband->n_bitrates, + mask)) return; - } - } else if (!(rate->flags & IEEE80211_TX_RC_VHT_MCS)) { + } else { /* handle legacy rates */ - if (rate_idx_match_legacy_mask(rate, sband->n_bitrates, mask)) + if (rate_idx_match_legacy_mask(rate_idx, sband->n_bitrates, + mask)) return; /* if HT BSS, and we handle a data frame, also try HT rates */ @@ -400,23 +513,19 @@ static void rate_idx_match_mask(struct ieee80211_tx_rate *rate, break; } - alt_rate.idx = 0; + *rate_idx = 0; /* keep protection flags */ - alt_rate.flags = rate->flags & - (IEEE80211_TX_RC_USE_RTS_CTS | - IEEE80211_TX_RC_USE_CTS_PROTECT | - IEEE80211_TX_RC_USE_SHORT_PREAMBLE); - alt_rate.count = rate->count; + *rate_flags &= (IEEE80211_TX_RC_USE_RTS_CTS | + IEEE80211_TX_RC_USE_CTS_PROTECT | + IEEE80211_TX_RC_USE_SHORT_PREAMBLE); - alt_rate.flags |= IEEE80211_TX_RC_MCS; + *rate_flags |= IEEE80211_TX_RC_MCS; if (chan_width == NL80211_CHAN_WIDTH_40) - alt_rate.flags |= IEEE80211_TX_RC_40_MHZ_WIDTH; + *rate_flags |= IEEE80211_TX_RC_40_MHZ_WIDTH; - if (rate_idx_match_mcs_mask(&alt_rate, mcs_mask)) { - *rate = alt_rate; + if (rate_idx_match_mcs_mask(rate_idx, mcs_mask)) return; - } } /* @@ -569,18 +678,92 @@ static void rate_control_fill_sta_table(struct ieee80211_sta *sta, } } +static bool rate_control_cap_mask(struct ieee80211_sub_if_data *sdata, + struct ieee80211_supported_band *sband, + struct ieee80211_sta *sta, u32 *mask, + u8 mcs_mask[IEEE80211_HT_MCS_MASK_LEN], + u16 vht_mask[NL80211_VHT_NSS_MAX]) +{ + u32 i, flags; + + *mask = sdata->rc_rateidx_mask[sband->band]; + flags = ieee80211_chandef_rate_flags(&sdata->vif.bss_conf.chandef); + for (i = 0; i < sband->n_bitrates; i++) { + if ((flags & sband->bitrates[i].flags) != flags) + *mask &= ~BIT(i); + } + + if (*mask == (1 << sband->n_bitrates) - 1 && + !sdata->rc_has_mcs_mask[sband->band] && + !sdata->rc_has_vht_mcs_mask[sband->band]) + return false; + + if (sdata->rc_has_mcs_mask[sband->band]) + memcpy(mcs_mask, sdata->rc_rateidx_mcs_mask[sband->band], + IEEE80211_HT_MCS_MASK_LEN); + else + memset(mcs_mask, 0xff, IEEE80211_HT_MCS_MASK_LEN); + + if (sdata->rc_has_vht_mcs_mask[sband->band]) + memcpy(vht_mask, sdata->rc_rateidx_vht_mcs_mask[sband->band], + sizeof(u16) * NL80211_VHT_NSS_MAX); + else + memset(vht_mask, 0xff, sizeof(u16) * NL80211_VHT_NSS_MAX); + + if (sta) { + __le16 sta_vht_cap; + u16 sta_vht_mask[NL80211_VHT_NSS_MAX]; + + /* Filter out rates that the STA does not support */ + *mask &= sta->supp_rates[sband->band]; + for (i = 0; i < IEEE80211_HT_MCS_MASK_LEN; i++) + mcs_mask[i] &= sta->ht_cap.mcs.rx_mask[i]; + + sta_vht_cap = sta->vht_cap.vht_mcs.rx_mcs_map; + ieee80211_get_vht_mask_from_cap(sta_vht_cap, sta_vht_mask); + for (i = 0; i < NL80211_VHT_NSS_MAX; i++) + vht_mask[i] &= sta_vht_mask[i]; + } + + return true; +} + +static void +rate_control_apply_mask_ratetbl(struct sta_info *sta, + struct ieee80211_supported_band *sband, + struct ieee80211_sta_rates *rates) +{ + int i; + u32 mask; + u8 mcs_mask[IEEE80211_HT_MCS_MASK_LEN]; + u16 vht_mask[NL80211_VHT_NSS_MAX]; + enum nl80211_chan_width chan_width; + + if (!rate_control_cap_mask(sta->sdata, sband, &sta->sta, &mask, + mcs_mask, vht_mask)) + return; + + chan_width = sta->sdata->vif.bss_conf.chandef.width; + for (i = 0; i < IEEE80211_TX_RATE_TABLE_SIZE; i++) { + if (rates->rate[i].idx < 0) + break; + + rate_idx_match_mask(&rates->rate[i].idx, &rates->rate[i].flags, + sband, chan_width, mask, mcs_mask, + vht_mask); + } +} + static void rate_control_apply_mask(struct ieee80211_sub_if_data *sdata, struct ieee80211_sta *sta, struct ieee80211_supported_band *sband, - struct ieee80211_tx_info *info, struct ieee80211_tx_rate *rates, int max_rates) { enum nl80211_chan_width chan_width; u8 mcs_mask[IEEE80211_HT_MCS_MASK_LEN]; - bool has_mcs_mask; u32 mask; - u32 rate_flags; + u16 rate_flags, vht_mask[NL80211_VHT_NSS_MAX]; int i; /* @@ -588,30 +771,10 @@ static void rate_control_apply_mask(struct ieee80211_sub_if_data *sdata, * default mask (allow all rates) is used to save some processing for * the common case. */ - mask = sdata->rc_rateidx_mask[info->band]; - has_mcs_mask = sdata->rc_has_mcs_mask[info->band]; - rate_flags = - ieee80211_chandef_rate_flags(&sdata->vif.bss_conf.chandef); - for (i = 0; i < sband->n_bitrates; i++) - if ((rate_flags & sband->bitrates[i].flags) != rate_flags) - mask &= ~BIT(i); - - if (mask == (1 << sband->n_bitrates) - 1 && !has_mcs_mask) + if (!rate_control_cap_mask(sdata, sband, sta, &mask, mcs_mask, + vht_mask)) return; - if (has_mcs_mask) - memcpy(mcs_mask, sdata->rc_rateidx_mcs_mask[info->band], - sizeof(mcs_mask)); - else - memset(mcs_mask, 0xff, sizeof(mcs_mask)); - - if (sta) { - /* Filter out rates that the STA does not support */ - mask &= sta->supp_rates[info->band]; - for (i = 0; i < sizeof(mcs_mask); i++) - mcs_mask[i] &= sta->ht_cap.mcs.rx_mask[i]; - } - /* * Make sure the rate index selected for each TX rate is * included in the configured mask and change the rate indexes @@ -623,8 +786,10 @@ static void rate_control_apply_mask(struct ieee80211_sub_if_data *sdata, if (rates[i].idx < 0) break; - rate_idx_match_mask(&rates[i], sband, chan_width, mask, - mcs_mask); + rate_flags = rates[i].flags; + rate_idx_match_mask(&rates[i].idx, &rate_flags, sband, + chan_width, mask, mcs_mask, vht_mask); + rates[i].flags = rate_flags; } } @@ -648,7 +813,7 @@ void ieee80211_get_tx_rates(struct ieee80211_vif *vif, sband = sdata->local->hw.wiphy->bands[info->band]; if (ieee80211_is_data(hdr->frame_control)) - rate_control_apply_mask(sdata, sta, sband, info, dest, max_rates); + rate_control_apply_mask(sdata, sta, sband, dest, max_rates); if (dest[0].idx < 0) __rate_control_send_low(&sdata->local->hw, sband, sta, info, @@ -705,7 +870,10 @@ int rate_control_set_rates(struct ieee80211_hw *hw, { struct sta_info *sta = container_of(pubsta, struct sta_info, sta); struct ieee80211_sta_rates *old; + struct ieee80211_supported_band *sband; + sband = hw->wiphy->bands[ieee80211_get_sdata_band(sta->sdata)]; + rate_control_apply_mask_ratetbl(sta, sband, rates); /* * mac80211 guarantees that this function will not be called * concurrently, so the following RCU access is safe, even without diff --git a/net/mac80211/rate.h b/net/mac80211/rate.h index 25c9be5dd7fd..624fe5b81615 100644 --- a/net/mac80211/rate.h +++ b/net/mac80211/rate.h @@ -71,64 +71,10 @@ rate_control_tx_status_noskb(struct ieee80211_local *local, spin_unlock_bh(&sta->rate_ctrl_lock); } -static inline void rate_control_rate_init(struct sta_info *sta) -{ - struct ieee80211_local *local = sta->sdata->local; - struct rate_control_ref *ref = sta->rate_ctrl; - struct ieee80211_sta *ista = &sta->sta; - void *priv_sta = sta->rate_ctrl_priv; - struct ieee80211_supported_band *sband; - struct ieee80211_chanctx_conf *chanctx_conf; - - ieee80211_sta_set_rx_nss(sta); - - if (!ref) - return; - - rcu_read_lock(); - - chanctx_conf = rcu_dereference(sta->sdata->vif.chanctx_conf); - if (WARN_ON(!chanctx_conf)) { - rcu_read_unlock(); - return; - } - - sband = local->hw.wiphy->bands[chanctx_conf->def.chan->band]; - - spin_lock_bh(&sta->rate_ctrl_lock); - ref->ops->rate_init(ref->priv, sband, &chanctx_conf->def, ista, - priv_sta); - spin_unlock_bh(&sta->rate_ctrl_lock); - rcu_read_unlock(); - set_sta_flag(sta, WLAN_STA_RATE_CONTROL); -} - -static inline void rate_control_rate_update(struct ieee80211_local *local, +void rate_control_rate_init(struct sta_info *sta); +void rate_control_rate_update(struct ieee80211_local *local, struct ieee80211_supported_band *sband, - struct sta_info *sta, u32 changed) -{ - struct rate_control_ref *ref = local->rate_ctrl; - struct ieee80211_sta *ista = &sta->sta; - void *priv_sta = sta->rate_ctrl_priv; - struct ieee80211_chanctx_conf *chanctx_conf; - - if (ref && ref->ops->rate_update) { - rcu_read_lock(); - - chanctx_conf = rcu_dereference(sta->sdata->vif.chanctx_conf); - if (WARN_ON(!chanctx_conf)) { - rcu_read_unlock(); - return; - } - - spin_lock_bh(&sta->rate_ctrl_lock); - ref->ops->rate_update(ref->priv, sband, &chanctx_conf->def, - ista, priv_sta, changed); - spin_unlock_bh(&sta->rate_ctrl_lock); - rcu_read_unlock(); - } - drv_sta_rc_update(local, sta->sdata, &sta->sta, changed); -} + struct sta_info *sta, u32 changed); static inline void *rate_control_alloc_sta(struct rate_control_ref *ref, struct sta_info *sta, gfp_t gfp) diff --git a/net/mac80211/rc80211_minstrel_ht.c b/net/mac80211/rc80211_minstrel_ht.c index 543b67233535..3928dbd24e25 100644 --- a/net/mac80211/rc80211_minstrel_ht.c +++ b/net/mac80211/rc80211_minstrel_ht.c @@ -867,7 +867,13 @@ minstrel_ht_set_rate(struct minstrel_priv *mp, struct minstrel_ht_sta *mi, else idx = index % MCS_GROUP_RATES + (group->streams - 1) * 8; - if (offset > 0) { + /* enable RTS/CTS if needed: + * - if station is in dynamic SMPS (and streams > 1) + * - for fallback rates, to increase chances of getting through + */ + if (offset > 0 && + (mi->sta->smps_mode == IEEE80211_SMPS_DYNAMIC && + group->streams > 1)) { ratetbl->rate[offset].count = ratetbl->rate[offset].count_rts; flags |= IEEE80211_TX_RC_USE_RTS_CTS; } diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c index 5dae166cb7f5..5bc0b88d9eb1 100644 --- a/net/mac80211/rx.c +++ b/net/mac80211/rx.c @@ -42,6 +42,51 @@ static inline void ieee80211_rx_stats(struct net_device *dev, u32 len) u64_stats_update_end(&tstats->syncp); } +static u8 *ieee80211_get_bssid(struct ieee80211_hdr *hdr, size_t len, + enum nl80211_iftype type) +{ + __le16 fc = hdr->frame_control; + + if (ieee80211_is_data(fc)) { + if (len < 24) /* drop incorrect hdr len (data) */ + return NULL; + + if (ieee80211_has_a4(fc)) + return NULL; + if (ieee80211_has_tods(fc)) + return hdr->addr1; + if (ieee80211_has_fromds(fc)) + return hdr->addr2; + + return hdr->addr3; + } + + if (ieee80211_is_mgmt(fc)) { + if (len < 24) /* drop incorrect hdr len (mgmt) */ + return NULL; + return hdr->addr3; + } + + if (ieee80211_is_ctl(fc)) { + if (ieee80211_is_pspoll(fc)) + return hdr->addr1; + + if (ieee80211_is_back_req(fc)) { + switch (type) { + case NL80211_IFTYPE_STATION: + return hdr->addr2; + case NL80211_IFTYPE_AP: + case NL80211_IFTYPE_AP_VLAN: + return hdr->addr1; + default: + break; /* fall through to the return */ + } + } + } + + return NULL; +} + /* * monitor mode reception * @@ -77,8 +122,7 @@ static inline bool should_drop_frame(struct sk_buff *skb, int present_fcs_len, hdr = (void *)(skb->data + rtap_vendor_space); if (status->flag & (RX_FLAG_FAILED_FCS_CRC | - RX_FLAG_FAILED_PLCP_CRC | - RX_FLAG_AMPDU_IS_ZEROLEN)) + RX_FLAG_FAILED_PLCP_CRC)) return true; if (unlikely(skb->len < 16 + present_fcs_len + rtap_vendor_space)) @@ -346,10 +390,6 @@ ieee80211_add_rx_radiotap_header(struct ieee80211_local *local, cpu_to_le32(1 << IEEE80211_RADIOTAP_AMPDU_STATUS); put_unaligned_le32(status->ampdu_reference, pos); pos += 4; - if (status->flag & RX_FLAG_AMPDU_REPORT_ZEROLEN) - flags |= IEEE80211_RADIOTAP_AMPDU_REPORT_ZEROLEN; - if (status->flag & RX_FLAG_AMPDU_IS_ZEROLEN) - flags |= IEEE80211_RADIOTAP_AMPDU_IS_ZEROLEN; if (status->flag & RX_FLAG_AMPDU_LAST_KNOWN) flags |= IEEE80211_RADIOTAP_AMPDU_LAST_KNOWN; if (status->flag & RX_FLAG_AMPDU_IS_LAST) @@ -1093,11 +1133,6 @@ ieee80211_rx_h_check(struct ieee80211_rx_data *rx) { struct ieee80211_hdr *hdr = (struct ieee80211_hdr *)rx->skb->data; - if (unlikely(rx->skb->len < 16)) { - I802_DEBUG_INC(rx->local->rx_handlers_drop_short); - return RX_DROP_MONITOR; - } - /* Drop disallowed frame classes based on STA auth/assoc state; * IEEE 802.11, Chap 5.5. * @@ -1240,22 +1275,22 @@ static void sta_ps_end(struct sta_info *sta) ieee80211_sta_ps_deliver_wakeup(sta); } -int ieee80211_sta_ps_transition(struct ieee80211_sta *sta, bool start) +int ieee80211_sta_ps_transition(struct ieee80211_sta *pubsta, bool start) { - struct sta_info *sta_inf = container_of(sta, struct sta_info, sta); + struct sta_info *sta = container_of(pubsta, struct sta_info, sta); bool in_ps; - WARN_ON(!ieee80211_hw_check(&sta_inf->local->hw, AP_LINK_PS)); + WARN_ON(!ieee80211_hw_check(&sta->local->hw, AP_LINK_PS)); /* Don't let the same PS state be set twice */ - in_ps = test_sta_flag(sta_inf, WLAN_STA_PS_STA); + in_ps = test_sta_flag(sta, WLAN_STA_PS_STA); if ((start && in_ps) || (!start && !in_ps)) return -EINVAL; if (start) - sta_ps_start(sta_inf); + sta_ps_start(sta); else - sta_ps_end(sta_inf); + sta_ps_end(sta); return 0; } @@ -1393,7 +1428,7 @@ ieee80211_rx_h_sta_process(struct ieee80211_rx_data *rx) sta->rx_bytes += rx->skb->len; if (!(status->flag & RX_FLAG_NO_SIGNAL_VAL)) { sta->last_signal = status->signal; - ewma_add(&sta->avg_signal, -status->signal); + ewma_signal_add(&sta->avg_signal, -status->signal); } if (status->chains) { @@ -1405,7 +1440,7 @@ ieee80211_rx_h_sta_process(struct ieee80211_rx_data *rx) continue; sta->chain_signal_last[i] = signal; - ewma_add(&sta->chain_signal_avg[i], -signal); + ewma_signal_add(&sta->chain_signal_avg[i], -signal); } } @@ -1647,7 +1682,6 @@ ieee80211_rx_h_decrypt(struct ieee80211_rx_data *rx) if (unlikely(rx->key->flags & KEY_FLAG_TAINTED)) return RX_DROP_MONITOR; - rx->key->tx_rx_count++; /* TODO: add threshold stuff again */ } else { return RX_DROP_MONITOR; @@ -1883,7 +1917,6 @@ ieee80211_rx_h_defragment(struct ieee80211_rx_data *rx) /* Complete frame has been reassembled - process it now */ status = IEEE80211_SKB_RXCB(rx->skb); - status->rx_flags |= IEEE80211_RX_FRAGMENTED; out: ieee80211_led_rx(rx->local); @@ -2108,9 +2141,8 @@ ieee80211_deliver_skb(struct ieee80211_rx_data *rx) /* deliver to local stack */ skb->protocol = eth_type_trans(skb, dev); memset(skb->cb, 0, sizeof(skb->cb)); - if (!(rx->flags & IEEE80211_RX_REORDER_TIMER) && - rx->local->napi) - napi_gro_receive(rx->local->napi, skb); + if (rx->napi) + napi_gro_receive(rx->napi, skb); else netif_receive_skb(skb); } @@ -2378,9 +2410,8 @@ ieee80211_rx_h_data(struct ieee80211_rx_data *rx) tf->category == WLAN_CATEGORY_TDLS && (tf->action_code == WLAN_TDLS_CHANNEL_SWITCH_REQUEST || tf->action_code == WLAN_TDLS_CHANNEL_SWITCH_RESPONSE)) { - rx->skb->pkt_type = IEEE80211_SDATA_QUEUE_TDLS_CHSW; - skb_queue_tail(&sdata->skb_queue, rx->skb); - ieee80211_queue_work(&rx->local->hw, &sdata->work); + skb_queue_tail(&local->skb_queue_tdls_chsw, rx->skb); + schedule_work(&local->tdls_chsw_work); if (rx->sta) rx->sta->rx_packets++; @@ -3004,7 +3035,6 @@ ieee80211_rx_h_mgmt(struct ieee80211_rx_data *rx) return RX_QUEUED; } -/* TODO: use IEEE80211_RX_FRAGMENTED */ static void ieee80211_rx_cooked_monitor(struct ieee80211_rx_data *rx, struct ieee80211_rate *rate) { @@ -3216,7 +3246,7 @@ void ieee80211_release_reorder_timeout(struct sta_info *sta, int tid) /* This is OK -- must be QoS data frame */ .security_idx = tid, .seqno_idx = tid, - .flags = IEEE80211_RX_REORDER_TIMER, + .napi = NULL, /* must be NULL to not have races */ }; struct tid_ampdu_rx *tid_agg_rx; @@ -3286,7 +3316,7 @@ static bool ieee80211_accept_frame(struct ieee80211_rx_data *rx) case NL80211_IFTYPE_OCB: if (!bssid) return false; - if (ieee80211_is_beacon(hdr->frame_control)) + if (!ieee80211_is_data_present(hdr->frame_control)) return false; if (!is_broadcast_ether_addr(bssid)) return false; @@ -3393,7 +3423,8 @@ static bool ieee80211_prepare_and_rx_handle(struct ieee80211_rx_data *rx, * be called with rcu_read_lock protection. */ static void __ieee80211_rx_handle_packet(struct ieee80211_hw *hw, - struct sk_buff *skb) + struct sk_buff *skb, + struct napi_struct *napi) { struct ieee80211_local *local = hw_to_local(hw); struct ieee80211_sub_if_data *sdata; @@ -3409,6 +3440,7 @@ static void __ieee80211_rx_handle_packet(struct ieee80211_hw *hw, memset(&rx, 0, sizeof(rx)); rx.skb = skb; rx.local = local; + rx.napi = napi; if (ieee80211_is_data(fc) || ieee80211_is_mgmt(fc)) I802_DEBUG_INC(local->dot11ReceivedFragmentCount); @@ -3510,7 +3542,8 @@ static void __ieee80211_rx_handle_packet(struct ieee80211_hw *hw, * This is the receive path handler. It is called by a low level driver when an * 802.11 MPDU is received from the hardware. */ -void ieee80211_rx(struct ieee80211_hw *hw, struct sk_buff *skb) +void ieee80211_rx_napi(struct ieee80211_hw *hw, struct sk_buff *skb, + struct napi_struct *napi) { struct ieee80211_local *local = hw_to_local(hw); struct ieee80211_rate *rate = NULL; @@ -3609,7 +3642,7 @@ void ieee80211_rx(struct ieee80211_hw *hw, struct sk_buff *skb) ieee80211_tpt_led_trig_rx(local, ((struct ieee80211_hdr *)skb->data)->frame_control, skb->len); - __ieee80211_rx_handle_packet(hw, skb); + __ieee80211_rx_handle_packet(hw, skb, napi); rcu_read_unlock(); @@ -3617,7 +3650,7 @@ void ieee80211_rx(struct ieee80211_hw *hw, struct sk_buff *skb) drop: kfree_skb(skb); } -EXPORT_SYMBOL(ieee80211_rx); +EXPORT_SYMBOL(ieee80211_rx_napi); /* This is a version of the rx handler that can be called from hard irq * context. Post the skb on the queue and schedule the tasklet */ diff --git a/net/mac80211/sta_info.c b/net/mac80211/sta_info.c index 666ddac3c87c..64f1936350c6 100644 --- a/net/mac80211/sta_info.c +++ b/net/mac80211/sta_info.c @@ -68,7 +68,7 @@ static const struct rhashtable_params sta_rht_params = { .nelem_hint = 3, /* start small */ .automatic_shrinking = true, .head_offset = offsetof(struct sta_info, hash_node), - .key_offset = offsetof(struct sta_info, sta.addr), + .key_offset = offsetof(struct sta_info, addr), .key_len = ETH_ALEN, .hashfn = sta_addr_hash, .max_size = CONFIG_MAC80211_STA_HASH_MAX_SIZE, @@ -249,6 +249,9 @@ void sta_info_free(struct ieee80211_local *local, struct sta_info *sta) if (sta->sta.txq[0]) kfree(to_txq_info(sta->sta.txq[0])); kfree(rcu_dereference_raw(sta->sta.rates)); +#ifdef CONFIG_MAC80211_MESH + kfree(sta->mesh); +#endif kfree(sta); } @@ -313,13 +316,19 @@ struct sta_info *sta_info_alloc(struct ieee80211_sub_if_data *sdata, INIT_WORK(&sta->ampdu_mlme.work, ieee80211_ba_session_work); mutex_init(&sta->ampdu_mlme.mtx); #ifdef CONFIG_MAC80211_MESH - spin_lock_init(&sta->plink_lock); - if (ieee80211_vif_is_mesh(&sdata->vif) && - !sdata->u.mesh.user_mpm) - init_timer(&sta->plink_timer); - sta->nonpeer_pm = NL80211_MESH_POWER_ACTIVE; + if (ieee80211_vif_is_mesh(&sdata->vif)) { + sta->mesh = kzalloc(sizeof(*sta->mesh), gfp); + if (!sta->mesh) + goto free; + spin_lock_init(&sta->mesh->plink_lock); + if (ieee80211_vif_is_mesh(&sdata->vif) && + !sdata->u.mesh.user_mpm) + init_timer(&sta->mesh->plink_timer); + sta->mesh->nonpeer_pm = NL80211_MESH_POWER_ACTIVE; + } #endif + memcpy(sta->addr, addr, ETH_ALEN); memcpy(sta->sta.addr, addr, ETH_ALEN); sta->local = local; sta->sdata = sdata; @@ -332,9 +341,9 @@ struct sta_info *sta_info_alloc(struct ieee80211_sub_if_data *sdata, ktime_get_ts(&uptime); sta->last_connected = uptime.tv_sec; - ewma_init(&sta->avg_signal, 1024, 8); + ewma_signal_init(&sta->avg_signal); for (i = 0; i < ARRAY_SIZE(sta->chain_signal_avg); i++) - ewma_init(&sta->chain_signal_avg[i], 1024, 8); + ewma_signal_init(&sta->chain_signal_avg[i]); if (local->ops->wake_tx_queue) { void *txq_data; @@ -405,6 +414,9 @@ free_txq: if (sta->sta.txq[0]) kfree(to_txq_info(sta->sta.txq[0])); free: +#ifdef CONFIG_MAC80211_MESH + kfree(sta->mesh); +#endif kfree(sta); return NULL; } @@ -623,7 +635,7 @@ static void __sta_info_recalc_tim(struct sta_info *sta, bool ignore_pending) bool indicate_tim = false; u8 ignore_for_tim = sta->sta.uapsd_queues; int ac; - u16 id; + u16 id = sta->sta.aid; if (sta->sdata->vif.type == NL80211_IFTYPE_AP || sta->sdata->vif.type == NL80211_IFTYPE_AP_VLAN) { @@ -631,12 +643,9 @@ static void __sta_info_recalc_tim(struct sta_info *sta, bool ignore_pending) return; ps = &sta->sdata->bss->ps; - id = sta->sta.aid; #ifdef CONFIG_MAC80211_MESH } else if (ieee80211_vif_is_mesh(&sta->sdata->vif)) { ps = &sta->sdata->u.mesh.ps; - /* TIM map only for 1 <= PLID <= IEEE80211_MAX_AID */ - id = sta->plid % (IEEE80211_MAX_AID + 1); #endif } else { return; @@ -1887,7 +1896,8 @@ void sta_set_sinfo(struct sta_info *sta, struct station_info *sinfo) } if (!(sinfo->filled & BIT(NL80211_STA_INFO_SIGNAL_AVG))) { - sinfo->signal_avg = (s8) -ewma_read(&sta->avg_signal); + sinfo->signal_avg = + (s8) -ewma_signal_read(&sta->avg_signal); sinfo->filled |= BIT(NL80211_STA_INFO_SIGNAL_AVG); } } @@ -1902,7 +1912,7 @@ void sta_set_sinfo(struct sta_info *sta, struct station_info *sinfo) for (i = 0; i < ARRAY_SIZE(sinfo->chain_signal); i++) { sinfo->chain_signal[i] = sta->chain_signal_last[i]; sinfo->chain_signal_avg[i] = - (s8) -ewma_read(&sta->chain_signal_avg[i]); + (s8) -ewma_signal_read(&sta->chain_signal_avg[i]); } } @@ -1956,16 +1966,16 @@ void sta_set_sinfo(struct sta_info *sta, struct station_info *sinfo) BIT(NL80211_STA_INFO_PEER_PM) | BIT(NL80211_STA_INFO_NONPEER_PM); - sinfo->llid = sta->llid; - sinfo->plid = sta->plid; - sinfo->plink_state = sta->plink_state; + sinfo->llid = sta->mesh->llid; + sinfo->plid = sta->mesh->plid; + sinfo->plink_state = sta->mesh->plink_state; if (test_sta_flag(sta, WLAN_STA_TOFFSET_KNOWN)) { sinfo->filled |= BIT(NL80211_STA_INFO_T_OFFSET); - sinfo->t_offset = sta->t_offset; + sinfo->t_offset = sta->mesh->t_offset; } - sinfo->local_pm = sta->local_pm; - sinfo->peer_pm = sta->peer_pm; - sinfo->nonpeer_pm = sta->nonpeer_pm; + sinfo->local_pm = sta->mesh->local_pm; + sinfo->peer_pm = sta->mesh->peer_pm; + sinfo->nonpeer_pm = sta->mesh->nonpeer_pm; #endif } diff --git a/net/mac80211/sta_info.h b/net/mac80211/sta_info.h index 226f8ca47ad6..b087c71ff7fe 100644 --- a/net/mac80211/sta_info.h +++ b/net/mac80211/sta_info.h @@ -53,6 +53,8 @@ * @WLAN_STA_TDLS_CHAN_SWITCH: This TDLS peer supports TDLS channel-switching * @WLAN_STA_TDLS_OFF_CHANNEL: The local STA is currently off-channel with this * TDLS peer + * @WLAN_STA_TDLS_WIDER_BW: This TDLS peer supports working on a wider bw on + * the BSS base channel. * @WLAN_STA_UAPSD: Station requested unscheduled SP while driver was * keeping station in power-save mode, reply when the driver * unblocks the station. @@ -84,6 +86,7 @@ enum ieee80211_sta_info_flags { WLAN_STA_TDLS_INITIATOR, WLAN_STA_TDLS_CHAN_SWITCH, WLAN_STA_TDLS_OFF_CHANNEL, + WLAN_STA_TDLS_WIDER_BW, WLAN_STA_UAPSD, WLAN_STA_SP, WLAN_STA_4ADDR_EVENT, @@ -270,6 +273,56 @@ struct ieee80211_fast_tx { }; /** + * struct mesh_sta - mesh STA information + * @plink_lock: serialize access to plink fields + * @llid: Local link ID + * @plid: Peer link ID + * @aid: local aid supplied by peer + * @reason: Cancel reason on PLINK_HOLDING state + * @plink_retries: Retries in establishment + * @plink_state: peer link state + * @plink_timeout: timeout of peer link + * @plink_timer: peer link watch timer + * @t_offset: timing offset relative to this host + * @t_offset_setpoint: reference timing offset of this sta to be used when + * calculating clockdrift + * @local_pm: local link-specific power save mode + * @peer_pm: peer-specific power save mode towards local STA + * @nonpeer_pm: STA power save mode towards non-peer neighbors + * @processed_beacon: set to true after peer rates and capabilities are + * processed + * @fail_avg: moving percentage of failed MSDUs + */ +struct mesh_sta { + struct timer_list plink_timer; + + s64 t_offset; + s64 t_offset_setpoint; + + spinlock_t plink_lock; + u16 llid; + u16 plid; + u16 aid; + u16 reason; + u8 plink_retries; + + bool processed_beacon; + + enum nl80211_plink_state plink_state; + u32 plink_timeout; + + /* mesh power save */ + enum nl80211_mesh_power_mode local_pm; + enum nl80211_mesh_power_mode peer_pm; + enum nl80211_mesh_power_mode nonpeer_pm; + + /* moving percentage of failed MSDUs */ + unsigned int fail_avg; +}; + +DECLARE_EWMA(signal, 1024, 8) + +/** * struct sta_info - STA information * * This structure collects information about a station that @@ -278,12 +331,13 @@ struct ieee80211_fast_tx { * @list: global linked list entry * @free_list: list entry for keeping track of stations to free * @hash_node: hash node for rhashtable + * @addr: station's MAC address - duplicated from public part to + * let the hash table work with just a single cacheline * @local: pointer to the global information * @sdata: virtual interface this station belongs to * @ptk: peer keys negotiated with this station, if any * @ptk_idx: last installed peer key index * @gtk: group keys negotiated with this station, if any - * @gtk_idx: last installed group key index * @rate_ctrl: rate control algorithm reference * @rate_ctrl_lock: spinlock used to protect rate control data * (data inside the algorithm, so serializes calls there) @@ -318,30 +372,17 @@ struct ieee80211_fast_tx { * @last_signal: signal of last received frame from this STA * @avg_signal: moving average of signal of received frames from this STA * @last_ack_signal: signal of last received Ack frame from this STA - * @last_seq_ctrl: last received seq/frag number from this STA (per RX queue) + * @last_seq_ctrl: last received seq/frag number from this STA (per TID + * plus one for non-QoS frames) * @tx_filtered_count: number of frames the hardware filtered for this STA * @tx_retry_failed: number of frames that failed retry * @tx_retry_count: total number of retries for frames to this STA - * @fail_avg: moving percentage of failed MSDUs * @tx_packets: number of RX/TX MSDUs * @tx_bytes: number of bytes transmitted to this STA * @tid_seq: per-TID sequence numbers for sending to this STA * @ampdu_mlme: A-MPDU state machine state * @timer_to_tid: identity mapping to ID timers - * @plink_lock: serialize access to plink fields - * @llid: Local link ID - * @plid: Peer link ID - * @reason: Cancel reason on PLINK_HOLDING state - * @plink_retries: Retries in establishment - * @plink_state: peer link state - * @plink_timeout: timeout of peer link - * @plink_timer: peer link watch timer - * @t_offset: timing offset relative to this host - * @t_offset_setpoint: reference timing offset of this sta to be used when - * calculating clockdrift - * @local_pm: local link-specific power save mode - * @peer_pm: peer-specific power save mode towards local STA - * @nonpeer_pm: STA power save mode towards non-peer neighbors + * @mesh: mesh STA information * @debugfs: debug filesystem info * @dead: set to true when sta is unlinked * @uploaded: set to true when sta is uploaded to the driver @@ -369,19 +410,19 @@ struct ieee80211_fast_tx { * @rx_msdu: MSDUs received from this station, using IEEE80211_NUM_TID * entry for non-QoS frames * @fast_tx: TX fastpath information - * @processed_beacon: set to true after peer rates and capabilities are - * processed + * @tdls_chandef: a TDLS peer can have a wider chandef that is compatible to + * the BSS one. */ struct sta_info { /* General information, mostly static */ struct list_head list, free_list; struct rcu_head rcu_head; struct rhash_head hash_node; + u8 addr[ETH_ALEN]; struct ieee80211_local *local; struct ieee80211_sub_if_data *sdata; struct ieee80211_key __rcu *gtk[NUM_DEFAULT_KEYS + NUM_DEFAULT_MGMT_KEYS]; struct ieee80211_key __rcu *ptk[NUM_DEFAULT_KEYS]; - u8 gtk_idx; u8 ptk_idx; struct rate_control_ref *rate_ctrl; void *rate_ctrl_priv; @@ -390,6 +431,10 @@ struct sta_info { struct ieee80211_fast_tx __rcu *fast_tx; +#ifdef CONFIG_MAC80211_MESH + struct mesh_sta *mesh; +#endif + struct work_struct drv_deliver_wk; u16 listen_interval; @@ -419,12 +464,12 @@ struct sta_info { unsigned long rx_fragments; unsigned long rx_dropped; int last_signal; - struct ewma avg_signal; + struct ewma_signal avg_signal; int last_ack_signal; u8 chains; s8 chain_signal_last[IEEE80211_MAX_CHAINS]; - struct ewma chain_signal_avg[IEEE80211_MAX_CHAINS]; + struct ewma_signal chain_signal_avg[IEEE80211_MAX_CHAINS]; /* Plus 1 for non-QoS frames */ __le16 last_seq_ctrl[IEEE80211_NUM_TIDS + 1]; @@ -432,8 +477,6 @@ struct sta_info { /* Updated from TX status path only, no locking requirements */ unsigned long tx_filtered_count; unsigned long tx_retry_failed, tx_retry_count; - /* moving percentage of failed MSDUs */ - unsigned int fail_avg; /* Updated from TX path only, no locking requirements */ u64 tx_packets[IEEE80211_NUM_ACS]; @@ -455,29 +498,6 @@ struct sta_info { struct sta_ampdu_mlme ampdu_mlme; u8 timer_to_tid[IEEE80211_NUM_TIDS]; -#ifdef CONFIG_MAC80211_MESH - /* - * Mesh peer link attributes, protected by plink_lock. - * TODO: move to a sub-structure that is referenced with pointer? - */ - spinlock_t plink_lock; - u16 llid; - u16 plid; - u16 reason; - u8 plink_retries; - enum nl80211_plink_state plink_state; - u32 plink_timeout; - struct timer_list plink_timer; - - s64 t_offset; - s64 t_offset_setpoint; - /* mesh power save */ - enum nl80211_mesh_power_mode local_pm; - enum nl80211_mesh_power_mode peer_pm; - enum nl80211_mesh_power_mode nonpeer_pm; - bool processed_beacon; -#endif - #ifdef CONFIG_MAC80211_DEBUGFS struct sta_info_debugfsdentries { struct dentry *dir; @@ -498,6 +518,8 @@ struct sta_info { u8 reserved_tid; + struct cfg80211_chan_def tdls_chandef; + /* keep last! */ struct ieee80211_sta sta; }; @@ -505,7 +527,7 @@ struct sta_info { static inline enum nl80211_plink_state sta_plink_state(struct sta_info *sta) { #ifdef CONFIG_MAC80211_MESH - return sta->plink_state; + return sta->mesh->plink_state; #endif return NL80211_PLINK_LISTEN; } @@ -608,7 +630,7 @@ u32 sta_addr_hash(const void *key, u32 length, u32 seed); _sta_bucket_idx(tbl, _addr), \ hash_node) \ /* compare address and run code only if it matches */ \ - if (ether_addr_equal(_sta->sta.addr, (_addr))) + if (ether_addr_equal(_sta->addr, (_addr))) /* * Get STA info by index, BROKEN! diff --git a/net/mac80211/status.c b/net/mac80211/status.c index 45628f37c083..8ba583243509 100644 --- a/net/mac80211/status.c +++ b/net/mac80211/status.c @@ -515,7 +515,7 @@ static void ieee80211_report_used_skb(struct ieee80211_local *local, if (!sdata) { skb->dev = NULL; - } else if (info->flags & IEEE80211_TX_INTFL_MLME_CONN_TX) { + } else { unsigned int hdr_size = ieee80211_hdrlen(hdr->frame_control); @@ -529,9 +529,6 @@ static void ieee80211_report_used_skb(struct ieee80211_local *local, ieee80211_mgd_conn_tx_status(sdata, hdr->frame_control, acked); - } else { - /* we assign ack frame ID for the others */ - WARN_ON(1); } rcu_read_unlock(); diff --git a/net/mac80211/tdls.c b/net/mac80211/tdls.c index 8db6e2994bbc..4e202d0679b2 100644 --- a/net/mac80211/tdls.c +++ b/net/mac80211/tdls.c @@ -4,6 +4,7 @@ * Copyright 2006-2010 Johannes Berg <johannes@sipsolutions.net> * Copyright 2014, Intel Corporation * Copyright 2014 Intel Mobile Communications GmbH + * Copyright 2015 Intel Deutschland GmbH * * This file is GPLv2 as found in COPYING. */ @@ -11,6 +12,7 @@ #include <linux/ieee80211.h> #include <linux/log2.h> #include <net/cfg80211.h> +#include <linux/rtnetlink.h> #include "ieee80211_i.h" #include "driver-ops.h" @@ -35,20 +37,28 @@ void ieee80211_tdls_peer_del_work(struct work_struct *wk) mutex_unlock(&local->mtx); } -static void ieee80211_tdls_add_ext_capab(struct ieee80211_local *local, +static void ieee80211_tdls_add_ext_capab(struct ieee80211_sub_if_data *sdata, struct sk_buff *skb) { - u8 *pos = (void *)skb_put(skb, 7); + struct ieee80211_local *local = sdata->local; bool chan_switch = local->hw.wiphy->features & NL80211_FEATURE_TDLS_CHANNEL_SWITCH; + bool wider_band = ieee80211_hw_check(&local->hw, TDLS_WIDER_BW); + enum ieee80211_band band = ieee80211_get_sdata_band(sdata); + struct ieee80211_supported_band *sband = local->hw.wiphy->bands[band]; + bool vht = sband && sband->vht_cap.vht_supported; + u8 *pos = (void *)skb_put(skb, 10); *pos++ = WLAN_EID_EXT_CAPABILITY; - *pos++ = 5; /* len */ + *pos++ = 8; /* len */ *pos++ = 0x0; *pos++ = 0x0; *pos++ = 0x0; *pos++ = chan_switch ? WLAN_EXT_CAPA4_TDLS_CHAN_SWITCH : 0; *pos++ = WLAN_EXT_CAPA5_TDLS_ENABLED; + *pos++ = 0; + *pos++ = 0; + *pos++ = (vht && wider_band) ? WLAN_EXT_CAPA8_TDLS_WIDE_BW_ENABLED : 0; } static u8 @@ -284,6 +294,60 @@ static void ieee80211_tdls_add_wmm_param_ie(struct ieee80211_sub_if_data *sdata, } static void +ieee80211_tdls_chandef_vht_upgrade(struct ieee80211_sub_if_data *sdata, + struct sta_info *sta) +{ + /* IEEE802.11ac-2013 Table E-4 */ + u16 centers_80mhz[] = { 5210, 5290, 5530, 5610, 5690, 5775 }; + struct cfg80211_chan_def uc = sta->tdls_chandef; + enum nl80211_chan_width max_width = ieee80211_get_sta_bw(&sta->sta); + int i; + + /* only support upgrading non-narrow channels up to 80Mhz */ + if (max_width == NL80211_CHAN_WIDTH_5 || + max_width == NL80211_CHAN_WIDTH_10) + return; + + if (max_width > NL80211_CHAN_WIDTH_80) + max_width = NL80211_CHAN_WIDTH_80; + + if (uc.width == max_width) + return; + /* + * Channel usage constrains in the IEEE802.11ac-2013 specification only + * allow expanding a 20MHz channel to 80MHz in a single way. In + * addition, there are no 40MHz allowed channels that are not part of + * the allowed 80MHz range in the 5GHz spectrum (the relevant one here). + */ + for (i = 0; i < ARRAY_SIZE(centers_80mhz); i++) + if (abs(uc.chan->center_freq - centers_80mhz[i]) <= 30) { + uc.center_freq1 = centers_80mhz[i]; + uc.width = NL80211_CHAN_WIDTH_80; + break; + } + + if (!uc.center_freq1) + return; + + /* proceed to downgrade the chandef until usable or the same */ + while (uc.width > max_width && + !cfg80211_reg_can_beacon(sdata->local->hw.wiphy, + &uc, sdata->wdev.iftype)) + ieee80211_chandef_downgrade(&uc); + + if (!cfg80211_chandef_identical(&uc, &sta->tdls_chandef)) { + tdls_dbg(sdata, "TDLS ch width upgraded %d -> %d\n", + sta->tdls_chandef.width, uc.width); + + /* + * the station is not yet authorized when BW upgrade is done, + * locking is not required + */ + sta->tdls_chandef = uc; + } +} + +static void ieee80211_tdls_add_setup_start_ies(struct ieee80211_sub_if_data *sdata, struct sk_buff *skb, const u8 *peer, u8 action_code, bool initiator, @@ -320,7 +384,7 @@ ieee80211_tdls_add_setup_start_ies(struct ieee80211_sub_if_data *sdata, offset = noffset; } - ieee80211_tdls_add_ext_capab(local, skb); + ieee80211_tdls_add_ext_capab(sdata, skb); /* add the QoS element if we support it */ if (local->hw.queues >= IEEE80211_NUM_ACS && @@ -350,15 +414,17 @@ ieee80211_tdls_add_setup_start_ies(struct ieee80211_sub_if_data *sdata, offset = noffset; } - rcu_read_lock(); + mutex_lock(&local->sta_mtx); /* we should have the peer STA if we're already responding */ if (action_code == WLAN_TDLS_SETUP_RESPONSE) { sta = sta_info_get(sdata, peer); if (WARN_ON_ONCE(!sta)) { - rcu_read_unlock(); + mutex_unlock(&local->sta_mtx); return; } + + sta->tdls_chandef = sdata->vif.bss_conf.chandef; } ieee80211_tdls_add_oper_classes(sdata, skb); @@ -384,10 +450,6 @@ ieee80211_tdls_add_setup_start_ies(struct ieee80211_sub_if_data *sdata, ieee80211_ie_build_ht_cap(pos, &ht_cap, ht_cap.cap); } else if (action_code == WLAN_TDLS_SETUP_RESPONSE && ht_cap.ht_supported && sta->sta.ht_cap.ht_supported) { - /* disable SMPS in TDLS responder */ - sta->sta.ht_cap.cap |= WLAN_HT_CAP_SM_PS_DISABLED - << IEEE80211_HT_CAP_SM_PS_SHIFT; - /* the peer caps are already intersected with our own */ memcpy(&ht_cap, &sta->sta.ht_cap, sizeof(ht_cap)); @@ -448,9 +510,16 @@ ieee80211_tdls_add_setup_start_ies(struct ieee80211_sub_if_data *sdata, pos = skb_put(skb, sizeof(struct ieee80211_vht_cap) + 2); ieee80211_ie_build_vht_cap(pos, &vht_cap, vht_cap.cap); + + /* + * if both peers support WIDER_BW, we can expand the chandef to + * a wider compatible one, up to 80MHz + */ + if (test_sta_flag(sta, WLAN_STA_TDLS_WIDER_BW)) + ieee80211_tdls_chandef_vht_upgrade(sdata, sta); } - rcu_read_unlock(); + mutex_unlock(&local->sta_mtx); /* add any remaining IEs */ if (extra_ies_len) { @@ -474,15 +543,17 @@ ieee80211_tdls_add_setup_cfm_ies(struct ieee80211_sub_if_data *sdata, enum ieee80211_band band = ieee80211_get_sdata_band(sdata); u8 *pos; - rcu_read_lock(); + mutex_lock(&local->sta_mtx); sta = sta_info_get(sdata, peer); ap_sta = sta_info_get(sdata, ifmgd->bssid); if (WARN_ON_ONCE(!sta || !ap_sta)) { - rcu_read_unlock(); + mutex_unlock(&local->sta_mtx); return; } + sta->tdls_chandef = sdata->vif.bss_conf.chandef; + /* add any custom IEs that go before the QoS IE */ if (extra_ies_len) { static const u8 before_qos[] = { @@ -530,12 +601,19 @@ ieee80211_tdls_add_setup_cfm_ies(struct ieee80211_sub_if_data *sdata, /* only include VHT-operation if not on the 2.4GHz band */ if (band != IEEE80211_BAND_2GHZ && sta->sta.vht_cap.vht_supported) { + /* + * if both peers support WIDER_BW, we can expand the chandef to + * a wider compatible one, up to 80MHz + */ + if (test_sta_flag(sta, WLAN_STA_TDLS_WIDER_BW)) + ieee80211_tdls_chandef_vht_upgrade(sdata, sta); + pos = skb_put(skb, 2 + sizeof(struct ieee80211_vht_operation)); ieee80211_ie_build_vht_oper(pos, &sta->sta.vht_cap, - &sdata->vif.bss_conf.chandef); + &sta->tdls_chandef); } - rcu_read_unlock(); + mutex_unlock(&local->sta_mtx); /* add any remaining IEs */ if (extra_ies_len) { @@ -784,7 +862,7 @@ ieee80211_tdls_build_mgmt_packet_data(struct ieee80211_sub_if_data *sdata, max(sizeof(struct ieee80211_mgmt), sizeof(struct ieee80211_tdls_data)) + 50 + /* supported rates */ - 7 + /* ext capab */ + 10 + /* ext capab */ 26 + /* max(WMM-info, WMM-param) */ 2 + max(sizeof(struct ieee80211_ht_cap), sizeof(struct ieee80211_ht_operation)) + @@ -983,8 +1061,17 @@ ieee80211_tdls_mgmt_setup(struct wiphy *wiphy, struct net_device *dev, { struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); struct ieee80211_local *local = sdata->local; + enum ieee80211_smps_mode smps_mode = sdata->u.mgd.driver_smps_mode; int ret; + /* don't support setup with forced SMPS mode that's not off */ + if (smps_mode != IEEE80211_SMPS_AUTOMATIC && + smps_mode != IEEE80211_SMPS_OFF) { + tdls_dbg(sdata, "Aborting TDLS setup due to SMPS mode %d\n", + smps_mode); + return -ENOTSUPP; + } + mutex_lock(&local->mtx); /* we don't support concurrent TDLS peer setups */ @@ -1146,6 +1233,74 @@ int ieee80211_tdls_mgmt(struct wiphy *wiphy, struct net_device *dev, return ret; } +static void iee80211_tdls_recalc_chanctx(struct ieee80211_sub_if_data *sdata) +{ + struct ieee80211_local *local = sdata->local; + struct ieee80211_chanctx_conf *conf; + struct ieee80211_chanctx *ctx; + + mutex_lock(&local->chanctx_mtx); + conf = rcu_dereference_protected(sdata->vif.chanctx_conf, + lockdep_is_held(&local->chanctx_mtx)); + if (conf) { + ctx = container_of(conf, struct ieee80211_chanctx, conf); + ieee80211_recalc_chanctx_chantype(local, ctx); + } + mutex_unlock(&local->chanctx_mtx); +} + +static int iee80211_tdls_have_ht_peers(struct ieee80211_sub_if_data *sdata) +{ + struct sta_info *sta; + bool result = false; + + rcu_read_lock(); + list_for_each_entry_rcu(sta, &sdata->local->sta_list, list) { + if (!sta->sta.tdls || sta->sdata != sdata || !sta->uploaded || + !test_sta_flag(sta, WLAN_STA_AUTHORIZED) || + !test_sta_flag(sta, WLAN_STA_TDLS_PEER_AUTH) || + !sta->sta.ht_cap.ht_supported) + continue; + result = true; + break; + } + rcu_read_unlock(); + + return result; +} + +static void +iee80211_tdls_recalc_ht_protection(struct ieee80211_sub_if_data *sdata, + struct sta_info *sta) +{ + struct ieee80211_if_managed *ifmgd = &sdata->u.mgd; + bool tdls_ht; + u16 protection = IEEE80211_HT_OP_MODE_PROTECTION_NONHT_MIXED | + IEEE80211_HT_OP_MODE_NON_GF_STA_PRSNT | + IEEE80211_HT_OP_MODE_NON_HT_STA_PRSNT; + u16 opmode; + + /* Nothing to do if the BSS connection uses HT */ + if (!(ifmgd->flags & IEEE80211_STA_DISABLE_HT)) + return; + + tdls_ht = (sta && sta->sta.ht_cap.ht_supported) || + iee80211_tdls_have_ht_peers(sdata); + + opmode = sdata->vif.bss_conf.ht_operation_mode; + + if (tdls_ht) + opmode |= protection; + else + opmode &= ~protection; + + if (opmode == sdata->vif.bss_conf.ht_operation_mode) + return; + + sdata->vif.bss_conf.ht_operation_mode = opmode; + ieee80211_bss_info_change_notify(sdata, BSS_CHANGED_HT); +} + int ieee80211_tdls_oper(struct wiphy *wiphy, struct net_device *dev, const u8 *peer, enum nl80211_tdls_operation oper) { @@ -1171,6 +1326,10 @@ int ieee80211_tdls_oper(struct wiphy *wiphy, struct net_device *dev, return -ENOTSUPP; } + /* protect possible bss_conf changes and avoid concurrency in + * ieee80211_bss_info_change_notify() + */ + sdata_lock(sdata); mutex_lock(&local->mtx); tdls_dbg(sdata, "TDLS oper %d peer %pM\n", oper, peer); @@ -1182,16 +1341,20 @@ int ieee80211_tdls_oper(struct wiphy *wiphy, struct net_device *dev, break; } - rcu_read_lock(); + iee80211_tdls_recalc_chanctx(sdata); + + mutex_lock(&local->sta_mtx); sta = sta_info_get(sdata, peer); if (!sta) { - rcu_read_unlock(); + mutex_unlock(&local->sta_mtx); ret = -ENOLINK; break; } + iee80211_tdls_recalc_ht_protection(sdata, sta); + set_sta_flag(sta, WLAN_STA_TDLS_PEER_AUTH); - rcu_read_unlock(); + mutex_unlock(&local->sta_mtx); WARN_ON_ONCE(is_zero_ether_addr(sdata->u.mgd.tdls_peer) || !ether_addr_equal(sdata->u.mgd.tdls_peer, peer)); @@ -1213,6 +1376,12 @@ int ieee80211_tdls_oper(struct wiphy *wiphy, struct net_device *dev, ieee80211_flush_queues(local, sdata, false); ret = sta_info_destroy_addr(sdata, peer); + + mutex_lock(&local->sta_mtx); + iee80211_tdls_recalc_ht_protection(sdata, NULL); + mutex_unlock(&local->sta_mtx); + + iee80211_tdls_recalc_chanctx(sdata); break; default: ret = -ENOTSUPP; @@ -1224,7 +1393,12 @@ int ieee80211_tdls_oper(struct wiphy *wiphy, struct net_device *dev, eth_zero_addr(sdata->u.mgd.tdls_peer); } + if (ret == 0) + ieee80211_queue_work(&sdata->local->hw, + &sdata->u.mgd.request_smps_work); + mutex_unlock(&local->mtx); + sdata_unlock(sdata); return ret; } @@ -1627,6 +1801,31 @@ ieee80211_process_tdls_channel_switch_req(struct ieee80211_sub_if_data *sdata, return -EINVAL; } + if (!elems.sec_chan_offs) { + chan_type = NL80211_CHAN_HT20; + } else { + switch (elems.sec_chan_offs->sec_chan_offs) { + case IEEE80211_HT_PARAM_CHA_SEC_ABOVE: + chan_type = NL80211_CHAN_HT40PLUS; + break; + case IEEE80211_HT_PARAM_CHA_SEC_BELOW: + chan_type = NL80211_CHAN_HT40MINUS; + break; + default: + chan_type = NL80211_CHAN_HT20; + break; + } + } + + cfg80211_chandef_create(&chandef, chan, chan_type); + + /* we will be active on the TDLS link */ + if (!cfg80211_reg_can_beacon_relax(sdata->local->hw.wiphy, &chandef, + sdata->wdev.iftype)) { + tdls_dbg(sdata, "TDLS chan switch to forbidden channel\n"); + return -EINVAL; + } + mutex_lock(&local->sta_mtx); sta = sta_info_get(sdata, tf->sa); if (!sta || !test_sta_flag(sta, WLAN_STA_TDLS_PEER_AUTH)) { @@ -1647,27 +1846,15 @@ ieee80211_process_tdls_channel_switch_req(struct ieee80211_sub_if_data *sdata, goto out; } - if (!sta->sta.ht_cap.ht_supported) { - chan_type = NL80211_CHAN_NO_HT; - } else if (!elems.sec_chan_offs) { - chan_type = NL80211_CHAN_HT20; - } else { - switch (elems.sec_chan_offs->sec_chan_offs) { - case IEEE80211_HT_PARAM_CHA_SEC_ABOVE: - chan_type = NL80211_CHAN_HT40PLUS; - break; - case IEEE80211_HT_PARAM_CHA_SEC_BELOW: - chan_type = NL80211_CHAN_HT40MINUS; - break; - default: - chan_type = NL80211_CHAN_HT20; - break; - } + /* peer should have known better */ + if (!sta->sta.ht_cap.ht_supported && elems.sec_chan_offs && + elems.sec_chan_offs->sec_chan_offs) { + tdls_dbg(sdata, "TDLS chan switch - wide chan unsupported\n"); + ret = -ENOTSUPP; + goto out; } - cfg80211_chandef_create(&chandef, chan, chan_type); params.chandef = &chandef; - params.switch_time = le16_to_cpu(elems.ch_sw_timing->switch_time); params.switch_timeout = le16_to_cpu(elems.ch_sw_timing->switch_timeout); @@ -1691,12 +1878,15 @@ out: return ret; } -void ieee80211_process_tdls_channel_switch(struct ieee80211_sub_if_data *sdata, - struct sk_buff *skb) +static void +ieee80211_process_tdls_channel_switch(struct ieee80211_sub_if_data *sdata, + struct sk_buff *skb) { struct ieee80211_tdls_data *tf = (void *)skb->data; struct wiphy *wiphy = sdata->local->hw.wiphy; + ASSERT_RTNL(); + /* make sure the driver supports it */ if (!(wiphy->features & NL80211_FEATURE_TDLS_CHANNEL_SWITCH)) return; @@ -1720,3 +1910,47 @@ void ieee80211_process_tdls_channel_switch(struct ieee80211_sub_if_data *sdata, return; } } + +void ieee80211_teardown_tdls_peers(struct ieee80211_sub_if_data *sdata) +{ + struct sta_info *sta; + u16 reason = WLAN_REASON_TDLS_TEARDOWN_UNSPECIFIED; + + rcu_read_lock(); + list_for_each_entry_rcu(sta, &sdata->local->sta_list, list) { + if (!sta->sta.tdls || sta->sdata != sdata || !sta->uploaded || + !test_sta_flag(sta, WLAN_STA_AUTHORIZED)) + continue; + + ieee80211_tdls_oper_request(&sdata->vif, sta->sta.addr, + NL80211_TDLS_TEARDOWN, reason, + GFP_ATOMIC); + } + rcu_read_unlock(); +} + +void ieee80211_tdls_chsw_work(struct work_struct *wk) +{ + struct ieee80211_local *local = + container_of(wk, struct ieee80211_local, tdls_chsw_work); + struct ieee80211_sub_if_data *sdata; + struct sk_buff *skb; + struct ieee80211_tdls_data *tf; + + rtnl_lock(); + while ((skb = skb_dequeue(&local->skb_queue_tdls_chsw))) { + tf = (struct ieee80211_tdls_data *)skb->data; + list_for_each_entry(sdata, &local->interfaces, list) { + if (!ieee80211_sdata_running(sdata) || + sdata->vif.type != NL80211_IFTYPE_STATION || + !ether_addr_equal(tf->da, sdata->vif.addr)) + continue; + + ieee80211_process_tdls_channel_switch(sdata, skb); + break; + } + + kfree_skb(skb); + } + rtnl_unlock(); +} diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c index b8233505bf9f..84e0e8c7fb23 100644 --- a/net/mac80211/tx.c +++ b/net/mac80211/tx.c @@ -311,9 +311,6 @@ ieee80211_tx_h_check_assoc(struct ieee80211_tx_data *tx) if (tx->sdata->vif.type == NL80211_IFTYPE_WDS) return TX_CONTINUE; - if (tx->sdata->vif.type == NL80211_IFTYPE_MESH_POINT) - return TX_CONTINUE; - if (tx->flags & IEEE80211_TX_PS_BUFFERED) return TX_CONTINUE; @@ -610,7 +607,6 @@ ieee80211_tx_h_select_key(struct ieee80211_tx_data *tx) if (tx->key) { bool skip_hw = false; - tx->key->tx_rx_count++; /* TODO: add threshold stuff again */ switch (tx->key->conf.cipher) { @@ -690,7 +686,8 @@ ieee80211_tx_h_rate_ctrl(struct ieee80211_tx_data *tx) txrc.bss = (tx->sdata->vif.type == NL80211_IFTYPE_AP || tx->sdata->vif.type == NL80211_IFTYPE_MESH_POINT || - tx->sdata->vif.type == NL80211_IFTYPE_ADHOC); + tx->sdata->vif.type == NL80211_IFTYPE_ADHOC || + tx->sdata->vif.type == NL80211_IFTYPE_OCB); /* set up RTS protection if desired */ if (len > tx->local->hw.wiphy->rts_threshold) { @@ -2777,7 +2774,11 @@ static bool ieee80211_xmit_fast(struct ieee80211_sub_if_data *sdata, sdata->sequence_number += 0x10; } - sta->tx_msdu[tid]++; + if (skb_shinfo(skb)->gso_size) + sta->tx_msdu[tid] += + DIV_ROUND_UP(skb->len, skb_shinfo(skb)->gso_size); + else + sta->tx_msdu[tid]++; info->hw_queue = sdata->vif.hw_queue[skb_get_queue_mapping(skb)]; @@ -3213,6 +3214,16 @@ static void ieee80211_set_csa(struct ieee80211_sub_if_data *sdata, rcu_read_unlock(); } +static u8 __ieee80211_csa_update_counter(struct beacon_data *beacon) +{ + beacon->csa_current_counter--; + + /* the counter should never reach 0 */ + WARN_ON_ONCE(!beacon->csa_current_counter); + + return beacon->csa_current_counter; +} + u8 ieee80211_csa_update_counter(struct ieee80211_vif *vif) { struct ieee80211_sub_if_data *sdata = vif_to_sdata(vif); @@ -3231,11 +3242,7 @@ u8 ieee80211_csa_update_counter(struct ieee80211_vif *vif) if (!beacon) goto unlock; - beacon->csa_current_counter--; - - /* the counter should never reach 0 */ - WARN_ON_ONCE(!beacon->csa_current_counter); - count = beacon->csa_current_counter; + count = __ieee80211_csa_update_counter(beacon); unlock: rcu_read_unlock(); @@ -3335,7 +3342,7 @@ __ieee80211_beacon_get(struct ieee80211_hw *hw, if (beacon) { if (beacon->csa_counter_offsets[0]) { if (!is_template) - ieee80211_csa_update_counter(vif); + __ieee80211_csa_update_counter(beacon); ieee80211_set_csa(sdata, beacon); } @@ -3381,7 +3388,7 @@ __ieee80211_beacon_get(struct ieee80211_hw *hw, if (beacon->csa_counter_offsets[0]) { if (!is_template) - ieee80211_csa_update_counter(vif); + __ieee80211_csa_update_counter(beacon); ieee80211_set_csa(sdata, beacon); } @@ -3411,7 +3418,7 @@ __ieee80211_beacon_get(struct ieee80211_hw *hw, * for now we leave it consistent with overall * mac80211's behavior. */ - ieee80211_csa_update_counter(vif); + __ieee80211_csa_update_counter(beacon); ieee80211_set_csa(sdata, beacon); } diff --git a/net/mac80211/util.c b/net/mac80211/util.c index 43e5aadd7a89..1104421bc525 100644 --- a/net/mac80211/util.c +++ b/net/mac80211/util.c @@ -47,55 +47,6 @@ struct ieee80211_hw *wiphy_to_ieee80211_hw(struct wiphy *wiphy) } EXPORT_SYMBOL(wiphy_to_ieee80211_hw); -u8 *ieee80211_get_bssid(struct ieee80211_hdr *hdr, size_t len, - enum nl80211_iftype type) -{ - __le16 fc = hdr->frame_control; - - /* drop ACK/CTS frames and incorrect hdr len (ctrl) */ - if (len < 16) - return NULL; - - if (ieee80211_is_data(fc)) { - if (len < 24) /* drop incorrect hdr len (data) */ - return NULL; - - if (ieee80211_has_a4(fc)) - return NULL; - if (ieee80211_has_tods(fc)) - return hdr->addr1; - if (ieee80211_has_fromds(fc)) - return hdr->addr2; - - return hdr->addr3; - } - - if (ieee80211_is_mgmt(fc)) { - if (len < 24) /* drop incorrect hdr len (mgmt) */ - return NULL; - return hdr->addr3; - } - - if (ieee80211_is_ctl(fc)) { - if (ieee80211_is_pspoll(fc)) - return hdr->addr1; - - if (ieee80211_is_back_req(fc)) { - switch (type) { - case NL80211_IFTYPE_STATION: - return hdr->addr2; - case NL80211_IFTYPE_AP: - case NL80211_IFTYPE_AP_VLAN: - return hdr->addr1; - default: - break; /* fall through to the return */ - } - } - } - - return NULL; -} - void ieee80211_tx_set_protected(struct ieee80211_tx_data *tx) { struct sk_buff *skb; @@ -752,7 +703,12 @@ EXPORT_SYMBOL_GPL(wdev_to_ieee80211_vif); struct wireless_dev *ieee80211_vif_to_wdev(struct ieee80211_vif *vif) { - struct ieee80211_sub_if_data *sdata = vif_to_sdata(vif); + struct ieee80211_sub_if_data *sdata; + + if (!vif) + return NULL; + + sdata = vif_to_sdata(vif); if (!ieee80211_sdata_running(sdata) || !(sdata->flags & IEEE80211_SDATA_IN_DRIVER)) @@ -1709,6 +1665,7 @@ static void ieee80211_handle_reconfig_failure(struct ieee80211_local *local) local->resuming = false; local->suspended = false; local->started = false; + local->in_reconfig = false; /* scheduled scan clearly can't be running any more, but tell * cfg80211 and clear local state @@ -1759,16 +1716,24 @@ int ieee80211_reconfig(struct ieee80211_local *local) struct ieee80211_sub_if_data *sched_scan_sdata; struct cfg80211_sched_scan_request *sched_scan_req; bool sched_scan_stopped = false; + bool suspended = local->suspended; /* nothing to do if HW shouldn't run */ if (!local->open_count) goto wake_up; #ifdef CONFIG_PM - if (local->suspended) + if (suspended) local->resuming = true; if (local->wowlan) { + /* + * In the wowlan case, both mac80211 and the device + * are functional when the resume op is called, so + * clear local->suspended so the device could operate + * normally (e.g. pass rx frames). + */ + local->suspended = false; res = drv_resume(local); local->wowlan = false; if (res < 0) { @@ -1781,8 +1746,10 @@ int ieee80211_reconfig(struct ieee80211_local *local) /* * res is 1, which means the driver requested * to go through a regular reset on wakeup. + * restore local->suspended in this case. */ reconfig_due_to_wowlan = true; + local->suspended = true; } #endif @@ -1794,7 +1761,7 @@ int ieee80211_reconfig(struct ieee80211_local *local) */ res = drv_start(local); if (res) { - if (local->suspended) + if (suspended) WARN(1, "Hardware became unavailable upon resume. This could be a software issue prior to suspend or a hardware issue.\n"); else WARN(1, "Hardware became unavailable during restart.\n"); @@ -2088,10 +2055,10 @@ int ieee80211_reconfig(struct ieee80211_local *local) * If this is for hw restart things are still running. * We may want to change that later, however. */ - if (local->open_count && (!local->suspended || reconfig_due_to_wowlan)) + if (local->open_count && (!suspended || reconfig_due_to_wowlan)) drv_reconfig_complete(local, IEEE80211_RECONFIG_TYPE_RESTART); - if (!local->suspended) + if (!suspended) return 0; #ifdef CONFIG_PM diff --git a/net/mac80211/vht.c b/net/mac80211/vht.c index 80694d55db74..ff1c798921a6 100644 --- a/net/mac80211/vht.c +++ b/net/mac80211/vht.c @@ -120,6 +120,7 @@ ieee80211_vht_cap_ie_to_sta_vht_cap(struct ieee80211_sub_if_data *sdata, struct ieee80211_sta_vht_cap *vht_cap = &sta->sta.vht_cap; struct ieee80211_sta_vht_cap own_cap; u32 cap_info, i; + bool have_80mhz; memset(vht_cap, 0, sizeof(*vht_cap)); @@ -129,6 +130,20 @@ ieee80211_vht_cap_ie_to_sta_vht_cap(struct ieee80211_sub_if_data *sdata, if (!vht_cap_ie || !sband->vht_cap.vht_supported) return; + /* Allow VHT if at least one channel on the sband supports 80 MHz */ + have_80mhz = false; + for (i = 0; i < sband->n_channels; i++) { + if (sband->channels[i].flags & (IEEE80211_CHAN_DISABLED | + IEEE80211_CHAN_NO_80MHZ)) + continue; + + have_80mhz = true; + break; + } + + if (!have_80mhz) + return; + /* * A VHT STA must support 40 MHz, but if we verify that here * then we break a few things - some APs (e.g. Netgear R6300v2 @@ -308,11 +323,15 @@ enum ieee80211_sta_rx_bandwidth ieee80211_sta_cur_vht_bw(struct sta_info *sta) { struct ieee80211_sub_if_data *sdata = sta->sdata; enum ieee80211_sta_rx_bandwidth bw; + enum nl80211_chan_width bss_width = sdata->vif.bss_conf.chandef.width; - bw = ieee80211_chan_width_to_rx_bw(sdata->vif.bss_conf.chandef.width); - bw = min(bw, ieee80211_sta_cap_rx_bw(sta)); + bw = ieee80211_sta_cap_rx_bw(sta); bw = min(bw, sta->cur_max_bandwidth); + /* do not cap the BW of TDLS WIDER_BW peers by the bss */ + if (!test_sta_flag(sta, WLAN_STA_TDLS_WIDER_BW)) + bw = min(bw, ieee80211_chan_width_to_rx_bw(bss_width)); + return bw; } @@ -422,3 +441,29 @@ void ieee80211_vht_handle_opmode(struct ieee80211_sub_if_data *sdata, if (changed > 0) rate_control_rate_update(local, sband, sta, changed); } + +void ieee80211_get_vht_mask_from_cap(__le16 vht_cap, + u16 vht_mask[NL80211_VHT_NSS_MAX]) +{ + int i; + u16 mask, cap = le16_to_cpu(vht_cap); + + for (i = 0; i < NL80211_VHT_NSS_MAX; i++) { + mask = (cap >> i * 2) & IEEE80211_VHT_MCS_NOT_SUPPORTED; + switch (mask) { + case IEEE80211_VHT_MCS_SUPPORT_0_7: + vht_mask[i] = 0x00FF; + break; + case IEEE80211_VHT_MCS_SUPPORT_0_8: + vht_mask[i] = 0x01FF; + break; + case IEEE80211_VHT_MCS_SUPPORT_0_9: + vht_mask[i] = 0x03FF; + break; + case IEEE80211_VHT_MCS_NOT_SUPPORTED: + default: + vht_mask[i] = 0; + break; + } + } +} diff --git a/net/mac80211/wpa.c b/net/mac80211/wpa.c index 943f7606527e..feb547dc8643 100644 --- a/net/mac80211/wpa.c +++ b/net/mac80211/wpa.c @@ -516,31 +516,34 @@ ieee80211_crypto_ccmp_decrypt(struct ieee80211_rx_data *rx, return RX_DROP_UNUSABLE; } - ccmp_hdr2pn(pn, skb->data + hdrlen); + if (!(status->flag & RX_FLAG_PN_VALIDATED)) { + ccmp_hdr2pn(pn, skb->data + hdrlen); - queue = rx->security_idx; + queue = rx->security_idx; - if (memcmp(pn, key->u.ccmp.rx_pn[queue], IEEE80211_CCMP_PN_LEN) <= 0) { - key->u.ccmp.replays++; - return RX_DROP_UNUSABLE; - } + if (memcmp(pn, key->u.ccmp.rx_pn[queue], + IEEE80211_CCMP_PN_LEN) <= 0) { + key->u.ccmp.replays++; + return RX_DROP_UNUSABLE; + } - if (!(status->flag & RX_FLAG_DECRYPTED)) { - u8 aad[2 * AES_BLOCK_SIZE]; - u8 b_0[AES_BLOCK_SIZE]; - /* hardware didn't decrypt/verify MIC */ - ccmp_special_blocks(skb, pn, b_0, aad); + if (!(status->flag & RX_FLAG_DECRYPTED)) { + u8 aad[2 * AES_BLOCK_SIZE]; + u8 b_0[AES_BLOCK_SIZE]; + /* hardware didn't decrypt/verify MIC */ + ccmp_special_blocks(skb, pn, b_0, aad); + + if (ieee80211_aes_ccm_decrypt( + key->u.ccmp.tfm, b_0, aad, + skb->data + hdrlen + IEEE80211_CCMP_HDR_LEN, + data_len, + skb->data + skb->len - mic_len, mic_len)) + return RX_DROP_UNUSABLE; + } - if (ieee80211_aes_ccm_decrypt( - key->u.ccmp.tfm, b_0, aad, - skb->data + hdrlen + IEEE80211_CCMP_HDR_LEN, - data_len, - skb->data + skb->len - mic_len, mic_len)) - return RX_DROP_UNUSABLE; + memcpy(key->u.ccmp.rx_pn[queue], pn, IEEE80211_CCMP_PN_LEN); } - memcpy(key->u.ccmp.rx_pn[queue], pn, IEEE80211_CCMP_PN_LEN); - /* Remove CCMP header and MIC */ if (pskb_trim(skb, skb->len - mic_len)) return RX_DROP_UNUSABLE; @@ -739,31 +742,35 @@ ieee80211_crypto_gcmp_decrypt(struct ieee80211_rx_data *rx) return RX_DROP_UNUSABLE; } - gcmp_hdr2pn(pn, skb->data + hdrlen); + if (!(status->flag & RX_FLAG_PN_VALIDATED)) { + gcmp_hdr2pn(pn, skb->data + hdrlen); - queue = rx->security_idx; + queue = rx->security_idx; - if (memcmp(pn, key->u.gcmp.rx_pn[queue], IEEE80211_GCMP_PN_LEN) <= 0) { - key->u.gcmp.replays++; - return RX_DROP_UNUSABLE; - } + if (memcmp(pn, key->u.gcmp.rx_pn[queue], + IEEE80211_GCMP_PN_LEN) <= 0) { + key->u.gcmp.replays++; + return RX_DROP_UNUSABLE; + } - if (!(status->flag & RX_FLAG_DECRYPTED)) { - u8 aad[2 * AES_BLOCK_SIZE]; - u8 j_0[AES_BLOCK_SIZE]; - /* hardware didn't decrypt/verify MIC */ - gcmp_special_blocks(skb, pn, j_0, aad); + if (!(status->flag & RX_FLAG_DECRYPTED)) { + u8 aad[2 * AES_BLOCK_SIZE]; + u8 j_0[AES_BLOCK_SIZE]; + /* hardware didn't decrypt/verify MIC */ + gcmp_special_blocks(skb, pn, j_0, aad); + + if (ieee80211_aes_gcm_decrypt( + key->u.gcmp.tfm, j_0, aad, + skb->data + hdrlen + IEEE80211_GCMP_HDR_LEN, + data_len, + skb->data + skb->len - + IEEE80211_GCMP_MIC_LEN)) + return RX_DROP_UNUSABLE; + } - if (ieee80211_aes_gcm_decrypt( - key->u.gcmp.tfm, j_0, aad, - skb->data + hdrlen + IEEE80211_GCMP_HDR_LEN, - data_len, - skb->data + skb->len - IEEE80211_GCMP_MIC_LEN)) - return RX_DROP_UNUSABLE; + memcpy(key->u.gcmp.rx_pn[queue], pn, IEEE80211_GCMP_PN_LEN); } - memcpy(key->u.gcmp.rx_pn[queue], pn, IEEE80211_GCMP_PN_LEN); - /* Remove GCMP header and MIC */ if (pskb_trim(skb, skb->len - IEEE80211_GCMP_MIC_LEN)) return RX_DROP_UNUSABLE; diff --git a/net/mac802154/cfg.c b/net/mac802154/cfg.c index 317c4662e544..c865ebb2ace2 100644 --- a/net/mac802154/cfg.c +++ b/net/mac802154/cfg.c @@ -44,6 +44,49 @@ static void ieee802154_del_iface_deprecated(struct wpan_phy *wpan_phy, ieee802154_if_remove(sdata); } +#ifdef CONFIG_PM +static int ieee802154_suspend(struct wpan_phy *wpan_phy) +{ + struct ieee802154_local *local = wpan_phy_priv(wpan_phy); + + if (!local->open_count) + goto suspend; + + ieee802154_stop_queue(&local->hw); + synchronize_net(); + + /* stop hardware - this must stop RX */ + ieee802154_stop_device(local); + +suspend: + local->suspended = true; + return 0; +} + +static int ieee802154_resume(struct wpan_phy *wpan_phy) +{ + struct ieee802154_local *local = wpan_phy_priv(wpan_phy); + int ret; + + /* nothing to do if HW shouldn't run */ + if (!local->open_count) + goto wake_up; + + /* restart hardware */ + ret = drv_start(local); + if (ret) + return ret; + +wake_up: + ieee802154_wake_queue(&local->hw); + local->suspended = false; + return 0; +} +#else +#define ieee802154_suspend NULL +#define ieee802154_resume NULL +#endif + static int ieee802154_add_iface(struct wpan_phy *phy, const char *name, unsigned char name_assign_type, @@ -145,13 +188,18 @@ static int ieee802154_set_pan_id(struct wpan_phy *wpan_phy, struct wpan_dev *wpan_dev, __le16 pan_id) { + int ret; + ASSERT_RTNL(); if (wpan_dev->pan_id == pan_id) return 0; - wpan_dev->pan_id = pan_id; - return 0; + ret = mac802154_wpan_update_llsec(wpan_dev->netdev); + if (!ret) + wpan_dev->pan_id = pan_id; + + return ret; } static int @@ -161,10 +209,6 @@ ieee802154_set_backoff_exponent(struct wpan_phy *wpan_phy, { ASSERT_RTNL(); - if (wpan_dev->min_be == min_be && - wpan_dev->max_be == max_be) - return 0; - wpan_dev->min_be = min_be; wpan_dev->max_be = max_be; return 0; @@ -176,9 +220,6 @@ ieee802154_set_short_addr(struct wpan_phy *wpan_phy, struct wpan_dev *wpan_dev, { ASSERT_RTNL(); - if (wpan_dev->short_addr == short_addr) - return 0; - wpan_dev->short_addr = short_addr; return 0; } @@ -190,9 +231,6 @@ ieee802154_set_max_csma_backoffs(struct wpan_phy *wpan_phy, { ASSERT_RTNL(); - if (wpan_dev->csma_retries == max_csma_backoffs) - return 0; - wpan_dev->csma_retries = max_csma_backoffs; return 0; } @@ -204,9 +242,6 @@ ieee802154_set_max_frame_retries(struct wpan_phy *wpan_phy, { ASSERT_RTNL(); - if (wpan_dev->frame_retries == max_frame_retries) - return 0; - wpan_dev->frame_retries = max_frame_retries; return 0; } @@ -217,16 +252,25 @@ ieee802154_set_lbt_mode(struct wpan_phy *wpan_phy, struct wpan_dev *wpan_dev, { ASSERT_RTNL(); - if (wpan_dev->lbt == mode) - return 0; - wpan_dev->lbt = mode; return 0; } +static int +ieee802154_set_ackreq_default(struct wpan_phy *wpan_phy, + struct wpan_dev *wpan_dev, bool ackreq) +{ + ASSERT_RTNL(); + + wpan_dev->ackreq = ackreq; + return 0; +} + const struct cfg802154_ops mac802154_config_ops = { .add_virtual_intf_deprecated = ieee802154_add_iface_deprecated, .del_virtual_intf_deprecated = ieee802154_del_iface_deprecated, + .suspend = ieee802154_suspend, + .resume = ieee802154_resume, .add_virtual_intf = ieee802154_add_iface, .del_virtual_intf = ieee802154_del_iface, .set_channel = ieee802154_set_channel, @@ -239,4 +283,5 @@ const struct cfg802154_ops mac802154_config_ops = { .set_max_csma_backoffs = ieee802154_set_max_csma_backoffs, .set_max_frame_retries = ieee802154_set_max_frame_retries, .set_lbt_mode = ieee802154_set_lbt_mode, + .set_ackreq_default = ieee802154_set_ackreq_default, }; diff --git a/net/mac802154/ieee802154_i.h b/net/mac802154/ieee802154_i.h index 34755d5751a4..56ccffa3f2bf 100644 --- a/net/mac802154/ieee802154_i.h +++ b/net/mac802154/ieee802154_i.h @@ -56,9 +56,13 @@ struct ieee802154_local { struct hrtimer ifs_timer; bool started; + bool suspended; struct tasklet_struct tasklet; struct sk_buff_head skb_queue; + + struct sk_buff *tx_skb; + struct work_struct tx_work; }; enum { @@ -94,8 +98,6 @@ struct ieee802154_sub_if_data { struct mac802154_llsec sec; }; -#define MAC802154_CHAN_NONE 0xff /* No channel is assigned */ - /* utility functions/constants */ extern const void *const mac802154_wpan_phy_privid; /* for wpan_phy privid */ @@ -125,6 +127,8 @@ ieee802154_sdata_running(struct ieee802154_sub_if_data *sdata) extern struct ieee802154_mlme_ops mac802154_mlme_wpan; +void ieee802154_rx(struct ieee802154_local *local, struct sk_buff *skb); +void ieee802154_xmit_worker(struct work_struct *work); netdev_tx_t ieee802154_monitor_start_xmit(struct sk_buff *skb, struct net_device *dev); netdev_tx_t @@ -167,6 +171,8 @@ void mac802154_get_table(struct net_device *dev, struct ieee802154_llsec_table **t); void mac802154_unlock_table(struct net_device *dev); +int mac802154_wpan_update_llsec(struct net_device *dev); + /* interface handling */ int ieee802154_iface_init(void); void ieee802154_iface_exit(void); @@ -176,5 +182,6 @@ ieee802154_if_add(struct ieee802154_local *local, const char *name, unsigned char name_assign_type, enum nl802154_iftype type, __le64 extended_addr); void ieee802154_remove_interfaces(struct ieee802154_local *local); +void ieee802154_stop_device(struct ieee802154_local *local); #endif /* __IEEE802154_I_H */ diff --git a/net/mac802154/iface.c b/net/mac802154/iface.c index 8b698246a51b..ed26952f9e14 100644 --- a/net/mac802154/iface.c +++ b/net/mac802154/iface.c @@ -30,7 +30,7 @@ #include "ieee802154_i.h" #include "driver-ops.h" -static int mac802154_wpan_update_llsec(struct net_device *dev) +int mac802154_wpan_update_llsec(struct net_device *dev) { struct ieee802154_sub_if_data *sdata = IEEE802154_DEV_TO_SUB_IF(dev); struct ieee802154_mlme_ops *ops = ieee802154_mlme_ops(dev); @@ -125,6 +125,14 @@ static int mac802154_wpan_mac_addr(struct net_device *dev, void *p) if (netif_running(dev)) return -EBUSY; + /* lowpan need to be down for update + * SLAAC address after ifup + */ + if (sdata->wpan_dev.lowpan_dev) { + if (netif_running(sdata->wpan_dev.lowpan_dev)) + return -EBUSY; + } + ieee802154_be64_to_le64(&extended_addr, addr->sa_data); if (!ieee802154_is_valid_extended_unicast_addr(extended_addr)) return -EINVAL; @@ -132,6 +140,13 @@ static int mac802154_wpan_mac_addr(struct net_device *dev, void *p) memcpy(dev->dev_addr, addr->sa_data, dev->addr_len); sdata->wpan_dev.extended_addr = extended_addr; + /* update lowpan interface mac address when + * wpan mac has been changed + */ + if (sdata->wpan_dev.lowpan_dev) + memcpy(sdata->wpan_dev.lowpan_dev->dev_addr, dev->dev_addr, + dev->addr_len); + return mac802154_wpan_update_llsec(dev); } @@ -314,11 +329,8 @@ static int mac802154_slave_close(struct net_device *dev) clear_bit(SDATA_STATE_RUNNING, &sdata->state); - if (!local->open_count) { - flush_workqueue(local->workqueue); - hrtimer_cancel(&local->ifs_timer); - drv_stop(local); - } + if (!local->open_count) + ieee802154_stop_device(local); return 0; } @@ -471,6 +483,7 @@ ieee802154_setup_sdata(struct ieee802154_sub_if_data *sdata, enum nl802154_iftype type) { struct wpan_dev *wpan_dev = &sdata->wpan_dev; + int ret; u8 tmp; /* set some type-dependent values */ @@ -485,8 +498,7 @@ ieee802154_setup_sdata(struct ieee802154_sub_if_data *sdata, wpan_dev->min_be = 3; wpan_dev->max_be = 5; wpan_dev->csma_retries = 4; - /* for compatibility, actual default is 3 */ - wpan_dev->frame_retries = -1; + wpan_dev->frame_retries = 3; wpan_dev->pan_id = cpu_to_le16(IEEE802154_PANID_BROADCAST); wpan_dev->short_addr = cpu_to_le16(IEEE802154_ADDR_BROADCAST); @@ -505,6 +517,10 @@ ieee802154_setup_sdata(struct ieee802154_sub_if_data *sdata, mutex_init(&sdata->sec_mtx); mac802154_llsec_init(&sdata->sec); + ret = mac802154_wpan_update_llsec(sdata->dev); + if (ret < 0) + return ret; + break; case NL802154_IFTYPE_MONITOR: sdata->dev->destructor = free_netdev; diff --git a/net/mac802154/main.c b/net/mac802154/main.c index 356b346e1ee8..e8cab5bb80c6 100644 --- a/net/mac802154/main.c +++ b/net/mac802154/main.c @@ -40,7 +40,7 @@ static void ieee802154_tasklet_handler(unsigned long data) * netstack. */ skb->pkt_type = 0; - ieee802154_rx(&local->hw, skb); + ieee802154_rx(local, skb); break; default: WARN(1, "mac802154: Packet is of unknown type %d\n", @@ -58,11 +58,9 @@ ieee802154_alloc_hw(size_t priv_data_len, const struct ieee802154_ops *ops) struct ieee802154_local *local; size_t priv_size; - if (!ops || !(ops->xmit_async || ops->xmit_sync) || !ops->ed || - !ops->start || !ops->stop || !ops->set_channel) { - pr_err("undefined IEEE802.15.4 device operations\n"); + if (WARN_ON(!ops || !(ops->xmit_async || ops->xmit_sync) || !ops->ed || + !ops->start || !ops->stop || !ops->set_channel)) return NULL; - } /* Ensure 32-byte alignment of our private data and hw private data. * We use the wpan_phy priv data for both our ieee802154_local and for @@ -107,11 +105,13 @@ ieee802154_alloc_hw(size_t priv_data_len, const struct ieee802154_ops *ops) skb_queue_head_init(&local->skb_queue); + INIT_WORK(&local->tx_work, ieee802154_xmit_worker); + /* init supported flags with 802.15.4 default ranges */ phy->supported.max_minbe = 8; phy->supported.min_maxbe = 3; phy->supported.max_maxbe = 8; - phy->supported.min_frame_retries = -1; + phy->supported.min_frame_retries = 0; phy->supported.max_frame_retries = 7; phy->supported.max_csma_backoffs = 5; phy->supported.lbt = NL802154_SUPPORTED_BOOL_FALSE; @@ -177,11 +177,8 @@ int ieee802154_register_hw(struct ieee802154_hw *hw) } if (!(hw->flags & IEEE802154_HW_FRAME_RETRIES)) { - /* TODO should be 3, but our default value is -1 which means - * no ARET handling. - */ - local->phy->supported.min_frame_retries = -1; - local->phy->supported.max_frame_retries = -1; + local->phy->supported.min_frame_retries = 3; + local->phy->supported.max_frame_retries = 3; } if (hw->flags & IEEE802154_HW_PROMISCUOUS) diff --git a/net/mac802154/rx.c b/net/mac802154/rx.c index d93ad2d4a4fc..d1c33c1d6b9b 100644 --- a/net/mac802154/rx.c +++ b/net/mac802154/rx.c @@ -246,13 +246,15 @@ ieee802154_monitors_rx(struct ieee802154_local *local, struct sk_buff *skb) } } -void ieee802154_rx(struct ieee802154_hw *hw, struct sk_buff *skb) +void ieee802154_rx(struct ieee802154_local *local, struct sk_buff *skb) { - struct ieee802154_local *local = hw_to_local(hw); u16 crc; WARN_ON_ONCE(softirq_count() == 0); + if (local->suspended) + goto drop; + /* TODO: When a transceiver omits the checksum here, we * add an own calculated one. This is currently an ugly * solution because the monitor needs a crc here. @@ -273,8 +275,7 @@ void ieee802154_rx(struct ieee802154_hw *hw, struct sk_buff *skb) crc = crc_ccitt(0, skb->data, skb->len); if (crc) { rcu_read_unlock(); - kfree_skb(skb); - return; + goto drop; } } /* remove crc */ @@ -283,8 +284,11 @@ void ieee802154_rx(struct ieee802154_hw *hw, struct sk_buff *skb) __ieee802154_rx_handle_packet(local, skb); rcu_read_unlock(); + + return; +drop: + kfree_skb(skb); } -EXPORT_SYMBOL(ieee802154_rx); void ieee802154_rx_irqsafe(struct ieee802154_hw *hw, struct sk_buff *skb, u8 lqi) diff --git a/net/mac802154/tx.c b/net/mac802154/tx.c index c62e95695c78..7ed439172f30 100644 --- a/net/mac802154/tx.c +++ b/net/mac802154/tx.c @@ -30,23 +30,11 @@ #include "ieee802154_i.h" #include "driver-ops.h" -/* IEEE 802.15.4 transceivers can sleep during the xmit session, so process - * packets through the workqueue. - */ -struct ieee802154_xmit_cb { - struct sk_buff *skb; - struct work_struct work; - struct ieee802154_local *local; -}; - -static struct ieee802154_xmit_cb ieee802154_xmit_cb; - -static void ieee802154_xmit_worker(struct work_struct *work) +void ieee802154_xmit_worker(struct work_struct *work) { - struct ieee802154_xmit_cb *cb = - container_of(work, struct ieee802154_xmit_cb, work); - struct ieee802154_local *local = cb->local; - struct sk_buff *skb = cb->skb; + struct ieee802154_local *local = + container_of(work, struct ieee802154_local, tx_work); + struct sk_buff *skb = local->tx_skb; struct net_device *dev = skb->dev; int res; @@ -106,11 +94,8 @@ ieee802154_tx(struct ieee802154_local *local, struct sk_buff *skb) dev->stats.tx_packets++; dev->stats.tx_bytes += skb->len; } else { - INIT_WORK(&ieee802154_xmit_cb.work, ieee802154_xmit_worker); - ieee802154_xmit_cb.skb = skb; - ieee802154_xmit_cb.local = local; - - queue_work(local->workqueue, &ieee802154_xmit_cb.work); + local->tx_skb = skb; + queue_work(local->workqueue, &local->tx_work); } return NETDEV_TX_OK; diff --git a/net/mac802154/util.c b/net/mac802154/util.c index 583435f38930..f9fd0957ab67 100644 --- a/net/mac802154/util.c +++ b/net/mac802154/util.c @@ -14,6 +14,7 @@ */ #include "ieee802154_i.h" +#include "driver-ops.h" /* privid for wpan_phys to determine whether they belong to us or not */ const void *const mac802154_wpan_phy_privid = &mac802154_wpan_phy_privid; @@ -92,3 +93,10 @@ void ieee802154_xmit_complete(struct ieee802154_hw *hw, struct sk_buff *skb, dev_consume_skb_any(skb); } EXPORT_SYMBOL(ieee802154_xmit_complete); + +void ieee802154_stop_device(struct ieee802154_local *local) +{ + flush_workqueue(local->workqueue); + hrtimer_cancel(&local->ifs_timer); + drv_stop(local); +} diff --git a/net/mpls/Kconfig b/net/mpls/Kconfig index 17bde799c854..5c467ef97311 100644 --- a/net/mpls/Kconfig +++ b/net/mpls/Kconfig @@ -24,7 +24,13 @@ config NET_MPLS_GSO config MPLS_ROUTING tristate "MPLS: routing support" - help + ---help--- Add support for forwarding of mpls packets. +config MPLS_IPTUNNEL + tristate "MPLS: IP over MPLS tunnel support" + depends on LWTUNNEL && MPLS_ROUTING + ---help--- + mpls ip tunnel support. + endif # MPLS diff --git a/net/mpls/Makefile b/net/mpls/Makefile index 65bbe68c72e6..9ca923625016 100644 --- a/net/mpls/Makefile +++ b/net/mpls/Makefile @@ -3,5 +3,6 @@ # obj-$(CONFIG_NET_MPLS_GSO) += mpls_gso.o obj-$(CONFIG_MPLS_ROUTING) += mpls_router.o +obj-$(CONFIG_MPLS_IPTUNNEL) += mpls_iptunnel.o mpls_router-y := af_mpls.o diff --git a/net/mpls/af_mpls.c b/net/mpls/af_mpls.c index 1f93a5978f2a..bb185a28de98 100644 --- a/net/mpls/af_mpls.c +++ b/net/mpls/af_mpls.c @@ -15,6 +15,10 @@ #include <net/ip_fib.h> #include <net/netevent.h> #include <net/netns/generic.h> +#if IS_ENABLED(CONFIG_IPV6) +#include <net/ipv6.h> +#include <net/addrconf.h> +#endif #include "internal.h" #define LABEL_NOT_SPECIFIED (1<<20) @@ -23,11 +27,23 @@ /* This maximum ha length copied from the definition of struct neighbour */ #define MAX_VIA_ALEN (ALIGN(MAX_ADDR_LEN, sizeof(unsigned long))) +enum mpls_payload_type { + MPT_UNSPEC, /* IPv4 or IPv6 */ + MPT_IPV4 = 4, + MPT_IPV6 = 6, + + /* Other types not implemented: + * - Pseudo-wire with or without control word (RFC4385) + * - GAL (RFC5586) + */ +}; + struct mpls_route { /* next hop label forwarding entry */ struct net_device __rcu *rt_dev; struct rcu_head rt_rcu; u32 rt_label[MAX_NEW_LABELS]; u8 rt_protocol; /* routing protocol that set this entry */ + u8 rt_payload_type; u8 rt_labels; u8 rt_via_alen; u8 rt_via_table; @@ -58,10 +74,11 @@ static inline struct mpls_dev *mpls_dev_get(const struct net_device *dev) return rcu_dereference_rtnl(dev->mpls_ptr); } -static bool mpls_output_possible(const struct net_device *dev) +bool mpls_output_possible(const struct net_device *dev) { return dev && (dev->flags & IFF_UP) && netif_carrier_ok(dev); } +EXPORT_SYMBOL_GPL(mpls_output_possible); static unsigned int mpls_rt_header_size(const struct mpls_route *rt) { @@ -69,13 +86,14 @@ static unsigned int mpls_rt_header_size(const struct mpls_route *rt) return rt->rt_labels * sizeof(struct mpls_shim_hdr); } -static unsigned int mpls_dev_mtu(const struct net_device *dev) +unsigned int mpls_dev_mtu(const struct net_device *dev) { /* The amount of data the layer 2 frame can hold */ return dev->mtu; } +EXPORT_SYMBOL_GPL(mpls_dev_mtu); -static bool mpls_pkt_too_big(const struct sk_buff *skb, unsigned int mtu) +bool mpls_pkt_too_big(const struct sk_buff *skb, unsigned int mtu) { if (skb->len <= mtu) return false; @@ -85,20 +103,13 @@ static bool mpls_pkt_too_big(const struct sk_buff *skb, unsigned int mtu) return true; } +EXPORT_SYMBOL_GPL(mpls_pkt_too_big); static bool mpls_egress(struct mpls_route *rt, struct sk_buff *skb, struct mpls_entry_decoded dec) { - /* RFC4385 and RFC5586 encode other packets in mpls such that - * they don't conflict with the ip version number, making - * decoding by examining the ip version correct in everything - * except for the strangest cases. - * - * The strange cases if we choose to support them will require - * manual configuration. - */ - struct iphdr *hdr4; - bool success = true; + enum mpls_payload_type payload_type; + bool success = false; /* The IPv4 code below accesses through the IPv4 header * checksum, which is 12 bytes into the packet. @@ -113,23 +124,32 @@ static bool mpls_egress(struct mpls_route *rt, struct sk_buff *skb, if (!pskb_may_pull(skb, 12)) return false; - /* Use ip_hdr to find the ip protocol version */ - hdr4 = ip_hdr(skb); - if (hdr4->version == 4) { + payload_type = rt->rt_payload_type; + if (payload_type == MPT_UNSPEC) + payload_type = ip_hdr(skb)->version; + + switch (payload_type) { + case MPT_IPV4: { + struct iphdr *hdr4 = ip_hdr(skb); skb->protocol = htons(ETH_P_IP); csum_replace2(&hdr4->check, htons(hdr4->ttl << 8), htons(dec.ttl << 8)); hdr4->ttl = dec.ttl; + success = true; + break; } - else if (hdr4->version == 6) { + case MPT_IPV6: { struct ipv6hdr *hdr6 = ipv6_hdr(skb); skb->protocol = htons(ETH_P_IPV6); hdr6->hop_limit = dec.ttl; + success = true; + break; + } + case MPT_UNSPEC: + break; } - else - /* version 0 and version 1 are used by pseudo wires */ - success = false; + return success; } @@ -248,16 +268,17 @@ static const struct nla_policy rtm_mpls_policy[RTA_MAX+1] = { }; struct mpls_route_config { - u32 rc_protocol; - u32 rc_ifindex; - u16 rc_via_table; - u16 rc_via_alen; - u8 rc_via[MAX_VIA_ALEN]; - u32 rc_label; - u32 rc_output_labels; - u32 rc_output_label[MAX_NEW_LABELS]; - u32 rc_nlflags; - struct nl_info rc_nlinfo; + u32 rc_protocol; + u32 rc_ifindex; + u16 rc_via_table; + u16 rc_via_alen; + u8 rc_via[MAX_VIA_ALEN]; + u32 rc_label; + u32 rc_output_labels; + u32 rc_output_label[MAX_NEW_LABELS]; + u32 rc_nlflags; + enum mpls_payload_type rc_payload_type; + struct nl_info rc_nlinfo; }; static struct mpls_route *mpls_rt_alloc(size_t alen) @@ -286,7 +307,7 @@ static void mpls_notify_route(struct net *net, unsigned index, struct mpls_route *rt = new ? new : old; unsigned nlm_flags = (old && new) ? NLM_F_REPLACE : 0; /* Ignore reserved labels for now */ - if (rt && (index >= 16)) + if (rt && (index >= MPLS_LABEL_FIRST_UNRESERVED)) rtmsg_lfib(event, index, rt, nlh, net, portid, nlm_flags); } @@ -320,13 +341,96 @@ static unsigned find_free_label(struct net *net) platform_label = rtnl_dereference(net->mpls.platform_label); platform_labels = net->mpls.platform_labels; - for (index = 16; index < platform_labels; index++) { + for (index = MPLS_LABEL_FIRST_UNRESERVED; index < platform_labels; + index++) { if (!rtnl_dereference(platform_label[index])) return index; } return LABEL_NOT_SPECIFIED; } +#if IS_ENABLED(CONFIG_INET) +static struct net_device *inet_fib_lookup_dev(struct net *net, void *addr) +{ + struct net_device *dev; + struct rtable *rt; + struct in_addr daddr; + + memcpy(&daddr, addr, sizeof(struct in_addr)); + rt = ip_route_output(net, daddr.s_addr, 0, 0, 0); + if (IS_ERR(rt)) + return ERR_CAST(rt); + + dev = rt->dst.dev; + dev_hold(dev); + + ip_rt_put(rt); + + return dev; +} +#else +static struct net_device *inet_fib_lookup_dev(struct net *net, void *addr) +{ + return ERR_PTR(-EAFNOSUPPORT); +} +#endif + +#if IS_ENABLED(CONFIG_IPV6) +static struct net_device *inet6_fib_lookup_dev(struct net *net, void *addr) +{ + struct net_device *dev; + struct dst_entry *dst; + struct flowi6 fl6; + int err; + + if (!ipv6_stub) + return ERR_PTR(-EAFNOSUPPORT); + + memset(&fl6, 0, sizeof(fl6)); + memcpy(&fl6.daddr, addr, sizeof(struct in6_addr)); + err = ipv6_stub->ipv6_dst_lookup(net, NULL, &dst, &fl6); + if (err) + return ERR_PTR(err); + + dev = dst->dev; + dev_hold(dev); + dst_release(dst); + + return dev; +} +#else +static struct net_device *inet6_fib_lookup_dev(struct net *net, void *addr) +{ + return ERR_PTR(-EAFNOSUPPORT); +} +#endif + +static struct net_device *find_outdev(struct net *net, + struct mpls_route_config *cfg) +{ + struct net_device *dev = NULL; + + if (!cfg->rc_ifindex) { + switch (cfg->rc_via_table) { + case NEIGH_ARP_TABLE: + dev = inet_fib_lookup_dev(net, cfg->rc_via); + break; + case NEIGH_ND_TABLE: + dev = inet6_fib_lookup_dev(net, cfg->rc_via); + break; + case NEIGH_LINK_TABLE: + break; + } + } else { + dev = dev_get_by_index(net, cfg->rc_ifindex); + } + + if (!dev) + return ERR_PTR(-ENODEV); + + return dev; +} + static int mpls_route_add(struct mpls_route_config *cfg) { struct mpls_route __rcu **platform_label; @@ -345,8 +449,8 @@ static int mpls_route_add(struct mpls_route_config *cfg) index = find_free_label(net); } - /* The first 16 labels are reserved, and may not be set */ - if (index < 16) + /* Reserved labels may not be set */ + if (index < MPLS_LABEL_FIRST_UNRESERVED) goto errout; /* The full 20 bit range may not be supported. */ @@ -357,10 +461,12 @@ static int mpls_route_add(struct mpls_route_config *cfg) if (cfg->rc_output_labels > MAX_NEW_LABELS) goto errout; - err = -ENODEV; - dev = dev_get_by_index(net, cfg->rc_ifindex); - if (!dev) + dev = find_outdev(net, cfg); + if (IS_ERR(dev)) { + err = PTR_ERR(dev); + dev = NULL; goto errout; + } /* Ensure this is a supported device */ err = -EINVAL; @@ -401,6 +507,7 @@ static int mpls_route_add(struct mpls_route_config *cfg) rt->rt_label[i] = cfg->rc_output_label[i]; rt->rt_protocol = cfg->rc_protocol; RCU_INIT_POINTER(rt->rt_dev, dev); + rt->rt_payload_type = cfg->rc_payload_type; rt->rt_via_table = cfg->rc_via_table; memcpy(rt->rt_via, cfg->rc_via, cfg->rc_via_alen); @@ -423,8 +530,8 @@ static int mpls_route_del(struct mpls_route_config *cfg) index = cfg->rc_label; - /* The first 16 labels are reserved, and may not be removed */ - if (index < 16) + /* Reserved labels may not be removed */ + if (index < MPLS_LABEL_FIRST_UNRESERVED) goto errout; /* The full 20 bit range may not be supported */ @@ -626,6 +733,7 @@ int nla_put_labels(struct sk_buff *skb, int attrtype, return 0; } +EXPORT_SYMBOL_GPL(nla_put_labels); int nla_get_labels(const struct nlattr *nla, u32 max_labels, u32 *labels, u32 label[]) @@ -671,6 +779,7 @@ int nla_get_labels(const struct nlattr *nla, *labels = nla_labels; return 0; } +EXPORT_SYMBOL_GPL(nla_get_labels); static int rtm_to_route_config(struct sk_buff *skb, struct nlmsghdr *nlh, struct mpls_route_config *cfg) @@ -740,8 +849,8 @@ static int rtm_to_route_config(struct sk_buff *skb, struct nlmsghdr *nlh, &cfg->rc_label)) goto errout; - /* The first 16 labels are reserved, and may not be set */ - if (cfg->rc_label < 16) + /* Reserved labels may not be set */ + if (cfg->rc_label < MPLS_LABEL_FIRST_UNRESERVED) goto errout; break; @@ -866,8 +975,8 @@ static int mpls_dump_routes(struct sk_buff *skb, struct netlink_callback *cb) ASSERT_RTNL(); index = cb->args[0]; - if (index < 16) - index = 16; + if (index < MPLS_LABEL_FIRST_UNRESERVED) + index = MPLS_LABEL_FIRST_UNRESERVED; platform_label = rtnl_dereference(net->mpls.platform_label); platform_labels = net->mpls.platform_labels; @@ -953,6 +1062,7 @@ static int resize_platform_label_table(struct net *net, size_t limit) goto nort0; RCU_INIT_POINTER(rt0->rt_dev, lo); rt0->rt_protocol = RTPROT_KERNEL; + rt0->rt_payload_type = MPT_IPV4; rt0->rt_via_table = NEIGH_LINK_TABLE; memcpy(rt0->rt_via, lo->dev_addr, lo->addr_len); } @@ -963,6 +1073,7 @@ static int resize_platform_label_table(struct net *net, size_t limit) goto nort2; RCU_INIT_POINTER(rt2->rt_dev, lo); rt2->rt_protocol = RTPROT_KERNEL; + rt2->rt_payload_type = MPT_IPV6; rt2->rt_via_table = NEIGH_LINK_TABLE; memcpy(rt2->rt_via, lo->dev_addr, lo->addr_len); } @@ -1066,8 +1177,10 @@ static int mpls_net_init(struct net *net) table[0].data = net; net->mpls.ctl = register_net_sysctl(net, "net/mpls", table); - if (net->mpls.ctl == NULL) + if (net->mpls.ctl == NULL) { + kfree(table); return -ENOMEM; + } return 0; } diff --git a/net/mpls/internal.h b/net/mpls/internal.h index 8cabeb5a1cb9..2681a4ba6c37 100644 --- a/net/mpls/internal.h +++ b/net/mpls/internal.h @@ -50,7 +50,12 @@ static inline struct mpls_entry_decoded mpls_entry_decode(struct mpls_shim_hdr * return result; } -int nla_put_labels(struct sk_buff *skb, int attrtype, u8 labels, const u32 label[]); -int nla_get_labels(const struct nlattr *nla, u32 max_labels, u32 *labels, u32 label[]); +int nla_put_labels(struct sk_buff *skb, int attrtype, u8 labels, + const u32 label[]); +int nla_get_labels(const struct nlattr *nla, u32 max_labels, u32 *labels, + u32 label[]); +bool mpls_output_possible(const struct net_device *dev); +unsigned int mpls_dev_mtu(const struct net_device *dev); +bool mpls_pkt_too_big(const struct sk_buff *skb, unsigned int mtu); #endif /* MPLS_INTERNAL_H */ diff --git a/net/mpls/mpls_iptunnel.c b/net/mpls/mpls_iptunnel.c new file mode 100644 index 000000000000..21e70bc9af98 --- /dev/null +++ b/net/mpls/mpls_iptunnel.c @@ -0,0 +1,231 @@ +/* + * mpls tunnels An implementation mpls tunnels using the light weight tunnel + * infrastructure + * + * Authors: Roopa Prabhu, <roopa@cumulusnetworks.com> + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + * + */ +#include <linux/types.h> +#include <linux/skbuff.h> +#include <linux/net.h> +#include <linux/module.h> +#include <linux/mpls.h> +#include <linux/vmalloc.h> +#include <net/ip.h> +#include <net/dst.h> +#include <net/lwtunnel.h> +#include <net/netevent.h> +#include <net/netns/generic.h> +#include <net/ip6_fib.h> +#include <net/route.h> +#include <net/mpls_iptunnel.h> +#include <linux/mpls_iptunnel.h> +#include "internal.h" + +static const struct nla_policy mpls_iptunnel_policy[MPLS_IPTUNNEL_MAX + 1] = { + [MPLS_IPTUNNEL_DST] = { .type = NLA_U32 }, +}; + +static unsigned int mpls_encap_size(struct mpls_iptunnel_encap *en) +{ + /* The size of the layer 2.5 labels to be added for this route */ + return en->labels * sizeof(struct mpls_shim_hdr); +} + +int mpls_output(struct sock *sk, struct sk_buff *skb) +{ + struct mpls_iptunnel_encap *tun_encap_info; + struct mpls_shim_hdr *hdr; + struct net_device *out_dev; + unsigned int hh_len; + unsigned int new_header_size; + unsigned int mtu; + struct dst_entry *dst = skb_dst(skb); + struct rtable *rt = NULL; + struct rt6_info *rt6 = NULL; + int err = 0; + bool bos; + int i; + unsigned int ttl; + + /* Obtain the ttl */ + if (skb->protocol == htons(ETH_P_IP)) { + ttl = ip_hdr(skb)->ttl; + rt = (struct rtable *)dst; + } else if (skb->protocol == htons(ETH_P_IPV6)) { + ttl = ipv6_hdr(skb)->hop_limit; + rt6 = (struct rt6_info *)dst; + } else { + goto drop; + } + + skb_orphan(skb); + + /* Find the output device */ + out_dev = dst->dev; + if (!mpls_output_possible(out_dev) || + !dst->lwtstate || skb_warn_if_lro(skb)) + goto drop; + + skb_forward_csum(skb); + + tun_encap_info = mpls_lwtunnel_encap(dst->lwtstate); + + /* Verify the destination can hold the packet */ + new_header_size = mpls_encap_size(tun_encap_info); + mtu = mpls_dev_mtu(out_dev); + if (mpls_pkt_too_big(skb, mtu - new_header_size)) + goto drop; + + hh_len = LL_RESERVED_SPACE(out_dev); + if (!out_dev->header_ops) + hh_len = 0; + + /* Ensure there is enough space for the headers in the skb */ + if (skb_cow(skb, hh_len + new_header_size)) + goto drop; + + skb_push(skb, new_header_size); + skb_reset_network_header(skb); + + skb->dev = out_dev; + skb->protocol = htons(ETH_P_MPLS_UC); + + /* Push the new labels */ + hdr = mpls_hdr(skb); + bos = true; + for (i = tun_encap_info->labels - 1; i >= 0; i--) { + hdr[i] = mpls_entry_encode(tun_encap_info->label[i], + ttl, 0, bos); + bos = false; + } + + if (rt) + err = neigh_xmit(NEIGH_ARP_TABLE, out_dev, &rt->rt_gateway, + skb); + else if (rt6) + err = neigh_xmit(NEIGH_ND_TABLE, out_dev, &rt6->rt6i_gateway, + skb); + if (err) + net_dbg_ratelimited("%s: packet transmission failed: %d\n", + __func__, err); + + return 0; + +drop: + kfree_skb(skb); + return -EINVAL; +} + +static int mpls_build_state(struct net_device *dev, struct nlattr *nla, + unsigned int family, const void *cfg, + struct lwtunnel_state **ts) +{ + struct mpls_iptunnel_encap *tun_encap_info; + struct nlattr *tb[MPLS_IPTUNNEL_MAX + 1]; + struct lwtunnel_state *newts; + int tun_encap_info_len; + int ret; + + ret = nla_parse_nested(tb, MPLS_IPTUNNEL_MAX, nla, + mpls_iptunnel_policy); + if (ret < 0) + return ret; + + if (!tb[MPLS_IPTUNNEL_DST]) + return -EINVAL; + + tun_encap_info_len = sizeof(*tun_encap_info); + + newts = lwtunnel_state_alloc(tun_encap_info_len); + if (!newts) + return -ENOMEM; + + newts->len = tun_encap_info_len; + tun_encap_info = mpls_lwtunnel_encap(newts); + ret = nla_get_labels(tb[MPLS_IPTUNNEL_DST], MAX_NEW_LABELS, + &tun_encap_info->labels, tun_encap_info->label); + if (ret) + goto errout; + newts->type = LWTUNNEL_ENCAP_MPLS; + newts->flags |= LWTUNNEL_STATE_OUTPUT_REDIRECT; + + *ts = newts; + + return 0; + +errout: + kfree(newts); + *ts = NULL; + + return ret; +} + +static int mpls_fill_encap_info(struct sk_buff *skb, + struct lwtunnel_state *lwtstate) +{ + struct mpls_iptunnel_encap *tun_encap_info; + + tun_encap_info = mpls_lwtunnel_encap(lwtstate); + + if (nla_put_labels(skb, MPLS_IPTUNNEL_DST, tun_encap_info->labels, + tun_encap_info->label)) + goto nla_put_failure; + + return 0; + +nla_put_failure: + return -EMSGSIZE; +} + +static int mpls_encap_nlsize(struct lwtunnel_state *lwtstate) +{ + struct mpls_iptunnel_encap *tun_encap_info; + + tun_encap_info = mpls_lwtunnel_encap(lwtstate); + + return nla_total_size(tun_encap_info->labels * 4); +} + +static int mpls_encap_cmp(struct lwtunnel_state *a, struct lwtunnel_state *b) +{ + struct mpls_iptunnel_encap *a_hdr = mpls_lwtunnel_encap(a); + struct mpls_iptunnel_encap *b_hdr = mpls_lwtunnel_encap(b); + int l; + + if (a_hdr->labels != b_hdr->labels) + return 1; + + for (l = 0; l < MAX_NEW_LABELS; l++) + if (a_hdr->label[l] != b_hdr->label[l]) + return 1; + return 0; +} + +static const struct lwtunnel_encap_ops mpls_iptun_ops = { + .build_state = mpls_build_state, + .output = mpls_output, + .fill_encap = mpls_fill_encap_info, + .get_encap_size = mpls_encap_nlsize, + .cmp_encap = mpls_encap_cmp, +}; + +static int __init mpls_iptunnel_init(void) +{ + return lwtunnel_encap_add_ops(&mpls_iptun_ops, LWTUNNEL_ENCAP_MPLS); +} +module_init(mpls_iptunnel_init); + +static void __exit mpls_iptunnel_exit(void) +{ + lwtunnel_encap_del_ops(&mpls_iptun_ops, LWTUNNEL_ENCAP_MPLS); +} +module_exit(mpls_iptunnel_exit); + +MODULE_DESCRIPTION("MultiProtocol Label Switching IP Tunnels"); +MODULE_LICENSE("GPL v2"); diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig index 6eae69a698ed..3e1b4abf1897 100644 --- a/net/netfilter/Kconfig +++ b/net/netfilter/Kconfig @@ -867,6 +867,8 @@ config NETFILTER_XT_TARGET_TEE depends on NETFILTER_ADVANCED depends on IPV6 || IPV6=n depends on !NF_CONNTRACK || NF_CONNTRACK + select NF_DUP_IPV4 + select NF_DUP_IPV6 if IP6_NF_IPTABLES ---help--- This option adds a "TEE" target with which a packet can be cloned and this clone be rerouted to another nexthop. diff --git a/net/netfilter/core.c b/net/netfilter/core.c index a0e54974e2c9..8e47f8113495 100644 --- a/net/netfilter/core.c +++ b/net/netfilter/core.c @@ -34,6 +34,9 @@ EXPORT_SYMBOL(nf_afinfo); const struct nf_ipv6_ops __rcu *nf_ipv6_ops __read_mostly; EXPORT_SYMBOL_GPL(nf_ipv6_ops); +DEFINE_PER_CPU(bool, nf_skb_duplicated); +EXPORT_SYMBOL_GPL(nf_skb_duplicated); + int nf_register_afinfo(const struct nf_afinfo *afinfo) { mutex_lock(&afinfo_mutex); @@ -52,9 +55,6 @@ void nf_unregister_afinfo(const struct nf_afinfo *afinfo) } EXPORT_SYMBOL_GPL(nf_unregister_afinfo); -struct list_head nf_hooks[NFPROTO_NUMPROTO][NF_MAX_HOOKS] __read_mostly; -EXPORT_SYMBOL(nf_hooks); - #ifdef HAVE_JUMP_LABEL struct static_key nf_hooks_needed[NFPROTO_NUMPROTO][NF_MAX_HOOKS]; EXPORT_SYMBOL(nf_hooks_needed); @@ -62,63 +62,166 @@ EXPORT_SYMBOL(nf_hooks_needed); static DEFINE_MUTEX(nf_hook_mutex); -int nf_register_hook(struct nf_hook_ops *reg) +static struct list_head *nf_find_hook_list(struct net *net, + const struct nf_hook_ops *reg) { - struct list_head *nf_hook_list; - struct nf_hook_ops *elem; + struct list_head *hook_list = NULL; - mutex_lock(&nf_hook_mutex); - switch (reg->pf) { - case NFPROTO_NETDEV: + if (reg->pf != NFPROTO_NETDEV) + hook_list = &net->nf.hooks[reg->pf][reg->hooknum]; + else if (reg->hooknum == NF_NETDEV_INGRESS) { #ifdef CONFIG_NETFILTER_INGRESS - if (reg->hooknum == NF_NETDEV_INGRESS) { - BUG_ON(reg->dev == NULL); - nf_hook_list = ®->dev->nf_hooks_ingress; - net_inc_ingress_queue(); - break; - } + if (reg->dev && dev_net(reg->dev) == net) + hook_list = ®->dev->nf_hooks_ingress; #endif - /* Fall through. */ - default: - nf_hook_list = &nf_hooks[reg->pf][reg->hooknum]; - break; } + return hook_list; +} + +struct nf_hook_entry { + const struct nf_hook_ops *orig_ops; + struct nf_hook_ops ops; +}; + +int nf_register_net_hook(struct net *net, const struct nf_hook_ops *reg) +{ + struct list_head *hook_list; + struct nf_hook_entry *entry; + struct nf_hook_ops *elem; - list_for_each_entry(elem, nf_hook_list, list) { + entry = kmalloc(sizeof(*entry), GFP_KERNEL); + if (!entry) + return -ENOMEM; + + entry->orig_ops = reg; + entry->ops = *reg; + + hook_list = nf_find_hook_list(net, reg); + if (!hook_list) { + kfree(entry); + return -ENOENT; + } + + mutex_lock(&nf_hook_mutex); + list_for_each_entry(elem, hook_list, list) { if (reg->priority < elem->priority) break; } - list_add_rcu(®->list, elem->list.prev); + list_add_rcu(&entry->ops.list, elem->list.prev); mutex_unlock(&nf_hook_mutex); +#ifdef CONFIG_NETFILTER_INGRESS + if (reg->pf == NFPROTO_NETDEV && reg->hooknum == NF_NETDEV_INGRESS) + net_inc_ingress_queue(); +#endif #ifdef HAVE_JUMP_LABEL static_key_slow_inc(&nf_hooks_needed[reg->pf][reg->hooknum]); #endif return 0; } -EXPORT_SYMBOL(nf_register_hook); +EXPORT_SYMBOL(nf_register_net_hook); -void nf_unregister_hook(struct nf_hook_ops *reg) +void nf_unregister_net_hook(struct net *net, const struct nf_hook_ops *reg) { + struct list_head *hook_list; + struct nf_hook_entry *entry; + struct nf_hook_ops *elem; + + hook_list = nf_find_hook_list(net, reg); + if (!hook_list) + return; + mutex_lock(&nf_hook_mutex); - list_del_rcu(®->list); - mutex_unlock(&nf_hook_mutex); - switch (reg->pf) { - case NFPROTO_NETDEV: -#ifdef CONFIG_NETFILTER_INGRESS - if (reg->hooknum == NF_NETDEV_INGRESS) { - net_dec_ingress_queue(); + list_for_each_entry(elem, hook_list, list) { + entry = container_of(elem, struct nf_hook_entry, ops); + if (entry->orig_ops == reg) { + list_del_rcu(&entry->ops.list); break; } - break; -#endif - default: - break; } + mutex_unlock(&nf_hook_mutex); + if (&elem->list == hook_list) { + WARN(1, "nf_unregister_net_hook: hook not found!