diff options
Diffstat (limited to 'net')
275 files changed, 17461 insertions, 2580 deletions
diff --git a/net/8021q/vlan_dev.c b/net/8021q/vlan_dev.c index 2a78da4072de..990b9fde28c6 100644 --- a/net/8021q/vlan_dev.c +++ b/net/8021q/vlan_dev.c @@ -647,8 +647,8 @@ static int vlan_ethtool_get_ts_info(struct net_device *dev, const struct ethtool_ops *ops = vlan->real_dev->ethtool_ops; struct phy_device *phydev = vlan->real_dev->phydev; - if (phydev && phydev->drv && phydev->drv->ts_info) { - return phydev->drv->ts_info(phydev, info); + if (phy_has_tsinfo(phydev)) { + return phy_ts_info(phydev, info); } else if (ops->get_ts_info) { return ops->get_ts_info(vlan->real_dev, info); } else { diff --git a/net/Kconfig b/net/Kconfig index bd191f978a23..b0937a700f01 100644 --- a/net/Kconfig +++ b/net/Kconfig @@ -91,6 +91,7 @@ if INET source "net/ipv4/Kconfig" source "net/ipv6/Kconfig" source "net/netlabel/Kconfig" +source "net/mptcp/Kconfig" endif # if INET @@ -108,9 +109,10 @@ config NETWORK_PHY_TIMESTAMPING bool "Timestamping in PHY devices" select NET_PTP_CLASSIFY help - This allows timestamping of network packets by PHYs with - hardware timestamping capabilities. This option adds some - overhead in the transmit and receive paths. + This allows timestamping of network packets by PHYs (or + other MII bus snooping devices) with hardware timestamping + capabilities. This option adds some overhead in the transmit + and receive paths. If you are unsure how to answer this question, answer N. @@ -448,6 +450,14 @@ config FAILOVER migration of VMs with direct attached VFs by failing over to the paravirtual datapath when the VF is unplugged. +config ETHTOOL_NETLINK + bool "Netlink interface for ethtool" + default y + help + An alternative userspace interface for ethtool based on generic + netlink. It provides better extensibility and some new features, + e.g. notification messages. + endif # if NET # Used by archs to tell that they support BPF JIT compiler plus which flavour. diff --git a/net/Makefile b/net/Makefile index 449fc0b221f8..07ea48160874 100644 --- a/net/Makefile +++ b/net/Makefile @@ -13,7 +13,7 @@ obj-$(CONFIG_NET) += $(tmp-y) # LLC has to be linked before the files in net/802/ obj-$(CONFIG_LLC) += llc/ -obj-$(CONFIG_NET) += ethernet/ 802/ sched/ netlink/ bpf/ +obj-$(CONFIG_NET) += ethernet/ 802/ sched/ netlink/ bpf/ ethtool/ obj-$(CONFIG_NETFILTER) += netfilter/ obj-$(CONFIG_INET) += ipv4/ obj-$(CONFIG_TLS) += tls/ @@ -87,3 +87,4 @@ endif obj-$(CONFIG_QRTR) += qrtr/ obj-$(CONFIG_NET_NCSI) += ncsi/ obj-$(CONFIG_XDP_SOCKETS) += xdp/ +obj-$(CONFIG_MPTCP) += mptcp/ diff --git a/net/atm/atm_sysfs.c b/net/atm/atm_sysfs.c index 39b94ca5f65d..aa1b57161f3b 100644 --- a/net/atm/atm_sysfs.c +++ b/net/atm/atm_sysfs.c @@ -33,23 +33,17 @@ static ssize_t show_atmaddress(struct device *cdev, unsigned long flags; struct atm_dev *adev = to_atm_dev(cdev); struct atm_dev_addr *aaddr; - int bin[] = { 1, 2, 10, 6, 1 }, *fmt = bin; - int i, j, count = 0; + int count = 0; spin_lock_irqsave(&adev->lock, flags); list_for_each_entry(aaddr, &adev->local, entry) { - for (i = 0, j = 0; i < ATM_ESA_LEN; ++i, ++j) { - if (j == *fmt) { - count += scnprintf(buf + count, - PAGE_SIZE - count, "."); - ++fmt; - j = 0; - } - count += scnprintf(buf + count, - PAGE_SIZE - count, "%02x", - aaddr->addr.sas_addr.prv[i]); - } - count += scnprintf(buf + count, PAGE_SIZE - count, "\n"); + count += scnprintf(buf + count, PAGE_SIZE - count, + "%1phN.%2phN.%10phN.%6phN.%1phN\n", + &aaddr->addr.sas_addr.prv[0], + &aaddr->addr.sas_addr.prv[1], + &aaddr->addr.sas_addr.prv[3], + &aaddr->addr.sas_addr.prv[13], + &aaddr->addr.sas_addr.prv[19]); } spin_unlock_irqrestore(&adev->lock, flags); diff --git a/net/atm/lec.c b/net/atm/lec.c index 5a77c235a212..25fa3a7b72bd 100644 --- a/net/atm/lec.c +++ b/net/atm/lec.c @@ -194,7 +194,7 @@ lec_send(struct atm_vcc *vcc, struct sk_buff *skb) dev->stats.tx_bytes += skb->len; } -static void lec_tx_timeout(struct net_device *dev) +static void lec_tx_timeout(struct net_device *dev, unsigned int txqueue) { pr_info("%s\n", dev->name); netif_trans_update(dev); @@ -799,14 +799,9 @@ static const char *lec_arp_get_status_string(unsigned char status) static void lec_info(struct seq_file *seq, struct lec_arp_table *entry) { - int i; - - for (i = 0; i < ETH_ALEN; i++) - seq_printf(seq, "%2.2x", entry->mac_addr[i] & 0xff); - seq_printf(seq, " "); - for (i = 0; i < ATM_ESA_LEN; i++) - seq_printf(seq, "%2.2x", entry->atm_addr[i] & 0xff); - seq_printf(seq, " %s %4.4x", lec_arp_get_status_string(entry->status), + seq_printf(seq, "%pM ", entry->mac_addr); + seq_printf(seq, "%*phN ", ATM_ESA_LEN, entry->atm_addr); + seq_printf(seq, "%s %4.4x", lec_arp_get_status_string(entry->status), entry->flags & 0xffff); if (entry->vcc) seq_printf(seq, "%3d %3d ", entry->vcc->vpi, entry->vcc->vci); @@ -1354,7 +1349,7 @@ static void dump_arp_table(struct lec_priv *priv) { struct lec_arp_table *rulla; char buf[256]; - int i, j, offset; + int i, offset; pr_info("Dump %p:\n", priv); for (i = 0; i < LEC_ARP_TABLE_SIZE; i++) { @@ -1362,14 +1357,10 @@ static void dump_arp_table(struct lec_priv *priv) &priv->lec_arp_tables[i], next) { offset = 0; offset += sprintf(buf, "%d: %p\n", i, rulla); - offset += sprintf(buf + offset, "Mac: %pM", + offset += sprintf(buf + offset, "Mac: %pM ", rulla->mac_addr); - offset += sprintf(buf + offset, " Atm:"); - for (j = 0; j < ATM_ESA_LEN; j++) { - offset += sprintf(buf + offset, - "%2.2x ", - rulla->atm_addr[j] & 0xff); - } + offset += sprintf(buf + offset, "Atm: %*ph ", ATM_ESA_LEN, + rulla->atm_addr); offset += sprintf(buf + offset, "Vcc vpi:%d vci:%d, Recv_vcc vpi:%d vci:%d Last_used:%lx, Timestamp:%lx, No_tries:%d ", rulla->vcc ? rulla->vcc->vpi : 0, @@ -1392,12 +1383,9 @@ static void dump_arp_table(struct lec_priv *priv) pr_info("No forward\n"); hlist_for_each_entry(rulla, &priv->lec_no_forward, next) { offset = 0; - offset += sprintf(buf + offset, "Mac: %pM", rulla->mac_addr); - offset += sprintf(buf + offset, " Atm:"); - for (j = 0; j < ATM_ESA_LEN; j++) { - offset += sprintf(buf + offset, "%2.2x ", - rulla->atm_addr[j] & 0xff); - } + offset += sprintf(buf + offset, "Mac: %pM ", rulla->mac_addr); + offset += sprintf(buf + offset, "Atm: %*ph ", ATM_ESA_LEN, + rulla->atm_addr); offset += sprintf(buf + offset, "Vcc vpi:%d vci:%d, Recv_vcc vpi:%d vci:%d Last_used:%lx, Timestamp:%lx, No_tries:%d ", rulla->vcc ? rulla->vcc->vpi : 0, @@ -1417,12 +1405,9 @@ static void dump_arp_table(struct lec_priv *priv) pr_info("Empty ones\n"); hlist_for_each_entry(rulla, &priv->lec_arp_empty_ones, next) { offset = 0; - offset += sprintf(buf + offset, "Mac: %pM", rulla->mac_addr); - offset += sprintf(buf + offset, " Atm:"); - for (j = 0; j < ATM_ESA_LEN; j++) { - offset += sprintf(buf + offset, "%2.2x ", - rulla->atm_addr[j] & 0xff); - } + offset += sprintf(buf + offset, "Mac: %pM ", rulla->mac_addr); + offset += sprintf(buf + offset, "Atm: %*ph ", ATM_ESA_LEN, + rulla->atm_addr); offset += sprintf(buf + offset, "Vcc vpi:%d vci:%d, Recv_vcc vpi:%d vci:%d Last_used:%lx, Timestamp:%lx, No_tries:%d ", rulla->vcc ? rulla->vcc->vpi : 0, @@ -1442,12 +1427,9 @@ static void dump_arp_table(struct lec_priv *priv) pr_info("Multicast Forward VCCs\n"); hlist_for_each_entry(rulla, &priv->mcast_fwds, next) { offset = 0; - offset += sprintf(buf + offset, "Mac: %pM", rulla->mac_addr); - offset += sprintf(buf + offset, " Atm:"); - for (j = 0; j < ATM_ESA_LEN; j++) { - offset += sprintf(buf + offset, "%2.2x ", - rulla->atm_addr[j] & 0xff); - } + offset += sprintf(buf + offset, "Mac: %pM ", rulla->mac_addr); + offset += sprintf(buf + offset, "Atm: %*ph ", ATM_ESA_LEN, + rulla->atm_addr); offset += sprintf(buf + offset, "Vcc vpi:%d vci:%d, Recv_vcc vpi:%d vci:%d Last_used:%lx, Timestamp:%lx, No_tries:%d ", rulla->vcc ? rulla->vcc->vpi : 0, @@ -1973,17 +1955,8 @@ lec_vcc_added(struct lec_priv *priv, const struct atmlec_ioc *ioc_data, * Vcc which we don't want to make default vcc, * attach it anyway. */ - pr_debug("LEC_ARP:Attaching data direct, not default: %2.2x%2.2x%2.2x%2.2x%2.2x%2.2x%2.2x%2.2x%2.2x%2.2x%2.2x%2.2x%2.2x%2.2x%2.2x%2.2x%2.2x%2.2x%2.2x%2.2x\n", - ioc_data->atm_addr[0], ioc_data->atm_addr[1], - ioc_data->atm_addr[2], ioc_data->atm_addr[3], - ioc_data->atm_addr[4], ioc_data->atm_addr[5], - ioc_data->atm_addr[6], ioc_data->atm_addr[7], - ioc_data->atm_addr[8], ioc_data->atm_addr[9], - ioc_data->atm_addr[10], ioc_data->atm_addr[11], - ioc_data->atm_addr[12], ioc_data->atm_addr[13], - ioc_data->atm_addr[14], ioc_data->atm_addr[15], - ioc_data->atm_addr[16], ioc_data->atm_addr[17], - ioc_data->atm_addr[18], ioc_data->atm_addr[19]); + pr_debug("LEC_ARP:Attaching data direct, not default: %*phN\n", + ATM_ESA_LEN, ioc_data->atm_addr); entry = make_entry(priv, bus_mac); if (entry == NULL) goto out; @@ -1999,17 +1972,8 @@ lec_vcc_added(struct lec_priv *priv, const struct atmlec_ioc *ioc_data, dump_arp_table(priv); goto out; } - pr_debug("LEC_ARP:Attaching data direct, default: %2.2x%2.2x%2.2x%2.2x%2.2x%2.2x%2.2x%2.2x%2.2x%2.2x%2.2x%2.2x%2.2x%2.2x%2.2x%2.2x%2.2x%2.2x%2.2x%2.2x\n", - ioc_data->atm_addr[0], ioc_data->atm_addr[1], - ioc_data->atm_addr[2], ioc_data->atm_addr[3], - ioc_data->atm_addr[4], ioc_data->atm_addr[5], - ioc_data->atm_addr[6], ioc_data->atm_addr[7], - ioc_data->atm_addr[8], ioc_data->atm_addr[9], - ioc_data->atm_addr[10], ioc_data->atm_addr[11], - ioc_data->atm_addr[12], ioc_data->atm_addr[13], - ioc_data->atm_addr[14], ioc_data->atm_addr[15], - ioc_data->atm_addr[16], ioc_data->atm_addr[17], - ioc_data->atm_addr[18], ioc_data->atm_addr[19]); + pr_debug("LEC_ARP:Attaching data direct, default: %*phN\n", + ATM_ESA_LEN, ioc_data->atm_addr); for (i = 0; i < LEC_ARP_TABLE_SIZE; i++) { hlist_for_each_entry(entry, &priv->lec_arp_tables[i], next) { diff --git a/net/ax25/af_ax25.c b/net/ax25/af_ax25.c index 324306d6fde0..ff57ea89c27e 100644 --- a/net/ax25/af_ax25.c +++ b/net/ax25/af_ax25.c @@ -808,7 +808,7 @@ static int ax25_create(struct net *net, struct socket *sock, int protocol, struct sock *sk; ax25_cb *ax25; - if (protocol < 0 || protocol > SK_PROTOCOL_MAX) + if (protocol < 0 || protocol > U8_MAX) return -EINVAL; if (!net_eq(net, &init_net)) diff --git a/net/batman-adv/Kconfig b/net/batman-adv/Kconfig index d5028af750d5..c762758a4649 100644 --- a/net/batman-adv/Kconfig +++ b/net/batman-adv/Kconfig @@ -1,5 +1,5 @@ # SPDX-License-Identifier: GPL-2.0 -# Copyright (C) 2007-2019 B.A.T.M.A.N. contributors: +# Copyright (C) 2007-2020 B.A.T.M.A.N. contributors: # # Marek Lindner, Simon Wunderlich @@ -100,7 +100,6 @@ config BATMAN_ADV_DEBUG config BATMAN_ADV_SYSFS bool "batman-adv sysfs entries" depends on BATMAN_ADV - default y help Say Y here if you want to enable batman-adv device configuration and status interface through sysfs attributes. It is replaced by the diff --git a/net/batman-adv/Makefile b/net/batman-adv/Makefile index fd63e116d9ff..daa49af7ff40 100644 --- a/net/batman-adv/Makefile +++ b/net/batman-adv/Makefile @@ -1,5 +1,5 @@ # SPDX-License-Identifier: GPL-2.0 -# Copyright (C) 2007-2019 B.A.T.M.A.N. contributors: +# Copyright (C) 2007-2020 B.A.T.M.A.N. contributors: # # Marek Lindner, Simon Wunderlich diff --git a/net/batman-adv/bat_algo.c b/net/batman-adv/bat_algo.c index fa39eaaab9d7..382fbe51fd34 100644 --- a/net/batman-adv/bat_algo.c +++ b/net/batman-adv/bat_algo.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright (C) 2007-2019 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2020 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich */ diff --git a/net/batman-adv/bat_algo.h b/net/batman-adv/bat_algo.h index 37898da8ad48..686a60bc9492 100644 --- a/net/batman-adv/bat_algo.h +++ b/net/batman-adv/bat_algo.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright (C) 2011-2019 B.A.T.M.A.N. contributors: +/* Copyright (C) 2011-2020 B.A.T.M.A.N. contributors: * * Marek Lindner, Linus Lüssing */ diff --git a/net/batman-adv/bat_iv_ogm.c b/net/batman-adv/bat_iv_ogm.c index 5b0b20e6da95..f0209505e41a 100644 --- a/net/batman-adv/bat_iv_ogm.c +++ b/net/batman-adv/bat_iv_ogm.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright (C) 2007-2019 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2020 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich */ diff --git a/net/batman-adv/bat_iv_ogm.h b/net/batman-adv/bat_iv_ogm.h index c7a9ba305bfc..0c57c1000c64 100644 --- a/net/batman-adv/bat_iv_ogm.h +++ b/net/batman-adv/bat_iv_ogm.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright (C) 2007-2019 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2020 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich */ diff --git a/net/batman-adv/bat_v.c b/net/batman-adv/bat_v.c index 4ff6cf1ecae7..0ecaf1bb0068 100644 --- a/net/batman-adv/bat_v.c +++ b/net/batman-adv/bat_v.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright (C) 2013-2019 B.A.T.M.A.N. contributors: +/* Copyright (C) 2013-2020 B.A.T.M.A.N. contributors: * * Linus Lüssing, Marek Lindner */ diff --git a/net/batman-adv/bat_v.h b/net/batman-adv/bat_v.h index 37833db098e6..5e0be10bc84e 100644 --- a/net/batman-adv/bat_v.h +++ b/net/batman-adv/bat_v.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright (C) 2011-2019 B.A.T.M.A.N. contributors: +/* Copyright (C) 2011-2020 B.A.T.M.A.N. contributors: * * Marek Lindner, Linus Lüssing */ diff --git a/net/batman-adv/bat_v_elp.c b/net/batman-adv/bat_v_elp.c index 2614a9caee00..1e3172db7492 100644 --- a/net/batman-adv/bat_v_elp.c +++ b/net/batman-adv/bat_v_elp.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright (C) 2011-2019 B.A.T.M.A.N. contributors: +/* Copyright (C) 2011-2020 B.A.T.M.A.N. contributors: * * Linus Lüssing, Marek Lindner */ @@ -107,10 +107,17 @@ static u32 batadv_v_elp_get_throughput(struct batadv_hardif_neigh_node *neigh) } if (ret) goto default_throughput; - if (!(sinfo.filled & BIT(NL80211_STA_INFO_EXPECTED_THROUGHPUT))) - goto default_throughput; - return sinfo.expected_throughput / 100; + if (sinfo.filled & BIT(NL80211_STA_INFO_EXPECTED_THROUGHPUT)) + return sinfo.expected_throughput / 100; + + /* try to estimate the expected throughput based on reported tx + * rates + */ + if (sinfo.filled & BIT(NL80211_STA_INFO_TX_BITRATE)) + return cfg80211_calculate_bitrate(&sinfo.txrate) / 3; + + goto default_throughput; } /* if not a wifi interface, check if this device provides data via diff --git a/net/batman-adv/bat_v_elp.h b/net/batman-adv/bat_v_elp.h index 1a29505f4f66..4358d436be2a 100644 --- a/net/batman-adv/bat_v_elp.h +++ b/net/batman-adv/bat_v_elp.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright (C) 2013-2019 B.A.T.M.A.N. contributors: +/* Copyright (C) 2013-2020 B.A.T.M.A.N. contributors: * * Linus Lüssing, Marek Lindner */ diff --git a/net/batman-adv/bat_v_ogm.c b/net/batman-adv/bat_v_ogm.c index 714ce56cfcc8..969466218999 100644 --- a/net/batman-adv/bat_v_ogm.c +++ b/net/batman-adv/bat_v_ogm.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright (C) 2013-2019 B.A.T.M.A.N. contributors: +/* Copyright (C) 2013-2020 B.A.T.M.A.N. contributors: * * Antonio Quartulli */ diff --git a/net/batman-adv/bat_v_ogm.h b/net/batman-adv/bat_v_ogm.h index bf16d040461d..0ae2575f70bb 100644 --- a/net/batman-adv/bat_v_ogm.h +++ b/net/batman-adv/bat_v_ogm.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright (C) 2013-2019 B.A.T.M.A.N. contributors: +/* Copyright (C) 2013-2020 B.A.T.M.A.N. contributors: * * Antonio Quartulli */ diff --git a/net/batman-adv/bitarray.c b/net/batman-adv/bitarray.c index 7f04a6acf14e..4bc695cda397 100644 --- a/net/batman-adv/bitarray.c +++ b/net/batman-adv/bitarray.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright (C) 2006-2019 B.A.T.M.A.N. contributors: +/* Copyright (C) 2006-2020 B.A.T.M.A.N. contributors: * * Simon Wunderlich, Marek Lindner */ diff --git a/net/batman-adv/bitarray.h b/net/batman-adv/bitarray.h index 84ad2d2b6ac9..533c6d44cb58 100644 --- a/net/batman-adv/bitarray.h +++ b/net/batman-adv/bitarray.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright (C) 2006-2019 B.A.T.M.A.N. contributors: +/* Copyright (C) 2006-2020 B.A.T.M.A.N. contributors: * * Simon Wunderlich, Marek Lindner */ diff --git a/net/batman-adv/bridge_loop_avoidance.c b/net/batman-adv/bridge_loop_avoidance.c index 663a53b6d36e..41cc87f06b14 100644 --- a/net/batman-adv/bridge_loop_avoidance.c +++ b/net/batman-adv/bridge_loop_avoidance.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright (C) 2011-2019 B.A.T.M.A.N. contributors: +/* Copyright (C) 2011-2020 B.A.T.M.A.N. contributors: * * Simon Wunderlich */ @@ -844,7 +844,7 @@ static bool batadv_handle_announce(struct batadv_priv *bat_priv, u8 *an_addr, /* handle as ANNOUNCE frame */ backbone_gw->lasttime = jiffies; - crc = ntohs(*((__be16 *)(&an_addr[4]))); + crc = ntohs(*((__force __be16 *)(&an_addr[4]))); batadv_dbg(BATADV_DBG_BLA, bat_priv, "%s(): ANNOUNCE vid %d (sent by %pM)... CRC = %#.4x\n", diff --git a/net/batman-adv/bridge_loop_avoidance.h b/net/batman-adv/bridge_loop_avoidance.h index 02b24a861a85..41edb2c4a327 100644 --- a/net/batman-adv/bridge_loop_avoidance.h +++ b/net/batman-adv/bridge_loop_avoidance.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright (C) 2011-2019 B.A.T.M.A.N. contributors: +/* Copyright (C) 2011-2020 B.A.T.M.A.N. contributors: * * Simon Wunderlich */ diff --git a/net/batman-adv/debugfs.c b/net/batman-adv/debugfs.c index 38c4d8e51155..452856c27d20 100644 --- a/net/batman-adv/debugfs.c +++ b/net/batman-adv/debugfs.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright (C) 2010-2019 B.A.T.M.A.N. contributors: +/* Copyright (C) 2010-2020 B.A.T.M.A.N. contributors: * * Marek Lindner */ diff --git a/net/batman-adv/debugfs.h b/net/batman-adv/debugfs.h index 1c5afd301ce9..7e2e8f586f42 100644 --- a/net/batman-adv/debugfs.h +++ b/net/batman-adv/debugfs.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright (C) 2010-2019 B.A.T.M.A.N. contributors: +/* Copyright (C) 2010-2020 B.A.T.M.A.N. contributors: * * Marek Lindner */ diff --git a/net/batman-adv/distributed-arp-table.c b/net/batman-adv/distributed-arp-table.c index ec7bf5a4a9fc..3d21dd83f8cc 100644 --- a/net/batman-adv/distributed-arp-table.c +++ b/net/batman-adv/distributed-arp-table.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright (C) 2011-2019 B.A.T.M.A.N. contributors: +/* Copyright (C) 2011-2020 B.A.T.M.A.N. contributors: * * Antonio Quartulli */ @@ -246,7 +246,7 @@ static u8 *batadv_arp_hw_src(struct sk_buff *skb, int hdr_size) */ static __be32 batadv_arp_ip_src(struct sk_buff *skb, int hdr_size) { - return *(__be32 *)(batadv_arp_hw_src(skb, hdr_size) + ETH_ALEN); + return *(__force __be32 *)(batadv_arp_hw_src(skb, hdr_size) + ETH_ALEN); } /** @@ -270,7 +270,9 @@ static u8 *batadv_arp_hw_dst(struct sk_buff *skb, int hdr_size) */ static __be32 batadv_arp_ip_dst(struct sk_buff *skb, int hdr_size) { - return *(__be32 *)(batadv_arp_hw_src(skb, hdr_size) + ETH_ALEN * 2 + 4); + u8 *dst = batadv_arp_hw_src(skb, hdr_size) + ETH_ALEN * 2 + 4; + + return *(__force __be32 *)dst; } /** @@ -288,7 +290,7 @@ static u32 batadv_hash_dat(const void *data, u32 size) __be16 vid; u32 i; - key = (const unsigned char *)&dat->ip; + key = (__force const unsigned char *)&dat->ip; for (i = 0; i < sizeof(dat->ip); i++) { hash += key[i]; hash += (hash << 10); diff --git a/net/batman-adv/distributed-arp-table.h b/net/batman-adv/distributed-arp-table.h index 67c7729add55..2bff2f4a325c 100644 --- a/net/batman-adv/distributed-arp-table.h +++ b/net/batman-adv/distributed-arp-table.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright (C) 2011-2019 B.A.T.M.A.N. contributors: +/* Copyright (C) 2011-2020 B.A.T.M.A.N. contributors: * * Antonio Quartulli */ diff --git a/net/batman-adv/fragmentation.c b/net/batman-adv/fragmentation.c index 385fccdcf69d..7cad97644d05 100644 --- a/net/batman-adv/fragmentation.c +++ b/net/batman-adv/fragmentation.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright (C) 2013-2019 B.A.T.M.A.N. contributors: +/* Copyright (C) 2013-2020 B.A.T.M.A.N. contributors: * * Martin Hundebøll <martin@hundeboll.net> */ diff --git a/net/batman-adv/fragmentation.h b/net/batman-adv/fragmentation.h index abfe8c6556de..881ef328b6cd 100644 --- a/net/batman-adv/fragmentation.h +++ b/net/batman-adv/fragmentation.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright (C) 2013-2019 B.A.T.M.A.N. contributors: +/* Copyright (C) 2013-2020 B.A.T.M.A.N. contributors: * * Martin Hundebøll <martin@hundeboll.net> */ diff --git a/net/batman-adv/gateway_client.c b/net/batman-adv/gateway_client.c index 47df4c678988..e22e49289677 100644 --- a/net/batman-adv/gateway_client.c +++ b/net/batman-adv/gateway_client.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright (C) 2009-2019 B.A.T.M.A.N. contributors: +/* Copyright (C) 2009-2020 B.A.T.M.A.N. contributors: * * Marek Lindner */ diff --git a/net/batman-adv/gateway_client.h b/net/batman-adv/gateway_client.h index 0be8e7178ec7..88b5dba84354 100644 --- a/net/batman-adv/gateway_client.h +++ b/net/batman-adv/gateway_client.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright (C) 2009-2019 B.A.T.M.A.N. contributors: +/* Copyright (C) 2009-2020 B.A.T.M.A.N. contributors: * * Marek Lindner */ diff --git a/net/batman-adv/gateway_common.c b/net/batman-adv/gateway_common.c index fc55750542e4..16cd9450ceb1 100644 --- a/net/batman-adv/gateway_common.c +++ b/net/batman-adv/gateway_common.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright (C) 2009-2019 B.A.T.M.A.N. contributors: +/* Copyright (C) 2009-2020 B.A.T.M.A.N. contributors: * * Marek Lindner */ diff --git a/net/batman-adv/gateway_common.h b/net/batman-adv/gateway_common.h index 211b14b37db8..c3a0c5a7f7e9 100644 --- a/net/batman-adv/gateway_common.h +++ b/net/batman-adv/gateway_common.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright (C) 2009-2019 B.A.T.M.A.N. contributors: +/* Copyright (C) 2009-2020 B.A.T.M.A.N. contributors: * * Marek Lindner */ diff --git a/net/batman-adv/hard-interface.c b/net/batman-adv/hard-interface.c index afb52282d5bd..c7e98a40dd33 100644 --- a/net/batman-adv/hard-interface.c +++ b/net/batman-adv/hard-interface.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright (C) 2007-2019 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2020 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich */ diff --git a/net/batman-adv/hard-interface.h b/net/batman-adv/hard-interface.h index bbb8a6f18d6b..bad2e50135e8 100644 --- a/net/batman-adv/hard-interface.h +++ b/net/batman-adv/hard-interface.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright (C) 2007-2019 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2020 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich */ diff --git a/net/batman-adv/hash.c b/net/batman-adv/hash.c index a9d4e176f4de..68638e0450a6 100644 --- a/net/batman-adv/hash.c +++ b/net/batman-adv/hash.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright (C) 2006-2019 B.A.T.M.A.N. contributors: +/* Copyright (C) 2006-2020 B.A.T.M.A.N. contributors: * * Simon Wunderlich, Marek Lindner */ diff --git a/net/batman-adv/hash.h b/net/batman-adv/hash.h index 57877f0b78e0..91ae9f32b580 100644 --- a/net/batman-adv/hash.h +++ b/net/batman-adv/hash.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright (C) 2006-2019 B.A.T.M.A.N. contributors: +/* Copyright (C) 2006-2020 B.A.T.M.A.N. contributors: * * Simon Wunderlich, Marek Lindner */ diff --git a/net/batman-adv/icmp_socket.c b/net/batman-adv/icmp_socket.c index 0a70b66e8770..ccb535c77e5d 100644 --- a/net/batman-adv/icmp_socket.c +++ b/net/batman-adv/icmp_socket.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright (C) 2007-2019 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2020 B.A.T.M.A.N. contributors: * * Marek Lindner */ diff --git a/net/batman-adv/icmp_socket.h b/net/batman-adv/icmp_socket.h index 27fafff586df..6abd0f4742ef 100644 --- a/net/batman-adv/icmp_socket.h +++ b/net/batman-adv/icmp_socket.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright (C) 2007-2019 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2020 B.A.T.M.A.N. contributors: * * Marek Lindner */ diff --git a/net/batman-adv/log.c b/net/batman-adv/log.c index 11941cf1adcc..a67b2b091447 100644 --- a/net/batman-adv/log.c +++ b/net/batman-adv/log.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright (C) 2010-2019 B.A.T.M.A.N. contributors: +/* Copyright (C) 2010-2020 B.A.T.M.A.N. contributors: * * Marek Lindner */ diff --git a/net/batman-adv/log.h b/net/batman-adv/log.h index 741cfa3719ff..f9884dc56cf3 100644 --- a/net/batman-adv/log.h +++ b/net/batman-adv/log.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright (C) 2007-2019 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2020 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich */ @@ -74,7 +74,7 @@ __printf(2, 3); * @bat_priv: the bat priv with all the soft interface information * @ratelimited: whether output should be rate limited * @fmt: format string - * @arg...: variable arguments + * @arg: variable arguments */ #define _batadv_dbg(type, bat_priv, ratelimited, fmt, arg...) \ do { \ @@ -98,7 +98,7 @@ static inline void _batadv_dbg(int type __always_unused, * batadv_dbg() - Store debug output without ratelimiting * @type: type of debug message * @bat_priv: the bat priv with all the soft interface information - * @arg...: format string and variable arguments + * @arg: format string and variable arguments */ #define batadv_dbg(type, bat_priv, arg...) \ _batadv_dbg(type, bat_priv, 0, ## arg) @@ -107,7 +107,7 @@ static inline void _batadv_dbg(int type __always_unused, * batadv_dbg_ratelimited() - Store debug output with ratelimiting * @type: type of debug message * @bat_priv: the bat priv with all the soft interface information - * @arg...: format string and variable arguments + * @arg: format string and variable arguments */ #define batadv_dbg_ratelimited(type, bat_priv, arg...) \ _batadv_dbg(type, bat_priv, 1, ## arg) @@ -116,7 +116,7 @@ static inline void _batadv_dbg(int type __always_unused, * batadv_info() - Store message in debug buffer and print it to kmsg buffer * @net_dev: the soft interface net device * @fmt: format string - * @arg...: variable arguments + * @arg: variable arguments */ #define batadv_info(net_dev, fmt, arg...) \ do { \ @@ -130,7 +130,7 @@ static inline void _batadv_dbg(int type __always_unused, * batadv_err() - Store error in debug buffer and print it to kmsg buffer * @net_dev: the soft interface net device * @fmt: format string - * @arg...: variable arguments + * @arg: variable arguments */ #define batadv_err(net_dev, fmt, arg...) \ do { \ diff --git a/net/batman-adv/main.c b/net/batman-adv/main.c index 4811ec65bc43..d8a255c85e77 100644 --- a/net/batman-adv/main.c +++ b/net/batman-adv/main.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright (C) 2007-2019 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2020 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich */ diff --git a/net/batman-adv/main.h b/net/batman-adv/main.h index c7b340ddd0e7..692306df7b6f 100644 --- a/net/batman-adv/main.h +++ b/net/batman-adv/main.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright (C) 2007-2019 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2020 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich */ @@ -13,7 +13,7 @@ #define BATADV_DRIVER_DEVICE "batman-adv" #ifndef BATADV_SOURCE_VERSION -#define BATADV_SOURCE_VERSION "2019.5" +#define BATADV_SOURCE_VERSION "2020.0" #endif /* B.A.T.M.A.N. parameters */ diff --git a/net/batman-adv/multicast.c b/net/batman-adv/multicast.c index f9ec8e7507b6..9ebdc1e864b9 100644 --- a/net/batman-adv/multicast.c +++ b/net/batman-adv/multicast.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright (C) 2014-2019 B.A.T.M.A.N. contributors: +/* Copyright (C) 2014-2020 B.A.T.M.A.N. contributors: * * Linus Lüssing */ diff --git a/net/batman-adv/multicast.h b/net/batman-adv/multicast.h index 5d9e2bb29c97..ebf825991ecd 100644 --- a/net/batman-adv/multicast.h +++ b/net/batman-adv/multicast.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright (C) 2014-2019 B.A.T.M.A.N. contributors: +/* Copyright (C) 2014-2020 B.A.T.M.A.N. contributors: * * Linus Lüssing */ diff --git a/net/batman-adv/netlink.c b/net/batman-adv/netlink.c index 7e052d6f759b..02ed073f95a9 100644 --- a/net/batman-adv/netlink.c +++ b/net/batman-adv/netlink.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright (C) 2016-2019 B.A.T.M.A.N. contributors: +/* Copyright (C) 2016-2020 B.A.T.M.A.N. contributors: * * Matthias Schiffer */ diff --git a/net/batman-adv/netlink.h b/net/batman-adv/netlink.h index ddc674e47dbb..7ee48f916997 100644 --- a/net/batman-adv/netlink.h +++ b/net/batman-adv/netlink.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright (C) 2016-2019 B.A.T.M.A.N. contributors: +/* Copyright (C) 2016-2020 B.A.T.M.A.N. contributors: * * Matthias Schiffer */ diff --git a/net/batman-adv/network-coding.c b/net/batman-adv/network-coding.c index 580609389f0f..8f0717c3f7b5 100644 --- a/net/batman-adv/network-coding.c +++ b/net/batman-adv/network-coding.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright (C) 2012-2019 B.A.T.M.A.N. contributors: +/* Copyright (C) 2012-2020 B.A.T.M.A.N. contributors: * * Martin Hundebøll, Jeppe Ledet-Pedersen */ diff --git a/net/batman-adv/network-coding.h b/net/batman-adv/network-coding.h index 753fa49723cf..334289084127 100644 --- a/net/batman-adv/network-coding.h +++ b/net/batman-adv/network-coding.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright (C) 2012-2019 B.A.T.M.A.N. contributors: +/* Copyright (C) 2012-2020 B.A.T.M.A.N. contributors: * * Martin Hundebøll, Jeppe Ledet-Pedersen */ diff --git a/net/batman-adv/originator.c b/net/batman-adv/originator.c index 38613487fb1b..5b0c2fffc214 100644 --- a/net/batman-adv/originator.c +++ b/net/batman-adv/originator.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright (C) 2009-2019 B.A.T.M.A.N. contributors: +/* Copyright (C) 2009-2020 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich */ diff --git a/net/batman-adv/originator.h b/net/batman-adv/originator.h index 512a1f99dd75..7bc01c138b3a 100644 --- a/net/batman-adv/originator.h +++ b/net/batman-adv/originator.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright (C) 2007-2019 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2020 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich */ diff --git a/net/batman-adv/routing.c b/net/batman-adv/routing.c index f0f864820dea..3632bd976c56 100644 --- a/net/batman-adv/routing.c +++ b/net/batman-adv/routing.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright (C) 2007-2019 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2020 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich */ diff --git a/net/batman-adv/routing.h b/net/batman-adv/routing.h index c20feac95107..2ed49db6eff5 100644 --- a/net/batman-adv/routing.h +++ b/net/batman-adv/routing.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright (C) 2007-2019 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2020 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich */ diff --git a/net/batman-adv/send.c b/net/batman-adv/send.c index 3ce5f7bad369..7f8ade04e08e 100644 --- a/net/batman-adv/send.c +++ b/net/batman-adv/send.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright (C) 2007-2019 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2020 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich */ diff --git a/net/batman-adv/send.h b/net/batman-adv/send.h index 5fc0fd1e5d08..0d36e15589f6 100644 --- a/net/batman-adv/send.h +++ b/net/batman-adv/send.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright (C) 2007-2019 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2020 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich */ diff --git a/net/batman-adv/soft-interface.c b/net/batman-adv/soft-interface.c index 832e156c519e..5f05a728f347 100644 --- a/net/batman-adv/soft-interface.c +++ b/net/batman-adv/soft-interface.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright (C) 2007-2019 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2020 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich */ diff --git a/net/batman-adv/soft-interface.h b/net/batman-adv/soft-interface.h index 29139ad769fe..534e08d6ad91 100644 --- a/net/batman-adv/soft-interface.h +++ b/net/batman-adv/soft-interface.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright (C) 2007-2019 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2020 B.A.T.M.A.N. contributors: * * Marek Lindner */ diff --git a/net/batman-adv/sysfs.c b/net/batman-adv/sysfs.c index e5bbc28ed12c..c45962d8527b 100644 --- a/net/batman-adv/sysfs.c +++ b/net/batman-adv/sysfs.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright (C) 2010-2019 B.A.T.M.A.N. contributors: +/* Copyright (C) 2010-2020 B.A.T.M.A.N. contributors: * * Marek Lindner */ diff --git a/net/batman-adv/sysfs.h b/net/batman-adv/sysfs.h index 5e466093dfa5..d987f8b30a98 100644 --- a/net/batman-adv/sysfs.h +++ b/net/batman-adv/sysfs.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright (C) 2010-2019 B.A.T.M.A.N. contributors: +/* Copyright (C) 2010-2020 B.A.T.M.A.N. contributors: * * Marek Lindner */ diff --git a/net/batman-adv/tp_meter.c b/net/batman-adv/tp_meter.c index dd6a9a40dbb9..bd2ac570c42c 100644 --- a/net/batman-adv/tp_meter.c +++ b/net/batman-adv/tp_meter.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright (C) 2012-2019 B.A.T.M.A.N. contributors: +/* Copyright (C) 2012-2020 B.A.T.M.A.N. contributors: * * Edo Monticelli, Antonio Quartulli */ diff --git a/net/batman-adv/tp_meter.h b/net/batman-adv/tp_meter.h index 78d310da0ad3..140105215aa2 100644 --- a/net/batman-adv/tp_meter.h +++ b/net/batman-adv/tp_meter.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright (C) 2012-2019 B.A.T.M.A.N. contributors: +/* Copyright (C) 2012-2020 B.A.T.M.A.N. contributors: * * Edo Monticelli, Antonio Quartulli */ diff --git a/net/batman-adv/trace.c b/net/batman-adv/trace.c index 3cedd2c36528..3444d9e4e90d 100644 --- a/net/batman-adv/trace.c +++ b/net/batman-adv/trace.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright (C) 2010-2019 B.A.T.M.A.N. contributors: +/* Copyright (C) 2010-2020 B.A.T.M.A.N. contributors: * * Sven Eckelmann */ diff --git a/net/batman-adv/trace.h b/net/batman-adv/trace.h index d8f764521c0b..f631b1e01b89 100644 --- a/net/batman-adv/trace.h +++ b/net/batman-adv/trace.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright (C) 2010-2019 B.A.T.M.A.N. contributors: +/* Copyright (C) 2010-2020 B.A.T.M.A.N. contributors: * * Sven Eckelmann */ diff --git a/net/batman-adv/translation-table.c b/net/batman-adv/translation-table.c index 8a482c5ec67b..852932838ddc 100644 --- a/net/batman-adv/translation-table.c +++ b/net/batman-adv/translation-table.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright (C) 2007-2019 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2020 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich, Antonio Quartulli */ diff --git a/net/batman-adv/translation-table.h b/net/batman-adv/translation-table.h index 4a98860d7f0e..b24d35b9226a 100644 --- a/net/batman-adv/translation-table.h +++ b/net/batman-adv/translation-table.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright (C) 2007-2019 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2020 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich, Antonio Quartulli */ diff --git a/net/batman-adv/tvlv.c b/net/batman-adv/tvlv.c index aae63f0d21eb..0963a43ad996 100644 --- a/net/batman-adv/tvlv.c +++ b/net/batman-adv/tvlv.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright (C) 2007-2019 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2020 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich */ diff --git a/net/batman-adv/tvlv.h b/net/batman-adv/tvlv.h index 36985000a0a8..d509d00c7a23 100644 --- a/net/batman-adv/tvlv.h +++ b/net/batman-adv/tvlv.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright (C) 2007-2019 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2020 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich */ diff --git a/net/batman-adv/types.h b/net/batman-adv/types.h index 47718a82eaf2..4a17a66cc572 100644 --- a/net/batman-adv/types.h +++ b/net/batman-adv/types.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright (C) 2007-2019 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2020 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich */ @@ -457,7 +457,7 @@ struct batadv_orig_node { /** * @tt_lock: prevents from updating the table while reading it. Table * update is made up by two operations (data structure update and - * metdata -CRC/TTVN-recalculation) and they have to be executed + * metadata -CRC/TTVN-recalculation) and they have to be executed * atomically in order to avoid another thread to read the * table/metadata between those. */ @@ -1011,7 +1011,7 @@ struct batadv_priv_tt { /** * @commit_lock: prevents from executing a local TT commit while reading * the local table. The local TT commit is made up by two operations - * (data structure update and metdata -CRC/TTVN- recalculation) and + * (data structure update and metadata -CRC/TTVN- recalculation) and * they have to be executed atomically in order to avoid another thread * to read the table/metadata between those. */ diff --git a/net/bluetooth/bnep/netdev.c b/net/bluetooth/bnep/netdev.c index 1d4d7d415730..cc1cff63194f 100644 --- a/net/bluetooth/bnep/netdev.c +++ b/net/bluetooth/bnep/netdev.c @@ -112,7 +112,7 @@ static int bnep_net_set_mac_addr(struct net_device *dev, void *arg) return 0; } -static void bnep_net_timeout(struct net_device *dev) +static void bnep_net_timeout(struct net_device *dev, unsigned int txqueue) { BT_DBG("net_timeout"); netif_wake_queue(dev); diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c index 9e19d5a3aac8..cbbc34a006d1 100644 --- a/net/bluetooth/hci_core.c +++ b/net/bluetooth/hci_core.c @@ -2311,6 +2311,33 @@ void hci_smp_irks_clear(struct hci_dev *hdev) } } +void hci_blocked_keys_clear(struct hci_dev *hdev) +{ + struct blocked_key *b; + + list_for_each_entry_rcu(b, &hdev->blocked_keys, list) { + list_del_rcu(&b->list); + kfree_rcu(b, rcu); + } +} + +bool hci_is_blocked_key(struct hci_dev *hdev, u8 type, u8 val[16]) +{ + bool blocked = false; + struct blocked_key *b; + + rcu_read_lock(); + list_for_each_entry(b, &hdev->blocked_keys, list) { + if (b->type == type && !memcmp(b->val, val, sizeof(b->val))) { + blocked = true; + break; + } + } + + rcu_read_unlock(); + return blocked; +} + struct link_key *hci_find_link_key(struct hci_dev *hdev, bdaddr_t *bdaddr) { struct link_key *k; @@ -2319,6 +2346,16 @@ struct link_key *hci_find_link_key(struct hci_dev *hdev, bdaddr_t *bdaddr) list_for_each_entry_rcu(k, &hdev->link_keys, list) { if (bacmp(bdaddr, &k->bdaddr) == 0) { rcu_read_unlock(); + + if (hci_is_blocked_key(hdev, + HCI_BLOCKED_KEY_TYPE_LINKKEY, + k->val)) { + bt_dev_warn_ratelimited(hdev, + "Link key blocked for %pMR", + &k->bdaddr); + return NULL; + } + return k; } } @@ -2387,6 +2424,15 @@ struct smp_ltk *hci_find_ltk(struct hci_dev *hdev, bdaddr_t *bdaddr, if (smp_ltk_is_sc(k) || ltk_role(k->type) == role) { rcu_read_unlock(); + + if (hci_is_blocked_key(hdev, HCI_BLOCKED_KEY_TYPE_LTK, + k->val)) { + bt_dev_warn_ratelimited(hdev, + "LTK blocked for %pMR", + &k->bdaddr); + return NULL; + } + return k; } } @@ -2397,31 +2443,42 @@ struct smp_ltk *hci_find_ltk(struct hci_dev *hdev, bdaddr_t *bdaddr, struct smp_irk *hci_find_irk_by_rpa(struct hci_dev *hdev, bdaddr_t *rpa) { + struct smp_irk *irk_to_return = NULL; struct smp_irk *irk; rcu_read_lock(); list_for_each_entry_rcu(irk, &hdev->identity_resolving_keys, list) { if (!bacmp(&irk->rpa, rpa)) { - rcu_read_unlock(); - return irk; + irk_to_return = irk; + goto done; } } list_for_each_entry_rcu(irk, &hdev->identity_resolving_keys, list) { if (smp_irk_matches(hdev, irk->val, rpa)) { bacpy(&irk->rpa, rpa); - rcu_read_unlock(); - return irk; + irk_to_return = irk; + goto done; } } + +done: + if (irk_to_return && hci_is_blocked_key(hdev, HCI_BLOCKED_KEY_TYPE_IRK, + irk_to_return->val)) { + bt_dev_warn_ratelimited(hdev, "Identity key blocked for %pMR", + &irk_to_return->bdaddr); + irk_to_return = NULL; + } + rcu_read_unlock(); - return NULL; + return irk_to_return; } struct smp_irk *hci_find_irk_by_addr(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 addr_type) { + struct smp_irk *irk_to_return = NULL; struct smp_irk *irk; /* Identity Address must be public or static random */ @@ -2432,13 +2489,23 @@ struct smp_irk *hci_find_irk_by_addr(struct hci_dev *hdev, bdaddr_t *bdaddr, list_for_each_entry_rcu(irk, &hdev->identity_resolving_keys, list) { if (addr_type == irk->addr_type && bacmp(bdaddr, &irk->bdaddr) == 0) { - rcu_read_unlock(); - return irk; + irk_to_return = irk; + goto done; } } + +done: + + if (irk_to_return && hci_is_blocked_key(hdev, HCI_BLOCKED_KEY_TYPE_IRK, + irk_to_return->val)) { + bt_dev_warn_ratelimited(hdev, "Identity key blocked for %pMR", + &irk_to_return->bdaddr); + irk_to_return = NULL; + } + rcu_read_unlock(); - return NULL; + return irk_to_return; } struct link_key *hci_add_link_key(struct hci_dev *hdev, struct hci_conn *conn, @@ -3244,6 +3311,7 @@ struct hci_dev *hci_alloc_dev(void) INIT_LIST_HEAD(&hdev->pend_le_reports); INIT_LIST_HEAD(&hdev->conn_hash.list); INIT_LIST_HEAD(&hdev->adv_instances); + INIT_LIST_HEAD(&hdev->blocked_keys); INIT_WORK(&hdev->rx_work, hci_rx_work); INIT_WORK(&hdev->cmd_work, hci_cmd_work); @@ -3443,6 +3511,7 @@ void hci_unregister_dev(struct hci_dev *hdev) hci_bdaddr_list_clear(&hdev->le_resolv_list); hci_conn_params_clear_all(hdev); hci_discovery_filter_clear(hdev); + hci_blocked_keys_clear(hdev); hci_dev_unlock(hdev); hci_dev_put(hdev); @@ -3496,7 +3565,8 @@ int hci_recv_frame(struct hci_dev *hdev, struct sk_buff *skb) if (hci_skb_pkt_type(skb) != HCI_EVENT_PKT && hci_skb_pkt_type(skb) != HCI_ACLDATA_PKT && - hci_skb_pkt_type(skb) != HCI_SCODATA_PKT) { + hci_skb_pkt_type(skb) != HCI_SCODATA_PKT && + hci_skb_pkt_type(skb) != HCI_ISODATA_PKT) { kfree_skb(skb); return -EINVAL; } @@ -4218,15 +4288,10 @@ static void hci_sched_le(struct hci_dev *hdev) if (!hci_conn_num(hdev, LE_LINK)) return; - if (!hci_dev_test_flag(hdev, HCI_UNCONFIGURED)) { - /* LE tx timeout must be longer than maximum - * link supervision timeout (40.9 seconds) */ - if (!hdev->le_cnt && hdev->le_pkts && - time_after(jiffies, hdev->le_last_tx + HZ * 45)) - hci_link_tx_to(hdev, LE_LINK); - } - cnt = hdev->le_pkts ? hdev->le_cnt : hdev->acl_cnt; + + __check_timeout(hdev, cnt); + tmp = cnt; while (cnt && (chan = hci_chan_sent(hdev, LE_LINK, "e))) { u32 priority = (skb_peek(&chan->data_q))->priority; @@ -4479,6 +4544,7 @@ static void hci_rx_work(struct work_struct *work) switch (hci_skb_pkt_type(skb)) { case HCI_ACLDATA_PKT: case HCI_SCODATA_PKT: + case HCI_ISODATA_PKT: kfree_skb(skb); continue; } diff --git a/net/bluetooth/hci_debugfs.c b/net/bluetooth/hci_debugfs.c index 402e2cc54044..6b1314c738b8 100644 --- a/net/bluetooth/hci_debugfs.c +++ b/net/bluetooth/hci_debugfs.c @@ -26,6 +26,7 @@ #include <net/bluetooth/bluetooth.h> #include <net/bluetooth/hci_core.h> +#include "smp.h" #include "hci_debugfs.h" #define DEFINE_QUIRK_ATTRIBUTE(__name, __quirk) \ @@ -152,6 +153,21 @@ static int blacklist_show(struct seq_file *f, void *p) DEFINE_SHOW_ATTRIBUTE(blacklist); +static int blocked_keys_show(struct seq_file *f, void *p) +{ + struct hci_dev *hdev = f->private; + struct blocked_key *key; + + rcu_read_lock(); + list_for_each_entry_rcu(key, &hdev->blocked_keys, list) + seq_printf(f, "%u %*phN\n", key->type, 16, key->val); + rcu_read_unlock(); + + return 0; +} + +DEFINE_SHOW_ATTRIBUTE(blocked_keys); + static int uuids_show(struct seq_file *f, void *p) { struct hci_dev *hdev = f->private; @@ -308,6 +324,8 @@ void hci_debugfs_create_common(struct hci_dev *hdev) &device_list_fops); debugfs_create_file("blacklist", 0444, hdev->debugfs, hdev, &blacklist_fops); + debugfs_create_file("blocked_keys", 0444, hdev->debugfs, hdev, + &blocked_keys_fops); debugfs_create_file("uuids", 0444, hdev->debugfs, hdev, &uuids_fops); debugfs_create_file("remote_oob", 0400, hdev->debugfs, hdev, &remote_oob_fops); @@ -972,6 +990,62 @@ static int adv_max_interval_get(void *data, u64 *val) DEFINE_SIMPLE_ATTRIBUTE(adv_max_interval_fops, adv_max_interval_get, adv_max_interval_set, "%llu\n"); +static int min_key_size_set(void *data, u64 val) +{ + struct hci_dev *hdev = data; + + if (val > hdev->le_max_key_size || val < SMP_MIN_ENC_KEY_SIZE) + return -EINVAL; + + hci_dev_lock(hdev); + hdev->le_min_key_size = val; + hci_dev_unlock(hdev); + + return 0; +} + +static int min_key_size_get(void *data, u64 *val) +{ + struct hci_dev *hdev = data; + + hci_dev_lock(hdev); + *val = hdev->le_min_key_size; + hci_dev_unlock(hdev); + + return 0; +} + +DEFINE_SIMPLE_ATTRIBUTE(min_key_size_fops, min_key_size_get, + min_key_size_set, "%llu\n"); + +static int max_key_size_set(void *data, u64 val) +{ + struct hci_dev *hdev = data; + + if (val > SMP_MAX_ENC_KEY_SIZE || val < hdev->le_min_key_size) + return -EINVAL; + + hci_dev_lock(hdev); + hdev->le_max_key_size = val; + hci_dev_unlock(hdev); + + return 0; +} + +static int max_key_size_get(void *data, u64 *val) +{ + struct hci_dev *hdev = data; + + hci_dev_lock(hdev); + *val = hdev->le_max_key_size; + hci_dev_unlock(hdev); + + return 0; +} + +DEFINE_SIMPLE_ATTRIBUTE(max_key_size_fops, max_key_size_get, + max_key_size_set, "%llu\n"); + static int auth_payload_timeout_set(void *data, u64 val) { struct hci_dev *hdev = data; @@ -1054,6 +1128,10 @@ void hci_debugfs_create_le(struct hci_dev *hdev) &adv_max_interval_fops); debugfs_create_u16("discov_interleaved_timeout", 0644, hdev->debugfs, &hdev->discov_interleaved_timeout); + debugfs_create_file("min_key_size", 0644, hdev->debugfs, hdev, + &min_key_size_fops); + debugfs_create_file("max_key_size", 0644, hdev->debugfs, hdev, + &max_key_size_fops); debugfs_create_file("auth_payload_timeout", 0644, hdev->debugfs, hdev, &auth_payload_timeout_fops); diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c index c1d3a303d97f..6ddc4a74a5e4 100644 --- a/net/bluetooth/hci_event.c +++ b/net/bluetooth/hci_event.c @@ -5451,7 +5451,7 @@ static void hci_le_adv_report_evt(struct hci_dev *hdev, struct sk_buff *skb) hci_dev_unlock(hdev); } -static u8 ext_evt_type_to_legacy(u16 evt_type) +static u8 ext_evt_type_to_legacy(struct hci_dev *hdev, u16 evt_type) { if (evt_type & LE_EXT_ADV_LEGACY_PDU) { switch (evt_type) { @@ -5468,10 +5468,7 @@ static u8 ext_evt_type_to_legacy(u16 evt_type) return LE_ADV_SCAN_RSP; } - BT_ERR_RATELIMITED("Unknown advertising packet type: 0x%02x", - evt_type); - - return LE_ADV_INVALID; + goto invalid; } if (evt_type & LE_EXT_ADV_CONN_IND) { @@ -5491,8 +5488,9 @@ static u8 ext_evt_type_to_legacy(u16 evt_type) evt_type & LE_EXT_ADV_DIRECT_IND) return LE_ADV_NONCONN_IND; - BT_ERR_RATELIMITED("Unknown advertising packet type: 0x%02x", - evt_type); +invalid: + bt_dev_err_ratelimited(hdev, "Unknown advertising packet type: 0x%02x", + evt_type); return LE_ADV_INVALID; } @@ -5510,7 +5508,7 @@ static void hci_le_ext_adv_report_evt(struct hci_dev *hdev, struct sk_buff *skb) u16 evt_type; evt_type = __le16_to_cpu(ev->evt_type); - legacy_evt_type = ext_evt_type_to_legacy(evt_type); + legacy_evt_type = ext_evt_type_to_legacy(hdev, evt_type); if (legacy_evt_type != LE_ADV_INVALID) { process_adv_report(hdev, legacy_evt_type, &ev->bdaddr, ev->bdaddr_type, NULL, 0, ev->rssi, @@ -5720,6 +5718,29 @@ static void hci_le_direct_adv_report_evt(struct hci_dev *hdev, hci_dev_unlock(hdev); } +static void hci_le_phy_update_evt(struct hci_dev *hdev, struct sk_buff *skb) +{ + struct hci_ev_le_phy_update_complete *ev = (void *) skb->data; + struct hci_conn *conn; + + BT_DBG("%s status 0x%2.2x", hdev->name, ev->status); + + if (!ev->status) + return; + + hci_dev_lock(hdev); + + conn = hci_conn_hash_lookup_handle(hdev, __le16_to_cpu(ev->handle)); + if (!conn) + goto unlock; + + conn->le_tx_phy = ev->tx_phy; + conn->le_rx_phy = ev->rx_phy; + +unlock: + hci_dev_unlock(hdev); +} + static void hci_le_meta_evt(struct hci_dev *hdev, struct sk_buff *skb) { struct hci_ev_le_meta *le_ev = (void *) skb->data; @@ -5755,6 +5776,10 @@ static void hci_le_meta_evt(struct hci_dev *hdev, struct sk_buff *skb) hci_le_direct_adv_report_evt(hdev, skb); break; + case HCI_EV_LE_PHY_UPDATE_COMPLETE: + hci_le_phy_update_evt(hdev, skb); + break; + case HCI_EV_LE_EXT_ADV_REPORT: hci_le_ext_adv_report_evt(hdev, skb); break; diff --git a/net/bluetooth/hci_sock.c b/net/bluetooth/hci_sock.c index 5d0ed28c0d3a..9c4a093f8960 100644 --- a/net/bluetooth/hci_sock.c +++ b/net/bluetooth/hci_sock.c @@ -211,7 +211,8 @@ void hci_send_to_sock(struct hci_dev *hdev, struct sk_buff *skb) if (hci_skb_pkt_type(skb) != HCI_COMMAND_PKT && hci_skb_pkt_type(skb) != HCI_EVENT_PKT && hci_skb_pkt_type(skb) != HCI_ACLDATA_PKT && - hci_skb_pkt_type(skb) != HCI_SCODATA_PKT) + hci_skb_pkt_type(skb) != HCI_SCODATA_PKT && + hci_skb_pkt_type(skb) != HCI_ISODATA_PKT) continue; if (is_filtered_packet(sk, skb)) continue; @@ -220,7 +221,8 @@ void hci_send_to_sock(struct hci_dev *hdev, struct sk_buff *skb) continue; if (hci_skb_pkt_type(skb) != HCI_EVENT_PKT && hci_skb_pkt_type(skb) != HCI_ACLDATA_PKT && - hci_skb_pkt_type(skb) != HCI_SCODATA_PKT) + hci_skb_pkt_type(skb) != HCI_SCODATA_PKT && + hci_skb_pkt_type(skb) != HCI_ISODATA_PKT) continue; } else { /* Don't send frame to other channel types */ @@ -324,6 +326,12 @@ void hci_send_to_monitor(struct hci_dev *hdev, struct sk_buff *skb) else opcode = cpu_to_le16(HCI_MON_SCO_TX_PKT); break; + case HCI_ISODATA_PKT: + if (bt_cb(skb)->incoming) + opcode = cpu_to_le16(HCI_MON_ISO_RX_PKT); + else + opcode = cpu_to_le16(HCI_MON_ISO_TX_PKT); + break; case HCI_DIAG_PKT: opcode = cpu_to_le16(HCI_MON_VENDOR_DIAG); break; @@ -831,6 +839,8 @@ static int hci_sock_release(struct socket *sock) if (!sk) return 0; + lock_sock(sk); + switch (hci_pi(sk)->channel) { case HCI_CHANNEL_MONITOR: atomic_dec(&monitor_promisc); @@ -878,6 +888,7 @@ static int hci_sock_release(struct socket *sock) skb_queue_purge(&sk->sk_receive_queue); skb_queue_purge(&sk->sk_write_queue); + release_sock(sk); sock_put(sk); return 0; } @@ -1762,7 +1773,8 @@ static int hci_sock_sendmsg(struct socket *sock, struct msghdr *msg, */ if (hci_skb_pkt_type(skb) != HCI_COMMAND_PKT && hci_skb_pkt_type(skb) != HCI_ACLDATA_PKT && - hci_skb_pkt_type(skb) != HCI_SCODATA_PKT) { + hci_skb_pkt_type(skb) != HCI_SCODATA_PKT && + hci_skb_pkt_type(skb) != HCI_ISODATA_PKT) { err = -EINVAL; goto drop; } @@ -1806,7 +1818,8 @@ static int hci_sock_sendmsg(struct socket *sock, struct msghdr *msg, } if (hci_skb_pkt_type(skb) != HCI_ACLDATA_PKT && - hci_skb_pkt_type(skb) != HCI_SCODATA_PKT) { + hci_skb_pkt_type(skb) != HCI_SCODATA_PKT && + hci_skb_pkt_type(skb) != HCI_ISODATA_PKT) { err = -EINVAL; goto drop; } diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c index a845786258a0..195459a1e53e 100644 --- a/net/bluetooth/l2cap_core.c +++ b/net/bluetooth/l2cap_core.c @@ -1289,6 +1289,9 @@ static void l2cap_le_connect(struct l2cap_chan *chan) if (test_and_set_bit(FLAG_LE_CONN_REQ_SENT, &chan->flags)) return; + if (!chan->imtu) + chan->imtu = chan->conn->mtu; + l2cap_le_flowctl_init(chan, 0); req.psm = chan->psm; @@ -3226,6 +3229,49 @@ static inline void l2cap_txwin_setup(struct l2cap_chan *chan) chan->ack_win = chan->tx_win; } +static void l2cap_mtu_auto(struct l2cap_chan *chan) +{ + struct hci_conn *conn = chan->conn->hcon; + + chan->imtu = L2CAP_DEFAULT_MIN_MTU; + + /* The 2-DH1 packet has between 2 and 56 information bytes + * (including the 2-byte payload header) + */ + if (!(conn->pkt_type & HCI_2DH1)) + chan->imtu = 54; + + /* The 3-DH1 packet has between 2 and 85 information bytes + * (including the 2-byte payload header) + */ + if (!(conn->pkt_type & HCI_3DH1)) + chan->imtu = 83; + + /* The 2-DH3 packet has between 2 and 369 information bytes + * (including the 2-byte payload header) + */ + if (!(conn->pkt_type & HCI_2DH3)) + chan->imtu = 367; + + /* The 3-DH3 packet has between 2 and 554 information bytes + * (including the 2-byte payload header) + */ + if (!(conn->pkt_type & HCI_3DH3)) + chan->imtu = 552; + + /* The 2-DH5 packet has between 2 and 681 information bytes + * (including the 2-byte payload header) + */ + if (!(conn->pkt_type & HCI_2DH5)) + chan->imtu = 679; + + /* The 3-DH5 packet has between 2 and 1023 information bytes + * (including the 2-byte payload header) + */ + if (!(conn->pkt_type & HCI_3DH5)) + chan->imtu = 1021; +} + static int l2cap_build_conf_req(struct l2cap_chan *chan, void *data, size_t data_size) { struct l2cap_conf_req *req = data; @@ -3255,8 +3301,12 @@ static int l2cap_build_conf_req(struct l2cap_chan *chan, void *data, size_t data } done: - if (chan->imtu != L2CAP_DEFAULT_MTU) - l2cap_add_conf_opt(&ptr, L2CAP_CONF_MTU, 2, chan->imtu, endptr - ptr); + if (chan->imtu != L2CAP_DEFAULT_MTU) { + if (!chan->imtu) + l2cap_mtu_auto(chan); + l2cap_add_conf_opt(&ptr, L2CAP_CONF_MTU, 2, chan->imtu, + endptr - ptr); + } switch (chan->mode) { case L2CAP_MODE_BASIC: @@ -5031,7 +5081,6 @@ static inline int l2cap_move_channel_req(struct l2cap_conn *conn, chan->move_role = L2CAP_MOVE_ROLE_RESPONDER; l2cap_move_setup(chan); chan->move_id = req->dest_amp_id; - icid = chan->dcid; if (req->dest_amp_id == AMP_ID_BREDR) { /* Moving to BR/EDR */ diff --git a/net/bluetooth/lib.c b/net/bluetooth/lib.c index 63e65d9b4b24..c09e0a3a0ed9 100644 --- a/net/bluetooth/lib.c +++ b/net/bluetooth/lib.c @@ -183,6 +183,22 @@ void bt_err(const char *format, ...) } EXPORT_SYMBOL(bt_err); +void bt_warn_ratelimited(const char *format, ...) +{ + struct va_format vaf; + va_list args; + + va_start(args, format); + + vaf.fmt = format; + vaf.va = &args; + + pr_warn_ratelimited("%pV", &vaf); + + va_end(args); +} +EXPORT_SYMBOL(bt_warn_ratelimited); + void bt_err_ratelimited(const char *format, ...) { struct va_format vaf; diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c index acb7c6d5643f..3074363c68df 100644 --- a/net/bluetooth/mgmt.c +++ b/net/bluetooth/mgmt.c @@ -38,7 +38,7 @@ #include "mgmt_util.h" #define MGMT_VERSION 1 -#define MGMT_REVISION 14 +#define MGMT_REVISION 15 static const u16 mgmt_commands[] = { MGMT_OP_READ_INDEX_LIST, @@ -106,6 +106,7 @@ static const u16 mgmt_commands[] = { MGMT_OP_START_LIMITED_DISCOVERY, MGMT_OP_READ_EXT_INFO, MGMT_OP_SET_APPEARANCE, + MGMT_OP_SET_BLOCKED_KEYS, }; static const u16 mgmt_events[] = { @@ -175,7 +176,7 @@ static const u16 mgmt_untrusted_events[] = { "\x00\x00\x00\x00\x00\x00\x00\x00" /* HCI to MGMT error code conversion table */ -static u8 mgmt_status_table[] = { +static const u8 mgmt_status_table[] = { MGMT_STATUS_SUCCESS, MGMT_STATUS_UNKNOWN_COMMAND, /* Unknown Command */ MGMT_STATUS_NOT_CONNECTED, /* No Connection */ @@ -2341,6 +2342,14 @@ static int load_link_keys(struct sock *sk, struct hci_dev *hdev, void *data, for (i = 0; i < key_count; i++) { struct mgmt_link_key_info *key = &cp->keys[i]; + if (hci_is_blocked_key(hdev, + HCI_BLOCKED_KEY_TYPE_LINKKEY, + key->val)) { + bt_dev_warn(hdev, "Skipping blocked link key for %pMR", + &key->addr.bdaddr); + continue; + } + /* Always ignore debug keys and require a new pairing if * the user wants to use them. */ @@ -3282,7 +3291,7 @@ static int set_appearance(struct sock *sk, struct hci_dev *hdev, void *data, u16 len) { struct mgmt_cp_set_appearance *cp = data; - u16 apperance; + u16 appearance; int err; BT_DBG(""); @@ -3291,12 +3300,12 @@ static int set_appearance(struct sock *sk, struct hci_dev *hdev, void *data, return mgmt_cmd_status(sk, hdev->id, MGMT_OP_SET_APPEARANCE, MGMT_STATUS_NOT_SUPPORTED); - apperance = le16_to_cpu(cp->appearance); + appearance = le16_to_cpu(cp->appearance); hci_dev_lock(hdev); - if (hdev->appearance != apperance) { - hdev->appearance = apperance; + if (hdev->appearance != appearance) { + hdev->appearance = appearance; if (hci_dev_test_flag(hdev, HCI_LE_ADV)) adv_expire(hdev, MGMT_ADV_FLAG_APPEARANCE); @@ -3531,6 +3540,55 @@ unlock: return err; } +static int set_blocked_keys(struct sock *sk, struct hci_dev *hdev, void *data, + u16 len) +{ + int err = MGMT_STATUS_SUCCESS; + struct mgmt_cp_set_blocked_keys *keys = data; + const u16 max_key_count = ((U16_MAX - sizeof(*keys)) / + sizeof(struct mgmt_blocked_key_info)); + u16 key_count, expected_len; + int i; + + BT_DBG("request for %s", hdev->name); + + key_count = __le16_to_cpu(keys->key_count); + if (key_count > max_key_count) { + bt_dev_err(hdev, "too big key_count value %u", key_count); + return mgmt_cmd_status(sk, hdev->id, MGMT_OP_SET_BLOCKED_KEYS, + MGMT_STATUS_INVALID_PARAMS); + } + + expected_len = struct_size(keys, keys, key_count); + if (expected_len != len) { + bt_dev_err(hdev, "expected %u bytes, got %u bytes", + expected_len, len); + return mgmt_cmd_status(sk, hdev->id, MGMT_OP_SET_BLOCKED_KEYS, + MGMT_STATUS_INVALID_PARAMS); + } + + hci_dev_lock(hdev); + + hci_blocked_keys_clear(hdev); + + for (i = 0; i < keys->key_count; ++i) { + struct blocked_key *b = kzalloc(sizeof(*b), GFP_KERNEL); + + if (!b) { + err = MGMT_STATUS_NO_RESOURCES; + break; + } + + b->type = keys->keys[i].type; + memcpy(b->val, keys->keys[i].val, sizeof(b->val)); + list_add_rcu(&b->list, &hdev->blocked_keys); + } + hci_dev_unlock(hdev); + + return mgmt_cmd_complete(sk, hdev->id, MGMT_OP_SET_BLOCKED_KEYS, + err, NULL, 0); +} + static void read_local_oob_data_complete(struct hci_dev *hdev, u8 status, u16 opcode, struct sk_buff *skb) { @@ -5051,6 +5109,14 @@ static int load_irks(struct sock *sk, struct hci_dev *hdev, void *cp_data, for (i = 0; i < irk_count; i++) { struct mgmt_irk_info *irk = &cp->irks[i]; + if (hci_is_blocked_key(hdev, + HCI_BLOCKED_KEY_TYPE_IRK, + irk->val)) { + bt_dev_warn(hdev, "Skipping blocked IRK for %pMR", + &irk->addr.bdaddr); + continue; + } + hci_add_irk(hdev, &irk->addr.bdaddr, le_addr_type(irk->addr.type), irk->val, BDADDR_ANY); @@ -5134,6 +5200,14 @@ static int load_long_term_keys(struct sock *sk, struct hci_dev *hdev, struct mgmt_ltk_info *key = &cp->keys[i]; u8 type, authenticated; + if (hci_is_blocked_key(hdev, + HCI_BLOCKED_KEY_TYPE_LTK, + key->val)) { + bt_dev_warn(hdev, "Skipping blocked LTK for %pMR", + &key->addr.bdaddr); + continue; + } + switch (key->type) { case MGMT_LTK_UNAUTHENTICATED: authenticated = 0x00; @@ -6914,6 +6988,8 @@ static const struct hci_mgmt_handler mgmt_handlers[] = { { set_appearance, MGMT_SET_APPEARANCE_SIZE }, { get_phy_configuration, MGMT_GET_PHY_CONFIGURATION_SIZE }, { set_phy_configuration, MGMT_SET_PHY_CONFIGURATION_SIZE }, + { set_blocked_keys, MGMT_OP_SET_BLOCKED_KEYS_SIZE, + HCI_MGMT_VAR_LEN }, }; void mgmt_index_added(struct hci_dev *hdev) diff --git a/net/bluetooth/smp.c b/net/bluetooth/smp.c index 6b42be4b5861..204f14f8b507 100644 --- a/net/bluetooth/smp.c +++ b/net/bluetooth/smp.c @@ -2453,6 +2453,15 @@ static int smp_cmd_encrypt_info(struct l2cap_conn *conn, struct sk_buff *skb) if (skb->len < sizeof(*rp)) return SMP_INVALID_PARAMS; + /* Pairing is aborted if any blocked keys are distributed */ + if (hci_is_blocked_key(conn->hcon->hdev, HCI_BLOCKED_KEY_TYPE_LTK, + rp->ltk)) { + bt_dev_warn_ratelimited(conn->hcon->hdev, + "LTK blocked for %pMR", + &conn->hcon->dst); + return SMP_INVALID_PARAMS; + } + SMP_ALLOW_CMD(smp, SMP_CMD_MASTER_IDENT); skb_pull(skb, sizeof(*rp)); @@ -2509,6 +2518,15 @@ static int smp_cmd_ident_info(struct l2cap_conn *conn, struct sk_buff *skb) if (skb->len < sizeof(*info)) return SMP_INVALID_PARAMS; + /* Pairing is aborted if any blocked keys are distributed */ + if (hci_is_blocked_key(conn->hcon->hdev, HCI_BLOCKED_KEY_TYPE_IRK, + info->irk)) { + bt_dev_warn_ratelimited(conn->hcon->hdev, + "Identity key blocked for %pMR", + &conn->hcon->dst); + return SMP_INVALID_PARAMS; + } + SMP_ALLOW_CMD(smp, SMP_CMD_IDENT_ADDR_INFO); skb_pull(skb, sizeof(*info)); @@ -3355,94 +3373,6 @@ static const struct file_operations force_bredr_smp_fops = { .llseek = default_llseek, }; -static ssize_t le_min_key_size_read(struct file *file, - char __user *user_buf, - size_t count, loff_t *ppos) -{ - struct hci_dev *hdev = file->private_data; - char buf[4]; - - snprintf(buf, sizeof(buf), "%2u\n", hdev->le_min_key_size); - - return simple_read_from_buffer(user_buf, count, ppos, buf, strlen(buf)); -} - -static ssize_t le_min_key_size_write(struct file *file, - const char __user *user_buf, - size_t count, loff_t *ppos) -{ - struct hci_dev *hdev = file->private_data; - char buf[32]; - size_t buf_size = min(count, (sizeof(buf) - 1)); - u8 key_size; - - if (copy_from_user(buf, user_buf, buf_size)) - return -EFAULT; - - buf[buf_size] = '\0'; - - sscanf(buf, "%hhu", &key_size); - - if (key_size > hdev->le_max_key_size || - key_size < SMP_MIN_ENC_KEY_SIZE) - return -EINVAL; - - hdev->le_min_key_size = key_size; - - return count; -} - -static const struct file_operations le_min_key_size_fops = { - .open = simple_open, - .read = le_min_key_size_read, - .write = le_min_key_size_write, - .llseek = default_llseek, -}; - -static ssize_t le_max_key_size_read(struct file *file, - char __user *user_buf, - size_t count, loff_t *ppos) -{ - struct hci_dev *hdev = file->private_data; - char buf[4]; - - snprintf(buf, sizeof(buf), "%2u\n", hdev->le_max_key_size); - - return simple_read_from_buffer(user_buf, count, ppos, buf, strlen(buf)); -} - -static ssize_t le_max_key_size_write(struct file *file, - const char __user *user_buf, - size_t count, loff_t *ppos) -{ - struct hci_dev *hdev = file->private_data; - char buf[32]; - size_t buf_size = min(count, (sizeof(buf) - 1)); - u8 key_size; - - if (copy_from_user(buf, user_buf, buf_size)) - return -EFAULT; - - buf[buf_size] = '\0'; - - sscanf(buf, "%hhu", &key_size); - - if (key_size > SMP_MAX_ENC_KEY_SIZE || - key_size < hdev->le_min_key_size) - return -EINVAL; - - hdev->le_max_key_size = key_size; - - return count; -} - -static const struct file_operations le_max_key_size_fops = { - .open = simple_open, - .read = le_max_key_size_read, - .write = le_max_key_size_write, - .llseek = default_llseek, -}; - int smp_register(struct hci_dev *hdev) { struct l2cap_chan *chan; @@ -3467,11 +3397,6 @@ int smp_register(struct hci_dev *hdev) hdev->smp_data = chan; - debugfs_create_file("le_min_key_size", 0644, hdev->debugfs, hdev, - &le_min_key_size_fops); - debugfs_create_file("le_max_key_size", 0644, hdev->debugfs, hdev, - &le_max_key_size_fops); - /* If the controller does not support BR/EDR Secure Connections * feature, then the BR/EDR SMP channel shall not be present. * diff --git a/net/bpf/test_run.c b/net/bpf/test_run.c index f79205d4444f..d555c0d8657d 100644 --- a/net/bpf/test_run.c +++ b/net/bpf/test_run.c @@ -15,7 +15,7 @@ #include <trace/events/bpf_test_run.h> static int bpf_test_run(struct bpf_prog *prog, void *ctx, u32 repeat, - u32 *retval, u32 *time) + u32 *retval, u32 *time, bool xdp) { struct bpf_cgroup_storage *storage[MAX_BPF_CGROUP_STORAGE_TYPE] = { NULL }; enum bpf_cgroup_storage_type stype; @@ -41,7 +41,11 @@ static int bpf_test_run(struct bpf_prog *prog, void *ctx, u32 repeat, time_start = ktime_get_ns(); for (i = 0; i < repeat; i++) { bpf_cgroup_storage_set(storage); - *retval = BPF_PROG_RUN(prog, ctx); + + if (xdp) + *retval = bpf_prog_run_xdp(prog, ctx); + else + *retval = BPF_PROG_RUN(prog, ctx); if (signal_pending(current)) { ret = -EINTR; @@ -247,34 +251,53 @@ static int convert___skb_to_skb(struct sk_buff *skb, struct __sk_buff *__skb) return 0; /* make sure the fields we don't use are zeroed */ - if (!range_is_zero(__skb, 0, offsetof(struct __sk_buff, priority))) + if (!range_is_zero(__skb, 0, offsetof(struct __sk_buff, mark))) + return -EINVAL; + + /* mark is allowed */ + + if (!range_is_zero(__skb, offsetofend(struct __sk_buff, mark), + offsetof(struct __sk_buff, priority))) return -EINVAL; /* priority is allowed */ - if (!range_is_zero(__skb, offsetof(struct __sk_buff, priority) + - sizeof_field(struct __sk_buff, priority), + if (!range_is_zero(__skb, offsetofend(struct __sk_buff, priority), offsetof(struct __sk_buff, cb))) return -EINVAL; /* cb is allowed */ - if (!range_is_zero(__skb, offsetof(struct __sk_buff, cb) + - sizeof_field(struct __sk_buff, cb), + if (!range_is_zero(__skb, offsetofend(struct __sk_buff, cb), offsetof(struct __sk_buff, tstamp))) return -EINVAL; /* tstamp is allowed */ + /* wire_len is allowed */ + /* gso_segs is allowed */ - if (!range_is_zero(__skb, offsetof(struct __sk_buff, tstamp) + - sizeof_field(struct __sk_buff, tstamp), + if (!range_is_zero(__skb, offsetofend(struct __sk_buff, gso_segs), sizeof(struct __sk_buff))) return -EINVAL; + skb->mark = __skb->mark; skb->priority = __skb->priority; skb->tstamp = __skb->tstamp; memcpy(&cb->data, __skb->cb, QDISC_CB_PRIV_LEN); + if (__skb->wire_len == 0) { + cb->pkt_len = skb->len; + } else { + if (__skb->wire_len < skb->len || + __skb->wire_len > GSO_MAX_SIZE) + return -EINVAL; + cb->pkt_len = __skb->wire_len; + } + + if (__skb->gso_segs > GSO_MAX_SEGS) + return -EINVAL; + skb_shinfo(skb)->gso_segs = __skb->gso_segs; + return 0; } @@ -285,9 +308,12 @@ static void convert_skb_to___skb(struct sk_buff *skb, struct __sk_buff *__skb) if (!__skb) return; + __skb->mark = skb->mark; __skb->priority = skb->priority; __skb->tstamp = skb->tstamp; memcpy(__skb->cb, &cb->data, QDISC_CB_PRIV_LEN); + __skb->wire_len = cb->pkt_len; + __skb->gso_segs = skb_shinfo(skb)->gso_segs; } int bpf_prog_test_run_skb(struct bpf_prog *prog, const union bpf_attr *kattr, @@ -359,7 +385,7 @@ int bpf_prog_test_run_skb(struct bpf_prog *prog, const union bpf_attr *kattr, ret = convert___skb_to_skb(skb, ctx); if (ret) goto out; - ret = bpf_test_run(prog, skb, repeat, &retval, &duration); + ret = bpf_test_run(prog, skb, repeat, &retval, &duration, false); if (ret) goto out; if (!is_l2) { @@ -416,8 +442,8 @@ int bpf_prog_test_run_xdp(struct bpf_prog *prog, const union bpf_attr *kattr, rxqueue = __netif_get_rx_queue(current->nsproxy->net_ns->loopback_dev, 0); xdp.rxq = &rxqueue->xdp_rxq; - - ret = bpf_test_run(prog, &xdp, repeat, &retval, &duration); + bpf_prog_change_xdp(NULL, prog); + ret = bpf_test_run(prog, &xdp, repeat, &retval, &duration, true); if (ret) goto out; if (xdp.data != data + XDP_PACKET_HEADROOM + NET_IP_ALIGN || @@ -425,6 +451,7 @@ int bpf_prog_test_run_xdp(struct bpf_prog *prog, const union bpf_attr *kattr, size = xdp.data_end - xdp.data; ret = bpf_test_finish(kattr, uattr, xdp.data, size, retval, duration); out: + bpf_prog_change_xdp(prog, NULL); kfree(data); return ret; } @@ -437,8 +464,7 @@ static int verify_user_bpf_flow_keys(struct bpf_flow_keys *ctx) /* flags is allowed */ - if (!range_is_zero(ctx, offsetof(struct bpf_flow_keys, flags) + - sizeof_field(struct bpf_flow_keys, flags), + if (!range_is_zero(ctx, offsetofend(struct bpf_flow_keys, flags), sizeof(struct bpf_flow_keys))) return -EINVAL; diff --git a/net/bridge/Makefile b/net/bridge/Makefile index ac9ef337f0fa..49da7ae6f077 100644 --- a/net/bridge/Makefile +++ b/net/bridge/Makefile @@ -20,7 +20,7 @@ obj-$(CONFIG_BRIDGE_NETFILTER) += br_netfilter.o bridge-$(CONFIG_BRIDGE_IGMP_SNOOPING) += br_multicast.o br_mdb.o -bridge-$(CONFIG_BRIDGE_VLAN_FILTERING) += br_vlan.o br_vlan_tunnel.o +bridge-$(CONFIG_BRIDGE_VLAN_FILTERING) += br_vlan.o br_vlan_tunnel.o br_vlan_options.o bridge-$(CONFIG_NET_SWITCHDEV) += br_switchdev.o diff --git a/net/bridge/br_device.c b/net/bridge/br_device.c index fb38add21b37..dc3d2c1dd9d5 100644 --- a/net/bridge/br_device.c +++ b/net/bridge/br_device.c @@ -32,6 +32,7 @@ netdev_tx_t br_dev_xmit(struct sk_buff *skb, struct net_device *dev) struct net_bridge_mdb_entry *mdst; struct pcpu_sw_netstats *brstats = this_cpu_ptr(br->stats); const struct nf_br_ops *nf_ops; + u8 state = BR_STATE_FORWARDING; const unsigned char *dest; struct ethhdr *eth; u16 vid = 0; @@ -56,7 +57,7 @@ netdev_tx_t br_dev_xmit(struct sk_buff *skb, struct net_device *dev) eth = eth_hdr(skb); skb_pull(skb, ETH_HLEN); - if (!br_allowed_ingress(br, br_vlan_group_rcu(br), skb, &vid)) + if (!br_allowed_ingress(br, br_vlan_group_rcu(br), skb, &vid, &state)) goto out; if (IS_ENABLED(CONFIG_INET) && diff --git a/net/bridge/br_forward.c b/net/bridge/br_forward.c index 86637000f275..7629b63f6f30 100644 --- a/net/bridge/br_forward.c +++ b/net/bridge/br_forward.c @@ -25,7 +25,7 @@ static inline int should_deliver(const struct net_bridge_port *p, vg = nbp_vlan_group_rcu(p); return ((p->flags & BR_HAIRPIN_MODE) || skb->dev != p->dev) && - br_allowed_egress(vg, skb) && p->state == BR_STATE_FORWARDING && + p->state == BR_STATE_FORWARDING && br_allowed_egress(vg, skb) && nbp_switchdev_allowed_egress(p, skb) && !br_skb_isolated(p, skb); } diff --git a/net/bridge/br_input.c b/net/bridge/br_input.c index 8944ceb47fe9..fcc260840028 100644 --- a/net/bridge/br_input.c +++ b/net/bridge/br_input.c @@ -76,11 +76,14 @@ int br_handle_frame_finish(struct net *net, struct sock *sk, struct sk_buff *skb bool local_rcv, mcast_hit = false; struct net_bridge *br; u16 vid = 0; + u8 state; if (!p || p->state == BR_STATE_DISABLED) goto drop; - if (!br_allowed_ingress(p->br, nbp_vlan_group_rcu(p), skb, &vid)) + state = p->state; + if (!br_allowed_ingress(p->br, nbp_vlan_group_rcu(p), skb, &vid, + &state)) goto out; nbp_switchdev_frame_mark(p, skb); @@ -103,7 +106,7 @@ int br_handle_frame_finish(struct net *net, struct sock *sk, struct sk_buff *skb } } - if (p->state == BR_STATE_LEARNING) + if (state == BR_STATE_LEARNING) goto drop; BR_INPUT_SKB_CB(skb)->brdev = br->dev; diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c index a0a54482aabc..43dab4066f91 100644 --- a/net/bridge/br_netlink.c +++ b/net/bridge/br_netlink.c @@ -561,52 +561,73 @@ static int br_vlan_info(struct net_bridge *br, struct net_bridge_port *p, return err; } -static int br_process_vlan_info(struct net_bridge *br, - struct net_bridge_port *p, int cmd, - struct bridge_vlan_info *vinfo_curr, - struct bridge_vlan_info **vinfo_last, - bool *changed, - struct netlink_ext_ack *extack) +int br_process_vlan_info(struct net_bridge *br, + struct net_bridge_port *p, int cmd, + struct bridge_vlan_info *vinfo_curr, + struct bridge_vlan_info **vinfo_last, + bool *changed, + struct netlink_ext_ack *extack) { - if (!vinfo_curr->vid || vinfo_curr->vid >= VLAN_VID_MASK) + int err, rtm_cmd; + + if (!br_vlan_valid_id(vinfo_curr->vid, extack)) return -EINVAL; + /* needed for vlan-only NEWVLAN/DELVLAN notifications */ + rtm_cmd = br_afspec_cmd_to_rtm(cmd); + if (vinfo_curr->flags & BRIDGE_VLAN_INFO_RANGE_BEGIN) { - /* check if we are already processing a range */ - if (*vinfo_last) + if (!br_vlan_valid_range(vinfo_curr, *vinfo_last, extack)) return -EINVAL; *vinfo_last = vinfo_curr; - /* don't allow range of pvids */ - if ((*vinfo_last)->flags & BRIDGE_VLAN_INFO_PVID) - return -EINVAL; return 0; } if (*vinfo_last) { struct bridge_vlan_info tmp_vinfo; - int v, err; - - if (!(vinfo_curr->flags & BRIDGE_VLAN_INFO_RANGE_END)) - return -EINVAL; + int v, v_change_start = 0; - if (vinfo_curr->vid <= (*vinfo_last)->vid) + if (!br_vlan_valid_range(vinfo_curr, *vinfo_last, extack)) return -EINVAL; memcpy(&tmp_vinfo, *vinfo_last, sizeof(struct bridge_vlan_info)); for (v = (*vinfo_last)->vid; v <= vinfo_curr->vid; v++) { + bool curr_change = false; + tmp_vinfo.vid = v; - err = br_vlan_info(br, p, cmd, &tmp_vinfo, changed, + err = br_vlan_info(br, p, cmd, &tmp_vinfo, &curr_change, extack); if (err) break; + if (curr_change) { + *changed = curr_change; + if (!v_change_start) + v_change_start = v; + } else { + /* nothing to notify yet */ + if (!v_change_start) + continue; + br_vlan_notify(br, p, v_change_start, + v - 1, rtm_cmd); + v_change_start = 0; + } } + /* v_change_start is set only if the last/whole range changed */ + if (v_change_start) + br_vlan_notify(br, p, v_change_start, + v - 1, rtm_cmd); + *vinfo_last = NULL; return err; } - return br_vlan_info(br, p, cmd, vinfo_curr, changed, extack); + err = br_vlan_info(br, p, cmd, vinfo_curr, changed, extack); + if (*changed) + br_vlan_notify(br, p, vinfo_curr->vid, 0, rtm_cmd); + + return err; } static int br_afspec(struct net_bridge *br, @@ -1607,6 +1628,19 @@ static int br_fill_linkxstats(struct sk_buff *skb, br_multicast_get_stats(br, p, nla_data(nla)); } #endif + + if (p) { + nla = nla_reserve_64bit(skb, BRIDGE_XSTATS_STP, + sizeof(p->stp_xstats), + BRIDGE_XSTATS_PAD); + if (!nla) + goto nla_put_failure; + + spin_lock_bh(&br->lock); + memcpy(nla_data(nla), &p->stp_xstats, sizeof(p->stp_xstats)); + spin_unlock_bh(&br->lock); + } + nla_nest_end(skb, nest); *prividx = 0; @@ -1651,6 +1685,7 @@ int __init br_netlink_init(void) int err; br_mdb_init(); + br_vlan_rtnl_init(); rtnl_af_register(&br_af_ops); err = rtnl_link_register(&br_link_ops); @@ -1668,6 +1703,7 @@ out_af: void br_netlink_fini(void) { br_mdb_uninit(); + br_vlan_rtnl_uninit(); rtnl_af_unregister(&br_af_ops); rtnl_link_unregister(&br_link_ops); } diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h index 36b0367ca1e0..5153ffe79a01 100644 --- a/net/bridge/br_private.h +++ b/net/bridge/br_private.h @@ -113,6 +113,7 @@ enum { * @vid: VLAN id * @flags: bridge vlan flags * @priv_flags: private (in-kernel) bridge vlan flags + * @state: STP state (e.g. blocking, learning, forwarding) * @stats: per-cpu VLAN statistics * @br: if MASTER flag set, this points to a bridge struct * @port: if MASTER flag unset, this points to a port struct @@ -133,6 +134,7 @@ struct net_bridge_vlan { u16 vid; u16 flags; u16 priv_flags; + u8 state; struct br_vlan_stats __percpu *stats; union { struct net_bridge *br; @@ -157,6 +159,7 @@ struct net_bridge_vlan { * @vlan_list: sorted VLAN entry list * @num_vlans: number of total VLAN entries * @pvid: PVID VLAN id + * @pvid_state: PVID's STP state (e.g. forwarding, learning, blocking) * * IMPORTANT: Be careful when checking if there're VLAN entries using list * primitives because the bridge can have entries in its list which @@ -170,6 +173,7 @@ struct net_bridge_vlan_group { struct list_head vlan_list; u16 num_vlans; u16 pvid; + u8 pvid_state; }; /* bridge fdb flags */ @@ -283,6 +287,8 @@ struct net_bridge_port { #endif u16 group_fwd_mask; u16 backup_redirected_cnt; + + struct bridge_stp_xstats stp_xstats; }; #define kobj_to_brport(obj) container_of(obj, struct net_bridge_port, kobj) @@ -505,6 +511,65 @@ static inline bool nbp_state_should_learn(const struct net_bridge_port *p) return p->state == BR_STATE_LEARNING || p->state == BR_STATE_FORWARDING; } +static inline bool br_vlan_valid_id(u16 vid, struct netlink_ext_ack *extack) +{ + bool ret = vid > 0 && vid < VLAN_VID_MASK; + + if (!ret) + NL_SET_ERR_MSG_MOD(extack, "Vlan id is invalid"); + + return ret; +} + +static inline bool br_vlan_valid_range(const struct bridge_vlan_info *cur, + const struct bridge_vlan_info *last, + struct netlink_ext_ack *extack) +{ + /* pvid flag is not allowed in ranges */ + if (cur->flags & BRIDGE_VLAN_INFO_PVID) { + NL_SET_ERR_MSG_MOD(extack, "Pvid isn't allowed in a range"); + return false; + } + + /* when cur is the range end, check if: + * - it has range start flag + * - range ids are invalid (end is equal to or before start) + */ + if (last) { + if (cur->flags & BRIDGE_VLAN_INFO_RANGE_BEGIN) { + NL_SET_ERR_MSG_MOD(extack, "Found a new vlan range start while processing one"); + return false; + } else if (!(cur->flags & BRIDGE_VLAN_INFO_RANGE_END)) { + NL_SET_ERR_MSG_MOD(extack, "Vlan range end flag is missing"); + return false; + } else if (cur->vid <= last->vid) { + NL_SET_ERR_MSG_MOD(extack, "End vlan id is less than or equal to start vlan id"); + return false; + } + } + + /* check for required range flags */ + if (!(cur->flags & (BRIDGE_VLAN_INFO_RANGE_BEGIN | + BRIDGE_VLAN_INFO_RANGE_END))) { + NL_SET_ERR_MSG_MOD(extack, "Both vlan range flags are missing"); + return false; + } + + return true; +} + +static inline int br_afspec_cmd_to_rtm(int cmd) +{ + switch (cmd) { + case RTM_SETLINK: + return RTM_NEWVLAN; + case RTM_DELLINK: + return RTM_DELVLAN; + } + + return 0; +} + static inline int br_opt_get(const struct net_bridge *br, enum net_bridge_opts opt) { @@ -874,7 +939,7 @@ static inline int br_multicast_igmp_type(const struct sk_buff *skb) #ifdef CONFIG_BRIDGE_VLAN_FILTERING bool br_allowed_ingress(const struct net_bridge *br, struct net_bridge_vlan_group *vg, struct sk_buff *skb, - u16 *vid); + u16 *vid, u8 *state); bool br_allowed_egress(struct net_bridge_vlan_group *vg, const struct sk_buff *skb); bool br_should_learn(struct net_bridge_port *p, struct sk_buff *skb, u16 *vid); @@ -909,6 +974,14 @@ void br_vlan_get_stats(const struct net_bridge_vlan *v, void br_vlan_port_event(struct net_bridge_port *p, unsigned long event); int br_vlan_bridge_event(struct net_device *dev, unsigned long event, void *ptr); +void br_vlan_rtnl_init(void); +void br_vlan_rtnl_uninit(void); +void br_vlan_notify(const struct net_bridge *br, + const struct net_bridge_port *p, + u16 vid, u16 vid_range, + int cmd); +bool br_vlan_can_enter_range(const struct net_bridge_vlan *v_curr, + const struct net_bridge_vlan *range_end); static inline struct net_bridge_vlan_group *br_vlan_group( const struct net_bridge *br) @@ -960,11 +1033,15 @@ static inline u16 br_get_pvid(const struct net_bridge_vlan_group *vg) return vg->pvid; } +static inline u16 br_vlan_flags(const struct net_bridge_vlan *v, u16 pvid) +{ + return v->vid == pvid ? v->flags | BRIDGE_VLAN_INFO_PVID : v->flags; +} #else static inline bool br_allowed_ingress(const struct net_bridge *br, struct net_bridge_vlan_group *vg, struct sk_buff *skb, - u16 *vid) + u16 *vid, u8 *state) { return true; } @@ -1103,6 +1180,70 @@ static inline int br_vlan_bridge_event(struct net_device *dev, { return 0; } + +static inline void br_vlan_rtnl_init(void) +{ +} + +static inline void br_vlan_rtnl_uninit(void) +{ +} + +static inline void br_vlan_notify(const struct net_bridge *br, + const struct net_bridge_port *p, + u16 vid, u16 vid_range, + int cmd) +{ +} +#endif + +/* br_vlan_options.c */ +#ifdef CONFIG_BRIDGE_VLAN_FILTERING +bool br_vlan_opts_eq(const struct net_bridge_vlan *v1, + const struct net_bridge_vlan *v2); +bool br_vlan_opts_fill(struct sk_buff *skb, const struct net_bridge_vlan *v); +size_t br_vlan_opts_nl_size(void); +int br_vlan_process_options(const struct net_bridge *br, + const struct net_bridge_port *p, + struct net_bridge_vlan *range_start, + struct net_bridge_vlan *range_end, + struct nlattr **tb, + struct netlink_ext_ack *extack); + +/* vlan state manipulation helpers using *_ONCE to annotate lock-free access */ +static inline u8 br_vlan_get_state(const struct net_bridge_vlan *v) +{ + return READ_ONCE(v->state); +} + +static inline void br_vlan_set_state(struct net_bridge_vlan *v, u8 state) +{ + WRITE_ONCE(v->state, state); +} + +static inline u8 br_vlan_get_pvid_state(const struct net_bridge_vlan_group *vg) +{ + return READ_ONCE(vg->pvid_state); +} + +static inline void br_vlan_set_pvid_state(struct net_bridge_vlan_group *vg, + u8 state) +{ + WRITE_ONCE(vg->pvid_state, state); +} + +/* learn_allow is true at ingress and false at egress */ +static inline bool br_vlan_state_allowed(u8 state, bool learn_allow) +{ + switch (state) { + case BR_STATE_LEARNING: + return learn_allow; + case BR_STATE_FORWARDING: + return true; + default: + return false; + } +} #endif struct nf_br_ops { @@ -1174,6 +1315,12 @@ int br_setlink(struct net_device *dev, struct nlmsghdr *nlmsg, u16 flags, int br_dellink(struct net_device *dev, struct nlmsghdr *nlmsg, u16 flags); int br_getlink(struct sk_buff *skb, u32 pid, u32 seq, struct net_device *dev, u32 filter_mask, int nlflags); +int br_process_vlan_info(struct net_bridge *br, + struct net_bridge_port *p, int cmd, + struct bridge_vlan_info *vinfo_curr, + struct bridge_vlan_info **vinfo_last, + bool *changed, + struct netlink_ext_ack *extack); #ifdef CONFIG_SYSFS /* br_sysfs_if.c */ diff --git a/net/bridge/br_stp.c b/net/bridge/br_stp.c index 1f1410f8d312..6856a6d9282b 100644 --- a/net/bridge/br_stp.c +++ b/net/bridge/br_stp.c @@ -45,6 +45,17 @@ void br_set_state(struct net_bridge_port *p, unsigned int state) br_info(p->br, "port %u(%s) entered %s state\n", (unsigned int) p->port_no, p->dev->name, br_port_state_names[p->state]); + + if (p->br->stp_enabled == BR_KERNEL_STP) { + switch (p->state) { + case BR_STATE_BLOCKING: + p->stp_xstats.transition_blk++; + break; + case BR_STATE_FORWARDING: + p->stp_xstats.transition_fwd++; + break; + } + } } /* called under bridge lock */ @@ -484,6 +495,8 @@ void br_received_config_bpdu(struct net_bridge_port *p, struct net_bridge *br; int was_root; + p->stp_xstats.rx_bpdu++; + br = p->br; was_root = br_is_root_bridge(br); @@ -517,6 +530,8 @@ void br_received_config_bpdu(struct net_bridge_port *p, /* called under bridge lock */ void br_received_tcn_bpdu(struct net_bridge_port *p) { + p->stp_xstats.rx_tcn++; + if (br_is_designated_port(p)) { br_info(p->br, "port %u(%s) received tcn bpdu\n", (unsigned int) p->port_no, p->dev->name); diff --git a/net/bridge/br_stp_bpdu.c b/net/bridge/br_stp_bpdu.c index 7796dd9d42d7..0e4572f31330 100644 --- a/net/bridge/br_stp_bpdu.c +++ b/net/bridge/br_stp_bpdu.c @@ -118,6 +118,8 @@ void br_send_config_bpdu(struct net_bridge_port *p, struct br_config_bpdu *bpdu) br_set_ticks(buf+33, bpdu->forward_delay); br_send_bpdu(p, buf, 35); + + p->stp_xstats.tx_bpdu++; } /* called under bridge lock */ @@ -133,6 +135,8 @@ void br_send_tcn_bpdu(struct net_bridge_port *p) buf[2] = 0; buf[3] = BPDU_TYPE_TCN; br_send_bpdu(p, buf, 4); + + p->stp_xstats.tx_tcn++; } /* diff --git a/net/bridge/br_vlan.c b/net/bridge/br_vlan.c index bb98984cd27d..6b5deca08b89 100644 --- a/net/bridge/br_vlan.c +++ b/net/bridge/br_vlan.c @@ -34,13 +34,15 @@ static struct net_bridge_vlan *br_vlan_lookup(struct rhashtable *tbl, u16 vid) return rhashtable_lookup_fast(tbl, &vid, br_vlan_rht_params); } -static bool __vlan_add_pvid(struct net_bridge_vlan_group *vg, u16 vid) +static bool __vlan_add_pvid(struct net_bridge_vlan_group *vg, + const struct net_bridge_vlan *v) { - if (vg->pvid == vid) + if (vg->pvid == v->vid) return false; smp_wmb(); - vg->pvid = vid; + br_vlan_set_pvid_state(vg, v->state); + vg->pvid = v->vid; return true; } @@ -69,7 +71,7 @@ static bool __vlan_add_flags(struct net_bridge_vlan *v, u16 flags) vg = nbp_vlan_group(v->port); if (flags & BRIDGE_VLAN_INFO_PVID) - ret = __vlan_add_pvid(vg, v->vid); + ret = __vlan_add_pvid(vg, v); else ret = __vlan_delete_pvid(vg, v->vid); @@ -257,6 +259,10 @@ static int __vlan_add(struct net_bridge_vlan *v, u16 flags, &changed, extack); if (err) goto out_filt; + + if (changed) + br_vlan_notify(br, NULL, v->vid, 0, + RTM_NEWVLAN); } masterv = br_vlan_get_master(br, v->vid, extack); @@ -289,6 +295,9 @@ static int __vlan_add(struct net_bridge_vlan *v, u16 flags, vg->num_vlans++; } + /* set the state before publishing */ + v->state = BR_STATE_FORWARDING; + err = rhashtable_lookup_insert_fast(&vg->vlan_hash, &v->vnode, br_vlan_rht_params); if (err) @@ -380,13 +389,31 @@ static void __vlan_group_free(struct net_bridge_vlan_group *vg) kfree(vg); } -static void __vlan_flush(struct net_bridge_vlan_group *vg) +static void __vlan_flush(const struct net_bridge *br, + const struct net_bridge_port *p, + struct net_bridge_vlan_group *vg) { struct net_bridge_vlan *vlan, *tmp; + u16 v_start = 0, v_end = 0; __vlan_delete_pvid(vg, vg->pvid); - list_for_each_entry_safe(vlan, tmp, &vg->vlan_list, vlist) + list_for_each_entry_safe(vlan, tmp, &vg->vlan_list, vlist) { + /* take care of disjoint ranges */ + if (!v_start) { + v_start = vlan->vid; + } else if (vlan->vid - v_end != 1) { + /* found range end, notify and start next one */ + br_vlan_notify(br, p, v_start, v_end, RTM_DELVLAN); + v_start = vlan->vid; + } + v_end = vlan->vid; + __vlan_del(vlan); + } + + /* notify about the last/whole vlan range */ + if (v_start) + br_vlan_notify(br, p, v_start, v_end, RTM_DELVLAN); } struct sk_buff *br_handle_vlan(struct net_bridge *br, @@ -444,7 +471,8 @@ out: /* Called under RCU */ static bool __allowed_ingress(const struct net_bridge *br, struct net_bridge_vlan_group *vg, - struct sk_buff *skb, u16 *vid) + struct sk_buff *skb, u16 *vid, + u8 *state) { struct br_vlan_stats *stats; struct net_bridge_vlan *v; @@ -510,13 +538,25 @@ static bool __allowed_ingress(const struct net_bridge *br, skb->vlan_tci |= pvid; /* if stats are disabled we can avoid the lookup */ - if (!br_opt_get(br, BROPT_VLAN_STATS_ENABLED)) - return true; + if (!br_opt_get(br, BROPT_VLAN_STATS_ENABLED)) { + if (*state == BR_STATE_FORWARDING) { + *state = br_vlan_get_pvid_state(vg); + return br_vlan_state_allowed(*state, true); + } else { + return true; + } + } } v = br_vlan_find(vg, *vid); if (!v || !br_vlan_should_use(v)) goto drop; + if (*state == BR_STATE_FORWARDING) { + *state = br_vlan_get_state(v); + if (!br_vlan_state_allowed(*state, true)) + goto drop; + } + if (br_opt_get(br, BROPT_VLAN_STATS_ENABLED)) { stats = this_cpu_ptr(v->stats); u64_stats_update_begin(&stats->syncp); @@ -534,7 +574,7 @@ drop: bool br_allowed_ingress(const struct net_bridge *br, struct net_bridge_vlan_group *vg, struct sk_buff *skb, - u16 *vid) + u16 *vid, u8 *state) { /* If VLAN filtering is disabled on the bridge, all packets are * permitted. @@ -544,7 +584,7 @@ bool br_allowed_ingress(const struct net_bridge *br, return true; } - return __allowed_ingress(br, vg, skb, vid); + return __allowed_ingress(br, vg, skb, vid, state); } /* Called under RCU. */ @@ -560,7 +600,8 @@ bool br_allowed_egress(struct net_bridge_vlan_group *vg, br_vlan_get_tag(skb, &vid); v = br_vlan_find(vg, vid); - if (v && br_vlan_should_use(v)) + if (v && br_vlan_should_use(v) && + br_vlan_state_allowed(br_vlan_get_state(v), false)) return true; return false; @@ -571,6 +612,7 @@ bool br_should_learn(struct net_bridge_port *p, struct sk_buff *skb, u16 *vid) { struct net_bridge_vlan_group *vg; struct net_bridge *br = p->br; + struct net_bridge_vlan *v; /* If filtering was disabled at input, let it pass. */ if (!br_opt_get(br, BROPT_VLAN_ENABLED)) @@ -585,13 +627,15 @@ bool br_should_learn(struct net_bridge_port *p, struct sk_buff *skb, u16 *vid) if (!*vid) { *vid = br_get_pvid(vg); - if (!*vid) + if (!*vid || + !br_vlan_state_allowed(br_vlan_get_pvid_state(vg), true)) return false; return true; } - if (br_vlan_find(vg, *vid)) + v = br_vlan_find(vg, *vid); + if (v && br_vlan_state_allowed(br_vlan_get_state(v), true)) return true; return false; @@ -716,7 +760,7 @@ void br_vlan_flush(struct net_bridge *br) ASSERT_RTNL(); vg = br_vlan_group(br); - __vlan_flush(vg); + __vlan_flush(br, NULL, vg); RCU_INIT_POINTER(br->vlgrp, NULL); synchronize_rcu(); __vlan_group_free(vg); @@ -925,12 +969,15 @@ static void br_vlan_disable_default_pvid(struct net_bridge *br) /* Disable default_pvid on all ports where it is still * configured. */ - if (vlan_default_pvid(br_vlan_group(br), pvid)) - br_vlan_delete(br, pvid); + if (vlan_default_pvid(br_vlan_group(br), pvid)) { + if (!br_vlan_delete(br, pvid)) + br_vlan_notify(br, NULL, pvid, 0, RTM_DELVLAN); + } list_for_each_entry(p, &br->port_list, list) { - if (vlan_default_pvid(nbp_vlan_group(p), pvid)) - nbp_vlan_delete(p, pvid); + if (vlan_default_pvid(nbp_vlan_group(p), pvid) && + !nbp_vlan_delete(p, pvid)) + br_vlan_notify(br, p, pvid, 0, RTM_DELVLAN); } br->default_pvid = 0; @@ -972,7 +1019,10 @@ int __br_vlan_set_default_pvid(struct net_bridge *br, u16 pvid, &vlchange, extack); if (err) goto out; - br_vlan_delete(br, old_pvid); + + if (br_vlan_delete(br, old_pvid)) + br_vlan_notify(br, NULL, old_pvid, 0, RTM_DELVLAN); + br_vlan_notify(br, NULL, pvid, 0, RTM_NEWVLAN); set_bit(0, changed); } @@ -992,7 +1042,9 @@ int __br_vlan_set_default_pvid(struct net_bridge *br, u16 pvid, &vlchange, extack); if (err) goto err_port; - nbp_vlan_delete(p, old_pvid); + if (nbp_vlan_delete(p, old_pvid)) + br_vlan_notify(br, p, old_pvid, 0, RTM_DELVLAN); + br_vlan_notify(p->br, p, pvid, 0, RTM_NEWVLAN); set_bit(p->port_no, changed); } @@ -1007,22 +1059,28 @@ err_port: if (!test_bit(p->port_no, changed)) continue; - if (old_pvid) + if (old_pvid) { nbp_vlan_add(p, old_pvid, BRIDGE_VLAN_INFO_PVID | BRIDGE_VLAN_INFO_UNTAGGED, &vlchange, NULL); + br_vlan_notify(p->br, p, old_pvid, 0, RTM_NEWVLAN); + } nbp_vlan_delete(p, pvid); + br_vlan_notify(br, p, pvid, 0, RTM_DELVLAN); } if (test_bit(0, changed)) { - if (old_pvid) + if (old_pvid) { br_vlan_add(br, old_pvid, BRIDGE_VLAN_INFO_PVID | BRIDGE_VLAN_INFO_UNTAGGED | BRIDGE_VLAN_INFO_BRENTRY, &vlchange, NULL); + br_vlan_notify(br, NULL, old_pvid, 0, RTM_NEWVLAN); + } br_vlan_delete(br, pvid); + br_vlan_notify(br, NULL, pvid, 0, RTM_DELVLAN); } goto out; } @@ -1115,6 +1173,7 @@ int nbp_vlan_init(struct net_bridge_port *p, struct netlink_ext_ack *extack) &changed, extack); if (ret) goto err_vlan_add; + br_vlan_notify(p->br, p, p->br->default_pvid, 0, RTM_NEWVLAN); } out: return ret; @@ -1196,7 +1255,7 @@ void nbp_vlan_flush(struct net_bridge_port *port) ASSERT_RTNL(); vg = nbp_vlan_group(port); - __vlan_flush(vg); + __vlan_flush(port->br, port, vg); RCU_INIT_POINTER(port->vlgrp, NULL); synchronize_rcu(); __vlan_group_free(vg); @@ -1462,8 +1521,8 @@ int br_vlan_bridge_event(struct net_device *dev, unsigned long event, void *ptr) { struct netdev_notifier_changeupper_info *info; struct net_bridge *br = netdev_priv(dev); - bool changed; - int ret = 0; + int vlcmd = 0, ret = 0; + bool changed = false; switch (event) { case NETDEV_REGISTER: @@ -1471,9 +1530,11 @@ int br_vlan_bridge_event(struct net_device *dev, unsigned long event, void *ptr) BRIDGE_VLAN_INFO_PVID | BRIDGE_VLAN_INFO_UNTAGGED | BRIDGE_VLAN_INFO_BRENTRY, &changed, NULL); + vlcmd = RTM_NEWVLAN; break; case NETDEV_UNREGISTER: - br_vlan_delete(br, br->default_pvid); + changed = !br_vlan_delete(br, br->default_pvid); + vlcmd = RTM_DELVLAN; break; case NETDEV_CHANGEUPPER: info = ptr; @@ -1487,6 +1548,8 @@ int br_vlan_bridge_event(struct net_device *dev, unsigned long event, void *ptr) br_vlan_link_state_change(dev, br); break; } + if (changed) + br_vlan_notify(br, NULL, br->default_pvid, 0, vlcmd); return ret; } @@ -1505,3 +1568,441 @@ void br_vlan_port_event(struct net_bridge_port *p, unsigned long event) break; } } + +/* v_opts is used to dump the options which must be equal in the whole range */ +static bool br_vlan_fill_vids(struct sk_buff *skb, u16 vid, u16 vid_range, + const struct net_bridge_vlan *v_opts, + u16 flags) +{ + struct bridge_vlan_info info; + struct nlattr *nest; + + nest = nla_nest_start(skb, BRIDGE_VLANDB_ENTRY); + if (!nest) + return false; + + memset(&info, 0, sizeof(info)); + info.vid = vid; + if (flags & BRIDGE_VLAN_INFO_UNTAGGED) + info.flags |= BRIDGE_VLAN_INFO_UNTAGGED; + if (flags & BRIDGE_VLAN_INFO_PVID) + info.flags |= BRIDGE_VLAN_INFO_PVID; + + if (nla_put(skb, BRIDGE_VLANDB_ENTRY_INFO, sizeof(info), &info)) + goto out_err; + + if (vid_range && vid < vid_range && + !(flags & BRIDGE_VLAN_INFO_PVID) && + nla_put_u16(skb, BRIDGE_VLANDB_ENTRY_RANGE, vid_range)) + goto out_err; + + if (v_opts && !br_vlan_opts_fill(skb, v_opts)) + goto out_err; + + nla_nest_end(skb, nest); + + return true; + +out_err: + nla_nest_cancel(skb, nest); + return false; +} + +static size_t rtnl_vlan_nlmsg_size(void) +{ + return NLMSG_ALIGN(sizeof(struct br_vlan_msg)) + + nla_total_size(0) /* BRIDGE_VLANDB_ENTRY */ + + nla_total_size(sizeof(u16)) /* BRIDGE_VLANDB_ENTRY_RANGE */ + + nla_total_size(sizeof(struct bridge_vlan_info)) /* BRIDGE_VLANDB_ENTRY_INFO */ + + br_vlan_opts_nl_size(); /* bridge vlan options */ +} + +void br_vlan_notify(const struct net_bridge *br, + const struct net_bridge_port *p, + u16 vid, u16 vid_range, + int cmd) +{ + struct net_bridge_vlan_group *vg; + struct net_bridge_vlan *v = NULL; + struct br_vlan_msg *bvm; + struct nlmsghdr *nlh; + struct sk_buff *skb; + int err = -ENOBUFS; + struct net *net; + u16 flags = 0; + int ifindex; + + /* right now notifications are done only with rtnl held */ + ASSERT_RTNL(); + + if (p) { + ifindex = p->dev->ifindex; + vg = nbp_vlan_group(p); + net = dev_net(p->dev); + } else { + ifindex = br->dev->ifindex; + vg = br_vlan_group(br); + net = dev_net(br->dev); + } + + skb = nlmsg_new(rtnl_vlan_nlmsg_size(), GFP_KERNEL); + if (!skb) + goto out_err; + + err = -EMSGSIZE; + nlh = nlmsg_put(skb, 0, 0, cmd, sizeof(*bvm), 0); + if (!nlh) + goto out_err; + bvm = nlmsg_data(nlh); + memset(bvm, 0, sizeof(*bvm)); + bvm->family = AF_BRIDGE; + bvm->ifindex = ifindex; + + switch (cmd) { + case RTM_NEWVLAN: + /* need to find the vlan due to flags/options */ + v = br_vlan_find(vg, vid); + if (!v || !br_vlan_should_use(v)) + goto out_kfree; + + flags = v->flags; + if (br_get_pvid(vg) == v->vid) + flags |= BRIDGE_VLAN_INFO_PVID; + break; + case RTM_DELVLAN: + break; + default: + goto out_kfree; + } + + if (!br_vlan_fill_vids(skb, vid, vid_range, v, flags)) + goto out_err; + + nlmsg_end(skb, nlh); + rtnl_notify(skb, net, 0, RTNLGRP_BRVLAN, NULL, GFP_KERNEL); + return; + +out_err: + rtnl_set_sk_err(net, RTNLGRP_BRVLAN, err); +out_kfree: + kfree_skb(skb); +} + +/* check if v_curr can enter a range ending in range_end */ +bool br_vlan_can_enter_range(const struct net_bridge_vlan *v_curr, + const struct net_bridge_vlan *range_end) +{ + return v_curr->vid - range_end->vid == 1 && + range_end->flags == v_curr->flags && + br_vlan_opts_eq(v_curr, range_end); +} + +static int br_vlan_dump_dev(const struct net_device *dev, + struct sk_buff *skb, + struct netlink_callback *cb) +{ + struct net_bridge_vlan *v, *range_start = NULL, *range_end = NULL; + struct net_bridge_vlan_group *vg; + int idx = 0, s_idx = cb->args[1]; + struct nlmsghdr *nlh = NULL; + struct net_bridge_port *p; + struct br_vlan_msg *bvm; + struct net_bridge *br; + int err = 0; + u16 pvid; + + if (!netif_is_bridge_master(dev) && !netif_is_bridge_port(dev)) + return -EINVAL; + + if (netif_is_bridge_master(dev)) { + br = netdev_priv(dev); + vg = br_vlan_group_rcu(br); + p = NULL; + } else { + p = br_port_get_rcu(dev); + if (WARN_ON(!p)) + return -EINVAL; + vg = nbp_vlan_group_rcu(p); + br = p->br; + } + + if (!vg) + return 0; + + nlh = nlmsg_put(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, + RTM_NEWVLAN, sizeof(*bvm), NLM_F_MULTI); + if (!nlh) + return -EMSGSIZE; + bvm = nlmsg_data(nlh); + memset(bvm, 0, sizeof(*bvm)); + bvm->family = PF_BRIDGE; + bvm->ifindex = dev->ifindex; + pvid = br_get_pvid(vg); + + /* idx must stay at range's beginning until it is filled in */ + list_for_each_entry_rcu(v, &vg->vlan_list, vlist) { + if (!br_vlan_should_use(v)) + continue; + if (idx < s_idx) { + idx++; + continue; + } + + if (!range_start) { + range_start = v; + range_end = v; + continue; + } + + if (v->vid == pvid || !br_vlan_can_enter_range(v, range_end)) { + u16 flags = br_vlan_flags(range_start, pvid); + + if (!br_vlan_fill_vids(skb, range_start->vid, + range_end->vid, range_start, + flags)) { + err = -EMSGSIZE; + break; + } + /* advance number of filled vlans */ + idx += range_end->vid - range_start->vid + 1; + + range_start = v; + } + range_end = v; + } + + /* err will be 0 and range_start will be set in 3 cases here: + * - first vlan (range_start == range_end) + * - last vlan (range_start == range_end, not in range) + * - last vlan range (range_start != range_end, in range) + */ + if (!err && range_start && + !br_vlan_fill_vids(skb, range_start->vid, range_end->vid, + range_start, br_vlan_flags(range_start, pvid))) + err = -EMSGSIZE; + + cb->args[1] = err ? idx : 0; + + nlmsg_end(skb, nlh); + + return err; +} + +static int br_vlan_rtm_dump(struct sk_buff *skb, struct netlink_callback *cb) +{ + int idx = 0, err = 0, s_idx = cb->args[0]; + struct net *net = sock_net(skb->sk); + struct br_vlan_msg *bvm; + struct net_device *dev; + + err = nlmsg_parse(cb->nlh, sizeof(*bvm), NULL, 0, NULL, cb->extack); + if (err < 0) + return err; + + bvm = nlmsg_data(cb->nlh); + + rcu_read_lock(); + if (bvm->ifindex) { + dev = dev_get_by_index_rcu(net, bvm->ifindex); + if (!dev) { + err = -ENODEV; + goto out_err; + } + err = br_vlan_dump_dev(dev, skb, cb); + if (err && err != -EMSGSIZE) + goto out_err; + } else { + for_each_netdev_rcu(net, dev) { + if (idx < s_idx) + goto skip; + + err = br_vlan_dump_dev(dev, skb, cb); + if (err == -EMSGSIZE) + break; +skip: + idx++; + } + } + cb->args[0] = idx; + rcu_read_unlock(); + + return skb->len; + +out_err: + rcu_read_unlock(); + + return err; +} + +static const struct nla_policy br_vlan_db_policy[BRIDGE_VLANDB_ENTRY_MAX + 1] = { + [BRIDGE_VLANDB_ENTRY_INFO] = { .type = NLA_EXACT_LEN, + .len = sizeof(struct bridge_vlan_info) }, + [BRIDGE_VLANDB_ENTRY_RANGE] = { .type = NLA_U16 }, + [BRIDGE_VLANDB_ENTRY_STATE] = { .type = NLA_U8 }, +}; + +static int br_vlan_rtm_process_one(struct net_device *dev, + const struct nlattr *attr, + int cmd, struct netlink_ext_ack *extack) +{ + struct bridge_vlan_info *vinfo, vrange_end, *vinfo_last = NULL; + struct nlattr *tb[BRIDGE_VLANDB_ENTRY_MAX + 1]; + bool changed = false, skip_processing = false; + struct net_bridge_vlan_group *vg; + struct net_bridge_port *p = NULL; + int err = 0, cmdmap = 0; + struct net_bridge *br; + + if (netif_is_bridge_master(dev)) { + br = netdev_priv(dev); + vg = br_vlan_group(br); + } else { + p = br_port_get_rtnl(dev); + if (WARN_ON(!p)) + return -ENODEV; + br = p->br; + vg = nbp_vlan_group(p); + } + + if (WARN_ON(!vg)) + return -ENODEV; + + err = nla_parse_nested(tb, BRIDGE_VLANDB_ENTRY_MAX, attr, + br_vlan_db_policy, extack); + if (err) + return err; + + if (!tb[BRIDGE_VLANDB_ENTRY_INFO]) { + NL_SET_ERR_MSG_MOD(extack, "Missing vlan entry info"); + return -EINVAL; + } + memset(&vrange_end, 0, sizeof(vrange_end)); + + vinfo = nla_data(tb[BRIDGE_VLANDB_ENTRY_INFO]); + if (vinfo->flags & (BRIDGE_VLAN_INFO_RANGE_BEGIN | + BRIDGE_VLAN_INFO_RANGE_END)) { + NL_SET_ERR_MSG_MOD(extack, "Old-style vlan ranges are not allowed when using RTM vlan calls"); + return -EINVAL; + } + if (!br_vlan_valid_id(vinfo->vid, extack)) + return -EINVAL; + + if (tb[BRIDGE_VLANDB_ENTRY_RANGE]) { + vrange_end.vid = nla_get_u16(tb[BRIDGE_VLANDB_ENTRY_RANGE]); + /* validate user-provided flags without RANGE_BEGIN */ + vrange_end.flags = BRIDGE_VLAN_INFO_RANGE_END | vinfo->flags; + vinfo->flags |= BRIDGE_VLAN_INFO_RANGE_BEGIN; + + /* vinfo_last is the range start, vinfo the range end */ + vinfo_last = vinfo; + vinfo = &vrange_end; + + if (!br_vlan_valid_id(vinfo->vid, extack) || + !br_vlan_valid_range(vinfo, vinfo_last, extack)) + return -EINVAL; + } + + switch (cmd) { + case RTM_NEWVLAN: + cmdmap = RTM_SETLINK; + skip_processing = !!(vinfo->flags & BRIDGE_VLAN_INFO_ONLY_OPTS); + break; + case RTM_DELVLAN: + cmdmap = RTM_DELLINK; + break; + } + + if (!skip_processing) { + struct bridge_vlan_info *tmp_last = vinfo_last; + + /* br_process_vlan_info may overwrite vinfo_last */ + err = br_process_vlan_info(br, p, cmdmap, vinfo, &tmp_last, + &changed, extack); + + /* notify first if anything changed */ + if (changed) + br_ifinfo_notify(cmdmap, br, p); + + if (err) + return err; + } + + /* deal with options */ + if (cmd == RTM_NEWVLAN) { + struct net_bridge_vlan *range_start, *range_end; + + if (vinfo_last) { + range_start = br_vlan_find(vg, vinfo_last->vid); + range_end = br_vlan_find(vg, vinfo->vid); + } else { + range_start = br_vlan_find(vg, vinfo->vid); + range_end = range_start; + } + + err = br_vlan_process_options(br, p, range_start, range_end, + tb, extack); + } + + return err; +} + +static int br_vlan_rtm_process(struct sk_buff *skb, struct nlmsghdr *nlh, + struct netlink_ext_ack *extack) +{ + struct net *net = sock_net(skb->sk); + struct br_vlan_msg *bvm; + struct net_device *dev; + struct nlattr *attr; + int err, vlans = 0; + int rem; + + /* this should validate the header and check for remaining bytes */ + err = nlmsg_parse(nlh, sizeof(*bvm), NULL, BRIDGE_VLANDB_MAX, NULL, + extack); + if (err < 0) + return err; + + bvm = nlmsg_data(nlh); + dev = __dev_get_by_index(net, bvm->ifindex); + if (!dev) + return -ENODEV; + + if (!netif_is_bridge_master(dev) && !netif_is_bridge_port(dev)) { + NL_SET_ERR_MSG_MOD(extack, "The device is not a valid bridge or bridge port"); + return -EINVAL; + } + + nlmsg_for_each_attr(attr, nlh, sizeof(*bvm), rem) { + if (nla_type(attr) != BRIDGE_VLANDB_ENTRY) + continue; + + vlans++; + err = br_vlan_rtm_process_one(dev, attr, nlh->nlmsg_type, + extack); + if (err) + break; + } + if (!vlans) { + NL_SET_ERR_MSG_MOD(extack, "No vlans found to process"); + err = -EINVAL; + } + + return err; +} + +void br_vlan_rtnl_init(void) +{ + rtnl_register_module(THIS_MODULE, PF_BRIDGE, RTM_GETVLAN, NULL, + br_vlan_rtm_dump, 0); + rtnl_register_module(THIS_MODULE, PF_BRIDGE, RTM_NEWVLAN, + br_vlan_rtm_process, NULL, 0); + rtnl_register_module(THIS_MODULE, PF_BRIDGE, RTM_DELVLAN, + br_vlan_rtm_process, NULL, 0); +} + +void br_vlan_rtnl_uninit(void) +{ + rtnl_unregister(PF_BRIDGE, RTM_GETVLAN); + rtnl_unregister(PF_BRIDGE, RTM_NEWVLAN); + rtnl_unregister(PF_BRIDGE, RTM_DELVLAN); +} diff --git a/net/bridge/br_vlan_options.c b/net/bridge/br_vlan_options.c new file mode 100644 index 000000000000..cd2eb194eb98 --- /dev/null +++ b/net/bridge/br_vlan_options.c @@ -0,0 +1,160 @@ +// SPDX-License-Identifier: GPL-2.0-only +// Copyright (c) 2020, Nikolay Aleksandrov <nikolay@cumulusnetworks.com> +#include <linux/kernel.h> +#include <linux/netdevice.h> +#include <linux/rtnetlink.h> +#include <linux/slab.h> + +#include "br_private.h" + +/* check if the options between two vlans are equal */ +bool br_vlan_opts_eq(const struct net_bridge_vlan *v1, + const struct net_bridge_vlan *v2) +{ + return v1->state == v2->state; +} + +bool br_vlan_opts_fill(struct sk_buff *skb, const struct net_bridge_vlan *v) +{ + return !nla_put_u8(skb, BRIDGE_VLANDB_ENTRY_STATE, + br_vlan_get_state(v)); +} + +size_t br_vlan_opts_nl_size(void) +{ + return nla_total_size(sizeof(u8)); /* BRIDGE_VLANDB_ENTRY_STATE */ +} + +static int br_vlan_modify_state(struct net_bridge_vlan_group *vg, + struct net_bridge_vlan *v, + u8 state, + bool *changed, + struct netlink_ext_ack *extack) +{ + struct net_bridge *br; + + ASSERT_RTNL(); + + if (state > BR_STATE_BLOCKING) { + NL_SET_ERR_MSG_MOD(extack, "Invalid vlan state"); + return -EINVAL; + } + + if (br_vlan_is_brentry(v)) + br = v->br; + else + br = v->port->br; + + if (br->stp_enabled == BR_KERNEL_STP) { + NL_SET_ERR_MSG_MOD(extack, "Can't modify vlan state when using kernel STP"); + return -EBUSY; + } + + if (v->state == state) + return 0; + + if (v->vid == br_get_pvid(vg)) + br_vlan_set_pvid_state(vg, state); + + br_vlan_set_state(v, state); + *changed = true; + + return 0; +} + +static int br_vlan_process_one_opts(const struct net_bridge *br, + const struct net_bridge_port *p, + struct net_bridge_vlan_group *vg, + struct net_bridge_vlan *v, + struct nlattr **tb, + bool *changed, + struct netlink_ext_ack *extack) +{ + int err; + + *changed = false; + if (tb[BRIDGE_VLANDB_ENTRY_STATE]) { + u8 state = nla_get_u8(tb[BRIDGE_VLANDB_ENTRY_STATE]); + + err = br_vlan_modify_state(vg, v, state, changed, extack); + if (err) + return err; + } + + return 0; +} + +int br_vlan_process_options(const struct net_bridge *br, + const struct net_bridge_port *p, + struct net_bridge_vlan *range_start, + struct net_bridge_vlan *range_end, + struct nlattr **tb, + struct netlink_ext_ack *extack) +{ + struct net_bridge_vlan *v, *curr_start = NULL, *curr_end = NULL; + struct net_bridge_vlan_group *vg; + int vid, err = 0; + u16 pvid; + + if (p) + vg = nbp_vlan_group(p); + else + vg = br_vlan_group(br); + + if (!range_start || !br_vlan_should_use(range_start)) { + NL_SET_ERR_MSG_MOD(extack, "Vlan range start doesn't exist, can't process options"); + return -ENOENT; + } + if (!range_end || !br_vlan_should_use(range_end)) { + NL_SET_ERR_MSG_MOD(extack, "Vlan range end doesn't exist, can't process options"); + return -ENOENT; + } + + pvid = br_get_pvid(vg); + for (vid = range_start->vid; vid <= range_end->vid; vid++) { + bool changed = false; + + v = br_vlan_find(vg, vid); + if (!v || !br_vlan_should_use(v)) { + NL_SET_ERR_MSG_MOD(extack, "Vlan in range doesn't exist, can't process options"); + err = -ENOENT; + break; + } + + err = br_vlan_process_one_opts(br, p, vg, v, tb, &changed, + extack); + if (err) + break; + + if (changed) { + /* vlan options changed, check for range */ + if (!curr_start) { + curr_start = v; + curr_end = v; + continue; + } + + if (v->vid == pvid || + !br_vlan_can_enter_range(v, curr_end)) { + br_vlan_notify(br, p, curr_start->vid, + curr_end->vid, RTM_NEWVLAN); + curr_start = v; + } + curr_end = v; + } else { + /* nothing changed and nothing to notify yet */ + if (!curr_start) + continue; + + br_vlan_notify(br, p, curr_start->vid, curr_end->vid, + RTM_NEWVLAN); + curr_start = NULL; + curr_end = NULL; + } + } + if (curr_start) + br_vlan_notify(br, p, curr_start->vid, curr_end->vid, + RTM_NEWVLAN); + + return err; +} diff --git a/net/core/Makefile b/net/core/Makefile index a104dc8faafc..3e2c378e5f31 100644 --- a/net/core/Makefile +++ b/net/core/Makefile @@ -8,7 +8,7 @@ obj-y := sock.o request_sock.o skbuff.o datagram.o stream.o scm.o \ obj-$(CONFIG_SYSCTL) += sysctl_net_core.o -obj-y += dev.o ethtool.o dev_addr_lists.o dst.o netevent.o \ +obj-y += dev.o dev_addr_lists.o dst.o netevent.o \ neighbour.o rtnetlink.o utils.o link_watch.o filter.o \ sock_diag.o dev_ioctl.o tso.o sock_reuseport.o \ fib_notifier.o xdp.o flow_offload.o diff --git a/net/core/datagram.c b/net/core/datagram.c index da3c24ed129c..a78e7f864c1e 100644 --- a/net/core/datagram.c +++ b/net/core/datagram.c @@ -84,7 +84,8 @@ static int receiver_wake_function(wait_queue_entry_t *wait, unsigned int mode, i /* * Wait for the last received packet to be different from skb */ -int __skb_wait_for_more_packets(struct sock *sk, int *err, long *timeo_p, +int __skb_wait_for_more_packets(struct sock *sk, struct sk_buff_head *queue, + int *err, long *timeo_p, const struct sk_buff *skb) { int error; @@ -97,7 +98,7 @@ int __skb_wait_for_more_packets(struct sock *sk, int *err, long *timeo_p, if (error) goto out_err; - if (READ_ONCE(sk->sk_receive_queue.prev) != skb) + if (READ_ONCE(queue->prev) != skb) goto out; /* Socket shut down? */ @@ -209,6 +210,7 @@ struct sk_buff *__skb_try_recv_from_queue(struct sock *sk, /** * __skb_try_recv_datagram - Receive a datagram skbuff * @sk: socket + * @queue: socket queue from which to receive * @flags: MSG\_ flags * @destructor: invoked under the receive lock on successful dequeue * @off: an offset in bytes to peek skb from. Returns an offset @@ -241,13 +243,14 @@ struct sk_buff *__skb_try_recv_from_queue(struct sock *sk, * quite explicitly by POSIX 1003.1g, don't change them without having * the standard around please. */ -struct sk_buff *__skb_try_recv_datagram(struct sock *sk, unsigned int flags, +struct sk_buff *__skb_try_recv_datagram(struct sock *sk, + struct sk_buff_head *queue, + unsigned int flags, void (*destructor)(struct sock *sk, struct sk_buff *skb), int *off, int *err, struct sk_buff **last) { - struct sk_buff_head *queue = &sk->sk_receive_queue; struct sk_buff *skb; unsigned long cpu_flags; /* @@ -278,7 +281,7 @@ struct sk_buff *__skb_try_recv_datagram(struct sock *sk, unsigned int flags, break; sk_busy_loop(sk, flags & MSG_DONTWAIT); - } while (READ_ONCE(sk->sk_receive_queue.prev) != *last); + } while (READ_ONCE(queue->prev) != *last); error = -EAGAIN; @@ -288,7 +291,9 @@ no_packet: } EXPORT_SYMBOL(__skb_try_recv_datagram); -struct sk_buff *__skb_recv_datagram(struct sock *sk, unsigned int flags, +struct sk_buff *__skb_recv_datagram(struct sock *sk, + struct sk_buff_head *sk_queue, + unsigned int flags, void (*destructor)(struct sock *sk, struct sk_buff *skb), int *off, int *err) @@ -299,15 +304,16 @@ struct sk_buff *__skb_recv_datagram(struct sock *sk, unsigned int flags, timeo = sock_rcvtimeo(sk, flags & MSG_DONTWAIT); do { - skb = __skb_try_recv_datagram(sk, flags, destructor, off, err, - &last); + skb = __skb_try_recv_datagram(sk, sk_queue, flags, destructor, + off, err, &last); if (skb) return skb; if (*err != -EAGAIN) break; } while (timeo && - !