diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2020-09-03 18:50:48 -0700 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2020-09-03 18:50:48 -0700 |
commit | 3e8d3bdc2a757cc6be5470297947799a7df445cc (patch) | |
tree | fcb5dd872a7d240c0d11b1800f282ffed00d0f97 /net | |
parent | 8381979dfa056dee4df83d1b98740b68776ae8ac (diff) | |
parent | b61ac5bb420adce0c9b79c6b9e1c854af083e33f (diff) | |
download | linux-stable-3e8d3bdc2a757cc6be5470297947799a7df445cc.tar.gz linux-stable-3e8d3bdc2a757cc6be5470297947799a7df445cc.tar.bz2 linux-stable-3e8d3bdc2a757cc6be5470297947799a7df445cc.zip |
Merge git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net
Pull networking fixes from David Miller:
1) Use netif_rx_ni() when necessary in batman-adv stack, from Jussi
Kivilinna.
2) Fix loss of RTT samples in rxrpc, from David Howells.
3) Memory leak in hns_nic_dev_probe(), from Dignhao Liu.
4) ravb module cannot be unloaded, fix from Yuusuke Ashizuka.
5) We disable BH for too lokng in sctp_get_port_local(), add a
cond_resched() here as well, from Xin Long.
6) Fix memory leak in st95hf_in_send_cmd, from Dinghao Liu.
7) Out of bound access in bpf_raw_tp_link_fill_link_info(), from
Yonghong Song.
8) Missing of_node_put() in mt7530 DSA driver, from Sumera
Priyadarsini.
9) Fix crash in bnxt_fw_reset_task(), from Michael Chan.
10) Fix geneve tunnel checksumming bug in hns3, from Yi Li.
11) Memory leak in rxkad_verify_response, from Dinghao Liu.
12) In tipc, don't use smp_processor_id() in preemptible context. From
Tuong Lien.
13) Fix signedness issue in mlx4 memory allocation, from Shung-Hsi Yu.
14) Missing clk_disable_prepare() in gemini driver, from Dan Carpenter.
15) Fix ABI mismatch between driver and firmware in nfp, from Louis
Peens.
* git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net: (110 commits)
net/smc: fix sock refcounting in case of termination
net/smc: reset sndbuf_desc if freed
net/smc: set rx_off for SMCR explicitly
net/smc: fix toleration of fake add_link messages
tg3: Fix soft lockup when tg3_reset_task() fails.
doc: net: dsa: Fix typo in config code sample
net: dp83867: Fix WoL SecureOn password
nfp: flower: fix ABI mismatch between driver and firmware
tipc: fix shutdown() of connectionless socket
ipv6: Fix sysctl max for fib_multipath_hash_policy
drivers/net/wan/hdlc: Change the default of hard_header_len to 0
net: gemini: Fix another missing clk_disable_unprepare() in probe
net: bcmgenet: fix mask check in bcmgenet_validate_flow()
amd-xgbe: Add support for new port mode
net: usb: dm9601: Add USB ID of Keenetic Plus DSL
vhost: fix typo in error message
net: ethernet: mlx4: Fix memory allocation in mlx4_buddy_init()
pktgen: fix error message with wrong function name
net: ethernet: ti: am65-cpsw: fix rmii 100Mbit link mode
cxgb4: fix thermal zone device registration
...
Diffstat (limited to 'net')
52 files changed, 627 insertions, 343 deletions
diff --git a/net/batman-adv/bat_v_ogm.c b/net/batman-adv/bat_v_ogm.c index 0f8495b9eeb1..717fe657561d 100644 --- a/net/batman-adv/bat_v_ogm.c +++ b/net/batman-adv/bat_v_ogm.c @@ -881,6 +881,12 @@ 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. */ @@ -1008,11 +1014,6 @@ 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 91a04ca373dc..8500f56cbd10 100644 --- a/net/batman-adv/bridge_loop_avoidance.c +++ b/net/batman-adv/bridge_loop_avoidance.c @@ -437,7 +437,10 @@ 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); diff --git a/net/batman-adv/gateway_client.c b/net/batman-adv/gateway_client.c index a18dcc686dc3..ef3f85b576c4 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/caif/cfrfml.c b/net/caif/cfrfml.c index ce2767e9cec6..7b0af33bdb97 100644 --- a/net/caif/cfrfml.c +++ b/net/caif/cfrfml.c @@ -116,7 +116,7 @@ static int cfrfml_receive(struct cflayer *layr, struct cfpkt *pkt) if (segmented) { if (rfml->incomplete_frm == NULL) { /* Initial Segment */ - if (cfpkt_peek_head(pkt, rfml->seghead, 6) < 0) + if (cfpkt_peek_head(pkt, rfml->seghead, 6) != 0) goto out; rfml->pdu_size = get_unaligned_le16(rfml->seghead+4); @@ -233,7 +233,7 @@ static int cfrfml_transmit(struct cflayer *layr, struct cfpkt *pkt) if (cfpkt_getlen(pkt) > rfml->fragment_size + RFM_HEAD_SIZE) err = cfpkt_peek_head(pkt, head, 6); - if (err < 0) + if (err != 0) goto out; while (cfpkt_getlen(frontpkt) > rfml->fragment_size + RFM_HEAD_SIZE) { diff --git a/net/core/dev.c b/net/core/dev.c index b9c6f31ae96e..4086d335978c 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -6612,12 +6612,13 @@ 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); diff --git a/net/core/netpoll.c b/net/core/netpoll.c index 093e90e52bc2..2338753e936b 100644 --- a/net/core/netpoll.c +++ b/net/core/netpoll.c @@ -162,7 +162,7 @@ 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/pktgen.c b/net/core/pktgen.c index 95f4c6b8f51a..44fdbb9c6e53 100644 --- a/net/core/pktgen.c +++ b/net/core/pktgen.c @@ -3699,7 +3699,7 @@ static int __net_init pktgen_create_thread(int cpu, struct pktgen_net *pn) cpu_to_node(cpu), "kpktgend_%d", cpu); if (IS_ERR(p)) { - pr_err("kernel_thread() failed for cpu %d\n", t->cpu); + pr_err("kthread_create_on_node() failed for cpu %d\n", t->cpu); list_del(&t->th_list); kfree(t); return PTR_ERR(p); diff --git a/net/core/skbuff.c b/net/core/skbuff.c index e18184ffa9c3..6faf73d6a0f7 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -820,6 +820,7 @@ void skb_tx_error(struct sk_buff *skb) } EXPORT_SYMBOL(skb_tx_error); +#ifdef CONFIG_TRACEPOINTS /** * consume_skb - free an skbuff * @skb: buffer to free @@ -837,6 +838,7 @@ void consume_skb(struct sk_buff *skb) __kfree_skb(skb); } EXPORT_SYMBOL(consume_skb); +#endif /** * consume_stateless_skb - free an skbuff, assuming it is stateless diff --git a/net/core/sock.c b/net/core/sock.c index f8e5ccc45272..6c5c6b18eff4 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -3254,7 +3254,7 @@ void sk_common_release(struct sock *sk) sk->sk_prot->destroy(sk); /* - * Observation: when sock_common_release is called, processes have + * Observation: when sk_common_release is called, processes have * no access to socket. But net still has. * Step one, detach it from networking: * diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c index c89b46fec153..ffc5332f1390 100644 --- a/net/ipv4/fib_trie.c +++ b/net/ipv4/fib_trie.c @@ -2121,7 +2121,8 @@ 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/netfilter/nf_nat_pptp.c b/net/ipv4/netfilter/nf_nat_pptp.c index 7afde8828b4c..3f248a19faa3 100644 --- a/net/ipv4/netfilter/nf_nat_pptp.c +++ b/net/ipv4/netfilter/nf_nat_pptp.c @@ -3,7 +3,7 @@ * nf_nat_pptp.c * * NAT support for PPTP (Point to Point Tunneling Protocol). - * PPTP is a a protocol for creating virtual private networks. + * PPTP is a protocol for creating virtual private networks. * It is a specification defined by Microsoft and some vendors * working with Microsoft. PPTP is built on top of a modified * version of