diff options
author | Igor Opaniuk <igor.opaniuk@toradex.com> | 2020-11-13 14:11:10 +0200 |
---|---|---|
committer | Igor Opaniuk <igor.opaniuk@toradex.com> | 2020-11-13 14:17:32 +0200 |
commit | 3b59d4725be760cd276094079b4fbe7bd44e1464 (patch) | |
tree | 37a4892c12efe64a69453ecdb694866dd18dc4f5 /net | |
parent | 4d47b797d6bb1db34ddf702f2cf78104be135a8f (diff) | |
parent | 70d1232fdbe28e4c765c4cfc3cc5c7580959d5e0 (diff) |
Merge commit '70d1232fdbe28e4c765c4cfc3cc5c7580959d5e0' into toradex_5.4-2.1.x-imx
Update 5.4-2.1.x-imx to v5.4.74 from [1].
[1] https://github.com/Freescale/linux-fslc
Diffstat (limited to 'net')
226 files changed, 2490 insertions, 1286 deletions
diff --git a/net/9p/trans_fd.c b/net/9p/trans_fd.c index 13cd683a658a..12ecacf0c55f 100644 --- a/net/9p/trans_fd.c +++ b/net/9p/trans_fd.c @@ -362,6 +362,10 @@ static void p9_read_work(struct work_struct *work) if (m->rreq->status == REQ_STATUS_SENT) { list_del(&m->rreq->req_list); p9_client_cb(m->client, m->rreq, REQ_STATUS_RCVD); + } else if (m->rreq->status == REQ_STATUS_FLSHD) { + /* Ignore replies associated with a cancelled request. */ + p9_debug(P9_DEBUG_TRANS, + "Ignore replies associated with a cancelled request\n"); } else { spin_unlock(&m->client->lock); p9_debug(P9_DEBUG_ERROR, @@ -703,11 +707,20 @@ static int p9_fd_cancelled(struct p9_client *client, struct p9_req_t *req) { p9_debug(P9_DEBUG_TRANS, "client %p req %p\n", client, req); + spin_lock(&client->lock); + /* Ignore cancelled request if message has been received + * before lock. + */ + if (req->status == REQ_STATUS_RCVD) { + spin_unlock(&client->lock); + return 0; + } + /* we haven't received a response for oldreq, * remove it from the list. */ - spin_lock(&client->lock); list_del(&req->req_list); + req->status = REQ_STATUS_FLSHD; spin_unlock(&client->lock); p9_req_put(req); @@ -803,20 +816,28 @@ static int p9_fd_open(struct p9_client *client, int rfd, int wfd) return -ENOMEM; ts->rd = fget(rfd); + if (!ts->rd) + goto out_free_ts; + if (!(ts->rd->f_mode & FMODE_READ)) + goto out_put_rd; ts->wr = fget(wfd); - if (!ts->rd || !ts->wr) { - if (ts->rd) - fput(ts->rd); - if (ts->wr) - fput(ts->wr); - kfree(ts); - return -EIO; - } + if (!ts->wr) + goto out_put_rd; + if (!(ts->wr->f_mode & FMODE_WRITE)) + goto out_put_wr; client->trans = ts; client->status = Connected; return 0; + +out_put_wr: + fput(ts->wr); +out_put_rd: + fput(ts->rd); +out_free_ts: + kfree(ts); + return -EIO; } static int p9_socket_open(struct p9_client *client, struct socket *csocket) diff --git a/net/appletalk/atalk_proc.c b/net/appletalk/atalk_proc.c index 550c6ca007cc..9c1241292d1d 100644 --- a/net/appletalk/atalk_proc.c +++ b/net/appletalk/atalk_proc.c @@ -229,6 +229,8 @@ int __init atalk_proc_init(void) sizeof(struct aarp_iter_state), NULL)) goto out; + return 0; + out: remove_proc_subtree("atalk", init_net.proc_net); return -ENOMEM; diff --git a/net/atm/lec.c b/net/atm/lec.c index 5a77c235a212..3625a04a6c70 100644 --- a/net/atm/lec.c +++ b/net/atm/lec.c @@ -1269,6 +1269,12 @@ static void lec_arp_clear_vccs(struct lec_arp_table *entry) entry->vcc = NULL; } if (entry->recv_vcc) { + struct atm_vcc *vcc = entry->recv_vcc; + struct lec_vcc_priv *vpriv = LEC_VCC_PRIV(vcc); + + kfree(vpriv); + vcc->user_back = NULL; + entry->recv_vcc->push = entry->old_recv_push; vcc_release_async(entry->recv_vcc, -EPIPE); entry->recv_vcc = NULL; diff --git a/net/atm/proc.c b/net/atm/proc.c index d79221fd4dae..c31896707313 100644 --- a/net/atm/proc.c +++ b/net/atm/proc.c @@ -134,8 +134,7 @@ static void vcc_seq_stop(struct seq_file *seq, void *v) static void *vcc_seq_next(struct seq_file *seq, void *v, loff_t *pos) { v = vcc_walk(seq, 1); - if (v) - (*pos)++; + (*pos)++; return v; } diff --git a/net/ax25/af_ax25.c b/net/ax25/af_ax25.c index e5a3dc28116d..2fdb1b573e8c 100644 --- a/net/ax25/af_ax25.c +++ b/net/ax25/af_ax25.c @@ -1187,7 +1187,10 @@ static int __must_check ax25_connect(struct socket *sock, if (addr_len > sizeof(struct sockaddr_ax25) && fsa->fsa_ax25.sax25_ndigis != 0) { /* Valid number of digipeaters ? */ - if (fsa->fsa_ax25.sax25_ndigis < 1 || fsa->fsa_ax25.sax25_ndigis > AX25_MAX_DIGIS) { + if (fsa->fsa_ax25.sax25_ndigis < 1 || + fsa->fsa_ax25.sax25_ndigis > AX25_MAX_DIGIS || + addr_len < sizeof(struct sockaddr_ax25) + + sizeof(ax25_address) * fsa->fsa_ax25.sax25_ndigis) { err = -EINVAL; goto out_release; } @@ -1507,7 +1510,10 @@ static int ax25_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) struct full_sockaddr_ax25 *fsa = (struct full_sockaddr_ax25 *)usax; /* Valid number of digipeaters ? */ - if (usax->sax25_ndigis < 1 || usax->sax25_ndigis > AX25_MAX_DIGIS) { + if (usax->sax25_ndigis < 1 || + usax->sax25_ndigis > AX25_MAX_DIGIS || + addr_len < sizeof(struct sockaddr_ax25) + + sizeof(ax25_address) * usax->sax25_ndigis) { err = -EINVAL; goto out; } diff --git a/net/batman-adv/bat_v_elp.c b/net/batman-adv/bat_v_elp.c index 2614a9caee00..a39af0eefad3 100644 --- a/net/batman-adv/bat_v_elp.c +++ b/net/batman-adv/bat_v_elp.c @@ -120,20 +120,7 @@ static u32 batadv_v_elp_get_throughput(struct batadv_hardif_neigh_node *neigh) rtnl_lock(); ret = __ethtool_get_link_ksettings(hard_iface->net_dev, &link_settings); rtnl_unlock(); - - /* Virtual interface drivers such as tun / tap interfaces, VLAN, etc - * tend to initialize the interface throughput with some value for the - * sake of having a throughput number to export via ethtool. This - * exported throughput leaves batman-adv to conclude the interface - * throughput is genuine (reflecting reality), thus no measurements - * are necessary. - * - * Based on the observation that those interface types also tend to set - * the link auto-negotiation to 'off', batman-adv shall check this - * setting to differentiate between genuine link throughput information - * and placeholders installed by virtual interfaces. - */ - if (ret == 0 && link_settings.base.autoneg == AUTONEG_ENABLE) { + if (ret == 0) { /* link characteristics might change over time */ if (link_settings.base.duplex == DUPLEX_FULL) hard_iface->bat_v.flags |= BATADV_FULL_DUPLEX; diff --git a/net/batman-adv/bat_v_ogm.c b/net/batman-adv/bat_v_ogm.c index a9e7540c5691..3165f6ff8ee7 100644 --- a/net/batman-adv/bat_v_ogm.c +++ b/net/batman-adv/bat_v_ogm.c @@ -878,6 +878,12 @@ static void batadv_v_ogm_process(const struct sk_buff *skb, int ogm_offset, ntohl(ogm_packet->seqno), ogm_throughput, ogm_packet->ttl, ogm_packet->version, ntohs(ogm_packet->tvlv_len)); + if (batadv_is_my_mac(bat_priv, ogm_packet->orig)) { + batadv_dbg(BATADV_DBG_BATMAN, bat_priv, + "Drop packet: originator packet from ourself\n"); + return; + } + /* If the throughput metric is 0, immediately drop the packet. No need * to create orig_node / neigh_node for an unusable route. */ @@ -1005,11 +1011,6 @@ int batadv_v_ogm_packet_recv(struct sk_buff *skb, if (batadv_is_my_mac(bat_priv, ethhdr->h_source)) goto free_skb; - ogm_packet = (struct batadv_ogm2_packet *)skb->data; - - if (batadv_is_my_mac(bat_priv, ogm_packet->orig)) - goto free_skb; - batadv_inc_counter(bat_priv, BATADV_CNT_MGMT_RX); batadv_add_counter(bat_priv, BATADV_CNT_MGMT_RX_BYTES, skb->len + ETH_HLEN); diff --git a/net/batman-adv/bridge_loop_avoidance.c b/net/batman-adv/bridge_loop_avoidance.c index 663a53b6d36e..a6b26ca5c697 100644 --- a/net/batman-adv/bridge_loop_avoidance.c +++ b/net/batman-adv/bridge_loop_avoidance.c @@ -25,6 +25,7 @@ #include <linux/lockdep.h> #include <linux/netdevice.h> #include <linux/netlink.h> +#include <linux/preempt.h> #include <linux/rculist.h> #include <linux/rcupdate.h> #include <linux/seq_file.h> @@ -83,11 +84,12 @@ static inline u32 batadv_choose_claim(const void *data, u32 size) */ static inline u32 batadv_choose_backbone_gw(const void *data, u32 size) { - const struct batadv_bla_claim *claim = (struct batadv_bla_claim *)data; + const struct batadv_bla_backbone_gw *gw; u32 hash = 0; - hash = jhash(&claim->addr, sizeof(claim->addr), hash); - hash = jhash(&claim->vid, sizeof(claim->vid), hash); + gw = (struct batadv_bla_backbone_gw *)data; + hash = jhash(&gw->orig, sizeof(gw->orig), hash); + hash = jhash(&gw->vid, sizeof(gw->vid), hash); return hash % size; } @@ -437,7 +439,10 @@ static void batadv_bla_send_claim(struct batadv_priv *bat_priv, u8 *mac, batadv_add_counter(bat_priv, BATADV_CNT_RX_BYTES, skb->len + ETH_HLEN); - netif_rx(skb); + if (in_interrupt()) + netif_rx(skb); + else + netif_rx_ni(skb); out: if (primary_if) batadv_hardif_put(primary_if); @@ -1576,13 +1581,16 @@ int batadv_bla_init(struct batadv_priv *bat_priv) } /** - * batadv_bla_check_bcast_duplist() - Check if a frame is in the broadcast dup. + * batadv_bla_check_duplist() - Check if a frame is in the broadcast dup. * @bat_priv: the bat priv with all the soft interface information - * @skb: contains the bcast_packet to be checked + * @skb: contains the multicast packet to be checked + * @payload_ptr: pointer to position inside the head buffer of the skb + * marking the start of the data to be CRC'ed + * @orig: originator mac address, NULL if unknown * - * check if it is on our broadcast list. Another gateway might - * have sent the same packet because it is connected to the same backbone, - * so we have to remove this duplicate. + * Check if it is on our broadcast list. Another gateway might have sent the + * same packet because it is connected to the same backbone, so we have to + * remove this duplicate. * * This is performed by checking the CRC, which will tell us * with a good chance that it is the same packet. If it is furthermore @@ -1591,19 +1599,17 @@ int batadv_bla_init(struct batadv_priv *bat_priv) * * Return: true if a packet is in the duplicate list, false otherwise. */ -bool batadv_bla_check_bcast_duplist(struct batadv_priv *bat_priv, - struct sk_buff *skb) +static bool batadv_bla_check_duplist(struct batadv_priv *bat_priv, + struct sk_buff *skb, u8 *payload_ptr, + const u8 *orig) { - int i, curr; - __be32 crc; - struct batadv_bcast_packet *bcast_packet; struct batadv_bcast_duplist_entry *entry; bool ret = false; - - bcast_packet = (struct batadv_bcast_packet *)skb->data; + int i, curr; + __be32 crc; /* calculate the crc ... */ - crc = batadv_skb_crc32(skb, (u8 *)(bcast_packet + 1)); + crc = batadv_skb_crc32(skb, payload_ptr); spin_lock_bh(&bat_priv->bla.bcast_duplist_lock); @@ -1622,8 +1628,21 @@ bool batadv_bla_check_bcast_duplist(struct batadv_priv *bat_priv, if (entry->crc != crc) continue; - if (batadv_compare_eth(entry->orig, bcast_packet->orig)) - continue; + /* are the originators both known and not anonymous? */ + if (orig && !is_zero_ether_addr(orig) && + !is_zero_ether_addr(entry->orig)) { + /* If known, check if the new frame came from + * the same originator: + * We are safe to take identical frames from the + * same orig, if known, as multiplications in + * the mesh are detected via the (orig, seqno) pair. + * So we can be a bit more liberal here and allow + * identical frames from the same orig which the source + * host might have sent multiple times on purpose. + */ + if (batadv_compare_eth(entry->orig, orig)) + continue; + } /* this entry seems to match: same crc, not too old, * and from another gw. therefore return true to forbid it. @@ -1639,7 +1658,14 @@ bool batadv_bla_check_bcast_duplist(struct batadv_priv *bat_priv, entry = &bat_priv->bla.bcast_duplist[curr]; entry->crc = crc; entry->entrytime = jiffies; - ether_addr_copy(entry->orig, bcast_packet->orig); + + /* known originator */ + if (orig) + ether_addr_copy(entry->orig, orig); + /* anonymous originator */ + else + eth_zero_addr(entry->orig); + bat_priv->bla.bcast_duplist_curr = curr; out: @@ -1649,6 +1675,48 @@ out: } /** + * batadv_bla_check_ucast_duplist() - Check if a frame is in the broadcast dup. + * @bat_priv: the bat priv with all the soft interface information + * @skb: contains the multicast packet to be checked, decapsulated from a + * unicast_packet + * + * Check if it is on our broadcast list. Another gateway might have sent the + * same packet because it is connected to the same backbone, so we have to + * remove this duplicate. + * + * Return: true if a packet is in the duplicate list, false otherwise. + */ +static bool batadv_bla_check_ucast_duplist(struct batadv_priv *bat_priv, + struct sk_buff *skb) +{ + return batadv_bla_check_duplist(bat_priv, skb, (u8 *)skb->data, NULL); +} + +/** + * batadv_bla_check_bcast_duplist() - Check if a frame is in the broadcast dup. + * @bat_priv: the bat priv with all the soft interface information + * @skb: contains the bcast_packet to be checked + * + * Check if it is on our broadcast list. Another gateway might have sent the + * same packet because it is connected to the same backbone, so we have to + * remove this duplicate. + * + * Return: true if a packet is in the duplicate list, false otherwise. + */ +bool batadv_bla_check_bcast_duplist(struct batadv_priv *bat_priv, + struct sk_buff *skb) +{ + struct batadv_bcast_packet *bcast_packet; + u8 *payload_ptr; + + bcast_packet = (struct batadv_bcast_packet *)skb->data; + payload_ptr = (u8 *)(bcast_packet + 1); + + return batadv_bla_check_duplist(bat_priv, skb, payload_ptr, + bcast_packet->orig); +} + +/** * batadv_bla_is_backbone_gw_orig() - Check if the originator is a gateway for * the VLAN identified by vid. * @bat_priv: the bat priv with all the soft interface information @@ -1809,7 +1877,7 @@ batadv_bla_loopdetect_check(struct batadv_priv *bat_priv, struct sk_buff *skb, * @bat_priv: the bat priv with all the soft interface information * @skb: the frame to be checked * @vid: the VLAN ID of the frame - * @is_bcast: the packet came in a broadcast packet type. + * @packet_type: the batman packet type this frame came in * * batadv_bla_rx avoidance checks if: * * we have to race for a claim @@ -1821,7 +1889,7 @@ batadv_bla_loopdetect_check(struct batadv_priv *bat_priv, struct sk_buff *skb, * further process the skb. */ bool batadv_bla_rx(struct batadv_priv *bat_priv, struct sk_buff *skb, - unsigned short vid, bool is_bcast) + unsigned short vid, int packet_type) { struct batadv_bla_backbone_gw *backbone_gw; struct ethhdr *ethhdr; @@ -1843,9 +1911,32 @@ bool batadv_bla_rx(struct batadv_priv *bat_priv, struct sk_buff *skb, goto handled; if (unlikely(atomic_read(&bat_priv->bla.num_requests))) - /* don't allow broadcasts while requests are in flight */ - if (is_multicast_ether_addr(ethhdr->h_dest) && is_bcast) - goto handled; + /* don't allow multicast packets while requests are in flight */ + if (is_multicast_ether_addr(ethhdr->h_dest)) + /* Both broadcast flooding or multicast-via-unicasts + * delivery might send to multiple backbone gateways + * sharing the same LAN and therefore need to coordinate + * which backbone gateway forwards into the LAN, + * by claiming the payload source address. + * + * Broadcast flooding and multicast-via-unicasts + * delivery use the following two batman packet types. + * Note: explicitly exclude BATADV_UNICAST_4ADDR, + * as the DHCP gateway feature will send explicitly + * to only one BLA gateway, so the claiming process + * should be avoided there. + */ + if (packet_type == BATADV_BCAST || + packet_type == BATADV_UNICAST) + goto handled; + + /* potential duplicates from foreign BLA backbone gateways via + * multicast-in-unicast packets + */ + if (is_multicast_ether_addr(ethhdr->h_dest) && + packet_type == BATADV_UNICAST && + batadv_bla_check_ucast_duplist(bat_priv, skb)) + goto handled; ether_addr_copy(search_claim.addr, ethhdr->h_source); search_claim.vid = vid; @@ -1880,13 +1971,14 @@ bool batadv_bla_rx(struct batadv_priv *bat_priv, struct sk_buff *skb, goto allow; } - /* if it is a broadcast ... */ - if (is_multicast_ether_addr(ethhdr->h_dest) && is_bcast) { + /* if it is a multicast ... */ + if (is_multicast_ether_addr(ethhdr->h_dest) && + (packet_type == BATADV_BCAST || packet_type == BATADV_UNICAST)) { /* ... drop it. the responsible gateway is in charge. * - * We need to check is_bcast because with the gateway + * We need to check packet type because with the gateway * feature, broadcasts (like DHCP requests) may be sent - * using a unicast packet type. + * using a unicast 4 address packet type. See comment above. */ goto handled; } else { diff --git a/net/batman-adv/bridge_loop_avoidance.h b/net/batman-adv/bridge_loop_avoidance.h index 02b24a861a85..9370be015813 100644 --- a/net/batman-adv/bridge_loop_avoidance.h +++ b/net/batman-adv/bridge_loop_avoidance.h @@ -35,7 +35,7 @@ static inline bool batadv_bla_is_loopdetect_mac(const uint8_t *mac) #ifdef CONFIG_BATMAN_ADV_BLA bool batadv_bla_rx(struct batadv_priv *bat_priv, struct sk_buff *skb, - unsigned short vid, bool is_bcast); + unsigned short vid, int packet_type); bool batadv_bla_tx(struct batadv_priv *bat_priv, struct sk_buff *skb, unsigned short vid); bool batadv_bla_is_backbone_gw(struct sk_buff *skb, @@ -66,7 +66,7 @@ bool batadv_bla_check_claim(struct batadv_priv *bat_priv, u8 *addr, static inline bool batadv_bla_rx(struct batadv_priv *bat_priv, struct sk_buff *skb, unsigned short vid, - bool is_bcast) + int packet_type) { return false; } diff --git a/net/batman-adv/gateway_client.c b/net/batman-adv/gateway_client.c index 47df4c678988..89c9097007c3 100644 --- a/net/batman-adv/gateway_client.c +++ b/net/batman-adv/gateway_client.c @@ -703,8 +703,10 @@ batadv_gw_dhcp_recipient_get(struct sk_buff *skb, unsigned int *header_len, chaddr_offset = *header_len + BATADV_DHCP_CHADDR_OFFSET; /* store the client address if the message is going to a client */ - if (ret == BATADV_DHCP_TO_CLIENT && - pskb_may_pull(skb, chaddr_offset + ETH_ALEN)) { + if (ret == BATADV_DHCP_TO_CLIENT) { + if (!pskb_may_pull(skb, chaddr_offset + ETH_ALEN)) + return BATADV_DHCP_NO; + /* check if the DHCP packet carries an Ethernet DHCP */ p = skb->data + *header_len + BATADV_DHCP_HTYPE_OFFSET; if (*p != BATADV_DHCP_HTYPE_ETHERNET) diff --git a/net/batman-adv/multicast.c b/net/batman-adv/multicast.c index 1d5bdf3a4b65..f5bf931252c4 100644 --- a/net/batman-adv/multicast.c +++ b/net/batman-adv/multicast.c @@ -51,6 +51,7 @@ #include <uapi/linux/batadv_packet.h> #include <uapi/linux/batman_adv.h> +#include "bridge_loop_avoidance.h" #include "hard-interface.h" #include "hash.h" #include "log.h" @@ -1435,6 +1436,35 @@ batadv_mcast_forw_mode(struct batadv_priv *bat_priv, struct sk_buff *skb, } /** + * batadv_mcast_forw_send_orig() - send a multicast packet to an originator + * @bat_priv: the bat priv with all the soft interface information + * @skb: the multicast packet to send + * @vid: the vlan identifier + * @orig_node: the originator to send the packet to + * + * Return: NET_XMIT_DROP in case of error or NET_XMIT_SUCCESS otherwise. + */ +int batadv_mcast_forw_send_orig(struct batadv_priv *bat_priv, + struct sk_buff *skb, + unsigned short vid, + struct batadv_orig_node *orig_node) +{ + /* Avoid sending multicast-in-unicast packets to other BLA + * gateways - they already got the frame from the LAN side + * we share with them. + * TODO: Refactor to take BLA into account earlier, to avoid + * reducing the mcast_fanout count. + */ + if (batadv_bla_is_backbone_gw_orig(bat_priv, orig_node->orig, vid)) { + dev_kfree_skb(skb); + return NET_XMIT_SUCCESS; + } + + return batadv_send_skb_unicast(bat_priv, skb, BATADV_UNICAST, 0, + orig_node, vid); +} + +/** * batadv_mcast_forw_tt() - forwards a packet to multicast listeners * @bat_priv: the bat priv with all the soft interface information * @skb: the multicast packet to transmit @@ -1471,8 +1501,8 @@ batadv_mcast_forw_tt(struct batadv_priv *bat_priv, struct sk_buff *skb, break; } - batadv_send_skb_unicast(bat_priv, newskb, BATADV_UNICAST, 0, - orig_entry->orig_node, vid); + batadv_mcast_forw_send_orig(bat_priv, newskb, vid, + orig_entry->orig_node); } rcu_read_unlock(); @@ -1513,8 +1543,7 @@ batadv_mcast_forw_want_all_ipv4(struct batadv_priv *bat_priv, break; } - batadv_send_skb_unicast(bat_priv, newskb, BATADV_UNICAST, 0, - orig_node, vid); + batadv_mcast_forw_send_orig(bat_priv, newskb, vid, orig_node); } rcu_read_unlock(); return ret; @@ -1551,8 +1580,7 @@ batadv_mcast_forw_want_all_ipv6(struct batadv_priv *bat_priv, break; } - batadv_send_skb_unicast(bat_priv, newskb, BATADV_UNICAST, 0, - orig_node, vid); + batadv_mcast_forw_send_orig(bat_priv, newskb, vid, orig_node); } rcu_read_unlock(); return ret; @@ -1618,8 +1646,7 @@ batadv_mcast_forw_want_all_rtr4(struct batadv_priv *bat_priv, break; } - batadv_send_skb_unicast(bat_priv, newskb, BATADV_UNICAST, 0, - orig_node, vid); + batadv_mcast_forw_send_orig(bat_priv, newskb, vid, orig_node); } rcu_read_unlock(); return ret; @@ -1656,8 +1683,7 @@ batadv_mcast_forw_want_all_rtr6(struct batadv_priv *bat_priv, break; } - batadv_send_skb_unicast(bat_priv, newskb, BATADV_UNICAST, 0, - orig_node, vid); + batadv_mcast_forw_send_orig(bat_priv, newskb, vid, orig_node); } rcu_read_unlock(); return ret; diff --git a/net/batman-adv/multicast.h b/net/batman-adv/multicast.h index 5d9e2bb29c97..403929013ac4 100644 --- a/net/batman-adv/multicast.h +++ b/net/batman-adv/multicast.h @@ -46,6 +46,11 @@ enum batadv_forw_mode batadv_mcast_forw_mode(struct batadv_priv *bat_priv, struct sk_buff *skb, struct batadv_orig_node **mcast_single_orig); +int batadv_mcast_forw_send_orig(struct batadv_priv *bat_priv, + struct sk_buff *skb, + unsigned short vid, + struct batadv_orig_node *orig_node); + int batadv_mcast_forw_send(struct batadv_priv *bat_priv, struct sk_buff *skb, unsigned short vid); @@ -72,6 +77,16 @@ batadv_mcast_forw_mode(struct batadv_priv *bat_priv, struct sk_buff *skb, } static inline int +batadv_mcast_forw_send_orig(struct batadv_priv *bat_priv, + struct sk_buff *skb, + unsigned short vid, + struct batadv_orig_node *orig_node) +{ + kfree_skb(skb); + return NET_XMIT_DROP; +} + +static inline int batadv_mcast_forw_send(struct batadv_priv *bat_priv, struct sk_buff *skb, unsigned short vid) { diff --git a/net/batman-adv/routing.c b/net/batman-adv/routing.c index f0f864820dea..708e90cb18a6 100644 --- a/net/batman-adv/routing.c +++ b/net/batman-adv/routing.c @@ -826,6 +826,10 @@ static bool batadv_check_unicast_ttvn(struct batadv_priv *bat_priv, vid = batadv_get_vid(skb, hdr_len); ethhdr = (struct ethhdr *)(skb->data + hdr_len); + /* do not reroute multicast frames in a unicast header */ + if (is_multicast_ether_addr(ethhdr->h_dest)) + return true; + /* check if the destination client was served by this node and it is now * roaming. In this case, it means that the node has got a ROAM_ADV * message and that it knows the new destination in the mesh to re-route diff --git a/net/batman-adv/soft-interface.c b/net/batman-adv/soft-interface.c index 5ee8e9a100f9..7f209390069e 100644 --- a/net/batman-adv/soft-interface.c +++ b/net/batman-adv/soft-interface.c @@ -364,9 +364,8 @@ send: goto dropped; ret = batadv_send_skb_via_gw(bat_priv, skb, vid); } else if (mcast_single_orig) { - ret = batadv_send_skb_unicast(bat_priv, skb, - BATADV_UNICAST, 0, - mcast_single_orig, vid); + ret = batadv_mcast_forw_send_orig(bat_priv, skb, vid, + mcast_single_orig); } else if (forw_mode == BATADV_FORW_SOME) { ret = batadv_mcast_forw_send(bat_priv, skb, vid); } else { @@ -425,10 +424,10 @@ void batadv_interface_rx(struct net_device *soft_iface, struct vlan_ethhdr *vhdr; struct ethhdr *ethhdr; unsigned short vid; - bool is_bcast; + int packet_type; batadv_bcast_packet = (struct batadv_bcast_packet *)skb->data; - is_bcast = (batadv_bcast_packet->packet_type == BATADV_BCAST); + packet_type = batadv_bcast_packet->packet_type; skb_pull_rcsum(skb, hdr_size); skb_reset_mac_header(skb); @@ -471,7 +470,7 @@ void batadv_interface_rx(struct net_device *soft_iface, /* Let the bridge loop avoidance check the packet. If will * not handle it, we can safely push it up. */ - if (batadv_bla_rx(bat_priv, skb, vid, is_bcast)) + if (batadv_bla_rx(bat_priv, skb, vid, packet_type)) goto out; if (orig_node) diff --git a/net/bluetooth/6lowpan.c b/net/bluetooth/6lowpan.c index 4febc82a7c76..52fb6d6d6d58 100644 --- a/net/bluetooth/6lowpan.c +++ b/net/bluetooth/6lowpan.c @@ -50,6 +50,7 @@ static bool enable_6lowpan; /* We are listening incoming connections via this channel */ static struct l2cap_chan *listen_chan; +static DEFINE_MUTEX(set_lock); struct lowpan_peer { struct list_head list; @@ -1070,12 +1071,14 @@ static void do_enable_set(struct work_struct *work) enable_6lowpan = set_enable->flag; + mutex_lock(&set_lock); if (listen_chan) { l2cap_chan_close(listen_chan, 0); l2cap_chan_put(listen_chan); } listen_chan = bt_6lowpan_listen(); + mutex_unlock(&set_lock); kfree(set_enable); } @@ -1127,11 +1130,13 @@ static ssize_t lowpan_control_write(struct file *fp, if (ret == -EINVAL) return ret; + mutex_lock(&set_lock); if (listen_chan) { l2cap_chan_close(listen_chan, 0); l2cap_chan_put(listen_chan); listen_chan = NULL; } + mutex_unlock(&set_lock); if (conn) { struct lowpan_peer *peer; diff --git a/net/bluetooth/a2mp.c b/net/bluetooth/a2mp.c index 26526be579c7..da7fd7c8c2dc 100644 --- a/net/bluetooth/a2mp.c +++ b/net/bluetooth/a2mp.c @@ -226,6 +226,9 @@ static int a2mp_discover_rsp(struct amp_mgr *mgr, struct sk_buff *skb, struct a2mp_info_req req; found = true; + + memset(&req, 0, sizeof(req)); + req.id = cl->id; a2mp_send(mgr, A2MP_GETINFO_REQ, __next_ident(mgr), sizeof(req), &req); @@ -305,6 +308,8 @@ static int a2mp_getinfo_req(struct amp_mgr *mgr, struct sk_buff *skb, if (!hdev || hdev->dev_type != HCI_AMP) { struct a2mp_info_rsp rsp; + memset(&rsp, 0, sizeof(rsp)); + rsp.id = req->id; rsp.status = A2MP_STATUS_INVALID_CTRL_ID; @@ -348,6 +353,8 @@ static int a2mp_getinfo_rsp(struct amp_mgr *mgr, struct sk_buff *skb, if (!ctrl) return -ENOMEM; + memset(&req, 0, sizeof(req)); + req.id = rsp->id; a2mp_send(mgr, A2MP_GETAMPASSOC_REQ, __next_ident(mgr), sizeof(req), &req); @@ -376,6 +383,8 @@ static int a2mp_getampassoc_req(struct amp_mgr *mgr, struct sk_buff *skb, struct a2mp_amp_assoc_rsp rsp; rsp.id = req->id; + memset(&rsp, 0, sizeof(rsp)); + if (tmp) { rsp.status = A2MP_STATUS_COLLISION_OCCURED; amp_mgr_put(tmp); @@ -464,7 +473,6 @@ static int a2mp_createphyslink_req(struct amp_mgr *mgr, struct sk_buff *skb, struct a2mp_cmd *hdr) { struct a2mp_physlink_req *req = (void *) skb->data; - struct a2mp_physlink_rsp rsp; struct hci_dev *hdev; struct hci_conn *hcon; @@ -475,6 +483,8 @@ static int a2mp_createphyslink_req(struct amp_mgr *mgr, struct sk_buff *skb, BT_DBG("local_id %d, remote_id %d", req->local_id, req->remote_id); + memset(&rsp, 0, sizeof(rsp)); + rsp.local_id = req->remote_id; rsp.remote_id = req->local_id; @@ -553,6 +563,8 @@ static int a2mp_discphyslink_req(struct amp_mgr *mgr, struct sk_buff *skb, BT_DBG("local_id %d remote_id %d", req->local_id, req->remote_id); + memset(&rsp, 0, sizeof(rsp)); + rsp.local_id = req->remote_id; rsp.remote_id = req->local_id; rsp.status = A2MP_STATUS_SUCCESS; @@ -675,6 +687,8 @@ static int a2mp_chan_recv_cb(struct l2cap_chan *chan, struct sk_buff *skb) if (err) { struct a2mp_cmd_rej rej; + memset(&rej, 0, sizeof(rej)); + rej.reason = cpu_to_le16(0); hdr = (void *) skb->data; @@ -898,6 +912,8 @@ void a2mp_send_getinfo_rsp(struct hci_dev *hdev) BT_DBG("%s mgr %p", hdev->name, mgr); + memset(&rsp, 0, sizeof(rsp)); + rsp.id = hdev->id; rsp.status = A2MP_STATUS_INVALID_CTRL_ID; @@ -995,6 +1011,8 @@ void a2mp_send_create_phy_link_rsp(struct hci_dev *hdev, u8 status) if (!mgr) return; + memset(&rsp, 0, sizeof(rsp)); + hs_hcon = hci_conn_hash_lookup_state(hdev, AMP_LINK, BT_CONNECT); if (!hs_hcon) { rsp.status = A2MP_STATUS_UNABLE_START_LINK_CREATION; @@ -1027,6 +1045,8 @@ void a2mp_discover_amp(struct l2cap_chan *chan) mgr->bredr_chan = chan; + memset(&req, 0, sizeof(req)); + req.mtu = cpu_to_le16(L2CAP_A2MP_DEFAULT_MTU); req.ext_feat = 0; a2mp_send(mgr, A2MP_DISCOVER_REQ, 1, sizeof(req), &req); diff --git a/net/bluetooth/hci_conn.c b/net/bluetooth/hci_conn.c index 83893b82a748..f07a2b11c3c9 100644 --- a/net/bluetooth/hci_conn.c +++ b/net/bluetooth/hci_conn.c @@ -1282,6 +1282,23 @@ int hci_conn_check_link_mode(struct hci_conn *conn) return 0; } + /* AES encryption is required for Level 4: + * + * BLUETOOTH CORE SPECIFICATION Version 5.2 | Vol 3, Part C + * page 1319: + * + * 128-bit equivalent strength for link and encryption keys + * required using FIPS approved algorithms (E0 not allowed, + * SAFER+ not allowed, and P-192 not allowed; encryption key + * not shortened) + */ + if (conn->sec_level == BT_SECURITY_FIPS && + !test_bit(HCI_CONN_AES_CCM, &conn->flags)) { + bt_dev_err(conn->hdev, + "Invalid security: Missing AES-CCM usage"); + return 0; + } + if (hci_conn_ssp_enabled(conn) && !test_bit(HCI_CONN_ENCRYPT, &conn->flags)) return 0; diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c index c1d3a303d97f..9917b399ddd0 100644 --- a/net/bluetooth/hci_event.c +++ b/net/bluetooth/hci_event.c @@ -41,12 +41,27 @@ /* Handle HCI Event packets */ -static void hci_cc_inquiry_cancel(struct hci_dev *hdev, struct sk_buff *skb) +static void hci_cc_inquiry_cancel(struct hci_dev *hdev, struct sk_buff *skb, + u8 *new_status) { __u8 status = *((__u8 *) skb->data); BT_DBG("%s status 0x%2.2x", hdev->name, status); + /* It is possible that we receive Inquiry Complete event right + * before we receive Inquiry Cancel Command Complete event, in + * which case the latter event should have status of Command + * Disallowed (0x0c). This should not be treated as error, since + * we actually achieve what Inquiry Cancel wants to achieve, + * which is to end the last Inquiry session. + */ + if (status == 0x0c && !test_bit(HCI_INQUIRY, &hdev->flags)) { + bt_dev_warn(hdev, "Ignoring error of Inquiry Cancel command"); + status = 0x00; + } + + *new_status = status; + if (status) return; @@ -1274,6 +1289,9 @@ static void store_pending_adv_report(struct hci_dev *hdev, bdaddr_t *bdaddr, { struct discovery_state *d = &hdev->discovery; + if (len > HCI_MAX_AD_LENGTH) + return; + bacpy(&d->last_adv_addr, bdaddr); d->last_adv_addr_type = bdaddr_type; d->last_adv_rssi = rssi; @@ -2441,7 +2459,7 @@ static void hci_inquiry_result_evt(struct hci_dev *hdev, struct sk_buff *skb) BT_DBG("%s num_rsp %d", hdev->name, num_rsp); - if (!num_rsp) + if (!num_rsp || skb->len < num_rsp * sizeof(*info) + 1) return; if (hci_dev_test_flag(hdev, HCI_PERIODIC_INQ)) @@ -2822,7 +2840,7 @@ static void hci_auth_complete_evt(struct hci_dev *hdev, struct sk_buff *skb) &cp); } else { clear_bit(HCI_CONN_ENCRYPT_PEND, &conn->flags); - hci_encrypt_cfm(conn, ev->status, 0x00); + hci_encrypt_cfm(conn, ev->status); } } @@ -2907,22 +2925,7 @@ static void read_enc_key_size_complete(struct hci_dev *hdev, u8 status, conn->enc_key_size = rp->key_size; } - if (conn->state == BT_CONFIG) { - conn->state = BT_CONNECTED; - hci_connect_cfm(conn, 0); - hci_conn_drop(conn); - } else { - u8 encrypt; - - if (!test_bit(HCI_CONN_ENCRYPT, &conn->flags)) - encrypt = 0x00; - else if (test_bit(HCI_CONN_AES_CCM, &conn->flags)) - encrypt = 0x02; - else - encrypt = 0x01; - - hci_encrypt_cfm(conn, 0, encrypt); - } + hci_encrypt_cfm(conn, 0); unlock: hci_dev_unlock(hdev); @@ -2971,27 +2974,23 @@ static void hci_encrypt_change_evt(struct hci_dev *hdev, struct sk_buff *skb) clear_bit(HCI_CONN_ENCRYPT_PEND, &conn->flags); + /* Check link security requirements are met */ + if (!hci_conn_check_link_mode(conn)) + ev->status = HCI_ERROR_AUTH_FAILURE; + if (ev->status && conn->state == BT_CONNECTED) { if (ev->status == HCI_ERROR_PIN_OR_KEY_MISSING) set_bit(HCI_CONN_AUTH_FAILURE, &conn->flags); + /* Notify upper layers so they can cleanup before + * disconnecting. + */ + hci_encrypt_cfm(conn, ev->status); hci_disconnect(conn, HCI_ERROR_AUTH_FAILURE); hci_conn_drop(conn); goto unlock; } - /* In Secure Connections Only mode, do not allow any connections - * that are not encrypted with AES-CCM using a P-256 authenticated - * combination key. - */ - if (hci_dev_test_flag(hdev, HCI_SC_ONLY) && - (!test_bit(HCI_CONN_AES_CCM, &conn->flags) || - conn->key_type != HCI_LK_AUTH_COMBINATION_P256)) { - hci_connect_cfm(conn, HCI_ERROR_AUTH_FAILURE); - hci_conn_drop(conn); - goto unlock; - } - /* Try reading the encryption key size for encrypted ACL links */ if (!ev->status && ev->encrypt && conn->type == ACL_LINK) { struct hci_cp_read_enc_key_size cp; @@ -3040,14 +3039,7 @@ static void hci_encrypt_change_evt(struct hci_dev *hdev, struct sk_buff *skb) } notify: - if (conn->state == BT_CONFIG) { - if (!ev->status) - conn->state = BT_CONNECTED; - - hci_connect_cfm(conn, ev->status); - hci_conn_drop(conn); - } else - hci_encrypt_cfm(conn, ev->status, ev->encrypt); + hci_encrypt_cfm(conn, ev->status); unlock: hci_dev_unlock(hdev); @@ -3139,7 +3131,7 @@ static void hci_cmd_complete_evt(struct hci_dev *hdev, struct sk_buff *skb, switch (*opcode) { case HCI_OP_INQUIRY_CANCEL: - hci_cc_inquiry_cancel(hdev, skb); + hci_cc_inquiry_cancel(hdev, skb, status); break; case HCI_OP_PERIODIC_INQ: @@ -4064,6 +4056,9 @@ static void hci_inquiry_result_with_rssi_evt(struct hci_dev *hdev, struct inquiry_info_with_rssi_and_pscan_mode *info; info = (void *) (skb->data + 1); + if (skb->len < num_rsp * sizeof(*info) + 1) + goto unlock; + for (; num_rsp; num_rsp--, info++) { u32 flags; @@ -4085,6 +4080,9 @@ static void hci_inquiry_result_with_rssi_evt(struct hci_dev *hdev, } else { struct inquiry_info_with_rssi *info = (void *) (skb->data + 1); + if (skb->len < num_rsp * sizeof(*info) + 1) + goto unlock; + for (; num_rsp; num_rsp--, info++) { u32 flags; @@ -4105,6 +4103,7 @@ static void hci_inquiry_result_with_rssi_evt(struct hci_dev *hdev, } } +unlock: hci_dev_unlock(hdev); } @@ -4216,6 +4215,7 @@ static void hci_sync_conn_complete_evt(struct hci_dev *hdev, case 0x11: /* Unsupported Feature or Parameter Value */ case 0x1c: /* SCO interval rejected */ case 0x1a: /* Unsupported Remote Feature */ + case 0x1e: /* Invalid LMP Parameters */ case 0x1f: /* Unspecified error */ case 0x20: /* Unsupported LMP Parameter value */ if (conn->out) { @@ -4266,7 +4266,7 @@ static void hci_extended_inquiry_result_evt(struct hci_dev *hdev, BT_DBG("%s num_rsp %d", hdev->name, num_rsp); - if (!num_rsp) + if (!num_rsp || skb->len < num_rsp * sizeof(*info) + 1) return; if (hci_dev_test_flag(hdev, HCI_PERIODIC_INQ)) @@ -5230,7 +5230,8 @@ static struct hci_conn *check_pending_le_conn(struct hci_dev *hdev, static void process_adv_report(struct hci_dev *hdev, u8 type, bdaddr_t *bdaddr, u8 bdaddr_type, bdaddr_t *direct_addr, - u8 direct_addr_type, s8 rssi, u8 *data, u8 len) + u8 direct_addr_type, s8 rssi, u8 *data, u8 len, + bool ext_adv) { struct discovery_state *d = &hdev->discovery; struct smp_irk *irk; @@ -5252,6 +5253,11 @@ static void process_adv_report(struct hci_dev *hdev, u8 type, bdaddr_t *bdaddr, return; } + if (!ext_adv && len > HCI_MAX_AD_LENGTH) { + bt_dev_err_ratelimited(hdev, "legacy adv larger than 31 bytes"); + return; + } + /* Find the end of the data in case the report contains padded zero * bytes at the end causing an invalid length value. * @@ -5311,7 +5317,7 @@ static void process_adv_report(struct hci_dev *hdev, u8 type, bdaddr_t *bdaddr, */ conn = check_pending_le_conn(hdev, bdaddr, bdaddr_type, type, direct_addr); - if (conn && type == LE_ADV_IND) { + if (!ext_adv && conn && type == LE_ADV_IND && len <= HCI_MAX_AD_LENGTH) { /* Store report for later inclusion by * mgmt_device_connected */ @@ -5365,7 +5371,7 @@ static void process_adv_report(struct hci_dev *hdev, u8 type, bdaddr_t *bdaddr, * event or send an immediate device found event if the data * should not be stored for later. */ - if (!has_pending_adv_report(hdev)) { + if (!ext_adv && !has_pending_adv_report(hdev)) { /* If the report will trigger a SCAN_REQ store it for * later merging. */ @@ -5400,7 +5406,8 @@ static void process_adv_report(struct hci_dev *hdev, u8 type, bdaddr_t *bdaddr, /* If the new report will trigger a SCAN_REQ store it for * later merging. */ - if (type == LE_ADV_IND || type == LE_ADV_SCAN_IND) { + if (!ext_adv && (type == LE_ADV_IND || + type == LE_ADV_SCAN_IND)) { store_pending_adv_report(hdev, bdaddr, bdaddr_type, rssi, flags, data, len); return; @@ -5440,7 +5447,7 @@ static void hci_le_adv_report_evt(struct hci_dev *hdev, struct sk_buff *skb) rssi = ev->data[ev->length]; process_adv_report(hdev, ev->evt_type, &ev->bdaddr, ev->bdaddr_type, NULL, 0, rssi, - ev->data, ev->length); + ev->data, ev->length, false); } else { bt_dev_err(hdev, "Dropping invalid advertising data"); } @@ -5514,7 +5521,8 @@ static void hci_le_ext_adv_report_evt(struct hci_dev *hdev, struct sk_buff *skb) if (legacy_evt_type != LE_ADV_INVALID) { process_adv_report(hdev, legacy_evt_type, &ev->bdaddr, ev->bdaddr_type, NULL, 0, ev->rssi, - ev->data, ev->length); + ev->data, ev->length, + !