__skb_wait_for_more_packets(sk, err, &timeo, last)); + !__skb_wait_for_more_packets(sk, sk_queue, err, + &timeo, last)); return NULL; } @@ -318,7 +324,8 @@ struct sk_buff *skb_recv_datagram(struct sock *sk, unsigned int flags, { int off = 0; - return __skb_recv_datagram(sk, flags | (noblock ? MSG_DONTWAIT : 0), + return __skb_recv_datagram(sk, &sk->sk_receive_queue, + flags | (noblock ? MSG_DONTWAIT : 0), NULL, &off, err); } EXPORT_SYMBOL(skb_recv_datagram); diff --git a/net/core/dev.c b/net/core/dev.c index 3d3ea1c30cf0..17529d49faec 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -1764,7 +1764,6 @@ EXPORT_SYMBOL(register_netdevice_notifier); int unregister_netdevice_notifier(struct notifier_block *nb) { - struct net_device *dev; struct net *net; int err; @@ -1775,16 +1774,9 @@ int unregister_netdevice_notifier(struct notifier_block *nb) if (err) goto unlock; - for_each_net(net) { - for_each_netdev(net, dev) { - if (dev->flags & IFF_UP) { - call_netdevice_notifier(nb, NETDEV_GOING_DOWN, - dev); - call_netdevice_notifier(nb, NETDEV_DOWN, dev); - } - call_netdevice_notifier(nb, NETDEV_UNREGISTER, dev); - } - } + for_each_net(net) + call_netdevice_unregister_net_notifiers(nb, net); + unlock: rtnl_unlock(); up_write(&pernet_ops_rwsem); @@ -1792,6 +1784,42 @@ unlock: } EXPORT_SYMBOL(unregister_netdevice_notifier); +static int __register_netdevice_notifier_net(struct net *net, + struct notifier_block *nb, + bool ignore_call_fail) +{ + int err; + + err = raw_notifier_chain_register(&net->netdev_chain, nb); + if (err) + return err; + if (dev_boot_phase) + return 0; + + err = call_netdevice_register_net_notifiers(nb, net); + if (err && !ignore_call_fail) + goto chain_unregister; + + return 0; + +chain_unregister: + raw_notifier_chain_unregister(&net->netdev_chain, nb); + return err; +} + +static int __unregister_netdevice_notifier_net(struct net *net, + struct notifier_block *nb) +{ + int err; + + err = raw_notifier_chain_unregister(&net->netdev_chain, nb); + if (err) + return err; + + call_netdevice_unregister_net_notifiers(nb, net); + return 0; +} + /** * register_netdevice_notifier_net - register a per-netns network notifier block * @net: network namespace @@ -1812,23 +1840,9 @@ int register_netdevice_notifier_net(struct net *net, struct notifier_block *nb) int err; rtnl_lock(); - err = raw_notifier_chain_register(&net->netdev_chain, nb); - if (err) - goto unlock; - if (dev_boot_phase) - goto unlock; - - err = call_netdevice_register_net_notifiers(nb, net); - if (err) - goto chain_unregister; - -unlock: + err = __register_netdevice_notifier_net(net, nb, false); rtnl_unlock(); return err; - -chain_unregister: - raw_notifier_chain_unregister(&netdev_chain, nb); - goto unlock; } EXPORT_SYMBOL(register_netdevice_notifier_net); @@ -1854,17 +1868,53 @@ int unregister_netdevice_notifier_net(struct net *net, int err; rtnl_lock(); - err = raw_notifier_chain_unregister(&net->netdev_chain, nb); - if (err) - goto unlock; + err = __unregister_netdevice_notifier_net(net, nb); + rtnl_unlock(); + return err; +} +EXPORT_SYMBOL(unregister_netdevice_notifier_net); - call_netdevice_unregister_net_notifiers(nb, net); +int register_netdevice_notifier_dev_net(struct net_device *dev, + struct notifier_block *nb, + struct netdev_net_notifier *nn) +{ + int err; -unlock: + rtnl_lock(); + err = __register_netdevice_notifier_net(dev_net(dev), nb, false); + if (!err) { + nn->nb = nb; + list_add(&nn->list, &dev->net_notifier_list); + } rtnl_unlock(); return err; } -EXPORT_SYMBOL(unregister_netdevice_notifier_net); +EXPORT_SYMBOL(register_netdevice_notifier_dev_net); + +int unregister_netdevice_notifier_dev_net(struct net_device *dev, + struct notifier_block *nb, + struct netdev_net_notifier *nn) +{ + int err; + + rtnl_lock(); + list_del(&nn->list); + err = __unregister_netdevice_notifier_net(dev_net(dev), nb); + rtnl_unlock(); + return err; +} +EXPORT_SYMBOL(unregister_netdevice_notifier_dev_net); + +static void move_netdevice_notifiers_dev_net(struct net_device *dev, + struct net *net) +{ + struct netdev_net_notifier *nn; + + list_for_each_entry(nn, &dev->net_notifier_list, list) { + __unregister_netdevice_notifier_net(dev_net(dev), nn->nb); + __register_netdevice_notifier_net(net, nn->nb, true); + } +} /** * call_netdevice_notifiers_info - call all network notifier blocks @@ -3249,7 +3299,7 @@ struct sk_buff *__skb_gso_segment(struct sk_buff *skb, segs = skb_mac_gso_segment(skb, features); - if (unlikely(skb_needs_check(skb, tx_path) && !IS_ERR(segs))) + if (segs != skb && unlikely(skb_needs_check(skb, tx_path) && !IS_ERR(segs))) skb_warn_bad_offload(skb); return segs; @@ -4932,7 +4982,6 @@ static bool skb_pfmemalloc_protocol(struct sk_buff *skb) static inline int nf_ingress(struct sk_buff *skb, struct packet_type **pt_prev, int *ret, struct net_device *orig_dev) { -#ifdef CONFIG_NETFILTER_INGRESS if (nf_hook_ingress_active(skb)) { int ingress_retval; @@ -4946,7 +4995,6 @@ static inline int nf_ingress(struct sk_buff *skb, struct packet_type **pt_prev, rcu_read_unlock(); return ingress_retval; } -#endif /* CONFIG_NETFILTER_INGRESS */ return 0; } @@ -8553,7 +8601,17 @@ static int dev_xdp_install(struct net_device *dev, bpf_op_t bpf_op, struct netlink_ext_ack *extack, u32 flags, struct bpf_prog *prog) { + bool non_hw = !(flags & XDP_FLAGS_HW_MODE); + struct bpf_prog *prev_prog = NULL; struct netdev_bpf xdp; + int err; + + if (non_hw) { + prev_prog = bpf_prog_by_id(__dev_xdp_query(dev, bpf_op, + XDP_QUERY_PROG)); + if (IS_ERR(prev_prog)) + prev_prog = NULL; + } memset(&xdp, 0, sizeof(xdp)); if (flags & XDP_FLAGS_HW_MODE) @@ -8564,7 +8622,14 @@ static int dev_xdp_install(struct net_device *dev, bpf_op_t bpf_op, xdp.flags = flags; xdp.prog = prog; - return bpf_op(dev, &xdp); + err = bpf_op(dev, &xdp); + if (!err && non_hw) + bpf_prog_change_xdp(prev_prog, prog); + + if (prev_prog) + bpf_prog_put(prev_prog); + + return err; } static void dev_xdp_uninstall(struct net_device *dev) @@ -9268,7 +9333,7 @@ int register_netdevice(struct net_device *dev) /* Transfer changeable features to wanted_features and enable * software offloads (GSO and GRO). */ - dev->hw_features |= NETIF_F_SOFT_FEATURES; + dev->hw_features |= (NETIF_F_SOFT_FEATURES | NETIF_F_SOFT_FEATURES_OFF); dev->features |= NETIF_F_SOFT_FEATURES; if (dev->netdev_ops->ndo_udp_tunnel_add) { @@ -9763,6 +9828,7 @@ struct net_device *alloc_netdev_mqs(int sizeof_priv, const char *name, INIT_LIST_HEAD(&dev->adj_list.lower); INIT_LIST_HEAD(&dev->ptype_all); INIT_LIST_HEAD(&dev->ptype_specific); + INIT_LIST_HEAD(&dev->net_notifier_list); #ifdef CONFIG_NET_SCHED hash_init(dev->qdisc_hash); #endif @@ -9833,6 +9899,8 @@ void free_netdev(struct net_device *dev) free_percpu(dev->pcpu_refcnt); dev->pcpu_refcnt = NULL; + free_percpu(dev->xdp_bulkq); + dev->xdp_bulkq = NULL; netdev_unregister_lockdep_key(dev); @@ -10024,6 +10092,9 @@ int dev_change_net_namespace(struct net_device *dev, struct net *net, const char kobject_uevent(&dev->dev.kobj, KOBJ_REMOVE); netdev_adjacent_del_links(dev); + /* Move per-net netdevice notifiers that are following the netdevice */ + move_netdevice_notifiers_dev_net(dev, net); + /* Actually switch the network namespace */ dev_net_set(dev, net); dev->ifindex = new_ifindex; diff --git a/net/core/dev_ioctl.c b/net/core/dev_ioctl.c index 5163d900bb4f..dbaebbe573f0 100644 --- a/net/core/dev_ioctl.c +++ b/net/core/dev_ioctl.c @@ -187,6 +187,7 @@ static int net_hwtstamp_validate(struct ifreq *ifr) case HWTSTAMP_TX_OFF: case HWTSTAMP_TX_ON: case HWTSTAMP_TX_ONESTEP_SYNC: + case HWTSTAMP_TX_ONESTEP_P2P: tx_type_valid = 1; break; } diff --git a/net/core/devlink.c b/net/core/devlink.c index f76219bf0c21..ca1df0ec3c97 100644 --- a/net/core/devlink.c +++ b/net/core/devlink.c @@ -4843,22 +4843,100 @@ devlink_health_reporter_destroy(struct devlink_health_reporter *reporter) } EXPORT_SYMBOL_GPL(devlink_health_reporter_destroy); -void -devlink_health_reporter_state_update(struct devlink_health_reporter *reporter, - enum devlink_health_reporter_state state) +static int +devlink_nl_health_reporter_fill(struct sk_buff *msg, + struct devlink *devlink, + struct devlink_health_reporter *reporter, + enum devlink_command cmd, u32 portid, + u32 seq, int flags) { - if (WARN_ON(state != DEVLINK_HEALTH_REPORTER_STATE_HEALTHY && - state != DEVLINK_HEALTH_REPORTER_STATE_ERROR)) + struct nlattr *reporter_attr; + void *hdr; + + hdr = genlmsg_put(msg, portid, seq, &devlink_nl_family, flags, cmd); + if (!hdr) + return -EMSGSIZE; + + if (devlink_nl_put_handle(msg, devlink)) + goto genlmsg_cancel; + + reporter_attr = nla_nest_start_noflag(msg, + DEVLINK_ATTR_HEALTH_REPORTER); + if (!reporter_attr) + goto genlmsg_cancel; + if (nla_put_string(msg, DEVLINK_ATTR_HEALTH_REPORTER_NAME, + reporter->ops->name)) + goto reporter_nest_cancel; + if (nla_put_u8(msg, DEVLINK_ATTR_HEALTH_REPORTER_STATE, + reporter->health_state)) + goto reporter_nest_cancel; + if (nla_put_u64_64bit(msg, DEVLINK_ATTR_HEALTH_REPORTER_ERR_COUNT, + reporter->error_count, DEVLINK_ATTR_PAD)) + goto reporter_nest_cancel; + if (nla_put_u64_64bit(msg, DEVLINK_ATTR_HEALTH_REPORTER_RECOVER_COUNT, + reporter->recovery_count, DEVLINK_ATTR_PAD)) + goto reporter_nest_cancel; + if (reporter->ops->recover && + nla_put_u64_64bit(msg, DEVLINK_ATTR_HEALTH_REPORTER_GRACEFUL_PERIOD, + reporter->graceful_period, + DEVLINK_ATTR_PAD)) + goto reporter_nest_cancel; + if (reporter->ops->recover && + nla_put_u8(msg, DEVLINK_ATTR_HEALTH_REPORTER_AUTO_RECOVER, + reporter->auto_recover)) + goto reporter_nest_cancel; + if (reporter->dump_fmsg && + nla_put_u64_64bit(msg, DEVLINK_ATTR_HEALTH_REPORTER_DUMP_TS, + jiffies_to_msecs(reporter->dump_ts), + DEVLINK_ATTR_PAD)) + goto reporter_nest_cancel; + if (reporter->dump_fmsg && + nla_put_u64_64bit(msg, DEVLINK_ATTR_HEALTH_REPORTER_DUMP_TS_NS, + reporter->dump_real_ts, DEVLINK_ATTR_PAD)) + goto reporter_nest_cancel; + + nla_nest_end(msg, reporter_attr); + genlmsg_end(msg, hdr); + return 0; + +reporter_nest_cancel: + nla_nest_end(msg, reporter_attr); +genlmsg_cancel: + genlmsg_cancel(msg, hdr); + return -EMSGSIZE; +} + +static void devlink_recover_notify(struct devlink_health_reporter *reporter, + enum devlink_command cmd) +{ + struct sk_buff *msg; + int err; + + WARN_ON(cmd != DEVLINK_CMD_HEALTH_REPORTER_RECOVER); + + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (!msg) return; - if (reporter->health_state == state) + err = devlink_nl_health_reporter_fill(msg, reporter->devlink, + reporter, cmd, 0, 0, 0); + if (err) { + nlmsg_free(msg); return; + } - reporter->health_state = state; - trace_devlink_health_reporter_state_update(reporter->devlink, - reporter->ops->name, state); + genlmsg_multicast_netns(&devlink_nl_family, + devlink_net(reporter->devlink), + msg, 0, DEVLINK_MCGRP_CONFIG, GFP_KERNEL); } -EXPORT_SYMBOL_GPL(devlink_health_reporter_state_update); + +void +devlink_health_reporter_recovery_done(struct devlink_health_reporter *reporter) +{ + reporter->recovery_count++; + reporter->last_recovery_ts = jiffies; +} +EXPORT_SYMBOL_GPL(devlink_health_reporter_recovery_done); static int devlink_health_reporter_recover(struct devlink_health_reporter *reporter, @@ -4876,9 +4954,9 @@ devlink_health_reporter_recover(struct devlink_health_reporter *reporter, if (err) return err; - reporter->recovery_count++; + devlink_health_reporter_recovery_done(reporter); reporter->health_state = DEVLINK_HEALTH_REPORTER_STATE_HEALTHY; - reporter->last_recovery_ts = jiffies; + devlink_recover_notify(reporter, DEVLINK_CMD_HEALTH_REPORTER_RECOVER); return 0; } @@ -4945,6 +5023,7 @@ int devlink_health_report(struct devlink_health_reporter *reporter, reporter->error_count++; prev_health_state = reporter->health_state; reporter->health_state = DEVLINK_HEALTH_REPORTER_STATE_ERROR; + devlink_recover_notify(reporter, DEVLINK_CMD_HEALTH_REPORTER_RECOVER); /* abort if the previous error wasn't recovered */ if (reporter->auto_recover && @@ -5027,68 +5106,23 @@ devlink_health_reporter_put(struct devlink_health_reporter *reporter) refcount_dec(&reporter->refcount); } -static int -devlink_nl_health_reporter_fill(struct sk_buff *msg, - struct devlink *devlink, - struct devlink_health_reporter *reporter, - enum devlink_command cmd, u32 portid, - u32 seq, int flags) +void +devlink_health_reporter_state_update(struct devlink_health_reporter *reporter, + enum devlink_health_reporter_state state) { - struct nlattr *reporter_attr; - void *hdr; - - hdr = genlmsg_put(msg, portid, seq, &devlink_nl_family, flags, cmd); - if (!hdr) - return -EMSGSIZE; - - if (devlink_nl_put_handle(msg, devlink)) - goto genlmsg_cancel; - - reporter_attr = nla_nest_start_noflag(msg, - DEVLINK_ATTR_HEALTH_REPORTER); - if (!reporter_attr) - goto genlmsg_cancel; - if (nla_put_string(msg, DEVLINK_ATTR_HEALTH_REPORTER_NAME, - reporter->ops->name)) - goto reporter_nest_cancel; - if (nla_put_u8(msg, DEVLINK_ATTR_HEALTH_REPORTER_STATE, - reporter->health_state)) - goto reporter_nest_cancel; - if (nla_put_u64_64bit(msg, DEVLINK_ATTR_HEALTH_REPORTER_ERR_COUNT, - reporter->error_count, DEVLINK_ATTR_PAD)) - goto reporter_nest_cancel; - if (nla_put_u64_64bit(msg, DEVLINK_ATTR_HEALTH_REPORTER_RECOVER_COUNT, - reporter->recovery_count, DEVLINK_ATTR_PAD)) - goto reporter_nest_cancel; - if (reporter->ops->recover && - nla_put_u64_64bit(msg, DEVLINK_ATTR_HEALTH_REPORTER_GRACEFUL_PERIOD, - reporter->graceful_period, - DEVLINK_ATTR_PAD)) - goto reporter_nest_cancel; - if (reporter->ops->recover && - nla_put_u8(msg, DEVLINK_ATTR_HEALTH_REPORTER_AUTO_RECOVER, - reporter->auto_recover)) - goto reporter_nest_cancel; - if (reporter->dump_fmsg && - nla_put_u64_64bit(msg, DEVLINK_ATTR_HEALTH_REPORTER_DUMP_TS, - jiffies_to_msecs(reporter->dump_ts), - DEVLINK_ATTR_PAD)) - goto reporter_nest_cancel; - if (reporter->dump_fmsg && - nla_put_u64_64bit(msg, DEVLINK_ATTR_HEALTH_REPORTER_DUMP_TS_NS, - reporter->dump_real_ts, DEVLINK_ATTR_PAD)) - goto reporter_nest_cancel; + if (WARN_ON(state != DEVLINK_HEALTH_REPORTER_STATE_HEALTHY && + state != DEVLINK_HEALTH_REPORTER_STATE_ERROR)) + return; - nla_nest_end(msg, reporter_attr); - genlmsg_end(msg, hdr); - return 0; + if (reporter->health_state == state) + return; -reporter_nest_cancel: - nla_nest_end(msg, reporter_attr); -genlmsg_cancel: - genlmsg_cancel(msg, hdr); - return -EMSGSIZE; + reporter->health_state = state; + trace_devlink_health_reporter_state_update(reporter->devlink, + reporter->ops->name, state); + devlink_recover_notify(reporter, DEVLINK_CMD_HEALTH_REPORTER_RECOVER); } +EXPORT_SYMBOL_GPL(devlink_health_reporter_state_update); static int devlink_nl_cmd_health_reporter_get_doit(struct sk_buff *skb, struct genl_info *info) @@ -7674,6 +7708,9 @@ static const struct devlink_trap devlink_trap_generic[] = { DEVLINK_TRAP(REJECT_ROUTE, EXCEPTION), DEVLINK_TRAP(IPV4_LPM_UNICAST_MISS, EXCEPTION), DEVLINK_TRAP(IPV6_LPM_UNICAST_MISS, EXCEPTION), + DEVLINK_TRAP(NON_ROUTABLE, DROP), + DEVLINK_TRAP(DECAP_ERROR, EXCEPTION), + DEVLINK_TRAP(OVERLAY_SMAC_MC, DROP), }; #define DEVLINK_TRAP_GROUP(_id) \ @@ -7686,6 +7723,7 @@ static const struct devlink_trap_group devlink_trap_group_generic[] = { DEVLINK_TRAP_GROUP(L2_DROPS), DEVLINK_TRAP_GROUP(L3_DROPS), DEVLINK_TRAP_GROUP(BUFFER_DROPS), + DEVLINK_TRAP_GROUP(TUNNEL_DROPS), }; static int devlink_trap_generic_verify(const struct devlink_trap *trap) diff --git a/net/core/filter.c b/net/core/filter.c index 538f6a735a19..792e3744b915 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -3459,119 +3459,30 @@ static const struct bpf_func_proto bpf_xdp_adjust_meta_proto = { .arg2_type = ARG_ANYTHING, }; -static int __bpf_tx_xdp(struct net_device *dev, - struct bpf_map *map, - struct xdp_buff *xdp, - u32 index) -{ - struct xdp_frame *xdpf; - int err, sent; - - if (!dev->netdev_ops->ndo_xdp_xmit) { - return -EOPNOTSUPP; - } - - err = xdp_ok_fwd_dev(dev, xdp->data_end - xdp->data); - if (unlikely(err)) - return err; - - xdpf = convert_to_xdp_frame(xdp); - if (unlikely(!xdpf)) - return -EOVERFLOW; - - sent = dev->netdev_ops->ndo_xdp_xmit(dev, 1, &xdpf, XDP_XMIT_FLUSH); - if (sent <= 0) - return sent; - return 0; -} - -static noinline int -xdp_do_redirect_slow(struct net_device *dev, struct xdp_buff *xdp, - struct bpf_prog *xdp_prog, struct bpf_redirect_info *ri) -{ - struct net_device *fwd; - u32 index = ri->tgt_index; - int err; - - fwd = dev_get_by_index_rcu(dev_net(dev), index); - ri->tgt_index = 0; - if (unlikely(!fwd)) { - err = -EINVAL; - goto err; - } - - err = __bpf_tx_xdp(fwd, NULL, xdp, 0); - if (unlikely(err)) - goto err; - - _trace_xdp_redirect(dev, xdp_prog, index); - return 0; -err: - _trace_xdp_redirect_err(dev, xdp_prog, index, err); - return err; -} - static int __bpf_tx_xdp_map(struct net_device *dev_rx, void *fwd, - struct bpf_map *map, - struct xdp_buff *xdp, - u32 index) + struct bpf_map *map, struct xdp_buff *xdp) { - int err; - switch (map->map_type) { case BPF_MAP_TYPE_DEVMAP: - case BPF_MAP_TYPE_DEVMAP_HASH: { - struct bpf_dtab_netdev *dst = fwd; - - err = dev_map_enqueue(dst, xdp, dev_rx); - if (unlikely(err)) - return err; - break; - } - case BPF_MAP_TYPE_CPUMAP: { - struct bpf_cpu_map_entry *rcpu = fwd; - - err = cpu_map_enqueue(rcpu, xdp, dev_rx); - if (unlikely(err)) - return err; - break; - } - case BPF_MAP_TYPE_XSKMAP: { - struct xdp_sock *xs = fwd; - - err = __xsk_map_redirect(map, xdp, xs); - return err; - } + case BPF_MAP_TYPE_DEVMAP_HASH: + return dev_map_enqueue(fwd, xdp, dev_rx); + case BPF_MAP_TYPE_CPUMAP: + return cpu_map_enqueue(fwd, xdp, dev_rx); + case BPF_MAP_TYPE_XSKMAP: + return __xsk_map_redirect(fwd, xdp); default: - break; + return -EBADRQC; } return 0; } -void xdp_do_flush_map(void) +void xdp_do_flush(void) { - struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info); - struct bpf_map *map = ri->map_to_flush; - - ri->map_to_flush = NULL; - if (map) { - switch (map->map_type) { - case BPF_MAP_TYPE_DEVMAP: - case BPF_MAP_TYPE_DEVMAP_HASH: - __dev_map_flush(map); - break; - case BPF_MAP_TYPE_CPUMAP: - __cpu_map_flush(map); - break; - case BPF_MAP_TYPE_XSKMAP: - __xsk_map_flush(map); - break; - default: - break; - } - } + __dev_flush(); + __cpu_map_flush(); + __xsk_map_flush(); } -EXPORT_SYMBOL_GPL(xdp_do_flush_map); +EXPORT_SYMBOL_GPL(xdp_do_flush); static inline void *__xdp_map_lookup_elem(struct bpf_map *map, u32 index) { @@ -3606,10 +3517,11 @@ void bpf_clear_redirect_map(struct bpf_map *map) } } -static int xdp_do_redirect_map(struct net_device *dev, struct xdp_buff *xdp, - struct bpf_prog *xdp_prog, struct bpf_map *map, - struct bpf_redirect_info *ri) +int xdp_do_redirect(struct net_device *dev, struct xdp_buff *xdp, + struct bpf_prog *xdp_prog) { + struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info); + struct bpf_map *map = READ_ONCE(ri->map); u32 index = ri->tgt_index; void *fwd = ri->tgt_value; int err; @@ -3618,32 +3530,27 @@ static int xdp_do_redirect_map(struct net_device *dev, struct xdp_buff *xdp, ri->tgt_value = NULL; WRITE_ONCE(ri->map, NULL); - if (ri->map_to_flush && unlikely(ri->map_to_flush != map)) - xdp_do_flush_map(); + if (unlikely(!map)) { + fwd = dev_get_by_index_rcu(dev_net(dev), index); + if (unlikely(!fwd)) { + err = -EINVAL; + goto err; + } + + err = dev_xdp_enqueue(fwd, xdp, dev); + } else { + err = __bpf_tx_xdp_map(dev, fwd, map, xdp); + } - err = __bpf_tx_xdp_map(dev, fwd, map, xdp, index); if (unlikely(err)) goto err; - ri->map_to_flush = map; _trace_xdp_redirect_map(dev, xdp_prog, fwd, map, index); return 0; err: _trace_xdp_redirect_map_err(dev, xdp_prog, fwd, map, index, err); return err; } - -int xdp_do_redirect(struct net_device *dev, struct xdp_buff *xdp, - struct bpf_prog *xdp_prog) -{ - struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info); - struct bpf_map *map = READ_ONCE(ri->map); - - if (likely(map)) - return xdp_do_redirect_map(dev, xdp, xdp_prog, map, ri); - - return xdp_do_redirect_slow(dev, xdp, xdp_prog, ri); -} EXPORT_SYMBOL_GPL(xdp_do_redirect); static int xdp_do_generic_redirect_map(struct net_device *dev, @@ -5976,7 +5883,7 @@ bool bpf_helper_changes_pkt_data(void *func) return false; } -static const struct bpf_func_proto * +const struct bpf_func_proto * bpf_base_func_proto(enum bpf_func_id func_id) { switch (func_id) { @@ -6016,6 +5923,8 @@ bpf_base_func_proto(enum bpf_func_id func_id) return &bpf_spin_unlock_proto; case BPF_FUNC_trace_printk: return bpf_get_trace_printk_proto(); + case BPF_FUNC_jiffies64: + return &bpf_jiffies64_proto; default: return NULL; } @@ -7648,21 +7557,21 @@ u32 bpf_sock_convert_ctx_access(enum bpf_access_type type, break; case offsetof(struct bpf_sock, type): - BUILD_BUG_ON(HWEIGHT32(SK_FL_TYPE_MASK) != BITS_PER_BYTE * 2); - *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->src_reg, - offsetof(struct sock, __sk_flags_offset)); - *insn++ = BPF_ALU32_IMM(BPF_AND, si->dst_reg, SK_FL_TYPE_MASK); - *insn++ = BPF_ALU32_IMM(BPF_RSH, si->dst_reg, SK_FL_TYPE_SHIFT); - *target_size = 2; + *insn++ = BPF_LDX_MEM( + BPF_FIELD_SIZEOF(struct sock, sk_type), + si->dst_reg, si->src_reg, + bpf_target_off(struct sock, sk_type, + sizeof_field(struct sock, sk_type), + target_size)); break; case offsetof(struct bpf_sock, protocol): - BUILD_BUG_ON(HWEIGHT32(SK_FL_PROTO_MASK) != BITS_PER_BYTE); - *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->src_reg, - offsetof(struct sock, __sk_flags_offset)); - *insn++ = BPF_ALU32_IMM(BPF_AND, si->dst_reg, SK_FL_PROTO_MASK); - *insn++ = BPF_ALU32_IMM(BPF_RSH, si->dst_reg, SK_FL_PROTO_SHIFT); - *target_size = 1; + *insn++ = BPF_LDX_MEM( + BPF_FIELD_SIZEOF(struct sock, sk_protocol), + si->dst_reg, si->src_reg, + bpf_target_off(struct sock, sk_protocol, + sizeof_field(struct sock, sk_protocol), + target_size)); break; case offsetof(struct bpf_sock, src_ip4): @@ -7944,20 +7853,13 @@ static u32 sock_addr_convert_ctx_access(enum bpf_access_type type, break; case offsetof(struct bpf_sock_addr, type): - SOCK_ADDR_LOAD_NESTED_FIELD_SIZE_OFF( - struct bpf_sock_addr_kern, struct sock, sk, - __sk_flags_offset, BPF_W, 0); - *insn++ = BPF_ALU32_IMM(BPF_AND, si->dst_reg, SK_FL_TYPE_MASK); - *insn++ = BPF_ALU32_IMM(BPF_RSH, si->dst_reg, SK_FL_TYPE_SHIFT); + SOCK_ADDR_LOAD_NESTED_FIELD(struct bpf_sock_addr_kern, + struct sock, sk, sk_type); break; case offsetof(struct bpf_sock_addr, protocol): - SOCK_ADDR_LOAD_NESTED_FIELD_SIZE_OFF( - struct bpf_sock_addr_kern, struct sock, sk, - __sk_flags_offset, BPF_W, 0); - *insn++ = BPF_ALU32_IMM(BPF_AND, si->dst_reg, SK_FL_PROTO_MASK); - *insn++ = BPF_ALU32_IMM(BPF_RSH, si->dst_reg, - SK_FL_PROTO_SHIFT); + SOCK_ADDR_LOAD_NESTED_FIELD(struct bpf_sock_addr_kern, + struct sock, sk, sk_protocol); break; case offsetof(struct bpf_sock_addr, msg_src_ip4): @@ -8876,11 +8778,11 @@ sk_reuseport_is_valid_access(int off, int size, skb, \ SKB_FIELD) -#define SK_REUSEPORT_LOAD_SK_FIELD_SIZE_OFF(SK_FIELD, BPF_SIZE, EXTRA_OFF) \ - SOCK_ADDR_LOAD_NESTED_FIELD_SIZE_OFF(struct sk_reuseport_kern, \ - struct sock, \ - sk, \ - SK_FIELD, BPF_SIZE, EXTRA_OFF) +#define SK_REUSEPORT_LOAD_SK_FIELD(SK_FIELD) \ + SOCK_ADDR_LOAD_NESTED_FIELD(struct sk_reuseport_kern, \ + struct sock, \ + sk, \ + SK_FIELD) static u32 sk_reuseport_convert_ctx_access(enum bpf_access_type type, const struct bpf_insn *si, @@ -8904,16 +8806,7 @@ static u32 sk_reuseport_convert_ctx_access(enum bpf_access_type type, break; case offsetof(struct sk_reuseport_md, ip_protocol): - BUILD_BUG_ON(HWEIGHT32(SK_FL_PROTO_MASK) != BITS_PER_BYTE); - SK_REUSEPORT_LOAD_SK_FIELD_SIZE_OFF(__sk_flags_offset, - BPF_W, 0); - *insn++ = BPF_ALU32_IMM(BPF_AND, si->dst_reg, SK_FL_PROTO_MASK); - *insn++ = BPF_ALU32_IMM(BPF_RSH, si->dst_reg, - SK_FL_PROTO_SHIFT); - /* SK_FL_PROTO_MASK and SK_FL_PROTO_SHIFT are endian - * aware. No further narrowing or masking is needed. - */ - *target_size = 1; + SK_REUSEPORT_LOAD_SK_FIELD(sk_protocol); break; case offsetof(struct sk_reuseport_md, data_end): @@ -8941,3 +8834,11 @@ const struct bpf_verifier_ops sk_reuseport_verifier_ops = { const struct bpf_prog_ops sk_reuseport_prog_ops = { }; #endif /* CONFIG_INET */ + +DEFINE_BPF_DISPATCHER(bpf_dispatcher_xdp) + +void bpf_prog_change_xdp(struct bpf_prog *prev_prog, struct bpf_prog *prog) +{ + bpf_dispatcher_change_prog(BPF_DISPATCHER_PTR(bpf_dispatcher_xdp), + prev_prog, prog); +} diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c index 2dbbb030fbed..a1670dff0629 100644 --- a/net/core/flow_dissector.c +++ b/net/core/flow_dissector.c @@ -233,7 +233,7 @@ static bool icmp_has_id(u8 type) * @skb: sk_buff to extract from * @key_icmp: struct flow_dissector_key_icmp to fill * @data: raw buffer pointer to the packet - * @toff: offset to extract at + * @thoff: offset to extract at * @hlen: packet header length */ void skb_flow_get_icmp_tci(const struct sk_buff *skb, @@ -834,10 +834,10 @@ static void __skb_flow_bpf_to_target(const struct bpf_flow_keys *flow_keys, struct flow_dissector *flow_dissector, void *target_container) { + struct flow_dissector_key_ports *key_ports = NULL; struct flow_dissector_key_control *key_control; struct flow_dissector_key_basic *key_basic; struct flow_dissector_key_addrs *key_addrs; - struct flow_dissector_key_ports *key_ports; struct flow_dissector_key_tags *key_tags; key_control = skb_flow_dissector_target(flow_dissector, @@ -876,10 +876,17 @@ static void __skb_flow_bpf_to_target(const struct bpf_flow_keys *flow_keys, key_control->addr_type = FLOW_DISSECTOR_KEY_IPV6_ADDRS; } - if (dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_PORTS)) { + if (dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_PORTS)) key_ports = skb_flow_dissector_target(flow_dissector, FLOW_DISSECTOR_KEY_PORTS, target_container); + else if (dissector_uses_key(flow_dissector, + FLOW_DISSECTOR_KEY_PORTS_RANGE)) + key_ports = skb_flow_dissector_target(flow_dissector, + FLOW_DISSECTOR_KEY_PORTS_RANGE, + target_container); + + if (key_ports) { key_ports->src = flow_keys->sport; key_ports->dst = flow_keys->dport; } diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c index 39402840025e..757cc1d084e7 100644 --- a/net/core/net_namespace.c +++ b/net/core/net_namespace.c @@ -211,16 +211,10 @@ static int net_eq_idr(int id, void *net, void *peer) return 0; } -/* Should be called with nsid_lock held. If a new id is assigned, the bool alloc - * is set to true, thus the caller knows that the new id must be notified via - * rtnl. - */ -static int __peernet2id_alloc(struct net *net, struct net *peer, bool *alloc) +/* Must be called from RCU-critical section or with nsid_lock held */ +static int __peernet2id(const struct net *net, struct net *peer) { int id = idr_for_each(&net->netns_ids, net_eq_idr, peer); - bool alloc_it = *alloc; - - *alloc = false; /* Magic value for id 0. */ if (id == NET_ID_ZERO) @@ -228,23 +222,9 @@ static int __peernet2id_alloc(struct net *net, struct net *peer, bool *alloc) if (id > 0) return id; - if (alloc_it) { - id = alloc_netid(net, peer, -1); - *alloc = true; - return id >= 0 ? id : NETNSA_NSID_NOT_ASSIGNED; - } - return NETNSA_NSID_NOT_ASSIGNED; } -/* should be called with nsid_lock held */ -static int __peernet2id(struct net *net, struct net *peer) -{ - bool no = false; - - return __peernet2id_alloc(net, peer, &no); -} - static void rtnl_net_notifyid(struct net *net, int cmd, int id, u32 portid, struct nlmsghdr *nlh, gfp_t gfp); /* This function returns the id of a peer netns. If no id is assigned, one will @@ -252,38 +232,50 @@ static void rtnl_net_notifyid(struct net *net, int cmd, int id, u32 portid, */ int peernet2id_alloc(struct net *net, struct net *peer, gfp_t gfp) { - bool alloc = false, alive = false; int id; if (refcount_read(&net->count) == 0) return NETNSA_NSID_NOT_ASSIGNED; - spin_lock_bh(&net->nsid_lock); - /* - * When peer is obtained from RCU lists, we may race with + + spin_lock(&net->nsid_lock); + id = __peernet2id(net, peer); + if (id >= 0) { + spin_unlock(&net->nsid_lock); + return id; + } + + /* When peer is obtained from RCU lists, we may race with * its cleanup. Check whether it's alive, and this guarantees * we never hash a peer back to net->netns_ids, after it has * just been idr_remove()'d from there in cleanup_net(). */ - if (maybe_get_net(peer)) - alive = alloc = true; - id = __peernet2id_alloc(net, peer, &alloc); - spin_unlock_bh(&net->nsid_lock); - if (alloc && id >= 0) - rtnl_net_notifyid(net, RTM_NEWNSID, id, 0, NULL, gfp); - if (alive) - put_net(peer); + if (!maybe_get_net(peer)) { + spin_unlock(&net->nsid_lock); + return NETNSA_NSID_NOT_ASSIGNED; + } + + id = alloc_netid(net, peer, -1); + spin_unlock(&net->nsid_lock); + + put_net(peer); + if (id < 0) + return NETNSA_NSID_NOT_ASSIGNED; + + rtnl_net_notifyid(net, RTM_NEWNSID, id, 0, NULL, gfp); + return id; } EXPORT_SYMBOL_GPL(peernet2id_alloc); /* This function returns, if assigned, the id of a peer netns. */ -int peernet2id(struct net *net, struct net *peer) +int peernet2id(const struct net *net, struct net *peer) { int id; - spin_lock_bh(&net->nsid_lock); + rcu_read_lock(); id = __peernet2id(net, peer); - spin_unlock_bh(&net->nsid_lock); + rcu_read_unlock(); + return id; } EXPORT_SYMBOL(peernet2id); @@ -291,12 +283,12 @@ EXPORT_SYMBOL(peernet2id); /* This function returns true is the peer netns has an id assigned into the * current netns. */ -bool peernet_has_id(struct net *net, struct net *peer) +bool peernet_has_id(const struct net *net, struct net *peer) { return peernet2id(net, peer) >= 0; } -struct net *get_net_ns_by_id(struct net *net, int id) +struct net *get_net_ns_by_id(const struct net *net, int id) { struct net *peer; @@ -528,20 +520,20 @@ static void unhash_nsid(struct net *net, struct net *last) for_each_net(tmp) { int id; - spin_lock_bh(&tmp->nsid_lock); + spin_lock(&tmp->nsid_lock); id = __peernet2id(tmp, net); if (id >= 0) idr_remove(&tmp->netns_ids, id); - spin_unlock_bh(&tmp->nsid_lock); + spin_unlock(&tmp->nsid_lock); if (id >= 0) rtnl_net_notifyid(tmp, RTM_DELNSID, id, 0, NULL, GFP_KERNEL); if (tmp == last) break; } - spin_lock_bh(&net->nsid_lock); + spin_lock(&net->nsid_lock); idr_destroy(&net->netns_ids); - spin_unlock_bh(&net->nsid_lock); + spin_unlock(&net->nsid_lock); } static LLIST_HEAD(cleanup_list); @@ -754,9 +746,9 @@ static int rtnl_net_newid(struct sk_buff *skb, struct nlmsghdr *nlh, return PTR_ERR(peer); } - spin_lock_bh(&net->nsid_lock); + spin_lock(&net->nsid_lock); if (__peernet2id(net, peer) >= 0) { - spin_unlock_bh(&net->nsid_lock); + spin_unlock(&net->nsid_lock); err = -EEXIST; NL_SET_BAD_ATTR(extack, nla); NL_SET_ERR_MSG(extack, @@ -765,7 +757,7 @@ static int rtnl_net_newid(struct sk_buff *skb, struct nlmsghdr *nlh, } err = alloc_netid(net, peer, nsid); - spin_unlock_bh(&net->nsid_lock); + spin_unlock(&net->nsid_lock); if (err >= 0) { rtnl_net_notifyid(net, RTM_NEWNSID, err, NETLINK_CB(skb).portid, nlh, GFP_KERNEL); @@ -950,6 +942,7 @@ struct rtnl_net_dump_cb { int s_idx; }; +/* Runs in RCU-critical section. */ static int rtnl_net_dumpid_one(int id, void *peer, void *data) { struct rtnl_net_dump_cb *net_cb = (struct rtnl_net_dump_cb *)data; @@ -1034,19 +1027,9 @@ static int rtnl_net_dumpid(struct sk_buff *skb, struct netlink_callback *cb) goto end; } - spin_lock_bh(&net_cb.tgt_net->nsid_lock); - if (net_cb.fillargs.add_ref && - !net_eq(net_cb.ref_net, net_cb.tgt_net) && - !spin_trylock_bh(&net_cb.ref_net->nsid_lock)) { - spin_unlock_bh(&net_cb.tgt_net->nsid_lock); - err = -EAGAIN; - goto end; - } + rcu_read_lock(); idr_for_each(&net_cb.tgt_net->netns_ids, rtnl_net_dumpid_one, &net_cb); - if (net_cb.fillargs.add_ref && - !net_eq(net_cb.ref_net, net_cb.tgt_net)) - spin_unlock_bh(&net_cb.ref_net->nsid_lock); - spin_unlock_bh(&net_cb.tgt_net->nsid_lock); + rcu_read_unlock(); cb->args[0] = net_cb.idx; end: diff --git a/net/core/page_pool.c b/net/core/page_pool.c index a6aefe989043..9b7cbe35df37 100644 --- a/net/core/page_pool.c +++ b/net/core/page_pool.c @@ -96,10 +96,65 @@ struct page_pool *page_pool_create(const struct page_pool_params *params) } EXPORT_SYMBOL(page_pool_create); +static void __page_pool_return_page(struct page_pool *pool, struct page *page); + +noinline +static struct page *page_pool_refill_alloc_cache(struct page_pool *pool, + bool refill) +{ + struct ptr_ring *r = &pool->ring; + struct page *page; + int pref_nid; /* preferred NUMA node */ + + /* Quicker fallback, avoid locks when ring is empty */ + if (__ptr_ring_empty(r)) + return NULL; + + /* Softirq guarantee CPU and thus NUMA node is stable. This, + * assumes CPU refilling driver RX-ring will also run RX-NAPI. + */ +#ifdef CONFIG_NUMA + pref_nid = (pool->p.nid == NUMA_NO_NODE) ? numa_mem_id() : pool->p.nid; +#else + /* Ignore pool->p.nid setting if !CONFIG_NUMA, helps compiler */ + pref_nid = numa_mem_id(); /* will be zero like page_to_nid() */ +#endif + + /* Slower-path: Get pages from locked ring queue */ + spin_lock(&r->consumer_lock); + + /* Refill alloc array, but only if NUMA match */ + do { + page = __ptr_ring_consume(r); + if (unlikely(!page)) + break; + + if (likely(page_to_nid(page) == pref_nid)) { + pool->alloc.cache[pool->alloc.count++] = page; + } else { + /* NUMA mismatch; + * (1) release 1 page to page-allocator and + * (2) break out to fallthrough to alloc_pages_node. + * This limit stress on page buddy alloactor. + */ + __page_pool_return_page(pool, page); + page = NULL; + break; + } + } while (pool->alloc.count < PP_ALLOC_CACHE_REFILL && + refill); + + /* Return last page */ + if (likely(pool->alloc.count > 0)) + page = pool->alloc.cache[--pool->alloc.count]; + + spin_unlock(&r->consumer_lock); + return page; +} + /* fast path */ static struct page *__page_pool_get_cached(struct page_pool *pool) { - struct ptr_ring *r = &pool->ring; bool refill = false; struct page *page; @@ -113,20 +168,7 @@ static struct page *__page_pool_get_cached(struct page_pool *pool) refill = true; } - /* Quicker fallback, avoid locks when ring is empty */ - if (__ptr_ring_empty(r)) - return NULL; - - /* Slow-path: Get page from locked ring queue, - * refill alloc array if requested. - */ - spin_lock(&r->consumer_lock); - page = __ptr_ring_consume(r); - if (refill) - pool->alloc.count = __ptr_ring_consume_batched(r, - pool->alloc.cache, - PP_ALLOC_CACHE_REFILL); - spin_unlock(&r->consumer_lock); + page = page_pool_refill_alloc_cache(pool, refill); return page; } @@ -163,7 +205,11 @@ static struct page *__page_pool_alloc_pages_slow(struct page_pool *pool, */ /* Cache was empty, do real allocation */ +#ifdef CONFIG_NUMA page = alloc_pages_node(pool->p.nid, gfp, pool->p.order); +#else + page = alloc_pages(gfp, pool->p.order); +#endif if (!page) return NULL; @@ -311,13 +357,10 @@ static bool __page_pool_recycle_direct(struct page *page, /* page is NOT reusable when: * 1) allocated when system is under some pressure. (page_is_pfmemalloc) - * 2) belongs to a different NUMA node than pool->p.nid. - * - * To update pool->p.nid users must call page_pool_update_nid. */ static bool pool_page_reusable(struct page_pool *pool, struct page *page) { - return !page_is_pfmemalloc(page) && page_to_nid(page) == pool->p.nid; + return !page_is_pfmemalloc(page); } void __page_pool_put_page(struct page_pool *pool, struct page *page, @@ -484,7 +527,15 @@ EXPORT_SYMBOL(page_pool_destroy); /* Caller must provide appropriate safe context, e.g. NAPI. */ void page_pool_update_nid(struct page_pool *pool, int new_nid) { + struct page *page; + trace_page_pool_update_nid(pool, new_nid); pool->p.nid = new_nid; + + /* Flush pool alloc cache, as refill will check NUMA node */ + while (pool->alloc.count) { + page = pool->alloc.cache[--pool->alloc.count]; + __page_pool_return_page(pool, page); + } } EXPORT_SYMBOL(page_pool_update_nid); diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index d9001b5c48eb..cdad6ed532c4 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -1041,6 +1041,7 @@ static noinline size_t if_nlmsg_size(const struct net_device *dev, + nla_total_size(4) /* IFLA_MIN_MTU */ + nla_total_size(4) /* IFLA_MAX_MTU */ + rtnl_prop_list_size(dev) + + nla_total_size(MAX_ADDR_LEN) /* IFLA_PERM_ADDRESS */ + 0; } @@ -1757,6 +1758,9 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, nla_put_s32(skb, IFLA_NEW_IFINDEX, new_ifindex) < 0) goto nla_put_failure; + if (memchr_inv(dev->perm_addr, '\0', dev->addr_len) && + nla_put(skb, IFLA_PERM_ADDRESS, dev->addr_len, dev->perm_addr)) + goto nla_put_failure; rcu_read_lock(); if (rtnl_fill_link_af(skb, dev, ext_filter_mask)) @@ -1822,6 +1826,7 @@ static const struct nla_policy ifla_policy[IFLA_MAX+1] = { [IFLA_PROP_LIST] = { .type = NLA_NESTED }, [IFLA_ALT_IFNAME] = { .type = NLA_STRING, .len = ALTIFNAMSIZ - 1 }, + [IFLA_PERM_ADDRESS] = { .type = NLA_REJECT }, }; static const struct nla_policy ifla_info_policy[IFLA_INFO_MAX+1] = { diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 973a71f4bc89..864cb9e9622f 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -68,6 +68,7 @@ #include <net/ip6_checksum.h> #include <net/xfrm.h> #include <net/mpls.h> +#include <net/mptcp.h> #include <linux/uaccess.h> #include <trace/events/skb.h> @@ -3638,6 +3639,97 @@ static inline skb_frag_t skb_head_frag_to_page_desc(struct sk_buff *frag_skb) return head_frag; } +struct sk_buff *skb_segment_list(struct sk_buff *skb, + netdev_features_t features, + unsigned int offset) +{ + struct sk_buff *list_skb = skb_shinfo(skb)->frag_list; + unsigned int tnl_hlen = skb_tnl_header_len(skb); + unsigned int delta_truesize = 0; + unsigned int delta_len = 0; + struct sk_buff *tail = NULL; + struct sk_buff *nskb; + + skb_push(skb, -skb_network_offset(skb) + offset); + + skb_shinfo(skb)->frag_list = NULL; + + do { + nskb = list_skb; + list_skb = list_skb->next; + + if (!tail) + skb->next = nskb; + else + tail->next = nskb; + + tail = nskb; + + delta_len += nskb->len; + delta_truesize += nskb->truesize; + + skb_push(nskb, -skb_network_offset(nskb) + offset); + + __copy_skb_header(nskb, skb); + + skb_headers_offset_update(nskb, skb_headroom(nskb) - skb_headroom(skb)); + skb_copy_from_linear_data_offset(skb, -tnl_hlen, + nskb->data - tnl_hlen, + offset + tnl_hlen); + + if (skb_needs_linearize(nskb, features) && + __skb_linearize(nskb)) + goto err_linearize; + + } while (list_skb); + + skb->truesize = skb->truesize - delta_truesize; + skb->data_len = skb->data_len - delta_len; + skb->len = skb->len - delta_len; + + skb_gso_reset(skb); + + skb->prev = tail; + + if (skb_needs_linearize(skb, features) && + __skb_linearize(skb)) + goto err_linearize; + + skb_get(skb); + + return skb; + +err_linearize: + kfree_skb_list(skb->next); + skb->next = NULL; + return ERR_PTR(-ENOMEM); +} +EXPORT_SYMBOL_GPL(skb_segment_list); + +int skb_gro_receive_list(struct sk_buff *p, struct sk_buff *skb) +{ + if (unlikely(p->len + skb->len >= 65536)) + return -E2BIG; + + if (NAPI_GRO_CB(p)->last == p) + skb_shinfo(p)->frag_list = skb; + else + NAPI_GRO_CB(p)->last->next = skb; + + skb_pull(skb, skb_gro_offset(skb)); + + NAPI_GRO_CB(p)->last = skb; + NAPI_GRO_CB(p)->count++; + p->data_len += skb->len; + p->truesize += skb->truesize; + p->len += skb->len; + + NAPI_GRO_CB(skb)->same_flow = 1; + + return 0; +} +EXPORT_SYMBOL_GPL(skb_gro_receive_list); + /** * skb_segment - Perform protocol segmentation on skb. * @head_skb: buffer to segment @@ -4109,6 +4201,9 @@ static const u8 skb_ext_type_len[] = { #if IS_ENABLED(CONFIG_NET_TC_SKB_EXT) [TC_SKB_EXT] = SKB_EXT_CHUNKSIZEOF(struct tc_skb_ext), #endif +#if IS_ENABLED(CONFIG_MPTCP) + [SKB_EXT_MPTCP] = SKB_EXT_CHUNKSIZEOF(struct mptcp_ext), +#endif }; static __always_inline unsigned int skb_ext_total_length(void) @@ -4123,6 +4218,9 @@ static __always_inline unsigned int skb_ext_total_length(void) #if IS_ENABLED(CONFIG_NET_TC_SKB_EXT) skb_ext_type_len[TC_SKB_EXT] + #endif +#if IS_ENABLED(CONFIG_MPTCP) + skb_ext_type_len[SKB_EXT_MPTCP] + +#endif 0; } @@ -5472,12 +5570,15 @@ static void skb_mod_eth_type(struct sk_buff *skb, struct ethhdr *hdr, } /** - * skb_mpls_push() - push a new MPLS header after the mac header + * skb_mpls_push() - push a new MPLS header after mac_len bytes from start of + * the packet * * @skb: buffer * @mpls_lse: MPLS label stack entry to push * @mpls_proto: ethertype of the new MPLS header (expects 0x8847 or 0x8848) * @mac_len: length of the MAC header + * @ethernet: flag to indicate if the resulting packet after skb_mpls_push is + * ethernet * * Expects skb->data at mac header. * @@ -5501,7 +5602,7 @@ int skb_mpls_push(struct sk_buff *skb, __be32 mpls_lse, __be16 mpls_proto, return err; if (!skb->inner_protocol) { - skb_set_inner_network_header(skb, mac_len); + skb_set_inner_network_header(skb, skb_network_offset(skb)); skb_set_inner_protocol(skb, skb->protocol); } @@ -5510,6 +5611,7 @@ int skb_mpls_push(struct sk_buff *skb, __be32 mpls_lse, __be16 mpls_proto, mac_len); skb_reset_mac_header(skb); skb_set_network_header(skb, mac_len); + skb_reset_mac_len(skb); lse = mpls_hdr(skb); lse->label_stack_entry = mpls_lse; @@ -5529,7 +5631,7 @@ EXPORT_SYMBOL_GPL(skb_mpls_push); * @skb: buffer * @next_proto: ethertype of header after popped MPLS header * @mac_len: length of the MAC header - * @ethernet: flag to indicate if ethernet header is present in packet + * @ethernet: flag to indicate if the packet is ethernet * * Expects skb->data at mac header. * @@ -5976,7 +6078,14 @@ static void *skb_ext_get_ptr(struct skb_ext *ext, enum skb_ext_id id) return (void *)ext + (ext->offset[id] * SKB_EXT_ALIGN_VALUE); } -static struct skb_ext *skb_ext_alloc(void) +/** + * __skb_ext_alloc - allocate a new skb extensions storage + * + * Returns the newly allocated pointer. The pointer can later attached to a + * skb via __skb_ext_set(). + * Note: caller must handle the skb_ext as an opaque data. + */ +struct skb_ext *__skb_ext_alloc(void) { struct skb_ext *new = kmem_cache_alloc(skbuff_ext_cache, GFP_ATOMIC); @@ -6017,6 +6126,30 @@ static struct skb_ext *skb_ext_maybe_cow(struct skb_ext *old, } /** + * __skb_ext_set - attach the specified extension storage to this skb + * @skb: buffer + * @id: extension id + * @ext: extension storage previously allocated via __skb_ext_alloc() + * + * Existing extensions, if any, are cleared. + * + * Returns the pointer to the extension. + */ +void *__skb_ext_set(struct sk_buff *skb, enum skb_ext_id id, + struct skb_ext *ext) +{ + unsigned int newlen, newoff = SKB_EXT_CHUNKSIZEOF(*ext); + + skb_ext_put(skb); + newlen = newoff + skb_ext_type_len[id]; + ext->chunks = newlen; + ext->offset[id] = newoff; + skb->extensions = ext; + skb->active_extensions = 1 << id; + return skb_ext_get_ptr(ext, id); +} + +/** * skb_ext_add - allocate space for given extension, COW if needed * @skb: buffer * @id: extension to allocate space for @@ -6049,7 +6182,7 @@ void *skb_ext_add(struct sk_buff *skb, enum skb_ext_id id) } else { newoff = SKB_EXT_CHUNKSIZEOF(*new); - new = skb_ext_alloc(); + new = __skb_ext_alloc(); if (!new) return NULL; } diff --git a/net/core/sock.c b/net/core/sock.c index 8459ad579f73..a4c8fac781ff 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -2786,7 +2786,7 @@ static void sock_def_error_report(struct sock *sk) rcu_read_unlock(); } -static void sock_def_readable(struct sock *sk) +void sock_def_readable(struct sock *sk) { struct socket_wq *wq; diff --git a/net/core/sock_reuseport.c b/net/core/sock_reuseport.c index f19f179538b9..91e9f2223c39 100644 --- a/net/core/sock_reuseport.c +++ b/net/core/sock_reuseport.c @@ -107,7 +107,6 @@ static struct sock_reuseport *reuseport_grow(struct sock_reuseport *reuse) if (!more_reuse) return NULL; - more_reuse->max_socks = more_socks_size; more_reuse->num_socks = reuse->num_socks; more_reuse->prog = reuse->prog; more_reuse->reuseport_id = reuse->reuseport_id; diff --git a/net/core/timestamping.c b/net/core/timestamping.c index 7911235706a9..04840697fe79 100644 --- a/net/core/timestamping.c +++ b/net/core/timestamping.c @@ -13,7 +13,7 @@ static unsigned int classify(const struct sk_buff *skb) { if (likely(skb->dev && skb->dev->phydev && - skb->dev->phydev->drv)) + skb->dev->phydev->mii_ts)) return ptp_classify_raw(skb); else return PTP_CLASS_NONE; @@ -21,7 +21,7 @@ static unsigned int classify(const struct sk_buff *skb) void skb_clone_tx_timestamp(struct sk_buff *skb) { - struct phy_device *phydev; + struct mii_timestamper *mii_ts; struct sk_buff *clone; unsigned int type; @@ -32,22 +32,22 @@ void skb_clone_tx_timestamp(struct sk_buff *skb) if (type == PTP_CLASS_NONE) return; - phydev = skb->dev->phydev; - if (likely(phydev->drv->txtstamp)) { + mii_ts = skb->dev->phydev->mii_ts; + if (likely(mii_ts->txtstamp)) { clone = skb_clone_sk(skb); if (!clone) return; - phydev->drv->txtstamp(phydev, clone, type); + mii_ts->txtstamp(mii_ts, clone, type); } } EXPORT_SYMBOL_GPL(skb_clone_tx_timestamp); bool skb_defer_rx_timestamp(struct sk_buff *skb) { - struct phy_device *phydev; + struct mii_timestamper *mii_ts; unsigned int type; - if (!skb->dev || !skb->dev->phydev || !skb->dev->phydev->drv) + if (!skb->dev || !skb->dev->phydev || !skb->dev->phydev->mii_ts) return false; if (skb_headroom(skb) < ETH_HLEN) @@ -62,9 +62,9 @@ bool skb_defer_rx_timestamp(struct sk_buff *skb) if (type == PTP_CLASS_NONE) return false; - phydev = skb->dev->phydev; - if (likely(phydev->drv->rxtstamp)) - return phydev->drv->rxtstamp(phydev, skb, type); + mii_ts = skb->dev->phydev->mii_ts; + if (likely(mii_ts->rxtstamp)) + return mii_ts->rxtstamp(mii_ts, skb, type); return false; } diff --git a/net/decnet/af_decnet.c b/net/decnet/af_decnet.c index e19a92a62e14..0a46ea3bddd5 100644 --- a/net/decnet/af_decnet.c +++ b/net/decnet/af_decnet.c @@ -670,7 +670,7 @@ static int dn_create(struct net *net, struct socket *sock, int protocol, { struct sock *sk; - if (protocol < 0 || protocol > SK_PROTOCOL_MAX) + if (protocol < 0 || protocol > U8_MAX) return -EINVAL; if (!net_eq(net, &init_net)) diff --git a/net/dsa/Kconfig b/net/dsa/Kconfig index 1e6c3cac11e6..92663dcb3aa2 100644 --- a/net/dsa/Kconfig +++ b/net/dsa/Kconfig @@ -29,6 +29,12 @@ config NET_DSA_TAG_8021Q Drivers which use these helpers should select this as dependency. +config NET_DSA_TAG_AR9331 + tristate "Tag driver for Atheros AR9331 SoC with built-in switch" + help + Say Y or M if you want to enable support for tagging frames for + the Atheros AR9331 SoC with built-in switch. + config NET_DSA_TAG_BRCM_COMMON tristate default n diff --git a/net/dsa/Makefile b/net/dsa/Makefile index 9a482c38bdb1..108486cfdeef 100644 --- a/net/dsa/Makefile +++ b/net/dsa/Makefile @@ -5,6 +5,7 @@ dsa_core-y += dsa.o dsa2.o master.o port.o slave.o switch.o # tagging formats obj-$(CONFIG_NET_DSA_TAG_8021Q) += tag_8021q.o +obj-$(CONFIG_NET_DSA_TAG_AR9331) += tag_ar9331.o obj-$(CONFIG_NET_DSA_TAG_BRCM_COMMON) += tag_brcm.o obj-$(CONFIG_NET_DSA_TAG_DSA) += tag_dsa.o obj-$(CONFIG_NET_DSA_TAG_EDSA) += tag_edsa.o diff --git a/net/dsa/dsa2.c b/net/dsa/dsa2.c index c66abbed4daf..e7c30b472034 100644 --- a/net/dsa/dsa2.c +++ b/net/dsa/dsa2.c @@ -614,6 +614,32 @@ static int dsa_port_parse_dsa(struct dsa_port *dp) return 0; } +static enum dsa_tag_protocol dsa_get_tag_protocol(struct dsa_port *dp, + struct net_device *master) +{ + enum dsa_tag_protocol tag_protocol = DSA_TAG_PROTO_NONE; + struct dsa_switch *mds, *ds = dp->ds; + unsigned int mdp_upstream; + struct dsa_port *mdp; + + /* It is possible to stack DSA switches onto one another when that + * happens the switch driver may want to know if its tagging protocol + * is going to work in such a configuration. + */ + if (dsa_slave_dev_check(master)) { + mdp = dsa_slave_to_port(master); + mds = mdp->ds; + mdp_upstream = dsa_upstream_port(mds, mdp->index); + tag_protocol = mds->ops->get_tag_protocol(mds, mdp_upstream, + DSA_TAG_PROTO_NONE); + } + + /* If the master device is not itself a DSA slave in a disjoint DSA + * tree, then return immediately. + */ + return ds->ops->get_tag_protocol(ds, dp->index, tag_protocol); +} + static int dsa_port_parse_cpu(struct dsa_port *dp, struct net_device *master) { struct dsa_switch *ds = dp->ds; @@ -621,20 +647,21 @@ static int dsa_port_parse_cpu(struct dsa_port *dp, struct net_device *master) const struct dsa_device_ops *tag_ops; enum dsa_tag_protocol tag_protocol; - tag_protocol = ds->ops->get_tag_protocol(ds, dp->index); + tag_protocol = dsa_get_tag_protocol(dp, master); tag_ops = dsa_tag_driver_get(tag_protocol); if (IS_ERR(tag_ops)) { if (PTR_ERR(tag_ops) == -ENOPROTOOPT) return -EPROBE_DEFER; dev_warn(ds->dev, "No tagger for this switch\n"); + dp->master = NULL; return PTR_ERR(tag_ops); } + dp->master = master; dp->type = DSA_PORT_TYPE_CPU; dp->filter = tag_ops->filter; dp->rcv = tag_ops->rcv; dp->tag_ops = tag_ops; - dp->master = master; dp->dst = dst; return 0; @@ -822,6 +849,19 @@ static int dsa_switch_parse(struct dsa_switch *ds, struct dsa_chip_data *cd) return dsa_switch_parse_ports(ds, cd); } +static void dsa_switch_release_ports(struct dsa_switch *ds) +{ + struct dsa_switch_tree *dst = ds->dst; + struct dsa_port *dp, *next; + + list_for_each_entry_safe(dp, next, &dst->ports, list) { + if (dp->ds != ds) + continue; + list_del(&dp->list); + kfree(dp); + } +} + static int dsa_switch_probe(struct dsa_switch *ds) { struct dsa_switch_tree *dst; @@ -838,12 +878,17 @@ static int dsa_switch_probe(struct dsa_switch *ds) if (!ds->num_ports) return -EINVAL; - if (np) + if (np) { err = dsa_switch_parse_of(ds, np); - else if (pdata) + if (err) + dsa_switch_release_ports(ds); + } else if (pdata) { err = dsa_switch_parse(ds, pdata); - else + if (err) + dsa_switch_release_ports(ds); + } else { err = -ENODEV; + } if (err) return err; @@ -851,8 +896,10 @@ static int dsa_switch_probe(struct dsa_switch *ds) dst = ds->dst; dsa_tree_get(dst); err = dsa_tree_setup(dst); - if (err) + if (err) { + dsa_switch_release_ports(ds); dsa_tree_put(dst); + } return err; } @@ -873,15 +920,9 @@ EXPORT_SYMBOL_GPL(dsa_register_switch); static void dsa_switch_remove(struct dsa_switch *ds) { struct dsa_switch_tree *dst = ds->dst; - struct dsa_port *dp, *next; dsa_tree_teardown(dst); - - list_for_each_entry_safe(dp, next, &dst->ports, list) { - list_del(&dp->list); - kfree(dp); - } - + dsa_switch_release_ports(ds); dsa_tree_put(dst); } diff --git a/net/dsa/dsa_priv.h b/net/dsa/dsa_priv.h index 2dd86d9bcda9..a7662e7a691d 100644 --- a/net/dsa/dsa_priv.h +++ b/net/dsa/dsa_priv.h @@ -150,22 +150,6 @@ int dsa_port_vid_add(struct dsa_port *dp, u16 vid, u16 flags); int dsa_port_vid_del(struct dsa_port *dp, u16 vid); int dsa_port_link_register_of(struct dsa_port *dp); void dsa_port_link_unregister_of(struct dsa_port *dp); -void dsa_port_phylink_validate(struct phylink_config *config, - unsigned long *supported, - struct phylink_link_state *state); -void dsa_port_phylink_mac_pcs_get_state(struct phylink_config *config, - struct phylink_link_state *state); -void dsa_port_phylink_mac_config(struct phylink_config *config, - unsigned int mode, - const struct phylink_link_state *state); -void dsa_port_phylink_mac_an_restart(struct phylink_config *config); -void dsa_port_phylink_mac_link_down(struct phylink_config *config, - unsigned int mode, - phy_interface_t interface); -void dsa_port_phylink_mac_link_up(struct phylink_config *config, - unsigned int mode, - phy_interface_t interface, - struct phy_device *phydev); extern const struct phylink_mac_ops dsa_port_phylink_mac_ops; /* slave.c */ @@ -173,13 +157,12 @@ extern const struct dsa_device_ops notag_netdev_ops; void dsa_slave_mii_bus_init(struct dsa_switch *ds); int dsa_slave_create(struct dsa_port *dp); void dsa_slave_destroy(struct net_device *slave_dev); +bool dsa_slave_dev_check(const struct net_device *dev); int dsa_slave_suspend(struct net_device *slave_dev); int dsa_slave_resume(struct net_device *slave_dev); int dsa_slave_register_notifier(void); void dsa_slave_unregister_notifier(void); -void *dsa_defer_xmit(struct sk_buff *skb, struct net_device *dev); - static inline struct dsa_port *dsa_slave_to_port(const struct net_device *dev) { struct dsa_slave_priv *p = netdev_priv(dev); diff --git a/net/dsa/master.c b/net/dsa/master.c index 3255dfc97f86..bd44bde272f4 100644 --- a/net/dsa/master.c +++ b/net/dsa/master.c @@ -197,6 +197,35 @@ static int dsa_master_get_phys_port_name(struct net_device *dev, return 0; } +static int dsa_master_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) +{ + struct dsa_port *cpu_dp = dev->dsa_ptr; + struct dsa_switch *ds = cpu_dp->ds; + struct dsa_switch_tree *dst; + int err = -EOPNOTSUPP; + struct dsa_port *dp; + + dst = ds->dst; + + switch (cmd) { + case SIOCGHWTSTAMP: + case SIOCSHWTSTAMP: + /* Deny PTP operations on master if there is at least one + * switch in the tree that is PTP capable. + */ + list_for_each_entry(dp, &dst->ports, list) + if (dp->ds->ops->port_hwtstamp_get || + dp->ds->ops->port_hwtstamp_set) + return -EBUSY; + break; + } + + if (cpu_dp->orig_ndo_ops && cpu_dp->orig_ndo_ops->ndo_do_ioctl) + err = cpu_dp->orig_ndo_ops->ndo_do_ioctl(dev, ifr, cmd); + + return err; +} + static int dsa_master_ethtool_setup(struct net_device *dev) { struct dsa_port *cpu_dp = dev->dsa_ptr; @@ -249,6 +278,7 @@ static int dsa_master_ndo_setup(struct net_device *dev) memcpy(ops, cpu_dp->orig_ndo_ops, sizeof(*ops)); ops->ndo_get_phys_port_name = dsa_master_get_phys_port_name; + ops->ndo_do_ioctl = dsa_master_ioctl; dev->netdev_ops = ops; diff --git a/net/dsa/port.c b/net/dsa/port.c index 46ac9ba21987..774facb8d547 100644 --- a/net/dsa/port.c +++ b/net/dsa/port.c @@ -415,9 +415,9 @@ static struct phy_device *dsa_port_get_phy_device(struct dsa_port *dp) return phydev; } -void dsa_port_phylink_validate(struct phylink_config *config, - unsigned long *supported, - struct phylink_link_state *state) +static void dsa_port_phylink_validate(struct phylink_config *config, + unsigned long *supported, + struct phylink_link_state *state) { struct dsa_port *dp = container_of(config, struct dsa_port, pl_config); struct dsa_switch *ds = dp->ds; @@ -427,10 +427,9 @@ void dsa_port_phylink_validate(struct phylink_config *config, ds->ops->phylink_validate(ds, dp->index, supported, state); } -EXPORT_SYMBOL_GPL(dsa_port_phylink_validate); -void dsa_port_phylink_mac_pcs_get_state(struct phylink_config *config, - struct phylink_link_state *state) +static void dsa_port_phylink_mac_pcs_get_state(struct phylink_config *config, + struct phylink_link_state *state) { struct dsa_port *dp = container_of(config, struct dsa_port, pl_config); struct dsa_switch *ds = dp->ds; @@ -444,11 +443,10 @@ void dsa_port_phylink_mac_pcs_get_state(struct phylink_config *config, if (ds->ops->phylink_mac_link_state(ds, dp->index, state) < 0) state->link = 0; } -EXPORT_SYMBOL_GPL(dsa_port_phylink_mac_pcs_get_state); -void dsa_port_phylink_mac_config(struct phylink_config *config, - unsigned int mode, - const struct phylink_link_state *state) +static void dsa_port_phylink_mac_config(struct phylink_config *config, + unsigned int mode, + const struct phylink_link_state *state) { struct dsa_port *dp = container_of(config, struct dsa_port, pl_config); struct dsa_switch *ds = dp->ds; @@ -458,9 +456,8 @@ void dsa_port_phylink_mac_config(struct phylink_config *config, ds->ops->phylink_mac_config(ds, dp->index, mode, state); } -EXPORT_SYMBOL_GPL(dsa_port_phylink_mac_config); -void dsa_port_phylink_mac_an_restart(struct phylink_config *config) +static void dsa_port_phylink_mac_an_restart(struct phylink_config *config) { struct dsa_port *dp = container_of(config, struct dsa_port, pl_config); struct dsa_switch *ds = dp->ds; @@ -470,11 +467,10 @@ void dsa_port_phylink_mac_an_restart(struct phylink_config *config) ds->ops->phylink_mac_an_restart(ds, dp->index); } -EXPORT_SYMBOL_GPL(dsa_port_phylink_mac_an_restart); -void dsa_port_phylink_mac_link_down(struct phylink_config *config, - unsigned int mode, - phy_interface_t interface) +static void dsa_port_phylink_mac_link_down(struct phylink_config *config, + unsigned int mode, + phy_interface_t interface) { struct dsa_port *dp = container_of(config, struct dsa_port, pl_config); struct phy_device *phydev = NULL; @@ -491,12 +487,11 @@ void dsa_port_phylink_mac_link_down(struct phylink_config *config, ds->ops->phylink_mac_link_down(ds, dp->index, mode, interface); } -EXPORT_SYMBOL_GPL(dsa_port_phylink_mac_link_down); -void dsa_port_phylink_mac_link_up(struct phylink_config *config, - unsigned int mode, - phy_interface_t interface, - struct phy_device *phydev) +static void dsa_port_phylink_mac_link_up(struct phylink_config *config, + unsigned int mode, + phy_interface_t interface, + struct phy_device *phydev) { struct dsa_port *dp = container_of(config, struct dsa_port, pl_config); struct dsa_switch *ds = dp->ds; @@ -509,7 +504,6 @@ void dsa_port_phylink_mac_link_up(struct phylink_config *config, ds->ops->phylink_mac_link_up(ds, dp->index, mode, interface, phydev); } -EXPORT_SYMBOL_GPL(dsa_port_phylink_mac_link_up); const struct phylink_mac_ops dsa_port_phylink_mac_ops = { .validate = dsa_port_phylink_validate, @@ -605,6 +599,7 @@ static int dsa_port_phylink_register(struct dsa_port *dp) dp->pl_config.dev = ds->dev; dp->pl_config.type = PHYLINK_DEV; + dp->pl_config.pcs_poll = ds->pcs_poll; dp->pl = phylink_create(&dp->pl_config, of_fwnode_handle(port_dn), mode, &dsa_port_phylink_mac_ops); diff --git a/net/dsa/slave.c b/net/dsa/slave.c index 78ffc87dc25e..088c886e609e 100644 --- a/net/dsa/slave.c +++ b/net/dsa/slave.c @@ -22,8 +22,6 @@ #include "dsa_priv.h" -static bool dsa_slave_dev_check(const struct net_device *dev); - /* slave mii_bus handling ***************************************************/ static int dsa_slave_phy_read(struct mii_bus *bus, int addr, int reg) { @@ -116,9 +114,6 @@ static int dsa_slave_close(struct net_device *dev) struct net_device *master = dsa_slave_to_master(dev); struct dsa_port *dp = dsa_slave_to_port(dev); - cancel_work_sync(&dp->xmit_work); - skb_queue_purge(&dp->xmit_queue); - phylink_stop(dp->pl); dsa_port_disable(dp); @@ -518,7 +513,6 @@ static netdev_tx_t dsa_slave_xmit(struct sk_buff *skb, struct net_device *dev) s->tx_bytes += skb->len; u64_stats_update_end(&s->syncp); - DSA_SKB_CB(skb)->deferred_xmit = false; DSA_SKB_CB(skb)->clone = NULL; /* Identify PTP protocol packets, clone them, and pass them to the @@ -531,39 +525,13 @@ static netdev_tx_t dsa_slave_xmit(struct sk_buff *skb, struct net_device *dev) */ nskb = p->xmit(skb, dev); if (!nskb) { - if (!DSA_SKB_CB(skb)->deferred_xmit) - kfree_skb(skb); + kfree_skb(skb); return NETDEV_TX_OK; } return dsa_enqueue_skb(nskb, dev); } -void *dsa_defer_xmit(struct sk_buff *skb, struct net_device *dev) -{ - struct dsa_port *dp = dsa_slave_to_port(dev); - - DSA_SKB_CB(skb)->deferred_xmit = true; - - skb_queue_tail(&dp->xmit_queue, skb); - schedule_work(&dp->xmit_work); - return NULL; -} -EXPORT_SYMBOL_GPL(dsa_defer_xmit); - -static void dsa_port_xmit_work(struct work_struct *work) -{ - struct dsa_port *dp = container_of(work, struct dsa_port, xmit_work); - struct dsa_switch *ds = dp->ds; - struct sk_buff *skb; - - if (unlikely(!ds->ops->port_deferred_xmit)) - return; - - while ((skb = skb_dequeue(&dp->xmit_queue)) != NULL) - ds->ops->port_deferred_xmit(ds, dp->index, skb); -} - /* ethtool operations *******************************************************/ static void dsa_slave_get_drvinfo(struct net_device *dev, @@ -1367,9 +1335,6 @@ int dsa_slave_suspend(struct net_device *slave_dev) if (!netif_running(slave_dev)) return 0; - cancel_work_sync(&dp->xmit_work); - skb_queue_purge(&dp->xmit_queue); - netif_device_detach(slave_dev); rtnl_lock(); @@ -1455,8 +1420,6 @@ int dsa_slave_create(struct dsa_port *port) } p->dp = port; INIT_LIST_HEAD(&p->mall_tc_list); - INIT_WORK(&port->xmit_work, dsa_port_xmit_work); - skb_queue_head_init(&port->xmit_queue); p->xmit = cpu_dp->tag_ops->xmit; port->slave = slave_dev; @@ -1508,7 +1471,7 @@ void dsa_slave_destroy(struct net_device *slave_dev) free_netdev(slave_dev); } -static bool dsa_slave_dev_check(const struct net_device *dev) +bool dsa_slave_dev_check(const struct net_device *dev) { return dev->netdev_ops == &dsa_slave_netdev_ops; } diff --git a/net/dsa/tag_ar9331.c b/net/dsa/tag_ar9331.c new file mode 100644 index 000000000000..466ffa92a474 --- /dev/null +++ b/net/dsa/tag_ar9331.c @@ -0,0 +1,96 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (c) 2019 Pengutronix, Oleksij Rempel <kernel@pengutronix.de> + */ + + +#include <linux/bitfield.h> +#include <linux/etherdevice.h> + +#include "dsa_priv.h" + +#define AR9331_HDR_LEN 2 +#define AR9331_HDR_VERSION 1 + +#define AR9331_HDR_VERSION_MASK GENMASK(15, 14) +#define AR9331_HDR_PRIORITY_MASK GENMASK(13, 12) +#define AR9331_HDR_TYPE_MASK GENMASK(10, 8) +#define AR9331_HDR_BROADCAST BIT(7) +#define AR9331_HDR_FROM_CPU BIT(6) +/* AR9331_HDR_RESERVED - not used or may be version field. + * According to the AR8216 doc it should 0b10. On AR9331 it is 0b11 on RX path + * and should be set to 0b11 to make it work. + */ +#define AR9331_HDR_RESERVED_MASK GENMASK(5, 4) +#define AR9331_HDR_PORT_NUM_MASK GENMASK(3, 0) + +static struct sk_buff *ar9331_tag_xmit(struct sk_buff *skb, + struct net_device *dev) +{ + struct dsa_port *dp = dsa_slave_to_port(dev); + __le16 *phdr; + u16 hdr; + + if (skb_cow_head(skb, 0) < 0) + return NULL; + + phdr = skb_push(skb, AR9331_HDR_LEN); + + hdr = FIELD_PREP(AR9331_HDR_VERSION_MASK, AR9331_HDR_VERSION); + hdr |= AR9331_HDR_FROM_CPU | dp->index; + /* 0b10 for AR8216 and 0b11 for AR9331 */ + hdr |= AR9331_HDR_RESERVED_MASK; + + phdr[0] = cpu_to_le16(hdr); + + return skb; +} + +static struct sk_buff *ar9331_tag_rcv(struct sk_buff *skb, + struct net_device *ndev, + struct packet_type *pt) +{ + u8 ver, port; + u16 hdr; + + if (unlikely(!pskb_may_pull(skb, AR9331_HDR_LEN))) + return NULL; + + hdr = le16_to_cpu(*(__le16 *)skb_mac_header(skb)); + + ver = FIELD_GET(AR9331_HDR_VERSION_MASK, hdr); + if (unlikely(ver != AR9331_HDR_VERSION)) { + netdev_warn_once(ndev, "%s:%i wrong header version 0x%2x\n", + __func__, __LINE__, hdr); + return NULL; + } + + if (unlikely(hdr & AR9331_HDR_FROM_CPU)) { + netdev_warn_once(ndev, "%s:%i packet should not be from cpu 0x%2x\n", + __func__, __LINE__, hdr); + return NULL; + } + + skb_pull_rcsum(skb, AR9331_HDR_LEN); + + /* Get source port information */ + port = FIELD_GET(AR9331_HDR_PORT_NUM_MASK, hdr); + + skb->dev = dsa_master_find_slave(ndev, 0, port); + if (!skb->dev) + return NULL; + + return skb; +} + +static const struct dsa_device_ops ar9331_netdev_ops = { + .name = "ar9331", + .proto = DSA_TAG_PROTO_AR9331, + .xmit = ar9331_tag_xmit, + .rcv = ar9331_tag_rcv, + .overhead = AR9331_HDR_LEN, +}; + +MODULE_LICENSE("GPL v2"); +MODULE_ALIAS_DSA_TAG_DRIVER(DSA_TAG_PROTO_AR9331); +module_dsa_tag_driver(ar9331_netdev_ops); diff --git a/net/dsa/tag_sja1105.c b/net/dsa/tag_sja1105.c index 63ef2a14c934..5366ea430349 100644 --- a/net/dsa/tag_sja1105.c +++ b/net/dsa/tag_sja1105.c @@ -83,12 +83,24 @@ static bool sja1105_filter(const struct sk_buff *skb, struct net_device *dev) return false; } +/* Calls sja1105_port_deferred_xmit in sja1105_main.c */ +static struct sk_buff *sja1105_defer_xmit(struct sja1105_port *sp, + struct sk_buff *skb) +{ + /* Increase refcount so the kfree_skb in dsa_slave_xmit + * won't really free the packet. + */ + skb_queue_tail(&sp->xmit_queue, skb_get(skb)); + kthread_queue_work(sp->xmit_worker, &sp->xmit_work); + + return NULL; +} + static struct sk_buff *sja1105_xmit(struct sk_buff *skb, struct net_device *netdev) { struct dsa_port *dp = dsa_slave_to_port(netdev); - struct dsa_switch *ds = dp->ds; - u16 tx_vid = dsa_8021q_tx_vid(ds, dp->index); + u16 tx_vid = dsa_8021q_tx_vid(dp->ds, dp->index); u16 queue_mapping = skb_get_queue_mapping(skb); u8 pcp = netdev_txq_to_tc(netdev, queue_mapping); @@ -97,7 +109,7 @@ static struct sk_buff *sja1105_xmit(struct sk_buff *skb, * is the .port_deferred_xmit driver callback. */ if (unlikely(sja1105_is_link_local(skb))) - return dsa_defer_xmit(skb, netdev); + return sja1105_defer_xmit(dp->priv, skb); /* If we are under a vlan_filtering bridge, IP termination on * switch ports based on 802.1Q tags is simply too brittle to diff --git a/net/ethernet/eth.c b/net/ethernet/eth.c index 9040fe55e0f5..c8b903302ff2 100644 --- a/net/ethernet/eth.c +++ b/net/ethernet/eth.c @@ -335,22 +335,6 @@ int eth_mac_addr(struct net_device *dev, void *p) } EXPORT_SYMBOL(eth_mac_addr); -/** - * eth_change_mtu - set new MTU size - * @dev: network device - * @new_mtu: new Maximum Transfer Unit - * - * Allow changing MTU size. Needs to be overridden for devices - * supporting jumbo frames. - */ -int eth_change_mtu(struct net_device *dev, int new_mtu) -{ - netdev_warn(dev, "%s is deprecated\n", __func__); - dev->mtu = new_mtu; - return 0; -} -EXPORT_SYMBOL(eth_change_mtu); - int eth_validate_addr(struct net_device *dev) { if (!is_valid_ether_addr(dev->dev_addr)) diff --git a/net/ethtool/Makefile b/net/ethtool/Makefile new file mode 100644 index 000000000000..424545a4aaec --- /dev/null +++ b/net/ethtool/Makefile @@ -0,0 +1,8 @@ +# SPDX-License-Identifier: GPL-2.0-only + +obj-y += ioctl.o common.o + +obj-$(CONFIG_ETHTOOL_NETLINK) += ethtool_nl.o + +ethtool_nl-y := netlink.o bitset.o strset.o linkinfo.o linkmodes.o \ + linkstate.o debug.o wol.o diff --git a/net/ethtool/bitset.c b/net/ethtool/bitset.c new file mode 100644 index 000000000000..fce45dac4205 --- /dev/null +++ b/net/ethtool/bitset.c @@ -0,0 +1,735 @@ +// SPDX-License-Identifier: GPL-2.0-only + +#include <linux/ethtool_netlink.h> +#include <linux/bitmap.h> +#include "netlink.h" +#include "bitset.h" + +/* Some bitmaps are internally represented as an array of unsigned long, some + * as an array of u32 (some even as single u32 for now). To avoid the need of + * wrappers on caller side, we provide two set of functions: those with "32" + * suffix in their names expect u32 based bitmaps, those without it expect + * unsigned long bitmaps. + */ + +static u32 ethnl_lower_bits(unsigned int n) +{ + return ~(u32)0 >> (32 - n % 32); +} + +static u32 ethnl_upper_bits(unsigned int n) +{ + return ~(u32)0 << (n % 32); +} + +/** + * ethnl_bitmap32_clear() - Clear u32 based bitmap + * @dst: bitmap to clear + * @start: beginning of the interval + * @end: end of the interval + * @mod: set if bitmap was modified + * + * Clear @nbits bits of a bitmap with indices @start <= i < @end + */ +static void ethnl_bitmap32_clear(u32 *dst, unsigned int start, unsigned int end, + bool *mod) +{ + unsigned int start_word = start / 32; + unsigned int end_word = end / 32; + unsigned int i; + u32 mask; + + if (end <= start) + return; + + if (start % 32) { + mask = ethnl_upper_bits(start); + if (end_word == start_word) { + mask &= ethnl_lower_bits(end); + if (dst[start_word] & mask) { + dst[start_word] &= ~mask; + *mod = true; + } + return; + } + if (dst[start_word] & mask) { + dst[start_word] &= ~mask; + *mod = true; + } + start_word++; + } + + for (i = start_word; i < end_word; i++) { + if (dst[i]) { + dst[i] = 0; + *mod = true; + } + } + if (end % 32) { + mask = ethnl_lower_bits(end); + if (dst[end_word] & mask) { + dst[end_word] &= ~mask; + *mod = true; + } + } +} + +/** + * ethnl_bitmap32_not_zero() - Check if any bit is set in an interval + * @map: bitmap to test + * @start: beginning of the interval + * @end: end of the interval + * + * Return: true if there is non-zero bit with index @start <= i < @end, + * false if the whole interval is zero + */ +static bool ethnl_bitmap32_not_zero(const u32 *map, unsigned int start, + unsigned int end) +{ + unsigned int start_word = start / 32; + unsigned int end_word = end / 32; + u32 mask; + + if (end <= start) + return true; + + if (start % 32) { + mask = ethnl_upper_bits(start); + if (end_word == start_word) { + mask &= ethnl_lower_bits(end); + return map[start_word] & mask; + } + if (map[start_word] & mask) + return true; + start_word++; + } + + if (!memchr_inv(map + start_word, '\0', + (end_word - start_word) * sizeof(u32))) + return true; + if (end % 32 == 0) + return true; + return map[end_word] & ethnl_lower_bits(end); +} + +/** + * ethnl_bitmap32_update() - Modify u32 based bitmap according to value/mask + * pair + * @dst: bitmap to update + * @nbits: bit size of the bitmap + * @value: values to set + * @mask: mask of bits to set + * @mod: set to true if bitmap is modified, preserve if not + * + * Set bits in @dst bitmap which are set in @mask to values from @value, leave + * the rest untouched. If destination bitmap was modified, set @mod to true, + * leave as it is if not. + */ +static void ethnl_bitmap32_update(u32 *dst, unsigned int nbits, + const u32 *value, const u32 *mask, bool *mod) +{ + while (nbits > 0) { + u32 real_mask = mask ? *mask : ~(u32)0; + u32 new_value; + + if (nbits < 32) + real_mask &= ethnl_lower_bits(nbits); + new_value = (*dst & ~real_mask) | (*value & real_mask); + if (new_value != *dst) { + *dst = new_value; + *mod = true; + } + + if (nbits <= 32) + break; + dst++; + nbits -= 32; + value++; + if (mask) + mask++; + } +} + +static bool ethnl_bitmap32_test_bit(const u32 *map, unsigned int index) +{ + return map[index / 32] & (1U << (index % 32)); +} + +/** + * ethnl_bitset32_size() - Calculate size of bitset nested attribute + * @val: value bitmap (u32 based) + * @mask: mask bitmap (u32 based, optional) + * @nbits: bit length of the bitset + * @names: array of bit names (optional) + * @compact: assume compact format for output + * + * Estimate length of netlink attribute composed by a later call to + * ethnl_put_bitset32() call with the same arguments. + * + * Return: negative error code or attribute length estimate + */ +int ethnl_bitset32_size(const u32 *val, const u32 *mask, unsigned int nbits, + ethnl_string_array_t names, bool compact) +{ + unsigned int len = 0; + + /* list flag */ + if (!mask) + len += nla_total_size(sizeof(u32)); + /* size */ + len += nla_total_size(sizeof(u32)); + + if (compact) { + unsigned int nwords = DIV_ROUND_UP(nbits, 32); + + /* value, mask */ + len += (mask ? 2 : 1) * nla_total_size(nwords * sizeof(u32)); + } else { + unsigned int bits_len = 0; + unsigned int bit_len, i; + + for (i = 0; i < nbits; i++) { + const char *name = names ? names[i] : NULL; + + if (!ethnl_bitmap32_test_bit(mask ?: val, i)) + continue; + /* index */ + bit_len = nla_total_size(sizeof(u32)); + /* name */ + if (name) + bit_len += ethnl_strz_size(name); + /* value */ + if (mask && ethnl_bitmap32_test_bit(val, i)) + bit_len += nla_total_size(0); + + /* bit nest */ + bits_len += nla_total_size(bit_len); + } + /* bits nest */ + len += nla_total_size(bits_len); + } + + /* outermost nest */ + return nla_total_size(len); +} + +/** + * ethnl_put_bitset32() - Put a bitset nest into a message + * @skb: skb with the message + * @attrtype: attribute type for the bitset nest + * @val: value bitmap (u32 based) + * @mask: mask bitmap (u32 based, optional) + * @nbits: bit length of the bitset + * @names: array of bit names (optional) + * @compact: use compact format for the output + * + * Compose a nested attribute representing a bitset. If @mask is null, simple + * bitmap (bit list) is created, if @mask is provided, represent a value/mask + * pair. Bit names are only used in verbose mode and when provided by calller. + * + * Return: 0 on success, negative error value on error + */ +int ethnl_put_bitset32(struct sk_buff *skb, int attrtype, const u32 *val, + const u32 *mask, unsigned int nbits, + ethnl_string_array_t names, bool compact) +{ + struct nlattr *nest; + struct nlattr *attr; + + nest = nla_nest_start(skb, attrtype); + if (!nest) + return -EMSGSIZE; + + if (!mask && nla_put_flag(skb, ETHTOOL_A_BITSET_NOMASK)) + goto nla_put_failure; + if (nla_put_u32(skb, ETHTOOL_A_BITSET_SIZE, nbits)) + goto nla_put_failure; + if (compact) { + unsigned int nwords = DIV_ROUND_UP(nbits, 32); + unsigned int nbytes = nwords * sizeof(u32); + u32 *dst; + + attr = nla_reserve(skb, ETHTOOL_A_BITSET_VALUE, nbytes); + if (!attr) + goto nla_put_failure; + dst = nla_data(attr); + memcpy(dst, val, nbytes); + if (nbits % 32) + dst[nwords - 1] &= ethnl_lower_bits(nbits); + + if (mask) { + attr = nla_reserve(skb, ETHTOOL_A_BITSET_MASK, nbytes); + if (!attr) + goto nla_put_failure; + dst = nla_data(attr); + memcpy(dst, mask, nbytes); + if (nbits % 32) + dst[nwords - 1] &= ethnl_lower_bits(nbits); + } + } else { + struct nlattr *bits; + unsigned int i; + + bits = nla_nest_start(skb, ETHTOOL_A_BITSET_BITS); + if (!bits) + goto nla_put_failure; + for (i = 0; i < nbits; i++) { + const char *name = names ? names[i] : NULL; + + if (!ethnl_bitmap32_test_bit(mask ?: val, i)) + continue; + attr = nla_nest_start(skb, ETHTOOL_A_BITSET_BITS_BIT); + if (!attr) + goto nla_put_failure; + if (nla_put_u32(skb, ETHTOOL_A_BITSET_BIT_INDEX, i)) + goto nla_put_failure; + if (name && + ethnl_put_strz(skb, ETHTOOL_A_BITSET_BIT_NAME, name)) + goto nla_put_failure; + if (mask && ethnl_bitmap32_test_bit(val, i) && + nla_put_flag(skb, ETHTOOL_A_BITSET_BIT_VALUE)) + goto nla_put_failure; + nla_nest_end(skb, attr); + } + nla_nest_end(skb, bits); + } + + nla_nest_end(skb, nest); + return 0; + +nla_put_failure: + nla_nest_cancel(skb, nest); + return -EMSGSIZE; +} + +static const struct nla_policy bitset_policy[ETHTOOL_A_BITSET_MAX + 1] = { + [ETHTOOL_A_BITSET_UNSPEC] = { .type = NLA_REJECT }, + [ETHTOOL_A_BITSET_NOMASK] = { .type = NLA_FLAG }, + [ETHTOOL_A_BITSET_SIZE] = { .type = NLA_U32 }, + [ETHTOOL_A_BITSET_BITS] = { .type = NLA_NESTED }, + [ETHTOOL_A_BITSET_VALUE] = { .type = NLA_BINARY }, + [ETHTOOL_A_BITSET_MASK] = { .type = NLA_BINARY }, +}; + +static const struct nla_policy bit_policy[ETHTOOL_A_BITSET_BIT_MAX + 1] = { + [ETHTOOL_A_BITSET_BIT_UNSPEC] = { .type = NLA_REJECT }, + [ETHTOOL_A_BITSET_BIT_INDEX] = { .type = NLA_U32 }, + [ETHTOOL_A_BITSET_BIT_NAME] = { .type = NLA_NUL_STRING }, + [ETHTOOL_A_BITSET_BIT_VALUE] = { .type = NLA_FLAG }, +}; + +/** + * ethnl_bitset_is_compact() - check if bitset attribute represents a compact + * bitset + * @bitset: nested attribute representing a bitset + * @compact: pointer for return value + * + * Return: 0 on success, negative error code on failure + */ +int ethnl_bitset_is_compact(const struct nlattr *bitset, bool *compact) +{ + struct nlattr *tb[ETHTOOL_A_BITSET_MAX + 1]; + int ret; + + ret = nla_parse_nested(tb, ETHTOOL_A_BITSET_MAX, bitset, + bitset_policy, NULL); + if (ret < 0) + return ret; + + if (tb[ETHTOOL_A_BITSET_BITS]) { + if (tb[ETHTOOL_A_BITSET_VALUE] || tb[ETHTOOL_A_BITSET_MASK]) + return -EINVAL; + *compact = false; + return 0; + } + if (!tb[ETHTOOL_A_BITSET_SIZE] || !tb[ETHTOOL_A_BITSET_VALUE]) + return -EINVAL; + + *compact = true; + return 0; +} + +/** + * ethnl_name_to_idx() - look up string index for a name + * @names: array of ETH_GSTRING_LEN sized strings + * @n_names: number of strings in the array + * @name: name to look up + * + * Return: index of the string if found, -ENOENT if not found + */ +static int ethnl_name_to_idx(ethnl_string_array_t names, unsigned int n_names, + const char *name) +{ + unsigned int i; + + if (!names) + return -ENOENT; + + for (i = 0; i < n_names; i++) { + /* names[i] may not be null terminated */ + if (!strncmp(names[i], name, ETH_GSTRING_LEN) && + strlen(name) <= ETH_GSTRING_LEN) + return i; + } + + return -ENOENT; +} + +static int ethnl_parse_bit(unsigned int *index, bool *val, unsigned int nbits, + const struct nlattr *bit_attr, bool no_mask, + ethnl_string_array_t names, + struct netlink_ext_ack *extack) +{ + struct nlattr *tb[ETHTOOL_A_BITSET_BIT_MAX + 1]; + int ret, idx; + + ret = nla_parse_nested(tb, ETHTOOL_A_BITSET_BIT_MAX, bit_attr, + bit_policy, extack); + if (ret < 0) + return ret; + + if (tb[ETHTOOL_A_BITSET_BIT_INDEX]) { + const char *name; + + idx = nla_get_u32(tb[ETHTOOL_A_BITSET_BIT_INDEX]); + if (idx >= nbits) { + NL_SET_ERR_MSG_ATTR(extack, + tb[ETHTOOL_A_BITSET_BIT_INDEX], + "bit index too high"); + return -EOPNOTSUPP; + } + name = names ? names[idx] : NULL; + if (tb[ETHTOOL_A_BITSET_BIT_NAME] && name && + strncmp(nla_data(tb[ETHTOOL_A_BITSET_BIT_NAME]), name, + nla_len(tb[ETHTOOL_A_BITSET_BIT_NAME]))) { + NL_SET_ERR_MSG_ATTR(extack, bit_attr, + "bit index and name mismatch"); + return -EINVAL; + } + } else if (tb[ETHTOOL_A_BITSET_BIT_NAME]) { + idx = ethnl_name_to_idx(names, nbits, + nla_data(tb[ETHTOOL_A_BITSET_BIT_NAME])); + if (idx < 0) { + NL_SET_ERR_MSG_ATTR(extack, + tb[ETHTOOL_A_BITSET_BIT_NAME], + "bit name not found"); + return -EOPNOTSUPP; + } + } else { + NL_SET_ERR_MSG_ATTR(extack, bit_attr, + "neither bit index nor name specified"); + return -EINVAL; + } + + *index = idx; + *val = no_mask || tb[ETHTOOL_A_BITSET_BIT_VALUE]; + return 0; +} + +static int +ethnl_update_bitset32_verbose(u32 *bitmap, unsigned int nbits, + const struct nlattr *attr, struct nlattr **tb, + ethnl_string_array_t names, + struct netlink_ext_ack *extack, bool *mod) +{ + struct nlattr *bit_attr; + bool no_mask; + int rem; + int ret; + + if (tb[ETHTOOL_A_BITSET_VALUE]) { + NL_SET_ERR_MSG_ATTR(extack, tb[ETHTOOL_A_BITSET_VALUE], + "value only allowed in compact bitset"); + return -EINVAL; + } + if (tb[ETHTOOL_A_BITSET_MASK]) { + NL_SET_ERR_MSG_ATTR(extack, tb[ETHTOOL_A_BITSET_MASK], + "mask only allowed in compact bitset"); + return -EINVAL; + } + no_mask = tb[ETHTOOL_A_BITSET_NOMASK]; + + nla_for_each_nested(bit_attr, tb[ETHTOOL_A_BITSET_BITS], rem) { + bool old_val, new_val; + unsigned int idx; + + if (nla_type(bit_attr) != ETHTOOL_A_BITSET_BITS_BIT) { + NL_SET_ERR_MSG_ATTR(extack, bit_attr, + "only ETHTOOL_A_BITSET_BITS_BIT allowed in ETHTOOL_A_BITSET_BITS"); + return -EINVAL; + } + ret = ethnl_parse_bit(&idx, &new_val, nbits, bit_attr, no_mask, + names, extack); + if (ret < 0) + return ret; + old_val = bitmap[idx / 32] & ((u32)1 << (idx % 32)); + if (new_val != old_val) { + if (new_val) + bitmap[idx / 32] |= ((u32)1 << (idx % 32)); + else + bitmap[idx / 32] &= ~((u32)1 << (idx % 32)); + *mod = true; + } + } + + return 0; +} + +static int ethnl_compact_sanity_checks(unsigned int nbits, + const struct nlattr *nest, + struct nlattr **tb, + struct netlink_ext_ack *extack) +{ + bool no_mask = tb[ETHTOOL_A_BITSET_NOMASK]; + unsigned int attr_nbits, attr_nwords; + const struct nlattr *test_attr; + + if (no_mask && tb[ETHTOOL_A_BITSET_MASK]) { + NL_SET_ERR_MSG_ATTR(extack, tb[ETHTOOL_A_BITSET_MASK], + "mask not allowed in list bitset"); + return -EINVAL; + } + if (!tb[ETHTOOL_A_BITSET_SIZE]) { + NL_SET_ERR_MSG_ATTR(extack, nest, + "missing size in compact bitset"); + return -EINVAL; + } + if (!tb[ETHTOOL_A_BITSET_VALUE]) { + NL_SET_ERR_MSG_ATTR(extack, nest, + "missing value in compact bitset"); + return -EINVAL; + } + if (!no_mask && !tb[ETHTOOL_A_BITSET_MASK]) { + NL_SET_ERR_MSG_ATTR(extack, nest, + "missing mask in compact nonlist bitset"); + return -EINVAL; + } + + attr_nbits = nla_get_u32(tb[ETHTOOL_A_BITSET_SIZE]); + attr_nwords = DIV_ROUND_UP(attr_nbits, 32); + if (nla_len(tb[ETHTOOL_A_BITSET_VALUE]) != attr_nwords * sizeof(u32)) { + NL_SET_ERR_MSG_ATTR(extack, tb[ETHTOOL_A_BITSET_VALUE], + "bitset value length does not match size"); + return -EINVAL; + } + if (tb[ETHTOOL_A_BITSET_MASK] && + nla_len(tb[ETHTOOL_A_BITSET_MASK]) != attr_nwords * sizeof(u32)) { + NL_SET_ERR_MSG_ATTR(extack, tb[ETHTOOL_A_BITSET_MASK], + "bitset mask length does not match size"); + return -EINVAL; + } + if (attr_nbits <= nbits) + return 0; + + test_attr = no_mask ? tb[ETHTOOL_A_BITSET_VALUE] : + tb[ETHTOOL_A_BITSET_MASK]; + if (ethnl_bitmap32_not_zero(nla_data(test_attr), nbits, attr_nbits)) { + NL_SET_ERR_MSG_ATTR(extack, test_attr, + "cannot modify bits past kernel bitset size"); + return -EINVAL; + } + return 0; +} + +/** + * ethnl_update_bitset32() - Apply a bitset nest to a u32 based bitmap + * @bitmap: bitmap to update + * @nbits: size of the updated bitmap in bits + * @attr: nest attribute to parse and apply + * @names: array of bit names; may be null for compact format + * @extack: extack for error reporting + * @mod: set this to true if bitmap is modified, leave as it is if not + * + * Apply bitset netsted attribute to a bitmap. If the attribute represents + * a bit list, @bitmap is set to its contents; otherwise, bits in mask are + * set to values from value. Bitmaps in the attribute may be longer than + * @nbits but the message must not request modifying any bits past @nbits. + * + * Return: negative error code on failure, 0 on success + */ +int ethnl_update_bitset32(u32 *bitmap, unsigned int nbits, + const struct nlattr *attr, ethnl_string_array_t names, + struct netlink_ext_ack *extack, bool *mod) +{ + struct nlattr *tb[ETHTOOL_A_BITSET_MAX + 1]; + unsigned int change_bits; + bool no_mask; + int ret; + + if (!attr) + return 0; + ret = nla_parse_nested(tb, ETHTOOL_A_BITSET_MAX, attr, bitset_policy, + extack); + if (ret < 0) + return ret; + + if (tb[ETHTOOL_A_BITSET_BITS]) + return ethnl_update_bitset32_verbose(bitmap, nbits, attr, tb, + names, extack, mod); + ret = ethnl_compact_sanity_checks(nbits, attr, tb, extack); + if (ret < 0) + return ret; + + no_mask = tb[ETHTOOL_A_BITSET_NOMASK]; + change_bits = min_t(unsigned int, + nla_get_u32(tb[ETHTOOL_A_BITSET_SIZE]), nbits); + ethnl_bitmap32_update(bitmap, change_bits, + nla_data(tb[ETHTOOL_A_BITSET_VALUE]), + no_mask ? NULL : + nla_data(tb[ETHTOOL_A_BITSET_MASK]), + mod); + if (no_mask && change_bits < nbits) + ethnl_bitmap32_clear(bitmap, change_bits, nbits, mod); + + return 0; +} + +#if BITS_PER_LONG == 64 && defined(__BIG_ENDIAN) + +/* 64-bit big endian architectures are the only case when u32 based bitmaps + * and unsigned long based bitmaps have different memory layout so that we + * cannot simply cast the latter to the former and need actual wrappers + * converting the latter to the former. + * + * To reduce the number of slab allocations, the wrappers use fixed size local + * variables for bitmaps up to ETHNL_SMALL_BITMAP_BITS bits which is the + * majority of bitmaps used by ethtool. + */ +#define ETHNL_SMALL_BITMAP_BITS 128 +#define ETHNL_SMALL_BITMAP_WORDS DIV_ROUND_UP(ETHNL_SMALL_BITMAP_BITS, 32) + +int ethnl_bitset_size(const unsigned long *val, const unsigned long *mask, + unsigned int nbits, ethnl_string_array_t names, + bool compact) +{ + u32 small_mask32[ETHNL_SMALL_BITMAP_WORDS]; + u32 small_val32[ETHNL_SMALL_BITMAP_WORDS]; + u32 *mask32; + u32 *val32; + int ret; + + if (nbits > ETHNL_SMALL_BITMAP_BITS) { + unsigned int nwords = DIV_ROUND_UP(nbits, 32); + + val32 = kmalloc_array(2 * nwords, sizeof(u32), GFP_KERNEL); + if (!val32) + return -ENOMEM; + mask32 = val32 + nwords; + } else { + val32 = small_val32; + mask32 = small_mask32; + } + + bitmap_to_arr32(val32, val, nbits); + if (mask) + bitmap_to_arr32(mask32, mask, nbits); + else + mask32 = NULL; + ret = ethnl_bitset32_size(val32, mask32, nbits, names, compact); + + if (nbits > ETHNL_SMALL_BITMAP_BITS) + kfree(val32); + + return ret; +} + +int ethnl_put_bitset(struct sk_buff *skb, int attrtype, + const unsigned long *val, const unsigned long *mask, + unsigned int nbits, ethnl_string_array_t names, + bool compact) +{ + u32 small_mask32[ETHNL_SMALL_BITMAP_WORDS]; + u32 small_val32[ETHNL_SMALL_BITMAP_WORDS]; + u32 *mask32; + u32 *val32; + int ret; + + if (nbits > ETHNL_SMALL_BITMAP_BITS) { + unsigned int nwords = DIV_ROUND_UP(nbits, 32); + + val32 = kmalloc_array(2 * nwords, sizeof(u32), GFP_KERNEL); + if (!val32) + return -ENOMEM; + mask32 = val32 + nwords; + } else { + val32 = small_val32; + mask32 = small_mask32; + } + + bitmap_to_arr32(val32, val, nbits); + if (mask) + bitmap_to_arr32(mask32, mask, nbits); + else + mask32 = NULL; + ret = ethnl_put_bitset32(skb, attrtype, val32, mask32, nbits, names, + compact); + + if (nbits > ETHNL_SMALL_BITMAP_BITS) + kfree(val32); + + return ret; +} + +int ethnl_update_bitset(unsigned long *bitmap, unsigned int nbits, + const struct nlattr *attr, ethnl_string_array_t names, + struct netlink_ext_ack *extack, bool *mod) +{ + u32 small_bitmap32[ETHNL_SMALL_BITMAP_WORDS]; + u32 *bitmap32 = small_bitmap32; + bool u32_mod = false; + int ret; + + if (nbits > ETHNL_SMALL_BITMAP_BITS) { + unsigned int dst_words = DIV_ROUND_UP(nbits, 32); + + bitmap32 = kmalloc_array(dst_words, sizeof(u32), GFP_KERNEL); + if (!bitmap32) + return -ENOMEM; + } + + bitmap_to_arr32(bitmap32, bitmap, nbits); + ret = ethnl_update_bitset32(bitmap32, nbits, attr, names, extack, + &u32_mod); + if (u32_mod) { + bitmap_from_arr32(bitmap, bitmap32, nbits); + *mod = true; + } + + if (nbits > ETHNL_SMALL_BITMAP_BITS) + kfree(bitmap32); + + return ret; +} + +#else + +/* On little endian 64-bit and all 32-bit architectures, an unsigned long + * based bitmap can be interpreted as u32 based one using a simple cast. + */ + +int ethnl_bitset_size(const unsigned long *val, const unsigned long *mask, + unsigned int nbits, ethnl_string_array_t names, + bool compact) +{ + return ethnl_bitset32_size((const u32 *)val, (const u32 *)mask, nbits, + names, compact); +} + +int ethnl_put_bitset(struct sk_buff *skb, int attrtype, + const unsigned long *val, const unsigned long *mask, + unsigned int nbits, ethnl_string_array_t names, + bool compact) +{ + return ethnl_put_bitset32(skb, attrtype, (const u32 *)val, + (const u32 *)mask, nbits, names, compact); +} + +int ethnl_update_bitset(unsigned long *bitmap, unsigned int nbits, + const struct nlattr *attr, ethnl_string_array_t names, + struct netlink_ext_ack *extack, bool *mod) +{ + return ethnl_update_bitset32((u32 *)bitmap, nbits, attr, names, extack, + mod); +} + +#endif /* BITS_PER_LONG == 64 && defined(__BIG_ENDIAN) */ diff --git a/net/ethtool/bitset.h b/net/ethtool/bitset.h new file mode 100644 index 000000000000..b8247e34109d --- /dev/null +++ b/net/ethtool/bitset.h @@ -0,0 +1,28 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ + +#ifndef _NET_ETHTOOL_BITSET_H +#define _NET_ETHTOOL_BITSET_H + +typedef const char (*const ethnl_string_array_t)[ETH_GSTRING_LEN]; + +int ethnl_bitset_is_compact(const struct nlattr *bitset, bool *compact); +int ethnl_bitset_size(const unsigned long *val, const unsigned long *mask, + unsigned int nbits, ethnl_string_array_t names, + bool compact); +int ethnl_bitset32_size(const u32 *val, const u32 *mask, unsigned int nbits, + ethnl_string_array_t names, bool compact); +int ethnl_put_bitset(struct sk_buff *skb, int attrtype, + const unsigned long *val, const unsigned long *mask, + unsigned int nbits, ethnl_string_array_t names, + bool compact); +int ethnl_put_bitset32(struct sk_buff *skb, int attrtype, const u32 *val, + const u32 *mask, unsigned int nbits, + ethnl_string_array_t names, bool compact); +int ethnl_update_bitset(unsigned long *bitmap, unsigned int nbits, + const struct nlattr *attr, ethnl_string_array_t names, + struct netlink_ext_ack *extack, bool *mod); +int ethnl_update_bitset32(u32 *bitmap, unsigned int nbits, + const struct nlattr *attr, ethnl_string_array_t names, + struct netlink_ext_ack *extack, bool *mod); + +#endif /* _NET_ETHTOOL_BITSET_H */ diff --git a/net/ethtool/common.c b/net/ethtool/common.c new file mode 100644 index 000000000000..636ec6d5110e --- /dev/null +++ b/net/ethtool/common.c @@ -0,0 +1,259 @@ +// SPDX-License-Identifier: GPL-2.0-only + +#include "common.h" + +const char netdev_features_strings[NETDEV_FEATURE_COUNT][ETH_GSTRING_LEN] = { + [NETIF_F_SG_BIT] = "tx-scatter-gather", + [NETIF_F_IP_CSUM_BIT] = "tx-checksum-ipv4", + [NETIF_F_HW_CSUM_BIT] = "tx-checksum-ip-generic", + [NETIF_F_IPV6_CSUM_BIT] = "tx-checksum-ipv6", + [NETIF_F_HIGHDMA_BIT] = "highdma", + [NETIF_F_FRAGLIST_BIT] = "tx-scatter-gather-fraglist", + [NETIF_F_HW_VLAN_CTAG_TX_BIT] = "tx-vlan-hw-insert", + + [NETIF_F_HW_VLAN_CTAG_RX_BIT] = "rx-vlan-hw-parse", + [NETIF_F_HW_VLAN_CTAG_FILTER_BIT] = "rx-vlan-filter", + [NETIF_F_HW_VLAN_STAG_TX_BIT] = "tx-vlan-stag-hw-insert", + [NETIF_F_HW_VLAN_STAG_RX_BIT] = "rx-vlan-stag-hw-parse", + [NETIF_F_HW_VLAN_STAG_FILTER_BIT] = "rx-vlan-stag-filter", + [NETIF_F_VLAN_CHALLENGED_BIT] = "vlan-challenged", + [NETIF_F_GSO_BIT] = "tx-generic-segmentation", + [NETIF_F_LLTX_BIT] = "tx-lockless", + [NETIF_F_NETNS_LOCAL_BIT] = "netns-local", + [NETIF_F_GRO_BIT] = "rx-gro", + [NETIF_F_GRO_HW_BIT] = "rx-gro-hw", + [NETIF_F_LRO_BIT] = "rx-lro", + + [NETIF_F_TSO_BIT] = "tx-tcp-segmentation", + [NETIF_F_GSO_ROBUST_BIT] = "tx-gso-robust", + [NETIF_F_TSO_ECN_BIT] = "tx-tcp-ecn-segmentation", + [NETIF_F_TSO_MANGLEID_BIT] = "tx-tcp-mangleid-segmentation", + [NETIF_F_TSO6_BIT] = "tx-tcp6-segmentation", + [NETIF_F_FSO_BIT] = "tx-fcoe-segmentation", + [NETIF_F_GSO_GRE_BIT] = "tx-gre-segmentation", + [NETIF_F_GSO_GRE_CSUM_BIT] = "tx-gre-csum-segmentation", + [NETIF_F_GSO_IPXIP4_BIT] = "tx-ipxip4-segmentation", + [NETIF_F_GSO_IPXIP6_BIT] = "tx-ipxip6-segmentation", + [NETIF_F_GSO_UDP_TUNNEL_BIT] = "tx-udp_tnl-segmentation", + [NETIF_F_GSO_UDP_TUNNEL_CSUM_BIT] = "tx-udp_tnl-csum-segmentation", + [NETIF_F_GSO_PARTIAL_BIT] = "tx-gso-partial", + [NETIF_F_GSO_SCTP_BIT] = "tx-sctp-segmentation", + [NETIF_F_GSO_ESP_BIT] = "tx-esp-segmentation", + [NETIF_F_GSO_UDP_L4_BIT] = "tx-udp-segmentation", + + [NETIF_F_FCOE_CRC_BIT] = "tx-checksum-fcoe-crc", + [NETIF_F_SCTP_CRC_BIT] = "tx-checksum-sctp", + [NETIF_F_FCOE_MTU_BIT] = "fcoe-mtu", + [NETIF_F_NTUPLE_BIT] = "rx-ntuple-filter", + [NETIF_F_RXHASH_BIT] = "rx-hashing", + [NETIF_F_RXCSUM_BIT] = "rx-checksum", + [NETIF_F_NOCACHE_COPY_BIT] = "tx-nocache-copy", + [NETIF_F_LOOPBACK_BIT] = "loopback", + [NETIF_F_RXFCS_BIT] = "rx-fcs", + [NETIF_F_RXALL_BIT] = "rx-all", + [NETIF_F_HW_L2FW_DOFFLOAD_BIT] = "l2-fwd-offload", + [NETIF_F_HW_TC_BIT] = "hw-tc-offload", + [NETIF_F_HW_ESP_BIT] = "esp-hw-offload", + [NETIF_F_HW_ESP_TX_CSUM_BIT] = "esp-tx-csum-hw-offload", + [NETIF_F_RX_UDP_TUNNEL_PORT_BIT] = "rx-udp_tunnel-port-offload", + [NETIF_F_HW_TLS_RECORD_BIT] = "tls-hw-record", + [NETIF_F_HW_TLS_TX_BIT] = "tls-hw-tx-offload", + [NETIF_F_HW_TLS_RX_BIT] = "tls-hw-rx-offload", + [NETIF_F_GRO_FRAGLIST_BIT] = "rx-gro-list", +}; + +const char +rss_hash_func_strings[ETH_RSS_HASH_FUNCS_COUNT][ETH_GSTRING_LEN] = { + [ETH_RSS_HASH_TOP_BIT] = "toeplitz", + [ETH_RSS_HASH_XOR_BIT] = "xor", + [ETH_RSS_HASH_CRC32_BIT] = "crc32", +}; + +const char +tunable_strings[__ETHTOOL_TUNABLE_COUNT][ETH_GSTRING_LEN] = { + [ETHTOOL_ID_UNSPEC] = "Unspec", + [ETHTOOL_RX_COPYBREAK] = "rx-copybreak", + [ETHTOOL_TX_COPYBREAK] = "tx-copybreak", + [ETHTOOL_PFC_PREVENTION_TOUT] = "pfc-prevention-tout", +}; + +const char +phy_tunable_strings[__ETHTOOL_PHY_TUNABLE_COUNT][ETH_GSTRING_LEN] = { + [ETHTOOL_ID_UNSPEC] = "Unspec", + [ETHTOOL_PHY_DOWNSHIFT] = "phy-downshift", + [ETHTOOL_PHY_FAST_LINK_DOWN] = "phy-fast-link-down", + [ETHTOOL_PHY_EDPD] = "phy-energy-detect-power-down", +}; + +#define __LINK_MODE_NAME(speed, type, duplex) \ + #speed "base" #type "/" #duplex +#define __DEFINE_LINK_MODE_NAME(speed, type, duplex) \ + [ETHTOOL_LINK_MODE(speed, type, duplex)] = \ + __LINK_MODE_NAME(speed, type, duplex) +#define __DEFINE_SPECIAL_MODE_NAME(_mode, _name) \ + [ETHTOOL_LINK_MODE_ ## _mode ## _BIT] = _name + +const char link_mode_names[][ETH_GSTRING_LEN] = { + __DEFINE_LINK_MODE_NAME(10, T, Half), + __DEFINE_LINK_MODE_NAME(10, T, Full), + __DEFINE_LINK_MODE_NAME(100, T, Half), + __DEFINE_LINK_MODE_NAME(100, T, Full), + __DEFINE_LINK_MODE_NAME(1000, T, Half), + __DEFINE_LINK_MODE_NAME(1000, T, Full), + __DEFINE_SPECIAL_MODE_NAME(Autoneg, "Autoneg"), + __DEFINE_SPECIAL_MODE_NAME(TP, "TP"), + __DEFINE_SPECIAL_MODE_NAME(AUI, "AUI"), + __DEFINE_SPECIAL_MODE_NAME(MII, "MII"), + __DEFINE_SPECIAL_MODE_NAME(FIBRE, "FIBRE"), + __DEFINE_SPECIAL_MODE_NAME(BNC, "BNC"), + __DEFINE_LINK_MODE_NAME(10000, T, Full), + __DEFINE_SPECIAL_MODE_NAME(Pause, "Pause"), + __DEFINE_SPECIAL_MODE_NAME(Asym_Pause, "Asym_Pause"), + __DEFINE_LINK_MODE_NAME(2500, X, Full), + __DEFINE_SPECIAL_MODE_NAME(Backplane, "Backplane"), + __DEFINE_LINK_MODE_NAME(1000, KX, Full), + __DEFINE_LINK_MODE_NAME(10000, KX4, Full), + __DEFINE_LINK_MODE_NAME(10000, KR, Full), + __DEFINE_SPECIAL_MODE_NAME(10000baseR_FEC, "10000baseR_FEC"), + __DEFINE_LINK_MODE_NAME(20000, MLD2, Full), + __DEFINE_LINK_MODE_NAME(20000, KR2, Full), + __DEFINE_LINK_MODE_NAME(40000, KR4, Full), + __DEFINE_LINK_MODE_NAME(40000, CR4, Full), + __DEFINE_LINK_MODE_NAME(40000, SR4, Full), + __DEFINE_LINK_MODE_NAME(40000, LR4, Full), + __DEFINE_LINK_MODE_NAME(56000, KR4, Full), + __DEFINE_LINK_MODE_NAME(56000, CR4, Full), + __DEFINE_LINK_MODE_NAME(56000, SR4, Full), + __DEFINE_LINK_MODE_NAME(56000, LR4, Full), + __DEFINE_LINK_MODE_NAME(25000, CR, Full), + __DEFINE_LINK_MODE_NAME(25000, KR, Full), + __DEFINE_LINK_MODE_NAME(25000, SR, Full), + __DEFINE_LINK_MODE_NAME(50000, CR2, Full), + __DEFINE_LINK_MODE_NAME(50000, KR2, Full), + __DEFINE_LINK_MODE_NAME(100000, KR4, Full), + __DEFINE_LINK_MODE_NAME(100000, SR4, Full), + __DEFINE_LINK_MODE_NAME(100000, CR4, Full), + __DEFINE_LINK_MODE_NAME(100000, LR4_ER4, Full), + __DEFINE_LINK_MODE_NAME(50000, SR2, Full), + __DEFINE_LINK_MODE_NAME(1000, X, Full), + __DEFINE_LINK_MODE_NAME(10000, CR, Full), + __DEFINE_LINK_MODE_NAME(10000, SR, Full), + __DEFINE_LINK_MODE_NAME(10000, LR, Full), + __DEFINE_LINK_MODE_NAME(10000, LRM, Full), + __DEFINE_LINK_MODE_NAME(10000, ER, Full), + __DEFINE_LINK_MODE_NAME(2500, T, Full), + __DEFINE_LINK_MODE_NAME(5000, T, Full), + __DEFINE_SPECIAL_MODE_NAME(FEC_NONE, "None"), + __DEFINE_SPECIAL_MODE_NAME(FEC_RS, "RS"), + __DEFINE_SPECIAL_MODE_NAME(FEC_BASER, "BASER"), + __DEFINE_LINK_MODE_NAME(50000, KR, Full), + __DEFINE_LINK_MODE_NAME(50000, SR, Full), + __DEFINE_LINK_MODE_NAME(50000, CR, Full), + __DEFINE_LINK_MODE_NAME(50000, LR_ER_FR, Full), + __DEFINE_LINK_MODE_NAME(50000, DR, Full), + __DEFINE_LINK_MODE_NAME(100000, KR2, Full), + __DEFINE_LINK_MODE_NAME(100000, SR2, Full), + __DEFINE_LINK_MODE_NAME(100000, CR2, Full), + __DEFINE_LINK_MODE_NAME(100000, LR2_ER2_FR2, Full), + __DEFINE_LINK_MODE_NAME(100000, DR2, Full), + __DEFINE_LINK_MODE_NAME(200000, KR4, Full), + __DEFINE_LINK_MODE_NAME(200000, SR4, Full), + __DEFINE_LINK_MODE_NAME(200000, LR4_ER4_FR4, Full), + __DEFINE_LINK_MODE_NAME(200000, DR4, Full), + __DEFINE_LINK_MODE_NAME(200000, CR4, Full), + __DEFINE_LINK_MODE_NAME(100, T1, Full), + __DEFINE_LINK_MODE_NAME(1000, T1, Full), + __DEFINE_LINK_MODE_NAME(400000, KR8, Full), + __DEFINE_LINK_MODE_NAME(400000, SR8, Full), + __DEFINE_LINK_MODE_NAME(400000, LR8_ER8_FR8, Full), + __DEFINE_LINK_MODE_NAME(400000, DR8, Full), + __DEFINE_LINK_MODE_NAME(400000, CR8, Full), +}; +static_assert(ARRAY_SIZE(link_mode_names) == __ETHTOOL_LINK_MODE_MASK_NBITS); + +const char netif_msg_class_names[][ETH_GSTRING_LEN] = { + [NETIF_MSG_DRV_BIT] = "drv", + [NETIF_MSG_PROBE_BIT] = "probe", + [NETIF_MSG_LINK_BIT] = "link", + [NETIF_MSG_TIMER_BIT] = "timer", + [NETIF_MSG_IFDOWN_BIT] = "ifdown", + [NETIF_MSG_IFUP_BIT] = "ifup", + [NETIF_MSG_RX_ERR_BIT] = "rx_err", + [NETIF_MSG_TX_ERR_BIT] = "tx_err", + [NETIF_MSG_TX_QUEUED_BIT] = "tx_queued", + [NETIF_MSG_INTR_BIT] = "intr", + [NETIF_MSG_TX_DONE_BIT] = "tx_done", + [NETIF_MSG_RX_STATUS_BIT] = "rx_status", + [NETIF_MSG_PKTDATA_BIT] = "pktdata", + [NETIF_MSG_HW_BIT] = "hw", + [NETIF_MSG_WOL_BIT] = "wol", +}; +static_assert(ARRAY_SIZE(netif_msg_class_names) == NETIF_MSG_CLASS_COUNT); + +const char wol_mode_names[][ETH_GSTRING_LEN] = { + [const_ilog2(WAKE_PHY)] = "phy", + [const_ilog2(WAKE_UCAST)] = "ucast", + [const_ilog2(WAKE_MCAST)] = "mcast", + [const_ilog2(WAKE_BCAST)] = "bcast", + [const_ilog2(WAKE_ARP)] = "arp", + [const_ilog2(WAKE_MAGIC)] = "magic", + [const_ilog2(WAKE_MAGICSECURE)] = "magicsecure", + [const_ilog2(WAKE_FILTER)] = "filter", +}; +static_assert(ARRAY_SIZE(wol_mode_names) == WOL_MODE_COUNT); + +/* return false if legacy contained non-0 deprecated fields + * maxtxpkt/maxrxpkt. rest of ksettings always updated + */ +bool +convert_legacy_settings_to_link_ksettings( + struct ethtool_link_ksettings *link_ksettings, + const struct ethtool_cmd *legacy_settings) +{ + bool retval = true; + + memset(link_ksettings, 0, sizeof(*link_ksettings)); + + /* This is used to tell users that driver is still using these + * deprecated legacy fields, and they should not use + * %ETHTOOL_GLINKSETTINGS/%ETHTOOL_SLINKSETTINGS + */ + if (legacy_settings->maxtxpkt || + legacy_settings->maxrxpkt) + retval = false; + + ethtool_convert_legacy_u32_to_link_mode( + link_ksettings->link_modes.supported, + legacy_settings->supported); + ethtool_convert_legacy_u32_to_link_mode( + link_ksettings->link_modes.advertising, + legacy_settings->advertising); + ethtool_convert_legacy_u32_to_link_mode( + link_ksettings->link_modes.lp_advertising, + legacy_settings->lp_advertising); + link_ksettings->base.speed + = ethtool_cmd_speed(legacy_settings); + link_ksettings->base.duplex + = legacy_settings->duplex; + link_ksettings->base.port + = legacy_settings->port; + link_ksettings->base.phy_address + = legacy_settings->phy_address; + link_ksettings->base.autoneg + = legacy_settings->autoneg; + link_ksettings->base.mdio_support + = legacy_settings->mdio_support; + link_ksettings->base.eth_tp_mdix + = legacy_settings->eth_tp_mdix; + link_ksettings->base.eth_tp_mdix_ctrl + = legacy_settings->eth_tp_mdix_ctrl; + return retval; +} + +int __ethtool_get_link(struct net_device *dev) +{ + if (!dev->ethtool_ops->get_link) + return -EOPNOTSUPP; + + return netif_running(dev) && dev->ethtool_ops->get_link(dev); +} diff --git a/net/ethtool/common.h b/net/ethtool/common.h new file mode 100644 index 000000000000..40ba74e0b9bb --- /dev/null +++ b/net/ethtool/common.h @@ -0,0 +1,31 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ + +#ifndef _ETHTOOL_COMMON_H +#define _ETHTOOL_COMMON_H + +#include <linux/netdevice.h> +#include <linux/ethtool.h> + +/* compose link mode index from speed, type and duplex */ +#define ETHTOOL_LINK_MODE(speed, type, duplex) \ + ETHTOOL_LINK_MODE_ ## speed ## base ## type ## _ ## duplex ## _BIT + +extern const char +netdev_features_strings[NETDEV_FEATURE_COUNT][ETH_GSTRING_LEN]; +extern const char +rss_hash_func_strings[ETH_RSS_HASH_FUNCS_COUNT][ETH_GSTRING_LEN]; +extern const char +tunable_strings[__ETHTOOL_TUNABLE_COUNT][ETH_GSTRING_LEN]; +extern const char +phy_tunable_strings[__ETHTOOL_PHY_TUNABLE_COUNT][ETH_GSTRING_LEN]; +extern const char link_mode_names[][ETH_GSTRING_LEN]; +extern const char netif_msg_class_names[][ETH_GSTRING_LEN]; +extern const char wol_mode_names[][ETH_GSTRING_LEN]; + +int __ethtool_get_link(struct net_device *dev); + +bool convert_legacy_settings_to_link_ksettings( + struct ethtool_link_ksettings *link_ksettings, + const struct ethtool_cmd *legacy_settings); + +#endif /* _ETHTOOL_COMMON_H */ diff --git a/net/ethtool/debug.c b/net/ethtool/debug.c new file mode 100644 index 000000000000..aaef4843e6ba --- /dev/null +++ b/net/ethtool/debug.c @@ -0,0 +1,134 @@ +// SPDX-License-Identifier: GPL-2.0-only + +#include "netlink.h" +#include "common.h" +#include "bitset.h" + +struct debug_req_info { + struct ethnl_req_info base; +}; + +struct debug_reply_data { + struct ethnl_reply_data base; + u32 msg_mask; +}; + +#define