diff options
Diffstat (limited to '')
324 files changed, 12216 insertions, 5740 deletions
diff --git a/net/8021q/vlan_dev.c b/net/8021q/vlan_dev.c index ec8408d1638f..dc1a197792e6 100644 --- a/net/8021q/vlan_dev.c +++ b/net/8021q/vlan_dev.c @@ -510,9 +510,17 @@ static void vlan_dev_set_lockdep_class(struct net_device *dev) netdev_for_each_tx_queue(dev, vlan_dev_set_lockdep_one, NULL); } +static __be16 vlan_parse_protocol(const struct sk_buff *skb) +{ + struct vlan_ethhdr *veth = (struct vlan_ethhdr *)(skb->data); + + return __vlan_get_protocol(skb, veth->h_vlan_proto, NULL); +} + static const struct header_ops vlan_header_ops = { .create = vlan_dev_hard_header, .parse = eth_header_parse, + .parse_protocol = vlan_parse_protocol, }; static int vlan_passthru_hard_header(struct sk_buff *skb, struct net_device *dev, @@ -532,6 +540,7 @@ static int vlan_passthru_hard_header(struct sk_buff *skb, struct net_device *dev static const struct header_ops vlan_passthru_header_ops = { .create = vlan_passthru_hard_header, .parse = eth_header_parse, + .parse_protocol = vlan_parse_protocol, }; static struct device_type vlan_type = { diff --git a/net/9p/Kconfig b/net/9p/Kconfig index 3d11fec3a8dc..64468c49791f 100644 --- a/net/9p/Kconfig +++ b/net/9p/Kconfig @@ -4,7 +4,6 @@ # menuconfig NET_9P - depends on NET tristate "Plan 9 Resource Sharing Support (9P2000)" help If you say Y here, you will get experimental support for diff --git a/net/Kconfig b/net/Kconfig index f4c32d982af6..8cea808ad9e8 100644 --- a/net/Kconfig +++ b/net/Kconfig @@ -256,9 +256,13 @@ config RFS_ACCEL select CPU_RMAP default y +config SOCK_RX_QUEUE_MAPPING + bool + config XPS bool depends on SMP + select SOCK_RX_QUEUE_MAPPING default y config HWBM diff --git a/net/Makefile b/net/Makefile index d96b0aa8f39f..9ca9572188fe 100644 --- a/net/Makefile +++ b/net/Makefile @@ -6,20 +6,19 @@ # Rewritten to use lists instead of if-statements. # -obj-$(CONFIG_NET) := devres.o socket.o core/ +obj-y := devres.o socket.o core/ -tmp-$(CONFIG_COMPAT) := compat.o -obj-$(CONFIG_NET) += $(tmp-y) +obj-$(CONFIG_COMPAT) += compat.o # LLC has to be linked before the files in net/802/ obj-$(CONFIG_LLC) += llc/ -obj-$(CONFIG_NET) += ethernet/ 802/ sched/ netlink/ bpf/ ethtool/ +obj-y += ethernet/ 802/ sched/ netlink/ bpf/ ethtool/ obj-$(CONFIG_NETFILTER) += netfilter/ obj-$(CONFIG_INET) += ipv4/ obj-$(CONFIG_TLS) += tls/ obj-$(CONFIG_XFRM) += xfrm/ obj-$(CONFIG_UNIX_SCM) += unix/ -obj-$(CONFIG_NET) += ipv6/ +obj-y += ipv6/ obj-$(CONFIG_BPFILTER) += bpfilter/ obj-$(CONFIG_PACKET) += packet/ obj-$(CONFIG_NET_KEY) += key/ @@ -56,16 +55,12 @@ obj-$(CONFIG_SMC) += smc/ obj-$(CONFIG_RFKILL) += rfkill/ obj-$(CONFIG_NET_9P) += 9p/ obj-$(CONFIG_CAIF) += caif/ -ifneq ($(CONFIG_DCB),) -obj-y += dcb/ -endif +obj-$(CONFIG_DCB) += dcb/ obj-$(CONFIG_6LOWPAN) += 6lowpan/ obj-$(CONFIG_IEEE802154) += ieee802154/ obj-$(CONFIG_MAC802154) += mac802154/ -ifeq ($(CONFIG_NET),y) obj-$(CONFIG_SYSCTL) += sysctl_net.o -endif obj-$(CONFIG_DNS_RESOLVER) += dns_resolver/ obj-$(CONFIG_CEPH_LIB) += ceph/ obj-$(CONFIG_BATMAN_ADV) += batman-adv/ @@ -77,12 +72,8 @@ obj-$(CONFIG_VSOCKETS) += vmw_vsock/ obj-$(CONFIG_MPLS) += mpls/ obj-$(CONFIG_NET_NSH) += nsh/ obj-$(CONFIG_HSR) += hsr/ -ifneq ($(CONFIG_NET_SWITCHDEV),) -obj-y += switchdev/ -endif -ifneq ($(CONFIG_NET_L3_MASTER_DEV),) -obj-y += l3mdev/ -endif +obj-$(CONFIG_NET_SWITCHDEV) += switchdev/ +obj-$(CONFIG_NET_L3_MASTER_DEV) += l3mdev/ obj-$(CONFIG_QRTR) += qrtr/ obj-$(CONFIG_NET_NCSI) += ncsi/ obj-$(CONFIG_XDP_SOCKETS) += xdp/ diff --git a/net/atm/pppoatm.c b/net/atm/pppoatm.c index 579b66da1d95..3e4f17d335fe 100644 --- a/net/atm/pppoatm.c +++ b/net/atm/pppoatm.c @@ -101,9 +101,11 @@ static inline struct pppoatm_vcc *chan_to_pvcc(const struct ppp_channel *chan) * doesn't want to be called in interrupt context, so we do it from * a tasklet */ -static void pppoatm_wakeup_sender(unsigned long arg) +static void pppoatm_wakeup_sender(struct tasklet_struct *t) { - ppp_output_wakeup((struct ppp_channel *) arg); + struct pppoatm_vcc *pvcc = from_tasklet(pvcc, t, wakeup_tasklet); + + ppp_output_wakeup(&pvcc->chan); } static void pppoatm_release_cb(struct atm_vcc *atmvcc) @@ -389,11 +391,7 @@ static int pppoatm_assign_vcc(struct atm_vcc *atmvcc, void __user *arg) struct atm_backend_ppp be; struct pppoatm_vcc *pvcc; int err; - /* - * Each PPPoATM instance has its own tasklet - this is just a - * prototypical one used to initialize them - */ - static const DECLARE_TASKLET_OLD(tasklet_proto, pppoatm_wakeup_sender); + if (copy_from_user(&be, arg, sizeof be)) return -EFAULT; if (be.encaps != PPPOATM_ENCAPS_AUTODETECT && @@ -415,8 +413,7 @@ static int pppoatm_assign_vcc(struct atm_vcc *atmvcc, void __user *arg) pvcc->chan.ops = &pppoatm_ops; pvcc->chan.mtu = atmvcc->qos.txtp.max_sdu - PPP_HDRLEN - (be.encaps == e_vc ? 0 : LLC_LEN); - pvcc->wakeup_tasklet = tasklet_proto; - pvcc->wakeup_tasklet.data = (unsigned long) &pvcc->chan; + tasklet_setup(&pvcc->wakeup_tasklet, pppoatm_wakeup_sender); err = ppp_register_channel(&pvcc->chan); if (err != 0) { kfree(pvcc); diff --git a/net/batman-adv/Kconfig b/net/batman-adv/Kconfig index 993afd5ff7bb..860a0786bc1e 100644 --- a/net/batman-adv/Kconfig +++ b/net/batman-adv/Kconfig @@ -1,5 +1,5 @@ # SPDX-License-Identifier: GPL-2.0 -# Copyright (C) 2007-2020 B.A.T.M.A.N. contributors: +# Copyright (C) B.A.T.M.A.N. contributors: # # Marek Lindner, Simon Wunderlich @@ -9,7 +9,6 @@ config BATMAN_ADV tristate "B.A.T.M.A.N. Advanced Meshing Protocol" - depends on NET select LIBCRC32C help B.A.T.M.A.N. (better approach to mobile ad-hoc networking) is diff --git a/net/batman-adv/Makefile b/net/batman-adv/Makefile index 8010c34b987c..3bd0760c76a2 100644 --- a/net/batman-adv/Makefile +++ b/net/batman-adv/Makefile @@ -1,5 +1,5 @@ # SPDX-License-Identifier: GPL-2.0 -# Copyright (C) 2007-2020 B.A.T.M.A.N. contributors: +# Copyright (C) B.A.T.M.A.N. contributors: # # Marek Lindner, Simon Wunderlich diff --git a/net/batman-adv/bat_algo.c b/net/batman-adv/bat_algo.c index c5f404f6892f..4eee53d19eb0 100644 --- a/net/batman-adv/bat_algo.c +++ b/net/batman-adv/bat_algo.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright (C) 2007-2020 B.A.T.M.A.N. contributors: +/* Copyright (C) B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich */ diff --git a/net/batman-adv/bat_algo.h b/net/batman-adv/bat_algo.h index 43b045ac8ac7..2c486374af58 100644 --- a/net/batman-adv/bat_algo.h +++ b/net/batman-adv/bat_algo.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright (C) 2011-2020 B.A.T.M.A.N. contributors: +/* Copyright (C) B.A.T.M.A.N. contributors: * * Marek Lindner, Linus Lüssing */ diff --git a/net/batman-adv/bat_iv_ogm.c b/net/batman-adv/bat_iv_ogm.c index 168621c9a081..a5e313cd6f44 100644 --- a/net/batman-adv/bat_iv_ogm.c +++ b/net/batman-adv/bat_iv_ogm.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright (C) 2007-2020 B.A.T.M.A.N. contributors: +/* Copyright (C) B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich */ diff --git a/net/batman-adv/bat_iv_ogm.h b/net/batman-adv/bat_iv_ogm.h index 0c57c1000c64..04b01bd684e8 100644 --- a/net/batman-adv/bat_iv_ogm.h +++ b/net/batman-adv/bat_iv_ogm.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright (C) 2007-2020 B.A.T.M.A.N. contributors: +/* Copyright (C) B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich */ diff --git a/net/batman-adv/bat_v.c b/net/batman-adv/bat_v.c index e4455babe4c2..e1ca2b8c3152 100644 --- a/net/batman-adv/bat_v.c +++ b/net/batman-adv/bat_v.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright (C) 2013-2020 B.A.T.M.A.N. contributors: +/* Copyright (C) B.A.T.M.A.N. contributors: * * Linus Lüssing, Marek Lindner */ diff --git a/net/batman-adv/bat_v.h b/net/batman-adv/bat_v.h index 5e0be10bc84e..964431f4dc8d 100644 --- a/net/batman-adv/bat_v.h +++ b/net/batman-adv/bat_v.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright (C) 2011-2020 B.A.T.M.A.N. contributors: +/* Copyright (C) B.A.T.M.A.N. contributors: * * Marek Lindner, Linus Lüssing */ diff --git a/net/batman-adv/bat_v_elp.c b/net/batman-adv/bat_v_elp.c index 0512ea6cd818..423c2d171703 100644 --- a/net/batman-adv/bat_v_elp.c +++ b/net/batman-adv/bat_v_elp.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright (C) 2011-2020 B.A.T.M.A.N. contributors: +/* Copyright (C) B.A.T.M.A.N. contributors: * * Linus Lüssing, Marek Lindner */ diff --git a/net/batman-adv/bat_v_elp.h b/net/batman-adv/bat_v_elp.h index 4358d436be2a..9e2740195fa2 100644 --- a/net/batman-adv/bat_v_elp.h +++ b/net/batman-adv/bat_v_elp.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright (C) 2013-2020 B.A.T.M.A.N. contributors: +/* Copyright (C) B.A.T.M.A.N. contributors: * * Linus Lüssing, Marek Lindner */ diff --git a/net/batman-adv/bat_v_ogm.c b/net/batman-adv/bat_v_ogm.c index 798d659855d0..a0a9636d1740 100644 --- a/net/batman-adv/bat_v_ogm.c +++ b/net/batman-adv/bat_v_ogm.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright (C) 2013-2020 B.A.T.M.A.N. contributors: +/* Copyright (C) B.A.T.M.A.N. contributors: * * Antonio Quartulli */ diff --git a/net/batman-adv/bat_v_ogm.h b/net/batman-adv/bat_v_ogm.h index 0ae2575f70bb..edeffedecade 100644 --- a/net/batman-adv/bat_v_ogm.h +++ b/net/batman-adv/bat_v_ogm.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright (C) 2013-2020 B.A.T.M.A.N. contributors: +/* Copyright (C) B.A.T.M.A.N. contributors: * * Antonio Quartulli */ diff --git a/net/batman-adv/bitarray.c b/net/batman-adv/bitarray.c index 4bc695cda397..649c41f393e1 100644 --- a/net/batman-adv/bitarray.c +++ b/net/batman-adv/bitarray.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright (C) 2006-2020 B.A.T.M.A.N. contributors: +/* Copyright (C) B.A.T.M.A.N. contributors: * * Simon Wunderlich, Marek Lindner */ diff --git a/net/batman-adv/bitarray.h b/net/batman-adv/bitarray.h index 533c6d44cb58..37f7ae413bc6 100644 --- a/net/batman-adv/bitarray.h +++ b/net/batman-adv/bitarray.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright (C) 2006-2020 B.A.T.M.A.N. contributors: +/* Copyright (C) B.A.T.M.A.N. contributors: * * Simon Wunderlich, Marek Lindner */ diff --git a/net/batman-adv/bridge_loop_avoidance.c b/net/batman-adv/bridge_loop_avoidance.c index d2de12e527ba..360bdbf44748 100644 --- a/net/batman-adv/bridge_loop_avoidance.c +++ b/net/batman-adv/bridge_loop_avoidance.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright (C) 2011-2020 B.A.T.M.A.N. contributors: +/* Copyright (C) B.A.T.M.A.N. contributors: * * Simon Wunderlich */ diff --git a/net/batman-adv/bridge_loop_avoidance.h b/net/batman-adv/bridge_loop_avoidance.h index 7dc6d3571925..5c22955bb9d5 100644 --- a/net/batman-adv/bridge_loop_avoidance.h +++ b/net/batman-adv/bridge_loop_avoidance.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright (C) 2011-2020 B.A.T.M.A.N. contributors: +/* Copyright (C) B.A.T.M.A.N. contributors: * * Simon Wunderlich */ diff --git a/net/batman-adv/distributed-arp-table.c b/net/batman-adv/distributed-arp-table.c index fd7ba6bbdf85..8c95a11a830a 100644 --- a/net/batman-adv/distributed-arp-table.c +++ b/net/batman-adv/distributed-arp-table.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright (C) 2011-2020 B.A.T.M.A.N. contributors: +/* Copyright (C) B.A.T.M.A.N. contributors: * * Antonio Quartulli */ @@ -87,7 +87,7 @@ struct batadv_dhcp_packet { __u8 sname[64]; __u8 file[128]; __be32 magic; - __u8 options[]; + /* __u8 options[]; */ }; #define BATADV_DHCP_YIADDR_LEN sizeof(((struct batadv_dhcp_packet *)0)->yiaddr) @@ -1564,7 +1564,7 @@ static int batadv_dat_get_dhcp_message_type(struct sk_buff *skb) } /** - * batadv_dat_get_dhcp_yiaddr() - get yiaddr from a DHCP packet + * batadv_dat_dhcp_get_yiaddr() - get yiaddr from a DHCP packet * @skb: the DHCP packet to parse * @buf: a buffer to store the yiaddr in * diff --git a/net/batman-adv/distributed-arp-table.h b/net/batman-adv/distributed-arp-table.h index e980fb45693a..bed7f3d20844 100644 --- a/net/batman-adv/distributed-arp-table.h +++ b/net/batman-adv/distributed-arp-table.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright (C) 2011-2020 B.A.T.M.A.N. contributors: +/* Copyright (C) B.A.T.M.A.N. contributors: * * Antonio Quartulli */ diff --git a/net/batman-adv/fragmentation.c b/net/batman-adv/fragmentation.c index e522f1fcfd9a..a5d9d800082b 100644 --- a/net/batman-adv/fragmentation.c +++ b/net/batman-adv/fragmentation.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright (C) 2013-2020 B.A.T.M.A.N. contributors: +/* Copyright (C) B.A.T.M.A.N. contributors: * * Martin Hundebøll <martin@hundeboll.net> */ diff --git a/net/batman-adv/fragmentation.h b/net/batman-adv/fragmentation.h index 881ef328b6cd..dbf0871f8703 100644 --- a/net/batman-adv/fragmentation.h +++ b/net/batman-adv/fragmentation.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright (C) 2013-2020 B.A.T.M.A.N. contributors: +/* Copyright (C) B.A.T.M.A.N. contributors: * * Martin Hundebøll <martin@hundeboll.net> */ diff --git a/net/batman-adv/gateway_client.c b/net/batman-adv/gateway_client.c index cffe72f4edd7..007f2827935d 100644 --- a/net/batman-adv/gateway_client.c +++ b/net/batman-adv/gateway_client.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright (C) 2009-2020 B.A.T.M.A.N. contributors: +/* Copyright (C) B.A.T.M.A.N. contributors: * * Marek Lindner */ diff --git a/net/batman-adv/gateway_client.h b/net/batman-adv/gateway_client.h index 2fbc500f0ac1..2ae5846ef958 100644 --- a/net/batman-adv/gateway_client.h +++ b/net/batman-adv/gateway_client.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright (C) 2009-2020 B.A.T.M.A.N. contributors: +/* Copyright (C) B.A.T.M.A.N. contributors: * * Marek Lindner */ diff --git a/net/batman-adv/gateway_common.c b/net/batman-adv/gateway_common.c index 16cd9450ceb1..fdde305a198e 100644 --- a/net/batman-adv/gateway_common.c +++ b/net/batman-adv/gateway_common.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright (C) 2009-2020 B.A.T.M.A.N. contributors: +/* Copyright (C) B.A.T.M.A.N. contributors: * * Marek Lindner */ diff --git a/net/batman-adv/gateway_common.h b/net/batman-adv/gateway_common.h index c3a0c5a7f7e9..87c37f907261 100644 --- a/net/batman-adv/gateway_common.h +++ b/net/batman-adv/gateway_common.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright (C) 2009-2020 B.A.T.M.A.N. contributors: +/* Copyright (C) B.A.T.M.A.N. contributors: * * Marek Lindner */ diff --git a/net/batman-adv/hard-interface.c b/net/batman-adv/hard-interface.c index 0f186ddc15e3..4a6a25d551a8 100644 --- a/net/batman-adv/hard-interface.c +++ b/net/batman-adv/hard-interface.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright (C) 2007-2020 B.A.T.M.A.N. contributors: +/* Copyright (C) B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich */ diff --git a/net/batman-adv/hard-interface.h b/net/batman-adv/hard-interface.h index f4b8e9efef19..83d11b46a9d8 100644 --- a/net/batman-adv/hard-interface.h +++ b/net/batman-adv/hard-interface.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright (C) 2007-2020 B.A.T.M.A.N. contributors: +/* Copyright (C) B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich */ diff --git a/net/batman-adv/hash.c b/net/batman-adv/hash.c index 68638e0450a6..8016e619787f 100644 --- a/net/batman-adv/hash.c +++ b/net/batman-adv/hash.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright (C) 2006-2020 B.A.T.M.A.N. contributors: +/* Copyright (C) B.A.T.M.A.N. contributors: * * Simon Wunderlich, Marek Lindner */ diff --git a/net/batman-adv/hash.h b/net/batman-adv/hash.h index 91ae9f32b580..46696759f194 100644 --- a/net/batman-adv/hash.h +++ b/net/batman-adv/hash.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright (C) 2006-2020 B.A.T.M.A.N. contributors: +/* Copyright (C) B.A.T.M.A.N. contributors: * * Simon Wunderlich, Marek Lindner */ diff --git a/net/batman-adv/log.c b/net/batman-adv/log.c index b7e9923b11a2..f0e5d1429662 100644 --- a/net/batman-adv/log.c +++ b/net/batman-adv/log.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright (C) 2010-2020 B.A.T.M.A.N. contributors: +/* Copyright (C) B.A.T.M.A.N. contributors: * * Marek Lindner */ diff --git a/net/batman-adv/log.h b/net/batman-adv/log.h index 979864c0fa6b..6717c965f0fa 100644 --- a/net/batman-adv/log.h +++ b/net/batman-adv/log.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright (C) 2007-2020 B.A.T.M.A.N. contributors: +/* Copyright (C) B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich */ diff --git a/net/batman-adv/main.c b/net/batman-adv/main.c index ed9d87ce3407..e48f7ac8a854 100644 --- a/net/batman-adv/main.c +++ b/net/batman-adv/main.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright (C) 2007-2020 B.A.T.M.A.N. contributors: +/* Copyright (C) B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich */ diff --git a/net/batman-adv/main.h b/net/batman-adv/main.h index 288201630ceb..8f0102b71656 100644 --- a/net/batman-adv/main.h +++ b/net/batman-adv/main.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright (C) 2007-2020 B.A.T.M.A.N. contributors: +/* Copyright (C) B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich */ @@ -13,7 +13,7 @@ #define BATADV_DRIVER_DEVICE "batman-adv" #ifndef BATADV_SOURCE_VERSION -#define BATADV_SOURCE_VERSION "2021.0" +#define BATADV_SOURCE_VERSION "2021.1" #endif /* B.A.T.M.A.N. parameters */ diff --git a/net/batman-adv/multicast.c b/net/batman-adv/multicast.c index 854e5ff28a3f..28166402d30c 100644 --- a/net/batman-adv/multicast.c +++ b/net/batman-adv/multicast.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright (C) 2014-2020 B.A.T.M.A.N. contributors: +/* Copyright (C) B.A.T.M.A.N. contributors: * * Linus Lüssing */ @@ -828,7 +828,7 @@ batadv_mcast_bridge_log(struct batadv_priv *bat_priv, } /** - * batadv_mcast_flags_logs() - output debug information about mcast flag changes + * batadv_mcast_flags_log() - output debug information about mcast flag changes * @bat_priv: the bat priv with all the soft interface information * @flags: TVLV flags indicating the new multicast state * diff --git a/net/batman-adv/multicast.h b/net/batman-adv/multicast.h index d61593d02072..9fee5da08311 100644 --- a/net/batman-adv/multicast.h +++ b/net/batman-adv/multicast.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright (C) 2014-2020 B.A.T.M.A.N. contributors: +/* Copyright (C) B.A.T.M.A.N. contributors: * * Linus Lüssing */ diff --git a/net/batman-adv/netlink.c b/net/batman-adv/netlink.c index 97bcf149633d..f317d206b411 100644 --- a/net/batman-adv/netlink.c +++ b/net/batman-adv/netlink.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright (C) 2016-2020 B.A.T.M.A.N. contributors: +/* Copyright (C) B.A.T.M.A.N. contributors: * * Matthias Schiffer */ @@ -193,7 +193,7 @@ static int batadv_netlink_mesh_fill_ap_isolation(struct sk_buff *msg, } /** - * batadv_option_set_ap_isolation() - Set ap_isolation from genl msg + * batadv_netlink_set_mesh_ap_isolation() - Set ap_isolation from genl msg * @attr: parsed BATADV_ATTR_AP_ISOLATION_ENABLED attribute * @bat_priv: the bat priv with all the soft interface information * @@ -757,7 +757,7 @@ batadv_netlink_tp_meter_start(struct sk_buff *skb, struct genl_info *info) } /** - * batadv_netlink_tp_meter_start() - Cancel a running tp_meter session + * batadv_netlink_tp_meter_cancel() - Cancel a running tp_meter session * @skb: received netlink message * @info: receiver information * diff --git a/net/batman-adv/netlink.h b/net/batman-adv/netlink.h index 7ee48f916997..48102cc7490c 100644 --- a/net/batman-adv/netlink.h +++ b/net/batman-adv/netlink.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright (C) 2016-2020 B.A.T.M.A.N. contributors: +/* Copyright (C) B.A.T.M.A.N. contributors: * * Matthias Schiffer */ diff --git a/net/batman-adv/network-coding.c b/net/batman-adv/network-coding.c index 0cec108b7a99..4bb76b434d07 100644 --- a/net/batman-adv/network-coding.c +++ b/net/batman-adv/network-coding.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright (C) 2012-2020 B.A.T.M.A.N. contributors: +/* Copyright (C) B.A.T.M.A.N. contributors: * * Martin Hundebøll, Jeppe Ledet-Pedersen */ diff --git a/net/batman-adv/network-coding.h b/net/batman-adv/network-coding.h index 8fb2c01e7837..368cc3130e4c 100644 --- a/net/batman-adv/network-coding.h +++ b/net/batman-adv/network-coding.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright (C) 2012-2020 B.A.T.M.A.N. contributors: +/* Copyright (C) B.A.T.M.A.N. contributors: * * Martin Hundebøll, Jeppe Ledet-Pedersen */ diff --git a/net/batman-adv/originator.c b/net/batman-adv/originator.c index 77431e59b228..da7249448474 100644 --- a/net/batman-adv/originator.c +++ b/net/batman-adv/originator.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright (C) 2009-2020 B.A.T.M.A.N. contributors: +/* Copyright (C) B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich */ diff --git a/net/batman-adv/originator.h b/net/batman-adv/originator.h index e75d4c4d11f5..805be87d55b8 100644 --- a/net/batman-adv/originator.h +++ b/net/batman-adv/originator.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright (C) 2007-2020 B.A.T.M.A.N. contributors: +/* Copyright (C) B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich */ diff --git a/net/batman-adv/routing.c b/net/batman-adv/routing.c index 49cbca4aa428..40f5cffde6a3 100644 --- a/net/batman-adv/routing.c +++ b/net/batman-adv/routing.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright (C) 2007-2020 B.A.T.M.A.N. contributors: +/* Copyright (C) B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich */ diff --git a/net/batman-adv/routing.h b/net/batman-adv/routing.h index 2ed49db6eff5..5f387786e9a7 100644 --- a/net/batman-adv/routing.h +++ b/net/batman-adv/routing.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright (C) 2007-2020 B.A.T.M.A.N. contributors: +/* Copyright (C) B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich */ diff --git a/net/batman-adv/send.c b/net/batman-adv/send.c index 87017332b567..157abe92d827 100644 --- a/net/batman-adv/send.c +++ b/net/batman-adv/send.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright (C) 2007-2020 B.A.T.M.A.N. contributors: +/* Copyright (C) B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich */ diff --git a/net/batman-adv/send.h b/net/batman-adv/send.h index 0d36e15589f6..2b0daf8b2bc4 100644 --- a/net/batman-adv/send.h +++ b/net/batman-adv/send.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright (C) 2007-2020 B.A.T.M.A.N. contributors: +/* Copyright (C) B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich */ diff --git a/net/batman-adv/soft-interface.c b/net/batman-adv/soft-interface.c index 97118efbe678..6b8181bc3122 100644 --- a/net/batman-adv/soft-interface.c +++ b/net/batman-adv/soft-interface.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright (C) 2007-2020 B.A.T.M.A.N. contributors: +/* Copyright (C) B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich */ diff --git a/net/batman-adv/soft-interface.h b/net/batman-adv/soft-interface.h index 74716d9ca4f6..38b0ad182584 100644 --- a/net/batman-adv/soft-interface.h +++ b/net/batman-adv/soft-interface.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright (C) 2007-2020 B.A.T.M.A.N. contributors: +/* Copyright (C) B.A.T.M.A.N. contributors: * * Marek Lindner */ diff --git a/net/batman-adv/tp_meter.c b/net/batman-adv/tp_meter.c index d4e10005df6c..789c851732b7 100644 --- a/net/batman-adv/tp_meter.c +++ b/net/batman-adv/tp_meter.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright (C) 2012-2020 B.A.T.M.A.N. contributors: +/* Copyright (C) B.A.T.M.A.N. contributors: * * Edo Monticelli, Antonio Quartulli */ @@ -131,7 +131,7 @@ static u32 batadv_tp_cwnd(u32 base, u32 increment, u32 min) } /** - * batadv_tp_updated_cwnd() - update the Congestion Windows + * batadv_tp_update_cwnd() - update the Congestion Windows * @tp_vars: the private data of the current TP meter session * @mss: maximum segment size of transmission * diff --git a/net/batman-adv/tp_meter.h b/net/batman-adv/tp_meter.h index 140105215aa2..f0046d366eac 100644 --- a/net/batman-adv/tp_meter.h +++ b/net/batman-adv/tp_meter.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright (C) 2012-2020 B.A.T.M.A.N. contributors: +/* Copyright (C) B.A.T.M.A.N. contributors: * * Edo Monticelli, Antonio Quartulli */ diff --git a/net/batman-adv/trace.c b/net/batman-adv/trace.c index 3444d9e4e90d..ec8b9519076b 100644 --- a/net/batman-adv/trace.c +++ b/net/batman-adv/trace.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright (C) 2010-2020 B.A.T.M.A.N. contributors: +/* Copyright (C) B.A.T.M.A.N. contributors: * * Sven Eckelmann */ diff --git a/net/batman-adv/trace.h b/net/batman-adv/trace.h index a87547570b4e..d673ebdd0426 100644 --- a/net/batman-adv/trace.h +++ b/net/batman-adv/trace.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright (C) 2010-2020 B.A.T.M.A.N. contributors: +/* Copyright (C) B.A.T.M.A.N. contributors: * * Sven Eckelmann */ diff --git a/net/batman-adv/translation-table.c b/net/batman-adv/translation-table.c index cd09916f97fe..f8761281aab0 100644 --- a/net/batman-adv/translation-table.c +++ b/net/batman-adv/translation-table.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright (C) 2007-2020 B.A.T.M.A.N. contributors: +/* Copyright (C) B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich, Antonio Quartulli */ diff --git a/net/batman-adv/translation-table.h b/net/batman-adv/translation-table.h index 57192c817229..e1285904f885 100644 --- a/net/batman-adv/translation-table.h +++ b/net/batman-adv/translation-table.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright (C) 2007-2020 B.A.T.M.A.N. contributors: +/* Copyright (C) B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich, Antonio Quartulli */ diff --git a/net/batman-adv/tvlv.c b/net/batman-adv/tvlv.c index 6a23a566cde1..253f5a33a914 100644 --- a/net/batman-adv/tvlv.c +++ b/net/batman-adv/tvlv.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright (C) 2007-2020 B.A.T.M.A.N. contributors: +/* Copyright (C) B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich */ diff --git a/net/batman-adv/tvlv.h b/net/batman-adv/tvlv.h index d509d00c7a23..54f2a35653d0 100644 --- a/net/batman-adv/tvlv.h +++ b/net/batman-adv/tvlv.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright (C) 2007-2020 B.A.T.M.A.N. contributors: +/* Copyright (C) B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich */ diff --git a/net/batman-adv/types.h b/net/batman-adv/types.h index 2f96e96a5ca4..7c0b475cc22a 100644 --- a/net/batman-adv/types.h +++ b/net/batman-adv/types.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright (C) 2007-2020 B.A.T.M.A.N. contributors: +/* Copyright (C) B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich */ @@ -228,7 +228,8 @@ struct batadv_hard_iface { }; /** - * struct batadv_orig_ifinfo - B.A.T.M.A.N. IV private orig_ifinfo members + * struct batadv_orig_ifinfo_bat_iv - B.A.T.M.A.N. IV private orig_ifinfo + * members */ struct batadv_orig_ifinfo_bat_iv { /** diff --git a/net/bluetooth/Kconfig b/net/bluetooth/Kconfig index 64e669acd42f..400c5130dc0a 100644 --- a/net/bluetooth/Kconfig +++ b/net/bluetooth/Kconfig @@ -5,7 +5,7 @@ menuconfig BT tristate "Bluetooth subsystem support" - depends on NET && !S390 + depends on !S390 depends on RFKILL || !RFKILL select CRC16 select CRYPTO diff --git a/net/bluetooth/a2mp.c b/net/bluetooth/a2mp.c index da7fd7c8c2dc..463bad58478b 100644 --- a/net/bluetooth/a2mp.c +++ b/net/bluetooth/a2mp.c @@ -381,9 +381,9 @@ static int a2mp_getampassoc_req(struct amp_mgr *mgr, struct sk_buff *skb, hdev = hci_dev_get(req->id); if (!hdev || hdev->amp_type == AMP_TYPE_BREDR || tmp) { struct a2mp_amp_assoc_rsp rsp; - rsp.id = req->id; memset(&rsp, 0, sizeof(rsp)); + rsp.id = req->id; if (tmp) { rsp.status = A2MP_STATUS_COLLISION_OCCURED; @@ -512,6 +512,7 @@ static int a2mp_createphyslink_req(struct amp_mgr *mgr, struct sk_buff *skb, assoc = kmemdup(req->amp_assoc, assoc_len, GFP_KERNEL); if (!assoc) { amp_ctrl_put(ctrl); + hci_dev_put(hdev); return -ENOMEM; } diff --git a/net/bluetooth/af_bluetooth.c b/net/bluetooth/af_bluetooth.c index 4ef6a54403aa..1661979b6a6e 100644 --- a/net/bluetooth/af_bluetooth.c +++ b/net/bluetooth/af_bluetooth.c @@ -72,8 +72,8 @@ void bt_sock_reclassify_lock(struct sock *sk, int proto) BUG_ON(!sock_allow_reclassification(sk)); sock_lock_init_class_and_name(sk, - bt_slock_key_strings[proto], &bt_slock_key[proto], - bt_key_strings[proto], &bt_lock_key[proto]); + bt_slock_key_strings[proto], &bt_slock_key[proto], + bt_key_strings[proto], &bt_lock_key[proto]); } EXPORT_SYMBOL(bt_sock_reclassify_lock); @@ -451,7 +451,7 @@ static inline __poll_t bt_accept_poll(struct sock *parent) } __poll_t bt_sock_poll(struct file *file, struct socket *sock, - poll_table *wait) + poll_table *wait) { struct sock *sk = sock->sk; __poll_t mask = 0; @@ -478,8 +478,8 @@ __poll_t bt_sock_poll(struct file *file, struct socket *sock, mask |= EPOLLHUP; if (sk->sk_state == BT_CONNECT || - sk->sk_state == BT_CONNECT2 || - sk->sk_state == BT_CONFIG) + sk->sk_state == BT_CONNECT2 || + sk->sk_state == BT_CONFIG) return mask; if (!test_bit(BT_SK_SUSPEND, &bt_sk(sk)->flags) && sock_writeable(sk)) @@ -508,7 +508,7 @@ int bt_sock_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) amount = sk->sk_sndbuf - sk_wmem_alloc_get(sk); if (amount < 0) amount = 0; - err = put_user(amount, (int __user *) arg); + err = put_user(amount, (int __user *)arg); break; case TIOCINQ: @@ -519,7 +519,7 @@ int bt_sock_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) skb = skb_peek(&sk->sk_receive_queue); amount = skb ? skb->len : 0; release_sock(sk); - err = put_user(amount, (int __user *) arg); + err = put_user(amount, (int __user *)arg); break; default: @@ -637,7 +637,7 @@ static int bt_seq_show(struct seq_file *seq, void *v) struct bt_sock_list *l = PDE_DATA(file_inode(seq->file)); if (v == SEQ_START_TOKEN) { - seq_puts(seq ,"sk RefCnt Rmem Wmem User Inode Parent"); + seq_puts(seq, "sk RefCnt Rmem Wmem User Inode Parent"); if (l->custom_seq_show) { seq_putc(seq, ' '); @@ -657,7 +657,7 @@ static int bt_seq_show(struct seq_file *seq, void *v) sk_wmem_alloc_get(sk), from_kuid(seq_user_ns(seq), sock_i_uid(sk)), sock_i_ino(sk), - bt->parent? sock_i_ino(bt->parent): 0LU); + bt->parent ? sock_i_ino(bt->parent) : 0LU); if (l->custom_seq_show) { seq_putc(seq, ' '); @@ -678,7 +678,7 @@ static const struct seq_operations bt_seq_ops = { int bt_procfs_init(struct net *net, const char *name, struct bt_sock_list *sk_list, - int (* seq_show)(struct seq_file *, void *)) + int (*seq_show)(struct seq_file *, void *)) { sk_list->custom_seq_show = seq_show; @@ -694,7 +694,7 @@ void bt_procfs_cleanup(struct net *net, const char *name) #else int bt_procfs_init(struct net *net, const char *name, struct bt_sock_list *sk_list, - int (* seq_show)(struct seq_file *, void *)) + int (*seq_show)(struct seq_file *, void *)) { return 0; } diff --git a/net/bluetooth/amp.c b/net/bluetooth/amp.c index 9c711f0dfae3..be2d469d6369 100644 --- a/net/bluetooth/amp.c +++ b/net/bluetooth/amp.c @@ -297,6 +297,9 @@ void amp_read_loc_assoc_final_data(struct hci_dev *hdev, struct hci_request req; int err; + if (!mgr) + return; + cp.phy_handle = hcon->handle; cp.len_so_far = cpu_to_le16(0); cp.max_len = cpu_to_le16(hdev->amp_assoc_size); diff --git a/net/bluetooth/hci_conn.c b/net/bluetooth/hci_conn.c index 4f1cd8063e72..6ffa89e3ba0a 100644 --- a/net/bluetooth/hci_conn.c +++ b/net/bluetooth/hci_conn.c @@ -203,6 +203,23 @@ static void hci_acl_create_connection(struct hci_conn *conn) BT_DBG("hcon %p", conn); + /* Many controllers disallow HCI Create Connection while it is doing + * HCI Inquiry. So we cancel the Inquiry first before issuing HCI Create + * Connection. This may cause the MGMT discovering state to become false + * without user space's request but it is okay since the MGMT Discovery + * APIs do not promise that discovery should be done forever. Instead, + * the user space monitors the status of MGMT discovering and it may + * request for discovery again when this flag becomes false. + */ + if (test_bit(HCI_INQUIRY, &hdev->flags)) { + /* Put this connection to "pending" state so that it will be + * executed after the inquiry cancel command complete event. + */ + conn->state = BT_CONNECT2; + hci_send_cmd(hdev, HCI_OP_INQUIRY_CANCEL, 0, NULL); + return; + } + conn->state = BT_CONNECT; conn->out = true; conn->role = HCI_ROLE_MASTER; @@ -276,6 +293,20 @@ static void hci_add_sco(struct hci_conn *conn, __u16 handle) hci_send_cmd(hdev, HCI_OP_ADD_SCO, sizeof(cp), &cp); } +static bool find_next_esco_param(struct hci_conn *conn, + const struct sco_param *esco_param, int size) +{ + for (; conn->attempt <= size; conn->attempt++) { + if (lmp_esco_2m_capable(conn->link) || + (esco_param[conn->attempt - 1].pkt_type & ESCO_2EV3)) + break; + BT_DBG("hcon %p skipped attempt %d, eSCO 2M not supported", + conn, conn->attempt); + } + + return conn->attempt <= size; +} + bool hci_setup_sync(struct hci_conn *conn, __u16 handle) { struct hci_dev *hdev = conn->hdev; @@ -297,13 +328,15 @@ bool hci_setup_sync(struct hci_conn *conn, __u16 handle) switch (conn->setting & SCO_AIRMODE_MASK) { case SCO_AIRMODE_TRANSP: - if (conn->attempt > ARRAY_SIZE(esco_param_msbc)) + if (!find_next_esco_param(conn, esco_param_msbc, + ARRAY_SIZE(esco_param_msbc))) return false; param = &esco_param_msbc[conn->attempt - 1]; break; case SCO_AIRMODE_CVSD: if (lmp_esco_capable(conn->link)) { - if (conn->attempt > ARRAY_SIZE(esco_param_cvsd)) + if (!find_next_esco_param(conn, esco_param_cvsd, + ARRAY_SIZE(esco_param_cvsd))) return false; param = &esco_param_cvsd[conn->attempt - 1]; } else { diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c index 9d2c9a1c552f..b0d9c36acc03 100644 --- a/net/bluetooth/hci_core.c +++ b/net/bluetooth/hci_core.c @@ -1362,8 +1362,10 @@ int hci_inquiry(void __user *arg) * cleared). If it is interrupted by a signal, return -EINTR. */ if (wait_on_bit(&hdev->flags, HCI_INQUIRY, - TASK_INTERRUPTIBLE)) - return -EINTR; + TASK_INTERRUPTIBLE)) { + err = -EINTR; + goto done; + } } /* for unlimited number of responses we will use buffer with @@ -3051,12 +3053,15 @@ void hci_adv_monitors_clear(struct hci_dev *hdev) int handle; idr_for_each_entry(&hdev->adv_monitors_idr, monitor, handle) - hci_free_adv_monitor(monitor); + hci_free_adv_monitor(hdev, monitor); idr_destroy(&hdev->adv_monitors_idr); } -void hci_free_adv_monitor(struct adv_monitor *monitor) +/* Frees the monitor structure and do some bookkeepings. + * This function requires the caller holds hdev->lock. + */ +void hci_free_adv_monitor(struct hci_dev *hdev, struct adv_monitor *monitor) { struct adv_pattern *pattern; struct adv_pattern *tmp; @@ -3064,68 +3069,167 @@ void hci_free_adv_monitor(struct adv_monitor *monitor) if (!monitor) return; - list_for_each_entry_safe(pattern, tmp, &monitor->patterns, list) + list_for_each_entry_safe(pattern, tmp, &monitor->patterns, list) { + list_del(&pattern->list); kfree(pattern); + } + + if (monitor->handle) + idr_remove(&hdev->adv_monitors_idr, monitor->handle); + + if (monitor->state != ADV_MONITOR_STATE_NOT_REGISTERED) { + hdev->adv_monitors_cnt--; + mgmt_adv_monitor_removed(hdev, monitor->handle); + } kfree(monitor); } -/* This function requires the caller holds hdev->lock */ -int hci_add_adv_monitor(struct hci_dev *hdev, struct adv_monitor *monitor) +int hci_add_adv_patterns_monitor_complete(struct hci_dev *hdev, u8 status) +{ + return mgmt_add_adv_patterns_monitor_complete(hdev, status); +} + +int hci_remove_adv_monitor_complete(struct hci_dev *hdev, u8 status) +{ + return mgmt_remove_adv_monitor_complete(hdev, status); +} + +/* Assigns handle to a monitor, and if offloading is supported and power is on, + * also attempts to forward the request to the controller. + * Returns true if request is forwarded (result is pending), false otherwise. + * This function requires the caller holds hdev->lock. + */ +bool hci_add_adv_monitor(struct hci_dev *hdev, struct adv_monitor *monitor, + int *err) { int min, max, handle; - if (!monitor) - return -EINVAL; + *err = 0; + + if (!monitor) { + *err = -EINVAL; + return false; + } min = HCI_MIN_ADV_MONITOR_HANDLE; max = HCI_MIN_ADV_MONITOR_HANDLE + HCI_MAX_ADV_MONITOR_NUM_HANDLES; handle = idr_alloc(&hdev->adv_monitors_idr, monitor, min, max, GFP_KERNEL); - if (handle < 0) - return handle; + if (handle < 0) { + *err = handle; + return false; + } - hdev->adv_monitors_cnt++; monitor->handle = handle; - hci_update_background_scan(hdev); + if (!hdev_is_powered(hdev)) + return false; - return 0; + switch (hci_get_adv_monitor_offload_ext(hdev)) { + case HCI_ADV_MONITOR_EXT_NONE: + hci_update_background_scan(hdev); + bt_dev_dbg(hdev, "%s add monitor status %d", hdev->name, *err); + /* Message was not forwarded to controller - not an error */ + return false; + case HCI_ADV_MONITOR_EXT_MSFT: + *err = msft_add_monitor_pattern(hdev, monitor); + bt_dev_dbg(hdev, "%s add monitor msft status %d", hdev->name, + *err); + break; + } + + return (*err == 0); } -static int free_adv_monitor(int id, void *ptr, void *data) +/* Attempts to tell the controller and free the monitor. If somehow the + * controller doesn't have a corresponding handle, remove anyway. + * Returns true if request is forwarded (result is pending), false otherwise. + * This function requires the caller holds hdev->lock. + */ +static bool hci_remove_adv_monitor(struct hci_dev *hdev, + struct adv_monitor *monitor, + u16 handle, int *err) { - struct hci_dev *hdev = data; - struct adv_monitor *monitor = ptr; + *err = 0; - idr_remove(&hdev->adv_monitors_idr, monitor->handle); - hci_free_adv_monitor(monitor); - hdev->adv_monitors_cnt--; + switch (hci_get_adv_monitor_offload_ext(hdev)) { + case HCI_ADV_MONITOR_EXT_NONE: /* also goes here when powered off */ + goto free_monitor; + case HCI_ADV_MONITOR_EXT_MSFT: + *err = msft_remove_monitor(hdev, monitor, handle); + break; + } - return 0; + /* In case no matching handle registered, just free the monitor */ + if (*err == -ENOENT) + goto free_monitor; + + return (*err == 0); + +free_monitor: + if (*err == -ENOENT) + bt_dev_warn(hdev, "Removing monitor with no matching handle %d", + monitor->handle); + hci_free_adv_monitor(hdev, monitor); + + *err = 0; + return false; } -/* This function requires the caller holds hdev->lock */ -int hci_remove_adv_monitor(struct hci_dev *hdev, u16 handle) +/* Returns true if request is forwarded (result is pending), false otherwise. + * This function requires the caller holds hdev->lock. + */ +bool hci_remove_single_adv_monitor(struct hci_dev *hdev, u16 handle, int *err) +{ + struct adv_monitor *monitor = idr_find(&hdev->adv_monitors_idr, handle); + bool pending; + + if (!monitor) { + *err = -EINVAL; + return false; + } + + pending = hci_remove_adv_monitor(hdev, monitor, handle, err); + if (!*err && !pending) + hci_update_background_scan(hdev); + + bt_dev_dbg(hdev, "%s remove monitor handle %d, status %d, %spending", + hdev->name, handle, *err, pending ? "" : "not "); + + return pending; +} + +/* Returns true if request is forwarded (result is pending), false otherwise. + * This function requires the caller holds hdev->lock. + */ +bool hci_remove_all_adv_monitor(struct hci_dev *hdev, int *err) { struct adv_monitor *monitor; + int idr_next_id = 0; + bool pending = false; + bool update = false; - if (handle) { - monitor = idr_find(&hdev->adv_monitors_idr, handle); + *err = 0; + + while (!*err && !pending) { + monitor = idr_get_next(&hdev->adv_monitors_idr, &idr_next_id); if (!monitor) - return -ENOENT; + break; - idr_remove(&hdev->adv_monitors_idr, monitor->handle); - hci_free_adv_monitor(monitor); - hdev->adv_monitors_cnt--; - } else { - /* Remove all monitors if handle is 0. */ - idr_for_each(&hdev->adv_monitors_idr, &free_adv_monitor, hdev); + pending = hci_remove_adv_monitor(hdev, monitor, 0, err); + + if (!*err && !pending) + update = true; } - hci_update_background_scan(hdev); + if (update) + hci_update_background_scan(hdev); - return 0; + bt_dev_dbg(hdev, "%s remove all monitors status %d, %spending", + hdev->name, *err, pending ? "" : "not "); + + return pending; } /* This function requires the caller holds hdev->lock */ @@ -3134,6 +3238,14 @@ bool hci_is_adv_monitoring(struct hci_dev *hdev) return !idr_is_empty(&hdev->adv_monitors_idr); } +int hci_get_adv_monitor_offload_ext(struct hci_dev *hdev) +{ + if (msft_monitor_supported(hdev)) + return HCI_ADV_MONITOR_EXT_MSFT; + + return HCI_ADV_MONITOR_EXT_NONE; +} + struct bdaddr_list *hci_bdaddr_list_lookup(struct list_head *bdaddr_list, bdaddr_t *bdaddr, u8 type) { @@ -3566,7 +3678,8 @@ static int hci_suspend_notifier(struct notifier_block *nb, unsigned long action, } /* Suspend notifier should only act on events when powered. */ - if (!hdev_is_powered(hdev)) + if (!hdev_is_powered(hdev) || + hci_dev_test_flag(hdev, HCI_UNREGISTER)) goto done; if (action == PM_SUSPEND_PREPARE) { @@ -3827,10 +3940,12 @@ int hci_register_dev(struct hci_dev *hdev) hci_sock_dev_event(hdev, HCI_DEV_REG); hci_dev_hold(hdev); - hdev->suspend_notifier.notifier_call = hci_suspend_notifier; - error = register_pm_notifier(&hdev->suspend_notifier); - if (error) - goto err_wqueue; + if (!test_bit(HCI_QUIRK_NO_SUSPEND_NOTIFIER, &hdev->quirks)) { + hdev->suspend_notifier.notifier_call = hci_suspend_notifier; + error = register_pm_notifier(&hdev->suspend_notifier); + if (error) + goto err_wqueue; + } queue_work(hdev->req_workqueue, &hdev->power_on); @@ -3865,9 +3980,11 @@ void hci_unregister_dev(struct hci_dev *hdev) cancel_work_sync(&hdev->power_on); - hci_suspend_clear_tasks(hdev); - unregister_pm_notifier(&hdev->suspend_notifier); - cancel_work_sync(&hdev->suspend_prepare); + if (!test_bit(HCI_QUIRK_NO_SUSPEND_NOTIFIER, &hdev->quirks)) { + hci_suspend_clear_tasks(hdev); + unregister_pm_notifier(&hdev->suspend_notifier); + cancel_work_sync(&hdev->suspend_prepare); + } hci_dev_do_close(hdev); diff --git a/net/bluetooth/hci_debugfs.c b/net/bluetooth/hci_debugfs.c index 4626e0289a97..1a0ab58bfad0 100644 --- a/net/bluetooth/hci_debugfs.c +++ b/net/bluetooth/hci_debugfs.c @@ -237,8 +237,8 @@ static int conn_info_min_age_get(void *data, u64 *val) return 0; } -DEFINE_SIMPLE_ATTRIBUTE(conn_info_min_age_fops, conn_info_min_age_get, - conn_info_min_age_set, "%llu\n"); +DEFINE_DEBUGFS_ATTRIBUTE(conn_info_min_age_fops, conn_info_min_age_get, + conn_info_min_age_set, "%llu\n"); static int conn_info_max_age_set(void *data, u64 val) { @@ -265,8 +265,8 @@ static int conn_info_max_age_get(void *data, u64 *val) return 0; } -DEFINE_SIMPLE_ATTRIBUTE(conn_info_max_age_fops, conn_info_max_age_get, - conn_info_max_age_set, "%llu\n"); +DEFINE_DEBUGFS_ATTRIBUTE(conn_info_max_age_fops, conn_info_max_age_get, + conn_info_max_age_set, "%llu\n"); static ssize_t use_debug_keys_read(struct file *file, char __user *user_buf, size_t count, loff_t *ppos) @@ -419,8 +419,8 @@ static int voice_setting_get(void *data, u64 *val) return 0; } -DEFINE_SIMPLE_ATTRIBUTE(voice_setting_fops, voice_setting_get, - NULL, "0x%4.4llx\n"); +DEFINE_DEBUGFS_ATTRIBUTE(voice_setting_fops, voice_setting_get, + NULL, "0x%4.4llx\n"); static ssize_t ssp_debug_mode_read(struct file *file, char __user *user_buf, size_t count, loff_t *ppos) @@ -476,9 +476,9 @@ static int min_encrypt_key_size_get(void *data, u64 *val) return 0; } -DEFINE_SIMPLE_ATTRIBUTE(min_encrypt_key_size_fops, - min_encrypt_key_size_get, - min_encrypt_key_size_set, "%llu\n"); +DEFINE_DEBUGFS_ATTRIBUTE(min_encrypt_key_size_fops, + min_encrypt_key_size_get, + min_encrypt_key_size_set, "%llu\n"); static int auto_accept_delay_get(void *data, u64 *val) { @@ -491,8 +491,8 @@ static int auto_accept_delay_get(void *data, u64 *val) return 0; } -DEFINE_SIMPLE_ATTRIBUTE(auto_accept_delay_fops, auto_accept_delay_get, - auto_accept_delay_set, "%llu\n"); +DEFINE_DEBUGFS_ATTRIBUTE(auto_accept_delay_fops, auto_accept_delay_get, + auto_accept_delay_set, "%llu\n"); static ssize_t force_bredr_smp_read(struct file *file, char __user *user_buf, @@ -558,8 +558,8 @@ static int idle_timeout_get(void *data, u64 *val) return 0; } -DEFINE_SIMPLE_ATTRIBUTE(idle_timeout_fops, idle_timeout_get, - idle_timeout_set, "%llu\n"); +DEFINE_DEBUGFS_ATTRIBUTE(idle_timeout_fops, idle_timeout_get, + idle_timeout_set, "%llu\n"); static int sniff_min_interval_set(void *data, u64 val) { @@ -586,8 +586,8 @@ static int sniff_min_interval_get(void *data, u64 *val) return 0; } -DEFINE_SIMPLE_ATTRIBUTE(sniff_min_interval_fops, sniff_min_interval_get, - sniff_min_interval_set, "%llu\n"); +DEFINE_DEBUGFS_ATTRIBUTE(sniff_min_interval_fops, sniff_min_interval_get, + sniff_min_interval_set, "%llu\n"); static int sniff_max_interval_set(void *data, u64 val) { @@ -614,8 +614,8 @@ static int sniff_max_interval_get(void *data, u64 *val) return 0; } -DEFINE_SIMPLE_ATTRIBUTE(sniff_max_interval_fops, sniff_max_interval_get, - sniff_max_interval_set, "%llu\n"); +DEFINE_DEBUGFS_ATTRIBUTE(sniff_max_interval_fops, sniff_max_interval_get, + sniff_max_interval_set, "%llu\n"); void hci_debugfs_create_bredr(struct hci_dev *hdev) { @@ -706,8 +706,8 @@ static int rpa_timeout_get(void *data, u64 *val) return 0; } -DEFINE_SIMPLE_ATTRIBUTE(rpa_timeout_fops, rpa_timeout_get, - rpa_timeout_set, "%llu\n"); +DEFINE_DEBUGFS_ATTRIBUTE(rpa_timeout_fops, rpa_timeout_get, + rpa_timeout_set, "%llu\n"); static int random_address_show(struct seq_file *f, void *p) { @@ -869,8 +869,8 @@ static int conn_min_interval_get(void *data, u64 *val) return 0; } -DEFINE_SIMPLE_ATTRIBUTE(conn_min_interval_fops, conn_min_interval_get, - conn_min_interval_set, "%llu\n"); +DEFINE_DEBUGFS_ATTRIBUTE(conn_min_interval_fops, conn_min_interval_get, + conn_min_interval_set, "%llu\n"); static int conn_max_interval_set(void *data, u64 val) { @@ -897,8 +897,8 @@ static int conn_max_interval_get(void *data, u64 *val) return 0; } -DEFINE_SIMPLE_ATTRIBUTE(conn_max_interval_fops, conn_max_interval_get, - conn_max_interval_set, "%llu\n"); +DEFINE_DEBUGFS_ATTRIBUTE(conn_max_interval_fops, conn_max_interval_get, + conn_max_interval_set, "%llu\n"); static int conn_latency_set(void *data, u64 val) { @@ -925,8 +925,8 @@ static int conn_latency_get(void *data, u64 *val) return 0; } -DEFINE_SIMPLE_ATTRIBUTE(conn_latency_fops, conn_latency_get, - conn_latency_set, "%llu\n"); +DEFINE_DEBUGFS_ATTRIBUTE(conn_latency_fops, conn_latency_get, + conn_latency_set, "%llu\n"); static int supervision_timeout_set(void *data, u64 val) { @@ -953,8 +953,8 @@ static int supervision_timeout_get(void *data, u64 *val) return 0; } -DEFINE_SIMPLE_ATTRIBUTE(supervision_timeout_fops, supervision_timeout_get, - supervision_timeout_set, "%llu\n"); +DEFINE_DEBUGFS_ATTRIBUTE(supervision_timeout_fops, supervision_timeout_get, + supervision_timeout_set, "%llu\n"); static int adv_channel_map_set(void *data, u64 val) { @@ -981,8 +981,8 @@ static int adv_channel_map_get(void *data, u64 *val) return 0; } -DEFINE_SIMPLE_ATTRIBUTE(adv_channel_map_fops, adv_channel_map_get, - adv_channel_map_set, "%llu\n"); +DEFINE_DEBUGFS_ATTRIBUTE(adv_channel_map_fops, adv_channel_map_get, + adv_channel_map_set, "%llu\n"); static int adv_min_interval_set(void *data, u64 val) { @@ -1009,8 +1009,8 @@ static int adv_min_interval_get(void *data, u64 *val) return 0; } -DEFINE_SIMPLE_ATTRIBUTE(adv_min_interval_fops, adv_min_interval_get, - adv_min_interval_set, "%llu\n"); +DEFINE_DEBUGFS_ATTRIBUTE(adv_min_interval_fops, adv_min_interval_get, + adv_min_interval_set, "%llu\n"); static int adv_max_interval_set(void *data, u64 val) { @@ -1037,8 +1037,8 @@ static int adv_max_interval_get(void *data, u64 *val) return 0; } -DEFINE_SIMPLE_ATTRIBUTE(adv_max_interval_fops, adv_max_interval_get, - adv_max_interval_set, "%llu\n"); +DEFINE_DEBUGFS_ATTRIBUTE(adv_max_interval_fops, adv_max_interval_get, + adv_max_interval_set, "%llu\n"); static int min_key_size_set(void *data, u64 val) { @@ -1065,8 +1065,8 @@ static int min_key_size_get(void *data, u64 *val) return 0; } -DEFINE_SIMPLE_ATTRIBUTE(min_key_size_fops, min_key_size_get, - min_key_size_set, "%llu\n"); +DEFINE_DEBUGFS_ATTRIBUTE(min_key_size_fops, min_key_size_get, + min_key_size_set, "%llu\n"); static int max_key_size_set(void *data, u64 val) { @@ -1093,8 +1093,8 @@ static int max_key_size_get(void *data, u64 *val) return 0; } -DEFINE_SIMPLE_ATTRIBUTE(max_key_size_fops, max_key_size_get, - max_key_size_set, "%llu\n"); +DEFINE_DEBUGFS_ATTRIBUTE(max_key_size_fops, max_key_size_get, + max_key_size_set, "%llu\n"); static int auth_payload_timeout_set(void *data, u64 val) { @@ -1121,9 +1121,9 @@ static int auth_payload_timeout_get(void *data, u64 *val) return 0; } -DEFINE_SIMPLE_ATTRIBUTE(auth_payload_timeout_fops, - auth_payload_timeout_get, - auth_payload_timeout_set, "%llu\n"); +DEFINE_DEBUGFS_ATTRIBUTE(auth_payload_timeout_fops, + auth_payload_timeout_get, + auth_payload_timeout_set, "%llu\n"); static ssize_t force_no_mitm_read(struct file *file, char __user *user_buf, diff --git a/net/bluetooth/hci_request.c b/net/bluetooth/hci_request.c index 71bffd745472..e55976db4403 100644 --- a/net/bluetooth/hci_request.c +++ b/net/bluetooth/hci_request.c @@ -29,6 +29,7 @@ #include "smp.h" #include "hci_request.h" +#include "msft.h" #define HCI_REQ_DONE 0 #define HCI_REQ_PEND 1 @@ -404,13 +405,18 @@ static void cancel_interleave_scan(struct hci_dev *hdev) */ static bool __hci_update_interleaved_scan(struct hci_dev *hdev) { - /* If there is at least one ADV monitors and one pending LE connection - * or one device to be scanned for, we should alternate between - * allowlist scan and one without any filters to save power. + /* Do interleaved scan only if all of the following are true: + * - There is at least one ADV monitor + * - At least one pending LE connection or one device to be scanned for + * - Monitor offloading is not supported + * If so, we should alternate between allowlist scan and one without + * any filters to save power. */ bool use_interleaving = hci_is_adv_monitoring(hdev) && !