(evt_type & LE_EXT_ADV_LEGACY_PDU)); } ptr += sizeof(*ev) + ev->length; @@ -5712,7 +5720,8 @@ static void hci_le_direct_adv_report_evt(struct hci_dev *hdev, process_adv_report(hdev, ev->evt_type, &ev->bdaddr, ev->bdaddr_type, &ev->direct_addr, - ev->direct_addr_type, ev->rssi, NULL, 0); + ev->direct_addr_type, ev->rssi, NULL, 0, + false); ptr += sizeof(*ev); } @@ -5833,6 +5842,11 @@ void hci_event_packet(struct hci_dev *hdev, struct sk_buff *skb) u8 status = 0, event = hdr->evt, req_evt = 0; u16 opcode = HCI_OP_NOP; + if (!event) { + bt_dev_warn(hdev, "Received unexpected HCI Event 00000000"); + goto done; + } + if (hdev->sent_cmd && bt_cb(hdev->sent_cmd)->hci.req_event == event) { struct hci_command_hdr *cmd_hdr = (void *) hdev->sent_cmd->data; opcode = __le16_to_cpu(cmd_hdr->opcode); @@ -6044,6 +6058,7 @@ void hci_event_packet(struct hci_dev *hdev, struct sk_buff *skb) req_complete_skb(hdev, status, opcode, orig_skb); } +done: kfree_skb(orig_skb); kfree_skb(skb); hdev->stat.evt_rx++; diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c index a845786258a0..3499bace25ec 100644 --- a/net/bluetooth/l2cap_core.c +++ b/net/bluetooth/l2cap_core.c @@ -419,6 +419,9 @@ static void l2cap_chan_timeout(struct work_struct *work) BT_DBG("chan %p state %s", chan, state_to_string(chan->state)); mutex_lock(&conn->chan_lock); + /* __set_chan_timer() calls l2cap_chan_hold(chan) while scheduling + * this work. No need to call l2cap_chan_hold(chan) here again. + */ l2cap_chan_lock(chan); if (chan->state == BT_CONNECTED || chan->state == BT_CONFIG) @@ -431,12 +434,12 @@ static void l2cap_chan_timeout(struct work_struct *work) l2cap_chan_close(chan, reason); - l2cap_chan_unlock(chan); - chan->ops->close(chan); - mutex_unlock(&conn->chan_lock); + l2cap_chan_unlock(chan); l2cap_chan_put(chan); + + mutex_unlock(&conn->chan_lock); } struct l2cap_chan *l2cap_chan_create(void) @@ -1734,9 +1737,9 @@ static void l2cap_conn_del(struct hci_conn *hcon, int err) l2cap_chan_del(chan, err); - l2cap_chan_unlock(chan); - chan->ops->close(chan); + + l2cap_chan_unlock(chan); l2cap_chan_put(chan); } @@ -4131,7 +4134,8 @@ static inline int l2cap_config_req(struct l2cap_conn *conn, return 0; } - if (chan->state != BT_CONFIG && chan->state != BT_CONNECT2) { + if (chan->state != BT_CONFIG && chan->state != BT_CONNECT2 && + chan->state != BT_CONNECTED) { cmd_reject_invalid_cid(conn, cmd->ident, chan->scid, chan->dcid); goto unlock; @@ -4355,6 +4359,7 @@ static inline int l2cap_disconnect_req(struct l2cap_conn *conn, return 0; } + l2cap_chan_hold(chan); l2cap_chan_lock(chan); rsp.dcid = cpu_to_le16(chan->scid); @@ -4363,12 +4368,11 @@ static inline int l2cap_disconnect_req(struct l2cap_conn *conn, chan->ops->set_shutdown(chan); - l2cap_chan_hold(chan); l2cap_chan_del(chan, ECONNRESET); - l2cap_chan_unlock(chan); - chan->ops->close(chan); + + l2cap_chan_unlock(chan); l2cap_chan_put(chan); mutex_unlock(&conn->chan_lock); @@ -4400,20 +4404,21 @@ static inline int l2cap_disconnect_rsp(struct l2cap_conn *conn, return 0; } + l2cap_chan_hold(chan); l2cap_chan_lock(chan); if (chan->state != BT_DISCONN) { l2cap_chan_unlock(chan); + l2cap_chan_put(chan); mutex_unlock(&conn->chan_lock); return 0; } - l2cap_chan_hold(chan); l2cap_chan_del(chan, 0); - l2cap_chan_unlock(chan); - chan->ops->close(chan); + + l2cap_chan_unlock(chan); l2cap_chan_put(chan); mutex_unlock(&conn->chan_lock); @@ -6696,9 +6701,10 @@ static int l2cap_data_rcv(struct l2cap_chan *chan, struct sk_buff *skb) goto drop; } - if ((chan->mode == L2CAP_MODE_ERTM || - chan->mode == L2CAP_MODE_STREAMING) && sk_filter(chan->data, skb)) - goto drop; + if (chan->ops->filter) { + if (chan->ops->filter(chan, skb)) + goto drop; + } if (!control->sframe) { int err; diff --git a/net/bluetooth/l2cap_sock.c b/net/bluetooth/l2cap_sock.c index a7be8b59b3c2..8648c5211ebe 100644 --- a/net/bluetooth/l2cap_sock.c +++ b/net/bluetooth/l2cap_sock.c @@ -1042,7 +1042,7 @@ done: } /* Kill socket (only if zapped and orphan) - * Must be called on unlocked socket. + * Must be called on unlocked socket, with l2cap channel lock. */ static void l2cap_sock_kill(struct sock *sk) { @@ -1193,6 +1193,7 @@ static int l2cap_sock_release(struct socket *sock) { struct sock *sk = sock->sk; int err; + struct l2cap_chan *chan; BT_DBG("sock %p, sk %p", sock, sk); @@ -1202,9 +1203,17 @@ static int l2cap_sock_release(struct socket *sock) bt_sock_unlink(&l2cap_sk_list, sk); err = l2cap_sock_shutdown(sock, 2); + chan = l2cap_pi(sk)->chan; + + l2cap_chan_hold(chan); + l2cap_chan_lock(chan); sock_orphan(sk); l2cap_sock_kill(sk); + + l2cap_chan_unlock(chan); + l2cap_chan_put(chan); + return err; } @@ -1222,12 +1231,15 @@ static void l2cap_sock_cleanup_listen(struct sock *parent) BT_DBG("child chan %p state %s", chan, state_to_string(chan->state)); + l2cap_chan_hold(chan); l2cap_chan_lock(chan); + __clear_chan_timer(chan); l2cap_chan_close(chan, ECONNRESET); - l2cap_chan_unlock(chan); - l2cap_sock_kill(sk); + + l2cap_chan_unlock(chan); + l2cap_chan_put(chan); } } @@ -1332,8 +1344,6 @@ static void l2cap_sock_teardown_cb(struct l2cap_chan *chan, int err) parent = bt_sk(sk)->parent; - sock_set_flag(sk, SOCK_ZAPPED); - switch (chan->state) { case BT_OPEN: case BT_BOUND: @@ -1360,8 +1370,11 @@ static void l2cap_sock_teardown_cb(struct l2cap_chan *chan, int err) break; } - release_sock(sk); + + /* Only zap after cleanup to avoid use after free race */ + sock_set_flag(sk, SOCK_ZAPPED); + } static void l2cap_sock_state_change_cb(struct l2cap_chan *chan, int state, @@ -1467,6 +1480,19 @@ static void l2cap_sock_suspend_cb(struct l2cap_chan *chan) sk->sk_state_change(sk); } +static int l2cap_sock_filter(struct l2cap_chan *chan, struct sk_buff *skb) +{ + struct sock *sk = chan->data; + + switch (chan->mode) { + case L2CAP_MODE_ERTM: + case L2CAP_MODE_STREAMING: + return sk_filter(sk, skb); + } + + return 0; +} + static const struct l2cap_ops l2cap_chan_ops = { .name = "L2CAP Socket Interface", .new_connection = l2cap_sock_new_connection_cb, @@ -1481,6 +1507,7 @@ static const struct l2cap_ops l2cap_chan_ops = { .set_shutdown = l2cap_sock_set_shutdown_cb, .get_sndtimeo = l2cap_sock_get_sndtimeo_cb, .alloc_skb = l2cap_sock_alloc_skb_cb, + .filter = l2cap_sock_filter, }; static void l2cap_sock_destruct(struct sock *sk) diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c index acb7c6d5643f..5fce559a61bf 100644 --- a/net/bluetooth/mgmt.c +++ b/net/bluetooth/mgmt.c @@ -756,7 +756,8 @@ static u32 get_supported_settings(struct hci_dev *hdev) if (lmp_ssp_capable(hdev)) { settings |= MGMT_SETTING_SSP; - settings |= MGMT_SETTING_HS; + if (IS_ENABLED(CONFIG_BT_HS)) + settings |= MGMT_SETTING_HS; } if (lmp_sc_capable(hdev)) @@ -1771,6 +1772,10 @@ static int set_hs(struct sock *sk, struct hci_dev *hdev, void *data, u16 len) BT_DBG("request for %s", hdev->name); + if (!IS_ENABLED(CONFIG_BT_HS)) + return mgmt_cmd_status(sk, hdev->id, MGMT_OP_SET_HS, + MGMT_STATUS_NOT_SUPPORTED); + status = mgmt_bredr_support(hdev); if (status) return mgmt_cmd_status(sk, hdev->id, MGMT_OP_SET_HS, status); diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c index ad12fe3fca8c..ee2902b51d45 100644 --- a/net/bridge/br_multicast.c +++ b/net/bridge/br_multicast.c @@ -1007,7 +1007,7 @@ static int br_ip6_multicast_mld2_report(struct net_bridge *br, nsrcs_offset = len + offsetof(struct mld2_grec, grec_nsrcs); if (skb_transport_offset(skb) + ipv6_transport_len(skb) < - nsrcs_offset + sizeof(_nsrcs)) + nsrcs_offset + sizeof(__nsrcs)) return -EINVAL; _nsrcs = skb_header_pointer(skb, nsrcs_offset, diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h index ce2ab14ee605..cecb4223440e 100644 --- a/net/bridge/br_private.h +++ b/net/bridge/br_private.h @@ -208,8 +208,8 @@ struct net_bridge_port_group { struct rcu_head rcu; struct timer_list timer; struct br_ip addr; + unsigned char eth_addr[ETH_ALEN] __aligned(2); unsigned char flags; - unsigned char eth_addr[ETH_ALEN]; }; struct net_bridge_mdb_entry { diff --git a/net/bridge/br_vlan.c b/net/bridge/br_vlan.c index bb98984cd27d..48413b5eb61f 100644 --- a/net/bridge/br_vlan.c +++ b/net/bridge/br_vlan.c @@ -1229,11 +1229,13 @@ void br_vlan_get_stats(const struct net_bridge_vlan *v, } } -static int __br_vlan_get_pvid(const struct net_device *dev, - struct net_bridge_port *p, u16 *p_pvid) +int br_vlan_get_pvid(const struct net_device *dev, u16 *p_pvid) { struct net_bridge_vlan_group *vg; + struct net_bridge_port *p; + ASSERT_RTNL(); + p = br_port_get_check_rtnl(dev); if (p) vg = nbp_vlan_group(p); else if (netif_is_bridge_master(dev)) @@ -1244,18 +1246,23 @@ static int __br_vlan_get_pvid(const struct net_device *dev, *p_pvid = br_get_pvid(vg); return 0; } - -int br_vlan_get_pvid(const struct net_device *dev, u16 *p_pvid) -{ - ASSERT_RTNL(); - - return __br_vlan_get_pvid(dev, br_port_get_check_rtnl(dev), p_pvid); -} EXPORT_SYMBOL_GPL(br_vlan_get_pvid); int br_vlan_get_pvid_rcu(const struct net_device *dev, u16 *p_pvid) { - return __br_vlan_get_pvid(dev, br_port_get_check_rcu(dev), p_pvid); + struct net_bridge_vlan_group *vg; + struct net_bridge_port *p; + + p = br_port_get_check_rcu(dev); + if (p) + vg = nbp_vlan_group_rcu(p); + else if (netif_is_bridge_master(dev)) + vg = br_vlan_group_rcu(netdev_priv(dev)); + else + return -EINVAL; + + *p_pvid = br_get_pvid(vg); + return 0; } EXPORT_SYMBOL_GPL(br_vlan_get_pvid_rcu); diff --git a/net/bridge/netfilter/ebt_dnat.c b/net/bridge/netfilter/ebt_dnat.c index 12a4f4d93681..3fda71a8579d 100644 --- a/net/bridge/netfilter/ebt_dnat.c +++ b/net/bridge/netfilter/ebt_dnat.c @@ -21,7 +21,7 @@ ebt_dnat_tg(struct sk_buff *skb, const struct xt_action_param *par) { const struct ebt_nat_info *info = par->targinfo; - if (skb_ensure_writable(skb, ETH_ALEN)) + if (skb_ensure_writable(skb, 0)) return EBT_DROP; ether_addr_copy(eth_hdr(skb)->h_dest, info->mac); diff --git a/net/bridge/netfilter/ebt_redirect.c b/net/bridge/netfilter/ebt_redirect.c index 0cad62a4052b..307790562b49 100644 --- a/net/bridge/netfilter/ebt_redirect.c +++ b/net/bridge/netfilter/ebt_redirect.c @@ -21,7 +21,7 @@ ebt_redirect_tg(struct sk_buff *skb, const struct xt_action_param *par) { const struct ebt_redirect_info *info = par->targinfo; - if (skb_ensure_writable(skb, ETH_ALEN)) + if (skb_ensure_writable(skb, 0)) return EBT_DROP; if (xt_hooknum(par) != NF_BR_BROUTING) diff --git a/net/bridge/netfilter/ebt_snat.c b/net/bridge/netfilter/ebt_snat.c index 27443bf229a3..7dfbcdfc30e5 100644 --- a/net/bridge/netfilter/ebt_snat.c +++ b/net/bridge/netfilter/ebt_snat.c @@ -22,7 +22,7 @@ ebt_snat_tg(struct sk_buff *skb, const struct xt_action_param *par) { const struct ebt_nat_info *info = par->targinfo; - if (skb_ensure_writable(skb, ETH_ALEN * 2)) + if (skb_ensure_writable(skb, 0)) return EBT_DROP; ether_addr_copy(eth_hdr(skb)->h_source, info->mac); diff --git a/net/bridge/netfilter/nf_conntrack_bridge.c b/net/bridge/netfilter/nf_conntrack_bridge.c index 809673222382..8d033a75a766 100644 --- a/net/bridge/netfilter/nf_conntrack_bridge.c +++ b/net/bridge/netfilter/nf_conntrack_bridge.c @@ -168,6 +168,7 @@ static unsigned int nf_ct_br_defrag4(struct sk_buff *skb, static unsigned int nf_ct_br_defrag6(struct sk_buff *skb, const struct nf_hook_state *state) { +#if IS_ENABLED(CONFIG_NF_DEFRAG_IPV6) u16 zone_id = NF_CT_DEFAULT_ZONE_ID; enum ip_conntrack_info ctinfo; struct br_input_skb_cb cb; @@ -180,14 +181,17 @@ static unsigned int nf_ct_br_defrag6(struct sk_buff *skb, br_skb_cb_save(skb, &cb, sizeof(struct inet6_skb_parm)); - err = nf_ipv6_br_defrag(state->net, skb, - IP_DEFRAG_CONNTRACK_BRIDGE_IN + zone_id); + err = nf_ct_frag6_gather(state->net, skb, + IP_DEFRAG_CONNTRACK_BRIDGE_IN + zone_id); /* queued */ if (err == -EINPROGRESS) return NF_STOLEN; br_skb_cb_restore(skb, &cb, IP6CB(skb)->frag_max_size); return err == 0 ? NF_ACCEPT : NF_DROP; +#else + return NF_ACCEPT; +#endif } static int nf_ct_br_ip_check(const struct sk_buff *skb) diff --git a/net/can/j1939/socket.c b/net/can/j1939/socket.c index f7587428febd..bf9fd6ee88fe 100644 --- a/net/can/j1939/socket.c +++ b/net/can/j1939/socket.c @@ -398,6 +398,7 @@ static int j1939_sk_init(struct sock *sk) spin_lock_init(&jsk->sk_session_queue_lock); INIT_LIST_HEAD(&jsk->sk_session_queue); sk->sk_destruct = j1939_sk_sock_destruct; + sk->sk_protocol = CAN_J1939; return 0; } @@ -466,6 +467,14 @@ static int j1939_sk_bind(struct socket *sock, struct sockaddr *uaddr, int len) goto out_release_sock; } + if (!ndev->ml_priv) { + netdev_warn_once(ndev, + "No CAN mid layer private allocated, please fix your driver and use alloc_candev()!\n"); + dev_put(ndev); + ret = -ENODEV; + goto out_release_sock; + } + priv = j1939_netdev_start(ndev); dev_put(ndev); if (IS_ERR(priv)) { @@ -553,6 +562,11 @@ static int j1939_sk_connect(struct socket *sock, struct sockaddr *uaddr, static void j1939_sk_sock2sockaddr_can(struct sockaddr_can *addr, const struct j1939_sock *jsk, int peer) { + /* There are two holes (2 bytes and 3 bytes) to clear to avoid + * leaking kernel information to user space. + */ + memset(addr, 0, J1939_MIN_NAMELEN); + addr->can_family = AF_CAN; addr->can_ifindex = jsk->ifindex; addr->can_addr.j1939.pgn = jsk->addr.pgn; diff --git a/net/can/j1939/transport.c b/net/can/j1939/transport.c index 9f99af5b0b11..916fdf2464bc 100644 --- a/net/can/j1939/transport.c +++ b/net/can/j1939/transport.c @@ -352,17 +352,16 @@ void j1939_session_skb_queue(struct j1939_session *session, skb_queue_tail(&session->skb_queue, skb); } -static struct sk_buff *j1939_session_skb_find(struct j1939_session *session) +static struct +sk_buff *j1939_session_skb_find_by_offset(struct j1939_session *session, + unsigned int offset_start) { struct j1939_priv *priv = session->priv; + struct j1939_sk_buff_cb *do_skcb; struct sk_buff *skb = NULL; struct sk_buff *do_skb; - struct j1939_sk_buff_cb *do_skcb; - unsigned int offset_start; unsigned long flags; - offset_start = session->pkt.dpo * 7; - spin_lock_irqsave(&session->skb_queue.lock, flags); skb_queue_walk(&session->skb_queue, do_skb) { do_skcb = j1939_skb_to_cb(do_skb); @@ -382,6 +381,14 @@ static struct sk_buff *j1939_session_skb_find(struct j1939_session *session) return skb; } +static struct sk_buff *j1939_session_skb_find(struct j1939_session *session) +{ + unsigned int offset_start; + + offset_start = session->pkt.dpo * 7; + return j1939_session_skb_find_by_offset(session, offset_start); +} + /* see if we are receiver * returns 0 for broadcasts, although we will receive them */ @@ -573,6 +580,7 @@ sk_buff *j1939_tp_tx_dat_new(struct j1939_priv *priv, skb->dev = priv->ndev; can_skb_reserve(skb); can_skb_prv(skb)->ifindex = priv->ndev->ifindex; + can_skb_prv(skb)->skbcnt = 0; /* reserve CAN header */ skb_reserve(skb, offsetof(struct can_frame, data)); @@ -716,10 +724,12 @@ static int j1939_session_tx_rts(struct j1939_session *session) return ret; session->last_txcmd = dat[0]; - if (dat[0] == J1939_TP_CMD_BAM) + if (dat[0] == J1939_TP_CMD_BAM) { j1939_tp_schedule_txtimer(session, 50); - - j1939_tp_set_rxtimeout(session, 1250); + j1939_tp_set_rxtimeout(session, 250); + } else { + j1939_tp_set_rxtimeout(session, 1250); + } netdev_dbg(session->priv->ndev, "%s: 0x%p\n", __func__, session); @@ -766,7 +776,7 @@ static int j1939_session_tx_dat(struct j1939_session *session) int ret = 0; u8 dat[8]; - se_skb = j1939_session_skb_find(session); + se_skb = j1939_session_skb_find_by_offset(session, session->pkt.tx * 7); if (!se_skb) return -ENOBUFS; @@ -787,6 +797,18 @@ static int j1939_session_tx_dat(struct j1939_session *session) if (len > 7) len = 7; + if (offset + len > se_skb->len) { + netdev_err_once(priv->ndev, + "%s: 0x%p: requested data outside of queued buffer: offset %i, len %i, pkt.tx: %i\n", + __func__, session, skcb->offset, se_skb->len , session->pkt.tx); + return -EOVERFLOW; + } + + if (!len) { + ret = -ENOBUFS; + break; + } + memcpy(&dat[1], &tpdat[offset], len); ret = j1939_tp_tx_dat(session, dat, len + 1); if (ret < 0) { @@ -1055,9 +1077,9 @@ static void __j1939_session_cancel(struct j1939_session *session, lockdep_assert_held(&session->priv->active_session_list_lock); session->err = j1939_xtp_abort_to_errno(priv, err); + session->state = J1939_SESSION_WAITING_ABORT; /* do not send aborts on incoming broadcasts */ if (!j1939_cb_is_broadcast(&session->skcb)) { - session->state = J1939_SESSION_WAITING_ABORT; j1939_xtp_tx_abort(priv, &session->skcb, !session->transmission, err, session->skcb.addr.pgn); @@ -1120,6 +1142,9 @@ static enum hrtimer_restart j1939_tp_txtimer(struct hrtimer *hrtimer) * cleanup including propagation of the error to user space. */ break; + case -EOVERFLOW: + j1939_session_cancel(session, J1939_XTP_ABORT_ECTS_TOO_BIG); + break; case 0: session->tx_retry = 0; break; @@ -1463,6 +1488,7 @@ j1939_session *j1939_session_fresh_new(struct j1939_priv *priv, skb->dev = priv->ndev; can_skb_reserve(skb); can_skb_prv(skb)->ifindex = priv->ndev->ifindex; + can_skb_prv(skb)->skbcnt = 0; skcb = j1939_skb_to_cb(skb); memcpy(skcb, rel_skcb, sizeof(*skcb)); @@ -1651,8 +1677,12 @@ static void j1939_xtp_rx_rts(struct j1939_priv *priv, struct sk_buff *skb, return; } session = j1939_xtp_rx_rts_session_new(priv, skb); - if (!session) + if (!session) { + if (cmd == J1939_TP_CMD_BAM && j1939_sk_recv_match(priv, skcb)) + netdev_info(priv->ndev, "%s: failed to create TP BAM session\n", + __func__); return; + } } else { if (j1939_xtp_rx_rts_session_active(session, skb)) { j1939_session_put(session); @@ -1661,11 +1691,15 @@ static void j1939_xtp_rx_rts(struct j1939_priv *priv, struct sk_buff *skb, } session->last_cmd = cmd; - j1939_tp_set_rxtimeout(session, 1250); - - if (cmd != J1939_TP_CMD_BAM && !session->transmission) { - j1939_session_txtimer_cancel(session); - j1939_tp_schedule_txtimer(session, 0); + if (cmd == J1939_TP_CMD_BAM) { + if (!session->transmission) + j1939_tp_set_rxtimeout(session, 750); + } else { + if (!session->transmission) { + j1939_session_txtimer_cancel(session); + j1939_tp_schedule_txtimer(session, 0); + } + j1939_tp_set_rxtimeout(session, 1250); } j1939_session_put(session); @@ -1716,6 +1750,7 @@ static void j1939_xtp_rx_dat_one(struct j1939_session *session, int offset; int nbytes; bool final = false; + bool remain = false; bool do_cts_eoma = false; int packet; @@ -1750,7 +1785,8 @@ static void j1939_xtp_rx_dat_one(struct j1939_session *session, __func__, session); goto out_session_cancel; } - se_skb = j1939_session_skb_find(session); + + se_skb = j1939_session_skb_find_by_offset(session, packet * 7); if (!se_skb) { netdev_warn(priv->ndev, "%s: 0x%p: no skb found\n", __func__, session); @@ -1769,7 +1805,20 @@ static void j1939_xtp_rx_dat_one(struct j1939_session *session, } tpdat = se_skb->data; - memcpy(&tpdat[offset], &dat[1], nbytes); + if (!session->transmission) { + memcpy(&tpdat[offset], &dat[1], nbytes); + } else { + int err; + + err = memcmp(&tpdat[offset], &dat[1], nbytes); + if (err) + netdev_err_once(priv->ndev, + "%s: 0x%p: Data of RX-looped back packet (%*ph) doesn't match TX data (%*ph)!\n", + __func__, session, + nbytes, &dat[1], + nbytes, &tpdat[offset]); + } + if (packet == session->pkt.rx) session->pkt.rx++; @@ -1777,6 +1826,8 @@ static void j1939_xtp_rx_dat_one(struct j1939_session *session, j1939_cb_is_broadcast(&session->skcb)) { if (session->pkt.rx >= session->pkt.total) final = true; + else + remain = true; } else { /* never final, an EOMA must follow */ if (session->pkt.rx >= session->pkt.last) @@ -1784,7 +1835,11 @@ static void j1939_xtp_rx_dat_one(struct j1939_session *session, } if (final) { + j1939_session_timers_cancel(session); j1939_session_completed(session); + } else if (remain) { + if (!session->transmission) + j1939_tp_set_rxtimeout(session, 750); } else if (do_cts_eoma) { j1939_tp_set_rxtimeout(session, 1250); if (!session->transmission) @@ -1829,6 +1884,13 @@ static void j1939_xtp_rx_dat(struct j1939_priv *priv, struct sk_buff *skb) else j1939_xtp_rx_dat_one(session, skb); } + + if (j1939_cb_is_broadcast(skcb)) { + session = j1939_session_get_by_addr(priv, &skcb->addr, false, + false); + if (session) + j1939_xtp_rx_dat_one(session, skb); + } } /* j1939 main intf */ @@ -1920,7 +1982,7 @@ static void j1939_tp_cmd_recv(struct j1939_priv *priv, struct sk_buff *skb) if (j1939_tp_im_transmitter(skcb)) j1939_xtp_rx_rts(priv, skb, true); - if (j1939_tp_im_receiver(skcb)) + if (j1939_tp_im_receiver(skcb) || j1939_cb_is_broadcast(skcb)) j1939_xtp_rx_rts(priv, skb, false); break; @@ -1984,7 +2046,7 @@ int j1939_tp_recv(struct j1939_priv *priv, struct sk_buff *skb) { struct j1939_sk_buff_cb *skcb = j1939_skb_to_cb(skb); - if (!j1939_tp_im_involved_anydir(skcb)) + if (!j1939_tp_im_involved_anydir(skcb) && !j1939_cb_is_broadcast(skcb)) return 0; switch (skcb->addr.pgn) { @@ -2017,6 +2079,10 @@ void j1939_simple_recv(struct j1939_priv *priv, struct sk_buff *skb) if (!skb->sk) return; + if (skb->sk->sk_family != AF_CAN || + skb->sk->sk_protocol != CAN_J1939) + return; + j1939_session_list_lock(priv); session = j1939_session_get_simple(priv, skb); j1939_session_list_unlock(priv); diff --git a/net/ceph/osd_client.c b/net/ceph/osd_client.c index e513b8876d13..a8481da37f1a 100644 --- a/net/ceph/osd_client.c +++ b/net/ceph/osd_client.c @@ -445,6 +445,7 @@ static void target_copy(struct ceph_osd_request_target *dest, dest->size = src->size; dest->min_size = src->min_size; dest->sort_bitwise = src->sort_bitwise; + dest->recovery_deletes = src->recovery_deletes; dest->flags = src->flags; dest->paused = src->paused; diff --git a/net/compat.c b/net/compat.c index 0f7ded26059e..c848bcb517f3 100644 --- a/net/compat.c +++ b/net/compat.c @@ -291,6 +291,7 @@ void scm_detach_fds_compat(struct msghdr *kmsg, struct scm_cookie *scm) break; } /* Bump the usage count and install the file. */ + __receive_sock(fp[i]); fd_install(new_fd, get_file(fp[i])); } diff --git a/net/core/dev.c b/net/core/dev.c index 8552874e5aac..20c7fd7b8b4b 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -79,6 +79,7 @@ #include <linux/sched.h> #include <linux/sched/mm.h> #include <linux/mutex.h> +#include <linux/rwsem.h> #include <linux/string.h> #include <linux/mm.h> #include <linux/socket.h> @@ -194,7 +195,7 @@ static DEFINE_SPINLOCK(napi_hash_lock); static unsigned int napi_gen_id = NR_CPUS; static DEFINE_READ_MOSTLY_HASHTABLE(napi_hash, 8); -static seqcount_t devnet_rename_seq; +static DECLARE_RWSEM(devnet_rename_sem); static inline void dev_base_seq_inc(struct net *net) { @@ -816,33 +817,28 @@ EXPORT_SYMBOL(dev_get_by_napi_id); * @net: network namespace * @name: a pointer to the buffer where the name will be stored. * @ifindex: the ifindex of the interface to get the name from. - * - * The use of raw_seqcount_begin() and cond_resched() before - * retrying is required as we want to give the writers a chance - * to complete when CONFIG_PREEMPT is not set. */ int netdev_get_name(struct net *net, char *name, int ifindex) { struct net_device *dev; - unsigned int seq; + int ret; -retry: - seq = raw_seqcount_begin(&devnet_rename_seq); + down_read(&devnet_rename_sem); rcu_read_lock(); + dev = dev_get_by_index_rcu(net, ifindex); if (!dev) { - rcu_read_unlock(); - return -ENODEV; + ret = -ENODEV; + goto out; } strcpy(name, dev->name); - rcu_read_unlock(); - if (read_seqcount_retry(&devnet_rename_seq, seq)) { - cond_resched(); - goto retry; - } - return 0; + ret = 0; +out: + rcu_read_unlock(); + up_read(&devnet_rename_sem); + return ret; } /** @@ -1115,10 +1111,10 @@ int dev_change_name(struct net_device *dev, const char *newname) likely(!(dev->priv_flags & IFF_LIVE_RENAME_OK))) return -EBUSY; - write_seqcount_begin(&devnet_rename_seq); + down_write(&devnet_rename_sem); if (strncmp(newname, dev->name, IFNAMSIZ) == 0) { - write_seqcount_end(&devnet_rename_seq); + up_write(&devnet_rename_sem); return 0; } @@ -1126,7 +1122,7 @@ int dev_change_name(struct net_device *dev, const char *newname) err = dev_get_valid_name(net, dev, newname); if (err < 0) { - write_seqcount_end(&devnet_rename_seq); + up_write(&devnet_rename_sem); return err; } @@ -1141,11 +1137,11 @@ rollback: if (ret) { memcpy(dev->name, oldname, IFNAMSIZ); dev->name_assign_type = old_assign_type; - write_seqcount_end(&devnet_rename_seq); + up_write(&devnet_rename_sem); return ret; } - write_seqcount_end(&devnet_rename_seq); + up_write(&devnet_rename_sem); netdev_adjacent_rename_links(dev, oldname); @@ -1166,7 +1162,7 @@ rollback: /* err >= 0 after dev_alloc_name() or stores the first errno */ if (err >= 0) { err = ret; - write_seqcount_begin(&devnet_rename_seq); + down_write(&devnet_rename_sem); memcpy(dev->name, oldname, IFNAMSIZ); memcpy(oldname, newname, IFNAMSIZ); dev->name_assign_type = old_assign_type; @@ -3836,10 +3832,12 @@ int dev_direct_xmit(struct sk_buff *skb, u16 queue_id) local_bh_disable(); + dev_xmit_recursion_inc(); HARD_TX_LOCK(dev, txq, smp_processor_id()); if (!netif_xmit_frozen_or_drv_stopped(txq)) ret = netdev_start_xmit(skb, dev, txq, false); HARD_TX_UNLOCK(dev, txq); + dev_xmit_recursion_dec(); local_bh_enable(); @@ -5231,7 +5229,7 @@ static void flush_backlog(struct work_struct *work) skb_queue_walk_safe(&sd->input_pkt_queue, skb, tmp) { if (skb->dev->reg_state == NETREG_UNREGISTERING) { __skb_unlink(skb, &sd->input_pkt_queue); - kfree_skb(skb); + dev_kfree_skb_irq(skb); input_queue_head_incr(sd); } } @@ -5604,12 +5602,13 @@ static void napi_skb_free_stolen_head(struct sk_buff *skb) kmem_cache_free(skbuff_head_cache, skb); } -static gro_result_t napi_skb_finish(gro_result_t ret, struct sk_buff *skb) +static gro_result_t napi_skb_finish(struct napi_struct *napi, + struct sk_buff *skb, + gro_result_t ret) { switch (ret) { case GRO_NORMAL: - if (netif_receive_skb_internal(skb)) - ret = GRO_DROP; + gro_normal_one(napi, skb); break; case GRO_DROP: @@ -5641,7 +5640,7 @@ gro_result_t napi_gro_receive(struct napi_struct *napi, struct sk_buff *skb) skb_gro_reset_offset(skb); - ret = napi_skb_finish(dev_gro_receive(napi, skb), skb); + ret = napi_skb_finish(napi, skb, dev_gro_receive(napi, skb)); trace_napi_gro_receive_exit(ret); return ret; @@ -6232,12 +6231,13 @@ void netif_napi_add(struct net_device *dev, struct napi_struct *napi, netdev_err_once(dev, "%s() called with weight %d\n", __func__, weight); napi->weight = weight; - list_add(&napi->dev_list, &dev->napi_list); napi->dev = dev; #ifdef CONFIG_NETPOLL napi->poll_owner = -1; #endif set_bit(NAPI_STATE_SCHED, &napi->state); + set_bit(NAPI_STATE_NPSVC, &napi->state); + list_add_rcu(&napi->dev_list, &dev->napi_list); napi_hash_add(napi); } EXPORT_SYMBOL(netif_napi_add); @@ -8241,7 +8241,7 @@ int dev_get_port_parent_id(struct net_device *dev, if (!first.id_len) first = *ppid; else if (memcmp(&first, ppid, sizeof(*ppid))) - return -ENODATA; + return -EOPNOTSUPP; } return err; @@ -9118,6 +9118,13 @@ int register_netdevice(struct net_device *dev) rcu_barrier(); dev->reg_state = NETREG_UNREGISTERED; + /* We should put the kobject that hold in + * netdev_unregister_kobject(), otherwise + * the net device cannot be freed when + * driver calls free_netdev(), because the + * kobject is being hold. + */ + kobject_put(&dev->dev.kobj); } /* * Prevent userspace races by waiting until the network diff --git a/net/core/devlink.c b/net/core/devlink.c index 5667cae57072..26c8993a17ae 100644 --- a/net/core/devlink.c +++ b/net/core/devlink.c @@ -4823,6 +4823,7 @@ int devlink_health_report(struct devlink_health_reporter *reporter, { enum devlink_health_reporter_state prev_health_state; struct devlink *devlink = reporter->devlink; + unsigned long recover_ts_threshold; /* write a log message of the current error */ WARN_ON(!msg); @@ -4832,10 +4833,12 @@ int devlink_health_report(struct devlink_health_reporter *reporter, reporter->health_state = DEVLINK_HEALTH_REPORTER_STATE_ERROR; /* abort if the previous error wasn't recovered */ + recover_ts_threshold = reporter->last_recovery_ts + + msecs_to_jiffies(reporter->graceful_period); if (reporter->auto_recover && (prev_health_state != DEVLINK_HEALTH_REPORTER_STATE_HEALTHY || - jiffies - reporter->last_recovery_ts < - msecs_to_jiffies(reporter->graceful_period))) { + (reporter->last_recovery_ts && reporter->recovery_count && + time_is_after_jiffies(recover_ts_threshold)))) { trace_devlink_health_recover_aborted(devlink, reporter->ops->name, reporter->health_state, diff --git a/net/core/filter.c b/net/core/filter.c index f1f2304822e3..b040b7bf2858 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -1766,25 +1766,27 @@ BPF_CALL_5(bpf_skb_load_bytes_relative, const struct sk_buff *, skb, u32, offset, void *, to, u32, len, u32, start_header) { u8 *end = skb_tail_pointer(skb); - u8 *net = skb_network_header(skb); - u8 *mac = skb_mac_header(skb); - u8 *ptr; + u8 *start, *ptr; - if (unlikely(offset > 0xffff || len > (end - mac))) + if (unlikely(offset > 0xffff)) goto err_clear; switch (start_header) { case BPF_HDR_START_MAC: - ptr = mac + offset; + if (unlikely(!skb_mac_header_was_set(skb))) + goto err_clear; + start = skb_mac_header(skb); break; case BPF_HDR_START_NET: - ptr = net + offset; + start = skb_network_header(skb); break; default: goto err_clear; } - if (likely(ptr >= mac && ptr + len <= end)) { + ptr = start + offset; + + if (likely(ptr + len <= end)) { memcpy(to, ptr, len); return 0; } @@ -4268,7 +4270,8 @@ BPF_CALL_5(bpf_setsockopt, struct bpf_sock_ops_kern *, bpf_sock, cmpxchg(&sk->sk_pacing_status, SK_PACING_NONE, SK_PACING_NEEDED); - sk->sk_max_pacing_rate = (val == ~0U) ? ~0UL : val; + sk->sk_max_pacing_rate = (val == ~0U) ? + ~0UL : (unsigned int)val; sk->sk_pacing_rate = min(sk->sk_pacing_rate, sk->sk_max_pacing_rate); break; @@ -4648,6 +4651,7 @@ static int bpf_ipv4_fib_lookup(struct net *net, struct bpf_fib_lookup *params, fl4.saddr = params->ipv4_src; fl4.fl4_sport = params->sport; fl4.fl4_dport = params->dport; + fl4.flowi4_multipath_hash = 0; if (flags & BPF_FIB_LOOKUP_DIRECT) { u32 tbid = l3mdev_fib_table_rcu(dev) ? : RT_TABLE_MAIN; @@ -5728,12 +5732,16 @@ BPF_CALL_1(bpf_skb_ecn_set_ce, struct sk_buff *, skb) { unsigned int iphdr_len; - if (skb->protocol == cpu_to_be16(ETH_P_IP)) + switch (skb_protocol(skb, true)) { + case cpu_to_be16(ETH_P_IP): iphdr_len = sizeof(struct iphdr); - else if (skb->protocol == cpu_to_be16(ETH_P_IPV6)) + break; + case cpu_to_be16(ETH_P_IPV6): iphdr_len = sizeof(struct ipv6hdr); - else + break; + default: return 0; + } if (skb_headlen(skb) < iphdr_len) return 0; @@ -6784,8 +6792,6 @@ static int bpf_gen_ld_abs(const struct bpf_insn *orig, bool indirect = BPF_MODE(orig->code) == BPF_IND; struct bpf_insn *insn = insn_buf; - /* We're guaranteed here that CTX is in R6. */ - *insn++ = BPF_MOV64_REG(BPF_REG_1, BPF_REG_CTX); if (!indirect) { *insn++ = BPF_MOV64_IMM(BPF_REG_2, orig->imm); } else { @@ -6793,6 +6799,8 @@ static int bpf_gen_ld_abs(const struct bpf_insn *orig, if (orig->imm) *insn++ = BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, orig->imm); } + /* We're guaranteed here that CTX is in R6. */ + *insn++ = BPF_MOV64_REG(BPF_REG_1, BPF_REG_CTX); switch (BPF_SIZE(orig->code)) { case BPF_B: @@ -8004,6 +8012,43 @@ static u32 sock_ops_convert_ctx_access(enum bpf_access_type type, offsetof(OBJ, OBJ_FIELD)); \ } while (0) +#define SOCK_OPS_GET_SK() \ + do { \ + int fullsock_reg = si->dst_reg, reg = BPF_REG_9, jmp = 1; \ + if (si->dst_reg == reg || si->src_reg == reg) \ + reg--; \ + if (si->dst_reg == reg || si->src_reg == reg) \ + reg--; \ + if (si->dst_reg == si->src_reg) { \ + *insn++ = BPF_STX_MEM(BPF_DW, si->src_reg, reg, \ + offsetof(struct bpf_sock_ops_kern, \ + temp)); \ + fullsock_reg = reg; \ + jmp += 2; \ + } \ + *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( \ + struct bpf_sock_ops_kern, \ + is_fullsock), \ + fullsock_reg, si->src_reg, \ + offsetof(struct bpf_sock_ops_kern, \ + is_fullsock)); \ + *insn++ = BPF_JMP_IMM(BPF_JEQ, fullsock_reg, 0, jmp); \ + if (si->dst_reg == si->src_reg) \ + *insn++ = BPF_LDX_MEM(BPF_DW, reg, si->src_reg, \ + offsetof(struct bpf_sock_ops_kern, \ + temp)); \ + *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( \ + struct bpf_sock_ops_kern, sk),\ + si->dst_reg, si->src_reg, \ + offsetof(struct bpf_sock_ops_kern, sk));\ + if (si->dst_reg == si->src_reg) { \ + *insn++ = BPF_JMP_A(1); \ + *insn++ = BPF_LDX_MEM(BPF_DW, reg, si->src_reg, \ + offsetof(struct bpf_sock_ops_kern, \ + temp)); \ + } \ + } while (0) + #define SOCK_OPS_GET_TCP_SOCK_FIELD(FIELD) \ SOCK_OPS_GET_FIELD(FIELD, FIELD, struct tcp_sock) @@ -8288,17 +8333,7 @@ static u32 sock_ops_convert_ctx_access(enum bpf_access_type type, SOCK_OPS_GET_TCP_SOCK_FIELD(bytes_acked); break; case offsetof(struct bpf_sock_ops, sk): - *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( - struct bpf_sock_ops_kern, - is_fullsock), - si->dst_reg, si->src_reg, - offsetof(struct bpf_sock_ops_kern, - is_fullsock)); - *insn++ = BPF_JMP_IMM(BPF_JEQ, si->dst_reg, 0, 1); - *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( - struct bpf_sock_ops_kern, sk), - si->dst_reg, si->src_reg, - offsetof(struct bpf_sock_ops_kern, sk)); + SOCK_OPS_GET_SK(); break; } return insn - insn_buf; diff --git a/net/core/neighbour.c b/net/core/neighbour.c index 7b40d12f0c22..04953e5f2530 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -3290,6 +3290,7 @@ static void *neigh_stat_seq_next(struct seq_file *seq, void *v, loff_t *pos) *pos = cpu+1; return per_cpu_ptr(tbl->stats, cpu); } + (*pos)++; return NULL; } diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c index 4c826b8bf9b1..2ebf9b252779 100644 --- a/net/core/net-sysfs.c +++ b/net/core/net-sysfs.c @@ -1036,7 +1036,7 @@ static ssize_t tx_timeout_show(struct netdev_queue *queue, char *buf) trans_timeout = queue->trans_timeout; spin_unlock_irq(&queue->_xmit_lock); - return sprintf(buf, "%lu", trans_timeout); + return sprintf(buf, fmt_ulong, trans_timeout); } static unsigned int get_netdev_queue_index(struct netdev_queue *queue) diff --git a/net/core/netpoll.c b/net/core/netpoll.c index 849380a622ef..cb67d36f3adb 100644 --- a/net/core/netpoll.c +++ b/net/core/netpoll.c @@ -161,7 +161,7 @@ static void poll_napi(struct net_device *dev) struct napi_struct *napi; int cpu = smp_processor_id(); - list_for_each_entry(napi, &dev->napi_list, dev_list) { + list_for_each_entry_rcu(napi, &dev->napi_list, dev_list) { if (cmpxchg(&napi->poll_owner, -1, cpu) == -1) { poll_one_napi(napi); smp_store_release(&napi->poll_owner, -1); diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 944acb1a9f29..b0c06a063776 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -3231,7 +3231,8 @@ replay: */ if (err < 0) { /* If device is not registered at all, free it now */ - if (dev->reg_state == NETREG_UNINITIALIZED) + if (dev->reg_state == NETREG_UNINITIALIZED || + dev->reg_state == NETREG_UNREGISTERED) free_netdev(dev); goto out; } diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 3823128f3256..0d8802e63abf 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -5343,8 +5343,8 @@ struct sk_buff *skb_vlan_untag(struct sk_buff *skb) skb = skb_share_check(skb, GFP_ATOMIC); if (unlikely(!skb)) goto err_free; - - if (unlikely(!pskb_may_pull(skb, VLAN_HLEN))) + /* We may access the two bytes after vlan_hdr in vlan_set_encap_proto(). */ + if (unlikely(!pskb_may_pull(skb, VLAN_HLEN + sizeof(unsigned short)))) goto err_free; vhdr = (struct vlan_hdr *)skb->data; @@ -5541,7 +5541,7 @@ int skb_mpls_push(struct sk_buff *skb, __be32 mpls_lse, __be16 mpls_proto, lse->label_stack_entry = mpls_lse; skb_postpush_rcsum(skb, lse, MPLS_HLEN); - if (ethernet) + if (ethernet && mac_len >= ETH_HLEN) skb_mod_eth_type(skb, eth_hdr(skb), mpls_proto); skb->protocol = mpls_proto; @@ -5581,7 +5581,7 @@ int skb_mpls_pop(struct sk_buff *skb, __be16 next_proto, int mac_len, skb_reset_mac_header(skb); skb_set_network_header(skb, mac_len); - if (ethernet) { + if (ethernet && mac_len >= ETH_HLEN) { struct ethhdr *hdr; /* use mpls_hdr() to get ethertype to account for VLANs. */ @@ -5908,9 +5908,13 @@ static int pskb_carve_inside_nonlinear(struct sk_buff *skb, const u32 off, if (skb_has_frag_list(skb)) skb_clone_fraglist(skb); - if (k == 0) { - /* split line is in frag list */ - pskb_carve_frag_list(skb, shinfo, off - pos, gfp_mask); + /* split line is in frag list */ + if (k == 0 && pskb_carve_frag_list(skb, shinfo, off - pos, gfp_mask)) { + /* skb_frag_unref() is not needed here as shinfo->nr_frags = 0. */ + if (skb_has_frag_list(skb)) + kfree_skb_list(skb_shinfo(skb)->frag_list); + kfree(data); + return -ENOMEM; } skb_release_data(skb); diff --git a/net/core/skmsg.c b/net/core/skmsg.c index ded2d5227678..118cf1ace43a 100644 --- a/net/core/skmsg.c +++ b/net/core/skmsg.c @@ -7,6 +7,7 @@ #include <net/sock.h> #include <net/tcp.h> +#include <net/tls.h> static bool sk_msg_try_coalesce_ok(struct sk_msg *msg, int elem_first_coalesce) { @@ -686,13 +687,74 @@ static struct sk_psock *sk_psock_from_strp(struct strparser *strp) return container_of(parser, struct sk_psock, parser); } -static void sk_psock_verdict_apply(struct sk_psock *psock, - struct sk_buff *skb, int verdict) +static void sk_psock_skb_redirect(struct sk_buff *skb) { struct sk_psock *psock_other; struct sock *sk_other; bool ingress; + sk_other = tcp_skb_bpf_redirect_fetch(skb); + if (unlikely(!sk_other)) { + kfree_skb(skb); + return; + } + psock_other = sk_psock(sk_other); + if (!psock_other || sock_flag(sk_other, SOCK_DEAD) || + !sk_psock_test_state(psock_other, SK_PSOCK_TX_ENABLED)) { + kfree_skb(skb); + return; + } + + ingress = tcp_skb_bpf_ingress(skb); + if ((!ingress && sock_writeable(sk_other)) || + (ingress && + atomic_read(&sk_other->sk_rmem_alloc) <= + sk_other->sk_rcvbuf)) { + if (!ingress) + skb_set_owner_w(skb, sk_other); + skb_queue_tail(&psock_other->ingress_skb, skb); + schedule_work(&psock_other->work); + } else { + kfree_skb(skb); + } +} + +static void sk_psock_tls_verdict_apply(struct sk_buff *skb, int verdict) +{ + switch (verdict) { + case __SK_REDIRECT: + sk_psock_skb_redirect(skb); + break; + case __SK_PASS: + case __SK_DROP: + default: + break; + } +} + +int sk_psock_tls_strp_read(struct sk_psock *psock, struct sk_buff *skb) +{ + struct bpf_prog *prog; + int ret = __SK_PASS; + + rcu_read_lock(); + prog = READ_ONCE(psock->progs.skb_verdict); + if (likely(prog)) { + tcp_skb_bpf_redirect_clear(skb); + ret = sk_psock_bpf_run(psock, prog, skb); + ret = sk_psock_map_verd(ret, tcp_skb_bpf_redirect_fetch(skb)); + } + sk_psock_tls_verdict_apply(skb, ret); + rcu_read_unlock(); + return ret; +} +EXPORT_SYMBOL_GPL(sk_psock_tls_strp_read); + +static void sk_psock_verdict_apply(struct sk_psock *psock, + struct sk_buff *skb, int verdict) +{ + struct sock *sk_other; + switch (verdict) { case __SK_PASS: sk_other = psock->sk; @@ -711,25 +773,8 @@ static void sk_psock_verdict_apply(struct sk_psock *psock, } goto out_free; case __SK_REDIRECT: - sk_other = tcp_skb_bpf_redirect_fetch(skb); - if (unlikely(!sk_other)) - goto out_free; - psock_other = sk_psock(sk_other); - if (!psock_other || sock_flag(sk_other, SOCK_DEAD) || - !sk_psock_test_state(psock_other, SK_PSOCK_TX_ENABLED)) - goto out_free; - ingress = tcp_skb_bpf_ingress(skb); - if ((!ingress && sock_writeable(sk_other)) || - (ingress && - atomic_read(&sk_other->sk_rmem_alloc) <= - sk_other->sk_rcvbuf)) { - if (!ingress) - skb_set_owner_w(skb, sk_other); - skb_queue_tail(&psock_other->ingress_skb, skb); - schedule_work(&psock_other->work); - break; - } - /* fall-through */ + sk_psock_skb_redirect(skb); + break; case __SK_DROP: /* fall-through */ default: @@ -740,11 +785,18 @@ out_free: static void sk_psock_strp_read(struct strparser *strp, struct sk_buff *skb) { - struct sk_psock *psock = sk_psock_from_strp(strp); + struct sk_psock *psock; struct bpf_prog *prog; int ret = __SK_DROP; + struct sock *sk; rcu_read_lock(); + sk = strp->sk; + psock = sk_psock(sk); + if (unlikely(!psock)) { + kfree_skb(skb); + goto out; + } prog = READ_ONCE(psock->progs.skb_verdict); if (likely(prog)) { skb_orphan(skb); @@ -752,8 +804,9 @@ static void sk_psock_strp_read(struct strparser *strp, struct sk_buff *skb) ret = sk_psock_bpf_run(psock, prog, skb); ret = sk_psock_map_verd(ret, tcp_skb_bpf_redirect_fetch(skb)); } - rcu_read_unlock(); sk_psock_verdict_apply(psock, skb, ret); +out: + rcu_read_unlock(); } static int sk_psock_strp_read_done(struct strparser *strp, int err) @@ -783,9 +836,13 @@ static void sk_psock_strp_data_ready(struct sock *sk) rcu_read_lock(); psock = sk_psock(sk); if (likely(psock)) { - write_lock_bh(&sk->sk_callback_lock); - strp_data_ready(&psock->parser.strp); - write_unlock_bh(&sk->sk_callback_lock); + if (tls_sw_has_ctx_rx(sk)) { + psock->parser.saved_data_ready(sk); + } else { + write_lock_bh(&sk->sk_callback_lock); + strp_data_ready(&psock->parser.strp); + write_unlock_bh(&sk->sk_callback_lock); + } } rcu_read_unlock(); } diff --git a/net/core/sock.c b/net/core/sock.c index 0adf7a9e5a90..33543d59a10d 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -709,7 +709,7 @@ bool sk_mc_loop(struct sock *sk) return inet6_sk(sk)->mc_loop; #endif } - WARN_ON(1); + WARN_ON_ONCE(1); return true; } EXPORT_SYMBOL(sk_mc_loop); @@ -923,13 +923,10 @@ set_rcvbuf: } else { sock_reset_flag(sk, SOCK_RCVTSTAMP); sock_reset_flag(sk, SOCK_RCVTSTAMPNS); - sock_reset_flag(sk, SOCK_TSTAMP_NEW); } break; case SO_TIMESTAMPING_NEW: - sock_set_flag(sk, SOCK_TSTAMP_NEW); - /* fall through */ case SO_TIMESTAMPING_OLD: if (val & ~SOF_TIMESTAMPING_MASK) { ret = -EINVAL; @@ -958,16 +955,14 @@ set_rcvbuf: } sk->sk_tsflags = val; + sock_valbool_flag(sk, SOCK_TSTAMP_NEW, optname == SO_TIMESTAMPING_NEW); + if (val & SOF_TIMESTAMPING_RX_SOFTWARE) sock_enable_timestamp(sk, SOCK_TIMESTAMPING_RX_SOFTWARE); - else { - if (optname == SO_TIMESTAMPING_NEW) - sock_reset_flag(sk, SOCK_TSTAMP_NEW); - + else sock_disable_timestamp(sk, (1UL << SOCK_TIMESTAMPING_RX_SOFTWARE)); - } break; case SO_RCVLOWAT: @@ -1110,7 +1105,7 @@ set_rcvbuf: case SO_MAX_PACING_RATE: { - unsigned long ulval = (val == ~0U) ? ~0UL : val; + unsigned long ulval = (val == ~0U) ? ~0UL : (unsigned int)val; if (sizeof(ulval) != sizeof(val) && optlen >= sizeof(ulval) && @@ -1679,6 +1674,7 @@ struct sock *sk_alloc(struct net *net, int family, gfp_t priority, cgroup_sk_alloc(&sk->sk_cgrp_data); sock_update_classid(&sk->sk_cgrp_data); sock_update_netprioidx(&sk->sk_cgrp_data); + sk_tx_queue_clear(sk); } return sk; @@ -1836,7 +1832,7 @@ struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority) /* sk->sk_memcg will be populated at accept() time */ newsk->sk_memcg = NULL; - cgroup_sk_alloc(&newsk->sk_cgrp_data); + cgroup_sk_clone(&newsk->sk_cgrp_data); rcu_read_lock(); filter = rcu_dereference(sk->sk_filter); @@ -1895,6 +1891,7 @@ struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority) */ sk_refcnt_debug_inc(newsk); sk_set_socket(newsk, NULL); + sk_tx_queue_clear(newsk); RCU_INIT_POINTER(newsk->sk_wq, NULL); if (newsk->sk_prot->sockets_allocated) @@ -2734,6 +2731,27 @@ int sock_no_mmap(struct file *file, struct socket *sock, struct vm_area_struct * } EXPORT_SYMBOL(sock_no_mmap); +/* + * When a file is received (via SCM_RIGHTS, etc), we must bump the + * various sock-based usage counts. + */ +void __receive_sock(struct file *file) +{ + struct socket *sock; + int error; + + /* + * The resulting value of "error" is ignored here since we only + * need to take action when the file is a socket and testing + * "sock" for NULL is sufficient. + */ + sock = sock_from_file(file, &error); + if (sock) { + sock_update_netprioidx(&sock->sk->sk_cgrp_data); + sock_update_classid(&sock->sk->sk_cgrp_data); + } +} + ssize_t sock_no_sendpage(struct socket *sock, struct page *page, int offset, size_t size, int flags) { ssize_t res; @@ -3335,6 +3353,16 @@ static void sock_inuse_add(struct net *net, int val) } #endif +static void tw_prot_cleanup(struct timewait_sock_ops *twsk_prot) +{ + if (!twsk_prot) + return; + kfree(twsk_prot->twsk_slab_name); + twsk_prot->twsk_slab_name = NULL; + kmem_cache_destroy(twsk_prot->twsk_slab); + twsk_prot->twsk_slab = NULL; +} + static void req_prot_cleanup(struct request_sock_ops *rsk_prot) { if (!rsk_prot) @@ -3405,7 +3433,7 @@ int proto_register(struct proto *prot, int alloc_slab) prot->slab_flags, NULL); if (prot->twsk_prot->twsk_slab == NULL) - goto out_free_timewait_sock_slab_name; + goto out_free_timewait_sock_slab; } } @@ -3413,15 +3441,15 @@ int proto_register(struct proto *prot, int alloc_slab) ret = assign_proto_idx(prot); if (ret) { mutex_unlock(&proto_list_mutex); - goto out_free_timewait_sock_slab_name; + goto out_free_timewait_sock_slab; } list_add(&prot->node, &proto_list); mutex_unlock(&proto_list_mutex); return ret; -out_free_timewait_sock_slab_name: +out_free_timewait_sock_slab: if (alloc_slab && prot->twsk_prot) - kfree(prot->twsk_prot->twsk_slab_name); + tw_prot_cleanup(prot->twsk_prot); out_free_request_sock_slab: if (alloc_slab) { req_prot_cleanup(prot->rsk_prot); @@ -3445,12 +3473,7 @@ void proto_unregister(struct proto *prot) prot->slab = NULL; req_prot_cleanup(prot->rsk_prot); - - if (prot->twsk_prot != NULL && prot->twsk_prot->twsk_slab != NULL) { - kmem_cache_destroy(prot->twsk_prot->twsk_slab); - kfree(prot->twsk_prot->twsk_slab_name); - prot->twsk_prot->twsk_slab = NULL; - } + tw_prot_cleanup(prot->twsk_prot); } EXPORT_SYMBOL(proto_unregister); diff --git a/net/core/sock_map.c b/net/core/sock_map.c index 8291568b707f..df52061f99f7 100644 --- a/net/core/sock_map.c +++ b/net/core/sock_map.c @@ -71,7 +71,42 @@ int sock_map_get_from_fd(const union bpf_attr *attr, struct bpf_prog *prog) map = __bpf_map_get(f); if (IS_ERR(map)) return PTR_ERR(map); - ret = sock_map_prog_update(map, prog, attr->attach_type); + ret = sock_map_prog_update(map, prog, NULL, attr->attach_type); + fdput(f); + return ret; +} + +int sock_map_prog_detach(const union bpf_attr *attr, enum bpf_prog_type ptype) +{ + u32 ufd = attr->target_fd; + struct bpf_prog *prog; + struct bpf_map *map; + struct fd f; + int ret; + + if (attr->attach_flags) + return -EINVAL; + + f = fdget(ufd); + map = __bpf_map_get(f); + if (IS_ERR(map)) + return PTR_ERR(map); + + prog = bpf_prog_get(attr->attach_bpf_fd); + if (IS_ERR(prog)) { + ret = PTR_ERR(prog); + goto put_map; + } + + if (prog->type != ptype) { + ret = -EINVAL; + goto put_prog; + } + + ret = sock_map_prog_update(map, NULL, prog, attr->attach_type); +put_prog: + bpf_prog_put(prog); +put_map: fdput(f); return ret; } @@ -837,11 +872,15 @@ static struct bpf_map *sock_hash_alloc(union bpf_attr *attr) err = -EINVAL; goto free_htab; } + err = bpf_map_charge_init(&htab->map.memory, cost); + if (err) + goto free_htab; htab->buckets = bpf_map_area_alloc(htab->buckets_num * sizeof(struct bpf_htab_bucket), htab->map.numa_node); if (!htab->buckets) { + bpf_map_charge_finish(&htab->map.memory); err = -ENOMEM; goto free_htab; } @@ -861,6 +900,7 @@ static void sock_hash_free(struct bpf_map *map) { struct bpf_htab *htab = container_of(map, struct bpf_htab, map); struct bpf_htab_bucket *bucket; + struct hlist_head unlink_list; struct bpf_htab_elem *elem; struct hlist_node *node; int i; @@ -872,13 +912,32 @@ static void sock_hash_free(struct bpf_map *map) synchronize_rcu(); for (i = 0; i < htab->buckets_num; i++) { bucket = sock_hash_select_bucket(htab, i); - hlist_for_each_entry_safe(elem, node, &bucket->head, node) { - hlist_del_rcu(&elem->node); + + /* We are racing with sock_hash_delete_from_link to + * enter the spin-lock critical section. Every socket on + * the list is still linked to sockhash. Since link + * exists, psock exists and holds a ref to socket. That + * lets us to grab a socket ref too. + */ + raw_spin_lock_bh(&bucket->lock); + hlist_for_each_entry(elem, &bucket->head, node) + sock_hold(elem->sk); + hlist_move_list(&bucket->head, &unlink_list); + raw_spin_unlock_bh(&bucket->lock); + + /* Process removed entries out of atomic context to + * block for socket lock before deleting the psock's + * link to sockhash. + */ + hlist_for_each_entry_safe(elem, node, &unlink_list, node) { + hlist_del(&elem->node); lock_sock(elem->sk); rcu_read_lock(); sock_map_unref(elem->sk, elem); rcu_read_unlock(); release_sock(elem->sk); + sock_put(elem->sk); + sock_hash_free_elem(htab, elem); } } @@ -991,27 +1050,32 @@ static struct sk_psock_progs *sock_map_progs(struct bpf_map *map) } int sock_map_prog_update(struct bpf_map *map, struct bpf_prog *prog, - u32 which) + struct bpf_prog *old, u32 which) { struct sk_psock_progs *progs = sock_map_progs(map); + struct bpf_prog **pprog; if (!progs) return -EOPNOTSUPP; switch (which) { case BPF_SK_MSG_VERDICT: - psock_set_prog(&progs->msg_parser, prog); + pprog = &progs->msg_parser; break; case BPF_SK_SKB_STREAM_PARSER: - psock_set_prog(&progs->skb_parser, prog); + pprog = &progs->skb_parser; break; case BPF_SK_SKB_STREAM_VERDICT: - psock_set_prog(&progs->skb_verdict, prog); + pprog = &progs->skb_verdict; break; default: return -EOPNOTSUPP; } + if (old) + return psock_replace_prog(pprog, prog, old); + + psock_set_prog(pprog, prog); return 0; } diff --git a/net/core/sock_reuseport.c b/net/core/sock_reuseport.c index f3ceec93f392..40829111fe00 100644 --- a/net/core/sock_reuseport.c +++ b/net/core/sock_reuseport.c @@ -112,6 +112,7 @@ static struct sock_reuseport *reuseport_grow(struct sock_reuseport *reuse) more_reuse->prog = reuse->prog; more_reuse->reuseport_id = reuse->reuseport_id; more_reuse->bind_inany = reuse->bind_inany; + more_reuse->has_conns = reuse->has_conns; memcpy(more_reuse->socks, reuse->socks, reuse->num_socks * sizeof(struct sock *)); diff --git a/net/core/sysctl_net_core.c b/net/core/sysctl_net_core.c index 9f9e00ba3ad7..669cbe1609d9 100644 --- a/net/core/sysctl_net_core.c +++ b/net/core/sysctl_net_core.c @@ -277,7 +277,7 @@ static int proc_dointvec_minmax_bpf_enable(struct ctl_table *table, int write, ret = proc_dointvec_minmax(&tmp, write, buffer, lenp, ppos); if (write && !ret) { if (jit_enable < 2 || - (jit_enable == 2 && bpf_dump_raw_ok())) { + (jit_enable == 2 && bpf_dump_raw_ok(current_cred()))) { *(int *)table->data = jit_enable; if (jit_enable == 2) pr_warn("bpf_jit_enable = 2 was set! NEVER use this in production, only for JIT debugging!\n"); diff --git a/net/dcb/dcbnl.c b/net/dcb/dcbnl.c index d2a4553bcf39..0fd1c2aa1361 100644 --- a/net/dcb/dcbnl.c +++ b/net/dcb/dcbnl.c @@ -1426,6 +1426,7 @@ static int dcbnl_ieee_set(struct net_device *netdev, struct nlmsghdr *nlh, { const struct dcbnl_rtnl_ops *ops = netdev->dcbnl_ops; struct nlattr *ieee[DCB_ATTR_IEEE_MAX + 1]; + int prio; int err; if (!ops) @@ -1475,6 +1476,13 @@ static int dcbnl_ieee_set(struct net_device *netdev, struct nlmsghdr *nlh, struct dcbnl_buffer *buffer = nla_data(ieee[DCB_ATTR_DCB_BUFFER]); + for (prio = 0; prio < ARRAY_SIZE(buffer->prio2buffer); prio++) { + if (buffer->prio2buffer[prio] >= DCBX_MAX_BUFFERS) { + err = -EINVAL; + goto err; + } + } + err = ops->dcbnl_setbuffer(netdev, buffer); if (err) goto err; diff --git a/net/dsa/tag_edsa.c b/net/dsa/tag_edsa.c index e8eaa804ccb9..d6200ff98200 100644 --- a/net/dsa/tag_edsa.c +++ b/net/dsa/tag_edsa.c @@ -13,6 +13,16 @@ #define DSA_HLEN 4 #define EDSA_HLEN 8 +#define FRAME_TYPE_TO_CPU 0x00 +#define FRAME_TYPE_FORWARD 0x03 + +#define TO_CPU_CODE_MGMT_TRAP 0x00 +#define TO_CPU_CODE_FRAME2REG 0x01 +#define TO_CPU_CODE_IGMP_MLD_TRAP 0x02 +#define TO_CPU_CODE_POLICY_TRAP 0x03 +#define TO_CPU_CODE_ARP_MIRROR 0x04 +#define TO_CPU_CODE_POLICY_MIRROR 0x05 + static struct sk_buff *edsa_xmit(struct sk_buff *skb, struct net_device *dev) { struct dsa_port *dp = dsa_slave_to_port(dev); @@ -77,6 +87,8 @@ static struct sk_buff *edsa_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt) { u8 *edsa_header; + int frame_type; + int code; int source_device; int source_port; @@ -91,8 +103,29 @@ static struct sk_buff *edsa_rcv(struct sk_buff *skb, struct net_device *dev, /* * Check that frame type is either TO_CPU or FORWARD. */ - if ((edsa_header[0] & 0xc0) != 0x00 && (edsa_header[0] & 0xc0) != 0xc0) + frame_type = edsa_header[0] >> 6; + + switch (frame_type) { + case FRAME_TYPE_TO_CPU: + code = (edsa_header[1] & 0x6) | ((edsa_header[2] >> 4) & 1); + + /* + * Mark the frame to never egress on any port of the same switch + * unless it's a trapped IGMP/MLD packet, in which case the + * bridge might want to forward it. + */ + if (code != TO_CPU_CODE_IGMP_MLD_TRAP) + skb->offload_fwd_mark = 1; + + break; + + case FRAME_TYPE_FORWARD: + skb->offload_fwd_mark = 1; + break; + + default: return NULL; + } /* * Determine source device and port. @@ -156,8 +189,6 @@ static struct sk_buff *edsa_rcv(struct sk_buff *skb, struct net_device *dev, 2 * ETH_ALEN); } - skb->offload_fwd_mark = 1; - return skb; } diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c index 2b0521feadaa..0a8220d30c99 100644 --- a/net/ipv4/fib_frontend.c +++ b/net/ipv4/fib_frontend.c @@ -372,6 +372,7 @@ static int __fib_validate_source(struct sk_buff *skb, __be32 src, __be32 dst, fl4.flowi4_tun_key.tun_id = 0; fl4.flowi4_flags = 0; fl4.flowi4_uid = sock_net_uid(net, NULL); + fl4.flowi4_multipath_hash = 0; no_addr = idev->ifa_list == NULL; diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c index 01588eef0cee..b1b3220917ca 100644 --- a/net/ipv4/fib_semantics.c +++ b/net/ipv4/fib_semantics.c @@ -1100,7 +1100,7 @@ static int fib_check_nh_v4_gw(struct net *net, struct fib_nh *nh, u32 table, if (fl4.flowi4_scope < RT_SCOPE_LINK) fl4.flowi4_scope = RT_SCOPE_LINK; - if (table) + if (table && table != RT_TABLE_MAIN) tbl = fib_get_table(net, table); if (tbl) diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c index 1b851fd82613..51673d00bbea 100644 --- a/net/ipv4/fib_trie.c +++ b/net/ipv4/fib_trie.c @@ -1751,7 +1751,7 @@ struct fib_table *fib_trie_unmerge(struct fib_table *oldtb) while ((l = leaf_walk_rcu(&tp, key)) != NULL) { struct key_vector *local_l = NULL, *local_tp; - hlist_for_each_entry_rcu(fa, &l->leaf, fa_list) { + hlist_for_each_entry(fa, &l->leaf, fa_list) { struct fib_alias *new_fa; if (local_tb->tb_id != fa->tb_id) @@ -2010,7 +2010,8 @@ void fib_info_notify_update(struct net *net, struct nl_info *info) struct hlist_head *head = &net->ipv4.fib_table_hash[h]; struct fib_table *tb; - hlist_for_each_entry_rcu(tb, head, tb_hlist) + hlist_for_each_entry_rcu(tb, head, tb_hlist, + lockdep_rtnl_is_held()) __fib_info_notify_update(net, tb, info); } } diff --git a/net/ipv4/gre_offload.c b/net/ipv4/gre_offload.c index 4de7e962d3da..c840141876bc 100644 --- a/net/ipv4/gre_offload.c +++ b/net/ipv4/gre_offload.c @@ -15,12 +15,12 @@ static struct sk_buff *gre_gso_segment(struct sk_buff *skb, netdev_features_t features) { int tnl_hlen = skb_inner_mac_header(skb) - skb_transport_header(skb); + bool need_csum, need_recompute_csum, gso_partial; struct sk_buff *segs = ERR_PTR(-EINVAL); u16 mac_offset = skb->mac_header; __be16 protocol = skb->protocol; u16 mac_len = skb->mac_len; int gre_offset, outer_hlen; - bool need_csum, gso_partial; if (!skb->encapsulation) goto out; @@ -41,6 +41,7 @@ static struct sk_buff *gre_gso_segment(struct sk_buff *skb, skb->protocol = skb->inner_protocol; need_csum = !!(skb_shinfo(skb)->gso_type & SKB_GSO_GRE_CSUM); + need_recompute_csum = skb->csum_not_inet; skb->encap_hdr_csum = need_csum; features &= skb->dev->hw_enc_features; @@ -98,7 +99,15 @@ static struct sk_buff *gre_gso_segment(struct sk_buff *skb, } *(pcsum + 1) = 0; - *pcsum = gso_make_checksum(skb, 0); + if (need_recompute_csum && !skb_is_gso(skb)) { + __wsum csum; + + csum = skb_checksum(skb, gre_offset, + skb->len - gre_offset, 0); + *pcsum = csum_fold(csum); + } else { + *pcsum = gso_make_checksum(skb, 0); + } } while ((skb = skb->next)); out: return segs; diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c index ac95ba78b903..d00533aea1f0 100644 --- a/net/ipv4/icmp.c +++ b/net/ipv4/icmp.c @@ -239,7 +239,7 @@ static struct { /** * icmp_global_allow - Are we allowed to send one more ICMP message ? * - * Uses a token bucket to limit our ICMP messages to sysctl_icmp_msgs_per_sec. + * Uses a token bucket to limit our ICMP messages to ~sysctl_icmp_msgs_per_sec. * Returns false if we reached the limit and can not send another packet. * Note: called with BH disabled */ @@ -267,7 +267,10 @@ bool icmp_global_allow(void) } credit = min_t(u32, icmp_global.credit + incr, sysctl_icmp_msgs_burst); if (credit) { - credit--; + /* We want to use a credit of one in average, but need to randomize + * it for security reasons. + */ + credit = max_t(int, credit - prandom_u32_max(3), 0); rc = true; } WRITE_ONCE(icmp_global.credit, credit); @@ -427,7 +430,7 @@ static void icmp_reply(struct icmp_bxm *icmp_param, struct sk_buff *skb) ipcm_init(&ipc); inet->tos = ip_hdr(skb)->tos; - sk->sk_mark = mark; + ipc.sockc.mark = mark; daddr = ipc.addr = ip_hdr(skb)->saddr; saddr = fib_compute_spec_dst(skb); @@ -709,10 +712,10 @@ void __icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info, icmp_param.skb = skb_in; icmp_param.offset = skb_network_offset(skb_in); inet_sk(sk)->tos = tos; - sk->sk_mark = mark; ipcm_init(&ipc); ipc.addr = iph->saddr; ipc.opt = &icmp_param.replyopts.opt; + ipc.sockc.mark = mark; rt = icmp_route_lookup(net, &fl4, skb_in, iph, saddr, tos, mark, type, code, &icmp_param); diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index 5e486895d67c..9745c52f49ca 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -284,6 +284,57 @@ static inline int sk_reuseport_match(struct inet_bind_bucket *tb, ipv6_only_sock(sk), true, false); } +void inet_csk_update_fastreuse(struct inet_bind_bucket *tb, + struct sock *sk) +{ + kuid_t uid = sock_i_uid(sk); + bool reuse = sk->sk_reuse && sk->sk_state != TCP_LISTEN; + + if (hlist_empty(&tb->owners)) { + tb->fastreuse = reuse; + if (sk->sk_reuseport) { + tb->fastreuseport = FASTREUSEPORT_ANY; + tb->fastuid = uid; + tb->fast_rcv_saddr = sk->sk_rcv_saddr; + tb->fast_ipv6_only = ipv6_only_sock(sk); + tb->fast_sk_family = sk->sk_family; +#if IS_ENABLED(CONFIG_IPV6) + tb->fast_v6_rcv_saddr = sk->sk_v6_rcv_saddr; +#endif + } else { + tb->fastreuseport = 0; + } + } else { + if (!reuse) + tb->fastreuse = 0; + if (sk->sk_reuseport) { + /* We didn't match or we don't have fastreuseport set on + * the tb, but we have sk_reuseport set on this socket + * and we know that there are no bind conflicts with + * this socket in this tb, so reset our tb's reuseport + * settings so that any subsequent sockets that match + * our current socket will be put on the fast path. + * + * If we reset we need to set FASTREUSEPORT_STRICT so we + * do extra checking for all subsequent sk_reuseport + * socks. + */ + if (!sk_reuseport_match(tb, sk)) { + tb->fastreuseport = FASTREUSEPORT_STRICT; + tb->fastuid = uid; + tb->fast_rcv_saddr = sk->sk_rcv_saddr; + tb->fast_ipv6_only = ipv6_only_sock(sk); + tb->fast_sk_family = sk->sk_family; +#if IS_ENABLED(CONFIG_IPV6) + tb->fast_v6_rcv_saddr = sk->sk_v6_rcv_saddr; +#endif + } + } else { + tb->fastreuseport = 0; + } + } +} + /* Obtain a reference to a local port for the given sock, * if snum is zero it means select any available local port. * We try to allocate an odd port (and leave even ports for connect()) @@ -296,7 +347,6 @@ int inet_csk_get_port(struct sock *sk, unsigned short snum) struct inet_bind_hashbucket *head; struct net *net = sock_net(sk); struct inet_bind_bucket *tb = NULL; - kuid_t uid = sock_i_uid(sk); int l3mdev; l3mdev = inet_sk_bound_l3mdev(sk); @@ -333,49 +383,8 @@ tb_found: goto fail_unlock; } success: - if (hlist_empty(&tb->owners)) { - tb->fastreuse = reuse; - if (sk->sk_reuseport) { - tb->fastreuseport = FASTREUSEPORT_ANY; - tb->fastuid = uid; - tb->fast_rcv_saddr = sk->sk_rcv_saddr; - tb->fast_ipv6_only = ipv6_only_sock(sk); - tb->fast_sk_family = sk->sk_family; -#if IS_ENABLED(CONFIG_IPV6) - tb->fast_v6_rcv_saddr = sk->sk_v6_rcv_saddr; -#endif - } else { - tb->fastreuseport = 0; - } - } else { - if (!reuse) - tb->fastreuse = 0; - if (sk->sk_reuseport) { - /* We didn't match or we don't have fastreuseport set on - * the tb, but we have sk_reuseport set on this socket - * and we know that there are no bind conflicts with - * this socket in this tb, so reset our tb's reuseport - * settings so that any subsequent sockets that match - * our current socket will be put on the fast path. - * - * If we reset we need to set FASTREUSEPORT_STRICT so we - * do extra checking for all subsequent sk_reuseport - * socks. - */ - if (!sk_reuseport_match(tb, sk)) { - tb->fastreuseport = FASTREUSEPORT_STRICT; - tb->fastuid = uid; - tb->fast_rcv_saddr = sk->sk_rcv_saddr; - tb->fast_ipv6_only = ipv6_only_sock(sk); - tb->fast_sk_family = sk->sk_family; -#if IS_ENABLED(CONFIG_IPV6) - tb->fast_v6_rcv_saddr = sk->sk_v6_rcv_saddr; -#endif - } - } else { - tb->fastreuseport = 0; - } - } + inet_csk_update_fastreuse(tb, sk); + if (!inet_csk(sk)->icsk_bind_hash) inet_bind_hash(sk, tb, port); WARN_ON(inet_csk(sk)->icsk_bind_hash != tb); diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c index 2bbaaf0c7176..006a34b18537 100644 --- a/net/ipv4/inet_hashtables.c +++ b/net/ipv4/inet_hashtables.c @@ -163,6 +163,7 @@ int __inet_inherit_port(const struct sock *sk, struct sock *child) return -ENOMEM; } } + inet_csk_update_fastreuse(tb, child); } inet_bind_hash(child, tb, port); spin_unlock(&head->lock); diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index 85ba1453ba5c..fedad3a3e61b 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -603,9 +603,7 @@ static netdev_tx_t ipgre_xmit(struct sk_buff *skb, } if (dev->header_ops) { - /* Need space for new headers */ - if (skb_cow_head(skb, dev->needed_headroom - - (tunnel->hlen + sizeof(struct iphdr)))) + if (skb_cow_head(skb, 0)) goto free_skb; tnl_params = (const struct iphdr *)skb->data; @@ -723,7 +721,11 @@ static void ipgre_link_update(struct net_device *dev, bool set_mtu) len = tunnel->tun_hlen - len; tunnel->hlen = tunnel->hlen + len; - dev->needed_headroom = dev->needed_headroom + len; + if (dev->header_ops) + dev->hard_header_len += len; + else + dev->needed_headroom += len; + if (set_mtu) dev->mtu = max_t(int, dev->mtu - len, 68); @@ -926,6 +928,7 @@ static void __gre_tunnel_init(struct net_device *dev) tunnel->parms.iph.protocol = IPPROTO_GRE; tunnel->hlen = tunnel->tun_hlen + tunnel->encap_hlen; + dev->needed_headroom = tunnel->hlen + sizeof(tunnel->parms.iph); dev->features |= GRE_FEATURES; dev->hw_features |= GRE_FEATURES; @@ -969,10 +972,14 @@ static int ipgre_tunnel_init(struct net_device *dev) return -EINVAL; dev->flags = IFF_BROADCAST; dev->header_ops = &ipgre_header_ops; + dev->hard_header_len = tunnel->hlen + sizeof(*iph); + dev->needed_headroom = 0; } #endif } else if (!tunnel->collect_md) { dev->header_ops = &ipgre_header_ops; + dev->hard_header_len = tunnel->hlen + sizeof(*iph); + dev->needed_headroom = 0; } return ip_tunnel_init(dev); diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index b268ee1c1b44..079dcf9f0c56 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -74,6 +74,7 @@ #include <net/icmp.h> #include <net/checksum.h> #include <net/inetpeer.h> +#include <net/inet_ecn.h> #include <net/lwtunnel.h> #include <linux/bpf-cgroup.h> #include <linux/igmp.h> @@ -1699,12 +1700,12 @@ void ip_send_unicast_reply(struct sock *sk, struct sk_buff *skb, if (IS_ERR(rt)) return; - inet_sk(sk)->tos = arg->tos; + inet_sk(sk)->tos = arg->tos & ~INET_ECN_MASK; sk->sk_protocol = ip_hdr(skb)->protocol; sk->sk_bound_dev_if = arg->bound_dev_if; sk->sk_sndbuf = sysctl_wmem_default; - sk->sk_mark = fl4.flowi4_mark; + ipc.sockc.mark = fl4.flowi4_mark; err = ip_append_data(sk, &fl4, ip_reply_glue_bits, arg->iov->iov_base, len, 0, &ipc, &rt, MSG_DONTWAIT); if (unlikely(err)) { diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c index cd4b84310d92..a0b4dc54f8a6 100644 --- a/net/ipv4/ip_tunnel.c +++ b/net/ipv4/ip_tunnel.c @@ -85,9 +85,10 @@ struct ip_tunnel *ip_tunnel_lookup(struct ip_tunnel_net *itn, __be32 remote, __be32 local, __be32 key) { - unsigned int hash; struct ip_tunnel *t, *cand = NULL; struct hlist_head *head; + struct net_device *ndev; + unsigned int hash; hash = ip_tunnel_hash(key, remote); head = &itn->tunnels[hash]; @@ -162,8 +163,9 @@ struct ip_tunnel *ip_tunnel_lookup(struct ip_tunnel_net *itn, if (t && t->dev->flags & IFF_UP) return t; - if (itn->fb_tunnel_dev && itn->fb_tunnel_dev->flags & IFF_UP) - return netdev_priv(itn->fb_tunnel_dev); + ndev = READ_ONCE(itn->fb_tunnel_dev); + if (ndev && ndev->flags & IFF_UP) + return netdev_priv(ndev); return NULL; } @@ -1245,9 +1247,9 @@ void ip_tunnel_uninit(struct net_device *dev) struct ip_tunnel_net *itn; 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(itn, netdev_priv(dev)); + ip_tunnel_del(itn, netdev_priv(dev)); + if (itn->fb_tunnel_dev == dev) + WRITE_ONCE(itn->fb_tunnel_dev, NULL); dst_cache_reset(&tunnel->dst_cache); } diff --git a/net/ipv4/netfilter/nf_log_arp.c b/net/ipv4/netfilter/nf_log_arp.c index 7a83f881efa9..136030ad2e54 100644 --- a/net/ipv4/netfilter/nf_log_arp.c +++ b/net/ipv4/netfilter/nf_log_arp.c @@ -43,16 +43,31 @@ static void dump_arp_packet(struct nf_log_buf *m, const struct nf_loginfo *info, const struct sk_buff *skb, unsigned int nhoff) { - const struct arphdr *ah; - struct arphdr _arph; const struct arppayload *ap; struct arppayload _arpp; + const struct arphdr *ah; + unsigned int logflags; + struct arphdr _arph; ah = skb_header_pointer(skb, 0, sizeof(_arph), &_arph); if (ah == NULL) { nf_log_buf_add(m, "TRUNCATED"); return; } + + if (info->type == NF_LOG_TYPE_LOG) + logflags = info->u.log.logflags; + else + logflags = NF_LOG_DEFAULT_MASK; + + if (logflags & NF_LOG_MACDECODE) { + nf_log_buf_add(m, "MACSRC=%pM MACDST=%pM ", + eth_hdr(skb)->h_source, eth_hdr(skb)->h_dest); + nf_log_dump_vlan(m, skb); + nf_log_buf_add(m, "MACPROTO=%04x ", + ntohs(eth_hdr(skb)->h_proto)); + } + nf_log_buf_add(m, "ARP HTYPE=%d PTYPE=0x%04x OPCODE=%d", ntohs(ah->ar_hrd), ntohs(ah->ar_pro), ntohs(ah->ar_op)); diff --git a/net/ipv4/netfilter/nf_log_ipv4.c b/net/ipv4/netfilter/nf_log_ipv4.c index 4b2d49cc9f1a..cb288ffbcfde 100644 --- a/net/ipv4/netfilter/nf_log_ipv4.c +++ b/net/ipv4/netfilter/nf_log_ipv4.c @@ -284,8 +284,10 @@ static void dump_ipv4_mac_header(struct nf_log_buf *m, switch (dev->type) { case ARPHRD_ETHER: - nf_log_buf_add(m, "MACSRC=%pM MACDST=%pM MACPROTO=%04x ", - eth_hdr(skb)->h_source, eth_hdr(skb)->h_dest, + nf_log_buf_add(m, "MACSRC=%pM MACDST=%pM ", + eth_hdr(skb)->h_source, eth_hdr(skb)->h_dest); + nf_log_dump_vlan(m, skb); + nf_log_buf_add(m, "MACPROTO=%04x ", ntohs(eth_hdr(skb)->h_proto)); return; default: diff --git a/net/ipv4/nexthop.c b/net/ipv4/nexthop.c index a01f500d6a6b..ea32b113089d 100644 --- a/net/ipv4/nexthop.c +++ b/net/ipv4/nexthop.c @@ -403,7 +403,7 @@ static int nh_check_attr_group(struct net *net, struct nlattr *tb[], struct nexthop_grp *nhg; unsigned int i, j; - if (len & (sizeof(struct nexthop_grp) - 1)) { + if (!len || len & (sizeof(struct nexthop_grp) - 1)) { NL_SET_ERR_MSG(extack, "Invalid length for nexthop group attribute"); return -EINVAL; @@ -763,7 +763,7 @@ static void remove_nexthop_from_groups(struct net *net, struct nexthop *nh, remove_nh_grp_entry(net, nhge, nlinfo); /* make sure all see the newly published array before releasing rtnl */ - synchronize_rcu(); + synchronize_net(); } static void remove_nexthop_group(struct nexthop *nh, struct nl_info *nlinfo) @@ -1105,6 +1105,9 @@ static struct nexthop *nexthop_create_group(struct net *net, struct nexthop *nh; int i; + if (WARN_ON(!num_nh)) + return ERR_PTR(-EINVAL); + nh = nexthop_alloc(); if (!nh) return ERR_PTR(-ENOMEM); diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c index 535427292194..df6fbefe44d4 100644 --- a/net/ipv4/ping.c +++ b/net/ipv4/ping.c @@ -786,6 +786,9 @@ static int ping_v4_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) inet_sk_flowi_flags(sk), faddr, saddr, 0, 0, sk->sk_uid); + fl4.fl4_icmp_type = user_icmph.type; + fl4.fl4_icmp_code = user_icmph.code; + security_sk_classify_flow(sk, flowi4_to_flowi(&fl4)); rt = ip_route_output_flow(net, &fl4, sk); if (IS_ERR(rt)) { diff --git a/net/ipv4/route.c b/net/ipv4/route.c index b3a8d32f7d8d..a293d4968d1e 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -271,6 +271,7 @@ static void *rt_cpu_seq_next(struct seq_file *seq, void *v, loff_t *pos) *pos = cpu+1; return &per_cpu(rt_cache_stat, cpu); } + (*pos)++; return NULL; } @@ -785,8 +786,10 @@ static void __ip_do_redirect(struct rtable *rt, struct sk_buff *skb, struct flow neigh_event_send(n, NULL); } else { if (fib_lookup(net, fl4, &res, 0) == 0) { - struct fib_nh_common *nhc = FIB_RES_NHC(res); + struct fib_nh_common *nhc; + fib_select_path(net, &res, fl4, skb); + nhc = FIB_RES_NHC(res); update_or_create_fnhe(nhc, fl4->daddr, new_gw, 0, false, jiffies + ip_rt_gc_timeout); @@ -1012,6 +1015,7 @@ out: kfree_skb(skb); static void __ip_rt_update_pmtu(struct rtable *rt, struct flowi4 *fl4, u32 mtu) { struct dst_entry *dst = &rt->dst; + struct net *net = dev_net(dst->dev); u32 old_mtu = ipv4_mtu(dst); struct fib_result res; bool lock = false; @@ -1032,9 +1036,11 @@ static void __ip_rt_update_pmtu(struct rtable *rt, struct flowi4 *fl4, u32 mtu) return; rcu_read_lock(); - if (fib_lookup(dev_net(dst->dev), fl4, &res, 0) == 0) { - struct fib_nh_common *nhc = FIB_RES_NHC(res); + if (fib_lookup(net, fl4, &res, 0) == 0) { + struct fib_nh_common *nhc; + fib_select_path(net, &res, fl4, NULL); + nhc = FIB_RES_NHC(res); update_or_create_fnhe(nhc, fl4->daddr, 0, mtu, lock, jiffies + ip_rt_mtu_expires); } @@ -2104,6 +2110,7 @@ static int ip_route_input_slow(struct sk_buff *skb, __be32 daddr, __be32 saddr, fl4.daddr = daddr; fl4.saddr = saddr; fl4.flowi4_uid = sock_net_uid(net, NULL); + fl4.flowi4_multipath_hash = 0; if (fib4_rules_early_flow_dissect(net, skb, &fl4, &_flkeys)) { flkeys = &_flkeys; @@ -2625,8 +2632,6 @@ struct rtable *ip_route_output_key_hash_rcu(struct net *net, struct flowi4 *fl4, fib_select_path(net, res, fl4, skb); dev_out = FIB_RES_DEV(*res); - fl4->flowi4_oif = dev_out->ifindex; - make_route: rth = __mkroute_output(res, fl4, orig_oif, dev_out, flags); @@ -2723,10 +2728,12 @@ struct rtable *ip_route_output_flow(struct net *net, struct flowi4 *flp4, if (IS_ERR(rt)) return rt; - if (flp4->flowi4_proto) + if (flp4->flowi4_proto) { + flp4->flowi4_oif = rt->dst.dev->ifindex; rt = (struct rtable *)xfrm_lookup_route(net, &rt->dst, flowi4_to_flowi(flp4), sk, 0); + } return rt; } diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c index 0902cb32bbad..c83a5d05aeaa 100644 --- a/net/ipv4/sysctl_net_ipv4.c +++ b/net/ipv4/sysctl_net_ipv4.c @@ -307,24 +307,16 @@ static int proc_tcp_fastopen_key(struct ctl_table *table, int write, struct ctl_table tbl = { .maxlen = ((TCP_FASTOPEN_KEY_LENGTH * 2 * TCP_FASTOPEN_KEY_MAX) + (TCP_FASTOPEN_KEY_MAX * 5)) }; - struct tcp_fastopen_context *ctx; - u32 user_key[TCP_FASTOPEN_KEY_MAX * 4]; - __le32 key[TCP_FASTOPEN_KEY_MAX * 4]; + u32 user_key[TCP_FASTOPEN_KEY_BUF_LENGTH / sizeof(u32)]; + __le32 key[TCP_FASTOPEN_KEY_BUF_LENGTH / sizeof(__le32)]; char *backup_data; - int ret, i = 0, off = 0, n_keys = 0; + int ret, i = 0, off = 0, n_keys; tbl.data = kmalloc(tbl.maxlen, GFP_KERNEL); if (!tbl.data) return -ENOMEM; - rcu_read_lock(); - ctx = rcu_dereference(net->ipv4.tcp_fastopen_ctx); - if (ctx) { - n_keys = tcp_fastopen_context_len(ctx); - memcpy(&key[0], &ctx->key[0], TCP_FASTOPEN_KEY_LENGTH * n_keys); - } - rcu_read_unlock(); - + n_keys = tcp_fastopen_get_cipher(net, NULL, (u64 *)key); if (!n_keys) { memset(&key[0], 0, TCP_FASTOPEN_KEY_LENGTH); n_keys = 1; diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index fe3cdeddd097..d3ced6a39bcf 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -484,6 +484,8 @@ static inline bool tcp_stream_is_readable(const struct tcp_sock *tp, return true; if (tcp_rmem_pressure(sk)) return true; + if (tcp_receive_window(tp) <= inet_csk(sk)->icsk_ack.rcv_mss) + return true; } if (sk->sk_prot->stream_memory_read) return sk->sk_prot->stream_memory_read(sk); @@ -971,7 +973,8 @@ ssize_t do_tcp_sendpages(struct sock *sk, struct page *page, int offset, long timeo = sock_sndtimeo(sk, flags & MSG_DONTWAIT); if (IS_ENABLED(CONFIG_DEBUG_VM) && - WARN_ONCE(PageSlab(page), "page must not be a Slab one")) + WARN_ONCE(!sendpage_ok(page), + "page must not be a Slab one and have page_count > 0")) return -EINVAL; /* Wait for a connection to finish. One exception is TCP Fast Open @@ -2053,7 +2056,7 @@ int tcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int nonblock, /* Well, if we have backlog, try to process it now yet. */ - if (copied >= target && !sk->sk_backlog.tail) + if (copied >= target && !READ_ONCE(sk->sk_backlog.tail)) break; if (copied) { @@ -2631,6 +2634,9 @@ int tcp_disconnect(struct sock *sk, int flags) tp->window_clamp = 0; tp->delivered = 0; tp->delivered_ce = 0; + if (icsk->icsk_ca_ops->release) + icsk->icsk_ca_ops->release(sk); + memset(icsk->icsk_ca_priv, 0, sizeof(icsk->icsk_ca_priv)); tcp_set_ca_state(sk, TCP_CA_Open); tp->is_sack_reneg = 0; tcp_clear_retrans(tp); @@ -3085,10 +3091,7 @@ static int do_tcp_setsockopt(struct sock *sk, int level, #ifdef CONFIG_TCP_MD5SIG case TCP_MD5SIG: case TCP_MD5SIG_EXT: - if ((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN)) - err = tp->af_specific->md5_parse(sk, optname, optval, optlen); - else - err = -EINVAL; + err = tp->af_specific->md5_parse(sk, optname, optval, optlen); break; #endif case TCP_USER_TIMEOUT: @@ -3527,22 +3530,14 @@ static int do_tcp_getsockopt(struct sock *sk, int level, return 0; case TCP_FASTOPEN_KEY: { - __u8 key[TCP_FASTOPEN_KEY_BUF_LENGTH]; - struct tcp_fastopen_context *ctx; - unsigned int key_len = 0; + u64 key[TCP_FASTOPEN_KEY_BUF_LENGTH / sizeof(u64)]; + unsigned int key_len; if (get_user(len, optlen)) return -EFAULT; - rcu_read_lock(); - ctx = rcu_dereference(icsk->icsk_accept_queue.fastopenq.ctx); - if (ctx) { - key_len = tcp_fastopen_context_len(ctx) * - TCP_FASTOPEN_KEY_LENGTH; - memcpy(&key[0], &ctx->key[0], key_len); - } - rcu_read_unlock(); - + key_len = tcp_fastopen_get_cipher(net, icsk, key) * + TCP_FASTOPEN_KEY_LENGTH; len = min_t(unsigned int, len, key_len); if (put_user(len, optlen)) return -EFAULT; @@ -3844,10 +3839,13 @@ EXPORT_SYMBOL(tcp_md5_hash_skb_data); int tcp_md5_hash_key(struct tcp_md5sig_pool *hp, const struct tcp_md5sig_key *key) { + u8 keylen = READ_ONCE(key->keylen); /* paired with WRITE_ONCE() in tcp_md5_do_add */ struct scatterlist sg; - sg_init_one(&sg, key->key, key->keylen); - ahash_request_set_crypt(hp->md5_req, &sg, NULL, key->keylen); + sg_init_one(&sg, key->key, keylen); + ahash_request_set_crypt(hp->md5_req, &sg, NULL, keylen); + + /* tcp_md5_do_add() might change key->key under us */ return crypto_ahash_update(hp->md5_req); } EXPORT_SYMBOL(tcp_md5_hash_key); diff --git a/net/ipv4/tcp_bpf.c b/net/ipv4/tcp_bpf.c index 69b025408390..ad9f38202731 100644 --- a/net/ipv4/tcp_bpf.c +++ b/net/ipv4/tcp_bpf.c @@ -96,6 +96,9 @@ int __tcp_bpf_recvmsg(struct sock *sk, struct sk_psock *psock, } while (i != msg_rx->sg.end); if (unlikely(peek)) { + if (msg_rx == list_last_entry(&psock->ingress_msg, + struct sk_msg, list)) + break; msg_rx = list_next_entry(msg_rx, list); continue; } diff --git a/net/ipv4/tcp_cong.c b/net/ipv4/tcp_cong.c index c445a81d144e..d7a1f2ef6c52 100644 --- a/net/ipv4/tcp_cong.c +++ b/net/ipv4/tcp_cong.c @@ -197,7 +197,7 @@ static void tcp_reinit_congestion_control(struct sock *sk, icsk->icsk_ca_setsockopt = 1; memset(icsk->icsk_ca_priv, 0, sizeof(icsk->icsk_ca_priv)); - if (sk->sk_state != TCP_CLOSE) + if (!