DEBUG_REPDATA(__reply_base) \ + container_of(__reply_base, struct debug_reply_data, base) + +static const struct nla_policy +debug_get_policy[ETHTOOL_A_DEBUG_MAX + 1] = { + [ETHTOOL_A_DEBUG_UNSPEC] = { .type = NLA_REJECT }, + [ETHTOOL_A_DEBUG_HEADER] = { .type = NLA_NESTED }, + [ETHTOOL_A_DEBUG_MSGMASK] = { .type = NLA_REJECT }, +}; + +static int debug_prepare_data(const struct ethnl_req_info *req_base, + struct ethnl_reply_data *reply_base, + struct genl_info *info) +{ + struct debug_reply_data *data = DEBUG_REPDATA(reply_base); + struct net_device *dev = reply_base->dev; + int ret; + + if (!dev->ethtool_ops->get_msglevel) + return -EOPNOTSUPP; + + ret = ethnl_ops_begin(dev); + if (ret < 0) + return ret; + data->msg_mask = dev->ethtool_ops->get_msglevel(dev); + ethnl_ops_complete(dev); + + return 0; +} + +static int debug_reply_size(const struct ethnl_req_info *req_base, + const struct ethnl_reply_data *reply_base) +{ + const struct debug_reply_data *data = DEBUG_REPDATA(reply_base); + bool compact = req_base->flags & ETHTOOL_FLAG_COMPACT_BITSETS; + + return ethnl_bitset32_size(&data->msg_mask, NULL, NETIF_MSG_CLASS_COUNT, + netif_msg_class_names, compact); +} + +static int debug_fill_reply(struct sk_buff *skb, + const struct ethnl_req_info *req_base, + const struct ethnl_reply_data *reply_base) +{ + const struct debug_reply_data *data = DEBUG_REPDATA(reply_base); + bool compact = req_base->flags & ETHTOOL_FLAG_COMPACT_BITSETS; + + return ethnl_put_bitset32(skb, ETHTOOL_A_DEBUG_MSGMASK, &data->msg_mask, + NULL, NETIF_MSG_CLASS_COUNT, + netif_msg_class_names, compact); +} + +const struct ethnl_request_ops ethnl_debug_request_ops = { + .request_cmd = ETHTOOL_MSG_DEBUG_GET, + .reply_cmd = ETHTOOL_MSG_DEBUG_GET_REPLY, + .hdr_attr = ETHTOOL_A_DEBUG_HEADER, + .max_attr = ETHTOOL_A_DEBUG_MAX, + .req_info_size = sizeof(struct debug_req_info), + .reply_data_size = sizeof(struct debug_reply_data), + .request_policy = debug_get_policy, + + .prepare_data = debug_prepare_data, + .reply_size = debug_reply_size, + .fill_reply = debug_fill_reply, +}; + +/* DEBUG_SET */ + +static const struct nla_policy +debug_set_policy[ETHTOOL_A_DEBUG_MAX + 1] = { + [ETHTOOL_A_DEBUG_UNSPEC] = { .type = NLA_REJECT }, + [ETHTOOL_A_DEBUG_HEADER] = { .type = NLA_NESTED }, + [ETHTOOL_A_DEBUG_MSGMASK] = { .type = NLA_NESTED }, +}; + +int ethnl_set_debug(struct sk_buff *skb, struct genl_info *info) +{ + struct nlattr *tb[ETHTOOL_A_DEBUG_MAX + 1]; + struct ethnl_req_info req_info = {}; + struct net_device *dev; + bool mod = false; + u32 msg_mask; + int ret; + + ret = nlmsg_parse(info->nlhdr, GENL_HDRLEN, tb, + ETHTOOL_A_DEBUG_MAX, debug_set_policy, + info->extack); + if (ret < 0) + return ret; + ret = ethnl_parse_header(&req_info, tb[ETHTOOL_A_DEBUG_HEADER], + genl_info_net(info), info->extack, true); + if (ret < 0) + return ret; + dev = req_info.dev; + if (!dev->ethtool_ops->get_msglevel || !dev->ethtool_ops->set_msglevel) + return -EOPNOTSUPP; + + rtnl_lock(); + ret = ethnl_ops_begin(dev); + if (ret < 0) + goto out_rtnl; + + msg_mask = dev->ethtool_ops->get_msglevel(dev); + ret = ethnl_update_bitset32(&msg_mask, NETIF_MSG_CLASS_COUNT, + tb[ETHTOOL_A_DEBUG_MSGMASK], + netif_msg_class_names, info->extack, &mod); + if (ret < 0 || !mod) + goto out_ops; + + dev->ethtool_ops->set_msglevel(dev, msg_mask); + ethtool_notify(dev, ETHTOOL_MSG_DEBUG_NTF, NULL); + +out_ops: + ethnl_ops_complete(dev); +out_rtnl: + rtnl_unlock(); + dev_put(dev); + return ret; +} diff --git a/net/core/ethtool.c b/net/ethtool/ioctl.c index cd9bc67381b2..b987052d91ef 100644 --- a/net/core/ethtool.c +++ b/net/ethtool/ioctl.c @@ -17,6 +17,7 @@ #include <linux/phy.h> #include <linux/bitops.h> #include <linux/uaccess.h> +#include <linux/vermagic.h> #include <linux/vmalloc.h> #include <linux/sfp.h> #include <linux/slab.h> @@ -26,6 +27,9 @@ #include <net/devlink.h> #include <net/xdp_sock.h> #include <net/flow_offload.h> +#include <linux/ethtool_netlink.h> + +#include "common.h" /* * Some useful ethtool_ops methods that're device independent. @@ -54,88 +58,6 @@ EXPORT_SYMBOL(ethtool_op_get_ts_info); #define ETHTOOL_DEV_FEATURE_WORDS ((NETDEV_FEATURE_COUNT + 31) / 32) -static const char netdev_features_strings[NETDEV_FEATURE_COUNT][ETH_GSTRING_LEN] = { - [NETIF_F_SG_BIT] = "tx-scatter-gather", - [NETIF_F_IP_CSUM_BIT] = "tx-checksum-ipv4", - [NETIF_F_HW_CSUM_BIT] = "tx-checksum-ip-generic", - [NETIF_F_IPV6_CSUM_BIT] = "tx-checksum-ipv6", - [NETIF_F_HIGHDMA_BIT] = "highdma", - [NETIF_F_FRAGLIST_BIT] = "tx-scatter-gather-fraglist", - [NETIF_F_HW_VLAN_CTAG_TX_BIT] = "tx-vlan-hw-insert", - - [NETIF_F_HW_VLAN_CTAG_RX_BIT] = "rx-vlan-hw-parse", - [NETIF_F_HW_VLAN_CTAG_FILTER_BIT] = "rx-vlan-filter", - [NETIF_F_HW_VLAN_STAG_TX_BIT] = "tx-vlan-stag-hw-insert", - [NETIF_F_HW_VLAN_STAG_RX_BIT] = "rx-vlan-stag-hw-parse", - [NETIF_F_HW_VLAN_STAG_FILTER_BIT] = "rx-vlan-stag-filter", - [NETIF_F_VLAN_CHALLENGED_BIT] = "vlan-challenged", - [NETIF_F_GSO_BIT] = "tx-generic-segmentation", - [NETIF_F_LLTX_BIT] = "tx-lockless", - [NETIF_F_NETNS_LOCAL_BIT] = "netns-local", - [NETIF_F_GRO_BIT] = "rx-gro", - [NETIF_F_GRO_HW_BIT] = "rx-gro-hw", - [NETIF_F_LRO_BIT] = "rx-lro", - - [NETIF_F_TSO_BIT] = "tx-tcp-segmentation", - [NETIF_F_GSO_ROBUST_BIT] = "tx-gso-robust", - [NETIF_F_TSO_ECN_BIT] = "tx-tcp-ecn-segmentation", - [NETIF_F_TSO_MANGLEID_BIT] = "tx-tcp-mangleid-segmentation", - [NETIF_F_TSO6_BIT] = "tx-tcp6-segmentation", - [NETIF_F_FSO_BIT] = "tx-fcoe-segmentation", - [NETIF_F_GSO_GRE_BIT] = "tx-gre-segmentation", - [NETIF_F_GSO_GRE_CSUM_BIT] = "tx-gre-csum-segmentation", - [NETIF_F_GSO_IPXIP4_BIT] = "tx-ipxip4-segmentation", - [NETIF_F_GSO_IPXIP6_BIT] = "tx-ipxip6-segmentation", - [NETIF_F_GSO_UDP_TUNNEL_BIT] = "tx-udp_tnl-segmentation", - [NETIF_F_GSO_UDP_TUNNEL_CSUM_BIT] = "tx-udp_tnl-csum-segmentation", - [NETIF_F_GSO_PARTIAL_BIT] = "tx-gso-partial", - [NETIF_F_GSO_SCTP_BIT] = "tx-sctp-segmentation", - [NETIF_F_GSO_ESP_BIT] = "tx-esp-segmentation", - [NETIF_F_GSO_UDP_L4_BIT] = "tx-udp-segmentation", - - [NETIF_F_FCOE_CRC_BIT] = "tx-checksum-fcoe-crc", - [NETIF_F_SCTP_CRC_BIT] = "tx-checksum-sctp", - [NETIF_F_FCOE_MTU_BIT] = "fcoe-mtu", - [NETIF_F_NTUPLE_BIT] = "rx-ntuple-filter", - [NETIF_F_RXHASH_BIT] = "rx-hashing", - [NETIF_F_RXCSUM_BIT] = "rx-checksum", - [NETIF_F_NOCACHE_COPY_BIT] = "tx-nocache-copy", - [NETIF_F_LOOPBACK_BIT] = "loopback", - [NETIF_F_RXFCS_BIT] = "rx-fcs", - [NETIF_F_RXALL_BIT] = "rx-all", - [NETIF_F_HW_L2FW_DOFFLOAD_BIT] = "l2-fwd-offload", - [NETIF_F_HW_TC_BIT] = "hw-tc-offload", - [NETIF_F_HW_ESP_BIT] = "esp-hw-offload", - [NETIF_F_HW_ESP_TX_CSUM_BIT] = "esp-tx-csum-hw-offload", - [NETIF_F_RX_UDP_TUNNEL_PORT_BIT] = "rx-udp_tunnel-port-offload", - [NETIF_F_HW_TLS_RECORD_BIT] = "tls-hw-record", - [NETIF_F_HW_TLS_TX_BIT] = "tls-hw-tx-offload", - [NETIF_F_HW_TLS_RX_BIT] = "tls-hw-rx-offload", -}; - -static const char -rss_hash_func_strings[ETH_RSS_HASH_FUNCS_COUNT][ETH_GSTRING_LEN] = { - [ETH_RSS_HASH_TOP_BIT] = "toeplitz", - [ETH_RSS_HASH_XOR_BIT] = "xor", - [ETH_RSS_HASH_CRC32_BIT] = "crc32", -}; - -static const char -tunable_strings[__ETHTOOL_TUNABLE_COUNT][ETH_GSTRING_LEN] = { - [ETHTOOL_ID_UNSPEC] = "Unspec", - [ETHTOOL_RX_COPYBREAK] = "rx-copybreak", - [ETHTOOL_TX_COPYBREAK] = "tx-copybreak", - [ETHTOOL_PFC_PREVENTION_TOUT] = "pfc-prevention-tout", -}; - -static const char -phy_tunable_strings[__ETHTOOL_PHY_TUNABLE_COUNT][ETH_GSTRING_LEN] = { - [ETHTOOL_ID_UNSPEC] = "Unspec", - [ETHTOOL_PHY_DOWNSHIFT] = "phy-downshift", - [ETHTOOL_PHY_FAST_LINK_DOWN] = "phy-fast-link-down", - [ETHTOOL_PHY_EDPD] = "phy-energy-detect-power-down", -}; - static int ethtool_get_features(struct net_device *dev, void __user *useraddr) { struct ethtool_gfeatures cmd = { @@ -234,6 +156,9 @@ static int __ethtool_get_sset_count(struct net_device *dev, int sset) !ops->get_ethtool_phy_stats) return phy_ethtool_get_sset_count(dev->phydev); + if (sset == ETH_SS_LINK_MODES) + return __ETHTOOL_LINK_MODE_MASK_NBITS; + if (ops->get_sset_count && ops->get_strings) return ops->get_sset_count(dev, sset); else @@ -258,6 +183,9 @@ static void __ethtool_get_strings(struct net_device *dev, else if (stringset == ETH_SS_PHY_STATS && dev->phydev && !ops->get_ethtool_phy_stats) phy_ethtool_get_strings(dev->phydev, data); + else if (stringset == ETH_SS_LINK_MODES) + memcpy(data, link_mode_names, + __ETHTOOL_LINK_MODE_MASK_NBITS * ETH_GSTRING_LEN); else /* ops->get_strings is valid because checked earlier */ ops->get_strings(dev, stringset, data); @@ -432,54 +360,6 @@ bool ethtool_convert_link_mode_to_legacy_u32(u32 *legacy_u32, } EXPORT_SYMBOL(ethtool_convert_link_mode_to_legacy_u32); -/* return false if legacy contained non-0 deprecated fields - * maxtxpkt/maxrxpkt. rest of ksettings always updated - */ -static bool -convert_legacy_settings_to_link_ksettings( - struct ethtool_link_ksettings *link_ksettings, - const struct ethtool_cmd *legacy_settings) -{ - bool retval = true; - - memset(link_ksettings, 0, sizeof(*link_ksettings)); - - /* This is used to tell users that driver is still using these - * deprecated legacy fields, and they should not use - * %ETHTOOL_GLINKSETTINGS/%ETHTOOL_SLINKSETTINGS - */ - if (legacy_settings->maxtxpkt || - legacy_settings->maxrxpkt) - retval = false; - - ethtool_convert_legacy_u32_to_link_mode( - link_ksettings->link_modes.supported, - legacy_settings->supported); - ethtool_convert_legacy_u32_to_link_mode( - link_ksettings->link_modes.advertising, - legacy_settings->advertising); - ethtool_convert_legacy_u32_to_link_mode( - link_ksettings->link_modes.lp_advertising, - legacy_settings->lp_advertising); - link_ksettings->base.speed - = ethtool_cmd_speed(legacy_settings); - link_ksettings->base.duplex - = legacy_settings->duplex; - link_ksettings->base.port - = legacy_settings->port; - link_ksettings->base.phy_address - = legacy_settings->phy_address; - link_ksettings->base.autoneg - = legacy_settings->autoneg; - link_ksettings->base.mdio_support - = legacy_settings->mdio_support; - link_ksettings->base.eth_tp_mdix - = legacy_settings->eth_tp_mdix; - link_ksettings->base.eth_tp_mdix_ctrl - = legacy_settings->eth_tp_mdix_ctrl; - return retval; -} - /* return false if ksettings link modes had higher bits * set. legacy_settings always updated (best effort) */ @@ -693,7 +573,12 @@ static int ethtool_set_link_ksettings(struct net_device *dev, != link_ksettings.base.link_mode_masks_nwords) return -EINVAL; - return dev->ethtool_ops->set_link_ksettings(dev, &link_ksettings); + err = dev->ethtool_ops->set_link_ksettings(dev, &link_ksettings); + if (err >= 0) { + ethtool_notify(dev, ETHTOOL_MSG_LINKINFO_NTF, NULL); + ethtool_notify(dev, ETHTOOL_MSG_LINKMODES_NTF, NULL); + } + return err; } /* Query device for its ethtool_cmd settings. @@ -742,6 +627,7 @@ static int ethtool_set_settings(struct net_device *dev, void __user *useraddr) { struct ethtool_link_ksettings link_ksettings; struct ethtool_cmd cmd; + int ret; ASSERT_RTNL(); @@ -754,7 +640,12 @@ static int ethtool_set_settings(struct net_device *dev, void __user *useraddr) return -EINVAL; link_ksettings.base.link_mode_masks_nwords = __ETHTOOL_LINK_MODE_MASK_NU32; - return dev->ethtool_ops->set_link_ksettings(dev, &link_ksettings); + ret = dev->ethtool_ops->set_link_ksettings(dev, &link_ksettings); + if (ret >= 0) { + ethtool_notify(dev, ETHTOOL_MSG_LINKINFO_NTF, NULL); + ethtool_notify(dev, ETHTOOL_MSG_LINKMODES_NTF, NULL); + } + return ret; } static noinline_for_stack int ethtool_get_drvinfo(struct net_device *dev, @@ -765,6 +656,7 @@ static noinline_for_stack int ethtool_get_drvinfo(struct net_device *dev, memset(&info, 0, sizeof(info)); info.cmd = ETHTOOL_GDRVINFO; + strlcpy(info.version, UTS_RELEASE, sizeof(info.version)); if (ops->get_drvinfo) { ops->get_drvinfo(dev, &info); } else if (dev->dev.parent && dev->dev.parent->driver) { @@ -1426,6 +1318,7 @@ static int ethtool_set_wol(struct net_device *dev, char __user *useraddr) return ret; dev->wol_enabled = !!wol.wolopts; + ethtool_notify(dev, ETHTOOL_MSG_WOL_NTF, NULL); return 0; } @@ -1475,12 +1368,12 @@ static int ethtool_nway_reset(struct net_device *dev) static int ethtool_get_link(struct net_device *dev, char __user *useraddr) { struct ethtool_value edata = { .cmd = ETHTOOL_GLINK }; + int link = __ethtool_get_link(dev); - if (!dev->ethtool_ops->get_link) - return -EOPNOTSUPP; - - edata.data = netif_running(dev) && dev->ethtool_ops->get_link(dev); + if (link < 0) + return link; + edata.data = link; if (copy_to_user(useraddr, &edata, sizeof(edata))) return -EFAULT; return 0; @@ -2170,8 +2063,8 @@ static int ethtool_get_ts_info(struct net_device *dev, void __user *useraddr) memset(&info, 0, sizeof(info)); info.cmd = ETHTOOL_GET_TS_INFO; - if (phydev && phydev->drv && phydev->drv->ts_info) { - err = phydev->drv->ts_info(phydev, &info); + if (phy_has_tsinfo(phydev)) { + err = phy_ts_info(phydev, &info); } else if (ops->get_ts_info) { err = ops->get_ts_info(dev, &info); } else { @@ -2655,6 +2548,8 @@ int dev_ethtool(struct net *net, struct ifreq *ifr) case ETHTOOL_SMSGLVL: rc = ethtool_set_value_void(dev, useraddr, dev->ethtool_ops->set_msglevel); + if (!rc) + ethtool_notify(dev, ETHTOOL_MSG_DEBUG_NTF, NULL); break; case ETHTOOL_GEEE: rc = ethtool_get_eee(dev, useraddr); diff --git a/net/ethtool/linkinfo.c b/net/ethtool/linkinfo.c new file mode 100644 index 000000000000..5d16cb4e8693 --- /dev/null +++ b/net/ethtool/linkinfo.c @@ -0,0 +1,167 @@ +// SPDX-License-Identifier: GPL-2.0-only + +#include "netlink.h" +#include "common.h" + +struct linkinfo_req_info { + struct ethnl_req_info base; +}; + +struct linkinfo_reply_data { + struct ethnl_reply_data base; + struct ethtool_link_ksettings ksettings; + struct ethtool_link_settings *lsettings; +}; + +#define LINKINFO_REPDATA(__reply_base) \ + container_of(__reply_base, struct linkinfo_reply_data, base) + +static const struct nla_policy +linkinfo_get_policy[ETHTOOL_A_LINKINFO_MAX + 1] = { + [ETHTOOL_A_LINKINFO_UNSPEC] = { .type = NLA_REJECT }, + [ETHTOOL_A_LINKINFO_HEADER] = { .type = NLA_NESTED }, + [ETHTOOL_A_LINKINFO_PORT] = { .type = NLA_REJECT }, + [ETHTOOL_A_LINKINFO_PHYADDR] = { .type = NLA_REJECT }, + [ETHTOOL_A_LINKINFO_TP_MDIX] = { .type = NLA_REJECT }, + [ETHTOOL_A_LINKINFO_TP_MDIX_CTRL] = { .type = NLA_REJECT }, + [ETHTOOL_A_LINKINFO_TRANSCEIVER] = { .type = NLA_REJECT }, +}; + +static int linkinfo_prepare_data(const struct ethnl_req_info *req_base, + struct ethnl_reply_data *reply_base, + struct genl_info *info) +{ + struct linkinfo_reply_data *data = LINKINFO_REPDATA(reply_base); + struct net_device *dev = reply_base->dev; + int ret; + + data->lsettings = &data->ksettings.base; + + ret = ethnl_ops_begin(dev); + if (ret < 0) + return ret; + ret = __ethtool_get_link_ksettings(dev, &data->ksettings); + if (ret < 0 && info) + GENL_SET_ERR_MSG(info, "failed to retrieve link settings"); + ethnl_ops_complete(dev); + + return ret; +} + +static int linkinfo_reply_size(const struct ethnl_req_info *req_base, + const struct ethnl_reply_data *reply_base) +{ + return nla_total_size(sizeof(u8)) /* LINKINFO_PORT */ + + nla_total_size(sizeof(u8)) /* LINKINFO_PHYADDR */ + + nla_total_size(sizeof(u8)) /* LINKINFO_TP_MDIX */ + + nla_total_size(sizeof(u8)) /* LINKINFO_TP_MDIX_CTRL */ + + nla_total_size(sizeof(u8)) /* LINKINFO_TRANSCEIVER */ + + 0; +} + +static int linkinfo_fill_reply(struct sk_buff *skb, + const struct ethnl_req_info *req_base, + const struct ethnl_reply_data *reply_base) +{ + const struct linkinfo_reply_data *data = LINKINFO_REPDATA(reply_base); + + if (nla_put_u8(skb, ETHTOOL_A_LINKINFO_PORT, data->lsettings->port) || + nla_put_u8(skb, ETHTOOL_A_LINKINFO_PHYADDR, + data->lsettings->phy_address) || + nla_put_u8(skb, ETHTOOL_A_LINKINFO_TP_MDIX, + data->lsettings->eth_tp_mdix) || + nla_put_u8(skb, ETHTOOL_A_LINKINFO_TP_MDIX_CTRL, + data->lsettings->eth_tp_mdix_ctrl) || + nla_put_u8(skb, ETHTOOL_A_LINKINFO_TRANSCEIVER, + data->lsettings->transceiver)) + return -EMSGSIZE; + + return 0; +} + +const struct ethnl_request_ops ethnl_linkinfo_request_ops = { + .request_cmd = ETHTOOL_MSG_LINKINFO_GET, + .reply_cmd = ETHTOOL_MSG_LINKINFO_GET_REPLY, + .hdr_attr = ETHTOOL_A_LINKINFO_HEADER, + .max_attr = ETHTOOL_A_LINKINFO_MAX, + .req_info_size = sizeof(struct linkinfo_req_info), + .reply_data_size = sizeof(struct linkinfo_reply_data), + .request_policy = linkinfo_get_policy, + + .prepare_data = linkinfo_prepare_data, + .reply_size = linkinfo_reply_size, + .fill_reply = linkinfo_fill_reply, +}; + +/* LINKINFO_SET */ + +static const struct nla_policy +linkinfo_set_policy[ETHTOOL_A_LINKINFO_MAX + 1] = { + [ETHTOOL_A_LINKINFO_UNSPEC] = { .type = NLA_REJECT }, + [ETHTOOL_A_LINKINFO_HEADER] = { .type = NLA_NESTED }, + [ETHTOOL_A_LINKINFO_PORT] = { .type = NLA_U8 }, + [ETHTOOL_A_LINKINFO_PHYADDR] = { .type = NLA_U8 }, + [ETHTOOL_A_LINKINFO_TP_MDIX] = { .type = NLA_REJECT }, + [ETHTOOL_A_LINKINFO_TP_MDIX_CTRL] = { .type = NLA_U8 }, + [ETHTOOL_A_LINKINFO_TRANSCEIVER] = { .type = NLA_REJECT }, +}; + +int ethnl_set_linkinfo(struct sk_buff *skb, struct genl_info *info) +{ + struct nlattr *tb[ETHTOOL_A_LINKINFO_MAX + 1]; + struct ethtool_link_ksettings ksettings = {}; + struct ethtool_link_settings *lsettings; + struct ethnl_req_info req_info = {}; + struct net_device *dev; + bool mod = false; + int ret; + + ret = nlmsg_parse(info->nlhdr, GENL_HDRLEN, tb, + ETHTOOL_A_LINKINFO_MAX, linkinfo_set_policy, + info->extack); + if (ret < 0) + return ret; + ret = ethnl_parse_header(&req_info, tb[ETHTOOL_A_LINKINFO_HEADER], + genl_info_net(info), info->extack, true); + if (ret < 0) + return ret; + dev = req_info.dev; + if (!dev->ethtool_ops->get_link_ksettings || + !dev->ethtool_ops->set_link_ksettings) + return -EOPNOTSUPP; + + rtnl_lock(); + ret = ethnl_ops_begin(dev); + if (ret < 0) + goto out_rtnl; + + ret = __ethtool_get_link_ksettings(dev, &ksettings); + if (ret < 0) { + if (info) + GENL_SET_ERR_MSG(info, "failed to retrieve link settings"); + goto out_ops; + } + lsettings = &ksettings.base; + + ethnl_update_u8(&lsettings->port, tb[ETHTOOL_A_LINKINFO_PORT], &mod); + ethnl_update_u8(&lsettings->phy_address, tb[ETHTOOL_A_LINKINFO_PHYADDR], + &mod); + ethnl_update_u8(&lsettings->eth_tp_mdix_ctrl, + tb[ETHTOOL_A_LINKINFO_TP_MDIX_CTRL], &mod); + ret = 0; + if (!mod) + goto out_ops; + + ret = dev->ethtool_ops->set_link_ksettings(dev, &ksettings); + if (ret < 0) + GENL_SET_ERR_MSG(info, "link settings update failed"); + else + ethtool_notify(dev, ETHTOOL_MSG_LINKINFO_NTF, NULL); + +out_ops: + ethnl_ops_complete(dev); +out_rtnl: + rtnl_unlock(); + dev_put(dev); + return ret; +} diff --git a/net/ethtool/linkmodes.c b/net/ethtool/linkmodes.c new file mode 100644 index 000000000000..96f20be64553 --- /dev/null +++ b/net/ethtool/linkmodes.c @@ -0,0 +1,375 @@ +// SPDX-License-Identifier: GPL-2.0-only + +#include "netlink.h" +#include "common.h" +#include "bitset.h" + +struct linkmodes_req_info { + struct ethnl_req_info base; +}; + +struct linkmodes_reply_data { + struct ethnl_reply_data base; + struct ethtool_link_ksettings ksettings; + struct ethtool_link_settings *lsettings; + bool peer_empty; +}; + +#define LINKMODES_REPDATA(__reply_base) \ + container_of(__reply_base, struct linkmodes_reply_data, base) + +static const struct nla_policy +linkmodes_get_policy[ETHTOOL_A_LINKMODES_MAX + 1] = { + [ETHTOOL_A_LINKMODES_UNSPEC] = { .type = NLA_REJECT }, + [ETHTOOL_A_LINKMODES_HEADER] = { .type = NLA_NESTED }, + [ETHTOOL_A_LINKMODES_AUTONEG] = { .type = NLA_REJECT }, + [ETHTOOL_A_LINKMODES_OURS] = { .type = NLA_REJECT }, + [ETHTOOL_A_LINKMODES_PEER] = { .type = NLA_REJECT }, + [ETHTOOL_A_LINKMODES_SPEED] = { .type = NLA_REJECT }, + [ETHTOOL_A_LINKMODES_DUPLEX] = { .type = NLA_REJECT }, +}; + +static int linkmodes_prepare_data(const struct ethnl_req_info *req_base, + struct ethnl_reply_data *reply_base, + struct genl_info *info) +{ + struct linkmodes_reply_data *data = LINKMODES_REPDATA(reply_base); + struct net_device *dev = reply_base->dev; + int ret; + + data->lsettings = &data->ksettings.base; + + ret = ethnl_ops_begin(dev); + if (ret < 0) + return ret; + + ret = __ethtool_get_link_ksettings(dev, &data->ksettings); + if (ret < 0 && info) { + GENL_SET_ERR_MSG(info, "failed to retrieve link settings"); + goto out; + } + + data->peer_empty = + bitmap_empty(data->ksettings.link_modes.lp_advertising, + __ETHTOOL_LINK_MODE_MASK_NBITS); + +out: + ethnl_ops_complete(dev); + return ret; +} + +static int linkmodes_reply_size(const struct ethnl_req_info *req_base, + const struct ethnl_reply_data *reply_base) +{ + const struct linkmodes_reply_data *data = LINKMODES_REPDATA(reply_base); + const struct ethtool_link_ksettings *ksettings = &data->ksettings; + bool compact = req_base->flags & ETHTOOL_FLAG_COMPACT_BITSETS; + int len, ret; + + len = nla_total_size(sizeof(u8)) /* LINKMODES_AUTONEG */ + + nla_total_size(sizeof(u32)) /* LINKMODES_SPEED */ + + nla_total_size(sizeof(u8)) /* LINKMODES_DUPLEX */ + + 0; + ret = ethnl_bitset_size(ksettings->link_modes.advertising, + ksettings->link_modes.supported, + __ETHTOOL_LINK_MODE_MASK_NBITS, + link_mode_names, compact); + if (ret < 0) + return ret; + len += ret; + if (!data->peer_empty) { + ret = ethnl_bitset_size(ksettings->link_modes.lp_advertising, + NULL, __ETHTOOL_LINK_MODE_MASK_NBITS, + link_mode_names, compact); + if (ret < 0) + return ret; + len += ret; + } + + return len; +} + +static int linkmodes_fill_reply(struct sk_buff *skb, + const struct ethnl_req_info *req_base, + const struct ethnl_reply_data *reply_base) +{ + const struct linkmodes_reply_data *data = LINKMODES_REPDATA(reply_base); + const struct ethtool_link_ksettings *ksettings = &data->ksettings; + const struct ethtool_link_settings *lsettings = &ksettings->base; + bool compact = req_base->flags & ETHTOOL_FLAG_COMPACT_BITSETS; + int ret; + + if (nla_put_u8(skb, ETHTOOL_A_LINKMODES_AUTONEG, lsettings->autoneg)) + return -EMSGSIZE; + + ret = ethnl_put_bitset(skb, ETHTOOL_A_LINKMODES_OURS, + ksettings->link_modes.advertising, + ksettings->link_modes.supported, + __ETHTOOL_LINK_MODE_MASK_NBITS, link_mode_names, + compact); + if (ret < 0) + return -EMSGSIZE; + if (!data->peer_empty) { + ret = ethnl_put_bitset(skb, ETHTOOL_A_LINKMODES_PEER, + ksettings->link_modes.lp_advertising, + NULL, __ETHTOOL_LINK_MODE_MASK_NBITS, + link_mode_names, compact); + if (ret < 0) + return -EMSGSIZE; + } + + if (nla_put_u32(skb, ETHTOOL_A_LINKMODES_SPEED, lsettings->speed) || + nla_put_u8(skb, ETHTOOL_A_LINKMODES_DUPLEX, lsettings->duplex)) + return -EMSGSIZE; + + return 0; +} + +const struct ethnl_request_ops ethnl_linkmodes_request_ops = { + .request_cmd = ETHTOOL_MSG_LINKMODES_GET, + .reply_cmd = ETHTOOL_MSG_LINKMODES_GET_REPLY, + .hdr_attr = ETHTOOL_A_LINKMODES_HEADER, + .max_attr = ETHTOOL_A_LINKMODES_MAX, + .req_info_size = sizeof(struct linkmodes_req_info), + .reply_data_size = sizeof(struct linkmodes_reply_data), + .request_policy = linkmodes_get_policy, + + .prepare_data = linkmodes_prepare_data, + .reply_size = linkmodes_reply_size, + .fill_reply = linkmodes_fill_reply, +}; + +/* LINKMODES_SET */ + +struct link_mode_info { + int speed; + u8 duplex; +}; + +#define __DEFINE_LINK_MODE_PARAMS(_speed, _type, _duplex) \ + [ETHTOOL_LINK_MODE(_speed, _type, _duplex)] = { \ + .speed = SPEED_ ## _speed, \ + .duplex = __DUPLEX_ ## _duplex \ + } +#define __DUPLEX_Half DUPLEX_HALF +#define __DUPLEX_Full DUPLEX_FULL +#define __DEFINE_SPECIAL_MODE_PARAMS(_mode) \ + [ETHTOOL_LINK_MODE_ ## _mode ## _BIT] = { \ + .speed = SPEED_UNKNOWN, \ + .duplex = DUPLEX_UNKNOWN, \ + } + +static const struct link_mode_info link_mode_params[] = { + __DEFINE_LINK_MODE_PARAMS(10, T, Half), + __DEFINE_LINK_MODE_PARAMS(10, T, Full), + __DEFINE_LINK_MODE_PARAMS(100, T, Half), + __DEFINE_LINK_MODE_PARAMS(100, T, Full), + __DEFINE_LINK_MODE_PARAMS(1000, T, Half), + __DEFINE_LINK_MODE_PARAMS(1000, T, Full), + __DEFINE_SPECIAL_MODE_PARAMS(Autoneg), + __DEFINE_SPECIAL_MODE_PARAMS(TP), + __DEFINE_SPECIAL_MODE_PARAMS(AUI), + __DEFINE_SPECIAL_MODE_PARAMS(MII), + __DEFINE_SPECIAL_MODE_PARAMS(FIBRE), + __DEFINE_SPECIAL_MODE_PARAMS(BNC), + __DEFINE_LINK_MODE_PARAMS(10000, T, Full), + __DEFINE_SPECIAL_MODE_PARAMS(Pause), + __DEFINE_SPECIAL_MODE_PARAMS(Asym_Pause), + __DEFINE_LINK_MODE_PARAMS(2500, X, Full), + __DEFINE_SPECIAL_MODE_PARAMS(Backplane), + __DEFINE_LINK_MODE_PARAMS(1000, KX, Full), + __DEFINE_LINK_MODE_PARAMS(10000, KX4, Full), + __DEFINE_LINK_MODE_PARAMS(10000, KR, Full), + [ETHTOOL_LINK_MODE_10000baseR_FEC_BIT] = { + .speed = SPEED_10000, + .duplex = DUPLEX_FULL, + }, + __DEFINE_LINK_MODE_PARAMS(20000, MLD2, Full), + __DEFINE_LINK_MODE_PARAMS(20000, KR2, Full), + __DEFINE_LINK_MODE_PARAMS(40000, KR4, Full), + __DEFINE_LINK_MODE_PARAMS(40000, CR4, Full), + __DEFINE_LINK_MODE_PARAMS(40000, SR4, Full), + __DEFINE_LINK_MODE_PARAMS(40000, LR4, Full), + __DEFINE_LINK_MODE_PARAMS(56000, KR4, Full), + __DEFINE_LINK_MODE_PARAMS(56000, CR4, Full), + __DEFINE_LINK_MODE_PARAMS(56000, SR4, Full), + __DEFINE_LINK_MODE_PARAMS(56000, LR4, Full), + __DEFINE_LINK_MODE_PARAMS(25000, CR, Full), + __DEFINE_LINK_MODE_PARAMS(25000, KR, Full), + __DEFINE_LINK_MODE_PARAMS(25000, SR, Full), + __DEFINE_LINK_MODE_PARAMS(50000, CR2, Full), + __DEFINE_LINK_MODE_PARAMS(50000, KR2, Full), + __DEFINE_LINK_MODE_PARAMS(100000, KR4, Full), + __DEFINE_LINK_MODE_PARAMS(100000, SR4, Full), + __DEFINE_LINK_MODE_PARAMS(100000, CR4, Full), + __DEFINE_LINK_MODE_PARAMS(100000, LR4_ER4, Full), + __DEFINE_LINK_MODE_PARAMS(50000, SR2, Full), + __DEFINE_LINK_MODE_PARAMS(1000, X, Full), + __DEFINE_LINK_MODE_PARAMS(10000, CR, Full), + __DEFINE_LINK_MODE_PARAMS(10000, SR, Full), + __DEFINE_LINK_MODE_PARAMS(10000, LR, Full), + __DEFINE_LINK_MODE_PARAMS(10000, LRM, Full), + __DEFINE_LINK_MODE_PARAMS(10000, ER, Full), + __DEFINE_LINK_MODE_PARAMS(2500, T, Full), + __DEFINE_LINK_MODE_PARAMS(5000, T, Full), + __DEFINE_SPECIAL_MODE_PARAMS(FEC_NONE), + __DEFINE_SPECIAL_MODE_PARAMS(FEC_RS), + __DEFINE_SPECIAL_MODE_PARAMS(FEC_BASER), + __DEFINE_LINK_MODE_PARAMS(50000, KR, Full), + __DEFINE_LINK_MODE_PARAMS(50000, SR, Full), + __DEFINE_LINK_MODE_PARAMS(50000, CR, Full), + __DEFINE_LINK_MODE_PARAMS(50000, LR_ER_FR, Full), + __DEFINE_LINK_MODE_PARAMS(50000, DR, Full), + __DEFINE_LINK_MODE_PARAMS(100000, KR2, Full), + __DEFINE_LINK_MODE_PARAMS(100000, SR2, Full), + __DEFINE_LINK_MODE_PARAMS(100000, CR2, Full), + __DEFINE_LINK_MODE_PARAMS(100000, LR2_ER2_FR2, Full), + __DEFINE_LINK_MODE_PARAMS(100000, DR2, Full), + __DEFINE_LINK_MODE_PARAMS(200000, KR4, Full), + __DEFINE_LINK_MODE_PARAMS(200000, SR4, Full), + __DEFINE_LINK_MODE_PARAMS(200000, LR4_ER4_FR4, Full), + __DEFINE_LINK_MODE_PARAMS(200000, DR4, Full), + __DEFINE_LINK_MODE_PARAMS(200000, CR4, Full), + __DEFINE_LINK_MODE_PARAMS(100, T1, Full), + __DEFINE_LINK_MODE_PARAMS(1000, T1, Full), + __DEFINE_LINK_MODE_PARAMS(400000, KR8, Full), + __DEFINE_LINK_MODE_PARAMS(400000, SR8, Full), + __DEFINE_LINK_MODE_PARAMS(400000, LR8_ER8_FR8, Full), + __DEFINE_LINK_MODE_PARAMS(400000, DR8, Full), + __DEFINE_LINK_MODE_PARAMS(400000, CR8, Full), +}; + +static const struct nla_policy +linkmodes_set_policy[ETHTOOL_A_LINKMODES_MAX + 1] = { + [ETHTOOL_A_LINKMODES_UNSPEC] = { .type = NLA_REJECT }, + [ETHTOOL_A_LINKMODES_HEADER] = { .type = NLA_NESTED }, + [ETHTOOL_A_LINKMODES_AUTONEG] = { .type = NLA_U8 }, + [ETHTOOL_A_LINKMODES_OURS] = { .type = NLA_NESTED }, + [ETHTOOL_A_LINKMODES_PEER] = { .type = NLA_REJECT }, + [ETHTOOL_A_LINKMODES_SPEED] = { .type = NLA_U32 }, + [ETHTOOL_A_LINKMODES_DUPLEX] = { .type = NLA_U8 }, +}; + +/* Set advertised link modes to all supported modes matching requested speed + * and duplex values. Called when autonegotiation is on, speed or duplex is + * requested but no link mode change. This is done in userspace with ioctl() + * interface, move it into kernel for netlink. + * Returns true if advertised modes bitmap was modified. + */ +static bool ethnl_auto_linkmodes(struct ethtool_link_ksettings *ksettings, + bool req_speed, bool req_duplex) +{ + unsigned long *advertising = ksettings->link_modes.advertising; + unsigned long *supported = ksettings->link_modes.supported; + DECLARE_BITMAP(old_adv, __ETHTOOL_LINK_MODE_MASK_NBITS); + unsigned int i; + + BUILD_BUG_ON(ARRAY_SIZE(link_mode_params) != + __ETHTOOL_LINK_MODE_MASK_NBITS); + + bitmap_copy(old_adv, advertising, __ETHTOOL_LINK_MODE_MASK_NBITS); + + for (i = 0; i < __ETHTOOL_LINK_MODE_MASK_NBITS; i++) { + const struct link_mode_info *info = &link_mode_params[i]; + + if (info->speed == SPEED_UNKNOWN) + continue; + if (test_bit(i, supported) && + (!req_speed || info->speed == ksettings->base.speed) && + (!req_duplex || info->duplex == ksettings->base.duplex)) + set_bit(i, advertising); + else + clear_bit(i, advertising); + } + + return !bitmap_equal(old_adv, advertising, + __ETHTOOL_LINK_MODE_MASK_NBITS); +} + +static int ethnl_update_linkmodes(struct genl_info *info, struct nlattr **tb, + struct ethtool_link_ksettings *ksettings, + bool *mod) +{ + struct ethtool_link_settings *lsettings = &ksettings->base; + bool req_speed, req_duplex; + int ret; + + *mod = false; + req_speed = tb[ETHTOOL_A_LINKMODES_SPEED]; + req_duplex = tb[ETHTOOL_A_LINKMODES_DUPLEX]; + + ethnl_update_u8(&lsettings->autoneg, tb[ETHTOOL_A_LINKMODES_AUTONEG], + mod); + ret = ethnl_update_bitset(ksettings->link_modes.advertising, + __ETHTOOL_LINK_MODE_MASK_NBITS, + tb[ETHTOOL_A_LINKMODES_OURS], link_mode_names, + info->extack, mod); + if (ret < 0) + return ret; + ethnl_update_u32(&lsettings->speed, tb[ETHTOOL_A_LINKMODES_SPEED], + mod); + ethnl_update_u8(&lsettings->duplex, tb[ETHTOOL_A_LINKMODES_DUPLEX], + mod); + + if (!tb[ETHTOOL_A_LINKMODES_OURS] && lsettings->autoneg && + (req_speed || req_duplex) && + ethnl_auto_linkmodes(ksettings, req_speed, req_duplex)) + *mod = true; + + return 0; +} + +int ethnl_set_linkmodes(struct sk_buff *skb, struct genl_info *info) +{ + struct nlattr *tb[ETHTOOL_A_LINKMODES_MAX + 1]; + struct ethtool_link_ksettings ksettings = {}; + struct ethnl_req_info req_info = {}; + struct net_device *dev; + bool mod = false; + int ret; + + ret = nlmsg_parse(info->nlhdr, GENL_HDRLEN, tb, + ETHTOOL_A_LINKMODES_MAX, linkmodes_set_policy, + info->extack); + if (ret < 0) + return ret; + ret = ethnl_parse_header(&req_info, tb[ETHTOOL_A_LINKMODES_HEADER], + genl_info_net(info), info->extack, true); + if (ret < 0) + return ret; + dev = req_info.dev; + if (!dev->ethtool_ops->get_link_ksettings || + !dev->ethtool_ops->set_link_ksettings) + return -EOPNOTSUPP; + + rtnl_lock(); + ret = ethnl_ops_begin(dev); + if (ret < 0) + goto out_rtnl; + + ret = __ethtool_get_link_ksettings(dev, &ksettings); + if (ret < 0) { + if (info) + GENL_SET_ERR_MSG(info, "failed to retrieve link settings"); + goto out_ops; + } + + ret = ethnl_update_linkmodes(info, tb, &ksettings, &mod); + if (ret < 0) + goto out_ops; + + if (mod) { + ret = dev->ethtool_ops->set_link_ksettings(dev, &ksettings); + if (ret < 0) + GENL_SET_ERR_MSG(info, "link settings update failed"); + else + ethtool_notify(dev, ETHTOOL_MSG_LINKMODES_NTF, NULL); + } + +out_ops: + ethnl_ops_complete(dev); +out_rtnl: + rtnl_unlock(); + dev_put(dev); + return ret; +} diff --git a/net/ethtool/linkstate.c b/net/ethtool/linkstate.c new file mode 100644 index 000000000000..2740cde0a182 --- /dev/null +++ b/net/ethtool/linkstate.c @@ -0,0 +1,74 @@ +// SPDX-License-Identifier: GPL-2.0-only + +#include "netlink.h" +#include "common.h" + +struct linkstate_req_info { + struct ethnl_req_info base; +}; + +struct linkstate_reply_data { + struct ethnl_reply_data base; + int link; +}; + +#define LINKSTATE_REPDATA(__reply_base) \ + container_of(__reply_base, struct linkstate_reply_data, base) + +static const struct nla_policy +linkstate_get_policy[ETHTOOL_A_LINKSTATE_MAX + 1] = { + [ETHTOOL_A_LINKSTATE_UNSPEC] = { .type = NLA_REJECT }, + [ETHTOOL_A_LINKSTATE_HEADER] = { .type = NLA_NESTED }, + [ETHTOOL_A_LINKSTATE_LINK] = { .type = NLA_REJECT }, +}; + +static int linkstate_prepare_data(const struct ethnl_req_info *req_base, + struct ethnl_reply_data *reply_base, + struct genl_info *info) +{ + struct linkstate_reply_data *data = LINKSTATE_REPDATA(reply_base); + struct net_device *dev = reply_base->dev; + int ret; + + ret = ethnl_ops_begin(dev); + if (ret < 0) + return ret; + data->link = __ethtool_get_link(dev); + ethnl_ops_complete(dev); + + return 0; +} + +static int linkstate_reply_size(const struct ethnl_req_info *req_base, + const struct ethnl_reply_data *reply_base) +{ + return nla_total_size(sizeof(u8)) /* LINKSTATE_LINK */ + + 0; +} + +static int linkstate_fill_reply(struct sk_buff *skb, + const struct ethnl_req_info *req_base, + const struct ethnl_reply_data *reply_base) +{ + struct linkstate_reply_data *data = LINKSTATE_REPDATA(reply_base); + + if (data->link >= 0 && + nla_put_u8(skb, ETHTOOL_A_LINKSTATE_LINK, !!data->link)) + return -EMSGSIZE; + + return 0; +} + +const struct ethnl_request_ops ethnl_linkstate_request_ops = { + .request_cmd = ETHTOOL_MSG_LINKSTATE_GET, + .reply_cmd = ETHTOOL_MSG_LINKSTATE_GET_REPLY, + .hdr_attr = ETHTOOL_A_LINKSTATE_HEADER, + .max_attr = ETHTOOL_A_LINKSTATE_MAX, + .req_info_size = sizeof(struct linkstate_req_info), + .reply_data_size = sizeof(struct linkstate_reply_data), + .request_policy = linkstate_get_policy, + + .prepare_data = linkstate_prepare_data, + .reply_size = linkstate_reply_size, + .fill_reply = linkstate_fill_reply, +}; diff --git a/net/ethtool/netlink.c b/net/ethtool/netlink.c new file mode 100644 index 000000000000..180c194fab07 --- /dev/null +++ b/net/ethtool/netlink.c @@ -0,0 +1,729 @@ +// SPDX-License-Identifier: GPL-2.0-only + +#include <net/sock.h> +#include <linux/ethtool_netlink.h> +#include "netlink.h" + +static struct genl_family ethtool_genl_family; + +static bool ethnl_ok __read_mostly; +static u32 ethnl_bcast_seq; + +static const struct nla_policy ethnl_header_policy[ETHTOOL_A_HEADER_MAX + 1] = { + [ETHTOOL_A_HEADER_UNSPEC] = { .type = NLA_REJECT }, + [ETHTOOL_A_HEADER_DEV_INDEX] = { .type = NLA_U32 }, + [ETHTOOL_A_HEADER_DEV_NAME] = { .type = NLA_NUL_STRING, + .len = ALTIFNAMSIZ - 1 }, + [ETHTOOL_A_HEADER_FLAGS] = { .type = NLA_U32 }, +}; + +/** + * ethnl_parse_header() - parse request header + * @req_info: structure to put results into + * @header: nest attribute with request header + * @net: request netns + * @extack: netlink extack for error reporting + * @require_dev: fail if no device identified in header + * + * Parse request header in nested attribute @nest and puts results into + * the structure pointed to by @req_info. Extack from @info is used for error + * reporting. If req_info->dev is not null on return, reference to it has + * been taken. If error is returned, *req_info is null initialized and no + * reference is held. + * + * Return: 0 on success or negative error code + */ +int ethnl_parse_header(struct ethnl_req_info *req_info, + const struct nlattr *header, struct net *net, + struct netlink_ext_ack *extack, bool require_dev) +{ + struct nlattr *tb[ETHTOOL_A_HEADER_MAX + 1]; + const struct nlattr *devname_attr; + struct net_device *dev = NULL; + int ret; + + if (!header) { + NL_SET_ERR_MSG(extack, "request header missing"); + return -EINVAL; + } + ret = nla_parse_nested(tb, ETHTOOL_A_HEADER_MAX, header, + ethnl_header_policy, extack); + if (ret < 0) + return ret; + devname_attr = tb[ETHTOOL_A_HEADER_DEV_NAME]; + + if (tb[ETHTOOL_A_HEADER_DEV_INDEX]) { + u32 ifindex = nla_get_u32(tb[ETHTOOL_A_HEADER_DEV_INDEX]); + + dev = dev_get_by_index(net, ifindex); + if (!dev) { + NL_SET_ERR_MSG_ATTR(extack, + tb[ETHTOOL_A_HEADER_DEV_INDEX], + "no device matches ifindex"); + return -ENODEV; + } + /* if both ifindex and ifname are passed, they must match */ + if (devname_attr && + strncmp(dev->name, nla_data(devname_attr), IFNAMSIZ)) { + dev_put(dev); + NL_SET_ERR_MSG_ATTR(extack, header, + "ifindex and name do not match"); + return -ENODEV; + } + } else if (devname_attr) { + dev = dev_get_by_name(net, nla_data(devname_attr)); + if (!dev) { + NL_SET_ERR_MSG_ATTR(extack, devname_attr, + "no device matches name"); + return -ENODEV; + } + } else if (require_dev) { + NL_SET_ERR_MSG_ATTR(extack, header, + "neither ifindex nor name specified"); + return -EINVAL; + } + + if (dev && !netif_device_present(dev)) { + dev_put(dev); + NL_SET_ERR_MSG(extack, "device not present"); + return -ENODEV; + } + + req_info->dev = dev; + if (tb[ETHTOOL_A_HEADER_FLAGS]) + req_info->flags = nla_get_u32(tb[ETHTOOL_A_HEADER_FLAGS]); + + return 0; +} + +/** + * ethnl_fill_reply_header() - Put common header into a reply message + * @skb: skb with the message + * @dev: network device to describe in header + * @attrtype: attribute type to use for the nest + * + * Create a nested attribute with attributes describing given network device. + * + * Return: 0 on success, error value (-EMSGSIZE only) on error + */ +int ethnl_fill_reply_header(struct sk_buff *skb, struct net_device *dev, + u16 attrtype) +{ + struct nlattr *nest; + + if (!dev) + return 0; + nest = nla_nest_start(skb, attrtype); + if (!nest) + return -EMSGSIZE; + + if (nla_put_u32(skb, ETHTOOL_A_HEADER_DEV_INDEX, (u32)dev->ifindex) || + nla_put_string(skb, ETHTOOL_A_HEADER_DEV_NAME, dev->name)) + goto nla_put_failure; + /* If more attributes are put into reply header, ethnl_header_size() + * must be updated to account for them. + */ + + nla_nest_end(skb, nest); + return 0; + +nla_put_failure: + nla_nest_cancel(skb, nest); + return -EMSGSIZE; +} + +/** + * ethnl_reply_init() - Create skb for a reply and fill device identification + * @payload: payload length (without netlink and genetlink header) + * @dev: device the reply is about (may be null) + * @cmd: ETHTOOL_MSG_* message type for reply + * @hdr_attrtype: attribute type for common header + * @info: genetlink info of the received packet we respond to + * @ehdrp: place to store payload pointer returned by genlmsg_new() + * + * Return: pointer to allocated skb on success, NULL on error + */ +struct sk_buff *ethnl_reply_init(size_t payload, struct net_device *dev, u8 cmd, + u16 hdr_attrtype, struct genl_info *info, + void **ehdrp) +{ + struct sk_buff *skb; + + skb = genlmsg_new(payload, GFP_KERNEL); + if (!skb) + goto err; + *ehdrp = genlmsg_put_reply(skb, info, ðtool_genl_family, 0, cmd); + if (!*ehdrp) + goto err_free; + + if (dev) { + int ret; + + ret = ethnl_fill_reply_header(skb, dev, hdr_attrtype); + if (ret < 0) + goto err_free; + } + return skb; + +err_free: + nlmsg_free(skb); +err: + if (info) + GENL_SET_ERR_MSG(info, "failed to setup reply message"); + return NULL; +} + +static void *ethnl_bcastmsg_put(struct sk_buff *skb, u8 cmd) +{ + return genlmsg_put(skb, 0, ++ethnl_bcast_seq, ðtool_genl_family, 0, + cmd); +} + +static int ethnl_multicast(struct sk_buff *skb, struct net_device *dev) +{ + return genlmsg_multicast_netns(ðtool_genl_family, dev_net(dev), skb, + 0, ETHNL_MCGRP_MONITOR, GFP_KERNEL); +} + +/* GET request helpers */ + +/** + * struct ethnl_dump_ctx - context structure for generic dumpit() callback + * @ops: request ops of currently processed message type + * @req_info: parsed request header of processed request + * @reply_data: data needed to compose the reply + * @pos_hash: saved iteration position - hashbucket + * @pos_idx: saved iteration position - index + * + * These parameters are kept in struct netlink_callback as context preserved + * between iterations. They are initialized by ethnl_default_start() and used + * in ethnl_default_dumpit() and ethnl_default_done(). + */ +struct ethnl_dump_ctx { + const struct ethnl_request_ops *ops; + struct ethnl_req_info *req_info; + struct ethnl_reply_data *reply_data; + int pos_hash; + int pos_idx; +}; + +static const struct ethnl_request_ops * +ethnl_default_requests[__ETHTOOL_MSG_USER_CNT] = { + [ETHTOOL_MSG_STRSET_GET] = ðnl_strset_request_ops, + [ETHTOOL_MSG_LINKINFO_GET] = ðnl_linkinfo_request_ops, + [ETHTOOL_MSG_LINKMODES_GET] = ðnl_linkmodes_request_ops, + [ETHTOOL_MSG_LINKSTATE_GET] = ðnl_linkstate_request_ops, + [ETHTOOL_MSG_DEBUG_GET] = ðnl_debug_request_ops, + [ETHTOOL_MSG_WOL_GET] = ðnl_wol_request_ops, +}; + +static struct ethnl_dump_ctx *ethnl_dump_context(struct netlink_callback *cb) +{ + return (struct ethnl_dump_ctx *)cb->ctx; +} + +/** + * ethnl_default_parse() - Parse request message + * @req_info: pointer to structure to put data into + * @nlhdr: pointer to request message header + * @net: request netns + * @request_ops: struct request_ops for request type + * @extack: netlink extack for error reporting + * @require_dev: fail if no device identified in header + * + * Parse universal request header and call request specific ->parse_request() + * callback (if defined) to parse the rest of the message. + * + * Return: 0 on success or negative error code + */ +static int ethnl_default_parse(struct ethnl_req_info *req_info, + const struct nlmsghdr *nlhdr, struct net *net, + const struct ethnl_request_ops *request_ops, + struct netlink_ext_ack *extack, bool require_dev) +{ + struct nlattr **tb; + int ret; + + tb = kmalloc_array(request_ops->max_attr + 1, sizeof(tb[0]), + GFP_KERNEL); + if (!tb) + return -ENOMEM; + + ret = nlmsg_parse(nlhdr, GENL_HDRLEN, tb, request_ops->max_attr, + request_ops->request_policy, extack); + if (ret < 0) + goto out; + ret = ethnl_parse_header(req_info, tb[request_ops->hdr_attr], net, + extack, require_dev); + if (ret < 0) + goto out; + + if (request_ops->parse_request) { + ret = request_ops->parse_request(req_info, tb, extack); + if (ret < 0) + goto out; + } + + ret = 0; +out: + kfree(tb); + return ret; +} + +/** + * ethnl_init_reply_data() - Initialize reply data for GET request + * @reply_data: pointer to embedded struct ethnl_reply_data + * @ops: instance of struct ethnl_request_ops describing the layout + * @dev: network device to initialize the reply for + * + * Fills the reply data part with zeros and sets the dev member. Must be called + * before calling the ->fill_reply() callback (for each iteration when handling + * dump requests). + */ +static void ethnl_init_reply_data(struct ethnl_reply_data *reply_data, + const struct ethnl_request_ops *ops, + struct net_device *dev) +{ + memset(reply_data, 0, ops->reply_data_size); + reply_data->dev = dev; +} + +/* default ->doit() handler for GET type requests */ +static int ethnl_default_doit(struct sk_buff *skb, struct genl_info *info) +{ + struct ethnl_reply_data *reply_data = NULL; + struct ethnl_req_info *req_info = NULL; + const u8 cmd = info->genlhdr->cmd; + const struct ethnl_request_ops *ops; + struct sk_buff *rskb; + void *reply_payload; + int reply_len; + int ret; + + ops = ethnl_default_requests[cmd]; + if (WARN_ONCE(!ops, "cmd %u has no ethnl_request_ops\n", cmd)) + return -EOPNOTSUPP; + req_info = kzalloc(ops->req_info_size, GFP_KERNEL); + if (!req_info) + return -ENOMEM; + reply_data = kmalloc(ops->reply_data_size, GFP_KERNEL); + if (!reply_data) { + kfree(req_info); + return -ENOMEM; + } + + ret = ethnl_default_parse(req_info, info->nlhdr, genl_info_net(info), ops, + info->extack, !ops->allow_nodev_do); + if (ret < 0) + goto err_dev; + ethnl_init_reply_data(reply_data, ops, req_info->dev); + + rtnl_lock(); + ret = ops->prepare_data(req_info, reply_data, info); + rtnl_unlock(); + if (ret < 0) + goto err_cleanup; + ret = ops->reply_size(req_info, reply_data); + if (ret < 0) + goto err_cleanup; + reply_len = ret; + ret = -ENOMEM; + rskb = ethnl_reply_init(reply_len, req_info->dev, ops->reply_cmd, + ops->hdr_attr, info, &reply_payload); + if (!rskb) + goto err_cleanup; + ret = ops->fill_reply(rskb, req_info, reply_data); + if (ret < 0) + goto err_msg; + if (ops->cleanup_data) + ops->cleanup_data(reply_data); + + genlmsg_end(rskb, reply_payload); + if (req_info->dev) + dev_put(req_info->dev); + kfree(reply_data); + kfree(req_info); + return genlmsg_reply(rskb, info); + +err_msg: + WARN_ONCE(ret == -EMSGSIZE, "calculated message payload length (%d) not sufficient\n", reply_len); + nlmsg_free(rskb); +err_cleanup: + if (ops->cleanup_data) + ops->cleanup_data(reply_data); +err_dev: + if (req_info->dev) + dev_put(req_info->dev); + kfree(reply_data); + kfree(req_info); + return ret; +} + +static int ethnl_default_dump_one(struct sk_buff *skb, struct net_device *dev, + const struct ethnl_dump_ctx *ctx) +{ + int ret; + + ethnl_init_reply_data(ctx->reply_data, ctx->ops, dev); + rtnl_lock(); + ret = ctx->ops->prepare_data(ctx->req_info, ctx->reply_data, NULL); + rtnl_unlock(); + if (ret < 0) + goto out; + ret = ethnl_fill_reply_header(skb, dev, ctx->ops->hdr_attr); + if (ret < 0) + goto out; + ret = ctx->ops->fill_reply(skb, ctx->req_info, ctx->reply_data); + +out: + if (ctx->ops->cleanup_data) + ctx->ops->cleanup_data(ctx->reply_data); + ctx->reply_data->dev = NULL; + return ret; +} + +/* Default ->dumpit() handler for GET requests. Device iteration copied from + * rtnl_dump_ifinfo(); we have to be more careful about device hashtable + * persistence as we cannot guarantee to hold RTNL lock through the whole + * function as rtnetnlink does. + */ +static int ethnl_default_dumpit(struct sk_buff *skb, + struct netlink_callback *cb) +{ + struct ethnl_dump_ctx *ctx = ethnl_dump_context(cb); + struct net *net = sock_net(skb->sk); + int s_idx = ctx->pos_idx; + int h, idx = 0; + int ret = 0; + void *ehdr; + + rtnl_lock(); + for (h = ctx->pos_hash; h < NETDEV_HASHENTRIES; h++, s_idx = 0) { + struct hlist_head *head; + struct net_device *dev; + unsigned int seq; + + head = &net->dev_index_head[h]; + +restart_chain: + seq = net->dev_base_seq; + cb->seq = seq; + idx = 0; + hlist_for_each_entry(dev, head, index_hlist) { + if (idx < s_idx) + goto cont; + dev_hold(dev); + rtnl_unlock(); + + ehdr = genlmsg_put(skb, NETLINK_CB(cb->skb).portid, + cb->nlh->nlmsg_seq, + ðtool_genl_family, 0, + ctx->ops->reply_cmd); + if (!ehdr) { + dev_put(dev); + ret = -EMSGSIZE; + goto out; + } + ret = ethnl_default_dump_one(skb, dev, ctx); + dev_put(dev); + if (ret < 0) { + genlmsg_cancel(skb, ehdr); + if (ret == -EOPNOTSUPP) + goto lock_and_cont; + if (likely(skb->len)) + ret = skb->len; + goto out; + } + genlmsg_end(skb, ehdr); +lock_and_cont: + rtnl_lock(); + if (net->dev_base_seq != seq) { + s_idx = idx + 1; + goto restart_chain; + } +cont: + idx++; + } + + } + rtnl_unlock(); + +out: + ctx->pos_hash = h; + ctx->pos_idx = idx; + nl_dump_check_consistent(cb, nlmsg_hdr(skb)); + + return ret; +} + +/* generic ->start() handler for GET requests */ +static int ethnl_default_start(struct netlink_callback *cb) +{ + struct ethnl_dump_ctx *ctx = ethnl_dump_context(cb); + struct ethnl_reply_data *reply_data; + const struct ethnl_request_ops *ops; + struct ethnl_req_info *req_info; + struct genlmsghdr *ghdr; + int ret; + + BUILD_BUG_ON(sizeof(*ctx) > sizeof(cb->ctx)); + + ghdr = nlmsg_data(cb->nlh); + ops = ethnl_default_requests[ghdr->cmd]; + if (WARN_ONCE(!ops, "cmd %u has no ethnl_request_ops\n", ghdr->cmd)) + return -EOPNOTSUPP; + req_info = kzalloc(ops->req_info_size, GFP_KERNEL); + if (!req_info) + return -ENOMEM; + reply_data = kmalloc(ops->reply_data_size, GFP_KERNEL); + if (!reply_data) { + ret = -ENOMEM; + goto free_req_info; + } + + ret = ethnl_default_parse(req_info, cb->nlh, sock_net(cb->skb->sk), ops, + cb->extack, false); + if (req_info->dev) { + /* We ignore device specification in dump requests but as the + * same parser as for non-dump (doit) requests is used, it + * would take reference to the device if it finds one + */ + dev_put(req_info->dev); + req_info->dev = NULL; + } + if (ret < 0) + goto free_reply_data; + + ctx->ops = ops; + ctx->req_info = req_info; + ctx->reply_data = reply_data; + ctx->pos_hash = 0; + ctx->pos_idx = 0; + + return 0; + +free_reply_data: + kfree(reply_data); +free_req_info: + kfree(req_info); + + return ret; +} + +/* default ->done() handler for GET requests */ +static int ethnl_default_done(struct netlink_callback *cb) +{ + struct ethnl_dump_ctx *ctx = ethnl_dump_context(cb); + + kfree(ctx->reply_data); + kfree(ctx->req_info); + + return 0; +} + +static const struct ethnl_request_ops * +ethnl_default_notify_ops[ETHTOOL_MSG_KERNEL_MAX + 1] = { + [ETHTOOL_MSG_LINKINFO_NTF] = ðnl_linkinfo_request_ops, + [ETHTOOL_MSG_LINKMODES_NTF] = ðnl_linkmodes_request_ops, + [ETHTOOL_MSG_DEBUG_NTF] = ðnl_debug_request_ops, + [ETHTOOL_MSG_WOL_NTF] = ðnl_wol_request_ops, +}; + +/* default notification handler */ +static void ethnl_default_notify(struct net_device *dev, unsigned int cmd, + const void *data) +{ + struct ethnl_reply_data *reply_data; + const struct ethnl_request_ops *ops; + struct ethnl_req_info *req_info; + struct sk_buff *skb; + void *reply_payload; + int reply_len; + int ret; + + if (WARN_ONCE(cmd > ETHTOOL_MSG_KERNEL_MAX || + !ethnl_default_notify_ops[cmd], + "unexpected notification type %u\n", cmd)) + return; + ops = ethnl_default_notify_ops[cmd]; + req_info = kzalloc(ops->req_info_size, GFP_KERNEL); + if (!req_info) + return; + reply_data = kmalloc(ops->reply_data_size, GFP_KERNEL); + if (!reply_data) { + kfree(req_info); + return; + } + + req_info->dev = dev; + req_info->flags |= ETHTOOL_FLAG_COMPACT_BITSETS; + + ethnl_init_reply_data(reply_data, ops, dev); + ret = ops->prepare_data(req_info, reply_data, NULL); + if (ret < 0) + goto err_cleanup; + ret = ops->reply_size(req_info, reply_data); + if (ret < 0) + goto err_cleanup; + reply_len = ret; + ret = -ENOMEM; + skb = genlmsg_new(reply_len, GFP_KERNEL); + if (!skb) + goto err_cleanup; + reply_payload = ethnl_bcastmsg_put(skb, cmd); + if (!reply_payload) + goto err_skb; + ret = ethnl_fill_reply_header(skb, dev, ops->hdr_attr); + if (ret < 0) + goto err_msg; + ret = ops->fill_reply(skb, req_info, reply_data); + if (ret < 0) + goto err_msg; + if (ops->cleanup_data) + ops->cleanup_data(reply_data); + + genlmsg_end(skb, reply_payload); + kfree(reply_data); + kfree(req_info); + ethnl_multicast(skb, dev); + return; + +err_msg: + WARN_ONCE(ret == -EMSGSIZE, + "calculated message payload length (%d) not sufficient\n", + reply_len); +err_skb: + nlmsg_free(skb); +err_cleanup: + if (ops->cleanup_data) + ops->cleanup_data(reply_data); + kfree(reply_data); + kfree(req_info); + return; +} + +/* notifications */ + +typedef void (*ethnl_notify_handler_t)(struct net_device *dev, unsigned int cmd, + const void *data); + +static const ethnl_notify_handler_t ethnl_notify_handlers[] = { + [ETHTOOL_MSG_LINKINFO_NTF] = ethnl_default_notify, + [ETHTOOL_MSG_LINKMODES_NTF] = ethnl_default_notify, + [ETHTOOL_MSG_DEBUG_NTF] = ethnl_default_notify, + [ETHTOOL_MSG_WOL_NTF] = ethnl_default_notify, +}; + +void ethtool_notify(struct net_device *dev, unsigned int cmd, const void *data) +{ + if (unlikely(!ethnl_ok)) + return; + ASSERT_RTNL(); + + if (likely(cmd < ARRAY_SIZE(ethnl_notify_handlers) && + ethnl_notify_handlers[cmd])) + ethnl_notify_handlers[cmd](dev, cmd, data); + else + WARN_ONCE(1, "notification %u not implemented (dev=%s)\n", + cmd, netdev_name(dev)); +} +EXPORT_SYMBOL(ethtool_notify); + +/* genetlink setup */ + +static const struct genl_ops ethtool_genl_ops[] = { + { + .cmd = ETHTOOL_MSG_STRSET_GET, + .doit = ethnl_default_doit, + .start = ethnl_default_start, + .dumpit = ethnl_default_dumpit, + .done = ethnl_default_done, + }, + { + .cmd = ETHTOOL_MSG_LINKINFO_GET, + .doit = ethnl_default_doit, + .start = ethnl_default_start, + .dumpit = ethnl_default_dumpit, + .done = ethnl_default_done, + }, + { + .cmd = ETHTOOL_MSG_LINKINFO_SET, + .flags = GENL_UNS_ADMIN_PERM, + .doit = ethnl_set_linkinfo, + }, + { + .cmd = ETHTOOL_MSG_LINKMODES_GET, + .doit = ethnl_default_doit, + .start = ethnl_default_start, + .dumpit = ethnl_default_dumpit, + .done = ethnl_default_done, + }, + { + .cmd = ETHTOOL_MSG_LINKMODES_SET, + .flags = GENL_UNS_ADMIN_PERM, + .doit = ethnl_set_linkmodes, + }, + { + .cmd = ETHTOOL_MSG_LINKSTATE_GET, + .doit = ethnl_default_doit, + .start = ethnl_default_start, + .dumpit = ethnl_default_dumpit, + .done = ethnl_default_done, + }, + { + .cmd = ETHTOOL_MSG_DEBUG_GET, + .doit = ethnl_default_doit, + .start = ethnl_default_start, + .dumpit = ethnl_default_dumpit, + .done = ethnl_default_done, + }, + { + .cmd = ETHTOOL_MSG_DEBUG_SET, + .flags = GENL_UNS_ADMIN_PERM, + .doit = ethnl_set_debug, + }, + { + .cmd = ETHTOOL_MSG_WOL_GET, + .flags = GENL_UNS_ADMIN_PERM, + .doit = ethnl_default_doit, + .start = ethnl_default_start, + .dumpit = ethnl_default_dumpit, + .done = ethnl_default_done, + }, + { + .cmd = ETHTOOL_MSG_WOL_SET, + .flags = GENL_UNS_ADMIN_PERM, + .doit = ethnl_set_wol, + }, +}; + +static const struct genl_multicast_group ethtool_nl_mcgrps[] = { + [ETHNL_MCGRP_MONITOR] = { .name = ETHTOOL_MCGRP_MONITOR_NAME }, +}; + +static struct genl_family ethtool_genl_family = { + .name = ETHTOOL_GENL_NAME, + .version = ETHTOOL_GENL_VERSION, + .netnsok = true, + .parallel_ops = true, + .ops = ethtool_genl_ops, + .n_ops = ARRAY_SIZE(ethtool_genl_ops), + .mcgrps = ethtool_nl_mcgrps, + .n_mcgrps = ARRAY_SIZE(ethtool_nl_mcgrps), +}; + +/* module setup */ + +static int __init ethnl_init(void) +{ + int ret; + + ret = genl_register_family(ðtool_genl_family); + if (WARN(ret < 0, "ethtool: genetlink family registration failed")) + return ret; + ethnl_ok = true; + + return 0; +} + +subsys_initcall(ethnl_init); diff --git a/net/ethtool/netlink.h b/net/ethtool/netlink.h new file mode 100644 index 000000000000..60efd87686ad --- /dev/null +++ b/net/ethtool/netlink.h @@ -0,0 +1,345 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ + +#ifndef _NET_ETHTOOL_NETLINK_H +#define _NET_ETHTOOL_NETLINK_H + +#include <linux/ethtool_netlink.h> +#include <linux/netdevice.h> +#include <net/genetlink.h> +#include <net/sock.h> + +struct ethnl_req_info; + +int ethnl_parse_header(struct ethnl_req_info *req_info, + const struct nlattr *nest, struct net *net, + struct netlink_ext_ack *extack, bool require_dev); +int ethnl_fill_reply_header(struct sk_buff *skb, struct net_device *dev, + u16 attrtype); +struct sk_buff *ethnl_reply_init(size_t payload, struct net_device *dev, u8 cmd, + u16 hdr_attrtype, struct genl_info *info, + void **ehdrp); + +/** + * ethnl_strz_size() - calculate attribute length for fixed size string + * @s: ETH_GSTRING_LEN sized string (may not be null terminated) + * + * Return: total length of an attribute with null terminated string from @s + */ +static inline int ethnl_strz_size(const char *s) +{ + return nla_total_size(strnlen(s, ETH_GSTRING_LEN) + 1); +} + +/** + * ethnl_put_strz() - put string attribute with fixed size string + * @skb: skb with the message + * @attrype: attribute type + * @s: ETH_GSTRING_LEN sized string (may not be null terminated) + * + * Puts an attribute with null terminated string from @s into the message. + * + * Return: 0 on success, negative error code on failure + */ +static inline int ethnl_put_strz(struct sk_buff *skb, u16 attrtype, + const char *s) +{ + unsigned int len = strnlen(s, ETH_GSTRING_LEN); + struct nlattr *attr; + + attr = nla_reserve(skb, attrtype, len + 1); + if (!attr) + return -EMSGSIZE; + + memcpy(nla_data(attr), s, len); + ((char *)nla_data(attr))[len] = '\0'; + return 0; +} + +/** + * ethnl_update_u32() - update u32 value from NLA_U32 attribute + * @dst: value to update + * @attr: netlink attribute with new value or null + * @mod: pointer to bool for modification tracking + * + * Copy the u32 value from NLA_U32 netlink attribute @attr into variable + * pointed to by @dst; do nothing if @attr is null. Bool pointed to by @mod + * is set to true if this function changed the value of *dst, otherwise it + * is left as is. + */ +static inline void ethnl_update_u32(u32 *dst, const struct nlattr *attr, + bool *mod) +{ + u32 val; + + if (!attr) + return; + val = nla_get_u32(attr); + if (*dst == val) + return; + + *dst = val; + *mod = true; +} + +/** + * ethnl_update_u8() - update u8 value from NLA_U8 attribute + * @dst: value to update + * @attr: netlink attribute with new value or null + * @mod: pointer to bool for modification tracking + * + * Copy the u8 value from NLA_U8 netlink attribute @attr into variable + * pointed to by @dst; do nothing if @attr is null. Bool pointed to by @mod + * is set to true if this function changed the value of *dst, otherwise it + * is left as is. + */ +static inline void ethnl_update_u8(u8 *dst, const struct nlattr *attr, + bool *mod) +{ + u8 val; + + if (!attr) + return; + val = nla_get_u8(attr); + if (*dst == val) + return; + + *dst = val; + *mod = true; +} + +/** + * ethnl_update_bool32() - update u32 used as bool from NLA_U8 attribute + * @dst: value to update + * @attr: netlink attribute with new value or null + * @mod: pointer to bool for modification tracking + * + * Use the u8 value from NLA_U8 netlink attribute @attr to set u32 variable + * pointed to by @dst to 0 (if zero) or 1 (if not); do nothing if @attr is + * null. Bool pointed to by @mod is set to true if this function changed the + * logical value of *dst, otherwise it is left as is. + */ +static inline void ethnl_update_bool32(u32 *dst, const struct nlattr *attr, + bool *mod) +{ + u8 val; + + if (!attr) + return; + val = !!nla_get_u8(attr); + if (!!*dst == val) + return; + + *dst = val; + *mod = true; +} + +/** + * ethnl_update_binary() - update binary data from NLA_BINARY atribute + * @dst: value to update + * @len: destination buffer length + * @attr: netlink attribute with new value or null + * @mod: pointer to bool for modification tracking + * + * Use the u8 value from NLA_U8 netlink attribute @attr to rewrite data block + * of length @len at @dst by attribute payload; do nothing if @attr is null. + * Bool pointed to by @mod is set to true if this function changed the logical + * value of *dst, otherwise it is left as is. + */ +static inline void ethnl_update_binary(void *dst, unsigned int len, + const struct nlattr *attr, bool *mod) +{ + if (!attr) + return; + if (nla_len(attr) < len) + len = nla_len(attr); + if (!memcmp(dst, nla_data(attr), len)) + return; + + memcpy(dst, nla_data(attr), len); + *mod = true; +} + +/** + * ethnl_update_bitfield32() - update u32 value from NLA_BITFIELD32 attribute + * @dst: value to update + * @attr: netlink attribute with new value or null + * @mod: pointer to bool for modification tracking + * + * Update bits in u32 value which are set in attribute's mask to values from + * attribute's value. Do nothing if @attr is null or the value wouldn't change; + * otherwise, set bool pointed to by @mod to true. + */ +static inline void ethnl_update_bitfield32(u32 *dst, const struct nlattr *attr, + bool *mod) +{ + struct nla_bitfield32 change; + u32 newval; + + if (!attr) + return; + change = nla_get_bitfield32(attr); + newval = (*dst & ~change.selector) | (change.value & change.selector); + if (*dst == newval) + return; + + *dst = newval; + *mod = true; +} + +/** + * ethnl_reply_header_size() - total size of reply header + * + * This is an upper estimate so that we do not need to hold RTNL lock longer + * than necessary (to prevent rename between size estimate and composing the + * message). Accounts only for device ifindex and name as those are the only + * attributes ethnl_fill_reply_header() puts into the reply header. + */ +static inline unsigned int ethnl_reply_header_size(void) +{ + return nla_total_size(nla_total_size(sizeof(u32)) + + nla_total_size(IFNAMSIZ)); +} + +/* GET request handling */ + +/* Unified processing of GET requests uses two data structures: request info + * and reply data. Request info holds information parsed from client request + * and its stays constant through all request processing. Reply data holds data + * retrieved from ethtool_ops callbacks or other internal sources which is used + * to compose the reply. When processing a dump request, request info is filled + * only once (when the request message is parsed) but reply data is filled for + * each reply message. + * + * Both structures consist of part common for all request types (struct + * ethnl_req_info and struct ethnl_reply_data defined below) and optional + * parts specific for each request type. Common part always starts at offset 0. + */ + +/** + * struct ethnl_req_info - base type of request information for GET requests + * @dev: network device the request is for (may be null) + * @flags: request flags common for all request types + * + * This is a common base for request specific structures holding data from + * parsed userspace request. These always embed struct ethnl_req_info at + * zero offset. + */ +struct ethnl_req_info { + struct net_device *dev; + u32 flags; +}; + +/** + * struct ethnl_reply_data - base type of reply data for GET requests + * @dev: device for current reply message; in single shot requests it is + * equal to ðnl_req_info.dev; in dumps it's different for each + * reply message + * + * This is a common base for request specific structures holding data for + * kernel reply message. These always embed struct ethnl_reply_data at zero + * offset. + */ +struct ethnl_reply_data { + struct net_device *dev; +}; + +static inline int ethnl_ops_begin(struct net_device *dev) +{ + if (dev && dev->ethtool_ops->begin) + return dev->ethtool_ops->begin(dev); + else + return 0; +} + +static inline void ethnl_ops_complete(struct net_device *dev) +{ + if (dev && dev->ethtool_ops->complete) + dev->ethtool_ops->complete(dev); +} + +/** + * struct ethnl_request_ops - unified handling of GET requests + * @request_cmd: command id for request (GET) + * @reply_cmd: command id for reply (GET_REPLY) + * @hdr_attr: attribute type for request header + * @max_attr: maximum (top level) attribute type + * @req_info_size: size of request info + * @reply_data_size: size of reply data + * @request_policy: netlink policy for message contents + * @allow_nodev_do: allow non-dump request with no device identification + * @parse_request: + * Parse request except common header (struct ethnl_req_info). Common + * header is already filled on entry, the rest up to @repdata_offset + * is zero initialized. This callback should only modify type specific + * request info by parsed attributes from request message. + * @prepare_data: + * Retrieve and prepare data needed to compose a reply message. Calls to + * ethtool_ops handlers are limited to this callback. Common reply data + * (struct ethnl_reply_data) is filled on entry, type specific part after + * it is zero initialized. This callback should only modify the type + * specific part of reply data. Device identification from struct + * ethnl_reply_data is to be used as for dump requests, it iterates + * through network devices while dev member of struct ethnl_req_info + * points to the device from client request. + * @reply_size: + * Estimate reply message size. Returned value must be sufficient for + * message payload without common reply header. The callback may returned + * estimate higher than actual message size if exact calculation would + * not be worth the saved memory space. + * @fill_reply: + * Fill reply message payload (except for common header) from reply data. + * The callback must not generate more payload than previously called + * ->reply_size() estimated. + * @cleanup_data: + * Optional cleanup called when reply data is no longer needed. Can be + * used e.g. to free any additional data structures outside the main + * structure which were allocated by ->prepare_data(). When processing + * dump requests, ->cleanup() is called for each message. + * + * Description of variable parts of GET request handling when using the + * unified infrastructure. When used, a pointer to an instance of this + * structure is to be added to ðnl_default_requests array and generic + * handlers ethnl_default_doit(), ethnl_default_dumpit(), + * ethnl_default_start() and ethnl_default_done() used in @ethtool_genl_ops; + * ethnl_default_notify() can be used in @ethnl_notify_handlers to send + * notifications of the corresponding type. + */ +struct ethnl_request_ops { + u8 request_cmd; + u8 reply_cmd; + u16 hdr_attr; + unsigned int max_attr; + unsigned int req_info_size; + unsigned int reply_data_size; + const struct nla_policy *request_policy; + bool allow_nodev_do; + + int (*parse_request)(struct ethnl_req_info *req_info, + struct nlattr **tb, + struct netlink_ext_ack *extack); + int (*prepare_data)(const struct ethnl_req_info *req_info, + struct ethnl_reply_data *reply_data, + struct genl_info *info); + int (*reply_size)(const struct ethnl_req_info *req_info, + const struct ethnl_reply_data *reply_data); + int (*fill_reply)(struct sk_buff *skb, + const struct ethnl_req_info *req_info, + const struct ethnl_reply_data *reply_data); + void (*cleanup_data)(struct ethnl_reply_data *reply_data); +}; + +/* request handlers */ + +extern const struct ethnl_request_ops ethnl_strset_request_ops; +extern const struct ethnl_request_ops ethnl_linkinfo_request_ops; +extern const struct ethnl_request_ops ethnl_linkmodes_request_ops; +extern const struct ethnl_request_ops ethnl_linkstate_request_ops; +extern const struct ethnl_request_ops ethnl_debug_request_ops; +extern const struct ethnl_request_ops ethnl_wol_request_ops; + +int ethnl_set_linkinfo(struct sk_buff *skb, struct genl_info *info); +int ethnl_set_linkmodes(struct sk_buff *skb, struct genl_info *info); +int ethnl_set_debug(struct sk_buff *skb, struct genl_info *info); +int ethnl_set_wol(struct sk_buff *skb, struct genl_info *info); + +#endif /* _NET_ETHTOOL_NETLINK_H */ diff --git a/net/ethtool/strset.c b/net/ethtool/strset.c new file mode 100644 index 000000000000..8e5911887b4c --- /dev/null +++ b/net/ethtool/strset.c @@ -0,0 +1,437 @@ +// SPDX-License-Identifier: GPL-2.0-only + +#include <linux/ethtool.h> +#include <linux/phy.h> +#include "netlink.h" +#include "common.h" + +struct strset_info { + bool per_dev; + bool free_strings; + unsigned int count; + const char (*strings)[ETH_GSTRING_LEN]; +}; + +static const struct strset_info info_template[] = { + [ETH_SS_TEST] = { + .per_dev = true, + }, + [ETH_SS_STATS] = { + .per_dev = true, + }, + [ETH_SS_PRIV_FLAGS] = { + .per_dev = true, + }, + [ETH_SS_FEATURES] = { + .per_dev = false, + .count = ARRAY_SIZE(netdev_features_strings), + .strings = netdev_features_strings, + }, + [ETH_SS_RSS_HASH_FUNCS] = { + .per_dev = false, + .count = ARRAY_SIZE(rss_hash_func_strings), + .strings = rss_hash_func_strings, + }, + [ETH_SS_TUNABLES] = { + .per_dev = false, + .count = ARRAY_SIZE(tunable_strings), + .strings = tunable_strings, + }, + [ETH_SS_PHY_STATS] = { + .per_dev = true, + }, + [ETH_SS_PHY_TUNABLES] = { + .per_dev = false, + .count = ARRAY_SIZE(phy_tunable_strings), + .strings = phy_tunable_strings, + }, + [ETH_SS_LINK_MODES] = { + .per_dev = false, + .count = __ETHTOOL_LINK_MODE_MASK_NBITS, + .strings = link_mode_names, + }, + [ETH_SS_MSG_CLASSES] = { + .per_dev = false, + .count = NETIF_MSG_CLASS_COUNT, + .strings = netif_msg_class_names, + }, + [ETH_SS_WOL_MODES] = { + .per_dev = false, + .count = WOL_MODE_COUNT, + .strings = wol_mode_names, + }, +}; + +struct strset_req_info { + struct ethnl_req_info base; + u32 req_ids; + bool counts_only; +}; + +#define STRSET_REQINFO(__req_base) \ + container_of(__req_base, struct strset_req_info, base) + +struct strset_reply_data { + struct ethnl_reply_data base; + struct strset_info sets[ETH_SS_COUNT]; +}; + +#define STRSET_REPDATA(__reply_base) \ + container_of(__reply_base, struct strset_reply_data, base) + +static const struct nla_policy strset_get_policy[ETHTOOL_A_STRSET_MAX + 1] = { + [ETHTOOL_A_STRSET_UNSPEC] = { .type = NLA_REJECT }, + [ETHTOOL_A_STRSET_HEADER] = { .type = NLA_NESTED }, + [ETHTOOL_A_STRSET_STRINGSETS] = { .type = NLA_NESTED }, +}; + +static const struct nla_policy +get_stringset_policy[ETHTOOL_A_STRINGSET_MAX + 1] = { + [ETHTOOL_A_STRINGSET_UNSPEC] = { .type = NLA_REJECT }, + [ETHTOOL_A_STRINGSET_ID] = { .type = NLA_U32 }, + [ETHTOOL_A_STRINGSET_COUNT] = { .type = NLA_REJECT }, + [ETHTOOL_A_STRINGSET_STRINGS] = { .type = NLA_REJECT }, +}; + +/** + * strset_include() - test if a string set should be included in reply + * @info: parsed client request + * @data: pointer to request data structure + * @id: id of string set to check (ETH_SS_* constants) + */ +static bool strset_include(const struct strset_req_info *info, + const struct strset_reply_data *data, u32 id) +{ + bool per_dev; + + BUILD_BUG_ON(ETH_SS_COUNT >= BITS_PER_BYTE * sizeof(info->req_ids)); + + if (info->req_ids) + return info->req_ids & (1U << id); + per_dev = data->sets[id].per_dev; + if (!per_dev && !data->sets[id].strings) + return false; + + return data->base.dev ? per_dev : !per_dev; +} + +static int strset_get_id(const struct nlattr *nest, u32 *val, + struct netlink_ext_ack *extack) +{ + struct nlattr *tb[ETHTOOL_A_STRINGSET_MAX + 1]; + int ret; + + ret = nla_parse_nested(tb, ETHTOOL_A_STRINGSET_MAX, nest, + get_stringset_policy, extack); + if (ret < 0) + return ret; + if (!tb[ETHTOOL_A_STRINGSET_ID]) + return -EINVAL; + + *val = nla_get_u32(tb[ETHTOOL_A_STRINGSET_ID]); + return 0; +} + +static const struct nla_policy +strset_stringsets_policy[ETHTOOL_A_STRINGSETS_MAX + 1] = { + [ETHTOOL_A_STRINGSETS_UNSPEC] = { .type = NLA_REJECT }, + [ETHTOOL_A_STRINGSETS_STRINGSET] = { .type = NLA_NESTED }, +}; + +static int strset_parse_request(struct ethnl_req_info *req_base, + struct nlattr **tb, + struct netlink_ext_ack *extack) +{ + struct strset_req_info *req_info = STRSET_REQINFO(req_base); + struct nlattr *nest = tb[ETHTOOL_A_STRSET_STRINGSETS]; + struct nlattr *attr; + int rem, ret; + + if (!nest) + return 0; + ret = nla_validate_nested(nest, ETHTOOL_A_STRINGSETS_MAX, + strset_stringsets_policy, extack); + if (ret < 0) + return ret; + + req_info->counts_only = tb[ETHTOOL_A_STRSET_COUNTS_ONLY]; + nla_for_each_nested(attr, nest, rem) { + u32 id; + + if (WARN_ONCE(nla_type(attr) != ETHTOOL_A_STRINGSETS_STRINGSET, + "unexpected attrtype %u in ETHTOOL_A_STRSET_STRINGSETS\n", + nla_type(attr))) + return -EINVAL; + + ret = strset_get_id(attr, &id, extack); + if (ret < 0) + return ret; + if (ret >= ETH_SS_COUNT) { + NL_SET_ERR_MSG_ATTR(extack, attr, + "unknown string set id"); + return -EOPNOTSUPP; + } + + req_info->req_ids |= (1U << id); + } + + return 0; +} + +static void strset_cleanup_data(struct ethnl_reply_data *reply_base) +{ + struct strset_reply_data *data = STRSET_REPDATA(reply_base); + unsigned int i; + + for (i = 0; i < ETH_SS_COUNT; i++) + if (data->sets[i].free_strings) { + kfree(data->sets[i].strings); + data->sets[i].strings = NULL; + data->sets[i].free_strings = false; + } +} + +static int strset_prepare_set(struct strset_info *info, struct net_device *dev, + unsigned int id, bool counts_only) +{ + const struct ethtool_ops *ops = dev->ethtool_ops; + void *strings; + int count, ret; + + if (id == ETH_SS_PHY_STATS && dev->phydev && + !ops->get_ethtool_phy_stats) + ret = phy_ethtool_get_sset_count(dev->phydev); + else if (ops->get_sset_count && ops->get_strings) + ret = ops->get_sset_count(dev, id); + else + ret = -EOPNOTSUPP; + if (ret <= 0) { + info->count = 0; + return 0; + } + + count = ret; + if (!counts_only) { + strings = kcalloc(count, ETH_GSTRING_LEN, GFP_KERNEL); + if (!strings) + return -ENOMEM; + if (id == ETH_SS_PHY_STATS && dev->phydev && + !ops->get_ethtool_phy_stats) + phy_ethtool_get_strings(dev->phydev, strings); + else + ops->get_strings(dev, id, strings); + info->strings = strings; + info->free_strings = true; + } + info->count = count; + + return 0; +} + +static int strset_prepare_data(const struct ethnl_req_info *req_base, + struct ethnl_reply_data *reply_base, + struct genl_info *info) +{ + const struct strset_req_info *req_info = STRSET_REQINFO(req_base); + struct strset_reply_data *data = STRSET_REPDATA(reply_base); + struct net_device *dev = reply_base->dev; + unsigned int i; + int ret; + + BUILD_BUG_ON(ARRAY_SIZE(info_template) != ETH_SS_COUNT); + memcpy(&data->sets, &info_template, sizeof(data->sets)); + + if (!dev) { + for (i = 0; i < ETH_SS_COUNT; i++) { + if ((req_info->req_ids & (1U << i)) && + data->sets[i].per_dev) { + if (info) + GENL_SET_ERR_MSG(info, "requested per device strings without dev"); + return -EINVAL; + } + } + return 0; + } + + ret = ethnl_ops_begin(dev); + if (ret < 0) + goto err_strset; + for (i = 0; i < ETH_SS_COUNT; i++) { + if (!strset_include(req_info, data, i) || + !data->sets[i].per_dev) + continue; + + ret = strset_prepare_set(&data->sets[i], dev, i, + req_info->counts_only); + if (ret < 0) + goto err_ops; + } + ethnl_ops_complete(dev); + + return 0; +err_ops: + ethnl_ops_complete(dev); +err_strset: + strset_cleanup_data(reply_base); + return ret; +} + +/* calculate size of ETHTOOL_A_STRSET_STRINGSET nest for one string set */ +static int strset_set_size(const struct strset_info *info, bool counts_only) +{ + unsigned int len = 0; + unsigned int i; + + if (info->count == 0) + return 0; + if (counts_only) + return nla_total_size(2 * nla_total_size(sizeof(u32))); + + for (i = 0; i < info->count; i++) { + const char *str = info->strings[i]; + + /* ETHTOOL_A_STRING_INDEX, ETHTOOL_A_STRING_VALUE, nest */ + len += nla_total_size(nla_total_size(sizeof(u32)) + + ethnl_strz_size(str)); + } + /* ETHTOOL_A_STRINGSET_ID, ETHTOOL_A_STRINGSET_COUNT */ + len = 2 * nla_total_size(sizeof(u32)) + nla_total_size(len); + + return nla_total_size(len); +} + +static int strset_reply_size(const struct ethnl_req_info *req_base, + const struct ethnl_reply_data *reply_base) +{ + const struct strset_req_info *req_info = STRSET_REQINFO(req_base); + const struct strset_reply_data *data = STRSET_REPDATA(reply_base); + unsigned int i; + int len = 0; + int ret; + + len += ethnl_reply_header_size(); + for (i = 0; i < ETH_SS_COUNT; i++) { + const struct strset_info *set_info = &data->sets[i]; + + if (!strset_include(req_info, data, i)) + continue; + + ret = strset_set_size(set_info, req_info->counts_only); + if (ret < 0) + return ret; + len += ret; + } + + return len; +} + +/* fill one string into reply */ +static int strset_fill_string(struct sk_buff *skb, + const struct strset_info *set_info, u32 idx) +{ + struct nlattr *string_attr; + const char *value; + + value = set_info->strings[idx]; + + string_attr = nla_nest_start(skb, ETHTOOL_A_STRINGS_STRING); + if (!string_attr) + return -EMSGSIZE; + if (nla_put_u32(skb, ETHTOOL_A_STRING_INDEX, idx) || + ethnl_put_strz(skb, ETHTOOL_A_STRING_VALUE, value)) + goto nla_put_failure; + nla_nest_end(skb, string_attr); + + return 0; +nla_put_failure: + nla_nest_cancel(skb, string_attr); + return -EMSGSIZE; +} + +/* fill one string set into reply */ +static int strset_fill_set(struct sk_buff *skb, + const struct strset_info *set_info, u32 id, + bool counts_only) +{ + struct nlattr *stringset_attr; + struct nlattr *strings_attr; + unsigned int i; + + if (!set_info->per_dev && !set_info->strings) + return -EOPNOTSUPP; + if (set_info->count == 0) + return 0; + stringset_attr = nla_nest_start(skb, ETHTOOL_A_STRINGSETS_STRINGSET); + if (!stringset_attr) + return -EMSGSIZE; + + if (nla_put_u32(skb, ETHTOOL_A_STRINGSET_ID, id) || + nla_put_u32(skb, ETHTOOL_A_STRINGSET_COUNT, set_info->count)) + goto nla_put_failure; + + if (!counts_only) { + strings_attr = nla_nest_start(skb, ETHTOOL_A_STRINGSET_STRINGS); + if (!strings_attr) + goto nla_put_failure; + for (i = 0; i < set_info->count; i++) { + if (strset_fill_string(skb, set_info, i) < 0) + goto nla_put_failure; + } + nla_nest_end(skb, strings_attr); + } + + nla_nest_end(skb, stringset_attr); + return 0; + +nla_put_failure: + nla_nest_cancel(skb, stringset_attr); + return -EMSGSIZE; +} + +static int strset_fill_reply(struct sk_buff *skb, + const struct ethnl_req_info *req_base, + const struct ethnl_reply_data *reply_base) +{ + const struct strset_req_info *req_info = STRSET_REQINFO(req_base); + const struct strset_reply_data *data = STRSET_REPDATA(reply_base); + struct nlattr *nest; + unsigned int i; + int ret; + + nest = nla_nest_start(skb, ETHTOOL_A_STRSET_STRINGSETS); + if (!nest) + return -EMSGSIZE; + + for (i = 0; i < ETH_SS_COUNT; i++) { + if (strset_include(req_info, data, i)) { + ret = strset_fill_set(skb, &data->sets[i], i, + req_info->counts_only); + if (ret < 0) + goto nla_put_failure; + } + } + + nla_nest_end(skb, nest); + return 0; + +nla_put_failure: + nla_nest_cancel(skb, nest); + return ret; +} + +const struct ethnl_request_ops ethnl_strset_request_ops = { + .request_cmd = ETHTOOL_MSG_STRSET_GET, + .reply_cmd = ETHTOOL_MSG_STRSET_GET_REPLY, + .hdr_attr = ETHTOOL_A_STRSET_HEADER, + .max_attr = ETHTOOL_A_STRSET_MAX, + .req_info_size = sizeof(struct strset_req_info), + .reply_data_size = sizeof(struct strset_reply_data), + .request_policy = strset_get_policy, + .allow_nodev_do = true, + + .parse_request = strset_parse_request, + .prepare_data = strset_prepare_data, + .reply_size = strset_reply_size, + .fill_reply = strset_fill_reply, + .cleanup_data = strset_cleanup_data, +}; diff --git a/net/ethtool/wol.c b/net/ethtool/wol.c new file mode 100644 index 000000000000..e1b8a65b64c4 --- /dev/null +++ b/net/ethtool/wol.c @@ -0,0 +1,177 @@ +// SPDX-License-Identifier: GPL-2.0-only + +#include "netlink.h" +#include "common.h" +#include "bitset.h" + +struct wol_req_info { + struct ethnl_req_info base; +}; + +struct wol_reply_data { + struct ethnl_reply_data base; + struct ethtool_wolinfo wol; + bool show_sopass; +}; + +#define WOL_REPDATA(__reply_base) \ + container_of(__reply_base, struct wol_reply_data, base) + +static const struct nla_policy +wol_get_policy[ETHTOOL_A_WOL_MAX + 1] = { + [ETHTOOL_A_WOL_UNSPEC] = { .type = NLA_REJECT }, + [ETHTOOL_A_WOL_HEADER] = { .type = NLA_NESTED }, + [ETHTOOL_A_WOL_MODES] = { .type = NLA_REJECT }, + [ETHTOOL_A_WOL_SOPASS] = { .type = NLA_REJECT }, +}; + +static int wol_prepare_data(const struct ethnl_req_info *req_base, + struct ethnl_reply_data *reply_base, + struct genl_info *info) +{ + struct wol_reply_data *data = WOL_REPDATA(reply_base); + struct net_device *dev = reply_base->dev; + int ret; + + if (!dev->ethtool_ops->get_wol) + return -EOPNOTSUPP; + + ret = ethnl_ops_begin(dev); + if (ret < 0) + return ret; + dev->ethtool_ops->get_wol(dev, &data->wol); + ethnl_ops_complete(dev); + /* do not include password in notifications */ + data->show_sopass = info && (data->wol.supported & WAKE_MAGICSECURE); + + return 0; +} + +static int wol_reply_size(const struct ethnl_req_info *req_base, + const struct ethnl_reply_data *reply_base) +{ + bool compact = req_base->flags & ETHTOOL_FLAG_COMPACT_BITSETS; + const struct wol_reply_data *data = WOL_REPDATA(reply_base); + int len; + + len = ethnl_bitset32_size(&data->wol.wolopts, &data->wol.supported, + WOL_MODE_COUNT, wol_mode_names, compact); + if (len < 0) + return len; + if (data->show_sopass) + len += nla_total_size(sizeof(data->wol.sopass)); + + return len; +} + +static int wol_fill_reply(struct sk_buff *skb, + const struct ethnl_req_info *req_base, + const struct ethnl_reply_data *reply_base) +{ + bool compact = req_base->flags & ETHTOOL_FLAG_COMPACT_BITSETS; + const struct wol_reply_data *data = WOL_REPDATA(reply_base); + int ret; + + ret = ethnl_put_bitset32(skb, ETHTOOL_A_WOL_MODES, &data->wol.wolopts, + &data->wol.supported, WOL_MODE_COUNT, + wol_mode_names, compact); + if (ret < 0) + return ret; + if (data->show_sopass && + nla_put(skb, ETHTOOL_A_WOL_SOPASS, sizeof(data->wol.sopass), + data->wol.sopass)) + return -EMSGSIZE; + + return 0; +} + +const struct ethnl_request_ops ethnl_wol_request_ops = { + .request_cmd = ETHTOOL_MSG_WOL_GET, + .reply_cmd = ETHTOOL_MSG_WOL_GET_REPLY, + .hdr_attr = ETHTOOL_A_WOL_HEADER, + .max_attr = ETHTOOL_A_WOL_MAX, + .req_info_size = sizeof(struct wol_req_info), + .reply_data_size = sizeof(struct wol_reply_data), + .request_policy = wol_get_policy, + + .prepare_data = wol_prepare_data, + .reply_size = wol_reply_size, + .fill_reply = wol_fill_reply, +}; + +/* WOL_SET */ + +static const struct nla_policy +wol_set_policy[ETHTOOL_A_WOL_MAX + 1] = { + [ETHTOOL_A_WOL_UNSPEC] = { .type = NLA_REJECT }, + [ETHTOOL_A_WOL_HEADER] = { .type = NLA_NESTED }, + [ETHTOOL_A_WOL_MODES] = { .type = NLA_NESTED }, + [ETHTOOL_A_WOL_SOPASS] = { .type = NLA_BINARY, + .len = SOPASS_MAX }, +}; + +int ethnl_set_wol(struct sk_buff *skb, struct genl_info *info) +{ + struct ethtool_wolinfo wol = { .cmd = ETHTOOL_GWOL }; + struct nlattr *tb[ETHTOOL_A_WOL_MAX + 1]; + struct ethnl_req_info req_info = {}; + struct net_device *dev; + bool mod = false; + int ret; + + ret = nlmsg_parse(info->nlhdr, GENL_HDRLEN, tb, ETHTOOL_A_WOL_MAX, + wol_set_policy, info->extack); + if (ret < 0) + return ret; + ret = ethnl_parse_header(&req_info, tb[ETHTOOL_A_WOL_HEADER], + genl_info_net(info), info->extack, true); + if (ret < 0) + return ret; + dev = req_info.dev; + if (!dev->ethtool_ops->get_wol || !dev->ethtool_ops->set_wol) + return -EOPNOTSUPP; + + rtnl_lock(); + ret = ethnl_ops_begin(dev); + if (ret < 0) + goto out_rtnl; + + dev->ethtool_ops->get_wol(dev, &wol); + ret = ethnl_update_bitset32(&wol.wolopts, WOL_MODE_COUNT, + tb[ETHTOOL_A_WOL_MODES], wol_mode_names, + info->extack, &mod); + if (ret < 0) + goto out_ops; + if (wol.wolopts & ~wol.supported) { + NL_SET_ERR_MSG_ATTR(info->extack, tb[ETHTOOL_A_WOL_MODES], + "cannot enable unsupported WoL mode"); + ret = -EINVAL; + goto out_ops; + } + if (tb[ETHTOOL_A_WOL_SOPASS]) { + if (!(wol.supported & WAKE_MAGICSECURE)) { + NL_SET_ERR_MSG_ATTR(info->extack, + tb[ETHTOOL_A_WOL_SOPASS], + "magicsecure not supported, cannot set password"); + ret = -EINVAL; + goto out_ops; + } + ethnl_update_binary(wol.sopass, sizeof(wol.sopass), + tb[ETHTOOL_A_WOL_SOPASS], &mod); + } + + if (!mod) + goto out_ops; + ret = dev->ethtool_ops->set_wol(dev, &wol); + if (ret) + goto out_ops; + dev->wol_enabled = !!wol.wolopts; + ethtool_notify(dev, ETHTOOL_MSG_WOL_NTF, NULL); + +out_ops: + ethnl_ops_complete(dev); +out_rtnl: + rtnl_unlock(); + dev_put(dev); + return ret; +} diff --git a/net/hsr/hsr_framereg.c b/net/hsr/hsr_framereg.c index 27dc65d7de67..364ea2cc028e 100644 --- a/net/hsr/hsr_framereg.c +++ b/net/hsr/hsr_framereg.c @@ -35,7 +35,6 @@ static bool seq_nr_after(u16 a, u16 b) } #define seq_nr_before(a, b) seq_nr_after((b), (a)) -#define seq_nr_after_or_eq(a, b) (!seq_nr_before((a), (b))) #define seq_nr_before_or_eq(a, b) (!seq_nr_after((a), (b))) bool hsr_addr_is_self(struct hsr_priv *hsr, unsigned char *addr) diff --git a/net/ipv4/Kconfig b/net/ipv4/Kconfig index fc816b187170..f96bd489b362 100644 --- a/net/ipv4/Kconfig +++ b/net/ipv4/Kconfig @@ -378,6 +378,17 @@ config INET_ESP_OFFLOAD If unsure, say N. +config INET_ESPINTCP + bool "IP: ESP in TCP encapsulation (RFC 8229)" + depends on XFRM && INET_ESP + select STREAM_PARSER + select NET_SOCK_MSG + help + Support for RFC 8229 encapsulation of ESP and IKE over + TCP/IPv4 sockets. + + If unsure, say N. + config INET_IPCOMP tristate "IP: IPComp transformation" select INET_XFRM_TUNNEL diff --git a/net/ipv4/Makefile b/net/ipv4/Makefile index d57ecfaf89d4..9d97bace13c8 100644 --- a/net/ipv4/Makefile +++ b/net/ipv4/Makefile @@ -65,3 +65,7 @@ obj-$(CONFIG_NETLABEL) += cipso_ipv4.o obj-$(CONFIG_XFRM) += xfrm4_policy.o xfrm4_state.o xfrm4_input.o \ xfrm4_output.o xfrm4_protocol.o + +ifeq ($(CONFIG_BPF_JIT),y) +obj-$(CONFIG_BPF_SYSCALL) += bpf_tcp_ca.o +endif diff --git a/net/ipv4/bpf_tcp_ca.c b/net/ipv4/bpf_tcp_ca.c new file mode 100644 index 000000000000..574972bc7299 --- /dev/null +++ b/net/ipv4/bpf_tcp_ca.c @@ -0,0 +1,252 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2019 Facebook */ + +#include <linux/types.h> +#include <linux/bpf_verifier.h> +#include <linux/bpf.h> +#include <linux/btf.h> +#include <linux/filter.h> +#include <net/tcp.h> + +static u32 optional_ops[] = { + offsetof(struct tcp_congestion_ops, init), + offsetof(struct tcp_congestion_ops, release), + offsetof(struct tcp_congestion_ops, set_state), + offsetof(struct tcp_congestion_ops, cwnd_event), + offsetof(struct tcp_congestion_ops, in_ack_event), + offsetof(struct tcp_congestion_ops, pkts_acked), + offsetof(struct tcp_congestion_ops, min_tso_segs), + offsetof(struct tcp_congestion_ops, sndbuf_expand), + offsetof(struct tcp_congestion_ops, cong_control), +}; + +static u32 unsupported_ops[] = { + offsetof(struct tcp_congestion_ops, get_info), +}; + +static const struct btf_type *tcp_sock_type; +static u32 tcp_sock_id, sock_id; + +static int bpf_tcp_ca_init(struct btf *btf) +{ + s32 type_id; + + type_id = btf_find_by_name_kind(btf, "sock", BTF_KIND_STRUCT); + if (type_id < 0) + return -EINVAL; + sock_id = type_id; + + type_id = btf_find_by_name_kind(btf, "tcp_sock", BTF_KIND_STRUCT); + if (type_id < 0) + return -EINVAL; + tcp_sock_id = type_id; + tcp_sock_type = btf_type_by_id(btf, tcp_sock_id); + + return 0; +} + +static bool is_optional(u32 member_offset) +{ + unsigned int i; + + for (i = 0; i < ARRAY_SIZE(optional_ops); i++) { + if (member_offset == optional_ops[i]) + return true; + } + + return false; +} + +static bool is_unsupported(u32 member_offset) +{ + unsigned int i; + + for (i = 0; i < ARRAY_SIZE(unsupported_ops); i++) { + if (member_offset == unsupported_ops[i]) + return true; + } + + return false; +} + +extern struct btf *btf_vmlinux; + +static bool bpf_tcp_ca_is_valid_access(int off, int size, + enum bpf_access_type type, + const struct bpf_prog *prog, + struct bpf_insn_access_aux *info) +{ + if (off < 0 || off >= sizeof(__u64) * MAX_BPF_FUNC_ARGS) + return false; + if (type != BPF_READ) + return false; + if (off % size != 0) + return false; + + if (!btf_ctx_access(off, size, type, prog, info)) + return false; + + if (info->reg_type == PTR_TO_BTF_ID && info->btf_id == sock_id) + /* promote it to tcp_sock */ + info->btf_id = tcp_sock_id; + + return true; +} + +static int bpf_tcp_ca_btf_struct_access(struct bpf_verifier_log *log, + const struct btf_type *t, int off, + int size, enum bpf_access_type atype, + u32 *next_btf_id) +{ + size_t end; + + if (atype == BPF_READ) + return btf_struct_access(log, t, off, size, atype, next_btf_id); + + if (t != tcp_sock_type) { + bpf_log(log, "only read is supported\n"); + return -EACCES; + } + + switch (off) { + case bpf_ctx_range(struct inet_connection_sock, icsk_ca_priv): + end = offsetofend(struct inet_connection_sock, icsk_ca_priv); + break; + case offsetof(struct inet_connection_sock, icsk_ack.pending): + end = offsetofend(struct inet_connection_sock, + icsk_ack.pending); + break; + case offsetof(struct tcp_sock, snd_cwnd): + end = offsetofend(struct tcp_sock, snd_cwnd); + break; + case offsetof(struct tcp_sock, snd_cwnd_cnt): + end = offsetofend(struct tcp_sock, snd_cwnd_cnt); + break; + case offsetof(struct tcp_sock, snd_ssthresh): + end = offsetofend(struct tcp_sock, snd_ssthresh); + break; + case offsetof(struct tcp_sock, ecn_flags): + end = offsetofend(struct tcp_sock, ecn_flags); + break; + default: + bpf_log(log, "no write support to tcp_sock at off %d\n", off); + return -EACCES; + } + + if (off + size > end) { + bpf_log(log, + "write access at off %d with size %d beyond the member of tcp_sock ended at %zu\n", + off, size, end); + return -EACCES; + } + + return NOT_INIT; +} + +BPF_CALL_2(bpf_tcp_send_ack, struct tcp_sock *, tp, u32, rcv_nxt) +{ + /* bpf_tcp_ca prog cannot have NULL tp */ + __tcp_send_ack((struct sock *)tp, rcv_nxt); + return 0; +} + +static const struct bpf_func_proto bpf_tcp_send_ack_proto = { + .func = bpf_tcp_send_ack, + .gpl_only = false, + /* In case we want to report error later */ + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_BTF_ID, + .arg2_type = ARG_ANYTHING, + .btf_id = &tcp_sock_id, +}; + +static const struct bpf_func_proto * +bpf_tcp_ca_get_func_proto(enum bpf_func_id func_id, + const struct bpf_prog *prog) +{ + switch (func_id) { + case BPF_FUNC_tcp_send_ack: + return &bpf_tcp_send_ack_proto; + default: + return bpf_base_func_proto(func_id); + } +} + +static const struct bpf_verifier_ops bpf_tcp_ca_verifier_ops = { + .get_func_proto = bpf_tcp_ca_get_func_proto, + .is_valid_access = bpf_tcp_ca_is_valid_access, + .btf_struct_access = bpf_tcp_ca_btf_struct_access, +}; + +static int bpf_tcp_ca_init_member(const struct btf_type *t, + const struct btf_member *member, + void *kdata, const void *udata) +{ + const struct tcp_congestion_ops *utcp_ca; + struct tcp_congestion_ops *tcp_ca; + size_t tcp_ca_name_len; + int prog_fd; + u32 moff; + + utcp_ca = (const struct tcp_congestion_ops *)udata; + tcp_ca = (struct tcp_congestion_ops *)kdata; + + moff = btf_member_bit_offset(t, member) / 8; + switch (moff) { + case offsetof(struct tcp_congestion_ops, flags): + if (utcp_ca->flags & ~TCP_CONG_MASK) + return -EINVAL; + tcp_ca->flags = utcp_ca->flags; + return 1; + case offsetof(struct tcp_congestion_ops, name): + tcp_ca_name_len = strnlen(utcp_ca->name, sizeof(utcp_ca->name)); + if (!tcp_ca_name_len || + tcp_ca_name_len == sizeof(utcp_ca->name)) + return -EINVAL; + if (tcp_ca_find(utcp_ca->name)) + return -EEXIST; + memcpy(tcp_ca->name, utcp_ca->name, sizeof(tcp_ca->name)); + return 1; + } + + if (!btf_type_resolve_func_ptr(btf_vmlinux, member->type, NULL)) + return 0; + + /* Ensure bpf_prog is provided for compulsory func ptr */ + prog_fd = (int)(*(unsigned long *)(udata + moff)); + if (!prog_fd && !is_optional(moff) && !is_unsupported(moff)) + return -EINVAL; + + return 0; +} + +static int bpf_tcp_ca_check_member(const struct btf_type *t, + const struct btf_member *member) +{ + if (is_unsupported(btf_member_bit_offset(t, member) / 8)) + return -ENOTSUPP; + return 0; +} + +static int bpf_tcp_ca_reg(void *kdata) +{ + return tcp_register_congestion_control(kdata); +} + +static void bpf_tcp_ca_unreg(void *kdata) +{ + tcp_unregister_congestion_control(kdata); +} + +/* Avoid sparse warning. It is only used in bpf_struct_ops.c. */ +extern struct bpf_struct_ops bpf_tcp_congestion_ops; + +struct bpf_struct_ops bpf_tcp_congestion_ops = { + .verifier_ops = &bpf_tcp_ca_verifier_ops, + .reg = bpf_tcp_ca_reg, + .unreg = bpf_tcp_ca_unreg, + .check_member = bpf_tcp_ca_check_member, + .init_member = bpf_tcp_ca_init_member, + .init = bpf_tcp_ca_init, + .name = "tcp_congestion_ops", +}; diff --git a/net/ipv4/esp4.c b/net/ipv4/esp4.c index 5c967764041f..103c7d599a3c 100644 --- a/net/ipv4/esp4.c +++ b/net/ipv4/esp4.c @@ -18,6 +18,8 @@ #include <net/icmp.h> #include <net/protocol.h> #include <net/udp.h> +#include <net/tcp.h> +#include <net/espintcp.h> #include <linux/highmem.h> @@ -117,6 +119,132 @@ static void esp_ssg_unref(struct xfrm_state *x, void *tmp) put_page(sg_page(sg)); } +#ifdef CONFIG_INET_ESPINTCP +struct esp_tcp_sk { + struct sock *sk; + struct rcu_head rcu; +}; + +static void esp_free_tcp_sk(struct rcu_head *head) +{ + struct esp_tcp_sk *esk = container_of(head, struct esp_tcp_sk, rcu); + + sock_put(esk->sk); + kfree(esk); +} + +static struct sock *esp_find_tcp_sk(struct xfrm_state *x) +{ + struct xfrm_encap_tmpl *encap = x->encap; + struct esp_tcp_sk *esk; + __be16 sport, dport; + struct sock *nsk; + struct sock *sk; + + sk = rcu_dereference(x->encap_sk); + if (sk && sk->sk_state == TCP_ESTABLISHED) + return sk; + + spin_lock_bh(&x->lock); + sport = encap->encap_sport; + dport = encap->encap_dport; + nsk = rcu_dereference_protected(x->encap_sk, + lockdep_is_held(&x->lock)); + if (sk && sk == nsk) { + esk = kmalloc(sizeof(*esk), GFP_ATOMIC); + if (!esk) { + spin_unlock_bh(&x->lock); + return ERR_PTR(-ENOMEM); + } + RCU_INIT_POINTER(x->encap_sk, NULL); + esk->sk = sk; + call_rcu(&esk->rcu, esp_free_tcp_sk); + } + spin_unlock_bh(&x->lock); + + sk = inet_lookup_established(xs_net(x), &tcp_hashinfo, x->id.daddr.a4, + dport, x->props.saddr.a4, sport, 0); + if (!sk) + return ERR_PTR(-ENOENT); + + if (!tcp_is_ulp_esp(sk)) { + sock_put(sk); + return ERR_PTR(-EINVAL); + } + + spin_lock_bh(&x->lock); + nsk = rcu_dereference_protected(x->encap_sk, + lockdep_is_held(&x->lock)); + if (encap->encap_sport != sport || + encap->encap_dport != dport) { + sock_put(sk); + sk = nsk ?: ERR_PTR(-EREMCHG); + } else if (sk == nsk) { + sock_put(sk); + } else { + rcu_assign_pointer(x->encap_sk, sk); + } + spin_unlock_bh(&x->lock); + + return sk; +} + +static int esp_output_tcp_finish(struct xfrm_state *x, struct sk_buff *skb) +{ + struct sock *sk; + int err; + + rcu_read_lock(); + + sk = esp_find_tcp_sk(x); + err = PTR_ERR_OR_ZERO(sk); + if (err) + goto out; + + bh_lock_sock(sk); + if (sock_owned_by_user(sk)) + err = espintcp_queue_out(sk, skb); + else + err = espintcp_push_skb(sk, skb); + bh_unlock_sock(sk); + +out: + rcu_read_unlock(); + return err; +} + +static int esp_output_tcp_encap_cb(struct net *net, struct sock *sk, + struct sk_buff *skb) +{ + struct dst_entry *dst = skb_dst(skb); + struct xfrm_state *x = dst->xfrm; + + return esp_output_tcp_finish(x, skb); +} + +static int esp_output_tail_tcp(struct xfrm_state *x, struct sk_buff *skb) +{ + int err; + + local_bh_disable(); + err = xfrm_trans_queue_net(xs_net(x), skb, esp_output_tcp_encap_cb); + local_bh_enable(); + + /* EINPROGRESS just happens to do the right thing. It + * actually means that the skb has been consumed and + * isn't coming back. + */ + return err ?: -EINPROGRESS; +} +#else +static int esp_output_tail_tcp(struct xfrm_state *x, struct sk_buff *skb) +{ + kfree_skb(skb); + + return -EOPNOTSUPP; +} +#endif + static void esp_output_done(struct crypto_async_request *base, int err) { struct sk_buff *skb = base->data; @@ -147,7 +275,11 @@ static void esp_output_done(struct crypto_async_request *base, int err) secpath_reset(skb); xfrm_dev_resume(skb); } else { - xfrm_output_resume(skb, err); + if (!err && + x->encap && x->encap->encap_type == TCP_ENCAP_ESPINTCP) + esp_output_tail_tcp(x, skb); + else + xfrm_output_resume(skb, err); } } @@ -225,45 +357,100 @@ static void esp_output_fill_trailer(u8 *tail, int tfclen, int plen, __u8 proto) tail[plen - 1] = proto; } -static int esp_output_udp_encap(struct xfrm_state *x, struct sk_buff *skb, struct esp_info *esp) +static struct ip_esp_hdr *esp_output_udp_encap(struct sk_buff *skb, + int encap_type, + struct esp_info *esp, + __be16 sport, + __be16 dport) { - int encap_type; struct udphdr *uh; __be32 *udpdata32; - __be16 sport, dport; - struct xfrm_encap_tmpl *encap = x->encap; - struct ip_esp_hdr *esph = esp->esph; unsigned int len; - spin_lock_bh(&x->lock); - sport = encap->encap_sport; - dport = encap->encap_dport; - encap_type = encap->encap_type; - spin_unlock_bh(&x->lock); - len = skb->len + esp->tailen - skb_transport_offset(skb); - if (len + sizeof(struct iphdr) >= IP_MAX_MTU) - return -EMSGSIZE; + if (len + sizeof(struct iphdr) > IP_MAX_MTU) + return ERR_PTR(-EMSGSIZE); - uh = (struct udphdr *)esph; + uh = (struct udphdr *)esp->esph; uh->source = sport; uh->dest = dport; uh->len = htons(len); uh->check = 0; + *skb_mac_header(skb) = IPPROTO_UDP; + + if (encap_type == UDP_ENCAP_ESPINUDP_NON_IKE) { + udpdata32 = (__be32 *)(uh + 1); + udpdata32[0] = udpdata32[1] = 0; + return (struct ip_esp_hdr *)(udpdata32 + 2); + } + + return (struct ip_esp_hdr *)(uh + 1); +} + +#ifdef CONFIG_INET_ESPINTCP +static struct ip_esp_hdr *esp_output_tcp_encap(struct xfrm_state *x, + struct sk_buff *skb, + struct esp_info *esp) +{ + __be16 *lenp = (void *)esp->esph; + struct ip_esp_hdr *esph; + unsigned int len; + struct sock *sk; + + len = skb->len + esp->tailen - skb_transport_offset(skb); + if (len > IP_MAX_MTU) + return ERR_PTR(-EMSGSIZE); + + rcu_read_lock(); + sk = esp_find_tcp_sk(x); + rcu_read_unlock(); + + if (IS_ERR(sk)) + return ERR_CAST(sk); + + *lenp = htons(len); + esph = (struct ip_esp_hdr *)(lenp + 1); + + return esph; +} +#else +static struct ip_esp_hdr *esp_output_tcp_encap(struct xfrm_state *x, + struct sk_buff *skb, + struct esp_info *esp) +{ + return ERR_PTR(-EOPNOTSUPP); +} +#endif + +static int esp_output_encap(struct xfrm_state *x, struct sk_buff *skb, + struct esp_info *esp) +{ + struct xfrm_encap_tmpl *encap = x->encap; + struct ip_esp_hdr *esph; + __be16 sport, dport; + int encap_type; + + spin_lock_bh(&x->lock); + sport = encap->encap_sport; + dport = encap->encap_dport; + encap_type = encap->encap_type; + spin_unlock_bh(&x->lock); + switch (encap_type) { default: case UDP_ENCAP_ESPINUDP: - esph = (struct ip_esp_hdr *)(uh + 1); - break; case UDP_ENCAP_ESPINUDP_NON_IKE: - udpdata32 = (__be32 *)(uh + 1); - udpdata32[0] = udpdata32[1] = 0; - esph = (struct ip_esp_hdr *)(udpdata32 + 2); + esph = esp_output_udp_encap(skb, encap_type, esp, sport, dport); + break; + case TCP_ENCAP_ESPINTCP: + esph = esp_output_tcp_encap(x, skb, esp); break; } - *skb_mac_header(skb) = IPPROTO_UDP; + if (IS_ERR(esph)) + return PTR_ERR(esph); + esp->esph = esph; return 0; @@ -279,9 +466,9 @@ int esp_output_head(struct xfrm_state *x, struct sk_buff *skb, struct esp_info * struct sk_buff *trailer; int tailen = esp->tailen; - /* this is non-NULL only with UDP Encapsulation */ + /* this is non-NULL only with TCP/UDP Encapsulation */ if (x->encap) { - int err = esp_output_udp_encap(x, skb, esp); + int err = esp_output_encap(x, skb, esp); if (err < 0) return err; @@ -474,6 +661,9 @@ int esp_output_tail(struct xfrm_state *x, struct sk_buff *skb, struct esp_info * if (sg != dsg) esp_ssg_unref(x, tmp); + if (!err && x->encap && x->encap->encap_type == TCP_ENCAP_ESPINTCP) + err = esp_output_tail_tcp(x, skb); + error_free: kfree(tmp); error: @@ -600,7 +790,23 @@ int esp_input_done2(struct sk_buff *skb, int err) if (x->encap) { struct xfrm_encap_tmpl *encap = x->encap; + struct tcphdr *th = (void *)(skb_network_header(skb) + ihl); struct udphdr *uh = (void *)(skb_network_header(skb) + ihl); + __be16 source; + + switch (x->encap->encap_type) { + case TCP_ENCAP_ESPINTCP: + source = th->source; + break; + case UDP_ENCAP_ESPINUDP: + case UDP_ENCAP_ESPINUDP_NON_IKE: + source = uh->source; + break; + default: + WARN_ON_ONCE(1); + err = -EINVAL; + goto out; + } /* * 1) if the NAT-T peer's IP or port changed then @@ -609,11 +815,11 @@ int esp_input_done2(struct sk_buff *skb, int err) * SRC ports. */ if (iph->saddr != x->props.saddr.a4 || - uh->source != encap->encap_sport) { + source != encap->encap_sport) { xfrm_address_t ipaddr; ipaddr.a4 = iph->saddr; - km_new_mapping(x, &ipaddr, uh->source); + km_new_mapping(x, &ipaddr, source); /* XXX: perhaps add an extra * policy check here, to see @@ -988,6 +1194,14 @@ static int esp_init_state(struct xfrm_state *x) case UDP_ENCAP_ESPINUDP_NON_IKE: x->props.header_len += sizeof(struct udphdr) + 2 * sizeof(u32); break; +#ifdef CONFIG_INET_ESPINTCP + case TCP_ENCAP_ESPINTCP: + /* only the length field, TCP encap is done by + * the socket + */ + x->props.header_len += 2; + break; +#endif } } diff --git a/net/ipv4/fib_lookup.h b/net/ipv4/fib_lookup.h index a68b5e21ec51..c092e9a55790 100644 --- a/net/ipv4/fib_lookup.h +++ b/net/ipv4/fib_lookup.h @@ -16,6 +16,9 @@ struct fib_alias { u8 fa_slen; u32 tb_id; s16 fa_default; + u8 offload:1, + trap:1, + unused:6; struct rcu_head rcu; }; @@ -35,9 +38,8 @@ struct fib_info *fib_create_info(struct fib_config *cfg, int fib_nh_match(struct fib_config *cfg, struct fib_info *fi, struct netlink_ext_ack *extack); bool fib_metrics_match(struct fib_config *cfg, struct fib_info *fi); -int fib_dump_info(struct sk_buff *skb, u32 pid, u32 seq, int event, u32 tb_id, - u8 type, __be32 dst, int dst_len, u8 tos, struct fib_info *fi, - unsigned int); +int fib_dump_info(struct sk_buff *skb, u32 pid, u32 seq, int event, + struct fib_rt_info *fri, unsigned int flags); void rtmsg_fib(int event, __be32 key, struct fib_alias *fa, int dst_len, u32 tb_id, const struct nl_info *info, unsigned int nlm_flags); diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c index f1888c683426..a803cdd9400a 100644 --- a/net/ipv4/fib_semantics.c +++ b/net/ipv4/fib_semantics.c @@ -504,6 +504,7 @@ void rtmsg_fib(int event, __be32 key, struct fib_alias *fa, int dst_len, u32 tb_id, const struct nl_info *info, unsigned int nlm_flags) { + struct fib_rt_info fri; struct sk_buff *skb; u32 seq = info->nlh ? info->nlh->nlmsg_seq : 0; int err = -ENOBUFS; @@ -512,9 +513,15 @@ void rtmsg_fib(int event, __be32 key, struct fib_alias *fa, if (!skb) goto errout; - err = fib_dump_info(skb, info->portid, seq, event, tb_id, - fa->fa_type, key, dst_len, - fa->fa_tos, fa->fa_info, nlm_flags); + fri.fi = fa->fa_info; + fri.tb_id = tb_id; + fri.dst = key; + fri.dst_len = dst_len; + fri.tos = fa->fa_tos; + fri.type = fa->fa_type; + fri.offload = fa->offload; + fri.trap = fa->trap; + err = fib_dump_info(skb, info->portid, seq, event, &fri, nlm_flags); if (err < 0) { /* -EMSGSIZE implies BUG in fib_nlmsg_size() */ WARN_ON(err == -EMSGSIZE); @@ -1725,10 +1732,11 @@ static int fib_add_multipath(struct sk_buff *skb, struct fib_info *fi) #endif int fib_dump_info(struct sk_buff *skb, u32 portid, u32 seq, int event, - u32 tb_id, u8 type, __be32 dst, int dst_len, u8 tos, - struct fib_info *fi, unsigned int flags) + struct fib_rt_info *fri, unsigned int flags) { - unsigned int nhs = fib_info_num_path(fi); + unsigned int nhs = fib_info_num_path(fri->fi); + struct fib_info *fi = fri->fi; + u32 tb_id = fri->tb_id; struct nlmsghdr *nlh; struct rtmsg *rtm; @@ -1738,22 +1746,22 @@ int fib_dump_info(struct sk_buff *skb, u32 portid, u32 seq, int event, rtm = nlmsg_data(nlh); rtm->rtm_family = AF_INET; - rtm->rtm_dst_len = dst_len; + rtm->rtm_dst_len = fri->dst_len; rtm->rtm_src_len = 0; - rtm->rtm_tos = tos; + rtm->rtm_tos = fri->tos; if (tb_id < 256) rtm->rtm_table = tb_id; else rtm->rtm_table = RT_TABLE_COMPAT; if (nla_put_u32(skb, RTA_TABLE, tb_id)) goto nla_put_failure; - rtm->rtm_type = type; + rtm->rtm_type = fri->type; rtm->rtm_flags = fi->fib_flags; rtm->rtm_scope = fi->fib_scope; rtm->rtm_protocol = fi->fib_protocol; if (rtm->rtm_dst_len && - nla_put_in_addr(skb, RTA_DST, dst)) + nla_put_in_addr(skb, RTA_DST, fri->dst)) goto nla_put_failure; if (fi->fib_priority && nla_put_u32(skb, RTA_PRIORITY, fi->fib_priority)) @@ -1795,6 +1803,11 @@ int fib_dump_info(struct sk_buff *skb, u32 portid, u32 seq, int event, goto nla_put_failure; } + if (fri->offload) + rtm->rtm_flags |= RTM_F_OFFLOAD; + if (fri->trap) + rtm->rtm_flags |= RTM_F_TRAP; + nlmsg_end(skb, nlh); return 0; diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c index 195469a13371..ff0c24371e33 100644 --- a/net/ipv4/fib_trie.c +++ b/net/ipv4/fib_trie.c @@ -980,9 +980,12 @@ static struct key_vector *fib_find_node(struct trie *t, /* Return the first fib alias matching TOS with * priority less than or equal to PRIO. + * If 'find_first' is set, return the first matching + * fib alias, regardless of TOS and priority. */ static struct fib_alias *fib_find_alias(struct hlist_head *fah, u8 slen, - u8 tos, u32 prio, u32 tb_id) + u8 tos, u32 prio, u32 tb_id, + bool find_first) { struct fib_alias *fa; @@ -998,6 +1001,8 @@ static struct fib_alias *fib_find_alias(struct hlist_head *fah, u8 slen, continue; if (fa->tb_id != tb_id) break; + if (find_first) + return fa; if (fa->fa_tos > tos) continue; if (fa->fa_info->fib_priority >= prio || fa->fa_tos < tos) @@ -1007,6 +1012,52 @@ static struct fib_alias *fib_find_alias(struct hlist_head *fah, u8 slen, return NULL; } +static struct fib_alias * +fib_find_matching_alias(struct net *net, const struct fib_rt_info *fri) +{ + u8 slen = KEYLENGTH - fri->dst_len; + struct key_vector *l, *tp; + struct fib_table *tb; + struct fib_alias *fa; + struct trie *t; + + tb = fib_get_table(net, fri->tb_id); + if (!tb) + return NULL; + + t = (struct trie *)tb->tb_data; + l = fib_find_node(t, &tp, be32_to_cpu(fri->dst)); + if (!l) + return NULL; + + hlist_for_each_entry_rcu(fa, &l->leaf, fa_list) { + if (fa->fa_slen == slen && fa->tb_id == fri->tb_id && + fa->fa_tos == fri->tos && fa->fa_info == fri->fi && + fa->fa_type == fri->type) + return fa; + } + + return NULL; +} + +void fib_alias_hw_flags_set(struct net *net, const struct fib_rt_info *fri) +{ + struct fib_alias *fa_match; + + rcu_read_lock(); + + fa_match = fib_find_matching_alias(net, fri); + if (!fa_match) + goto out; + + fa_match->offload = fri->offload; + fa_match->trap = fri->trap; + +out: + rcu_read_unlock(); +} +EXPORT_SYMBOL_GPL(fib_alias_hw_flags_set); + static void trie_rebalance(struct trie *t, struct key_vector *tn) { while (!IS_TRIE(tn)) @@ -1063,9 +1114,6 @@ noleaf: return -ENOMEM; } -/* fib notifier for ADD is sent before calling fib_insert_alias with - * the expectation that the only possible failure ENOMEM - */ static int fib_insert_alias(struct trie *t, struct key_vector *tp, struct key_vector *l, struct fib_alias *new, struct fib_alias *fa, t_key key) @@ -1118,11 +1166,13 @@ static bool fib_valid_key_len(u32 key, u8 plen, struct netlink_ext_ack *extack) return true; } +static void fib_remove_alias(struct trie *t, struct key_vector *tp, + struct key_vector *l, struct fib_alias *old); + /* Caller must hold RTNL. */ int fib_table_insert(struct net *net, struct fib_table *tb, struct fib_config *cfg, struct netlink_ext_ack *extack) { - enum fib_event_type event = FIB_EVENT_ENTRY_ADD; struct trie *t = (struct trie *)tb->tb_data; struct fib_alias *fa, *new_fa; struct key_vector *l, *tp; @@ -1149,7 +1199,7 @@ int fib_table_insert(struct net *net, struct fib_table *tb, l = fib_find_node(t, &tp, key); fa = l ? fib_find_alias(&l->leaf, slen, tos, fi->fib_priority, - tb->tb_id) : NULL; + tb->tb_id, false) : NULL; /* Now fa, if non-NULL, points to the first fib alias * with the same keys [prefix,tos,priority], if such key already @@ -1216,19 +1266,29 @@ int fib_table_insert(struct net *net, struct fib_table *tb, new_fa->fa_slen = fa->fa_slen; new_fa->tb_id = tb->tb_id; new_fa->fa_default = -1; + new_fa->offload = 0; + new_fa->trap = 0; - err = call_fib_entry_notifiers(net, - FIB_EVENT_ENTRY_REPLACE, - key, plen, new_fa, - extack); - if (err) - goto out_free_new_fa; + hlist_replace_rcu(&fa->fa_list, &new_fa->fa_list); + + if (fib_find_alias(&l->leaf, fa->fa_slen, 0, 0, + tb->tb_id, true) == new_fa) { + enum fib_event_type fib_event; + + fib_event = FIB_EVENT_ENTRY_REPLACE; + err = call_fib_entry_notifiers(net, fib_event, + key, plen, + new_fa, extack); + if (err) { + hlist_replace_rcu(&new_fa->fa_list, + &fa->fa_list); + goto out_free_new_fa; + } + } rtmsg_fib(RTM_NEWROUTE, htonl(key), new_fa, plen, tb->tb_id, &cfg->fc_nlinfo, nlflags); - hlist_replace_rcu(&fa->fa_list, &new_fa->fa_list); - alias_free_mem_rcu(fa); fib_release_info(fi_drop); @@ -1244,12 +1304,10 @@ int fib_table_insert(struct net *net, struct fib_table *tb, if (fa_match) goto out; - if (cfg->fc_nlflags & NLM_F_APPEND) { - event = FIB_EVENT_ENTRY_APPEND; + if (cfg->fc_nlflags & NLM_F_APPEND) nlflags |= NLM_F_APPEND; - } else { + else fa = fa_first; - } } err = -ENOENT; if (!