\n"); + return; + } +#ifdef CONFIG_NETFILTER_INGRESS + if (reg->pf == NFPROTO_NETDEV && reg->hooknum == NF_NETDEV_INGRESS) + net_dec_ingress_queue(); +#endif #ifdef HAVE_JUMP_LABEL static_key_slow_dec(&nf_hooks_needed[reg->pf][reg->hooknum]); #endif synchronize_net(); - nf_queue_nf_hook_drop(reg); + nf_queue_nf_hook_drop(net, &entry->ops); + kfree(entry); +} +EXPORT_SYMBOL(nf_unregister_net_hook); + +int nf_register_net_hooks(struct net *net, const struct nf_hook_ops *reg, + unsigned int n) +{ + unsigned int i; + int err = 0; + + for (i = 0; i < n; i++) { + err = nf_register_net_hook(net, ®[i]); + if (err) + goto err; + } + return err; + +err: + if (i > 0) + nf_unregister_net_hooks(net, reg, i); + return err; +} +EXPORT_SYMBOL(nf_register_net_hooks); + +void nf_unregister_net_hooks(struct net *net, const struct nf_hook_ops *reg, + unsigned int n) +{ + while (n-- > 0) + nf_unregister_net_hook(net, ®[n]); +} +EXPORT_SYMBOL(nf_unregister_net_hooks); + +static LIST_HEAD(nf_hook_list); + +int nf_register_hook(struct nf_hook_ops *reg) +{ + struct net *net, *last; + int ret; + + rtnl_lock(); + for_each_net(net) { + ret = nf_register_net_hook(net, reg); + if (ret && ret != -ENOENT) + goto rollback; + } + list_add_tail(®->list, &nf_hook_list); + rtnl_unlock(); + + return 0; +rollback: + last = net; + for_each_net(net) { + if (net == last) + break; + nf_unregister_net_hook(net, reg); + } + rtnl_unlock(); + return ret; +} +EXPORT_SYMBOL(nf_register_hook); + +void nf_unregister_hook(struct nf_hook_ops *reg) +{ + struct net *net; + + rtnl_lock(); + list_del(®->list); + for_each_net(net) + nf_unregister_net_hook(net, reg); + rtnl_unlock(); } EXPORT_SYMBOL(nf_unregister_hook); @@ -285,9 +388,12 @@ EXPORT_SYMBOL(nf_conntrack_destroy); struct nfq_ct_hook __rcu *nfq_ct_hook __read_mostly; EXPORT_SYMBOL_GPL(nfq_ct_hook); -struct nfq_ct_nat_hook __rcu *nfq_ct_nat_hook __read_mostly; -EXPORT_SYMBOL_GPL(nfq_ct_nat_hook); - +/* Built-in default zone used e.g. by modules. */ +const struct nf_conntrack_zone nf_ct_zone_dflt = { + .id = NF_CT_DEFAULT_ZONE_ID, + .dir = NF_CT_DEFAULT_ZONE_DIR, +}; +EXPORT_SYMBOL_GPL(nf_ct_zone_dflt); #endif /* CONFIG_NF_CONNTRACK */ #ifdef CONFIG_NF_NAT_NEEDED @@ -295,8 +401,46 @@ void (*nf_nat_decode_session_hook)(struct sk_buff *, struct flowi *); EXPORT_SYMBOL(nf_nat_decode_session_hook); #endif +static int nf_register_hook_list(struct net *net) +{ + struct nf_hook_ops *elem; + int ret; + + rtnl_lock(); + list_for_each_entry(elem, &nf_hook_list, list) { + ret = nf_register_net_hook(net, elem); + if (ret && ret != -ENOENT) + goto out_undo; + } + rtnl_unlock(); + return 0; + +out_undo: + list_for_each_entry_continue_reverse(elem, &nf_hook_list, list) + nf_unregister_net_hook(net, elem); + rtnl_unlock(); + return ret; +} + +static void nf_unregister_hook_list(struct net *net) +{ + struct nf_hook_ops *elem; + + rtnl_lock(); + list_for_each_entry(elem, &nf_hook_list, list) + nf_unregister_net_hook(net, elem); + rtnl_unlock(); +} + static int __net_init netfilter_net_init(struct net *net) { + int i, h, ret; + + for (i = 0; i < ARRAY_SIZE(net->nf.hooks); i++) { + for (h = 0; h < NF_MAX_HOOKS; h++) + INIT_LIST_HEAD(&net->nf.hooks[i][h]); + } + #ifdef CONFIG_PROC_FS net->nf.proc_netfilter = proc_net_mkdir(net, "netfilter", net->proc_net); @@ -307,11 +451,16 @@ static int __net_init netfilter_net_init(struct net *net) return -ENOMEM; } #endif - return 0; + ret = nf_register_hook_list(net); + if (ret) + remove_proc_entry("netfilter", net->proc_net); + + return ret; } static void __net_exit netfilter_net_exit(struct net *net) { + nf_unregister_hook_list(net); remove_proc_entry("netfilter", net->proc_net); } @@ -322,12 +471,7 @@ static struct pernet_operations netfilter_net_ops = { int __init netfilter_init(void) { - int i, h, ret; - - for (i = 0; i < ARRAY_SIZE(nf_hooks); i++) { - for (h = 0; h < NF_MAX_HOOKS; h++) - INIT_LIST_HEAD(&nf_hooks[i][h]); - } + int ret; ret = register_pernet_subsys(&netfilter_net_ops); if (ret < 0) diff --git a/net/netfilter/ipset/ip_set_hash_gen.h b/net/netfilter/ipset/ip_set_hash_gen.h index afe905c208af..691b54fcaf2a 100644 --- a/net/netfilter/ipset/ip_set_hash_gen.h +++ b/net/netfilter/ipset/ip_set_hash_gen.h @@ -152,9 +152,13 @@ htable_bits(u32 hashsize) #define SET_HOST_MASK(family) (family == AF_INET ? 32 : 128) #ifdef IP_SET_HASH_WITH_NET0 +/* cidr from 0 to SET_HOST_MASK() value and c = cidr + 1 */ #define NLEN(family) (SET_HOST_MASK(family) + 1) +#define CIDR_POS(c) ((c) - 1) #else +/* cidr from 1 to SET_HOST_MASK() value and c = cidr + 1 */ #define NLEN(family) SET_HOST_MASK(family) +#define CIDR_POS(c) ((c) - 2) #endif #else @@ -305,7 +309,7 @@ mtype_add_cidr(struct htype *h, u8 cidr, u8 nets_length, u8 n) } else if (h->nets[i].cidr[n] < cidr) { j = i; } else if (h->nets[i].cidr[n] == cidr) { - h->nets[cidr - 1].nets[n]++; + h->nets[CIDR_POS(cidr)].nets[n]++; return; } } @@ -314,7 +318,7 @@ mtype_add_cidr(struct htype *h, u8 cidr, u8 nets_length, u8 n) h->nets[i].cidr[n] = h->nets[i - 1].cidr[n]; } h->nets[i].cidr[n] = cidr; - h->nets[cidr - 1].nets[n] = 1; + h->nets[CIDR_POS(cidr)].nets[n] = 1; } static void @@ -325,8 +329,8 @@ mtype_del_cidr(struct htype *h, u8 cidr, u8 nets_length, u8 n) for (i = 0; i < nets_length; i++) { if (h->nets[i].cidr[n] != cidr) continue; - h->nets[cidr - 1].nets[n]--; - if (h->nets[cidr - 1].nets[n] > 0) + h->nets[CIDR_POS(cidr)].nets[n]--; + if (h->nets[CIDR_POS(cidr)].nets[n] > 0) return; for (j = i; j < net_end && h->nets[j].cidr[n]; j++) h->nets[j].cidr[n] = h->nets[j + 1].cidr[n]; diff --git a/net/netfilter/ipset/ip_set_hash_netnet.c b/net/netfilter/ipset/ip_set_hash_netnet.c index 3c862c0a76d1..a93dfebffa81 100644 --- a/net/netfilter/ipset/ip_set_hash_netnet.c +++ b/net/netfilter/ipset/ip_set_hash_netnet.c @@ -131,6 +131,13 @@ hash_netnet4_data_next(struct hash_netnet4_elem *next, #define HOST_MASK 32 #include "ip_set_hash_gen.h" +static void +hash_netnet4_init(struct hash_netnet4_elem *e) +{ + e->cidr[0] = HOST_MASK; + e->cidr[1] = HOST_MASK; +} + static int hash_netnet4_kadt(struct ip_set *set, const struct sk_buff *skb, const struct xt_action_param *par, @@ -160,7 +167,7 @@ hash_netnet4_uadt(struct ip_set *set, struct nlattr *tb[], { const struct hash_netnet *h = set->data; ipset_adtfn adtfn = set->variant->adt[adt]; - struct hash_netnet4_elem e = { .cidr = { HOST_MASK, HOST_MASK, }, }; + struct hash_netnet4_elem e = { }; struct ip_set_ext ext = IP_SET_INIT_UEXT(set); u32 ip = 0, ip_to = 0, last; u32 ip2 = 0, ip2_from = 0, ip2_to = 0, last2; @@ -169,6 +176,7 @@ hash_netnet4_uadt(struct ip_set *set, struct nlattr *tb[], if (tb[IPSET_ATTR_LINENO]) *lineno = nla_get_u32(tb[IPSET_ATTR_LINENO]); + hash_netnet4_init(&e); if (unlikely(!tb[IPSET_ATTR_IP] || !tb[IPSET_ATTR_IP2] || !ip_set_optattr_netorder(tb, IPSET_ATTR_CADT_FLAGS))) return -IPSET_ERR_PROTOCOL; @@ -357,6 +365,13 @@ hash_netnet6_data_next(struct hash_netnet4_elem *next, #define IP_SET_EMIT_CREATE #include "ip_set_hash_gen.h" +static void +hash_netnet6_init(struct hash_netnet6_elem *e) +{ + e->cidr[0] = HOST_MASK; + e->cidr[1] = HOST_MASK; +} + static int hash_netnet6_kadt(struct ip_set *set, const struct sk_buff *skb, const struct xt_action_param *par, @@ -385,13 +400,14 @@ hash_netnet6_uadt(struct ip_set *set, struct nlattr *tb[], enum ipset_adt adt, u32 *lineno, u32 flags, bool retried) { ipset_adtfn adtfn = set->variant->adt[adt]; - struct hash_netnet6_elem e = { .cidr = { HOST_MASK, HOST_MASK, }, }; + struct hash_netnet6_elem e = { }; struct ip_set_ext ext = IP_SET_INIT_UEXT(set); int ret; if (tb[IPSET_ATTR_LINENO]) *lineno = nla_get_u32(tb[IPSET_ATTR_LINENO]); + hash_netnet6_init(&e); if (unlikely(!tb[IPSET_ATTR_IP] || !tb[IPSET_ATTR_IP2] || !ip_set_optattr_netorder(tb, IPSET_ATTR_CADT_FLAGS))) return -IPSET_ERR_PROTOCOL; diff --git a/net/netfilter/ipset/ip_set_hash_netportnet.c b/net/netfilter/ipset/ip_set_hash_netportnet.c index 0c68734f5cc4..9a14c237830f 100644 --- a/net/netfilter/ipset/ip_set_hash_netportnet.c +++ b/net/netfilter/ipset/ip_set_hash_netportnet.c @@ -142,6 +142,13 @@ hash_netportnet4_data_next(struct hash_netportnet4_elem *next, #define HOST_MASK 32 #include "ip_set_hash_gen.h" +static void +hash_netportnet4_init(struct hash_netportnet4_elem *e) +{ + e->cidr[0] = HOST_MASK; + e->cidr[1] = HOST_MASK; +} + static int hash_netportnet4_kadt(struct ip_set *set, const struct sk_buff *skb, const struct xt_action_param *par, @@ -175,7 +182,7 @@ hash_netportnet4_uadt(struct ip_set *set, struct nlattr *tb[], { const struct hash_netportnet *h = set->data; ipset_adtfn adtfn = set->variant->adt[adt]; - struct hash_netportnet4_elem e = { .cidr = { HOST_MASK, HOST_MASK, }, }; + struct hash_netportnet4_elem e = { }; struct ip_set_ext ext = IP_SET_INIT_UEXT(set); u32 ip = 0, ip_to = 0, ip_last, p = 0, port, port_to; u32 ip2_from = 0, ip2_to = 0, ip2_last, ip2; @@ -185,6 +192,7 @@ hash_netportnet4_uadt(struct ip_set *set, struct nlattr *tb[], if (tb[IPSET_ATTR_LINENO]) *lineno = nla_get_u32(tb[IPSET_ATTR_LINENO]); + hash_netportnet4_init(&e); if (unlikely(!tb[IPSET_ATTR_IP] || !tb[IPSET_ATTR_IP2] || !ip_set_attr_netorder(tb, IPSET_ATTR_PORT) || !ip_set_optattr_netorder(tb, IPSET_ATTR_PORT_TO) || @@ -412,6 +420,13 @@ hash_netportnet6_data_next(struct hash_netportnet4_elem *next, #define IP_SET_EMIT_CREATE #include "ip_set_hash_gen.h" +static void +hash_netportnet6_init(struct hash_netportnet6_elem *e) +{ + e->cidr[0] = HOST_MASK; + e->cidr[1] = HOST_MASK; +} + static int hash_netportnet6_kadt(struct ip_set *set, const struct sk_buff *skb, const struct xt_action_param *par, @@ -445,7 +460,7 @@ hash_netportnet6_uadt(struct ip_set *set, struct nlattr *tb[], { const struct hash_netportnet *h = set->data; ipset_adtfn adtfn = set->variant->adt[adt]; - struct hash_netportnet6_elem e = { .cidr = { HOST_MASK, HOST_MASK, }, }; + struct hash_netportnet6_elem e = { }; struct ip_set_ext ext = IP_SET_INIT_UEXT(set); u32 port, port_to; bool with_ports = false; @@ -454,6 +469,7 @@ hash_netportnet6_uadt(struct ip_set *set, struct nlattr *tb[], if (tb[IPSET_ATTR_LINENO]) *lineno = nla_get_u32(tb[IPSET_ATTR_LINENO]); + hash_netportnet6_init(&e); if (unlikely(!tb[IPSET_ATTR_IP] || !tb[IPSET_ATTR_IP2] || !ip_set_attr_netorder(tb, IPSET_ATTR_PORT) || !ip_set_optattr_netorder(tb, IPSET_ATTR_PORT_TO) || diff --git a/net/netfilter/ipvs/Kconfig b/net/netfilter/ipvs/Kconfig index 3b6929dec748..b32fb0dbe237 100644 --- a/net/netfilter/ipvs/Kconfig +++ b/net/netfilter/ipvs/Kconfig @@ -162,6 +162,17 @@ config IP_VS_FO If you want to compile it in kernel, say Y. To compile it as a module, choose M here. If unsure, say N. +config IP_VS_OVF + tristate "weighted overflow scheduling" + ---help--- + The weighted overflow scheduling algorithm directs network + connections to the server with the highest weight that is + currently available and overflows to the next when active + connections exceed the node's weight. + + If you want to compile it in kernel, say Y. To compile it as a + module, choose M here. If unsure, say N. + config IP_VS_LBLC tristate "locality-based least-connection scheduling" ---help--- diff --git a/net/netfilter/ipvs/Makefile b/net/netfilter/ipvs/Makefile index 38b2723b2e3d..67f3f4389602 100644 --- a/net/netfilter/ipvs/Makefile +++ b/net/netfilter/ipvs/Makefile @@ -27,6 +27,7 @@ obj-$(CONFIG_IP_VS_WRR) += ip_vs_wrr.o obj-$(CONFIG_IP_VS_LC) += ip_vs_lc.o obj-$(CONFIG_IP_VS_WLC) += ip_vs_wlc.o obj-$(CONFIG_IP_VS_FO) += ip_vs_fo.o +obj-$(CONFIG_IP_VS_OVF) += ip_vs_ovf.o obj-$(CONFIG_IP_VS_LBLC) += ip_vs_lblc.o obj-$(CONFIG_IP_VS_LBLCR) += ip_vs_lblcr.o obj-$(CONFIG_IP_VS_DH) += ip_vs_dh.o diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c index 24c554201a76..1a23e91d50d8 100644 --- a/net/netfilter/ipvs/ip_vs_ctl.c +++ b/net/netfilter/ipvs/ip_vs_ctl.c @@ -2335,13 +2335,23 @@ do_ip_vs_set_ctl(struct sock *sk, int cmd, void __user *user, unsigned int len) cmd == IP_VS_SO_SET_STOPDAEMON) { struct ip_vs_daemon_user *dm = (struct ip_vs_daemon_user *)arg; - mutex_lock(&ipvs->sync_mutex); - if (cmd == IP_VS_SO_SET_STARTDAEMON) - ret = start_sync_thread(net, dm->state, dm->mcast_ifn, - dm->syncid); - else + if (cmd == IP_VS_SO_SET_STARTDAEMON) { + struct ipvs_sync_daemon_cfg cfg; + + memset(&cfg, 0, sizeof(cfg)); + strlcpy(cfg.mcast_ifn, dm->mcast_ifn, + sizeof(cfg.mcast_ifn)); + cfg.syncid = dm->syncid; + rtnl_lock(); + mutex_lock(&ipvs->sync_mutex); + ret = start_sync_thread(net, &cfg, dm->state); + mutex_unlock(&ipvs->sync_mutex); + rtnl_unlock(); + } else { + mutex_lock(&ipvs->sync_mutex); ret = stop_sync_thread(net, dm->state); - mutex_unlock(&ipvs->sync_mutex); + mutex_unlock(&ipvs->sync_mutex); + } goto out_dec; } @@ -2645,15 +2655,15 @@ do_ip_vs_get_ctl(struct sock *sk, int cmd, void __user *user, int *len) mutex_lock(&ipvs->sync_mutex); if (ipvs->sync_state & IP_VS_STATE_MASTER) { d[0].state = IP_VS_STATE_MASTER; - strlcpy(d[0].mcast_ifn, ipvs->master_mcast_ifn, + strlcpy(d[0].mcast_ifn, ipvs->mcfg.mcast_ifn, sizeof(d[0].mcast_ifn)); - d[0].syncid = ipvs->master_syncid; + d[0].syncid = ipvs->mcfg.syncid; } if (ipvs->sync_state & IP_VS_STATE_BACKUP) { d[1].state = IP_VS_STATE_BACKUP; - strlcpy(d[1].mcast_ifn, ipvs->backup_mcast_ifn, + strlcpy(d[1].mcast_ifn, ipvs->bcfg.mcast_ifn, sizeof(d[1].mcast_ifn)); - d[1].syncid = ipvs->backup_syncid; + d[1].syncid = ipvs->bcfg.syncid; } if (copy_to_user(user, &d, sizeof(d)) != 0) ret = -EFAULT; @@ -2808,6 +2818,11 @@ static const struct nla_policy ip_vs_daemon_policy[IPVS_DAEMON_ATTR_MAX + 1] = { [IPVS_DAEMON_ATTR_MCAST_IFN] = { .type = NLA_NUL_STRING, .len = IP_VS_IFNAME_MAXLEN }, [IPVS_DAEMON_ATTR_SYNC_ID] = { .type = NLA_U32 }, + [IPVS_DAEMON_ATTR_SYNC_MAXLEN] = { .type = NLA_U16 }, + [IPVS_DAEMON_ATTR_MCAST_GROUP] = { .type = NLA_U32 }, + [IPVS_DAEMON_ATTR_MCAST_GROUP6] = { .len = sizeof(struct in6_addr) }, + [IPVS_DAEMON_ATTR_MCAST_PORT] = { .type = NLA_U16 }, + [IPVS_DAEMON_ATTR_MCAST_TTL] = { .type = NLA_U8 }, }; /* Policy used for attributes in nested attribute IPVS_CMD_ATTR_SERVICE */ @@ -3266,7 +3281,7 @@ static int ip_vs_genl_parse_dest(struct ip_vs_dest_user_kern *udest, } static int ip_vs_genl_fill_daemon(struct sk_buff *skb, __u32 state, - const char *mcast_ifn, __u32 syncid) + struct ipvs_sync_daemon_cfg *c) { struct nlattr *nl_daemon; @@ -3275,9 +3290,23 @@ static int ip_vs_genl_fill_daemon(struct sk_buff *skb, __u32 state, return -EMSGSIZE; if (nla_put_u32(skb, IPVS_DAEMON_ATTR_STATE, state) || - nla_put_string(skb, IPVS_DAEMON_ATTR_MCAST_IFN, mcast_ifn) || - nla_put_u32(skb, IPVS_DAEMON_ATTR_SYNC_ID, syncid)) + nla_put_string(skb, IPVS_DAEMON_ATTR_MCAST_IFN, c->mcast_ifn) || + nla_put_u32(skb, IPVS_DAEMON_ATTR_SYNC_ID, c->syncid) || + nla_put_u16(skb, IPVS_DAEMON_ATTR_SYNC_MAXLEN, c->sync_maxlen) || + nla_put_u16(skb, IPVS_DAEMON_ATTR_MCAST_PORT, c->mcast_port) || + nla_put_u8(skb, IPVS_DAEMON_ATTR_MCAST_TTL, c->mcast_ttl)) goto nla_put_failure; +#ifdef CONFIG_IP_VS_IPV6 + if (c->mcast_af == AF_INET6) { + if (nla_put_in6_addr(skb, IPVS_DAEMON_ATTR_MCAST_GROUP6, + &c->mcast_group.in6)) + goto nla_put_failure; + } else +#endif + if (c->mcast_af == AF_INET && + nla_put_in_addr(skb, IPVS_DAEMON_ATTR_MCAST_GROUP, + c->mcast_group.ip)) + goto nla_put_failure; nla_nest_end(skb, nl_daemon); return 0; @@ -3288,7 +3317,7 @@ nla_put_failure: } static int ip_vs_genl_dump_daemon(struct sk_buff *skb, __u32 state, - const char *mcast_ifn, __u32 syncid, + struct ipvs_sync_daemon_cfg *c, struct netlink_callback *cb) { void *hdr; @@ -3298,7 +3327,7 @@ static int ip_vs_genl_dump_daemon(struct sk_buff *skb, __u32 state, if (!hdr) return -EMSGSIZE; - if (ip_vs_genl_fill_daemon(skb, state, mcast_ifn, syncid)) + if (ip_vs_genl_fill_daemon(skb, state, c)) goto nla_put_failure; genlmsg_end(skb, hdr); @@ -3318,8 +3347,7 @@ static int ip_vs_genl_dump_daemons(struct sk_buff *skb, mutex_lock(&ipvs->sync_mutex); if ((ipvs->sync_state & IP_VS_STATE_MASTER) && !cb->args[0]) { if (ip_vs_genl_dump_daemon(skb, IP_VS_STATE_MASTER, - ipvs->master_mcast_ifn, - ipvs->master_syncid, cb) < 0) + &ipvs->mcfg, cb) < 0) goto nla_put_failure; cb->args[0] = 1; @@ -3327,8 +3355,7 @@ static int ip_vs_genl_dump_daemons(struct sk_buff *skb, if ((ipvs->sync_state & IP_VS_STATE_BACKUP) && !cb->args[1]) { if (ip_vs_genl_dump_daemon(skb, IP_VS_STATE_BACKUP, - ipvs->backup_mcast_ifn, - ipvs->backup_syncid, cb) < 0) + &ipvs->bcfg, cb) < 0) goto nla_put_failure; cb->args[1] = 1; @@ -3342,30 +3369,83 @@ nla_put_failure: static int ip_vs_genl_new_daemon(struct net *net, struct nlattr **attrs) { + struct netns_ipvs *ipvs = net_ipvs(net); + struct ipvs_sync_daemon_cfg c; + struct nlattr *a; + int ret; + + memset(&c, 0, sizeof(c)); if (!(attrs[IPVS_DAEMON_ATTR_STATE] && attrs[IPVS_DAEMON_ATTR_MCAST_IFN] && attrs[IPVS_DAEMON_ATTR_SYNC_ID])) return -EINVAL; + strlcpy(c.mcast_ifn, nla_data(attrs[IPVS_DAEMON_ATTR_MCAST_IFN]), + sizeof(c.mcast_ifn)); + c.syncid = nla_get_u32(attrs[IPVS_DAEMON_ATTR_SYNC_ID]); + + a = attrs[IPVS_DAEMON_ATTR_SYNC_MAXLEN]; + if (a) + c.sync_maxlen = nla_get_u16(a); + + a = attrs[IPVS_DAEMON_ATTR_MCAST_GROUP]; + if (a) { + c.mcast_af = AF_INET; + c.mcast_group.ip = nla_get_in_addr(a); + if (!ipv4_is_multicast(c.mcast_group.ip)) + return -EINVAL; + } else { + a = attrs[IPVS_DAEMON_ATTR_MCAST_GROUP6]; + if (a) { +#ifdef CONFIG_IP_VS_IPV6 + int addr_type; + + c.mcast_af = AF_INET6; + c.mcast_group.in6 = nla_get_in6_addr(a); + addr_type = ipv6_addr_type(&c.mcast_group.in6); + if (!(addr_type & IPV6_ADDR_MULTICAST)) + return -EINVAL; +#else + return -EAFNOSUPPORT; +#endif + } + } + + a = attrs[IPVS_DAEMON_ATTR_MCAST_PORT]; + if (a) + c.mcast_port = nla_get_u16(a); + + a = attrs[IPVS_DAEMON_ATTR_MCAST_TTL]; + if (a) + c.mcast_ttl = nla_get_u8(a); /* The synchronization protocol is incompatible with mixed family * services */ - if (net_ipvs(net)->mixed_address_family_dests > 0) + if (ipvs->mixed_address_family_dests > 0) return -EINVAL; - return start_sync_thread(net, - nla_get_u32(attrs[IPVS_DAEMON_ATTR_STATE]), - nla_data(attrs[IPVS_DAEMON_ATTR_MCAST_IFN]), - nla_get_u32(attrs[IPVS_DAEMON_ATTR_SYNC_ID])); + rtnl_lock(); + mutex_lock(&ipvs->sync_mutex); + ret = start_sync_thread(net, &c, + nla_get_u32(attrs[IPVS_DAEMON_ATTR_STATE])); + mutex_unlock(&ipvs->sync_mutex); + rtnl_unlock(); + return ret; } static int ip_vs_genl_del_daemon(struct net *net, struct nlattr **attrs) { + struct netns_ipvs *ipvs = net_ipvs(net); + int ret; + if (!attrs[IPVS_DAEMON_ATTR_STATE]) return -EINVAL; - return stop_sync_thread(net, - nla_get_u32(attrs[IPVS_DAEMON_ATTR_STATE])); + mutex_lock(&ipvs->sync_mutex); + ret = stop_sync_thread(net, + nla_get_u32(attrs[IPVS_DAEMON_ATTR_STATE])); + mutex_unlock(&ipvs->sync_mutex); + return ret; } static int ip_vs_genl_set_config(struct net *net, struct nlattr **attrs) @@ -3389,7 +3469,7 @@ static int ip_vs_genl_set_config(struct net *net, struct nlattr **attrs) static int ip_vs_genl_set_daemon(struct sk_buff *skb, struct genl_info *info) { - int ret = 0, cmd; + int ret = -EINVAL, cmd; struct net *net; struct netns_ipvs *ipvs; @@ -3400,22 +3480,19 @@ static int ip_vs_genl_set_daemon(struct sk_buff *skb, struct genl_info *info) if (cmd == IPVS_CMD_NEW_DAEMON || cmd == IPVS_CMD_DEL_DAEMON) { struct nlattr *daemon_attrs[IPVS_DAEMON_ATTR_MAX + 1]; - mutex_lock(&ipvs->sync_mutex); if (!info->attrs[IPVS_CMD_ATTR_DAEMON] || nla_parse_nested(daemon_attrs, IPVS_DAEMON_ATTR_MAX, info->attrs[IPVS_CMD_ATTR_DAEMON], - ip_vs_daemon_policy)) { - ret = -EINVAL; + ip_vs_daemon_policy)) goto out; - } if (cmd == IPVS_CMD_NEW_DAEMON) ret = ip_vs_genl_new_daemon(net, daemon_attrs); else ret = ip_vs_genl_del_daemon(net, daemon_attrs); -out: - mutex_unlock(&ipvs->sync_mutex); } + +out: return ret; } diff --git a/net/netfilter/ipvs/ip_vs_nfct.c b/net/netfilter/ipvs/ip_vs_nfct.c index 5882bbfd198c..136184572fc9 100644 --- a/net/netfilter/ipvs/ip_vs_nfct.c +++ b/net/netfilter/ipvs/ip_vs_nfct.c @@ -274,7 +274,7 @@ void ip_vs_conn_drop_conntrack(struct ip_vs_conn *cp) " for conn " FMT_CONN "\n", __func__, ARG_TUPLE(&tuple), ARG_CONN(cp)); - h = nf_conntrack_find_get(ip_vs_conn_net(cp), NF_CT_DEFAULT_ZONE, + h = nf_conntrack_find_get(ip_vs_conn_net(cp), &nf_ct_zone_dflt, &tuple); if (h) { ct = nf_ct_tuplehash_to_ctrack(h); diff --git a/net/netfilter/ipvs/ip_vs_ovf.c b/net/netfilter/ipvs/ip_vs_ovf.c new file mode 100644 index 000000000000..f7d62c3b7329 --- /dev/null +++ b/net/netfilter/ipvs/ip_vs_ovf.c @@ -0,0 +1,86 @@ +/* + * IPVS: Overflow-Connection Scheduling module + * + * Authors: Raducu Deaconu <rhadoo_io@yahoo.com> + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + * + * Scheduler implements "overflow" loadbalancing according to number of active + * connections , will keep all conections to the node with the highest weight + * and overflow to the next node if the number of connections exceeds the node's + * weight. + * Note that this scheduler might not be suitable for UDP because it only uses + * active connections + * + */ + +#define KMSG_COMPONENT "IPVS" +#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt + +#include <linux/module.h> +#include <linux/kernel.h> + +#include <net/ip_vs.h> + +/* OVF Connection scheduling */ +static struct ip_vs_dest * +ip_vs_ovf_schedule(struct ip_vs_service *svc, const struct sk_buff *skb, + struct ip_vs_iphdr *iph) +{ + struct ip_vs_dest *dest, *h = NULL; + int hw = 0, w; + + IP_VS_DBG(6, "ip_vs_ovf_schedule(): Scheduling...\n"); + /* select the node with highest weight, go to next in line if active + * connections exceed weight + */ + list_for_each_entry_rcu(dest, &svc->destinations, n_list) { + w = atomic_read(&dest->weight); + if ((dest->flags & IP_VS_DEST_F_OVERLOAD) || + atomic_read(&dest->activeconns) > w || + w == 0) + continue; + if (!h || w > hw) { + h = dest; + hw = w; + } + } + + if (h) { + IP_VS_DBG_BUF(6, "OVF: server %s:%u active %d w %d\n", + IP_VS_DBG_ADDR(h->af, &h->addr), + ntohs(h->port), + atomic_read(&h->activeconns), + atomic_read(&h->weight)); + return h; + } + + ip_vs_scheduler_err(svc, "no destination available"); + return NULL; +} + +static struct ip_vs_scheduler ip_vs_ovf_scheduler = { + .name = "ovf", + .refcnt = ATOMIC_INIT(0), + .module = THIS_MODULE, + .n_list = LIST_HEAD_INIT(ip_vs_ovf_scheduler.n_list), + .schedule = ip_vs_ovf_schedule, +}; + +static int __init ip_vs_ovf_init(void) +{ + return register_ip_vs_scheduler(&ip_vs_ovf_scheduler); +} + +static void __exit ip_vs_ovf_cleanup(void) +{ + unregister_ip_vs_scheduler(&ip_vs_ovf_scheduler); + synchronize_rcu(); +} + +module_init(ip_vs_ovf_init); +module_exit(ip_vs_ovf_cleanup); +MODULE_LICENSE("GPL"); diff --git a/net/netfilter/ipvs/ip_vs_sched.c b/net/netfilter/ipvs/ip_vs_sched.c index 7e8141647943..a2ff7d746ebf 100644 --- a/net/netfilter/ipvs/ip_vs_sched.c +++ b/net/netfilter/ipvs/ip_vs_sched.c @@ -137,7 +137,7 @@ struct ip_vs_scheduler *ip_vs_scheduler_get(const char *sched_name) void ip_vs_scheduler_put(struct ip_vs_scheduler *scheduler) { - if (scheduler && scheduler->module) + if (scheduler) module_put(scheduler->module); } diff --git a/net/netfilter/ipvs/ip_vs_sync.c b/net/netfilter/ipvs/ip_vs_sync.c index d99ad93eb855..43f140950075 100644 --- a/net/netfilter/ipvs/ip_vs_sync.c +++ b/net/netfilter/ipvs/ip_vs_sync.c @@ -262,6 +262,11 @@ struct ip_vs_sync_mesg { /* ip_vs_sync_conn entries start here */ }; +union ipvs_sockaddr { + struct sockaddr_in in; + struct sockaddr_in6 in6; +}; + struct ip_vs_sync_buff { struct list_head list; unsigned long firstuse; @@ -320,26 +325,28 @@ sb_dequeue(struct netns_ipvs *ipvs, struct ipvs_master_sync_state *ms) * Create a new sync buffer for Version 1 proto. */ static inline struct ip_vs_sync_buff * -ip_vs_sync_buff_create(struct netns_ipvs *ipvs) +ip_vs_sync_buff_create(struct netns_ipvs *ipvs, unsigned int len) { struct ip_vs_sync_buff *sb; if (!(sb=kmalloc(sizeof(struct ip_vs_sync_buff), GFP_ATOMIC))) return NULL; - sb->mesg = kmalloc(ipvs->send_mesg_maxlen, GFP_ATOMIC); + len = max_t(unsigned int, len + sizeof(struct ip_vs_sync_mesg), + ipvs->mcfg.sync_maxlen); + sb->mesg = kmalloc(len, GFP_ATOMIC); if (!sb->mesg) { kfree(sb); return NULL; } sb->mesg->reserved = 0; /* old nr_conns i.e. must be zero now */ sb->mesg->version = SYNC_PROTO_VER; - sb->mesg->syncid = ipvs->master_syncid; + sb->mesg->syncid = ipvs->mcfg.syncid; sb->mesg->size = htons(sizeof(struct ip_vs_sync_mesg)); sb->mesg->nr_conns = 0; sb->mesg->spare = 0; sb->head = (unsigned char *)sb->mesg + sizeof(struct ip_vs_sync_mesg); - sb->end = (unsigned char *)sb->mesg + ipvs->send_mesg_maxlen; + sb->end = (unsigned char *)sb->mesg + len; sb->firstuse = jiffies; return sb; @@ -402,7 +409,7 @@ select_master_thread_id(struct netns_ipvs *ipvs, struct ip_vs_conn *cp) * Create a new sync buffer for Version 0 proto. */ static inline struct ip_vs_sync_buff * -ip_vs_sync_buff_create_v0(struct netns_ipvs *ipvs) +ip_vs_sync_buff_create_v0(struct netns_ipvs *ipvs, unsigned int len) { struct ip_vs_sync_buff *sb; struct ip_vs_sync_mesg_v0 *mesg; @@ -410,17 +417,19 @@ ip_vs_sync_buff_create_v0(struct netns_ipvs *ipvs) if (!(sb=kmalloc(sizeof(struct ip_vs_sync_buff), GFP_ATOMIC))) return NULL; - sb->mesg = kmalloc(ipvs->send_mesg_maxlen, GFP_ATOMIC); + len = max_t(unsigned int, len + sizeof(struct ip_vs_sync_mesg_v0), + ipvs->mcfg.sync_maxlen); + sb->mesg = kmalloc(len, GFP_ATOMIC); if (!sb->mesg) { kfree(sb); return NULL; } mesg = (struct ip_vs_sync_mesg_v0 *)sb->mesg; mesg->nr_conns = 0; - mesg->syncid = ipvs->master_syncid; + mesg->syncid = ipvs->mcfg.syncid; mesg->size = htons(sizeof(struct ip_vs_sync_mesg_v0)); sb->head = (unsigned char *)mesg + sizeof(struct ip_vs_sync_mesg_v0); - sb->end = (unsigned char *)mesg + ipvs->send_mesg_maxlen; + sb->end = (unsigned char *)mesg + len; sb->firstuse = jiffies; return sb; } @@ -533,7 +542,7 @@ static void ip_vs_sync_conn_v0(struct net *net, struct ip_vs_conn *cp, struct ip_vs_sync_buff *buff; struct ipvs_master_sync_state *ms; int id; - int len; + unsigned int len; if (unlikely(cp->af != AF_INET)) return; @@ -553,17 +562,19 @@ static void ip_vs_sync_conn_v0(struct net *net, struct ip_vs_conn *cp, id = select_master_thread_id(ipvs, cp); ms = &ipvs->ms[id]; buff = ms->sync_buff; + len = (cp->flags & IP_VS_CONN_F_SEQ_MASK) ? FULL_CONN_SIZE : + SIMPLE_CONN_SIZE; if (buff) { m = (struct ip_vs_sync_mesg_v0 *) buff->mesg; /* Send buffer if it is for v1 */ - if (!m->nr_conns) { + if (buff->head + len > buff->end || !m->nr_conns) { sb_queue_tail(ipvs, ms); ms->sync_buff = NULL; buff = NULL; } } if (!buff) { - buff = ip_vs_sync_buff_create_v0(ipvs); + buff = ip_vs_sync_buff_create_v0(ipvs, len); if (!buff) { spin_unlock_bh(&ipvs->sync_buff_lock); pr_err("ip_vs_sync_buff_create failed.\n"); @@ -572,8 +583,6 @@ static void ip_vs_sync_conn_v0(struct net *net, struct ip_vs_conn *cp, ms->sync_buff = buff; } - len = (cp->flags & IP_VS_CONN_F_SEQ_MASK) ? FULL_CONN_SIZE : - SIMPLE_CONN_SIZE; m = (struct ip_vs_sync_mesg_v0 *) buff->mesg; s = (struct ip_vs_sync_conn_v0 *) buff->head; @@ -597,12 +606,6 @@ static void ip_vs_sync_conn_v0(struct net *net, struct ip_vs_conn *cp, m->nr_conns++; m->size = htons(ntohs(m->size) + len); buff->head += len; - - /* check if there is a space for next one */ - if (buff->head + FULL_CONN_SIZE > buff->end) { - sb_queue_tail(ipvs, ms); - ms->sync_buff = NULL; - } spin_unlock_bh(&ipvs->sync_buff_lock); /* synchronize its controller if it has */ @@ -694,7 +697,7 @@ sloop: } if (!buff) { - buff = ip_vs_sync_buff_create(ipvs); + buff = ip_vs_sync_buff_create(ipvs, len); if (!buff) { spin_unlock_bh(&ipvs->sync_buff_lock); pr_err("ip_vs_sync_buff_create failed.\n"); @@ -1219,7 +1222,7 @@ static void ip_vs_process_message(struct net *net, __u8 *buffer, return; } /* SyncID sanity check */ - if (ipvs->backup_syncid != 0 && m2->syncid != ipvs->backup_syncid) { + if (ipvs->bcfg.syncid != 0 && m2->syncid != ipvs->bcfg.syncid) { IP_VS_DBG(7, "BACKUP, Ignoring syncid = %d\n", m2->syncid); return; } @@ -1303,6 +1306,14 @@ static void set_mcast_loop(struct sock *sk, u_char loop) /* setsockopt(sock, SOL_IP, IP_MULTICAST_LOOP, &loop, sizeof(loop)); */ lock_sock(sk); inet->mc_loop = loop ? 1 : 0; +#ifdef CONFIG_IP_VS_IPV6 + if (sk->sk_family == AF_INET6) { + struct ipv6_pinfo *np = inet6_sk(sk); + + /* IPV6_MULTICAST_LOOP */ + np->mc_loop = loop ? 1 : 0; + } +#endif release_sock(sk); } @@ -1316,6 +1327,33 @@ static void set_mcast_ttl(struct sock *sk, u_char ttl) /* setsockopt(sock, SOL_IP, IP_MULTICAST_TTL, &ttl, sizeof(ttl)); */ lock_sock(sk); inet->mc_ttl = ttl; +#ifdef CONFIG_IP_VS_IPV6 + if (sk->sk_family == AF_INET6) { + struct ipv6_pinfo *np = inet6_sk(sk); + + /* IPV6_MULTICAST_HOPS */ + np->mcast_hops = ttl; + } +#endif + release_sock(sk); +} + +/* Control fragmentation of messages */ +static void set_mcast_pmtudisc(struct sock *sk, int val) +{ + struct inet_sock *inet = inet_sk(sk); + + /* setsockopt(sock, SOL_IP, IP_MTU_DISCOVER, &val, sizeof(val)); */ + lock_sock(sk); + inet->pmtudisc = val; +#ifdef CONFIG_IP_VS_IPV6 + if (sk->sk_family == AF_INET6) { + struct ipv6_pinfo *np = inet6_sk(sk); + + /* IPV6_MTU_DISCOVER */ + np->pmtudisc = val; + } +#endif release_sock(sk); } @@ -1338,44 +1376,15 @@ static int set_mcast_if(struct sock *sk, char *ifname) lock_sock(sk); inet->mc_index = dev->ifindex; /* inet->mc_addr = 0; */ - release_sock(sk); - - return 0; -} - +#ifdef CONFIG_IP_VS_IPV6 + if (sk->sk_family == AF_INET6) { + struct ipv6_pinfo *np = inet6_sk(sk); -/* - * Set the maximum length of sync message according to the - * specified interface's MTU. - */ -static int set_sync_mesg_maxlen(struct net *net, int sync_state) -{ - struct netns_ipvs *ipvs = net_ipvs(net); - struct net_device *dev; - int num; - - if (sync_state == IP_VS_STATE_MASTER) { - dev = __dev_get_by_name(net, ipvs->master_mcast_ifn); - if (!dev) - return -ENODEV; - - num = (dev->mtu - sizeof(struct iphdr) - - sizeof(struct udphdr) - - SYNC_MESG_HEADER_LEN - 20) / SIMPLE_CONN_SIZE; - ipvs->send_mesg_maxlen = SYNC_MESG_HEADER_LEN + - SIMPLE_CONN_SIZE * min(num, MAX_CONNS_PER_SYNCBUFF); - IP_VS_DBG(7, "setting the maximum length of sync sending " - "message %d.\n", ipvs->send_mesg_maxlen); - } else if (sync_state == IP_VS_STATE_BACKUP) { - dev = __dev_get_by_name(net, ipvs->backup_mcast_ifn); - if (!dev) - return -ENODEV; - - ipvs->recv_mesg_maxlen = dev->mtu - - sizeof(struct iphdr) - sizeof(struct udphdr); - IP_VS_DBG(7, "setting the maximum length of sync receiving " - "message %d.\n", ipvs->recv_mesg_maxlen); + /* IPV6_MULTICAST_IF */ + np->mcast_oif = dev->ifindex; } +#endif + release_sock(sk); return 0; } @@ -1405,15 +1414,34 @@ join_mcast_group(struct sock *sk, struct in_addr *addr, char *ifname) mreq.imr_ifindex = dev->ifindex; - rtnl_lock(); lock_sock(sk); ret = ip_mc_join_group(sk, &mreq); release_sock(sk); - rtnl_unlock(); return ret; } +#ifdef CONFIG_IP_VS_IPV6 +static int join_mcast_group6(struct sock *sk, struct in6_addr *addr, + char *ifname) +{ + struct net *net = sock_net(sk); + struct net_device *dev; + int ret; + + dev = __dev_get_by_name(net, ifname); + if (!dev) + return -ENODEV; + if (sk->sk_bound_dev_if && dev->ifindex != sk->sk_bound_dev_if) + return -EINVAL; + + lock_sock(sk); + ret = ipv6_sock_mc_join(sk, dev->ifindex, addr); + release_sock(sk); + + return ret; +} +#endif static int bind_mcastif_addr(struct socket *sock, char *ifname) { @@ -1442,6 +1470,26 @@ static int bind_mcastif_addr(struct socket *sock, char *ifname) return sock->ops->bind(sock, (struct sockaddr*)&sin, sizeof(sin)); } +static void get_mcast_sockaddr(union ipvs_sockaddr *sa, int *salen, + struct ipvs_sync_daemon_cfg *c, int id) +{ + if (AF_INET6 == c->mcast_af) { + sa->in6 = (struct sockaddr_in6) { + .sin6_family = AF_INET6, + .sin6_port = htons(c->mcast_port + id), + }; + sa->in6.sin6_addr = c->mcast_group.in6; + *salen = sizeof(sa->in6); + } else { + sa->in = (struct sockaddr_in) { + .sin_family = AF_INET, + .sin_port = htons(c->mcast_port + id), + }; + sa->in.sin_addr = c->mcast_group.in; + *salen = sizeof(sa->in); + } +} + /* * Set up sending multicast socket over UDP */ @@ -1449,40 +1497,43 @@ static struct socket *make_send_sock(struct net *net, int id) { struct netns_ipvs *ipvs = net_ipvs(net); /* multicast addr */ - struct sockaddr_in mcast_addr = { - .sin_family = AF_INET, - .sin_port = cpu_to_be16(IP_VS_SYNC_PORT + id), - .sin_addr.s_addr = cpu_to_be32(IP_VS_SYNC_GROUP), - }; + union ipvs_sockaddr mcast_addr; struct socket *sock; - int result; + int result, salen; /* First create a socket */ - result = sock_create_kern(net, PF_INET, SOCK_DGRAM, IPPROTO_UDP, &sock); + result = sock_create_kern(net, ipvs->mcfg.mcast_af, SOCK_DGRAM, + IPPROTO_UDP, &sock); if (result < 0) { pr_err("Error during creation of socket; terminating\n"); return ERR_PTR(result); } - result = set_mcast_if(sock->sk, ipvs->master_mcast_ifn); + result = set_mcast_if(sock->sk, ipvs->mcfg.mcast_ifn); if (result < 0) { pr_err("Error setting outbound mcast interface\n"); goto error; } set_mcast_loop(sock->sk, 0); - set_mcast_ttl(sock->sk, 1); + set_mcast_ttl(sock->sk, ipvs->mcfg.mcast_ttl); + /* Allow fragmentation if MTU changes */ + set_mcast_pmtudisc(sock->sk, IP_PMTUDISC_DONT); result = sysctl_sync_sock_size(ipvs); if (result > 0) set_sock_size(sock->sk, 1, result); - result = bind_mcastif_addr(sock, ipvs->master_mcast_ifn); + if (AF_INET == ipvs->mcfg.mcast_af) + result = bind_mcastif_addr(sock, ipvs->mcfg.mcast_ifn); + else + result = 0; if (result < 0) { pr_err("Error binding address of the mcast interface\n"); goto error; } + get_mcast_sockaddr(&mcast_addr, &salen, &ipvs->mcfg, id); result = sock->ops->connect(sock, (struct sockaddr *) &mcast_addr, - sizeof(struct sockaddr), 0); + salen, 0); if (result < 0) { pr_err("Error connecting to the multicast addr\n"); goto error; @@ -1503,16 +1554,13 @@ static struct socket *make_receive_sock(struct net *net, int id) { struct netns_ipvs *ipvs = net_ipvs(net); /* multicast addr */ - struct sockaddr_in mcast_addr = { - .sin_family = AF_INET, - .sin_port = cpu_to_be16(IP_VS_SYNC_PORT + id), - .sin_addr.s_addr = cpu_to_be32(IP_VS_SYNC_GROUP), - }; + union ipvs_sockaddr mcast_addr; struct socket *sock; - int result; + int result, salen; /* First create a socket */ - result = sock_create_kern(net, PF_INET, SOCK_DGRAM, IPPROTO_UDP, &sock); + result = sock_create_kern(net, ipvs->bcfg.mcast_af, SOCK_DGRAM, + IPPROTO_UDP, &sock); if (result < 0) { pr_err("Error during creation of socket; terminating\n"); return ERR_PTR(result); @@ -1523,17 +1571,22 @@ static struct socket *make_receive_sock(struct net *net, int id) if (result > 0) set_sock_size(sock->sk, 0, result); - result = sock->ops->bind(sock, (struct sockaddr *) &mcast_addr, - sizeof(struct sockaddr)); + get_mcast_sockaddr(&mcast_addr, &salen, &ipvs->bcfg, id); + result = sock->ops->bind(sock, (struct sockaddr *)&mcast_addr, salen); if (result < 0) { pr_err("Error binding to the multicast addr\n"); goto error; } /* join the multicast group */ - result = join_mcast_group(sock->sk, - (struct in_addr *) &mcast_addr.sin_addr, - ipvs->backup_mcast_ifn); +#ifdef CONFIG_IP_VS_IPV6 + if (ipvs->bcfg.mcast_af == AF_INET6) + result = join_mcast_group6(sock->sk, &mcast_addr.in6.sin6_addr, + ipvs->bcfg.mcast_ifn); + else +#endif + result = join_mcast_group(sock->sk, &mcast_addr.in.sin_addr, + ipvs->bcfg.mcast_ifn); if (result < 0) { pr_err("Error joining to the multicast group\n"); goto error; @@ -1641,7 +1694,7 @@ static int sync_thread_master(void *data) pr_info("sync thread started: state = MASTER, mcast_ifn = %s, " "syncid = %d, id = %d\n", - ipvs->master_mcast_ifn, ipvs->master_syncid, tinfo->id); + ipvs->mcfg.mcast_ifn, ipvs->mcfg.syncid, tinfo->id); for (;;) { sb = next_sync_buff(ipvs, ms); @@ -1695,7 +1748,7 @@ static int sync_thread_backup(void *data) pr_info("sync thread started: state = BACKUP, mcast_ifn = %s, " "syncid = %d, id = %d\n", - ipvs->backup_mcast_ifn, ipvs->backup_syncid, tinfo->id); + ipvs->bcfg.mcast_ifn, ipvs->bcfg.syncid, tinfo->id); while (!kthread_should_stop()) { wait_event_interruptible(*sk_sleep(tinfo->sock->sk), @@ -1705,7 +1758,7 @@ static int sync_thread_backup(void *data) /* do we have data now? */ while (!skb_queue_empty(&(tinfo->sock->sk->sk_receive_queue))) { len = ip_vs_receive(tinfo->sock, tinfo->buf, - ipvs->recv_mesg_maxlen); + ipvs->bcfg.sync_maxlen); if (len <= 0) { if (len != -EAGAIN) pr_err("receiving message error\n"); @@ -1725,16 +1778,19 @@ static int sync_thread_backup(void *data) } -int start_sync_thread(struct net *net, int state, char *mcast_ifn, __u8 syncid) +int start_sync_thread(struct net *net, struct ipvs_sync_daemon_cfg *c, + int state) { struct ip_vs_sync_thread_data *tinfo; struct task_struct **array = NULL, *task; struct socket *sock; struct netns_ipvs *ipvs = net_ipvs(net); + struct net_device *dev; char *name; int (*threadfn)(void *data); - int id, count; + int id, count, hlen; int result = -ENOMEM; + u16 mtu, min_mtu; IP_VS_DBG(7, "%s(): pid %d\n", __func__, task_pid_nr(current)); IP_VS_DBG(7, "Each ip_vs_sync_conn entry needs %Zd bytes\n", @@ -1746,22 +1802,46 @@ int start_sync_thread(struct net *net, int state, char *mcast_ifn, __u8 syncid) } else count = ipvs->threads_mask + 1; + if (c->mcast_af == AF_UNSPEC) { + c->mcast_af = AF_INET; + c->mcast_group.ip = cpu_to_be32(IP_VS_SYNC_GROUP); + } + if (!c->mcast_port) + c->mcast_port = IP_VS_SYNC_PORT; + if (!c->mcast_ttl) + c->mcast_ttl = 1; + + dev = __dev_get_by_name(net, c->mcast_ifn); + if (!dev) { + pr_err("Unknown mcast interface: %s\n", c->mcast_ifn); + return -ENODEV; + } + hlen = (AF_INET6 == c->mcast_af) ? + sizeof(struct ipv6hdr) + sizeof(struct udphdr) : + sizeof(struct iphdr) + sizeof(struct udphdr); + mtu = (state == IP_VS_STATE_BACKUP) ? + clamp(dev->mtu, 1500U, 65535U) : 1500U; + min_mtu = (state == IP_VS_STATE_BACKUP) ? 1024 : 1; + + if (c->sync_maxlen) + c->sync_maxlen = clamp_t(unsigned int, + c->sync_maxlen, min_mtu, + 65535 - hlen); + else + c->sync_maxlen = mtu - hlen; + if (state == IP_VS_STATE_MASTER) { if (ipvs->ms) return -EEXIST; - strlcpy(ipvs->master_mcast_ifn, mcast_ifn, - sizeof(ipvs->master_mcast_ifn)); - ipvs->master_syncid = syncid; + ipvs->mcfg = *c; name = "ipvs-m:%d:%d"; threadfn = sync_thread_master; } else if (state == IP_VS_STATE_BACKUP) { if (ipvs->backup_threads) return -EEXIST; - strlcpy(ipvs->backup_mcast_ifn, mcast_ifn, - sizeof(ipvs->backup_mcast_ifn)); - ipvs->backup_syncid = syncid; + ipvs->bcfg = *c; name = "ipvs-b:%d:%d"; threadfn = sync_thread_backup; } else { @@ -1789,7 +1869,6 @@ int start_sync_thread(struct net *net, int state, char *mcast_ifn, __u8 syncid) if (!array) goto out; } - set_sync_mesg_maxlen(net, state); tinfo = NULL; for (id = 0; id < count; id++) { @@ -1807,7 +1886,7 @@ int start_sync_thread(struct net *net, int state, char *mcast_ifn, __u8 syncid) tinfo->net = net; tinfo->sock = sock; if (state == IP_VS_STATE_BACKUP) { - tinfo->buf = kmalloc(ipvs->recv_mesg_maxlen, + tinfo->buf = kmalloc(ipvs->bcfg.sync_maxlen, GFP_KERNEL); if (!tinfo->buf) goto outtinfo; diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index 3c20d02aee73..c09d6c7198f6 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -126,7 +126,7 @@ EXPORT_PER_CPU_SYMBOL(nf_conntrack_untracked); unsigned int nf_conntrack_hash_rnd __read_mostly; EXPORT_SYMBOL_GPL(nf_conntrack_hash_rnd); -static u32 hash_conntrack_raw(const struct nf_conntrack_tuple *tuple, u16 zone) +static u32 hash_conntrack_raw(const struct nf_conntrack_tuple *tuple) { unsigned int n; @@ -135,7 +135,7 @@ static u32 hash_conntrack_raw(const struct nf_conntrack_tuple *tuple, u16 zone) * three bytes manually. */ n = (sizeof(tuple->src) + sizeof(tuple->dst.u3)) / sizeof(u32); - return jhash2((u32 *)tuple, n, zone ^ nf_conntrack_hash_rnd ^ + return jhash2((u32 *)tuple, n, nf_conntrack_hash_rnd ^ (((__force __u16)tuple->dst.u.all << 16) | tuple->dst.protonum)); } @@ -151,15 +151,15 @@ static u32 hash_bucket(u32 hash, const struct net *net) } static u_int32_t __hash_conntrack(const struct nf_conntrack_tuple *tuple, - u16 zone, unsigned int size) + unsigned int size) { - return __hash_bucket(hash_conntrack_raw(tuple, zone), size); + return __hash_bucket(hash_conntrack_raw(tuple), size); } -static inline u_int32_t hash_conntrack(const struct net *net, u16 zone, +static inline u_int32_t hash_conntrack(const struct net *net, const struct nf_conntrack_tuple *tuple) { - return __hash_conntrack(tuple, zone, net->ct.htable_size); + return __hash_conntrack(tuple, net->ct.htable_size); } bool @@ -288,7 +288,9 @@ static void nf_ct_del_from_dying_or_unconfirmed_list(struct nf_conn *ct) } /* Released via destroy_conntrack() */ -struct nf_conn *nf_ct_tmpl_alloc(struct net *net, u16 zone, gfp_t flags) +struct nf_conn *nf_ct_tmpl_alloc(struct net *net, + const struct nf_conntrack_zone *zone, + gfp_t flags) { struct nf_conn *tmpl; @@ -299,33 +301,25 @@ struct nf_conn *nf_ct_tmpl_alloc(struct net *net, u16 zone, gfp_t flags) tmpl->status = IPS_TEMPLATE; write_pnet(&tmpl->ct_net, net); -#ifdef CONFIG_NF_CONNTRACK_ZONES - if (zone) { - struct nf_conntrack_zone *nf_ct_zone; + if (nf_ct_zone_add(tmpl, flags, zone) < 0) + goto out_free; - nf_ct_zone = nf_ct_ext_add(tmpl, NF_CT_EXT_ZONE, flags); - if (!nf_ct_zone) - goto out_free; - nf_ct_zone->id = zone; - } -#endif atomic_set(&tmpl->ct_general.use, 0); return tmpl; -#ifdef CONFIG_NF_CONNTRACK_ZONES out_free: kfree(tmpl); return NULL; -#endif } EXPORT_SYMBOL_GPL(nf_ct_tmpl_alloc); -static void nf_ct_tmpl_free(struct nf_conn *tmpl) +void nf_ct_tmpl_free(struct nf_conn *tmpl) { nf_ct_ext_destroy(tmpl); nf_ct_ext_free(tmpl); kfree(tmpl); } +EXPORT_SYMBOL_GPL(nf_ct_tmpl_free); static void destroy_conntrack(struct nf_conntrack *nfct) @@ -373,7 +367,6 @@ static void nf_ct_delete_from_lists(struct nf_conn *ct) { struct net *net = nf_ct_net(ct); unsigned int hash, reply_hash; - u16 zone = nf_ct_zone(ct); unsigned int sequence; nf_ct_helper_destroy(ct); @@ -381,9 +374,9 @@ static void nf_ct_delete_from_lists(struct nf_conn *ct) local_bh_disable(); do { sequence = read_seqcount_begin(&net->ct.generation); - hash = hash_conntrack(net, zone, + hash = hash_conntrack(net, &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple); - reply_hash = hash_conntrack(net, zone, + reply_hash = hash_conntrack(net, &ct->tuplehash[IP_CT_DIR_REPLY].tuple); } while (nf_conntrack_double_lock(net, hash, reply_hash, sequence)); @@ -431,8 +424,8 @@ static void death_by_timeout(unsigned long ul_conntrack) static inline bool nf_ct_key_equal(struct nf_conntrack_tuple_hash *h, - const struct nf_conntrack_tuple *tuple, - u16 zone) + const struct nf_conntrack_tuple *tuple, + const struct nf_conntrack_zone *zone) { struct nf_conn *ct = nf_ct_tuplehash_to_ctrack(h); @@ -440,8 +433,8 @@ nf_ct_key_equal(struct nf_conntrack_tuple_hash *h, * so we need to check that the conntrack is confirmed */ return nf_ct_tuple_equal(tuple, &h->tuple) && - nf_ct_zone(ct) == zone && - nf_ct_is_confirmed(ct); + nf_ct_zone_equal(ct, zone, NF_CT_DIRECTION(h)) && + nf_ct_is_confirmed(ct); } /* @@ -450,7 +443,7 @@ nf_ct_key_equal(struct nf_conntrack_tuple_hash *h, * and recheck nf_ct_tuple_equal(tuple, &h->tuple) */ static struct nf_conntrack_tuple_hash * -____nf_conntrack_find(struct net *net, u16 zone, +____nf_conntrack_find(struct net *net, const struct nf_conntrack_zone *zone, const struct nf_conntrack_tuple *tuple, u32 hash) { struct nf_conntrack_tuple_hash *h; @@ -486,7 +479,7 @@ begin: /* Find a connection corresponding to a tuple. */ static struct nf_conntrack_tuple_hash * -__nf_conntrack_find_get(struct net *net, u16 zone, +__nf_conntrack_find_get(struct net *net, const struct nf_conntrack_zone *zone, const struct nf_conntrack_tuple *tuple, u32 hash) { struct nf_conntrack_tuple_hash *h; @@ -513,11 +506,11 @@ begin: } struct nf_conntrack_tuple_hash * -nf_conntrack_find_get(struct net *net, u16 zone, +nf_conntrack_find_get(struct net *net, const struct nf_conntrack_zone *zone, const struct nf_conntrack_tuple *tuple) { return __nf_conntrack_find_get(net, zone, tuple, - hash_conntrack_raw(tuple, zone)); + hash_conntrack_raw(tuple)); } EXPORT_SYMBOL_GPL(nf_conntrack_find_get); @@ -536,11 +529,11 @@ static void __nf_conntrack_hash_insert(struct nf_conn *ct, int nf_conntrack_hash_check_insert(struct nf_conn *ct) { + const struct nf_conntrack_zone *zone; struct net *net = nf_ct_net(ct); unsigned int hash, reply_hash; struct nf_conntrack_tuple_hash *h; struct hlist_nulls_node *n; - u16 zone; unsigned int sequence; zone = nf_ct_zone(ct); @@ -548,9 +541,9 @@ nf_conntrack_hash_check_insert(struct nf_conn *ct) local_bh_disable(); do { sequence = read_seqcount_begin(&net->ct.generation); - hash = hash_conntrack(net, zone, + hash = hash_conntrack(net, &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple); - reply_hash = hash_conntrack(net, zone, + reply_hash = hash_conntrack(net, &ct->tuplehash[IP_CT_DIR_REPLY].tuple); } while (nf_conntrack_double_lock(net, hash, reply_hash, sequence)); @@ -558,12 +551,14 @@ nf_conntrack_hash_check_insert(struct nf_conn *ct) hlist_nulls_for_each_entry(h, n, &net->ct.hash[hash], hnnode) if (nf_ct_tuple_equal(&ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple, &h->tuple) && - zone == nf_ct_zone(nf_ct_tuplehash_to_ctrack(h))) + nf_ct_zone_equal(nf_ct_tuplehash_to_ctrack(h), zone, + NF_CT_DIRECTION(h))) goto out; hlist_nulls_for_each_entry(h, n, &net->ct.hash[reply_hash], hnnode) if (nf_ct_tuple_equal(&ct->tuplehash[IP_CT_DIR_REPLY].tuple, &h->tuple) && - zone == nf_ct_zone(nf_ct_tuplehash_to_ctrack(h))) + nf_ct_zone_equal(nf_ct_tuplehash_to_ctrack(h), zone, + NF_CT_DIRECTION(h))) goto out; add_timer(&ct->timeout); @@ -588,6 +583,7 @@ EXPORT_SYMBOL_GPL(nf_conntrack_hash_check_insert); int __nf_conntrack_confirm(struct sk_buff *skb) { + const struct nf_conntrack_zone *zone; unsigned int hash, reply_hash; struct nf_conntrack_tuple_hash *h; struct nf_conn *ct; @@ -596,7 +592,6 @@ __nf_conntrack_confirm(struct sk_buff *skb) struct hlist_nulls_node *n; enum ip_conntrack_info ctinfo; struct net *net; - u16 zone; unsigned int sequence; ct = nf_ct_get(skb, &ctinfo); @@ -617,7 +612,7 @@ __nf_conntrack_confirm(struct sk_buff *skb) /* reuse the hash saved before */ hash = *(unsigned long *)&ct->tuplehash[IP_CT_DIR_REPLY].hnnode.pprev; hash = hash_bucket(hash, net); - reply_hash = hash_conntrack(net, zone, + reply_hash = hash_conntrack(net, &ct->tuplehash[IP_CT_DIR_REPLY].tuple); } while (nf_conntrack_double_lock(net, hash, reply_hash, sequence)); @@ -649,12 +644,14 @@ __nf_conntrack_confirm(struct sk_buff *skb) hlist_nulls_for_each_entry(h, n, &net->ct.hash[hash], hnnode) if (nf_ct_tuple_equal(&ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple, &h->tuple) && - zone == nf_ct_zone(nf_ct_tuplehash_to_ctrack(h))) + nf_ct_zone_equal(nf_ct_tuplehash_to_ctrack(h), zone, + NF_CT_DIRECTION(h))) goto out; hlist_nulls_for_each_entry(h, n, &net->ct.hash[reply_hash], hnnode) if (nf_ct_tuple_equal(&ct->tuplehash[IP_CT_DIR_REPLY].tuple, &h->tuple) && - zone == nf_ct_zone(nf_ct_tuplehash_to_ctrack(h))) + nf_ct_zone_equal(nf_ct_tuplehash_to_ctrack(h), zone, + NF_CT_DIRECTION(h))) goto out; /* Timer relative to confirmation time, not original @@ -707,11 +704,14 @@ nf_conntrack_tuple_taken(const struct nf_conntrack_tuple *tuple, const struct nf_conn *ignored_conntrack) { struct net *net = nf_ct_net(ignored_conntrack); + const struct nf_conntrack_zone *zone; struct nf_conntrack_tuple_hash *h; struct hlist_nulls_node *n; struct nf_conn *ct; - u16 zone = nf_ct_zone(ignored_conntrack); - unsigned int hash = hash_conntrack(net, zone, tuple); + unsigned int hash; + + zone = nf_ct_zone(ignored_conntrack); + hash = hash_conntrack(net, tuple); /* Disable BHs the entire time since we need to disable them at * least once for the stats anyway. @@ -721,7 +721,7 @@ nf_conntrack_tuple_taken(const struct nf_conntrack_tuple *tuple, ct = nf_ct_tuplehash_to_ctrack(h); if (ct != ignored_conntrack && nf_ct_tuple_equal(tuple, &h->tuple) && - nf_ct_zone(ct) == zone) { + nf_ct_zone_equal(ct, zone, NF_CT_DIRECTION(h))) { NF_CT_STAT_INC(net, found); rcu_read_unlock_bh(); return 1; @@ -810,7 +810,8 @@ void init_nf_conntrack_hash_rnd(void) } static struct nf_conn * -__nf_conntrack_alloc(struct net *net, u16 zone, +__nf_conntrack_alloc(struct net *net, + const struct nf_conntrack_zone *zone, const struct nf_conntrack_tuple *orig, const struct nf_conntrack_tuple *repl, gfp_t gfp, u32 hash) @@ -820,7 +821,7 @@ __nf_conntrack_alloc(struct net *net, u16 zone, if (unlikely(!nf_conntrack_hash_rnd)) { init_nf_conntrack_hash_rnd(); /* recompute the hash as nf_conntrack_hash_rnd is initialized */ - hash = hash_conntrack_raw(orig, zone); + hash = hash_conntrack_raw(orig); } /* We don't want any race condition at early drop stage */ @@ -840,10 +841,9 @@ __nf_conntrack_alloc(struct net *net, u16 zone, * SLAB_DESTROY_BY_RCU. */ ct = kmem_cache_alloc(net->ct.nf_conntrack_cachep, gfp); - if (ct == NULL) { - atomic_dec(&net->ct.count); - return ERR_PTR(-ENOMEM); - } + if (ct == NULL) + goto out; + spin_lock_init(&ct->lock); ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple = *orig; ct->tuplehash[IP_CT_DIR_ORIGINAL].hnnode.pprev = NULL; @@ -857,31 +857,24 @@ __nf_conntrack_alloc(struct net *net, u16 zone, memset(&ct->__nfct_init_offset[0], 0, offsetof(struct nf_conn, proto) - offsetof(struct nf_conn, __nfct_init_offset[0])); -#ifdef CONFIG_NF_CONNTRACK_ZONES - if (zone) { - struct nf_conntrack_zone *nf_ct_zone; - nf_ct_zone = nf_ct_ext_add(ct, NF_CT_EXT_ZONE, GFP_ATOMIC); - if (!nf_ct_zone) - goto out_free; - nf_ct_zone->id = zone; - } -#endif + if (zone && nf_ct_zone_add(ct, GFP_ATOMIC, zone) < 0) + goto out_free; + /* Because we use RCU lookups, we set ct_general.use to zero before * this is inserted in any list. */ atomic_set(&ct->ct_general.use, 0); return ct; - -#ifdef CONFIG_NF_CONNTRACK_ZONES out_free: - atomic_dec(&net->ct.count); kmem_cache_free(net->ct.nf_conntrack_cachep, ct); +out: + atomic_dec(&net->ct.count); return ERR_PTR(-ENOMEM); -#endif } -struct nf_conn *nf_conntrack_alloc(struct net *net, u16 zone, +struct nf_conn *nf_conntrack_alloc(struct net *net, + const struct nf_conntrack_zone *zone, const struct nf_conntrack_tuple *orig, const struct nf_conntrack_tuple *repl, gfp_t gfp) @@ -923,8 +916,9 @@ init_conntrack(struct net *net, struct nf_conn *tmpl, struct nf_conntrack_tuple repl_tuple; struct nf_conntrack_ecache *ecache; struct nf_conntrack_expect *exp = NULL; - u16 zone = tmpl ? nf_ct_zone(tmpl) : NF_CT_DEFAULT_ZONE; + const struct nf_conntrack_zone *zone; struct nf_conn_timeout *timeout_ext; + struct nf_conntrack_zone tmp; unsigned int *timeouts; if (!nf_ct_invert_tuple(&repl_tuple, tuple, l3proto, l4proto)) { @@ -932,6 +926,7 @@ init_conntrack(struct net *net, struct nf_conn *tmpl, return NULL; } + zone = nf_ct_zone_tmpl(tmpl, skb, &tmp); ct = __nf_conntrack_alloc(net, zone, tuple, &repl_tuple, GFP_ATOMIC, hash); if (IS_ERR(ct)) @@ -1026,10 +1021,11 @@ resolve_normal_ct(struct net *net, struct nf_conn *tmpl, int *set_reply, enum ip_conntrack_info *ctinfo) { + const struct nf_conntrack_zone *zone; struct nf_conntrack_tuple tuple; struct nf_conntrack_tuple_hash *h; + struct nf_conntrack_zone tmp; struct nf_conn *ct; - u16 zone = tmpl ? nf_ct_zone(tmpl) : NF_CT_DEFAULT_ZONE; u32 hash; if (!nf_ct_get_tuple(skb, skb_network_offset(skb), @@ -1040,7 +1036,8 @@ resolve_normal_ct(struct net *net, struct nf_conn *tmpl, } /* look for tuple match */ - hash = hash_conntrack_raw(&tuple, zone); + zone = nf_ct_zone_tmpl(tmpl, skb, &tmp); + hash = hash_conntrack_raw(&tuple); h = __nf_conntrack_find_get(net, zone, &tuple, hash); if (!h) { h = init_conntrack(net, tmpl, &tuple, l3proto, l4proto, @@ -1596,8 +1593,7 @@ int nf_conntrack_set_hashsize(const char *val, struct kernel_param *kp) struct nf_conntrack_tuple_hash, hnnode); ct = nf_ct_tuplehash_to_ctrack(h); hlist_nulls_del_rcu(&h->hnnode); - bucket = __hash_conntrack(&h->tuple, nf_ct_zone(ct), - hashsize); + bucket = __hash_conntrack(&h->tuple, hashsize); hlist_nulls_add_head_rcu(&h->hnnode, &hash[bucket]); } } diff --git a/net/netfilter/nf_conntrack_expect.c b/net/netfilter/nf_conntrack_expect.c index b45a4223cb05..acf5c7b3f378 100644 --- a/net/netfilter/nf_conntrack_expect.c +++ b/net/netfilter/nf_conntrack_expect.c @@ -88,7 +88,8 @@ static unsigned int nf_ct_expect_dst_hash(const struct nf_conntrack_tuple *tuple } struct nf_conntrack_expect * -__nf_ct_expect_find(struct net *net, u16 zone, +__nf_ct_expect_find(struct net *net, + const struct nf_conntrack_zone *zone, const struct nf_conntrack_tuple *tuple) { struct nf_conntrack_expect *i; @@ -100,7 +101,7 @@ __nf_ct_expect_find(struct net *net, u16 zone, h = nf_ct_expect_dst_hash(tuple); hlist_for_each_entry_rcu(i, &net->ct.expect_hash[h], hnode) { if (nf_ct_tuple_mask_cmp(tuple, &i->tuple, &i->mask) && - nf_ct_zone(i->master) == zone) + nf_ct_zone_equal_any(i->master, zone)) return i; } return NULL; @@ -109,7 +110,8 @@ EXPORT_SYMBOL_GPL(__nf_ct_expect_find); /* Just find a expectation corresponding to a tuple. */ struct nf_conntrack_expect * -nf_ct_expect_find_get(struct net *net, u16 zone, +nf_ct_expect_find_get(struct net *net, + const struct nf_conntrack_zone *zone, const struct nf_conntrack_tuple *tuple) { struct nf_conntrack_expect *i; @@ -127,7 +129,8 @@ EXPORT_SYMBOL_GPL(nf_ct_expect_find_get); /* If an expectation for this connection is found, it gets delete from * global list then returned. */ struct nf_conntrack_expect * -nf_ct_find_expectation(struct net *net, u16 zone, +nf_ct_find_expectation(struct net *net, + const struct nf_conntrack_zone *zone, const struct nf_conntrack_tuple *tuple) { struct nf_conntrack_expect *i, *exp = NULL; @@ -140,7 +143,7 @@ nf_ct_find_expectation(struct net *net, u16 zone, hlist_for_each_entry(i, &net->ct.expect_hash[h], hnode) { if (!(i->flags & NF_CT_EXPECT_INACTIVE) && nf_ct_tuple_mask_cmp(tuple, &i->tuple, &i->mask) && - nf_ct_zone(i->master) == zone) { + nf_ct_zone_equal_any(i->master, zone)) { exp = i; break; } @@ -220,16 +223,16 @@ static inline int expect_clash(const struct nf_conntrack_expect *a, } return nf_ct_tuple_mask_cmp(&a->tuple, &b->tuple, &intersect_mask) && - nf_ct_zone(a->master) == nf_ct_zone(b->master); + nf_ct_zone_equal_any(a->master, nf_ct_zone(b->master)); } static inline int expect_matches(const struct nf_conntrack_expect *a, const struct nf_conntrack_expect *b) { return a->master == b->master && a->class == b->class && - nf_ct_tuple_equal(&a->tuple, &b->tuple) && - nf_ct_tuple_mask_equal(&a->mask, &b->mask) && - nf_ct_zone(a->master) == nf_ct_zone(b->master); + nf_ct_tuple_equal(&a->tuple, &b->tuple) && + nf_ct_tuple_mask_equal(&a->mask, &b->mask) && + nf_ct_zone_equal_any(a->master, nf_ct_zone(b->master)); } /* Generally a bad idea to call this: could have matched already. */ diff --git a/net/netfilter/nf_conntrack_labels.c b/net/netfilter/nf_conntrack_labels.c index bb53f120e79c..3ce5c314ea4b 100644 --- a/net/netfilter/nf_conntrack_labels.c +++ b/net/netfilter/nf_conntrack_labels.c @@ -14,6 +14,8 @@ #include <net/netfilter/nf_conntrack_ecache.h> #include <net/netfilter/nf_conntrack_labels.h> +static spinlock_t nf_connlabels_lock; + static unsigned int label_bits(const struct nf_conn_labels *l) { unsigned int longs = l->words; @@ -48,7 +50,6 @@ int nf_connlabel_set(struct nf_conn *ct, u16 bit) } EXPORT_SYMBOL_GPL(nf_connlabel_set); -#if IS_ENABLED(CONFIG_NF_CT_NETLINK) static void replace_u32(u32 *address, u32 mask, u32 new) { u32 old, tmp; @@ -89,7 +90,35 @@ int nf_connlabels_replace(struct nf_conn *ct, return 0; } EXPORT_SYMBOL_GPL(nf_connlabels_replace); -#endif + +int nf_connlabels_get(struct net *net, unsigned int n_bits) +{ + size_t words; + + if (n_bits > (NF_CT_LABELS_MAX_SIZE * BITS_PER_BYTE)) + return -ERANGE; + + words = BITS_TO_LONGS(n_bits); + + spin_lock(&nf_connlabels_lock); + net->ct.labels_used++; + if (words > net->ct.label_words) + net->ct.label_words = words; + spin_unlock(&nf_connlabels_lock); + + return 0; +} +EXPORT_SYMBOL_GPL(nf_connlabels_get); + +void nf_connlabels_put(struct net *net) +{ + spin_lock(&nf_connlabels_lock); + net->ct.labels_used--; + if (net->ct.labels_used == 0) + net->ct.label_words = 0; + spin_unlock(&nf_connlabels_lock); +} +EXPORT_SYMBOL_GPL(nf_connlabels_put); static struct nf_ct_ext_type labels_extend __read_mostly = { .len = sizeof(struct nf_conn_labels), @@ -99,6 +128,7 @@ static struct nf_ct_ext_type labels_extend __read_mostly = { int nf_conntrack_labels_init(void) { + spin_lock_init(&nf_connlabels_lock); return nf_ct_extend_register(&labels_extend); } diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c index 6b8b0abbfab4..94a66541e0b7 100644 --- a/net/netfilter/nf_conntrack_netlink.c +++ b/net/netfilter/nf_conntrack_netlink.c @@ -128,6 +128,20 @@ ctnetlink_dump_tuples(struct sk_buff *skb, } static inline int +ctnetlink_dump_zone_id(struct sk_buff *skb, int attrtype, + const struct nf_conntrack_zone *zone, int dir) +{ + if (zone->id == NF_CT_DEFAULT_ZONE_ID || zone->dir != dir) + return 0; + if (nla_put_be16(skb, attrtype, htons(zone->id))) + goto nla_put_failure; + return 0; + +nla_put_failure: + return -1; +} + +static inline int ctnetlink_dump_status(struct sk_buff *skb, const struct nf_conn *ct) { if (nla_put_be32(skb, CTA_STATUS, htonl(ct->status))) @@ -458,6 +472,7 @@ static int ctnetlink_fill_info(struct sk_buff *skb, u32 portid, u32 seq, u32 type, struct nf_conn *ct) { + const struct nf_conntrack_zone *zone; struct nlmsghdr *nlh; struct nfgenmsg *nfmsg; struct nlattr *nest_parms; @@ -473,11 +488,16 @@ ctnetlink_fill_info(struct sk_buff *skb, u32 portid, u32 seq, u32 type, nfmsg->version = NFNETLINK_V0; nfmsg->res_id = 0; + zone = nf_ct_zone(ct); + nest_parms = nla_nest_start(skb, CTA_TUPLE_ORIG | NLA_F_NESTED); if (!nest_parms) goto nla_put_failure; if (ctnetlink_dump_tuples(skb, nf_ct_tuple(ct, IP_CT_DIR_ORIGINAL)) < 0) goto nla_put_failure; + if (ctnetlink_dump_zone_id(skb, CTA_TUPLE_ZONE, zone, + NF_CT_ZONE_DIR_ORIG) < 0) + goto nla_put_failure; nla_nest_end(skb, nest_parms); nest_parms = nla_nest_start(skb, CTA_TUPLE_REPLY | NLA_F_NESTED); @@ -485,10 +505,13 @@ ctnetlink_fill_info(struct sk_buff *skb, u32 portid, u32 seq, u32 type, goto nla_put_failure; if (ctnetlink_dump_tuples(skb, nf_ct_tuple(ct, IP_CT_DIR_REPLY)) < 0) goto nla_put_failure; + if (ctnetlink_dump_zone_id(skb, CTA_TUPLE_ZONE, zone, + NF_CT_ZONE_DIR_REPL) < 0) + goto nla_put_failure; nla_nest_end(skb, nest_parms); - if (nf_ct_zone(ct) && - nla_put_be16(skb, CTA_ZONE, htons(nf_ct_zone(ct)))) + if (ctnetlink_dump_zone_id(skb, CTA_ZONE, zone, + NF_CT_DEFAULT_ZONE_DIR) < 0) goto nla_put_failure; if (ctnetlink_dump_status(skb, ct) < 0 || @@ -598,7 +621,7 @@ ctnetlink_nlmsg_size(const struct nf_conn *ct) + nla_total_size(sizeof(u_int32_t)) /* CTA_MARK */ #endif #ifdef CONFIG_NF_CONNTRACK_ZONES - + nla_total_size(sizeof(u_int16_t)) /* CTA_ZONE */ + + nla_total_size(sizeof(u_int16_t)) /* CTA_ZONE|CTA_TUPLE_ZONE */ #endif + ctnetlink_proto_size(ct) + ctnetlink_label_size(ct) @@ -609,6 +632,7 @@ ctnetlink_nlmsg_size(const struct nf_conn *ct) static int ctnetlink_conntrack_event(unsigned int events, struct nf_ct_event *item) { + const struct nf_conntrack_zone *zone; struct net *net; struct nlmsghdr *nlh; struct nfgenmsg *nfmsg; @@ -655,11 +679,16 @@ ctnetlink_conntrack_event(unsigned int events, struct nf_ct_event *item) nfmsg->res_id = 0; rcu_read_lock(); + zone = nf_ct_zone(ct); + nest_parms = nla_nest_start(skb, CTA_TUPLE_ORIG | NLA_F_NESTED); if (!nest_parms) goto nla_put_failure; if (ctnetlink_dump_tuples(skb, nf_ct_tuple(ct, IP_CT_DIR_ORIGINAL)) < 0) goto nla_put_failure; + if (ctnetlink_dump_zone_id(skb, CTA_TUPLE_ZONE, zone, + NF_CT_ZONE_DIR_ORIG) < 0) + goto nla_put_failure; nla_nest_end(skb, nest_parms); nest_parms = nla_nest_start(skb, CTA_TUPLE_REPLY | NLA_F_NESTED); @@ -667,10 +696,13 @@ ctnetlink_conntrack_event(unsigned int events, struct nf_ct_event *item) goto nla_put_failure; if (ctnetlink_dump_tuples(skb, nf_ct_tuple(ct, IP_CT_DIR_REPLY)) < 0) goto nla_put_failure; + if (ctnetlink_dump_zone_id(skb, CTA_TUPLE_ZONE, zone, + NF_CT_ZONE_DIR_REPL) < 0) + goto nla_put_failure; nla_nest_end(skb, nest_parms); - if (nf_ct_zone(ct) && - nla_put_be16(skb, CTA_ZONE, htons(nf_ct_zone(ct)))) + if (ctnetlink_dump_zone_id(skb, CTA_ZONE, zone, + NF_CT_DEFAULT_ZONE_DIR) < 0) goto nla_put_failure; if (ctnetlink_dump_id(skb, ct) < 0) @@ -920,15 +952,54 @@ ctnetlink_parse_tuple_proto(struct nlattr *attr, return ret; } +static int +ctnetlink_parse_zone(const struct nlattr *attr, + struct nf_conntrack_zone *zone) +{ + nf_ct_zone_init(zone, NF_CT_DEFAULT_ZONE_ID, + NF_CT_DEFAULT_ZONE_DIR, 0); +#ifdef CONFIG_NF_CONNTRACK_ZONES + if (attr) + zone->id = ntohs(nla_get_be16(attr)); +#else + if (attr) + return -EOPNOTSUPP; +#endif + return 0; +} + +static int +ctnetlink_parse_tuple_zone(struct nlattr *attr, enum ctattr_type type, + struct nf_conntrack_zone *zone) +{ + int ret; + + if (zone->id != NF_CT_DEFAULT_ZONE_ID) + return -EINVAL; + + ret = ctnetlink_parse_zone(attr, zone); + if (ret < 0) + return ret; + + if (type == CTA_TUPLE_REPLY) + zone->dir = NF_CT_ZONE_DIR_REPL; + else + zone->dir = NF_CT_ZONE_DIR_ORIG; + + return 0; +} + static const struct nla_policy tuple_nla_policy[CTA_TUPLE_MAX+1] = { [CTA_TUPLE_IP] = { .type = NLA_NESTED }, [CTA_TUPLE_PROTO] = { .type = NLA_NESTED }, + [CTA_TUPLE_ZONE] = { .type = NLA_U16 }, }; static int ctnetlink_parse_tuple(const struct nlattr * const cda[], struct nf_conntrack_tuple *tuple, - enum ctattr_type type, u_int8_t l3num) + enum ctattr_type type, u_int8_t l3num, + struct nf_conntrack_zone *zone) { struct nlattr *tb[CTA_TUPLE_MAX+1]; int err; @@ -955,6 +1026,16 @@ ctnetlink_parse_tuple(const struct nlattr * const cda[], if (err < 0) return err; + if (tb[CTA_TUPLE_ZONE]) { + if (!zone) + return -EINVAL; + + err = ctnetlink_parse_tuple_zone(tb[CTA_TUPLE_ZONE], + type, zone); + if (err < 0) + return err; + } + /* orig and expect tuples get DIR_ORIGINAL */ if (type == CTA_TUPLE_REPLY) tuple->dst.dir = IP_CT_DIR_REPLY; @@ -964,21 +1045,6 @@ ctnetlink_parse_tuple(const struct nlattr * const cda[], return 0; } -static int -ctnetlink_parse_zone(const struct nlattr *attr, u16 *zone) -{ - if (attr) -#ifdef CONFIG_NF_CONNTRACK_ZONES - *zone = ntohs(nla_get_be16(attr)); -#else - return -EOPNOTSUPP; -#endif - else - *zone = 0; - - return 0; -} - static const struct nla_policy help_nla_policy[CTA_HELP_MAX+1] = { [CTA_HELP_NAME] = { .type = NLA_NUL_STRING, .len = NF_CT_HELPER_NAME_LEN - 1 }, @@ -1058,7 +1124,7 @@ ctnetlink_del_conntrack(struct sock *ctnl, struct sk_buff *skb, struct nf_conn *ct; struct nfgenmsg *nfmsg = nlmsg_data(nlh); u_int8_t u3 = nfmsg->nfgen_family; - u16 zone; + struct nf_conntrack_zone zone; int err; err = ctnetlink_parse_zone(cda[CTA_ZONE], &zone); @@ -1066,9 +1132,11 @@ ctnetlink_del_conntrack(struct sock *ctnl, struct sk_buff *skb, return err; if (cda[CTA_TUPLE_ORIG]) - err = ctnetlink_parse_tuple(cda, &tuple, CTA_TUPLE_ORIG, u3); + err = ctnetlink_parse_tuple(cda, &tuple, CTA_TUPLE_ORIG, + u3, &zone); else if (cda[CTA_TUPLE_REPLY]) - err = ctnetlink_parse_tuple(cda, &tuple, CTA_TUPLE_REPLY, u3); + err = ctnetlink_parse_tuple(cda, &tuple, CTA_TUPLE_REPLY, + u3, &zone); else { return ctnetlink_flush_conntrack(net, cda, NETLINK_CB(skb).portid, @@ -1078,7 +1146,7 @@ ctnetlink_del_conntrack(struct sock *ctnl, struct sk_buff *skb, if (err < 0) return err; - h = nf_conntrack_find_get(net, zone, &tuple); + h = nf_conntrack_find_get(net, &zone, &tuple); if (!h) return -ENOENT; @@ -1112,7 +1180,7 @@ ctnetlink_get_conntrack(struct sock *ctnl, struct sk_buff *skb, struct sk_buff *skb2 = NULL; struct nfgenmsg *nfmsg = nlmsg_data(nlh); u_int8_t u3 = nfmsg->nfgen_family; - u16 zone; + struct nf_conntrack_zone zone; int err; if (nlh->nlmsg_flags & NLM_F_DUMP) { @@ -1138,16 +1206,18 @@ ctnetlink_get_conntrack(struct sock *ctnl, struct sk_buff *skb, return err; if (cda[CTA_TUPLE_ORIG]) - err = ctnetlink_parse_tuple(cda, &tuple, CTA_TUPLE_ORIG, u3); + err = ctnetlink_parse_tuple(cda, &tuple, CTA_TUPLE_ORIG, + u3, &zone); else if (cda[CTA_TUPLE_REPLY]) - err = ctnetlink_parse_tuple(cda, &tuple, CTA_TUPLE_REPLY, u3); + err = ctnetlink_parse_tuple(cda, &tuple, CTA_TUPLE_REPLY, + u3, &zone); else return -EINVAL; if (err < 0) return err; - h = nf_conntrack_find_get(net, zone, &tuple); + h = nf_conntrack_find_get(net, &zone, &tuple); if (!h) return -ENOENT; @@ -1645,7 +1715,8 @@ ctnetlink_change_conntrack(struct nf_conn *ct, } static struct nf_conn * -ctnetlink_create_conntrack(struct net *net, u16 zone, +ctnetlink_create_conntrack(struct net *net, + const struct nf_conntrack_zone *zone, const struct nlattr * const cda[], struct nf_conntrack_tuple *otuple, struct nf_conntrack_tuple *rtuple, @@ -1761,7 +1832,8 @@ ctnetlink_create_conntrack(struct net *net, u16 zone, struct nf_conntrack_tuple_hash *master_h; struct nf_conn *master_ct; - err = ctnetlink_parse_tuple(cda, &master, CTA_TUPLE_MASTER, u3); + err = ctnetlink_parse_tuple(cda, &master, CTA_TUPLE_MASTER, + u3, NULL); if (err < 0) goto err2; @@ -1804,7 +1876,7 @@ ctnetlink_new_conntrack(struct sock *ctnl, struct sk_buff *skb, struct nfgenmsg *nfmsg = nlmsg_data(nlh); struct nf_conn *ct; u_int8_t u3 = nfmsg->nfgen_family; - u16 zone; + struct nf_conntrack_zone zone; int err; err = ctnetlink_parse_zone(cda[CTA_ZONE], &zone); @@ -1812,21 +1884,23 @@ ctnetlink_new_conntrack(struct sock *ctnl, struct sk_buff *skb, return err; if (cda[CTA_TUPLE_ORIG]) { - err = ctnetlink_parse_tuple(cda, &otuple, CTA_TUPLE_ORIG, u3); + err = ctnetlink_parse_tuple(cda, &otuple, CTA_TUPLE_ORIG, + u3, &zone); if (err < 0) return err; } if (cda[CTA_TUPLE_REPLY]) { - err = ctnetlink_parse_tuple(cda, &rtuple, CTA_TUPLE_REPLY, u3); + err = ctnetlink_parse_tuple(cda, &rtuple, CTA_TUPLE_REPLY, + u3, &zone); if (err < 0) return err; } if (cda[CTA_TUPLE_ORIG]) - h = nf_conntrack_find_get(net, zone, &otuple); + h = nf_conntrack_find_get(net, &zone, &otuple); else if (cda[CTA_TUPLE_REPLY]) - h = nf_conntrack_find_get(net, zone, &rtuple); + h = nf_conntrack_find_get(net, &zone, &rtuple); if (h == NULL) { err = -ENOENT; @@ -1836,7 +1910,7 @@ ctnetlink_new_conntrack(struct sock *ctnl, struct sk_buff *skb, if (!cda[CTA_TUPLE_ORIG] || !cda[CTA_TUPLE_REPLY]) return -EINVAL; - ct = ctnetlink_create_conntrack(net, zone, cda, &otuple, + ct = ctnetlink_create_conntrack(net, &zone, cda, &otuple, &rtuple, u3); if (IS_ERR(ct)) return PTR_ERR(ct); @@ -2082,7 +2156,7 @@ ctnetlink_nfqueue_build_size(const struct nf_conn *ct) + nla_total_size(sizeof(u_int32_t)) /* CTA_MARK */ #endif #ifdef CONFIG_NF_CONNTRACK_ZONES - + nla_total_size(sizeof(u_int16_t)) /* CTA_ZONE */ + + nla_total_size(sizeof(u_int16_t)) /* CTA_ZONE|CTA_TUPLE_ZONE */ #endif + ctnetlink_proto_size(ct) ; @@ -2091,14 +2165,20 @@ ctnetlink_nfqueue_build_size(const struct nf_conn *ct) static int ctnetlink_nfqueue_build(struct sk_buff *skb, struct nf_conn *ct) { + const struct nf_conntrack_zone *zone; struct nlattr *nest_parms; rcu_read_lock(); + zone = nf_ct_zone(ct); + nest_parms = nla_nest_start(skb, CTA_TUPLE_ORIG | NLA_F_NESTED); if (!nest_parms) goto nla_put_failure; if (ctnetlink_dump_tuples(skb, nf_ct_tuple(ct, IP_CT_DIR_ORIGINAL)) < 0) goto nla_put_failure; + if (ctnetlink_dump_zone_id(skb, CTA_TUPLE_ZONE, zone, + NF_CT_ZONE_DIR_ORIG) < 0) + goto nla_put_failure; nla_nest_end(skb, nest_parms); nest_parms = nla_nest_start(skb, CTA_TUPLE_REPLY | NLA_F_NESTED); @@ -2106,12 +2186,14 @@ ctnetlink_nfqueue_build(struct sk_buff *skb, struct nf_conn *ct) goto nla_put_failure; if (ctnetlink_dump_tuples(skb, nf_ct_tuple(ct, IP_CT_DIR_REPLY)) < 0) goto nla_put_failure; + if (ctnetlink_dump_zone_id(skb, CTA_TUPLE_ZONE, zone, + NF_CT_ZONE_DIR_REPL) < 0) + goto nla_put_failure; nla_nest_end(skb, nest_parms); - if (nf_ct_zone(ct)) { - if (nla_put_be16(skb, CTA_ZONE, htons(nf_ct_zone(ct)))) - goto nla_put_failure; - } + if (ctnetlink_dump_zone_id(skb, CTA_ZONE, zone, + NF_CT_DEFAULT_ZONE_DIR) < 0) + goto nla_put_failure; if (ctnetlink_dump_id(skb, ct) < 0) goto nla_put_failure; @@ -2218,12 +2300,12 @@ static int ctnetlink_nfqueue_exp_parse(const struct nlattr * const *cda, int err; err = ctnetlink_parse_tuple(cda, tuple, CTA_EXPECT_TUPLE, - nf_ct_l3num(ct)); + nf_ct_l3num(ct), NULL); if (err < 0) return err; return ctnetlink_parse_tuple(cda, mask, CTA_EXPECT_MASK, - nf_ct_l3num(ct)); + nf_ct_l3num(ct), NULL); } static int @@ -2612,23 +2694,22 @@ static int ctnetlink_dump_exp_ct(struct sock *ctnl, struct sk_buff *skb, struct nf_conntrack_tuple tuple; struct nf_conntrack_tuple_hash *h; struct nf_conn *ct; - u16 zone = 0; + struct nf_conntrack_zone zone; struct netlink_dump_control c = { .dump = ctnetlink_exp_ct_dump_table, .done = ctnetlink_exp_done, }; - err = ctnetlink_parse_tuple(cda, &tuple, CTA_EXPECT_MASTER, u3); + err = ctnetlink_parse_tuple(cda, &tuple, CTA_EXPECT_MASTER, + u3, NULL); if (err < 0) return err; - if (cda[CTA_EXPECT_ZONE]) { - err = ctnetlink_parse_zone(cda[CTA_EXPECT_ZONE], &zone); - if (err < 0) - return err; - } + err = ctnetlink_parse_zone(cda[CTA_EXPECT_ZONE], &zone); + if (err < 0) + return err; - h = nf_conntrack_find_get(net, zone, &tuple); + h = nf_conntrack_find_get(net, &zone, &tuple); if (!h) return -ENOENT; @@ -2652,7 +2733,7 @@ ctnetlink_get_expect(struct sock *ctnl, struct sk_buff *skb, struct sk_buff *skb2; struct nfgenmsg *nfmsg = nlmsg_data(nlh); u_int8_t u3 = nfmsg->nfgen_family; - u16 zone; + struct nf_conntrack_zone zone; int err; if (nlh->nlmsg_flags & NLM_F_DUMP) { @@ -2672,16 +2753,18 @@ ctnetlink_get_expect(struct sock *ctnl, struct sk_buff *skb, return err; if (cda[CTA_EXPECT_TUPLE]) - err = ctnetlink_parse_tuple(cda, &tuple, CTA_EXPECT_TUPLE, u3); + err = ctnetlink_parse_tuple(cda, &tuple, CTA_EXPECT_TUPLE, + u3, NULL); else if (cda[CTA_EXPECT_MASTER]) - err = ctnetlink_parse_tuple(cda, &tuple, CTA_EXPECT_MASTER, u3); + err = ctnetlink_parse_tuple(cda, &tuple, CTA_EXPECT_MASTER, + u3, NULL); else return -EINVAL; if (err < 0) return err; - exp = nf_ct_expect_find_get(net, zone, &tuple); + exp = nf_ct_expect_find_get(net, &zone, &tuple); if (!exp) return -ENOENT; @@ -2732,8 +2815,8 @@ ctnetlink_del_expect(struct sock *ctnl, struct sk_buff *skb, struct nfgenmsg *nfmsg = nlmsg_data(nlh); struct hlist_node *next; u_int8_t u3 = nfmsg->nfgen_family; + struct nf_conntrack_zone zone; unsigned int i; - u16 zone; int err; if (cda[CTA_EXPECT_TUPLE]) { @@ -2742,12 +2825,13 @@ ctnetlink_del_expect(struct sock *ctnl, struct sk_buff *skb, if (err < 0) return err; - err = ctnetlink_parse_tuple(cda, &tuple, CTA_EXPECT_TUPLE, u3); + err = ctnetlink_parse_tuple(cda, &tuple, CTA_EXPECT_TUPLE, + u3, NULL); if (err < 0) return err; /* bump usage count to 2 */ - exp = nf_ct_expect_find_get(net, zone, &tuple); + exp = nf_ct_expect_find_get(net, &zone, &tuple); if (!exp) return -ENOENT; @@ -2849,7 +2933,8 @@ ctnetlink_parse_expect_nat(const struct nlattr *attr, return -EINVAL; err = ctnetlink_parse_tuple((const struct nlattr * const *)tb, - &nat_tuple, CTA_EXPECT_NAT_TUPLE, u3); + &nat_tuple, CTA_EXPECT_NAT_TUPLE, + u3, NULL); if (err < 0) return err; @@ -2937,7 +3022,8 @@ err_out: } static int -ctnetlink_create_expect(struct net *net, u16 zone, +ctnetlink_create_expect(struct net *net, + const struct nf_conntrack_zone *zone, const struct nlattr * const cda[], u_int8_t u3, u32 portid, int report) { @@ -2949,13 +3035,16 @@ ctnetlink_create_expect(struct net *net, u16 zone, int err; /* caller guarantees that those three CTA_EXPECT_* exist */ - err = ctnetlink_parse_tuple(cda, &tuple, CTA_EXPECT_TUPLE, u3); + err = ctnetlink_parse_tuple(cda, &tuple, CTA_EXPECT_TUPLE, + u3, NULL); if (err < 0) return err; - err = ctnetlink_parse_tuple(cda, &mask, CTA_EXPECT_MASK, u3); + err = ctnetlink_parse_tuple(cda, &mask, CTA_EXPECT_MASK, + u3, NULL); if (err < 0) return err; - err = ctnetlink_parse_tuple(cda, &master_tuple, CTA_EXPECT_MASTER, u3); + err = ctnetlink_parse_tuple(cda, &master_tuple, CTA_EXPECT_MASTER, + u3, NULL); if (err < 0) return err; @@ -3011,7 +3100,7 @@ ctnetlink_new_expect(struct sock *ctnl, struct sk_buff *skb, struct nf_conntrack_expect *exp; struct nfgenmsg *nfmsg = nlmsg_data(nlh); u_int8_t u3 = nfmsg->nfgen_family; - u16 zone; + struct nf_conntrack_zone zone; int err; if (!cda[CTA_EXPECT_TUPLE] @@ -3023,19 +3112,18 @@ ctnetlink_new_expect(struct sock *ctnl, struct sk_buff *skb, if (err < 0) return err; - err = ctnetlink_parse_tuple(cda, &tuple, CTA_EXPECT_TUPLE, u3); + err = ctnetlink_parse_tuple(cda, &tuple, CTA_EXPECT_TUPLE, + u3, NULL); if (err < 0) return err; spin_lock_bh(&nf_conntrack_expect_lock); - exp = __nf_ct_expect_find(net, zone, &tuple); - + exp = __nf_ct_expect_find(net, &zone, &tuple); if (!exp) { spin_unlock_bh(&nf_conntrack_expect_lock); err = -ENOENT; if (nlh->nlmsg_flags & NLM_F_CREATE) { - err = ctnetlink_create_expect(net, zone, cda, - u3, + err = ctnetlink_create_expect(net, &zone, cda, u3, NETLINK_CB(skb).portid, nlmsg_report(nlh)); } diff --git a/net/netfilter/nf_conntrack_pptp.c b/net/netfilter/nf_conntrack_pptp.c index 825c3e3f8305..5588c7ae1ac2 100644 --- a/net/netfilter/nf_conntrack_pptp.c +++ b/net/netfilter/nf_conntrack_pptp.c @@ -143,13 +143,14 @@ static int destroy_sibling_or_exp(struct net *net, struct nf_conn *ct, const struct nf_conntrack_tuple *t) { const struct nf_conntrack_tuple_hash *h; + const struct nf_conntrack_zone *zone; struct nf_conntrack_expect *exp; struct nf_conn *sibling; - u16 zone = nf_ct_zone(ct); pr_debug("trying to timeout ct or exp for tuple "); nf_ct_dump_tuple(t); + zone = nf_ct_zone(ct); h = nf_conntrack_find_get(net, zone, t); if (h) { sibling = nf_ct_tuplehash_to_ctrack(h); diff --git a/net/netfilter/nf_conntrack_proto_sctp.c b/net/netfilter/nf_conntrack_proto_sctp.c index b45da90fad32..67197731eb68 100644 --- a/net/netfilter/nf_conntrack_proto_sctp.c +++ b/net/netfilter/nf_conntrack_proto_sctp.c @@ -42,6 +42,8 @@ static const char *const sctp_conntrack_names[] = { "SHUTDOWN_SENT", "SHUTDOWN_RECD", "SHUTDOWN_ACK_SENT", + "HEARTBEAT_SENT", + "HEARTBEAT_ACKED", }; #define SECS * HZ @@ -57,6 +59,8 @@ static unsigned int sctp_timeouts[SCTP_CONNTRACK_MAX] __read_mostly = { [SCTP_CONNTRACK_SHUTDOWN_SENT] = 300 SECS / 1000, [SCTP_CONNTRACK_SHUTDOWN_RECD] = 300 SECS / 1000, [SCTP_CONNTRACK_SHUTDOWN_ACK_SENT] = 3 SECS, + [SCTP_CONNTRACK_HEARTBEAT_SENT] = 30 SECS, + [SCTP_CONNTRACK_HEARTBEAT_ACKED] = 210 SECS, }; #define sNO SCTP_CONNTRACK_NONE @@ -67,6 +71,8 @@ static unsigned int sctp_timeouts[SCTP_CONNTRACK_MAX] __read_mostly = { #define sSS SCTP_CONNTRACK_SHUTDOWN_SENT #define sSR SCTP_CONNTRACK_SHUTDOWN_RECD #define sSA SCTP_CONNTRACK_SHUTDOWN_ACK_SENT +#define sHS SCTP_CONNTRACK_HEARTBEAT_SENT +#define sHA SCTP_CONNTRACK_HEARTBEAT_ACKED #define sIV SCTP_CONNTRACK_MAX /* @@ -88,6 +94,10 @@ SHUTDOWN_ACK_SENT - We have seen a SHUTDOWN_ACK chunk in the direction opposite to that of the SHUTDOWN chunk. CLOSED - We have seen a SHUTDOWN_COMPLETE chunk in the direction of the SHUTDOWN chunk. Connection is closed. +HEARTBEAT_SENT - We have seen a HEARTBEAT in a new flow. +HEARTBEAT_ACKED - We have seen a HEARTBEAT-ACK in the direction opposite to + that of the HEARTBEAT chunk. Secondary connection is + established. */ /* TODO @@ -97,36 +107,40 @@ CLOSED - We have seen a SHUTDOWN_COMPLETE chunk in the direction of - Check the error type in the reply dir before transitioning from cookie echoed to closed. - Sec 5.2.4 of RFC 2960 - - Multi Homing support. + - Full Multi Homing support. */ /* SCTP conntrack state transitions */ -static const u8 sctp_conntracks[2][9][SCTP_CONNTRACK_MAX] = { +static const u8 sctp_conntracks[2][11][SCTP_CONNTRACK_MAX] = { { /* ORIGINAL */ -/* sNO, sCL, sCW, sCE, sES, sSS, sSR, sSA */ -/* init */ {sCW, sCW, sCW, sCE, sES, sSS, sSR, sSA}, -/* init_ack */ {sCL, sCL, sCW, sCE, sES, sSS, sSR, sSA}, -/* abort */ {sCL, sCL, sCL, sCL, sCL, sCL, sCL, sCL}, -/* shutdown */ {sCL, sCL, sCW, sCE, sSS, sSS, sSR, sSA}, -/* shutdown_ack */ {sSA, sCL, sCW, sCE, sES, sSA, sSA, sSA}, -/* error */ {sCL, sCL, sCW, sCE, sES, sSS, sSR, sSA},/* Can't have Stale cookie*/ -/* cookie_echo */ {sCL, sCL, sCE, sCE, sES, sSS, sSR, sSA},/* 5.2.4 - Big TODO */ -/* cookie_ack */ {sCL, sCL, sCW, sCE, sES, sSS, sSR, sSA},/* Can't come in orig dir */ -/* shutdown_comp*/ {sCL, sCL, sCW, sCE, sES, sSS, sSR, sCL} +/* sNO, sCL, sCW, sCE, sES, sSS, sSR, sSA, sHS, sHA */ +/* init */ {sCW, sCW, sCW, sCE, sES, sSS, sSR, sSA, sCW, sHA}, +/* init_ack */ {sCL, sCL, sCW, sCE, sES, sSS, sSR, sSA, sCL, sHA}, +/* abort */ {sCL, sCL, sCL, sCL, sCL, sCL, sCL, sCL, sCL, sCL}, +/* shutdown */ {sCL, sCL, sCW, sCE, sSS, sSS, sSR, sSA, sCL, sSS}, +/* shutdown_ack */ {sSA, sCL, sCW, sCE, sES, sSA, sSA, sSA, sSA, sHA}, +/* error */ {sCL, sCL, sCW, sCE, sES, sSS, sSR, sSA, sCL, sHA},/* Can't have Stale cookie*/ +/* cookie_echo */ {sCL, sCL, sCE, sCE, sES, sSS, sSR, sSA, sCL, sHA},/* 5.2.4 - Big TODO */ +/* cookie_ack */ {sCL, sCL, sCW, sCE, sES, sSS, sSR, sSA, sCL, sHA},/* Can't come in orig dir */ +/* shutdown_comp*/ {sCL, sCL, sCW, sCE, sES, sSS, sSR, sCL, sCL, sHA}, +/* heartbeat */ {sHS, sCL, sCW, sCE, sES, sSS, sSR, sSA, sHS, sHA}, +/* heartbeat_ack*/ {sCL, sCL, sCW, sCE, sES, sSS, sSR, sSA, sHS, sHA} }, { /* REPLY */ -/* sNO, sCL, sCW, sCE, sES, sSS, sSR, sSA */ -/* init */ {sIV, sCL, sCW, sCE, sES, sSS, sSR, sSA},/* INIT in sCL Big TODO */ -/* init_ack */ {sIV, sCL, sCW, sCE, sES, sSS, sSR, sSA}, -/* abort */ {sIV, sCL, sCL, sCL, sCL, sCL, sCL, sCL}, -/* shutdown */ {sIV, sCL, sCW, sCE, sSR, sSS, sSR, sSA}, -/* shutdown_ack */ {sIV, sCL, sCW, sCE, sES, sSA, sSA, sSA}, -/* error */ {sIV, sCL, sCW, sCL, sES, sSS, sSR, sSA}, -/* cookie_echo */ {sIV, sCL, sCW, sCE, sES, sSS, sSR, sSA},/* Can't come in reply dir */ -/* cookie_ack */ {sIV, sCL, sCW, sES, sES, sSS, sSR, sSA}, -/* shutdown_comp*/ {sIV, sCL, sCW, sCE, sES, sSS, sSR, sCL} +/* sNO, sCL, sCW, sCE, sES, sSS, sSR, sSA, sHS, sHA */ +/* init */ {sIV, sCL, sCW, sCE, sES, sSS, sSR, sSA, sIV, sHA},/* INIT in sCL Big TODO */ +/* init_ack */ {sIV, sCL, sCW, sCE, sES, sSS, sSR, sSA, sIV, sHA}, +/* abort */ {sIV, sCL, sCL, sCL, sCL, sCL, sCL, sCL, sIV, sCL}, +/* shutdown */ {sIV, sCL, sCW, sCE, sSR, sSS, sSR, sSA, sIV, sSR}, +/* shutdown_ack */ {sIV, sCL, sCW, sCE, sES, sSA, sSA, sSA, sIV, sHA}, +/* error */ {sIV, sCL, sCW, sCL, sES, sSS, sSR, sSA, sIV, sHA}, +/* cookie_echo */ {sIV, sCL, sCW, sCE, sES, sSS, sSR, sSA, sIV, sHA},/* Can't come in reply dir */ +/* cookie_ack */ {sIV, sCL, sCW, sES, sES, sSS, sSR, sSA, sIV, sHA}, +/* shutdown_comp*/ {sIV, sCL, sCW, sCE, sES, sSS, sSR, sCL, sIV, sHA}, +/* heartbeat */ {sIV, sCL, sCW, sCE, sES, sSS, sSR, sSA, sHS, sHA}, +/* heartbeat_ack*/ {sIV, sCL, sCW, sCE, sES, sSS, sSR, sSA, sHA, sHA} } }; @@ -278,9 +292,16 @@ static int sctp_new_state(enum ip_conntrack_dir dir, pr_debug("SCTP_CID_SHUTDOWN_COMPLETE\n"); i = 8; break; + case SCTP_CID_HEARTBEAT: + pr_debug("SCTP_CID_HEARTBEAT"); + i = 9; + break; + case SCTP_CID_HEARTBEAT_ACK: + pr_debug("SCTP_CID_HEARTBEAT_ACK"); + i = 10; + break; default: - /* Other chunks like DATA, SACK, HEARTBEAT and - its ACK do not cause a change in state */ + /* Other chunks like DATA or SACK do not change the state */ pr_debug("Unknown chunk type, Will stay in %s\n", sctp_conntrack_names[cur_state]); return cur_state; @@ -329,6 +350,8 @@ static int sctp_packet(struct nf_conn *ct, !test_bit(SCTP_CID_COOKIE_ECHO, map) && !test_bit(SCTP_CID_ABORT, map) && !test_bit(SCTP_CID_SHUTDOWN_ACK, map) && + !test_bit(SCTP_CID_HEARTBEAT, map) && + !test_bit(SCTP_CID_HEARTBEAT_ACK, map) && sh->vtag != ct->proto.sctp.vtag[dir]) { pr_debug("Verification tag check failed\n"); goto out; @@ -357,6 +380,16 @@ static int sctp_packet(struct nf_conn *ct, /* Sec 8.5.1 (D) */ if (sh->vtag != ct->proto.sctp.vtag[dir]) goto out_unlock; + } else if (sch->type == SCTP_CID_HEARTBEAT || + sch->type == SCTP_CID_HEARTBEAT_ACK) { + if (ct->proto.sctp.vtag[dir] == 0) { + pr_debug("Setting vtag %x for dir %d\n", + sh->vtag, dir); + ct->proto.sctp.vtag[dir] = sh->vtag; + } else if (sh->vtag != ct->proto.sctp.vtag[dir]) { + pr_debug("Verification tag check failed\n"); + goto out_unlock; + } } old_state = ct->proto.sctp.state; @@ -466,6 +499,10 @@ static bool sctp_new(struct nf_conn *ct, const struct sk_buff *skb, /* Sec 8.5.1 (A) */ return false; } + } else if (sch->type == SCTP_CID_HEARTBEAT) { + pr_debug("Setting vtag %x for secondary conntrack\n", + sh->vtag); + ct->proto.sctp.vtag[IP_CT_DIR_ORIGINAL] = sh->vtag; } /* If it is a shutdown ack OOTB packet, we expect a return shutdown complete, otherwise an ABORT Sec 8.4 (5) and (8) */ @@ -610,6 +647,8 @@ sctp_timeout_nla_policy[CTA_TIMEOUT_SCTP_MAX+1] = { [CTA_TIMEOUT_SCTP_SHUTDOWN_SENT] = { .type = NLA_U32 }, [CTA_TIMEOUT_SCTP_SHUTDOWN_RECD] = { .type = NLA_U32 }, [CTA_TIMEOUT_SCTP_SHUTDOWN_ACK_SENT] = { .type = NLA_U32 }, + [CTA_TIMEOUT_SCTP_HEARTBEAT_SENT] = { .type = NLA_U32 }, + [CTA_TIMEOUT_SCTP_HEARTBEAT_ACKED] = { .type = NLA_U32 }, }; #endif /* CONFIG_NF_CT_NETLINK_TIMEOUT */ @@ -658,6 +697,18 @@ static struct ctl_table sctp_sysctl_table[] = { .