the Internet Generic Routing Encapsulation Protocol. diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c index 6fd4330287c2..407956be7deb 100644 --- a/net/ipv4/raw.c +++ b/net/ipv4/raw.c @@ -610,7 +610,7 @@ static int raw_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) } else if (!ipc.oif) { ipc.oif = inet->uc_index; } else if (ipv4_is_lbcast(daddr) && inet->uc_index) { - /* oif is set, packet is to local broadcast and + /* oif is set, packet is to local broadcast * and uc_index is set. oif is most likely set * by sk_bound_dev_if. If uc_index != oif check if the * oif is an L3 master and uc_index is an L3 slave. diff --git a/net/ipv6/sysctl_net_ipv6.c b/net/ipv6/sysctl_net_ipv6.c index fac2135aa47b..5b60a4bdd36a 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; @@ -150,7 +151,7 @@ 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/l3mdev/l3mdev.c b/net/l3mdev/l3mdev.c index e71ca5aec684..864326f150e2 100644 --- a/net/l3mdev/l3mdev.c +++ b/net/l3mdev/l3mdev.c @@ -154,7 +154,7 @@ int l3mdev_master_upper_ifindex_by_index_rcu(struct net *net, int ifindex) EXPORT_SYMBOL_GPL(l3mdev_master_upper_ifindex_by_index_rcu); /** - * l3mdev_fib_table - get FIB table id associated with an L3 + * l3mdev_fib_table_rcu - get FIB table id associated with an L3 * master interface * @dev: targeted interface */ diff --git a/net/mac80211/airtime.c b/net/mac80211/airtime.c index 366f76c9003d..314973033d03 100644 --- a/net/mac80211/airtime.c +++ b/net/mac80211/airtime.c @@ -405,18 +405,14 @@ ieee80211_calc_legacy_rate_duration(u16 bitrate, bool short_pre, return duration; } -u32 ieee80211_calc_rx_airtime(struct ieee80211_hw *hw, - struct ieee80211_rx_status *status, - int len) +static u32 ieee80211_get_rate_duration(struct ieee80211_hw *hw, + struct ieee80211_rx_status *status, + u32 *overhead) { - struct ieee80211_supported_band *sband; - const struct ieee80211_rate *rate; bool sgi = status->enc_flags & RX_ENC_FLAG_SHORT_GI; - bool sp = status->enc_flags & RX_ENC_FLAG_SHORTPRE; int bw, streams; int group, idx; u32 duration; - bool cck; switch (status->bw) { case RATE_INFO_BW_20: @@ -437,20 +433,6 @@ u32 ieee80211_calc_rx_airtime(struct ieee80211_hw *hw, } switch (status->encoding) { - case RX_ENC_LEGACY: - if (WARN_ON_ONCE(status->band > NL80211_BAND_5GHZ)) - return 0; - - sband = hw->wiphy->bands[status->band]; - if (!sband || status->rate_idx >= sband->n_bitrates) - return 0; - - rate = &sband->bitrates[status->rate_idx]; - cck = rate->flags & IEEE80211_RATE_MANDATORY_B; - - return ieee80211_calc_legacy_rate_duration(rate->bitrate, sp, - cck, len); - case RX_ENC_VHT: streams = status->nss; idx = status->rate_idx; @@ -477,51 +459,144 @@ u32 ieee80211_calc_rx_airtime(struct ieee80211_hw *hw, duration = airtime_mcs_groups[group].duration[idx]; duration <<= airtime_mcs_groups[group].shift; + *overhead = 36 + (streams << 2); + + return duration; +} + + +u32 ieee80211_calc_rx_airtime(struct ieee80211_hw *hw, + struct ieee80211_rx_status *status, + int len) +{ + struct ieee80211_supported_band *sband; + u32 duration, overhead = 0; + + if (status->encoding == RX_ENC_LEGACY) { + const struct ieee80211_rate *rate; + bool sp = status->enc_flags & RX_ENC_FLAG_SHORTPRE; + bool cck; + + if (WARN_ON_ONCE(status->band > NL80211_BAND_5GHZ)) + return 0; + + sband = hw->wiphy->bands[status->band]; + if (!sband || status->rate_idx >= sband->n_bitrates) + return 0; + + rate = &sband->bitrates[status->rate_idx]; + cck = rate->flags & IEEE80211_RATE_MANDATORY_B; + + return ieee80211_calc_legacy_rate_duration(rate->bitrate, sp, + cck, len); + } + + duration = ieee80211_get_rate_duration(hw, status, &overhead); + if (!duration) + return 0; + duration *= len; duration /= AVG_PKT_SIZE; duration /= 1024; - duration += 36 + (streams << 2); - - return duration; + return duration + overhead; } EXPORT_SYMBOL_GPL(ieee80211_calc_rx_airtime); -static u32 ieee80211_calc_tx_airtime_rate(struct ieee80211_hw *hw, - struct ieee80211_tx_rate *rate, - u8 band, int len) +static bool ieee80211_fill_rate_info(struct ieee80211_hw *hw, + struct ieee80211_rx_status *stat, u8 band, + struct rate_info *ri) { - struct ieee80211_rx_status stat = { - .band = band, - }; + struct ieee80211_supported_band *sband = hw->wiphy->bands[band]; + int i; - if (rate->idx < 0 || !rate->count) + if (!ri || !sband) + return false; + + stat->bw = ri->bw; + stat->nss = ri->nss; + stat->rate_idx = ri->mcs; + + if (ri->flags & RATE_INFO_FLAGS_HE_MCS) + stat->encoding = RX_ENC_HE; + else if (ri->flags & RATE_INFO_FLAGS_VHT_MCS) + stat->encoding = RX_ENC_VHT; + else if (ri->flags & RATE_INFO_FLAGS_MCS) + stat->encoding = RX_ENC_HT; + else + stat->encoding = RX_ENC_LEGACY; + + if (ri->flags & RATE_INFO_FLAGS_SHORT_GI) + stat->enc_flags |= RX_ENC_FLAG_SHORT_GI; + + stat->he_gi = ri->he_gi; + + if (stat->encoding != RX_ENC_LEGACY) + return true; + + stat->rate_idx = 0; + for (i = 0; i < sband->n_bitrates; i++) { + if (ri->legacy != sband->bitrates[i].bitrate) + continue; + + stat->rate_idx = i; + return true; + } + + return false; +} + +static int ieee80211_fill_rx_status(struct ieee80211_rx_status *stat, + struct ieee80211_hw *hw, + struct ieee80211_tx_rate *rate, + struct rate_info *ri, u8 band, int len) +{ + memset(stat, 0, sizeof(*stat)); + stat->band = band; + + if (ieee80211_fill_rate_info(hw, stat, band, ri)) return 0; + if (rate->idx < 0 || !rate->count) + return -1; + if (rate->flags & IEEE80211_TX_RC_80_MHZ_WIDTH) - stat.bw = RATE_INFO_BW_80; + stat->bw = RATE_INFO_BW_80; else if (rate->flags & IEEE80211_TX_RC_40_MHZ_WIDTH) - stat.bw = RATE_INFO_BW_40; + stat->bw = RATE_INFO_BW_40; else - stat.bw = RATE_INFO_BW_20; + stat->bw = RATE_INFO_BW_20; - stat.enc_flags = 0; + stat->enc_flags = 0; if (rate->flags & IEEE80211_TX_RC_USE_SHORT_PREAMBLE) - stat.enc_flags |= RX_ENC_FLAG_SHORTPRE; + stat->enc_flags |= RX_ENC_FLAG_SHORTPRE; if (rate->flags & IEEE80211_TX_RC_SHORT_GI) - stat.enc_flags |= RX_ENC_FLAG_SHORT_GI; + stat->enc_flags |= RX_ENC_FLAG_SHORT_GI; - stat.rate_idx = rate->idx; + stat->rate_idx = rate->idx; if (rate->flags & IEEE80211_TX_RC_VHT_MCS) { - stat.encoding = RX_ENC_VHT; - stat.rate_idx = ieee80211_rate_get_vht_mcs(rate); - stat.nss = ieee80211_rate_get_vht_nss(rate); + stat->encoding = RX_ENC_VHT; + stat->rate_idx = ieee80211_rate_get_vht_mcs(rate); + stat->nss = ieee80211_rate_get_vht_nss(rate); } else if (rate->flags & IEEE80211_TX_RC_MCS) { - stat.encoding = RX_ENC_HT; + stat->encoding = RX_ENC_HT; } else { - stat.encoding = RX_ENC_LEGACY; + stat->encoding = RX_ENC_LEGACY; } + return 0; +} + +static u32 ieee80211_calc_tx_airtime_rate(struct ieee80211_hw *hw, + struct ieee80211_tx_rate *rate, + struct rate_info *ri, + u8 band, int len) +{ + struct ieee80211_rx_status stat; + + if (ieee80211_fill_rx_status(&stat, hw, rate, ri, band, len)) + return 0; + return ieee80211_calc_rx_airtime(hw, &stat, len); } @@ -536,7 +611,7 @@ u32 ieee80211_calc_tx_airtime(struct ieee80211_hw *hw, struct ieee80211_tx_rate *rate = &info->status.rates[i]; u32 cur_duration; - cur_duration = ieee80211_calc_tx_airtime_rate(hw, rate, + cur_duration = ieee80211_calc_tx_airtime_rate(hw, rate, NULL, info->band, len); if (!cur_duration) break; @@ -572,26 +647,41 @@ u32 ieee80211_calc_expected_tx_airtime(struct ieee80211_hw *hw, if (pubsta) { struct sta_info *sta = container_of(pubsta, struct sta_info, sta); + struct ieee80211_rx_status stat; struct ieee80211_tx_rate *rate = &sta->tx_stats.last_rate; - u32 airtime; + struct rate_info *ri = &sta->tx_stats.last_rate_info; + u32 duration, overhead; + u8 agg_shift; - if (!