(list_empty(&hdev->pend_le_conns) && - list_empty(&hdev->pend_le_reports)); + list_empty(&hdev->pend_le_reports)) && + hci_get_adv_monitor_offload_ext(hdev) == + HCI_ADV_MONITOR_EXT_NONE; bool is_interleaving = is_interleave_scanning(hdev); if (use_interleaving && !is_interleaving) { @@ -899,14 +905,11 @@ static u8 update_white_list(struct hci_request *req) /* Use the allowlist unless the following conditions are all true: * - We are not currently suspending - * - There are 1 or more ADV monitors registered + * - There are 1 or more ADV monitors registered and it's not offloaded * - Interleaved scanning is not currently using the allowlist - * - * Once the controller offloading of advertisement monitor is in place, - * the above condition should include the support of MSFT extension - * support. */ if (!idr_is_empty(&hdev->adv_monitors_idr) && !hdev->suspended && + hci_get_adv_monitor_offload_ext(hdev) == HCI_ADV_MONITOR_EXT_NONE && hdev->interleave_scan_state != INTERLEAVE_SCAN_ALLOWLIST) return 0x00; @@ -1087,6 +1090,8 @@ void hci_req_add_le_passive_scan(struct hci_request *req) if (hdev->suspended) { window = hdev->le_scan_window_suspend; interval = hdev->le_scan_int_suspend; + + set_bit(SUSPEND_SCAN_ENABLE, hdev->suspend_tasks); } else if (hci_is_le_conn_scanning(hdev)) { window = hdev->le_scan_window_connect; interval = hdev->le_scan_int_connect; @@ -1170,19 +1175,6 @@ static void hci_req_set_event_filter(struct hci_request *req) hci_req_add(req, HCI_OP_WRITE_SCAN_ENABLE, 1, &scan); } -static void hci_req_config_le_suspend_scan(struct hci_request *req) -{ - /* Before changing params disable scan if enabled */ - if (hci_dev_test_flag(req->hdev, HCI_LE_SCAN)) - hci_req_add_le_scan_disable(req, false); - - /* Configure params and enable scanning */ - hci_req_add_le_passive_scan(req); - - /* Block suspend notifier on response */ - set_bit(SUSPEND_SCAN_ENABLE, req->hdev->suspend_tasks); -} - static void cancel_adv_timeout(struct hci_dev *hdev) { if (hdev->adv_instance_timeout) { @@ -1245,12 +1237,37 @@ static void suspend_req_complete(struct hci_dev *hdev, u8 status, u16 opcode) { bt_dev_dbg(hdev, "Request complete opcode=0x%x, status=0x%x", opcode, status); - if (test_and_clear_bit(SUSPEND_SCAN_ENABLE, hdev->suspend_tasks) || - test_and_clear_bit(SUSPEND_SCAN_DISABLE, hdev->suspend_tasks)) { + if (test_bit(SUSPEND_SCAN_ENABLE, hdev->suspend_tasks) || + test_bit(SUSPEND_SCAN_DISABLE, hdev->suspend_tasks)) { + clear_bit(SUSPEND_SCAN_ENABLE, hdev->suspend_tasks); + clear_bit(SUSPEND_SCAN_DISABLE, hdev->suspend_tasks); + wake_up(&hdev->suspend_wait_q); + } + + if (test_bit(SUSPEND_SET_ADV_FILTER, hdev->suspend_tasks)) { + clear_bit(SUSPEND_SET_ADV_FILTER, hdev->suspend_tasks); wake_up(&hdev->suspend_wait_q); } } +static void hci_req_add_set_adv_filter_enable(struct hci_request *req, + bool enable) +{ + struct hci_dev *hdev = req->hdev; + + switch (hci_get_adv_monitor_offload_ext(hdev)) { + case HCI_ADV_MONITOR_EXT_MSFT: + msft_req_add_set_filter_enable(req, enable); + break; + default: + return; + } + + /* No need to block when enabling since it's on resume path */ + if (hdev->suspended && !enable) + set_bit(SUSPEND_SET_ADV_FILTER, hdev->suspend_tasks); +} + /* Call with hci_dev_lock */ void hci_req_prepare_suspend(struct hci_dev *hdev, enum suspended_state next) { @@ -1308,6 +1325,9 @@ void hci_req_prepare_suspend(struct hci_dev *hdev, enum suspended_state next) hci_req_add_le_scan_disable(&req, false); } + /* Disable advertisement filters */ + hci_req_add_set_adv_filter_enable(&req, false); + /* Mark task needing completion */ set_bit(SUSPEND_SCAN_DISABLE, hdev->suspend_tasks); @@ -1336,7 +1356,7 @@ void hci_req_prepare_suspend(struct hci_dev *hdev, enum suspended_state next) /* Enable event filter for paired devices */ hci_req_set_event_filter(&req); /* Enable passive scan at lower duty cycle */ - hci_req_config_le_suspend_scan(&req); + __hci_update_background_scan(&req); /* Pause scan changes again. */ hdev->scanning_paused = true; hci_req_run(&req, suspend_req_complete); @@ -1346,7 +1366,9 @@ void hci_req_prepare_suspend(struct hci_dev *hdev, enum suspended_state next) hci_req_clear_event_filter(&req); /* Reset passive/background scanning to normal */ - hci_req_config_le_suspend_scan(&req); + __hci_update_background_scan(&req); + /* Enable all of the advertisement filters */ + hci_req_add_set_adv_filter_enable(&req, true); /* Unpause directed advertising */ hdev->advertising_paused = false; diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c index 17b87b57a175..72c2f5226d67 100644 --- a/net/bluetooth/l2cap_core.c +++ b/net/bluetooth/l2cap_core.c @@ -4519,6 +4519,7 @@ static inline int l2cap_config_rsp(struct l2cap_conn *conn, } goto done; + case L2CAP_CONF_UNKNOWN: case L2CAP_CONF_UNACCEPT: if (chan->num_conf_rsp <= L2CAP_CONF_MAX_CONF_RSP) { char req[64]; @@ -8276,10 +8277,73 @@ static void l2cap_security_cfm(struct hci_conn *hcon, u8 status, u8 encrypt) mutex_unlock(&conn->chan_lock); } +/* Append fragment into frame respecting the maximum len of rx_skb */ +static int l2cap_recv_frag(struct l2cap_conn *conn, struct sk_buff *skb, + u16 len) +{ + if (!conn->rx_skb) { + /* Allocate skb for the complete frame (with header) */ + conn->rx_skb = bt_skb_alloc(len, GFP_KERNEL); + if (!conn->rx_skb) + return -ENOMEM; + /* Init rx_len */ + conn->rx_len = len; + } + + /* Copy as much as the rx_skb can hold */ + len = min_t(u16, len, skb->len); + skb_copy_from_linear_data(skb, skb_put(conn->rx_skb, len), len); + skb_pull(skb, len); + conn->rx_len -= len; + + return len; +} + +static int l2cap_recv_len(struct l2cap_conn *conn, struct sk_buff *skb) +{ + struct sk_buff *rx_skb; + int len; + + /* Append just enough to complete the header */ + len = l2cap_recv_frag(conn, skb, L2CAP_LEN_SIZE - conn->rx_skb->len); + + /* If header could not be read just continue */ + if (len < 0 || conn->rx_skb->len < L2CAP_LEN_SIZE) + return len; + + rx_skb = conn->rx_skb; + len = get_unaligned_le16(rx_skb->data); + + /* Check if rx_skb has enough space to received all fragments */ + if (len + (L2CAP_HDR_SIZE - L2CAP_LEN_SIZE) <= skb_tailroom(rx_skb)) { + /* Update expected len */ + conn->rx_len = len + (L2CAP_HDR_SIZE - L2CAP_LEN_SIZE); + return L2CAP_LEN_SIZE; + } + + /* Reset conn->rx_skb since it will need to be reallocated in order to + * fit all fragments. + */ + conn->rx_skb = NULL; + + /* Reallocates rx_skb using the exact expected length */ + len = l2cap_recv_frag(conn, rx_skb, + len + (L2CAP_HDR_SIZE - L2CAP_LEN_SIZE)); + kfree_skb(rx_skb); + + return len; +} + +static void l2cap_recv_reset(struct l2cap_conn *conn) +{ + kfree_skb(conn->rx_skb); + conn->rx_skb = NULL; + conn->rx_len = 0; +} + void l2cap_recv_acldata(struct hci_conn *hcon, struct sk_buff *skb, u16 flags) { struct l2cap_conn *conn = hcon->l2cap_data; - struct l2cap_hdr *hdr; int len; /* For AMP controller do not create l2cap conn */ @@ -8298,23 +8362,23 @@ void l2cap_recv_acldata(struct hci_conn *hcon, struct sk_buff *skb, u16 flags) case ACL_START: case ACL_START_NO_FLUSH: case ACL_COMPLETE: - if (conn->rx_len) { + if (conn->rx_skb) { BT_ERR("Unexpected start frame (len %d)", skb->len); - kfree_skb(conn->rx_skb); - conn->rx_skb = NULL; - conn->rx_len = 0; + l2cap_recv_reset(conn); l2cap_conn_unreliable(conn, ECOMM); } - /* Start fragment always begin with Basic L2CAP header */ - if (skb->len < L2CAP_HDR_SIZE) { - BT_ERR("Frame is too short (len %d)", skb->len); - l2cap_conn_unreliable(conn, ECOMM); - goto drop; + /* Start fragment may not contain the L2CAP length so just + * copy the initial byte when that happens and use conn->mtu as + * expected length. + */ + if (skb->len < L2CAP_LEN_SIZE) { + if (l2cap_recv_frag(conn, skb, conn->mtu) < 0) + goto drop; + return; } - hdr = (struct l2cap_hdr *) skb->data; - len = __le16_to_cpu(hdr->len) + L2CAP_HDR_SIZE; + len = get_unaligned_le16(skb->data) + L2CAP_HDR_SIZE; if (len == skb->len) { /* Complete frame received */ @@ -8331,38 +8395,43 @@ void l2cap_recv_acldata(struct hci_conn *hcon, struct sk_buff *skb, u16 flags) goto drop; } - /* Allocate skb for the complete frame (with header) */ - conn->rx_skb = bt_skb_alloc(len, GFP_KERNEL); - if (!conn->rx_skb) + /* Append fragment into frame (with header) */ + if (l2cap_recv_frag(conn, skb, len) < 0) goto drop; - skb_copy_from_linear_data(skb, skb_put(conn->rx_skb, skb->len), - skb->len); - conn->rx_len = len - skb->len; break; case ACL_CONT: BT_DBG("Cont: frag len %d (expecting %d)", skb->len, conn->rx_len); - if (!conn->rx_len) { + if (!conn->rx_skb) { BT_ERR("Unexpected continuation frame (len %d)", skb->len); l2cap_conn_unreliable(conn, ECOMM); goto drop; } + /* Complete the L2CAP length if it has not been read */ + if (conn->rx_skb->len < L2CAP_LEN_SIZE) { + if (l2cap_recv_len(conn, skb) < 0) { + l2cap_conn_unreliable(conn, ECOMM); + goto drop; + } + + /* Header still could not be read just continue */ + if (conn->rx_skb->len < L2CAP_LEN_SIZE) + return; + } + if (skb->len > conn->rx_len) { BT_ERR("Fragment is too long (len %d, expected %d)", skb->len, conn->rx_len); - kfree_skb(conn->rx_skb); - conn->rx_skb = NULL; - conn->rx_len = 0; + l2cap_recv_reset(conn); l2cap_conn_unreliable(conn, ECOMM); goto drop; } - skb_copy_from_linear_data(skb, skb_put(conn->rx_skb, skb->len), - skb->len); - conn->rx_len -= skb->len; + /* Append fragment into frame (with header) */ + l2cap_recv_frag(conn, skb, skb->len); if (!conn->rx_len) { /* Complete frame received. l2cap_recv_frame diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c index fa0f7a4a1d2f..74971b4bd457 100644 --- a/net/bluetooth/mgmt.c +++ b/net/bluetooth/mgmt.c @@ -124,6 +124,7 @@ static const u16 mgmt_commands[] = { MGMT_OP_REMOVE_ADV_MONITOR, MGMT_OP_ADD_EXT_ADV_PARAMS, MGMT_OP_ADD_EXT_ADV_DATA, + MGMT_OP_ADD_ADV_PATTERNS_MONITOR_RSSI, }; static const u16 mgmt_events[] = { @@ -4166,14 +4167,24 @@ static void mgmt_adv_monitor_added(struct sock *sk, struct hci_dev *hdev, mgmt_event(MGMT_EV_ADV_MONITOR_ADDED, hdev, &ev, sizeof(ev), sk); } -static void mgmt_adv_monitor_removed(struct sock *sk, struct hci_dev *hdev, - u16 handle) +void mgmt_adv_monitor_removed(struct hci_dev *hdev, u16 handle) { - struct mgmt_ev_adv_monitor_added ev; + struct mgmt_ev_adv_monitor_removed ev; + struct mgmt_pending_cmd *cmd; + struct sock *sk_skip = NULL; + struct mgmt_cp_remove_adv_monitor *cp; + + cmd = pending_find(MGMT_OP_REMOVE_ADV_MONITOR, hdev); + if (cmd) { + cp = cmd->param; + + if (cp->monitor_handle) + sk_skip = cmd->sk; + } ev.monitor_handle = cpu_to_le16(handle); - mgmt_event(MGMT_EV_ADV_MONITOR_REMOVED, hdev, &ev, sizeof(ev), sk); + mgmt_event(MGMT_EV_ADV_MONITOR_REMOVED, hdev, &ev, sizeof(ev), sk_skip); } static int read_adv_mon_features(struct sock *sk, struct hci_dev *hdev, @@ -4184,6 +4195,7 @@ static int read_adv_mon_features(struct sock *sk, struct hci_dev *hdev, int handle, err; size_t rp_size = 0; __u32 supported = 0; + __u32 enabled = 0; __u16 num_handles = 0; __u16 handles[HCI_MAX_ADV_MONITOR_NUM_HANDLES]; @@ -4191,12 +4203,11 @@ static int read_adv_mon_features(struct sock *sk, struct hci_dev *hdev, hci_dev_lock(hdev); - if (msft_get_features(hdev) & MSFT_FEATURE_MASK_LE_ADV_MONITOR) + if (msft_monitor_supported(hdev)) supported |= MGMT_ADV_MONITOR_FEATURE_MASK_OR_PATTERNS; - idr_for_each_entry(&hdev->adv_monitors_idr, monitor, handle) { + idr_for_each_entry(&hdev->adv_monitors_idr, monitor, handle) handles[num_handles++] = monitor->handle; - } hci_dev_unlock(hdev); @@ -4205,11 +4216,11 @@ static int read_adv_mon_features(struct sock *sk, struct hci_dev *hdev, if (!rp) return -ENOMEM; - /* Once controller-based monitoring is in place, the enabled_features - * should reflect the use. - */ + /* All supported features are currently enabled */ + enabled = supported; + rp->supported_features = cpu_to_le32(supported); - rp->enabled_features = 0; + rp->enabled_features = cpu_to_le32(enabled); rp->max_num_handles = cpu_to_le16(HCI_MAX_ADV_MONITOR_NUM_HANDLES); rp->max_num_patterns = HCI_MAX_ADV_MONITOR_NUM_PATTERNS; rp->num_handles = cpu_to_le16(num_handles); @@ -4225,105 +4236,267 @@ static int read_adv_mon_features(struct sock *sk, struct hci_dev *hdev, return err; } +int mgmt_add_adv_patterns_monitor_complete(struct hci_dev *hdev, u8 status) +{ + struct mgmt_rp_add_adv_patterns_monitor rp; + struct mgmt_pending_cmd *cmd; + struct adv_monitor *monitor; + int err = 0; + + hci_dev_lock(hdev); + + cmd = pending_find(MGMT_OP_ADD_ADV_PATTERNS_MONITOR_RSSI, hdev); + if (!cmd) { + cmd = pending_find(MGMT_OP_ADD_ADV_PATTERNS_MONITOR, hdev); + if (!cmd) + goto done; + } + + monitor = cmd->user_data; + rp.monitor_handle = cpu_to_le16(monitor->handle); + + if (!status) { + mgmt_adv_monitor_added(cmd->sk, hdev, monitor->handle); + hdev->adv_monitors_cnt++; + if (monitor->state == ADV_MONITOR_STATE_NOT_REGISTERED) + monitor->state = ADV_MONITOR_STATE_REGISTERED; + hci_update_background_scan(hdev); + } + + err = mgmt_cmd_complete(cmd->sk, cmd->index, cmd->opcode, + mgmt_status(status), &rp, sizeof(rp)); + mgmt_pending_remove(cmd); + +done: + hci_dev_unlock(hdev); + bt_dev_dbg(hdev, "add monitor %d complete, status %d", + rp.monitor_handle, status); + + return err; +} + +static int __add_adv_patterns_monitor(struct sock *sk, struct hci_dev *hdev, + struct adv_monitor *m, u8 status, + void *data, u16 len, u16 op) +{ + struct mgmt_rp_add_adv_patterns_monitor rp; + struct mgmt_pending_cmd *cmd; + int err; + bool pending; + + hci_dev_lock(hdev); + + if (status) + goto unlock; + + if (pending_find(MGMT_OP_SET_LE, hdev) || + pending_find(MGMT_OP_ADD_ADV_PATTERNS_MONITOR, hdev) || + pending_find(MGMT_OP_ADD_ADV_PATTERNS_MONITOR_RSSI, hdev) || + pending_find(MGMT_OP_REMOVE_ADV_MONITOR, hdev)) { + status = MGMT_STATUS_BUSY; + goto unlock; + } + + cmd = mgmt_pending_add(sk, op, hdev, data, len); + if (!cmd) { + status = MGMT_STATUS_NO_RESOURCES; + goto unlock; + } + + cmd->user_data = m; + pending = hci_add_adv_monitor(hdev, m, &err); + if (err) { + if (err == -ENOSPC || err == -ENOMEM) + status = MGMT_STATUS_NO_RESOURCES; + else if (err == -EINVAL) + status = MGMT_STATUS_INVALID_PARAMS; + else + status = MGMT_STATUS_FAILED; + + mgmt_pending_remove(cmd); + goto unlock; + } + + if (!pending) { + mgmt_pending_remove(cmd); + rp.monitor_handle = cpu_to_le16(m->handle); + mgmt_adv_monitor_added(sk, hdev, m->handle); + m->state = ADV_MONITOR_STATE_REGISTERED; + hdev->adv_monitors_cnt++; + + hci_dev_unlock(hdev); + return mgmt_cmd_complete(sk, hdev->id, op, MGMT_STATUS_SUCCESS, + &rp, sizeof(rp)); + } + + hci_dev_unlock(hdev); + + return 0; + +unlock: + hci_free_adv_monitor(hdev, m); + hci_dev_unlock(hdev); + return mgmt_cmd_status(sk, hdev->id, op, status); +} + +static void parse_adv_monitor_rssi(struct adv_monitor *m, + struct mgmt_adv_rssi_thresholds *rssi) +{ + if (rssi) { + m->rssi.low_threshold = rssi->low_threshold; + m->rssi.low_threshold_timeout = + __le16_to_cpu(rssi->low_threshold_timeout); + m->rssi.high_threshold = rssi->high_threshold; + m->rssi.high_threshold_timeout = + __le16_to_cpu(rssi->high_threshold_timeout); + m->rssi.sampling_period = rssi->sampling_period; + } else { + /* Default values. These numbers are the least constricting + * parameters for MSFT API to work, so it behaves as if there + * are no rssi parameter to consider. May need to be changed + * if other API are to be supported. + */ + m->rssi.low_threshold = -127; + m->rssi.low_threshold_timeout = 60; + m->rssi.high_threshold = -127; + m->rssi.high_threshold_timeout = 0; + m->rssi.sampling_period = 0; + } +} + +static u8 parse_adv_monitor_pattern(struct adv_monitor *m, u8 pattern_count, + struct mgmt_adv_pattern *patterns) +{ + u8 offset = 0, length = 0; + struct adv_pattern *p = NULL; + int i; + + for (i = 0; i < pattern_count; i++) { + offset = patterns[i].offset; + length = patterns[i].length; + if (offset >= HCI_MAX_AD_LENGTH || + length > HCI_MAX_AD_LENGTH || + (offset + length) > HCI_MAX_AD_LENGTH) + return MGMT_STATUS_INVALID_PARAMS; + + p = kmalloc(sizeof(*p), GFP_KERNEL); + if (!p) + return MGMT_STATUS_NO_RESOURCES; + + p->ad_type = patterns[i].ad_type; + p->offset = patterns[i].offset; + p->length = patterns[i].length; + memcpy(p->value, patterns[i].value, p->length); + + INIT_LIST_HEAD(&p->list); + list_add(&p->list, &m->patterns); + } + + return MGMT_STATUS_SUCCESS; +} + static int add_adv_patterns_monitor(struct sock *sk, struct hci_dev *hdev, void *data, u16 len) { struct mgmt_cp_add_adv_patterns_monitor *cp = data; - struct mgmt_rp_add_adv_patterns_monitor rp; struct adv_monitor *m = NULL; - struct adv_pattern *p = NULL; - unsigned int mp_cnt = 0, prev_adv_monitors_cnt; - __u8 cp_ofst = 0, cp_len = 0; - int err, i; + u8 status = MGMT_STATUS_SUCCESS; + size_t expected_size = sizeof(*cp); BT_DBG("request for %s", hdev->name); - if (len <= sizeof(*cp) || cp->pattern_count == 0) { - err = mgmt_cmd_status(sk, hdev->id, - MGMT_OP_ADD_ADV_PATTERNS_MONITOR, - MGMT_STATUS_INVALID_PARAMS); - goto failed; + if (len <= sizeof(*cp)) { + status = MGMT_STATUS_INVALID_PARAMS; + goto done; } - m = kmalloc(sizeof(*m), GFP_KERNEL); + expected_size += cp->pattern_count * sizeof(struct mgmt_adv_pattern); + if (len != expected_size) { + status = MGMT_STATUS_INVALID_PARAMS; + goto done; + } + + m = kzalloc(sizeof(*m), GFP_KERNEL); if (!m) { - err = -ENOMEM; - goto failed; + status = MGMT_STATUS_NO_RESOURCES; + goto done; } INIT_LIST_HEAD(&m->patterns); - m->active = false; - for (i = 0; i < cp->pattern_count; i++) { - if (++mp_cnt > HCI_MAX_ADV_MONITOR_NUM_PATTERNS) { - err = mgmt_cmd_status(sk, hdev->id, - MGMT_OP_ADD_ADV_PATTERNS_MONITOR, - MGMT_STATUS_INVALID_PARAMS); - goto failed; - } + parse_adv_monitor_rssi(m, NULL); + status = parse_adv_monitor_pattern(m, cp->pattern_count, cp->patterns); - cp_ofst = cp->patterns[i].offset; - cp_len = cp->patterns[i].length; - if (cp_ofst >= HCI_MAX_AD_LENGTH || - cp_len > HCI_MAX_AD_LENGTH || - (cp_ofst + cp_len) > HCI_MAX_AD_LENGTH) { - err = mgmt_cmd_status(sk, hdev->id, - MGMT_OP_ADD_ADV_PATTERNS_MONITOR, - MGMT_STATUS_INVALID_PARAMS); - goto failed; - } +done: + return __add_adv_patterns_monitor(sk, hdev, m, status, data, len, + MGMT_OP_ADD_ADV_PATTERNS_MONITOR); +} - p = kmalloc(sizeof(*p), GFP_KERNEL); - if (!p) { - err = -ENOMEM; - goto failed; - } +static int add_adv_patterns_monitor_rssi(struct sock *sk, struct hci_dev *hdev, + void *data, u16 len) +{ + struct mgmt_cp_add_adv_patterns_monitor_rssi *cp = data; + struct adv_monitor *m = NULL; + u8 status = MGMT_STATUS_SUCCESS; + size_t expected_size = sizeof(*cp); - p->ad_type = cp->patterns[i].ad_type; - p->offset = cp->patterns[i].offset; - p->length = cp->patterns[i].length; - memcpy(p->value, cp->patterns[i].value, p->length); + BT_DBG("request for %s", hdev->name); - INIT_LIST_HEAD(&p->list); - list_add(&p->list, &m->patterns); + if (len <= sizeof(*cp)) { + status = MGMT_STATUS_INVALID_PARAMS; + goto done; } - if (mp_cnt != cp->pattern_count) { - err = mgmt_cmd_status(sk, hdev->id, - MGMT_OP_ADD_ADV_PATTERNS_MONITOR, - MGMT_STATUS_INVALID_PARAMS); - goto failed; + expected_size += cp->pattern_count * sizeof(struct mgmt_adv_pattern); + if (len != expected_size) { + status = MGMT_STATUS_INVALID_PARAMS; + goto done; } - hci_dev_lock(hdev); + m = kzalloc(sizeof(*m), GFP_KERNEL); + if (!m) { + status = MGMT_STATUS_NO_RESOURCES; + goto done; + } - prev_adv_monitors_cnt = hdev->adv_monitors_cnt; + INIT_LIST_HEAD(&m->patterns); - err = hci_add_adv_monitor(hdev, m); - if (err) { - if (err == -ENOSPC) { - mgmt_cmd_status(sk, hdev->id, - MGMT_OP_ADD_ADV_PATTERNS_MONITOR, - MGMT_STATUS_NO_RESOURCES); - } - goto unlock; - } + parse_adv_monitor_rssi(m, &cp->rssi); + status = parse_adv_monitor_pattern(m, cp->pattern_count, cp->patterns); - if (hdev->adv_monitors_cnt > prev_adv_monitors_cnt) - mgmt_adv_monitor_added(sk, hdev, m->handle); +done: + return __add_adv_patterns_monitor(sk, hdev, m, status, data, len, + MGMT_OP_ADD_ADV_PATTERNS_MONITOR_RSSI); +} - hci_dev_unlock(hdev); +int mgmt_remove_adv_monitor_complete(struct hci_dev *hdev, u8 status) +{ + struct mgmt_rp_remove_adv_monitor rp; + struct mgmt_cp_remove_adv_monitor *cp; + struct mgmt_pending_cmd *cmd; + int err = 0; - rp.monitor_handle = cpu_to_le16(m->handle); + hci_dev_lock(hdev); - return mgmt_cmd_complete(sk, hdev->id, MGMT_OP_ADD_ADV_PATTERNS_MONITOR, - MGMT_STATUS_SUCCESS, &rp, sizeof(rp)); + cmd = pending_find(MGMT_OP_REMOVE_ADV_MONITOR, hdev); + if (!cmd) + goto done; -unlock: + cp = cmd->param; + rp.monitor_handle = cp->monitor_handle; + + if (!status) + hci_update_background_scan(hdev); + + err = mgmt_cmd_complete(cmd->sk, cmd->index, cmd->opcode, + mgmt_status(status), &rp, sizeof(rp)); + mgmt_pending_remove(cmd); + +done: hci_dev_unlock(hdev); + bt_dev_dbg(hdev, "remove monitor %d complete, status %d", + rp.monitor_handle, status); -failed: - hci_free_adv_monitor(m); return err; } @@ -4332,37 +4505,64 @@ static int remove_adv_monitor(struct sock *sk, struct hci_dev *hdev, { struct mgmt_cp_remove_adv_monitor *cp = data; struct mgmt_rp_remove_adv_monitor rp; - unsigned int prev_adv_monitors_cnt; - u16 handle; - int err; + struct mgmt_pending_cmd *cmd; + u16 handle = __le16_to_cpu(cp->monitor_handle); + int err, status; + bool pending; BT_DBG("request for %s", hdev->name); + rp.monitor_handle = cp->monitor_handle; hci_dev_lock(hdev); - handle = __le16_to_cpu(cp->monitor_handle); - prev_adv_monitors_cnt = hdev->adv_monitors_cnt; + if (pending_find(MGMT_OP_SET_LE, hdev) || + pending_find(MGMT_OP_REMOVE_ADV_MONITOR, hdev) || + pending_find(MGMT_OP_ADD_ADV_PATTERNS_MONITOR, hdev) || + pending_find(MGMT_OP_ADD_ADV_PATTERNS_MONITOR_RSSI, hdev)) { + status = MGMT_STATUS_BUSY; + goto unlock; + } - err = hci_remove_adv_monitor(hdev, handle); - if (err == -ENOENT) { - err = mgmt_cmd_status(sk, hdev->id, MGMT_OP_REMOVE_ADV_MONITOR, - MGMT_STATUS_INVALID_INDEX); + cmd = mgmt_pending_add(sk, MGMT_OP_REMOVE_ADV_MONITOR, hdev, data, len); + if (!cmd) { + status = MGMT_STATUS_NO_RESOURCES; goto unlock; } - if (hdev->adv_monitors_cnt < prev_adv_monitors_cnt) - mgmt_adv_monitor_removed(sk, hdev, handle); + if (handle) + pending = hci_remove_single_adv_monitor(hdev, handle, &err); + else + pending = hci_remove_all_adv_monitor(hdev, &err); - hci_dev_unlock(hdev); + if (err) { + mgmt_pending_remove(cmd); - rp.monitor_handle = cp->monitor_handle; + if (err == -ENOENT) + status = MGMT_STATUS_INVALID_INDEX; + else + status = MGMT_STATUS_FAILED; - return mgmt_cmd_complete(sk, hdev->id, MGMT_OP_REMOVE_ADV_MONITOR, - MGMT_STATUS_SUCCESS, &rp, sizeof(rp)); + goto unlock; + } + + /* monitor can be removed without forwarding request to controller */ + if (!pending) { + mgmt_pending_remove(cmd); + hci_dev_unlock(hdev); + + return mgmt_cmd_complete(sk, hdev->id, + MGMT_OP_REMOVE_ADV_MONITOR, + MGMT_STATUS_SUCCESS, + &rp, sizeof(rp)); + } + + hci_dev_unlock(hdev); + return 0; unlock: hci_dev_unlock(hdev); - return err; + return mgmt_cmd_status(sk, hdev->id, MGMT_OP_REMOVE_ADV_MONITOR, + status); } static void read_local_oob_data_complete(struct hci_dev *hdev, u8 status, @@ -4798,6 +4998,14 @@ static int start_service_discovery(struct sock *sk, struct hci_dev *hdev, goto failed; } + if (hdev->discovery_paused) { + err = mgmt_cmd_complete(sk, hdev->id, + MGMT_OP_START_SERVICE_DISCOVERY, + MGMT_STATUS_BUSY, &cp->type, + sizeof(cp->type)); + goto failed; + } + uuid_count = __le16_to_cpu(cp->uuid_count); if (uuid_count > max_uuid_count) { bt_dev_err(hdev, "service_discovery: too big uuid_count value %u", @@ -8234,6 +8442,9 @@ static const struct hci_mgmt_handler mgmt_handlers[] = { HCI_MGMT_VAR_LEN }, { add_ext_adv_data, MGMT_ADD_EXT_ADV_DATA_SIZE, HCI_MGMT_VAR_LEN }, + { add_adv_patterns_monitor_rssi, + MGMT_ADD_ADV_PATTERNS_MONITOR_RSSI_SIZE, + HCI_MGMT_VAR_LEN }, }; void mgmt_index_added(struct hci_dev *hdev) diff --git a/net/bluetooth/msft.c b/net/bluetooth/msft.c index 4b39534a14a1..47b104f318e9 100644 --- a/net/bluetooth/msft.c +++ b/net/bluetooth/msft.c @@ -5,9 +5,16 @@ #include <net/bluetooth/bluetooth.h> #include <net/bluetooth/hci_core.h> +#include <net/bluetooth/mgmt.h> +#include "hci_request.h" +#include "mgmt_util.h" #include "msft.h" +#define MSFT_RSSI_THRESHOLD_VALUE_MIN -127 +#define MSFT_RSSI_THRESHOLD_VALUE_MAX 20 +#define MSFT_RSSI_LOW_TIMEOUT_MAX 0x3C + #define MSFT_OP_READ_SUPPORTED_FEATURES 0x00 struct msft_cp_read_supported_features { __u8 sub_opcode; @@ -21,12 +28,83 @@ struct msft_rp_read_supported_features { __u8 evt_prefix[]; } __packed; +#define MSFT_OP_LE_MONITOR_ADVERTISEMENT 0x03 +#define MSFT_MONITOR_ADVERTISEMENT_TYPE_PATTERN 0x01 +struct msft_le_monitor_advertisement_pattern { + __u8 length; + __u8 data_type; + __u8 start_byte; + __u8 pattern[0]; +}; + +struct msft_le_monitor_advertisement_pattern_data { + __u8 count; + __u8 data[0]; +}; + +struct msft_cp_le_monitor_advertisement { + __u8 sub_opcode; + __s8 rssi_high; + __s8 rssi_low; + __u8 rssi_low_interval; + __u8 rssi_sampling_period; + __u8 cond_type; + __u8 data[0]; +} __packed; + +struct msft_rp_le_monitor_advertisement { + __u8 status; + __u8 sub_opcode; + __u8 handle; +} __packed; + +#define MSFT_OP_LE_CANCEL_MONITOR_ADVERTISEMENT 0x04 +struct msft_cp_le_cancel_monitor_advertisement { + __u8 sub_opcode; + __u8 handle; +} __packed; + +struct msft_rp_le_cancel_monitor_advertisement { + __u8 status; + __u8 sub_opcode; +} __packed; + +#define MSFT_OP_LE_SET_ADVERTISEMENT_FILTER_ENABLE 0x05 +struct msft_cp_le_set_advertisement_filter_enable { + __u8 sub_opcode; + __u8 enable; +} __packed; + +struct msft_rp_le_set_advertisement_filter_enable { + __u8 status; + __u8 sub_opcode; +} __packed; + +struct msft_monitor_advertisement_handle_data { + __u8 msft_handle; + __u16 mgmt_handle; + struct list_head list; +}; + struct msft_data { __u64 features; __u8 evt_prefix_len; __u8 *evt_prefix; + struct list_head handle_map; + __u16 pending_add_handle; + __u16 pending_remove_handle; + __u8 reregistering; + __u8 filter_enabled; }; +static int __msft_add_monitor_pattern(struct hci_dev *hdev, + struct adv_monitor *monitor); + +bool msft_monitor_supported(struct hci_dev *hdev) +{ + return !!(msft_get_features(hdev) & MSFT_FEATURE_MASK_LE_ADV_MONITOR); +} + static bool read_supported_features(struct hci_dev *hdev, struct msft_data *msft) { @@ -72,6 +150,35 @@ failed: return false; } +/* This function requires the caller holds hdev->lock */ +static void reregister_monitor_on_restart(struct hci_dev *hdev, int handle) +{ + struct adv_monitor *monitor; + struct msft_data *msft = hdev->msft_data; + int err; + + while (1) { + monitor = idr_get_next(&hdev->adv_monitors_idr, &handle); + if (!monitor) { + /* All monitors have been reregistered */ + msft->reregistering = false; + hci_update_background_scan(hdev); + return; + } + + msft->pending_add_handle = (u16)handle; + err = __msft_add_monitor_pattern(hdev, monitor); + + /* If success, we return and wait for monitor added callback */ + if (!err) + return; + + /* Otherwise remove the monitor and keep registering */ + hci_free_adv_monitor(hdev, monitor); + handle++; + } +} + void msft_do_open(struct hci_dev *hdev) { struct msft_data *msft; @@ -90,12 +197,21 @@ void msft_do_open(struct hci_dev *hdev) return; } + INIT_LIST_HEAD(&msft->handle_map); hdev->msft_data = msft; + + if (msft_monitor_supported(hdev)) { + msft->reregistering = true; + msft_set_filter_enable(hdev, true); + reregister_monitor_on_restart(hdev, 0); + } } void msft_do_close(struct hci_dev *hdev) { struct msft_data *msft = hdev->msft_data; + struct msft_monitor_advertisement_handle_data *handle_data, *tmp; + struct adv_monitor *monitor; if (!msft) return; @@ -104,6 +220,17 @@ void msft_do_close(struct hci_dev *hdev) hdev->msft_data = NULL; + list_for_each_entry_safe(handle_data, tmp, &msft->handle_map, list) { + monitor = idr_find(&hdev->adv_monitors_idr, + handle_data->mgmt_handle); + + if (monitor && monitor->state == ADV_MONITOR_STATE_OFFLOADED) + monitor->state = ADV_MONITOR_STATE_REGISTERED; + + list_del(&handle_data->list); + kfree(handle_data); + } + kfree(msft->evt_prefix); kfree(msft); } @@ -145,5 +272,336 @@ __u64 msft_get_features(struct hci_dev *hdev) { struct msft_data *msft = hdev->msft_data; - return msft ? msft->features : 0; + return msft ? msft->features : 0; +} + +/* is_mgmt = true matches the handle exposed to userspace via mgmt. + * is_mgmt = false matches the handle used by the msft controller. + * This function requires the caller holds hdev->lock + */ +static struct msft_monitor_advertisement_handle_data *msft_find_handle_data + (struct hci_dev *hdev, u16 handle, bool is_mgmt) +{ + struct msft_monitor_advertisement_handle_data *entry; + struct msft_data *msft = hdev->msft_data; + + list_for_each_entry(entry, &msft->handle_map, list) { + if (is_mgmt && entry->mgmt_handle == handle) + return entry; + if (!is_mgmt && entry->msft_handle == handle) + return entry; + } + + return NULL; +} + +static void msft_le_monitor_advertisement_cb(struct hci_dev *hdev, + u8 status, u16 opcode, + struct sk_buff *skb) +{ + struct msft_rp_le_monitor_advertisement *rp; + struct adv_monitor *monitor; + struct msft_monitor_advertisement_handle_data *handle_data; + struct msft_data *msft = hdev->msft_data; + + hci_dev_lock(hdev); + + monitor = idr_find(&hdev->adv_monitors_idr, msft->pending_add_handle); + if (!monitor) { + bt_dev_err(hdev, "msft add advmon: monitor %d is not found!", + msft->pending_add_handle); + status = HCI_ERROR_UNSPECIFIED; + goto unlock; + } + + if (status) + goto unlock; + + rp = (struct msft_rp_le_monitor_advertisement *)skb->data; + if (skb->len < sizeof(*rp)) { + status = HCI_ERROR_UNSPECIFIED; + goto unlock; + } + + handle_data = kmalloc(sizeof(*handle_data), GFP_KERNEL); + if (!handle_data) { + status = HCI_ERROR_UNSPECIFIED; + goto unlock; + } + + handle_data->mgmt_handle = monitor->handle; + handle_data->msft_handle = rp->handle; + INIT_LIST_HEAD(&handle_data->list); + list_add(&handle_data->list, &msft->handle_map); + + monitor->state = ADV_MONITOR_STATE_OFFLOADED; + +unlock: + if (status && monitor) + hci_free_adv_monitor(hdev, monitor); + + /* If in restart/reregister sequence, keep registering. */ + if (msft->reregistering) + reregister_monitor_on_restart(hdev, + msft->pending_add_handle + 1); + + hci_dev_unlock(hdev); + + if (!msft->reregistering) + hci_add_adv_patterns_monitor_complete(hdev, status); +} + +static void msft_le_cancel_monitor_advertisement_cb(struct hci_dev *hdev, + u8 status, u16 opcode, + struct sk_buff *skb) +{ + struct msft_cp_le_cancel_monitor_advertisement *cp; + struct msft_rp_le_cancel_monitor_advertisement *rp; + struct adv_monitor *monitor; + struct msft_monitor_advertisement_handle_data *handle_data; + struct msft_data *msft = hdev->msft_data; + int err; + bool pending; + + if (status) + goto done; + + rp = (struct msft_rp_le_cancel_monitor_advertisement *)skb->data; + if (skb->len < sizeof(*rp)) { + status = HCI_ERROR_UNSPECIFIED; + goto done; + } + + hci_dev_lock(hdev); + + cp = hci_sent_cmd_data(hdev, hdev->msft_opcode); + handle_data = msft_find_handle_data(hdev, cp->handle, false); + + if (handle_data) { + monitor = idr_find(&hdev->adv_monitors_idr, + handle_data->mgmt_handle); + if (monitor) + hci_free_adv_monitor(hdev, monitor); + + list_del(&handle_data->list); + kfree(handle_data); + } + + /* If remove all monitors is required, we need to continue the process + * here because the earlier it was paused when waiting for the + * response from controller. + */ + if (msft->pending_remove_handle == 0) { + pending = hci_remove_all_adv_monitor(hdev, &err); + if (pending) { + hci_dev_unlock(hdev); + return; + } + + if (err) + status = HCI_ERROR_UNSPECIFIED; + } + + hci_dev_unlock(hdev); + +done: + hci_remove_adv_monitor_complete(hdev, status); +} + +static void msft_le_set_advertisement_filter_enable_cb(struct hci_dev *hdev, + u8 status, u16 opcode, + struct sk_buff *skb) +{ + struct msft_cp_le_set_advertisement_filter_enable *cp; + struct msft_rp_le_set_advertisement_filter_enable *rp; + struct msft_data *msft = hdev->msft_data; + + rp = (struct msft_rp_le_set_advertisement_filter_enable *)skb->data; + if (skb->len < sizeof(*rp)) + return; + + /* Error 0x0C would be returned if the filter enabled status is + * already set to whatever we were trying to set. + * Although the default state should be disabled, some controller set + * the initial value to enabled. Because there is no way to know the + * actual initial value before sending this command, here we also treat + * error 0x0C as success. + */ + if (status != 0x00 && status != 0x0C) + return; + + hci_dev_lock(hdev); + + cp = hci_sent_cmd_data(hdev, hdev->msft_opcode); + msft->filter_enabled = cp->enable; + + if (status == 0x0C) + bt_dev_warn(hdev, "MSFT filter_enable is already %s", + cp->enable ? "on" : "off"); + + hci_dev_unlock(hdev); +} + +static bool msft_monitor_rssi_valid(struct adv_monitor *monitor) +{ + struct adv_rssi_thresholds *r = &monitor->rssi; + + if (r->high_threshold < MSFT_RSSI_THRESHOLD_VALUE_MIN || + r->high_threshold > MSFT_RSSI_THRESHOLD_VALUE_MAX || + r->low_threshold < MSFT_RSSI_THRESHOLD_VALUE_MIN || + r->low_threshold > MSFT_RSSI_THRESHOLD_VALUE_MAX) + return false; + + /* High_threshold_timeout is not supported, + * once high_threshold is reached, events are immediately reported. + */ + if (r->high_threshold_timeout != 0) + return false; + + if (r->low_threshold_timeout > MSFT_RSSI_LOW_TIMEOUT_MAX) + return false; + + /* Sampling period from 0x00 to 0xFF are all allowed */ + return true; +} + +static bool msft_monitor_pattern_valid(struct adv_monitor *monitor) +{ + return msft_monitor_rssi_valid(monitor); + /* No additional check needed for pattern-based monitor */ +} + +/* This function requires the caller holds hdev->lock */ +static int __msft_add_monitor_pattern(struct hci_dev *hdev, + struct adv_monitor *monitor) +{ + struct msft_cp_le_monitor_advertisement *cp; + struct msft_le_monitor_advertisement_pattern_data *pattern_data; + struct msft_le_monitor_advertisement_pattern *pattern; + struct adv_pattern *entry; + struct hci_request req; + struct msft_data *msft = hdev->msft_data; + size_t total_size = sizeof(*cp) + sizeof(*pattern_data); + ptrdiff_t offset = 0; + u8 pattern_count = 0; + int err = 0; + + if (!msft_monitor_pattern_valid(monitor)) + return -EINVAL; + + list_for_each_entry(entry, &monitor->patterns, list) { + pattern_count++; + total_size += sizeof(*pattern) + entry->length; + } + + cp = kmalloc(total_size, GFP_KERNEL); + if (!cp) + return -ENOMEM; + + cp->sub_opcode = MSFT_OP_LE_MONITOR_ADVERTISEMENT; + cp->rssi_high = monitor->rssi.high_threshold; + cp->rssi_low = monitor->rssi.low_threshold; + cp->rssi_low_interval = (u8)monitor->rssi.low_threshold_timeout; + cp->rssi_sampling_period = monitor->rssi.sampling_period; + + cp->cond_type = MSFT_MONITOR_ADVERTISEMENT_TYPE_PATTERN; + + pattern_data = (void *)cp->data; + pattern_data->count = pattern_count; + + list_for_each_entry(entry, &monitor->patterns, list) { + pattern = (void *)(pattern_data->data + offset); + /* the length also includes data_type and offset */ + pattern->length = entry->length + 2; + pattern->data_type = entry->ad_type; + pattern->start_byte = entry->offset; + memcpy(pattern->pattern, entry->value, entry->length); + offset += sizeof(*pattern) + entry->length; + } + + hci_req_init(&req, hdev); + hci_req_add(&req, hdev->msft_opcode, total_size, cp); + err = hci_req_run_skb(&req, msft_le_monitor_advertisement_cb); + kfree(cp); + + if (!err) + msft->pending_add_handle = monitor->handle; + + return err; +} + +/* This function requires the caller holds hdev->lock */ +int msft_add_monitor_pattern(struct hci_dev *hdev, struct adv_monitor *monitor) +{ + struct msft_data *msft = hdev->msft_data; + + if (!msft) + return -EOPNOTSUPP; + + if (msft->reregistering) + return -EBUSY; + + return __msft_add_monitor_pattern(hdev, monitor); +} + +/* This function requires the caller holds hdev->lock */ +int msft_remove_monitor(struct hci_dev *hdev, struct adv_monitor *monitor, + u16 handle) +{ + struct msft_cp_le_cancel_monitor_advertisement cp; + struct msft_monitor_advertisement_handle_data *handle_data; + struct hci_request req; + struct msft_data *msft = hdev->msft_data; + int err = 0; + + if (!msft) + return -EOPNOTSUPP; + + if (msft->reregistering) + return -EBUSY; + + handle_data = msft_find_handle_data(hdev, monitor->handle, true); + + /* If no matched handle, just remove without telling controller */ + if (!handle_data) + return -ENOENT; + + cp.sub_opcode = MSFT_OP_LE_CANCEL_MONITOR_ADVERTISEMENT; + cp.handle = handle_data->msft_handle; + + hci_req_init(&req, hdev); + hci_req_add(&req, hdev->msft_opcode, sizeof(cp), &cp); + err = hci_req_run_skb(&req, msft_le_cancel_monitor_advertisement_cb); + + if (!err) + msft->pending_remove_handle = handle; + + return err; +} + +void msft_req_add_set_filter_enable(struct hci_request *req, bool enable) +{ + struct hci_dev *hdev = req->hdev; + struct msft_cp_le_set_advertisement_filter_enable cp; + + cp.sub_opcode = MSFT_OP_LE_SET_ADVERTISEMENT_FILTER_ENABLE; + cp.enable = enable; + + hci_req_add(req, hdev->msft_opcode, sizeof(cp), &cp); +} + +int msft_set_filter_enable(struct hci_dev *hdev, bool enable) +{ + struct hci_request req; + struct msft_data *msft = hdev->msft_data; + int err; + + if (!msft) + return -EOPNOTSUPP; + + hci_req_init(&req, hdev); + msft_req_add_set_filter_enable(&req, enable); + err = hci_req_run_skb(&req, msft_le_set_advertisement_filter_enable_cb); + + return err; } diff --git a/net/bluetooth/msft.h b/net/bluetooth/msft.h index e9c478e890b8..88ed613dfa08 100644 --- a/net/bluetooth/msft.h +++ b/net/bluetooth/msft.h @@ -12,16 +12,46 @@ #if IS_ENABLED(CONFIG_BT_MSFTEXT) +bool msft_monitor_supported(struct hci_dev *hdev); void msft_do_open(struct hci_dev *hdev); void msft_do_close(struct hci_dev *hdev); void msft_vendor_evt(struct hci_dev *hdev, struct sk_buff *skb); __u64 msft_get_features(struct hci_dev *hdev); +int msft_add_monitor_pattern(struct hci_dev *hdev, struct adv_monitor *monitor); +int msft_remove_monitor(struct hci_dev *hdev, struct adv_monitor *monitor, + u16 handle); +void msft_req_add_set_filter_enable(struct hci_request *req, bool enable); +int msft_set_filter_enable(struct hci_dev *hdev, bool enable); #else +static inline bool msft_monitor_supported(struct hci_dev *hdev) +{ + return false; +} + static inline void msft_do_open(struct hci_dev *hdev) {} static inline void msft_do_close(struct hci_dev *hdev) {} static inline void msft_vendor_evt(struct hci_dev *hdev, struct sk_buff *skb) {} static inline __u64 msft_get_features(struct hci_dev *hdev) { return 0; } +static inline int msft_add_monitor_pattern(struct hci_dev *hdev, + struct adv_monitor *monitor) +{ + return -EOPNOTSUPP; +} + +static inline int msft_remove_monitor(struct hci_dev *hdev, + struct adv_monitor *monitor, + u16 handle) +{ + return -EOPNOTSUPP; +} + +static inline void msft_req_add_set_filter_enable(struct hci_request *req, + bool enable) {} +static inline int msft_set_filter_enable(struct hci_dev *hdev, bool enable) +{ + return -EOPNOTSUPP; +} #endif diff --git a/net/bluetooth/smp.c b/net/bluetooth/smp.c index c659c464f7ca..b0c1ee110eff 100644 --- a/net/bluetooth/smp.c +++ b/net/bluetooth/smp.c @@ -25,7 +25,6 @@ #include <linux/crypto.h> #include <crypto/aes.h> #include <crypto/algapi.h> -#include <crypto/b128ops.h> #include <crypto/hash.h> #include <crypto/kpp.h> @@ -425,7 +424,7 @@ static int smp_c1(const u8 k[16], SMP_DBG("p1 %16phN", p1); /* res = r XOR p1 */ - u128_xor((u128 *) res, (u128 *) r, (u128 *) p1); + crypto_xor_cpy(res, r, p1, sizeof(p1)); /* res = e(k, res) */ err = smp_e(k, res); @@ -442,7 +441,7 @@ static int smp_c1(const u8 k[16], SMP_DBG("p2 %16phN", p2); /* res = res XOR p2 */ - u128_xor((u128 *) res, (u128 *) res, (u128 *) p2); + crypto_xor(res, p2, sizeof(p2)); /* res = e(k, res) */ err = smp_e(k, res); diff --git a/net/bpf/test_run.c b/net/bpf/test_run.c index 8b796c499cbb..58bcb8c849d5 100644 --- a/net/bpf/test_run.c +++ b/net/bpf/test_run.c @@ -637,14 +637,11 @@ int bpf_prog_test_run_xdp(struct bpf_prog *prog, const union bpf_attr *kattr, if (IS_ERR(data)) return PTR_ERR(data); - xdp.data_hard_start = data; - xdp.data = data + headroom; - xdp.data_meta = xdp.data; - xdp.data_end = xdp.data + size; - xdp.frame_sz = headroom + max_data_sz + tailroom; - rxqueue = __netif_get_rx_queue(current->nsproxy->net_ns->loopback_dev, 0); - xdp.rxq = &rxqueue->xdp_rxq; + xdp_init_buff(&xdp, headroom + max_data_sz + tailroom, + &rxqueue->xdp_rxq); + xdp_prepare_buff(&xdp, data, headroom, size, true); + bpf_prog_change_xdp(NULL, prog); ret = bpf_test_run(prog, &xdp, repeat, &retval, &duration, true); if (ret) diff --git a/net/bpfilter/Kconfig b/net/bpfilter/Kconfig index 8ad0233ce497..3d4a21462458 100644 --- a/net/bpfilter/Kconfig +++ b/net/bpfilter/Kconfig @@ -1,7 +1,7 @@ # SPDX-License-Identifier: GPL-2.0-only menuconfig BPFILTER bool "BPF based packet filtering framework (BPFILTER)" - depends on NET && BPF && INET + depends on BPF && INET select USERMODE_DRIVER help This builds experimental bpfilter framework that is aiming to diff --git a/net/bridge/Makefile b/net/bridge/Makefile index 4702702a74d3..7fb9a021873b 100644 --- a/net/bridge/Makefile +++ b/net/bridge/Makefile @@ -18,7 +18,7 @@ br_netfilter-y := br_netfilter_hooks.o br_netfilter-$(subst m,y,$(CONFIG_IPV6)) += br_netfilter_ipv6.o obj-$(CONFIG_BRIDGE_NETFILTER) += br_netfilter.o -bridge-$(CONFIG_BRIDGE_IGMP_SNOOPING) += br_multicast.o br_mdb.o +bridge-$(CONFIG_BRIDGE_IGMP_SNOOPING) += br_multicast.o br_mdb.o br_multicast_eht.o bridge-$(CONFIG_BRIDGE_VLAN_FILTERING) += br_vlan.o br_vlan_tunnel.o br_vlan_options.o diff --git a/net/bridge/br.c b/net/bridge/br.c index 1b169f8e7491..ef743f94254d 100644 --- a/net/bridge/br.c +++ b/net/bridge/br.c @@ -122,7 +122,7 @@ static int br_device_event(struct notifier_block *unused, unsigned long event, v break; case NETDEV_PRE_TYPE_CHANGE: - /* Forbid underlaying device to change its type. */ + /* Forbid underlying device to change its type. */ return NOTIFY_BAD; case NETDEV_RESEND_IGMP: diff --git a/net/bridge/br_fdb.c b/net/bridge/br_fdb.c index 32ac8343b0ba..b7490237f3fc 100644 --- a/net/bridge/br_fdb.c +++ b/net/bridge/br_fdb.c @@ -602,6 +602,7 @@ void br_fdb_update(struct net_bridge *br, struct net_bridge_port *source, /* fastpath: update of existing entry */ if (unlikely(source != fdb->dst && !test_bit(BR_FDB_STICKY, &fdb->flags))) { + br_switchdev_fdb_notify(fdb, RTM_DELNEIGH); fdb->dst = source; fdb_modified = true; /* Take over HW learned entry */ diff --git a/net/bridge/br_forward.c b/net/bridge/br_forward.c index e28ffadd1371..6e9b049ae521 100644 --- a/net/bridge/br_forward.c +++ b/net/bridge/br_forward.c @@ -39,8 +39,7 @@ int br_dev_queue_push_xmit(struct net *net, struct sock *sk, struct sk_buff *skb br_drop_fake_rtable(skb); if (skb->ip_summed == CHECKSUM_PARTIAL && - (skb->protocol == htons(ETH_P_8021Q) || - skb->protocol == htons(ETH_P_8021AD))) { + eth_type_vlan(skb->protocol)) { int depth; if (!__vlan_get_protocol(skb, skb->protocol, &depth)) diff --git a/net/bridge/br_input.c b/net/bridge/br_input.c index 8ca1f1bc6d12..222285d9dae2 100644 --- a/net/bridge/br_input.c +++ b/net/bridge/br_input.c @@ -40,7 +40,7 @@ static int br_pass_frame_up(struct sk_buff *skb) vg = br_vlan_group_rcu(br); /* Bridge is just like any other port. Make sure the - * packet is allowed except in promisc modue when someone + * packet is allowed except in promisc mode when someone * may be running packet capture. */ if (!(brdev->flags & IFF_PROMISC) && diff --git a/net/bridge/br_mrp.c b/net/bridge/br_mrp.c index 5aeae6ad17b3..12487f6fe9b4 100644 --- a/net/bridge/br_mrp.c +++ b/net/bridge/br_mrp.c @@ -639,7 +639,7 @@ int br_mrp_set_ring_role(struct net_bridge *br, struct br_mrp_ring_role *role) { struct br_mrp *mrp = br_mrp_find_id(br, role->ring_id); - int err; + enum br_mrp_hw_support support; if (!mrp) return -EINVAL; @@ -647,9 +647,9 @@ int br_mrp_set_ring_role(struct net_bridge *br, mrp->ring_role = role->ring_role; /* If there is an error just bailed out */ - err = br_mrp_switchdev_set_ring_role(br, mrp, role->ring_role); - if (err && err != -EOPNOTSUPP) - return err; + support = br_mrp_switchdev_set_ring_role(br, mrp, role->ring_role); + if (support == BR_MRP_NONE) + return -EOPNOTSUPP; /* Now detect if the HW actually applied the role or not. If the HW * applied the role it means that the SW will not to do those operations @@ -657,7 +657,7 @@ int br_mrp_set_ring_role(struct net_bridge *br, * SW when ring is open, but if the is not pushed to the HW the SW will * need to detect when the ring is open */ - mrp->ring_role_offloaded = err == -EOPNOTSUPP ? 0 : 1; + mrp->ring_role_offloaded = support == BR_MRP_SW ? 0 : 1; return 0; } @@ -670,6 +670,7 @@ int br_mrp_start_test(struct net_bridge *br, struct br_mrp_start_test *test) { struct br_mrp *mrp = br_mrp_find_id(br, test->ring_id); + enum br_mrp_hw_support support; if (!mrp) return -EINVAL; @@ -677,9 +678,13 @@ int br_mrp_start_test(struct net_bridge *br, /* Try to push it to the HW and if it fails then continue with SW * implementation and if that also fails then return error. */ - if (!br_mrp_switchdev_send_ring_test(br, mrp, test->interval, - test->max_miss, test->period, - test->monitor)) + support = br_mrp_switchdev_send_ring_test(br, mrp, test->interval, + test->max_miss, test->period, + test->monitor); + if (support == BR_MRP_NONE) + return -EOPNOTSUPP; + + if (support == BR_MRP_HW) return 0; mrp->test_interval = test->interval; @@ -721,8 +726,8 @@ int br_mrp_set_in_state(struct net_bridge *br, struct br_mrp_in_state *state) int br_mrp_set_in_role(struct net_bridge *br, struct br_mrp_in_role *role) { struct br_mrp *mrp = br_mrp_find_id(br, role->ring_id); + enum br_mrp_hw_support support; struct net_bridge_port *p; - int err; if (!mrp) return -EINVAL; @@ -780,10 +785,10 @@ int br_mrp_set_in_role(struct net_bridge *br, struct br_mrp_in_role *role) mrp->in_id = role->in_id; /* If there is an error just bailed out */ - err = br_mrp_switchdev_set_in_role(br, mrp, role->in_id, - role->ring_id, role->in_role); - if (err && err != -EOPNOTSUPP) - return err; + support = br_mrp_switchdev_set_in_role(br, mrp, role->in_id, + role->ring_id, role->in_role); + if (support == BR_MRP_NONE) + return -EOPNOTSUPP; /* Now detect if the HW actually applied the role or not. If the HW * applied the role it means that the SW will not to do those operations @@ -791,7 +796,7 @@ int br_mrp_set_in_role(struct net_bridge *br, struct br_mrp_in_role *role) * SW when interconnect ring is open, but if the is not pushed to the HW * the SW will need to detect when the interconnect ring is open. */ - mrp->in_role_offloaded = err == -EOPNOTSUPP ? 0 : 1; + mrp->in_role_offloaded = support == BR_MRP_SW ? 