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, + { + .procname = "nf_conntrack_sctp_timeout_heartbeat_sent", + .maxlen = sizeof(unsigned int), + .mode = 0644, + .proc_handler = proc_dointvec_jiffies, + }, + { + .procname = "nf_conntrack_sctp_timeout_heartbeat_acked", + .maxlen = sizeof(unsigned int), + .mode = 0644, + .proc_handler = proc_dointvec_jiffies, + }, { } }; @@ -730,6 +781,8 @@ static int sctp_kmemdup_sysctl_table(struct nf_proto_net *pn, pn->ctl_table[4].data = &sn->timeouts[SCTP_CONNTRACK_SHUTDOWN_SENT]; pn->ctl_table[5].data = &sn->timeouts[SCTP_CONNTRACK_SHUTDOWN_RECD]; pn->ctl_table[6].data = &sn->timeouts[SCTP_CONNTRACK_SHUTDOWN_ACK_SENT]; + pn->ctl_table[7].data = &sn->timeouts[SCTP_CONNTRACK_HEARTBEAT_SENT]; + pn->ctl_table[8].data = &sn->timeouts[SCTP_CONNTRACK_HEARTBEAT_ACKED]; #endif return 0; } diff --git a/net/netfilter/nf_conntrack_seqadj.c b/net/netfilter/nf_conntrack_seqadj.c index ce3e840c8704..dff0f0cc59e4 100644 --- a/net/netfilter/nf_conntrack_seqadj.c +++ b/net/netfilter/nf_conntrack_seqadj.c @@ -103,9 +103,9 @@ static void nf_ct_sack_block_adjust(struct sk_buff *skb, ntohl(sack->end_seq), ntohl(new_end_seq)); inet_proto_csum_replace4(&tcph->check, skb, - sack->start_seq, new_start_seq, 0); + sack->start_seq, new_start_seq, false); inet_proto_csum_replace4(&tcph->check, skb, - sack->end_seq, new_end_seq, 0); + sack->end_seq, new_end_seq, false); sack->start_seq = new_start_seq; sack->end_seq = new_end_seq; sackoff += sizeof(*sack); @@ -193,8 +193,9 @@ int nf_ct_seq_adjust(struct sk_buff *skb, newseq = htonl(ntohl(tcph->seq) + seqoff); newack = htonl(ntohl(tcph->ack_seq) - ackoff); - inet_proto_csum_replace4(&tcph->check, skb, tcph->seq, newseq, 0); - inet_proto_csum_replace4(&tcph->check, skb, tcph->ack_seq, newack, 0); + inet_proto_csum_replace4(&tcph->check, skb, tcph->seq, newseq, false); + inet_proto_csum_replace4(&tcph->check, skb, tcph->ack_seq, newack, + false); pr_debug("Adjusting sequence number from %u->%u, ack from %u->%u\n", ntohl(tcph->seq), ntohl(newseq), ntohl(tcph->ack_seq), diff --git a/net/netfilter/nf_conntrack_standalone.c b/net/netfilter/nf_conntrack_standalone.c index fc823fa5dcf5..1fb3cacc04e1 100644 --- a/net/netfilter/nf_conntrack_standalone.c +++ b/net/netfilter/nf_conntrack_standalone.c @@ -140,6 +140,35 @@ static inline void ct_show_secctx(struct seq_file *s, const struct nf_conn *ct) } #endif +#ifdef CONFIG_NF_CONNTRACK_ZONES +static void ct_show_zone(struct seq_file *s, const struct nf_conn *ct, + int dir) +{ + const struct nf_conntrack_zone *zone = nf_ct_zone(ct); + + if (zone->dir != dir) + return; + switch (zone->dir) { + case NF_CT_DEFAULT_ZONE_DIR: + seq_printf(s, "zone=%u ", zone->id); + break; + case NF_CT_ZONE_DIR_ORIG: + seq_printf(s, "zone-orig=%u ", zone->id); + break; + case NF_CT_ZONE_DIR_REPL: + seq_printf(s, "zone-reply=%u ", zone->id); + break; + default: + break; + } +} +#else +static inline void ct_show_zone(struct seq_file *s, const struct nf_conn *ct, + int dir) +{ +} +#endif + #ifdef CONFIG_NF_CONNTRACK_TIMESTAMP static void ct_show_delta_time(struct seq_file *s, const struct nf_conn *ct) { @@ -202,6 +231,8 @@ static int ct_seq_show(struct seq_file *s, void *v) print_tuple(s, &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple, l3proto, l4proto); + ct_show_zone(s, ct, NF_CT_ZONE_DIR_ORIG); + if (seq_has_overflowed(s)) goto release; @@ -214,6 +245,8 @@ static int ct_seq_show(struct seq_file *s, void *v) print_tuple(s, &ct->tuplehash[IP_CT_DIR_REPLY].tuple, l3proto, l4proto); + ct_show_zone(s, ct, NF_CT_ZONE_DIR_REPL); + if (seq_print_acct(s, ct, IP_CT_DIR_REPLY)) goto release; @@ -228,11 +261,7 @@ static int ct_seq_show(struct seq_file *s, void *v) #endif ct_show_secctx(s, ct); - -#ifdef CONFIG_NF_CONNTRACK_ZONES - seq_printf(s, "zone=%u ", nf_ct_zone(ct)); -#endif - + ct_show_zone(s, ct, NF_CT_DEFAULT_ZONE_DIR); ct_show_delta_time(s, ct); seq_printf(s, "use=%u\n", atomic_read(&ct->ct_general.use)); diff --git a/net/netfilter/nf_internals.h b/net/netfilter/nf_internals.h index 399210693c2a..065522564ac6 100644 --- a/net/netfilter/nf_internals.h +++ b/net/netfilter/nf_internals.h @@ -19,7 +19,7 @@ unsigned int nf_iterate(struct list_head *head, struct sk_buff *skb, /* nf_queue.c */ int nf_queue(struct sk_buff *skb, struct nf_hook_ops *elem, struct nf_hook_state *state, unsigned int queuenum); -void nf_queue_nf_hook_drop(struct nf_hook_ops *ops); +void nf_queue_nf_hook_drop(struct net *net, struct nf_hook_ops *ops); int __init netfilter_queue_init(void); /* nf_log.c */ diff --git a/net/netfilter/nf_nat_core.c b/net/netfilter/nf_nat_core.c index 4e0b47831d43..5113dfd39df9 100644 --- a/net/netfilter/nf_nat_core.c +++ b/net/netfilter/nf_nat_core.c @@ -118,14 +118,13 @@ EXPORT_SYMBOL(nf_xfrm_me_harder); /* We keep an extra hash for each conntrack, for fast searching. */ static inline unsigned int -hash_by_src(const struct net *net, u16 zone, - const struct nf_conntrack_tuple *tuple) +hash_by_src(const struct net *net, const struct nf_conntrack_tuple *tuple) { unsigned int hash; /* Original src, to ensure we map it consistently if poss. */ hash = jhash2((u32 *)&tuple->src, sizeof(tuple->src) / sizeof(u32), - tuple->dst.protonum ^ zone ^ nf_conntrack_hash_rnd); + tuple->dst.protonum ^ nf_conntrack_hash_rnd); return reciprocal_scale(hash, net->ct.nat_htable_size); } @@ -185,20 +184,22 @@ same_src(const struct nf_conn *ct, /* Only called for SRC manip */ static int -find_appropriate_src(struct net *net, u16 zone, +find_appropriate_src(struct net *net, + const struct nf_conntrack_zone *zone, const struct nf_nat_l3proto *l3proto, const struct nf_nat_l4proto *l4proto, const struct nf_conntrack_tuple *tuple, struct nf_conntrack_tuple *result, const struct nf_nat_range *range) { - unsigned int h = hash_by_src(net, zone, tuple); + unsigned int h = hash_by_src(net, tuple); const struct nf_conn_nat *nat; const struct nf_conn *ct; hlist_for_each_entry_rcu(nat, &net->ct.nat_bysource[h], bysource) { ct = nat->ct; - if (same_src(ct, tuple) && nf_ct_zone(ct) == zone) { + if (same_src(ct, tuple) && + nf_ct_zone_equal(ct, zone, IP_CT_DIR_ORIGINAL)) { /* Copy source part from reply tuple. */ nf_ct_invert_tuplepr(result, &ct->tuplehash[IP_CT_DIR_REPLY].tuple); @@ -218,7 +219,8 @@ find_appropriate_src(struct net *net, u16 zone, * the ip with the lowest src-ip/dst-ip/proto usage. */ static void -find_best_ips_proto(u16 zone, struct nf_conntrack_tuple *tuple, +find_best_ips_proto(const struct nf_conntrack_zone *zone, + struct nf_conntrack_tuple *tuple, const struct nf_nat_range *range, const struct nf_conn *ct, enum nf_nat_manip_type maniptype) @@ -258,7 +260,7 @@ find_best_ips_proto(u16 zone, struct nf_conntrack_tuple *tuple, */ j = jhash2((u32 *)&tuple->src.u3, sizeof(tuple->src.u3) / sizeof(u32), range->flags & NF_NAT_RANGE_PERSISTENT ? - 0 : (__force u32)tuple->dst.u3.all[max] ^ zone); + 0 : (__force u32)tuple->dst.u3.all[max] ^ zone->id); full_range = false; for (i = 0; i <= max; i++) { @@ -297,10 +299,12 @@ get_unique_tuple(struct nf_conntrack_tuple *tuple, struct nf_conn *ct, enum nf_nat_manip_type maniptype) { + const struct nf_conntrack_zone *zone; const struct nf_nat_l3proto *l3proto; const struct nf_nat_l4proto *l4proto; struct net *net = nf_ct_net(ct); - u16 zone = nf_ct_zone(ct); + + zone = nf_ct_zone(ct); rcu_read_lock(); l3proto = __nf_nat_l3proto_find(orig_tuple->src.l3num); @@ -420,7 +424,7 @@ nf_nat_setup_info(struct nf_conn *ct, if (maniptype == NF_NAT_MANIP_SRC) { unsigned int srchash; - srchash = hash_by_src(net, nf_ct_zone(ct), + srchash = hash_by_src(net, &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple); spin_lock_bh(&nf_nat_lock); /* nf_conntrack_alter_reply might re-allocate extension aera */ diff --git a/net/netfilter/nf_nat_proto_dccp.c b/net/netfilter/nf_nat_proto_dccp.c index b8067b53ff3a..15c47b246d0d 100644 --- a/net/netfilter/nf_nat_proto_dccp.c +++ b/net/netfilter/nf_nat_proto_dccp.c @@ -69,7 +69,7 @@ dccp_manip_pkt(struct sk_buff *skb, l3proto->csum_update(skb, iphdroff, &hdr->dccph_checksum, tuple, maniptype); inet_proto_csum_replace2(&hdr->dccph_checksum, skb, oldport, newport, - 0); + false); return true; } diff --git a/net/netfilter/nf_nat_proto_tcp.c b/net/netfilter/nf_nat_proto_tcp.c index 37f5505f4529..4f8820fc5148 100644 --- a/net/netfilter/nf_nat_proto_tcp.c +++ b/net/netfilter/nf_nat_proto_tcp.c @@ -70,7 +70,7 @@ tcp_manip_pkt(struct sk_buff *skb, return true; l3proto->csum_update(skb, iphdroff, &hdr->check, tuple, maniptype); - inet_proto_csum_replace2(&hdr->check, skb, oldport, newport, 0); + inet_proto_csum_replace2(&hdr->check, skb, oldport, newport, false); return true; } diff --git a/net/netfilter/nf_nat_proto_udp.c b/net/netfilter/nf_nat_proto_udp.c index b0ede2f0d8bc..b1e627227b6e 100644 --- a/net/netfilter/nf_nat_proto_udp.c +++ b/net/netfilter/nf_nat_proto_udp.c @@ -57,7 +57,7 @@ udp_manip_pkt(struct sk_buff *skb, l3proto->csum_update(skb, iphdroff, &hdr->check, tuple, maniptype); inet_proto_csum_replace2(&hdr->check, skb, *portptr, newport, - 0); + false); if (!hdr->check) hdr->check = CSUM_MANGLED_0; } diff --git a/net/netfilter/nf_nat_proto_udplite.c b/net/netfilter/nf_nat_proto_udplite.c index 368f14e01e75..58340c97bd83 100644 --- a/net/netfilter/nf_nat_proto_udplite.c +++ b/net/netfilter/nf_nat_proto_udplite.c @@ -56,7 +56,7 @@ udplite_manip_pkt(struct sk_buff *skb, } l3proto->csum_update(skb, iphdroff, &hdr->check, tuple, maniptype); - inet_proto_csum_replace2(&hdr->check, skb, *portptr, newport, 0); + inet_proto_csum_replace2(&hdr->check, skb, *portptr, newport, false); if (!hdr->check) hdr->check = CSUM_MANGLED_0; diff --git a/net/netfilter/nf_queue.c b/net/netfilter/nf_queue.c index 8a8b2abc35ff..96777f9a9350 100644 --- a/net/netfilter/nf_queue.c +++ b/net/netfilter/nf_queue.c @@ -105,21 +105,15 @@ bool nf_queue_entry_get_refs(struct nf_queue_entry *entry) } EXPORT_SYMBOL_GPL(nf_queue_entry_get_refs); -void nf_queue_nf_hook_drop(struct nf_hook_ops *ops) +void nf_queue_nf_hook_drop(struct net *net, struct nf_hook_ops *ops) { const struct nf_queue_handler *qh; - struct net *net; - rtnl_lock(); rcu_read_lock(); qh = rcu_dereference(queue_handler); - if (qh) { - for_each_net(net) { - qh->nf_hook_drop(net, ops); - } - } + if (qh) + qh->nf_hook_drop(net, ops); rcu_read_unlock(); - rtnl_unlock(); } /* diff --git a/net/netfilter/nf_synproxy_core.c b/net/netfilter/nf_synproxy_core.c index d7f168527903..c8a4a48bced9 100644 --- a/net/netfilter/nf_synproxy_core.c +++ b/net/netfilter/nf_synproxy_core.c @@ -17,10 +17,12 @@ #include <linux/netfilter/x_tables.h> #include <linux/netfilter/xt_tcpudp.h> #include <linux/netfilter/xt_SYNPROXY.h> + #include <net/netfilter/nf_conntrack.h> #include <net/netfilter/nf_conntrack_extend.h> #include <net/netfilter/nf_conntrack_seqadj.h> #include <net/netfilter/nf_conntrack_synproxy.h> +#include <net/netfilter/nf_conntrack_zones.h> int synproxy_net_id; EXPORT_SYMBOL_GPL(synproxy_net_id); @@ -186,7 +188,7 @@ unsigned int synproxy_tstamp_adjust(struct sk_buff *skb, const struct nf_conn_synproxy *synproxy) { unsigned int optoff, optend; - u32 *ptr, old; + __be32 *ptr, old; if (synproxy->tsoff == 0) return 1; @@ -214,18 +216,18 @@ unsigned int synproxy_tstamp_adjust(struct sk_buff *skb, if (op[0] == TCPOPT_TIMESTAMP && op[1] == TCPOLEN_TIMESTAMP) { if (CTINFO2DIR(ctinfo) == IP_CT_DIR_REPLY) { - ptr = (u32 *)&op[2]; + ptr = (__be32 *)&op[2]; old = *ptr; *ptr = htonl(ntohl(*ptr) - synproxy->tsoff); } else { - ptr = (u32 *)&op[6]; + ptr = (__be32 *)&op[6]; old = *ptr; *ptr = htonl(ntohl(*ptr) + synproxy->tsoff); } inet_proto_csum_replace4(&th->check, skb, - old, *ptr, 0); + old, *ptr, false); return 1; } optoff += op[1]; @@ -352,7 +354,7 @@ static int __net_init synproxy_net_init(struct net *net) struct nf_conn *ct; int err = -ENOMEM; - ct = nf_ct_tmpl_alloc(net, 0, GFP_KERNEL); + ct = nf_ct_tmpl_alloc(net, &nf_ct_zone_dflt, GFP_KERNEL); if (!ct) goto err1; @@ -378,7 +380,7 @@ static int __net_init synproxy_net_init(struct net *net) err3: free_percpu(snet->stats); err2: - nf_conntrack_free(ct); + nf_ct_tmpl_free(ct); err1: return err; } diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index cfe636808541..4a41eb92bcc0 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -130,20 +130,24 @@ static void nft_trans_destroy(struct nft_trans *trans) int nft_register_basechain(struct nft_base_chain *basechain, unsigned int hook_nops) { + struct net *net = read_pnet(&basechain->pnet); + if (basechain->flags & NFT_BASECHAIN_DISABLED) return 0; - return nf_register_hooks(basechain->ops, hook_nops); + return nf_register_net_hooks(net, basechain->ops, hook_nops); } EXPORT_SYMBOL_GPL(nft_register_basechain); void nft_unregister_basechain(struct nft_base_chain *basechain, unsigned int hook_nops) { + struct net *net = read_pnet(&basechain->pnet); + if (basechain->flags & NFT_BASECHAIN_DISABLED) return; - nf_unregister_hooks(basechain->ops, hook_nops); + nf_unregister_net_hooks(net, basechain->ops, hook_nops); } EXPORT_SYMBOL_GPL(nft_unregister_basechain); diff --git a/net/netfilter/nf_tables_core.c b/net/netfilter/nf_tables_core.c index f77bad46ac68..05d0b03530f6 100644 --- a/net/netfilter/nf_tables_core.c +++ b/net/netfilter/nf_tables_core.c @@ -114,7 +114,6 @@ unsigned int nft_do_chain(struct nft_pktinfo *pkt, const struct nf_hook_ops *ops) { const struct nft_chain *chain = ops->priv, *basechain = chain; - const struct net *chain_net = read_pnet(&nft_base_chain(basechain)->pnet); const struct net *net = dev_net(pkt->in ? pkt->in : pkt->out); const struct nft_rule *rule; const struct nft_expr *expr, *last; @@ -125,10 +124,6 @@ nft_do_chain(struct nft_pktinfo *pkt, const struct nf_hook_ops *ops) int rulenum; unsigned int gencursor = nft_genmask_cur(net); - /* Ignore chains that are not for the current network namespace */ - if (!net_eq(net, chain_net)) - return NF_ACCEPT; - do_chain: rulenum = 0; rule = list_entry(&chain->rules, struct nft_rule, list); diff --git a/net/netfilter/nfnetlink.c b/net/netfilter/nfnetlink.c index 0c0e8ecf02ab..70277b11f742 100644 --- a/net/netfilter/nfnetlink.c +++ b/net/netfilter/nfnetlink.c @@ -444,6 +444,7 @@ done: static void nfnetlink_rcv(struct sk_buff *skb) { struct nlmsghdr *nlh = nlmsg_hdr(skb); + u_int16_t res_id; int msglen; if (nlh->nlmsg_len < NLMSG_HDRLEN || @@ -468,7 +469,12 @@ static void nfnetlink_rcv(struct sk_buff *skb) nfgenmsg = nlmsg_data(nlh); skb_pull(skb, msglen); - nfnetlink_rcv_batch(skb, nlh, nfgenmsg->res_id); + /* Work around old nft using host byte order */ + if (nfgenmsg->res_id == NFNL_SUBSYS_NFTABLES) + res_id = NFNL_SUBSYS_NFTABLES; + else + res_id = ntohs(nfgenmsg->res_id); + nfnetlink_rcv_batch(skb, nlh, res_id); } else { netlink_rcv_skb(skb, &nfnetlink_rcv_msg); } diff --git a/net/netfilter/nfnetlink_acct.c b/net/netfilter/nfnetlink_acct.c index c18af2f63eef..fefbf5f0b28d 100644 --- a/net/netfilter/nfnetlink_acct.c +++ b/net/netfilter/nfnetlink_acct.c @@ -27,8 +27,6 @@ MODULE_LICENSE("GPL"); MODULE_AUTHOR("Pablo Neira Ayuso <pablo@netfilter.org>"); MODULE_DESCRIPTION("nfacct: Extended Netfilter accounting infrastructure"); -static LIST_HEAD(nfnl_acct_list); - struct nf_acct { atomic64_t pkts; atomic64_t bytes; @@ -53,6 +51,7 @@ nfnl_acct_new(struct sock *nfnl, struct sk_buff *skb, const struct nlmsghdr *nlh, const struct nlattr * const tb[]) { struct nf_acct *nfacct, *matching = NULL; + struct net *net = sock_net(nfnl); char *acct_name; unsigned int size = 0; u32 flags = 0; @@ -64,7 +63,7 @@ nfnl_acct_new(struct sock *nfnl, struct sk_buff *skb, if (strlen(acct_name) == 0) return -EINVAL; - list_for_each_entry(nfacct, &nfnl_acct_list, head) { + list_for_each_entry(nfacct, &net->nfnl_acct_list, head) { if (strncmp(nfacct->name, acct_name, NFACCT_NAME_MAX) != 0) continue; @@ -124,7 +123,7 @@ nfnl_acct_new(struct sock *nfnl, struct sk_buff *skb, be64_to_cpu(nla_get_be64(tb[NFACCT_PKTS]))); } atomic_set(&nfacct->refcnt, 1); - list_add_tail_rcu(&nfacct->head, &nfnl_acct_list); + list_add_tail_rcu(&nfacct->head, &net->nfnl_acct_list); return 0; } @@ -185,6 +184,7 @@ nla_put_failure: static int nfnl_acct_dump(struct sk_buff *skb, struct netlink_callback *cb) { + struct net *net = sock_net(skb->sk); struct nf_acct *cur, *last; const struct nfacct_filter *filter = cb->data; @@ -196,7 +196,7 @@ nfnl_acct_dump(struct sk_buff *skb, struct netlink_callback *cb) cb->args[1] = 0; rcu_read_lock(); - list_for_each_entry_rcu(cur, &nfnl_acct_list, head) { + list_for_each_entry_rcu(cur, &net->nfnl_acct_list, head) { if (last) { if (cur != last) continue; @@ -257,6 +257,7 @@ static int nfnl_acct_get(struct sock *nfnl, struct sk_buff *skb, const struct nlmsghdr *nlh, const struct nlattr * const tb[]) { + struct net *net = sock_net(nfnl); int ret = -ENOENT; struct nf_acct *cur; char *acct_name; @@ -283,7 +284,7 @@ nfnl_acct_get(struct sock *nfnl, struct sk_buff *skb, return -EINVAL; acct_name = nla_data(tb[NFACCT_NAME]); - list_for_each_entry(cur, &nfnl_acct_list, head) { + list_for_each_entry(cur, &net->nfnl_acct_list, head) { struct sk_buff *skb2; if (strncmp(cur->name, acct_name, NFACCT_NAME_MAX)!= 0) @@ -336,19 +337,20 @@ static int nfnl_acct_del(struct sock *nfnl, struct sk_buff *skb, const struct nlmsghdr *nlh, const struct nlattr * const tb[]) { + struct net *net = sock_net(nfnl); char *acct_name; struct nf_acct *cur; int ret = -ENOENT; if (!tb[NFACCT_NAME]) { - list_for_each_entry(cur, &nfnl_acct_list, head) + list_for_each_entry(cur, &net->nfnl_acct_list, head) nfnl_acct_try_del(cur); return 0; } acct_name = nla_data(tb[NFACCT_NAME]); - list_for_each_entry(cur, &nfnl_acct_list, head) { + list_for_each_entry(cur, &net->nfnl_acct_list, head) { if (strncmp(cur->name, acct_name, NFACCT_NAME_MAX) != 0) continue; @@ -394,12 +396,12 @@ static const struct nfnetlink_subsystem nfnl_acct_subsys = { MODULE_ALIAS_NFNL_SUBSYS(NFNL_SUBSYS_ACCT); -struct nf_acct *nfnl_acct_find_get(const char *acct_name) +struct nf_acct *nfnl_acct_find_get(struct net *net, const char *acct_name) { struct nf_acct *cur, *acct = NULL; rcu_read_lock(); - list_for_each_entry_rcu(cur, &nfnl_acct_list, head) { + list_for_each_entry_rcu(cur, &net->nfnl_acct_list, head) { if (strncmp(cur->name, acct_name, NFACCT_NAME_MAX)!= 0) continue; @@ -422,7 +424,9 @@ EXPORT_SYMBOL_GPL(nfnl_acct_find_get); void nfnl_acct_put(struct nf_acct *acct) { - atomic_dec(&acct->refcnt); + if (atomic_dec_and_test(&acct->refcnt)) + kfree_rcu(acct, rcu_head); + module_put(THIS_MODULE); } EXPORT_SYMBOL_GPL(nfnl_acct_put); @@ -478,34 +482,59 @@ int nfnl_acct_overquota(const struct sk_buff *skb, struct nf_acct *nfacct) } EXPORT_SYMBOL_GPL(nfnl_acct_overquota); +static int __net_init nfnl_acct_net_init(struct net *net) +{ + INIT_LIST_HEAD(&net->nfnl_acct_list); + + return 0; +} + +static void __net_exit nfnl_acct_net_exit(struct net *net) +{ + struct nf_acct *cur, *tmp; + + list_for_each_entry_safe(cur, tmp, &net->nfnl_acct_list, head) { + list_del_rcu(&cur->head); + + if (atomic_dec_and_test(&cur->refcnt)) + kfree_rcu(cur, rcu_head); + } +} + +static struct pernet_operations nfnl_acct_ops = { + .init = nfnl_acct_net_init, + .exit = nfnl_acct_net_exit, +}; + static int __init nfnl_acct_init(void) { int ret; + ret = register_pernet_subsys(&nfnl_acct_ops); + if (ret < 0) { + pr_err("nfnl_acct_init: failed to register pernet ops\n"); + goto err_out; + } + pr_info("nfnl_acct: registering with nfnetlink.\n"); ret = nfnetlink_subsys_register(&nfnl_acct_subsys); if (ret < 0) { pr_err("nfnl_acct_init: cannot register with nfnetlink.\n"); - goto err_out; + goto cleanup_pernet; } return 0; + +cleanup_pernet: + unregister_pernet_subsys(&nfnl_acct_ops); err_out: return ret; } static void __exit nfnl_acct_exit(void) { - struct nf_acct *cur, *tmp; - pr_info("nfnl_acct: unregistering from nfnetlink.\n"); nfnetlink_subsys_unregister(&nfnl_acct_subsys); - - list_for_each_entry_safe(cur, tmp, &nfnl_acct_list, head) { - list_del_rcu(&cur->head); - /* We are sure that our objects have no clients at this point, - * it's safe to release them all without checking refcnt. */ - kfree_rcu(cur, rcu_head); - } + unregister_pernet_subsys(&nfnl_acct_ops); } module_init(nfnl_acct_init); diff --git a/net/netfilter/nfnetlink_queue_core.c b/net/netfilter/nfnetlink_queue_core.c index 685cc6a17163..a5cd6d90b78b 100644 --- a/net/netfilter/nfnetlink_queue_core.c +++ b/net/netfilter/nfnetlink_queue_core.c @@ -301,7 +301,7 @@ nfqnl_build_packet_message(struct net *net, struct nfqnl_instance *queue, __be32 **packet_id_ptr) { size_t size; - size_t data_len = 0, cap_len = 0; + size_t data_len = 0, cap_len = 0, rem_len = 0; unsigned int hlen = 0; struct sk_buff *skb; struct nlattr *nla; @@ -360,6 +360,7 @@ nfqnl_build_packet_message(struct net *net, struct nfqnl_instance *queue, hlen = min_t(unsigned int, hlen, data_len); size += sizeof(struct nlattr) + hlen; cap_len = entskb->len; + rem_len = data_len - hlen; break; } @@ -377,7 +378,7 @@ nfqnl_build_packet_message(struct net *net, struct nfqnl_instance *queue, size += nla_total_size(seclen); } - skb = nfnetlink_alloc_skb(net, size, queue->peer_portid, + skb = __netlink_alloc_skb(net->nfnl, size, rem_len, queue->peer_portid, GFP_ATOMIC); if (!skb) { skb_tx_error(entskb); diff --git a/net/netfilter/nft_counter.c b/net/netfilter/nft_counter.c index 17591239229f..1067fb4c1ffa 100644 --- a/net/netfilter/nft_counter.c +++ b/net/netfilter/nft_counter.c @@ -18,39 +18,59 @@ #include <net/netfilter/nf_tables.h> struct nft_counter { - seqlock_t lock; u64 bytes; u64 packets; }; +struct nft_counter_percpu { + struct nft_counter counter; + struct u64_stats_sync syncp; +}; + +struct nft_counter_percpu_priv { + struct nft_counter_percpu __percpu *counter; +}; + static void nft_counter_eval(const struct nft_expr *expr, struct nft_regs *regs, const struct nft_pktinfo *pkt) { - struct nft_counter *priv = nft_expr_priv(expr); - - write_seqlock_bh(&priv->lock); - priv->bytes += pkt->skb->len; - priv->packets++; - write_sequnlock_bh(&priv->lock); + struct nft_counter_percpu_priv *priv = nft_expr_priv(expr); + struct nft_counter_percpu *this_cpu; + + local_bh_disable(); + this_cpu = this_cpu_ptr(priv->counter); + u64_stats_update_begin(&this_cpu->syncp); + this_cpu->counter.bytes += pkt->skb->len; + this_cpu->counter.packets++; + u64_stats_update_end(&this_cpu->syncp); + local_bh_enable(); } static int nft_counter_dump(struct sk_buff *skb, const struct nft_expr *expr) { - struct nft_counter *priv = nft_expr_priv(expr); + struct nft_counter_percpu_priv *priv = nft_expr_priv(expr); + struct nft_counter_percpu *cpu_stats; + struct nft_counter total; + u64 bytes, packets; unsigned int seq; - u64 bytes; - u64 packets; - - do { - seq = read_seqbegin(&priv->lock); - bytes = priv->bytes; - packets = priv->packets; - } while (read_seqretry(&priv->lock, seq)); - - if (nla_put_be64(skb, NFTA_COUNTER_BYTES, cpu_to_be64(bytes))) - goto nla_put_failure; - if (nla_put_be64(skb, NFTA_COUNTER_PACKETS, cpu_to_be64(packets))) + int cpu; + + memset(&total, 0, sizeof(total)); + for_each_possible_cpu(cpu) { + cpu_stats = per_cpu_ptr(priv->counter, cpu); + do { + seq = u64_stats_fetch_begin_irq(&cpu_stats->syncp); + bytes = cpu_stats->counter.bytes; + packets = cpu_stats->counter.packets; + } while (u64_stats_fetch_retry_irq(&cpu_stats->syncp, seq)); + + total.packets += packets; + total.bytes += bytes; + } + + if (nla_put_be64(skb, NFTA_COUNTER_BYTES, cpu_to_be64(total.bytes)) || + nla_put_be64(skb, NFTA_COUNTER_PACKETS, cpu_to_be64(total.packets))) goto nla_put_failure; return 0; @@ -67,23 +87,44 @@ static int nft_counter_init(const struct nft_ctx *ctx, const struct nft_expr *expr, const struct nlattr * const tb[]) { - struct nft_counter *priv = nft_expr_priv(expr); + struct nft_counter_percpu_priv *priv = nft_expr_priv(expr); + struct nft_counter_percpu __percpu *cpu_stats; + struct nft_counter_percpu *this_cpu; + + cpu_stats = netdev_alloc_pcpu_stats(struct nft_counter_percpu); + if (cpu_stats == NULL) + return ENOMEM; + + preempt_disable(); + this_cpu = this_cpu_ptr(cpu_stats); + if (tb[NFTA_COUNTER_PACKETS]) { + this_cpu->counter.packets = + be64_to_cpu(nla_get_be64(tb[NFTA_COUNTER_PACKETS])); + } + if (tb[NFTA_COUNTER_BYTES]) { + this_cpu->counter.bytes = + be64_to_cpu(nla_get_be64(tb[NFTA_COUNTER_BYTES])); + } + preempt_enable(); + priv->counter = cpu_stats; + return 0; +} - if (tb[NFTA_COUNTER_PACKETS]) - priv->packets = be64_to_cpu(nla_get_be64(tb[NFTA_COUNTER_PACKETS])); - if (tb[NFTA_COUNTER_BYTES]) - priv->bytes = be64_to_cpu(nla_get_be64(tb[NFTA_COUNTER_BYTES])); +static void nft_counter_destroy(const struct nft_ctx *ctx, + const struct nft_expr *expr) +{ + struct nft_counter_percpu_priv *priv = nft_expr_priv(expr); - seqlock_init(&priv->lock); - return 0; + free_percpu(priv->counter); } static struct nft_expr_type nft_counter_type; static const struct nft_expr_ops nft_counter_ops = { .type = &nft_counter_type, - .size = NFT_EXPR_SIZE(sizeof(struct nft_counter)), + .size = NFT_EXPR_SIZE(sizeof(struct nft_counter_percpu_priv)), .eval = nft_counter_eval, .init = nft_counter_init, + .destroy = nft_counter_destroy, .dump = nft_counter_dump, }; diff --git a/net/netfilter/nft_limit.c b/net/netfilter/nft_limit.c index 435c1ccd6c0e..5d67938f8b2f 100644 --- a/net/netfilter/nft_limit.c +++ b/net/netfilter/nft_limit.c @@ -20,63 +20,79 @@ static DEFINE_SPINLOCK(limit_lock); struct nft_limit { + u64 last; u64 tokens; + u64 tokens_max; u64 rate; - u64 unit; - unsigned long stamp; + u64 nsecs; + u32 burst; }; -static void nft_limit_eval(const struct nft_expr *expr, - struct nft_regs *regs, - const struct nft_pktinfo *pkt) +static inline bool nft_limit_eval(struct nft_limit *limit, u64 cost) { - struct nft_limit *priv = nft_expr_priv(expr); + u64 now, tokens; + s64 delta; spin_lock_bh(&limit_lock); - if (time_after_eq(jiffies, priv->stamp)) { - priv->tokens = priv->rate; - priv->stamp = jiffies + priv->unit * HZ; - } - - if (priv->tokens >= 1) { - priv->tokens--; + now = ktime_get_ns(); + tokens = limit->tokens + now - limit->last; + if (tokens > limit->tokens_max) + tokens = limit->tokens_max; + + limit->last = now; + delta = tokens - cost; + if (delta >= 0) { + limit->tokens = delta; spin_unlock_bh(&limit_lock); - return; + return false; } + limit->tokens = tokens; spin_unlock_bh(&limit_lock); - - regs->verdict.code = NFT_BREAK; + return true; } -static const struct nla_policy nft_limit_policy[NFTA_LIMIT_MAX + 1] = { - [NFTA_LIMIT_RATE] = { .type = NLA_U64 }, - [NFTA_LIMIT_UNIT] = { .type = NLA_U64 }, -}; - -static int nft_limit_init(const struct nft_ctx *ctx, - const struct nft_expr *expr, +static int nft_limit_init(struct nft_limit *limit, const struct nlattr * const tb[]) { - struct nft_limit *priv = nft_expr_priv(expr); + u64 unit; if (tb[NFTA_LIMIT_RATE] == NULL || tb[NFTA_LIMIT_UNIT] == NULL) return -EINVAL; - priv->rate = be64_to_cpu(nla_get_be64(tb[NFTA_LIMIT_RATE])); - priv->unit = be64_to_cpu(nla_get_be64(tb[NFTA_LIMIT_UNIT])); - priv->stamp = jiffies + priv->unit * HZ; - priv->tokens = priv->rate; + limit->rate = be64_to_cpu(nla_get_be64(tb[NFTA_LIMIT_RATE])); + unit = be64_to_cpu(nla_get_be64(tb[NFTA_LIMIT_UNIT])); + limit->nsecs = unit * NSEC_PER_SEC; + if (limit->rate == 0 || limit->nsecs < unit) + return -EOVERFLOW; + limit->tokens = limit->tokens_max = limit->nsecs; + + if (tb[NFTA_LIMIT_BURST]) { + u64 rate; + + limit->burst = ntohl(nla_get_be32(tb[NFTA_LIMIT_BURST])); + + rate = limit->rate + limit->burst; + if (rate < limit->rate) + return -EOVERFLOW; + + limit->rate = rate; + } + limit->last = ktime_get_ns(); + return 0; } -static int nft_limit_dump(struct sk_buff *skb, const struct nft_expr *expr) +static int nft_limit_dump(struct sk_buff *skb, const struct nft_limit *limit, + enum nft_limit_type type) { - const struct nft_limit *priv = nft_expr_priv(expr); + u64 secs = div_u64(limit->nsecs, NSEC_PER_SEC); + u64 rate = limit->rate - limit->burst; - if (nla_put_be64(skb, NFTA_LIMIT_RATE, cpu_to_be64(priv->rate))) - goto nla_put_failure; - if (nla_put_be64(skb, NFTA_LIMIT_UNIT, cpu_to_be64(priv->unit))) + if (nla_put_be64(skb, NFTA_LIMIT_RATE, cpu_to_be64(rate)) || + nla_put_be64(skb, NFTA_LIMIT_UNIT, cpu_to_be64(secs)) || + nla_put_be32(skb, NFTA_LIMIT_BURST, htonl(limit->burst)) || + nla_put_be32(skb, NFTA_LIMIT_TYPE, htonl(type))) goto nla_put_failure; return 0; @@ -84,18 +100,114 @@ nla_put_failure: return -1; } +struct nft_limit_pkts { + struct nft_limit limit; + u64 cost; +}; + +static void nft_limit_pkts_eval(const struct nft_expr *expr, + struct nft_regs *regs, + const struct nft_pktinfo *pkt) +{ + struct nft_limit_pkts *priv = nft_expr_priv(expr); + + if (nft_limit_eval(&priv->limit, priv->cost)) + regs->verdict.code = NFT_BREAK; +} + +static const struct nla_policy nft_limit_policy[NFTA_LIMIT_MAX + 1] = { + [NFTA_LIMIT_RATE] = { .type = NLA_U64 }, + [NFTA_LIMIT_UNIT] = { .type = NLA_U64 }, + [NFTA_LIMIT_BURST] = { .type = NLA_U32 }, + [NFTA_LIMIT_TYPE] = { .type = NLA_U32 }, +}; + +static int nft_limit_pkts_init(const struct nft_ctx *ctx, + const struct nft_expr *expr, + const struct nlattr * const tb[]) +{ + struct nft_limit_pkts *priv = nft_expr_priv(expr); + int err; + + err = nft_limit_init(&priv->limit, tb); + if (err < 0) + return err; + + priv->cost = div_u64(priv->limit.nsecs, priv->limit.rate); + return 0; +} + +static int nft_limit_pkts_dump(struct sk_buff *skb, const struct nft_expr *expr) +{ + const struct nft_limit_pkts *priv = nft_expr_priv(expr); + + return nft_limit_dump(skb, &priv->limit, NFT_LIMIT_PKTS); +} + static struct nft_expr_type nft_limit_type; -static const struct nft_expr_ops nft_limit_ops = { +static const struct nft_expr_ops nft_limit_pkts_ops = { + .type = &nft_limit_type, + .size = NFT_EXPR_SIZE(sizeof(struct nft_limit_pkts)), + .eval = nft_limit_pkts_eval, + .init = nft_limit_pkts_init, + .dump = nft_limit_pkts_dump, +}; + +static void nft_limit_pkt_bytes_eval(const struct nft_expr *expr, + struct nft_regs *regs, + const struct nft_pktinfo *pkt) +{ + struct nft_limit *priv = nft_expr_priv(expr); + u64 cost = div_u64(priv->nsecs * pkt->skb->len, priv->rate); + + if (nft_limit_eval(priv, cost)) + regs->verdict.code = NFT_BREAK; +} + +static int nft_limit_pkt_bytes_init(const struct nft_ctx *ctx, + const struct nft_expr *expr, + const struct nlattr * const tb[]) +{ + struct nft_limit *priv = nft_expr_priv(expr); + + return nft_limit_init(priv, tb); +} + +static int nft_limit_pkt_bytes_dump(struct sk_buff *skb, + const struct nft_expr *expr) +{ + const struct nft_limit *priv = nft_expr_priv(expr); + + return nft_limit_dump(skb, priv, NFT_LIMIT_PKT_BYTES); +} + +static const struct nft_expr_ops nft_limit_pkt_bytes_ops = { .type = &nft_limit_type, .size = NFT_EXPR_SIZE(sizeof(struct nft_limit)), - .eval = nft_limit_eval, - .init = nft_limit_init, - .dump = nft_limit_dump, + .eval = nft_limit_pkt_bytes_eval, + .init = nft_limit_pkt_bytes_init, + .dump = nft_limit_pkt_bytes_dump, }; +static const struct nft_expr_ops * +nft_limit_select_ops(const struct nft_ctx *ctx, + const struct nlattr * const tb[]) +{ + if (tb[NFTA_LIMIT_TYPE] == NULL) + return &nft_limit_pkts_ops; + + switch (ntohl(nla_get_be32(tb[NFTA_LIMIT_TYPE]))) { + case NFT_LIMIT_PKTS: + return &nft_limit_pkts_ops; + case NFT_LIMIT_PKT_BYTES: + return &nft_limit_pkt_bytes_ops; + } + return ERR_PTR(-EOPNOTSUPP); +} + static struct nft_expr_type nft_limit_type __read_mostly = { .name = "limit", - .ops = &nft_limit_ops, + .select_ops = nft_limit_select_ops, .policy = nft_limit_policy, .maxattr = NFTA_LIMIT_MAX, .flags = NFT_EXPR_STATEFUL, diff --git a/net/netfilter/nft_meta.c b/net/netfilter/nft_meta.c index 52561e1c31e2..cb2f13ebb5a6 100644 --- a/net/netfilter/nft_meta.c +++ b/net/netfilter/nft_meta.c @@ -166,11 +166,13 @@ void nft_meta_get_eval(const struct nft_expr *expr, goto err; *dest = out->group; break; +#ifdef CONFIG_CGROUP_NET_CLASSID case NFT_META_CGROUP: if (skb->sk == NULL || !sk_fullsock(skb->sk)) goto err; *dest = skb->sk->sk_classid; break; +#endif default: WARN_ON(1); goto err; @@ -246,7 +248,9 @@ int nft_meta_get_init(const struct nft_ctx *ctx, case NFT_META_CPU: case NFT_META_IIFGROUP: case NFT_META_OIFGROUP: +#ifdef CONFIG_CGROUP_NET_CLASSID case NFT_META_CGROUP: +#endif len = sizeof(u32); break; case NFT_META_IIFNAME: diff --git a/net/netfilter/nft_payload.c b/net/netfilter/nft_payload.c index 94fb3b27a2c5..09b4b07eb676 100644 --- a/net/netfilter/nft_payload.c +++ b/net/netfilter/nft_payload.c @@ -9,6 +9,7 @@ */ #include <linux/kernel.h> +#include <linux/if_vlan.h> #include <linux/init.h> #include <linux/module.h> #include <linux/netlink.h> @@ -17,6 +18,53 @@ #include <net/netfilter/nf_tables_core.h> #include <net/netfilter/nf_tables.h> +/* add vlan header into the user buffer for if tag was removed by offloads */ +static bool +nft_payload_copy_vlan(u32 *d, const struct sk_buff *skb, u8 offset, u8 len) +{ + int mac_off = skb_mac_header(skb) - skb->data; + u8 vlan_len, *vlanh, *dst_u8 = (u8 *) d; + struct vlan_ethhdr veth; + + vlanh = (u8 *) &veth; + if (offset < ETH_HLEN) { + u8 ethlen = min_t(u8, len, ETH_HLEN - offset); + + if (skb_copy_bits(skb, mac_off, &veth, ETH_HLEN)) + return false; + + veth.h_vlan_proto = skb->vlan_proto; + + memcpy(dst_u8, vlanh + offset, ethlen); + + len -= ethlen; + if (len == 0) + return true; + + dst_u8 += ethlen; + offset = ETH_HLEN; + } else if (offset >= VLAN_ETH_HLEN) { + offset -= VLAN_HLEN; + goto skip; + } + + veth.h_vlan_TCI = htons(skb_vlan_tag_get(skb)); + veth.h_vlan_encapsulated_proto = skb->protocol; + + vlanh += offset; + + vlan_len = min_t(u8, len, VLAN_ETH_HLEN - offset); + memcpy(dst_u8, vlanh, vlan_len); + + len -= vlan_len; + if (!len) + return true; + + dst_u8 += vlan_len; + skip: + return skb_copy_bits(skb, offset + mac_off, dst_u8, len) == 0; +} + static void nft_payload_eval(const struct nft_expr *expr, struct nft_regs *regs, const struct nft_pktinfo *pkt) @@ -26,10 +74,18 @@ static void nft_payload_eval(const struct nft_expr *expr, u32 *dest = ®s->data[priv->dreg]; int offset; + dest[priv->len / NFT_REG32_SIZE] = 0; switch (priv->base) { case NFT_PAYLOAD_LL_HEADER: if (!skb_mac_header_was_set(skb)) goto err; + + if (skb_vlan_tag_present(skb)) { + if (!nft_payload_copy_vlan(dest, skb, + priv->offset, priv->len)) + goto err; + return; + } offset = skb_mac_header(skb) - skb->data; break; case NFT_PAYLOAD_NETWORK_HEADER: @@ -43,7 +99,6 @@ static void nft_payload_eval(const struct nft_expr *expr, } offset += priv->offset; - dest[priv->len / NFT_REG32_SIZE] = 0; if (skb_copy_bits(skb, offset, dest, priv->len) < 0) goto err; return; diff --git a/net/netfilter/x_tables.c b/net/netfilter/x_tables.c index d324fe71260c..9b42b5ea6dcd 100644 --- a/net/netfilter/x_tables.c +++ b/net/netfilter/x_tables.c @@ -67,9 +67,6 @@ static const char *const xt_prefix[NFPROTO_NUMPROTO] = { [NFPROTO_IPV6] = "ip6", }; -/* Allow this many total (re)entries. */ -static const unsigned int xt_jumpstack_multiplier = 2; - /* Registration hooks for targets. */ int xt_register_target(struct xt_target *target) { @@ -688,8 +685,6 @@ void xt_free_table_info(struct xt_table_info *info) kvfree(info->jumpstack); } - free_percpu(info->stackptr); - kvfree(info); } EXPORT_SYMBOL(xt_free_table_info); @@ -732,15 +727,14 @@ EXPORT_SYMBOL_GPL(xt_compat_unlock); DEFINE_PER_CPU(seqcount_t, xt_recseq); EXPORT_PER_CPU_SYMBOL_GPL(xt_recseq); +struct static_key xt_tee_enabled __read_mostly; +EXPORT_SYMBOL_GPL(xt_tee_enabled); + static int xt_jumpstack_alloc(struct xt_table_info *i) { unsigned int size; int cpu; - i->stackptr = alloc_percpu(unsigned int); - if (i->stackptr == NULL) - return -ENOMEM; - size = sizeof(void **) * nr_cpu_ids; if (size > PAGE_SIZE) i->jumpstack = vzalloc(size); @@ -749,8 +743,21 @@ static int xt_jumpstack_alloc(struct xt_table_info *i) if (i->jumpstack == NULL) return -ENOMEM; - i->stacksize *= xt_jumpstack_multiplier; - size = sizeof(void *) * i->stacksize; + /* ruleset without jumps -- no stack needed */ + if (i->stacksize == 0) + return 0; + + /* Jumpstack needs to be able to record two full callchains, one + * from the first rule set traversal, plus one table reentrancy + * via -j TEE without clobbering the callchain that brought us to + * TEE target. + * + * This is done by allocating two jumpstacks per cpu, on reentry + * the upper half of the stack is used. + * + * see the jumpstack setup in ipt_do_table() for more details. + */ + size = sizeof(void *) * i->stacksize * 2u; for_each_possible_cpu(cpu) { if (size > PAGE_SIZE) i->jumpstack[cpu] = vmalloc_node(size, diff --git a/net/netfilter/xt_CT.c b/net/netfilter/xt_CT.c index 43ddeee404e9..faf32d888198 100644 --- a/net/netfilter/xt_CT.c +++ b/net/netfilter/xt_CT.c @@ -181,9 +181,23 @@ out: #endif } +static u16 xt_ct_flags_to_dir(const struct xt_ct_target_info_v1 *info) +{ + switch (info->flags & (XT_CT_ZONE_DIR_ORIG | + XT_CT_ZONE_DIR_REPL)) { + case XT_CT_ZONE_DIR_ORIG: + return NF_CT_ZONE_DIR_ORIG; + case XT_CT_ZONE_DIR_REPL: + return NF_CT_ZONE_DIR_REPL; + default: + return NF_CT_DEFAULT_ZONE_DIR; + } +} + static int xt_ct_tg_check(const struct xt_tgchk_param *par, struct xt_ct_target_info_v1 *info) { + struct nf_conntrack_zone zone; struct nf_conn *ct; int ret = -EOPNOTSUPP; @@ -193,7 +207,9 @@ static int xt_ct_tg_check(const struct xt_tgchk_param *par, } #ifndef CONFIG_NF_CONNTRACK_ZONES - if (info->zone) + if (info->zone || info->flags & (XT_CT_ZONE_DIR_ORIG | + XT_CT_ZONE_DIR_REPL | + XT_CT_ZONE_MARK)) goto err1; #endif @@ -201,7 +217,13 @@ static int xt_ct_tg_check(const struct xt_tgchk_param *par, if (ret < 0) goto err1; - ct = nf_ct_tmpl_alloc(par->net, info->zone, GFP_KERNEL); + memset(&zone, 0, sizeof(zone)); + zone.id = info->zone; + zone.dir = xt_ct_flags_to_dir(info); + if (info->flags & XT_CT_ZONE_MARK) + zone.flags |= NF_CT_FLAG_MARK; + + ct = nf_ct_tmpl_alloc(par->net, &zone, GFP_KERNEL); if (!ct) { ret = -ENOMEM; goto err2; @@ -233,7 +255,7 @@ out: return 0; err3: - nf_conntrack_free(ct); + nf_ct_tmpl_free(ct); err2: nf_ct_l3proto_module_put(par->family); err1: diff --git a/net/netfilter/xt_TCPMSS.c b/net/netfilter/xt_TCPMSS.c index 8c3190e2fc6a..8c02501a530f 100644 --- a/net/netfilter/xt_TCPMSS.c +++ b/net/netfilter/xt_TCPMSS.c @@ -144,7 +144,7 @@ tcpmss_mangle_packet(struct sk_buff *skb, inet_proto_csum_replace2(&tcph->check, skb, htons(oldmss), htons(newmss), - 0); + false); return 0; } } @@ -185,18 +185,18 @@ tcpmss_mangle_packet(struct sk_buff *skb, memmove(opt + TCPOLEN_MSS, opt, len - sizeof(struct tcphdr)); inet_proto_csum_replace2(&tcph->check, skb, - htons(len), htons(len + TCPOLEN_MSS), 1); + htons(len), htons(len + TCPOLEN_MSS), true); opt[0] = TCPOPT_MSS; opt[1] = TCPOLEN_MSS; opt[2] = (newmss & 0xff00) >> 8; opt[3] = newmss & 0x00ff; - inet_proto_csum_replace4(&tcph->check, skb, 0, *((__be32 *)opt), 0); + inet_proto_csum_replace4(&tcph->check, skb, 0, *((__be32 *)opt), false); oldval = ((__be16 *)tcph)[6]; tcph->doff += TCPOLEN_MSS/4; inet_proto_csum_replace2(&tcph->check, skb, - oldval, ((__be16 *)tcph)[6], 0); + oldval, ((__be16 *)tcph)[6], false); return TCPOLEN_MSS; } diff --git a/net/netfilter/xt_TCPOPTSTRIP.c b/net/netfilter/xt_TCPOPTSTRIP.c index 625fa1d636a0..eb92bffff11c 100644 --- a/net/netfilter/xt_TCPOPTSTRIP.c +++ b/net/netfilter/xt_TCPOPTSTRIP.c @@ -80,7 +80,7 @@ tcpoptstrip_mangle_packet(struct sk_buff *skb, n <<= 8; } inet_proto_csum_replace2(&tcph->check, skb, htons(o), - htons(n), 0); + htons(n), false); } memset(opt + i, TCPOPT_NOP, optl); } diff --git a/net/netfilter/xt_TEE.c b/net/netfilter/xt_TEE.c index a747eb475b68..fd980aa7715d 100644 --- a/net/netfilter/xt_TEE.c +++ b/net/netfilter/xt_TEE.c @@ -10,26 +10,15 @@ * modify it under the terms of the GNU General Public License * version 2 or later, as published by the Free Software Foundation. */ -#include <linux/ip.h> #include <linux/module.h> -#include <linux/percpu.h> -#include <linux/route.h> #include <linux/skbuff.h> -#include <linux/notifier.h> -#include <net/checksum.h> -#include <net/icmp.h> -#include <net/ip.h> -#include <net/ipv6.h> -#include <net/ip6_route.h> -#include <net/route.h> +#include <linux/route.h> #include <linux/netfilter/x_tables.h> +#include <net/route.h> +#include <net/netfilter/ipv4/nf_dup_ipv4.h> +#include <net/netfilter/ipv6/nf_dup_ipv6.h> #include <linux/netfilter/xt_TEE.h> -#if IS_ENABLED(CONFIG_NF_CONNTRACK) -# define WITH_CONNTRACK 1 -# include <net/netfilter/nf_conntrack.h> -#endif - struct xt_tee_priv { struct notifier_block notifier; struct xt_tee_tginfo *tginfo; @@ -37,163 +26,25 @@ struct xt_tee_priv { }; static const union nf_inet_addr tee_zero_address; -static DEFINE_PER_CPU(bool, tee_active); - -static struct net *pick_net(struct sk_buff *skb) -{ -#ifdef CONFIG_NET_NS - const struct dst_entry *dst; - - if (skb->dev != NULL) - return dev_net(skb->dev); - dst = skb_dst(skb); - if (dst != NULL && dst->dev != NULL) - return dev_net(dst->dev); -#endif - return &init_net; -} - -static bool -tee_tg_route4(struct sk_buff *skb, const struct xt_tee_tginfo *info) -{ - const struct iphdr *iph = ip_hdr(skb); - struct net *net = pick_net(skb); - struct rtable *rt; - struct flowi4 fl4; - - memset(&fl4, 0, sizeof(fl4)); - if (info->priv) { - if (info->priv->oif == -1) - return false; - fl4.flowi4_oif = info->priv->oif; - } - fl4.daddr = info->gw.ip; - fl4.flowi4_tos = RT_TOS(iph->tos); - fl4.flowi4_scope = RT_SCOPE_UNIVERSE; - fl4.flowi4_flags = FLOWI_FLAG_KNOWN_NH; - rt = ip_route_output_key(net, &fl4); - if (IS_ERR(rt)) - return false; - - skb_dst_drop(skb); - skb_dst_set(skb, &rt->dst); - skb->dev = rt->dst.dev; - skb->protocol = htons(ETH_P_IP); - return true; -} static unsigned int tee_tg4(struct sk_buff *skb, const struct xt_action_param *par) { const struct xt_tee_tginfo *info = par->targinfo; - struct iphdr *iph; - if (__this_cpu_read(tee_active)) - return XT_CONTINUE; - /* - * Copy the skb, and route the copy. Will later return %XT_CONTINUE for - * the original skb, which should continue on its way as if nothing has - * happened. The copy should be independently delivered to the TEE - * --gateway. - */ - skb = pskb_copy(skb, GFP_ATOMIC); - if (skb == NULL) - return XT_CONTINUE; - -#ifdef WITH_CONNTRACK - /* Avoid counting cloned packets towards the original connection. */ - nf_conntrack_put(skb->nfct); - skb->nfct = &nf_ct_untracked_get()->ct_general; - skb->nfctinfo = IP_CT_NEW; - nf_conntrack_get(skb->nfct); -#endif - /* - * If we are in PREROUTING/INPUT, the checksum must be recalculated - * since the length could have changed as a result of defragmentation. - * - * We also decrease the TTL to mitigate potential TEE loops - * between two hosts. - * - * Set %IP_DF so that the original source is notified of a potentially - * decreased MTU on the clone route. IPv6 does this too. - */ - iph = ip_hdr(skb); - iph->frag_off |= htons(IP_DF); - if (par->hooknum == NF_INET_PRE_ROUTING || - par->hooknum == NF_INET_LOCAL_IN) - --iph->ttl; - ip_send_check(iph); + nf_dup_ipv4(skb, par->hooknum, &info->gw.in, info->priv->oif); - if (tee_tg_route4(skb, info)) { - __this_cpu_write(tee_active, true); - ip_local_out(skb); - __this_cpu_write(tee_active, false); - } else { - kfree_skb(skb); - } return XT_CONTINUE; } -#if IS_ENABLED(CONFIG_IPV6) -static bool -tee_tg_route6(struct sk_buff *skb, const struct xt_tee_tginfo *info) -{ - const struct ipv6hdr *iph = ipv6_hdr(skb); - struct net *net = pick_net(skb); - struct dst_entry *dst; - struct flowi6 fl6; - - memset(&fl6, 0, sizeof(fl6)); - if (info->priv) { - if (info->priv->oif == -1) - return false; - fl6.flowi6_oif = info->priv->oif; - } - fl6.daddr = info->gw.in6; - fl6.flowlabel = ((iph->flow_lbl[0] & 0xF) << 16) | - (iph->flow_lbl[1] << 8) | iph->flow_lbl[2]; - fl6.flowi6_flags = FLOWI_FLAG_KNOWN_NH; - dst = ip6_route_output(net, NULL, &fl6); - if (dst->error) { - dst_release(dst); - return false; - } - skb_dst_drop(skb); - skb_dst_set(skb, dst); - skb->dev = dst->dev; - skb->protocol = htons(ETH_P_IPV6); - return true; -} - +#if IS_ENABLED(CONFIG_NF_DUP_IPV6) static unsigned int tee_tg6(struct sk_buff *skb, const struct xt_action_param *par) { const struct xt_tee_tginfo *info = par->targinfo; - if (__this_cpu_read(tee_active)) - return XT_CONTINUE; - skb = pskb_copy(skb, GFP_ATOMIC); - if (skb == NULL) - return XT_CONTINUE; + nf_dup_ipv6(skb, par->hooknum, &info->gw.in6, info->priv->oif); -#ifdef WITH_CONNTRACK - nf_conntrack_put(skb->nfct); - skb->nfct = &nf_ct_untracked_get()->ct_general; - skb->nfctinfo = IP_CT_NEW; - nf_conntrack_get(skb->nfct); -#endif - if (par->hooknum == NF_INET_PRE_ROUTING || - par->hooknum == NF_INET_LOCAL_IN) { - struct ipv6hdr *iph = ipv6_hdr(skb); - --iph->hop_limit; - } - if (tee_tg_route6(skb, info)) { - __this_cpu_write(tee_active, true); - ip6_local_out(skb); - __this_cpu_write(tee_active, false); - } else { - kfree_skb(skb); - } return XT_CONTINUE; } #endif @@ -252,6 +103,7 @@ static int tee_tg_check(const struct xt_tgchk_param *par) } else info->priv = NULL; + static_key_slow_inc(&xt_tee_enabled); return 0; } @@ -263,6 +115,7 @@ static void tee_tg_destroy(const struct xt_tgdtor_param *par) unregister_netdevice_notifier(&info->priv->notifier); kfree(info->priv); } + static_key_slow_dec(&xt_tee_enabled); } static struct xt_target tee_tg_reg[] __read_mostly = { @@ -276,7 +129,7 @@ static struct xt_target tee_tg_reg[] __read_mostly = { .destroy = tee_tg_destroy, .me = THIS_MODULE, }, -#if IS_ENABLED(CONFIG_IPV6) +#if IS_ENABLED(CONFIG_NF_DUP_IPV6) { .name = "TEE", .revision = 1, diff --git a/net/netfilter/xt_TPROXY.c b/net/netfilter/xt_TPROXY.c index cca96cec1b68..d0c96c5ae29a 100644 --- a/net/netfilter/xt_TPROXY.c +++ b/net/netfilter/xt_TPROXY.c @@ -272,8 +272,7 @@ tproxy_handle_time_wait4(struct sk_buff *skb, __be32 laddr, __be16 lport, hp->source, lport ? lport : hp->dest, skb->dev, NFT_LOOKUP_LISTENER); if (sk2) { - inet_twsk_deschedule(inet_twsk(sk)); - inet_twsk_put(inet_twsk(sk)); + inet_twsk_deschedule_put(inet_twsk(sk)); sk = sk2; } } @@ -437,8 +436,7 @@ tproxy_handle_time_wait6(struct sk_buff *skb, int tproto, int thoff, tgi->lport ? tgi->lport : hp->dest, skb->dev, NFT_LOOKUP_LISTENER); if (sk2) { - inet_twsk_deschedule(inet_twsk(sk)); - inet_twsk_put(inet_twsk(sk)); + inet_twsk_deschedule_put(inet_twsk(sk)); sk = sk2; } } diff --git a/net/netfilter/xt_connlabel.c b/net/netfilter/xt_connlabel.c index 9f8719df2001..bb9cbeb18868 100644 --- a/net/netfilter/xt_connlabel.c +++ b/net/netfilter/xt_connlabel.c @@ -42,10 +42,6 @@ static int connlabel_mt_check(const struct xt_mtchk_param *par) XT_CONNLABEL_OP_SET; struct xt_connlabel_mtinfo *info = par->matchinfo; int ret; - size_t words; - - if (info->bit > XT_CONNLABEL_MAXBIT) - return -ERANGE; if (info->options & ~options) { pr_err("Unknown options in mask %x\n", info->options); @@ -59,19 +55,15 @@ static int connlabel_mt_check(const struct xt_mtchk_param *par) return ret; } - par->net->ct.labels_used++; - words = BITS_TO_LONGS(info->bit+1); - if (words > par->net->ct.label_words) - par->net->ct.label_words = words; - + ret = nf_connlabels_get(par->net, info->bit + 1); + if (ret < 0) + nf_ct_l3proto_module_put(par->family); return ret; } static void connlabel_mt_destroy(const struct xt_mtdtor_param *par) { - par->net->ct.labels_used--; - if (par->net->ct.labels_used == 0) - par->net->ct.label_words = 0; + nf_connlabels_put(par->net); nf_ct_l3proto_module_put(par->family); } diff --git a/net/netfilter/xt_connlimit.c b/net/netfilter/xt_connlimit.c index 29ba6218a820..075d89d94d28 100644 --- a/net/netfilter/xt_connlimit.c +++ b/net/netfilter/xt_connlimit.c @@ -134,7 +134,7 @@ static bool add_hlist(struct hlist_head *head, static unsigned int check_hlist(struct net *net, struct hlist_head *head, const struct nf_conntrack_tuple *tuple, - u16 zone, + const struct nf_conntrack_zone *zone, bool *addit) { const struct nf_conntrack_tuple_hash *found; @@ -201,7 +201,7 @@ static unsigned int count_tree(struct net *net, struct rb_root *root, const struct nf_conntrack_tuple *tuple, const union nf_inet_addr *addr, const union nf_inet_addr *mask, - u8 family, u16 zone) + u8 family, const struct nf_conntrack_zone *zone) { struct xt_connlimit_rb *gc_nodes[CONNLIMIT_GC_MAX_NODES]; struct rb_node **rbnode, *parent; @@ -290,7 +290,8 @@ static int count_them(struct net *net, const struct nf_conntrack_tuple *tuple, const union nf_inet_addr *addr, const union nf_inet_addr *mask, - u_int8_t family, u16 zone) + u_int8_t family, + const struct nf_conntrack_zone *zone) { struct rb_root *root; int count; @@ -321,10 +322,10 @@ connlimit_mt(const struct sk_buff *skb, struct xt_action_param *par) union nf_inet_addr addr; struct nf_conntrack_tuple tuple; const struct nf_conntrack_tuple *tuple_ptr = &tuple; + const struct nf_conntrack_zone *zone = &nf_ct_zone_dflt; enum ip_conntrack_info ctinfo; const struct nf_conn *ct; unsigned int connections; - u16 zone = NF_CT_DEFAULT_ZONE; ct = nf_ct_get(skb, &ctinfo); if (ct != NULL) { diff --git a/net/netfilter/xt_nfacct.c b/net/netfilter/xt_nfacct.c index 8c646ed9c921..3048a7e3a90a 100644 --- a/net/netfilter/xt_nfacct.c +++ b/net/netfilter/xt_nfacct.c @@ -37,7 +37,7 @@ nfacct_mt_checkentry(const struct xt_mtchk_param *par) struct xt_nfacct_match_info *info = par->matchinfo; struct nf_acct *nfacct; - nfacct = nfnl_acct_find_get(info->name); + nfacct = nfnl_acct_find_get(par->net, info->name); if (nfacct == NULL) { pr_info("xt_nfacct: accounting object with name `%s' " "does not exists\n", info->name); diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index a774985489e2..7f86d3b55060 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -84,6 +84,7 @@ struct listeners { #define NETLINK_F_BROADCAST_SEND_ERROR 0x4 #define NETLINK_F_RECV_NO_ENOBUFS 0x8 #define NETLINK_F_LISTEN_ALL_NSID 0x10 +#define NETLINK_F_CAP_ACK 0x20 static inline int netlink_is_kernel(struct sock *sk) { @@ -593,16 +594,6 @@ netlink_current_frame(const struct netlink_ring *ring, return netlink_lookup_frame(ring, ring->head, status); } -static struct nl_mmap_hdr * -netlink_previous_frame(const struct netlink_ring *ring, - enum nl_mmap_status status) -{ - unsigned int prev; - - prev = ring->head ? ring->head - 1 : ring->frame_max; - return netlink_lookup_frame(ring, prev, status); -} - static void netlink_increment_head(struct netlink_ring *ring) { ring->head = ring->head != ring->frame_max ? ring->head + 1 : 0; @@ -610,11 +601,11 @@ static void netlink_increment_head(struct netlink_ring *ring) static void netlink_forward_ring(struct netlink_ring *ring) { - unsigned int head = ring->head, pos = head; + unsigned int head = ring->head; const struct nl_mmap_hdr *hdr; do { - hdr = __netlink_lookup_frame(ring, pos); + hdr = __netlink_lookup_frame(ring, ring->head); if (hdr->nm_status == NL_MMAP_STATUS_UNUSED) break; if (hdr->nm_status != NL_MMAP_STATUS_SKIP) @@ -623,6 +614,21 @@ static void netlink_forward_ring(struct netlink_ring *ring) } while (ring->head != head); } +static bool netlink_has_valid_frame(struct netlink_ring *ring) +{ + unsigned int head = ring->head, pos = head; + const struct nl_mmap_hdr *hdr; + + do { + hdr = __netlink_lookup_frame(ring, pos); + if (hdr->nm_status == NL_MMAP_STATUS_VALID) + return true; + pos = pos != 0 ? pos - 1 : ring->frame_max; + } while (pos != head); + + return false; +} + static bool netlink_dump_space(struct netlink_sock *nlk) { struct netlink_ring *ring = &nlk->rx_ring; @@ -668,13 +674,19 @@ static unsigned int netlink_poll(struct file *file, struct socket *sock, mask = datagram_poll(file, sock, wait); - spin_lock_bh(&sk->sk_receive_queue.lock); - if (nlk->rx_ring.pg_vec) { - netlink_forward_ring(&nlk->rx_ring); - if (!netlink_previous_frame(&nlk->rx_ring, NL_MMAP_STATUS_UNUSED)) - mask |= POLLIN | POLLRDNORM; + /* We could already have received frames in the normal receive + * queue, that will show up as NL_MMAP_STATUS_COPY in the ring, + * so if mask contains pollin/etc already, there's no point + * walking the ring. + */ + if ((mask & (POLLIN | POLLRDNORM)) != (POLLIN | POLLRDNORM)) { + spin_lock_bh(&sk->sk_receive_queue.lock); + if (nlk->rx_ring.pg_vec) { + if (netlink_has_valid_frame(&nlk->rx_ring)) + mask |= POLLIN | POLLRDNORM; + } + spin_unlock_bh(&sk->sk_receive_queue.lock); } - spin_unlock_bh(&sk->sk_receive_queue.lock); spin_lock_bh(&sk->sk_write_queue.lock); if (nlk->tx_ring.pg_vec) { @@ -1832,15 +1844,16 @@ retry: } EXPORT_SYMBOL(netlink_unicast); -struct sk_buff *netlink_alloc_skb(struct sock *ssk, unsigned int size, - u32 dst_portid, gfp_t gfp_mask) +struct sk_buff *__netlink_alloc_skb(struct sock *ssk, unsigned int size, + unsigned int ldiff, u32 dst_portid, + gfp_t gfp_mask) { #ifdef CONFIG_NETLINK_MMAP + unsigned int maxlen, linear_size; struct sock *sk = NULL; struct sk_buff *skb; struct netlink_ring *ring; struct nl_mmap_hdr *hdr; - unsigned int maxlen; sk = netlink_getsockbyportid(ssk, dst_portid); if (IS_ERR(sk)) @@ -1851,7 +1864,11 @@ struct sk_buff *netlink_alloc_skb(struct sock *ssk, unsigned int size, if (ring->pg_vec == NULL) goto out_put; - if (ring->frame_size - NL_MMAP_HDRLEN < size) + /* We need to account the full linear size needed as a ring + * slot cannot have non-linear parts. + */ + linear_size = size + ldiff; + if (ring->frame_size - NL_MMAP_HDRLEN < linear_size) goto out_put; skb = alloc_skb_head(gfp_mask); @@ -1865,13 +1882,14 @@ struct sk_buff *netlink_alloc_skb(struct sock *ssk, unsigned int size, /* check again under lock */ maxlen = ring->frame_size - NL_MMAP_HDRLEN; - if (maxlen < size) + if (maxlen < linear_size) goto out_free; netlink_forward_ring(ring); hdr = netlink_current_frame(ring, NL_MMAP_STATUS_UNUSED); if (hdr == NULL) goto err2; + netlink_ring_setup_skb(skb, sk, ring, hdr); netlink_set_status(hdr, NL_MMAP_STATUS_RESERVED); atomic_inc(&ring->pending); @@ -1897,7 +1915,7 @@ out: #endif return alloc_skb(size, gfp_mask); } -EXPORT_SYMBOL_GPL(netlink_alloc_skb); +EXPORT_SYMBOL_GPL(__netlink_alloc_skb); int netlink_has_listeners(struct sock *sk, unsigned int group) { @@ -2258,6 +2276,13 @@ static int netlink_setsockopt(struct socket *sock, int level, int optname, nlk->flags &= ~NETLINK_F_LISTEN_ALL_NSID; err = 0; break; + case NETLINK_CAP_ACK: + if (val) + nlk->flags |= NETLINK_F_CAP_ACK; + else + nlk->flags &= ~NETLINK_F_CAP_ACK; + err = 0; + break; default: err = -ENOPROTOOPT; } @@ -2332,6 +2357,16 @@ static int netlink_getsockopt(struct socket *sock, int level, int optname, netlink_table_ungrab(); break; } + case NETLINK_CAP_ACK: + if (len < sizeof(int)) + return -EINVAL; + len = sizeof(int); + val = nlk->flags & NETLINK_F_CAP_ACK ? 1 : 0; + if (put_user(len, optlen) || + put_user(val, optval)) + return -EFAULT; + err = 0; + break; default: err = -ENOPROTOOPT; } @@ -2873,9 +2908,12 @@ void netlink_ack(struct sk_buff *in_skb, struct nlmsghdr *nlh, int err) struct nlmsghdr *rep; struct nlmsgerr *errmsg; size_t payload = sizeof(*errmsg); + struct netlink_sock *nlk = nlk_sk(NETLINK_CB(in_skb).sk); - /* error messages get the original request appened */ - if (err) + /* Error messages get the original request appened, unless the user + * requests to cap the error message. + */ + if (!(nlk->flags & NETLINK_F_CAP_ACK) && err) payload += nlmsg_len(nlh); skb = netlink_alloc_skb(in_skb->sk, nlmsg_total_size(payload), @@ -2898,7 +2936,7 @@ void netlink_ack(struct sk_buff *in_skb, struct nlmsghdr *nlh, int err) NLMSG_ERROR, payload, 0); errmsg = nlmsg_data(rep); errmsg->error = err; - memcpy(&errmsg->msg, nlh, err ? nlh->nlmsg_len : sizeof(*nlh)); + memcpy(&errmsg->msg, nlh, payload > sizeof(*errmsg) ? nlh->nlmsg_len : sizeof(*nlh)); netlink_unicast(in_skb->sk, skb, NETLINK_CB(in_skb).portid, MSG_DONTWAIT); } EXPORT_SYMBOL(netlink_ack); diff --git a/net/nfc/nci/core.c b/net/nfc/nci/core.c index 95af2d24d5be..943889b87a34 100644 --- a/net/nfc/nci/core.c +++ b/net/nfc/nci/core.c @@ -351,6 +351,20 @@ int nci_prop_cmd(struct nci_dev *ndev, __u8 oid, size_t len, __u8 *payload) } EXPORT_SYMBOL(nci_prop_cmd); +int nci_core_reset(struct nci_dev *ndev) +{ + return __nci_request(ndev, nci_reset_req, 0, + msecs_to_jiffies(NCI_RESET_TIMEOUT)); +} +EXPORT_SYMBOL(nci_core_reset); + +int nci_core_init(struct nci_dev *ndev) +{ + return __nci_request(ndev, nci_init_req, 0, + msecs_to_jiffies(NCI_INIT_TIMEOUT)); +} +EXPORT_SYMBOL(nci_core_init); + static int nci_open_device(struct nci_dev *ndev) { int rc = 0; @@ -388,6 +402,10 @@ static int nci_open_device(struct nci_dev *ndev) msecs_to_jiffies(NCI_INIT_TIMEOUT)); } + if (ndev->ops->post_setup) { + rc = ndev->ops->post_setup(ndev); + } + if (!rc) { rc = __nci_request(ndev, nci_init_complete_req, 0, msecs_to_jiffies(NCI_INIT_TIMEOUT)); diff --git a/net/nfc/nci/hci.c b/net/nfc/nci/hci.c index af002df640c7..609f92283d1b 100644 --- a/net/nfc/nci/hci.c +++ b/net/nfc/nci/hci.c @@ -233,7 +233,7 @@ int nci_hci_send_cmd(struct nci_dev *ndev, u8 gate, u8 cmd, r = nci_request(ndev, nci_hci_send_data_req, (unsigned long)&data, msecs_to_jiffies(NCI_DATA_TIMEOUT)); - if (r == NCI_STATUS_OK) + if (r == NCI_STATUS_OK && skb) *skb = conn_info->rx_skb; return r; diff --git a/net/nfc/netlink.c b/net/nfc/netlink.c index f85f37ed19b2..853172c27f68 100644 --- a/net/nfc/netlink.c +++ b/net/nfc/netlink.c @@ -63,6 +63,8 @@ static const struct nla_policy nfc_genl_policy[NFC_ATTR_MAX + 1] = { [NFC_ATTR_FIRMWARE_NAME] = { .type = NLA_STRING, .len = NFC_FIRMWARE_NAME_MAXSIZE }, [NFC_ATTR_SE_APDU] = { .type = NLA_BINARY }, + [NFC_ATTR_VENDOR_DATA] = { .type = NLA_BINARY }, + }; static const struct nla_policy nfc_sdp_genl_policy[NFC_SDP_ATTR_MAX + 1] = { @@ -1503,7 +1505,7 @@ static int nfc_genl_vendor_cmd(struct sk_buff *skb, u32 dev_idx, vid, subcmd; u8 *data; size_t data_len; - int i; + int i, err; if (!info->attrs[NFC_ATTR_DEVICE_INDEX] || !info->attrs[NFC_ATTR_VENDOR_ID] || @@ -1518,12 +1520,13 @@ static int nfc_genl_vendor_cmd(struct sk_buff *skb, if (!dev || !dev->vendor_cmds || !dev->n_vendor_cmds) return -ENODEV; - data = nla_data(info->attrs[NFC_ATTR_VENDOR_DATA]); - if (data) { + if (info->attrs[NFC_ATTR_VENDOR_DATA]) { + data = nla_data(info->attrs[NFC_ATTR_VENDOR_DATA]); data_len = nla_len(info->attrs[NFC_ATTR_VENDOR_DATA]); if (data_len == 0) return -EINVAL; } else { + data = NULL; data_len = 0; } @@ -1533,12 +1536,92 @@ static int nfc_genl_vendor_cmd(struct sk_buff *skb, if (cmd->vendor_id != vid || cmd->subcmd != subcmd) continue; - return cmd->doit(dev, data, data_len); + dev->cur_cmd_info = info; + err = cmd->doit(dev, data, data_len); + dev->cur_cmd_info = NULL; + return err; } return -EOPNOTSUPP; } +/* message building helper */ +static inline void *nfc_hdr_put(struct sk_buff *skb, u32 portid, u32 seq, + int flags, u8 cmd) +{ + /* since there is no private header just add the generic one */ + return genlmsg_put(skb, portid, seq, &nfc_genl_family, flags, cmd); +} + +static struct sk_buff * +__nfc_alloc_vendor_cmd_skb(struct nfc_dev *dev, int approxlen, + u32 portid, u32 seq, + enum nfc_attrs attr, + u32 oui, u32 subcmd, gfp_t gfp) +{ + struct sk_buff *skb; + void *hdr; + + skb = nlmsg_new(approxlen + 100, gfp); + if (!skb) + return NULL; + + hdr = nfc_hdr_put(skb, portid, seq, 0, NFC_CMD_VENDOR); + if (!hdr) { + kfree_skb(skb); + return NULL; + } + + if (nla_put_u32(skb, NFC_ATTR_DEVICE_INDEX, dev->idx)) + goto nla_put_failure; + if (nla_put_u32(skb, NFC_ATTR_VENDOR_ID, oui)) + goto nla_put_failure; + if (nla_put_u32(skb, NFC_ATTR_VENDOR_SUBCMD, subcmd)) + goto nla_put_failure; + + ((void **)skb->cb)[0] = dev; + ((void **)skb->cb)[1] = hdr; + + return skb; + +nla_put_failure: + kfree_skb(skb); + return NULL; +} + +struct sk_buff *__nfc_alloc_vendor_cmd_reply_skb(struct nfc_dev *dev, + enum nfc_attrs attr, + u32 oui, u32 subcmd, + int approxlen) +{ + if (WARN_ON(!dev->cur_cmd_info)) + return NULL; + + return __nfc_alloc_vendor_cmd_skb(dev, approxlen, + dev->cur_cmd_info->snd_portid, + dev->cur_cmd_info->snd_seq, attr, + oui, subcmd, GFP_KERNEL); +} +EXPORT_SYMBOL(__nfc_alloc_vendor_cmd_reply_skb); + +int nfc_vendor_cmd_reply(struct sk_buff *skb) +{ + struct nfc_dev *dev = ((void **)skb->cb)[0]; + void *hdr = ((void **)skb->cb)[1]; + + /* clear CB data for netlink core to own from now on */ + memset(skb->cb, 0, sizeof(skb->cb)); + + if (WARN_ON(!dev->cur_cmd_info)) { + kfree_skb(skb); + return -EINVAL; + } + + genlmsg_end(skb, hdr); + return genlmsg_reply(skb, dev->cur_cmd_info); +} +EXPORT_SYMBOL(nfc_vendor_cmd_reply); + static const struct genl_ops nfc_genl_ops[] = { { .cmd = NFC_CMD_GET_DEVICE, diff --git a/net/openvswitch/Kconfig b/net/openvswitch/Kconfig index 15840401a2ce..2a071f470d57 100644 --- a/net/openvswitch/Kconfig +++ b/net/openvswitch/Kconfig @@ -5,6 +5,7 @@ config OPENVSWITCH tristate "Open vSwitch" depends on INET + depends on (!NF_CONNTRACK || NF_CONNTRACK) select LIBCRC32C select MPLS select NET_MPLS_GSO @@ -34,7 +35,7 @@ config OPENVSWITCH config OPENVSWITCH_GRE tristate "Open vSwitch GRE tunneling support" depends on OPENVSWITCH - depends on NET_IPGRE_DEMUX + depends on NET_IPGRE default OPENVSWITCH ---help--- If you say Y here, then the Open vSwitch will be able create GRE @@ -59,7 +60,7 @@ config OPENVSWITCH_VXLAN config OPENVSWITCH_GENEVE tristate "Open vSwitch Geneve tunneling support" depends on OPENVSWITCH - depends on GENEVE_CORE + depends on GENEVE default OPENVSWITCH ---help--- If you say Y here, then the Open vSwitch will be able create geneve vport. diff --git a/net/openvswitch/Makefile b/net/openvswitch/Makefile index 91b9478413ef..60f809085b92 100644 --- a/net/openvswitch/Makefile +++ b/net/openvswitch/Makefile @@ -15,6 +15,10 @@ openvswitch-y := \ vport-internal_dev.o \ vport-netdev.o +ifneq ($(CONFIG_NF_CONNTRACK),) +openvswitch-y += conntrack.o +endif + +obj-$(CONFIG_OPENVSWITCH_VXLAN)+= vport-vxlan.o obj-$(CONFIG_OPENVSWITCH_GENEVE)+= vport-geneve.o -obj-$(CONFIG_OPENVSWITCH_VXLAN) += vport-vxlan.o obj-$(CONFIG_OPENVSWITCH_GRE) += vport-gre.o diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c index ee34f474ad14..315f5330b6e5 100644 --- a/net/openvswitch/actions.c +++ b/net/openvswitch/actions.c @@ -22,6 +22,7 @@ #include <linux/in.h> #include <linux/ip.h> #include <linux/openvswitch.h> +#include <linux/netfilter_ipv6.h> #include <linux/sctp.h> #include <linux/tcp.h> #include <linux/udp.h> @@ -29,8 +30,10 @@ #include <linux/if_arp.h> #include <linux/if_vlan.h> +#include <net/dst.h> #include <net/ip.h> #include <net/ipv6.h> +#include <net/ip6_fib.h> #include <net/checksum.h> #include <net/dsfield.h> #include <net/mpls.h> @@ -38,6 +41,7 @@ #include "datapath.h" #include "flow.h" +#include "conntrack.h" #include "vport.h" static int do_execute_actions(struct datapath *dp, struct sk_buff *skb, @@ -52,6 +56,20 @@ struct deferred_action { struct sw_flow_key pkt_key; }; +#define MAX_L2_LEN (VLAN_ETH_HLEN + 3 * MPLS_HLEN) +struct ovs_frag_data { + unsigned long dst; + struct vport *vport; + struct ovs_skb_cb cb; + __be16 inner_protocol; + __u16 vlan_tci; + __be16 vlan_proto; + unsigned int l2_len; + u8 l2_data[MAX_L2_LEN]; +}; + +static DEFINE_PER_CPU(struct ovs_frag_data, ovs_frag_data_storage); + #define DEFERRED_ACTION_FIFO_SIZE 10 struct action_fifo { int head; @@ -185,10 +203,6 @@ static int pop_mpls(struct sk_buff *skb, struct sw_flow_key *key, return 0; } -/* 'KEY' must not have any bits set outside of the 'MASK' */ -#define MASKED(OLD, KEY, MASK) ((KEY) | ((OLD) & ~(MASK))) -#define SET_MASKED(OLD, KEY, MASK) ((OLD) = MASKED(OLD, KEY, MASK)) - static int set_mpls(struct sk_buff *skb, struct sw_flow_key *flow_key, const __be32 *mpls_lse, const __be32 *mask) { @@ -201,7 +215,7 @@ static int set_mpls(struct sk_buff *skb, struct sw_flow_key *flow_key, return err; stack = (__be32 *)skb_mpls_header(skb); - lse = MASKED(*stack, *mpls_lse, *mask); + lse = OVS_MASKED(*stack, *mpls_lse, *mask); if (skb->ip_summed == CHECKSUM_COMPLETE) { __be32 diff[] = { ~(*stack), lse }; @@ -244,9 +258,9 @@ static void ether_addr_copy_masked(u8 *dst_, const u8 *src_, const u8 *mask_) const u16 *src = (const u16 *)src_; const u16 *mask = (const u16 *)mask_; - SET_MASKED(dst[0], src[0], mask[0]); - SET_MASKED(dst[1], src[1], mask[1]); - SET_MASKED(dst[2], src[2], mask[2]); + OVS_SET_MASKED(dst[0], src[0], mask[0]); + OVS_SET_MASKED(dst[1], src[1], mask[1]); + OVS_SET_MASKED(dst[2], src[2], mask[2]); } static int set_eth_addr(struct sk_buff *skb, struct sw_flow_key *flow_key, @@ -284,14 +298,14 @@ static void update_ip_l4_checksum(struct sk_buff *skb, struct iphdr *nh, if (nh->protocol == IPPROTO_TCP) { if (likely(transport_len >= sizeof(struct tcphdr))) inet_proto_csum_replace4(&tcp_hdr(skb)->check, skb, - addr, new_addr, 1); + addr, new_addr, true); } else if (nh->protocol == IPPROTO_UDP) { if (likely(transport_len >= sizeof(struct udphdr))) { struct udphdr *uh = udp_hdr(skb); if (uh->check || skb->ip_summed == CHECKSUM_PARTIAL) { inet_proto_csum_replace4(&uh->check, skb, - addr, new_addr, 1); + addr, new_addr, true); if (!uh->check) uh->check = CSUM_MANGLED_0; } @@ -316,14 +330,14 @@ static void update_ipv6_checksum(struct sk_buff *skb, u8 l4_proto, if (l4_proto == NEXTHDR_TCP) { if (likely(transport_len >= sizeof(struct tcphdr))) inet_proto_csum_replace16(&tcp_hdr(skb)->check, skb, - addr, new_addr, 1); + addr, new_addr, true); } else if (l4_proto == NEXTHDR_UDP) { if (likely(transport_len >= sizeof(struct udphdr))) { struct udphdr *uh = udp_hdr(skb); if (uh->check || skb->ip_summed == CHECKSUM_PARTIAL) { inet_proto_csum_replace16(&uh->check, skb, - addr, new_addr, 1); + addr, new_addr, true); if (!uh->check) uh->check = CSUM_MANGLED_0; } @@ -331,17 +345,17 @@ static void update_ipv6_checksum(struct sk_buff *skb, u8 l4_proto, } else if (l4_proto == NEXTHDR_ICMP) { if (likely(transport_len >= sizeof(struct icmp6hdr))) inet_proto_csum_replace16(&icmp6_hdr(skb)->icmp6_cksum, - skb, addr, new_addr, 1); + skb, addr, new_addr, true); } } static void mask_ipv6_addr(const __be32 old[4], const __be32 addr[4], const __be32 mask[4], __be32 masked[4]) { - masked[0] = MASKED(old[0], addr[0], mask[0]); - masked[1] = MASKED(old[1], addr[1], mask[1]); - masked[2] = MASKED(old[2], addr[2], mask[2]); - masked[3] = MASKED(old[3], addr[3], mask[3]); + masked[0] = OVS_MASKED(old[0], addr[0], mask[0]); + masked[1] = OVS_MASKED(old[1], addr[1], mask[1]); + masked[2] = OVS_MASKED(old[2], addr[2], mask[2]); + masked[3] = OVS_MASKED(old[3], addr[3], mask[3]); } static void set_ipv6_addr(struct sk_buff *skb, u8 l4_proto, @@ -358,15 +372,15 @@ static void set_ipv6_addr(struct sk_buff *skb, u8 l4_proto, static void set_ipv6_fl(struct ipv6hdr *nh, u32 fl, u32 mask) { /* Bits 21-24 are always unmasked, so this retains their values. */ - SET_MASKED(nh->flow_lbl[0], (u8)(fl >> 16), (u8)(mask >> 16)); - SET_MASKED(nh->flow_lbl[1], (u8)(fl >> 8), (u8)(mask >> 8)); - SET_MASKED(nh->flow_lbl[2], (u8)fl, (u8)mask); + OVS_SET_MASKED(nh->flow_lbl[0], (u8)(fl >> 16), (u8)(mask >> 16)); + OVS_SET_MASKED(nh->flow_lbl[1], (u8)(fl >> 8), (u8)(mask >> 8)); + OVS_SET_MASKED(nh->flow_lbl[2], (u8)fl, (u8)mask); } static void set_ip_ttl(struct sk_buff *skb, struct iphdr *nh, u8 new_ttl, u8 mask) { - new_ttl = MASKED(nh->ttl, new_ttl, mask); + new_ttl = OVS_MASKED(nh->ttl, new_ttl, mask); csum_replace2(&nh->check, htons(nh->ttl << 8), htons(new_ttl << 8)); nh->ttl = new_ttl; @@ -392,7 +406,7 @@ static int set_ipv4(struct sk_buff *skb, struct sw_flow_key *flow_key, * makes sense to check if the value actually changed. */ if (mask->ipv4_src) { - new_addr = MASKED(nh->saddr, key->ipv4_src, mask->ipv4_src); + new_addr = OVS_MASKED(nh->saddr, key->ipv4_src, mask->ipv4_src); if (unlikely(new_addr != nh->saddr)) { set_ip_addr(skb, nh, &nh->saddr, new_addr); @@ -400,7 +414,7 @@ static int set_ipv4(struct sk_buff *skb, struct sw_flow_key *flow_key, } } if (mask->ipv4_dst) { - new_addr = MASKED(nh->daddr, key->ipv4_dst, mask->ipv4_dst); + new_addr = OVS_MASKED(nh->daddr, key->ipv4_dst, mask->ipv4_dst); if (unlikely(new_addr != nh->daddr)) { set_ip_addr(skb, nh, &nh->daddr, new_addr); @@ -488,7 +502,8 @@ static int set_ipv6(struct sk_buff *skb, struct sw_flow_key *flow_key, *(__be32 *)nh & htonl(IPV6_FLOWINFO_FLOWLABEL); } if (mask->ipv6_hlimit) { - SET_MASKED(nh->hop_limit, key->ipv6_hlimit, mask->ipv6_hlimit); + OVS_SET_MASKED(nh->hop_limit, key->ipv6_hlimit, + mask->ipv6_hlimit); flow_key->ip.ttl = nh->hop_limit; } return 0; @@ -498,7 +513,7 @@ static int set_ipv6(struct sk_buff *skb, struct sw_flow_key *flow_key, static void set_tp_port(struct sk_buff *skb, __be16 *port, __be16 new_port, __sum16 *check) { - inet_proto_csum_replace2(check, skb, *port, new_port, 0); + inet_proto_csum_replace2(check, skb, *port, new_port, false); *port = new_port; } @@ -517,8 +532,8 @@ static int set_udp(struct sk_buff *skb, struct sw_flow_key *flow_key, uh = udp_hdr(skb); /* Either of the masks is non-zero, so do not bother checking them. */ - src = MASKED(uh->source, key->udp_src, mask->udp_src); - dst = MASKED(uh->dest, key->udp_dst, mask->udp_dst); + src = OVS_MASKED(uh->source, key->udp_src, mask->udp_src); + dst = OVS_MASKED(uh->dest, key->udp_dst, mask->udp_dst); if (uh->check && skb->ip_summed != CHECKSUM_PARTIAL) { if (likely(src != uh->source)) { @@ -558,12 +573,12 @@ static int set_tcp(struct sk_buff *skb, struct sw_flow_key *flow_key, return err; th = tcp_hdr(skb); - src = MASKED(th->source, key->tcp_src, mask->tcp_src); + src = OVS_MASKED(th->source, key->tcp_src, mask->tcp_src); if (likely(src != th->source)) { set_tp_port(skb, &th->source, src, &th->check); flow_key->tp.src = src; } - dst = MASKED(th->dest, key->tcp_dst, mask->tcp_dst); + dst = OVS_MASKED(th->dest, key->tcp_dst, mask->tcp_dst); if (likely(dst != th->dest)) { set_tp_port(skb, &th->dest, dst, &th->check); flow_key->tp.dst = dst; @@ -590,8 +605,8 @@ static int set_sctp(struct sk_buff *skb, struct sw_flow_key *flow_key, old_csum = sh->checksum; old_correct_csum = sctp_compute_cksum(skb, sctphoff); - sh->source = MASKED(sh->source, key->sctp_src, mask->sctp_src); - sh->dest = MASKED(sh->dest, key->sctp_dst, mask->sctp_dst); + sh->source = OVS_MASKED(sh->source, key->sctp_src, mask->sctp_src); + sh->dest = OVS_MASKED(sh->dest, key->sctp_dst, mask->sctp_dst); new_csum = sctp_compute_cksum(skb, sctphoff); @@ -605,27 +620,159 @@ static int set_sctp(struct sk_buff *skb, struct sw_flow_key *flow_key, return 0; } -static void do_output(struct datapath *dp, struct sk_buff *skb, int out_port) +static int ovs_vport_output(struct sock *sock, struct sk_buff *skb) +{ + struct ovs_frag_data *data = this_cpu_ptr(&ovs_frag_data_storage); + struct vport *vport = data->vport; + + if (skb_cow_head(skb, data->l2_len) < 0) { + kfree_skb(skb); + return -ENOMEM; + } + + __skb_dst_copy(skb, data->dst); + *OVS_CB(skb) = data->cb; + skb->inner_protocol = data->inner_protocol; + skb->vlan_tci = data->vlan_tci; + skb->vlan_proto = data->vlan_proto; + + /* Reconstruct the MAC header. */ + skb_push(skb, data->l2_len); + memcpy(skb->data, &data->l2_data, data->l2_len); + ovs_skb_postpush_rcsum(skb, skb->data, data->l2_len); + skb_reset_mac_header(skb); + + ovs_vport_send(vport, skb); + return 0; +} + +static unsigned int +ovs_dst_get_mtu(const struct dst_entry *dst) +{ + return dst->dev->mtu; +} + +static struct dst_ops ovs_dst_ops = { + .family = AF_UNSPEC, + .mtu = ovs_dst_get_mtu, +}; + +/* prepare_frag() is called once per (larger-than-MTU) frame; its inverse is + * ovs_vport_output(), which is called once per fragmented packet. + */ +static void prepare_frag(struct vport *vport, struct sk_buff *skb) +{ + unsigned int hlen = skb_network_offset(skb); + struct ovs_frag_data *data; + + data = this_cpu_ptr(&ovs_frag_data_storage); + data->dst = skb->_skb_refdst; + data->vport = vport; + data->cb = *OVS_CB(skb); + data->inner_protocol = skb->inner_protocol; + data->vlan_tci = skb->vlan_tci; + data->vlan_proto = skb->vlan_proto; + data->l2_len = hlen; + memcpy(&data->l2_data, skb->data, hlen); + + memset(IPCB(skb), 0, sizeof(struct inet_skb_parm)); + skb_pull(skb, hlen); +} + +static void ovs_fragment(struct vport *vport, struct sk_buff *skb, u16 mru, + __be16 ethertype) +{ + if (skb_network_offset(skb) > MAX_L2_LEN) { + OVS_NLERR(1, "L2 header too long to fragment"); + return; + } + + if (ethertype == htons(ETH_P_IP)) { + struct dst_entry ovs_dst; + unsigned long orig_dst; + + prepare_frag(vport, skb); + dst_init(&ovs_dst, &ovs_dst_ops, NULL, 1, + DST_OBSOLETE_NONE, DST_NOCOUNT); + ovs_dst.dev = vport->dev; + + orig_dst = skb->_skb_refdst; + skb_dst_set_noref(skb, &ovs_dst); + IPCB(skb)->frag_max_size = mru; + + ip_do_fragment(skb->sk, skb, ovs_vport_output); + refdst_drop(orig_dst); + } else if (ethertype == htons(ETH_P_IPV6)) { + const struct nf_ipv6_ops *v6ops = nf_get_ipv6_ops(); + unsigned long orig_dst; + struct rt6_info ovs_rt; + + if (!v6ops) { + kfree_skb(skb); + return; + } + + prepare_frag(vport, skb); + memset(&ovs_rt, 0, sizeof(ovs_rt)); + dst_init(&ovs_rt.dst, &ovs_dst_ops, NULL, 1, + DST_OBSOLETE_NONE, DST_NOCOUNT); + ovs_rt.dst.dev = vport->dev; + + orig_dst = skb->_skb_refdst; + skb_dst_set_noref(skb, &ovs_rt.dst); + IP6CB(skb)->frag_max_size = mru; + + v6ops->fragment(skb->sk, skb, ovs_vport_output); + refdst_drop(orig_dst); + } else { + WARN_ONCE(1, "Failed fragment ->%s: eth=%04x, MRU=%d, MTU=%d.", + ovs_vport_name(vport), ntohs(ethertype), mru, + vport->dev->mtu); + kfree_skb(skb); + } +} + +static void do_output(struct datapath *dp, struct sk_buff *skb, int out_port, + struct sw_flow_key *key) { struct vport *vport = ovs_vport_rcu(dp, out_port); - if (likely(vport)) - ovs_vport_send(vport, skb); - else + if (likely(vport)) { + u16 mru = OVS_CB(skb)->mru; + + if (likely(!mru || (skb->len <= mru + ETH_HLEN))) { + ovs_vport_send(vport, skb); + } else if (mru <= vport->dev->mtu) { + __be16 ethertype = key->eth.type; + + if (!is_flow_key_valid(key)) { + if (eth_p_mpls(skb->protocol)) + ethertype = skb->inner_protocol; + else + ethertype = vlan_get_protocol(skb); + } + + ovs_fragment(vport, skb, mru, ethertype); + } else { + kfree_skb(skb); + } + } else { kfree_skb(skb); + } } static int output_userspace(struct datapath *dp, struct sk_buff *skb, struct sw_flow_key *key, const struct nlattr *attr, const struct nlattr *actions, int actions_len) { - struct ovs_tunnel_info info; + struct ip_tunnel_info info; struct dp_upcall_info upcall; const struct nlattr *a; int rem; memset(&upcall, 0, sizeof(upcall)); upcall.cmd = OVS_PACKET_CMD_ACTION; + upcall.mru = OVS_CB(skb)->mru; for (a = nla_data(attr), rem = nla_len(attr); rem > 0; a = nla_next(a, &rem)) { @@ -646,11 +793,13 @@ static int output_userspace(struct datapath *dp, struct sk_buff *skb, if (vport) { int err; + upcall.egress_tun_info = &info; err = ovs_vport_get_egress_tun_info(vport, skb, - &info); - if (!err) - upcall.egress_tun_info = &info; + &upcall); + if (err) + upcall.egress_tun_info = NULL; } + break; } @@ -677,9 +826,12 @@ static int sample(struct datapath *dp, struct sk_buff *skb, for (a = nla_data(attr), rem = nla_len(attr); rem > 0; a = nla_next(a, &rem)) { + u32 probability; + switch (nla_type(a)) { case OVS_SAMPLE_ATTR_PROBABILITY: - if (prandom_u32() >= nla_get_u32(a)) + probability = nla_get_u32(a); + if (!probability || prandom_u32() > probability) return 0; break; @@ -741,7 +893,11 @@ static int execute_set_action(struct sk_buff *skb, { /* Only tunnel set execution is supported without a mask. */ if (nla_type(a) == OVS_KEY_ATTR_TUNNEL_INFO) { - OVS_CB(skb)->egress_tun_info = nla_data(a); + struct ovs_tunnel_info *tun = nla_data(a); + + skb_dst_drop(skb); + dst_hold((struct dst_entry *)tun->tun_dst); + skb_dst_set(skb, (struct dst_entry *)tun->tun_dst); return 0; } @@ -759,12 +915,13 @@ static int execute_masked_set_action(struct sk_buff *skb, switch (nla_type(a)) { case OVS_KEY_ATTR_PRIORITY: - SET_MASKED(skb->priority, nla_get_u32(a), *get_mask(a, u32 *)); + OVS_SET_MASKED(skb->priority, nla_get_u32(a), + *get_mask(a, u32 *)); flow_key->phy.priority = skb->priority; break; case OVS_KEY_ATTR_SKB_MARK: - SET_MASKED(skb->mark, nla_get_u32(a), *get_mask(a, u32 *)); + OVS_SET_MASKED(skb->mark, nla_get_u32(a), *get_mask(a, u32 *)); flow_key->phy.skb_mark = skb->mark; break; @@ -807,6 +964,13 @@ static int execute_masked_set_action(struct sk_buff *skb, err = set_mpls(skb, flow_key, nla_data(a), get_mask(a, __be32 *)); break; + + case OVS_KEY_ATTR_CT_STATE: + case OVS_KEY_ATTR_CT_ZONE: + case OVS_KEY_ATTR_CT_MARK: + case OVS_KEY_ATTR_CT_LABEL: + err = -EINVAL; + break; } return err; @@ -876,7 +1040,7 @@ static int do_execute_actions(struct datapath *dp, struct sk_buff *skb, struct sk_buff *out_skb = skb_clone(skb, GFP_ATOMIC); if (out_skb) - do_output(dp, out_skb, prev_port); + do_output(dp, out_skb, prev_port, key); prev_port = -1; } @@ -933,6 +1097,15 @@ static int do_execute_actions(struct datapath *dp, struct sk_buff *skb, case OVS_ACTION_ATTR_SAMPLE: err = sample(dp, skb, key, a, attr, len); break; + + case OVS_ACTION_ATTR_CT: + err = ovs_ct_execute(ovs_dp_get_net(dp), skb, key, + nla_data(a)); + + /* Hide stolen IP fragments from user space. */ + if (err == -EINPROGRESS) + return 0; + break; } if (unlikely(err)) { @@ -942,7 +1115,7 @@ static int do_execute_actions(struct datapath *dp, struct sk_buff *skb, } if (prev_port != -1) - do_output(dp, skb, prev_port); + do_output(dp, skb, prev_port, key); else consume_skb(skb); @@ -984,7 +1157,6 @@ int ovs_execute_actions(struct datapath *dp, struct sk_buff *skb, int err; this_cpu_inc(exec_actions_level); - OVS_CB(skb)->egress_tun_info = NULL; err = do_execute_actions(dp, skb, key, acts->actions, acts->actions_len); diff --git a/net/openvswitch/conntrack.c b/net/openvswitch/conntrack.c new file mode 100644 index 000000000000..e8e524ad8a01 --- /dev/null +++ b/net/openvswitch/conntrack.c @@ -0,0 +1,755 @@ +/* + * Copyright (c) 2015 Nicira, Inc. + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of version 2 of the GNU General Public + * License as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, but + * WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * General Public License for more details. + */ + +#include <linux/module.h> +#include <linux/openvswitch.h> +#include <net/ip.h> +#include <net/netfilter/nf_conntrack_core.h> +#include <net/netfilter/nf_conntrack_helper.h> +#include <net/netfilter/nf_conntrack_labels.h> +#include <net/netfilter/nf_conntrack_zones.h> +#include <net/netfilter/ipv6/nf_defrag_ipv6.h> + +#include "datapath.h" +#include "conntrack.h" +#include "flow.h" +#include "flow_netlink.h" + +struct ovs_ct_len_tbl { + size_t maxlen; + size_t minlen; +}; + +/* Metadata mark for masked write to conntrack mark */ +struct md_mark { + u32 value; + u32 mask; +}; + +/* Metadata label for masked write to conntrack label. */ +struct md_label { + struct ovs_key_ct_label value; + struct ovs_key_ct_label mask; +}; + +/* Conntrack action context for execution. */ +struct ovs_conntrack_info { + struct nf_conntrack_helper *helper; + struct nf_conntrack_zone zone; + struct nf_conn *ct; + u32 flags; + u16 family; + struct md_mark mark; + struct md_label label; +}; + +static u16 key_to_nfproto(const struct sw_flow_key *key) +{ + switch (ntohs(key->eth.type)) { + case ETH_P_IP: + return NFPROTO_IPV4; + case ETH_P_IPV6: + return NFPROTO_IPV6; + default: + return NFPROTO_UNSPEC; + } +} + +/* Map SKB connection state into the values used by flow definition. */ +static u8 ovs_ct_get_state(enum ip_conntrack_info ctinfo) +{ + u8 ct_state = OVS_CS_F_TRACKED; + + switch (ctinfo) { + case IP_CT_ESTABLISHED_REPLY: + case IP_CT_RELATED_REPLY: + case IP_CT_NEW_REPLY: + ct_state |= OVS_CS_F_REPLY_DIR; + break; + default: + break; + } + + switch (ctinfo) { + case IP_CT_ESTABLISHED: + case IP_CT_ESTABLISHED_REPLY: + ct_state |= OVS_CS_F_ESTABLISHED; + break; + case IP_CT_RELATED: + case IP_CT_RELATED_REPLY: + ct_state |= OVS_CS_F_RELATED; + break; + case IP_CT_NEW: + case IP_CT_NEW_REPLY: + ct_state |= OVS_CS_F_NEW; + break; + default: + break; + } + + return ct_state; +} + +static u32 ovs_ct_get_mark(const struct nf_conn *ct) +{ +#if IS_ENABLED(CONFIG_NF_CONNTRACK_MARK) + return ct ? ct->mark : 0; +#else + return 0; +#endif +} + +static void ovs_ct_get_label(const struct nf_conn *ct, + struct ovs_key_ct_label *label) +{ + struct nf_conn_labels *cl = ct ? nf_ct_labels_find(ct) : NULL; + + if (cl) { + size_t len = cl->words * sizeof(long); + + if (len > OVS_CT_LABEL_LEN) + len = OVS_CT_LABEL_LEN; + else if (len < OVS_CT_LABEL_LEN) + memset(label, 0, OVS_CT_LABEL_LEN); + memcpy(label, cl->bits, len); + } else { + memset(label, 0, OVS_CT_LABEL_LEN); + } +} + +static void __ovs_ct_update_key(struct sw_flow_key *key, u8 state, + const struct nf_conntrack_zone *zone, + const struct nf_conn *ct) +{ + key->ct.state = state; + key->ct.zone = zone->id; + key->ct.mark = ovs_ct_get_mark(ct); + ovs_ct_get_label(ct, &key->ct.label); +} + +/* Update 'key' based on skb->nfct. If 'post_ct' is true, then OVS has + * previously sent the packet to conntrack via the ct action. + */ +static void ovs_ct_update_key(const struct sk_buff *skb, + struct sw_flow_key *key, bool post_ct) +{ + const struct nf_conntrack_zone *zone = &nf_ct_zone_dflt; + enum ip_conntrack_info ctinfo; + struct nf_conn *ct; + u8 state = 0; + + ct = nf_ct_get(skb, &ctinfo); + if (ct) { + state = ovs_ct_get_state(ctinfo); + if (ct->master) + state |= OVS_CS_F_RELATED; + zone = nf_ct_zone(ct); + } else if (post_ct) { + state = OVS_CS_F_TRACKED | OVS_CS_F_INVALID; + } + __ovs_ct_update_key(key, state, zone, ct); +} + +void ovs_ct_fill_key(const struct sk_buff *skb, struct sw_flow_key *key) +{ + ovs_ct_update_key(skb, key, false); +} + +int ovs_ct_put_key(const struct sw_flow_key *key, struct sk_buff *skb) +{ + if (nla_put_u8(skb, OVS_KEY_ATTR_CT_STATE, key->ct.state)) + return -EMSGSIZE; + + if (IS_ENABLED(CONFIG_NF_CONNTRACK_ZONES) && + nla_put_u16(skb, OVS_KEY_ATTR_CT_ZONE, key->ct.zone)) + return -EMSGSIZE; + + if (IS_ENABLED(CONFIG_NF_CONNTRACK_MARK) && + nla_put_u32(skb, OVS_KEY_ATTR_CT_MARK, key->ct.mark)) + return -EMSGSIZE; + + if (IS_ENABLED(CONFIG_NF_CONNTRACK_LABELS) && + nla_put(skb, OVS_KEY_ATTR_CT_LABEL, sizeof(key->ct.label), + &key->ct.label)) + return -EMSGSIZE; + + return 0; +} + +static int ovs_ct_set_mark(struct sk_buff *skb, struct sw_flow_key *key, + u32 ct_mark, u32 mask) +{ +#if IS_ENABLED(CONFIG_NF_CONNTRACK_MARK) + enum ip_conntrack_info ctinfo; + struct nf_conn *ct; + u32 new_mark; + + + /* The connection could be invalid, in which case set_mark is no-op. */ + ct = nf_ct_get(skb, &ctinfo); + if (!ct) + return 0; + + new_mark = ct_mark | (ct->mark & ~(mask)); + if (ct->mark != new_mark) { + ct->mark = new_mark; + nf_conntrack_event_cache(IPCT_MARK, ct); + key->ct.mark = new_mark; + } + + return 0; +#else + return -ENOTSUPP; +#endif +} + +static int ovs_ct_set_label(struct sk_buff *skb, struct sw_flow_key *key, + const struct ovs_key_ct_label *label, + const struct ovs_key_ct_label *mask) +{ + enum ip_conntrack_info ctinfo; + struct nf_conn_labels *cl; + struct nf_conn *ct; + int err; + + if (!IS_ENABLED(CONFIG_NF_CONNTRACK_LABELS)) + return -ENOTSUPP; + + /* The connection could be invalid, in which case set_label is no-op.*/ + ct = nf_ct_get(skb, &ctinfo); + if (!ct) + return 0; + + cl = nf_ct_labels_find(ct); + if (!cl) { + nf_ct_labels_ext_add(ct); + cl = nf_ct_labels_find(ct); + } + if (!cl || cl->words * sizeof(long) < OVS_CT_LABEL_LEN) + return -ENOSPC; + + err = nf_connlabels_replace(ct, (u32 *)label, (u32 *)mask, + OVS_CT_LABEL_LEN / sizeof(u32)); + if (err) + return err; + + ovs_ct_get_label(ct, &key->ct.label); + return 0; +} + +/* 'skb' should already be pulled to nh_ofs. */ +static int ovs_ct_helper(struct sk_buff *skb, u16 proto) +{ + const struct nf_conntrack_helper *helper; + const struct nf_conn_help *help; + enum ip_conntrack_info ctinfo; + unsigned int protoff; + struct nf_conn *ct; + + ct = nf_ct_get(skb, &ctinfo); + if (!ct || ctinfo == IP_CT_RELATED_REPLY) + return NF_ACCEPT; + + help = nfct_help(ct); + if (!help) + return NF_ACCEPT; + + helper = rcu_dereference(help->helper); + if (!helper) + return NF_ACCEPT; + + switch (proto) { + case NFPROTO_IPV4: + protoff = ip_hdrlen(skb); + break; + case NFPROTO_IPV6: { + u8 nexthdr = ipv6_hdr(skb)->nexthdr; + __be16 frag_off; + + protoff = ipv6_skip_exthdr(skb, sizeof(struct ipv6hdr), + &nexthdr, &frag_off); + if (protoff < 0 || (frag_off & htons(~0x7)) != 0) { + pr_debug("proto header not found\n"); + return NF_ACCEPT; + } + break; + } + default: + WARN_ONCE(1, "helper invoked on non-IP family!"); + return NF_DROP; + } + + return helper->help(skb, protoff, ct, ctinfo); +} + +static int handle_fragments(struct net *net, struct sw_flow_key *key, + u16 zone, struct sk_buff *skb) +{ + struct ovs_skb_cb ovs_cb = *OVS_CB(skb); + + if (key->eth.type == htons(ETH_P_IP)) { + enum ip_defrag_users user = IP_DEFRAG_CONNTRACK_IN + zone; + int err; + + memset(IPCB(skb), 0, sizeof(struct inet_skb_parm)); + err = ip_defrag(skb, user); + if (err) + return err; + + ovs_cb.mru = IPCB(skb)->frag_max_size; + } else if (key->eth.type == htons(ETH_P_IPV6)) { +#if IS_ENABLED(CONFIG_NF_DEFRAG_IPV6) + enum ip6_defrag_users user = IP6_DEFRAG_CONNTRACK_IN + zone; + struct sk_buff *reasm; + + memset(IP6CB(skb), 0, sizeof(struct inet6_skb_parm)); + reasm = nf_ct_frag6_gather(skb, user); + if (!reasm) + return -EINPROGRESS; + + if (skb == reasm) + return -EINVAL; + + key->ip.proto = ipv6_hdr(reasm)->nexthdr; + skb_morph(skb, reasm); + consume_skb(reasm); + ovs_cb.mru = IP6CB(skb)->frag_max_size; +#else + return -EPFNOSUPPORT; +#endif + } else { + return -EPFNOSUPPORT; + } + + key->ip.frag = OVS_FRAG_TYPE_NONE; + skb_clear_hash(skb); + skb->ignore_df = 1; + *OVS_CB(skb) = ovs_cb; + + return 0; +} + +static struct nf_conntrack_expect * +ovs_ct_expect_find(struct net *net, const struct nf_conntrack_zone *zone, + u16 proto, const struct sk_buff *skb) +{ + struct nf_conntrack_tuple tuple; + + if (!nf_ct_get_tuplepr(skb, skb_network_offset(skb), proto, &tuple)) + return NULL; + return __nf_ct_expect_find(net, zone, &tuple); +} + +/* Determine whether skb->nfct is equal to the result of conntrack lookup. */ +static bool skb_nfct_cached(const struct net *net, const struct sk_buff *skb, + const struct ovs_conntrack_info *info) +{ + enum ip_conntrack_info ctinfo; + struct nf_conn *ct; + + ct = nf_ct_get(skb, &ctinfo); + if (!ct) + return false; + if (!net_eq(net, read_pnet(&ct->ct_net))) + return false; + if (!nf_ct_zone_equal_any(info->ct, nf_ct_zone(ct))) + return false; + if (info->helper) { + struct nf_conn_help *help; + + help = nf_ct_ext_find(ct, NF_CT_EXT_HELPER); + if (help && rcu_access_pointer(help->helper) != info->helper) + return false; + } + + return true; +} + +static int __ovs_ct_lookup(struct net *net, const struct sw_flow_key *key, + const struct ovs_conntrack_info *info, + struct sk_buff *skb) +{ + /* If we are recirculating packets to match on conntrack fields and + * committing with a separate conntrack action, then we don't need to + * actually run the packet through conntrack twice unless it's for a + * different zone. + */ + if (!skb_nfct_cached(net, skb, info)) { + struct nf_conn *tmpl = info->ct; + + /* Associate skb with specified zone. */ + if (tmpl) { + if (skb->nfct) + nf_conntrack_put(skb->nfct); + nf_conntrack_get(&tmpl->ct_general); + skb->nfct = &tmpl->ct_general; + skb->nfctinfo = IP_CT_NEW; + } + + if (nf_conntrack_in(net, info->family, NF_INET_PRE_ROUTING, + skb) != NF_ACCEPT) + return -ENOENT; + + if (ovs_ct_helper(skb, info->family) != NF_ACCEPT) { + WARN_ONCE(1, "helper rejected packet"); + return -EINVAL; + } + } + + return 0; +} + +/* Lookup connection and read fields into key. */ +static int ovs_ct_lookup(struct net *net, struct sw_flow_key *key, + const struct ovs_conntrack_info *info, + struct sk_buff *skb) +{ + struct nf_conntrack_expect *exp; + + exp = ovs_ct_expect_find(net, &info->zone, info->family, skb); + if (exp) { + u8 state; + + state = OVS_CS_F_TRACKED | OVS_CS_F_NEW | OVS_CS_F_RELATED; + __ovs_ct_update_key(key, state, &info->zone, exp->master); + } else { + int err; + + err = __ovs_ct_lookup(net, key, info, skb); + if (err) + return err; + + ovs_ct_update_key(skb, key, true); + } + + return 0; +} + +/* Lookup connection and confirm if unconfirmed. */ +static int ovs_ct_commit(struct net *net, struct sw_flow_key *key, + const struct ovs_conntrack_info *info, + struct sk_buff *skb) +{ + u8 state; + int err; + + state = key->ct.state; + if (key->ct.zone == info->zone.id && + ((state & OVS_CS_F_TRACKED) && !