(rate->flags & (IEEE80211_TX_RC_VHT_MCS | - IEEE80211_TX_RC_MCS))) - ampdu = false; + if (ieee80211_fill_rx_status(&stat, hw, rate, ri, band, len)) + return 0; + if (stat.encoding == RX_ENC_LEGACY || !ampdu) + return ieee80211_calc_rx_airtime(hw, &stat, len); + + duration = ieee80211_get_rate_duration(hw, &stat, &overhead); /* * Assume that HT/VHT transmission on any AC except VO will * use aggregation. Since we don't have reliable reporting - * of aggregation length, assume an average of 16. + * of aggregation length, assume an average size based on the + * tx rate. * This will not be very accurate, but much better than simply - * assuming un-aggregated tx. + * assuming un-aggregated tx in all cases. */ - airtime = ieee80211_calc_tx_airtime_rate(hw, rate, band, - ampdu ? len * 16 : len); - if (ampdu) - airtime /= 16; - - return airtime; + if (duration > 400) /* <= VHT20 MCS2 1S */ + agg_shift = 1; + else if (duration > 250) /* <= VHT20 MCS3 1S or MCS1 2S */ + agg_shift = 2; + else if (duration > 150) /* <= VHT20 MCS5 1S or MCS3 2S */ + agg_shift = 3; + else + agg_shift = 4; + + duration *= len; + duration /= AVG_PKT_SIZE; + duration /= 1024; + + return duration + (overhead >> agg_shift); } if (!conf) diff --git a/net/mac80211/sta_info.h b/net/mac80211/sta_info.h index 9d398c9daa4c..d5010116cf4d 100644 --- a/net/mac80211/sta_info.h +++ b/net/mac80211/sta_info.h @@ -524,7 +524,7 @@ struct ieee80211_sta_rx_stats { * @status_stats.retry_failed: # of frames that failed after retry * @status_stats.retry_count: # of retries attempted * @status_stats.lost_packets: # of lost packets - * @status_stats.last_tdls_pkt_time: timestamp of last TDLS packet + * @status_stats.last_pkt_time: timestamp of last ACKed packet * @status_stats.msdu_retries: # of MSDU retries * @status_stats.msdu_failed: # of failed MSDUs * @status_stats.last_ack: last ack timestamp (jiffies) @@ -597,7 +597,7 @@ struct sta_info { unsigned long filtered; unsigned long retry_failed, retry_count; unsigned int lost_packets; - unsigned long last_tdls_pkt_time; + unsigned long last_pkt_time; u64 msdu_retries[IEEE80211_NUM_TIDS + 1]; u64 msdu_failed[IEEE80211_NUM_TIDS + 1]; unsigned long last_ack; @@ -611,6 +611,7 @@ struct sta_info { u64 packets[IEEE80211_NUM_ACS]; u64 bytes[IEEE80211_NUM_ACS]; struct ieee80211_tx_rate last_rate; + struct rate_info last_rate_info; u64 msdu[IEEE80211_NUM_TIDS + 1]; } tx_stats; u16 tid_seq[IEEE80211_QOS_CTL_TID_MASK + 1]; diff --git a/net/mac80211/status.c b/net/mac80211/status.c index adb1d30ce06e..0794396a7988 100644 --- a/net/mac80211/status.c +++ b/net/mac80211/status.c @@ -755,12 +755,16 @@ static void ieee80211_report_used_skb(struct ieee80211_local *local, * - current throughput (higher value for higher tpt)? */ #define STA_LOST_PKT_THRESHOLD 50 +#define STA_LOST_PKT_TIME HZ /* 1 sec since last ACK */ #define STA_LOST_TDLS_PKT_THRESHOLD 10 #define STA_LOST_TDLS_PKT_TIME (10*HZ) /* 10secs since last ACK */ static void ieee80211_lost_packet(struct sta_info *sta, struct ieee80211_tx_info *info) { + unsigned long pkt_time = STA_LOST_PKT_TIME; + unsigned int pkt_thr = STA_LOST_PKT_THRESHOLD; + /* If driver relies on its own algorithm for station kickout, skip * mac80211 packet loss mechanism. */ @@ -773,21 +777,20 @@ static void ieee80211_lost_packet(struct sta_info *sta, return; sta->status_stats.lost_packets++; - if (!sta->sta.tdls && - sta->status_stats.lost_packets < STA_LOST_PKT_THRESHOLD) - return; + if (sta->sta.tdls) { + pkt_time = STA_LOST_TDLS_PKT_TIME; + pkt_thr = STA_LOST_PKT_THRESHOLD; + } /* * If we're in TDLS mode, make sure that all STA_LOST_TDLS_PKT_THRESHOLD * of the last packets were lost, and that no ACK was received in the * last STA_LOST_TDLS_PKT_TIME ms, before triggering the CQM packet-loss * mechanism. + * For non-TDLS, use STA_LOST_PKT_THRESHOLD and STA_LOST_PKT_TIME */ - if (sta->sta.tdls && - (sta->status_stats.lost_packets < STA_LOST_TDLS_PKT_THRESHOLD || - time_before(jiffies, - sta->status_stats.last_tdls_pkt_time + - STA_LOST_TDLS_PKT_TIME))) + if (sta->status_stats.lost_packets < pkt_thr || + !time_after(jiffies, sta->status_stats.last_pkt_time + pkt_time)) return; cfg80211_cqm_pktloss_notify(sta->sdata->dev, sta->sta.addr, @@ -1033,9 +1036,7 @@ static void __ieee80211_tx_status(struct ieee80211_hw *hw, sta->status_stats.lost_packets = 0; /* Track when last TDLS packet was ACKed */ - if (test_sta_flag(sta, WLAN_STA_TDLS_PEER_AUTH)) - sta->status_stats.last_tdls_pkt_time = - jiffies; + sta->status_stats.last_pkt_time = jiffies; } else if (noack_success) { /* nothing to do here, do not account as lost */ } else { @@ -1137,9 +1138,17 @@ void ieee80211_tx_status_ext(struct ieee80211_hw *hw, struct ieee80211_tx_info *info = status->info; struct ieee80211_sta *pubsta = status->sta; struct ieee80211_supported_band *sband; + struct sta_info *sta; int retry_count; bool acked, noack_success; + if (pubsta) { + sta = container_of(pubsta, struct sta_info, sta); + + if (status->rate) + sta->tx_stats.last_rate_info = *status->rate; + } + if (status->skb) return __ieee80211_tx_status(hw, status); @@ -1154,10 +1163,6 @@ void ieee80211_tx_status_ext(struct ieee80211_hw *hw, noack_success = !!(info->flags & IEEE80211_TX_STAT_NOACK_TRANSMITTED); if (pubsta) { - struct sta_info *sta; - - sta = container_of(pubsta, struct sta_info, sta); - if (!acked && !noack_success) sta->status_stats.retry_failed++; sta->status_stats.retry_count += retry_count; @@ -1168,9 +1173,8 @@ void ieee80211_tx_status_ext(struct ieee80211_hw *hw, if (sta->status_stats.lost_packets) sta->status_stats.lost_packets = 0; - /* Track when last TDLS packet was ACKed */ - if (test_sta_flag(sta, WLAN_STA_TDLS_PEER_AUTH)) - sta->status_stats.last_tdls_pkt_time = jiffies; + /* Track when last packet was ACKed */ + sta->status_stats.last_pkt_time = jiffies; } else if (test_sta_flag(sta, WLAN_STA_PS_STA)) { return; } else if (noack_success) { @@ -1259,8 +1263,7 @@ void ieee80211_tx_status_8023(struct ieee80211_hw *hw, if (sta->status_stats.lost_packets) sta->status_stats.lost_packets = 0; - if (test_sta_flag(sta, WLAN_STA_TDLS_PEER_AUTH)) - sta->status_stats.last_tdls_pkt_time = jiffies; + sta->status_stats.last_pkt_time = jiffies; } else { ieee80211_lost_packet(sta, info); } diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index 49b815023986..365ba96c84b0 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -891,7 +891,6 @@ restart: goto out; } -wait_for_sndbuf: __mptcp_flush_join_list(msk); ssk = mptcp_subflow_get_send(msk); while (!sk_stream_memory_free(sk) || @@ -981,7 +980,7 @@ wait_for_sndbuf: */ mptcp_set_timeout(sk, ssk); release_sock(ssk); - goto wait_for_sndbuf; + goto restart; } } } diff --git a/net/netfilter/nf_conntrack_pptp.c b/net/netfilter/nf_conntrack_pptp.c index 1f44d523b512..5105d4250012 100644 --- a/net/netfilter/nf_conntrack_pptp.c +++ b/net/netfilter/nf_conntrack_pptp.c @@ -1,7 +1,7 @@ // SPDX-License-Identifier: GPL-2.0-only /* * Connection tracking support for PPTP (Point to Point Tunneling Protocol). - * PPTP is a a protocol for creating virtual private networks. + * PPTP is a protocol for creating virtual private networks. * It is a specification defined by Microsoft and some vendors * working with Microsoft. PPTP is built on top of a modified * version of the Internet Generic Routing Encapsulation Protocol. 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 6892e497781c..e8c86ee4c1c4 100644 --- a/net/netfilter/nf_conntrack_proto_tcp.c +++ b/net/netfilter/nf_conntrack_proto_tcp.c @@ -1152,7 +1152,7 @@ int nf_conntrack_tcp_packet(struct nf_conn *ct, && (old_state == TCP_CONNTRACK_SYN_RECV || old_state == TCP_CONNTRACK_ESTABLISHED) && new_state == TCP_CONNTRACK_ESTABLISHED) { - /* Set ASSURED if we see see valid ack in ESTABLISHED + /* Set ASSURED if we see valid ack in ESTABLISHED after SYN_RECV or a valid answer for a picked up connection. */ set_bit(IPS_ASSURED_BIT, &ct->status); diff --git a/net/netfilter/nf_conntrack_proto_udp.c b/net/netfilter/nf_conntrack_proto_udp.c index 760ca2422816..af402f458ee0 100644 --- a/net/netfilter/nf_conntrack_proto_udp.c +++ b/net/netfilter/nf_conntrack_proto_udp.c @@ -81,18 +81,6 @@ static bool udp_error(struct sk_buff *skb, return false; } -static void nf_conntrack_udp_refresh_unreplied(struct nf_conn *ct, - struct sk_buff *skb, - enum ip_conntrack_info ctinfo, - u32 extra_jiffies) -{ - if (unlikely(ctinfo == IP_CT_ESTABLISHED_REPLY && - ct->status & IPS_NAT_CLASH)) - nf_ct_kill(ct); - else - nf_ct_refresh_acct(ct, ctinfo, skb, extra_jiffies); -} - /* Returns verdict for packet, and may modify conntracktype */ int nf_conntrack_udp_packet(struct nf_conn *ct, struct sk_buff *skb, @@ -124,12 +112,15 @@ int nf_conntrack_udp_packet(struct nf_conn *ct, nf_ct_refresh_acct(ct, ctinfo, skb, extra); + /* never set ASSURED for IPS_NAT_CLASH, they time out soon */ + if (unlikely((ct->status & IPS_NAT_CLASH))) + return NF_ACCEPT; + /* Also, more likely to be important, and not a probe */ if (!test_and_set_bit(IPS_ASSURED_BIT, &ct->status)) nf_conntrack_event_cache(IPCT_ASSURED, ct); } else { - nf_conntrack_udp_refresh_unreplied(ct, skb, ctinfo, - timeouts[UDP_CT_UNREPLIED]); + nf_ct_refresh_acct(ct, ctinfo, skb, timeouts[UDP_CT_UNREPLIED]); } return NF_ACCEPT; } @@ -206,12 +197,15 @@ int nf_conntrack_udplite_packet(struct nf_conn *ct, if (test_bit(IPS_SEEN_REPLY_BIT, &ct->status)) { nf_ct_refresh_acct(ct, ctinfo, skb, timeouts[UDP_CT_REPLIED]); + + if (unlikely((ct->status & IPS_NAT_CLASH))) + return NF_ACCEPT; + /* Also, more likely to be important, and not a probe */ if (!test_and_set_bit(IPS_ASSURED_BIT, &ct->status)) nf_conntrack_event_cache(IPCT_ASSURED, ct); } else { - nf_conntrack_udp_refresh_unreplied(ct, skb, ctinfo, - timeouts[UDP_CT_UNREPLIED]); + nf_ct_refresh_acct(ct, ctinfo, skb, timeouts[UDP_CT_UNREPLIED]); } return NF_ACCEPT; } diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index fd814e514f94..b7dc1cbf40ea 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -815,11 +815,11 @@ 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; } @@ -1563,11 +1563,11 @@ 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; } @@ -3008,11 +3008,11 @@ 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; } @@ -3770,7 +3770,8 @@ 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; nest = nla_nest_start_noflag(skb, NFTA_SET_DESC); @@ -3967,11 +3968,11 @@ 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; } @@ -4859,24 +4860,18 @@ 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 */ @@ -6181,10 +6176,11 @@ 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; } @@ -7044,10 +7040,11 @@ static int nf_tables_getflowtable(struct net *net, struct sock *nlsk, NFT_MSG_NEWFLOWTABLE, 0, family, flowtable, &flowtable->hook_list); 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; } @@ -7233,10 +7230,11 @@ 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/nfnetlink.c b/net/netfilter/nfnetlink.c index 5f24edf95830..3a2e64e13b22 100644 --- a/net/netfilter/nfnetlink.c +++ b/net/netfilter/nfnetlink.c @@ -149,10 +149,15 @@ 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 f02992419850..b35e8d9a5b37 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 dadfc06245a3..d1d8bca03b4f 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_flow_offload.c b/net/netfilter/nft_flow_offload.c index 3b9b97aa4b32..3a6c84fb2c90 100644 --- a/net/netfilter/nft_flow_offload.c +++ b/net/netfilter/nft_flow_offload.c @@ -102,7 +102,7 @@ static void nft_flow_offload_eval(const struct nft_expr *expr, } if (nf_ct_ext_exist(ct, NF_CT_EXT_HELPER) || - ct->status & IPS_SEQ_ADJUST) + ct->status & (IPS_SEQ_ADJUST | IPS_NAT_CLASH)) goto out; if (!nf_ct_is_confirmed(ct)) diff --git a/net/netfilter/nft_payload.c b/net/netfilter/nft_payload.c index ed7cb9f747f6..7a2e59638499 100644 --- a/net/netfilter/nft_payload.c +++ b/net/netfilter/nft_payload.c @@ -87,7 +87,9 @@ 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/netfilter/nft_set_rbtree.c b/net/netfilter/nft_set_rbtree.c index 4b2834fd17b2..217ab3644c25 100644 --- a/net/netfilter/nft_set_rbtree.c +++ b/net/netfilter/nft_set_rbtree.c @@ -218,11 +218,11 @@ static int __nft_rbtree_insert(const struct net *net, const struct nft_set *set, struct nft_rbtree_elem *new, struct nft_set_ext **ext) { + bool overlap = false, dup_end_left = false, dup_end_right = false; struct nft_rbtree *priv = nft_set_priv(set); u8 genmask = nft_genmask_next(net); struct nft_rbtree_elem *rbe; struct rb_node *parent, **p; - bool overlap = false; int d; /* Detect overlaps as we descend the tree. Set the flag in these cases: @@ -238,24 +238,44 @@ static int __nft_rbtree_insert(const struct net *net, const struct nft_set *set, * * b1. _ _ __>| !_ _ __| (insert end before existing start) * b2. _ _ ___| !