(cfg->fc_nlflags & NLM_F_CREATE)) @@ -1268,15 +1326,29 @@ int fib_table_insert(struct net *net, struct fib_table *tb, new_fa->fa_slen = slen; new_fa->tb_id = tb->tb_id; new_fa->fa_default = -1; - - err = call_fib_entry_notifiers(net, event, key, plen, new_fa, extack); - if (err) - goto out_free_new_fa; + new_fa->offload = 0; + new_fa->trap = 0; /* Insert new entry to the list. */ err = fib_insert_alias(t, tp, l, new_fa, fa, key); if (err) - goto out_fib_notif; + goto out_free_new_fa; + + /* The alias was already inserted, so the node must exist. */ + l = l ? l : fib_find_node(t, &tp, key); + if (WARN_ON_ONCE(!l)) + goto out_free_new_fa; + + if (fib_find_alias(&l->leaf, new_fa->fa_slen, 0, 0, tb->tb_id, true) == + new_fa) { + enum fib_event_type fib_event; + + fib_event = FIB_EVENT_ENTRY_REPLACE; + err = call_fib_entry_notifiers(net, fib_event, key, plen, + new_fa, extack); + if (err) + goto out_remove_new_fa; + } if (!plen) tb->tb_num_default++; @@ -1287,14 +1359,8 @@ int fib_table_insert(struct net *net, struct fib_table *tb, succeeded: return 0; -out_fib_notif: - /* notifier was sent that entry would be added to trie, but - * the add failed and need to recover. Only failure for - * fib_insert_alias is ENOMEM. - */ - NL_SET_ERR_MSG(extack, "Failed to insert route into trie"); - call_fib_entry_notifiers(net, FIB_EVENT_ENTRY_DEL, key, - plen, new_fa, NULL); +out_remove_new_fa: + fib_remove_alias(t, tp, l, new_fa); out_free_new_fa: kmem_cache_free(fn_alias_kmem, new_fa); out: @@ -1545,6 +1611,36 @@ static void fib_remove_alias(struct trie *t, struct key_vector *tp, node_pull_suffix(tp, fa->fa_slen); } +static void fib_notify_alias_delete(struct net *net, u32 key, + struct hlist_head *fah, + struct fib_alias *fa_to_delete, + struct netlink_ext_ack *extack) +{ + struct fib_alias *fa_next, *fa_to_notify; + u32 tb_id = fa_to_delete->tb_id; + u8 slen = fa_to_delete->fa_slen; + enum fib_event_type fib_event; + + /* Do not notify if we do not care about the route. */ + if (fib_find_alias(fah, slen, 0, 0, tb_id, true) != fa_to_delete) + return; + + /* Determine if the route should be replaced by the next route in the + * list. + */ + fa_next = hlist_entry_safe(fa_to_delete->fa_list.next, + struct fib_alias, fa_list); + if (fa_next && fa_next->fa_slen == slen && fa_next->tb_id == tb_id) { + fib_event = FIB_EVENT_ENTRY_REPLACE; + fa_to_notify = fa_next; + } else { + fib_event = FIB_EVENT_ENTRY_DEL; + fa_to_notify = fa_to_delete; + } + call_fib_entry_notifiers(net, fib_event, key, KEYLENGTH - slen, + fa_to_notify, extack); +} + /* Caller must hold RTNL. */ int fib_table_delete(struct net *net, struct fib_table *tb, struct fib_config *cfg, struct netlink_ext_ack *extack) @@ -1566,7 +1662,7 @@ int fib_table_delete(struct net *net, struct fib_table *tb, if (!l) return -ESRCH; - fa = fib_find_alias(&l->leaf, slen, tos, 0, tb->tb_id); + fa = fib_find_alias(&l->leaf, slen, tos, 0, tb->tb_id, false); if (!fa) return -ESRCH; @@ -1598,8 +1694,7 @@ int fib_table_delete(struct net *net, struct fib_table *tb, if (!fa_to_delete) return -ESRCH; - call_fib_entry_notifiers(net, FIB_EVENT_ENTRY_DEL, key, plen, - fa_to_delete, extack); + fib_notify_alias_delete(net, key, &l->leaf, fa_to_delete, extack); rtmsg_fib(RTM_DELROUTE, htonl(key), fa_to_delete, plen, tb->tb_id, &cfg->fc_nlinfo, 0); @@ -1923,10 +2018,8 @@ int fib_table_flush(struct net *net, struct fib_table *tb, bool flush_all) continue; } - call_fib_entry_notifiers(net, FIB_EVENT_ENTRY_DEL, - n->key, - KEYLENGTH - fa->fa_slen, fa, - NULL); + fib_notify_alias_delete(net, n->key, &n->leaf, fa, + NULL); hlist_del_rcu(&fa->fa_list); fib_release_info(fa->fa_info); alias_free_mem_rcu(fa); @@ -2022,6 +2115,7 @@ static int fib_leaf_notify(struct key_vector *l, struct fib_table *tb, struct netlink_ext_ack *extack) { struct fib_alias *fa; + int last_slen = -1; int err; hlist_for_each_entry_rcu(fa, &l->leaf, fa_list) { @@ -2036,8 +2130,12 @@ static int fib_leaf_notify(struct key_vector *l, struct fib_table *tb, if (tb->tb_id != fa->tb_id) continue; - err = call_fib_entry_notifier(nb, FIB_EVENT_ENTRY_ADD, l->key, - KEYLENGTH - fa->fa_slen, + if (fa->fa_slen == last_slen) + continue; + + last_slen = fa->fa_slen; + err = call_fib_entry_notifier(nb, FIB_EVENT_ENTRY_REPLACE, + l->key, KEYLENGTH - fa->fa_slen, fa, extack); if (err) return err; @@ -2146,14 +2244,20 @@ static int fn_trie_dump_leaf(struct key_vector *l, struct fib_table *tb, if (filter->dump_routes) { if (!s_fa) { + struct fib_rt_info fri; + + fri.fi = fi; + fri.tb_id = tb->tb_id; + fri.dst = xkey; + fri.dst_len = KEYLENGTH - fa->fa_slen; + fri.tos = fa->fa_tos; + fri.type = fa->fa_type; + fri.offload = fa->offload; + fri.trap = fa->trap; err = fib_dump_info(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, - RTM_NEWROUTE, - tb->tb_id, fa->fa_type, - xkey, - KEYLENGTH - fa->fa_slen, - fa->fa_tos, fi, flags); + RTM_NEWROUTE, &fri, flags); if (err < 0) goto stop; } diff --git a/net/ipv4/gre_offload.c b/net/ipv4/gre_offload.c index 4de7e962d3da..2e6d1b7a7bc9 100644 --- a/net/ipv4/gre_offload.c +++ b/net/ipv4/gre_offload.c @@ -174,7 +174,7 @@ static struct sk_buff *gre_gro_receive(struct list_head *head, if (skb_gro_checksum_simple_validate(skb)) goto out_unlock; - skb_gro_checksum_try_convert(skb, IPPROTO_GRE, 0, + skb_gro_checksum_try_convert(skb, IPPROTO_GRE, null_compute_pseudo); } diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index 18c0d5bffe12..a4db79b1b643 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -610,12 +610,6 @@ no_route: } EXPORT_SYMBOL_GPL(inet_csk_route_child_sock); -#if IS_ENABLED(CONFIG_IPV6) -#define AF_INET_FAMILY(fam) ((fam) == AF_INET) -#else -#define AF_INET_FAMILY(fam) true -#endif - /* Decide when to expire the request and when to resend SYN-ACK */ static inline void syn_ack_recalc(struct request_sock *req, const int thresh, const int max_retries, @@ -770,6 +764,18 @@ void inet_csk_reqsk_queue_hash_add(struct sock *sk, struct request_sock *req, } EXPORT_SYMBOL_GPL(inet_csk_reqsk_queue_hash_add); +static void inet_clone_ulp(const struct request_sock *req, struct sock *newsk, + const gfp_t priority) +{ + struct inet_connection_sock *icsk = inet_csk(newsk); + + if (!icsk->icsk_ulp_ops) + return; + + if (icsk->icsk_ulp_ops->clone) + icsk->icsk_ulp_ops->clone(req, newsk, priority); +} + /** * inet_csk_clone_lock - clone an inet socket, and lock its clone * @sk: the socket to clone @@ -810,6 +816,8 @@ struct sock *inet_csk_clone_lock(const struct sock *sk, /* Deinitialize accept_queue to trap illegal accesses. */ memset(&newicsk->icsk_accept_queue, 0, sizeof(newicsk->icsk_accept_queue)); + inet_clone_ulp(req, newsk, priority); + security_inet_csk_clone(newsk, req); } return newsk; diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index 14db1e0b8a6e..d84819893db9 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -240,8 +240,8 @@ static int ip_finish_output2(struct net *net, struct sock *sk, struct sk_buff *s static int ip_finish_output_gso(struct net *net, struct sock *sk, struct sk_buff *skb, unsigned int mtu) { + struct sk_buff *segs, *nskb; netdev_features_t features; - struct sk_buff *segs; int ret = 0; /* common case: seglen is <= mtu @@ -272,8 +272,7 @@ static int ip_finish_output_gso(struct net *net, struct sock *sk, consume_skb(skb); - do { - struct sk_buff *nskb = segs->next; + skb_list_walk_safe(segs, segs, nskb) { int err; skb_mark_not_on_list(segs); @@ -281,8 +280,7 @@ static int ip_finish_output_gso(struct net *net, struct sock *sk, if (err && ret == 0) ret = err; - segs = nskb; - } while (segs); + } return ret; } diff --git a/net/ipv4/nexthop.c b/net/ipv4/nexthop.c index 511eaa94e2d1..d072c326dd64 100644 --- a/net/ipv4/nexthop.c +++ b/net/ipv4/nexthop.c @@ -321,7 +321,9 @@ static size_t nh_nlmsg_size_single(struct nexthop *nh) static size_t nh_nlmsg_size(struct nexthop *nh) { - size_t sz = nla_total_size(4); /* NHA_ID */ + size_t sz = NLMSG_ALIGN(sizeof(struct nhmsg)); + + sz += nla_total_size(4); /* NHA_ID */ if (nh->is_group) sz += nh_nlmsg_size_grp(nh); diff --git a/net/ipv4/proc.c b/net/ipv4/proc.c index cc90243ccf76..2580303249e2 100644 --- a/net/ipv4/proc.c +++ b/net/ipv4/proc.c @@ -289,6 +289,8 @@ static const struct snmp_mib snmp4_net_list[] = { SNMP_MIB_ITEM("TCPRcvQDrop", LINUX_MIB_TCPRCVQDROP), SNMP_MIB_ITEM("TCPWqueueTooBig", LINUX_MIB_TCPWQUEUETOOBIG), SNMP_MIB_ITEM("TCPFastOpenPassiveAltKey", LINUX_MIB_TCPFASTOPENPASSIVEALTKEY), + SNMP_MIB_ITEM("TcpTimeoutRehash", LINUX_MIB_TCPTIMEOUTREHASH), + SNMP_MIB_ITEM("TcpDuplicateDataRehash", LINUX_MIB_TCPDUPLICATEDATAREHASH), SNMP_MIB_SENTINEL }; diff --git a/net/ipv4/route.c b/net/ipv4/route.c index e356ea779227..d5c57b3f77d5 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -3224,16 +3224,41 @@ static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh, skb_reset_mac_header(skb); if (rtm->rtm_flags & RTM_F_FIB_MATCH) { + struct fib_rt_info fri; + if (!res.fi) { err = fib_props[res.type].error; if (!err) err = -EHOSTUNREACH; goto errout_rcu; } + fri.fi = res.fi; + fri.tb_id = table_id; + fri.dst = res.prefix; + fri.dst_len = res.prefixlen; + fri.tos = fl4.flowi4_tos; + fri.type = rt->rt_type; + fri.offload = 0; + fri.trap = 0; + if (res.fa_head) { + struct fib_alias *fa; + + hlist_for_each_entry_rcu(fa, res.fa_head, fa_list) { + u8 slen = 32 - fri.dst_len; + + if (fa->fa_slen == slen && + fa->tb_id == fri.tb_id && + fa->fa_tos == fri.tos && + fa->fa_info == res.fi && + fa->fa_type == fri.type) { + fri.offload = fa->offload; + fri.trap = fa->trap; + break; + } + } + } err = fib_dump_info(skb, NETLINK_CB(in_skb).portid, - nlh->nlmsg_seq, RTM_NEWROUTE, table_id, - rt->rt_type, res.prefix, res.prefixlen, - fl4.flowi4_tos, res.fi, 0); + nlh->nlmsg_seq, RTM_NEWROUTE, &fri, 0); } else { err = rt_fill_info(net, dst, src, rt, table_id, &fl4, skb, NETLINK_CB(in_skb).portid, diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c index fcb2cd167f64..9684af02e0a5 100644 --- a/net/ipv4/sysctl_net_ipv4.c +++ b/net/ipv4/sysctl_net_ipv4.c @@ -1193,6 +1193,15 @@ static struct ctl_table ipv4_net_table[] = { .proc_handler = proc_dointvec, }, { + .procname = "tcp_no_ssthresh_metrics_save", + .data = &init_net.ipv4.sysctl_tcp_no_ssthresh_metrics_save, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_ONE, + }, + { .procname = "tcp_moderate_rcvbuf", .data = &init_net.ipv4.sysctl_tcp_moderate_rcvbuf, .maxlen = sizeof(int), diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index a7d766e6390e..484485ae74c2 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -271,6 +271,7 @@ #include <net/icmp.h> #include <net/inet_common.h> #include <net/tcp.h> +#include <net/mptcp.h> #include <net/xfrm.h> #include <net/ip.h> #include <net/sock.h> @@ -443,8 +444,6 @@ void tcp_init_sock(struct sock *sk) tp->tsoffset = 0; tp->rack.reo_wnd_steps = 1; - sk->sk_state = TCP_CLOSE; - sk->sk_write_space = sk_stream_write_space; sock_set_flag(sk, SOCK_USE_WRITE_QUEUE); @@ -692,8 +691,8 @@ static bool tcp_should_autocork(struct sock *sk, struct sk_buff *skb, refcount_read(&sk->sk_wmem_alloc) > skb->truesize; } -static void tcp_push(struct sock *sk, int flags, int mss_now, - int nonagle, int size_goal) +void tcp_push(struct sock *sk, int flags, int mss_now, + int nonagle, int size_goal) { struct tcp_sock *tp = tcp_sk(sk); struct sk_buff *skb; @@ -927,7 +926,7 @@ static unsigned int tcp_xmit_size_goal(struct sock *sk, u32 mss_now, return max(size_goal, mss_now); } -static int tcp_send_mss(struct sock *sk, int *size_goal, int flags) +int tcp_send_mss(struct sock *sk, int *size_goal, int flags) { int mss_now; @@ -1778,6 +1777,8 @@ static int tcp_zerocopy_receive(struct sock *sk, while (length + PAGE_SIZE <= zc->length) { if (zc->recv_skip_hint < PAGE_SIZE) { if (skb) { + if (zc->recv_skip_hint > 0) + break; skb = skb->next; offset = seq - TCP_SKB_CB(skb)->seq; } else { @@ -3336,6 +3337,7 @@ static size_t tcp_opt_stats_get_size(void) nla_total_size(sizeof(u32)) + /* TCP_NLA_DSACK_DUPS */ nla_total_size(sizeof(u32)) + /* TCP_NLA_REORD_SEEN */ nla_total_size(sizeof(u32)) + /* TCP_NLA_SRTT */ + nla_total_size(sizeof(u16)) + /* TCP_NLA_TIMEOUT_REHASH */ 0; } @@ -3390,6 +3392,7 @@ struct sk_buff *tcp_get_timestamping_opt_stats(const struct sock *sk) nla_put_u32(stats, TCP_NLA_DSACK_DUPS, tp->dsack_dups); nla_put_u32(stats, TCP_NLA_REORD_SEEN, tp->reord_seen); nla_put_u32(stats, TCP_NLA_SRTT, tp->srtt_us >> 3); + nla_put_u16(stats, TCP_NLA_TIMEOUT_REHASH, tp->timeout_rehash); return stats; } @@ -4021,4 +4024,5 @@ void __init tcp_init(void) tcp_metrics_init(); BUG_ON(tcp_register_congestion_control(&tcp_reno) != 0); tcp_tasklet_init(); + mptcp_init(); } diff --git a/net/ipv4/tcp_cong.c b/net/ipv4/tcp_cong.c index 3737ec096650..3172e31987be 100644 --- a/net/ipv4/tcp_cong.c +++ b/net/ipv4/tcp_cong.c @@ -21,7 +21,7 @@ static DEFINE_SPINLOCK(tcp_cong_list_lock); static LIST_HEAD(tcp_cong_list); /* Simple linear search, don't expect many entries! */ -static struct tcp_congestion_ops *tcp_ca_find(const char *name) +struct tcp_congestion_ops *tcp_ca_find(const char *name) { struct tcp_congestion_ops *e; @@ -162,7 +162,7 @@ void tcp_assign_congestion_control(struct sock *sk) rcu_read_lock(); ca = rcu_dereference(net->ipv4.tcp_congestion_control); - if (unlikely(!try_module_get(ca->owner))) + if (unlikely(!bpf_try_module_get(ca, ca->owner))) ca = &tcp_reno; icsk->icsk_ca_ops = ca; rcu_read_unlock(); @@ -208,7 +208,7 @@ void tcp_cleanup_congestion_control(struct sock *sk) if (icsk->icsk_ca_ops->release) icsk->icsk_ca_ops->release(sk); - module_put(icsk->icsk_ca_ops->owner); + bpf_module_put(icsk->icsk_ca_ops, icsk->icsk_ca_ops->owner); } /* Used by sysctl to change default congestion control */ @@ -222,12 +222,12 @@ int tcp_set_default_congestion_control(struct net *net, const char *name) ca = tcp_ca_find_autoload(net, name); if (!ca) { ret = -ENOENT; - } else if (!try_module_get(ca->owner)) { + } else if (!bpf_try_module_get(ca, ca->owner)) { ret = -EBUSY; } else { prev = xchg(&net->ipv4.tcp_congestion_control, ca); if (prev) - module_put(prev->owner); + bpf_module_put(prev, prev->owner); ca->flags |= TCP_CONG_NON_RESTRICTED; ret = 0; @@ -366,19 +366,19 @@ int tcp_set_congestion_control(struct sock *sk, const char *name, bool load, } else if (!load) { const struct tcp_congestion_ops *old_ca = icsk->icsk_ca_ops; - if (try_module_get(ca->owner)) { + if (bpf_try_module_get(ca, ca->owner)) { if (reinit) { tcp_reinit_congestion_control(sk, ca); } else { icsk->icsk_ca_ops = ca; - module_put(old_ca->owner); + bpf_module_put(old_ca, old_ca->owner); } } else { err = -EBUSY; } } else if (!((ca->flags & TCP_CONG_NON_RESTRICTED) || cap_net_admin)) { err = -EPERM; - } else if (!try_module_get(ca->owner)) { + } else if (!bpf_try_module_get(ca, ca->owner)) { err = -EBUSY; } else { tcp_reinit_congestion_control(sk, ca); diff --git a/net/ipv4/tcp_cubic.c b/net/ipv4/tcp_cubic.c index 1b3d032a4df2..8f8eefd3a3ce 100644 --- a/net/ipv4/tcp_cubic.c +++ b/net/ipv4/tcp_cubic.c @@ -40,8 +40,8 @@ /* Number of delay samples for detecting the increase of delay */ #define HYSTART_MIN_SAMPLES 8 -#define HYSTART_DELAY_MIN (4U<<3) -#define HYSTART_DELAY_MAX (16U<<3) +#define HYSTART_DELAY_MIN (4000U) /* 4 ms */ +#define HYSTART_DELAY_MAX (16000U) /* 16 ms */ #define HYSTART_DELAY_THRESH(x) clamp(x, HYSTART_DELAY_MIN, HYSTART_DELAY_MAX) static int fast_convergence __read_mostly = 1; @@ -53,7 +53,7 @@ static int tcp_friendliness __read_mostly = 1; static int hystart __read_mostly = 1; static int hystart_detect __read_mostly = HYSTART_ACK_TRAIN | HYSTART_DELAY; static int hystart_low_window __read_mostly = 16; -static int hystart_ack_delta __read_mostly = 2; +static int hystart_ack_delta_us __read_mostly = 2000; static u32 cube_rtt_scale __read_mostly; static u32 beta_scale __read_mostly; @@ -77,8 +77,8 @@ MODULE_PARM_DESC(hystart_detect, "hybrid slow start detection mechanisms" " 1: packet-train 2: delay 3: both packet-train and delay"); module_param(hystart_low_window, int, 0644); MODULE_PARM_DESC(hystart_low_window, "lower bound cwnd for hybrid slow start"); -module_param(hystart_ack_delta, int, 0644); -MODULE_PARM_DESC(hystart_ack_delta, "spacing between ack's indicating train (msecs)"); +module_param(hystart_ack_delta_us, int, 0644); +MODULE_PARM_DESC(hystart_ack_delta_us, "spacing between ack's indicating train (usecs)"); /* BIC TCP Parameters */ struct bictcp { @@ -89,7 +89,7 @@ struct bictcp { u32 bic_origin_point;/* origin point of bic function */ u32 bic_K; /* time to origin point from the beginning of the current epoch */ - u32 delay_min; /* min delay (msec << 3) */ + u32 delay_min; /* min delay (usec) */ u32 epoch_start; /* beginning of an epoch */ u32 ack_cnt; /* number of acks */ u32 tcp_cwnd; /* estimated tcp cwnd */ @@ -117,13 +117,9 @@ static inline void bictcp_reset(struct bictcp *ca) ca->found = 0; } -static inline u32 bictcp_clock(void) +static inline u32 bictcp_clock_us(const struct sock *sk) { -#if HZ < 1000 - return ktime_to_ms(ktime_get_real()); -#else - return jiffies_to_msecs(jiffies); -#endif + return tcp_sk(sk)->tcp_mstamp; } static inline void bictcp_hystart_reset(struct sock *sk) @@ -131,9 +127,9 @@ static inline void bictcp_hystart_reset(struct sock *sk) struct tcp_sock *tp = tcp_sk(sk); struct bictcp *ca = inet_csk_ca(sk); - ca->round_start = ca->last_ack = bictcp_clock(); + ca->round_start = ca->last_ack = bictcp_clock_us(sk); ca->end_seq = tp->snd_nxt; - ca->curr_rtt = 0; + ca->curr_rtt = ~0U; ca->sample_cnt = 0; } @@ -276,7 +272,7 @@ static inline void bictcp_update(struct bictcp *ca, u32 cwnd, u32 acked) */ t = (s32)(tcp_jiffies32 - ca->epoch_start); - t += msecs_to_jiffies(ca->delay_min >> 3); + t += usecs_to_jiffies(ca->delay_min); /* change the unit from HZ to bictcp_HZ */ t <<= BICTCP_HZ; do_div(t, HZ); @@ -376,22 +372,54 @@ static void bictcp_state(struct sock *sk, u8 new_state) } } +/* Account for TSO/GRO delays. + * Otherwise short RTT flows could get too small ssthresh, since during + * slow start we begin with small TSO packets and ca->delay_min would + * not account for long aggregation delay when TSO packets get bigger. + * Ideally even with a very small RTT we would like to have at least one + * TSO packet being sent and received by GRO, and another one in qdisc layer. + * We apply another 100% factor because @rate is doubled at this point. + * We cap the cushion to 1ms. + */ +static u32 hystart_ack_delay(struct sock *sk) +{ + unsigned long rate; + + rate = READ_ONCE(sk->sk_pacing_rate); + if (!rate) + return 0; + return min_t(u64, USEC_PER_MSEC, + div64_ul((u64)GSO_MAX_SIZE * 4 * USEC_PER_SEC, rate)); +} + static void hystart_update(struct sock *sk, u32 delay) { struct tcp_sock *tp = tcp_sk(sk); struct bictcp *ca = inet_csk_ca(sk); - - if (ca->found & hystart_detect) - return; + u32 threshold; if (hystart_detect & HYSTART_ACK_TRAIN) { - u32 now = bictcp_clock(); + u32 now = bictcp_clock_us(sk); /* first detection parameter - ack-train detection */ - if ((s32)(now - ca->last_ack) <= hystart_ack_delta) { + if ((s32)(now - ca->last_ack) <= hystart_ack_delta_us) { ca->last_ack = now; - if ((s32)(now - ca->round_start) > ca->delay_min >> 4) { - ca->found |= HYSTART_ACK_TRAIN; + + threshold = ca->delay_min + hystart_ack_delay(sk); + + /* Hystart ack train triggers if we get ack past + * ca->delay_min/2. + * Pacing might have delayed packets up to RTT/2 + * during slow start. + */ + if (sk->sk_pacing_status == SK_PACING_NONE) + threshold >>= 1; + + if ((s32)(now - ca->round_start) > threshold) { + ca->found = 1; + pr_debug("hystart_ack_train (%u > %u) delay_min %u (+ ack_delay %u) cwnd %u\n", + now - ca->round_start, threshold, + ca->delay_min, hystart_ack_delay(sk), tp->snd_cwnd); NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPHYSTARTTRAINDETECT); NET_ADD_STATS(sock_net(sk), @@ -405,14 +433,14 @@ 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->sample_cnt < HYSTART_MIN_SAMPLES) { - if (ca->curr_rtt == 0 || ca->curr_rtt > delay) + if (ca->curr_rtt > delay) ca->curr_rtt = delay; ca->sample_cnt++; } else { if (ca->curr_rtt > ca->delay_min + HYSTART_DELAY_THRESH(ca->delay_min >> 3)) { - ca->found |= HYSTART_DELAY; + ca->found = 1; NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPHYSTARTDELAYDETECT); NET_ADD_STATS(sock_net(sk), @@ -424,9 +452,6 @@ static void hystart_update(struct sock *sk, u32 delay) } } -/* Track delayed acknowledgment ratio using sliding window - * ratio = (15*ratio + sample) / 16 - */ static void bictcp_acked(struct sock *sk, const struct ack_sample *sample) { const struct tcp_sock *tp = tcp_sk(sk); @@ -441,7 +466,7 @@ static void bictcp_acked(struct sock *sk, const struct ack_sample *sample) if (ca->epoch_start && (s32)(tcp_jiffies32 - ca->epoch_start) < HZ) return; - delay = (sample->rtt_us << 3) / USEC_PER_MSEC; + delay = sample->rtt_us; if (delay == 0) delay = 1; @@ -450,7 +475,7 @@ static void bictcp_acked(struct sock *sk, const struct ack_sample *sample) ca->delay_min = delay; /* hystart triggers when cwnd is larger than some threshold */ - if (hystart && tcp_in_slow_start(tp) && + if (!ca->found && tcp_in_slow_start(tp) && hystart && tp->snd_cwnd >= hystart_low_window) hystart_update(sk, delay); } diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 2a976f57f7e7..e8b840a4767e 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -79,6 +79,7 @@ #include <trace/events/tcp.h> #include <linux/jump_label_ratelimit.h> #include <net/busy_poll.h> +#include <net/mptcp.h> int sysctl_tcp_max_orphans __read_mostly = NR_FILE; @@ -1423,7 +1424,7 @@ static struct sk_buff *tcp_shift_skb_data(struct sock *sk, struct sk_buff *skb, if ((TCP_SKB_CB(prev)->sacked & TCPCB_TAGBITS) != TCPCB_SACKED_ACKED) goto fallback; - if (!tcp_skb_can_collapse_to(prev)) + if (!tcp_skb_can_collapse(prev, skb)) goto fallback; in_sack = !after(start_seq, TCP_SKB_CB(skb)->seq) && @@ -3555,7 +3556,7 @@ static void tcp_xmit_recovery(struct sock *sk, int rexmit) if (rexmit == REXMIT_NONE || sk->sk_state == TCP_SYN_SENT) return; - if (unlikely(rexmit == 2)) { + if (unlikely(rexmit == REXMIT_NEW)) { __tcp_push_pending_frames(sk, tcp_current_mss(sk), TCP_NAGLE_OFF); if (after(tp->snd_nxt, tp->high_seq)) @@ -3925,6 +3926,10 @@ void tcp_parse_options(const struct net *net, */ break; #endif + case TCPOPT_MPTCP: + mptcp_parse_option(skb, ptr, opsize, opt_rx); + break; + case TCPOPT_FASTOPEN: tcp_parse_fastopen_option( opsize - TCPOLEN_FASTOPEN_BASE, @@ -4266,8 +4271,10 @@ static void tcp_rcv_spurious_retrans(struct sock *sk, const struct sk_buff *skb) * The receiver remembers and reflects via DSACKs. Leverage the * DSACK state and change the txhash to re-route speculatively. */ - if (TCP_SKB_CB(skb)->seq == tcp_sk(sk)->duplicate_sack[0].start_seq) + if (TCP_SKB_CB(skb)->seq == tcp_sk(sk)->duplicate_sack[0].start_seq) { sk_rethink_txhash(sk); + NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPDUPLICATEDATAREHASH); + } } static void tcp_send_dupack(struct sock *sk, const struct sk_buff *skb) @@ -4425,6 +4432,9 @@ static bool tcp_try_coalesce(struct sock *sk, if (TCP_SKB_CB(from)->seq != TCP_SKB_CB(to)->end_seq) return false; + if (!mptcp_skb_can_collapse(to, from)) + return false; + #ifdef CONFIG_TLS_DEVICE if (from->decrypted != to->decrypted) return false; @@ -4763,6 +4773,9 @@ static void tcp_data_queue(struct sock *sk, struct sk_buff *skb) bool fragstolen; int eaten; + if (sk_is_mptcp(sk)) + mptcp_incoming_options(sk, skb, &tp->rx_opt); + if (TCP_SKB_CB(skb)->seq == TCP_SKB_CB(skb)->end_seq) { __kfree_skb(skb); return; @@ -4934,7 +4947,7 @@ restart: /* The first skb to collapse is: * - not SYN/FIN and * - bloated or contains data before "start" or - * overlaps to the next one. + * overlaps to the next one and mptcp allow collapsing. */ if (!(TCP_SKB_CB(skb)->tcp_flags & (TCPHDR_SYN | TCPHDR_FIN)) && (tcp_win_from_space(sk, skb->truesize) > skb->len || @@ -4943,7 +4956,7 @@ restart: break; } - if (n && n != tail && + if (n && n != tail && mptcp_skb_can_collapse(skb, n) && TCP_SKB_CB(skb)->end_seq != TCP_SKB_CB(n)->seq) { end_of_skbs = false; break; @@ -4976,6 +4989,7 @@ restart: else __skb_queue_tail(&tmp, nskb); /* defer rbtree insertion */ skb_set_owner_r(nskb, sk); + mptcp_skb_ext_move(nskb, skb); /* Copy data, releasing collapsed skbs. */ while (copy > 0) { @@ -4995,6 +5009,7 @@ restart: skb = tcp_collapse_one(sk, skb, list, root); if (!skb || skb == tail || + !mptcp_skb_can_collapse(nskb, skb) || (TCP_SKB_CB(skb)->tcp_flags & (TCPHDR_SYN | TCPHDR_FIN))) goto end; #ifdef CONFIG_TLS_DEVICE @@ -5969,6 +5984,9 @@ static int tcp_rcv_synsent_state_process(struct sock *sk, struct sk_buff *skb, tcp_sync_mss(sk, icsk->icsk_pmtu_cookie); tcp_initialize_rcv_mss(sk); + if (sk_is_mptcp(sk)) + mptcp_rcv_synsent(sk); + /* Remember, tcp_poll() does not lock socket! * Change state from SYN-SENT only after copied_seq * is initialized. */ @@ -6334,8 +6352,11 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb) case TCP_CLOSE_WAIT: case TCP_CLOSING: case TCP_LAST_ACK: - if (!before(TCP_SKB_CB(skb)->seq, tp->rcv_nxt)) + if (!before(TCP_SKB_CB(skb)->seq, tp->rcv_nxt)) { + if (sk_is_mptcp(sk)) + mptcp_incoming_options(sk, skb, &tp->rx_opt); break; + } /* fall through */ case TCP_FIN_WAIT1: case TCP_FIN_WAIT2: @@ -6591,6 +6612,9 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops, tcp_rsk(req)->af_specific = af_ops; tcp_rsk(req)->ts_off = 0; +#if IS_ENABLED(CONFIG_MPTCP) + tcp_rsk(req)->is_mptcp = 0; +#endif tcp_clear_options(&tmp_opt); tmp_opt.mss_clamp = af_ops->mss_clamp; diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 1c7326e04f9b..df1166b76126 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -701,9 +701,21 @@ static void tcp_v4_send_reset(const struct sock *sk, struct sk_buff *skb) rcu_read_lock(); hash_location = tcp_parse_md5sig_option(th); if (sk && sk_fullsock(sk)) { - key = tcp_md5_do_lookup(sk, (union tcp_md5_addr *) - &ip_hdr(skb)->saddr, AF_INET); + const union tcp_md5_addr *addr; + int l3index; + + /* sdif set, means packet ingressed via a device + * in an L3 domain and inet_iif is set to it. + */ + l3index = tcp_v4_sdif(skb) ? inet_iif(skb) : 0; + addr = (union tcp_md5_addr *)&ip_hdr(skb)->saddr; + key = tcp_md5_do_lookup(sk, l3index, addr, AF_INET); } else if (hash_location) { + const union tcp_md5_addr *addr; + int sdif = tcp_v4_sdif(skb); + int dif = inet_iif(skb); + int l3index; + /* * active side is lost. Try to find listening socket through * source port, and then find md5 key through listening socket. @@ -714,14 +726,17 @@ static void tcp_v4_send_reset(const struct sock *sk, struct sk_buff *skb) sk1 = __inet_lookup_listener(net, &tcp_hashinfo, NULL, 0, ip_hdr(skb)->saddr, th->source, ip_hdr(skb)->daddr, - ntohs(th->source), inet_iif(skb), - tcp_v4_sdif(skb)); + ntohs(th->source), dif, sdif); /* don't send rst if it can't find key */ if (!sk1) goto out; - key = tcp_md5_do_lookup(sk1, (union tcp_md5_addr *) - &ip_hdr(skb)->saddr, AF_INET); + /* sdif set, means packet ingressed via a device + * in an L3 domain and dif is set to it. + */ + l3index = sdif ? dif : 0; + addr = (union tcp_md5_addr *)&ip_hdr(skb)->saddr; + key = tcp_md5_do_lookup(sk1, l3index, addr, AF_INET); if (!key) goto out; @@ -905,6 +920,9 @@ static void tcp_v4_timewait_ack(struct sock *sk, struct sk_buff *skb) static void tcp_v4_reqsk_send_ack(const struct sock *sk, struct sk_buff *skb, struct request_sock *req) { + const union tcp_md5_addr *addr; + int l3index; + /* sk->sk_state == TCP_LISTEN -> for regular TCP_SYN_RECV * sk->sk_state == TCP_SYN_RECV -> for Fast Open. */ @@ -916,14 +934,15 @@ static void tcp_v4_reqsk_send_ack(const struct sock *sk, struct sk_buff *skb, * exception of <SYN> segments, MUST be right-shifted by * Rcv.Wind.Shift bits: */ + addr = (union tcp_md5_addr *)&ip_hdr(skb)->saddr; + l3index = tcp_v4_sdif(skb) ? inet_iif(skb) : 0; tcp_v4_send_ack(sk, skb, seq, tcp_rsk(req)->rcv_nxt, req->rsk_rcv_wnd >> inet_rsk(req)->rcv_wscale, tcp_time_stamp_raw() + tcp_rsk(req)->ts_off, req->ts_recent, 0, - tcp_md5_do_lookup(sk, (union tcp_md5_addr *)&ip_hdr(skb)->saddr, - AF_INET), + tcp_md5_do_lookup(sk, l3index, addr, AF_INET), inet_rsk(req)->no_srccheck ? IP_REPLY_ARG_NOSRCCHECK : 0, ip_hdr(skb)->tos); } @@ -983,7 +1002,7 @@ DEFINE_STATIC_KEY_FALSE(tcp_md5_needed); EXPORT_SYMBOL(tcp_md5_needed); /* Find the Key structure for an address. */ -struct tcp_md5sig_key *__tcp_md5_do_lookup(const struct sock *sk, +struct tcp_md5sig_key *__tcp_md5_do_lookup(const struct sock *sk, int l3index, const union tcp_md5_addr *addr, int family) { @@ -1003,7 +1022,8 @@ struct tcp_md5sig_key *__tcp_md5_do_lookup(const struct sock *sk, hlist_for_each_entry_rcu(key, &md5sig->head, node) { if (key->family != family) continue; - + if (key->l3index && key->l3index != l3index) + continue; if (family == AF_INET) { mask = inet_make_mask(key->prefixlen); match = (key->addr.a4.s_addr & mask) == @@ -1027,7 +1047,8 @@ EXPORT_SYMBOL(__tcp_md5_do_lookup); static struct tcp_md5sig_key *tcp_md5_do_lookup_exact(const struct sock *sk, const union tcp_md5_addr *addr, - int family, u8 prefixlen) + int family, u8 prefixlen, + int l3index) { const struct tcp_sock *tp = tcp_sk(sk); struct tcp_md5sig_key *key; @@ -1046,6 +1067,8 @@ static struct tcp_md5sig_key *tcp_md5_do_lookup_exact(const struct sock *sk, hlist_for_each_entry_rcu(key, &md5sig->head, node) { if (key->family != family) continue; + if (key->l3index && key->l3index != l3index) + continue; if (!memcmp(&key->addr, addr, size) && key->prefixlen == prefixlen) return key; @@ -1057,23 +1080,26 @@ struct tcp_md5sig_key *tcp_v4_md5_lookup(const struct sock *sk, const struct sock *addr_sk) { const union tcp_md5_addr *addr; + int l3index; + l3index = l3mdev_master_ifindex_by_index(sock_net(sk), + addr_sk->sk_bound_dev_if); addr = (const union tcp_md5_addr *)&addr_sk->sk_daddr; - return tcp_md5_do_lookup(sk, addr, AF_INET); + return tcp_md5_do_lookup(sk, l3index, addr, AF_INET); } EXPORT_SYMBOL(tcp_v4_md5_lookup); /* This can be called on a newly created socket, from other files */ int tcp_md5_do_add(struct sock *sk, const union tcp_md5_addr *addr, - int family, u8 prefixlen, const u8 *newkey, u8 newkeylen, - gfp_t gfp) + int family, u8 prefixlen, int l3index, + const u8 *newkey, u8 newkeylen, gfp_t gfp) { /* Add Key to the list */ struct tcp_md5sig_key *key; struct tcp_sock *tp = tcp_sk(sk); struct tcp_md5sig_info *md5sig; - key = tcp_md5_do_lookup_exact(sk, addr, family, prefixlen); + key = tcp_md5_do_lookup_exact(sk, addr, family, prefixlen, l3index); if (key) { /* Pre-existing entry - just update that one. */ memcpy(key->key, newkey, newkeylen); @@ -1105,6 +1131,7 @@ int tcp_md5_do_add(struct sock *sk, const union tcp_md5_addr *addr, key->keylen = newkeylen; key->family = family; key->prefixlen = prefixlen; + key->l3index = l3index; memcpy(&key->addr, addr, (family == AF_INET6) ? sizeof(struct in6_addr) : sizeof(struct in_addr)); @@ -1114,11 +1141,11 @@ int tcp_md5_do_add(struct sock *sk, const union tcp_md5_addr *addr, EXPORT_SYMBOL(tcp_md5_do_add); int tcp_md5_do_del(struct sock *sk, const union tcp_md5_addr *addr, int family, - u8 prefixlen) + u8 prefixlen, int l3index) { struct tcp_md5sig_key *key; - key = tcp_md5_do_lookup_exact(sk, addr, family, prefixlen); + key = tcp_md5_do_lookup_exact(sk, addr, family, prefixlen, l3index); if (!key) return -ENOENT; hlist_del_rcu(&key->node); @@ -1149,7 +1176,9 @@ static int tcp_v4_parse_md5_keys(struct sock *sk, int optname, { struct tcp_md5sig cmd; struct sockaddr_in *sin = (struct sockaddr_in *)&cmd.tcpm_addr; + const union tcp_md5_addr *addr; u8 prefixlen = 32; + int l3index = 0; if (optlen < sizeof(cmd)) return -EINVAL; @@ -1167,16 +1196,34 @@ static int tcp_v4_parse_md5_keys(struct sock *sk, int optname, return -EINVAL; } + if (optname == TCP_MD5SIG_EXT && + cmd.tcpm_flags & TCP_MD5SIG_FLAG_IFINDEX) { + struct net_device *dev; + + rcu_read_lock(); + dev = dev_get_by_index_rcu(sock_net(sk), cmd.tcpm_ifindex); + if (dev && netif_is_l3_master(dev)) + l3index = dev->ifindex; + + rcu_read_unlock(); + + /* ok to reference set/not set outside of rcu; + * right now device MUST be an L3 master + */ + if (!dev || !l3index) + return -EINVAL; + } + + addr = (union tcp_md5_addr *)&sin->sin_addr.s_addr; + if (!cmd.tcpm_keylen) - return tcp_md5_do_del(sk, (union tcp_md5_addr *)&sin->sin_addr.s_addr, - AF_INET, prefixlen); + return tcp_md5_do_del(sk, addr, AF_INET, prefixlen, l3index); if (cmd.tcpm_keylen > TCP_MD5SIG_MAXKEYLEN) return -EINVAL; - return tcp_md5_do_add(sk, (union tcp_md5_addr *)&sin->sin_addr.s_addr, - AF_INET, prefixlen, cmd.tcpm_key, cmd.tcpm_keylen, - GFP_KERNEL); + return tcp_md5_do_add(sk, addr, AF_INET, prefixlen, l3index, + cmd.tcpm_key, cmd.tcpm_keylen, GFP_KERNEL); } static int tcp_v4_md5_hash_headers(struct tcp_md5sig_pool *hp, @@ -1286,7 +1333,8 @@ EXPORT_SYMBOL(tcp_v4_md5_hash_skb); /* Called with rcu_read_lock() */ static bool tcp_v4_inbound_md5_hash(const struct sock *sk, - const struct sk_buff *skb) + const struct sk_buff *skb, + int dif, int sdif) { #ifdef CONFIG_TCP_MD5SIG /* @@ -1301,11 +1349,17 @@ static bool tcp_v4_inbound_md5_hash(const struct sock *sk, struct tcp_md5sig_key *hash_expected; const struct iphdr *iph = ip_hdr(skb); const struct tcphdr *th = tcp_hdr(skb); - int genhash; + const union tcp_md5_addr *addr; unsigned char newhash[16]; + int genhash, l3index; - hash_expected = tcp_md5_do_lookup(sk, (union tcp_md5_addr *)&iph->saddr, - AF_INET); + /* sdif set, means packet ingressed via a device + * in an L3 domain and dif is set to the l3mdev + */ + l3index = sdif ? dif : 0; + + addr = (union tcp_md5_addr *)&iph->saddr; + hash_expected = tcp_md5_do_lookup(sk, l3index, addr, AF_INET); hash_location = tcp_parse_md5sig_option(th); /* We've parsed the options - do we have a hash? */ @@ -1331,11 +1385,11 @@ static bool tcp_v4_inbound_md5_hash(const struct sock *sk, if (genhash || memcmp(hash_location, newhash, 16) != 0) { NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPMD5FAILURE); - net_info_ratelimited("MD5 Hash failed for (%pI4, %d)->(%pI4, %d)%s\n", + net_info_ratelimited("MD5 Hash failed for (%pI4, %d)->(%pI4, %d)%s L3 index %d\n", &iph->saddr, ntohs(th->source), &iph->daddr, ntohs(th->dest), genhash ? " tcp_v4_calc_md5_hash failed" - : ""); + : "", l3index); return true; } return false; @@ -1372,7 +1426,7 @@ struct request_sock_ops tcp_request_sock_ops __read_mostly = { .syn_ack_timeout = tcp_syn_ack_timeout, }; -static const struct tcp_request_sock_ops tcp_request_sock_ipv4_ops = { +const struct tcp_request_sock_ops tcp_request_sock_ipv4_ops = { .mss_clamp = TCP_MSS_DEFAULT, #ifdef CONFIG_TCP_MD5SIG .req_md5_lookup = tcp_v4_md5_lookup, @@ -1419,7 +1473,9 @@ struct sock *tcp_v4_syn_recv_sock(const struct sock *sk, struct sk_buff *skb, struct tcp_sock *newtp; struct sock *newsk; #ifdef CONFIG_TCP_MD5SIG + const union tcp_md5_addr *addr; struct tcp_md5sig_key *key; + int l3index; #endif struct ip_options_rcu *inet_opt; @@ -1467,9 +1523,10 @@ struct sock *tcp_v4_syn_recv_sock(const struct sock *sk, struct sk_buff *skb, tcp_initialize_rcv_mss(newsk); #ifdef CONFIG_TCP_MD5SIG + l3index = l3mdev_master_ifindex_by_index(sock_net(sk), ireq->ir_iif); /* Copy over the MD5 key from the original socket */ - key = tcp_md5_do_lookup(sk, (union tcp_md5_addr *)&newinet->inet_daddr, - AF_INET); + addr = (union tcp_md5_addr *)&newinet->inet_daddr; + key = tcp_md5_do_lookup(sk, l3index, addr, AF_INET); if (key) { /* * We're using one, so create a matching key @@ -1477,8 +1534,8 @@ struct sock *tcp_v4_syn_recv_sock(const struct sock *sk, struct sk_buff *skb, * memory, then we end up not copying the key * across. Shucks. */ - tcp_md5_do_add(newsk, (union tcp_md5_addr *)&newinet->inet_daddr, - AF_INET, 32, key->key, key->keylen, GFP_ATOMIC); + tcp_md5_do_add(newsk, addr, AF_INET, 32, l3index, + key->key, key->keylen, GFP_ATOMIC); sk_nocaps_add(newsk, NETIF_F_GSO_MASK); } #endif @@ -1808,6 +1865,7 @@ int tcp_v4_rcv(struct sk_buff *skb) struct net *net = dev_net(skb->dev); struct sk_buff *skb_to_free; int sdif = inet_sdif(skb); + int dif = inet_iif(skb); const struct iphdr *iph; const struct tcphdr *th; bool refcounted; @@ -1856,7 +1914,7 @@ process: struct sock *nsk; sk = req->rsk_listener; - if (unlikely(tcp_v4_inbound_md5_hash(sk, skb))) { + if (unlikely(tcp_v4_inbound_md5_hash(sk, skb, dif, sdif))) { sk_drops_add(sk, skb); reqsk_put(req); goto discard_it; @@ -1914,7 +1972,7 @@ process: if (!xfrm4_policy_check(sk, XFRM_POLICY_IN, skb)) goto discard_and_relse; - if (tcp_v4_inbound_md5_hash(sk, skb)) + if (tcp_v4_inbound_md5_hash(sk, skb, dif, sdif)) goto discard_and_relse; nf_reset_ct(skb); @@ -2620,7 +2678,8 @@ static void __net_exit tcp_sk_exit(struct net *net) int cpu; if (net->ipv4.tcp_congestion_control) - module_put(net->ipv4.tcp_congestion_control->owner); + bpf_module_put(net->ipv4.tcp_congestion_control, + net->ipv4.tcp_congestion_control->owner); for_each_possible_cpu(cpu) inet_ctl_sock_destroy(*per_cpu_ptr(net->ipv4.tcp_sk, cpu)); @@ -2675,6 +2734,7 @@ static int __net_init tcp_sk_init(struct net *net) net->ipv4.sysctl_tcp_fin_timeout = TCP_FIN_TIMEOUT; net->ipv4.sysctl_tcp_notsent_lowat = UINT_MAX; net->ipv4.sysctl_tcp_tw_reuse = 2; + net->ipv4.sysctl_tcp_no_ssthresh_metrics_save = 1; cnt = tcp_hashinfo.ehash_mask + 1; net->ipv4.tcp_death_row.sysctl_max_tw_buckets = cnt / 2; @@ -2726,7 +2786,8 @@ static int __net_init tcp_sk_init(struct net *net) /* Reno is always built in */ if (!net_eq(net, &init_net) && - try_module_get(init_net.ipv4.tcp_congestion_control->owner)) + bpf_try_module_get(init_net.ipv4.tcp_congestion_control, + init_net.ipv4.tcp_congestion_control->owner)) net->ipv4.tcp_congestion_control = init_net.ipv4.tcp_congestion_control; else net->ipv4.tcp_congestion_control = &tcp_reno; diff --git a/net/ipv4/tcp_metrics.c b/net/ipv4/tcp_metrics.c index c4848e7a0aad..279db8822439 100644 --- a/net/ipv4/tcp_metrics.c +++ b/net/ipv4/tcp_metrics.c @@ -385,7 +385,8 @@ void tcp_update_metrics(struct sock *sk) if (tcp_in_initial_slowstart(tp)) { /* Slow start still did not finish. */ - if (!tcp_metric_locked(tm, TCP_METRIC_SSTHRESH)) { + if (!net->ipv4.sysctl_tcp_no_ssthresh_metrics_save && + !tcp_metric_locked(tm, TCP_METRIC_SSTHRESH)) { val = tcp_metric_get(tm, TCP_METRIC_SSTHRESH); if (val && (tp->snd_cwnd >> 1) > val) tcp_metric_set(tm, TCP_METRIC_SSTHRESH, @@ -400,7 +401,8 @@ void tcp_update_metrics(struct sock *sk) } else if (!tcp_in_slow_start(tp) && icsk->icsk_ca_state == TCP_CA_Open) { /* Cong. avoidance phase, cwnd is reliable. */ - if (!tcp_metric_locked(tm, TCP_METRIC_SSTHRESH)) + if (!net->ipv4.sysctl_tcp_no_ssthresh_metrics_save && + !tcp_metric_locked(tm, TCP_METRIC_SSTHRESH)) tcp_metric_set(tm, TCP_METRIC_SSTHRESH, max(tp->snd_cwnd >> 1, tp->snd_ssthresh)); if (!tcp_metric_locked(tm, TCP_METRIC_CWND)) { @@ -416,7 +418,8 @@ void tcp_update_metrics(struct sock *sk) tcp_metric_set(tm, TCP_METRIC_CWND, (val + tp->snd_ssthresh) >> 1); } - if (!tcp_metric_locked(tm, TCP_METRIC_SSTHRESH)) { + if (!net->ipv4.sysctl_tcp_no_ssthresh_metrics_save && + !tcp_metric_locked(tm, TCP_METRIC_SSTHRESH)) { val = tcp_metric_get(tm, TCP_METRIC_SSTHRESH); if (val && tp->snd_ssthresh > val) tcp_metric_set(tm, TCP_METRIC_SSTHRESH, @@ -441,6 +444,7 @@ void tcp_init_metrics(struct sock *sk) { struct dst_entry *dst = __sk_dst_get(sk); struct tcp_sock *tp = tcp_sk(sk); + struct net *net = sock_net(sk); struct tcp_metrics_block *tm; u32 val, crtt = 0; /* cached RTT scaled by 8 */ @@ -458,7 +462,8 @@ void tcp_init_metrics(struct sock *sk) if (tcp_metric_locked(tm, TCP_METRIC_CWND)) tp->snd_cwnd_clamp = tcp_metric_get(tm, TCP_METRIC_CWND); - val = tcp_metric_get(tm, TCP_METRIC_SSTHRESH); + val = net->ipv4.sysctl_tcp_no_ssthresh_metrics_save ? + 0 : tcp_metric_get(tm, TCP_METRIC_SSTHRESH); if (val) { tp->snd_ssthresh = val; if (tp->snd_ssthresh > tp->snd_cwnd_clamp) diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index c802bc80c400..ad3b56d9fa71 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -414,7 +414,7 @@ void tcp_ca_openreq_child(struct sock *sk, const struct dst_entry *dst) rcu_read_lock(); ca = tcp_ca_find_key(ca_key); - if (likely(ca && try_module_get(ca->owner))) { + if (likely(ca && bpf_try_module_get(ca, ca->owner))) { icsk->icsk_ca_dst_locked = tcp_ca_dst_locked(dst); icsk->icsk_ca_ops = ca; ca_got_dst = true; @@ -425,7 +425,7 @@ void tcp_ca_openreq_child(struct sock *sk, const struct dst_entry *dst) /* If no valid choice made yet, assign current system default ca. */ if (!ca_got_dst && (!icsk->icsk_ca_setsockopt || - !try_module_get(icsk->icsk_ca_ops->owner))) + !bpf_try_module_get(icsk->icsk_ca_ops, icsk->icsk_ca_ops->owner))) tcp_assign_congestion_control(sk); tcp_set_ca_state(sk, TCP_CA_Open); diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index b62b59b18db9..306e25d743e8 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -38,6 +38,7 @@ #define pr_fmt(fmt) "TCP: " fmt #include <net/tcp.h> +#include <net/mptcp.h> #include <linux/compiler.h> #include <linux/gfp.h> @@ -414,6 +415,7 @@ static inline bool tcp_urg_mode(const struct tcp_sock *tp) #define OPTION_WSCALE (1 << 3) #define OPTION_FAST_OPEN_COOKIE (1 << 8) #define OPTION_SMC (1 << 9) +#define OPTION_MPTCP (1 << 10) static void smc_options_write(__be32 *ptr, u16 *options) { @@ -439,8 +441,17 @@ struct tcp_out_options { __u8 *hash_location; /* temporary pointer, overloaded */ __u32 tsval, tsecr; /* need to include OPTION_TS */ struct tcp_fastopen_cookie *fastopen_cookie; /* Fast open cookie */ + struct mptcp_out_options mptcp; }; +static void mptcp_options_write(__be32 *ptr, struct tcp_out_options *opts) +{ +#if IS_ENABLED(CONFIG_MPTCP) + if (unlikely(OPTION_MPTCP & opts->options)) + mptcp_write_options(ptr, &opts->mptcp); +#endif +} + /* Write previously computed TCP options to the packet. * * Beware: Something in the Internet is very sensitive to the ordering of @@ -549,6 +560,8 @@ static void tcp_options_write(__be32 *ptr, struct tcp_sock *tp, } smc_options_write(ptr, &options); + + mptcp_options_write(ptr, opts); } static void smc_set_option(const struct tcp_sock *tp, @@ -584,6 +597,22 @@ static void smc_set_option_cond(const struct tcp_sock *tp, #endif } +static void mptcp_set_option_cond(const struct request_sock *req, + struct tcp_out_options *opts, + unsigned int *remaining) +{ + if (rsk_is_mptcp(req)) { + unsigned int size; + + if (mptcp_synack_options(req, &size, &opts->mptcp)) { + if (*remaining >= size) { + opts->options |= OPTION_MPTCP; + *remaining -= size; + } + } + } +} + /* Compute TCP options for SYN packets. This is not the final * network wire format yet. */ @@ -653,6 +682,15 @@ static unsigned int tcp_syn_options(struct sock *sk, struct sk_buff *skb, smc_set_option(tp, opts, &remaining); + if (sk_is_mptcp(sk)) { + unsigned int size; + + if (mptcp_syn_options(sk, skb, &size, &opts->mptcp)) { + opts->options |= OPTION_MPTCP; + remaining -= size; + } + } + return MAX_TCP_OPTION_SPACE - remaining; } @@ -714,6 +752,8 @@ static unsigned int tcp_synack_options(const struct sock *sk, } } + mptcp_set_option_cond(req, opts, &remaining); + smc_set_option_cond(tcp_sk(sk), ireq, opts, &remaining); return MAX_TCP_OPTION_SPACE - remaining; @@ -751,16 +791,37 @@ static unsigned int tcp_established_options(struct sock *sk, struct sk_buff *skb size += TCPOLEN_TSTAMP_ALIGNED; } + /* MPTCP options have precedence over SACK for the limited TCP + * option space because a MPTCP connection would be forced to + * fall back to regular TCP if a required multipath option is + * missing. SACK still gets a chance to use whatever space is + * left. + */ + if (sk_is_mptcp(sk)) { + unsigned int remaining = MAX_TCP_OPTION_SPACE - size; + unsigned int opt_size = 0; + + if (mptcp_established_options(sk, skb, &opt_size, remaining, + &opts->mptcp)) { + opts->options |= OPTION_MPTCP; + size += opt_size; + } + } + eff_sacks = tp->rx_opt.num_sacks + tp->rx_opt.dsack; if (unlikely(eff_sacks)) { const unsigned int remaining = MAX_TCP_OPTION_SPACE - size; + if (unlikely(remaining < TCPOLEN_SACK_BASE_ALIGNED + + TCPOLEN_SACK_PERBLOCK)) + return size; + opts->num_sack_blocks = min_t(unsigned int, eff_sacks, (remaining - TCPOLEN_SACK_BASE_ALIGNED) / TCPOLEN_SACK_PERBLOCK); - if (likely(opts->num_sack_blocks)) - size += TCPOLEN_SACK_BASE_ALIGNED + - opts->num_sack_blocks * TCPOLEN_SACK_PERBLOCK; + + size += TCPOLEN_SACK_BASE_ALIGNED + + opts->num_sack_blocks * TCPOLEN_SACK_PERBLOCK; } return size; @@ -2865,7 +2926,7 @@ static void tcp_retrans_try_collapse(struct sock *sk, struct sk_buff *to, if (!tcp_can_collapse(sk, skb)) break; - if (!tcp_skb_can_collapse_to(to)) + if (!tcp_skb_can_collapse(to, skb)) break; space -= skb->len; @@ -3369,8 +3430,8 @@ static void tcp_ca_dst_init(struct sock *sk, const struct dst_entry *dst) rcu_read_lock(); ca = tcp_ca_find_key(ca_key); - if (likely(ca && try_module_get(ca->owner))) { - module_put(icsk->icsk_ca_ops->owner); + if (likely(ca && bpf_try_module_get(ca, ca->owner))) { + bpf_module_put(icsk->icsk_ca_ops, icsk->icsk_ca_ops->owner); icsk->icsk_ca_dst_locked = tcp_ca_dst_locked(dst); icsk->icsk_ca_ops = ca; } diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c index 1097b438befe..c3f26dcd6704 100644 --- a/net/ipv4/tcp_timer.c +++ b/net/ipv4/tcp_timer.c @@ -223,6 +223,9 @@ static int tcp_write_timeout(struct sock *sk) dst_negative_advice(sk); } else { sk_rethink_txhash(sk); + tp->timeout_rehash++; + __NET_INC_STATS(sock_net(sk), + LINUX_MIB_TCPTIMEOUTREHASH); } retry_until = icsk->icsk_syn_retries ? : net->ipv4.sysctl_tcp_syn_retries; expired = icsk->icsk_retransmits >= retry_until; @@ -234,6 +237,9 @@ static int tcp_write_timeout(struct sock *sk) dst_negative_advice(sk); } else { sk_rethink_txhash(sk); + tp->timeout_rehash++; + __NET_INC_STATS(sock_net(sk), + LINUX_MIB_TCPTIMEOUTREHASH); } retry_until = net->ipv4.sysctl_tcp_retries2; diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 030d43c7c957..db76b9609299 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -1709,7 +1709,8 @@ busy_check: /* sk_queue is empty, reader_queue may contain peeked packets */ } while (timeo && - !__skb_wait_for_more_packets(sk, &error, &timeo, + !__skb_wait_for_more_packets(sk, &sk->sk_receive_queue, + &error, &timeo, (struct sk_buff *)sk_queue)); *err = error; @@ -2105,8 +2106,7 @@ static int udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) BUILD_BUG_ON(sizeof(struct udp_skb_cb) > SKB_SGO_CB_OFFSET); __skb_push(skb, -skb_mac_offset(skb)); segs = udp_rcv_segment(sk, skb, true); - for (skb = segs; skb; skb = next) { - next = skb->next; + skb_list_walk_safe(segs, skb, next) { __skb_pull(skb, skb_transport_offset(skb)); ret = udp_queue_rcv_one_skb(sk, skb); if (ret > 0) diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c index a3908e55ed89..1a98583a79f4 100644 --- a/net/ipv4/udp_offload.c +++ b/net/ipv4/udp_offload.c @@ -184,6 +184,20 @@ out_unlock: } EXPORT_SYMBOL(skb_udp_tunnel_segment); +static struct sk_buff *__udp_gso_segment_list(struct sk_buff *skb, + netdev_features_t features) +{ + unsigned int mss = skb_shinfo(skb)->gso_size; + + skb = skb_segment_list(skb, features, skb_mac_header_len(skb)); + if (IS_ERR(skb)) + return skb; + + udp_hdr(skb)->len = htons(sizeof(struct udphdr) + mss); + + return skb; +} + struct sk_buff *__udp_gso_segment(struct sk_buff *gso_skb, netdev_features_t features) { @@ -196,6 +210,9 @@ struct sk_buff *__udp_gso_segment(struct sk_buff *gso_skb, __sum16 check; __be16 newlen; + if (skb_shinfo(gso_skb)->gso_type & SKB_GSO_FRAGLIST) + return __udp_gso_segment_list(gso_skb, features); + mss = skb_shinfo(gso_skb)->gso_size; if (gso_skb->len <= sizeof(*uh) + mss) return ERR_PTR(-EINVAL); @@ -354,6 +371,7 @@ static struct sk_buff *udp_gro_receive_segment(struct list_head *head, struct udphdr *uh2; struct sk_buff *p; unsigned int ulen; + int ret = 0; /* requires non zero csum, for symmetry with GSO */ if (!uh->check) { @@ -369,7 +387,6 @@ static struct sk_buff *udp_gro_receive_segment(struct list_head *head, } /* pull encapsulating udp header */ skb_gro_pull(skb, sizeof(struct udphdr)); - skb_gro_postpull_rcsum(skb, uh, sizeof(struct udphdr)); list_for_each_entry(p, head, list) { if (!NAPI_GRO_CB(p)->same_flow) @@ -383,14 +400,40 @@ static struct sk_buff *udp_gro_receive_segment(struct list_head *head, continue; } + if (NAPI_GRO_CB(skb)->is_flist != NAPI_GRO_CB(p)->is_flist) { + NAPI_GRO_CB(skb)->flush = 1; + return p; + } + /* Terminate the flow on len mismatch or if it grow "too much". * Under small packet flood GRO count could elsewhere grow a lot * leading to excessive truesize values. * On len mismatch merge the first packet shorter than gso_size, * otherwise complete the GRO packet. */ - if (ulen > ntohs(uh2->len) || skb_gro_receive(p, skb) || - ulen != ntohs(uh2->len) || + if (ulen > ntohs(uh2->len)) { + pp = p; + } else { + if (NAPI_GRO_CB(skb)->is_flist) { + if (!pskb_may_pull(skb, skb_gro_offset(skb))) { + NAPI_GRO_CB(skb)->flush = 1; + return NULL; + } + if ((skb->ip_summed != p->ip_summed) || + (skb->csum_level != p->csum_level)) { + NAPI_GRO_CB(skb)->flush = 1; + return NULL; + } + ret = skb_gro_receive_list(p, skb); + } else { + skb_gro_postpull_rcsum(skb, uh, + sizeof(struct udphdr)); + + ret = skb_gro_receive(p, skb); + } + } + + if (ret || ulen != ntohs(uh2->len) || NAPI_GRO_CB(p)->count >= UDP_GRO_CNT_MAX) pp = p; @@ -401,36 +444,29 @@ static struct sk_buff *udp_gro_receive_segment(struct list_head *head, return NULL; } -INDIRECT_CALLABLE_DECLARE(struct sock *udp6_lib_lookup_skb(struct sk_buff *skb, - __be16 sport, __be16 dport)); struct sk_buff *udp_gro_receive(struct list_head *head, struct sk_buff *skb, - struct udphdr *uh, udp_lookup_t lookup) + struct udphdr *uh, struct sock *sk) { struct sk_buff *pp = NULL; struct sk_buff *p; struct udphdr *uh2; unsigned int off = skb_gro_offset(skb); int flush = 1; - struct sock *sk; - rcu_read_lock(); - sk = INDIRECT_CALL_INET(lookup, udp6_lib_lookup_skb, - udp4_lib_lookup_skb, skb, uh->source, uh->dest); - if (!sk) - goto out_unlock; + if (skb->dev->features & NETIF_F_GRO_FRAGLIST) + NAPI_GRO_CB(skb)->is_flist = sk ? !udp_sk(sk)->gro_enabled: 1; - if (udp_sk(sk)->gro_enabled) { + if ((sk && udp_sk(sk)->gro_enabled) || NAPI_GRO_CB(skb)->is_flist) { pp = call_gro_receive(udp_gro_receive_segment, head, skb); - rcu_read_unlock(); return pp; } - if (NAPI_GRO_CB(skb)->encap_mark || + if (!sk || NAPI_GRO_CB(skb)->encap_mark || (skb->ip_summed != CHECKSUM_PARTIAL && NAPI_GRO_CB(skb)->csum_cnt == 0 && !NAPI_GRO_CB(skb)->csum_valid) || !udp_sk(sk)->gro_receive) - goto out_unlock; + goto out; /* mark that this skb passed once through the tunnel gro layer */ NAPI_GRO_CB(skb)->encap_mark = 1; @@ -457,8 +493,7 @@ struct sk_buff *udp_gro_receive(struct list_head *head, struct sk_buff *skb, skb_gro_postpull_rcsum(skb, uh, sizeof(struct udphdr)); pp = call_gro_receive_sk(udp_sk(sk)->gro_receive, sk, head, skb); -out_unlock: - rcu_read_unlock(); +out: skb_gro_flush_final(skb, pp, flush); return pp; } @@ -468,8 +503,10 @@ INDIRECT_CALLABLE_SCOPE struct sk_buff *udp4_gro_receive(struct list_head *head, struct sk_buff *skb) { struct udphdr *uh = udp_gro_udphdr(skb); + struct sk_buff *pp; + struct sock *sk; - if (unlikely(!uh) || !static_branch_unlikely(&udp_encap_needed_key)) + if (unlikely(!uh)) goto flush; /* Don't bother verifying checksum if we're going to flush anyway. */ @@ -480,11 +517,15 @@ struct sk_buff *udp4_gro_receive(struct list_head *head, struct sk_buff *skb) inet_gro_compute_pseudo)) goto flush; else if (uh->check) - skb_gro_checksum_try_convert(skb, IPPROTO_UDP, uh->check, + skb_gro_checksum_try_convert(skb, IPPROTO_UDP, inet_gro_compute_pseudo); skip: NAPI_GRO_CB(skb)->is_ipv6 = 0; - return udp_gro_receive(head, skb, uh, udp4_lib_lookup_skb); + rcu_read_lock(); + sk = static_branch_unlikely(&udp_encap_needed_key) ? udp4_lib_lookup_skb(skb, uh->source, uh->dest) : NULL; + pp = udp_gro_receive(head, skb, uh, sk); + rcu_read_unlock(); + return pp; flush: NAPI_GRO_CB(skb)->flush = 1; @@ -517,9 +558,7 @@ int udp_gro_complete(struct sk_buff *skb, int nhoff, rcu_read_lock(); sk = INDIRECT_CALL_INET(lookup, udp6_lib_lookup_skb, udp4_lib_lookup_skb, skb, uh->source, uh->dest); - if (sk && udp_sk(sk)->gro_enabled) { - err = udp_gro_complete_segment(skb); - } else if (sk && udp_sk(sk)->gro_complete) { + if (sk && udp_sk(sk)->gro_complete) { skb_shinfo(skb)->gso_type = uh->check ? SKB_GSO_UDP_TUNNEL_CSUM : SKB_GSO_UDP_TUNNEL; @@ -529,6 +568,8 @@ int udp_gro_complete(struct sk_buff *skb, int nhoff, skb->encapsulation = 1; err = udp_sk(sk)->gro_complete(sk, skb, nhoff + sizeof(struct udphdr)); + } else { + err = udp_gro_complete_segment(skb); } rcu_read_unlock(); @@ -544,6 +585,23 @@ INDIRECT_CALLABLE_SCOPE int udp4_gro_complete(struct sk_buff *skb, int nhoff) const struct iphdr *iph = ip_hdr(skb); struct udphdr *uh = (struct udphdr *)(skb->data + nhoff); + if (NAPI_GRO_CB(skb)->is_flist) { + uh->len = htons(skb->len - nhoff); + + skb_shinfo(skb)->gso_type |= (SKB_GSO_FRAGLIST|SKB_GSO_UDP_L4); + skb_shinfo(skb)->gso_segs = NAPI_GRO_CB(skb)->count; + + if (skb->ip_summed == CHECKSUM_UNNECESSARY) { + if (skb->csum_level < SKB_MAX_CSUM_LEVEL) + skb->csum_level++; + } else { + skb->ip_summed = CHECKSUM_UNNECESSARY; + skb->csum_level = 0; + } + + return 0; + } + if (uh->check) uh->check = ~udp_v4_check(skb->len - nhoff, iph->saddr, iph->daddr, 0); diff --git a/net/ipv4/xfrm4_protocol.c b/net/ipv4/xfrm4_protocol.c index 8a4285712808..ea595c8549c7 100644 --- a/net/ipv4/xfrm4_protocol.c +++ b/net/ipv4/xfrm4_protocol.c @@ -72,6 +72,14 @@ int xfrm4_rcv_encap(struct sk_buff *skb, int nexthdr, __be32 spi, if (!head) goto out; + if (!skb_dst(skb)) { + const struct iphdr *iph = ip_hdr(skb); + + if (ip_route_input_noref(skb, iph->daddr, iph->saddr, + iph->tos, skb->dev)) + goto drop; + } + for_each_protocol_rcu(*head, handler) if ((ret = handler->input_handler(skb, nexthdr, spi, encap_type)) != -EINVAL) return ret; @@ -79,6 +87,7 @@ int xfrm4_rcv_encap(struct sk_buff *skb, int nexthdr, __be32 spi, out: icmp_send(skb, ICMP_DEST_UNREACH, ICMP_PORT_UNREACH, 0); +drop: kfree_skb(skb); return 0; } diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c index cfae0a1529a1..58fbde244381 100644 --- a/net/ipv6/ip6_fib.c +++ b/net/ipv6/ip6_fib.c @@ -370,6 +370,21 @@ static int call_fib6_entry_notifier(struct notifier_block *nb, return call_fib6_notifier(nb, event_type, &info.info); } +static int call_fib6_multipath_entry_notifier(struct notifier_block *nb, + enum fib_event_type event_type, + struct fib6_info *rt, + unsigned int nsiblings, + struct netlink_ext_ack *extack) +{ + struct fib6_entry_notifier_info info = { + .info.extack = extack, + .rt = rt, + .nsiblings = nsiblings, + }; + + return call_fib6_notifier(nb, event_type, &info.info); +} + int call_fib6_entry_notifiers(struct net *net, enum fib_event_type event_type, struct fib6_info *rt, @@ -400,6 +415,17 @@ int call_fib6_multipath_entry_notifiers(struct net *net, return call_fib6_notifiers(net, event_type, &info.info); } +int call_fib6_entry_notifiers_replace(struct net *net, struct fib6_info *rt) +{ + struct fib6_entry_notifier_info info = { + .rt = rt, + .nsiblings = rt->fib6_nsiblings, + }; + + rt->fib6_table->fib_seq++; + return call_fib6_notifiers(net, FIB_EVENT_ENTRY_REPLACE, &info.info); +} + struct fib6_dump_arg { struct net *net; struct notifier_block *nb; @@ -408,22 +434,29 @@ struct fib6_dump_arg { static int fib6_rt_dump(struct fib6_info *rt, struct fib6_dump_arg *arg) { - if (rt == arg->net->ipv6.fib6_null_entry) + enum fib_event_type fib_event = FIB_EVENT_ENTRY_REPLACE; + int err; + + if (!rt || rt == arg->net->ipv6.fib6_null_entry) return 0; - return call_fib6_entry_notifier(arg->nb, FIB_EVENT_ENTRY_ADD, - rt, arg->extack); + + if (rt->fib6_nsiblings) + err = call_fib6_multipath_entry_notifier(arg->nb, fib_event, + rt, + rt->fib6_nsiblings, + arg->extack); + else + err = call_fib6_entry_notifier(arg->nb, fib_event, rt, + arg->extack); + + return err; } static int fib6_node_dump(struct fib6_walker *w) { - struct fib6_info *rt; - int err = 0; + int err; - for_each_fib6_walker_rt(w) { - err = fib6_rt_dump(rt, w->args); - if (err) - break; - } + err = fib6_rt_dump(w->leaf, w->args); w->leaf = NULL; return err; } @@ -1039,6 +1072,7 @@ static int fib6_add_rt2node(struct fib6_node *fn, struct fib6_info *rt, (info->nlh->nlmsg_flags & NLM_F_CREATE)); int found = 0; bool rt_can_ecmp = rt6_qualify_for_ecmp(rt); + bool notify_sibling_rt = false; u16 nlflags = NLM_F_EXCL; int err; @@ -1130,6 +1164,7 @@ next_iter: /* Find the first route that have the same metric */ sibling = leaf; + notify_sibling_rt = true; while (sibling) { if (sibling->fib6_metric == rt->fib6_metric && rt6_qualify_for_ecmp(sibling)) { @@ -1139,6 +1174,7 @@ next_iter: } sibling = rcu_dereference_protected(sibling->fib6_next, lockdep_is_held(&rt->fib6_table->tb6_lock)); + notify_sibling_rt = false; } /* For each sibling in the list, increment the counter of * siblings. BUG() if counters does not match, list of siblings @@ -1165,10 +1201,21 @@ next_iter: add: nlflags |= NLM_F_CREATE; - if (!info->skip_notify_kernel) { + /* The route should only be notified if it is the first + * route in the node or if it is added as a sibling + * route to the first route in the node. + */ + if (!info->skip_notify_kernel && + (notify_sibling_rt || ins == &fn->leaf)) { + enum fib_event_type fib_event; + + if (notify_sibling_rt) + fib_event = FIB_EVENT_ENTRY_APPEND; + else + fib_event = FIB_EVENT_ENTRY_REPLACE; err = call_fib6_entry_notifiers(info->nl_net, - FIB_EVENT_ENTRY_ADD, - rt, extack); + fib_event, rt, + extack); if (err) { struct fib6_info *sibling, *next_sibling; @@ -1212,7 +1259,7 @@ add: return -ENOENT; } - if (!info->skip_notify_kernel) { + if (!info->skip_notify_kernel && ins == &fn->leaf) { err = call_fib6_entry_notifiers(info->nl_net, FIB_EVENT_ENTRY_REPLACE, rt, extack); @@ -1845,13 +1892,29 @@ static struct fib6_node *fib6_repair_tree(struct net *net, static void fib6_del_route(struct fib6_table *table, struct fib6_node *fn, struct fib6_info __rcu **rtp, struct nl_info *info) { + struct fib6_info *leaf, *replace_rt = NULL; struct fib6_walker *w; struct fib6_info *rt = rcu_dereference_protected(*rtp, lockdep_is_held(&table->tb6_lock)); struct net *net = info->nl_net; + bool notify_del = false; RT6_TRACE("fib6_del_route\n"); + /* If the deleted route is the first in the node and it is not part of + * a multipath route, then we need to replace it with the next route + * in the node, if exists. + */ + leaf = rcu_dereference_protected(fn->leaf, + lockdep_is_held(&table->tb6_lock)); + if (leaf == rt && !rt->fib6_nsiblings) { + if (rcu_access_pointer(rt->fib6_next)) + replace_rt = rcu_dereference_protected(rt->fib6_next, + lockdep_is_held(&table->tb6_lock)); + else + notify_del = true; + } + /* Unlink it */ *rtp = rt->fib6_next; rt->fib6_node = NULL; @@ -1869,6 +1932,14 @@ static void fib6_del_route(struct fib6_table *table, struct fib6_node *fn, if (rt->fib6_nsiblings) { struct fib6_info *sibling, *next_sibling; + /* The route is deleted from a multipath route. If this + * multipath route is the first route in the node, then we need + * to emit a delete notification. Otherwise, we need to skip + * the notification. + */ + if (rt->fib6_metric == leaf->fib6_metric && + rt6_qualify_for_ecmp(leaf)) + notify_del = true; list_for_each_entry_safe(sibling, next_sibling, &rt->fib6_siblings, fib6_siblings) sibling->fib6_nsiblings--; @@ -1904,8 +1975,13 @@ static void fib6_del_route(struct fib6_table *table, struct fib6_node *fn, fib6_purge_rt(rt, fn, net); - if (!info->skip_notify_kernel) - call_fib6_entry_notifiers(net, FIB_EVENT_ENTRY_DEL, rt, NULL); + if (!info->skip_notify_kernel) { + if (notify_del) + call_fib6_entry_notifiers(net, FIB_EVENT_ENTRY_DEL, + rt, NULL); + else if (replace_rt) + call_fib6_entry_notifiers_replace(net, replace_rt); + } if (!info->skip_notify) inet6_rt_notify(RTM_DELROUTE, rt, info, 0); diff --git a/net/ipv6/route.c b/net/ipv6/route.c index affb51c11a25..4fbdc60b4e07 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -3757,6 +3757,7 @@ static int __ip6_del_rt_siblings(struct fib6_info *rt, struct fib6_config *cfg) if (rt->fib6_nsiblings && cfg->fc_delete_all_nh) { struct fib6_info *sibling, *next_sibling; + struct fib6_node *fn; /* prefer to send a single notification with all hops */ skb = nlmsg_new(rt6_nlmsg_size(rt), gfp_any()); @@ -3772,12 +3773,32 @@ static int __ip6_del_rt_siblings(struct fib6_info *rt, struct fib6_config *cfg) info->skip_notify = 1; } + /* 'rt' points to the first sibling route. If it is not the + * leaf, then we do not need to send a notification. Otherwise, + * we need to check if the last sibling has a next route or not + * and emit a replace or delete notification, respectively. + */ info->skip_notify_kernel = 1; - call_fib6_multipath_entry_notifiers(net, - FIB_EVENT_ENTRY_DEL, - rt, - rt->fib6_nsiblings, - NULL); + fn = rcu_dereference_protected(rt->fib6_node, + lockdep_is_held(&table->tb6_lock)); + if (rcu_access_pointer(fn->leaf) == rt) { + struct fib6_info *last_sibling, *replace_rt; + + last_sibling = list_last_entry(&rt->fib6_siblings, + struct fib6_info, + fib6_siblings); + replace_rt = rcu_dereference_protected( + last_sibling->fib6_next, + lockdep_is_held(&table->tb6_lock)); + if (replace_rt) + call_fib6_entry_notifiers_replace(net, + replace_rt); + else + call_fib6_multipath_entry_notifiers(net, + FIB_EVENT_ENTRY_DEL, + rt, rt->fib6_nsiblings, + NULL); + } list_for_each_entry_safe(sibling, next_sibling, &rt->fib6_siblings, fib6_siblings) { @@ -5025,12 +5046,37 @@ static void ip6_route_mpath_notify(struct fib6_info *rt, inet6_rt_notify(RTM_NEWROUTE, rt, info, nlflags); } +static bool ip6_route_mpath_should_notify(const struct fib6_info *rt) +{ + bool rt_can_ecmp = rt6_qualify_for_ecmp(rt); + bool should_notify = false; + struct fib6_info *leaf; + struct fib6_node *fn; + + rcu_read_lock(); + fn = rcu_dereference(rt->fib6_node); + if (!fn) + goto out; + + leaf = rcu_dereference(fn->leaf); + if (!leaf) + goto out; + + if (rt == leaf || + (rt_can_ecmp && rt->fib6_metric == leaf->fib6_metric && + rt6_qualify_for_ecmp(leaf))) + should_notify = true; +out: + rcu_read_unlock(); + + return should_notify; +} + static int ip6_route_multipath_add(struct fib6_config *cfg, struct netlink_ext_ack *extack) { struct fib6_info *rt_notif = NULL, *rt_last = NULL; struct nl_info *info = &cfg->fc_nlinfo; - enum fib_event_type event_type; struct fib6_config r_cfg; struct rtnexthop *rtnh; struct fib6_info *rt; @@ -5155,13 +5201,27 @@ static int ip6_route_multipath_add(struct fib6_config *cfg, nhn++; } - event_type = replace ? FIB_EVENT_ENTRY_REPLACE : FIB_EVENT_ENTRY_ADD; - err = call_fib6_multipath_entry_notifiers(info->nl_net, event_type, - rt_notif, nhn - 1, extack); - if (err) { - /* Delete all the siblings that were just added */ - err_nh = NULL; - goto add_errout; + /* An in-kernel notification should only be sent in case the new + * multipath route is added as the first route in the node, or if + * it was appended to it. We pass 'rt_notif' since it is the first + * sibling and might allow us to skip some checks in the replace case. + */ + if (ip6_route_mpath_should_notify(rt_notif)) { + enum fib_event_type fib_event; + + if (rt_notif->fib6_nsiblings != nhn - 1) + fib_event = FIB_EVENT_ENTRY_APPEND; + else + fib_event = FIB_EVENT_ENTRY_REPLACE; + + err = call_fib6_multipath_entry_notifiers(info->nl_net, + fib_event, rt_notif, + nhn - 1, extack); + if (err) { + /* Delete all the siblings that were just added */ + err_nh = NULL; + goto add_errout; + } } /* success ... tell user about new route */ @@ -5516,6 +5576,13 @@ static int rt6_fill_node(struct net *net, struct sk_buff *skb, expires -= jiffies; } + if (!dst) { + if (rt->offload) + rtm->rtm_flags |= RTM_F_OFFLOAD; + if (rt->trap) + rtm->rtm_flags |= RTM_F_TRAP; + } + if (rtnl_put_cacheinfo(skb, dst, 0, expires, dst ? dst->error : 0) < 0) goto nla_put_failure; diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index df5fd9109696..33a578a3eb3a 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -75,13 +75,14 @@ static void tcp_v6_reqsk_send_ack(const struct sock *sk, struct sk_buff *skb, static int tcp_v6_do_rcv(struct sock *sk, struct sk_buff *skb); static const struct inet_connection_sock_af_ops ipv6_mapped; -static const struct inet_connection_sock_af_ops ipv6_specific; +const struct inet_connection_sock_af_ops ipv6_specific; #ifdef CONFIG_TCP_MD5SIG static const struct tcp_sock_af_ops tcp_sock_ipv6_specific; static const struct tcp_sock_af_ops tcp_sock_ipv6_mapped_specific; #else static struct tcp_md5sig_key *tcp_v6_md5_do_lookup(const struct sock *sk, - const struct in6_addr *addr) + const struct in6_addr *addr, + int l3index) { return NULL; } @@ -237,6 +238,8 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr, sin.sin_addr.s_addr = usin->sin6_addr.s6_addr32[3]; icsk->icsk_af_ops = &ipv6_mapped; + if (sk_is_mptcp(sk)) + mptcp_handle_ipv6_mapped(sk, true); sk->sk_backlog_rcv = tcp_v4_do_rcv; #ifdef CONFIG_TCP_MD5SIG tp->af_specific = &tcp_sock_ipv6_mapped_specific; @@ -247,6 +250,8 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr, if (err) { icsk->icsk_ext_hdr_len = exthdrlen; icsk->icsk_af_ops = &ipv6_specific; + if (sk_is_mptcp(sk)) + mptcp_handle_ipv6_mapped(sk, false); sk->sk_backlog_rcv = tcp_v6_do_rcv; #ifdef CONFIG_TCP_MD5SIG tp->af_specific = &tcp_sock_ipv6_specific; @@ -532,15 +537,22 @@ static void tcp_v6_reqsk_destructor(struct request_sock *req) #ifdef CONFIG_TCP_MD5SIG static struct tcp_md5sig_key *tcp_v6_md5_do_lookup(const struct sock *sk, - const struct in6_addr *addr) + const struct in6_addr *addr, + int l3index) { - return tcp_md5_do_lookup(sk, (union tcp_md5_addr *)addr, AF_INET6); + return tcp_md5_do_lookup(sk, l3index, + (union tcp_md5_addr *)addr, AF_INET6); } static struct tcp_md5sig_key *tcp_v6_md5_lookup(const struct sock *sk, const struct sock *addr_sk) { - return tcp_v6_md5_do_lookup(sk, &addr_sk->sk_v6_daddr); + int l3index; + + l3index = l3mdev_master_ifindex_by_index(sock_net(sk), + addr_sk->sk_bound_dev_if); + return tcp_v6_md5_do_lookup(sk, &addr_sk->sk_v6_daddr, + l3index); } static int tcp_v6_parse_md5_keys(struct sock *sk, int optname, @@ -548,6 +560,7 @@ static int tcp_v6_parse_md5_keys(struct sock *sk, int optname, { struct tcp_md5sig cmd; struct sockaddr_in6 *sin6 = (struct sockaddr_in6 *)&cmd.tcpm_addr; + int l3index = 0; u8 prefixlen; if (optlen < sizeof(cmd)) @@ -569,12 +582,30 @@ static int tcp_v6_parse_md5_keys(struct sock *sk, int optname, prefixlen = ipv6_addr_v4mapped(&sin6->sin6_addr) ? 32 : 128; } + if (optname == TCP_MD5SIG_EXT && + cmd.tcpm_flags & TCP_MD5SIG_FLAG_IFINDEX) { + struct net_device *dev; + + rcu_read_lock(); + dev = dev_get_by_index_rcu(sock_net(sk), cmd.tcpm_ifindex); + if (dev && netif_is_l3_master(dev)) + l3index = dev->ifindex; + rcu_read_unlock(); + + /* ok to reference set/not set outside of rcu; + * right now device MUST be an L3 master + */ + if (!dev || !l3index) + return -EINVAL; + } + if (!cmd.tcpm_keylen) { if (ipv6_addr_v4mapped(&sin6->sin6_addr)) return tcp_md5_do_del(sk, (union tcp_md5_addr *)&sin6->sin6_addr.s6_addr32[3], - AF_INET, prefixlen); + AF_INET, prefixlen, + l3index); return tcp_md5_do_del(sk, (union tcp_md5_addr *)&sin6->sin6_addr, - AF_INET6, prefixlen); + AF_INET6, prefixlen, l3index); } if (cmd.tcpm_keylen > TCP_MD5SIG_MAXKEYLEN) @@ -582,12 +613,13 @@ static int tcp_v6_parse_md5_keys(struct sock *sk, int optname, if (ipv6_addr_v4mapped(&sin6->sin6_addr)) return tcp_md5_do_add(sk, (union tcp_md5_addr *)&sin6->sin6_addr.s6_addr32[3], - AF_INET, prefixlen, cmd.tcpm_key, - cmd.tcpm_keylen, GFP_KERNEL); + AF_INET, prefixlen, l3index, + cmd.tcpm_key, cmd.tcpm_keylen, + GFP_KERNEL); return tcp_md5_do_add(sk, (union tcp_md5_addr *)&sin6->sin6_addr, - AF_INET6, prefixlen, cmd.tcpm_key, - cmd.tcpm_keylen, GFP_KERNEL); + AF_INET6, prefixlen, l3index, + cmd.tcpm_key, cmd.tcpm_keylen, GFP_KERNEL); } static int tcp_v6_md5_hash_headers(struct tcp_md5sig_pool *hp, @@ -698,17 +730,23 @@ clear_hash_noput: #endif static bool tcp_v6_inbound_md5_hash(const struct sock *sk, - const struct sk_buff *skb) + const struct sk_buff *skb, + int dif, int sdif) { #ifdef CONFIG_TCP_MD5SIG const __u8 *hash_location = NULL; struct tcp_md5sig_key *hash_expected; const struct ipv6hdr *ip6h = ipv6_hdr(skb); const struct tcphdr *th = tcp_hdr(skb); - int genhash; + int genhash, l3index; u8 newhash[16]; - hash_expected = tcp_v6_md5_do_lookup(sk, &ip6h->saddr); + /* sdif set, means packet ingressed via a device + * in an L3 domain and dif is set to the l3mdev + */ + l3index = sdif ? dif : 0; + + hash_expected = tcp_v6_md5_do_lookup(sk, &ip6h->saddr, l3index); hash_location = tcp_parse_md5sig_option(th); /* We've parsed the options - do we have a hash? */ @@ -732,10 +770,10 @@ static bool tcp_v6_inbound_md5_hash(const struct sock *sk, if (genhash || memcmp(hash_location, newhash, 16) != 0) { NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPMD5FAILURE); - net_info_ratelimited("MD5 Hash %s for [%pI6c]:%u->[%pI6c]:%u\n", + net_info_ratelimited("MD5 Hash %s for [%pI6c]:%u->[%pI6c]:%u L3 index %d\n", genhash ? "failed" : "mismatch", &ip6h->saddr, ntohs(th->source), - &ip6h->daddr, ntohs(th->dest)); + &ip6h->daddr, ntohs(th->dest), l3index); return true; } #endif @@ -785,7 +823,7 @@ struct request_sock_ops tcp6_request_sock_ops __read_mostly = { .syn_ack_timeout = tcp_syn_ack_timeout, }; -static const struct tcp_request_sock_ops tcp_request_sock_ipv6_ops = { +const struct tcp_request_sock_ops tcp_request_sock_ipv6_ops = { .mss_clamp = IPV6_MIN_MTU - sizeof(struct tcphdr) - sizeof(struct ipv6hdr), #ifdef CONFIG_TCP_MD5SIG @@ -951,8 +989,18 @@ static void tcp_v6_send_reset(const struct sock *sk, struct sk_buff *skb) rcu_read_lock(); hash_location = tcp_parse_md5sig_option(th); if (sk && sk_fullsock(sk)) { - key = tcp_v6_md5_do_lookup(sk, &ipv6h->saddr); + int l3index; + + /* sdif set, means packet ingressed via a device + * in an L3 domain and inet_iif is set to it. + */ + l3index = tcp_v6_sdif(skb) ? tcp_v6_iif_l3_slave(skb) : 0; + key = tcp_v6_md5_do_lookup(sk, &ipv6h->saddr, l3index); } else if (hash_location) { + int dif = tcp_v6_iif_l3_slave(skb); + int sdif = tcp_v6_sdif(skb); + int l3index; + /* * active side is lost. Try to find listening socket through * source port, and then find md5 key through listening socket. @@ -964,13 +1012,16 @@ static void tcp_v6_send_reset(const struct sock *sk, struct sk_buff *skb) &tcp_hashinfo, NULL, 0, &ipv6h->saddr, th->source, &ipv6h->daddr, - ntohs(th->source), - tcp_v6_iif_l3_slave(skb), - tcp_v6_sdif(skb)); + ntohs(th->source), dif, sdif); if (!sk1) goto out; - key = tcp_v6_md5_do_lookup(sk1, &ipv6h->saddr); + /* sdif set, means packet ingressed via a device + * in an L3 domain and dif is set to it. + */ + l3index = tcp_v6_sdif(skb) ? dif : 0; + + key = tcp_v6_md5_do_lookup(sk1, &ipv6h->saddr, l3index); if (!key) goto out; @@ -1040,6 +1091,10 @@ static void tcp_v6_timewait_ack(struct sock *sk, struct sk_buff *skb) static void tcp_v6_reqsk_send_ack(const struct sock *sk, struct sk_buff *skb, struct request_sock *req) { + int l3index; + + l3index = tcp_v6_sdif(skb) ? tcp_v6_iif_l3_slave(skb) : 0; + /* sk->sk_state == TCP_LISTEN -> for regular TCP_SYN_RECV * sk->sk_state == TCP_SYN_RECV -> for Fast Open. */ @@ -1054,7 +1109,7 @@ static void tcp_v6_reqsk_send_ack(const struct sock *sk, struct sk_buff *skb, req->rsk_rcv_wnd >> inet_rsk(req)->rcv_wscale, tcp_time_stamp_raw() + tcp_rsk(req)->ts_off, req->ts_recent, sk->sk_bound_dev_if, - tcp_v6_md5_do_lookup(sk, &ipv6_hdr(skb)->saddr), + tcp_v6_md5_do_lookup(sk, &ipv6_hdr(skb)->saddr, l3index), 0, 0, sk->sk_priority); } @@ -1126,6 +1181,7 @@ static struct sock *tcp_v6_syn_recv_sock(const struct sock *sk, struct sk_buff * struct sock *newsk; #ifdef CONFIG_TCP_MD5SIG struct tcp_md5sig_key *key; + int l3index; #endif struct flowi6 fl6; @@ -1151,6 +1207,8 @@ static struct sock *tcp_v6_syn_recv_sock(const struct sock *sk, struct sk_buff * newnp->saddr = newsk->sk_v6_rcv_saddr; inet_csk(newsk)->icsk_af_ops = &ipv6_mapped; + if (sk_is_mptcp(newsk)) + mptcp_handle_ipv6_mapped(newsk, true); newsk->sk_backlog_rcv = tcp_v4_do_rcv; #ifdef CONFIG_TCP_MD5SIG newtp->af_specific = &tcp_sock_ipv6_mapped_specific; @@ -1269,8 +1327,10 @@ static struct sock *tcp_v6_syn_recv_sock(const struct sock *sk, struct sk_buff * newinet->inet_rcv_saddr = LOOPBACK4_IPV6; #ifdef CONFIG_TCP_MD5SIG + l3index = l3mdev_master_ifindex_by_index(sock_net(sk), ireq->ir_iif); + /* Copy over the MD5 key from the original socket */ - key = tcp_v6_md5_do_lookup(sk, &newsk->sk_v6_daddr); + key = tcp_v6_md5_do_lookup(sk, &newsk->sk_v6_daddr, l3index); if (key) { /* We're using one, so create a matching key * on the newsk structure. If we fail to get @@ -1278,7 +1338,7 @@ static struct sock *tcp_v6_syn_recv_sock(const struct sock *sk, struct sk_buff * * across. Shucks. */ tcp_md5_do_add(newsk, (union tcp_md5_addr *)&newsk->sk_v6_daddr, - AF_INET6, 128, key->key, key->keylen, + AF_INET6, 128, l3index, key->key, key->keylen, sk_gfp_mask(sk, GFP_ATOMIC)); } #endif @@ -1480,6 +1540,7 @@ INDIRECT_CALLABLE_SCOPE int tcp_v6_rcv(struct sk_buff *skb) { struct sk_buff *skb_to_free; int sdif = inet6_sdif(skb); + int dif = inet6_iif(skb); const struct tcphdr *th; const struct ipv6hdr *hdr; bool refcounted; @@ -1528,7 +1589,7 @@ process: struct sock *nsk; sk = req->rsk_listener; - if (tcp_v6_inbound_md5_hash(sk, skb)) { + if (tcp_v6_inbound_md5_hash(sk, skb, dif, sdif)) { sk_drops_add(sk, skb); reqsk_put(req); goto discard_it; @@ -1583,7 +1644,7 @@ process: if (!xfrm6_policy_check(sk, XFRM_POLICY_IN, skb)) goto discard_and_relse; - if (tcp_v6_inbound_md5_hash(sk, skb)) + if (tcp_v6_inbound_md5_hash(sk, skb, dif, sdif)) goto discard_and_relse; if (tcp_filter(sk, skb)) @@ -1739,7 +1800,7 @@ static struct timewait_sock_ops tcp6_timewait_sock_ops = { .twsk_destructor = tcp_twsk_destructor, }; -static const struct inet_connection_sock_af_ops ipv6_specific = { +const struct inet_connection_sock_af_ops ipv6_specific = { .queue_xmit = inet6_csk_xmit, .send_check = tcp_v6_send_check, .rebuild_header = inet6_sk_rebuild_header, @@ -2108,9 +2169,16 @@ int __init tcpv6_init(void) ret = register_pernet_subsys(&tcpv6_net_ops); if (ret) goto out_tcpv6_protosw; + + ret = mptcpv6_init(); + if (ret) + goto out_tcpv6_pernet_subsys; + out: return ret; +out_tcpv6_pernet_subsys: + unregister_pernet_subsys(&tcpv6_net_ops); out_tcpv6_protosw: inet6_unregister_protosw(&tcpv6_protosw); out_tcpv6_protocol: diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 9fec580c968e..5dc439a391fe 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -690,8 +690,7 @@ static int udpv6_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) __skb_push(skb, -skb_mac_offset(skb)); segs = udp_rcv_segment(sk, skb, false); - for (skb = segs; skb; skb = next) { - next = skb->next; + skb_list_walk_safe(segs, skb, next) { __skb_pull(skb, skb_transport_offset(skb)); ret = udpv6_queue_rcv_one_skb(sk, skb); diff --git a/net/ipv6/udp_offload.c b/net/ipv6/udp_offload.c index 64b8f05d6735..584157a07759 100644 --- a/net/ipv6/udp_offload.c +++ b/net/ipv6/udp_offload.c @@ -115,8 +115,10 @@ INDIRECT_CALLABLE_SCOPE struct sk_buff *udp6_gro_receive(struct list_head *head, struct sk_buff *skb) { struct udphdr *uh = udp_gro_udphdr(skb); + struct sk_buff *pp; + struct sock *sk; - if (unlikely(!uh) || !static_branch_unlikely(&udpv6_encap_needed_key)) + if (unlikely(!uh)) goto flush; /* Don't bother verifying checksum if we're going to flush anyway. */ @@ -127,12 +129,16 @@ struct sk_buff *udp6_gro_receive(struct list_head *head, struct sk_buff *skb) ip6_gro_compute_pseudo)) goto flush; else if (uh->check) - skb_gro_checksum_try_convert(skb, IPPROTO_UDP, uh->check, + skb_gro_checksum_try_convert(skb, IPPROTO_UDP, ip6_gro_compute_pseudo); skip: NAPI_GRO_CB(skb)->is_ipv6 = 1; - return udp_gro_receive(head, skb, uh, udp6_lib_lookup_skb); + rcu_read_lock(); + sk = static_branch_unlikely(&udpv6_encap_needed_key) ? udp6_lib_lookup_skb(skb, uh->source, uh->dest) : NULL; + pp = udp_gro_receive(head, skb, uh, sk); + rcu_read_unlock(); + return pp; flush: NAPI_GRO_CB(skb)->flush = 1; @@ -144,6 +150,23 @@ INDIRECT_CALLABLE_SCOPE int udp6_gro_complete(struct sk_buff *skb, int nhoff) const struct ipv6hdr *ipv6h = ipv6_hdr(skb); struct udphdr *uh = (struct udphdr *)(skb->data + nhoff); + if (NAPI_GRO_CB(skb)->is_flist) { + uh->len = htons(skb->len - nhoff); + + skb_shinfo(skb)->gso_type |= (SKB_GSO_FRAGLIST|SKB_GSO_UDP_L4); + skb_shinfo(skb)->gso_segs = NAPI_GRO_CB(skb)->count; + + if (skb->ip_summed == CHECKSUM_UNNECESSARY) { + if (skb->csum_level < SKB_MAX_CSUM_LEVEL) + skb->csum_level++; + } else { + skb->ip_summed = CHECKSUM_UNNECESSARY; + skb->csum_level = 0; + } + + return 0; + } + if (uh->check) uh->check = ~udp_v6_check(skb->len - nhoff, &ipv6h->saddr, &ipv6h->daddr, 0); diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c index f82ea12bac37..c99223cb3338 100644 --- a/net/l2tp/l2tp_core.c +++ b/net/l2tp/l2tp_core.c @@ -122,8 +122,6 @@ static inline struct l2tp_tunnel *l2tp_tunnel(struct sock *sk) static inline struct l2tp_net *l2tp_pernet(const struct net *net) { - BUG_ON(!net); - return net_generic(net, l2tp_net_id); } diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c index a8a7306a1f56..4bd1faf4f779 100644 --- a/net/mac80211/tx.c +++ b/net/mac80211/tx.c @@ -3949,18 +3949,15 @@ void __ieee80211_subif_start_xmit(struct sk_buff *skb, } } - next = skb; - while (next) { - skb = next; - next = skb->next; - - skb->prev = NULL; - skb->next = NULL; + skb_list_walk_safe(skb, skb, next) { + skb_mark_not_on_list(skb); skb = ieee80211_build_hdr(sdata, skb, info_flags, sta, ctrl_flags); - if (IS_ERR(skb)) + if (IS_ERR(skb)) { + kfree_skb_list(next); goto out; + } ieee80211_tx_stats(dev, skb->len); diff --git a/net/mptcp/Kconfig b/net/mptcp/Kconfig new file mode 100644 index 000000000000..5db56d2218c5 --- /dev/null +++ b/net/mptcp/Kconfig @@ -0,0 +1,26 @@ + +config MPTCP + bool "MPTCP: Multipath TCP" + depends on INET + select SKB_EXTENSIONS + select CRYPTO_LIB_SHA256 + help + Multipath TCP (MPTCP) connections send and receive data over multiple + subflows in order to utilize multiple network paths. Each subflow + uses the TCP protocol, and TCP options carry header information for + MPTCP. + +config MPTCP_IPV6 + bool "MPTCP: IPv6 support for Multipath TCP" + depends on MPTCP + select IPV6 + default y + +config MPTCP_HMAC_TEST + bool "Tests for MPTCP HMAC implementation" + default n + help + This option enable boot time self-test for the HMAC implementation + used by the MPTCP code + + Say N if you are unsure. diff --git a/net/mptcp/Makefile b/net/mptcp/Makefile new file mode 100644 index 000000000000..4e98d9edfd0a --- /dev/null +++ b/net/mptcp/Makefile @@ -0,0 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0 +obj-$(CONFIG_MPTCP) += mptcp.o + +mptcp-y := protocol.o subflow.o options.o token.o crypto.o ctrl.o diff --git a/net/mptcp/crypto.c b/net/mptcp/crypto.c new file mode 100644 index 000000000000..40d1bb18fd60 --- /dev/null +++ b/net/mptcp/crypto.c @@ -0,0 +1,152 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Multipath TCP cryptographic functions + * Copyright (c) 2017 - 2019, Intel Corporation. + * + * Note: This code is based on mptcp_ctrl.c, mptcp_ipv4.c, and + * mptcp_ipv6 from multipath-tcp.org, authored by: + * + * Sébastien Barré <sebastien.barre@uclouvain.be> + * Christoph Paasch <christoph.paasch@uclouvain.be> + * Jaakko Korkeaniemi <jaakko.korkeaniemi@aalto.fi> + * Gregory Detal <gregory.detal@uclouvain.be> + * Fabien Duchêne <fabien.duchene@uclouvain.be> + * Andreas Seelinger <Andreas.Seelinger@rwth-aachen.de> + * Lavkesh Lahngir <lavkesh51@gmail.com> + * Andreas Ripke <ripke@neclab.eu> + * Vlad Dogaru <vlad.dogaru@intel.com> + * Octavian Purdila <octavian.purdila@intel.com> + * John Ronan <jronan@tssg.org> + * Catalin Nicutar <catalin.nicutar@gmail.com> + * Brandon Heller <brandonh@stanford.edu> + */ + +#include <linux/kernel.h> +#include <crypto/sha.h> +#include <asm/unaligned.h> + +#include "protocol.h" + +#define SHA256_DIGEST_WORDS (SHA256_DIGEST_SIZE / 4) + +void mptcp_crypto_key_sha(u64 key, u32 *token, u64 *idsn) +{ + __be32 mptcp_hashed_key[SHA256_DIGEST_WORDS]; + __be64 input = cpu_to_be64(key); + struct sha256_state state; + + sha256_init(&state); + sha256_update(&state, (__force u8 *)&input, sizeof(input)); + sha256_final(&state, (u8 *)mptcp_hashed_key); + + if (token) + *token = be32_to_cpu(mptcp_hashed_key[0]); + if (idsn) + *idsn = be64_to_cpu(*((__be64 *)&mptcp_hashed_key[6])); +} + +void mptcp_crypto_hmac_sha(u64 key1, u64 key2, u32 nonce1, u32 nonce2, + void *hmac) +{ + u8 input[SHA256_BLOCK_SIZE + SHA256_DIGEST_SIZE]; + __be32 mptcp_hashed_key[SHA256_DIGEST_WORDS]; + __be32 *hash_out = (__force __be32 *)hmac; + struct sha256_state state; + u8 key1be[8]; + u8 key2be[8]; + int i; + + put_unaligned_be64(key1, key1be); + put_unaligned_be64(key2, key2be); + + /* Generate key xored with ipad */ + memset(input, 0x36, SHA_MESSAGE_BYTES); + for (i = 0; i < 8; i++) + input[i] ^= key1be[i]; + for (i = 0; i < 8; i++) + input[i + 8] ^= key2be[i]; + + put_unaligned_be32(nonce1, &input[SHA256_BLOCK_SIZE]); + put_unaligned_be32(nonce2, &input[SHA256_BLOCK_SIZE + 4]); + + sha256_init(&state); + sha256_update(&state, input, SHA256_BLOCK_SIZE + 8); + + /* emit sha256(K1 || msg) on the second input block, so we can + * reuse 'input' for the last hashing + */ + sha256_final(&state, &input[SHA256_BLOCK_SIZE]); + + /* Prepare second part of hmac */ + memset(input, 0x5C, SHA_MESSAGE_BYTES); + for (i = 0; i < 8; i++) + input[i] ^= key1be[i]; + for (i = 0; i < 8; i++) + input[i + 8] ^= key2be[i]; + + sha256_init(&state); + sha256_update(&state, input, SHA256_BLOCK_SIZE + SHA256_DIGEST_SIZE); + sha256_final(&state, (u8 *)mptcp_hashed_key); + + /* takes only first 160 bits */ + for (i = 0; i < 5; i++) + hash_out[i] = mptcp_hashed_key[i]; +} + +#ifdef CONFIG_MPTCP_HMAC_TEST +struct test_cast { + char *key; + char *msg; + char *result; +}; + +/* we can't reuse RFC 4231 test vectors, as we have constraint on the + * input and key size, and we truncate the output. + */ +static struct test_cast tests[] = { + { + .key = "0b0b0b0b0b0b0b0b", + .msg = "48692054", + .result = "8385e24fb4235ac37556b6b886db106284a1da67", + }, + { + .key = "aaaaaaaaaaaaaaaa", + .msg = "dddddddd", + .result = "2c5e219164ff1dca1c4a92318d847bb6b9d44492", + }, + { + .key = "0102030405060708", + .msg = "cdcdcdcd", + .result = "e73b9ba9969969cefb04aa0d6df18ec2fcc075b6", + }, +}; + +static int __init test_mptcp_crypto(void) +{ + char hmac[20], hmac_hex[41]; + u32 nonce1, nonce2; + u64 key1, key2; + int i, j; + + for (i = 0; i < ARRAY_SIZE(tests); ++i) { + /* mptcp hmap will convert to be before computing the hmac */ + key1 = be64_to_cpu(*((__be64 *)&tests[i].key[0])); + key2 = be64_to_cpu(*((__be64 *)&tests[i].key[8])); + nonce1 = be32_to_cpu(*((__be32 *)&tests[i].msg[0])); + nonce2 = be32_to_cpu(*((__be32 *)&tests[i].msg[4])); + + mptcp_crypto_hmac_sha(key1, key2, nonce1, nonce2, hmac); + for (j = 0; j < 20; ++j) + sprintf(&hmac_hex[j << 1], "%02x", hmac[j] & 0xff); + hmac_hex[40] = 0; + + if (memcmp(hmac_hex, tests[i].result, 40)) + pr_err("test %d failed, got %s expected %s", i, + hmac_hex, tests[i].result); + else + pr_info("test %d [ ok ]", i); + } + return 0; +} + +late_initcall(test_mptcp_crypto); +#endif diff --git a/net/mptcp/ctrl.c b/net/mptcp/ctrl.c new file mode 100644 index 000000000000..8e39585d37f3 --- /dev/null +++ b/net/mptcp/ctrl.c @@ -0,0 +1,130 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Multipath TCP + * + * Copyright (c) 2019, Tessares SA. + */ + +#include <linux/sysctl.h> + +#include <net/net_namespace.h> +#include <net/netns/generic.h> + +#include "protocol.h" + +#define MPTCP_SYSCTL_PATH "net/mptcp" + +static int mptcp_pernet_id; +struct mptcp_pernet { + struct ctl_table_header *ctl_table_hdr; + + int mptcp_enabled; +}; + +static struct mptcp_pernet *mptcp_get_pernet(struct net *net) +{ + return net_generic(net, mptcp_pernet_id); +} + +int mptcp_is_enabled(struct net *net) +{ + return mptcp_get_pernet(net)->mptcp_enabled; +} + +static struct ctl_table mptcp_sysctl_table[] = { + { + .procname = "enabled", + .maxlen = sizeof(int), + .mode = 0644, + /* users with CAP_NET_ADMIN or root (not and) can change this + * value, same as other sysctl or the 'net' tree. + */ + .proc_handler = proc_dointvec, + }, + {} +}; + +static void mptcp_pernet_set_defaults(struct mptcp_pernet *pernet) +{ + pernet->mptcp_enabled = 1; +} + +static int mptcp_pernet_new_table(struct net *net, struct mptcp_pernet *pernet) +{ + struct ctl_table_header *hdr; + struct ctl_table *table; + + table = mptcp_sysctl_table; + if (!net_eq(net, &init_net)) { + table = kmemdup(table, sizeof(mptcp_sysctl_table), GFP_KERNEL); + if (!table) + goto err_alloc; + } + + table[0].data = &pernet->mptcp_enabled; + + hdr = register_net_sysctl(net, MPTCP_SYSCTL_PATH, table); + if (!hdr) + goto err_reg; + + pernet->ctl_table_hdr = hdr; + + return 0; + +err_reg: + if (!net_eq(net, &init_net)) + kfree(table); +err_alloc: + return -ENOMEM; +} + +static void mptcp_pernet_del_table(struct mptcp_pernet *pernet) +{ + struct ctl_table *table = pernet->ctl_table_hdr->ctl_table_arg; + + unregister_net_sysctl_table(pernet->ctl_table_hdr); + + kfree(table); +} + +static int __net_init mptcp_net_init(struct net *net) +{ + struct mptcp_pernet *pernet = mptcp_get_pernet(net); + + mptcp_pernet_set_defaults(pernet); + + return mptcp_pernet_new_table(net, pernet); +} + +/* Note: the callback will only be called per extra netns */ +static void __net_exit mptcp_net_exit(struct net *net) +{ + struct mptcp_pernet *pernet = mptcp_get_pernet(net); + + mptcp_pernet_del_table(pernet); +} + +static struct pernet_operations mptcp_pernet_ops = { + .init = mptcp_net_init, + .exit = mptcp_net_exit, + .id = &mptcp_pernet_id, + .size = sizeof(struct mptcp_pernet), +}; + +void __init mptcp_init(void) +{ + mptcp_proto_init(); + + if (register_pernet_subsys(&mptcp_pernet_ops) < 0) + panic("Failed to register MPTCP pernet subsystem.\n"); +} + +#if IS_ENABLED(CONFIG_MPTCP_IPV6) +int __init mptcpv6_init(void) +{ + int err; + + err = mptcp_proto_v6_init(); + + return err; +} +#endif diff --git a/net/mptcp/options.c b/net/mptcp/options.c new file mode 100644 index 000000000000..45acd877bef3 --- /dev/null +++ b/net/mptcp/options.c @@ -0,0 +1,586 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Multipath TCP + * + * Copyright (c) 2017 - 2019, Intel Corporation. + */ + +#include <linux/kernel.h> +#include <net/tcp.h> +#include <net/mptcp.h> +#include "protocol.h" + +static bool mptcp_cap_flag_sha256(u8 flags) +{ + return (flags & MPTCP_CAP_FLAG_MASK) == MPTCP_CAP_HMAC_SHA256; +} + +void mptcp_parse_option(const struct sk_buff *skb, const unsigned char *ptr, + int opsize, struct tcp_options_received *opt_rx) +{ + struct mptcp_options_received *mp_opt = &opt_rx->mptcp; + u8 subtype = *ptr >> 4; + int expected_opsize; + u8 version; + u8 flags; + + switch (subtype) { + case MPTCPOPT_MP_CAPABLE: + /* strict size checking */ + if (!(TCP_SKB_CB(skb)->tcp_flags & TCPHDR_SYN)) { + if (skb->len > tcp_hdr(skb)->doff << 2) + expected_opsize = TCPOLEN_MPTCP_MPC_ACK_DATA; + else + expected_opsize = TCPOLEN_MPTCP_MPC_ACK; + } else { + if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_ACK) + expected_opsize = TCPOLEN_MPTCP_MPC_SYNACK; + else + expected_opsize = TCPOLEN_MPTCP_MPC_SYN; + } + if (opsize != expected_opsize) + break; + + /* try to be gentle vs future versions on the initial syn */ + version = *ptr++ & MPTCP_VERSION_MASK; + if (opsize != TCPOLEN_MPTCP_MPC_SYN) { + if (version != MPTCP_SUPPORTED_VERSION) + break; + } else if (version < MPTCP_SUPPORTED_VERSION) { + break; + } + + flags = *ptr++; + if (!mptcp_cap_flag_sha256(flags) || + (flags & MPTCP_CAP_EXTENSIBILITY)) + break; + + /* RFC 6824, Section 3.1: + * "For the Checksum Required bit (labeled "A"), if either + * host requires the use of checksums, checksums MUST be used. + * In other words, the only way for checksums not to be used + * is if both hosts in their SYNs set A=0." + * + * Section 3.3.0: + * "If a checksum is not present when its use has been + * negotiated, the receiver MUST close the subflow with a RST as + * it is considered broken." + * + * We don't implement DSS checksum - fall back to TCP. + */ + if (flags & MPTCP_CAP_CHECKSUM_REQD) + break; + + mp_opt->mp_capable = 1; + if (opsize >= TCPOLEN_MPTCP_MPC_SYNACK) { + mp_opt->sndr_key = get_unaligned_be64(ptr); + ptr += 8; + } + if (opsize >= TCPOLEN_MPTCP_MPC_ACK) { + mp_opt->rcvr_key = get_unaligned_be64(ptr); + ptr += 8; + } + if (opsize == TCPOLEN_MPTCP_MPC_ACK_DATA) { + /* Section 3.1.: + * "the data parameters in a MP_CAPABLE are semantically + * equivalent to those in a DSS option and can be used + * interchangeably." + */ + mp_opt->dss = 1; + mp_opt->use_map = 1; + mp_opt->mpc_map = 1; + mp_opt->data_len = get_unaligned_be16(ptr); + ptr += 2; + } + pr_debug("MP_CAPABLE version=%x, flags=%x, optlen=%d sndr=%llu, rcvr=%llu len=%d", + version, flags, opsize, mp_opt->sndr_key, + mp_opt->rcvr_key, mp_opt->data_len); + break; + + case MPTCPOPT_DSS: + pr_debug("DSS"); + ptr++; + + /* we must clear 'mpc_map' be able to detect MP_CAPABLE + * map vs DSS map in mptcp_incoming_options(), and reconstruct + * map info accordingly + */ + mp_opt->mpc_map = 0; + flags = (*ptr++) & MPTCP_DSS_FLAG_MASK; + mp_opt->data_fin = (flags & MPTCP_DSS_DATA_FIN) != 0; + mp_opt->dsn64 = (flags & MPTCP_DSS_DSN64) != 0; + mp_opt->use_map = (flags & MPTCP_DSS_HAS_MAP) != 0; + mp_opt->ack64 = (flags & MPTCP_DSS_ACK64) != 0; + mp_opt->use_ack = (flags & MPTCP_DSS_HAS_ACK); + + pr_debug("data_fin=%d dsn64=%d use_map=%d ack64=%d use_ack=%d", + mp_opt->data_fin, mp_opt->dsn64, + mp_opt->use_map, mp_opt->ack64, + mp_opt->use_ack); + + expected_opsize = TCPOLEN_MPTCP_DSS_BASE; + + if (mp_opt->use_ack) { + if (mp_opt->ack64) + expected_opsize += TCPOLEN_MPTCP_DSS_ACK64; + else + expected_opsize += TCPOLEN_MPTCP_DSS_ACK32; + } + + if (mp_opt->use_map) { + if (mp_opt->dsn64) + expected_opsize += TCPOLEN_MPTCP_DSS_MAP64; + else + expected_opsize += TCPOLEN_MPTCP_DSS_MAP32; + } + + /* RFC 6824, Section 3.3: + * If a checksum is present, but its use had + * not been negotiated in the MP_CAPABLE handshake, + * the checksum field MUST be ignored. + */ + if (opsize != expected_opsize && + opsize != expected_opsize + TCPOLEN_MPTCP_DSS_CHECKSUM) + break; + + mp_opt->dss = 1; + + if (mp_opt->use_ack) { + if (mp_opt->ack64) { + mp_opt->data_ack = get_unaligned_be64(ptr); + ptr += 8; + } else { + mp_opt->data_ack = get_unaligned_be32(ptr); + ptr += 4; + } + + pr_debug("data_ack=%llu", mp_opt->data_ack); + } + + if (mp_opt->use_map) { + if (mp_opt->dsn64) { + mp_opt->data_seq = get_unaligned_be64(ptr); + ptr += 8; + } else { + mp_opt->data_seq = get_unaligned_be32(ptr); + ptr += 4; + } + + mp_opt->subflow_seq = get_unaligned_be32(ptr); + ptr += 4; + + mp_opt->data_len = get_unaligned_be16(ptr); + ptr += 2; + + pr_debug("data_seq=%llu subflow_seq=%u data_len=%u", + mp_opt->data_seq, mp_opt->subflow_seq, + mp_opt->data_len); + } + + break; + + default: + break; + } +} + +void mptcp_get_options(const struct sk_buff *skb, + struct tcp_options_received *opt_rx) +{ + const unsigned char *ptr; + const struct tcphdr *th = tcp_hdr(skb); + int length = (th->doff * 4) - sizeof(struct tcphdr); + + ptr = (const unsigned char *)(th + 1); + + while (length > 0) { + int opcode = *ptr++; + int opsize; + + switch (opcode) { + case TCPOPT_EOL: + return; + case TCPOPT_NOP: /* Ref: RFC 793 section 3.1 */ + length--; + continue; + default: + opsize = *ptr++; + if (opsize < 2) /* "silly options" */ + return; + if (opsize > length) + return; /* don't parse partial options */ + if (opcode == TCPOPT_MPTCP) + mptcp_parse_option(skb, ptr, opsize, opt_rx); + ptr += opsize - 2; + length -= opsize; + } + } +} + +bool mptcp_syn_options(struct sock *sk, const struct sk_buff *skb, + unsigned int *size, struct mptcp_out_options *opts) +{ + struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk); + + /* we will use snd_isn to detect first pkt [re]transmission + * in mptcp_established_options_mp() + */ + subflow->snd_isn = TCP_SKB_CB(skb)->end_seq; + if (subflow->request_mptcp) { + pr_debug("local_key=%llu", subflow->local_key); + opts->suboptions = OPTION_MPTCP_MPC_SYN; + opts->sndr_key = subflow->local_key; + *size = TCPOLEN_MPTCP_MPC_SYN; + return true; + } + return false; +} + +void mptcp_rcv_synsent(struct sock *sk) +{ + struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk); + struct tcp_sock *tp = tcp_sk(sk); + + pr_debug("subflow=%p", subflow); + if (subflow->request_mptcp && tp->rx_opt.mptcp.mp_capable) { + subflow->mp_capable = 1; + subflow->can_ack = 1; + subflow->remote_key = tp->rx_opt.mptcp.sndr_key; + } else { + tcp_sk(sk)->is_mptcp = 0; + } +} + +static bool mptcp_established_options_mp(struct sock *sk, struct sk_buff *skb, + unsigned int *size, + unsigned int remaining, + struct mptcp_out_options *opts) +{ + struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk); + struct mptcp_ext *mpext; + unsigned int data_len; + + pr_debug("subflow=%p fourth_ack=%d seq=%x:%x remaining=%d", subflow, + subflow->fourth_ack, subflow->snd_isn, + skb ? TCP_SKB_CB(skb)->seq : 0, remaining); + + if (subflow->mp_capable && !subflow->fourth_ack && skb && + subflow->snd_isn == TCP_SKB_CB(skb)->seq) { + /* When skb is not available, we better over-estimate the + * emitted options len. A full DSS option is longer than + * TCPOLEN_MPTCP_MPC_ACK_DATA, so let's the caller try to fit + * that. + */ + mpext = mptcp_get_ext(skb); + data_len = mpext ? mpext->data_len : 0; + + /* we will check ext_copy.data_len in mptcp_write_options() to + * discriminate between TCPOLEN_MPTCP_MPC_ACK_DATA and + * TCPOLEN_MPTCP_MPC_ACK + */ + opts->ext_copy.data_len = data_len; + opts->suboptions = OPTION_MPTCP_MPC_ACK; + opts->sndr_key = subflow->local_key; + opts->rcvr_key = subflow->remote_key; + + /* Section 3.1. + * The MP_CAPABLE option is carried on the SYN, SYN/ACK, and ACK + * packets that start the first subflow of an MPTCP connection, + * as well as the first packet that carries data + */ + if (data_len > 0) + *size = ALIGN(TCPOLEN_MPTCP_MPC_ACK_DATA, 4); + else + *size = TCPOLEN_MPTCP_MPC_ACK; + + pr_debug("subflow=%p, local_key=%llu, remote_key=%llu map_len=%d", + subflow, subflow->local_key, subflow->remote_key, + data_len); + + return true; + } + return false; +} + +static void mptcp_write_data_fin(struct mptcp_subflow_context *subflow, + struct mptcp_ext *ext) +{ + ext->data_fin = 1; + + if (!ext->use_map) { + /* RFC6824 requires a DSS mapping with specific values + * if DATA_FIN is set but no data payload is mapped + */ + ext->use_map = 1; + ext->dsn64 = 1; + ext->data_seq = mptcp_sk(subflow->conn)->write_seq; + ext->subflow_seq = 0; + ext->data_len = 1; + } else { + /* If there's an existing DSS mapping, DATA_FIN consumes + * 1 additional byte of mapping space. + */ + ext->data_len++; + } +} + +static bool mptcp_established_options_dss(struct sock *sk, struct sk_buff *skb, + unsigned int *size, + unsigned int remaining, + struct mptcp_out_options *opts) +{ + struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk); + unsigned int dss_size = 0; + struct mptcp_ext *mpext; + struct mptcp_sock *msk; + unsigned int ack_size; + bool ret = false; + u8 tcp_fin; + + if (skb) { + mpext = mptcp_get_ext(skb); + tcp_fin = TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN; + } else { + mpext = NULL; + tcp_fin = 0; + } + + if (!skb || (mpext && mpext->use_map) || tcp_fin) { + unsigned int map_size; + + map_size = TCPOLEN_MPTCP_DSS_BASE + TCPOLEN_MPTCP_DSS_MAP64; + + remaining -= map_size; + dss_size = map_size; + if (mpext) + opts->ext_copy = *mpext; + + if (skb && tcp_fin && + subflow->conn->sk_state != TCP_ESTABLISHED) + mptcp_write_data_fin(subflow, &opts->ext_copy); + ret = true; + } + + opts->ext_copy.use_ack = 0; + msk = mptcp_sk(subflow->conn); + if (!msk || !READ_ONCE(msk->can_ack)) { + *size = ALIGN(dss_size, 4); + return ret; + } + + ack_size = TCPOLEN_MPTCP_DSS_ACK64; + + /* Add kind/length/subtype/flag overhead if mapping is not populated */ + if (dss_size == 0) + ack_size += TCPOLEN_MPTCP_DSS_BASE; + + dss_size += ack_size; + + opts->ext_copy.data_ack = msk->ack_seq; + opts->ext_copy.ack64 = 1; + opts->ext_copy.use_ack = 1; + + *size = ALIGN(dss_size, 4); + return true; +} + +bool mptcp_established_options(struct sock *sk, struct sk_buff *skb, + unsigned int *size, unsigned int remaining, + struct mptcp_out_options *opts) +{ + unsigned int opt_size = 0; + bool ret = false; + + if (mptcp_established_options_mp(sk, skb, &opt_size, remaining, opts)) + ret = true; + else if (mptcp_established_options_dss(sk, skb, &opt_size, remaining, + opts)) + ret = true; + + /* we reserved enough space for the above options, and exceeding the + * TCP option space would be fatal + */ + if (WARN_ON_ONCE(opt_size > remaining)) + return false; + + *size += opt_size; + remaining -= opt_size; + + return ret; +} + +bool mptcp_synack_options(const struct request_sock *req, unsigned int *size, + struct mptcp_out_options *opts) +{ + struct mptcp_subflow_request_sock *subflow_req = mptcp_subflow_rsk(req); + + if (subflow_req->mp_capable) { + opts->suboptions = OPTION_MPTCP_MPC_SYNACK; + opts->sndr_key = subflow_req->local_key; + *size = TCPOLEN_MPTCP_MPC_SYNACK; + pr_debug("subflow_req=%p, local_key=%llu", + subflow_req, subflow_req->local_key); + return true; + } + return false; +} + +static bool check_fourth_ack(struct mptcp_subflow_context *subflow, + struct sk_buff *skb, + struct mptcp_options_received *mp_opt) +{ + /* here we can process OoO, in-window pkts, only in-sequence 4th ack + * are relevant + */ + if (likely(subflow->fourth_ack || + TCP_SKB_CB(skb)->seq != subflow->ssn_offset + 1)) + return true; + + if (mp_opt->use_ack) + subflow->fourth_ack = 1; + + if (subflow->can_ack) + return true; + + /* If the first established packet does not contain MP_CAPABLE + data + * then fallback to TCP + */ + if (!mp_opt->mp_capable) { + subflow->mp_capable = 0; + tcp_sk(mptcp_subflow_tcp_sock(subflow))->is_mptcp = 0; + return false; + } + subflow->remote_key = mp_opt->sndr_key; + subflow->can_ack = 1; + return true; +} + +void mptcp_incoming_options(struct sock *sk, struct sk_buff *skb, + struct tcp_options_received *opt_rx) +{ + struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk); + struct mptcp_options_received *mp_opt; + struct mptcp_ext *mpext; + + mp_opt = &opt_rx->mptcp; + if (!check_fourth_ack(subflow, skb, mp_opt)) + return; + + if (!mp_opt->dss) + return; + + mpext = skb_ext_add(skb, SKB_EXT_MPTCP); + if (!mpext) + return; + + memset(mpext, 0, sizeof(*mpext)); + + if (mp_opt->use_map) { + if (mp_opt->mpc_map) { + /* this is an MP_CAPABLE carrying MPTCP data + * we know this map the first chunk of data + */ + mptcp_crypto_key_sha(subflow->remote_key, NULL, + &mpext->data_seq); + mpext->data_seq++; + mpext->subflow_seq = 1; + mpext->dsn64 = 1; + mpext->mpc_map = 1; + } else { + mpext->data_seq = mp_opt->data_seq; + mpext->subflow_seq = mp_opt->subflow_seq; + mpext->dsn64 = mp_opt->dsn64; + } + mpext->data_len = mp_opt->data_len; + mpext->use_map = 1; + } + + if (mp_opt->use_ack) { + mpext->data_ack = mp_opt->data_ack; + mpext->use_ack = 1; + mpext->ack64 = mp_opt->ack64; + } + + mpext->data_fin = mp_opt->data_fin; +} + +void mptcp_write_options(__be32 *ptr, struct mptcp_out_options *opts) +{ + if ((OPTION_MPTCP_MPC_SYN | OPTION_MPTCP_MPC_SYNACK | + OPTION_MPTCP_MPC_ACK) & opts->suboptions) { + u8 len; + + if (OPTION_MPTCP_MPC_SYN & opts->suboptions) + len = TCPOLEN_MPTCP_MPC_SYN; + else if (OPTION_MPTCP_MPC_SYNACK & opts->suboptions) + len = TCPOLEN_MPTCP_MPC_SYNACK; + else if (opts->ext_copy.data_len) + len = TCPOLEN_MPTCP_MPC_ACK_DATA; + else + len = TCPOLEN_MPTCP_MPC_ACK; + + *ptr++ = htonl((TCPOPT_MPTCP << 24) | (len << 16) | + (MPTCPOPT_MP_CAPABLE << 12) | + (MPTCP_SUPPORTED_VERSION << 8) | + MPTCP_CAP_HMAC_SHA256); + + if (!((OPTION_MPTCP_MPC_SYNACK | OPTION_MPTCP_MPC_ACK) & + opts->suboptions)) + goto mp_capable_done; + + put_unaligned_be64(opts->sndr_key, ptr); + ptr += 2; + if (!