0 : 1; return 0; } @@ -804,6 +809,7 @@ int br_mrp_start_in_test(struct net_bridge *br, struct br_mrp_start_in_test *in_test) { struct br_mrp *mrp = br_mrp_find_in_id(br, in_test->in_id); + enum br_mrp_hw_support support; if (!mrp) return -EINVAL; @@ -814,8 +820,13 @@ int br_mrp_start_in_test(struct net_bridge *br, /* Try to push it to the HW and if it fails then continue with SW * implementation and if that also fails then return error. */ - if (!br_mrp_switchdev_send_in_test(br, mrp, in_test->interval, - in_test->max_miss, in_test->period)) + support = br_mrp_switchdev_send_in_test(br, mrp, in_test->interval, + in_test->max_miss, + in_test->period); + if (support == BR_MRP_NONE) + return -EOPNOTSUPP; + + if (support == BR_MRP_HW) return 0; mrp->in_test_interval = in_test->interval; @@ -828,7 +839,7 @@ int br_mrp_start_in_test(struct net_bridge *br, return 0; } -/* Determin if the frame type is a ring frame */ +/* Determine if the frame type is a ring frame */ static bool br_mrp_ring_frame(struct sk_buff *skb) { const struct br_mrp_tlv_hdr *hdr; @@ -848,7 +859,7 @@ static bool br_mrp_ring_frame(struct sk_buff *skb) return false; } -/* Determin if the frame type is an interconnect frame */ +/* Determine if the frame type is an interconnect frame */ static bool br_mrp_in_frame(struct sk_buff *skb) { const struct br_mrp_tlv_hdr *hdr; @@ -897,7 +908,7 @@ static void br_mrp_mrm_process(struct br_mrp *mrp, struct net_bridge_port *port, br_mrp_ring_port_open(port->dev, false); } -/* Determin if the test hdr has a better priority than the node */ +/* Determine if the test hdr has a better priority than the node */ static bool br_mrp_test_better_than_own(struct br_mrp *mrp, struct net_bridge *br, const struct br_mrp_ring_test_hdr *hdr) diff --git a/net/bridge/br_mrp_switchdev.c b/net/bridge/br_mrp_switchdev.c index 75a7e8d0a268..cb54b324fa8c 100644 --- a/net/bridge/br_mrp_switchdev.c +++ b/net/bridge/br_mrp_switchdev.c @@ -4,6 +4,30 @@ #include "br_private_mrp.h" +static enum br_mrp_hw_support +br_mrp_switchdev_port_obj(struct net_bridge *br, + const struct switchdev_obj *obj, bool add) +{ + int err; + + if (add) + err = switchdev_port_obj_add(br->dev, obj, NULL); + else + err = switchdev_port_obj_del(br->dev, obj); + + /* In case of success just return and notify the SW that doesn't need + * to do anything + */ + if (!err) + return BR_MRP_HW; + + if (err != -EOPNOTSUPP) + return BR_MRP_NONE; + + /* Continue with SW backup */ + return BR_MRP_SW; +} + int br_mrp_switchdev_add(struct net_bridge *br, struct br_mrp *mrp) { struct switchdev_obj_mrp mrp_obj = { @@ -14,14 +38,11 @@ int br_mrp_switchdev_add(struct net_bridge *br, struct br_mrp *mrp) .ring_id = mrp->ring_id, .prio = mrp->prio, }; - int err; - err = switchdev_port_obj_add(br->dev, &mrp_obj.obj, NULL); + if (!IS_ENABLED(CONFIG_NET_SWITCHDEV)) + return 0; - if (err && err != -EOPNOTSUPP) - return err; - - return 0; + return switchdev_port_obj_add(br->dev, &mrp_obj.obj, NULL); } int br_mrp_switchdev_del(struct net_bridge *br, struct br_mrp *mrp) @@ -33,40 +54,54 @@ int br_mrp_switchdev_del(struct net_bridge *br, struct br_mrp *mrp) .s_port = NULL, .ring_id = mrp->ring_id, }; - int err; - - err = switchdev_port_obj_del(br->dev, &mrp_obj.obj); - if (err && err != -EOPNOTSUPP) - return err; + if (!IS_ENABLED(CONFIG_NET_SWITCHDEV)) + return 0; - return 0; + return switchdev_port_obj_del(br->dev, &mrp_obj.obj); } -int br_mrp_switchdev_set_ring_role(struct net_bridge *br, - struct br_mrp *mrp, - enum br_mrp_ring_role_type role) +enum br_mrp_hw_support +br_mrp_switchdev_set_ring_role(struct net_bridge *br, struct br_mrp *mrp, + enum br_mrp_ring_role_type role) { struct switchdev_obj_ring_role_mrp mrp_role = { .obj.orig_dev = br->dev, .obj.id = SWITCHDEV_OBJ_ID_RING_ROLE_MRP, .ring_role = role, .ring_id = mrp->ring_id, + .sw_backup = false, }; + enum br_mrp_hw_support support; int err; - if (role == BR_MRP_RING_ROLE_DISABLED) - err = switchdev_port_obj_del(br->dev, &mrp_role.obj); - else + if (!IS_ENABLED(CONFIG_NET_SWITCHDEV)) + return BR_MRP_SW; + + support = br_mrp_switchdev_port_obj(br, &mrp_role.obj, + role != BR_MRP_RING_ROLE_DISABLED); + if (support != BR_MRP_SW) + return support; + + /* If the driver can't configure to run completely the protocol in HW, + * then try again to configure the HW so the SW can run the protocol. + */ + mrp_role.sw_backup = true; + if (role != BR_MRP_RING_ROLE_DISABLED) err = switchdev_port_obj_add(br->dev, &mrp_role.obj, NULL); + else + err = switchdev_port_obj_del(br->dev, &mrp_role.obj); - return err; + if (!err) + return BR_MRP_SW; + + return BR_MRP_NONE; } -int br_mrp_switchdev_send_ring_test(struct net_bridge *br, - struct br_mrp *mrp, u32 interval, - u8 max_miss, u32 period, - bool monitor) +enum br_mrp_hw_support +br_mrp_switchdev_send_ring_test(struct net_bridge *br, struct br_mrp *mrp, + u32 interval, u8 max_miss, u32 period, + bool monitor) { struct switchdev_obj_ring_test_mrp test = { .obj.orig_dev = br->dev, @@ -77,14 +112,11 @@ int br_mrp_switchdev_send_ring_test(struct net_bridge *br, .period = period, .monitor = monitor, }; - int err; - if (interval == 0) - err = switchdev_port_obj_del(br->dev, &test.obj); - else - err = switchdev_port_obj_add(br->dev, &test.obj, NULL); + if (!IS_ENABLED(CONFIG_NET_SWITCHDEV)) + return BR_MRP_SW; - return err; + return br_mrp_switchdev_port_obj(br, &test.obj, interval != 0); } int br_mrp_switchdev_set_ring_state(struct net_bridge *br, @@ -97,19 +129,17 @@ int br_mrp_switchdev_set_ring_state(struct net_bridge *br, .ring_state = state, .ring_id = mrp->ring_id, }; - int err; - - err = switchdev_port_obj_add(br->dev, &mrp_state.obj, NULL); - if (err && err != -EOPNOTSUPP) - return err; + if (!IS_ENABLED(CONFIG_NET_SWITCHDEV)) + return 0; - return 0; + return switchdev_port_obj_add(br->dev, &mrp_state.obj, NULL); } -int br_mrp_switchdev_set_in_role(struct net_bridge *br, struct br_mrp *mrp, - u16 in_id, u32 ring_id, - enum br_mrp_in_role_type role) +enum br_mrp_hw_support +br_mrp_switchdev_set_in_role(struct net_bridge *br, struct br_mrp *mrp, + u16 in_id, u32 ring_id, + enum br_mrp_in_role_type role) { struct switchdev_obj_in_role_mrp mrp_role = { .obj.orig_dev = br->dev, @@ -118,15 +148,32 @@ int br_mrp_switchdev_set_in_role(struct net_bridge *br, struct br_mrp *mrp, .in_id = mrp->in_id, .ring_id = mrp->ring_id, .i_port = rtnl_dereference(mrp->i_port)->dev, + .sw_backup = false, }; + enum br_mrp_hw_support support; int err; - if (role == BR_MRP_IN_ROLE_DISABLED) - err = switchdev_port_obj_del(br->dev, &mrp_role.obj); - else + if (!IS_ENABLED(CONFIG_NET_SWITCHDEV)) + return BR_MRP_SW; + + support = br_mrp_switchdev_port_obj(br, &mrp_role.obj, + role != BR_MRP_IN_ROLE_DISABLED); + if (support != BR_MRP_NONE) + return support; + + /* If the driver can't configure to run completely the protocol in HW, + * then try again to configure the HW so the SW can run the protocol. + */ + mrp_role.sw_backup = true; + if (role != BR_MRP_IN_ROLE_DISABLED) err = switchdev_port_obj_add(br->dev, &mrp_role.obj, NULL); + else + err = switchdev_port_obj_del(br->dev, &mrp_role.obj); + + if (!err) + return BR_MRP_SW; - return err; + return BR_MRP_NONE; } int br_mrp_switchdev_set_in_state(struct net_bridge *br, struct br_mrp *mrp, @@ -138,18 +185,16 @@ int br_mrp_switchdev_set_in_state(struct net_bridge *br, struct br_mrp *mrp, .in_state = state, .in_id = mrp->in_id, }; - int err; - - err = switchdev_port_obj_add(br->dev, &mrp_state.obj, NULL); - if (err && err != -EOPNOTSUPP) - return err; + if (!IS_ENABLED(CONFIG_NET_SWITCHDEV)) + return 0; - return 0; + return switchdev_port_obj_add(br->dev, &mrp_state.obj, NULL); } -int br_mrp_switchdev_send_in_test(struct net_bridge *br, struct br_mrp *mrp, - u32 interval, u8 max_miss, u32 period) +enum br_mrp_hw_support +br_mrp_switchdev_send_in_test(struct net_bridge *br, struct br_mrp *mrp, + u32 interval, u8 max_miss, u32 period) { struct switchdev_obj_in_test_mrp test = { .obj.orig_dev = br->dev, @@ -159,14 +204,11 @@ int br_mrp_switchdev_send_in_test(struct net_bridge *br, struct br_mrp *mrp, .in_id = mrp->in_id, .period = period, }; - int err; - if (interval == 0) - err = switchdev_port_obj_del(br->dev, &test.obj); - else - err = switchdev_port_obj_add(br->dev, &test.obj, NULL); + if (!IS_ENABLED(CONFIG_NET_SWITCHDEV)) + return BR_MRP_SW; - return err; + return br_mrp_switchdev_port_obj(br, &test.obj, interval != 0); } int br_mrp_port_switchdev_set_state(struct net_bridge_port *p, u32 state) @@ -176,14 +218,11 @@ int br_mrp_port_switchdev_set_state(struct net_bridge_port *p, u32 state) .id = SWITCHDEV_ATTR_ID_PORT_STP_STATE, .u.stp_state = state, }; - int err; - err = switchdev_port_attr_set(p->dev, &attr); - if (err && err != -EOPNOTSUPP) - br_warn(p->br, "error setting offload MRP state on port %u(%s)\n", - (unsigned int)p->port_no, p->dev->name); + if (!IS_ENABLED(CONFIG_NET_SWITCHDEV)) + return 0; - return err; + return switchdev_port_attr_set(p->dev, &attr, NULL); } int br_mrp_port_switchdev_set_role(struct net_bridge_port *p, @@ -194,11 +233,9 @@ int br_mrp_port_switchdev_set_role(struct net_bridge_port *p, .id = SWITCHDEV_ATTR_ID_MRP_PORT_ROLE, .u.mrp_port_role = role, }; - int err; - err = switchdev_port_attr_set(p->dev, &attr); - if (err && err != -EOPNOTSUPP) - return err; + if (!IS_ENABLED(CONFIG_NET_SWITCHDEV)) + return 0; - return 0; + return switchdev_port_attr_set(p->dev, &attr, NULL); } diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c index 257ac4e25f6d..9d265447d654 100644 --- a/net/bridge/br_multicast.c +++ b/net/bridge/br_multicast.c @@ -33,6 +33,7 @@ #endif #include "br_private.h" +#include "br_private_mcast_eht.h" static const struct rhashtable_params br_mdb_rht_params = { .head_offset = offsetof(struct net_bridge_mdb_entry, rhnode), @@ -441,7 +442,8 @@ static void br_multicast_fwd_src_add(struct net_bridge_group_src *src) br_multicast_sg_add_exclude_ports(star_mp, sg); } -static void br_multicast_fwd_src_remove(struct net_bridge_group_src *src) +static void br_multicast_fwd_src_remove(struct net_bridge_group_src *src, + bool fastleave) { struct net_bridge_port_group *p, *pg = src->pg; struct net_bridge_port_group __rcu **pp; @@ -466,6 +468,8 @@ static void br_multicast_fwd_src_remove(struct net_bridge_group_src *src) (p->flags & MDB_PG_FLAGS_PERMANENT)) break; + if (fastleave) + p->flags |= MDB_PG_FLAGS_FAST_LEAVE; br_multicast_del_pg(mp, p, pp); break; } @@ -559,11 +563,12 @@ static void br_multicast_destroy_group_src(struct net_bridge_mcast_gc *gc) kfree_rcu(src, rcu); } -static void br_multicast_del_group_src(struct net_bridge_group_src *src) +void br_multicast_del_group_src(struct net_bridge_group_src *src, + bool fastleave) { struct net_bridge *br = src->pg->key.port->br; - br_multicast_fwd_src_remove(src); + br_multicast_fwd_src_remove(src, fastleave); hlist_del_init_rcu(&src->node); src->pg->src_ents--; hlist_add_head(&src->mcast_gc.gc_node, &br->mcast_gc_list); @@ -593,8 +598,9 @@ void br_multicast_del_pg(struct net_bridge_mdb_entry *mp, rcu_assign_pointer(*pp, pg->next); hlist_del_init(&pg->mglist); + br_multicast_eht_clean_sets(pg); hlist_for_each_entry_safe(ent, tmp, &pg->src_list, node) - br_multicast_del_group_src(ent); + br_multicast_del_group_src(ent, false); br_mdb_notify(br->dev, mp, pg, RTM_DELMDB); if (!br_multicast_is_star_g(&mp->addr)) { rhashtable_remove_fast(&br->sg_port_tbl, &pg->rhnode, @@ -651,7 +657,7 @@ static void br_multicast_port_group_expired(struct timer_list *t) pg->filter_mode = MCAST_INCLUDE; hlist_for_each_entry_safe(src_ent, tmp, &pg->src_list, node) { if (!timer_pending(&src_ent->timer)) { - br_multicast_del_group_src(src_ent); + br_multicast_del_group_src(src_ent, false); changed = true; } } @@ -1078,7 +1084,7 @@ static void br_multicast_group_src_expired(struct timer_list *t) pg = src->pg; if (pg->filter_mode == MCAST_INCLUDE) { - br_multicast_del_group_src(src); + br_multicast_del_group_src(src, false); if (!hlist_empty(&pg->src_list)) goto out; br_multicast_find_del_pg(br, pg); @@ -1090,7 +1096,7 @@ out: spin_unlock(&br->multicast_lock); } -static struct net_bridge_group_src * +struct net_bridge_group_src * br_multicast_find_group_src(struct net_bridge_port_group *pg, struct br_ip *ip) { struct net_bridge_group_src *ent; @@ -1172,6 +1178,8 @@ struct net_bridge_port_group *br_multicast_new_port_group( p->flags = flags; p->filter_mode = filter_mode; p->rt_protocol = rt_protocol; + p->eht_host_tree = RB_ROOT; + p->eht_set_tree = RB_ROOT; p->mcast_gc.destroy = br_multicast_destroy_port_group; INIT_HLIST_HEAD(&p->src_list); @@ -1243,7 +1251,7 @@ __br_multicast_add_group(struct net_bridge *br, mp = br_multicast_new_group(br, group); if (IS_ERR(mp)) - return ERR_PTR(PTR_ERR(mp)); + return ERR_CAST(mp); if (!port) { br_multicast_host_join(mp, true); @@ -1292,7 +1300,7 @@ static int br_multicast_add_group(struct net_bridge *br, pg = __br_multicast_add_group(br, port, group, src, filter_mode, igmpv2_mldv1, false); /* NULL is considered valid for host joined groups */ - err = IS_ERR(pg) ? PTR_ERR(pg) : 0; + err = PTR_ERR_OR_ZERO(pg); spin_unlock(&br->multicast_lock); return err; @@ -1373,7 +1381,7 @@ static void br_mc_router_state_change(struct net_bridge *p, .u.mrouter = is_mc_router, }; - switchdev_port_attr_set(p->dev, &attr); + switchdev_port_attr_set(p->dev, &attr, NULL); } static void br_multicast_local_router_expired(struct timer_list *t) @@ -1594,12 +1602,13 @@ static void br_mc_disabled_update(struct net_device *dev, bool value) .u.mc_disabled = !value, }; - switchdev_port_attr_set(dev, &attr); + switchdev_port_attr_set(dev, &attr, NULL); } int br_multicast_add_port(struct net_bridge_port *port) { port->multicast_router = MDB_RTR_TYPE_TEMP_QUERY; + port->multicast_eht_hosts_limit = BR_MCAST_DEFAULT_EHT_HOSTS_LIMIT; timer_setup(&port->multicast_router_timer, br_multicast_router_expired, 0); @@ -1700,7 +1709,7 @@ static int __grp_src_delete_marked(struct net_bridge_port_group *pg) hlist_for_each_entry_safe(ent, tmp, &pg->src_list, node) if (ent->flags & BR_SGRP_F_DELETE) { - br_multicast_del_group_src(ent); + br_multicast_del_group_src(ent, false); deleted++; } @@ -1799,8 +1808,9 @@ static void __grp_send_query_and_rexmit(struct net_bridge_port_group *pg) * INCLUDE (A) ALLOW (B) INCLUDE (A+B) (B)=GMI * EXCLUDE (X,Y) ALLOW (A) EXCLUDE (X+A,Y-A) (A)=GMI */ -static bool br_multicast_isinc_allow(struct net_bridge_port_group *pg, - void *srcs, u32 nsrcs, size_t src_size) +static bool br_multicast_isinc_allow(struct net_bridge_port_group *pg, void *h_addr, + void *srcs, u32 nsrcs, size_t addr_size, + int grec_type) { struct net_bridge *br = pg->key.port->br; struct net_bridge_group_src *ent; @@ -1812,7 +1822,7 @@ static bool br_multicast_isinc_allow(struct net_bridge_port_group *pg, memset(&src_ip, 0, sizeof(src_ip)); src_ip.proto = pg->key.addr.proto; for (src_idx = 0; src_idx < nsrcs; src_idx++) { - memcpy(&src_ip.src, srcs, src_size); + memcpy(&src_ip.src, srcs + (src_idx * addr_size), addr_size); ent = br_multicast_find_group_src(pg, &src_ip); if (!ent) { ent = br_multicast_new_group_src(pg, &src_ip); @@ -1822,9 +1832,11 @@ static bool br_multicast_isinc_allow(struct net_bridge_port_group *pg, if (ent) __grp_src_mod_timer(ent, now + br_multicast_gmi(br)); - srcs += src_size; } + if (br_multicast_eht_handle(pg, h_addr, srcs, nsrcs, addr_size, grec_type)) + changed = true; + return changed; } @@ -1833,8 +1845,9 @@ static bool br_multicast_isinc_allow(struct net_bridge_port_group *pg, * Delete (A-B) * Group Timer=GMI */ -static void __grp_src_isexc_incl(struct net_bridge_port_group *pg, - void *srcs, u32 nsrcs, size_t src_size) +static void __grp_src_isexc_incl(struct net_bridge_port_group *pg, void *h_addr, + void *srcs, u32 nsrcs, size_t addr_size, + int grec_type) { struct net_bridge_group_src *ent; struct br_ip src_ip; @@ -1846,7 +1859,7 @@ static void __grp_src_isexc_incl(struct net_bridge_port_group *pg, memset(&src_ip, 0, sizeof(src_ip)); src_ip.proto = pg->key.addr.proto; for (src_idx = 0; src_idx < nsrcs; src_idx++) { - memcpy(&src_ip.src, srcs, src_size); + memcpy(&src_ip.src, srcs + (src_idx * addr_size), addr_size); ent = br_multicast_find_group_src(pg, &src_ip); if (ent) ent->flags &= ~BR_SGRP_F_DELETE; @@ -1854,9 +1867,10 @@ static void __grp_src_isexc_incl(struct net_bridge_port_group *pg, ent = br_multicast_new_group_src(pg, &src_ip); if (ent) br_multicast_fwd_src_handle(ent); - srcs += src_size; } + br_multicast_eht_handle(pg, h_addr, srcs, nsrcs, addr_size, grec_type); + __grp_src_delete_marked(pg); } @@ -1866,8 +1880,9 @@ static void __grp_src_isexc_incl(struct net_bridge_port_group *pg, * Delete (Y-A) * Group Timer=GMI */ -static bool __grp_src_isexc_excl(struct net_bridge_port_group *pg, - void *srcs, u32 nsrcs, size_t src_size) +static bool __grp_src_isexc_excl(struct net_bridge_port_group *pg, void *h_addr, + void *srcs, u32 nsrcs, size_t addr_size, + int grec_type) { struct net_bridge *br = pg->key.port->br; struct net_bridge_group_src *ent; @@ -1882,7 +1897,7 @@ static bool __grp_src_isexc_excl(struct net_bridge_port_group *pg, memset(&src_ip, 0, sizeof(src_ip)); src_ip.proto = pg->key.addr.proto; for (src_idx = 0; src_idx < nsrcs; src_idx++) { - memcpy(&src_ip.src, srcs, src_size); + memcpy(&src_ip.src, srcs + (src_idx * addr_size), addr_size); ent = br_multicast_find_group_src(pg, &src_ip); if (ent) { ent->flags &= ~BR_SGRP_F_DELETE; @@ -1894,29 +1909,34 @@ static bool __grp_src_isexc_excl(struct net_bridge_port_group *pg, changed = true; } } - srcs += src_size; } + if (br_multicast_eht_handle(pg, h_addr, srcs, nsrcs, addr_size, grec_type)) + changed = true; + if (__grp_src_delete_marked(pg)) changed = true; return changed; } -static bool br_multicast_isexc(struct net_bridge_port_group *pg, - void *srcs, u32 nsrcs, size_t src_size) +static bool br_multicast_isexc(struct net_bridge_port_group *pg, void *h_addr, + void *srcs, u32 nsrcs, size_t addr_size, + int grec_type) { struct net_bridge *br = pg->key.port->br; bool changed = false; switch (pg->filter_mode) { case MCAST_INCLUDE: - __grp_src_isexc_incl(pg, srcs, nsrcs, src_size); + __grp_src_isexc_incl(pg, h_addr, srcs, nsrcs, addr_size, + grec_type); br_multicast_star_g_handle_mode(pg, MCAST_EXCLUDE); changed = true; break; case MCAST_EXCLUDE: - changed = __grp_src_isexc_excl(pg, srcs, nsrcs, src_size); + changed = __grp_src_isexc_excl(pg, h_addr, srcs, nsrcs, addr_size, + grec_type); break; } @@ -1930,8 +1950,9 @@ static bool br_multicast_isexc(struct net_bridge_port_group *pg, * INCLUDE (A) TO_IN (B) INCLUDE (A+B) (B)=GMI * Send Q(G,A-B) */ -static bool __grp_src_toin_incl(struct net_bridge_port_group *pg, - void *srcs, u32 nsrcs, size_t src_size) +static bool __grp_src_toin_incl(struct net_bridge_port_group *pg, void *h_addr, + void *srcs, u32 nsrcs, size_t addr_size, + int grec_type) { struct net_bridge *br = pg->key.port->br; u32 src_idx, to_send = pg->src_ents; @@ -1946,7 +1967,7 @@ static bool __grp_src_toin_incl(struct net_bridge_port_group *pg, memset(&src_ip, 0, sizeof(src_ip)); src_ip.proto = pg->key.addr.proto; for (src_idx = 0; src_idx < nsrcs; src_idx++) { - memcpy(&src_ip.src, srcs, src_size); + memcpy(&src_ip.src, srcs + (src_idx * addr_size), addr_size); ent = br_multicast_find_group_src(pg, &src_ip); if (ent) { ent->flags &= ~BR_SGRP_F_SEND; @@ -1958,9 +1979,11 @@ static bool __grp_src_toin_incl(struct net_bridge_port_group *pg, } if (ent) __grp_src_mod_timer(ent, now + br_multicast_gmi(br)); - srcs += src_size; } + if (br_multicast_eht_handle(pg, h_addr, srcs, nsrcs, addr_size, grec_type)) + changed = true; + if (to_send) __grp_src_query_marked_and_rexmit(pg); @@ -1972,8 +1995,9 @@ static bool __grp_src_toin_incl(struct net_bridge_port_group *pg, * Send Q(G,X-A) * Send Q(G) */ -static bool __grp_src_toin_excl(struct net_bridge_port_group *pg, - void *srcs, u32 nsrcs, size_t src_size) +static bool __grp_src_toin_excl(struct net_bridge_port_group *pg, void *h_addr, + void *srcs, u32 nsrcs, size_t addr_size, + int grec_type) { struct net_bridge *br = pg->key.port->br; u32 src_idx, to_send = pg->src_ents; @@ -1989,7 +2013,7 @@ static bool __grp_src_toin_excl(struct net_bridge_port_group *pg, memset(&src_ip, 0, sizeof(src_ip)); src_ip.proto = pg->key.addr.proto; for (src_idx = 0; src_idx < nsrcs; src_idx++) { - memcpy(&src_ip.src, srcs, src_size); + memcpy(&src_ip.src, srcs + (src_idx * addr_size), addr_size); ent = br_multicast_find_group_src(pg, &src_ip); if (ent) { if (timer_pending(&ent->timer)) { @@ -2003,9 +2027,11 @@ static bool __grp_src_toin_excl(struct net_bridge_port_group *pg, } if (ent) __grp_src_mod_timer(ent, now + br_multicast_gmi(br)); - srcs += src_size; } + if (br_multicast_eht_handle(pg, h_addr, srcs, nsrcs, addr_size, grec_type)) + changed = true; + if (to_send) __grp_src_query_marked_and_rexmit(pg); @@ -2014,20 +2040,32 @@ static bool __grp_src_toin_excl(struct net_bridge_port_group *pg, return changed; } -static bool br_multicast_toin(struct net_bridge_port_group *pg, - void *srcs, u32 nsrcs, size_t src_size) +static bool br_multicast_toin(struct net_bridge_port_group *pg, void *h_addr, + void *srcs, u32 nsrcs, size_t addr_size, + int grec_type) { bool changed = false; switch (pg->filter_mode) { case MCAST_INCLUDE: - changed = __grp_src_toin_incl(pg, srcs, nsrcs, src_size); + changed = __grp_src_toin_incl(pg, h_addr, srcs, nsrcs, addr_size, + grec_type); break; case MCAST_EXCLUDE: - changed = __grp_src_toin_excl(pg, srcs, nsrcs, src_size); + changed = __grp_src_toin_excl(pg, h_addr, srcs, nsrcs, addr_size, + grec_type); break; } + if (br_multicast_eht_should_del_pg(pg)) { + pg->flags |= MDB_PG_FLAGS_FAST_LEAVE; + br_multicast_find_del_pg(pg->key.port->br, pg); + /* a notification has already been sent and we shouldn't + * access pg after the delete so we have to return false + */ + changed = false; + } + return changed; } @@ -2037,8 +2075,9 @@ static bool br_multicast_toin(struct net_bridge_port_group *pg, * Send Q(G,A*B) * Group Timer=GMI */ -static void __grp_src_toex_incl(struct net_bridge_port_group *pg, - void *srcs, u32 nsrcs, size_t src_size) +static void __grp_src_toex_incl(struct net_bridge_port_group *pg, void *h_addr, + void *srcs, u32 nsrcs, size_t addr_size, + int grec_type) { struct net_bridge_group_src *ent; u32 src_idx, to_send = 0; @@ -2050,7 +2089,7 @@ static void __grp_src_toex_incl(struct net_bridge_port_group *pg, memset(&src_ip, 0, sizeof(src_ip)); src_ip.proto = pg->key.addr.proto; for (src_idx = 0; src_idx < nsrcs; src_idx++) { - memcpy(&src_ip.src, srcs, src_size); + memcpy(&src_ip.src, srcs + (src_idx * addr_size), addr_size); ent = br_multicast_find_group_src(pg, &src_ip); if (ent) { ent->flags = (ent->flags & ~BR_SGRP_F_DELETE) | @@ -2061,9 +2100,10 @@ static void __grp_src_toex_incl(struct net_bridge_port_group *pg, } if (ent) br_multicast_fwd_src_handle(ent); - srcs += src_size; } + br_multicast_eht_handle(pg, h_addr, srcs, nsrcs, addr_size, grec_type); + __grp_src_delete_marked(pg); if (to_send) __grp_src_query_marked_and_rexmit(pg); @@ -2076,8 +2116,9 @@ static void __grp_src_toex_incl(struct net_bridge_port_group *pg, * Send Q(G,A-Y) * Group Timer=GMI */ -static bool __grp_src_toex_excl(struct net_bridge_port_group *pg, - void *srcs, u32 nsrcs, size_t src_size) +static bool __grp_src_toex_excl(struct net_bridge_port_group *pg, void *h_addr, + void *srcs, u32 nsrcs, size_t addr_size, + int grec_type) { struct net_bridge_group_src *ent; u32 src_idx, to_send = 0; @@ -2090,7 +2131,7 @@ static bool __grp_src_toex_excl(struct net_bridge_port_group *pg, memset(&src_ip, 0, sizeof(src_ip)); src_ip.proto = pg->key.addr.proto; for (src_idx = 0; src_idx < nsrcs; src_idx++) { - memcpy(&src_ip.src, srcs, src_size); + memcpy(&src_ip.src, srcs + (src_idx * addr_size), addr_size); ent = br_multicast_find_group_src(pg, &src_ip); if (ent) { ent->flags &= ~BR_SGRP_F_DELETE; @@ -2105,9 +2146,11 @@ static bool __grp_src_toex_excl(struct net_bridge_port_group *pg, ent->flags |= BR_SGRP_F_SEND; to_send++; } - srcs += src_size; } + if (br_multicast_eht_handle(pg, h_addr, srcs, nsrcs, addr_size, grec_type)) + changed = true; + if (__grp_src_delete_marked(pg)) changed = true; if (to_send) @@ -2116,20 +2159,23 @@ static bool __grp_src_toex_excl(struct net_bridge_port_group *pg, return changed; } -static bool br_multicast_toex(struct net_bridge_port_group *pg, - void *srcs, u32 nsrcs, size_t src_size) +static bool br_multicast_toex(struct net_bridge_port_group *pg, void *h_addr, + void *srcs, u32 nsrcs, size_t addr_size, + int grec_type) { struct net_bridge *br = pg->key.port->br; bool changed = false; switch (pg->filter_mode) { case MCAST_INCLUDE: - __grp_src_toex_incl(pg, srcs, nsrcs, src_size); + __grp_src_toex_incl(pg, h_addr, srcs, nsrcs, addr_size, + grec_type); br_multicast_star_g_handle_mode(pg, MCAST_EXCLUDE); changed = true; break; case MCAST_EXCLUDE: - changed = __grp_src_toex_excl(pg, srcs, nsrcs, src_size); + changed = __grp_src_toex_excl(pg, h_addr, srcs, nsrcs, addr_size, + grec_type); break; } @@ -2142,11 +2188,12 @@ static bool br_multicast_toex(struct net_bridge_port_group *pg, /* State Msg type New state Actions * INCLUDE (A) BLOCK (B) INCLUDE (A) Send Q(G,A*B) */ -static void __grp_src_block_incl(struct net_bridge_port_group *pg, - void *srcs, u32 nsrcs, size_t src_size) +static bool __grp_src_block_incl(struct net_bridge_port_group *pg, void *h_addr, + void *srcs, u32 nsrcs, size_t addr_size, int grec_type) { struct net_bridge_group_src *ent; u32 src_idx, to_send = 0; + bool changed = false; struct br_ip src_ip; hlist_for_each_entry(ent, &pg->src_list, node) @@ -2155,28 +2202,29 @@ static void __grp_src_block_incl(struct net_bridge_port_group *pg, memset(&src_ip, 0, sizeof(src_ip)); src_ip.proto = pg->key.addr.proto; for (src_idx = 0; src_idx < nsrcs; src_idx++) { - memcpy(&src_ip.src, srcs, src_size); + memcpy(&src_ip.src, srcs + (src_idx * addr_size), addr_size); ent = br_multicast_find_group_src(pg, &src_ip); if (ent) { ent->flags |= BR_SGRP_F_SEND; to_send++; } - srcs += src_size; } + if (br_multicast_eht_handle(pg, h_addr, srcs, nsrcs, addr_size, grec_type)) + changed = true; + if (to_send) __grp_src_query_marked_and_rexmit(pg); - if (pg->filter_mode == MCAST_INCLUDE && hlist_empty(&pg->src_list)) - br_multicast_find_del_pg(pg->key.port->br, pg); + return changed; } /* State Msg type New state Actions * EXCLUDE (X,Y) BLOCK (A) EXCLUDE (X+(A-Y),Y) (A-X-Y)=Group Timer * Send Q(G,A-Y) */ -static bool __grp_src_block_excl(struct net_bridge_port_group *pg, - void *srcs, u32 nsrcs, size_t src_size) +static bool __grp_src_block_excl(struct net_bridge_port_group *pg, void *h_addr, + void *srcs, u32 nsrcs, size_t addr_size, int grec_type) { struct net_bridge_group_src *ent; u32 src_idx, to_send = 0; @@ -2189,7 +2237,7 @@ static bool __grp_src_block_excl(struct net_bridge_port_group *pg, memset(&src_ip, 0, sizeof(src_ip)); src_ip.proto = pg->key.addr.proto; for (src_idx = 0; src_idx < nsrcs; src_idx++) { - memcpy(&src_ip.src, srcs, src_size); + memcpy(&src_ip.src, srcs + (src_idx * addr_size), addr_size); ent = br_multicast_find_group_src(pg, &src_ip); if (!ent) { ent = br_multicast_new_group_src(pg, &src_ip); @@ -2202,29 +2250,44 @@ static bool __grp_src_block_excl(struct net_bridge_port_group *pg, ent->flags |= BR_SGRP_F_SEND; to_send++; } - srcs += src_size; } + if (br_multicast_eht_handle(pg, h_addr, srcs, nsrcs, addr_size, grec_type)) + changed = true; + if (to_send) __grp_src_query_marked_and_rexmit(pg); return changed; } -static bool br_multicast_block(struct net_bridge_port_group *pg, - void *srcs, u32 nsrcs, size_t src_size) +static bool br_multicast_block(struct net_bridge_port_group *pg, void *h_addr, + void *srcs, u32 nsrcs, size_t addr_size, int grec_type) { bool changed = false; switch (pg->filter_mode) { case MCAST_INCLUDE: - __grp_src_block_incl(pg, srcs, nsrcs, src_size); + changed = __grp_src_block_incl(pg, h_addr, srcs, nsrcs, addr_size, + grec_type); break; case MCAST_EXCLUDE: - changed = __grp_src_block_excl(pg, srcs, nsrcs, src_size); + changed = __grp_src_block_excl(pg, h_addr, srcs, nsrcs, addr_size, + grec_type); break; } + if ((pg->filter_mode == MCAST_INCLUDE && hlist_empty(&pg->src_list)) || + br_multicast_eht_should_del_pg(pg)) { + if (br_multicast_eht_should_del_pg(pg)) + pg->flags |= MDB_PG_FLAGS_FAST_LEAVE; + br_multicast_find_del_pg(pg->key.port->br, pg); + /* a notification has already been sent and we shouldn't + * access pg after the delete so we have to return false + */ + changed = false; + } + return changed; } @@ -2257,8 +2320,8 @@ static int br_ip4_multicast_igmp3_report(struct net_bridge *br, struct igmpv3_report *ih; struct igmpv3_grec *grec; int i, len, num, type; + __be32 group, *h_addr; bool changed = false; - __be32 group; int err = 0; u16 nsrcs; @@ -2318,32 +2381,33 @@ static int br_ip4_multicast_igmp3_report(struct net_bridge *br, pg = br_multicast_find_port(mdst, port, src); if (!pg || (pg->flags & MDB_PG_FLAGS_PERMANENT)) goto unlock_continue; - /* reload grec */ + /* reload grec and host addr */ grec = (void *)(skb->data + len - sizeof(*grec) - (nsrcs * 4)); + h_addr = &ip_hdr(skb)->saddr; switch (type) { case IGMPV3_ALLOW_NEW_SOURCES: - changed = br_multicast_isinc_allow(pg, grec->grec_src, - nsrcs, sizeof(__be32)); + changed = br_multicast_isinc_allow(pg, h_addr, grec->grec_src, + nsrcs, sizeof(__be32), type); break; case IGMPV3_MODE_IS_INCLUDE: - changed = br_multicast_isinc_allow(pg, grec->grec_src, nsrcs, - sizeof(__be32)); + changed = br_multicast_isinc_allow(pg, h_addr, grec->grec_src, + nsrcs, sizeof(__be32), type); break; case IGMPV3_MODE_IS_EXCLUDE: - changed = br_multicast_isexc(pg, grec->grec_src, nsrcs, - sizeof(__be32)); + changed = br_multicast_isexc(pg, h_addr, grec->grec_src, + nsrcs, sizeof(__be32), type); break; case IGMPV3_CHANGE_TO_INCLUDE: - changed = br_multicast_toin(pg, grec->grec_src, nsrcs, - sizeof(__be32)); + changed = br_multicast_toin(pg, h_addr, grec->grec_src, + nsrcs, sizeof(__be32), type); break; case IGMPV3_CHANGE_TO_EXCLUDE: - changed = br_multicast_toex(pg, grec->grec_src, nsrcs, - sizeof(__be32)); + changed = br_multicast_toex(pg, h_addr, grec->grec_src, + nsrcs, sizeof(__be32), type); break; case IGMPV3_BLOCK_OLD_SOURCES: - changed = br_multicast_block(pg, grec->grec_src, nsrcs, - sizeof(__be32)); + changed = br_multicast_block(pg, h_addr, grec->grec_src, + nsrcs, sizeof(__be32), type); break; } if (changed) @@ -2367,6 +2431,7 @@ static int br_ip6_multicast_mld2_report(struct net_bridge *br, unsigned int nsrcs_offset; const unsigned char *src; struct icmp6hdr *icmp6h; + struct in6_addr *h_addr; struct mld2_grec *grec; unsigned int grec_len; bool changed = false; @@ -2445,31 +2510,43 @@ static int br_ip6_multicast_mld2_report(struct net_bridge *br, pg = br_multicast_find_port(mdst, port, src); if (!pg || (pg->flags & MDB_PG_FLAGS_PERMANENT)) goto unlock_continue; + h_addr = &ipv6_hdr(skb)->saddr; switch (grec->grec_type) { case MLD2_ALLOW_NEW_SOURCES: - changed = br_multicast_isinc_allow(pg, grec->grec_src, - nsrcs, - sizeof(struct in6_addr)); + changed = br_multicast_isinc_allow(pg, h_addr, + grec->grec_src, nsrcs, + sizeof(struct in6_addr), + grec->grec_type); break; case MLD2_MODE_IS_INCLUDE: - changed = br_multicast_isinc_allow(pg, grec->grec_src, nsrcs, - sizeof(struct in6_addr)); + changed = br_multicast_isinc_allow(pg, h_addr, + grec->grec_src, nsrcs, + sizeof(struct in6_addr), + grec->grec_type); break; case MLD2_MODE_IS_EXCLUDE: - changed = br_multicast_isexc(pg, grec->grec_src, nsrcs, - sizeof(struct in6_addr)); + changed = br_multicast_isexc(pg, h_addr, + grec->grec_src, nsrcs, + sizeof(struct in6_addr), + grec->grec_type); break; case MLD2_CHANGE_TO_INCLUDE: - changed = br_multicast_toin(pg, grec->grec_src, nsrcs, - sizeof(struct in6_addr)); + changed = br_multicast_toin(pg, h_addr, + grec->grec_src, nsrcs, + sizeof(struct in6_addr), + grec->grec_type); break; case MLD2_CHANGE_TO_EXCLUDE: - changed = br_multicast_toex(pg, grec->grec_src, nsrcs, - sizeof(struct in6_addr)); + changed = br_multicast_toex(pg, h_addr, + grec->grec_src, nsrcs, + sizeof(struct in6_addr), + grec->grec_type); break; case MLD2_BLOCK_OLD_SOURCES: - changed = br_multicast_block(pg, grec->grec_src, nsrcs, - sizeof(struct in6_addr)); + changed = br_multicast_block(pg, h_addr, + grec->grec_src, nsrcs, + sizeof(struct in6_addr), + grec->grec_type); break; } if (changed) @@ -2568,7 +2645,7 @@ static void br_port_mc_router_state_change(struct net_bridge_port *p, .u.mrouter = is_mc_router, }; - switchdev_port_attr_set(p->dev, &attr); + switchdev_port_attr_set(p->dev, &attr, NULL); } /* diff --git a/net/bridge/br_multicast_eht.c b/net/bridge/br_multicast_eht.c new file mode 100644 index 000000000000..fea38b9a7268 --- /dev/null +++ b/net/bridge/br_multicast_eht.c @@ -0,0 +1,878 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +// Copyright (c) 2020, Nikolay Aleksandrov <nikolay@nvidia.com> +#include <linux/err.h> +#include <linux/export.h> +#include <linux/if_ether.h> +#include <linux/igmp.h> +#include <linux/in.h> +#include <linux/jhash.h> +#include <linux/kernel.h> +#include <linux/log2.h> +#include <linux/netdevice.h> +#include <linux/netfilter_bridge.h> +#include <linux/random.h> +#include <linux/rculist.h> +#include <linux/skbuff.h> +#include <linux/slab.h> +#include <linux/timer.h> +#include <linux/inetdevice.h> +#include <linux/mroute.h> +#include <net/ip.h> +#include <net/switchdev.h> +#if IS_ENABLED(CONFIG_IPV6) +#include <linux/icmpv6.h> +#include <net/ipv6.h> +#include <net/mld.h> +#include <net/ip6_checksum.h> +#include <net/addrconf.h> +#endif + +#include "br_private.h" +#include "br_private_mcast_eht.h" + +static bool br_multicast_del_eht_set_entry(struct net_bridge_port_group *pg, + union net_bridge_eht_addr *src_addr, + union net_bridge_eht_addr *h_addr); +static void br_multicast_create_eht_set_entry(struct net_bridge_port_group *pg, + union net_bridge_eht_addr *src_addr, + union net_bridge_eht_addr *h_addr, + int filter_mode, + bool allow_zero_src); + +static struct net_bridge_group_eht_host * +br_multicast_eht_host_lookup(struct net_bridge_port_group *pg, + union net_bridge_eht_addr *h_addr) +{ + struct rb_node *node = pg->eht_host_tree.rb_node; + + while (node) { + struct net_bridge_group_eht_host *this; + int result; + + this = rb_entry(node, struct net_bridge_group_eht_host, + rb_node); + result = memcmp(h_addr, &this->h_addr, sizeof(*h_addr)); + if (result < 0) + node = node->rb_left; + else if (result > 0) + node = node->rb_right; + else + return this; + } + + return NULL; +} + +static int br_multicast_eht_host_filter_mode(struct net_bridge_port_group *pg, + union net_bridge_eht_addr *h_addr) +{ + struct net_bridge_group_eht_host *eht_host; + + eht_host = br_multicast_eht_host_lookup(pg, h_addr); + if (!eht_host) + return MCAST_INCLUDE; + + return eht_host->filter_mode; +} + +static struct net_bridge_group_eht_set_entry * +br_multicast_eht_set_entry_lookup(struct net_bridge_group_eht_set *eht_set, + union net_bridge_eht_addr *h_addr) +{ + struct rb_node *node = eht_set->entry_tree.rb_node; + + while (node) { + struct net_bridge_group_eht_set_entry *this; + int result; + + this = rb_entry(node, struct net_bridge_group_eht_set_entry, + rb_node); + result = memcmp(h_addr, &this->h_addr, sizeof(*h_addr)); + if (result < 0) + node = node->rb_left; + else if (result > 0) + node = node->rb_right; + else + return this; + } + + return NULL; +} + +static struct net_bridge_group_eht_set * +br_multicast_eht_set_lookup(struct net_bridge_port_group *pg, + union net_bridge_eht_addr *src_addr) +{ + struct rb_node *node = pg->eht_set_tree.rb_node; + + while (node) { + struct net_bridge_group_eht_set *this; + int result; + + this = rb_entry(node, struct net_bridge_group_eht_set, + rb_node); + result = memcmp(src_addr, &this->src_addr, sizeof(*src_addr)); + if (result < 0) + node = node->rb_left; + else if (result > 0) + node = node->rb_right; + else + return this; + } + + return NULL; +} + +static void __eht_destroy_host(struct net_bridge_group_eht_host *eht_host) +{ + WARN_ON(!hlist_empty(&eht_host->set_entries)); + + br_multicast_eht_hosts_dec(eht_host->pg); + + rb_erase(&eht_host->rb_node, &eht_host->pg->eht_host_tree); + RB_CLEAR_NODE(&eht_host->rb_node); + kfree(eht_host); +} + +static void br_multicast_destroy_eht_set_entry(struct net_bridge_mcast_gc *gc) +{ + struct net_bridge_group_eht_set_entry *set_h; + + set_h = container_of(gc, struct net_bridge_group_eht_set_entry, mcast_gc); + WARN_ON(!RB_EMPTY_NODE(&set_h->rb_node)); + + del_timer_sync(&set_h->timer); + kfree(set_h); +} + +static void br_multicast_destroy_eht_set(struct net_bridge_mcast_gc *gc) +{ + struct net_bridge_group_eht_set *eht_set; + + eht_set = container_of(gc, struct net_bridge_group_eht_set, mcast_gc); + WARN_ON(!RB_EMPTY_NODE(&eht_set->rb_node)); + WARN_ON(!RB_EMPTY_ROOT(&eht_set->entry_tree)); + + del_timer_sync(&eht_set->timer); + kfree(eht_set); +} + +static void __eht_del_set_entry(struct net_bridge_group_eht_set_entry *set_h) +{ + struct net_bridge_group_eht_host *eht_host = set_h->h_parent; + union net_bridge_eht_addr zero_addr; + + rb_erase(&set_h->rb_node, &set_h->eht_set->entry_tree); + RB_CLEAR_NODE(&set_h->rb_node); + hlist_del_init(&set_h->host_list); + memset(&zero_addr, 0, sizeof(zero_addr)); + if (memcmp(&set_h->h_addr, &zero_addr, sizeof(zero_addr))) + eht_host->num_entries--; + hlist_add_head(&set_h->mcast_gc.gc_node, &set_h->br->mcast_gc_list); + queue_work(system_long_wq, &set_h->br->mcast_gc_work); + + if (hlist_empty(&eht_host->set_entries)) + __eht_destroy_host(eht_host); +} + +static void br_multicast_del_eht_set(struct net_bridge_group_eht_set *eht_set) +{ + struct net_bridge_group_eht_set_entry *set_h; + struct rb_node *node; + + while ((node = rb_first(&eht_set->entry_tree))) { + set_h = rb_entry(node, struct net_bridge_group_eht_set_entry, + rb_node); + __eht_del_set_entry(set_h); + } + + rb_erase(&eht_set->rb_node, &eht_set->pg->eht_set_tree); + RB_CLEAR_NODE(&eht_set->rb_node); + hlist_add_head(&eht_set->mcast_gc.gc_node, &eht_set->br->mcast_gc_list); + queue_work(system_long_wq, &eht_set->br->mcast_gc_work); +} + +void br_multicast_eht_clean_sets(struct net_bridge_port_group *pg) +{ + struct net_bridge_group_eht_set *eht_set; + struct rb_node *node; + + while ((node = rb_first(&pg->eht_set_tree))) { + eht_set = rb_entry(node, struct net_bridge_group_eht_set, + rb_node); + br_multicast_del_eht_set(eht_set); + } +} + +static void br_multicast_eht_set_entry_expired(struct timer_list *t) +{ + struct net_bridge_group_eht_set_entry *set_h = from_timer(set_h, t, timer); + struct net_bridge *br = set_h->br; + + spin_lock(&br->multicast_lock); + if (RB_EMPTY_NODE(&set_h->rb_node) || timer_pending(&set_h->timer)) + goto out; + + br_multicast_del_eht_set_entry(set_h->eht_set->pg, + &set_h->eht_set->src_addr, + &set_h->h_addr); +out: + spin_unlock(&br->multicast_lock); +} + +static void br_multicast_eht_set_expired(struct timer_list *t) +{ + struct net_bridge_group_eht_set *eht_set = from_timer(eht_set, t, + timer); + struct net_bridge *br = eht_set->br; + + spin_lock(&br->multicast_lock); + if (RB_EMPTY_NODE(&eht_set->rb_node) || timer_pending(&eht_set->timer)) + goto out; + + br_multicast_del_eht_set(eht_set); +out: + spin_unlock(&br->multicast_lock); +} + +static struct net_bridge_group_eht_host * +__eht_lookup_create_host(struct net_bridge_port_group *pg, + union net_bridge_eht_addr *h_addr, + unsigned char filter_mode) +{ + struct rb_node **link = &pg->eht_host_tree.rb_node, *parent = NULL; + struct net_bridge_group_eht_host *eht_host; + + while (*link) { + struct net_bridge_group_eht_host *this; + int result; + + this = rb_entry(*link, struct net_bridge_group_eht_host, + rb_node); + result = memcmp(h_addr, &this->h_addr, sizeof(*h_addr)); + parent = *link; + if (result < 0) + link = &((*link)->rb_left); + else if (result > 0) + link = &((*link)->rb_right); + else + return this; + } + + if (br_multicast_eht_hosts_over_limit(pg)) + return NULL; + + eht_host = kzalloc(sizeof(*eht_host), GFP_ATOMIC); + if (!eht_host) + return NULL; + + memcpy(&eht_host->h_addr, h_addr, sizeof(*h_addr)); + INIT_HLIST_HEAD(&eht_host->set_entries); + eht_host->pg = pg; + eht_host->filter_mode = filter_mode; + + rb_link_node(&eht_host->rb_node, parent, link); + rb_insert_color(&eht_host->rb_node, &pg->eht_host_tree); + + br_multicast_eht_hosts_inc(pg); + + return eht_host; +} + +static struct net_bridge_group_eht_set_entry * +__eht_lookup_create_set_entry(struct net_bridge *br, + struct net_bridge_group_eht_set *eht_set, + struct net_bridge_group_eht_host *eht_host, + bool allow_zero_src) +{ + struct rb_node **link = &eht_set->entry_tree.rb_node, *parent = NULL; + struct net_bridge_group_eht_set_entry *set_h; + + while (*link) { + struct net_bridge_group_eht_set_entry *this; + int result; + + this = rb_entry(*link, struct net_bridge_group_eht_set_entry, + rb_node); + result = memcmp(&eht_host->h_addr, &this->h_addr, + sizeof(union net_bridge_eht_addr)); + parent = *link; + if (result < 0) + link = &((*link)->rb_left); + else if (result > 0) + link = &((*link)->rb_right); + else + return this; + } + + /* always allow auto-created zero entry */ + if (!allow_zero_src && eht_host->num_entries >= PG_SRC_ENT_LIMIT) + return NULL; + + set_h = kzalloc(sizeof(*set_h), GFP_ATOMIC); + if (!set_h) + return NULL; + + memcpy(&set_h->h_addr, &eht_host->h_addr, + sizeof(union net_bridge_eht_addr)); + set_h->mcast_gc.destroy = br_multicast_destroy_eht_set_entry; + set_h->eht_set = eht_set; + set_h->h_parent = eht_host; + set_h->br = br; + timer_setup(&set_h->timer, br_multicast_eht_set_entry_expired, 0); + + hlist_add_head(&set_h->host_list, &eht_host->set_entries); + rb_link_node(&set_h->rb_node, parent, link); + rb_insert_color(&set_h->rb_node, &eht_set->entry_tree); + /* we must not count the auto-created zero entry otherwise we won't be + * able to track the full list of PG_SRC_ENT_LIMIT entries + */ + if (!allow_zero_src) + eht_host->num_entries++; + + return set_h; +} + +static struct net_bridge_group_eht_set * +__eht_lookup_create_set(struct net_bridge_port_group *pg, + union net_bridge_eht_addr *src_addr) +{ + struct rb_node **link = &pg->eht_set_tree.rb_node, *parent = NULL; + struct net_bridge_group_eht_set *eht_set; + + while (*link) { + struct net_bridge_group_eht_set *this; + int result; + + this = rb_entry(*link, struct net_bridge_group_eht_set, + rb_node); + result = memcmp(src_addr, &this->src_addr, sizeof(*src_addr)); + parent = *link; + if (result < 0) + link = &((*link)->rb_left); + else if (result > 0) + link = &((*link)->rb_right); + else + return this; + } + + eht_set = kzalloc(sizeof(*eht_set), GFP_ATOMIC); + if (!eht_set) + return NULL; + + memcpy(&eht_set->src_addr, src_addr, sizeof(*src_addr)); + eht_set->mcast_gc.destroy = br_multicast_destroy_eht_set; + eht_set->pg = pg; + eht_set->br = pg->key.port->br; + eht_set->entry_tree = RB_ROOT; + timer_setup(&eht_set->timer, br_multicast_eht_set_expired, 0); + + rb_link_node(&eht_set->rb_node, parent, link); + rb_insert_color(&eht_set->rb_node, &pg->eht_set_tree); + + return eht_set; +} + +static void br_multicast_ip_src_to_eht_addr(const struct br_ip *src, + union net_bridge_eht_addr *dest) +{ + switch (src->proto) { + case htons(ETH_P_IP): + dest->ip4 = src->src.ip4; + break; +#if IS_ENABLED(CONFIG_IPV6) + case htons(ETH_P_IPV6): + memcpy(&dest->ip6, &src->src.ip6, sizeof(struct in6_addr)); + break; +#endif + } +} + +static void br_eht_convert_host_filter_mode(struct net_bridge_port_group *pg, + union net_bridge_eht_addr *h_addr, + int filter_mode) +{ + struct net_bridge_group_eht_host *eht_host; + union net_bridge_eht_addr zero_addr; + + eht_host = br_multicast_eht_host_lookup(pg, h_addr); + if (eht_host) + eht_host->filter_mode = filter_mode; + + memset(&zero_addr, 0, sizeof(zero_addr)); + switch (filter_mode) { + case MCAST_INCLUDE: + br_multicast_del_eht_set_entry(pg, &zero_addr, h_addr); + break; + case MCAST_EXCLUDE: + br_multicast_create_eht_set_entry(pg, &zero_addr, h_addr, + MCAST_EXCLUDE, + true); + break; + } +} + +static void br_multicast_create_eht_set_entry(struct net_bridge_port_group *pg, + union net_bridge_eht_addr *src_addr, + union net_bridge_eht_addr *h_addr, + int filter_mode, + bool allow_zero_src) +{ + struct net_bridge_group_eht_set_entry *set_h; + struct net_bridge_group_eht_host *eht_host; + struct net_bridge *br = pg->key.port->br; + struct net_bridge_group_eht_set *eht_set; + union net_bridge_eht_addr zero_addr; + + memset(&zero_addr, 0, sizeof(zero_addr)); + if (!allow_zero_src && !memcmp(src_addr, &zero_addr, sizeof(zero_addr))) + return; + + eht_set = __eht_lookup_create_set(pg, src_addr); + if (!eht_set) + return; + + eht_host = __eht_lookup_create_host(pg, h_addr, filter_mode); + if (!eht_host) + goto fail_host; + + set_h = __eht_lookup_create_set_entry(br, eht_set, eht_host, + allow_zero_src); + if (!set_h) + goto fail_set_entry; + + mod_timer(&set_h->timer, jiffies + br_multicast_gmi(br)); + mod_timer(&eht_set->timer, jiffies + br_multicast_gmi(br)); + + return; + +fail_set_entry: + if (hlist_empty(&eht_host->set_entries)) + __eht_destroy_host(eht_host); +fail_host: + if (RB_EMPTY_ROOT(&eht_set->entry_tree)) + br_multicast_del_eht_set(eht_set); +} + +static bool br_multicast_del_eht_set_entry(struct net_bridge_port_group *pg, + union net_bridge_eht_addr *src_addr, + union net_bridge_eht_addr *h_addr) +{ + struct net_bridge_group_eht_set_entry *set_h; + struct net_bridge_group_eht_set *eht_set; + bool set_deleted = false; + + eht_set = br_multicast_eht_set_lookup(pg, src_addr); + if (!eht_set) + goto out; + + set_h = br_multicast_eht_set_entry_lookup(eht_set, h_addr); + if (!set_h) + goto out; + + __eht_del_set_entry(set_h); + + if (RB_EMPTY_ROOT(&eht_set->entry_tree)) { + br_multicast_del_eht_set(eht_set); + set_deleted = true; + } + +out: + return set_deleted; +} + +static void br_multicast_del_eht_host(struct net_bridge_port_group *pg, + union net_bridge_eht_addr *h_addr) +{ + struct net_bridge_group_eht_set_entry *set_h; + struct net_bridge_group_eht_host *eht_host; + struct hlist_node *tmp; + + eht_host = br_multicast_eht_host_lookup(pg, h_addr); + if (!eht_host) + return; + + hlist_for_each_entry_safe(set_h, tmp, &eht_host->set_entries, host_list) + br_multicast_del_eht_set_entry(set_h->eht_set->pg, + &set_h->eht_set->src_addr, + &set_h->h_addr); +} + +static void __eht_allow_incl(struct net_bridge_port_group *pg, + union net_bridge_eht_addr *h_addr, + void *srcs, + u32 nsrcs, + size_t addr_size) +{ + union net_bridge_eht_addr eht_src_addr; + u32 src_idx; + + memset(&eht_src_addr, 0, sizeof(eht_src_addr)); + for (src_idx = 0; src_idx < nsrcs; src_idx++) { + memcpy(&eht_src_addr, srcs + (src_idx * addr_size), addr_size); + br_multicast_create_eht_set_entry(pg, &eht_src_addr, h_addr, + MCAST_INCLUDE, + false); + } +} + +static bool __eht_allow_excl(struct net_bridge_port_group *pg, + union net_bridge_eht_addr *h_addr, + void *srcs, + u32 nsrcs, + size_t addr_size) +{ + bool changed = false, host_excl = false; + union net_bridge_eht_addr eht_src_addr; + struct net_bridge_group_src *src_ent; + struct br_ip src_ip; + u32 src_idx; + + host_excl = !!(br_multicast_eht_host_filter_mode(pg, h_addr) == MCAST_EXCLUDE); + memset(&eht_src_addr, 0, sizeof(eht_src_addr)); + for (src_idx = 0; src_idx < nsrcs; src_idx++) { + memcpy(&eht_src_addr, srcs + (src_idx * addr_size), addr_size); + if (!host_excl) { + br_multicast_create_eht_set_entry(pg, &eht_src_addr, h_addr, + MCAST_INCLUDE, + false); + } else { + if (!br_multicast_del_eht_set_entry(pg, &eht_src_addr, + h_addr)) + continue; + memcpy(&src_ip, srcs + (src_idx * addr_size), addr_size); + src_ent = br_multicast_find_group_src(pg, &src_ip); + if (!src_ent) + continue; + br_multicast_del_group_src(src_ent, true); + changed = true; + } + } + + return changed; +} + +static bool br_multicast_eht_allow(struct net_bridge_port_group *pg, + union net_bridge_eht_addr *h_addr, + void *srcs, + u32 nsrcs, + size_t addr_size) +{ + bool changed = false; + + switch (br_multicast_eht_host_filter_mode(pg, h_addr)) { + case MCAST_INCLUDE: + __eht_allow_incl(pg, h_addr, srcs, nsrcs, addr_size); + break; + case MCAST_EXCLUDE: + changed = __eht_allow_excl(pg, h_addr, srcs, nsrcs, addr_size); + break; + } + + return changed; +} + +static bool __eht_block_incl(struct net_bridge_port_group *pg, + union net_bridge_eht_addr *h_addr, + void *srcs, + u32 nsrcs, + size_t addr_size) +{ + union net_bridge_eht_addr eht_src_addr; + struct net_bridge_group_src *src_ent; + bool changed = false; + struct br_ip src_ip; + u32 src_idx; + + memset(&eht_src_addr, 0, sizeof(eht_src_addr)); + memset(&src_ip, 0, sizeof(src_ip)); + src_ip.proto = pg->key.addr.proto; + for (src_idx = 0; src_idx < nsrcs; src_idx++) { + memcpy(&eht_src_addr, srcs + (src_idx * addr_size), addr_size); + if (!br_multicast_del_eht_set_entry(pg, &eht_src_addr, h_addr)) + continue; + memcpy(&src_ip, srcs + (src_idx * addr_size), addr_size); + src_ent = br_multicast_find_group_src(pg, &src_ip); + if (!src_ent) + continue; + br_multicast_del_group_src(src_ent, true); + changed = true; + } + + return changed; +} + +static bool __eht_block_excl(struct net_bridge_port_group *pg, + union net_bridge_eht_addr *h_addr, + void *srcs, + u32 nsrcs, + size_t addr_size) +{ + bool changed = false, host_excl = false; + union net_bridge_eht_addr eht_src_addr; + struct net_bridge_group_src *src_ent; + struct br_ip src_ip; + u32 src_idx; + + host_excl = !!(br_multicast_eht_host_filter_mode(pg, h_addr) == MCAST_EXCLUDE); + memset(&eht_src_addr, 0, sizeof(eht_src_addr)); + memset(&src_ip, 0, sizeof(src_ip)); + src_ip.proto = pg->key.addr.proto; + for (src_idx = 0; src_idx < nsrcs; src_idx++) { + memcpy(&eht_src_addr, srcs + (src_idx * addr_size), addr_size); + if (host_excl) { + br_multicast_create_eht_set_entry(pg, &eht_src_addr, h_addr, + MCAST_EXCLUDE, + false); + } else { + if (!br_multicast_del_eht_set_entry(pg, &eht_src_addr, + h_addr)) + continue; + memcpy(&src_ip, srcs + (src_idx * addr_size), addr_size); + src_ent = br_multicast_find_group_src(pg, &src_ip); + if (!src_ent) + continue; + br_multicast_del_group_src(src_ent, true); + changed = true; + } + } + + return changed; +} + +static bool br_multicast_eht_block(struct net_bridge_port_group *pg, + union net_bridge_eht_addr *h_addr, + void *srcs, + u32 nsrcs, + size_t addr_size) +{ + bool changed = false; + + switch (br_multicast_eht_host_filter_mode(pg, h_addr)) { + case MCAST_INCLUDE: + changed = __eht_block_incl(pg, h_addr, srcs, nsrcs, addr_size); + break; + case MCAST_EXCLUDE: + changed = __eht_block_excl(pg, h_addr, srcs, nsrcs, addr_size); + break; + } + + return changed; +} + +/* flush_entries is true when changing mode */ +static bool __eht_inc_exc(struct net_bridge_port_group *pg, + union net_bridge_eht_addr *h_addr, + void *srcs, + u32 nsrcs, + size_t addr_size, + unsigned char filter_mode, + bool to_report) +{ + bool changed = false, flush_entries = to_report; + union net_bridge_eht_addr eht_src_addr; + u32 src_idx; + + if (br_multicast_eht_host_filter_mode(pg, h_addr) != filter_mode) + flush_entries = true; + + memset(&eht_src_addr, 0, sizeof(eht_src_addr)); + /* if we're changing mode del host and its entries */ + if (flush_entries) + br_multicast_del_eht_host(pg, h_addr); + for (src_idx = 0; src_idx < nsrcs; src_idx++) { + memcpy(&eht_src_addr, srcs + (src_idx * addr_size), addr_size); + br_multicast_create_eht_set_entry(pg, &eht_src_addr, h_addr, + filter_mode, false); + } + /* we can be missing sets only if we've deleted some entries */ + if (flush_entries) { + struct net_bridge *br = pg->key.port->br; + struct net_bridge_group_eht_set *eht_set; + struct net_bridge_group_src *src_ent; + struct hlist_node *tmp; + + hlist_for_each_entry_safe(src_ent, tmp, &pg->src_list, node) { + br_multicast_ip_src_to_eht_addr(&src_ent->addr, + &eht_src_addr); + if (!br_multicast_eht_set_lookup(pg, &eht_src_addr)) { + br_multicast_del_group_src(src_ent, true); + changed = true; + continue; + } + /* this is an optimization for TO_INCLUDE where we lower + * the set's timeout to LMQT to catch timeout hosts: + * - host A (timing out): set entries X, Y + * - host B: set entry Z (new from current TO_INCLUDE) + * sends BLOCK Z after LMQT but host A's EHT + * entries still exist (unless lowered to LMQT + * so they can timeout with the S,Gs) + * => we wait another LMQT, when we can just delete the + * group immediately + */ + if (!