_ _ _>| (insert end after existing start) - * b3. _ _ ___! >|_ _ __| (insert start after existing end) + * b3. _ _ ___! >|_ _ __| (insert start after existing end, as a leaf) + * '--' no nodes falling in this range + * b4. >|_ _ ! (insert start before existing start) * * Case a3. resolves to b3.: * - if the inserted start element is the leftmost, because the '0' * element in the tree serves as end element - * - otherwise, if an existing end is found. Note that end elements are - * always inserted after corresponding start elements. + * - otherwise, if an existing end is found immediately to the left. If + * there are existing nodes in between, we need to further descend the + * tree before we can conclude the new start isn't causing an overlap + * + * or to b4., which, preceded by a3., means we already traversed one or + * more existing intervals entirely, from the right. * * For a new, rightmost pair of elements, we'll hit cases b3. and b2., * in that order. * * The flag is also cleared in two special cases: * - * b4. |__ _ _!|<_ _ _ (insert start right before existing end) - * b5. |__ _ >|!__ _ _ (insert end right after existing start) + * b5. |__ _ _!|<_ _ _ (insert start right before existing end) + * b6. |__ _ >|!__ _ _ (insert end right after existing start) * * which always happen as last step and imply that no further * overlapping is possible. + * + * Another special case comes from the fact that start elements matching + * an already existing start element are allowed: insertion is not + * performed but we return -EEXIST in that case, and the error will be + * cleared by the caller if NLM_F_EXCL is not present in the request. + * This way, request for insertion of an exact overlap isn't reported as + * error to userspace if not desired. + * + * However, if the existing start matches a pre-existing start, but the + * end element doesn't match the corresponding pre-existing end element, + * we need to report a partial overlap. This is a local condition that + * can be noticed without need for a tracking flag, by checking for a + * local duplicated end for a corresponding start, from left and right, + * separately. */ parent = NULL; @@ -272,26 +292,41 @@ static int __nft_rbtree_insert(const struct net *net, const struct nft_set *set, if (nft_rbtree_interval_start(new)) { if (nft_rbtree_interval_end(rbe) && nft_set_elem_active(&rbe->ext, genmask) && - !nft_set_elem_expired(&rbe->ext)) + !nft_set_elem_expired(&rbe->ext) && !*p) overlap = false; } else { + if (dup_end_left && !*p) + return -ENOTEMPTY; + overlap = nft_rbtree_interval_end(rbe) && nft_set_elem_active(&rbe->ext, genmask) && !nft_set_elem_expired(&rbe->ext); + + if (overlap) { + dup_end_right = true; + continue; + } } } else if (d > 0) { p = &parent->rb_right; if (nft_rbtree_interval_end(new)) { + if (dup_end_right && !*p) + return -ENOTEMPTY; + overlap = nft_rbtree_interval_end(rbe) && nft_set_elem_active(&rbe->ext, genmask) && !nft_set_elem_expired(&rbe->ext); - } else if (nft_rbtree_interval_end(rbe) && - nft_set_elem_active(&rbe->ext, genmask) && + + if (overlap) { + dup_end_left = true; + continue; + } + } else if (nft_set_elem_active(&rbe->ext, genmask) && !nft_set_elem_expired(&rbe->ext)) { - overlap = true; + overlap = nft_rbtree_interval_end(rbe); } } else { if (nft_rbtree_interval_end(rbe) && @@ -316,6 +351,8 @@ static int __nft_rbtree_insert(const struct net *net, const struct nft_set *set, p = &parent->rb_left; } } + + dup_end_left = dup_end_right = false; } if (overlap) diff --git a/net/netfilter/xt_recent.c b/net/netfilter/xt_recent.c index 19bef176145e..606411869698 100644 --- a/net/netfilter/xt_recent.c +++ b/net/netfilter/xt_recent.c @@ -640,7 +640,7 @@ static void __net_exit recent_proc_net_exit(struct net *net) struct recent_table *t; /* recent_net_exit() is called before recent_mt_destroy(). Make sure - * that the parent xt_recent proc entry is is empty before trying to + * that the parent xt_recent proc entry is empty before trying to * remove it. */ spin_lock_bh(&recent_lock); diff --git a/net/netlabel/netlabel_domainhash.c b/net/netlabel/netlabel_domainhash.c index d07de2c0fbc7..f73a8382c275 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); @@ -537,6 +538,8 @@ 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; @@ -580,6 +583,12 @@ 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; @@ -597,6 +606,9 @@ 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, @@ -606,40 +618,29 @@ 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/af_netlink.c b/net/netlink/af_netlink.c index b5f30d7d30d0..d2d1448274f5 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -353,7 +353,7 @@ static void netlink_rcv_wake(struct sock *sk) { struct netlink_sock *nlk = nlk_sk(sk); - if (skb_queue_empty(&sk->sk_receive_queue)) + if (skb_queue_empty_lockless(&sk->sk_receive_queue)) clear_bit(NETLINK_S_CONGESTED, &nlk->state); if (!test_bit(NETLINK_S_CONGESTED, &nlk->state)) wake_up_interruptible(&nlk->wait); diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h index 6d29a3603a3e..884cff7bb169 100644 --- a/net/rxrpc/ar-internal.h +++ b/net/rxrpc/ar-internal.h @@ -488,7 +488,6 @@ enum rxrpc_call_flag { RXRPC_CALL_RX_LAST, /* Received the last packet (at rxtx_top) */ RXRPC_CALL_TX_LAST, /* Last packet in Tx buffer (at rxtx_top) */ RXRPC_CALL_SEND_PING, /* A ping will need to be sent */ - RXRPC_CALL_PINGING, /* Ping in process */ RXRPC_CALL_RETRANS_TIMEOUT, /* Retransmission due to timeout occurred */ RXRPC_CALL_BEGAN_RX_TIMER, /* We began the expect_rx_by timer */ RXRPC_CALL_RX_HEARD, /* The peer responded at least once to this call */ @@ -673,9 +672,13 @@ struct rxrpc_call { rxrpc_seq_t ackr_consumed; /* Highest packet shown consumed */ rxrpc_seq_t ackr_seen; /* Highest packet shown seen */ - /* ping management */ - rxrpc_serial_t ping_serial; /* Last ping sent */ - ktime_t ping_time; /* Time last ping sent */ + /* RTT management */ + rxrpc_serial_t rtt_serial[4]; /* Serial number of DATA or PING sent */ + ktime_t rtt_sent_at[4]; /* Time packet sent */ + unsigned long rtt_avail; /* Mask of available slots in bits 0-3, + * Mask of pending samples in 8-11 */ +#define RXRPC_CALL_RTT_AVAIL_MASK 0xf +#define RXRPC_CALL_RTT_PEND_SHIFT 8 /* transmission-phase ACK management */ ktime_t acks_latest_ts; /* Timestamp of latest ACK received */ @@ -1037,7 +1040,7 @@ static inline bool __rxrpc_abort_eproto(struct rxrpc_call *call, /* * rtt.c */ -void rxrpc_peer_add_rtt(struct rxrpc_call *, enum rxrpc_rtt_rx_trace, +void rxrpc_peer_add_rtt(struct rxrpc_call *, enum rxrpc_rtt_rx_trace, int, rxrpc_serial_t, rxrpc_serial_t, ktime_t, ktime_t); unsigned long rxrpc_get_rto_backoff(struct rxrpc_peer *, bool); void rxrpc_peer_init_rtt(struct rxrpc_peer *); diff --git a/net/rxrpc/call_object.c b/net/rxrpc/call_object.c index 38a46167523f..a40fae013942 100644 --- a/net/rxrpc/call_object.c +++ b/net/rxrpc/call_object.c @@ -153,6 +153,7 @@ struct rxrpc_call *rxrpc_alloc_call(struct rxrpc_sock *rx, gfp_t gfp, call->cong_ssthresh = RXRPC_RXTX_BUFF_SIZE - 1; call->rxnet = rxnet; + call->rtt_avail = RXRPC_CALL_RTT_AVAIL_MASK; atomic_inc(&rxnet->nr_calls); return call; diff --git a/net/rxrpc/input.c b/net/rxrpc/input.c index fbde8b824e23..667c44aa5a63 100644 --- a/net/rxrpc/input.c +++ b/net/rxrpc/input.c @@ -608,36 +608,57 @@ unlock: } /* - * Process