((OPTION_MPTCP_MPC_ACK) & opts->suboptions)) + goto mp_capable_done; + + put_unaligned_be64(opts->rcvr_key, ptr); + ptr += 2; + if (!opts->ext_copy.data_len) + goto mp_capable_done; + + put_unaligned_be32(opts->ext_copy.data_len << 16 | + TCPOPT_NOP << 8 | TCPOPT_NOP, ptr); + ptr += 1; + } + +mp_capable_done: + if (opts->ext_copy.use_ack || opts->ext_copy.use_map) { + struct mptcp_ext *mpext = &opts->ext_copy; + u8 len = TCPOLEN_MPTCP_DSS_BASE; + u8 flags = 0; + + if (mpext->use_ack) { + len += TCPOLEN_MPTCP_DSS_ACK64; + flags = MPTCP_DSS_HAS_ACK | MPTCP_DSS_ACK64; + } + + if (mpext->use_map) { + len += TCPOLEN_MPTCP_DSS_MAP64; + + /* Use only 64-bit mapping flags for now, add + * support for optional 32-bit mappings later. + */ + flags |= MPTCP_DSS_HAS_MAP | MPTCP_DSS_DSN64; + if (mpext->data_fin) + flags |= MPTCP_DSS_DATA_FIN; + } + + *ptr++ = htonl((TCPOPT_MPTCP << 24) | + (len << 16) | + (MPTCPOPT_DSS << 12) | + (flags)); + + if (mpext->use_ack) { + put_unaligned_be64(mpext->data_ack, ptr); + ptr += 2; + } + + if (mpext->use_map) { + put_unaligned_be64(mpext->data_seq, ptr); + ptr += 2; + put_unaligned_be32(mpext->subflow_seq, ptr); + ptr += 1; + put_unaligned_be32(mpext->data_len << 16 | + TCPOPT_NOP << 8 | TCPOPT_NOP, ptr); + } + } +} diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c new file mode 100644 index 000000000000..39fdca79ce90 --- /dev/null +++ b/net/mptcp/protocol.c @@ -0,0 +1,1276 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Multipath TCP + * + * Copyright (c) 2017 - 2019, Intel Corporation. + */ + +#define pr_fmt(fmt) "MPTCP: " fmt + +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/netdevice.h> +#include <linux/sched/signal.h> +#include <linux/atomic.h> +#include <net/sock.h> +#include <net/inet_common.h> +#include <net/inet_hashtables.h> +#include <net/protocol.h> +#include <net/tcp.h> +#if IS_ENABLED(CONFIG_MPTCP_IPV6) +#include <net/transp_v6.h> +#endif +#include <net/mptcp.h> +#include "protocol.h" + +#define MPTCP_SAME_STATE TCP_MAX_STATES + +static void __mptcp_close(struct sock *sk, long timeout); + +static const struct proto_ops *tcp_proto_ops(struct sock *sk) +{ +#if IS_ENABLED(CONFIG_IPV6) + if (sk->sk_family == AF_INET6) + return &inet6_stream_ops; +#endif + return &inet_stream_ops; +} + +/* MP_CAPABLE handshake failed, convert msk to plain tcp, replacing + * socket->sk and stream ops and destroying msk + * return the msk socket, as we can't access msk anymore after this function + * completes + * Called with msk lock held, releases such lock before returning + */ +static struct socket *__mptcp_fallback_to_tcp(struct mptcp_sock *msk, + struct sock *ssk) +{ + struct mptcp_subflow_context *subflow; + struct socket *sock; + struct sock *sk; + + sk = (struct sock *)msk; + sock = sk->sk_socket; + subflow = mptcp_subflow_ctx(ssk); + + /* detach the msk socket */ + list_del_init(&subflow->node); + sock_orphan(sk); + sock->sk = NULL; + + /* socket is now TCP */ + lock_sock(ssk); + sock_graft(ssk, sock); + if (subflow->conn) { + /* We can't release the ULP data on a live socket, + * restore the tcp callback + */ + mptcp_subflow_tcp_fallback(ssk, subflow); + sock_put(subflow->conn); + subflow->conn = NULL; + } + release_sock(ssk); + sock->ops = tcp_proto_ops(ssk); + + /* destroy the left-over msk sock */ + __mptcp_close(sk, 0); + return sock; +} + +/* If msk has an initial subflow socket, and the MP_CAPABLE handshake has not + * completed yet or has failed, return the subflow socket. + * Otherwise return NULL. + */ +static struct socket *__mptcp_nmpc_socket(const struct mptcp_sock *msk) +{ + if (!msk->subflow || READ_ONCE(msk->can_ack)) + return NULL; + + return msk->subflow; +} + +static bool __mptcp_needs_tcp_fallback(const struct mptcp_sock *msk) +{ + return msk->first && !sk_is_mptcp(msk->first); +} + +/* if the mp_capable handshake has failed, it fallbacks msk to plain TCP, + * releases the socket lock and returns a reference to the now TCP socket. + * Otherwise returns NULL + */ +static struct socket *__mptcp_tcp_fallback(struct mptcp_sock *msk) +{ + sock_owned_by_me((const struct sock *)msk); + + if (likely(!__mptcp_needs_tcp_fallback(msk))) + return NULL; + + if (msk->subflow) { + /* the first subflow is an active connection, discart the + * paired socket + */ + msk->subflow->sk = NULL; + sock_release(msk->subflow); + msk->subflow = NULL; + } + + return __mptcp_fallback_to_tcp(msk, msk->first); +} + +static bool __mptcp_can_create_subflow(const struct mptcp_sock *msk) +{ + return !msk->first; +} + +static struct socket *__mptcp_socket_create(struct mptcp_sock *msk, int state) +{ + struct mptcp_subflow_context *subflow; + struct sock *sk = (struct sock *)msk; + struct socket *ssock; + int err; + + ssock = __mptcp_nmpc_socket(msk); + if (ssock) + goto set_state; + + if (!__mptcp_can_create_subflow(msk)) + return ERR_PTR(-EINVAL); + + err = mptcp_subflow_create_socket(sk, &ssock); + if (err) + return ERR_PTR(err); + + msk->first = ssock->sk; + msk->subflow = ssock; + subflow = mptcp_subflow_ctx(ssock->sk); + list_add(&subflow->node, &msk->conn_list); + subflow->request_mptcp = 1; + +set_state: + if (state != MPTCP_SAME_STATE) + inet_sk_state_store(sk, state); + return ssock; +} + +static struct sock *mptcp_subflow_get(const struct mptcp_sock *msk) +{ + struct mptcp_subflow_context *subflow; + + sock_owned_by_me((const struct sock *)msk); + + mptcp_for_each_subflow(msk, subflow) { + return mptcp_subflow_tcp_sock(subflow); + } + + return NULL; +} + +static bool mptcp_ext_cache_refill(struct mptcp_sock *msk) +{ + if (!msk->cached_ext) + msk->cached_ext = __skb_ext_alloc(); + + return !!msk->cached_ext; +} + +static struct sock *mptcp_subflow_recv_lookup(const struct mptcp_sock *msk) +{ + struct mptcp_subflow_context *subflow; + struct sock *sk = (struct sock *)msk; + + sock_owned_by_me(sk); + + mptcp_for_each_subflow(msk, subflow) { + if (subflow->data_avail) + return mptcp_subflow_tcp_sock(subflow); + } + + return NULL; +} + +static inline bool mptcp_skb_can_collapse_to(const struct mptcp_sock *msk, + const struct sk_buff *skb, + const struct mptcp_ext *mpext) +{ + if (!tcp_skb_can_collapse_to(skb)) + return false; + + /* can collapse only if MPTCP level sequence is in order */ + return mpext && mpext->data_seq + mpext->data_len == msk->write_seq; +} + +static int mptcp_sendmsg_frag(struct sock *sk, struct sock *ssk, + struct msghdr *msg, long *timeo, int *pmss_now, + int *ps_goal) +{ + int mss_now, avail_size, size_goal, ret; + struct mptcp_sock *msk = mptcp_sk(sk); + struct mptcp_ext *mpext = NULL; + struct sk_buff *skb, *tail; + bool can_collapse = false; + struct page_frag *pfrag; + size_t psize; + + /* use the mptcp page cache so that we can easily move the data + * from one substream to another, but do per subflow memory accounting + */ + pfrag = sk_page_frag(sk); + while (!sk_page_frag_refill(ssk, pfrag) || + !mptcp_ext_cache_refill(msk)) { + ret = sk_stream_wait_memory(ssk, timeo); + if (ret) + return ret; + if (unlikely(__mptcp_needs_tcp_fallback(msk))) + return 0; + } + + /* compute copy limit */ + mss_now = tcp_send_mss(ssk, &size_goal, msg->msg_flags); + *pmss_now = mss_now; + *ps_goal = size_goal; + avail_size = size_goal; + skb = tcp_write_queue_tail(ssk); + if (skb) { + mpext = skb_ext_find(skb, SKB_EXT_MPTCP); + + /* Limit the write to the size available in the + * current skb, if any, so that we create at most a new skb. + * Explicitly tells TCP internals to avoid collapsing on later + * queue management operation, to avoid breaking the ext <-> + * SSN association set here + */ + can_collapse = (size_goal - skb->len > 0) && + mptcp_skb_can_collapse_to(msk, skb, mpext); + if (!can_collapse) + TCP_SKB_CB(skb)->eor = 1; + else + avail_size = size_goal - skb->len; + } + psize = min_t(size_t, pfrag->size - pfrag->offset, avail_size); + + /* Copy to page */ + pr_debug("left=%zu", msg_data_left(msg)); + psize = copy_page_from_iter(pfrag->page, pfrag->offset, + min_t(size_t, msg_data_left(msg), psize), + &msg->msg_iter); + pr_debug("left=%zu", msg_data_left(msg)); + if (!psize) + return -EINVAL; + + /* tell the TCP stack to delay the push so that we can safely + * access the skb after the sendpages call + */ + ret = do_tcp_sendpages(ssk, pfrag->page, pfrag->offset, psize, + msg->msg_flags | MSG_SENDPAGE_NOTLAST); + if (ret <= 0) + return ret; + if (unlikely(ret < psize)) + iov_iter_revert(&msg->msg_iter, psize - ret); + + /* if the tail skb extension is still the cached one, collapsing + * really happened. Note: we can't check for 'same skb' as the sk_buff + * hdr on tail can be transmitted, freed and re-allocated by the + * do_tcp_sendpages() call + */ + tail = tcp_write_queue_tail(ssk); + if (mpext && tail && mpext == skb_ext_find(tail, SKB_EXT_MPTCP)) { + WARN_ON_ONCE(!can_collapse); + mpext->data_len += ret; + goto out; + } + + skb = tcp_write_queue_tail(ssk); + mpext = __skb_ext_set(skb, SKB_EXT_MPTCP, msk->cached_ext); + msk->cached_ext = NULL; + + memset(mpext, 0, sizeof(*mpext)); + mpext->data_seq = msk->write_seq; + mpext->subflow_seq = mptcp_subflow_ctx(ssk)->rel_write_seq; + mpext->data_len = ret; + mpext->use_map = 1; + mpext->dsn64 = 1; + + pr_debug("data_seq=%llu subflow_seq=%u data_len=%u dsn64=%d", + mpext->data_seq, mpext->subflow_seq, mpext->data_len, + mpext->dsn64); + +out: + pfrag->offset += ret; + msk->write_seq += ret; + mptcp_subflow_ctx(ssk)->rel_write_seq += ret; + + return ret; +} + +static void ssk_check_wmem(struct mptcp_sock *msk, struct sock *ssk) +{ + struct socket *sock; + + if (likely(sk_stream_is_writeable(ssk))) + return; + + sock = READ_ONCE(ssk->sk_socket); + + if (sock) { + clear_bit(MPTCP_SEND_SPACE, &msk->flags); + smp_mb__after_atomic(); + /* set NOSPACE only after clearing SEND_SPACE flag */ + set_bit(SOCK_NOSPACE, &sock->flags); + } +} + +static int mptcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) +{ + int mss_now = 0, size_goal = 0, ret = 0; + struct mptcp_sock *msk = mptcp_sk(sk); + struct socket *ssock; + size_t copied = 0; + struct sock *ssk; + long timeo; + + if (msg->msg_flags & ~(MSG_MORE | MSG_DONTWAIT | MSG_NOSIGNAL)) + return -EOPNOTSUPP; + + lock_sock(sk); + ssock = __mptcp_tcp_fallback(msk); + if (unlikely(ssock)) { +fallback: + pr_debug("fallback passthrough"); + ret = sock_sendmsg(ssock, msg); + return ret >= 0 ? ret + copied : (copied ? copied : ret); + } + + timeo = sock_sndtimeo(sk, msg->msg_flags & MSG_DONTWAIT); + + ssk = mptcp_subflow_get(msk); + if (!ssk) { + release_sock(sk); + return -ENOTCONN; + } + + pr_debug("conn_list->subflow=%p", ssk); + + lock_sock(ssk); + while (msg_data_left(msg)) { + ret = mptcp_sendmsg_frag(sk, ssk, msg, &timeo, &mss_now, + &size_goal); + if (ret < 0) + break; + if (ret == 0 && unlikely(__mptcp_needs_tcp_fallback(msk))) { + release_sock(ssk); + ssock = __mptcp_tcp_fallback(msk); + goto fallback; + } + + copied += ret; + } + + if (copied) { + ret = copied; + tcp_push(ssk, msg->msg_flags, mss_now, tcp_sk(ssk)->nonagle, + size_goal); + } + + ssk_check_wmem(msk, ssk); + release_sock(ssk); + release_sock(sk); + return ret; +} + +int mptcp_read_actor(read_descriptor_t *desc, struct sk_buff *skb, + unsigned int offset, size_t len) +{ + struct mptcp_read_arg *arg = desc->arg.data; + size_t copy_len; + + copy_len = min(desc->count, len); + + if (likely(arg->msg)) { + int err; + + err = skb_copy_datagram_msg(skb, offset, arg->msg, copy_len); + if (err) { + pr_debug("error path"); + desc->error = err; + return err; + } + } else { + pr_debug("Flushing skb payload"); + } + + desc->count -= copy_len; + + pr_debug("consumed %zu bytes, %zu left", copy_len, desc->count); + return copy_len; +} + +static void mptcp_wait_data(struct sock *sk, long *timeo) +{ + DEFINE_WAIT_FUNC(wait, woken_wake_function); + struct mptcp_sock *msk = mptcp_sk(sk); + + add_wait_queue(sk_sleep(sk), &wait); + sk_set_bit(SOCKWQ_ASYNC_WAITDATA, sk); + + sk_wait_event(sk, timeo, + test_and_clear_bit(MPTCP_DATA_READY, &msk->flags), &wait); + + sk_clear_bit(SOCKWQ_ASYNC_WAITDATA, sk); + remove_wait_queue(sk_sleep(sk), &wait); +} + +static int mptcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, + int nonblock, int flags, int *addr_len) +{ + struct mptcp_sock *msk = mptcp_sk(sk); + struct mptcp_subflow_context *subflow; + bool more_data_avail = false; + struct mptcp_read_arg arg; + read_descriptor_t desc; + bool wait_data = false; + struct socket *ssock; + struct tcp_sock *tp; + bool done = false; + struct sock *ssk; + int copied = 0; + int target; + long timeo; + + if (msg->msg_flags & ~(MSG_WAITALL | MSG_DONTWAIT)) + return -EOPNOTSUPP; + + lock_sock(sk); + ssock = __mptcp_tcp_fallback(msk); + if (unlikely(ssock)) { +fallback: + pr_debug("fallback-read subflow=%p", + mptcp_subflow_ctx(ssock->sk)); + copied = sock_recvmsg(ssock, msg, flags); + return copied; + } + + arg.msg = msg; + desc.arg.data = &arg; + desc.error = 0; + + timeo = sock_rcvtimeo(sk, nonblock); + + len = min_t(size_t, len, INT_MAX); + target = sock_rcvlowat(sk, flags & MSG_WAITALL, len); + + while (!done) { + u32 map_remaining; + int bytes_read; + + ssk = mptcp_subflow_recv_lookup(msk); + pr_debug("msk=%p ssk=%p", msk, ssk); + if (!ssk) + goto wait_for_data; + + subflow = mptcp_subflow_ctx(ssk); + tp = tcp_sk(ssk); + + lock_sock(ssk); + do { + /* try to read as much data as available */ + map_remaining = subflow->map_data_len - + mptcp_subflow_get_map_offset(subflow); + desc.count = min_t(size_t, len - copied, map_remaining); + pr_debug("reading %zu bytes, copied %d", desc.count, + copied); + bytes_read = tcp_read_sock(ssk, &desc, + mptcp_read_actor); + if (bytes_read < 0) { + if (!copied) + copied = bytes_read; + done = true; + goto next; + } + + pr_debug("msk ack_seq=%llx -> %llx", msk->ack_seq, + msk->ack_seq + bytes_read); + msk->ack_seq += bytes_read; + copied += bytes_read; + if (copied >= len) { + done = true; + goto next; + } + if (tp->urg_data && tp->urg_seq == tp->copied_seq) { + pr_err("Urgent data present, cannot proceed"); + done = true; + goto next; + } +next: + more_data_avail = mptcp_subflow_data_available(ssk); + } while (more_data_avail && !done); + release_sock(ssk); + continue; + +wait_for_data: + more_data_avail = false; + + /* only the master socket status is relevant here. The exit + * conditions mirror closely tcp_recvmsg() + */ + if (copied >= target) + break; + + if (copied) { + if (sk->sk_err || + sk->sk_state == TCP_CLOSE || + (sk->sk_shutdown & RCV_SHUTDOWN) || + !timeo || + signal_pending(current)) + break; + } else { + if (sk->sk_err) { + copied = sock_error(sk); + break; + } + + if (sk->sk_shutdown & RCV_SHUTDOWN) + break; + + if (sk->sk_state == TCP_CLOSE) { + copied = -ENOTCONN; + break; + } + + if (!timeo) { + copied = -EAGAIN; + break; + } + + if (signal_pending(current)) { + copied = sock_intr_errno(timeo); + break; + } + } + + pr_debug("block timeout %ld", timeo); + wait_data = true; + mptcp_wait_data(sk, &timeo); + if (unlikely(__mptcp_tcp_fallback(msk))) + goto fallback; + } + + if (more_data_avail) { + if (!test_bit(MPTCP_DATA_READY, &msk->flags)) + set_bit(MPTCP_DATA_READY, &msk->flags); + } else if (!wait_data) { + clear_bit(MPTCP_DATA_READY, &msk->flags); + + /* .. race-breaker: ssk might get new data after last + * data_available() returns false. + */ + ssk = mptcp_subflow_recv_lookup(msk); + if (unlikely(ssk)) + set_bit(MPTCP_DATA_READY, &msk->flags); + } + + release_sock(sk); + return copied; +} + +/* subflow sockets can be either outgoing (connect) or incoming + * (accept). + * + * Outgoing subflows use in-kernel sockets. + * Incoming subflows do not have their own 'struct socket' allocated, + * so we need to use tcp_close() after detaching them from the mptcp + * parent socket. + */ +static void __mptcp_close_ssk(struct sock *sk, struct sock *ssk, + struct mptcp_subflow_context *subflow, + long timeout) +{ + struct socket *sock = READ_ONCE(ssk->sk_socket); + + list_del(&subflow->node); + + if (sock && sock != sk->sk_socket) { + /* outgoing subflow */ + sock_release(sock); + } else { + /* incoming subflow */ + tcp_close(ssk, timeout); + } +} + +static int __mptcp_init_sock(struct sock *sk) +{ + struct mptcp_sock *msk = mptcp_sk(sk); + + INIT_LIST_HEAD(&msk->conn_list); + __set_bit(MPTCP_SEND_SPACE, &msk->flags); + + msk->first = NULL; + + return 0; +} + +static int mptcp_init_sock(struct sock *sk) +{ + if (!mptcp_is_enabled(sock_net(sk))) + return -ENOPROTOOPT; + + return __mptcp_init_sock(sk); +} + +static void mptcp_subflow_shutdown(struct sock *ssk, int how) +{ + lock_sock(ssk); + + switch (ssk->sk_state) { + case TCP_LISTEN: + if (!(how & RCV_SHUTDOWN)) + break; + /* fall through */ + case TCP_SYN_SENT: + tcp_disconnect(ssk, O_NONBLOCK); + break; + default: + ssk->sk_shutdown |= how; + tcp_shutdown(ssk, how); + break; + } + + /* Wake up anyone sleeping in poll. */ + ssk->sk_state_change(ssk); + release_sock(ssk); +} + +/* Called with msk lock held, releases such lock before returning */ +static void __mptcp_close(struct sock *sk, long timeout) +{ + struct mptcp_subflow_context *subflow, *tmp; + struct mptcp_sock *msk = mptcp_sk(sk); + + mptcp_token_destroy(msk->token); + inet_sk_state_store(sk, TCP_CLOSE); + + list_for_each_entry_safe(subflow, tmp, &msk->conn_list, node) { + struct sock *ssk = mptcp_subflow_tcp_sock(subflow); + + __mptcp_close_ssk(sk, ssk, subflow, timeout); + } + + if (msk->cached_ext) + __skb_ext_put(msk->cached_ext); + release_sock(sk); + sk_common_release(sk); +} + +static void mptcp_close(struct sock *sk, long timeout) +{ + lock_sock(sk); + __mptcp_close(sk, timeout); +} + +static void mptcp_copy_inaddrs(struct sock *msk, const struct sock *ssk) +{ +#if IS_ENABLED(CONFIG_MPTCP_IPV6) + const struct ipv6_pinfo *ssk6 = inet6_sk(ssk); + struct ipv6_pinfo *msk6 = inet6_sk(msk); + + msk->sk_v6_daddr = ssk->sk_v6_daddr; + msk->sk_v6_rcv_saddr = ssk->sk_v6_rcv_saddr; + + if (msk6 && ssk6) { + msk6->saddr = ssk6->saddr; + msk6->flow_label = ssk6->flow_label; + } +#endif + + inet_sk(msk)->inet_num = inet_sk(ssk)->inet_num; + inet_sk(msk)->inet_dport = inet_sk(ssk)->inet_dport; + inet_sk(msk)->inet_sport = inet_sk(ssk)->inet_sport; + inet_sk(msk)->inet_daddr = inet_sk(ssk)->inet_daddr; + inet_sk(msk)->inet_saddr = inet_sk(ssk)->inet_saddr; + inet_sk(msk)->inet_rcv_saddr = inet_sk(ssk)->inet_rcv_saddr; +} + +static struct sock *mptcp_accept(struct sock *sk, int flags, int *err, + bool kern) +{ + struct mptcp_sock *msk = mptcp_sk(sk); + struct socket *listener; + struct sock *newsk; + + listener = __mptcp_nmpc_socket(msk); + if (WARN_ON_ONCE(!listener)) { + *err = -EINVAL; + return NULL; + } + + pr_debug("msk=%p, listener=%p", msk, mptcp_subflow_ctx(listener->sk)); + newsk = inet_csk_accept(listener->sk, flags, err, kern); + if (!newsk) + return NULL; + + pr_debug("msk=%p, subflow is mptcp=%d", msk, sk_is_mptcp(newsk)); + + if (sk_is_mptcp(newsk)) { + struct mptcp_subflow_context *subflow; + struct sock *new_mptcp_sock; + struct sock *ssk = newsk; + u64 ack_seq; + + subflow = mptcp_subflow_ctx(newsk); + lock_sock(sk); + + local_bh_disable(); + new_mptcp_sock = sk_clone_lock(sk, GFP_ATOMIC); + if (!new_mptcp_sock) { + *err = -ENOBUFS; + local_bh_enable(); + release_sock(sk); + mptcp_subflow_shutdown(newsk, SHUT_RDWR + 1); + tcp_close(newsk, 0); + return NULL; + } + + __mptcp_init_sock(new_mptcp_sock); + + msk = mptcp_sk(new_mptcp_sock); + msk->local_key = subflow->local_key; + msk->token = subflow->token; + msk->subflow = NULL; + msk->first = newsk; + + mptcp_token_update_accept(newsk, new_mptcp_sock); + + msk->write_seq = subflow->idsn + 1; + if (subflow->can_ack) { + msk->can_ack = true; + msk->remote_key = subflow->remote_key; + mptcp_crypto_key_sha(msk->remote_key, NULL, &ack_seq); + ack_seq++; + msk->ack_seq = ack_seq; + } + newsk = new_mptcp_sock; + mptcp_copy_inaddrs(newsk, ssk); + list_add(&subflow->node, &msk->conn_list); + + /* will be fully established at mptcp_stream_accept() + * completion. + */ + inet_sk_state_store(new_mptcp_sock, TCP_SYN_RECV); + bh_unlock_sock(new_mptcp_sock); + local_bh_enable(); + release_sock(sk); + + /* the subflow can already receive packet, avoid racing with + * the receive path and process the pending ones + */ + lock_sock(ssk); + subflow->rel_write_seq = 1; + subflow->tcp_sock = ssk; + subflow->conn = new_mptcp_sock; + if (unlikely(!skb_queue_empty(&ssk->sk_receive_queue))) + mptcp_subflow_data_available(ssk); + release_sock(ssk); + } + + return newsk; +} + +static void mptcp_destroy(struct sock *sk) +{ +} + +static int mptcp_setsockopt(struct sock *sk, int level, int optname, + char __user *uoptval, unsigned int optlen) +{ + struct mptcp_sock *msk = mptcp_sk(sk); + char __kernel *optval; + int ret = -EOPNOTSUPP; + struct socket *ssock; + + /* will be treated as __user in tcp_setsockopt */ + optval = (char __kernel __force *)uoptval; + + pr_debug("msk=%p", msk); + + /* @@ the meaning of setsockopt() when the socket is connected and + * there are multiple subflows is not defined. + */ + lock_sock(sk); + ssock = __mptcp_socket_create(msk, MPTCP_SAME_STATE); + if (!IS_ERR(ssock)) { + pr_debug("subflow=%p", ssock->sk); + ret = kernel_setsockopt(ssock, level, optname, optval, optlen); + } + release_sock(sk); + + return ret; +} + +static int mptcp_getsockopt(struct sock *sk, int level, int optname, + char __user *uoptval, int __user *uoption) +{ + struct mptcp_sock *msk = mptcp_sk(sk); + char __kernel *optval; + int ret = -EOPNOTSUPP; + int __kernel *option; + struct socket *ssock; + + /* will be treated as __user in tcp_getsockopt */ + optval = (char __kernel __force *)uoptval; + option = (int __kernel __force *)uoption; + + pr_debug("msk=%p", msk); + + /* @@ the meaning of getsockopt() when the socket is connected and + * there are multiple subflows is not defined. + */ + lock_sock(sk); + ssock = __mptcp_socket_create(msk, MPTCP_SAME_STATE); + if (!IS_ERR(ssock)) { + pr_debug("subflow=%p", ssock->sk); + ret = kernel_getsockopt(ssock, level, optname, optval, option); + } + release_sock(sk); + + return ret; +} + +static int mptcp_get_port(struct sock *sk, unsigned short snum) +{ + struct mptcp_sock *msk = mptcp_sk(sk); + struct socket *ssock; + + ssock = __mptcp_nmpc_socket(msk); + pr_debug("msk=%p, subflow=%p", msk, ssock); + if (WARN_ON_ONCE(!ssock)) + return -EINVAL; + + return inet_csk_get_port(ssock->sk, snum); +} + +void mptcp_finish_connect(struct sock *ssk) +{ + struct mptcp_subflow_context *subflow; + struct mptcp_sock *msk; + struct sock *sk; + u64 ack_seq; + + subflow = mptcp_subflow_ctx(ssk); + + if (!subflow->mp_capable) + return; + + sk = subflow->conn; + msk = mptcp_sk(sk); + + pr_debug("msk=%p, token=%u", sk, subflow->token); + + mptcp_crypto_key_sha(subflow->remote_key, NULL, &ack_seq); + ack_seq++; + subflow->map_seq = ack_seq; + subflow->map_subflow_seq = 1; + subflow->rel_write_seq = 1; + + /* the socket is not connected yet, no msk/subflow ops can access/race + * accessing the field below + */ + WRITE_ONCE(msk->remote_key, subflow->remote_key); + WRITE_ONCE(msk->local_key, subflow->local_key); + WRITE_ONCE(msk->token, subflow->token); + WRITE_ONCE(msk->write_seq, subflow->idsn + 1); + WRITE_ONCE(msk->ack_seq, ack_seq); + WRITE_ONCE(msk->can_ack, 1); +} + +static void mptcp_sock_graft(struct sock *sk, struct socket *parent) +{ + write_lock_bh(&sk->sk_callback_lock); + rcu_assign_pointer(sk->sk_wq, &parent->wq); + sk_set_socket(sk, parent); + sk->sk_uid = SOCK_INODE(parent)->i_uid; + write_unlock_bh(&sk->sk_callback_lock); +} + +static bool mptcp_memory_free(const struct sock *sk, int wake) +{ + struct mptcp_sock *msk = mptcp_sk(sk); + + return wake ? test_bit(MPTCP_SEND_SPACE, &msk->flags) : true; +} + +static struct proto mptcp_prot = { + .name = "MPTCP", + .owner = THIS_MODULE, + .init = mptcp_init_sock, + .close = mptcp_close, + .accept = mptcp_accept, + .setsockopt = mptcp_setsockopt, + .getsockopt = mptcp_getsockopt, + .shutdown = tcp_shutdown, + .destroy = mptcp_destroy, + .sendmsg = mptcp_sendmsg, + .recvmsg = mptcp_recvmsg, + .hash = inet_hash, + .unhash = inet_unhash, + .get_port = mptcp_get_port, + .stream_memory_free = mptcp_memory_free, + .obj_size = sizeof(struct mptcp_sock), + .no_autobind = true, +}; + +static int mptcp_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) +{ + struct mptcp_sock *msk = mptcp_sk(sock->sk); + struct socket *ssock; + int err; + + lock_sock(sock->sk); + ssock = __mptcp_socket_create(msk, MPTCP_SAME_STATE); + if (IS_ERR(ssock)) { + err = PTR_ERR(ssock); + goto unlock; + } + + err = ssock->ops->bind(ssock, uaddr, addr_len); + if (!err) + mptcp_copy_inaddrs(sock->sk, ssock->sk); + +unlock: + release_sock(sock->sk); + return err; +} + +static int mptcp_stream_connect(struct socket *sock, struct sockaddr *uaddr, + int addr_len, int flags) +{ + struct mptcp_sock *msk = mptcp_sk(sock->sk); + struct socket *ssock; + int err; + + lock_sock(sock->sk); + ssock = __mptcp_socket_create(msk, TCP_SYN_SENT); + if (IS_ERR(ssock)) { + err = PTR_ERR(ssock); + goto unlock; + } + +#ifdef CONFIG_TCP_MD5SIG + /* no MPTCP if MD5SIG is enabled on this socket or we may run out of + * TCP option space. + */ + if (rcu_access_pointer(tcp_sk(ssock->sk)->md5sig_info)) + mptcp_subflow_ctx(ssock->sk)->request_mptcp = 0; +#endif + + err = ssock->ops->connect(ssock, uaddr, addr_len, flags); + inet_sk_state_store(sock->sk, inet_sk_state_load(ssock->sk)); + mptcp_copy_inaddrs(sock->sk, ssock->sk); + +unlock: + release_sock(sock->sk); + return err; +} + +static int mptcp_v4_getname(struct socket *sock, struct sockaddr *uaddr, + int peer) +{ + if (sock->sk->sk_prot == &tcp_prot) { + /* we are being invoked from __sys_accept4, after + * mptcp_accept() has just accepted a non-mp-capable + * flow: sk is a tcp_sk, not an mptcp one. + * + * Hand the socket over to tcp so all further socket ops + * bypass mptcp. + */ + sock->ops = &inet_stream_ops; + } + + return inet_getname(sock, uaddr, peer); +} + +#if IS_ENABLED(CONFIG_MPTCP_IPV6) +static int mptcp_v6_getname(struct socket *sock, struct sockaddr *uaddr, + int peer) +{ + if (sock->sk->sk_prot == &tcpv6_prot) { + /* we are being invoked from __sys_accept4 after + * mptcp_accept() has accepted a non-mp-capable + * subflow: sk is a tcp_sk, not mptcp. + * + * Hand the socket over to tcp so all further + * socket ops bypass mptcp. + */ + sock->ops = &inet6_stream_ops; + } + + return inet6_getname(sock, uaddr, peer); +} +#endif + +static int mptcp_listen(struct socket *sock, int backlog) +{ + struct mptcp_sock *msk = mptcp_sk(sock->sk); + struct socket *ssock; + int err; + + pr_debug("msk=%p", msk); + + lock_sock(sock->sk); + ssock = __mptcp_socket_create(msk, TCP_LISTEN); + if (IS_ERR(ssock)) { + err = PTR_ERR(ssock); + goto unlock; + } + + err = ssock->ops->listen(ssock, backlog); + inet_sk_state_store(sock->sk, inet_sk_state_load(ssock->sk)); + if (!err) + mptcp_copy_inaddrs(sock->sk, ssock->sk); + +unlock: + release_sock(sock->sk); + return err; +} + +static bool is_tcp_proto(const struct proto *p) +{ +#if IS_ENABLED(CONFIG_MPTCP_IPV6) + return p == &tcp_prot || p == &tcpv6_prot; +#else + return p == &tcp_prot; +#endif +} + +static int mptcp_stream_accept(struct socket *sock, struct socket *newsock, + int flags, bool kern) +{ + struct mptcp_sock *msk = mptcp_sk(sock->sk); + struct socket *ssock; + int err; + + pr_debug("msk=%p", msk); + + lock_sock(sock->sk); + if (sock->sk->sk_state != TCP_LISTEN) + goto unlock_fail; + + ssock = __mptcp_nmpc_socket(msk); + if (!ssock) + goto unlock_fail; + + sock_hold(ssock->sk); + release_sock(sock->sk); + + err = ssock->ops->accept(sock, newsock, flags, kern); + if (err == 0 && !is_tcp_proto(newsock->sk->sk_prot)) { + struct mptcp_sock *msk = mptcp_sk(newsock->sk); + struct mptcp_subflow_context *subflow; + + /* set ssk->sk_socket of accept()ed flows to mptcp socket. + * This is needed so NOSPACE flag can be set from tcp stack. + */ + list_for_each_entry(subflow, &msk->conn_list, node) { + struct sock *ssk = mptcp_subflow_tcp_sock(subflow); + + if (!ssk->sk_socket) + mptcp_sock_graft(ssk, newsock); + } + + inet_sk_state_store(newsock->sk, TCP_ESTABLISHED); + } + + sock_put(ssock->sk); + return err; + +unlock_fail: + release_sock(sock->sk); + return -EINVAL; +} + +static __poll_t mptcp_poll(struct file *file, struct socket *sock, + struct poll_table_struct *wait) +{ + struct sock *sk = sock->sk; + struct mptcp_sock *msk; + struct socket *ssock; + __poll_t mask = 0; + + msk = mptcp_sk(sk); + lock_sock(sk); + ssock = __mptcp_nmpc_socket(msk); + if (ssock) { + mask = ssock->ops->poll(file, ssock, wait); + release_sock(sk); + return mask; + } + + release_sock(sk); + sock_poll_wait(file, sock, wait); + lock_sock(sk); + ssock = __mptcp_tcp_fallback(msk); + if (unlikely(ssock)) + return ssock->ops->poll(file, ssock, NULL); + + if (test_bit(MPTCP_DATA_READY, &msk->flags)) + mask = EPOLLIN | EPOLLRDNORM; + if (sk_stream_is_writeable(sk) && + test_bit(MPTCP_SEND_SPACE, &msk->flags)) + mask |= EPOLLOUT | EPOLLWRNORM; + if (sk->sk_shutdown & RCV_SHUTDOWN) + mask |= EPOLLIN | EPOLLRDNORM | EPOLLRDHUP; + + release_sock(sk); + + return mask; +} + +static int mptcp_shutdown(struct socket *sock, int how) +{ + struct mptcp_sock *msk = mptcp_sk(sock->sk); + struct mptcp_subflow_context *subflow; + int ret = 0; + + pr_debug("sk=%p, how=%d", msk, how); + + lock_sock(sock->sk); + + if (how == SHUT_WR || how == SHUT_RDWR) + inet_sk_state_store(sock->sk, TCP_FIN_WAIT1); + + how++; + + if ((how & ~SHUTDOWN_MASK) || !how) { + ret = -EINVAL; + goto out_unlock; + } + + if (sock->state == SS_CONNECTING) { + if ((1 << sock->sk->sk_state) & + (TCPF_SYN_SENT | TCPF_SYN_RECV | TCPF_CLOSE)) + sock->state = SS_DISCONNECTING; + else + sock->state = SS_CONNECTED; + } + + mptcp_for_each_subflow(msk, subflow) { + struct sock *tcp_sk = mptcp_subflow_tcp_sock(subflow); + + mptcp_subflow_shutdown(tcp_sk, how); + } + +out_unlock: + release_sock(sock->sk); + + return ret; +} + +static const struct proto_ops mptcp_stream_ops = { + .family = PF_INET, + .owner = THIS_MODULE, + .release = inet_release, + .bind = mptcp_bind, + .connect = mptcp_stream_connect, + .socketpair = sock_no_socketpair, + .accept = mptcp_stream_accept, + .getname = mptcp_v4_getname, + .poll = mptcp_poll, + .ioctl = inet_ioctl, + .gettstamp = sock_gettstamp, + .listen = mptcp_listen, + .shutdown = mptcp_shutdown, + .setsockopt = sock_common_setsockopt, + .getsockopt = sock_common_getsockopt, + .sendmsg = inet_sendmsg, + .recvmsg = inet_recvmsg, + .mmap = sock_no_mmap, + .sendpage = inet_sendpage, +#ifdef CONFIG_COMPAT + .compat_setsockopt = compat_sock_common_setsockopt, + .compat_getsockopt = compat_sock_common_getsockopt, +#endif +}; + +static struct inet_protosw mptcp_protosw = { + .type = SOCK_STREAM, + .protocol = IPPROTO_MPTCP, + .prot = &mptcp_prot, + .ops = &mptcp_stream_ops, + .flags = INET_PROTOSW_ICSK, +}; + +void mptcp_proto_init(void) +{ + mptcp_prot.h.hashinfo = tcp_prot.h.hashinfo; + + mptcp_subflow_init(); + + if (proto_register(&mptcp_prot, 1) != 0) + panic("Failed to register MPTCP proto.\n"); + + inet_register_protosw(&mptcp_protosw); +} + +#if IS_ENABLED(CONFIG_MPTCP_IPV6) +static const struct proto_ops mptcp_v6_stream_ops = { + .family = PF_INET6, + .owner = THIS_MODULE, + .release = inet6_release, + .bind = mptcp_bind, + .connect = mptcp_stream_connect, + .socketpair = sock_no_socketpair, + .accept = mptcp_stream_accept, + .getname = mptcp_v6_getname, + .poll = mptcp_poll, + .ioctl = inet6_ioctl, + .gettstamp = sock_gettstamp, + .listen = mptcp_listen, + .shutdown = mptcp_shutdown, + .setsockopt = sock_common_setsockopt, + .getsockopt = sock_common_getsockopt, + .sendmsg = inet6_sendmsg, + .recvmsg = inet6_recvmsg, + .mmap = sock_no_mmap, + .sendpage = inet_sendpage, +#ifdef CONFIG_COMPAT + .compat_setsockopt = compat_sock_common_setsockopt, + .compat_getsockopt = compat_sock_common_getsockopt, +#endif +}; + +static struct proto mptcp_v6_prot; + +static void mptcp_v6_destroy(struct sock *sk) +{ + mptcp_destroy(sk); + inet6_destroy_sock(sk); +} + +static struct inet_protosw mptcp_v6_protosw = { + .type = SOCK_STREAM, + .protocol = IPPROTO_MPTCP, + .prot = &mptcp_v6_prot, + .ops = &mptcp_v6_stream_ops, + .flags = INET_PROTOSW_ICSK, +}; + +int mptcp_proto_v6_init(void) +{ + int err; + + mptcp_v6_prot = mptcp_prot; + strcpy(mptcp_v6_prot.name, "MPTCPv6"); + mptcp_v6_prot.slab = NULL; + mptcp_v6_prot.destroy = mptcp_v6_destroy; + mptcp_v6_prot.obj_size = sizeof(struct mptcp_sock) + + sizeof(struct ipv6_pinfo); + + err = proto_register(&mptcp_v6_prot, 1); + if (err) + return err; + + err = inet6_register_protosw(&mptcp_v6_protosw); + if (err) + proto_unregister(&mptcp_v6_prot); + + return err; +} +#endif diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h new file mode 100644 index 000000000000..8a99a2930284 --- /dev/null +++ b/net/mptcp/protocol.h @@ -0,0 +1,240 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Multipath TCP + * + * Copyright (c) 2017 - 2019, Intel Corporation. + */ + +#ifndef __MPTCP_PROTOCOL_H +#define __MPTCP_PROTOCOL_H + +#include <linux/random.h> +#include <net/tcp.h> +#include <net/inet_connection_sock.h> + +#define MPTCP_SUPPORTED_VERSION 1 + +/* MPTCP option bits */ +#define OPTION_MPTCP_MPC_SYN BIT(0) +#define OPTION_MPTCP_MPC_SYNACK BIT(1) +#define OPTION_MPTCP_MPC_ACK BIT(2) + +/* MPTCP option subtypes */ +#define MPTCPOPT_MP_CAPABLE 0 +#define MPTCPOPT_MP_JOIN 1 +#define MPTCPOPT_DSS 2 +#define MPTCPOPT_ADD_ADDR 3 +#define MPTCPOPT_RM_ADDR 4 +#define MPTCPOPT_MP_PRIO 5 +#define MPTCPOPT_MP_FAIL 6 +#define MPTCPOPT_MP_FASTCLOSE 7 + +/* MPTCP suboption lengths */ +#define TCPOLEN_MPTCP_MPC_SYN 4 +#define TCPOLEN_MPTCP_MPC_SYNACK 12 +#define TCPOLEN_MPTCP_MPC_ACK 20 +#define TCPOLEN_MPTCP_MPC_ACK_DATA 22 +#define TCPOLEN_MPTCP_DSS_BASE 4 +#define TCPOLEN_MPTCP_DSS_ACK32 4 +#define TCPOLEN_MPTCP_DSS_ACK64 8 +#define TCPOLEN_MPTCP_DSS_MAP32 10 +#define TCPOLEN_MPTCP_DSS_MAP64 14 +#define TCPOLEN_MPTCP_DSS_CHECKSUM 2 + +/* MPTCP MP_CAPABLE flags */ +#define MPTCP_VERSION_MASK (0x0F) +#define MPTCP_CAP_CHECKSUM_REQD BIT(7) +#define MPTCP_CAP_EXTENSIBILITY BIT(6) +#define MPTCP_CAP_HMAC_SHA256 BIT(0) +#define MPTCP_CAP_FLAG_MASK (0x3F) + +/* MPTCP DSS flags */ +#define MPTCP_DSS_DATA_FIN BIT(4) +#define MPTCP_DSS_DSN64 BIT(3) +#define MPTCP_DSS_HAS_MAP BIT(2) +#define MPTCP_DSS_ACK64 BIT(1) +#define MPTCP_DSS_HAS_ACK BIT(0) +#define MPTCP_DSS_FLAG_MASK (0x1F) + +/* MPTCP socket flags */ +#define MPTCP_DATA_READY BIT(0) +#define MPTCP_SEND_SPACE BIT(1) + +/* MPTCP connection sock */ +struct mptcp_sock { + /* inet_connection_sock must be the first member */ + struct inet_connection_sock sk; + u64 local_key; + u64 remote_key; + u64 write_seq; + u64 ack_seq; + u32 token; + unsigned long flags; + bool can_ack; + struct list_head conn_list; + struct skb_ext *cached_ext; /* for the next sendmsg */ + struct socket *subflow; /* outgoing connect/listener/!mp_capable */ + struct sock *first; +}; + +#define mptcp_for_each_subflow(__msk, __subflow) \ + list_for_each_entry(__subflow, &((__msk)->conn_list), node) + +static inline struct mptcp_sock *mptcp_sk(const struct sock *sk) +{ + return (struct mptcp_sock *)sk; +} + +struct mptcp_subflow_request_sock { + struct tcp_request_sock sk; + u16 mp_capable : 1, + mp_join : 1, + backup : 1, + remote_key_valid : 1; + u64 local_key; + u64 remote_key; + u64 idsn; + u32 token; + u32 ssn_offset; +}; + +static inline struct mptcp_subflow_request_sock * +mptcp_subflow_rsk(const struct request_sock *rsk) +{ + return (struct mptcp_subflow_request_sock *)rsk; +} + +/* MPTCP subflow context */ +struct mptcp_subflow_context { + struct list_head node;/* conn_list of subflows */ + u64 local_key; + u64 remote_key; + u64 idsn; + u64 map_seq; + u32 snd_isn; + u32 token; + u32 rel_write_seq; + u32 map_subflow_seq; + u32 ssn_offset; + u32 map_data_len; + u32 request_mptcp : 1, /* send MP_CAPABLE */ + mp_capable : 1, /* remote is MPTCP capable */ + fourth_ack : 1, /* send initial DSS */ + conn_finished : 1, + map_valid : 1, + mpc_map : 1, + data_avail : 1, + rx_eof : 1, + can_ack : 1; /* only after processing the remote a key */ + + struct sock *tcp_sock; /* tcp sk backpointer */ + struct sock *conn; /* parent mptcp_sock */ + const struct inet_connection_sock_af_ops *icsk_af_ops; + void (*tcp_data_ready)(struct sock *sk); + void (*tcp_state_change)(struct sock *sk); + void (*tcp_write_space)(struct sock *sk); + + struct rcu_head rcu; +}; + +static inline struct mptcp_subflow_context * +mptcp_subflow_ctx(const struct sock *sk) +{ + struct inet_connection_sock *icsk = inet_csk(sk); + + /* Use RCU on icsk_ulp_data only for sock diag code */ + return (__force struct mptcp_subflow_context *)icsk->icsk_ulp_data; +} + +static inline struct sock * +mptcp_subflow_tcp_sock(const struct mptcp_subflow_context *subflow) +{ + return subflow->tcp_sock; +} + +static inline u64 +mptcp_subflow_get_map_offset(const struct mptcp_subflow_context *subflow) +{ + return tcp_sk(mptcp_subflow_tcp_sock(subflow))->copied_seq - + subflow->ssn_offset - + subflow->map_subflow_seq; +} + +static inline u64 +mptcp_subflow_get_mapped_dsn(const struct mptcp_subflow_context *subflow) +{ + return subflow->map_seq + mptcp_subflow_get_map_offset(subflow); +} + +int mptcp_is_enabled(struct net *net); +bool mptcp_subflow_data_available(struct sock *sk); +void mptcp_subflow_init(void); +int mptcp_subflow_create_socket(struct sock *sk, struct socket **new_sock); + +static inline void mptcp_subflow_tcp_fallback(struct sock *sk, + struct mptcp_subflow_context *ctx) +{ + sk->sk_data_ready = ctx->tcp_data_ready; + sk->sk_state_change = ctx->tcp_state_change; + sk->sk_write_space = ctx->tcp_write_space; + + inet_csk(sk)->icsk_af_ops = ctx->icsk_af_ops; +} + +extern const struct inet_connection_sock_af_ops ipv4_specific; +#if IS_ENABLED(CONFIG_MPTCP_IPV6) +extern const struct inet_connection_sock_af_ops ipv6_specific; +#endif + +void mptcp_proto_init(void); +#if IS_ENABLED(CONFIG_MPTCP_IPV6) +int mptcp_proto_v6_init(void); +#endif + +struct mptcp_read_arg { + struct msghdr *msg; +}; + +int mptcp_read_actor(read_descriptor_t *desc, struct sk_buff *skb, + unsigned int offset, size_t len); + +void mptcp_get_options(const struct sk_buff *skb, + struct tcp_options_received *opt_rx); + +void mptcp_finish_connect(struct sock *sk); + +int mptcp_token_new_request(struct request_sock *req); +void mptcp_token_destroy_request(u32 token); +int mptcp_token_new_connect(struct sock *sk); +int mptcp_token_new_accept(u32 token); +void mptcp_token_update_accept(struct sock *sk, struct sock *conn); +void mptcp_token_destroy(u32 token); + +void mptcp_crypto_key_sha(u64 key, u32 *token, u64 *idsn); +static inline void mptcp_crypto_key_gen_sha(u64 *key, u32 *token, u64 *idsn) +{ + /* we might consider a faster version that computes the key as a + * hash of some information available in the MPTCP socket. Use + * random data at the moment, as it's probably the safest option + * in case multiple sockets are opened in different namespaces at + * the same time. + */ + get_random_bytes(key, sizeof(u64)); + mptcp_crypto_key_sha(*key, token, idsn); +} + +void mptcp_crypto_hmac_sha(u64 key1, u64 key2, u32 nonce1, u32 nonce2, + void *hash_out); + +static inline struct mptcp_ext *mptcp_get_ext(struct sk_buff *skb) +{ + return (struct mptcp_ext *)skb_ext_find(skb, SKB_EXT_MPTCP); +} + +static inline bool before64(__u64 seq1, __u64 seq2) +{ + return (__s64)(seq1 - seq2) < 0; +} + +#define after64(seq2, seq1) before64(seq1, seq2) + +#endif /* __MPTCP_PROTOCOL_H */ diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c new file mode 100644 index 000000000000..1662e1178949 --- /dev/null +++ b/net/mptcp/subflow.c @@ -0,0 +1,860 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Multipath TCP + * + * Copyright (c) 2017 - 2019, Intel Corporation. + */ + +#define pr_fmt(fmt) "MPTCP: " fmt + +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/netdevice.h> +#include <net/sock.h> +#include <net/inet_common.h> +#include <net/inet_hashtables.h> +#include <net/protocol.h> +#include <net/tcp.h> +#if IS_ENABLED(CONFIG_MPTCP_IPV6) +#include <net/ip6_route.h> +#endif +#include <net/mptcp.h> +#include "protocol.h" + +static int subflow_rebuild_header(struct sock *sk) +{ + struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk); + int err = 0; + + if (subflow->request_mptcp && !subflow->token) { + pr_debug("subflow=%p", sk); + err = mptcp_token_new_connect(sk); + } + + if (err) + return err; + + return subflow->icsk_af_ops->rebuild_header(sk); +} + +static void subflow_req_destructor(struct request_sock *req) +{ + struct mptcp_subflow_request_sock *subflow_req = mptcp_subflow_rsk(req); + + pr_debug("subflow_req=%p", subflow_req); + + if (subflow_req->mp_capable) + mptcp_token_destroy_request(subflow_req->token); + tcp_request_sock_ops.destructor(req); +} + +static void subflow_init_req(struct request_sock *req, + const struct sock *sk_listener, + struct sk_buff *skb) +{ + struct mptcp_subflow_context *listener = mptcp_subflow_ctx(sk_listener); + struct mptcp_subflow_request_sock *subflow_req = mptcp_subflow_rsk(req); + struct tcp_options_received rx_opt; + + pr_debug("subflow_req=%p, listener=%p", subflow_req, listener); + + memset(&rx_opt.mptcp, 0, sizeof(rx_opt.mptcp)); + mptcp_get_options(skb, &rx_opt); + + subflow_req->mp_capable = 0; + subflow_req->remote_key_valid = 0; + +#ifdef CONFIG_TCP_MD5SIG + /* no MPTCP if MD5SIG is enabled on this socket or we may run out of + * TCP option space. + */ + if (rcu_access_pointer(tcp_sk(sk_listener)->md5sig_info)) + return; +#endif + + if (rx_opt.mptcp.mp_capable && listener->request_mptcp) { + int err; + + err = mptcp_token_new_request(req); + if (err == 0) + subflow_req->mp_capable = 1; + + subflow_req->ssn_offset = TCP_SKB_CB(skb)->seq; + } +} + +static void subflow_v4_init_req(struct request_sock *req, + const struct sock *sk_listener, + struct sk_buff *skb) +{ + tcp_rsk(req)->is_mptcp = 1; + + tcp_request_sock_ipv4_ops.init_req(req, sk_listener, skb); + + subflow_init_req(req, sk_listener, skb); +} + +#if IS_ENABLED(CONFIG_MPTCP_IPV6) +static void subflow_v6_init_req(struct request_sock *req, + const struct sock *sk_listener, + struct sk_buff *skb) +{ + tcp_rsk(req)->is_mptcp = 1; + + tcp_request_sock_ipv6_ops.init_req(req, sk_listener, skb); + + subflow_init_req(req, sk_listener, skb); +} +#endif + +static void subflow_finish_connect(struct sock *sk, const struct sk_buff *skb) +{ + struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk); + + subflow->icsk_af_ops->sk_rx_dst_set(sk, skb); + + if (subflow->conn && !subflow->conn_finished) { + pr_debug("subflow=%p, remote_key=%llu", mptcp_subflow_ctx(sk), + subflow->remote_key); + mptcp_finish_connect(sk); + subflow->conn_finished = 1; + + if (skb) { + pr_debug("synack seq=%u", TCP_SKB_CB(skb)->seq); + subflow->ssn_offset = TCP_SKB_CB(skb)->seq; + } + } +} + +static struct request_sock_ops subflow_request_sock_ops; +static struct tcp_request_sock_ops subflow_request_sock_ipv4_ops; + +static int subflow_v4_conn_request(struct sock *sk, struct sk_buff *skb) +{ + struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk); + + pr_debug("subflow=%p", subflow); + + /* Never answer to SYNs sent to broadcast or multicast */ + if (skb_rtable(skb)->rt_flags & (RTCF_BROADCAST | RTCF_MULTICAST)) + goto drop; + + return tcp_conn_request(&subflow_request_sock_ops, + &subflow_request_sock_ipv4_ops, + sk, skb); +drop: + tcp_listendrop(sk); + return 0; +} + +#if IS_ENABLED(CONFIG_MPTCP_IPV6) +static struct tcp_request_sock_ops subflow_request_sock_ipv6_ops; +static struct inet_connection_sock_af_ops subflow_v6_specific; +static struct inet_connection_sock_af_ops subflow_v6m_specific; + +static int subflow_v6_conn_request(struct sock *sk, struct sk_buff *skb) +{ + struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk); + + pr_debug("subflow=%p", subflow); + + if (skb->protocol == htons(ETH_P_IP)) + return subflow_v4_conn_request(sk, skb); + + if (!ipv6_unicast_destination(skb)) + goto drop; + + return tcp_conn_request(&subflow_request_sock_ops, + &subflow_request_sock_ipv6_ops, sk, skb); + +drop: + tcp_listendrop(sk); + return 0; /* don't send reset */ +} +#endif + +static struct sock *subflow_syn_recv_sock(const struct sock *sk, + struct sk_buff *skb, + struct request_sock *req, + struct dst_entry *dst, + struct request_sock *req_unhash, + bool *own_req) +{ + struct mptcp_subflow_context *listener = mptcp_subflow_ctx(sk); + struct mptcp_subflow_request_sock *subflow_req; + struct tcp_options_received opt_rx; + struct sock *child; + + pr_debug("listener=%p, req=%p, conn=%p", listener, req, listener->conn); + + /* if the sk is MP_CAPABLE, we try to fetch the client key */ + subflow_req = mptcp_subflow_rsk(req); + if (subflow_req->mp_capable) { + if (TCP_SKB_CB(skb)->seq != subflow_req->ssn_offset + 1) { + /* here we can receive and accept an in-window, + * out-of-order pkt, which will not carry the MP_CAPABLE + * opt even on mptcp enabled paths + */ + goto create_child; + } + + opt_rx.mptcp.mp_capable = 0; + mptcp_get_options(skb, &opt_rx); + if (opt_rx.mptcp.mp_capable) { + subflow_req->remote_key = opt_rx.mptcp.sndr_key; + subflow_req->remote_key_valid = 1; + } else { + subflow_req->mp_capable = 0; + } + } + +create_child: + child = listener->icsk_af_ops->syn_recv_sock(sk, skb, req, dst, + req_unhash, own_req); + + if (child && *own_req) { + struct mptcp_subflow_context *ctx = mptcp_subflow_ctx(child); + + /* we have null ctx on TCP fallback, not fatal on MPC + * handshake + */ + if (!ctx) + return child; + + if (ctx->mp_capable) { + if (mptcp_token_new_accept(ctx->token)) + goto close_child; + } + } + + return child; + +close_child: + pr_debug("closing child socket"); + tcp_send_active_reset(child, GFP_ATOMIC); + inet_csk_prepare_forced_close(child); + tcp_done(child); + return NULL; +} + +static struct inet_connection_sock_af_ops subflow_specific; + +enum mapping_status { + MAPPING_OK, + MAPPING_INVALID, + MAPPING_EMPTY, + MAPPING_DATA_FIN +}; + +static u64 expand_seq(u64 old_seq, u16 old_data_len, u64 seq) +{ + if ((u32)seq == (u32)old_seq) + return old_seq; + + /* Assume map covers data not mapped yet. */ + return seq | ((old_seq + old_data_len + 1) & GENMASK_ULL(63, 32)); +} + +static void warn_bad_map(struct mptcp_subflow_context *subflow, u32 ssn) +{ + WARN_ONCE(1, "Bad mapping: ssn=%d map_seq=%d map_data_len=%d", + ssn, subflow->map_subflow_seq, subflow->map_data_len); +} + +static bool skb_is_fully_mapped(struct sock *ssk, struct sk_buff *skb) +{ + struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk); + unsigned int skb_consumed; + + skb_consumed = tcp_sk(ssk)->copied_seq - TCP_SKB_CB(skb)->seq; + if (WARN_ON_ONCE(skb_consumed >= skb->len)) + return true; + + return skb->len - skb_consumed <= subflow->map_data_len - + mptcp_subflow_get_map_offset(subflow); +} + +static bool validate_mapping(struct sock *ssk, struct sk_buff *skb) +{ + struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk); + u32 ssn = tcp_sk(ssk)->copied_seq - subflow->ssn_offset; + + if (unlikely(before(ssn, subflow->map_subflow_seq))) { + /* Mapping covers data later in the subflow stream, + * currently unsupported. + */ + warn_bad_map(subflow, ssn); + return false; + } + if (unlikely(!before(ssn, subflow->map_subflow_seq + + subflow->map_data_len))) { + /* Mapping does covers past subflow data, invalid */ + warn_bad_map(subflow, ssn + skb->len); + return false; + } + return true; +} + +static enum mapping_status get_mapping_status(struct sock *ssk) +{ + struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk); + struct mptcp_ext *mpext; + struct sk_buff *skb; + u16 data_len; + u64 map_seq; + + skb = skb_peek(&ssk->sk_receive_queue); + if (!skb) + return MAPPING_EMPTY; + + mpext = mptcp_get_ext(skb); + if (!mpext || !mpext->use_map) { + if (!subflow->map_valid && !skb->len) { + /* the TCP stack deliver 0 len FIN pkt to the receive + * queue, that is the only 0len pkts ever expected here, + * and we can admit no mapping only for 0 len pkts + */ + if (!(TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN)) + WARN_ONCE(1, "0len seq %d:%d flags %x", + TCP_SKB_CB(skb)->seq, + TCP_SKB_CB(skb)->end_seq, + TCP_SKB_CB(skb)->tcp_flags); + sk_eat_skb(ssk, skb); + return MAPPING_EMPTY; + } + + if (!subflow->map_valid) + return MAPPING_INVALID; + + goto validate_seq; + } + + pr_debug("seq=%llu is64=%d ssn=%u data_len=%u data_fin=%d", + mpext->data_seq, mpext->dsn64, mpext->subflow_seq, + mpext->data_len, mpext->data_fin); + + data_len = mpext->data_len; + if (data_len == 0) { + pr_err("Infinite mapping not handled"); + return MAPPING_INVALID; + } + + if (mpext->data_fin == 1) { + if (data_len == 1) { + pr_debug("DATA_FIN with no payload"); + if (subflow->map_valid) { + /* A DATA_FIN might arrive in a DSS + * option before the previous mapping + * has been fully consumed. Continue + * handling the existing mapping. + */ + skb_ext_del(skb, SKB_EXT_MPTCP); + return MAPPING_OK; + } else { + return MAPPING_DATA_FIN; + } + } + + /* Adjust for DATA_FIN using 1 byte of sequence space */ + data_len--; + } + + if (!mpext->dsn64) { + map_seq = expand_seq(subflow->map_seq, subflow->map_data_len, + mpext->data_seq); + pr_debug("expanded seq=%llu", subflow->map_seq); + } else { + map_seq = mpext->data_seq; + } + + if (subflow->map_valid) { + /* Allow replacing only with an identical map */ + if (subflow->map_seq == map_seq && + subflow->map_subflow_seq == mpext->subflow_seq && + subflow->map_data_len == data_len) { + skb_ext_del(skb, SKB_EXT_MPTCP); + return MAPPING_OK; + } + + /* If this skb data are fully covered by the current mapping, + * the new map would need caching, which is not supported + */ + if (skb_is_fully_mapped(ssk, skb)) + return MAPPING_INVALID; + + /* will validate the next map after consuming the current one */ + return MAPPING_OK; + } + + subflow->map_seq = map_seq; + subflow->map_subflow_seq = mpext->subflow_seq; + subflow->map_data_len = data_len; + subflow->map_valid = 1; + subflow->mpc_map = mpext->mpc_map; + pr_debug("new map seq=%llu subflow_seq=%u data_len=%u", + subflow->map_seq, subflow->map_subflow_seq, + subflow->map_data_len); + +validate_seq: + /* we revalidate valid mapping on new skb, because we must ensure + * the current skb is completely covered by the available mapping + */ + if (!validate_mapping(ssk, skb)) + return MAPPING_INVALID; + + skb_ext_del(skb, SKB_EXT_MPTCP); + return MAPPING_OK; +} + +static bool subflow_check_data_avail(struct sock *ssk) +{ + struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk); + enum mapping_status status; + struct mptcp_sock *msk; + struct sk_buff *skb; + + pr_debug("msk=%p ssk=%p data_avail=%d skb=%p", subflow->conn, ssk, + subflow->data_avail, skb_peek(&ssk->sk_receive_queue)); + if (subflow->data_avail) + return true; + + if (!subflow->conn) + return false; + + msk = mptcp_sk(subflow->conn); + for (;;) { + u32 map_remaining; + size_t delta; + u64 ack_seq; + u64 old_ack; + + status = get_mapping_status(ssk); + pr_debug("msk=%p ssk=%p status=%d", msk, ssk, status); + if (status == MAPPING_INVALID) { + ssk->sk_err = EBADMSG; + goto fatal; + } + + if (status != MAPPING_OK) + return false; + + skb = skb_peek(&ssk->sk_receive_queue); + if (WARN_ON_ONCE(!skb)) + return false; + + /* if msk lacks the remote key, this subflow must provide an + * MP_CAPABLE-based mapping + */ + if (unlikely(!READ_ONCE(msk->can_ack))) { + if (!subflow->mpc_map) { + ssk->sk_err = EBADMSG; + goto fatal; + } + WRITE_ONCE(msk->remote_key, subflow->remote_key); + WRITE_ONCE(msk->ack_seq, subflow->map_seq); + WRITE_ONCE(msk->can_ack, true); + } + + old_ack = READ_ONCE(msk->ack_seq); + ack_seq = mptcp_subflow_get_mapped_dsn(subflow); + pr_debug("msk ack_seq=%llx subflow ack_seq=%llx", old_ack, + ack_seq); + if (ack_seq == old_ack) + break; + + /* only accept in-sequence mapping. Old values are spurious + * retransmission; we can hit "future" values on active backup + * subflow switch, we relay on retransmissions to get + * in-sequence data. + * Cuncurrent subflows support will require subflow data + * reordering + */ + map_remaining = subflow->map_data_len - + mptcp_subflow_get_map_offset(subflow); + if (before64(ack_seq, old_ack)) + delta = min_t(size_t, old_ack - ack_seq, map_remaining); + else + delta = min_t(size_t, ack_seq - old_ack, map_remaining); + + /* discard mapped data */ + pr_debug("discarding %zu bytes, current map len=%d", delta, + map_remaining); + if (delta) { + struct mptcp_read_arg arg = { + .msg = NULL, + }; + read_descriptor_t desc = { + .count = delta, + .arg.data = &arg, + }; + int ret; + + ret = tcp_read_sock(ssk, &desc, mptcp_read_actor); + if (ret < 0) { + ssk->sk_err = -ret; + goto fatal; + } + if (ret < delta) + return false; + if (delta == map_remaining) + subflow->map_valid = 0; + } + } + return true; + +fatal: + /* fatal protocol error, close the socket */ + /* This barrier is coupled with smp_rmb() in tcp_poll() */ + smp_wmb(); + ssk->sk_error_report(ssk); + tcp_set_state(ssk, TCP_CLOSE); + tcp_send_active_reset(ssk, GFP_ATOMIC); + return false; +} + +bool mptcp_subflow_data_available(struct sock *sk) +{ + struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk); + struct sk_buff *skb; + + /* check if current mapping is still valid */ + if (subflow->map_valid && + mptcp_subflow_get_map_offset(subflow) >= subflow->map_data_len) { + subflow->map_valid = 0; + subflow->data_avail = 0; + + pr_debug("Done with mapping: seq=%u data_len=%u", + subflow->map_subflow_seq, + subflow->map_data_len); + } + + if (!subflow_check_data_avail(sk)) { + subflow->data_avail = 0; + return false; + } + + skb = skb_peek(&sk->sk_receive_queue); + subflow->data_avail = skb && + before(tcp_sk(sk)->copied_seq, TCP_SKB_CB(skb)->end_seq); + return subflow->data_avail; +} + +static void subflow_data_ready(struct sock *sk) +{ + struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk); + struct sock *parent = subflow->conn; + + if (!parent || !subflow->mp_capable) { + subflow->tcp_data_ready(sk); + + if (parent) + parent->sk_data_ready(parent); + return; + } + + if (mptcp_subflow_data_available(sk)) { + set_bit(MPTCP_DATA_READY, &mptcp_sk(parent)->flags); + + parent->sk_data_ready(parent); + } +} + +static void subflow_write_space(struct sock *sk) +{ + struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk); + struct sock *parent = subflow->conn; + + sk_stream_write_space(sk); + if (parent && sk_stream_is_writeable(sk)) { + set_bit(MPTCP_SEND_SPACE, &mptcp_sk(parent)->flags); + smp_mb__after_atomic(); + /* set SEND_SPACE before sk_stream_write_space clears NOSPACE */ + sk_stream_write_space(parent); + } +} + +static struct inet_connection_sock_af_ops * +subflow_default_af_ops(struct sock *sk) +{ +#if IS_ENABLED(CONFIG_MPTCP_IPV6) + if (sk->sk_family == AF_INET6) + return &subflow_v6_specific; +#endif + return &subflow_specific; +} + +void mptcp_handle_ipv6_mapped(struct sock *sk, bool mapped) +{ +#if IS_ENABLED(CONFIG_MPTCP_IPV6) + struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk); + struct inet_connection_sock *icsk = inet_csk(sk); + struct inet_connection_sock_af_ops *target; + + target = mapped ? &subflow_v6m_specific : subflow_default_af_ops(sk); + + pr_debug("subflow=%p family=%d ops=%p target=%p mapped=%d", + subflow, sk->sk_family, icsk->icsk_af_ops, target, mapped); + + if (likely(icsk->icsk_af_ops == target)) + return; + + subflow->icsk_af_ops = icsk->icsk_af_ops; + icsk->icsk_af_ops = target; +#endif +} + +int mptcp_subflow_create_socket(struct sock *sk, struct socket **new_sock) +{ + struct mptcp_subflow_context *subflow; + struct net *net = sock_net(sk); + struct socket *sf; + int err; + + err = sock_create_kern(net, sk->sk_family, SOCK_STREAM, IPPROTO_TCP, + &sf); + if (err) + return err; + + lock_sock(sf->sk); + + /* kernel sockets do not by default acquire net ref, but TCP timer + * needs it. + */ + sf->sk->sk_net_refcnt = 1; + get_net(net); + this_cpu_add(*net->core.sock_inuse, 1); + err = tcp_set_ulp(sf->sk, "mptcp"); + release_sock(sf->sk); + + if (err) + return err; + + subflow = mptcp_subflow_ctx(sf->sk); + pr_debug("subflow=%p", subflow); + + *new_sock = sf; + sock_hold(sk); + subflow->conn = sk; + + return 0; +} + +static struct mptcp_subflow_context *subflow_create_ctx(struct sock *sk, + gfp_t priority) +{ + struct inet_connection_sock *icsk = inet_csk(sk); + struct mptcp_subflow_context *ctx; + + ctx = kzalloc(sizeof(*ctx), priority); + if (!ctx) + return NULL; + + rcu_assign_pointer(icsk->icsk_ulp_data, ctx); + INIT_LIST_HEAD(&ctx->node); + + pr_debug("subflow=%p", ctx); + + ctx->tcp_sock = sk; + + return ctx; +} + +static void __subflow_state_change(struct sock *sk) +{ + struct socket_wq *wq; + + rcu_read_lock(); + wq = rcu_dereference(sk->sk_wq); + if (skwq_has_sleeper(wq)) + wake_up_interruptible_all(&wq->wait); + rcu_read_unlock(); +} + +static bool subflow_is_done(const struct sock *sk) +{ + return sk->sk_shutdown & RCV_SHUTDOWN || sk->sk_state == TCP_CLOSE; +} + +static void subflow_state_change(struct sock *sk) +{ + struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk); + struct sock *parent = READ_ONCE(subflow->conn); + + __subflow_state_change(sk); + + /* as recvmsg() does not acquire the subflow socket for ssk selection + * a fin packet carrying a DSS can be unnoticed if we don't trigger + * the data available machinery here. + */ + if (parent && subflow->mp_capable && mptcp_subflow_data_available(sk)) { + set_bit(MPTCP_DATA_READY, &mptcp_sk(parent)->flags); + + parent->sk_data_ready(parent); + } + + if (parent && !(parent->sk_shutdown & RCV_SHUTDOWN) && + !subflow->rx_eof && subflow_is_done(sk)) { + subflow->rx_eof = 1; + parent->sk_shutdown |= RCV_SHUTDOWN; + __subflow_state_change(parent); + } +} + +static int subflow_ulp_init(struct sock *sk) +{ + struct inet_connection_sock *icsk = inet_csk(sk); + struct mptcp_subflow_context *ctx; + struct tcp_sock *tp = tcp_sk(sk); + int err = 0; + + /* disallow attaching ULP to a socket unless it has been + * created with sock_create_kern() + */ + if (!sk->sk_kern_sock) { + err = -EOPNOTSUPP; + goto out; + } + + ctx = subflow_create_ctx(sk, GFP_KERNEL); + if (!ctx) { + err = -ENOMEM; + goto out; + } + + pr_debug("subflow=%p, family=%d", ctx, sk->sk_family); + + tp->is_mptcp = 1; + ctx->icsk_af_ops = icsk->icsk_af_ops; + icsk->icsk_af_ops = subflow_default_af_ops(sk); + ctx->tcp_data_ready = sk->sk_data_ready; + ctx->tcp_state_change = sk->sk_state_change; + ctx->tcp_write_space = sk->sk_write_space; + sk->sk_data_ready = subflow_data_ready; + sk->sk_write_space = subflow_write_space; + sk->sk_state_change = subflow_state_change; +out: + return err; +} + +static void subflow_ulp_release(struct sock *sk) +{ + struct mptcp_subflow_context *ctx = mptcp_subflow_ctx(sk); + + if (!ctx) + return; + + if (ctx->conn) + sock_put(ctx->conn); + + kfree_rcu(ctx, rcu); +} + +static void subflow_ulp_fallback(struct sock *sk, + struct mptcp_subflow_context *old_ctx) +{ + struct inet_connection_sock *icsk = inet_csk(sk); + + mptcp_subflow_tcp_fallback(sk, old_ctx); + icsk->icsk_ulp_ops = NULL; + rcu_assign_pointer(icsk->icsk_ulp_data, NULL); + tcp_sk(sk)->is_mptcp = 0; +} + +static void subflow_ulp_clone(const struct request_sock *req, + struct sock *newsk, + const gfp_t priority) +{ + struct mptcp_subflow_request_sock *subflow_req = mptcp_subflow_rsk(req); + struct mptcp_subflow_context *old_ctx = mptcp_subflow_ctx(newsk); + struct mptcp_subflow_context *new_ctx; + + if (!subflow_req->mp_capable) { + subflow_ulp_fallback(newsk, old_ctx); + return; + } + + new_ctx = subflow_create_ctx(newsk, priority); + if (!new_ctx) { + subflow_ulp_fallback(newsk, old_ctx); + return; + } + + /* see comments in subflow_syn_recv_sock(), MPTCP connection is fully + * established only after we receive the remote key + */ + new_ctx->conn_finished = 1; + new_ctx->icsk_af_ops = old_ctx->icsk_af_ops; + new_ctx->tcp_data_ready = old_ctx->tcp_data_ready; + new_ctx->tcp_state_change = old_ctx->tcp_state_change; + new_ctx->tcp_write_space = old_ctx->tcp_write_space; + new_ctx->mp_capable = 1; + new_ctx->fourth_ack = subflow_req->remote_key_valid; + new_ctx->can_ack = subflow_req->remote_key_valid; + new_ctx->remote_key = subflow_req->remote_key; + new_ctx->local_key = subflow_req->local_key; + new_ctx->token = subflow_req->token; + new_ctx->ssn_offset = subflow_req->ssn_offset; + new_ctx->idsn = subflow_req->idsn; +} + +static struct tcp_ulp_ops subflow_ulp_ops __read_mostly = { + .name = "mptcp", + .owner = THIS_MODULE, + .init = subflow_ulp_init, + .release = subflow_ulp_release, + .clone = subflow_ulp_clone, +}; + +static int subflow_ops_init(struct request_sock_ops *subflow_ops) +{ + subflow_ops->obj_size = sizeof(struct mptcp_subflow_request_sock); + subflow_ops->slab_name = "request_sock_subflow"; + + subflow_ops->slab = kmem_cache_create(subflow_ops->slab_name, + subflow_ops->obj_size, 0, + SLAB_ACCOUNT | + SLAB_TYPESAFE_BY_RCU, + NULL); + if (!subflow_ops->slab) + return -ENOMEM; + + subflow_ops->destructor = subflow_req_destructor; + + return 0; +} + +void mptcp_subflow_init(void) +{ + subflow_request_sock_ops = tcp_request_sock_ops; + if (subflow_ops_init(&subflow_request_sock_ops) != 0) + panic("MPTCP: failed to init subflow request sock ops\n"); + + subflow_request_sock_ipv4_ops = tcp_request_sock_ipv4_ops; + subflow_request_sock_ipv4_ops.init_req = subflow_v4_init_req; + + subflow_specific = ipv4_specific; + subflow_specific.conn_request = subflow_v4_conn_request; + subflow_specific.syn_recv_sock = subflow_syn_recv_sock; + subflow_specific.sk_rx_dst_set = subflow_finish_connect; + subflow_specific.rebuild_header = subflow_rebuild_header; + +#if IS_ENABLED(CONFIG_MPTCP_IPV6) + subflow_request_sock_ipv6_ops = tcp_request_sock_ipv6_ops; + subflow_request_sock_ipv6_ops.init_req = subflow_v6_init_req; + + subflow_v6_specific = ipv6_specific; + subflow_v6_specific.conn_request = subflow_v6_conn_request; + subflow_v6_specific.syn_recv_sock = subflow_syn_recv_sock; + subflow_v6_specific.sk_rx_dst_set = subflow_finish_connect; + subflow_v6_specific.rebuild_header = subflow_rebuild_header; + + subflow_v6m_specific = subflow_v6_specific; + subflow_v6m_specific.queue_xmit = ipv4_specific.queue_xmit; + subflow_v6m_specific.send_check = ipv4_specific.send_check; + subflow_v6m_specific.net_header_len = ipv4_specific.net_header_len; + subflow_v6m_specific.mtu_reduced = ipv4_specific.mtu_reduced; + subflow_v6m_specific.net_frag_header_len = 0; +#endif + + if (tcp_register_ulp(&subflow_ulp_ops) != 0) + panic("MPTCP: failed to register subflows to ULP\n"); +} diff --git a/net/mptcp/token.c b/net/mptcp/token.c new file mode 100644 index 000000000000..84d887806090 --- /dev/null +++ b/net/mptcp/token.c @@ -0,0 +1,195 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Multipath TCP token management + * Copyright (c) 2017 - 2019, Intel Corporation. + * + * Note: This code is based on mptcp_ctrl.c from multipath-tcp.org, + * authored by: + * + * Sébastien Barré <sebastien.barre@uclouvain.be> + * Christoph Paasch <christoph.paasch@uclouvain.be> + * Jaakko Korkeaniemi <jaakko.korkeaniemi@aalto.fi> + * Gregory Detal <gregory.detal@uclouvain.be> + * Fabien Duchêne <fabien.duchene@uclouvain.be> + * Andreas Seelinger <Andreas.Seelinger@rwth-aachen.de> + * Lavkesh Lahngir <lavkesh51@gmail.com> + * Andreas Ripke <ripke@neclab.eu> + * Vlad Dogaru <vlad.dogaru@intel.com> + * Octavian Purdila <octavian.purdila@intel.com> + * John Ronan <jronan@tssg.org> + * Catalin Nicutar <catalin.nicutar@gmail.com> + * Brandon Heller <brandonh@stanford.edu> + */ + +#define pr_fmt(fmt) "MPTCP: " fmt + +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/radix-tree.h> +#include <linux/ip.h> +#include <linux/tcp.h> +#include <net/sock.h> +#include <net/inet_common.h> +#include <net/protocol.h> +#include <net/mptcp.h> +#include "protocol.h" + +static RADIX_TREE(token_tree, GFP_ATOMIC); +static RADIX_TREE(token_req_tree, GFP_ATOMIC); +static DEFINE_SPINLOCK(token_tree_lock); +static int token_used __read_mostly; + +/** + * mptcp_token_new_request - create new key/idsn/token for subflow_request + * @req - the request socket + * + * This function is called when a new mptcp connection is coming in. + * + * It creates a unique token to identify the new mptcp connection, + * a secret local key and the initial data sequence number (idsn). + * + * Returns 0 on success. + */ +int mptcp_token_new_request(struct request_sock *req) +{ + struct mptcp_subflow_request_sock *subflow_req = mptcp_subflow_rsk(req); + int err; + + while (1) { + u32 token; + + mptcp_crypto_key_gen_sha(&subflow_req->local_key, + &subflow_req->token, + &subflow_req->idsn); + pr_debug("req=%p local_key=%llu, token=%u, idsn=%llu\n", + req, subflow_req->local_key, subflow_req->token, + subflow_req->idsn); + + token = subflow_req->token; + spin_lock_bh(&token_tree_lock); + if (!radix_tree_lookup(&token_req_tree, token) && + !radix_tree_lookup(&token_tree, token)) + break; + spin_unlock_bh(&token_tree_lock); + } + + err = radix_tree_insert(&token_req_tree, + subflow_req->token, &token_used); + spin_unlock_bh(&token_tree_lock); + return err; +} + +/** + * mptcp_token_new_connect - create new key/idsn/token for subflow + * @sk - the socket that will initiate a connection + * + * This function is called when a new outgoing mptcp connection is + * initiated. + * + * It creates a unique token to identify the new mptcp connection, + * a secret local key and the initial data sequence number (idsn). + * + * On success, the mptcp connection can be found again using + * the computed token at a later time, this is needed to process + * join requests. + * + * returns 0 on success. + */ +int mptcp_token_new_connect(struct sock *sk) +{ + struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk); + struct sock *mptcp_sock = subflow->conn; + int err; + + while (1) { + u32 token; + + mptcp_crypto_key_gen_sha(&subflow->local_key, &subflow->token, + &subflow->idsn); + + pr_debug("ssk=%p, local_key=%llu, token=%u, idsn=%llu\n", + sk, subflow->local_key, subflow->token, subflow->idsn); + + token = subflow->token; + spin_lock_bh(&token_tree_lock); + if (!radix_tree_lookup(&token_req_tree, token) && + !radix_tree_lookup(&token_tree, token)) + break; + spin_unlock_bh(&token_tree_lock); + } + err = radix_tree_insert(&token_tree, subflow->token, mptcp_sock); + spin_unlock_bh(&token_tree_lock); + + return err; +} + +/** + * mptcp_token_new_accept - insert token for later processing + * @token: the token to insert to the tree + * + * Called when a SYN packet creates a new logical connection, i.e. + * is not a join request. + * + * We don't have an mptcp socket yet at that point. + * This is paired with mptcp_token_update_accept, called on accept(). + */ +int mptcp_token_new_accept(u32 token) +{ + int err; + + spin_lock_bh(&token_tree_lock); + err = radix_tree_insert(&token_tree, token, &token_used); + spin_unlock_bh(&token_tree_lock); + + return err; +} + +/** + * mptcp_token_update_accept - update token to map to mptcp socket + * @conn: the new struct mptcp_sock + * @sk: the initial subflow for this mptcp socket + * + * Called when the first mptcp socket is created on accept to + * refresh the dummy mapping (done to reserve the token) with + * the mptcp_socket structure that wasn't allocated before. + */ +void mptcp_token_update_accept(struct sock *sk, struct sock *conn) +{ + struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk); + void __rcu **slot; + + spin_lock_bh(&token_tree_lock); + slot = radix_tree_lookup_slot(&token_tree, subflow->token); + WARN_ON_ONCE(!slot); + if (slot) { + WARN_ON_ONCE(rcu_access_pointer(*slot) != &token_used); + radix_tree_replace_slot(&token_tree, slot, conn); + } + spin_unlock_bh(&token_tree_lock); +} + +/** + * mptcp_token_destroy_request - remove mptcp connection/token + * @token - token of mptcp connection to remove + * + * Remove not-yet-fully-established incoming connection identified + * by @token. + */ +void mptcp_token_destroy_request(u32 token) +{ + spin_lock_bh(&token_tree_lock); + radix_tree_delete(&token_req_tree, token); + spin_unlock_bh(&token_tree_lock); +} + +/** + * mptcp_token_destroy - remove mptcp connection/token + * @token - token of mptcp connection to remove + * + * Remove the connection identified by @token. + */ +void mptcp_token_destroy(u32 token) +{ + spin_lock_bh(&token_tree_lock); + radix_tree_delete(&token_tree, token); + spin_unlock_bh(&token_tree_lock); +} diff --git a/net/ncsi/internal.h b/net/ncsi/internal.h index ad3fd7f1da75..e37102546be6 100644 --- a/net/ncsi/internal.h +++ b/net/ncsi/internal.h @@ -64,6 +64,17 @@ enum { NCSI_MODE_MAX }; +/* Supported media status bits for Mellanox Mac affinity command. + * Bit (0-2) for different protocol support; Bit 1 for RBT support, + * bit 1 for SMBUS support and bit 2 for PCIE support. Bit (3-5) + * for different protocol availability. Bit 4 for RBT, bit 4 for + * SMBUS and bit 5 for PCIE. + */ +enum { + MLX_MC_RBT_SUPPORT = 0x01, /* MC supports RBT */ + MLX_MC_RBT_AVL = 0x08, /* RBT medium is available */ +}; + /* OEM Vendor Manufacture ID */ #define NCSI_OEM_MFR_MLX_ID 0x8119 #define NCSI_OEM_MFR_BCM_ID 0x113d @@ -72,9 +83,15 @@ enum { /* Mellanox specific OEM Command */ #define NCSI_OEM_MLX_CMD_GMA 0x00 /* CMD ID for Get MAC */ #define NCSI_OEM_MLX_CMD_GMA_PARAM 0x1b /* Parameter for GMA */ +#define NCSI_OEM_MLX_CMD_SMAF 0x01 /* CMD ID for Set MC Affinity */ +#define NCSI_OEM_MLX_CMD_SMAF_PARAM 0x07 /* Parameter for SMAF */ /* OEM Command payload lengths*/ #define NCSI_OEM_BCM_CMD_GMA_LEN 12 #define NCSI_OEM_MLX_CMD_GMA_LEN 8 +#define NCSI_OEM_MLX_CMD_SMAF_LEN 60 +/* Offset in OEM request */ +#define MLX_SMAF_MAC_ADDR_OFFSET 8 /* Offset for MAC in SMAF */ +#define MLX_SMAF_MED_SUPPORT_OFFSET 14 /* Offset for medium in SMAF */ /* Mac address offset in OEM response */ #define BCM_MAC_ADDR_OFFSET 28 #define MLX_MAC_ADDR_OFFSET 8 @@ -251,6 +268,8 @@ enum { ncsi_dev_state_probe_deselect = 0x0201, ncsi_dev_state_probe_package, ncsi_dev_state_probe_channel, + ncsi_dev_state_probe_mlx_gma, + ncsi_dev_state_probe_mlx_smaf, ncsi_dev_state_probe_cis, ncsi_dev_state_probe_gvi, ncsi_dev_state_probe_gc, @@ -311,6 +330,7 @@ struct ncsi_dev_priv { struct list_head vlan_vids; /* List of active VLAN IDs */ bool multi_package; /* Enable multiple packages */ + bool mlx_multi_host; /* Enable multi host Mellanox */ u32 package_whitelist; /* Packages to configure */ }; diff --git a/net/ncsi/ncsi-cmd.c b/net/ncsi/ncsi-cmd.c index 0187e65176c0..ba9ae482141b 100644 --- a/net/ncsi/ncsi-cmd.c +++ b/net/ncsi/ncsi-cmd.c @@ -369,7 +369,15 @@ int ncsi_xmit_cmd(struct ncsi_cmd_arg *nca) eh = skb_push(nr->cmd, sizeof(*eh)); eh->h_proto = htons(ETH_P_NCSI); eth_broadcast_addr(eh->h_dest); - eth_broadcast_addr(eh->h_source); + + /* If mac address received from device then use it for + * source address as unicast address else use broadcast + * address as source address + */ + if (nca->ndp->gma_flag == 1) + memcpy(eh->h_source, nca->ndp->ndev.dev->dev_addr, ETH_ALEN); + else + eth_broadcast_addr(eh->h_source); /* Start the timer for the request that might not have * corresponding response. Given NCSI is an internal diff --git a/net/ncsi/ncsi-manage.c b/net/ncsi/ncsi-manage.c index 70fe02697544..1f387be7827b 100644 --- a/net/ncsi/ncsi-manage.c +++ b/net/ncsi/ncsi-manage.c @@ -8,6 +8,8 @@ #include <linux/init.h> #include <linux/netdevice.h> #include <linux/skbuff.h> +#include <linux/of.h> +#include <linux/platform_device.h> #include <net/ncsi.h> #include <net/net_namespace.h> @@ -730,6 +732,34 @@ static int ncsi_oem_gma_handler_mlx(struct ncsi_cmd_arg *nca) return ret; } +static int ncsi_oem_smaf_mlx(struct ncsi_cmd_arg *nca) +{ + union { + u8 data_u8[NCSI_OEM_MLX_CMD_SMAF_LEN]; + u32 data_u32[NCSI_OEM_MLX_CMD_SMAF_LEN / sizeof(u32)]; + } u; + int ret = 0; + + memset(&u, 0, sizeof(u)); + u.data_u32[0] = ntohl(NCSI_OEM_MFR_MLX_ID); + u.data_u8[5] = NCSI_OEM_MLX_CMD_SMAF; + u.data_u8[6] = NCSI_OEM_MLX_CMD_SMAF_PARAM; + memcpy(&u.data_u8[MLX_SMAF_MAC_ADDR_OFFSET], + nca->ndp->ndev.dev->dev_addr, ETH_ALEN); + u.data_u8[MLX_SMAF_MED_SUPPORT_OFFSET] = + (MLX_MC_RBT_AVL | MLX_MC_RBT_SUPPORT); + + nca->payload = NCSI_OEM_MLX_CMD_SMAF_LEN; + nca->data = u.data_u8; + + ret = ncsi_xmit_cmd(nca); + if (ret) + netdev_err(nca->ndp->ndev.dev, + "NCSI: Failed to transmit cmd 0x%x during probe\n", + nca->type); + return ret; +} + /* OEM Command handlers initialization */ static struct ncsi_oem_gma_handler { unsigned int mfr_id; @@ -764,9 +794,6 @@ static int ncsi_gma_handler(struct ncsi_cmd_arg *nca, unsigned int mf_id) return -1; } - /* Set the flag for GMA command which should only be called once */ - nca->ndp->gma_flag = 1; - /* Get Mac address from NCSI device */ return nch->handler(nca); } @@ -1313,8 +1340,38 @@ static void ncsi_probe_channel(struct ncsi_dev_priv *ndp) break; } nd->state = ncsi_dev_state_probe_cis; + if (IS_ENABLED(CONFIG_NCSI_OEM_CMD_GET_MAC) && + ndp->mlx_multi_host) + nd->state = ncsi_dev_state_probe_mlx_gma; + schedule_work(&ndp->work); break; +#if IS_ENABLED(CONFIG_NCSI_OEM_CMD_GET_MAC) + case ncsi_dev_state_probe_mlx_gma: + ndp->pending_req_num = 1; + + nca.type = NCSI_PKT_CMD_OEM; + nca.package = ndp->active_package->id; + nca.channel = 0; + ret = ncsi_oem_gma_handler_mlx(&nca); + if (ret) + goto error; + + nd->state = ncsi_dev_state_probe_mlx_smaf; + break; + case ncsi_dev_state_probe_mlx_smaf: + ndp->pending_req_num = 1; + + nca.type = NCSI_PKT_CMD_OEM; + nca.package = ndp->active_package->id; + nca.channel = 0; + ret = ncsi_oem_smaf_mlx(&nca); + if (ret) + goto error; + + nd->state = ncsi_dev_state_probe_cis; + break; +#endif /* CONFIG_NCSI_OEM_CMD_GET_MAC */ case ncsi_dev_state_probe_cis: ndp->pending_req_num = NCSI_RESERVED_CHANNEL; @@ -1624,6 +1681,8 @@ struct ncsi_dev *ncsi_register_dev(struct net_device *dev, { struct ncsi_dev_priv *ndp; struct ncsi_dev *nd; + struct platform_device *pdev; + struct device_node *np; unsigned long flags; int i; @@ -1670,6 +1729,13 @@ struct ncsi_dev *ncsi_register_dev(struct net_device *dev, /* Set up generic netlink interface */ ncsi_init_netlink(dev); + pdev = to_platform_device(dev->dev.parent); + if (pdev) { + np = pdev->dev.of_node; + if (np && of_get_property(np, "mlx,multi-host", NULL)) + ndp->mlx_multi_host = true; + } + return nd; } EXPORT_SYMBOL_GPL(ncsi_register_dev); diff --git a/net/ncsi/ncsi-rsp.c b/net/ncsi/ncsi-rsp.c index d5611f04926d..a94bb59793f0 100644 --- a/net/ncsi/ncsi-rsp.c +++ b/net/ncsi/ncsi-rsp.c @@ -627,6 +627,9 @@ static int ncsi_rsp_handler_oem_mlx_gma(struct ncsi_request *nr) saddr.sa_family = ndev->type; ndev->priv_flags |= IFF_LIVE_ADDR_CHANGE; memcpy(saddr.sa_data, &rsp->data[MLX_MAC_ADDR_OFFSET], ETH_ALEN); + /* Set the flag for GMA command which should only be called once */ + ndp->gma_flag = 1; + ret = ops->ndo_set_mac_address(ndev, &saddr); if (ret < 0) netdev_warn(ndev, "NCSI: 'Writing mac address to device failed\n"); @@ -671,6 +674,9 @@ static int ncsi_rsp_handler_oem_bcm_gma(struct ncsi_request *nr) if (!is_valid_ether_addr((const u8 *)saddr.sa_data)) return -ENXIO; + /* Set the flag for GMA command which should only be called once */ + ndp->gma_flag = 1; + ret = ops->ndo_set_mac_address(ndev, &saddr); if (ret < 0) netdev_warn(ndev, "NCSI: 'Writing mac address to device failed\n"); diff --git a/net/netfilter/Makefile b/net/netfilter/Makefile index 5e9b2eb24349..3f572e5a975e 100644 --- a/net/netfilter/Makefile +++ b/net/netfilter/Makefile @@ -81,7 +81,8 @@ nf_tables-objs := nf_tables_core.o nf_tables_api.o nft_chain_filter.o \ nft_chain_route.o nf_tables_offload.o nf_tables_set-objs := nf_tables_set_core.o \ - nft_set_hash.o nft_set_bitmap.o nft_set_rbtree.o + nft_set_hash.o nft_set_bitmap.o nft_set_rbtree.o \ + nft_set_pipapo.o obj-$(CONFIG_NF_TABLES) += nf_tables.o obj-$(CONFIG_NF_TABLES_SET) += nf_tables_set.o diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index f475fec84536..f4c4b467c87e 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -2334,7 +2334,6 @@ int nf_conntrack_set_hashsize(const char *val, const struct kernel_param *kp) return nf_conntrack_hash_resize(hashsize); } -EXPORT_SYMBOL_GPL(nf_conntrack_set_hashsize); static __always_inline unsigned int total_extension_size(void) { diff --git a/net/netfilter/nf_conntrack_extend.c b/net/netfilter/nf_conntrack_extend.c index c24e5b64b00c..3dbe2329c3f1 100644 --- a/net/netfilter/nf_conntrack_extend.c +++ b/net/netfilter/nf_conntrack_extend.c @@ -37,7 +37,6 @@ void nf_ct_ext_destroy(struct nf_conn *ct) kfree(ct->ext); } -EXPORT_SYMBOL(nf_ct_ext_destroy); void *nf_ct_ext_add(struct nf_conn *ct, enum nf_ct_ext_id id, gfp_t gfp) { diff --git a/net/netfilter/nf_flow_table_core.c b/net/netfilter/nf_flow_table_core.c index e33a73cb1f42..7e91989a1b55 100644 --- a/net/netfilter/nf_flow_table_core.c +++ b/net/netfilter/nf_flow_table_core.c @@ -61,9 +61,9 @@ struct flow_offload *flow_offload_alloc(struct nf_conn *ct) flow_offload_fill_dir(flow, FLOW_OFFLOAD_DIR_REPLY); if (ct->status & IPS_SRC_NAT) - flow->flags |= FLOW_OFFLOAD_SNAT; + __set_bit(NF_FLOW_SNAT, &flow->flags); if (ct->status & IPS_DST_NAT) - flow->flags |= FLOW_OFFLOAD_DNAT; + __set_bit(NF_FLOW_DNAT, &flow->flags); return flow; @@ -182,8 +182,6 @@ void flow_offload_free(struct flow_offload *flow) default: break; } - if (flow->flags & FLOW_OFFLOAD_DYING) - nf_ct_delete(flow->ct, 0, 0); nf_ct_put(flow->ct); kfree_rcu(flow, rcu_head); } @@ -245,8 +243,10 @@ int flow_offload_add(struct nf_flowtable *flow_table, struct flow_offload *flow) return err; } - if (flow_table->flags & NF_FLOWTABLE_HW_OFFLOAD) + if (nf_flowtable_hw_offload(flow_table)) { + __set_bit(NF_FLOW_HW, &flow->flags); nf_flow_offload_add(flow_table, flow); + } return 0; } @@ -271,7 +271,7 @@ static void flow_offload_del(struct nf_flowtable *flow_table, if (nf_flow_has_expired(flow)) flow_offload_fixup_ct(flow->ct); - else if (flow->flags & FLOW_OFFLOAD_TEARDOWN) + else if (test_bit(NF_FLOW_TEARDOWN, &flow->flags)) flow_offload_fixup_ct_timeout(flow->ct); flow_offload_free(flow); @@ -279,7 +279,7 @@ static void flow_offload_del(struct nf_flowtable *flow_table, void flow_offload_teardown(struct flow_offload *flow) { - flow->flags |= FLOW_OFFLOAD_TEARDOWN; + set_bit(NF_FLOW_TEARDOWN, &flow->flags); flow_offload_fixup_ct_state(flow->ct); } @@ -300,7 +300,7 @@ flow_offload_lookup(struct nf_flowtable *flow_table, dir = tuplehash->tuple.dir; flow = container_of(tuplehash, struct flow_offload, tuplehash[dir]); - if (flow->flags & (FLOW_OFFLOAD_DYING | FLOW_OFFLOAD_TEARDOWN)) + if (test_bit(NF_FLOW_TEARDOWN, &flow->flags)) return NULL; if (unlikely(nf_ct_is_dying(flow->ct))) @@ -348,19 +348,18 @@ static void nf_flow_offload_gc_step(struct flow_offload *flow, void *data) { struct nf_flowtable *flow_table = data; - if (flow->flags & FLOW_OFFLOAD_HW) - nf_flow_offload_stats(flow_table, flow); - if (nf_flow_has_expired(flow) || nf_ct_is_dying(flow->ct) || - (flow->flags & (FLOW_OFFLOAD_DYING | FLOW_OFFLOAD_TEARDOWN))) { - if (flow->flags & FLOW_OFFLOAD_HW) { - if (!(flow->flags & FLOW_OFFLOAD_HW_DYING)) + test_bit(NF_FLOW_TEARDOWN, &flow->flags)) { + if (test_bit(NF_FLOW_HW, &flow->flags)) { + if (!test_bit(NF_FLOW_HW_DYING, &flow->flags)) nf_flow_offload_del(flow_table, flow); - else if (flow->flags & FLOW_OFFLOAD_HW_DEAD) + else if (test_bit(NF_FLOW_HW_DEAD, &flow->flags)) flow_offload_del(flow_table, flow); } else { flow_offload_del(flow_table, flow); } + } else if (test_bit(NF_FLOW_HW, &flow->flags)) { + nf_flow_offload_stats(flow_table, flow); } } @@ -524,7 +523,7 @@ static void nf_flow_table_do_cleanup(struct flow_offload *flow, void *data) if (net_eq(nf_ct_net(flow->ct), dev_net(dev)) && (flow->tuplehash[0].tuple.iifidx == dev->ifindex || flow->tuplehash[1].tuple.iifidx == dev->ifindex)) - flow_offload_dead(flow); + flow_offload_teardown(flow); } static void nf_flow_table_iterate_cleanup(struct nf_flowtable *flowtable, diff --git a/net/netfilter/nf_flow_table_ip.c b/net/netfilter/nf_flow_table_ip.c index 7ea2ddc2aa93..9e563fd3da0f 100644 --- a/net/netfilter/nf_flow_table_ip.c +++ b/net/netfilter/nf_flow_table_ip.c @@ -144,11 +144,11 @@ static int nf_flow_nat_ip(const struct flow_offload *flow, struct sk_buff *skb, { struct iphdr *iph = ip_hdr(skb); - if (flow->flags & FLOW_OFFLOAD_SNAT && + if (test_bit(NF_FLOW_SNAT, &flow->flags) && (nf_flow_snat_port(flow, skb, thoff, iph->protocol, dir) < 0 || nf_flow_snat_ip(flow, skb, iph, thoff, dir) < 0)) return -1; - if (flow->flags & FLOW_OFFLOAD_DNAT && + if (test_bit(NF_FLOW_DNAT, &flow->flags) && (nf_flow_dnat_port(flow, skb, thoff, iph->protocol, dir) < 0 || nf_flow_dnat_ip(flow, skb, iph, thoff, dir) < 0)) return -1; @@ -232,6 +232,13 @@ static unsigned int nf_flow_xmit_xfrm(struct sk_buff *skb, return NF_STOLEN; } +static bool nf_flow_offload_refresh(struct nf_flowtable *flow_table, + struct flow_offload *flow) +{ + return nf_flowtable_hw_offload(flow_table) && + test_and_clear_bit(NF_FLOW_HW_REFRESH, &flow->flags); +} + unsigned int nf_flow_offload_ip_hook(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) @@ -272,6 +279,9 @@ nf_flow_offload_ip_hook(void *priv, struct sk_buff *skb, if (nf_flow_state_check(flow, ip_hdr(skb)->protocol, skb, thoff)) return NF_ACCEPT; + if (unlikely(nf_flow_offload_refresh(flow_table, flow))) + nf_flow_offload_add(flow_table, flow); + if (nf_flow_offload_dst_check(&rt->dst)) { flow_offload_teardown(flow); return NF_ACCEPT; @@ -414,11 +424,11 @@ static int nf_flow_nat_ipv6(const struct flow_offload *flow, struct ipv6hdr *ip6h = ipv6_hdr(skb); unsigned int thoff = sizeof(*ip6h); - if (flow->flags & FLOW_OFFLOAD_SNAT && + if (test_bit(NF_FLOW_SNAT, &flow->flags) && (nf_flow_snat_port(flow, skb, thoff, ip6h->nexthdr, dir) < 0 || nf_flow_snat_ipv6(flow, skb, ip6h, thoff, dir) < 0)) return -1; - if (flow->flags & FLOW_OFFLOAD_DNAT && + if (test_bit(NF_FLOW_DNAT, &flow->flags) && (nf_flow_dnat_port(flow, skb, thoff, ip6h->nexthdr, dir) < 0 || nf_flow_dnat_ipv6(flow, skb, ip6h, thoff, dir) < 0)) return -1; @@ -498,6 +508,9 @@ nf_flow_offload_ipv6_hook(void *priv, struct sk_buff *skb, sizeof(*ip6h))) return NF_ACCEPT; + if (unlikely(nf_flow_offload_refresh(flow_table, flow))) + nf_flow_offload_add(flow_table, flow); + if (nf_flow_offload_dst_check(&rt->dst)) { flow_offload_teardown(flow); return NF_ACCEPT; diff --git a/net/netfilter/nf_flow_table_offload.c b/net/netfilter/nf_flow_table_offload.c index d06969af1085..c8b70ffeef0c 100644 --- a/net/netfilter/nf_flow_table_offload.c +++ b/net/netfilter/nf_flow_table_offload.c @@ -24,6 +24,7 @@ struct flow_offload_work { }; struct nf_flow_key { + struct flow_dissector_key_meta meta; struct flow_dissector_key_control control; struct flow_dissector_key_basic basic; union { @@ -55,6 +56,7 @@ static int nf_flow_rule_match(struct nf_flow_match *match, struct nf_flow_key *mask = &match->mask; struct nf_flow_key *key = &match->key; + NF_FLOW_DISSECTOR(match, FLOW_DISSECTOR_KEY_META, meta); NF_FLOW_DISSECTOR(match, FLOW_DISSECTOR_KEY_CONTROL, control); NF_FLOW_DISSECTOR(match, FLOW_DISSECTOR_KEY_BASIC, basic); NF_FLOW_DISSECTOR(match, FLOW_DISSECTOR_KEY_IPV4_ADDRS, ipv4); @@ -62,6 +64,9 @@ static int nf_flow_rule_match(struct nf_flow_match *match, NF_FLOW_DISSECTOR(match, FLOW_DISSECTOR_KEY_TCP, tcp); NF_FLOW_DISSECTOR(match, FLOW_DISSECTOR_KEY_PORTS, tp); + key->meta.ingress_ifindex = tuple->iifidx; + mask->meta.ingress_ifindex = 0xffffffff; + switch (tuple->l3proto) { case AF_INET: key->control.addr_type = FLOW_DISSECTOR_KEY_IPV4_ADDRS; @@ -105,7 +110,8 @@ static int nf_flow_rule_match(struct nf_flow_match *match, key->tp.dst = tuple->dst_port; mask->tp.dst = 0xffff; - match->dissector.used_keys |= BIT(FLOW_DISSECTOR_KEY_CONTROL) | + match->dissector.used_keys |= BIT(FLOW_DISSECTOR_KEY_META) | + BIT(FLOW_DISSECTOR_KEY_CONTROL) | BIT(FLOW_DISSECTOR_KEY_BASIC) | BIT(FLOW_DISSECTOR_KEY_PORTS); return 0; @@ -444,16 +450,16 @@ int nf_flow_rule_route_ipv4(struct net *net, const struct flow_offload *flow, flow_offload_eth_dst(net, flow, dir, flow_rule) < 0) return -1; - if (flow->flags & FLOW_OFFLOAD_SNAT) { + if (test_bit(NF_FLOW_SNAT, &flow->flags)) { flow_offload_ipv4_snat(net, flow, dir, flow_rule); flow_offload_port_snat(net, flow, dir, flow_rule); } - if (flow->flags & FLOW_OFFLOAD_DNAT) { + if (test_bit(NF_FLOW_DNAT, &flow->flags)) { flow_offload_ipv4_dnat(net, flow, dir, flow_rule); flow_offload_port_dnat(net, flow, dir, flow_rule); } - if (flow->flags & FLOW_OFFLOAD_SNAT || - flow->flags & FLOW_OFFLOAD_DNAT) + if (test_bit(NF_FLOW_SNAT, &flow->flags) || + test_bit(NF_FLOW_DNAT, &flow->flags)) flow_offload_ipv4_checksum(net, flow, flow_rule); flow_offload_redirect(flow, dir, flow_rule); @@ -470,11 +476,11 @@ int nf_flow_rule_route_ipv6(struct net *net, const struct flow_offload *flow, flow_offload_eth_dst(net, flow, dir, flow_rule) < 0) return -1; - if (flow->flags & FLOW_OFFLOAD_SNAT) { + if (test_bit(NF_FLOW_SNAT, &flow->flags)) { flow_offload_ipv6_snat(net, flow, dir, flow_rule); flow_offload_port_snat(net, flow, dir, flow_rule); } - if (flow->flags & FLOW_OFFLOAD_DNAT) { + if (test_bit(NF_FLOW_DNAT, &flow->flags)) { flow_offload_ipv6_dnat(net, flow, dir, flow_rule); flow_offload_port_dnat(net, flow, dir, flow_rule); } @@ -586,23 +592,25 @@ static void nf_flow_offload_init(struct flow_cls_offload *cls_flow, cls_flow->cookie = (unsigned long)tuple; } -static int flow_offload_tuple_add(struct flow_offload_work *offload, - struct nf_flow_rule *flow_rule, - enum flow_offload_tuple_dir dir) +static int nf_flow_offload_tuple(struct nf_flowtable *flowtable, + struct flow_offload *flow, + struct nf_flow_rule *flow_rule, + enum flow_offload_tuple_dir dir, + int priority, int cmd, + struct list_head *block_cb_list) { - struct nf_flowtable *flowtable = offload->flowtable; struct flow_cls_offload cls_flow = {}; struct flow_block_cb *block_cb; struct netlink_ext_ack extack; __be16 proto = ETH_P_ALL; int err, i = 0; - nf_flow_offload_init(&cls_flow, proto, offload->priority, - FLOW_CLS_REPLACE, - &offload->flow->tuplehash[dir].tuple, &extack); - cls_flow.rule = flow_rule->rule; + nf_flow_offload_init(&cls_flow, proto, priority, cmd, + &flow->tuplehash[dir].tuple, &extack); + if (cmd == FLOW_CLS_REPLACE) + cls_flow.rule = flow_rule->rule; - list_for_each_entry(block_cb, &flowtable->flow_block.cb_list, list) { + list_for_each_entry(block_cb, block_cb_list, list) { err = block_cb->cb(TC_SETUP_CLSFLOWER, &cls_flow, block_cb->cb_priv); if (err < 0) @@ -614,23 +622,22 @@ static int flow_offload_tuple_add(struct flow_offload_work *offload, return i; } +static int flow_offload_tuple_add(struct flow_offload_work *offload, + struct nf_flow_rule *flow_rule, + enum flow_offload_tuple_dir dir) +{ + return nf_flow_offload_tuple(offload->flowtable, offload->flow, + flow_rule, dir, offload->priority, + FLOW_CLS_REPLACE, + &offload->flowtable->flow_block.cb_list); +} + static void flow_offload_tuple_del(struct flow_offload_work *offload, enum flow_offload_tuple_dir dir) { - struct nf_flowtable *flowtable = offload->flowtable; - struct flow_cls_offload cls_flow = {}; - struct flow_block_cb *block_cb; - struct netlink_ext_ack extack; - __be16 proto = ETH_P_ALL; - - nf_flow_offload_init(&cls_flow, proto, offload->priority, - FLOW_CLS_DESTROY, - &offload->flow->tuplehash[dir].tuple, &extack); - - list_for_each_entry(block_cb, &flowtable->flow_block.cb_list, list) - block_cb->cb(TC_SETUP_CLSFLOWER, &cls_flow, block_cb->cb_priv); - - offload->flow->flags |= FLOW_OFFLOAD_HW_DEAD; + nf_flow_offload_tuple(offload->flowtable, offload->flow, NULL, dir, + offload->priority, FLOW_CLS_DESTROY, + &offload->flowtable->flow_block.cb_list); } static int flow_offload_rule_add(struct flow_offload_work *offload, @@ -648,20 +655,20 @@ static int flow_offload_rule_add(struct flow_offload_work *offload, return 0; } -static int flow_offload_work_add(struct flow_offload_work *offload) +static void flow_offload_work_add(struct flow_offload_work *offload) { struct nf_flow_rule *flow_rule[FLOW_OFFLOAD_DIR_MAX]; int err; err = nf_flow_offload_alloc(offload, flow_rule); if (err < 0) - return -ENOMEM; + return; err = flow_offload_rule_add(offload, flow_rule); + if (err < 0) + set_bit(NF_FLOW_HW_REFRESH, &offload->flow->flags); nf_flow_offload_destroy(flow_rule); - - return err; } static void flow_offload_work_del(struct flow_offload_work *offload) @@ -706,7 +713,6 @@ static void flow_offload_work_handler(struct work_struct *work) { struct flow_offload_work *offload, *next; LIST_HEAD(offload_pending_list); - int ret; spin_lock_bh(&flow_offload_pending_list_lock); list_replace_init(&flow_offload_pending_list, &offload_pending_list); @@ -715,9 +721,7 @@ static void flow_offload_work_handler(struct work_struct *work) list_for_each_entry_safe(offload, next, &offload_pending_list, list) { switch (offload->cmd) { case FLOW_CLS_REPLACE: - ret = flow_offload_work_add(offload); - if (ret < 0) - offload->flow->flags &= ~FLOW_OFFLOAD_HW; + flow_offload_work_add(offload); break; case FLOW_CLS_DESTROY: flow_offload_work_del(offload); @@ -742,20 +746,33 @@ static void flow_offload_queue_work(struct flow_offload_work *offload) schedule_work(&nf_flow_offload_work); } -void nf_flow_offload_add(struct nf_flowtable *flowtable, - struct flow_offload *flow) +static struct flow_offload_work * +nf_flow_offload_work_alloc(struct nf_flowtable *flowtable, + struct flow_offload *flow, unsigned int cmd) { struct flow_offload_work *offload; offload = kmalloc(sizeof(struct flow_offload_work), GFP_ATOMIC); if (!offload) - return; + return NULL; - offload->cmd = FLOW_CLS_REPLACE; + offload->cmd = cmd; offload->flow = flow; offload->priority = flowtable->priority; offload->flowtable = flowtable; - flow->flags |= FLOW_OFFLOAD_HW; + + return offload; +} + + +void nf_flow_offload_add(struct nf_flowtable *flowtable, + struct flow_offload *flow) +{ + struct flow_offload_work *offload; + + offload = nf_flow_offload_work_alloc(flowtable, flow, FLOW_CLS_REPLACE); + if (!offload) + return; flow_offload_queue_work(offload); } @@ -765,15 +782,11 @@ void nf_flow_offload_del(struct nf_flowtable *flowtable, { struct flow_offload_work *offload; - offload = kzalloc(sizeof(struct flow_offload_work), GFP_ATOMIC); + offload = nf_flow_offload_work_alloc(flowtable, flow, FLOW_CLS_DESTROY); if (!offload) return; - offload->cmd = FLOW_CLS_DESTROY; - offload->flow = flow; - offload->flow->flags |= FLOW_OFFLOAD_HW_DYING; - offload->flowtable = flowtable; - + set_bit(NF_FLOW_HW_DYING, &flow->flags); flow_offload_queue_work(offload); } @@ -784,24 +797,19 @@ void nf_flow_offload_stats(struct nf_flowtable *flowtable, __s32 delta; delta = nf_flow_timeout_delta(flow->timeout); - if ((delta >= (9 * NF_FLOW_TIMEOUT) / 10) || - flow->flags & FLOW_OFFLOAD_HW_DYING) + if ((delta >= (9 * NF_FLOW_TIMEOUT) / 10)) return; - offload = kzalloc(sizeof(struct flow_offload_work), GFP_ATOMIC); + offload = nf_flow_offload_work_alloc(flowtable, flow, FLOW_CLS_STATS); if (!offload) return; - offload->cmd = FLOW_CLS_STATS; - offload->flow = flow; - offload->flowtable = flowtable; - flow_offload_queue_work(offload); } void nf_flow_table_offload_flush(struct nf_flowtable *flowtable) { - if (flowtable->flags & NF_FLOWTABLE_HW_OFFLOAD) + if (nf_flowtable_hw_offload(flowtable)) flush_work(&nf_flow_offload_work); } @@ -830,28 +838,44 @@ static int nf_flow_table_block_setup(struct nf_flowtable *flowtable, return err; } -int nf_flow_table_offload_setup(struct nf_flowtable *flowtable, - struct net_device *dev, - enum flow_block_command cmd) +static int nf_flow_table_offload_cmd(struct flow_block_offload *bo, + struct nf_flowtable *flowtable, + struct net_device *dev, + enum flow_block_command cmd, + struct netlink_ext_ack *extack) { - struct netlink_ext_ack extack = {}; - struct flow_block_offload bo = {}; int err; - if (!(flowtable->flags & NF_FLOWTABLE_HW_OFFLOAD)) + if (!nf_flowtable_hw_offload(flowtable)) return 0; if (!dev->netdev_ops->ndo_setup_tc) return -EOPNOTSUPP; - bo.net = dev_net(dev); - bo.block = &flowtable->flow_block; - bo.command = cmd; - bo.binder_type = FLOW_BLOCK_BINDER_TYPE_CLSACT_INGRESS; - bo.extack = &extack; - INIT_LIST_HEAD(&bo.cb_list); + memset(bo, 0, sizeof(*bo)); + bo->net = dev_net(dev); + bo->block = &flowtable->flow_block; + bo->command = cmd; + bo->binder_type = FLOW_BLOCK_BINDER_TYPE_CLSACT_INGRESS; + bo->extack = extack; + INIT_LIST_HEAD(&bo->cb_list); + + err = dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_FT, bo); + if (err < 0) + return err; + + return 0; +} + +int nf_flow_table_offload_setup(struct nf_flowtable *flowtable, + struct net_device *dev, + enum flow_block_command cmd) +{ + struct netlink_ext_ack extack = {}; + struct flow_block_offload bo; + int err; - err = dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_FT, &bo); + err = nf_flow_table_offload_cmd(&bo, flowtable, dev, cmd, &extack); if (err < 0) return err; diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 7e63b481cc86..d1318bdf49ca 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -3391,6 +3391,7 @@ static const struct nla_policy nft_set_policy[NFTA_SET_MAX + 1] = { static const struct nla_policy nft_set_desc_policy[NFTA_SET_DESC_MAX + 1] = { [NFTA_SET_DESC_SIZE] = { .type = NLA_U32 }, + [NFTA_SET_DESC_CONCAT] = { .type = NLA_NESTED }, }; static int nft_ctx_init_from_setattr(struct nft_ctx *ctx, struct net *net, @@ -3557,6 +3558,33 @@ static __be64 nf_jiffies64_to_msecs(u64 input) return cpu_to_be64(jiffies64_to_msecs(input)); } +static int nf_tables_fill_set_concat(struct sk_buff *skb, + const struct nft_set *set) +{ + struct nlattr *concat, *field; + int i; + + concat = nla_nest_start_noflag(skb, NFTA_SET_DESC_CONCAT); + if (!concat) + return -ENOMEM; + + for (i = 0; i < set->field_count; i++) { + field = nla_nest_start_noflag(skb, NFTA_LIST_ELEM); + if (!field) + return -ENOMEM; + + if (nla_put_be32(skb, NFTA_SET_FIELD_LEN, + htonl(set->field_len[i]))) + return -ENOMEM; + + nla_nest_end(skb, field); + } + + nla_nest_end(skb, concat); + + return 0; +} + static int nf_tables_fill_set(struct sk_buff *skb, const struct nft_ctx *ctx, const struct nft_set *set, u16 event, u16 flags) { @@ -3620,11 +3648,17 @@ static int nf_tables_fill_set(struct sk_buff *skb, const struct nft_ctx *ctx, goto nla_put_failure; desc = nla_nest_start_noflag(skb, NFTA_SET_DESC); + if (desc == NULL) goto nla_put_failure; if (set->size && nla_put_be32(skb, NFTA_SET_DESC_SIZE, htonl(set->size))) goto nla_put_failure; + + if (set->field_count > 1 && + nf_tables_fill_set_concat(skb, set)) + goto nla_put_failure; + nla_nest_end(skb, desc); nlmsg_end(skb, nlh); @@ -3797,6 +3831,53 @@ err: return err; } +static const struct nla_policy nft_concat_policy[NFTA_SET_FIELD_MAX + 1] = { + [NFTA_SET_FIELD_LEN] = { .type = NLA_U32 }, +}; + +static int nft_set_desc_concat_parse(const struct nlattr *attr, + struct nft_set_desc *desc) +{ + struct nlattr *tb[NFTA_SET_FIELD_MAX + 1]; + u32 len; + int err; + + err = nla_parse_nested_deprecated(tb, NFTA_SET_FIELD_MAX, attr, + nft_concat_policy, NULL); + if (err < 0) + return err; + + if (!tb[NFTA_SET_FIELD_LEN]) + return -EINVAL; + + len = ntohl(nla_get_be32(tb[NFTA_SET_FIELD_LEN])); + + if (len * BITS_PER_BYTE / 32 > NFT_REG32_COUNT) + return -E2BIG; + + desc->field_len[desc->field_count++] = len; + + return 0; +} + +static int nft_set_desc_concat(struct nft_set_desc *desc, + const struct nlattr *nla) +{ + struct nlattr *attr; + int rem, err; + + nla_for_each_nested(attr, nla, rem) { + if (nla_type(attr) != NFTA_LIST_ELEM) + return -EINVAL; + + err = nft_set_desc_concat_parse(attr, desc); + if (err < 0) + return err; + } + + return 0; +} + static int nf_tables_set_desc_parse(struct nft_set_desc *desc, const struct nlattr *nla) { @@ -3810,8 +3891,10 @@ static int nf_tables_set_desc_parse(struct nft_set_desc *desc, if (da[NFTA_SET_DESC_SIZE] != NULL) desc->size = ntohl(nla_get_be32(da[NFTA_SET_DESC_SIZE])); + if (da[NFTA_SET_DESC_CONCAT]) + err = nft_set_desc_concat(desc, da[NFTA_SET_DESC_CONCAT]); - return 0; + return err; } static int nf_tables_newset(struct net *net, struct sock *nlsk, @@ -3834,6 +3917,7 @@ static int nf_tables_newset(struct net *net, struct sock *nlsk, unsigned char *udata; u16 udlen; int err; + int i; if (nla[NFTA_SET_TABLE] == NULL || nla[NFTA_SET_NAME] == NULL || @@ -4012,6 +4096,10 @@ static int nf_tables_newset(struct net *net, struct sock *nlsk, set->gc_int = gc_int; set->handle = nf_tables_alloc_handle(table); + set->field_count = desc.field_count; + for (i = 0; i < desc.field_count; i++) + set->field_len[i] = desc.field_len[i]; + err = ops->init(set, &desc, nla); if (err < 0) goto err3; @@ -4215,6 +4303,9 @@ const struct nft_set_ext_type nft_set_ext_types[] = { .len = sizeof(struct nft_userdata), .align = __alignof__(struct nft_userdata), }, + [NFT_SET_EXT_KEY_END] = { + .align = __alignof__(u32), + }, }; EXPORT_SYMBOL_GPL(nft_set_ext_types); @@ -4233,6 +4324,7 @@ static const struct nla_policy nft_set_elem_policy[NFTA_SET_ELEM_MAX + 1] = { [NFTA_SET_ELEM_EXPR] = { .type = NLA_NESTED }, [NFTA_SET_ELEM_OBJREF] = { .type = NLA_STRING, .len = NFT_OBJ_MAXNAMELEN - 1 }, + [NFTA_SET_ELEM_KEY_END] = { .type = NLA_NESTED }, }; static const struct nla_policy nft_set_elem_list_policy[NFTA_SET_ELEM_LIST_MAX + 1] = { @@ -4282,6 +4374,11 @@ static int nf_tables_fill_setelem(struct sk_buff *skb, NFT_DATA_VALUE, set->klen) < 0) goto nla_put_failure; + if (nft_set_ext_exists(ext, NFT_SET_EXT_KEY_END) && + nft_data_dump(skb, NFTA_SET_ELEM_KEY_END, nft_set_ext_key_end(ext), + NFT_DATA_VALUE, set->klen) < 0) + goto nla_put_failure; + if (nft_set_ext_exists(ext, NFT_SET_EXT_DATA) && nft_data_dump(skb, NFTA_SET_ELEM_DATA, nft_set_ext_data(ext), set->dtype == NFT_DATA_VERDICT ? NFT_DATA_VERDICT : NFT_DATA_VALUE, @@ -4524,11 +4621,28 @@ static int nft_setelem_parse_flags(const struct nft_set *set, return 0; } +static int nft_setelem_parse_key(struct nft_ctx *ctx, struct nft_set *set, + struct nft_data *key, struct nlattr *attr) +{ + struct nft_data_desc desc; + int err; + + err = nft_data_init(ctx, key, NFT_DATA_VALUE_MAXLEN, &desc, attr); + if (err < 0) + return err; + + if (desc.type != NFT_DATA_VALUE || desc.len != set->klen) { + nft_data_release(key, desc.type); + return -EINVAL; + } + + return 0; +} + static int nft_get_set_elem(struct nft_ctx *ctx, struct nft_set *set, const struct nlattr *attr) { struct nlattr *nla[NFTA_SET_ELEM_MAX + 1]; - struct nft_data_desc desc; struct nft_set_elem elem; struct sk_buff *skb; uint32_t flags = 0; @@ -4547,15 +4661,16 @@ static int nft_get_set_elem(struct nft_ctx *ctx, struct nft_set *set, if (err < 0) return err; - err = nft_data_init(ctx, &elem.key.val, sizeof(elem.key), &desc, - nla[NFTA_SET_ELEM_KEY]); + err = nft_setelem_parse_key(ctx, set, &elem.key.val, + nla[NFTA_SET_ELEM_KEY]); if (err < 0) return err; - err = -EINVAL; - if (desc.type != NFT_DATA_VALUE || desc.len != set->klen) { - nft_data_release(&elem.key.val, desc.type); - return err; + if (nla[NFTA_SET_ELEM_KEY_END]) { + err = nft_setelem_parse_key(ctx, set, &elem.key_end.val, + nla[NFTA_SET_ELEM_KEY_END]); + if (err < 0) + return err; } priv = set->ops->get(ctx->net, set, &elem, flags); @@ -4683,8 +4798,8 @@ static struct nft_trans *nft_trans_elem_alloc(struct nft_ctx *ctx, void *nft_set_elem_init(const struct nft_set *set, const struct nft_set_ext_tmpl *tmpl, - const u32 *key, const u32 *data, - u64 timeout, u64 expiration, gfp_t gfp) + const u32 *key, const u32 *key_end, + const u32 *data, u64 timeout, u64 expiration, gfp_t gfp) { struct nft_set_ext *ext; void *elem; @@ -4697,6 +4812,8 @@ void *nft_set_elem_init(const struct nft_set *set, nft_set_ext_init(ext, tmpl); memcpy(nft_set_ext_key(ext), key, set->klen); + if (nft_set_ext_exists(ext, NFT_SET_EXT_KEY_END)) + memcpy(nft_set_ext_key_end(ext), key_end, set->klen); if (nft_set_ext_exists(ext, NFT_SET_EXT_DATA)) memcpy(nft_set_ext_data(ext), data, set->dlen); if (nft_set_ext_exists(ext, NFT_SET_EXT_EXPIRATION)) { @@ -4756,13 +4873,13 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set, { struct nlattr *nla[NFTA_SET_ELEM_MAX + 1]; u8 genmask = nft_genmask_next(ctx->net); - struct nft_data_desc d1, d2; struct nft_set_ext_tmpl tmpl; struct nft_set_ext *ext, *ext2; struct nft_set_elem elem; struct nft_set_binding *binding; struct nft_object *obj = NULL; struct nft_userdata *udata; + struct nft_data_desc desc; struct nft_data data; enum nft_registers dreg; struct nft_trans *trans; @@ -4828,15 +4945,22 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set, return err; } - err = nft_data_init(ctx, &elem.key.val, sizeof(elem.key), &d1, - nla[NFTA_SET_ELEM_KEY]); + err = nft_setelem_parse_key(ctx, set, &elem.key.val, + nla[NFTA_SET_ELEM_KEY]); if (err < 0) - goto err1; - err = -EINVAL; - if (d1.type != NFT_DATA_VALUE || d1.len != set->klen) - goto err2; + return err; + + nft_set_ext_add_length(&tmpl, NFT_SET_EXT_KEY, set->klen); + + if (nla[NFTA_SET_ELEM_KEY_END]) { + err = nft_setelem_parse_key(ctx, set, &elem.key_end.val, + nla[NFTA_SET_ELEM_KEY_END]); + if (err < 0) + goto err_parse_key; + + nft_set_ext_add_length(&tmpl, NFT_SET_EXT_KEY_END, set->klen); + } - nft_set_ext_add_length(&tmpl, NFT_SET_EXT_KEY, d1.len); if (timeout > 0) { nft_set_ext_add(&tmpl, NFT_SET_EXT_EXPIRATION); if (timeout != set->timeout) @@ -4846,27 +4970,27 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set, if (nla[NFTA_SET_ELEM_OBJREF] != NULL) { if (!(set->flags & NFT_SET_OBJECT)) { err = -EINVAL; - goto err2; + goto err_parse_key_end; } obj = nft_obj_lookup(ctx->net, ctx->table, nla[NFTA_SET_ELEM_OBJREF], set->objtype, genmask); if (IS_ERR(obj)) { err = PTR_ERR(obj); - goto err2; + goto err_parse_key_end; } nft_set_ext_add(&tmpl, NFT_SET_EXT_OBJREF); } if (nla[NFTA_SET_ELEM_DATA] != NULL) { - err = nft_data_init(ctx, &data, sizeof(data), &d2, + err = nft_data_init(ctx, &data, sizeof(data), &desc, nla[NFTA_SET_ELEM_DATA]); if (err < 0) - goto err2; + goto err_parse_key_end; err = -EINVAL; - if (set->dtype != NFT_DATA_VERDICT && d2.len != set->dlen) - goto err3; + if (set->dtype != NFT_DATA_VERDICT && desc.len != set->dlen) + goto err_parse_data; dreg = nft_type_to_reg(set->dtype); list_for_each_entry(binding, &set->bindings, list) { @@ -4882,18 +5006,18 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set, err = nft_validate_register_store(&bind_ctx, dreg, &data, - d2.type, d2.len); + desc.type, desc.len); if (err < 0) - goto err3; + goto err_parse_data; - if (d2.type == NFT_DATA_VERDICT && + if (desc.type == NFT_DATA_VERDICT && (data.verdict.code == NFT_GOTO || data.verdict.code == NFT_JUMP)) nft_validate_state_update(ctx->net, NFT_VALIDATE_NEED); } - nft_set_ext_add_length(&tmpl, NFT_SET_EXT_DATA, d2.len); + nft_set_ext_add_length(&tmpl, NFT_SET_EXT_DATA, desc.len); } /* The full maximum length of userdata can exceed the maximum @@ -4909,10 +5033,11 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set, } err = -ENOMEM; - elem.priv = nft_set_elem_init(set, &tmpl, elem.key.val.data, data.data, + elem.priv = nft_set_elem_init(set, &tmpl, elem.key.val.data, + elem.key_end.val.data, data.data, timeout, expiration, GFP_KERNEL); if (elem.priv == NULL) - goto err3; + goto err_parse_data; ext = nft_set_elem_ext(set, elem.priv); if (flags) @@ -4929,7 +5054,7 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set, trans = nft_trans_elem_alloc(ctx, NFT_MSG_NEWSETELEM, set); if (trans == NULL) - goto err4; + goto err_trans; ext->genmask = nft_genmask_cur(ctx->net) | NFT_SET_ELEM_BUSY_MASK; err = set->ops->insert(ctx->net, set, &elem, &ext2); @@ -4940,7 +5065,7 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set, nft_set_ext_exists(ext, NFT_SET_EXT_OBJREF) ^ nft_set_ext_exists(ext2, NFT_SET_EXT_OBJREF)) { err = -EBUSY; - goto err5; + goto err_element_clash; } if ((nft_set_ext_exists(ext, NFT_SET_EXT_DATA) && nft_set_ext_exists(ext2, NFT_SET_EXT_DATA) && @@ -4953,33 +5078,35 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set, else if (!