(src_ent->flags & BR_SGRP_F_SEND) || + filter_mode != MCAST_INCLUDE || + !to_report) + continue; + eht_set = br_multicast_eht_set_lookup(pg, + &eht_src_addr); + if (!eht_set) + continue; + mod_timer(&eht_set->timer, jiffies + br_multicast_lmqt(br)); + } + } + + return changed; +} + +static bool br_multicast_eht_inc(struct net_bridge_port_group *pg, + union net_bridge_eht_addr *h_addr, + void *srcs, + u32 nsrcs, + size_t addr_size, + bool to_report) +{ + bool changed; + + changed = __eht_inc_exc(pg, h_addr, srcs, nsrcs, addr_size, + MCAST_INCLUDE, to_report); + br_eht_convert_host_filter_mode(pg, h_addr, MCAST_INCLUDE); + + return changed; +} + +static bool br_multicast_eht_exc(struct net_bridge_port_group *pg, + union net_bridge_eht_addr *h_addr, + void *srcs, + u32 nsrcs, + size_t addr_size, + bool to_report) +{ + bool changed; + + changed = __eht_inc_exc(pg, h_addr, srcs, nsrcs, addr_size, + MCAST_EXCLUDE, to_report); + br_eht_convert_host_filter_mode(pg, h_addr, MCAST_EXCLUDE); + + return changed; +} + +static bool __eht_ip4_handle(struct net_bridge_port_group *pg, + union net_bridge_eht_addr *h_addr, + void *srcs, + u32 nsrcs, + int grec_type) +{ + bool changed = false, to_report = false; + + switch (grec_type) { + case IGMPV3_ALLOW_NEW_SOURCES: + br_multicast_eht_allow(pg, h_addr, srcs, nsrcs, sizeof(__be32)); + break; + case IGMPV3_BLOCK_OLD_SOURCES: + changed = br_multicast_eht_block(pg, h_addr, srcs, nsrcs, + sizeof(__be32)); + break; + case IGMPV3_CHANGE_TO_INCLUDE: + to_report = true; + fallthrough; + case IGMPV3_MODE_IS_INCLUDE: + changed = br_multicast_eht_inc(pg, h_addr, srcs, nsrcs, + sizeof(__be32), to_report); + break; + case IGMPV3_CHANGE_TO_EXCLUDE: + to_report = true; + fallthrough; + case IGMPV3_MODE_IS_EXCLUDE: + changed = br_multicast_eht_exc(pg, h_addr, srcs, nsrcs, + sizeof(__be32), to_report); + break; + } + + return changed; +} + +#if IS_ENABLED(CONFIG_IPV6) +static bool __eht_ip6_handle(struct net_bridge_port_group *pg, + union net_bridge_eht_addr *h_addr, + void *srcs, + u32 nsrcs, + int grec_type) +{ + bool changed = false, to_report = false; + + switch (grec_type) { + case MLD2_ALLOW_NEW_SOURCES: + br_multicast_eht_allow(pg, h_addr, srcs, nsrcs, + sizeof(struct in6_addr)); + break; + case MLD2_BLOCK_OLD_SOURCES: + changed = br_multicast_eht_block(pg, h_addr, srcs, nsrcs, + sizeof(struct in6_addr)); + break; + case MLD2_CHANGE_TO_INCLUDE: + to_report = true; + fallthrough; + case MLD2_MODE_IS_INCLUDE: + changed = br_multicast_eht_inc(pg, h_addr, srcs, nsrcs, + sizeof(struct in6_addr), + to_report); + break; + case MLD2_CHANGE_TO_EXCLUDE: + to_report = true; + fallthrough; + case MLD2_MODE_IS_EXCLUDE: + changed = br_multicast_eht_exc(pg, h_addr, srcs, nsrcs, + sizeof(struct in6_addr), + to_report); + break; + } + + return changed; +} +#endif + +/* true means an entry was deleted */ +bool br_multicast_eht_handle(struct net_bridge_port_group *pg, + void *h_addr, + void *srcs, + u32 nsrcs, + size_t addr_size, + int grec_type) +{ + bool eht_enabled = !!(pg->key.port->flags & BR_MULTICAST_FAST_LEAVE); + union net_bridge_eht_addr eht_host_addr; + bool changed = false; + + if (!eht_enabled) + goto out; + + memset(&eht_host_addr, 0, sizeof(eht_host_addr)); + memcpy(&eht_host_addr, h_addr, addr_size); + if (addr_size == sizeof(__be32)) + changed = __eht_ip4_handle(pg, &eht_host_addr, srcs, nsrcs, + grec_type); +#if IS_ENABLED(CONFIG_IPV6) + else + changed = __eht_ip6_handle(pg, &eht_host_addr, srcs, nsrcs, + grec_type); +#endif + +out: + return changed; +} + +int br_multicast_eht_set_hosts_limit(struct net_bridge_port *p, + u32 eht_hosts_limit) +{ + struct net_bridge *br = p->br; + + if (!eht_hosts_limit) + return -EINVAL; + + spin_lock_bh(&br->multicast_lock); + p->multicast_eht_hosts_limit = eht_hosts_limit; + spin_unlock_bh(&br->multicast_lock); + + return 0; +} diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c index 49700ce0e919..f2b1343f8332 100644 --- a/net/bridge/br_netlink.c +++ b/net/bridge/br_netlink.c @@ -18,6 +18,7 @@ #include "br_private_stp.h" #include "br_private_cfm.h" #include "br_private_tunnel.h" +#include "br_private_mcast_eht.h" static int __get_num_vlan_infos(struct net_bridge_vlan_group *vg, u32 filter_mask) @@ -199,6 +200,8 @@ static inline size_t br_port_info_size(void) + nla_total_size(sizeof(u16)) /* IFLA_BRPORT_GROUP_FWD_MASK */ + nla_total_size(sizeof(u8)) /* IFLA_BRPORT_MRP_RING_OPEN */ + nla_total_size(sizeof(u8)) /* IFLA_BRPORT_MRP_IN_OPEN */ + + nla_total_size(sizeof(u32)) /* IFLA_BRPORT_MCAST_EHT_HOSTS_LIMIT */ + + nla_total_size(sizeof(u32)) /* IFLA_BRPORT_MCAST_EHT_HOSTS_CNT */ + 0; } @@ -283,7 +286,11 @@ static int br_port_fill_attrs(struct sk_buff *skb, #ifdef CONFIG_BRIDGE_IGMP_SNOOPING if (nla_put_u8(skb, IFLA_BRPORT_MULTICAST_ROUTER, - p->multicast_router)) + p->multicast_router) || + nla_put_u32(skb, IFLA_BRPORT_MCAST_EHT_HOSTS_LIMIT, + p->multicast_eht_hosts_limit) || + nla_put_u32(skb, IFLA_BRPORT_MCAST_EHT_HOSTS_CNT, + p->multicast_eht_hosts_cnt)) return -EMSGSIZE; #endif @@ -820,6 +827,7 @@ static const struct nla_policy br_port_policy[IFLA_BRPORT_MAX + 1] = { [IFLA_BRPORT_NEIGH_SUPPRESS] = { .type = NLA_U8 }, [IFLA_BRPORT_ISOLATED] = { .type = NLA_U8 }, [IFLA_BRPORT_BACKUP_PORT] = { .type = NLA_U32 }, + [IFLA_BRPORT_MCAST_EHT_HOSTS_LIMIT] = { .type = NLA_U32 }, }; /* Change the state of the port and notify spanning tree */ @@ -845,87 +853,59 @@ static int br_set_port_state(struct net_bridge_port *p, u8 state) } /* Set/clear or port flags based on attribute */ -static int br_set_port_flag(struct net_bridge_port *p, struct nlattr *tb[], - int attrtype, unsigned long mask) +static void br_set_port_flag(struct net_bridge_port *p, struct nlattr *tb[], + int attrtype, unsigned long mask) { - unsigned long flags; - int err; - if (!tb[attrtype]) - return 0; + return; if (nla_get_u8(tb[attrtype])) - flags = p->flags | mask; + p->flags |= mask; else - flags = p->flags & ~mask; - - err = br_switchdev_set_port_flag(p, flags, mask); - if (err) - return err; - - p->flags = flags; - return 0; + p->flags &= ~mask; } /* Process bridge protocol info on port */ -static int br_setport(struct net_bridge_port *p, struct nlattr *tb[]) +static int br_setport(struct net_bridge_port *p, struct nlattr *tb[], + struct netlink_ext_ack *extack) { - unsigned long old_flags = p->flags; - bool br_vlan_tunnel_old = false; + unsigned long old_flags, changed_mask; + bool br_vlan_tunnel_old; int err; - err = br_set_port_flag(p, tb, IFLA_BRPORT_MODE, BR_HAIRPIN_MODE); - if (err) - return err; - - err = br_set_port_flag(p, tb, IFLA_BRPORT_GUARD, BR_BPDU_GUARD); - if (err) - return err; - - err = br_set_port_flag(p, tb, IFLA_BRPORT_FAST_LEAVE, BR_MULTICAST_FAST_LEAVE); - if (err) - return err; - - err = br_set_port_flag(p, tb, IFLA_BRPORT_PROTECT, BR_ROOT_BLOCK); - if (err) - return err; - - err = br_set_port_flag(p, tb, IFLA_BRPORT_LEARNING, BR_LEARNING); - if (err) - return err; - - err = br_set_port_flag(p, tb, IFLA_BRPORT_UNICAST_FLOOD, BR_FLOOD); - if (err) - return err; - - err = br_set_port_flag(p, tb, IFLA_BRPORT_MCAST_FLOOD, BR_MCAST_FLOOD); - if (err) - return err; - - err = br_set_port_flag(p, tb, IFLA_BRPORT_MCAST_TO_UCAST, BR_MULTICAST_TO_UNICAST); - if (err) - return err; - - err = br_set_port_flag(p, tb, IFLA_BRPORT_BCAST_FLOOD, BR_BCAST_FLOOD); - if (err) - return err; - - err = br_set_port_flag(p, tb, IFLA_BRPORT_PROXYARP, BR_PROXYARP); - if (err) - return err; - - err = br_set_port_flag(p, tb, IFLA_BRPORT_PROXYARP_WIFI, BR_PROXYARP_WIFI); - if (err) - return err; - - br_vlan_tunnel_old = (p->flags & BR_VLAN_TUNNEL) ? true : false; - err = br_set_port_flag(p, tb, IFLA_BRPORT_VLAN_TUNNEL, BR_VLAN_TUNNEL); - if (err) + old_flags = p->flags; + br_vlan_tunnel_old = (old_flags & BR_VLAN_TUNNEL) ? true : false; + + br_set_port_flag(p, tb, IFLA_BRPORT_MODE, BR_HAIRPIN_MODE); + br_set_port_flag(p, tb, IFLA_BRPORT_GUARD, BR_BPDU_GUARD); + br_set_port_flag(p, tb, IFLA_BRPORT_FAST_LEAVE, + BR_MULTICAST_FAST_LEAVE); + br_set_port_flag(p, tb, IFLA_BRPORT_PROTECT, BR_ROOT_BLOCK); + br_set_port_flag(p, tb, IFLA_BRPORT_LEARNING, BR_LEARNING); + br_set_port_flag(p, tb, IFLA_BRPORT_UNICAST_FLOOD, BR_FLOOD); + br_set_port_flag(p, tb, IFLA_BRPORT_MCAST_FLOOD, BR_MCAST_FLOOD); + br_set_port_flag(p, tb, IFLA_BRPORT_MCAST_TO_UCAST, + BR_MULTICAST_TO_UNICAST); + br_set_port_flag(p, tb, IFLA_BRPORT_BCAST_FLOOD, BR_BCAST_FLOOD); + br_set_port_flag(p, tb, IFLA_BRPORT_PROXYARP, BR_PROXYARP); + br_set_port_flag(p, tb, IFLA_BRPORT_PROXYARP_WIFI, BR_PROXYARP_WIFI); + br_set_port_flag(p, tb, IFLA_BRPORT_VLAN_TUNNEL, BR_VLAN_TUNNEL); + br_set_port_flag(p, tb, IFLA_BRPORT_NEIGH_SUPPRESS, BR_NEIGH_SUPPRESS); + br_set_port_flag(p, tb, IFLA_BRPORT_ISOLATED, BR_ISOLATED); + + changed_mask = old_flags ^ p->flags; + + err = br_switchdev_set_port_flag(p, p->flags, changed_mask, extack); + if (err) { + p->flags = old_flags; return err; + } if (br_vlan_tunnel_old && !(p->flags & BR_VLAN_TUNNEL)) nbp_vlan_tunnel_info_flush(p); + br_port_flags_change(p, changed_mask); + if (tb[IFLA_BRPORT_COST]) { err = br_stp_set_path_cost(p, nla_get_u32(tb[IFLA_BRPORT_COST])); if (err) @@ -955,6 +935,15 @@ static int br_setport(struct net_bridge_port *p, struct nlattr *tb[]) if (err) return err; } + + if (tb[IFLA_BRPORT_MCAST_EHT_HOSTS_LIMIT]) { + u32 hlimit; + + hlimit = nla_get_u32(tb[IFLA_BRPORT_MCAST_EHT_HOSTS_LIMIT]); + err = br_multicast_eht_set_hosts_limit(p, hlimit); + if (err) + return err; + } #endif if (tb[IFLA_BRPORT_GROUP_FWD_MASK]) { @@ -965,15 +954,6 @@ static int br_setport(struct net_bridge_port *p, struct nlattr *tb[]) p->group_fwd_mask = fwd_mask; } - err = br_set_port_flag(p, tb, IFLA_BRPORT_NEIGH_SUPPRESS, - BR_NEIGH_SUPPRESS); - if (err) - return err; - - err = br_set_port_flag(p, tb, IFLA_BRPORT_ISOLATED, BR_ISOLATED); - if (err) - return err; - if (tb[IFLA_BRPORT_BACKUP_PORT]) { struct net_device *backup_dev = NULL; u32 backup_ifindex; @@ -991,7 +971,6 @@ static int br_setport(struct net_bridge_port *p, struct nlattr *tb[]) return err; } - br_port_flags_change(p, old_flags ^ p->flags); return 0; } @@ -1029,7 +1008,7 @@ int br_setlink(struct net_device *dev, struct nlmsghdr *nlh, u16 flags, return err; spin_lock_bh(&p->br->lock); - err = br_setport(p, tb); + err = br_setport(p, tb, extack); spin_unlock_bh(&p->br->lock); } else { /* Binary compatibility with old RSTP */ @@ -1096,15 +1075,9 @@ static int br_validate(struct nlattr *tb[], struct nlattr *data[], return 0; #ifdef CONFIG_BRIDGE_VLAN_FILTERING - if (data[IFLA_BR_VLAN_PROTOCOL]) { - switch (nla_get_be16(data[IFLA_BR_VLAN_PROTOCOL])) { - case htons(ETH_P_8021Q): - case htons(ETH_P_8021AD): - break; - default: - return -EPROTONOSUPPORT; - } - } + if (data[IFLA_BR_VLAN_PROTOCOL] && + !eth_type_vlan(nla_get_be16(data[IFLA_BR_VLAN_PROTOCOL]))) + return -EPROTONOSUPPORT; if (data[IFLA_BR_VLAN_DEFAULT_PVID]) { __u16 defpvid = nla_get_u16(data[IFLA_BR_VLAN_DEFAULT_PVID]); @@ -1130,7 +1103,7 @@ static int br_port_slave_changelink(struct net_device *brdev, return 0; spin_lock_bh(&br->lock); - ret = br_setport(br_port_get_rtnl(dev), data); + ret = br_setport(br_port_get_rtnl(dev), data, extack); spin_unlock_bh(&br->lock); return ret; @@ -1239,7 +1212,7 @@ static int br_changelink(struct net_device *brdev, struct nlattr *tb[], if (data[IFLA_BR_VLAN_FILTERING]) { u8 vlan_filter = nla_get_u8(data[IFLA_BR_VLAN_FILTERING]); - err = __br_vlan_filter_toggle(br, vlan_filter); + err = br_vlan_filter_toggle(br, vlan_filter, extack); if (err) return err; } @@ -1248,7 +1221,7 @@ static int br_changelink(struct net_device *brdev, struct nlattr *tb[], if (data[IFLA_BR_VLAN_PROTOCOL]) { __be16 vlan_proto = nla_get_be16(data[IFLA_BR_VLAN_PROTOCOL]); - err = __br_vlan_set_proto(br, vlan_proto); + err = __br_vlan_set_proto(br, vlan_proto, extack); if (err) return err; } diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h index d62c6e1af64a..d7d167e10b70 100644 --- a/net/bridge/br_private.h +++ b/net/bridge/br_private.h @@ -252,6 +252,8 @@ struct net_bridge_port_group { struct timer_list timer; struct timer_list rexmit_timer; struct hlist_node mglist; + struct rb_root eht_set_tree; + struct rb_root eht_host_tree; struct rhash_head rhnode; struct net_bridge_mcast_gc mcast_gc; @@ -308,6 +310,8 @@ struct net_bridge_port { #if IS_ENABLED(CONFIG_IPV6) struct bridge_mcast_own_query ip6_own_query; #endif /* IS_ENABLED(CONFIG_IPV6) */ + u32 multicast_eht_hosts_limit; + u32 multicast_eht_hosts_cnt; unsigned char multicast_router; struct bridge_mcast_stats __percpu *mcast_stats; struct timer_list multicast_router_timer; @@ -846,6 +850,10 @@ void br_multicast_star_g_handle_mode(struct net_bridge_port_group *pg, u8 filter_mode); void br_multicast_sg_add_exclude_ports(struct net_bridge_mdb_entry *star_mp, struct net_bridge_port_group *sg); +struct net_bridge_group_src * +br_multicast_find_group_src(struct net_bridge_port_group *pg, struct br_ip *ip); +void br_multicast_del_group_src(struct net_bridge_group_src *src, + bool fastleave); static inline bool br_group_is_l2(const struct br_ip *group) { @@ -1077,14 +1085,17 @@ int br_vlan_delete(struct net_bridge *br, u16 vid); void br_vlan_flush(struct net_bridge *br); struct net_bridge_vlan *br_vlan_find(struct net_bridge_vlan_group *vg, u16 vid); void br_recalculate_fwd_mask(struct net_bridge *br); -int __br_vlan_filter_toggle(struct net_bridge *br, unsigned long val); -int br_vlan_filter_toggle(struct net_bridge *br, unsigned long val); -int __br_vlan_set_proto(struct net_bridge *br, __be16 proto); -int br_vlan_set_proto(struct net_bridge *br, unsigned long val); +int br_vlan_filter_toggle(struct net_bridge *br, unsigned long val, + struct netlink_ext_ack *extack); +int __br_vlan_set_proto(struct net_bridge *br, __be16 proto, + struct netlink_ext_ack *extack); +int br_vlan_set_proto(struct net_bridge *br, unsigned long val, + struct netlink_ext_ack *extack); int br_vlan_set_stats(struct net_bridge *br, unsigned long val); int br_vlan_set_stats_per_port(struct net_bridge *br, unsigned long val); int br_vlan_init(struct net_bridge *br); -int br_vlan_set_default_pvid(struct net_bridge *br, unsigned long val); +int br_vlan_set_default_pvid(struct net_bridge *br, unsigned long val, + struct netlink_ext_ack *extack); int __br_vlan_set_default_pvid(struct net_bridge *br, u16 pvid, struct netlink_ext_ack *extack); int nbp_vlan_add(struct net_bridge_port *port, u16 vid, u16 flags, @@ -1253,8 +1264,9 @@ static inline u16 br_get_pvid(const struct net_bridge_vlan_group *vg) return 0; } -static inline int __br_vlan_filter_toggle(struct net_bridge *br, - unsigned long val) +static inline int br_vlan_filter_toggle(struct net_bridge *br, + unsigned long val, + struct netlink_ext_ack *extack) { return -EOPNOTSUPP; } @@ -1567,7 +1579,8 @@ bool nbp_switchdev_allowed_egress(const struct net_bridge_port *p, const struct sk_buff *skb); int br_switchdev_set_port_flag(struct net_bridge_port *p, unsigned long flags, - unsigned long mask); + unsigned long mask, + struct netlink_ext_ack *extack); void br_switchdev_fdb_notify(const struct net_bridge_fdb_entry *fdb, int type); int br_switchdev_port_vlan_add(struct net_device *dev, u16 vid, u16 flags, @@ -1597,7 +1610,8 @@ static inline bool nbp_switchdev_allowed_egress(const struct net_bridge_port *p, static inline int br_switchdev_set_port_flag(struct net_bridge_port *p, unsigned long flags, - unsigned long mask) + unsigned long mask, + struct netlink_ext_ack *extack) { return 0; } diff --git a/net/bridge/br_private_mcast_eht.h b/net/bridge/br_private_mcast_eht.h new file mode 100644 index 000000000000..f89049f4892c --- /dev/null +++ b/net/bridge/br_private_mcast_eht.h @@ -0,0 +1,93 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later + * Copyright (c) 2020, Nikolay Aleksandrov <nikolay@nvidia.com> + */ +#ifndef _BR_PRIVATE_MCAST_EHT_H_ +#define _BR_PRIVATE_MCAST_EHT_H_ + +#define BR_MCAST_DEFAULT_EHT_HOSTS_LIMIT 512 + +union net_bridge_eht_addr { + __be32 ip4; +#if IS_ENABLED(CONFIG_IPV6) + struct in6_addr ip6; +#endif +}; + +/* single host's list of set entries and filter_mode */ +struct net_bridge_group_eht_host { + struct rb_node rb_node; + + union net_bridge_eht_addr h_addr; + struct hlist_head set_entries; + unsigned int num_entries; + unsigned char filter_mode; + struct net_bridge_port_group *pg; +}; + +/* (host, src entry) added to a per-src set and host's list */ +struct net_bridge_group_eht_set_entry { + struct rb_node rb_node; + struct hlist_node host_list; + + union net_bridge_eht_addr h_addr; + struct timer_list timer; + struct net_bridge *br; + struct net_bridge_group_eht_set *eht_set; + struct net_bridge_group_eht_host *h_parent; + struct net_bridge_mcast_gc mcast_gc; +}; + +/* per-src set */ +struct net_bridge_group_eht_set { + struct rb_node rb_node; + + union net_bridge_eht_addr src_addr; + struct rb_root entry_tree; + struct timer_list timer; + struct net_bridge_port_group *pg; + struct net_bridge *br; + struct net_bridge_mcast_gc mcast_gc; +}; + +#ifdef CONFIG_BRIDGE_IGMP_SNOOPING +void br_multicast_eht_clean_sets(struct net_bridge_port_group *pg); +bool br_multicast_eht_handle(struct net_bridge_port_group *pg, + void *h_addr, + void *srcs, + u32 nsrcs, + size_t addr_size, + int grec_type); +int br_multicast_eht_set_hosts_limit(struct net_bridge_port *p, + u32 eht_hosts_limit); + +static inline bool +br_multicast_eht_should_del_pg(const struct net_bridge_port_group *pg) +{ + return !!((pg->key.port->flags & BR_MULTICAST_FAST_LEAVE) && + RB_EMPTY_ROOT(&pg->eht_host_tree)); +} + +static inline bool +br_multicast_eht_hosts_over_limit(const struct net_bridge_port_group *pg) +{ + const struct net_bridge_port *p = pg->key.port; + + return !!(p->multicast_eht_hosts_cnt >= p->multicast_eht_hosts_limit); +} + +static inline void br_multicast_eht_hosts_inc(struct net_bridge_port_group *pg) +{ + struct net_bridge_port *p = pg->key.port; + + p->multicast_eht_hosts_cnt++; +} + +static inline void br_multicast_eht_hosts_dec(struct net_bridge_port_group *pg) +{ + struct net_bridge_port *p = pg->key.port; + + p->multicast_eht_hosts_cnt--; +} +#endif /* CONFIG_BRIDGE_IGMP_SNOOPING */ + +#endif /* _BR_PRIVATE_MCAST_EHT_H_ */ diff --git a/net/bridge/br_private_mrp.h b/net/bridge/br_private_mrp.h index 2514954c1431..9559aa2750fb 100644 --- a/net/bridge/br_private_mrp.h +++ b/net/bridge/br_private_mrp.h @@ -46,6 +46,20 @@ struct br_mrp { struct rcu_head rcu; }; +/* This type is returned by br_mrp_switchdev functions that allow to have a SW + * backup in case the HW can't implement completely the protocol. + * BR_MRP_NONE - means the HW can't run at all the protocol, so the SW stops + * configuring the node anymore. + * BR_MRP_SW - the HW can help the SW to run the protocol, by redirecting MRP + * frames to CPU. + * BR_MRP_HW - the HW can implement completely the protocol. + */ +enum br_mrp_hw_support { + BR_MRP_NONE, + BR_MRP_SW, + BR_MRP_HW, +}; + /* br_mrp.c */ int br_mrp_add(struct net_bridge *br, struct br_mrp_instance *instance); int br_mrp_del(struct net_bridge *br, struct br_mrp_instance *instance); @@ -65,23 +79,27 @@ int br_mrp_start_in_test(struct net_bridge *br, /* br_mrp_switchdev.c */ int br_mrp_switchdev_add(struct net_bridge *br, struct br_mrp *mrp); int br_mrp_switchdev_del(struct net_bridge *br, struct br_mrp *mrp); -int br_mrp_switchdev_set_ring_role(struct net_bridge *br, struct br_mrp *mrp, - enum br_mrp_ring_role_type role); +enum br_mrp_hw_support +br_mrp_switchdev_set_ring_role(struct net_bridge *br, struct br_mrp *mrp, + enum br_mrp_ring_role_type role); int br_mrp_switchdev_set_ring_state(struct net_bridge *br, struct br_mrp *mrp, enum br_mrp_ring_state_type state); -int br_mrp_switchdev_send_ring_test(struct net_bridge *br, struct br_mrp *mrp, - u32 interval, u8 max_miss, u32 period, - bool monitor); +enum br_mrp_hw_support +br_mrp_switchdev_send_ring_test(struct net_bridge *br, struct br_mrp *mrp, + u32 interval, u8 max_miss, u32 period, + bool monitor); int br_mrp_port_switchdev_set_state(struct net_bridge_port *p, u32 state); int br_mrp_port_switchdev_set_role(struct net_bridge_port *p, enum br_mrp_port_role_type role); -int br_mrp_switchdev_set_in_role(struct net_bridge *br, struct br_mrp *mrp, - u16 in_id, u32 ring_id, - enum br_mrp_in_role_type role); +enum br_mrp_hw_support +br_mrp_switchdev_set_in_role(struct net_bridge *br, struct br_mrp *mrp, + u16 in_id, u32 ring_id, + enum br_mrp_in_role_type role); int br_mrp_switchdev_set_in_state(struct net_bridge *br, struct br_mrp *mrp, enum br_mrp_in_state_type state); -int br_mrp_switchdev_send_in_test(struct net_bridge *br, struct br_mrp *mrp, - u32 interval, u8 max_miss, u32 period); +enum br_mrp_hw_support +br_mrp_switchdev_send_in_test(struct net_bridge *br, struct br_mrp *mrp, + u32 interval, u8 max_miss, u32 period); /* br_mrp_netlink.c */ int br_mrp_ring_port_open(struct net_device *dev, u8 loc); diff --git a/net/bridge/br_stp.c b/net/bridge/br_stp.c index 3e88be7aa269..21c6781906aa 100644 --- a/net/bridge/br_stp.c +++ b/net/bridge/br_stp.c @@ -43,7 +43,7 @@ void br_set_state(struct net_bridge_port *p, unsigned int state) return; p->state = state; - err = switchdev_port_attr_set(p->dev, &attr); + err = switchdev_port_attr_set(p->dev, &attr, NULL); if (err && err != -EOPNOTSUPP) br_warn(p->br, "error setting offload STP state on port %u(%s)\n", (unsigned int) p->port_no, p->dev->name); @@ -591,7 +591,7 @@ int __set_ageing_time(struct net_device *dev, unsigned long t) }; int err; - err = switchdev_port_attr_set(dev, &attr); + err = switchdev_port_attr_set(dev, &attr, NULL); if (err && err != -EOPNOTSUPP) return err; @@ -601,8 +601,8 @@ int __set_ageing_time(struct net_device *dev, unsigned long t) /* Set time interval that dynamic forwarding entries live * For pure software bridge, allow values outside the 802.1 * standard specification for special cases: - * 0 - entry never ages (all permanant) - * 1 - entry disappears (no persistance) + * 0 - entry never ages (all permanent) + * 1 - entry disappears (no persistence) * * Offloaded switch entries maybe more restrictive */ diff --git a/net/bridge/br_switchdev.c b/net/bridge/br_switchdev.c index 015209bf44aa..b89503832fcc 100644 --- a/net/bridge/br_switchdev.c +++ b/net/bridge/br_switchdev.c @@ -60,42 +60,47 @@ bool nbp_switchdev_allowed_egress(const struct net_bridge_port *p, int br_switchdev_set_port_flag(struct net_bridge_port *p, unsigned long flags, - unsigned long mask) + unsigned long mask, + struct netlink_ext_ack *extack) { struct switchdev_attr attr = { .orig_dev = p->dev, - .id = SWITCHDEV_ATTR_ID_PORT_PRE_BRIDGE_FLAGS, - .u.brport_flags = mask, }; struct switchdev_notifier_port_attr_info info = { .attr = &attr, }; int err; - if (mask & ~BR_PORT_FLAGS_HW_OFFLOAD) + mask &= BR_PORT_FLAGS_HW_OFFLOAD; + if (!mask) return 0; + attr.id = SWITCHDEV_ATTR_ID_PORT_PRE_BRIDGE_FLAGS; + attr.u.brport_flags.val = flags; + attr.u.brport_flags.mask = mask; + /* We run from atomic context here */ err = call_switchdev_notifiers(SWITCHDEV_PORT_ATTR_SET, p->dev, - &info.info, NULL); + &info.info, extack); err = notifier_to_errno(err); if (err == -EOPNOTSUPP) return 0; if (err) { - br_warn(p->br, "bridge flag offload is not supported %u(%s)\n", - (unsigned int)p->port_no, p->dev->name); + if (extack && !extack->_msg) + NL_SET_ERR_MSG_MOD(extack, + "bridge flag offload is not supported"); return -EOPNOTSUPP; } attr.id = SWITCHDEV_ATTR_ID_PORT_BRIDGE_FLAGS; attr.flags = SWITCHDEV_F_DEFER; - attr.u.brport_flags = flags; - err = switchdev_port_attr_set(p->dev, &attr); + err = switchdev_port_attr_set(p->dev, &attr, extack); if (err) { - br_warn(p->br, "error setting offload flag on port %u(%s)\n", - (unsigned int)p->port_no, p->dev->name); + if (extack && !extack->_msg) + NL_SET_ERR_MSG_MOD(extack, + "error setting offload flag on port"); return err; } @@ -153,8 +158,7 @@ int br_switchdev_port_vlan_add(struct net_device *dev, u16 vid, u16 flags, .obj.orig_dev = dev, .obj.id = SWITCHDEV_OBJ_ID_PORT_VLAN, .flags = flags, - .vid_begin = vid, - .vid_end = vid, + .vid = vid, }; return switchdev_port_obj_add(dev, &v.obj, extack); @@ -165,8 +169,7 @@ int br_switchdev_port_vlan_del(struct net_device *dev, u16 vid) struct switchdev_obj_port_vlan v = { .obj.orig_dev = dev, .obj.id = SWITCHDEV_OBJ_ID_PORT_VLAN, - .vid_begin = vid, - .vid_end = vid, + .vid = vid, }; return switchdev_port_obj_del(dev, &v.obj); diff --git a/net/bridge/br_sysfs_br.c b/net/bridge/br_sysfs_br.c index 7db06e3f642a..072e29840082 100644 --- a/net/bridge/br_sysfs_br.c +++ b/net/bridge/br_sysfs_br.c @@ -19,6 +19,10 @@ #include "br_private.h" +/* IMPORTANT: new bridge options must be added with netlink support only + * please do not add new sysfs entries + */ + #define to_bridge(cd) ((struct net_bridge *)netdev_priv(to_net_dev(cd))) /* @@ -26,11 +30,13 @@ */ static ssize_t store_bridge_parm(struct device *d, const char *buf, size_t len, - int (*set)(struct net_bridge *, unsigned long)) + int (*set)(struct net_bridge *br, unsigned long val, + struct netlink_ext_ack *extack)) { struct net_bridge *br = to_bridge(d); - char *endp; + struct netlink_ext_ack extack = {0}; unsigned long val; + char *endp; int err; if (!ns_capable(dev_net(br->dev)->user_ns, CAP_NET_ADMIN)) @@ -43,9 +49,15 @@ static ssize_t store_bridge_parm(struct device *d, if (!rtnl_trylock()) return restart_syscall(); - err = (*set)(br, val); + err = (*set)(br, val, &extack); if (!err) netdev_state_change(br->dev); + if (extack._msg) { + if (err) + br_err(br, "%s\n", extack._msg); + else + br_warn(br, "%s\n", extack._msg); + } rtnl_unlock(); return err ? err : len; @@ -59,11 +71,17 @@ static ssize_t forward_delay_show(struct device *d, return sprintf(buf, "%lu\n", jiffies_to_clock_t(br->forward_delay)); } +static int set_forward_delay(struct net_bridge *br, unsigned long val, + struct netlink_ext_ack *extack) +{ + return br_set_forward_delay(br, val); +} + static ssize_t forward_delay_store(struct device *d, struct device_attribute *attr, const char *buf, size_t len) { - return store_bridge_parm(d, buf, len, br_set_forward_delay); + return store_bridge_parm(d, buf, len, set_forward_delay); } static DEVICE_ATTR_RW(forward_delay); @@ -74,11 +92,17 @@ static ssize_t hello_time_show(struct device *d, struct device_attribute *attr, jiffies_to_clock_t(to_bridge(d)->hello_time)); } +static int set_hello_time(struct net_bridge *br, unsigned long val, + struct netlink_ext_ack *extack) +{ + return br_set_hello_time(br, val); +} + static ssize_t hello_time_store(struct device *d, struct device_attribute *attr, const char *buf, size_t len) { - return store_bridge_parm(d, buf, len, br_set_hello_time); + return store_bridge_parm(d, buf, len, set_hello_time); } static DEVICE_ATTR_RW(hello_time); @@ -89,10 +113,16 @@ static ssize_t max_age_show(struct device *d, struct device_attribute *attr, jiffies_to_clock_t(to_bridge(d)->max_age)); } +static int set_max_age(struct net_bridge *br, unsigned long val, + struct netlink_ext_ack *extack) +{ + return br_set_max_age(br, val); +} + static ssize_t max_age_store(struct device *d, struct device_attribute *attr, const char *buf, size_t len) { - return store_bridge_parm(d, buf, len, br_set_max_age); + return store_bridge_parm(d, buf, len, set_max_age); } static DEVICE_ATTR_RW(max_age); @@ -103,7 +133,8 @@ static ssize_t ageing_time_show(struct device *d, return sprintf(buf, "%lu\n", jiffies_to_clock_t(br->ageing_time)); } -static int set_ageing_time(struct net_bridge *br, unsigned long val) +static int set_ageing_time(struct net_bridge *br, unsigned long val, + struct netlink_ext_ack *extack) { return br_set_ageing_time(br, val); } @@ -124,9 +155,10 @@ static ssize_t stp_state_show(struct device *d, } -static int set_stp_state(struct net_bridge *br, unsigned long val) +static int set_stp_state(struct net_bridge *br, unsigned long val, + struct netlink_ext_ack *extack) { - return br_stp_set_enabled(br, val, NULL); + return br_stp_set_enabled(br, val, extack); } static ssize_t stp_state_store(struct device *d, @@ -145,7 +177,8 @@ static ssize_t group_fwd_mask_show(struct device *d, return sprintf(buf, "%#x\n", br->group_fwd_mask); } -static int set_group_fwd_mask(struct net_bridge *br, unsigned long val) +static int set_group_fwd_mask(struct net_bridge *br, unsigned long val, + struct netlink_ext_ack *extack) { if (val & BR_GROUPFWD_RESTRICTED) return -EINVAL; @@ -172,7 +205,8 @@ static ssize_t priority_show(struct device *d, struct device_attribute *attr, (br->bridge_id.prio[0] << 8) | br->bridge_id.prio[1]); } -static int set_priority(struct net_bridge *br, unsigned long val) +static int set_priority(struct net_bridge *br, unsigned long val, + struct netlink_ext_ack *extack) { br_stp_set_bridge_priority(br, (u16) val); return 0; @@ -308,7 +342,8 @@ static ssize_t group_addr_store(struct device *d, static DEVICE_ATTR_RW(group_addr); -static int set_flush(struct net_bridge *br, unsigned long val) +static int set_flush(struct net_bridge *br, unsigned long val, + struct netlink_ext_ack *extack) { br_fdb_flush(br); return 0; @@ -330,9 +365,10 @@ static ssize_t no_linklocal_learn_show(struct device *d, return sprintf(buf, "%d\n", br_boolopt_get(br, BR_BOOLOPT_NO_LL_LEARN)); } -static int set_no_linklocal_learn(struct net_bridge *br, unsigned long val) +static int set_no_linklocal_learn(struct net_bridge *br, unsigned long val, + struct netlink_ext_ack *extack) { - return br_boolopt_toggle(br, BR_BOOLOPT_NO_LL_LEARN, !!val, NULL); + return br_boolopt_toggle(br, BR_BOOLOPT_NO_LL_LEARN, !!val, extack); } static ssize_t no_linklocal_learn_store(struct device *d, @@ -351,11 +387,17 @@ static ssize_t multicast_router_show(struct device *d, return sprintf(buf, "%d\n", br->multicast_router); } +static int set_multicast_router(struct net_bridge *br, unsigned long val, + struct netlink_ext_ack *extack) +{ + return br_multicast_set_router(br, val); +} + static ssize_t multicast_router_store(struct device *d, struct device_attribute *attr, const char *buf, size_t len) { - return store_bridge_parm(d, buf, len, br_multicast_set_router); + return store_bridge_parm(d, buf, len, set_multicast_router); } static DEVICE_ATTR_RW(multicast_router); @@ -367,11 +409,17 @@ static ssize_t multicast_snooping_show(struct device *d, return sprintf(buf, "%d\n", br_opt_get(br, BROPT_MULTICAST_ENABLED)); } +static int toggle_multicast(struct net_bridge *br, unsigned long val, + struct netlink_ext_ack *extack) +{ + return br_multicast_toggle(br, val); +} + static ssize_t multicast_snooping_store(struct device *d, struct device_attribute *attr, const char *buf, size_t len) { - return store_bridge_parm(d, buf, len, br_multicast_toggle); + return store_bridge_parm(d, buf, len, toggle_multicast); } static DEVICE_ATTR_RW(multicast_snooping); @@ -384,7 +432,8 @@ static ssize_t multicast_query_use_ifaddr_show(struct device *d, br_opt_get(br, BROPT_MULTICAST_QUERY_USE_IFADDR)); } -static int set_query_use_ifaddr(struct net_bridge *br, unsigned long val) +static int set_query_use_ifaddr(struct net_bridge *br, unsigned long val, + struct netlink_ext_ack *extack) { br_opt_toggle(br, BROPT_MULTICAST_QUERY_USE_IFADDR, !!val); return 0; @@ -407,11 +456,17 @@ static ssize_t multicast_querier_show(struct device *d, return sprintf(buf, "%d\n", br_opt_get(br, BROPT_MULTICAST_QUERIER)); } +static int set_multicast_querier(struct net_bridge *br, unsigned long val, + struct netlink_ext_ack *extack) +{ + return br_multicast_set_querier(br, val); +} + static ssize_t multicast_querier_store(struct device *d, struct device_attribute *attr, const char *buf, size_t len) { - return store_bridge_parm(d, buf, len, br_multicast_set_querier); + return store_bridge_parm(d, buf, len, set_multicast_querier); } static DEVICE_ATTR_RW(multicast_querier); @@ -421,10 +476,12 @@ static ssize_t hash_elasticity_show(struct device *d, return sprintf(buf, "%u\n", RHT_ELASTICITY); } -static int set_elasticity(struct net_bridge *br, unsigned long val) +static int set_elasticity(struct net_bridge *br, unsigned long val, + struct netlink_ext_ack *extack) { - br_warn(br, "the hash_elasticity option has been deprecated and is always %u\n", - RHT_ELASTICITY); + /* 16 is RHT_ELASTICITY */ + NL_SET_ERR_MSG_MOD(extack, + "the hash_elasticity option has been deprecated and is always 16"); return 0; } @@ -443,7 +500,8 @@ static ssize_t hash_max_show(struct device *d, struct device_attribute *attr, return sprintf(buf, "%u\n", br->hash_max); } -static int set_hash_max(struct net_bridge *br, unsigned long val) +static int set_hash_max(struct net_bridge *br, unsigned long val, + struct netlink_ext_ack *extack) { br->hash_max = val; return 0; @@ -465,11 +523,17 @@ static ssize_t multicast_igmp_version_show(struct device *d, return sprintf(buf, "%u\n", br->multicast_igmp_version); } +static int set_multicast_igmp_version(struct net_bridge *br, unsigned long val, + struct netlink_ext_ack *extack) +{ + return br_multicast_set_igmp_version(br, val); +} + static ssize_t multicast_igmp_version_store(struct device *d, struct device_attribute *attr, const char *buf, size_t len) { - return store_bridge_parm(d, buf, len, br_multicast_set_igmp_version); + return store_bridge_parm(d, buf, len, set_multicast_igmp_version); } static DEVICE_ATTR_RW(multicast_igmp_version); @@ -481,7 +545,8 @@ static ssize_t multicast_last_member_count_show(struct device *d, return sprintf(buf, "%u\n", br->multicast_last_member_count); } -static int set_last_member_count(struct net_bridge *br, unsigned long val) +static int set_last_member_count(struct net_bridge *br, unsigned long val, + struct netlink_ext_ack *extack) { br->multicast_last_member_count = val; return 0; @@ -502,7 +567,8 @@ static ssize_t multicast_startup_query_count_show( return sprintf(buf, "%u\n", br->multicast_startup_query_count); } -static int set_startup_query_count(struct net_bridge *br, unsigned long val) +static int set_startup_query_count(struct net_bridge *br, unsigned long val, + struct netlink_ext_ack *extack) { br->multicast_startup_query_count = val; return 0; @@ -524,7 +590,8 @@ static ssize_t multicast_last_member_interval_show( jiffies_to_clock_t(br->multicast_last_member_interval)); } -static int set_last_member_interval(struct net_bridge *br, unsigned long val) +static int set_last_member_interval(struct net_bridge *br, unsigned long val, + struct netlink_ext_ack *extack) { br->multicast_last_member_interval = clock_t_to_jiffies(val); return 0; @@ -546,7 +613,8 @@ static ssize_t multicast_membership_interval_show( jiffies_to_clock_t(br->multicast_membership_interval)); } -static int set_membership_interval(struct net_bridge *br, unsigned long val) +static int set_membership_interval(struct net_bridge *br, unsigned long val, + struct netlink_ext_ack *extack) { br->multicast_membership_interval = clock_t_to_jiffies(val); return 0; @@ -569,7 +637,8 @@ static ssize_t multicast_querier_interval_show(struct device *d, jiffies_to_clock_t(br->multicast_querier_interval)); } -static int set_querier_interval(struct net_bridge *br, unsigned long val) +static int set_querier_interval(struct net_bridge *br, unsigned long val, + struct netlink_ext_ack *extack) { br->multicast_querier_interval = clock_t_to_jiffies(val); return 0; @@ -592,7 +661,8 @@ static ssize_t multicast_query_interval_show(struct device *d, jiffies_to_clock_t(br->multicast_query_interval)); } -static int set_query_interval(struct net_bridge *br, unsigned long val) +static int set_query_interval(struct net_bridge *br, unsigned long val, + struct netlink_ext_ack *extack) { br->multicast_query_interval = clock_t_to_jiffies(val); return 0; @@ -615,7 +685,8 @@ static ssize_t multicast_query_response_interval_show( jiffies_to_clock_t(br->multicast_query_response_interval)); } -static int set_query_response_interval(struct net_bridge *br, unsigned long val) +static int set_query_response_interval(struct net_bridge *br, unsigned long val, + struct netlink_ext_ack *extack) { br->multicast_query_response_interval = clock_t_to_jiffies(val); return 0; @@ -638,7 +709,8 @@ static ssize_t multicast_startup_query_interval_show( jiffies_to_clock_t(br->multicast_startup_query_interval)); } -static int set_startup_query_interval(struct net_bridge *br, unsigned long val) +static int set_startup_query_interval(struct net_bridge *br, unsigned long val, + struct netlink_ext_ack *extack) { br->multicast_startup_query_interval = clock_t_to_jiffies(val); return 0; @@ -662,7 +734,8 @@ static ssize_t multicast_stats_enabled_show(struct device *d, br_opt_get(br, BROPT_MULTICAST_STATS_ENABLED)); } -static int set_stats_enabled(struct net_bridge *br, unsigned long val) +static int set_stats_enabled(struct net_bridge *br, unsigned long val, + struct netlink_ext_ack *extack) { br_opt_toggle(br, BROPT_MULTICAST_STATS_ENABLED, !!val); return 0; @@ -687,11 +760,17 @@ static ssize_t multicast_mld_version_show(struct device *d, return sprintf(buf, "%u\n", br->multicast_mld_version); } +static int set_multicast_mld_version(struct net_bridge *br, unsigned long val, + struct netlink_ext_ack *extack) +{ + return br_multicast_set_mld_version(br, val); +} + static ssize_t multicast_mld_version_store(struct device *d, struct device_attribute *attr, const char *buf, size_t len) { - return store_bridge_parm(d, buf, len, br_multicast_set_mld_version); + return store_bridge_parm(d, buf, len, set_multicast_mld_version); } static DEVICE_ATTR_RW(multicast_mld_version); #endif @@ -704,7 +783,8 @@ static ssize_t nf_call_iptables_show( return sprintf(buf, "%u\n", br_opt_get(br, BROPT_NF_CALL_IPTABLES)); } -static int set_nf_call_iptables(struct net_bridge *br, unsigned long val) +static int set_nf_call_iptables(struct net_bridge *br, unsigned long val, + struct netlink_ext_ack *extack) { br_opt_toggle(br, BROPT_NF_CALL_IPTABLES, !!val); return 0; @@ -725,7 +805,8 @@ static ssize_t nf_call_ip6tables_show( return sprintf(buf, "%u\n", br_opt_get(br, BROPT_NF_CALL_IP6TABLES)); } -static int set_nf_call_ip6tables(struct net_bridge *br, unsigned long val) +static int set_nf_call_ip6tables(struct net_bridge *br, unsigned long val, + struct netlink_ext_ack *extack) { br_opt_toggle(br, BROPT_NF_CALL_IP6TABLES, !!val); return 0; @@ -746,7 +827,8 @@ static ssize_t nf_call_arptables_show( return sprintf(buf, "%u\n", br_opt_get(br, BROPT_NF_CALL_ARPTABLES)); } -static int set_nf_call_arptables(struct net_bridge *br, unsigned long val) +static int set_nf_call_arptables(struct net_bridge *br, unsigned long val, + struct netlink_ext_ack *extack) { br_opt_toggle(br, BROPT_NF_CALL_ARPTABLES, !!val); return 0; @@ -817,11 +899,17 @@ static ssize_t vlan_stats_enabled_show(struct device *d, return sprintf(buf, "%u\n", br_opt_get(br, BROPT_VLAN_STATS_ENABLED)); } +static int set_vlan_stats_enabled(struct net_bridge *br, unsigned long val, + struct netlink_ext_ack *extack) +{ + return br_vlan_set_stats(br, val); +} + static ssize_t vlan_stats_enabled_store(struct device *d, struct device_attribute *attr, const char *buf, size_t len) { - return store_bridge_parm(d, buf, len, br_vlan_set_stats); + return store_bridge_parm(d, buf, len, set_vlan_stats_enabled); } static DEVICE_ATTR_RW(vlan_stats_enabled); @@ -833,11 +921,17 @@ static ssize_t vlan_stats_per_port_show(struct device *d, return sprintf(buf, "%u\n", br_opt_get(br, BROPT_VLAN_STATS_PER_PORT)); } +static int set_vlan_stats_per_port(struct net_bridge *br, unsigned long val, + struct netlink_ext_ack *extack) +{ + return br_vlan_set_stats_per_port(br, val); +} + static ssize_t vlan_stats_per_port_store(struct device *d, struct device_attribute *attr, const char *buf, size_t len) { - return store_bridge_parm(d, buf, len, br_vlan_set_stats_per_port); + return store_bridge_parm(d, buf, len, set_vlan_stats_per_port); } static DEVICE_ATTR_RW(vlan_stats_per_port); #endif diff --git a/net/bridge/br_sysfs_if.c b/net/bridge/br_sysfs_if.c index 7a59cdddd3ce..72e92376eef1 100644 --- a/net/bridge/br_sysfs_if.c +++ b/net/bridge/br_sysfs_if.c @@ -17,6 +17,10 @@ #include "br_private.h" +/* IMPORTANT: new bridge port options must be added with netlink support only + * please do not add new sysfs entries + */ + struct brport_attribute { struct attribute attr; ssize_t (*show)(struct net_bridge_port *, char *); @@ -55,9 +59,9 @@ static BRPORT_ATTR(_name, 0644, \ static int store_flag(struct net_bridge_port *p, unsigned long v, unsigned long mask) { - unsigned long flags; - - flags = p->flags; + struct netlink_ext_ack extack = {0}; + unsigned long flags = p->flags; + int err; if (v) flags |= mask; @@ -65,6 +69,12 @@ static int store_flag(struct net_bridge_port *p, unsigned long v, flags &= ~mask; if (flags != p->flags) { + err = br_switchdev_set_port_flag(p, flags, mask, &extack); + if (err) { + netdev_err(p->dev, "%s\n", extack._msg); + return err; + } + p->flags = flags; br_port_flags_change(p, mask); } diff --git a/net/bridge/br_vlan.c b/net/bridge/br_vlan.c index 701cad646b20..8829f621b8ec 100644 --- a/net/bridge/br_vlan.c +++ b/net/bridge/br_vlan.c @@ -806,7 +806,8 @@ void br_recalculate_fwd_mask(struct net_bridge *br) ~(1u << br->group_addr[5]); } -int __br_vlan_filter_toggle(struct net_bridge *br, unsigned long val) +int br_vlan_filter_toggle(struct net_bridge *br, unsigned long val, + struct netlink_ext_ack *extack) { struct switchdev_attr attr = { .orig_dev = br->dev, @@ -819,7 +820,7 @@ int __br_vlan_filter_toggle(struct net_bridge *br, unsigned long val) if (br_opt_get(br, BROPT_VLAN_ENABLED) == !!val) return 0; - err = switchdev_port_attr_set(br->dev, &attr); + err = switchdev_port_attr_set(br->dev, &attr, extack); if (err && err != -EOPNOTSUPP) return err; @@ -831,11 +832,6 @@ int __br_vlan_filter_toggle(struct net_bridge *br, unsigned long val) return 0; } -int br_vlan_filter_toggle(struct net_bridge *br, unsigned long val) -{ - return __br_vlan_filter_toggle(br, val); -} - bool br_vlan_enabled(const struct net_device *dev) { struct net_bridge *br = netdev_priv(dev); @@ -854,7 +850,8 @@ int br_vlan_get_proto(const struct net_device *dev, u16 *p_proto) } EXPORT_SYMBOL_GPL(br_vlan_get_proto); -int __br_vlan_set_proto(struct net_bridge *br, __be16 proto) +int __br_vlan_set_proto(struct net_bridge *br, __be16 proto, + struct netlink_ext_ack *extack) { struct switchdev_attr attr = { .orig_dev = br->dev, @@ -871,7 +868,7 @@ int __br_vlan_set_proto(struct net_bridge *br, __be16 proto) if (br->vlan_proto == proto) return 0; - err = switchdev_port_attr_set(br->dev, &attr); + err = switchdev_port_attr_set(br->dev, &attr, extack); if (err && err != -EOPNOTSUPP) return err; @@ -901,7 +898,7 @@ int __br_vlan_set_proto(struct net_bridge *br, __be16 proto) err_filt: attr.u.vlan_protocol = ntohs(oldproto); - switchdev_port_attr_set(br->dev, &attr); + switchdev_port_attr_set(br->dev, &attr, NULL); list_for_each_entry_continue_reverse(vlan, &vg->vlan_list, vlist) vlan_vid_del(p->dev, proto, vlan->vid); @@ -915,12 +912,13 @@ err_filt: return err; } -int br_vlan_set_proto(struct net_bridge *br, unsigned long val) +int br_vlan_set_proto(struct net_bridge *br, unsigned long val, + struct netlink_ext_ack *extack) { - if (val != ETH_P_8021Q && val != ETH_P_8021AD) + if (!eth_type_vlan(htons(val))) return -EPROTONOSUPPORT; - return __br_vlan_set_proto(br, htons(val)); + return __br_vlan_set_proto(br, htons(val), extack); } int br_vlan_set_stats(struct net_bridge *br, unsigned long val) @@ -1100,7 +1098,8 @@ err_port: goto out; } -int br_vlan_set_default_pvid(struct net_bridge *br, unsigned long val) +int br_vlan_set_default_pvid(struct net_bridge *br, unsigned long val, + struct netlink_ext_ack *extack) { u16 pvid = val; int err = 0; @@ -1117,7 +1116,7 @@ int br_vlan_set_default_pvid(struct net_bridge *br, unsigned long val) err = -EPERM; goto out; } - err = __br_vlan_set_default_pvid(br, pvid, NULL); + err = __br_vlan_set_default_pvid(br, pvid, extack); out: return err; } @@ -1167,7 +1166,7 @@ int nbp_vlan_init(struct net_bridge_port *p, struct netlink_ext_ack *extack) if (!vg) goto out; - ret = switchdev_port_attr_set(p->dev, &attr); + ret = switchdev_port_attr_set(p->dev, &attr, extack); if (ret && ret != -EOPNOTSUPP) goto err_vlan_enabled; diff --git a/net/bridge/netfilter/nft_meta_bridge.c b/net/bridge/netfilter/nft_meta_bridge.c index 8e8ffac037cd..97805ec424c1 100644 --- a/net/bridge/netfilter/nft_meta_bridge.c +++ b/net/bridge/netfilter/nft_meta_bridge.c @@ -87,9 +87,8 @@ static int nft_meta_bridge_get_init(const struct nft_ctx *ctx, return nft_meta_get_init(ctx, expr, tb); } - priv->dreg = nft_parse_register(tb[NFTA_META_DREG]); - return nft_validate_register_store(ctx, priv->dreg, NULL, - NFT_DATA_VALUE, len); + return nft_parse_register_store(ctx, tb[NFTA_META_DREG], &priv->dreg, + NULL, NFT_DATA_VALUE, len); } static struct nft_expr_type nft_meta_bridge_type; diff --git a/net/can/Kconfig b/net/can/Kconfig index 7c9958df91d3..a9ac5ffab286 100644 --- a/net/can/Kconfig +++ b/net/can/Kconfig @@ -4,7 +4,6 @@ # menuconfig CAN - depends on NET tristate "CAN bus subsystem support" help Controller Area Network (CAN) is a slow (up to 1Mbit/s) serial diff --git a/net/can/gw.c b/net/can/gw.c index 8598d9da0e5f..ba4124805602 100644 --- a/net/can/gw.c +++ b/net/can/gw.c @@ -225,7 +225,7 @@ static void mod_store_ccdlc(struct canfd_frame *cf) if (ccf->len <= CAN_MAX_DLEN) return; - /* potentially broken values are catched in can_can_gw_rcv() */ + /* potentially broken values are caught in can_can_gw_rcv() */ if (ccf->len > CAN_MAX_RAW_DLC) return; diff --git a/net/can/raw.c b/net/can/raw.c index 6ec8aa1d0da4..37b47a39a3ed 100644 --- a/net/can/raw.c +++ b/net/can/raw.c @@ -665,10 +665,18 @@ static int raw_getsockopt(struct socket *sock, int level, int optname, if (ro->count > 0) { int fsize = ro->count * sizeof(struct can_filter); - if (len > fsize) - len = fsize; - if (copy_to_user(optval, ro->filter, len)) - err = -EFAULT; + /* user space buffer to small for filter list? */ + if (len < fsize) { + /* return -ERANGE and needed space in optlen */ + err = -ERANGE; + if (put_user(fsize, optlen)) + err = -EFAULT; + } else { + if (len > fsize) + len = fsize; + if (copy_to_user(optval, ro->filter, len)) + err = -EFAULT; + } } else { len = 0; } diff --git a/net/core/dev.c b/net/core/dev.c index 449b45b843d4..6c5967e80132 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -91,6 +91,7 @@ #include <linux/etherdevice.h> #include <linux/ethtool.h> #include <linux/skbuff.h> +#include <linux/kthread.h> #include <linux/bpf.h> #include <linux/bpf_trace.h> #include <net/net_namespace.h> @@ -101,6 +102,7 @@ #include <net/dsa.h> #include <net/dst.h> #include <net/dst_metadata.h> +#include <net/gro.h> #include <net/pkt_sched.h> #include <net/pkt_cls.h> #include <net/checksum.h> @@ -1493,6 +1495,27 @@ void netdev_notify_peers(struct net_device *dev) } EXPORT_SYMBOL(netdev_notify_peers); +static int napi_threaded_poll(void *data); + +static int napi_kthread_create(struct napi_struct *n) +{ + int err = 0; + + /* Create and wake up the kthread once to put it in + * TASK_INTERRUPTIBLE mode to avoid the blocked task + * warning and work with loadavg. + */ + n->thread = kthread_run(napi_threaded_poll, n, "napi/%s-%d", + n->dev->name, n->napi_id); + if (IS_ERR(n->thread)) { + err = PTR_ERR(n->thread); + pr_err("kthread_run failed with err %d\n", err); + n->thread = NULL; + } + + return err; +} + static int __dev_open(struct net_device *dev, struct netlink_ext_ack *extack) { const struct net_device_ops *ops = dev->netdev_ops; @@ -2194,28 +2217,14 @@ static inline void net_timestamp_set(struct sk_buff *skb) bool is_skb_forwardable(const struct net_device *dev, const struct sk_buff *skb) { - unsigned int len; - - if (!(dev->flags & IFF_UP)) - return false; - - len = dev->mtu + dev->hard_header_len + VLAN_HLEN; - if (skb->len <= len) - return true; - - /* if TSO is enabled, we don't care about the length as the packet - * could be forwarded without being segmented before - */ - if (skb_is_gso(skb)) - return true; - - return false; + return __is_skb_forwardable(dev, skb, true); } EXPORT_SYMBOL_GPL(is_skb_forwardable); -int __dev_forward_skb(struct net_device *dev, struct sk_buff *skb) +static int __dev_forward_skb2(struct net_device *dev, struct sk_buff *skb, + bool check_mtu) { - int ret = ____dev_forward_skb(dev, skb); + int ret = ____dev_forward_skb(dev, skb, check_mtu); if (likely(!ret)) { skb->protocol = eth_type_trans(skb, dev); @@ -2224,6 +2233,11 @@ int __dev_forward_skb(struct net_device *dev, struct sk_buff *skb) return ret; } + +int __dev_forward_skb(struct net_device *dev, struct sk_buff *skb) +{ + return __dev_forward_skb2(dev, skb, true); +} EXPORT_SYMBOL_GPL(__dev_forward_skb); /** @@ -2250,6 +2264,11 @@ int dev_forward_skb(struct net_device *dev, struct sk_buff *skb) } EXPORT_SYMBOL_GPL(dev_forward_skb); +int dev_forward_skb_nomtu(struct net_device *dev, struct sk_buff *skb) +{ + return __dev_forward_skb2(dev, skb, false) ?: netif_rx_internal(skb); +} + static inline int deliver_skb(struct sk_buff *skb, struct packet_type *pt_prev, struct net_device *orig_dev) @@ -3617,11 +3636,22 @@ static struct sk_buff *validate_xmit_vlan(struct sk_buff *skb, int skb_csum_hwoffload_help(struct sk_buff *skb, const netdev_features_t features) { - if (unlikely(skb->csum_not_inet)) + if (unlikely(skb_csum_is_sctp(skb))) return !!(features & NETIF_F_SCTP_CRC) ? 0 : skb_crc32c_csum_help(skb); - return !!(features & NETIF_F_CSUM_MASK) ? 