a requested ACK. + * See if there's a cached RTT probe to complete. */ -static void rxrpc_input_requested_ack(struct rxrpc_call *call, - ktime_t resp_time, - rxrpc_serial_t orig_serial, - rxrpc_serial_t ack_serial) +static void rxrpc_complete_rtt_probe(struct rxrpc_call *call, + ktime_t resp_time, + rxrpc_serial_t acked_serial, + rxrpc_serial_t ack_serial, + enum rxrpc_rtt_rx_trace type) { - struct rxrpc_skb_priv *sp; - struct sk_buff *skb; + rxrpc_serial_t orig_serial; + unsigned long avail; ktime_t sent_at; - int ix; + bool matched = false; + int i; - for (ix = 0; ix < RXRPC_RXTX_BUFF_SIZE; ix++) { - skb = call->rxtx_buffer[ix]; - if (!skb) - continue; + avail = READ_ONCE(call->rtt_avail); + smp_rmb(); /* Read avail bits before accessing data. */ - sent_at = skb->tstamp; - smp_rmb(); /* Read timestamp before serial. */ - sp = rxrpc_skb(skb); - if (sp->hdr.serial != orig_serial) + for (i = 0; i < ARRAY_SIZE(call->rtt_serial); i++) { + if (!test_bit(i + RXRPC_CALL_RTT_PEND_SHIFT, &avail)) continue; - goto found; - } - return; + sent_at = call->rtt_sent_at[i]; + orig_serial = call->rtt_serial[i]; + + if (orig_serial == acked_serial) { + clear_bit(i + RXRPC_CALL_RTT_PEND_SHIFT, &call->rtt_avail); + smp_mb(); /* Read data before setting avail bit */ + set_bit(i, &call->rtt_avail); + if (type != rxrpc_rtt_rx_cancel) + rxrpc_peer_add_rtt(call, type, i, acked_serial, ack_serial, + sent_at, resp_time); + else + trace_rxrpc_rtt_rx(call, rxrpc_rtt_rx_cancel, i, + orig_serial, acked_serial, 0, 0); + matched = true; + } + + /* If a later serial is being acked, then mark this slot as + * being available. + */ + if (after(acked_serial, orig_serial)) { + trace_rxrpc_rtt_rx(call, rxrpc_rtt_rx_obsolete, i, + orig_serial, acked_serial, 0, 0); + clear_bit(i + RXRPC_CALL_RTT_PEND_SHIFT, &call->rtt_avail); + smp_wmb(); + set_bit(i, &call->rtt_avail); + } + } -found: - rxrpc_peer_add_rtt(call, rxrpc_rtt_rx_requested_ack, - orig_serial, ack_serial, sent_at, resp_time); + if (!matched) + trace_rxrpc_rtt_rx(call, rxrpc_rtt_rx_lost, 9, 0, acked_serial, 0, 0); } /* @@ -682,27 +703,11 @@ static void rxrpc_input_check_for_lost_ack(struct rxrpc_call *call) */ static void rxrpc_input_ping_response(struct rxrpc_call *call, ktime_t resp_time, - rxrpc_serial_t orig_serial, + rxrpc_serial_t acked_serial, rxrpc_serial_t ack_serial) { - rxrpc_serial_t ping_serial; - ktime_t ping_time; - - ping_time = call->ping_time; - smp_rmb(); - ping_serial = READ_ONCE(call->ping_serial); - - if (orig_serial == call->acks_lost_ping) + if (acked_serial == call->acks_lost_ping) rxrpc_input_check_for_lost_ack(call); - - if (before(orig_serial, ping_serial) || - !test_and_clear_bit(RXRPC_CALL_PINGING, &call->flags)) - return; - if (after(orig_serial, ping_serial)) - return; - - rxrpc_peer_add_rtt(call, rxrpc_rtt_rx_ping_response, - orig_serial, ack_serial, ping_time, resp_time); } /* @@ -843,7 +848,7 @@ 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; @@ -856,6 +861,7 @@ 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); @@ -864,31 +870,42 @@ 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) + switch (buf.ack.reason) { + case RXRPC_ACK_PING_RESPONSE: rxrpc_input_ping_response(call, skb->tstamp, acked_serial, - sp->hdr.serial); - if (buf.ack.reason == RXRPC_ACK_REQUESTED) - rxrpc_input_requested_ack(call, skb->tstamp, acked_serial, - sp->hdr.serial); + ack_serial); + rxrpc_complete_rtt_probe(call, skb->tstamp, acked_serial, ack_serial, + rxrpc_rtt_rx_ping_response); + break; + case RXRPC_ACK_REQUESTED: + rxrpc_complete_rtt_probe(call, skb->tstamp, acked_serial, ack_serial, + rxrpc_rtt_rx_requested_ack); + break; + default: + if (acked_serial != 0) + rxrpc_complete_rtt_probe(call, skb->tstamp, acked_serial, ack_serial, + rxrpc_rtt_rx_cancel); + break; + } 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; @@ -904,7 +921,7 @@ 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; @@ -964,7 +981,7 @@ 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/output.c b/net/rxrpc/output.c index 1ba43c3df4ad..3cfff7922ba8 100644 --- a/net/rxrpc/output.c +++ b/net/rxrpc/output.c @@ -124,6 +124,49 @@ static size_t rxrpc_fill_out_ack(struct rxrpc_connection *conn, } /* + * Record the beginning of an RTT probe. + */ +static int rxrpc_begin_rtt_probe(struct rxrpc_call *call, rxrpc_serial_t serial, + enum rxrpc_rtt_tx_trace why) +{ + unsigned long avail = call->rtt_avail; + int rtt_slot = 9; + + if (!(avail & RXRPC_CALL_RTT_AVAIL_MASK)) + goto no_slot; + + rtt_slot = __ffs(avail & RXRPC_CALL_RTT_AVAIL_MASK); + if (!test_and_clear_bit(rtt_slot, &call->rtt_avail)) + goto no_slot; + + call->rtt_serial[rtt_slot] = serial; + call->rtt_sent_at[rtt_slot] = ktime_get_real(); + smp_wmb(); /* Write data before avail bit */ + set_bit(rtt_slot + RXRPC_CALL_RTT_PEND_SHIFT, &call->rtt_avail); + + trace_rxrpc_rtt_tx(call, why, rtt_slot, serial); + return rtt_slot; + +no_slot: + trace_rxrpc_rtt_tx(call, rxrpc_rtt_tx_no_slot, rtt_slot, serial); + return -1; +} + +/* + * Cancel an RTT probe. + */ +static void rxrpc_cancel_rtt_probe(struct rxrpc_call *call, + rxrpc_serial_t serial, int rtt_slot) +{ + if (rtt_slot != -1) { + clear_bit(rtt_slot + RXRPC_CALL_RTT_PEND_SHIFT, &call->rtt_avail); + smp_wmb(); /* Clear pending bit before setting slot */ + set_bit(rtt_slot, &call->rtt_avail); + trace_rxrpc_rtt_tx(call, rxrpc_rtt_tx_cancel, rtt_slot, serial); + } +} + +/* * Send an ACK call packet. */ int rxrpc_send_ack_packet(struct rxrpc_call *call, bool ping, @@ -136,7 +179,7 @@ int rxrpc_send_ack_packet(struct rxrpc_call *call, bool ping, rxrpc_serial_t serial; rxrpc_seq_t hard_ack, top; size_t len, n; - int ret; + int ret, rtt_slot = -1; u8 reason; if (test_bit(RXRPC_CALL_DISCONNECTED, &call->flags)) @@ -196,18 +239,8 @@ int rxrpc_send_ack_packet(struct rxrpc_call *call, bool ping, if (_serial) *_serial = serial; - if (ping) { - call->ping_serial = serial; - smp_wmb(); - /* We need to stick a time in before we send the packet in case - * the reply gets back before kernel_sendmsg() completes - but - * asking UDP to send the packet can take a relatively long - * time. - */ - call->ping_time = ktime_get_real(); - set_bit(RXRPC_CALL_PINGING, &call->flags); - trace_rxrpc_rtt_tx(call, rxrpc_rtt_tx_ping, serial); - } + if (ping) + rtt_slot = rxrpc_begin_rtt_probe(call, serial, rxrpc_rtt_tx_ping); ret = kernel_sendmsg(conn->params.local->socket, &msg, iov, 2, len); conn->params.peer->last_tx_at = ktime_get_seconds(); @@ -221,8 +254,7 @@ int rxrpc_send_ack_packet(struct rxrpc_call *call, bool ping, if (call->state < RXRPC_CALL_COMPLETE) { if (ret < 0) { - if (ping) - clear_bit(RXRPC_CALL_PINGING, &call->flags); + rxrpc_cancel_rtt_probe(call, serial, rtt_slot); rxrpc_propose_ACK(call, pkt->ack.reason, ntohl(pkt->ack.serial), false, true, @@ -321,7 +353,7 @@ int rxrpc_send_data_packet(struct rxrpc_call *call, struct sk_buff *skb, struct kvec iov[2]; rxrpc_serial_t