((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN))) tcp_init_congestion_control(sk); } diff --git a/net/ipv4/tcp_cubic.c b/net/ipv4/tcp_cubic.c index 1b3d032a4df2..ee6c38a73325 100644 --- a/net/ipv4/tcp_cubic.c +++ b/net/ipv4/tcp_cubic.c @@ -404,6 +404,8 @@ static void hystart_update(struct sock *sk, u32 delay) if (hystart_detect & HYSTART_DELAY) { /* obtain the minimum delay of more than sampling packets */ + if (ca->curr_rtt > delay) + ca->curr_rtt = delay; if (ca->sample_cnt < HYSTART_MIN_SAMPLES) { if (ca->curr_rtt == 0 || ca->curr_rtt > delay) ca->curr_rtt = delay; diff --git a/net/ipv4/tcp_fastopen.c b/net/ipv4/tcp_fastopen.c index a915ade0c818..a9971e41f31b 100644 --- a/net/ipv4/tcp_fastopen.c +++ b/net/ipv4/tcp_fastopen.c @@ -108,6 +108,29 @@ out: return err; } +int tcp_fastopen_get_cipher(struct net *net, struct inet_connection_sock *icsk, + u64 *key) +{ + struct tcp_fastopen_context *ctx; + int n_keys = 0, i; + + rcu_read_lock(); + if (icsk) + ctx = rcu_dereference(icsk->icsk_accept_queue.fastopenq.ctx); + else + ctx = rcu_dereference(net->ipv4.tcp_fastopen_ctx); + if (ctx) { + n_keys = tcp_fastopen_context_len(ctx); + for (i = 0; i < n_keys; i++) { + put_unaligned_le64(ctx->key[i].key[0], key + (i * 2)); + put_unaligned_le64(ctx->key[i].key[1], key + (i * 2) + 1); + } + } + rcu_read_unlock(); + + return n_keys; +} + static bool __tcp_fastopen_cookie_gen_cipher(struct request_sock *req, struct sk_buff *syn, const siphash_key_t *key, diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 677facbeed26..54fd6bc5adcc 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -260,7 +260,8 @@ static void tcp_ecn_accept_cwr(struct sock *sk, const struct sk_buff *skb) * cwnd may be very low (even just 1 packet), so we should ACK * immediately. */ - inet_csk(sk)->icsk_ack.pending |= ICSK_ACK_NOW; + if (TCP_SKB_CB(skb)->seq != TCP_SKB_CB(skb)->end_seq) + inet_csk(sk)->icsk_ack.pending |= ICSK_ACK_NOW; } } @@ -2943,6 +2944,8 @@ static bool tcp_ack_update_rtt(struct sock *sk, const int flag, u32 delta = tcp_time_stamp(tp) - tp->rx_opt.rcv_tsecr; if (likely(delta < INT_MAX / (USEC_PER_SEC / TCP_TS_HZ))) { + if (!delta) + delta = 1; seq_rtt_us = delta * (USEC_PER_SEC / TCP_TS_HZ); ca_rtt_us = seq_rtt_us; } @@ -3504,10 +3507,8 @@ static void tcp_replace_ts_recent(struct tcp_sock *tp, u32 seq) } } -/* This routine deals with acks during a TLP episode. - * We mark the end of a TLP episode on receiving TLP dupack or when - * ack is after tlp_high_seq. - * Ref: loss detection algorithm in draft-dukkipati-tcpm-tcp-loss-probe. +/* This routine deals with acks during a TLP episode and ends an episode by + * resetting tlp_high_seq. Ref: TLP algorithm in draft-ietf-tcpm-rack */ static void tcp_process_tlp_ack(struct sock *sk, u32 ack, int flag) { @@ -3516,7 +3517,10 @@ static void tcp_process_tlp_ack(struct sock *sk, u32 ack, int flag) if (before(ack, tp->tlp_high_seq)) return; - if (flag & FLAG_DSACKING_ACK) { + if (!tp->tlp_retrans) { + /* TLP of new data has been acknowledged */ + tp->tlp_high_seq = 0; + } else if (flag & FLAG_DSACKING_ACK) { /* This DSACK means original and TLP probe arrived; no loss */ tp->tlp_high_seq = 0; } else if (after(ack, tp->tlp_high_seq)) { @@ -3682,6 +3686,15 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag) tcp_in_ack_event(sk, ack_ev_flags); } + /* This is a deviation from RFC3168 since it states that: + * "When the TCP data sender is ready to set the CWR bit after reducing + * the congestion window, it SHOULD set the CWR bit only on the first + * new data packet that it transmits." + * We accept CWR on pure ACKs to be more robust + * with widely-deployed TCP implementations that do this. + */ + tcp_ecn_accept_cwr(sk, skb); + /* We passed data and got it acked, remove any soft error * log. Something worked... */ @@ -4554,6 +4567,7 @@ static void tcp_data_queue_ofo(struct sock *sk, struct sk_buff *skb) if (unlikely(tcp_try_rmem_schedule(sk, skb, skb->truesize))) { NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPOFODROP); + sk->sk_data_ready(sk); tcp_drop(sk, skb); return; } @@ -4587,7 +4601,11 @@ static void tcp_data_queue_ofo(struct sock *sk, struct sk_buff *skb) if (tcp_ooo_try_coalesce(sk, tp->ooo_last_skb, skb, &fragstolen)) { coalesce_done: - tcp_grow_window(sk, skb); + /* For non sack flows, do not grow window to force DUPACK + * and trigger fast retransmit. + */ + if (tcp_is_sack(tp)) + tcp_grow_window(sk, skb); kfree_skb_partial(skb, fragstolen); skb = NULL; goto add_sack; @@ -4671,7 +4689,11 @@ add_sack: tcp_sack_new_ofo_skb(sk, seq, end_seq); end: if (skb) { - tcp_grow_window(sk, skb); + /* For non sack flows, do not grow window to force DUPACK + * and trigger fast retransmit. + */ + if (tcp_is_sack(tp)) + tcp_grow_window(sk, skb); skb_condense(skb); skb_set_owner_r(skb, sk); } @@ -4752,7 +4774,8 @@ void tcp_data_ready(struct sock *sk) int avail = tp->rcv_nxt - tp->copied_seq; if (avail < sk->sk_rcvlowat && !tcp_rmem_pressure(sk) && - !sock_flag(sk, SOCK_DONE)) + !sock_flag(sk, SOCK_DONE) && + tcp_receive_window(tp) > inet_csk(sk)->icsk_ack.rcv_mss) return; sk->sk_data_ready(sk); @@ -4771,8 +4794,6 @@ static void tcp_data_queue(struct sock *sk, struct sk_buff *skb) skb_dst_drop(skb); __skb_pull(skb, tcp_hdr(skb)->doff * 4); - tcp_ecn_accept_cwr(sk, skb); - tp->rx_opt.dsack = 0; /* Queue data for delivery to the user. @@ -4791,6 +4812,7 @@ queue_and_out: sk_forced_mem_schedule(sk, skb->truesize); else if (tcp_try_rmem_schedule(sk, skb, skb->truesize)) { NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPRCVQDROP); + sk->sk_data_ready(sk); goto drop; } @@ -5675,6 +5697,8 @@ void tcp_rcv_established(struct sock *sk, struct sk_buff *skb) tcp_data_snd_check(sk); if (!inet_csk_ack_scheduled(sk)) goto no_ack; + } else { + tcp_update_wl(tp, TCP_SKB_CB(skb)->seq); } __tcp_ack_snd_check(sk, 0); diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index eda64871f983..87a5037a9cb3 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -1077,9 +1077,18 @@ int tcp_md5_do_add(struct sock *sk, const union tcp_md5_addr *addr, key = tcp_md5_do_lookup_exact(sk, addr, family, prefixlen); if (key) { - /* Pre-existing entry - just update that one. */ + /* Pre-existing entry - just update that one. + * Note that the key might be used concurrently. + */ memcpy(key->key, newkey, newkeylen); - key->keylen = newkeylen; + + /* Pairs with READ_ONCE() in tcp_md5_hash_key(). + * Also note that a reader could catch new key->keylen value + * but old key->key[], this is the reason we use __GFP_ZERO + * at sock_kmalloc() time below these lines. + */ + WRITE_ONCE(key->keylen, newkeylen); + return 0; } @@ -1095,7 +1104,7 @@ int tcp_md5_do_add(struct sock *sk, const union tcp_md5_addr *addr, rcu_assign_pointer(tp->md5sig_info, md5sig); } - key = sock_kmalloc(sk, sizeof(*key), gfp); + key = sock_kmalloc(sk, sizeof(*key), gfp | __GFP_ZERO); if (!key) return -ENOMEM; if (!tcp_alloc_md5sig_pool()) { @@ -1710,12 +1719,12 @@ bool tcp_add_backlog(struct sock *sk, struct sk_buff *skb) __skb_pull(skb, hdrlen); if (skb_try_coalesce(tail, skb, &fragstolen, &delta)) { - thtail->window = th->window; - TCP_SKB_CB(tail)->end_seq = TCP_SKB_CB(skb)->end_seq; - if (after(TCP_SKB_CB(skb)->ack_seq, TCP_SKB_CB(tail)->ack_seq)) + if (likely(!before(TCP_SKB_CB(skb)->ack_seq, TCP_SKB_CB(tail)->ack_seq))) { TCP_SKB_CB(tail)->ack_seq = TCP_SKB_CB(skb)->ack_seq; + thtail->window = th->window; + } /* We have to update both TCP_SKB_CB(tail)->tcp_flags and * thtail->fin, so that the fast path in tcp_rcv_established() diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index c8d03c1b4c6b..4407193bd702 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -662,7 +662,8 @@ static unsigned int tcp_synack_options(const struct sock *sk, unsigned int mss, struct sk_buff *skb, struct tcp_out_options *opts, const struct tcp_md5sig_key *md5, - struct tcp_fastopen_cookie *foc) + struct tcp_fastopen_cookie *foc, + enum tcp_synack_type synack_type) { struct inet_request_sock *ireq = inet_rsk(req); unsigned int remaining = MAX_TCP_OPTION_SPACE; @@ -677,7 +678,8 @@ static unsigned int tcp_synack_options(const struct sock *sk, * rather than TS in order to fit in better with old, * buggy kernels, but that was deemed to be unnecessary. */ - ireq->tstamp_ok &= !ireq->sack_ok; + if (synack_type != TCP_SYNACK_COOKIE) + ireq->tstamp_ok &= !ireq->sack_ok; } #endif @@ -2562,6 +2564,11 @@ void tcp_send_loss_probe(struct sock *sk) int pcount; int mss = tcp_current_mss(sk); + /* At most one outstanding TLP */ + if (tp->tlp_high_seq) + goto rearm_timer; + + tp->tlp_retrans = 0; skb = tcp_send_head(sk); if (skb && tcp_snd_wnd_test(tp, skb, mss)) { pcount = tp->packets_out; @@ -2579,10 +2586,6 @@ void tcp_send_loss_probe(struct sock *sk) return; } - /* At most one outstanding TLP retransmission. */ - if (tp->tlp_high_seq) - goto rearm_timer; - if (skb_still_in_host_queue(sk, skb)) goto rearm_timer; @@ -2604,10 +2607,12 @@ void tcp_send_loss_probe(struct sock *sk) if (__tcp_retransmit_skb(sk, skb, 1)) goto rearm_timer; + tp->tlp_retrans = 1; + +probe_sent: /* Record snd_nxt for loss detection. */ tp->tlp_high_seq = tp->snd_nxt; -probe_sent: NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPLOSSPROBES); /* Reset s.t. tcp_rearm_rto will restart timer from now */ inet_csk(sk)->icsk_pending = 0; @@ -3326,7 +3331,7 @@ struct sk_buff *tcp_make_synack(const struct sock *sk, struct dst_entry *dst, #endif skb_set_hash(skb, tcp_rsk(req)->txhash, PKT_HASH_TYPE_L4); tcp_header_size = tcp_synack_options(sk, req, mss, skb, &opts, md5, - foc) + sizeof(*th); + foc, synack_type) + sizeof(*th); skb_push(skb, tcp_header_size); skb_reset_transport_header(skb); diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index f3b7cb725c1b..5d016bbdf16e 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -413,7 +413,7 @@ static struct sock *udp4_lib_lookup2(struct net *net, struct udp_hslot *hslot2, struct sk_buff *skb) { - struct sock *sk, *result; + struct sock *sk, *result, *reuseport_result; int score, badness; u32 hash = 0; @@ -423,17 +423,20 @@ static struct sock *udp4_lib_lookup2(struct net *net, score = compute_score(sk, net, saddr, sport, daddr, hnum, dif, sdif); if (score > badness) { + reuseport_result = NULL; + if (sk->sk_reuseport && sk->sk_state != TCP_ESTABLISHED) { hash = udp_ehashfn(net, daddr, hnum, saddr, sport); - result = reuseport_select_sock(sk, hash, skb, - sizeof(struct udphdr)); - if (result && !reuseport_has_conns(sk, false)) - return result; + reuseport_result = reuseport_select_sock(sk, hash, skb, + sizeof(struct udphdr)); + if (reuseport_result && !reuseport_has_conns(sk, false)) + return reuseport_result; } + + result = reuseport_result ? : sk; badness = score; - result = sk; } } return result; @@ -2045,7 +2048,7 @@ static int udp_queue_rcv_one_skb(struct sock *sk, struct sk_buff *skb) /* * UDP-Lite specific tests, ignored on UDP sockets */ - if ((is_udplite & UDPLITE_RECV_CC) && UDP_SKB_CB(skb)->partial_cov) { + if ((up->pcflag & UDPLITE_RECV_CC) && UDP_SKB_CB(skb)->partial_cov) { /* * MIB statistics other than incrementing the error count are diff --git a/net/ipv6/Kconfig b/net/ipv6/Kconfig index ae1344e4cec5..dce14470b15a 100644 --- a/net/ipv6/Kconfig +++ b/net/ipv6/Kconfig @@ -289,6 +289,7 @@ config IPV6_SEG6_LWTUNNEL config IPV6_SEG6_HMAC bool "IPv6: Segment Routing HMAC support" depends on IPV6 + select CRYPTO select CRYPTO_HMAC select CRYPTO_SHA1 select CRYPTO_SHA256 diff --git a/net/ipv6/anycast.c b/net/ipv6/anycast.c index fed91ab7ec46..cf3a88a10ddd 100644 --- a/net/ipv6/anycast.c +++ b/net/ipv6/anycast.c @@ -183,7 +183,7 @@ int ipv6_sock_ac_drop(struct sock *sk, int ifindex, const struct in6_addr *addr) return 0; } -void ipv6_sock_ac_close(struct sock *sk) +void __ipv6_sock_ac_close(struct sock *sk) { struct ipv6_pinfo *np = inet6_sk(sk); struct net_device *dev = NULL; @@ -191,10 +191,7 @@ void ipv6_sock_ac_close(struct sock *sk) struct net *net = sock_net(sk); int prev_index; - if (!np->ipv6_ac_list) - return; - - rtnl_lock(); + ASSERT_RTNL(); pac = np->ipv6_ac_list; np->ipv6_ac_list = NULL; @@ -211,6 +208,16 @@ void ipv6_sock_ac_close(struct sock *sk) sock_kfree_s(sk, pac, sizeof(*pac)); pac = next; } +} + +void ipv6_sock_ac_close(struct sock *sk) +{ + struct ipv6_pinfo *np = inet6_sk(sk); + + if (!np->ipv6_ac_list) + return; + rtnl_lock(); + __ipv6_sock_ac_close(sk); rtnl_unlock(); } diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c index 62c997201970..7d3a3894f785 100644 --- a/net/ipv6/icmp.c +++ b/net/ipv6/icmp.c @@ -535,7 +535,6 @@ static void icmp6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info, if (!sk) goto out_bh_enable; - sk->sk_mark = mark; np = inet6_sk(sk); if (!icmpv6_xrlim_allow(sk, type, &fl6)) @@ -552,6 +551,7 @@ static void icmp6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info, fl6.flowi6_oif = np->ucast_oif; ipcm6_init_sk(&ipc6, np); + ipc6.sockc.mark = mark; fl6.flowlabel = ip6_make_flowinfo(ipc6.tclass, fl6.flowlabel); dst = icmpv6_route_lookup(net, skb, sk, &fl6); @@ -720,7 +720,6 @@ static void icmpv6_echo_reply(struct sk_buff *skb) sk = icmpv6_xmit_lock(net); if (!sk) goto out_bh_enable; - sk->sk_mark = mark; np = inet6_sk(sk); if (!fl6.flowi6_oif && ipv6_addr_is_multicast(&fl6.daddr)) @@ -748,6 +747,7 @@ static void icmpv6_echo_reply(struct sk_buff *skb) ipcm6_init_sk(&ipc6, np); ipc6.hlimit = ip6_sk_dst_hoplimit(np, &fl6, dst); ipc6.tclass = ipv6_get_dsfield(ipv6_hdr(skb)); + ipc6.sockc.mark = mark; if (ip6_append_data(sk, icmpv6_getfrag, &msg, skb->len + sizeof(struct icmp6hdr), diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c index 7a0c877ca306..0646fce31b67 100644 --- a/net/ipv6/ip6_fib.c +++ b/net/ipv6/ip6_fib.c @@ -1896,14 +1896,19 @@ static void fib6_del_route(struct fib6_table *table, struct fib6_node *fn, /* Need to own table->tb6_lock */ int fib6_del(struct fib6_info *rt, struct nl_info *info) { - struct fib6_node *fn = rcu_dereference_protected(rt->fib6_node, - lockdep_is_held(&rt->fib6_table->tb6_lock)); - struct fib6_table *table = rt->fib6_table; struct net *net = info->nl_net; struct fib6_info __rcu **rtp; struct fib6_info __rcu **rtp_next; + struct fib6_table *table; + struct fib6_node *fn; - if (!fn || rt == net->ipv6.fib6_null_entry) + if (rt == net->ipv6.fib6_null_entry) + return -ENOENT; + + table = rt->fib6_table; + fn = rcu_dereference_protected(rt->fib6_node, + lockdep_is_held(&table->tb6_lock)); + if (!fn) return -ENOENT; WARN_ON(!(fn->fn_flags & RTN_RTINFO)); @@ -2474,14 +2479,13 @@ static void *ipv6_route_seq_next(struct seq_file *seq, void *v, loff_t *pos) struct net *net = seq_file_net(seq); struct ipv6_route_iter *iter = seq->private; + ++(*pos); if (!v) goto iter_table; n = rcu_dereference_bh(((struct fib6_info *)v)->fib6_next); - if (n) { - ++*pos; + if (n) return n; - } iter_table: ipv6_route_check_sernum(iter); @@ -2489,8 +2493,6 @@ iter_table: r = fib6_walk_continue(&iter->w); spin_unlock_bh(&iter->tbl->tb6_lock); if (r > 0) { - if (v) - ++*pos; return iter->w.leaf; } else if (r < 0) { fib6_walker_unlink(net, &iter->w); @@ -2517,8 +2519,10 @@ static void *ipv6_route_seq_start(struct seq_file *seq, loff_t *pos) iter->skip = *pos; if (iter->tbl) { + loff_t p = 0; + ipv6_route_seq_setup_walk(iter, net); - return ipv6_route_seq_next(seq, NULL, pos); + return ipv6_route_seq_next(seq, NULL, &p); } else { return NULL; } diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c index 9ec05a1df5e1..44876509d215 100644 --- a/net/ipv6/ip6_gre.c +++ b/net/ipv6/ip6_gre.c @@ -127,6 +127,7 @@ static struct ip6_tnl *ip6gre_tunnel_lookup(struct net_device *dev, gre_proto == htons(ETH_P_ERSPAN2)) ? ARPHRD_ETHER : ARPHRD_IP6GRE; int score, cand_score = 4; + struct net_device *ndev; for_each_ip_tunnel_rcu(t, ign->tunnels_r_l[h0 ^ h1]) { if (!ipv6_addr_equal(local, &t->parms.laddr) || @@ -238,9 +239,9 @@ static struct ip6_tnl *ip6gre_tunnel_lookup(struct net_device *dev, if (t && t->dev->flags & IFF_UP) return t; - dev = ign->fb_tunnel_dev; - if (dev && dev->flags & IFF_UP) - return netdev_priv(dev); + ndev = READ_ONCE(ign->fb_tunnel_dev); + if (ndev && ndev->flags & IFF_UP) + return netdev_priv(ndev); return NULL; } @@ -413,6 +414,8 @@ static void ip6gre_tunnel_uninit(struct net_device *dev) ip6gre_tunnel_unlink_md(ign, t); ip6gre_tunnel_unlink(ign, t); + if (ign->fb_tunnel_dev == dev) + WRITE_ONCE(ign->fb_tunnel_dev, NULL); dst_cache_reset(&t->dst_cache); dev_put(dev); } @@ -1557,17 +1560,18 @@ static void ip6gre_destroy_tunnels(struct net *net, struct list_head *head) static int __net_init ip6gre_init_net(struct net *net) { struct ip6gre_net *ign = net_generic(net, ip6gre_net_id); + struct net_device *ndev; int err; if (!net_has_fallback_tunnels(net)) return 0; - ign->fb_tunnel_dev = alloc_netdev(sizeof(struct ip6_tnl), "ip6gre0", - NET_NAME_UNKNOWN, - ip6gre_tunnel_setup); - if (!ign->fb_tunnel_dev) { + ndev = alloc_netdev(sizeof(struct ip6_tnl), "ip6gre0", + NET_NAME_UNKNOWN, ip6gre_tunnel_setup); + if (!ndev) { err = -ENOMEM; goto err_alloc_dev; } + ign->fb_tunnel_dev = ndev; dev_net_set(ign->fb_tunnel_dev, net); /* FB netdevice is special: we have one, and only one per netns. * Allowing to move it to another netns is clearly unsafe. @@ -1587,7 +1591,7 @@ static int __net_init ip6gre_init_net(struct net *net) return 0; err_reg_dev: - free_netdev(ign->fb_tunnel_dev); + free_netdev(ndev); err_alloc_dev: return err; } diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c index b5dd20c4599b..8dcf7bacc99a 100644 --- a/net/ipv6/ip6_tunnel.c +++ b/net/ipv6/ip6_tunnel.c @@ -860,7 +860,15 @@ int ip6_tnl_rcv(struct ip6_tnl *t, struct sk_buff *skb, struct metadata_dst *tun_dst, bool log_ecn_err) { - return __ip6_tnl_rcv(t, skb, tpi, tun_dst, ip6ip6_dscp_ecn_decapsulate, + int (*dscp_ecn_decapsulate)(const struct ip6_tnl *t, + const struct ipv6hdr *ipv6h, + struct sk_buff *skb); + + dscp_ecn_decapsulate = ip6ip6_dscp_ecn_decapsulate; + if (tpi->proto == htons(ETH_P_IP)) + dscp_ecn_decapsulate = ip4ip6_dscp_ecn_decapsulate; + + return __ip6_tnl_rcv(t, skb, tpi, tun_dst, dscp_ecn_decapsulate, log_ecn_err); } EXPORT_SYMBOL(ip6_tnl_rcv); diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c index 5af97b4f5df3..5352c7e68c42 100644 --- a/net/ipv6/ipv6_sockglue.c +++ b/net/ipv6/ipv6_sockglue.c @@ -205,6 +205,7 @@ static int do_ipv6_setsockopt(struct sock *sk, int level, int optname, fl6_free_socklist(sk); __ipv6_sock_mc_close(sk); + __ipv6_sock_ac_close(sk); /* * Sock is moving from IPv6 to IPv4 (sk_prot), so diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c index eaa4c2cc2fbb..c875c9b6edbe 100644 --- a/net/ipv6/mcast.c +++ b/net/ipv6/mcast.c @@ -2618,6 +2618,7 @@ void ipv6_mc_destroy_dev(struct inet6_dev *idev) idev->mc_list = i->next; write_unlock_bh(&idev->lock); + ip6_mc_clear_src(i); ma_put(i); write_lock_bh(&idev->lock); } diff --git a/net/ipv6/netfilter.c b/net/ipv6/netfilter.c index 409e79b84a83..6d0e942d082d 100644 --- a/net/ipv6/netfilter.c +++ b/net/ipv6/netfilter.c @@ -245,9 +245,6 @@ static const struct nf_ipv6_ops ipv6ops = { .route_input = ip6_route_input, .fragment = ip6_fragment, .reroute = nf_ip6_reroute, -#if IS_MODULE(CONFIG_IPV6) && IS_ENABLED(CONFIG_NF_DEFRAG_IPV6) - .br_defrag = nf_ct_frag6_gather, -#endif #if IS_MODULE(CONFIG_IPV6) .br_fragment = br_ip6_fragment, #endif diff --git a/net/ipv6/netfilter/nf_log_ipv6.c b/net/ipv6/netfilter/nf_log_ipv6.c index 22b80db6d882..5b40258d3a5e 100644 --- a/net/ipv6/netfilter/nf_log_ipv6.c +++ b/net/ipv6/netfilter/nf_log_ipv6.c @@ -297,9 +297,11 @@ static void dump_ipv6_mac_header(struct nf_log_buf *m, switch (dev->type) { case ARPHRD_ETHER: - nf_log_buf_add(m, "MACSRC=%pM MACDST=%pM MACPROTO=%04x ", - eth_hdr(skb)->h_source, eth_hdr(skb)->h_dest, - ntohs(eth_hdr(skb)->h_proto)); + nf_log_buf_add(m, "MACSRC=%pM MACDST=%pM ", + eth_hdr(skb)->h_source, eth_hdr(skb)->h_dest); + nf_log_dump_vlan(m, skb); + nf_log_buf_add(m, "MACPROTO=%04x ", + ntohs(eth_hdr(skb)->h_proto)); return; default: break; diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 3b4af0a8bca6..46df6345bb99 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -431,9 +431,12 @@ void fib6_select_path(const struct net *net, struct fib6_result *res, struct fib6_info *sibling, *next_sibling; struct fib6_info *match = res->f6i; - if ((!match->fib6_nsiblings && !match->nh) || have_oif_match) + if (!match->nh && (!match->fib6_nsiblings || have_oif_match)) goto out; + if (match->nh && have_oif_match && res->nh) + return; + /* We might have already computed the hash for ICMPv6 errors. In such * case it will always be non-zero. Otherwise now is the time to do it. */ @@ -3406,7 +3409,7 @@ static bool fib6_is_reject(u32 flags, struct net_device *dev, int addr_type) if ((flags & RTF_REJECT) || (dev && (dev->flags & IFF_LOOPBACK) && !(addr_type & IPV6_ADDR_LOOPBACK) && - !(flags & RTF_LOCAL))) + !(flags & (RTF_ANYCAST | RTF_LOCAL)))) return true; return false; @@ -3683,14 +3686,14 @@ static struct fib6_info *ip6_route_info_create(struct fib6_config *cfg, rt->fib6_src.plen = cfg->fc_src_len; #endif if (nh) { - if (!nexthop_get(nh)) { - NL_SET_ERR_MSG(extack, "Nexthop has been deleted"); - goto out; - } if (rt->fib6_src.plen) { NL_SET_ERR_MSG(extack, "Nexthops can not be used with source routing"); goto out; } + if (!nexthop_get(nh)) { + NL_SET_ERR_MSG(extack, "Nexthop has been deleted"); + goto out; + } rt->nh = nh; fib6_nh = nexthop_fib6_nh(rt->nh); } else { diff --git a/net/ipv6/sysctl_net_ipv6.c b/net/ipv6/sysctl_net_ipv6.c index ec8fcfc60a27..73842054bfe6 100644 --- a/net/ipv6/sysctl_net_ipv6.c +++ b/net/ipv6/sysctl_net_ipv6.c @@ -21,6 +21,7 @@ #include <net/calipso.h> #endif +static int two = 2; static int flowlabel_reflect_max = 0x7; static int auto_flowlabels_min; static int auto_flowlabels_max = IP6_AUTO_FLOW_LABEL_MAX; @@ -151,7 +152,7 @@ static struct ctl_table ipv6_table_template[] = { .mode = 0644, .proc_handler = proc_rt6_multipath_hash_policy, .extra1 = SYSCTL_ZERO, - .extra2 = SYSCTL_ONE, + .extra2 = &two, }, { .procname = "seg6_flowlabel", diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 9fec580c968e..6762430280f5 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -148,7 +148,7 @@ static struct sock *udp6_lib_lookup2(struct net *net, int dif, int sdif, struct udp_hslot *hslot2, struct sk_buff *skb) { - struct sock *sk, *result; + struct sock *sk, *result, *reuseport_result; int score, badness; u32 hash = 0; @@ -158,17 +158,20 @@ static struct sock *udp6_lib_lookup2(struct net *net, score = compute_score(sk, net, saddr, sport, daddr, hnum, dif, sdif); if (score > badness) { + reuseport_result = NULL; + if (sk->sk_reuseport && sk->sk_state != TCP_ESTABLISHED) { hash = udp6_ehashfn(net, daddr, hnum, saddr, sport); - result = reuseport_select_sock(sk, hash, skb, - sizeof(struct udphdr)); - if (result && !reuseport_has_conns(sk, false)) - return result; + reuseport_result = reuseport_select_sock(sk, hash, skb, + sizeof(struct udphdr)); + if (reuseport_result && !reuseport_has_conns(sk, false)) + return reuseport_result; } - result = sk; + + result = reuseport_result ? : sk; badness = score; } } @@ -643,7 +646,7 @@ static int udpv6_queue_rcv_one_skb(struct sock *sk, struct sk_buff *skb) /* * UDP-Lite specific tests, ignored on UDP sockets (see net/ipv4/udp.c). */ - if ((is_udplite & UDPLITE_RECV_CC) && UDP_SKB_CB(skb)->partial_cov) { + if ((up->pcflag & UDPLITE_RECV_CC) && UDP_SKB_CB(skb)->partial_cov) { if (up->pcrlen == 0) { /* full coverage was set */ net_dbg_ratelimited("UDPLITE6: partial coverage %d while full coverage %d requested\n", diff --git a/net/key/af_key.c b/net/key/af_key.c index b67ed3a8486c..a915bc86620a 100644 --- a/net/key/af_key.c +++ b/net/key/af_key.c @@ -1849,6 +1849,13 @@ static int pfkey_dump(struct sock *sk, struct sk_buff *skb, const struct sadb_ms if (ext_hdrs[SADB_X_EXT_FILTER - 1]) { struct sadb_x_filter *xfilter = ext_hdrs[SADB_X_EXT_FILTER - 1]; + if ((xfilter->sadb_x_filter_splen >= + (sizeof(xfrm_address_t) << 3)) || + (xfilter->sadb_x_filter_dplen >= + (sizeof(xfrm_address_t) << 3))) { + mutex_unlock(&pfk->dump_lock); + return -EINVAL; + } filter = kmalloc(sizeof(*filter), GFP_KERNEL); if (filter == NULL) { mutex_unlock(&pfk->dump_lock); @@ -2400,7 +2407,7 @@ static int pfkey_spddelete(struct sock *sk, struct sk_buff *skb, const struct sa return err; } - xp = xfrm_policy_bysel_ctx(net, DUMMY_MARK, 0, XFRM_POLICY_TYPE_MAIN, + xp = xfrm_policy_bysel_ctx(net, &dummy_mark, 0, XFRM_POLICY_TYPE_MAIN, pol->sadb_x_policy_dir - 1, &sel, pol_ctx, 1, &err); security_xfrm_policy_free(pol_ctx); @@ -2651,7 +2658,7 @@ static int pfkey_spdget(struct sock *sk, struct sk_buff *skb, const struct sadb_ return -EINVAL; delete = (hdr->sadb_msg_type == SADB_X_SPDDELETE2); - xp = xfrm_policy_byid(net, DUMMY_MARK, 0, XFRM_POLICY_TYPE_MAIN, + xp = xfrm_policy_byid(net, &dummy_mark, 0, XFRM_POLICY_TYPE_MAIN, dir, pol->sadb_x_policy_id, delete, &err); if (xp == NULL) return -ENOENT; diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c index 6dc3bfa12b1e..95805a6331be 100644 --- a/net/l2tp/l2tp_core.c +++ b/net/l2tp/l2tp_core.c @@ -1030,6 +1030,7 @@ static void l2tp_xmit_core(struct l2tp_session *session, struct sk_buff *skb, /* Queue the packet to IP for output */ skb->ignore_df = 1; + skb_dst_drop(skb); #if IS_ENABLED(CONFIG_IPV6) if (l2tp_sk_is_v6(tunnel->sock)) error = inet6_csk_xmit(tunnel->sock, skb, NULL); @@ -1101,10 +1102,6 @@ int l2tp_xmit_skb(struct l2tp_session *session, struct sk_buff *skb, int hdr_len goto out_unlock; } - /* Get routing info from the tunnel socket */ - skb_dst_drop(skb); - skb_dst_set(skb, sk_dst_check(sk, 0)); - inet = inet_sk(sk); fl = &inet->cork.fl; switch (tunnel->encap) { diff --git a/net/llc/af_llc.c b/net/llc/af_llc.c index c74f44dfaa22..fa0f3c1543ba 100644 --- a/net/llc/af_llc.c +++ b/net/llc/af_llc.c @@ -273,6 +273,10 @@ static int llc_ui_autobind(struct socket *sock, struct sockaddr_llc *addr) if (!sock_flag(sk, SOCK_ZAPPED)) goto out; + if (!addr->sllc_arphrd) + addr->sllc_arphrd = ARPHRD_ETHER; + if (addr->sllc_arphrd != ARPHRD_ETHER) + goto out; rc = -ENODEV; if (sk->sk_bound_dev_if) { llc->dev = dev_get_by_index(&init_net, sk->sk_bound_dev_if); @@ -328,7 +332,9 @@ static int llc_ui_bind(struct socket *sock, struct sockaddr *uaddr, int addrlen) if (unlikely(!sock_flag(sk, SOCK_ZAPPED) || addrlen != sizeof(*addr))) goto out; rc = -EAFNOSUPPORT; - if (unlikely(addr->sllc_family != AF_LLC)) + if (!addr->sllc_arphrd) + addr->sllc_arphrd = ARPHRD_ETHER; + if (unlikely(addr->sllc_family != AF_LLC || addr->sllc_arphrd != ARPHRD_ETHER)) goto out; dprintk("%s: binding %02X\n", __func__, addr->sllc_sap); rc = -ENODEV; @@ -336,8 +342,6 @@ static int llc_ui_bind(struct socket *sock, struct sockaddr *uaddr, int addrlen) if (sk->sk_bound_dev_if) { llc->dev = dev_get_by_index_rcu(&init_net, sk->sk_bound_dev_if); if (llc->dev) { - if (!addr->sllc_arphrd) - addr->sllc_arphrd = llc->dev->type; if (is_zero_ether_addr(addr->sllc_mac)) memcpy(addr->sllc_mac, llc->dev->dev_addr, IFHWADDRLEN); @@ -780,7 +784,7 @@ static int llc_ui_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, } /* Well, if we have backlog, try to process it now yet. */ - if (copied >= target && !sk->sk_backlog.tail) + if (copied >= target && !READ_ONCE(sk->sk_backlog.tail)) break; if (copied) { diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c index 0daaf7e37a21..fa293feef935 100644 --- a/net/mac80211/cfg.c +++ b/net/mac80211/cfg.c @@ -698,7 +698,8 @@ void sta_set_rate_info_tx(struct sta_info *sta, u16 brate; sband = ieee80211_get_sband(sta->sdata); - if (sband) { + WARN_ON_ONCE(sband && !sband->bitrates); + if (sband && sband->bitrates) { brate = sband->bitrates[rate->idx].bitrate; rinfo->legacy = DIV_ROUND_UP(brate, 1 << shift); } @@ -2140,6 +2141,7 @@ static int ieee80211_leave_mesh(struct wiphy *wiphy, struct net_device *dev) ieee80211_stop_mesh(sdata); mutex_lock(&sdata->local->mtx); ieee80211_vif_release_channel(sdata); + kfree(sdata->u.mesh.ie); mutex_unlock(&sdata->local->mtx); return 0; diff --git a/net/mac80211/mesh_pathtbl.c b/net/mac80211/mesh_pathtbl.c index 117519bf33d6..aca608ae313f 100644 --- a/net/mac80211/mesh_pathtbl.c +++ b/net/mac80211/mesh_pathtbl.c @@ -521,6 +521,7 @@ static void mesh_path_free_rcu(struct mesh_table *tbl, del_timer_sync(&mpath->timer); atomic_dec(&sdata->u.mesh.mpaths); atomic_dec(&tbl->entries); + mesh_path_flush_pending(mpath); kfree_rcu(mpath, rcu); } diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c index 69429c8df7b3..3ab85e1e38d8 100644 --- a/net/mac80211/rx.c +++ b/net/mac80211/rx.c @@ -419,7 +419,8 @@ ieee80211_add_rx_radiotap_header(struct ieee80211_local *local, else if (status->bw == RATE_INFO_BW_5) channel_flags |= IEEE80211_CHAN_QUARTER; - if (status->band == NL80211_BAND_5GHZ) + if (status->band == NL80211_BAND_5GHZ || + status->band == NL80211_BAND_6GHZ) channel_flags |= IEEE80211_CHAN_OFDM | IEEE80211_CHAN_5GHZ; else if (status->encoding != RX_ENC_LEGACY) channel_flags |= IEEE80211_CHAN_DYN | IEEE80211_CHAN_2GHZ; @@ -2305,6 +2306,7 @@ static int ieee80211_802_1x_port_control(struct ieee80211_rx_data *rx) static int ieee80211_drop_unencrypted(struct ieee80211_rx_data *rx, __le16 fc) { + struct ieee80211_hdr *hdr = (void *)rx->skb->data; struct sk_buff *skb = rx->skb; struct ieee80211_rx_status *status = IEEE80211_SKB_RXCB(skb); @@ -2315,6 +2317,31 @@ static int ieee80211_drop_unencrypted(struct ieee80211_rx_data *rx, __le16 fc) if (status->flag & RX_FLAG_DECRYPTED) return 0; + /* check mesh EAPOL frames first */ + if (unlikely(rx->sta && ieee80211_vif_is_mesh(&rx->sdata->vif) && + ieee80211_is_data(fc))) { + struct ieee80211s_hdr *mesh_hdr; + u16 hdr_len = ieee80211_hdrlen(fc); + u16 ethertype_offset; + __be16 ethertype; + + if (!ether_addr_equal(hdr->addr1, rx->sdata->vif.addr)) + goto drop_check; + + /* make sure fixed part of mesh header is there, also checks skb len */ + if (!pskb_may_pull(rx->skb, hdr_len + 6)) + goto drop_check; + + mesh_hdr = (struct ieee80211s_hdr *)(skb->data + hdr_len); + ethertype_offset = hdr_len + ieee80211_get_mesh_hdrlen(mesh_hdr) + + sizeof(rfc1042_header); + + if (skb_copy_bits(rx->skb, ethertype_offset, ðertype, 2) == 0 && + ethertype == rx->sdata->control_port_protocol) + return 0; + } + +drop_check: /* Drop unencrypted frames if key is set. */ if (unlikely(!ieee80211_has_protected(fc) && !ieee80211_is_any_nullfunc(fc) && diff --git a/net/mac80211/sta_info.c b/net/mac80211/sta_info.c index b1669f024470..4f14d8a06915 100644 --- a/net/mac80211/sta_info.c +++ b/net/mac80211/sta_info.c @@ -1033,7 +1033,7 @@ static void __sta_info_destroy_part2(struct sta_info *sta) might_sleep(); lockdep_assert_held(&local->sta_mtx); - while (sta->sta_state == IEEE80211_STA_AUTHORIZED) { + if (sta->sta_state == IEEE80211_STA_AUTHORIZED) { ret = sta_info_move_state(sta, IEEE80211_STA_ASSOC); WARN_ON_ONCE(ret); } @@ -2083,6 +2083,10 @@ static void sta_stats_decode_rate(struct ieee80211_local *local, u32 rate, int rate_idx = STA_STATS_GET(LEGACY_IDX, rate); sband = local->hw.wiphy->bands[band]; + + if (WARN_ON_ONCE(!sband->bitrates)) + break; + brate = sband->bitrates[rate_idx].bitrate; if (rinfo->bw == RATE_INFO_BW_5) shift = 2; diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c index 30201aeb426c..f029e75ec815 100644 --- a/net/mac80211/tx.c +++ b/net/mac80211/tx.c @@ -3913,6 +3913,9 @@ void __ieee80211_subif_start_xmit(struct sk_buff *skb, skb->prev = NULL; skb->next = NULL; + if (skb->protocol == sdata->control_port_protocol) + ctrl_flags |= IEEE80211_TX_CTRL_SKIP_MPATH_LOOKUP; + skb = ieee80211_build_hdr(sdata, skb, info_flags, sta, ctrl_flags); if (IS_ERR(skb)) @@ -5096,7 +5099,8 @@ int ieee80211_tx_control_port(struct wiphy *wiphy, struct net_device *dev, return -EINVAL; if (proto == sdata->control_port_protocol) - ctrl_flags |= IEEE80211_TX_CTRL_PORT_CTRL_PROTO; + ctrl_flags |= IEEE80211_TX_CTRL_PORT_CTRL_PROTO | + IEEE80211_TX_CTRL_SKIP_MPATH_LOOKUP; if (unencrypted) flags = IEEE80211_TX_INTFL_DONT_ENCRYPT; diff --git a/net/mac80211/vht.c b/net/mac80211/vht.c index ccdcb9ad9ac7..aabc63dadf17 100644 --- a/net/mac80211/vht.c +++ b/net/mac80211/vht.c @@ -168,10 +168,7 @@ ieee80211_vht_cap_ie_to_sta_vht_cap(struct ieee80211_sub_if_data *sdata, /* take some capabilities as-is */ cap_info = le32_to_cpu(vht_cap_ie->vht_cap_info); vht_cap->cap = cap_info; - vht_cap->cap &= IEEE80211_VHT_CAP_MAX_MPDU_LENGTH_3895 | - IEEE80211_VHT_CAP_MAX_MPDU_LENGTH_7991 | - IEEE80211_VHT_CAP_MAX_MPDU_LENGTH_11454 | - IEEE80211_VHT_CAP_RXLDPC | + vht_cap->cap &= IEEE80211_VHT_CAP_RXLDPC | IEEE80211_VHT_CAP_VHT_TXOP_PS | IEEE80211_VHT_CAP_HTC_VHT | IEEE80211_VHT_CAP_MAX_A_MPDU_LENGTH_EXPONENT_MASK | @@ -180,6 +177,9 @@ ieee80211_vht_cap_ie_to_sta_vht_cap(struct ieee80211_sub_if_data *sdata, IEEE80211_VHT_CAP_RX_ANTENNA_PATTERN | IEEE80211_VHT_CAP_TX_ANTENNA_PATTERN; + vht_cap->cap |= min_t(u32, cap_info & IEEE80211_VHT_CAP_MAX_MPDU_MASK, + own_cap.cap & IEEE80211_VHT_CAP_MAX_MPDU_MASK); + /* and some based on our own capabilities */ switch (own_cap.cap & IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_MASK) { case IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_160MHZ: diff --git a/net/mac802154/tx.c b/net/mac802154/tx.c index ab52811523e9..c829e4a75325 100644 --- a/net/mac802154/tx.c +++ b/net/mac802154/tx.c @@ -34,11 +34,11 @@ void ieee802154_xmit_worker(struct work_struct *work) if (res) goto err_tx; - ieee802154_xmit_complete(&local->hw, skb, false); - dev->stats.tx_packets++; dev->stats.tx_bytes += skb->len; + ieee802154_xmit_complete(&local->hw, skb, false); + return; err_tx: @@ -78,6 +78,8 @@ ieee802154_tx(struct ieee802154_local *local, struct sk_buff *skb) /* async is priority, otherwise sync is fallback */ if (local->ops->xmit_async) { + unsigned int len = skb->len; + ret = drv_xmit_async(local, skb); if (ret) { ieee802154_wake_queue(&local->hw); @@ -85,7 +87,7 @@ ieee802154_tx(struct ieee802154_local *local, struct sk_buff *skb) } dev->stats.tx_packets++; - dev->stats.tx_bytes += skb->len; + dev->stats.tx_bytes += len; } else { local->tx_skb = skb; queue_work(local->workqueue, &local->tx_work); diff --git a/net/netfilter/ipset/ip_set_bitmap_ip.c b/net/netfilter/ipset/ip_set_bitmap_ip.c index d934384f31ad..6e3cf4d19ce8 100644 --- a/net/netfilter/ipset/ip_set_bitmap_ip.c +++ b/net/netfilter/ipset/ip_set_bitmap_ip.c @@ -314,7 +314,7 @@ bitmap_ip_create(struct net *net, struct ip_set *set, struct nlattr *tb[], set->variant = &bitmap_ip; if (!init_map_ip(set, map, first_ip, last_ip, elements, hosts, netmask)) { - kfree(map); + ip_set_free(map); return -ENOMEM; } if (tb[IPSET_ATTR_TIMEOUT]) { diff --git a/net/netfilter/ipset/ip_set_bitmap_ipmac.c b/net/netfilter/ipset/ip_set_bitmap_ipmac.c index e8532783b43a..ae7cdc0d0f29 100644 --- a/net/netfilter/ipset/ip_set_bitmap_ipmac.c +++ b/net/netfilter/ipset/ip_set_bitmap_ipmac.c @@ -363,7 +363,7 @@ bitmap_ipmac_create(struct net *net, struct ip_set *set, struct nlattr *tb[], map->memsize = BITS_TO_LONGS(elements) * sizeof(unsigned long); set->variant = &bitmap_ipmac; if (!init_map_ipmac(set, map, first_ip, last_ip, elements)) { - kfree(map); + ip_set_free(map); return -ENOMEM; } if (tb[IPSET_ATTR_TIMEOUT]) { diff --git a/net/netfilter/ipset/ip_set_bitmap_port.c b/net/netfilter/ipset/ip_set_bitmap_port.c index e3ac914fff1a..d4a14750f5c4 100644 --- a/net/netfilter/ipset/ip_set_bitmap_port.c +++ b/net/netfilter/ipset/ip_set_bitmap_port.c @@ -247,7 +247,7 @@ bitmap_port_create(struct net *net, struct ip_set *set, struct nlattr *tb[], map->memsize = BITS_TO_LONGS(elements) * sizeof(unsigned long); set->variant = &bitmap_port; if (!init_map_port(set, map, first_port, last_port)) { - kfree(map); + ip_set_free(map); return -ENOMEM; } if (tb[IPSET_ATTR_TIMEOUT]) { diff --git a/net/netfilter/ipset/ip_set_core.c b/net/netfilter/ipset/ip_set_core.c index 75da200aa5d8..133a3f1b6f56 100644 --- a/net/netfilter/ipset/ip_set_core.c +++ b/net/netfilter/ipset/ip_set_core.c @@ -382,6 +382,8 @@ ip_set_elem_len(struct ip_set *set, struct nlattr *tb[], size_t len, for (id = 0; id < IPSET_EXT_ID_MAX; id++) { if (!add_extension(id, cadt_flags, tb)) continue; + if (align < ip_set_extensions[id].align) + align = ip_set_extensions[id].align; len = ALIGN(len, ip_set_extensions[id].align); set->offset[id] = len; set->extensions |= ip_set_extensions[id].type; diff --git a/net/netfilter/ipset/ip_set_hash_gen.h b/net/netfilter/ipset/ip_set_hash_gen.h index 2389c9f89e48..a7a982a3e676 100644 --- a/net/netfilter/ipset/ip_set_hash_gen.h +++ b/net/netfilter/ipset/ip_set_hash_gen.h @@ -682,7 +682,7 @@ retry: } t->hregion = ip_set_alloc(ahash_sizeof_regions(htable_bits)); if (!t->hregion) { - kfree(t); + ip_set_free(t); ret = -ENOMEM; goto out; } @@ -1533,7 +1533,7 @@ IPSET_TOKEN(HTYPE, _create)(struct net *net, struct ip_set *set, } t->hregion = ip_set_alloc(ahash_sizeof_regions(hbits)); if (!t->hregion) { - kfree(t); + ip_set_free(t); kfree(h); return -ENOMEM; } diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c index 8b80ab794a92..64a05906cc0e 100644 --- a/net/netfilter/ipvs/ip_vs_core.c +++ b/net/netfilter/ipvs/ip_vs_core.c @@ -2061,14 +2061,14 @@ ip_vs_in(struct netns_ipvs *ipvs, unsigned int hooknum, struct sk_buff *skb, int conn_reuse_mode = sysctl_conn_reuse_mode(ipvs); if (conn_reuse_mode && !iph.fragoffs && is_new_conn(skb, &iph) && cp) { - bool uses_ct = false, resched = false; + bool old_ct = false, resched = false; if (unlikely(sysctl_expire_nodest_conn(ipvs)) && cp->dest && unlikely(!atomic_read(&cp->dest->weight))) { resched = true; - uses_ct = ip_vs_conn_uses_conntrack(cp, skb); + old_ct = ip_vs_conn_uses_old_conntrack(cp, skb); } else if (is_new_conn_expected(cp, conn_reuse_mode)) { - uses_ct = ip_vs_conn_uses_conntrack(cp, skb); + old_ct = ip_vs_conn_uses_old_conntrack(cp, skb); if (!atomic_read(&cp->n_control)) { resched = true; } else { @@ -2076,15 +2076,17 @@ ip_vs_in(struct netns_ipvs *ipvs, unsigned int hooknum, struct sk_buff *skb, int * that uses conntrack while it is still * referenced by controlled connection(s). */ - resched = !uses_ct; + resched = !old_ct; } } if (resched) { + if (!old_ct) + cp->flags &= ~IP_VS_CONN_F_NFCT; if (!atomic_read(&cp->n_control)) ip_vs_conn_expire_now(cp); __ip_vs_conn_put(cp); - if (uses_ct) + if (old_ct) return NF_DROP; cp = NULL; } diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c index 3cccc88ef817..99168af0c28d 100644 --- a/net/netfilter/ipvs/ip_vs_ctl.c +++ b/net/netfilter/ipvs/ip_vs_ctl.c @@ -2465,6 +2465,10 @@ do_ip_vs_set_ctl(struct sock *sk, int cmd, void __user *user, unsigned int len) /* Set timeout values for (tcp tcpfin udp) */ ret = ip_vs_set_timeout(ipvs, (struct ip_vs_timeout_user *)arg); goto out_unlock; + } else if (!len) { + /* No more commands with len == 0 below */ + ret = -EINVAL; + goto out_unlock; } usvc_compat = (struct ip_vs_service_user *)arg; @@ -2541,9 +2545,6 @@ do_ip_vs_set_ctl(struct sock *sk, int cmd, void __user *user, unsigned int len) break; case IP_VS_SO_SET_DELDEST: ret = ip_vs_del_dest(svc, &udest); - break; - default: - ret = -EINVAL; } out_unlock: diff --git a/net/netfilter/ipvs/ip_vs_sync.c b/net/netfilter/ipvs/ip_vs_sync.c index 8dc892a9dc91..0c1bc654245c 100644 --- a/net/netfilter/ipvs/ip_vs_sync.c +++ b/net/netfilter/ipvs/ip_vs_sync.c @@ -1717,6 +1717,8 @@ static int sync_thread_backup(void *data) { struct ip_vs_sync_thread_data *tinfo = data; struct netns_ipvs *ipvs = tinfo->ipvs; + struct sock *sk = tinfo->sock->sk; + struct udp_sock *up = udp_sk(sk); int len; pr_info("sync thread started: state = BACKUP, mcast_ifn = %s, " @@ -1724,12 +1726,14 @@ static int sync_thread_backup(void *data) ipvs->bcfg.mcast_ifn, ipvs->bcfg.syncid, tinfo->id); while (!kthread_should_stop()) { - wait_event_interruptible(*sk_sleep(tinfo->sock->sk), - !skb_queue_empty(&tinfo->sock->sk->sk_receive_queue) - || kthread_should_stop()); + wait_event_interruptible(*sk_sleep(sk), + !skb_queue_empty_lockless(&sk->sk_receive_queue) || + !skb_queue_empty_lockless(&up->reader_queue) || + kthread_should_stop()); /* do we have data now? */ - while (!skb_queue_empty(&(tinfo->sock->sk->sk_receive_queue))) { + while (!skb_queue_empty_lockless(&sk->sk_receive_queue) || + !skb_queue_empty_lockless(&up->reader_queue)) { len = ip_vs_receive(tinfo->sock, tinfo->buf, ipvs->bcfg.sync_maxlen); if (len <= 0) { diff --git a/net/netfilter/ipvs/ip_vs_xmit.c b/net/netfilter/ipvs/ip_vs_xmit.c index c62a131a6094..cefc39878b1a 100644 --- a/net/netfilter/ipvs/ip_vs_xmit.c +++ b/net/netfilter/ipvs/ip_vs_xmit.c @@ -615,6 +615,8 @@ static inline int ip_vs_tunnel_xmit_prepare(struct sk_buff *skb, if (ret == NF_ACCEPT) { nf_reset_ct(skb); skb_forward_csum(skb); + if (skb->dev) + skb->tstamp = 0; } return ret; } @@ -655,6 +657,8 @@ static inline int ip_vs_nat_send_or_cont(int pf, struct sk_buff *skb, if (!local) { skb_forward_csum(skb); + if (skb->dev) + skb->tstamp = 0; NF_HOOK(pf, NF_INET_LOCAL_OUT, cp->ipvs->net, NULL, skb, NULL, skb_dst(skb)->dev, dst_output); } else @@ -675,6 +679,8 @@ static inline int ip_vs_send_or_cont(int pf, struct sk_buff *skb, if (!local) { ip_vs_drop_early_demux_sk(skb); skb_forward_csum(skb); + if (skb->dev) + skb->tstamp = 0; NF_HOOK(pf, NF_INET_LOCAL_OUT, cp->ipvs->net, NULL, skb, NULL, skb_dst(skb)->dev, dst_output); } else diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index 48db4aec02de..200cdad3ff3a 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -2012,6 +2012,8 @@ static int nf_conntrack_update(struct net *net, struct sk_buff *skb) err = __nf_conntrack_update(net, skb, ct, ctinfo); if (err < 0) return err; + + ct = nf_ct_get(skb, &ctinfo); } return nf_confirm_cthelper(skb, ct, ctinfo); diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c index aa8adf930b3c..b7f0d52e5f1b 100644 --- a/net/netfilter/nf_conntrack_netlink.c +++ b/net/netfilter/nf_conntrack_netlink.c @@ -1141,6 +1141,8 @@ ctnetlink_parse_tuple(const struct nlattr * const cda[], if (!tb[CTA_TUPLE_IP]) return -EINVAL; + if (l3num != NFPROTO_IPV4 && l3num != NFPROTO_IPV6) + return -EOPNOTSUPP; tuple->src.l3num = l3num; err = ctnetlink_parse_tuple_ip(tb[CTA_TUPLE_IP], tuple); diff --git a/net/netfilter/nf_conntrack_proto.c b/net/netfilter/nf_conntrack_proto.c index a0560d175a7f..aaf4293ddd45 100644 --- a/net/netfilter/nf_conntrack_proto.c +++ b/net/netfilter/nf_conntrack_proto.c @@ -565,6 +565,7 @@ static int nf_ct_netns_inet_get(struct net *net) int err; err = nf_ct_netns_do_get(net, NFPROTO_IPV4); +#if IS_ENABLED(CONFIG_IPV6) if (err < 0) goto err1; err = nf_ct_netns_do_get(net, NFPROTO_IPV6); @@ -575,6 +576,7 @@ static int nf_ct_netns_inet_get(struct net *net) err2: nf_ct_netns_put(net, NFPROTO_IPV4); err1: +#endif return err; } diff --git a/net/netfilter/nf_conntrack_proto_sctp.c b/net/netfilter/nf_conntrack_proto_sctp.c index 4f897b14b606..810cca24b399 100644 --- a/net/netfilter/nf_conntrack_proto_sctp.c +++ b/net/netfilter/nf_conntrack_proto_sctp.c @@ -62,6 +62,8 @@ static const unsigned int sctp_timeouts[SCTP_CONNTRACK_MAX] = { [SCTP_CONNTRACK_HEARTBEAT_ACKED] = 210 SECS, }; +#define SCTP_FLAG_HEARTBEAT_VTAG_FAILED 1 + #define sNO SCTP_CONNTRACK_NONE #define sCL SCTP_CONNTRACK_CLOSED #define sCW SCTP_CONNTRACK_COOKIE_WAIT @@ -369,6 +371,7 @@ int nf_conntrack_sctp_packet(struct nf_conn *ct, u_int32_t offset, count; unsigned int *timeouts; unsigned long map[256 / sizeof(unsigned long)] = { 0 }; + bool ignore = false; if (sctp_error(skb, dataoff, state)) return -NF_ACCEPT; @@ -427,15 +430,39 @@ int nf_conntrack_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) { + } else if (sch->type == SCTP_CID_HEARTBEAT) { + if (ct->proto.sctp.vtag[dir] == 0) { + pr_debug("Setting %d vtag %x for dir %d\n", sch->type, sh->vtag, dir); + ct->proto.sctp.vtag[dir] = sh->vtag; + } else if (sh->vtag != ct->proto.sctp.vtag[dir]) { + if (test_bit(SCTP_CID_DATA, map) || ignore) + goto out_unlock; + + ct->proto.sctp.flags |= SCTP_FLAG_HEARTBEAT_VTAG_FAILED; + ct->proto.sctp.last_dir = dir; + ignore = true; + continue; + } else if (ct->proto.sctp.flags & SCTP_FLAG_HEARTBEAT_VTAG_FAILED) { + ct->proto.sctp.flags &= ~SCTP_FLAG_HEARTBEAT_VTAG_FAILED; + } + } else if (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; + if (test_bit(SCTP_CID_DATA, map) || ignore) + goto out_unlock; + + if ((ct->proto.sctp.flags & SCTP_FLAG_HEARTBEAT_VTAG_FAILED) == 0 || + ct->proto.sctp.last_dir == dir) + goto out_unlock; + + ct->proto.sctp.flags &= ~SCTP_FLAG_HEARTBEAT_VTAG_FAILED; + ct->proto.sctp.vtag[dir] = sh->vtag; + ct->proto.sctp.vtag[!dir] = 0; + } else if (ct->proto.sctp.flags & SCTP_FLAG_HEARTBEAT_VTAG_FAILED) { + ct->proto.sctp.flags &= ~SCTP_FLAG_HEARTBEAT_VTAG_FAILED; } } @@ -470,6 +497,10 @@ int nf_conntrack_sctp_packet(struct nf_conn *ct, } spin_unlock_bh(&ct->lock); + /* allow but do not refresh timeout */ + if (ignore) + return NF_ACCEPT; + timeouts = nf_ct_timeout_lookup(ct); if (!timeouts) timeouts = nf_sctp_pernet(nf_ct_net(ct))->timeouts; diff --git a/net/netfilter/nf_conntrack_proto_tcp.c b/net/netfilter/nf_conntrack_proto_tcp.c index 1926fd56df56..848b137151c2 100644 --- a/net/netfilter/nf_conntrack_proto_tcp.c +++ b/net/netfilter/nf_conntrack_proto_tcp.c @@ -541,13 +541,20 @@ static bool tcp_in_window(const struct nf_conn *ct, swin = win << sender->td_scale; sender->td_maxwin = (swin == 0 ? 1 : swin); sender->td_maxend = end + sender->td_maxwin; - /* - * We haven't seen traffic in the other direction yet - * but we have to tweak window tracking to pass III - * and IV until that happens. - */ - if (receiver->td_maxwin == 0) + if (receiver->td_maxwin == 0) { + /* We haven't seen traffic in the other + * direction yet but we have to tweak window + * tracking to pass III and IV until that + * happens. + */ receiver->td_end = receiver->td_maxend = sack; + } else if (sack == receiver->td_end + 1) { + /* Likely a reply to a keepalive. + * Needed for III. + */ + receiver->td_end++; + } + } } else if (((state->state == TCP_CONNTRACK_SYN_SENT && dir == IP_CT_DIR_ORIGINAL) diff --git a/net/netfilter/nf_dup_netdev.c b/net/netfilter/nf_dup_netdev.c index f108a76925dd..ec6e7d686016 100644 --- a/net/netfilter/nf_dup_netdev.c +++ b/net/netfilter/nf_dup_netdev.c @@ -19,6 +19,7 @@ static void nf_do_netdev_egress(struct sk_buff *skb, struct net_device *dev) skb_push(skb, skb->mac_len); skb->dev = dev; + skb->tstamp = 0; dev_queue_xmit(skb); } diff --git a/net/netfilter/nf_log_common.c b/net/netfilter/nf_log_common.c index ae5628ddbe6d..fd7c5f0f5c25 100644 --- a/net/netfilter/nf_log_common.c +++ b/net/netfilter/nf_log_common.c @@ -171,6 +171,18 @@ nf_log_dump_packet_common(struct nf_log_buf *m, u_int8_t pf, } EXPORT_SYMBOL_GPL(nf_log_dump_packet_common); +void nf_log_dump_vlan(struct nf_log_buf *m, const struct sk_buff *skb) +{ + u16 vid; + + if (!skb_vlan_tag_present(skb)) + return; + + vid = skb_vlan_tag_get(skb); + nf_log_buf_add(m, "VPROTO=%04x VID=%u ", ntohs(skb->vlan_proto), vid); +} +EXPORT_SYMBOL_GPL(nf_log_dump_vlan); + /* bridge and netdev logging families share this code. */ void nf_log_l2packet(struct net *net, u_int8_t pf, __be16 protocol, diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index f7129232c825..5a77b7a17722 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -254,7 +254,7 @@ static void nft_rule_expr_activate(const struct nft_ctx *ctx, struct nft_expr *expr; expr = nft_expr_first(rule); - while (expr != nft_expr_last(rule) && expr->ops) { + while (nft_expr_more(rule, expr)) { if (expr->ops->activate) expr->ops->activate(ctx, expr); @@ -269,7 +269,7 @@ static void nft_rule_expr_deactivate(const struct nft_ctx *ctx, struct nft_expr *expr; expr = nft_expr_first(rule); - while (expr != nft_expr_last(rule) && expr->ops) { + while (nft_expr_more(rule, expr)) { if (expr->ops->deactivate) expr->ops->deactivate(ctx, expr, phase); @@ -456,7 +456,8 @@ static struct nft_table *nft_table_lookup(const struct net *net, if (nla == NULL) return ERR_PTR(-EINVAL); - list_for_each_entry_rcu(table, &net->nft.tables, list) { + list_for_each_entry_rcu(table, &net->nft.tables, list, + lockdep_is_held(&net->nft.commit_mutex)) { if (!nla_strcmp(nla, table->name) && table->family == family && nft_active_genmask(table, genmask)) @@ -744,11 +745,11 @@ static int nf_tables_gettable(struct net *net, struct sock *nlsk, nlh->nlmsg_seq, NFT_MSG_NEWTABLE, 0, family, table); if (err < 0) - goto err; + goto err_fill_table_info; - return nlmsg_unicast(nlsk, skb2, NETLINK_CB(skb).portid); + return nfnetlink_unicast(skb2, net, NETLINK_CB(skb).portid); -err: +err_fill_table_info: kfree_skb(skb2); return err; } @@ -1443,11 +1444,11 @@ static int nf_tables_getchain(struct net *net, struct sock *nlsk, nlh->nlmsg_seq, NFT_MSG_NEWCHAIN, 0, family, table, chain); if (err < 0) - goto err; + goto err_fill_chain_info; - return nlmsg_unicast(nlsk, skb2, NETLINK_CB(skb).portid); + return nfnetlink_unicast(skb2, net, NETLINK_CB(skb).portid); -err: +err_fill_chain_info: kfree_skb(skb2); return err; } @@ -2622,11 +2623,11 @@ static int nf_tables_getrule(struct net *net, struct sock *nlsk, nlh->nlmsg_seq, NFT_MSG_NEWRULE, 0, family, table, chain, rule, NULL); if (err < 0) - goto err; + goto err_fill_rule_info; - return nlmsg_unicast(nlsk, skb2, NETLINK_CB(skb).portid); + return nfnetlink_unicast(skb2, net, NETLINK_CB(skb).portid); -err: +err_fill_rule_info: kfree_skb(skb2); return err; } @@ -2641,7 +2642,7 @@ static void nf_tables_rule_destroy(const struct nft_ctx *ctx, * is called on error from nf_tables_newrule(). */ expr = nft_expr_first(rule); - while (expr != nft_expr_last(rule) && expr->ops) { + while (nft_expr_more(rule, expr)) { next = nft_expr_next(expr); nf_tables_expr_destroy(ctx, expr); expr = next; @@ -3353,7 +3354,8 @@ static int nf_tables_fill_set(struct sk_buff *skb, const struct nft_ctx *ctx, goto nla_put_failure; } - if (nla_put(skb, NFTA_SET_USERDATA, set->udlen, set->udata)) + if (set->udata && + nla_put(skb, NFTA_SET_USERDATA, set->udlen, set->udata)) goto nla_put_failure; desc = nla_nest_start_noflag(skb, NFTA_SET_DESC); @@ -3525,11 +3527,11 @@ static int nf_tables_getset(struct net *net, struct sock *nlsk, err = nf_tables_fill_set(skb2, &ctx, set, NFT_MSG_NEWSET, 0); if (err < 0) - goto err; + goto err_fill_set_info; - return nlmsg_unicast(nlsk, skb2, NETLINK_CB(skb).portid); + return nfnetlink_unicast(skb2, net, NETLINK_CB(skb).portid); -err: +err_fill_set_info: kfree_skb(skb2); return err; } @@ -4304,24 +4306,18 @@ static int nft_get_set_elem(struct nft_ctx *ctx, struct nft_set *set, err = -ENOMEM; skb = nlmsg_new(NLMSG_GOODSIZE, GFP_ATOMIC); if (skb == NULL) - goto err1; + return err; err = nf_tables_fill_setelem_info(skb, ctx, ctx->seq, ctx->portid, NFT_MSG_NEWSETELEM, 0, set, &elem); if (err < 0) - goto err2; + goto err_fill_setelem; - err = nfnetlink_unicast(skb, ctx->net, ctx->portid, MSG_DONTWAIT); - /* This avoids a loop in nfnetlink. */ - if (err < 0) - goto err1; + return nfnetlink_unicast(skb, ctx->net, ctx->portid); - return 0; -err2: +err_fill_setelem: kfree_skb(skb); -err1: - /* this avoids a loop in nfnetlink. */ - return err == -EAGAIN ? -ENOBUFS : err; + return err; } /* called with rcu_read_lock held */ @@ -5498,10 +5494,11 @@ static int nf_tables_getobj(struct net *net, struct sock *nlsk, nlh->nlmsg_seq, NFT_MSG_NEWOBJ, 0, family, table, obj, reset); if (err < 0) - goto err; + goto err_fill_obj_info; - return nlmsg_unicast(nlsk, skb2, NETLINK_CB(skb).portid); -err: + return nfnetlink_unicast(skb2, net, NETLINK_CB(skb).portid); + +err_fill_obj_info: kfree_skb(skb2); return err; } @@ -6173,10 +6170,11 @@ static int nf_tables_getflowtable(struct net *net, struct sock *nlsk, NFT_MSG_NEWFLOWTABLE, 0, family, flowtable); if (err < 0) - goto err; + goto err_fill_flowtable_info; - return nlmsg_unicast(nlsk, skb2, NETLINK_CB(skb).portid); -err: + return nfnetlink_unicast(skb2, net, NETLINK_CB(skb).portid); + +err_fill_flowtable_info: kfree_skb(skb2); return err; } @@ -6337,10 +6335,11 @@ static int nf_tables_getgen(struct net *net, struct sock *nlsk, err = nf_tables_fill_gen_info(skb2, net, NETLINK_CB(skb).portid, nlh->nlmsg_seq); if (err < 0) - goto err; + goto err_fill_gen_info; - return nlmsg_unicast(nlsk, skb2, NETLINK_CB(skb).portid); -err: + return nfnetlink_unicast(skb2, net, NETLINK_CB(skb).portid); + +err_fill_gen_info: kfree_skb(skb2); return err; } diff --git a/net/netfilter/nf_tables_offload.c b/net/netfilter/nf_tables_offload.c index 914cd0618d5a..c480549a7f94 100644 --- a/net/netfilter/nf_tables_offload.c +++ b/net/netfilter/nf_tables_offload.c @@ -37,7 +37,7 @@ struct nft_flow_rule *nft_flow_rule_create(struct net *net, struct nft_expr *expr; expr = nft_expr_first(rule); - while (expr->ops && expr != nft_expr_last(rule)) { + while (nft_expr_more(rule, expr)) { if (expr->ops->offload_flags & NFT_OFFLOAD_F_ACTION) num_actions++; @@ -61,7 +61,7 @@ struct nft_flow_rule *nft_flow_rule_create(struct net *net, ctx->net = net; ctx->dep.type = NFT_OFFLOAD_DEP_UNSPEC; - while (expr->ops && expr != nft_expr_last(rule)) { + while (nft_expr_more(rule, expr)) { if (!expr->ops->offload) { err = -EOPNOTSUPP; goto err_out; diff --git a/net/netfilter/nfnetlink.c b/net/netfilter/nfnetlink.c index 99127e2d95a8..6d03b0909621 100644 --- a/net/netfilter/nfnetlink.c +++ b/net/netfilter/nfnetlink.c @@ -148,10 +148,15 @@ int nfnetlink_set_err(struct net *net, u32 portid, u32 group, int error) } EXPORT_SYMBOL_GPL(nfnetlink_set_err); -int nfnetlink_unicast(struct sk_buff *skb, struct net *net, u32 portid, - int flags) +int nfnetlink_unicast(struct sk_buff *skb, struct net *net, u32 portid) { - return netlink_unicast(net->nfnl, skb, portid, flags); + int err; + + err = nlmsg_unicast(net->nfnl, skb, portid); + if (err == -EAGAIN) + err = -ENOBUFS; + + return err; } EXPORT_SYMBOL_GPL(nfnetlink_unicast); diff --git a/net/netfilter/nfnetlink_log.c b/net/netfilter/nfnetlink_log.c index 0ba020ca38e6..7ca2ca4bba05 100644 --- a/net/netfilter/nfnetlink_log.c +++ b/net/netfilter/nfnetlink_log.c @@ -356,8 +356,7 @@ __nfulnl_send(struct nfulnl_instance *inst) goto out; } } - nfnetlink_unicast(inst->skb, inst->net, inst->peer_portid, - MSG_DONTWAIT); + nfnetlink_unicast(inst->skb, inst->net, inst->peer_portid); out: inst->qlen = 0; inst->skb = NULL; diff --git a/net/netfilter/nfnetlink_queue.c b/net/netfilter/nfnetlink_queue.c index feabdfb22920..6f0a2bad8ad5 100644 --- a/net/netfilter/nfnetlink_queue.c +++ b/net/netfilter/nfnetlink_queue.c @@ -681,7 +681,7 @@ __nfqnl_enqueue_packet(struct net *net, struct nfqnl_instance *queue, *packet_id_ptr = htonl(entry->id); /* nfnetlink_unicast will either free the nskb or add it to a socket */ - err = nfnetlink_unicast(nskb, net, queue->peer_portid, MSG_DONTWAIT); + err = nfnetlink_unicast(nskb, net, queue->peer_portid); if (err < 0) { if (queue->flags & NFQA_CFG_F_FAIL_OPEN) { failopen = 1; diff --git a/net/netfilter/nft_exthdr.c b/net/netfilter/nft_exthdr.c index a5e8469859e3..427d77b111b1 100644 --- a/net/netfilter/nft_exthdr.c +++ b/net/netfilter/nft_exthdr.c @@ -44,7 +44,7 @@ static void nft_exthdr_ipv6_eval(const struct nft_expr *expr, err = ipv6_find_hdr(pkt->skb, &offset, priv->type, NULL, NULL); if (priv->flags & NFT_EXTHDR_F_PRESENT) { - *dest = (err >= 0); + nft_reg_store8(dest, err >= 0); return; } else if (err < 0) { goto err; @@ -141,7 +141,7 @@ static void nft_exthdr_ipv4_eval(const struct nft_expr *expr, err = ipv4_find_option(nft_net(pkt), skb, &offset, priv->type); if (priv->flags & NFT_EXTHDR_F_PRESENT) { - *dest = (err >= 0); + nft_reg_store8(dest, err >= 0); return; } else if (err < 0) { goto err; diff --git a/net/netfilter/nft_fwd_netdev.c b/net/netfilter/nft_fwd_netdev.c index 3087e23297db..b77985986b24 100644 --- a/net/netfilter/nft_fwd_netdev.c +++ b/net/netfilter/nft_fwd_netdev.c @@ -138,6 +138,7 @@ static void nft_fwd_neigh_eval(const struct nft_expr *expr, return; skb->dev = dev; + skb->tstamp = 0; neigh_xmit(neigh_table, dev, addr, skb); out: regs->verdict.code = verdict; diff --git a/net/netfilter/nft_nat.c b/net/netfilter/nft_nat.c index c3c93e95b46e..243e8107f456 100644 --- a/net/netfilter/nft_nat.c +++ b/net/netfilter/nft_nat.c @@ -129,7 +129,7 @@ static int nft_nat_init(const struct nft_ctx *ctx, const struct nft_expr *expr, priv->type = NF_NAT_MANIP_DST; break; default: - return -EINVAL; + return -EOPNOTSUPP; } if (tb[NFTA_NAT_FAMILY] == NULL) @@ -196,7 +196,7 @@ static int nft_nat_init(const struct nft_ctx *ctx, const struct nft_expr *expr, if (tb[NFTA_NAT_FLAGS]) { priv->flags = ntohl(nla_get_be32(tb[NFTA_NAT_FLAGS])); if (priv->flags & ~NF_NAT_RANGE_MASK) - return -EINVAL; + return -EOPNOTSUPP; } return nf_ct_netns_get(ctx->net, family); diff --git a/net/netfilter/nft_payload.c b/net/netfilter/nft_payload.c index 0e3bfbc26e79..62dc728bf93c 100644 --- a/net/netfilter/nft_payload.c +++ b/net/netfilter/nft_payload.c @@ -79,7 +79,9 @@ void nft_payload_eval(const struct nft_expr *expr, u32 *dest = ®s->data[priv->dreg]; int offset; - dest[priv->len / NFT_REG32_SIZE] = 0; + if (priv->len % NFT_REG32_SIZE) + dest[priv->len / NFT_REG32_SIZE] = 0; + switch (priv->base) { case NFT_PAYLOAD_LL_HEADER: if (!skb_mac_header_was_set(skb)) diff --git a/net/netlabel/netlabel_domainhash.c b/net/netlabel/netlabel_domainhash.c index f5d34da0646e..12aa803b2f68 100644 --- a/net/netlabel/netlabel_domainhash.c +++ b/net/netlabel/netlabel_domainhash.c @@ -85,6 +85,7 @@ static void netlbl_domhsh_free_entry(struct rcu_head *entry) kfree(netlbl_domhsh_addr6_entry(iter6)); } #endif /* IPv6 */ + kfree(ptr->def.addrsel); } kfree(ptr->domain); kfree(ptr); @@ -536,6 +537,8 @@ int netlbl_domhsh_add(struct netlbl_dom_map *entry, goto add_return; } #endif /* IPv6 */ + /* cleanup the new entry since we've moved everything over */ + netlbl_domhsh_free_entry(&entry->rcu); } else ret_val = -EINVAL; @@ -579,6 +582,12 @@ int netlbl_domhsh_remove_entry(struct netlbl_dom_map *entry, { int ret_val = 0; struct audit_buffer *audit_buf; + struct netlbl_af4list *iter4; + struct netlbl_domaddr4_map *map4; +#if IS_ENABLED(CONFIG_IPV6) + struct netlbl_af6list *iter6; + struct netlbl_domaddr6_map *map6; +#endif /* IPv6 */ if (entry == NULL) return -ENOENT; @@ -596,6 +605,9 @@ int netlbl_domhsh_remove_entry(struct netlbl_dom_map *entry, ret_val = -ENOENT; spin_unlock(&netlbl_domhsh_lock); + if (ret_val) + return ret_val; + audit_buf = netlbl_audit_start_common(AUDIT_MAC_MAP_DEL, audit_info); if (audit_buf != NULL) { audit_log_format(audit_buf, @@ -605,40 +617,29 @@ int netlbl_domhsh_remove_entry(struct netlbl_dom_map *entry, audit_log_end(audit_buf); } - if (ret_val == 0) { - struct netlbl_af4list *iter4; - struct netlbl_domaddr4_map *map4; -#if IS_ENABLED(CONFIG_IPV6) - struct netlbl_af6list *iter6; - struct netlbl_domaddr6_map *map6; -#endif /* IPv6 */ - - switch (entry->def.type) { - case NETLBL_NLTYPE_ADDRSELECT: - netlbl_af4list_foreach_rcu(iter4, - &entry->def.addrsel->list4) { - map4 = netlbl_domhsh_addr4_entry(iter4); - cipso_v4_doi_putdef(map4->def.cipso); - } + switch (entry->def.type) { + case NETLBL_NLTYPE_ADDRSELECT: + netlbl_af4list_foreach_rcu(iter4, &entry->def.addrsel->list4) { + map4 = netlbl_domhsh_addr4_entry(iter4); + cipso_v4_doi_putdef(map4->def.cipso); + } #if IS_ENABLED(CONFIG_IPV6) - netlbl_af6list_foreach_rcu(iter6, - &entry->def.addrsel->list6) { - map6 = netlbl_domhsh_addr6_entry(iter6); - calipso_doi_putdef(map6->def.calipso); - } + netlbl_af6list_foreach_rcu(iter6, &entry->def.addrsel->list6) { + map6 = netlbl_domhsh_addr6_entry(iter6); + calipso_doi_putdef(map6->def.calipso); + } #endif /* IPv6 */ - break; - case NETLBL_NLTYPE_CIPSOV4: - cipso_v4_doi_putdef(entry->def.cipso); - break; + break; + case NETLBL_NLTYPE_CIPSOV4: + cipso_v4_doi_putdef(entry->def.cipso); + break; #if IS_ENABLED(CONFIG_IPV6) - case NETLBL_NLTYPE_CALIPSO: - calipso_doi_putdef(entry->def.calipso); - break; + case NETLBL_NLTYPE_CALIPSO: + calipso_doi_putdef(entry->def.calipso); + break; #endif /* IPv6 */ - } - call_rcu(&entry->rcu, netlbl_domhsh_free_entry); } + call_rcu(&entry->rcu, netlbl_domhsh_free_entry); return ret_val; } diff --git a/net/netlink/genetlink.c b/net/netlink/genetlink.c index efccd1ac9a66..102b8d6b5612 100644 --- a/net/netlink/genetlink.c +++ b/net/netlink/genetlink.c @@ -989,60 +989,11 @@ static struct genl_family genl_ctrl __ro_after_init = { .netnsok = true, }; -static int genl_bind(struct net *net, int group) -{ - struct genl_family *f; - int err = -ENOENT; - unsigned int id; - - down_read(&cb_lock); - - idr_for_each_entry(&genl_fam_idr, f, id) { - if (group >= f->mcgrp_offset && - group < f->mcgrp_offset + f->n_mcgrps) { - int fam_grp = group - f->mcgrp_offset; - - if (!f->netnsok && net != &init_net) - err = -ENOENT; - else if (f->mcast_bind) - err = f->mcast_bind(net, fam_grp); - else - err = 0; - break; - } - } - up_read(&cb_lock); - - return err; -} - -static void genl_unbind(struct net *net, int group) -{ - struct genl_family *f; - unsigned int id; - - down_read(&cb_lock); - - idr_for_each_entry(&genl_fam_idr, f, id) { - if (group >= f->mcgrp_offset && - group < f->mcgrp_offset + f->n_mcgrps) { - int fam_grp = group - f->mcgrp_offset; - - if (f->mcast_unbind) - f->mcast_unbind(net, fam_grp); - break; - } - } - up_read(&cb_lock); -} - static int __net_init genl_pernet_init(struct net *net) { struct netlink_kernel_cfg cfg = { .input = genl_rcv, .flags = NL_CFG_F_NONROOT_RECV, - .bind = genl_bind, - .unbind = genl_unbind, }; /* we'll bump the group number right afterwards */ diff --git a/net/nfc/netlink.c b/net/nfc/netlink.c index 1b261375722e..4170acc2dc28 100644 --- a/net/nfc/netlink.c +++ b/net/nfc/netlink.c @@ -1225,7 +1225,7 @@ static int nfc_genl_fw_download(struct sk_buff *skb, struct genl_info *info) u32 idx; char firmware_name[NFC_FIRMWARE_NAME_MAXSIZE + 1]; - if (!info->attrs[NFC_ATTR_DEVICE_INDEX]) + if (!info->attrs[NFC_ATTR_DEVICE_INDEX] || !info->attrs[NFC_ATTR_FIRMWARE_NAME]) return -EINVAL; idx = nla_get_u32(info->attrs[NFC_ATTR_DEVICE_INDEX]); diff --git a/net/nfc/rawsock.c b/net/nfc/rawsock.c index ba5ffd3badd3..b5c867fe3232 100644 --- a/net/nfc/rawsock.c +++ b/net/nfc/rawsock.c @@ -332,10 +332,13 @@ static int rawsock_create(struct net *net, struct socket *sock, if ((sock->type != SOCK_SEQPACKET) && (sock->type != SOCK_RAW)) return -ESOCKTNOSUPPORT; - if (sock->type == SOCK_RAW) + if (sock->type == SOCK_RAW) { + if (!capable(CAP_NET_RAW)) + return -EPERM; sock->ops = &rawsock_raw_ops; - else + } else { sock->ops = &rawsock_ops; + } sk = sk_alloc(net, PF_NFC, GFP_ATOMIC, nfc_proto->proto, kern); if (!sk) diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c index 99352f09deaa..3d96dab10449 100644 --- a/net/openvswitch/actions.c +++ b/net/openvswitch/actions.c @@ -1146,9 +1146,10 @@ static int execute_check_pkt_len(struct datapath *dp, struct sk_buff *skb, struct sw_flow_key *key, const struct nlattr *attr, bool last) { + struct ovs_skb_cb *ovs_cb = OVS_CB(skb); const struct nlattr *actions, *cpl_arg; + int len, max_len, rem = nla_len(attr); const struct check_pkt_len_arg *arg; - int rem = nla_len(attr); bool clone_flow_key; /* The first netlink attribute in 'attr' is always @@ -1157,7 +1158,11 @@ static int execute_check_pkt_len(struct datapath *dp, struct sk_buff *skb, cpl_arg = nla_data(attr); arg = nla_data(cpl_arg); - if (skb->len <= arg->pkt_len) { + len = ovs_cb->mru ? ovs_cb->mru + skb->mac_len : skb->len; + max_len = arg->pkt_len; + + if ((skb_is_gso(skb) && skb_gso_validate_mac_len(skb, max_len)) || + len <= max_len) { /* Second netlink attribute in 'attr' is always * 'OVS_CHECK_PKT_LEN_ATTR_ACTIONS_IF_LESS_EQUAL'. */ diff --git a/net/openvswitch/conntrack.c b/net/openvswitch/conntrack.c index 8b70298857e3..d06d7d58eaf2 100644 --- a/net/openvswitch/conntrack.c +++ b/net/openvswitch/conntrack.c @@ -276,10 +276,6 @@ void ovs_ct_fill_key(const struct sk_buff *skb, struct sw_flow_key *key) ovs_ct_update_key(skb, NULL, key, false, false); } -#define IN6_ADDR_INITIALIZER(ADDR) \ - { (ADDR).s6_addr32[0], (ADDR).s6_addr32[1], \ - (ADDR).s6_addr32[2], (ADDR).s6_addr32[3] } - int ovs_ct_put_key(const struct sw_flow_key *swkey, const struct sw_flow_key *output, struct sk_buff *skb) { @@ -301,24 +297,30 @@ int ovs_ct_put_key(const struct sw_flow_key *swkey, if (swkey->ct_orig_proto) { if (swkey->eth.type == htons(ETH_P_IP)) { - struct ovs_key_ct_tuple_ipv4 orig = { - output->ipv4.ct_orig.src, - output->ipv4.ct_orig.dst, - output->ct.orig_tp.src, - output->ct.orig_tp.dst, - output->ct_orig_proto, - }; + struct ovs_key_ct_tuple_ipv4 orig; + + memset(&orig, 0, sizeof(orig)); + orig.ipv4_src = output->ipv4.ct_orig.src; + orig.ipv4_dst = output->ipv4.ct_orig.dst; + orig.src_port = output->ct.orig_tp.src; + orig.dst_port = output->ct.orig_tp.dst; + orig.ipv4_proto = output->ct_orig_proto; + if (nla_put(skb, OVS_KEY_ATTR_CT_ORIG_TUPLE_IPV4, sizeof(orig), &orig)) return -EMSGSIZE; } else if (swkey->eth.type == htons(ETH_P_IPV6)) { - struct ovs_key_ct_tuple_ipv6 orig = { - IN6_ADDR_INITIALIZER(output->ipv6.ct_orig.src), - IN6_ADDR_INITIALIZER(output->ipv6.ct_orig.dst), - output->ct.orig_tp.src, - output->ct.orig_tp.dst, - output->ct_orig_proto, - }; + struct ovs_key_ct_tuple_ipv6 orig; + + memset(&orig, 0, sizeof(orig)); + memcpy(orig.ipv6_src, output->ipv6.ct_orig.src.s6_addr32, + sizeof(orig.ipv6_src)); + memcpy(orig.ipv6_dst, output->ipv6.ct_orig.dst.s6_addr32, + sizeof(orig.ipv6_dst)); + orig.src_port = output->ct.orig_tp.src; + orig.dst_port = output->ct.orig_tp.dst; + orig.ipv6_proto = output->ct_orig_proto; + if (nla_put(skb, OVS_KEY_ATTR_CT_ORIG_TUPLE_IPV6, sizeof(orig), &orig)) return -EMSGSIZE; @@ -903,15 +905,19 @@ static int ovs_ct_nat(struct net *net, struct sw_flow_key *key, } err = ovs_ct_nat_execute(skb, ct, ctinfo, &info->range, maniptype); - if (err == NF_ACCEPT && - ct->status & IPS_SRC_NAT && ct->status & IPS_DST_NAT) { - if (maniptype == NF_NAT_MANIP_SRC) - maniptype = NF_NAT_MANIP_DST; - else - maniptype = NF_NAT_MANIP_SRC; - - err = ovs_ct_nat_execute(skb, ct, ctinfo, &info->range, - maniptype); + if (err == NF_ACCEPT && ct->status & IPS_DST_NAT) { + if (ct->status & IPS_SRC_NAT) { + if (maniptype == NF_NAT_MANIP_SRC) + maniptype = NF_NAT_MANIP_DST; + else + maniptype = NF_NAT_MANIP_SRC; + + err = ovs_ct_nat_execute(skb, ct, ctinfo, &info->range, + maniptype); + } else if (CTINFO2DIR(ctinfo) == IP_CT_DIR_ORIGINAL) { + err = ovs_ct_nat_execute(skb, ct, ctinfo, NULL, + NF_NAT_MANIP_SRC); + } } /* Mark NAT done if successful and update the flow key. */ diff --git a/net/openvswitch/meter.c b/net/openvswitch/meter.c index 3323b79ff548..541eea74ef7a 100644 --- a/net/openvswitch/meter.c +++ b/net/openvswitch/meter.c @@ -251,8 +251,8 @@ static struct dp_meter *dp_meter_create(struct nlattr **a) * * Start with a full bucket. */ - band->bucket = (band->burst_size + band->rate) * 1000; - band_max_delta_t = band->bucket / band->rate; + band->bucket = (band->burst_size + band->rate) * 1000ULL; + band_max_delta_t = div_u64(band->bucket, band->rate); if (band_max_delta_t > meter->max_delta_t) meter->max_delta_t = band_max_delta_t; band++; diff --git a/net/openvswitch/meter.h b/net/openvswitch/meter.h index f645913870bd..2e3fd6f1d7eb 100644 --- a/net/openvswitch/meter.h +++ b/net/openvswitch/meter.h @@ -23,7 +23,7 @@ struct dp_meter_band { u32 type; u32 rate; u32 burst_size; - u32 bucket; /* 1/1000 packets, or in bits */ + u64 bucket; /* 1/1000 packets, or in bits */ struct ovs_flow_stats stats; }; diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index 1d63ab3a878a..fbc2d4dfddf0 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -941,6 +941,7 @@ static int prb_queue_frozen(struct tpacket_kbdq_core *pkc) } static void prb_clear_blk_fill_status(struct packet_ring_buffer *rb) + __releases(&pkc->blk_fill_in_prog_lock) { struct tpacket_kbdq_core *pkc = GET_PBDQC_FROM_RB(rb); atomic_dec(&pkc->blk_fill_in_prog); @@ -988,6 +989,7 @@ static void prb_fill_curr_block(char *curr, struct tpacket_kbdq_core *pkc, struct tpacket_block_desc *pbd, unsigned int len) + __acquires(&pkc->blk_fill_in_prog_lock) { struct tpacket3_hdr *ppd; @@ -2167,7 +2169,8 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev, int skb_len = skb->len; unsigned int snaplen, res; unsigned long status = TP_STATUS_USER; - unsigned short macoff, netoff, hdrlen; + unsigned short macoff, hdrlen; + unsigned int netoff; struct sk_buff *copy_skb = NULL; struct timespec ts; __u32 ts_status; @@ -2236,6 +2239,10 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev, } macoff = netoff - maclen; } + if (netoff > USHRT_MAX) { + atomic_inc(&po->tp_drops); + goto drop_n_restore; + } if (po->tp_version <= TPACKET_V2) { if (macoff + snaplen > po->rx_ring.frame_size) { if (po->copy_thresh && @@ -2285,8 +2292,11 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev, if (do_vnet && virtio_net_hdr_from_skb(skb, h.raw + macoff - sizeof(struct virtio_net_hdr), - vio_le(), true, 0)) + vio_le(), true, 0)) { + if (po->tp_version == TPACKET_V3) + prb_clear_blk_fill_status(&po->rx_ring); goto drop_n_account; + } if (po->tp_version <= TPACKET_V2) { packet_increment_rx_head(po, &po->rx_ring); @@ -2392,7 +2402,7 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev, __clear_bit(slot_id, po->rx_ring.rx_owner_map); spin_unlock(&sk->sk_receive_queue.lock); sk->sk_data_ready(sk); - } else { + } else if (po->tp_version == TPACKET_V3) { prb_clear_blk_fill_status(&po->rx_ring); } diff --git a/net/qrtr/qrtr.c b/net/qrtr/qrtr.c index 2a4d50e04441..d6d2736ec927 100644 --- a/net/qrtr/qrtr.c +++ b/net/qrtr/qrtr.c @@ -178,7 +178,7 @@ static int qrtr_node_enqueue(struct qrtr_node *node, struct sk_buff *skb, { struct qrtr_hdr_v1 *hdr; size_t len = skb->len; - int rc = -ENODEV; + int rc; hdr = skb_push(skb, sizeof(*hdr)); hdr->version = cpu_to_le32(QRTR_PROTO_VER_1); @@ -196,15 +196,17 @@ static int qrtr_node_enqueue(struct qrtr_node *node, struct sk_buff *skb, hdr->size = cpu_to_le32(len); hdr->confirm_rx = 0; - skb_put_padto(skb, ALIGN(len, 4) + sizeof(*hdr)); - - mutex_lock(&node->ep_lock); - if (node->ep) - rc = node->ep->xmit(node->ep, skb); - else - kfree_skb(skb); - mutex_unlock(&node->ep_lock); + rc = skb_put_padto(skb, ALIGN(len, 4) + sizeof(*hdr)); + if (!rc) { + mutex_lock(&node->ep_lock); + rc = -ENODEV; + if (node->ep) + rc = node->ep->xmit(node->ep, skb); + else + kfree_skb(skb); + mutex_unlock(&node->ep_lock); + } return rc; } @@ -259,7 +261,7 @@ int qrtr_endpoint_post(struct qrtr_endpoint *ep, const void *data, size_t len) unsigned int ver; size_t hdrlen; - if (len & 3) + if (len == 0 || len & 3) return -EINVAL; skb = netdev_alloc_skb(NULL, len); @@ -273,6 +275,8 @@ int qrtr_endpoint_post(struct qrtr_endpoint *ep, const void *data, size_t len) switch (ver) { case QRTR_PROTO_VER_1: + if (len < sizeof(*v1)) + goto err; v1 = data; hdrlen = sizeof(*v1); @@ -286,6 +290,8 @@ int qrtr_endpoint_post(struct qrtr_endpoint *ep, const void *data, size_t len) size = le32_to_cpu(v1->size); break; case QRTR_PROTO_VER_2: + if (len < sizeof(*v2)) + goto err; v2 = data; hdrlen = sizeof(*v2) + v2->optlen; @@ -543,23 +549,25 @@ static void qrtr_port_remove(struct qrtr_sock *ipc) */ static int qrtr_port_assign(struct qrtr_sock *ipc, int *port) { + u32 min_port; int rc; mutex_lock(&qrtr_port_lock); if (!