0 : skb_checksum_help(skb); + if (features & NETIF_F_HW_CSUM) + return 0; + + if (features & (NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM)) { + switch (skb->csum_offset) { + case offsetof(struct tcphdr, check): + case offsetof(struct udphdr, check): + return 0; + } + } + + return skb_checksum_help(skb); } EXPORT_SYMBOL(skb_csum_hwoffload_help); @@ -3878,6 +3908,7 @@ sch_handle_egress(struct sk_buff *skb, int *ret, struct net_device *dev) /* qdisc_skb_cb(skb)->pkt_len was already set by the caller. */ qdisc_skb_cb(skb)->mru = 0; + qdisc_skb_cb(skb)->post_ct = false; mini_qdisc_bstats_cpu_update(miniq, skb); switch (tcf_classify(skb, miniq->filter_list, &cl_res, false)) { @@ -4083,7 +4114,7 @@ static int __dev_queue_xmit(struct sk_buff *skb, struct net_device *sb_dev) skb_reset_mac_header(skb); if (unlikely(skb_shinfo(skb)->tx_flags & SKBTX_SCHED_TSTAMP)) - __skb_tstamp_tx(skb, NULL, skb->sk, SCM_TSTAMP_SCHED); + __skb_tstamp_tx(skb, NULL, NULL, skb->sk, SCM_TSTAMP_SCHED); /* Disable soft irqs for various locks below. Also * stops preemption for RCU. @@ -4252,6 +4283,22 @@ int gro_normal_batch __read_mostly = 8; static inline void ____napi_schedule(struct softnet_data *sd, struct napi_struct *napi) { + struct task_struct *thread; + + if (test_bit(NAPI_STATE_THREADED, &napi->state)) { + /* Paired with smp_mb__before_atomic() in + * napi_enable()/dev_set_threaded(). + * Use READ_ONCE() to guarantee a complete + * read on napi->thread. Only call + * wake_up_process() when it's not NULL. + */ + thread = READ_ONCE(napi->thread); + if (thread) { + wake_up_process(thread); + return; + } + } + list_add_tail(&napi->poll_list, &sd->poll_list); __raise_softirq_irqoff(NET_RX_SOFTIRQ); } @@ -4603,14 +4650,14 @@ static u32 netif_receive_generic_xdp(struct sk_buff *skb, struct xdp_buff *xdp, struct bpf_prog *xdp_prog) { + void *orig_data, *orig_data_end, *hard_start; struct netdev_rx_queue *rxqueue; - void *orig_data, *orig_data_end; u32 metalen, act = XDP_DROP; + u32 mac_len, frame_sz; __be16 orig_eth_type; struct ethhdr *eth; bool orig_bcast; - int hlen, off; - u32 mac_len; + int off; /* Reinjected packets coming from act_mirred or similar should * not get XDP generic processing. @@ -4642,15 +4689,16 @@ static u32 netif_receive_generic_xdp(struct sk_buff *skb, * header. */ mac_len = skb->data - skb_mac_header(skb); - hlen = skb_headlen(skb) + mac_len; - xdp->data = skb->data - mac_len; - xdp->data_meta = xdp->data; - xdp->data_end = xdp->data + hlen; - xdp->data_hard_start = skb->data - skb_headroom(skb); + hard_start = skb->data - skb_headroom(skb); /* SKB "head" area always have tailroom for skb_shared_info */ - xdp->frame_sz = (void *)skb_end_pointer(skb) - xdp->data_hard_start; - xdp->frame_sz += SKB_DATA_ALIGN(sizeof(struct skb_shared_info)); + frame_sz = (void *)skb_end_pointer(skb) - hard_start; + frame_sz += SKB_DATA_ALIGN(sizeof(struct skb_shared_info)); + + rxqueue = netif_get_rxqueue(skb); + xdp_init_buff(xdp, frame_sz, &rxqueue->xdp_rxq); + xdp_prepare_buff(xdp, hard_start, skb_headroom(skb) - mac_len, + skb_headlen(skb) + mac_len, true); orig_data_end = xdp->data_end; orig_data = xdp->data; @@ -4658,9 +4706,6 @@ static u32 netif_receive_generic_xdp(struct sk_buff *skb, orig_bcast = is_multicast_ether_addr_64bits(eth->h_dest); orig_eth_type = eth->h_proto; - rxqueue = netif_get_rxqueue(skb); - xdp->rxq = &rxqueue->xdp_rxq; - act = bpf_prog_run_xdp(xdp_prog, xdp); /* check if bpf_xdp_adjust_head was used */ @@ -4895,8 +4940,6 @@ static __latent_entropy void net_tx_action(struct softirq_action *h) else __kfree_skb_defer(skb); } - - __kfree_skb_flush(); } if (sd->output_queue) { @@ -4962,6 +5005,7 @@ sch_handle_ingress(struct sk_buff *skb, struct packet_type **pt_prev, int *ret, qdisc_skb_cb(skb)->pkt_len = skb->len; qdisc_skb_cb(skb)->mru = 0; + qdisc_skb_cb(skb)->post_ct = false; skb->tc_at_ingress = 1; mini_qdisc_bstats_cpu_update(miniq, skb); @@ -5151,8 +5195,7 @@ another_round: skb_reset_mac_len(skb); } - if (skb->protocol == cpu_to_be16(ETH_P_8021Q) || - skb->protocol == cpu_to_be16(ETH_P_8021AD)) { + if (eth_type_vlan(skb->protocol)) { skb = skb_vlan_untag(skb); if (unlikely(!skb)) goto out; @@ -5236,8 +5279,7 @@ check_vlan_id: * find vlan device. */ skb->pkt_type = PACKET_OTHERHOST; - } else if (skb->protocol == cpu_to_be16(ETH_P_8021Q) || - skb->protocol == cpu_to_be16(ETH_P_8021AD)) { + } else if (eth_type_vlan(skb->protocol)) { /* Outer header is 802.1P with vlan 0, inner header is * 802.1Q or 802.1AD and vlan_do_receive() above could * not find vlan dev for vlan id 0. @@ -5713,7 +5755,7 @@ static void flush_all_backlogs(void) } /* we can have in flight packet[s] on the cpus we are not flushing, - * synchronize_net() in rollback_registered_many() will take care of + * synchronize_net() in unregister_netdevice_many() will take care of * them */ for_each_cpu(cpu, &flush_cpus) @@ -5743,8 +5785,6 @@ static void gro_normal_one(struct napi_struct *napi, struct sk_buff *skb, int se gro_normal_list(napi); } -INDIRECT_CALLABLE_DECLARE(int inet_gro_complete(struct sk_buff *, int)); -INDIRECT_CALLABLE_DECLARE(int ipv6_gro_complete(struct sk_buff *, int)); static int napi_gro_complete(struct napi_struct *napi, struct sk_buff *skb) { struct packet_offload *ptype; @@ -5913,10 +5953,6 @@ static void gro_flush_oldest(struct napi_struct *napi, struct list_head *head) napi_gro_complete(napi, oldest); } -INDIRECT_CALLABLE_DECLARE(struct sk_buff *inet_gro_receive(struct list_head *, - struct sk_buff *)); -INDIRECT_CALLABLE_DECLARE(struct sk_buff *ipv6_gro_receive(struct list_head *, - struct sk_buff *)); static enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff *skb) { u32 hash = skb_get_hash_raw(skb) & (GRO_HASH_BUCKETS - 1); @@ -6055,13 +6091,6 @@ struct packet_offload *gro_find_complete_by_type(__be16 type) } EXPORT_SYMBOL(gro_find_complete_by_type); -static void napi_skb_free_stolen_head(struct sk_buff *skb) -{ - skb_dst_drop(skb); - skb_ext_put(skb); - kmem_cache_free(skbuff_head_cache, skb); -} - static gro_result_t napi_skb_finish(struct napi_struct *napi, struct sk_buff *skb, gro_result_t ret) @@ -6071,15 +6100,11 @@ static gro_result_t napi_skb_finish(struct napi_struct *napi, gro_normal_one(napi, skb, 1); break; - case GRO_DROP: - kfree_skb(skb); - break; - case GRO_MERGED_FREE: if (NAPI_GRO_CB(skb)->free == NAPI_GRO_FREE_STOLEN_HEAD) napi_skb_free_stolen_head(skb); else - __kfree_skb(skb); + __kfree_skb_defer(skb); break; case GRO_HELD: @@ -6159,10 +6184,6 @@ static gro_result_t napi_frags_finish(struct napi_struct *napi, gro_normal_one(napi, skb, 1); break; - case GRO_DROP: - napi_reuse_skb(napi, skb); - break; - case GRO_MERGED_FREE: if (NAPI_GRO_CB(skb)->free == NAPI_GRO_FREE_STOLEN_HEAD) napi_skb_free_stolen_head(skb); @@ -6224,9 +6245,6 @@ gro_result_t napi_gro_frags(struct napi_struct *napi) gro_result_t ret; struct sk_buff *skb = napi_frags_skb(napi); - if (!skb) - return GRO_DROP; - trace_napi_gro_frags_entry(skb); ret = napi_frags_finish(napi, skb, dev_gro_receive(napi, skb)); @@ -6709,6 +6727,49 @@ static void init_gro_hash(struct napi_struct *napi) napi->gro_bitmask = 0; } +int dev_set_threaded(struct net_device *dev, bool threaded) +{ + struct napi_struct *napi; + int err = 0; + + if (dev->threaded == threaded) + return 0; + + if (threaded) { + list_for_each_entry(napi, &dev->napi_list, dev_list) { + if (!napi->thread) { + err = napi_kthread_create(napi); + if (err) { + threaded = false; + break; + } + } + } + } + + dev->threaded = threaded; + + /* Make sure kthread is created before THREADED bit + * is set. + */ + smp_mb__before_atomic(); + + /* Setting/unsetting threaded mode on a napi might not immediately + * take effect, if the current napi instance is actively being + * polled. In this case, the switch between threaded mode and + * softirq mode will happen in the next round of napi_schedule(). + * This should not cause hiccups/stalls to the live traffic. + */ + list_for_each_entry(napi, &dev->napi_list, dev_list) { + if (threaded) + set_bit(NAPI_STATE_THREADED, &napi->state); + else + clear_bit(NAPI_STATE_THREADED, &napi->state); + } + + return err; +} + void netif_napi_add(struct net_device *dev, struct napi_struct *napi, int (*poll)(struct napi_struct *, int), int weight) { @@ -6736,6 +6797,12 @@ void netif_napi_add(struct net_device *dev, struct napi_struct *napi, set_bit(NAPI_STATE_NPSVC, &napi->state); list_add_rcu(&napi->dev_list, &dev->napi_list); napi_hash_add(napi); + /* Create kthread for this napi if dev->threaded is set. + * Clear dev->threaded if kthread creation failed so that + * threaded mode will not be enabled in napi_enable(). + */ + if (dev->threaded && napi_kthread_create(napi)) + dev->threaded = 0; } EXPORT_SYMBOL(netif_napi_add); @@ -6753,9 +6820,28 @@ void napi_disable(struct napi_struct *n) clear_bit(NAPI_STATE_PREFER_BUSY_POLL, &n->state); clear_bit(NAPI_STATE_DISABLE, &n->state); + clear_bit(NAPI_STATE_THREADED, &n->state); } EXPORT_SYMBOL(napi_disable); +/** + * napi_enable - enable NAPI scheduling + * @n: NAPI context + * + * Resume NAPI from being scheduled on this context. + * Must be paired with napi_disable. + */ +void napi_enable(struct napi_struct *n) +{ + BUG_ON(!test_bit(NAPI_STATE_SCHED, &n->state)); + smp_mb__before_atomic(); + clear_bit(NAPI_STATE_SCHED, &n->state); + clear_bit(NAPI_STATE_NPSVC, &n->state); + if (n->dev->threaded && n->thread) + set_bit(NAPI_STATE_THREADED, &n->state); +} +EXPORT_SYMBOL(napi_enable); + static void flush_gro_hash(struct napi_struct *napi) { int i; @@ -6781,18 +6867,18 @@ void __netif_napi_del(struct napi_struct *napi) flush_gro_hash(napi); napi->gro_bitmask = 0; + + if (napi->thread) { + kthread_stop(napi->thread); + napi->thread = NULL; + } } EXPORT_SYMBOL(__netif_napi_del); -static int napi_poll(struct napi_struct *n, struct list_head *repoll) +static int __napi_poll(struct napi_struct *n, bool *repoll) { - void *have; int work, weight; - list_del_init(&n->poll_list); - - have = netpoll_poll_lock(n); - weight = n->weight; /* This NAPI_STATE_SCHED test is for avoiding a race @@ -6812,7 +6898,7 @@ static int napi_poll(struct napi_struct *n, struct list_head *repoll) n->poll, work, weight); if (likely(work < weight)) - goto out_unlock; + return work; /* Drivers must not modify the NAPI state if they * consume the entire weight. In such cases this code @@ -6821,7 +6907,7 @@ static int napi_poll(struct napi_struct *n, struct list_head *repoll) */ if (unlikely(napi_disable_pending(n))) { napi_complete(n); - goto out_unlock; + return work; } /* The NAPI context has more processing work, but busy-polling @@ -6834,7 +6920,7 @@ static int napi_poll(struct napi_struct *n, struct list_head *repoll) */ napi_schedule(n); } - goto out_unlock; + return work; } if (n->gro_bitmask) { @@ -6852,17 +6938,78 @@ static int napi_poll(struct napi_struct *n, struct list_head *repoll) if (unlikely(!list_empty(&n->poll_list))) { pr_warn_once("%s: Budget exhausted after napi rescheduled\n", n->dev ? n->dev->name : "backlog"); - goto out_unlock; + return work; } - list_add_tail(&n->poll_list, repoll); + *repoll = true; + + return work; +} + +static int napi_poll(struct napi_struct *n, struct list_head *repoll) +{ + bool do_repoll = false; + void *have; + int work; + + list_del_init(&n->poll_list); + + have = netpoll_poll_lock(n); + + work = __napi_poll(n, &do_repoll); + + if (do_repoll) + list_add_tail(&n->poll_list, repoll); -out_unlock: netpoll_poll_unlock(have); return work; } +static int napi_thread_wait(struct napi_struct *napi) +{ + set_current_state(TASK_INTERRUPTIBLE); + + while (!kthread_should_stop() && !napi_disable_pending(napi)) { + if (test_bit(NAPI_STATE_SCHED, &napi->state)) { + WARN_ON(!list_empty(&napi->poll_list)); + __set_current_state(TASK_RUNNING); + return 0; + } + + schedule(); + set_current_state(TASK_INTERRUPTIBLE); + } + __set_current_state(TASK_RUNNING); + return -1; +} + +static int napi_threaded_poll(void *data) +{ + struct napi_struct *napi = data; + void *have; + + while (!napi_thread_wait(napi)) { + for (;;) { + bool repoll = false; + + local_bh_disable(); + + have = netpoll_poll_lock(napi); + __napi_poll(napi, &repoll); + netpoll_poll_unlock(have); + + local_bh_enable(); + + if (!repoll) + break; + + cond_resched(); + } + } + return 0; +} + static __latent_entropy void net_rx_action(struct softirq_action *h) { struct softnet_data *sd = this_cpu_ptr(&softnet_data); @@ -6881,7 +7028,7 @@ static __latent_entropy void net_rx_action(struct softirq_action *h) if (list_empty(&list)) { if (!sd_has_rps_ipi_waiting(sd) && list_empty(&repoll)) - goto out; + return; break; } @@ -6908,8 +7055,6 @@ static __latent_entropy void net_rx_action(struct softirq_action *h) __raise_softirq_irqoff(NET_RX_SOFTIRQ); net_rps_action_and_irq_enable(sd); -out: - __kfree_skb_flush(); } struct netdev_adjacent { @@ -8121,6 +8266,39 @@ struct net_device *netdev_get_xmit_slave(struct net_device *dev, } EXPORT_SYMBOL(netdev_get_xmit_slave); +static struct net_device *netdev_sk_get_lower_dev(struct net_device *dev, + struct sock *sk) +{ + const struct net_device_ops *ops = dev->netdev_ops; + + if (!ops->ndo_sk_get_lower_dev) + return NULL; + return ops->ndo_sk_get_lower_dev(dev, sk); +} + +/** + * netdev_sk_get_lowest_dev - Get the lowest device in chain given device and socket + * @dev: device + * @sk: the socket + * + * %NULL is returned if no lower device is found. + */ + +struct net_device *netdev_sk_get_lowest_dev(struct net_device *dev, + struct sock *sk) +{ + struct net_device *lower; + + lower = netdev_sk_get_lower_dev(dev, sk); + while (lower) { + dev = lower; + lower = netdev_sk_get_lower_dev(dev, sk); + } + + return dev; +} +EXPORT_SYMBOL(netdev_sk_get_lowest_dev); + static void netdev_adjacent_add_links(struct net_device *dev) { struct netdev_adjacent *iter; @@ -8743,6 +8921,48 @@ int dev_set_mac_address(struct net_device *dev, struct sockaddr *sa, } EXPORT_SYMBOL(dev_set_mac_address); +static DECLARE_RWSEM(dev_addr_sem); + +int dev_set_mac_address_user(struct net_device *dev, struct sockaddr *sa, + struct netlink_ext_ack *extack) +{ + int ret; + + down_write(&dev_addr_sem); + ret = dev_set_mac_address(dev, sa, extack); + up_write(&dev_addr_sem); + return ret; +} +EXPORT_SYMBOL(dev_set_mac_address_user); + +int dev_get_mac_address(struct sockaddr *sa, struct net *net, char *dev_name) +{ + size_t size = sizeof(sa->sa_data); + struct net_device *dev; + int ret = 0; + + down_read(&dev_addr_sem); + rcu_read_lock(); + + dev = dev_get_by_name_rcu(net, dev_name); + if (!dev) { + ret = -ENODEV; + goto unlock; + } + if (!dev->addr_len) + memset(sa->sa_data, 0, size); + else + memcpy(sa->sa_data, dev->dev_addr, + min_t(size_t, size, dev->addr_len)); + sa->sa_family = dev->type; + +unlock: + rcu_read_unlock(); + up_read(&dev_addr_sem); + return ret; +} +EXPORT_SYMBOL(dev_get_mac_address); + /** * dev_change_carrier - Change device carrier * @dev: device @@ -9442,106 +9662,6 @@ static void net_set_todo(struct net_device *dev) dev_net(dev)->dev_unreg_count++; } -static void rollback_registered_many(struct list_head *head) -{ - struct net_device *dev, *tmp; - LIST_HEAD(close_head); - - BUG_ON(dev_boot_phase); - ASSERT_RTNL(); - - list_for_each_entry_safe(dev, tmp, head, unreg_list) { - /* Some devices call without registering - * for initialization unwind. Remove those - * devices and proceed with the remaining. - */ - if (dev->reg_state == NETREG_UNINITIALIZED) { - pr_debug("unregister_netdevice: device %s/%p never was registered\n", - dev->name, dev); - - WARN_ON(1); - list_del(&dev->unreg_list); - continue; - } - dev->dismantle = true; - BUG_ON(dev->reg_state != NETREG_REGISTERED); - } - - /* If device is running, close it first. */ - list_for_each_entry(dev, head, unreg_list) - list_add_tail(&dev->close_list, &close_head); - dev_close_many(&close_head, true); - - list_for_each_entry(dev, head, unreg_list) { - /* And unlink it from device chain. */ - unlist_netdevice(dev); - - dev->reg_state = NETREG_UNREGISTERING; - } - flush_all_backlogs(); - - synchronize_net(); - - list_for_each_entry(dev, head, unreg_list) { - struct sk_buff *skb = NULL; - - /* Shutdown queueing discipline. */ - dev_shutdown(dev); - - dev_xdp_uninstall(dev); - - /* Notify protocols, that we are about to destroy - * this device. They should clean all the things. - */ - call_netdevice_notifiers(NETDEV_UNREGISTER, dev); - - if (!dev->rtnl_link_ops || - dev->rtnl_link_state == RTNL_LINK_INITIALIZED) - skb = rtmsg_ifinfo_build_skb(RTM_DELLINK, dev, ~0U, 0, - GFP_KERNEL, NULL, 0); - - /* - * Flush the unicast and multicast chains - */ - dev_uc_flush(dev); - dev_mc_flush(dev); - - netdev_name_node_alt_flush(dev); - netdev_name_node_free(dev->name_node); - - if (dev->netdev_ops->ndo_uninit) - dev->netdev_ops->ndo_uninit(dev); - - if (skb) - rtmsg_ifinfo_send(skb, dev, GFP_KERNEL); - - /* Notifier chain MUST detach us all upper devices. */ - WARN_ON(netdev_has_any_upper_dev(dev)); - WARN_ON(netdev_has_any_lower_dev(dev)); - - /* Remove entries from kobject tree */ - netdev_unregister_kobject(dev); -#ifdef CONFIG_XPS - /* Remove XPS queueing entries */ - netif_reset_xps_queues_gt(dev, 0); -#endif - } - - synchronize_net(); - - list_for_each_entry(dev, head, unreg_list) - dev_put(dev); -} - -static void rollback_registered(struct net_device *dev) -{ - LIST_HEAD(single); - - list_add(&dev->unreg_list, &single); - rollback_registered_many(&single); - list_del(&single); -} - static netdev_features_t netdev_sync_upper_features(struct net_device *lower, struct net_device *upper, netdev_features_t features) { @@ -10014,7 +10134,7 @@ int register_netdevice(struct net_device *dev) dev->hw_features |= (NETIF_F_SOFT_FEATURES | NETIF_F_SOFT_FEATURES_OFF); dev->features |= NETIF_F_SOFT_FEATURES; - if (dev->netdev_ops->ndo_udp_tunnel_add) { + if (dev->udp_tunnel_nic_info) { dev->features |= NETIF_F_RX_UDP_TUNNEL_PORT; dev->hw_features |= NETIF_F_RX_UDP_TUNNEL_PORT; } @@ -10091,8 +10211,7 @@ int register_netdevice(struct net_device *dev) if (ret) { /* Expect explicit free_netdev() on failure */ dev->needs_free_netdev = false; - rollback_registered(dev); - net_set_todo(dev); + unregister_netdevice_queue(dev, NULL); goto out; } /* @@ -10714,9 +10833,10 @@ void unregister_netdevice_queue(struct net_device *dev, struct list_head *head) if (head) { list_move_tail(&dev->unreg_list, head); } else { - rollback_registered(dev); - /* Finish processing unregister after unlock */ - net_set_todo(dev); + LIST_HEAD(single); + + list_add(&dev->unreg_list, &single); + unregister_netdevice_many(&single); } } EXPORT_SYMBOL(unregister_netdevice_queue); @@ -10730,14 +10850,100 @@ EXPORT_SYMBOL(unregister_netdevice_queue); */ void unregister_netdevice_many(struct list_head *head) { - struct net_device *dev; + struct net_device *dev, *tmp; + LIST_HEAD(close_head); + + BUG_ON(dev_boot_phase); + ASSERT_RTNL(); + + if (list_empty(head)) + return; + + list_for_each_entry_safe(dev, tmp, head, unreg_list) { + /* Some devices call without registering + * for initialization unwind. Remove those + * devices and proceed with the remaining. + */ + if (dev->reg_state == NETREG_UNINITIALIZED) { + pr_debug("unregister_netdevice: device %s/%p never was registered\n", + dev->name, dev); + + WARN_ON(1); + list_del(&dev->unreg_list); + continue; + } + dev->dismantle = true; + BUG_ON(dev->reg_state != NETREG_REGISTERED); + } + + /* If device is running, close it first. */ + list_for_each_entry(dev, head, unreg_list) + list_add_tail(&dev->close_list, &close_head); + dev_close_many(&close_head, true); + + list_for_each_entry(dev, head, unreg_list) { + /* And unlink it from device chain. */ + unlist_netdevice(dev); + + dev->reg_state = NETREG_UNREGISTERING; + } + flush_all_backlogs(); + + synchronize_net(); + + list_for_each_entry(dev, head, unreg_list) { + struct sk_buff *skb = NULL; + + /* Shutdown queueing discipline. */ + dev_shutdown(dev); + + dev_xdp_uninstall(dev); + + /* Notify protocols, that we are about to destroy + * this device. They should clean all the things. + */ + call_netdevice_notifiers(NETDEV_UNREGISTER, dev); + + if (!dev->rtnl_link_ops || + dev->rtnl_link_state == RTNL_LINK_INITIALIZED) + skb = rtmsg_ifinfo_build_skb(RTM_DELLINK, dev, ~0U, 0, + GFP_KERNEL, NULL, 0); + + /* + * Flush the unicast and multicast chains + */ + dev_uc_flush(dev); + dev_mc_flush(dev); + + netdev_name_node_alt_flush(dev); + netdev_name_node_free(dev->name_node); + + if (dev->netdev_ops->ndo_uninit) + dev->netdev_ops->ndo_uninit(dev); + + if (skb) + rtmsg_ifinfo_send(skb, dev, GFP_KERNEL); + + /* Notifier chain MUST detach us all upper devices. */ + WARN_ON(netdev_has_any_upper_dev(dev)); + WARN_ON(netdev_has_any_lower_dev(dev)); - if (!list_empty(head)) { - rollback_registered_many(head); - list_for_each_entry(dev, head, unreg_list) - net_set_todo(dev); - list_del(head); + /* Remove entries from kobject tree */ + netdev_unregister_kobject(dev); +#ifdef CONFIG_XPS + /* Remove XPS queueing entries */ + netif_reset_xps_queues_gt(dev, 0); +#endif } + + synchronize_net(); + + list_for_each_entry(dev, head, unreg_list) { + dev_put(dev); + net_set_todo(dev); + } + + list_del(head); } EXPORT_SYMBOL(unregister_netdevice_many); diff --git a/net/core/dev_ioctl.c b/net/core/dev_ioctl.c index db8a0ff86f36..478d032f34ac 100644 --- a/net/core/dev_ioctl.c +++ b/net/core/dev_ioctl.c @@ -123,17 +123,6 @@ static int dev_ifsioc_locked(struct net *net, struct ifreq *ifr, unsigned int cm ifr->ifr_mtu = dev->mtu; return 0; - case SIOCGIFHWADDR: - if (!dev->addr_len) - memset(ifr->ifr_hwaddr.sa_data, 0, - sizeof(ifr->ifr_hwaddr.sa_data)); - else - memcpy(ifr->ifr_hwaddr.sa_data, dev->dev_addr, - min(sizeof(ifr->ifr_hwaddr.sa_data), - (size_t)dev->addr_len)); - ifr->ifr_hwaddr.sa_family = dev->type; - return 0; - case SIOCGIFSLAVE: err = -EINVAL; break; @@ -274,7 +263,7 @@ static int dev_ifsioc(struct net *net, struct ifreq *ifr, unsigned int cmd) case SIOCSIFHWADDR: if (dev->addr_len > sizeof(struct sockaddr)) return -EINVAL; - return dev_set_mac_address(dev, &ifr->ifr_hwaddr, NULL); + return dev_set_mac_address_user(dev, &ifr->ifr_hwaddr, NULL); case SIOCSIFHWBROADCAST: if (ifr->ifr_hwaddr.sa_family != dev->type) @@ -418,6 +407,12 @@ int dev_ioctl(struct net *net, unsigned int cmd, struct ifreq *ifr, bool *need_c */ switch (cmd) { + case SIOCGIFHWADDR: + dev_load(net, ifr->ifr_name); + ret = dev_get_mac_address(&ifr->ifr_hwaddr, net, ifr->ifr_name); + if (colon) + *colon = ':'; + return ret; /* * These ioctl calls: * - can be done by all. @@ -427,7 +422,6 @@ int dev_ioctl(struct net *net, unsigned int cmd, struct ifreq *ifr, bool *need_c case SIOCGIFFLAGS: case SIOCGIFMETRIC: case SIOCGIFMTU: - case SIOCGIFHWADDR: case SIOCGIFSLAVE: case SIOCGIFMAP: case SIOCGIFINDEX: diff --git a/net/core/devlink.c b/net/core/devlink.c index 738d4344d679..737b61c2976e 100644 --- a/net/core/devlink.c +++ b/net/core/devlink.c @@ -87,6 +87,9 @@ EXPORT_TRACEPOINT_SYMBOL_GPL(devlink_trap_report); static const struct nla_policy devlink_function_nl_policy[DEVLINK_PORT_FUNCTION_ATTR_MAX + 1] = { [DEVLINK_PORT_FUNCTION_ATTR_HW_ADDR] = { .type = NLA_BINARY }, + [DEVLINK_PORT_FN_ATTR_STATE] = + NLA_POLICY_RANGE(NLA_U8, DEVLINK_PORT_FN_STATE_INACTIVE, + DEVLINK_PORT_FN_STATE_ACTIVE), }; static LIST_HEAD(devlink_list); @@ -690,6 +693,15 @@ static int devlink_nl_port_attrs_put(struct sk_buff *msg, if (nla_put_u8(msg, DEVLINK_ATTR_PORT_EXTERNAL, attrs->pci_vf.external)) return -EMSGSIZE; break; + case DEVLINK_PORT_FLAVOUR_PCI_SF: + if (nla_put_u32(msg, DEVLINK_ATTR_PORT_CONTROLLER_NUMBER, + attrs->pci_sf.controller) || + nla_put_u16(msg, DEVLINK_ATTR_PORT_PCI_PF_NUMBER, + attrs->pci_sf.pf) || + nla_put_u32(msg, DEVLINK_ATTR_PORT_PCI_SF_NUMBER, + attrs->pci_sf.sf)) + return -EMSGSIZE; + break; case DEVLINK_PORT_FLAVOUR_PHYSICAL: case DEVLINK_PORT_FLAVOUR_CPU: case DEVLINK_PORT_FLAVOUR_DSA: @@ -713,42 +725,105 @@ static int devlink_nl_port_attrs_put(struct sk_buff *msg, } static int +devlink_port_fn_hw_addr_fill(struct devlink *devlink, const struct devlink_ops *ops, + struct devlink_port *port, struct sk_buff *msg, + struct netlink_ext_ack *extack, bool *msg_updated) +{ + u8 hw_addr[MAX_ADDR_LEN]; + int hw_addr_len; + int err; + + if (!ops->port_function_hw_addr_get) + return 0; + + err = ops->port_function_hw_addr_get(devlink, port, hw_addr, &hw_addr_len, extack); + if (err) { + if (err == -EOPNOTSUPP) + return 0; + return err; + } + err = nla_put(msg, DEVLINK_PORT_FUNCTION_ATTR_HW_ADDR, hw_addr_len, hw_addr); + if (err) + return err; + *msg_updated = true; + return 0; +} + +static bool +devlink_port_fn_state_valid(enum devlink_port_fn_state state) +{ + return state == DEVLINK_PORT_FN_STATE_INACTIVE || + state == DEVLINK_PORT_FN_STATE_ACTIVE; +} + +static bool +devlink_port_fn_opstate_valid(enum devlink_port_fn_opstate opstate) +{ + return opstate == DEVLINK_PORT_FN_OPSTATE_DETACHED || + opstate == DEVLINK_PORT_FN_OPSTATE_ATTACHED; +} + +static int +devlink_port_fn_state_fill(struct devlink *devlink, + const struct devlink_ops *ops, + struct devlink_port *port, struct sk_buff *msg, + struct netlink_ext_ack *extack, + bool *msg_updated) +{ + enum devlink_port_fn_opstate opstate; + enum devlink_port_fn_state state; + int err; + + if (!ops->port_fn_state_get) + return 0; + + err = ops->port_fn_state_get(devlink, port, &state, &opstate, extack); + if (err) { + if (err == -EOPNOTSUPP) + return 0; + return err; + } + if (!devlink_port_fn_state_valid(state)) { + WARN_ON_ONCE(1); + NL_SET_ERR_MSG_MOD(extack, "Invalid state read from driver"); + return -EINVAL; + } + if (!devlink_port_fn_opstate_valid(opstate)) { + WARN_ON_ONCE(1); + NL_SET_ERR_MSG_MOD(extack, + "Invalid operational state read from driver"); + return -EINVAL; + } + if (nla_put_u8(msg, DEVLINK_PORT_FN_ATTR_STATE, state) || + nla_put_u8(msg, DEVLINK_PORT_FN_ATTR_OPSTATE, opstate)) + return -EMSGSIZE; + *msg_updated = true; + return 0; +} + +static int devlink_nl_port_function_attrs_put(struct sk_buff *msg, struct devlink_port *port, struct netlink_ext_ack *extack) { struct devlink *devlink = port->devlink; const struct devlink_ops *ops; struct nlattr *function_attr; - bool empty_nest = true; - int err = 0; + bool msg_updated = false; + int err; function_attr = nla_nest_start_noflag(msg, DEVLINK_ATTR_PORT_FUNCTION); if (!function_attr) return -EMSGSIZE; ops = devlink->ops; - if (ops->port_function_hw_addr_get) { - int hw_addr_len; - u8 hw_addr[MAX_ADDR_LEN]; - - err = ops->port_function_hw_addr_get(devlink, port, hw_addr, &hw_addr_len, extack); - if (err == -EOPNOTSUPP) { - /* Port function attributes are optional for a port. If port doesn't - * support function attribute, returning -EOPNOTSUPP is not an error. - */ - err = 0; - goto out; - } else if (err) { - goto out; - } - err = nla_put(msg, DEVLINK_PORT_FUNCTION_ATTR_HW_ADDR, hw_addr_len, hw_addr); - if (err) - goto out; - empty_nest = false; - } - + err = devlink_port_fn_hw_addr_fill(devlink, ops, port, msg, + extack, &msg_updated); + if (err) + goto out; + err = devlink_port_fn_state_fill(devlink, ops, port, msg, extack, + &msg_updated); out: - if (err || empty_nest) + if (err || !msg_updated) nla_nest_cancel(msg, function_attr); else nla_nest_end(msg, function_attr); @@ -986,7 +1061,6 @@ devlink_port_function_hw_addr_set(struct devlink *devlink, struct devlink_port * const struct devlink_ops *ops; const u8 *hw_addr; int hw_addr_len; - int err; hw_addr = nla_data(attr); hw_addr_len = nla_len(attr); @@ -1011,12 +1085,25 @@ devlink_port_function_hw_addr_set(struct devlink *devlink, struct devlink_port * return -EOPNOTSUPP; } - err = ops->port_function_hw_addr_set(devlink, port, hw_addr, hw_addr_len, extack); - if (err) - return err; + return ops->port_function_hw_addr_set(devlink, port, hw_addr, hw_addr_len, extack); +} - devlink_port_notify(port, DEVLINK_CMD_PORT_NEW); - return 0; +static int devlink_port_fn_state_set(struct devlink *devlink, + struct devlink_port *port, + const struct nlattr *attr, + struct netlink_ext_ack *extack) +{ + enum devlink_port_fn_state state; + const struct devlink_ops *ops; + + state = nla_get_u8(attr); + ops = devlink->ops; + if (!ops->port_fn_state_set) { + NL_SET_ERR_MSG_MOD(extack, + "Function does not support state setting"); + return -EOPNOTSUPP; + } + return ops->port_fn_state_set(devlink, port, state, extack); } static int @@ -1034,9 +1121,21 @@ devlink_port_function_set(struct devlink *devlink, struct devlink_port *port, } attr = tb[DEVLINK_PORT_FUNCTION_ATTR_HW_ADDR]; - if (attr) + if (attr) { err = devlink_port_function_hw_addr_set(devlink, port, attr, extack); + if (err) + return err; + } + /* Keep this as the last function attribute set, so that when + * multiple port function attributes are set along with state, + * Those can be applied first before activating the state. + */ + attr = tb[DEVLINK_PORT_FN_ATTR_STATE]; + if (attr) + err = devlink_port_fn_state_set(devlink, port, attr, extack); + if (!err) + devlink_port_notify(port, DEVLINK_CMD_PORT_NEW); return err; } @@ -1136,6 +1235,111 @@ static int devlink_nl_cmd_port_unsplit_doit(struct sk_buff *skb, return devlink_port_unsplit(devlink, port_index, info->extack); } +static int devlink_port_new_notifiy(struct devlink *devlink, + unsigned int port_index, + struct genl_info *info) +{ + struct devlink_port *devlink_port; + struct sk_buff *msg; + int err; + + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (!msg) + return -ENOMEM; + + mutex_lock(&devlink->lock); + devlink_port = devlink_port_get_by_index(devlink, port_index); + if (!devlink_port) { + err = -ENODEV; + goto out; + } + + err = devlink_nl_port_fill(msg, devlink, devlink_port, + DEVLINK_CMD_NEW, info->snd_portid, + info->snd_seq, 0, NULL); + if (err) + goto out; + + err = genlmsg_reply(msg, info); + mutex_unlock(&devlink->lock); + return err; + +out: + mutex_unlock(&devlink->lock); + nlmsg_free(msg); + return err; +} + +static int devlink_nl_cmd_port_new_doit(struct sk_buff *skb, + struct genl_info *info) +{ + struct netlink_ext_ack *extack = info->extack; + struct devlink_port_new_attrs new_attrs = {}; + struct devlink *devlink = info->user_ptr[0]; + unsigned int new_port_index; + int err; + + if (!devlink->ops->port_new || !devlink->ops->port_del) + return -EOPNOTSUPP; + + if (!info->attrs[DEVLINK_ATTR_PORT_FLAVOUR] || + !info->attrs[DEVLINK_ATTR_PORT_PCI_PF_NUMBER]) { + NL_SET_ERR_MSG_MOD(extack, "Port flavour or PCI PF are not specified"); + return -EINVAL; + } + new_attrs.flavour = nla_get_u16(info->attrs[DEVLINK_ATTR_PORT_FLAVOUR]); + new_attrs.pfnum = + nla_get_u16(info->attrs[DEVLINK_ATTR_PORT_PCI_PF_NUMBER]); + + if (info->attrs[DEVLINK_ATTR_PORT_INDEX]) { + /* Port index of the new port being created by driver. */ + new_attrs.port_index = + nla_get_u32(info->attrs[DEVLINK_ATTR_PORT_INDEX]); + new_attrs.port_index_valid = true; + } + if (info->attrs[DEVLINK_ATTR_PORT_CONTROLLER_NUMBER]) { + new_attrs.controller = + nla_get_u16(info->attrs[DEVLINK_ATTR_PORT_CONTROLLER_NUMBER]); + new_attrs.controller_valid = true; + } + if (new_attrs.flavour == DEVLINK_PORT_FLAVOUR_PCI_SF && + info->attrs[DEVLINK_ATTR_PORT_PCI_SF_NUMBER]) { + new_attrs.sfnum = nla_get_u32(info->attrs[DEVLINK_ATTR_PORT_PCI_SF_NUMBER]); + new_attrs.sfnum_valid = true; + } + + err = devlink->ops->port_new(devlink, &new_attrs, extack, + &new_port_index); + if (err) + return err; + + err = devlink_port_new_notifiy(devlink, new_port_index, info); + if (err && err != -ENODEV) { + /* Fail to send the response; destroy newly created port. */ + devlink->ops->port_del(devlink, new_port_index, extack); + } + return err; +} + +static int devlink_nl_cmd_port_del_doit(struct sk_buff *skb, + struct genl_info *info) +{ + struct netlink_ext_ack *extack = info->extack; + struct devlink *devlink = info->user_ptr[0]; + unsigned int port_index; + + if (!devlink->ops->port_del) + return -EOPNOTSUPP; + + if (!info->attrs[DEVLINK_ATTR_PORT_INDEX]) { + NL_SET_ERR_MSG_MOD(extack, "Port index is not specified"); + return -EINVAL; + } + port_index = nla_get_u32(info->attrs[DEVLINK_ATTR_PORT_INDEX]); + + return devlink->ops->port_del(devlink, port_index, extack); +} + static int devlink_nl_sb_fill(struct sk_buff *msg, struct devlink *devlink, struct devlink_sb *devlink_sb, enum devlink_command cmd, u32 portid, @@ -7594,6 +7798,10 @@ static const struct nla_policy devlink_nl_policy[DEVLINK_ATTR_MAX + 1] = { [DEVLINK_ATTR_RELOAD_ACTION] = NLA_POLICY_RANGE(NLA_U8, DEVLINK_RELOAD_ACTION_DRIVER_REINIT, DEVLINK_RELOAD_ACTION_MAX), [DEVLINK_ATTR_RELOAD_LIMITS] = NLA_POLICY_BITFIELD32(DEVLINK_RELOAD_LIMITS_VALID_MASK), + [DEVLINK_ATTR_PORT_FLAVOUR] = { .type = NLA_U16 }, + [DEVLINK_ATTR_PORT_PCI_PF_NUMBER] = { .type = NLA_U16 }, + [DEVLINK_ATTR_PORT_PCI_SF_NUMBER] = { .type = NLA_U32 }, + [DEVLINK_ATTR_PORT_CONTROLLER_NUMBER] = { .type = NLA_U32 }, }; static const struct genl_small_ops devlink_nl_ops[] = { @@ -7634,6 +7842,18 @@ static const struct genl_small_ops devlink_nl_ops[] = { .internal_flags = DEVLINK_NL_FLAG_NO_LOCK, }, { + .cmd = DEVLINK_CMD_PORT_NEW, + .doit = devlink_nl_cmd_port_new_doit, + .flags = GENL_ADMIN_PERM, + .internal_flags = DEVLINK_NL_FLAG_NO_LOCK, + }, + { + .cmd = DEVLINK_CMD_PORT_DEL, + .doit = devlink_nl_cmd_port_del_doit, + .flags = GENL_ADMIN_PERM, + .internal_flags = DEVLINK_NL_FLAG_NO_LOCK, + }, + { .cmd = DEVLINK_CMD_SB_GET, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = devlink_nl_cmd_sb_get_doit, @@ -8372,6 +8592,32 @@ void devlink_port_attrs_pci_vf_set(struct devlink_port *devlink_port, u32 contro } EXPORT_SYMBOL_GPL(devlink_port_attrs_pci_vf_set); +/** + * devlink_port_attrs_pci_sf_set - Set PCI SF port attributes + * + * @devlink_port: devlink port + * @controller: associated controller number for the devlink port instance + * @pf: associated PF for the devlink port instance + * @sf: associated SF of a PF for the devlink port instance + */ +void devlink_port_attrs_pci_sf_set(struct devlink_port *devlink_port, u32 controller, + u16 pf, u32 sf) +{ + struct devlink_port_attrs *attrs = &devlink_port->attrs; + int ret; + + if (WARN_ON(devlink_port->registered)) + return; + ret = __devlink_port_attrs_set(devlink_port, + DEVLINK_PORT_FLAVOUR_PCI_SF); + if (ret) + return; + attrs->pci_sf.controller = controller; + attrs->pci_sf.pf = pf; + attrs->pci_sf.sf = sf; +} +EXPORT_SYMBOL_GPL(devlink_port_attrs_pci_sf_set); + static int __devlink_port_phys_port_name_get(struct devlink_port *devlink_port, char *name, size_t len) { @@ -8420,6 +8666,10 @@ static int __devlink_port_phys_port_name_get(struct devlink_port *devlink_port, n = snprintf(name, len, "pf%uvf%u", attrs->pci_vf.pf, attrs->pci_vf.vf); break; + case DEVLINK_PORT_FLAVOUR_PCI_SF: + n = snprintf(name, len, "pf%usf%u", attrs->pci_sf.pf, + attrs->pci_sf.sf); + break; } if (n >= len) @@ -8617,6 +8867,10 @@ EXPORT_SYMBOL_GPL(devlink_dpipe_table_unregister); * @resource_id: resource's id * @parent_resource_id: resource's parent id * @size_params: size parameters + * + * Generic resources should reuse the same names across drivers. + * Please see the generic resources list at: + * Documentation/networking/devlink/devlink-resource.rst */ int devlink_resource_register(struct devlink *devlink, const char *resource_name, @@ -9508,6 +9762,7 @@ static const struct devlink_trap devlink_trap_generic[] = { DEVLINK_TRAP(GTP_PARSING, DROP), DEVLINK_TRAP(ESP_PARSING, DROP), DEVLINK_TRAP(BLACKHOLE_NEXTHOP, DROP), + DEVLINK_TRAP(DMAC_FILTER, DROP), }; #define DEVLINK_TRAP_GROUP(_id) \ diff --git a/net/core/filter.c b/net/core/filter.c index 255aeee72402..adfdad234674 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -2083,13 +2083,13 @@ static const struct bpf_func_proto bpf_csum_level_proto = { static inline int __bpf_rx_skb(struct net_device *dev, struct sk_buff *skb) { - return dev_forward_skb(dev, skb); + return dev_forward_skb_nomtu(dev, skb); } static inline int __bpf_rx_skb_no_mac(struct net_device *dev, struct sk_buff *skb) { - int ret = ____dev_forward_skb(dev, skb); + int ret = ____dev_forward_skb(dev, skb, false); if (likely(!ret)) { skb->dev = dev; @@ -2480,7 +2480,7 @@ int skb_do_redirect(struct sk_buff *skb) goto out_drop; dev = ops->ndo_get_peer_dev(dev); if (unlikely(!dev || - !is_skb_forwardable(dev, skb) || + !(dev->flags & IFF_UP) || net_eq(net, dev_net(dev)))) goto out_drop; skb->dev = dev; @@ -3552,11 +3552,7 @@ static int bpf_skb_net_shrink(struct sk_buff *skb, u32 off, u32 len_diff, return 0; } -static u32 __bpf_skb_max_len(const struct sk_buff *skb) -{ - return skb->dev ? skb->dev->mtu + skb->dev->hard_header_len : - SKB_MAX_ALLOC; -} +#define BPF_SKB_MAX_LEN SKB_MAX_ALLOC BPF_CALL_4(sk_skb_adjust_room, struct sk_buff *, skb, s32, len_diff, u32, mode, u64, flags) @@ -3605,7 +3601,7 @@ BPF_CALL_4(bpf_skb_adjust_room, struct sk_buff *, skb, s32, len_diff, { u32 len_cur, len_diff_abs = abs(len_diff); u32 len_min = bpf_skb_net_base_len(skb); - u32 len_max = __bpf_skb_max_len(skb); + u32 len_max = BPF_SKB_MAX_LEN; __be16 proto = skb->protocol; bool shrink = len_diff < 0; u32 off; @@ -3688,7 +3684,7 @@ static int bpf_skb_trim_rcsum(struct sk_buff *skb, unsigned int new_len) static inline int __bpf_skb_change_tail(struct sk_buff *skb, u32 new_len, u64 flags) { - u32 max_len = __bpf_skb_max_len(skb); + u32 max_len = BPF_SKB_MAX_LEN; u32 min_len = __bpf_skb_min_len(skb); int ret; @@ -3764,7 +3760,7 @@ static const struct bpf_func_proto sk_skb_change_tail_proto = { static inline int __bpf_skb_change_head(struct sk_buff *skb, u32 head_room, u64 flags) { - u32 max_len = __bpf_skb_max_len(skb); + u32 max_len = BPF_SKB_MAX_LEN; u32 new_len = skb->len + head_room; int ret; @@ -4631,6 +4627,18 @@ static const struct bpf_func_proto bpf_get_socket_cookie_sock_proto = { .arg1_type = ARG_PTR_TO_CTX, }; +BPF_CALL_1(bpf_get_socket_ptr_cookie, struct sock *, sk) +{ + return sk ? sock_gen_cookie(sk) : 0; +} + +const struct bpf_func_proto bpf_get_socket_ptr_cookie_proto = { + .func = bpf_get_socket_ptr_cookie, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_BTF_ID_SOCK_COMMON, +}; + BPF_CALL_1(bpf_get_socket_cookie_sock_ops, struct bpf_sock_ops_kern *, ctx) { return __sock_gen_cookie(ctx->sk); @@ -4645,11 +4653,9 @@ static const struct bpf_func_proto bpf_get_socket_cookie_sock_ops_proto = { static u64 __bpf_get_netns_cookie(struct sock *sk) { -#ifdef CONFIG_NET_NS - return __net_gen_cookie(sk ? sk->sk_net.net : &init_net); -#else - return 0; -#endif + const struct net *net = sk ? sock_net(sk) : &init_net; + + return net->net_cookie; } BPF_CALL_1(bpf_get_netns_cookie_sock, struct sock *, ctx) @@ -4770,6 +4776,10 @@ static int _bpf_setsockopt(struct sock *sk, int level, int optname, ifindex = dev->ifindex; dev_put(dev); } + fallthrough; + case SO_BINDTOIFINDEX: + if (optname == SO_BINDTOIFINDEX) + ifindex = val; ret = sock_bindtoindex(sk, ifindex, false); break; case SO_KEEPALIVE: @@ -4932,8 +4942,25 @@ static int _bpf_getsockopt(struct sock *sk, int level, int optname, sock_owned_by_me(sk); + if (level == SOL_SOCKET) { + if (optlen != sizeof(int)) + goto err_clear; + + switch (optname) { + case SO_MARK: + *((int *)optval) = sk->sk_mark; + break; + case SO_PRIORITY: + *((int *)optval) = sk->sk_priority; + break; + case SO_BINDTOIFINDEX: + *((int *)optval) = sk->sk_bound_dev_if; + break; + default: + goto err_clear; + } #ifdef CONFIG_INET - if (level == SOL_TCP && sk->sk_prot->getsockopt == tcp_getsockopt) { + } else if (level == SOL_TCP && sk->sk_prot->getsockopt == tcp_getsockopt) { struct inet_connection_sock *icsk; struct tcp_sock *tp; @@ -4987,11 +5014,11 @@ static int _bpf_getsockopt(struct sock *sk, int level, int optname, goto err_clear; } #endif +#endif } else { goto err_clear; } return 0; -#endif err_clear: memset(optval, 0, optlen); return -EINVAL; @@ -5272,12 +5299,14 @@ static const struct bpf_func_proto bpf_skb_get_xfrm_state_proto = { #if IS_ENABLED(CONFIG_INET) || IS_ENABLED(CONFIG_IPV6) static int bpf_fib_set_fwd_params(struct bpf_fib_lookup *params, const struct neighbour *neigh, - const struct net_device *dev) + const struct net_device *dev, u32 mtu) { memcpy(params->dmac, neigh->ha, ETH_ALEN); memcpy(params->smac, dev->dev_addr, ETH_ALEN); params->h_vlan_TCI = 0; params->h_vlan_proto = 0; + if (mtu) + params->mtu_result = mtu; /* union with tot_len */ return 0; } @@ -5293,8 +5322,8 @@ static int bpf_ipv4_fib_lookup(struct net *net, struct bpf_fib_lookup *params, struct net_device *dev; struct fib_result res; struct flowi4 fl4; + u32 mtu = 0; int err; - u32 mtu; dev = dev_get_by_index_rcu(net, params->ifindex); if (unlikely(!dev)) @@ -5361,8 +5390,10 @@ static int bpf_ipv4_fib_lookup(struct net *net, struct bpf_fib_lookup *params, if (check_mtu) { mtu = ip_mtu_from_fib_result(&res, params->ipv4_dst); - if (params->tot_len > mtu) + if (params->tot_len > mtu) { + params->mtu_result = mtu; /* union with tot_len */ return BPF_FIB_LKUP_RET_FRAG_NEEDED; + } } nhc = res.nhc; @@ -5396,7 +5427,7 @@ static int bpf_ipv4_fib_lookup(struct net *net, struct bpf_fib_lookup *params, if (!neigh) return BPF_FIB_LKUP_RET_NO_NEIGH; - return bpf_fib_set_fwd_params(params, neigh, dev); + return bpf_fib_set_fwd_params(params, neigh, dev, mtu); } #endif @@ -5413,7 +5444,7 @@ static int bpf_ipv6_fib_lookup(struct net *net, struct bpf_fib_lookup *params, struct flowi6 fl6; int strict = 0; int oif, err; - u32 mtu; + u32 mtu = 0; /* link local addresses are never forwarded */ if (rt6_need_strict(dst) || rt6_need_strict(src)) @@ -5488,8 +5519,10 @@ static int bpf_ipv6_fib_lookup(struct net *net, struct bpf_fib_lookup *params, if (check_mtu) { mtu = ipv6_stub->ip6_mtu_from_fib6(&res, dst, src); - if (params->tot_len > mtu) + if (params->tot_len > mtu) { + params->mtu_result = mtu; /* union with tot_len */ return BPF_FIB_LKUP_RET_FRAG_NEEDED; + } } if (res.nh->fib_nh_lws) @@ -5509,7 +5542,7 @@ static int bpf_ipv6_fib_lookup(struct net *net, struct bpf_fib_lookup *params, if (!neigh) return BPF_FIB_LKUP_RET_NO_NEIGH; - return bpf_fib_set_fwd_params(params, neigh, dev); + return bpf_fib_set_fwd_params(params, neigh, dev, mtu); } #endif @@ -5552,6 +5585,7 @@ BPF_CALL_4(bpf_skb_fib_lookup, struct sk_buff *, skb, { struct net *net = dev_net(skb->dev); int rc = -EAFNOSUPPORT; + bool check_mtu = false; if (plen < sizeof(*params)) return -EINVAL; @@ -5559,25 +5593,33 @@ BPF_CALL_4(bpf_skb_fib_lookup, struct sk_buff *, skb, if (flags & ~(BPF_FIB_LOOKUP_DIRECT | BPF_FIB_LOOKUP_OUTPUT)) return -EINVAL; + if (params->tot_len) + check_mtu = true; + switch (params->family) { #if IS_ENABLED(CONFIG_INET) case AF_INET: - rc = bpf_ipv4_fib_lookup(net, params, flags, false); + rc = bpf_ipv4_fib_lookup(net, params, flags, check_mtu); break; #endif #if IS_ENABLED(CONFIG_IPV6) case AF_INET6: - rc = bpf_ipv6_fib_lookup(net, params, flags, false); + rc = bpf_ipv6_fib_lookup(net, params, flags, check_mtu); break; #endif } - if (!rc) { + if (rc == BPF_FIB_LKUP_RET_SUCCESS && !check_mtu) { struct net_device *dev; + /* When tot_len isn't provided by user, check skb + * against MTU of FIB lookup resulting net_device + */ dev = dev_get_by_index_rcu(net, params->ifindex); if (!is_skb_forwardable(dev, skb)) rc = BPF_FIB_LKUP_RET_FRAG_NEEDED; + + params->mtu_result = dev->mtu; /* union with tot_len */ } return rc; @@ -5593,6 +5635,116 @@ static const struct bpf_func_proto bpf_skb_fib_lookup_proto = { .arg4_type = ARG_ANYTHING, }; +static struct net_device *__dev_via_ifindex(struct net_device *dev_curr, + u32 ifindex) +{ + struct net *netns = dev_net(dev_curr); + + /* Non-redirect use-cases can use ifindex=0 and save ifindex lookup */ + if (ifindex == 0) + return dev_curr; + + return dev_get_by_index_rcu(netns, ifindex); +} + +BPF_CALL_5(bpf_skb_check_mtu, struct sk_buff *, skb, + u32, ifindex, u32 *, mtu_len, s32, len_diff, u64, flags) +{ + int ret = BPF_MTU_CHK_RET_FRAG_NEEDED; + struct net_device *dev = skb->dev; + int skb_len, dev_len; + int mtu; + + if (unlikely(flags & ~(BPF_MTU_CHK_SEGS))) + return -EINVAL; + + if (unlikely(flags & BPF_MTU_CHK_SEGS && len_diff)) + return -EINVAL; + + dev = __dev_via_ifindex(dev, ifindex); + if (unlikely(!dev)) + return -ENODEV; + + mtu = READ_ONCE(dev->mtu); + + dev_len = mtu + dev->hard_header_len; + skb_len = skb->len + len_diff; /* minus result pass check */ + if (skb_len <= dev_len) { + ret = BPF_MTU_CHK_RET_SUCCESS; + goto out; + } + /* At this point, skb->len exceed MTU, but as it include length of all + * segments, it can still be below MTU. The SKB can possibly get + * re-segmented in transmit path (see validate_xmit_skb). Thus, user + * must choose if segs are to be MTU checked. + */ + if (skb_is_gso(skb)) { + ret = BPF_MTU_CHK_RET_SUCCESS; + + if (flags & BPF_MTU_CHK_SEGS && + !skb_gso_validate_network_len(skb, mtu)) + ret = BPF_MTU_CHK_RET_SEGS_TOOBIG; + } +out: + /* BPF verifier guarantees valid pointer */ + *mtu_len = mtu; + + return ret; +} + +BPF_CALL_5(bpf_xdp_check_mtu, struct xdp_buff *, xdp, + u32, ifindex, u32 *, mtu_len, s32, len_diff, u64, flags) +{ + struct net_device *dev = xdp->rxq->dev; + int xdp_len = xdp->data_end - xdp->data; + int ret = BPF_MTU_CHK_RET_SUCCESS; + int mtu, dev_len; + + /* XDP variant doesn't support multi-buffer segment check (yet) */ + if (unlikely(flags)) + return -EINVAL; + + dev = __dev_via_ifindex(dev, ifindex); + if (unlikely(!dev)) + return -ENODEV; + + mtu = READ_ONCE(dev->mtu); + + /* Add L2-header as dev MTU is L3 size */ + dev_len = mtu + dev->hard_header_len; + + xdp_len += len_diff; /* minus result pass check */ + if (xdp_len > dev_len) + ret = BPF_MTU_CHK_RET_FRAG_NEEDED; + + /* BPF verifier guarantees valid pointer */ + *mtu_len = mtu; + + return ret; +} + +static const struct bpf_func_proto bpf_skb_check_mtu_proto = { + .func = bpf_skb_check_mtu, + .gpl_only = true, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_CTX, + .arg2_type = ARG_ANYTHING, + .arg3_type = ARG_PTR_TO_INT, + .arg4_type = ARG_ANYTHING, + .arg5_type = ARG_ANYTHING, +}; + +static const struct bpf_func_proto bpf_xdp_check_mtu_proto = { + .func = bpf_xdp_check_mtu, + .gpl_only = true, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_CTX, + .arg2_type = ARG_ANYTHING, + .arg3_type = ARG_PTR_TO_INT, + .arg4_type = ARG_ANYTHING, + .arg5_type = ARG_ANYTHING, +}; + #if IS_ENABLED(CONFIG_IPV6_SEG6_BPF) static int bpf_push_seg6_encap(struct sk_buff *skb, u32 type, void *hdr, u32 len) { @@ -7002,6 +7154,14 @@ sock_addr_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) case BPF_CGROUP_INET6_BIND: case BPF_CGROUP_INET4_CONNECT: case BPF_CGROUP_INET6_CONNECT: + case BPF_CGROUP_UDP4_RECVMSG: + case BPF_CGROUP_UDP6_RECVMSG: + case BPF_CGROUP_UDP4_SENDMSG: + case BPF_CGROUP_UDP6_SENDMSG: + case BPF_CGROUP_INET4_GETPEERNAME: + case BPF_CGROUP_INET6_GETPEERNAME: + case BPF_CGROUP_INET4_GETSOCKNAME: + case BPF_CGROUP_INET6_GETSOCKNAME: return &bpf_sock_addr_setsockopt_proto; default: return NULL; @@ -7012,6 +7172,14 @@ sock_addr_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) case BPF_CGROUP_INET6_BIND: case BPF_CGROUP_INET4_CONNECT: case BPF_CGROUP_INET6_CONNECT: + case BPF_CGROUP_UDP4_RECVMSG: + case BPF_CGROUP_UDP6_RECVMSG: + case BPF_CGROUP_UDP4_SENDMSG: + case BPF_CGROUP_UDP6_SENDMSG: + case BPF_CGROUP_INET4_GETPEERNAME: + case BPF_CGROUP_INET6_GETPEERNAME: + case BPF_CGROUP_INET4_GETSOCKNAME: + case BPF_CGROUP_INET6_GETSOCKNAME: return &bpf_sock_addr_getsockopt_proto; default: return NULL; @@ -7162,6 +7330,8 @@ tc_cls_act_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_get_socket_uid_proto; case BPF_FUNC_fib_lookup: return &bpf_skb_fib_lookup_proto; + case BPF_FUNC_check_mtu: + return &bpf_skb_check_mtu_proto; case BPF_FUNC_sk_fullsock: return &bpf_sk_fullsock_proto; case BPF_FUNC_sk_storage_get: @@ -7231,6 +7401,8 @@ xdp_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_xdp_adjust_tail_proto; case BPF_FUNC_fib_lookup: return &bpf_xdp_fib_lookup_proto; + case BPF_FUNC_check_mtu: + return &bpf_xdp_check_mtu_proto; #ifdef CONFIG_INET case BPF_FUNC_sk_lookup_udp: return &bpf_xdp_sk_lookup_udp_proto; @@ -8795,7 +8967,7 @@ u32 bpf_sock_convert_ctx_access(enum bpf_access_type type, target_size)); break; case offsetof(struct bpf_sock, rx_queue_mapping): -#ifdef CONFIG_XPS +#ifdef CONFIG_SOCK_RX_QUEUE_MAPPING *insn++ = BPF_LDX_MEM( BPF_FIELD_SIZEOF(struct sock, sk_rx_queue_mapping), si->dst_reg, si->src_reg, diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c index 0b4f536bc32d..2ef2224b3bff 100644 --- a/net/core/flow_dissector.c +++ b/net/core/flow_dissector.c @@ -23,6 +23,7 @@ #include <linux/if_ether.h> #include <linux/mpls.h> #include <linux/tcp.h> +#include <linux/ptp_classify.h> #include <net/flow_dissector.h> #include <scsi/fc/fc_fcoe.h> #include <uapi/linux/batadv_packet.h> @@ -236,9 +237,8 @@ skb_flow_dissect_set_enc_addr_type(enum flow_dissector_key_id type, void skb_flow_dissect_ct(const struct sk_buff *skb, struct flow_dissector *flow_dissector, - void *target_container, - u16 *ctinfo_map, - size_t mapsize) + void *target_container, u16 *ctinfo_map, + size_t mapsize, bool post_ct) { #if IS_ENABLED(CONFIG_NF_CONNTRACK) struct flow_dissector_key_ct *key; @@ -250,13 +250,19 @@ skb_flow_dissect_ct(const struct sk_buff *skb, return; ct = nf_ct_get(skb, &ctinfo); - if (!ct) + if (!ct && !post_ct) return; key = skb_flow_dissector_target(flow_dissector, FLOW_DISSECTOR_KEY_CT, target_container); + if (!ct) { + key->ct_state = TCA_FLOWER_KEY_CT_FLAGS_TRACKED | + TCA_FLOWER_KEY_CT_FLAGS_INVALID; + return; + } + if (ctinfo < mapsize) key->ct_state = ctinfo_map[ctinfo]; #if IS_ENABLED(CONFIG_NF_CONNTRACK_ZONES) @@ -1251,6 +1257,21 @@ proto_again: &proto, &nhoff, hlen, flags); break; + case htons(ETH_P_1588): { + struct ptp_header *hdr, _hdr; + + hdr = __skb_header_pointer(skb, nhoff, sizeof(_hdr), data, + hlen, &_hdr); + if (!hdr) { + fdret = FLOW_DISSECT_RET_OUT_BAD; + break; + } + + nhoff += ntohs(hdr->message_length); + fdret = FLOW_DISSECT_RET_OUT_GOOD; + break; + } + default: fdret = FLOW_DISSECT_RET_OUT_BAD; break; diff --git a/net/core/neighbour.c b/net/core/neighbour.c index 6d2d557442dc..e2982b3970b8 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -41,7 +41,6 @@ #include <trace/events/neigh.h> -#define DEBUG #define NEIGH_DEBUG 1 #define neigh_dbg(level, fmt, ...) \ do { \ diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c index daf502c13d6d..307628fdf380 100644 --- a/net/core/net-sysfs.c +++ b/net/core/net-sysfs.c @@ -538,6 +538,45 @@ static ssize_t phys_switch_id_show(struct device *dev, } static DEVICE_ATTR_RO(phys_switch_id); +static ssize_t threaded_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct net_device *netdev = to_net_dev(dev); + ssize_t ret = -EINVAL; + + if (!rtnl_trylock()) + return restart_syscall(); + + if (dev_isalive(netdev)) + ret = sprintf(buf, fmt_dec, netdev->threaded); + + rtnl_unlock(); + return ret; +} + +static int modify_napi_threaded(struct net_device *dev, unsigned long val) +{ + int ret; + + if (list_empty(&dev->napi_list)) + return -EOPNOTSUPP; + + if (val != 0 && val != 1) + return -EOPNOTSUPP; + + ret = dev_set_threaded(dev, val); + + return ret; +} + +static ssize_t threaded_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t len) +{ + return netdev_store(dev, attr, buf, len, modify_napi_threaded); +} +static DEVICE_ATTR_RW(threaded); + static struct attribute *net_class_attrs[] __ro_after_init = { &dev_attr_netdev_group.attr, &dev_attr_type.attr, @@ -570,6 +609,7 @@ static struct attribute *net_class_attrs[] __ro_after_init = { &dev_attr_proto_down.attr, &dev_attr_carrier_up_count.attr, &dev_attr_carrier_down_count.attr, + &dev_attr_threaded.attr, NULL, }; ATTRIBUTE_GROUPS(net_class); @@ -1136,18 +1176,25 @@ static ssize_t traffic_class_show(struct netdev_queue *queue, char *buf) { struct net_device *dev = queue->dev; + int num_tc, tc; int index; - int tc; if (!netif_is_multiqueue(dev)) return -ENOENT; + if (!rtnl_trylock()) + return restart_syscall(); + index = get_netdev_queue_index(queue); /* If queue belongs to subordinate dev use its TC mapping */ dev = netdev_get_tx_queue(dev, index)->sb_dev ? : dev; + num_tc = dev->num_tc; tc = netdev_txq_to_tc(dev, index); + + rtnl_unlock(); + if (tc < 0) return -EINVAL; @@ -1158,8 +1205,8 @@ static ssize_t traffic_class_show(struct netdev_queue *queue, * belongs to the root device it will be reported with just the * traffic class, so just "0" for TC 0 for example. */ - return dev->num_tc < 0 ? sprintf(buf, "%d%d\n", tc, dev->num_tc) : - sprintf(buf, "%d\n", tc); + return num_tc < 0 ? sprintf(buf, "%d%d\n", tc, num_tc) : + sprintf(buf, "%d\n", tc); } #ifdef CONFIG_XPS diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c index 2ef3b4557f40..43b6ac4c4439 100644 --- a/net/core/net_namespace.c +++ b/net/core/net_namespace.c @@ -72,18 +72,6 @@ static unsigned int max_gen_ptrs = INITIAL_NET_GEN_PTRS; DEFINE_COOKIE(net_cookie); -u64 __net_gen_cookie(struct net *net) -{ - while (1) { - u64 res = atomic64_read(&net->net_cookie); - - if (res) - return res; - res = gen_cookie_next(&net_cookie); - atomic64_cmpxchg(&net->net_cookie, 0, res); - } -} - static struct net_generic *net_alloc_generic(void) { struct net_generic *ng; @@ -332,6 +320,9 @@ static __net_init int setup_net(struct net *net, struct user_namespace *user_ns) refcount_set(&net->ns.count, 1); refcount_set(&net->passive, 1); get_random_bytes(&net->hash_mix, sizeof(u32)); + preempt_disable(); + net->net_cookie = gen_cookie_next(&net_cookie); + preempt_enable(); net->dev_base_seq = 1; net->user_ns = user_ns; idr_init(&net->netns_ids); @@ -1103,10 +1094,6 @@ static int __init net_ns_init(void) rcu_assign_pointer(init_net.gen, ng); - preempt_disable(); - __net_gen_cookie(&init_net); - preempt_enable(); - down_write(&pernet_ops_rwsem); if (setup_net(&init_net, &init_user_ns)) panic("Could not setup the initial network namespace"); diff --git a/net/core/netpoll.c b/net/core/netpoll.c index 960948290001..c310c7c1cef7 100644 --- a/net/core/netpoll.c +++ b/net/core/netpoll.c @@ -29,7 +29,6 @@ #include <linux/slab.h> #include <linux/export.h> #include <linux/if_vlan.h> -#include <net/dsa.h> #include <net/tcp.h> #include <net/udp.h> #include <net/addrconf.h> @@ -658,15 +657,15 @@ EXPORT_SYMBOL_GPL(__netpoll_setup); int netpoll_setup(struct netpoll *np) { - struct net_device *ndev = NULL, *dev = NULL; - struct net *net = current->nsproxy->net_ns; + struct net_device *ndev = NULL; struct in_device *in_dev; int err; rtnl_lock(); - if (np->dev_name[0]) + if (np->dev_name[0]) { + struct net *net = current->nsproxy->net_ns; ndev = __dev_get_by_name(net, np->dev_name); - + } if (!ndev) { np_err(np, "%s doesn't exist, aborting\n", np->dev_name); err = -ENODEV; @@ -674,19 +673,6 @@ int netpoll_setup(struct netpoll *np) } dev_hold(ndev); - /* bring up DSA management network devices up first */ - for_each_netdev(net, dev) { - if (!netdev_uses_dsa(dev)) - continue; - - err = dev_change_flags(dev, dev->flags | IFF_UP, NULL); - if (err < 0) { - np_err(np, "%s failed to open %s\n", - np->dev_name, dev->name); - goto put; - } - } - if (netdev_master_upper_dev_get(ndev)) { np_err(np, "%s is a slave device, aborting\n", np->dev_name); err = -EBUSY; diff --git a/net/core/page_pool.c b/net/core/page_pool.c index f3c690b8c8e3..ad8b0707af04 100644 --- a/net/core/page_pool.c +++ b/net/core/page_pool.c @@ -350,14 +350,6 @@ static bool page_pool_recycle_in_cache(struct page *page, return true; } -/* page is NOT reusable when: - * 1) allocated when system is under some pressure. (page_is_pfmemalloc) - */ -static bool pool_page_reusable(struct page_pool *pool, struct page *page) -{ - return !page_is_pfmemalloc(page); -} - /* If the page refcnt == 1, this will try to recycle the page. * if PP_FLAG_DMA_SYNC_DEV is set, we'll try to sync the DMA area for * the configured size min(dma_sync_size, pool->max_len). @@ -373,9 +365,11 @@ __page_pool_put_page(struct page_pool *pool, struct page *page, * regular page allocator APIs. * * refcnt == 1 means page_pool owns page, and can recycle it. + * + * page is NOT reusable when allocated when system is under + * some pressure. (page_is_pfmemalloc) */ - if (likely(page_ref_count(page) == 1 && - pool_page_reusable(pool, page))) { + if (likely(page_ref_count(page) == 1 && !page_is_pfmemalloc(page))) { /* Read barrier done in page_ref_count / READ_ONCE */ if (pool->p.flags & PP_FLAG_DMA_SYNC_DEV) diff --git a/net/core/pktgen.c b/net/core/pktgen.c index 105978604ffd..3fba429f1f57 100644 --- a/net/core/pktgen.c +++ b/net/core/pktgen.c @@ -3464,7 +3464,7 @@ static int pktgen_thread_worker(void *arg) struct pktgen_dev *pkt_dev = NULL; int cpu = t->cpu; - BUG_ON(smp_processor_id() != cpu); + WARN_ON(smp_processor_id() != cpu); init_waitqueue_head(&t->queue); complete(&t->start_done); diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 3d6ab194d0f5..0edc0b2baaa4 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -55,7 +55,7 @@ #include <net/net_namespace.h> #define RTNL_MAX_TYPE 50 -#define RTNL_SLAVE_MAX_TYPE 36 +#define RTNL_SLAVE_MAX_TYPE 40 struct rtnl_link { rtnl_doit_func doit; @@ -2660,7 +2660,7 @@ static int do_setlink(const struct sk_buff *skb, sa->sa_family = dev->type; memcpy(sa->sa_data, nla_data(tb[IFLA_ADDRESS]), dev->addr_len); - err = dev_set_mac_address(dev, sa, extack); + err = dev_set_mac_address_user(dev, sa, extack); kfree(sa); if (err) goto errout; diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 785daff48030..545a472273a5 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -119,151 +119,75 @@ static void skb_under_panic(struct sk_buff *skb, unsigned int sz, void *addr) skb_panic(skb, sz, addr, __func__); } -/* - * kmalloc_reserve is a wrapper around kmalloc_node_track_caller that tells - * the caller if emergency pfmemalloc reserves are being used. If it is and - * the socket is later found to be SOCK_MEMALLOC then PFMEMALLOC reserves - * may be used. Otherwise, the packet data may be discarded until enough - * memory is free - */ -#define kmalloc_reserve(size, gfp, node, pfmemalloc) \ - __kmalloc_reserve(size, gfp, node, _RET_IP_, pfmemalloc) - -static void *__kmalloc_reserve(size_t size, gfp_t flags, int node, - unsigned long ip, bool *pfmemalloc) -{ - void *obj; - bool ret_pfmemalloc = false; +#define NAPI_SKB_CACHE_SIZE 64 +#define NAPI_SKB_CACHE_BULK 16 +#define NAPI_SKB_CACHE_HALF (NAPI_SKB_CACHE_SIZE / 2) - /* - * Try a regular allocation, when that fails and we're not entitled - * to the reserves, fail. - */ - obj = kmalloc_node_track_caller(size, - flags | __GFP_NOMEMALLOC | __GFP_NOWARN, - node); - if (obj || !