(nlmsg_flags & NLM_F_EXCL)) err = 0; } - goto err5; + goto err_element_clash; } if (set->size && !atomic_add_unless(&set->nelems, 1, set->size + set->ndeact)) { err = -ENFILE; - goto err6; + goto err_set_full; } nft_trans_elem(trans) = elem; list_add_tail(&trans->list, &ctx->net->nft.commit_list); return 0; -err6: +err_set_full: set->ops->remove(ctx->net, set, &elem); -err5: +err_element_clash: kfree(trans); -err4: +err_trans: if (obj) obj->use--; kfree(elem.priv); -err3: +err_parse_data: if (nla[NFTA_SET_ELEM_DATA] != NULL) - nft_data_release(&data, d2.type); -err2: - nft_data_release(&elem.key.val, d1.type); -err1: + nft_data_release(&data, desc.type); +err_parse_key_end: + nft_data_release(&elem.key_end.val, NFT_DATA_VALUE); +err_parse_key: + nft_data_release(&elem.key.val, NFT_DATA_VALUE); + return err; } @@ -5074,7 +5201,6 @@ static int nft_del_setelem(struct nft_ctx *ctx, struct nft_set *set, { struct nlattr *nla[NFTA_SET_ELEM_MAX + 1]; struct nft_set_ext_tmpl tmpl; - struct nft_data_desc desc; struct nft_set_elem elem; struct nft_set_ext *ext; struct nft_trans *trans; @@ -5085,11 +5211,10 @@ static int nft_del_setelem(struct nft_ctx *ctx, struct nft_set *set, err = nla_parse_nested_deprecated(nla, NFTA_SET_ELEM_MAX, attr, nft_set_elem_policy, NULL); if (err < 0) - goto err1; + return err; - err = -EINVAL; if (nla[NFTA_SET_ELEM_KEY] == NULL) - goto err1; + return -EINVAL; nft_set_ext_prepare(&tmpl); @@ -5099,37 +5224,41 @@ static int nft_del_setelem(struct nft_ctx *ctx, struct nft_set *set, if (flags != 0) nft_set_ext_add(&tmpl, NFT_SET_EXT_FLAGS); - err = nft_data_init(ctx, &elem.key.val, sizeof(elem.key), &desc, - nla[NFTA_SET_ELEM_KEY]); + err = nft_setelem_parse_key(ctx, set, &elem.key.val, + nla[NFTA_SET_ELEM_KEY]); if (err < 0) - goto err1; + return err; - err = -EINVAL; - if (desc.type != NFT_DATA_VALUE || desc.len != set->klen) - goto err2; + nft_set_ext_add_length(&tmpl, NFT_SET_EXT_KEY, set->klen); - nft_set_ext_add_length(&tmpl, NFT_SET_EXT_KEY, desc.len); + if (nla[NFTA_SET_ELEM_KEY_END]) { + err = nft_setelem_parse_key(ctx, set, &elem.key_end.val, + nla[NFTA_SET_ELEM_KEY_END]); + if (err < 0) + return err; + + nft_set_ext_add_length(&tmpl, NFT_SET_EXT_KEY_END, set->klen); + } err = -ENOMEM; - elem.priv = nft_set_elem_init(set, &tmpl, elem.key.val.data, NULL, 0, - 0, GFP_KERNEL); + elem.priv = nft_set_elem_init(set, &tmpl, elem.key.val.data, + elem.key_end.val.data, NULL, 0, 0, + GFP_KERNEL); if (elem.priv == NULL) - goto err2; + goto fail_elem; ext = nft_set_elem_ext(set, elem.priv); if (flags) *nft_set_ext_flags(ext) = flags; trans = nft_trans_elem_alloc(ctx, NFT_MSG_DELSETELEM, set); - if (trans == NULL) { - err = -ENOMEM; - goto err3; - } + if (trans == NULL) + goto fail_trans; priv = set->ops->deactivate(ctx->net, set, &elem); if (priv == NULL) { err = -ENOENT; - goto err4; + goto fail_ops; } kfree(elem.priv); elem.priv = priv; @@ -5140,13 +5269,12 @@ static int nft_del_setelem(struct nft_ctx *ctx, struct nft_set *set, list_add_tail(&trans->list, &ctx->net->nft.commit_list); return 0; -err4: +fail_ops: kfree(trans); -err3: +fail_trans: kfree(elem.priv); -err2: - nft_data_release(&elem.key.val, desc.type); -err1: +fail_elem: + nft_data_release(&elem.key.val, NFT_DATA_VALUE); return err; } diff --git a/net/netfilter/nf_tables_set_core.c b/net/netfilter/nf_tables_set_core.c index a9fce8d10051..586b621007eb 100644 --- a/net/netfilter/nf_tables_set_core.c +++ b/net/netfilter/nf_tables_set_core.c @@ -9,12 +9,14 @@ static int __init nf_tables_set_module_init(void) nft_register_set(&nft_set_rhash_type); nft_register_set(&nft_set_bitmap_type); nft_register_set(&nft_set_rbtree_type); + nft_register_set(&nft_set_pipapo_type); return 0; } static void __exit nf_tables_set_module_exit(void) { + nft_unregister_set(&nft_set_pipapo_type); nft_unregister_set(&nft_set_rbtree_type); nft_unregister_set(&nft_set_bitmap_type); nft_unregister_set(&nft_set_rhash_type); diff --git a/net/netfilter/nfnetlink_queue.c b/net/netfilter/nfnetlink_queue.c index feabdfb22920..76535fd9278c 100644 --- a/net/netfilter/nfnetlink_queue.c +++ b/net/netfilter/nfnetlink_queue.c @@ -778,7 +778,7 @@ nfqnl_enqueue_packet(struct nf_queue_entry *entry, unsigned int queuenum) { unsigned int queued; struct nfqnl_instance *queue; - struct sk_buff *skb, *segs; + struct sk_buff *skb, *segs, *nskb; int err = -ENOBUFS; struct net *net = entry->state.net; struct nfnl_queue_net *q = nfnl_queue_pernet(net); @@ -815,8 +815,7 @@ nfqnl_enqueue_packet(struct nf_queue_entry *entry, unsigned int queuenum) goto out_err; queued = 0; err = 0; - do { - struct sk_buff *nskb = segs->next; + skb_list_walk_safe(segs, segs, nskb) { if (err == 0) err = __nfqnl_enqueue_packet_gso(net, queue, segs, entry); @@ -824,8 +823,7 @@ nfqnl_enqueue_packet(struct nf_queue_entry *entry, unsigned int queuenum) queued++; else kfree_skb(segs); - segs = nskb; - } while (segs); + } if (queued) { if (err) /* some segments are already queued */ diff --git a/net/netfilter/nft_bitwise.c b/net/netfilter/nft_bitwise.c index 10e9d50e4e19..0ed2281f03be 100644 --- a/net/netfilter/nft_bitwise.c +++ b/net/netfilter/nft_bitwise.c @@ -18,21 +18,66 @@ struct nft_bitwise { enum nft_registers sreg:8; enum nft_registers dreg:8; + enum nft_bitwise_ops op:8; u8 len; struct nft_data mask; struct nft_data xor; + struct nft_data data; }; +static void nft_bitwise_eval_bool(u32 *dst, const u32 *src, + const struct nft_bitwise *priv) +{ + unsigned int i; + + for (i = 0; i < DIV_ROUND_UP(priv->len, 4); i++) + dst[i] = (src[i] & priv->mask.data[i]) ^ priv->xor.data[i]; +} + +static void nft_bitwise_eval_lshift(u32 *dst, const u32 *src, + const struct nft_bitwise *priv) +{ + u32 shift = priv->data.data[0]; + unsigned int i; + u32 carry = 0; + + for (i = DIV_ROUND_UP(priv->len, sizeof(u32)); i > 0; i--) { + dst[i - 1] = (src[i - 1] << shift) | carry; + carry = src[i - 1] >> (BITS_PER_TYPE(u32) - shift); + } +} + +static void nft_bitwise_eval_rshift(u32 *dst, const u32 *src, + const struct nft_bitwise *priv) +{ + u32 shift = priv->data.data[0]; + unsigned int i; + u32 carry = 0; + + for (i = 0; i < DIV_ROUND_UP(priv->len, sizeof(u32)); i++) { + dst[i] = carry | (src[i] >> shift); + carry = src[i] << (BITS_PER_TYPE(u32) - shift); + } +} + void nft_bitwise_eval(const struct nft_expr *expr, struct nft_regs *regs, const struct nft_pktinfo *pkt) { const struct nft_bitwise *priv = nft_expr_priv(expr); const u32 *src = ®s->data[priv->sreg]; u32 *dst = ®s->data[priv->dreg]; - unsigned int i; - for (i = 0; i < DIV_ROUND_UP(priv->len, 4); i++) - dst[i] = (src[i] & priv->mask.data[i]) ^ priv->xor.data[i]; + switch (priv->op) { + case NFT_BITWISE_BOOL: + nft_bitwise_eval_bool(dst, src, priv); + break; + case NFT_BITWISE_LSHIFT: + nft_bitwise_eval_lshift(dst, src, priv); + break; + case NFT_BITWISE_RSHIFT: + nft_bitwise_eval_rshift(dst, src, priv); + break; + } } static const struct nla_policy nft_bitwise_policy[NFTA_BITWISE_MAX + 1] = { @@ -41,40 +86,22 @@ static const struct nla_policy nft_bitwise_policy[NFTA_BITWISE_MAX + 1] = { [NFTA_BITWISE_LEN] = { .type = NLA_U32 }, [NFTA_BITWISE_MASK] = { .type = NLA_NESTED }, [NFTA_BITWISE_XOR] = { .type = NLA_NESTED }, + [NFTA_BITWISE_OP] = { .type = NLA_U32 }, + [NFTA_BITWISE_DATA] = { .type = NLA_NESTED }, }; -static int nft_bitwise_init(const struct nft_ctx *ctx, - const struct nft_expr *expr, - const struct nlattr * const tb[]) +static int nft_bitwise_init_bool(struct nft_bitwise *priv, + const struct nlattr *const tb[]) { - struct nft_bitwise *priv = nft_expr_priv(expr); struct nft_data_desc d1, d2; - u32 len; int err; - if (tb[NFTA_BITWISE_SREG] == NULL || - tb[NFTA_BITWISE_DREG] == NULL || - tb[NFTA_BITWISE_LEN] == NULL || - tb[NFTA_BITWISE_MASK] == NULL || - tb[NFTA_BITWISE_XOR] == NULL) + if (tb[NFTA_BITWISE_DATA]) return -EINVAL; - err = nft_parse_u32_check(tb[NFTA_BITWISE_LEN], U8_MAX, &len); - if (err < 0) - return err; - - priv->len = len; - - priv->sreg = nft_parse_register(tb[NFTA_BITWISE_SREG]); - err = nft_validate_register_load(priv->sreg, priv->len); - if (err < 0) - return err; - - priv->dreg = nft_parse_register(tb[NFTA_BITWISE_DREG]); - err = nft_validate_register_store(ctx, priv->dreg, NULL, - NFT_DATA_VALUE, priv->len); - if (err < 0) - return err; + if (!tb[NFTA_BITWISE_MASK] || + !tb[NFTA_BITWISE_XOR]) + return -EINVAL; err = nft_data_init(NULL, &priv->mask, sizeof(priv->mask), &d1, tb[NFTA_BITWISE_MASK]); @@ -102,40 +129,151 @@ err1: return err; } -static int nft_bitwise_dump(struct sk_buff *skb, const struct nft_expr *expr) +static int nft_bitwise_init_shift(struct nft_bitwise *priv, + const struct nlattr *const tb[]) { - const struct nft_bitwise *priv = nft_expr_priv(expr); + struct nft_data_desc d; + int err; - if (nft_dump_register(skb, NFTA_BITWISE_SREG, priv->sreg)) - goto nla_put_failure; - if (nft_dump_register(skb, NFTA_BITWISE_DREG, priv->dreg)) - goto nla_put_failure; - if (nla_put_be32(skb, NFTA_BITWISE_LEN, htonl(priv->len))) - goto nla_put_failure; + if (tb[NFTA_BITWISE_MASK] || + tb[NFTA_BITWISE_XOR]) + return -EINVAL; + + if (!tb[NFTA_BITWISE_DATA]) + return -EINVAL; + err = nft_data_init(NULL, &priv->data, sizeof(priv->data), &d, + tb[NFTA_BITWISE_DATA]); + if (err < 0) + return err; + if (d.type != NFT_DATA_VALUE || d.len != sizeof(u32) || + priv->data.data[0] >= BITS_PER_TYPE(u32)) { + nft_data_release(&priv->data, d.type); + return -EINVAL; + } + + return 0; +} + +static int nft_bitwise_init(const struct nft_ctx *ctx, + const struct nft_expr *expr, + const struct nlattr * const tb[]) +{ + struct nft_bitwise *priv = nft_expr_priv(expr); + u32 len; + int err; + + if (!tb[NFTA_BITWISE_SREG] || + !tb[NFTA_BITWISE_DREG] || + !tb[NFTA_BITWISE_LEN]) + return -EINVAL; + + err = nft_parse_u32_check(tb[NFTA_BITWISE_LEN], U8_MAX, &len); + if (err < 0) + return err; + + priv->len = len; + + priv->sreg = nft_parse_register(tb[NFTA_BITWISE_SREG]); + err = nft_validate_register_load(priv->sreg, priv->len); + if (err < 0) + return err; + + priv->dreg = nft_parse_register(tb[NFTA_BITWISE_DREG]); + err = nft_validate_register_store(ctx, priv->dreg, NULL, + NFT_DATA_VALUE, priv->len); + if (err < 0) + return err; + + if (tb[NFTA_BITWISE_OP]) { + priv->op = ntohl(nla_get_be32(tb[NFTA_BITWISE_OP])); + switch (priv->op) { + case NFT_BITWISE_BOOL: + case NFT_BITWISE_LSHIFT: + case NFT_BITWISE_RSHIFT: + break; + default: + return -EOPNOTSUPP; + } + } else { + priv->op = NFT_BITWISE_BOOL; + } + + switch(priv->op) { + case NFT_BITWISE_BOOL: + err = nft_bitwise_init_bool(priv, tb); + break; + case NFT_BITWISE_LSHIFT: + case NFT_BITWISE_RSHIFT: + err = nft_bitwise_init_shift(priv, tb); + break; + } + + return err; +} + +static int nft_bitwise_dump_bool(struct sk_buff *skb, + const struct nft_bitwise *priv) +{ if (nft_data_dump(skb, NFTA_BITWISE_MASK, &priv->mask, NFT_DATA_VALUE, priv->len) < 0) - goto nla_put_failure; + return -1; if (nft_data_dump(skb, NFTA_BITWISE_XOR, &priv->xor, NFT_DATA_VALUE, priv->len) < 0) - goto nla_put_failure; + return -1; return 0; +} + +static int nft_bitwise_dump_shift(struct sk_buff *skb, + const struct nft_bitwise *priv) +{ + if (nft_data_dump(skb, NFTA_BITWISE_DATA, &priv->data, + NFT_DATA_VALUE, sizeof(u32)) < 0) + return -1; + return 0; +} + +static int nft_bitwise_dump(struct sk_buff *skb, const struct nft_expr *expr) +{ + const struct nft_bitwise *priv = nft_expr_priv(expr); + int err = 0; + + if (nft_dump_register(skb, NFTA_BITWISE_SREG, priv->sreg)) + return -1; + if (nft_dump_register(skb, NFTA_BITWISE_DREG, priv->dreg)) + return -1; + if (nla_put_be32(skb, NFTA_BITWISE_LEN, htonl(priv->len))) + return -1; + if (nla_put_be32(skb, NFTA_BITWISE_OP, htonl(priv->op))) + return -1; + + switch (priv->op) { + case NFT_BITWISE_BOOL: + err = nft_bitwise_dump_bool(skb, priv); + break; + case NFT_BITWISE_LSHIFT: + case NFT_BITWISE_RSHIFT: + err = nft_bitwise_dump_shift(skb, priv); + break; + } -nla_put_failure: - return -1; + return err; } static struct nft_data zero; static int nft_bitwise_offload(struct nft_offload_ctx *ctx, - struct nft_flow_rule *flow, - const struct nft_expr *expr) + struct nft_flow_rule *flow, + const struct nft_expr *expr) { const struct nft_bitwise *priv = nft_expr_priv(expr); struct nft_offload_reg *reg = &ctx->regs[priv->dreg]; + if (priv->op != NFT_BITWISE_BOOL) + return -EOPNOTSUPP; + if (memcmp(&priv->xor, &zero, sizeof(priv->xor)) || priv->sreg != priv->dreg || priv->len != reg->len) return -EOPNOTSUPP; diff --git a/net/netfilter/nft_dynset.c b/net/netfilter/nft_dynset.c index 8887295414dc..683785225a3e 100644 --- a/net/netfilter/nft_dynset.c +++ b/net/netfilter/nft_dynset.c @@ -54,7 +54,7 @@ static void *nft_dynset_new(struct nft_set *set, const struct nft_expr *expr, timeout = priv->timeout ? : set->timeout; elem = nft_set_elem_init(set, &priv->tmpl, - ®s->data[priv->sreg_key], + ®s->data[priv->sreg_key], NULL, ®s->data[priv->sreg_data], timeout, 0, GFP_ATOMIC); if (elem == NULL) diff --git a/net/netfilter/nft_meta.c b/net/netfilter/nft_meta.c index 9740b554fdb3..951b6e87ed5d 100644 --- a/net/netfilter/nft_meta.c +++ b/net/netfilter/nft_meta.c @@ -17,6 +17,7 @@ #include <linux/smp.h> #include <linux/static_key.h> #include <net/dst.h> +#include <net/ip.h> #include <net/sock.h> #include <net/tcp_states.h> /* for TCP_TIME_WAIT */ #include <net/netfilter/nf_tables.h> @@ -33,8 +34,9 @@ static DEFINE_PER_CPU(struct rnd_state, nft_prandom_state); -static u8 nft_meta_weekday(time64_t secs) +static u8 nft_meta_weekday(void) { + time64_t secs = ktime_get_real_seconds(); unsigned int dse; u8 wday; @@ -56,14 +58,264 @@ static u32 nft_meta_hour(time64_t secs) + tm.tm_sec; } +static noinline_for_stack void +nft_meta_get_eval_time(enum nft_meta_keys key, + u32 *dest) +{ + switch (key) { + case NFT_META_TIME_NS: + nft_reg_store64(dest, ktime_get_real_ns()); + break; + case NFT_META_TIME_DAY: + nft_reg_store8(dest, nft_meta_weekday()); + break; + case NFT_META_TIME_HOUR: + *dest = nft_meta_hour(ktime_get_real_seconds()); + break; + default: + break; + } +} + +static noinline bool +nft_meta_get_eval_pkttype_lo(const struct nft_pktinfo *pkt, + u32 *dest) +{ + const struct sk_buff *skb = pkt->skb; + + switch (nft_pf(pkt)) { + case NFPROTO_IPV4: + if (ipv4_is_multicast(ip_hdr(skb)->daddr)) + nft_reg_store8(dest, PACKET_MULTICAST); + else + nft_reg_store8(dest, PACKET_BROADCAST); + break; + case NFPROTO_IPV6: + nft_reg_store8(dest, PACKET_MULTICAST); + break; + case NFPROTO_NETDEV: + switch (skb->protocol) { + case htons(ETH_P_IP): { + int noff = skb_network_offset(skb); + struct iphdr *iph, _iph; + + iph = skb_header_pointer(skb, noff, + sizeof(_iph), &_iph); + if (!iph) + return false; + + if (ipv4_is_multicast(iph->daddr)) + nft_reg_store8(dest, PACKET_MULTICAST); + else + nft_reg_store8(dest, PACKET_BROADCAST); + + break; + } + case htons(ETH_P_IPV6): + nft_reg_store8(dest, PACKET_MULTICAST); + break; + default: + WARN_ON_ONCE(1); + return false; + } + break; + default: + WARN_ON_ONCE(1); + return false; + } + + return true; +} + +static noinline bool +nft_meta_get_eval_skugid(enum nft_meta_keys key, + u32 *dest, + const struct nft_pktinfo *pkt) +{ + struct sock *sk = skb_to_full_sk(pkt->skb); + struct socket *sock; + + if (!sk || !sk_fullsock(sk) || !net_eq(nft_net(pkt), sock_net(sk))) + return false; + + read_lock_bh(&sk->sk_callback_lock); + sock = sk->sk_socket; + if (!sock || !sock->file) { + read_unlock_bh(&sk->sk_callback_lock); + return false; + } + + switch (key) { + case NFT_META_SKUID: + *dest = from_kuid_munged(&init_user_ns, + sock->file->f_cred->fsuid); + break; + case NFT_META_SKGID: + *dest = from_kgid_munged(&init_user_ns, + sock->file->f_cred->fsgid); + break; + default: + break; + } + + read_unlock_bh(&sk->sk_callback_lock); + return true; +} + +#ifdef CONFIG_CGROUP_NET_CLASSID +static noinline bool +nft_meta_get_eval_cgroup(u32 *dest, const struct nft_pktinfo *pkt) +{ + struct sock *sk = skb_to_full_sk(pkt->skb); + + if (!sk || !sk_fullsock(sk) || !net_eq(nft_net(pkt), sock_net(sk))) + return false; + + *dest = sock_cgroup_classid(&sk->sk_cgrp_data); + return true; +} +#endif + +static noinline bool nft_meta_get_eval_kind(enum nft_meta_keys key, + u32 *dest, + const struct nft_pktinfo *pkt) +{ + const struct net_device *in = nft_in(pkt), *out = nft_out(pkt); + + switch (key) { + case NFT_META_IIFKIND: + if (!in || !in->rtnl_link_ops) + return false; + strncpy((char *)dest, in->rtnl_link_ops->kind, IFNAMSIZ); + break; + case NFT_META_OIFKIND: + if (!out || !out->rtnl_link_ops) + return false; + strncpy((char *)dest, out->rtnl_link_ops->kind, IFNAMSIZ); + break; + default: + return false; + } + + return true; +} + +static void nft_meta_store_ifindex(u32 *dest, const struct net_device *dev) +{ + *dest = dev ? dev->ifindex : 0; +} + +static void nft_meta_store_ifname(u32 *dest, const struct net_device *dev) +{ + strncpy((char *)dest, dev ? dev->name : "", IFNAMSIZ); +} + +static bool nft_meta_store_iftype(u32 *dest, const struct net_device *dev) +{ + if (!dev) + return false; + + nft_reg_store16(dest, dev->type); + return true; +} + +static bool nft_meta_store_ifgroup(u32 *dest, const struct net_device *dev) +{ + if (!dev) + return false; + + *dest = dev->group; + return true; +} + +static bool nft_meta_get_eval_ifname(enum nft_meta_keys key, u32 *dest, + const struct nft_pktinfo *pkt) +{ + switch (key) { + case NFT_META_IIFNAME: + nft_meta_store_ifname(dest, nft_in(pkt)); + break; + case NFT_META_OIFNAME: + nft_meta_store_ifname(dest, nft_out(pkt)); + break; + case NFT_META_IIF: + nft_meta_store_ifindex(dest, nft_in(pkt)); + break; + case NFT_META_OIF: + nft_meta_store_ifindex(dest, nft_out(pkt)); + break; + case NFT_META_IIFTYPE: + if (!nft_meta_store_iftype(dest, nft_in(pkt))) + return false; + break; + case NFT_META_OIFTYPE: + if (!nft_meta_store_iftype(dest, nft_out(pkt))) + return false; + break; + case NFT_META_IIFGROUP: + if (!nft_meta_store_ifgroup(dest, nft_out(pkt))) + return false; + break; + case NFT_META_OIFGROUP: + if (!nft_meta_store_ifgroup(dest, nft_out(pkt))) + return false; + break; + default: + return false; + } + + return true; +} + +static noinline u32 nft_prandom_u32(void) +{ + struct rnd_state *state = this_cpu_ptr(&nft_prandom_state); + + return prandom_u32_state(state); +} + +#ifdef CONFIG_IP_ROUTE_CLASSID +static noinline bool +nft_meta_get_eval_rtclassid(const struct sk_buff *skb, u32 *dest) +{ + const struct dst_entry *dst = skb_dst(skb); + + if (!dst) + return false; + + *dest = dst->tclassid; + return true; +} +#endif + +static noinline u32 nft_meta_get_eval_sdif(const struct nft_pktinfo *pkt) +{ + switch (nft_pf(pkt)) { + case NFPROTO_IPV4: + return inet_sdif(pkt->skb); + case NFPROTO_IPV6: + return inet6_sdif(pkt->skb); + } + + return 0; +} + +static noinline void +nft_meta_get_eval_sdifname(u32 *dest, const struct nft_pktinfo *pkt) +{ + u32 sdif = nft_meta_get_eval_sdif(pkt); + const struct net_device *dev; + + dev = sdif ? dev_get_by_index_rcu(nft_net(pkt), sdif) : NULL; + nft_meta_store_ifname(dest, dev); +} + void nft_meta_get_eval(const struct nft_expr *expr, struct nft_regs *regs, const struct nft_pktinfo *pkt) { const struct nft_meta *priv = nft_expr_priv(expr); const struct sk_buff *skb = pkt->skb; - const struct net_device *in = nft_in(pkt), *out = nft_out(pkt); - struct sock *sk; u32 *dest = ®s->data[priv->dreg]; switch (priv->key) { @@ -88,69 +340,26 @@ void nft_meta_get_eval(const struct nft_expr *expr, *dest = skb->mark; break; case NFT_META_IIF: - *dest = in ? in->ifindex : 0; - break; case NFT_META_OIF: - *dest = out ? out->ifindex : 0; - break; case NFT_META_IIFNAME: - strncpy((char *)dest, in ? in->name : "", IFNAMSIZ); - break; case NFT_META_OIFNAME: - strncpy((char *)dest, out ? out->name : "", IFNAMSIZ); - break; case NFT_META_IIFTYPE: - if (in == NULL) - goto err; - nft_reg_store16(dest, in->type); - break; case NFT_META_OIFTYPE: - if (out == NULL) + case NFT_META_IIFGROUP: + case NFT_META_OIFGROUP: + if (!nft_meta_get_eval_ifname(priv->key, dest, pkt)) goto err; - nft_reg_store16(dest, out->type); break; case NFT_META_SKUID: - sk = skb_to_full_sk(skb); - if (!sk || !sk_fullsock(sk) || - !net_eq(nft_net(pkt), sock_net(sk))) - goto err; - - read_lock_bh(&sk->sk_callback_lock); - if (sk->sk_socket == NULL || - sk->sk_socket->file == NULL) { - read_unlock_bh(&sk->sk_callback_lock); - goto err; - } - - *dest = from_kuid_munged(&init_user_ns, - sk->sk_socket->file->f_cred->fsuid); - read_unlock_bh(&sk->sk_callback_lock); - break; case NFT_META_SKGID: - sk = skb_to_full_sk(skb); - if (!sk || !sk_fullsock(sk) || - !net_eq(nft_net(pkt), sock_net(sk))) + if (!nft_meta_get_eval_skugid(priv->key, dest, pkt)) goto err; - - read_lock_bh(&sk->sk_callback_lock); - if (sk->sk_socket == NULL || - sk->sk_socket->file == NULL) { - read_unlock_bh(&sk->sk_callback_lock); - goto err; - } - *dest = from_kgid_munged(&init_user_ns, - sk->sk_socket->file->f_cred->fsgid); - read_unlock_bh(&sk->sk_callback_lock); break; #ifdef CONFIG_IP_ROUTE_CLASSID - case NFT_META_RTCLASSID: { - const struct dst_entry *dst = skb_dst(skb); - - if (dst == NULL) + case NFT_META_RTCLASSID: + if (!nft_meta_get_eval_rtclassid(skb, dest)) goto err; - *dest = dst->tclassid; break; - } #endif #ifdef CONFIG_NETWORK_SECMARK case NFT_META_SECMARK: @@ -163,97 +372,41 @@ void nft_meta_get_eval(const struct nft_expr *expr, break; } - switch (nft_pf(pkt)) { - case NFPROTO_IPV4: - if (ipv4_is_multicast(ip_hdr(skb)->daddr)) - nft_reg_store8(dest, PACKET_MULTICAST); - else - nft_reg_store8(dest, PACKET_BROADCAST); - break; - case NFPROTO_IPV6: - nft_reg_store8(dest, PACKET_MULTICAST); - break; - case NFPROTO_NETDEV: - switch (skb->protocol) { - case htons(ETH_P_IP): { - int noff = skb_network_offset(skb); - struct iphdr *iph, _iph; - - iph = skb_header_pointer(skb, noff, - sizeof(_iph), &_iph); - if (!iph) - goto err; - - if (ipv4_is_multicast(iph->daddr)) - nft_reg_store8(dest, PACKET_MULTICAST); - else - nft_reg_store8(dest, PACKET_BROADCAST); - - break; - } - case htons(ETH_P_IPV6): - nft_reg_store8(dest, PACKET_MULTICAST); - break; - default: - WARN_ON_ONCE(1); - goto err; - } - break; - default: - WARN_ON_ONCE(1); + if (!nft_meta_get_eval_pkttype_lo(pkt, dest)) goto err; - } break; case NFT_META_CPU: *dest = raw_smp_processor_id(); break; - case NFT_META_IIFGROUP: - if (in == NULL) - goto err; - *dest = in->group; - break; - case NFT_META_OIFGROUP: - if (out == NULL) - goto err; - *dest = out->group; - break; #ifdef CONFIG_CGROUP_NET_CLASSID case NFT_META_CGROUP: - sk = skb_to_full_sk(skb); - if (!sk || !sk_fullsock(sk) || - !net_eq(nft_net(pkt), sock_net(sk))) + if (!nft_meta_get_eval_cgroup(dest, pkt)) goto err; - *dest = sock_cgroup_classid(&sk->sk_cgrp_data); break; #endif - case NFT_META_PRANDOM: { - struct rnd_state *state = this_cpu_ptr(&nft_prandom_state); - *dest = prandom_u32_state(state); + case NFT_META_PRANDOM: + *dest = nft_prandom_u32(); break; - } #ifdef CONFIG_XFRM case NFT_META_SECPATH: nft_reg_store8(dest, secpath_exists(skb)); break; #endif case NFT_META_IIFKIND: - if (in == NULL || in->rtnl_link_ops == NULL) - goto err; - strncpy((char *)dest, in->rtnl_link_ops->kind, IFNAMSIZ); - break; case NFT_META_OIFKIND: - if (out == NULL || out->rtnl_link_ops == NULL) + if (!nft_meta_get_eval_kind(priv->key, dest, pkt)) goto err; - strncpy((char *)dest, out->rtnl_link_ops->kind, IFNAMSIZ); break; case NFT_META_TIME_NS: - nft_reg_store64(dest, ktime_get_real_ns()); - break; case NFT_META_TIME_DAY: - nft_reg_store8(dest, nft_meta_weekday(ktime_get_real_seconds())); - break; case NFT_META_TIME_HOUR: - *dest = nft_meta_hour(ktime_get_real_seconds()); + nft_meta_get_eval_time(priv->key, dest); + break; + case NFT_META_SDIF: + *dest = nft_meta_get_eval_sdif(pkt); + break; + case NFT_META_SDIFNAME: + nft_meta_get_eval_sdifname(dest, pkt); break; default: WARN_ON(1); @@ -335,6 +488,7 @@ int nft_meta_get_init(const struct nft_ctx *ctx, case NFT_META_MARK: case NFT_META_IIF: case NFT_META_OIF: + case NFT_META_SDIF: case NFT_META_SKUID: case NFT_META_SKGID: #ifdef CONFIG_IP_ROUTE_CLASSID @@ -356,6 +510,7 @@ int nft_meta_get_init(const struct nft_ctx *ctx, case NFT_META_OIFNAME: case NFT_META_IIFKIND: case NFT_META_OIFKIND: + case NFT_META_SDIFNAME: len = IFNAMSIZ; break; case NFT_META_PRANDOM: @@ -386,16 +541,28 @@ int nft_meta_get_init(const struct nft_ctx *ctx, } EXPORT_SYMBOL_GPL(nft_meta_get_init); -static int nft_meta_get_validate(const struct nft_ctx *ctx, - const struct nft_expr *expr, - const struct nft_data **data) +static int nft_meta_get_validate_sdif(const struct nft_ctx *ctx) { -#ifdef CONFIG_XFRM - const struct nft_meta *priv = nft_expr_priv(expr); unsigned int hooks; - if (priv->key != NFT_META_SECPATH) - return 0; + switch (ctx->family) { + case NFPROTO_IPV4: + case NFPROTO_IPV6: + case NFPROTO_INET: + hooks = (1 << NF_INET_LOCAL_IN) | + (1 << NF_INET_FORWARD); + break; + default: + return -EOPNOTSUPP; + } + + return nft_chain_validate_hooks(ctx->chain, hooks); +} + +static int nft_meta_get_validate_xfrm(const struct nft_ctx *ctx) +{ +#ifdef CONFIG_XFRM + unsigned int hooks; switch (ctx->family) { case NFPROTO_NETDEV: @@ -418,6 +585,25 @@ static int nft_meta_get_validate(const struct nft_ctx *ctx, #endif } +static int nft_meta_get_validate(const struct nft_ctx *ctx, + const struct nft_expr *expr, + const struct nft_data **data) +{ + const struct nft_meta *priv = nft_expr_priv(expr); + + switch (priv->key) { + case NFT_META_SECPATH: + return nft_meta_get_validate_xfrm(ctx); + case NFT_META_SDIF: + case NFT_META_SDIFNAME: + return nft_meta_get_validate_sdif(ctx); + default: + break; + } + + return 0; +} + int nft_meta_set_validate(const struct nft_ctx *ctx, const struct nft_expr *expr, const struct nft_data **data) diff --git a/net/netfilter/nft_set_bitmap.c b/net/netfilter/nft_set_bitmap.c index 087a056e34d1..87e8d9ba0c9b 100644 --- a/net/netfilter/nft_set_bitmap.c +++ b/net/netfilter/nft_set_bitmap.c @@ -259,8 +259,8 @@ static u64 nft_bitmap_privsize(const struct nlattr * const nla[], } static int nft_bitmap_init(const struct nft_set *set, - const struct nft_set_desc *desc, - const struct nlattr * const nla[]) + const struct nft_set_desc *desc, + const struct nlattr * const nla[]) { struct nft_bitmap *priv = nft_set_priv(set); diff --git a/net/netfilter/nft_set_hash.c b/net/netfilter/nft_set_hash.c index b331a3c9a3a8..d350a7cd3af0 100644 --- a/net/netfilter/nft_set_hash.c +++ b/net/netfilter/nft_set_hash.c @@ -645,7 +645,7 @@ static bool nft_hash_estimate(const struct nft_set_desc *desc, u32 features, } static bool nft_hash_fast_estimate(const struct nft_set_desc *desc, u32 features, - struct nft_set_estimate *est) + struct nft_set_estimate *est) { if (!desc->size) return false; diff --git a/net/netfilter/nft_set_pipapo.c b/net/netfilter/nft_set_pipapo.c new file mode 100644 index 000000000000..f0cb1e13af50 --- /dev/null +++ b/net/netfilter/nft_set_pipapo.c @@ -0,0 +1,2102 @@ +// SPDX-License-Identifier: GPL-2.0-only + +/* PIPAPO: PIle PAcket POlicies: set for arbitrary concatenations of ranges + * + * Copyright (c) 2019-2020 Red Hat GmbH + * + * Author: Stefano Brivio <sbrivio@redhat.com> + */ + +/** + * DOC: Theory of Operation + * + * + * Problem + * ------- + * + * Match packet bytes against entries composed of ranged or non-ranged packet + * field specifiers, mapping them to arbitrary references. For example: + * + * :: + * + * --- fields ---> + * | [net],[port],[net]... => [reference] + * entries [net],[port],[net]... => [reference] + * | [net],[port],[net]... => [reference] + * V ... + * + * where [net] fields can be IP ranges or netmasks, and [port] fields are port + * ranges. Arbitrary packet fields can be matched. + * + * + * Algorithm Overview + * ------------------ + * + * This algorithm is loosely inspired by [Ligatti 2010], and fundamentally + * relies on the consideration that every contiguous range in a space of b bits + * can be converted into b * 2 netmasks, from Theorem 3 in [Rottenstreich 2010], + * as also illustrated in Section 9 of [Kogan 2014]. + * + * Classification against a number of entries, that require matching given bits + * of a packet field, is performed by grouping those bits in sets of arbitrary + * size, and classifying packet bits one group at a time. + * + * Example: + * to match the source port (16 bits) of a packet, we can divide those 16 bits + * in 4 groups of 4 bits each. Given the entry: + * 0000 0001 0101 1001 + * and a packet with source port: + * 0000 0001 1010 1001 + * first and second groups match, but the third doesn't. We conclude that the + * packet doesn't match the given entry. + * + * Translate the set to a sequence of lookup tables, one per field. Each table + * has two dimensions: bit groups to be matched for a single packet field, and + * all the possible values of said groups (buckets). Input entries are + * represented as one or more rules, depending on the number of composing + * netmasks for the given field specifier, and a group match is indicated as a + * set bit, with number corresponding to the rule index, in all the buckets + * whose value matches the entry for a given group. + * + * Rules are mapped between fields through an array of x, n pairs, with each + * item mapping a matched rule to one or more rules. The position of the pair in + * the array indicates the matched rule to be mapped to the next field, x + * indicates the first rule index in the next field, and n the amount of + * next-field rules the current rule maps to. + * + * The mapping array for the last field maps to the desired references. + * + * To match, we perform table lookups using the values of grouped packet bits, + * and use a sequence of bitwise operations to progressively evaluate rule + * matching. + * + * A stand-alone, reference implementation, also including notes about possible + * future optimisations, is available at: + * https://pipapo.lameexcu.se/ + * + * Insertion + * --------- + * + * - For each packet field: + * + * - divide the b packet bits we want to classify into groups of size t, + * obtaining ceil(b / t) groups + * + * Example: match on destination IP address, with t = 4: 32 bits, 8 groups + * of 4 bits each + * + * - allocate a lookup table with one column ("bucket") for each possible + * value of a group, and with one row for each group + * + * Example: 8 groups, 2^4 buckets: + * + * :: + * + * bucket + * group 0 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 + * 0 + * 1 + * 2 + * 3 + * 4 + * 5 + * 6 + * 7 + * + * - map the bits we want to classify for the current field, for a given + * entry, to a single rule for non-ranged and netmask set items, and to one + * or multiple rules for ranges. Ranges are expanded to composing netmasks + * by pipapo_expand(). + * + * Example: 2 entries, 10.0.0.5:1024 and 192.168.1.0-192.168.2.1:2048 + * - rule #0: 10.0.0.5 + * - rule #1: 192.168.1.0/24 + * - rule #2: 192.168.2.0/31 + * + * - insert references to the rules in the lookup table, selecting buckets + * according to bit values of a rule in the given group. This is done by + * pipapo_insert(). + * + * Example: given: + * - rule #0: 10.0.0.5 mapping to buckets + * < 0 10 0 0 0 0 0 5 > + * - rule #1: 192.168.1.0/24 mapping to buckets + * < 12 0 10 8 0 1 < 0..15 > < 0..15 > > + * - rule #2: 192.168.2.0/31 mapping to buckets + * < 12 0 10 8 0 2 0 < 0..1 > > + * + * these bits are set in the lookup table: + * + * :: + * + * bucket + * group 0 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 + * 0 0 1,2 + * 1 1,2 0 + * 2 0 1,2 + * 3 0 1,2 + * 4 0,1,2 + * 5 0 1 2 + * 6 0,1,2 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 + * 7 1,2 1,2 1 1 1 0,1 1 1 1 1 1 1 1 1 1 1 + * + * - if this is not the last field in the set, fill a mapping array that maps + * rules from the lookup table to rules belonging to the same entry in + * the next lookup table, done by pipapo_map(). + * + * Note that as rules map to contiguous ranges of rules, given how netmask + * expansion and insertion is performed, &union nft_pipapo_map_bucket stores + * this information as pairs of first rule index, rule count. + * + * Example: 2 entries, 10.0.0.5:1024 and 192.168.1.0-192.168.2.1:2048, + * given lookup table #0 for field 0 (see example above): + * + * :: + * + * bucket + * group 0 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 + * 0 0 1,2 + * 1 1,2 0 + * 2 0 1,2 + * 3 0 1,2 + * 4 0,1,2 + * 5 0 1 2 + * 6 0,1,2 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 + * 7 1,2 1,2 1 1 1 0,1 1 1 1 1 1 1 1 1 1 1 + * + * and lookup table #1 for field 1 with: + * - rule #0: 1024 mapping to buckets + * < 0 0 4 0 > + * - rule #1: 2048 mapping to buckets + * < 0 0 5 0 > + * + * :: + * + * bucket + * group 0 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 + * 0 0,1 + * 1 0,1 + * 2 0 1 + * 3 0,1 + * + * we need to map rules for 10.0.0.5 in lookup table #0 (rule #0) to 1024 + * in lookup table #1 (rule #0) and rules for 192.168.1.0-192.168.2.1 + * (rules #1, #2) to 2048 in lookup table #2 (rule #1): + * + * :: + * + * rule indices in current field: 0 1 2 + * map to rules in next field: 0 1 1 + * + * - if this is the last field in the set, fill a mapping array that maps + * rules from the last lookup table to element pointers, also done by + * pipapo_map(). + * + * Note that, in this implementation, we have two elements (start, end) for + * each entry. The pointer to the end element is stored in this array, and + * the pointer to the start element is linked from it. + * + * Example: entry 10.0.0.5:1024 has a corresponding &struct nft_pipapo_elem + * pointer, 0x66, and element for 192.168.1.0-192.168.2.1:2048 is at 0x42. + * From the rules of lookup table #1 as mapped above: + * + * :: + * + * rule indices in last field: 0 1 + * map to elements: 0x42 0x66 + * + * + * Matching + * -------- + * + * We use a result bitmap, with the size of a single lookup table bucket, to + * represent the matching state that applies at every algorithm step. This is + * done by pipapo_lookup(). + * + * - For each packet field: + * + * - start with an all-ones result bitmap (res_map in pipapo_lookup()) + * + * - perform a lookup into the table corresponding to the current field, + * for each group, and at every group, AND the current result bitmap with + * the value from the lookup table bucket + * + * :: + * + * Example: 192.168.1.5 < 12 0 10 8 0 1 0 5 >, with lookup table from + * insertion examples. + * Lookup table buckets are at least 3 bits wide, we'll assume 8 bits for + * convenience in this example. Initial result bitmap is 0xff, the steps + * below show the value of the result bitmap after each group is processed: + * + * bucket + * group 0 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 + * 0 0 1,2 + * result bitmap is now: 0xff & 0x6 [bucket 12] = 0x6 + * + * 1 1,2 0 + * result bitmap is now: 0x6 & 0x6 [bucket 0] = 0x6 + * + * 2 0 1,2 + * result bitmap is now: 0x6 & 0x6 [bucket 10] = 0x6 + * + * 3 0 1,2 + * result bitmap is now: 0x6 & 0x6 [bucket 8] = 0x6 + * + * 4 0,1,2 + * result bitmap is now: 0x6 & 0x7 [bucket 0] = 0x6 + * + * 5 0 1 2 + * result bitmap is now: 0x6 & 0x2 [bucket 1] = 0x2 + * + * 6 0,1,2 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 + * result bitmap is now: 0x2 & 0x7 [bucket 0] = 0x2 + * + * 7 1,2 1,2 1 1 1 0,1 1 1 1 1 1 1 1 1 1 1 + * final result bitmap for this field is: 0x2 & 0x3 [bucket 5] = 0x2 + * + * - at the next field, start with a new, all-zeroes result bitmap. For each + * bit set in the previous result bitmap, fill the new result bitmap + * (fill_map in pipapo_lookup()) with the rule indices from the + * corresponding buckets of the mapping field for this field, done by + * pipapo_refill() + * + * Example: with mapping table from insertion examples, with the current + * result bitmap from the previous example, 0x02: + * + * :: + * + * rule indices in current field: 0 1 2 + * map to rules in next field: 0 1 1 + * + * the new result bitmap will be 0x02: rule 1 was set, and rule 1 will be + * set. + * + * We can now extend this example to cover the second iteration of the step + * above (lookup and AND bitmap): assuming the port field is + * 2048 < 0 0 5 0 >, with starting result bitmap 0x2, and lookup table + * for "port" field from pre-computation example: + * + * :: + * + * bucket + * group 0 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 + * 0 0,1 + * 1 0,1 + * 2 0 1 + * 3 0,1 + * + * operations are: 0x2 & 0x3 [bucket 0] & 0x3 [bucket 0] & 0x2 [bucket 5] + * & 0x3 [bucket 0], resulting bitmap is 0x2. + * + * - if this is the last field in the set, look up the value from the mapping + * array corresponding to the final result bitmap + * + * Example: 0x2 resulting bitmap from 192.168.1.5:2048, mapping array for + * last field from insertion example: + * + * :: + * + * rule indices in last field: 0 1 + * map to elements: 0x42 0x66 + * + * the matching element is at 0x42. + * + * + * References + * ---------- + * + * [Ligatti 2010] + * A Packet-classification Algorithm for Arbitrary Bitmask Rules, with + * Automatic Time-space Tradeoffs + * Jay Ligatti, Josh Kuhn, and Chris Gage. + * Proceedings of the IEEE International Conference on Computer + * Communication Networks (ICCCN), August 2010. + * http://www.cse.usf.edu/~ligatti/papers/grouper-conf.pdf + * + * [Rottenstreich 2010] + * Worst-Case TCAM Rule Expansion + * Ori Rottenstreich and Isaac Keslassy. + * 2010 Proceedings IEEE INFOCOM, San Diego, CA, 2010. + * http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.212.4592&rep=rep1&type=pdf + * + * [Kogan 2014] + * SAX-PAC (Scalable And eXpressive PAcket Classification) + * Kirill Kogan, Sergey Nikolenko, Ori Rottenstreich, William Culhane, + * and Patrick Eugster. + * Proceedings of the 2014 ACM conference on SIGCOMM, August 2014. + * http://www.sigcomm.org/sites/default/files/ccr/papers/2014/August/2619239-2626294.pdf + */ + +#include <linux/kernel.h> +#include <linux/init.h> +#include <linux/log2.h> +#include <linux/module.h> +#include <linux/netlink.h> +#include <linux/netfilter.h> +#include <linux/netfilter/nf_tables.h> +#include <net/netfilter/nf_tables_core.h> +#include <uapi/linux/netfilter/nf_tables.h> +#include <net/ipv6.h> /* For the maximum length of a field */ +#include <linux/bitmap.h> +#include <linux/bitops.h> + +/* Count of concatenated fields depends on count of 32-bit nftables registers */ +#define NFT_PIPAPO_MAX_FIELDS NFT_REG32_COUNT + +/* Largest supported field size */ +#define NFT_PIPAPO_MAX_BYTES (sizeof(struct in6_addr)) +#define NFT_PIPAPO_MAX_BITS (NFT_PIPAPO_MAX_BYTES * BITS_PER_BYTE) + +/* Number of bits to be grouped together in lookup table buckets, arbitrary */ +#define NFT_PIPAPO_GROUP_BITS 4 +#define NFT_PIPAPO_GROUPS_PER_BYTE (BITS_PER_BYTE / NFT_PIPAPO_GROUP_BITS) + +/* Fields are padded to 32 bits in input registers */ +#define NFT_PIPAPO_GROUPS_PADDED_SIZE(x) \ + (round_up((x) / NFT_PIPAPO_GROUPS_PER_BYTE, sizeof(u32))) +#define NFT_PIPAPO_GROUPS_PADDING(x) \ + (NFT_PIPAPO_GROUPS_PADDED_SIZE((x)) - (x) / NFT_PIPAPO_GROUPS_PER_BYTE) + +/* Number of buckets, given by 2 ^ n, with n grouped bits */ +#define NFT_PIPAPO_BUCKETS (1 << NFT_PIPAPO_GROUP_BITS) + +/* Each n-bit range maps to up to n * 2 rules */ +#define NFT_PIPAPO_MAP_NBITS (const_ilog2(NFT_PIPAPO_MAX_BITS * 2)) + +/* Use the rest of mapping table buckets for rule indices, but it makes no sense + * to exceed 32 bits + */ +#if BITS_PER_LONG == 64 +#define NFT_PIPAPO_MAP_TOBITS 32 +#else +#define NFT_PIPAPO_MAP_TOBITS (BITS_PER_LONG - NFT_PIPAPO_MAP_NBITS) +#endif + +/* ...which gives us the highest allowed index for a rule */ +#define NFT_PIPAPO_RULE0_MAX ((1UL << (NFT_PIPAPO_MAP_TOBITS - 1)) \ + - (1UL << NFT_PIPAPO_MAP_NBITS)) + +#define nft_pipapo_for_each_field(field, index, match) \ + for ((field) = (match)->f, (index) = 0; \ + (index) < (match)->field_count; \ + (index)++, (field)++) + +/** + * union nft_pipapo_map_bucket - Bucket of mapping table + * @to: First rule number (in next field) this rule maps to + * @n: Number of rules (in next field) this rule maps to + * @e: If there's no next field, pointer to element this rule maps to + */ +union nft_pipapo_map_bucket { + struct { +#if BITS_PER_LONG == 64 + static_assert(NFT_PIPAPO_MAP_TOBITS <= 32); + u32 to; + + static_assert(NFT_PIPAPO_MAP_NBITS <= 32); + u32 n; +#else + unsigned long to:NFT_PIPAPO_MAP_TOBITS; + unsigned long n:NFT_PIPAPO_MAP_NBITS; +#endif + }; + struct nft_pipapo_elem *e; +}; + +/** + * struct nft_pipapo_field - Lookup, mapping tables and related data for a field + * @groups: Amount of 4-bit groups + * @rules: Number of inserted rules + * @bsize: Size of each bucket in lookup table, in longs + * @lt: Lookup table: 'groups' rows of NFT_PIPAPO_BUCKETS buckets + * @mt: Mapping table: one bucket per rule + */ +struct nft_pipapo_field { + int groups; + unsigned long rules; + size_t bsize; + unsigned long *lt; + union nft_pipapo_map_bucket *mt; +}; + +/** + * struct nft_pipapo_match - Data used for lookup and matching + * @field_count Amount of fields in set + * @scratch: Preallocated per-CPU maps for partial matching results + * @bsize_max: Maximum lookup table bucket size of all fields, in longs + * @rcu Matching data is swapped on commits + * @f: Fields, with lookup and mapping tables + */ +struct nft_pipapo_match { + int field_count; + unsigned long * __percpu *scratch; + size_t bsize_max; + struct rcu_head rcu; + struct nft_pipapo_field f[0]; +}; + +/* Current working bitmap index, toggled between field matches */ +static DEFINE_PER_CPU(bool, nft_pipapo_scratch_index); + +/** + * struct nft_pipapo - Representation of a set + * @match: Currently in-use matching data + * @clone: Copy where pending insertions and deletions are kept + * @groups: Total amount of 4-bit groups for fields in this set + * @width: Total bytes to be matched for one packet, including padding + * @dirty: Working copy has pending insertions or deletions + * @last_gc: Timestamp of last garbage collection run, jiffies + */ +struct nft_pipapo { + struct nft_pipapo_match __rcu *match; + struct nft_pipapo_match *clone; + int groups; + int width; + bool dirty; + unsigned long last_gc; +}; + +struct nft_pipapo_elem; + +/** + * struct nft_pipapo_elem - API-facing representation of single set element + * @ext: nftables API extensions + */ +struct nft_pipapo_elem { + struct nft_set_ext ext; +}; + +/** + * pipapo_refill() - For each set bit, set bits from selected mapping table item + * @map: Bitmap to be scanned for set bits + * @len: Length of bitmap in longs + * @rules: Number of rules in field + * @dst: Destination bitmap + * @mt: Mapping table containing bit set specifiers + * @match_only: Find a single bit and return, don't fill + * + * Iteration over set bits with __builtin_ctzl(): Daniel Lemire, public domain. + * + * For each bit set in map, select the bucket from mapping table with index + * corresponding to the position of the bit set. Use start bit and amount of + * bits specified in bucket to fill region in dst. + * + * Return: -1 on no match, bit position on 'match_only', 0 otherwise. + */ +static int pipapo_refill(unsigned long *map, int len, int rules, + unsigned long *dst, union nft_pipapo_map_bucket *mt, + bool match_only) +{ + unsigned long bitset; + int k, ret = -1; + + for (k = 0; k < len; k++) { + bitset = map[k]; + while (bitset) { + unsigned long t = bitset & -bitset; + int r = __builtin_ctzl(bitset); + int i = k * BITS_PER_LONG + r; + + if (unlikely(i >= rules)) { + map[k] = 0; + return -1; + } + + if (unlikely(match_only)) { + bitmap_clear(map, i, 1); + return i; + } + + ret = 0; + + bitmap_set(dst, mt[i].to, mt[i].n); + + bitset ^= t; + } + map[k] = 0; + } + + return ret; +} + +/** + * nft_pipapo_lookup() - Lookup function + * @net: Network namespace + * @set: nftables API set representation + * @elem: nftables API element representation containing key data + * @ext: nftables API extension pointer, filled with matching reference + * + * For more details, see DOC: Theory of Operation. + * + * Return: true on match, false otherwise. + */ +static bool nft_pipapo_lookup(const struct net *net, const struct nft_set *set, + const u32 *key, const struct nft_set_ext **ext) +{ + struct nft_pipapo *priv = nft_set_priv(set); + unsigned long *res_map, *fill_map; + u8 genmask = nft_genmask_cur(net); + const u8 *rp = (const u8 *)key; + struct nft_pipapo_match *m; + struct nft_pipapo_field *f; + bool map_index; + int i; + + local_bh_disable(); + + map_index = raw_cpu_read(nft_pipapo_scratch_index); + + m = rcu_dereference(priv->match); + + if (unlikely(!m || !*raw_cpu_ptr(m->scratch))) + goto out; + + res_map = *raw_cpu_ptr(m->scratch) + (map_index ? m->bsize_max : 0); + fill_map = *raw_cpu_ptr(m->scratch) + (map_index ? 0 : m->bsize_max); + + memset(res_map, 0xff, m->bsize_max * sizeof(*res_map)); + + nft_pipapo_for_each_field(f, i, m) { + bool last = i == m->field_count - 1; + unsigned long *lt = f->lt; + int b, group; + + /* For each 4-bit group: select lookup table bucket depending on + * packet bytes value, then AND bucket value + */ + for (group = 0; group < f->groups; group += 2) { + u8 v; + + v = *rp >> 4; + __bitmap_and(res_map, res_map, lt + v * f->bsize, + f->bsize * BITS_PER_LONG); + lt += f->bsize * NFT_PIPAPO_BUCKETS; + + v = *rp & 0x0f; + rp++; + __bitmap_and(res_map, res_map, lt + v * f->bsize, + f->bsize * BITS_PER_LONG); + lt += f->bsize * NFT_PIPAPO_BUCKETS; + } + + /* Now populate the bitmap for the next field, unless this is + * the last field, in which case return the matched 'ext' + * pointer if any. + * + * Now res_map contains the matching bitmap, and fill_map is the + * bitmap for the next field. + */ +next_match: + b = pipapo_refill(res_map, f->bsize, f->rules, fill_map, f->mt, + last); + if (b < 0) { + raw_cpu_write(nft_pipapo_scratch_index, map_index); + local_bh_enable(); + + return false; + } + + if (last) { + *ext = &f->mt[b].e->ext; + if (unlikely(nft_set_elem_expired(*ext) || + !nft_set_elem_active(*ext, genmask))) + goto next_match; + + /* Last field: we're just returning the key without + * filling the initial bitmap for the next field, so the + * current inactive bitmap is clean and can be reused as + * *next* bitmap (not initial) for the next packet. + */ + raw_cpu_write(nft_pipapo_scratch_index, map_index); + local_bh_enable(); + + return true; + } + + /* Swap bitmap indices: res_map is the initial bitmap for the + * next field, and fill_map is guaranteed to be all-zeroes at + * this point. + */ + map_index = !map_index; + swap(res_map, fill_map); + + rp += NFT_PIPAPO_GROUPS_PADDING(f->groups); + } + +out: + local_bh_enable(); + return false; +} + +/** + * pipapo_get() - Get matching element reference given key data + * @net: Network namespace + * @set: nftables API set representation + * @data: Key data to be matched against existing elements + * @genmask: If set, check that element is active in given genmask + * + * This is essentially the same as the lookup function, except that it matches + * key data against the uncommitted copy and doesn't use preallocated maps for + * bitmap results. + * + * Return: pointer to &struct nft_pipapo_elem on match, error pointer otherwise. + */ +static struct nft_pipapo_elem *pipapo_get(const struct net *net, + const struct nft_set *set, + const u8 *data, u8 genmask) +{ + struct nft_pipapo_elem *ret = ERR_PTR(-ENOENT); + struct nft_pipapo *priv = nft_set_priv(set); + struct nft_pipapo_match *m = priv->clone; + unsigned long *res_map, *fill_map = NULL; + struct nft_pipapo_field *f; + int i; + + res_map = kmalloc_array(m->bsize_max, sizeof(*res_map), GFP_ATOMIC); + if (!res_map) { + ret = ERR_PTR(-ENOMEM); + goto out; + } + + fill_map = kcalloc(m->bsize_max, sizeof(*res_map), GFP_ATOMIC); + if (!fill_map) { + ret = ERR_PTR(-ENOMEM); + goto out; + } + + memset(res_map, 0xff, m->bsize_max * sizeof(*res_map)); + + nft_pipapo_for_each_field(f, i, m) { + bool last = i == m->field_count - 1; + unsigned long *lt = f->lt; + int b, group; + + /* For each 4-bit group: select lookup table bucket depending on + * packet bytes value, then AND bucket value + */ + for (group = 0; group < f->groups; group++) { + u8 v; + + if (group % 2) { + v = *data & 0x0f; + data++; + } else { + v = *data >> 4; + } + __bitmap_and(res_map, res_map, lt + v * f->bsize, + f->bsize * BITS_PER_LONG); + + lt += f->bsize * NFT_PIPAPO_BUCKETS; + } + + /* Now populate the bitmap for the next field, unless this is + * the last field, in which case return the matched 'ext' + * pointer if any. + * + * Now res_map contains the matching bitmap, and fill_map is the + * bitmap for the next field. + */ +next_match: + b = pipapo_refill(res_map, f->bsize, f->rules, fill_map, f->mt, + last); + if (b < 0) + goto out; + + if (last) { + if (nft_set_elem_expired(&f->mt[b].e->ext) || + (genmask && + !nft_set_elem_active(&f->mt[b].e->ext, genmask))) + goto next_match; + + ret = f->mt[b].e; + goto out; + } + + data += NFT_PIPAPO_GROUPS_PADDING(f->groups); + + /* Swap bitmap indices: fill_map will be the initial bitmap for + * the next field (i.e. the new res_map), and res_map is + * guaranteed to be all-zeroes at this point, ready to be filled + * according to the next mapping table. + */ + swap(res_map, fill_map); + } + +out: + kfree(fill_map); + kfree(res_map); + return ret; +} + +/** + * nft_pipapo_get() - Get matching element reference given key data + * @net: Network namespace + * @set: nftables API set representation + * @elem: nftables API element representation containing key data + * @flags: Unused + */ +void *nft_pipapo_get(const struct net *net, const struct nft_set *set, + const struct nft_set_elem *elem, unsigned int flags) +{ + return pipapo_get(net, set, (const u8 *)elem->key.val.data, + nft_genmask_cur(net)); +} + +/** + * pipapo_resize() - Resize lookup or mapping table, or both + * @f: Field containing lookup and mapping tables + * @old_rules: Previous amount of rules in field + * @rules: New amount of rules + * + * Increase, decrease or maintain tables size depending on new amount of rules, + * and copy data over. In case the new size is smaller, throw away data for + * highest-numbered rules. + * + * Return: 0 on success, -ENOMEM on allocation failure. + */ +static int pipapo_resize(struct nft_pipapo_field *f, int old_rules, int rules) +{ + long *new_lt = NULL, *new_p, *old_lt = f->lt, *old_p; + union nft_pipapo_map_bucket *new_mt, *old_mt = f->mt; + size_t new_bucket_size, copy; + int group, bucket; + + new_bucket_size = DIV_ROUND_UP(rules, BITS_PER_LONG); + + if (new_bucket_size == f->bsize) + goto mt; + + if (new_bucket_size > f->bsize) + copy = f->bsize; + else + copy = new_bucket_size; + + new_lt = kvzalloc(f->groups * NFT_PIPAPO_BUCKETS * new_bucket_size * + sizeof(*new_lt), GFP_KERNEL); + if (!new_lt) + return -ENOMEM; + + new_p = new_lt; + old_p = old_lt; + for (group = 0; group < f->groups; group++) { + for (bucket = 0; bucket < NFT_PIPAPO_BUCKETS; bucket++) { + memcpy(new_p, old_p, copy * sizeof(*new_p)); + new_p += copy; + old_p += copy; + + if (new_bucket_size > f->bsize) + new_p += new_bucket_size - f->bsize; + else + old_p += f->bsize - new_bucket_size; + } + } + +mt: + new_mt = kvmalloc(rules * sizeof(*new_mt), GFP_KERNEL); + if (!new_mt) { + kvfree(new_lt); + return -ENOMEM; + } + + memcpy(new_mt, f->mt, min(old_rules, rules) * sizeof(*new_mt)); + if (rules > old_rules) { + memset(new_mt + old_rules, 0, + (rules - old_rules) * sizeof(*new_mt)); + } + + if (new_lt) { + f->bsize = new_bucket_size; + f->lt = new_lt; + kvfree(old_lt); + } + + f->mt = new_mt; + kvfree(old_mt); + + return 0; +} + +/** + * pipapo_bucket_set() - Set rule bit in bucket given group and group value + * @f: Field containing lookup table + * @rule: Rule index + * @group: Group index + * @v: Value of bit group + */ +static void pipapo_bucket_set(struct nft_pipapo_field *f, int rule, int group, + int v) +{ + unsigned long *pos; + + pos = f->lt + f->bsize * NFT_PIPAPO_BUCKETS * group; + pos += f->bsize * v; + + __set_bit(rule, pos); +} + +/** + * pipapo_insert() - Insert new rule in field given input key and mask length + * @f: Field containing lookup table + * @k: Input key for classification, without nftables padding + * @mask_bits: Length of mask; matches field length for non-ranged entry + * + * Insert a new rule reference in lookup buckets corresponding to k and + * mask_bits. + * + * Return: 1 on success (one rule inserted), negative error code on failure. + */ +static int pipapo_insert(struct nft_pipapo_field *f, const uint8_t *k, + int mask_bits) +{ + int rule = f->rules++, group, ret; + + ret = pipapo_resize(f, f->rules - 1, f->rules); + if (ret) + return ret; + + for (group = 0; group < f->groups; group++) { + int i, v; + u8 mask; + + if (group % 2) + v = k[group / 2] & 0x0f; + else + v = k[group / 2] >> 4; + + if (mask_bits >= (group + 1) * 4) { + /* Not masked */ + pipapo_bucket_set(f, rule, group, v); + } else if (mask_bits <= group * 4) { + /* Completely masked */ + for (i = 0; i < NFT_PIPAPO_BUCKETS; i++) + pipapo_bucket_set(f, rule, group, i); + } else { + /* The mask limit falls on this group */ + mask = 0x0f >> (mask_bits - group * 4); + for (i = 0; i < NFT_PIPAPO_BUCKETS; i++) { + if ((i & ~mask) == (v & ~mask)) + pipapo_bucket_set(f, rule, group, i); + } + } + } + + return 1; +} + +/** + * pipapo_step_diff() - Check if setting @step bit in netmask would change it + * @base: Mask we are expanding + * @step: Step bit for given expansion step + * @len: Total length of mask space (set and unset bits), bytes + * + * Convenience function for mask expansion. + * + * Return: true if step bit changes mask (i.e. isn't set), false otherwise. + */ +static bool pipapo_step_diff(u8 *base, int step, int len) +{ + /* Network order, byte-addressed */ +#ifdef __BIG_ENDIAN__ + return !(BIT(step % BITS_PER_BYTE) & base[step / BITS_PER_BYTE]); +#else + return !(BIT(step % BITS_PER_BYTE) & + base[len - 1 - step / BITS_PER_BYTE]); +#endif +} + +/** + * pipapo_step_after_end() - Check if mask exceeds range end with given step + * @base: Mask we are expanding + * @end: End of range + * @step: Step bit for given expansion step, highest bit to be set + * @len: Total length of mask space (set and unset bits), bytes + * + * Convenience function for mask expansion. + * + * Return: true if mask exceeds range setting step bits, false otherwise. + */ +static bool pipapo_step_after_end(const u8 *base, const u8 *end, int step, + int len) +{ + u8 tmp[NFT_PIPAPO_MAX_BYTES]; + int i; + + memcpy(tmp, base, len); + + /* Network order, byte-addressed */ + for (i = 0; i <= step; i++) +#ifdef __BIG_ENDIAN__ + tmp[i / BITS_PER_BYTE] |= BIT(i % BITS_PER_BYTE); +#else + tmp[len - 1 - i / BITS_PER_BYTE] |= BIT(i % BITS_PER_BYTE); +#endif + + return memcmp(tmp, end, len) > 0; +} + +/** + * pipapo_base_sum() - Sum step bit to given len-sized netmask base with carry + * @base: Netmask base + * @step: Step bit to sum + * @len: Netmask length, bytes + */ +static void pipapo_base_sum(u8 *base, int step, int len) +{ + bool carry = false; + int i; + + /* Network order, byte-addressed */ +#ifdef __BIG_ENDIAN__ + for (i = step / BITS_PER_BYTE; i < len; i++) { +#else + for (i = len - 1 - step / BITS_PER_BYTE; i >= 0; i--) { +#endif + if (carry) + base[i]++; + else + base[i] += 1 << (step % BITS_PER_BYTE); + + if (base[i]) + break; + + carry = true; + } +} + +/** + * pipapo_expand() - Expand to composing netmasks, insert into lookup table + * @f: Field containing lookup table + * @start: Start of range + * @end: End of range + * @len: Length of value in bits + * + * Expand range to composing netmasks and insert corresponding rule references + * in lookup buckets. + * + * Return: number of inserted rules on success, negative error code on failure. + */ +static int pipapo_expand(struct nft_pipapo_field *f, + const u8 *start, const u8 *end, int len) +{ + int step, masks = 0, bytes = DIV_ROUND_UP(len, BITS_PER_BYTE); + u8 base[NFT_PIPAPO_MAX_BYTES]; + + memcpy(base, start, bytes); + while (memcmp(base, end, bytes) <= 0) { + int err; + + step = 0; + while (pipapo_step_diff(base, step, bytes)) { + if (pipapo_step_after_end(base, end, step, bytes)) + break; + + step++; + if (step >= len) { + if (!masks) { + pipapo_insert(f, base, 0); + masks = 1; + } + goto out; + } + } + + err = pipapo_insert(f, base, len - step); + + if (err < 0) + return err; + + masks++; + pipapo_base_sum(base, step, bytes); + } +out: + return masks; +} + +/** + * pipapo_map() - Insert rules in mapping tables, mapping them between fields + * @m: Matching data, including mapping table + * @map: Table of rule maps: array of first rule and amount of rules + * in next field a given rule maps to, for each field + * @ext: For last field, nft_set_ext pointer matching rules map to + */ +static void pipapo_map(struct nft_pipapo_match *m, + union nft_pipapo_map_bucket map[NFT_PIPAPO_MAX_FIELDS], + struct nft_pipapo_elem *e) +{ + struct nft_pipapo_field *f; + int i, j; + + for (i = 0, f = m->f; i < m->field_count - 1; i++, f++) { + for (j = 0; j < map[i].n; j++) { + f->mt[map[i].to + j].to = map[i + 1].to; + f->mt[map[i].to + j].n = map[i + 1].n; + } + } + + /* Last field: map to ext instead of mapping to next field */ + for (j = 0; j < map[i].n; j++) + f->mt[map[i].to + j].e = e; +} + +/** + * pipapo_realloc_scratch() - Reallocate scratch maps for partial match results + * @clone: Copy of matching data with pending insertions and deletions + * @bsize_max Maximum bucket size, scratch maps cover two buckets + * + * Return: 0 on success, -ENOMEM on failure. + */ +static int pipapo_realloc_scratch(struct nft_pipapo_match *clone, + unsigned long bsize_max) +{ + int i; + + for_each_possible_cpu(i) { + unsigned long *scratch; + + scratch = kzalloc_node(bsize_max * sizeof(*scratch) * 2, + GFP_KERNEL, cpu_to_node(i)); + if (!scratch) { + /* On failure, there's no need to undo previous + * allocations: this means that some scratch maps have + * a bigger allocated size now (this is only called on + * insertion), but the extra space won't be used by any + * CPU as new elements are not inserted and m->bsize_max + * is not updated. + */ + return -ENOMEM; + } + + kfree(*per_cpu_ptr(clone->scratch, i)); + + *per_cpu_ptr(clone->scratch, i) = scratch; + } + + return 0; +} + +/** + * nft_pipapo_insert() - Validate and insert ranged elements + * @net: Network namespace + * @set: nftables API set representation + * @elem: nftables API element representation containing key data + * @ext2: Filled with pointer to &struct nft_set_ext in inserted element + * + * Return: 0 on success, error pointer on failure. + */ +static int nft_pipapo_insert(const struct net *net, const struct nft_set *set, + const struct nft_set_elem *elem, + struct nft_set_ext **ext2) +{ + const struct nft_set_ext *ext = nft_set_elem_ext(set, elem->priv); + union nft_pipapo_map_bucket rulemap[NFT_PIPAPO_MAX_FIELDS]; + const u8 *start = (const u8 *)elem->key.val.data, *end; + struct nft_pipapo_elem *e = elem->priv, *dup; + struct nft_pipapo *priv = nft_set_priv(set); + struct nft_pipapo_match *m = priv->clone; + u8 genmask = nft_genmask_next(net); + struct nft_pipapo_field *f; + int i, bsize_max, err = 0; + + dup = pipapo_get(net, set, start, genmask); + if (PTR_ERR(dup) == -ENOENT) { + if (nft_set_ext_exists(ext, NFT_SET_EXT_KEY_END)) { + end = (const u8 *)nft_set_ext_key_end(ext)->data; + dup = pipapo_get(net, set, end, nft_genmask_next(net)); + } else { + end = start; + } + } + + if (PTR_ERR(dup) != -ENOENT) { + if (IS_ERR(dup)) + return PTR_ERR(dup); + *ext2 = &dup->ext; + return -EEXIST; + } + + /* Validate */ + nft_pipapo_for_each_field(f, i, m) { + const u8 *start_p = start, *end_p = end; + + if (f->rules >= (unsigned long)NFT_PIPAPO_RULE0_MAX) + return -ENOSPC; + + if (memcmp(start_p, end_p, + f->groups / NFT_PIPAPO_GROUPS_PER_BYTE) > 0) + return -EINVAL; + + start_p += NFT_PIPAPO_GROUPS_PADDED_SIZE(f->groups); + end_p += NFT_PIPAPO_GROUPS_PADDED_SIZE(f->groups); + } + + /* Insert */ + priv->dirty = true; + + bsize_max = m->bsize_max; + + nft_pipapo_for_each_field(f, i, m) { + int ret; + + rulemap[i].to = f->rules; + + ret = memcmp(start, end, + f->groups / NFT_PIPAPO_GROUPS_PER_BYTE); + if (!ret) { + ret = pipapo_insert(f, start, + f->groups * NFT_PIPAPO_GROUP_BITS); + } else { + ret = pipapo_expand(f, start, end, + f->groups * NFT_PIPAPO_GROUP_BITS); + } + + if (f->bsize > bsize_max) + bsize_max = f->bsize; + + rulemap[i].n = ret; + + start += NFT_PIPAPO_GROUPS_PADDED_SIZE(f->groups); + end += NFT_PIPAPO_GROUPS_PADDED_SIZE(f->groups); + } + + if (!*this_cpu_ptr(m->scratch) || bsize_max > m->bsize_max) { + err = pipapo_realloc_scratch(m, bsize_max); + if (err) + return err; + + this_cpu_write(nft_pipapo_scratch_index, false); + + m->bsize_max = bsize_max; + } + + *ext2 = &e->ext; + + pipapo_map(m, rulemap, e); + + return 0; +} + +/** + * pipapo_clone() - Clone matching data to create new working copy + * @old: Existing matching data + * + * Return: copy of matching data passed as 'old', error pointer on failure + */ +static struct nft_pipapo_match *pipapo_clone(struct nft_pipapo_match *old) +{ + struct nft_pipapo_field *dst, *src; + struct nft_pipapo_match *new; + int i; + + new = kmalloc(sizeof(*new) + sizeof(*dst) * old->field_count, + GFP_KERNEL); + if (!new) + return ERR_PTR(-ENOMEM); + + new->field_count = old->field_count; + new->bsize_max = old->bsize_max; + + new->scratch = alloc_percpu(*new->scratch); + if (!new->scratch) + goto out_scratch; + + rcu_head_init(&new->rcu); + + src = old->f; + dst = new->f; + + for (i = 0; i < old->field_count; i++) { + memcpy(dst, src, offsetof(struct nft_pipapo_field, lt)); + + dst->lt = kvzalloc(src->groups * NFT_PIPAPO_BUCKETS * + src->bsize * sizeof(*dst->lt), + GFP_KERNEL); + if (!dst->lt) + goto out_lt; + + memcpy(dst->lt, src->lt, + src->bsize * sizeof(*dst->lt) * + src->groups * NFT_PIPAPO_BUCKETS); + + dst->mt = kvmalloc(src->rules * sizeof(*src->mt), GFP_KERNEL); + if (!dst->mt) + goto out_mt; + + memcpy(dst->mt, src->mt, src->rules * sizeof(*src->mt)); + src++; + dst++; + } + + return new; + +out_mt: + kvfree(dst->lt); +out_lt: + for (dst--; i > 0; i--) { + kvfree(dst->mt); + kvfree(dst->lt); + dst--; + } + free_percpu(new->scratch); +out_scratch: + kfree(new); + + return ERR_PTR(-ENOMEM); +} + +/** + * pipapo_rules_same_key() - Get number of rules originated from the same entry + * @f: Field containing mapping table + * @first: Index of first rule in set of rules mapping to same entry + * + * Using the fact that all rules in a field that originated from the same entry + * will map to the same set of rules in the next field, or to the same element + * reference, return the cardinality of the set of rules that originated from + * the same entry as the rule with index @first, @first rule included. + * + * In pictures: + * rules + * field #0 0 1 2 3 4 + * map to: 0 1 2-4 2-4 5-9 + * . . ....... . ... + * | | | | \ \ + * | | | | \ \ + * | | | | \ \ + * ' ' ' ' ' \ + * in field #1 0 1 2 3 4 5 ... + * + * if this is called for rule 2 on field #0, it will return 3, as also rules 2 + * and 3 in field 0 map to the same set of rules (2, 3, 4) in the next field. + * + * For the last field in a set, we can rely on associated entries to map to the + * same element references. + * + * Return: Number of rules that originated from the same entry as @first. + */ +static int pipapo_rules_same_key(struct nft_pipapo_field *f, int first) +{ + struct nft_pipapo_elem *e = NULL; /* Keep gcc happy */ + int r; + + for (r = first; r < f->rules; r++) { + if (r != first && e != f->mt[r].e) + return r - first; + + e = f->mt[r].e; + } + + if (r != first) + return r - first; + + return 0; +} + +/** + * pipapo_unmap() - Remove rules from mapping tables, renumber remaining ones + * @mt: Mapping array + * @rules: Original amount of rules in mapping table + * @start: First rule index to be removed + * @n: Amount of rules to be removed + * @to_offset: First rule index, in next field, this group of rules maps to + * @is_last: If this is the last field, delete reference from mapping array + * + * This is used to unmap rules from the mapping table for a single field, + * maintaining consistency and compactness for the existing ones. + * + * In pictures: let's assume that we want to delete rules 2 and 3 from the + * following mapping array: + * + * rules + * 0 1 2 3 4 + * map to: 4-10 4-10 11-15 11-15 16-18 + * + * the result will be: + * + * rules + * 0 1 2 + * map to: 4-10 4-10 11-13 + * + * for fields before the last one. In case this is the mapping table for the + * last field in a set, and rules map to pointers to &struct nft_pipapo_elem: + * + * rules + * 0 1 2 3 4 + * element pointers: 0x42 0x42 0x33 0x33 0x44 + * + * the result will be: + * + * rules + * 0 1 2 + * element pointers: 0x42 0x42 0x44 + */ +static void pipapo_unmap(union nft_pipapo_map_bucket *mt, int rules, + int start, int n, int to_offset, bool is_last) +{ + int i; + + memmove(mt + start, mt + start + n, (rules - start - n) * sizeof(*mt)); + memset(mt + rules - n, 0, n * sizeof(*mt)); + + if (is_last) + return; + + for (i = start; i < rules - n; i++) + mt[i].to -= to_offset; +} + +/** + * pipapo_drop() - Delete entry from lookup and mapping tables, given rule map + * @m: Matching data + * @rulemap Table of rule maps, arrays of first rule and amount of rules + * in next field a given entry maps to, for each field + * + * For each rule in lookup table buckets mapping to this set of rules, drop + * all bits set in lookup table mapping. In pictures, assuming we want to drop + * rules 0 and 1 from this lookup table: + * + * bucket + * group 0 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 + * 0 0 1,2 + * 1 1,2 0 + * 2 0 1,2 + * 3 0 1,2 + * 4 0,1,2 + * 5 0 1 2 + * 6 0,1,2 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 + * 7 1,2 1,2 1 1 1 0,1 1 1 1 1 1 1 1 1 1 1 + * + * rule 2 becomes rule 0, and the result will be: + * + * bucket + * group 0 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 + * 0 0 + * 1 0 + * 2 0 + * 3 0 + * 4 0 + * 5 0 + * 6 0 + * 7 0 0 + * + * once this is done, call unmap() to drop all the corresponding rule references + * from mapping tables. + */ +static void pipapo_drop(struct nft_pipapo_match *m, + union nft_pipapo_map_bucket rulemap[]) +{ + struct nft_pipapo_field *f; + int i; + + nft_pipapo_for_each_field(f, i, m) { + int g; + + for (g = 0; g < f->groups; g++) { + unsigned long *pos; + int b; + + pos = f->lt + g * NFT_PIPAPO_BUCKETS * f->bsize; + + for (b = 0; b < NFT_PIPAPO_BUCKETS; b++) { + bitmap_cut(pos, pos, rulemap[i].to, + rulemap[i].n, + f->bsize * BITS_PER_LONG); + + pos += f->bsize; + } + } + + pipapo_unmap(f->mt, f->rules, rulemap[i].to, rulemap[i].n, + rulemap[i + 1].n, i == m->field_count - 1); + if (pipapo_resize(f, f->rules, f->rules - rulemap[i].n)) { + /* We can ignore this, a failure to shrink tables down + * doesn't make tables invalid. + */ + ; + } + f->rules -= rulemap[i].n; + } +} + +/** + * pipapo_gc() - Drop expired entries from set, destroy start and end elements + * @set: nftables API set representation + * @m: Matching data + */ +static void pipapo_gc(const struct nft_set *set, struct nft_pipapo_match *m) +{ + struct nft_pipapo *priv = nft_set_priv(set); + int rules_f0, first_rule = 0; + + while ((rules_f0 = pipapo_rules_same_key(m->f, first_rule))) { + union nft_pipapo_map_bucket rulemap[NFT_PIPAPO_MAX_FIELDS]; + struct nft_pipapo_field *f; + struct nft_pipapo_elem *e; + int i, start, rules_fx; + + start = first_rule; + rules_fx = rules_f0; + + nft_pipapo_for_each_field(f, i, m) { + rulemap[i].to = start; + rulemap[i].n = rules_fx; + + if (i < m->field_count - 1) { + rules_fx = f->mt[start].n; + start = f->mt[start].to; + } + } + + /* Pick the last field, and its last index */ + f--; + i--; + e = f->mt[rulemap[i].to].e; + if (nft_set_elem_expired(&e->ext) && + !nft_set_elem_mark_busy(&e->ext)) { + priv->dirty = true; + pipapo_drop(m, rulemap); + + rcu_barrier(); + nft_set_elem_destroy(set, e, true); + + /* And check again current first rule, which is now the + * first we haven't checked. + */ + } else { + first_rule += rules_f0; + } + } + + priv->last_gc = jiffies; +} + +/** + * pipapo_free_fields() - Free per-field tables contained in matching data + * @m: Matching data + */ +static void pipapo_free_fields(struct nft_pipapo_match *m) +{ + struct nft_pipapo_field *f; + int i; + + nft_pipapo_for_each_field(f, i, m) { + kvfree(f->lt); + kvfree(f->mt); + } +} + +/** + * pipapo_reclaim_match - RCU callback to free fields from old matching data + * @rcu: RCU head + */ +static void pipapo_reclaim_match(struct rcu_head *rcu) +{ + struct nft_pipapo_match *m; + int i; + + m = container_of(rcu, struct nft_pipapo_match, rcu); + + for_each_possible_cpu(i) + kfree(*per_cpu_ptr(m->scratch, i)); + + free_percpu(m->scratch); + + pipapo_free_fields(m); + + kfree(m); +} + +/** + * pipapo_commit() - Replace lookup data with current working copy + * @set: nftables API set representation + * + * While at it, check if we should perform garbage collection on the working + * copy before committing it for lookup, and don't replace the table if the + * working copy doesn't have pending changes. + * + * We also need to create a new working copy for subsequent insertions and + * deletions. + */ +static void pipapo_commit(const struct nft_set *set) +{ + struct nft_pipapo *priv = nft_set_priv(set); + struct nft_pipapo_match *new_clone, *old; + + if (time_after_eq(jiffies, priv->last_gc + nft_set_gc_interval(set))) + pipapo_gc(set, priv->clone); + + if (!priv->dirty) + return; + + new_clone = pipapo_clone(priv->clone); + if (IS_ERR(new_clone)) + return; + + priv->dirty = false; + + old = rcu_access_pointer(priv->match); + rcu_assign_pointer(priv->match, priv->clone); + if (old) + call_rcu(&old->rcu, pipapo_reclaim_match); + + priv->clone = new_clone; +} + +/** + * nft_pipapo_activate() - Mark element reference as active given key, commit + * @net: Network namespace + * @set: nftables API set representation + * @elem: nftables API element representation containing key data + * + * On insertion, elements are added to a copy of the matching data currently + * in use for lookups, and not directly inserted into current lookup data, so + * we'll take care of that by calling pipapo_commit() here. Both + * nft_pipapo_insert() and nft_pipapo_activate() are called once for each + * element, hence we can't purpose either one as a real commit operation. + */ +static void nft_pipapo_activate(const struct net *net, + const struct nft_set *set, + const struct nft_set_elem *elem) +{ + struct nft_pipapo_elem *e; + + e = pipapo_get(net, set, (const u8 *)elem->key.val.data, 0); + if (IS_ERR(e)) + return; + + nft_set_elem_change_active(net, set, &e->ext); + nft_set_elem_clear_busy(&e->ext); + + pipapo_commit(set); +} + +/** + * pipapo_deactivate() - Check that element is in set, mark as inactive + * @net: Network namespace + * @set: nftables API set representation + * @data: Input key data + * @ext: nftables API extension pointer, used to check for end element + * + * This is a convenience function that can be called from both + * nft_pipapo_deactivate() and nft_pipapo_flush(), as they are in fact the same + * operation. + * + * Return: deactivated element if found, NULL otherwise. + */ +static void *pipapo_deactivate(const struct net *net, const struct nft_set *set, + const u8 *data, const struct nft_set_ext *ext) +{ + struct nft_pipapo_elem *e; + + e = pipapo_get(net, set, data, nft_genmask_next(net)); + if (IS_ERR(e)) + return NULL; + + nft_set_elem_change_active(net, set, &e->ext); + + return e; +} + +/** + * nft_pipapo_deactivate() - Call pipapo_deactivate() to make element inactive + * @net: Network namespace + * @set: nftables API set representation + * @elem: nftables API element representation containing key data + * + * Return: deactivated element if found, NULL otherwise. + */ +static void *nft_pipapo_deactivate(const struct net *net, + const struct nft_set *set, + const struct nft_set_elem *elem) +{ + const struct nft_set_ext *ext = nft_set_elem_ext(set, elem->priv); + + return pipapo_deactivate(net, set, (const u8 *)elem->key.val.data, ext); +} + +/** + * nft_pipapo_flush() - Call pipapo_deactivate() to make element inactive + * @net: Network namespace + * @set: nftables API set representation + * @elem: nftables API element representation containing key data + * + * This is functionally the same as nft_pipapo_deactivate(), with a slightly + * different interface, and it's also called once for each element in a set + * being flushed, so we can't implement, strictly speaking, a flush operation, + * which would otherwise be as simple as allocating an empty copy of the + * matching data. + * + * Note that we could in theory do that, mark the set as flushed, and ignore + * subsequent calls, but we would leak all the elements after the first one, + * because they wouldn't then be freed as result of API calls. + * + * Return: true if element was found and deactivated. + */ +static bool nft_pipapo_flush(const struct net *net, const struct nft_set *set, + void *elem) +{ + struct nft_pipapo_elem *e = elem; + + return pipapo_deactivate(net, set, (const u8 *)nft_set_ext_key(&e->ext), + &e->ext); +} + +/** + * pipapo_get_boundaries() - Get byte interval for associated rules + * @f: Field including lookup table + * @first_rule: First rule (lowest index) + * @rule_count: Number of associated rules + * @left: Byte expression for left boundary (start of range) + * @right: Byte expression for right boundary (end of range) + * + * Given the first rule and amount of rules that originated from the same entry, + * build the original range associated with the entry, and calculate the length + * of the originating netmask. + * + * In pictures: + * + * bucket + * group 0 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 + * 0 1,2 + * 1 1,2 + * 2 1,2 + * 3 1,2 + * 4 1,2 + * 5 1 2 + * 6 1,2 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 + * 7 1,2 1,2 1 1 1 1 1 1 1 1 1 1 1 1 1 1 + * + * this is the lookup table corresponding to the IPv4 range + * 192.168.1.0-192.168.2.1, which was expanded to the two composing netmasks, + * rule #1: 192.168.1.0/24, and rule #2: 192.168.2.0/31. + * + * This function fills @left and @right with the byte values of the leftmost + * and rightmost bucket indices for the lowest and highest rule indices, + * respectively. If @first_rule is 1 and @rule_count is 2, we obtain, in + * nibbles: + * left: < 12, 0, 10, 8, 0, 1, 0, 0 > + * right: < 12, 0, 10, 8, 0, 2, 2, 1 > + * corresponding to bytes: + * left: < 192, 168, 1, 0 > + * right: < 192, 168, 2, 1 > + * with mask length irrelevant here, unused on return, as the range is already + * defined by its start and end points. The mask length is relevant for a single + * ranged entry instead: if @first_rule is 1 and @rule_count is 1, we ignore + * rule 2 above: @left becomes < 192, 168, 1, 0 >, @right becomes + * < 192, 168, 1, 255 >, and the mask length, calculated from the distances + * between leftmost and rightmost bucket indices for each group, would be 24. + * + * Return: mask length, in bits. + */ +static int pipapo_get_boundaries(struct nft_pipapo_field *f, int first_rule, + int rule_count, u8 *left, u8 *right) +{ + u8 *l = left, *r = right; + int g, mask_len = 0; + + for (g = 0; g < f->groups; g++) { + int b, x0, x1; + + x0 = -1; + x1 = -1; + for (b = 0; b < NFT_PIPAPO_BUCKETS; b++) { + unsigned long *pos; + + pos = f->lt + (g * NFT_PIPAPO_BUCKETS + b) * f->bsize; + if (test_bit(first_rule, pos) && x0 == -1) + x0 = b; + if (test_bit(first_rule + rule_count - 1, pos)) + x1 = b; + } + + if (g % 2) { + *(l++) |= x0 & 0x0f; + *(r++) |= x1 & 0x0f; + } else { + *l |= x0 << 4; + *r |= x1 << 4; + } + + if (x1 - x0 == 0) + mask_len += 4; + else if (x1 - x0 == 1) + mask_len += 3; + else if (x1 - x0 == 3) + mask_len += 2; + else if (x1 - x0 == 7) + mask_len += 1; + } + + return mask_len; +} + +/** + * pipapo_match_field() - Match rules against byte ranges + * @f: Field including the lookup table + * @first_rule: First of associated rules originating from same entry + * @rule_count: Amount of associated rules + * @start: Start of range to be matched + * @end: End of range to be matched + * + * Return: true on match, false otherwise. + */ +static bool pipapo_match_field(struct nft_pipapo_field *f, + int first_rule, int rule_count, + const u8 *start, const u8 *end) +{ + u8 right[NFT_PIPAPO_MAX_BYTES] = { 0 }; + u8 left[NFT_PIPAPO_MAX_BYTES] = { 0 }; + + pipapo_get_boundaries(f, first_rule, rule_count, left, right); + + return !memcmp(start, left, f->groups / NFT_PIPAPO_GROUPS_PER_BYTE) && + !memcmp(end, right, f->groups / NFT_PIPAPO_GROUPS_PER_BYTE); +} + +/** + * nft_pipapo_remove() - Remove element given key, commit + * @net: Network namespace + * @set: nftables API set representation + * @elem: nftables API element representation containing key data + * + * Similarly to nft_pipapo_activate(), this is used as commit operation by the + * API, but it's called once per element in the pending transaction, so we can't + * implement this as a single commit operation. Closest we can get is to remove + * the matched element here, if any, and commit the updated matching data. + */ +static void nft_pipapo_remove(const struct net *net, const struct nft_set *set, + const struct nft_set_elem *elem) +{ + const u8 *data = (const u8 *)elem->key.val.data; + struct nft_pipapo *priv = nft_set_priv(set); + struct nft_pipapo_match *m = priv->clone; + int rules_f0, first_rule = 0; + struct nft_pipapo_elem *e; + + e = pipapo_get(net, set, data, 0); + if (IS_ERR(e)) + return; + + while ((rules_f0 = pipapo_rules_same_key(m->f, first_rule))) { + union nft_pipapo_map_bucket rulemap[NFT_PIPAPO_MAX_FIELDS]; + const u8 *match_start, *match_end; + struct nft_pipapo_field *f; + int i, start, rules_fx; + + match_start = data; + match_end = (const u8 *)nft_set_ext_key_end(&e->ext)->data; + + start = first_rule; + rules_fx = rules_f0; + + nft_pipapo_for_each_field(f, i, m) { + if (!pipapo_match_field(f, start, rules_fx, + match_start, match_end)) + break; + + rulemap[i].to = start; + rulemap[i].n = rules_fx; + + rules_fx = f->mt[start].n; + start = f->mt[start].to; + + match_start += NFT_PIPAPO_GROUPS_PADDED_SIZE(f->groups); + match_end += NFT_PIPAPO_GROUPS_PADDED_SIZE(f->groups); + } + + if (i == m->field_count) { + priv->dirty = true; + pipapo_drop(m, rulemap); + pipapo_commit(set); + return; + } + + first_rule += rules_f0; + } +} + +/** + * nft_pipapo_walk() - Walk over elements + * @ctx: nftables API context + * @set: nftables API set representation + * @iter: Iterator + * + * As elements are referenced in the mapping array for the last field, directly + * scan that array: there's no need to follow rule mappings from the first + * field. + */ +static void nft_pipapo_walk(const struct nft_ctx *ctx, struct nft_set *set, + struct nft_set_iter *iter) +{ + struct nft_pipapo *priv = nft_set_priv(set); + struct nft_pipapo_match *m; + struct nft_pipapo_field *f; + int i, r; + + rcu_read_lock(); + m = rcu_dereference(priv->match); + + if (unlikely(!m)) + goto out; + + for (i = 0, f = m->f; i < m->field_count - 1; i++, f++) + ; + + for (r = 0; r < f->rules; r++) { + struct nft_pipapo_elem *e; + struct nft_set_elem elem; + + if (r < f->rules - 1 && f->mt[r + 1].e == f->mt[r].e) + continue; + + if (iter->count < iter->skip) + goto cont; + + e = f->mt[r].e; + if (nft_set_elem_expired(&e->ext)) + goto cont; + + elem.priv = e; + + iter->err = iter->fn(ctx, set, iter, &elem); + if (iter->err < 0) + goto out; + +cont: + iter->count++; + } + +out: + rcu_read_unlock(); +} + +/** + * nft_pipapo_privsize() - Return the size of private data for the set + * @nla: netlink attributes, ignored as size doesn't depend on them + * @desc: Set description, ignored as size doesn't depend on it + * + * Return: size of private data for this set implementation, in bytes + */ +static u64 nft_pipapo_privsize(const struct nlattr * const nla[], + const struct nft_set_desc *desc) +{ + return sizeof(struct nft_pipapo); +} + +/** + * nft_pipapo_estimate() - Estimate set size, space and lookup complexity + * @desc: Set description, element count and field description used here + * @features: Flags: NFT_SET_INTERVAL needs to be there + * @est: Storage for estimation data + * + * The size for this set type can vary dramatically, as it depends on the number + * of rules (composing netmasks) the entries expand to. We compute the worst + * case here. + * + * In general, for a non-ranged entry or a single composing netmask, we need + * one bit in each of the sixteen NFT_PIPAPO_BUCKETS, for each 4-bit group (that + * is, each input bit needs four bits of matching data), plus a bucket in the + * mapping table for each field. + * + * Return: true only for compatible range concatenations + */ +static bool nft_pipapo_estimate(const struct nft_set_desc *desc, u32 features, + struct nft_set_estimate *est) +{ + unsigned long entry_size; + int i; + + if (!(features & NFT_SET_INTERVAL) || desc->field_count <= 1) + return false; + + for (i = 0, entry_size = 0; i < desc->field_count; i++) { + unsigned long rules; + + if (desc->field_len[i] > NFT_PIPAPO_MAX_BYTES) + return false; + + /* Worst-case ranges for each concatenated field: each n-bit + * field can expand to up to n * 2 rules in each bucket, and + * each rule also needs a mapping bucket. + */ + rules = ilog2(desc->field_len[i] * BITS_PER_BYTE) * 2; + entry_size += rules * NFT_PIPAPO_BUCKETS / BITS_PER_BYTE; + entry_size += rules * sizeof(union nft_pipapo_map_bucket); + } + + /* Rules in lookup and mapping tables are needed for each entry */ + est->size = desc->size * entry_size; + if (est->size && div_u64(est->size, desc->size) != entry_size) + return false; + + est->size += sizeof(struct nft_pipapo) + + sizeof(struct nft_pipapo_match) * 2; + + est->size += sizeof(struct nft_pipapo_field) * desc->field_count; + + est->lookup = NFT_SET_CLASS_O_LOG_N; + + est->space = NFT_SET_CLASS_O_N; + + return true; +} + +/** + * nft_pipapo_init() - Initialise data for a set instance + * @set: nftables API set representation + * @desc: Set description + * @nla: netlink attributes + * + * Validate number and size of fields passed as NFTA_SET_DESC_CONCAT netlink + * attributes, initialise internal set parameters, current instance of matching + * data and a copy for subsequent insertions. + * + * Return: 0 on success, negative error code on failure. + */ +static int nft_pipapo_init(const struct nft_set *set, + const struct nft_set_desc *desc, + const struct nlattr * const nla[]) +{ + struct nft_pipapo *priv = nft_set_priv(set); + struct nft_pipapo_match *m; + struct nft_pipapo_field *f; + int err, i; + + if (desc->field_count > NFT_PIPAPO_MAX_FIELDS) + return -EINVAL; + + m = kmalloc(sizeof(*priv->match) + sizeof(*f) * desc->field_count, + GFP_KERNEL); + if (!m) + return -ENOMEM; + + m->field_count = desc->field_count; + m->bsize_max = 0; + + m->scratch = alloc_percpu(unsigned long *); + if (!m->scratch) { + err = -ENOMEM; + goto out_free; + } + for_each_possible_cpu(i) + *per_cpu_ptr(m->scratch, i) = NULL; + + rcu_head_init(&m->rcu); + + nft_pipapo_for_each_field(f, i, m) { + f->groups = desc->field_len[i] * NFT_PIPAPO_GROUPS_PER_BYTE; + priv->groups += f->groups; + + priv->width += round_up(desc->field_len[i], sizeof(u32)); + + f->bsize = 0; + f->rules = 0; + f->lt = NULL; + f->mt = NULL; + } + + /* Create an initial clone of matching data for next insertion */ + priv->clone = pipapo_clone(m); + if (IS_ERR(priv->clone)) { + err = PTR_ERR(priv->clone); + goto out_free; + } + + priv->dirty = false; + + rcu_assign_pointer(priv->match, m); + + return 0; + +out_free: + free_percpu(m->scratch); + kfree(m); + + return err; +} + +/** + * nft_pipapo_destroy() - Free private data for set and all committed elements + * @set: nftables API set representation + */ +static void nft_pipapo_destroy(const struct nft_set *set) +{ + struct nft_pipapo *priv = nft_set_priv(set); + struct nft_pipapo_match *m; + struct nft_pipapo_field *f; + int i, r, cpu; + + m = rcu_dereference_protected(priv->match, true); + if (m) { + rcu_barrier(); + + for (i = 0, f = m->f; i < m->field_count - 1; i++, f++) + ; + + for (r = 0; r < f->rules; r++) { + struct nft_pipapo_elem *e; + + if (r < f->rules - 1 && f->mt[r + 1].e == f->mt[r].e) + continue; + + e = f->mt[r].e; + + nft_set_elem_destroy(set, e, true); + } + + for_each_possible_cpu(cpu) + kfree(*per_cpu_ptr(m->scratch, cpu)); + free_percpu(m->scratch); + + pipapo_free_fields(m); + kfree(m); + priv->match = NULL; + } + + if (priv->clone) { + for_each_possible_cpu(cpu) + kfree(*per_cpu_ptr(priv->clone->scratch, cpu)); + free_percpu(priv->clone->scratch); + + pipapo_free_fields(priv->clone); + kfree(priv->clone); + priv->clone = NULL; + } +} + +/** + * nft_pipapo_gc_init() - Initialise garbage collection + * @set: nftables API set representation + * + * Instead of actually setting up a periodic work for garbage collection, as + * this operation requires a swap of matching data with the working copy, we'll + * do that opportunistically with other commit operations if the interval is + * elapsed, so we just need to set the current jiffies timestamp here. + */ +static void nft_pipapo_gc_init(const struct nft_set *set) +{ + struct nft_pipapo *priv = nft_set_priv(set); + + priv->last_gc = jiffies; +} + +struct nft_set_type nft_set_pipapo_type __read_mostly = { + .owner = THIS_MODULE, + .features = NFT_SET_INTERVAL | NFT_SET_MAP | NFT_SET_OBJECT | + NFT_SET_TIMEOUT, + .ops = { + .lookup = nft_pipapo_lookup, + .insert = nft_pipapo_insert, + .activate = nft_pipapo_activate, + .deactivate = nft_pipapo_deactivate, + .flush = nft_pipapo_flush, + .remove = nft_pipapo_remove, + .walk = nft_pipapo_walk, + .get = nft_pipapo_get, + .privsize = nft_pipapo_privsize, + .estimate = nft_pipapo_estimate, + .init = nft_pipapo_init, + .destroy = nft_pipapo_destroy, + .gc_init = nft_pipapo_gc_init, + .elemsize = offsetof(struct nft_pipapo_elem, ext), + }, +}; diff --git a/net/netfilter/nft_set_rbtree.c b/net/netfilter/nft_set_rbtree.c index a9f804f7a04a..5000b938ab1e 100644 --- a/net/netfilter/nft_set_rbtree.c +++ b/net/netfilter/nft_set_rbtree.c @@ -466,6 +466,9 @@ static void nft_rbtree_destroy(const struct nft_set *set) static bool nft_rbtree_estimate(const struct nft_set_desc *desc, u32 features, struct nft_set_estimate *est) { + if (desc->field_count > 1) + return false; + if (desc->size) est->size = sizeof(struct nft_rbtree) + desc->size * sizeof(struct nft_rbtree_elem); diff --git a/net/netfilter/nft_tunnel.c b/net/netfilter/nft_tunnel.c index 5284fcf16be7..4c3f2e24c7cb 100644 --- a/net/netfilter/nft_tunnel.c +++ b/net/netfilter/nft_tunnel.c @@ -248,8 +248,9 @@ static int nft_tunnel_obj_vxlan_init(const struct nlattr *attr, } static const struct nla_policy nft_tunnel_opts_erspan_policy[NFTA_TUNNEL_KEY_ERSPAN_MAX + 1] = { + [NFTA_TUNNEL_KEY_ERSPAN_VERSION] = { .type = NLA_U32 }, [NFTA_TUNNEL_KEY_ERSPAN_V1_INDEX] = { .type = NLA_U32 }, - [NFTA_TUNNEL_KEY_ERSPAN_V2_DIR] = { .type = NLA_U8 }, + [NFTA_TUNNEL_KEY_ERSPAN_V2_DIR] = { .type = NLA_U8 }, [NFTA_TUNNEL_KEY_ERSPAN_V2_HWID] = { .type = NLA_U8 }, }; @@ -445,10 +446,15 @@ static int nft_tunnel_ip_dump(struct sk_buff *skb, struct ip_tunnel_info *info) if (!nest) return -1; - if (nla_put_in6_addr(skb, NFTA_TUNNEL_KEY_IP6_SRC, &info->key.u.ipv6.src) < 0 || - nla_put_in6_addr(skb, NFTA_TUNNEL_KEY_IP6_DST, &info->key.u.ipv6.dst) < 0 || - nla_put_be32(skb, NFTA_TUNNEL_KEY_IP6_FLOWLABEL, info->key.label)) + if (nla_put_in6_addr(skb, NFTA_TUNNEL_KEY_IP6_SRC, + &info->key.u.ipv6.src) < 0 || + nla_put_in6_addr(skb, NFTA_TUNNEL_KEY_IP6_DST, + &info->key.u.ipv6.dst) < 0 || + nla_put_be32(skb, NFTA_TUNNEL_KEY_IP6_FLOWLABEL, + info->key.label)) { + nla_nest_cancel(skb, nest); return -1; + } nla_nest_end(skb, nest); } else { @@ -456,9 +462,13 @@ static int nft_tunnel_ip_dump(struct sk_buff *skb, struct ip_tunnel_info *info) if (!nest) return -1; - if (nla_put_in_addr(skb, NFTA_TUNNEL_KEY_IP_SRC, info->key.u.ipv4.src) < 0 || - nla_put_in_addr(skb, NFTA_TUNNEL_KEY_IP_DST, info->key.u.ipv4.dst) < 0) + if (nla_put_in_addr(skb, NFTA_TUNNEL_KEY_IP_SRC, + info->key.u.ipv4.src) < 0 || + nla_put_in_addr(skb, NFTA_TUNNEL_KEY_IP_DST, + info->key.u.ipv4.dst) < 0) { + nla_nest_cancel(skb, nest); return -1; + } nla_nest_end(skb, nest); } @@ -470,42 +480,58 @@ static int nft_tunnel_opts_dump(struct sk_buff *skb, struct nft_tunnel_obj *priv) { struct nft_tunnel_opts *opts = &priv->opts; - struct nlattr *nest; + struct nlattr *nest, *inner; nest = nla_nest_start_noflag(skb, NFTA_TUNNEL_KEY_OPTS); if (!nest) return -1; if (opts->flags & TUNNEL_VXLAN_OPT) { + inner = nla_nest_start_noflag(skb, NFTA_TUNNEL_KEY_OPTS_VXLAN); + if (!inner) + goto failure; if (nla_put_be32(skb, NFTA_TUNNEL_KEY_VXLAN_GBP, htonl(opts->u.vxlan.gbp))) - return -1; + goto inner_failure; + nla_nest_end(skb, inner); } else if (opts->flags & TUNNEL_ERSPAN_OPT) { + inner = nla_nest_start_noflag(skb, NFTA_TUNNEL_KEY_OPTS_ERSPAN); + if (!inner) + goto failure; + if (nla_put_be32(skb, NFTA_TUNNEL_KEY_ERSPAN_VERSION, + htonl(opts->u.erspan.version))) + goto inner_failure; switch (opts->u.erspan.version) { case ERSPAN_VERSION: if (nla_put_be32(skb, NFTA_TUNNEL_KEY_ERSPAN_V1_INDEX, opts->u.erspan.u.index)) - return -1; + goto inner_failure; break; case ERSPAN_VERSION2: if (nla_put_u8(skb, NFTA_TUNNEL_KEY_ERSPAN_V2_HWID, get_hwid(&opts->u.erspan.u.md2)) || nla_put_u8(skb, NFTA_TUNNEL_KEY_ERSPAN_V2_DIR, opts->u.erspan.u.md2.dir)) - return -1; + goto inner_failure; break; } + nla_nest_end(skb, inner); } nla_nest_end(skb, nest); - return 0; + +inner_failure: + nla_nest_cancel(skb, inner); +failure: + nla_nest_cancel(skb, nest); + return -1; } static int nft_tunnel_ports_dump(struct sk_buff *skb, struct ip_tunnel_info *info) { - if (nla_put_be16(skb, NFTA_TUNNEL_KEY_SPORT, htons(info->key.tp_src)) < 0 || - nla_put_be16(skb, NFTA_TUNNEL_KEY_DPORT, htons(info->key.tp_dst)) < 0) + if (nla_put_be16(skb, NFTA_TUNNEL_KEY_SPORT, info->key.tp_src) < 0 || + nla_put_be16(skb, NFTA_TUNNEL_KEY_DPORT, info->key.tp_dst) < 0) return -1; return 0; diff --git a/net/netfilter/xt_hashlimit.c b/net/netfilter/xt_hashlimit.c index ced3fc8fad7c..bccd47cd7190 100644 --- a/net/netfilter/xt_hashlimit.c +++ b/net/netfilter/xt_hashlimit.c @@ -357,21 +357,7 @@ static int htable_create(struct net *net, struct hashlimit_cfg3 *cfg, return 0; } -static bool select_all(const struct xt_hashlimit_htable *ht, - const struct dsthash_ent *he) -{ - return true; -} - -static bool select_gc(const struct xt_hashlimit_htable *ht, - const struct dsthash_ent *he) -{ - return time_after_eq(jiffies, he->expires); -} - -static void htable_selective_cleanup(struct xt_hashlimit_htable *ht, - bool (*select)(const struct xt_hashlimit_htable *ht, - const struct dsthash_ent *he)) +static void htable_selective_cleanup(struct xt_hashlimit_htable *ht, bool select_all) { unsigned int i; @@ -381,7 +367,7 @@ static void htable_selective_cleanup(struct xt_hashlimit_htable *ht, spin_lock_bh(&ht->lock); hlist_for_each_entry_safe(dh, n, &ht->hash[i], node) { - if ((*select)(ht, dh)) + if (time_after_eq(jiffies, dh->expires) || select_all) dsthash_free(ht, dh); } spin_unlock_bh(&ht->lock); @@ -395,7 +381,7 @@ static void htable_gc(struct work_struct *work) ht = container_of(work, struct xt_hashlimit_htable, gc_work.work); - htable_selective_cleanup(ht, select_gc); + htable_selective_cleanup(ht, false); queue_delayed_work(system_power_efficient_wq, &ht->gc_work, msecs_to_jiffies(ht->cfg.gc_interval)); @@ -419,7 +405,7 @@ static void htable_destroy(struct xt_hashlimit_htable *hinfo) { cancel_delayed_work_sync(&hinfo->gc_work); htable_remove_proc_entry(hinfo); - htable_selective_cleanup(hinfo, select_all); + htable_selective_cleanup(hinfo, true); kfree(hinfo->name); vfree(hinfo); } diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c index 4c8395462303..7fbfe2adfffa 100644 --- a/net/openvswitch/actions.c +++ b/net/openvswitch/actions.c @@ -161,16 +161,17 @@ static int do_execute_actions(struct datapath *dp, struct sk_buff *skb, const struct nlattr *attr, int len); static int push_mpls(struct sk_buff *skb, struct sw_flow_key *key, - const struct ovs_action_push_mpls *mpls) + __be32 mpls_lse, __be16 mpls_ethertype, __u16 mac_len) { int err; - err = skb_mpls_push(skb, mpls->mpls_lse, mpls->mpls_ethertype, - skb->mac_len, - ovs_key_mac_proto(key) == MAC_PROTO_ETHERNET); + err = skb_mpls_push(skb, mpls_lse, mpls_ethertype, mac_len, !!mac_len); if (err) return err; + if (!mac_len) + key->mac_proto = MAC_PROTO_NONE; + invalidate_flow_key(key); return 0; } @@ -185,6 +186,9 @@ static int pop_mpls(struct sk_buff *skb, struct sw_flow_key *key, if (err) return err; + if (ethertype == htons(ETH_P_TEB)) + key->mac_proto = MAC_PROTO_ETHERNET; + invalidate_flow_key(key); return 0; } @@ -1229,10 +1233,24 @@ static int do_execute_actions(struct datapath *dp, struct sk_buff *skb, execute_hash(skb, key, a); break; - case OVS_ACTION_ATTR_PUSH_MPLS: - err = push_mpls(skb, key, nla_data(a)); + case OVS_ACTION_ATTR_PUSH_MPLS: { + struct ovs_action_push_mpls *mpls = nla_data(a); + + err = push_mpls(skb, key, mpls->mpls_lse, + mpls->mpls_ethertype, skb->mac_len); break; + } + case OVS_ACTION_ATTR_ADD_MPLS: { + struct ovs_action_add_mpls *mpls = nla_data(a); + __u16 mac_len = 0; + + if (mpls->tun_flags & OVS_MPLS_L3_TUNNEL_FLAG_MASK) + mac_len = skb->mac_len; + err = push_mpls(skb, key, mpls->mpls_lse, + mpls->mpls_ethertype, mac_len); + break; + } case OVS_ACTION_ATTR_POP_MPLS: err = pop_mpls(skb, key, nla_get_be16(a)); break; diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c index e3a37d22539c..659c2a790fe7 100644 --- a/net/openvswitch/datapath.c +++ b/net/openvswitch/datapath.c @@ -321,8 +321,7 @@ static int queue_gso_packets(struct datapath *dp, struct sk_buff *skb, } /* Queue all of the segments. */ - skb = segs; - do { + skb_list_walk_safe(segs, skb, nskb) { if (gso_type & SKB_GSO_UDP && skb != segs) key = &later_key; @@ -330,17 +329,15 @@ static int queue_gso_packets(struct datapath *dp, struct sk_buff *skb, if (err) break; - } while ((skb = skb->next)); + } /* Free all of the segments. */ - skb = segs; - do { - nskb = skb->next; + skb_list_walk_safe(segs, skb, nskb) { if (err) kfree_skb(skb); else consume_skb(skb); - } while ((skb = nskb)); + } return err; } diff --git a/net/openvswitch/flow_netlink.c b/net/openvswitch/flow_netlink.c index 65c2e3458ff5..7da4230627f5 100644 --- a/net/openvswitch/flow_netlink.c +++ b/net/openvswitch/flow_netlink.c @@ -79,6 +79,7 @@ static bool actions_may_change_flow(const struct nlattr *actions) case OVS_ACTION_ATTR_SET_MASKED: case OVS_ACTION_ATTR_METER: case OVS_ACTION_ATTR_CHECK_PKT_LEN: + case OVS_ACTION_ATTR_ADD_MPLS: default: return true; } @@ -3005,6 +3006,7 @@ static int __ovs_nla_copy_actions(struct net *net, const struct nlattr *attr, [OVS_ACTION_ATTR_METER] = sizeof(u32), [OVS_ACTION_ATTR_CLONE] = (u32)-1, [OVS_ACTION_ATTR_CHECK_PKT_LEN] = (u32)-1, + [OVS_ACTION_ATTR_ADD_MPLS] = sizeof(struct ovs_action_add_mpls), }; const struct ovs_action_push_vlan *vlan; int type = nla_type(a); @@ -3072,6 +3074,33 @@ static int __ovs_nla_copy_actions(struct net *net, const struct nlattr *attr, case OVS_ACTION_ATTR_RECIRC: break; + case OVS_ACTION_ATTR_ADD_MPLS: { + const struct ovs_action_add_mpls *mpls = nla_data(a); + + if (!eth_p_mpls(mpls->mpls_ethertype)) + return -EINVAL; + + if (mpls->tun_flags & OVS_MPLS_L3_TUNNEL_FLAG_MASK) { + if (vlan_tci & htons(VLAN_CFI_MASK) || + (eth_type != htons(ETH_P_IP) && + eth_type != htons(ETH_P_IPV6) && + eth_type != htons(ETH_P_ARP) && + eth_type != htons(ETH_P_RARP) && + !eth_p_mpls(eth_type))) + return -EINVAL; + mpls_label_count++; + } else { + if (mac_proto == MAC_PROTO_ETHERNET) { + mpls_label_count = 1; + mac_proto = MAC_PROTO_NONE; + } else { + mpls_label_count++; + } + } + eth_type = mpls->mpls_ethertype; + break; + } + case OVS_ACTION_ATTR_PUSH_MPLS: { const struct ovs_action_push_mpls *mpls = nla_data(a); @@ -3109,6 +3138,11 @@ static int __ovs_nla_copy_actions(struct net *net, const struct nlattr *attr, * recirculation. */ proto = nla_get_be16(a); + + if (proto == htons(ETH_P_TEB) && + mac_proto != MAC_PROTO_NONE) + return -EINVAL; + mpls_label_count--; if (!eth_p_mpls(proto) || !mpls_label_count) diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index 118cd66b7516..3bec515ccde3 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -520,7 +520,7 @@ static int prb_calc_retire_blk_tmo(struct packet_sock *po, int blk_size_in_bytes) { struct net_device *dev; - unsigned int mbits = 0, msec = 0, div = 0, tmo = 0; + unsigned int mbits, div; struct ethtool_link_ksettings ecmd; int err; @@ -532,31 +532,25 @@ static int prb_calc_retire_blk_tmo(struct packet_sock *po, } err = __ethtool_get_link_ksettings(dev, &ecmd); rtnl_unlock(); - if (!err) { - /* - * If the link speed is so slow you don't really - * need to worry about perf anyways - */ - if (ecmd.base.speed < SPEED_1000 || - ecmd.base.speed == SPEED_UNKNOWN) { - return DEFAULT_PRB_RETIRE_TOV; - } else { - msec = 1; - div = ecmd.base.speed / 1000; - } - } else + if (err) return DEFAULT_PRB_RETIRE_TOV; + /* If the link speed is so slow you don't really + * need to worry about perf anyways + */ + if (ecmd.base.speed < SPEED_1000 || + ecmd.base.speed == SPEED_UNKNOWN) + return DEFAULT_PRB_RETIRE_TOV; + + div = ecmd.base.speed / 1000; mbits = (blk_size_in_bytes * 8) / (1024 * 1024); if (div) mbits /= div; - tmo = mbits * msec; - if (div) - return tmo+1; - return tmo; + return mbits + 1; + return mbits; } static void prb_init_ft_ops(struct tpacket_kbdq_core *p1, diff --git a/net/phonet/pn_dev.c b/net/phonet/pn_dev.c index 49bd76a87461..ac0fae06cc15 100644 --- a/net/phonet/pn_dev.c +++ b/net/phonet/pn_dev.c @@ -35,8 +35,6 @@ static unsigned int phonet_net_id __read_mostly; static struct phonet_net *phonet_pernet(struct net *net) { - BUG_ON(!net); - return net_generic(net, phonet_net_id); } diff --git a/net/qrtr/qrtr.c b/net/qrtr/qrtr.c index 3d24d45be5f4..5a8e42ad1504 100644 --- a/net/qrtr/qrtr.c +++ b/net/qrtr/qrtr.c @@ -8,6 +8,8 @@ #include <linux/qrtr.h> #include <linux/termios.h> /* For TIOCINQ/OUTQ */ #include <linux/numa.h> +#include <linux/spinlock.h> +#include <linux/wait.h> #include <net/sock.h> @@ -97,10 +99,11 @@ static inline struct qrtr_sock *qrtr_sk(struct sock *sk) static unsigned int qrtr_local_nid = NUMA_NO_NODE; /* for node ids */ -static RADIX_TREE(qrtr_nodes, GFP_KERNEL); +static RADIX_TREE(qrtr_nodes, GFP_ATOMIC); +static DEFINE_SPINLOCK(qrtr_nodes_lock); /* broadcast list */ static LIST_HEAD(qrtr_all_nodes); -/* lock for qrtr_nodes, qrtr_all_nodes and node reference */ +/* lock for qrtr_all_nodes and node reference */ static DEFINE_MUTEX(qrtr_node_lock); /* local port allocation management */ @@ -113,8 +116,9 @@ static DEFINE_MUTEX(qrtr_port_lock); * @ep: endpoint * @ref: reference count for node * @nid: node id + * @qrtr_tx_flow: tree of qrtr_tx_flow, keyed by node << 32 | port + * @qrtr_tx_lock: lock for qrtr_tx_flow inserts * @rx_queue: receive queue - * @work: scheduled work struct for recv work * @item: list item for broadcast list */ struct qrtr_node { @@ -123,17 +127,36 @@ struct qrtr_node { struct kref ref; unsigned int nid; + struct radix_tree_root qrtr_tx_flow; + struct mutex qrtr_tx_lock; /* for qrtr_tx_flow */ + struct sk_buff_head rx_queue; - struct work_struct work; struct list_head item; }; +/** + * struct qrtr_tx_flow - tx flow control + * @resume_tx: waiters for a resume tx from the remote + * @pending: number of waiting senders + * @tx_failed: indicates that a message with confirm_rx flag was lost + */ +struct qrtr_tx_flow { + struct wait_queue_head resume_tx; + int pending; + int tx_failed; +}; + +#define QRTR_TX_FLOW_HIGH 10 +#define QRTR_TX_FLOW_LOW 5 + static int qrtr_local_enqueue(struct qrtr_node *node, struct sk_buff *skb, int type, struct sockaddr_qrtr *from, struct sockaddr_qrtr *to); static int qrtr_bcast_enqueue(struct qrtr_node *node, struct sk_buff *skb, int type, struct sockaddr_qrtr *from, struct sockaddr_qrtr *to); +static struct qrtr_sock *qrtr_port_lookup(int port); +static void qrtr_port_put(struct qrtr_sock *ipc); /* Release node resources and free the node. * @@ -143,15 +166,25 @@ static int qrtr_bcast_enqueue(struct qrtr_node *node, struct sk_buff *skb, static void __qrtr_node_release(struct kref *kref) { struct qrtr_node *node = container_of(kref, struct qrtr_node, ref); + struct radix_tree_iter iter; + unsigned long flags; + void __rcu **slot; + spin_lock_irqsave(&qrtr_nodes_lock, flags); if (node->nid != QRTR_EP_NID_AUTO) radix_tree_delete(&qrtr_nodes, node->nid); + spin_unlock_irqrestore(&qrtr_nodes_lock, flags); list_del(&node->item); mutex_unlock(&qrtr_node_lock); - cancel_work_sync(&node->work); skb_queue_purge(&node->rx_queue); + + /* Free tx flow counters */ + radix_tree_for_each_slot(slot, &node->qrtr_tx_flow, &iter, 0) { + radix_tree_iter_delete(&node->qrtr_tx_flow, &iter, slot); + kfree(*slot); + } kfree(node); } @@ -171,6 +204,126 @@ static void qrtr_node_release(struct qrtr_node *node) kref_put_mutex(&node->ref, __qrtr_node_release, &qrtr_node_lock); } +/** + * qrtr_tx_resume() - reset flow control counter + * @node: qrtr_node that the QRTR_TYPE_RESUME_TX packet arrived on + * @skb: resume_tx packet + */ +static void qrtr_tx_resume(struct qrtr_node *node, struct sk_buff *skb) +{ + struct qrtr_ctrl_pkt *pkt = (struct qrtr_ctrl_pkt *)skb->data; + u64 remote_node = le32_to_cpu(pkt->client.node); + u32 remote_port = le32_to_cpu(pkt->client.port); + struct qrtr_tx_flow *flow; + unsigned long key; + + key = remote_node << 32 | remote_port; + + rcu_read_lock(); + flow = radix_tree_lookup(&node->qrtr_tx_flow, key); + rcu_read_unlock(); + if (flow) { + spin_lock(&flow->resume_tx.lock); + flow->pending = 0; + spin_unlock(&flow->resume_tx.lock); + wake_up_interruptible_all(&flow->resume_tx); + } + + consume_skb(skb); +} + +/** + * qrtr_tx_wait() - flow control for outgoing packets + * @node: qrtr_node that the packet is to be send to + * @dest_node: node id of the destination + * @dest_port: port number of the destination + * @type: type of message + * + * The flow control scheme is based around the low and high "watermarks". When + * the low watermark is passed the confirm_rx flag is set on the outgoing + * message, which will trigger the remote to send a control message of the type + * QRTR_TYPE_RESUME_TX to reset the counter. If the high watermark is hit + * further transmision should be paused. + * + * Return: 1 if confirm_rx should be set, 0 otherwise or errno failure + */ +static int qrtr_tx_wait(struct qrtr_node *node, int dest_node, int dest_port, + int type) +{ + unsigned long key = (u64)dest_node << 32 | dest_port; + struct qrtr_tx_flow *flow; + int confirm_rx = 0; + int ret; + + /* Never set confirm_rx on non-data packets */ + if (type != QRTR_TYPE_DATA) + return 0; + + mutex_lock(&node->qrtr_tx_lock); + flow = radix_tree_lookup(&node->qrtr_tx_flow, key); + if (!flow) { + flow = kzalloc(sizeof(*flow), GFP_KERNEL); + if (flow) { + init_waitqueue_head(&flow->resume_tx); + radix_tree_insert(&node->qrtr_tx_flow, key, flow); + } + } + mutex_unlock(&node->qrtr_tx_lock); + + /* Set confirm_rx if we where unable to find and allocate a flow */ + if (!flow) + return 1; + + spin_lock_irq(&flow->resume_tx.lock); + ret = wait_event_interruptible_locked_irq(flow->resume_tx, + flow->pending < QRTR_TX_FLOW_HIGH || + flow->tx_failed || + !node->ep); + if (ret < 0) { + confirm_rx = ret; + } else if (!node->ep) { + confirm_rx = -EPIPE; + } else if (flow->tx_failed) { + flow->tx_failed = 0; + confirm_rx = 1; + } else { + flow->pending++; + confirm_rx = flow->pending == QRTR_TX_FLOW_LOW; + } + spin_unlock_irq(&flow->resume_tx.lock); + + return confirm_rx; +} + +/** + * qrtr_tx_flow_failed() - flag that tx of confirm_rx flagged messages failed + * @node: qrtr_node that the packet is to be send to + * @dest_node: node id of the destination + * @dest_port: port number of the destination + * + * Signal that the transmission of a message with confirm_rx flag failed. The + * flow's "pending" counter will keep incrementing towards QRTR_TX_FLOW_HIGH, + * at which point transmission would stall forever waiting for the resume TX + * message associated with the dropped confirm_rx message. + * Work around this by marking the flow as having a failed transmission and + * cause the next transmission attempt to be sent with the confirm_rx. + */ +static void qrtr_tx_flow_failed(struct qrtr_node *node, int dest_node, + int dest_port) +{ + unsigned long key = (u64)dest_node << 32 | dest_port; + struct qrtr_tx_flow *flow; + + rcu_read_lock(); + flow = radix_tree_lookup(&node->qrtr_tx_flow, key); + rcu_read_unlock(); + if (flow) { + spin_lock_irq(&flow->resume_tx.lock); + flow->tx_failed = 1; + spin_unlock_irq(&flow->resume_tx.lock); + } +} + /* Pass an outgoing packet socket buffer to the endpoint driver. */ static int qrtr_node_enqueue(struct qrtr_node *node, struct sk_buff *skb, int type, struct sockaddr_qrtr *from, @@ -179,6 +332,13 @@ 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 confirm_rx; + + confirm_rx = qrtr_tx_wait(node, to->sq_node, to->sq_port, type); + if (confirm_rx < 0) { + kfree_skb(skb); + return confirm_rx; + } hdr = skb_push(skb, sizeof(*hdr)); hdr->version = cpu_to_le32(QRTR_PROTO_VER_1); @@ -194,7 +354,7 @@ static int qrtr_node_enqueue(struct qrtr_node *node, struct sk_buff *skb, } hdr->size = cpu_to_le32(len); - hdr->confirm_rx = 0; + hdr->confirm_rx = !!confirm_rx; skb_put_padto(skb, ALIGN(len, 4) + sizeof(*hdr)); @@ -205,6 +365,11 @@ static int qrtr_node_enqueue(struct qrtr_node *node, struct sk_buff *skb, kfree_skb(skb); mutex_unlock(&node->ep_lock); + /* Need to ensure that a subsequent message carries the otherwise lost + * confirm_rx flag if we dropped this one */ + if (rc && confirm_rx) + qrtr_tx_flow_failed(node, to->sq_node, to->sq_port); + return rc; } @@ -215,11 +380,12 @@ static int qrtr_node_enqueue(struct qrtr_node *node, struct sk_buff *skb, static struct qrtr_node *qrtr_node_lookup(unsigned int nid) { struct qrtr_node *node; + unsigned long flags; - mutex_lock(&qrtr_node_lock); + spin_lock_irqsave(&qrtr_nodes_lock, flags); node = radix_tree_lookup(&qrtr_nodes, nid); node = qrtr_node_acquire(node); - mutex_unlock(&qrtr_node_lock); + spin_unlock_irqrestore(&qrtr_nodes_lock, flags); return node; } @@ -231,13 +397,15 @@ static struct qrtr_node *qrtr_node_lookup(unsigned int nid) */ static void qrtr_node_assign(struct qrtr_node *node, unsigned int nid) { + unsigned long flags; + if (node->nid != QRTR_EP_NID_AUTO || nid == QRTR_EP_NID_AUTO) return; - mutex_lock(&qrtr_node_lock); + spin_lock_irqsave(&qrtr_nodes_lock, flags); radix_tree_insert(&qrtr_nodes, nid, node); node->nid = nid; - mutex_unlock(&qrtr_node_lock); + spin_unlock_irqrestore(&qrtr_nodes_lock, flags); } /** @@ -253,6 +421,7 @@ int qrtr_endpoint_post(struct qrtr_endpoint *ep, const void *data, size_t len) struct qrtr_node *node = ep->node; const struct qrtr_hdr_v1 *v1; const struct qrtr_hdr_v2 *v2; + struct qrtr_sock *ipc; struct sk_buff *skb; struct qrtr_cb *cb; unsigned int size; @@ -311,13 +480,26 @@ int qrtr_endpoint_post(struct qrtr_endpoint *ep, const void *data, size_t len) if (len != ALIGN(size, 4) + hdrlen) goto err; - if (cb->dst_port != QRTR_PORT_CTRL && cb->type != QRTR_TYPE_DATA) + if (cb->dst_port != QRTR_PORT_CTRL && cb->type != QRTR_TYPE_DATA && + cb->type != QRTR_TYPE_RESUME_TX) goto err; skb_put_data(skb, data + hdrlen, size); - skb_queue_tail(&node->rx_queue, skb); - schedule_work(&node->work); + qrtr_node_assign(node, cb->src_node); + + if (cb->type == QRTR_TYPE_RESUME_TX) { + qrtr_tx_resume(node, skb); + } else { + ipc = qrtr_port_lookup(cb->dst_port); + if (!ipc) + goto err; + + if (sock_queue_rcv_skb(&ipc->sk, skb)) + goto err; + + qrtr_port_put(ipc); + } return 0; @@ -352,61 +534,6 @@ static struct sk_buff *qrtr_alloc_ctrl_packet(struct qrtr_ctrl_pkt **pkt) return skb; } -static struct qrtr_sock *qrtr_port_lookup(int port); -static void qrtr_port_put(struct qrtr_sock *ipc); - -/* Handle and route a received packet. - * - * This will auto-reply with resume-tx packet as necessary. - */ -static void qrtr_node_rx_work(struct work_struct *work) -{ - struct qrtr_node *node = container_of(work, struct qrtr_node, work); - struct qrtr_ctrl_pkt *pkt; - struct sockaddr_qrtr dst; - struct sockaddr_qrtr src; - struct sk_buff *skb; - - while ((skb = skb_dequeue(&node->rx_queue)) != NULL) { - struct qrtr_sock *ipc; - struct qrtr_cb *cb; - int confirm; - - cb = (struct qrtr_cb *)skb->cb; - src.sq_node = cb->src_node; - src.sq_port = cb->src_port; - dst.sq_node = cb->dst_node; - dst.sq_port = cb->dst_port; - confirm = !!cb->confirm_rx; - - qrtr_node_assign(node, cb->src_node); - - ipc = qrtr_port_lookup(cb->dst_port); - if (!ipc) { - kfree_skb(skb); - } else { - if (sock_queue_rcv_skb(&ipc->sk, skb)) - kfree_skb(skb); - - qrtr_port_put(ipc); - } - - if (confirm) { - skb = qrtr_alloc_ctrl_packet(&pkt); - if (!skb) - break; - - pkt->cmd = cpu_to_le32(QRTR_TYPE_RESUME_TX); - pkt->client.node = cpu_to_le32(dst.sq_node); - pkt->client.port = cpu_to_le32(dst.sq_port); - - if (qrtr_node_enqueue(node, skb, QRTR_TYPE_RESUME_TX, - &dst, &src)) - break; - } - } -} - /** * qrtr_endpoint_register() - register a new endpoint * @ep: endpoint to register @@ -426,13 +553,15 @@ int qrtr_endpoint_register(struct qrtr_endpoint *ep, unsigned int nid) if (!node) return -ENOMEM; - INIT_WORK(&node->work, qrtr_node_rx_work); kref_init(&node->ref); mutex_init(&node->ep_lock); skb_queue_head_init(&node->rx_queue); node->nid = QRTR_EP_NID_AUTO; node->ep = ep; + INIT_RADIX_TREE(&node->qrtr_tx_flow, GFP_KERNEL); + mutex_init(&node->qrtr_tx_lock); + qrtr_node_assign(node, nid); mutex_lock(&qrtr_node_lock); @@ -453,8 +582,11 @@ void qrtr_endpoint_unregister(struct qrtr_endpoint *ep) struct qrtr_node *node = ep->node; struct sockaddr_qrtr src = {AF_QIPCRTR, node->nid, QRTR_PORT_CTRL}; struct sockaddr_qrtr dst = {AF_QIPCRTR, qrtr_local_nid, QRTR_PORT_CTRL}; + struct radix_tree_iter iter; struct qrtr_ctrl_pkt *pkt; + struct qrtr_tx_flow *flow; struct sk_buff *skb; + void __rcu **slot; mutex_lock(&node->ep_lock); node->ep = NULL; @@ -467,6 +599,14 @@ void qrtr_endpoint_unregister(struct qrtr_endpoint *ep) qrtr_local_enqueue(NULL, skb, QRTR_TYPE_BYE, &src, &dst); } + /* Wake up any transmitters waiting for resume-tx from the node */ + mutex_lock(&node->qrtr_tx_lock); + radix_tree_for_each_slot(slot, &node->qrtr_tx_flow, &iter, 0) { + flow = *slot; + wake_up_interruptible_all(&flow->resume_tx); + } + mutex_unlock(&node->qrtr_tx_lock); + qrtr_node_release(node); ep->node = NULL; } @@ -483,11 +623,11 @@ static struct qrtr_sock *qrtr_port_lookup(int port) if (port == QRTR_PORT_CTRL) port = 0; - mutex_lock(&qrtr_port_lock); + rcu_read_lock(); ipc = idr_find(&qrtr_ports, port); if (ipc) sock_hold(&ipc->sk); - mutex_unlock(&qrtr_port_lock); + rcu_read_unlock(); return ipc; } @@ -529,6 +669,10 @@ static void qrtr_port_remove(struct qrtr_sock *ipc) mutex_lock(&qrtr_port_lock); idr_remove(&qrtr_ports, port); mutex_unlock(&qrtr_port_lock); + + /* Ensure that if qrtr_port_lookup() did enter the RCU read section we + * wait for it to up increment the refcount */ + synchronize_rcu(); } /* Assign port number to socket. @@ -816,6 +960,34 @@ out_node: return rc; } +static int qrtr_send_resume_tx(struct qrtr_cb *cb) +{ + struct sockaddr_qrtr remote = { AF_QIPCRTR, cb->src_node, cb->src_port }; + struct sockaddr_qrtr local = { AF_QIPCRTR, cb->dst_node, cb->dst_port }; + struct qrtr_ctrl_pkt *pkt; + struct qrtr_node *node; + struct sk_buff *skb; + int ret; + + node = qrtr_node_lookup(remote.sq_node); + if (!node) + return -EINVAL; + + skb = qrtr_alloc_ctrl_packet(&pkt); + if (!skb) + return -ENOMEM; + + pkt->cmd = cpu_to_le32(QRTR_TYPE_RESUME_TX); + pkt->client.node = cpu_to_le32(cb->dst_node); + pkt->client.port = cpu_to_le32(cb->dst_port); + + ret = qrtr_node_enqueue(node, skb, QRTR_TYPE_RESUME_TX, &local, &remote); + + qrtr_node_release(node); + + return ret; +} + static int qrtr_recvmsg(struct socket *sock, struct msghdr *msg, size_t size, int flags) { @@ -838,6 +1010,7 @@ static int qrtr_recvmsg(struct socket *sock, struct msghdr *msg, release_sock(sk); return rc; } + cb = (struct qrtr_cb *)skb->cb; copied = skb->len; if (copied > size) { @@ -851,7 +1024,6 @@ static int qrtr_recvmsg(struct socket *sock, struct msghdr *msg, rc = copied; if (addr) { - cb = (struct qrtr_cb *)skb->cb; addr->sq_family = AF_QIPCRTR; addr->sq_node = cb->src_node; addr->sq_port = cb->src_port; @@ -859,6 +1031,9 @@ static int qrtr_recvmsg(struct socket *sock, struct msghdr *msg, } out: + if (cb->confirm_rx) + qrtr_send_resume_tx(cb); + skb_free_datagram(sk, skb); release_sock(sk); diff --git a/net/rds/ib.c b/net/rds/ib.c index 3fd5f40189bd..a792d8a3872a 100644 --- a/net/rds/ib.c +++ b/net/rds/ib.c @@ -156,6 +156,13 @@ static void rds_ib_add_one(struct ib_device *device) has_fmr = (device->ops.alloc_fmr && device->ops.dealloc_fmr && device->ops.map_phys_fmr && device->ops.unmap_fmr); rds_ibdev->use_fastreg = (has_fr && !has_fmr); + rds_ibdev->odp_capable = + !!