*port) { - rc = idr_alloc(&qrtr_ports, ipc, - QRTR_MIN_EPH_SOCKET, QRTR_MAX_EPH_SOCKET + 1, - GFP_ATOMIC); - if (rc >= 0) - *port = rc; + min_port = QRTR_MIN_EPH_SOCKET; + rc = idr_alloc_u32(&qrtr_ports, ipc, &min_port, QRTR_MAX_EPH_SOCKET, GFP_ATOMIC); + if (!rc) + *port = min_port; } else if (*port < QRTR_MIN_EPH_SOCKET && !capable(CAP_NET_ADMIN)) { rc = -EACCES; } else if (*port == QRTR_PORT_CTRL) { - rc = idr_alloc(&qrtr_ports, ipc, 0, 1, GFP_ATOMIC); + min_port = 0; + rc = idr_alloc_u32(&qrtr_ports, ipc, &min_port, 0, GFP_ATOMIC); } else { - rc = idr_alloc(&qrtr_ports, ipc, *port, *port + 1, GFP_ATOMIC); - if (rc >= 0) - *port = rc; + min_port = *port; + rc = idr_alloc_u32(&qrtr_ports, ipc, &min_port, *port, GFP_ATOMIC); + if (!rc) + *port = min_port; } mutex_unlock(&qrtr_port_lock); @@ -1000,6 +1008,7 @@ static int qrtr_release(struct socket *sock) sk->sk_state_change(sk); sock_set_flag(sk, SOCK_DEAD); + sock_orphan(sk); sock->sk = NULL; if (!sock_flag(sk, SOCK_ZAPPED)) diff --git a/net/rds/recv.c b/net/rds/recv.c index c8404971d5ab..aba4afe4dfed 100644 --- a/net/rds/recv.c +++ b/net/rds/recv.c @@ -450,12 +450,13 @@ static int rds_still_queued(struct rds_sock *rs, struct rds_incoming *inc, int rds_notify_queue_get(struct rds_sock *rs, struct msghdr *msghdr) { struct rds_notifier *notifier; - struct rds_rdma_notify cmsg = { 0 }; /* fill holes with zero */ + struct rds_rdma_notify cmsg; unsigned int count = 0, max_messages = ~0U; unsigned long flags; LIST_HEAD(copy); int err = 0; + memset(&cmsg, 0, sizeof(cmsg)); /* fill holes with zero */ /* put_cmsg copies to user space and thus may sleep. We can't do this * with rs_lock held, so first grab as many notifications as we can stuff diff --git a/net/rxrpc/call_accept.c b/net/rxrpc/call_accept.c index b7611cc159e5..032ed76c0166 100644 --- a/net/rxrpc/call_accept.c +++ b/net/rxrpc/call_accept.c @@ -22,6 +22,11 @@ #include <net/ip.h> #include "ar-internal.h" +static void rxrpc_dummy_notify(struct sock *sk, struct rxrpc_call *call, + unsigned long user_call_ID) +{ +} + /* * Preallocate a single service call, connection and peer and, if possible, * give them a user ID and attach the user's side of the ID to them. @@ -228,6 +233,8 @@ void rxrpc_discard_prealloc(struct rxrpc_sock *rx) if (rx->discard_new_call) { _debug("discard %lx", call->user_call_ID); rx->discard_new_call(call, call->user_call_ID); + if (call->notify_rx) + call->notify_rx = rxrpc_dummy_notify; rxrpc_put_call(call, rxrpc_call_put_kernel); } rxrpc_call_completed(call); diff --git a/net/rxrpc/call_event.c b/net/rxrpc/call_event.c index 2a65ac41055f..9ff85ee8337c 100644 --- a/net/rxrpc/call_event.c +++ b/net/rxrpc/call_event.c @@ -248,7 +248,18 @@ static void rxrpc_resend(struct rxrpc_call *call, unsigned long now_j) if (anno_type != RXRPC_TX_ANNO_RETRANS) continue; + /* We need to reset the retransmission state, but we need to do + * so before we drop the lock as a new ACK/NAK may come in and + * confuse things + */ + annotation &= ~RXRPC_TX_ANNO_MASK; + annotation |= RXRPC_TX_ANNO_UNACK | RXRPC_TX_ANNO_RESENT; + call->rxtx_annotations[ix] = annotation; + skb = call->rxtx_buffer[ix]; + if (!skb) + continue; + rxrpc_get_skb(skb, rxrpc_skb_got); spin_unlock_bh(&call->lock); @@ -262,24 +273,6 @@ static void rxrpc_resend(struct rxrpc_call *call, unsigned long now_j) rxrpc_free_skb(skb, rxrpc_skb_freed); spin_lock_bh(&call->lock); - - /* We need to clear the retransmit state, but there are two - * things we need to be aware of: A new ACK/NAK might have been - * received and the packet might have been hard-ACK'd (in which - * case it will no longer be in the buffer). - */ - if (after(seq, call->tx_hard_ack)) { - annotation = call->rxtx_annotations[ix]; - anno_type = annotation & RXRPC_TX_ANNO_MASK; - if (anno_type == RXRPC_TX_ANNO_RETRANS || - anno_type == RXRPC_TX_ANNO_NAK) { - annotation &= ~RXRPC_TX_ANNO_MASK; - annotation |= RXRPC_TX_ANNO_UNACK; - } - annotation |= RXRPC_TX_ANNO_RESENT; - call->rxtx_annotations[ix] = annotation; - } - if (after(call->tx_hard_ack, seq)) seq = call->tx_hard_ack; } diff --git a/net/rxrpc/call_object.c b/net/rxrpc/call_object.c index f07970207b54..38a46167523f 100644 --- a/net/rxrpc/call_object.c +++ b/net/rxrpc/call_object.c @@ -288,7 +288,7 @@ struct rxrpc_call *rxrpc_new_client_call(struct rxrpc_sock *rx, */ ret = rxrpc_connect_call(rx, call, cp, srx, gfp); if (ret < 0) - goto error; + goto error_attached_to_socket; trace_rxrpc_call(call->debug_id, rxrpc_call_connected, atomic_read(&call->usage), here, NULL); @@ -308,18 +308,29 @@ struct rxrpc_call *rxrpc_new_client_call(struct rxrpc_sock *rx, error_dup_user_ID: write_unlock(&rx->call_lock); release_sock(&rx->sk); - ret = -EEXIST; - -error: __rxrpc_set_call_completion(call, RXRPC_CALL_LOCAL_ERROR, - RX_CALL_DEAD, ret); + RX_CALL_DEAD, -EEXIST); trace_rxrpc_call(call->debug_id, rxrpc_call_error, - atomic_read(&call->usage), here, ERR_PTR(ret)); + atomic_read(&call->usage), here, ERR_PTR(-EEXIST)); rxrpc_release_call(rx, call); mutex_unlock(&call->user_mutex); rxrpc_put_call(call, rxrpc_call_put); - _leave(" = %d", ret); - return ERR_PTR(ret); + _leave(" = -EEXIST"); + return ERR_PTR(-EEXIST); + + /* We got an error, but the call is attached to the socket and is in + * need of release. However, we might now race with recvmsg() when + * completing the call queues it. Return 0 from sys_sendmsg() and + * leave the error to recvmsg() to deal with. + */ +error_attached_to_socket: + trace_rxrpc_call(call->debug_id, rxrpc_call_error, + atomic_read(&call->usage), here, ERR_PTR(ret)); + set_bit(RXRPC_CALL_DISCONNECTED, &call->flags); + __rxrpc_set_call_completion(call, RXRPC_CALL_LOCAL_ERROR, + RX_CALL_DEAD, ret); + _leave(" = c=%08x [err]", call->debug_id); + return call; } /* diff --git a/net/rxrpc/conn_event.c b/net/rxrpc/conn_event.c index 06fcff2ebbba..b5864683f200 100644 --- a/net/rxrpc/conn_event.c +++ b/net/rxrpc/conn_event.c @@ -341,18 +341,18 @@ static int rxrpc_process_event(struct rxrpc_connection *conn, return ret; spin_lock(&conn->channel_lock); - spin_lock(&conn->state_lock); + spin_lock_bh(&conn->state_lock); if (conn->state == RXRPC_CONN_SERVICE_CHALLENGING) { conn->state = RXRPC_CONN_SERVICE; - spin_unlock(&conn->state_lock); + spin_unlock_bh(&conn->state_lock); for (loop = 0; loop < RXRPC_MAXCALLS; loop++) rxrpc_call_is_secure( rcu_dereference_protected( conn->channels[loop].call, lockdep_is_held(&conn->channel_lock))); } else { - spin_unlock(&conn->state_lock); + spin_unlock_bh(&conn->state_lock); } spin_unlock(&conn->channel_lock); diff --git a/net/rxrpc/conn_object.c b/net/rxrpc/conn_object.c index 19e141eeed17..8cbe0bf20ed5 100644 --- a/net/rxrpc/conn_object.c +++ b/net/rxrpc/conn_object.c @@ -212,9 +212,11 @@ void rxrpc_disconnect_call(struct rxrpc_call *call) call->peer->cong_cwnd = call->cong_cwnd; - spin_lock_bh(&conn->params.peer->lock); - hlist_del_rcu(&call->error_link); - spin_unlock_bh(&conn->params.peer->lock); + if (!hlist_unhashed(&call->error_link)) { + spin_lock_bh(&call->peer->lock); + hlist_del_rcu(&call->error_link); + spin_unlock_bh(&call->peer->lock); + } if (rxrpc_is_client_call(call)) return rxrpc_disconnect_client_call(call); diff --git a/net/rxrpc/input.c b/net/rxrpc/input.c index 3be4177baf70..6cace43b217e 100644 --- a/net/rxrpc/input.c +++ b/net/rxrpc/input.c @@ -723,13 +723,12 @@ static void rxrpc_input_ackinfo(struct rxrpc_call *call, struct sk_buff *skb, ntohl(ackinfo->rxMTU), ntohl(ackinfo->maxMTU), rwind, ntohl(ackinfo->jumbo_max)); + if (rwind > RXRPC_RXTX_BUFF_SIZE - 1) + rwind = RXRPC_RXTX_BUFF_SIZE - 1; if (call->tx_winsize != rwind) { - if (rwind > RXRPC_RXTX_BUFF_SIZE - 1) - rwind = RXRPC_RXTX_BUFF_SIZE - 1; if (rwind > call->tx_winsize) wake = true; - trace_rxrpc_rx_rwind_change(call, sp->hdr.serial, - ntohl(ackinfo->rwind), wake); + trace_rxrpc_rx_rwind_change(call, sp->hdr.serial, rwind, wake); call->tx_winsize = rwind; } @@ -845,7 +844,7 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb) struct rxrpc_ackinfo info; u8 acks[RXRPC_MAXACKS]; } buf; - rxrpc_serial_t acked_serial; + rxrpc_serial_t ack_serial, acked_serial; rxrpc_seq_t first_soft_ack, hard_ack, prev_pkt; int nr_acks, offset, ioffset; @@ -858,6 +857,7 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb) } offset += sizeof(buf.ack); + ack_serial = sp->hdr.serial; acked_serial = ntohl(buf.ack.serial); first_soft_ack = ntohl(buf.ack.firstPacket); prev_pkt = ntohl(buf.ack.previousPacket); @@ -866,31 +866,31 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb) summary.ack_reason = (buf.ack.reason < RXRPC_ACK__INVALID ? buf.ack.reason : RXRPC_ACK__INVALID); - trace_rxrpc_rx_ack(call, sp->hdr.serial, acked_serial, + trace_rxrpc_rx_ack(call, ack_serial, acked_serial, first_soft_ack, prev_pkt, summary.ack_reason, nr_acks); if (buf.ack.reason == RXRPC_ACK_PING_RESPONSE) rxrpc_input_ping_response(call, skb->tstamp, acked_serial, - sp->hdr.serial); + ack_serial); if (buf.ack.reason == RXRPC_ACK_REQUESTED) rxrpc_input_requested_ack(call, skb->tstamp, acked_serial, - sp->hdr.serial); + ack_serial); if (buf.ack.reason == RXRPC_ACK_PING) { - _proto("Rx ACK %%%u PING Request", sp->hdr.serial); + _proto("Rx ACK %%%u PING Request", ack_serial); rxrpc_propose_ACK(call, RXRPC_ACK_PING_RESPONSE, - sp->hdr.serial, true, true, + ack_serial, true, true, rxrpc_propose_ack_respond_to_ping); } else if (sp->hdr.flags & RXRPC_REQUEST_ACK) { rxrpc_propose_ACK(call, RXRPC_ACK_REQUESTED, - sp->hdr.serial, true, true, + ack_serial, true, true, rxrpc_propose_ack_respond_to_ack); } /* Discard any out-of-order or duplicate ACKs (outside lock). */ if (!rxrpc_is_ack_valid(call, first_soft_ack, prev_pkt)) { - trace_rxrpc_rx_discard_ack(call->debug_id, sp->hdr.serial, + trace_rxrpc_rx_discard_ack(call->debug_id, ack_serial, first_soft_ack, call->ackr_first_seq, prev_pkt, call->ackr_prev_seq); return; @@ -906,7 +906,7 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb) /* Discard any out-of-order or duplicate ACKs (inside lock). */ if (!rxrpc_is_ack_valid(call, first_soft_ack, prev_pkt)) { - trace_rxrpc_rx_discard_ack(call->debug_id, sp->hdr.serial, + trace_rxrpc_rx_discard_ack(call->debug_id, ack_serial, first_soft_ack, call->ackr_first_seq, prev_pkt, call->ackr_prev_seq); goto out; @@ -966,7 +966,7 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb) RXRPC_TX_ANNO_LAST && summary.nr_acks == call->tx_top - hard_ack && rxrpc_is_client_call(call)) - rxrpc_propose_ACK(call, RXRPC_ACK_PING, sp->hdr.serial, + rxrpc_propose_ACK(call, RXRPC_ACK_PING, ack_serial, false, true, rxrpc_propose_ack_ping_for_lost_reply); diff --git a/net/rxrpc/key.c b/net/rxrpc/key.c index 0c98313dd7a8..85a9ff8cd236 100644 --- a/net/rxrpc/key.c +++ b/net/rxrpc/key.c @@ -903,7 +903,7 @@ int rxrpc_request_key(struct rxrpc_sock *rx, char __user *optval, int optlen) _enter(""); - if (optlen <= 0 || optlen > PAGE_SIZE - 1) + if (optlen <= 0 || optlen > PAGE_SIZE - 1 || rx->securities) return -EINVAL; description = memdup_user_nul(optval, optlen); @@ -941,7 +941,7 @@ int rxrpc_server_keyring(struct rxrpc_sock *rx, char __user *optval, if (IS_ERR(description)) return PTR_ERR(description); - key = request_key_net(&key_type_keyring, description, sock_net(&rx->sk), NULL); + key = request_key(&key_type_keyring, description, NULL); if (IS_ERR(key)) { kfree(description); _leave(" = %ld", PTR_ERR(key)); @@ -1073,7 +1073,7 @@ static long rxrpc_read(const struct key *key, switch (token->security_index) { case RXRPC_SECURITY_RXKAD: - toksize += 9 * 4; /* viceid, kvno, key*2 + len, begin, + toksize += 8 * 4; /* viceid, kvno, key*2, begin, * end, primary, tktlen */ toksize += RND(token->kad->ticket_len); break; @@ -1108,7 +1108,8 @@ static long rxrpc_read(const struct key *key, break; default: /* we have a ticket we can't encode */ - BUG(); + pr_err("Unsupported key token type (%u)\n", + token->security_index); continue; } @@ -1139,6 +1140,14 @@ static long rxrpc_read(const struct key *key, memcpy((u8 *)xdr + _l, &zero, 4 - (_l & 3)); \ xdr += (_l + 3) >> 2; \ } while(0) +#define ENCODE_BYTES(l, s) \ + do { \ + u32 _l = (l); \ + memcpy(xdr, (s), _l); \ + if (_l & 3) \ + memcpy((u8 *)xdr + _l, &zero, 4 - (_l & 3)); \ + xdr += (_l + 3) >> 2; \ + } while(0) #define ENCODE64(x) \ do { \ __be64 y = cpu_to_be64(x); \ @@ -1166,7 +1175,7 @@ static long rxrpc_read(const struct key *key, case RXRPC_SECURITY_RXKAD: ENCODE(token->kad->vice_id); ENCODE(token->kad->kvno); - ENCODE_DATA(8, token->kad->session_key); + ENCODE_BYTES(8, token->kad->session_key); ENCODE(token->kad->start); ENCODE(token->kad->expiry); ENCODE(token->kad->primary_flag); @@ -1216,7 +1225,6 @@ static long rxrpc_read(const struct key *key, break; default: - BUG(); break; } diff --git a/net/rxrpc/peer_object.c b/net/rxrpc/peer_object.c index efce27802a74..e011594adcd1 100644 --- a/net/rxrpc/peer_object.c +++ b/net/rxrpc/peer_object.c @@ -500,11 +500,21 @@ EXPORT_SYMBOL(rxrpc_kernel_get_peer); * rxrpc_kernel_get_srtt - Get a call's peer smoothed RTT * @sock: The socket on which the call is in progress. * @call: The call to query + * @_srtt: Where to store the SRTT value. * - * Get the call's peer smoothed RTT. + * Get the call's peer smoothed RTT in uS. */ -u32 rxrpc_kernel_get_srtt(struct socket *sock, struct rxrpc_call *call) +bool rxrpc_kernel_get_srtt(struct socket *sock, struct rxrpc_call *call, + u32 *_srtt) { - return call->peer->srtt_us >> 3; + struct rxrpc_peer *peer = call->peer; + + if (peer->rtt_count == 0) { + *_srtt = 1000000; /* 1S */ + return false; + } + + *_srtt = call->peer->srtt_us >> 3; + return true; } EXPORT_SYMBOL(rxrpc_kernel_get_srtt); diff --git a/net/rxrpc/proc.c b/net/rxrpc/proc.c index 8b179e3c802a..543afd9bd664 100644 --- a/net/rxrpc/proc.c +++ b/net/rxrpc/proc.c @@ -68,7 +68,7 @@ static int rxrpc_call_seq_show(struct seq_file *seq, void *v) "Proto Local " " Remote " " SvID ConnID CallID End Use State Abort " - " UserID TxSeq TW RxSeq RW RxSerial RxTimo\n"); + " DebugId TxSeq TW RxSeq RW RxSerial RxTimo\n"); return 0; } @@ -100,7 +100,7 @@ static int rxrpc_call_seq_show(struct seq_file *seq, void *v) rx_hard_ack = READ_ONCE(call->rx_hard_ack); seq_printf(seq, "UDP %-47.47s %-47.47s %4x %08x %08x %s %3u" - " %-8.8s %08x %lx %08x %02x %08x %02x %08x %06lx\n", + " %-8.8s %08x %08x %08x %02x %08x %02x %08x %06lx\n", lbuff, rbuff, call->service_id, @@ -110,7 +110,7 @@ static int rxrpc_call_seq_show(struct seq_file *seq, void *v) atomic_read(&call->usage), rxrpc_call_states[call->state], call->abort_code, - call->user_call_ID, + call->debug_id, tx_hard_ack, READ_ONCE(call->tx_top) - tx_hard_ack, rx_hard_ack, READ_ONCE(call->rx_top) - rx_hard_ack, call->rx_serial, diff --git a/net/rxrpc/recvmsg.c b/net/rxrpc/recvmsg.c index 8578c39ec839..4f48e3bdd4b4 100644 --- a/net/rxrpc/recvmsg.c +++ b/net/rxrpc/recvmsg.c @@ -464,7 +464,7 @@ try_again: list_empty(&rx->recvmsg_q) && rx->sk.sk_state != RXRPC_SERVER_LISTENING) { release_sock(&rx->sk); - return -ENODATA; + return -EAGAIN; } if (list_empty(&rx->recvmsg_q)) { @@ -541,7 +541,7 @@ try_again: goto error_unlock_call; } - if (msg->msg_name) { + if (msg->msg_name && call->peer) { struct sockaddr_rxrpc *srx = msg->msg_name; size_t len = sizeof(call->peer->srx); diff --git a/net/rxrpc/sendmsg.c b/net/rxrpc/sendmsg.c index 5e9c43d4a314..1a340eb0abf7 100644 --- a/net/rxrpc/sendmsg.c +++ b/net/rxrpc/sendmsg.c @@ -306,7 +306,7 @@ static int rxrpc_send_data(struct rxrpc_sock *rx, /* this should be in poll */ sk_clear_bit(SOCKWQ_ASYNC_NOSPACE, sk); - if (sk->sk_err || (sk->sk_shutdown & SEND_SHUTDOWN)) + if (sk->sk_shutdown & SEND_SHUTDOWN) return -EPIPE; more = msg->msg_flags & MSG_MORE; @@ -683,6 +683,9 @@ int rxrpc_do_sendmsg(struct rxrpc_sock *rx, struct msghdr *msg, size_t len) if (IS_ERR(call)) return PTR_ERR(call); /* ... and we have the call lock. */ + ret = 0; + if (READ_ONCE(call->state) == RXRPC_CALL_COMPLETE) + goto out_put_unlock; } else { switch (READ_ONCE(call->state)) { case RXRPC_CALL_UNINITIALISED: diff --git a/net/sched/act_api.c b/net/sched/act_api.c index 69d4676a402f..1dc642b11443 100644 --- a/net/sched/act_api.c +++ b/net/sched/act_api.c @@ -303,6 +303,8 @@ static int tcf_del_walker(struct tcf_idrinfo *idrinfo, struct sk_buff *skb, mutex_lock(&idrinfo->lock); idr_for_each_entry_ul(idr, p, tmp, id) { + if (IS_ERR(p)) + continue; ret = tcf_idr_release_unsafe(p); if (ret == ACT_P_DELETED) { module_put(ops->owner); @@ -451,17 +453,6 @@ err1: } EXPORT_SYMBOL(tcf_idr_create); -void tcf_idr_insert(struct tc_action_net *tn, struct tc_action *a) -{ - struct tcf_idrinfo *idrinfo = tn->idrinfo; - - mutex_lock(&idrinfo->lock); - /* Replace ERR_PTR(-EBUSY) allocated by tcf_idr_check_alloc */ - WARN_ON(!IS_ERR(idr_replace(&idrinfo->action_idr, a, a->tcfa_index))); - mutex_unlock(&idrinfo->lock); -} -EXPORT_SYMBOL(tcf_idr_insert); - /* Cleanup idr index that was allocated but not initialized. */ void tcf_idr_cleanup(struct tc_action_net *tn, u32 index) @@ -715,13 +706,6 @@ int tcf_action_destroy(struct tc_action *actions[], int bind) return ret; } -static int tcf_action_destroy_1(struct tc_action *a, int bind) -{ - struct tc_action *actions[] = { a, NULL }; - - return tcf_action_destroy(actions, bind); -} - static int tcf_action_put(struct tc_action *p) { return __tcf_action_put(p, false); @@ -839,6 +823,26 @@ static const struct nla_policy tcf_action_policy[TCA_ACT_MAX + 1] = { [TCA_ACT_OPTIONS] = { .type = NLA_NESTED }, }; +static void tcf_idr_insert_many(struct tc_action *actions[]) +{ + int i; + + for (i = 0; i < TCA_ACT_MAX_PRIO; i++) { + struct tc_action *a = actions[i]; + struct tcf_idrinfo *idrinfo; + + if (!a) + continue; + idrinfo = a->idrinfo; + mutex_lock(&idrinfo->lock); + /* Replace ERR_PTR(-EBUSY) allocated by tcf_idr_check_alloc if + * it is just created, otherwise this is just a nop. + */ + idr_replace(&idrinfo->action_idr, a, a->tcfa_index); + mutex_unlock(&idrinfo->lock); + } +} + struct tc_action *tcf_action_init_1(struct net *net, struct tcf_proto *tp, struct nlattr *nla, struct nlattr *est, char *name, int ovr, int bind, @@ -931,13 +935,6 @@ struct tc_action *tcf_action_init_1(struct net *net, struct tcf_proto *tp, if (err != ACT_P_CREATED) module_put(a_o->owner); - if (TC_ACT_EXT_CMP(a->tcfa_action, TC_ACT_GOTO_CHAIN) && - !rcu_access_pointer(a->goto_chain)) { - tcf_action_destroy_1(a, bind); - NL_SET_ERR_MSG(extack, "can't use goto chain with NULL chain"); - return ERR_PTR(-EINVAL); - } - return a; err_mod: @@ -981,6 +978,11 @@ int tcf_action_init(struct net *net, struct tcf_proto *tp, struct nlattr *nla, actions[i - 1] = act; } + /* We have to commit them all together, because if any error happened in + * between, we could not handle the failure gracefully. + */ + tcf_idr_insert_many(actions); + *attr_size = tcf_action_full_attrs_size(sz); return i - 1; diff --git a/net/sched/act_bpf.c b/net/sched/act_bpf.c index 04b7bd4ec751..b7d83d01841b 100644 --- a/net/sched/act_bpf.c +++ b/net/sched/act_bpf.c @@ -361,9 +361,7 @@ static int tcf_bpf_init(struct net *net, struct nlattr *nla, if (goto_ch) tcf_chain_put_by_act(goto_ch); - if (res == ACT_P_CREATED) { - tcf_idr_insert(tn, *act); - } else { + if (res != ACT_P_CREATED) { /* make sure the program being replaced is no longer executing */ synchronize_rcu(); tcf_bpf_cfg_cleanup(&old); diff --git a/net/sched/act_connmark.c b/net/sched/act_connmark.c index 2b43cacf82af..b00105e62334 100644 --- a/net/sched/act_connmark.c +++ b/net/sched/act_connmark.c @@ -43,17 +43,20 @@ static int tcf_connmark_act(struct sk_buff *skb, const struct tc_action *a, tcf_lastuse_update(&ca->tcf_tm); bstats_update(&ca->tcf_bstats, skb); - if (skb->protocol == htons(ETH_P_IP)) { + switch (skb_protocol(skb, true)) { + case htons(ETH_P_IP): if (skb->len < sizeof(struct iphdr)) goto out; proto = NFPROTO_IPV4; - } else if (skb->protocol == htons(ETH_P_IPV6)) { + break; + case htons(ETH_P_IPV6): if (skb->len < sizeof(struct ipv6hdr)) goto out; proto = NFPROTO_IPV6; - } else { + break; + default: goto out; } @@ -136,7 +139,6 @@ static int tcf_connmark_init(struct net *net, struct nlattr *nla, ci->net = net; ci->zone = parm->zone; - tcf_idr_insert(tn, *a); ret = ACT_P_CREATED; } else if (ret > 0) { ci = to_connmark(*a); diff --git a/net/sched/act_csum.c b/net/sched/act_csum.c index d3cfad88dc3a..fa1b1fd10c44 100644 --- a/net/sched/act_csum.c +++ b/net/sched/act_csum.c @@ -110,9 +110,6 @@ static int tcf_csum_init(struct net *net, struct nlattr *nla, if (params_new) kfree_rcu(params_new, rcu); - if (ret == ACT_P_CREATED) - tcf_idr_insert(tn, *a); - return ret; put_chain: if (goto_ch) @@ -587,7 +584,7 @@ static int tcf_csum_act(struct sk_buff *skb, const struct tc_action *a, goto drop; update_flags = params->update_flags; - protocol = tc_skb_protocol(skb); + protocol = skb_protocol(skb, false); again: switch (protocol) { case cpu_to_be16(ETH_P_IP): diff --git a/net/sched/act_ct.c b/net/sched/act_ct.c index 0586546c20d7..6119c31dcd07 100644 --- a/net/sched/act_ct.c +++ b/net/sched/act_ct.c @@ -100,7 +100,7 @@ static u8 tcf_ct_skb_nf_family(struct sk_buff *skb) { u8 family = NFPROTO_UNSPEC; - switch (skb->protocol) { + switch (skb_protocol(skb, true)) { case htons(ETH_P_IP): family = NFPROTO_IPV4; break; @@ -186,7 +186,7 @@ static int tcf_ct_handle_fragments(struct net *net, struct sk_buff *skb, memset(IP6CB(skb), 0, sizeof(struct inet6_skb_parm)); err = nf_ct_frag6_gather(net, skb, user); if (err && err != -EINPROGRESS) - goto out_free; + return err; #else err = -EOPNOTSUPP; goto out_free; @@ -222,6 +222,7 @@ static int ct_nat_execute(struct sk_buff *skb, struct nf_conn *ct, const struct nf_nat_range2 *range, enum nf_nat_manip_type maniptype) { + __be16 proto = skb_protocol(skb, true); int hooknum, err = NF_ACCEPT; /* See HOOK2MANIP(). */ @@ -233,14 +234,13 @@ static int ct_nat_execute(struct sk_buff *skb, struct nf_conn *ct, switch (ctinfo) { case IP_CT_RELATED: case IP_CT_RELATED_REPLY: - if (skb->protocol == htons(ETH_P_IP) && + if (proto == htons(ETH_P_IP) && ip_hdr(skb)->protocol == IPPROTO_ICMP) { if (!nf_nat_icmp_reply_translation(skb, ct, ctinfo, hooknum)) err = NF_DROP; goto out; - } else if (IS_ENABLED(CONFIG_IPV6) && - skb->protocol == htons(ETH_P_IPV6)) { + } else if (IS_ENABLED(CONFIG_IPV6) && proto == htons(ETH_P_IPV6)) { __be16 frag_off; u8 nexthdr = ipv6_hdr(skb)->nexthdr; int hdrlen = ipv6_skip_exthdr(skb, @@ -740,8 +740,6 @@ static int tcf_ct_init(struct net *net, struct nlattr *nla, tcf_chain_put_by_act(goto_ch); if (params) call_rcu(¶ms->rcu, tcf_ct_params_free); - if (res == ACT_P_CREATED) - tcf_idr_insert(tn, *a); return res; @@ -993,4 +991,3 @@ MODULE_AUTHOR("Yossi Kuperman <yossiku@mellanox.com>"); MODULE_AUTHOR("Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>"); MODULE_DESCRIPTION("Connection tracking action"); MODULE_LICENSE("GPL v2"); - diff --git a/net/sched/act_ctinfo.c b/net/sched/act_ctinfo.c index f45995a6237a..9722204399a4 100644 --- a/net/sched/act_ctinfo.c +++ b/net/sched/act_ctinfo.c @@ -96,19 +96,22 @@ static int tcf_ctinfo_act(struct sk_buff *skb, const struct tc_action *a, action = READ_ONCE(ca->tcf_action); wlen = skb_network_offset(skb); - if (tc_skb_protocol(skb) == htons(ETH_P_IP)) { + switch (skb_protocol(skb, true)) { + case htons(ETH_P_IP): wlen += sizeof(struct iphdr); if (!pskb_may_pull(skb, wlen)) goto out; proto = NFPROTO_IPV4; - } else if (tc_skb_protocol(skb) == htons(ETH_P_IPV6)) { + break; + case htons(ETH_P_IPV6): wlen += sizeof(struct ipv6hdr); if (!pskb_may_pull(skb, wlen)) goto out; proto = NFPROTO_IPV6; - } else { + break; + default: goto out; } @@ -266,9 +269,6 @@ static int tcf_ctinfo_init(struct net *net, struct nlattr *nla, if (cp_new) kfree_rcu(cp_new, rcu); - if (ret == ACT_P_CREATED) - tcf_idr_insert(tn, *a); - return ret; put_chain: diff --git a/net/sched/act_gact.c b/net/sched/act_gact.c index 324f1d1f6d47..faf68a44b845 100644 --- a/net/sched/act_gact.c +++ b/net/sched/act_gact.c @@ -139,8 +139,6 @@ static int tcf_gact_init(struct net *net, struct nlattr *nla, if (goto_ch) tcf_chain_put_by_act(goto_ch); - if (ret == ACT_P_CREATED) - tcf_idr_insert(tn, *a); return ret; release_idr: tcf_idr_release(*a, bind); diff --git a/net/sched/act_ife.c b/net/sched/act_ife.c index a0cfb4793c93..488d10476e85 100644 --- a/net/sched/act_ife.c +++ b/net/sched/act_ife.c @@ -436,6 +436,25 @@ static void tcf_ife_cleanup(struct tc_action *a) kfree_rcu(p, rcu); } +static int load_metalist(struct nlattr **tb, bool rtnl_held) +{ + int i; + + for (i = 1; i < max_metacnt; i++) { + if (tb[i]) { + void *val = nla_data(tb[i]); + int len = nla_len(tb[i]); + int rc; + + rc = load_metaops_and_vet(i, val, len, rtnl_held); + if (rc != 0) + return rc; + } + } + + return 0; +} + static int populate_metalist(struct tcf_ife_info *ife, struct nlattr **tb, bool exists, bool rtnl_held) { @@ -449,10 +468,6 @@ static int populate_metalist(struct tcf_ife_info *ife, struct nlattr **tb, val = nla_data(tb[i]); len = nla_len(tb[i]); - rc = load_metaops_and_vet(i, val, len, rtnl_held); - if (rc != 0) - return rc; - rc = add_metainfo(ife, i, val, len, exists); if (rc) return rc; @@ -508,6 +523,21 @@ static int tcf_ife_init(struct net *net, struct nlattr *nla, if (!p) return -ENOMEM; + if (tb[TCA_IFE_METALST]) { + err = nla_parse_nested_deprecated(tb2, IFE_META_MAX, + tb[TCA_IFE_METALST], NULL, + NULL); + if (err) { + kfree(p); + return err; + } + err = load_metalist(tb2, rtnl_held); + if (err) { + kfree(p); + return err; + } + } + index = parm->index; err = tcf_idr_check_alloc(tn, &index, a, bind); if (err < 0) { @@ -569,15 +599,9 @@ static int tcf_ife_init(struct net *net, struct nlattr *nla, } if (tb[TCA_IFE_METALST]) { - err = nla_parse_nested_deprecated(tb2, IFE_META_MAX, - tb[TCA_IFE_METALST], NULL, - NULL); - if (err) - goto metadata_parse_err; err = populate_metalist(ife, tb2, exists, rtnl_held); if (err) goto metadata_parse_err; - } else { /* if no passed metadata allow list or passed allow-all * then here we process by adding as many supported metadatum @@ -602,9 +626,6 @@ static int tcf_ife_init(struct net *net, struct nlattr *nla, if (p) kfree_rcu(p, rcu); - if (ret == ACT_P_CREATED) - tcf_idr_insert(tn, *a); - return ret; metadata_parse_err: if (goto_ch) diff --git a/net/sched/act_ipt.c b/net/sched/act_ipt.c index 214a03d405cf..02b0cb67643e 100644 --- a/net/sched/act_ipt.c +++ b/net/sched/act_ipt.c @@ -189,8 +189,6 @@ static int __tcf_ipt_init(struct net *net, unsigned int id, struct nlattr *nla, ipt->tcfi_t = t; ipt->tcfi_hook = hook; spin_unlock_bh(&ipt->tcf_lock); - if (ret == ACT_P_CREATED) - tcf_idr_insert(tn, *a); return ret; err3: diff --git a/net/sched/act_mirred.c b/net/sched/act_mirred.c index 27f624971121..8327ef9793ef 100644 --- a/net/sched/act_mirred.c +++ b/net/sched/act_mirred.c @@ -194,8 +194,6 @@ static int tcf_mirred_init(struct net *net, struct nlattr *nla, spin_lock(&mirred_list_lock); list_add(&m->tcfm_list, &mirred_list); spin_unlock(&mirred_list_lock); - - tcf_idr_insert(tn, *a); } return ret; diff --git a/net/sched/act_mpls.c b/net/sched/act_mpls.c index db570d2bd0e0..7954021ade33 100644 --- a/net/sched/act_mpls.c +++ b/net/sched/act_mpls.c @@ -82,7 +82,7 @@ static int tcf_mpls_act(struct sk_buff *skb, const struct tc_action *a, goto drop; break; case TCA_MPLS_ACT_PUSH: - new_lse = tcf_mpls_get_lse(NULL, p, !eth_p_mpls(skb->protocol)); + new_lse = tcf_mpls_get_lse(NULL, p, !eth_p_mpls(skb_protocol(skb, true))); if (skb_mpls_push(skb, new_lse, p->tcfm_proto, mac_len, skb->dev && skb->dev->type == ARPHRD_ETHER)) goto drop; @@ -273,8 +273,6 @@ static int tcf_mpls_init(struct net *net, struct nlattr *nla, if (p) kfree_rcu(p, rcu); - if (ret == ACT_P_CREATED) - tcf_idr_insert(tn, *a); return ret; put_chain: if (goto_ch) @@ -410,6 +408,7 @@ static void __exit mpls_cleanup_module(void) module_init(mpls_init_module); module_exit(mpls_cleanup_module); +MODULE_SOFTDEP("post: mpls_gso"); MODULE_AUTHOR("Netronome Systems <oss-drivers@netronome.com>"); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("MPLS manipulation actions"); diff --git a/net/sched/act_nat.c b/net/sched/act_nat.c index ea4c5359e7df..8b5d2360a4dc 100644 --- a/net/sched/act_nat.c +++ b/net/sched/act_nat.c @@ -93,9 +93,6 @@ static int tcf_nat_init(struct net *net, struct nlattr *nla, struct nlattr *est, if (goto_ch) tcf_chain_put_by_act(goto_ch); - if (ret == ACT_P_CREATED) - tcf_idr_insert(tn, *a); - return ret; release_idr: tcf_idr_release(*a, bind); diff --git a/net/sched/act_pedit.c b/net/sched/act_pedit.c index b5bc631b96b7..ff4f2437b592 100644 --- a/net/sched/act_pedit.c +++ b/net/sched/act_pedit.c @@ -237,8 +237,6 @@ static int tcf_pedit_init(struct net *net, struct nlattr *nla, spin_unlock_bh(&p->tcf_lock); if (goto_ch) tcf_chain_put_by_act(goto_ch); - if (ret == ACT_P_CREATED) - tcf_idr_insert(tn, *a); return ret; put_chain: diff --git a/net/sched/act_police.c b/net/sched/act_police.c index 89c04c52af3d..8fd23a8b88a5 100644 --- a/net/sched/act_police.c +++ b/net/sched/act_police.c @@ -201,8 +201,6 @@ static int tcf_police_init(struct net *net, struct nlattr *nla, if (new) kfree_rcu(new, rcu); - if (ret == ACT_P_CREATED) - tcf_idr_insert(tn, *a); return ret; failure: diff --git a/net/sched/act_sample.c b/net/sched/act_sample.c index 514456a0b9a8..74450b0f69fc 100644 --- a/net/sched/act_sample.c +++ b/net/sched/act_sample.c @@ -116,8 +116,6 @@ static int tcf_sample_init(struct net *net, struct nlattr *nla, if (goto_ch) tcf_chain_put_by_act(goto_ch); - if (ret == ACT_P_CREATED) - tcf_idr_insert(tn, *a); return ret; put_chain: if (goto_ch) diff --git a/net/sched/act_simple.c b/net/sched/act_simple.c index 6120e56117ca..6b0617de71c0 100644 --- a/net/sched/act_simple.c +++ b/net/sched/act_simple.c @@ -156,8 +156,6 @@ static int tcf_simp_init(struct net *net, struct nlattr *nla, goto release_idr; } - if (ret == ACT_P_CREATED) - tcf_idr_insert(tn, *a); return ret; put_chain: if (goto_ch) diff --git a/net/sched/act_skbedit.c b/net/sched/act_skbedit.c index 6a8d3337c577..f736da513d53 100644 --- a/net/sched/act_skbedit.c +++ b/net/sched/act_skbedit.c @@ -41,7 +41,7 @@ static int tcf_skbedit_act(struct sk_buff *skb, const struct tc_action *a, if (params->flags & SKBEDIT_F_INHERITDSFIELD) { int wlen = skb_network_offset(skb); - switch (tc_skb_protocol(skb)) { + switch (skb_protocol(skb, true)) { case htons(ETH_P_IP): wlen += sizeof(struct iphdr); if (!pskb_may_pull(skb, wlen)) @@ -214,8 +214,6 @@ static int tcf_skbedit_init(struct net *net, struct nlattr *nla, if (goto_ch) tcf_chain_put_by_act(goto_ch); - if (ret == ACT_P_CREATED) - tcf_idr_insert(tn, *a); return ret; put_chain: if (goto_ch) diff --git a/net/sched/act_skbmod.c b/net/sched/act_skbmod.c index 888437f97ba6..e858a0a9c045 100644 --- a/net/sched/act_skbmod.c +++ b/net/sched/act_skbmod.c @@ -190,8 +190,6 @@ static int tcf_skbmod_init(struct net *net, struct nlattr *nla, if (goto_ch) tcf_chain_put_by_act(goto_ch); - if (ret == ACT_P_CREATED) - tcf_idr_insert(tn, *a); return ret; put_chain: if (goto_ch) diff --git a/net/sched/act_tunnel_key.c b/net/sched/act_tunnel_key.c index d55669e14741..a5a2bf01eb9b 100644 --- a/net/sched/act_tunnel_key.c +++ b/net/sched/act_tunnel_key.c @@ -315,7 +315,7 @@ static int tunnel_key_init(struct net *net, struct nlattr *nla, metadata = __ipv6_tun_set_dst(&saddr, &daddr, tos, ttl, dst_port, 0, flags, - key_id, 0); + key_id, opts_len); } else { NL_SET_ERR_MSG(extack, "Missing either ipv4 or ipv6 src and dst"); ret = -EINVAL; @@ -392,9 +392,6 @@ static int tunnel_key_init(struct net *net, struct nlattr *nla, if (goto_ch) tcf_chain_put_by_act(goto_ch); - if (ret == ACT_P_CREATED) - tcf_idr_insert(tn, *a); - return ret; put_chain: diff --git a/net/sched/act_vlan.c b/net/sched/act_vlan.c index 08aaf719a70f..3c26042f4ea6 100644 --- a/net/sched/act_vlan.c +++ b/net/sched/act_vlan.c @@ -228,8 +228,6 @@ static int tcf_vlan_init(struct net *net, struct nlattr *nla, if (p) kfree_rcu(p, rcu); - if (ret == ACT_P_CREATED) - tcf_idr_insert(tn, *a); return ret; put_chain: if (goto_ch) diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index 68c8fc6f535c..d7604417367d 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -1571,7 +1571,7 @@ int tcf_classify(struct sk_buff *skb, const struct tcf_proto *tp, reclassify: #endif for (; tp; tp = rcu_dereference_bh(tp->next)) { - __be16 protocol = tc_skb_protocol(skb); + __be16 protocol = skb_protocol(skb, false); int err; if (tp->protocol != protocol && diff --git a/net/sched/cls_flow.c b/net/sched/cls_flow.c index 80ae7b9fa90a..ab53a93b2f2b 100644 --- a/net/sched/cls_flow.c +++ b/net/sched/cls_flow.c @@ -80,7 +80,7 @@ static u32 flow_get_dst(const struct sk_buff *skb, const struct flow_keys *flow) if (dst) return ntohl(dst); - return addr_fold(skb_dst(skb)) ^ (__force u16) tc_skb_protocol(skb); + return addr_fold(skb_dst(skb)) ^ (__force u16)skb_protocol(skb, true); } static u32 flow_get_proto(const struct sk_buff *skb, @@ -104,7 +104,7 @@ static u32 flow_get_proto_dst(const struct sk_buff *skb, if (flow->ports.ports) return ntohs(flow->ports.dst); - return addr_fold(skb_dst(skb)) ^ (__force u16) tc_skb_protocol(skb); + return addr_fold(skb_dst(skb)) ^ (__force u16)skb_protocol(skb, true); } static u32 flow_get_iif(const struct sk_buff *skb) @@ -151,7 +151,7 @@ static u32 flow_get_nfct(const struct sk_buff *skb) static u32 flow_get_nfct_src(const struct sk_buff *skb, const struct flow_keys *flow) { - switch (tc_skb_protocol(skb)) { + switch (skb_protocol(skb, true)) { case htons(ETH_P_IP): return ntohl(CTTUPLE(skb, src.u3.ip)); case htons(ETH_P_IPV6): @@ -164,7 +164,7 @@ fallback: static u32 flow_get_nfct_dst(const struct sk_buff *skb, const struct flow_keys *flow) { - switch (tc_skb_protocol(skb)) { + switch (skb_protocol(skb, true)) { case htons(ETH_P_IP): return ntohl(CTTUPLE(skb, dst.u3.ip)); case htons(ETH_P_IPV6): diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c index 1d270540e74d..c5a0f2c2635e 100644 --- a/net/sched/cls_flower.c +++ b/net/sched/cls_flower.c @@ -310,7 +310,7 @@ static int fl_classify(struct sk_buff *skb, const struct tcf_proto *tp, /* skb_flow_dissect() does not set n_proto in case an unknown * protocol, so do it rather here. */ - skb_key.basic.n_proto = skb->protocol; + skb_key.basic.n_proto = skb_protocol(skb, false); skb_flow_dissect_tunnel_info(skb, &mask->dissector, &skb_key); skb_flow_dissect_ct(skb, &mask->dissector, &skb_key, fl_ct_info_to_flower_map, diff --git a/net/sched/em_ipset.c b/net/sched/em_ipset.c index df00566d327d..c95cf86fb431 100644 --- a/net/sched/em_ipset.c +++ b/net/sched/em_ipset.c @@ -59,7 +59,7 @@ static int em_ipset_match(struct sk_buff *skb, struct tcf_ematch *em, }; int ret, network_offset; - switch (tc_skb_protocol(skb)) { + switch (skb_protocol(skb, true)) { case htons(ETH_P_IP): state.pf = NFPROTO_IPV4; if (!pskb_network_may_pull(skb, sizeof(struct iphdr))) diff --git a/net/sched/em_ipt.c b/net/sched/em_ipt.c index 9fff6480acc6..e2c157df3f8b 100644 --- a/net/sched/em_ipt.c +++ b/net/sched/em_ipt.c @@ -212,7 +212,7 @@ static int em_ipt_match(struct sk_buff *skb, struct tcf_ematch *em, struct nf_hook_state state; int ret; - switch (tc_skb_protocol(skb)) { + switch (skb_protocol(skb, true)) { case htons(ETH_P_IP): if (!pskb_network_may_pull(skb, sizeof(struct iphdr))) return 0; diff --git a/net/sched/em_meta.c b/net/sched/em_meta.c index 3177dcb17316..ad007cdcec97 100644 --- a/net/sched/em_meta.c +++ b/net/sched/em_meta.c @@ -195,7 +195,7 @@ META_COLLECTOR(int_priority) META_COLLECTOR(int_protocol) { /* Let userspace take care of the byte ordering */ - dst->value = tc_skb_protocol(skb); + dst->value = skb_protocol(skb, false); } META_COLLECTOR(int_pkttype) diff --git a/net/sched/sch_atm.c b/net/sched/sch_atm.c index f4f9b8cdbffb..6385995dc700 100644 --- a/net/sched/sch_atm.c +++ b/net/sched/sch_atm.c @@ -553,16 +553,16 @@ static int atm_tc_init(struct Qdisc *sch, struct nlattr *opt, if (!p->link.q) p->link.q = &noop_qdisc; pr_debug("atm_tc_init: link (%p) qdisc %p\n", &p->link, p->link.q); + p->link.vcc = NULL; + p->link.sock = NULL; + p->link.common.classid = sch->handle; + p->link.ref = 1; err = tcf_block_get(&p->link.block, &p->link.filter_list, sch, extack); if (err) return err; - p->link.vcc = NULL; - p->link.sock = NULL; - p->link.common.classid = sch->handle; - p->link.ref = 1; tasklet_init(&p->task, sch_atm_dequeue, (unsigned long)sch); return 0; } diff --git a/net/sched/sch_cake.c b/net/sched/sch_cake.c index 2277369feae5..896c0562cb42 100644 --- a/net/sched/sch_cake.c +++ b/net/sched/sch_cake.c @@ -592,7 +592,7 @@ static void cake_update_flowkeys(struct flow_keys *keys, struct nf_conntrack_tuple tuple = {}; bool rev = !skb->_nfct; - if (tc_skb_protocol(skb) != htons(ETH_P_IP)) + if (skb_protocol(skb, true) != htons(ETH_P_IP)) return; if (!nf_ct_get_tuple_skb(&tuple, skb)) @@ -1515,32 +1515,51 @@ static unsigned int cake_drop(struct Qdisc *sch, struct sk_buff **to_free) return idx + (tin << 16); } -static u8 cake_handle_diffserv(struct sk_buff *skb, u16 wash) +static u8 cake_handle_diffserv(struct sk_buff *skb, bool wash) { - int wlen = skb_network_offset(skb); + const int offset = skb_network_offset(skb); + u16 *buf, buf_; u8 dscp; - switch (tc_skb_protocol(skb)) { + switch (skb_protocol(skb, true)) { case htons(ETH_P_IP): - wlen += sizeof(struct iphdr); - if (!pskb_may_pull(skb, wlen) || - skb_try_make_writable(skb, wlen)) + buf = skb_header_pointer(skb, offset, sizeof(buf_), &buf_); + if (unlikely(!buf)) return 0; - dscp = ipv4_get_dsfield(ip_hdr(skb)) >> 2; - if (wash && dscp) + /* ToS is in the second byte of iphdr */ + dscp = ipv4_get_dsfield((struct iphdr *)buf) >> 2; + + if (wash && dscp) { + const int wlen = offset + sizeof(struct iphdr); + + if (!pskb_may_pull(skb, wlen) || + skb_try_make_writable(skb, wlen)) + return 0; + ipv4_change_dsfield(ip_hdr(skb), INET_ECN_MASK, 0); + } + return dscp; case htons(ETH_P_IPV6): - wlen += sizeof(struct ipv6hdr); - if (!pskb_may_pull(skb, wlen) || - skb_try_make_writable(skb, wlen)) + buf = skb_header_pointer(skb, offset, sizeof(buf_), &buf_); + if (unlikely(!buf)) return 0; - dscp = ipv6_get_dsfield(ipv6_hdr(skb)) >> 2; - if (wash && dscp) + /* Traffic class is in the first and second bytes of ipv6hdr */ + dscp = ipv6_get_dsfield((struct ipv6hdr *)buf) >> 2; + + if (wash && dscp) { + const int wlen = offset + sizeof(struct ipv6hdr); + + if (!pskb_may_pull(skb, wlen) || + skb_try_make_writable(skb, wlen)) + return 0; + ipv6_change_dsfield(ipv6_hdr(skb), INET_ECN_MASK, 0); + } + return dscp; case htons(ETH_P_ARP): @@ -1557,14 +1576,17 @@ static struct cake_tin_data *cake_select_tin(struct Qdisc *sch, { struct cake_sched_data *q = qdisc_priv(sch); u32 tin, mark; + bool wash; u8 dscp; /* Tin selection: Default to diffserv-based selection, allow overriding - * using firewall marks or skb->priority. + * using firewall marks or skb->priority. Call DSCP parsing early if + * wash is enabled, otherwise defer to below to skip unneeded parsing. */ - dscp = cake_handle_diffserv(skb, - q->rate_flags & CAKE_FLAG_WASH); mark = (skb->mark & q->fwmark_mask) >> q->fwmark_shft; + wash = !!(q->rate_flags & CAKE_FLAG_WASH); + if (wash) + dscp = cake_handle_diffserv(skb, wash); if (q->tin_mode == CAKE_DIFFSERV_BESTEFFORT) tin = 0; @@ -1578,6 +1600,8 @@ static struct cake_tin_data *cake_select_tin(struct Qdisc *sch, tin = q->tin_order[TC_H_MIN(skb->priority) - 1]; else { + if (!wash) + dscp = cake_handle_diffserv(skb, wash); tin = q->tin_index[dscp]; if (unlikely(tin >= q->tin_cnt)) @@ -2679,7 +2703,7 @@ static int cake_init(struct Qdisc *sch, struct nlattr *opt, qdisc_watchdog_init(&q->watchdog, sch); if (opt) { - int err = cake_change(sch, opt, extack); + err = cake_change(sch, opt, extack); if (err) return err; @@ -2996,7 +3020,7 @@ static int cake_dump_class_stats(struct Qdisc *sch, unsigned long cl, PUT_STAT_S32(BLUE_TIMER_US, ktime_to_us( ktime_sub(now, - flow->cvars.blue_timer))); + flow->cvars.blue_timer))); } if (flow->cvars.dropping) { PUT_STAT_S32(DROP_NEXT_US, diff --git a/net/sched/sch_dsmark.c b/net/sched/sch_dsmark.c index 05605b30bef3..2b88710994d7 100644 --- a/net/sched/sch_dsmark.c +++ b/net/sched/sch_dsmark.c @@ -210,7 +210,7 @@ static int dsmark_enqueue(struct sk_buff *skb, struct Qdisc *sch, if (p->set_tc_index) { int wlen = skb_network_offset(skb); - switch (tc_skb_protocol(skb)) { + switch (skb_protocol(skb, true)) { case htons(ETH_P_IP): wlen += sizeof(struct iphdr); if (!pskb_may_pull(skb, wlen) || @@ -303,7 +303,7 @@ static struct sk_buff *dsmark_dequeue(struct Qdisc *sch) index = skb->tc_index & (p->indices - 1); pr_debug("index %d->%d\n", skb->tc_index, index); - switch (tc_skb_protocol(skb)) { + switch (skb_protocol(skb, true)) { case htons(ETH_P_IP): ipv4_change_dsfield(ip_hdr(skb), p->mv[index].mask, p->mv[index].value); @@ -320,7 +320,7 @@ static struct sk_buff *dsmark_dequeue(struct Qdisc *sch) */ if (p->mv[index].mask != 0xff || p->mv[index].value) pr_warn("%s: unsupported protocol %d\n", - __func__, ntohs(tc_skb_protocol(skb))); + __func__, ntohs(skb_protocol(skb, true))); break; } diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c index f5cc6069131e..0623d88a1e16 100644 --- a/net/sched/sch_generic.c +++ b/net/sched/sch_generic.c @@ -476,6 +476,7 @@ void __netdev_watchdog_up(struct net_device *dev) dev_hold(dev); } } +EXPORT_SYMBOL_GPL(__netdev_watchdog_up); static void dev_watchdog_up(struct net_device *dev) { @@ -1132,27 +1133,36 @@ static void dev_deactivate_queue(struct net_device *dev, struct netdev_queue *dev_queue, void *_qdisc_default) { - struct Qdisc *qdisc_default = _qdisc_default; - struct Qdisc *qdisc; + struct Qdisc *qdisc = rtnl_dereference(dev_queue->qdisc); - qdisc = rtnl_dereference(dev_queue->qdisc); if (qdisc) { - bool nolock = qdisc->flags & TCQ_F_NOLOCK; - - if (nolock) - spin_lock_bh(&qdisc->seqlock); - spin_lock_bh(qdisc_lock(qdisc)); - if (!