(state & OVS_CS_F_NEW))) { + /* Previous lookup has shown that this connection is already + * tracked and committed. Skip committing. + */ + return 0; + } + + err = __ovs_ct_lookup(net, key, info, skb); + if (err) + return err; + if (nf_conntrack_confirm(skb) != NF_ACCEPT) + return -EINVAL; + + ovs_ct_update_key(skb, key, true); + + return 0; +} + +static bool label_nonzero(const struct ovs_key_ct_label *label) +{ + size_t i; + + for (i = 0; i < sizeof(*label); i++) + if (label->ct_label[i]) + return true; + + return false; +} + +int ovs_ct_execute(struct net *net, struct sk_buff *skb, + struct sw_flow_key *key, + const struct ovs_conntrack_info *info) +{ + int nh_ofs; + int err; + + /* The conntrack module expects to be working at L3. */ + nh_ofs = skb_network_offset(skb); + skb_pull(skb, nh_ofs); + + if (key->ip.frag != OVS_FRAG_TYPE_NONE) { + err = handle_fragments(net, key, info->zone.id, skb); + if (err) + return err; + } + + if (info->flags & OVS_CT_F_COMMIT) + err = ovs_ct_commit(net, key, info, skb); + else + err = ovs_ct_lookup(net, key, info, skb); + if (err) + goto err; + + if (info->mark.mask) { + err = ovs_ct_set_mark(skb, key, info->mark.value, + info->mark.mask); + if (err) + goto err; + } + if (label_nonzero(&info->label.mask)) + err = ovs_ct_set_label(skb, key, &info->label.value, + &info->label.mask); +err: + skb_push(skb, nh_ofs); + return err; +} + +static int ovs_ct_add_helper(struct ovs_conntrack_info *info, const char *name, + const struct sw_flow_key *key, bool log) +{ + struct nf_conntrack_helper *helper; + struct nf_conn_help *help; + + helper = nf_conntrack_helper_try_module_get(name, info->family, + key->ip.proto); + if (!helper) { + OVS_NLERR(log, "Unknown helper \"%s\"", name); + return -EINVAL; + } + + help = nf_ct_helper_ext_add(info->ct, helper, GFP_KERNEL); + if (!help) { + module_put(helper->me); + return -ENOMEM; + } + + rcu_assign_pointer(help->helper, helper); + info->helper = helper; + return 0; +} + +static const struct ovs_ct_len_tbl ovs_ct_attr_lens[OVS_CT_ATTR_MAX + 1] = { + [OVS_CT_ATTR_FLAGS] = { .minlen = sizeof(u32), + .maxlen = sizeof(u32) }, + [OVS_CT_ATTR_ZONE] = { .minlen = sizeof(u16), + .maxlen = sizeof(u16) }, + [OVS_CT_ATTR_MARK] = { .minlen = sizeof(struct md_mark), + .maxlen = sizeof(struct md_mark) }, + [OVS_CT_ATTR_LABEL] = { .minlen = sizeof(struct md_label), + .maxlen = sizeof(struct md_label) }, + [OVS_CT_ATTR_HELPER] = { .minlen = 1, + .maxlen = NF_CT_HELPER_NAME_LEN } +}; + +static int parse_ct(const struct nlattr *attr, struct ovs_conntrack_info *info, + const char **helper, bool log) +{ + struct nlattr *a; + int rem; + + nla_for_each_nested(a, attr, rem) { + int type = nla_type(a); + int maxlen = ovs_ct_attr_lens[type].maxlen; + int minlen = ovs_ct_attr_lens[type].minlen; + + if (type > OVS_CT_ATTR_MAX) { + OVS_NLERR(log, + "Unknown conntrack attr (type=%d, max=%d)", + type, OVS_CT_ATTR_MAX); + return -EINVAL; + } + if (nla_len(a) < minlen || nla_len(a) > maxlen) { + OVS_NLERR(log, + "Conntrack attr type has unexpected length (type=%d, length=%d, expected=%d)", + type, nla_len(a), maxlen); + return -EINVAL; + } + + switch (type) { + case OVS_CT_ATTR_FLAGS: + info->flags = nla_get_u32(a); + break; +#ifdef CONFIG_NF_CONNTRACK_ZONES + case OVS_CT_ATTR_ZONE: + info->zone.id = nla_get_u16(a); + break; +#endif +#ifdef CONFIG_NF_CONNTRACK_MARK + case OVS_CT_ATTR_MARK: { + struct md_mark *mark = nla_data(a); + + info->mark = *mark; + break; + } +#endif +#ifdef CONFIG_NF_CONNTRACK_LABELS + case OVS_CT_ATTR_LABEL: { + struct md_label *label = nla_data(a); + + info->label = *label; + break; + } +#endif + case OVS_CT_ATTR_HELPER: + *helper = nla_data(a); + if (!memchr(*helper, '\0', nla_len(a))) { + OVS_NLERR(log, "Invalid conntrack helper"); + return -EINVAL; + } + break; + default: + OVS_NLERR(log, "Unknown conntrack attr (%d)", + type); + return -EINVAL; + } + } + + if (rem > 0) { + OVS_NLERR(log, "Conntrack attr has %d unknown bytes", rem); + return -EINVAL; + } + + return 0; +} + +bool ovs_ct_verify(struct net *net, enum ovs_key_attr attr) +{ + if (attr == OVS_KEY_ATTR_CT_STATE) + return true; + if (IS_ENABLED(CONFIG_NF_CONNTRACK_ZONES) && + attr == OVS_KEY_ATTR_CT_ZONE) + return true; + if (IS_ENABLED(CONFIG_NF_CONNTRACK_MARK) && + attr == OVS_KEY_ATTR_CT_MARK) + return true; + if (IS_ENABLED(CONFIG_NF_CONNTRACK_LABELS) && + attr == OVS_KEY_ATTR_CT_LABEL) { + struct ovs_net *ovs_net = net_generic(net, ovs_net_id); + + return ovs_net->xt_label; + } + + return false; +} + +int ovs_ct_copy_action(struct net *net, const struct nlattr *attr, + const struct sw_flow_key *key, + struct sw_flow_actions **sfa, bool log) +{ + struct ovs_conntrack_info ct_info; + const char *helper = NULL; + u16 family; + int err; + + family = key_to_nfproto(key); + if (family == NFPROTO_UNSPEC) { + OVS_NLERR(log, "ct family unspecified"); + return -EINVAL; + } + + memset(&ct_info, 0, sizeof(ct_info)); + ct_info.family = family; + + nf_ct_zone_init(&ct_info.zone, NF_CT_DEFAULT_ZONE_ID, + NF_CT_DEFAULT_ZONE_DIR, 0); + + err = parse_ct(attr, &ct_info, &helper, log); + if (err) + return err; + + /* Set up template for tracking connections in specific zones. */ + ct_info.ct = nf_ct_tmpl_alloc(net, &ct_info.zone, GFP_KERNEL); + if (!ct_info.ct) { + OVS_NLERR(log, "Failed to allocate conntrack template"); + return -ENOMEM; + } + if (helper) { + err = ovs_ct_add_helper(&ct_info, helper, key, log); + if (err) + goto err_free_ct; + } + + err = ovs_nla_add_action(sfa, OVS_ACTION_ATTR_CT, &ct_info, + sizeof(ct_info), log); + if (err) + goto err_free_ct; + + __set_bit(IPS_CONFIRMED_BIT, &ct_info.ct->status); + nf_conntrack_get(&ct_info.ct->ct_general); + return 0; +err_free_ct: + nf_conntrack_free(ct_info.ct); + return err; +} + +int ovs_ct_action_to_attr(const struct ovs_conntrack_info *ct_info, + struct sk_buff *skb) +{ + struct nlattr *start; + + start = nla_nest_start(skb, OVS_ACTION_ATTR_CT); + if (!start) + return -EMSGSIZE; + + if (nla_put_u32(skb, OVS_CT_ATTR_FLAGS, ct_info->flags)) + return -EMSGSIZE; + if (IS_ENABLED(CONFIG_NF_CONNTRACK_ZONES) && + nla_put_u16(skb, OVS_CT_ATTR_ZONE, ct_info->zone.id)) + return -EMSGSIZE; + if (IS_ENABLED(CONFIG_NF_CONNTRACK_MARK) && + nla_put(skb, OVS_CT_ATTR_MARK, sizeof(ct_info->mark), + &ct_info->mark)) + return -EMSGSIZE; + if (IS_ENABLED(CONFIG_NF_CONNTRACK_LABELS) && + nla_put(skb, OVS_CT_ATTR_LABEL, sizeof(ct_info->label), + &ct_info->label)) + return -EMSGSIZE; + if (ct_info->helper) { + if (nla_put_string(skb, OVS_CT_ATTR_HELPER, + ct_info->helper->name)) + return -EMSGSIZE; + } + + nla_nest_end(skb, start); + + return 0; +} + +void ovs_ct_free_action(const struct nlattr *a) +{ + struct ovs_conntrack_info *ct_info = nla_data(a); + + if (ct_info->helper) + module_put(ct_info->helper->me); + if (ct_info->ct) + nf_ct_put(ct_info->ct); +} + +void ovs_ct_init(struct net *net) +{ + unsigned int n_bits = sizeof(struct ovs_key_ct_label) * BITS_PER_BYTE; + struct ovs_net *ovs_net = net_generic(net, ovs_net_id); + + if (nf_connlabels_get(net, n_bits)) { + ovs_net->xt_label = false; + OVS_NLERR(true, "Failed to set connlabel length"); + } else { + ovs_net->xt_label = true; + } +} + +void ovs_ct_exit(struct net *net) +{ + struct ovs_net *ovs_net = net_generic(net, ovs_net_id); + + if (ovs_net->xt_label) + nf_connlabels_put(net); +} diff --git a/net/openvswitch/conntrack.h b/net/openvswitch/conntrack.h new file mode 100644 index 000000000000..43f5dd7a5577 --- /dev/null +++ b/net/openvswitch/conntrack.h @@ -0,0 +1,86 @@ +/* + * Copyright (c) 2015 Nicira, Inc. + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of version 2 of the GNU General Public + * License as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, but + * WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * General Public License for more details. + */ + +#ifndef OVS_CONNTRACK_H +#define OVS_CONNTRACK_H 1 + +#include "flow.h" + +struct ovs_conntrack_info; +enum ovs_key_attr; + +#if IS_ENABLED(CONFIG_NF_CONNTRACK) +void ovs_ct_init(struct net *); +void ovs_ct_exit(struct net *); +bool ovs_ct_verify(struct net *, enum ovs_key_attr attr); +int ovs_ct_copy_action(struct net *, const struct nlattr *, + const struct sw_flow_key *, struct sw_flow_actions **, + bool log); +int ovs_ct_action_to_attr(const struct ovs_conntrack_info *, struct sk_buff *); + +int ovs_ct_execute(struct net *, struct sk_buff *, struct sw_flow_key *, + const struct ovs_conntrack_info *); + +void ovs_ct_fill_key(const struct sk_buff *skb, struct sw_flow_key *key); +int ovs_ct_put_key(const struct sw_flow_key *key, struct sk_buff *skb); +void ovs_ct_free_action(const struct nlattr *a); +#else +#include <linux/errno.h> + +static inline void ovs_ct_init(struct net *net) { } + +static inline void ovs_ct_exit(struct net *net) { } + +static inline bool ovs_ct_verify(struct net *net, int attr) +{ + return false; +} + +static inline int ovs_ct_copy_action(struct net *net, const struct nlattr *nla, + const struct sw_flow_key *key, + struct sw_flow_actions **acts, bool log) +{ + return -ENOTSUPP; +} + +static inline int ovs_ct_action_to_attr(const struct ovs_conntrack_info *info, + struct sk_buff *skb) +{ + return -ENOTSUPP; +} + +static inline int ovs_ct_execute(struct net *net, struct sk_buff *skb, + struct sw_flow_key *key, + const struct ovs_conntrack_info *info) +{ + return -ENOTSUPP; +} + +static inline void ovs_ct_fill_key(const struct sk_buff *skb, + struct sw_flow_key *key) +{ + key->ct.state = 0; + key->ct.zone = 0; + key->ct.mark = 0; + memset(&key->ct.label, 0, sizeof(key->ct.label)); +} + +static inline int ovs_ct_put_key(const struct sw_flow_key *key, + struct sk_buff *skb) +{ + return 0; +} + +static inline void ovs_ct_free_action(const struct nlattr *a) { } +#endif /* CONFIG_NF_CONNTRACK */ +#endif /* ovs_conntrack.h */ diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c index ff8c4a4c1609..6fbd2decb19e 100644 --- a/net/openvswitch/datapath.c +++ b/net/openvswitch/datapath.c @@ -176,7 +176,7 @@ static inline struct datapath *get_dp(struct net *net, int dp_ifindex) const char *ovs_dp_name(const struct datapath *dp) { struct vport *vport = ovs_vport_ovsl_rcu(dp, OVSP_LOCAL); - return vport->ops->get_name(vport); + return ovs_vport_name(vport); } static int get_dpifindex(const struct datapath *dp) @@ -188,7 +188,7 @@ static int get_dpifindex(const struct datapath *dp) local = ovs_vport_rcu(dp, OVSP_LOCAL); if (local) - ifindex = netdev_vport_priv(local)->dev->ifindex; + ifindex = local->dev->ifindex; else ifindex = 0; @@ -275,6 +275,7 @@ void ovs_dp_process_packet(struct sk_buff *skb, struct sw_flow_key *key) memset(&upcall, 0, sizeof(upcall)); upcall.cmd = OVS_PACKET_CMD_MISS; upcall.portid = ovs_vport_find_upcall_portid(p, skb); + upcall.mru = OVS_CB(skb)->mru; error = ovs_dp_upcall(dp, skb, key, &upcall); if (unlikely(error)) kfree_skb(skb); @@ -400,9 +401,23 @@ static size_t upcall_msg_size(const struct dp_upcall_info *upcall_info, if (upcall_info->actions_len) size += nla_total_size(upcall_info->actions_len); + /* OVS_PACKET_ATTR_MRU */ + if (upcall_info->mru) + size += nla_total_size(sizeof(upcall_info->mru)); + return size; } +static void pad_packet(struct datapath *dp, struct sk_buff *skb) +{ + if (!(dp->user_features & OVS_DP_F_UNALIGNED)) { + size_t plen = NLA_ALIGN(skb->len) - skb->len; + + if (plen > 0) + memset(skb_put(skb, plen), 0, plen); + } +} + static int queue_userspace_packet(struct datapath *dp, struct sk_buff *skb, const struct sw_flow_key *key, const struct dp_upcall_info *upcall_info) @@ -476,7 +491,8 @@ static int queue_userspace_packet(struct datapath *dp, struct sk_buff *skb, if (upcall_info->egress_tun_info) { nla = nla_nest_start(user_skb, OVS_PACKET_ATTR_EGRESS_TUN_KEY); err = ovs_nla_put_egress_tunnel_key(user_skb, - upcall_info->egress_tun_info); + upcall_info->egress_tun_info, + upcall_info->egress_tun_opts); BUG_ON(err); nla_nest_end(user_skb, nla); } @@ -492,6 +508,16 @@ static int queue_userspace_packet(struct datapath *dp, struct sk_buff *skb, nla_nest_cancel(user_skb, nla); } + /* Add OVS_PACKET_ATTR_MRU */ + if (upcall_info->mru) { + if (nla_put_u16(user_skb, OVS_PACKET_ATTR_MRU, + upcall_info->mru)) { + err = -ENOBUFS; + goto out; + } + pad_packet(dp, user_skb); + } + /* Only reserve room for attribute header, packet data is added * in skb_zerocopy() */ if (!(nla = nla_reserve(user_skb, OVS_PACKET_ATTR_PACKET, 0))) { @@ -505,12 +531,7 @@ static int queue_userspace_packet(struct datapath *dp, struct sk_buff *skb, goto out; /* Pad OVS_PACKET_ATTR_PACKET if linear copy was performed */ - if (!(dp->user_features & OVS_DP_F_UNALIGNED)) { - size_t plen = NLA_ALIGN(user_skb->len) - user_skb->len; - - if (plen > 0) - memset(skb_put(user_skb, plen), 0, plen); - } + pad_packet(dp, user_skb); ((struct nlmsghdr *) user_skb->data)->nlmsg_len = user_skb->len; @@ -527,6 +548,7 @@ out: static int ovs_packet_cmd_execute(struct sk_buff *skb, struct genl_info *info) { struct ovs_header *ovs_header = info->userhdr; + struct net *net = sock_net(skb->sk); struct nlattr **a = info->attrs; struct sw_flow_actions *acts; struct sk_buff *packet; @@ -535,6 +557,7 @@ static int ovs_packet_cmd_execute(struct sk_buff *skb, struct genl_info *info) struct datapath *dp; struct ethhdr *eth; struct vport *input_vport; + u16 mru = 0; int len; int err; bool log = !a[OVS_PACKET_ATTR_PROBE]; @@ -564,29 +587,35 @@ static int ovs_packet_cmd_execute(struct sk_buff *skb, struct genl_info *info) else packet->protocol = htons(ETH_P_802_2); + /* Set packet's mru */ + if (a[OVS_PACKET_ATTR_MRU]) { + mru = nla_get_u16(a[OVS_PACKET_ATTR_MRU]); + packet->ignore_df = 1; + } + OVS_CB(packet)->mru = mru; + /* Build an sw_flow for sending this packet. */ flow = ovs_flow_alloc(); err = PTR_ERR(flow); if (IS_ERR(flow)) goto err_kfree_skb; - err = ovs_flow_key_extract_userspace(a[OVS_PACKET_ATTR_KEY], packet, - &flow->key, log); + err = ovs_flow_key_extract_userspace(net, a[OVS_PACKET_ATTR_KEY], + packet, &flow->key, log); if (err) goto err_flow_free; - err = ovs_nla_copy_actions(a[OVS_PACKET_ATTR_ACTIONS], + err = ovs_nla_copy_actions(net, a[OVS_PACKET_ATTR_ACTIONS], &flow->key, &acts, log); if (err) goto err_flow_free; rcu_assign_pointer(flow->sf_acts, acts); - OVS_CB(packet)->egress_tun_info = NULL; packet->priority = flow->key.phy.priority; packet->mark = flow->key.phy.skb_mark; rcu_read_lock(); - dp = get_dp_rcu(sock_net(skb->sk), ovs_header->dp_ifindex); + dp = get_dp_rcu(net, ovs_header->dp_ifindex); err = -ENODEV; if (!dp) goto err_unlock; @@ -598,6 +627,7 @@ static int ovs_packet_cmd_execute(struct sk_buff *skb, struct genl_info *info) if (!input_vport) goto err_unlock; + packet->dev = input_vport->dev; OVS_CB(packet)->input_vport = input_vport; sf_acts = rcu_dereference(flow->sf_acts); @@ -624,6 +654,7 @@ static const struct nla_policy packet_policy[OVS_PACKET_ATTR_MAX + 1] = { [OVS_PACKET_ATTR_KEY] = { .type = NLA_NESTED }, [OVS_PACKET_ATTR_ACTIONS] = { .type = NLA_NESTED }, [OVS_PACKET_ATTR_PROBE] = { .type = NLA_FLAG }, + [OVS_PACKET_ATTR_MRU] = { .type = NLA_U16 }, }; static const struct genl_ops dp_packet_genl_ops[] = { @@ -713,7 +744,7 @@ static size_t ovs_flow_cmd_msg_size(const struct sw_flow_actions *acts, /* OVS_FLOW_ATTR_ACTIONS */ if (should_fill_actions(ufid_flags)) - len += nla_total_size(acts->actions_len); + len += nla_total_size(acts->orig_len); return len + nla_total_size(sizeof(struct ovs_flow_stats)) /* OVS_FLOW_ATTR_STATS */ @@ -880,6 +911,7 @@ static struct sk_buff *ovs_flow_cmd_build_info(const struct sw_flow *flow, static int ovs_flow_cmd_new(struct sk_buff *skb, struct genl_info *info) { + struct net *net = sock_net(skb->sk); struct nlattr **a = info->attrs; struct ovs_header *ovs_header = info->userhdr; struct sw_flow *flow = NULL, *new_flow; @@ -915,7 +947,7 @@ static int ovs_flow_cmd_new(struct sk_buff *skb, struct genl_info *info) /* Extract key. */ ovs_match_init(&match, &key, &mask); - error = ovs_nla_get_match(&match, a[OVS_FLOW_ATTR_KEY], + error = ovs_nla_get_match(net, &match, a[OVS_FLOW_ATTR_KEY], a[OVS_FLOW_ATTR_MASK], log); if (error) goto err_kfree_flow; @@ -929,8 +961,8 @@ static int ovs_flow_cmd_new(struct sk_buff *skb, struct genl_info *info) goto err_kfree_flow; /* Validate actions. */ - error = ovs_nla_copy_actions(a[OVS_FLOW_ATTR_ACTIONS], &new_flow->key, - &acts, log); + error = ovs_nla_copy_actions(net, a[OVS_FLOW_ATTR_ACTIONS], + &new_flow->key, &acts, log); if (error) { OVS_NLERR(log, "Flow actions may not be safe on all matching packets."); goto err_kfree_flow; @@ -944,7 +976,7 @@ static int ovs_flow_cmd_new(struct sk_buff *skb, struct genl_info *info) } ovs_lock(); - dp = get_dp(sock_net(skb->sk), ovs_header->dp_ifindex); + dp = get_dp(net, ovs_header->dp_ifindex); if (unlikely(!dp)) { error = -ENODEV; goto err_unlock_ovs; @@ -1018,7 +1050,7 @@ static int ovs_flow_cmd_new(struct sk_buff *skb, struct genl_info *info) } ovs_unlock(); - ovs_nla_free_flow_actions(old_acts); + ovs_nla_free_flow_actions_rcu(old_acts); ovs_flow_free(new_flow, false); } @@ -1030,7 +1062,7 @@ err_unlock_ovs: ovs_unlock(); kfree_skb(reply); err_kfree_acts: - kfree(acts); + ovs_nla_free_flow_actions(acts); err_kfree_flow: ovs_flow_free(new_flow, false); error: @@ -1038,7 +1070,8 @@ error: } /* Factor out action copy to avoid "Wframe-larger-than=1024" warning. */ -static struct sw_flow_actions *get_flow_actions(const struct nlattr *a, +static struct sw_flow_actions *get_flow_actions(struct net *net, + const struct nlattr *a, const struct sw_flow_key *key, const struct sw_flow_mask *mask, bool log) @@ -1048,7 +1081,7 @@ static struct sw_flow_actions *get_flow_actions(const struct nlattr *a, int error; ovs_flow_mask_key(&masked_key, key, mask); - error = ovs_nla_copy_actions(a, &masked_key, &acts, log); + error = ovs_nla_copy_actions(net, a, &masked_key, &acts, log); if (error) { OVS_NLERR(log, "Actions may not be safe on all matching packets"); @@ -1060,6 +1093,7 @@ static struct sw_flow_actions *get_flow_actions(const struct nlattr *a, static int ovs_flow_cmd_set(struct sk_buff *skb, struct genl_info *info) { + struct net *net = sock_net(skb->sk); struct nlattr **a = info->attrs; struct ovs_header *ovs_header = info->userhdr; struct sw_flow_key key; @@ -1084,15 +1118,15 @@ static int ovs_flow_cmd_set(struct sk_buff *skb, struct genl_info *info) ufid_present = ovs_nla_get_ufid(&sfid, a[OVS_FLOW_ATTR_UFID], log); ovs_match_init(&match, &key, &mask); - error = ovs_nla_get_match(&match, a[OVS_FLOW_ATTR_KEY], + error = ovs_nla_get_match(net, &match, a[OVS_FLOW_ATTR_KEY], a[OVS_FLOW_ATTR_MASK], log); if (error) goto error; /* Validate actions. */ if (a[OVS_FLOW_ATTR_ACTIONS]) { - acts = get_flow_actions(a[OVS_FLOW_ATTR_ACTIONS], &key, &mask, - log); + acts = get_flow_actions(net, a[OVS_FLOW_ATTR_ACTIONS], &key, + &mask, log); if (IS_ERR(acts)) { error = PTR_ERR(acts); goto error; @@ -1108,7 +1142,7 @@ static int ovs_flow_cmd_set(struct sk_buff *skb, struct genl_info *info) } ovs_lock(); - dp = get_dp(sock_net(skb->sk), ovs_header->dp_ifindex); + dp = get_dp(net, ovs_header->dp_ifindex); if (unlikely(!dp)) { error = -ENODEV; goto err_unlock_ovs; @@ -1157,7 +1191,7 @@ static int ovs_flow_cmd_set(struct sk_buff *skb, struct genl_info *info) if (reply) ovs_notify(&dp_flow_genl_family, reply, info); if (old_acts) - ovs_nla_free_flow_actions(old_acts); + ovs_nla_free_flow_actions_rcu(old_acts); return 0; @@ -1165,7 +1199,7 @@ err_unlock_ovs: ovs_unlock(); kfree_skb(reply); err_kfree_acts: - kfree(acts); + ovs_nla_free_flow_actions(acts); error: return error; } @@ -1174,6 +1208,7 @@ static int ovs_flow_cmd_get(struct sk_buff *skb, struct genl_info *info) { struct nlattr **a = info->attrs; struct ovs_header *ovs_header = info->userhdr; + struct net *net = sock_net(skb->sk); struct sw_flow_key key; struct sk_buff *reply; struct sw_flow *flow; @@ -1188,7 +1223,7 @@ static int ovs_flow_cmd_get(struct sk_buff *skb, struct genl_info *info) ufid_present = ovs_nla_get_ufid(&ufid, a[OVS_FLOW_ATTR_UFID], log); if (a[OVS_FLOW_ATTR_KEY]) { ovs_match_init(&match, &key, NULL); - err = ovs_nla_get_match(&match, a[OVS_FLOW_ATTR_KEY], NULL, + err = ovs_nla_get_match(net, &match, a[OVS_FLOW_ATTR_KEY], NULL, log); } else if (!ufid_present) { OVS_NLERR(log, @@ -1232,6 +1267,7 @@ static int ovs_flow_cmd_del(struct sk_buff *skb, struct genl_info *info) { struct nlattr **a = info->attrs; struct ovs_header *ovs_header = info->userhdr; + struct net *net = sock_net(skb->sk); struct sw_flow_key key; struct sk_buff *reply; struct sw_flow *flow = NULL; @@ -1246,8 +1282,8 @@ static int ovs_flow_cmd_del(struct sk_buff *skb, struct genl_info *info) ufid_present = ovs_nla_get_ufid(&ufid, a[OVS_FLOW_ATTR_UFID], log); if (a[OVS_FLOW_ATTR_KEY]) { ovs_match_init(&match, &key, NULL); - err = ovs_nla_get_match(&match, a[OVS_FLOW_ATTR_KEY], NULL, - log); + err = ovs_nla_get_match(net, &match, a[OVS_FLOW_ATTR_KEY], + NULL, log); if (unlikely(err)) return err; } @@ -1800,7 +1836,7 @@ static int ovs_vport_cmd_fill_info(struct vport *vport, struct sk_buff *skb, if (nla_put_u32(skb, OVS_VPORT_ATTR_PORT_NO, vport->port_no) || nla_put_u32(skb, OVS_VPORT_ATTR_TYPE, vport->ops->type) || nla_put_string(skb, OVS_VPORT_ATTR_NAME, - vport->ops->get_name(vport))) + ovs_vport_name(vport))) goto nla_put_failure; ovs_vport_get_stats(vport, &vport_stats); @@ -2203,6 +2239,7 @@ static int __net_init ovs_init_net(struct net *net) INIT_LIST_HEAD(&ovs_net->dps); INIT_WORK(&ovs_net->dp_notify_work, ovs_dp_notify_wq); + ovs_ct_init(net); return 0; } @@ -2219,13 +2256,10 @@ static void __net_exit list_vports_from_net(struct net *net, struct net *dnet, struct vport *vport; hlist_for_each_entry(vport, &dp->ports[i], dp_hash_node) { - struct netdev_vport *netdev_vport; - if (vport->ops->type != OVS_VPORT_TYPE_INTERNAL) continue; - netdev_vport = netdev_vport_priv(vport); - if (dev_net(netdev_vport->dev) == dnet) + if (dev_net(vport->dev) == dnet) list_add(&vport->detach_list, head); } } @@ -2240,6 +2274,7 @@ static void __net_exit ovs_exit_net(struct net *dnet) struct net *net; LIST_HEAD(head); + ovs_ct_exit(dnet); ovs_lock(); list_for_each_entry_safe(dp, dp_next, &ovs_net->dps, list_node) __dp_destroy(dp); diff --git a/net/openvswitch/datapath.h b/net/openvswitch/datapath.h index cd691e935e08..f88038a99f44 100644 --- a/net/openvswitch/datapath.h +++ b/net/openvswitch/datapath.h @@ -25,10 +25,11 @@ #include <linux/netdevice.h> #include <linux/skbuff.h> #include <linux/u64_stats_sync.h> +#include <net/ip_tunnels.h> +#include "conntrack.h" #include "flow.h" #include "flow_table.h" -#include "vport.h" #define DP_MAX_PORTS USHRT_MAX #define DP_VPORT_HASH_BUCKETS 1024 @@ -92,14 +93,14 @@ struct datapath { /** * struct ovs_skb_cb - OVS data in skb CB - * @egress_tun_key: Tunnel information about this packet on egress path. - * NULL if the packet is not being tunneled. * @input_vport: The original vport packet came in on. This value is cached * when a packet is received by OVS. + * @mru: The maximum received fragement size; 0 if the packet is not + * fragmented. */ struct ovs_skb_cb { - struct ovs_tunnel_info *egress_tun_info; struct vport *input_vport; + u16 mru; }; #define OVS_CB(skb) ((struct ovs_skb_cb *)(skb)->cb) @@ -112,14 +113,17 @@ struct ovs_skb_cb { * then no packet is sent and the packet is accounted in the datapath's @n_lost * counter. * @egress_tun_info: If nonnull, becomes %OVS_PACKET_ATTR_EGRESS_TUN_KEY. + * @mru: If not zero, Maximum received IP fragment size. */ struct dp_upcall_info { - const struct ovs_tunnel_info *egress_tun_info; + struct ip_tunnel_info *egress_tun_info; + const void *egress_tun_opts; const struct nlattr *userdata; const struct nlattr *actions; int actions_len; u32 portid; u8 cmd; + u16 mru; }; /** @@ -130,7 +134,9 @@ struct dp_upcall_info { struct ovs_net { struct list_head dps; struct work_struct dp_notify_work; - struct vport_net vport_net; + + /* Module reference for configuring conntrack. */ + bool xt_label; }; extern int ovs_net_id; @@ -199,6 +205,10 @@ void ovs_dp_notify_wq(struct work_struct *work); int action_fifos_init(void); void action_fifos_exit(void); +/* 'KEY' must not have any bits set outside of the 'MASK' */ +#define OVS_MASKED(OLD, KEY, MASK) ((KEY) | ((OLD) & ~(MASK))) +#define OVS_SET_MASKED(OLD, KEY, MASK) ((OLD) = OVS_MASKED(OLD, KEY, MASK)) + #define OVS_NLERR(logging_allowed, fmt, ...) \ do { \ if (logging_allowed && net_ratelimit()) \ diff --git a/net/openvswitch/dp_notify.c b/net/openvswitch/dp_notify.c index 2c631fe76be1..a7a80a6b77b0 100644 --- a/net/openvswitch/dp_notify.c +++ b/net/openvswitch/dp_notify.c @@ -58,13 +58,10 @@ void ovs_dp_notify_wq(struct work_struct *work) struct hlist_node *n; hlist_for_each_entry_safe(vport, n, &dp->ports[i], dp_hash_node) { - struct netdev_vport *netdev_vport; - if (vport->ops->type != OVS_VPORT_TYPE_NETDEV) continue; - netdev_vport = netdev_vport_priv(vport); - if (!(netdev_vport->dev->priv_flags & IFF_OVS_DATAPATH)) + if (!(vport->dev->priv_flags & IFF_OVS_DATAPATH)) dp_detach_port_notify(vport); } } diff --git a/net/openvswitch/flow.c b/net/openvswitch/flow.c index bc7b0aba994a..c8db44ab2ee7 100644 --- a/net/openvswitch/flow.c +++ b/net/openvswitch/flow.c @@ -46,9 +46,11 @@ #include <net/mpls.h> #include <net/ndisc.h> +#include "conntrack.h" #include "datapath.h" #include "flow.h" #include "flow_netlink.h" +#include "vport.h" u64 ovs_flow_used_time(unsigned long flow_jiffies) { @@ -271,8 +273,6 @@ static int parse_ipv6hdr(struct sk_buff *skb, struct sw_flow_key *key) key->ipv6.addr.dst = nh->daddr; payload_ofs = ipv6_skip_exthdr(skb, payload_ofs, &nexthdr, &frag_off); - if (unlikely(payload_ofs < 0)) - return -EINVAL; if (frag_off) { if (frag_off & htons(~0x7)) @@ -283,6 +283,13 @@ static int parse_ipv6hdr(struct sk_buff *skb, struct sw_flow_key *key) key->ip.frag = OVS_FRAG_TYPE_NONE; } + /* Delayed handling of error in ipv6_skip_exthdr() as it + * always sets frag_off to a valid value which may be + * used to set key->ip.frag above. + */ + if (unlikely(payload_ofs < 0)) + return -EPROTO; + nh_len = payload_ofs - nh_ofs; skb_set_transport_header(skb, nh_ofs + nh_len); key->ip.proto = nexthdr; @@ -622,12 +629,16 @@ static int key_extract(struct sk_buff *skb, struct sw_flow_key *key) nh_len = parse_ipv6hdr(skb, key); if (unlikely(nh_len < 0)) { - memset(&key->ip, 0, sizeof(key->ip)); - memset(&key->ipv6.addr, 0, sizeof(key->ipv6.addr)); - if (nh_len == -EINVAL) { + switch (nh_len) { + case -EINVAL: + memset(&key->ip, 0, sizeof(key->ip)); + memset(&key->ipv6.addr, 0, sizeof(key->ipv6.addr)); + /* fall-through */ + case -EPROTO: skb->transport_header = skb->network_header; error = 0; - } else { + break; + default: error = nh_len; } return error; @@ -682,19 +693,22 @@ int ovs_flow_key_update(struct sk_buff *skb, struct sw_flow_key *key) return key_extract(skb, key); } -int ovs_flow_key_extract(const struct ovs_tunnel_info *tun_info, +int ovs_flow_key_extract(const struct ip_tunnel_info *tun_info, struct sk_buff *skb, struct sw_flow_key *key) { /* Extract metadata from packet. */ if (tun_info) { - memcpy(&key->tun_key, &tun_info->tunnel, sizeof(key->tun_key)); + if (ip_tunnel_info_af(tun_info) != AF_INET) + return -EINVAL; + memcpy(&key->tun_key, &tun_info->key, sizeof(key->tun_key)); - if (tun_info->options) { + if (tun_info->options_len) { BUILD_BUG_ON((1 << (sizeof(tun_info->options_len) * 8)) - 1 > sizeof(key->tun_opts)); - memcpy(TUN_METADATA_OPTS(key, tun_info->options_len), - tun_info->options, tun_info->options_len); + + ip_tunnel_info_opts_get(TUN_METADATA_OPTS(key, tun_info->options_len), + tun_info); key->tun_opts_len = tun_info->options_len; } else { key->tun_opts_len = 0; @@ -707,13 +721,14 @@ int ovs_flow_key_extract(const struct ovs_tunnel_info *tun_info, key->phy.priority = skb->priority; key->phy.in_port = OVS_CB(skb)->input_vport->port_no; key->phy.skb_mark = skb->mark; + ovs_ct_fill_key(skb, key); key->ovs_flow_hash = 0; key->recirc_id = 0; return key_extract(skb, key); } -int ovs_flow_key_extract_userspace(const struct nlattr *attr, +int ovs_flow_key_extract_userspace(struct net *net, const struct nlattr *attr, struct sk_buff *skb, struct sw_flow_key *key, bool log) { @@ -722,7 +737,7 @@ int ovs_flow_key_extract_userspace(const struct nlattr *attr, memset(key, 0, OVS_SW_FLOW_KEY_METADATA_SIZE); /* Extract metadata from netlink attributes. */ - err = ovs_nla_get_flow_metadata(attr, key, log); + err = ovs_nla_get_flow_metadata(net, attr, key, log); if (err) return err; diff --git a/net/openvswitch/flow.h b/net/openvswitch/flow.h index a076e445ccc2..fe527d2dd4b7 100644 --- a/net/openvswitch/flow.h +++ b/net/openvswitch/flow.h @@ -32,31 +32,11 @@ #include <linux/time.h> #include <linux/flex_array.h> #include <net/inet_ecn.h> +#include <net/ip_tunnels.h> +#include <net/dst_metadata.h> struct sk_buff; -/* Used to memset ovs_key_ipv4_tunnel padding. */ -#define OVS_TUNNEL_KEY_SIZE \ - (offsetof(struct ovs_key_ipv4_tunnel, tp_dst) + \ - FIELD_SIZEOF(struct ovs_key_ipv4_tunnel, tp_dst)) - -struct ovs_key_ipv4_tunnel { - __be64 tun_id; - __be32 ipv4_src; - __be32 ipv4_dst; - __be16 tun_flags; - u8 ipv4_tos; - u8 ipv4_ttl; - __be16 tp_src; - __be16 tp_dst; -} __packed __aligned(4); /* Minimize padding. */ - -struct ovs_tunnel_info { - struct ovs_key_ipv4_tunnel tunnel; - const void *options; - u8 options_len; -}; - /* Store options at the end of the array if they are less than the * maximum size. This allows us to get the benefits of variable length * matching for small options. @@ -66,54 +46,9 @@ struct ovs_tunnel_info { #define TUN_METADATA_OPTS(flow_key, opt_len) \ ((void *)((flow_key)->tun_opts + TUN_METADATA_OFFSET(opt_len))) -static inline void __ovs_flow_tun_info_init(struct ovs_tunnel_info *tun_info, - __be32 saddr, __be32 daddr, - u8 tos, u8 ttl, - __be16 tp_src, - __be16 tp_dst, - __be64 tun_id, - __be16 tun_flags, - const void *opts, - u8 opts_len) -{ - tun_info->tunnel.tun_id = tun_id; - tun_info->tunnel.ipv4_src = saddr; - tun_info->tunnel.ipv4_dst = daddr; - tun_info->tunnel.ipv4_tos = tos; - tun_info->tunnel.ipv4_ttl = ttl; - tun_info->tunnel.tun_flags = tun_flags; - - /* For the tunnel types on the top of IPsec, the tp_src and tp_dst of - * the upper tunnel are used. - * E.g: GRE over IPSEC, the tp_src and tp_port are zero. - */ - tun_info->tunnel.tp_src = tp_src; - tun_info->tunnel.tp_dst = tp_dst; - - /* Clear struct padding. */ - if (sizeof(tun_info->tunnel) != OVS_TUNNEL_KEY_SIZE) - memset((unsigned char *)&tun_info->tunnel + OVS_TUNNEL_KEY_SIZE, - 0, sizeof(tun_info->tunnel) - OVS_TUNNEL_KEY_SIZE); - - tun_info->options = opts; - tun_info->options_len = opts_len; -} - -static inline void ovs_flow_tun_info_init(struct ovs_tunnel_info *tun_info, - const struct iphdr *iph, - __be16 tp_src, - __be16 tp_dst, - __be64 tun_id, - __be16 tun_flags, - const void *opts, - u8 opts_len) -{ - __ovs_flow_tun_info_init(tun_info, iph->saddr, iph->daddr, - iph->tos, iph->ttl, - tp_src, tp_dst, - tun_id, tun_flags, - opts, opts_len); -} +struct ovs_tunnel_info { + struct metadata_dst *tun_dst; +}; #define OVS_SW_FLOW_KEY_METADATA_SIZE \ (offsetof(struct sw_flow_key, recirc_id) + \ @@ -122,7 +57,7 @@ static inline void ovs_flow_tun_info_init(struct ovs_tunnel_info *tun_info, struct sw_flow_key { u8 tun_opts[255]; u8 tun_opts_len; - struct ovs_key_ipv4_tunnel tun_key; /* Encapsulating tunnel key. */ + struct ip_tunnel_key tun_key; /* Encapsulating tunnel key. */ struct { u32 priority; /* Packet QoS priority. */ u32 skb_mark; /* SKB mark. */ @@ -176,6 +111,14 @@ struct sw_flow_key { } nd; } ipv6; }; + struct { + /* Connection tracking fields. */ + u16 zone; + u32 mark; + u8 state; + struct ovs_key_ct_label label; + } ct; + } __aligned(BITS_PER_LONG/8); /* Ensure that we can do comparisons as longs. */ struct sw_flow_key_range { @@ -209,6 +152,7 @@ struct sw_flow_id { struct sw_flow_actions { struct rcu_head rcu; + size_t orig_len; /* From flow_cmd_new netlink actions size */ u32 actions_len; struct nlattr actions[]; }; @@ -273,11 +217,11 @@ void ovs_flow_stats_clear(struct sw_flow *); u64 ovs_flow_used_time(unsigned long flow_jiffies); int ovs_flow_key_update(struct sk_buff *skb, struct sw_flow_key *key); -int ovs_flow_key_extract(const struct ovs_tunnel_info *tun_info, +int ovs_flow_key_extract(const struct ip_tunnel_info *tun_info, struct sk_buff *skb, struct sw_flow_key *key); /* Extract key from packet coming from userspace. */ -int ovs_flow_key_extract_userspace(const struct nlattr *attr, +int ovs_flow_key_extract_userspace(struct net *net, const struct nlattr *attr, struct sk_buff *skb, struct sw_flow_key *key, bool log); diff --git a/net/openvswitch/flow_netlink.c b/net/openvswitch/flow_netlink.c index 624e41c4267f..c92d6a262bc5 100644 --- a/net/openvswitch/flow_netlink.c +++ b/net/openvswitch/flow_netlink.c @@ -47,9 +47,9 @@ #include <net/ipv6.h> #include <net/ndisc.h> #include <net/mpls.h> +#include <net/vxlan.h> #include "flow_netlink.h" -#include "vport-vxlan.h" struct ovs_len_tbl { int len; @@ -281,7 +281,7 @@ size_t ovs_key_attr_size(void) /* Whenever adding new OVS_KEY_ FIELDS, we should consider * updating this function. */ - BUILD_BUG_ON(OVS_KEY_ATTR_TUNNEL_INFO != 22); + BUILD_BUG_ON(OVS_KEY_ATTR_TUNNEL_INFO != 26); return nla_total_size(4) /* OVS_KEY_ATTR_PRIORITY */ + nla_total_size(0) /* OVS_KEY_ATTR_TUNNEL */ @@ -290,6 +290,10 @@ size_t ovs_key_attr_size(void) + nla_total_size(4) /* OVS_KEY_ATTR_SKB_MARK */ + nla_total_size(4) /* OVS_KEY_ATTR_DP_HASH */ + nla_total_size(4) /* OVS_KEY_ATTR_RECIRC_ID */ + + nla_total_size(1) /* OVS_KEY_ATTR_CT_STATE */ + + nla_total_size(2) /* OVS_KEY_ATTR_CT_ZONE */ + + nla_total_size(4) /* OVS_KEY_ATTR_CT_MARK */ + + nla_total_size(16) /* OVS_KEY_ATTR_CT_LABEL */ + nla_total_size(12) /* OVS_KEY_ATTR_ETHERNET */ + nla_total_size(2) /* OVS_KEY_ATTR_ETHERTYPE */ + nla_total_size(4) /* OVS_KEY_ATTR_VLAN */ @@ -339,6 +343,10 @@ static const struct ovs_len_tbl ovs_key_lens[OVS_KEY_ATTR_MAX + 1] = { [OVS_KEY_ATTR_TUNNEL] = { .len = OVS_ATTR_NESTED, .next = ovs_tunnel_key_lens, }, [OVS_KEY_ATTR_MPLS] = { .len = sizeof(struct ovs_key_mpls) }, + [OVS_KEY_ATTR_CT_STATE] = { .len = sizeof(u8) }, + [OVS_KEY_ATTR_CT_ZONE] = { .len = sizeof(u16) }, + [OVS_KEY_ATTR_CT_MARK] = { .len = sizeof(u32) }, + [OVS_KEY_ATTR_CT_LABEL] = { .len = sizeof(struct ovs_key_ct_label) }, }; static bool is_all_zero(const u8 *fp, size_t size) @@ -475,7 +483,7 @@ static int vxlan_tun_opt_from_nlattr(const struct nlattr *a, { struct nlattr *tb[OVS_VXLAN_EXT_MAX+1]; unsigned long opt_key_offset; - struct ovs_vxlan_opts opts; + struct vxlan_metadata opts; int err; BUILD_BUG_ON(sizeof(opts) > sizeof(match->key->tun_opts)); @@ -534,19 +542,19 @@ static int ipv4_tun_from_nlattr(const struct nlattr *attr, tun_flags |= TUNNEL_KEY; break; case OVS_TUNNEL_KEY_ATTR_IPV4_SRC: - SW_FLOW_KEY_PUT(match, tun_key.ipv4_src, + SW_FLOW_KEY_PUT(match, tun_key.u.ipv4.src, nla_get_in_addr(a), is_mask); break; case OVS_TUNNEL_KEY_ATTR_IPV4_DST: - SW_FLOW_KEY_PUT(match, tun_key.ipv4_dst, + SW_FLOW_KEY_PUT(match, tun_key.u.ipv4.dst, nla_get_in_addr(a), is_mask); break; case OVS_TUNNEL_KEY_ATTR_TOS: - SW_FLOW_KEY_PUT(match, tun_key.ipv4_tos, + SW_FLOW_KEY_PUT(match, tun_key.tos, nla_get_u8(a), is_mask); break; case OVS_TUNNEL_KEY_ATTR_TTL: - SW_FLOW_KEY_PUT(match, tun_key.ipv4_ttl, + SW_FLOW_KEY_PUT(match, tun_key.ttl, nla_get_u8(a), is_mask); ttl = true; break; @@ -609,7 +617,7 @@ static int ipv4_tun_from_nlattr(const struct nlattr *attr, } if (!is_mask) { - if (!match->key->tun_key.ipv4_dst) { + if (!match->key->tun_key.u.ipv4.dst) { OVS_NLERR(log, "IPv4 tunnel dst address is zero"); return -EINVAL; } @@ -626,7 +634,7 @@ static int ipv4_tun_from_nlattr(const struct nlattr *attr, static int vxlan_opt_to_nlattr(struct sk_buff *skb, const void *tun_opts, int swkey_tun_opts_len) { - const struct ovs_vxlan_opts *opts = tun_opts; + const struct vxlan_metadata *opts = tun_opts; struct nlattr *nla; nla = nla_nest_start(skb, OVS_TUNNEL_KEY_ATTR_VXLAN_OPTS); @@ -641,24 +649,24 @@ static int vxlan_opt_to_nlattr(struct sk_buff *skb, } static int __ipv4_tun_to_nlattr(struct sk_buff *skb, - const struct ovs_key_ipv4_tunnel *output, + const struct ip_tunnel_key *output, const void *tun_opts, int swkey_tun_opts_len) { if (output->tun_flags & TUNNEL_KEY && nla_put_be64(skb, OVS_TUNNEL_KEY_ATTR_ID, output->tun_id)) return -EMSGSIZE; - if (output->ipv4_src && + if (output->u.ipv4.src && nla_put_in_addr(skb, OVS_TUNNEL_KEY_ATTR_IPV4_SRC, - output->ipv4_src)) + output->u.ipv4.src)) return -EMSGSIZE; - if (output->ipv4_dst && + if (output->u.ipv4.dst && nla_put_in_addr(skb, OVS_TUNNEL_KEY_ATTR_IPV4_DST, - output->ipv4_dst)) + output->u.ipv4.dst)) return -EMSGSIZE; - if (output->ipv4_tos && - nla_put_u8(skb, OVS_TUNNEL_KEY_ATTR_TOS, output->ipv4_tos)) + if (output->tos && + nla_put_u8(skb, OVS_TUNNEL_KEY_ATTR_TOS, output->tos)) return -EMSGSIZE; - if (nla_put_u8(skb, OVS_TUNNEL_KEY_ATTR_TTL, output->ipv4_ttl)) + if (nla_put_u8(skb, OVS_TUNNEL_KEY_ATTR_TTL, output->ttl)) return -EMSGSIZE; if ((output->tun_flags & TUNNEL_DONT_FRAGMENT) && nla_put_flag(skb, OVS_TUNNEL_KEY_ATTR_DONT_FRAGMENT)) @@ -689,7 +697,7 @@ static int __ipv4_tun_to_nlattr(struct sk_buff *skb, } static int ipv4_tun_to_nlattr(struct sk_buff *skb, - const struct ovs_key_ipv4_tunnel *output, + const struct ip_tunnel_key *output, const void *tun_opts, int swkey_tun_opts_len) { struct nlattr *nla; @@ -708,16 +716,17 @@ static int ipv4_tun_to_nlattr(struct sk_buff *skb, } int ovs_nla_put_egress_tunnel_key(struct sk_buff *skb, - const struct ovs_tunnel_info *egress_tun_info) + const struct ip_tunnel_info *egress_tun_info, + const void *egress_tun_opts) { - return __ipv4_tun_to_nlattr(skb, &egress_tun_info->tunnel, - egress_tun_info->options, + return __ipv4_tun_to_nlattr(skb, &egress_tun_info->key, + egress_tun_opts, egress_tun_info->options_len); } -static int metadata_from_nlattrs(struct sw_flow_match *match, u64 *attrs, - const struct nlattr **a, bool is_mask, - bool log) +static int metadata_from_nlattrs(struct net *net, struct sw_flow_match *match, + u64 *attrs, const struct nlattr **a, + bool is_mask, bool log) { if (*attrs & (1 << OVS_KEY_ATTR_DP_HASH)) { u32 hash_val = nla_get_u32(a[OVS_KEY_ATTR_DP_HASH]); @@ -768,16 +777,47 @@ static int metadata_from_nlattrs(struct sw_flow_match *match, u64 *attrs, return -EINVAL; *attrs &= ~(1 << OVS_KEY_ATTR_TUNNEL); } + + if (*attrs & (1 << OVS_KEY_ATTR_CT_STATE) && + ovs_ct_verify(net, OVS_KEY_ATTR_CT_STATE)) { + u8 ct_state = nla_get_u8(a[OVS_KEY_ATTR_CT_STATE]); + + SW_FLOW_KEY_PUT(match, ct.state, ct_state, is_mask); + *attrs &= ~(1ULL << OVS_KEY_ATTR_CT_STATE); + } + if (*attrs & (1 << OVS_KEY_ATTR_CT_ZONE) && + ovs_ct_verify(net, OVS_KEY_ATTR_CT_ZONE)) { + u16 ct_zone = nla_get_u16(a[OVS_KEY_ATTR_CT_ZONE]); + + SW_FLOW_KEY_PUT(match, ct.zone, ct_zone, is_mask); + *attrs &= ~(1ULL << OVS_KEY_ATTR_CT_ZONE); + } + if (*attrs & (1 << OVS_KEY_ATTR_CT_MARK) && + ovs_ct_verify(net, OVS_KEY_ATTR_CT_MARK)) { + u32 mark = nla_get_u32(a[OVS_KEY_ATTR_CT_MARK]); + + SW_FLOW_KEY_PUT(match, ct.mark, mark, is_mask); + *attrs &= ~(1ULL << OVS_KEY_ATTR_CT_MARK); + } + if (*attrs & (1 << OVS_KEY_ATTR_CT_LABEL) && + ovs_ct_verify(net, OVS_KEY_ATTR_CT_LABEL)) { + const struct ovs_key_ct_label *cl; + + cl = nla_data(a[OVS_KEY_ATTR_CT_LABEL]); + SW_FLOW_KEY_MEMCPY(match, ct.label, cl->ct_label, + sizeof(*cl), is_mask); + *attrs &= ~(1ULL << OVS_KEY_ATTR_CT_LABEL); + } return 0; } -static int ovs_key_from_nlattrs(struct sw_flow_match *match, u64 attrs, - const struct nlattr **a, bool is_mask, - bool log) +static int ovs_key_from_nlattrs(struct net *net, struct sw_flow_match *match, + u64 attrs, const struct nlattr **a, + bool is_mask, bool log) { int err; - err = metadata_from_nlattrs(match, &attrs, a, is_mask, log); + err = metadata_from_nlattrs(net, match, &attrs, a, is_mask, log); if (err) return err; @@ -1029,6 +1069,7 @@ static void mask_set_nlattr(struct nlattr *attr, u8 val) * mask. In case the 'mask' is NULL, the flow is treated as exact match * flow. Otherwise, it is treated as a wildcarded flow, except the mask * does not include any don't care bit. + * @net: Used to determine per-namespace field support. * @match: receives the extracted flow match information. * @key: Netlink attribute holding nested %OVS_KEY_ATTR_* Netlink attribute * sequence. The fields should of the packet that triggered the creation @@ -1039,7 +1080,7 @@ static void mask_set_nlattr(struct nlattr *attr, u8 val) * probing for feature compatibility this should be passed in as false to * suppress unnecessary error logging. */ -int ovs_nla_get_match(struct sw_flow_match *match, +int ovs_nla_get_match(struct net *net, struct sw_flow_match *match, const struct nlattr *nla_key, const struct nlattr *nla_mask, bool log) @@ -1089,7 +1130,7 @@ int ovs_nla_get_match(struct sw_flow_match *match, } } - err = ovs_key_from_nlattrs(match, key_attrs, a, false, log); + err = ovs_key_from_nlattrs(net, match, key_attrs, a, false, log); if (err) return err; @@ -1116,7 +1157,7 @@ int ovs_nla_get_match(struct sw_flow_match *match, /* The userspace does not send tunnel attributes that * are 0, but we should not wildcard them nonetheless. */ - if (match->key->tun_key.ipv4_dst) + if (match->key->tun_key.u.ipv4.dst) SW_FLOW_KEY_MEMSET_FIELD(match, tun_key, 0xff, true); @@ -1169,7 +1210,8 @@ int ovs_nla_get_match(struct sw_flow_match *match, } } - err = ovs_key_from_nlattrs(match, mask_attrs, a, true, log); + err = ovs_key_from_nlattrs(net, match, mask_attrs, a, true, + log); if (err) goto free_newmask; } @@ -1250,7 +1292,7 @@ u32 ovs_nla_get_ufid_flags(const struct nlattr *attr) * extracted from the packet itself. */ -int ovs_nla_get_flow_metadata(const struct nlattr *attr, +int ovs_nla_get_flow_metadata(struct net *net, const struct nlattr *attr, struct sw_flow_key *key, bool log) { @@ -1266,9 +1308,10 @@ int ovs_nla_get_flow_metadata(const struct nlattr *attr, memset(&match, 0, sizeof(match)); match.key = key; + memset(&key->ct, 0, sizeof(key->ct)); key->phy.in_port = DP_MAX_PORTS; - return metadata_from_nlattrs(&match, &attrs, a, false, log); + return metadata_from_nlattrs(net, &match, &attrs, a, false, log); } static int __ovs_nla_put_key(const struct sw_flow_key *swkey, @@ -1287,7 +1330,7 @@ static int __ovs_nla_put_key(const struct sw_flow_key *swkey, if (nla_put_u32(skb, OVS_KEY_ATTR_PRIORITY, output->phy.priority)) goto nla_put_failure; - if ((swkey->tun_key.ipv4_dst || is_mask)) { + if ((swkey->tun_key.u.ipv4.dst || is_mask)) { const void *opts = NULL; if (output->tun_key.tun_flags & TUNNEL_OPTIONS_PRESENT) @@ -1314,6 +1357,9 @@ static int __ovs_nla_put_key(const struct sw_flow_key *swkey, if (nla_put_u32(skb, OVS_KEY_ATTR_SKB_MARK, output->phy.skb_mark)) goto nla_put_failure; + if (ovs_ct_put_key(output, skb)) + goto nla_put_failure; + nla = nla_reserve(skb, OVS_KEY_ATTR_ETHERNET, sizeof(*eth_key)); if (!nla) goto nla_put_failure; @@ -1548,11 +1594,51 @@ static struct sw_flow_actions *nla_alloc_flow_actions(int size, bool log) return sfa; } +static void ovs_nla_free_set_action(const struct nlattr *a) +{ + const struct nlattr *ovs_key = nla_data(a); + struct ovs_tunnel_info *ovs_tun; + + switch (nla_type(ovs_key)) { + case OVS_KEY_ATTR_TUNNEL_INFO: + ovs_tun = nla_data(ovs_key); + dst_release((struct dst_entry *)ovs_tun->tun_dst); + break; + } +} + +void ovs_nla_free_flow_actions(struct sw_flow_actions *sf_acts) +{ + const struct nlattr *a; + int rem; + + if (!sf_acts) + return; + + nla_for_each_attr(a, sf_acts->actions, sf_acts->actions_len, rem) { + switch (nla_type(a)) { + case OVS_ACTION_ATTR_SET: + ovs_nla_free_set_action(a); + break; + case OVS_ACTION_ATTR_CT: + ovs_ct_free_action(a); + break; + } + } + + kfree(sf_acts); +} + +static void __ovs_nla_free_flow_actions(struct rcu_head *head) +{ + ovs_nla_free_flow_actions(container_of(head, struct sw_flow_actions, rcu)); +} + /* Schedules 'sf_acts' to be freed after the next RCU grace period. * The caller must hold rcu_read_lock for this to be sensible. */ -void ovs_nla_free_flow_actions(struct sw_flow_actions *sf_acts) +void ovs_nla_free_flow_actions_rcu(struct sw_flow_actions *sf_acts) { - kfree_rcu(sf_acts, rcu); + call_rcu(&sf_acts->rcu, __ovs_nla_free_flow_actions); } static struct nlattr *reserve_sfa_size(struct sw_flow_actions **sfa, @@ -1582,6 +1668,7 @@ static struct nlattr *reserve_sfa_size(struct sw_flow_actions **sfa, memcpy(acts->actions, (*sfa)->actions, (*sfa)->actions_len); acts->actions_len = (*sfa)->actions_len; + acts->orig_len = (*sfa)->orig_len; kfree(*sfa); *sfa = acts; @@ -1609,8 +1696,8 @@ static struct nlattr *__add_action(struct sw_flow_actions **sfa, return a; } -static int add_action(struct sw_flow_actions **sfa, int attrtype, - void *data, int len, bool log) +int ovs_nla_add_action(struct sw_flow_actions **sfa, int attrtype, void *data, + int len, bool log) { struct nlattr *a; @@ -1625,7 +1712,7 @@ static inline int add_nested_action_start(struct sw_flow_actions **sfa, int used = (*sfa)->actions_len; int err; - err = add_action(sfa, attrtype, NULL, 0, log); + err = ovs_nla_add_action(sfa, attrtype, NULL, 0, log); if (err) return err; @@ -1641,12 +1728,12 @@ static inline void add_nested_action_end(struct sw_flow_actions *sfa, a->nla_len = sfa->actions_len - st_offset; } -static int __ovs_nla_copy_actions(const struct nlattr *attr, +static int __ovs_nla_copy_actions(struct net *net, const struct nlattr *attr, const struct sw_flow_key *key, int depth, struct sw_flow_actions **sfa, __be16 eth_type, __be16 vlan_tci, bool log); -static int validate_and_copy_sample(const struct nlattr *attr, +static int validate_and_copy_sample(struct net *net, const struct nlattr *attr, const struct sw_flow_key *key, int depth, struct sw_flow_actions **sfa, __be16 eth_type, __be16 vlan_tci, bool log) @@ -1678,15 +1765,15 @@ static int validate_and_copy_sample(const struct nlattr *attr, start = add_nested_action_start(sfa, OVS_ACTION_ATTR_SAMPLE, log); if (start < 0) return start; - err = add_action(sfa, OVS_SAMPLE_ATTR_PROBABILITY, - nla_data(probability), sizeof(u32), log); + err = ovs_nla_add_action(sfa, OVS_SAMPLE_ATTR_PROBABILITY, + nla_data(probability), sizeof(u32), log); if (err) return err; st_acts = add_nested_action_start(sfa, OVS_SAMPLE_ATTR_ACTIONS, log); if (st_acts < 0) return st_acts; - err = __ovs_nla_copy_actions(actions, key, depth + 1, sfa, + err = __ovs_nla_copy_actions(net, actions, key, depth + 1, sfa, eth_type, vlan_tci, log); if (err) return err; @@ -1746,7 +1833,9 @@ static int validate_and_copy_set_tun(const struct nlattr *attr, { struct sw_flow_match match; struct sw_flow_key key; - struct ovs_tunnel_info *tun_info; + struct metadata_dst *tun_dst; + struct ip_tunnel_info *tun_info; + struct ovs_tunnel_info *ovs_tun; struct nlattr *a; int err = 0, start, opts_type; @@ -1771,27 +1860,31 @@ static int validate_and_copy_set_tun(const struct nlattr *attr, if (start < 0) return start; + tun_dst = metadata_dst_alloc(key.tun_opts_len, GFP_KERNEL); + if (!tun_dst) + return -ENOMEM; + a = __add_action(sfa, OVS_KEY_ATTR_TUNNEL_INFO, NULL, - sizeof(*tun_info) + key.tun_opts_len, log); - if (IS_ERR(a)) + sizeof(*ovs_tun), log); + if (IS_ERR(a)) { + dst_release((struct dst_entry *)tun_dst); return PTR_ERR(a); + } - tun_info = nla_data(a); - tun_info->tunnel = key.tun_key; - tun_info->options_len = key.tun_opts_len; + ovs_tun = nla_data(a); + ovs_tun->tun_dst = tun_dst; - if (tun_info->options_len) { - /* We need to store the options in the action itself since - * everything else will go away after flow setup. We can append - * it to tun_info and then point there. - */ - memcpy((tun_info + 1), - TUN_METADATA_OPTS(&key, key.tun_opts_len), key.tun_opts_len); - tun_info->options = (tun_info + 1); - } else { - tun_info->options = NULL; - } + tun_info = &tun_dst->u.tun_info; + tun_info->mode = IP_TUNNEL_INFO_TX; + tun_info->key = key.tun_key; + /* We need to store the options in the action itself since + * everything else will go away after flow setup. We can append + * it to tun_info and then point there. + */ + ip_tunnel_info_opts_set(tun_info, + TUN_METADATA_OPTS(&key, key.tun_opts_len), + key.tun_opts_len); add_nested_action_end(*sfa, start); return err; @@ -1843,6 +1936,8 @@ static int validate_set(const struct nlattr *a, case OVS_KEY_ATTR_PRIORITY: case OVS_KEY_ATTR_SKB_MARK: + case OVS_KEY_ATTR_CT_MARK: + case OVS_KEY_ATTR_CT_LABEL: case OVS_KEY_ATTR_ETHERNET: break; @@ -2008,7 +2103,7 @@ static int copy_action(const struct nlattr *from, return 0; } -static int __ovs_nla_copy_actions(const struct nlattr *attr, +static int __ovs_nla_copy_actions(struct net *net, const struct nlattr *attr, const struct sw_flow_key *key, int depth, struct sw_flow_actions **sfa, __be16 eth_type, __be16 vlan_tci, bool log) @@ -2032,7 +2127,8 @@ static int __ovs_nla_copy_actions(const struct nlattr *attr, [OVS_ACTION_ATTR_SET] = (u32)-1, [OVS_ACTION_ATTR_SET_MASKED] = (u32)-1, [OVS_ACTION_ATTR_SAMPLE] = (u32)-1, - [OVS_ACTION_ATTR_HASH] = sizeof(struct ovs_action_hash) + [OVS_ACTION_ATTR_HASH] = sizeof(struct ovs_action_hash), + [OVS_ACTION_ATTR_CT] = (u32)-1, }; const struct ovs_action_push_vlan *vlan; int type = nla_type(a); @@ -2139,13 +2235,20 @@ static int __ovs_nla_copy_actions(const struct nlattr *attr, break; case OVS_ACTION_ATTR_SAMPLE: - err = validate_and_copy_sample(a, key, depth, sfa, + err = validate_and_copy_sample(net, a, key, depth, sfa, eth_type, vlan_tci, log); if (err) return err; skip_copy = true; break; + case OVS_ACTION_ATTR_CT: + err = ovs_ct_copy_action(net, a, key, sfa, log); + if (err) + return err; + skip_copy = true; + break; + default: OVS_NLERR(log, "Unknown Action type %d", type); return -EINVAL; @@ -2164,7 +2267,7 @@ static int __ovs_nla_copy_actions(const struct nlattr *attr, } /* 'key' must be the masked key. */ -int ovs_nla_copy_actions(const struct nlattr *attr, +int ovs_nla_copy_actions(struct net *net, const struct nlattr *attr, const struct sw_flow_key *key, struct sw_flow_actions **sfa, bool log) { @@ -2174,10 +2277,11 @@ int ovs_nla_copy_actions(const struct nlattr *attr, if (IS_ERR(*sfa)) return PTR_ERR(*sfa); - err = __ovs_nla_copy_actions(attr, key, 0, sfa, key->eth.type, + (*sfa)->orig_len = nla_len(attr); + err = __ovs_nla_copy_actions(net, attr, key, 0, sfa, key->eth.type, key->eth.tci, log); if (err) - kfree(*sfa); + ovs_nla_free_flow_actions(*sfa); return err; } @@ -2227,15 +2331,16 @@ static int set_action_to_attr(const struct nlattr *a, struct sk_buff *skb) switch (key_type) { case OVS_KEY_ATTR_TUNNEL_INFO: { - struct ovs_tunnel_info *tun_info = nla_data(ovs_key); + struct ovs_tunnel_info *ovs_tun = nla_data(ovs_key); + struct ip_tunnel_info *tun_info = &ovs_tun->tun_dst->u.tun_info; start = nla_nest_start(skb, OVS_ACTION_ATTR_SET); if (!start) return -EMSGSIZE; - err = ipv4_tun_to_nlattr(skb, &tun_info->tunnel, + err = ipv4_tun_to_nlattr(skb, &tun_info->key, tun_info->options_len ? - tun_info->options : NULL, + ip_tunnel_info_opts(tun_info) : NULL, tun_info->options_len); if (err) return err; @@ -2298,6 +2403,13 @@ int ovs_nla_put_actions(const struct nlattr *attr, int len, struct sk_buff *skb) if (err) return err; break; + + case OVS_ACTION_ATTR_CT: + err = ovs_ct_action_to_attr(nla_data(a), skb); + if (err) + return err; + break; + default: if (nla_put(skb, type, nla_len(a), nla_data(a))) return -EMSGSIZE; diff --git a/net/openvswitch/flow_netlink.h b/net/openvswitch/flow_netlink.h index 5c3d75bff310..6ca3f0baf449 100644 --- a/net/openvswitch/flow_netlink.h +++ b/net/openvswitch/flow_netlink.h @@ -45,29 +45,34 @@ void ovs_match_init(struct sw_flow_match *match, int ovs_nla_put_key(const struct sw_flow_key *, const struct sw_flow_key *, int attr, bool is_mask, struct sk_buff *); -int ovs_nla_get_flow_metadata(const struct nlattr *, struct sw_flow_key *, - bool log); +int ovs_nla_get_flow_metadata(struct net *, const struct nlattr *, + struct sw_flow_key *, bool log); int ovs_nla_put_identifier(const struct sw_flow *flow, struct sk_buff *skb); int ovs_nla_put_masked_key(const struct sw_flow *flow, struct sk_buff *skb); int ovs_nla_put_mask(const struct sw_flow *flow, struct sk_buff *skb); -int ovs_nla_get_match(struct sw_flow_match *, const struct nlattr *key, - const struct nlattr *mask, bool log); +int ovs_nla_get_match(struct net *, struct sw_flow_match *, + const struct nlattr *key, const struct nlattr *mask, + bool log); int ovs_nla_put_egress_tunnel_key(struct sk_buff *, - const struct ovs_tunnel_info *); + const struct ip_tunnel_info *, + const void *egress_tun_opts); bool ovs_nla_get_ufid(struct sw_flow_id *, const struct nlattr *, bool log); int ovs_nla_get_identifier(struct sw_flow_id *sfid, const struct nlattr *ufid, const struct sw_flow_key *key, bool log); u32 ovs_nla_get_ufid_flags(const struct nlattr *attr); -int ovs_nla_copy_actions(const struct nlattr *attr, +int ovs_nla_copy_actions(struct net *net, const struct nlattr *attr, const struct sw_flow_key *key, struct sw_flow_actions **sfa, bool log); +int ovs_nla_add_action(struct sw_flow_actions **sfa, int attrtype, + void *data, int len, bool log); int ovs_nla_put_actions(const struct nlattr *attr, int len, struct sk_buff *skb); void ovs_nla_free_flow_actions(struct sw_flow_actions *); +void ovs_nla_free_flow_actions_rcu(struct sw_flow_actions *); #endif /* flow_netlink.h */ diff --git a/net/openvswitch/flow_table.c b/net/openvswitch/flow_table.c index 65523948fb95..d22d8e948d0f 100644 --- a/net/openvswitch/flow_table.c +++ b/net/openvswitch/flow_table.c @@ -18,6 +18,7 @@ #include "flow.h" #include "datapath.h" +#include "flow_netlink.h" #include <linux/uaccess.h> #include <linux/netdevice.h> #include <linux/etherdevice.h> @@ -143,7 +144,8 @@ static void flow_free(struct sw_flow *flow) if (ovs_identifier_is_key(&flow->id)) kfree(flow->id.unmasked_key); - kfree((struct sw_flow_actions __force *)flow->sf_acts); + if (flow->sf_acts) + ovs_nla_free_flow_actions((struct sw_flow_actions __force *)flow->sf_acts); for_each_node(node) if (flow->stats[node]) kmem_cache_free(flow_stats_cache, @@ -424,7 +426,7 @@ static u32 flow_hash(const struct sw_flow_key *key, static int flow_key_start(const struct sw_flow_key *key) { - if (key->tun_key.ipv4_dst) + if (key->tun_key.u.ipv4.dst) return 0; else return rounddown(offsetof(struct sw_flow_key, phy), diff --git a/net/openvswitch/vport-geneve.c b/net/openvswitch/vport-geneve.c index 208c576bd1b6..2735e9c4a3b8 100644 --- a/net/openvswitch/vport-geneve.c +++ b/net/openvswitch/vport-geneve.c @@ -26,96 +26,42 @@ #include "datapath.h" #include "vport.h" +#include "vport-netdev.h" static struct vport_ops ovs_geneve_vport_ops; - /** * struct geneve_port - Keeps track of open UDP ports - * @gs: The socket created for this port number. - * @name: vport name. + * @dst_port: destination port. */ struct geneve_port { - struct geneve_sock *gs; - char name[IFNAMSIZ]; + u16 port_no; }; -static LIST_HEAD(geneve_ports); - static inline struct geneve_port *geneve_vport(const struct vport *vport) { return vport_priv(vport); } -/* Convert 64 bit tunnel ID to 24 bit VNI. */ -static void tunnel_id_to_vni(__be64 tun_id, __u8 *vni) -{ -#ifdef __BIG_ENDIAN - vni[0] = (__force __u8)(tun_id >> 16); - vni[1] = (__force __u8)(tun_id >> 8); - vni[2] = (__force __u8)tun_id; -#else - vni[0] = (__force __u8)((__force u64)tun_id >> 40); - vni[1] = (__force __u8)((__force u64)tun_id >> 48); - vni[2] = (__force __u8)((__force u64)tun_id >> 56); -#endif -} - -/* Convert 24 bit VNI to 64 bit tunnel ID. */ -static __be64 vni_to_tunnel_id(const __u8 *vni) -{ -#ifdef __BIG_ENDIAN - return (vni[0] << 16) | (vni[1] << 8) | vni[2]; -#else - return (__force __be64)(((__force u64)vni[0] << 40) | - ((__force u64)vni[1] << 48) | - ((__force u64)vni[2] << 56)); -#endif -} - -static void geneve_rcv(struct geneve_sock *gs, struct sk_buff *skb) -{ - struct vport *vport = gs->rcv_data; - struct genevehdr *geneveh = geneve_hdr(skb); - int opts_len; - struct ovs_tunnel_info tun_info; - __be64 key; - __be16 flags; - - opts_len = geneveh->opt_len * 4; - - flags = TUNNEL_KEY | TUNNEL_GENEVE_OPT | - (udp_hdr(skb)->check != 0 ? TUNNEL_CSUM : 0) | - (geneveh->oam ? TUNNEL_OAM : 0) | - (geneveh->critical ? TUNNEL_CRIT_OPT : 0); - - key = vni_to_tunnel_id(geneveh->vni); - - ovs_flow_tun_info_init(&tun_info, ip_hdr(skb), - udp_hdr(skb)->source, udp_hdr(skb)->dest, - key, flags, - geneveh->options, opts_len); - - ovs_vport_receive(vport, skb, &tun_info); -} - static int geneve_get_options(const struct vport *vport, struct sk_buff *skb) { struct geneve_port *geneve_port = geneve_vport(vport); - struct inet_sock *sk = inet_sk(geneve_port->gs->sock->sk); - if (nla_put_u16(skb, OVS_TUNNEL_ATTR_DST_PORT, ntohs(sk->inet_sport))) + if (nla_put_u16(skb, OVS_TUNNEL_ATTR_DST_PORT, geneve_port->port_no)) return -EMSGSIZE; return 0; } -static void geneve_tnl_destroy(struct vport *vport) +static int geneve_get_egress_tun_info(struct vport *vport, struct sk_buff *skb, + struct dp_upcall_info *upcall) { struct geneve_port *geneve_port = geneve_vport(vport); + struct net *net = ovs_dp_get_net(vport->dp); + __be16 dport = htons(geneve_port->port_no); + __be16 sport = udp_flow_src_port(net, skb, 1, USHRT_MAX, true); - geneve_sock_release(geneve_port->gs); - - ovs_vport_deferred_free(vport); + return ovs_tunnel_get_egress_info(upcall, ovs_dp_get_net(vport->dp), + skb, IPPROTO_UDP, sport, dport); } static struct vport *geneve_tnl_create(const struct vport_parms *parms) @@ -123,11 +69,11 @@ static struct vport *geneve_tnl_create(const struct vport_parms *parms) struct net *net = ovs_dp_get_net(parms->dp); struct nlattr *options = parms->options; struct geneve_port *geneve_port; - struct geneve_sock *gs; + struct net_device *dev; struct vport *vport; struct nlattr *a; - int err; u16 dst_port; + int err; if (!options) { err = -EINVAL; @@ -149,104 +95,40 @@ static struct vport *geneve_tnl_create(const struct vport_parms *parms) return vport; geneve_port = geneve_vport(vport); - strncpy(geneve_port->name, parms->name, IFNAMSIZ); + geneve_port->port_no = dst_port; - gs = geneve_sock_add(net, htons(dst_port), geneve_rcv, vport, true, 0); - if (IS_ERR(gs)) { + rtnl_lock(); + dev = geneve_dev_create_fb(net, parms->name, NET_NAME_USER, dst_port); + if (IS_ERR(dev)) { + rtnl_unlock(); ovs_vport_free(vport); - return (void *)gs; + return ERR_CAST(dev); } - geneve_port->gs = gs; + dev_change_flags(dev, dev->flags | IFF_UP); + rtnl_unlock(); return vport; error: return ERR_PTR(err); } -static int geneve_tnl_send(struct vport *vport, struct sk_buff *skb) +static struct vport *geneve_create(const struct vport_parms *parms) { - const struct ovs_key_ipv4_tunnel *tun_key; - struct ovs_tunnel_info *tun_info; - struct net *net = ovs_dp_get_net(vport->dp); - struct geneve_port *geneve_port = geneve_vport(vport); - __be16 dport = inet_sk(geneve_port->gs->sock->sk)->inet_sport; - __be16 sport; - struct rtable *rt; - struct flowi4 fl; - u8 vni[3], opts_len, *opts; - __be16 df; - int err; - - tun_info = OVS_CB(skb)->egress_tun_info; - if (unlikely(!tun_info)) { - err = -EINVAL; - goto error; - } - - tun_key = &tun_info->tunnel; - rt = ovs_tunnel_route_lookup(net, tun_key, skb->mark, &fl, IPPROTO_UDP); - if (IS_ERR(rt)) { - err = PTR_ERR(rt); - goto error; - } - - df = tun_key->tun_flags & TUNNEL_DONT_FRAGMENT ? htons(IP_DF) : 0; - sport = udp_flow_src_port(net, skb, 1, USHRT_MAX, true); - tunnel_id_to_vni(tun_key->tun_id, vni); - skb->ignore_df = 1; - - if (tun_key->tun_flags & TUNNEL_GENEVE_OPT) { - opts = (u8 *)tun_info->options; - opts_len = tun_info->options_len; - } else { - opts = NULL; - opts_len = 0; - } - - err = geneve_xmit_skb(geneve_port->gs, rt, skb, fl.saddr, - tun_key->ipv4_dst, tun_key->ipv4_tos, - tun_key->ipv4_ttl, df, sport, dport, - tun_key->tun_flags, vni, opts_len, opts, - !!(tun_key->tun_flags & TUNNEL_CSUM), false); - if (err < 0) - ip_rt_put(rt); - return err; - -error: - kfree_skb(skb); - return err; -} - -static const char *geneve_get_name(const struct vport *vport) -{ - struct geneve_port *geneve_port = geneve_vport(vport); - - return geneve_port->name; -} + struct vport *vport; -static int geneve_get_egress_tun_info(struct vport *vport, struct sk_buff *skb, - struct ovs_tunnel_info *egress_tun_info) -{ - struct geneve_port *geneve_port = geneve_vport(vport); - struct net *net = ovs_dp_get_net(vport->dp); - __be16 dport = inet_sk(geneve_port->gs->sock->sk)->inet_sport; - __be16 sport = udp_flow_src_port(net, skb, 1, USHRT_MAX, true); + vport = geneve_tnl_create(parms); + if (IS_ERR(vport)) + return vport; - /* Get tp_src and tp_dst, refert to geneve_build_header(). - */ - return ovs_tunnel_get_egress_info(egress_tun_info, - ovs_dp_get_net(vport->dp), - OVS_CB(skb)->egress_tun_info, - IPPROTO_UDP, skb->mark, sport, dport); + return ovs_netdev_link(vport, parms->name); } static struct vport_ops ovs_geneve_vport_ops = { .type = OVS_VPORT_TYPE_GENEVE, - .create = geneve_tnl_create, - .destroy = geneve_tnl_destroy, - .get_name = geneve_get_name, + .create = geneve_create, + .destroy = ovs_netdev_tunnel_destroy, .get_options = geneve_get_options, - .send = geneve_tnl_send, + .send = ovs_netdev_send, .owner = THIS_MODULE, .get_egress_tun_info = geneve_get_egress_tun_info, }; diff --git a/net/openvswitch/vport-gre.c b/net/openvswitch/vport-gre.c index f17ac9642f4e..4d24481669c9 100644 --- a/net/openvswitch/vport-gre.c +++ b/net/openvswitch/vport-gre.c @@ -45,253 +45,58 @@ #include "datapath.h" #include "vport.h" +#include "vport-netdev.h" static struct vport_ops ovs_gre_vport_ops; -/* Returns the least-significant 32 bits of a __be64. */ -static __be32 be64_get_low32(__be64 x) +static struct vport *gre_tnl_create(const struct vport_parms *parms) { -#ifdef __BIG_ENDIAN - return (__force __be32)x; -#else - return (__force __be32)((__force u64)x >> 32); -#endif -} - -static __be16 filter_tnl_flags(__be16 flags) -{ - return flags & (TUNNEL_CSUM | TUNNEL_KEY); -} - -static struct sk_buff *__build_header(struct sk_buff *skb, - int tunnel_hlen) -{ - struct tnl_ptk_info tpi; - const struct ovs_key_ipv4_tunnel *tun_key; - - tun_key = &OVS_CB(skb)->egress_tun_info->tunnel; - - skb = gre_handle_offloads(skb, !!(tun_key->tun_flags & TUNNEL_CSUM)); - if (IS_ERR(skb)) - return skb; - - tpi.flags = filter_tnl_flags(tun_key->tun_flags); - tpi.proto = htons(ETH_P_TEB); - tpi.key = be64_get_low32(tun_key->tun_id); - tpi.seq = 0; - gre_build_header(skb, &tpi, tunnel_hlen); - - return skb; -} - -static __be64 key_to_tunnel_id(__be32 key, __be32 seq) -{ -#ifdef __BIG_ENDIAN - return (__force __be64)((__force u64)seq << 32 | (__force u32)key); -#else - return (__force __be64)((__force u64)key << 32 | (__force u32)seq); -#endif -} - -/* Called with rcu_read_lock and BH disabled. */ -static int gre_rcv(struct sk_buff *skb, - const struct tnl_ptk_info *tpi) -{ - struct ovs_tunnel_info tun_info; - struct ovs_net *ovs_net; - struct vport *vport; - __be64 key; - - ovs_net = net_generic(dev_net(skb->dev), ovs_net_id); - vport = rcu_dereference(ovs_net->vport_net.gre_vport); - if (unlikely(!vport)) - return PACKET_REJECT; - - key = key_to_tunnel_id(tpi->key, tpi->seq); - ovs_flow_tun_info_init(&tun_info, ip_hdr(skb), 0, 0, key, - filter_tnl_flags(tpi->flags), NULL, 0); - - ovs_vport_receive(vport, skb, &tun_info); - return PACKET_RCVD; -} - -/* Called with rcu_read_lock and BH disabled. */ -static int gre_err(struct sk_buff *skb, u32 info, - const struct tnl_ptk_info *tpi) -{ - struct ovs_net *ovs_net; + struct net *net = ovs_dp_get_net(parms->dp); + struct net_device *dev; struct vport *vport; - ovs_net = net_generic(dev_net(skb->dev), ovs_net_id); - vport = rcu_dereference(ovs_net->vport_net.gre_vport); - - if (unlikely(!vport)) - return PACKET_REJECT; - else - return PACKET_RCVD; -} - -static int gre_tnl_send(struct vport *vport, struct sk_buff *skb) -{ - struct net *net = ovs_dp_get_net(vport->dp); - const struct ovs_key_ipv4_tunnel *tun_key; - struct flowi4 fl; - struct rtable *rt; - int min_headroom; - int tunnel_hlen; - __be16 df; - int err; - - if (unlikely(!OVS_CB(skb)->egress_tun_info)) { - err = -EINVAL; - goto err_free_skb; - } - - tun_key = &OVS_CB(skb)->egress_tun_info->tunnel; - rt = ovs_tunnel_route_lookup(net, tun_key, skb->mark, &fl, IPPROTO_GRE); - if (IS_ERR(rt)) { - err = PTR_ERR(rt); - goto err_free_skb; - } - - tunnel_hlen = ip_gre_calc_hlen(tun_key->tun_flags); - - min_headroom = LL_RESERVED_SPACE(rt->dst.dev) + rt->dst.header_len - + tunnel_hlen + sizeof(struct iphdr) - + (skb_vlan_tag_present(skb) ? VLAN_HLEN : 0); - if (skb_headroom(skb) < min_headroom || skb_header_cloned(skb)) { - int head_delta = SKB_DATA_ALIGN(min_headroom - - skb_headroom(skb) + - 16); - err = pskb_expand_head(skb, max_t(int, head_delta, 0), - 0, GFP_ATOMIC); - if (unlikely(err)) - goto err_free_rt; - } - - skb = vlan_hwaccel_push_inside(skb); - if (unlikely(!skb)) { - err = -ENOMEM; - goto err_free_rt; - } - - /* Push Tunnel header. */ - skb = __build_header(skb, tunnel_hlen); - if (IS_ERR(skb)) { - err = PTR_ERR(skb); - skb = NULL; - goto err_free_rt; + vport = ovs_vport_alloc(0, &ovs_gre_vport_ops, parms); + if (IS_ERR(vport)) + return vport; + + rtnl_lock(); + dev = gretap_fb_dev_create(net, parms->name, NET_NAME_USER); + if (IS_ERR(dev)) { + rtnl_unlock(); + ovs_vport_free(vport); + return ERR_CAST(dev); } - df = tun_key->tun_flags & TUNNEL_DONT_FRAGMENT ? - htons(IP_DF) : 0; - - skb->ignore_df = 1; - - return iptunnel_xmit(skb->sk, rt, skb, fl.saddr, - tun_key->ipv4_dst, IPPROTO_GRE, - tun_key->ipv4_tos, tun_key->ipv4_ttl, df, false); -err_free_rt: - ip_rt_put(rt); -err_free_skb: - kfree_skb(skb); - return err; -} - -static struct gre_cisco_protocol gre_protocol = { - .handler = gre_rcv, - .err_handler = gre_err, - .priority = 1, -}; - -static int gre_ports; -static int gre_init(void) -{ - int err; - - gre_ports++; - if (gre_ports > 1) - return 0; - - err = gre_cisco_register(&gre_protocol); - if (err) - pr_warn("cannot register gre protocol handler\n"); - - return err; -} - -static void gre_exit(void) -{ - gre_ports--; - if (gre_ports > 0) - return; - - gre_cisco_unregister(&gre_protocol); -} + dev_change_flags(dev, dev->flags | IFF_UP); + rtnl_unlock(); -static const char *gre_get_name(const struct vport *vport) -{ - return vport_priv(vport); + return vport; } static struct vport *gre_create(const struct vport_parms *parms) { - struct net *net = ovs_dp_get_net(parms->dp); - struct ovs_net *ovs_net; struct vport *vport; - int err; - - err = gre_init(); - if (err) - return ERR_PTR(err); - - ovs_net = net_generic(net, ovs_net_id); - if (ovsl_dereference(ovs_net->vport_net.gre_vport)) { - vport = ERR_PTR(-EEXIST); - goto error; - } - vport = ovs_vport_alloc(IFNAMSIZ, &ovs_gre_vport_ops, parms); + vport = gre_tnl_create(parms); if (IS_ERR(vport)) - goto error; - - strncpy(vport_priv(vport), parms->name, IFNAMSIZ); - rcu_assign_pointer(ovs_net->vport_net.gre_vport, vport); - return vport; - -error: - gre_exit(); - return vport; -} - -static void gre_tnl_destroy(struct vport *vport) -{ - struct net *net = ovs_dp_get_net(vport->dp); - struct ovs_net *ovs_net; - - ovs_net = net_generic(net, ovs_net_id); + return vport; - RCU_INIT_POINTER(ovs_net->vport_net.gre_vport, NULL); - ovs_vport_deferred_free(vport); - gre_exit(); + return ovs_netdev_link(vport, parms->name); } static int gre_get_egress_tun_info(struct vport *vport, struct sk_buff *skb, - struct ovs_tunnel_info *egress_tun_info) + struct dp_upcall_info *upcall) { - return ovs_tunnel_get_egress_info(egress_tun_info, - ovs_dp_get_net(vport->dp), - OVS_CB(skb)->egress_tun_info, - IPPROTO_GRE, skb->mark, 0, 0); + return ovs_tunnel_get_egress_info(upcall, ovs_dp_get_net(vport->dp), + skb, IPPROTO_GRE, 0, 0); } static struct vport_ops ovs_gre_vport_ops = { .type = OVS_VPORT_TYPE_GRE, .create = gre_create, - .destroy = gre_tnl_destroy, - .get_name = gre_get_name, - .send = gre_tnl_send, + .send = ovs_netdev_send, .get_egress_tun_info = gre_get_egress_tun_info, + .destroy = ovs_netdev_tunnel_destroy, .owner = THIS_MODULE, }; diff --git a/net/openvswitch/vport-internal_dev.c b/net/openvswitch/vport-internal_dev.c index 6a55f7105505..388b8a6bf112 100644 --- a/net/openvswitch/vport-internal_dev.c +++ b/net/openvswitch/vport-internal_dev.c @@ -43,35 +43,26 @@ static struct internal_dev *internal_dev_priv(struct net_device *netdev) return netdev_priv(netdev); } -/* This function is only called by the kernel network layer.*/ -static struct rtnl_link_stats64 *internal_dev_get_stats(struct net_device *netdev, - struct rtnl_link_stats64 *stats) -{ - struct vport *vport = ovs_internal_dev_get_vport(netdev); - struct ovs_vport_stats vport_stats; - - ovs_vport_get_stats(vport, &vport_stats); - - /* The tx and rx stats need to be swapped because the - * switch and host OS have opposite perspectives. */ - stats->rx_packets = vport_stats.tx_packets; - stats->tx_packets = vport_stats.rx_packets; - stats->rx_bytes = vport_stats.tx_bytes; - stats->tx_bytes = vport_stats.rx_bytes; - stats->rx_errors = vport_stats.tx_errors; - stats->tx_errors = vport_stats.rx_errors; - stats->rx_dropped = vport_stats.tx_dropped; - stats->tx_dropped = vport_stats.rx_dropped; - - return stats; -} - /* Called with rcu_read_lock_bh. */ static int internal_dev_xmit(struct sk_buff *skb, struct net_device *netdev) { + int len, err; + + len = skb->len; rcu_read_lock(); - ovs_vport_receive(internal_dev_priv(netdev)->vport, skb, NULL); + err = ovs_vport_receive(internal_dev_priv(netdev)->vport, skb, NULL); rcu_read_unlock(); + + if (likely(!err)) { + struct pcpu_sw_netstats *tstats = this_cpu_ptr(netdev->tstats); + + u64_stats_update_begin(&tstats->syncp); + tstats->tx_bytes += len; + tstats->tx_packets++; + u64_stats_update_end(&tstats->syncp); + } else { + netdev->stats.tx_errors++; + } return 0; } @@ -121,7 +112,6 @@ static const struct net_device_ops internal_dev_netdev_ops = { .ndo_start_xmit = internal_dev_xmit, .ndo_set_mac_address = eth_mac_addr, .ndo_change_mtu = internal_dev_change_mtu, - .ndo_get_stats64 = internal_dev_get_stats, }; static struct rtnl_link_ops internal_dev_link_ops __read_mostly = { @@ -135,7 +125,7 @@ static void do_setup(struct net_device *netdev) netdev->netdev_ops = &internal_dev_netdev_ops; netdev->priv_flags &= ~IFF_TX_SKB_SHARING; - netdev->priv_flags |= IFF_LIVE_ADDR_CHANGE; + netdev->priv_flags |= IFF_LIVE_ADDR_CHANGE | IFF_OPENVSWITCH; netdev->destructor = internal_dev_destructor; netdev->ethtool_ops = &internal_dev_ethtool_ops; netdev->rtnl_link_ops = &internal_dev_link_ops; @@ -156,49 +146,44 @@ static void do_setup(struct net_device *netdev) static struct vport *internal_dev_create(const struct vport_parms *parms) { struct vport *vport; - struct netdev_vport *netdev_vport; struct internal_dev *internal_dev; int err; - vport = ovs_vport_alloc(sizeof(struct netdev_vport), - &ovs_internal_vport_ops, parms); + vport = ovs_vport_alloc(0, &ovs_internal_vport_ops, parms); if (IS_ERR(vport)) { err = PTR_ERR(vport); goto error; } - netdev_vport = netdev_vport_priv(vport); - - netdev_vport->dev = alloc_netdev(sizeof(struct internal_dev), - parms->name, NET_NAME_UNKNOWN, - do_setup); - if (!netdev_vport->dev) { + vport->dev = alloc_netdev(sizeof(struct internal_dev), + parms->name, NET_NAME_UNKNOWN, do_setup); + if (!vport->dev) { err = -ENOMEM; goto error_free_vport; } - dev_net_set(netdev_vport->dev, ovs_dp_get_net(vport->dp)); - internal_dev = internal_dev_priv(netdev_vport->dev); + dev_net_set(vport->dev, ovs_dp_get_net(vport->dp)); + internal_dev = internal_dev_priv(vport->dev); internal_dev->vport = vport; /* Restrict bridge port to current netns. */ if (vport->port_no == OVSP_LOCAL) - netdev_vport->dev->features |= NETIF_F_NETNS_LOCAL; + vport->dev->features |= NETIF_F_NETNS_LOCAL; rtnl_lock(); - err = register_netdevice(netdev_vport->dev); + err = register_netdevice(vport->dev); if (err) goto error_free_netdev; - dev_set_promiscuity(netdev_vport->dev, 1); + dev_set_promiscuity(vport->dev, 1); rtnl_unlock(); - netif_start_queue(netdev_vport->dev); + netif_start_queue(vport->dev); return vport; error_free_netdev: rtnl_unlock(); - free_netdev(netdev_vport->dev); + free_netdev(vport->dev); error_free_vport: ovs_vport_free(vport); error: @@ -207,30 +192,27 @@ error: static void internal_dev_destroy(struct vport *vport) { - struct netdev_vport *netdev_vport = netdev_vport_priv(vport); - - netif_stop_queue(netdev_vport->dev); + netif_stop_queue(vport->dev); rtnl_lock(); - dev_set_promiscuity(netdev_vport->dev, -1); + dev_set_promiscuity(vport->dev, -1); /* unregister_netdevice() waits for an RCU grace period. */ - unregister_netdevice(netdev_vport->dev); + unregister_netdevice(vport->dev); rtnl_unlock(); } -static int internal_dev_recv(struct vport *vport, struct sk_buff *skb) +static void internal_dev_recv(struct vport *vport, struct sk_buff *skb) { - struct net_device *netdev = netdev_vport_priv(vport)->dev; - int len; + struct net_device *netdev = vport->dev; + struct pcpu_sw_netstats *stats; if (unlikely(!