(device->attrs.device_cap_flags & + IB_DEVICE_ON_DEMAND_PAGING) && + !!(device->attrs.odp_caps.per_transport_caps.rc_odp_caps & + IB_ODP_SUPPORT_WRITE) && + !!(device->attrs.odp_caps.per_transport_caps.rc_odp_caps & + IB_ODP_SUPPORT_READ); rds_ibdev->fmr_max_remaps = device->attrs.max_map_per_fmr?: 32; rds_ibdev->max_1m_mrs = device->attrs.max_mr ? diff --git a/net/rds/ib.h b/net/rds/ib.h index 6e6f24753998..0296f1f7acda 100644 --- a/net/rds/ib.h +++ b/net/rds/ib.h @@ -247,7 +247,8 @@ struct rds_ib_device { struct ib_device *dev; struct ib_pd *pd; struct dma_pool *rid_hdrs_pool; /* RDS headers DMA pool */ - bool use_fastreg; + u8 use_fastreg:1; + u8 odp_capable:1; unsigned int max_mrs; struct rds_ib_mr_pool *mr_1m_pool; diff --git a/net/rds/ib_mr.h b/net/rds/ib_mr.h index 9045a8c0edff..0c8252d7fe2b 100644 --- a/net/rds/ib_mr.h +++ b/net/rds/ib_mr.h @@ -67,6 +67,7 @@ struct rds_ib_frmr { /* This is stored as mr->r_trans_private. */ struct rds_ib_mr { + struct delayed_work work; struct rds_ib_device *device; struct rds_ib_mr_pool *pool; struct rds_ib_connection *ic; @@ -81,9 +82,11 @@ struct rds_ib_mr { unsigned int sg_len; int sg_dma_len; + u8 odp:1; union { struct rds_ib_fmr fmr; struct rds_ib_frmr frmr; + struct ib_mr *mr; } u; }; @@ -122,12 +125,14 @@ void rds6_ib_get_mr_info(struct rds_ib_device *rds_ibdev, void rds_ib_destroy_mr_pool(struct rds_ib_mr_pool *); void *rds_ib_get_mr(struct scatterlist *sg, unsigned long nents, struct rds_sock *rs, u32 *key_ret, - struct rds_connection *conn); + struct rds_connection *conn, u64 start, u64 length, + int need_odp); void rds_ib_sync_mr(void *trans_private, int dir); void rds_ib_free_mr(void *trans_private, int invalidate); void rds_ib_flush_mrs(void); int rds_ib_mr_init(void); void rds_ib_mr_exit(void); +u32 rds_ib_get_lkey(void *trans_private); void __rds_ib_teardown_mr(struct rds_ib_mr *); void rds_ib_teardown_mr(struct rds_ib_mr *); diff --git a/net/rds/ib_rdma.c b/net/rds/ib_rdma.c index c8c1e3ae8d84..b34b24e237f8 100644 --- a/net/rds/ib_rdma.c +++ b/net/rds/ib_rdma.c @@ -37,8 +37,15 @@ #include "rds_single_path.h" #include "ib_mr.h" +#include "rds.h" struct workqueue_struct *rds_ib_mr_wq; +struct rds_ib_dereg_odp_mr { + struct work_struct work; + struct ib_mr *mr; +}; + +static void rds_ib_odp_mr_worker(struct work_struct *work); static struct rds_ib_device *rds_ib_get_device(__be32 ipaddr) { @@ -213,6 +220,9 @@ void rds_ib_sync_mr(void *trans_private, int direction) struct rds_ib_mr *ibmr = trans_private; struct rds_ib_device *rds_ibdev = ibmr->device; + if (ibmr->odp) + return; + switch (direction) { case DMA_FROM_DEVICE: ib_dma_sync_sg_for_cpu(rds_ibdev->dev, ibmr->sg, @@ -482,6 +492,16 @@ void rds_ib_free_mr(void *trans_private, int invalidate) rdsdebug("RDS/IB: free_mr nents %u\n", ibmr->sg_len); + if (ibmr->odp) { + /* A MR created and marked as use_once. We use delayed work, + * because there is a change that we are in interrupt and can't + * call to ib_dereg_mr() directly. + */ + INIT_DELAYED_WORK(&ibmr->work, rds_ib_odp_mr_worker); + queue_delayed_work(rds_ib_mr_wq, &ibmr->work, 0); + return; + } + /* Return it to the pool's free list */ if (rds_ibdev->use_fastreg) rds_ib_free_frmr_list(ibmr); @@ -526,9 +546,17 @@ void rds_ib_flush_mrs(void) up_read(&rds_ib_devices_lock); } +u32 rds_ib_get_lkey(void *trans_private) +{ + struct rds_ib_mr *ibmr = trans_private; + + return ibmr->u.mr->lkey; +} + void *rds_ib_get_mr(struct scatterlist *sg, unsigned long nents, struct rds_sock *rs, u32 *key_ret, - struct rds_connection *conn) + struct rds_connection *conn, + u64 start, u64 length, int need_odp) { struct rds_ib_device *rds_ibdev; struct rds_ib_mr *ibmr = NULL; @@ -541,6 +569,51 @@ void *rds_ib_get_mr(struct scatterlist *sg, unsigned long nents, goto out; } + if (need_odp == ODP_ZEROBASED || need_odp == ODP_VIRTUAL) { + u64 virt_addr = need_odp == ODP_ZEROBASED ? 0 : start; + int access_flags = + (IB_ACCESS_LOCAL_WRITE | IB_ACCESS_REMOTE_READ | + IB_ACCESS_REMOTE_WRITE | IB_ACCESS_REMOTE_ATOMIC | + IB_ACCESS_ON_DEMAND); + struct ib_sge sge = {}; + struct ib_mr *ib_mr; + + if (!rds_ibdev->odp_capable) { + ret = -EOPNOTSUPP; + goto out; + } + + ib_mr = ib_reg_user_mr(rds_ibdev->pd, start, length, virt_addr, + access_flags); + + if (IS_ERR(ib_mr)) { + rdsdebug("rds_ib_get_user_mr returned %d\n", + IS_ERR(ib_mr)); + ret = PTR_ERR(ib_mr); + goto out; + } + if (key_ret) + *key_ret = ib_mr->rkey; + + ibmr = kzalloc(sizeof(*ibmr), GFP_KERNEL); + if (!ibmr) { + ib_dereg_mr(ib_mr); + ret = -ENOMEM; + goto out; + } + ibmr->u.mr = ib_mr; + ibmr->odp = 1; + + sge.addr = virt_addr; + sge.length = length; + sge.lkey = ib_mr->lkey; + + ib_advise_mr(rds_ibdev->pd, + IB_UVERBS_ADVISE_MR_ADVICE_PREFETCH_WRITE, + IB_UVERBS_ADVISE_MR_FLAG_FLUSH, &sge, 1); + return ibmr; + } + if (conn) ic = conn->c_transport_data; @@ -629,3 +702,12 @@ void rds_ib_mr_exit(void) { destroy_workqueue(rds_ib_mr_wq); } + +static void rds_ib_odp_mr_worker(struct work_struct *work) +{ + struct rds_ib_mr *ibmr; + + ibmr = container_of(work, struct rds_ib_mr, work.work); + ib_dereg_mr(ibmr->u.mr); + kfree(ibmr); +} diff --git a/net/rds/ib_send.c b/net/rds/ib_send.c index d1cc1d7778d8..dfe778220657 100644 --- a/net/rds/ib_send.c +++ b/net/rds/ib_send.c @@ -39,6 +39,7 @@ #include "rds_single_path.h" #include "rds.h" #include "ib.h" +#include "ib_mr.h" /* * Convert IB-specific error message to RDS error message and call core @@ -635,6 +636,7 @@ int rds_ib_xmit(struct rds_connection *conn, struct rds_message *rm, send->s_sge[0].addr = ic->i_send_hdrs_dma[pos]; send->s_sge[0].length = sizeof(struct rds_header); + send->s_sge[0].lkey = ic->i_pd->local_dma_lkey; memcpy(ic->i_send_hdrs[pos], &rm->m_inc.i_hdr, sizeof(struct rds_header)); @@ -650,6 +652,7 @@ int rds_ib_xmit(struct rds_connection *conn, struct rds_message *rm, send->s_sge[1].addr = sg_dma_address(scat); send->s_sge[1].addr += rm->data.op_dmaoff; send->s_sge[1].length = len; + send->s_sge[1].lkey = ic->i_pd->local_dma_lkey; bytes_sent += len; rm->data.op_dmaoff += len; @@ -858,20 +861,29 @@ int rds_ib_xmit_rdma(struct rds_connection *conn, struct rm_rdma_op *op) int ret; int num_sge; int nr_sig = 0; + u64 odp_addr = op->op_odp_addr; + u32 odp_lkey = 0; /* map the op the first time we see it */ - if (!op->op_mapped) { - op->op_count = ib_dma_map_sg(ic->i_cm_id->device, - op->op_sg, op->op_nents, (op->op_write) ? - DMA_TO_DEVICE : DMA_FROM_DEVICE); - rdsdebug("ic %p mapping op %p: %d\n", ic, op, op->op_count); - if (op->op_count == 0) { - rds_ib_stats_inc(s_ib_tx_sg_mapping_failure); - ret = -ENOMEM; /* XXX ? */ - goto out; + if (!op->op_odp_mr) { + if (!op->op_mapped) { + op->op_count = + ib_dma_map_sg(ic->i_cm_id->device, op->op_sg, + op->op_nents, + (op->op_write) ? DMA_TO_DEVICE : + DMA_FROM_DEVICE); + rdsdebug("ic %p mapping op %p: %d\n", ic, op, + op->op_count); + if (op->op_count == 0) { + rds_ib_stats_inc(s_ib_tx_sg_mapping_failure); + ret = -ENOMEM; /* XXX ? */ + goto out; + } + op->op_mapped = 1; } - - op->op_mapped = 1; + } else { + op->op_count = op->op_nents; + odp_lkey = rds_ib_get_lkey(op->op_odp_mr->r_trans_private); } /* @@ -923,14 +935,20 @@ int rds_ib_xmit_rdma(struct rds_connection *conn, struct rm_rdma_op *op) for (j = 0; j < send->s_rdma_wr.wr.num_sge && scat != &op->op_sg[op->op_count]; j++) { len = sg_dma_len(scat); - send->s_sge[j].addr = sg_dma_address(scat); + if (!op->op_odp_mr) { + send->s_sge[j].addr = sg_dma_address(scat); + send->s_sge[j].lkey = ic->i_pd->local_dma_lkey; + } else { + send->s_sge[j].addr = odp_addr; + send->s_sge[j].lkey = odp_lkey; + } send->s_sge[j].length = len; - send->s_sge[j].lkey = ic->i_pd->local_dma_lkey; sent += len; rdsdebug("ic %p sent %d remote_addr %llu\n", ic, sent, remote_addr); remote_addr += len; + odp_addr += len; scat++; } diff --git a/net/rds/rdma.c b/net/rds/rdma.c index 916f5ec373d8..3341eee87bf9 100644 --- a/net/rds/rdma.c +++ b/net/rds/rdma.c @@ -156,11 +156,13 @@ void rds_rdma_drop_keys(struct rds_sock *rs) static int rds_pin_pages(unsigned long user_addr, unsigned int nr_pages, struct page **pages, int write) { + unsigned int gup_flags = FOLL_LONGTERM; int ret; - ret = get_user_pages_fast(user_addr, nr_pages, write ? FOLL_WRITE : 0, - pages); + if (write) + gup_flags |= FOLL_WRITE; + ret = get_user_pages_fast(user_addr, nr_pages, gup_flags, pages); if (ret >= 0 && ret < nr_pages) { while (ret--) put_page(pages[ret]); @@ -175,13 +177,14 @@ static int __rds_rdma_map(struct rds_sock *rs, struct rds_get_mr_args *args, struct rds_conn_path *cp) { struct rds_mr *mr = NULL, *found; + struct scatterlist *sg = NULL; unsigned int nr_pages; struct page **pages = NULL; - struct scatterlist *sg; void *trans_private; unsigned long flags; rds_rdma_cookie_t cookie; - unsigned int nents; + unsigned int nents = 0; + int need_odp = 0; long i; int ret; @@ -195,6 +198,21 @@ static int __rds_rdma_map(struct rds_sock *rs, struct rds_get_mr_args *args, goto out; } + /* If the combination of the addr and size requested for this memory + * region causes an integer overflow, return error. + */ + if (((args->vec.addr + args->vec.bytes) < args->vec.addr) || + PAGE_ALIGN(args->vec.addr + args->vec.bytes) < + (args->vec.addr + args->vec.bytes)) { + ret = -EINVAL; + goto out; + } + + if (!can_do_mlock()) { + ret = -EPERM; + goto out; + } + nr_pages = rds_pages_in_vec(&args->vec); if (nr_pages == 0) { ret = -EINVAL; @@ -248,36 +266,44 @@ static int __rds_rdma_map(struct rds_sock *rs, struct rds_get_mr_args *args, * the zero page. */ ret = rds_pin_pages(args->vec.addr, nr_pages, pages, 1); - if (ret < 0) - goto out; - - nents = ret; - sg = kcalloc(nents, sizeof(*sg), GFP_KERNEL); - if (!sg) { - ret = -ENOMEM; + if (ret == -EOPNOTSUPP) { + need_odp = 1; + } else if (ret <= 0) { goto out; - } - WARN_ON(!nents); - sg_init_table(sg, nents); - - /* Stick all pages into the scatterlist */ - for (i = 0 ; i < nents; i++) - sg_set_page(&sg[i], pages[i], PAGE_SIZE, 0); + } else { + nents = ret; + sg = kcalloc(nents, sizeof(*sg), GFP_KERNEL); + if (!sg) { + ret = -ENOMEM; + goto out; + } + WARN_ON(!nents); + sg_init_table(sg, nents); - rdsdebug("RDS: trans_private nents is %u\n", nents); + /* Stick all pages into the scatterlist */ + for (i = 0 ; i < nents; i++) + sg_set_page(&sg[i], pages[i], PAGE_SIZE, 0); + rdsdebug("RDS: trans_private nents is %u\n", nents); + } /* Obtain a transport specific MR. If this succeeds, the * s/g list is now owned by the MR. * Note that dma_map() implies that pending writes are * flushed to RAM, so no dma_sync is needed here. */ - trans_private = rs->rs_transport->get_mr(sg, nents, rs, - &mr->r_key, - cp ? cp->cp_conn : NULL); + trans_private = rs->rs_transport->get_mr( + sg, nents, rs, &mr->r_key, cp ? cp->cp_conn : NULL, + args->vec.addr, args->vec.bytes, + need_odp ? ODP_ZEROBASED : ODP_NOT_NEEDED); if (IS_ERR(trans_private)) { - for (i = 0 ; i < nents; i++) - put_page(sg_page(&sg[i])); - kfree(sg); + /* In ODP case, we don't GUP pages, so don't need + * to release anything. + */ + if (!need_odp) { + for (i = 0 ; i < nents; i++) + put_page(sg_page(&sg[i])); + kfree(sg); + } ret = PTR_ERR(trans_private); goto out; } @@ -291,7 +317,11 @@ static int __rds_rdma_map(struct rds_sock *rs, struct rds_get_mr_args *args, * map page aligned regions. So we keep the offset, and build * a 64bit cookie containing <R_Key, offset> and pass that * around. */ - cookie = rds_rdma_make_cookie(mr->r_key, args->vec.addr & ~PAGE_MASK); + if (need_odp) + cookie = rds_rdma_make_cookie(mr->r_key, 0); + else + cookie = rds_rdma_make_cookie(mr->r_key, + args->vec.addr & ~PAGE_MASK); if (cookie_ret) *cookie_ret = cookie; @@ -456,22 +486,26 @@ void rds_rdma_free_op(struct rm_rdma_op *ro) { unsigned int i; - for (i = 0; i < ro->op_nents; i++) { - struct page *page = sg_page(&ro->op_sg[i]); - - /* Mark page dirty if it was possibly modified, which - * is the case for a RDMA_READ which copies from remote - * to local memory */ - if (!ro->op_write) { - WARN_ON(!page->mapping && irqs_disabled()); - set_page_dirty(page); + if (ro->op_odp_mr) { + rds_mr_put(ro->op_odp_mr); + } else { + for (i = 0; i < ro->op_nents; i++) { + struct page *page = sg_page(&ro->op_sg[i]); + + /* Mark page dirty if it was possibly modified, which + * is the case for a RDMA_READ which copies from remote + * to local memory + */ + if (!ro->op_write) + set_page_dirty(page); + put_page(page); } - put_page(page); } kfree(ro->op_notifier); ro->op_notifier = NULL; ro->op_active = 0; + ro->op_odp_mr = NULL; } void rds_atomic_free_op(struct rm_atomic_op *ao) @@ -581,6 +615,7 @@ int rds_cmsg_rdma_args(struct rds_sock *rs, struct rds_message *rm, struct rds_iovec *iovs; unsigned int i, j; int ret = 0; + bool odp_supported = true; if (cmsg->cmsg_len < CMSG_LEN(sizeof(struct rds_rdma_args)) || rm->rdma.op_active) @@ -602,6 +637,9 @@ int rds_cmsg_rdma_args(struct rds_sock *rs, struct rds_message *rm, ret = -EINVAL; goto out_ret; } + /* odp-mr is not supported for multiple requests within one message */ + if (args->nr_local != 1) + odp_supported = false; iovs = vec->iov; @@ -623,6 +661,8 @@ int rds_cmsg_rdma_args(struct rds_sock *rs, struct rds_message *rm, op->op_silent = !!(args->flags & RDS_RDMA_SILENT); op->op_active = 1; op->op_recverr = rs->rs_recverr; + op->op_odp_mr = NULL; + WARN_ON(!nr_pages); op->op_sg = rds_message_alloc_sgs(rm, nr_pages, &ret); if (!op->op_sg) @@ -672,10 +712,44 @@ int rds_cmsg_rdma_args(struct rds_sock *rs, struct rds_message *rm, * If it's a READ operation, we need to pin the pages for writing. */ ret = rds_pin_pages(iov->addr, nr, pages, !op->op_write); - if (ret < 0) + if ((!odp_supported && ret <= 0) || + (odp_supported && ret <= 0 && ret != -EOPNOTSUPP)) goto out_pages; - else - ret = 0; + + if (ret == -EOPNOTSUPP) { + struct rds_mr *local_odp_mr; + + if (!rs->rs_transport->get_mr) { + ret = -EOPNOTSUPP; + goto out_pages; + } + local_odp_mr = + kzalloc(sizeof(*local_odp_mr), GFP_KERNEL); + if (!local_odp_mr) { + ret = -ENOMEM; + goto out_pages; + } + RB_CLEAR_NODE(&local_odp_mr->r_rb_node); + refcount_set(&local_odp_mr->r_refcount, 1); + local_odp_mr->r_trans = rs->rs_transport; + local_odp_mr->r_sock = rs; + local_odp_mr->r_trans_private = + rs->rs_transport->get_mr( + NULL, 0, rs, &local_odp_mr->r_key, NULL, + iov->addr, iov->bytes, ODP_VIRTUAL); + if (IS_ERR(local_odp_mr->r_trans_private)) { + ret = IS_ERR(local_odp_mr->r_trans_private); + rdsdebug("get_mr ret %d %p\"", ret, + local_odp_mr->r_trans_private); + kfree(local_odp_mr); + ret = -EOPNOTSUPP; + goto out_pages; + } + rdsdebug("Need odp; local_odp_mr %p trans_private %p\n", + local_odp_mr, local_odp_mr->r_trans_private); + op->op_odp_mr = local_odp_mr; + op->op_odp_addr = iov->addr; + } rdsdebug("RDS: nr_bytes %u nr %u iov->bytes %llu iov->addr %llx\n", nr_bytes, nr, iov->bytes, iov->addr); @@ -691,6 +765,7 @@ int rds_cmsg_rdma_args(struct rds_sock *rs, struct rds_message *rm, min_t(unsigned int, iov->bytes, PAGE_SIZE - offset), offset); + sg_dma_len(sg) = sg->length; rdsdebug("RDS: sg->offset %x sg->len %x iov->addr %llx iov->bytes %llu\n", sg->offset, sg->length, iov->addr, iov->bytes); @@ -709,6 +784,7 @@ int rds_cmsg_rdma_args(struct rds_sock *rs, struct rds_message *rm, goto out_pages; } op->op_bytes = nr_bytes; + ret = 0; out_pages: kfree(pages); @@ -755,7 +831,8 @@ int rds_cmsg_rdma_dest(struct rds_sock *rs, struct rds_message *rm, spin_unlock_irqrestore(&rs->rs_rdma_lock, flags); if (mr) { - mr->r_trans->sync_mr(mr->r_trans_private, DMA_TO_DEVICE); + mr->r_trans->sync_mr(mr->r_trans_private, + DMA_TO_DEVICE); rm->rdma.op_rdma_mr = mr; } return err; diff --git a/net/rds/rds.h b/net/rds/rds.h index 53e86911773a..e4a603523083 100644 --- a/net/rds/rds.h +++ b/net/rds/rds.h @@ -40,7 +40,6 @@ #ifdef ATOMIC64_INIT #define KERNEL_HAS_ATOMIC64 #endif - #ifdef RDS_DEBUG #define rdsdebug(fmt, args...) pr_debug("%s(): " fmt, __func__ , ##args) #else @@ -478,6 +477,9 @@ struct rds_message { struct rds_notifier *op_notifier; struct rds_mr *op_rdma_mr; + + u64 op_odp_addr; + struct rds_mr *op_odp_mr; } rdma; struct rm_data_op { unsigned int op_active:1; @@ -573,7 +575,8 @@ struct rds_transport { void (*exit)(void); void *(*get_mr)(struct scatterlist *sg, unsigned long nr_sg, struct rds_sock *rs, u32 *key_ret, - struct rds_connection *conn); + struct rds_connection *conn, + u64 start, u64 length, int need_odp); void (*sync_mr)(void *trans_private, int direction); void (*free_mr)(void *trans_private, int invalidate); void (*flush_mrs)(void); @@ -956,6 +959,12 @@ static inline bool rds_destroy_pending(struct rds_connection *conn) (conn->c_trans->t_unloading && conn->c_trans->t_unloading(conn)); } +enum { + ODP_NOT_NEEDED, + ODP_ZEROBASED, + ODP_VIRTUAL +}; + /* stats.c */ DECLARE_PER_CPU_SHARED_ALIGNED(struct rds_statistics, rds_stats); #define rds_stats_inc_which(which, member) do { \ diff --git a/net/rose/rose_route.c b/net/rose/rose_route.c index c53307623236..5277631fa14c 100644 --- a/net/rose/rose_route.c +++ b/net/rose/rose_route.c @@ -696,7 +696,6 @@ struct rose_neigh *rose_get_neigh(rose_address *addr, unsigned char *cause, for (i = 0; i < node->count; i++) { if (!rose_ftimer_running(node->neighbour[i])) { res = node->neighbour[i]; - failed = 0; goto out; } failed = 1; diff --git a/net/rxrpc/input.c b/net/rxrpc/input.c index 86bd133b4fa0..96d54e5bf7bc 100644 --- a/net/rxrpc/input.c +++ b/net/rxrpc/input.c @@ -413,7 +413,7 @@ static void rxrpc_input_data(struct rxrpc_call *call, struct sk_buff *skb) { struct rxrpc_skb_priv *sp = rxrpc_skb(skb); enum rxrpc_call_state state; - unsigned int j; + unsigned int j, nr_subpackets; rxrpc_serial_t serial = sp->hdr.serial, ack_serial = 0; rxrpc_seq_t seq0 = sp->hdr.seq, hard_ack; bool immediate_ack = false, jumbo_bad = false; @@ -457,7 +457,8 @@ static void rxrpc_input_data(struct rxrpc_call *call, struct sk_buff *skb) call->ackr_prev_seq = seq0; hard_ack = READ_ONCE(call->rx_hard_ack); - if (sp->nr_subpackets > 1) { + nr_subpackets = sp->nr_subpackets; + if (nr_subpackets > 1) { if (call->nr_jumbo_bad > 3) { ack = RXRPC_ACK_NOSPACE; ack_serial = serial; @@ -465,11 +466,11 @@ static void rxrpc_input_data(struct rxrpc_call *call, struct sk_buff *skb) } } - for (j = 0; j < sp->nr_subpackets; j++) { + for (j = 0; j < nr_subpackets; j++) { rxrpc_serial_t serial = sp->hdr.serial + j; rxrpc_seq_t seq = seq0 + j; unsigned int ix = seq & RXRPC_RXTX_BUFF_MASK; - bool terminal = (j == sp->nr_subpackets - 1); + bool terminal = (j == nr_subpackets - 1); bool last = terminal && (sp->rx_flags & RXRPC_SKB_INCL_LAST); u8 flags, annotation = j; @@ -506,7 +507,7 @@ static void rxrpc_input_data(struct rxrpc_call *call, struct sk_buff *skb) } if (call->rxtx_buffer[ix]) { - rxrpc_input_dup_data(call, seq, sp->nr_subpackets > 1, + rxrpc_input_dup_data(call, seq, nr_subpackets > 1, &jumbo_bad); if (ack != RXRPC_ACK_DUPLICATE) { ack = RXRPC_ACK_DUPLICATE; @@ -564,6 +565,7 @@ static void rxrpc_input_data(struct rxrpc_call *call, struct sk_buff *skb) * ring. */ skb = NULL; + sp = NULL; } if (last) { diff --git a/net/sched/Kconfig b/net/sched/Kconfig index 2985509147a2..edde0e519438 100644 --- a/net/sched/Kconfig +++ b/net/sched/Kconfig @@ -366,6 +366,19 @@ config NET_SCH_PIE If unsure, say N. +config NET_SCH_FQ_PIE + depends on NET_SCH_PIE + tristate "Flow Queue Proportional Integral controller Enhanced (FQ-PIE)" + help + Say Y here if you want to use the Flow Queue Proportional Integral + controller Enhanced (FQ-PIE) packet scheduling algorithm. + For more information, please see https://tools.ietf.org/html/rfc8033 + + To compile this driver as a module, choose M here: the module + will be called sch_fq_pie. + + If unsure, say N. + config NET_SCH_INGRESS tristate "Ingress/classifier-action Qdisc" depends on NET_CLS_ACT @@ -409,6 +422,23 @@ config NET_SCH_PLUG To compile this code as a module, choose M here: the module will be called sch_plug. +config NET_SCH_ETS + tristate "Enhanced transmission selection scheduler (ETS)" + help + The Enhanced Transmission Selection scheduler is a classful + queuing discipline that merges functionality of PRIO and DRR + qdiscs in one scheduler. ETS makes it easy to configure a set of + strict and bandwidth-sharing bands to implement the transmission + selection described in 802.1Qaz. + + Say Y here if you want to use the ETS packet scheduling + algorithm. + + To compile this driver as a module, choose M here: the module + will be called sch_ets. + + If unsure, say N. + menuconfig NET_SCH_DEFAULT bool "Allow override default queue discipline" ---help--- diff --git a/net/sched/Makefile b/net/sched/Makefile index 415d1e1f237e..31c367a6cd09 100644 --- a/net/sched/Makefile +++ b/net/sched/Makefile @@ -48,6 +48,7 @@ obj-$(CONFIG_NET_SCH_ATM) += sch_atm.o obj-$(CONFIG_NET_SCH_NETEM) += sch_netem.o obj-$(CONFIG_NET_SCH_DRR) += sch_drr.o obj-$(CONFIG_NET_SCH_PLUG) += sch_plug.o +obj-$(CONFIG_NET_SCH_ETS) += sch_ets.o obj-$(CONFIG_NET_SCH_MQPRIO) += sch_mqprio.o obj-$(CONFIG_NET_SCH_SKBPRIO) += sch_skbprio.o obj-$(CONFIG_NET_SCH_CHOKE) += sch_choke.o @@ -58,6 +59,7 @@ obj-$(CONFIG_NET_SCH_CAKE) += sch_cake.o obj-$(CONFIG_NET_SCH_FQ) += sch_fq.o obj-$(CONFIG_NET_SCH_HHF) += sch_hhf.o obj-$(CONFIG_NET_SCH_PIE) += sch_pie.o +obj-$(CONFIG_NET_SCH_FQ_PIE) += sch_fq_pie.o obj-$(CONFIG_NET_SCH_CBS) += sch_cbs.o obj-$(CONFIG_NET_SCH_ETF) += sch_etf.o obj-$(CONFIG_NET_SCH_TAPRIO) += sch_taprio.o diff --git a/net/sched/cls_basic.c b/net/sched/cls_basic.c index 4aafbe3d435c..f256a7c69093 100644 --- a/net/sched/cls_basic.c +++ b/net/sched/cls_basic.c @@ -263,12 +263,17 @@ skip: } } -static void basic_bind_class(void *fh, u32 classid, unsigned long cl) +static void basic_bind_class(void *fh, u32 classid, unsigned long cl, void *q, + unsigned long base) { struct basic_filter *f = fh; - if (f && f->res.classid == classid) - f->res.class = cl; + if (f && f->res.classid == classid) { + if (cl) + __tcf_bind_filter(q, &f->res, base); + else + __tcf_unbind_filter(q, &f->res); + } } static int basic_dump(struct net *net, struct tcf_proto *tp, void *fh, diff --git a/net/sched/cls_bpf.c b/net/sched/cls_bpf.c index 8229ed4a67be..6e3e63db0e01 100644 --- a/net/sched/cls_bpf.c +++ b/net/sched/cls_bpf.c @@ -631,12 +631,17 @@ nla_put_failure: return -1; } -static void cls_bpf_bind_class(void *fh, u32 classid, unsigned long cl) +static void cls_bpf_bind_class(void *fh, u32 classid, unsigned long cl, + void *q, unsigned long base) { struct cls_bpf_prog *prog = fh; - if (prog && prog->res.classid == classid) - prog->res.class = cl; + if (prog && prog->res.classid == classid) { + if (cl) + __tcf_bind_filter(q, &prog->res, base); + else + __tcf_unbind_filter(q, &prog->res); + } } static void cls_bpf_walk(struct tcf_proto *tp, struct tcf_walker *arg, diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c index b0f42e62dd76..f9c0d1e8d380 100644 --- a/net/sched/cls_flower.c +++ b/net/sched/cls_flower.c @@ -2765,12 +2765,17 @@ nla_put_failure: return -EMSGSIZE; } -static void fl_bind_class(void *fh, u32 classid, unsigned long cl) +static void fl_bind_class(void *fh, u32 classid, unsigned long cl, void *q, + unsigned long base) { struct cls_fl_filter *f = fh; - if (f && f->res.classid == classid) - f->res.class = cl; + if (f && f->res.classid == classid) { + if (cl) + __tcf_bind_filter(q, &f->res, base); + else + __tcf_unbind_filter(q, &f->res); + } } static bool fl_delete_empty(struct tcf_proto *tp) diff --git a/net/sched/cls_fw.c b/net/sched/cls_fw.c index c9496c920d6f..ec945294626a 100644 --- a/net/sched/cls_fw.c +++ b/net/sched/cls_fw.c @@ -419,12 +419,17 @@ nla_put_failure: return -1; } -static void fw_bind_class(void *fh, u32 classid, unsigned long cl) +static void fw_bind_class(void *fh, u32 classid, unsigned long cl, void *q, + unsigned long base) { struct fw_filter *f = fh; - if (f && f->res.classid == classid) - f->res.class = cl; + if (f && f->res.classid == classid) { + if (cl) + __tcf_bind_filter(q, &f->res, base); + else + __tcf_unbind_filter(q, &f->res); + } } static struct tcf_proto_ops cls_fw_ops __read_mostly = { diff --git a/net/sched/cls_matchall.c b/net/sched/cls_matchall.c index 7fc2eb62aa98..039cc86974f4 100644 --- a/net/sched/cls_matchall.c +++ b/net/sched/cls_matchall.c @@ -393,12 +393,17 @@ nla_put_failure: return -1; } -static void mall_bind_class(void *fh, u32 classid, unsigned long cl) +static void mall_bind_class(void *fh, u32 classid, unsigned long cl, void *q, + unsigned long base) { struct cls_mall_head *head = fh; - if (head && head->res.classid == classid) - head->res.class = cl; + if (head && head->res.classid == classid) { + if (cl) + __tcf_bind_filter(q, &head->res, base); + else + __tcf_unbind_filter(q, &head->res); + } } static struct tcf_proto_ops cls_mall_ops __read_mostly = { diff --git a/net/sched/cls_route.c b/net/sched/cls_route.c index 2d9e0b4484ea..6f8786b06bde 100644 --- a/net/sched/cls_route.c +++ b/net/sched/cls_route.c @@ -641,12 +641,17 @@ nla_put_failure: return -1; } -static void route4_bind_class(void *fh, u32 classid, unsigned long cl) +static void route4_bind_class(void *fh, u32 classid, unsigned long cl, void *q, + unsigned long base) { struct route4_filter *f = fh; - if (f && f->res.classid == classid) - f->res.class = cl; + if (f && f->res.classid == classid) { + if (cl) + __tcf_bind_filter(q, &f->res, base); + else + __tcf_unbind_filter(q, &f->res); + } } static struct tcf_proto_ops cls_route4_ops __read_mostly = { diff --git a/net/sched/cls_rsvp.h b/net/sched/cls_rsvp.h index 2f3c03b25d5d..c22624131949 100644 --- a/net/sched/cls_rsvp.h +++ b/net/sched/cls_rsvp.h @@ -738,12 +738,17 @@ nla_put_failure: return -1; } -static void rsvp_bind_class(void *fh, u32 classid, unsigned long cl) +static void rsvp_bind_class(void *fh, u32 classid, unsigned long cl, void *q, + unsigned long base) { struct rsvp_filter *f = fh; - if (f && f->res.classid == classid) - f->res.class = cl; + if (f && f->res.classid == classid) { + if (cl) + __tcf_bind_filter(q, &f->res, base); + else + __tcf_unbind_filter(q, &f->res); + } } static struct tcf_proto_ops RSVP_OPS __read_mostly = { diff --git a/net/sched/cls_tcindex.c b/net/sched/cls_tcindex.c index e573e5a5c794..3d4a1280352f 100644 --- a/net/sched/cls_tcindex.c +++ b/net/sched/cls_tcindex.c @@ -654,12 +654,17 @@ nla_put_failure: return -1; } -static void tcindex_bind_class(void *fh, u32 classid, unsigned long cl) +static void tcindex_bind_class(void *fh, u32 classid, unsigned long cl, + void *q, unsigned long base) { struct tcindex_filter_result *r = fh; - if (r && r->res.classid == classid) - r->res.class = cl; + if (r && r->res.classid == classid) { + if (cl) + __tcf_bind_filter(q, &r->res, base); + else + __tcf_unbind_filter(q, &r->res); + } } static struct tcf_proto_ops cls_tcindex_ops __read_mostly = { diff --git a/net/sched/cls_u32.c b/net/sched/cls_u32.c index a0e6fac613de..e15ff335953d 100644 --- a/net/sched/cls_u32.c +++ b/net/sched/cls_u32.c @@ -1255,12 +1255,17 @@ static int u32_reoffload(struct tcf_proto *tp, bool add, flow_setup_cb_t *cb, return 0; } -static void u32_bind_class(void *fh, u32 classid, unsigned long cl) +static void u32_bind_class(void *fh, u32 classid, unsigned long cl, void *q, + unsigned long base) { struct tc_u_knode *n = fh; - if (n && n->res.classid == classid) - n->res.class = cl; + if (n && n->res.classid == classid) { + if (cl) + __tcf_bind_filter(q, &n->res, base); + else + __tcf_unbind_filter(q, &n->res); + } } static int u32_dump(struct net *net, struct tcf_proto *tp, void *fh, diff --git a/net/sched/ematch.c b/net/sched/ematch.c index d0140a92694a..dd3b8c11a2e0 100644 --- a/net/sched/ematch.c +++ b/net/sched/ematch.c @@ -238,6 +238,9 @@ static int tcf_em_validate(struct tcf_proto *tp, goto errout; if (em->ops->change) { + err = -EINVAL; + if (em_hdr->flags & TCF_EM_SIMPLE) + goto errout; err = em->ops->change(net, data, data_len, em); if (err < 0) goto errout; diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c index 1047825d9f48..50794125bf02 100644 --- a/net/sched/sch_api.c +++ b/net/sched/sch_api.c @@ -1891,8 +1891,9 @@ static int tclass_del_notify(struct net *net, struct tcf_bind_args { struct tcf_walker w; - u32 classid; + unsigned long base; unsigned long cl; + u32 classid; }; static int tcf_node_bind(struct tcf_proto *tp, void *n, struct tcf_walker *arg) @@ -1903,28 +1904,30 @@ static int tcf_node_bind(struct tcf_proto *tp, void *n, struct tcf_walker *arg) struct Qdisc *q = tcf_block_q(tp->chain->block); sch_tree_lock(q); - tp->ops->bind_class(n, a->classid, a->cl); + tp->ops->bind_class(n, a->classid, a->cl, q, a->base); sch_tree_unlock(q); } return 0; } -static void tc_bind_tclass(struct Qdisc *q, u32 portid, u32 clid, - unsigned long new_cl) +struct tc_bind_class_args { + struct qdisc_walker w; + unsigned long new_cl; + u32 portid; + u32 clid; +}; + +static int tc_bind_class_walker(struct Qdisc *q, unsigned long cl, + struct qdisc_walker *w) { + struct tc_bind_class_args *a = (struct tc_bind_class_args *)w; const struct Qdisc_class_ops *cops = q->ops->cl_ops; struct tcf_block *block; struct tcf_chain *chain; - unsigned long cl; - cl = cops->find(q, portid); - if (!cl) - return; - if (!cops->tcf_block) - return; block = cops->tcf_block(q, cl, NULL); if (!block) - return; + return 0; for (chain = tcf_get_next_chain(block, NULL); chain; chain = tcf_get_next_chain(block, chain)) { @@ -1935,11 +1938,29 @@ static void tc_bind_tclass(struct Qdisc *q, u32 portid, u32 clid, struct tcf_bind_args arg = {}; arg.w.fn = tcf_node_bind; - arg.classid = clid; - arg.cl = new_cl; + arg.classid = a->clid; + arg.base = cl; + arg.cl = a->new_cl; tp->ops->walk(tp, &arg.w, true); } } + + return 0; +} + +static void tc_bind_tclass(struct Qdisc *q, u32 portid, u32 clid, + unsigned long new_cl) +{ + const struct Qdisc_class_ops *cops = q->ops->cl_ops; + struct tc_bind_class_args args = {}; + + if (!cops->tcf_block) + return; + args.portid = portid; + args.clid = clid; + args.new_cl = new_cl; + args.w.fn = tc_bind_class_walker; + q->ops->cl_ops->walk(q, &args.w); } #else diff --git a/net/sched/sch_cake.c b/net/sched/sch_cake.c index 2277369feae5..1496e87cd07b 100644 --- a/net/sched/sch_cake.c +++ b/net/sched/sch_cake.c @@ -173,8 +173,7 @@ struct cake_tin_data { u64 tin_rate_bps; u16 tin_rate_shft; - u16 tin_quantum_prio; - u16 tin_quantum_band; + u16 tin_quantum; s32 tin_deficit; u32 tin_backlog; u32 tin_dropped; @@ -1683,8 +1682,7 @@ static s32 cake_enqueue(struct sk_buff *skb, struct Qdisc *sch, if (IS_ERR_OR_NULL(segs)) return qdisc_drop(skb, sch, to_free); - while (segs) { - nskb = segs->next; + skb_list_walk_safe(segs, segs, nskb) { skb_mark_not_on_list(segs); qdisc_skb_cb(segs)->pkt_len = segs->len; cobalt_set_enqueue_time(segs, now); @@ -1697,7 +1695,6 @@ static s32 cake_enqueue(struct sk_buff *skb, struct Qdisc *sch, slen += segs->len; q->buffer_used += segs->truesize; b->packets++; - segs = nskb; } /* stats */ @@ -1919,7 +1916,7 @@ begin: while (b->tin_deficit < 0 || !(b->sparse_flow_count + b->bulk_flow_count)) { if (b->tin_deficit <= 0) - b->tin_deficit += b->tin_quantum_band; + b->tin_deficit += b->tin_quantum; if (b->sparse_flow_count + b->bulk_flow_count) empty = false; @@ -2241,8 +2238,7 @@ static int cake_config_besteffort(struct Qdisc *sch) cake_set_rate(b, rate, mtu, us_to_ns(q->target), us_to_ns(q->interval)); - b->tin_quantum_band = 65535; - b->tin_quantum_prio = 65535; + b->tin_quantum = 65535; return 0; } @@ -2253,8 +2249,7 @@ static int cake_config_precedence(struct Qdisc *sch) struct cake_sched_data *q = qdisc_priv(sch); u32 mtu = psched_mtu(qdisc_dev(sch)); u64 rate = q->rate_bps; - u32 quantum1 = 256; - u32 quantum2 = 256; + u32 quantum = 256; u32 i; q->tin_cnt = 8; @@ -2267,18 +2262,14 @@ static int cake_config_precedence(struct Qdisc *sch) cake_set_rate(b, rate, mtu, us_to_ns(q->target), us_to_ns(q->interval)); - b->tin_quantum_prio = max_t(u16, 1U, quantum1); - b->tin_quantum_band = max_t(u16, 1U, quantum2); + b->tin_quantum = max_t(u16, 1U, quantum); /* calculate next class's parameters */ rate *= 7; rate >>= 3; - quantum1 *= 3; - quantum1 >>= 1; - - quantum2 *= 7; - quantum2 >>= 3; + quantum *= 7; + quantum >>= 3; } return 0; @@ -2347,8 +2338,7 @@ static int cake_config_diffserv8(struct Qdisc *sch) struct cake_sched_data *q = qdisc_priv(sch); u32 mtu = psched_mtu(qdisc_dev(sch)); u64 rate = q->rate_bps; - u32 quantum1 = 256; - u32 quantum2 = 256; + u32 quantum = 256; u32 i; q->tin_cnt = 8; @@ -2364,18 +2354,14 @@ static int cake_config_diffserv8(struct Qdisc *sch) cake_set_rate(b, rate, mtu, us_to_ns(q->target), us_to_ns(q->interval)); - b->tin_quantum_prio = max_t(u16, 1U, quantum1); - b->tin_quantum_band = max_t(u16, 1U, quantum2); + b->tin_quantum = max_t(u16, 1U, quantum); /* calculate next class's parameters */ rate *= 7; rate >>= 3; - quantum1 *= 3; - quantum1 >>= 1; - - quantum2 *= 7; - quantum2 >>= 3; + quantum *= 7; + quantum >>= 3; } return 0; @@ -2414,17 +2400,11 @@ static int cake_config_diffserv4(struct Qdisc *sch) cake_set_rate(&q->tins[3], rate >> 2, mtu, us_to_ns(q->target), us_to_ns(q->interval)); - /* priority weights */ - q->tins[0].tin_quantum_prio = quantum; - q->tins[1].tin_quantum_prio = quantum >> 4; - q->tins[2].tin_quantum_prio = quantum << 2; - q->tins[3].tin_quantum_prio = quantum << 4; - /* bandwidth-sharing weights */ - q->tins[0].tin_quantum_band = quantum; - q->tins[1].tin_quantum_band = quantum >> 4; - q->tins[2].tin_quantum_band = quantum >> 1; - q->tins[3].tin_quantum_band = quantum >> 2; + q->tins[0].tin_quantum = quantum; + q->tins[1].tin_quantum = quantum >> 4; + q->tins[2].tin_quantum = quantum >> 1; + q->tins[3].tin_quantum = quantum >> 2; return 0; } @@ -2455,15 +2435,10 @@ static int cake_config_diffserv3(struct Qdisc *sch) cake_set_rate(&q->tins[2], rate >> 2, mtu, us_to_ns(q->target), us_to_ns(q->interval)); - /* priority weights */ - q->tins[0].tin_quantum_prio = quantum; - q->tins[1].tin_quantum_prio = quantum >> 4; - q->tins[2].tin_quantum_prio = quantum << 4; - /* bandwidth-sharing weights */ - q->tins[0].tin_quantum_band = quantum; - q->tins[1].tin_quantum_band = quantum >> 4; - q->tins[2].tin_quantum_band = quantum >> 2; + q->tins[0].tin_quantum = quantum; + q->tins[1].tin_quantum = quantum >> 4; + q->tins[2].tin_quantum = quantum >> 2; return 0; } diff --git a/net/sched/sch_ets.c b/net/sched/sch_ets.c new file mode 100644 index 000000000000..a87e9159338c --- /dev/null +++ b/net/sched/sch_ets.c @@ -0,0 +1,828 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * net/sched/sch_ets.c Enhanced Transmission Selection scheduler + * + * Description + * ----------- + * + * The Enhanced Transmission Selection scheduler is a classful queuing + * discipline that merges functionality of PRIO and DRR qdiscs in one scheduler. + * ETS makes it easy to configure a set of strict and bandwidth-sharing bands to + * implement the transmission selection described in 802.1Qaz. + * + * Although ETS is technically classful, it's not possible to add and remove + * classes at will. Instead one specifies number of classes, how many are + * PRIO-like and how many DRR-like, and quanta for the latter. + * + * Algorithm + * --------- + * + * The strict classes, if any, are tried for traffic first: first band 0, if it + * has no traffic then band 1, etc. + * + * When there is no traffic in any of the strict queues, the bandwidth-sharing + * ones are tried next. Each band is assigned a deficit counter, initialized to + * "quantum" of that band. ETS maintains a list of active bandwidth-sharing + * bands whose qdiscs are non-empty. A packet is dequeued from the band at the + * head of the list if the packet size is smaller or equal to the deficit + * counter. If the counter is too small, it is increased by "quantum" and the + * scheduler moves on to the next band in the active list. + */ + +#include <linux/module.h> +#include <net/gen_stats.h> +#include <net/netlink.h> +#include <net/pkt_cls.h> +#include <net/pkt_sched.h> +#include <net/sch_generic.h> + +struct ets_class { + struct list_head alist; /* In struct ets_sched.active. */ + struct Qdisc *qdisc; + u32 quantum; + u32 deficit; + struct gnet_stats_basic_packed bstats; + struct gnet_stats_queue qstats; +}; + +struct ets_sched { + struct list_head active; + struct tcf_proto __rcu *filter_list; + struct tcf_block *block; + unsigned int nbands; + unsigned int nstrict; + u8 prio2band[TC_PRIO_MAX + 1]; + struct ets_class classes[TCQ_ETS_MAX_BANDS]; +}; + +static const struct nla_policy ets_policy[TCA_ETS_MAX + 1] = { + [TCA_ETS_NBANDS] = { .type = NLA_U8 }, + [TCA_ETS_NSTRICT] = { .type = NLA_U8 }, + [TCA_ETS_QUANTA] = { .type = NLA_NESTED }, + [TCA_ETS_PRIOMAP] = { .type = NLA_NESTED }, +}; + +static const struct nla_policy ets_priomap_policy[TCA_ETS_MAX + 1] = { + [TCA_ETS_PRIOMAP_BAND] = { .type = NLA_U8 }, +}; + +static const struct nla_policy ets_quanta_policy[TCA_ETS_MAX + 1] = { + [TCA_ETS_QUANTA_BAND] = { .type = NLA_U32 }, +}; + +static const struct nla_policy ets_class_policy[TCA_ETS_MAX + 1] = { + [TCA_ETS_QUANTA_BAND] = { .type = NLA_U32 }, +}; + +static int ets_quantum_parse(struct Qdisc *sch, const struct nlattr *attr, + unsigned int *quantum, + struct netlink_ext_ack *extack) +{ + *quantum = nla_get_u32(attr); + if (!*quantum) { + NL_SET_ERR_MSG(extack, "ETS quantum cannot be zero"); + return -EINVAL; + } + return 0; +} + +static struct ets_class * +ets_class_from_arg(struct Qdisc *sch, unsigned long arg) +{ + struct ets_sched *q = qdisc_priv(sch); + + return &q->classes[arg - 1]; +} + +static u32 ets_class_id(struct Qdisc *sch, const struct ets_class *cl) +{ + struct ets_sched *q = qdisc_priv(sch); + int band = cl - q->classes; + + return TC_H_MAKE(sch->handle, band + 1); +} + +static void ets_offload_change(struct Qdisc *sch) +{ + struct net_device *dev = qdisc_dev(sch); + struct ets_sched *q = qdisc_priv(sch); + struct tc_ets_qopt_offload qopt; + unsigned int w_psum_prev = 0; + unsigned int q_psum = 0; + unsigned int q_sum = 0; + unsigned int quantum; + unsigned int w_psum; + unsigned int weight; + unsigned int i; + + if (!tc_can_offload(dev) || !dev->netdev_ops->ndo_setup_tc) + return; + + qopt.command = TC_ETS_REPLACE; + qopt.handle = sch->handle; + qopt.parent = sch->parent; + qopt.replace_params.bands = q->nbands; + qopt.replace_params.qstats = &sch->qstats; + memcpy(&qopt.replace_params.priomap, + q->prio2band, sizeof(q->prio2band)); + + for (i = 0; i < q->nbands; i++) + q_sum += q->classes[i].quantum; + + for (i = 0; i < q->nbands; i++) { + quantum = q->classes[i].quantum; + q_psum += quantum; + w_psum = quantum ? q_psum * 100 / q_sum : 0; + weight = w_psum - w_psum_prev; + w_psum_prev = w_psum; + + qopt.replace_params.quanta[i] = quantum; + qopt.replace_params.weights[i] = weight; + } + + dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_QDISC_ETS, &qopt); +} + +static void ets_offload_destroy(struct Qdisc *sch) +{ + struct net_device *dev = qdisc_dev(sch); + struct tc_ets_qopt_offload qopt; + + if (!tc_can_offload(dev) || !dev->netdev_ops->ndo_setup_tc) + return; + + qopt.command = TC_ETS_DESTROY; + qopt.handle = sch->handle; + qopt.parent = sch->parent; + dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_QDISC_ETS, &qopt); +} + +static void ets_offload_graft(struct Qdisc *sch, struct Qdisc *new, + struct Qdisc *old, unsigned long arg, + struct netlink_ext_ack *extack) +{ + struct net_device *dev = qdisc_dev(sch); + struct tc_ets_qopt_offload qopt; + + qopt.command = TC_ETS_GRAFT; + qopt.handle = sch->handle; + qopt.parent = sch->parent; + qopt.graft_params.band = arg - 1; + qopt.graft_params.child_handle = new->handle; + + qdisc_offload_graft_helper(dev, sch, new, old, TC_SETUP_QDISC_ETS, + &qopt, extack); +} + +static int ets_offload_dump(struct Qdisc *sch) +{ + struct tc_ets_qopt_offload qopt; + + qopt.command = TC_ETS_STATS; + qopt.handle = sch->handle; + qopt.parent = sch->parent; + qopt.stats.bstats = &sch->bstats; + qopt.stats.qstats = &sch->qstats; + + return qdisc_offload_dump_helper(sch, TC_SETUP_QDISC_ETS, &qopt); +} + +static bool ets_class_is_strict(struct ets_sched *q, const struct ets_class *cl) +{ + unsigned int band = cl - q->classes; + + return band < q->nstrict; +} + +static int ets_class_change(struct Qdisc *sch, u32 classid, u32 parentid, + struct nlattr **tca, unsigned long *arg, + struct netlink_ext_ack *extack) +{ + struct ets_class *cl = ets_class_from_arg(sch, *arg); + struct ets_sched *q = qdisc_priv(sch); + struct nlattr *opt = tca[TCA_OPTIONS]; + struct nlattr *tb[TCA_ETS_MAX + 1]; + unsigned int quantum; + int err; + + /* Classes can be added and removed only through Qdisc_ops.change + * interface. + */ + if (!cl) { + NL_SET_ERR_MSG(extack, "Fine-grained class addition and removal is not supported"); + return -EOPNOTSUPP; + } + + if (!opt) { + NL_SET_ERR_MSG(extack, "ETS options are required for this operation"); + return -EINVAL; + } + + err = nla_parse_nested(tb, TCA_ETS_MAX, opt, ets_class_policy, extack); + if (err < 0) + return err; + + if (!tb[TCA_ETS_QUANTA_BAND]) + /* Nothing to configure. */ + return 0; + + if (ets_class_is_strict(q, cl)) { + NL_SET_ERR_MSG(extack, "Strict bands do not have a configurable quantum"); + return -EINVAL; + } + + err = ets_quantum_parse(sch, tb[TCA_ETS_QUANTA_BAND], &quantum, + extack); + if (err) + return err; + + sch_tree_lock(sch); + cl->quantum = quantum; + sch_tree_unlock(sch); + + ets_offload_change(sch); + return 0; +} + +static int ets_class_graft(struct Qdisc *sch, unsigned long arg, + struct Qdisc *new, struct Qdisc **old, + struct netlink_ext_ack *extack) +{ + struct ets_class *cl = ets_class_from_arg(sch, arg); + + if (!new) { + new = qdisc_create_dflt(sch->dev_queue, &pfifo_qdisc_ops, + ets_class_id(sch, cl), NULL); + if (!new) + new = &noop_qdisc; + else + qdisc_hash_add(new, true); + } + + *old = qdisc_replace(sch, new, &cl->qdisc); + ets_offload_graft(sch, new, *old, arg, extack); + return 0; +} + +static struct Qdisc *ets_class_leaf(struct Qdisc *sch, unsigned long arg) +{ + struct ets_class *cl = ets_class_from_arg(sch, arg); + + return cl->qdisc; +} + +static unsigned long ets_class_find(struct Qdisc *sch, u32 classid) +{ + unsigned long band = TC_H_MIN(classid); + struct ets_sched *q = qdisc_priv(sch); + + if (band - 1 >= q->nbands) + return 0; + return band; +} + +static void ets_class_qlen_notify(struct Qdisc *sch, unsigned long arg) +{ + struct ets_class *cl = ets_class_from_arg(sch, arg); + struct ets_sched *q = qdisc_priv(sch); + + /* We get notified about zero-length child Qdiscs as well if they are + * offloaded. Those aren't on the active list though, so don't attempt + * to remove them. + */ + if (!ets_class_is_strict(q, cl) && sch->q.qlen) + list_del(&cl->alist); +} + +static int ets_class_dump(struct Qdisc *sch, unsigned long arg, + struct sk_buff *skb, struct tcmsg *tcm) +{ + struct ets_class *cl = ets_class_from_arg(sch, arg); + struct ets_sched *q = qdisc_priv(sch); + struct nlattr *nest; + + tcm->tcm_parent = TC_H_ROOT; + tcm->tcm_handle = ets_class_id(sch, cl); + tcm->tcm_info = cl->qdisc->handle; + + nest = nla_nest_start_noflag(skb, TCA_OPTIONS); + if (!nest) + goto nla_put_failure; + if (!ets_class_is_strict(q, cl)) { + if (nla_put_u32(skb, TCA_ETS_QUANTA_BAND, cl->quantum)) + goto nla_put_failure; + } + return nla_nest_end(skb, nest); + +nla_put_failure: + nla_nest_cancel(skb, nest); + return -EMSGSIZE; +} + +static int ets_class_dump_stats(struct Qdisc *sch, unsigned long arg, + struct gnet_dump *d) +{ + struct ets_class *cl = ets_class_from_arg(sch, arg); + struct Qdisc *cl_q = cl->qdisc; + + if (gnet_stats_copy_basic(qdisc_root_sleeping_running(sch), + d, NULL, &cl_q->bstats) < 0 || + qdisc_qstats_copy(d, cl_q) < 0) + return -1; + + return 0; +} + +static void ets_qdisc_walk(struct Qdisc *sch, struct qdisc_walker *arg) +{ + struct ets_sched *q = qdisc_priv(sch); + int i; + + if (arg->stop) + return; + + for (i = 0; i < q->nbands; i++) { + if (arg->count < arg->skip) { + arg->count++; + continue; + } + if (arg->fn(sch, i + 1, arg) < 0) { + arg->stop = 1; + break; + } + arg->count++; + } +} + +static struct tcf_block * +ets_qdisc_tcf_block(struct Qdisc *sch, unsigned long cl, + struct netlink_ext_ack *extack) +{ + struct ets_sched *q = qdisc_priv(sch); + + if (cl) { + NL_SET_ERR_MSG(extack, "ETS classid must be zero"); + return NULL; + } + + return q->block; +} + +static unsigned long ets_qdisc_bind_tcf(struct Qdisc *sch, unsigned long parent, + u32 classid) +{ + return ets_class_find(sch, classid); +} + +static void ets_qdisc_unbind_tcf(struct Qdisc *sch, unsigned long arg) +{ +} + +static struct ets_class *ets_classify(struct sk_buff *skb, struct Qdisc *sch, + int *qerr) +{ + struct ets_sched *q = qdisc_priv(sch); + u32 band = skb->priority; + struct tcf_result res; + struct tcf_proto *fl; + int err; + + *qerr = NET_XMIT_SUCCESS | __NET_XMIT_BYPASS; + if (TC_H_MAJ(skb->priority) != sch->handle) { + fl = rcu_dereference_bh(q->filter_list); + err = tcf_classify(skb, fl, &res, false); +#ifdef CONFIG_NET_CLS_ACT + switch (err) { + case TC_ACT_STOLEN: + case TC_ACT_QUEUED: + case TC_ACT_TRAP: + *qerr = NET_XMIT_SUCCESS | __NET_XMIT_STOLEN; + /* fall through */ + case TC_ACT_SHOT: + return NULL; + } +#endif + if (!fl || err < 0) { + if (TC_H_MAJ(band)) + band = 0; + return &q->classes[q->prio2band[band & TC_PRIO_MAX]]; + } + band = res.classid; + } + band = TC_H_MIN(band) - 1; + if (band >= q->nbands) + return &q->classes[q->prio2band[0]]; + return &q->classes[band]; +} + +static int ets_qdisc_enqueue(struct sk_buff *skb, struct Qdisc *sch, + struct sk_buff **to_free) +{ + unsigned int len = qdisc_pkt_len(skb); + struct ets_sched *q = qdisc_priv(sch); + struct ets_class *cl; + int err = 0; + bool first; + + cl = ets_classify(skb, sch, &err); + if (!cl) { + if (err & __NET_XMIT_BYPASS) + qdisc_qstats_drop(sch); + __qdisc_drop(skb, to_free); + return err; + } + + first = !cl->qdisc->q.qlen; + err = qdisc_enqueue(skb, cl->qdisc, to_free); + if (unlikely(err != NET_XMIT_SUCCESS)) { + if (net_xmit_drop_count(err)) { + cl->qstats.drops++; + qdisc_qstats_drop(sch); + } + return err; + } + + if (first && !ets_class_is_strict(q, cl)) { + list_add_tail(&cl->alist, &q->active); + cl->deficit = cl->quantum; + } + + sch->qstats.backlog += len; + sch->q.qlen++; + return err; +} + +static struct sk_buff * +ets_qdisc_dequeue_skb(struct Qdisc *sch, struct sk_buff *skb) +{ + qdisc_bstats_update(sch, skb); + qdisc_qstats_backlog_dec(sch, skb); + sch->q.qlen--; + return skb; +} + +static struct sk_buff *ets_qdisc_dequeue(struct Qdisc *sch) +{ + struct ets_sched *q = qdisc_priv(sch); + struct ets_class *cl; + struct sk_buff *skb; + unsigned int band; + unsigned int len; + + while (1) { + for (band = 0; band < q->nstrict; band++) { + cl = &q->classes[band]; + skb = qdisc_dequeue_peeked(cl->qdisc); + if (skb) + return ets_qdisc_dequeue_skb(sch, skb); + } + + if (list_empty(&q->active)) + goto out; + + cl = list_first_entry(&q->active, struct ets_class, alist); + skb = cl->qdisc->ops->peek(cl->qdisc); + if (!skb) { + qdisc_warn_nonwc(__func__, cl->qdisc); + goto out; + } + + len = qdisc_pkt_len(skb); + if (len <= cl->deficit) { + cl->deficit -= len; + skb = qdisc_dequeue_peeked(cl->qdisc); + if (unlikely(!skb)) + goto out; + if (cl->qdisc->q.qlen == 0) + list_del(&cl->alist); + return ets_qdisc_dequeue_skb(sch, skb); + } + + cl->deficit += cl->quantum; + list_move_tail(&cl->alist, &q->active); + } +out: + return NULL; +} + +static int ets_qdisc_priomap_parse(struct nlattr *priomap_attr, + unsigned int nbands, u8 *priomap, + struct netlink_ext_ack *extack) +{ + const struct nlattr *attr; + int prio = 0; + u8 band; + int rem; + int err; + + err = __nla_validate_nested(priomap_attr, TCA_ETS_MAX, + ets_priomap_policy, NL_VALIDATE_STRICT, + extack); + if (err) + return err; + + nla_for_each_nested(attr, priomap_attr, rem) { + switch (nla_type(attr)) { + case TCA_ETS_PRIOMAP_BAND: + if (prio > TC_PRIO_MAX) { + NL_SET_ERR_MSG_MOD(extack, "Too many priorities in ETS priomap"); + return -EINVAL; + } + band = nla_get_u8(attr); + if (band >= nbands) { + NL_SET_ERR_MSG_MOD(extack, "Invalid band number in ETS priomap"); + return -EINVAL; + } + priomap[prio++] = band; + break; + default: + WARN_ON_ONCE(1); /* Validate should have caught this. */ + return -EINVAL; + } + } + + return 0; +} + +static int ets_qdisc_quanta_parse(struct Qdisc *sch, struct nlattr *quanta_attr, + unsigned int nbands, unsigned int nstrict, + unsigned int *quanta, + struct netlink_ext_ack *extack) +{ + const struct nlattr *attr; + int band = nstrict; + int rem; + int err; + + err = __nla_validate_nested(quanta_attr, TCA_ETS_MAX, + ets_quanta_policy, NL_VALIDATE_STRICT, + extack); + if (err < 0) + return err; + + nla_for_each_nested(attr, quanta_attr, rem) { + switch (nla_type(attr)) { + case TCA_ETS_QUANTA_BAND: + if (band >= nbands) { + NL_SET_ERR_MSG_MOD(extack, "ETS quanta has more values than bands"); + return -EINVAL; + } + err = ets_quantum_parse(sch, attr, &quanta[band++], + extack); + if (err) + return err; + break; + default: + WARN_ON_ONCE(1); /* Validate should have caught this. */ + return -EINVAL; + } + } + + return 0; +} + +static int ets_qdisc_change(struct Qdisc *sch, struct nlattr *opt, + struct netlink_ext_ack *extack) +{ + unsigned int quanta[TCQ_ETS_MAX_BANDS] = {0}; + struct Qdisc *queues[TCQ_ETS_MAX_BANDS]; + struct ets_sched *q = qdisc_priv(sch); + struct nlattr *tb[TCA_ETS_MAX + 1]; + unsigned int oldbands = q->nbands; + u8 priomap[TC_PRIO_MAX + 1]; + unsigned int nstrict = 0; + unsigned int nbands; + unsigned int i; + int err; + + if (!opt) { + NL_SET_ERR_MSG(extack, "ETS options are required for this operation"); + return -EINVAL; + } + + err = nla_parse_nested(tb, TCA_ETS_MAX, opt, ets_policy, extack); + if (err < 0) + return err; + + if (!tb[TCA_ETS_NBANDS]) { + NL_SET_ERR_MSG_MOD(extack, "Number of bands is a required argument"); + return -EINVAL; + } + nbands = nla_get_u8(tb[TCA_ETS_NBANDS]); + if (nbands < 1 || nbands > TCQ_ETS_MAX_BANDS) { + NL_SET_ERR_MSG_MOD(extack, "Invalid number of bands"); + return -EINVAL; + } + /* Unless overridden, traffic goes to the last band. */ + memset(priomap, nbands - 1, sizeof(priomap)); + + if (tb[TCA_ETS_NSTRICT]) { + nstrict = nla_get_u8(tb[TCA_ETS_NSTRICT]); + if (nstrict > nbands) { + NL_SET_ERR_MSG_MOD(extack, "Invalid number of strict bands"); + return -EINVAL; + } + } + + if (tb[TCA_ETS_PRIOMAP]) { + err = ets_qdisc_priomap_parse(tb[TCA_ETS_PRIOMAP], + nbands, priomap, extack); + if (err) + return err; + } + + if (tb[TCA_ETS_QUANTA]) { + err = ets_qdisc_quanta_parse(sch, tb[TCA_ETS_QUANTA], + nbands, nstrict, quanta, extack); + if (err) + return err; + } + /* If there are more bands than strict + quanta provided, the remaining + * ones are ETS with quantum of MTU. Initialize the missing values here. + */ + for (i = nstrict; i < nbands; i++) { + if (!quanta[i]) + quanta[i] = psched_mtu(qdisc_dev(sch)); + } + + /* Before commit, make sure we can allocate all new qdiscs */ + for (i = oldbands; i < nbands; i++) { + queues[i] = qdisc_create_dflt(sch->dev_queue, &pfifo_qdisc_ops, + ets_class_id(sch, &q->classes[i]), + extack); + if (!queues[i]) { + while (i > oldbands) + qdisc_put(queues[--i]); + return -ENOMEM; + } + } + + sch_tree_lock(sch); + + q->nbands = nbands; + q->nstrict = nstrict; + memcpy(q->prio2band, priomap, sizeof(priomap)); + + for (i = q->nbands; i < oldbands; i++) + qdisc_tree_flush_backlog(q->classes[i].qdisc); + + for (i = 0; i < q->nbands; i++) + q->classes[i].quantum = quanta[i]; + + for (i = oldbands; i < q->nbands; i++) { + q->classes[i].qdisc = queues[i]; + if (q->classes[i].qdisc != &noop_qdisc) + qdisc_hash_add(q->classes[i].qdisc, true); + } + + sch_tree_unlock(sch); + + ets_offload_change(sch); + for (i = q->nbands; i < oldbands; i++) { + qdisc_put(q->classes[i].qdisc); + memset(&q->classes[i], 0, sizeof(q->classes[i])); + } + return 0; +} + +static int ets_qdisc_init(struct Qdisc *sch, struct nlattr *opt, + struct netlink_ext_ack *extack) +{ + struct ets_sched *q = qdisc_priv(sch); + int err; + + if (!opt) + return -EINVAL; + + err = tcf_block_get(&q->block, &q->filter_list, sch, extack); + if (err) + return err; + + INIT_LIST_HEAD(&q->active); + return ets_qdisc_change(sch, opt, extack); +} + +static void ets_qdisc_reset(struct Qdisc *sch) +{ + struct ets_sched *q = qdisc_priv(sch); + int band; + + for (band = q->nstrict; band < q->nbands; band++) { + if (q->classes[band].qdisc->q.qlen) + list_del(&q->classes[band].alist); + } + for (band = 0; band < q->nbands; band++) + qdisc_reset(q->classes[band].qdisc); + sch->qstats.backlog = 0; + sch->q.qlen = 0; +} + +static void ets_qdisc_destroy(struct Qdisc *sch) +{ + struct ets_sched *q = qdisc_priv(sch); + int band; + + ets_offload_destroy(sch); + tcf_block_put(q->block); + for (band = 0; band < q->nbands; band++) + qdisc_put(q->classes[band].qdisc); +} + +static int ets_qdisc_dump(struct Qdisc *sch, struct sk_buff *skb) +{ + struct ets_sched *q = qdisc_priv(sch); + struct nlattr *opts; + struct nlattr *nest; + int band; + int prio; + int err; + + err = ets_offload_dump(sch); + if (err) + return err; + + opts = nla_nest_start_noflag(skb, TCA_OPTIONS); + if (!opts) + goto nla_err; + + if (nla_put_u8(skb, TCA_ETS_NBANDS, q->nbands)) + goto nla_err; + + if (q->nstrict && + nla_put_u8(skb, TCA_ETS_NSTRICT, q->nstrict)) + goto nla_err; + + if (q->nbands > q->nstrict) { + nest = nla_nest_start(skb, TCA_ETS_QUANTA); + if (!nest) + goto nla_err; + + for (band = q->nstrict; band < q->nbands; band++) { + if (nla_put_u32(skb, TCA_ETS_QUANTA_BAND, + q->classes[band].quantum)) + goto nla_err; + } + + nla_nest_end(skb, nest); + } + + nest = nla_nest_start(skb, TCA_ETS_PRIOMAP); + if (!nest) + goto nla_err; + + for (prio = 0; prio <= TC_PRIO_MAX; prio++) { + if (nla_put_u8(skb, TCA_ETS_PRIOMAP_BAND, q->prio2band[prio])) + goto nla_err; + } + + nla_nest_end(skb, nest); + + return nla_nest_end(skb, opts); + +nla_err: + nla_nest_cancel(skb, opts); + return -EMSGSIZE; +} + +static const struct Qdisc_class_ops ets_class_ops = { + .change = ets_class_change, + .graft = ets_class_graft, + .leaf = ets_class_leaf, + .find = ets_class_find, + .qlen_notify = ets_class_qlen_notify, + .dump = ets_class_dump, + .dump_stats = ets_class_dump_stats, + .walk = ets_qdisc_walk, + .tcf_block = ets_qdisc_tcf_block, + .bind_tcf = ets_qdisc_bind_tcf, + .unbind_tcf = ets_qdisc_unbind_tcf, +}; + +static struct Qdisc_ops ets_qdisc_ops __read_mostly = { + .cl_ops = &ets_class_ops, + .id = "ets", + .priv_size = sizeof(struct ets_sched), + .enqueue = ets_qdisc_enqueue, + .dequeue = ets_qdisc_dequeue, + .peek = qdisc_peek_dequeued, + .change = ets_qdisc_change, + .init = ets_qdisc_init, + .reset = ets_qdisc_reset, + .destroy = ets_qdisc_destroy, + .dump = ets_qdisc_dump, + .owner = THIS_MODULE, +}; + +static int __init ets_init(void) +{ + return register_qdisc(&ets_qdisc_ops); +} + +static void __exit ets_exit(void) +{ + unregister_qdisc(&ets_qdisc_ops); +} + +module_init(ets_init); +module_exit(ets_exit); +MODULE_LICENSE("GPL"); diff --git a/net/sched/sch_fq_pie.c b/net/sched/sch_fq_pie.c new file mode 100644 index 000000000000..bbd0dea6b6b9 --- /dev/null +++ b/net/sched/sch_fq_pie.c @@ -0,0 +1,562 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* Flow Queue PIE discipline + * + * Copyright (C) 2019 Mohit P. Tahiliani <tahiliani@nitk.edu.in> + * Copyright (C) 2019 Sachin D. Patil <sdp.sachin@gmail.com> + * Copyright (C) 2019 V. Saicharan <vsaicharan1998@gmail.com> + * Copyright (C) 2019 Mohit Bhasi <mohitbhasi1998@gmail.com> + * Copyright (C) 2019 Leslie Monis <lesliemonis@gmail.com> + * Copyright (C) 2019 Gautam Ramakrishnan <gautamramk@gmail.com> + */ + +#include <linux/jhash.h> +#include <linux/sizes.h> +#include <linux/vmalloc.h> +#include <net/pkt_cls.h> +#include <net/pie.h> + +/* Flow Queue PIE + * + * Principles: + * - Packets are classified on flows. + * - This is a Stochastic model (as we use a hash, several flows might + * be hashed to the same slot) + * - Each flow has a PIE managed queue. + * - Flows are linked onto two (Round Robin) lists, + * so that new flows have priority on old ones. + * - For a given flow, packets are not reordered. + * - Drops during enqueue only. + * - ECN capability is off by default. + * - ECN threshold (if ECN is enabled) is at 10% by default. + * - Uses timestamps to calculate queue delay by default. + */ + +/** + * struct fq_pie_flow - contains data for each flow + * @vars: pie vars associated with the flow + * @deficit: number of remaining byte credits + * @backlog: size of data in the flow + * @qlen: number of packets in the flow + * @flowchain: flowchain for the flow + * @head: first packet in the flow + * @tail: last packet in the flow + */ +struct fq_pie_flow { + struct pie_vars vars; + s32 deficit; + u32 backlog; + u32 qlen; + struct list_head flowchain; + struct sk_buff *head; + struct sk_buff *tail; +}; + +struct fq_pie_sched_data { + struct tcf_proto __rcu *filter_list; /* optional external classifier */ + struct tcf_block *block; + struct fq_pie_flow *flows; + struct Qdisc *sch; + struct list_head old_flows; + struct list_head new_flows; + struct pie_params p_params; + u32 ecn_prob; + u32 flows_cnt; + u32 quantum; + u32 memory_limit; + u32 new_flow_count; + u32 memory_usage; + u32 overmemory; + struct pie_stats stats; + struct timer_list adapt_timer; +}; + +static unsigned int fq_pie_hash(const struct fq_pie_sched_data *q, + struct sk_buff *skb) +{ + return reciprocal_scale(skb_get_hash(skb), q->flows_cnt); +} + +static unsigned int fq_pie_classify(struct sk_buff *skb, struct Qdisc *sch, + int *qerr) +{ + struct fq_pie_sched_data *q = qdisc_priv(sch); + struct tcf_proto *filter; + struct tcf_result res; + int result; + + if (TC_H_MAJ(skb->priority) == sch->handle && + TC_H_MIN(skb->priority) > 0 && + TC_H_MIN(skb->priority) <= q->flows_cnt) + return TC_H_MIN(skb->priority); + + filter = rcu_dereference_bh(q->filter_list); + if (!filter) + return fq_pie_hash(q, skb) + 1; + + *qerr = NET_XMIT_SUCCESS | __NET_XMIT_BYPASS; + result = tcf_classify(skb, filter, &res, false); + if (result >= 0) { +#ifdef CONFIG_NET_CLS_ACT + switch (result) { + case TC_ACT_STOLEN: + case TC_ACT_QUEUED: + case TC_ACT_TRAP: + *qerr = NET_XMIT_SUCCESS | __NET_XMIT_STOLEN; + /* fall through */ + case TC_ACT_SHOT: + return 0; + } +#endif + if (TC_H_MIN(res.classid) <= q->flows_cnt) + return TC_H_MIN(res.classid); + } + return 0; +} + +/* add skb to flow queue (tail add) */ +static inline void flow_queue_add(struct fq_pie_flow *flow, + struct sk_buff *skb) +{ + if (!flow->head) + flow->head = skb; + else + flow->tail->next = skb; + flow->tail = skb; + skb->next = NULL; +} + +static int fq_pie_qdisc_enqueue(struct sk_buff *skb, struct Qdisc *sch, + struct sk_buff **to_free) +{ + struct fq_pie_sched_data *q = qdisc_priv(sch); + struct fq_pie_flow *sel_flow; + int uninitialized_var(ret); + u8 memory_limited = false; + u8 enqueue = false; + u32 pkt_len; + u32 idx; + + /* Classifies packet into corresponding flow */ + idx = fq_pie_classify(skb, sch, &ret); + sel_flow = &q->flows[idx]; + + /* Checks whether adding a new packet would exceed memory limit */ + get_pie_cb(skb)->mem_usage = skb->truesize; + memory_limited = q->memory_usage > q->memory_limit + skb->truesize; + + /* Checks if the qdisc is full */ + if (unlikely(qdisc_qlen(sch) >= sch->limit)) { + q->stats.overlimit++; + goto out; + } else if (unlikely(memory_limited)) { + q->overmemory++; + } + + if (!pie_drop_early(sch, &q->p_params, &sel_flow->vars, + sel_flow->backlog, skb->len)) { + enqueue = true; + } else if (q->p_params.ecn && + sel_flow->vars.prob <= (MAX_PROB / 100) * q->ecn_prob && + INET_ECN_set_ce(skb)) { + /* If packet is ecn capable, mark it if drop probability + * is lower than the parameter ecn_prob, else drop it. + */ + q->stats.ecn_mark++; + enqueue = true; + } + if (enqueue) { + /* Set enqueue time only when dq_rate_estimator is disabled. */ + if (!q->p_params.dq_rate_estimator) + pie_set_enqueue_time(skb); + + pkt_len = qdisc_pkt_len(skb); + q->stats.packets_in++; + q->memory_usage += skb->truesize; + sch->qstats.backlog += pkt_len; + sch->q.qlen++; + flow_queue_add(sel_flow, skb); + if (list_empty(&sel_flow->flowchain)) { + list_add_tail(&sel_flow->flowchain, &q->new_flows); + q->new_flow_count++; + sel_flow->deficit = q->quantum; + sel_flow->qlen = 0; + sel_flow->backlog = 0; + } + sel_flow->qlen++; + sel_flow->backlog += pkt_len; + return NET_XMIT_SUCCESS; + } +out: + q->stats.dropped++; + sel_flow->vars.accu_prob = 0; + sel_flow->vars.accu_prob_overflows = 0; + __qdisc_drop(skb, to_free); + qdisc_qstats_drop(sch); + return NET_XMIT_CN; +} + +static const struct nla_policy fq_pie_policy[TCA_FQ_PIE_MAX + 1] = { + [TCA_FQ_PIE_LIMIT] = {.type = NLA_U32}, + [TCA_FQ_PIE_FLOWS] = {.type = NLA_U32}, + [TCA_FQ_PIE_TARGET] = {.type = NLA_U32}, + [TCA_FQ_PIE_TUPDATE] = {.type = NLA_U32}, + [TCA_FQ_PIE_ALPHA] = {.type = NLA_U32}, + [TCA_FQ_PIE_BETA] = {.type = NLA_U32}, + [TCA_FQ_PIE_QUANTUM] = {.type = NLA_U32}, + [TCA_FQ_PIE_MEMORY_LIMIT] = {.type = NLA_U32}, + [TCA_FQ_PIE_ECN_PROB] = {.type = NLA_U32}, + [TCA_FQ_PIE_ECN] = {.type = NLA_U32}, + [TCA_FQ_PIE_BYTEMODE] = {.type = NLA_U32}, + [TCA_FQ_PIE_DQ_RATE_ESTIMATOR] = {.type = NLA_U32}, +}; + +static inline struct sk_buff *dequeue_head(struct fq_pie_flow *flow) +{ + struct sk_buff *skb = flow->head; + + flow->head = skb->next; + skb->next = NULL; + return skb; +} + +static struct sk_buff *fq_pie_qdisc_dequeue(struct Qdisc *sch) +{ + struct fq_pie_sched_data *q = qdisc_priv(sch); + struct sk_buff *skb = NULL; + struct fq_pie_flow *flow; + struct list_head *head; + u32 pkt_len; + +begin: + head = &q->new_flows; + if (list_empty(head)) { + head = &q->old_flows; + if (list_empty(head)) + return NULL; + } + + flow = list_first_entry(head, struct fq_pie_flow, flowchain); + /* Flow has exhausted all its credits */ + if (flow->deficit <= 0) { + flow->deficit += q->quantum; + list_move_tail(&flow->flowchain, &q->old_flows); + goto begin; + } + + if (flow->head) { + skb = dequeue_head(flow); + pkt_len = qdisc_pkt_len(skb); + sch->qstats.backlog -= pkt_len; + sch->q.qlen--; + qdisc_bstats_update(sch, skb); + } + + if (!skb) { + /* force a pass through old_flows to prevent starvation */ + if (head == &q->new_flows && !list_empty(&q->old_flows)) + list_move_tail(&flow->flowchain, &q->old_flows); + else + list_del_init(&flow->flowchain); + goto begin; + } + + flow->qlen--; + flow->deficit -= pkt_len; + flow->backlog -= pkt_len; + q->memory_usage -= get_pie_cb(skb)->mem_usage; + pie_process_dequeue(skb, &q->p_params, &flow->vars, flow->backlog); + return skb; +} + +static int fq_pie_change(struct Qdisc *sch, struct nlattr *opt, + struct netlink_ext_ack *extack) +{ + struct fq_pie_sched_data *q = qdisc_priv(sch); + struct nlattr *tb[TCA_FQ_PIE_MAX + 1]; + unsigned int len_dropped = 0; + unsigned int num_dropped = 0; + int err; + + if (!opt) + return -EINVAL; + + err = nla_parse_nested(tb, TCA_FQ_PIE_MAX, opt, fq_pie_policy, extack); + if (err < 0) + return err; + + sch_tree_lock(sch); + if (tb[TCA_FQ_PIE_LIMIT]) { + u32 limit = nla_get_u32(tb[TCA_FQ_PIE_LIMIT]); + + q->p_params.limit = limit; + sch->limit = limit; + } + if (tb[TCA_FQ_PIE_FLOWS]) { + if (q->flows) { + NL_SET_ERR_MSG_MOD(extack, + "Number of flows cannot be changed"); + goto flow_error; + } + q->flows_cnt = nla_get_u32(tb[TCA_FQ_PIE_FLOWS]); + if (!q->flows_cnt || q->flows_cnt > 65536) { + NL_SET_ERR_MSG_MOD(extack, + "Number of flows must be < 65536"); + goto flow_error; + } + } + + /* convert from microseconds to pschedtime */ + if (tb[TCA_FQ_PIE_TARGET]) { + /* target is in us */ + u32 target = nla_get_u32(tb[TCA_FQ_PIE_TARGET]); + + /* convert to pschedtime */ + q->p_params.target = + PSCHED_NS2TICKS((u64)target * NSEC_PER_USEC); + } + + /* tupdate is in jiffies */ + if (tb[TCA_FQ_PIE_TUPDATE]) + q->p_params.tupdate = + usecs_to_jiffies(nla_get_u32(tb[TCA_FQ_PIE_TUPDATE])); + + if (tb[TCA_FQ_PIE_ALPHA]) + q->p_params.alpha = nla_get_u32(tb[TCA_FQ_PIE_ALPHA]); + + if (tb[TCA_FQ_PIE_BETA]) + q->p_params.beta = nla_get_u32(tb[TCA_FQ_PIE_BETA]); + + if (tb[TCA_FQ_PIE_QUANTUM]) + q->quantum = nla_get_u32(tb[TCA_FQ_PIE_QUANTUM]); + + if (tb[TCA_FQ_PIE_MEMORY_LIMIT]) + q->memory_limit = nla_get_u32(tb[TCA_FQ_PIE_MEMORY_LIMIT]); + + if (tb[TCA_FQ_PIE_ECN_PROB]) + q->ecn_prob = nla_get_u32(tb[TCA_FQ_PIE_ECN_PROB]); + + if (tb[TCA_FQ_PIE_ECN]) + q->p_params.ecn = nla_get_u32(tb[TCA_FQ_PIE_ECN]); + + if (tb[TCA_FQ_PIE_BYTEMODE]) + q->p_params.bytemode = nla_get_u32(tb[TCA_FQ_PIE_BYTEMODE]); + + if (tb[TCA_FQ_PIE_DQ_RATE_ESTIMATOR]) + q->p_params.dq_rate_estimator = + nla_get_u32(tb[TCA_FQ_PIE_DQ_RATE_ESTIMATOR]); + + /* Drop excess packets if new limit is lower */ + while (sch->q.qlen > sch->limit) { + struct sk_buff *skb = fq_pie_qdisc_dequeue(sch); + + kfree_skb(skb); + len_dropped += qdisc_pkt_len(skb); + num_dropped += 1; + } + qdisc_tree_reduce_backlog(sch, num_dropped, len_dropped); + + sch_tree_unlock(sch); + return 0; + +flow_error: + sch_tree_unlock(sch); + return -EINVAL; +} + +static void fq_pie_timer(struct timer_list *t) +{ + struct fq_pie_sched_data *q = from_timer(q, t, adapt_timer); + struct Qdisc *sch = q->sch; + spinlock_t *root_lock; /* to lock qdisc for probability calculations */ + u16 idx; + + root_lock = qdisc_lock(qdisc_root_sleeping(sch)); + spin_lock(root_lock); + + for (idx = 0; idx < q->flows_cnt; idx++) + pie_calculate_probability(&q->p_params, &q->flows[idx].vars, + q->flows[idx].backlog); + + /* reset the timer to fire after 'tupdate' jiffies. */ + if (q->p_params.tupdate) + mod_timer(&q->adapt_timer, jiffies + q->p_params.tupdate); + + spin_unlock(root_lock); +} + +static int fq_pie_init(struct Qdisc *sch, struct nlattr *opt, + struct netlink_ext_ack *extack) +{ + struct fq_pie_sched_data *q = qdisc_priv(sch); + int err; + u16 idx; + + pie_params_init(&q->p_params); + sch->limit = 10 * 1024; + q->p_params.limit = sch->limit; + q->quantum = psched_mtu(qdisc_dev(sch)); + q->sch = sch; + q->ecn_prob = 10; + q->flows_cnt = 1024; + q->memory_limit = SZ_32M; + + INIT_LIST_HEAD(&q->new_flows); + INIT_LIST_HEAD(&q->old_flows); + + if (opt) { + err = fq_pie_change(sch, opt, extack); + + if (err) + return err; + } + + err = tcf_block_get(&q->block, &q->filter_list, sch, extack); + if (err) + goto init_failure; + + q->flows = kvcalloc(q->flows_cnt, sizeof(struct fq_pie_flow), + GFP_KERNEL); + if (!q->flows) { + err = -ENOMEM; + goto init_failure; + } + for (idx = 0; idx < q->flows_cnt; idx++) { + struct fq_pie_flow *flow = q->flows + idx; + + INIT_LIST_HEAD(&flow->flowchain); + pie_vars_init(&flow->vars); + } + + timer_setup(&q->adapt_timer, fq_pie_timer, 0); + mod_timer(&q->adapt_timer, jiffies + HZ / 2); + + return 0; + +init_failure: + q->flows_cnt = 0; + + return err; +} + +static int fq_pie_dump(struct Qdisc *sch, struct sk_buff *skb) +{ + struct fq_pie_sched_data *q = qdisc_priv(sch); + struct nlattr *opts; + + opts = nla_nest_start(skb, TCA_OPTIONS); + if (!opts) + return -EMSGSIZE; + + /* convert target from pschedtime to us */ + if (nla_put_u32(skb, TCA_FQ_PIE_LIMIT, sch->limit) || + nla_put_u32(skb, TCA_FQ_PIE_FLOWS, q->flows_cnt) || + nla_put_u32(skb, TCA_FQ_PIE_TARGET, + ((u32)PSCHED_TICKS2NS(q->p_params.target)) / + NSEC_PER_USEC) || + nla_put_u32(skb, TCA_FQ_PIE_TUPDATE, + jiffies_to_usecs(q->p_params.tupdate)) || + nla_put_u32(skb, TCA_FQ_PIE_ALPHA, q->p_params.alpha) || + nla_put_u32(skb, TCA_FQ_PIE_BETA, q->p_params.beta) || + nla_put_u32(skb, TCA_FQ_PIE_QUANTUM, q->quantum) || + nla_put_u32(skb, TCA_FQ_PIE_MEMORY_LIMIT, q->memory_limit) || + nla_put_u32(skb, TCA_FQ_PIE_ECN_PROB, q->ecn_prob) || + nla_put_u32(skb, TCA_FQ_PIE_ECN, q->p_params.ecn) || + nla_put_u32(skb, TCA_FQ_PIE_BYTEMODE, q->p_params.bytemode) || + nla_put_u32(skb, TCA_FQ_PIE_DQ_RATE_ESTIMATOR, + q->p_params.dq_rate_estimator)) + goto nla_put_failure; + + return nla_nest_end(skb, opts); + +nla_put_failure: + nla_nest_cancel(skb, opts); + return -EMSGSIZE; +} + +static int fq_pie_dump_stats(struct Qdisc *sch, struct gnet_dump *d) +{ + struct fq_pie_sched_data *q = qdisc_priv(sch); + struct tc_fq_pie_xstats st = { + .packets_in = q->stats.packets_in, + .overlimit = q->stats.overlimit, + .overmemory = q->overmemory, + .dropped = q->stats.dropped, + .ecn_mark = q->stats.ecn_mark, + .new_flow_count = q->new_flow_count, + .memory_usage = q->memory_usage, + }; + struct list_head *pos; + + sch_tree_lock(sch); + list_for_each(pos, &q->new_flows) + st.new_flows_len++; + + list_for_each(pos, &q->old_flows) + st.old_flows_len++; + sch_tree_unlock(sch); + + return gnet_stats_copy_app(d, &st, sizeof(st)); +} + +static void fq_pie_reset(struct Qdisc *sch) +{ + struct fq_pie_sched_data *q = qdisc_priv(sch); + u16 idx; + + INIT_LIST_HEAD(&q->new_flows); + INIT_LIST_HEAD(&q->old_flows); + for (idx = 0; idx < q->flows_cnt; idx++) { + struct fq_pie_flow *flow = q->flows + idx; + + /* Removes all packets from flow */ + rtnl_kfree_skbs(flow->head, flow->tail); + flow->head = NULL; + + INIT_LIST_HEAD(&flow->flowchain); + pie_vars_init(&flow->vars); + } + + sch->q.qlen = 0; + sch->qstats.backlog = 0; +} + +static void fq_pie_destroy(struct Qdisc *sch) +{ + struct fq_pie_sched_data *q = qdisc_priv(sch); + + tcf_block_put(q->block); + del_timer_sync(&q->adapt_timer); + kvfree(q->flows); +} + +static struct Qdisc_ops fq_pie_qdisc_ops __read_mostly = { + .id = "fq_pie", + .priv_size = sizeof(struct fq_pie_sched_data), + .enqueue = fq_pie_qdisc_enqueue, + .dequeue = fq_pie_qdisc_dequeue, + .peek = qdisc_peek_dequeued, + .init = fq_pie_init, + .destroy = fq_pie_destroy, + .reset = fq_pie_reset, + .change = fq_pie_change, + .dump = fq_pie_dump, + .dump_stats = fq_pie_dump_stats, + .owner = THIS_MODULE, +}; + +static int __init fq_pie_module_init(void) +{ + return register_qdisc(&fq_pie_qdisc_ops); +} + +static void __exit fq_pie_module_exit(void) +{ + unregister_qdisc(&fq_pie_qdisc_ops); +} + +module_init(fq_pie_module_init); +module_exit(fq_pie_module_exit); + +MODULE_DESCRIPTION("Flow Queue Proportional Integral controller Enhanced (FQ-PIE)"); +MODULE_AUTHOR("Mohit P. Tahiliani"); +MODULE_LICENSE("GPL"); diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c index 5ab696efca95..6c9595f1048a 100644 --- a/net/sched/sch_generic.c +++ b/net/sched/sch_generic.c @@ -441,7 +441,7 @@ static void dev_watchdog(struct timer_list *t) trace_net_dev_xmit_timeout(dev, i); WARN_ONCE(1, KERN_INFO "NETDEV WATCHDOG: %s (%s): transmit queue %u timed out\n", dev->name, netdev_drivername(dev), i); - dev->netdev_ops->ndo_tx_timeout(dev); + dev->netdev_ops->ndo_tx_timeout(dev, i); } if (!mod_timer(&dev->watchdog_timer, round_jiffies(jiffies + diff --git a/net/sched/sch_pie.c b/net/sched/sch_pie.c index b0b0dc46af61..915bcdb59a9f 100644 --- a/net/sched/sch_pie.c +++ b/net/sched/sch_pie.c @@ -19,159 +19,76 @@ #include <linux/skbuff.h> #include <net/pkt_sched.h> #include <net/inet_ecn.h> - -#define QUEUE_THRESHOLD 16384 -#define DQCOUNT_INVALID -1 -#define DTIME_INVALID 0xffffffffffffffff -#define MAX_PROB 0xffffffffffffffff -#define PIE_SCALE 8 - -/* parameters used */ -struct pie_params { - psched_time_t target; /* user specified target delay in pschedtime */ - u32 tupdate; /* timer frequency (in jiffies) */ - u32 limit; /* number of packets that can be enqueued */ - u32 alpha; /* alpha and beta are between 0 and 32 */ - u32 beta; /* and are used for shift relative to 1 */ - bool ecn; /* true if ecn is enabled */ - bool bytemode; /* to scale drop early prob based on pkt size */ - u8 dq_rate_estimator; /* to calculate delay using Little's law */ -}; - -/* variables used */ -struct pie_vars { - u64 prob; /* probability but scaled by u64 limit. */ - psched_time_t burst_time; - psched_time_t qdelay; - psched_time_t qdelay_old; - u64 dq_count; /* measured in bytes */ - psched_time_t dq_tstamp; /* drain rate */ - u64 accu_prob; /* accumulated drop probability */ - u32 avg_dq_rate; /* bytes per pschedtime tick,scaled */ - u32 qlen_old; /* in bytes */ - u8 accu_prob_overflows; /* overflows of accu_prob */ -}; - -/* statistics gathering */ -struct pie_stats { - u32 packets_in; /* total number of packets enqueued */ - u32 dropped; /* packets dropped due to pie_action */ - u32 overlimit; /* dropped due to lack of space in queue */ - u32 maxq; /* maximum queue size */ - u32 ecn_mark; /* packets marked with ECN */ -}; +#include <net/pie.h> /* private data for the Qdisc */ struct pie_sched_data { - struct pie_params params; struct pie_vars vars; + struct pie_params params; struct pie_stats stats; struct timer_list adapt_timer; struct Qdisc *sch; }; -static void pie_params_init(struct pie_params *params) +bool pie_drop_early(struct Qdisc *sch, struct pie_params *params, + struct pie_vars *vars, u32 qlen, u32 packet_size) { - params->alpha = 2; - params->beta = 20; - params->tupdate = usecs_to_jiffies(15 * USEC_PER_MSEC); /* 15 ms */ - params->limit = 1000; /* default of 1000 packets */ - params->target = PSCHED_NS2TICKS(15 * NSEC_PER_MSEC); /* 15 ms */ - params->ecn = false; - params->bytemode = false; - params->dq_rate_estimator = false; -} - -/* private skb vars */ -struct pie_skb_cb { - psched_time_t enqueue_time; -}; - -static struct pie_skb_cb *get_pie_cb(const struct sk_buff *skb) -{ - qdisc_cb_private_validate(skb, sizeof(struct pie_skb_cb)); - return (struct pie_skb_cb *)qdisc_skb_cb(skb)->data; -} - -static psched_time_t pie_get_enqueue_time(const struct sk_buff *skb) -{ - return get_pie_cb(skb)->enqueue_time; -} - -static void pie_set_enqueue_time(struct sk_buff *skb) -{ - get_pie_cb(skb)->enqueue_time = psched_get_time(); -} - -static void pie_vars_init(struct pie_vars *vars) -{ - vars->dq_count = DQCOUNT_INVALID; - vars->dq_tstamp = DTIME_INVALID; - vars->accu_prob = 0; - vars->avg_dq_rate = 0; - /* default of 150 ms in pschedtime */ - vars->burst_time = PSCHED_NS2TICKS(150 * NSEC_PER_MSEC); - vars->accu_prob_overflows = 0; -} - -static bool drop_early(struct Qdisc *sch, u32 packet_size) -{ - struct pie_sched_data *q = qdisc_priv(sch); u64 rnd; - u64 local_prob = q->vars.prob; + u64 local_prob = vars->prob; u32 mtu = psched_mtu(qdisc_dev(sch)); /* If there is still burst allowance left skip random early drop */ - if (q->vars.burst_time > 0) + if (vars->burst_time > 0) return false; /* If current delay is less than half of target, and * if drop prob is low already, disable early_drop */ - if ((q->vars.qdelay < q->params.target / 2) && - (q->vars.prob < MAX_PROB / 5)) + if ((vars->qdelay < params->target / 2) && + (vars->prob < MAX_PROB / 5)) return false; - /* If we have fewer than 2 mtu-sized packets, disable drop_early, + /* If we have fewer than 2 mtu-sized packets, disable pie_drop_early, * similar to min_th in RED */ - if (sch->qstats.backlog < 2 * mtu) + if (qlen < 2 * mtu) return false; /* If bytemode is turned on, use packet size to compute new * probablity. Smaller packets will have lower drop prob in this case */ - if (q->params.bytemode && packet_size <= mtu) + if (params->bytemode && packet_size <= mtu) local_prob = (u64)packet_size * div_u64(local_prob, mtu); else - local_prob = q->vars.prob; + local_prob = vars->prob; if (local_prob == 0) { - q->vars.accu_prob = 0; - q->vars.accu_prob_overflows = 0; + vars->accu_prob = 0; + vars->accu_prob_overflows = 0; } - if (local_prob > MAX_PROB - q->vars.accu_prob) - q->vars.accu_prob_overflows++; + if (local_prob > MAX_PROB - vars->accu_prob) + vars->accu_prob_overflows++; - q->vars.accu_prob += local_prob; + vars->accu_prob += local_prob; - if (q->vars.accu_prob_overflows == 0 && - q->vars.accu_prob < (MAX_PROB / 100) * 85) + if (vars->accu_prob_overflows == 0 && + vars->accu_prob < (MAX_PROB / 100) * 85) return false; - if (q->vars.accu_prob_overflows == 8 && - q->vars.accu_prob >= MAX_PROB / 2) + if (vars->accu_prob_overflows == 8 && + vars->accu_prob >= MAX_PROB / 2) return true; prandom_bytes(&rnd, 8); if (rnd < local_prob) { - q->vars.accu_prob = 0; - q->vars.accu_prob_overflows = 0; + vars->accu_prob = 0; + vars->accu_prob_overflows = 0; return true; } return false; } +EXPORT_SYMBOL_GPL(pie_drop_early); static int pie_qdisc_enqueue(struct sk_buff *skb, struct Qdisc *sch, struct sk_buff **to_free) @@ -184,7 +101,8 @@ static int pie_qdisc_enqueue(struct sk_buff *skb, struct Qdisc *sch, goto out; } - if (!drop_early(sch, skb->len)) { + if (!pie_drop_early(sch, &q->params, &q->vars, sch->qstats.backlog, + skb->len)) { enqueue = true; } else if (q->params.ecn && (q->vars.prob <= MAX_PROB / 10) && INET_ECN_set_ce(skb)) { @@ -216,14 +134,14 @@ out: } static const struct nla_policy pie_policy[TCA_PIE_MAX + 1] = { - [TCA_PIE_TARGET] = {.type = NLA_U32}, - [TCA_PIE_LIMIT] = {.type = NLA_U32}, - [TCA_PIE_TUPDATE] = {.type = NLA_U32}, - [TCA_PIE_ALPHA] = {.type = NLA_U32}, - [TCA_PIE_BETA] = {.type = NLA_U32}, - [TCA_PIE_ECN] = {.type = NLA_U32}, - [TCA_PIE_BYTEMODE] = {.type = NLA_U32}, - [TCA_PIE_DQ_RATE_ESTIMATOR] = {.type = NLA_U32}, + [TCA_PIE_TARGET] = {.type = NLA_U32}, + [TCA_PIE_LIMIT] = {.type = NLA_U32}, + [TCA_PIE_TUPDATE] = {.type = NLA_U32}, + [TCA_PIE_ALPHA] = {.type = NLA_U32}, + [TCA_PIE_BETA] = {.type = NLA_U32}, + [TCA_PIE_ECN] = {.type = NLA_U32}, + [TCA_PIE_BYTEMODE] = {.type = NLA_U32}, + [TCA_PIE_DQ_RATE_ESTIMATOR] = {.type = NLA_U32}, }; static int pie_change(struct Qdisc *sch, struct nlattr *opt, @@ -296,26 +214,25 @@ static int pie_change(struct Qdisc *sch, struct nlattr *opt, return 0; } -static void pie_process_dequeue(struct Qdisc *sch, struct sk_buff *skb) +void pie_process_dequeue(struct sk_buff *skb, struct pie_params *params, + struct pie_vars *vars, u32 qlen) { - struct pie_sched_data *q = qdisc_priv(sch); - int qlen = sch->qstats.backlog; /* current queue size in bytes */ psched_time_t now = psched_get_time(); u32 dtime = 0; /* If dq_rate_estimator is disabled, calculate qdelay using the * packet timestamp. */ - if (!q->params.dq_rate_estimator) { - q->vars.qdelay = now - pie_get_enqueue_time(skb); + if (!params->dq_rate_estimator) { + vars->qdelay = now - pie_get_enqueue_time(skb); - if (q->vars.dq_tstamp != DTIME_INVALID) - dtime = now - q->vars.dq_tstamp; + if (vars->dq_tstamp != DTIME_INVALID) + dtime = now - vars->dq_tstamp; - q->vars.dq_tstamp = now; + vars->dq_tstamp = now; if (qlen == 0) - q->vars.qdelay = 0; + vars->qdelay = 0; if (dtime == 0) return; @@ -327,39 +244,39 @@ static void pie_process_dequeue(struct Qdisc *sch, struct sk_buff *skb) * we have enough packets to calculate the drain rate. Save * current time as dq_tstamp and start measurement cycle. */ - if (qlen >= QUEUE_THRESHOLD && q->vars.dq_count == DQCOUNT_INVALID) { - q->vars.dq_tstamp = psched_get_time(); - q->vars.dq_count = 0; + if (qlen >= QUEUE_THRESHOLD && vars->dq_count == DQCOUNT_INVALID) { + vars->dq_tstamp = psched_get_time(); + vars->dq_count = 0; } - /* Calculate the average drain rate from this value. If queue length - * has receded to a small value viz., <= QUEUE_THRESHOLD bytes,reset + /* Calculate the average drain rate from this value. If queue length + * has receded to a small value viz., <= QUEUE_THRESHOLD bytes, reset * the dq_count to -1 as we don't have enough packets to calculate the - * drain rate anymore The following if block is entered only when we + * drain rate anymore. The following if block is entered only when we * have a substantial queue built up (QUEUE_THRESHOLD bytes or more) * and we calculate the drain rate for the threshold here. dq_count is * in bytes, time difference in psched_time, hence rate is in * bytes/psched_time. */ - if (q->vars.dq_count != DQCOUNT_INVALID) { - q->vars.dq_count += skb->len; + if (vars->dq_count != DQCOUNT_INVALID) { + vars->dq_count += skb->len; - if (q->vars.dq_count >= QUEUE_THRESHOLD) { - u32 count = q->vars.dq_count << PIE_SCALE; + if (vars->dq_count >= QUEUE_THRESHOLD) { + u32 count = vars->dq_count << PIE_SCALE; - dtime = now - q->vars.dq_tstamp; + dtime = now - vars->dq_tstamp; if (dtime == 0) return; count = count / dtime; - if (q->vars.avg_dq_rate == 0) - q->vars.avg_dq_rate = count; + if (vars->avg_dq_rate == 0) + vars->avg_dq_rate = count; else - q->vars.avg_dq_rate = - (q->vars.avg_dq_rate - - (q->vars.avg_dq_rate >> 3)) + (count >> 3); + vars->avg_dq_rate = + (vars->avg_dq_rate - + (vars->avg_dq_rate >> 3)) + (count >> 3); /* If the queue has receded below the threshold, we hold * on to the last drain rate calculated, else we reset @@ -367,10 +284,10 @@ static void pie_process_dequeue(struct Qdisc *sch, struct sk_buff *skb) * packet is dequeued */ if (qlen < QUEUE_THRESHOLD) { - q->vars.dq_count = DQCOUNT_INVALID; + vars->dq_count = DQCOUNT_INVALID; } else { - q->vars.dq_count = 0; - q->vars.dq_tstamp = psched_get_time(); + vars->dq_count = 0; + vars->dq_tstamp = psched_get_time(); } goto burst_allowance_reduction; @@ -380,18 +297,18 @@ static void pie_process_dequeue(struct Qdisc *sch, struct sk_buff *skb) return; burst_allowance_reduction: - if (q->vars.burst_time > 0) { - if (q->vars.burst_time > dtime) - q->vars.burst_time -= dtime; + if (vars->burst_time > 0) { + if (vars->burst_time > dtime) + vars->burst_time -= dtime; else - q->vars.burst_time = 0; + vars->burst_time = 0; } } +EXPORT_SYMBOL_GPL(pie_process_dequeue); -static void calculate_probability(struct Qdisc *sch) +void pie_calculate_probability(struct pie_params *params, struct pie_vars *vars, + u32 qlen) { - struct pie_sched_data *q = qdisc_priv(sch); - u32 qlen = sch->qstats.backlog; /* queue size in bytes */ psched_time_t qdelay = 0; /* in pschedtime */ psched_time_t qdelay_old = 0; /* in pschedtime */ s64 delta = 0; /* determines the change in probability */ @@ -400,21 +317,21 @@ static void calculate_probability(struct Qdisc *sch) u32 power; bool update_prob = true; - if (q->params.dq_rate_estimator) { - qdelay_old = q->vars.qdelay; - q->vars.qdelay_old = q->vars.qdelay; + if (params->dq_rate_estimator) { + qdelay_old = vars->qdelay; + vars->qdelay_old = vars->qdelay; - if (q->vars.avg_dq_rate > 0) - qdelay = (qlen << PIE_SCALE) / q->vars.avg_dq_rate; + if (vars->avg_dq_rate > 0) + qdelay = (qlen << PIE_SCALE) / vars->avg_dq_rate; else qdelay = 0; } else { - qdelay = q->vars.qdelay; - qdelay_old = q->vars.qdelay_old; + qdelay = vars->qdelay; + qdelay_old = vars->qdelay_old; } - /* If qdelay is zero and qlen is not, it means qlen is very small, less - * than dequeue_rate, so we do not update probabilty in this round + /* If qdelay is zero and qlen is not, it means qlen is very small, + * so we do not update probabilty in this round. */ if (qdelay == 0 && qlen != 0) update_prob = false; @@ -426,18 +343,18 @@ static void calculate_probability(struct Qdisc *sch) * probability. alpha/beta are updated locally below by scaling down * by 16 to come to 0-2 range. */ - alpha = ((u64)q->params.alpha * (MAX_PROB / PSCHED_TICKS_PER_SEC)) >> 4; - beta = ((u64)q->params.beta * (MAX_PROB / PSCHED_TICKS_PER_SEC)) >> 4; + alpha = ((u64)params->alpha * (MAX_PROB / PSCHED_TICKS_PER_SEC)) >> 4; + beta = ((u64)params->beta * (MAX_PROB / PSCHED_TICKS_PER_SEC)) >> 4; /* We scale alpha and beta differently depending on how heavy the * congestion is. Please see RFC 8033 for details. */ - if (q->vars.prob < MAX_PROB / 10) { + if (vars->prob < MAX_PROB / 10) { alpha >>= 1; beta >>= 1; power = 100; - while (q->vars.prob < div_u64(MAX_PROB, power) && + while (vars->prob < div_u64(MAX_PROB, power) && power <= 1000000) { alpha >>= 2; beta >>= 2; @@ -446,14 +363,14 @@ static void calculate_probability(struct Qdisc *sch) } /* alpha and beta should be between 0 and 32, in multiples of 1/16 */ - delta += alpha * (u64)(qdelay - q->params.target); + delta += alpha * (u64)(qdelay - params->target); delta += beta * (u64)(qdelay - qdelay_old); - oldprob = q->vars.prob; + oldprob = vars->prob; /* to ensure we increase probability in steps of no more than 2% */ if (delta > (s64)(MAX_PROB / (100 / 2)) && - q->vars.prob >= MAX_PROB / 10) + vars->prob >= MAX_PROB / 10) delta = (MAX_PROB / 100) * 2; /* Non-linear drop: @@ -464,12 +381,12 @@ static void calculate_probability(struct Qdisc *sch) if (qdelay > (PSCHED_NS2TICKS(250 * NSEC_PER_MSEC))) delta += MAX_PROB / (100 / 2); - q->vars.prob += delta; + vars->prob += delta; if (delta > 0) { /* prevent overflow */ - if (q->vars.prob < oldprob) { - q->vars.prob = MAX_PROB; + if (vars->prob < oldprob) { + vars->prob = MAX_PROB; /* Prevent normalization error. If probability is at * maximum value already, we normalize it here, and * skip the check to do a non-linear drop in the next @@ -479,8 +396,8 @@ static void calculate_probability(struct Qdisc *sch) } } else { /* prevent underflow */ - if (q->vars.prob > oldprob) - q->vars.prob = 0; + if (vars->prob > oldprob) + vars->prob = 0; } /* Non-linear drop in probability: Reduce drop probability quickly if @@ -489,10 +406,10 @@ static void calculate_probability(struct Qdisc *sch) if (qdelay == 0 && qdelay_old == 0 && update_prob) /* Reduce drop probability to 98.4% */ - q->vars.prob -= q->vars.prob / 64u; + vars->prob -= vars->prob / 64; - q->vars.qdelay = qdelay; - q->vars.qlen_old = qlen; + vars->qdelay = qdelay; + vars->qlen_old = qlen; /* We restart the measurement cycle if the following conditions are met * 1. If the delay has been low for 2 consecutive Tupdate periods @@ -500,16 +417,17 @@ static void calculate_probability(struct Qdisc *sch) * 3. If average dq_rate_estimator is enabled, we have atleast one * estimate for the avg_dq_rate ie., is a non-zero value */ - if ((q->vars.qdelay < q->params.target / 2) && - (q->vars.qdelay_old < q->params.target / 2) && - q->vars.prob == 0 && - (!q->params.dq_rate_estimator || q->vars.avg_dq_rate > 0)) { - pie_vars_init(&q->vars); + if ((vars->qdelay < params->target / 2) && + (vars->qdelay_old < params->target / 2) && + vars->prob == 0 && + (!params->dq_rate_estimator || vars->avg_dq_rate > 0)) { + pie_vars_init(vars); } - if (!q->params.dq_rate_estimator) - q->vars.qdelay_old = qdelay; + if (!params->dq_rate_estimator) + vars->qdelay_old = qdelay; } +EXPORT_SYMBOL_GPL(pie_calculate_probability); static void pie_timer(struct timer_list *t) { @@ -518,7 +436,7 @@ static void pie_timer(struct timer_list *t) spinlock_t *root_lock = qdisc_lock(qdisc_root_sleeping(sch)); spin_lock(root_lock); - calculate_probability(sch); + pie_calculate_probability(&q->params, &q->vars, sch->qstats.backlog); /* reset the timer to fire after 'tupdate'. tupdate is in jiffies. */ if (q->params.tupdate) @@ -607,12 +525,13 @@ static int pie_dump_stats(struct Qdisc *sch, struct gnet_dump *d) static struct sk_buff *pie_qdisc_dequeue(struct Qdisc *sch) { + struct pie_sched_data *q = qdisc_priv(sch); struct sk_buff *skb = qdisc_dequeue_head(sch); if (!skb) return NULL; - pie_process_dequeue(sch, skb); + pie_process_dequeue(skb, &q->params, &q->vars, sch->qstats.backlog); return skb; } @@ -633,7 +552,7 @@ static void pie_destroy(struct Qdisc *sch) } static struct Qdisc_ops pie_qdisc_ops __read_mostly = { - .id = "pie", + .id = "pie", .priv_size = sizeof(struct pie_sched_data), .enqueue = pie_qdisc_enqueue, .dequeue = pie_qdisc_dequeue, diff --git a/net/sched/sch_tbf.c b/net/sched/sch_tbf.c index 5f72f3f916a5..78e79029dc63 100644 --- a/net/sched/sch_tbf.c +++ b/net/sched/sch_tbf.c @@ -15,6 +15,7 @@ #include <linux/skbuff.h> #include <net/netlink.h> #include <net/sch_generic.h> +#include <net/pkt_cls.h> #include <net/pkt_sched.h> @@ -137,6 +138,52 @@ static u64 psched_ns_t2l(const struct psched_ratecfg *r, return len; } +static void tbf_offload_change(struct Qdisc *sch) +{ + struct tbf_sched_data *q = qdisc_priv(sch); + struct net_device *dev = qdisc_dev(sch); + struct tc_tbf_qopt_offload qopt; + + if (!tc_can_offload(dev) || !dev->netdev_ops->ndo_setup_tc) + return; + + qopt.command = TC_TBF_REPLACE; + qopt.handle = sch->handle; + qopt.parent = sch->parent; + qopt.replace_params.rate = q->rate; + qopt.replace_params.max_size = q->max_size; + qopt.replace_params.qstats = &sch->qstats; + + dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_QDISC_TBF, &qopt); +} + +static void tbf_offload_destroy(struct Qdisc *sch) +{ + struct net_device *dev = qdisc_dev(sch); + struct tc_tbf_qopt_offload qopt; + + if (!tc_can_offload(dev) || !dev->netdev_ops->ndo_setup_tc) + return; + + qopt.command = TC_TBF_DESTROY; + qopt.handle = sch->handle; + qopt.parent = sch->parent; + dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_QDISC_TBF, &qopt); +} + +static int tbf_offload_dump(struct Qdisc *sch) +{ + struct tc_tbf_qopt_offload qopt; + + qopt.command = TC_TBF_STATS; + qopt.handle = sch->handle; + qopt.parent = sch->parent; + qopt.stats.bstats = &sch->bstats; + qopt.stats.qstats = &sch->qstats; + + return qdisc_offload_dump_helper(sch, TC_SETUP_QDISC_TBF, &qopt); +} + /* GSO packet is too big, segment it so that tbf can transmit * each segment in time */ @@ -155,8 +202,7 @@ static int tbf_segment(struct sk_buff *skb, struct Qdisc *sch, return qdisc_drop(skb, sch, to_free); nb = 0; - while (segs) { - nskb = segs->next; + skb_list_walk_safe(segs, segs, nskb) { skb_mark_not_on_list(segs); qdisc_skb_cb(segs)->pkt_len = segs->len; len += segs->len; @@ -167,7 +213,6 @@ static int tbf_segment(struct sk_buff *skb, struct Qdisc *sch, } else { nb++; } - segs = nskb; } sch->q.qlen += nb; if (nb > 1) @@ -409,6 +454,8 @@ static int tbf_change(struct Qdisc *sch, struct nlattr *opt, sch_tree_unlock(sch); err = 0; + + tbf_offload_change(sch); done: return err; } @@ -434,6 +481,7 @@ static void tbf_destroy(struct Qdisc *sch) struct tbf_sched_data *q = qdisc_priv(sch); qdisc_watchdog_cancel(&q->watchdog); + tbf_offload_destroy(sch); qdisc_put(q->qdisc); } @@ -442,8 +490,12 @@ static int tbf_dump(struct Qdisc *sch, struct sk_buff *skb) struct tbf_sched_data *q = qdisc_priv(sch); struct nlattr *nest; struct tc_tbf_qopt opt; + int err; + + err = tbf_offload_dump(sch); + if (err) + return err; - sch->qstats.backlog = q->qdisc->qstats.backlog; nest = nla_nest_start_noflag(skb, TCA_OPTIONS); if (nest == NULL) goto nla_put_failure; diff --git a/net/sctp/associola.c b/net/sctp/associola.c index bbd5004a5d09..437079a4883d 100644 --- a/net/sctp/associola.c +++ b/net/sctp/associola.c @@ -584,7 +584,6 @@ struct sctp_transport *sctp_assoc_add_peer(struct sctp_association *asoc, const gfp_t gfp, const int peer_state) { - struct net *net = sock_net(asoc->base.sk); struct sctp_transport *peer; struct sctp_sock *sp; unsigned short port; @@ -614,7 +613,7 @@ struct sctp_transport *sctp_assoc_add_peer(struct sctp_association *asoc, return peer; } - peer = sctp_transport_new(net, addr, gfp); + peer = sctp_transport_new(asoc->base.net, addr, gfp); if (!peer) return NULL; @@ -974,7 +973,7 @@ static void sctp_assoc_bh_rcv(struct work_struct *work) struct sctp_association *asoc = container_of(work, struct sctp_association, base.inqueue.immediate); - struct net *net = sock_net(asoc->base.sk); + struct net *net = asoc->base.net; union sctp_subtype subtype; struct sctp_endpoint *ep; struct sctp_chunk *chunk; @@ -1442,7 +1441,8 @@ void sctp_assoc_sync_pmtu(struct sctp_association *asoc) /* Should we send a SACK to update our peer? */ static inline bool sctp_peer_needs_update(struct sctp_association *asoc) { - struct net *net = sock_net(asoc->base.sk); + struct net *net = asoc->base.net; + switch (asoc->state) { case SCTP_STATE_ESTABLISHED: case SCTP_STATE_SHUTDOWN_PENDING: @@ -1576,7 +1576,7 @@ int sctp_assoc_set_bind_addr_from_ep(struct sctp_association *asoc, if (asoc->peer.ipv6_address) flags |= SCTP_ADDR6_PEERSUPP; - return sctp_bind_addr_copy(sock_net(asoc->base.sk), + return sctp_bind_addr_copy(asoc->base.net, &asoc->base.bind_addr, &asoc->ep->base.bind_addr, scope, gfp, flags); diff --git a/net/sctp/chunk.c b/net/sctp/chunk.c index cc3ce5d80b08..ab6a997e222f 100644 --- a/net/sctp/chunk.c +++ b/net/sctp/chunk.c @@ -225,7 +225,7 @@ struct sctp_datamsg *sctp_datamsg_from_user(struct sctp_association *asoc, if (msg_len >= first_len) { msg->can_delay = 0; if (msg_len > first_len) - SCTP_INC_STATS(sock_net(asoc->base.sk), + SCTP_INC_STATS(asoc->base.net, SCTP_MIB_FRAGUSRMSGS); } else { /* Which may be the only one... */ diff --git a/net/sctp/endpointola.c b/net/sctp/endpointola.c index 3ccab7440c9e..48c9c2c7602f 100644 --- a/net/sctp/endpointola.c +++ b/net/sctp/endpointola.c @@ -244,7 +244,7 @@ struct sctp_endpoint *sctp_endpoint_is_match(struct sctp_endpoint *ep, struct sctp_endpoint *retval = NULL; if ((htons(ep->base.bind_addr.port) == laddr->v4.sin_port) && - net_eq(sock_net(ep->base.sk), net)) { + net_eq(ep->base.net, net)) { if (sctp_bind_addr_match(&ep->base.bind_addr, laddr, sctp_sk(ep->base.sk))) retval = ep; @@ -292,8 +292,8 @@ bool sctp_endpoint_is_peeled_off(struct sctp_endpoint *ep, const union sctp_addr *paddr) { struct sctp_sockaddr_entry *addr; + struct net *net = ep->base.net; struct sctp_bind_addr *bp; - struct net *net = sock_net(ep->base.sk); bp = &ep->base.bind_addr; /* This function is called with the socket lock held, @@ -384,7 +384,7 @@ normal: if (asoc && sctp_chunk_is_data(chunk)) asoc->peer.last_data_from = chunk->transport; else { - SCTP_INC_STATS(sock_net(ep->base.sk), SCTP_MIB_INCTRLCHUNKS); + SCTP_INC_STATS(ep->base.net, SCTP_MIB_INCTRLCHUNKS); if (asoc) asoc->stats.ictrlchunks++; } diff --git a/net/sctp/input.c b/net/sctp/input.c index 4d2bcfc9d7f8..efaaefc3bb1c 100644 --- a/net/sctp/input.c +++ b/net/sctp/input.c @@ -937,7 +937,7 @@ int sctp_hash_transport(struct sctp_transport *t) if (t->asoc->temp) return 0; - arg.net = sock_net(t->asoc->base.sk); + arg.net = t->asoc->base.net; arg.paddr = &t->ipaddr; arg.lport = htons(t->asoc->base.bind_addr.port); @@ -1004,12 +1004,11 @@ struct sctp_transport *sctp_epaddr_lookup_transport( const struct sctp_endpoint *ep, const union sctp_addr *paddr) { - struct net *net = sock_net(ep->base.sk); struct rhlist_head *tmp, *list; struct sctp_transport *t; struct sctp_hash_cmp_arg arg = { .paddr = paddr, - .net = net, + .net = ep->base.net, .lport = htons(ep->base.bind_addr.port), }; diff --git a/net/sctp/output.c b/net/sctp/output.c index dbda7e7927fd..1441eaf460bb 100644 --- a/net/sctp/output.c +++ b/net/sctp/output.c @@ -282,7 +282,7 @@ static enum sctp_xmit sctp_packet_bundle_sack(struct sctp_packet *pkt, sctp_chunk_free(sack); goto out; } - SCTP_INC_STATS(sock_net(asoc->base.sk), + SCTP_INC_STATS(asoc->base.net, SCTP_MIB_OUTCTRLCHUNKS); asoc->stats.octrlchunks++; asoc->peer.sack_needed = 0; diff --git a/net/sctp/outqueue.c b/net/sctp/outqueue.c index 0dab62b67b9a..577e3bc4ee6f 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); @@ -279,7 +280,7 @@ void sctp_outq_free(struct sctp_outq *q) /* Put a new chunk in an sctp_outq. */ void sctp_outq_tail(struct sctp_outq *q, struct sctp_chunk *chunk, gfp_t gfp) { - struct net *net = sock_net(q->asoc->base.sk); + struct net *net = q->asoc->base.net; pr_debug("%s: outq:%p, chunk:%p[%s]\n", __func__, q, chunk, chunk && chunk->chunk_hdr ? @@ -533,7 +534,7 @@ void sctp_retransmit_mark(struct sctp_outq *q, void sctp_retransmit(struct sctp_outq *q, struct sctp_transport *transport, enum sctp_retransmit_reason reason) { - struct net *net = sock_net(q->asoc->base.sk); + struct net *net = q->asoc->base.net; switch (reason) { case SCTP_RTXR_T3_RTX: @@ -1238,6 +1239,12 @@ 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. */ + if (trace_sctp_probe_path_enabled()) { + 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; @@ -1884,6 +1891,6 @@ void sctp_generate_fwdtsn(struct sctp_outq *q, __u32 ctsn) if (ftsn_chunk) { list_add_tail(&ftsn_chunk->list, &q->control_chunk_list); - SCTP_INC_STATS(sock_net(asoc->base.sk), SCTP_MIB_OUTCTRLCHUNKS); + SCTP_INC_STATS(asoc->base.net, SCTP_MIB_OUTCTRLCHUNKS); } } diff --git a/net/sctp/sm_make_chunk.c b/net/sctp/sm_make_chunk.c index 48d63956a68c..09050c1d5517 100644 --- a/net/sctp/sm_make_chunk.c +++ b/net/sctp/sm_make_chunk.c @@ -2307,7 +2307,6 @@ int sctp_process_init(struct sctp_association *asoc, struct sctp_chunk *chunk, const union sctp_addr *peer_addr, struct sctp_init_chunk *peer_init, gfp_t gfp) { - struct net *net = sock_net(asoc->base.sk); struct sctp_transport *transport; struct list_head *pos, *temp; union sctp_params param; @@ -2363,8 +2362,8 @@ int sctp_process_init(struct sctp_association *asoc, struct sctp_chunk *chunk, * also give us an option to silently ignore the packet, which * is what we'll do here. */ - if (!net->sctp.addip_noauth && - (asoc->peer.asconf_capable && !asoc->peer.auth_capable)) { + if (!asoc->base.net->sctp.addip_noauth && + (asoc->peer.asconf_capable && !asoc->peer.auth_capable)) { asoc->peer.addip_disabled_mask |= (SCTP_PARAM_ADD_IP | SCTP_PARAM_DEL_IP | SCTP_PARAM_SET_PRIMARY); @@ -2491,9 +2490,9 @@ static int sctp_process_param(struct sctp_association *asoc, const union sctp_addr *peer_addr, gfp_t gfp) { - struct net *net = sock_net(asoc->base.sk); struct sctp_endpoint *ep = asoc->ep; union sctp_addr_param *addr_param; + struct net *net = asoc->base.net; struct sctp_transport *t; enum sctp_scope scope; union sctp_addr addr; diff --git a/net/sctp/sm_sideeffect.c b/net/sctp/sm_sideeffect.c index 834e9f82afed..2bc29463e1dc 100644 --- a/net/sctp/sm_sideeffect.c +++ b/net/sctp/sm_sideeffect.c @@ -516,8 +516,6 @@ static void sctp_do_8_2_transport_strike(struct sctp_cmd_seq *commands, struct sctp_transport *transport, int is_hb) { - struct net *net = sock_net(asoc->base.sk); - /* The check for association's overall error counter exceeding the * threshold is done in the state function. */ @@ -544,10 +542,10 @@ static void sctp_do_8_2_transport_strike(struct sctp_cmd_seq *commands, * is SCTP_ACTIVE, then mark this transport as Partially Failed, * see SCTP Quick Failover Draft, section 5.1 */ - if (net->sctp.pf_enable && - (transport->state == SCTP_ACTIVE) && - (transport->error_count < transport->pathmaxrxt) && - (transport->error_count > transport->pf_retrans)) { + if (asoc->base.net->sctp.pf_enable && + transport->state == SCTP_ACTIVE && + transport->error_count < transport->pathmaxrxt && + transport->error_count > transport->pf_retrans) { sctp_assoc_control_transport(asoc, transport, SCTP_TRANSPORT_PF, @@ -798,10 +796,8 @@ static int sctp_cmd_process_sack(struct sctp_cmd_seq *cmds, int err = 0; if (sctp_outq_sack(&asoc->outqueue, chunk)) { - struct net *net = sock_net(asoc->base.sk); - /* There are no more TSNs awaiting SACK. */ - err = sctp_do_sm(net, SCTP_EVENT_T_OTHER, + err = sctp_do_sm(asoc->base.net, SCTP_EVENT_T_OTHER, SCTP_ST_OTHER(SCTP_EVENT_NO_PENDING_TSN), asoc->state, asoc->ep, asoc, NULL, GFP_ATOMIC); @@ -834,7 +830,7 @@ static void sctp_cmd_assoc_update(struct sctp_cmd_seq *cmds, struct sctp_association *asoc, struct sctp_association *new) { - struct net *net = sock_net(asoc->base.sk); + struct net *net = asoc->base.net; struct sctp_chunk *abort; if (!sctp_assoc_update(asoc, new)) diff --git a/net/sctp/sm_statefuns.c b/net/sctp/sm_statefuns.c index 4ab8208a2dd4..748e3b19ec1d 100644 --- a/net/sctp/sm_statefuns.c +++ b/net/sctp/sm_statefuns.c @@ -1320,7 +1320,7 @@ static int sctp_sf_check_restart_addrs(const struct sctp_association *new_asoc, struct sctp_chunk *init, struct sctp_cmd_seq *commands) { - struct net *net = sock_net(new_asoc->base.sk); + struct net *net = new_asoc->base.net; struct sctp_transport *new_addr; int ret = 1; @@ -3281,8 +3281,6 @@ enum sctp_disposition sctp_sf_eat_sack_6_2(struct net *net, struct sctp_sackhdr *sackh; __u32 ctsn; - trace_sctp_probe(ep, asoc, chunk); - if (!sctp_vtag_verify(chunk, asoc)) return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands); @@ -3299,6 +3297,15 @@ enum sctp_disposition sctp_sf_eat_sack_6_2(struct net *net, chunk->subh.sack_hdr = sackh; ctsn = ntohl(sackh->cum_tsn_ack); + /* If Cumulative TSN Ack beyond the max tsn currently + * send, terminating the association and respond to the + * sender with an ABORT. + */ + if (TSN_lte(asoc->next_tsn, ctsn)) + return sctp_sf_violation_ctsn(net, ep, asoc, type, arg, commands); + + trace_sctp_probe(ep, asoc, chunk); + /* i) If Cumulative TSN Ack is less than the Cumulative TSN * Ack Point, then drop the SACK. Since Cumulative TSN * Ack is monotonically increasing, a SACK whose @@ -3312,13 +3319,6 @@ enum sctp_disposition sctp_sf_eat_sack_6_2(struct net *net, return SCTP_DISPOSITION_DISCARD; } - /* If Cumulative TSN Ack beyond the max tsn currently - * send, terminating the association and respond to the - * sender with an ABORT. - */ - if (!TSN_lt(ctsn, asoc->next_tsn)) - return sctp_sf_violation_ctsn(net, ep, asoc, type, arg, commands); - /* Return this SACK for further processing. */ sctp_add_cmd_sf(commands, SCTP_CMD_PROCESS_SACK, SCTP_CHUNK(chunk)); diff --git a/net/sctp/socket.c b/net/sctp/socket.c index 0b485952a71c..1b56fc440606 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -436,8 +436,7 @@ static int sctp_do_bind(struct sock *sk, union sctp_addr *addr, int len) static int sctp_send_asconf(struct sctp_association *asoc, struct sctp_chunk *chunk) { - struct net *net = sock_net(asoc->base.sk); - int retval = 0; + int retval = 0; /* If there is an outstanding ASCONF chunk, queue it for later * transmission. @@ -449,7 +448,7 @@ static int sctp_send_asconf(struct sctp_association *asoc, /* Hold the chunk until an ASCONF_ACK is received. */ sctp_chunk_hold(chunk); - retval = sctp_primitive_ASCONF(net, asoc, chunk); + retval = sctp_primitive_ASCONF(asoc->base.net, asoc, chunk); if (retval) sctp_chunk_free(chunk); else @@ -2428,9 +2427,8 @@ static int sctp_apply_peer_addr_params(struct sctp_paddrparams *params, int error; if (params->spp_flags & SPP_HB_DEMAND && trans) { - struct net *net = sock_net(trans->asoc->base.sk); - - error = sctp_primitive_REQUESTHEARTBEAT(net, trans->asoc, trans); + error = sctp_primitive_REQUESTHEARTBEAT(trans->asoc->base.net, + trans->asoc, trans); if (error) return error; } @@ -5364,7 +5362,7 @@ struct sctp_transport *sctp_transport_get_next(struct net *net, if (!sctp_transport_hold(t)) continue; - if (net_eq(sock_net(t->asoc->base.sk), net) && + if (net_eq(t->asoc->base.net, net) && t->asoc->peer.primary_path == t) break; diff --git a/net/sctp/stream.c b/net/sctp/stream.c index c1a100d2fed3..67f7e71f9129 100644 --- a/net/sctp/stream.c +++ b/net/sctp/stream.c @@ -222,10 +222,9 @@ void sctp_stream_update(struct sctp_stream *stream, struct sctp_stream *new) static int sctp_send_reconf(struct sctp_association *asoc, struct sctp_chunk *chunk) { - struct net *net = sock_net(asoc->base.sk); int retval = 0; - retval = sctp_primitive_RECONF(net, asoc, chunk); + retval = sctp_primitive_RECONF(asoc->base.net, asoc, chunk); if (retval) sctp_chunk_free(chunk); diff --git a/net/sctp/stream_interleave.c b/net/sctp/stream_interleave.c index 40c40be23fcb..6b13f737ebf2 100644 --- a/net/sctp/stream_interleave.c +++ b/net/sctp/stream_interleave.c @@ -241,9 +241,8 @@ out: if (!first_frag) return NULL; - retval = sctp_make_reassembled_event(sock_net(ulpq->asoc->base.sk), - &ulpq->reasm, first_frag, - last_frag); + retval = sctp_make_reassembled_event(ulpq->asoc->base.net, &ulpq->reasm, + first_frag, last_frag); if (retval) { sin->fsn = next_fsn; if (is_last) { @@ -326,7 +325,7 @@ static struct sctp_ulpevent *sctp_intl_retrieve_reassembled( pd_point = sctp_sk(asoc->base.sk)->pd_point; if (pd_point && pd_point <= pd_len) { - retval = sctp_make_reassembled_event(sock_net(asoc->base.sk), + retval = sctp_make_reassembled_event(asoc->base.net, &ulpq->reasm, pd_first, pd_last); if (retval) { @@ -337,8 +336,7 @@ static struct sctp_ulpevent *sctp_intl_retrieve_reassembled( goto out; found: - retval = sctp_make_reassembled_event(sock_net(asoc->base.sk), - &ulpq->reasm, + retval = sctp_make_reassembled_event(asoc->base.net, &ulpq->reasm, first_frag, pos); if (retval) retval->msg_flags |= MSG_EOR; @@ -630,7 +628,7 @@ out: if (!first_frag) return NULL; - retval = sctp_make_reassembled_event(sock_net(ulpq->asoc->base.sk), + retval = sctp_make_reassembled_event(ulpq->asoc->base.net, &ulpq->reasm_uo, first_frag, last_frag); if (retval) { @@ -716,7 +714,7 @@ static struct sctp_ulpevent *sctp_intl_retrieve_reassembled_uo( pd_point = sctp_sk(asoc->base.sk)->pd_point; if (pd_point && pd_point <= pd_len) { - retval = sctp_make_reassembled_event(sock_net(asoc->base.sk), + retval = sctp_make_reassembled_event(asoc->base.net, &ulpq->reasm_uo, pd_first, pd_last); if (retval) { @@ -727,8 +725,7 @@ static struct sctp_ulpevent *sctp_intl_retrieve_reassembled_uo( goto out; found: - retval = sctp_make_reassembled_event(sock_net(asoc->base.sk), - &ulpq->reasm_uo, + retval = sctp_make_reassembled_event(asoc->base.net, &ulpq->reasm_uo, first_frag, pos); if (retval) retval->msg_flags |= MSG_EOR; @@ -814,7 +811,7 @@ static struct sctp_ulpevent *sctp_intl_retrieve_first_uo(struct sctp_ulpq *ulpq) return NULL; out: - retval = sctp_make_reassembled_event(sock_net(ulpq->asoc->base.sk), + retval = sctp_make_reassembled_event(ulpq->asoc->base.net, &ulpq->reasm_uo, first_frag, last_frag); if (retval) { @@ -921,7 +918,7 @@ static struct sctp_ulpevent *sctp_intl_retrieve_first(struct sctp_ulpq *ulpq) return NULL; out: - retval = sctp_make_reassembled_event(sock_net(ulpq->asoc->base.sk), + retval = sctp_make_reassembled_event(ulpq->asoc->base.net, &ulpq->reasm, first_frag, last_frag); if (retval) { @@ -1159,7 +1156,7 @@ static void sctp_generate_iftsn(struct sctp_outq *q, __u32 ctsn) if (ftsn_chunk) { list_add_tail(&ftsn_chunk->list, &q->control_chunk_list); - SCTP_INC_STATS(sock_net(asoc->base.sk), SCTP_MIB_OUTCTRLCHUNKS); + SCTP_INC_STATS(asoc->base.net, SCTP_MIB_OUTCTRLCHUNKS); } } diff --git a/net/sctp/transport.c b/net/sctp/transport.c index 3bbe1a58ec87..806af58f4375 100644 --- a/net/sctp/transport.c +++ b/net/sctp/transport.c @@ -334,7 +334,7 @@ void sctp_transport_update_rto(struct sctp_transport *tp, __u32 rtt) pr_debug("%s: rto_pending not set on transport %p!