(gfp_pfmemalloc_allowed(flags))) - goto out; +struct napi_alloc_cache { + struct page_frag_cache page; + unsigned int skb_count; + void *skb_cache[NAPI_SKB_CACHE_SIZE]; +}; - /* Try again but now we are using pfmemalloc reserves */ - ret_pfmemalloc = true; - obj = kmalloc_node_track_caller(size, flags, node); +static DEFINE_PER_CPU(struct page_frag_cache, netdev_alloc_cache); +static DEFINE_PER_CPU(struct napi_alloc_cache, napi_alloc_cache); -out: - if (pfmemalloc) - *pfmemalloc = ret_pfmemalloc; +static void *__alloc_frag_align(unsigned int fragsz, gfp_t gfp_mask, + unsigned int align_mask) +{ + struct napi_alloc_cache *nc = this_cpu_ptr(&napi_alloc_cache); - return obj; + return page_frag_alloc_align(&nc->page, fragsz, gfp_mask, align_mask); } -/* Allocate a new skbuff. We do this ourselves so we can fill in a few - * 'private' fields and also do memory statistics to find all the - * [BEEP] leaks. - * - */ - -/** - * __alloc_skb - allocate a network buffer - * @size: size to allocate - * @gfp_mask: allocation mask - * @flags: If SKB_ALLOC_FCLONE is set, allocate from fclone cache - * instead of head cache and allocate a cloned (child) skb. - * If SKB_ALLOC_RX is set, __GFP_MEMALLOC will be used for - * allocations in case the data is required for writeback - * @node: numa node to allocate memory on - * - * Allocate a new &sk_buff. The returned buffer has no headroom and a - * tail room of at least size bytes. The object has a reference count - * of one. The return is the buffer. On a failure the return is %NULL. - * - * Buffers may only be allocated from interrupts using a @gfp_mask of - * %GFP_ATOMIC. - */ -struct sk_buff *__alloc_skb(unsigned int size, gfp_t gfp_mask, - int flags, int node) +void *__napi_alloc_frag_align(unsigned int fragsz, unsigned int align_mask) { - struct kmem_cache *cache; - struct skb_shared_info *shinfo; - struct sk_buff *skb; - u8 *data; - bool pfmemalloc; - - cache = (flags & SKB_ALLOC_FCLONE) - ? skbuff_fclone_cache : skbuff_head_cache; - - if (sk_memalloc_socks() && (flags & SKB_ALLOC_RX)) - gfp_mask |= __GFP_MEMALLOC; - - /* Get the HEAD */ - skb = kmem_cache_alloc_node(cache, gfp_mask & ~__GFP_DMA, node); - if (!skb) - goto out; - prefetchw(skb); - - /* We do our best to align skb_shared_info on a separate cache - * line. It usually works because kmalloc(X > SMP_CACHE_BYTES) gives - * aligned memory blocks, unless SLUB/SLAB debug is enabled. - * Both skb->head and skb_shared_info are cache line aligned. - */ - size = SKB_DATA_ALIGN(size); - size += SKB_DATA_ALIGN(sizeof(struct skb_shared_info)); - data = kmalloc_reserve(size, gfp_mask, node, &pfmemalloc); - if (!data) - goto nodata; - /* kmalloc(size) might give us more room than requested. - * Put skb_shared_info exactly at the end of allocated zone, - * to allow max possible filling before reallocation. - */ - size = SKB_WITH_OVERHEAD(ksize(data)); - prefetchw(data + size); - - /* - * Only clear those fields we need to clear, not those that we will - * actually initialise below. Hence, don't put any more fields after - * the tail pointer in struct sk_buff! - */ - memset(skb, 0, offsetof(struct sk_buff, tail)); - /* Account for allocated memory : skb + skb->head */ - skb->truesize = SKB_TRUESIZE(size); - skb->pfmemalloc = pfmemalloc; - refcount_set(&skb->users, 1); - skb->head = data; - skb->data = data; - skb_reset_tail_pointer(skb); - skb->end = skb->tail + size; - skb->mac_header = (typeof(skb->mac_header))~0U; - skb->transport_header = (typeof(skb->transport_header))~0U; + fragsz = SKB_DATA_ALIGN(fragsz); - /* make sure we initialize shinfo sequentially */ - shinfo = skb_shinfo(skb); - memset(shinfo, 0, offsetof(struct skb_shared_info, dataref)); - atomic_set(&shinfo->dataref, 1); + return __alloc_frag_align(fragsz, GFP_ATOMIC, align_mask); +} +EXPORT_SYMBOL(__napi_alloc_frag_align); - if (flags & SKB_ALLOC_FCLONE) { - struct sk_buff_fclones *fclones; +void *__netdev_alloc_frag_align(unsigned int fragsz, unsigned int align_mask) +{ + struct page_frag_cache *nc; + void *data; - fclones = container_of(skb, struct sk_buff_fclones, skb1); + fragsz = SKB_DATA_ALIGN(fragsz); + if (in_irq() || irqs_disabled()) { + nc = this_cpu_ptr(&netdev_alloc_cache); + data = page_frag_alloc_align(nc, fragsz, GFP_ATOMIC, align_mask); + } else { + local_bh_disable(); + data = __alloc_frag_align(fragsz, GFP_ATOMIC, align_mask); + local_bh_enable(); + } + return data; +} +EXPORT_SYMBOL(__netdev_alloc_frag_align); - skb->fclone = SKB_FCLONE_ORIG; - refcount_set(&fclones->fclone_ref, 1); +static struct sk_buff *napi_skb_cache_get(void) +{ + struct napi_alloc_cache *nc = this_cpu_ptr(&napi_alloc_cache); + struct sk_buff *skb; - fclones->skb2.fclone = SKB_FCLONE_CLONE; - } + if (unlikely(!nc->skb_count)) + nc->skb_count = kmem_cache_alloc_bulk(skbuff_head_cache, + GFP_ATOMIC, + NAPI_SKB_CACHE_BULK, + nc->skb_cache); + if (unlikely(!nc->skb_count)) + return NULL; - skb_set_kcov_handle(skb, kcov_common_handle()); + skb = nc->skb_cache[--nc->skb_count]; + kasan_unpoison_object_data(skbuff_head_cache, skb); -out: return skb; -nodata: - kmem_cache_free(cache, skb); - skb = NULL; - goto out; } -EXPORT_SYMBOL(__alloc_skb); /* Caller must provide SKB that is memset cleared */ -static struct sk_buff *__build_skb_around(struct sk_buff *skb, - void *data, unsigned int frag_size) +static void __build_skb_around(struct sk_buff *skb, void *data, + unsigned int frag_size) { struct skb_shared_info *shinfo; unsigned int size = frag_size ? : ksize(data); @@ -286,8 +210,6 @@ static struct sk_buff *__build_skb_around(struct sk_buff *skb, atomic_set(&shinfo->dataref, 1); skb_set_kcov_handle(skb, kcov_common_handle()); - - return skb; } /** @@ -318,8 +240,9 @@ struct sk_buff *__build_skb(void *data, unsigned int frag_size) return NULL; memset(skb, 0, offsetof(struct sk_buff, tail)); + __build_skb_around(skb, data, frag_size); - return __build_skb_around(skb, data, frag_size); + return skb; } /* build_skb() is wrapper over __build_skb(), that specifically @@ -352,9 +275,9 @@ struct sk_buff *build_skb_around(struct sk_buff *skb, if (unlikely(!skb)) return NULL; - skb = __build_skb_around(skb, data, frag_size); + __build_skb_around(skb, data, frag_size); - if (skb && frag_size) { + if (frag_size) { skb->head_frag = 1; if (page_is_pfmemalloc(virt_to_head_page(data))) skb->pfmemalloc = 1; @@ -363,56 +286,178 @@ struct sk_buff *build_skb_around(struct sk_buff *skb, } EXPORT_SYMBOL(build_skb_around); -#define NAPI_SKB_CACHE_SIZE 64 +/** + * __napi_build_skb - build a network buffer + * @data: data buffer provided by caller + * @frag_size: size of data, or 0 if head was kmalloced + * + * Version of __build_skb() that uses NAPI percpu caches to obtain + * skbuff_head instead of inplace allocation. + * + * Returns a new &sk_buff on success, %NULL on allocation failure. + */ +static struct sk_buff *__napi_build_skb(void *data, unsigned int frag_size) +{ + struct sk_buff *skb; -struct napi_alloc_cache { - struct page_frag_cache page; - unsigned int skb_count; - void *skb_cache[NAPI_SKB_CACHE_SIZE]; -}; + skb = napi_skb_cache_get(); + if (unlikely(!skb)) + return NULL; -static DEFINE_PER_CPU(struct page_frag_cache, netdev_alloc_cache); -static DEFINE_PER_CPU(struct napi_alloc_cache, napi_alloc_cache); + memset(skb, 0, offsetof(struct sk_buff, tail)); + __build_skb_around(skb, data, frag_size); -static void *__napi_alloc_frag(unsigned int fragsz, gfp_t gfp_mask) + return skb; +} + +/** + * napi_build_skb - build a network buffer + * @data: data buffer provided by caller + * @frag_size: size of data, or 0 if head was kmalloced + * + * Version of __napi_build_skb() that takes care of skb->head_frag + * and skb->pfmemalloc when the data is a page or page fragment. + * + * Returns a new &sk_buff on success, %NULL on allocation failure. + */ +struct sk_buff *napi_build_skb(void *data, unsigned int frag_size) { - struct napi_alloc_cache *nc = this_cpu_ptr(&napi_alloc_cache); + struct sk_buff *skb = __napi_build_skb(data, frag_size); - return page_frag_alloc(&nc->page, fragsz, gfp_mask); + if (likely(skb) && frag_size) { + skb->head_frag = 1; + skb_propagate_pfmemalloc(virt_to_head_page(data), skb); + } + + return skb; } +EXPORT_SYMBOL(napi_build_skb); -void *napi_alloc_frag(unsigned int fragsz) +/* + * kmalloc_reserve is a wrapper around kmalloc_node_track_caller that tells + * the caller if emergency pfmemalloc reserves are being used. If it is and + * the socket is later found to be SOCK_MEMALLOC then PFMEMALLOC reserves + * may be used. Otherwise, the packet data may be discarded until enough + * memory is free + */ +static void *kmalloc_reserve(size_t size, gfp_t flags, int node, + bool *pfmemalloc) { - fragsz = SKB_DATA_ALIGN(fragsz); + void *obj; + bool ret_pfmemalloc = false; - return __napi_alloc_frag(fragsz, GFP_ATOMIC); + /* + * Try a regular allocation, when that fails and we're not entitled + * to the reserves, fail. + */ + obj = kmalloc_node_track_caller(size, + flags | __GFP_NOMEMALLOC | __GFP_NOWARN, + node); + if (obj || !(gfp_pfmemalloc_allowed(flags))) + goto out; + + /* Try again but now we are using pfmemalloc reserves */ + ret_pfmemalloc = true; + obj = kmalloc_node_track_caller(size, flags, node); + +out: + if (pfmemalloc) + *pfmemalloc = ret_pfmemalloc; + + return obj; } -EXPORT_SYMBOL(napi_alloc_frag); + +/* Allocate a new skbuff. We do this ourselves so we can fill in a few + * 'private' fields and also do memory statistics to find all the + * [BEEP] leaks. + * + */ /** - * netdev_alloc_frag - allocate a page fragment - * @fragsz: fragment size + * __alloc_skb - allocate a network buffer + * @size: size to allocate + * @gfp_mask: allocation mask + * @flags: If SKB_ALLOC_FCLONE is set, allocate from fclone cache + * instead of head cache and allocate a cloned (child) skb. + * If SKB_ALLOC_RX is set, __GFP_MEMALLOC will be used for + * allocations in case the data is required for writeback + * @node: numa node to allocate memory on + * + * Allocate a new &sk_buff. The returned buffer has no headroom and a + * tail room of at least size bytes. The object has a reference count + * of one. The return is the buffer. On a failure the return is %NULL. * - * Allocates a frag from a page for receive buffer. - * Uses GFP_ATOMIC allocations. + * Buffers may only be allocated from interrupts using a @gfp_mask of + * %GFP_ATOMIC. */ -void *netdev_alloc_frag(unsigned int fragsz) +struct sk_buff *__alloc_skb(unsigned int size, gfp_t gfp_mask, + int flags, int node) { - struct page_frag_cache *nc; - void *data; + struct kmem_cache *cache; + struct sk_buff *skb; + u8 *data; + bool pfmemalloc; - fragsz = SKB_DATA_ALIGN(fragsz); - if (in_irq() || irqs_disabled()) { - nc = this_cpu_ptr(&netdev_alloc_cache); - data = page_frag_alloc(nc, fragsz, GFP_ATOMIC); - } else { - local_bh_disable(); - data = __napi_alloc_frag(fragsz, GFP_ATOMIC); - local_bh_enable(); + cache = (flags & SKB_ALLOC_FCLONE) + ? skbuff_fclone_cache : skbuff_head_cache; + + if (sk_memalloc_socks() && (flags & SKB_ALLOC_RX)) + gfp_mask |= __GFP_MEMALLOC; + + /* Get the HEAD */ + if ((flags & (SKB_ALLOC_FCLONE | SKB_ALLOC_NAPI)) == SKB_ALLOC_NAPI && + likely(node == NUMA_NO_NODE || node == numa_mem_id())) + skb = napi_skb_cache_get(); + else + skb = kmem_cache_alloc_node(cache, gfp_mask & ~GFP_DMA, node); + if (unlikely(!skb)) + return NULL; + prefetchw(skb); + + /* We do our best to align skb_shared_info on a separate cache + * line. It usually works because kmalloc(X > SMP_CACHE_BYTES) gives + * aligned memory blocks, unless SLUB/SLAB debug is enabled. + * Both skb->head and skb_shared_info are cache line aligned. + */ + size = SKB_DATA_ALIGN(size); + size += SKB_DATA_ALIGN(sizeof(struct skb_shared_info)); + data = kmalloc_reserve(size, gfp_mask, node, &pfmemalloc); + if (unlikely(!data)) + goto nodata; + /* kmalloc(size) might give us more room than requested. + * Put skb_shared_info exactly at the end of allocated zone, + * to allow max possible filling before reallocation. + */ + size = SKB_WITH_OVERHEAD(ksize(data)); + prefetchw(data + size); + + /* + * Only clear those fields we need to clear, not those that we will + * actually initialise below. Hence, don't put any more fields after + * the tail pointer in struct sk_buff! + */ + memset(skb, 0, offsetof(struct sk_buff, tail)); + __build_skb_around(skb, data, 0); + skb->pfmemalloc = pfmemalloc; + + if (flags & SKB_ALLOC_FCLONE) { + struct sk_buff_fclones *fclones; + + fclones = container_of(skb, struct sk_buff_fclones, skb1); + + skb->fclone = SKB_FCLONE_ORIG; + refcount_set(&fclones->fclone_ref, 1); + + fclones->skb2.fclone = SKB_FCLONE_CLONE; } - return data; + + return skb; + +nodata: + kmem_cache_free(cache, skb); + return NULL; } -EXPORT_SYMBOL(netdev_alloc_frag); +EXPORT_SYMBOL(__alloc_skb); /** * __netdev_alloc_skb - allocate an skbuff for rx on a specific device @@ -517,7 +562,8 @@ struct sk_buff *__napi_alloc_skb(struct napi_struct *napi, unsigned int len, if (len <= SKB_WITH_OVERHEAD(1024) || len > SKB_WITH_OVERHEAD(PAGE_SIZE) || (gfp_mask & (__GFP_DIRECT_RECLAIM | GFP_DMA))) { - skb = __alloc_skb(len, gfp_mask, SKB_ALLOC_RX, NUMA_NO_NODE); + skb = __alloc_skb(len, gfp_mask, SKB_ALLOC_RX | SKB_ALLOC_NAPI, + NUMA_NO_NODE); if (!skb) goto skb_fail; goto skb_success; @@ -534,7 +580,7 @@ struct sk_buff *__napi_alloc_skb(struct napi_struct *napi, unsigned int len, if (unlikely(!data)) return NULL; - skb = __build_skb(data, len); + skb = __napi_build_skb(data, len); if (unlikely(!skb)) { skb_free_frag(data); return NULL; @@ -614,13 +660,14 @@ static void skb_release_data(struct sk_buff *skb) &shinfo->dataref)) return; + skb_zcopy_clear(skb, true); + for (i = 0; i < shinfo->nr_frags; i++) __skb_frag_unref(&shinfo->frags[i]); if (shinfo->frag_list) kfree_skb_list(shinfo->frag_list); - skb_zcopy_clear(skb, true); skb_free_head(skb); } @@ -864,43 +911,36 @@ void __consume_stateless_skb(struct sk_buff *skb) kfree_skbmem(skb); } -void __kfree_skb_flush(void) +static void napi_skb_cache_put(struct sk_buff *skb) { struct napi_alloc_cache *nc = this_cpu_ptr(&napi_alloc_cache); + u32 i; - /* flush skb_cache if containing objects */ - if (nc->skb_count) { - kmem_cache_free_bulk(skbuff_head_cache, nc->skb_count, - nc->skb_cache); - nc->skb_count = 0; - } -} - -static inline void _kfree_skb_defer(struct sk_buff *skb) -{ - struct napi_alloc_cache *nc = this_cpu_ptr(&napi_alloc_cache); - - /* drop skb->head and call any destructors for packet */ - skb_release_all(skb); - - /* record skb to CPU local list */ + kasan_poison_object_data(skbuff_head_cache, skb); nc->skb_cache[nc->skb_count++] = skb; -#ifdef CONFIG_SLUB - /* SLUB writes into objects when freeing */ - prefetchw(skb); -#endif - - /* flush skb_cache if it is filled */ if (unlikely(nc->skb_count == NAPI_SKB_CACHE_SIZE)) { - kmem_cache_free_bulk(skbuff_head_cache, NAPI_SKB_CACHE_SIZE, - nc->skb_cache); - nc->skb_count = 0; + for (i = NAPI_SKB_CACHE_HALF; i < NAPI_SKB_CACHE_SIZE; i++) + kasan_unpoison_object_data(skbuff_head_cache, + nc->skb_cache[i]); + + kmem_cache_free_bulk(skbuff_head_cache, NAPI_SKB_CACHE_HALF, + nc->skb_cache + NAPI_SKB_CACHE_HALF); + nc->skb_count = NAPI_SKB_CACHE_HALF; } } + void __kfree_skb_defer(struct sk_buff *skb) { - _kfree_skb_defer(skb); + skb_release_all(skb); + napi_skb_cache_put(skb); +} + +void napi_skb_free_stolen_head(struct sk_buff *skb) +{ + skb_dst_drop(skb); + skb_ext_put(skb); + napi_skb_cache_put(skb); } void napi_consume_skb(struct sk_buff *skb, int budget) @@ -925,7 +965,8 @@ void napi_consume_skb(struct sk_buff *skb, int budget) return; } - _kfree_skb_defer(skb); + skb_release_all(skb); + napi_skb_cache_put(skb); } EXPORT_SYMBOL(napi_consume_skb); @@ -1102,7 +1143,7 @@ void mm_unaccount_pinned_pages(struct mmpin *mmp) } EXPORT_SYMBOL_GPL(mm_unaccount_pinned_pages); -struct ubuf_info *sock_zerocopy_alloc(struct sock *sk, size_t size) +struct ubuf_info *msg_zerocopy_alloc(struct sock *sk, size_t size) { struct ubuf_info *uarg; struct sk_buff *skb; @@ -1122,25 +1163,26 @@ struct ubuf_info *sock_zerocopy_alloc(struct sock *sk, size_t size) return NULL; } - uarg->callback = sock_zerocopy_callback; + uarg->callback = msg_zerocopy_callback; uarg->id = ((u32)atomic_inc_return(&sk->sk_zckey)) - 1; uarg->len = 1; uarg->bytelen = size; uarg->zerocopy = 1; + uarg->flags = SKBFL_ZEROCOPY_FRAG; refcount_set(&uarg->refcnt, 1); sock_hold(sk); return uarg; } -EXPORT_SYMBOL_GPL(sock_zerocopy_alloc); +EXPORT_SYMBOL_GPL(msg_zerocopy_alloc); static inline struct sk_buff *skb_from_uarg(struct ubuf_info *uarg) { return container_of((void *)uarg, struct sk_buff, cb); } -struct ubuf_info *sock_zerocopy_realloc(struct sock *sk, size_t size, - struct ubuf_info *uarg) +struct ubuf_info *msg_zerocopy_realloc(struct sock *sk, size_t size, + struct ubuf_info *uarg) { if (uarg) { const u32 byte_limit = 1 << 19; /* limit to a few TSO */ @@ -1172,16 +1214,16 @@ struct ubuf_info *sock_zerocopy_realloc(struct sock *sk, size_t size, /* no extra ref when appending to datagram (MSG_MORE) */ if (sk->sk_type == SOCK_STREAM) - sock_zerocopy_get(uarg); + net_zcopy_get(uarg); return uarg; } } new_alloc: - return sock_zerocopy_alloc(sk, size); + return msg_zerocopy_alloc(sk, size); } -EXPORT_SYMBOL_GPL(sock_zerocopy_realloc); +EXPORT_SYMBOL_GPL(msg_zerocopy_realloc); static bool skb_zerocopy_notify_extend(struct sk_buff *skb, u32 lo, u16 len) { @@ -1203,7 +1245,7 @@ static bool skb_zerocopy_notify_extend(struct sk_buff *skb, u32 lo, u16 len) return true; } -void sock_zerocopy_callback(struct ubuf_info *uarg, bool success) +static void __msg_zerocopy_callback(struct ubuf_info *uarg) { struct sk_buff *tail, *skb = skb_from_uarg(uarg); struct sock_exterr_skb *serr; @@ -1231,7 +1273,7 @@ void sock_zerocopy_callback(struct ubuf_info *uarg, bool success) serr->ee.ee_origin = SO_EE_ORIGIN_ZEROCOPY; serr->ee.ee_data = hi; serr->ee.ee_info = lo; - if (!success) + if (!uarg->zerocopy) serr->ee.ee_code |= SO_EE_CODE_ZEROCOPY_COPIED; q = &sk->sk_error_queue; @@ -1250,32 +1292,28 @@ release: consume_skb(skb); sock_put(sk); } -EXPORT_SYMBOL_GPL(sock_zerocopy_callback); -void sock_zerocopy_put(struct ubuf_info *uarg) +void msg_zerocopy_callback(struct sk_buff *skb, struct ubuf_info *uarg, + bool success) { - if (uarg && refcount_dec_and_test(&uarg->refcnt)) { - if (uarg->callback) - uarg->callback(uarg, uarg->zerocopy); - else - consume_skb(skb_from_uarg(uarg)); - } + uarg->zerocopy = uarg->zerocopy & success; + + if (refcount_dec_and_test(&uarg->refcnt)) + __msg_zerocopy_callback(uarg); } -EXPORT_SYMBOL_GPL(sock_zerocopy_put); +EXPORT_SYMBOL_GPL(msg_zerocopy_callback); -void sock_zerocopy_put_abort(struct ubuf_info *uarg, bool have_uref) +void msg_zerocopy_put_abort(struct ubuf_info *uarg, bool have_uref) { - if (uarg) { - struct sock *sk = skb_from_uarg(uarg)->sk; + struct sock *sk = skb_from_uarg(uarg)->sk; - atomic_dec(&sk->sk_zckey); - uarg->len--; + atomic_dec(&sk->sk_zckey); + uarg->len--; - if (have_uref) - sock_zerocopy_put(uarg); - } + if (have_uref) + msg_zerocopy_callback(NULL, uarg, true); } -EXPORT_SYMBOL_GPL(sock_zerocopy_put_abort); +EXPORT_SYMBOL_GPL(msg_zerocopy_put_abort); int skb_zerocopy_iter_dgram(struct sk_buff *skb, struct msghdr *msg, int len) { @@ -1339,7 +1377,7 @@ static int skb_zerocopy_clone(struct sk_buff *nskb, struct sk_buff *orig, * @skb: the skb to modify * @gfp_mask: allocation priority * - * This must be called on SKBTX_DEV_ZEROCOPY skb. + * This must be called on skb with SKBFL_ZEROCOPY_ENABLE. * It will copy all frags into kernel and drop the reference * to userspace pages. * @@ -3276,8 +3314,7 @@ void skb_split(struct sk_buff *skb, struct sk_buff *skb1, const u32 len) { int pos = skb_headlen(skb); - skb_shinfo(skb1)->tx_flags |= skb_shinfo(skb)->tx_flags & - SKBTX_SHARED_FRAG; + skb_shinfo(skb1)->flags |= skb_shinfo(skb)->flags & SKBFL_SHARED_FRAG; skb_zerocopy_clone(skb1, skb, 0); if (len < pos) /* Split line is inside header. */ skb_split_inside_header(skb, skb1, len, pos); @@ -3292,7 +3329,19 @@ EXPORT_SYMBOL(skb_split); */ static int skb_prepare_for_shift(struct sk_buff *skb) { - return skb_cloned(skb) && pskb_expand_head(skb, 0, 0, GFP_ATOMIC); + int ret = 0; + + if (skb_cloned(skb)) { + /* Save and restore truesize: pskb_expand_head() may reallocate + * memory where ksize(kmalloc(S)) != ksize(kmalloc(S)), but we + * cannot change truesize at this point. + */ + unsigned int save_truesize = skb->truesize; + + ret = pskb_expand_head(skb, 0, 0, GFP_ATOMIC); + skb->truesize = save_truesize; + } + return ret; } /** @@ -3901,12 +3950,8 @@ normal: } hsize = skb_headlen(head_skb) - offset; - if (hsize < 0) - hsize = 0; - if (hsize > len || !sg) - hsize = len; - if (!hsize && i >= nfrags && skb_headlen(list_skb) && + if (hsize <= 0 && i >= nfrags && skb_headlen(list_skb) && (skb_headlen(list_skb) == len || sg)) { BUG_ON(skb_headlen(list_skb) > len); @@ -3949,6 +3994,11 @@ normal: skb_release_head_state(nskb); __skb_push(nskb, doffset); } else { + if (hsize < 0) + hsize = 0; + if (hsize > len || !sg) + hsize = len; + nskb = __alloc_skb(hsize + doffset + headroom, GFP_ATOMIC, skb_alloc_rx_flag(head_skb), NUMA_NO_NODE); @@ -4002,8 +4052,8 @@ normal: skb_copy_from_linear_data_offset(head_skb, offset, skb_put(nskb, hsize), hsize); - skb_shinfo(nskb)->tx_flags |= skb_shinfo(head_skb)->tx_flags & - SKBTX_SHARED_FRAG; + skb_shinfo(nskb)->flags |= skb_shinfo(head_skb)->flags & + SKBFL_SHARED_FRAG; if (skb_orphan_frags(frag_skb, GFP_ATOMIC) || skb_zerocopy_clone(nskb, frag_skb, GFP_ATOMIC)) @@ -4723,6 +4773,7 @@ err: EXPORT_SYMBOL_GPL(skb_complete_tx_timestamp); void __skb_tstamp_tx(struct sk_buff *orig_skb, + const struct sk_buff *ack_skb, struct skb_shared_hwtstamps *hwtstamps, struct sock *sk, int tstype) { @@ -4745,7 +4796,8 @@ void __skb_tstamp_tx(struct sk_buff *orig_skb, if ((sk->sk_tsflags & SOF_TIMESTAMPING_OPT_STATS) && sk->sk_protocol == IPPROTO_TCP && sk->sk_type == SOCK_STREAM) { - skb = tcp_get_timestamping_opt_stats(sk, orig_skb); + skb = tcp_get_timestamping_opt_stats(sk, orig_skb, + ack_skb); opt_stats = true; } else #endif @@ -4774,7 +4826,7 @@ EXPORT_SYMBOL_GPL(__skb_tstamp_tx); void skb_tstamp_tx(struct sk_buff *orig_skb, struct skb_shared_hwtstamps *hwtstamps) { - return __skb_tstamp_tx(orig_skb, hwtstamps, orig_skb->sk, + return __skb_tstamp_tx(orig_skb, NULL, hwtstamps, orig_skb->sk, SCM_TSTAMP_SND); } EXPORT_SYMBOL_GPL(skb_tstamp_tx); diff --git a/net/core/skmsg.c b/net/core/skmsg.c index 25cdbb20f3a0..1261512d6807 100644 --- a/net/core/skmsg.c +++ b/net/core/skmsg.c @@ -669,14 +669,13 @@ static void sk_psock_destroy_deferred(struct work_struct *gc) kfree(psock); } -void sk_psock_destroy(struct rcu_head *rcu) +static void sk_psock_destroy(struct rcu_head *rcu) { struct sk_psock *psock = container_of(rcu, struct sk_psock, rcu); INIT_WORK(&psock->gc, sk_psock_destroy_deferred); schedule_work(&psock->gc); } -EXPORT_SYMBOL_GPL(sk_psock_destroy); void sk_psock_drop(struct sock *sk, struct sk_psock *psock) { diff --git a/net/core/sock.c b/net/core/sock.c index bbcd4b97eddd..0ed98f20448a 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -526,11 +526,17 @@ discard_and_relse: } EXPORT_SYMBOL(__sk_receive_skb); +INDIRECT_CALLABLE_DECLARE(struct dst_entry *ip6_dst_check(struct dst_entry *, + u32)); +INDIRECT_CALLABLE_DECLARE(struct dst_entry *ipv4_dst_check(struct dst_entry *, + u32)); struct dst_entry *__sk_dst_check(struct sock *sk, u32 cookie) { struct dst_entry *dst = __sk_dst_get(sk); - if (dst && dst->obsolete && dst->ops->check(dst, cookie) == NULL) { + if (dst && dst->obsolete && + INDIRECT_CALL_INET(dst->ops->check, ip6_dst_check, ipv4_dst_check, + dst, cookie) == NULL) { sk_tx_queue_clear(sk); sk->sk_dst_pending_confirm = 0; RCU_INIT_POINTER(sk->sk_dst_cache, NULL); @@ -546,7 +552,9 @@ struct dst_entry *sk_dst_check(struct sock *sk, u32 cookie) { struct dst_entry *dst = sk_dst_get(sk); - if (dst && dst->obsolete && dst->ops->check(dst, cookie) == NULL) { + if (dst && dst->obsolete && + INDIRECT_CALL_INET(dst->ops->check, ip6_dst_check, ipv4_dst_check, + dst, cookie) == NULL) { sk_dst_reset(sk); dst_release(dst); return NULL; @@ -1657,6 +1665,16 @@ static void sock_copy(struct sock *nsk, const struct sock *osk) #ifdef CONFIG_SECURITY_NETWORK void *sptr = nsk->sk_security; #endif + + /* If we move sk_tx_queue_mapping out of the private section, + * we must check if sk_tx_queue_clear() is called after + * sock_copy() in sk_clone_lock(). + */ + BUILD_BUG_ON(offsetof(struct sock, sk_tx_queue_mapping) < + offsetof(struct sock, sk_dontcopy_begin) || + offsetof(struct sock, sk_tx_queue_mapping) >= + offsetof(struct sock, sk_dontcopy_end)); + memcpy(nsk, osk, offsetof(struct sock, sk_dontcopy_begin)); memcpy(&nsk->sk_dontcopy_end, &osk->sk_dontcopy_end, @@ -1690,7 +1708,6 @@ static struct sock *sk_prot_alloc(struct proto *prot, gfp_t priority, if (!try_module_get(prot->owner)) goto out_free_sec; - sk_tx_queue_clear(sk); } return sk; @@ -1876,123 +1893,120 @@ static void sk_init_common(struct sock *sk) struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority) { struct proto *prot = READ_ONCE(sk->sk_prot); - struct sock *newsk; + struct sk_filter *filter; bool is_charged = true; + struct sock *newsk; newsk = sk_prot_alloc(prot, priority, sk->sk_family); - if (newsk != NULL) { - struct sk_filter *filter; + if (!newsk) + goto out; - sock_copy(newsk, sk); + sock_copy(newsk, sk); - newsk->sk_prot_creator = prot; + newsk->sk_prot_creator = prot; - /* SANITY */ - if (likely(newsk->sk_net_refcnt)) - get_net(sock_net(newsk)); - sk_node_init(&newsk->sk_node); - sock_lock_init(newsk); - bh_lock_sock(newsk); - newsk->sk_backlog.head = newsk->sk_backlog.tail = NULL; - newsk->sk_backlog.len = 0; + /* SANITY */ + if (likely(newsk->sk_net_refcnt)) + get_net(sock_net(newsk)); + sk_node_init(&newsk->sk_node); + sock_lock_init(newsk); + bh_lock_sock(newsk); + newsk->sk_backlog.head = newsk->sk_backlog.tail = NULL; + newsk->sk_backlog.len = 0; - atomic_set(&newsk->sk_rmem_alloc, 0); - /* - * sk_wmem_alloc set to one (see sk_free() and sock_wfree()) - */ - refcount_set(&newsk->sk_wmem_alloc, 1); - atomic_set(&newsk->sk_omem_alloc, 0); - sk_init_common(newsk); + atomic_set(&newsk->sk_rmem_alloc, 0); - newsk->sk_dst_cache = NULL; - newsk->sk_dst_pending_confirm = 0; - newsk->sk_wmem_queued = 0; - newsk->sk_forward_alloc = 0; - atomic_set(&newsk->sk_drops, 0); - newsk->sk_send_head = NULL; - newsk->sk_userlocks = sk->sk_userlocks & ~SOCK_BINDPORT_LOCK; - atomic_set(&newsk->sk_zckey, 0); + /* sk_wmem_alloc set to one (see sk_free() and sock_wfree()) */ + refcount_set(&newsk->sk_wmem_alloc, 1); - sock_reset_flag(newsk, SOCK_DONE); + atomic_set(&newsk->sk_omem_alloc, 0); + sk_init_common(newsk); - /* sk->sk_memcg will be populated at accept() time */ - newsk->sk_memcg = NULL; + newsk->sk_dst_cache = NULL; + newsk->sk_dst_pending_confirm = 0; + newsk->sk_wmem_queued = 0; + newsk->sk_forward_alloc = 0; + atomic_set(&newsk->sk_drops, 0); + newsk->sk_send_head = NULL; + newsk->sk_userlocks = sk->sk_userlocks & ~SOCK_BINDPORT_LOCK; + atomic_set(&newsk->sk_zckey, 0); - cgroup_sk_clone(&newsk->sk_cgrp_data); + sock_reset_flag(newsk, SOCK_DONE); - rcu_read_lock(); - filter = rcu_dereference(sk->sk_filter); - if (filter != NULL) - /* though it's an empty new sock, the charging may fail - * if sysctl_optmem_max was changed between creation of - * original socket and cloning - */ - is_charged = sk_filter_charge(newsk, filter); - RCU_INIT_POINTER(newsk->sk_filter, filter); - rcu_read_unlock(); + /* sk->sk_memcg will be populated at accept() time */ + newsk->sk_memcg = NULL; - if (unlikely(!is_charged || xfrm_sk_clone_policy(newsk, sk))) { - /* We need to make sure that we don't uncharge the new - * socket if we couldn't charge it in the first place - * as otherwise we uncharge the parent's filter. - */ - if (!is_charged) - RCU_INIT_POINTER(newsk->sk_filter, NULL); - sk_free_unlock_clone(newsk); - newsk = NULL; - goto out; - } - RCU_INIT_POINTER(newsk->sk_reuseport_cb, NULL); + cgroup_sk_clone(&newsk->sk_cgrp_data); - if (bpf_sk_storage_clone(sk, newsk)) { - sk_free_unlock_clone(newsk); - newsk = NULL; - goto out; - } + rcu_read_lock(); + filter = rcu_dereference(sk->sk_filter); + if (filter != NULL) + /* though it's an empty new sock, the charging may fail + * if sysctl_optmem_max was changed between creation of + * original socket and cloning + */ + is_charged = sk_filter_charge(newsk, filter); + RCU_INIT_POINTER(newsk->sk_filter, filter); + rcu_read_unlock(); - /* Clear sk_user_data if parent had the pointer tagged - * as not suitable for copying when cloning. + if (unlikely(!is_charged || xfrm_sk_clone_policy(newsk, sk))) { + /* We need to make sure that we don't uncharge the new + * socket if we couldn't charge it in the first place + * as otherwise we uncharge the parent's filter. */ - if (sk_user_data_is_nocopy(newsk)) - newsk->sk_user_data = NULL; + if (!is_charged) + RCU_INIT_POINTER(newsk->sk_filter, NULL); + sk_free_unlock_clone(newsk); + newsk = NULL; + goto out; + } + RCU_INIT_POINTER(newsk->sk_reuseport_cb, NULL); - newsk->sk_err = 0; - newsk->sk_err_soft = 0; - newsk->sk_priority = 0; - newsk->sk_incoming_cpu = raw_smp_processor_id(); - if (likely(newsk->sk_net_refcnt)) - sock_inuse_add(sock_net(newsk), 1); + if (bpf_sk_storage_clone(sk, newsk)) { + sk_free_unlock_clone(newsk); + newsk = NULL; + goto out; + } - /* - * Before updating sk_refcnt, we must commit prior changes to memory - * (Documentation/RCU/rculist_nulls.rst for details) - */ - smp_wmb(); - refcount_set(&newsk->sk_refcnt, 2); + /* Clear sk_user_data if parent had the pointer tagged + * as not suitable for copying when cloning. + */ + if (sk_user_data_is_nocopy(newsk)) + newsk->sk_user_data = NULL; - /* - * Increment the counter in the same struct proto as the master - * sock (sk_refcnt_debug_inc uses newsk->sk_prot->socks, that - * is the same as sk->sk_prot->socks, as this field was copied - * with memcpy). - * - * This _changes_ the previous behaviour, where - * tcp_create_openreq_child always was incrementing the - * equivalent to tcp_prot->socks (inet_sock_nr), so this have - * to be taken into account in all callers. -acme - */ - sk_refcnt_debug_inc(newsk); - sk_set_socket(newsk, NULL); - sk_tx_queue_clear(newsk); - RCU_INIT_POINTER(newsk->sk_wq, NULL); + newsk->sk_err = 0; + newsk->sk_err_soft = 0; + newsk->sk_priority = 0; + newsk->sk_incoming_cpu = raw_smp_processor_id(); + if (likely(newsk->sk_net_refcnt)) + sock_inuse_add(sock_net(newsk), 1); - if (newsk->sk_prot->sockets_allocated) - sk_sockets_allocated_inc(newsk); + /* Before updating sk_refcnt, we must commit prior changes to memory + * (Documentation/RCU/rculist_nulls.rst for details) + */ + smp_wmb(); + refcount_set(&newsk->sk_refcnt, 2); - if (sock_needs_netstamp(sk) && - newsk->sk_flags & SK_FLAGS_TIMESTAMP) - net_enable_timestamp(); - } + /* Increment the counter in the same struct proto as the master + * sock (sk_refcnt_debug_inc uses newsk->sk_prot->socks, that + * is the same as sk->sk_prot->socks, as this field was copied + * with memcpy). + * + * This _changes_ the previous behaviour, where + * tcp_create_openreq_child always was incrementing the + * equivalent to tcp_prot->socks (inet_sock_nr), so this have + * to be taken into account in all callers. -acme + */ + sk_refcnt_debug_inc(newsk); + sk_set_socket(newsk, NULL); + sk_tx_queue_clear(newsk); + RCU_INIT_POINTER(newsk->sk_wq, NULL); + + if (newsk->sk_prot->sockets_allocated) + sk_sockets_allocated_inc(newsk); + + if (sock_needs_netstamp(sk) && newsk->sk_flags & SK_FLAGS_TIMESTAMP) + net_enable_timestamp(); out: return newsk; } diff --git a/net/core/sock_map.c b/net/core/sock_map.c index 64b5ec14ff50..d758fb83c884 100644 --- a/net/core/sock_map.c +++ b/net/core/sock_map.c @@ -602,7 +602,7 @@ int sock_map_update_elem_sys(struct bpf_map *map, void *key, void *value, ret = sock_hash_update_common(map, key, sk, flags); sock_map_sk_release(sk); out: - fput(sock->file); + sockfd_put(sock); return ret; } diff --git a/net/core/sysctl_net_core.c b/net/core/sysctl_net_core.c index d86d8d11cfe4..4567de519603 100644 --- a/net/core/sysctl_net_core.c +++ b/net/core/sysctl_net_core.c @@ -309,7 +309,6 @@ proc_dolongvec_minmax_bpf_restricted(struct ctl_table *table, int write, #endif static struct ctl_table net_core_table[] = { -#ifdef CONFIG_NET { .procname = "wmem_max", .data = &sysctl_wmem_max, @@ -507,7 +506,6 @@ static struct ctl_table net_core_table[] = { .proc_handler = set_default_qdisc }, #endif -#endif /* CONFIG_NET */ { .procname = "netdev_budget", .data = &netdev_budget, diff --git a/net/core/xdp.c b/net/core/xdp.c index 3a8c9ab4ecbe..05354976c1fc 100644 --- a/net/core/xdp.c +++ b/net/core/xdp.c @@ -513,3 +513,73 @@ void xdp_warn(const char *msg, const char *func, const int line) WARN(1, "XDP_WARN: %s(line:%d): %s\n", func, line, msg); }; EXPORT_SYMBOL_GPL(xdp_warn); + +int xdp_alloc_skb_bulk(void **skbs, int n_skb, gfp_t gfp) +{ + n_skb = kmem_cache_alloc_bulk(skbuff_head_cache, gfp, + n_skb, skbs); + if (unlikely(!n_skb)) + return -ENOMEM; + + return 0; +} +EXPORT_SYMBOL_GPL(xdp_alloc_skb_bulk); + +struct sk_buff *__xdp_build_skb_from_frame(struct xdp_frame *xdpf, + struct sk_buff *skb, + struct net_device *dev) +{ + unsigned int headroom, frame_size; + void *hard_start; + + /* Part of headroom was reserved to xdpf */ + headroom = sizeof(*xdpf) + xdpf->headroom; + + /* Memory size backing xdp_frame data already have reserved + * room for build_skb to place skb_shared_info in tailroom. + */ + frame_size = xdpf->frame_sz; + + hard_start = xdpf->data - headroom; + skb = build_skb_around(skb, hard_start, frame_size); + if (unlikely(!skb)) + return NULL; + + skb_reserve(skb, headroom); + __skb_put(skb, xdpf->len); + if (xdpf->metasize) + skb_metadata_set(skb, xdpf->metasize); + + /* Essential SKB info: protocol and skb->dev */ + skb->protocol = eth_type_trans(skb, dev); + + /* Optional SKB info, currently missing: + * - HW checksum info (skb->ip_summed) + * - HW RX hash (skb_set_hash) + * - RX ring dev queue index (skb_record_rx_queue) + */ + + /* Until page_pool get SKB return path, release DMA here */ + xdp_release_frame(xdpf); + + /* Allow SKB to reuse area used by xdp_frame */ + xdp_scrub_frame(xdpf); + + return skb; +} +EXPORT_SYMBOL_GPL(__xdp_build_skb_from_frame); + +struct sk_buff *xdp_build_skb_from_frame(struct xdp_frame *xdpf, + struct net_device *dev) +{ + struct sk_buff *skb; + + skb = kmem_cache_alloc(skbuff_head_cache, GFP_ATOMIC); + if (unlikely(!skb)) + return NULL; + + memset(skb, 0, offsetof(struct sk_buff, tail)); + + return __xdp_build_skb_from_frame(xdpf, skb, dev); +} +EXPORT_SYMBOL_GPL(xdp_build_skb_from_frame); diff --git a/net/dcb/Makefile b/net/dcb/Makefile index 3016e5a7716a..2c0fa16ee2a9 100644 --- a/net/dcb/Makefile +++ b/net/dcb/Makefile @@ -1,2 +1,2 @@ # SPDX-License-Identifier: GPL-2.0-only -obj-$(CONFIG_DCB) += dcbnl.o dcbevent.o +obj-y += dcbnl.o dcbevent.o diff --git a/net/dccp/feat.c b/net/dccp/feat.c index 305f56804832..54086bb05c42 100644 --- a/net/dccp/feat.c +++ b/net/dccp/feat.c @@ -371,7 +371,7 @@ static int dccp_feat_clone_sp_val(dccp_feat_val *fval, u8 const *val, u8 len) fval->sp.vec = kmemdup(val, len, gfp_any()); if (fval->sp.vec == NULL) { fval->sp.len = 0; - return -ENOBUFS; + return -ENOMEM; } } return 0; diff --git a/net/dns_resolver/Kconfig b/net/dns_resolver/Kconfig index 255df9b6e9e8..155b06163409 100644 --- a/net/dns_resolver/Kconfig +++ b/net/dns_resolver/Kconfig @@ -4,7 +4,7 @@ # config DNS_RESOLVER tristate "DNS Resolver support" - depends on NET && KEYS + depends on KEYS help Saying Y here will include support for the DNS Resolver key type which can be used to make upcalls to perform DNS lookups in diff --git a/net/dsa/Kconfig b/net/dsa/Kconfig index dfecd7b22fd7..3589224c8da9 100644 --- a/net/dsa/Kconfig +++ b/net/dsa/Kconfig @@ -9,6 +9,7 @@ menuconfig NET_DSA tristate "Distributed Switch Architecture" depends on HAVE_NET_DSA depends on BRIDGE || BRIDGE=n + depends on HSR || HSR=n select GRO_CELLS select NET_SWITCHDEV select PHYLINK @@ -105,11 +106,26 @@ config NET_DSA_TAG_RTL4_A the Realtek RTL8366RB. config NET_DSA_TAG_OCELOT - tristate "Tag driver for Ocelot family of switches" + tristate "Tag driver for Ocelot family of switches, using NPI port" select PACKING help - Say Y or M if you want to enable support for tagging frames for the - Ocelot switches (VSC7511, VSC7512, VSC7513, VSC7514, VSC9959). + Say Y or M if you want to enable NPI tagging for the Ocelot switches + (VSC7511, VSC7512, VSC7513, VSC7514, VSC9953, VSC9959). In this mode, + the frames over the Ethernet CPU port are prepended with a + hardware-defined injection/extraction frame header. Flow control + (PAUSE frames) over the CPU port is not supported when operating in + this mode. + +config NET_DSA_TAG_OCELOT_8021Q + tristate "Tag driver for Ocelot family of switches, using VLAN" + select NET_DSA_TAG_8021Q + help + Say Y or M if you want to enable support for tagging frames with a + custom VLAN-based header. Frames that require timestamping, such as + PTP, are not delivered over Ethernet but over register-based MMIO. + Flow control over the CPU port is functional in this mode. When using + this mode, less TCAM resources (VCAP IS1, IS2, ES0) are available for + use with tc-flower. config NET_DSA_TAG_QCA tristate "Tag driver for Qualcomm Atheros QCA8K switches" @@ -139,4 +155,10 @@ config NET_DSA_TAG_TRAILER Say Y or M if you want to enable support for tagging frames at with a trailed. e.g. Marvell 88E6060. +config NET_DSA_TAG_XRS700X + tristate "Tag driver for XRS700x switches" + help + Say Y or M if you want to enable support for tagging frames for + Arrow SpeedChips XRS700x switches that use a single byte tag trailer. + endif diff --git a/net/dsa/Makefile b/net/dsa/Makefile index 0fb2b75a7ae3..44bc79952b8b 100644 --- a/net/dsa/Makefile +++ b/net/dsa/Makefile @@ -15,6 +15,8 @@ obj-$(CONFIG_NET_DSA_TAG_RTL4_A) += tag_rtl4_a.o obj-$(CONFIG_NET_DSA_TAG_LAN9303) += tag_lan9303.o obj-$(CONFIG_NET_DSA_TAG_MTK) += tag_mtk.o obj-$(CONFIG_NET_DSA_TAG_OCELOT) += tag_ocelot.o +obj-$(CONFIG_NET_DSA_TAG_OCELOT_8021Q) += tag_ocelot_8021q.o obj-$(CONFIG_NET_DSA_TAG_QCA) += tag_qca.o obj-$(CONFIG_NET_DSA_TAG_SJA1105) += tag_sja1105.o obj-$(CONFIG_NET_DSA_TAG_TRAILER) += tag_trailer.o +obj-$(CONFIG_NET_DSA_TAG_XRS700X) += tag_xrs700x.o diff --git a/net/dsa/dsa.c b/net/dsa/dsa.c index a1b1dc8a4d87..84cad1be9ce4 100644 --- a/net/dsa/dsa.c +++ b/net/dsa/dsa.c @@ -84,6 +84,32 @@ const char *dsa_tag_protocol_to_str(const struct dsa_device_ops *ops) return ops->name; }; +/* Function takes a reference on the module owning the tagger, + * so dsa_tag_driver_put must be called afterwards. + */ +const struct dsa_device_ops *dsa_find_tagger_by_name(const char *buf) +{ + const struct dsa_device_ops *ops = ERR_PTR(-ENOPROTOOPT); + struct dsa_tag_driver *dsa_tag_driver; + + mutex_lock(&dsa_tag_drivers_lock); + list_for_each_entry(dsa_tag_driver, &dsa_tag_drivers_list, list) { + const struct dsa_device_ops *tmp = dsa_tag_driver->ops; + + if (!sysfs_streq(buf, tmp->name)) + continue; + + if (!try_module_get(dsa_tag_driver->owner)) + break; + + ops = tmp; + break; + } + mutex_unlock(&dsa_tag_drivers_lock); + + return ops; +} + const struct dsa_device_ops *dsa_tag_driver_get(int tag_protocol) { struct dsa_tag_driver *dsa_tag_driver; @@ -219,11 +245,21 @@ static int dsa_switch_rcv(struct sk_buff *skb, struct net_device *dev, } skb = nskb; - p = netdev_priv(skb->dev); skb_push(skb, ETH_HLEN); skb->pkt_type = PACKET_HOST; skb->protocol = eth_type_trans(skb, skb->dev); + if (unlikely(!dsa_slave_dev_check(skb->dev))) { + /* Packet is to be injected directly on an upper + * device, e.g. a team/bond, so skip all DSA-port + * specific actions. + */ + netif_rx(skb); + return 0; + } + + p = netdev_priv(skb->dev); + if (unlikely(cpu_dp->ds->untag_bridge_pvid)) { nskb = dsa_untag_bridge_pvid(skb); if (!nskb) { @@ -309,28 +345,6 @@ bool dsa_schedule_work(struct work_struct *work) return queue_work(dsa_owq, work); } -static ATOMIC_NOTIFIER_HEAD(dsa_notif_chain); - -int register_dsa_notifier(struct notifier_block *nb) -{ - return atomic_notifier_chain_register(&dsa_notif_chain, nb); -} -EXPORT_SYMBOL_GPL(register_dsa_notifier); - -int unregister_dsa_notifier(struct notifier_block *nb) -{ - return atomic_notifier_chain_unregister(&dsa_notif_chain, nb); -} -EXPORT_SYMBOL_GPL(unregister_dsa_notifier); - -int call_dsa_notifiers(unsigned long val, struct net_device *dev, - struct dsa_notifier_info *info) -{ - info->dev = dev; - return atomic_notifier_call_chain(&dsa_notif_chain, val, info); -} -EXPORT_SYMBOL_GPL(call_dsa_notifiers); - int dsa_devlink_param_get(struct devlink *dl, u32 id, struct devlink_param_gset_ctx *ctx) { diff --git a/net/dsa/dsa2.c b/net/dsa/dsa2.c index a04fd637b4cd..4d4956ed303b 100644 --- a/net/dsa/dsa2.c +++ b/net/dsa/dsa2.c @@ -21,6 +21,108 @@ static DEFINE_MUTEX(dsa2_mutex); LIST_HEAD(dsa_tree_list); +/** + * dsa_tree_notify - Execute code for all switches in a DSA switch tree. + * @dst: collection of struct dsa_switch devices to notify. + * @e: event, must be of type DSA_NOTIFIER_* + * @v: event-specific value. + * + * Given a struct dsa_switch_tree, this can be used to run a function once for + * each member DSA switch. The other alternative of traversing the tree is only + * through its ports list, which does not uniquely list the switches. + */ +int dsa_tree_notify(struct dsa_switch_tree *dst, unsigned long e, void *v) +{ + struct raw_notifier_head *nh = &dst->nh; + int err; + + err = raw_notifier_call_chain(nh, e, v); + + return notifier_to_errno(err); +} + +/** + * dsa_broadcast - Notify all DSA trees in the system. + * @e: event, must be of type DSA_NOTIFIER_* + * @v: event-specific value. + * + * Can be used to notify the switching fabric of events such as cross-chip + * bridging between disjoint trees (such as islands of tagger-compatible + * switches bridged by an incompatible middle switch). + */ +int dsa_broadcast(unsigned long e, void *v) +{ + struct dsa_switch_tree *dst; + int err = 0; + + list_for_each_entry(dst, &dsa_tree_list, list) { + err = dsa_tree_notify(dst, e, v); + if (err) + break; + } + + return err; +} + +/** + * dsa_lag_map() - Map LAG netdev to a linear LAG ID + * @dst: Tree in which to record the mapping. + * @lag: Netdev that is to be mapped to an ID. + * + * dsa_lag_id/dsa_lag_dev can then be used to translate between the + * two spaces. The size of the mapping space is determined by the + * driver by setting ds->num_lag_ids. It is perfectly legal to leave + * it unset if it is not needed, in which case these functions become + * no-ops. + */ +void dsa_lag_map(struct dsa_switch_tree *dst, struct net_device *lag) +{ + unsigned int id; + + if (dsa_lag_id(dst, lag) >= 0) + /* Already mapped */ + return; + + for (id = 0; id < dst->lags_len; id++) { + if (!dsa_lag_dev(dst, id)) { + dst->lags[id] = lag; + return; + } + } + + /* No IDs left, which is OK. Some drivers do not need it. The + * ones that do, e.g. mv88e6xxx, will discover that dsa_lag_id + * returns an error for this device when joining the LAG. The + * driver can then return -EOPNOTSUPP back to DSA, which will + * fall back to a software LAG. + */ +} + +/** + * dsa_lag_unmap() - Remove a LAG ID mapping + * @dst: Tree in which the mapping is recorded. + * @lag: Netdev that was mapped. + * + * As there may be multiple users of the mapping, it is only removed + * if there are no other references to it. + */ +void dsa_lag_unmap(struct dsa_switch_tree *dst, struct net_device *lag) +{ + struct dsa_port *dp; + unsigned int id; + + dsa_lag_foreach_port(dp, dst, lag) + /* There are remaining users of this mapping */ + return; + + dsa_lags_foreach_id(id, dst) { + if (dsa_lag_dev(dst, id) == lag) { + dst->lags[id] = NULL; + break; + } + } +} + struct dsa_switch *dsa_switch_find(int tree_index, int sw_index) { struct dsa_switch_tree *dst; @@ -77,6 +179,8 @@ static struct dsa_switch_tree *dsa_tree_alloc(int index) static void dsa_tree_free(struct dsa_switch_tree *dst) { + if (dst->tag_ops) + dsa_tag_driver_put(dst->tag_ops); list_del(&dst->list); kfree(dst); } @@ -365,7 +469,6 @@ static void dsa_port_teardown(struct dsa_port *dp) break; case DSA_PORT_TYPE_CPU: dsa_port_disable(dp); - dsa_tag_driver_put(dp->tag_ops); dsa_port_link_unregister_of(dp); break; case