(netdev->flags & IFF_UP))) { kfree_skb(skb); - return 0; + netdev->stats.rx_dropped++; + return; } - len = skb->len; - skb_dst_drop(skb); nf_reset(skb); secpath_reset(skb); @@ -240,16 +222,19 @@ static int internal_dev_recv(struct vport *vport, struct sk_buff *skb) skb->protocol = eth_type_trans(skb, netdev); skb_postpull_rcsum(skb, eth_hdr(skb), ETH_HLEN); - netif_rx(skb); + stats = this_cpu_ptr(netdev->tstats); + u64_stats_update_begin(&stats->syncp); + stats->rx_packets++; + stats->rx_bytes += skb->len; + u64_stats_update_end(&stats->syncp); - return len; + netif_rx(skb); } static struct vport_ops ovs_internal_vport_ops = { .type = OVS_VPORT_TYPE_INTERNAL, .create = internal_dev_create, .destroy = internal_dev_destroy, - .get_name = ovs_netdev_get_name, .send = internal_dev_recv, }; diff --git a/net/openvswitch/vport-netdev.c b/net/openvswitch/vport-netdev.c index 33e6d6e2908f..f7e8dcce7ada 100644 --- a/net/openvswitch/vport-netdev.c +++ b/net/openvswitch/vport-netdev.c @@ -26,18 +26,24 @@ #include <linux/rtnetlink.h> #include <linux/skbuff.h> #include <linux/openvswitch.h> +#include <linux/export.h> -#include <net/llc.h> +#include <net/ip_tunnels.h> +#include <net/rtnetlink.h> #include "datapath.h" +#include "vport.h" #include "vport-internal_dev.h" #include "vport-netdev.h" static struct vport_ops ovs_netdev_vport_ops; /* Must be called with rcu_read_lock. */ -static void netdev_port_receive(struct vport *vport, struct sk_buff *skb) +static void netdev_port_receive(struct sk_buff *skb) { + struct vport *vport; + + vport = ovs_netdev_get_vport(skb->dev); if (unlikely(!vport)) goto error; @@ -53,10 +59,8 @@ static void netdev_port_receive(struct vport *vport, struct sk_buff *skb) skb_push(skb, ETH_HLEN); ovs_skb_postpush_rcsum(skb, skb->data, ETH_HLEN); - - ovs_vport_receive(vport, skb, NULL); + ovs_vport_receive(vport, skb, skb_tunnel_info(skb)); return; - error: kfree_skb(skb); } @@ -65,15 +69,11 @@ error: static rx_handler_result_t netdev_frame_hook(struct sk_buff **pskb) { struct sk_buff *skb = *pskb; - struct vport *vport; if (unlikely(skb->pkt_type == PACKET_LOOPBACK)) return RX_HANDLER_PASS; - vport = ovs_netdev_get_vport(skb->dev); - - netdev_port_receive(vport, skb); - + netdev_port_receive(skb); return RX_HANDLER_CONSUMED; } @@ -83,105 +83,112 @@ static struct net_device *get_dpdev(const struct datapath *dp) local = ovs_vport_ovsl(dp, OVSP_LOCAL); BUG_ON(!local); - return netdev_vport_priv(local)->dev; + return local->dev; } -static struct vport *netdev_create(const struct vport_parms *parms) +struct vport *ovs_netdev_link(struct vport *vport, const char *name) { - struct vport *vport; - struct netdev_vport *netdev_vport; int err; - vport = ovs_vport_alloc(sizeof(struct netdev_vport), - &ovs_netdev_vport_ops, parms); - if (IS_ERR(vport)) { - err = PTR_ERR(vport); - goto error; - } - - netdev_vport = netdev_vport_priv(vport); - - netdev_vport->dev = dev_get_by_name(ovs_dp_get_net(vport->dp), parms->name); - if (!netdev_vport->dev) { + vport->dev = dev_get_by_name(ovs_dp_get_net(vport->dp), name); + if (!vport->dev) { err = -ENODEV; goto error_free_vport; } - if (netdev_vport->dev->flags & IFF_LOOPBACK || - netdev_vport->dev->type != ARPHRD_ETHER || - ovs_is_internal_dev(netdev_vport->dev)) { + if (vport->dev->flags & IFF_LOOPBACK || + vport->dev->type != ARPHRD_ETHER || + ovs_is_internal_dev(vport->dev)) { err = -EINVAL; goto error_put; } rtnl_lock(); - err = netdev_master_upper_dev_link(netdev_vport->dev, + err = netdev_master_upper_dev_link(vport->dev, get_dpdev(vport->dp)); if (err) goto error_unlock; - err = netdev_rx_handler_register(netdev_vport->dev, netdev_frame_hook, + err = netdev_rx_handler_register(vport->dev, netdev_frame_hook, vport); if (err) goto error_master_upper_dev_unlink; - dev_disable_lro(netdev_vport->dev); - dev_set_promiscuity(netdev_vport->dev, 1); - netdev_vport->dev->priv_flags |= IFF_OVS_DATAPATH; + dev_disable_lro(vport->dev); + dev_set_promiscuity(vport->dev, 1); + vport->dev->priv_flags |= IFF_OVS_DATAPATH; rtnl_unlock(); return vport; error_master_upper_dev_unlink: - netdev_upper_dev_unlink(netdev_vport->dev, get_dpdev(vport->dp)); + netdev_upper_dev_unlink(vport->dev, get_dpdev(vport->dp)); error_unlock: rtnl_unlock(); error_put: - dev_put(netdev_vport->dev); + dev_put(vport->dev); error_free_vport: ovs_vport_free(vport); -error: return ERR_PTR(err); } +EXPORT_SYMBOL_GPL(ovs_netdev_link); -static void free_port_rcu(struct rcu_head *rcu) +static struct vport *netdev_create(const struct vport_parms *parms) { - struct netdev_vport *netdev_vport = container_of(rcu, - struct netdev_vport, rcu); + struct vport *vport; + + vport = ovs_vport_alloc(0, &ovs_netdev_vport_ops, parms); + if (IS_ERR(vport)) + return vport; - dev_put(netdev_vport->dev); - ovs_vport_free(vport_from_priv(netdev_vport)); + return ovs_netdev_link(vport, parms->name); } -void ovs_netdev_detach_dev(struct vport *vport) +static void vport_netdev_free(struct rcu_head *rcu) { - struct netdev_vport *netdev_vport = netdev_vport_priv(vport); + struct vport *vport = container_of(rcu, struct vport, rcu); + + if (vport->dev) + dev_put(vport->dev); + ovs_vport_free(vport); +} +void ovs_netdev_detach_dev(struct vport *vport) +{ ASSERT_RTNL(); - netdev_vport->dev->priv_flags &= ~IFF_OVS_DATAPATH; - netdev_rx_handler_unregister(netdev_vport->dev); - netdev_upper_dev_unlink(netdev_vport->dev, - netdev_master_upper_dev_get(netdev_vport->dev)); - dev_set_promiscuity(netdev_vport->dev, -1); + vport->dev->priv_flags &= ~IFF_OVS_DATAPATH; + netdev_rx_handler_unregister(vport->dev); + netdev_upper_dev_unlink(vport->dev, + netdev_master_upper_dev_get(vport->dev)); + dev_set_promiscuity(vport->dev, -1); } +EXPORT_SYMBOL_GPL(ovs_netdev_detach_dev); static void netdev_destroy(struct vport *vport) { - struct netdev_vport *netdev_vport = netdev_vport_priv(vport); - rtnl_lock(); - if (netdev_vport->dev->priv_flags & IFF_OVS_DATAPATH) + if (vport->dev->priv_flags & IFF_OVS_DATAPATH) ovs_netdev_detach_dev(vport); rtnl_unlock(); - call_rcu(&netdev_vport->rcu, free_port_rcu); + call_rcu(&vport->rcu, vport_netdev_free); } -const char *ovs_netdev_get_name(const struct vport *vport) +void ovs_netdev_tunnel_destroy(struct vport *vport) { - const struct netdev_vport *netdev_vport = netdev_vport_priv(vport); - return netdev_vport->dev->name; + rtnl_lock(); + if (vport->dev->priv_flags & IFF_OVS_DATAPATH) + ovs_netdev_detach_dev(vport); + + /* Early release so we can unregister the device */ + dev_put(vport->dev); + rtnl_delete_link(vport->dev); + vport->dev = NULL; + rtnl_unlock(); + + call_rcu(&vport->rcu, vport_netdev_free); } +EXPORT_SYMBOL_GPL(ovs_netdev_tunnel_destroy); static unsigned int packet_length(const struct sk_buff *skb) { @@ -193,29 +200,26 @@ static unsigned int packet_length(const struct sk_buff *skb) return length; } -static int netdev_send(struct vport *vport, struct sk_buff *skb) +void ovs_netdev_send(struct vport *vport, struct sk_buff *skb) { - struct netdev_vport *netdev_vport = netdev_vport_priv(vport); - int mtu = netdev_vport->dev->mtu; - int len; + int mtu = vport->dev->mtu; if (unlikely(packet_length(skb) > mtu && !skb_is_gso(skb))) { net_warn_ratelimited("%s: dropped over-mtu packet: %d > %d\n", - netdev_vport->dev->name, + vport->dev->name, packet_length(skb), mtu); + vport->dev->stats.tx_errors++; goto drop; } - skb->dev = netdev_vport->dev; - len = skb->len; + skb->dev = vport->dev; dev_queue_xmit(skb); - - return len; + return; drop: kfree_skb(skb); - return 0; } +EXPORT_SYMBOL_GPL(ovs_netdev_send); /* Returns null if this device is not attached to a datapath. */ struct vport *ovs_netdev_get_vport(struct net_device *dev) @@ -231,8 +235,7 @@ static struct vport_ops ovs_netdev_vport_ops = { .type = OVS_VPORT_TYPE_NETDEV, .create = netdev_create, .destroy = netdev_destroy, - .get_name = ovs_netdev_get_name, - .send = netdev_send, + .send = ovs_netdev_send, }; int __init ovs_netdev_init(void) diff --git a/net/openvswitch/vport-netdev.h b/net/openvswitch/vport-netdev.h index 6f7038e79c52..bf22fcedbc69 100644 --- a/net/openvswitch/vport-netdev.h +++ b/net/openvswitch/vport-netdev.h @@ -26,22 +26,12 @@ struct vport *ovs_netdev_get_vport(struct net_device *dev); -struct netdev_vport { - struct rcu_head rcu; - - struct net_device *dev; -}; - -static inline struct netdev_vport * -netdev_vport_priv(const struct vport *vport) -{ - return vport_priv(vport); -} - -const char *ovs_netdev_get_name(const struct vport *); +struct vport *ovs_netdev_link(struct vport *vport, const char *name); +void ovs_netdev_send(struct vport *vport, struct sk_buff *skb); void ovs_netdev_detach_dev(struct vport *); int __init ovs_netdev_init(void); void ovs_netdev_exit(void); +void ovs_netdev_tunnel_destroy(struct vport *vport); #endif /* vport_netdev.h */ diff --git a/net/openvswitch/vport-vxlan.c b/net/openvswitch/vport-vxlan.c index 6d39766e7828..c11413d5075f 100644 --- a/net/openvswitch/vport-vxlan.c +++ b/net/openvswitch/vport-vxlan.c @@ -17,94 +17,37 @@ * 02110-1301, USA */ -#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt - -#include <linux/in.h> -#include <linux/ip.h> -#include <linux/net.h> -#include <linux/rculist.h> -#include <linux/udp.h> +#include <linux/kernel.h> +#include <linux/skbuff.h> +#include <linux/openvswitch.h> #include <linux/module.h> - -#include <net/icmp.h> -#include <net/ip.h> #include <net/udp.h> #include <net/ip_tunnels.h> #include <net/rtnetlink.h> -#include <net/route.h> -#include <net/dsfield.h> -#include <net/inet_ecn.h> -#include <net/net_namespace.h> -#include <net/netns/generic.h> #include <net/vxlan.h> #include "datapath.h" #include "vport.h" -#include "vport-vxlan.h" - -/** - * struct vxlan_port - Keeps track of open UDP ports - * @vs: vxlan_sock created for the port. - * @name: vport name. - */ -struct vxlan_port { - struct vxlan_sock *vs; - char name[IFNAMSIZ]; - u32 exts; /* VXLAN_F_* in <net/vxlan.h> */ -}; - -static struct vport_ops ovs_vxlan_vport_ops; +#include "vport-netdev.h" -static inline struct vxlan_port *vxlan_vport(const struct vport *vport) -{ - return vport_priv(vport); -} - -/* Called with rcu_read_lock and BH disabled. */ -static void vxlan_rcv(struct vxlan_sock *vs, struct sk_buff *skb, - struct vxlan_metadata *md) -{ - struct ovs_tunnel_info tun_info; - struct vxlan_port *vxlan_port; - struct vport *vport = vs->data; - struct iphdr *iph; - struct ovs_vxlan_opts opts = { - .gbp = md->gbp, - }; - __be64 key; - __be16 flags; - - flags = TUNNEL_KEY | (udp_hdr(skb)->check != 0 ? TUNNEL_CSUM : 0); - vxlan_port = vxlan_vport(vport); - if (vxlan_port->exts & VXLAN_F_GBP && md->gbp) - flags |= TUNNEL_VXLAN_OPT; - - /* Save outer tunnel values */ - iph = ip_hdr(skb); - key = cpu_to_be64(ntohl(md->vni) >> 8); - ovs_flow_tun_info_init(&tun_info, iph, - udp_hdr(skb)->source, udp_hdr(skb)->dest, - key, flags, &opts, sizeof(opts)); - - ovs_vport_receive(vport, skb, &tun_info); -} +static struct vport_ops ovs_vxlan_netdev_vport_ops; static int vxlan_get_options(const struct vport *vport, struct sk_buff *skb) { - struct vxlan_port *vxlan_port = vxlan_vport(vport); - __be16 dst_port = inet_sk(vxlan_port->vs->sock->sk)->inet_sport; + struct vxlan_dev *vxlan = netdev_priv(vport->dev); + __be16 dst_port = vxlan->cfg.dst_port; if (nla_put_u16(skb, OVS_TUNNEL_ATTR_DST_PORT, ntohs(dst_port))) return -EMSGSIZE; - if (vxlan_port->exts) { + if (vxlan->flags & VXLAN_F_GBP) { struct nlattr *exts; exts = nla_nest_start(skb, OVS_TUNNEL_ATTR_EXTENSION); if (!exts) return -EMSGSIZE; - if (vxlan_port->exts & VXLAN_F_GBP && + if (vxlan->flags & VXLAN_F_GBP && nla_put_flag(skb, OVS_VXLAN_EXT_GBP)) return -EMSGSIZE; @@ -114,23 +57,14 @@ static int vxlan_get_options(const struct vport *vport, struct sk_buff *skb) return 0; } -static void vxlan_tnl_destroy(struct vport *vport) -{ - struct vxlan_port *vxlan_port = vxlan_vport(vport); - - vxlan_sock_release(vxlan_port->vs); - - ovs_vport_deferred_free(vport); -} - -static const struct nla_policy exts_policy[OVS_VXLAN_EXT_MAX+1] = { +static const struct nla_policy exts_policy[OVS_VXLAN_EXT_MAX + 1] = { [OVS_VXLAN_EXT_GBP] = { .type = NLA_FLAG, }, }; -static int vxlan_configure_exts(struct vport *vport, struct nlattr *attr) +static int vxlan_configure_exts(struct vport *vport, struct nlattr *attr, + struct vxlan_config *conf) { - struct nlattr *exts[OVS_VXLAN_EXT_MAX+1]; - struct vxlan_port *vxlan_port; + struct nlattr *exts[OVS_VXLAN_EXT_MAX + 1]; int err; if (nla_len(attr) < sizeof(struct nlattr)) @@ -140,10 +74,8 @@ static int vxlan_configure_exts(struct vport *vport, struct nlattr *attr) if (err < 0) return err; - vxlan_port = vxlan_vport(vport); - if (exts[OVS_VXLAN_EXT_GBP]) - vxlan_port->exts |= VXLAN_F_GBP; + conf->flags |= VXLAN_F_GBP; return 0; } @@ -152,128 +84,74 @@ static struct vport *vxlan_tnl_create(const struct vport_parms *parms) { struct net *net = ovs_dp_get_net(parms->dp); struct nlattr *options = parms->options; - struct vxlan_port *vxlan_port; - struct vxlan_sock *vs; + struct net_device *dev; struct vport *vport; struct nlattr *a; - u16 dst_port; int err; + struct vxlan_config conf = { + .no_share = true, + .flags = VXLAN_F_COLLECT_METADATA, + }; if (!options) { err = -EINVAL; goto error; } + a = nla_find_nested(options, OVS_TUNNEL_ATTR_DST_PORT); if (a && nla_len(a) == sizeof(u16)) { - dst_port = nla_get_u16(a); + conf.dst_port = htons(nla_get_u16(a)); } else { /* Require destination port from userspace. */ err = -EINVAL; goto error; } - vport = ovs_vport_alloc(sizeof(struct vxlan_port), - &ovs_vxlan_vport_ops, parms); + vport = ovs_vport_alloc(0, &ovs_vxlan_netdev_vport_ops, parms); if (IS_ERR(vport)) return vport; - vxlan_port = vxlan_vport(vport); - strncpy(vxlan_port->name, parms->name, IFNAMSIZ); - a = nla_find_nested(options, OVS_TUNNEL_ATTR_EXTENSION); if (a) { - err = vxlan_configure_exts(vport, a); + err = vxlan_configure_exts(vport, a, &conf); if (err) { ovs_vport_free(vport); goto error; } } - vs = vxlan_sock_add(net, htons(dst_port), vxlan_rcv, vport, true, - vxlan_port->exts); - if (IS_ERR(vs)) { + rtnl_lock(); + dev = vxlan_dev_create(net, parms->name, NET_NAME_USER, &conf); + if (IS_ERR(dev)) { + rtnl_unlock(); ovs_vport_free(vport); - return (void *)vs; + return ERR_CAST(dev); } - vxlan_port->vs = vs; + dev_change_flags(dev, dev->flags | IFF_UP); + rtnl_unlock(); return vport; - error: return ERR_PTR(err); } -static int vxlan_ext_gbp(struct sk_buff *skb) +static struct vport *vxlan_create(const struct vport_parms *parms) { - const struct ovs_tunnel_info *tun_info; - const struct ovs_vxlan_opts *opts; - - tun_info = OVS_CB(skb)->egress_tun_info; - opts = tun_info->options; - - if (tun_info->tunnel.tun_flags & TUNNEL_VXLAN_OPT && - tun_info->options_len >= sizeof(*opts)) - return opts->gbp; - else - return 0; -} - -static int vxlan_tnl_send(struct vport *vport, struct sk_buff *skb) -{ - struct net *net = ovs_dp_get_net(vport->dp); - struct vxlan_port *vxlan_port = vxlan_vport(vport); - struct sock *sk = vxlan_port->vs->sock->sk; - __be16 dst_port = inet_sk(sk)->inet_sport; - const struct ovs_key_ipv4_tunnel *tun_key; - struct vxlan_metadata md = {0}; - struct rtable *rt; - struct flowi4 fl; - __be16 src_port; - __be16 df; - int err; - u32 vxflags; - - if (unlikely(!OVS_CB(skb)->egress_tun_info)) { - err = -EINVAL; - goto error; - } - - tun_key = &OVS_CB(skb)->egress_tun_info->tunnel; - rt = ovs_tunnel_route_lookup(net, tun_key, skb->mark, &fl, IPPROTO_UDP); - if (IS_ERR(rt)) { - err = PTR_ERR(rt); - goto error; - } - - df = tun_key->tun_flags & TUNNEL_DONT_FRAGMENT ? - htons(IP_DF) : 0; + struct vport *vport; - skb->ignore_df = 1; + vport = vxlan_tnl_create(parms); + if (IS_ERR(vport)) + return vport; - src_port = udp_flow_src_port(net, skb, 0, 0, true); - md.vni = htonl(be64_to_cpu(tun_key->tun_id) << 8); - md.gbp = vxlan_ext_gbp(skb); - vxflags = vxlan_port->exts | - (tun_key->tun_flags & TUNNEL_CSUM ? VXLAN_F_UDP_CSUM : 0); - - err = vxlan_xmit_skb(rt, sk, skb, fl.saddr, tun_key->ipv4_dst, - tun_key->ipv4_tos, tun_key->ipv4_ttl, df, - src_port, dst_port, - &md, false, vxflags); - if (err < 0) - ip_rt_put(rt); - return err; -error: - kfree_skb(skb); - return err; + return ovs_netdev_link(vport, parms->name); } static int vxlan_get_egress_tun_info(struct vport *vport, struct sk_buff *skb, - struct ovs_tunnel_info *egress_tun_info) + struct dp_upcall_info *upcall) { + struct vxlan_dev *vxlan = netdev_priv(vport->dev); struct net *net = ovs_dp_get_net(vport->dp); - struct vxlan_port *vxlan_port = vxlan_vport(vport); - __be16 dst_port = inet_sk(vxlan_port->vs->sock->sk)->inet_sport; + __be16 dst_port = vxlan_dev_dst_port(vxlan); __be16 src_port; int port_min; int port_max; @@ -281,37 +159,28 @@ static int vxlan_get_egress_tun_info(struct vport *vport, struct sk_buff *skb, inet_get_local_port_range(net, &port_min, &port_max); src_port = udp_flow_src_port(net, skb, 0, 0, true); - return ovs_tunnel_get_egress_info(egress_tun_info, net, - OVS_CB(skb)->egress_tun_info, - IPPROTO_UDP, skb->mark, + return ovs_tunnel_get_egress_info(upcall, net, + skb, IPPROTO_UDP, src_port, dst_port); } -static const char *vxlan_get_name(const struct vport *vport) -{ - struct vxlan_port *vxlan_port = vxlan_vport(vport); - return vxlan_port->name; -} - -static struct vport_ops ovs_vxlan_vport_ops = { - .type = OVS_VPORT_TYPE_VXLAN, - .create = vxlan_tnl_create, - .destroy = vxlan_tnl_destroy, - .get_name = vxlan_get_name, - .get_options = vxlan_get_options, - .send = vxlan_tnl_send, +static struct vport_ops ovs_vxlan_netdev_vport_ops = { + .type = OVS_VPORT_TYPE_VXLAN, + .create = vxlan_create, + .destroy = ovs_netdev_tunnel_destroy, + .get_options = vxlan_get_options, + .send = ovs_netdev_send, .get_egress_tun_info = vxlan_get_egress_tun_info, - .owner = THIS_MODULE, }; static int __init ovs_vxlan_tnl_init(void) { - return ovs_vport_ops_register(&ovs_vxlan_vport_ops); + return ovs_vport_ops_register(&ovs_vxlan_netdev_vport_ops); } static void __exit ovs_vxlan_tnl_exit(void) { - ovs_vport_ops_unregister(&ovs_vxlan_vport_ops); + ovs_vport_ops_unregister(&ovs_vxlan_netdev_vport_ops); } module_init(ovs_vxlan_tnl_init); diff --git a/net/openvswitch/vport-vxlan.h b/net/openvswitch/vport-vxlan.h deleted file mode 100644 index 4b08233e73d5..000000000000 --- a/net/openvswitch/vport-vxlan.h +++ /dev/null @@ -1,11 +0,0 @@ -#ifndef VPORT_VXLAN_H -#define VPORT_VXLAN_H 1 - -#include <linux/kernel.h> -#include <linux/types.h> - -struct ovs_vxlan_opts { - __u32 gbp; -}; - -#endif diff --git a/net/openvswitch/vport.c b/net/openvswitch/vport.c index 067a3fff1d2c..dc81dc619aa2 100644 --- a/net/openvswitch/vport.c +++ b/net/openvswitch/vport.c @@ -34,9 +34,6 @@ #include "vport.h" #include "vport-internal_dev.h" -static void ovs_vport_record_error(struct vport *, - enum vport_err_type err_type); - static LIST_HEAD(vport_ops_list); /* Protected by RCU read lock for reading, ovs_mutex for writing. */ @@ -113,7 +110,7 @@ struct vport *ovs_vport_locate(const struct net *net, const char *name) struct vport *vport; hlist_for_each_entry_rcu(vport, bucket, hash_node) - if (!strcmp(name, vport->ops->get_name(vport)) && + if (!strcmp(name, ovs_vport_name(vport)) && net_eq(ovs_dp_get_net(vport->dp), net)) return vport; @@ -157,12 +154,6 @@ struct vport *ovs_vport_alloc(int priv_size, const struct vport_ops *ops, return ERR_PTR(-EINVAL); } - vport->percpu_stats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats); - if (!vport->percpu_stats) { - kfree(vport); - return ERR_PTR(-ENOMEM); - } - return vport; } EXPORT_SYMBOL_GPL(ovs_vport_alloc); @@ -183,7 +174,6 @@ void ovs_vport_free(struct vport *vport) * it is safe to use raw dereference. */ kfree(rcu_dereference_raw(vport->upcall_portids)); - free_percpu(vport->percpu_stats); kfree(vport); } EXPORT_SYMBOL_GPL(ovs_vport_free); @@ -226,7 +216,7 @@ struct vport *ovs_vport_add(const struct vport_parms *parms) } bucket = hash_bucket(ovs_dp_get_net(vport->dp), - vport->ops->get_name(vport)); + ovs_vport_name(vport)); hlist_add_head_rcu(&vport->hash_node, bucket); return vport; } @@ -290,30 +280,24 @@ void ovs_vport_del(struct vport *vport) */ void ovs_vport_get_stats(struct vport *vport, struct ovs_vport_stats *stats) { + struct net_device *dev = vport->dev; int i; memset(stats, 0, sizeof(*stats)); + stats->rx_errors = dev->stats.rx_errors; + stats->tx_errors = dev->stats.tx_errors; + stats->tx_dropped = dev->stats.tx_dropped; + stats->rx_dropped = dev->stats.rx_dropped; - /* We potentially have 2 sources of stats that need to be combined: - * those we have collected (split into err_stats and percpu_stats) from - * set_stats() and device error stats from netdev->get_stats() (for - * errors that happen downstream and therefore aren't reported through - * our vport_record_error() function). - * Stats from first source are reported by ovs (OVS_VPORT_ATTR_STATS). - * netdev-stats can be directly read over netlink-ioctl. - */ - - stats->rx_errors = atomic_long_read(&vport->err_stats.rx_errors); - stats->tx_errors = atomic_long_read(&vport->err_stats.tx_errors); - stats->tx_dropped = atomic_long_read(&vport->err_stats.tx_dropped); - stats->rx_dropped = atomic_long_read(&vport->err_stats.rx_dropped); + stats->rx_dropped += atomic_long_read(&dev->rx_dropped); + stats->tx_dropped += atomic_long_read(&dev->tx_dropped); for_each_possible_cpu(i) { const struct pcpu_sw_netstats *percpu_stats; struct pcpu_sw_netstats local_stats; unsigned int start; - percpu_stats = per_cpu_ptr(vport->percpu_stats, i); + percpu_stats = per_cpu_ptr(dev->tstats, i); do { start = u64_stats_fetch_begin_irq(&percpu_stats->syncp); @@ -468,94 +452,25 @@ u32 ovs_vport_find_upcall_portid(const struct vport *vport, struct sk_buff *skb) * Must be called with rcu_read_lock. The packet cannot be shared and * skb->data should point to the Ethernet header. */ -void ovs_vport_receive(struct vport *vport, struct sk_buff *skb, - const struct ovs_tunnel_info *tun_info) +int ovs_vport_receive(struct vport *vport, struct sk_buff *skb, + const struct ip_tunnel_info *tun_info) { - struct pcpu_sw_netstats *stats; struct sw_flow_key key; int error; - stats = this_cpu_ptr(vport->percpu_stats); - u64_stats_update_begin(&stats->syncp); - stats->rx_packets++; - stats->rx_bytes += skb->len + - (skb_vlan_tag_present(skb) ? VLAN_HLEN : 0); - u64_stats_update_end(&stats->syncp); - OVS_CB(skb)->input_vport = vport; - OVS_CB(skb)->egress_tun_info = NULL; + OVS_CB(skb)->mru = 0; /* Extract flow from 'skb' into 'key'. */ error = ovs_flow_key_extract(tun_info, skb, &key); if (unlikely(error)) { kfree_skb(skb); - return; + return error; } ovs_dp_process_packet(skb, &key); + return 0; } EXPORT_SYMBOL_GPL(ovs_vport_receive); -/** - * ovs_vport_send - send a packet on a device - * - * @vport: vport on which to send the packet - * @skb: skb to send - * - * Sends the given packet and returns the length of data sent. Either ovs - * lock or rcu_read_lock must be held. - */ -int ovs_vport_send(struct vport *vport, struct sk_buff *skb) -{ - int sent = vport->ops->send(vport, skb); - - if (likely(sent > 0)) { - struct pcpu_sw_netstats *stats; - - stats = this_cpu_ptr(vport->percpu_stats); - - u64_stats_update_begin(&stats->syncp); - stats->tx_packets++; - stats->tx_bytes += sent; - u64_stats_update_end(&stats->syncp); - } else if (sent < 0) { - ovs_vport_record_error(vport, VPORT_E_TX_ERROR); - } else { - ovs_vport_record_error(vport, VPORT_E_TX_DROPPED); - } - return sent; -} - -/** - * ovs_vport_record_error - indicate device error to generic stats layer - * - * @vport: vport that encountered the error - * @err_type: one of enum vport_err_type types to indicate the error type - * - * If using the vport generic stats layer indicate that an error of the given - * type has occurred. - */ -static void ovs_vport_record_error(struct vport *vport, - enum vport_err_type err_type) -{ - switch (err_type) { - case VPORT_E_RX_DROPPED: - atomic_long_inc(&vport->err_stats.rx_dropped); - break; - - case VPORT_E_RX_ERROR: - atomic_long_inc(&vport->err_stats.rx_errors); - break; - - case VPORT_E_TX_DROPPED: - atomic_long_inc(&vport->err_stats.tx_dropped); - break; - - case VPORT_E_TX_ERROR: - atomic_long_inc(&vport->err_stats.tx_errors); - break; - } - -} - static void free_vport_rcu(struct rcu_head *rcu) { struct vport *vport = container_of(rcu, struct vport, rcu); @@ -572,22 +487,26 @@ void ovs_vport_deferred_free(struct vport *vport) } EXPORT_SYMBOL_GPL(ovs_vport_deferred_free); -int ovs_tunnel_get_egress_info(struct ovs_tunnel_info *egress_tun_info, +int ovs_tunnel_get_egress_info(struct dp_upcall_info *upcall, struct net *net, - const struct ovs_tunnel_info *tun_info, + struct sk_buff *skb, u8 ipproto, - u32 skb_mark, __be16 tp_src, __be16 tp_dst) { - const struct ovs_key_ipv4_tunnel *tun_key; + struct ip_tunnel_info *egress_tun_info = upcall->egress_tun_info; + const struct ip_tunnel_info *tun_info = skb_tunnel_info(skb); + const struct ip_tunnel_key *tun_key; + u32 skb_mark = skb->mark; struct rtable *rt; struct flowi4 fl; if (unlikely(!tun_info)) return -EINVAL; + if (ip_tunnel_info_af(tun_info) != AF_INET) + return -EINVAL; - tun_key = &tun_info->tunnel; + tun_key = &tun_info->key; /* Route lookup to get srouce IP address. * The process may need to be changed if the corresponding process @@ -602,26 +521,26 @@ int ovs_tunnel_get_egress_info(struct ovs_tunnel_info *egress_tun_info, /* Generate egress_tun_info based on tun_info, * saddr, tp_src and tp_dst */ - __ovs_flow_tun_info_init(egress_tun_info, - fl.saddr, tun_key->ipv4_dst, - tun_key->ipv4_tos, - tun_key->ipv4_ttl, - tp_src, tp_dst, - tun_key->tun_id, - tun_key->tun_flags, - tun_info->options, - tun_info->options_len); - + ip_tunnel_key_init(&egress_tun_info->key, + fl.saddr, tun_key->u.ipv4.dst, + tun_key->tos, + tun_key->ttl, + tp_src, tp_dst, + tun_key->tun_id, + tun_key->tun_flags); + egress_tun_info->options_len = tun_info->options_len; + egress_tun_info->mode = tun_info->mode; + upcall->egress_tun_opts = ip_tunnel_info_opts(egress_tun_info); return 0; } EXPORT_SYMBOL_GPL(ovs_tunnel_get_egress_info); int ovs_vport_get_egress_tun_info(struct vport *vport, struct sk_buff *skb, - struct ovs_tunnel_info *info) + struct dp_upcall_info *upcall) { /* get_egress_tun_info() is only implemented on tunnel ports. */ if (unlikely(!vport->ops->get_egress_tun_info)) return -EINVAL; - return vport->ops->get_egress_tun_info(vport, skb, info); + return vport->ops->get_egress_tun_info(vport, skb, upcall); } diff --git a/net/openvswitch/vport.h b/net/openvswitch/vport.h index bc85331a6c60..a413f3ae6a7b 100644 --- a/net/openvswitch/vport.h +++ b/net/openvswitch/vport.h @@ -27,6 +27,7 @@ #include <linux/skbuff.h> #include <linux/spinlock.h> #include <linux/u64_stats_sync.h> +#include <net/route.h> #include "datapath.h" @@ -35,10 +36,6 @@ struct vport_parms; /* The following definitions are for users of the vport subsytem: */ -struct vport_net { - struct vport __rcu *gre_vport; -}; - int ovs_vport_init(void); void ovs_vport_exit(void); @@ -56,26 +53,16 @@ int ovs_vport_set_upcall_portids(struct vport *, const struct nlattr *pids); int ovs_vport_get_upcall_portids(const struct vport *, struct sk_buff *); u32 ovs_vport_find_upcall_portid(const struct vport *, struct sk_buff *); -int ovs_vport_send(struct vport *, struct sk_buff *); - -int ovs_tunnel_get_egress_info(struct ovs_tunnel_info *egress_tun_info, +int ovs_tunnel_get_egress_info(struct dp_upcall_info *upcall, struct net *net, - const struct ovs_tunnel_info *tun_info, + struct sk_buff *, u8 ipproto, - u32 skb_mark, __be16 tp_src, __be16 tp_dst); -int ovs_vport_get_egress_tun_info(struct vport *vport, struct sk_buff *skb, - struct ovs_tunnel_info *info); -/* The following definitions are for implementers of vport devices: */ +int ovs_vport_get_egress_tun_info(struct vport *vport, struct sk_buff *skb, + struct dp_upcall_info *upcall); -struct vport_err_stats { - atomic_long_t rx_dropped; - atomic_long_t rx_errors; - atomic_long_t tx_dropped; - atomic_long_t tx_errors; -}; /** * struct vport_portids - array of netlink portids of a vport. * must be protected by rcu. @@ -101,12 +88,10 @@ struct vport_portids { * @hash_node: Element in @dev_table hash table in vport.c. * @dp_hash_node: Element in @datapath->ports hash table in datapath.c. * @ops: Class structure. - * @percpu_stats: Points to per-CPU statistics used and maintained by vport - * @err_stats: Points to error statistics used and maintained by vport * @detach_list: list used for detaching vport in net-exit call. */ struct vport { - struct rcu_head rcu; + struct net_device *dev; struct datapath *dp; struct vport_portids __rcu *upcall_portids; u16 port_no; @@ -115,10 +100,8 @@ struct vport { struct hlist_node dp_hash_node; const struct vport_ops *ops; - struct pcpu_sw_netstats __percpu *percpu_stats; - - struct vport_err_stats err_stats; struct list_head detach_list; + struct rcu_head rcu; }; /** @@ -155,8 +138,7 @@ struct vport_parms { * @get_options: Appends vport-specific attributes for the configuration of an * existing vport to a &struct sk_buff. May be %NULL for a vport that does not * have any configuration. - * @get_name: Get the device's name. - * @send: Send a packet on the device. Returns the length of the packet sent, + * @send: Send a packet on the device. * zero for dropped packets or negative for error. * @get_egress_tun_info: Get the egress tunnel 5-tuple and other info for * a packet. @@ -171,24 +153,14 @@ struct vport_ops { int (*set_options)(struct vport *, struct nlattr *); int (*get_options)(const struct vport *, struct sk_buff *); - /* Called with rcu_read_lock or ovs_mutex. */ - const char *(*get_name)(const struct vport *); - - int (*send)(struct vport *, struct sk_buff *); + void (*send)(struct vport *, struct sk_buff *); int (*get_egress_tun_info)(struct vport *, struct sk_buff *, - struct ovs_tunnel_info *); + struct dp_upcall_info *upcall); struct module *owner; struct list_head list; }; -enum vport_err_type { - VPORT_E_RX_DROPPED, - VPORT_E_RX_ERROR, - VPORT_E_TX_DROPPED, - VPORT_E_TX_ERROR, -}; - struct vport *ovs_vport_alloc(int priv_size, const struct vport_ops *, const struct vport_parms *); void ovs_vport_free(struct vport *); @@ -225,8 +197,8 @@ static inline struct vport *vport_from_priv(void *priv) return (struct vport *)((u8 *)priv - ALIGN(sizeof(struct vport), VPORT_ALIGN)); } -void ovs_vport_receive(struct vport *, struct sk_buff *, - const struct ovs_tunnel_info *); +int ovs_vport_receive(struct vport *, struct sk_buff *, + const struct ip_tunnel_info *); static inline void ovs_skb_postpush_rcsum(struct sk_buff *skb, const void *start, unsigned int len) @@ -235,11 +207,16 @@ static inline void ovs_skb_postpush_rcsum(struct sk_buff *skb, skb->csum = csum_add(skb->csum, csum_partial(start, len, 0)); } +static inline const char *ovs_vport_name(struct vport *vport) +{ + return vport->dev->name; +} + int ovs_vport_ops_register(struct vport_ops *ops); void ovs_vport_ops_unregister(struct vport_ops *ops); static inline struct rtable *ovs_tunnel_route_lookup(struct net *net, - const struct ovs_key_ipv4_tunnel *key, + const struct ip_tunnel_key *key, u32 mark, struct flowi4 *fl, u8 protocol) @@ -247,13 +224,19 @@ static inline struct rtable *ovs_tunnel_route_lookup(struct net *net, struct rtable *rt; memset(fl, 0, sizeof(*fl)); - fl->daddr = key->ipv4_dst; - fl->saddr = key->ipv4_src; - fl->flowi4_tos = RT_TOS(key->ipv4_tos); + fl->daddr = key->u.ipv4.dst; + fl->saddr = key->u.ipv4.src; + fl->flowi4_tos = RT_TOS(key->tos); fl->flowi4_mark = mark; fl->flowi4_proto = protocol; rt = ip_route_output_key(net, fl); return rt; } + +static inline void ovs_vport_send(struct vport *vport, struct sk_buff *skb) +{ + vport->ops->send(vport, skb); +} + #endif /* vport.h */ diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index ed458b315ef4..7b8e39a22387 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -92,6 +92,7 @@ #ifdef CONFIG_INET #include <net/inet_common.h> #endif +#include <linux/bpf.h> #include "internal.h" @@ -518,13 +519,11 @@ static void prb_del_retire_blk_timer(struct tpacket_kbdq_core *pkc) } static void prb_shutdown_retire_blk_timer(struct packet_sock *po, - int tx_ring, struct sk_buff_head *rb_queue) { struct tpacket_kbdq_core *pkc; - pkc = tx_ring ? GET_PBDQC_FROM_RB(&po->tx_ring) : - GET_PBDQC_FROM_RB(&po->rx_ring); + pkc = GET_PBDQC_FROM_RB(&po->rx_ring); spin_lock_bh(&rb_queue->lock); pkc->delete_blk_timer = 1; @@ -1412,6 +1411,22 @@ static unsigned int fanout_demux_qm(struct packet_fanout *f, return skb_get_queue_mapping(skb) % num; } +static unsigned int fanout_demux_bpf(struct packet_fanout *f, + struct sk_buff *skb, + unsigned int num) +{ + struct bpf_prog *prog; + unsigned int ret = 0; + + rcu_read_lock(); + prog = rcu_dereference(f->bpf_prog); + if (prog) + ret = BPF_PROG_RUN(prog, skb) % num; + rcu_read_unlock(); + + return ret; +} + static bool fanout_has_flag(struct packet_fanout *f, u16 flag) { return f->flags & (flag >> 8); @@ -1456,6 +1471,10 @@ static int packet_rcv_fanout(struct sk_buff *skb, struct net_device *dev, case PACKET_FANOUT_ROLLOVER: idx = fanout_demux_rollover(f, skb, 0, false, num); break; + case PACKET_FANOUT_CBPF: + case PACKET_FANOUT_EBPF: + idx = fanout_demux_bpf(f, skb, num); + break; } if (fanout_has_flag(f, PACKET_FANOUT_FLAG_ROLLOVER)) @@ -1504,6 +1523,103 @@ static bool match_fanout_group(struct packet_type *ptype, struct sock *sk) return false; } +static void fanout_init_data(struct packet_fanout *f) +{ + switch (f->type) { + case PACKET_FANOUT_LB: + atomic_set(&f->rr_cur, 0); + break; + case PACKET_FANOUT_CBPF: + case PACKET_FANOUT_EBPF: + RCU_INIT_POINTER(f->bpf_prog, NULL); + break; + } +} + +static void __fanout_set_data_bpf(struct packet_fanout *f, struct bpf_prog *new) +{ + struct bpf_prog *old; + + spin_lock(&f->lock); + old = rcu_dereference_protected(f->bpf_prog, lockdep_is_held(&f->lock)); + rcu_assign_pointer(f->bpf_prog, new); + spin_unlock(&f->lock); + + if (old) { + synchronize_net(); + bpf_prog_destroy(old); + } +} + +static int fanout_set_data_cbpf(struct packet_sock *po, char __user *data, + unsigned int len) +{ + struct bpf_prog *new; + struct sock_fprog fprog; + int ret; + + if (sock_flag(&po->sk, SOCK_FILTER_LOCKED)) + return -EPERM; + if (len != sizeof(fprog)) + return -EINVAL; + if (copy_from_user(&fprog, data, len)) + return -EFAULT; + + ret = bpf_prog_create_from_user(&new, &fprog, NULL); + if (ret) + return ret; + + __fanout_set_data_bpf(po->fanout, new); + return 0; +} + +static int fanout_set_data_ebpf(struct packet_sock *po, char __user *data, + unsigned int len) +{ + struct bpf_prog *new; + u32 fd; + + if (sock_flag(&po->sk, SOCK_FILTER_LOCKED)) + return -EPERM; + if (len != sizeof(fd)) + return -EINVAL; + if (copy_from_user(&fd, data, len)) + return -EFAULT; + + new = bpf_prog_get(fd); + if (IS_ERR(new)) + return PTR_ERR(new); + if (new->type != BPF_PROG_TYPE_SOCKET_FILTER) { + bpf_prog_put(new); + return -EINVAL; + } + + __fanout_set_data_bpf(po->fanout, new); + return 0; +} + +static int fanout_set_data(struct packet_sock *po, char __user *data, + unsigned int len) +{ + switch (po->fanout->type) { + case PACKET_FANOUT_CBPF: + return fanout_set_data_cbpf(po, data, len); + case PACKET_FANOUT_EBPF: + return fanout_set_data_ebpf(po, data, len); + default: + return -EINVAL; + }; +} + +static void fanout_release_data(struct packet_fanout *f) +{ + switch (f->type) { + case PACKET_FANOUT_CBPF: + case PACKET_FANOUT_EBPF: + __fanout_set_data_bpf(f, NULL); + }; +} + static int fanout_add(struct sock *sk, u16 id, u16 type_flags) { struct packet_sock *po = pkt_sk(sk); @@ -1521,6 +1637,8 @@ static int fanout_add(struct sock *sk, u16 id, u16 type_flags) case PACKET_FANOUT_CPU: case PACKET_FANOUT_RND: case PACKET_FANOUT_QM: + case PACKET_FANOUT_CBPF: + case PACKET_FANOUT_EBPF: break; default: return -EINVAL; @@ -1563,10 +1681,10 @@ static int fanout_add(struct sock *sk, u16 id, u16 type_flags) match->id = id; match->type = type; match->flags = flags; - atomic_set(&match->rr_cur, 0); INIT_LIST_HEAD(&match->list); spin_lock_init(&match->lock); atomic_set(&match->sk_ref, 0); + fanout_init_data(match); match->prot_hook.type = po->prot_hook.type; match->prot_hook.dev = po->prot_hook.dev; match->prot_hook.func = packet_rcv_fanout; @@ -1612,6 +1730,7 @@ static void fanout_release(struct sock *sk) if (atomic_dec_and_test(&f->sk_ref)) { list_del(&f->list); dev_remove_pack(&f->prot_hook); + fanout_release_data(f); kfree(f); } mutex_unlock(&fanout_mutex); @@ -3531,6 +3650,13 @@ packet_setsockopt(struct socket *sock, int level, int optname, char __user *optv return fanout_add(sk, val & 0xffff, val >> 16); } + case PACKET_FANOUT_DATA: + { + if (!po->fanout) + return -EINVAL; + + return fanout_set_data(po, optval, optlen); + } case PACKET_TX_HAS_OFF: { unsigned int val; @@ -4043,7 +4169,7 @@ static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u, if (closing && (po->tp_version > TPACKET_V2)) { /* Because we don't support block-based V3 on tx-ring */ if (!tx_ring) - prb_shutdown_retire_blk_timer(po, tx_ring, rb_queue); + prb_shutdown_retire_blk_timer(po, rb_queue); } release_sock(sk); diff --git a/net/packet/internal.h b/net/packet/internal.h index e20b3e8829b8..9ee46314b7d7 100644 --- a/net/packet/internal.h +++ b/net/packet/internal.h @@ -79,7 +79,10 @@ struct packet_fanout { u16 id; u8 type; u8 flags; - atomic_t rr_cur; + union { + atomic_t rr_cur; + struct bpf_prog __rcu *bpf_prog; + }; struct list_head list; struct sock *arr[PACKET_FANOUT_MAX]; spinlock_t lock; diff --git a/net/rds/af_rds.c b/net/rds/af_rds.c index 896834cd3b9a..a2f28a6d4dc5 100644 --- a/net/rds/af_rds.c +++ b/net/rds/af_rds.c @@ -438,6 +438,14 @@ static const struct proto_ops rds_proto_ops = { .sendpage = sock_no_sendpage, }; +static void rds_sock_destruct(struct sock *sk) +{ + struct rds_sock *rs = rds_sk_to_rs(sk); + + WARN_ON((&rs->rs_item != rs->rs_item.next || + &rs->rs_item != rs->rs_item.prev)); +} + static int __rds_create(struct socket *sock, struct sock *sk, int protocol) { struct rds_sock *rs; @@ -445,6 +453,7 @@ static int __rds_create(struct socket *sock, struct sock *sk, int protocol) sock_init_data(sock, sk); sock->ops = &rds_proto_ops; sk->sk_protocol = protocol; + sk->sk_destruct = rds_sock_destruct; rs = rds_sk_to_rs(sk); spin_lock_init(&rs->rs_lock); diff --git a/net/rds/bind.c b/net/rds/bind.c index 4ebd29c128b6..dd666fb9b4e1 100644 --- a/net/rds/bind.c +++ b/net/rds/bind.c @@ -185,7 +185,8 @@ int rds_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) ret = 0; goto out; } - trans = rds_trans_get_preferred(sin->sin_addr.s_addr); + trans = rds_trans_get_preferred(sock_net(sock->sk), + sin->sin_addr.s_addr); if (!trans) { ret = -EADDRNOTAVAIL; rds_remove_bound(rs); diff --git a/net/rds/connection.c b/net/rds/connection.c index da6da57e5f36..49adeef8090c 100644 --- a/net/rds/connection.c +++ b/net/rds/connection.c @@ -70,7 +70,8 @@ static struct hlist_head *rds_conn_bucket(__be32 laddr, __be32 faddr) } while (0) /* rcu read lock must be held or the connection spinlock */ -static struct rds_connection *rds_conn_lookup(struct hlist_head *head, +static struct rds_connection *rds_conn_lookup(struct net *net, + struct hlist_head *head, __be32 laddr, __be32 faddr, struct rds_transport *trans) { @@ -78,7 +79,7 @@ static struct rds_connection *rds_conn_lookup(struct hlist_head *head, hlist_for_each_entry_rcu(conn, head, c_hash_node) { if (conn->c_faddr == faddr && conn->c_laddr == laddr && - conn->c_trans == trans) { + conn->c_trans == trans && net == rds_conn_net(conn)) { ret = conn; break; } @@ -117,7 +118,8 @@ static void rds_conn_reset(struct rds_connection *conn) * For now they are not garbage collected once they're created. They * are torn down as the module is removed, if ever. */ -static struct rds_connection *__rds_conn_create(__be32 laddr, __be32 faddr, +static struct rds_connection *__rds_conn_create(struct net *net, + __be32 laddr, __be32 faddr, struct rds_transport *trans, gfp_t gfp, int is_outgoing) { @@ -131,7 +133,7 @@ static struct rds_connection *__rds_conn_create(__be32 laddr, __be32 faddr, if (!is_outgoing && otrans->t_type == RDS_TRANS_TCP) goto new_conn; rcu_read_lock(); - conn = rds_conn_lookup(head, laddr, faddr, trans); + conn = rds_conn_lookup(net, head, laddr, faddr, trans); if (conn && conn->c_loopback && conn->c_trans != &rds_loop_transport && laddr == faddr && !is_outgoing) { /* This is a looped back IB connection, and we're @@ -157,6 +159,7 @@ new_conn: conn->c_faddr = faddr; spin_lock_init(&conn->c_lock); conn->c_next_tx_seq = 1; + rds_conn_net_set(conn, net); init_waitqueue_head(&conn->c_waitq); INIT_LIST_HEAD(&conn->c_send_queue); @@ -174,7 +177,7 @@ new_conn: * can bind to the destination address then we'd rather the messages * flow through loopback rather than either transport. */ - loop_trans = rds_trans_get_preferred(faddr); + loop_trans = rds_trans_get_preferred(net, faddr); if (loop_trans) { rds_trans_put(loop_trans); conn->c_loopback = 1; @@ -187,6 +190,12 @@ new_conn: } } + if (trans == NULL) { + kmem_cache_free(rds_conn_slab, conn); + conn = ERR_PTR(-ENODEV); + goto out; + } + conn->c_trans = trans; ret = trans->conn_alloc(conn, gfp); @@ -237,7 +246,7 @@ new_conn: if (!is_outgoing && otrans->t_type == RDS_TRANS_TCP) found = NULL; else - found = rds_conn_lookup(head, laddr, faddr, trans); + found = rds_conn_lookup(net, head, laddr, faddr, trans); if (found) { trans->conn_free(conn->c_transport_data); kmem_cache_free(rds_conn_slab, conn); @@ -260,17 +269,19 @@ out: return conn; } -struct rds_connection *rds_conn_create(__be32 laddr, __be32 faddr, +struct rds_connection *rds_conn_create(struct net *net, + __be32 laddr, __be32 faddr, struct rds_transport *trans, gfp_t gfp) { - return __rds_conn_create(laddr, faddr, trans, gfp, 0); + return __rds_conn_create(net, laddr, faddr, trans, gfp, 0); } EXPORT_SYMBOL_GPL(rds_conn_create); -struct rds_connection *rds_conn_create_outgoing(__be32 laddr, __be32 faddr, +struct rds_connection *rds_conn_create_outgoing(struct net *net, + __be32 laddr, __be32 faddr, struct rds_transport *trans, gfp_t gfp) { - return __rds_conn_create(laddr, faddr, trans, gfp, 1); + return __rds_conn_create(net, laddr, faddr, trans, gfp, 1); } EXPORT_SYMBOL_GPL(rds_conn_create_outgoing); @@ -297,6 +308,8 @@ void rds_conn_shutdown(struct rds_connection *conn) wait_event(conn->c_waitq, !test_bit(RDS_IN_XMIT, &conn->c_flags)); + wait_event(conn->c_waitq, + !test_bit(RDS_RECV_REFILL, &conn->c_flags)); conn->c_trans->conn_shutdown(conn); rds_conn_reset(conn); diff --git a/net/rds/ib.c b/net/rds/ib.c index ba2dffeff608..2d3f2ab475df 100644 --- a/net/rds/ib.c +++ b/net/rds/ib.c @@ -99,8 +99,6 @@ static void rds_ib_dev_free(struct work_struct *work) if (rds_ibdev->mr_pool) rds_ib_destroy_mr_pool(rds_ibdev->mr_pool); - if (rds_ibdev->mr) - ib_dereg_mr(rds_ibdev->mr); if (rds_ibdev->pd) ib_dealloc_pd(rds_ibdev->pd); @@ -164,12 +162,6 @@ static void rds_ib_add_one(struct ib_device *device) goto put_dev; } - rds_ibdev->mr = ib_get_dma_mr(rds_ibdev->pd, IB_ACCESS_LOCAL_WRITE); - if (IS_ERR(rds_ibdev->mr)) { - rds_ibdev->mr = NULL; - goto put_dev; - } - rds_ibdev->mr_pool = rds_ib_create_mr_pool(rds_ibdev); if (IS_ERR(rds_ibdev->mr_pool)) { rds_ibdev->mr_pool = NULL; @@ -230,11 +222,10 @@ struct rds_ib_device *rds_ib_get_client_data(struct ib_device *device) * * This can be called at any time and can be racing with any other RDS path. */ -static void rds_ib_remove_one(struct ib_device *device) +static void rds_ib_remove_one(struct ib_device *device, void *client_data) { - struct rds_ib_device *rds_ibdev; + struct rds_ib_device *rds_ibdev = client_data; - rds_ibdev = ib_get_client_data(device, &rds_ib_client); if (!rds_ibdev) return; @@ -317,7 +308,7 @@ static void rds_ib_ic_info(struct socket *sock, unsigned int len, * allowed to influence which paths have priority. We could call userspace * asserting this policy "routing". */ -static int rds_ib_laddr_check(__be32 addr) +static int rds_ib_laddr_check(struct net *net, __be32 addr) { int ret; struct rdma_cm_id *cm_id; @@ -366,6 +357,7 @@ void rds_ib_exit(void) rds_ib_sysctl_exit(); rds_ib_recv_exit(); rds_trans_unregister(&rds_ib_transport); + rds_ib_fmr_exit(); } struct rds_transport rds_ib_transport = { @@ -401,10 +393,14 @@ int rds_ib_init(void) INIT_LIST_HEAD(&rds_ib_devices); - ret = ib_register_client(&rds_ib_client); + ret = rds_ib_fmr_init(); if (ret) goto out; + ret = ib_register_client(&rds_ib_client); + if (ret) + goto out_fmr_exit; + ret = rds_ib_sysctl_init(); if (ret) goto out_ibreg; @@ -427,6 +423,8 @@ out_sysctl: rds_ib_sysctl_exit(); out_ibreg: rds_ib_unregister_client(); +out_fmr_exit: + rds_ib_fmr_exit(); out: return ret; } diff --git a/net/rds/ib.h b/net/rds/ib.h index 86d88ec5d556..aae60fda77f6 100644 --- a/net/rds/ib.h +++ b/net/rds/ib.h @@ -100,7 +100,6 @@ struct rds_ib_connection { /* alphabet soup, IBTA style */ struct rdma_cm_id *i_cm_id; struct ib_pd *i_pd; - struct ib_mr *i_mr; struct ib_cq *i_send_cq; struct ib_cq *i_recv_cq; @@ -173,7 +172,6 @@ struct rds_ib_device { struct list_head conn_list; struct ib_device *dev; struct ib_pd *pd; - struct ib_mr *mr; struct rds_ib_mr_pool *mr_pool; unsigned int fmr_max_remaps; unsigned int max_fmrs; @@ -313,6 +311,8 @@ void *rds_ib_get_mr(struct scatterlist *sg, unsigned long nents, void rds_ib_sync_mr(void *trans_private, int dir); void rds_ib_free_mr(void *trans_private, int invalidate); void rds_ib_flush_mrs(void); +int rds_ib_fmr_init(void); +void rds_ib_fmr_exit(void); /* ib_recv.c */ int rds_ib_recv_init(void); @@ -320,7 +320,7 @@ void rds_ib_recv_exit(void); int rds_ib_recv(struct rds_connection *conn); int rds_ib_recv_alloc_caches(struct rds_ib_connection *ic); void rds_ib_recv_free_caches(struct rds_ib_connection *ic); -void rds_ib_recv_refill(struct rds_connection *conn, int prefill); +void rds_ib_recv_refill(struct rds_connection *conn, int prefill, gfp_t gfp); void rds_ib_inc_free(struct rds_incoming *inc); int rds_ib_inc_copy_to_user(struct rds_incoming *inc, struct iov_iter *to); void rds_ib_recv_cq_comp_handler(struct ib_cq *cq, void *context); diff --git a/net/rds/ib_cm.c b/net/rds/ib_cm.c index 0da2a45b33bd..9043f5c04787 100644 --- a/net/rds/ib_cm.c +++ b/net/rds/ib_cm.c @@ -135,7 +135,7 @@ void rds_ib_cm_connect_complete(struct rds_connection *conn, struct rdma_cm_even rds_ib_recv_init_ring(ic); /* Post receive buffers - as a side effect, this will update * the posted credit count. */ - rds_ib_recv_refill(conn, 1); + rds_ib_recv_refill(conn, 1, GFP_KERNEL); /* Tune RNR behavior */ rds_ib_tune_rnr(ic, &qp_attr); @@ -269,7 +269,6 @@ static int rds_ib_setup_qp(struct rds_connection *conn) /* Protection domain and memory range */ ic->i_pd = rds_ibdev->pd; - ic->i_mr = rds_ibdev->mr; cq_attr.cqe = ic->i_send_ring.w_nr + 1; ic->i_send_cq = ib_create_cq(dev, rds_ib_send_cq_comp_handler, @@ -375,7 +374,7 @@ static int rds_ib_setup_qp(struct rds_connection *conn) rds_ib_recv_init_ack(ic); - rdsdebug("conn %p pd %p mr %p cq %p %p\n", conn, ic->i_pd, ic->i_mr, + rdsdebug("conn %p pd %p cq %p %p\n", conn, ic->i_pd, ic->i_send_cq, ic->i_recv_cq); out: @@ -448,8 +447,9 @@ int rds_ib_cm_handle_connect(struct rdma_cm_id *cm_id, (unsigned long long)be64_to_cpu(lguid), (unsigned long long)be64_to_cpu(fguid)); - conn = rds_conn_create(dp->dp_daddr, dp->dp_saddr, &rds_ib_transport, - GFP_KERNEL); + /* RDS/IB is not currently netns aware, thus init_net */ + conn = rds_conn_create(&init_net, dp->dp_daddr, dp->dp_saddr, + &rds_ib_transport, GFP_KERNEL); if (IS_ERR(conn)) { rdsdebug("rds_conn_create failed (%ld)\n", PTR_ERR(conn)); conn = NULL; @@ -639,6 +639,15 @@ void rds_ib_conn_shutdown(struct rds_connection *conn) (atomic_read(&ic->i_signaled_sends) == 0)); tasklet_kill(&ic->i_recv_tasklet); + /* first destroy the ib state that generates callbacks */ + if (ic->i_cm_id->qp) + rdma_destroy_qp(ic->i_cm_id); + if (ic->i_send_cq) + ib_destroy_cq(ic->i_send_cq); + if (ic->i_recv_cq) + ib_destroy_cq(ic->i_recv_cq); + + /* then free the resources that ib callbacks use */ if (ic->i_send_hdrs) ib_dma_free_coherent(dev, ic->i_send_ring.w_nr * @@ -662,12 +671,6 @@ void rds_ib_conn_shutdown(struct rds_connection *conn) if (ic->i_recvs) rds_ib_recv_clear_ring(ic); - if (ic->i_cm_id->qp) - rdma_destroy_qp(ic->i_cm_id); - if (ic->i_send_cq) - ib_destroy_cq(ic->i_send_cq); - if (ic->i_recv_cq) - ib_destroy_cq(ic->i_recv_cq); rdma_destroy_id(ic->i_cm_id); /* @@ -678,7 +681,6 @@ void rds_ib_conn_shutdown(struct rds_connection *conn) ic->i_cm_id = NULL; ic->i_pd = NULL; - ic->i_mr = NULL; ic->i_send_cq = NULL; ic->i_recv_cq = NULL; ic->i_send_hdrs = NULL; diff --git a/net/rds/ib_rdma.c b/net/rds/ib_rdma.c index 657ba9f5d308..251d1ce0b7c7 100644 --- a/net/rds/ib_rdma.c +++ b/net/rds/ib_rdma.c @@ -83,6 +83,25 @@ struct rds_ib_mr_pool { struct ib_fmr_attr fmr_attr; }; +struct workqueue_struct *rds_ib_fmr_wq; + +int rds_ib_fmr_init(void) +{ + rds_ib_fmr_wq = create_workqueue("rds_fmr_flushd"); + if (!rds_ib_fmr_wq) + return -ENOMEM; + return 0; +} + +/* By the time this is called all the IB devices should have been torn down and + * had their pools freed. As each pool is freed its work struct is waited on, + * so the pool flushing work queue should be idle by the time we get here. + */ +void rds_ib_fmr_exit(void) +{ + destroy_workqueue(rds_ib_fmr_wq); +} + static int rds_ib_flush_mr_pool(struct rds_ib_mr_pool *pool, int free_all, struct rds_ib_mr **); static void rds_ib_teardown_mr(struct rds_ib_mr *ibmr); static void rds_ib_mr_pool_flush_worker(struct work_struct *work); @@ -151,12 +170,17 @@ int rds_ib_update_ipaddr(struct rds_ib_device *rds_ibdev, __be32 ipaddr) struct rds_ib_device *rds_ibdev_old; rds_ibdev_old = rds_ib_get_device(ipaddr); - if (rds_ibdev_old) { + if (!rds_ibdev_old) + return rds_ib_add_ipaddr(rds_ibdev, ipaddr); + + if (rds_ibdev_old != rds_ibdev) { rds_ib_remove_ipaddr(rds_ibdev_old, ipaddr); rds_ib_dev_put(rds_ibdev_old); + return rds_ib_add_ipaddr(rds_ibdev, ipaddr); } + rds_ib_dev_put(rds_ibdev_old); - return rds_ib_add_ipaddr(rds_ibdev, ipaddr); + return 0; } void rds_ib_add_conn(struct rds_ib_device *rds_ibdev, struct rds_connection *conn) @@ -336,8 +360,6 @@ static struct rds_ib_mr *rds_ib_alloc_fmr(struct rds_ib_device *rds_ibdev) goto out_no_cigar; } - memset(ibmr, 0, sizeof(*ibmr)); - ibmr->fmr = ib_alloc_fmr(rds_ibdev->pd, (IB_ACCESS_LOCAL_WRITE | IB_ACCESS_REMOTE_READ | @@ -485,7 +507,7 @@ static void __rds_ib_teardown_mr(struct rds_ib_mr *ibmr) /* FIXME we need a way to tell a r/w MR * from a r/o MR */ - BUG_ON(irqs_disabled()); + WARN_ON(!page->mapping && irqs_disabled()); set_page_dirty(page); put_page(page); } @@ -523,11 +545,13 @@ static inline unsigned int rds_ib_flush_goal(struct rds_ib_mr_pool *pool, int fr /* * given an llist of mrs, put them all into the list_head for more processing */ -static void llist_append_to_list(struct llist_head *llist, struct list_head *list) +static unsigned int llist_append_to_list(struct llist_head *llist, + struct list_head *list) { struct rds_ib_mr *ibmr; struct llist_node *node; struct llist_node *next; + unsigned int count = 0; node = llist_del_all(llist); while (node) { @@ -535,7 +559,9 @@ static void llist_append_to_list(struct llist_head *llist, struct list_head *lis ibmr = llist_entry(node, struct rds_ib_mr, llnode); list_add_tail(&ibmr->unmap_list, list); node = next; + count++; } + return count; } /* @@ -576,7 +602,7 @@ static int rds_ib_flush_mr_pool(struct rds_ib_mr_pool *pool, LIST_HEAD(unmap_list); LIST_HEAD(fmr_list); unsigned long unpinned = 0; - unsigned int nfreed = 0, ncleaned = 0, free_goal; + unsigned int nfreed = 0, dirty_to_clean = 0, free_goal; int ret = 0; rds_ib_stats_inc(s_ib_rdma_mr_pool_flush); @@ -618,8 +644,8 @@ static int rds_ib_flush_mr_pool(struct rds_ib_mr_pool *pool, /* Get the list of all MRs to be dropped. Ordering matters - * we want to put drop_list ahead of free_list. */ - llist_append_to_list(&pool->drop_list, &unmap_list); - llist_append_to_list(&pool->free_list, &unmap_list); + dirty_to_clean = llist_append_to_list(&pool->drop_list, &unmap_list); + dirty_to_clean += llist_append_to_list(&pool->free_list, &unmap_list); if (free_all) llist_append_to_list(&pool->clean_list, &unmap_list); @@ -647,7 +673,6 @@ static int rds_ib_flush_mr_pool(struct rds_ib_mr_pool *pool, kfree(ibmr); nfreed++; } - ncleaned++; } if (!list_empty(&unmap_list)) { @@ -673,7 +698,7 @@ static int rds_ib_flush_mr_pool(struct rds_ib_mr_pool *pool, } atomic_sub(unpinned, &pool->free_pinned); - atomic_sub(ncleaned, &pool->dirty_count); + atomic_sub(dirty_to_clean, &pool->dirty_count); atomic_sub(nfreed, &pool->item_count); out: @@ -710,16 +735,18 @@ void rds_ib_free_mr(void *trans_private, int invalidate) /* If we've pinned too many pages, request a flush */ if (atomic_read(&pool->free_pinned) >= pool->max_free_pinned || - atomic_read(&pool->dirty_count) >= pool->max_items / 10) - schedule_delayed_work(&pool->flush_worker, 10); + atomic_read(&pool->dirty_count) >= pool->max_items / 5) + queue_delayed_work(rds_ib_fmr_wq, &pool->flush_worker, 10); if (invalidate) { if (likely(!in_interrupt())) { rds_ib_flush_mr_pool(pool, 0, NULL); } else { /* We get here if the user created a MR marked - * as use_once and invalidate at the same time. */ - schedule_delayed_work(&pool->flush_worker, 10); + * as use_once and invalidate at the same time. + */ + queue_delayed_work(rds_ib_fmr_wq, + &pool->flush_worker, 10); } } diff --git a/net/rds/ib_recv.c b/net/rds/ib_recv.c index cac5b4506ee3..f43831e4186a 100644 --- a/net/rds/ib_recv.c +++ b/net/rds/ib_recv.c @@ -62,12 +62,12 @@ void rds_ib_recv_init_ring(struct rds_ib_connection *ic) sge = &recv->r_sge[0]; sge->addr = ic->i_recv_hdrs_dma + (i * sizeof(struct rds_header)); sge->length = sizeof(struct rds_header); - sge->lkey = ic->i_mr->lkey; + sge->lkey = ic->i_pd->local_dma_lkey; sge = &recv->r_sge[1]; sge->addr = 0; sge->length = RDS_FRAG_SIZE; - sge->lkey = ic->i_mr->lkey; + sge->lkey = ic->i_pd->local_dma_lkey; } } @@ -297,7 +297,7 @@ static struct rds_page_frag *rds_ib_refill_one_frag(struct rds_ib_connection *ic } static int rds_ib_recv_refill_one(struct rds_connection *conn, - struct rds_ib_recv_work *recv, int prefill) + struct rds_ib_recv_work *recv, gfp_t gfp) { struct rds_ib_connection *ic = conn->c_transport_data; struct ib_sge *sge; @@ -305,7 +305,7 @@ static int rds_ib_recv_refill_one(struct rds_connection *conn, gfp_t slab_mask = GFP_NOWAIT; gfp_t page_mask = GFP_NOWAIT; - if (prefill) { + if (gfp & __GFP_WAIT) { slab_mask = GFP_KERNEL; page_mask = GFP_HIGHUSER; } @@ -347,6 +347,24 @@ out: return ret; } +static int acquire_refill(struct rds_connection *conn) +{ + return test_and_set_bit(RDS_RECV_REFILL, &conn->c_flags) == 0; +} + +static void release_refill(struct rds_connection *conn) +{ + clear_bit(RDS_RECV_REFILL, &conn->c_flags); + + /* We don't use wait_on_bit()/wake_up_bit() because our waking is in a + * hot path and finding waiters is very rare. We don't want to walk + * the system-wide hashed waitqueue buckets in the fast path only to + * almost never find waiters. + */ + if (waitqueue_active(&conn->c_waitq)) + wake_up_all(&conn->c_waitq); +} + /* * This tries to allocate and post unused work requests after making sure that * they have all the allocations they need to queue received fragments into @@ -354,15 +372,23 @@ out: * * -1 is returned if posting fails due to temporary resource exhaustion. */ -void rds_ib_recv_refill(struct rds_connection *conn, int prefill) +void rds_ib_recv_refill(struct rds_connection *conn, int prefill, gfp_t gfp) { struct rds_ib_connection *ic = conn->c_transport_data; struct rds_ib_recv_work *recv; struct ib_recv_wr *failed_wr; unsigned int posted = 0; int ret = 0; + bool can_wait = !!(gfp & __GFP_WAIT); u32 pos; + /* the goal here is to just make sure that someone, somewhere + * is posting buffers. If we can't get the refill lock, + * let them do their thing + */ + if (!acquire_refill(conn)) + return; + while ((prefill || rds_conn_up(conn)) && rds_ib_ring_alloc(&ic->i_recv_ring, 1, &pos)) { if (pos >= ic->i_recv_ring.w_nr) { @@ -372,7 +398,7 @@ void rds_ib_recv_refill(struct rds_connection *conn, int prefill) } recv = &ic->i_recvs[pos]; - ret = rds_ib_recv_refill_one(conn, recv, prefill); + ret = rds_ib_recv_refill_one(conn, recv, gfp); if (ret) { break; } @@ -402,6 +428,24 @@ void rds_ib_recv_refill(struct rds_connection *conn, int prefill) if (ret) rds_ib_ring_unalloc(&ic->i_recv_ring, 1); + + release_refill(conn); + + /* if we're called from the softirq handler, we'll be GFP_NOWAIT. + * in this case the ring being low is going to lead to more interrupts + * and we can safely let the softirq code take care of it unless the + * ring is completely empty. + * + * if we're called from krdsd, we'll be GFP_KERNEL. In this case + * we might have raced with the softirq code while we had the refill + * lock held. Use rds_ib_ring_low() instead of ring_empty to decide + * if we should requeue. + */ + if (rds_conn_up(conn) && + ((can_wait && rds_ib_ring_low(&ic->i_recv_ring)) || + rds_ib_ring_empty(&ic->i_recv_ring))) { + queue_delayed_work(rds_wq, &conn->c_recv_w, 1); + } } /* @@ -520,7 +564,7 @@ void rds_ib_recv_init_ack(struct rds_ib_connection *ic) sge->addr = ic->i_ack_dma; sge->length = sizeof(struct rds_header); - sge->lkey = ic->i_mr->lkey; + sge->lkey = ic->i_pd->local_dma_lkey; wr->sg_list = sge; wr->num_sge = 1; @@ -982,10 +1026,17 @@ static inline void rds_poll_cq(struct rds_ib_connection *ic, } /* - * It's very important that we only free this ring entry if we've truly - * freed the resources allocated to the entry. The refilling path can - * leak if we don't. + * rds_ib_process_recv() doesn't always consume the frag, and + * we might not have called it at all if the wc didn't indicate + * success. We already unmapped the frag's pages, though, and + * the following rds_ib_ring_free() call tells the refill path + * that it will not find an allocated frag here. Make sure we + * keep that promise by freeing a frag that's still on the ring. */ + if (recv->r_frag) { + rds_ib_frag_free(ic, recv->r_frag); + recv->r_frag = NULL; + } rds_ib_ring_free(&ic->i_recv_ring, 1); } } @@ -1016,7 +1067,7 @@ void rds_ib_recv_tasklet_fn(unsigned long data) rds_ib_stats_inc(s_ib_rx_ring_empty); if (rds_ib_ring_low(&ic->i_recv_ring)) - rds_ib_recv_refill(conn, 0); + rds_ib_recv_refill(conn, 0, GFP_NOWAIT); } int rds_ib_recv(struct rds_connection *conn) @@ -1025,8 +1076,10 @@ int rds_ib_recv(struct rds_connection *conn) int ret = 0; rdsdebug("conn %p\n", conn); - if (rds_conn_up(conn)) + if (rds_conn_up(conn)) { rds_ib_attempt_ack(ic); + rds_ib_recv_refill(conn, 0, GFP_KERNEL); + } return ret; } @@ -1049,9 +1102,10 @@ int rds_ib_recv_init(void) rds_ib_frag_slab = kmem_cache_create("rds_ib_frag", sizeof(struct rds_page_frag), 0, SLAB_HWCACHE_ALIGN, NULL); - if (!rds_ib_frag_slab) + if (!rds_ib_frag_slab) { kmem_cache_destroy(rds_ib_incoming_slab); - else + rds_ib_incoming_slab = NULL; + } else ret = 0; out: return ret; diff --git a/net/rds/ib_send.c b/net/rds/ib_send.c index 5d0a704fa039..4e88047086b6 100644 --- a/net/rds/ib_send.c +++ b/net/rds/ib_send.c @@ -202,9 +202,9 @@ void rds_ib_send_init_ring(struct rds_ib_connection *ic) sge = &send->s_sge[0]; sge->addr = ic->i_send_hdrs_dma + (i * sizeof(struct rds_header)); sge->length = sizeof(struct rds_header); - sge->lkey = ic->i_mr->lkey; + sge->lkey = ic->i_pd->local_dma_lkey; - send->s_sge[1].lkey = ic->i_mr->lkey; + send->s_sge[1].lkey = ic->i_pd->local_dma_lkey; } } @@ -709,6 +709,11 @@ int rds_ib_xmit(struct rds_connection *conn, struct rds_message *rm, if (scat == &rm->data.op_sg[rm->data.op_count]) { prev->s_op = ic->i_data_op; prev->s_wr.send_flags |= IB_SEND_SOLICITED; + if (!(prev->s_wr.send_flags & IB_SEND_SIGNALED)) { + ic->i_unsignaled_wrs = rds_ib_sysctl_max_unsig_wrs; + prev->s_wr.send_flags |= IB_SEND_SIGNALED; + nr_sig++; + } ic->i_data_op = NULL; } @@ -813,7 +818,7 @@ int rds_ib_xmit_atomic(struct rds_connection *conn, struct rm_atomic_op *op) /* Convert our struct scatterlist to struct ib_sge */ send->s_sge[0].addr = ib_sg_dma_address(ic->i_cm_id->device, op->op_sg); send->s_sge[0].length = ib_sg_dma_len(ic->i_cm_id->device, op->op_sg); - send->s_sge[0].lkey = ic->i_mr->lkey; + send->s_sge[0].lkey = ic->i_pd->local_dma_lkey; rdsdebug("rva %Lx rpa %Lx len %u\n", op->op_remote_addr, send->s_sge[0].addr, send->s_sge[0].length); @@ -927,7 +932,7 @@ int rds_ib_xmit_rdma(struct rds_connection *conn, struct rm_rdma_op *op) send->s_sge[j].addr = ib_sg_dma_address(ic->i_cm_id->device, scat); send->s_sge[j].length = len; - send->s_sge[j].lkey = ic->i_mr->lkey; + send->s_sge[j].lkey = ic->i_pd->local_dma_lkey; sent += len; rdsdebug("ic %p sent %d remote_addr %llu\n", ic, sent, remote_addr); diff --git a/net/rds/iw.c b/net/rds/iw.c index 589935661d66..3df0295c6659 100644 --- a/net/rds/iw.c +++ b/net/rds/iw.c @@ -125,12 +125,11 @@ free_attr: kfree(dev_attr); } -static void rds_iw_remove_one(struct ib_device *device) +static void rds_iw_remove_one(struct ib_device *device, void *client_data) { - struct rds_iw_device *rds_iwdev; + struct rds_iw_device *rds_iwdev = client_data; struct rds_iw_cm_id *i_cm_id, *next; - rds_iwdev = ib_get_client_data(device, &rds_iw_client); if (!rds_iwdev) return; @@ -149,10 +148,7 @@ static void rds_iw_remove_one(struct ib_device *device) if (rds_iwdev->mr) ib_dereg_mr(rds_iwdev->mr); - while (ib_dealloc_pd(rds_iwdev->pd)) { - rdsdebug("Failed to dealloc pd %p\n", rds_iwdev->pd); - msleep(1); - } + ib_dealloc_pd(rds_iwdev->pd); list_del(&rds_iwdev->list); kfree(rds_iwdev); @@ -218,7 +214,7 @@ static void rds_iw_ic_info(struct socket *sock, unsigned int len, * allowed to influence which paths have priority. We could call userspace * asserting this policy "routing". */ -static int rds_iw_laddr_check(__be32 addr) +static int rds_iw_laddr_check(struct net *net, __be32 addr) { int ret; struct rdma_cm_id *cm_id; diff --git a/net/rds/iw_cm.c b/net/rds/iw_cm.c index 8f486fa32079..a6553a6fb2bc 100644 --- a/net/rds/iw_cm.c +++ b/net/rds/iw_cm.c @@ -398,8 +398,9 @@ int rds_iw_cm_handle_connect(struct rdma_cm_id *cm_id, &dp->dp_saddr, &dp->dp_daddr, RDS_PROTOCOL_MAJOR(version), RDS_PROTOCOL_MINOR(version)); - conn = rds_conn_create(dp->dp_daddr, dp->dp_saddr, &rds_iw_transport, - GFP_KERNEL); + /* RDS/IW is not currently netns aware, thus init_net */ + conn = rds_conn_create(&init_net, dp->dp_daddr, dp->dp_saddr, + &rds_iw_transport, GFP_KERNEL); if (IS_ERR(conn)) { rdsdebug("rds_conn_create failed (%ld)\n", PTR_ERR(conn)); conn = NULL; diff --git a/net/rds/iw_rdma.c b/net/rds/iw_rdma.c index dba8d0864f18..6a8fbd6e69e7 100644 --- a/net/rds/iw_rdma.c +++ b/net/rds/iw_rdma.c @@ -667,11 +667,12 @@ static int rds_iw_init_fastreg(struct rds_iw_mr_pool *pool, struct ib_mr *mr; int err; - mr = ib_alloc_fast_reg_mr(rds_iwdev->pd, pool->max_message_size); + mr = ib_alloc_mr(rds_iwdev->pd, IB_MR_TYPE_MEM_REG, + pool->max_message_size); if (IS_ERR(mr)) { err = PTR_ERR(mr); - printk(KERN_WARNING "RDS/IW: ib_alloc_fast_reg_mr failed (err=%d)\n", err); + printk(KERN_WARNING "RDS/IW: ib_alloc_mr failed (err=%d)\n", err); return err; } diff --git a/net/rds/iw_send.c b/net/rds/iw_send.c index 334fe98c5084..86152ec3b887 100644 --- a/net/rds/iw_send.c +++ b/net/rds/iw_send.c @@ -153,9 +153,10 @@ void rds_iw_send_init_ring(struct rds_iw_connection *ic) sge->length = sizeof(struct rds_header); sge->lkey = 0; - send->s_mr = ib_alloc_fast_reg_mr(ic->i_pd, fastreg_message_size); + send->s_mr = ib_alloc_mr(ic->i_pd, IB_MR_TYPE_MEM_REG, + fastreg_message_size); if (IS_ERR(send->s_mr)) { - printk(KERN_WARNING "RDS/IW: ib_alloc_fast_reg_mr failed\n"); + printk(KERN_WARNING "RDS/IW: ib_alloc_mr failed\n"); break; } diff --git a/net/rds/rdma.c b/net/rds/rdma.c index 40084d843e9f..4c93badeabf2 100644 --- a/net/rds/rdma.c +++ b/net/rds/rdma.c @@ -435,9 +435,10 @@ void rds_rdma_unuse(struct rds_sock *rs, u32 r_key, int force) /* If the MR was marked as invalidate, this will * trigger an async flush. */ - if (zot_me) + if (zot_me) { rds_destroy_mr(mr); - rds_mr_put(mr); + rds_mr_put(mr); + } } void rds_rdma_free_op(struct rm_rdma_op *ro) @@ -451,7 +452,7 @@ void rds_rdma_free_op(struct rm_rdma_op *ro) * is the case for a RDMA_READ which copies from remote * to local memory */ if (!ro->op_write) { - BUG_ON(irqs_disabled()); + WARN_ON(!page->mapping && irqs_disabled()); set_page_dirty(page); } put_page(page); @@ -658,6 +659,8 @@ int rds_cmsg_rdma_args(struct rds_sock *rs, struct rds_message *rm, ret = rds_pin_pages(iov->addr, nr, pages, !op->op_write); if (ret < 0) goto out; + else + ret = 0; rdsdebug("RDS: nr_bytes %u nr %u iov->bytes %llu iov->addr %llx\n", nr_bytes, nr, iov->bytes, iov->addr); diff --git a/net/rds/rdma_transport.c b/net/rds/rdma_transport.c index 208240836043..b9b40af5345b 100644 --- a/net/rds/rdma_transport.c +++ b/net/rds/rdma_transport.c @@ -34,6 +34,7 @@ #include <rdma/rdma_cm.h> #include "rdma_transport.h" +#include "ib.h" static struct rdma_cm_id *rds_rdma_listen_id; @@ -82,8 +83,18 @@ int rds_rdma_cm_event_handler(struct rdma_cm_id *cm_id, break; case RDMA_CM_EVENT_ROUTE_RESOLVED: - /* XXX worry about racing with listen acceptance */ - ret = trans->cm_initiate_connect(cm_id); + /* Connection could have been dropped so make sure the + * cm_id is valid before proceeding + */ + if (conn) { + struct rds_ib_connection *ibic; + + ibic = conn->c_transport_data; + if (ibic && ibic->i_cm_id == cm_id) + ret = trans->cm_initiate_connect(cm_id); + else + rds_conn_drop(conn); + } break; case RDMA_CM_EVENT_ESTABLISHED: diff --git a/net/rds/rds.h b/net/rds/rds.h index 2260c1e434b1..afb4048d0cfd 100644 --- a/net/rds/rds.h +++ b/net/rds/rds.h @@ -80,6 +80,7 @@ enum { #define RDS_LL_SEND_FULL 0 #define RDS_RECONNECT_PENDING 1 #define RDS_IN_XMIT 2 +#define RDS_RECV_REFILL 3 struct rds_connection { struct hlist_node c_hash_node; @@ -128,8 +129,21 @@ struct rds_connection { /* Protocol version */ unsigned int c_version; + possible_net_t c_net; }; +static inline +struct net *rds_conn_net(struct rds_connection *conn) +{ + return read_pnet(&conn->c_net); +} + +static inline +void rds_conn_net_set(struct rds_connection *conn, struct net *net) +{ + write_pnet(&conn->c_net, net); +} + #define RDS_FLAG_CONG_BITMAP 0x01 #define RDS_FLAG_ACK_REQUIRED 0x02 #define RDS_FLAG_RETRANSMITTED 0x04 @@ -417,7 +431,7 @@ struct rds_transport { unsigned int t_prefer_loopback:1; unsigned int t_type; - int (*laddr_check)(__be32 addr); + int (*laddr_check)(struct net *net, __be32 addr); int (*conn_alloc)(struct rds_connection *conn, gfp_t gfp); void (*conn_free)(void *data); int (*conn_connect)(struct rds_connection *conn); @@ -608,9 +622,11 @@ struct rds_message *rds_cong_update_alloc(struct rds_connection *conn); /* conn.c */ int rds_conn_init(void); void rds_conn_exit(void); -struct rds_connection *rds_conn_create(__be32 laddr, __be32 faddr, +struct rds_connection *rds_conn_create(struct net *net, + __be32 laddr, __be32 faddr, struct rds_transport *trans, gfp_t gfp); -struct rds_connection *rds_conn_create_outgoing(__be32 laddr, __be32 faddr, +struct rds_connection *rds_conn_create_outgoing(struct net *net, + __be32 laddr, __be32 faddr, struct rds_transport *trans, gfp_t gfp); void rds_conn_shutdown(struct rds_connection *conn); void rds_conn_destroy(struct rds_connection *conn); @@ -795,7 +811,7 @@ void rds_connect_complete(struct rds_connection *conn); /* transport.c */ int rds_trans_register(struct rds_transport *trans); void rds_trans_unregister(struct rds_transport *trans); -struct rds_transport *rds_trans_get_preferred(__be32 addr); +struct rds_transport *rds_trans_get_preferred(struct net *net, __be32 addr); void rds_trans_put(struct rds_transport *trans); unsigned int rds_trans_stats_info_copy(struct rds_info_iterator *iter, unsigned int avail); diff --git a/net/rds/send.c b/net/rds/send.c index e9430f537f9c..4df61a515b83 100644 --- a/net/rds/send.c +++ b/net/rds/send.c @@ -282,26 +282,34 @@ restart: /* The transport either sends the whole rdma or none of it */ if (rm->rdma.op_active && !conn->c_xmit_rdma_sent) { rm->m_final_op = &rm->rdma; + /* The transport owns the mapped memory for now. + * You can't unmap it while it's on the send queue + */ + set_bit(RDS_MSG_MAPPED, &rm->m_flags); ret = conn->c_trans->xmit_rdma(conn, &rm->rdma); - if (ret) + if (ret) { + clear_bit(RDS_MSG_MAPPED, &rm->m_flags); + wake_up_interruptible(&rm->m_flush_wait); break; + } conn->c_xmit_rdma_sent = 1; - /* The transport owns the mapped memory for now. - * You can't unmap it while it's on the send queue */ - set_bit(RDS_MSG_MAPPED, &rm->m_flags); } if (rm->atomic.op_active && !conn->c_xmit_atomic_sent) { rm->m_final_op = &rm->atomic; + /* The transport owns the mapped memory for now. + * You can't unmap it while it's on the send queue + */ + set_bit(RDS_MSG_MAPPED, &rm->m_flags); ret = conn->c_trans->xmit_atomic(conn, &rm->atomic); - if (ret) + if (ret) { + clear_bit(RDS_MSG_MAPPED, &rm->m_flags); + wake_up_interruptible(&rm->m_flush_wait); break; + } conn->c_xmit_atomic_sent = 1; - /* The transport owns the mapped memory for now. - * You can't unmap it while it's on the send queue */ - set_bit(RDS_MSG_MAPPED, &rm->m_flags); } /* @@ -411,7 +419,8 @@ over_batch: */ if (ret == 0) { smp_mb(); - if (!list_empty(&conn->c_send_queue) && + if ((test_bit(0, &conn->c_map_queued) || + !list_empty(&conn->c_send_queue)) && send_gen == conn->c_send_gen) { rds_stats_inc(s_send_lock_queue_raced); goto restart; @@ -769,8 +778,22 @@ void rds_send_drop_to(struct rds_sock *rs, struct sockaddr_in *dest) while (!list_empty(&list)) { rm = list_entry(list.next, struct rds_message, m_sock_item); list_del_init(&rm->m_sock_item); - rds_message_wait(rm); + + /* just in case the code above skipped this message + * because RDS_MSG_ON_CONN wasn't set, run it again here + * taking m_rs_lock is the only thing that keeps us + * from racing with ack processing. + */ + spin_lock_irqsave(&rm->m_rs_lock, flags); + + spin_lock(&rs->rs_lock); + __rds_send_complete(rs, rm, RDS_RDMA_CANCELED); + spin_unlock(&rs->rs_lock); + + rm->m_rs = NULL; + spin_unlock_irqrestore(&rm->m_rs_lock, flags); + rds_message_put(rm); } } @@ -992,6 +1015,11 @@ int rds_sendmsg(struct socket *sock, struct msghdr *msg, size_t payload_len) goto out; } + if (payload_len > rds_sk_sndbuf(rs)) { + ret = -EMSGSIZE; + goto out; + } + /* size of rm including all sgs */ ret = rds_rm_size(msg, payload_len); if (ret < 0) @@ -1023,7 +1051,8 @@ int rds_sendmsg(struct socket *sock, struct msghdr *msg, size_t payload_len) if (rs->rs_conn && rs->rs_conn->c_faddr == daddr) conn = rs->rs_conn; else { - conn = rds_conn_create_outgoing(rs->rs_bound_addr, daddr, + conn = rds_conn_create_outgoing(sock_net(sock->sk), + rs->rs_bound_addr, daddr, rs->rs_transport, sock->sk->sk_allocation); if (IS_ERR(conn)) { @@ -1063,11 +1092,7 @@ int rds_sendmsg(struct socket *sock, struct msghdr *msg, size_t payload_len) while (!rds_send_queue_rm(rs, conn, rm, rs->rs_bound_port, dport, &queued)) { rds_stats_inc(s_send_queue_full); - /* XXX make sure this is reasonable */ - if (payload_len > rds_sk_sndbuf(rs)) { - ret = -EMSGSIZE; - goto out; - } + if (nonblock) { ret = -EAGAIN; goto out; diff --git a/net/rds/tcp.c b/net/rds/tcp.c index edac9ef2bc8b..c42b60bf4c68 100644 --- a/net/rds/tcp.c +++ b/net/rds/tcp.c @@ -35,6 +35,9 @@ #include <linux/in.h> #include <linux/module.h> #include <net/tcp.h> +#include <net/net_namespace.h> +#include <net/netns/generic.h> +#include <net/tcp.h> #include "rds.h" #include "tcp.h" @@ -189,9 +192,9 @@ out: spin_unlock_irqrestore(&rds_tcp_tc_list_lock, flags); } -static int rds_tcp_laddr_check(__be32 addr) +static int rds_tcp_laddr_check(struct net *net, __be32 addr) { - if (inet_addr_type(&init_net, addr) == RTN_LOCAL) + if (inet_addr_type(net, addr) == RTN_LOCAL) return 0; return -EADDRNOTAVAIL; } @@ -250,16 +253,7 @@ static void rds_tcp_destroy_conns(void) } } -static void rds_tcp_exit(void) -{ - rds_info_deregister_func(RDS_INFO_TCP_SOCKETS, rds_tcp_tc_info); - rds_tcp_listen_stop(); - rds_tcp_destroy_conns(); - rds_trans_unregister(&rds_tcp_transport); - rds_tcp_recv_exit(); - kmem_cache_destroy(rds_tcp_conn_slab); -} -module_exit(rds_tcp_exit); +static void rds_tcp_exit(void); struct rds_transport rds_tcp_transport = { .laddr_check = rds_tcp_laddr_check, @@ -281,6 +275,136 @@ struct rds_transport rds_tcp_transport = { .t_prefer_loopback = 1, }; +static int rds_tcp_netid; + +/* per-network namespace private data for this module */ +struct rds_tcp_net { + struct socket *rds_tcp_listen_sock; + struct work_struct rds_tcp_accept_w; +}; + +static void rds_tcp_accept_worker(struct work_struct *work) +{ + struct rds_tcp_net *rtn = container_of(work, + struct rds_tcp_net, + rds_tcp_accept_w); + + while (rds_tcp_accept_one(rtn->rds_tcp_listen_sock) == 0) + cond_resched(); +} + +void rds_tcp_accept_work(struct sock *sk) +{ + struct net *net = sock_net(sk); + struct rds_tcp_net *rtn = net_generic(net, rds_tcp_netid); + + queue_work(rds_wq, &rtn->rds_tcp_accept_w); +} + +static __net_init int rds_tcp_init_net(struct net *net) +{ + struct rds_tcp_net *rtn = net_generic(net, rds_tcp_netid); + + rtn->rds_tcp_listen_sock = rds_tcp_listen_init(net); + if (!rtn->rds_tcp_listen_sock) { + pr_warn("could not set up listen sock\n"); + return -EAFNOSUPPORT; + } + INIT_WORK(&rtn->rds_tcp_accept_w, rds_tcp_accept_worker); + return 0; +} + +static void __net_exit rds_tcp_exit_net(struct net *net) +{ + struct rds_tcp_net *rtn = net_generic(net, rds_tcp_netid); + + /* If rds_tcp_exit_net() is called as a result of netns deletion, + * the rds_tcp_kill_sock() device notifier would already have cleaned + * up the listen socket, thus there is no work to do in this function. + * + * If rds_tcp_exit_net() is called as a result of module unload, + * i.e., due to rds_tcp_exit() -> unregister_pernet_subsys(), then + * we do need to clean up the listen socket here. + */ + if (rtn->rds_tcp_listen_sock) { + rds_tcp_listen_stop(rtn->rds_tcp_listen_sock); + rtn->rds_tcp_listen_sock = NULL; + flush_work(&rtn->rds_tcp_accept_w); + } +} + +static struct pernet_operations rds_tcp_net_ops = { + .init = rds_tcp_init_net, + .exit = rds_tcp_exit_net, + .id = &rds_tcp_netid, + .size = sizeof(struct rds_tcp_net), +}; + +static void rds_tcp_kill_sock(struct net *net) +{ + struct rds_tcp_connection *tc, *_tc; + struct sock *sk; + LIST_HEAD(tmp_list); + struct rds_tcp_net *rtn = net_generic(net, rds_tcp_netid); + + rds_tcp_listen_stop(rtn->rds_tcp_listen_sock); + rtn->rds_tcp_listen_sock = NULL; + flush_work(&rtn->rds_tcp_accept_w); + spin_lock_irq(&rds_tcp_conn_lock); + list_for_each_entry_safe(tc, _tc, &rds_tcp_conn_list, t_tcp_node) { + struct net *c_net = read_pnet(&tc->conn->c_net); + + if (net != c_net || !tc->t_sock) + continue; + list_move_tail(&tc->t_tcp_node, &tmp_list); + } + spin_unlock_irq(&rds_tcp_conn_lock); + list_for_each_entry_safe(tc, _tc, &tmp_list, t_tcp_node) { + sk = tc->t_sock->sk; + sk->sk_prot->disconnect(sk, 0); + tcp_done(sk); + if (tc->conn->c_passive) + rds_conn_destroy(tc->conn->c_passive); + rds_conn_destroy(tc->conn); + } +} + +static int rds_tcp_dev_event(struct notifier_block *this, + unsigned long event, void *ptr) +{ + struct net_device *dev = netdev_notifier_info_to_dev(ptr); + + /* rds-tcp registers as a pernet subys, so the ->exit will only + * get invoked after network acitivity has quiesced. We need to + * clean up all sockets to quiesce network activity, and use + * the unregistration of the per-net loopback device as a trigger + * to start that cleanup. + */ + if (event == NETDEV_UNREGISTER_FINAL && + dev->ifindex == LOOPBACK_IFINDEX) + rds_tcp_kill_sock(dev_net(dev)); + + return NOTIFY_DONE; +} + +static struct notifier_block rds_tcp_dev_notifier = { + .notifier_call = rds_tcp_dev_event, + .priority = -10, /* must be called after other network notifiers */ +}; + +static void rds_tcp_exit(void) +{ + rds_info_deregister_func(RDS_INFO_TCP_SOCKETS, rds_tcp_tc_info); + unregister_pernet_subsys(&rds_tcp_net_ops); + if (unregister_netdevice_notifier(&rds_tcp_dev_notifier)) + pr_warn("could not unregister rds_tcp_dev_notifier\n"); + rds_tcp_destroy_conns(); + rds_trans_unregister(&rds_tcp_transport); + rds_tcp_recv_exit(); + kmem_cache_destroy(rds_tcp_conn_slab); +} +module_exit(rds_tcp_exit); + static int rds_tcp_init(void) { int ret; @@ -293,6 +417,16 @@ static int rds_tcp_init(void) goto out; } + ret = register_netdevice_notifier(&rds_tcp_dev_notifier); + if (ret) { + pr_warn("could not register rds_tcp_dev_notifier\n"); + goto out; + } + + ret = register_pernet_subsys(&rds_tcp_net_ops); + if (ret) + goto out_slab; + ret = rds_tcp_recv_init(); if (ret) goto out_slab; @@ -301,19 +435,14 @@ static int rds_tcp_init(void) if (ret) goto out_recv; - ret = rds_tcp_listen_init(); - if (ret) - goto out_register; - rds_info_register_func(RDS_INFO_TCP_SOCKETS, rds_tcp_tc_info); goto out; -out_register: - rds_trans_unregister(&rds_tcp_transport); out_recv: rds_tcp_recv_exit(); out_slab: + unregister_pernet_subsys(&rds_tcp_net_ops); kmem_cache_destroy(rds_tcp_conn_slab); out: return ret; diff --git a/net/rds/tcp.h b/net/rds/tcp.h index 0dbdd37162da..64f873c0c6b6 100644 --- a/net/rds/tcp.h +++ b/net/rds/tcp.h @@ -52,6 +52,7 @@ u32 rds_tcp_snd_nxt(struct rds_tcp_connection *tc); u32 rds_tcp_snd_una(struct rds_tcp_connection *tc); u64 rds_tcp_map_seq(struct rds_tcp_connection *tc, u32 seq); extern struct rds_transport rds_tcp_transport; +void rds_tcp_accept_work(struct sock *sk); /* tcp_connect.c */ int rds_tcp_conn_connect(struct rds_connection *conn); @@ -59,9 +60,11 @@ void rds_tcp_conn_shutdown(struct rds_connection *conn); void rds_tcp_state_change(struct sock *sk); /* tcp_listen.c */ -int rds_tcp_listen_init(void); -void rds_tcp_listen_stop(void); +struct socket *rds_tcp_listen_init(struct net *); +void rds_tcp_listen_stop(struct socket *); void rds_tcp_listen_data_ready(struct sock *sk); +int rds_tcp_accept_one(struct socket *sock); +int rds_tcp_keepalive(struct socket *sock); /* tcp_recv.c */ int rds_tcp_recv_init(void); diff --git a/net/rds/tcp_connect.c b/net/rds/tcp_connect.c index 973109c7b8e8..5cb16875c460 100644 --- a/net/rds/tcp_connect.c +++ b/net/rds/tcp_connect.c @@ -79,7 +79,8 @@ int rds_tcp_conn_connect(struct rds_connection *conn) struct sockaddr_in src, dest; int ret; - ret = sock_create(PF_INET, SOCK_STREAM, IPPROTO_TCP, &sock); + ret = sock_create_kern(rds_conn_net(conn), PF_INET, + SOCK_STREAM, IPPROTO_TCP, &sock); if (ret < 0) goto out; @@ -111,10 +112,12 @@ int rds_tcp_conn_connect(struct rds_connection *conn) rdsdebug("connect to address %pI4 returned %d\n", &conn->c_faddr, ret); if (ret == -EINPROGRESS) ret = 0; - if (ret == 0) + if (ret == 0) { + rds_tcp_keepalive(sock); sock = NULL; - else + } else { rds_tcp_restore_callbacks(sock, conn->c_transport_data); + } out: if (sock) diff --git a/net/rds/tcp_listen.c b/net/rds/tcp_listen.c index 0da49e34495f..444d78d0bd77 100644 --- a/net/rds/tcp_listen.c +++ b/net/rds/tcp_listen.c @@ -38,14 +38,7 @@ #include "rds.h" #include "tcp.h" -/* - * cheesy, but simple.. - */ -static void rds_tcp_accept_worker(struct work_struct *work); -static DECLARE_WORK(rds_tcp_listen_work, rds_tcp_accept_worker); -static struct socket *rds_tcp_listen_sock; - -static int rds_tcp_keepalive(struct socket *sock) +int rds_tcp_keepalive(struct socket *sock) { /* values below based on xs_udp_default_timeout */ int keepidle = 5; /* send a probe 'keepidle' secs after last data */ @@ -77,7 +70,7 @@ bail: return ret; } -static int rds_tcp_accept_one(struct socket *sock) +int rds_tcp_accept_one(struct socket *sock) { struct socket *new_sock = NULL; struct rds_connection *conn; @@ -85,8 +78,9 @@ static int rds_tcp_accept_one(struct socket *sock) struct inet_sock *inet; struct rds_tcp_connection *rs_tcp; - ret = sock_create_lite(sock->sk->sk_family, sock->sk->sk_type, - sock->sk->sk_protocol, &new_sock); + ret = sock_create_kern(sock_net(sock->sk), sock->sk->sk_family, + sock->sk->sk_type, sock->sk->sk_protocol, + &new_sock); if (ret) goto out; @@ -108,7 +102,8 @@ static int rds_tcp_accept_one(struct socket *sock) &inet->inet_saddr, ntohs(inet->inet_sport), &inet->inet_daddr, ntohs(inet->inet_dport)); - conn = rds_conn_create(inet->inet_saddr, inet->inet_daddr, + conn = rds_conn_create(sock_net(sock->sk), + inet->inet_saddr, inet->inet_daddr, &rds_tcp_transport, GFP_KERNEL); if (IS_ERR(conn)) { ret = PTR_ERR(conn); @@ -148,12 +143,6 @@ out: return ret; } -static void rds_tcp_accept_worker(struct work_struct *work) -{ - while (rds_tcp_accept_one(rds_tcp_listen_sock) == 0) - cond_resched(); -} - void rds_tcp_listen_data_ready(struct sock *sk) { void (*ready)(struct sock *sk); @@ -174,20 +163,20 @@ void rds_tcp_listen_data_ready(struct sock *sk) * socket */ if (sk->sk_state == TCP_LISTEN) - queue_work(rds_wq, &rds_tcp_listen_work); + rds_tcp_accept_work(sk); out: read_unlock(&sk->sk_callback_lock); ready(sk); } -int rds_tcp_listen_init(void) +struct socket *rds_tcp_listen_init(struct net *net) { struct sockaddr_in sin; struct socket *sock = NULL; int ret; - ret = sock_create(PF_INET, SOCK_STREAM, IPPROTO_TCP, &sock); + ret = sock_create_kern(net, PF_INET, SOCK_STREAM, IPPROTO_TCP, &sock); if (ret < 0) goto out; @@ -211,17 +200,15 @@ int rds_tcp_listen_init(void) if (ret < 0) goto out; - rds_tcp_listen_sock = sock; - sock = NULL; + return sock; out: if (sock) sock_release(sock); - return ret; + return NULL; } -void rds_tcp_listen_stop(void) +void rds_tcp_listen_stop(struct socket *sock) { - struct socket *sock = rds_tcp_listen_sock; struct sock *sk; if (!sock) @@ -242,5 +229,4 @@ void rds_tcp_listen_stop(void) /* wait for accepts to stop and close the socket */ flush_workqueue(rds_wq); sock_release(sock); - rds_tcp_listen_sock = NULL; } diff --git a/net/rds/transport.c b/net/rds/transport.c index 83498e1c75b8..f3afd1d60d3c 100644 --- a/net/rds/transport.c +++ b/net/rds/transport.c @@ -77,7 +77,7 @@ void rds_trans_put(struct rds_transport *trans) module_put(trans->t_owner); } -struct rds_transport *rds_trans_get_preferred(__be32 addr) +struct rds_transport *rds_trans_get_preferred(struct net *net, __be32 addr) { struct rds_transport *ret = NULL; struct rds_transport *trans; @@ -90,7 +90,7 @@ struct rds_transport *rds_trans_get_preferred(__be32 addr) for (i = 0; i < RDS_TRANS_COUNT; i++) { trans = transports[i]; - if (trans && (trans->laddr_check(addr) == 0) && + if (trans && (trans->laddr_check(net, addr) == 0) && (!trans->t_owner || try_module_get(trans->t_owner))) { ret = trans; break; diff --git a/net/rfkill/Kconfig b/net/rfkill/Kconfig index 4c10e7e6c9f6..598d374f6a35 100644 --- a/net/rfkill/Kconfig +++ b/net/rfkill/Kconfig @@ -36,7 +36,8 @@ config RFKILL_REGULATOR config RFKILL_GPIO tristate "GPIO RFKILL driver" - depends on RFKILL && GPIOLIB + depends on RFKILL + depends on GPIOLIB || COMPILE_TEST default n help If you say yes here you get support of a generic gpio RFKILL diff --git a/net/rfkill/core.c b/net/rfkill/core.c index f12149a29cb1..b41e9ea2ffff 100644 --- a/net/rfkill/core.c +++ b/net/rfkill/core.c @@ -341,7 +341,15 @@ static void __rfkill_switch_all(const enum rfkill_type type, bool blocked) { struct rfkill *rfkill; - rfkill_global_states[type].cur = blocked; + if (type == RFKILL_TYPE_ALL) { + int i; + + for (i = 0; i < NUM_RFKILL_TYPES; i++) + rfkill_global_states[i].cur = blocked; + } else { + rfkill_global_states[type].cur = blocked; + } + list_for_each_entry(rfkill, &rfkill_list, node) { if (rfkill->type != type && type != RFKILL_TYPE_ALL) continue; diff --git a/net/rfkill/rfkill-gpio.c b/net/rfkill/rfkill-gpio.c index d5d58d919552..93127220cb54 100644 --- a/net/rfkill/rfkill-gpio.c +++ b/net/rfkill/rfkill-gpio.c @@ -164,7 +164,6 @@ static int rfkill_gpio_remove(struct platform_device *pdev) #ifdef CONFIG_ACPI static const struct acpi_device_id rfkill_acpi_match[] = { { "BCM2E1A", RFKILL_TYPE_BLUETOOTH }, - { "BCM2E39", RFKILL_TYPE_BLUETOOTH }, { "BCM2E3D", RFKILL_TYPE_BLUETOOTH }, { "BCM2E40", RFKILL_TYPE_BLUETOOTH }, { "BCM2E64", RFKILL_TYPE_BLUETOOTH }, diff --git a/net/sched/act_api.c b/net/sched/act_api.c index 43ec92680ae8..06e7c4a37245 100644 --- a/net/sched/act_api.c +++ b/net/sched/act_api.c @@ -27,7 +27,16 @@ #include <net/act_api.h> #include <net/netlink.h> -void tcf_hash_destroy(struct tc_action *a) +static void free_tcf(struct rcu_head *head) +{ + struct tcf_common *p = container_of(head, struct tcf_common, tcfc_rcu); + + free_percpu(p->cpu_bstats); + free_percpu(p->cpu_qstats); + kfree(p); +} + +static void tcf_hash_destroy(struct tc_action *a) { struct tcf_common *p = a->priv; struct tcf_hashinfo *hinfo = a->ops->hinfo; @@ -41,9 +50,8 @@ void tcf_hash_destroy(struct tc_action *a) * gen_estimator est_timer() might access p->tcfc_lock * or bstats, wait a RCU grace period before freeing p */ - kfree_rcu(p, tcfc_rcu); + call_rcu(&p->tcfc_rcu, free_tcf); } -EXPORT_SYMBOL(tcf_hash_destroy); int __tcf_hash_release(struct tc_action *a, bool bind, bool strict) { @@ -231,15 +239,16 @@ void tcf_hash_cleanup(struct tc_action *a, struct nlattr *est) if (est) gen_kill_estimator(&pc->tcfc_bstats, &pc->tcfc_rate_est); - kfree_rcu(pc, tcfc_rcu); + call_rcu(&pc->tcfc_rcu, free_tcf); } EXPORT_SYMBOL(tcf_hash_cleanup); int tcf_hash_create(u32 index, struct nlattr *est, struct tc_action *a, - int size, int bind) + int size, int bind, bool cpustats) { struct tcf_hashinfo *hinfo = a->ops->hinfo; struct tcf_common *p = kzalloc(size, GFP_KERNEL); + int err = -ENOMEM; if (unlikely(!p)) return -ENOMEM; @@ -247,18 +256,32 @@ int tcf_hash_create(u32 index, struct nlattr *est, struct tc_action *a, if (bind) p->tcfc_bindcnt = 1; + if (cpustats) { + p->cpu_bstats = netdev_alloc_pcpu_stats(struct gnet_stats_basic_cpu); + if (!p->cpu_bstats) { +err1: + kfree(p); + return err; + } + p->cpu_qstats = alloc_percpu(struct gnet_stats_queue); + if (!p->cpu_qstats) { +err2: + free_percpu(p->cpu_bstats); + goto err1; + } + } spin_lock_init(&p->tcfc_lock); INIT_HLIST_NODE(&p->tcfc_head); p->tcfc_index = index ? index : tcf_hash_new_index(hinfo); p->tcfc_tm.install = jiffies; p->tcfc_tm.lastuse = jiffies; if (est) { - int err = gen_new_estimator(&p->tcfc_bstats, NULL, - &p->tcfc_rate_est, - &p->tcfc_lock, est); + err = gen_new_estimator(&p->tcfc_bstats, p->cpu_bstats, + &p->tcfc_rate_est, + &p->tcfc_lock, est); if (err) { - kfree(p); - return err; + free_percpu(p->cpu_qstats); + goto err2; } } @@ -616,10 +639,10 @@ int tcf_action_copy_stats(struct sk_buff *skb, struct tc_action *a, if (err < 0) goto errout; - if (gnet_stats_copy_basic(&d, NULL, &p->tcfc_bstats) < 0 || + if (gnet_stats_copy_basic(&d, p->cpu_bstats, &p->tcfc_bstats) < 0 || gnet_stats_copy_rate_est(&d, &p->tcfc_bstats, &p->tcfc_rate_est) < 0 || - gnet_stats_copy_queue(&d, NULL, + gnet_stats_copy_queue(&d, p->cpu_qstats, &p->tcfc_qstats, p->tcfc_qstats.qlen) < 0) goto errout; diff --git a/net/sched/act_bpf.c b/net/sched/act_bpf.c index d0edeb7a1950..559bfa011bda 100644 --- a/net/sched/act_bpf.c +++ b/net/sched/act_bpf.c @@ -37,25 +37,24 @@ static int tcf_bpf(struct sk_buff *skb, const struct tc_action *act, struct tcf_result *res) { struct tcf_bpf *prog = act->priv; + struct bpf_prog *filter; int action, filter_res; bool at_ingress = G_TC_AT(skb->tc_verd) & AT_INGRESS; if (unlikely(!skb_mac_header_was_set(skb))) return TC_ACT_UNSPEC; - spin_lock(&prog->tcf_lock); - - prog->tcf_tm.lastuse = jiffies; - bstats_update(&prog->tcf_bstats, skb); + tcf_lastuse_update(&prog->tcf_tm); + bstats_cpu_update(this_cpu_ptr(prog->common.cpu_bstats), skb); - /* Needed here for accessing maps. */ rcu_read_lock(); + filter = rcu_dereference(prog->filter); if (at_ingress) { __skb_push(skb, skb->mac_len); - filter_res = BPF_PROG_RUN(prog->filter, skb); + filter_res = BPF_PROG_RUN(filter, skb); __skb_pull(skb, skb->mac_len); } else { - filter_res = BPF_PROG_RUN(prog->filter, skb); + filter_res = BPF_PROG_RUN(filter, skb); } rcu_read_unlock(); @@ -77,7 +76,7 @@ static int tcf_bpf(struct sk_buff *skb, const struct tc_action *act, break; case TC_ACT_SHOT: action = filter_res; - prog->tcf_qstats.drops++; + qstats_drop_inc(this_cpu_ptr(prog->common.cpu_qstats)); break; case TC_ACT_UNSPEC: action = prog->tcf_action; @@ -87,7 +86,6 @@ static int tcf_bpf(struct sk_buff *skb, const struct tc_action *act, break; } - spin_unlock(&prog->tcf_lock); return action; } @@ -263,7 +261,10 @@ static void tcf_bpf_prog_fill_cfg(const struct tcf_bpf *prog, struct tcf_bpf_cfg *cfg) { cfg->is_ebpf = tcf_bpf_is_ebpf(prog); - cfg->filter = prog->filter; + /* updates to prog->filter are prevented, since it's called either + * with rtnl lock or during final cleanup in rcu callback + */ + cfg->filter = rcu_dereference_protected(prog->filter, 1); cfg->bpf_ops = prog->bpf_ops; cfg->bpf_name = prog->bpf_name; @@ -278,7 +279,7 @@ static int tcf_bpf_init(struct net *net, struct nlattr *nla, struct tc_act_bpf *parm; struct tcf_bpf *prog; bool is_bpf, is_ebpf; - int ret; + int ret, res = 0; if (!nla) return -EINVAL; @@ -287,45 +288,47 @@ static int tcf_bpf_init(struct net *net, struct nlattr *nla, if (ret < 0) return ret; - is_bpf = tb[TCA_ACT_BPF_OPS_LEN] && tb[TCA_ACT_BPF_OPS]; - is_ebpf = tb[TCA_ACT_BPF_FD]; - - if ((!is_bpf && !is_ebpf) || (is_bpf && is_ebpf) || - !tb[TCA_ACT_BPF_PARMS]) + if (!tb[TCA_ACT_BPF_PARMS]) return -EINVAL; parm = nla_data(tb[TCA_ACT_BPF_PARMS]); - memset(&cfg, 0, sizeof(cfg)); - - ret = is_bpf ? tcf_bpf_init_from_ops(tb, &cfg) : - tcf_bpf_init_from_efd(tb, &cfg); - if (ret < 0) - return ret; - if (!tcf_hash_check(parm->index, act, bind)) { ret = tcf_hash_create(parm->index, est, act, - sizeof(*prog), bind); + sizeof(*prog), bind, true); if (ret < 0) - goto destroy_fp; + return ret; - ret = ACT_P_CREATED; + res = ACT_P_CREATED; } else { /* Don't override defaults. */ if (bind) - goto destroy_fp; + return 0; tcf_hash_release(act, bind); - if (!replace) { - ret = -EEXIST; - goto destroy_fp; - } + if (!replace) + return -EEXIST; } + is_bpf = tb[TCA_ACT_BPF_OPS_LEN] && tb[TCA_ACT_BPF_OPS]; + is_ebpf = tb[TCA_ACT_BPF_FD]; + + if ((!is_bpf && !is_ebpf) || (is_bpf && is_ebpf)) { + ret = -EINVAL; + goto out; + } + + memset(&cfg, 0, sizeof(cfg)); + + ret = is_bpf ? tcf_bpf_init_from_ops(tb, &cfg) : + tcf_bpf_init_from_efd(tb, &cfg); + if (ret < 0) + goto out; + prog = to_bpf(act); - spin_lock_bh(&prog->tcf_lock); + ASSERT_RTNL(); - if (ret != ACT_P_CREATED) + if (res != ACT_P_CREATED) tcf_bpf_prog_fill_cfg(prog, &old); prog->bpf_ops = cfg.bpf_ops; @@ -337,19 +340,21 @@ static int tcf_bpf_init(struct net *net, struct nlattr *nla, prog->bpf_fd = cfg.bpf_fd; prog->tcf_action = parm->action; - prog->filter = cfg.filter; + rcu_assign_pointer(prog->filter, cfg.filter); - spin_unlock_bh(&prog->tcf_lock); - - if (ret == ACT_P_CREATED) + if (res == ACT_P_CREATED) { tcf_hash_insert(act); - else + } else { + /* make sure the program being replaced is no longer executing */ + synchronize_rcu(); tcf_bpf_cfg_cleanup(&old); + } - return ret; + return res; +out: + if (res == ACT_P_CREATED) + tcf_hash_cleanup(act, est); -destroy_fp: - tcf_bpf_cfg_cleanup(&cfg); return ret; } diff --git a/net/sched/act_connmark.c b/net/sched/act_connmark.c index 295d14bd6c67..5019a47b9270 100644 --- a/net/sched/act_connmark.c +++ b/net/sched/act_connmark.c @@ -37,6 +37,7 @@ static int tcf_connmark(struct sk_buff *skb, const struct tc_action *a, struct nf_conntrack_tuple tuple; enum ip_conntrack_info ctinfo; struct tcf_connmark_info *ca = a->priv; + struct nf_conntrack_zone zone; struct nf_conn *c; int proto; @@ -70,7 +71,10 @@ static int tcf_connmark(struct sk_buff *skb, const struct tc_action *a, proto, &tuple)) goto out; - thash = nf_conntrack_find_get(dev_net(skb->dev), ca->zone, &tuple); + zone.id = ca->zone; + zone.dir = NF_CT_DEFAULT_ZONE_DIR; + + thash = nf_conntrack_find_get(dev_net(skb->dev), &zone, &tuple); if (!thash) goto out; @@ -108,7 +112,8 @@ static int tcf_connmark_init(struct net *net, struct nlattr *nla, parm = nla_data(tb[TCA_CONNMARK_PARMS]); if (!tcf_hash_check(parm->index, a, bind)) { - ret = tcf_hash_create(parm->index, est, a, sizeof(*ci), bind); + ret = tcf_hash_create(parm->index, est, a, sizeof(*ci), + bind, false); if (ret) return ret; diff --git a/net/sched/act_csum.c b/net/sched/act_csum.c index 4cd5cf1aedf8..b07c535ba8e7 100644 --- a/net/sched/act_csum.c +++ b/net/sched/act_csum.c @@ -62,7 +62,8 @@ static int tcf_csum_init(struct net *n, struct nlattr *nla, struct nlattr *est, parm = nla_data(tb[TCA_CSUM_PARMS]); if (!tcf_hash_check(parm->index, a, bind)) { - ret = tcf_hash_create(parm->index, est, a, sizeof(*p), bind); + ret = tcf_hash_create(parm->index, est, a, sizeof(*p), + bind, false); if (ret) return ret; ret = ACT_P_CREATED; diff --git a/net/sched/act_gact.c b/net/sched/act_gact.c index 7fffc2272701..5c1b05170736 100644 --- a/net/sched/act_gact.c +++ b/net/sched/act_gact.c @@ -28,14 +28,18 @@ #ifdef CONFIG_GACT_PROB static int gact_net_rand(struct tcf_gact *gact) { - if (!gact->tcfg_pval || prandom_u32() % gact->tcfg_pval) + smp_rmb(); /* coupled with smp_wmb() in tcf_gact_init() */ + if (prandom_u32() % gact->tcfg_pval) return gact->tcf_action; return gact->tcfg_paction; } static int gact_determ(struct tcf_gact *gact) { - if (!gact->tcfg_pval || gact->tcf_bstats.packets % gact->tcfg_pval) + u32 pack = atomic_inc_return(&gact->packets); + + smp_rmb(); /* coupled with smp_wmb() in tcf_gact_init() */ + if (pack % gact->tcfg_pval) return gact->tcf_action; return gact->tcfg_paction; } @@ -85,7 +89,8 @@ static int tcf_gact_init(struct net *net, struct nlattr *nla, #endif if (!tcf_hash_check(parm->index, a, bind)) { - ret = tcf_hash_create(parm->index, est, a, sizeof(*gact), bind); + ret = tcf_hash_create(parm->index, est, a, sizeof(*gact), + bind, true); if (ret) return ret; ret = ACT_P_CREATED; @@ -99,16 +104,19 @@ static int tcf_gact_init(struct net *net, struct nlattr *nla, gact = to_gact(a); - spin_lock_bh(&gact->tcf_lock); + ASSERT_RTNL(); gact->tcf_action = parm->action; #ifdef CONFIG_GACT_PROB if (p_parm) { gact->tcfg_paction = p_parm->paction; - gact->tcfg_pval = p_parm->pval; + gact->tcfg_pval = max_t(u16, 1, p_parm->pval); + /* Make sure tcfg_pval is written before tcfg_ptype + * coupled with smp_rmb() in gact_net_rand() & gact_determ() + */ + smp_wmb(); gact->tcfg_ptype = p_parm->ptype; } #endif - spin_unlock_bh(&gact->tcf_lock); if (ret == ACT_P_CREATED) tcf_hash_insert(a); return ret; @@ -118,23 +126,21 @@ static int tcf_gact(struct sk_buff *skb, const struct tc_action *a, struct tcf_result *res) { struct tcf_gact *gact = a->priv; - int action = TC_ACT_SHOT; + int action = READ_ONCE(gact->tcf_action); - spin_lock(&gact->tcf_lock); #ifdef CONFIG_GACT_PROB - if (gact->tcfg_ptype) - action = gact_rand[gact->tcfg_ptype](gact); - else - action = gact->tcf_action; -#else - action = gact->tcf_action; + { + u32 ptype = READ_ONCE(gact->tcfg_ptype); + + if (ptype) + action = gact_rand[ptype](gact); + } #endif - gact->tcf_bstats.bytes += qdisc_pkt_len(skb); - gact->tcf_bstats.packets++; + bstats_cpu_update(this_cpu_ptr(gact->common.cpu_bstats), skb); if (action == TC_ACT_SHOT) - gact->tcf_qstats.drops++; - gact->tcf_tm.lastuse = jiffies; - spin_unlock(&gact->tcf_lock); + qstats_drop_inc(this_cpu_ptr(gact->common.cpu_qstats)); + + tcf_lastuse_update(&gact->tcf_tm); return action; } diff --git a/net/sched/act_ipt.c b/net/sched/act_ipt.c index cbc8dd7dd48a..99c9cc1c7af9 100644 --- a/net/sched/act_ipt.c +++ b/net/sched/act_ipt.c @@ -114,7 +114,7 @@ static int tcf_ipt_init(struct net *net, struct nlattr *nla, struct nlattr *est, index = nla_get_u32(tb[TCA_IPT_INDEX]); if (!tcf_hash_check(index, a, bind) ) { - ret = tcf_hash_create(index, est, a, sizeof(*ipt), bind); + ret = tcf_hash_create(index, est, a, sizeof(*ipt), bind, false); if (ret) return ret; ret = ACT_P_CREATED; diff --git a/net/sched/act_mirred.c b/net/sched/act_mirred.c index 268545050ddb..2d1be4a760fd 100644 --- a/net/sched/act_mirred.c +++ b/net/sched/act_mirred.c @@ -35,9 +35,11 @@ static LIST_HEAD(mirred_list); static void tcf_mirred_release(struct tc_action *a, int bind) { struct tcf_mirred *m = to_mirred(a); + struct net_device *dev = rcu_dereference_protected(m->tcfm_dev, 1); + list_del(&m->tcfm_list); - if (m->tcfm_dev) - dev_put(m->tcfm_dev); + if (dev) + dev_put(dev); } static const struct nla_policy mirred_policy[TCA_MIRRED_MAX + 1] = { @@ -93,7 +95,8 @@ static int tcf_mirred_init(struct net *net, struct nlattr *nla, if (!tcf_hash_check(parm->index, a, bind)) { if (dev == NULL) return -EINVAL; - ret = tcf_hash_create(parm->index, est, a, sizeof(*m), bind); + ret = tcf_hash_create(parm->index, est, a, sizeof(*m), + bind, true); if (ret) return ret; ret = ACT_P_CREATED; @@ -107,18 +110,18 @@ static int tcf_mirred_init(struct net *net, struct nlattr *nla, } m = to_mirred(a); - spin_lock_bh(&m->tcf_lock); + ASSERT_RTNL(); m->tcf_action = parm->action; m->tcfm_eaction = parm->eaction; if (dev != NULL) { m->tcfm_ifindex = parm->ifindex; if (ret != ACT_P_CREATED) - dev_put(m->tcfm_dev); + dev_put(rcu_dereference_protected(m->tcfm_dev, 1)); dev_hold(dev); - m->tcfm_dev = dev; + rcu_assign_pointer(m->tcfm_dev, dev); m->tcfm_ok_push = ok_push; } - spin_unlock_bh(&m->tcf_lock); + if (ret == ACT_P_CREATED) { list_add(&m->tcfm_list, &mirred_list); tcf_hash_insert(a); @@ -133,20 +136,22 @@ static int tcf_mirred(struct sk_buff *skb, const struct tc_action *a, struct tcf_mirred *m = a->priv; struct net_device *dev; struct sk_buff *skb2; + int retval, err; u32 at; - int retval, err = 1; - spin_lock(&m->tcf_lock); - m->tcf_tm.lastuse = jiffies; - bstats_update(&m->tcf_bstats, skb); + tcf_lastuse_update(&m->tcf_tm); + + bstats_cpu_update(this_cpu_ptr(m->common.cpu_bstats), skb); - dev = m->tcfm_dev; - if (!dev) { - printk_once(KERN_NOTICE "tc mirred: target device is gone\n"); + rcu_read_lock(); + retval = READ_ONCE(m->tcf_action); + dev = rcu_dereference(m->tcfm_dev); + if (unlikely(!dev)) { + pr_notice_once("tc mirred: target device is gone\n"); goto out; } - if (!(dev->flags & IFF_UP)) { + if (unlikely(!