\n", __func__, tp); if (tp->rttvar || tp->srtt) { - struct net *net = sock_net(tp->asoc->base.sk); + struct net *net = tp->asoc->base.net; /* 6.3.1 C3) When a new RTT measurement R' is made, set * RTTVAR <- (1 - RTO.Beta) * RTTVAR + RTO.Beta * |SRTT - R'| * SRTT <- (1 - RTO.Alpha) * SRTT + RTO.Alpha * R' diff --git a/net/sctp/ulpqueue.c b/net/sctp/ulpqueue.c index b6536b7f14c0..1c6c640607c5 100644 --- a/net/sctp/ulpqueue.c +++ b/net/sctp/ulpqueue.c @@ -486,10 +486,9 @@ static struct sctp_ulpevent *sctp_ulpq_retrieve_reassembled(struct sctp_ulpq *ul cevent = sctp_skb2event(pd_first); pd_point = sctp_sk(asoc->base.sk)->pd_point; if (pd_point && pd_point <= pd_len) { - retval = sctp_make_reassembled_event(sock_net(asoc->base.sk), + retval = sctp_make_reassembled_event(asoc->base.net, &ulpq->reasm, - pd_first, - pd_last); + pd_first, pd_last); if (retval) sctp_ulpq_set_pd(ulpq); } @@ -497,7 +496,7 @@ static struct sctp_ulpevent *sctp_ulpq_retrieve_reassembled(struct sctp_ulpq *ul done: return retval; found: - retval = sctp_make_reassembled_event(sock_net(ulpq->asoc->base.sk), + retval = sctp_make_reassembled_event(ulpq->asoc->base.net, &ulpq->reasm, first_frag, pos); if (retval) retval->msg_flags |= MSG_EOR; @@ -563,8 +562,8 @@ static struct sctp_ulpevent *sctp_ulpq_retrieve_partial(struct sctp_ulpq *ulpq) * further. */ done: - retval = sctp_make_reassembled_event(sock_net(ulpq->asoc->base.sk), - &ulpq->reasm, first_frag, last_frag); + retval = sctp_make_reassembled_event(ulpq->asoc->base.net, &ulpq->reasm, + first_frag, last_frag); if (retval && is_last) retval->msg_flags |= MSG_EOR; @@ -664,8 +663,8 @@ static struct sctp_ulpevent *sctp_ulpq_retrieve_first(struct sctp_ulpq *ulpq) * further. */ done: - retval = sctp_make_reassembled_event(sock_net(ulpq->asoc->base.sk), - &ulpq->reasm, first_frag, last_frag); + retval = sctp_make_reassembled_event(ulpq->asoc->base.net, &ulpq->reasm, + first_frag, last_frag); return retval; } diff --git a/net/smc/smc_core.c b/net/smc/smc_core.c index e419ff277e55..2249de5379ee 100644 --- a/net/smc/smc_core.c +++ b/net/smc/smc_core.c @@ -41,7 +41,7 @@ static struct smc_lgr_list smc_lgr_list = { /* established link groups */ .num = 0, }; -static atomic_t lgr_cnt; /* number of existing link groups */ +static atomic_t lgr_cnt = ATOMIC_INIT(0); /* number of existing link groups */ static DECLARE_WAIT_QUEUE_HEAD(lgrs_deleted); static void smc_buf_free(struct smc_link_group *lgr, bool is_rmb, @@ -1297,7 +1297,6 @@ static struct notifier_block smc_reboot_notifier = { int __init smc_core_init(void) { - atomic_set(&lgr_cnt, 0); return register_reboot_notifier(&smc_reboot_notifier); } diff --git a/net/smc/smc_pnet.c b/net/smc/smc_pnet.c index 82dedf052d86..2a5ed47c3e08 100644 --- a/net/smc/smc_pnet.c +++ b/net/smc/smc_pnet.c @@ -611,7 +611,7 @@ static const struct genl_ops smc_pnet_ops[] = { { .cmd = SMC_PNETID_GET, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, - .flags = GENL_ADMIN_PERM, + /* can be retrieved by unprivileged users */ .doit = smc_pnet_get, .dumpit = smc_pnet_dump, .start = smc_pnet_dump_start diff --git a/net/socket.c b/net/socket.c index 50623218747f..b79a05de7c6e 100644 --- a/net/socket.c +++ b/net/socket.c @@ -129,6 +129,18 @@ static ssize_t sock_splice_read(struct file *file, loff_t *ppos, struct pipe_inode_info *pipe, size_t len, unsigned int flags); +#ifdef CONFIG_PROC_FS +static void sock_show_fdinfo(struct seq_file *m, struct file *f) +{ + struct socket *sock = f->private_data; + + if (sock->ops->show_fdinfo) + sock->ops->show_fdinfo(m, sock); +} +#else +#define sock_show_fdinfo NULL +#endif + /* * Socket files have a set of 'special' operations as well as the generic file ones. These don't appear * in the operation structures but are done directly via the socketcall() multiplexor. @@ -150,6 +162,7 @@ static const struct file_operations socket_file_ops = { .sendpage = sock_sendpage, .splice_write = generic_splice_sendpage, .splice_read = sock_splice_read, + .show_fdinfo = sock_show_fdinfo, }; /* diff --git a/net/tipc/bcast.c b/net/tipc/bcast.c index 656ebc79c64e..4c20be08b9c4 100644 --- a/net/tipc/bcast.c +++ b/net/tipc/bcast.c @@ -568,18 +568,18 @@ int tipc_bclink_reset_stats(struct net *net) return 0; } -static int tipc_bc_link_set_queue_limits(struct net *net, u32 limit) +static int tipc_bc_link_set_queue_limits(struct net *net, u32 max_win) { struct tipc_link *l = tipc_bc_sndlink(net); if (!l) return -ENOPROTOOPT; - if (limit < BCLINK_WIN_MIN) - limit = BCLINK_WIN_MIN; - if (limit > TIPC_MAX_LINK_WIN) + if (max_win < BCLINK_WIN_MIN) + max_win = BCLINK_WIN_MIN; + if (max_win > TIPC_MAX_LINK_WIN) return -EINVAL; tipc_bcast_lock(net); - tipc_link_set_queue_limits(l, limit); + tipc_link_set_queue_limits(l, BCLINK_WIN_MIN, max_win); tipc_bcast_unlock(net); return 0; } @@ -689,6 +689,7 @@ int tipc_bcast_init(struct net *net) if (!tipc_link_bc_create(net, 0, 0, FB_MTU, BCLINK_WIN_DEFAULT, + BCLINK_WIN_DEFAULT, 0, &bb->inputq, NULL, diff --git a/net/tipc/bearer.c b/net/tipc/bearer.c index d7ec26bd739d..34ca7b789eba 100644 --- a/net/tipc/bearer.c +++ b/net/tipc/bearer.c @@ -311,7 +311,8 @@ static int tipc_enable_bearer(struct net *net, const char *name, b->identity = bearer_id; b->tolerance = m->tolerance; - b->window = m->window; + b->min_win = m->min_win; + b->max_win = m->max_win; b->domain = disc_domain; b->net_plane = bearer_id + 'A'; b->priority = prio; @@ -796,7 +797,7 @@ static int __tipc_nl_add_bearer(struct tipc_nl_msg *msg, goto prop_msg_full; if (nla_put_u32(msg->skb, TIPC_NLA_PROP_TOL, bearer->tolerance)) goto prop_msg_full; - if (nla_put_u32(msg->skb, TIPC_NLA_PROP_WIN, bearer->window)) + if (nla_put_u32(msg->skb, TIPC_NLA_PROP_WIN, bearer->max_win)) goto prop_msg_full; if (bearer->media->type_id == TIPC_MEDIA_TYPE_UDP) if (nla_put_u32(msg->skb, TIPC_NLA_PROP_MTU, bearer->mtu)) @@ -1088,7 +1089,7 @@ int __tipc_nl_bearer_set(struct sk_buff *skb, struct genl_info *info) if (props[TIPC_NLA_PROP_PRIO]) b->priority = nla_get_u32(props[TIPC_NLA_PROP_PRIO]); if (props[TIPC_NLA_PROP_WIN]) - b->window = nla_get_u32(props[TIPC_NLA_PROP_WIN]); + b->max_win = nla_get_u32(props[TIPC_NLA_PROP_WIN]); if (props[TIPC_NLA_PROP_MTU]) { if (b->media->type_id != TIPC_MEDIA_TYPE_UDP) return -EINVAL; @@ -1142,7 +1143,7 @@ static int __tipc_nl_add_media(struct tipc_nl_msg *msg, goto prop_msg_full; if (nla_put_u32(msg->skb, TIPC_NLA_PROP_TOL, media->tolerance)) goto prop_msg_full; - if (nla_put_u32(msg->skb, TIPC_NLA_PROP_WIN, media->window)) + if (nla_put_u32(msg->skb, TIPC_NLA_PROP_WIN, media->max_win)) goto prop_msg_full; if (media->type_id == TIPC_MEDIA_TYPE_UDP) if (nla_put_u32(msg->skb, TIPC_NLA_PROP_MTU, media->mtu)) @@ -1275,7 +1276,7 @@ int __tipc_nl_media_set(struct sk_buff *skb, struct genl_info *info) if (props[TIPC_NLA_PROP_PRIO]) m->priority = nla_get_u32(props[TIPC_NLA_PROP_PRIO]); if (props[TIPC_NLA_PROP_WIN]) - m->window = nla_get_u32(props[TIPC_NLA_PROP_WIN]); + m->max_win = nla_get_u32(props[TIPC_NLA_PROP_WIN]); if (props[TIPC_NLA_PROP_MTU]) { if (m->type_id != TIPC_MEDIA_TYPE_UDP) return -EINVAL; diff --git a/net/tipc/bearer.h b/net/tipc/bearer.h index d0c79cc6c0c2..bc0023119da2 100644 --- a/net/tipc/bearer.h +++ b/net/tipc/bearer.h @@ -119,7 +119,8 @@ struct tipc_media { char *raw); u32 priority; u32 tolerance; - u32 window; + u32 min_win; + u32 max_win; u32 mtu; u32 type_id; u32 hwaddr_len; @@ -158,7 +159,8 @@ struct tipc_bearer { struct packet_type pt; struct rcu_head rcu; u32 priority; - u32 window; + u32 min_win; + u32 max_win; u32 tolerance; u32 domain; u32 identity; diff --git a/net/tipc/eth_media.c b/net/tipc/eth_media.c index f69a2fde9f4a..8b0bb600602d 100644 --- a/net/tipc/eth_media.c +++ b/net/tipc/eth_media.c @@ -92,7 +92,8 @@ struct tipc_media eth_media_info = { .raw2addr = tipc_eth_raw2addr, .priority = TIPC_DEF_LINK_PRI, .tolerance = TIPC_DEF_LINK_TOL, - .window = TIPC_DEF_LINK_WIN, + .min_win = TIPC_DEF_LINK_WIN, + .max_win = TIPC_MAX_LINK_WIN, .type_id = TIPC_MEDIA_TYPE_ETH, .hwaddr_len = ETH_ALEN, .name = "eth" diff --git a/net/tipc/ib_media.c b/net/tipc/ib_media.c index e8c16718e3fa..7aa9ff88458d 100644 --- a/net/tipc/ib_media.c +++ b/net/tipc/ib_media.c @@ -42,6 +42,8 @@ #include "core.h" #include "bearer.h" +#define TIPC_MAX_IB_LINK_WIN 500 + /* convert InfiniBand address (media address format) media address to string */ static int tipc_ib_addr2str(struct tipc_media_addr *a, char *str_buf, int str_size) @@ -94,7 +96,8 @@ struct tipc_media ib_media_info = { .raw2addr = tipc_ib_raw2addr, .priority = TIPC_DEF_LINK_PRI, .tolerance = TIPC_DEF_LINK_TOL, - .window = TIPC_DEF_LINK_WIN, + .min_win = TIPC_DEF_LINK_WIN, + .max_win = TIPC_MAX_IB_LINK_WIN, .type_id = TIPC_MEDIA_TYPE_IB, .hwaddr_len = INFINIBAND_ALEN, .name = "ib" diff --git a/net/tipc/link.c b/net/tipc/link.c index 24d4d10756d3..467c53a1fb5c 100644 --- a/net/tipc/link.c +++ b/net/tipc/link.c @@ -164,7 +164,6 @@ struct tipc_link { struct sk_buff *target_bskb; } backlog[5]; u16 snd_nxt; - u16 window; /* Reception */ u16 rcv_nxt; @@ -175,6 +174,12 @@ struct tipc_link { /* Congestion handling */ struct sk_buff_head wakeupq; + u16 window; + u16 min_win; + u16 ssthresh; + u16 max_win; + u16 cong_acks; + u16 checkpoint; /* Fragmentation/reassembly */ struct sk_buff *reasm_buf; @@ -244,12 +249,13 @@ static int tipc_link_build_nack_msg(struct tipc_link *l, struct sk_buff_head *xmitq); static void tipc_link_build_bc_init_msg(struct tipc_link *l, struct sk_buff_head *xmitq); -static bool tipc_link_release_pkts(struct tipc_link *l, u16 to); -static u16 tipc_build_gap_ack_blks(struct tipc_link *l, void *data); +static int tipc_link_release_pkts(struct tipc_link *l, u16 to); +static u16 tipc_build_gap_ack_blks(struct tipc_link *l, void *data, u16 gap); static int tipc_link_advance_transmq(struct tipc_link *l, u16 acked, u16 gap, struct tipc_gap_ack_blks *ga, struct sk_buff_head *xmitq); - +static void tipc_link_update_cwin(struct tipc_link *l, int released, + bool retransmitted); /* * Simple non-static link routines (i.e. referenced outside this file) */ @@ -308,9 +314,14 @@ u32 tipc_link_id(struct tipc_link *l) return l->peer_bearer_id << 16 | l->bearer_id; } -int tipc_link_window(struct tipc_link *l) +int tipc_link_min_win(struct tipc_link *l) { - return l->window; + return l->min_win; +} + +int tipc_link_max_win(struct tipc_link *l) +{ + return l->max_win; } int tipc_link_prio(struct tipc_link *l) @@ -436,7 +447,8 @@ u32 tipc_link_state(struct tipc_link *l) * @net_plane: network plane (A,B,c..) this link belongs to * @mtu: mtu to be advertised by link * @priority: priority to be used by link - * @window: send window to be used by link + * @min_win: minimal send window to be used by link + * @max_win: maximal send window to be used by link * @session: session to be used by link * @ownnode: identity of own node * @peer: node id of peer node @@ -451,7 +463,7 @@ u32 tipc_link_state(struct tipc_link *l) */ bool tipc_link_create(struct net *net, char *if_name, int bearer_id, int tolerance, char net_plane, u32 mtu, int priority, - int window, u32 session, u32 self, + u32 min_win, u32 max_win, u32 session, u32 self, u32 peer, u8 *peer_id, u16 peer_caps, struct tipc_link *bc_sndlink, struct tipc_link *bc_rcvlink, @@ -495,7 +507,7 @@ bool tipc_link_create(struct net *net, char *if_name, int bearer_id, l->advertised_mtu = mtu; l->mtu = mtu; l->priority = priority; - tipc_link_set_queue_limits(l, window); + tipc_link_set_queue_limits(l, min_win, max_win); l->ackers = 1; l->bc_sndlink = bc_sndlink; l->bc_rcvlink = bc_rcvlink; @@ -523,7 +535,7 @@ bool tipc_link_create(struct net *net, char *if_name, int bearer_id, * Returns true if link was created, otherwise false */ bool tipc_link_bc_create(struct net *net, u32 ownnode, u32 peer, - int mtu, int window, u16 peer_caps, + int mtu, u32 min_win, u32 max_win, u16 peer_caps, struct sk_buff_head *inputq, struct sk_buff_head *namedq, struct tipc_link *bc_sndlink, @@ -531,9 +543,9 @@ bool tipc_link_bc_create(struct net *net, u32 ownnode, u32 peer, { struct tipc_link *l; - if (!tipc_link_create(net, "", MAX_BEARERS, 0, 'Z', mtu, 0, window, - 0, ownnode, peer, NULL, peer_caps, bc_sndlink, - NULL, inputq, namedq, link)) + if (!tipc_link_create(net, "", MAX_BEARERS, 0, 'Z', mtu, 0, min_win, + max_win, 0, ownnode, peer, NULL, peer_caps, + bc_sndlink, NULL, inputq, namedq, link)) return false; l = *link; @@ -772,6 +784,8 @@ bool tipc_link_too_silent(struct tipc_link *l) return (l->silent_intv_cnt + 2 > l->abort_limit); } +static int tipc_link_bc_retrans(struct tipc_link *l, struct tipc_link *r, + u16 from, u16 to, struct sk_buff_head *xmitq); /* tipc_link_timeout - perform periodic task as instructed from node timeout */ int tipc_link_timeout(struct tipc_link *l, struct sk_buff_head *xmitq) @@ -804,6 +818,11 @@ int tipc_link_timeout(struct tipc_link *l, struct sk_buff_head *xmitq) probe |= l->silent_intv_cnt; if (probe || mstate->monitoring) l->silent_intv_cnt++; + if (l->snd_nxt == l->checkpoint) { + tipc_link_update_cwin(l, 0, 0); + probe = true; + } + l->checkpoint = l->snd_nxt; break; case LINK_RESET: setup = l->rst_cnt++ <= 4; @@ -959,7 +978,7 @@ int tipc_link_xmit(struct tipc_link *l, struct sk_buff_head *list, int pkt_cnt = skb_queue_len(list); int imp = msg_importance(hdr); unsigned int mss = tipc_link_mss(l); - unsigned int maxwin = l->window; + unsigned int cwin = l->window; unsigned int mtu = l->mtu; bool new_bundle; int rc = 0; @@ -988,7 +1007,7 @@ int tipc_link_xmit(struct tipc_link *l, struct sk_buff_head *list, /* Prepare each packet for sending, and add to relevant queue: */ while ((skb = __skb_dequeue(list))) { - if (likely(skb_queue_len(transmq) < maxwin)) { + if (likely(skb_queue_len(transmq) < cwin)) { hdr = buf_msg(skb); msg_set_seqno(hdr, seqno); msg_set_ack(hdr, ack); @@ -1035,17 +1054,61 @@ int tipc_link_xmit(struct tipc_link *l, struct sk_buff_head *list, return rc; } +static void tipc_link_update_cwin(struct tipc_link *l, int released, + bool retransmitted) +{ + int bklog_len = skb_queue_len(&l->backlogq); + struct sk_buff_head *txq = &l->transmq; + int txq_len = skb_queue_len(txq); + u16 cwin = l->window; + + /* Enter fast recovery */ + if (unlikely(retransmitted)) { + l->ssthresh = max_t(u16, l->window / 2, 300); + l->window = l->ssthresh; + return; + } + /* Enter slow start */ + if (unlikely(!released)) { + l->ssthresh = max_t(u16, l->window / 2, 300); + l->window = l->min_win; + return; + } + /* Don't increase window if no pressure on the transmit queue */ + if (txq_len + bklog_len < cwin) + return; + + /* Don't increase window if there are holes the transmit queue */ + if (txq_len && l->snd_nxt - buf_seqno(skb_peek(txq)) != txq_len) + return; + + l->cong_acks += released; + + /* Slow start */ + if (cwin <= l->ssthresh) { + l->window = min_t(u16, cwin + released, l->max_win); + return; + } + /* Congestion avoidance */ + if (l->cong_acks < cwin) + return; + l->window = min_t(u16, ++cwin, l->max_win); + l->cong_acks = 0; +} + static void tipc_link_advance_backlog(struct tipc_link *l, struct sk_buff_head *xmitq) { + u16 bc_ack = l->bc_rcvlink->rcv_nxt - 1; + struct sk_buff_head *txq = &l->transmq; struct sk_buff *skb, *_skb; - struct tipc_msg *hdr; - u16 seqno = l->snd_nxt; u16 ack = l->rcv_nxt - 1; - u16 bc_ack = l->bc_rcvlink->rcv_nxt - 1; + u16 seqno = l->snd_nxt; + struct tipc_msg *hdr; + u16 cwin = l->window; u32 imp; - while (skb_queue_len(&l->transmq) < l->window) { + while (skb_queue_len(txq) < cwin) { skb = skb_peek(&l->backlogq); if (!skb) break; @@ -1141,6 +1204,7 @@ static int tipc_link_bc_retrans(struct tipc_link *l, struct tipc_link *r, struct sk_buff *_skb, *skb = skb_peek(&l->transmq); u16 bc_ack = l->bc_rcvlink->rcv_nxt - 1; u16 ack = l->rcv_nxt - 1; + int retransmitted = 0; struct tipc_msg *hdr; int rc = 0; @@ -1160,7 +1224,6 @@ static int tipc_link_bc_retrans(struct tipc_link *l, struct tipc_link *r, continue; if (more(msg_seqno(hdr), to)) break; - if (time_before(jiffies, TIPC_SKB_CB(skb)->nxt_retr)) continue; TIPC_SKB_CB(skb)->nxt_retr = TIPC_BC_RETR_LIM; @@ -1173,11 +1236,12 @@ static int tipc_link_bc_retrans(struct tipc_link *l, struct tipc_link *r, _skb->priority = TC_PRIO_CONTROL; __skb_queue_tail(xmitq, _skb); l->stats.retransmitted++; - + retransmitted++; /* Increase actual retrans counter & mark first time */ if (!TIPC_SKB_CB(skb)->retr_cnt++) TIPC_SKB_CB(skb)->retr_stamp = jiffies; } + tipc_link_update_cwin(l, 0, retransmitted); return 0; } @@ -1338,9 +1402,9 @@ static int tipc_link_tnl_rcv(struct tipc_link *l, struct sk_buff *skb, return rc; } -static bool tipc_link_release_pkts(struct tipc_link *l, u16 acked) +static int tipc_link_release_pkts(struct tipc_link *l, u16 acked) { - bool released = false; + int released = 0; struct sk_buff *skb, *tmp; skb_queue_walk_safe(&l->transmq, skb, tmp) { @@ -1348,7 +1412,7 @@ static bool tipc_link_release_pkts(struct tipc_link *l, u16 acked) break; __skb_unlink(skb, &l->transmq); kfree_skb(skb); - released = true; + released++; } return released; } @@ -1359,14 +1423,14 @@ static bool tipc_link_release_pkts(struct tipc_link *l, u16 acked) * * returns the actual allocated memory size */ -static u16 tipc_build_gap_ack_blks(struct tipc_link *l, void *data) +static u16 tipc_build_gap_ack_blks(struct tipc_link *l, void *data, u16 gap) { struct sk_buff *skb = skb_peek(&l->deferdq); struct tipc_gap_ack_blks *ga = data; u16 len, expect, seqno = 0; u8 n = 0; - if (!skb) + if (!skb || !gap) goto exit; expect = buf_seqno(skb); @@ -1417,8 +1481,10 @@ static int tipc_link_advance_transmq(struct tipc_link *l, u16 acked, u16 gap, struct sk_buff *skb, *_skb, *tmp; struct tipc_msg *hdr; u16 bc_ack = l->bc_rcvlink->rcv_nxt - 1; + bool retransmitted = false; u16 ack = l->rcv_nxt - 1; bool passed = false; + u16 released = 0; u16 seqno, n = 0; int rc = 0; @@ -1430,6 +1496,7 @@ next_gap_ack: /* release skb */ __skb_unlink(skb, &l->transmq); kfree_skb(skb); + released++; } else if (less_eq(seqno, acked + gap)) { /* First, check if repeated retrans failures occurs? */ if (!passed && link_retransmit_failure(l, l, &rc)) @@ -1449,7 +1516,7 @@ next_gap_ack: _skb->priority = TC_PRIO_CONTROL; __skb_queue_tail(xmitq, _skb); l->stats.retransmitted++; - + retransmitted = true; /* Increase actual retrans counter & mark first time */ if (!TIPC_SKB_CB(skb)->retr_cnt++) TIPC_SKB_CB(skb)->retr_stamp = jiffies; @@ -1463,7 +1530,10 @@ next_gap_ack: goto next_gap_ack; } } - + if (released || retransmitted) + tipc_link_update_cwin(l, released, retransmitted); + if (released) + tipc_link_advance_backlog(l, xmitq); return 0; } @@ -1487,7 +1557,6 @@ int tipc_link_build_state_msg(struct tipc_link *l, struct sk_buff_head *xmitq) l->snd_nxt = l->rcv_nxt; return TIPC_LINK_SND_STATE; } - /* Unicast ACK */ l->rcv_unacked = 0; l->stats.sent_acks++; @@ -1521,7 +1590,8 @@ static int tipc_link_build_nack_msg(struct tipc_link *l, struct sk_buff_head *xmitq) { u32 def_cnt = ++l->stats.deferred_recv; - u32 defq_len = skb_queue_len(&l->deferdq); + struct sk_buff_head *dfq = &l->deferdq; + u32 defq_len = skb_queue_len(dfq); int match1, match2; if (link_is_bc_rcvlink(l)) { @@ -1532,8 +1602,12 @@ static int tipc_link_build_nack_msg(struct tipc_link *l, return 0; } - if (defq_len >= 3 && !((defq_len - 3) % 16)) - tipc_link_build_proto_msg(l, STATE_MSG, 0, 0, 0, 0, 0, xmitq); + if (defq_len >= 3 && !((defq_len - 3) % 16)) { + u16 rcvgap = buf_seqno(skb_peek(dfq)) - l->rcv_nxt; + + tipc_link_build_proto_msg(l, STATE_MSG, 0, 0, + rcvgap, 0, 0, xmitq); + } return 0; } @@ -1548,6 +1622,7 @@ int tipc_link_rcv(struct tipc_link *l, struct sk_buff *skb, struct sk_buff_head *defq = &l->deferdq; struct tipc_msg *hdr = buf_msg(skb); u16 seqno, rcv_nxt, win_lim; + int released = 0; int rc = 0; /* Verify and update link state */ @@ -1566,21 +1641,17 @@ int tipc_link_rcv(struct tipc_link *l, struct sk_buff *skb, if (unlikely(!link_is_up(l))) { if (l->state == LINK_ESTABLISHING) rc = TIPC_LINK_UP_EVT; - goto drop; + kfree_skb(skb); + break; } /* Drop if outside receive window */ if (unlikely(less(seqno, rcv_nxt) || more(seqno, win_lim))) { l->stats.duplicates++; - goto drop; - } - - /* Forward queues and wake up waiting users */ - if (likely(tipc_link_release_pkts(l, msg_ack(hdr)))) { - tipc_link_advance_backlog(l, xmitq); - if (unlikely(!skb_queue_empty(&l->wakeupq))) - link_prepare_wakeup(l); + kfree_skb(skb); + break; } + released += tipc_link_release_pkts(l, msg_ack(hdr)); /* Defer delivery if sequence gap */ if (unlikely(seqno != rcv_nxt)) { @@ -1603,9 +1674,13 @@ int tipc_link_rcv(struct tipc_link *l, struct sk_buff *skb, break; } while ((skb = __tipc_skb_dequeue(defq, l->rcv_nxt))); - return rc; -drop: - kfree_skb(skb); + /* Forward queues and wake up waiting users */ + if (released) { + tipc_link_update_cwin(l, released, 0); + tipc_link_advance_backlog(l, xmitq); + if (unlikely(!skb_queue_empty(&l->wakeupq))) + link_prepare_wakeup(l); + } return rc; } @@ -1631,7 +1706,7 @@ static void tipc_link_build_proto_msg(struct tipc_link *l, int mtyp, bool probe, if (!tipc_link_is_up(l) && (mtyp == STATE_MSG)) return; - if (!skb_queue_empty(dfq)) + if ((probe || probe_reply) && !skb_queue_empty(dfq)) rcvgap = buf_seqno(skb_peek(dfq)) - l->rcv_nxt; skb = tipc_msg_create(LINK_PROTOCOL, mtyp, INT_H_SIZE, @@ -1664,7 +1739,7 @@ static void tipc_link_build_proto_msg(struct tipc_link *l, int mtyp, bool probe, msg_set_probe(hdr, probe); msg_set_is_keepalive(hdr, probe || probe_reply); if (l->peer_caps & TIPC_GAP_ACK_BLOCK) - glen = tipc_build_gap_ack_blks(l, data); + glen = tipc_build_gap_ack_blks(l, data, rcvgap); tipc_mon_prep(l->net, data + glen, &dlen, mstate, l->bearer_id); msg_set_size(hdr, INT_H_SIZE + glen + dlen); skb_trim(skb, INT_H_SIZE + glen + dlen); @@ -2074,19 +2149,18 @@ static int tipc_link_proto_rcv(struct tipc_link *l, struct sk_buff *skb, &l->mon_state, l->bearer_id); /* Send NACK if peer has sent pkts we haven't received yet */ - if (more(peers_snd_nxt, rcv_nxt) && !tipc_link_is_synching(l)) + if ((reply || msg_is_keepalive(hdr)) && + more(peers_snd_nxt, rcv_nxt) && + !tipc_link_is_synching(l) && + skb_queue_empty(&l->deferdq)) rcvgap = peers_snd_nxt - l->rcv_nxt; if (rcvgap || reply) tipc_link_build_proto_msg(l, STATE_MSG, 0, reply, rcvgap, 0, 0, xmitq); rc |= tipc_link_advance_transmq(l, ack, gap, ga, xmitq); - - /* If NACK, retransmit will now start at right position */ if (gap) l->stats.recv_nacks++; - - tipc_link_advance_backlog(l, xmitq); if (unlikely(!skb_queue_empty(&l->wakeupq))) link_prepare_wakeup(l); } @@ -2305,15 +2379,18 @@ int tipc_link_bc_nack_rcv(struct tipc_link *l, struct sk_buff *skb, return 0; } -void tipc_link_set_queue_limits(struct tipc_link *l, u32 win) +void tipc_link_set_queue_limits(struct tipc_link *l, u32 min_win, u32 max_win) { int max_bulk = TIPC_MAX_PUBL / (l->mtu / ITEM_SIZE); - l->window = win; - l->backlog[TIPC_LOW_IMPORTANCE].limit = max_t(u16, 50, win); - l->backlog[TIPC_MEDIUM_IMPORTANCE].limit = max_t(u16, 100, win * 2); - l->backlog[TIPC_HIGH_IMPORTANCE].limit = max_t(u16, 150, win * 3); - l->backlog[TIPC_CRITICAL_IMPORTANCE].limit = max_t(u16, 200, win * 4); + l->min_win = min_win; + l->ssthresh = max_win; + l->max_win = max_win; + l->window = min_win; + l->backlog[TIPC_LOW_IMPORTANCE].limit = min_win * 2; + l->backlog[TIPC_MEDIUM_IMPORTANCE].limit = min_win * 4; + l->backlog[TIPC_HIGH_IMPORTANCE].limit = min_win * 6; + l->backlog[TIPC_CRITICAL_IMPORTANCE].limit = min_win * 8; l->backlog[TIPC_SYSTEM_IMPORTANCE].limit = max_bulk; } @@ -2366,10 +2443,10 @@ int tipc_nl_parse_link_prop(struct nlattr *prop, struct nlattr *props[]) } if (props[TIPC_NLA_PROP_WIN]) { - u32 win; + u32 max_win; - win = nla_get_u32(props[TIPC_NLA_PROP_WIN]); - if ((win < TIPC_MIN_LINK_WIN) || (win > TIPC_MAX_LINK_WIN)) + max_win = nla_get_u32(props[TIPC_NLA_PROP_WIN]); + if (max_win < TIPC_DEF_LINK_WIN || max_win > TIPC_MAX_LINK_WIN) return -EINVAL; } @@ -2605,7 +2682,7 @@ int tipc_nl_add_bc_link(struct net *net, struct tipc_nl_msg *msg) prop = nla_nest_start_noflag(msg->skb, TIPC_NLA_LINK_PROP); if (!prop) goto attr_msg_full; - if (nla_put_u32(msg->skb, TIPC_NLA_PROP_WIN, bcl->window)) + if (nla_put_u32(msg->skb, TIPC_NLA_PROP_WIN, bcl->max_win)) goto prop_msg_full; if (nla_put_u32(msg->skb, TIPC_NLA_PROP_BROADCAST, bc_mode)) goto prop_msg_full; diff --git a/net/tipc/link.h b/net/tipc/link.h index c09e9d49d0a3..d3c1c3fc1659 100644 --- a/net/tipc/link.h +++ b/net/tipc/link.h @@ -73,7 +73,7 @@ enum { bool tipc_link_create(struct net *net, char *if_name, int bearer_id, int tolerance, char net_plane, u32 mtu, int priority, - int window, u32 session, u32 ownnode, + u32 min_win, u32 max_win, u32 session, u32 ownnode, u32 peer, u8 *peer_id, u16 peer_caps, struct tipc_link *bc_sndlink, struct tipc_link *bc_rcvlink, @@ -81,7 +81,7 @@ bool tipc_link_create(struct net *net, char *if_name, int bearer_id, struct sk_buff_head *namedq, struct tipc_link **link); bool tipc_link_bc_create(struct net *net, u32 ownnode, u32 peer, - int mtu, int window, u16 peer_caps, + int mtu, u32 min_win, u32 max_win, u16 peer_caps, struct sk_buff_head *inputq, struct sk_buff_head *namedq, struct tipc_link *bc_sndlink, @@ -115,7 +115,8 @@ char *tipc_link_name_ext(struct tipc_link *l, char *buf); u32 tipc_link_state(struct tipc_link *l); char tipc_link_plane(struct tipc_link *l); int tipc_link_prio(struct tipc_link *l); -int tipc_link_window(struct tipc_link *l); +int tipc_link_min_win(struct tipc_link *l); +int tipc_link_max_win(struct tipc_link *l); void tipc_link_update_caps(struct tipc_link *l, u16 capabilities); bool tipc_link_validate_msg(struct tipc_link *l, struct tipc_msg *hdr); unsigned long tipc_link_tolerance(struct tipc_link *l); @@ -124,7 +125,7 @@ void tipc_link_set_tolerance(struct tipc_link *l, u32 tol, void tipc_link_set_prio(struct tipc_link *l, u32 prio, struct sk_buff_head *xmitq); void tipc_link_set_abort_limit(struct tipc_link *l, u32 limit); -void tipc_link_set_queue_limits(struct tipc_link *l, u32 window); +void tipc_link_set_queue_limits(struct tipc_link *l, u32 min_win, u32 max_win); int __tipc_nl_add_link(struct net *net, struct tipc_nl_msg *msg, struct tipc_link *link, int nlflags); int tipc_nl_parse_link_prop(struct nlattr *prop, struct nlattr *props[]); diff --git a/net/tipc/net.c b/net/tipc/net.c index 2de3cec9929d..85400e4242de 100644 --- a/net/tipc/net.c +++ b/net/tipc/net.c @@ -302,3 +302,59 @@ int tipc_nl_net_set(struct sk_buff *skb, struct genl_info *info) return err; } + +static int __tipc_nl_addr_legacy_get(struct net *net, struct tipc_nl_msg *msg) +{ + struct tipc_net *tn = tipc_net(net); + struct nlattr *attrs; + void *hdr; + + hdr = genlmsg_put(msg->skb, msg->portid, msg->seq, &tipc_genl_family, + 0, TIPC_NL_ADDR_LEGACY_GET); + if (!hdr) + return -EMSGSIZE; + + attrs = nla_nest_start(msg->skb, TIPC_NLA_NET); + if (!attrs) + goto msg_full; + + if (tn->legacy_addr_format) + if (nla_put_flag(msg->skb, TIPC_NLA_NET_ADDR_LEGACY)) + goto attr_msg_full; + + nla_nest_end(msg->skb, attrs); + genlmsg_end(msg->skb, hdr); + + return 0; + +attr_msg_full: + nla_nest_cancel(msg->skb, attrs); +msg_full: + genlmsg_cancel(msg->skb, hdr); + + return -EMSGSIZE; +} + +int tipc_nl_net_addr_legacy_get(struct sk_buff *skb, struct genl_info *info) +{ + struct net *net = sock_net(skb->sk); + struct tipc_nl_msg msg; + struct sk_buff *rep; + int err; + + rep = nlmsg_new(NLMSG_GOODSIZE, GFP_KERNEL); + if (!rep) + return -ENOMEM; + + msg.skb = rep; + msg.portid = info->snd_portid; + msg.seq = info->snd_seq; + + err = __tipc_nl_addr_legacy_get(net, &msg); + if (err) { + nlmsg_free(msg.skb); + return err; + } + + return genlmsg_reply(msg.skb, info); +} diff --git a/net/tipc/net.h b/net/tipc/net.h index b7f2e364eb99..6740d97c706e 100644 --- a/net/tipc/net.h +++ b/net/tipc/net.h @@ -47,5 +47,6 @@ void tipc_net_stop(struct net *net); int tipc_nl_net_dump(struct sk_buff *skb, struct netlink_callback *cb); int tipc_nl_net_set(struct sk_buff *skb, struct genl_info *info); int __tipc_nl_net_set(struct sk_buff *skb, struct genl_info *info); +int tipc_nl_net_addr_legacy_get(struct sk_buff *skb, struct genl_info *info); #endif diff --git a/net/tipc/netlink.c b/net/tipc/netlink.c index e53231bd23b4..7c35094c20b8 100644 --- a/net/tipc/netlink.c +++ b/net/tipc/netlink.c @@ -83,6 +83,7 @@ const struct nla_policy tipc_nl_net_policy[TIPC_NLA_NET_MAX + 1] = { [TIPC_NLA_NET_ADDR] = { .type = NLA_U32 }, [TIPC_NLA_NET_NODEID] = { .type = NLA_U64 }, [TIPC_NLA_NET_NODEID_W1] = { .type = NLA_U64 }, + [TIPC_NLA_NET_ADDR_LEGACY] = { .type = NLA_FLAG } }; const struct nla_policy tipc_nl_link_policy[TIPC_NLA_LINK_MAX + 1] = { @@ -273,6 +274,11 @@ static const struct genl_ops tipc_genl_v2_ops[] = { .doit = tipc_nl_node_flush_key, }, #endif + { + .cmd = TIPC_NL_ADDR_LEGACY_GET, + .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, + .doit = tipc_nl_net_addr_legacy_get, + }, }; struct genl_family tipc_genl_family __ro_after_init = { diff --git a/net/tipc/node.c b/net/tipc/node.c index ab04e00cb95b..99b28b69fc17 100644 --- a/net/tipc/node.c +++ b/net/tipc/node.c @@ -1139,7 +1139,8 @@ void tipc_node_check_dest(struct net *net, u32 addr, snd_l = tipc_bc_sndlink(net); if (!tipc_link_bc_create(net, tipc_own_addr(net), addr, U16_MAX, - tipc_link_window(snd_l), + tipc_link_min_win(snd_l), + tipc_link_max_win(snd_l), n->capabilities, &n->bc_entry.inputq1, &n->bc_entry.namedq, snd_l, @@ -1233,7 +1234,7 @@ void tipc_node_check_dest(struct net *net, u32 addr, get_random_bytes(&session, sizeof(u16)); if (!tipc_link_create(net, if_name, b->identity, b->tolerance, b->net_plane, b->mtu, b->priority, - b->window, session, + b->min_win, b->max_win, session, tipc_own_addr(net), addr, peer_id, n->capabilities, tipc_bc_sndlink(n->net), n->bc_entry.link, @@ -2360,8 +2361,7 @@ int tipc_nl_node_set_link(struct sk_buff *skb, struct genl_info *info) if (attrs[TIPC_NLA_LINK_PROP]) { struct nlattr *props[TIPC_NLA_PROP_MAX + 1]; - err = tipc_nl_parse_link_prop(attrs[TIPC_NLA_LINK_PROP], - props); + err = tipc_nl_parse_link_prop(attrs[TIPC_NLA_LINK_PROP], props); if (err) { res = err; goto out; @@ -2380,10 +2380,12 @@ int tipc_nl_node_set_link(struct sk_buff *skb, struct genl_info *info) tipc_link_set_prio(link, prio, &xmitq); } if (props[TIPC_NLA_PROP_WIN]) { - u32 win; + u32 max_win; - win = nla_get_u32(props[TIPC_NLA_PROP_WIN]); - tipc_link_set_queue_limits(link, win); + max_win = nla_get_u32(props[TIPC_NLA_PROP_WIN]); + tipc_link_set_queue_limits(link, + tipc_link_min_win(link), + max_win); } } diff --git a/net/tipc/udp_media.c b/net/tipc/udp_media.c index ed113735c019..d6620ad53546 100644 --- a/net/tipc/udp_media.c +++ b/net/tipc/udp_media.c @@ -828,7 +828,8 @@ struct tipc_media udp_media_info = { .msg2addr = tipc_udp_msg2addr, .priority = TIPC_DEF_LINK_PRI, .tolerance = TIPC_DEF_LINK_TOL, - .window = TIPC_DEF_LINK_WIN, + .min_win = TIPC_DEF_LINK_WIN, + .max_win = TIPC_DEF_LINK_WIN, .mtu = TIPC_DEF_LINK_UDP_MTU, .type_id = TIPC_MEDIA_TYPE_UDP, .hwaddr_len = 0, diff --git a/net/tls/tls_device.c b/net/tls/tls_device.c index cd91ad812291..1ba5a92832bb 100644 --- a/net/tls/tls_device.c +++ b/net/tls/tls_device.c @@ -178,7 +178,7 @@ static void tls_icsk_clean_acked(struct sock *sk, u32 acked_seq) * socket and no in-flight SKBs associated with this * socket, so it is safe to free all the resources. */ -static void tls_device_sk_destruct(struct sock *sk) +void tls_device_sk_destruct(struct sock *sk) { struct tls_context *tls_ctx = tls_get_ctx(sk); struct tls_offload_context_tx *ctx = tls_offload_ctx_tx(tls_ctx); @@ -196,6 +196,7 @@ static void tls_device_sk_destruct(struct sock *sk) if (refcount_dec_and_test(&tls_ctx->refcount)) tls_device_queue_ctx_destruction(tls_ctx); } +EXPORT_SYMBOL_GPL(tls_device_sk_destruct); void tls_device_free_resources_tx(struct sock *sk) { @@ -903,7 +904,7 @@ static void tls_device_attach(struct tls_context *ctx, struct sock *sk, spin_unlock_irq(&tls_device_lock); ctx->sk_destruct = sk->sk_destruct; - sk->sk_destruct = tls_device_sk_destruct; + smp_store_release(&sk->sk_destruct, tls_device_sk_destruct); } } diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index 774babbee045..321af97c7bbe 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -676,6 +676,16 @@ static int unix_set_peek_off(struct sock *sk, int val) return 0; } +static void unix_show_fdinfo(struct seq_file *m, struct socket *sock) +{ + struct sock *sk = sock->sk; + struct unix_sock *u; + + if (sk) { + u = unix_sk(sock->sk); + seq_printf(m, "scm_fds: %u\n", READ_ONCE(u->scm_stat.nr_fds)); + } +} static const struct proto_ops unix_stream_ops = { .family = PF_UNIX, @@ -701,6 +711,7 @@ static const struct proto_ops unix_stream_ops = { .sendpage = unix_stream_sendpage, .splice_read = unix_stream_splice_read, .set_peek_off = unix_set_peek_off, + .show_fdinfo = unix_show_fdinfo, }; static const struct proto_ops unix_dgram_ops = { @@ -726,6 +737,7 @@ static const struct proto_ops unix_dgram_ops = { .mmap = sock_no_mmap, .sendpage = sock_no_sendpage, .set_peek_off = unix_set_peek_off, + .show_fdinfo = unix_show_fdinfo, }; static const struct proto_ops unix_seqpacket_ops = { @@ -751,6 +763,7 @@ static const struct proto_ops unix_seqpacket_ops = { .mmap = sock_no_mmap, .sendpage = sock_no_sendpage, .set_peek_off = unix_set_peek_off, + .show_fdinfo = unix_show_fdinfo, }; static struct proto unix_proto = { @@ -788,6 +801,7 @@ static struct sock *unix_create1(struct net *net, struct socket *sock, int kern) mutex_init(&u->bindlock); /* single task binding lock */ init_waitqueue_head(&u->peer_wait); init_waitqueue_func_entry(&u->peer_wake, unix_dgram_peer_wake_relay); + memset(&u->scm_stat, 0, sizeof(struct scm_stat)); unix_insert_socket(unix_sockets_unbound(sk), sk); out: if (sk == NULL) @@ -1572,6 +1586,28 @@ static bool unix_skb_scm_eq(struct sk_buff *skb, unix_secdata_eq(scm, skb); } +static void scm_stat_add(struct sock *sk, struct sk_buff *skb) +{ + struct scm_fp_list *fp = UNIXCB(skb).fp; + struct unix_sock *u = unix_sk(sk); + + lockdep_assert_held(&sk->sk_receive_queue.lock); + + if (unlikely(fp && fp->count)) + u->scm_stat.nr_fds += fp->count; +} + +static void scm_stat_del(struct sock *sk, struct sk_buff *skb) +{ + struct scm_fp_list *fp = UNIXCB(skb).fp; + struct unix_sock *u = unix_sk(sk); + + lockdep_assert_held(&sk->sk_receive_queue.lock); + + if (unlikely(fp && fp->count)) + u->scm_stat.nr_fds -= fp->count; +} + /* * Send AF_UNIX data. */ @@ -1757,7 +1793,10 @@ restart_locked: if (sock_flag(other, SOCK_RCVTSTAMP)) __net_timestamp(skb); maybe_add_creds(skb, sock, other); - skb_queue_tail(&other->sk_receive_queue, skb); + spin_lock(&other->sk_receive_queue.lock); + scm_stat_add(other, skb); + __skb_queue_tail(&other->sk_receive_queue, skb); + spin_unlock(&other->sk_receive_queue.lock); unix_state_unlock(other); other->sk_data_ready(other); sock_put(other); @@ -1859,7 +1898,10 @@ static int unix_stream_sendmsg(struct socket *sock, struct msghdr *msg, goto pipe_err_free; maybe_add_creds(skb, sock, other); - skb_queue_tail(&other->sk_receive_queue, skb); + spin_lock(&other->sk_receive_queue.lock); + scm_stat_add(other, skb); + __skb_queue_tail(&other->sk_receive_queue, skb); + spin_unlock(&other->sk_receive_queue.lock); unix_state_unlock(other); other->sk_data_ready(other); sent += size; @@ -2058,8 +2100,8 @@ static int unix_dgram_recvmsg(struct socket *sock, struct msghdr *msg, mutex_lock(&u->iolock); skip = sk_peek_offset(sk, flags); - skb = __skb_try_recv_datagram(sk, flags, NULL, &skip, &err, - &last); + skb = __skb_try_recv_datagram(sk, &sk->sk_receive_queue, flags, + scm_stat_del, &skip, &err, &last); if (skb) break; @@ -2068,7 +2110,8 @@ static int unix_dgram_recvmsg(struct socket *sock, struct msghdr *msg, if (err != -EAGAIN) break; } while (timeo && - !__skb_wait_for_more_packets(sk, &err, &timeo, last)); + !__skb_wait_for_more_packets(sk, &sk->sk_receive_queue, + &err, &timeo, last)); if (!skb) { /* implies iolock unlocked */ unix_state_lock(sk); @@ -2353,8 +2396,12 @@ unlock: sk_peek_offset_bwd(sk, chunk); - if (UNIXCB(skb).fp) + if (UNIXCB(skb).fp) { + spin_lock(&sk->sk_receive_queue.lock); + scm_stat_del(sk, skb); + spin_unlock(&sk->sk_receive_queue.lock); unix_detach_fds(&scm, skb); + } if (unix_skb_len(skb)) break; diff --git a/net/vmw_vsock/Kconfig b/net/vmw_vsock/Kconfig index 8abcb815af2d..56356d2980c8 100644 --- a/net/vmw_vsock/Kconfig +++ b/net/vmw_vsock/Kconfig @@ -26,6 +26,18 @@ config VSOCKETS_DIAG Enable this module so userspace applications can query open sockets. +config VSOCKETS_LOOPBACK + tristate "Virtual Sockets loopback transport" + depends on VSOCKETS + default y + select VIRTIO_VSOCKETS_COMMON + help + This module implements a loopback transport for Virtual Sockets, + using vmw_vsock_virtio_transport_common. + + To compile this driver as a module, choose M here: the module + will be called vsock_loopback. If unsure, say N. + config VMWARE_VMCI_VSOCKETS tristate "VMware VMCI transport for Virtual Sockets" depends on VSOCKETS && VMWARE_VMCI diff --git a/net/vmw_vsock/Makefile b/net/vmw_vsock/Makefile index 7c6f9a0b67b0..6a943ec95c4a 100644 --- a/net/vmw_vsock/Makefile +++ b/net/vmw_vsock/Makefile @@ -5,6 +5,7 @@ obj-$(CONFIG_VMWARE_VMCI_VSOCKETS) += vmw_vsock_vmci_transport.o obj-$(CONFIG_VIRTIO_VSOCKETS) += vmw_vsock_virtio_transport.o obj-$(CONFIG_VIRTIO_VSOCKETS_COMMON) += vmw_vsock_virtio_transport_common.o obj-$(CONFIG_HYPERV_VSOCKETS) += hv_sock.o +obj-$(CONFIG_VSOCKETS_LOOPBACK) += vsock_loopback.o vsock-y += af_vsock.o af_vsock_tap.o vsock_addr.o diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c index 74db4cd637a7..9c5b2a91baad 100644 --- a/net/vmw_vsock/af_vsock.c +++ b/net/vmw_vsock/af_vsock.c @@ -136,6 +136,8 @@ static const struct vsock_transport *transport_h2g; static const struct vsock_transport *transport_g2h; /* Transport used for DGRAM communication */ static const struct vsock_transport *transport_dgram; +/* Transport used for local communication */ +static const struct vsock_transport *transport_local; static DEFINE_MUTEX(vsock_register_mutex); /**** UTILS ****/ @@ -386,6 +388,21 @@ void vsock_enqueue_accept(struct sock *listener, struct sock *connected) } EXPORT_SYMBOL_GPL(vsock_enqueue_accept); +static bool vsock_use_local_transport(unsigned int remote_cid) +{ + if (!transport_local) + return false; + + if (remote_cid == VMADDR_CID_LOCAL) + return true; + + if (transport_g2h) { + return remote_cid == transport_g2h->get_local_cid(); + } else { + return remote_cid == VMADDR_CID_HOST; + } +} + static void vsock_deassign_transport(struct vsock_sock *vsk) { if (!vsk->transport) @@ -402,9 +419,9 @@ static void vsock_deassign_transport(struct vsock_sock *vsk) * (e.g. during the connect() or when a connection request on a listener * socket is received). * The vsk->remote_addr is used to decide which transport to use: + * - remote CID == VMADDR_CID_LOCAL or g2h->local_cid or VMADDR_CID_HOST if + * g2h is not loaded, will use local transport; * - remote CID <= VMADDR_CID_HOST will use guest->host transport; - * - remote CID == local_cid (guest->host transport) will use guest->host - * transport for loopback (host->guest transports don't support loopback); * - remote CID > VMADDR_CID_HOST will use host->guest transport; */ int vsock_assign_transport(struct vsock_sock *vsk, struct vsock_sock *psk) @@ -419,9 +436,9 @@ int vsock_assign_transport(struct vsock_sock *vsk, struct vsock_sock *psk) new_transport = transport_dgram; break; case SOCK_STREAM: - if (remote_cid <= VMADDR_CID_HOST || - (transport_g2h && - remote_cid == transport_g2h->get_local_cid())) + if (vsock_use_local_transport(remote_cid)) + new_transport = transport_local; + else if (remote_cid <= VMADDR_CID_HOST) new_transport = transport_g2h; else new_transport = transport_h2g; @@ -464,6 +481,9 @@ bool vsock_find_cid(unsigned int cid) if (transport_h2g && cid == VMADDR_CID_HOST) return true; + if (transport_local && cid == VMADDR_CID_LOCAL) + return true; + return false; } EXPORT_SYMBOL_GPL(vsock_find_cid); @@ -2137,7 +2157,7 @@ EXPORT_SYMBOL_GPL(vsock_core_get_transport); int vsock_core_register(const struct vsock_transport *t, int features) { - const struct vsock_transport *t_h2g, *t_g2h, *t_dgram; + const struct vsock_transport *t_h2g, *t_g2h, *t_dgram, *t_local; int err = mutex_lock_interruptible(&vsock_register_mutex); if (err) @@ -2146,6 +2166,7 @@ int vsock_core_register(const struct vsock_transport *t, int features) t_h2g = transport_h2g; t_g2h = transport_g2h; t_dgram = transport_dgram; + t_local = transport_local; if (features & VSOCK_TRANSPORT_F_H2G) { if (t_h2g) { @@ -2171,9 +2192,18 @@ int vsock_core_register(const struct vsock_transport *t, int features) t_dgram = t; } + if (features & VSOCK_TRANSPORT_F_LOCAL) { + if (t_local) { + err = -EBUSY; + goto err_busy; + } + t_local = t; + } + transport_h2g = t_h2g; transport_g2h = t_g2h; transport_dgram = t_dgram; + transport_local = t_local; err_busy: mutex_unlock(&vsock_register_mutex); @@ -2194,6 +2224,9 @@ void vsock_core_unregister(const struct vsock_transport *t) if (transport_dgram == t) transport_dgram = NULL; + if (transport_local == t) + transport_local = NULL; + mutex_unlock(&vsock_register_mutex); } EXPORT_SYMBOL_GPL(vsock_core_unregister); diff --git a/net/vmw_vsock/virtio_transport.c b/net/vmw_vsock/virtio_transport.c index 1458c5c8b64d..dfbaf6bd8b1c 100644 --- a/net/vmw_vsock/virtio_transport.c +++ b/net/vmw_vsock/virtio_transport.c @@ -44,10 +44,6 @@ struct virtio_vsock { spinlock_t send_pkt_list_lock; struct list_head send_pkt_list; - struct work_struct loopback_work; - spinlock_t loopback_list_lock; /* protects loopback_list */ - struct list_head loopback_list; - atomic_t queued_replies; /* The following fields are protected by rx_lock. vqs[VSOCK_VQ_RX] @@ -86,20 +82,6 @@ out_rcu: return ret; } -static int virtio_transport_send_pkt_loopback(struct virtio_vsock *vsock, - struct virtio_vsock_pkt *pkt) -{ - int len = pkt->len; - - spin_lock_bh(&vsock->loopback_list_lock); - list_add_tail(&pkt->list, &vsock->loopback_list); - spin_unlock_bh(&vsock->loopback_list_lock); - - queue_work(virtio_vsock_workqueue, &vsock->loopback_work); - - return len; -} - static void virtio_transport_send_pkt_work(struct work_struct *work) { @@ -194,7 +176,8 @@ virtio_transport_send_pkt(struct virtio_vsock_pkt *pkt) } if (le64_to_cpu(pkt->hdr.dst_cid) == vsock->guest_cid) { - len = virtio_transport_send_pkt_loopback(vsock, pkt); + virtio_transport_free_pkt(pkt); + len = -ENODEV; goto out_rcu; } @@ -502,33 +485,6 @@ 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 = @@ -633,13 +589,10 @@ static int virtio_vsock_probe(struct virtio_device *vdev) mutex_init(&vsock->event_lock); spin_lock_init(&vsock->send_pkt_list_lock); INIT_LIST_HEAD(&vsock->send_pkt_list); - spin_lock_init(&vsock->loopback_list_lock); - INIT_LIST_HEAD(&vsock->loopback_list); INIT_WORK(&vsock->rx_work, virtio_transport_rx_work); INIT_WORK(&vsock->tx_work, virtio_transport_tx_work); INIT_WORK(&vsock->event_work, virtio_transport_event_work); INIT_WORK(&vsock->send_pkt_work, virtio_transport_send_pkt_work); - INIT_WORK(&vsock->loopback_work, virtio_transport_loopback_work); mutex_lock(&vsock->tx_lock); vsock->tx_run = true; @@ -720,22 +673,12 @@ static void virtio_vsock_remove(struct virtio_device *vdev) } spin_unlock_bh(&vsock->send_pkt_list_lock); - spin_lock_bh(&vsock->loopback_list_lock); - while (!list_empty(&vsock->loopback_list)) { - pkt = list_first_entry(&vsock->loopback_list, - struct virtio_vsock_pkt, list); - list_del(&pkt->list); - virtio_transport_free_pkt(pkt); - } - spin_unlock_bh(&vsock->loopback_list_lock); - /* Delete virtqueues and flush outstanding callbacks if any */ vdev->config->del_vqs(vdev); /* Other works can be queued before 'config->del_vqs()', so we flush * all works before to free the vsock object to avoid use after free. */ - flush_work(&vsock->loopback_work); flush_work(&vsock->rx_work); flush_work(&vsock->tx_work); flush_work(&vsock->event_work); diff --git a/net/vmw_vsock/virtio_transport_common.c b/net/vmw_vsock/virtio_transport_common.c index 6abec3fc81d1..d9f0c9c5425a 100644 --- a/net/vmw_vsock/virtio_transport_common.c +++ b/net/vmw_vsock/virtio_transport_common.c @@ -11,9 +11,6 @@ #include <linux/sched/signal.h> #include <linux/ctype.h> #include <linux/list.h> -#include <linux/virtio.h> -#include <linux/virtio_ids.h> -#include <linux/virtio_config.h> #include <linux/virtio_vsock.h> #include <uapi/linux/vsockmon.h> diff --git a/net/vmw_vsock/vmci_transport.c b/net/vmw_vsock/vmci_transport.c index 644d32e43d23..4b8b1150a738 100644 --- a/net/vmw_vsock/vmci_transport.c +++ b/net/vmw_vsock/vmci_transport.c @@ -648,7 +648,7 @@ static int vmci_transport_recv_dgram_cb(void *data, struct vmci_datagram *dg) static bool vmci_transport_stream_allow(u32 cid, u32 port) { static const u32 non_socket_contexts[] = { - VMADDR_CID_RESERVED, + VMADDR_CID_LOCAL, }; int i; diff --git a/net/vmw_vsock/vsock_loopback.c b/net/vmw_vsock/vsock_loopback.c new file mode 100644 index 000000000000..a45f7ffca8c5 --- /dev/null +++ b/net/vmw_vsock/vsock_loopback.c @@ -0,0 +1,180 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* loopback transport for vsock using virtio_transport_common APIs + * + * Copyright (C) 2013-2019 Red Hat, Inc. + * Authors: Asias He <asias@redhat.com> + * Stefan Hajnoczi <stefanha@redhat.com> + * Stefano Garzarella <sgarzare@redhat.com> + * + */ +#include <linux/spinlock.h> +#include <linux/module.h> +#include <linux/list.h> +#include <linux/virtio_vsock.h> + +struct vsock_loopback { + struct workqueue_struct *workqueue; + + spinlock_t pkt_list_lock; /* protects pkt_list */ + struct list_head pkt_list; + struct work_struct pkt_work; +}; + +static struct vsock_loopback the_vsock_loopback; + +static u32 vsock_loopback_get_local_cid(void) +{ + return VMADDR_CID_LOCAL; +} + +static int vsock_loopback_send_pkt(struct virtio_vsock_pkt *pkt) +{ + struct vsock_loopback *vsock = &the_vsock_loopback; + int len = pkt->len; + + spin_lock_bh(&vsock->pkt_list_lock); + list_add_tail(&pkt->list, &vsock->pkt_list); + spin_unlock_bh(&vsock->pkt_list_lock); + + queue_work(vsock->workqueue, &vsock->pkt_work); + + return len; +} + +static int vsock_loopback_cancel_pkt(struct vsock_sock *vsk) +{ + struct vsock_loopback *vsock = &the_vsock_loopback; + struct virtio_vsock_pkt *pkt, *n; + LIST_HEAD(freeme); + + spin_lock_bh(&vsock->pkt_list_lock); + list_for_each_entry_safe(pkt, n, &vsock->pkt_list, list) { + if (pkt->vsk != vsk) + continue; + list_move(&pkt->list, &freeme); + } + spin_unlock_bh(&vsock->pkt_list_lock); + + list_for_each_entry_safe(pkt, n, &freeme, list) { + list_del(&pkt->list); + virtio_transport_free_pkt(pkt); + } + + return 0; +} + +static struct virtio_transport loopback_transport = { + .transport = { + .module = THIS_MODULE, + + .get_local_cid = vsock_loopback_get_local_cid, + + .init = virtio_transport_do_socket_init, + .destruct = virtio_transport_destruct, + .release = virtio_transport_release, + .connect = virtio_transport_connect, + .shutdown = virtio_transport_shutdown, + .cancel_pkt = vsock_loopback_cancel_pkt, + + .dgram_bind = virtio_transport_dgram_bind, + .dgram_dequeue = virtio_transport_dgram_dequeue, + .dgram_enqueue = virtio_transport_dgram_enqueue, + .dgram_allow = virtio_transport_dgram_allow, + + .stream_dequeue = virtio_transport_stream_dequeue, + .stream_enqueue = virtio_transport_stream_enqueue, + .stream_has_data = virtio_transport_stream_has_data, + .stream_has_space = virtio_transport_stream_has_space, + .stream_rcvhiwat = virtio_transport_stream_rcvhiwat, + .stream_is_active = virtio_transport_stream_is_active, + .stream_allow = virtio_transport_stream_allow, + + .notify_poll_in = virtio_transport_notify_poll_in, + .notify_poll_out = virtio_transport_notify_poll_out, + .notify_recv_init = virtio_transport_notify_recv_init, + .notify_recv_pre_block = virtio_transport_notify_recv_pre_block, + .notify_recv_pre_dequeue = virtio_transport_notify_recv_pre_dequeue, + .notify_recv_post_dequeue = virtio_transport_notify_recv_post_dequeue, + .notify_send_init = virtio_transport_notify_send_init, + .notify_send_pre_block = virtio_transport_notify_send_pre_block, + .notify_send_pre_enqueue = virtio_transport_notify_send_pre_enqueue, + .notify_send_post_enqueue = virtio_transport_notify_send_post_enqueue, + .notify_buffer_size = virtio_transport_notify_buffer_size, + }, + + .send_pkt = vsock_loopback_send_pkt, +}; + +static void vsock_loopback_work(struct work_struct *work) +{ + struct vsock_loopback *vsock = + container_of(work, struct vsock_loopback, pkt_work); + LIST_HEAD(pkts); + + spin_lock_bh(&vsock->pkt_list_lock); + list_splice_init(&vsock->pkt_list, &pkts); + spin_unlock_bh(&vsock->pkt_list_lock); + + 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_deliver_tap_pkt(pkt); + virtio_transport_recv_pkt(&loopback_transport, pkt); + } +} + +static int __init vsock_loopback_init(void) +{ + struct vsock_loopback *vsock = &the_vsock_loopback; + int ret; + + vsock->workqueue = alloc_workqueue("vsock-loopback", 0, 0); + if (!vsock->workqueue) + return -ENOMEM; + + spin_lock_init(&vsock->pkt_list_lock); + INIT_LIST_HEAD(&vsock->pkt_list); + INIT_WORK(&vsock->pkt_work, vsock_loopback_work); + + ret = vsock_core_register(&loopback_transport.transport, + VSOCK_TRANSPORT_F_LOCAL); + if (ret) + goto out_wq; + + return 0; + +out_wq: + destroy_workqueue(vsock->workqueue); + return ret; +} + +static void __exit vsock_loopback_exit(void) +{ + struct vsock_loopback *vsock = &the_vsock_loopback; + struct virtio_vsock_pkt *pkt; + + vsock_core_unregister(&loopback_transport.transport); + + flush_work(&vsock->pkt_work); + + spin_lock_bh(&vsock->pkt_list_lock); + while (!list_empty(&vsock->pkt_list)) { + pkt = list_first_entry(&vsock->pkt_list, + struct virtio_vsock_pkt, list); + list_del(&pkt->list); + virtio_transport_free_pkt(pkt); + } + spin_unlock_bh(&vsock->pkt_list_lock); + + destroy_workqueue(vsock->workqueue); +} + +module_init(vsock_loopback_init); +module_exit(vsock_loopback_exit); +MODULE_LICENSE("GPL v2"); +MODULE_AUTHOR("Stefano Garzarella <sgarzare@redhat.com>"); +MODULE_DESCRIPTION("loopback transport for vsock"); +MODULE_ALIAS_NETPROTO(PF_VSOCK); diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 1e97ac5435b2..123b8d720a59 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -12901,8 +12901,7 @@ static int nl80211_vendor_check_policy(const struct wiphy_vendor_command *vcmd, return -EINVAL; } - return nl80211_validate_nested(attr, vcmd->maxattr, vcmd->policy, - extack); + return nla_validate_nested(attr, vcmd->maxattr, vcmd->policy, extack); } static int nl80211_vendor_cmd(struct sk_buff *skb, struct genl_info *info) diff --git a/net/xdp/xdp_umem.c b/net/xdp/xdp_umem.c index 3049af269fbf..f93e917e0929 100644 --- a/net/xdp/xdp_umem.c +++ b/net/xdp/xdp_umem.c @@ -249,7 +249,7 @@ static void xdp_umem_release(struct xdp_umem *umem) xdp_umem_unmap_pages(umem); xdp_umem_unpin_pages(umem); - kfree(umem->pages); + kvfree(umem->pages); umem->pages = NULL; xdp_umem_unaccount_pages(umem); @@ -409,7 +409,8 @@ static int xdp_umem_reg(struct xdp_umem *umem, struct xdp_umem_reg *mr) if (err) goto out_account; - umem->pages = kcalloc(umem->npgs, sizeof(*umem->pages), GFP_KERNEL); + umem->pages = kvcalloc(umem->npgs, sizeof(*umem->pages), + GFP_KERNEL_ACCOUNT); if (!umem->pages) { err = -ENOMEM; goto out_pin; @@ -419,7 +420,7 @@ static int xdp_umem_reg(struct xdp_umem *umem, struct xdp_umem_reg *mr) if (!err) return 0; - kfree(umem->pages); + kvfree(umem->pages); out_pin: xdp_umem_unpin_pages(umem); diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c index 328f661b83b2..df600487a68d 100644 --- a/net/xdp/xsk.c +++ b/net/xdp/xsk.c @@ -31,6 +31,8 @@ #define TX_BATCH_SIZE 16 +static DEFINE_PER_CPU(struct list_head, xskmap_flush_list); + bool xsk_is_setup_for_bpf_map(struct xdp_sock *xs) { return READ_ONCE(xs->rx) && READ_ONCE(xs->umem) && @@ -39,21 +41,21 @@ bool xsk_is_setup_for_bpf_map(struct xdp_sock *xs) bool xsk_umem_has_addrs(struct xdp_umem *umem, u32 cnt) { - return xskq_has_addrs(umem->fq, cnt); + return xskq_cons_has_entries(umem->fq, cnt); } EXPORT_SYMBOL(xsk_umem_has_addrs); -u64 *xsk_umem_peek_addr(struct xdp_umem *umem, u64 *addr) +bool xsk_umem_peek_addr(struct xdp_umem *umem, u64 *addr) { - return xskq_peek_addr(umem->fq, addr, umem); + return xskq_cons_peek_addr(umem->fq, addr, umem); } EXPORT_SYMBOL(xsk_umem_peek_addr); -void xsk_umem_discard_addr(struct xdp_umem *umem) +void xsk_umem_release_addr(struct xdp_umem *umem) { - xskq_discard_addr(umem->fq); + xskq_cons_release(umem->fq); } -EXPORT_SYMBOL(xsk_umem_discard_addr); +EXPORT_SYMBOL(xsk_umem_release_addr); void xsk_set_rx_need_wakeup(struct xdp_umem *umem) { @@ -124,7 +126,7 @@ static void __xsk_rcv_memcpy(struct xdp_umem *umem, u64 addr, void *from_buf, void *to_buf = xdp_umem_get_data(umem, addr); addr = xsk_umem_add_offset_to_addr(addr); - if (xskq_crosses_non_contig_pg(umem, addr, len + metalen)) { + if (xskq_cons_crosses_non_contig_pg(umem, addr, len + metalen)) { void *next_pg_addr = umem->pages[(addr >> PAGE_SHIFT) + 1].addr; u64 page_start = addr & ~(PAGE_SIZE - 1); u64 first_len = PAGE_SIZE - (addr - page_start); @@ -146,7 +148,7 @@ static int __xsk_rcv(struct xdp_sock *xs, struct xdp_buff *xdp, u32 len) u32 metalen; int err; - if (!xskq_peek_addr(xs->umem->fq, &addr, xs->umem) || + if (!xskq_cons_peek_addr(xs->umem->fq, &addr, xs->umem) || len > xs->umem->chunk_size_nohr - XDP_PACKET_HEADROOM) { xs->rx_dropped++; return -ENOSPC; @@ -165,9 +167,9 @@ static int __xsk_rcv(struct xdp_sock *xs, struct xdp_buff *xdp, u32 len) offset += metalen; addr = xsk_umem_adjust_offset(xs->umem, addr, offset); - err = xskq_produce_batch_desc(xs->rx, addr, len); + err = xskq_prod_reserve_desc(xs->rx, addr, len); if (!err) { - xskq_discard_addr(xs->umem->fq); + xskq_cons_release(xs->umem->fq); xdp_return_buff(xdp); return 0; } @@ -178,7 +180,7 @@ static int __xsk_rcv(struct xdp_sock *xs, struct xdp_buff *xdp, u32 len) static int __xsk_rcv_zc(struct xdp_sock *xs, struct xdp_buff *xdp, u32 len) { - int err = xskq_produce_batch_desc(xs->rx, (u64)xdp->handle, len); + int err = xskq_prod_reserve_desc(xs->rx, xdp->handle, len); if (err) xs->rx_dropped++; @@ -214,8 +216,8 @@ static int xsk_rcv(struct xdp_sock *xs, struct xdp_buff *xdp) static void xsk_flush(struct xdp_sock *xs) { - xskq_produce_flush_desc(xs->rx); - xs->sk.sk_data_ready(&xs->sk); + xskq_prod_submit(xs->rx); + sock_def_readable(&xs->sk); } int xsk_generic_rcv(struct xdp_sock *xs, struct xdp_buff *xdp) @@ -234,7 +236,7 @@ int xsk_generic_rcv(struct xdp_sock *xs, struct xdp_buff *xdp) goto out_unlock; } - if (!xskq_peek_addr(xs->umem->fq, &addr, xs->umem) || + if (!xskq_cons_peek_addr(xs->umem->fq, &addr, xs->umem) || len > xs->umem->chunk_size_nohr - XDP_PACKET_HEADROOM) { err = -ENOSPC; goto out_drop; @@ -245,12 +247,12 @@ int xsk_generic_rcv(struct xdp_sock *xs, struct xdp_buff *xdp) memcpy(buffer, xdp->data_meta, len + metalen); addr = xsk_umem_adjust_offset(xs->umem, addr, metalen); - err = xskq_produce_batch_desc(xs->rx, addr, len); + err = xskq_prod_reserve_desc(xs->rx, addr, len); if (err) goto out_drop; - xskq_discard_addr(xs->umem->fq); - xskq_produce_flush_desc(xs->rx); + xskq_cons_release(xs->umem->fq); + xskq_prod_submit(xs->rx); spin_unlock_bh(&xs->rx_lock); @@ -264,11 +266,9 @@ out_unlock: return err; } -int __xsk_map_redirect(struct bpf_map *map, struct xdp_buff *xdp, - struct xdp_sock *xs) +int __xsk_map_redirect(struct xdp_sock *xs, struct xdp_buff *xdp) { - struct xsk_map *m = container_of(map, struct xsk_map, map); - struct list_head *flush_list = this_cpu_ptr(m->flush_list); + struct list_head *flush_list = this_cpu_ptr(&xskmap_flush_list); int err; err = xsk_rcv(xs, xdp); @@ -281,10 +281,9 @@ int __xsk_map_redirect(struct bpf_map *map, struct xdp_buff *xdp, return 0; } -void __xsk_map_flush(struct bpf_map *map) +void __xsk_map_flush(void) { - struct xsk_map *m = container_of(map, struct xsk_map, map); - struct list_head *flush_list = this_cpu_ptr(m->flush_list); + struct list_head *flush_list = this_cpu_ptr(&xskmap_flush_list); struct xdp_sock *xs, *tmp; list_for_each_entry_safe(xs, tmp, flush_list, flush_node) { @@ -295,7 +294,7 @@ void __xsk_map_flush(struct bpf_map *map) void xsk_umem_complete_tx(struct xdp_umem *umem, u32 nb_entries) { - xskq_produce_flush_addr_n(umem->cq, nb_entries); + xskq_prod_submit_n(umem->cq, nb_entries); } EXPORT_SYMBOL(xsk_umem_complete_tx); @@ -317,13 +316,18 @@ bool xsk_umem_consume_tx(struct xdp_umem *umem, struct xdp_desc *desc) rcu_read_lock(); list_for_each_entry_rcu(xs, &umem->xsk_list, list) { - if (!xskq_peek_desc(xs->tx, desc, umem)) + if (!xskq_cons_peek_desc(xs->tx, desc, umem)) continue; - if (xskq_produce_addr_lazy(umem->cq, desc->addr)) + /* This is the backpreassure mechanism for the Tx path. + * Reserve space in the completion queue and only proceed + * if there is space in it. This avoids having to implement + * any buffering in the Tx path. + */ + if (xskq_prod_reserve_addr(umem->cq, desc->addr)) goto out; - xskq_discard_desc(xs->tx); + xskq_cons_release(xs->tx); rcu_read_unlock(); return true; } @@ -358,7 +362,7 @@ static void xsk_destruct_skb(struct sk_buff *skb) unsigned long flags; spin_lock_irqsave(&xs->tx_completion_lock, flags); - WARN_ON_ONCE(xskq_produce_addr(xs->umem->cq, addr)); + xskq_prod_submit_addr(xs->umem->cq, addr); spin_unlock_irqrestore(&xs->tx_completion_lock, flags); sock_wfree(skb); @@ -378,7 +382,7 @@ static int xsk_generic_xmit(struct sock *sk) if (xs->queue_id >= xs->dev->real_num_tx_queues) goto out; - while (xskq_peek_desc(xs->tx, &desc, xs->umem)) { + while (xskq_cons_peek_desc(xs->tx, &desc, xs->umem)) { char *buffer; u64 addr; u32 len; @@ -399,7 +403,12 @@ static int xsk_generic_xmit(struct sock *sk) addr = desc.addr; buffer = xdp_umem_get_data(xs->umem, addr); err = skb_store_bits(skb, 0, buffer, len); - if (unlikely(err) || xskq_reserve_addr(xs->umem->cq)) { + /* This is the backpreassure mechanism for the Tx path. + * Reserve space in the completion queue and only proceed + * if there is space in it. This avoids having to implement + * any buffering in the Tx path. + */ + if (unlikely(err) || xskq_prod_reserve(xs->umem->cq)) { kfree_skb(skb); goto out; } @@ -411,7 +420,7 @@ static int xsk_generic_xmit(struct sock *sk) skb->destructor = xsk_destruct_skb; err = dev_direct_xmit(skb, xs->queue_id); - xskq_discard_desc(xs->tx); + xskq_cons_release(xs->tx); /* Ignore NET_XMIT_CN as packet might have been sent */ if (err == NET_XMIT_DROP || err == NETDEV_TX_BUSY) { /* SKB completed but not sent */ @@ -477,9 +486,9 @@ static __poll_t xsk_poll(struct file *file, struct socket *sock, __xsk_sendmsg(sk); } - if (xs->rx && !xskq_empty_desc(xs->rx)) + if (xs->rx && !xskq_prod_is_empty(xs->rx)) mask |= EPOLLIN | EPOLLRDNORM; - if (xs->tx && !xskq_full_desc(xs->tx)) + if (xs->tx && !xskq_cons_is_full(xs->tx)) mask |= EPOLLOUT | EPOLLWRNORM; return mask; @@ -1183,7 +1192,7 @@ static struct pernet_operations xsk_net_ops = { static int __init xsk_init(void) { - int err; + int err, cpu; err = proto_register(&xsk_proto, 0 /* no slab */); if (err) @@ -1201,6 +1210,8 @@ static int __init xsk_init(void) if (err) goto out_pernet; + for_each_possible_cpu(cpu) + INIT_LIST_HEAD(&per_cpu(xskmap_flush_list, cpu)); return 0; out_pernet: diff --git a/net/xdp/xsk_queue.c b/net/xdp/xsk_queue.c index b66504592d9b..c90e9c1e3c63 100644 --- a/net/xdp/xsk_queue.c +++ b/net/xdp/xsk_queue.c @@ -18,14 +18,14 @@ void xskq_set_umem(struct xsk_queue *q, u64 size, u64 chunk_mask) q->chunk_mask = chunk_mask; } -static u32 xskq_umem_get_ring_size(struct xsk_queue *q) +static size_t xskq_get_ring_size(struct xsk_queue *q, bool umem_queue) { - return sizeof(struct xdp_umem_ring) + q->nentries * sizeof(u64); -} + struct xdp_umem_ring *umem_ring; + struct xdp_rxtx_ring *rxtx_ring; -static u32 xskq_rxtx_get_ring_size(struct xsk_queue *q) -{ - return sizeof(struct xdp_ring) + q->nentries * sizeof(struct xdp_desc); + if (umem_queue) + return struct_size(umem_ring, desc, q->nentries); + return struct_size(rxtx_ring, desc, q->nentries); } struct xsk_queue *xskq_create(u32 nentries, bool umem_queue) @@ -43,8 +43,7 @@ struct xsk_queue *xskq_create(u32 nentries, bool umem_queue) gfp_flags = GFP_KERNEL | __GFP_ZERO | __GFP_NOWARN | __GFP_COMP | __GFP_NORETRY; - size = umem_queue ? xskq_umem_get_ring_size(q) : - xskq_rxtx_get_ring_size(q); + size = xskq_get_ring_size(q, umem_queue); q->ring = (struct xdp_ring *)__get_free_pages(gfp_flags, get_order(size)); diff --git a/net/xdp/xsk_queue.h b/net/xdp/xsk_queue.h index eddae4688862..bec2af11853a 100644 --- a/net/xdp/xsk_queue.h +++ b/net/xdp/xsk_queue.h @@ -10,9 +10,6 @@ #include <linux/if_xdp.h> #include <net/xdp_sock.h> -#define RX_BATCH_SIZE 16 -#define LAZY_UPDATE_THRESHOLD 128 - struct xdp_ring { u32 producer ____cacheline_aligned_in_smp; u32 consumer ____cacheline_aligned_in_smp; @@ -36,10 +33,8 @@ struct xsk_queue { u64 size; u32 ring_mask; u32 nentries; - u32 prod_head; - u32 prod_tail; - u32 cons_head; - u32 cons_tail; + u32 cached_prod; + u32 cached_cons; struct xdp_ring *ring; u64 invalid_descs; }; @@ -86,56 +81,31 @@ struct xsk_queue { * now and again after circling through the ring. */ -/* Common functions operating for both RXTX and umem queues */ - -static inline u64 xskq_nb_invalid_descs(struct xsk_queue *q) -{ - return q ? q->invalid_descs : 0; -} - -static inline u32 xskq_nb_avail(struct xsk_queue *q, u32 dcnt) -{ - u32 entries = q->prod_tail - q->cons_tail; - - if (entries == 0) { - /* Refresh the local pointer */ - q->prod_tail = READ_ONCE(q->ring->producer); - entries = q->prod_tail - q->cons_tail; - } - - return (entries > dcnt) ? dcnt : entries; -} - -static inline u32 xskq_nb_free(struct xsk_queue *q, u32 producer, u32 dcnt) -{ - u32 free_entries = q->nentries - (producer - q->cons_tail); - - if (free_entries >= dcnt) - return free_entries; - - /* Refresh the local tail pointer */ - q->cons_tail = READ_ONCE(q->ring->consumer); - return q->nentries - (producer - q->cons_tail); -} - -static inline bool xskq_has_addrs(struct xsk_queue *q, u32 cnt) -{ - u32 entries = q->prod_tail - q->cons_tail; - - if (entries >= cnt) - return true; - - /* Refresh the local pointer. */ - q->prod_tail = READ_ONCE(q->ring->producer); - entries = q->prod_tail - q->cons_tail; - - return entries >= cnt; -} +/* The operations on the rings are the following: + * + * producer consumer + * + * RESERVE entries PEEK in the ring for entries + * WRITE data into the ring READ data from the ring + * SUBMIT entries RELEASE entries + * + * The producer reserves one or more entries in the ring. It can then + * fill in these entries and finally submit them so that they can be + * seen and read by the consumer. + * + * The consumer peeks into the ring to see if the producer has written + * any new entries. If so, the producer can then read these entries + * and when it is done reading them release them back to the producer + * so that the producer can use these slots to fill in new entries. + * + * The function names below reflect these operations. + */ -/* UMEM queue */ +/* Functions that read and validate content from consumer rings. */ -static inline bool xskq_crosses_non_contig_pg(struct xdp_umem *umem, u64 addr, - u64 length) +static inline bool xskq_cons_crosses_non_contig_pg(struct xdp_umem *umem, + u64 addr, + u64 length) { bool cross_pg = (addr & (PAGE_SIZE - 1)) + length > PAGE_SIZE; bool next_pg_contig = @@ -145,9 +115,16 @@ static inline bool xskq_crosses_non_contig_pg(struct xdp_umem *umem, u64 addr, return cross_pg && !next_pg_contig; } -static inline bool xskq_is_valid_addr(struct xsk_queue *q, u64 addr) +static inline bool xskq_cons_is_valid_unaligned(struct xsk_queue *q, + u64 addr, + u64 length, + struct xdp_umem *umem) { - if (addr >= q->size) { + u64 base_addr = xsk_umem_extract_addr(addr); + + addr = xsk_umem_add_offset_to_addr(addr); + if (base_addr >= q->size || addr >= q->size || + xskq_cons_crosses_non_contig_pg(umem, addr, length)) { q->invalid_descs++; return false; } @@ -155,15 +132,9 @@ static inline bool xskq_is_valid_addr(struct xsk_queue *q, u64 addr) return true; } -static inline bool xskq_is_valid_addr_unaligned(struct xsk_queue *q, u64 addr, - u64 length, - struct xdp_umem *umem) +static inline bool xskq_cons_is_valid_addr(struct xsk_queue *q, u64 addr) { - u64 base_addr = xsk_umem_extract_addr(addr); - - addr = xsk_umem_add_offset_to_addr(addr); - if (base_addr >= q->size || addr >= q->size || - xskq_crosses_non_contig_pg(umem, addr, length)) { + if (addr >= q->size) { q->invalid_descs++; return false; } @@ -171,204 +142,240 @@ static inline bool xskq_is_valid_addr_unaligned(struct xsk_queue *q, u64 addr, return true; } -static inline u64 *xskq_validate_addr(struct xsk_queue *q, u64 *addr, - struct xdp_umem *umem) +static inline bool xskq_cons_read_addr(struct xsk_queue *q, u64 *addr, + struct xdp_umem *umem) { - while (q->cons_tail != q->cons_head) { - struct xdp_umem_ring *ring = (struct xdp_umem_ring *)q->ring; - unsigned int idx = q->cons_tail & q->ring_mask; + struct xdp_umem_ring *ring = (struct xdp_umem_ring *)q->ring; - *addr = READ_ONCE(ring->desc[idx]) & q->chunk_mask; + while (q->cached_cons != q->cached_prod) { + u32 idx = q->cached_cons & q->ring_mask; + + *addr = ring->desc[idx] & q->chunk_mask; if (umem->flags & XDP_UMEM_UNALIGNED_CHUNK_FLAG) { - if (xskq_is_valid_addr_unaligned(q, *addr, + if (xskq_cons_is_valid_unaligned(q, *addr, umem->chunk_size_nohr, umem)) - return addr; + return true; goto out; } - if (xskq_is_valid_addr(q, *addr)) - return addr; + if (xskq_cons_is_valid_addr(q, *addr)) + return true; out: - q->cons_tail++; + q->cached_cons++; } - return NULL; + return false; } -static inline u64 *xskq_peek_addr(struct xsk_queue *q, u64 *addr, - struct xdp_umem *umem) +static inline bool xskq_cons_is_valid_desc(struct xsk_queue *q, + struct xdp_desc *d, + struct xdp_umem *umem) { - if (q->cons_tail == q->cons_head) { - smp_mb(); /* D, matches A */ - WRITE_ONCE(q->ring->consumer, q->cons_tail); - q->cons_head = q->cons_tail + xskq_nb_avail(q, RX_BATCH_SIZE); + if (umem->flags & XDP_UMEM_UNALIGNED_CHUNK_FLAG) { + if (!xskq_cons_is_valid_unaligned(q, d->addr, d->len, umem)) + return false; + + if (d->len > umem->chunk_size_nohr || d->options) { + q->invalid_descs++; + return false; + } - /* Order consumer and data */ - smp_rmb(); + return true; } - return xskq_validate_addr(q, addr, umem); -} + if (!xskq_cons_is_valid_addr(q, d->addr)) + return false; -static inline void xskq_discard_addr(struct xsk_queue *q) -{ - q->cons_tail++; + if (((d->addr + d->len) & q->chunk_mask) != (d->addr & q->chunk_mask) || + d->options) { + q->invalid_descs++; + return false; + } + + return true; } -static inline int xskq_produce_addr(struct xsk_queue *q, u64 addr) +static inline bool xskq_cons_read_desc(struct xsk_queue *q, + struct xdp_desc *desc, + struct xdp_umem *umem) { - struct xdp_umem_ring *ring = (struct xdp_umem_ring *)q->ring; - - if (xskq_nb_free(q, q->prod_tail, 1) == 0) - return -ENOSPC; + while (q->cached_cons != q->cached_prod) { + struct xdp_rxtx_ring *ring = (struct xdp_rxtx_ring *)q->ring; + u32 idx = q->cached_cons & q->ring_mask; - /* A, matches D */ - ring->desc[q->prod_tail++ & q->ring_mask] = addr; + *desc = ring->desc[idx]; + if (xskq_cons_is_valid_desc(q, desc, umem)) + return true; - /* Order producer and data */ - smp_wmb(); /* B, matches C */ + q->cached_cons++; + } - WRITE_ONCE(q->ring->producer, q->prod_tail); - return 0; + return false; } -static inline int xskq_produce_addr_lazy(struct xsk_queue *q, u64 addr) +/* Functions for consumers */ + +static inline void __xskq_cons_release(struct xsk_queue *q) { - struct xdp_umem_ring *ring = (struct xdp_umem_ring *)q->ring; + smp_mb(); /* D, matches A */ + WRITE_ONCE(q->ring->consumer, q->cached_cons); +} - if (xskq_nb_free(q, q->prod_head, LAZY_UPDATE_THRESHOLD) == 0) - return -ENOSPC; +static inline void __xskq_cons_peek(struct xsk_queue *q) +{ + /* Refresh the local pointer */ + q->cached_prod = READ_ONCE(q->ring->producer); + smp_rmb(); /* C, matches B */ +} - /* A, matches D */ - ring->desc[q->prod_head++ & q->ring_mask] = addr; - return 0; +static inline void xskq_cons_get_entries(struct xsk_queue *q) +{ + __xskq_cons_release(q); + __xskq_cons_peek(q); } -static inline void xskq_produce_flush_addr_n(struct xsk_queue *q, - u32 nb_entries) +static inline bool xskq_cons_has_entries(struct xsk_queue *q, u32 cnt) { - /* Order producer and data */ - smp_wmb(); /* B, matches C */ + u32 entries = q->cached_prod - q->cached_cons; - q->prod_tail += nb_entries; - WRITE_ONCE(q->ring->producer, q->prod_tail); + if (entries >= cnt) + return true; + + __xskq_cons_peek(q); + entries = q->cached_prod - q->cached_cons; + + return entries >= cnt; } -static inline int xskq_reserve_addr(struct xsk_queue *q) +static inline bool xskq_cons_peek_addr(struct xsk_queue *q, u64 *addr, + struct xdp_umem *umem) { - if (xskq_nb_free(q, q->prod_head, 1) == 0) - return -ENOSPC; + if (q->cached_prod == q->cached_cons) + xskq_cons_get_entries(q); + return xskq_cons_read_addr(q, addr, umem); +} - /* A, matches D */ - q->prod_head++; - return 0; +static inline bool xskq_cons_peek_desc(struct xsk_queue *q, + struct xdp_desc *desc, + struct xdp_umem *umem) +{ + if (q->cached_prod == q->cached_cons) + xskq_cons_get_entries(q); + return xskq_cons_read_desc(q, desc, umem); } -/* Rx/Tx queue */ +static inline void xskq_cons_release(struct xsk_queue *q) +{ + /* To improve performance, only update local state here. + * Reflect this to global state when we get new entries + * from the ring in xskq_cons_get_entries(). + */ + q->cached_cons++; +} -static inline bool xskq_is_valid_desc(struct xsk_queue *q, struct xdp_desc *d, - struct xdp_umem *umem) +static inline bool xskq_cons_is_full(struct xsk_queue *q) { - if (umem->flags & XDP_UMEM_UNALIGNED_CHUNK_FLAG) { - if (!xskq_is_valid_addr_unaligned(q, d->addr, d->len, umem)) - return false; + /* No barriers needed since data is not accessed */ + return READ_ONCE(q->ring->producer) - READ_ONCE(q->ring->consumer) == + q->nentries; +} - if (d->len > umem->chunk_size_nohr || d->options) { - q->invalid_descs++; - return false; - } +/* Functions for producers */ - return true; - } +static inline bool xskq_prod_is_full(struct xsk_queue *q) +{ + u32 free_entries = q->nentries - (q->cached_prod - q->cached_cons); - if (!xskq_is_valid_addr(q, d->addr)) + if (free_entries) return false; - if (((d->addr + d->len) & q->chunk_mask) != (d->addr & q->chunk_mask) || - d->options) { - q->invalid_descs++; - return false; - } + /* Refresh the local tail pointer */ + q->cached_cons = READ_ONCE(q->ring->consumer); + free_entries = q->nentries - (q->cached_prod - q->cached_cons); - return true; + return !free_entries; } -static inline struct xdp_desc *xskq_validate_desc(struct xsk_queue *q, - struct xdp_desc *desc, - struct xdp_umem *umem) +static inline int xskq_prod_reserve(struct xsk_queue *q) { - while (q->cons_tail != q->cons_head) { - struct xdp_rxtx_ring *ring = (struct xdp_rxtx_ring *)q->ring; - unsigned int idx = q->cons_tail & q->ring_mask; - - *desc = READ_ONCE(ring->desc[idx]); - if (xskq_is_valid_desc(q, desc, umem)) - return desc; - - q->cons_tail++; - } + if (xskq_prod_is_full(q)) + return -ENOSPC; - return NULL; + /* A, matches D */ + q->cached_prod++; + return 0; } -static inline struct xdp_desc *xskq_peek_desc(struct xsk_queue *q, - struct xdp_desc *desc, - struct xdp_umem *umem) +static inline int xskq_prod_reserve_addr(struct xsk_queue *q, u64 addr) { - if (q->cons_tail == q->cons_head) { - smp_mb(); /* D, matches A */ - WRITE_ONCE(q->ring->consumer, q->cons_tail); - q->cons_head = q->cons_tail + xskq_nb_avail(q, RX_BATCH_SIZE); - - /* Order consumer and data */ - smp_rmb(); /* C, matches B */ - } + struct xdp_umem_ring *ring = (struct xdp_umem_ring *)q->ring; - return xskq_validate_desc(q, desc, umem); -} + if (xskq_prod_is_full(q)) + return -ENOSPC; -static inline void xskq_discard_desc(struct xsk_queue *q) -{ - q->cons_tail++; + /* A, matches D */ + ring->desc[q->cached_prod++ & q->ring_mask] = addr; + return 0; } -static inline int xskq_produce_batch_desc(struct xsk_queue *q, - u64 addr, u32 len) +static inline int xskq_prod_reserve_desc(struct xsk_queue *q, + u64 addr, u32 len) { struct xdp_rxtx_ring *ring = (struct xdp_rxtx_ring *)q->ring; - unsigned int idx; + u32 idx; - if (xskq_nb_free(q, q->prod_head, 1) == 0) + if (xskq_prod_is_full(q)) return -ENOSPC; /* A, matches D */ - idx = (q->prod_head++) & q->ring_mask; + idx = q->cached_prod++ & q->ring_mask; ring->desc[idx].addr = addr; ring->desc[idx].len = len; return 0; } -static inline void xskq_produce_flush_desc(struct xsk_queue *q) +static inline void __xskq_prod_submit(struct xsk_queue *q, u32 idx) { - /* Order producer and data */ smp_wmb(); /* B, matches C */ - q->prod_tail = q->prod_head; - WRITE_ONCE(q->ring->producer, q->prod_tail); + WRITE_ONCE(q->ring->producer, idx); +} + +static inline void xskq_prod_submit(struct xsk_queue *q) +{ + __xskq_prod_submit(q, q->cached_prod); +} + +static inline void xskq_prod_submit_addr(struct xsk_queue *q, u64 addr) +{ + struct xdp_umem_ring *ring = (struct xdp_umem_ring *)q->ring; + u32 idx = q->ring->producer; + + ring->desc[idx++ & q->ring_mask] = addr; + + __xskq_prod_submit(q, idx); } -static inline bool xskq_full_desc(struct xsk_queue *q) +static inline void xskq_prod_submit_n(struct xsk_queue *q, u32 nb_entries) { - return xskq_nb_avail(q, q->nentries) == q->nentries; + __xskq_prod_submit(q, q->ring->producer + nb_entries); } -static inline bool xskq_empty_desc(struct xsk_queue *q) +static inline bool xskq_prod_is_empty(struct xsk_queue *q) { - return xskq_nb_free(q, q->prod_tail, q->nentries) == q->nentries; + /* No barriers needed since data is not accessed */ + return READ_ONCE(q->ring->consumer) == READ_ONCE(q->ring->producer); +} + +/* For both producers and consumers */ + +static inline u64 xskq_nb_invalid_descs(struct xsk_queue *q) +{ + return q ? q->invalid_descs : 0; } void xskq_set_umem(struct xsk_queue *q, u64 size, u64 chunk_mask); diff --git a/net/xfrm/Makefile b/net/xfrm/Makefile index fbc4552d17b8..212a4fcb4a88 100644 --- a/net/xfrm/Makefile +++ b/net/xfrm/Makefile @@ -11,3 +11,4 @@ obj-$(CONFIG_XFRM_ALGO) += xfrm_algo.o obj-$(CONFIG_XFRM_USER) += xfrm_user.o obj-$(CONFIG_XFRM_IPCOMP) += xfrm_ipcomp.o obj-$(CONFIG_XFRM_INTERFACE) += xfrm_interface.o +obj-$(CONFIG_INET_ESPINTCP) += espintcp.o diff --git a/net/xfrm/espintcp.c b/net/xfrm/espintcp.c new file mode 100644 index 000000000000..f15d6a564b0e --- /dev/null +++ b/net/xfrm/espintcp.c @@ -0,0 +1,509 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <net/tcp.h> +#include <net/strparser.h> +#include <net/xfrm.h> +#include <net/esp.h> +#include <net/espintcp.h> +#include <linux/skmsg.h> +#include <net/inet_common.h> + +static void handle_nonesp(struct espintcp_ctx *ctx, struct sk_buff *skb, + struct sock *sk) +{ + if (atomic_read(&sk->sk_rmem_alloc) >= sk->sk_rcvbuf || + !sk_rmem_schedule(sk, skb, skb->truesize)) { + kfree_skb(skb); + return; + } + + skb_set_owner_r(skb, sk); + + memset(skb->cb, 0, sizeof(skb->cb)); + skb_queue_tail(&ctx->ike_queue, skb); + ctx->saved_data_ready(sk); +} + +static void handle_esp(struct sk_buff *skb, struct sock *sk) +{ + skb_reset_transport_header(skb); + memset(skb->cb, 0, sizeof(skb->cb)); + + rcu_read_lock(); + skb->dev = dev_get_by_index_rcu(sock_net(sk), skb->skb_iif); + local_bh_disable(); + xfrm4_rcv_encap(skb, IPPROTO_ESP, 0, TCP_ENCAP_ESPINTCP); + local_bh_enable(); + rcu_read_unlock(); +} + +static void espintcp_rcv(struct strparser *strp, struct sk_buff *skb) +{ + struct espintcp_ctx *ctx = container_of(strp, struct espintcp_ctx, + strp); + struct strp_msg *rxm = strp_msg(skb); + u32 nonesp_marker; + int err; + + err = skb_copy_bits(skb, rxm->offset + 2, &nonesp_marker, + sizeof(nonesp_marker)); + if (err < 0) { + kfree_skb(skb); + return; + } + + /* remove header, leave non-ESP marker/SPI */ + if (!__pskb_pull(skb, rxm->offset + 2)) { + kfree_skb(skb); + return; + } + + if (pskb_trim(skb, rxm->full_len - 2) != 0) { + kfree_skb(skb); + return; + } + + if (nonesp_marker == 0) + handle_nonesp(ctx, skb, strp->sk); + else + handle_esp(skb, strp->sk); +} + +static int espintcp_parse(struct strparser *strp, struct sk_buff *skb) +{ + struct strp_msg *rxm = strp_msg(skb); + __be16 blen; + u16 len; + int err; + + if (skb->len < rxm->offset + 2) + return 0; + + err = skb_copy_bits(skb, rxm->offset, &blen, sizeof(blen)); + if (err < 0) + return err; + + len = be16_to_cpu(blen); + if (len < 6) + return -EINVAL; + + return len; +} + +static int espintcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, + int nonblock, int flags, int *addr_len) +{ + struct espintcp_ctx *ctx = espintcp_getctx(sk); + struct sk_buff *skb; + int err = 0; + int copied; + int off = 0; + + flags |= nonblock ? MSG_DONTWAIT : 0; + + skb = __skb_recv_datagram(sk, &ctx->ike_queue, flags, NULL, &off, &err); + if (!skb) + return err; + + copied = len; + if (copied > skb->len) + copied = skb->len; + else if (copied < skb->len) + msg->msg_flags |= MSG_TRUNC; + + err = skb_copy_datagram_msg(skb, 0, msg, copied); + if (unlikely(err)) { + kfree_skb(skb); + return err; + } + + if (flags & MSG_TRUNC) + copied = skb->len; + kfree_skb(skb); + return copied; +} + +int espintcp_queue_out(struct sock *sk, struct sk_buff *skb) +{ + struct espintcp_ctx *ctx = espintcp_getctx(sk); + + if (skb_queue_len(&ctx->out_queue) >= netdev_max_backlog) + return -ENOBUFS; + + __skb_queue_tail(&ctx->out_queue, skb); + + return 0; +} +EXPORT_SYMBOL_GPL(espintcp_queue_out); + +/* espintcp length field is 2B and length includes the length field's size */ +#define MAX_ESPINTCP_MSG (((1 << 16) - 1) - 2) + +static int espintcp_sendskb_locked(struct sock *sk, struct espintcp_msg *emsg, + int flags) +{ + do { + int ret; + + ret = skb_send_sock_locked(sk, emsg->skb, + emsg->offset, emsg->len); + if (ret < 0) + return ret; + + emsg->len -= ret; + emsg->offset += ret; + } while (emsg->len > 0); + + kfree_skb(emsg->skb); + memset(emsg, 0, sizeof(*emsg)); + + return 0; +} + +static int espintcp_sendskmsg_locked(struct sock *sk, + struct espintcp_msg *emsg, int flags) +{ + struct sk_msg *skmsg = &emsg->skmsg; + struct scatterlist *sg; + int done = 0; + int ret; + + flags |= MSG_SENDPAGE_NOTLAST; + sg = &skmsg->sg.data[skmsg->sg.start]; + do { + size_t size = sg->length - emsg->offset; + int offset = sg->offset + emsg->offset; + struct page *p; + + emsg->offset = 0; + + if (sg_is_last(sg)) + flags &= ~MSG_SENDPAGE_NOTLAST; + + p = sg_page(sg); +retry: + ret = do_tcp_sendpages(sk, p, offset, size, flags); + if (ret < 0) { + emsg->offset = offset - sg->offset; + skmsg->sg.start += done; + return ret; + } + + if (ret != size) { + offset += ret; + size -= ret; + goto retry; + } + + done++; + put_page(p); + sk_mem_uncharge(sk, sg->length); + sg = sg_next(sg); + } while (sg); + + memset(emsg, 0, sizeof(*emsg)); + + return 0; +} + +static int espintcp_push_msgs(struct sock *sk) +{ + struct espintcp_ctx *ctx = espintcp_getctx(sk); + struct espintcp_msg *emsg = &ctx->partial; + int err; + + if (!emsg->len) + return 0; + + if (ctx->tx_running) + return -EAGAIN; + ctx->tx_running = 1; + + if (emsg->skb) + err = espintcp_sendskb_locked(sk, emsg, 0); + else + err = espintcp_sendskmsg_locked(sk, emsg, 0); + if (err == -EAGAIN) { + ctx->tx_running = 0; + return 0; + } + if (!err) + memset(emsg, 0, sizeof(*emsg)); + + ctx->tx_running = 0; + + return err; +} + +int espintcp_push_skb(struct sock *sk, struct sk_buff *skb) +{ + struct espintcp_ctx *ctx = espintcp_getctx(sk); + struct espintcp_msg *emsg = &ctx->partial; + unsigned int len; + int offset; + + if (sk->sk_state != TCP_ESTABLISHED) { + kfree_skb(skb); + return -ECONNRESET; + } + + offset = skb_transport_offset(skb); + len = skb->len - offset; + + espintcp_push_msgs(sk); + + if (emsg->len) { + kfree_skb(skb); + return -ENOBUFS; + } + + skb_set_owner_w(skb, sk); + + emsg->offset = offset; + emsg->len = len; + emsg->skb = skb; + + espintcp_push_msgs(sk); + + return 0; +} +EXPORT_SYMBOL_GPL(espintcp_push_skb); + +static int espintcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t size) +{ + long timeo = sock_sndtimeo(sk, msg->msg_flags & MSG_DONTWAIT); + struct espintcp_ctx *ctx = espintcp_getctx(sk); + struct espintcp_msg *emsg = &ctx->partial; + struct iov_iter pfx_iter; + struct kvec pfx_iov = {}; + size_t msglen = size + 2; + char buf[2] = {0}; + int err, end; + + if (msg->msg_flags) + return -EOPNOTSUPP; + + if (size > MAX_ESPINTCP_MSG) + return -EMSGSIZE; + + if (msg->msg_controllen) + return -EOPNOTSUPP; + + lock_sock(sk); + + err = espintcp_push_msgs(sk); + if (err < 0) { + err = -ENOBUFS; + goto unlock; + } + + sk_msg_init(&emsg->skmsg); + while (1) { + /* only -ENOMEM is possible since we don't coalesce */ + err = sk_msg_alloc(sk, &emsg->skmsg, msglen, 0); + if (!err) + break; + + err = sk_stream_wait_memory(sk, &timeo); + if (err) + goto fail; + } + + *((__be16 *)buf) = cpu_to_be16(msglen); + pfx_iov.iov_base = buf; + pfx_iov.iov_len = sizeof(buf); + iov_iter_kvec(&pfx_iter, WRITE, &pfx_iov, 1, pfx_iov.iov_len); + + err = sk_msg_memcopy_from_iter(sk, &pfx_iter, &emsg->skmsg, + pfx_iov.iov_len); + if (err < 0) + goto fail; + + err = sk_msg_memcopy_from_iter(sk, &msg->msg_iter, &emsg->skmsg, size); + if (err < 0) + goto fail; + + end = emsg->skmsg.sg.end; + emsg->len = size; + sk_msg_iter_var_prev(end); + sg_mark_end(sk_msg_elem(&emsg->skmsg, end)); + + tcp_rate_check_app_limited(sk); + + err = espintcp_push_msgs(sk); + /* this message could be partially sent, keep it */ + if (err < 0) + goto unlock; + release_sock(sk); + + return size; + +fail: + sk_msg_free(sk, &emsg->skmsg); + memset(emsg, 0, sizeof(*emsg)); +unlock: + release_sock(sk); + return err; +} + +static struct proto espintcp_prot __ro_after_init; +static struct proto_ops espintcp_ops __ro_after_init; + +static void espintcp_data_ready(struct sock *sk) +{ + struct espintcp_ctx *ctx = espintcp_getctx(sk); + + strp_data_ready(&ctx->strp); +} + +static void espintcp_tx_work(struct work_struct *work) +{ + struct espintcp_ctx *ctx = container_of(work, + struct espintcp_ctx, work); + struct sock *sk = ctx->strp.sk; + + lock_sock(sk); + if (!ctx->tx_running) + espintcp_push_msgs(sk); + release_sock(sk); +} + +static void espintcp_write_space(struct sock *sk) +{ + struct espintcp_ctx *ctx = espintcp_getctx(sk); + + schedule_work(&ctx->work); + ctx->saved_write_space(sk); +} + +static void espintcp_destruct(struct sock *sk) +{ + struct espintcp_ctx *ctx = espintcp_getctx(sk); + + kfree(ctx); +} + +bool tcp_is_ulp_esp(struct sock *sk) +{ + return sk->sk_prot == &espintcp_prot; +} +EXPORT_SYMBOL_GPL(tcp_is_ulp_esp); + +static int espintcp_init_sk(struct sock *sk) +{ + struct inet_connection_sock *icsk = inet_csk(sk); + struct strp_callbacks cb = { + .rcv_msg = espintcp_rcv, + .parse_msg = espintcp_parse, + }; + struct espintcp_ctx *ctx; + int err; + + /* sockmap is not compatible with espintcp */ + if (sk->sk_user_data) + return -EBUSY; + + ctx = kzalloc(sizeof(*ctx), GFP_KERNEL); + if (!ctx) + return -ENOMEM; + + err = strp_init(&ctx->strp, sk, &cb); + if (err) + goto free; + + __sk_dst_reset(sk); + + strp_check_rcv(&ctx->strp); + skb_queue_head_init(&ctx->ike_queue); + skb_queue_head_init(&ctx->out_queue); + sk->sk_prot = &espintcp_prot; + sk->sk_socket->ops = &espintcp_ops; + ctx->saved_data_ready = sk->sk_data_ready; + ctx->saved_write_space = sk->sk_write_space; + sk->sk_data_ready = espintcp_data_ready; + sk->sk_write_space = espintcp_write_space; + sk->sk_destruct = espintcp_destruct; + rcu_assign_pointer(icsk->icsk_ulp_data, ctx); + INIT_WORK(&ctx->work, espintcp_tx_work); + + /* avoid using task_frag */ + sk->sk_allocation = GFP_ATOMIC; + + return 0; + +free: + kfree(ctx); + return err; +} + +static void espintcp_release(struct sock *sk) +{ + struct espintcp_ctx *ctx = espintcp_getctx(sk); + struct sk_buff_head queue; + struct sk_buff *skb; + + __skb_queue_head_init(&queue); + skb_queue_splice_init(&ctx->out_queue, &queue); + + while ((skb = __skb_dequeue(&queue))) + espintcp_push_skb(sk, skb); + + tcp_release_cb(sk); +} + +static void espintcp_close(struct sock *sk, long timeout) +{ + struct espintcp_ctx *ctx = espintcp_getctx(sk); + struct espintcp_msg *emsg = &ctx->partial; + + strp_stop(&ctx->strp); + + sk->sk_prot = &tcp_prot; + barrier(); + + cancel_work_sync(&ctx->work); + strp_done(&ctx->strp); + + skb_queue_purge(&ctx->out_queue); + skb_queue_purge(&ctx->ike_queue); + + if (emsg->len) { + if (emsg->skb) + kfree_skb(emsg->skb); + else + sk_msg_free(sk, &emsg->skmsg); + } + + tcp_close(sk, timeout); +} + +static __poll_t espintcp_poll(struct file *file, struct socket *sock, + poll_table *wait) +{ + __poll_t mask = datagram_poll(file, sock, wait); + struct sock *sk = sock->sk; + struct espintcp_ctx *ctx = espintcp_getctx(sk); + + if (!skb_queue_empty(&ctx->ike_queue)) + mask |= EPOLLIN | EPOLLRDNORM; + + return mask; +} + +static struct tcp_ulp_ops espintcp_ulp __read_mostly = { + .name = "espintcp", + .owner = THIS_MODULE, + .init = espintcp_init_sk, +}; + +void __init espintcp_init(void) +{ + memcpy(&espintcp_prot, &tcp_prot, sizeof(tcp_prot)); + memcpy(&espintcp_ops, &inet_stream_ops, sizeof(inet_stream_ops)); + espintcp_prot.sendmsg = espintcp_sendmsg; + espintcp_prot.recvmsg = espintcp_recvmsg; + espintcp_prot.close = espintcp_close; + espintcp_prot.release_cb = espintcp_release; + espintcp_ops.poll = espintcp_poll; + + tcp_register_ulp(&espintcp_ulp); +} diff --git a/net/xfrm/xfrm_device.c b/net/xfrm/xfrm_device.c index 189ef15acbbc..50f567a88f45 100644 --- a/net/xfrm/xfrm_device.c +++ b/net/xfrm/xfrm_device.c @@ -78,7 +78,7 @@ struct sk_buff *validate_xmit_xfrm(struct sk_buff *skb, netdev_features_t featur int err; unsigned long flags; struct xfrm_state *x; - struct sk_buff *skb2; + struct sk_buff *skb2, *nskb; struct softnet_data *sd; netdev_features_t esp_features = features; struct xfrm_offload *xo = xfrm_offload(skb); @@ -148,11 +148,7 @@ struct sk_buff *validate_xmit_xfrm(struct sk_buff *skb, netdev_features_t featur return skb; } - skb2 = skb; - - do { - struct sk_buff *nskb = skb2->next; - + skb_list_walk_safe(skb, skb2, nskb) { esp_features |= skb->dev->gso_partial_features; skb_mark_not_on_list(skb2); @@ -176,14 +172,11 @@ struct sk_buff *validate_xmit_xfrm(struct sk_buff *skb, netdev_features_t featur if (!skb) return NULL; - goto skip_push; + continue; } skb_push(skb2, skb2->data - skb_mac_header(skb2)); - -skip_push: - skb2 = nskb; - } while (skb2); + } return skb; } diff --git a/net/xfrm/xfrm_input.c b/net/xfrm/xfrm_input.c index 2c86a2fc3915..aa35f23c4912 100644 --- a/net/xfrm/xfrm_input.c +++ b/net/xfrm/xfrm_input.c @@ -36,6 +36,7 @@ struct xfrm_trans_cb { #endif } header; int (*finish)(struct net *net, struct sock *sk, struct sk_buff *skb); + struct net *net; }; #define XFRM_TRANS_SKB_CB(__skb) ((struct xfrm_trans_cb *)&((__skb)->cb[0])) @@ -766,12 +767,13 @@ static void xfrm_trans_reinject(unsigned long data) skb_queue_splice_init(&trans->queue, &queue); while ((skb = __skb_dequeue(&queue))) - XFRM_TRANS_SKB_CB(skb)->finish(dev_net(skb->dev), NULL, skb); + XFRM_TRANS_SKB_CB(skb)->finish(XFRM_TRANS_SKB_CB(skb)->net, + NULL, skb); } -int xfrm_trans_queue(struct sk_buff *skb, - int (*finish)(struct net *, struct sock *, - struct sk_buff *)) +int xfrm_trans_queue_net(struct net *net, struct sk_buff *skb, + int (*finish)(struct net *, struct sock *, + struct sk_buff *)) { struct xfrm_trans_tasklet *trans; @@ -780,11 +782,22 @@ int xfrm_trans_queue(struct sk_buff *skb, if (skb_queue_len(&trans->queue) >= netdev_max_backlog) return -ENOBUFS; + BUILD_BUG_ON(sizeof(struct xfrm_trans_cb) > sizeof(skb->cb)); + XFRM_TRANS_SKB_CB(skb)->finish = finish; + XFRM_TRANS_SKB_CB(skb)->net = net; __skb_queue_tail(&trans->queue, skb); tasklet_schedule(&trans->tasklet); return 0; } +EXPORT_SYMBOL(xfrm_trans_queue_net); + +int xfrm_trans_queue(struct sk_buff *skb, + int (*finish)(struct net *, struct sock *, + struct sk_buff *)) +{ + return xfrm_trans_queue_net(dev_net(skb->dev), skb, finish); +} EXPORT_SYMBOL(xfrm_trans_queue); void __init xfrm_input_init(void) diff --git a/net/xfrm/xfrm_output.c b/net/xfrm/xfrm_output.c index b1db55b50ba1..fafc7aba705f 100644 --- a/net/xfrm/xfrm_output.c +++ b/net/xfrm/xfrm_output.c @@ -533,7 +533,7 @@ static int xfrm_output2(struct net *net, struct sock *sk, struct sk_buff *skb) static int xfrm_output_gso(struct net *net, struct sock *sk, struct sk_buff *skb) { - struct sk_buff *segs; + struct sk_buff *segs, *nskb; BUILD_BUG_ON(sizeof(*IPCB(skb)) > SKB_SGO_CB_OFFSET); BUILD_BUG_ON(sizeof(*IP6CB(skb)) > SKB_SGO_CB_OFFSET); @@ -544,8 +544,7 @@ static int xfrm_output_gso(struct net *net, struct sock *sk, struct sk_buff *skb if (segs == NULL) return -EINVAL; - do { - struct sk_buff *nskb = segs->next; + skb_list_walk_safe(segs, segs, nskb) { int err; skb_mark_not_on_list(segs); @@ -555,9 +554,7 @@ static int xfrm_output_gso(struct net *net, struct sock *sk, struct sk_buff *skb kfree_skb_list(nskb); return err; } - - segs = nskb; - } while (segs); + } return 0; } diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index f2d1e573ea55..297d1eb79e5c 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -39,6 +39,9 @@ #ifdef CONFIG_XFRM_STATISTICS #include <net/snmp.h> #endif +#ifdef CONFIG_INET_ESPINTCP +#include <net/espintcp.h> +#endif #include "xfrm_hash.h" @@ -4157,6 +4160,10 @@ void __init xfrm_init(void) seqcount_init(&xfrm_policy_hash_generation); xfrm_input_init(); +#ifdef CONFIG_INET_ESPINTCP + espintcp_init(); +#endif + RCU_INIT_POINTER(xfrm_if_cb, NULL); synchronize_rcu(); } diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c index f3423562d933..170d6e7f31d3 100644 --- a/net/xfrm/xfrm_state.c +++ b/net/xfrm/xfrm_state.c @@ -670,6 +670,9 @@ int __xfrm_state_delete(struct xfrm_state *x) net->xfrm.state_num--; spin_unlock(&net->xfrm.xfrm_state_lock); + if (x->encap_sk) + sock_put(rcu_dereference_raw(x->encap_sk)); + xfrm_dev_state_delete(x); /* All xfrm_state objects are created by xfrm_state_alloc. |