(qdisc->flags & TCQ_F_BUILTIN)) set_bit(__QDISC_STATE_DEACTIVATED, &qdisc->state); + } +} - rcu_assign_pointer(dev_queue->qdisc, qdisc_default); - qdisc_reset(qdisc); +static void dev_reset_queue(struct net_device *dev, + struct netdev_queue *dev_queue, + void *_unused) +{ + struct Qdisc *qdisc; + bool nolock; - spin_unlock_bh(qdisc_lock(qdisc)); - if (nolock) - spin_unlock_bh(&qdisc->seqlock); - } + qdisc = dev_queue->qdisc_sleeping; + if (!qdisc) + return; + + nolock = qdisc->flags & TCQ_F_NOLOCK; + + if (nolock) + spin_lock_bh(&qdisc->seqlock); + spin_lock_bh(qdisc_lock(qdisc)); + + qdisc_reset(qdisc); + + spin_unlock_bh(qdisc_lock(qdisc)); + if (nolock) + spin_unlock_bh(&qdisc->seqlock); } static bool some_qdisc_is_busy(struct net_device *dev) @@ -1213,12 +1223,20 @@ void dev_deactivate_many(struct list_head *head) dev_watchdog_down(dev); } - /* Wait for outstanding qdisc-less dev_queue_xmit calls. + /* Wait for outstanding qdisc-less dev_queue_xmit calls or + * outstanding qdisc enqueuing calls. * This is avoided if all devices are in dismantle phase : * Caller will call synchronize_net() for us */ synchronize_net(); + list_for_each_entry(dev, head, close_list) { + netdev_for_each_tx_queue(dev, dev_reset_queue, NULL); + + if (dev_ingress_queue(dev)) + dev_reset_queue(dev, dev_ingress_queue(dev), NULL); + } + /* Wait for outstanding qdisc_run calls. */ list_for_each_entry(dev, head, close_list) { while (some_qdisc_is_busy(dev)) diff --git a/net/sched/sch_netem.c b/net/sched/sch_netem.c index 42e557d48e4e..f4101a920d1f 100644 --- a/net/sched/sch_netem.c +++ b/net/sched/sch_netem.c @@ -330,7 +330,7 @@ static s64 tabledist(s64 mu, s32 sigma, /* default uniform distribution */ if (dist == NULL) - return ((rnd % (2 * sigma)) + mu) - sigma; + return ((rnd % (2 * (u32)sigma)) + mu) - sigma; t = dist->table[rnd % dist->size]; x = (sigma % NETEM_DIST_SCALE) * t; @@ -812,6 +812,10 @@ static void get_slot(struct netem_sched_data *q, const struct nlattr *attr) q->slot_config.max_packets = INT_MAX; if (q->slot_config.max_bytes == 0) q->slot_config.max_bytes = INT_MAX; + + /* capping dist_jitter to the range acceptable by tabledist() */ + q->slot_config.dist_jitter = min_t(__s64, INT_MAX, abs(q->slot_config.dist_jitter)); + q->slot.packets_left = q->slot_config.max_packets; q->slot.bytes_left = q->slot_config.max_bytes; if (q->slot_config.min_delay | q->slot_config.max_delay | @@ -1037,6 +1041,9 @@ static int netem_change(struct Qdisc *sch, struct nlattr *opt, if (tb[TCA_NETEM_SLOT]) get_slot(q, tb[TCA_NETEM_SLOT]); + /* capping jitter to the range acceptable by tabledist() */ + q->jitter = min_t(s64, abs(q->jitter), INT_MAX); + return ret; get_table_failure: diff --git a/net/sched/sch_taprio.c b/net/sched/sch_taprio.c index b1eb12d33b9a..2b797a71e9bd 100644 --- a/net/sched/sch_taprio.c +++ b/net/sched/sch_taprio.c @@ -777,9 +777,11 @@ static const struct nla_policy taprio_policy[TCA_TAPRIO_ATTR_MAX + 1] = { [TCA_TAPRIO_ATTR_TXTIME_DELAY] = { .type = NLA_U32 }, }; -static int fill_sched_entry(struct nlattr **tb, struct sched_entry *entry, +static int fill_sched_entry(struct taprio_sched *q, struct nlattr **tb, + struct sched_entry *entry, struct netlink_ext_ack *extack) { + int min_duration = length_to_duration(q, ETH_ZLEN); u32 interval = 0; if (tb[TCA_TAPRIO_SCHED_ENTRY_CMD]) @@ -794,7 +796,10 @@ static int fill_sched_entry(struct nlattr **tb, struct sched_entry *entry, interval = nla_get_u32( tb[TCA_TAPRIO_SCHED_ENTRY_INTERVAL]); - if (interval == 0) { + /* The interval should allow at least the minimum ethernet + * frame to go out. + */ + if (interval < min_duration) { NL_SET_ERR_MSG(extack, "Invalid interval for schedule entry"); return -EINVAL; } @@ -804,8 +809,9 @@ static int fill_sched_entry(struct nlattr **tb, struct sched_entry *entry, return 0; } -static int parse_sched_entry(struct nlattr *n, struct sched_entry *entry, - int index, struct netlink_ext_ack *extack) +static int parse_sched_entry(struct taprio_sched *q, struct nlattr *n, + struct sched_entry *entry, int index, + struct netlink_ext_ack *extack) { struct nlattr *tb[TCA_TAPRIO_SCHED_ENTRY_MAX + 1] = { }; int err; @@ -819,10 +825,10 @@ static int parse_sched_entry(struct nlattr *n, struct sched_entry *entry, entry->index = index; - return fill_sched_entry(tb, entry, extack); + return fill_sched_entry(q, tb, entry, extack); } -static int parse_sched_list(struct nlattr *list, +static int parse_sched_list(struct taprio_sched *q, struct nlattr *list, struct sched_gate_list *sched, struct netlink_ext_ack *extack) { @@ -847,7 +853,7 @@ static int parse_sched_list(struct nlattr *list, return -ENOMEM; } - err = parse_sched_entry(n, entry, i, extack); + err = parse_sched_entry(q, n, entry, i, extack); if (err < 0) { kfree(entry); return err; @@ -862,7 +868,7 @@ static int parse_sched_list(struct nlattr *list, return i; } -static int parse_taprio_schedule(struct nlattr **tb, +static int parse_taprio_schedule(struct taprio_sched *q, struct nlattr **tb, struct sched_gate_list *new, struct netlink_ext_ack *extack) { @@ -883,8 +889,8 @@ static int parse_taprio_schedule(struct nlattr **tb, new->cycle_time = nla_get_s64(tb[TCA_TAPRIO_ATTR_SCHED_CYCLE_TIME]); if (tb[TCA_TAPRIO_ATTR_SCHED_ENTRY_LIST]) - err = parse_sched_list( - tb[TCA_TAPRIO_ATTR_SCHED_ENTRY_LIST], new, extack); + err = parse_sched_list(q, tb[TCA_TAPRIO_ATTR_SCHED_ENTRY_LIST], + new, extack); if (err < 0) return err; @@ -1177,9 +1183,27 @@ static void taprio_offload_config_changed(struct taprio_sched *q) spin_unlock(&q->current_entry_lock); } -static void taprio_sched_to_offload(struct taprio_sched *q, +static u32 tc_map_to_queue_mask(struct net_device *dev, u32 tc_mask) +{ + u32 i, queue_mask = 0; + + for (i = 0; i < dev->num_tc; i++) { + u32 offset, count; + + if (!(tc_mask & BIT(i))) + continue; + + offset = dev->tc_to_txq[i].offset; + count = dev->tc_to_txq[i].count; + + queue_mask |= GENMASK(offset + count - 1, offset); + } + + return queue_mask; +} + +static void taprio_sched_to_offload(struct net_device *dev, struct sched_gate_list *sched, - const struct tc_mqprio_qopt *mqprio, struct tc_taprio_qopt_offload *offload) { struct sched_entry *entry; @@ -1194,7 +1218,8 @@ static void taprio_sched_to_offload(struct taprio_sched *q, e->command = entry->command; e->interval = entry->interval; - e->gate_mask = entry->gate_mask; + e->gate_mask = tc_map_to_queue_mask(dev, entry->gate_mask); + i++; } @@ -1202,7 +1227,6 @@ static void taprio_sched_to_offload(struct taprio_sched *q, } static int taprio_enable_offload(struct net_device *dev, - struct tc_mqprio_qopt *mqprio, struct taprio_sched *q, struct sched_gate_list *sched, struct netlink_ext_ack *extack) @@ -1224,7 +1248,7 @@ static int taprio_enable_offload(struct net_device *dev, return -ENOMEM; } offload->enable = 1; - taprio_sched_to_offload(q, sched, mqprio, offload); + taprio_sched_to_offload(dev, sched, offload); err = ops->ndo_setup_tc(dev, TC_SETUP_QDISC_TAPRIO, offload); if (err < 0) { @@ -1456,7 +1480,7 @@ static int taprio_change(struct Qdisc *sch, struct nlattr *opt, goto free_sched; } - err = parse_taprio_schedule(tb, new_admin, extack); + err = parse_taprio_schedule(q, tb, new_admin, extack); if (err < 0) goto free_sched; @@ -1486,7 +1510,7 @@ static int taprio_change(struct Qdisc *sch, struct nlattr *opt, } if (FULL_OFFLOAD_IS_ENABLED(q->flags)) - err = taprio_enable_offload(dev, mqprio, q, new_admin, extack); + err = taprio_enable_offload(dev, q, new_admin, extack); else err = taprio_disable_offload(dev, q, extack); if (err) diff --git a/net/sched/sch_teql.c b/net/sched/sch_teql.c index 689ef6f3ded8..2f1f0a378408 100644 --- a/net/sched/sch_teql.c +++ b/net/sched/sch_teql.c @@ -239,7 +239,7 @@ __teql_resolve(struct sk_buff *skb, struct sk_buff *skb_res, char haddr[MAX_ADDR_LEN]; neigh_ha_snapshot(haddr, n, dev); - err = dev_hard_header(skb, dev, ntohs(tc_skb_protocol(skb)), + err = dev_hard_header(skb, dev, ntohs(skb_protocol(skb, false)), haddr, NULL, skb->len); if (err < 0) diff --git a/net/sctp/associola.c b/net/sctp/associola.c index 41839b85c268..fb6f62264e87 100644 --- a/net/sctp/associola.c +++ b/net/sctp/associola.c @@ -1569,12 +1569,15 @@ void sctp_assoc_rwnd_decrease(struct sctp_association *asoc, unsigned int len) int sctp_assoc_set_bind_addr_from_ep(struct sctp_association *asoc, enum sctp_scope scope, gfp_t gfp) { + struct sock *sk = asoc->base.sk; int flags; /* Use scoping rules to determine the subset of addresses from * the endpoint. */ - flags = (PF_INET6 == asoc->base.sk->sk_family) ? SCTP_ADDR6_ALLOWED : 0; + flags = (PF_INET6 == sk->sk_family) ? SCTP_ADDR6_ALLOWED : 0; + if (!inet_v6_ipv6only(sk)) + flags |= SCTP_ADDR4_ALLOWED; if (asoc->peer.ipv4_address) flags |= SCTP_ADDR4_PEERSUPP; if (asoc->peer.ipv6_address) diff --git a/net/sctp/auth.c b/net/sctp/auth.c index 4278764d82b8..1d898ee4018c 100644 --- a/net/sctp/auth.c +++ b/net/sctp/auth.c @@ -494,6 +494,7 @@ int sctp_auth_init_hmacs(struct sctp_endpoint *ep, gfp_t gfp) out_err: /* Clean up any successful allocations */ sctp_auth_destroy_hmacs(ep->auth_hmacs); + ep->auth_hmacs = NULL; return -ENOMEM; } diff --git a/net/sctp/bind_addr.c b/net/sctp/bind_addr.c index 53bc61537f44..701c5a4e441d 100644 --- a/net/sctp/bind_addr.c +++ b/net/sctp/bind_addr.c @@ -461,6 +461,7 @@ static int sctp_copy_one_addr(struct net *net, struct sctp_bind_addr *dest, * well as the remote peer. */ if ((((AF_INET == addr->sa.sa_family) && + (flags & SCTP_ADDR4_ALLOWED) && (flags & SCTP_ADDR4_PEERSUPP))) || (((AF_INET6 == addr->sa.sa_family) && (flags & SCTP_ADDR6_ALLOWED) && diff --git a/net/sctp/outqueue.c b/net/sctp/outqueue.c index 0dab62b67b9a..adceb226ffab 100644 --- a/net/sctp/outqueue.c +++ b/net/sctp/outqueue.c @@ -36,6 +36,7 @@ #include <net/sctp/sctp.h> #include <net/sctp/sm.h> #include <net/sctp/stream_sched.h> +#include <trace/events/sctp.h> /* Declare internal functions here. */ static int sctp_acked(struct sctp_sackhdr *sack, __u32 tsn); @@ -1238,6 +1239,11 @@ int sctp_outq_sack(struct sctp_outq *q, struct sctp_chunk *chunk) /* Grab the association's destination address list. */ transport_list = &asoc->peer.transport_addr_list; + /* SCTP path tracepoint for congestion control debugging. */ + list_for_each_entry(transport, transport_list, transports) { + trace_sctp_probe_path(transport, asoc); + } + sack_ctsn = ntohl(sack->cum_tsn_ack); gap_ack_blocks = ntohs(sack->num_gap_ack_blocks); asoc->stats.gapcnt += gap_ack_blocks; diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c index 237c88eeb538..981c7cbca46a 100644 --- a/net/sctp/protocol.c +++ b/net/sctp/protocol.c @@ -148,7 +148,8 @@ int sctp_copy_local_addr_list(struct net *net, struct sctp_bind_addr *bp, * sock as well as the remote peer. */ if (addr->a.sa.sa_family == AF_INET && - !(copy_flags & SCTP_ADDR4_PEERSUPP)) + (!(copy_flags & SCTP_ADDR4_ALLOWED) || + !(copy_flags & SCTP_ADDR4_PEERSUPP))) continue; if (addr->a.sa.sa_family == AF_INET6 && (!(copy_flags & SCTP_ADDR6_ALLOWED) || diff --git a/net/sctp/socket.c b/net/sctp/socket.c index 58fe6556cdf5..1fcc13f6073e 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -8176,8 +8176,6 @@ static int sctp_get_port_local(struct sock *sk, union sctp_addr *addr) pr_debug("%s: begins, snum:%d\n", __func__, snum); - local_bh_disable(); - if (snum == 0) { /* Search for an available port. */ int low, high, remaining, index; @@ -8196,20 +8194,21 @@ static int sctp_get_port_local(struct sock *sk, union sctp_addr *addr) continue; index = sctp_phashfn(sock_net(sk), rover); head = &sctp_port_hashtable[index]; - spin_lock(&head->lock); + spin_lock_bh(&head->lock); sctp_for_each_hentry(pp, &head->chain) if ((pp->port == rover) && net_eq(sock_net(sk), pp->net)) goto next; break; next: - spin_unlock(&head->lock); + spin_unlock_bh(&head->lock); + cond_resched(); } while (--remaining > 0); /* Exhausted local port range during search? */ ret = 1; if (remaining <= 0) - goto fail; + return ret; /* OK, here is the one we will use. HEAD (the port * hash table list entry) is non-NULL and we hold it's @@ -8224,7 +8223,7 @@ static int sctp_get_port_local(struct sock *sk, union sctp_addr *addr) * port iterator, pp being NULL. */ head = &sctp_port_hashtable[sctp_phashfn(sock_net(sk), snum)]; - spin_lock(&head->lock); + spin_lock_bh(&head->lock); sctp_for_each_hentry(pp, &head->chain) { if ((pp->port == snum) && net_eq(pp->net, sock_net(sk))) goto pp_found; @@ -8324,10 +8323,7 @@ success: ret = 0; fail_unlock: - spin_unlock(&head->lock); - -fail: - local_bh_enable(); + spin_unlock_bh(&head->lock); return ret; } @@ -9341,13 +9337,10 @@ void sctp_copy_sock(struct sock *newsk, struct sock *sk, static inline void sctp_copy_descendant(struct sock *sk_to, const struct sock *sk_from) { - int ancestor_size = sizeof(struct inet_sock) + - sizeof(struct sctp_sock) - - offsetof(struct sctp_sock, pd_lobby); - - if (sk_from->sk_family == PF_INET6) - ancestor_size += sizeof(struct ipv6_pinfo); + size_t ancestor_size = sizeof(struct inet_sock); + ancestor_size += sk_from->sk_prot->obj_size; + ancestor_size -= offsetof(struct sctp_sock, pd_lobby); __inet_sk_copy_descendant(sk_to, sk_from, ancestor_size); } diff --git a/net/sctp/stream.c b/net/sctp/stream.c index c1a100d2fed3..cd20638b6151 100644 --- a/net/sctp/stream.c +++ b/net/sctp/stream.c @@ -22,17 +22,11 @@ #include <net/sctp/sm.h> #include <net/sctp/stream_sched.h> -/* Migrates chunks from stream queues to new stream queues if needed, - * but not across associations. Also, removes those chunks to streams - * higher than the new max. - */ -static void sctp_stream_outq_migrate(struct sctp_stream *stream, - struct sctp_stream *new, __u16 outcnt) +static void sctp_stream_shrink_out(struct sctp_stream *stream, __u16 outcnt) { struct sctp_association *asoc; struct sctp_chunk *ch, *temp; struct sctp_outq *outq; - int i; asoc = container_of(stream, struct sctp_association, stream); outq = &asoc->outqueue; @@ -56,6 +50,19 @@ static void sctp_stream_outq_migrate(struct sctp_stream *stream, sctp_chunk_free(ch); } +} + +/* Migrates chunks from stream queues to new stream queues if needed, + * but not across associations. Also, removes those chunks to streams + * higher than the new max. + */ +static void sctp_stream_outq_migrate(struct sctp_stream *stream, + struct sctp_stream *new, __u16 outcnt) +{ + int i; + + if (stream->outcnt > outcnt) + sctp_stream_shrink_out(stream, outcnt); if (new) { /* Here we actually move the old ext stuff into the new @@ -81,12 +88,13 @@ static int sctp_stream_alloc_out(struct sctp_stream *stream, __u16 outcnt, int ret; if (outcnt <= stream->outcnt) - return 0; + goto out; ret = genradix_prealloc(&stream->out, outcnt, gfp); if (ret) return ret; +out: stream->outcnt = outcnt; return 0; } @@ -97,12 +105,13 @@ static int sctp_stream_alloc_in(struct sctp_stream *stream, __u16 incnt, int ret; if (incnt <= stream->incnt) - return 0; + goto out; ret = genradix_prealloc(&stream->in, incnt, gfp); if (ret) return ret; +out: stream->incnt = incnt; return 0; } @@ -1038,11 +1047,13 @@ struct sctp_chunk *sctp_process_strreset_resp( nums = ntohs(addstrm->number_of_streams); number = stream->outcnt - nums; - if (result == SCTP_STRRESET_PERFORMED) + if (result == SCTP_STRRESET_PERFORMED) { for (i = number; i < stream->outcnt; i++) SCTP_SO(stream, i)->state = SCTP_STREAM_OPEN; - else + } else { + sctp_stream_shrink_out(stream, number); stream->outcnt = number; + } *evp = sctp_ulpevent_make_stream_change_event(asoc, flags, 0, nums, GFP_ATOMIC); diff --git a/net/smc/smc_core.c b/net/smc/smc_core.c index 0c5fcb8ed404..aeea67f90841 100644 --- a/net/smc/smc_core.c +++ b/net/smc/smc_core.c @@ -795,7 +795,7 @@ static struct smc_buf_desc *smcr_new_buf_create(struct smc_link_group *lgr, return buf_desc; } -#define SMCD_DMBE_SIZES 7 /* 0 -> 16KB, 1 -> 32KB, .. 6 -> 1MB */ +#define SMCD_DMBE_SIZES 6 /* 0 -> 16KB, 1 -> 32KB, .. 6 -> 1MB */ static struct smc_buf_desc *smcd_new_buf_create(struct smc_link_group *lgr, bool is_dmb, int bufsize) diff --git a/net/smc/smc_diag.c b/net/smc/smc_diag.c index e1f64f4ba236..da9ba6d1679b 100644 --- a/net/smc/smc_diag.c +++ b/net/smc/smc_diag.c @@ -170,13 +170,15 @@ static int __smc_diag_dump(struct sock *sk, struct sk_buff *skb, (req->diag_ext & (1 << (SMC_DIAG_DMBINFO - 1))) && !list_empty(&smc->conn.lgr->list)) { struct smc_connection *conn = &smc->conn; - struct smcd_diag_dmbinfo dinfo = { - .linkid = *((u32 *)conn->lgr->id), - .peer_gid = conn->lgr->peer_gid, - .my_gid = conn->lgr->smcd->local_gid, - .token = conn->rmb_desc->token, - .peer_token = conn->peer_token - }; + struct smcd_diag_dmbinfo dinfo; + + memset(&dinfo, 0, sizeof(dinfo)); + + dinfo.linkid = *((u32 *)conn->lgr->id); + dinfo.peer_gid = conn->lgr->peer_gid; + dinfo.my_gid = conn->lgr->smcd->local_gid; + dinfo.token = conn->rmb_desc->token; + dinfo.peer_token = conn->peer_token; if (nla_put(skb, SMC_DIAG_DMBINFO, sizeof(dinfo), &dinfo) < 0) goto errout; diff --git a/net/socket.c b/net/socket.c index 432800b39ddb..d1a0264401b7 100644 --- a/net/socket.c +++ b/net/socket.c @@ -485,7 +485,7 @@ static struct socket *sockfd_lookup_light(int fd, int *err, int *fput_needed) if (f.file) { sock = sock_from_file(f.file, err); if (likely(sock)) { - *fput_needed = f.flags; + *fput_needed = f.flags & FDPUT_FPUT; return sock; } fdput(f); diff --git a/net/sunrpc/addr.c b/net/sunrpc/addr.c index d024af4be85e..105d17af4abc 100644 --- a/net/sunrpc/addr.c +++ b/net/sunrpc/addr.c @@ -82,11 +82,11 @@ static size_t rpc_ntop6(const struct sockaddr *sap, rc = snprintf(scopebuf, sizeof(scopebuf), "%c%u", IPV6_SCOPE_DELIMITER, sin6->sin6_scope_id); - if (unlikely((size_t)rc > sizeof(scopebuf))) + if (unlikely((size_t)rc >= sizeof(scopebuf))) return 0; len += rc; - if (unlikely(len > buflen)) + if (unlikely(len >= buflen)) return 0; strcat(buf, scopebuf); diff --git a/net/sunrpc/auth_gss/gss_krb5_wrap.c b/net/sunrpc/auth_gss/gss_krb5_wrap.c index 683755d95075..78ad41656996 100644 --- a/net/sunrpc/auth_gss/gss_krb5_wrap.c +++ b/net/sunrpc/auth_gss/gss_krb5_wrap.c @@ -584,7 +584,7 @@ gss_unwrap_kerberos_v2(struct krb5_ctx *kctx, int offset, int len, buf->head[0].iov_len); memmove(ptr, ptr + GSS_KRB5_TOK_HDR_LEN + headskip, movelen); buf->head[0].iov_len -= GSS_KRB5_TOK_HDR_LEN + headskip; - buf->len = len - GSS_KRB5_TOK_HDR_LEN + headskip; + buf->len = len - (GSS_KRB5_TOK_HDR_LEN + headskip); /* Trim off the trailing "extra count" and checksum blob */ xdr_buf_trim(buf, ec + GSS_KRB5_TOK_HDR_LEN + tailskip); diff --git a/net/sunrpc/auth_gss/gss_mech_switch.c b/net/sunrpc/auth_gss/gss_mech_switch.c index 8fa924c8e282..9314999bf095 100644 --- a/net/sunrpc/auth_gss/gss_mech_switch.c +++ b/net/sunrpc/auth_gss/gss_mech_switch.c @@ -36,6 +36,8 @@ gss_mech_free(struct gss_api_mech *gm) for (i = 0; i < gm->gm_pf_num; i++) { pf = &gm->gm_pfs[i]; + if (pf->domain) + auth_domain_put(pf->domain); kfree(pf->auth_domain_name); pf->auth_domain_name = NULL; } @@ -58,6 +60,7 @@ make_auth_domain_name(char *name) static int gss_mech_svc_setup(struct gss_api_mech *gm) { + struct auth_domain *dom; struct pf_desc *pf; int i, status; @@ -67,10 +70,13 @@ gss_mech_svc_setup(struct gss_api_mech *gm) status = -ENOMEM; if (pf->auth_domain_name == NULL) goto out; - status = svcauth_gss_register_pseudoflavor(pf->pseudoflavor, - pf->auth_domain_name); - if (status) + dom = svcauth_gss_register_pseudoflavor( + pf->pseudoflavor, pf->auth_domain_name); + if (IS_ERR(dom)) { + status = PTR_ERR(dom); goto out; + } + pf->domain = dom; } return 0; out: diff --git a/net/sunrpc/auth_gss/svcauth_gss.c b/net/sunrpc/auth_gss/svcauth_gss.c index d9f7439e2431..cf4d6d7e7282 100644 --- a/net/sunrpc/auth_gss/svcauth_gss.c +++ b/net/sunrpc/auth_gss/svcauth_gss.c @@ -800,7 +800,7 @@ u32 svcauth_gss_flavor(struct auth_domain *dom) EXPORT_SYMBOL_GPL(svcauth_gss_flavor); -int +struct auth_domain * svcauth_gss_register_pseudoflavor(u32 pseudoflavor, char * name) { struct gss_domain *new; @@ -817,21 +817,23 @@ svcauth_gss_register_pseudoflavor(u32 pseudoflavor, char * name) new->h.flavour = &svcauthops_gss; new->pseudoflavor = pseudoflavor; - stat = 0; test = auth_domain_lookup(name, &new->h); - if (test != &new->h) { /* Duplicate registration */ + if (test != &new->h) { + pr_warn("svc: duplicate registration of gss pseudo flavour %s.\n", + name); + stat = -EADDRINUSE; auth_domain_put(test); - kfree(new->h.name); - goto out_free_dom; + goto out_free_name; } - return 0; + return test; +out_free_name: + kfree(new->h.name); out_free_dom: kfree(new); out: - return stat; + return ERR_PTR(stat); } - EXPORT_SYMBOL_GPL(svcauth_gss_register_pseudoflavor); static inline int @@ -947,7 +949,6 @@ unwrap_priv_data(struct svc_rqst *rqstp, struct xdr_buf *buf, u32 seq, struct gs maj_stat = gss_unwrap(ctx, 0, priv_len, buf); pad = priv_len - buf->len; - buf->len -= pad; /* The upper layers assume the buffer is aligned on 4-byte boundaries. * In the krb5p case, at least, the data ends up offset, so we need to * move it around. */ @@ -1094,9 +1095,9 @@ static int gss_read_proxy_verf(struct svc_rqst *rqstp, struct gssp_in_token *in_token) { struct kvec *argv = &rqstp->rq_arg.head[0]; - unsigned int page_base, length; - int pages, i, res; - size_t inlen; + unsigned int length, pgto_offs, pgfrom_offs; + int pages, i, res, pgto, pgfrom; + size_t inlen, to_offs, from_offs; res = gss_read_common_verf(gc, argv, authp, in_handle); if (res) @@ -1124,17 +1125,24 @@ static int gss_read_proxy_verf(struct svc_rqst *rqstp, memcpy(page_address(in_token->pages[0]), argv->iov_base, length); inlen -= length; - i = 1; - page_base = rqstp->rq_arg.page_base; + to_offs = length; + from_offs = rqstp->rq_arg.page_base; while (inlen) { - length = min_t(unsigned int, inlen, PAGE_SIZE); - memcpy(page_address(in_token->pages[i]), - page_address(rqstp->rq_arg.pages[i]) + page_base, + pgto = to_offs >> PAGE_SHIFT; + pgfrom = from_offs >> PAGE_SHIFT; + pgto_offs = to_offs & ~PAGE_MASK; + pgfrom_offs = from_offs & ~PAGE_MASK; + + length = min_t(unsigned int, inlen, + min_t(unsigned int, PAGE_SIZE - pgto_offs, + PAGE_SIZE - pgfrom_offs)); + memcpy(page_address(in_token->pages[pgto]) + pgto_offs, + page_address(rqstp->rq_arg.pages[pgfrom]) + pgfrom_offs, length); + to_offs += length; + from_offs += length; inlen -= length; - page_base = 0; - i++; } return 0; } diff --git a/net/sunrpc/rpc_pipe.c b/net/sunrpc/rpc_pipe.c index b71a39ded930..37792675ed57 100644 --- a/net/sunrpc/rpc_pipe.c +++ b/net/sunrpc/rpc_pipe.c @@ -1317,6 +1317,7 @@ rpc_gssd_dummy_populate(struct dentry *root, struct rpc_pipe *pipe_data) q.len = strlen(gssd_dummy_clnt_dir[0].name); clnt_dentry = d_hash_and_lookup(gssd_dentry, &q); if (!clnt_dentry) { + __rpc_depopulate(gssd_dentry, gssd_dummy_clnt_dir, 0, 1); pipe_dentry = ERR_PTR(-ENOENT); goto out; } diff --git a/net/sunrpc/rpcb_clnt.c b/net/sunrpc/rpcb_clnt.c index 4a020b688860..1db9f62e466d 100644 --- a/net/sunrpc/rpcb_clnt.c +++ b/net/sunrpc/rpcb_clnt.c @@ -988,8 +988,8 @@ static int rpcb_dec_getaddr(struct rpc_rqst *req, struct xdr_stream *xdr, p = xdr_inline_decode(xdr, len); if (unlikely(p == NULL)) goto out_fail; - dprintk("RPC: %5u RPCB_%s reply: %s\n", req->rq_task->tk_pid, - req->rq_task->tk_msg.rpc_proc->p_name, (char *)p); + dprintk("RPC: %5u RPCB_%s reply: %*pE\n", req->rq_task->tk_pid, + req->rq_task->tk_msg.rpc_proc->p_name, len, (char *)p); if (rpc_uaddr2sockaddr(req->rq_xprt->xprt_net, (char *)p, len, sap, sizeof(address)) == 0) diff --git a/net/sunrpc/sched.c b/net/sunrpc/sched.c index 987c4b1f0b17..53d8b82eda00 100644 --- a/net/sunrpc/sched.c +++ b/net/sunrpc/sched.c @@ -204,10 +204,6 @@ static void __rpc_add_wait_queue(struct rpc_wait_queue *queue, struct rpc_task *task, unsigned char queue_priority) { - WARN_ON_ONCE(RPC_IS_QUEUED(task)); - if (RPC_IS_QUEUED(task)) - return; - INIT_LIST_HEAD(&task->u.tk_wait.timer_list); if (RPC_IS_PRIORITY(queue)) __rpc_add_wait_queue_priority(queue, task, queue_priority); @@ -382,7 +378,7 @@ static void rpc_make_runnable(struct workqueue_struct *wq, * NB: An RPC task will only receive interrupt-driven events as long * as it's on a wait queue. */ -static void __rpc_sleep_on_priority(struct rpc_wait_queue *q, +static void __rpc_do_sleep_on_priority(struct rpc_wait_queue *q, struct rpc_task *task, unsigned char queue_priority) { @@ -395,12 +391,23 @@ static void __rpc_sleep_on_priority(struct rpc_wait_queue *q, } +static void __rpc_sleep_on_priority(struct rpc_wait_queue *q, + struct rpc_task *task, + unsigned char queue_priority) +{ + if (WARN_ON_ONCE(RPC_IS_QUEUED(task))) + return; + __rpc_do_sleep_on_priority(q, task, queue_priority); +} + static void __rpc_sleep_on_priority_timeout(struct rpc_wait_queue *q, struct rpc_task *task, unsigned long timeout, unsigned char queue_priority) { + if (WARN_ON_ONCE(RPC_IS_QUEUED(task))) + return; if (time_is_after_jiffies(timeout)) { - __rpc_sleep_on_priority(q, task, queue_priority); + __rpc_do_sleep_on_priority(q, task, queue_priority); __rpc_add_timer(q, task, timeout); } else task->tk_status = -ETIMEDOUT; @@ -824,6 +831,7 @@ rpc_reset_task_statistics(struct rpc_task *task) */ void rpc_exit_task(struct rpc_task *task) { + trace_rpc_task_end(task, task->tk_action); task->tk_action = NULL; if (task->tk_ops->rpc_count_stats) task->tk_ops->rpc_count_stats(task, task->tk_calldata); diff --git a/net/sunrpc/sunrpc.h b/net/sunrpc/sunrpc.h index c9bacb3c930f..82035fa65b8f 100644 --- a/net/sunrpc/sunrpc.h +++ b/net/sunrpc/sunrpc.h @@ -56,4 +56,5 @@ int svc_send_common(struct socket *sock, struct xdr_buf *xdr, int rpc_clients_notifier_register(void); void rpc_clients_notifier_unregister(void); +void auth_domain_cleanup(void); #endif /* _NET_SUNRPC_SUNRPC_H */ diff --git a/net/sunrpc/sunrpc_syms.c b/net/sunrpc/sunrpc_syms.c index f9edaa9174a4..236fadc4a439 100644 --- a/net/sunrpc/sunrpc_syms.c +++ b/net/sunrpc/sunrpc_syms.c @@ -23,6 +23,7 @@ #include <linux/sunrpc/rpc_pipe_fs.h> #include <linux/sunrpc/xprtsock.h> +#include "sunrpc.h" #include "netns.h" unsigned int sunrpc_net_id; @@ -131,6 +132,7 @@ cleanup_sunrpc(void) unregister_rpc_pipefs(); rpc_destroy_mempool(); unregister_pernet_subsys(&sunrpc_net_ops); + auth_domain_cleanup(); #if IS_ENABLED(CONFIG_SUNRPC_DEBUG) rpc_unregister_sysctl(); #endif diff --git a/net/sunrpc/svc.c b/net/sunrpc/svc.c index d11b70552c33..f0dcb6d14bbb 100644 --- a/net/sunrpc/svc.c +++ b/net/sunrpc/svc.c @@ -1635,6 +1635,22 @@ u32 svc_max_payload(const struct svc_rqst *rqstp) EXPORT_SYMBOL_GPL(svc_max_payload); /** + * svc_encode_read_payload - mark a range of bytes as a READ payload + * @rqstp: svc_rqst to operate on + * @offset: payload's byte offset in rqstp->rq_res + * @length: size of payload, in bytes + * + * Returns zero on success, or a negative errno if a permanent + * error occurred. + */ +int svc_encode_read_payload(struct svc_rqst *rqstp, unsigned int offset, + unsigned int length) +{ + return rqstp->rq_xprt->xpt_ops->xpo_read_payload(rqstp, offset, length); +} +EXPORT_SYMBOL_GPL(svc_encode_read_payload); + +/** * svc_fill_write_vector - Construct data argument for VFS write call * @rqstp: svc_rqst to operate on * @pages: list of pages containing data payload diff --git a/net/sunrpc/svc_xprt.c b/net/sunrpc/svc_xprt.c index dc74519286be..fe4cd0b4c412 100644 --- a/net/sunrpc/svc_xprt.c +++ b/net/sunrpc/svc_xprt.c @@ -104,8 +104,17 @@ void svc_unreg_xprt_class(struct svc_xprt_class *xcl) } EXPORT_SYMBOL_GPL(svc_unreg_xprt_class); -/* - * Format the transport list for printing +/** + * svc_print_xprts - Format the transport list for printing + * @buf: target buffer for formatted address + * @maxlen: length of target buffer + * + * Fills in @buf with a string containing a list of transport names, each name + * terminated with '\n'. If the buffer is too small, some entries may be + * missing, but it is guaranteed that all lines in the output buffer are + * complete. + * + * Returns positive length of the filled-in string. */ int svc_print_xprts(char *buf, int maxlen) { @@ -118,9 +127,9 @@ int svc_print_xprts(char *buf, int maxlen) list_for_each_entry(xcl, &svc_xprt_class_list, xcl_list) { int slen; - sprintf(tmpstr, "%s %d\n", xcl->xcl_name, xcl->xcl_max_payload); - slen = strlen(tmpstr); - if (len + slen > maxlen) + slen = snprintf(tmpstr, sizeof(tmpstr), "%s %d\n", + xcl->xcl_name, xcl->xcl_max_payload); + if (slen >= sizeof(tmpstr) || len + slen >= maxlen) break; len += slen; strcat(buf, tmpstr); diff --git a/net/sunrpc/svcauth.c b/net/sunrpc/svcauth.c index 550b214cb001..998b196b6176 100644 --- a/net/sunrpc/svcauth.c +++ b/net/sunrpc/svcauth.c @@ -19,6 +19,10 @@ #include <linux/err.h> #include <linux/hash.h> +#include <trace/events/sunrpc.h> + +#include "sunrpc.h" + #define RPCDBG_FACILITY RPCDBG_AUTH @@ -203,3 +207,26 @@ struct auth_domain *auth_domain_find(char *name) return NULL; } EXPORT_SYMBOL_GPL(auth_domain_find); + +/** + * auth_domain_cleanup - check that the auth_domain table is empty + * + * On module unload the auth_domain_table must be empty. To make it + * easier to catch bugs which don't clean up domains properly, we + * warn if anything remains in the table at cleanup time. + * + * Note that we cannot proactively remove the domains at this stage. + * The ->release() function might be in a module that has already been + * unloaded. + */ + +void auth_domain_cleanup(void) +{ + int h; + struct auth_domain *hp; + + for (h = 0; h < DN_HASHMAX; h++) + hlist_for_each_entry(hp, &auth_domain_table[h], hash) + pr_warn("svc: domain %s still present at module unload.\n", + hp->name); +} diff --git a/net/sunrpc/svcsock.c b/net/sunrpc/svcsock.c index 4260924ad9db..d52abde51f1b 100644 --- a/net/sunrpc/svcsock.c +++ b/net/sunrpc/svcsock.c @@ -279,6 +279,12 @@ out: return len; } +static int svc_sock_read_payload(struct svc_rqst *rqstp, unsigned int offset, + unsigned int length) +{ + return 0; +} + /* * Report socket names for nfsdfs */ @@ -655,6 +661,7 @@ static const struct svc_xprt_ops svc_udp_ops = { .xpo_create = svc_udp_create, .xpo_recvfrom = svc_udp_recvfrom, .xpo_sendto = svc_udp_sendto, + .xpo_read_payload = svc_sock_read_payload, .xpo_release_rqst = svc_release_udp_skb, .xpo_detach = svc_sock_detach, .xpo_free = svc_sock_free, @@ -1175,6 +1182,7 @@ static const struct svc_xprt_ops svc_tcp_ops = { .xpo_create = svc_tcp_create, .xpo_recvfrom = svc_tcp_recvfrom, .xpo_sendto = svc_tcp_sendto, + .xpo_read_payload = svc_sock_read_payload, .xpo_release_rqst = svc_release_skb, .xpo_detach = svc_tcp_sock_detach, .xpo_free = svc_sock_free, diff --git a/net/sunrpc/xdr.c b/net/sunrpc/xdr.c index 451ca7ec321c..7ef37054071f 100644 --- a/net/sunrpc/xdr.c +++ b/net/sunrpc/xdr.c @@ -1118,6 +1118,7 @@ xdr_buf_subsegment(struct xdr_buf *buf, struct xdr_buf *subbuf, base = 0; } else { base -= buf->head[0].iov_len; + subbuf->head[0].iov_base = buf->head[0].iov_base; subbuf->head[0].iov_len = 0; } @@ -1130,6 +1131,8 @@ xdr_buf_subsegment(struct xdr_buf *buf, struct xdr_buf *subbuf, base = 0; } else { base -= buf->page_len; + subbuf->pages = buf->pages; + subbuf->page_base = 0; subbuf->page_len = 0; } @@ -1141,6 +1144,7 @@ xdr_buf_subsegment(struct xdr_buf *buf, struct xdr_buf *subbuf, base = 0; } else { base -= buf->tail[0].iov_len; + subbuf->tail[0].iov_base = buf->tail[0].iov_base; subbuf->tail[0].iov_len = 0; } diff --git a/net/sunrpc/xprtrdma/rpc_rdma.c b/net/sunrpc/xprtrdma/rpc_rdma.c index ef5102b60589..21970185485f 100644 --- a/net/sunrpc/xprtrdma/rpc_rdma.c +++ b/net/sunrpc/xprtrdma/rpc_rdma.c @@ -71,7 +71,7 @@ static unsigned int rpcrdma_max_call_header_size(unsigned int maxsegs) size = RPCRDMA_HDRLEN_MIN; /* Maximum Read list size */ - size = maxsegs * rpcrdma_readchunk_maxsz * sizeof(__be32); + size += maxsegs * rpcrdma_readchunk_maxsz * sizeof(__be32); /* Minimal Read chunk size */ size += sizeof(__be32); /* segment count */ @@ -96,7 +96,7 @@ static unsigned int rpcrdma_max_reply_header_size(unsigned int maxsegs) size = RPCRDMA_HDRLEN_MIN; /* Maximum Write list size */ - size = sizeof(__be32); /* segment count */ + size += sizeof(__be32); /* segment count */ size += maxsegs * rpcrdma_segment_maxsz * sizeof(__be32); size += sizeof(__be32); /* list discriminator */ @@ -1246,8 +1246,7 @@ rpcrdma_decode_error(struct rpcrdma_xprt *r_xprt, struct rpcrdma_rep *rep, be32_to_cpup(p), be32_to_cpu(rep->rr_xid)); } - r_xprt->rx_stats.bad_reply_count++; - return -EREMOTEIO; + return -EIO; } /* Perform XID lookup, reconstruction of the RPC reply, and @@ -1284,13 +1283,11 @@ out: spin_unlock(&xprt->queue_lock); return; -/* If the incoming reply terminated a pending RPC, the next - * RPC call will post a replacement receive buffer as it is - * being marshaled. - */ out_badheader: trace_xprtrdma_reply_hdr(rep); r_xprt->rx_stats.bad_reply_count++; + rqst->rq_task->tk_status = status; + status = 0; goto out; } diff --git a/net/sunrpc/xprtrdma/svc_rdma_backchannel.c b/net/sunrpc/xprtrdma/svc_rdma_backchannel.c index cf80394b2db3..68d2dcf0a1be 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_backchannel.c +++ b/net/sunrpc/xprtrdma/svc_rdma_backchannel.c @@ -15,26 +15,25 @@ #undef SVCRDMA_BACKCHANNEL_DEBUG /** - * svc_rdma_handle_bc_reply - Process incoming backchannel reply - * @xprt: controlling backchannel transport - * @rdma_resp: pointer to incoming transport header - * @rcvbuf: XDR buffer into which to decode the reply + * svc_rdma_handle_bc_reply - Process incoming backchannel Reply + * @rqstp: resources for handling the Reply + * @rctxt: Received message * - * Returns: - * %0 if @rcvbuf is filled in, xprt_complete_rqst called, - * %-EAGAIN if server should call ->recvfrom again. */ -int svc_rdma_handle_bc_reply(struct rpc_xprt *xprt, __be32 *rdma_resp, - struct xdr_buf *rcvbuf) +void svc_rdma_handle_bc_reply(struct svc_rqst *rqstp, + struct svc_rdma_recv_ctxt *rctxt) { + struct svc_xprt *sxprt = rqstp->rq_xprt; + struct rpc_xprt *xprt = sxprt->xpt_bc_xprt; struct rpcrdma_xprt *r_xprt = rpcx_to_rdmax(xprt); + struct xdr_buf *rcvbuf = &rqstp->rq_arg; struct kvec *dst, *src = &rcvbuf->head[0]; + __be32 *rdma_resp = rctxt->rc_recv_buf; struct rpc_rqst *req; u32 credits; size_t len; __be32 xid; __be32 *p; - int ret; p = (__be32 *)src->iov_base; len = src->iov_len; @@ -49,14 +48,10 @@ int svc_rdma_handle_bc_reply(struct rpc_xprt *xprt, __be32 *rdma_resp, __func__, (int)len, p); #endif - ret = -EAGAIN; - if (src->iov_len < 24) - goto out_shortreply; - spin_lock(&xprt->queue_lock); req = xprt_lookup_rqst(xprt, xid); if (!req) - goto out_notfound; + goto out_unlock; dst = &req->rq_private_buf.head[0]; memcpy(&req->rq_private_buf, &req->rq_rcv_buf, sizeof(struct xdr_buf)); @@ -77,25 +72,12 @@ int svc_rdma_handle_bc_reply(struct rpc_xprt *xprt, __be32 *rdma_resp, spin_unlock(&xprt->transport_lock); spin_lock(&xprt->queue_lock); - ret = 0; xprt_complete_rqst(req->rq_task, rcvbuf->len); xprt_unpin_rqst(req); rcvbuf->len = 0; out_unlock: spin_unlock(&xprt->queue_lock); -out: - return ret; - -out_shortreply: - dprintk("svcrdma: short bc reply: xprt=%p, len=%zu\n", - xprt, src->iov_len); - goto out; - -out_notfound: - dprintk("svcrdma: unrecognized bc reply: xprt=%p, xid=%08x\n", - xprt, be32_to_cpu(xid)); - goto out_unlock; } /* Send a backwards direction RPC call. @@ -252,6 +234,7 @@ xprt_rdma_bc_put(struct rpc_xprt *xprt) { dprintk("svcrdma: %s: xprt %p\n", __func__, xprt); + xprt_rdma_free_addresses(xprt); xprt_free(xprt); } diff --git a/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c b/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c index b8ee91ffedda..fd5c1f1bb988 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c +++ b/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c @@ -193,6 +193,7 @@ svc_rdma_recv_ctxt_get(struct svcxprt_rdma *rdma) out: ctxt->rc_page_count = 0; + ctxt->rc_read_payload_length = 0; return ctxt; out_empty: @@ -264,6 +265,8 @@ static int svc_rdma_post_recv(struct svcxprt_rdma *rdma) { struct svc_rdma_recv_ctxt *ctxt; + if (test_bit(XPT_CLOSE, &rdma->sc_xprt.xpt_flags)) + return 0; ctxt = svc_rdma_recv_ctxt_get(rdma); if (!ctxt) return -ENOMEM; @@ -814,12 +817,9 @@ int svc_rdma_recvfrom(struct svc_rqst *rqstp) goto out_drop; rqstp->rq_xprt_hlen = ret; - if (svc_rdma_is_backchannel_reply(xprt, p)) { - ret = svc_rdma_handle_bc_reply(xprt->xpt_bc_xprt, p, - &rqstp->rq_arg); - svc_rdma_recv_ctxt_put(rdma_xprt, ctxt); - return ret; - } + if (svc_rdma_is_backchannel_reply(xprt, p)) + goto out_backchannel; + svc_rdma_get_inv_rkey(rdma_xprt, ctxt); p += rpcrdma_fixed_maxsz; @@ -849,6 +849,8 @@ out_postfail: svc_rdma_recv_ctxt_put(rdma_xprt, ctxt); return ret; +out_backchannel: + svc_rdma_handle_bc_reply(rqstp, ctxt); out_drop: svc_rdma_recv_ctxt_put(rdma_xprt, ctxt); return 0; diff --git a/net/sunrpc/xprtrdma/svc_rdma_rw.c b/net/sunrpc/xprtrdma/svc_rdma_rw.c index a59912e2666d..0bb3f0dca80d 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_rw.c +++ b/net/sunrpc/xprtrdma/svc_rdma_rw.c @@ -481,18 +481,19 @@ static int svc_rdma_send_xdr_kvec(struct svc_rdma_write_info *info, vec->iov_len); } -/* Send an xdr_buf's page list by itself. A Write chunk is - * just the page list. a Reply chunk is the head, page list, - * and tail. This function is shared between the two types - * of chunk. +/* Send an xdr_buf's page list by itself. A Write chunk is just + * the page list. A Reply chunk is @xdr's head, page list, and + * tail. This function is shared between the two types of chunk. */ static int svc_rdma_send_xdr_pagelist(struct svc_rdma_write_info *info, - struct xdr_buf *xdr) + struct xdr_buf *xdr, + unsigned int offset, + unsigned long length) { info->wi_xdr = xdr; - info->wi_next_off = 0; + info->wi_next_off = offset - xdr->head[0].iov_len; return svc_rdma_build_writes(info, svc_rdma_pagelist_to_sg, - xdr->page_len); + length); } /** @@ -500,6 +501,8 @@ static int svc_rdma_send_xdr_pagelist(struct svc_rdma_write_info *info, * @rdma: controlling RDMA transport * @wr_ch: Write chunk provided by client * @xdr: xdr_buf containing the data payload + * @offset: payload's byte offset in @xdr + * @length: size of payload, in bytes * * Returns a non-negative number of bytes the chunk consumed, or * %-E2BIG if the payload was larger than the Write chunk, @@ -509,19 +512,20 @@ static int svc_rdma_send_xdr_pagelist(struct svc_rdma_write_info *info, * %-EIO if rdma_rw initialization failed (DMA mapping, etc). */ int svc_rdma_send_write_chunk(struct svcxprt_rdma *rdma, __be32 *wr_ch, - struct xdr_buf *xdr) + struct xdr_buf *xdr, + unsigned int offset, unsigned long length) { struct svc_rdma_write_info *info; int ret; - if (!xdr->page_len) + if (!length) return 0; info = svc_rdma_write_info_alloc(rdma, wr_ch); if (!info) return -ENOMEM; - ret = svc_rdma_send_xdr_pagelist(info, xdr); + ret = svc_rdma_send_xdr_pagelist(info, xdr, offset, length); if (ret < 0) goto out_err; @@ -530,7 +534,7 @@ int svc_rdma_send_write_chunk(struct svcxprt_rdma *rdma, __be32 *wr_ch, goto out_err; trace_svcrdma_encode_write(xdr->page_len); - return xdr->page_len; + return length; out_err: svc_rdma_write_info_free(info); @@ -570,7 +574,9 @@ int svc_rdma_send_reply_chunk(struct svcxprt_rdma *rdma, __be32 *rp_ch, * client did not provide Write chunks. */ if (!writelist && xdr->page_len) { - ret = svc_rdma_send_xdr_pagelist(info, xdr); + ret = svc_rdma_send_xdr_pagelist(info, xdr, + xdr->head[0].iov_len, + xdr->page_len); if (ret < 0) goto out_err; consumed += xdr->page_len; @@ -671,7 +677,6 @@ static int svc_rdma_build_read_chunk(struct svc_rqst *rqstp, struct svc_rdma_read_info *info, __be32 *p) { - unsigned int i; int ret; ret = -EINVAL; @@ -694,12 +699,6 @@ static int svc_rdma_build_read_chunk(struct svc_rqst *rqstp, info->ri_chunklen += rs_length; } - /* Pages under I/O have been copied to head->rc_pages. - * Prevent their premature release by svc_xprt_release() . - */ - for (i = 0; i < info->ri_readctxt->rc_page_count; i++) - rqstp->rq_pages[i] = NULL; - return ret; } @@ -794,6 +793,26 @@ out: return ret; } +/* Pages under I/O have been copied to head->rc_pages. Ensure they + * are not released by svc_xprt_release() until the I/O is complete. + * + * This has to be done after all Read WRs are constructed to properly + * handle a page that is part of I/O on behalf of two different RDMA + * segments. + * + * Do this only if I/O has been posted. Otherwise, we do indeed want + * svc_xprt_release() to clean things up properly. + */ +static void svc_rdma_save_io_pages(struct svc_rqst *rqstp, + const unsigned int start, + const unsigned int num_pages) +{ + unsigned int i; + + for (i = start; i < num_pages + start; i++) + rqstp->rq_pages[i] = NULL; +} + /** * svc_rdma_recv_read_chunk - Pull a Read chunk from the client * @rdma: controlling RDMA transport @@ -847,6 +866,7 @@ int svc_rdma_recv_read_chunk(struct svcxprt_rdma *rdma, struct svc_rqst *rqstp, ret = svc_rdma_post_chunk_ctxt(&info->ri_cc); if (ret < 0) goto out_err; + svc_rdma_save_io_pages(rqstp, 0, head->rc_page_count); return 0; out_err: diff --git a/net/sunrpc/xprtrdma/svc_rdma_sendto.c b/net/sunrpc/xprtrdma/svc_rdma_sendto.c index 93ff7967389a..25e8922c10b2 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_sendto.c +++ b/net/sunrpc/xprtrdma/svc_rdma_sendto.c @@ -609,10 +609,11 @@ static int svc_rdma_pull_up_reply_msg(struct svcxprt_rdma *rdma, while (remaining) { len = min_t(u32, PAGE_SIZE - pageoff, remaining); - memcpy(dst, page_address(*ppages), len); + memcpy(dst, page_address(*ppages) + pageoff, len); remaining -= len; dst += len; pageoff = 0; + ppages++; } } @@ -856,7 +857,18 @@ int svc_rdma_sendto(struct svc_rqst *rqstp) if (wr_lst) { /* XXX: Presume the client sent only one Write chunk */ - ret = svc_rdma_send_write_chunk(rdma, wr_lst, xdr); + unsigned long offset; + unsigned int length; + + if (rctxt->rc_read_payload_length) { + offset = rctxt->rc_read_payload_offset; + length = rctxt->rc_read_payload_length; + } else { + offset = xdr->head[0].iov_len; + length = xdr->page_len; + } + ret = svc_rdma_send_write_chunk(rdma, wr_lst, xdr, offset, + length); if (ret < 0) goto err2; svc_rdma_xdr_encode_write_list(rdma_resp, wr_lst, ret); @@ -891,3 +903,30 @@ int svc_rdma_sendto(struct svc_rqst *rqstp) set_bit(XPT_CLOSE, &xprt->xpt_flags); return -ENOTCONN; } + +/** + * svc_rdma_read_payload - special processing for a READ payload + * @rqstp: svc_rqst to operate on + * @offset: payload's byte offset in @xdr + * @length: size of payload, in bytes + * + * Returns zero on success. + * + * For the moment, just record the xdr_buf location of the READ + * payload. svc_rdma_sendto will use that location later when + * we actually send the payload. + */ +int svc_rdma_read_payload(struct svc_rqst *rqstp, unsigned int offset, + unsigned int length) +{ + struct svc_rdma_recv_ctxt *rctxt = rqstp->rq_xprt_ctxt; + + /* XXX: Just one READ payload slot for now, since our + * transport implementation currently supports only one + * Write chunk. + */ + rctxt->rc_read_payload_offset = offset; + rctxt->rc_read_payload_length = length; + + return 0; +} diff --git a/net/sunrpc/xprtrdma/svc_rdma_transport.c b/net/sunrpc/xprtrdma/svc_rdma_transport.c index 889220f11a70..89a12676c59d 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_transport.c +++ b/net/sunrpc/xprtrdma/svc_rdma_transport.c @@ -81,6 +81,7 @@ static const struct svc_xprt_ops svc_rdma_ops = { .xpo_create = svc_rdma_create, .xpo_recvfrom = svc_rdma_recvfrom, .xpo_sendto = svc_rdma_sendto, + .xpo_read_payload = svc_rdma_read_payload, .xpo_release_rqst = svc_rdma_release_rqst, .xpo_detach = svc_rdma_detach, .xpo_free = svc_rdma_free, diff --git a/net/tipc/group.c b/net/tipc/group.c index 89257e2a980d..f53871baa42e 100644 --- a/net/tipc/group.c +++ b/net/tipc/group.c @@ -273,8 +273,8 @@ static struct tipc_member *tipc_group_find_node(struct tipc_group *grp, return NULL; } -static void tipc_group_add_to_tree(struct tipc_group *grp, - struct tipc_member *m) +static int tipc_group_add_to_tree(struct tipc_group *grp, + struct tipc_member *m) { u64 nkey, key = (u64)m->node << 32 | m->port; struct rb_node **n, *parent = NULL; @@ -291,10 +291,11 @@ static void tipc_group_add_to_tree(struct tipc_group *grp, else if (key > nkey) n = &(*n)->rb_right; else - return; + return -EEXIST; } rb_link_node(&m->tree_node, parent, n); rb_insert_color(&m->tree_node, &grp->members); + return 0; } static struct tipc_member *tipc_group_create_member(struct tipc_group *grp, @@ -302,6 +303,7 @@ static struct tipc_member *tipc_group_create_member(struct tipc_group *grp, u32 instance, int state) { struct tipc_member *m; + int ret; m = kzalloc(sizeof(*m), GFP_ATOMIC); if (!m) @@ -314,8 +316,12 @@ static struct tipc_member *tipc_group_create_member(struct tipc_group *grp, m->port = port; m->instance = instance; m->bc_acked = grp->bc_snd_nxt - 1; + ret = tipc_group_add_to_tree(grp, m); + if (ret < 0) { + kfree(m); + return NULL; + } grp->member_cnt++; - tipc_group_add_to_tree(grp, m); tipc_nlist_add(&grp->dests, m->node); m->state = state; return m; diff --git a/net/tipc/msg.c b/net/tipc/msg.c index 922d262e153f..46e89c992c2d 100644 --- a/net/tipc/msg.c +++ b/net/tipc/msg.c @@ -140,10 +140,11 @@ int tipc_buf_append(struct sk_buff **headbuf, struct sk_buff **buf) if (fragid == FIRST_FRAGMENT) { if (unlikely(head)) goto err; - if (unlikely(skb_unclone(frag, GFP_ATOMIC))) + *buf = NULL; + frag = skb_unshare(frag, GFP_ATOMIC); + if (unlikely(!frag)) goto err; head = *headbuf = frag; - *buf = NULL; TIPC_SKB_CB(head)->tail = NULL; if (skb_is_nonlinear(head)) { skb_walk_frags(head, tail) { diff --git a/net/tipc/netlink_compat.c b/net/tipc/netlink_compat.c index d4d2928424e2..11be9a84f8de 100644 --- a/net/tipc/netlink_compat.c +++ b/net/tipc/netlink_compat.c @@ -255,8 +255,9 @@ err_out: static int tipc_nl_compat_dumpit(struct tipc_nl_compat_cmd_dump *cmd, struct tipc_nl_compat_msg *msg) { - int err; + struct nlmsghdr *nlh; struct sk_buff *arg; + int err; if (msg->req_type && (!msg->req_size || !TLV_CHECK_TYPE(msg->req, msg->req_type))) @@ -285,6 +286,15 @@ static int tipc_nl_compat_dumpit(struct tipc_nl_compat_cmd_dump *cmd, return -ENOMEM; } + nlh = nlmsg_put(arg, 0, 0, tipc_genl_family.id, 0, NLM_F_MULTI); + if (!nlh) { + kfree_skb(arg); + kfree_skb(msg->rep); + msg->rep = NULL; + return -EMSGSIZE; + } + nlmsg_end(arg, nlh); + err = __tipc_nl_compat_dumpit(cmd, msg, arg); if (err) { kfree_skb(msg->rep); diff --git a/net/tipc/socket.c b/net/tipc/socket.c index aea951a1f805..66e8f89bce53 100644 --- a/net/tipc/socket.c +++ b/net/tipc/socket.c @@ -260,12 +260,12 @@ static void tipc_sk_respond(struct sock *sk, struct sk_buff *skb, int err) * * Caller must hold socket lock */ -static void tsk_rej_rx_queue(struct sock *sk) +static void tsk_rej_rx_queue(struct sock *sk, int error) { struct sk_buff *skb; while ((skb = __skb_dequeue(&sk->sk_receive_queue))) - tipc_sk_respond(sk, skb, TIPC_ERR_NO_PORT); + tipc_sk_respond(sk, skb, error); } static bool tipc_sk_connected(struct sock *sk) @@ -515,34 +515,45 @@ static void __tipc_shutdown(struct socket *sock, int error) /* Remove any pending SYN message */ __skb_queue_purge(&sk->sk_write_queue); - /* Reject all unreceived messages, except on an active connection - * (which disconnects locally & sends a 'FIN+' to peer). - */ - while ((skb = __skb_dequeue(&sk->sk_receive_queue)) != NULL) { - if (TIPC_SKB_CB(skb)->bytes_read) { - kfree_skb(skb); - continue; - } - if (!tipc_sk_type_connectionless(sk) && - sk->sk_state != TIPC_DISCONNECTING) { - tipc_set_sk_state(sk, TIPC_DISCONNECTING); - tipc_node_remove_conn(net, dnode, tsk->portid); - } - tipc_sk_respond(sk, skb, error); + /* Remove partially received buffer if any */ + skb = skb_peek(&sk->sk_receive_queue); + if (skb && TIPC_SKB_CB(skb)->bytes_read) { + __skb_unlink(skb, &sk->sk_receive_queue); + kfree_skb(skb); } - if (tipc_sk_type_connectionless(sk)) + /* Reject all unreceived messages if connectionless */ + if (tipc_sk_type_connectionless(sk)) { + tsk_rej_rx_queue(sk, error); return; + } - if (sk->sk_state != TIPC_DISCONNECTING) { + switch (sk->sk_state) { + case TIPC_CONNECTING: + case TIPC_ESTABLISHED: + tipc_set_sk_state(sk, TIPC_DISCONNECTING); + tipc_node_remove_conn(net, dnode, tsk->portid); + /* Send a FIN+/- to its peer */ + skb = __skb_dequeue(&sk->sk_receive_queue); + if (skb) { + __skb_queue_purge(&sk->sk_receive_queue); + tipc_sk_respond(sk, skb, error); + break; + } 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, error); if (skb) tipc_node_xmit_skb(net, skb, dnode, tsk->portid); - tipc_node_remove_conn(net, dnode, tsk->portid); - tipc_set_sk_state(sk, TIPC_DISCONNECTING); + break; + case TIPC_LISTEN: + /* Reject all SYN messages */ + tsk_rej_rx_queue(sk, error); + break; + default: + __skb_queue_purge(&sk->sk_receive_queue); + break; } } @@ -2564,7 +2575,7 @@ static int tipc_accept(struct socket *sock, struct socket *new_sock, int flags, * Reject any stray messages received by new socket * before the socket lock was taken (very, very unlikely) */ - tsk_rej_rx_queue(new_sk); + tsk_rej_rx_queue(new_sk, TIPC_ERR_NO_PORT); /* Connect new socket to it's peer */ tipc_sk_finish_conn(new_tsock, msg_origport(msg), msg_orignode(msg)); @@ -2616,18 +2627,18 @@ static int tipc_shutdown(struct socket *sock, int how) trace_tipc_sk_shutdown(sk, NULL, TIPC_DUMP_ALL, " "); __tipc_shutdown(sock, TIPC_CONN_SHUTDOWN); - sk->sk_shutdown = SEND_SHUTDOWN; + sk->sk_shutdown = SHUTDOWN_MASK; if (sk->sk_state == TIPC_DISCONNECTING) { /* Discard any unreceived messages */ __skb_queue_purge(&sk->sk_receive_queue); - /* Wake up anyone sleeping in poll */ - sk->sk_state_change(sk); res = 0; } else { res = -ENOTCONN; } + /* Wake up anyone sleeping in poll. */ + sk->sk_state_change(sk); release_sock(sk); return res; diff --git a/net/tipc/topsrv.c b/net/tipc/topsrv.c index 73dbed0c4b6b..931c426673c0 100644 --- a/net/tipc/topsrv.c +++ b/net/tipc/topsrv.c @@ -400,7 +400,9 @@ static int tipc_conn_rcv_from_sock(struct tipc_conn *con) return -EWOULDBLOCK; if (ret == sizeof(s)) { read_lock_bh(&sk->sk_callback_lock); - ret = tipc_conn_rcv_sub(srv, con, &s); + /* RACE: the connection can be closed in the meantime */ + if (likely(connected(con))) + ret = tipc_conn_rcv_sub(srv, con, &s); read_unlock_bh(&sk->sk_callback_lock); if (!ret) return 0; diff --git a/net/tls/tls_device.c b/net/tls/tls_device.c index 1adeb1c0473b..933a3187d3bf 100644 --- a/net/tls/tls_device.c +++ b/net/tls/tls_device.c @@ -405,14 +405,14 @@ static int tls_push_data(struct sock *sk, struct tls_context *tls_ctx = tls_get_ctx(sk); struct tls_prot_info *prot = &tls_ctx->prot_info; struct tls_offload_context_tx *ctx = tls_offload_ctx_tx(tls_ctx); - int more = flags & (MSG_SENDPAGE_NOTLAST | MSG_MORE); struct tls_record_info *record = ctx->open_record; int tls_push_record_flags; struct page_frag *pfrag; size_t orig_size = size; u32 max_open_record_len; - int copy, rc = 0; + bool more = false; bool done = false; + int copy, rc = 0; long timeo; if (flags & @@ -480,9 +480,8 @@ handle_error: if (!size) { last_record: tls_push_record_flags = flags; - if (more) { - tls_ctx->pending_open_record_frags = - !!record->num_frags; + if (flags & (MSG_SENDPAGE_NOTLAST | MSG_MORE)) { + more = true; break; } @@ -514,6 +513,8 @@ last_record: } } while (!done); + tls_ctx->pending_open_record_frags = more; + if (orig_size - size > 0) rc = orig_size - size; @@ -549,7 +550,7 @@ int tls_device_sendpage(struct sock *sk, struct page *page, { struct tls_context *tls_ctx = tls_get_ctx(sk); struct iov_iter msg_iter; - char *kaddr = kmap(page); + char *kaddr; struct kvec iov; int rc; @@ -564,6 +565,7 @@ int tls_device_sendpage(struct sock *sk, struct page *page, goto out; } + kaddr = kmap(page); iov.iov_base = kaddr + offset; iov.iov_len = size; iov_iter_kvec(&msg_iter, WRITE, &iov, 1, size); diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c index fbf6a496ee8b..515d295309a8 100644 --- a/net/tls/tls_sw.c +++ b/net/tls/tls_sw.c @@ -1737,6 +1737,7 @@ int tls_sw_recvmsg(struct sock *sk, long timeo; bool is_kvec = iov_iter_is_kvec(&msg->msg_iter); bool is_peek = flags & MSG_PEEK; + bool bpf_strp_enabled; int num_async = 0; int pending; @@ -1747,6 +1748,7 @@ int tls_sw_recvmsg(struct sock *sk, psock = sk_psock_get(sk); lock_sock(sk); + bpf_strp_enabled = sk_psock_strp_enabled(psock); /* Process pending decrypted records. It must be non-zero-copy */ err = process_rx_list(ctx, msg, &control, &cmsg, 0, len, false, @@ -1800,11 +1802,12 @@ int tls_sw_recvmsg(struct sock *sk, if (to_decrypt <= len && !is_kvec && !is_peek && ctx->control == TLS_RECORD_TYPE_DATA && - prot->version != TLS_1_3_VERSION) + prot->version != TLS_1_3_VERSION && + !bpf_strp_enabled) zc = true; /* Do not use async mode if record is non-data */ - if (ctx->control == TLS_RECORD_TYPE_DATA) + if (ctx->control == TLS_RECORD_TYPE_DATA && !bpf_strp_enabled) async_capable = ctx->async_capable; else async_capable = false; @@ -1854,6 +1857,19 @@ int tls_sw_recvmsg(struct sock *sk, goto pick_next_record; if (!zc) { + if (bpf_strp_enabled) { + err = sk_psock_tls_strp_read(psock, skb); + if (err != __SK_PASS) { + rxm->offset = rxm->offset + rxm->full_len; + rxm->full_len = 0; + if (err == __SK_DROP) + consume_skb(skb); + ctx->recv_pkt = NULL; + __strp_unpause(&ctx->strp); + continue; + } + } + if (rxm->full_len > len) { retain_skb = true; chunk = len; @@ -2121,10 +2137,15 @@ void tls_sw_release_resources_tx(struct sock *sk) struct tls_context *tls_ctx = tls_get_ctx(sk); struct tls_sw_context_tx *ctx = tls_sw_ctx_tx(tls_ctx); struct tls_rec *rec, *tmp; + int pending; /* Wait for any pending async encryptions to complete */ - smp_store_mb(ctx->async_notify, true); - if (atomic_read(&ctx->encrypt_pending)) + spin_lock_bh(&ctx->encrypt_compl_lock); + ctx->async_notify = true; + pending = atomic_read(&ctx->encrypt_pending); + spin_unlock_bh(&ctx->encrypt_compl_lock); + + if (pending) crypto_wait_req(-EINPROGRESS, &ctx->async_wait); tls_tx_records(sk, -1); diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index b3369d678f1a..ecadd9e482c4 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -189,11 +189,17 @@ static inline int unix_may_send(struct sock *sk, struct sock *osk) return unix_peer(osk) == NULL || unix_our_peer(sk, osk); } -static inline int unix_recvq_full(struct sock const *sk) +static inline int unix_recvq_full(const struct sock *sk) { return skb_queue_len(&sk->sk_receive_queue) > sk->sk_max_ack_backlog; } +static inline int unix_recvq_full_lockless(const struct sock *sk) +{ + return skb_queue_len_lockless(&sk->sk_receive_queue) > + READ_ONCE(sk->sk_max_ack_backlog); +} + struct sock *unix_peer_get(struct sock *s) { struct sock *peer; @@ -1724,7 +1730,8 @@ restart_locked: * - unix_peer(sk) == sk by time of get but disconnected before lock */ if (other != sk && - unlikely(unix_peer(other) != sk && unix_recvq_full(other))) { + unlikely(unix_peer(other) != sk && + unix_recvq_full_lockless(other))) { if (timeo) { timeo = unix_wait_for_peer(other, timeo); diff --git a/net/vmw_vsock/virtio_transport.c b/net/vmw_vsock/virtio_transport.c index 082a30936690..5905f0cddc89 100644 --- a/net/vmw_vsock/virtio_transport.c +++ b/net/vmw_vsock/virtio_transport.c @@ -22,7 +22,7 @@ #include <net/af_vsock.h> static struct workqueue_struct *virtio_vsock_workqueue; -static struct virtio_vsock *the_virtio_vsock; +static struct virtio_vsock __rcu *the_virtio_vsock; static DEFINE_MUTEX(the_virtio_vsock_mutex); /* protects the_virtio_vsock */ struct virtio_vsock { @@ -86,33 +86,6 @@ out_rcu: return ret; } -static void virtio_transport_loopback_work(struct work_struct *work) -{ - struct virtio_vsock *vsock = - container_of(work, struct virtio_vsock, loopback_work); - LIST_HEAD(pkts); - - spin_lock_bh(&vsock->loopback_list_lock); - list_splice_init(&vsock->loopback_list, &pkts); - spin_unlock_bh(&vsock->loopback_list_lock); - - mutex_lock(&vsock->rx_lock); - - if (!vsock->rx_run) - goto out; - - while (!list_empty(&pkts)) { - struct virtio_vsock_pkt *pkt; - - pkt = list_first_entry(&pkts, struct virtio_vsock_pkt, list); - list_del_init(&pkt->list); - - virtio_transport_recv_pkt(pkt); - } -out: - mutex_unlock(&vsock->rx_lock); -} - static int virtio_transport_send_pkt_loopback(struct virtio_vsock *vsock, struct virtio_vsock_pkt *pkt) { @@ -370,59 +343,6 @@ static bool virtio_transport_more_replies(struct virtio_vsock *vsock) return val < virtqueue_get_vring_size(vq); } -static void virtio_transport_rx_work(struct work_struct *work) -{ - struct virtio_vsock *vsock = - container_of(work, struct virtio_vsock, rx_work); - struct virtqueue *vq; - - vq = vsock->vqs[VSOCK_VQ_RX]; - - mutex_lock(&vsock->rx_lock); - - if (!vsock->rx_run) - goto out; - - do { - virtqueue_disable_cb(vq); - for (;;) { - struct virtio_vsock_pkt *pkt; - unsigned int len; - - if (!virtio_transport_more_replies(vsock)) { - /* Stop rx until the device processes already - * pending replies. Leave rx virtqueue - * callbacks disabled. - */ - goto out; - } - - pkt = virtqueue_get_buf(vq, &len); - if (!pkt) { - break; - } - - vsock->rx_buf_nr--; - - /* Drop short/long packets */ - if (unlikely(len < sizeof(pkt->hdr) || - len > sizeof(pkt->hdr) + pkt->len)) { - virtio_transport_free_pkt(pkt); - continue; - } - - pkt->len = len - sizeof(pkt->hdr); - virtio_transport_deliver_tap_pkt(pkt); - virtio_transport_recv_pkt(pkt); - } - } while (!virtqueue_enable_cb(vq)); - -out: - if (vsock->rx_buf_nr < vsock->rx_buf_max_nr / 2) - virtio_vsock_rx_fill(vsock); - mutex_unlock(&vsock->rx_lock); -} - /* event_lock must be held */ static int virtio_vsock_event_fill_one(struct virtio_vsock *vsock, struct virtio_vsock_event *event) @@ -586,6 +506,86 @@ static struct virtio_transport virtio_transport = { .send_pkt = virtio_transport_send_pkt, }; +static void virtio_transport_loopback_work(struct work_struct *work) +{ + struct virtio_vsock *vsock = + container_of(work, struct virtio_vsock, loopback_work); + LIST_HEAD(pkts); + + spin_lock_bh(&vsock->loopback_list_lock); + list_splice_init(&vsock->loopback_list, &pkts); + spin_unlock_bh(&vsock->loopback_list_lock); + + mutex_lock(&vsock->rx_lock); + + if (!vsock->rx_run) + goto out; + + while (!list_empty(&pkts)) { + struct virtio_vsock_pkt *pkt; + + pkt = list_first_entry(&pkts, struct virtio_vsock_pkt, list); + list_del_init(&pkt->list); + + virtio_transport_recv_pkt(&virtio_transport, pkt); + } +out: + mutex_unlock(&vsock->rx_lock); +} + +static void virtio_transport_rx_work(struct work_struct *work) +{ + struct virtio_vsock *vsock = + container_of(work, struct virtio_vsock, rx_work); + struct virtqueue *vq; + + vq = vsock->vqs[VSOCK_VQ_RX]; + + mutex_lock(&vsock->rx_lock); + + if (!vsock->rx_run) + goto out; + + do { + virtqueue_disable_cb(vq); + for (;;) { + struct virtio_vsock_pkt *pkt; + unsigned int len; + + if (!virtio_transport_more_replies(vsock)) { + /* Stop rx until the device processes already + * pending replies. Leave rx virtqueue + * callbacks disabled. + */ + goto out; + } + + pkt = virtqueue_get_buf(vq, &len); + if (!pkt) { + break; + } + + vsock->rx_buf_nr--; + + /* Drop short/long packets */ + if (unlikely(len < sizeof(pkt->hdr) || + len > sizeof(pkt->hdr) + pkt->len)) { + virtio_transport_free_pkt(pkt); + continue; + } + + pkt->len = len - sizeof(pkt->hdr); + virtio_transport_deliver_tap_pkt(pkt); + virtio_transport_recv_pkt(&virtio_transport, pkt); + } + } while (!virtqueue_enable_cb(vq)); + +out: + if (vsock->rx_buf_nr < vsock->rx_buf_max_nr / 2) + virtio_vsock_rx_fill(vsock); + mutex_unlock(&vsock->rx_lock); +} + static int virtio_vsock_probe(struct virtio_device *vdev) { vq_callback_t *callbacks[] = { diff --git a/net/vmw_vsock/virtio_transport_common.c b/net/vmw_vsock/virtio_transport_common.c index fb2060dffb0a..efbb521bff13 100644 --- a/net/vmw_vsock/virtio_transport_common.c +++ b/net/vmw_vsock/virtio_transport_common.c @@ -696,9 +696,9 @@ static int virtio_transport_reset(struct vsock_sock *vsk, /* Normally packets are associated with a socket. There may be no socket if an * attempt was made to connect to a socket that does not exist. */ -static int virtio_transport_reset_no_sock(struct virtio_vsock_pkt *pkt) +static int virtio_transport_reset_no_sock(const struct virtio_transport *t, + struct virtio_vsock_pkt *pkt) { - const struct virtio_transport *t; struct virtio_vsock_pkt *reply; struct virtio_vsock_pkt_info info = { .op = VIRTIO_VSOCK_OP_RST, @@ -718,7 +718,6 @@ static int virtio_transport_reset_no_sock(struct virtio_vsock_pkt *pkt) if (!reply) return -ENOMEM; - t = virtio_transport_get_ops(); if (!t) { virtio_transport_free_pkt(reply); return -ENOTCONN; @@ -1060,7 +1059,8 @@ static bool virtio_transport_space_update(struct sock *sk, /* We are under the virtio-vsock's vsock->rx_lock or vhost-vsock's vq->mutex * lock. */ -void virtio_transport_recv_pkt(struct virtio_vsock_pkt *pkt) +void virtio_transport_recv_pkt(struct virtio_transport *t, + struct virtio_vsock_pkt *pkt) { struct sockaddr_vm src, dst; struct vsock_sock *vsk; @@ -1082,7 +1082,7 @@ void virtio_transport_recv_pkt(struct virtio_vsock_pkt *pkt) le32_to_cpu(pkt->hdr.fwd_cnt)); if (le16_to_cpu(pkt->hdr.type) != VIRTIO_VSOCK_TYPE_STREAM) { - (void)virtio_transport_reset_no_sock(pkt); + (void)virtio_transport_reset_no_sock(t, pkt); goto free_pkt; } @@ -1093,7 +1093,7 @@ void virtio_transport_recv_pkt(struct virtio_vsock_pkt *pkt) if (!sk) { sk = vsock_find_bound_socket(&dst); if (!sk) { - (void)virtio_transport_reset_no_sock(pkt); + (void)virtio_transport_reset_no_sock(t, pkt); goto free_pkt; } } @@ -1127,6 +1127,7 @@ void virtio_transport_recv_pkt(struct virtio_vsock_pkt *pkt) virtio_transport_free_pkt(pkt); break; default: + (void)virtio_transport_reset_no_sock(t, pkt); virtio_transport_free_pkt(pkt); break; } diff --git a/net/wireless/Kconfig b/net/wireless/Kconfig index 593de9ae0d64..19959fb5df4e 100644 --- a/net/wireless/Kconfig +++ b/net/wireless/Kconfig @@ -217,6 +217,7 @@ config LIB80211_CRYPT_WEP config LIB80211_CRYPT_CCMP tristate + select CRYPTO select CRYPTO_AES select CRYPTO_CCM diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index b65180e874fb..672b70730e89 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -2227,7 +2227,10 @@ static int nl80211_send_wiphy(struct cfg80211_registered_device *rdev, * case we'll continue with more data in the next round, * but break unconditionally so unsplit data stops here. */ - state->split_start++; + if (state->split) + state->split_start++; + else + state->split_start = 0; break; case 9: if (rdev->wiphy.extended_capabilities && @@ -3975,6 +3978,9 @@ static int nl80211_del_key(struct sk_buff *skb, struct genl_info *info) if (err) return err; + if (key.idx < 0) + return -EINVAL; + if (info->attrs[NL80211_ATTR_MAC]) mac_addr = nla_data(info->attrs[NL80211_ATTR_MAC]); @@ -4493,16 +4499,14 @@ static int nl80211_parse_he_obss_pd(struct nlattr *attrs, if (err) return err; - if (!tb[NL80211_HE_OBSS_PD_ATTR_MIN_OFFSET] || - !tb[NL80211_HE_OBSS_PD_ATTR_MAX_OFFSET]) - return -EINVAL; + if (tb[NL80211_HE_OBSS_PD_ATTR_MIN_OFFSET]) + he_obss_pd->min_offset = + nla_get_u8(tb[NL80211_HE_OBSS_PD_ATTR_MIN_OFFSET]); + if (tb[NL80211_HE_OBSS_PD_ATTR_MAX_OFFSET]) + he_obss_pd->max_offset = + nla_get_u8(tb[NL80211_HE_OBSS_PD_ATTR_MAX_OFFSET]); - he_obss_pd->min_offset = - nla_get_u32(tb[NL80211_HE_OBSS_PD_ATTR_MIN_OFFSET]); - he_obss_pd->max_offset = - nla_get_u32(tb[NL80211_HE_OBSS_PD_ATTR_MAX_OFFSET]); - - if (he_obss_pd->min_offset >= he_obss_pd->max_offset) + if (he_obss_pd->min_offset > he_obss_pd->max_offset) return -EINVAL; he_obss_pd->enable = true; @@ -4798,7 +4802,8 @@ static int nl80211_start_ap(struct sk_buff *skb, struct genl_info *info) err = nl80211_parse_he_obss_pd( info->attrs[NL80211_ATTR_HE_OBSS_PD], ¶ms.he_obss_pd); - goto out; + if (err) + goto out; } nl80211_calculate_ap_params(¶ms); @@ -12948,13 +12953,13 @@ static int nl80211_vendor_cmd(struct sk_buff *skb, struct genl_info *info) if (!wdev_running(wdev)) return -ENETDOWN; } - - if (!vcmd->doit) - return -EOPNOTSUPP; } else { wdev = NULL; } + if (!vcmd->doit) + return -EOPNOTSUPP; + if (info->attrs[NL80211_ATTR_VENDOR_DATA]) { data = nla_data(info->attrs[NL80211_ATTR_VENDOR_DATA]); len = nla_len(info->attrs[NL80211_ATTR_VENDOR_DATA]); diff --git a/net/wireless/reg.c b/net/wireless/reg.c index b0e7dd04bbe9..7a75db7533f8 100644 --- a/net/wireless/reg.c +++ b/net/wireless/reg.c @@ -2941,6 +2941,9 @@ int regulatory_hint_user(const char *alpha2, if (WARN_ON(!alpha2)) return -EINVAL; + if (!is_world_regdom(alpha2) && !is_an_alpha2(alpha2)) + return -EINVAL; + request = kzalloc(sizeof(struct regulatory_request), GFP_KERNEL); if (!request) return -ENOMEM; diff --git a/net/wireless/util.c b/net/wireless/util.c index 82cf62d5156e..6c430d9df59a 100644 --- a/net/wireless/util.c +++ b/net/wireless/util.c @@ -116,11 +116,13 @@ int ieee80211_frequency_to_channel(int freq) return (freq - 2407) / 5; else if (freq >= 4910 && freq <= 4980) return (freq - 4000) / 5; - else if (freq < 5945) + else if (freq < 5925) return (freq - 5000) / 5; + else if (freq == 5935) + return 2; else if (freq <= 45000) /* DMG band lower limit */ - /* see 802.11ax D4.1 27.3.22.2 */ - return (freq - 5940) / 5; + /* see 802.11ax D6.1 27.3.22.2 */ + return (freq - 5950) / 5; else if (freq >= 58320 && freq <= 70200) return (freq - 56160) / 2160; else diff --git a/net/x25/x25_subr.c b/net/x25/x25_subr.c index 8aa415a38814..0285aaa1e93c 100644 --- a/net/x25/x25_subr.c +++ b/net/x25/x25_subr.c @@ -357,6 +357,12 @@ void x25_disconnect(struct sock *sk, int reason, unsigned char cause, sk->sk_state_change(sk); sock_set_flag(sk, SOCK_DEAD); } + if (x25->neighbour) { + read_lock_bh(&x25_list_lock); + x25_neigh_put(x25->neighbour); + x25->neighbour = NULL; + read_unlock_bh(&x25_list_lock); + } } /* diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c index 7181a30666b4..f9eb5efb237c 100644 --- a/net/xdp/xsk.c +++ b/net/xdp/xsk.c @@ -362,10 +362,8 @@ static int xsk_generic_xmit(struct sock *sk) len = desc.len; skb = sock_alloc_send_skb(sk, len, 1, &err); - if (unlikely(!skb)) { - err = -EAGAIN; + if (unlikely(!skb)) goto out; - } skb_put(skb, len); addr = desc.addr; diff --git a/net/xfrm/xfrm_device.c b/net/xfrm/xfrm_device.c index c365b918be35..bb2292b5260c 100644 --- a/net/xfrm/xfrm_device.c +++ b/net/xfrm/xfrm_device.c @@ -82,7 +82,7 @@ struct sk_buff *validate_xmit_xfrm(struct sk_buff *skb, netdev_features_t featur struct xfrm_offload *xo = xfrm_offload(skb); struct sec_path *sp; - if (!xo) + if (!xo || (xo->flags & XFRM_XMIT)) return skb; if (!(features & NETIF_F_HW_ESP)) @@ -103,6 +103,8 @@ struct sk_buff *validate_xmit_xfrm(struct sk_buff *skb, netdev_features_t featur return skb; } + xo->flags |= XFRM_XMIT; + if (skb_is_gso(skb)) { struct net_device *dev = skb->dev; diff --git a/net/xfrm/xfrm_interface.c b/net/xfrm/xfrm_interface.c index 0ab2b35c95de..00af31d3e774 100644 --- a/net/xfrm/xfrm_interface.c +++ b/net/xfrm/xfrm_interface.c @@ -293,7 +293,7 @@ xfrmi_xmit2(struct sk_buff *skb, struct net_device *dev, struct flowi *fl) } mtu = dst_mtu(dst); - if (!skb->ignore_df && skb->len > mtu) { + if (skb->len > mtu) { skb_dst_update_pmtu_no_confirm(skb, mtu); if (skb->protocol == htons(ETH_P_IPV6)) { diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index 6a1a21ae47bb..2917711ff8ab 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -1430,14 +1430,10 @@ static void xfrm_policy_requeue(struct xfrm_policy *old, spin_unlock_bh(&pq->hold_queue.lock); } -static bool xfrm_policy_mark_match(struct xfrm_policy *policy, - struct xfrm_policy *pol) +static inline bool xfrm_policy_mark_match(const struct xfrm_mark *mark, + struct xfrm_policy *pol) { - if (policy->mark.v == pol->mark.v && - policy->priority == pol->priority) - return true; - - return false; + return mark->v == pol->mark.v && mark->m == pol->mark.m; } static u32 xfrm_pol_bin_key(const void *data, u32 len, u32 seed) @@ -1500,7 +1496,7 @@ static void xfrm_policy_insert_inexact_list(struct hlist_head *chain, if (pol->type == policy->type && pol->if_id == policy->if_id && !selector_cmp(&pol->selector, &policy->selector) && - xfrm_policy_mark_match(policy, pol) && + xfrm_policy_mark_match(&policy->mark, pol) && xfrm_sec_ctx_match(pol->security, policy->security) && !WARN_ON(delpol)) { delpol = pol; @@ -1535,7 +1531,7 @@ static struct xfrm_policy *xfrm_policy_insert_list(struct hlist_head *chain, if (pol->type == policy->type && pol->if_id == policy->if_id && !selector_cmp(&pol->selector, &policy->selector) && - xfrm_policy_mark_match(policy, pol) && + xfrm_policy_mark_match(&policy->mark, pol) && xfrm_sec_ctx_match(pol->security, policy->security) && !WARN_ON(delpol)) { if (excl) @@ -1607,9 +1603,8 @@ int xfrm_policy_insert(int dir, struct xfrm_policy *policy, int excl) EXPORT_SYMBOL(xfrm_policy_insert); static struct xfrm_policy * -__xfrm_policy_bysel_ctx(struct hlist_head *chain, u32 mark, u32 if_id, - u8 type, int dir, - struct xfrm_selector *sel, +__xfrm_policy_bysel_ctx(struct hlist_head *chain, const struct xfrm_mark *mark, + u32 if_id, u8 type, int dir, struct xfrm_selector *sel, struct xfrm_sec_ctx *ctx) { struct xfrm_policy *pol; @@ -1620,7 +1615,7 @@ __xfrm_policy_bysel_ctx(struct hlist_head *chain, u32 mark, u32 if_id, hlist_for_each_entry(pol, chain, bydst) { if (pol->type == type && pol->if_id == if_id && - (mark & pol->mark.m) == pol->mark.v && + xfrm_policy_mark_match(mark, pol) && !selector_cmp(sel, &pol->selector) && xfrm_sec_ctx_match(ctx, pol->security)) return pol; @@ -1629,11 +1624,10 @@ __xfrm_policy_bysel_ctx(struct hlist_head *chain, u32 mark, u32 if_id, return NULL; } -struct xfrm_policy *xfrm_policy_bysel_ctx(struct net *net, u32 mark, u32 if_id, - u8 type, int dir, - struct xfrm_selector *sel, - struct xfrm_sec_ctx *ctx, int delete, - int *err) +struct xfrm_policy * +xfrm_policy_bysel_ctx(struct net *net, const struct xfrm_mark *mark, u32 if_id, + u8 type, int dir, struct xfrm_selector *sel, + struct xfrm_sec_ctx *ctx, int delete, int *err) { struct xfrm_pol_inexact_bin *bin = NULL; struct xfrm_policy *pol, *ret = NULL; @@ -1700,9 +1694,9 @@ struct xfrm_policy *xfrm_policy_bysel_ctx(struct net *net, u32 mark, u32 if_id, } EXPORT_SYMBOL(xfrm_policy_bysel_ctx); -struct xfrm_policy *xfrm_policy_byid(struct net *net, u32 mark, u32 if_id, - u8 type, int dir, u32 id, int delete, - int *err) +struct xfrm_policy * +xfrm_policy_byid(struct net *net, const struct xfrm_mark *mark, u32 if_id, + u8 type, int dir, u32 id, int delete, int *err) { struct xfrm_policy *pol, *ret; struct hlist_head *chain; @@ -1717,8 +1711,7 @@ struct xfrm_policy *xfrm_policy_byid(struct net *net, u32 mark, u32 if_id, ret = NULL; hlist_for_each_entry(pol, chain, byidx) { if (pol->type == type && pol->index == id && - pol->if_id == if_id && - (mark & pol->mark.m) == pol->mark.v) { + pol->if_id == if_id && xfrm_policy_mark_match(mark, pol)) { xfrm_pol_hold(pol); if (delete) { *err = security_xfrm_policy_delete( diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c index f3423562d933..aaea8cb7459d 100644 --- a/net/xfrm/xfrm_state.c +++ b/net/xfrm/xfrm_state.c @@ -1016,7 +1016,8 @@ static void xfrm_state_look_at(struct xfrm_policy *pol, struct xfrm_state *x, */ if (x->km.state == XFRM_STATE_VALID) { if ((x->sel.family && - !xfrm_selector_match(&x->sel, fl, x->sel.family)) || + (x->sel.family != family || + !xfrm_selector_match(&x->sel, fl, family))) || !security_xfrm_state_pol_flow_match(x, pol, fl)) return; @@ -1029,7 +1030,9 @@ static void xfrm_state_look_at(struct xfrm_policy *pol, struct xfrm_state *x, *acq_in_progress = 1; } else if (x->km.state == XFRM_STATE_ERROR || x->km.state == XFRM_STATE_EXPIRED) { - if (xfrm_selector_match(&x->sel, fl, x->sel.family) && + if ((!x->sel.family || + (x->sel.family == family && + xfrm_selector_match(&x->sel, fl, family))) && security_xfrm_state_pol_flow_match(x, pol, fl)) *error = -ESRCH; } @@ -1069,7 +1072,7 @@ xfrm_state_find(const xfrm_address_t *daddr, const xfrm_address_t *saddr, tmpl->mode == x->props.mode && tmpl->id.proto == x->id.proto && (tmpl->id.spi == x->id.spi || !tmpl->id.spi)) - xfrm_state_look_at(pol, x, fl, encap_family, + xfrm_state_look_at(pol, x, fl, family, &best, &acquire_in_progress, &error); } if (best || acquire_in_progress) @@ -1086,7 +1089,7 @@ xfrm_state_find(const xfrm_address_t *daddr, const xfrm_address_t *saddr, tmpl->mode == x->props.mode && tmpl->id.proto == x->id.proto && (tmpl->id.spi == x->id.spi || !tmpl->id.spi)) - xfrm_state_look_at(pol, x, fl, encap_family, + xfrm_state_look_at(pol, x, fl, family, &best, &acquire_in_progress, &error); } @@ -1438,6 +1441,30 @@ out: EXPORT_SYMBOL(xfrm_state_add); #ifdef CONFIG_XFRM_MIGRATE +static inline int clone_security(struct xfrm_state *x, struct xfrm_sec_ctx *security) +{ + struct xfrm_user_sec_ctx *uctx; + int size = sizeof(*uctx) + security->ctx_len; + int err; + + uctx = kmalloc(size, GFP_KERNEL); + if (!uctx) + return -ENOMEM; + + uctx->exttype = XFRMA_SEC_CTX; + uctx->len = size; + uctx->ctx_doi = security->ctx_doi; + uctx->ctx_alg = security->ctx_alg; + uctx->ctx_len = security->ctx_len; + memcpy(uctx + 1, security->ctx_str, security->ctx_len); + err = security_xfrm_state_alloc(x, uctx); + kfree(uctx); + if (err) + return err; + + return 0; +} + static struct xfrm_state *xfrm_state_clone(struct xfrm_state *orig, struct xfrm_encap_tmpl *encap) { @@ -1494,6 +1521,10 @@ static struct xfrm_state *xfrm_state_clone(struct xfrm_state *orig, goto error; } + if (orig->security) + if (clone_security(x, orig->security)) + goto error; + if (orig->coaddr) { x->coaddr = kmemdup(orig->coaddr, sizeof(*x->coaddr), GFP_KERNEL); @@ -1507,6 +1538,7 @@ static struct xfrm_state *xfrm_state_clone(struct xfrm_state *orig, } memcpy(&x->mark, &orig->mark, sizeof(x->mark)); + memcpy(&x->props.smark, &orig->props.smark, sizeof(x->props.smark)); if (xfrm_init_state(x) < 0) goto error; @@ -1518,7 +1550,7 @@ static struct xfrm_state *xfrm_state_clone(struct xfrm_state *orig, x->tfcpad = orig->tfcpad; x->replay_maxdiff = orig->replay_maxdiff; x->replay_maxage = orig->replay_maxage; - x->curlft.add_time = orig->curlft.add_time; + memcpy(&x->curlft, &orig->curlft, sizeof(x->curlft)); x->km.state = orig->km.state; x->km.seq = orig->km.seq; x->replay = orig->replay; diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c index e6cfaa680ef3..fbb7d9d06478 100644 --- a/net/xfrm/xfrm_user.c +++ b/net/xfrm/xfrm_user.c @@ -1863,7 +1863,6 @@ static int xfrm_get_policy(struct sk_buff *skb, struct nlmsghdr *nlh, struct km_event c; int delete; struct xfrm_mark m; - u32 mark = xfrm_mark_get(attrs, &m); u32 if_id = 0; p = nlmsg_data(nlh); @@ -1880,8 +1879,11 @@ static int xfrm_get_policy(struct sk_buff *skb, struct nlmsghdr *nlh, if (attrs[XFRMA_IF_ID]) if_id = nla_get_u32(attrs[XFRMA_IF_ID]); + xfrm_mark_get(attrs, &m); + if (p->index) - xp = xfrm_policy_byid(net, mark, if_id, type, p->dir, p->index, delete, &err); + xp = xfrm_policy_byid(net, &m, if_id, type, p->dir, + p->index, delete, &err); else { struct nlattr *rt = attrs[XFRMA_SEC_CTX]; struct xfrm_sec_ctx *ctx; @@ -1898,8 +1900,8 @@ static int xfrm_get_policy(struct sk_buff *skb, struct nlmsghdr *nlh, if (err) return err; } - xp = xfrm_policy_bysel_ctx(net, mark, if_id, type, p->dir, &p->sel, - ctx, delete, &err); + xp = xfrm_policy_bysel_ctx(net, &m, if_id, type, p->dir, + &p->sel, ctx, delete, &err); security_xfrm_policy_free(ctx); } if (xp == NULL) @@ -2166,7 +2168,6 @@ static int xfrm_add_pol_expire(struct sk_buff *skb, struct nlmsghdr *nlh, u8 type = XFRM_POLICY_TYPE_MAIN; int err = -ENOENT; struct xfrm_mark m; - u32 mark = xfrm_mark_get(attrs, &m); u32 if_id = 0; err = copy_from_user_policy_type(&type, attrs); @@ -2180,8 +2181,11 @@ static int xfrm_add_pol_expire(struct sk_buff *skb, struct nlmsghdr *nlh, if (attrs[XFRMA_IF_ID]) if_id = nla_get_u32(attrs[XFRMA_IF_ID]); + xfrm_mark_get(attrs, &m); + if (p->index) - xp = xfrm_policy_byid(net, mark, if_id, type, p->dir, p->index, 0, &err); + xp = xfrm_policy_byid(net, &m, if_id, type, p->dir, p->index, + 0, &err); else { struct nlattr *rt = attrs[XFRMA_SEC_CTX]; struct xfrm_sec_ctx *ctx; @@ -2198,7 +2202,7 @@ static int xfrm_add_pol_expire(struct sk_buff *skb, struct nlmsghdr *nlh, if (err) return err; } - xp = xfrm_policy_bysel_ctx(net, mark, if_id, type, p->dir, + xp = xfrm_policy_bysel_ctx(net, &m, if_id, type, p->dir, &p->sel, ctx, 0, &err); security_xfrm_policy_free(ctx); } |