serial; size_t len; - int ret; + int ret, rtt_slot = -1; _enter(",{%d}", skb->len); @@ -397,6 +429,8 @@ int rxrpc_send_data_packet(struct rxrpc_call *call, struct sk_buff *skb, sp->hdr.serial = serial; smp_wmb(); /* Set serial before timestamp */ skb->tstamp = ktime_get_real(); + if (whdr.flags & RXRPC_REQUEST_ACK) + rtt_slot = rxrpc_begin_rtt_probe(call, serial, rxrpc_rtt_tx_data); /* send the packet by UDP * - returns -EMSGSIZE if UDP would have to fragment the packet @@ -408,12 +442,15 @@ int rxrpc_send_data_packet(struct rxrpc_call *call, struct sk_buff *skb, conn->params.peer->last_tx_at = ktime_get_seconds(); up_read(&conn->params.local->defrag_sem); - if (ret < 0) + if (ret < 0) { + rxrpc_cancel_rtt_probe(call, serial, rtt_slot); trace_rxrpc_tx_fail(call->debug_id, serial, ret, rxrpc_tx_point_call_data_nofrag); - else + } else { trace_rxrpc_tx_packet(call->debug_id, &whdr, rxrpc_tx_point_call_data_nofrag); + } + rxrpc_tx_backoff(call, ret); if (ret == -EMSGSIZE) goto send_fragmentable; @@ -422,7 +459,6 @@ done: if (ret >= 0) { if (whdr.flags & RXRPC_REQUEST_ACK) { call->peer->rtt_last_req = skb->tstamp; - trace_rxrpc_rtt_tx(call, rxrpc_rtt_tx_data, serial); if (call->peer->rtt_count > 1) { unsigned long nowj = jiffies, ack_lost_at; @@ -469,6 +505,8 @@ send_fragmentable: sp->hdr.serial = serial; smp_wmb(); /* Set serial before timestamp */ skb->tstamp = ktime_get_real(); + if (whdr.flags & RXRPC_REQUEST_ACK) + rtt_slot = rxrpc_begin_rtt_probe(call, serial, rxrpc_rtt_tx_data); switch (conn->params.local->srx.transport.family) { case AF_INET6: @@ -487,12 +525,14 @@ send_fragmentable: BUG(); } - if (ret < 0) + if (ret < 0) { + rxrpc_cancel_rtt_probe(call, serial, rtt_slot); trace_rxrpc_tx_fail(call->debug_id, serial, ret, rxrpc_tx_point_call_data_frag); - else + } else { trace_rxrpc_tx_packet(call->debug_id, &whdr, rxrpc_tx_point_call_data_frag); + } rxrpc_tx_backoff(call, ret); up_write(&conn->params.local->defrag_sem); diff --git a/net/rxrpc/peer_object.c b/net/rxrpc/peer_object.c index ca29976bb193..68396d052052 100644 --- a/net/rxrpc/peer_object.c +++ b/net/rxrpc/peer_object.c @@ -502,11 +502,21 @@ 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/rtt.c b/net/rxrpc/rtt.c index 928d8b34a3ee..1221b0637a7e 100644 --- a/net/rxrpc/rtt.c +++ b/net/rxrpc/rtt.c @@ -146,6 +146,7 @@ static void rxrpc_ack_update_rtt(struct rxrpc_peer *peer, long rtt_us) * exclusive access to the peer RTT data. */ void rxrpc_peer_add_rtt(struct rxrpc_call *call, enum rxrpc_rtt_rx_trace why, + int rtt_slot, rxrpc_serial_t send_serial, rxrpc_serial_t resp_serial, ktime_t send_time, ktime_t resp_time) { @@ -162,7 +163,7 @@ void rxrpc_peer_add_rtt(struct rxrpc_call *call, enum rxrpc_rtt_rx_trace why, peer->rtt_count++; spin_unlock(&peer->rtt_input_lock); - trace_rxrpc_rtt_rx(call, why, send_serial, resp_serial, + trace_rxrpc_rtt_rx(call, why, rtt_slot, send_serial, resp_serial, peer->srtt_us >> 3, peer->rto_j); } diff --git a/net/rxrpc/rxkad.c b/net/rxrpc/rxkad.c index 52a24d4ef5d8..e08130e5746b 100644 --- a/net/rxrpc/rxkad.c +++ b/net/rxrpc/rxkad.c @@ -1137,7 +1137,7 @@ static int rxkad_verify_response(struct rxrpc_connection *conn, ret = -ENOMEM; ticket = kmalloc(ticket_len, GFP_NOFS); if (!ticket) - goto temporary_error; + goto temporary_error_free_resp; eproto = tracepoint_string("rxkad_tkt_short"); abort_code = RXKADPACKETSHORT; @@ -1230,6 +1230,7 @@ protocol_error: temporary_error_free_ticket: kfree(ticket); +temporary_error_free_resp: kfree(response); temporary_error: /* Ignore the response packet if we got a temporary error such as diff --git a/net/sched/sch_red.c b/net/sched/sch_red.c index deac82f3ad7b..e89fab6ccb34 100644 --- a/net/sched/sch_red.c +++ b/net/sched/sch_red.c @@ -353,23 +353,11 @@ static int red_init(struct Qdisc *sch, struct nlattr *opt, FLOW_BLOCK_BINDER_TYPE_RED_EARLY_DROP, tb[TCA_RED_EARLY_DROP_BLOCK], extack); if (err) - goto err_early_drop_init; - - err = tcf_qevent_init(&q->qe_mark, sch, - FLOW_BLOCK_BINDER_TYPE_RED_MARK, - tb[TCA_RED_MARK_BLOCK], extack); - if (err) - goto err_mark_init; - - return 0; + return err; -err_mark_init: - tcf_qevent_destroy(&q->qe_early_drop, sch); -err_early_drop_init: - del_timer_sync(&q->adapt_timer); - red_offload(sch, false); - qdisc_put(q->qdisc); - return err; + return tcf_qevent_init(&q->qe_mark, sch, + FLOW_BLOCK_BINDER_TYPE_RED_MARK, + tb[TCA_RED_MARK_BLOCK], extack); } static int red_change(struct Qdisc *sch, struct nlattr *opt, diff --git a/net/sched/sch_taprio.c b/net/sched/sch_taprio.c index e981992634dd..fe53c1e38c7d 100644 --- a/net/sched/sch_taprio.c +++ b/net/sched/sch_taprio.c @@ -1176,9 +1176,27 @@ 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; @@ -1193,7 +1211,8 @@ 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++; } @@ -1201,7 +1220,6 @@ 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) @@ -1223,7 +1241,7 @@ 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) { @@ -1485,7 +1503,7 @@ 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/sctp/socket.c b/net/sctp/socket.c index ec1fba1fbe71..836615f71a7d 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -8060,8 +8060,6 @@ 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; @@ -8079,20 +8077,21 @@ static int sctp_get_port_local(struct sock *sk, union sctp_addr *addr) continue; index = sctp_phashfn(net, 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(net, 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 @@ -8107,7 +8106,7 @@ static int sctp_get_port_local(struct sock *sk, union sctp_addr *addr) * port iterator, pp being NULL. */ head = &sctp_port_hashtable[sctp_phashfn(net, 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, net)) goto pp_found; @@ -8207,10 +8206,7 @@ success: ret = 0; fail_unlock: - spin_unlock(&head->lock); - -fail: - local_bh_enable(); + spin_unlock_bh(&head->lock); return ret; } diff --git a/net/smc/smc_close.c b/net/smc/smc_close.c index 3b5c374c6d2c..0e7409e469c0 100644 --- a/net/smc/smc_close.c +++ b/net/smc/smc_close.c @@ -116,7 +116,6 @@ static void smc_close_cancel_work(struct smc_sock *smc) cancel_work_sync(&smc->conn.close_work); cancel_delayed_work_sync(&smc->conn.tx_work); lock_sock(sk); - sk->sk_state = SMC_CLOSED; } /* terminate smc socket abnormally - active abort @@ -134,22 +133,22 @@ void smc_close_active_abort(struct smc_sock *smc) } switch (sk->sk_state) { case SMC_ACTIVE: - sk->sk_state = SMC_PEERABORTWAIT; - smc_close_cancel_work(smc); - sk->sk_state = SMC_CLOSED; - sock_put(sk); /* passive closing */ - break; case SMC_APPCLOSEWAIT1: case SMC_APPCLOSEWAIT2: + sk->sk_state = SMC_PEERABORTWAIT; smc_close_cancel_work(smc); + if (sk->sk_state != SMC_PEERABORTWAIT) + break; sk->sk_state = SMC_CLOSED; - sock_put(sk); /* postponed passive closing */ + sock_put(sk); /* (postponed) passive closing */ break; case SMC_PEERCLOSEWAIT1: case SMC_PEERCLOSEWAIT2: case SMC_PEERFINCLOSEWAIT: sk->sk_state = SMC_PEERABORTWAIT; smc_close_cancel_work(smc); + if (sk->sk_state != SMC_PEERABORTWAIT) + break; sk->sk_state = SMC_CLOSED; smc_conn_free(&smc->conn); release_clcsock = true; @@ -159,6 +158,8 @@ void smc_close_active_abort(struct smc_sock *smc) case SMC_APPFINCLOSEWAIT: sk->sk_state = SMC_PEERABORTWAIT; smc_close_cancel_work(smc); + if (sk->sk_state != SMC_PEERABORTWAIT) + break; sk->sk_state = SMC_CLOSED; smc_conn_free(&smc->conn); release_clcsock = true; diff --git a/net/smc/smc_core.c b/net/smc/smc_core.c index b42fa3b00d00..a406627b1d55 100644 --- a/net/smc/smc_core.c +++ b/net/smc/smc_core.c @@ -1356,6 +1356,8 @@ create: if (ini->is_smcd) { conn->rx_off = sizeof(struct smcd_cdc_msg); smcd_cdc_rx_init(conn); /* init tasklet for this conn */ + } else { + conn->rx_off = 0; } #ifndef KERNEL_HAS_ATOMIC64 spin_lock_init(&conn->acurs_lock); @@ -1777,6 +1779,7 @@ int smc_buf_create(struct smc_sock *smc, bool is_smcd) list_del(&smc->conn.sndbuf_desc->list); mutex_unlock(&smc->conn.lgr->sndbufs_lock); smc_buf_free(smc->conn.lgr, false, smc->conn.sndbuf_desc); + smc->conn.sndbuf_desc = NULL; } return rc; } diff --git a/net/smc/smc_llc.c b/net/smc/smc_llc.c index df5b0a6ea848..3ea33466ebe9 100644 --- a/net/smc/smc_llc.c +++ b/net/smc/smc_llc.c @@ -841,6 +841,9 @@ int smc_llc_cli_add_link(struct smc_link *link, struct smc_llc_qentry *qentry) struct smc_init_info ini; int lnk_idx, rc = 0; + if (!llc->qp_mtu) + goto out_reject; + ini.vlan_id = lgr->vlan_id; smc_pnet_find_alt_roce(lgr, &ini, link->smcibdev); if (!memcmp(llc->sender_gid, link->peer_gid, SMC_GID_SIZE) && @@ -917,10 +920,20 @@ out: kfree(qentry); } +static bool smc_llc_is_empty_llc_message(union smc_llc_msg *llc) +{ + int i; + + for (i = 0; i < ARRAY_SIZE(llc->raw.data); i++) + if (llc->raw.data[i]) + return false; + return true; +} + static bool smc_llc_is_local_add_link(union smc_llc_msg *llc) { if (llc->raw.hdr.common.type == SMC_LLC_ADD_LINK && - !llc->add_link.qp_mtu && !llc->add_link.link_num) + smc_llc_is_empty_llc_message(llc)) return true; return false; } diff --git a/net/socket.c b/net/socket.c index dbbe8ea7d395..0c0144604f81 100644 --- a/net/socket.c +++ b/net/socket.c @@ -3610,7 +3610,7 @@ int kernel_getsockname(struct socket *sock, struct sockaddr *addr) EXPORT_SYMBOL(kernel_getsockname); /** - * kernel_peername - get the address which the socket is connected (kernel space) + * kernel_getpeername - get the address which the socket is connected (kernel space) * @sock: socket * @addr: address holder * @@ -3671,7 +3671,7 @@ int kernel_sendpage_locked(struct sock *sk, struct page *page, int offset, EXPORT_SYMBOL(kernel_sendpage_locked); /** - * kernel_shutdown - shut down part of a full-duplex connection (kernel space) + * kernel_sock_shutdown - shut down part of a full-duplex connection (kernel space) * @sock: socket * @how: connection part * diff --git a/net/tipc/crypto.c b/net/tipc/crypto.c index c38babaa4e57..7c523dc81575 100644 --- a/net/tipc/crypto.c +++ b/net/tipc/crypto.c @@ -326,7 +326,8 @@ static void tipc_aead_free(struct rcu_head *rp) if (aead->cloned) { tipc_aead_put(aead->cloned); } else { - head = *this_cpu_ptr(aead->tfm_entry); + head = *get_cpu_ptr(aead->tfm_entry); + put_cpu_ptr(aead->tfm_entry); list_for_each_entry_safe(tfm_entry, tmp, &head->list, list) { crypto_free_aead(tfm_entry->tfm); list_del(&tfm_entry->list); @@ -399,10 +400,15 @@ static void tipc_aead_users_set(struct tipc_aead __rcu *aead, int val) */ static struct crypto_aead *tipc_aead_tfm_next(struct tipc_aead *aead) { - struct tipc_tfm **tfm_entry = this_cpu_ptr(aead->tfm_entry); + struct tipc_tfm **tfm_entry; + struct crypto_aead *tfm; + tfm_entry = get_cpu_ptr(aead->tfm_entry); *tfm_entry = list_next_entry(*tfm_entry, list); - return (*tfm_entry)->tfm; + tfm = (*tfm_entry)->tfm; + put_cpu_ptr(tfm_entry); + + return tfm; } /** diff --git a/net/tipc/socket.c b/net/tipc/socket.c index 2679e97e0389..ebd280e767bd 100644 --- a/net/tipc/socket.c +++ b/net/tipc/socket.c @@ -2771,18 +2771,21 @@ 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; + if (tipc_sk_type_connectionless(sk)) + sk->sk_shutdown = SHUTDOWN_MASK; + else + sk->sk_shutdown = SEND_SHUTDOWN; 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/wireless/chan.c b/net/wireless/chan.c index e97a4f0c32a3..6a6f2f214c10 100644 --- a/net/wireless/chan.c +++ b/net/wireless/chan.c @@ -10,6 +10,7 @@ */ #include <linux/export.h> +#include <linux/bitfield.h> #include <net/cfg80211.h> #include "core.h" #include "rdev-ops.h" @@ -912,6 +913,7 @@ bool cfg80211_chandef_usable(struct wiphy *wiphy, struct ieee80211_sta_vht_cap *vht_cap; struct ieee80211_edmg *edmg_cap; u32 width, control_freq, cap; + bool support_80_80 = false; if (WARN_ON(!cfg80211_chandef_valid(chandef))) return false; @@ -979,9 +981,13 @@ bool cfg80211_chandef_usable(struct wiphy *wiphy, return false; break; case NL80211_CHAN_WIDTH_80P80: - cap = vht_cap->cap & IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_MASK; - if (chandef->chan->band != NL80211_BAND_6GHZ && - cap != IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_160_80PLUS80MHZ) + cap = vht_cap->cap; + support_80_80 = + (cap & IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_160_80PLUS80MHZ) || + (cap & IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_160MHZ && + cap & IEEE80211_VHT_CAP_EXT_NSS_BW_MASK) || + u32_get_bits(cap, IEEE80211_VHT_CAP_EXT_NSS_BW_MASK) > 1; + if (chandef->chan->band != NL80211_BAND_6GHZ && !support_80_80) return false; fallthrough; case NL80211_CHAN_WIDTH_80: @@ -1001,7 +1007,8 @@ bool cfg80211_chandef_usable(struct wiphy *wiphy, return false; cap = vht_cap->cap & IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_MASK; if (cap != IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_160MHZ && - cap != IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_160_80PLUS80MHZ) + cap != IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_160_80PLUS80MHZ && + !(vht_cap->cap & IEEE80211_VHT_CAP_EXT_NSS_BW_MASK)) return false; break; default: diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index fde420af3f00..2c9e9a2d1688 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -6011,7 +6011,7 @@ static int nl80211_set_station(struct sk_buff *skb, struct genl_info *info) if (info->attrs[NL80211_ATTR_HE_6GHZ_CAPABILITY]) params.he_6ghz_capa = - nla_data(info->attrs[NL80211_ATTR_HE_CAPABILITY]); + nla_data(info->attrs[NL80211_ATTR_HE_6GHZ_CAPABILITY]); if (info->attrs[NL80211_ATTR_AIRTIME_WEIGHT]) params.airtime_weight = diff --git a/net/wireless/reg.c b/net/wireless/reg.c index 35b8847a2f6d..d8a90d397423 100644 --- a/net/wireless/reg.c +++ b/net/wireless/reg.c @@ -2946,6 +2946,9 @@ 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 7c5d5365a5eb..4a9ff9ef513f 100644 --- a/net/wireless/util.c +++ b/net/wireless/util.c @@ -123,11 +123,13 @@ int ieee80211_freq_khz_to_channel(u32 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 |