(dev->flags & IFF_UP))) { net_notice_ratelimited("tc mirred to Houston: device %s is down\n", dev->name); goto out; @@ -154,7 +159,7 @@ static int tcf_mirred(struct sk_buff *skb, const struct tc_action *a, at = G_TC_AT(skb->tc_verd); skb2 = skb_clone(skb, GFP_ATOMIC); - if (skb2 == NULL) + if (!skb2) goto out; if (!(at & AT_EGRESS)) { @@ -170,16 +175,13 @@ static int tcf_mirred(struct sk_buff *skb, const struct tc_action *a, skb2->dev = dev; err = dev_queue_xmit(skb2); -out: if (err) { - m->tcf_qstats.overlimits++; +out: + qstats_overlimit_inc(this_cpu_ptr(m->common.cpu_qstats)); if (m->tcfm_eaction != TCA_EGRESS_MIRROR) retval = TC_ACT_SHOT; - else - retval = m->tcf_action; - } else - retval = m->tcf_action; - spin_unlock(&m->tcf_lock); + } + rcu_read_unlock(); return retval; } @@ -218,14 +220,16 @@ static int mirred_device_event(struct notifier_block *unused, struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct tcf_mirred *m; + ASSERT_RTNL(); if (event == NETDEV_UNREGISTER) list_for_each_entry(m, &mirred_list, tcfm_list) { - spin_lock_bh(&m->tcf_lock); - if (m->tcfm_dev == dev) { + if (rcu_access_pointer(m->tcfm_dev) == dev) { dev_put(dev); - m->tcfm_dev = NULL; + /* Note : no rcu grace period necessary, as + * net_device are already rcu protected. + */ + RCU_INIT_POINTER(m->tcfm_dev, NULL); } - spin_unlock_bh(&m->tcf_lock); } return NOTIFY_DONE; diff --git a/net/sched/act_nat.c b/net/sched/act_nat.c index 270a030d5fd0..b7c4ead8b5a8 100644 --- a/net/sched/act_nat.c +++ b/net/sched/act_nat.c @@ -55,7 +55,8 @@ static int tcf_nat_init(struct net *net, struct nlattr *nla, struct nlattr *est, parm = nla_data(tb[TCA_NAT_PARMS]); if (!tcf_hash_check(parm->index, a, bind)) { - ret = tcf_hash_create(parm->index, est, a, sizeof(*p), bind); + ret = tcf_hash_create(parm->index, est, a, sizeof(*p), + bind, false); if (ret) return ret; ret = ACT_P_CREATED; @@ -161,7 +162,8 @@ static int tcf_nat(struct sk_buff *skb, const struct tc_action *a, goto drop; tcph = (void *)(skb_network_header(skb) + ihl); - inet_proto_csum_replace4(&tcph->check, skb, addr, new_addr, 1); + inet_proto_csum_replace4(&tcph->check, skb, addr, new_addr, + true); break; } case IPPROTO_UDP: @@ -177,7 +179,7 @@ static int tcf_nat(struct sk_buff *skb, const struct tc_action *a, udph = (void *)(skb_network_header(skb) + ihl); if (udph->check || skb->ip_summed == CHECKSUM_PARTIAL) { inet_proto_csum_replace4(&udph->check, skb, addr, - new_addr, 1); + new_addr, true); if (!udph->check) udph->check = CSUM_MANGLED_0; } @@ -230,7 +232,7 @@ static int tcf_nat(struct sk_buff *skb, const struct tc_action *a, iph->saddr = new_addr; inet_proto_csum_replace4(&icmph->checksum, skb, addr, new_addr, - 0); + false); break; } default: diff --git a/net/sched/act_pedit.c b/net/sched/act_pedit.c index ff8b466a73f6..e38a7701f154 100644 --- a/net/sched/act_pedit.c +++ b/net/sched/act_pedit.c @@ -57,7 +57,8 @@ static int tcf_pedit_init(struct net *net, struct nlattr *nla, if (!tcf_hash_check(parm->index, a, bind)) { if (!parm->nkeys) return -EINVAL; - ret = tcf_hash_create(parm->index, est, a, sizeof(*p), bind); + ret = tcf_hash_create(parm->index, est, a, sizeof(*p), + bind, false); if (ret) return ret; p = to_pedit(a); diff --git a/net/sched/act_simple.c b/net/sched/act_simple.c index 6a8d9488613a..d6b708d6afdf 100644 --- a/net/sched/act_simple.c +++ b/net/sched/act_simple.c @@ -103,7 +103,8 @@ static int tcf_simp_init(struct net *net, struct nlattr *nla, defdata = nla_data(tb[TCA_DEF_DATA]); if (!tcf_hash_check(parm->index, a, bind)) { - ret = tcf_hash_create(parm->index, est, a, sizeof(*d), bind); + ret = tcf_hash_create(parm->index, est, a, sizeof(*d), + bind, false); if (ret) return ret; diff --git a/net/sched/act_skbedit.c b/net/sched/act_skbedit.c index fcfeeaf838be..6751b5f8c046 100644 --- a/net/sched/act_skbedit.c +++ b/net/sched/act_skbedit.c @@ -99,7 +99,8 @@ static int tcf_skbedit_init(struct net *net, struct nlattr *nla, parm = nla_data(tb[TCA_SKBEDIT_PARMS]); if (!tcf_hash_check(parm->index, a, bind)) { - ret = tcf_hash_create(parm->index, est, a, sizeof(*d), bind); + ret = tcf_hash_create(parm->index, est, a, sizeof(*d), + bind, false); if (ret) return ret; diff --git a/net/sched/act_vlan.c b/net/sched/act_vlan.c index d735ecf0b1a7..796785e0bf96 100644 --- a/net/sched/act_vlan.c +++ b/net/sched/act_vlan.c @@ -116,7 +116,8 @@ static int tcf_vlan_init(struct net *net, struct nlattr *nla, action = parm->v_action; if (!tcf_hash_check(parm->index, a, bind)) { - ret = tcf_hash_create(parm->index, est, a, sizeof(*v), bind); + ret = tcf_hash_create(parm->index, est, a, sizeof(*v), + bind, false); if (ret) return ret; diff --git a/net/sched/cls_cgroup.c b/net/sched/cls_cgroup.c index ea611b216412..4c85bd3a750c 100644 --- a/net/sched/cls_cgroup.c +++ b/net/sched/cls_cgroup.c @@ -30,35 +30,16 @@ static int cls_cgroup_classify(struct sk_buff *skb, const struct tcf_proto *tp, struct tcf_result *res) { struct cls_cgroup_head *head = rcu_dereference_bh(tp->root); - u32 classid; - - classid = task_cls_state(current)->classid; - - /* - * Due to the nature of the classifier it is required to ignore all - * packets originating from softirq context as accessing `current' - * would lead to false results. - * - * This test assumes that all callers of dev_queue_xmit() explicitely - * disable bh. Knowing this, it is possible to detect softirq based - * calls by looking at the number of nested bh disable calls because - * softirqs always disables bh. - */ - if (in_serving_softirq()) { - /* If there is an sk_classid we'll use that. */ - if (!skb->sk) - return -1; - classid = skb->sk->sk_classid; - } + u32 classid = task_get_classid(skb); if (!classid) return -1; - if (!tcf_em_tree_match(skb, &head->ematches, NULL)) return -1; res->classid = classid; res->class = 0; + return tcf_exts_exec(skb, &head->exts, res); } diff --git a/net/sched/cls_flow.c b/net/sched/cls_flow.c index bb2a0f529c1f..536838b657bf 100644 --- a/net/sched/cls_flow.c +++ b/net/sched/cls_flow.c @@ -301,7 +301,7 @@ static int flow_classify(struct sk_buff *skb, const struct tcf_proto *tp, keymask = f->keymask; if (keymask & FLOW_KEYS_NEEDED) - skb_flow_dissect_flow_keys(skb, &flow_keys); + skb_flow_dissect_flow_keys(skb, &flow_keys, 0); for (n = 0; n < f->nkeys; n++) { key = ffs(keymask) - 1; diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c index 2f3d03f99487..57692947ebbe 100644 --- a/net/sched/cls_flower.c +++ b/net/sched/cls_flower.c @@ -129,7 +129,7 @@ static int fl_classify(struct sk_buff *skb, const struct tcf_proto *tp, * so do it rather here. */ skb_key.basic.n_proto = skb->protocol; - skb_flow_dissect(skb, &head->dissector, &skb_key); + skb_flow_dissect(skb, &head->dissector, &skb_key, 0); fl_set_masked_key(&skb_mkey, &skb_key, &head->mask); diff --git a/net/sched/cls_rsvp.h b/net/sched/cls_rsvp.h index 02fa82792dab..f9c9fc075fe6 100644 --- a/net/sched/cls_rsvp.h +++ b/net/sched/cls_rsvp.h @@ -283,12 +283,22 @@ static int rsvp_init(struct tcf_proto *tp) return -ENOBUFS; } -static void -rsvp_delete_filter(struct tcf_proto *tp, struct rsvp_filter *f) +static void rsvp_delete_filter_rcu(struct rcu_head *head) { - tcf_unbind_filter(tp, &f->res); + struct rsvp_filter *f = container_of(head, struct rsvp_filter, rcu); + tcf_exts_destroy(&f->exts); - kfree_rcu(f, rcu); + kfree(f); +} + +static void rsvp_delete_filter(struct tcf_proto *tp, struct rsvp_filter *f) +{ + tcf_unbind_filter(tp, &f->res); + /* all classifiers are required to call tcf_exts_destroy() after rcu + * grace period, since converted-to-rcu actions are relying on that + * in cleanup() callback + */ + call_rcu(&f->rcu, rsvp_delete_filter_rcu); } static bool rsvp_destroy(struct tcf_proto *tp, bool force) diff --git a/net/sched/cls_tcindex.c b/net/sched/cls_tcindex.c index a557dbaf5afe..944c8ff45055 100644 --- a/net/sched/cls_tcindex.c +++ b/net/sched/cls_tcindex.c @@ -27,6 +27,7 @@ struct tcindex_filter_result { struct tcf_exts exts; struct tcf_result res; + struct rcu_head rcu; }; struct tcindex_filter { @@ -133,8 +134,23 @@ static int tcindex_init(struct tcf_proto *tp) return 0; } -static int -tcindex_delete(struct tcf_proto *tp, unsigned long arg) +static void tcindex_destroy_rexts(struct rcu_head *head) +{ + struct tcindex_filter_result *r; + + r = container_of(head, struct tcindex_filter_result, rcu); + tcf_exts_destroy(&r->exts); +} + +static void tcindex_destroy_fexts(struct rcu_head *head) +{ + struct tcindex_filter *f = container_of(head, struct tcindex_filter, rcu); + + tcf_exts_destroy(&f->result.exts); + kfree(f); +} + +static int tcindex_delete(struct tcf_proto *tp, unsigned long arg) { struct tcindex_data *p = rtnl_dereference(tp->root); struct tcindex_filter_result *r = (struct tcindex_filter_result *) arg; @@ -162,9 +178,14 @@ found: rcu_assign_pointer(*walk, rtnl_dereference(f->next)); } tcf_unbind_filter(tp, &r->res); - tcf_exts_destroy(&r->exts); + /* all classifiers are required to call tcf_exts_destroy() after rcu + * grace period, since converted-to-rcu actions are relying on that + * in cleanup() callback + */ if (f) - kfree_rcu(f, rcu); + call_rcu(&f->rcu, tcindex_destroy_fexts); + else + call_rcu(&r->rcu, tcindex_destroy_rexts); return 0; } diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c index f06aa01d60fd..f43c8f33f09e 100644 --- a/net/sched/sch_api.c +++ b/net/sched/sch_api.c @@ -1806,51 +1806,45 @@ done: * to this qdisc, (optionally) tests for protocol and asks * specific classifiers. */ -int tc_classify_compat(struct sk_buff *skb, const struct tcf_proto *tp, - struct tcf_result *res) +int tc_classify(struct sk_buff *skb, const struct tcf_proto *tp, + struct tcf_result *res, bool compat_mode) { __be16 protocol = tc_skb_protocol(skb); - int err; +#ifdef CONFIG_NET_CLS_ACT + const struct tcf_proto *old_tp = tp; + int limit = 0; +reclassify: +#endif for (; tp; tp = rcu_dereference_bh(tp->next)) { + int err; + if (tp->protocol != protocol && tp->protocol != htons(ETH_P_ALL)) continue; - err = tp->classify(skb, tp, res); + err = tp->classify(skb, tp, res); +#ifdef CONFIG_NET_CLS_ACT + if (unlikely(err == TC_ACT_RECLASSIFY && !compat_mode)) + goto reset; +#endif if (err >= 0) return err; } - return -1; -} -EXPORT_SYMBOL(tc_classify_compat); -int tc_classify(struct sk_buff *skb, const struct tcf_proto *tp, - struct tcf_result *res) -{ - int err = 0; -#ifdef CONFIG_NET_CLS_ACT - const struct tcf_proto *otp = tp; - int limit = 0; -reclassify: -#endif - - err = tc_classify_compat(skb, tp, res); + return -1; #ifdef CONFIG_NET_CLS_ACT - if (err == TC_ACT_RECLASSIFY) { - tp = otp; - - if (unlikely(limit++ >= MAX_REC_LOOP)) { - net_notice_ratelimited("%s: packet reclassify loop rule prio %u protocol %02x\n", - tp->q->ops->id, - tp->prio & 0xffff, - ntohs(tp->protocol)); - return TC_ACT_SHOT; - } - goto reclassify; +reset: + if (unlikely(limit++ >= MAX_REC_LOOP)) { + net_notice_ratelimited("%s: reclassify loop, rule prio %u, protocol %02x\n", + tp->q->ops->id, tp->prio & 0xffff, + ntohs(tp->protocol)); + return TC_ACT_SHOT; } + + tp = old_tp; + goto reclassify; #endif - return err; } EXPORT_SYMBOL(tc_classify); @@ -1947,6 +1941,7 @@ static int __init pktsched_init(void) register_qdisc(&bfifo_qdisc_ops); register_qdisc(&pfifo_head_drop_qdisc_ops); register_qdisc(&mq_qdisc_ops); + register_qdisc(&noqueue_qdisc_ops); rtnl_register(PF_UNSPEC, RTM_NEWQDISC, tc_modify_qdisc, NULL, NULL); rtnl_register(PF_UNSPEC, RTM_DELQDISC, tc_get_qdisc, NULL, NULL); diff --git a/net/sched/sch_atm.c b/net/sched/sch_atm.c index e3e2cc5fd068..1911af3ca7c0 100644 --- a/net/sched/sch_atm.c +++ b/net/sched/sch_atm.c @@ -375,7 +375,7 @@ static int atm_tc_enqueue(struct sk_buff *skb, struct Qdisc *sch) list_for_each_entry(flow, &p->flows, list) { fl = rcu_dereference_bh(flow->filter_list); if (fl) { - result = tc_classify_compat(skb, fl, &res); + result = tc_classify(skb, fl, &res, true); if (result < 0) continue; flow = (struct atm_flow_data *)res.class; diff --git a/net/sched/sch_cbq.c b/net/sched/sch_cbq.c index beeb75f80fdb..c538d9e4a8f6 100644 --- a/net/sched/sch_cbq.c +++ b/net/sched/sch_cbq.c @@ -240,7 +240,7 @@ cbq_classify(struct sk_buff *skb, struct Qdisc *sch, int *qerr) /* * Step 2+n. Apply classifier. */ - result = tc_classify_compat(skb, fl, &res); + result = tc_classify(skb, fl, &res, true); if (!fl || result < 0) goto fallback; diff --git a/net/sched/sch_choke.c b/net/sched/sch_choke.c index 6a783afe4960..02bfd3d1c4f0 100644 --- a/net/sched/sch_choke.c +++ b/net/sched/sch_choke.c @@ -170,13 +170,13 @@ static bool choke_match_flow(struct sk_buff *skb1, if (!choke_skb_cb(skb1)->keys_valid) { choke_skb_cb(skb1)->keys_valid = 1; - skb_flow_dissect_flow_keys(skb1, &temp); + skb_flow_dissect_flow_keys(skb1, &temp, 0); make_flow_keys_digest(&choke_skb_cb(skb1)->keys, &temp); } if (!choke_skb_cb(skb2)->keys_valid) { choke_skb_cb(skb2)->keys_valid = 1; - skb_flow_dissect_flow_keys(skb2, &temp); + skb_flow_dissect_flow_keys(skb2, &temp, 0); make_flow_keys_digest(&choke_skb_cb(skb2)->keys, &temp); } @@ -201,7 +201,7 @@ static bool choke_classify(struct sk_buff *skb, int result; fl = rcu_dereference_bh(q->filter_list); - result = tc_classify(skb, fl, &res); + result = tc_classify(skb, fl, &res, false); if (result >= 0) { #ifdef CONFIG_NET_CLS_ACT switch (result) { diff --git a/net/sched/sch_drr.c b/net/sched/sch_drr.c index 338706092c27..f26bdea875c1 100644 --- a/net/sched/sch_drr.c +++ b/net/sched/sch_drr.c @@ -331,7 +331,7 @@ static struct drr_class *drr_classify(struct sk_buff *skb, struct Qdisc *sch, *qerr = NET_XMIT_SUCCESS | __NET_XMIT_BYPASS; fl = rcu_dereference_bh(q->filter_list); - result = tc_classify(skb, fl, &res); + result = tc_classify(skb, fl, &res, false); if (result >= 0) { #ifdef CONFIG_NET_CLS_ACT switch (result) { diff --git a/net/sched/sch_dsmark.c b/net/sched/sch_dsmark.c index 66700a6116aa..c4d45fd8c551 100644 --- a/net/sched/sch_dsmark.c +++ b/net/sched/sch_dsmark.c @@ -230,7 +230,7 @@ static int dsmark_enqueue(struct sk_buff *skb, struct Qdisc *sch) else { struct tcf_result res; struct tcf_proto *fl = rcu_dereference_bh(p->filter_list); - int result = tc_classify(skb, fl, &res); + int result = tc_classify(skb, fl, &res, false); pr_debug("result %d class 0x%04x\n", result, res.classid); diff --git a/net/sched/sch_fifo.c b/net/sched/sch_fifo.c index 2e2398cfc694..2177eac0a61e 100644 --- a/net/sched/sch_fifo.c +++ b/net/sched/sch_fifo.c @@ -54,7 +54,7 @@ static int fifo_init(struct Qdisc *sch, struct nlattr *opt) bool is_bfifo = sch->ops == &bfifo_qdisc_ops; if (opt == NULL) { - u32 limit = qdisc_dev(sch)->tx_queue_len ? : 1; + u32 limit = qdisc_dev(sch)->tx_queue_len; if (is_bfifo) limit *= psched_mtu(qdisc_dev(sch)); diff --git a/net/sched/sch_fq_codel.c b/net/sched/sch_fq_codel.c index a9ba030435a2..4c834e93dafb 100644 --- a/net/sched/sch_fq_codel.c +++ b/net/sched/sch_fq_codel.c @@ -92,7 +92,7 @@ static unsigned int fq_codel_classify(struct sk_buff *skb, struct Qdisc *sch, return fq_codel_hash(q, skb) + 1; *qerr = NET_XMIT_SUCCESS | __NET_XMIT_BYPASS; - result = tc_classify(skb, filter, &res); + result = tc_classify(skb, filter, &res, false); if (result >= 0) { #ifdef CONFIG_NET_CLS_ACT switch (result) { diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c index 6efca30894aa..cb5d4ad32946 100644 --- a/net/sched/sch_generic.c +++ b/net/sched/sch_generic.c @@ -416,33 +416,25 @@ struct Qdisc noop_qdisc = { }; EXPORT_SYMBOL(noop_qdisc); -static struct Qdisc_ops noqueue_qdisc_ops __read_mostly = { +static int noqueue_init(struct Qdisc *qdisc, struct nlattr *opt) +{ + /* register_qdisc() assigns a default of noop_enqueue if unset, + * but __dev_queue_xmit() treats noqueue only as such + * if this is NULL - so clear it here. */ + qdisc->enqueue = NULL; + return 0; +} + +struct Qdisc_ops noqueue_qdisc_ops __read_mostly = { .id = "noqueue", .priv_size = 0, + .init = noqueue_init, .enqueue = noop_enqueue, .dequeue = noop_dequeue, .peek = noop_dequeue, .owner = THIS_MODULE, }; -static struct Qdisc noqueue_qdisc; -static struct netdev_queue noqueue_netdev_queue = { - .qdisc = &noqueue_qdisc, - .qdisc_sleeping = &noqueue_qdisc, -}; - -static struct Qdisc noqueue_qdisc = { - .enqueue = NULL, - .dequeue = noop_dequeue, - .flags = TCQ_F_BUILTIN, - .ops = &noqueue_qdisc_ops, - .list = LIST_HEAD_INIT(noqueue_qdisc.list), - .q.lock = __SPIN_LOCK_UNLOCKED(noqueue_qdisc.q.lock), - .dev_queue = &noqueue_netdev_queue, - .busylock = __SPIN_LOCK_UNLOCKED(noqueue_qdisc.busylock), -}; - - static const u8 prio2band[TC_PRIO_MAX + 1] = { 1, 2, 2, 2, 1, 2, 0, 0 , 1, 1, 1, 1, 1, 1, 1, 1 }; @@ -733,18 +725,19 @@ static void attach_one_default_qdisc(struct net_device *dev, struct netdev_queue *dev_queue, void *_unused) { - struct Qdisc *qdisc = &noqueue_qdisc; + struct Qdisc *qdisc; + const struct Qdisc_ops *ops = default_qdisc_ops; - if (dev->tx_queue_len) { - qdisc = qdisc_create_dflt(dev_queue, - default_qdisc_ops, TC_H_ROOT); - if (!qdisc) { - netdev_info(dev, "activation failed\n"); - return; - } - if (!netif_is_multiqueue(dev)) - qdisc->flags |= TCQ_F_ONETXQUEUE; + if (dev->priv_flags & IFF_NO_QUEUE) + ops = &noqueue_qdisc_ops; + + qdisc = qdisc_create_dflt(dev_queue, ops, TC_H_ROOT); + if (!qdisc) { + netdev_info(dev, "activation failed\n"); + return; } + if (!netif_is_multiqueue(dev)) + qdisc->flags |= TCQ_F_ONETXQUEUE; dev_queue->qdisc_sleeping = qdisc; } @@ -755,7 +748,8 @@ static void attach_default_qdiscs(struct net_device *dev) txq = netdev_get_tx_queue(dev, 0); - if (!netif_is_multiqueue(dev) || dev->tx_queue_len == 0) { + if (!netif_is_multiqueue(dev) || + dev->priv_flags & IFF_NO_QUEUE) { netdev_for_each_tx_queue(dev, attach_one_default_qdisc, NULL); dev->qdisc = txq->qdisc_sleeping; atomic_inc(&dev->qdisc->refcnt); @@ -779,7 +773,7 @@ static void transition_one_qdisc(struct net_device *dev, clear_bit(__QDISC_STATE_DEACTIVATED, &new_qdisc->state); rcu_assign_pointer(dev_queue->qdisc, new_qdisc); - if (need_watchdog_p && new_qdisc != &noqueue_qdisc) { + if (need_watchdog_p) { dev_queue->trans_start = 0; *need_watchdog_p = 1; } diff --git a/net/sched/sch_gred.c b/net/sched/sch_gred.c index abb9f2fec28f..80105109f756 100644 --- a/net/sched/sch_gred.c +++ b/net/sched/sch_gred.c @@ -512,11 +512,9 @@ static int gred_init(struct Qdisc *sch, struct nlattr *opt) if (tb[TCA_GRED_LIMIT]) sch->limit = nla_get_u32(tb[TCA_GRED_LIMIT]); - else { - u32 qlen = qdisc_dev(sch)->tx_queue_len ? : 1; - - sch->limit = qlen * psched_mtu(qdisc_dev(sch)); - } + else + sch->limit = qdisc_dev(sch)->tx_queue_len + * psched_mtu(qdisc_dev(sch)); return gred_change_table_def(sch, tb[TCA_GRED_DPS]); } diff --git a/net/sched/sch_hfsc.c b/net/sched/sch_hfsc.c index e6c7416d0332..b7ebe2c87586 100644 --- a/net/sched/sch_hfsc.c +++ b/net/sched/sch_hfsc.c @@ -1165,7 +1165,7 @@ hfsc_classify(struct sk_buff *skb, struct Qdisc *sch, int *qerr) *qerr = NET_XMIT_SUCCESS | __NET_XMIT_BYPASS; head = &q->root; tcf = rcu_dereference_bh(q->root.filter_list); - while (tcf && (result = tc_classify(skb, tcf, &res)) >= 0) { + while (tcf && (result = tc_classify(skb, tcf, &res, false)) >= 0) { #ifdef CONFIG_NET_CLS_ACT switch (result) { case TC_ACT_QUEUED: diff --git a/net/sched/sch_htb.c b/net/sched/sch_htb.c index f1acb0f60dc3..15ccd7f8fb2a 100644 --- a/net/sched/sch_htb.c +++ b/net/sched/sch_htb.c @@ -229,7 +229,7 @@ static struct htb_class *htb_classify(struct sk_buff *skb, struct Qdisc *sch, } *qerr = NET_XMIT_SUCCESS | __NET_XMIT_BYPASS; - while (tcf && (result = tc_classify(skb, tcf, &res)) >= 0) { + while (tcf && (result = tc_classify(skb, tcf, &res, false)) >= 0) { #ifdef CONFIG_NET_CLS_ACT switch (result) { case TC_ACT_QUEUED: @@ -1048,11 +1048,9 @@ static int htb_init(struct Qdisc *sch, struct nlattr *opt) if (tb[TCA_HTB_DIRECT_QLEN]) q->direct_qlen = nla_get_u32(tb[TCA_HTB_DIRECT_QLEN]); - else { + else q->direct_qlen = qdisc_dev(sch)->tx_queue_len; - if (q->direct_qlen < 2) /* some devices have zero tx_queue_len */ - q->direct_qlen = 2; - } + if ((q->rate2quantum = gopt->rate2quantum) < 1) q->rate2quantum = 1; q->defcls = gopt->defcls; diff --git a/net/sched/sch_multiq.c b/net/sched/sch_multiq.c index 42dd218871e0..4e904ca0af9d 100644 --- a/net/sched/sch_multiq.c +++ b/net/sched/sch_multiq.c @@ -46,7 +46,7 @@ multiq_classify(struct sk_buff *skb, struct Qdisc *sch, int *qerr) int err; *qerr = NET_XMIT_SUCCESS | __NET_XMIT_BYPASS; - err = tc_classify(skb, fl, &res); + err = tc_classify(skb, fl, &res, false); #ifdef CONFIG_NET_CLS_ACT switch (err) { case TC_ACT_STOLEN: diff --git a/net/sched/sch_plug.c b/net/sched/sch_plug.c index ade9445a55ab..5abfe44678d4 100644 --- a/net/sched/sch_plug.c +++ b/net/sched/sch_plug.c @@ -130,12 +130,8 @@ static int plug_init(struct Qdisc *sch, struct nlattr *opt) q->unplug_indefinite = false; if (opt == NULL) { - /* We will set a default limit of 100 pkts (~150kB) - * in case tx_queue_len is not available. The - * default value is completely arbitrary. - */ - u32 pkt_limit = qdisc_dev(sch)->tx_queue_len ? : 100; - q->limit = pkt_limit * psched_mtu(qdisc_dev(sch)); + q->limit = qdisc_dev(sch)->tx_queue_len + * psched_mtu(qdisc_dev(sch)); } else { struct tc_plug_qopt *ctl = nla_data(opt); diff --git a/net/sched/sch_prio.c b/net/sched/sch_prio.c index 8e5cd34aaa74..ba6487f2741f 100644 --- a/net/sched/sch_prio.c +++ b/net/sched/sch_prio.c @@ -42,7 +42,7 @@ prio_classify(struct sk_buff *skb, struct Qdisc *sch, int *qerr) *qerr = NET_XMIT_SUCCESS | __NET_XMIT_BYPASS; if (TC_H_MAJ(skb->priority) != sch->handle) { fl = rcu_dereference_bh(q->filter_list); - err = tc_classify(skb, fl, &res); + err = tc_classify(skb, fl, &res, false); #ifdef CONFIG_NET_CLS_ACT switch (err) { case TC_ACT_STOLEN: diff --git a/net/sched/sch_qfq.c b/net/sched/sch_qfq.c index b8d73bca683c..3dc3a6e56052 100644 --- a/net/sched/sch_qfq.c +++ b/net/sched/sch_qfq.c @@ -186,7 +186,6 @@ struct qfq_sched { u64 oldV, V; /* Precise virtual times. */ struct qfq_aggregate *in_serv_agg; /* Aggregate being served. */ - u32 num_active_agg; /* Num. of active aggregates */ u32 wsum; /* weight sum */ u32 iwsum; /* inverse weight sum */ @@ -718,7 +717,7 @@ static struct qfq_class *qfq_classify(struct sk_buff *skb, struct Qdisc *sch, *qerr = NET_XMIT_SUCCESS | __NET_XMIT_BYPASS; fl = rcu_dereference_bh(q->filter_list); - result = tc_classify(skb, fl, &res); + result = tc_classify(skb, fl, &res, false); if (result >= 0) { #ifdef CONFIG_NET_CLS_ACT switch (result) { diff --git a/net/sched/sch_sfb.c b/net/sched/sch_sfb.c index 4b815193326c..5bbb6332ec57 100644 --- a/net/sched/sch_sfb.c +++ b/net/sched/sch_sfb.c @@ -258,7 +258,7 @@ static bool sfb_classify(struct sk_buff *skb, struct tcf_proto *fl, struct tcf_result res; int result; - result = tc_classify(skb, fl, &res); + result = tc_classify(skb, fl, &res, false); if (result >= 0) { #ifdef CONFIG_NET_CLS_ACT switch (result) { @@ -502,7 +502,7 @@ static int sfb_change(struct Qdisc *sch, struct nlattr *opt) limit = ctl->limit; if (limit == 0) - limit = max_t(u32, qdisc_dev(sch)->tx_queue_len, 1); + limit = qdisc_dev(sch)->tx_queue_len; child = fifo_create_dflt(sch, &pfifo_qdisc_ops, limit); if (IS_ERR(child)) diff --git a/net/sched/sch_sfq.c b/net/sched/sch_sfq.c index 52f75a5473e1..3abab534eb5c 100644 --- a/net/sched/sch_sfq.c +++ b/net/sched/sch_sfq.c @@ -179,7 +179,7 @@ static unsigned int sfq_classify(struct sk_buff *skb, struct Qdisc *sch, return sfq_hash(q, skb) + 1; *qerr = NET_XMIT_SUCCESS | __NET_XMIT_BYPASS; - result = tc_classify(skb, fl, &res); + result = tc_classify(skb, fl, &res, false); if (result >= 0) { #ifdef CONFIG_NET_CLS_ACT switch (result) { diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c index 59e80356672b..b7143337e4fa 100644 --- a/net/sctp/protocol.c +++ b/net/sctp/protocol.c @@ -487,23 +487,43 @@ static void sctp_v4_get_dst(struct sctp_transport *t, union sctp_addr *saddr, */ rcu_read_lock(); list_for_each_entry_rcu(laddr, &bp->address_list, list) { + struct net_device *odev; + if (!laddr->valid) continue; - if ((laddr->state == SCTP_ADDR_SRC) && - (AF_INET == laddr->a.sa.sa_family)) { - fl4->fl4_sport = laddr->a.v4.sin_port; - flowi4_update_output(fl4, - asoc->base.sk->sk_bound_dev_if, - RT_CONN_FLAGS(asoc->base.sk), - daddr->v4.sin_addr.s_addr, - laddr->a.v4.sin_addr.s_addr); - - rt = ip_route_output_key(sock_net(sk), fl4); - if (!IS_ERR(rt)) { - dst = &rt->dst; - goto out_unlock; - } + if (laddr->state != SCTP_ADDR_SRC || + AF_INET != laddr->a.sa.sa_family) + continue; + + fl4->fl4_sport = laddr->a.v4.sin_port; + flowi4_update_output(fl4, + asoc->base.sk->sk_bound_dev_if, + RT_CONN_FLAGS(asoc->base.sk), + daddr->v4.sin_addr.s_addr, + laddr->a.v4.sin_addr.s_addr); + + rt = ip_route_output_key(sock_net(sk), fl4); + if (IS_ERR(rt)) + continue; + + if (!dst) + dst = &rt->dst; + + /* Ensure the src address belongs to the output + * interface. + */ + odev = __ip_dev_find(sock_net(sk), laddr->a.v4.sin_addr.s_addr, + false); + if (!odev || odev->ifindex != fl4->flowi4_oif) { + if (&rt->dst != dst) + dst_release(&rt->dst); + continue; } + + if (dst != &rt->dst) + dst_release(dst); + dst = &rt->dst; + break; } out_unlock: diff --git a/net/sctp/sm_make_chunk.c b/net/sctp/sm_make_chunk.c index a655ddc3f353..7954c52e1794 100644 --- a/net/sctp/sm_make_chunk.c +++ b/net/sctp/sm_make_chunk.c @@ -3090,8 +3090,19 @@ static __be16 sctp_process_asconf_param(struct sctp_association *asoc, sctp_assoc_set_primary(asoc, asconf->transport); sctp_assoc_del_nonprimary_peers(asoc, asconf->transport); - } else - sctp_assoc_del_peer(asoc, &addr); + return SCTP_ERROR_NO_ERROR; + } + + /* If the address is not part of the association, the + * ASCONF-ACK with Error Cause Indication Parameter + * which including cause of Unresolvable Address should + * be sent. + */ + peer = sctp_assoc_lookup_paddr(asoc, &addr); + if (!peer) + return SCTP_ERROR_DNS_FAILED; + + sctp_assoc_rm_peer(asoc, peer); break; case SCTP_PARAM_SET_PRIMARY: /* ADDIP Section 4.2.4 diff --git a/net/sctp/sm_sideeffect.c b/net/sctp/sm_sideeffect.c index 85e6f03aeb70..35df1266bf07 100644 --- a/net/sctp/sm_sideeffect.c +++ b/net/sctp/sm_sideeffect.c @@ -954,7 +954,7 @@ static void sctp_cmd_del_non_primary(struct sctp_association *asoc) t = list_entry(pos, struct sctp_transport, transports); if (!sctp_cmp_addr_exact(&t->ipaddr, &asoc->peer.primary_addr)) { - sctp_assoc_del_peer(asoc, &t->ipaddr); + sctp_assoc_rm_peer(asoc, t); } } } diff --git a/net/sctp/sm_statefuns.c b/net/sctp/sm_statefuns.c index 3ee27b7704ff..d7eaa7354cf7 100644 --- a/net/sctp/sm_statefuns.c +++ b/net/sctp/sm_statefuns.c @@ -853,7 +853,7 @@ nomem: /* * Respond to a normal COOKIE ACK chunk. - * We are the side that is being asked for an association. + * We are the side that is asking for an association. * * RFC 2960 5.1 Normal Establishment of an Association * diff --git a/net/sunrpc/auth_unix.c b/net/sunrpc/auth_unix.c index 4feda2d0a833..548240dd15fc 100644 --- a/net/sunrpc/auth_unix.c +++ b/net/sunrpc/auth_unix.c @@ -23,7 +23,7 @@ struct unx_cred { }; #define uc_uid uc_base.cr_uid -#define UNX_WRITESLACK (21 + (UNX_MAXNODENAME >> 2)) +#define UNX_WRITESLACK (21 + XDR_QUADLEN(UNX_MAXNODENAME)) #if IS_ENABLED(CONFIG_SUNRPC_DEBUG) # define RPCDBG_FACILITY RPCDBG_AUTH diff --git a/net/sunrpc/cache.c b/net/sunrpc/cache.c index 2928afffbb81..4a2340a54401 100644 --- a/net/sunrpc/cache.c +++ b/net/sunrpc/cache.c @@ -44,7 +44,7 @@ static void cache_revisit_request(struct cache_head *item); static void cache_init(struct cache_head *h) { time_t now = seconds_since_boot(); - h->next = NULL; + INIT_HLIST_NODE(&h->cache_list); h->flags = 0; kref_init(&h->ref); h->expiry_time = now + CACHE_NEW_EXPIRY; @@ -54,15 +54,14 @@ static void cache_init(struct cache_head *h) struct cache_head *sunrpc_cache_lookup(struct cache_detail *detail, struct cache_head *key, int hash) { - struct cache_head **head, **hp; - struct cache_head *new = NULL, *freeme = NULL; + struct cache_head *new = NULL, *freeme = NULL, *tmp = NULL; + struct hlist_head *head; head = &detail->hash_table[hash]; read_lock(&detail->hash_lock); - for (hp=head; *hp != NULL ; hp = &(*hp)->next) { - struct cache_head *tmp = *hp; + hlist_for_each_entry(tmp, head, cache_list) { if (detail->match(tmp, key)) { if (cache_is_expired(detail, tmp)) /* This entry is expired, we will discard it. */ @@ -88,12 +87,10 @@ struct cache_head *sunrpc_cache_lookup(struct cache_detail *detail, write_lock(&detail->hash_lock); /* check if entry appeared while we slept */ - for (hp=head; *hp != NULL ; hp = &(*hp)->next) { - struct cache_head *tmp = *hp; + hlist_for_each_entry(tmp, head, cache_list) { if (detail->match(tmp, key)) { if (cache_is_expired(detail, tmp)) { - *hp = tmp->next; - tmp->next = NULL; + hlist_del_init(&tmp->cache_list); detail->entries --; freeme = tmp; break; @@ -104,8 +101,8 @@ struct cache_head *sunrpc_cache_lookup(struct cache_detail *detail, return tmp; } } - new->next = *head; - *head = new; + + hlist_add_head(&new->cache_list, head); detail->entries++; cache_get(new); write_unlock(&detail->hash_lock); @@ -143,7 +140,6 @@ struct cache_head *sunrpc_cache_update(struct cache_detail *detail, * If 'old' is not VALID, we update it directly, * otherwise we need to replace it */ - struct cache_head **head; struct cache_head *tmp; if (!test_bit(CACHE_VALID, &old->flags)) { @@ -168,15 +164,13 @@ struct cache_head *sunrpc_cache_update(struct cache_detail *detail, } cache_init(tmp); detail->init(tmp, old); - head = &detail->hash_table[hash]; write_lock(&detail->hash_lock); if (test_bit(CACHE_NEGATIVE, &new->flags)) set_bit(CACHE_NEGATIVE, &tmp->flags); else detail->update(tmp, new); - tmp->next = *head; - *head = tmp; + hlist_add_head(&tmp->cache_list, &detail->hash_table[hash]); detail->entries++; cache_get(tmp); cache_fresh_locked(tmp, new->expiry_time); @@ -416,28 +410,29 @@ static int cache_clean(void) /* find a non-empty bucket in the table */ while (current_detail && current_index < current_detail->hash_size && - current_detail->hash_table[current_index] == NULL) + hlist_empty(¤t_detail->hash_table[current_index])) current_index++; /* find a cleanable entry in the bucket and clean it, or set to next bucket */ if (current_detail && current_index < current_detail->hash_size) { - struct cache_head *ch, **cp; + struct cache_head *ch = NULL; struct cache_detail *d; + struct hlist_head *head; + struct hlist_node *tmp; write_lock(¤t_detail->hash_lock); /* Ok, now to clean this strand */ - cp = & current_detail->hash_table[current_index]; - for (ch = *cp ; ch ; cp = & ch->next, ch = *cp) { + head = ¤t_detail->hash_table[current_index]; + hlist_for_each_entry_safe(ch, tmp, head, cache_list) { if (current_detail->nextcheck > ch->expiry_time) current_detail->nextcheck = ch->expiry_time+1; if (!cache_is_expired(current_detail, ch)) continue; - *cp = ch->next; - ch->next = NULL; + hlist_del_init(&ch->cache_list); current_detail->entries--; rv = 1; break; @@ -1270,18 +1265,13 @@ EXPORT_SYMBOL_GPL(qword_get); * get a header, then pass each real item in the cache */ -struct handle { - struct cache_detail *cd; -}; - -static void *c_start(struct seq_file *m, loff_t *pos) +void *cache_seq_start(struct seq_file *m, loff_t *pos) __acquires(cd->hash_lock) { loff_t n = *pos; unsigned int hash, entry; struct cache_head *ch; - struct cache_detail *cd = ((struct handle*)m->private)->cd; - + struct cache_detail *cd = m->private; read_lock(&cd->hash_lock); if (!n--) @@ -1289,7 +1279,7 @@ static void *c_start(struct seq_file *m, loff_t *pos) hash = n >> 32; entry = n & ((1LL<<32) - 1); - for (ch=cd->hash_table[hash]; ch; ch=ch->next) + hlist_for_each_entry(ch, &cd->hash_table[hash], cache_list) if (!entry--) return ch; n &= ~((1LL<<32) - 1); @@ -1297,51 +1287,57 @@ static void *c_start(struct seq_file *m, loff_t *pos) hash++; n += 1LL<<32; } while(hash < cd->hash_size && - cd->hash_table[hash]==NULL); + hlist_empty(&cd->hash_table[hash])); if (hash >= cd->hash_size) return NULL; *pos = n+1; - return cd->hash_table[hash]; + return hlist_entry_safe(cd->hash_table[hash].first, + struct cache_head, cache_list); } +EXPORT_SYMBOL_GPL(cache_seq_start); -static void *c_next(struct seq_file *m, void *p, loff_t *pos) +void *cache_seq_next(struct seq_file *m, void *p, loff_t *pos) { struct cache_head *ch = p; int hash = (*pos >> 32); - struct cache_detail *cd = ((struct handle*)m->private)->cd; + struct cache_detail *cd = m->private; if (p == SEQ_START_TOKEN) hash = 0; - else if (ch->next == NULL) { + else if (ch->cache_list.next == NULL) { hash++; *pos += 1LL<<32; } else { ++*pos; - return ch->next; + return hlist_entry_safe(ch->cache_list.next, + struct cache_head, cache_list); } *pos &= ~((1LL<<32) - 1); while (hash < cd->hash_size && - cd->hash_table[hash] == NULL) { + hlist_empty(&cd->hash_table[hash])) { hash++; *pos += 1LL<<32; } if (hash >= cd->hash_size) return NULL; ++*pos; - return cd->hash_table[hash]; + return hlist_entry_safe(cd->hash_table[hash].first, + struct cache_head, cache_list); } +EXPORT_SYMBOL_GPL(cache_seq_next); -static void c_stop(struct seq_file *m, void *p) +void cache_seq_stop(struct seq_file *m, void *p) __releases(cd->hash_lock) { - struct cache_detail *cd = ((struct handle*)m->private)->cd; + struct cache_detail *cd = m->private; read_unlock(&cd->hash_lock); } +EXPORT_SYMBOL_GPL(cache_seq_stop); static int c_show(struct seq_file *m, void *p) { struct cache_head *cp = p; - struct cache_detail *cd = ((struct handle*)m->private)->cd; + struct cache_detail *cd = m->private; if (p == SEQ_START_TOKEN) return cd->cache_show(m, cd, NULL); @@ -1364,33 +1360,36 @@ static int c_show(struct seq_file *m, void *p) } static const struct seq_operations cache_content_op = { - .start = c_start, - .next = c_next, - .stop = c_stop, + .start = cache_seq_start, + .next = cache_seq_next, + .stop = cache_seq_stop, .show = c_show, }; static int content_open(struct inode *inode, struct file *file, struct cache_detail *cd) { - struct handle *han; + struct seq_file *seq; + int err; if (!cd || !try_module_get(cd->owner)) return -EACCES; - han = __seq_open_private(file, &cache_content_op, sizeof(*han)); - if (han == NULL) { + + err = seq_open(file, &cache_content_op); + if (err) { module_put(cd->owner); - return -ENOMEM; + return err; } - han->cd = cd; + seq = file->private_data; + seq->private = cd; return 0; } static int content_release(struct inode *inode, struct file *file, struct cache_detail *cd) { - int ret = seq_release_private(inode, file); + int ret = seq_release(inode, file); module_put(cd->owner); return ret; } @@ -1665,17 +1664,21 @@ EXPORT_SYMBOL_GPL(cache_unregister_net); struct cache_detail *cache_create_net(struct cache_detail *tmpl, struct net *net) { struct cache_detail *cd; + int i; cd = kmemdup(tmpl, sizeof(struct cache_detail), GFP_KERNEL); if (cd == NULL) return ERR_PTR(-ENOMEM); - cd->hash_table = kzalloc(cd->hash_size * sizeof(struct cache_head *), + cd->hash_table = kzalloc(cd->hash_size * sizeof(struct hlist_head), GFP_KERNEL); if (cd->hash_table == NULL) { kfree(cd); return ERR_PTR(-ENOMEM); } + + for (i = 0; i < cd->hash_size; i++) + INIT_HLIST_HEAD(&cd->hash_table[i]); cd->net = net; return cd; } diff --git a/net/sunrpc/sched.c b/net/sunrpc/sched.c index 337ca851a350..b140c092d226 100644 --- a/net/sunrpc/sched.c +++ b/net/sunrpc/sched.c @@ -297,7 +297,7 @@ static int rpc_complete_task(struct rpc_task *task) clear_bit(RPC_TASK_ACTIVE, &task->tk_runstate); ret = atomic_dec_and_test(&task->tk_count); if (waitqueue_active(wq)) - __wake_up_locked_key(wq, TASK_NORMAL, &k); + __wake_up_locked_key(wq, TASK_NORMAL, 1, &k); spin_unlock_irqrestore(&wq->lock, flags); return ret; } diff --git a/net/sunrpc/svc.c b/net/sunrpc/svc.c index 5a16d8d8c831..a8f579df14d8 100644 --- a/net/sunrpc/svc.c +++ b/net/sunrpc/svc.c @@ -34,36 +34,19 @@ static void svc_unregister(const struct svc_serv *serv, struct net *net); -#define svc_serv_is_pooled(serv) ((serv)->sv_function) +#define svc_serv_is_pooled(serv) ((serv)->sv_ops->svo_function) -/* - * Mode for mapping cpus to pools. - */ -enum { - SVC_POOL_AUTO = -1, /* choose one of the others */ - SVC_POOL_GLOBAL, /* no mapping, just a single global pool - * (legacy & UP mode) */ - SVC_POOL_PERCPU, /* one pool per cpu */ - SVC_POOL_PERNODE /* one pool per numa node */ -}; #define SVC_POOL_DEFAULT SVC_POOL_GLOBAL /* * Structure for mapping cpus to pools and vice versa. * Setup once during sunrpc initialisation. */ -static struct svc_pool_map { - int count; /* How many svc_servs use us */ - int mode; /* Note: int not enum to avoid - * warnings about "enumeration value - * not handled in switch" */ - unsigned int npools; - unsigned int *pool_to; /* maps pool id to cpu or node */ - unsigned int *to_pool; /* maps cpu or node to pool id */ -} svc_pool_map = { - .count = 0, +struct svc_pool_map svc_pool_map = { .mode = SVC_POOL_DEFAULT }; +EXPORT_SYMBOL_GPL(svc_pool_map); + static DEFINE_MUTEX(svc_pool_map_mutex);/* protects svc_pool_map.count only */ static int @@ -236,7 +219,7 @@ svc_pool_map_init_pernode(struct svc_pool_map *m) * vice versa). Initialise the map if we're the first user. * Returns the number of pools. */ -static unsigned int +unsigned int svc_pool_map_get(void) { struct svc_pool_map *m = &svc_pool_map; @@ -271,7 +254,7 @@ svc_pool_map_get(void) mutex_unlock(&svc_pool_map_mutex); return m->npools; } - +EXPORT_SYMBOL_GPL(svc_pool_map_get); /* * Drop a reference to the global map of cpus to pools. @@ -280,7 +263,7 @@ svc_pool_map_get(void) * mode using the pool_mode module option without * rebooting or re-loading sunrpc.ko. */ -static void +void svc_pool_map_put(void) { struct svc_pool_map *m = &svc_pool_map; @@ -297,7 +280,7 @@ svc_pool_map_put(void) mutex_unlock(&svc_pool_map_mutex); } - +EXPORT_SYMBOL_GPL(svc_pool_map_put); static int svc_pool_map_get_node(unsigned int pidx) { @@ -423,7 +406,7 @@ EXPORT_SYMBOL_GPL(svc_bind); */ static struct svc_serv * __svc_create(struct svc_program *prog, unsigned int bufsize, int npools, - void (*shutdown)(struct svc_serv *serv, struct net *net)) + struct svc_serv_ops *ops) { struct svc_serv *serv; unsigned int vers; @@ -440,7 +423,7 @@ __svc_create(struct svc_program *prog, unsigned int bufsize, int npools, bufsize = RPCSVC_MAXPAYLOAD; serv->sv_max_payload = bufsize? bufsize : 4096; serv->sv_max_mesg = roundup(serv->sv_max_payload + PAGE_SIZE, PAGE_SIZE); - serv->sv_shutdown = shutdown; + serv->sv_ops = ops; xdrsize = 0; while (prog) { prog->pg_lovers = prog->pg_nvers-1; @@ -486,26 +469,22 @@ __svc_create(struct svc_program *prog, unsigned int bufsize, int npools, struct svc_serv * svc_create(struct svc_program *prog, unsigned int bufsize, - void (*shutdown)(struct svc_serv *serv, struct net *net)) + struct svc_serv_ops *ops) { - return __svc_create(prog, bufsize, /*npools*/1, shutdown); + return __svc_create(prog, bufsize, /*npools*/1, ops); } EXPORT_SYMBOL_GPL(svc_create); struct svc_serv * svc_create_pooled(struct svc_program *prog, unsigned int bufsize, - void (*shutdown)(struct svc_serv *serv, struct net *net), - svc_thread_fn func, struct module *mod) + struct svc_serv_ops *ops) { struct svc_serv *serv; unsigned int npools = svc_pool_map_get(); - serv = __svc_create(prog, bufsize, npools, shutdown); + serv = __svc_create(prog, bufsize, npools, ops); if (!serv) goto out_err; - - serv->sv_function = func; - serv->sv_module = mod; return serv; out_err: svc_pool_map_put(); @@ -517,8 +496,8 @@ void svc_shutdown_net(struct svc_serv *serv, struct net *net) { svc_close_net(serv, net); - if (serv->sv_shutdown) - serv->sv_shutdown(serv, net); + if (serv->sv_ops->svo_shutdown) + serv->sv_ops->svo_shutdown(serv, net); } EXPORT_SYMBOL_GPL(svc_shutdown_net); @@ -604,40 +583,52 @@ svc_release_buffer(struct svc_rqst *rqstp) } struct svc_rqst * -svc_prepare_thread(struct svc_serv *serv, struct svc_pool *pool, int node) +svc_rqst_alloc(struct svc_serv *serv, struct svc_pool *pool, int node) { struct svc_rqst *rqstp; rqstp = kzalloc_node(sizeof(*rqstp), GFP_KERNEL, node); if (!rqstp) - goto out_enomem; + return rqstp; - serv->sv_nrthreads++; __set_bit(RQ_BUSY, &rqstp->rq_flags); spin_lock_init(&rqstp->rq_lock); rqstp->rq_server = serv; rqstp->rq_pool = pool; - spin_lock_bh(&pool->sp_lock); - pool->sp_nrthreads++; - list_add_rcu(&rqstp->rq_all, &pool->sp_all_threads); - spin_unlock_bh(&pool->sp_lock); rqstp->rq_argp = kmalloc_node(serv->sv_xdrsize, GFP_KERNEL, node); if (!rqstp->rq_argp) - goto out_thread; + goto out_enomem; rqstp->rq_resp = kmalloc_node(serv->sv_xdrsize, GFP_KERNEL, node); if (!rqstp->rq_resp) - goto out_thread; + goto out_enomem; if (!svc_init_buffer(rqstp, serv->sv_max_mesg, node)) - goto out_thread; + goto out_enomem; return rqstp; -out_thread: - svc_exit_thread(rqstp); out_enomem: - return ERR_PTR(-ENOMEM); + svc_rqst_free(rqstp); + return NULL; +} +EXPORT_SYMBOL_GPL(svc_rqst_alloc); + +struct svc_rqst * +svc_prepare_thread(struct svc_serv *serv, struct svc_pool *pool, int node) +{ + struct svc_rqst *rqstp; + + rqstp = svc_rqst_alloc(serv, pool, node); + if (!rqstp) + return ERR_PTR(-ENOMEM); + + serv->sv_nrthreads++; + spin_lock_bh(&pool->sp_lock); + pool->sp_nrthreads++; + list_add_rcu(&rqstp->rq_all, &pool->sp_all_threads); + spin_unlock_bh(&pool->sp_lock); + return rqstp; } EXPORT_SYMBOL_GPL(svc_prepare_thread); @@ -739,12 +730,12 @@ svc_set_num_threads(struct svc_serv *serv, struct svc_pool *pool, int nrservs) break; } - __module_get(serv->sv_module); - task = kthread_create_on_node(serv->sv_function, rqstp, + __module_get(serv->sv_ops->svo_module); + task = kthread_create_on_node(serv->sv_ops->svo_function, rqstp, node, "%s", serv->sv_name); if (IS_ERR(task)) { error = PTR_ERR(task); - module_put(serv->sv_module); + module_put(serv->sv_ops->svo_module); svc_exit_thread(rqstp); break; } @@ -772,15 +763,21 @@ EXPORT_SYMBOL_GPL(svc_set_num_threads); * mutex" for the service. */ void -svc_exit_thread(struct svc_rqst *rqstp) +svc_rqst_free(struct svc_rqst *rqstp) { - struct svc_serv *serv = rqstp->rq_server; - struct svc_pool *pool = rqstp->rq_pool; - svc_release_buffer(rqstp); kfree(rqstp->rq_resp); kfree(rqstp->rq_argp); kfree(rqstp->rq_auth_data); + kfree_rcu(rqstp, rq_rcu_head); +} +EXPORT_SYMBOL_GPL(svc_rqst_free); + +void +svc_exit_thread(struct svc_rqst *rqstp) +{ + struct svc_serv *serv = rqstp->rq_server; + struct svc_pool *pool = rqstp->rq_pool; spin_lock_bh(&pool->sp_lock); pool->sp_nrthreads--; @@ -788,7 +785,7 @@ svc_exit_thread(struct svc_rqst *rqstp) list_del_rcu(&rqstp->rq_all); spin_unlock_bh(&pool->sp_lock); - kfree_rcu(rqstp, rq_rcu_head); + svc_rqst_free(rqstp); /* Release the server */ if (serv) diff --git a/net/sunrpc/svc_xprt.c b/net/sunrpc/svc_xprt.c index 163ac45c3639..a6cbb2104667 100644 --- a/net/sunrpc/svc_xprt.c +++ b/net/sunrpc/svc_xprt.c @@ -24,7 +24,6 @@ static int svc_deferred_recv(struct svc_rqst *rqstp); static struct cache_deferred_req *svc_defer(struct cache_req *req); static void svc_age_temp_xprts(unsigned long closure); static void svc_delete_xprt(struct svc_xprt *xprt); -static void svc_xprt_do_enqueue(struct svc_xprt *xprt); /* apparently the "standard" is that clients close * idle connections after 5 minutes, servers after @@ -225,12 +224,12 @@ static void svc_xprt_received(struct svc_xprt *xprt) } /* As soon as we clear busy, the xprt could be closed and - * 'put', so we need a reference to call svc_xprt_do_enqueue with: + * 'put', so we need a reference to call svc_enqueue_xprt with: */ svc_xprt_get(xprt); smp_mb__before_atomic(); clear_bit(XPT_BUSY, &xprt->xpt_flags); - svc_xprt_do_enqueue(xprt); + xprt->xpt_server->sv_ops->svo_enqueue_xprt(xprt); svc_xprt_put(xprt); } @@ -320,7 +319,7 @@ static bool svc_xprt_has_something_to_do(struct svc_xprt *xprt) return false; } -static void svc_xprt_do_enqueue(struct svc_xprt *xprt) +void svc_xprt_do_enqueue(struct svc_xprt *xprt) { struct svc_pool *pool; struct svc_rqst *rqstp = NULL; @@ -402,6 +401,7 @@ redo_search: out: trace_svc_xprt_do_enqueue(xprt, rqstp); } +EXPORT_SYMBOL_GPL(svc_xprt_do_enqueue); /* * Queue up a transport with data pending. If there are idle nfsd @@ -412,7 +412,7 @@ void svc_xprt_enqueue(struct svc_xprt *xprt) { if (test_bit(XPT_BUSY, &xprt->xpt_flags)) return; - svc_xprt_do_enqueue(xprt); + xprt->xpt_server->sv_ops->svo_enqueue_xprt(xprt); } EXPORT_SYMBOL_GPL(svc_xprt_enqueue); diff --git a/net/sunrpc/xprtrdma/fmr_ops.c b/net/sunrpc/xprtrdma/fmr_ops.c index f1e8dafbd507..cb25c89da623 100644 --- a/net/sunrpc/xprtrdma/fmr_ops.c +++ b/net/sunrpc/xprtrdma/fmr_ops.c @@ -39,6 +39,25 @@ static int fmr_op_open(struct rpcrdma_ia *ia, struct rpcrdma_ep *ep, struct rpcrdma_create_data_internal *cdata) { + struct ib_device_attr *devattr = &ia->ri_devattr; + struct ib_mr *mr; + + /* Obtain an lkey to use for the regbufs, which are + * protected from remote access. + */ + if (devattr->device_cap_flags & IB_DEVICE_LOCAL_DMA_LKEY) { + ia->ri_dma_lkey = ia->ri_device->local_dma_lkey; + } else { + mr = ib_get_dma_mr(ia->ri_pd, IB_ACCESS_LOCAL_WRITE); + if (IS_ERR(mr)) { + pr_err("%s: ib_get_dma_mr for failed with %lX\n", + __func__, PTR_ERR(mr)); + return -ENOMEM; + } + ia->ri_dma_lkey = ia->ri_dma_mr->lkey; + ia->ri_dma_mr = mr; + } + return 0; } diff --git a/net/sunrpc/xprtrdma/frwr_ops.c b/net/sunrpc/xprtrdma/frwr_ops.c index 04ea914201b2..d6653f5d0830 100644 --- a/net/sunrpc/xprtrdma/frwr_ops.c +++ b/net/sunrpc/xprtrdma/frwr_ops.c @@ -117,7 +117,7 @@ __frwr_recovery_worker(struct work_struct *work) if (ib_dereg_mr(r->r.frmr.fr_mr)) goto out_fail; - r->r.frmr.fr_mr = ib_alloc_fast_reg_mr(pd, depth); + r->r.frmr.fr_mr = ib_alloc_mr(pd, IB_MR_TYPE_MEM_REG, depth); if (IS_ERR(r->r.frmr.fr_mr)) goto out_fail; @@ -148,7 +148,7 @@ __frwr_init(struct rpcrdma_mw *r, struct ib_pd *pd, struct ib_device *device, struct rpcrdma_frmr *f = &r->r.frmr; int rc; - f->fr_mr = ib_alloc_fast_reg_mr(pd, depth); + f->fr_mr = ib_alloc_mr(pd, IB_MR_TYPE_MEM_REG, depth); if (IS_ERR(f->fr_mr)) goto out_mr_err; f->fr_pgl = ib_alloc_fast_reg_page_list(device, depth); @@ -158,7 +158,7 @@ __frwr_init(struct rpcrdma_mw *r, struct ib_pd *pd, struct ib_device *device, out_mr_err: rc = PTR_ERR(f->fr_mr); - dprintk("RPC: %s: ib_alloc_fast_reg_mr status %i\n", + dprintk("RPC: %s: ib_alloc_mr status %i\n", __func__, rc); return rc; @@ -189,6 +189,11 @@ frwr_op_open(struct rpcrdma_ia *ia, struct rpcrdma_ep *ep, struct ib_device_attr *devattr = &ia->ri_devattr; int depth, delta; + /* Obtain an lkey to use for the regbufs, which are + * protected from remote access. + */ + ia->ri_dma_lkey = ia->ri_device->local_dma_lkey; + ia->ri_max_frmr_depth = min_t(unsigned int, RPCRDMA_MAX_DATA_SEGS, devattr->max_fast_reg_page_list_len); diff --git a/net/sunrpc/xprtrdma/physical_ops.c b/net/sunrpc/xprtrdma/physical_ops.c index 41985d07fdb7..72cf8b15bbb4 100644 --- a/net/sunrpc/xprtrdma/physical_ops.c +++ b/net/sunrpc/xprtrdma/physical_ops.c @@ -23,6 +23,29 @@ static int physical_op_open(struct rpcrdma_ia *ia, struct rpcrdma_ep *ep, struct rpcrdma_create_data_internal *cdata) { + struct ib_device_attr *devattr = &ia->ri_devattr; + struct ib_mr *mr; + + /* Obtain an rkey to use for RPC data payloads. + */ + mr = ib_get_dma_mr(ia->ri_pd, + IB_ACCESS_LOCAL_WRITE | + IB_ACCESS_REMOTE_WRITE | + IB_ACCESS_REMOTE_READ); + if (IS_ERR(mr)) { + pr_err("%s: ib_get_dma_mr for failed with %lX\n", + __func__, PTR_ERR(mr)); + return -ENOMEM; + } + ia->ri_dma_mr = mr; + + /* Obtain an lkey to use for regbufs. + */ + if (devattr->device_cap_flags & IB_DEVICE_LOCAL_DMA_LKEY) + ia->ri_dma_lkey = ia->ri_device->local_dma_lkey; + else + ia->ri_dma_lkey = ia->ri_dma_mr->lkey; + return 0; } @@ -51,7 +74,7 @@ physical_op_map(struct rpcrdma_xprt *r_xprt, struct rpcrdma_mr_seg *seg, struct rpcrdma_ia *ia = &r_xprt->rx_ia; rpcrdma_map_one(ia->ri_device, seg, rpcrdma_data_dir(writing)); - seg->mr_rkey = ia->ri_bind_mem->rkey; + seg->mr_rkey = ia->ri_dma_mr->rkey; seg->mr_base = seg->mr_dma; seg->mr_nsegs = 1; return 1; diff --git a/net/sunrpc/xprtrdma/rpc_rdma.c b/net/sunrpc/xprtrdma/rpc_rdma.c index 84ea37daef36..bc8bd6577467 100644 --- a/net/sunrpc/xprtrdma/rpc_rdma.c +++ b/net/sunrpc/xprtrdma/rpc_rdma.c @@ -71,6 +71,67 @@ static const char transfertypes[][12] = { }; #endif +/* The client can send a request inline as long as the RPCRDMA header + * plus the RPC call fit under the transport's inline limit. If the + * combined call message size exceeds that limit, the client must use + * the read chunk list for this operation. + */ +static bool rpcrdma_args_inline(struct rpc_rqst *rqst) +{ + unsigned int callsize = RPCRDMA_HDRLEN_MIN + rqst->rq_snd_buf.len; + + return callsize <= RPCRDMA_INLINE_WRITE_THRESHOLD(rqst); +} + +/* The client can't know how large the actual reply will be. Thus it + * plans for the largest possible reply for that particular ULP + * operation. If the maximum combined reply message size exceeds that + * limit, the client must provide a write list or a reply chunk for + * this request. + */ +static bool rpcrdma_results_inline(struct rpc_rqst *rqst) +{ + unsigned int repsize = RPCRDMA_HDRLEN_MIN + rqst->rq_rcv_buf.buflen; + + return repsize <= RPCRDMA_INLINE_READ_THRESHOLD(rqst); +} + +static int +rpcrdma_tail_pullup(struct xdr_buf *buf) +{ + size_t tlen = buf->tail[0].iov_len; + size_t skip = tlen & 3; + + /* Do not include the tail if it is only an XDR pad */ + if (tlen < 4) + return 0; + + /* xdr_write_pages() adds a pad at the beginning of the tail + * if the content in "buf->pages" is unaligned. Force the + * tail's actual content to land at the next XDR position + * after the head instead. + */ + if (skip) { + unsigned char *src, *dst; + unsigned int count; + + src = buf->tail[0].iov_base; + dst = buf->head[0].iov_base; + dst += buf->head[0].iov_len; + + src += skip; + tlen -= skip; + + dprintk("RPC: %s: skip=%zu, memmove(%p, %p, %zu)\n", + __func__, skip, dst, src, tlen); + + for (count = tlen; count; count--) + *dst++ = *src++; + } + + return tlen; +} + /* * Chunk assembly from upper layer xdr_buf. * @@ -122,6 +183,10 @@ rpcrdma_convert_iovs(struct xdr_buf *xdrbuf, unsigned int pos, if (len && n == nsegs) return -EIO; + /* When encoding the read list, the tail is always sent inline */ + if (type == rpcrdma_readch) + return n; + if (xdrbuf->tail[0].iov_len) { /* the rpcrdma protocol allows us to omit any trailing * xdr pad bytes, saving the server an RDMA operation. */ @@ -297,8 +362,7 @@ out: * pre-registered memory buffer for this request. For small amounts * of data, this is efficient. The cutoff value is tunable. */ -static int -rpcrdma_inline_pullup(struct rpc_rqst *rqst, int pad) +static void rpcrdma_inline_pullup(struct rpc_rqst *rqst) { int i, npages, curlen; int copy_len; @@ -310,16 +374,9 @@ rpcrdma_inline_pullup(struct rpc_rqst *rqst, int pad) destp = rqst->rq_svec[0].iov_base; curlen = rqst->rq_svec[0].iov_len; destp += curlen; - /* - * Do optional padding where it makes sense. Alignment of write - * payload can help the server, if our setting is accurate. - */ - pad -= (curlen + 36/*sizeof(struct rpcrdma_msg_padded)*/); - if (pad < 0 || rqst->rq_slen - curlen < RPCRDMA_INLINE_PAD_THRESH) - pad = 0; /* don't pad this request */ - dprintk("RPC: %s: pad %d destp 0x%p len %d hdrlen %d\n", - __func__, pad, destp, rqst->rq_slen, curlen); + dprintk("RPC: %s: destp 0x%p len %d hdrlen %d\n", + __func__, destp, rqst->rq_slen, curlen); copy_len = rqst->rq_snd_buf.page_len; @@ -355,7 +412,6 @@ rpcrdma_inline_pullup(struct rpc_rqst *rqst, int pad) page_base = 0; } /* header now contains entire send message */ - return pad; } /* @@ -380,7 +436,7 @@ rpcrdma_marshal_req(struct rpc_rqst *rqst) struct rpcrdma_xprt *r_xprt = rpcx_to_rdmax(xprt); struct rpcrdma_req *req = rpcr_to_rdmar(rqst); char *base; - size_t rpclen, padlen; + size_t rpclen; ssize_t hdrlen; enum rpcrdma_chunktype rtype, wtype; struct rpcrdma_msg *headerp; @@ -402,28 +458,15 @@ rpcrdma_marshal_req(struct rpc_rqst *rqst) /* * Chunks needed for results? * + * o Read ops return data as write chunk(s), header as inline. * o If the expected result is under the inline threshold, all ops - * return as inline (but see later). + * return as inline. * o Large non-read ops return as a single reply chunk. - * o Large read ops return data as write chunk(s), header as inline. - * - * Note: the NFS code sending down multiple result segments implies - * the op is one of read, readdir[plus], readlink or NFSv4 getacl. - */ - - /* - * This code can handle read chunks, write chunks OR reply - * chunks -- only one type. If the request is too big to fit - * inline, then we will choose read chunks. If the request is - * a READ, then use write chunks to separate the file data - * into pages; otherwise use reply chunks. */ - if (rqst->rq_rcv_buf.buflen <= RPCRDMA_INLINE_READ_THRESHOLD(rqst)) - wtype = rpcrdma_noch; - else if (rqst->rq_rcv_buf.page_len == 0) - wtype = rpcrdma_replych; - else if (rqst->rq_rcv_buf.flags & XDRBUF_READ) + if (rqst->rq_rcv_buf.flags & XDRBUF_READ) wtype = rpcrdma_writech; + else if (rpcrdma_results_inline(rqst)) + wtype = rpcrdma_noch; else wtype = rpcrdma_replych; @@ -432,21 +475,25 @@ rpcrdma_marshal_req(struct rpc_rqst *rqst) * * o If the total request is under the inline threshold, all ops * are sent as inline. - * o Large non-write ops are sent with the entire message as a - * single read chunk (protocol 0-position special case). * o Large write ops transmit data as read chunk(s), header as * inline. + * o Large non-write ops are sent with the entire message as a + * single read chunk (protocol 0-position special case). * - * Note: the NFS code sending down multiple argument segments - * implies the op is a write. - * TBD check NFSv4 setacl + * This assumes that the upper layer does not present a request + * that both has a data payload, and whose non-data arguments + * by themselves are larger than the inline threshold. */ - if (rqst->rq_snd_buf.len <= RPCRDMA_INLINE_WRITE_THRESHOLD(rqst)) + if (rpcrdma_args_inline(rqst)) { rtype = rpcrdma_noch; - else if (rqst->rq_snd_buf.page_len == 0) - rtype = rpcrdma_areadch; - else + } else if (rqst->rq_snd_buf.flags & XDRBUF_WRITE) { rtype = rpcrdma_readch; + } else { + r_xprt->rx_stats.nomsg_call_count++; + headerp->rm_type = htonl(RDMA_NOMSG); + rtype = rpcrdma_areadch; + rpclen = 0; + } /* The following simplification is not true forever */ if (rtype != rpcrdma_noch && wtype == rpcrdma_replych) @@ -458,7 +505,6 @@ rpcrdma_marshal_req(struct rpc_rqst *rqst) } hdrlen = RPCRDMA_HDRLEN_MIN; - padlen = 0; /* * Pull up any extra send data into the preregistered buffer. @@ -467,45 +513,15 @@ rpcrdma_marshal_req(struct rpc_rqst *rqst) */ if (rtype == rpcrdma_noch) { - padlen = rpcrdma_inline_pullup(rqst, - RPCRDMA_INLINE_PAD_VALUE(rqst)); - - if (padlen) { - headerp->rm_type = rdma_msgp; - headerp->rm_body.rm_padded.rm_align = - cpu_to_be32(RPCRDMA_INLINE_PAD_VALUE(rqst)); - headerp->rm_body.rm_padded.rm_thresh = - cpu_to_be32(RPCRDMA_INLINE_PAD_THRESH); - headerp->rm_body.rm_padded.rm_pempty[0] = xdr_zero; - headerp->rm_body.rm_padded.rm_pempty[1] = xdr_zero; - headerp->rm_body.rm_padded.rm_pempty[2] = xdr_zero; - hdrlen += 2 * sizeof(u32); /* extra words in padhdr */ - if (wtype != rpcrdma_noch) { - dprintk("RPC: %s: invalid chunk list\n", - __func__); - return -EIO; - } - } else { - headerp->rm_body.rm_nochunks.rm_empty[0] = xdr_zero; - headerp->rm_body.rm_nochunks.rm_empty[1] = xdr_zero; - headerp->rm_body.rm_nochunks.rm_empty[2] = xdr_zero; - /* new length after pullup */ - rpclen = rqst->rq_svec[0].iov_len; - /* - * Currently we try to not actually use read inline. - * Reply chunks have the desirable property that - * they land, packed, directly in the target buffers - * without headers, so they require no fixup. The - * additional RDMA Write op sends the same amount - * of data, streams on-the-wire and adds no overhead - * on receive. Therefore, we request a reply chunk - * for non-writes wherever feasible and efficient. - */ - if (wtype == rpcrdma_noch) - wtype = rpcrdma_replych; - } - } + rpcrdma_inline_pullup(rqst); + headerp->rm_body.rm_nochunks.rm_empty[0] = xdr_zero; + headerp->rm_body.rm_nochunks.rm_empty[1] = xdr_zero; + headerp->rm_body.rm_nochunks.rm_empty[2] = xdr_zero; + /* new length after pullup */ + rpclen = rqst->rq_svec[0].iov_len; + } else if (rtype == rpcrdma_readch) + rpclen += rpcrdma_tail_pullup(&rqst->rq_snd_buf); if (rtype != rpcrdma_noch) { hdrlen = rpcrdma_create_chunks(rqst, &rqst->rq_snd_buf, headerp, rtype); @@ -518,9 +534,9 @@ rpcrdma_marshal_req(struct rpc_rqst *rqst) if (hdrlen < 0) return hdrlen; - dprintk("RPC: %s: %s: hdrlen %zd rpclen %zd padlen %zd" + dprintk("RPC: %s: %s: hdrlen %zd rpclen %zd" " headerp 0x%p base 0x%p lkey 0x%x\n", - __func__, transfertypes[wtype], hdrlen, rpclen, padlen, + __func__, transfertypes[wtype], hdrlen, rpclen, headerp, base, rdmab_lkey(req->rl_rdmabuf)); /* @@ -534,26 +550,15 @@ rpcrdma_marshal_req(struct rpc_rqst *rqst) req->rl_send_iov[0].length = hdrlen; req->rl_send_iov[0].lkey = rdmab_lkey(req->rl_rdmabuf); + req->rl_niovs = 1; + if (rtype == rpcrdma_areadch) + return 0; + req->rl_send_iov[1].addr = rdmab_addr(req->rl_sendbuf); req->rl_send_iov[1].length = rpclen; req->rl_send_iov[1].lkey = rdmab_lkey(req->rl_sendbuf); req->rl_niovs = 2; - - if (padlen) { - struct rpcrdma_ep *ep = &r_xprt->rx_ep; - - req->rl_send_iov[2].addr = rdmab_addr(ep->rep_padbuf); - req->rl_send_iov[2].length = padlen; - req->rl_send_iov[2].lkey = rdmab_lkey(ep->rep_padbuf); - - req->rl_send_iov[3].addr = req->rl_send_iov[1].addr + rpclen; - req->rl_send_iov[3].length = rqst->rq_slen - rpclen; - req->rl_send_iov[3].lkey = rdmab_lkey(req->rl_sendbuf); - - req->rl_niovs = 4; - } - return 0; } diff --git a/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c b/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c index 2e1348bde325..cb5174284074 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c +++ b/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c @@ -115,15 +115,6 @@ static void rdma_build_arg_xdr(struct svc_rqst *rqstp, rqstp->rq_arg.tail[0].iov_len = 0; } -static int rdma_read_max_sge(struct svcxprt_rdma *xprt, int sge_count) -{ - if (!rdma_cap_read_multi_sge(xprt->sc_cm_id->device, - xprt->sc_cm_id->port_num)) - return 1; - else - return min_t(int, sge_count, xprt->sc_max_sge); -} - /* Issue an RDMA_READ using the local lkey to map the data sink */ int rdma_read_chunk_lcl(struct svcxprt_rdma *xprt, struct svc_rqst *rqstp, @@ -144,8 +135,7 @@ int rdma_read_chunk_lcl(struct svcxprt_rdma *xprt, ctxt->direction = DMA_FROM_DEVICE; ctxt->read_hdr = head; - pages_needed = - min_t(int, pages_needed, rdma_read_max_sge(xprt, pages_needed)); + pages_needed = min_t(int, pages_needed, xprt->sc_max_sge_rd); read = min_t(int, pages_needed << PAGE_SHIFT, rs_length); for (pno = 0; pno < pages_needed; pno++) { diff --git a/net/sunrpc/xprtrdma/svc_rdma_sendto.c b/net/sunrpc/xprtrdma/svc_rdma_sendto.c index d25cd430f9ff..1dfae8317065 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_sendto.c +++ b/net/sunrpc/xprtrdma/svc_rdma_sendto.c @@ -136,6 +136,79 @@ static dma_addr_t dma_map_xdr(struct svcxprt_rdma *xprt, return dma_addr; } +/* Returns the address of the first read chunk or <nul> if no read chunk + * is present + */ +struct rpcrdma_read_chunk * +svc_rdma_get_read_chunk(struct rpcrdma_msg *rmsgp) +{ + struct rpcrdma_read_chunk *ch = + (struct rpcrdma_read_chunk *)&rmsgp->rm_body.rm_chunks[0]; + + if (ch->rc_discrim == xdr_zero) + return NULL; + return ch; +} + +/* Returns the address of the first read write array element or <nul> + * if no write array list is present + */ +static struct rpcrdma_write_array * +svc_rdma_get_write_array(struct rpcrdma_msg *rmsgp) +{ + if (rmsgp->rm_body.rm_chunks[0] != xdr_zero || + rmsgp->rm_body.rm_chunks[1] == xdr_zero) + return NULL; + return (struct rpcrdma_write_array *)&rmsgp->rm_body.rm_chunks[1]; +} + +/* Returns the address of the first reply array element or <nul> if no + * reply array is present + */ +static struct rpcrdma_write_array * +svc_rdma_get_reply_array(struct rpcrdma_msg *rmsgp) +{ + struct rpcrdma_read_chunk *rch; + struct rpcrdma_write_array *wr_ary; + struct rpcrdma_write_array *rp_ary; + + /* XXX: Need to fix when reply chunk may occur with read list + * and/or write list. + */ + if (rmsgp->rm_body.rm_chunks[0] != xdr_zero || + rmsgp->rm_body.rm_chunks[1] != xdr_zero) + return NULL; + + rch = svc_rdma_get_read_chunk(rmsgp); + if (rch) { + while (rch->rc_discrim != xdr_zero) + rch++; + + /* The reply chunk follows an empty write array located + * at 'rc_position' here. The reply array is at rc_target. + */ + rp_ary = (struct rpcrdma_write_array *)&rch->rc_target; + goto found_it; + } + + wr_ary = svc_rdma_get_write_array(rmsgp); + if (wr_ary) { + int chunk = be32_to_cpu(wr_ary->wc_nchunks); + + rp_ary = (struct rpcrdma_write_array *) + &wr_ary->wc_array[chunk].wc_target.rs_length; + goto found_it; + } + + /* No read list, no write list */ + rp_ary = (struct rpcrdma_write_array *)&rmsgp->rm_body.rm_chunks[2]; + + found_it: + if (rp_ary->wc_discrim == xdr_zero) + return NULL; + return rp_ary; +} + /* Assumptions: * - The specified write_len can be represented in sc_max_sge * PAGE_SIZE */ @@ -384,6 +457,7 @@ static int send_reply(struct svcxprt_rdma *rdma, int byte_count) { struct ib_send_wr send_wr; + u32 xdr_off; int sge_no; int sge_bytes; int page_no; @@ -418,8 +492,8 @@ static int send_reply(struct svcxprt_rdma *rdma, ctxt->direction = DMA_TO_DEVICE; /* Map the payload indicated by 'byte_count' */ + xdr_off = 0; for (sge_no = 1; byte_count && sge_no < vec->count; sge_no++) { - int xdr_off = 0; sge_bytes = min_t(size_t, vec->sge[sge_no].iov_len, byte_count); byte_count -= sge_bytes; ctxt->sge[sge_no].addr = @@ -457,6 +531,13 @@ static int send_reply(struct svcxprt_rdma *rdma, } rqstp->rq_next_page = rqstp->rq_respages + 1; + /* The loop above bumps sc_dma_used for each sge. The + * xdr_buf.tail gets a separate sge, but resides in the + * same page as xdr_buf.head. Don't count it twice. + */ + if (sge_no > ctxt->count) + atomic_dec(&rdma->sc_dma_used); + if (sge_no > rdma->sc_max_sge) { pr_err("svcrdma: Too many sges (%d)\n", sge_no); goto err; diff --git a/net/sunrpc/xprtrdma/svc_rdma_transport.c b/net/sunrpc/xprtrdma/svc_rdma_transport.c index 6b36279e4288..fcc3eb80c265 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_transport.c +++ b/net/sunrpc/xprtrdma/svc_rdma_transport.c @@ -91,7 +91,7 @@ struct svc_xprt_class svc_rdma_class = { .xcl_name = "rdma", .xcl_owner = THIS_MODULE, .xcl_ops = &svc_rdma_ops, - .xcl_max_payload = RPCRDMA_MAXPAYLOAD, + .xcl_max_payload = RPCSVC_MAXPAYLOAD_RDMA, .xcl_ident = XPRT_TRANSPORT_RDMA, }; @@ -659,6 +659,7 @@ static int rdma_cma_handler(struct rdma_cm_id *cma_id, if (xprt) { set_bit(XPT_CLOSE, &xprt->xpt_flags); svc_xprt_enqueue(xprt); + svc_xprt_put(xprt); } break; default: @@ -733,17 +734,19 @@ static struct svc_rdma_fastreg_mr *rdma_alloc_frmr(struct svcxprt_rdma *xprt) struct ib_mr *mr; struct ib_fast_reg_page_list *pl; struct svc_rdma_fastreg_mr *frmr; + u32 num_sg; frmr = kmalloc(sizeof(*frmr), GFP_KERNEL); if (!frmr) goto err; - mr = ib_alloc_fast_reg_mr(xprt->sc_pd, RPCSVC_MAXPAGES); + num_sg = min_t(u32, RPCSVC_MAXPAGES, xprt->sc_frmr_pg_list_len); + mr = ib_alloc_mr(xprt->sc_pd, IB_MR_TYPE_MEM_REG, num_sg); if (IS_ERR(mr)) goto err_free_frmr; pl = ib_alloc_fast_reg_page_list(xprt->sc_cm_id->device, - RPCSVC_MAXPAGES); + num_sg); if (IS_ERR(pl)) goto err_free_mr; @@ -872,6 +875,8 @@ static struct svc_xprt *svc_rdma_accept(struct svc_xprt *xprt) * capabilities of this particular device */ newxprt->sc_max_sge = min((size_t)devattr.max_sge, (size_t)RPCSVC_MAXPAGES); + newxprt->sc_max_sge_rd = min_t(size_t, devattr.max_sge_rd, + RPCSVC_MAXPAGES); newxprt->sc_max_requests = min((size_t)devattr.max_qp_wr, (size_t)svcrdma_max_requests); newxprt->sc_sq_depth = RPCRDMA_SQ_DEPTH_MULT * newxprt->sc_max_requests; @@ -1046,6 +1051,7 @@ static struct svc_xprt *svc_rdma_accept(struct svc_xprt *xprt) " remote_ip : %pI4\n" " remote_port : %d\n" " max_sge : %d\n" + " max_sge_rd : %d\n" " sq_depth : %d\n" " max_requests : %d\n" " ord : %d\n", @@ -1059,6 +1065,7 @@ static struct svc_xprt *svc_rdma_accept(struct svc_xprt *xprt) ntohs(((struct sockaddr_in *)&newxprt->sc_cm_id-> route.addr.dst_addr)->sin_port), newxprt->sc_max_sge, + newxprt->sc_max_sge_rd, newxprt->sc_sq_depth, newxprt->sc_max_requests, newxprt->sc_ord); @@ -1201,40 +1208,6 @@ static int svc_rdma_secure_port(struct svc_rqst *rqstp) return 1; } -/* - * Attempt to register the kvec representing the RPC memory with the - * device. - * - * Returns: - * NULL : The device does not support fastreg or there were no more - * fastreg mr. - * frmr : The kvec register request was successfully posted. - * <0 : An error was encountered attempting to register the kvec. - */ -int svc_rdma_fastreg(struct svcxprt_rdma *xprt, - struct svc_rdma_fastreg_mr *frmr) -{ - struct ib_send_wr fastreg_wr; - u8 key; - - /* Bump the key */ - key = (u8)(frmr->mr->lkey & 0x000000FF); - ib_update_fast_reg_key(frmr->mr, ++key); - - /* Prepare FASTREG WR */ - memset(&fastreg_wr, 0, sizeof fastreg_wr); - fastreg_wr.opcode = IB_WR_FAST_REG_MR; - fastreg_wr.send_flags = IB_SEND_SIGNALED; - fastreg_wr.wr.fast_reg.iova_start = (unsigned long)frmr->kva; - fastreg_wr.wr.fast_reg.page_list = frmr->page_list; - fastreg_wr.wr.fast_reg.page_list_len = frmr->page_list_len; - fastreg_wr.wr.fast_reg.page_shift = PAGE_SHIFT; - fastreg_wr.wr.fast_reg.length = frmr->map_len; - fastreg_wr.wr.fast_reg.access_flags = frmr->access_flags; - fastreg_wr.wr.fast_reg.rkey = frmr->mr->lkey; - return svc_rdma_send(xprt, &fastreg_wr); -} - int svc_rdma_send(struct svcxprt_rdma *xprt, struct ib_send_wr *wr) { struct ib_send_wr *bad_wr, *n_wr; diff --git a/net/sunrpc/xprtrdma/transport.c b/net/sunrpc/xprtrdma/transport.c index 680f888a9ddd..64443eb754ad 100644 --- a/net/sunrpc/xprtrdma/transport.c +++ b/net/sunrpc/xprtrdma/transport.c @@ -175,10 +175,8 @@ xprt_rdma_format_addresses6(struct rpc_xprt *xprt, struct sockaddr *sap) } static void -xprt_rdma_format_addresses(struct rpc_xprt *xprt) +xprt_rdma_format_addresses(struct rpc_xprt *xprt, struct sockaddr *sap) { - struct sockaddr *sap = (struct sockaddr *) - &rpcx_to_rdmad(xprt).addr; char buf[128]; switch (sap->sa_family) { @@ -302,7 +300,7 @@ xprt_setup_rdma(struct xprt_create *args) struct rpc_xprt *xprt; struct rpcrdma_xprt *new_xprt; struct rpcrdma_ep *new_ep; - struct sockaddr_in *sin; + struct sockaddr *sap; int rc; if (args->addrlen > sizeof(xprt->addr)) { @@ -333,26 +331,20 @@ xprt_setup_rdma(struct xprt_create *args) * Set up RDMA-specific connect data. */ - /* Put server RDMA address in local cdata */ - memcpy(&cdata.addr, args->dstaddr, args->addrlen); + sap = (struct sockaddr *)&cdata.addr; + memcpy(sap, args->dstaddr, args->addrlen); /* Ensure xprt->addr holds valid server TCP (not RDMA) * address, for any side protocols which peek at it */ xprt->prot = IPPROTO_TCP; xprt->addrlen = args->addrlen; - memcpy(&xprt->addr, &cdata.addr, xprt->addrlen); + memcpy(&xprt->addr, sap, xprt->addrlen); - sin = (struct sockaddr_in *)&cdata.addr; - if (ntohs(sin->sin_port) != 0) + if (rpc_get_port(sap)) xprt_set_bound(xprt); - dprintk("RPC: %s: %pI4:%u\n", - __func__, &sin->sin_addr.s_addr, ntohs(sin->sin_port)); - - /* Set max requests */ cdata.max_requests = xprt->max_reqs; - /* Set some length limits */ cdata.rsize = RPCRDMA_MAX_SEGS * PAGE_SIZE; /* RDMA write max */ cdata.wsize = RPCRDMA_MAX_SEGS * PAGE_SIZE; /* RDMA read max */ @@ -375,8 +367,7 @@ xprt_setup_rdma(struct xprt_create *args) new_xprt = rpcx_to_rdmax(xprt); - rc = rpcrdma_ia_open(new_xprt, (struct sockaddr *) &cdata.addr, - xprt_rdma_memreg_strategy); + rc = rpcrdma_ia_open(new_xprt, sap, xprt_rdma_memreg_strategy); if (rc) goto out1; @@ -409,7 +400,7 @@ xprt_setup_rdma(struct xprt_create *args) INIT_DELAYED_WORK(&new_xprt->rx_connect_worker, xprt_rdma_connect_worker); - xprt_rdma_format_addresses(xprt); + xprt_rdma_format_addresses(xprt, sap); xprt->max_payload = new_xprt->rx_ia.ri_ops->ro_maxpages(new_xprt); if (xprt->max_payload == 0) goto out4; @@ -420,6 +411,9 @@ xprt_setup_rdma(struct xprt_create *args) if (!try_module_get(THIS_MODULE)) goto out4; + dprintk("RPC: %s: %s:%s\n", __func__, + xprt->address_strings[RPC_DISPLAY_ADDR], + xprt->address_strings[RPC_DISPLAY_PORT]); return xprt; out4: @@ -653,31 +647,30 @@ static void xprt_rdma_print_stats(struct rpc_xprt *xprt, struct seq_file *seq) if (xprt_connected(xprt)) idle_time = (long)(jiffies - xprt->last_used) / HZ; - seq_printf(seq, - "\txprt:\trdma %u %lu %lu %lu %ld %lu %lu %lu %Lu %Lu " - "%lu %lu %lu %Lu %Lu %Lu %Lu %lu %lu %lu\n", - - 0, /* need a local port? */ - xprt->stat.bind_count, - xprt->stat.connect_count, - xprt->stat.connect_time, - idle_time, - xprt->stat.sends, - xprt->stat.recvs, - xprt->stat.bad_xids, - xprt->stat.req_u, - xprt->stat.bklog_u, - - r_xprt->rx_stats.read_chunk_count, - r_xprt->rx_stats.write_chunk_count, - r_xprt->rx_stats.reply_chunk_count, - r_xprt->rx_stats.total_rdma_request, - r_xprt->rx_stats.total_rdma_reply, - r_xprt->rx_stats.pullup_copy_count, - r_xprt->rx_stats.fixup_copy_count, - r_xprt->rx_stats.hardway_register_count, - r_xprt->rx_stats.failed_marshal_count, - r_xprt->rx_stats.bad_reply_count); + seq_puts(seq, "\txprt:\trdma "); + seq_printf(seq, "%u %lu %lu %lu %ld %lu %lu %lu %llu %llu ", + 0, /* need a local port? */ + xprt->stat.bind_count, + xprt->stat.connect_count, + xprt->stat.connect_time, + idle_time, + xprt->stat.sends, + xprt->stat.recvs, + xprt->stat.bad_xids, + xprt->stat.req_u, + xprt->stat.bklog_u); + seq_printf(seq, "%lu %lu %lu %llu %llu %llu %llu %lu %lu %lu %lu\n", + r_xprt->rx_stats.read_chunk_count, + r_xprt->rx_stats.write_chunk_count, + r_xprt->rx_stats.reply_chunk_count, + r_xprt->rx_stats.total_rdma_request, + r_xprt->rx_stats.total_rdma_reply, + r_xprt->rx_stats.pullup_copy_count, + r_xprt->rx_stats.fixup_copy_count, + r_xprt->rx_stats.hardway_register_count, + r_xprt->rx_stats.failed_marshal_count, + r_xprt->rx_stats.bad_reply_count, + r_xprt->rx_stats.nomsg_call_count); } static int diff --git a/net/sunrpc/xprtrdma/verbs.c b/net/sunrpc/xprtrdma/verbs.c index 891c4ede2c20..682996779970 100644 --- a/net/sunrpc/xprtrdma/verbs.c +++ b/net/sunrpc/xprtrdma/verbs.c @@ -52,6 +52,7 @@ #include <linux/prefetch.h> #include <linux/sunrpc/addr.h> #include <asm/bitops.h> +#include <linux/module.h> /* try_module_get()/module_put() */ #include "xprt_rdma.h" @@ -414,6 +415,14 @@ connected: return 0; } +static void rpcrdma_destroy_id(struct rdma_cm_id *id) +{ + if (id) { + module_put(id->device->owner); + rdma_destroy_id(id); + } +} + static struct rdma_cm_id * rpcrdma_create_id(struct rpcrdma_xprt *xprt, struct rpcrdma_ia *ia, struct sockaddr *addr) @@ -440,6 +449,17 @@ rpcrdma_create_id(struct rpcrdma_xprt *xprt, } wait_for_completion_interruptible_timeout(&ia->ri_done, msecs_to_jiffies(RDMA_RESOLVE_TIMEOUT) + 1); + + /* FIXME: + * Until xprtrdma supports DEVICE_REMOVAL, the provider must + * be pinned while there are active NFS/RDMA mounts to prevent + * hangs and crashes at umount time. + */ + if (!ia->ri_async_rc && !try_module_get(id->device->owner)) { + dprintk("RPC: %s: Failed to get device module\n", + __func__); + ia->ri_async_rc = -ENODEV; + } rc = ia->ri_async_rc; if (rc) goto out; @@ -449,16 +469,17 @@ rpcrdma_create_id(struct rpcrdma_xprt *xprt, if (rc) { dprintk("RPC: %s: rdma_resolve_route() failed %i\n", __func__, rc); - goto out; + goto put; } wait_for_completion_interruptible_timeout(&ia->ri_done, msecs_to_jiffies(RDMA_RESOLVE_TIMEOUT) + 1); rc = ia->ri_async_rc; if (rc) - goto out; + goto put; return id; - +put: + module_put(id->device->owner); out: rdma_destroy_id(id); return ERR_PTR(rc); @@ -493,9 +514,11 @@ rpcrdma_clean_cq(struct ib_cq *cq) int rpcrdma_ia_open(struct rpcrdma_xprt *xprt, struct sockaddr *addr, int memreg) { - int rc, mem_priv; struct rpcrdma_ia *ia = &xprt->rx_ia; struct ib_device_attr *devattr = &ia->ri_devattr; + int rc; + + ia->ri_dma_mr = NULL; ia->ri_id = rpcrdma_create_id(xprt, ia, addr); if (IS_ERR(ia->ri_id)) { @@ -519,11 +542,6 @@ rpcrdma_ia_open(struct rpcrdma_xprt *xprt, struct sockaddr *addr, int memreg) goto out3; } - if (devattr->device_cap_flags & IB_DEVICE_LOCAL_DMA_LKEY) { - ia->ri_have_dma_lkey = 1; - ia->ri_dma_lkey = ia->ri_device->local_dma_lkey; - } - if (memreg == RPCRDMA_FRMR) { /* Requires both frmr reg and local dma lkey */ if (((devattr->device_cap_flags & @@ -539,42 +557,19 @@ rpcrdma_ia_open(struct rpcrdma_xprt *xprt, struct sockaddr *addr, int memreg) if (!ia->ri_device->alloc_fmr) { dprintk("RPC: %s: MTHCAFMR registration " "not supported by HCA\n", __func__); - memreg = RPCRDMA_ALLPHYSICAL; + goto out3; } } - /* - * Optionally obtain an underlying physical identity mapping in - * order to do a memory window-based bind. This base registration - * is protected from remote access - that is enabled only by binding - * for the specific bytes targeted during each RPC operation, and - * revoked after the corresponding completion similar to a storage - * adapter. - */ switch (memreg) { case RPCRDMA_FRMR: ia->ri_ops = &rpcrdma_frwr_memreg_ops; break; case RPCRDMA_ALLPHYSICAL: ia->ri_ops = &rpcrdma_physical_memreg_ops; - mem_priv = IB_ACCESS_LOCAL_WRITE | - IB_ACCESS_REMOTE_WRITE | - IB_ACCESS_REMOTE_READ; - goto register_setup; + break; case RPCRDMA_MTHCAFMR: ia->ri_ops = &rpcrdma_fmr_memreg_ops; - if (ia->ri_have_dma_lkey) - break; - mem_priv = IB_ACCESS_LOCAL_WRITE; - register_setup: - ia->ri_bind_mem = ib_get_dma_mr(ia->ri_pd, mem_priv); - if (IS_ERR(ia->ri_bind_mem)) { - printk(KERN_ALERT "%s: ib_get_dma_mr for " - "phys register failed with %lX\n", - __func__, PTR_ERR(ia->ri_bind_mem)); - rc = -ENOMEM; - goto out3; - } break; default: printk(KERN_ERR "RPC: Unsupported memory " @@ -592,7 +587,7 @@ out3: ib_dealloc_pd(ia->ri_pd); ia->ri_pd = NULL; out2: - rdma_destroy_id(ia->ri_id); + rpcrdma_destroy_id(ia->ri_id); ia->ri_id = NULL; out1: return rc; @@ -606,25 +601,17 @@ out1: void rpcrdma_ia_close(struct rpcrdma_ia *ia) { - int rc; - dprintk("RPC: %s: entering\n", __func__); - if (ia->ri_bind_mem != NULL) { - rc = ib_dereg_mr(ia->ri_bind_mem); - dprintk("RPC: %s: ib_dereg_mr returned %i\n", - __func__, rc); - } - if (ia->ri_id != NULL && !IS_ERR(ia->ri_id)) { if (ia->ri_id->qp) rdma_destroy_qp(ia->ri_id); - rdma_destroy_id(ia->ri_id); + rpcrdma_destroy_id(ia->ri_id); ia->ri_id = NULL; } /* If the pd is still busy, xprtrdma missed freeing a resource */ if (ia->ri_pd && !IS_ERR(ia->ri_pd)) - WARN_ON(ib_dealloc_pd(ia->ri_pd)); + ib_dealloc_pd(ia->ri_pd); } /* @@ -639,6 +626,12 @@ rpcrdma_ep_create(struct rpcrdma_ep *ep, struct rpcrdma_ia *ia, struct ib_cq_init_attr cq_attr = {}; int rc, err; + if (devattr->max_sge < RPCRDMA_MAX_IOVS) { + dprintk("RPC: %s: insufficient sge's available\n", + __func__); + return -ENOMEM; + } + /* check provider's send/recv wr limits */ if (cdata->max_requests > devattr->max_qp_wr) cdata->max_requests = devattr->max_qp_wr; @@ -651,21 +644,13 @@ rpcrdma_ep_create(struct rpcrdma_ep *ep, struct rpcrdma_ia *ia, if (rc) return rc; ep->rep_attr.cap.max_recv_wr = cdata->max_requests; - ep->rep_attr.cap.max_send_sge = (cdata->padding ? 4 : 2); + ep->rep_attr.cap.max_send_sge = RPCRDMA_MAX_IOVS; ep->rep_attr.cap.max_recv_sge = 1; ep->rep_attr.cap.max_inline_data = 0; ep->rep_attr.sq_sig_type = IB_SIGNAL_REQ_WR; ep->rep_attr.qp_type = IB_QPT_RC; ep->rep_attr.port_num = ~0; - if (cdata->padding) { - ep->rep_padbuf = rpcrdma_alloc_regbuf(ia, cdata->padding, - GFP_KERNEL); - if (IS_ERR(ep->rep_padbuf)) - return PTR_ERR(ep->rep_padbuf); - } else - ep->rep_padbuf = NULL; - dprintk("RPC: %s: requested max: dtos: send %d recv %d; " "iovs: send %d recv %d\n", __func__, @@ -748,7 +733,8 @@ out2: dprintk("RPC: %s: ib_destroy_cq returned %i\n", __func__, err); out1: - rpcrdma_free_regbuf(ia, ep->rep_padbuf); + if (ia->ri_dma_mr) + ib_dereg_mr(ia->ri_dma_mr); return rc; } @@ -775,8 +761,6 @@ rpcrdma_ep_destroy(struct rpcrdma_ep *ep, struct rpcrdma_ia *ia) ia->ri_id->qp = NULL; } - rpcrdma_free_regbuf(ia, ep->rep_padbuf); - rpcrdma_clean_cq(ep->rep_attr.recv_cq); rc = ib_destroy_cq(ep->rep_attr.recv_cq); if (rc) @@ -788,6 +772,12 @@ rpcrdma_ep_destroy(struct rpcrdma_ep *ep, struct rpcrdma_ia *ia) if (rc) dprintk("RPC: %s: ib_destroy_cq returned %i\n", __func__, rc); + + if (ia->ri_dma_mr) { + rc = ib_dereg_mr(ia->ri_dma_mr); + dprintk("RPC: %s: ib_dereg_mr returned %i\n", + __func__, rc); + } } /* @@ -825,7 +815,7 @@ retry: if (ia->ri_device != id->device) { printk("RPC: %s: can't reconnect on " "different device!\n", __func__); - rdma_destroy_id(id); + rpcrdma_destroy_id(id); rc = -ENETUNREACH; goto out; } @@ -834,7 +824,7 @@ retry: if (rc) { dprintk("RPC: %s: rdma_create_qp failed %i\n", __func__, rc); - rdma_destroy_id(id); + rpcrdma_destroy_id(id); rc = -ENETUNREACH; goto out; } @@ -845,7 +835,7 @@ retry: write_unlock(&ia->ri_qplock); rdma_destroy_qp(old); - rdma_destroy_id(old); + rpcrdma_destroy_id(old); } else { dprintk("RPC: %s: connecting...