diff options
Diffstat (limited to 'net')
66 files changed, 1926 insertions, 439 deletions
diff --git a/net/Makefile b/net/Makefile index 449fc0b221f8..848303d98d3d 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/ diff --git a/net/atm/lec.c b/net/atm/lec.c index 5a77c235a212..b57368e70aab 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); 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/bridge/br_netlink.c b/net/bridge/br_netlink.c index a0a54482aabc..60136575aea4 100644 --- a/net/bridge/br_netlink.c +++ b/net/bridge/br_netlink.c @@ -1607,6 +1607,19 @@ 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; diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h index 36b0367ca1e0..f540f3bdf294 100644 --- a/net/bridge/br_private.h +++ b/net/bridge/br_private.h @@ -283,6 +283,8 @@ 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) 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/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/rtnetlink.c b/net/core/rtnetlink.c index 02916f43bf63..20bc406f3871 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/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/dsa_priv.h b/net/dsa/dsa_priv.h index 2dd86d9bcda9..09ea2fd78c74 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 */ diff --git a/net/dsa/port.c b/net/dsa/port.c index 46ac9ba21987..ffb5601f7ed6 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, 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/ethtool/Makefile b/net/ethtool/Makefile new file mode 100644 index 000000000000..f68387618973 --- /dev/null +++ b/net/ethtool/Makefile @@ -0,0 +1,3 @@ +# SPDX-License-Identifier: GPL-2.0-only + +obj-y += ioctl.o common.o diff --git a/net/ethtool/common.c b/net/ethtool/common.c new file mode 100644 index 000000000000..0a8728565356 --- /dev/null +++ b/net/ethtool/common.c @@ -0,0 +1,171 @@ +// 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", +}; + +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); diff --git a/net/ethtool/common.h b/net/ethtool/common.h new file mode 100644 index 000000000000..bbb788908cb1 --- /dev/null +++ b/net/ethtool/common.h @@ -0,0 +1,22 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ + +#ifndef _ETHTOOL_COMMON_H +#define _ETHTOOL_COMMON_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]; + +#endif /* _ETHTOOL_COMMON_H */ diff --git a/net/core/ethtool.c b/net/ethtool/ioctl.c index cd9bc67381b2..aed2c2cf1623 100644 --- a/net/core/ethtool.c +++ b/net/ethtool/ioctl.c @@ -27,6 +27,8 @@ #include <net/xdp_sock.h> #include <net/flow_offload.h> +#include "common.h" + /* * Some useful ethtool_ops methods that're device independent. * If we find that all drivers want to do the same thing here, @@ -54,88 +56,6 @@ 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 +154,9 @@ 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 +181,9 @@ 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); diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c index b9df9c09b84e..b92a42433a7d 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) @@ -1063,9 +1068,6 @@ 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 +1120,13 @@ 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 +1153,7 @@ 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 @@ -1217,12 +1221,17 @@ int fib_table_insert(struct net *net, struct fib_table *tb, new_fa->tb_id = tb->tb_id; new_fa->fa_default = -1; - err = call_fib_entry_notifiers(net, - FIB_EVENT_ENTRY_REPLACE, - key, plen, new_fa, - extack); - if (err) - goto out_free_new_fa; + if (fib_find_alias(&l->leaf, fa->fa_slen, 0, 0, + tb->tb_id, true) == 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_free_new_fa; + } rtmsg_fib(RTM_NEWROUTE, htonl(key), new_fa, plen, tb->tb_id, &cfg->fc_nlinfo, nlflags); @@ -1244,12 +1253,10 @@ 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)) @@ -1269,14 +1276,26 @@ int fib_table_insert(struct net *net, struct fib_table *tb, 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; - /* 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 +1306,8 @@ 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 +1558,36 @@ 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 +1609,7 @@ 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 +1641,7 @@ 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 +1965,8 @@ 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 +2062,7 @@ 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 +2077,12 @@ 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; 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 d885ba868822..f09fbc85b108 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -443,8 +443,6 @@ 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); @@ -1778,6 +1776,8 @@ 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 { diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 1c7326e04f9b..6f52e5288a6f 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -2675,6 +2675,7 @@ 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; 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/sched/Kconfig b/net/sched/Kconfig index 2985509147a2..b1e7ec726958 100644 --- a/net/sched/Kconfig +++ b/net/sched/Kconfig @@ -409,6 +409,23 @@ 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..bc8856b865ff 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 diff --git a/net/sched/sch_cake.c b/net/sched/sch_cake.c index e0f40400f679..6cc3ab145513 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; @@ -1919,7 +1918,7 @@ 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 +2240,7 @@ 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 +2251,7 @@ 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 +2264,14 @@ 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 +2340,7 @@ 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 +2356,14 @@ 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 +2402,11 @@ 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 +2437,10 @@ 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_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/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..a031d1134c60 100644 --- a/net/sctp/outqueue.c +++ b/net/sctp/outqueue.c @@ -279,7 +279,7 @@ 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 +533,7 @@ 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: @@ -1884,6 +1884,6 @@ 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 acd737d4c0e0..ce82699d0dca 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..42558fa3f3e4 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; 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 6a30392068a0..e0b01bf912b3 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 7235a6032671..f4de064598f8 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/socket.c b/net/socket.c index 50623218747f..51bf34995bcb 100644 --- a/net/socket.c +++ b/net/socket.c @@ -128,6 +128,7 @@ static ssize_t sock_sendpage(struct file *file, struct page *page, static ssize_t sock_splice_read(struct file *file, loff_t *ppos, struct pipe_inode_info *pipe, size_t len, unsigned int flags); +static void sock_show_fdinfo(struct seq_file *m, struct file *f); /* * Socket files have a set of 'special' operations as well as the generic file ones. These don't appear @@ -150,6 +151,9 @@ static const struct file_operations socket_file_ops = { .sendpage = sock_sendpage, .splice_write = generic_splice_sendpage, .splice_read = sock_splice_read, +#ifdef CONFIG_PROC_FS + .show_fdinfo = sock_show_fdinfo, +#endif }; /* @@ -993,6 +997,14 @@ static ssize_t sock_write_iter(struct kiocb *iocb, struct iov_iter *from) return res; } +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); +} + /* * Atomic setting of ioctl hooks to avoid race * with module unload. 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..6756a3ccc392 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, flags, scm_stat_del, + &skip, &err, &last); if (skb) break; @@ -2353,8 +2395,12 @@ 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 da5262b2298b..fa3526592c51 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -12900,8 +12900,7 @@ 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) |