\n", __func__); rc = rdma_create_qp(ia->ri_id, ia->ri_pd, &ep->rep_attr); @@ -1229,75 +1219,6 @@ rpcrdma_mapping_error(struct rpcrdma_mr_seg *seg) (unsigned long long)seg->mr_dma, seg->mr_dmalen); } -static int -rpcrdma_register_internal(struct rpcrdma_ia *ia, void *va, int len, - struct ib_mr **mrp, struct ib_sge *iov) -{ - struct ib_phys_buf ipb; - struct ib_mr *mr; - int rc; - - /* - * All memory passed here was kmalloc'ed, therefore phys-contiguous. - */ - iov->addr = ib_dma_map_single(ia->ri_device, - va, len, DMA_BIDIRECTIONAL); - if (ib_dma_mapping_error(ia->ri_device, iov->addr)) - return -ENOMEM; - - iov->length = len; - - if (ia->ri_have_dma_lkey) { - *mrp = NULL; - iov->lkey = ia->ri_dma_lkey; - return 0; - } else if (ia->ri_bind_mem != NULL) { - *mrp = NULL; - iov->lkey = ia->ri_bind_mem->lkey; - return 0; - } - - ipb.addr = iov->addr; - ipb.size = iov->length; - mr = ib_reg_phys_mr(ia->ri_pd, &ipb, 1, - IB_ACCESS_LOCAL_WRITE, &iov->addr); - - dprintk("RPC: %s: phys convert: 0x%llx " - "registered 0x%llx length %d\n", - __func__, (unsigned long long)ipb.addr, - (unsigned long long)iov->addr, len); - - if (IS_ERR(mr)) { - *mrp = NULL; - rc = PTR_ERR(mr); - dprintk("RPC: %s: failed with %i\n", __func__, rc); - } else { - *mrp = mr; - iov->lkey = mr->lkey; - rc = 0; - } - - return rc; -} - -static int -rpcrdma_deregister_internal(struct rpcrdma_ia *ia, - struct ib_mr *mr, struct ib_sge *iov) -{ - int rc; - - ib_dma_unmap_single(ia->ri_device, - iov->addr, iov->length, DMA_BIDIRECTIONAL); - - if (NULL == mr) - return 0; - - rc = ib_dereg_mr(mr); - if (rc) - dprintk("RPC: %s: ib_dereg_mr failed %i\n", __func__, rc); - return rc; -} - /** * rpcrdma_alloc_regbuf - kmalloc and register memory for SEND/RECV buffers * @ia: controlling rpcrdma_ia @@ -1317,26 +1238,29 @@ struct rpcrdma_regbuf * rpcrdma_alloc_regbuf(struct rpcrdma_ia *ia, size_t size, gfp_t flags) { struct rpcrdma_regbuf *rb; - int rc; + struct ib_sge *iov; - rc = -ENOMEM; rb = kmalloc(sizeof(*rb) + size, flags); if (rb == NULL) goto out; - rb->rg_size = size; - rb->rg_owner = NULL; - rc = rpcrdma_register_internal(ia, rb->rg_base, size, - &rb->rg_mr, &rb->rg_iov); - if (rc) + iov = &rb->rg_iov; + iov->addr = ib_dma_map_single(ia->ri_device, + (void *)rb->rg_base, size, + DMA_BIDIRECTIONAL); + if (ib_dma_mapping_error(ia->ri_device, iov->addr)) goto out_free; + iov->length = size; + iov->lkey = ia->ri_dma_lkey; + rb->rg_size = size; + rb->rg_owner = NULL; return rb; out_free: kfree(rb); out: - return ERR_PTR(rc); + return ERR_PTR(-ENOMEM); } /** @@ -1347,10 +1271,15 @@ out: void rpcrdma_free_regbuf(struct rpcrdma_ia *ia, struct rpcrdma_regbuf *rb) { - if (rb) { - rpcrdma_deregister_internal(ia, rb->rg_mr, &rb->rg_iov); - kfree(rb); - } + struct ib_sge *iov; + + if (!rb) + return; + + iov = &rb->rg_iov; + ib_dma_unmap_single(ia->ri_device, + iov->addr, iov->length, DMA_BIDIRECTIONAL); + kfree(rb); } /* @@ -1363,9 +1292,11 @@ rpcrdma_ep_post(struct rpcrdma_ia *ia, struct rpcrdma_ep *ep, struct rpcrdma_req *req) { + struct ib_device *device = ia->ri_device; struct ib_send_wr send_wr, *send_wr_fail; struct rpcrdma_rep *rep = req->rl_reply; - int rc; + struct ib_sge *iov = req->rl_send_iov; + int i, rc; if (rep) { rc = rpcrdma_ep_post_recv(ia, ep, rep); @@ -1376,22 +1307,15 @@ rpcrdma_ep_post(struct rpcrdma_ia *ia, send_wr.next = NULL; send_wr.wr_id = RPCRDMA_IGNORE_COMPLETION; - send_wr.sg_list = req->rl_send_iov; + send_wr.sg_list = iov; send_wr.num_sge = req->rl_niovs; send_wr.opcode = IB_WR_SEND; - if (send_wr.num_sge == 4) /* no need to sync any pad (constant) */ - ib_dma_sync_single_for_device(ia->ri_device, - req->rl_send_iov[3].addr, - req->rl_send_iov[3].length, - DMA_TO_DEVICE); - ib_dma_sync_single_for_device(ia->ri_device, - req->rl_send_iov[1].addr, - req->rl_send_iov[1].length, - DMA_TO_DEVICE); - ib_dma_sync_single_for_device(ia->ri_device, - req->rl_send_iov[0].addr, - req->rl_send_iov[0].length, - DMA_TO_DEVICE); + + for (i = 0; i < send_wr.num_sge; i++) + ib_dma_sync_single_for_device(device, iov[i].addr, + iov[i].length, DMA_TO_DEVICE); + dprintk("RPC: %s: posting %d s/g entries\n", + __func__, send_wr.num_sge); if (DECR_CQCOUNT(ep) > 0) send_wr.send_flags = 0; diff --git a/net/sunrpc/xprtrdma/xprt_rdma.h b/net/sunrpc/xprtrdma/xprt_rdma.h index f49dd8b38122..02512221b8bc 100644 --- a/net/sunrpc/xprtrdma/xprt_rdma.h +++ b/net/sunrpc/xprtrdma/xprt_rdma.h @@ -51,7 +51,6 @@ #include <linux/sunrpc/clnt.h> /* rpc_xprt */ #include <linux/sunrpc/rpc_rdma.h> /* RPC/RDMA protocol */ #include <linux/sunrpc/xprtrdma.h> /* xprt parameters */ -#include <linux/sunrpc/svc.h> /* RPCSVC_MAXPAYLOAD */ #define RDMA_RESOLVE_TIMEOUT (5000) /* 5 seconds */ #define RDMA_CONNECT_RETRY_MAX (2) /* retries if no listener backlog */ @@ -65,9 +64,8 @@ struct rpcrdma_ia { struct ib_device *ri_device; struct rdma_cm_id *ri_id; struct ib_pd *ri_pd; - struct ib_mr *ri_bind_mem; + struct ib_mr *ri_dma_mr; u32 ri_dma_lkey; - int ri_have_dma_lkey; struct completion ri_done; int ri_async_rc; unsigned int ri_max_frmr_depth; @@ -89,7 +87,6 @@ struct rpcrdma_ep { int rep_connected; struct ib_qp_init_attr rep_attr; wait_queue_head_t rep_connect_wait; - struct rpcrdma_regbuf *rep_padbuf; struct rdma_conn_param rep_remote_cma; struct sockaddr_storage rep_remote_addr; struct delayed_work rep_connect_worker; @@ -119,7 +116,6 @@ struct rpcrdma_ep { struct rpcrdma_regbuf { size_t rg_size; struct rpcrdma_req *rg_owner; - struct ib_mr *rg_mr; struct ib_sge rg_iov; __be32 rg_base[0] __attribute__ ((aligned(256))); }; @@ -165,8 +161,7 @@ rdmab_to_msg(struct rpcrdma_regbuf *rb) * struct rpcrdma_buffer. N is the max number of outstanding requests. */ -/* temporary static scatter/gather max */ -#define RPCRDMA_MAX_DATA_SEGS (64) /* max scatter/gather */ +#define RPCRDMA_MAX_DATA_SEGS ((1 * 1024 * 1024) / PAGE_SIZE) #define RPCRDMA_MAX_SEGS (RPCRDMA_MAX_DATA_SEGS + 2) /* head+tail = 2 */ struct rpcrdma_buffer; @@ -258,16 +253,18 @@ struct rpcrdma_mr_seg { /* chunk descriptors */ char *mr_offset; /* kva if no page, else offset */ }; +#define RPCRDMA_MAX_IOVS (2) + struct rpcrdma_req { - unsigned int rl_niovs; /* 0, 2 or 4 */ - unsigned int rl_nchunks; /* non-zero if chunks */ - unsigned int rl_connect_cookie; /* retry detection */ - struct rpcrdma_buffer *rl_buffer; /* home base for this structure */ + unsigned int rl_niovs; + unsigned int rl_nchunks; + unsigned int rl_connect_cookie; + struct rpcrdma_buffer *rl_buffer; struct rpcrdma_rep *rl_reply;/* holder for reply buffer */ - struct ib_sge rl_send_iov[4]; /* for active requests */ - struct rpcrdma_regbuf *rl_rdmabuf; - struct rpcrdma_regbuf *rl_sendbuf; - struct rpcrdma_mr_seg rl_segments[RPCRDMA_MAX_SEGS]; + struct ib_sge rl_send_iov[RPCRDMA_MAX_IOVS]; + struct rpcrdma_regbuf *rl_rdmabuf; + struct rpcrdma_regbuf *rl_sendbuf; + struct rpcrdma_mr_seg rl_segments[RPCRDMA_MAX_SEGS]; }; static inline struct rpcrdma_req * @@ -342,6 +339,7 @@ struct rpcrdma_stats { unsigned long hardway_register_count; unsigned long failed_marshal_count; unsigned long bad_reply_count; + unsigned long nomsg_call_count; }; /* diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c index 0030376327b7..7be90bc1a7c2 100644 --- a/net/sunrpc/xprtsock.c +++ b/net/sunrpc/xprtsock.c @@ -822,6 +822,8 @@ static void xs_reset_transport(struct sock_xprt *transport) if (atomic_read(&transport->xprt.swapper)) sk_clear_memalloc(sk); + kernel_sock_shutdown(sock, SHUT_RDWR); + write_lock_bh(&sk->sk_callback_lock); transport->inet = NULL; transport->sock = NULL; @@ -829,6 +831,7 @@ static void xs_reset_transport(struct sock_xprt *transport) sk->sk_user_data = NULL; xs_restore_old_callbacks(transport, sk); + xprt_clear_connected(xprt); write_unlock_bh(&sk->sk_callback_lock); xs_sock_reset_connection_flags(xprt); @@ -1866,7 +1869,7 @@ static int xs_local_finish_connecting(struct rpc_xprt *xprt, sk->sk_data_ready = xs_local_data_ready; sk->sk_write_space = xs_udp_write_space; sk->sk_error_report = xs_error_report; - sk->sk_allocation = GFP_ATOMIC; + sk->sk_allocation = GFP_NOIO; xprt_clear_connected(xprt); @@ -2051,7 +2054,7 @@ static void xs_udp_finish_connecting(struct rpc_xprt *xprt, struct socket *sock) sk->sk_user_data = xprt; sk->sk_data_ready = xs_udp_data_ready; sk->sk_write_space = xs_udp_write_space; - sk->sk_allocation = GFP_ATOMIC; + sk->sk_allocation = GFP_NOIO; xprt_set_connected(xprt); @@ -2153,7 +2156,7 @@ static int xs_tcp_finish_connecting(struct rpc_xprt *xprt, struct socket *sock) sk->sk_state_change = xs_tcp_state_change; sk->sk_write_space = xs_tcp_write_space; sk->sk_error_report = xs_error_report; - sk->sk_allocation = GFP_ATOMIC; + sk->sk_allocation = GFP_NOIO; /* socket options */ sock_reset_flag(sk, SOCK_LINGER); @@ -2279,13 +2282,14 @@ static void xs_connect(struct rpc_xprt *xprt, struct rpc_task *task) WARN_ON_ONCE(!xprt_lock_connect(xprt, task, transport)); - /* Start by resetting any existing state */ - xs_reset_transport(transport); - - if (transport->sock != NULL && !RPC_IS_SOFTCONN(task)) { + if (transport->sock != NULL) { dprintk("RPC: xs_connect delayed xprt %p for %lu " "seconds\n", xprt, xprt->reestablish_timeout / HZ); + + /* Start by resetting any existing state */ + xs_reset_transport(transport); + queue_delayed_work(rpciod_workqueue, &transport->connect_worker, xprt->reestablish_timeout); diff --git a/net/switchdev/switchdev.c b/net/switchdev/switchdev.c index 9f2add3cba26..fda38f830a10 100644 --- a/net/switchdev/switchdev.c +++ b/net/switchdev/switchdev.c @@ -810,7 +810,7 @@ static int switchdev_port_fdb_dump_cb(struct net_device *dev, ndm->ndm_flags = NTF_SELF; ndm->ndm_type = 0; ndm->ndm_ifindex = dev->ifindex; - ndm->ndm_state = NUD_REACHABLE; + ndm->ndm_state = obj->u.fdb.ndm_state; if (nla_put(dump->skb, NDA_LLADDR, ETH_ALEN, obj->u.fdb.addr)) goto nla_put_failure; @@ -853,12 +853,8 @@ int switchdev_port_fdb_dump(struct sk_buff *skb, struct netlink_callback *cb, .cb = cb, .idx = idx, }; - int err; - - err = switchdev_port_obj_dump(dev, &dump.obj); - if (err) - return err; + switchdev_port_obj_dump(dev, &dump.obj); return dump.idx; } EXPORT_SYMBOL_GPL(switchdev_port_fdb_dump); @@ -910,13 +906,9 @@ static struct net_device *switchdev_get_dev_by_nhs(struct fib_info *fi) if (switchdev_port_attr_get(dev, &attr)) return NULL; - if (nhsel > 0) { - if (prev_attr.u.ppid.id_len != attr.u.ppid.id_len) - return NULL; - if (memcmp(prev_attr.u.ppid.id, attr.u.ppid.id, - attr.u.ppid.id_len)) + if (nhsel > 0 && + !netdev_phys_item_id_same(&prev_attr.u.ppid, &attr.u.ppid)) return NULL; - } prev_attr = attr; } @@ -1043,3 +1035,106 @@ void switchdev_fib_ipv4_abort(struct fib_info *fi) fi->fib_net->ipv4.fib_offload_disabled = true; } EXPORT_SYMBOL_GPL(switchdev_fib_ipv4_abort); + +static bool switchdev_port_same_parent_id(struct net_device *a, + struct net_device *b) +{ + struct switchdev_attr a_attr = { + .id = SWITCHDEV_ATTR_PORT_PARENT_ID, + .flags = SWITCHDEV_F_NO_RECURSE, + }; + struct switchdev_attr b_attr = { + .id = SWITCHDEV_ATTR_PORT_PARENT_ID, + .flags = SWITCHDEV_F_NO_RECURSE, + }; + + if (switchdev_port_attr_get(a, &a_attr) || + switchdev_port_attr_get(b, &b_attr)) + return false; + + 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; +} + +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 && joining) { + mark = switchdev_port_fwd_mark_get(dev, group_dev); + } else if (group_dev && !joining) { + 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/tipc/bcast.c b/net/tipc/bcast.c index a816382fc8af..41042de3ae9b 100644 --- a/net/tipc/bcast.c +++ b/net/tipc/bcast.c @@ -170,6 +170,30 @@ static void bclink_retransmit_pkt(struct tipc_net *tn, u32 after, u32 to) } /** + * bclink_prepare_wakeup - prepare users for wakeup after congestion + * @bcl: broadcast link + * @resultq: queue for users which can be woken up + * Move a number of waiting users, as permitted by available space in + * the send queue, from link wait queue to specified queue for wakeup + */ +static void bclink_prepare_wakeup(struct tipc_link *bcl, struct sk_buff_head *resultq) +{ + int pnd[TIPC_SYSTEM_IMPORTANCE + 1] = {0,}; + int imp, lim; + struct sk_buff *skb, *tmp; + + skb_queue_walk_safe(&bcl->wakeupq, skb, tmp) { + imp = TIPC_SKB_CB(skb)->chain_imp; + lim = bcl->window + bcl->backlog[imp].limit; + pnd[imp] += TIPC_SKB_CB(skb)->chain_sz; + if ((pnd[imp] + bcl->backlog[imp].len) >= lim) + continue; + skb_unlink(skb, &bcl->wakeupq); + skb_queue_tail(resultq, skb); + } +} + +/** * tipc_bclink_wakeup_users - wake up pending users * * Called with no locks taken @@ -177,8 +201,12 @@ static void bclink_retransmit_pkt(struct tipc_net *tn, u32 after, u32 to) void tipc_bclink_wakeup_users(struct net *net) { struct tipc_net *tn = net_generic(net, tipc_net_id); + struct tipc_link *bcl = tn->bcl; + struct sk_buff_head resultq; - tipc_sk_rcv(net, &tn->bclink->link.wakeupq); + skb_queue_head_init(&resultq); + bclink_prepare_wakeup(bcl, &resultq); + tipc_sk_rcv(net, &resultq); } /** @@ -316,6 +344,29 @@ void tipc_bclink_update_link_state(struct tipc_node *n_ptr, } } +void tipc_bclink_sync_state(struct tipc_node *n, struct tipc_msg *hdr) +{ + u16 last = msg_last_bcast(hdr); + int mtyp = msg_type(hdr); + + if (unlikely(msg_user(hdr) != LINK_PROTOCOL)) + return; + if (mtyp == STATE_MSG) { + tipc_bclink_update_link_state(n, last); + return; + } + /* Compatibility: older nodes don't know BCAST_PROTOCOL synchronization, + * and transfer synch info in LINK_PROTOCOL messages. + */ + if (tipc_node_is_up(n)) + return; + if ((mtyp != RESET_MSG) && (mtyp != ACTIVATE_MSG)) + return; + n->bclink.last_sent = last; + n->bclink.last_in = last; + n->bclink.oos_state = 0; +} + /** * bclink_peek_nack - monitor retransmission requests sent by other nodes * @@ -358,10 +409,9 @@ int tipc_bclink_xmit(struct net *net, struct sk_buff_head *list) /* Prepare clone of message for local node */ skb = tipc_msg_reassemble(list); - if (unlikely(!skb)) { - __skb_queue_purge(list); + if (unlikely(!skb)) return -EHOSTUNREACH; - } + /* Broadcast to all nodes */ if (likely(bclink)) { tipc_bclink_lock(net); @@ -413,7 +463,7 @@ static void bclink_accept_pkt(struct tipc_node *node, u32 seqno) * all nodes in the cluster don't ACK at the same time */ if (((seqno - tn->own_addr) % TIPC_MIN_LINK_WIN) == 0) { - tipc_link_proto_xmit(node->active_links[node->addr & 1], + tipc_link_proto_xmit(node_active_link(node, node->addr), STATE_MSG, 0, 0, 0, 0); tn->bcl->stats.sent_acks++; } @@ -925,7 +975,6 @@ int tipc_bclink_init(struct net *net) tipc_link_set_queue_limits(bcl, BCLINK_WIN_DEFAULT); bcl->bearer_id = MAX_BEARERS; rcu_assign_pointer(tn->bearer_list[MAX_BEARERS], &bcbearer->bearer); - bcl->state = WORKING_WORKING; bcl->pmsg = (struct tipc_msg *)&bcl->proto_msg; msg_set_prevnode(bcl->pmsg, tn->own_addr); strlcpy(bcl->name, tipc_bclink_name, TIPC_MAX_LINK_NAME); diff --git a/net/tipc/bcast.h b/net/tipc/bcast.h index 3c290a48f720..d74c69bcf60b 100644 --- a/net/tipc/bcast.h +++ b/net/tipc/bcast.h @@ -133,5 +133,6 @@ void tipc_bclink_wakeup_users(struct net *net); 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[]); void tipc_bclink_input(struct net *net); +void tipc_bclink_sync_state(struct tipc_node *n, struct tipc_msg *msg); #endif diff --git a/net/tipc/bearer.c b/net/tipc/bearer.c index 00bc0e620532..ce9f7bfc0b92 100644 --- a/net/tipc/bearer.c +++ b/net/tipc/bearer.c @@ -343,7 +343,7 @@ restart: static int tipc_reset_bearer(struct net *net, struct tipc_bearer *b_ptr) { pr_info("Resetting bearer <%s>\n", b_ptr->name); - tipc_link_delete_list(net, b_ptr->identity); + tipc_node_delete_links(net, b_ptr->identity); tipc_disc_reset(net, b_ptr); return 0; } @@ -361,7 +361,7 @@ static void bearer_disable(struct net *net, struct tipc_bearer *b_ptr) pr_info("Disabling bearer <%s>\n", b_ptr->name); b_ptr->media->disable_media(b_ptr); - tipc_link_delete_list(net, b_ptr->identity); + tipc_node_delete_links(net, b_ptr->identity); if (b_ptr->link_req) tipc_disc_delete(b_ptr->link_req); @@ -470,6 +470,32 @@ void tipc_bearer_send(struct net *net, u32 bearer_id, struct sk_buff *buf, rcu_read_unlock(); } +/* tipc_bearer_xmit() -send buffer to destination over bearer + */ +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; + + if (skb_queue_empty(xmitq)) + return; + + rcu_read_lock(); + b = rcu_dereference_rtnl(tn->bearer_list[bearer_id]); + if (likely(b)) { + skb_queue_walk_safe(xmitq, skb, tmp) { + __skb_dequeue(xmitq); + b->media->send_msg(net, skb, b, dst); + /* Until we remove cloning in tipc_l2_send_msg(): */ + kfree_skb(skb); + } + } + rcu_read_unlock(); +} + /** * tipc_l2_rcv_msg - handle incoming TIPC message from an interface * @buf: the received packet diff --git a/net/tipc/bearer.h b/net/tipc/bearer.h index dc714d977768..6426f242f626 100644 --- a/net/tipc/bearer.h +++ b/net/tipc/bearer.h @@ -217,5 +217,8 @@ void tipc_bearer_cleanup(void); void tipc_bearer_stop(struct net *net); void tipc_bearer_send(struct net *net, u32 bearer_id, struct sk_buff *buf, struct tipc_media_addr *dest); +void tipc_bearer_xmit(struct net *net, u32 bearer_id, + struct sk_buff_head *xmitq, + struct tipc_media_addr *dst); #endif /* _TIPC_BEARER_H */ diff --git a/net/tipc/core.h b/net/tipc/core.h index 0fcf133d5cb7..b96b41eabf12 100644 --- a/net/tipc/core.h +++ b/net/tipc/core.h @@ -109,6 +109,11 @@ struct tipc_net { atomic_t subscription_count; }; +static inline struct tipc_net *tipc_net(struct net *net) +{ + return net_generic(net, tipc_net_id); +} + static inline u16 mod(u16 x) { return x & 0xffffu; @@ -129,6 +134,11 @@ static inline int less(u16 left, u16 right) return less_eq(left, right) && (mod(right) != mod(left)); } +static inline int in_range(u16 val, u16 min, u16 max) +{ + return !less(val, min) && !more(val, max); +} + #ifdef CONFIG_SYSCTL int tipc_register_sysctl(void); void tipc_unregister_sysctl(void); diff --git a/net/tipc/discover.c b/net/tipc/discover.c index 967e292f53c8..d14e0a4aa9af 100644 --- a/net/tipc/discover.c +++ b/net/tipc/discover.c @@ -35,7 +35,7 @@ */ #include "core.h" -#include "link.h" +#include "node.h" #include "discover.h" /* min delay during bearer start up */ @@ -120,30 +120,24 @@ static void disc_dupl_alert(struct tipc_bearer *b_ptr, u32 node_addr, * @buf: buffer containing message * @bearer: bearer that message arrived on */ -void tipc_disc_rcv(struct net *net, struct sk_buff *buf, +void tipc_disc_rcv(struct net *net, struct sk_buff *skb, struct tipc_bearer *bearer) { struct tipc_net *tn = net_generic(net, tipc_net_id); - struct tipc_node *node; - struct tipc_link *link; struct tipc_media_addr maddr; - struct sk_buff *rbuf; - struct tipc_msg *msg = buf_msg(buf); - u32 ddom = msg_dest_domain(msg); - u32 onode = msg_prevnode(msg); - u32 net_id = msg_bc_netid(msg); - u32 mtyp = msg_type(msg); - u32 signature = msg_node_sig(msg); - u16 caps = msg_node_capabilities(msg); - bool addr_match = false; - bool sign_match = false; - bool link_up = false; - bool accept_addr = false; - bool accept_sign = false; + struct sk_buff *rskb; + struct tipc_msg *hdr = buf_msg(skb); + u32 ddom = msg_dest_domain(hdr); + u32 onode = msg_prevnode(hdr); + u32 net_id = msg_bc_netid(hdr); + u32 mtyp = msg_type(hdr); + u32 signature = msg_node_sig(hdr); + u16 caps = msg_node_capabilities(hdr); bool respond = false; + bool dupl_addr = false; - bearer->media->msg2addr(bearer, &maddr, msg_media_addr(msg)); - kfree_skb(buf); + bearer->media->msg2addr(bearer, &maddr, msg_media_addr(hdr)); + kfree_skb(skb); /* Ensure message from node is valid and communication is permitted */ if (net_id != tn->net_id) @@ -165,102 +159,20 @@ void tipc_disc_rcv(struct net *net, struct sk_buff *buf, if (!tipc_in_scope(bearer->domain, onode)) return; - node = tipc_node_create(net, onode); - if (!node) - return; - tipc_node_lock(node); - node->capabilities = caps; - link = node->links[bearer->identity]; - - /* Prepare to validate requesting node's signature and media address */ - sign_match = (signature == node->signature); - addr_match = link && !memcmp(&link->media_addr, &maddr, sizeof(maddr)); - link_up = link && tipc_link_is_up(link); - - - /* These three flags give us eight permutations: */ - - if (sign_match && addr_match && link_up) { - /* All is fine. Do nothing. */ - } else if (sign_match && addr_match && !link_up) { - /* Respond. The link will come up in due time */ - respond = true; - } else if (sign_match && !addr_match && link_up) { - /* Peer has changed i/f address without rebooting. - * If so, the link will reset soon, and the next - * discovery will be accepted. So we can ignore it. - * It may also be an cloned or malicious peer having - * chosen the same node address and signature as an - * existing one. - * Ignore requests until the link goes down, if ever. - */ - disc_dupl_alert(bearer, onode, &maddr); - } else if (sign_match && !addr_match && !link_up) { - /* Peer link has changed i/f address without rebooting. - * It may also be a cloned or malicious peer; we can't - * distinguish between the two. - * The signature is correct, so we must accept. - */ - accept_addr = true; - respond = true; - } else if (!sign_match && addr_match && link_up) { - /* Peer node rebooted. Two possibilities: - * - Delayed re-discovery; this link endpoint has already - * reset and re-established contact with the peer, before - * receiving a discovery message from that node. - * (The peer happened to receive one from this node first). - * - The peer came back so fast that our side has not - * discovered it yet. Probing from this side will soon - * reset the link, since there can be no working link - * endpoint at the peer end, and the link will re-establish. - * Accept the signature, since it comes from a known peer. - */ - accept_sign = true; - } else if (!sign_match && addr_match && !link_up) { - /* The peer node has rebooted. - * Accept signature, since it is a known peer. - */ - accept_sign = true; - respond = true; - } else if (!sign_match && !addr_match && link_up) { - /* Peer rebooted with new address, or a new/duplicate peer. - * Ignore until the link goes down, if ever. - */ + tipc_node_check_dest(net, onode, bearer, caps, signature, + &maddr, &respond, &dupl_addr); + if (dupl_addr) disc_dupl_alert(bearer, onode, &maddr); - } else if (!sign_match && !addr_match && !link_up) { - /* Peer rebooted with new address, or it is a new peer. - * Accept signature and address. - */ - accept_sign = true; - accept_addr = true; - respond = true; - } - - if (accept_sign) - node->signature = signature; - - if (accept_addr) { - if (!link) - link = tipc_link_create(node, bearer, &maddr); - if (link) { - memcpy(&link->media_addr, &maddr, sizeof(maddr)); - tipc_link_reset(link); - } else { - respond = false; - } - } /* Send response, if necessary */ if (respond && (mtyp == DSC_REQ_MSG)) { - rbuf = tipc_buf_acquire(MAX_H_SIZE); - if (rbuf) { - tipc_disc_init_msg(net, rbuf, DSC_RESP_MSG, bearer); - tipc_bearer_send(net, bearer->identity, rbuf, &maddr); - kfree_skb(rbuf); + rskb = tipc_buf_acquire(MAX_H_SIZE); + if (rskb) { + tipc_disc_init_msg(net, rskb, DSC_RESP_MSG, bearer); + tipc_bearer_send(net, bearer->identity, rskb, &maddr); + kfree_skb(rskb); } } - tipc_node_unlock(node); - tipc_node_put(node); } /** diff --git a/net/tipc/link.c b/net/tipc/link.c index eaa9fe54b4ae..75db07c78a69 100644 --- a/net/tipc/link.c +++ b/net/tipc/link.c @@ -48,9 +48,8 @@ /* * Error message prefixes */ -static const char *link_co_err = "Link changeover error, "; +static const char *link_co_err = "Link tunneling error, "; static const char *link_rst_msg = "Resetting link "; -static const char *link_unk_evt = "Unknown link event "; static const struct nla_policy tipc_nl_link_policy[TIPC_NLA_LINK_MAX + 1] = { [TIPC_NLA_LINK_UNSPEC] = { .type = NLA_UNSPEC }, @@ -77,256 +76,413 @@ static const struct nla_policy tipc_nl_prop_policy[TIPC_NLA_PROP_MAX + 1] = { }; /* + * Interval between NACKs when packets arrive out of order + */ +#define TIPC_NACK_INTV (TIPC_MIN_LINK_WIN * 2) +/* * Out-of-range value for link session numbers */ -#define INVALID_SESSION 0x10000 +#define WILDCARD_SESSION 0x10000 -/* - * Link state events: +/* Link FSM states: */ -#define STARTING_EVT 856384768 /* link processing trigger */ -#define TRAFFIC_MSG_EVT 560815u /* rx'd ??? */ -#define SILENCE_EVT 560817u /* timer dicovered silence from peer */ +enum { + LINK_ESTABLISHED = 0xe, + LINK_ESTABLISHING = 0xe << 4, + LINK_RESET = 0x1 << 8, + LINK_RESETTING = 0x2 << 12, + LINK_PEER_RESET = 0xd << 16, + LINK_FAILINGOVER = 0xf << 20, + LINK_SYNCHING = 0xc << 24 +}; -/* - * State value stored in 'failover_pkts' +/* Link FSM state checking routines */ -#define FIRST_FAILOVER 0xffffu - -static void link_handle_out_of_seq_msg(struct tipc_link *link, - struct sk_buff *skb); -static void tipc_link_proto_rcv(struct tipc_link *link, - struct sk_buff *skb); -static void link_set_supervision_props(struct tipc_link *l_ptr, u32 tol); -static void link_state_event(struct tipc_link *l_ptr, u32 event); +static int link_is_up(struct tipc_link *l) +{ + return l->state & (LINK_ESTABLISHED | LINK_SYNCHING); +} + +static int tipc_link_proto_rcv(struct tipc_link *l, struct sk_buff *skb, + struct sk_buff_head *xmitq); +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_reset_statistics(struct tipc_link *l_ptr); static void link_print(struct tipc_link *l_ptr, const char *str); -static void tipc_link_sync_xmit(struct tipc_link *l); static void tipc_link_sync_rcv(struct tipc_node *n, struct sk_buff *buf); -static void tipc_link_input(struct tipc_link *l, struct sk_buff *skb); -static bool tipc_data_input(struct tipc_link *l, struct sk_buff *skb); -static bool tipc_link_failover_rcv(struct tipc_link *l, struct sk_buff **skb); -static void link_set_timer(struct tipc_link *link, unsigned long time); + /* - * Simple link routines + * Simple non-static link routines (i.e. referenced outside this file) */ -static unsigned int align(unsigned int i) +bool tipc_link_is_up(struct tipc_link *l) { - return (i + 3) & ~3u; + return link_is_up(l); } -static void tipc_link_release(struct kref *kref) +bool tipc_link_is_reset(struct tipc_link *l) { - kfree(container_of(kref, struct tipc_link, ref)); + return l->state & (LINK_RESET | LINK_FAILINGOVER | LINK_ESTABLISHING); } -static void tipc_link_get(struct tipc_link *l_ptr) +bool tipc_link_is_synching(struct tipc_link *l) { - kref_get(&l_ptr->ref); + return l->state == LINK_SYNCHING; } -static void tipc_link_put(struct tipc_link *l_ptr) +bool tipc_link_is_failingover(struct tipc_link *l) { - kref_put(&l_ptr->ref, tipc_link_release); + return l->state == LINK_FAILINGOVER; } -static struct tipc_link *tipc_parallel_link(struct tipc_link *l) +bool tipc_link_is_blocked(struct tipc_link *l) { - if (l->owner->active_links[0] != l) - return l->owner->active_links[0]; - return l->owner->active_links[1]; + return l->state & (LINK_RESETTING | LINK_PEER_RESET | LINK_FAILINGOVER); } -/* - * Simple non-static link routines (i.e. referenced outside this file) - */ -int tipc_link_is_up(struct tipc_link *l_ptr) +int tipc_link_is_active(struct tipc_link *l) { - if (!l_ptr) - return 0; - return link_working_working(l_ptr) || link_working_unknown(l_ptr); + struct tipc_node *n = l->owner; + + return (node_active_link(n, 0) == l) || (node_active_link(n, 1) == l); } -int tipc_link_is_active(struct tipc_link *l_ptr) +static u32 link_own_addr(struct tipc_link *l) { - return (l_ptr->owner->active_links[0] == l_ptr) || - (l_ptr->owner->active_links[1] == l_ptr); + return msg_prevnode(l->pmsg); } /** - * link_timeout - handle expiration of link timer - * @l_ptr: pointer to link + * tipc_link_create - create a new link + * @n: pointer to associated node + * @b: pointer to associated bearer + * @ownnode: identity of own node + * @peer: identity of peer node + * @maddr: media address to be used + * @inputq: queue to put messages ready for delivery + * @namedq: queue to put binding table update messages ready for delivery + * @link: return value, pointer to put the created link + * + * Returns true if link was created, otherwise false */ -static void link_timeout(unsigned long data) +bool tipc_link_create(struct tipc_node *n, struct tipc_bearer *b, u32 session, + u32 ownnode, u32 peer, struct tipc_media_addr *maddr, + struct sk_buff_head *inputq, struct sk_buff_head *namedq, + struct tipc_link **link) { - struct tipc_link *l_ptr = (struct tipc_link *)data; - struct sk_buff *skb; + struct tipc_link *l; + struct tipc_msg *hdr; + char *if_name; + + l = kzalloc(sizeof(*l), GFP_ATOMIC); + if (!l) + return false; + *link = l; + + /* Note: peer i/f name is completed by reset/activate message */ + if_name = strchr(b->name, ':') + 1; + sprintf(l->name, "%u.%u.%u:%s-%u.%u.%u:unknown", + tipc_zone(ownnode), tipc_cluster(ownnode), tipc_node(ownnode), + if_name, tipc_zone(peer), tipc_cluster(peer), tipc_node(peer)); + + l->addr = peer; + l->media_addr = maddr; + l->owner = n; + l->peer_session = WILDCARD_SESSION; + l->bearer_id = b->identity; + l->tolerance = b->tolerance; + l->net_plane = b->net_plane; + l->advertised_mtu = b->mtu; + l->mtu = b->mtu; + l->priority = b->priority; + tipc_link_set_queue_limits(l, b->window); + l->inputq = inputq; + l->namedq = namedq; + l->state = LINK_RESETTING; + l->pmsg = (struct tipc_msg *)&l->proto_msg; + hdr = l->pmsg; + tipc_msg_init(ownnode, hdr, LINK_PROTOCOL, RESET_MSG, INT_H_SIZE, peer); + msg_set_size(hdr, sizeof(l->proto_msg)); + msg_set_session(hdr, session); + msg_set_bearer_id(hdr, l->bearer_id); + strcpy((char *)msg_data(hdr), if_name); + __skb_queue_head_init(&l->transmq); + __skb_queue_head_init(&l->backlogq); + __skb_queue_head_init(&l->deferdq); + skb_queue_head_init(&l->wakeupq); + skb_queue_head_init(l->inputq); + return true; +} - tipc_node_lock(l_ptr->owner); +/* tipc_link_build_bcast_sync_msg() - synchronize broadcast link endpoints. + * + * Give a newly added peer node the sequence number where it should + * start receiving and acking broadcast packets. + */ +void tipc_link_build_bcast_sync_msg(struct tipc_link *l, + struct sk_buff_head *xmitq) +{ + struct sk_buff *skb; + struct sk_buff_head list; + u16 last_sent; - /* update counters used in statistical profiling of send traffic */ - l_ptr->stats.accu_queue_sz += skb_queue_len(&l_ptr->transmq); - l_ptr->stats.queue_sz_counts++; + skb = tipc_msg_create(BCAST_PROTOCOL, STATE_MSG, INT_H_SIZE, + 0, l->addr, link_own_addr(l), 0, 0, 0); + if (!skb) + return; + last_sent = tipc_bclink_get_last_sent(l->owner->net); + msg_set_last_bcast(buf_msg(skb), last_sent); + __skb_queue_head_init(&list); + __skb_queue_tail(&list, skb); + tipc_link_xmit(l, &list, xmitq); +} - skb = skb_peek(&l_ptr->transmq); - if (skb) { - struct tipc_msg *msg = buf_msg(skb); - u32 length = msg_size(msg); +/** + * tipc_link_fsm_evt - link finite state machine + * @l: pointer to link + * @evt: state machine event to be processed + */ +int tipc_link_fsm_evt(struct tipc_link *l, int evt) +{ + int rc = 0; - if ((msg_user(msg) == MSG_FRAGMENTER) && - (msg_type(msg) == FIRST_FRAGMENT)) { - length = msg_size(msg_get_wrapped(msg)); + switch (l->state) { + case LINK_RESETTING: + switch (evt) { + case LINK_PEER_RESET_EVT: + l->state = LINK_PEER_RESET; + break; + case LINK_RESET_EVT: + l->state = LINK_RESET; + break; + case LINK_FAILURE_EVT: + case LINK_FAILOVER_BEGIN_EVT: + case LINK_ESTABLISH_EVT: + case LINK_FAILOVER_END_EVT: + case LINK_SYNCH_BEGIN_EVT: + case LINK_SYNCH_END_EVT: + default: + goto illegal_evt; } - if (length) { - l_ptr->stats.msg_lengths_total += length; - l_ptr->stats.msg_length_counts++; - if (length <= 64) - l_ptr->stats.msg_length_profile[0]++; - else if (length <= 256) - l_ptr->stats.msg_length_profile[1]++; - else if (length <= 1024) - l_ptr->stats.msg_length_profile[2]++; - else if (length <= 4096) - l_ptr->stats.msg_length_profile[3]++; - else if (length <= 16384) - l_ptr->stats.msg_length_profile[4]++; - else if (length <= 32768) - l_ptr->stats.msg_length_profile[5]++; - else - l_ptr->stats.msg_length_profile[6]++; + break; + case LINK_RESET: + switch (evt) { + case LINK_PEER_RESET_EVT: + l->state = LINK_ESTABLISHING; + break; + case LINK_FAILOVER_BEGIN_EVT: + l->state = LINK_FAILINGOVER; + case LINK_FAILURE_EVT: + case LINK_RESET_EVT: + case LINK_ESTABLISH_EVT: + case LINK_FAILOVER_END_EVT: + break; + case LINK_SYNCH_BEGIN_EVT: + case LINK_SYNCH_END_EVT: + default: + goto illegal_evt; + } + break; + case LINK_PEER_RESET: + switch (evt) { + case LINK_RESET_EVT: + l->state = LINK_ESTABLISHING; + break; + case LINK_PEER_RESET_EVT: + case LINK_ESTABLISH_EVT: + case LINK_FAILURE_EVT: + break; + case LINK_SYNCH_BEGIN_EVT: + case LINK_SYNCH_END_EVT: + case LINK_FAILOVER_BEGIN_EVT: + case LINK_FAILOVER_END_EVT: + default: + goto illegal_evt; } + break; + case LINK_FAILINGOVER: + switch (evt) { + case LINK_FAILOVER_END_EVT: + l->state = LINK_RESET; + break; + case LINK_PEER_RESET_EVT: + case LINK_RESET_EVT: + case LINK_ESTABLISH_EVT: + case LINK_FAILURE_EVT: + break; + case LINK_FAILOVER_BEGIN_EVT: + case LINK_SYNCH_BEGIN_EVT: + case LINK_SYNCH_END_EVT: + default: + goto illegal_evt; + } + break; + case LINK_ESTABLISHING: + switch (evt) { + case LINK_ESTABLISH_EVT: + l->state = LINK_ESTABLISHED; + rc |= TIPC_LINK_UP_EVT; + break; + case LINK_FAILOVER_BEGIN_EVT: + l->state = LINK_FAILINGOVER; + break; + case LINK_PEER_RESET_EVT: + case LINK_RESET_EVT: + case LINK_FAILURE_EVT: + case LINK_SYNCH_BEGIN_EVT: + case LINK_FAILOVER_END_EVT: + break; + case LINK_SYNCH_END_EVT: + default: + goto illegal_evt; + } + break; + case LINK_ESTABLISHED: + switch (evt) { + case LINK_PEER_RESET_EVT: + l->state = LINK_PEER_RESET; + rc |= TIPC_LINK_DOWN_EVT; + break; + case LINK_FAILURE_EVT: + l->state = LINK_RESETTING; + rc |= TIPC_LINK_DOWN_EVT; + break; + case LINK_RESET_EVT: + l->state = LINK_RESET; + break; + case LINK_ESTABLISH_EVT: + case LINK_SYNCH_END_EVT: + break; + case LINK_SYNCH_BEGIN_EVT: + l->state = LINK_SYNCHING; + break; + case LINK_FAILOVER_BEGIN_EVT: + case LINK_FAILOVER_END_EVT: + default: + goto illegal_evt; + } + break; + case LINK_SYNCHING: + switch (evt) { + case LINK_PEER_RESET_EVT: + l->state = LINK_PEER_RESET; + rc |= TIPC_LINK_DOWN_EVT; + break; + case LINK_FAILURE_EVT: + l->state = LINK_RESETTING; + rc |= TIPC_LINK_DOWN_EVT; + break; + case LINK_RESET_EVT: + l->state = LINK_RESET; + break; + case LINK_ESTABLISH_EVT: + case LINK_SYNCH_BEGIN_EVT: + break; + case LINK_SYNCH_END_EVT: + l->state = LINK_ESTABLISHED; + break; + case LINK_FAILOVER_BEGIN_EVT: + case LINK_FAILOVER_END_EVT: + default: + goto illegal_evt; + } + break; + default: + pr_err("Unknown FSM state %x in %s\n", l->state, l->name); } - - /* do all other link processing performed on a periodic basis */ - if (l_ptr->silent_intv_cnt || tipc_bclink_acks_missing(l_ptr->owner)) - link_state_event(l_ptr, SILENCE_EVT); - l_ptr->silent_intv_cnt++; - if (skb_queue_len(&l_ptr->backlogq)) - tipc_link_push_packets(l_ptr); - link_set_timer(l_ptr, l_ptr->keepalive_intv); - tipc_node_unlock(l_ptr->owner); - tipc_link_put(l_ptr); -} - -static void link_set_timer(struct tipc_link *link, unsigned long time) -{ - if (!mod_timer(&link->timer, jiffies + time)) - tipc_link_get(link); + return rc; +illegal_evt: + pr_err("Illegal FSM event %x in state %x on link %s\n", + evt, l->state, l->name); + return rc; } -/** - * tipc_link_create - create a new link - * @n_ptr: pointer to associated node - * @b_ptr: pointer to associated bearer - * @media_addr: media address to use when sending messages over link - * - * Returns pointer to link. +/* link_profile_stats - update statistical profiling of traffic */ -struct tipc_link *tipc_link_create(struct tipc_node *n_ptr, - struct tipc_bearer *b_ptr, - const struct tipc_media_addr *media_addr) +static void link_profile_stats(struct tipc_link *l) { - struct tipc_net *tn = net_generic(n_ptr->net, tipc_net_id); - struct tipc_link *l_ptr; + struct sk_buff *skb; struct tipc_msg *msg; - char *if_name; - char addr_string[16]; - u32 peer = n_ptr->addr; + int length; - if (n_ptr->link_cnt >= MAX_BEARERS) { - tipc_addr_string_fill(addr_string, n_ptr->addr); - pr_err("Cannot establish %uth link to %s. Max %u allowed.\n", - n_ptr->link_cnt, addr_string, MAX_BEARERS); - return NULL; - } + /* Update counters used in statistical profiling of send traffic */ + l->stats.accu_queue_sz += skb_queue_len(&l->transmq); + l->stats.queue_sz_counts++; - if (n_ptr->links[b_ptr->identity]) { - tipc_addr_string_fill(addr_string, n_ptr->addr); - pr_err("Attempt to establish second link on <%s> to %s\n", - b_ptr->name, addr_string); - return NULL; - } + skb = skb_peek(&l->transmq); + if (!skb) + return; + msg = buf_msg(skb); + length = msg_size(msg); - l_ptr = kzalloc(sizeof(*l_ptr), GFP_ATOMIC); - if (!l_ptr) { - pr_warn("Link creation failed, no memory\n"); - return NULL; + if (msg_user(msg) == MSG_FRAGMENTER) { + if (msg_type(msg) != FIRST_FRAGMENT) + return; + length = msg_size(msg_get_wrapped(msg)); } - kref_init(&l_ptr->ref); - l_ptr->addr = peer; - if_name = strchr(b_ptr->name, ':') + 1; - sprintf(l_ptr->name, "%u.%u.%u:%s-%u.%u.%u:unknown", - tipc_zone(tn->own_addr), tipc_cluster(tn->own_addr), - tipc_node(tn->own_addr), - if_name, - tipc_zone(peer), tipc_cluster(peer), tipc_node(peer)); - /* note: peer i/f name is updated by reset/activate message */ - memcpy(&l_ptr->media_addr, media_addr, sizeof(*media_addr)); - l_ptr->owner = n_ptr; - l_ptr->peer_session = INVALID_SESSION; - l_ptr->bearer_id = b_ptr->identity; - link_set_supervision_props(l_ptr, b_ptr->tolerance); - l_ptr->state = RESET_UNKNOWN; - - l_ptr->pmsg = (struct tipc_msg *)&l_ptr->proto_msg; - msg = l_ptr->pmsg; - tipc_msg_init(tn->own_addr, msg, LINK_PROTOCOL, RESET_MSG, INT_H_SIZE, - l_ptr->addr); - msg_set_size(msg, sizeof(l_ptr->proto_msg)); - msg_set_session(msg, (tn->random & 0xffff)); - msg_set_bearer_id(msg, b_ptr->identity); - strcpy((char *)msg_data(msg), if_name); - l_ptr->net_plane = b_ptr->net_plane; - l_ptr->advertised_mtu = b_ptr->mtu; - l_ptr->mtu = l_ptr->advertised_mtu; - l_ptr->priority = b_ptr->priority; - tipc_link_set_queue_limits(l_ptr, b_ptr->window); - l_ptr->snd_nxt = 1; - __skb_queue_head_init(&l_ptr->transmq); - __skb_queue_head_init(&l_ptr->backlogq); - __skb_queue_head_init(&l_ptr->deferdq); - skb_queue_head_init(&l_ptr->wakeupq); - skb_queue_head_init(&l_ptr->inputq); - skb_queue_head_init(&l_ptr->namedq); - link_reset_statistics(l_ptr); - tipc_node_attach_link(n_ptr, l_ptr); - setup_timer(&l_ptr->timer, link_timeout, (unsigned long)l_ptr); - link_state_event(l_ptr, STARTING_EVT); - - return l_ptr; + l->stats.msg_lengths_total += length; + l->stats.msg_length_counts++; + if (length <= 64) + l->stats.msg_length_profile[0]++; + else if (length <= 256) + l->stats.msg_length_profile[1]++; + else if (length <= 1024) + l->stats.msg_length_profile[2]++; + else if (length <= 4096) + l->stats.msg_length_profile[3]++; + else if (length <= 16384) + l->stats.msg_length_profile[4]++; + else if (length <= 32768) + l->stats.msg_length_profile[5]++; + else + l->stats.msg_length_profile[6]++; } -/** - * tipc_link_delete - Delete a link - * @l: link to be deleted +/* tipc_link_timeout - perform periodic task as instructed from node timeout */ -void tipc_link_delete(struct tipc_link *l) +int tipc_link_timeout(struct tipc_link *l, struct sk_buff_head *xmitq) { - tipc_link_reset(l); - if (del_timer(&l->timer)) - tipc_link_put(l); - l->flags |= LINK_STOPPED; - /* Delete link now, or when timer is finished: */ - tipc_link_reset_fragments(l); - tipc_node_detach_link(l->owner, l); - tipc_link_put(l); -} + int rc = 0; + int mtyp = STATE_MSG; + bool xmit = false; + bool prb = false; + + link_profile_stats(l); + + switch (l->state) { + case LINK_ESTABLISHED: + case LINK_SYNCHING: + if (!l->silent_intv_cnt) { + if (tipc_bclink_acks_missing(l->owner)) + xmit = true; + } else if (l->silent_intv_cnt <= l->abort_limit) { + xmit = true; + prb = true; + } else { + rc |= tipc_link_fsm_evt(l, LINK_FAILURE_EVT); + } + l->silent_intv_cnt++; + break; + case LINK_RESET: + xmit = true; + mtyp = RESET_MSG; + break; + case LINK_ESTABLISHING: + xmit = true; + mtyp = ACTIVATE_MSG; + break; + case LINK_PEER_RESET: + case LINK_RESETTING: + case LINK_FAILINGOVER: + break; + default: + break; + } -void tipc_link_delete_list(struct net *net, unsigned int bearer_id) -{ - struct tipc_net *tn = net_generic(net, tipc_net_id); - struct tipc_link *link; - struct tipc_node *node; + if (xmit) + tipc_link_build_proto_msg(l, mtyp, prb, 0, 0, 0, xmitq); - rcu_read_lock(); - list_for_each_entry_rcu(node, &tn->node_list, list) { - tipc_node_lock(node); - link = node->links[bearer_id]; - if (link) - tipc_link_delete(link); - tipc_node_unlock(node); - } - rcu_read_unlock(); + return rc; } /** @@ -334,7 +490,7 @@ void tipc_link_delete_list(struct net *net, unsigned int bearer_id) * @link: congested link * @list: message that was attempted sent * Create pseudo msg to send back to user when congestion abates - * Only consumes message if there is an error + * Does not consume buffer list */ static int link_schedule_user(struct tipc_link *link, struct sk_buff_head *list) { @@ -347,8 +503,7 @@ static int link_schedule_user(struct tipc_link *link, struct sk_buff_head *list) /* This really cannot happen... */ if (unlikely(imp > TIPC_CRITICAL_IMPORTANCE)) { pr_warn("%s<%s>, send queue full", link_rst_msg, link->name); - tipc_link_reset(link); - goto err; + return -ENOBUFS; } /* Non-blocking sender: */ if (TIPC_SKB_CB(skb_peek(list))->wakeup_pending) @@ -358,15 +513,12 @@ static int link_schedule_user(struct tipc_link *link, struct sk_buff_head *list) skb = tipc_msg_create(SOCK_WAKEUP, 0, INT_H_SIZE, 0, addr, addr, oport, 0, 0); if (!skb) - goto err; + return -ENOBUFS; TIPC_SKB_CB(skb)->chain_sz = skb_queue_len(list); TIPC_SKB_CB(skb)->chain_imp = imp; skb_queue_tail(&link->wakeupq, skb); link->stats.link_congs++; return -ELINKCONG; -err: - __skb_queue_purge(list); - return -ENOBUFS; } /** @@ -388,9 +540,7 @@ void link_prepare_wakeup(struct tipc_link *l) if ((pnd[imp] + l->backlog[imp].len) >= lim) break; skb_unlink(skb, &l->wakeupq); - skb_queue_tail(&l->inputq, skb); - l->owner->inputq = &l->inputq; - l->owner->action_flags |= TIPC_MSG_EVT; + skb_queue_tail(l->inputq, skb); } } @@ -426,208 +576,36 @@ void tipc_link_purge_queues(struct tipc_link *l_ptr) tipc_link_reset_fragments(l_ptr); } -void tipc_link_reset(struct tipc_link *l_ptr) +void tipc_link_reset(struct tipc_link *l) { - u32 prev_state = l_ptr->state; - int was_active_link = tipc_link_is_active(l_ptr); - struct tipc_node *owner = l_ptr->owner; - struct tipc_link *pl = tipc_parallel_link(l_ptr); - - msg_set_session(l_ptr->pmsg, ((msg_session(l_ptr->pmsg) + 1) & 0xffff)); + tipc_link_fsm_evt(l, LINK_RESET_EVT); /* Link is down, accept any session */ - l_ptr->peer_session = INVALID_SESSION; - - /* Prepare for renewed mtu size negotiation */ - l_ptr->mtu = l_ptr->advertised_mtu; - - l_ptr->state = RESET_UNKNOWN; + l->peer_session = WILDCARD_SESSION; - if ((prev_state == RESET_UNKNOWN) || (prev_state == RESET_RESET)) - return; - - tipc_node_link_down(l_ptr->owner, l_ptr); - tipc_bearer_remove_dest(owner->net, l_ptr->bearer_id, l_ptr->addr); + /* If peer is up, it only accepts an incremented session number */ + msg_set_session(l->pmsg, msg_session(l->pmsg) + 1); - if (was_active_link && tipc_node_is_up(l_ptr->owner) && (pl != l_ptr)) { - l_ptr->flags |= LINK_FAILINGOVER; - l_ptr->failover_checkpt = l_ptr->rcv_nxt; - pl->failover_pkts = FIRST_FAILOVER; - pl->failover_checkpt = l_ptr->rcv_nxt; - pl->failover_skb = l_ptr->reasm_buf; - } else { - kfree_skb(l_ptr->reasm_buf); - } - /* Clean up all queues, except inputq: */ - __skb_queue_purge(&l_ptr->transmq); - __skb_queue_purge(&l_ptr->deferdq); - if (!owner->inputq) - owner->inputq = &l_ptr->inputq; - skb_queue_splice_init(&l_ptr->wakeupq, owner->inputq); - if (!skb_queue_empty(owner->inputq)) - owner->action_flags |= TIPC_MSG_EVT; - tipc_link_purge_backlog(l_ptr); - l_ptr->reasm_buf = NULL; - l_ptr->rcv_unacked = 0; - l_ptr->snd_nxt = 1; - l_ptr->silent_intv_cnt = 0; - l_ptr->stale_count = 0; - link_reset_statistics(l_ptr); -} - -static void link_activate(struct tipc_link *link) -{ - struct tipc_node *node = link->owner; - - link->rcv_nxt = 1; - link->stats.recv_info = 1; - link->silent_intv_cnt = 0; - tipc_node_link_up(node, link); - tipc_bearer_add_dest(node->net, link->bearer_id, link->addr); -} - -/** - * link_state_event - link finite state machine - * @l_ptr: pointer to link - * @event: state machine event to process - */ -static void link_state_event(struct tipc_link *l_ptr, unsigned int event) -{ - struct tipc_link *other; - unsigned long timer_intv = l_ptr->keepalive_intv; - - if (l_ptr->flags & LINK_STOPPED) - return; - - if (!(l_ptr->flags & LINK_STARTED) && (event != STARTING_EVT)) - return; /* Not yet. */ - - if (l_ptr->flags & LINK_FAILINGOVER) - return; - - switch (l_ptr->state) { - case WORKING_WORKING: - switch (event) { - case TRAFFIC_MSG_EVT: - case ACTIVATE_MSG: - l_ptr->silent_intv_cnt = 0; - break; - case SILENCE_EVT: - if (!l_ptr->silent_intv_cnt) { - if (tipc_bclink_acks_missing(l_ptr->owner)) - tipc_link_proto_xmit(l_ptr, STATE_MSG, - 0, 0, 0, 0); - break; - } - l_ptr->state = WORKING_UNKNOWN; - tipc_link_proto_xmit(l_ptr, STATE_MSG, 1, 0, 0, 0); - break; - case RESET_MSG: - pr_debug("%s<%s>, requested by peer\n", - link_rst_msg, l_ptr->name); - tipc_link_reset(l_ptr); - l_ptr->state = RESET_RESET; - tipc_link_proto_xmit(l_ptr, ACTIVATE_MSG, - 0, 0, 0, 0); - break; - default: - pr_debug("%s%u in WW state\n", link_unk_evt, event); - } - break; - case WORKING_UNKNOWN: - switch (event) { - case TRAFFIC_MSG_EVT: - case ACTIVATE_MSG: - l_ptr->state = WORKING_WORKING; - l_ptr->silent_intv_cnt = 0; - break; - case RESET_MSG: - pr_debug("%s<%s>, requested by peer while probing\n", - link_rst_msg, l_ptr->name); - tipc_link_reset(l_ptr); - l_ptr->state = RESET_RESET; - tipc_link_proto_xmit(l_ptr, ACTIVATE_MSG, - 0, 0, 0, 0); - break; - case SILENCE_EVT: - if (!l_ptr->silent_intv_cnt) { - l_ptr->state = WORKING_WORKING; - if (tipc_bclink_acks_missing(l_ptr->owner)) - tipc_link_proto_xmit(l_ptr, STATE_MSG, - 0, 0, 0, 0); - } else if (l_ptr->silent_intv_cnt < - l_ptr->abort_limit) { - tipc_link_proto_xmit(l_ptr, STATE_MSG, - 1, 0, 0, 0); - } else { /* Link has failed */ - pr_debug("%s<%s>, peer not responding\n", - link_rst_msg, l_ptr->name); - tipc_link_reset(l_ptr); - l_ptr->state = RESET_UNKNOWN; - tipc_link_proto_xmit(l_ptr, RESET_MSG, - 0, 0, 0, 0); - } - break; - default: - pr_err("%s%u in WU state\n", link_unk_evt, event); - } - break; - case RESET_UNKNOWN: - switch (event) { - case TRAFFIC_MSG_EVT: - break; - case ACTIVATE_MSG: - other = l_ptr->owner->active_links[0]; - if (other && link_working_unknown(other)) - break; - l_ptr->state = WORKING_WORKING; - link_activate(l_ptr); - tipc_link_proto_xmit(l_ptr, STATE_MSG, 1, 0, 0, 0); - if (l_ptr->owner->working_links == 1) - tipc_link_sync_xmit(l_ptr); - break; - case RESET_MSG: - l_ptr->state = RESET_RESET; - tipc_link_proto_xmit(l_ptr, ACTIVATE_MSG, - 1, 0, 0, 0); - break; - case STARTING_EVT: - l_ptr->flags |= LINK_STARTED; - link_set_timer(l_ptr, timer_intv); - break; - case SILENCE_EVT: - tipc_link_proto_xmit(l_ptr, RESET_MSG, 0, 0, 0, 0); - break; - default: - pr_err("%s%u in RU state\n", link_unk_evt, event); - } - break; - case RESET_RESET: - switch (event) { - case TRAFFIC_MSG_EVT: - case ACTIVATE_MSG: - other = l_ptr->owner->active_links[0]; - if (other && link_working_unknown(other)) - break; - l_ptr->state = WORKING_WORKING; - link_activate(l_ptr); - tipc_link_proto_xmit(l_ptr, STATE_MSG, 1, 0, 0, 0); - if (l_ptr->owner->working_links == 1) - tipc_link_sync_xmit(l_ptr); - break; - case RESET_MSG: - break; - case SILENCE_EVT: - tipc_link_proto_xmit(l_ptr, ACTIVATE_MSG, - 0, 0, 0, 0); - break; - default: - pr_err("%s%u in RR state\n", link_unk_evt, event); - } - break; - default: - pr_err("Unknown link state %u/%u\n", l_ptr->state, event); - } + /* Prepare for renewed mtu size negotiation */ + l->mtu = l->advertised_mtu; + + /* Clean up all queues: */ + __skb_queue_purge(&l->transmq); + __skb_queue_purge(&l->deferdq); + skb_queue_splice_init(&l->wakeupq, l->inputq); + + tipc_link_purge_backlog(l); + kfree_skb(l->reasm_buf); + kfree_skb(l->failover_reasm_skb); + l->reasm_buf = NULL; + l->failover_reasm_skb = NULL; + l->rcv_unacked = 0; + l->snd_nxt = 1; + l->rcv_nxt = 1; + l->silent_intv_cnt = 0; + l->stats.recv_info = 0; + l->stale_count = 0; + link_reset_statistics(l); } /** @@ -635,8 +613,7 @@ static void link_state_event(struct tipc_link *l_ptr, unsigned int event) * @link: link to use * @list: chain of buffers containing message * - * Consumes the buffer chain, except when returning -ELINKCONG, - * since the caller then may want to make more send attempts. + * Consumes the buffer chain, except when returning an error code, * Returns 0 if success, or errno: -ELINKCONG, -EMSGSIZE or -ENOBUFS * Messages at TIPC_SYSTEM_IMPORTANCE are always accepted */ @@ -650,7 +627,7 @@ int __tipc_link_xmit(struct net *net, struct tipc_link *link, u16 ack = mod(link->rcv_nxt - 1); u16 seqno = link->snd_nxt; u16 bc_last_in = link->owner->bclink.last_in; - struct tipc_media_addr *addr = &link->media_addr; + struct tipc_media_addr *addr = link->media_addr; struct sk_buff_head *transmq = &link->transmq; struct sk_buff_head *backlogq = &link->backlogq; struct sk_buff *skb, *bskb; @@ -660,10 +637,9 @@ int __tipc_link_xmit(struct net *net, struct tipc_link *link, if (unlikely(link->backlog[i].len >= link->backlog[i].limit)) return link_schedule_user(link, list); } - if (unlikely(msg_size(msg) > mtu)) { - __skb_queue_purge(list); + if (unlikely(msg_size(msg) > mtu)) return -EMSGSIZE; - } + /* Prepare each packet for sending, and add to relevant queue: */ while (skb_queue_len(list)) { skb = skb_peek(list); @@ -700,101 +676,76 @@ int __tipc_link_xmit(struct net *net, struct tipc_link *link, return 0; } -static void skb2list(struct sk_buff *skb, struct sk_buff_head *list) -{ - skb_queue_head_init(list); - __skb_queue_tail(list, skb); -} - -static int __tipc_link_xmit_skb(struct tipc_link *link, struct sk_buff *skb) -{ - struct sk_buff_head head; - - skb2list(skb, &head); - return __tipc_link_xmit(link->owner->net, link, &head); -} - -/* tipc_link_xmit_skb(): send single buffer to destination - * Buffers sent via this functon are generally TIPC_SYSTEM_IMPORTANCE - * messages, which will not be rejected - * The only exception is datagram messages rerouted after secondary - * lookup, which are rare and safe to dispose of anyway. - * TODO: Return real return value, and let callers use - * tipc_wait_for_sendpkt() where applicable - */ -int tipc_link_xmit_skb(struct net *net, struct sk_buff *skb, u32 dnode, - u32 selector) -{ - struct sk_buff_head head; - int rc; - - skb2list(skb, &head); - rc = tipc_link_xmit(net, &head, dnode, selector); - if (rc == -ELINKCONG) - kfree_skb(skb); - return 0; -} - /** - * tipc_link_xmit() is the general link level function for message sending - * @net: the applicable net namespace + * tipc_link_xmit(): enqueue buffer list according to queue situation + * @link: link to use * @list: chain of buffers containing message - * @dsz: amount of user data to be sent - * @dnode: address of destination node - * @selector: a number used for deterministic link selection - * Consumes the buffer chain, except when returning -ELINKCONG - * Returns 0 if success, otherwise errno: -ELINKCONG,-EHOSTUNREACH,-EMSGSIZE + * @xmitq: returned list of packets to be sent by caller + * + * Consumes the buffer chain, except when returning -ELINKCONG, + * since the caller then may want to make more send attempts. + * Returns 0 if success, or errno: -ELINKCONG, -EMSGSIZE or -ENOBUFS + * Messages at TIPC_SYSTEM_IMPORTANCE are always accepted */ -int tipc_link_xmit(struct net *net, struct sk_buff_head *list, u32 dnode, - u32 selector) +int tipc_link_xmit(struct tipc_link *l, struct sk_buff_head *list, + struct sk_buff_head *xmitq) { - struct tipc_link *link = NULL; - struct tipc_node *node; - int rc = -EHOSTUNREACH; + struct tipc_msg *hdr = buf_msg(skb_peek(list)); + unsigned int maxwin = l->window; + unsigned int i, imp = msg_importance(hdr); + unsigned int mtu = l->mtu; + u16 ack = l->rcv_nxt - 1; + u16 seqno = l->snd_nxt; + u16 bc_last_in = l->owner->bclink.last_in; + struct sk_buff_head *transmq = &l->transmq; + struct sk_buff_head *backlogq = &l->backlogq; + struct sk_buff *skb, *_skb, *bskb; - node = tipc_node_find(net, dnode); - if (node) { - tipc_node_lock(node); - link = node->active_links[selector & 1]; - if (link) - rc = __tipc_link_xmit(net, link, list); - tipc_node_unlock(node); - tipc_node_put(node); - } - if (link) - return rc; - - if (likely(in_own_node(net, dnode))) { - tipc_sk_rcv(net, list); - return 0; + /* 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 (unlikely(msg_size(hdr) > mtu)) + return -EMSGSIZE; - __skb_queue_purge(list); - return rc; -} - -/* - * tipc_link_sync_xmit - synchronize broadcast link endpoints. - * - * Give a newly added peer node the sequence number where it should - * start receiving and acking broadcast packets. - * - * Called with node locked - */ -static void tipc_link_sync_xmit(struct tipc_link *link) -{ - struct sk_buff *skb; - struct tipc_msg *msg; - - skb = tipc_buf_acquire(INT_H_SIZE); - if (!skb) - return; + /* Prepare each packet for sending, and add to relevant queue: */ + while (skb_queue_len(list)) { + skb = skb_peek(list); + hdr = buf_msg(skb); + msg_set_seqno(hdr, seqno); + msg_set_ack(hdr, ack); + msg_set_bcast_ack(hdr, bc_last_in); - msg = buf_msg(skb); - tipc_msg_init(link_own_addr(link), msg, BCAST_PROTOCOL, STATE_MSG, - INT_H_SIZE, link->addr); - msg_set_last_bcast(msg, link->owner->bclink.acked); - __tipc_link_xmit_skb(link, skb); + if (likely(skb_queue_len(transmq) < maxwin)) { + _skb = skb_clone(skb, GFP_ATOMIC); + if (!_skb) + return -ENOBUFS; + __skb_dequeue(list); + __skb_queue_tail(transmq, skb); + __skb_queue_tail(xmitq, _skb); + l->rcv_unacked = 0; + seqno++; + continue; + } + if (tipc_msg_bundle(skb_peek_tail(backlogq), hdr, mtu)) { + kfree_skb(__skb_dequeue(list)); + l->stats.sent_bundled++; + continue; + } + if (tipc_msg_make_bundle(&bskb, hdr, mtu, l->addr)) { + kfree_skb(__skb_dequeue(list)); + __skb_queue_tail(backlogq, bskb); + l->backlog[msg_importance(buf_msg(bskb))].len++; + l->stats.sent_bundled++; + l->stats.sent_bundles++; + continue; + } + l->backlog[imp].len += skb_queue_len(list); + skb_queue_splice_tail_init(list, backlogq); + } + l->snd_nxt = seqno; + return 0; } /* @@ -842,29 +793,37 @@ void tipc_link_push_packets(struct tipc_link *link) link->rcv_unacked = 0; __skb_queue_tail(&link->transmq, skb); tipc_bearer_send(link->owner->net, link->bearer_id, - skb, &link->media_addr); + skb, link->media_addr); } link->snd_nxt = seqno; } -void tipc_link_reset_all(struct tipc_node *node) +void tipc_link_advance_backlog(struct tipc_link *l, struct sk_buff_head *xmitq) { - char addr_string[16]; - u32 i; - - tipc_node_lock(node); + struct sk_buff *skb, *_skb; + struct tipc_msg *hdr; + u16 seqno = l->snd_nxt; + u16 ack = l->rcv_nxt - 1; - pr_warn("Resetting all links to %s\n", - tipc_addr_string_fill(addr_string, node->addr)); - - for (i = 0; i < MAX_BEARERS; i++) { - if (node->links[i]) { - link_print(node->links[i], "Resetting link\n"); - tipc_link_reset(node->links[i]); - } + while (skb_queue_len(&l->transmq) < l->window) { + skb = skb_peek(&l->backlogq); + if (!skb) + break; + _skb = skb_clone(skb, GFP_ATOMIC); + if (!_skb) + break; + __skb_dequeue(&l->backlogq); + hdr = buf_msg(skb); + l->backlog[msg_importance(hdr)].len--; + __skb_queue_tail(&l->transmq, skb); + __skb_queue_tail(xmitq, _skb); + msg_set_ack(hdr, ack); + msg_set_seqno(hdr, seqno); + msg_set_bcast_ack(hdr, l->owner->bclink.last_in); + l->rcv_unacked = 0; + seqno++; } - - tipc_node_unlock(node); + l->snd_nxt = seqno; } static void link_retransmit_failure(struct tipc_link *l_ptr, @@ -877,9 +836,12 @@ static void link_retransmit_failure(struct tipc_link *l_ptr, if (l_ptr->addr) { /* Handle failure on standard link */ - link_print(l_ptr, "Resetting link\n"); - tipc_link_reset(l_ptr); - + link_print(l_ptr, "Resetting link "); + pr_info("Failed msg: usr %u, typ %u, len %u, err %u\n", + msg_user(msg), msg_type(msg), msg_size(msg), + msg_errcode(msg)); + pr_info("sqno %u, prev: %x, src: %x\n", + msg_seqno(msg), msg_prevnode(msg), msg_orignode(msg)); } else { /* Handle failure on broadcast link */ struct tipc_node *n_ptr; @@ -934,191 +896,45 @@ void tipc_link_retransmit(struct tipc_link *l_ptr, struct sk_buff *skb, msg_set_ack(msg, mod(l_ptr->rcv_nxt - 1)); msg_set_bcast_ack(msg, l_ptr->owner->bclink.last_in); tipc_bearer_send(l_ptr->owner->net, l_ptr->bearer_id, skb, - &l_ptr->media_addr); + l_ptr->media_addr); retransmits--; l_ptr->stats.retransmitted++; } } -/* link_synch(): check if all packets arrived before the synch - * point have been consumed - * Returns true if the parallel links are synched, otherwise false - */ -static bool link_synch(struct tipc_link *l) +static int tipc_link_retransm(struct tipc_link *l, int retransm, + struct sk_buff_head *xmitq) { - unsigned int post_synch; - struct tipc_link *pl; + struct sk_buff *_skb, *skb = skb_peek(&l->transmq); + struct tipc_msg *hdr; - pl = tipc_parallel_link(l); - if (pl == l) - goto synched; - - /* Was last pre-synch packet added to input queue ? */ - if (less_eq(pl->rcv_nxt, l->synch_point)) - return false; - - /* Is it still in the input queue ? */ - post_synch = mod(pl->rcv_nxt - l->synch_point) - 1; - if (skb_queue_len(&pl->inputq) > post_synch) - return false; -synched: - l->flags &= ~LINK_SYNCHING; - return true; -} - -static void link_retrieve_defq(struct tipc_link *link, - struct sk_buff_head *list) -{ - u16 seq_no; - - if (skb_queue_empty(&link->deferdq)) - return; - - seq_no = buf_seqno(skb_peek(&link->deferdq)); - if (seq_no == link->rcv_nxt) - skb_queue_splice_tail_init(&link->deferdq, list); -} - -/** - * tipc_rcv - process TIPC packets/messages arriving from off-node - * @net: the applicable net namespace - * @skb: TIPC packet - * @b_ptr: pointer to bearer message arrived on - * - * Invoked with no locks held. Bearer pointer must point to a valid bearer - * structure (i.e. cannot be NULL), but bearer can be inactive. - */ -void tipc_rcv(struct net *net, struct sk_buff *skb, struct tipc_bearer *b_ptr) -{ - struct tipc_net *tn = net_generic(net, tipc_net_id); - struct sk_buff_head head; - struct tipc_node *n_ptr; - struct tipc_link *l_ptr; - struct sk_buff *skb1, *tmp; - struct tipc_msg *msg; - u16 seq_no; - u16 ackd; - u32 released; - - skb2list(skb, &head); - - while ((skb = __skb_dequeue(&head))) { - /* Ensure message is well-formed */ - if (unlikely(!tipc_msg_validate(skb))) - goto discard; - - /* Handle arrival of a non-unicast link message */ - msg = buf_msg(skb); - if (unlikely(msg_non_seq(msg))) { - if (msg_user(msg) == LINK_CONFIG) - tipc_disc_rcv(net, skb, b_ptr); - else - tipc_bclink_rcv(net, skb); - continue; - } - - /* Discard unicast link messages destined for another node */ - if (unlikely(!msg_short(msg) && - (msg_destnode(msg) != tn->own_addr))) - goto discard; - - /* Locate neighboring node that sent message */ - n_ptr = tipc_node_find(net, msg_prevnode(msg)); - if (unlikely(!n_ptr)) - goto discard; - - tipc_node_lock(n_ptr); - /* Locate unicast link endpoint that should handle message */ - l_ptr = n_ptr->links[b_ptr->identity]; - if (unlikely(!l_ptr)) - goto unlock; - - /* Verify that communication with node is currently allowed */ - if ((n_ptr->action_flags & TIPC_WAIT_PEER_LINKS_DOWN) && - msg_user(msg) == LINK_PROTOCOL && - (msg_type(msg) == RESET_MSG || - msg_type(msg) == ACTIVATE_MSG) && - !msg_redundant_link(msg)) - n_ptr->action_flags &= ~TIPC_WAIT_PEER_LINKS_DOWN; - - if (tipc_node_blocked(n_ptr)) - goto unlock; - - /* Validate message sequence number info */ - seq_no = msg_seqno(msg); - ackd = msg_ack(msg); - - /* Release acked messages */ - if (unlikely(n_ptr->bclink.acked != msg_bcast_ack(msg))) - tipc_bclink_acknowledge(n_ptr, msg_bcast_ack(msg)); - - released = 0; - skb_queue_walk_safe(&l_ptr->transmq, skb1, tmp) { - if (more(buf_seqno(skb1), ackd)) - break; - __skb_unlink(skb1, &l_ptr->transmq); - kfree_skb(skb1); - released = 1; - } - - /* Try sending any messages link endpoint has pending */ - if (unlikely(skb_queue_len(&l_ptr->backlogq))) - tipc_link_push_packets(l_ptr); - - if (released && !skb_queue_empty(&l_ptr->wakeupq)) - link_prepare_wakeup(l_ptr); - - /* Process the incoming packet */ - if (unlikely(!link_working_working(l_ptr))) { - if (msg_user(msg) == LINK_PROTOCOL) { - tipc_link_proto_rcv(l_ptr, skb); - link_retrieve_defq(l_ptr, &head); - skb = NULL; - goto unlock; - } - - /* Traffic message. Conditionally activate link */ - link_state_event(l_ptr, TRAFFIC_MSG_EVT); - - if (link_working_working(l_ptr)) { - /* Re-insert buffer in front of queue */ - __skb_queue_head(&head, skb); - skb = NULL; - goto unlock; - } - goto unlock; - } - - /* Link is now in state WORKING_WORKING */ - if (unlikely(seq_no != l_ptr->rcv_nxt)) { - link_handle_out_of_seq_msg(l_ptr, skb); - link_retrieve_defq(l_ptr, &head); - skb = NULL; - goto unlock; - } - l_ptr->silent_intv_cnt = 0; + if (!skb) + return 0; - /* Synchronize with parallel link if applicable */ - if (unlikely((l_ptr->flags & LINK_SYNCHING) && !msg_dup(msg))) { - if (!link_synch(l_ptr)) - goto unlock; - } - l_ptr->rcv_nxt++; - if (unlikely(!skb_queue_empty(&l_ptr->deferdq))) - link_retrieve_defq(l_ptr, &head); - if (unlikely(++l_ptr->rcv_unacked >= TIPC_MIN_LINK_WIN)) { - l_ptr->stats.sent_acks++; - tipc_link_proto_xmit(l_ptr, STATE_MSG, 0, 0, 0, 0); - } - tipc_link_input(l_ptr, skb); - skb = NULL; -unlock: - tipc_node_unlock(n_ptr); - tipc_node_put(n_ptr); -discard: - if (unlikely(skb)) - kfree_skb(skb); + /* Detect repeated retransmit failures on same packet */ + if (likely(l->last_retransm != buf_seqno(skb))) { + l->last_retransm = buf_seqno(skb); + l->stale_count = 1; + } else if (++l->stale_count > 100) { + link_retransmit_failure(l, skb); + return tipc_link_fsm_evt(l, LINK_FAILURE_EVT); + } + skb_queue_walk(&l->transmq, skb) { + if (!retransm) + return 0; + hdr = buf_msg(skb); + _skb = __pskb_copy(skb, MIN_H_SIZE, GFP_ATOMIC); + if (!_skb) + return 0; + hdr = buf_msg(_skb); + msg_set_ack(hdr, l->rcv_nxt - 1); + msg_set_bcast_ack(hdr, l->owner->bclink.last_in); + _skb->priority = TC_PRIO_CONTROL; + __skb_queue_tail(xmitq, _skb); + retransm--; + l->stats.retransmitted++; } + return 0; } /* tipc_data_input - deliver data and name distr msgs to upper layer @@ -1126,29 +942,22 @@ discard: * Consumes buffer if message is of right type * Node lock must be held */ -static bool tipc_data_input(struct tipc_link *link, struct sk_buff *skb) +static bool tipc_data_input(struct tipc_link *link, struct sk_buff *skb, + struct sk_buff_head *inputq) { struct tipc_node *node = link->owner; - struct tipc_msg *msg = buf_msg(skb); - u32 dport = msg_destport(msg); - switch (msg_user(msg)) { + switch (msg_user(buf_msg(skb))) { case TIPC_LOW_IMPORTANCE: case TIPC_MEDIUM_IMPORTANCE: case TIPC_HIGH_IMPORTANCE: case TIPC_CRITICAL_IMPORTANCE: case CONN_MANAGER: - if (tipc_skb_queue_tail(&link->inputq, skb, dport)) { - node->inputq = &link->inputq; - node->action_flags |= TIPC_MSG_EVT; - } + __skb_queue_tail(inputq, skb); return true; case NAME_DISTRIBUTOR: node->bclink.recv_permitted = true; - node->namedq = &link->namedq; - skb_queue_tail(&link->namedq, skb); - if (skb_queue_len(&link->namedq) == 1) - node->action_flags |= TIPC_NAMED_MSG_EVT; + skb_queue_tail(link->namedq, skb); return true; case MSG_BUNDLER: case TUNNEL_PROTOCOL: @@ -1165,54 +974,160 @@ static bool tipc_data_input(struct tipc_link *link, struct sk_buff *skb) /* tipc_link_input - process packet that has passed link protocol check * * Consumes buffer - * Node lock must be held */ -static void tipc_link_input(struct tipc_link *link, struct sk_buff *skb) +static int tipc_link_input(struct tipc_link *l, struct sk_buff *skb, + struct sk_buff_head *inputq) { - struct tipc_node *node = link->owner; - struct tipc_msg *msg = buf_msg(skb); + struct tipc_node *node = l->owner; + struct tipc_msg *hdr = buf_msg(skb); + struct sk_buff **reasm_skb = &l->reasm_buf; struct sk_buff *iskb; + int usr = msg_user(hdr); + int rc = 0; int pos = 0; + int ipos = 0; - if (likely(tipc_data_input(link, skb))) - return; + if (unlikely(usr == TUNNEL_PROTOCOL)) { + if (msg_type(hdr) == SYNCH_MSG) { + __skb_queue_purge(&l->deferdq); + goto drop; + } + if (!tipc_msg_extract(skb, &iskb, &ipos)) + return rc; + kfree_skb(skb); + skb = iskb; + hdr = buf_msg(skb); + if (less(msg_seqno(hdr), l->drop_point)) + goto drop; + if (tipc_data_input(l, skb, inputq)) + return rc; + usr = msg_user(hdr); + reasm_skb = &l->failover_reasm_skb; + } - switch (msg_user(msg)) { - case TUNNEL_PROTOCOL: - if (msg_dup(msg)) { - link->flags |= LINK_SYNCHING; - link->synch_point = msg_seqno(msg_get_wrapped(msg)); - kfree_skb(skb); - break; + if (usr == MSG_BUNDLER) { + l->stats.recv_bundles++; + l->stats.recv_bundled += msg_msgcnt(hdr); + while (tipc_msg_extract(skb, &iskb, &pos)) + tipc_data_input(l, iskb, inputq); + return 0; + } else if (usr == MSG_FRAGMENTER) { + l->stats.recv_fragments++; + if (tipc_buf_append(reasm_skb, &skb)) { + l->stats.recv_fragmented++; + tipc_data_input(l, skb, inputq); + } else if (!*reasm_skb) { + return tipc_link_fsm_evt(l, LINK_FAILURE_EVT); } - if (!tipc_link_failover_rcv(link, &skb)) - break; - if (msg_user(buf_msg(skb)) != MSG_BUNDLER) { - tipc_data_input(link, skb); + return 0; + } else if (usr == BCAST_PROTOCOL) { + tipc_link_sync_rcv(node, skb); + return 0; + } +drop: + kfree_skb(skb); + return 0; +} + +static bool tipc_link_release_pkts(struct tipc_link *l, u16 acked) +{ + bool released = false; + struct sk_buff *skb, *tmp; + + skb_queue_walk_safe(&l->transmq, skb, tmp) { + if (more(buf_seqno(skb), acked)) break; + __skb_unlink(skb, &l->transmq); + kfree_skb(skb); + released = true; + } + return released; +} + +/* tipc_link_rcv - process TIPC packets/messages arriving from off-node + * @link: the link that should handle the message + * @skb: TIPC packet + * @xmitq: queue to place packets to be sent after this call + */ +int tipc_link_rcv(struct tipc_link *l, struct sk_buff *skb, + struct sk_buff_head *xmitq) +{ + struct sk_buff_head *arrvq = &l->deferdq; + struct sk_buff_head tmpq; + struct tipc_msg *hdr; + u16 seqno, rcv_nxt; + int rc = 0; + + __skb_queue_head_init(&tmpq); + + if (unlikely(!__tipc_skb_queue_sorted(arrvq, skb))) { + if (!(skb_queue_len(arrvq) % TIPC_NACK_INTV)) + tipc_link_build_proto_msg(l, STATE_MSG, 0, + 0, 0, 0, xmitq); + return rc; + } + + while ((skb = skb_peek(arrvq))) { + hdr = buf_msg(skb); + + /* Verify and update link state */ + if (unlikely(msg_user(hdr) == LINK_PROTOCOL)) { + __skb_dequeue(arrvq); + rc = tipc_link_proto_rcv(l, skb, xmitq); + continue; } - case MSG_BUNDLER: - link->stats.recv_bundles++; - link->stats.recv_bundled += msg_msgcnt(msg); - while (tipc_msg_extract(skb, &iskb, &pos)) - tipc_data_input(link, iskb); - break; - case MSG_FRAGMENTER: - link->stats.recv_fragments++; - if (tipc_buf_append(&link->reasm_buf, &skb)) { - link->stats.recv_fragmented++; - tipc_data_input(link, skb); - } else if (!link->reasm_buf) { - tipc_link_reset(link); + if (unlikely(!link_is_up(l))) { + rc = tipc_link_fsm_evt(l, LINK_ESTABLISH_EVT); + if (!link_is_up(l)) { + kfree_skb(__skb_dequeue(arrvq)); + goto exit; + } } - break; - case BCAST_PROTOCOL: - tipc_link_sync_rcv(node, skb); - break; - default: - break; - }; + + l->silent_intv_cnt = 0; + + /* Forward queues and wake up waiting users */ + if (likely(tipc_link_release_pkts(l, msg_ack(hdr)))) { + tipc_link_advance_backlog(l, xmitq); + if (unlikely(!skb_queue_empty(&l->wakeupq))) + link_prepare_wakeup(l); + } + + /* Defer reception if there is a gap in the sequence */ + seqno = msg_seqno(hdr); + rcv_nxt = l->rcv_nxt; + if (unlikely(less(rcv_nxt, seqno))) { + l->stats.deferred_recv++; + goto exit; + } + + __skb_dequeue(arrvq); + + /* Drop if packet already received */ + if (unlikely(more(rcv_nxt, seqno))) { + l->stats.duplicates++; + kfree_skb(skb); + goto exit; + } + + /* Packet can be delivered */ + l->rcv_nxt++; + l->stats.recv_info++; + if (unlikely(!tipc_data_input(l, skb, &tmpq))) + rc = tipc_link_input(l, skb, &tmpq); + + /* Ack at regular intervals */ + if (unlikely(++l->rcv_unacked >= TIPC_MIN_LINK_WIN)) { + l->rcv_unacked = 0; + l->stats.sent_acks++; + tipc_link_build_proto_msg(l, STATE_MSG, + 0, 0, 0, 0, xmitq); + } + } +exit: + tipc_skb_queue_splice_tail(&tmpq, l->inputq); + return rc; } /** @@ -1255,458 +1170,250 @@ u32 tipc_link_defer_pkt(struct sk_buff_head *list, struct sk_buff *skb) } /* - * link_handle_out_of_seq_msg - handle arrival of out-of-sequence packet + * Send protocol message to the other endpoint. */ -static void link_handle_out_of_seq_msg(struct tipc_link *l_ptr, - struct sk_buff *buf) +void tipc_link_proto_xmit(struct tipc_link *l, u32 msg_typ, int probe_msg, + u32 gap, u32 tolerance, u32 priority) { - u32 seq_no = buf_seqno(buf); + struct sk_buff *skb = NULL; + struct sk_buff_head xmitq; - if (likely(msg_user(buf_msg(buf)) == LINK_PROTOCOL)) { - tipc_link_proto_rcv(l_ptr, buf); + __skb_queue_head_init(&xmitq); + tipc_link_build_proto_msg(l, msg_typ, probe_msg, gap, + tolerance, priority, &xmitq); + skb = __skb_dequeue(&xmitq); + if (!skb) return; - } - - /* Record OOS packet arrival */ - l_ptr->silent_intv_cnt = 0; + tipc_bearer_send(l->owner->net, l->bearer_id, skb, l->media_addr); + l->rcv_unacked = 0; + kfree_skb(skb); +} - /* - * Discard packet if a duplicate; otherwise add it to deferred queue - * and notify peer of gap as per protocol specification - */ - if (less(seq_no, l_ptr->rcv_nxt)) { - l_ptr->stats.duplicates++; - kfree_skb(buf); +/* tipc_link_build_proto_msg: prepare link protocol message for transmission + */ +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 sk_buff *skb = NULL; + struct tipc_msg *hdr = l->pmsg; + u16 snd_nxt = l->snd_nxt; + u16 rcv_nxt = l->rcv_nxt; + u16 rcv_last = rcv_nxt - 1; + int node_up = l->owner->bclink.recv_permitted; + + /* Don't send protocol message during reset or link failover */ + if (tipc_link_is_blocked(l)) return; - } - if (tipc_link_defer_pkt(&l_ptr->deferdq, buf)) { - l_ptr->stats.deferred_recv++; - if ((skb_queue_len(&l_ptr->deferdq) % TIPC_MIN_LINK_WIN) == 1) - tipc_link_proto_xmit(l_ptr, STATE_MSG, 0, 0, 0, 0); + msg_set_type(hdr, mtyp); + msg_set_net_plane(hdr, l->net_plane); + msg_set_bcast_ack(hdr, l->owner->bclink.last_in); + msg_set_last_bcast(hdr, tipc_bclink_get_last_sent(l->owner->net)); + msg_set_link_tolerance(hdr, tolerance); + msg_set_linkprio(hdr, priority); + msg_set_redundant_link(hdr, node_up); + msg_set_seq_gap(hdr, 0); + + /* Compatibility: created msg must not be in sequence with pkt flow */ + msg_set_seqno(hdr, snd_nxt + U16_MAX / 2); + + if (mtyp == STATE_MSG) { + if (!tipc_link_is_up(l)) + return; + msg_set_next_sent(hdr, snd_nxt); + + /* Override rcvgap if there are packets in deferred queue */ + if (!skb_queue_empty(&l->deferdq)) + rcvgap = buf_seqno(skb_peek(&l->deferdq)) - rcv_nxt; + if (rcvgap) { + msg_set_seq_gap(hdr, rcvgap); + l->stats.sent_nacks++; + } + msg_set_ack(hdr, rcv_last); + msg_set_probe(hdr, probe); + if (probe) + l->stats.sent_probes++; + l->stats.sent_states++; } else { - l_ptr->stats.duplicates++; + /* RESET_MSG or ACTIVATE_MSG */ + msg_set_max_pkt(hdr, l->advertised_mtu); + msg_set_ack(hdr, l->rcv_nxt - 1); + msg_set_next_sent(hdr, 1); } + skb = tipc_buf_acquire(msg_size(hdr)); + if (!skb) + return; + skb_copy_to_linear_data(skb, hdr, msg_size(hdr)); + skb->priority = TC_PRIO_CONTROL; + __skb_queue_tail(xmitq, skb); } -/* - * Send protocol message to the other endpoint. +/* tipc_link_tnl_prepare(): prepare and return a list of tunnel packets + * with contents of the link's tranmsit and backlog queues. */ -void tipc_link_proto_xmit(struct tipc_link *l_ptr, u32 msg_typ, int probe_msg, - u32 gap, u32 tolerance, u32 priority) +void tipc_link_tnl_prepare(struct tipc_link *l, struct tipc_link *tnl, + int mtyp, struct sk_buff_head *xmitq) { - struct sk_buff *buf = NULL; - struct tipc_msg *msg = l_ptr->pmsg; - u32 msg_size = sizeof(l_ptr->proto_msg); - int r_flag; - u16 last_rcv; - - /* Don't send protocol message during link failover */ - if (l_ptr->flags & LINK_FAILINGOVER) - return; + struct sk_buff *skb, *tnlskb; + struct tipc_msg *hdr, tnlhdr; + struct sk_buff_head *queue = &l->transmq; + struct sk_buff_head tmpxq, tnlq; + u16 pktlen, pktcnt, seqno = l->snd_nxt; - /* Abort non-RESET send if communication with node is prohibited */ - if ((tipc_node_blocked(l_ptr->owner)) && (msg_typ != RESET_MSG)) + if (!tnl) return; - /* Create protocol message with "out-of-sequence" sequence number */ - msg_set_type(msg, msg_typ); - msg_set_net_plane(msg, l_ptr->net_plane); - msg_set_bcast_ack(msg, l_ptr->owner->bclink.last_in); - msg_set_last_bcast(msg, tipc_bclink_get_last_sent(l_ptr->owner->net)); - - if (msg_typ == STATE_MSG) { - u16 next_sent = l_ptr->snd_nxt; + skb_queue_head_init(&tnlq); + skb_queue_head_init(&tmpxq); - if (!tipc_link_is_up(l_ptr)) + /* At least one packet required for safe algorithm => add dummy */ + skb = tipc_msg_create(TIPC_LOW_IMPORTANCE, TIPC_DIRECT_MSG, + BASIC_H_SIZE, 0, l->addr, link_own_addr(l), + 0, 0, TIPC_ERR_NO_PORT); + if (!skb) { + pr_warn("%sunable to create tunnel packet\n", link_co_err); + return; + } + skb_queue_tail(&tnlq, skb); + tipc_link_xmit(l, &tnlq, &tmpxq); + __skb_queue_purge(&tmpxq); + + /* Initialize reusable tunnel packet header */ + tipc_msg_init(link_own_addr(l), &tnlhdr, TUNNEL_PROTOCOL, + mtyp, INT_H_SIZE, l->addr); + pktcnt = skb_queue_len(&l->transmq) + skb_queue_len(&l->backlogq); + msg_set_msgcnt(&tnlhdr, pktcnt); + msg_set_bearer_id(&tnlhdr, l->peer_bearer_id); +tnl: + /* Wrap each packet into a tunnel packet */ + skb_queue_walk(queue, skb) { + hdr = buf_msg(skb); + if (queue == &l->backlogq) + msg_set_seqno(hdr, seqno++); + pktlen = msg_size(hdr); + msg_set_size(&tnlhdr, pktlen + INT_H_SIZE); + tnlskb = tipc_buf_acquire(pktlen + INT_H_SIZE); + if (!tnlskb) { + pr_warn("%sunable to send packet\n", link_co_err); return; - msg_set_next_sent(msg, next_sent); - if (!skb_queue_empty(&l_ptr->deferdq)) { - last_rcv = buf_seqno(skb_peek(&l_ptr->deferdq)); - gap = mod(last_rcv - l_ptr->rcv_nxt); } - msg_set_seq_gap(msg, gap); - if (gap) - l_ptr->stats.sent_nacks++; - msg_set_link_tolerance(msg, tolerance); - msg_set_linkprio(msg, priority); - msg_set_max_pkt(msg, l_ptr->mtu); - msg_set_ack(msg, mod(l_ptr->rcv_nxt - 1)); - msg_set_probe(msg, probe_msg != 0); - if (probe_msg) - l_ptr->stats.sent_probes++; - l_ptr->stats.sent_states++; - } else { /* RESET_MSG or ACTIVATE_MSG */ - msg_set_ack(msg, mod(l_ptr->failover_checkpt - 1)); - msg_set_seq_gap(msg, 0); - msg_set_next_sent(msg, 1); - msg_set_probe(msg, 0); - msg_set_link_tolerance(msg, l_ptr->tolerance); - msg_set_linkprio(msg, l_ptr->priority); - msg_set_max_pkt(msg, l_ptr->advertised_mtu); + skb_copy_to_linear_data(tnlskb, &tnlhdr, INT_H_SIZE); + skb_copy_to_linear_data_offset(tnlskb, INT_H_SIZE, hdr, pktlen); + __skb_queue_tail(&tnlq, tnlskb); + } + if (queue != &l->backlogq) { + queue = &l->backlogq; + goto tnl; } - r_flag = (l_ptr->owner->working_links > tipc_link_is_up(l_ptr)); - msg_set_redundant_link(msg, r_flag); - msg_set_linkprio(msg, l_ptr->priority); - msg_set_size(msg, msg_size); - - msg_set_seqno(msg, mod(l_ptr->snd_nxt + (0xffff / 2))); - - buf = tipc_buf_acquire(msg_size); - if (!buf) - return; + tipc_link_xmit(tnl, &tnlq, xmitq); - skb_copy_to_linear_data(buf, msg, sizeof(l_ptr->proto_msg)); - buf->priority = TC_PRIO_CONTROL; - tipc_bearer_send(l_ptr->owner->net, l_ptr->bearer_id, buf, - &l_ptr->media_addr); - l_ptr->rcv_unacked = 0; - kfree_skb(buf); + if (mtyp == FAILOVER_MSG) { + tnl->drop_point = l->rcv_nxt; + tnl->failover_reasm_skb = l->reasm_buf; + l->reasm_buf = NULL; + } } -/* - * Receive protocol message : +/* tipc_link_proto_rcv(): receive link level protocol message : * Note that network plane id propagates through the network, and may - * change at any time. The node with lowest address rules + * change at any time. The node with lowest numerical id determines + * network plane */ -static void tipc_link_proto_rcv(struct tipc_link *l_ptr, - struct sk_buff *buf) +static int tipc_link_proto_rcv(struct tipc_link *l, struct sk_buff *skb, + struct sk_buff_head *xmitq) { - u32 rec_gap = 0; - u32 msg_tol; - struct tipc_msg *msg = buf_msg(buf); + struct tipc_msg *hdr = buf_msg(skb); + u16 rcvgap = 0; + u16 nacked_gap = msg_seq_gap(hdr); + u16 peers_snd_nxt = msg_next_sent(hdr); + u16 peers_tol = msg_link_tolerance(hdr); + u16 peers_prio = msg_linkprio(hdr); + u16 rcv_nxt = l->rcv_nxt; + char *if_name; + int rc = 0; - if (l_ptr->flags & LINK_FAILINGOVER) + if (tipc_link_is_blocked(l)) goto exit; - if (l_ptr->net_plane != msg_net_plane(msg)) - if (link_own_addr(l_ptr) > msg_prevnode(msg)) - l_ptr->net_plane = msg_net_plane(msg); - - switch (msg_type(msg)) { + if (link_own_addr(l) > msg_prevnode(hdr)) + l->net_plane = msg_net_plane(hdr); + switch (msg_type(hdr)) { case RESET_MSG: - if (!link_working_unknown(l_ptr) && - (l_ptr->peer_session != INVALID_SESSION)) { - if (less_eq(msg_session(msg), l_ptr->peer_session)) - break; /* duplicate or old reset: ignore */ - } - - if (!msg_redundant_link(msg) && (link_working_working(l_ptr) || - link_working_unknown(l_ptr))) { - /* - * peer has lost contact -- don't allow peer's links - * to reactivate before we recognize loss & clean up - */ - l_ptr->owner->action_flags |= TIPC_WAIT_OWN_LINKS_DOWN; - } - - link_state_event(l_ptr, RESET_MSG); + /* Ignore duplicate RESET with old session number */ + if ((less_eq(msg_session(hdr), l->peer_session)) && + (l->peer_session != WILDCARD_SESSION)) + break; /* fall thru' */ - case ACTIVATE_MSG: - /* Update link settings according other endpoint's values */ - strcpy((strrchr(l_ptr->name, ':') + 1), (char *)msg_data(msg)); - msg_tol = msg_link_tolerance(msg); - if (msg_tol > l_ptr->tolerance) - link_set_supervision_props(l_ptr, msg_tol); - - if (msg_linkprio(msg) > l_ptr->priority) - l_ptr->priority = msg_linkprio(msg); - - if (l_ptr->mtu > msg_max_pkt(msg)) - l_ptr->mtu = msg_max_pkt(msg); - - /* Synchronize broadcast link info, if not done previously */ - if (!tipc_node_is_up(l_ptr->owner)) { - l_ptr->owner->bclink.last_sent = - l_ptr->owner->bclink.last_in = - msg_last_bcast(msg); - l_ptr->owner->bclink.oos_state = 0; - } - - l_ptr->peer_session = msg_session(msg); - l_ptr->peer_bearer_id = msg_bearer_id(msg); - - if (msg_type(msg) == ACTIVATE_MSG) - link_state_event(l_ptr, ACTIVATE_MSG); - break; - case STATE_MSG: + case ACTIVATE_MSG: - msg_tol = msg_link_tolerance(msg); - if (msg_tol) - link_set_supervision_props(l_ptr, msg_tol); - - if (msg_linkprio(msg) && - (msg_linkprio(msg) != l_ptr->priority)) { - pr_debug("%s<%s>, priority change %u->%u\n", - link_rst_msg, l_ptr->name, - l_ptr->priority, msg_linkprio(msg)); - l_ptr->priority = msg_linkprio(msg); - tipc_link_reset(l_ptr); /* Enforce change to take effect */ + /* Complete own link name with peer's interface name */ + if_name = strrchr(l->name, ':') + 1; + if (sizeof(l->name) - (if_name - l->name) <= TIPC_MAX_IF_NAME) break; - } - - /* Record reception; force mismatch at next timeout: */ - l_ptr->silent_intv_cnt = 0; - - link_state_event(l_ptr, TRAFFIC_MSG_EVT); - l_ptr->stats.recv_states++; - if (link_reset_unknown(l_ptr)) + if (msg_data_sz(hdr) < TIPC_MAX_IF_NAME) break; + strncpy(if_name, msg_data(hdr), TIPC_MAX_IF_NAME); - if (less_eq(l_ptr->rcv_nxt, msg_next_sent(msg))) - rec_gap = mod(msg_next_sent(msg) - l_ptr->rcv_nxt); + /* Update own tolerance if peer indicates a non-zero value */ + if (in_range(peers_tol, TIPC_MIN_LINK_TOL, TIPC_MAX_LINK_TOL)) + l->tolerance = peers_tol; - if (msg_probe(msg)) - l_ptr->stats.recv_probes++; + /* Update own priority if peer's priority is higher */ + if (in_range(peers_prio, l->priority + 1, TIPC_MAX_LINK_PRI)) + l->priority = peers_prio; - /* Protocol message before retransmits, reduce loss risk */ - if (l_ptr->owner->bclink.recv_permitted) - tipc_bclink_update_link_state(l_ptr->owner, - msg_last_bcast(msg)); - - if (rec_gap || (msg_probe(msg))) { - tipc_link_proto_xmit(l_ptr, STATE_MSG, 0, - rec_gap, 0, 0); - } - if (msg_seq_gap(msg)) { - l_ptr->stats.recv_nacks++; - tipc_link_retransmit(l_ptr, skb_peek(&l_ptr->transmq), - msg_seq_gap(msg)); + if (msg_type(hdr) == RESET_MSG) { + rc |= tipc_link_fsm_evt(l, LINK_PEER_RESET_EVT); + } else if (!link_is_up(l)) { + tipc_link_fsm_evt(l, LINK_PEER_RESET_EVT); + rc |= tipc_link_fsm_evt(l, LINK_ESTABLISH_EVT); } + l->peer_session = msg_session(hdr); + l->peer_bearer_id = msg_bearer_id(hdr); + if (l->mtu > msg_max_pkt(hdr)) + l->mtu = msg_max_pkt(hdr); break; - } -exit: - kfree_skb(buf); -} - - -/* tipc_link_tunnel_xmit(): Tunnel one packet via a link belonging to - * a different bearer. Owner node is locked. - */ -static void tipc_link_tunnel_xmit(struct tipc_link *l_ptr, - struct tipc_msg *tunnel_hdr, - struct tipc_msg *msg, - u32 selector) -{ - struct tipc_link *tunnel; - struct sk_buff *skb; - u32 length = msg_size(msg); - - tunnel = l_ptr->owner->active_links[selector & 1]; - if (!tipc_link_is_up(tunnel)) { - pr_warn("%stunnel link no longer available\n", link_co_err); - return; - } - msg_set_size(tunnel_hdr, length + INT_H_SIZE); - skb = tipc_buf_acquire(length + INT_H_SIZE); - if (!skb) { - pr_warn("%sunable to send tunnel msg\n", link_co_err); - return; - } - skb_copy_to_linear_data(skb, tunnel_hdr, INT_H_SIZE); - skb_copy_to_linear_data_offset(skb, INT_H_SIZE, msg, length); - __tipc_link_xmit_skb(tunnel, skb); -} - - -/* tipc_link_failover_send_queue(): A link has gone down, but a second - * link is still active. We can do failover. Tunnel the failing link's - * whole send queue via the remaining link. This way, we don't lose - * any packets, and sequence order is preserved for subsequent traffic - * sent over the remaining link. Owner node is locked. - */ -void tipc_link_failover_send_queue(struct tipc_link *l_ptr) -{ - int msgcount; - struct tipc_link *tunnel = l_ptr->owner->active_links[0]; - struct tipc_msg tunnel_hdr; - struct sk_buff *skb; - int split_bundles; - - if (!tunnel) - return; - tipc_msg_init(link_own_addr(l_ptr), &tunnel_hdr, TUNNEL_PROTOCOL, - FAILOVER_MSG, INT_H_SIZE, l_ptr->addr); - - skb_queue_walk(&l_ptr->backlogq, skb) { - msg_set_seqno(buf_msg(skb), l_ptr->snd_nxt); - l_ptr->snd_nxt = mod(l_ptr->snd_nxt + 1); - } - skb_queue_splice_tail_init(&l_ptr->backlogq, &l_ptr->transmq); - tipc_link_purge_backlog(l_ptr); - msgcount = skb_queue_len(&l_ptr->transmq); - msg_set_bearer_id(&tunnel_hdr, l_ptr->peer_bearer_id); - msg_set_msgcnt(&tunnel_hdr, msgcount); - - if (skb_queue_empty(&l_ptr->transmq)) { - skb = tipc_buf_acquire(INT_H_SIZE); - if (skb) { - skb_copy_to_linear_data(skb, &tunnel_hdr, INT_H_SIZE); - msg_set_size(&tunnel_hdr, INT_H_SIZE); - __tipc_link_xmit_skb(tunnel, skb); - } else { - pr_warn("%sunable to send changeover msg\n", - link_co_err); - } - return; - } - - split_bundles = (l_ptr->owner->active_links[0] != - l_ptr->owner->active_links[1]); + case STATE_MSG: - skb_queue_walk(&l_ptr->transmq, skb) { - struct tipc_msg *msg = buf_msg(skb); + /* Update own tolerance if peer indicates a non-zero value */ + if (in_range(peers_tol, TIPC_MIN_LINK_TOL, TIPC_MAX_LINK_TOL)) + l->tolerance = peers_tol; - if ((msg_user(msg) == MSG_BUNDLER) && split_bundles) { - struct tipc_msg *m = msg_get_wrapped(msg); - unchar *pos = (unchar *)m; + l->silent_intv_cnt = 0; + l->stats.recv_states++; + if (msg_probe(hdr)) + l->stats.recv_probes++; + rc = tipc_link_fsm_evt(l, LINK_ESTABLISH_EVT); + if (!link_is_up(l)) + break; - msgcount = msg_msgcnt(msg); - while (msgcount--) { - msg_set_seqno(m, msg_seqno(msg)); - tipc_link_tunnel_xmit(l_ptr, &tunnel_hdr, m, - msg_link_selector(m)); - pos += align(msg_size(m)); - m = (struct tipc_msg *)pos; - } - } else { - tipc_link_tunnel_xmit(l_ptr, &tunnel_hdr, msg, - msg_link_selector(msg)); + /* Send NACK if peer has sent pkts we haven't received yet */ + if (more(peers_snd_nxt, rcv_nxt) && !tipc_link_is_synching(l)) + rcvgap = peers_snd_nxt - l->rcv_nxt; + if (rcvgap || (msg_probe(hdr))) + tipc_link_build_proto_msg(l, STATE_MSG, 0, rcvgap, + 0, 0, xmitq); + tipc_link_release_pkts(l, msg_ack(hdr)); + + /* If NACK, retransmit will now start at right position */ + if (nacked_gap) { + rc = tipc_link_retransm(l, nacked_gap, xmitq); + l->stats.recv_nacks++; } - } -} - -/* tipc_link_dup_queue_xmit(): A second link has become active. Tunnel a - * duplicate of the first link's send queue via the new link. This way, we - * are guaranteed that currently queued packets from a socket are delivered - * before future traffic from the same socket, even if this is using the - * new link. The last arriving copy of each duplicate packet is dropped at - * the receiving end by the regular protocol check, so packet cardinality - * and sequence order is preserved per sender/receiver socket pair. - * Owner node is locked. - */ -void tipc_link_dup_queue_xmit(struct tipc_link *link, - struct tipc_link *tnl) -{ - struct sk_buff *skb; - struct tipc_msg tnl_hdr; - struct sk_buff_head *queue = &link->transmq; - int mcnt; - u16 seqno; - - tipc_msg_init(link_own_addr(link), &tnl_hdr, TUNNEL_PROTOCOL, - SYNCH_MSG, INT_H_SIZE, link->addr); - mcnt = skb_queue_len(&link->transmq) + skb_queue_len(&link->backlogq); - msg_set_msgcnt(&tnl_hdr, mcnt); - msg_set_bearer_id(&tnl_hdr, link->peer_bearer_id); - -tunnel_queue: - skb_queue_walk(queue, skb) { - struct sk_buff *outskb; - struct tipc_msg *msg = buf_msg(skb); - u32 len = msg_size(msg); - msg_set_ack(msg, mod(link->rcv_nxt - 1)); - msg_set_bcast_ack(msg, link->owner->bclink.last_in); - msg_set_size(&tnl_hdr, len + INT_H_SIZE); - outskb = tipc_buf_acquire(len + INT_H_SIZE); - if (outskb == NULL) { - pr_warn("%sunable to send duplicate msg\n", - link_co_err); - return; - } - skb_copy_to_linear_data(outskb, &tnl_hdr, INT_H_SIZE); - skb_copy_to_linear_data_offset(outskb, INT_H_SIZE, - skb->data, len); - __tipc_link_xmit_skb(tnl, outskb); - if (!tipc_link_is_up(link)) - return; - } - if (queue == &link->backlogq) - return; - seqno = link->snd_nxt; - skb_queue_walk(&link->backlogq, skb) { - msg_set_seqno(buf_msg(skb), seqno); - seqno = mod(seqno + 1); - } - queue = &link->backlogq; - goto tunnel_queue; -} - -/* tipc_link_failover_rcv(): Receive a tunnelled FAILOVER_MSG packet - * Owner node is locked. - */ -static bool tipc_link_failover_rcv(struct tipc_link *link, - struct sk_buff **skb) -{ - struct tipc_msg *msg = buf_msg(*skb); - struct sk_buff *iskb = NULL; - struct tipc_link *pl = NULL; - int bearer_id = msg_bearer_id(msg); - int pos = 0; - - if (msg_type(msg) != FAILOVER_MSG) { - pr_warn("%sunknown tunnel pkt received\n", link_co_err); - goto exit; - } - if (bearer_id >= MAX_BEARERS) - goto exit; - - if (bearer_id == link->bearer_id) - goto exit; - - pl = link->owner->links[bearer_id]; - if (pl && tipc_link_is_up(pl)) - tipc_link_reset(pl); - - if (link->failover_pkts == FIRST_FAILOVER) - link->failover_pkts = msg_msgcnt(msg); - - /* Should we expect an inner packet? */ - if (!link->failover_pkts) - goto exit; - - if (!tipc_msg_extract(*skb, &iskb, &pos)) { - pr_warn("%sno inner failover pkt\n", link_co_err); - *skb = NULL; - goto exit; - } - link->failover_pkts--; - *skb = NULL; - - /* Was this packet already delivered? */ - if (less(buf_seqno(iskb), link->failover_checkpt)) { - kfree_skb(iskb); - iskb = NULL; - goto exit; - } - if (msg_user(buf_msg(iskb)) == MSG_FRAGMENTER) { - link->stats.recv_fragments++; - tipc_buf_append(&link->failover_skb, &iskb); + tipc_link_advance_backlog(l, xmitq); + if (unlikely(!skb_queue_empty(&l->wakeupq))) + link_prepare_wakeup(l); } exit: - if (!link->failover_pkts && pl) - pl->flags &= ~LINK_FAILINGOVER; - kfree_skb(*skb); - *skb = iskb; - return *skb; -} - -static void link_set_supervision_props(struct tipc_link *l_ptr, u32 tol) -{ - unsigned long intv = ((tol / 4) > 500) ? 500 : tol / 4; - - if ((tol < TIPC_MIN_LINK_TOL) || (tol > TIPC_MAX_LINK_TOL)) - return; - - l_ptr->tolerance = tol; - l_ptr->keepalive_intv = msecs_to_jiffies(intv); - l_ptr->abort_limit = tol / (jiffies_to_msecs(l_ptr->keepalive_intv)); + kfree_skb(skb); + return rc; } void tipc_link_set_queue_limits(struct tipc_link *l, u32 win) @@ -1743,7 +1450,7 @@ static struct tipc_node *tipc_link_find_owner(struct net *net, list_for_each_entry_rcu(n_ptr, &tn->node_list, list) { tipc_node_lock(n_ptr); for (i = 0; i < MAX_BEARERS; i++) { - l_ptr = n_ptr->links[i]; + l_ptr = n_ptr->links[i].link; if (l_ptr && !strcmp(l_ptr->name, link_name)) { *bearer_id = i; found_node = n_ptr; @@ -1770,27 +1477,16 @@ static void link_reset_statistics(struct tipc_link *l_ptr) l_ptr->stats.recv_info = l_ptr->rcv_nxt; } -static void link_print(struct tipc_link *l_ptr, const char *str) +static void link_print(struct tipc_link *l, const char *str) { - struct tipc_net *tn = net_generic(l_ptr->owner->net, tipc_net_id); - struct tipc_bearer *b_ptr; - - rcu_read_lock(); - b_ptr = rcu_dereference_rtnl(tn->bearer_list[l_ptr->bearer_id]); - if (b_ptr) - pr_info("%s Link %x<%s>:", str, l_ptr->addr, b_ptr->name); - rcu_read_unlock(); - - if (link_working_unknown(l_ptr)) - pr_cont(":WU\n"); - else if (link_reset_reset(l_ptr)) - pr_cont(":RR\n"); - else if (link_reset_unknown(l_ptr)) - pr_cont(":RU\n"); - else if (link_working_working(l_ptr)) - pr_cont(":WW\n"); - else - pr_cont("\n"); + struct sk_buff *hskb = skb_peek(&l->transmq); + u16 head = hskb ? msg_seqno(buf_msg(hskb)) : l->snd_nxt; + u16 tail = l->snd_nxt - 1; + + pr_info("%s Link <%s> state %x\n", str, l->name, l->state); + pr_info("XMTQ: %u [%u-%u], BKLGQ: %u, SNDNX: %u, RCVNX: %u\n", + skb_queue_len(&l->transmq), head, tail, + skb_queue_len(&l->backlogq), l->snd_nxt, l->rcv_nxt); } /* Parse and validate nested (link) properties valid for media, bearer and link @@ -1865,7 +1561,7 @@ int tipc_nl_link_set(struct sk_buff *skb, struct genl_info *info) tipc_node_lock(node); - link = node->links[bearer_id]; + link = node->links[bearer_id].link; if (!link) { res = -EINVAL; goto out; @@ -1885,7 +1581,7 @@ int tipc_nl_link_set(struct sk_buff *skb, struct genl_info *info) u32 tol; tol = nla_get_u32(props[TIPC_NLA_PROP_TOL]); - link_set_supervision_props(link, tol); + link->tolerance = tol; tipc_link_proto_xmit(link, STATE_MSG, 0, 0, tol, 0); } if (props[TIPC_NLA_PROP_PRIO]) { @@ -2055,10 +1751,11 @@ static int __tipc_nl_add_node_links(struct net *net, struct tipc_nl_msg *msg, for (i = *prev_link; i < MAX_BEARERS; i++) { *prev_link = i; - if (!node->links[i]) + if (!node->links[i].link) continue; - err = __tipc_nl_add_link(net, msg, node->links[i], NLM_F_MULTI); + err = __tipc_nl_add_link(net, msg, + node->links[i].link, NLM_F_MULTI); if (err) return err; } @@ -2172,7 +1869,7 @@ int tipc_nl_link_get(struct sk_buff *skb, struct genl_info *info) return -EINVAL; tipc_node_lock(node); - link = node->links[bearer_id]; + link = node->links[bearer_id].link; if (!link) { tipc_node_unlock(node); nlmsg_free(msg.skb); @@ -2227,7 +1924,7 @@ int tipc_nl_link_reset_stats(struct sk_buff *skb, struct genl_info *info) tipc_node_lock(node); - link = node->links[bearer_id]; + link = node->links[bearer_id].link; if (!link) { tipc_node_unlock(node); return -EINVAL; diff --git a/net/tipc/link.h b/net/tipc/link.h index ae0a0ea572f2..39ff8b6919a4 100644 --- a/net/tipc/link.h +++ b/net/tipc/link.h @@ -49,19 +49,25 @@ */ #define INVALID_LINK_SEQ 0x10000 -/* Link working states +/* Link FSM events: */ -#define WORKING_WORKING 560810u -#define WORKING_UNKNOWN 560811u -#define RESET_UNKNOWN 560812u -#define RESET_RESET 560813u +enum { + LINK_ESTABLISH_EVT = 0xec1ab1e, + LINK_PEER_RESET_EVT = 0x9eed0e, + LINK_FAILURE_EVT = 0xfa110e, + LINK_RESET_EVT = 0x10ca1d0e, + LINK_FAILOVER_BEGIN_EVT = 0xfa110bee, + LINK_FAILOVER_END_EVT = 0xfa110ede, + LINK_SYNCH_BEGIN_EVT = 0xc1ccbee, + LINK_SYNCH_END_EVT = 0xc1ccede +}; -/* Link endpoint execution states +/* Events returned from link at packet reception or at timeout */ -#define LINK_STARTED 0x0001 -#define LINK_STOPPED 0x0002 -#define LINK_SYNCHING 0x0004 -#define LINK_FAILINGOVER 0x0008 +enum { + TIPC_LINK_UP_EVT = 1, + TIPC_LINK_DOWN_EVT = (1 << 1) +}; /* Starting value for maximum packet size negotiation on unicast links * (unless bearer MTU is less) @@ -106,7 +112,6 @@ struct tipc_stats { * @timer: link timer * @owner: pointer to peer node * @refcnt: reference counter for permanent references (owner node & timer) - * @flags: execution state flags for link endpoint instance * @peer_session: link session # being used by peer end of link * @peer_bearer_id: bearer id used by link's peer endpoint * @bearer_id: local bearer id used by link @@ -143,20 +148,17 @@ struct tipc_stats { struct tipc_link { u32 addr; char name[TIPC_MAX_LINK_NAME]; - struct tipc_media_addr media_addr; - struct timer_list timer; + struct tipc_media_addr *media_addr; struct tipc_node *owner; - struct kref ref; /* Management and link supervision data */ - unsigned int flags; u32 peer_session; u32 peer_bearer_id; u32 bearer_id; u32 tolerance; unsigned long keepalive_intv; u32 abort_limit; - int state; + u32 state; u32 silent_intv_cnt; struct { unchar hdr[INT_H_SIZE]; @@ -165,12 +167,10 @@ struct tipc_link { struct tipc_msg *pmsg; u32 priority; char net_plane; - u16 synch_point; - /* Failover */ - u16 failover_pkts; - u16 failover_checkpt; - struct sk_buff *failover_skb; + /* Failover/synch */ + u16 drop_point; + struct sk_buff *failover_reasm_skb; /* Max packet negotiation */ u16 mtu; @@ -192,8 +192,8 @@ struct tipc_link { u16 rcv_nxt; u32 rcv_unacked; struct sk_buff_head deferdq; - struct sk_buff_head inputq; - struct sk_buff_head namedq; + struct sk_buff_head *inputq; + struct sk_buff_head *namedq; /* Congestion handling */ struct sk_buff_head wakeupq; @@ -205,28 +205,29 @@ struct tipc_link { struct tipc_stats stats; }; -struct tipc_port; - -struct tipc_link *tipc_link_create(struct tipc_node *n_ptr, - struct tipc_bearer *b_ptr, - const struct tipc_media_addr *media_addr); -void tipc_link_delete(struct tipc_link *link); -void tipc_link_delete_list(struct net *net, unsigned int bearer_id); -void tipc_link_failover_send_queue(struct tipc_link *l_ptr); -void tipc_link_dup_queue_xmit(struct tipc_link *l_ptr, struct tipc_link *dest); +bool tipc_link_create(struct tipc_node *n, struct tipc_bearer *b, u32 session, + u32 ownnode, u32 peer, struct tipc_media_addr *maddr, + struct sk_buff_head *inputq, struct sk_buff_head *namedq, + struct tipc_link **link); +void tipc_link_tnl_prepare(struct tipc_link *l, struct tipc_link *tnl, + int mtyp, struct sk_buff_head *xmitq); +void tipc_link_build_bcast_sync_msg(struct tipc_link *l, + struct sk_buff_head *xmitq); +int tipc_link_fsm_evt(struct tipc_link *l, int evt); void tipc_link_reset_fragments(struct tipc_link *l_ptr); -int tipc_link_is_up(struct tipc_link *l_ptr); +bool tipc_link_is_up(struct tipc_link *l); +bool tipc_link_is_reset(struct tipc_link *l); +bool tipc_link_is_synching(struct tipc_link *l); +bool tipc_link_is_failingover(struct tipc_link *l); +bool tipc_link_is_blocked(struct tipc_link *l); int tipc_link_is_active(struct tipc_link *l_ptr); void tipc_link_purge_queues(struct tipc_link *l_ptr); void tipc_link_purge_backlog(struct tipc_link *l); -void tipc_link_reset_all(struct tipc_node *node); void tipc_link_reset(struct tipc_link *l_ptr); -int tipc_link_xmit_skb(struct net *net, struct sk_buff *skb, u32 dest, - u32 selector); -int tipc_link_xmit(struct net *net, struct sk_buff_head *list, u32 dest, - u32 selector); int __tipc_link_xmit(struct net *net, struct tipc_link *link, struct sk_buff_head *list); +int tipc_link_xmit(struct tipc_link *link, struct sk_buff_head *list, + struct sk_buff_head *xmitq); void tipc_link_proto_xmit(struct tipc_link *l_ptr, u32 msg_typ, int prob, u32 gap, u32 tolerance, u32 priority); void tipc_link_push_packets(struct tipc_link *l_ptr); @@ -242,34 +243,8 @@ int tipc_nl_link_get(struct sk_buff *skb, struct genl_info *info); int tipc_nl_link_set(struct sk_buff *skb, struct genl_info *info); int tipc_nl_link_reset_stats(struct sk_buff *skb, struct genl_info *info); int tipc_nl_parse_link_prop(struct nlattr *prop, struct nlattr *props[]); -void link_prepare_wakeup(struct tipc_link *l); - -static inline u32 link_own_addr(struct tipc_link *l) -{ - return msg_prevnode(l->pmsg); -} - -/* - * Link status checking routines - */ -static inline int link_working_working(struct tipc_link *l_ptr) -{ - return l_ptr->state == WORKING_WORKING; -} - -static inline int link_working_unknown(struct tipc_link *l_ptr) -{ - return l_ptr->state == WORKING_UNKNOWN; -} - -static inline int link_reset_unknown(struct tipc_link *l_ptr) -{ - return l_ptr->state == RESET_UNKNOWN; -} - -static inline int link_reset_reset(struct tipc_link *l_ptr) -{ - return l_ptr->state == RESET_RESET; -} +int tipc_link_timeout(struct tipc_link *l, struct sk_buff_head *xmitq); +int tipc_link_rcv(struct tipc_link *l, struct sk_buff *skb, + struct sk_buff_head *xmitq); #endif diff --git a/net/tipc/msg.c b/net/tipc/msg.c index 08b4cc7d496d..562c926a51cc 100644 --- a/net/tipc/msg.c +++ b/net/tipc/msg.c @@ -463,60 +463,72 @@ bool tipc_msg_make_bundle(struct sk_buff **skb, struct tipc_msg *msg, /** * tipc_msg_reverse(): swap source and destination addresses and add error code - * @buf: buffer containing message to be reversed - * @dnode: return value: node where to send message after reversal - * @err: error code to be set in message - * Consumes buffer if failure + * @own_node: originating node id for reversed message + * @skb: buffer containing message to be reversed; may be replaced. + * @err: error code to be set in message, if any + * Consumes buffer at failure * Returns true if success, otherwise false */ -bool tipc_msg_reverse(u32 own_addr, struct sk_buff *buf, u32 *dnode, - int err) +bool tipc_msg_reverse(u32 own_node, struct sk_buff **skb, int err) { - struct tipc_msg *msg = buf_msg(buf); + struct sk_buff *_skb = *skb; + struct tipc_msg *hdr = buf_msg(_skb); struct tipc_msg ohdr; - uint rdsz = min_t(uint, msg_data_sz(msg), MAX_FORWARD_SIZE); + int dlen = min_t(uint, msg_data_sz(hdr), MAX_FORWARD_SIZE); - if (skb_linearize(buf)) + if (skb_linearize(_skb)) goto exit; - msg = buf_msg(buf); - if (msg_dest_droppable(msg)) + hdr = buf_msg(_skb); + if (msg_dest_droppable(hdr)) goto exit; - if (msg_errcode(msg)) + if (msg_errcode(hdr)) goto exit; - memcpy(&ohdr, msg, msg_hdr_sz(msg)); - msg_set_errcode(msg, err); - msg_set_origport(msg, msg_destport(&ohdr)); - msg_set_destport(msg, msg_origport(&ohdr)); - msg_set_prevnode(msg, own_addr); - if (!msg_short(msg)) { - msg_set_orignode(msg, msg_destnode(&ohdr)); - msg_set_destnode(msg, msg_orignode(&ohdr)); + + /* Take a copy of original header before altering message */ + memcpy(&ohdr, hdr, msg_hdr_sz(hdr)); + + /* Never return SHORT header; expand by replacing buffer if necessary */ + if (msg_short(hdr)) { + *skb = tipc_buf_acquire(BASIC_H_SIZE + dlen); + if (!*skb) + goto exit; + memcpy((*skb)->data + BASIC_H_SIZE, msg_data(hdr), dlen); + kfree_skb(_skb); + _skb = *skb; + hdr = buf_msg(_skb); + memcpy(hdr, &ohdr, BASIC_H_SIZE); + msg_set_hdr_sz(hdr, BASIC_H_SIZE); } - msg_set_size(msg, msg_hdr_sz(msg) + rdsz); - skb_trim(buf, msg_size(msg)); - skb_orphan(buf); - *dnode = msg_orignode(&ohdr); + + /* Now reverse the concerned fields */ + msg_set_errcode(hdr, err); + msg_set_origport(hdr, msg_destport(&ohdr)); + msg_set_destport(hdr, msg_origport(&ohdr)); + msg_set_destnode(hdr, msg_prevnode(&ohdr)); + msg_set_prevnode(hdr, own_node); + msg_set_orignode(hdr, own_node); + msg_set_size(hdr, msg_hdr_sz(hdr) + dlen); + skb_trim(_skb, msg_size(hdr)); + skb_orphan(_skb); return true; exit: - kfree_skb(buf); - *dnode = 0; + kfree_skb(_skb); + *skb = NULL; return false; } /** * tipc_msg_lookup_dest(): try to find new destination for named message * @skb: the buffer containing the message. - * @dnode: return value: next-hop node, if destination found - * @err: return value: error code to use, if message to be rejected + * @err: error code to be used by caller if lookup fails * Does not consume buffer * Returns true if a destination is found, false otherwise */ -bool tipc_msg_lookup_dest(struct net *net, struct sk_buff *skb, - u32 *dnode, int *err) +bool tipc_msg_lookup_dest(struct net *net, struct sk_buff *skb, int *err) { struct tipc_msg *msg = buf_msg(skb); - u32 dport; - u32 own_addr = tipc_own_addr(net); + u32 dport, dnode; + u32 onode = tipc_own_addr(net); if (!msg_isdata(msg)) return false; @@ -529,15 +541,15 @@ bool tipc_msg_lookup_dest(struct net *net, struct sk_buff *skb, return false; if (msg_reroute_cnt(msg)) return false; - *dnode = addr_domain(net, msg_lookup_scope(msg)); + dnode = addr_domain(net, msg_lookup_scope(msg)); dport = tipc_nametbl_translate(net, msg_nametype(msg), - msg_nameinst(msg), dnode); + msg_nameinst(msg), &dnode); if (!dport) return false; msg_incr_reroute_cnt(msg); - if (*dnode != own_addr) - msg_set_prevnode(msg, own_addr); - msg_set_destnode(msg, *dnode); + if (dnode != onode) + msg_set_prevnode(msg, onode); + msg_set_destnode(msg, dnode); msg_set_destport(msg, dport); *err = TIPC_OK; return true; diff --git a/net/tipc/msg.h b/net/tipc/msg.h index 19c45fb66238..a82c5848d4bc 100644 --- a/net/tipc/msg.h +++ b/net/tipc/msg.h @@ -38,6 +38,7 @@ #define _TIPC_MSG_H #include <linux/tipc.h> +#include "core.h" /* * Constants and routines used to read and write TIPC payload message headers @@ -109,7 +110,6 @@ struct tipc_skb_cb { struct sk_buff *tail; bool validated; bool wakeup_pending; - bool bundling; u16 chain_sz; u16 chain_imp; }; @@ -558,15 +558,6 @@ static inline void msg_set_node_capabilities(struct tipc_msg *m, u32 n) msg_set_bits(m, 1, 15, 0x1fff, n); } -static inline bool msg_dup(struct tipc_msg *m) -{ - if (likely(msg_user(m) != TUNNEL_PROTOCOL)) - return false; - if (msg_type(m) != SYNCH_MSG) - return false; - return true; -} - /* * Word 2 */ @@ -620,12 +611,12 @@ static inline void msg_set_fragm_no(struct tipc_msg *m, u32 n) } -static inline u32 msg_next_sent(struct tipc_msg *m) +static inline u16 msg_next_sent(struct tipc_msg *m) { return msg_bits(m, 4, 0, 0xffff); } -static inline void msg_set_next_sent(struct tipc_msg *m, u32 n) +static inline void msg_set_next_sent(struct tipc_msg *m, u16 n) { msg_set_bits(m, 4, 0, 0xffff, n); } @@ -658,12 +649,12 @@ static inline void msg_set_link_selector(struct tipc_msg *m, u32 n) /* * Word 5 */ -static inline u32 msg_session(struct tipc_msg *m) +static inline u16 msg_session(struct tipc_msg *m) { return msg_bits(m, 5, 16, 0xffff); } -static inline void msg_set_session(struct tipc_msg *m, u32 n) +static inline void msg_set_session(struct tipc_msg *m, u16 n) { msg_set_bits(m, 5, 16, 0xffff, n); } @@ -726,12 +717,12 @@ static inline char *msg_media_addr(struct tipc_msg *m) /* * Word 9 */ -static inline u32 msg_msgcnt(struct tipc_msg *m) +static inline u16 msg_msgcnt(struct tipc_msg *m) { return msg_bits(m, 9, 16, 0xffff); } -static inline void msg_set_msgcnt(struct tipc_msg *m, u32 n) +static inline void msg_set_msgcnt(struct tipc_msg *m, u16 n) { msg_set_bits(m, 9, 16, 0xffff, n); } @@ -766,10 +757,25 @@ static inline void msg_set_link_tolerance(struct tipc_msg *m, u32 n) msg_set_bits(m, 9, 0, 0xffff, n); } +static inline bool msg_peer_link_is_up(struct tipc_msg *m) +{ + if (likely(msg_user(m) != LINK_PROTOCOL)) + return true; + if (msg_type(m) == STATE_MSG) + return true; + return false; +} + +static inline bool msg_peer_node_is_up(struct tipc_msg *m) +{ + if (msg_peer_link_is_up(m)) + return true; + return msg_redundant_link(m); +} + struct sk_buff *tipc_buf_acquire(u32 size); bool tipc_msg_validate(struct sk_buff *skb); -bool tipc_msg_reverse(u32 own_addr, struct sk_buff *buf, u32 *dnode, - int err); +bool tipc_msg_reverse(u32 own_addr, struct sk_buff **skb, int err); void tipc_msg_init(u32 own_addr, struct tipc_msg *m, u32 user, u32 type, u32 hsize, u32 destnode); struct sk_buff *tipc_msg_create(uint user, uint type, uint hdr_sz, @@ -782,8 +788,7 @@ bool tipc_msg_make_bundle(struct sk_buff **skb, struct tipc_msg *msg, bool tipc_msg_extract(struct sk_buff *skb, struct sk_buff **iskb, int *pos); int tipc_msg_build(struct tipc_msg *mhdr, struct msghdr *m, int offset, int dsz, int mtu, struct sk_buff_head *list); -bool tipc_msg_lookup_dest(struct net *net, struct sk_buff *skb, u32 *dnode, - int *err); +bool tipc_msg_lookup_dest(struct net *net, struct sk_buff *skb, int *err); struct sk_buff *tipc_msg_reassemble(struct sk_buff_head *list); static inline u16 buf_seqno(struct sk_buff *skb) @@ -857,26 +862,65 @@ static inline struct sk_buff *tipc_skb_dequeue(struct sk_buff_head *list, return skb; } -/* tipc_skb_queue_tail(): add buffer to tail of list; +/* tipc_skb_queue_sorted(); sort pkt into list according to sequence number * @list: list to be appended to - * @skb: buffer to append. Always appended - * @dport: the destination port of the buffer - * returns true if dport differs from previous destination + * @skb: buffer to add + * Returns true if queue should treated further, otherwise false */ -static inline bool tipc_skb_queue_tail(struct sk_buff_head *list, - struct sk_buff *skb, u32 dport) +static inline bool __tipc_skb_queue_sorted(struct sk_buff_head *list, + struct sk_buff *skb) { - struct sk_buff *_skb = NULL; - bool rv = false; + struct sk_buff *_skb, *tmp; + struct tipc_msg *hdr = buf_msg(skb); + u16 seqno = msg_seqno(hdr); - spin_lock_bh(&list->lock); - _skb = skb_peek_tail(list); - if (!_skb || (msg_destport(buf_msg(_skb)) != dport) || - (skb_queue_len(list) > 32)) - rv = true; + if (skb_queue_empty(list) || (msg_user(hdr) == LINK_PROTOCOL)) { + __skb_queue_head(list, skb); + return true; + } + if (likely(less(seqno, buf_seqno(skb_peek(list))))) { + __skb_queue_head(list, skb); + return true; + } + if (!more(seqno, buf_seqno(skb_peek_tail(list)))) { + skb_queue_walk_safe(list, _skb, tmp) { + if (likely(less(seqno, buf_seqno(_skb)))) { + __skb_queue_before(list, _skb, skb); + return true; + } + } + } __skb_queue_tail(list, skb); + return false; +} + +/* tipc_skb_queue_splice_tail - append an skb list to lock protected list + * @list: the new list to append. Not lock protected + * @head: target list. Lock protected. + */ +static inline void tipc_skb_queue_splice_tail(struct sk_buff_head *list, + struct sk_buff_head *head) +{ + spin_lock_bh(&head->lock); + skb_queue_splice_tail(list, head); + spin_unlock_bh(&head->lock); +} + +/* tipc_skb_queue_splice_tail_init - merge two lock protected skb lists + * @list: the new list to add. Lock protected. Will be reinitialized + * @head: target list. Lock protected. + */ +static inline void tipc_skb_queue_splice_tail_init(struct sk_buff_head *list, + struct sk_buff_head *head) +{ + struct sk_buff_head tmp; + + __skb_queue_head_init(&tmp); + + spin_lock_bh(&list->lock); + skb_queue_splice_tail_init(list, &tmp); spin_unlock_bh(&list->lock); - return rv; + tipc_skb_queue_splice_tail(&tmp, head); } #endif diff --git a/net/tipc/name_distr.c b/net/tipc/name_distr.c index 41e7b7e4dda0..e6018b7eb197 100644 --- a/net/tipc/name_distr.c +++ b/net/tipc/name_distr.c @@ -96,13 +96,13 @@ void named_cluster_distribute(struct net *net, struct sk_buff *skb) dnode = node->addr; if (in_own_node(net, dnode)) continue; - if (!tipc_node_active_links(node)) + if (!tipc_node_is_up(node)) continue; oskb = pskb_copy(skb, GFP_ATOMIC); if (!oskb) break; msg_set_destnode(buf_msg(oskb), dnode); - tipc_link_xmit_skb(net, oskb, dnode, dnode); + tipc_node_xmit_skb(net, oskb, dnode, dnode); } rcu_read_unlock(); @@ -223,7 +223,7 @@ void tipc_named_node_up(struct net *net, u32 dnode) &tn->nametbl->publ_list[TIPC_ZONE_SCOPE]); rcu_read_unlock(); - tipc_link_xmit(net, &head, dnode, dnode); + tipc_node_xmit(net, &head, dnode, dnode); } static void tipc_publ_subscribe(struct net *net, struct publication *publ, diff --git a/net/tipc/netlink_compat.c b/net/tipc/netlink_compat.c index 53e0fee80086..1eadc95e1132 100644 --- a/net/tipc/netlink_compat.c +++ b/net/tipc/netlink_compat.c @@ -1114,7 +1114,7 @@ static int tipc_nl_compat_recv(struct sk_buff *skb, struct genl_info *info) } len = nlmsg_attrlen(req_nlh, GENL_HDRLEN + TIPC_GENL_HDRLEN); - if (TLV_GET_LEN(msg.req) && !TLV_OK(msg.req, len)) { + if (len && !TLV_OK(msg.req, len)) { msg.rep = tipc_get_err_tlv(TIPC_CFG_NOT_SUPPORTED); err = -EOPNOTSUPP; goto send; diff --git a/net/tipc/node.c b/net/tipc/node.c index 0b1d61a5f853..703875fd6cde 100644 --- a/net/tipc/node.c +++ b/net/tipc/node.c @@ -40,10 +40,42 @@ #include "name_distr.h" #include "socket.h" #include "bcast.h" +#include "discover.h" -static void node_lost_contact(struct tipc_node *n_ptr); +/* Node FSM states and events: + */ +enum { + SELF_DOWN_PEER_DOWN = 0xdd, + SELF_UP_PEER_UP = 0xaa, + SELF_DOWN_PEER_LEAVING = 0xd1, + SELF_UP_PEER_COMING = 0xac, + SELF_COMING_PEER_UP = 0xca, + SELF_LEAVING_PEER_DOWN = 0x1d, + NODE_FAILINGOVER = 0xf0, + NODE_SYNCHING = 0xcc +}; + +enum { + SELF_ESTABL_CONTACT_EVT = 0xece, + SELF_LOST_CONTACT_EVT = 0x1ce, + PEER_ESTABL_CONTACT_EVT = 0x9ece, + PEER_LOST_CONTACT_EVT = 0x91ce, + NODE_FAILOVER_BEGIN_EVT = 0xfbe, + NODE_FAILOVER_END_EVT = 0xfee, + NODE_SYNCH_BEGIN_EVT = 0xcbe, + NODE_SYNCH_END_EVT = 0xcee +}; + +static void __tipc_node_link_down(struct tipc_node *n, int *bearer_id, + struct sk_buff_head *xmitq, + struct tipc_media_addr **maddr); +static void tipc_node_link_down(struct tipc_node *n, int bearer_id, + bool delete); +static void node_lost_contact(struct tipc_node *n, struct sk_buff_head *inputq); static void node_established_contact(struct tipc_node *n_ptr); static void tipc_node_delete(struct tipc_node *node); +static void tipc_node_timeout(unsigned long data); +static void tipc_node_fsm_evt(struct tipc_node *n, int evt); struct tipc_sock_conn { u32 port; @@ -110,7 +142,7 @@ struct tipc_node *tipc_node_find(struct net *net, u32 addr) return NULL; } -struct tipc_node *tipc_node_create(struct net *net, u32 addr) +struct tipc_node *tipc_node_create(struct net *net, u32 addr, u16 capabilities) { struct tipc_net *tn = net_generic(net, tipc_net_id); struct tipc_node *n_ptr, *temp_node; @@ -126,12 +158,14 @@ struct tipc_node *tipc_node_create(struct net *net, u32 addr) } n_ptr->addr = addr; n_ptr->net = net; + n_ptr->capabilities = capabilities; kref_init(&n_ptr->kref); spin_lock_init(&n_ptr->lock); INIT_HLIST_NODE(&n_ptr->hash); INIT_LIST_HEAD(&n_ptr->list); INIT_LIST_HEAD(&n_ptr->publ_list); INIT_LIST_HEAD(&n_ptr->conn_sks); + skb_queue_head_init(&n_ptr->bclink.namedq); __skb_queue_head_init(&n_ptr->bclink.deferdq); hlist_add_head_rcu(&n_ptr->hash, &tn->node_htable[tipc_hashfn(addr)]); list_for_each_entry_rcu(temp_node, &tn->node_list, list) { @@ -139,14 +173,32 @@ struct tipc_node *tipc_node_create(struct net *net, u32 addr) break; } list_add_tail_rcu(&n_ptr->list, &temp_node->list); - n_ptr->action_flags = TIPC_WAIT_PEER_LINKS_DOWN; + n_ptr->state = SELF_DOWN_PEER_LEAVING; n_ptr->signature = INVALID_NODE_SIG; + n_ptr->active_links[0] = INVALID_BEARER_ID; + n_ptr->active_links[1] = INVALID_BEARER_ID; tipc_node_get(n_ptr); + setup_timer(&n_ptr->timer, tipc_node_timeout, (unsigned long)n_ptr); + n_ptr->keepalive_intv = U32_MAX; exit: spin_unlock_bh(&tn->node_list_lock); return n_ptr; } +static void tipc_node_calculate_timer(struct tipc_node *n, struct tipc_link *l) +{ + unsigned long tol = l->tolerance; + unsigned long intv = ((tol / 4) > 500) ? 500 : tol / 4; + unsigned long keepalive_intv = msecs_to_jiffies(intv); + + /* Link with lowest tolerance determines timer interval */ + if (keepalive_intv < n->keepalive_intv) + n->keepalive_intv = keepalive_intv; + + /* Ensure link's abort limit corresponds to current interval */ + l->abort_limit = l->tolerance / jiffies_to_msecs(n->keepalive_intv); +} + static void tipc_node_delete(struct tipc_node *node) { list_del_rcu(&node->list); @@ -160,8 +212,11 @@ void tipc_node_stop(struct net *net) struct tipc_node *node, *t_node; spin_lock_bh(&tn->node_list_lock); - list_for_each_entry_safe(node, t_node, &tn->node_list, list) + list_for_each_entry_safe(node, t_node, &tn->node_list, list) { + if (del_timer(&node->timer)) + tipc_node_put(node); tipc_node_put(node); + } spin_unlock_bh(&tn->node_list_lock); } @@ -219,158 +274,551 @@ void tipc_node_remove_conn(struct net *net, u32 dnode, u32 port) tipc_node_put(node); } +/* tipc_node_timeout - handle expiration of node timer + */ +static void tipc_node_timeout(unsigned long data) +{ + struct tipc_node *n = (struct tipc_node *)data; + struct tipc_link_entry *le; + struct sk_buff_head xmitq; + int bearer_id; + int rc = 0; + + __skb_queue_head_init(&xmitq); + + for (bearer_id = 0; bearer_id < MAX_BEARERS; bearer_id++) { + tipc_node_lock(n); + le = &n->links[bearer_id]; + if (le->link) { + /* Link tolerance may change asynchronously: */ + tipc_node_calculate_timer(n, le->link); + rc = tipc_link_timeout(le->link, &xmitq); + } + tipc_node_unlock(n); + tipc_bearer_xmit(n->net, bearer_id, &xmitq, &le->maddr); + if (rc & TIPC_LINK_DOWN_EVT) + tipc_node_link_down(n, bearer_id, false); + } + if (!mod_timer(&n->timer, jiffies + n->keepalive_intv)) + tipc_node_get(n); + tipc_node_put(n); +} + /** - * tipc_node_link_up - handle addition of link - * + * __tipc_node_link_up - handle addition of link + * Node lock must be held by caller * Link becomes active (alone or shared) or standby, depending on its priority. */ -void tipc_node_link_up(struct tipc_node *n_ptr, struct tipc_link *l_ptr) +static void __tipc_node_link_up(struct tipc_node *n, int bearer_id, + struct sk_buff_head *xmitq) { - struct tipc_link **active = &n_ptr->active_links[0]; + int *slot0 = &n->active_links[0]; + int *slot1 = &n->active_links[1]; + struct tipc_link *ol = node_active_link(n, 0); + struct tipc_link *nl = n->links[bearer_id].link; - n_ptr->working_links++; - n_ptr->action_flags |= TIPC_NOTIFY_LINK_UP; - n_ptr->link_id = l_ptr->peer_bearer_id << 16 | l_ptr->bearer_id; + if (!nl || !tipc_link_is_up(nl)) + return; - pr_debug("Established link <%s> on network plane %c\n", - l_ptr->name, l_ptr->net_plane); + n->working_links++; + n->action_flags |= TIPC_NOTIFY_LINK_UP; + n->link_id = nl->peer_bearer_id << 16 | bearer_id; - if (!active[0]) { - active[0] = active[1] = l_ptr; - node_established_contact(n_ptr); - goto exit; - } - if (l_ptr->priority < active[0]->priority) { - pr_debug("New link <%s> becomes standby\n", l_ptr->name); - goto exit; + /* Leave room for tunnel header when returning 'mtu' to users: */ + n->links[bearer_id].mtu = nl->mtu - INT_H_SIZE; + + tipc_bearer_add_dest(n->net, bearer_id, n->addr); + + pr_debug("Established link <%s> on network plane %c\n", + nl->name, nl->net_plane); + + /* First link? => give it both slots */ + if (!ol) { + *slot0 = bearer_id; + *slot1 = bearer_id; + tipc_link_build_bcast_sync_msg(nl, xmitq); + node_established_contact(n); + return; } - tipc_link_dup_queue_xmit(active[0], l_ptr); - if (l_ptr->priority == active[0]->priority) { - active[0] = l_ptr; - goto exit; + + /* Second link => redistribute slots */ + if (nl->priority > ol->priority) { + pr_debug("Old link <%s> becomes standby\n", ol->name); + *slot0 = bearer_id; + *slot1 = bearer_id; + } else if (nl->priority == ol->priority) { + *slot0 = bearer_id; + } else { + pr_debug("New link <%s> is standby\n", nl->name); } - pr_debug("Old link <%s> becomes standby\n", active[0]->name); - if (active[1] != active[0]) - pr_debug("Old link <%s> becomes standby\n", active[1]->name); - active[0] = active[1] = l_ptr; -exit: - /* Leave room for changeover header when returning 'mtu' to users: */ - n_ptr->act_mtus[0] = active[0]->mtu - INT_H_SIZE; - n_ptr->act_mtus[1] = active[1]->mtu - INT_H_SIZE; + + /* Prepare synchronization with first link */ + tipc_link_tnl_prepare(ol, nl, SYNCH_MSG, xmitq); } /** - * node_select_active_links - select active link + * tipc_node_link_up - handle addition of link + * + * Link becomes active (alone or shared) or standby, depending on its priority. */ -static void node_select_active_links(struct tipc_node *n_ptr) +static void tipc_node_link_up(struct tipc_node *n, int bearer_id, + struct sk_buff_head *xmitq) { - struct tipc_link **active = &n_ptr->active_links[0]; - u32 i; - u32 highest_prio = 0; + tipc_node_lock(n); + __tipc_node_link_up(n, bearer_id, xmitq); + tipc_node_unlock(n); +} - active[0] = active[1] = NULL; +/** + * __tipc_node_link_down - handle loss of link + */ +static void __tipc_node_link_down(struct tipc_node *n, int *bearer_id, + struct sk_buff_head *xmitq, + struct tipc_media_addr **maddr) +{ + struct tipc_link_entry *le = &n->links[*bearer_id]; + int *slot0 = &n->active_links[0]; + int *slot1 = &n->active_links[1]; + int i, highest = 0; + struct tipc_link *l, *_l, *tnl; + + l = n->links[*bearer_id].link; + if (!l || tipc_link_is_reset(l)) + return; - for (i = 0; i < MAX_BEARERS; i++) { - struct tipc_link *l_ptr = n_ptr->links[i]; + n->working_links--; + n->action_flags |= TIPC_NOTIFY_LINK_DOWN; + n->link_id = l->peer_bearer_id << 16 | *bearer_id; - if (!l_ptr || !tipc_link_is_up(l_ptr) || - (l_ptr->priority < highest_prio)) - continue; + tipc_bearer_remove_dest(n->net, *bearer_id, n->addr); - if (l_ptr->priority > highest_prio) { - highest_prio = l_ptr->priority; - active[0] = active[1] = l_ptr; - } else { - active[1] = l_ptr; + pr_debug("Lost link <%s> on network plane %c\n", + l->name, l->net_plane); + + /* Select new active link if any available */ + *slot0 = INVALID_BEARER_ID; + *slot1 = INVALID_BEARER_ID; + for (i = 0; i < MAX_BEARERS; i++) { + _l = n->links[i].link; + if (!_l || !tipc_link_is_up(_l)) + continue; + if (_l == l) + continue; + if (_l->priority < highest) + continue; + if (_l->priority > highest) { + highest = _l->priority; + *slot0 = i; + *slot1 = i; + continue; } + *slot1 = i; + } + + if (!tipc_node_is_up(n)) { + tipc_link_reset(l); + node_lost_contact(n, &le->inputq); + return; } + + /* There is still a working link => initiate failover */ + tnl = node_active_link(n, 0); + tipc_link_fsm_evt(tnl, LINK_SYNCH_END_EVT); + tipc_node_fsm_evt(n, NODE_SYNCH_END_EVT); + n->sync_point = tnl->rcv_nxt + (U16_MAX / 2 - 1); + tipc_link_tnl_prepare(l, tnl, FAILOVER_MSG, xmitq); + tipc_link_reset(l); + tipc_link_fsm_evt(l, LINK_FAILOVER_BEGIN_EVT); + tipc_node_fsm_evt(n, NODE_FAILOVER_BEGIN_EVT); + *maddr = &n->links[tnl->bearer_id].maddr; + *bearer_id = tnl->bearer_id; } -/** - * tipc_node_link_down - handle loss of link - */ -void tipc_node_link_down(struct tipc_node *n_ptr, struct tipc_link *l_ptr) +static void tipc_node_link_down(struct tipc_node *n, int bearer_id, bool delete) { - struct tipc_net *tn = net_generic(n_ptr->net, tipc_net_id); - struct tipc_link **active; + struct tipc_link_entry *le = &n->links[bearer_id]; + struct tipc_media_addr *maddr; + struct sk_buff_head xmitq; + + __skb_queue_head_init(&xmitq); + + tipc_node_lock(n); + __tipc_node_link_down(n, &bearer_id, &xmitq, &maddr); + if (delete && le->link) { + kfree(le->link); + le->link = NULL; + n->link_cnt--; + } + tipc_node_unlock(n); - n_ptr->working_links--; - n_ptr->action_flags |= TIPC_NOTIFY_LINK_DOWN; - n_ptr->link_id = l_ptr->peer_bearer_id << 16 | l_ptr->bearer_id; + tipc_bearer_xmit(n->net, bearer_id, &xmitq, maddr); + tipc_sk_rcv(n->net, &le->inputq); +} - if (!tipc_link_is_active(l_ptr)) { - pr_debug("Lost standby link <%s> on network plane %c\n", - l_ptr->name, l_ptr->net_plane); - return; - } - pr_debug("Lost link <%s> on network plane %c\n", - l_ptr->name, l_ptr->net_plane); - - active = &n_ptr->active_links[0]; - if (active[0] == l_ptr) - active[0] = active[1]; - if (active[1] == l_ptr) - active[1] = active[0]; - if (active[0] == l_ptr) - node_select_active_links(n_ptr); - if (tipc_node_is_up(n_ptr)) - tipc_link_failover_send_queue(l_ptr); - else - node_lost_contact(n_ptr); - - /* Leave room for changeover header when returning 'mtu' to users: */ - if (active[0]) { - n_ptr->act_mtus[0] = active[0]->mtu - INT_H_SIZE; - n_ptr->act_mtus[1] = active[1]->mtu - INT_H_SIZE; +bool tipc_node_is_up(struct tipc_node *n) +{ + return n->active_links[0] != INVALID_BEARER_ID; +} + +void tipc_node_check_dest(struct net *net, u32 onode, + struct tipc_bearer *b, + u16 capabilities, u32 signature, + struct tipc_media_addr *maddr, + bool *respond, bool *dupl_addr) +{ + struct tipc_node *n; + struct tipc_link *l; + struct tipc_link_entry *le; + bool addr_match = false; + bool sign_match = false; + bool link_up = false; + bool accept_addr = false; + bool reset = true; + + *dupl_addr = false; + *respond = false; + + n = tipc_node_create(net, onode, capabilities); + if (!n) return; + + tipc_node_lock(n); + + le = &n->links[b->identity]; + + /* Prepare to validate requesting node's signature and media address */ + l = le->link; + link_up = l && tipc_link_is_up(l); + addr_match = l && !memcmp(&le->maddr, maddr, sizeof(*maddr)); + sign_match = (signature == n->signature); + + /* These three flags give us eight permutations: */ + + if (sign_match && addr_match && link_up) { + /* All is fine. Do nothing. */ + reset = false; + } else if (sign_match && addr_match && !link_up) { + /* Respond. The link will come up in due time */ + *respond = true; + } else if (sign_match && !addr_match && link_up) { + /* Peer has changed i/f address without rebooting. + * If so, the link will reset soon, and the next + * discovery will be accepted. So we can ignore it. + * It may also be an cloned or malicious peer having + * chosen the same node address and signature as an + * existing one. + * Ignore requests until the link goes down, if ever. + */ + *dupl_addr = true; + } else if (sign_match && !addr_match && !link_up) { + /* Peer link has changed i/f address without rebooting. + * It may also be a cloned or malicious peer; we can't + * distinguish between the two. + * The signature is correct, so we must accept. + */ + accept_addr = true; + *respond = true; + } else if (!sign_match && addr_match && link_up) { + /* Peer node rebooted. Two possibilities: + * - Delayed re-discovery; this link endpoint has already + * reset and re-established contact with the peer, before + * receiving a discovery message from that node. + * (The peer happened to receive one from this node first). + * - The peer came back so fast that our side has not + * discovered it yet. Probing from this side will soon + * reset the link, since there can be no working link + * endpoint at the peer end, and the link will re-establish. + * Accept the signature, since it comes from a known peer. + */ + n->signature = signature; + } else if (!sign_match && addr_match && !link_up) { + /* The peer node has rebooted. + * Accept signature, since it is a known peer. + */ + n->signature = signature; + *respond = true; + } else if (!sign_match && !addr_match && link_up) { + /* Peer rebooted with new address, or a new/duplicate peer. + * Ignore until the link goes down, if ever. + */ + *dupl_addr = true; + } else if (!sign_match && !addr_match && !link_up) { + /* Peer rebooted with new address, or it is a new peer. + * Accept signature and address. + */ + n->signature = signature; + accept_addr = true; + *respond = true; } - /* Loopback link went down? No fragmentation needed from now on. */ - if (n_ptr->addr == tn->own_addr) { - n_ptr->act_mtus[0] = MAX_MSG_SIZE; - n_ptr->act_mtus[1] = MAX_MSG_SIZE; + + if (!accept_addr) + goto exit; + + /* Now create new link if not already existing */ + if (!l) { + if (n->link_cnt == 2) { + pr_warn("Cannot establish 3rd link to %x\n", n->addr); + goto exit; + } + if (!tipc_link_create(n, b, mod(tipc_net(net)->random), + tipc_own_addr(net), onode, &le->maddr, + &le->inputq, &n->bclink.namedq, &l)) { + *respond = false; + goto exit; + } + tipc_link_reset(l); + if (n->state == NODE_FAILINGOVER) + tipc_link_fsm_evt(l, LINK_FAILOVER_BEGIN_EVT); + le->link = l; + n->link_cnt++; + tipc_node_calculate_timer(n, l); + if (n->link_cnt == 1) + if (!mod_timer(&n->timer, jiffies + n->keepalive_intv)) + tipc_node_get(n); } + memcpy(&le->maddr, maddr, sizeof(*maddr)); +exit: + tipc_node_unlock(n); + if (reset) + tipc_node_link_down(n, b->identity, false); + tipc_node_put(n); } -int tipc_node_active_links(struct tipc_node *n_ptr) +void tipc_node_delete_links(struct net *net, int bearer_id) { - return n_ptr->active_links[0] != NULL; + struct tipc_net *tn = net_generic(net, tipc_net_id); + struct tipc_node *n; + + rcu_read_lock(); + list_for_each_entry_rcu(n, &tn->node_list, list) { + tipc_node_link_down(n, bearer_id, true); + } + rcu_read_unlock(); } -int tipc_node_is_up(struct tipc_node *n_ptr) +static void tipc_node_reset_links(struct tipc_node *n) { - return tipc_node_active_links(n_ptr); + char addr_string[16]; + int i; + + pr_warn("Resetting all links to %s\n", + tipc_addr_string_fill(addr_string, n->addr)); + + for (i = 0; i < MAX_BEARERS; i++) { + tipc_node_link_down(n, i, false); + } } -void tipc_node_attach_link(struct tipc_node *n_ptr, struct tipc_link *l_ptr) +/* tipc_node_fsm_evt - node finite state machine + * Determines when contact is allowed with peer node + */ +static void tipc_node_fsm_evt(struct tipc_node *n, int evt) { - n_ptr->links[l_ptr->bearer_id] = l_ptr; - n_ptr->link_cnt++; + int state = n->state; + + switch (state) { + case SELF_DOWN_PEER_DOWN: + switch (evt) { + case SELF_ESTABL_CONTACT_EVT: + state = SELF_UP_PEER_COMING; + break; + case PEER_ESTABL_CONTACT_EVT: + state = SELF_COMING_PEER_UP; + break; + case SELF_LOST_CONTACT_EVT: + case PEER_LOST_CONTACT_EVT: + break; + case NODE_SYNCH_END_EVT: + case NODE_SYNCH_BEGIN_EVT: + case NODE_FAILOVER_BEGIN_EVT: + case NODE_FAILOVER_END_EVT: + default: + goto illegal_evt; + } + break; + case SELF_UP_PEER_UP: + switch (evt) { + case SELF_LOST_CONTACT_EVT: + state = SELF_DOWN_PEER_LEAVING; + break; + case PEER_LOST_CONTACT_EVT: + state = SELF_LEAVING_PEER_DOWN; + break; + case NODE_SYNCH_BEGIN_EVT: + state = NODE_SYNCHING; + break; + case NODE_FAILOVER_BEGIN_EVT: + state = NODE_FAILINGOVER; + break; + case SELF_ESTABL_CONTACT_EVT: + case PEER_ESTABL_CONTACT_EVT: + case NODE_SYNCH_END_EVT: + case NODE_FAILOVER_END_EVT: + break; + default: + goto illegal_evt; + } + break; + case SELF_DOWN_PEER_LEAVING: + switch (evt) { + case PEER_LOST_CONTACT_EVT: + state = SELF_DOWN_PEER_DOWN; + break; + case SELF_ESTABL_CONTACT_EVT: + case PEER_ESTABL_CONTACT_EVT: + case SELF_LOST_CONTACT_EVT: + break; + case NODE_SYNCH_END_EVT: + case NODE_SYNCH_BEGIN_EVT: + case NODE_FAILOVER_BEGIN_EVT: + case NODE_FAILOVER_END_EVT: + default: + goto illegal_evt; + } + break; + case SELF_UP_PEER_COMING: + switch (evt) { + case PEER_ESTABL_CONTACT_EVT: + state = SELF_UP_PEER_UP; + break; + case SELF_LOST_CONTACT_EVT: + state = SELF_DOWN_PEER_LEAVING; + break; + case SELF_ESTABL_CONTACT_EVT: + case PEER_LOST_CONTACT_EVT: + break; + case NODE_SYNCH_END_EVT: + case NODE_SYNCH_BEGIN_EVT: + case NODE_FAILOVER_BEGIN_EVT: + case NODE_FAILOVER_END_EVT: + default: + goto illegal_evt; + } + break; + case SELF_COMING_PEER_UP: + switch (evt) { + case SELF_ESTABL_CONTACT_EVT: + state = SELF_UP_PEER_UP; + break; + case PEER_LOST_CONTACT_EVT: + state = SELF_LEAVING_PEER_DOWN; + break; + case SELF_LOST_CONTACT_EVT: + case PEER_ESTABL_CONTACT_EVT: + break; + case NODE_SYNCH_END_EVT: + case NODE_SYNCH_BEGIN_EVT: + case NODE_FAILOVER_BEGIN_EVT: + case NODE_FAILOVER_END_EVT: + default: + goto illegal_evt; + } + break; + case SELF_LEAVING_PEER_DOWN: + switch (evt) { + case SELF_LOST_CONTACT_EVT: + state = SELF_DOWN_PEER_DOWN; + break; + case SELF_ESTABL_CONTACT_EVT: + case PEER_ESTABL_CONTACT_EVT: + case PEER_LOST_CONTACT_EVT: + break; + case NODE_SYNCH_END_EVT: + case NODE_SYNCH_BEGIN_EVT: + case NODE_FAILOVER_BEGIN_EVT: + case NODE_FAILOVER_END_EVT: + default: + goto illegal_evt; + } + break; + case NODE_FAILINGOVER: + switch (evt) { + case SELF_LOST_CONTACT_EVT: + state = SELF_DOWN_PEER_LEAVING; + break; + case PEER_LOST_CONTACT_EVT: + state = SELF_LEAVING_PEER_DOWN; + break; + case NODE_FAILOVER_END_EVT: + state = SELF_UP_PEER_UP; + break; + case NODE_FAILOVER_BEGIN_EVT: + case SELF_ESTABL_CONTACT_EVT: + case PEER_ESTABL_CONTACT_EVT: + break; + case NODE_SYNCH_BEGIN_EVT: + case NODE_SYNCH_END_EVT: + default: + goto illegal_evt; + } + break; + case NODE_SYNCHING: + switch (evt) { + case SELF_LOST_CONTACT_EVT: + state = SELF_DOWN_PEER_LEAVING; + break; + case PEER_LOST_CONTACT_EVT: + state = SELF_LEAVING_PEER_DOWN; + break; + case NODE_SYNCH_END_EVT: + state = SELF_UP_PEER_UP; + break; + case NODE_FAILOVER_BEGIN_EVT: + state = NODE_FAILINGOVER; + break; + case NODE_SYNCH_BEGIN_EVT: + case SELF_ESTABL_CONTACT_EVT: + case PEER_ESTABL_CONTACT_EVT: + break; + case NODE_FAILOVER_END_EVT: + default: + goto illegal_evt; + } + break; + default: + pr_err("Unknown node fsm state %x\n", state); + break; + } + n->state = state; + return; + +illegal_evt: + pr_err("Illegal node fsm evt %x in state %x\n", evt, state); } -void tipc_node_detach_link(struct tipc_node *n_ptr, struct tipc_link *l_ptr) +bool tipc_node_filter_pkt(struct tipc_node *n, struct tipc_msg *hdr) { - int i; + int state = n->state; - for (i = 0; i < MAX_BEARERS; i++) { - if (l_ptr != n_ptr->links[i]) - continue; - n_ptr->links[i] = NULL; - n_ptr->link_cnt--; + if (likely(state == SELF_UP_PEER_UP)) + return true; + + if (state == SELF_LEAVING_PEER_DOWN) + return false; + + if (state == SELF_DOWN_PEER_LEAVING) { + if (msg_peer_node_is_up(hdr)) + return false; } + + return true; } static void node_established_contact(struct tipc_node *n_ptr) { + tipc_node_fsm_evt(n_ptr, SELF_ESTABL_CONTACT_EVT); n_ptr->action_flags |= TIPC_NOTIFY_NODE_UP; n_ptr->bclink.oos_state = 0; n_ptr->bclink.acked = tipc_bclink_get_last_sent(n_ptr->net); tipc_bclink_add_node(n_ptr->net, n_ptr->addr); } -static void node_lost_contact(struct tipc_node *n_ptr) +static void node_lost_contact(struct tipc_node *n_ptr, + struct sk_buff_head *inputq) { char addr_string[16]; struct tipc_sock_conn *conn, *safe; + struct tipc_link *l; struct list_head *conns = &n_ptr->conn_sks; struct sk_buff *skb; struct tipc_net *tn = net_generic(n_ptr->net, tipc_net_id); @@ -396,21 +844,13 @@ static void node_lost_contact(struct tipc_node *n_ptr) /* Abort any ongoing link failover */ for (i = 0; i < MAX_BEARERS; i++) { - struct tipc_link *l_ptr = n_ptr->links[i]; - if (!l_ptr) - continue; - l_ptr->flags &= ~LINK_FAILINGOVER; - l_ptr->failover_checkpt = 0; - l_ptr->failover_pkts = 0; - kfree_skb(l_ptr->failover_skb); - l_ptr->failover_skb = NULL; - tipc_link_reset_fragments(l_ptr); + l = n_ptr->links[i].link; + if (l) + tipc_link_fsm_evt(l, LINK_FAILOVER_END_EVT); } - n_ptr->action_flags &= ~TIPC_WAIT_OWN_LINKS_DOWN; - /* Prevent re-contact with node until cleanup is done */ - n_ptr->action_flags |= TIPC_WAIT_PEER_LINKS_DOWN; + tipc_node_fsm_evt(n_ptr, SELF_LOST_CONTACT_EVT); /* Notify publications from this node */ n_ptr->action_flags |= TIPC_NOTIFY_NODE_DOWN; @@ -421,10 +861,8 @@ static void node_lost_contact(struct tipc_node *n_ptr) SHORT_H_SIZE, 0, tn->own_addr, conn->peer_node, conn->port, conn->peer_port, TIPC_ERR_NO_NODE); - if (likely(skb)) { - skb_queue_tail(n_ptr->inputq, skb); - n_ptr->action_flags |= TIPC_MSG_EVT; - } + if (likely(skb)) + skb_queue_tail(inputq, skb); list_del(&conn->list); kfree(conn); } @@ -453,7 +891,7 @@ int tipc_node_get_linkname(struct net *net, u32 bearer_id, u32 addr, goto exit; tipc_node_lock(node); - link = node->links[bearer_id]; + link = node->links[bearer_id].link; if (link) { strncpy(linkname, link->name, len); err = 0; @@ -471,27 +909,20 @@ void tipc_node_unlock(struct tipc_node *node) u32 flags = node->action_flags; u32 link_id = 0; struct list_head *publ_list; - struct sk_buff_head *inputq = node->inputq; - struct sk_buff_head *namedq; - if (likely(!flags || (flags == TIPC_MSG_EVT))) { - node->action_flags = 0; + if (likely(!flags)) { spin_unlock_bh(&node->lock); - if (flags == TIPC_MSG_EVT) - tipc_sk_rcv(net, inputq); return; } addr = node->addr; link_id = node->link_id; - namedq = node->namedq; publ_list = &node->publ_list; - node->action_flags &= ~(TIPC_MSG_EVT | - TIPC_NOTIFY_NODE_DOWN | TIPC_NOTIFY_NODE_UP | + node->action_flags &= ~(TIPC_NOTIFY_NODE_DOWN | TIPC_NOTIFY_NODE_UP | TIPC_NOTIFY_LINK_DOWN | TIPC_NOTIFY_LINK_UP | TIPC_WAKEUP_BCAST_USERS | TIPC_BCAST_MSG_EVT | - TIPC_NAMED_MSG_EVT | TIPC_BCAST_RESET); + TIPC_BCAST_RESET); spin_unlock_bh(&node->lock); @@ -512,17 +943,11 @@ void tipc_node_unlock(struct tipc_node *node) tipc_nametbl_withdraw(net, TIPC_LINK_STATE, addr, link_id, addr); - if (flags & TIPC_MSG_EVT) - tipc_sk_rcv(net, inputq); - - if (flags & TIPC_NAMED_MSG_EVT) - tipc_named_rcv(net, namedq); - if (flags & TIPC_BCAST_MSG_EVT) tipc_bclink_input(net); if (flags & TIPC_BCAST_RESET) - tipc_link_reset_all(node); + tipc_node_reset_links(node); } /* Caller should hold node lock for the passed node */ @@ -559,6 +984,290 @@ msg_full: return -EMSGSIZE; } +static struct tipc_link *tipc_node_select_link(struct tipc_node *n, int sel, + int *bearer_id, + struct tipc_media_addr **maddr) +{ + int id = n->active_links[sel & 1]; + + if (unlikely(id < 0)) + return NULL; + + *bearer_id = id; + *maddr = &n->links[id].maddr; + return n->links[id].link; +} + +/** + * tipc_node_xmit() is the general link level function for message sending + * @net: the applicable net namespace + * @list: chain of buffers containing message + * @dnode: address of destination node + * @selector: a number used for deterministic link selection + * Consumes the buffer chain, except when returning -ELINKCONG + * Returns 0 if success, otherwise errno: -ELINKCONG,-EHOSTUNREACH,-EMSGSIZE + */ +int tipc_node_xmit(struct net *net, struct sk_buff_head *list, + u32 dnode, int selector) +{ + struct tipc_link *l = NULL; + struct tipc_node *n; + struct sk_buff_head xmitq; + struct tipc_media_addr *maddr; + int bearer_id; + int rc = -EHOSTUNREACH; + + __skb_queue_head_init(&xmitq); + n = tipc_node_find(net, dnode); + if (likely(n)) { + tipc_node_lock(n); + l = tipc_node_select_link(n, selector, &bearer_id, &maddr); + if (likely(l)) + rc = tipc_link_xmit(l, list, &xmitq); + tipc_node_unlock(n); + if (unlikely(rc == -ENOBUFS)) + tipc_node_link_down(n, bearer_id, false); + tipc_node_put(n); + } + if (likely(!rc)) { + tipc_bearer_xmit(net, bearer_id, &xmitq, maddr); + return 0; + } + if (likely(in_own_node(net, dnode))) { + tipc_sk_rcv(net, list); + return 0; + } + return rc; +} + +/* tipc_node_xmit_skb(): send single buffer to destination + * Buffers sent via this functon are generally TIPC_SYSTEM_IMPORTANCE + * messages, which will not be rejected + * The only exception is datagram messages rerouted after secondary + * lookup, which are rare and safe to dispose of anyway. + * TODO: Return real return value, and let callers use + * tipc_wait_for_sendpkt() where applicable + */ +int tipc_node_xmit_skb(struct net *net, struct sk_buff *skb, u32 dnode, + u32 selector) +{ + struct sk_buff_head head; + int rc; + + skb_queue_head_init(&head); + __skb_queue_tail(&head, skb); + rc = tipc_node_xmit(net, &head, dnode, selector); + if (rc == -ELINKCONG) + kfree_skb(skb); + return 0; +} + +/** + * tipc_node_check_state - check and if necessary update node state + * @skb: TIPC packet + * @bearer_id: identity of bearer delivering the packet + * Returns true if state is ok, otherwise consumes buffer and returns false + */ +static bool tipc_node_check_state(struct tipc_node *n, struct sk_buff *skb, + int bearer_id, struct sk_buff_head *xmitq) +{ + struct tipc_msg *hdr = buf_msg(skb); + int usr = msg_user(hdr); + int mtyp = msg_type(hdr); + u16 oseqno = msg_seqno(hdr); + u16 iseqno = msg_seqno(msg_get_wrapped(hdr)); + u16 exp_pkts = msg_msgcnt(hdr); + u16 rcv_nxt, syncpt, dlv_nxt; + int state = n->state; + struct tipc_link *l, *tnl, *pl = NULL; + struct tipc_media_addr *maddr; + int i, pb_id; + + l = n->links[bearer_id].link; + if (!l) + return false; + rcv_nxt = l->rcv_nxt; + + + if (likely((state == SELF_UP_PEER_UP) && (usr != TUNNEL_PROTOCOL))) + return true; + + /* Find parallel link, if any */ + for (i = 0; i < MAX_BEARERS; i++) { + if ((i != bearer_id) && n->links[i].link) { + pl = n->links[i].link; + break; + } + } + + /* Update node accesibility if applicable */ + if (state == SELF_UP_PEER_COMING) { + if (!tipc_link_is_up(l)) + return true; + if (!msg_peer_link_is_up(hdr)) + return true; + tipc_node_fsm_evt(n, PEER_ESTABL_CONTACT_EVT); + } + + if (state == SELF_DOWN_PEER_LEAVING) { + if (msg_peer_node_is_up(hdr)) + return false; + tipc_node_fsm_evt(n, PEER_LOST_CONTACT_EVT); + } + + /* Ignore duplicate packets */ + if (less(oseqno, rcv_nxt)) + return true; + + /* Initiate or update failover mode if applicable */ + if ((usr == TUNNEL_PROTOCOL) && (mtyp == FAILOVER_MSG)) { + syncpt = oseqno + exp_pkts - 1; + if (pl && tipc_link_is_up(pl)) { + pb_id = pl->bearer_id; + __tipc_node_link_down(n, &pb_id, xmitq, &maddr); + tipc_skb_queue_splice_tail_init(pl->inputq, l->inputq); + } + /* If pkts arrive out of order, use lowest calculated syncpt */ + if (less(syncpt, n->sync_point)) + n->sync_point = syncpt; + } + + /* Open parallel link when tunnel link reaches synch point */ + if ((n->state == NODE_FAILINGOVER) && tipc_link_is_up(l)) { + if (!more(rcv_nxt, n->sync_point)) + return true; + tipc_node_fsm_evt(n, NODE_FAILOVER_END_EVT); + if (pl) + tipc_link_fsm_evt(pl, LINK_FAILOVER_END_EVT); + return true; + } + + /* No synching needed if only one link */ + if (!pl || !tipc_link_is_up(pl)) + return true; + + /* Initiate or update synch mode if applicable */ + if ((usr == TUNNEL_PROTOCOL) && (mtyp == SYNCH_MSG)) { + syncpt = iseqno + exp_pkts - 1; + if (!tipc_link_is_up(l)) { + tipc_link_fsm_evt(l, LINK_ESTABLISH_EVT); + __tipc_node_link_up(n, bearer_id, xmitq); + } + if (n->state == SELF_UP_PEER_UP) { + n->sync_point = syncpt; + tipc_link_fsm_evt(l, LINK_SYNCH_BEGIN_EVT); + tipc_node_fsm_evt(n, NODE_SYNCH_BEGIN_EVT); + } + if (less(syncpt, n->sync_point)) + n->sync_point = syncpt; + } + + /* Open tunnel link when parallel link reaches synch point */ + if ((n->state == NODE_SYNCHING) && tipc_link_is_synching(l)) { + if (tipc_link_is_synching(l)) { + tnl = l; + } else { + tnl = pl; + pl = l; + } + dlv_nxt = pl->rcv_nxt - mod(skb_queue_len(pl->inputq)); + if (more(dlv_nxt, n->sync_point)) { + tipc_link_fsm_evt(tnl, LINK_SYNCH_END_EVT); + tipc_node_fsm_evt(n, NODE_SYNCH_END_EVT); + return true; + } + if (l == pl) + return true; + if ((usr == TUNNEL_PROTOCOL) && (mtyp == SYNCH_MSG)) + return true; + if (usr == LINK_PROTOCOL) + return true; + return false; + } + return true; +} + +/** + * tipc_rcv - process TIPC packets/messages arriving from off-node + * @net: the applicable net namespace + * @skb: TIPC packet + * @bearer: pointer to bearer message arrived on + * + * Invoked with no locks held. Bearer pointer must point to a valid bearer + * structure (i.e. cannot be NULL), but bearer can be inactive. + */ +void tipc_rcv(struct net *net, struct sk_buff *skb, struct tipc_bearer *b) +{ + struct sk_buff_head xmitq; + struct tipc_node *n; + struct tipc_msg *hdr = buf_msg(skb); + int usr = msg_user(hdr); + int bearer_id = b->identity; + struct tipc_link_entry *le; + int rc = 0; + + __skb_queue_head_init(&xmitq); + + /* Ensure message is well-formed */ + if (unlikely(!tipc_msg_validate(skb))) + goto discard; + + /* Handle arrival of a non-unicast link packet */ + if (unlikely(msg_non_seq(hdr))) { + if (usr == LINK_CONFIG) + tipc_disc_rcv(net, skb, b); + else + tipc_bclink_rcv(net, skb); + return; + } + + /* Locate neighboring node that sent packet */ + n = tipc_node_find(net, msg_prevnode(hdr)); + if (unlikely(!n)) + goto discard; + le = &n->links[bearer_id]; + + tipc_node_lock(n); + + /* Is reception permitted at the moment ? */ + if (!tipc_node_filter_pkt(n, hdr)) + goto unlock; + + if (unlikely(msg_user(hdr) == LINK_PROTOCOL)) + tipc_bclink_sync_state(n, hdr); + + /* Release acked broadcast packets */ + if (unlikely(n->bclink.acked != msg_bcast_ack(hdr))) + tipc_bclink_acknowledge(n, msg_bcast_ack(hdr)); + + /* Check and if necessary update node state */ + if (likely(tipc_node_check_state(n, skb, bearer_id, &xmitq))) { + rc = tipc_link_rcv(le->link, skb, &xmitq); + skb = NULL; + } +unlock: + tipc_node_unlock(n); + + if (unlikely(rc & TIPC_LINK_UP_EVT)) + tipc_node_link_up(n, bearer_id, &xmitq); + + if (unlikely(rc & TIPC_LINK_DOWN_EVT)) + tipc_node_link_down(n, bearer_id, false); + + if (unlikely(!skb_queue_empty(&n->bclink.namedq))) + tipc_named_rcv(net, &n->bclink.namedq); + + if (!skb_queue_empty(&le->inputq)) + tipc_sk_rcv(net, &le->inputq); + + if (!skb_queue_empty(&xmitq)) + tipc_bearer_xmit(net, bearer_id, &xmitq, &le->maddr); + + tipc_node_put(n); +discard: + kfree_skb(skb); +} + 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 5a834cf142c8..344b3e7594fd 100644 --- a/net/tipc/node.h +++ b/net/tipc/node.h @@ -45,23 +45,19 @@ /* Out-of-range value for node signature */ #define INVALID_NODE_SIG 0x10000 +#define INVALID_BEARER_ID -1 + /* Flags used to take different actions according to flag type - * TIPC_WAIT_PEER_LINKS_DOWN: wait to see that peer's links are down - * TIPC_WAIT_OWN_LINKS_DOWN: wait until peer node is declared down * TIPC_NOTIFY_NODE_DOWN: notify node is down * TIPC_NOTIFY_NODE_UP: notify node is up * TIPC_DISTRIBUTE_NAME: publish or withdraw link state name type */ enum { - TIPC_MSG_EVT = 1, - TIPC_WAIT_PEER_LINKS_DOWN = (1 << 1), - TIPC_WAIT_OWN_LINKS_DOWN = (1 << 2), TIPC_NOTIFY_NODE_DOWN = (1 << 3), TIPC_NOTIFY_NODE_UP = (1 << 4), TIPC_WAKEUP_BCAST_USERS = (1 << 5), TIPC_NOTIFY_LINK_UP = (1 << 6), TIPC_NOTIFY_LINK_DOWN = (1 << 7), - TIPC_NAMED_MSG_EVT = (1 << 8), TIPC_BCAST_MSG_EVT = (1 << 9), TIPC_BCAST_RESET = (1 << 10) }; @@ -85,10 +81,17 @@ struct tipc_node_bclink { u32 deferred_size; struct sk_buff_head deferdq; struct sk_buff *reasm_buf; - int inputq_map; + struct sk_buff_head namedq; bool recv_permitted; }; +struct tipc_link_entry { + struct tipc_link *link; + u32 mtu; + struct sk_buff_head inputq; + struct tipc_media_addr maddr; +}; + /** * struct tipc_node - TIPC node structure * @addr: network address of node @@ -98,11 +101,12 @@ struct tipc_node_bclink { * @hash: links to adjacent nodes in unsorted hash chain * @inputq: pointer to input queue containing messages for msg event * @namedq: pointer to name table input queue with name table messages - * @curr_link: the link holding the node lock, if any - * @active_links: pointers to active links to node - * @links: pointers to all links to node + * @active_links: bearer ids of active links, used as index into links[] array + * @links: array containing references to all links to node * @action_flags: bit mask of different types of node actions * @bclink: broadcast-related info + * @state: connectivity state vs peer node + * @sync_point: sequence number where synch/failover is finished * @list: links to adjacent nodes in sorted list of cluster's nodes * @working_links: number of working links to node (both active and standby) * @link_cnt: number of links to node @@ -118,14 +122,13 @@ struct tipc_node { spinlock_t lock; struct net *net; struct hlist_node hash; - struct sk_buff_head *inputq; - struct sk_buff_head *namedq; - struct tipc_link *active_links[2]; - u32 act_mtus[2]; - struct tipc_link *links[MAX_BEARERS]; + int active_links[2]; + struct tipc_link_entry links[MAX_BEARERS]; int action_flags; struct tipc_node_bclink bclink; struct list_head list; + int state; + u16 sync_point; int link_cnt; u16 working_links; u16 capabilities; @@ -133,25 +136,32 @@ struct tipc_node { u32 link_id; struct list_head publ_list; struct list_head conn_sks; + unsigned long keepalive_intv; + struct timer_list timer; struct rcu_head rcu; }; struct tipc_node *tipc_node_find(struct net *net, u32 addr); void tipc_node_put(struct tipc_node *node); -struct tipc_node *tipc_node_create(struct net *net, u32 addr); void tipc_node_stop(struct net *net); +void tipc_node_check_dest(struct net *net, u32 onode, + struct tipc_bearer *bearer, + u16 capabilities, u32 signature, + struct tipc_media_addr *maddr, + bool *respond, bool *dupl_addr); +void tipc_node_delete_links(struct net *net, int bearer_id); void tipc_node_attach_link(struct tipc_node *n_ptr, struct tipc_link *l_ptr); void tipc_node_detach_link(struct tipc_node *n_ptr, struct tipc_link *l_ptr); -void tipc_node_link_down(struct tipc_node *n_ptr, struct tipc_link *l_ptr); -void tipc_node_link_up(struct tipc_node *n_ptr, struct tipc_link *l_ptr); -int tipc_node_active_links(struct tipc_node *n_ptr); -int tipc_node_is_up(struct tipc_node *n_ptr); +bool tipc_node_is_up(struct tipc_node *n); int tipc_node_get_linkname(struct net *net, u32 bearer_id, u32 node, char *linkname, size_t len); void tipc_node_unlock(struct tipc_node *node); +int tipc_node_xmit(struct net *net, struct sk_buff_head *list, u32 dnode, + int selector); +int tipc_node_xmit_skb(struct net *net, struct sk_buff *skb, u32 dest, + u32 selector); int tipc_node_add_conn(struct net *net, u32 dnode, u32 port, u32 peer_port); void tipc_node_remove_conn(struct net *net, u32 dnode, u32 port); - int tipc_nl_node_dump(struct sk_buff *skb, struct netlink_callback *cb); static inline void tipc_node_lock(struct tipc_node *node) @@ -159,26 +169,30 @@ static inline void tipc_node_lock(struct tipc_node *node) spin_lock_bh(&node->lock); } -static inline bool tipc_node_blocked(struct tipc_node *node) +static inline struct tipc_link *node_active_link(struct tipc_node *n, int sel) { - return (node->action_flags & (TIPC_WAIT_PEER_LINKS_DOWN | - TIPC_NOTIFY_NODE_DOWN | TIPC_WAIT_OWN_LINKS_DOWN)); + int bearer_id = n->active_links[sel & 1]; + + if (unlikely(bearer_id == INVALID_BEARER_ID)) + return NULL; + + return n->links[bearer_id].link; } -static inline uint tipc_node_get_mtu(struct net *net, u32 addr, u32 selector) +static inline unsigned int tipc_node_get_mtu(struct net *net, u32 addr, u32 sel) { - struct tipc_node *node; - u32 mtu; - - node = tipc_node_find(net, addr); + struct tipc_node *n; + int bearer_id; + unsigned int mtu = MAX_MSG_SIZE; - if (likely(node)) { - mtu = node->act_mtus[selector & 1]; - tipc_node_put(node); - } else { - mtu = MAX_MSG_SIZE; - } + n = tipc_node_find(net, addr); + if (unlikely(!n)) + return mtu; + bearer_id = n->active_links[sel & 1]; + if (likely(bearer_id != INVALID_BEARER_ID)) + mtu = n->links[bearer_id].mtu; + tipc_node_put(n); return mtu; } diff --git a/net/tipc/socket.c b/net/tipc/socket.c index 3a7567f690f3..1060d52ff23e 100644 --- a/net/tipc/socket.c +++ b/net/tipc/socket.c @@ -248,6 +248,22 @@ static void tsk_advance_rx_queue(struct sock *sk) kfree_skb(__skb_dequeue(&sk->sk_receive_queue)); } +/* tipc_sk_respond() : send response message back to sender + */ +static void tipc_sk_respond(struct sock *sk, struct sk_buff *skb, int err) +{ + u32 selector; + u32 dnode; + u32 onode = tipc_own_addr(sock_net(sk)); + + if (!tipc_msg_reverse(onode, &skb, err)) + return; + + dnode = msg_destnode(buf_msg(skb)); + selector = msg_origport(buf_msg(skb)); + tipc_node_xmit_skb(sock_net(sk), skb, dnode, selector); +} + /** * tsk_rej_rx_queue - reject all buffers in socket receive queue * @@ -256,13 +272,9 @@ static void tsk_advance_rx_queue(struct sock *sk) static void tsk_rej_rx_queue(struct sock *sk) { struct sk_buff *skb; - u32 dnode; - u32 own_node = tsk_own_node(tipc_sk(sk)); - while ((skb = __skb_dequeue(&sk->sk_receive_queue))) { - if (tipc_msg_reverse(own_node, skb, &dnode, TIPC_ERR_NO_PORT)) - tipc_link_xmit_skb(sock_net(sk), skb, dnode, 0); - } + while ((skb = __skb_dequeue(&sk->sk_receive_queue))) + tipc_sk_respond(sk, skb, TIPC_ERR_NO_PORT); } /* tsk_peer_msg - verify if message was sent by connected port's peer @@ -441,9 +453,7 @@ static int tipc_release(struct socket *sock) tsk->connected = 0; tipc_node_remove_conn(net, dnode, tsk->portid); } - if (tipc_msg_reverse(tsk_own_node(tsk), skb, &dnode, - TIPC_ERR_NO_PORT)) - tipc_link_xmit_skb(net, skb, dnode, 0); + tipc_sk_respond(sk, skb, TIPC_ERR_NO_PORT); } } @@ -456,7 +466,7 @@ static int tipc_release(struct socket *sock) tsk_own_node(tsk), tsk_peer_port(tsk), tsk->portid, TIPC_ERR_NO_PORT); if (skb) - tipc_link_xmit_skb(net, skb, dnode, tsk->portid); + tipc_node_xmit_skb(net, skb, dnode, tsk->portid); tipc_node_remove_conn(net, dnode, tsk->portid); } @@ -686,21 +696,22 @@ new_mtu: do { rc = tipc_bclink_xmit(net, pktchain); - if (likely(rc >= 0)) { - rc = dsz; - break; + if (likely(!rc)) + return dsz; + + if (rc == -ELINKCONG) { + tsk->link_cong = 1; + rc = tipc_wait_for_sndmsg(sock, &timeo); + if (!rc) + continue; } + __skb_queue_purge(pktchain); if (rc == -EMSGSIZE) { msg->msg_iter = save; goto new_mtu; } - if (rc != -ELINKCONG) - break; - tipc_sk(sk)->link_cong = 1; - rc = tipc_wait_for_sndmsg(sock, &timeo); - if (rc) - __skb_queue_purge(pktchain); - } while (!rc); + break; + } while (1); return rc; } @@ -763,35 +774,35 @@ void tipc_sk_mcast_rcv(struct net *net, struct sk_buff_head *arrvq, /** * tipc_sk_proto_rcv - receive a connection mng protocol message * @tsk: receiving socket - * @skb: pointer to message buffer. Set to NULL if buffer is consumed. + * @skb: pointer to message buffer. */ -static void tipc_sk_proto_rcv(struct tipc_sock *tsk, struct sk_buff **skb) +static void tipc_sk_proto_rcv(struct tipc_sock *tsk, struct sk_buff *skb) { - struct tipc_msg *msg = buf_msg(*skb); + struct sock *sk = &tsk->sk; + struct tipc_msg *hdr = buf_msg(skb); + int mtyp = msg_type(hdr); int conn_cong; - u32 dnode; - u32 own_node = tsk_own_node(tsk); + /* Ignore if connection cannot be validated: */ - if (!tsk_peer_msg(tsk, msg)) + if (!tsk_peer_msg(tsk, hdr)) goto exit; tsk->probing_state = TIPC_CONN_OK; - if (msg_type(msg) == CONN_ACK) { + if (mtyp == CONN_PROBE) { + msg_set_type(hdr, CONN_PROBE_REPLY); + tipc_sk_respond(sk, skb, TIPC_OK); + return; + } else if (mtyp == CONN_ACK) { conn_cong = tsk_conn_cong(tsk); - tsk->sent_unacked -= msg_msgcnt(msg); + tsk->sent_unacked -= msg_msgcnt(hdr); if (conn_cong) - tsk->sk.sk_write_space(&tsk->sk); - } else if (msg_type(msg) == CONN_PROBE) { - if (tipc_msg_reverse(own_node, *skb, &dnode, TIPC_OK)) { - msg_set_type(msg, CONN_PROBE_REPLY); - return; - } + sk->sk_write_space(sk); + } else if (mtyp != CONN_PROBE_REPLY) { + pr_warn("Received unknown CONN_PROTO msg\n"); } - /* Do nothing if msg_type() == CONN_PROBE_REPLY */ exit: - kfree_skb(*skb); - *skb = NULL; + kfree_skb(skb); } static int tipc_wait_for_sndmsg(struct socket *sock, long *timeo_p) @@ -924,24 +935,25 @@ new_mtu: do { skb = skb_peek(pktchain); TIPC_SKB_CB(skb)->wakeup_pending = tsk->link_cong; - rc = tipc_link_xmit(net, pktchain, dnode, tsk->portid); - if (likely(rc >= 0)) { + rc = tipc_node_xmit(net, pktchain, dnode, tsk->portid); + if (likely(!rc)) { if (sock->state != SS_READY) sock->state = SS_CONNECTING; - rc = dsz; - break; + return dsz; } + if (rc == -ELINKCONG) { + tsk->link_cong = 1; + rc = tipc_wait_for_sndmsg(sock, &timeo); + if (!rc) + continue; + } + __skb_queue_purge(pktchain); if (rc == -EMSGSIZE) { m->msg_iter = save; goto new_mtu; } - if (rc != -ELINKCONG) - break; - tsk->link_cong = 1; - rc = tipc_wait_for_sndmsg(sock, &timeo); - if (rc) - __skb_queue_purge(pktchain); - } while (!rc); + break; + } while (1); return rc; } @@ -1043,15 +1055,16 @@ next: return rc; do { if (likely(!tsk_conn_cong(tsk))) { - rc = tipc_link_xmit(net, pktchain, dnode, portid); + rc = tipc_node_xmit(net, pktchain, dnode, portid); if (likely(!rc)) { tsk->sent_unacked++; sent += send; if (sent == dsz) - break; + return dsz; goto next; } if (rc == -EMSGSIZE) { + __skb_queue_purge(pktchain); tsk->max_pkt = tipc_node_get_mtu(net, dnode, portid); m->msg_iter = save; @@ -1059,13 +1072,13 @@ next: } if (rc != -ELINKCONG) break; + tsk->link_cong = 1; } rc = tipc_wait_for_sndpkt(sock, &timeo); - if (rc) - __skb_queue_purge(pktchain); } while (!rc); + __skb_queue_purge(pktchain); return sent ? sent : rc; } @@ -1221,7 +1234,7 @@ static void tipc_sk_send_ack(struct tipc_sock *tsk, uint ack) return; msg = buf_msg(skb); msg_set_msgcnt(msg, ack); - tipc_link_xmit_skb(net, skb, dnode, msg_link_selector(msg)); + tipc_node_xmit_skb(net, skb, dnode, msg_link_selector(msg)); } static int tipc_wait_for_rcvmsg(struct socket *sock, long *timeop) @@ -1507,82 +1520,81 @@ static void tipc_data_ready(struct sock *sk) * @tsk: TIPC socket * @skb: pointer to message buffer. Set to NULL if buffer is consumed * - * Returns 0 (TIPC_OK) if everything ok, -TIPC_ERR_NO_PORT otherwise + * Returns true if everything ok, false otherwise */ -static int filter_connect(struct tipc_sock *tsk, struct sk_buff **skb) +static bool filter_connect(struct tipc_sock *tsk, struct sk_buff *skb) { struct sock *sk = &tsk->sk; struct net *net = sock_net(sk); struct socket *sock = sk->sk_socket; - struct tipc_msg *msg = buf_msg(*skb); - int retval = -TIPC_ERR_NO_PORT; + struct tipc_msg *hdr = buf_msg(skb); - if (msg_mcast(msg)) - return retval; + if (unlikely(msg_mcast(hdr))) + return false; switch ((int)sock->state) { case SS_CONNECTED: + /* Accept only connection-based messages sent by peer */ - if (tsk_peer_msg(tsk, msg)) { - if (unlikely(msg_errcode(msg))) { - sock->state = SS_DISCONNECTING; - tsk->connected = 0; - /* let timer expire on it's own */ - tipc_node_remove_conn(net, tsk_peer_node(tsk), - tsk->portid); - } - retval = TIPC_OK; + if (unlikely(!tsk_peer_msg(tsk, hdr))) + return false; + + if (unlikely(msg_errcode(hdr))) { + sock->state = SS_DISCONNECTING; + tsk->connected = 0; + /* Let timer expire on it's own */ + tipc_node_remove_conn(net, tsk_peer_node(tsk), + tsk->portid); } - break; + return true; + case SS_CONNECTING: - /* Accept only ACK or NACK message */ - if (unlikely(!msg_connected(msg))) - break; + /* Accept only ACK or NACK message */ + if (unlikely(!msg_connected(hdr))) + return false; - if (unlikely(msg_errcode(msg))) { + if (unlikely(msg_errcode(hdr))) { sock->state = SS_DISCONNECTING; sk->sk_err = ECONNREFUSED; - retval = TIPC_OK; - break; + return true; } - if (unlikely(msg_importance(msg) > TIPC_CRITICAL_IMPORTANCE)) { + if (unlikely(!msg_isdata(hdr))) { sock->state = SS_DISCONNECTING; sk->sk_err = EINVAL; - retval = TIPC_OK; - break; + return true; } - tipc_sk_finish_conn(tsk, msg_origport(msg), msg_orignode(msg)); - msg_set_importance(&tsk->phdr, msg_importance(msg)); + tipc_sk_finish_conn(tsk, msg_origport(hdr), msg_orignode(hdr)); + msg_set_importance(&tsk->phdr, msg_importance(hdr)); sock->state = SS_CONNECTED; - /* If an incoming message is an 'ACK-', it should be - * discarded here because it doesn't contain useful - * data. In addition, we should try to wake up - * connect() routine if sleeping. - */ - if (msg_data_sz(msg) == 0) { - kfree_skb(*skb); - *skb = NULL; - if (waitqueue_active(sk_sleep(sk))) - wake_up_interruptible(sk_sleep(sk)); - } - retval = TIPC_OK; - break; + /* If 'ACK+' message, add to socket receive queue */ + if (msg_data_sz(hdr)) + return true; + + /* If empty 'ACK-' message, wake up sleeping connect() */ + if (waitqueue_active(sk_sleep(sk))) + wake_up_interruptible(sk_sleep(sk)); + + /* 'ACK-' message is neither accepted nor rejected: */ + msg_set_dest_droppable(hdr, 1); + return false; + case SS_LISTENING: case SS_UNCONNECTED: + /* Accept only SYN message */ - if (!msg_connected(msg) && !(msg_errcode(msg))) - retval = TIPC_OK; + if (!msg_connected(hdr) && !(msg_errcode(hdr))) + return true; break; case SS_DISCONNECTING: break; default: pr_err("Unknown socket state %u\n", sock->state); } - return retval; + return false; } /** @@ -1617,61 +1629,70 @@ static unsigned int rcvbuf_limit(struct sock *sk, struct sk_buff *buf) /** * filter_rcv - validate incoming message * @sk: socket - * @skb: pointer to message. Set to NULL if buffer is consumed. + * @skb: pointer to message. * * Enqueues message on receive queue if acceptable; optionally handles * disconnect indication for a connected socket. * * Called with socket lock already taken * - * Returns 0 (TIPC_OK) if message was ok, -TIPC error code if rejected + * Returns true if message was added to socket receive queue, otherwise false */ -static int filter_rcv(struct sock *sk, struct sk_buff **skb) +static bool filter_rcv(struct sock *sk, struct sk_buff *skb) { struct socket *sock = sk->sk_socket; struct tipc_sock *tsk = tipc_sk(sk); - struct tipc_msg *msg = buf_msg(*skb); - unsigned int limit = rcvbuf_limit(sk, *skb); - int rc = TIPC_OK; + struct tipc_msg *hdr = buf_msg(skb); + unsigned int limit = rcvbuf_limit(sk, skb); + int err = TIPC_OK; + int usr = msg_user(hdr); - if (unlikely(msg_user(msg) == CONN_MANAGER)) { + if (unlikely(msg_user(hdr) == CONN_MANAGER)) { tipc_sk_proto_rcv(tsk, skb); - return TIPC_OK; + return false; } - if (unlikely(msg_user(msg) == SOCK_WAKEUP)) { - kfree_skb(*skb); + if (unlikely(usr == SOCK_WAKEUP)) { + kfree_skb(skb); tsk->link_cong = 0; sk->sk_write_space(sk); - *skb = NULL; - return TIPC_OK; + return false; } - /* Reject message if it is wrong sort of message for socket */ - if (msg_type(msg) > TIPC_DIRECT_MSG) - return -TIPC_ERR_NO_PORT; + /* Drop if illegal message type */ + if (unlikely(msg_type(hdr) > TIPC_DIRECT_MSG)) { + kfree_skb(skb); + return false; + } - if (sock->state == SS_READY) { - if (msg_connected(msg)) - return -TIPC_ERR_NO_PORT; - } else { - rc = filter_connect(tsk, skb); - if (rc != TIPC_OK || !*skb) - return rc; + /* Reject if wrong message type for current socket state */ + if (unlikely(sock->state == SS_READY)) { + if (msg_connected(hdr)) { + err = TIPC_ERR_NO_PORT; + goto reject; + } + } else if (unlikely(!filter_connect(tsk, skb))) { + err = TIPC_ERR_NO_PORT; + goto reject; } /* Reject message if there isn't room to queue it */ - if (sk_rmem_alloc_get(sk) + (*skb)->truesize >= limit) - return -TIPC_ERR_OVERLOAD; + if (unlikely(sk_rmem_alloc_get(sk) + skb->truesize >= limit)) { + err = TIPC_ERR_OVERLOAD; + goto reject; + } /* Enqueue message */ - TIPC_SKB_CB(*skb)->handle = NULL; - __skb_queue_tail(&sk->sk_receive_queue, *skb); - skb_set_owner_r(*skb, sk); + TIPC_SKB_CB(skb)->handle = NULL; + __skb_queue_tail(&sk->sk_receive_queue, skb); + skb_set_owner_r(skb, sk); sk->sk_data_ready(sk); - *skb = NULL; - return TIPC_OK; + return true; + +reject: + tipc_sk_respond(sk, skb, err); + return false; } /** @@ -1685,22 +1706,10 @@ static int filter_rcv(struct sock *sk, struct sk_buff **skb) */ static int tipc_backlog_rcv(struct sock *sk, struct sk_buff *skb) { - int err; - atomic_t *dcnt; - u32 dnode; - struct tipc_sock *tsk = tipc_sk(sk); - struct net *net = sock_net(sk); - uint truesize = skb->truesize; + unsigned int truesize = skb->truesize; - err = filter_rcv(sk, &skb); - if (likely(!skb)) { - dcnt = &tsk->dupl_rcvcnt; - if (atomic_read(dcnt) < TIPC_CONN_OVERLOAD_LIMIT) - atomic_add(truesize, dcnt); - return 0; - } - if (!err || tipc_msg_reverse(tsk_own_node(tsk), skb, &dnode, -err)) - tipc_link_xmit_skb(net, skb, dnode, tsk->portid); + if (likely(filter_rcv(sk, skb))) + atomic_add(truesize, &tipc_sk(sk)->dupl_rcvcnt); return 0; } @@ -1710,45 +1719,43 @@ static int tipc_backlog_rcv(struct sock *sk, struct sk_buff *skb) * @inputq: list of incoming buffers with potentially different destinations * @sk: socket where the buffers should be enqueued * @dport: port number for the socket - * @_skb: returned buffer to be forwarded or rejected, if applicable * * Caller must hold socket lock - * - * Returns TIPC_OK if all buffers enqueued, otherwise -TIPC_ERR_OVERLOAD - * or -TIPC_ERR_NO_PORT */ -static int tipc_sk_enqueue(struct sk_buff_head *inputq, struct sock *sk, - u32 dport, struct sk_buff **_skb) +static void tipc_sk_enqueue(struct sk_buff_head *inputq, struct sock *sk, + u32 dport) { unsigned int lim; atomic_t *dcnt; - int err; struct sk_buff *skb; unsigned long time_limit = jiffies + 2; while (skb_queue_len(inputq)) { if (unlikely(time_after_eq(jiffies, time_limit))) - return TIPC_OK; + return; + skb = tipc_skb_dequeue(inputq, dport); if (unlikely(!skb)) - return TIPC_OK; + return; + + /* Add message directly to receive queue if possible */ if (!sock_owned_by_user(sk)) { - err = filter_rcv(sk, &skb); - if (likely(!skb)) - continue; - *_skb = skb; - return err; + filter_rcv(sk, skb); + continue; } + + /* Try backlog, compensating for double-counted bytes */ dcnt = &tipc_sk(sk)->dupl_rcvcnt; if (sk->sk_backlog.len) atomic_set(dcnt, 0); lim = rcvbuf_limit(sk, skb) + atomic_read(dcnt); if (likely(!sk_add_backlog(sk, skb, lim))) continue; - *_skb = skb; - return -TIPC_ERR_OVERLOAD; + + /* Overload => reject message back to sender */ + tipc_sk_respond(sk, skb, TIPC_ERR_OVERLOAD); + break; } - return TIPC_OK; } /** @@ -1756,49 +1763,46 @@ static int tipc_sk_enqueue(struct sk_buff_head *inputq, struct sock *sk, * @inputq: buffer list containing the buffers * Consumes all buffers in list until inputq is empty * Note: may be called in multiple threads referring to the same queue - * Returns 0 if last buffer was accepted, otherwise -EHOSTUNREACH - * Only node local calls check the return value, sending single-buffer queues */ -int tipc_sk_rcv(struct net *net, struct sk_buff_head *inputq) +void tipc_sk_rcv(struct net *net, struct sk_buff_head *inputq) { u32 dnode, dport = 0; int err; - struct sk_buff *skb; struct tipc_sock *tsk; - struct tipc_net *tn; struct sock *sk; + struct sk_buff *skb; while (skb_queue_len(inputq)) { - err = -TIPC_ERR_NO_PORT; - skb = NULL; dport = tipc_skb_peek_port(inputq, dport); tsk = tipc_sk_lookup(net, dport); + if (likely(tsk)) { sk = &tsk->sk; if (likely(spin_trylock_bh(&sk->sk_lock.slock))) { - err = tipc_sk_enqueue(inputq, sk, dport, &skb); + tipc_sk_enqueue(inputq, sk, dport); spin_unlock_bh(&sk->sk_lock.slock); - dport = 0; } sock_put(sk); - } else { - skb = tipc_skb_dequeue(inputq, dport); - } - if (likely(!skb)) continue; - if (tipc_msg_lookup_dest(net, skb, &dnode, &err)) - goto xmit; - if (!err) { - dnode = msg_destnode(buf_msg(skb)); - goto xmit; } - tn = net_generic(net, tipc_net_id); - if (!tipc_msg_reverse(tn->own_addr, skb, &dnode, -err)) + + /* No destination socket => dequeue skb if still there */ + skb = tipc_skb_dequeue(inputq, dport); + if (!skb) + return; + + /* Try secondary lookup if unresolved named message */ + err = TIPC_ERR_NO_PORT; + if (tipc_msg_lookup_dest(net, skb, &err)) + goto xmit; + + /* Prepare for message rejection */ + if (!tipc_msg_reverse(tipc_own_addr(net), &skb, err)) continue; xmit: - tipc_link_xmit_skb(net, skb, dnode, dport); + dnode = msg_destnode(buf_msg(skb)); + tipc_node_xmit_skb(net, skb, dnode, dport); } - return err ? -EHOSTUNREACH : 0; } static int tipc_wait_for_connect(struct socket *sock, long *timeo_p) @@ -2067,7 +2071,10 @@ static int tipc_shutdown(struct socket *sock, int how) struct net *net = sock_net(sk); struct tipc_sock *tsk = tipc_sk(sk); struct sk_buff *skb; - u32 dnode; + u32 dnode = tsk_peer_node(tsk); + u32 dport = tsk_peer_port(tsk); + u32 onode = tipc_own_addr(net); + u32 oport = tsk->portid; int res; if (how != SHUT_RDWR) @@ -2080,6 +2087,8 @@ static int tipc_shutdown(struct socket *sock, int how) case SS_CONNECTED: restart: + dnode = tsk_peer_node(tsk); + /* Disconnect and send a 'FIN+' or 'FIN-' message to peer */ skb = __skb_dequeue(&sk->sk_receive_queue); if (skb) { @@ -2087,19 +2096,13 @@ restart: kfree_skb(skb); goto restart; } - if (tipc_msg_reverse(tsk_own_node(tsk), skb, &dnode, - TIPC_CONN_SHUTDOWN)) - tipc_link_xmit_skb(net, skb, dnode, - tsk->portid); + tipc_sk_respond(sk, skb, TIPC_CONN_SHUTDOWN); } else { - dnode = tsk_peer_node(tsk); - skb = tipc_msg_create(TIPC_CRITICAL_IMPORTANCE, TIPC_CONN_MSG, SHORT_H_SIZE, - 0, dnode, tsk_own_node(tsk), - tsk_peer_port(tsk), - tsk->portid, TIPC_CONN_SHUTDOWN); - tipc_link_xmit_skb(net, skb, dnode, tsk->portid); + 0, dnode, onode, dport, oport, + TIPC_CONN_SHUTDOWN); + tipc_node_xmit_skb(net, skb, dnode, tsk->portid); } tsk->connected = 0; sock->state = SS_DISCONNECTING; @@ -2161,7 +2164,7 @@ static void tipc_sk_timeout(unsigned long data) } bh_unlock_sock(sk); if (skb) - tipc_link_xmit_skb(sock_net(sk), skb, peer_node, tsk->portid); + tipc_node_xmit_skb(sock_net(sk), skb, peer_node, tsk->portid); exit: sock_put(sk); } diff --git a/net/tipc/socket.h b/net/tipc/socket.h index bf6551389522..4241f22069dc 100644 --- a/net/tipc/socket.h +++ b/net/tipc/socket.h @@ -44,7 +44,7 @@ SKB_TRUESIZE(TIPC_MAX_USER_MSG_SIZE)) int tipc_socket_init(void); void tipc_socket_stop(void); -int tipc_sk_rcv(struct net *net, struct sk_buff_head *inputq); +void tipc_sk_rcv(struct net *net, struct sk_buff_head *inputq); void tipc_sk_mcast_rcv(struct net *net, struct sk_buff_head *arrvq, struct sk_buff_head *inputq); void tipc_sk_reinit(struct net *net); diff --git a/net/tipc/udp_media.c b/net/tipc/udp_media.c index 66deebc66aa1..c170d3138953 100644 --- a/net/tipc/udp_media.c +++ b/net/tipc/udp_media.c @@ -194,7 +194,8 @@ static int tipc_udp_send_msg(struct net *net, struct sk_buff *skb, .saddr = src->ipv6, .flowi6_proto = IPPROTO_UDP }; - err = ipv6_stub->ipv6_dst_lookup(ub->ubsock->sk, &ndst, &fl6); + err = ipv6_stub->ipv6_dst_lookup(net, ub->ubsock->sk, &ndst, + &fl6); if (err) goto tx_error; ttl = ip6_dst_hoplimit(ndst); diff --git a/net/wimax/op-rfkill.c b/net/wimax/op-rfkill.c index 7d730543f243..477364ad750e 100644 --- a/net/wimax/op-rfkill.c +++ b/net/wimax/op-rfkill.c @@ -135,8 +135,7 @@ EXPORT_SYMBOL_GPL(wimax_report_rfkill_hw); * @state: New state of the RF kill switch. %WIMAX_RF_ON radio on, * %WIMAX_RF_OFF radio off. * - * Reports changes in the software RF switch state to the the WiMAX - * stack. + * Reports changes in the software RF switch state to the WiMAX stack. * * The main use is during initialization, so the driver can query the * device for its current software radio kill switch state and feed it diff --git a/net/wireless/core.c b/net/wireless/core.c index 2a0bbd22854b..3893409dee95 100644 --- a/net/wireless/core.c +++ b/net/wireless/core.c @@ -407,6 +407,9 @@ use_default_name: INIT_LIST_HEAD(&rdev->bss_list); INIT_WORK(&rdev->scan_done_wk, __cfg80211_scan_done); INIT_WORK(&rdev->sched_scan_results_wk, __cfg80211_sched_scan_results); + INIT_LIST_HEAD(&rdev->mlme_unreg); + spin_lock_init(&rdev->mlme_unreg_lock); + INIT_WORK(&rdev->mlme_unreg_wk, cfg80211_mlme_unreg_wk); INIT_DELAYED_WORK(&rdev->dfs_update_channels_wk, cfg80211_dfs_channels_update_work); #ifdef CONFIG_CFG80211_WEXT @@ -802,6 +805,7 @@ void wiphy_unregister(struct wiphy *wiphy) cancel_delayed_work_sync(&rdev->dfs_update_channels_wk); flush_work(&rdev->destroy_work); flush_work(&rdev->sched_scan_stop_wk); + flush_work(&rdev->mlme_unreg_wk); #ifdef CONFIG_PM if (rdev->wiphy.wowlan_config && rdev->ops->set_wakeup) @@ -855,6 +859,7 @@ void cfg80211_unregister_wdev(struct wireless_dev *wdev) switch (wdev->iftype) { case NL80211_IFTYPE_P2P_DEVICE: + cfg80211_mlme_purge_registrations(wdev); cfg80211_stop_p2p_device(rdev, wdev); break; default: diff --git a/net/wireless/core.h b/net/wireless/core.h index 311eef26bf88..b9d5bc8c148d 100644 --- a/net/wireless/core.h +++ b/net/wireless/core.h @@ -59,6 +59,10 @@ struct cfg80211_registered_device { struct list_head beacon_registrations; spinlock_t beacon_registrations_lock; + struct list_head mlme_unreg; + spinlock_t mlme_unreg_lock; + struct work_struct mlme_unreg_wk; + /* protected by RTNL only */ int num_running_ifaces; int num_running_monitor_ifaces; @@ -348,6 +352,7 @@ void cfg80211_mlme_down(struct cfg80211_registered_device *rdev, int cfg80211_mlme_register_mgmt(struct wireless_dev *wdev, u32 snd_pid, u16 frame_type, const u8 *match_data, int match_len); +void cfg80211_mlme_unreg_wk(struct work_struct *wk); void cfg80211_mlme_unregister_socket(struct wireless_dev *wdev, u32 nlpid); void cfg80211_mlme_purge_registrations(struct wireless_dev *wdev); int cfg80211_mlme_mgmt_tx(struct cfg80211_registered_device *rdev, diff --git a/net/wireless/mlme.c b/net/wireless/mlme.c index 7aae329e2b4e..fb44fa3bf4ef 100644 --- a/net/wireless/mlme.c +++ b/net/wireless/mlme.c @@ -2,6 +2,7 @@ * cfg80211 MLME SAP interface * * Copyright (c) 2009, Jouni Malinen <j@w1.fi> + * Copyright (c) 2015 Intel Deutschland GmbH */ #include <linux/kernel.h> @@ -389,6 +390,7 @@ void cfg80211_mlme_down(struct cfg80211_registered_device *rdev, struct cfg80211_mgmt_registration { struct list_head list; + struct wireless_dev *wdev; u32 nlportid; @@ -399,6 +401,46 @@ struct cfg80211_mgmt_registration { u8 match[]; }; +static void +cfg80211_process_mlme_unregistrations(struct cfg80211_registered_device *rdev) +{ + struct cfg80211_mgmt_registration *reg; + + ASSERT_RTNL(); + + spin_lock_bh(&rdev->mlme_unreg_lock); + while ((reg = list_first_entry_or_null(&rdev->mlme_unreg, + struct cfg80211_mgmt_registration, + list))) { + list_del(®->list); + spin_unlock_bh(&rdev->mlme_unreg_lock); + + if (rdev->ops->mgmt_frame_register) { + u16 frame_type = le16_to_cpu(reg->frame_type); + + rdev_mgmt_frame_register(rdev, reg->wdev, + frame_type, false); + } + + kfree(reg); + + spin_lock_bh(&rdev->mlme_unreg_lock); + } + spin_unlock_bh(&rdev->mlme_unreg_lock); +} + +void cfg80211_mlme_unreg_wk(struct work_struct *wk) +{ + struct cfg80211_registered_device *rdev; + + rdev = container_of(wk, struct cfg80211_registered_device, + mlme_unreg_wk); + + rtnl_lock(); + cfg80211_process_mlme_unregistrations(rdev); + rtnl_unlock(); +} + int cfg80211_mlme_register_mgmt(struct wireless_dev *wdev, u32 snd_portid, u16 frame_type, const u8 *match_data, int match_len) @@ -449,11 +491,18 @@ int cfg80211_mlme_register_mgmt(struct wireless_dev *wdev, u32 snd_portid, nreg->match_len = match_len; nreg->nlportid = snd_portid; nreg->frame_type = cpu_to_le16(frame_type); + nreg->wdev = wdev; list_add(&nreg->list, &wdev->mgmt_registrations); + spin_unlock_bh(&wdev->mgmt_registrations_lock); + + /* process all unregistrations to avoid driver confusion */ + cfg80211_process_mlme_unregistrations(rdev); if (rdev->ops->mgmt_frame_register) rdev_mgmt_frame_register(rdev, wdev, frame_type, true); + return 0; + out: spin_unlock_bh(&wdev->mgmt_registrations_lock); @@ -472,15 +521,12 @@ void cfg80211_mlme_unregister_socket(struct wireless_dev *wdev, u32 nlportid) if (reg->nlportid != nlportid) continue; - if (rdev->ops->mgmt_frame_register) { - u16 frame_type = le16_to_cpu(reg->frame_type); - - rdev_mgmt_frame_register(rdev, wdev, - frame_type, false); - } - list_del(®->list); - kfree(reg); + spin_lock(&rdev->mlme_unreg_lock); + list_add_tail(®->list, &rdev->mlme_unreg); + spin_unlock(&rdev->mlme_unreg_lock); + + schedule_work(&rdev->mlme_unreg_wk); } spin_unlock_bh(&wdev->mgmt_registrations_lock); @@ -496,16 +542,15 @@ void cfg80211_mlme_unregister_socket(struct wireless_dev *wdev, u32 nlportid) void cfg80211_mlme_purge_registrations(struct wireless_dev *wdev) { - struct cfg80211_mgmt_registration *reg, *tmp; + struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); spin_lock_bh(&wdev->mgmt_registrations_lock); - - list_for_each_entry_safe(reg, tmp, &wdev->mgmt_registrations, list) { - list_del(®->list); - kfree(reg); - } - + spin_lock(&rdev->mlme_unreg_lock); + list_splice_tail_init(&wdev->mgmt_registrations, &rdev->mlme_unreg); + spin_unlock(&rdev->mlme_unreg_lock); spin_unlock_bh(&wdev->mgmt_registrations_lock); + + cfg80211_process_mlme_unregistrations(rdev); } int cfg80211_mlme_mgmt_tx(struct cfg80211_registered_device *rdev, diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 76b41578a838..5d8748b4c8a2 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -2321,6 +2321,7 @@ static int nl80211_set_wiphy(struct sk_buff *skb, struct genl_info *info) rdev->wiphy.frag_threshold = old_frag_threshold; rdev->wiphy.rts_threshold = old_rts_threshold; rdev->wiphy.coverage_class = old_coverage_class; + return result; } } return 0; @@ -7390,7 +7391,8 @@ static int nl80211_set_mcast_rate(struct sk_buff *skb, struct genl_info *info) int err; if (dev->ieee80211_ptr->iftype != NL80211_IFTYPE_ADHOC && - dev->ieee80211_ptr->iftype != NL80211_IFTYPE_MESH_POINT) + dev->ieee80211_ptr->iftype != NL80211_IFTYPE_MESH_POINT && + dev->ieee80211_ptr->iftype != NL80211_IFTYPE_OCB) return -EOPNOTSUPP; if (!rdev->ops->set_mcast_rate) diff --git a/net/wireless/rdev-ops.h b/net/wireless/rdev-ops.h index c6e83a7468c0..c23516d0f807 100644 --- a/net/wireless/rdev-ops.h +++ b/net/wireless/rdev-ops.h @@ -733,6 +733,8 @@ static inline void rdev_mgmt_frame_register(struct cfg80211_registered_device *rdev, struct wireless_dev *wdev, u16 frame_type, bool reg) { + might_sleep(); + trace_rdev_mgmt_frame_register(&rdev->wiphy, wdev , frame_type, reg); rdev->ops->mgmt_frame_register(&rdev->wiphy, wdev , frame_type, reg); trace_rdev_return_void(&rdev->wiphy); diff --git a/net/wireless/reg.c b/net/wireless/reg.c index aa2d75482017..2510b231451e 100644 --- a/net/wireless/reg.c +++ b/net/wireless/reg.c @@ -1004,7 +1004,7 @@ static u32 map_regdom_flags(u32 rd_flags) static const struct ieee80211_reg_rule * freq_reg_info_regd(struct wiphy *wiphy, u32 center_freq, - const struct ieee80211_regdomain *regd) + const struct ieee80211_regdomain *regd, u32 bw) { int i; bool band_rule_found = false; @@ -1028,7 +1028,7 @@ freq_reg_info_regd(struct wiphy *wiphy, u32 center_freq, if (!band_rule_found) band_rule_found = freq_in_rule_band(fr, center_freq); - bw_fits = reg_does_bw_fit(fr, center_freq, MHZ_TO_KHZ(20)); + bw_fits = reg_does_bw_fit(fr, center_freq, bw); if (band_rule_found && bw_fits) return rr; @@ -1040,14 +1040,26 @@ freq_reg_info_regd(struct wiphy *wiphy, u32 center_freq, return ERR_PTR(-EINVAL); } -const struct ieee80211_reg_rule *freq_reg_info(struct wiphy *wiphy, - u32 center_freq) +const struct ieee80211_reg_rule *__freq_reg_info(struct wiphy *wiphy, + u32 center_freq, u32 min_bw) { - const struct ieee80211_regdomain *regd; + const struct ieee80211_regdomain *regd = reg_get_regdomain(wiphy); + const struct ieee80211_reg_rule *reg_rule = NULL; + u32 bw; - regd = reg_get_regdomain(wiphy); + for (bw = MHZ_TO_KHZ(20); bw >= min_bw; bw = bw / 2) { + reg_rule = freq_reg_info_regd(wiphy, center_freq, regd, bw); + if (!IS_ERR(reg_rule)) + return reg_rule; + } - return freq_reg_info_regd(wiphy, center_freq, regd); + return reg_rule; +} + +const struct ieee80211_reg_rule *freq_reg_info(struct wiphy *wiphy, + u32 center_freq) +{ + return __freq_reg_info(wiphy, center_freq, MHZ_TO_KHZ(20)); } EXPORT_SYMBOL(freq_reg_info); @@ -1176,8 +1188,20 @@ static void handle_channel(struct wiphy *wiphy, if (reg_rule->flags & NL80211_RRF_AUTO_BW) max_bandwidth_khz = reg_get_max_bandwidth(regd, reg_rule); + /* If we get a reg_rule we can assume that at least 5Mhz fit */ + if (!reg_does_bw_fit(freq_range, MHZ_TO_KHZ(chan->center_freq), + MHZ_TO_KHZ(10))) + bw_flags |= IEEE80211_CHAN_NO_10MHZ; + if (!reg_does_bw_fit(freq_range, MHZ_TO_KHZ(chan->center_freq), + MHZ_TO_KHZ(20))) + bw_flags |= IEEE80211_CHAN_NO_20MHZ; + + if (max_bandwidth_khz < MHZ_TO_KHZ(10)) + bw_flags |= IEEE80211_CHAN_NO_10MHZ; + if (max_bandwidth_khz < MHZ_TO_KHZ(20)) + bw_flags |= IEEE80211_CHAN_NO_20MHZ; if (max_bandwidth_khz < MHZ_TO_KHZ(40)) - bw_flags = IEEE80211_CHAN_NO_HT40; + bw_flags |= IEEE80211_CHAN_NO_HT40; if (max_bandwidth_khz < MHZ_TO_KHZ(80)) bw_flags |= IEEE80211_CHAN_NO_80MHZ; if (max_bandwidth_khz < MHZ_TO_KHZ(160)) @@ -1695,9 +1719,15 @@ static void handle_channel_custom(struct wiphy *wiphy, const struct ieee80211_power_rule *power_rule = NULL; const struct ieee80211_freq_range *freq_range = NULL; u32 max_bandwidth_khz; + u32 bw; - reg_rule = freq_reg_info_regd(wiphy, MHZ_TO_KHZ(chan->center_freq), - regd); + for (bw = MHZ_TO_KHZ(20); bw >= MHZ_TO_KHZ(5); bw = bw / 2) { + reg_rule = freq_reg_info_regd(wiphy, + MHZ_TO_KHZ(chan->center_freq), + regd, bw); + if (!IS_ERR(reg_rule)) + break; + } if (IS_ERR(reg_rule)) { REG_DBG_PRINT("Disabling freq %d MHz as custom regd has no rule that fits it\n", @@ -1721,8 +1751,20 @@ static void handle_channel_custom(struct wiphy *wiphy, if (reg_rule->flags & NL80211_RRF_AUTO_BW) max_bandwidth_khz = reg_get_max_bandwidth(regd, reg_rule); + /* If we get a reg_rule we can assume that at least 5Mhz fit */ + if (!reg_does_bw_fit(freq_range, MHZ_TO_KHZ(chan->center_freq), + MHZ_TO_KHZ(10))) + bw_flags |= IEEE80211_CHAN_NO_10MHZ; + if (!reg_does_bw_fit(freq_range, MHZ_TO_KHZ(chan->center_freq), + MHZ_TO_KHZ(20))) + bw_flags |= IEEE80211_CHAN_NO_20MHZ; + + if (max_bandwidth_khz < MHZ_TO_KHZ(10)) + bw_flags |= IEEE80211_CHAN_NO_10MHZ; + if (max_bandwidth_khz < MHZ_TO_KHZ(20)) + bw_flags |= IEEE80211_CHAN_NO_20MHZ; if (max_bandwidth_khz < MHZ_TO_KHZ(40)) - bw_flags = IEEE80211_CHAN_NO_HT40; + bw_flags |= IEEE80211_CHAN_NO_HT40; if (max_bandwidth_khz < MHZ_TO_KHZ(80)) bw_flags |= IEEE80211_CHAN_NO_80MHZ; if (max_bandwidth_khz < MHZ_TO_KHZ(160)) @@ -2079,10 +2121,7 @@ static void reg_process_hint(struct regulatory_request *reg_request) reg_process_hint_core(reg_request); return; case NL80211_REGDOM_SET_BY_USER: - treatment = reg_process_hint_user(reg_request); - if (treatment == REG_REQ_IGNORE || - treatment == REG_REQ_ALREADY_SET) - return; + reg_process_hint_user(reg_request); return; case NL80211_REGDOM_SET_BY_DRIVER: if (!wiphy) @@ -2099,7 +2138,9 @@ static void reg_process_hint(struct regulatory_request *reg_request) goto out_free; } - /* This is required so that the orig_* parameters are saved */ + /* This is required so that the orig_* parameters are saved. + * NOTE: treatment must be set for any case that reaches here! + */ if (treatment == REG_REQ_ALREADY_SET && wiphy && wiphy->regulatory_flags & REGULATORY_STRICT_REG) { wiphy_update_regulatory(wiphy, reg_request->initiator); @@ -2584,7 +2625,7 @@ static void restore_regulatory_settings(bool reset_user) * settings, user regulatory settings takes precedence. */ if (is_an_alpha2(alpha2)) - regulatory_hint_user(user_alpha2, NL80211_USER_REG_HINT_USER); + regulatory_hint_user(alpha2, NL80211_USER_REG_HINT_USER); spin_lock(®_requests_lock); list_splice_tail_init(&tmp_reg_req_list, ®_requests_list); diff --git a/net/xfrm/xfrm_algo.c b/net/xfrm/xfrm_algo.c index 42f7c76cf853..f07224d8b88f 100644 --- a/net/xfrm/xfrm_algo.c +++ b/net/xfrm/xfrm_algo.c @@ -31,7 +31,7 @@ static struct xfrm_algo_desc aead_list[] = { .uinfo = { .aead = { - .geniv = "seqniv", + .geniv = "seqiv", .icv_truncbits = 64, } }, @@ -50,7 +50,7 @@ static struct xfrm_algo_desc aead_list[] = { .uinfo = { .aead = { - .geniv = "seqniv", + .geniv = "seqiv", .icv_truncbits = 96, } }, @@ -69,7 +69,7 @@ static struct xfrm_algo_desc aead_list[] = { .uinfo = { .aead = { - .geniv = "seqniv", + .geniv = "seqiv", .icv_truncbits = 128, } }, @@ -88,7 +88,7 @@ static struct xfrm_algo_desc aead_list[] = { .uinfo = { .aead = { - .geniv = "seqniv", + .geniv = "seqiv", .icv_truncbits = 64, } }, @@ -107,7 +107,7 @@ static struct xfrm_algo_desc aead_list[] = { .uinfo = { .aead = { - .geniv = "seqniv", + .geniv = "seqiv", .icv_truncbits = 96, } }, @@ -126,7 +126,7 @@ static struct xfrm_algo_desc aead_list[] = { .uinfo = { .aead = { - .geniv = "seqniv", + .geniv = "seqiv", .icv_truncbits = 128, } }, @@ -164,7 +164,7 @@ static struct xfrm_algo_desc aead_list[] = { .uinfo = { .aead = { - .geniv = "seqniv", + .geniv = "seqiv", .icv_truncbits = 128, } }, diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index 18cead7645be..94af3d065785 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -115,7 +115,8 @@ static void xfrm_policy_put_afinfo(struct xfrm_policy_afinfo *afinfo) rcu_read_unlock(); } -static inline struct dst_entry *__xfrm_dst_lookup(struct net *net, int tos, +static inline struct dst_entry *__xfrm_dst_lookup(struct net *net, + int tos, int oif, const xfrm_address_t *saddr, const xfrm_address_t *daddr, int family) @@ -127,14 +128,15 @@ static inline struct dst_entry *__xfrm_dst_lookup(struct net *net, int tos, if (unlikely(afinfo == NULL)) return ERR_PTR(-EAFNOSUPPORT); - dst = afinfo->dst_lookup(net, tos, saddr, daddr); + dst = afinfo->dst_lookup(net, tos, oif, saddr, daddr); xfrm_policy_put_afinfo(afinfo); return dst; } -static inline struct dst_entry *xfrm_dst_lookup(struct xfrm_state *x, int tos, +static inline struct dst_entry *xfrm_dst_lookup(struct xfrm_state *x, + int tos, int oif, xfrm_address_t *prev_saddr, xfrm_address_t *prev_daddr, int family) @@ -153,7 +155,7 @@ static inline struct dst_entry *xfrm_dst_lookup(struct xfrm_state *x, int tos, daddr = x->coaddr; } - dst = __xfrm_dst_lookup(net, tos, saddr, daddr, family); + dst = __xfrm_dst_lookup(net, tos, oif, saddr, daddr, family); if (!IS_ERR(dst)) { if (prev_saddr != saddr) @@ -1373,15 +1375,15 @@ int __xfrm_sk_clone_policy(struct sock *sk) } static int -xfrm_get_saddr(struct net *net, xfrm_address_t *local, xfrm_address_t *remote, - unsigned short family) +xfrm_get_saddr(struct net *net, int oif, xfrm_address_t *local, + xfrm_address_t *remote, unsigned short family) { int err; struct xfrm_policy_afinfo *afinfo = xfrm_policy_get_afinfo(family); if (unlikely(afinfo == NULL)) return -EINVAL; - err = afinfo->get_saddr(net, local, remote); + err = afinfo->get_saddr(net, oif, local, remote); xfrm_policy_put_afinfo(afinfo); return err; } @@ -1410,7 +1412,9 @@ xfrm_tmpl_resolve_one(struct xfrm_policy *policy, const struct flowi *fl, remote = &tmpl->id.daddr; local = &tmpl->saddr; if (xfrm_addr_any(local, tmpl->encap_family)) { - error = xfrm_get_saddr(net, &tmp, remote, tmpl->encap_family); + error = xfrm_get_saddr(net, fl->flowi_oif, + &tmp, remote, + tmpl->encap_family); if (error) goto fail; local = &tmp; @@ -1690,8 +1694,8 @@ static struct dst_entry *xfrm_bundle_create(struct xfrm_policy *policy, if (xfrm[i]->props.mode != XFRM_MODE_TRANSPORT) { family = xfrm[i]->props.family; - dst = xfrm_dst_lookup(xfrm[i], tos, &saddr, &daddr, - family); + dst = xfrm_dst_lookup(xfrm[i], tos, fl->flowi_oif, + &saddr, &daddr, family); err = PTR_ERR(dst); if (IS_ERR(dst)) goto put_states; diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c index bd16c6c7e1e7..a8de9e300200 100644 --- a/net/xfrm/xfrm_user.c +++ b/net/xfrm/xfrm_user.c @@ -925,12 +925,10 @@ static int xfrm_dump_sa(struct sk_buff *skb, struct netlink_callback *cb) return err; if (attrs[XFRMA_ADDRESS_FILTER]) { - filter = kmalloc(sizeof(*filter), GFP_KERNEL); + filter = kmemdup(nla_data(attrs[XFRMA_ADDRESS_FILTER]), + sizeof(*filter), GFP_KERNEL); if (filter == NULL) return -ENOMEM; - - memcpy(filter, nla_data(attrs[XFRMA_ADDRESS_FILTER]), - sizeof(*filter)); } if (attrs[XFRMA_PROTO]) @@ -2048,7 +2046,7 @@ static int xfrm_add_pol_expire(struct sk_buff *skb, struct nlmsghdr *nlh, xfrm_audit_policy_delete(xp, 1, true); } else { // reset the timers here? - WARN(1, "Dont know what to do with soft policy expire\n"); + WARN(1, "Don't know what to do with soft policy expire\n"); } km_policy_expired(xp, p->dir, up->hard, nlh->nlmsg_pid); |