DSA_PORT_TYPE_DSA: @@ -404,8 +507,165 @@ static int dsa_devlink_info_get(struct devlink *dl, return -EOPNOTSUPP; } +static int dsa_devlink_sb_pool_get(struct devlink *dl, + unsigned int sb_index, u16 pool_index, + struct devlink_sb_pool_info *pool_info) +{ + struct dsa_switch *ds = dsa_devlink_to_ds(dl); + + if (!ds->ops->devlink_sb_pool_get) + return -EOPNOTSUPP; + + return ds->ops->devlink_sb_pool_get(ds, sb_index, pool_index, + pool_info); +} + +static int dsa_devlink_sb_pool_set(struct devlink *dl, unsigned int sb_index, + u16 pool_index, u32 size, + enum devlink_sb_threshold_type threshold_type, + struct netlink_ext_ack *extack) +{ + struct dsa_switch *ds = dsa_devlink_to_ds(dl); + + if (!ds->ops->devlink_sb_pool_set) + return -EOPNOTSUPP; + + return ds->ops->devlink_sb_pool_set(ds, sb_index, pool_index, size, + threshold_type, extack); +} + +static int dsa_devlink_sb_port_pool_get(struct devlink_port *dlp, + unsigned int sb_index, u16 pool_index, + u32 *p_threshold) +{ + struct dsa_switch *ds = dsa_devlink_port_to_ds(dlp); + int port = dsa_devlink_port_to_port(dlp); + + if (!ds->ops->devlink_sb_port_pool_get) + return -EOPNOTSUPP; + + return ds->ops->devlink_sb_port_pool_get(ds, port, sb_index, + pool_index, p_threshold); +} + +static int dsa_devlink_sb_port_pool_set(struct devlink_port *dlp, + unsigned int sb_index, u16 pool_index, + u32 threshold, + struct netlink_ext_ack *extack) +{ + struct dsa_switch *ds = dsa_devlink_port_to_ds(dlp); + int port = dsa_devlink_port_to_port(dlp); + + if (!ds->ops->devlink_sb_port_pool_set) + return -EOPNOTSUPP; + + return ds->ops->devlink_sb_port_pool_set(ds, port, sb_index, + pool_index, threshold, extack); +} + +static int +dsa_devlink_sb_tc_pool_bind_get(struct devlink_port *dlp, + unsigned int sb_index, u16 tc_index, + enum devlink_sb_pool_type pool_type, + u16 *p_pool_index, u32 *p_threshold) +{ + struct dsa_switch *ds = dsa_devlink_port_to_ds(dlp); + int port = dsa_devlink_port_to_port(dlp); + + if (!ds->ops->devlink_sb_tc_pool_bind_get) + return -EOPNOTSUPP; + + return ds->ops->devlink_sb_tc_pool_bind_get(ds, port, sb_index, + tc_index, pool_type, + p_pool_index, p_threshold); +} + +static int +dsa_devlink_sb_tc_pool_bind_set(struct devlink_port *dlp, + unsigned int sb_index, u16 tc_index, + enum devlink_sb_pool_type pool_type, + u16 pool_index, u32 threshold, + struct netlink_ext_ack *extack) +{ + struct dsa_switch *ds = dsa_devlink_port_to_ds(dlp); + int port = dsa_devlink_port_to_port(dlp); + + if (!ds->ops->devlink_sb_tc_pool_bind_set) + return -EOPNOTSUPP; + + return ds->ops->devlink_sb_tc_pool_bind_set(ds, port, sb_index, + tc_index, pool_type, + pool_index, threshold, + extack); +} + +static int dsa_devlink_sb_occ_snapshot(struct devlink *dl, + unsigned int sb_index) +{ + struct dsa_switch *ds = dsa_devlink_to_ds(dl); + + if (!ds->ops->devlink_sb_occ_snapshot) + return -EOPNOTSUPP; + + return ds->ops->devlink_sb_occ_snapshot(ds, sb_index); +} + +static int dsa_devlink_sb_occ_max_clear(struct devlink *dl, + unsigned int sb_index) +{ + struct dsa_switch *ds = dsa_devlink_to_ds(dl); + + if (!ds->ops->devlink_sb_occ_max_clear) + return -EOPNOTSUPP; + + return ds->ops->devlink_sb_occ_max_clear(ds, sb_index); +} + +static int dsa_devlink_sb_occ_port_pool_get(struct devlink_port *dlp, + unsigned int sb_index, + u16 pool_index, u32 *p_cur, + u32 *p_max) +{ + struct dsa_switch *ds = dsa_devlink_port_to_ds(dlp); + int port = dsa_devlink_port_to_port(dlp); + + if (!ds->ops->devlink_sb_occ_port_pool_get) + return -EOPNOTSUPP; + + return ds->ops->devlink_sb_occ_port_pool_get(ds, port, sb_index, + pool_index, p_cur, p_max); +} + +static int +dsa_devlink_sb_occ_tc_port_bind_get(struct devlink_port *dlp, + unsigned int sb_index, u16 tc_index, + enum devlink_sb_pool_type pool_type, + u32 *p_cur, u32 *p_max) +{ + struct dsa_switch *ds = dsa_devlink_port_to_ds(dlp); + int port = dsa_devlink_port_to_port(dlp); + + if (!ds->ops->devlink_sb_occ_tc_port_bind_get) + return -EOPNOTSUPP; + + return ds->ops->devlink_sb_occ_tc_port_bind_get(ds, port, + sb_index, tc_index, + pool_type, p_cur, + p_max); +} + static const struct devlink_ops dsa_devlink_ops = { - .info_get = dsa_devlink_info_get, + .info_get = dsa_devlink_info_get, + .sb_pool_get = dsa_devlink_sb_pool_get, + .sb_pool_set = dsa_devlink_sb_pool_set, + .sb_port_pool_get = dsa_devlink_sb_port_pool_get, + .sb_port_pool_set = dsa_devlink_sb_port_pool_set, + .sb_tc_pool_bind_get = dsa_devlink_sb_tc_pool_bind_get, + .sb_tc_pool_bind_set = dsa_devlink_sb_tc_pool_bind_set, + .sb_occ_snapshot = dsa_devlink_sb_occ_snapshot, + .sb_occ_max_clear = dsa_devlink_sb_occ_max_clear, + .sb_occ_port_pool_get = dsa_devlink_sb_occ_port_pool_get, + .sb_occ_tc_port_bind_get = dsa_devlink_sb_occ_tc_port_bind_get, }; static int dsa_switch_setup(struct dsa_switch *ds) @@ -452,6 +712,8 @@ static int dsa_switch_setup(struct dsa_switch *ds) if (err) goto unregister_devlink_ports; + ds->configure_vlan_while_not_filtering = true; + err = ds->ops->setup(ds); if (err < 0) goto unregister_notifier; @@ -585,6 +847,32 @@ static void dsa_tree_teardown_master(struct dsa_switch_tree *dst) dsa_master_teardown(dp->master); } +static int dsa_tree_setup_lags(struct dsa_switch_tree *dst) +{ + unsigned int len = 0; + struct dsa_port *dp; + + list_for_each_entry(dp, &dst->ports, list) { + if (dp->ds->num_lag_ids > len) + len = dp->ds->num_lag_ids; + } + + if (!len) + return 0; + + dst->lags = kcalloc(len, sizeof(*dst->lags), GFP_KERNEL); + if (!dst->lags) + return -ENOMEM; + + dst->lags_len = len; + return 0; +} + +static void dsa_tree_teardown_lags(struct dsa_switch_tree *dst) +{ + kfree(dst->lags); +} + static int dsa_tree_setup(struct dsa_switch_tree *dst) { bool complete; @@ -612,12 +900,18 @@ static int dsa_tree_setup(struct dsa_switch_tree *dst) if (err) goto teardown_switches; + err = dsa_tree_setup_lags(dst); + if (err) + goto teardown_master; + dst->setup = true; pr_info("DSA: tree %d setup\n", dst->index); return 0; +teardown_master: + dsa_tree_teardown_master(dst); teardown_switches: dsa_tree_teardown_switches(dst); teardown_default_cpu: @@ -633,6 +927,8 @@ static void dsa_tree_teardown(struct dsa_switch_tree *dst) if (!dst->setup) return; + dsa_tree_teardown_lags(dst); + dsa_tree_teardown_master(dst); dsa_tree_teardown_switches(dst); @@ -649,6 +945,57 @@ static void dsa_tree_teardown(struct dsa_switch_tree *dst) dst->setup = false; } +/* Since the dsa/tagging sysfs device attribute is per master, the assumption + * is that all DSA switches within a tree share the same tagger, otherwise + * they would have formed disjoint trees (different "dsa,member" values). + */ +int dsa_tree_change_tag_proto(struct dsa_switch_tree *dst, + struct net_device *master, + const struct dsa_device_ops *tag_ops, + const struct dsa_device_ops *old_tag_ops) +{ + struct dsa_notifier_tag_proto_info info; + struct dsa_port *dp; + int err = -EBUSY; + + if (!rtnl_trylock()) + return restart_syscall(); + + /* At the moment we don't allow changing the tag protocol under + * traffic. The rtnl_mutex also happens to serialize concurrent + * attempts to change the tagging protocol. If we ever lift the IFF_UP + * restriction, there needs to be another mutex which serializes this. + */ + if (master->flags & IFF_UP) + goto out_unlock; + + list_for_each_entry(dp, &dst->ports, list) { + if (!dsa_is_user_port(dp->ds, dp->index)) + continue; + + if (dp->slave->flags & IFF_UP) + goto out_unlock; + } + + info.tag_ops = tag_ops; + err = dsa_tree_notify(dst, DSA_NOTIFIER_TAG_PROTO, &info); + if (err) + goto out_unwind_tagger; + + dst->tag_ops = tag_ops; + + rtnl_unlock(); + + return 0; + +out_unwind_tagger: + info.tag_ops = old_tag_ops; + dsa_tree_notify(dst, DSA_NOTIFIER_TAG_PROTO, &info); +out_unlock: + rtnl_unlock(); + return err; +} + static struct dsa_port *dsa_port_touch(struct dsa_switch *ds, int index) { struct dsa_switch_tree *dst = ds->dst; @@ -719,24 +1066,33 @@ static int dsa_port_parse_cpu(struct dsa_port *dp, struct net_device *master) { struct dsa_switch *ds = dp->ds; struct dsa_switch_tree *dst = ds->dst; - const struct dsa_device_ops *tag_ops; enum dsa_tag_protocol tag_protocol; tag_protocol = dsa_get_tag_protocol(dp, master); - tag_ops = dsa_tag_driver_get(tag_protocol); - if (IS_ERR(tag_ops)) { - if (PTR_ERR(tag_ops) == -ENOPROTOOPT) - return -EPROBE_DEFER; - dev_warn(ds->dev, "No tagger for this switch\n"); - dp->master = NULL; - return PTR_ERR(tag_ops); + if (dst->tag_ops) { + if (dst->tag_ops->proto != tag_protocol) { + dev_err(ds->dev, + "A DSA switch tree can have only one tagging protocol\n"); + return -EINVAL; + } + /* In the case of multiple CPU ports per switch, the tagging + * protocol is still reference-counted only per switch tree, so + * nothing to do here. + */ + } else { + dst->tag_ops = dsa_tag_driver_get(tag_protocol); + if (IS_ERR(dst->tag_ops)) { + if (PTR_ERR(dst->tag_ops) == -ENOPROTOOPT) + return -EPROBE_DEFER; + dev_warn(ds->dev, "No tagger for this switch\n"); + dp->master = NULL; + return PTR_ERR(dst->tag_ops); + } } dp->master = master; dp->type = DSA_PORT_TYPE_CPU; - dp->filter = tag_ops->filter; - dp->rcv = tag_ops->rcv; - dp->tag_ops = tag_ops; + dsa_port_set_tag_protocol(dp, dst->tag_ops); dp->dst = dst; return 0; @@ -790,6 +1146,8 @@ static int dsa_switch_parse_ports_of(struct dsa_switch *ds, goto out_put_node; if (reg >= ds->num_ports) { + dev_err(ds->dev, "port %pOF index %u exceeds num_ports (%zu)\n", + port, reg, ds->num_ports); err = -EINVAL; goto out_put_node; } diff --git a/net/dsa/dsa_priv.h b/net/dsa/dsa_priv.h index 7c96aae9062c..2eeaa42f2e08 100644 --- a/net/dsa/dsa_priv.h +++ b/net/dsa/dsa_priv.h @@ -20,16 +20,25 @@ enum { DSA_NOTIFIER_BRIDGE_LEAVE, DSA_NOTIFIER_FDB_ADD, DSA_NOTIFIER_FDB_DEL, + DSA_NOTIFIER_HSR_JOIN, + DSA_NOTIFIER_HSR_LEAVE, + DSA_NOTIFIER_LAG_CHANGE, + DSA_NOTIFIER_LAG_JOIN, + DSA_NOTIFIER_LAG_LEAVE, DSA_NOTIFIER_MDB_ADD, DSA_NOTIFIER_MDB_DEL, DSA_NOTIFIER_VLAN_ADD, DSA_NOTIFIER_VLAN_DEL, DSA_NOTIFIER_MTU, + DSA_NOTIFIER_TAG_PROTO, + DSA_NOTIFIER_MRP_ADD, + DSA_NOTIFIER_MRP_DEL, + DSA_NOTIFIER_MRP_ADD_RING_ROLE, + DSA_NOTIFIER_MRP_DEL_RING_ROLE, }; /* DSA_NOTIFIER_AGEING_TIME */ struct dsa_notifier_ageing_time_info { - struct switchdev_trans *trans; unsigned int ageing_time; }; @@ -52,17 +61,25 @@ struct dsa_notifier_fdb_info { /* DSA_NOTIFIER_MDB_* */ struct dsa_notifier_mdb_info { const struct switchdev_obj_port_mdb *mdb; - struct switchdev_trans *trans; int sw_index; int port; }; +/* DSA_NOTIFIER_LAG_* */ +struct dsa_notifier_lag_info { + struct net_device *lag; + int sw_index; + int port; + + struct netdev_lag_upper_info *info; +}; + /* DSA_NOTIFIER_VLAN_* */ struct dsa_notifier_vlan_info { const struct switchdev_obj_port_vlan *vlan; - struct switchdev_trans *trans; int sw_index; int port; + struct netlink_ext_ack *extack; }; /* DSA_NOTIFIER_MTU */ @@ -73,6 +90,44 @@ struct dsa_notifier_mtu_info { int mtu; }; +/* DSA_NOTIFIER_TAG_PROTO_* */ +struct dsa_notifier_tag_proto_info { + const struct dsa_device_ops *tag_ops; +}; + +/* DSA_NOTIFIER_MRP_* */ +struct dsa_notifier_mrp_info { + const struct switchdev_obj_mrp *mrp; + int sw_index; + int port; +}; + +/* DSA_NOTIFIER_MRP_* */ +struct dsa_notifier_mrp_ring_role_info { + const struct switchdev_obj_ring_role_mrp *mrp; + int sw_index; + int port; +}; + +struct dsa_switchdev_event_work { + struct dsa_switch *ds; + int port; + struct work_struct work; + unsigned long event; + /* Specific for SWITCHDEV_FDB_ADD_TO_DEVICE and + * SWITCHDEV_FDB_DEL_TO_DEVICE + */ + unsigned char addr[ETH_ALEN]; + u16 vid; +}; + +/* DSA_NOTIFIER_HSR_* */ +struct dsa_notifier_hsr_info { + struct net_device *hsr; + int sw_index; + int port; +}; + struct dsa_slave_priv { /* Copy of CPU port xmit for faster access in slave transmit hot path */ struct sk_buff * (*xmit)(struct sk_buff *skb, @@ -94,19 +149,11 @@ struct dsa_slave_priv { /* dsa.c */ const struct dsa_device_ops *dsa_tag_driver_get(int tag_protocol); void dsa_tag_driver_put(const struct dsa_device_ops *ops); +const struct dsa_device_ops *dsa_find_tagger_by_name(const char *buf); bool dsa_schedule_work(struct work_struct *work); const char *dsa_tag_protocol_to_str(const struct dsa_device_ops *ops); -int dsa_legacy_fdb_add(struct ndmsg *ndm, struct nlattr *tb[], - struct net_device *dev, - const unsigned char *addr, u16 vid, - u16 flags, - struct netlink_ext_ack *extack); -int dsa_legacy_fdb_del(struct ndmsg *ndm, struct nlattr *tb[], - struct net_device *dev, - const unsigned char *addr, u16 vid); - /* master.c */ int dsa_master_setup(struct net_device *dev, struct dsa_port *cpu_dp); void dsa_master_teardown(struct net_device *dev); @@ -127,19 +174,24 @@ static inline struct net_device *dsa_master_find_slave(struct net_device *dev, } /* port.c */ -int dsa_port_set_state(struct dsa_port *dp, u8 state, - struct switchdev_trans *trans); +void dsa_port_set_tag_protocol(struct dsa_port *cpu_dp, + const struct dsa_device_ops *tag_ops); +int dsa_port_set_state(struct dsa_port *dp, u8 state); int dsa_port_enable_rt(struct dsa_port *dp, struct phy_device *phy); int dsa_port_enable(struct dsa_port *dp, struct phy_device *phy); void dsa_port_disable_rt(struct dsa_port *dp); void dsa_port_disable(struct dsa_port *dp); int dsa_port_bridge_join(struct dsa_port *dp, struct net_device *br); void dsa_port_bridge_leave(struct dsa_port *dp, struct net_device *br); +int dsa_port_lag_change(struct dsa_port *dp, + struct netdev_lag_lower_state_info *linfo); +int dsa_port_lag_join(struct dsa_port *dp, struct net_device *lag_dev, + struct netdev_lag_upper_info *uinfo); +void dsa_port_lag_leave(struct dsa_port *dp, struct net_device *lag_dev); int dsa_port_vlan_filtering(struct dsa_port *dp, bool vlan_filtering, - struct switchdev_trans *trans); + struct netlink_ext_ack *extack); bool dsa_port_skip_vlan_configuration(struct dsa_port *dp); -int dsa_port_ageing_time(struct dsa_port *dp, clock_t ageing_clock, - struct switchdev_trans *trans); +int dsa_port_ageing_time(struct dsa_port *dp, clock_t ageing_clock); int dsa_port_mtu_change(struct dsa_port *dp, int new_mtu, bool propagate_upstream); int dsa_port_fdb_add(struct dsa_port *dp, const unsigned char *addr, @@ -148,35 +200,84 @@ int dsa_port_fdb_del(struct dsa_port *dp, const unsigned char *addr, u16 vid); int dsa_port_fdb_dump(struct dsa_port *dp, dsa_fdb_dump_cb_t *cb, void *data); int dsa_port_mdb_add(const struct dsa_port *dp, - const struct switchdev_obj_port_mdb *mdb, - struct switchdev_trans *trans); + const struct switchdev_obj_port_mdb *mdb); int dsa_port_mdb_del(const struct dsa_port *dp, const struct switchdev_obj_port_mdb *mdb); -int dsa_port_pre_bridge_flags(const struct dsa_port *dp, unsigned long flags, - struct switchdev_trans *trans); -int dsa_port_bridge_flags(const struct dsa_port *dp, unsigned long flags, - struct switchdev_trans *trans); +int dsa_port_pre_bridge_flags(const struct dsa_port *dp, + struct switchdev_brport_flags flags, + struct netlink_ext_ack *extack); +int dsa_port_bridge_flags(const struct dsa_port *dp, + struct switchdev_brport_flags flags, + struct netlink_ext_ack *extack); int dsa_port_mrouter(struct dsa_port *dp, bool mrouter, - struct switchdev_trans *trans); + struct netlink_ext_ack *extack); int dsa_port_vlan_add(struct dsa_port *dp, const struct switchdev_obj_port_vlan *vlan, - struct switchdev_trans *trans); + struct netlink_ext_ack *extack); int dsa_port_vlan_del(struct dsa_port *dp, const struct switchdev_obj_port_vlan *vlan); +int dsa_port_mrp_add(const struct dsa_port *dp, + const struct switchdev_obj_mrp *mrp); +int dsa_port_mrp_del(const struct dsa_port *dp, + const struct switchdev_obj_mrp *mrp); +int dsa_port_mrp_add_ring_role(const struct dsa_port *dp, + const struct switchdev_obj_ring_role_mrp *mrp); +int dsa_port_mrp_del_ring_role(const struct dsa_port *dp, + const struct switchdev_obj_ring_role_mrp *mrp); int dsa_port_link_register_of(struct dsa_port *dp); void dsa_port_link_unregister_of(struct dsa_port *dp); +int dsa_port_hsr_join(struct dsa_port *dp, struct net_device *hsr); +void dsa_port_hsr_leave(struct dsa_port *dp, struct net_device *hsr); extern const struct phylink_mac_ops dsa_port_phylink_mac_ops; +static inline bool dsa_port_offloads_netdev(struct dsa_port *dp, + struct net_device *dev) +{ + /* Switchdev offloading can be configured on: */ + + if (dev == dp->slave) + /* DSA ports directly connected to a bridge, and event + * was emitted for the ports themselves. + */ + return true; + + if (dp->bridge_dev == dev) + /* DSA ports connected to a bridge, and event was emitted + * for the bridge. + */ + return true; + + if (dp->lag_dev == dev) + /* DSA ports connected to a bridge via a LAG */ + return true; + + return false; +} + +/* Returns true if any port of this tree offloads the given net_device */ +static inline bool dsa_tree_offloads_netdev(struct dsa_switch_tree *dst, + struct net_device *dev) +{ + struct dsa_port *dp; + + list_for_each_entry(dp, &dst->ports, list) + if (dsa_port_offloads_netdev(dp, dev)) + return true; + + return false; +} + /* slave.c */ extern const struct dsa_device_ops notag_netdev_ops; void dsa_slave_mii_bus_init(struct dsa_switch *ds); int dsa_slave_create(struct dsa_port *dp); void dsa_slave_destroy(struct net_device *slave_dev); -bool dsa_slave_dev_check(const struct net_device *dev); int dsa_slave_suspend(struct net_device *slave_dev); int dsa_slave_resume(struct net_device *slave_dev); int dsa_slave_register_notifier(void); void dsa_slave_unregister_notifier(void); +void dsa_slave_setup_tagger(struct net_device *slave); +int dsa_slave_change_mtu(struct net_device *dev, int new_mtu); static inline struct dsa_port *dsa_slave_to_port(const struct net_device *dev) { @@ -257,6 +358,15 @@ int dsa_switch_register_notifier(struct dsa_switch *ds); void dsa_switch_unregister_notifier(struct dsa_switch *ds); /* dsa2.c */ +void dsa_lag_map(struct dsa_switch_tree *dst, struct net_device *lag); +void dsa_lag_unmap(struct dsa_switch_tree *dst, struct net_device *lag); +int dsa_tree_notify(struct dsa_switch_tree *dst, unsigned long e, void *v); +int dsa_broadcast(unsigned long e, void *v); +int dsa_tree_change_tag_proto(struct dsa_switch_tree *dst, + struct net_device *master, + const struct dsa_device_ops *tag_ops, + const struct dsa_device_ops *old_tag_ops); + extern struct list_head dsa_tree_list; #endif diff --git a/net/dsa/master.c b/net/dsa/master.c index cb3a5cf99b25..052a977914a6 100644 --- a/net/dsa/master.c +++ b/net/dsa/master.c @@ -280,7 +280,44 @@ static ssize_t tagging_show(struct device *d, struct device_attribute *attr, return sprintf(buf, "%s\n", dsa_tag_protocol_to_str(cpu_dp->tag_ops)); } -static DEVICE_ATTR_RO(tagging); + +static ssize_t tagging_store(struct device *d, struct device_attribute *attr, + const char *buf, size_t count) +{ + const struct dsa_device_ops *new_tag_ops, *old_tag_ops; + struct net_device *dev = to_net_dev(d); + struct dsa_port *cpu_dp = dev->dsa_ptr; + int err; + + old_tag_ops = cpu_dp->tag_ops; + new_tag_ops = dsa_find_tagger_by_name(buf); + /* Bad tagger name, or module is not loaded? */ + if (IS_ERR(new_tag_ops)) + return PTR_ERR(new_tag_ops); + + if (new_tag_ops == old_tag_ops) + /* Drop the temporarily held duplicate reference, since + * the DSA switch tree uses this tagger. + */ + goto out; + + err = dsa_tree_change_tag_proto(cpu_dp->ds->dst, dev, new_tag_ops, + old_tag_ops); + if (err) { + /* On failure the old tagger is restored, so we don't need the + * driver for the new one. + */ + dsa_tag_driver_put(new_tag_ops); + return err; + } + + /* On success we no longer need the module for the old tagging protocol + */ +out: + dsa_tag_driver_put(old_tag_ops); + return count; +} +static DEVICE_ATTR_RW(tagging); static struct attribute *dsa_slave_attrs[] = { &dev_attr_tagging.attr, diff --git a/net/dsa/port.c b/net/dsa/port.c index 73569c9af3cc..c9c6d7ab3f47 100644 --- a/net/dsa/port.c +++ b/net/dsa/port.c @@ -13,44 +13,32 @@ #include "dsa_priv.h" -static int dsa_broadcast(unsigned long e, void *v) -{ - struct dsa_switch_tree *dst; - int err = 0; - - list_for_each_entry(dst, &dsa_tree_list, list) { - struct raw_notifier_head *nh = &dst->nh; - - err = raw_notifier_call_chain(nh, e, v); - err = notifier_to_errno(err); - if (err) - break; - } - - return err; -} - +/** + * dsa_port_notify - Notify the switching fabric of changes to a port + * @dp: port on which change occurred + * @e: event, must be of type DSA_NOTIFIER_* + * @v: event-specific value. + * + * Notify all switches in the DSA tree that this port's switch belongs to, + * including this switch itself, of an event. Allows the other switches to + * reconfigure themselves for cross-chip operations. Can also be used to + * reconfigure ports without net_devices (CPU ports, DSA links) whenever + * a user port's state changes. + */ static int dsa_port_notify(const struct dsa_port *dp, unsigned long e, void *v) { - struct raw_notifier_head *nh = &dp->ds->dst->nh; - int err; - - err = raw_notifier_call_chain(nh, e, v); - - return notifier_to_errno(err); + return dsa_tree_notify(dp->ds->dst, e, v); } -int dsa_port_set_state(struct dsa_port *dp, u8 state, - struct switchdev_trans *trans) +int dsa_port_set_state(struct dsa_port *dp, u8 state) { struct dsa_switch *ds = dp->ds; int port = dp->index; - if (switchdev_trans_ph_prepare(trans)) - return ds->ops->port_stp_state_set ? 0 : -EOPNOTSUPP; + if (!ds->ops->port_stp_state_set) + return -EOPNOTSUPP; - if (ds->ops->port_stp_state_set) - ds->ops->port_stp_state_set(ds, port, state); + ds->ops->port_stp_state_set(ds, port, state); if (ds->ops->port_fast_age) { /* Fast age FDB entries or flush appropriate forwarding database @@ -75,7 +63,7 @@ static void dsa_port_set_state_now(struct dsa_port *dp, u8 state) { int err; - err = dsa_port_set_state(dp, state, NULL); + err = dsa_port_set_state(dp, state); if (err) pr_err("DSA: failed to set STP state %u (%d)\n", state, err); } @@ -134,6 +122,28 @@ void dsa_port_disable(struct dsa_port *dp) rtnl_unlock(); } +static void dsa_port_change_brport_flags(struct dsa_port *dp, + bool bridge_offload) +{ + struct switchdev_brport_flags flags; + int flag; + + flags.mask = BR_LEARNING | BR_FLOOD | BR_MCAST_FLOOD | BR_BCAST_FLOOD; + if (bridge_offload) + flags.val = flags.mask; + else + flags.val = flags.mask & ~BR_LEARNING; + + for_each_set_bit(flag, &flags.mask, 32) { + struct switchdev_brport_flags tmp; + + tmp.val = flags.val & BIT(flag); + tmp.mask = BIT(flag); + + dsa_port_bridge_flags(dp, tmp, NULL); + } +} + int dsa_port_bridge_join(struct dsa_port *dp, struct net_device *br) { struct dsa_notifier_bridge_info info = { @@ -144,10 +154,10 @@ int dsa_port_bridge_join(struct dsa_port *dp, struct net_device *br) }; int err; - /* Set the flooding mode before joining the port in the switch */ - err = dsa_port_bridge_flags(dp, BR_FLOOD | BR_MCAST_FLOOD, NULL); - if (err) - return err; + /* Notify the port driver to set its configurable flags in a way that + * matches the initial settings of a bridge port. + */ + dsa_port_change_brport_flags(dp, true); /* Here the interface is already bridged. Reflect the current * configuration so that drivers can program their chips accordingly. @@ -158,7 +168,7 @@ int dsa_port_bridge_join(struct dsa_port *dp, struct net_device *br) /* The bridging is rolled back on error */ if (err) { - dsa_port_bridge_flags(dp, 0, NULL); + dsa_port_change_brport_flags(dp, false); dp->bridge_dev = NULL; } @@ -184,8 +194,18 @@ void dsa_port_bridge_leave(struct dsa_port *dp, struct net_device *br) if (err) pr_err("DSA: failed to notify DSA_NOTIFIER_BRIDGE_LEAVE\n"); - /* Port is leaving the bridge, disable flooding */ - dsa_port_bridge_flags(dp, 0, NULL); + /* Configure the port for standalone mode (no address learning, + * flood everything). + * The bridge only emits SWITCHDEV_ATTR_ID_PORT_BRIDGE_FLAGS events + * when the user requests it through netlink or sysfs, but not + * automatically at port join or leave, so we need to handle resetting + * the brport flags ourselves. But we even prefer it that way, because + * otherwise, some setups might never get the notification they need, + * for example, when a port leaves a LAG that offloads the bridge, + * it becomes standalone, but as far as the bridge is concerned, no + * port ever left. + */ + dsa_port_change_brport_flags(dp, false); /* Port left the bridge, put in BR_STATE_DISABLED by the bridge layer, * so allow it to be in BR_STATE_FORWARDING to be kept functional @@ -193,9 +213,89 @@ void dsa_port_bridge_leave(struct dsa_port *dp, struct net_device *br) dsa_port_set_state_now(dp, BR_STATE_FORWARDING); } +int dsa_port_lag_change(struct dsa_port *dp, + struct netdev_lag_lower_state_info *linfo) +{ + struct dsa_notifier_lag_info info = { + .sw_index = dp->ds->index, + .port = dp->index, + }; + bool tx_enabled; + + if (!dp->lag_dev) + return 0; + + /* On statically configured aggregates (e.g. loadbalance + * without LACP) ports will always be tx_enabled, even if the + * link is down. Thus we require both link_up and tx_enabled + * in order to include it in the tx set. + */ + tx_enabled = linfo->link_up && linfo->tx_enabled; + + if (tx_enabled == dp->lag_tx_enabled) + return 0; + + dp->lag_tx_enabled = tx_enabled; + + return dsa_port_notify(dp, DSA_NOTIFIER_LAG_CHANGE, &info); +} + +int dsa_port_lag_join(struct dsa_port *dp, struct net_device *lag, + struct netdev_lag_upper_info *uinfo) +{ + struct dsa_notifier_lag_info info = { + .sw_index = dp->ds->index, + .port = dp->index, + .lag = lag, + .info = uinfo, + }; + int err; + + dsa_lag_map(dp->ds->dst, lag); + dp->lag_dev = lag; + + err = dsa_port_notify(dp, DSA_NOTIFIER_LAG_JOIN, &info); + if (err) { + dp->lag_dev = NULL; + dsa_lag_unmap(dp->ds->dst, lag); + } + + return err; +} + +void dsa_port_lag_leave(struct dsa_port *dp, struct net_device *lag) +{ + struct dsa_notifier_lag_info info = { + .sw_index = dp->ds->index, + .port = dp->index, + .lag = lag, + }; + int err; + + if (!dp->lag_dev) + return; + + /* Port might have been part of a LAG that in turn was + * attached to a bridge. + */ + if (dp->bridge_dev) + dsa_port_bridge_leave(dp, dp->bridge_dev); + + dp->lag_tx_enabled = false; + dp->lag_dev = NULL; + + err = dsa_port_notify(dp, DSA_NOTIFIER_LAG_LEAVE, &info); + if (err) + pr_err("DSA: failed to notify DSA_NOTIFIER_LAG_LEAVE: %d\n", + err); + + dsa_lag_unmap(dp->ds->dst, lag); +} + /* Must be called under rcu_read_lock() */ static bool dsa_port_can_apply_vlan_filtering(struct dsa_port *dp, - bool vlan_filtering) + bool vlan_filtering, + struct netlink_ext_ack *extack) { struct dsa_switch *ds = dp->ds; int err, i; @@ -225,8 +325,8 @@ static bool dsa_port_can_apply_vlan_filtering(struct dsa_port *dp, */ err = br_vlan_get_info(br, vid, &br_info); if (err == 0) { - dev_err(ds->dev, "Must remove upper %s first\n", - upper_dev->name); + NL_SET_ERR_MSG_MOD(extack, + "Must first remove VLAN uppers having VIDs also present in bridge"); return false; } } @@ -252,7 +352,8 @@ static bool dsa_port_can_apply_vlan_filtering(struct dsa_port *dp, if (other_bridge == dp->bridge_dev) continue; if (br_vlan_enabled(other_bridge) != vlan_filtering) { - dev_err(ds->dev, "VLAN filtering is a global setting\n"); + NL_SET_ERR_MSG_MOD(extack, + "VLAN filtering is a global setting"); return false; } } @@ -260,42 +361,37 @@ static bool dsa_port_can_apply_vlan_filtering(struct dsa_port *dp, } int dsa_port_vlan_filtering(struct dsa_port *dp, bool vlan_filtering, - struct switchdev_trans *trans) + struct netlink_ext_ack *extack) { struct dsa_switch *ds = dp->ds; + bool apply; int err; - if (switchdev_trans_ph_prepare(trans)) { - bool apply; - - if (!ds->ops->port_vlan_filtering) - return -EOPNOTSUPP; + if (!ds->ops->port_vlan_filtering) + return -EOPNOTSUPP; - /* We are called from dsa_slave_switchdev_blocking_event(), - * which is not under rcu_read_lock(), unlike - * dsa_slave_switchdev_event(). - */ - rcu_read_lock(); - apply = dsa_port_can_apply_vlan_filtering(dp, vlan_filtering); - rcu_read_unlock(); - if (!apply) - return -EINVAL; - } + /* We are called from dsa_slave_switchdev_blocking_event(), + * which is not under rcu_read_lock(), unlike + * dsa_slave_switchdev_event(). + */ + rcu_read_lock(); + apply = dsa_port_can_apply_vlan_filtering(dp, vlan_filtering, extack); + rcu_read_unlock(); + if (!apply) + return -EINVAL; if (dsa_port_is_vlan_filtering(dp) == vlan_filtering) return 0; err = ds->ops->port_vlan_filtering(ds, dp->index, vlan_filtering, - trans); + extack); if (err) return err; - if (switchdev_trans_ph_commit(trans)) { - if (ds->vlan_filtering_is_global) - ds->vlan_filtering = vlan_filtering; - else - dp->vlan_filtering = vlan_filtering; - } + if (ds->vlan_filtering_is_global) + ds->vlan_filtering = vlan_filtering; + else + dp->vlan_filtering = vlan_filtering; return 0; } @@ -314,63 +410,57 @@ bool dsa_port_skip_vlan_configuration(struct dsa_port *dp) !br_vlan_enabled(dp->bridge_dev)); } -int dsa_port_ageing_time(struct dsa_port *dp, clock_t ageing_clock, - struct switchdev_trans *trans) +int dsa_port_ageing_time(struct dsa_port *dp, clock_t ageing_clock) { unsigned long ageing_jiffies = clock_t_to_jiffies(ageing_clock); unsigned int ageing_time = jiffies_to_msecs(ageing_jiffies); - struct dsa_notifier_ageing_time_info info = { - .ageing_time = ageing_time, - .trans = trans, - }; + struct dsa_notifier_ageing_time_info info; + int err; + + info.ageing_time = ageing_time; - if (switchdev_trans_ph_prepare(trans)) - return dsa_port_notify(dp, DSA_NOTIFIER_AGEING_TIME, &info); + err = dsa_port_notify(dp, DSA_NOTIFIER_AGEING_TIME, &info); + if (err) + return err; dp->ageing_time = ageing_time; - return dsa_port_notify(dp, DSA_NOTIFIER_AGEING_TIME, &info); + return 0; } -int dsa_port_pre_bridge_flags(const struct dsa_port *dp, unsigned long flags, - struct switchdev_trans *trans) +int dsa_port_pre_bridge_flags(const struct dsa_port *dp, + struct switchdev_brport_flags flags, + struct netlink_ext_ack *extack) { struct dsa_switch *ds = dp->ds; - if (!ds->ops->port_egress_floods || - (flags & ~(BR_FLOOD | BR_MCAST_FLOOD))) + if (!ds->ops->port_pre_bridge_flags) return -EINVAL; - return 0; + return ds->ops->port_pre_bridge_flags(ds, dp->index, flags, extack); } -int dsa_port_bridge_flags(const struct dsa_port *dp, unsigned long flags, - struct switchdev_trans *trans) +int dsa_port_bridge_flags(const struct dsa_port *dp, + struct switchdev_brport_flags flags, + struct netlink_ext_ack *extack) { struct dsa_switch *ds = dp->ds; - int port = dp->index; - int err = 0; - if (switchdev_trans_ph_prepare(trans)) - return 0; - - if (ds->ops->port_egress_floods) - err = ds->ops->port_egress_floods(ds, port, flags & BR_FLOOD, - flags & BR_MCAST_FLOOD); + if (!ds->ops->port_bridge_flags) + return -EINVAL; - return err; + return ds->ops->port_bridge_flags(ds, dp->index, flags, extack); } int dsa_port_mrouter(struct dsa_port *dp, bool mrouter, - struct switchdev_trans *trans) + struct netlink_ext_ack *extack) { struct dsa_switch *ds = dp->ds; - int port = dp->index; - if (switchdev_trans_ph_prepare(trans)) - return ds->ops->port_egress_floods ? 0 : -EOPNOTSUPP; + if (!ds->ops->port_set_mrouter) + return -EOPNOTSUPP; - return ds->ops->port_egress_floods(ds, port, true, mrouter); + return ds->ops->port_set_mrouter(ds, dp->index, mrouter, extack); } int dsa_port_mtu_change(struct dsa_port *dp, int new_mtu, @@ -425,13 +515,11 @@ int dsa_port_fdb_dump(struct dsa_port *dp, dsa_fdb_dump_cb_t *cb, void *data) } int dsa_port_mdb_add(const struct dsa_port *dp, - const struct switchdev_obj_port_mdb *mdb, - struct switchdev_trans *trans) + const struct switchdev_obj_port_mdb *mdb) { struct dsa_notifier_mdb_info info = { .sw_index = dp->ds->index, .port = dp->index, - .trans = trans, .mdb = mdb, }; @@ -452,13 +540,13 @@ int dsa_port_mdb_del(const struct dsa_port *dp, int dsa_port_vlan_add(struct dsa_port *dp, const struct switchdev_obj_port_vlan *vlan, - struct switchdev_trans *trans) + struct netlink_ext_ack *extack) { struct dsa_notifier_vlan_info info = { .sw_index = dp->ds->index, .port = dp->index, - .trans = trans, .vlan = vlan, + .extack = extack, }; return dsa_port_notify(dp, DSA_NOTIFIER_VLAN_ADD, &info); @@ -476,6 +564,62 @@ int dsa_port_vlan_del(struct dsa_port *dp, return dsa_port_notify(dp, DSA_NOTIFIER_VLAN_DEL, &info); } +int dsa_port_mrp_add(const struct dsa_port *dp, + const struct switchdev_obj_mrp *mrp) +{ + struct dsa_notifier_mrp_info info = { + .sw_index = dp->ds->index, + .port = dp->index, + .mrp = mrp, + }; + + return dsa_port_notify(dp, DSA_NOTIFIER_MRP_ADD, &info); +} + +int dsa_port_mrp_del(const struct dsa_port *dp, + const struct switchdev_obj_mrp *mrp) +{ + struct dsa_notifier_mrp_info info = { + .sw_index = dp->ds->index, + .port = dp->index, + .mrp = mrp, + }; + + return dsa_port_notify(dp, DSA_NOTIFIER_MRP_DEL, &info); +} + +int dsa_port_mrp_add_ring_role(const struct dsa_port *dp, + const struct switchdev_obj_ring_role_mrp *mrp) +{ + struct dsa_notifier_mrp_ring_role_info info = { + .sw_index = dp->ds->index, + .port = dp->index, + .mrp = mrp, + }; + + return dsa_port_notify(dp, DSA_NOTIFIER_MRP_ADD_RING_ROLE, &info); +} + +int dsa_port_mrp_del_ring_role(const struct dsa_port *dp, + const struct switchdev_obj_ring_role_mrp *mrp) +{ + struct dsa_notifier_mrp_ring_role_info info = { + .sw_index = dp->ds->index, + .port = dp->index, + .mrp = mrp, + }; + + return dsa_port_notify(dp, DSA_NOTIFIER_MRP_DEL_RING_ROLE, &info); +} + +void dsa_port_set_tag_protocol(struct dsa_port *cpu_dp, + const struct dsa_device_ops *tag_ops) +{ + cpu_dp->filter = tag_ops->filter; + cpu_dp->rcv = tag_ops->rcv; + cpu_dp->tag_ops = tag_ops; +} + static struct phy_device *dsa_port_get_phy_device(struct dsa_port *dp) { struct device_node *phy_dn; @@ -810,3 +954,37 @@ int dsa_port_get_phy_sset_count(struct dsa_port *dp) return ret; } EXPORT_SYMBOL_GPL(dsa_port_get_phy_sset_count); + +int dsa_port_hsr_join(struct dsa_port *dp, struct net_device *hsr) +{ + struct dsa_notifier_hsr_info info = { + .sw_index = dp->ds->index, + .port = dp->index, + .hsr = hsr, + }; + int err; + + dp->hsr_dev = hsr; + + err = dsa_port_notify(dp, DSA_NOTIFIER_HSR_JOIN, &info); + if (err) + dp->hsr_dev = NULL; + + return err; +} + +void dsa_port_hsr_leave(struct dsa_port *dp, struct net_device *hsr) +{ + struct dsa_notifier_hsr_info info = { + .sw_index = dp->ds->index, + .port = dp->index, + .hsr = hsr, + }; + int err; + + dp->hsr_dev = NULL; + + err = dsa_port_notify(dp, DSA_NOTIFIER_HSR_LEAVE, &info); + if (err) + pr_err("DSA: failed to notify DSA_NOTIFIER_HSR_LEAVE\n"); +} diff --git a/net/dsa/slave.c b/net/dsa/slave.c index 4a0498bf6c65..491e3761b5f4 100644 --- a/net/dsa/slave.c +++ b/net/dsa/slave.c @@ -17,6 +17,7 @@ #include <net/pkt_cls.h> #include <net/tc_act/tc_mirred.h> #include <linux/if_bridge.h> +#include <linux/if_hsr.h> #include <linux/netpoll.h> #include <linux/ptp_classify.h> @@ -68,8 +69,11 @@ static int dsa_slave_open(struct net_device *dev) struct dsa_port *dp = dsa_slave_to_port(dev); int err; - if (!(master->flags & IFF_UP)) - return -ENETDOWN; + err = dev_open(master, NULL); + if (err < 0) { + netdev_err(dev, "failed to open master %s\n", master->name); + goto out; + } if (!ether_addr_equal(dev->dev_addr, master->dev_addr)) { err = dev_uc_add(master, dev->dev_addr); @@ -269,31 +273,34 @@ static int dsa_slave_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) static int dsa_slave_port_attr_set(struct net_device *dev, const struct switchdev_attr *attr, - struct switchdev_trans *trans) + struct netlink_ext_ack *extack) { struct dsa_port *dp = dsa_slave_to_port(dev); int ret; + if (!dsa_port_offloads_netdev(dp, attr->orig_dev)) + return -EOPNOTSUPP; + switch (attr->id) { case SWITCHDEV_ATTR_ID_PORT_STP_STATE: - ret = dsa_port_set_state(dp, attr->u.stp_state, trans); + ret = dsa_port_set_state(dp, attr->u.stp_state); break; case SWITCHDEV_ATTR_ID_BRIDGE_VLAN_FILTERING: ret = dsa_port_vlan_filtering(dp, attr->u.vlan_filtering, - trans); + extack); break; case SWITCHDEV_ATTR_ID_BRIDGE_AGEING_TIME: - ret = dsa_port_ageing_time(dp, attr->u.ageing_time, trans); + ret = dsa_port_ageing_time(dp, attr->u.ageing_time); break; case SWITCHDEV_ATTR_ID_PORT_PRE_BRIDGE_FLAGS: ret = dsa_port_pre_bridge_flags(dp, attr->u.brport_flags, - trans); + extack); break; case SWITCHDEV_ATTR_ID_PORT_BRIDGE_FLAGS: - ret = dsa_port_bridge_flags(dp, attr->u.brport_flags, trans); + ret = dsa_port_bridge_flags(dp, attr->u.brport_flags, extack); break; case SWITCHDEV_ATTR_ID_BRIDGE_MROUTER: - ret = dsa_port_mrouter(dp->cpu_dp, attr->u.mrouter, trans); + ret = dsa_port_mrouter(dp->cpu_dp, attr->u.mrouter, extack); break; default: ret = -EOPNOTSUPP; @@ -318,7 +325,7 @@ dsa_slave_vlan_check_for_8021q_uppers(struct net_device *slave, continue; vid = vlan_dev_vlan_id(upper_dev); - if (vid >= vlan->vid_begin && vid <= vlan->vid_end) + if (vid == vlan->vid) return -EBUSY; } @@ -327,33 +334,38 @@ dsa_slave_vlan_check_for_8021q_uppers(struct net_device *slave, static int dsa_slave_vlan_add(struct net_device *dev, const struct switchdev_obj *obj, - struct switchdev_trans *trans) + struct netlink_ext_ack *extack) { struct net_device *master = dsa_slave_to_master(dev); struct dsa_port *dp = dsa_slave_to_port(dev); struct switchdev_obj_port_vlan vlan; - int vid, err; + int err; - if (obj->orig_dev != dev) + if (!dsa_port_offloads_netdev(dp, obj->orig_dev)) return -EOPNOTSUPP; - if (dsa_port_skip_vlan_configuration(dp)) + if (dsa_port_skip_vlan_configuration(dp)) { + NL_SET_ERR_MSG_MOD(extack, "skipping configuration of VLAN"); return 0; + } vlan = *SWITCHDEV_OBJ_PORT_VLAN(obj); /* Deny adding a bridge VLAN when there is already an 802.1Q upper with * the same VID. */ - if (trans->ph_prepare && br_vlan_enabled(dp->bridge_dev)) { + if (br_vlan_enabled(dp->bridge_dev)) { rcu_read_lock(); err = dsa_slave_vlan_check_for_8021q_uppers(dev, &vlan); rcu_read_unlock(); - if (err) + if (err) { + NL_SET_ERR_MSG_MOD(extack, + "Port already has a VLAN upper with this VID"); return err; + } } - err = dsa_port_vlan_add(dp, &vlan, trans); + err = dsa_port_vlan_add(dp, &vlan, extack); if (err) return err; @@ -363,47 +375,45 @@ static int dsa_slave_vlan_add(struct net_device *dev, */ vlan.flags &= ~BRIDGE_VLAN_INFO_PVID; - err = dsa_port_vlan_add(dp->cpu_dp, &vlan, trans); + err = dsa_port_vlan_add(dp->cpu_dp, &vlan, extack); if (err) return err; - for (vid = vlan.vid_begin; vid <= vlan.vid_end; vid++) { - err = vlan_vid_add(master, htons(ETH_P_8021Q), vid); - if (err) - return err; - } - - return 0; + return vlan_vid_add(master, htons(ETH_P_8021Q), vlan.vid); } static int dsa_slave_port_obj_add(struct net_device *dev, const struct switchdev_obj *obj, - struct switchdev_trans *trans, struct netlink_ext_ack *extack) { struct dsa_port *dp = dsa_slave_to_port(dev); int err; - /* For the prepare phase, ensure the full set of changes is feasable in - * one go in order to signal a failure properly. If an operation is not - * supported, return -EOPNOTSUPP. - */ - switch (obj->id) { case SWITCHDEV_OBJ_ID_PORT_MDB: - if (obj->orig_dev != dev) + if (!dsa_port_offloads_netdev(dp, obj->orig_dev)) return -EOPNOTSUPP; - err = dsa_port_mdb_add(dp, SWITCHDEV_OBJ_PORT_MDB(obj), trans); + err = dsa_port_mdb_add(dp, SWITCHDEV_OBJ_PORT_MDB(obj)); break; case SWITCHDEV_OBJ_ID_HOST_MDB: /* DSA can directly translate this to a normal MDB add, * but on the CPU port. */ - err = dsa_port_mdb_add(dp->cpu_dp, SWITCHDEV_OBJ_PORT_MDB(obj), - trans); + err = dsa_port_mdb_add(dp->cpu_dp, SWITCHDEV_OBJ_PORT_MDB(obj)); break; case SWITCHDEV_OBJ_ID_PORT_VLAN: - err = dsa_slave_vlan_add(dev, obj, trans); + err = dsa_slave_vlan_add(dev, obj, extack); + break; + case SWITCHDEV_OBJ_ID_MRP: + if (!dsa_port_offloads_netdev(dp, obj->orig_dev)) + return -EOPNOTSUPP; + err = dsa_port_mrp_add(dp, SWITCHDEV_OBJ_MRP(obj)); + break; + case SWITCHDEV_OBJ_ID_RING_ROLE_MRP: + if (!dsa_port_offloads_netdev(dp, obj->orig_dev)) + return -EOPNOTSUPP; + err = dsa_port_mrp_add_ring_role(dp, + SWITCHDEV_OBJ_RING_ROLE_MRP(obj)); break; default: err = -EOPNOTSUPP; @@ -419,9 +429,9 @@ static int dsa_slave_vlan_del(struct net_device *dev, struct net_device *master = dsa_slave_to_master(dev); struct dsa_port *dp = dsa_slave_to_port(dev); struct switchdev_obj_port_vlan *vlan; - int vid, err; + int err; - if (obj->orig_dev != dev) + if (!dsa_port_offloads_netdev(dp, obj->orig_dev)) return -EOPNOTSUPP; if (dsa_port_skip_vlan_configuration(dp)) @@ -436,8 +446,7 @@ static int dsa_slave_vlan_del(struct net_device *dev, if (err) return err; - for (vid = vlan->vid_begin; vid <= vlan->vid_end; vid++) - vlan_vid_del(master, htons(ETH_P_8021Q), vid); + vlan_vid_del(master, htons(ETH_P_8021Q), vlan->vid); return 0; } @@ -450,7 +459,7 @@ static int dsa_slave_port_obj_del(struct net_device *dev, switch (obj->id) { case SWITCHDEV_OBJ_ID_PORT_MDB: - if (obj->orig_dev != dev) + if (!dsa_port_offloads_netdev(dp, obj->orig_dev)) return -EOPNOTSUPP; err = dsa_port_mdb_del(dp, SWITCHDEV_OBJ_PORT_MDB(obj)); break; @@ -463,6 +472,17 @@ static int dsa_slave_port_obj_del(struct net_device *dev, case SWITCHDEV_OBJ_ID_PORT_VLAN: err = dsa_slave_vlan_del(dev, obj); break; + case SWITCHDEV_OBJ_ID_MRP: + if (!dsa_port_offloads_netdev(dp, obj->orig_dev)) + return -EOPNOTSUPP; + err = dsa_port_mrp_del(dp, SWITCHDEV_OBJ_MRP(obj)); + break; + case SWITCHDEV_OBJ_ID_RING_ROLE_MRP: + if (!dsa_port_offloads_netdev(dp, obj->orig_dev)) + return -EOPNOTSUPP; + err = dsa_port_mrp_del_ring_role(dp, + SWITCHDEV_OBJ_RING_ROLE_MRP(obj)); + break; default: err = -EOPNOTSUPP; break; @@ -1289,35 +1309,29 @@ static int dsa_slave_vlan_rx_add_vid(struct net_device *dev, __be16 proto, struct dsa_port *dp = dsa_slave_to_port(dev); struct switchdev_obj_port_vlan vlan = { .obj.id = SWITCHDEV_OBJ_ID_PORT_VLAN, - .vid_begin = vid, - .vid_end = vid, + .vid = vid, /* This API only allows programming tagged, non-PVID VIDs */ .flags = 0, }; - struct switchdev_trans trans; + struct netlink_ext_ack extack = {0}; int ret; /* User port... */ - trans.ph_prepare = true; - ret = dsa_port_vlan_add(dp, &vlan, &trans); - if (ret) - return ret; - - trans.ph_prepare = false; - ret = dsa_port_vlan_add(dp, &vlan, &trans); - if (ret) + ret = dsa_port_vlan_add(dp, &vlan, &extack); + if (ret) { + if (extack._msg) + netdev_err(dev, "%s\n", extack._msg); return ret; + } /* And CPU port... */ - trans.ph_prepare = true; - ret = dsa_port_vlan_add(dp->cpu_dp, &vlan, &trans); - if (ret) - return ret; - - trans.ph_prepare = false; - ret = dsa_port_vlan_add(dp->cpu_dp, &vlan, &trans); - if (ret) + ret = dsa_port_vlan_add(dp->cpu_dp, &vlan, &extack); + if (ret) { + if (extack._msg) + netdev_err(dev, "CPU port %d: %s\n", dp->cpu_dp->index, + extack._msg); return ret; + } return vlan_vid_add(master, proto, vid); } @@ -1328,8 +1342,7 @@ static int dsa_slave_vlan_rx_kill_vid(struct net_device *dev, __be16 proto, struct net_device *master = dsa_slave_to_master(dev); struct dsa_port *dp = dsa_slave_to_port(dev); struct switchdev_obj_port_vlan vlan = { - .vid_begin = vid, - .vid_end = vid, + .vid = vid, /* This API only allows programming tagged, non-PVID VIDs */ .flags = 0, }; @@ -1457,7 +1470,7 @@ out: dsa_hw_port_list_free(&hw_port_list); } -static int dsa_slave_change_mtu(struct net_device *dev, int new_mtu) +int dsa_slave_change_mtu(struct net_device *dev, int new_mtu) { struct net_device *master = dsa_slave_to_master(dev); struct dsa_port *dp = dsa_slave_to_port(dev); @@ -1575,20 +1588,20 @@ static const struct ethtool_ops dsa_slave_ethtool_ops = { }; /* legacy way, bypassing the bridge *****************************************/ -int dsa_legacy_fdb_add(struct ndmsg *ndm, struct nlattr *tb[], - struct net_device *dev, - const unsigned char *addr, u16 vid, - u16 flags, - struct netlink_ext_ack *extack) +static int dsa_legacy_fdb_add(struct ndmsg *ndm, struct nlattr *tb[], + struct net_device *dev, + const unsigned char *addr, u16 vid, + u16 flags, + struct netlink_ext_ack *extack) { struct dsa_port *dp = dsa_slave_to_port(dev); return dsa_port_fdb_add(dp, addr, vid); } -int dsa_legacy_fdb_del(struct ndmsg *ndm, struct nlattr *tb[], - struct net_device *dev, - const unsigned char *addr, u16 vid) +static int dsa_legacy_fdb_del(struct ndmsg *ndm, struct nlattr *tb[], + struct net_device *dev, + const unsigned char *addr, u16 vid) { struct dsa_port *dp = dsa_slave_to_port(dev); @@ -1602,6 +1615,18 @@ static struct devlink_port *dsa_slave_get_devlink_port(struct net_device *dev) return dp->ds->devlink ? &dp->devlink_port : NULL; } +static void dsa_slave_get_stats64(struct net_device *dev, + struct rtnl_link_stats64 *s) +{ + struct dsa_port *dp = dsa_slave_to_port(dev); + struct dsa_switch *ds = dp->ds; + + if (ds->ops->get_stats64) + ds->ops->get_stats64(ds, dp->index, s); + else + dev_get_tstats64(dev, s); +} + static const struct net_device_ops dsa_slave_netdev_ops = { .ndo_open = dsa_slave_open, .ndo_stop = dsa_slave_close, @@ -1621,7 +1646,7 @@ static const struct net_device_ops dsa_slave_netdev_ops = { #endif .ndo_get_phys_port_name = dsa_slave_get_phys_port_name, .ndo_setup_tc = dsa_slave_setup_tc, - .ndo_get_stats64 = dev_get_tstats64, + .ndo_get_stats64 = dsa_slave_get_stats64, .ndo_get_port_parent_id = dsa_slave_get_port_parent_id, .ndo_vlan_rx_add_vid = dsa_slave_vlan_rx_add_vid, .ndo_vlan_rx_kill_vid = dsa_slave_vlan_rx_kill_vid, @@ -1723,6 +1748,27 @@ static int dsa_slave_phy_setup(struct net_device *slave_dev) return ret; } +void dsa_slave_setup_tagger(struct net_device *slave) +{ + struct dsa_port *dp = dsa_slave_to_port(slave); + struct dsa_slave_priv *p = netdev_priv(slave); + const struct dsa_port *cpu_dp = dp->cpu_dp; + struct net_device *master = cpu_dp->master; + + if (cpu_dp->tag_ops->tail_tag) + slave->needed_tailroom = cpu_dp->tag_ops->overhead; + else + slave->needed_headroom = cpu_dp->tag_ops->overhead; + /* Try to save one extra realloc later in the TX path (in the master) + * by also inheriting the master's needed headroom and tailroom. + * The 8021q driver also does this. + */ + slave->needed_headroom += master->needed_headroom; + slave->needed_tailroom += master->needed_tailroom; + + p->xmit = cpu_dp->tag_ops->xmit; +} + static struct lock_class_key dsa_slave_netdev_xmit_lock_key; static void dsa_slave_set_lockdep_class_one(struct net_device *dev, struct netdev_queue *txq, @@ -1764,20 +1810,6 @@ int dsa_slave_resume(struct net_device *slave_dev) return 0; } -static void dsa_slave_notify(struct net_device *dev, unsigned long val) -{ - struct net_device *master = dsa_slave_to_master(dev); - struct dsa_port *dp = dsa_slave_to_port(dev); - struct dsa_notifier_register_info rinfo = { - .switch_number = dp->ds->index, - .port_number = dp->index, - .master = master, - .info.dev = dev, - }; - - call_dsa_notifiers(val, dev, &rinfo.info); -} - int dsa_slave_create(struct dsa_port *port) { const struct dsa_port *cpu_dp = port->cpu_dp; @@ -1811,16 +1843,6 @@ int dsa_slave_create(struct dsa_port *port) slave_dev->netdev_ops = &dsa_slave_netdev_ops; if (ds->ops->port_max_mtu) slave_dev->max_mtu = ds->ops->port_max_mtu(ds, port->index); - if (cpu_dp->tag_ops->tail_tag) - slave_dev->needed_tailroom = cpu_dp->tag_ops->overhead; - else - slave_dev->needed_headroom = cpu_dp->tag_ops->overhead; - /* Try to save one extra realloc later in the TX path (in the master) - * by also inheriting the master's needed headroom and tailroom. - * The 8021q driver also does this. - */ - slave_dev->needed_headroom += master->needed_headroom; - slave_dev->needed_tailroom += master->needed_tailroom; SET_NETDEV_DEVTYPE(slave_dev, &dsa_type); netdev_for_each_tx_queue(slave_dev, dsa_slave_set_lockdep_class_one, @@ -1843,8 +1865,8 @@ int dsa_slave_create(struct dsa_port *port) p->dp = port; INIT_LIST_HEAD(&p->mall_tc_list); - p->xmit = cpu_dp->tag_ops->xmit; port->slave = slave_dev; + dsa_slave_setup_tagger(slave_dev); rtnl_lock(); ret = dsa_slave_change_mtu(slave_dev, ETH_DATA_LEN); @@ -1863,8 +1885,6 @@ int dsa_slave_create(struct dsa_port *port) goto out_gcells; } - dsa_slave_notify(slave_dev, DSA_PORT_REGISTER); - rtnl_lock(); ret = register_netdevice(slave_dev); @@ -1913,7 +1933,6 @@ void dsa_slave_destroy(struct net_device *slave_dev) phylink_disconnect_phy(dp->pl); rtnl_unlock(); - dsa_slave_notify(slave_dev, DSA_PORT_UNREGISTER); phylink_destroy(dp->pl); gro_cells_destroy(&p->gcells); free_percpu(slave_dev->tstats); @@ -1924,6 +1943,7 @@ bool dsa_slave_dev_check(const struct net_device *dev) { return dev->netdev_ops == &dsa_slave_netdev_ops; } +EXPORT_SYMBOL_GPL(dsa_slave_dev_check); static int dsa_slave_changeupper(struct net_device *dev, struct netdev_notifier_changeupper_info *info) @@ -1941,6 +1961,59 @@ static int dsa_slave_changeupper(struct net_device *dev, dsa_port_bridge_leave(dp, info->upper_dev); err = NOTIFY_OK; } + } else if (netif_is_lag_master(info->upper_dev)) { + if (info->linking) { + err = dsa_port_lag_join(dp, info->upper_dev, + info->upper_info); + if (err == -EOPNOTSUPP) { + NL_SET_ERR_MSG_MOD(info->info.extack, + "Offloading not supported"); + err = 0; + } + err = notifier_from_errno(err); + } else { + dsa_port_lag_leave(dp, info->upper_dev); + err = NOTIFY_OK; + } + } else if (is_hsr_master(info->upper_dev)) { + if (info->linking) { + err = dsa_port_hsr_join(dp, info->upper_dev); + if (err == -EOPNOTSUPP) { + NL_SET_ERR_MSG_MOD(info->info.extack, + "Offloading not supported"); + err = 0; + } + err = notifier_from_errno(err); + } else { + dsa_port_hsr_leave(dp, info->upper_dev); + err = NOTIFY_OK; + } + } + + return err; +} + +static int +dsa_slave_lag_changeupper(struct net_device *dev, + struct netdev_notifier_changeupper_info *info) +{ + struct net_device *lower; + struct list_head *iter; + int err = NOTIFY_DONE; + struct dsa_port *dp; + + netdev_for_each_lower_dev(dev, lower, iter) { + if (!dsa_slave_dev_check(lower)) + continue; + + dp = dsa_slave_to_port(lower); + if (!dp->lag_dev) + /* Software LAG */ + continue; + + err = dsa_slave_changeupper(lower, info); + if (notifier_to_errno(err)) + break; } return err; @@ -2038,128 +2111,224 @@ static int dsa_slave_netdevice_event(struct notifier_block *nb, break; } case NETDEV_CHANGEUPPER: + if (dsa_slave_dev_check(dev)) + return dsa_slave_changeupper(dev, ptr); + + if (netif_is_lag_master(dev)) + return dsa_slave_lag_changeupper(dev, ptr); + + break; + case NETDEV_CHANGELOWERSTATE: { + struct netdev_notifier_changelowerstate_info *info = ptr; + struct dsa_port *dp; + int err; + if (!dsa_slave_dev_check(dev)) + break; + + dp = dsa_slave_to_port(dev); + + err = dsa_port_lag_change(dp, info->lower_state_info); + return notifier_from_errno(err); + } + case NETDEV_GOING_DOWN: { + struct dsa_port *dp, *cpu_dp; + struct dsa_switch_tree *dst; + LIST_HEAD(close_list); + + if (!netdev_uses_dsa(dev)) return NOTIFY_DONE; - return dsa_slave_changeupper(dev, ptr); + cpu_dp = dev->dsa_ptr; + dst = cpu_dp->ds->dst; + + list_for_each_entry(dp, &dst->ports, list) { + if (!dsa_is_user_port(dp->ds, dp->index)) + continue; + + list_add(&dp->slave->close_list, &close_list); + } + + dev_close_many(&close_list, true); + + return NOTIFY_OK; + } + default: + break; } return NOTIFY_DONE; } -struct dsa_switchdev_event_work { - struct work_struct work; - struct switchdev_notifier_fdb_info fdb_info; - struct net_device *dev; - unsigned long event; -}; +static void +dsa_fdb_offload_notify(struct dsa_switchdev_event_work *switchdev_work) +{ + struct dsa_switch *ds = switchdev_work->ds; + struct switchdev_notifier_fdb_info info; + struct dsa_port *dp; + + if (!dsa_is_user_port(ds, switchdev_work->port)) + return; + + info.addr = switchdev_work->addr; + info.vid = switchdev_work->vid; + info.offloaded = true; + dp = dsa_to_port(ds, switchdev_work->port); + call_switchdev_notifiers(SWITCHDEV_FDB_OFFLOADED, + dp->slave, &info.info, NULL); +} static void dsa_slave_switchdev_event_work(struct work_struct *work) { struct dsa_switchdev_event_work *switchdev_work = container_of(work, struct dsa_switchdev_event_work, work); - struct net_device *dev = switchdev_work->dev; - struct switchdev_notifier_fdb_info *fdb_info; - struct dsa_port *dp = dsa_slave_to_port(dev); + struct dsa_switch *ds = switchdev_work->ds; + struct dsa_port *dp; int err; + dp = dsa_to_port(ds, switchdev_work->port); + rtnl_lock(); switch (switchdev_work->event) { case SWITCHDEV_FDB_ADD_TO_DEVICE: - fdb_info = &switchdev_work->fdb_info; - if (!fdb_info->added_by_user) - break; - - err = dsa_port_fdb_add(dp, fdb_info->addr, fdb_info->vid); + err = dsa_port_fdb_add(dp, switchdev_work->addr, + switchdev_work->vid); if (err) { - netdev_dbg(dev, "fdb add failed err=%d\n", err); + dev_err(ds->dev, + "port %d failed to add %pM vid %d to fdb: %d\n", + dp->index, switchdev_work->addr, + switchdev_work->vid, err); break; } - fdb_info->offloaded = true; - call_switchdev_notifiers(SWITCHDEV_FDB_OFFLOADED, dev, - &fdb_info->info, NULL); + dsa_fdb_offload_notify(switchdev_work); break; case SWITCHDEV_FDB_DEL_TO_DEVICE: - fdb_info = &switchdev_work->fdb_info; - if (!fdb_info->added_by_user) - break; - - err = dsa_port_fdb_del(dp, fdb_info->addr, fdb_info->vid); + err = dsa_port_fdb_del(dp, switchdev_work->addr, + switchdev_work->vid); if (err) { - netdev_dbg(dev, "fdb del failed err=%d\n", err); - dev_close(dev); + dev_err(ds->dev, + "port %d failed to delete %pM vid %d from fdb: %d\n", + dp->index, switchdev_work->addr, + switchdev_work->vid, err); } + break; } rtnl_unlock(); - kfree(switchdev_work->fdb_info.addr); kfree(switchdev_work); - dev_put(dev); + if (dsa_is_user_port(ds, dp->index)) + dev_put(dp->slave); } -static int -dsa_slave_switchdev_fdb_work_init(struct dsa_switchdev_event_work * - switchdev_work, - const struct switchdev_notifier_fdb_info * - fdb_info) -{ - memcpy(&switchdev_work->fdb_info, fdb_info, - sizeof(switchdev_work->fdb_info)); - switchdev_work->fdb_info.addr = kzalloc(ETH_ALEN, GFP_ATOMIC); - if (!switchdev_work->fdb_info.addr) - return -ENOMEM; - ether_addr_copy((u8 *)switchdev_work->fdb_info.addr, - fdb_info->addr); +static int dsa_lower_dev_walk(struct net_device *lower_dev, + struct netdev_nested_priv *priv) +{ + if (dsa_slave_dev_check(lower_dev)) { + priv->data = (void *)netdev_priv(lower_dev); + return 1; + } + return 0; } +static struct dsa_slave_priv *dsa_slave_dev_lower_find(struct net_device *dev) +{ + struct netdev_nested_priv priv = { + .data = NULL, + }; + + netdev_walk_all_lower_dev_rcu(dev, dsa_lower_dev_walk, &priv); + + return (struct dsa_slave_priv *)priv.data; +} + /* Called under rcu_read_lock() */ static int dsa_slave_switchdev_event(struct notifier_block *unused, unsigned long event, void *ptr) { struct net_device *dev = switchdev_notifier_info_to_dev(ptr); + const struct switchdev_notifier_fdb_info *fdb_info; struct dsa_switchdev_event_work *switchdev_work; + struct dsa_port *dp; int err; - if (event == SWITCHDEV_PORT_ATTR_SET) { + switch (event) { + case SWITCHDEV_PORT_ATTR_SET: err = switchdev_handle_port_attr_set(dev, ptr, dsa_slave_dev_check, dsa_slave_port_attr_set); return notifier_from_errno(err); - } + case SWITCHDEV_FDB_ADD_TO_DEVICE: + case SWITCHDEV_FDB_DEL_TO_DEVICE: + fdb_info = ptr; - if (!dsa_slave_dev_check(dev)) - return NOTIFY_DONE; + if (dsa_slave_dev_check(dev)) { + if (!fdb_info->added_by_user) + return NOTIFY_OK; - switchdev_work = kzalloc(sizeof(*switchdev_work), GFP_ATOMIC); - if (!switchdev_work) - return NOTIFY_BAD; + dp = dsa_slave_to_port(dev); + } else { + /* Snoop addresses learnt on foreign interfaces + * bridged with us, for switches that don't + * automatically learn SA from CPU-injected traffic + */ + struct net_device *br_dev; + struct dsa_slave_priv *p; + + br_dev = netdev_master_upper_dev_get_rcu(dev); + if (!br_dev) + return NOTIFY_DONE; + + if (!netif_is_bridge_master(br_dev)) + return NOTIFY_DONE; + + p = dsa_slave_dev_lower_find(br_dev); + if (!p) + return NOTIFY_DONE; + + dp = p->dp->cpu_dp; + + if (!dp->ds->assisted_learning_on_cpu_port) + return NOTIFY_DONE; + + /* When the bridge learns an address on an offloaded + * LAG we don't want to send traffic to the CPU, the + * other ports bridged with the LAG should be able to + * autonomously forward towards it. + */ + if (dsa_tree_offloads_netdev(dp->ds->dst, dev)) + return NOTIFY_DONE; + } - INIT_WORK(&switchdev_work->work, - dsa_slave_switchdev_event_work); - switchdev_work->dev = dev; - switchdev_work->event = event; + if (!dp->ds->ops->port_fdb_add || !dp->ds->ops->port_fdb_del) + return NOTIFY_DONE; - switch (event) { - case SWITCHDEV_FDB_ADD_TO_DEVICE: - case SWITCHDEV_FDB_DEL_TO_DEVICE: - if (dsa_slave_switchdev_fdb_work_init(switchdev_work, ptr)) - goto err_fdb_work_init; - dev_hold(dev); + switchdev_work = kzalloc(sizeof(*switchdev_work), GFP_ATOMIC); + if (!switchdev_work) + return NOTIFY_BAD; + + INIT_WORK(&switchdev_work->work, + dsa_slave_switchdev_event_work); + switchdev_work->ds = dp->ds; + switchdev_work->port = dp->index; + switchdev_work->event = event; + + ether_addr_copy(switchdev_work->addr, + fdb_info->addr); + switchdev_work->vid = fdb_info->vid; + + /* Hold a reference on the slave for dsa_fdb_offload_notify */ + if (dsa_is_user_port(dp->ds, dp->index)) + dev_hold(dev); + dsa_schedule_work(&switchdev_work->work); break; default: - kfree(switchdev_work); return NOTIFY_DONE; } - dsa_schedule_work(&switchdev_work->work); return NOTIFY_OK; - -err_fdb_work_init: - kfree(switchdev_work); - return NOTIFY_BAD; } static int dsa_slave_switchdev_blocking_event(struct notifier_block *unused, diff --git a/net/dsa/switch.c b/net/dsa/switch.c index 3fb362b6874e..4b5da89dc27a 100644 --- a/net/dsa/switch.c +++ b/net/dsa/switch.c @@ -33,15 +33,12 @@ static int dsa_switch_ageing_time(struct dsa_switch *ds, struct dsa_notifier_ageing_time_info *info) { unsigned int ageing_time = info->ageing_time; - struct switchdev_trans *trans = info->trans; - - if (switchdev_trans_ph_prepare(trans)) { - if (ds->ageing_time_min && ageing_time < ds->ageing_time_min) - return -ERANGE; - if (ds->ageing_time_max && ageing_time > ds->ageing_time_max) - return -ERANGE; - return 0; - } + + if (ds->ageing_time_min && ageing_time < ds->ageing_time_min) + return -ERANGE; + + if (ds->ageing_time_max && ageing_time > ds->ageing_time_max) + return -ERANGE; /* Program the fastest ageing time in case of multiple bridges */ ageing_time = dsa_switch_fastest_ageing_time(ds, ageing_time); @@ -109,6 +106,7 @@ static int dsa_switch_bridge_leave(struct dsa_switch *ds, { bool unset_vlan_filtering = br_vlan_enabled(info->br); struct dsa_switch_tree *dst = ds->dst; + struct netlink_ext_ack extack = {0}; int err, i; if (dst->index == info->tree_index && ds->index == info->sw_index && @@ -139,17 +137,11 @@ static int dsa_switch_bridge_leave(struct dsa_switch *ds, } } if (unset_vlan_filtering) { - struct switchdev_trans trans; - - trans.ph_prepare = true; err = dsa_port_vlan_filtering(dsa_to_port(ds, info->port), - false, &trans); - if (err && err != EOPNOTSUPP) - return err; - - trans.ph_prepare = false; - err = dsa_port_vlan_filtering(dsa_to_port(ds, info->port), - false, &trans); + false, &extack); + if (extack._msg) + dev_err(ds->dev, "port %d: %s\n", info->port, + extack._msg); if (err && err != EOPNOTSUPP) return err; } @@ -178,6 +170,65 @@ static int dsa_switch_fdb_del(struct dsa_switch *ds, return ds->ops->port_fdb_del(ds, port, info->addr, info->vid); } +static int dsa_switch_hsr_join(struct dsa_switch *ds, + struct dsa_notifier_hsr_info *info) +{ + if (ds->index == info->sw_index && ds->ops->port_hsr_join) + return ds->ops->port_hsr_join(ds, info->port, info->hsr); + + return -EOPNOTSUPP; +} + +static int dsa_switch_hsr_leave(struct dsa_switch *ds, + struct dsa_notifier_hsr_info *info) +{ + if (ds->index == info->sw_index && ds->ops->port_hsr_leave) + return ds->ops->port_hsr_leave(ds, info->port, info->hsr); + + return -EOPNOTSUPP; +} + +static int dsa_switch_lag_change(struct dsa_switch *ds, + struct dsa_notifier_lag_info *info) +{ + if (ds->index == info->sw_index && ds->ops->port_lag_change) + return ds->ops->port_lag_change(ds, info->port); + + if (ds->index != info->sw_index && ds->ops->crosschip_lag_change) + return ds->ops->crosschip_lag_change(ds, info->sw_index, + info->port); + + return 0; +} + +static int dsa_switch_lag_join(struct dsa_switch *ds, + struct dsa_notifier_lag_info *info) +{ + if (ds->index == info->sw_index && ds->ops->port_lag_join) + return ds->ops->port_lag_join(ds, info->port, info->lag, + info->info); + + if (ds->index != info->sw_index && ds->ops->crosschip_lag_join) + return ds->ops->crosschip_lag_join(ds, info->sw_index, + info->port, info->lag, + info->info); + + return 0; +} + +static int dsa_switch_lag_leave(struct dsa_switch *ds, + struct dsa_notifier_lag_info *info) +{ + if (ds->index == info->sw_index && ds->ops->port_lag_leave) + return ds->ops->port_lag_leave(ds, info->port, info->lag); + + if (ds->index != info->sw_index && ds->ops->crosschip_lag_leave) + return ds->ops->crosschip_lag_leave(ds, info->sw_index, + info->port, info->lag); + + return 0; +} + static bool dsa_switch_mdb_match(struct dsa_switch *ds, int port, struct dsa_notifier_mdb_info *info) { @@ -190,41 +241,24 @@ static bool dsa_switch_mdb_match(struct dsa_switch *ds, int port, return false; } -static int dsa_switch_mdb_prepare(struct dsa_switch *ds, - struct dsa_notifier_mdb_info *info) +static int dsa_switch_mdb_add(struct dsa_switch *ds, + struct dsa_notifier_mdb_info *info) { - int port, err; + int err = 0; + int port; - if (!ds->ops->port_mdb_prepare || !ds->ops->port_mdb_add) + if (!ds->ops->port_mdb_add) return -EOPNOTSUPP; for (port = 0; port < ds->num_ports; port++) { if (dsa_switch_mdb_match(ds, port, info)) { - err = ds->ops->port_mdb_prepare(ds, port, info->mdb); + err = ds->ops->port_mdb_add(ds, port, info->mdb); if (err) - return err; + break; } } - return 0; -} - -static int dsa_switch_mdb_add(struct dsa_switch *ds, - struct dsa_notifier_mdb_info *info) -{ - int port; - - if (switchdev_trans_ph_prepare(info->trans)) - return dsa_switch_mdb_prepare(ds, info); - - if (!ds->ops->port_mdb_add) - return 0; - - for (port = 0; port < ds->num_ports; port++) - if (dsa_switch_mdb_match(ds, port, info)) - ds->ops->port_mdb_add(ds, port, info->mdb); - - return 0; + return err; } static int dsa_switch_mdb_del(struct dsa_switch *ds, @@ -251,17 +285,18 @@ static bool dsa_switch_vlan_match(struct dsa_switch *ds, int port, return false; } -static int dsa_switch_vlan_prepare(struct dsa_switch *ds, - struct dsa_notifier_vlan_info *info) +static int dsa_switch_vlan_add(struct dsa_switch *ds, + struct dsa_notifier_vlan_info *info) { int port, err; - if (!ds->ops->port_vlan_prepare || !ds->ops->port_vlan_add) + if (!ds->ops->port_vlan_add) return -EOPNOTSUPP; for (port = 0; port < ds->num_ports; port++) { if (dsa_switch_vlan_match(ds, port, info)) { - err = ds->ops->port_vlan_prepare(ds, port, info->vlan); + err = ds->ops->port_vlan_add(ds, port, info->vlan, + info->extack); if (err) return err; } @@ -270,36 +305,163 @@ static int dsa_switch_vlan_prepare(struct dsa_switch *ds, return 0; } -static int dsa_switch_vlan_add(struct dsa_switch *ds, +static int dsa_switch_vlan_del(struct dsa_switch *ds, struct dsa_notifier_vlan_info *info) { + if (!ds->ops->port_vlan_del) + return -EOPNOTSUPP; + + if (ds->index == info->sw_index) + return ds->ops->port_vlan_del(ds, info->port, info->vlan); + + /* Do not deprogram the DSA links as they may be used as conduit + * for other VLAN members in the fabric. + */ + return 0; +} + +static bool dsa_switch_tag_proto_match(struct dsa_switch *ds, int port, + struct dsa_notifier_tag_proto_info *info) +{ + if (dsa_is_cpu_port(ds, port) || dsa_is_dsa_port(ds, port)) + return true; + + return false; +} + +static int dsa_switch_change_tag_proto(struct dsa_switch *ds, + struct dsa_notifier_tag_proto_info *info) +{ + const struct dsa_device_ops *tag_ops = info->tag_ops; + int port, err; + + if (!ds->ops->change_tag_protocol) + return -EOPNOTSUPP; + + ASSERT_RTNL(); + + for (port = 0; port < ds->num_ports; port++) { + if (dsa_switch_tag_proto_match(ds, port, info)) { + err = ds->ops->change_tag_protocol(ds, port, + tag_ops->proto); + if (err) + return err; + + if (dsa_is_cpu_port(ds, port)) + dsa_port_set_tag_protocol(dsa_to_port(ds, port), + tag_ops); + } + } + + /* Now that changing the tag protocol can no longer fail, let's update + * the remaining bits which are "duplicated for faster access", and the + * bits that depend on the tagger, such as the MTU. + */ + for (port = 0; port < ds->num_ports; port++) { + if (dsa_is_user_port(ds, port)) { + struct net_device *slave; + + slave = dsa_to_port(ds, port)->slave; + dsa_slave_setup_tagger(slave); + + /* rtnl_mutex is held in dsa_tree_change_tag_proto */ + dsa_slave_change_mtu(slave, slave->mtu); + } + } + + return 0; +} + +static bool dsa_switch_mrp_match(struct dsa_switch *ds, int port, + struct dsa_notifier_mrp_info *info) +{ + if (ds->index == info->sw_index && port == info->port) + return true; + + if (dsa_is_dsa_port(ds, port)) + return true; + + return false; +} + +static int dsa_switch_mrp_add(struct dsa_switch *ds, + struct dsa_notifier_mrp_info *info) +{ + int err = 0; int port; - if (switchdev_trans_ph_prepare(info->trans)) - return dsa_switch_vlan_prepare(ds, info); + if (!ds->ops->port_mrp_add) + return -EOPNOTSUPP; - if (!ds->ops->port_vlan_add) - return 0; + for (port = 0; port < ds->num_ports; port++) { + if (dsa_switch_mrp_match(ds, port, info)) { + err = ds->ops->port_mrp_add(ds, port, info->mrp); + if (err) + break; + } + } + + return err; +} - for (port = 0; port < ds->num_ports; port++) - if (dsa_switch_vlan_match(ds, port, info)) - ds->ops->port_vlan_add(ds, port, info->vlan); +static int dsa_switch_mrp_del(struct dsa_switch *ds, + struct dsa_notifier_mrp_info *info) +{ + if (!ds->ops->port_mrp_del) + return -EOPNOTSUPP; + + if (ds->index == info->sw_index) + return ds->ops->port_mrp_del(ds, info->port, info->mrp); return 0; } -static int dsa_switch_vlan_del(struct dsa_switch *ds, - struct dsa_notifier_vlan_info *info) +static bool +dsa_switch_mrp_ring_role_match(struct dsa_switch *ds, int port, + struct dsa_notifier_mrp_ring_role_info *info) { - if (!ds->ops->port_vlan_del) + if (ds->index == info->sw_index && port == info->port) + return true; + + if (dsa_is_dsa_port(ds, port)) + return true; + + return false; +} + +static int +dsa_switch_mrp_add_ring_role(struct dsa_switch *ds, + struct dsa_notifier_mrp_ring_role_info *info) +{ + int err = 0; + int port; + + if (!ds->ops->port_mrp_add) + return -EOPNOTSUPP; + + for (port = 0; port < ds->num_ports; port++) { + if (dsa_switch_mrp_ring_role_match(ds, port, info)) { + err = ds->ops->port_mrp_add_ring_role(ds, port, + info->mrp); + if (err) + break; + } + } + + return err; +} + +static int +dsa_switch_mrp_del_ring_role(struct dsa_switch *ds, + struct dsa_notifier_mrp_ring_role_info *info) +{ + if (!ds->ops->port_mrp_del) return -EOPNOTSUPP; if (ds->index == info->sw_index) - return ds->ops->port_vlan_del(ds, info->port, info->vlan); + return ds->ops->port_mrp_del_ring_role(ds, info->port, + info->mrp); - /* Do not deprogram the DSA links as they may be used as conduit - * for other VLAN members in the fabric. - */ return 0; } @@ -325,6 +487,21 @@ static int dsa_switch_event(struct notifier_block *nb, case DSA_NOTIFIER_FDB_DEL: err = dsa_switch_fdb_del(ds, info); break; + case DSA_NOTIFIER_HSR_JOIN: + err = dsa_switch_hsr_join(ds, info); + break; + case DSA_NOTIFIER_HSR_LEAVE: + err = dsa_switch_hsr_leave(ds, info); + break; + case DSA_NOTIFIER_LAG_CHANGE: + err = dsa_switch_lag_change(ds, info); + break; + case DSA_NOTIFIER_LAG_JOIN: + err = dsa_switch_lag_join(ds, info); + break; + case DSA_NOTIFIER_LAG_LEAVE: + err = dsa_switch_lag_leave(ds, info); + break; case DSA_NOTIFIER_MDB_ADD: err = dsa_switch_mdb_add(ds, info); break; @@ -340,15 +517,26 @@ static int dsa_switch_event(struct notifier_block *nb, case DSA_NOTIFIER_MTU: err = dsa_switch_mtu(ds, info); break; + case DSA_NOTIFIER_TAG_PROTO: + err = dsa_switch_change_tag_proto(ds, info); + break; + case DSA_NOTIFIER_MRP_ADD: + err = dsa_switch_mrp_add(ds, info); + break; + case DSA_NOTIFIER_MRP_DEL: + err = dsa_switch_mrp_del(ds, info); + break; + case DSA_NOTIFIER_MRP_ADD_RING_ROLE: + err = dsa_switch_mrp_add_ring_role(ds, info); + break; + case DSA_NOTIFIER_MRP_DEL_RING_ROLE: + err = dsa_switch_mrp_del_ring_role(ds, info); + break; default: err = -EOPNOTSUPP; break; } - /* Non-switchdev operations cannot be rolled back. If a DSA driver - * returns an error during the chained call, switch chips may be in an - * inconsistent state. - */ if (err) dev_dbg(ds->dev, "breaking chain for DSA event %lu (%d)\n", event, err); diff --git a/net/dsa/tag_8021q.c b/net/dsa/tag_8021q.c index 8e3e8a5b8559..008c1ec6e20c 100644 --- a/net/dsa/tag_8021q.c +++ b/net/dsa/tag_8021q.c @@ -133,10 +133,21 @@ u16 dsa_8021q_rx_subvlan(u16 vid) } EXPORT_SYMBOL_GPL(dsa_8021q_rx_subvlan); +bool vid_is_dsa_8021q_rxvlan(u16 vid) +{ + return (vid & DSA_8021Q_DIR_MASK) == DSA_8021Q_DIR_RX; +} +EXPORT_SYMBOL_GPL(vid_is_dsa_8021q_rxvlan); + +bool vid_is_dsa_8021q_txvlan(u16 vid) +{ + return (vid & DSA_8021Q_DIR_MASK) == DSA_8021Q_DIR_TX; +} +EXPORT_SYMBOL_GPL(vid_is_dsa_8021q_txvlan); + bool vid_is_dsa_8021q(u16 vid) { - return ((vid & DSA_8021Q_DIR_MASK) == DSA_8021Q_DIR_RX || - (vid & DSA_8021Q_DIR_MASK) == DSA_8021Q_DIR_TX); + return vid_is_dsa_8021q_rxvlan(vid) || vid_is_dsa_8021q_txvlan(vid); } EXPORT_SYMBOL_GPL(vid_is_dsa_8021q); diff --git a/net/dsa/tag_brcm.c b/net/dsa/tag_brcm.c index e934dace3922..e2577a7dcbca 100644 --- a/net/dsa/tag_brcm.c +++ b/net/dsa/tag_brcm.c @@ -5,6 +5,7 @@ * Copyright (C) 2014 Broadcom Corporation */ +#include <linux/dsa/brcm.h> #include <linux/etherdevice.h> #include <linux/list.h> #include <linux/slab.h> diff --git a/net/dsa/tag_dsa.c b/net/dsa/tag_dsa.c index 112c7c6dd568..7e7b7decdf39 100644 --- a/net/dsa/tag_dsa.c +++ b/net/dsa/tag_dsa.c @@ -163,6 +163,7 @@ static struct sk_buff *dsa_rcv_ll(struct sk_buff *skb, struct net_device *dev, u8 extra) { int source_device, source_port; + bool trunk = false; enum dsa_code code; enum dsa_cmd cmd; u8 *dsa_header; @@ -174,6 +175,8 @@ static struct sk_buff *dsa_rcv_ll(struct sk_buff *skb, struct net_device *dev, switch (cmd) { case DSA_CMD_FORWARD: skb->offload_fwd_mark = 1; + + trunk = !!(dsa_header[1] & 7); break; case DSA_CMD_TO_CPU: @@ -216,7 +219,19 @@ static struct sk_buff *dsa_rcv_ll(struct sk_buff *skb, struct net_device *dev, source_device = dsa_header[0] & 0x1f; source_port = (dsa_header[1] >> 3) & 0x1f; - skb->dev = dsa_master_find_slave(dev, source_device, source_port); + if (trunk) { + struct dsa_port *cpu_dp = dev->dsa_ptr; + + /* The exact source port is not available in the tag, + * so we inject the frame directly on the upper + * team/bond. + */ + skb->dev = dsa_lag_dev(cpu_dp->dst, source_port); + } else { + skb->dev = dsa_master_find_slave(dev, source_device, + source_port); + } + if (!skb->dev) return NULL; diff --git a/net/dsa/tag_ocelot.c b/net/dsa/tag_ocelot.c index 16a1afd5b8e1..743809b5806b 100644 --- a/net/dsa/tag_ocelot.c +++ b/net/dsa/tag_ocelot.c @@ -1,174 +1,74 @@ // SPDX-License-Identifier: GPL-2.0 /* Copyright 2019 NXP Semiconductors */ +#include <linux/dsa/ocelot.h> #include <soc/mscc/ocelot.h> -#include <linux/packing.h> #include "dsa_priv.h" -/* The CPU injection header and the CPU extraction header can have 3 types of - * prefixes: long, short and no prefix. The format of the header itself is the - * same in all 3 cases. - * - * Extraction with long prefix: - * - * +-------------------+-------------------+------+------+------------+-------+ - * | ff:ff:ff:ff:ff:ff | ff:ff:ff:ff:ff:ff | 8880 | 000a | extraction | frame | - * | | | | | header | | - * +-------------------+-------------------+------+------+------------+-------+ - * 48 bits 48 bits 16 bits 16 bits 128 bits - * - * Extraction with short prefix: - * - * +------+------+------------+-------+ - * | 8880 | 000a | extraction | frame | - * | | | header | | - * +------+------+------------+-------+ - * 16 bits 16 bits 128 bits - * - * Extraction with no prefix: - * - * +------------+-------+ - * | extraction | frame | - * | header | | - * +------------+-------+ - * 128 bits - * - * - * Injection with long prefix: - * - * +-------------------+-------------------+------+------+------------+-------+ - * | any dmac | any smac | 8880 | 000a | injection | frame | - * | | | | | header | | - * +-------------------+-------------------+------+------+------------+-------+ - * 48 bits 48 bits 16 bits 16 bits 128 bits - * - * Injection with short prefix: - * - * +------+------+------------+-------+ - * | 8880 | 000a | injection | frame | - * | | | header | | - * +------+------+------------+-------+ - * 16 bits 16 bits 128 bits - * - * Injection with no prefix: - * - * +------------+-------+ - * | injection | frame | - * | header | | - * +------------+-------+ - * 128 bits - * - * The injection header looks like this (network byte order, bit 127 - * is part of lowest address byte in memory, bit 0 is part of highest - * address byte): - * - * +------+------+------+------+------+------+------+------+ - * 127:120 |BYPASS| MASQ | MASQ_PORT |REW_OP|REW_OP| - * +------+------+------+------+------+------+------+------+ - * 119:112 | REW_OP | - * +------+------+------+------+------+------+------+------+ - * 111:104 | REW_VAL | - * +------+------+------+------+------+------+------+------+ - * 103: 96 | REW_VAL | - * +------+------+------+------+------+------+------+------+ - * 95: 88 | REW_VAL | - * +------+------+------+------+------+------+------+------+ - * 87: 80 | REW_VAL | - * +------+------+------+------+------+------+------+------+ - * 79: 72 | RSV | - * +------+------+------+------+------+------+------+------+ - * 71: 64 | RSV | DEST | - * +------+------+------+------+------+------+------+------+ - * 63: 56 | DEST | - * +------+------+------+------+------+------+------+------+ - * 55: 48 | RSV | - * +------+------+------+------+------+------+------+------+ - * 47: 40 | RSV | SRC_PORT | RSV |TFRM_TIMER| - * +------+------+------+------+------+------+------+------+ - * 39: 32 | TFRM_TIMER | RSV | - * +------+------+------+------+------+------+------+------+ - * 31: 24 | RSV | DP | POP_CNT | CPUQ | - * +------+------+------+------+------+------+------+------+ - * 23: 16 | CPUQ | QOS_CLASS |TAG_TYPE| - * +------+------+------+------+------+------+------+------+ - * 15: 8 | PCP | DEI | VID | - * +------+------+------+------+------+------+------+------+ - * 7: 0 | VID | - * +------+------+------+------+------+------+------+------+ - * - * And the extraction header looks like this: - * - * +------+------+------+------+------+------+------+------+ - * 127:120 | RSV | REW_OP | - * +------+------+------+------+------+------+------+------+ - * 119:112 | REW_OP | REW_VAL | - * +------+------+------+------+------+------+------+------+ - * 111:104 | REW_VAL | - * +------+------+------+------+------+------+------+------+ - * 103: 96 | REW_VAL | - * +------+------+------+------+------+------+------+------+ - * 95: 88 | REW_VAL | - * +------+------+------+------+------+------+------+------+ - * 87: 80 | REW_VAL | LLEN | - * +------+------+------+------+------+------+------+------+ - * 79: 72 | LLEN | WLEN | - * +------+------+------+------+------+------+------+------+ - * 71: 64 | WLEN | RSV | - * +------+------+------+------+------+------+------+------+ - * 63: 56 | RSV | - * +------+------+------+------+------+------+------+------+ - * 55: 48 | RSV | - * +------+------+------+------+------+------+------+------+ - * 47: 40 | RSV | SRC_PORT | ACL_ID | - * +------+------+------+------+------+------+------+------+ - * 39: 32 | ACL_ID | RSV | SFLOW_ID | - * +------+------+------+------+------+------+------+------+ - * 31: 24 |ACL_HIT| DP | LRN_FLAGS | CPUQ | - * +------+------+------+------+------+------+------+------+ - * 23: 16 | CPUQ | QOS_CLASS |TAG_TYPE| - * +------+------+------+------+------+------+------+------+ - * 15: 8 | PCP | DEI | VID | - * +------+------+------+------+------+------+------+------+ - * 7: 0 | VID | - * +------+------+------+------+------+------+------+------+ - */ +static void ocelot_xmit_ptp(struct dsa_port *dp, void *injection, + struct sk_buff *clone) +{ + struct ocelot *ocelot = dp->ds->priv; + struct ocelot_port *ocelot_port; + u64 rew_op; -static struct sk_buff *ocelot_xmit(struct sk_buff *skb, - struct net_device *netdev) + ocelot_port = ocelot->ports[dp->index]; + rew_op = ocelot_port->ptp_cmd; + + /* Retrieve timestamp ID populated inside skb->cb[0] of the + * clone by ocelot_port_add_txtstamp_skb + */ + if (ocelot_port->ptp_cmd == IFH_REW_OP_TWO_STEP_PTP) + rew_op |= clone->cb[0] << 3; + + ocelot_ifh_set_rew_op(injection, rew_op); +} + +static void ocelot_xmit_common(struct sk_buff *skb, struct net_device *netdev, + __be32 ifh_prefix, void **ifh) { struct dsa_port *dp = dsa_slave_to_port(netdev); struct sk_buff *clone = DSA_SKB_CB(skb)->clone; struct dsa_switch *ds = dp->ds; - struct ocelot *ocelot = ds->priv; - struct ocelot_port *ocelot_port; - u8 *prefix, *injection; - u64 qos_class, rew_op; - - ocelot_port = ocelot->ports[dp->index]; + void *injection; + __be32 *prefix; injection = skb_push(skb, OCELOT_TAG_LEN); - prefix = skb_push(skb, OCELOT_SHORT_PREFIX_LEN); - memcpy(prefix, ocelot_port->xmit_template, OCELOT_TOTAL_TAG_LEN); - - /* Fix up the fields which are not statically determined - * in the template - */ - qos_class = skb->priority; - packing(injection, &qos_class, 19, 17, OCELOT_TAG_LEN, PACK, 0); + *prefix = ifh_prefix; + memset(injection, 0, OCELOT_TAG_LEN); + ocelot_ifh_set_bypass(injection, 1); + ocelot_ifh_set_src(injection, ds->num_ports); + ocelot_ifh_set_qos_class(injection, skb->priority); /* TX timestamping was requested */ - if (clone) { - rew_op = ocelot_port->ptp_cmd; - /* Retrieve timestamp ID populated inside skb->cb[0] of the - * clone by ocelot_port_add_txtstamp_skb - */ - if (ocelot_port->ptp_cmd == IFH_REW_OP_TWO_STEP_PTP) - rew_op |= clone->cb[0] << 3; + if (clone) + ocelot_xmit_ptp(dp, injection, clone); - packing(injection, &rew_op, 125, 117, OCELOT_TAG_LEN, PACK, 0); - } + *ifh = injection; +} + +static struct sk_buff *ocelot_xmit(struct sk_buff *skb, + struct net_device *netdev) +{ + struct dsa_port *dp = dsa_slave_to_port(netdev); + void *injection; + + ocelot_xmit_common(skb, netdev, cpu_to_be32(0x8880000a), &injection); + ocelot_ifh_set_dest(injection, BIT_ULL(dp->index)); + + return skb; +} + +static struct sk_buff *seville_xmit(struct sk_buff *skb, + struct net_device *netdev) +{ + struct dsa_port *dp = dsa_slave_to_port(netdev); + void *injection; + + ocelot_xmit_common(skb, netdev, cpu_to_be32(0x88800005), &injection); + seville_ifh_set_dest(injection, BIT_ULL(dp->index)); return skb; } @@ -177,14 +77,13 @@ static struct sk_buff *ocelot_rcv(struct sk_buff *skb, struct net_device *netdev, struct packet_type *pt) { - struct dsa_port *cpu_dp = netdev->dsa_ptr; - struct dsa_switch *ds = cpu_dp->ds; - struct ocelot *ocelot = ds->priv; u64 src_port, qos_class; u64 vlan_tci, tag_type; u8 *start = skb->data; + struct dsa_port *dp; u8 *extraction; u16 vlan_tpid; + u64 cpuq; /* Revert skb->data by the amount consumed by the DSA master, * so it points to the beginning of the frame. @@ -210,10 +109,11 @@ static struct sk_buff *ocelot_rcv(struct sk_buff *skb, /* Remove from inet csum the extraction header */ skb_postpull_rcsum(skb, start, OCELOT_TOTAL_TAG_LEN); - packing(extraction, &src_port, 46, 43, OCELOT_TAG_LEN, UNPACK, 0); - packing(extraction, &qos_class, 19, 17, OCELOT_TAG_LEN, UNPACK, 0); - packing(extraction, &tag_type, 16, 16, OCELOT_TAG_LEN, UNPACK, 0); - packing(extraction, &vlan_tci, 15, 0, OCELOT_TAG_LEN, UNPACK, 0); + ocelot_xfh_get_src_port(extraction, &src_port); + ocelot_xfh_get_qos_class(extraction, &qos_class); + ocelot_xfh_get_tag_type(extraction, &tag_type); + ocelot_xfh_get_vlan_tci(extraction, &vlan_tci); + ocelot_xfh_get_cpuq(extraction, &cpuq); skb->dev = dsa_master_find_slave(netdev, 0, src_port); if (!skb->dev) @@ -228,6 +128,12 @@ static struct sk_buff *ocelot_rcv(struct sk_buff *skb, skb->offload_fwd_mark = 1; skb->priority = qos_class; +#if IS_ENABLED(CONFIG_BRIDGE_MRP) + if (eth_hdr(skb)->h_proto == cpu_to_be16(ETH_P_MRP) && + cpuq & BIT(OCELOT_MRP_CPUQ)) + skb->offload_fwd_mark = 0; +#endif + /* Ocelot switches copy frames unmodified to the CPU. However, it is * possible for the user to request a VLAN modification through * VCAP_IS1_ACT_VID_REPLACE_ENA. In this case, what will happen is that @@ -243,9 +149,10 @@ static struct sk_buff *ocelot_rcv(struct sk_buff *skb, * equal to the pvid of the ingress port and should not be used for * processing. */ + dp = dsa_slave_to_port(skb->dev); vlan_tpid = tag_type ? ETH_P_8021AD : ETH_P_8021Q; - if (ocelot->ports[src_port]->vlan_aware && + if (dsa_port_is_vlan_filtering(dp) && eth_hdr(skb)->h_proto == htons(vlan_tpid)) { u16 dummy_vlan_tci; @@ -267,7 +174,26 @@ static const struct dsa_device_ops ocelot_netdev_ops = { .promisc_on_master = true, }; -MODULE_LICENSE("GPL v2"); +DSA_TAG_DRIVER(ocelot_netdev_ops); MODULE_ALIAS_DSA_TAG_DRIVER(DSA_TAG_PROTO_OCELOT); -module_dsa_tag_driver(ocelot_netdev_ops); +static const struct dsa_device_ops seville_netdev_ops = { + .name = "seville", + .proto = DSA_TAG_PROTO_SEVILLE, + .xmit = seville_xmit, + .rcv = ocelot_rcv, + .overhead = OCELOT_TOTAL_TAG_LEN, + .promisc_on_master = true, +}; + +DSA_TAG_DRIVER(seville_netdev_ops); +MODULE_ALIAS_DSA_TAG_DRIVER(DSA_TAG_PROTO_SEVILLE); + +static struct dsa_tag_driver *ocelot_tag_driver_array[] = { + &DSA_TAG_DRIVER_NAME(ocelot_netdev_ops), + &DSA_TAG_DRIVER_NAME(seville_netdev_ops), +}; + +module_dsa_tag_drivers(ocelot_tag_driver_array); + +MODULE_LICENSE("GPL v2"); diff --git a/net/dsa/tag_ocelot_8021q.c b/net/dsa/tag_ocelot_8021q.c new file mode 100644 index 000000000000..5f3e8e124a82 --- /dev/null +++ b/net/dsa/tag_ocelot_8021q.c @@ -0,0 +1,102 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright 2020-2021 NXP Semiconductors + * + * An implementation of the software-defined tag_8021q.c tagger format, which + * also preserves full functionality under a vlan_filtering bridge. It does + * this by using the TCAM engines for: + * - pushing the RX VLAN as a second, outer tag, on egress towards the CPU port + * - redirecting towards the correct front port based on TX VLAN and popping + * that on egress + */ +#include <linux/dsa/8021q.h> +#include <soc/mscc/ocelot.h> +#include <soc/mscc/ocelot_ptp.h> +#include "dsa_priv.h" + +static struct sk_buff *ocelot_xmit_ptp(struct dsa_port *dp, + struct sk_buff *skb, + struct sk_buff *clone) +{ + struct ocelot *ocelot = dp->ds->priv; + struct ocelot_port *ocelot_port; + int port = dp->index; + u32 rew_op; + + if (!ocelot_can_inject(ocelot, 0)) + return NULL; + + ocelot_port = ocelot->ports[port]; + rew_op = ocelot_port->ptp_cmd; + + /* Retrieve timestamp ID populated inside skb->cb[0] of the + * clone by ocelot_port_add_txtstamp_skb + */ + if (ocelot_port->ptp_cmd == IFH_REW_OP_TWO_STEP_PTP) + rew_op |= clone->cb[0] << 3; + + ocelot_port_inject_frame(ocelot, port, 0, rew_op, skb); + + return NULL; +} + +static struct sk_buff *ocelot_xmit(struct sk_buff *skb, + struct net_device *netdev) +{ + struct dsa_port *dp = dsa_slave_to_port(netdev); + u16 tx_vid = dsa_8021q_tx_vid(dp->ds, dp->index); + u16 queue_mapping = skb_get_queue_mapping(skb); + u8 pcp = netdev_txq_to_tc(netdev, queue_mapping); + struct sk_buff *clone = DSA_SKB_CB(skb)->clone; + + /* TX timestamping was requested, so inject through MMIO */ + if (clone) + return ocelot_xmit_ptp(dp, skb, clone); + + return dsa_8021q_xmit(skb, netdev, ETH_P_8021Q, + ((pcp << VLAN_PRIO_SHIFT) | tx_vid)); +} + +static struct sk_buff *ocelot_rcv(struct sk_buff *skb, + struct net_device *netdev, + struct packet_type *pt) +{ + int src_port, switch_id, qos_class; + u16 vid, tci; + + skb_push_rcsum(skb, ETH_HLEN); + if (skb_vlan_tag_present(skb)) { + tci = skb_vlan_tag_get(skb); + __vlan_hwaccel_clear_tag(skb); + } else { + __skb_vlan_pop(skb, &tci); + } + skb_pull_rcsum(skb, ETH_HLEN); + + vid = tci & VLAN_VID_MASK; + src_port = dsa_8021q_rx_source_port(vid); + switch_id = dsa_8021q_rx_switch_id(vid); + qos_class = (tci & VLAN_PRIO_MASK) >> VLAN_PRIO_SHIFT; + + skb->dev = dsa_master_find_slave(netdev, switch_id, src_port); + if (!skb->dev) + return NULL; + + skb->offload_fwd_mark = 1; + skb->priority = qos_class; + + return skb; +} + +static const struct dsa_device_ops ocelot_8021q_netdev_ops = { + .name = "ocelot-8021q", + .proto = DSA_TAG_PROTO_OCELOT_8021Q, + .xmit = ocelot_xmit, + .rcv = ocelot_rcv, + .overhead = VLAN_HLEN, + .promisc_on_master = true, +}; + +MODULE_LICENSE("GPL v2"); +MODULE_ALIAS_DSA_TAG_DRIVER(DSA_TAG_PROTO_OCELOT_8021Q); + +module_dsa_tag_driver(ocelot_8021q_netdev_ops); diff --git a/net/dsa/tag_rtl4_a.c b/net/dsa/tag_rtl4_a.c index 2646abe5a69e..c17d39b4a1a0 100644 --- a/net/dsa/tag_rtl4_a.c +++ b/net/dsa/tag_rtl4_a.c @@ -12,9 +12,7 @@ * * The 2 bytes tag form a 16 bit big endian word. The exact * meaning has been guessed from packet dumps from ingress - * frames, as no working egress traffic has been available - * we do not know the format of the egress tags or if they - * are even supported. + * frames. */ #include <linux/etherdevice.h> @@ -36,17 +34,34 @@ static struct sk_buff *rtl4a_tag_xmit(struct sk_buff *skb, struct net_device *dev) { - /* - * Just let it pass thru, we don't know if it is possible - * to tag a frame with the 0x8899 ethertype and direct it - * to a specific port, all attempts at reverse-engineering have - * ended up with the frames getting dropped. - * - * The VLAN set-up needs to restrict the frames to the right port. - * - * If you have documentation on the tagging format for RTL8366RB - * (tag type A) then please contribute. - */ + struct dsa_port *dp = dsa_slave_to_port(dev); + u8 *tag; + u16 *p; + u16 out; + + /* Pad out to at least 60 bytes */ + if (unlikely(eth_skb_pad(skb))) + return NULL; + if (skb_cow_head(skb, RTL4_A_HDR_LEN) < 0) + return NULL; + + netdev_dbg(dev, "add realtek tag to package to port %d\n", + dp->index); + skb_push(skb, RTL4_A_HDR_LEN); + + memmove(skb->data, skb->data + RTL4_A_HDR_LEN, 2 * ETH_ALEN); + tag = skb->data + 2 * ETH_ALEN; + + /* Set Ethertype */ + p = (u16 *)tag; + *p = htons(RTL4_A_ETHERTYPE); + + out = (RTL4_A_PROTOCOL_RTL8366RB << 12) | (2 << 8); + /* The lower bits is the port numer */ + out |= (u8)dp->index; + p = (u16 *)(tag + 2); + *p = htons(out); + return skb; } diff --git a/net/dsa/tag_xrs700x.c b/net/dsa/tag_xrs700x.c new file mode 100644 index 000000000000..858cdf9d2913 --- /dev/null +++ b/net/dsa/tag_xrs700x.c @@ -0,0 +1,66 @@ +// SPDX-License-Identifier: GPL-2.0+ +/* + * XRS700x tag format handling + * Copyright (c) 2008-2009 Marvell Semiconductor + * Copyright (c) 2020 NovaTech LLC + */ + +#include <linux/bitops.h> + +#include "dsa_priv.h" + +static struct sk_buff *xrs700x_xmit(struct sk_buff *skb, struct net_device *dev) +{ + struct dsa_port *partner, *dp = dsa_slave_to_port(dev); + u8 *trailer; + + trailer = skb_put(skb, 1); + trailer[0] = BIT(dp->index); + + if (dp->hsr_dev) + dsa_hsr_foreach_port(partner, dp->ds, dp->hsr_dev) + if (partner != dp) + trailer[0] |= BIT(partner->index); + + return skb; +} + +static struct sk_buff *xrs700x_rcv(struct sk_buff *skb, struct net_device *dev, + struct packet_type *pt) +{ + int source_port; + u8 *trailer; + + trailer = skb_tail_pointer(skb) - 1; + + source_port = ffs((int)trailer[0]) - 1; + + if (source_port < 0) + return NULL; + + skb->dev = dsa_master_find_slave(dev, 0, source_port); + if (!skb->dev) + return NULL; + + if (pskb_trim_rcsum(skb, skb->len - 1)) + return NULL; + + /* Frame is forwarded by hardware, don't forward in software. */ + skb->offload_fwd_mark = 1; + + return skb; +} + +static const struct dsa_device_ops xrs700x_netdev_ops = { + .name = "xrs700x", + .proto = DSA_TAG_PROTO_XRS700X, + .xmit = xrs700x_xmit, + .rcv = xrs700x_rcv, + .overhead = 1, + .tail_tag = true, +}; + +MODULE_LICENSE("GPL"); +MODULE_ALIAS_DSA_TAG_DRIVER(DSA_TAG_PROTO_XRS700X); + +module_dsa_tag_driver(xrs700x_netdev_ops); diff --git a/net/ethtool/common.c b/net/ethtool/common.c index 24036e3055a1..c6a383dfd6c2 100644 --- a/net/ethtool/common.c +++ b/net/ethtool/common.c @@ -68,6 +68,11 @@ const char netdev_features_strings[NETDEV_FEATURE_COUNT][ETH_GSTRING_LEN] = { [NETIF_F_HW_TLS_RX_BIT] = "tls-hw-rx-offload", [NETIF_F_GRO_FRAGLIST_BIT] = "rx-gro-list", [NETIF_F_HW_MACSEC_BIT] = "macsec-hw-offload", + [NETIF_F_GRO_UDP_FWD_BIT] = "rx-udp-gro-forwarding", + [NETIF_F_HW_HSR_TAG_INS_BIT] = "hsr-tag-ins-offload", + [NETIF_F_HW_HSR_TAG_RM_BIT] = "hsr-tag-rm-offload", + [NETIF_F_HW_HSR_FWD_BIT] = "hsr-fwd-offload", + [NETIF_F_HW_HSR_DUP_BIT] = "hsr-dup-offload", }; const char @@ -197,6 +202,153 @@ const char link_mode_names[][ETH_GSTRING_LEN] = { }; static_assert(ARRAY_SIZE(link_mode_names) == __ETHTOOL_LINK_MODE_MASK_NBITS); +#define __LINK_MODE_LANES_CR 1 +#define __LINK_MODE_LANES_CR2 2 +#define __LINK_MODE_LANES_CR4 4 +#define __LINK_MODE_LANES_CR8 8 +#define __LINK_MODE_LANES_DR 1 +#define __LINK_MODE_LANES_DR2 2 +#define __LINK_MODE_LANES_DR4 4 +#define __LINK_MODE_LANES_DR8 8 +#define __LINK_MODE_LANES_KR 1 +#define __LINK_MODE_LANES_KR2 2 +#define __LINK_MODE_LANES_KR4 4 +#define __LINK_MODE_LANES_KR8 8 +#define __LINK_MODE_LANES_SR 1 +#define __LINK_MODE_LANES_SR2 2 +#define __LINK_MODE_LANES_SR4 4 +#define __LINK_MODE_LANES_SR8 8 +#define __LINK_MODE_LANES_ER 1 +#define __LINK_MODE_LANES_KX 1 +#define __LINK_MODE_LANES_KX4 4 +#define __LINK_MODE_LANES_LR 1 +#define __LINK_MODE_LANES_LR4 4 +#define __LINK_MODE_LANES_LR4_ER4 4 +#define __LINK_MODE_LANES_LR_ER_FR 1 +#define __LINK_MODE_LANES_LR2_ER2_FR2 2 +#define __LINK_MODE_LANES_LR4_ER4_FR4 4 +#define __LINK_MODE_LANES_LR8_ER8_FR8 8 +#define __LINK_MODE_LANES_LRM 1 +#define __LINK_MODE_LANES_MLD2 2 +#define __LINK_MODE_LANES_T 1 +#define __LINK_MODE_LANES_T1 1 +#define __LINK_MODE_LANES_X 1 +#define __LINK_MODE_LANES_FX 1 + +#define __DEFINE_LINK_MODE_PARAMS(_speed, _type, _duplex) \ + [ETHTOOL_LINK_MODE(_speed, _type, _duplex)] = { \ + .speed = SPEED_ ## _speed, \ + .lanes = __LINK_MODE_LANES_ ## _type, \ + .duplex = __DUPLEX_ ## _duplex \ + } +#define __DUPLEX_Half DUPLEX_HALF +#define __DUPLEX_Full DUPLEX_FULL +#define __DEFINE_SPECIAL_MODE_PARAMS(_mode) \ + [ETHTOOL_LINK_MODE_ ## _mode ## _BIT] = { \ + .speed = SPEED_UNKNOWN, \ + .lanes = 0, \ + .duplex = DUPLEX_UNKNOWN, \ + } + +const struct link_mode_info link_mode_params[] = { + __DEFINE_LINK_MODE_PARAMS(10, T, Half), + __DEFINE_LINK_MODE_PARAMS(10, T, Full), + __DEFINE_LINK_MODE_PARAMS(100, T, Half), + __DEFINE_LINK_MODE_PARAMS(100, T, Full), + __DEFINE_LINK_MODE_PARAMS(1000, T, Half), + __DEFINE_LINK_MODE_PARAMS(1000, T, Full), + __DEFINE_SPECIAL_MODE_PARAMS(Autoneg), + __DEFINE_SPECIAL_MODE_PARAMS(TP), + __DEFINE_SPECIAL_MODE_PARAMS(AUI), + __DEFINE_SPECIAL_MODE_PARAMS(MII), + __DEFINE_SPECIAL_MODE_PARAMS(FIBRE), + __DEFINE_SPECIAL_MODE_PARAMS(BNC), + __DEFINE_LINK_MODE_PARAMS(10000, T, Full), + __DEFINE_SPECIAL_MODE_PARAMS(Pause), + __DEFINE_SPECIAL_MODE_PARAMS(Asym_Pause), + __DEFINE_LINK_MODE_PARAMS(2500, X, Full), + __DEFINE_SPECIAL_MODE_PARAMS(Backplane), + __DEFINE_LINK_MODE_PARAMS(1000, KX, Full), + __DEFINE_LINK_MODE_PARAMS(10000, KX4, Full), + __DEFINE_LINK_MODE_PARAMS(10000, KR, Full), + [ETHTOOL_LINK_MODE_10000baseR_FEC_BIT] = { + .speed = SPEED_10000, + .duplex = DUPLEX_FULL, + }, + __DEFINE_LINK_MODE_PARAMS(20000, MLD2, Full), + __DEFINE_LINK_MODE_PARAMS(20000, KR2, Full), + __DEFINE_LINK_MODE_PARAMS(40000, KR4, Full), + __DEFINE_LINK_MODE_PARAMS(40000, CR4, Full), + __DEFINE_LINK_MODE_PARAMS(40000, SR4, Full), + __DEFINE_LINK_MODE_PARAMS(40000, LR4, Full), + __DEFINE_LINK_MODE_PARAMS(56000, KR4, Full), + __DEFINE_LINK_MODE_PARAMS(56000, CR4, Full), + __DEFINE_LINK_MODE_PARAMS(56000, SR4, Full), + __DEFINE_LINK_MODE_PARAMS(56000, LR4, Full), + __DEFINE_LINK_MODE_PARAMS(25000, CR, Full), + __DEFINE_LINK_MODE_PARAMS(25000, KR, Full), + __DEFINE_LINK_MODE_PARAMS(25000, SR, Full), + __DEFINE_LINK_MODE_PARAMS(50000, CR2, Full), + __DEFINE_LINK_MODE_PARAMS(50000, KR2, Full), + __DEFINE_LINK_MODE_PARAMS(100000, KR4, Full), + __DEFINE_LINK_MODE_PARAMS(100000, SR4, Full), + __DEFINE_LINK_MODE_PARAMS(100000, CR4, Full), + __DEFINE_LINK_MODE_PARAMS(100000, LR4_ER4, Full), + __DEFINE_LINK_MODE_PARAMS(50000, SR2, Full), + __DEFINE_LINK_MODE_PARAMS(1000, X, Full), + __DEFINE_LINK_MODE_PARAMS(10000, CR, Full), + __DEFINE_LINK_MODE_PARAMS(10000, SR, Full), + __DEFINE_LINK_MODE_PARAMS(10000, LR, Full), + __DEFINE_LINK_MODE_PARAMS(10000, LRM, Full), + __DEFINE_LINK_MODE_PARAMS(10000, ER, Full), + __DEFINE_LINK_MODE_PARAMS(2500, T, Full), + __DEFINE_LINK_MODE_PARAMS(5000, T, Full), + __DEFINE_SPECIAL_MODE_PARAMS(FEC_NONE), + __DEFINE_SPECIAL_MODE_PARAMS(FEC_RS), + __DEFINE_SPECIAL_MODE_PARAMS(FEC_BASER), + __DEFINE_LINK_MODE_PARAMS(50000, KR, Full), + __DEFINE_LINK_MODE_PARAMS(50000, SR, Full), + __DEFINE_LINK_MODE_PARAMS(50000, CR, Full), + __DEFINE_LINK_MODE_PARAMS(50000, LR_ER_FR, Full), + __DEFINE_LINK_MODE_PARAMS(50000, DR, Full), + __DEFINE_LINK_MODE_PARAMS(100000, KR2, Full), + __DEFINE_LINK_MODE_PARAMS(100000, SR2, Full), + __DEFINE_LINK_MODE_PARAMS(100000, CR2, Full), + __DEFINE_LINK_MODE_PARAMS(100000, LR2_ER2_FR2, Full), + __DEFINE_LINK_MODE_PARAMS(100000, DR2, Full), + __DEFINE_LINK_MODE_PARAMS(200000, KR4, Full), + __DEFINE_LINK_MODE_PARAMS(200000, SR4, Full), + __DEFINE_LINK_MODE_PARAMS(200000, LR4_ER4_FR4, Full), + __DEFINE_LINK_MODE_PARAMS(200000, DR4, Full), + __DEFINE_LINK_MODE_PARAMS(200000, CR4, Full), + __DEFINE_LINK_MODE_PARAMS(100, T1, Full), + __DEFINE_LINK_MODE_PARAMS(1000, T1, Full), + __DEFINE_LINK_MODE_PARAMS(400000, KR8, Full), + __DEFINE_LINK_MODE_PARAMS(400000, SR8, Full), + __DEFINE_LINK_MODE_PARAMS(400000, LR8_ER8_FR8, Full), + __DEFINE_LINK_MODE_PARAMS(400000, DR8, Full), + __DEFINE_LINK_MODE_PARAMS(400000, CR8, Full), + __DEFINE_SPECIAL_MODE_PARAMS(FEC_LLRS), + __DEFINE_LINK_MODE_PARAMS(100000, KR, Full), + __DEFINE_LINK_MODE_PARAMS(100000, SR, Full), + __DEFINE_LINK_MODE_PARAMS(100000, LR_ER_FR, Full), + __DEFINE_LINK_MODE_PARAMS(100000, DR, Full), + __DEFINE_LINK_MODE_PARAMS(100000, CR, Full), + __DEFINE_LINK_MODE_PARAMS(200000, KR2, Full), + __DEFINE_LINK_MODE_PARAMS(200000, SR2, Full), + __DEFINE_LINK_MODE_PARAMS(200000, LR2_ER2_FR2, Full), + __DEFINE_LINK_MODE_PARAMS(200000, DR2, Full), + __DEFINE_LINK_MODE_PARAMS(200000, CR2, Full), + __DEFINE_LINK_MODE_PARAMS(400000, KR4, Full), + __DEFINE_LINK_MODE_PARAMS(400000, SR4, Full), + __DEFINE_LINK_MODE_PARAMS(400000, LR4_ER4_FR4, Full), + __DEFINE_LINK_MODE_PARAMS(400000, DR4, Full), + __DEFINE_LINK_MODE_PARAMS(400000, CR4, Full), + __DEFINE_LINK_MODE_PARAMS(100, FX, Half), + __DEFINE_LINK_MODE_PARAMS(100, FX, Full), +}; +static_assert(ARRAY_SIZE(link_mode_params) == __ETHTOOL_LINK_MODE_MASK_NBITS); + const char netif_msg_class_names[][ETH_GSTRING_LEN] = { [NETIF_MSG_DRV_BIT] = "drv", [NETIF_MSG_PROBE_BIT] = "probe", diff --git a/net/ethtool/common.h b/net/ethtool/common.h index 3d9251c95a8b..a9d071248698 100644 --- a/net/ethtool/common.h +++ b/net/ethtool/common.h @@ -14,6 +14,12 @@ #define __SOF_TIMESTAMPING_CNT (const_ilog2(SOF_TIMESTAMPING_LAST) + 1) +struct link_mode_info { + int speed; + u8 lanes; + u8 duplex; +}; + extern const char netdev_features_strings[NETDEV_FEATURE_COUNT][ETH_GSTRING_LEN]; extern const char @@ -23,6 +29,7 @@ tunable_strings[__ETHTOOL_TUNABLE_COUNT][ETH_GSTRING_LEN]; extern const char phy_tunable_strings[__ETHTOOL_PHY_TUNABLE_COUNT][ETH_GSTRING_LEN]; extern const char link_mode_names[][ETH_GSTRING_LEN]; +extern const struct link_mode_info link_mode_params[]; extern const char netif_msg_class_names[][ETH_GSTRING_LEN]; extern const char wol_mode_names[][ETH_GSTRING_LEN]; extern const char sof_timestamping_names[][ETH_GSTRING_LEN]; diff --git a/net/ethtool/ioctl.c b/net/ethtool/ioctl.c index 771688e1b0da..24783b71c584 100644 --- a/net/ethtool/ioctl.c +++ b/net/ethtool/ioctl.c @@ -426,13 +426,29 @@ struct ethtool_link_usettings { int __ethtool_get_link_ksettings(struct net_device *dev, struct ethtool_link_ksettings *link_ksettings) { + const struct link_mode_info *link_info; + int err; + ASSERT_RTNL(); if (!dev->ethtool_ops->get_link_ksettings) return -EOPNOTSUPP; memset(link_ksettings, 0, sizeof(*link_ksettings)); - return dev->ethtool_ops->get_link_ksettings(dev, link_ksettings); + + link_ksettings->link_mode = -1; + err = dev->ethtool_ops->get_link_ksettings(dev, link_ksettings); + if (err) + return err; + + if (link_ksettings->link_mode != -1) { + link_info = &link_mode_params[link_ksettings->link_mode]; + link_ksettings->base.speed = link_info->speed; + link_ksettings->lanes = link_info->lanes; + link_ksettings->base.duplex = link_info->duplex; + } + + return 0; } EXPORT_SYMBOL(__ethtool_get_link_ksettings); diff --git a/net/ethtool/linkmodes.c b/net/ethtool/linkmodes.c index c5bcb9abc8b9..f9eda596f301 100644 --- a/net/ethtool/linkmodes.c +++ b/net/ethtool/linkmodes.c @@ -4,6 +4,8 @@ #include "common.h" #include "bitset.h" +/* LINKMODES_GET */ + struct linkmodes_req_info { struct ethnl_req_info base; }; @@ -43,6 +45,9 @@ static int linkmodes_prepare_data(const struct ethnl_req_info *req_base, goto out; } + if (!dev->ethtool_ops->cap_link_lanes_supported) + data->ksettings.lanes = 0; + data->peer_empty = bitmap_empty(data->ksettings.link_modes.lp_advertising, __ETHTOOL_LINK_MODE_MASK_NBITS); @@ -63,6 +68,7 @@ static int linkmodes_reply_size(const struct ethnl_req_info *req_base, len = nla_total_size(sizeof(u8)) /* LINKMODES_AUTONEG */ + nla_total_size(sizeof(u32)) /* LINKMODES_SPEED */ + + nla_total_size(sizeof(u32)) /* LINKMODES_LANES */ + nla_total_size(sizeof(u8)) /* LINKMODES_DUPLEX */ + 0; ret = ethnl_bitset_size(ksettings->link_modes.advertising, @@ -123,6 +129,10 @@ static int linkmodes_fill_reply(struct sk_buff *skb, nla_put_u8(skb, ETHTOOL_A_LINKMODES_DUPLEX, lsettings->duplex)) return -EMSGSIZE; + if (ksettings->lanes && + nla_put_u32(skb, ETHTOOL_A_LINKMODES_LANES, ksettings->lanes)) + return -EMSGSIZE; + if (lsettings->master_slave_cfg != MASTER_SLAVE_CFG_UNSUPPORTED && nla_put_u8(skb, ETHTOOL_A_LINKMODES_MASTER_SLAVE_CFG, lsettings->master_slave_cfg)) @@ -150,122 +160,6 @@ const struct ethnl_request_ops ethnl_linkmodes_request_ops = { /* LINKMODES_SET */ -struct link_mode_info { - int speed; - u8 duplex; -}; - -#define __DEFINE_LINK_MODE_PARAMS(_speed, _type, _duplex) \ - [ETHTOOL_LINK_MODE(_speed, _type, _duplex)] = { \ - .speed = SPEED_ ## _speed, \ - .duplex = __DUPLEX_ ## _duplex \ - } -#define __DUPLEX_Half DUPLEX_HALF -#define __DUPLEX_Full DUPLEX_FULL -#define __DEFINE_SPECIAL_MODE_PARAMS(_mode) \ - [ETHTOOL_LINK_MODE_ ## _mode ## _BIT] = { \ - .speed = SPEED_UNKNOWN, \ - .duplex = DUPLEX_UNKNOWN, \ - } - -static const struct link_mode_info link_mode_params[] = { - __DEFINE_LINK_MODE_PARAMS(10, T, Half), - __DEFINE_LINK_MODE_PARAMS(10, T, Full), - __DEFINE_LINK_MODE_PARAMS(100, T, Half), - __DEFINE_LINK_MODE_PARAMS(100, T, Full), - __DEFINE_LINK_MODE_PARAMS(1000, T, Half), - __DEFINE_LINK_MODE_PARAMS(1000, T, Full), - __DEFINE_SPECIAL_MODE_PARAMS(Autoneg), - __DEFINE_SPECIAL_MODE_PARAMS(TP), - __DEFINE_SPECIAL_MODE_PARAMS(AUI), - __DEFINE_SPECIAL_MODE_PARAMS(MII), - __DEFINE_SPECIAL_MODE_PARAMS(FIBRE), - __DEFINE_SPECIAL_MODE_PARAMS(BNC), - __DEFINE_LINK_MODE_PARAMS(10000, T, Full), - __DEFINE_SPECIAL_MODE_PARAMS(Pause), - __DEFINE_SPECIAL_MODE_PARAMS(Asym_Pause), - __DEFINE_LINK_MODE_PARAMS(2500, X, Full), - __DEFINE_SPECIAL_MODE_PARAMS(Backplane), - __DEFINE_LINK_MODE_PARAMS(1000, KX, Full), - __DEFINE_LINK_MODE_PARAMS(10000, KX4, Full), - __DEFINE_LINK_MODE_PARAMS(10000, KR, Full), - [ETHTOOL_LINK_MODE_10000baseR_FEC_BIT] = { - .speed = SPEED_10000, - .duplex = DUPLEX_FULL, - }, - __DEFINE_LINK_MODE_PARAMS(20000, MLD2, Full), - __DEFINE_LINK_MODE_PARAMS(20000, KR2, Full), - __DEFINE_LINK_MODE_PARAMS(40000, KR4, Full), - __DEFINE_LINK_MODE_PARAMS(40000, CR4, Full), - __DEFINE_LINK_MODE_PARAMS(40000, SR4, Full), - __DEFINE_LINK_MODE_PARAMS(40000, LR4, Full), - __DEFINE_LINK_MODE_PARAMS(56000, KR4, Full), - __DEFINE_LINK_MODE_PARAMS(56000, CR4, Full), - __DEFINE_LINK_MODE_PARAMS(56000, SR4, Full), - __DEFINE_LINK_MODE_PARAMS(56000, LR4, Full), - __DEFINE_LINK_MODE_PARAMS(25000, CR, Full), - __DEFINE_LINK_MODE_PARAMS(25000, KR, Full), - __DEFINE_LINK_MODE_PARAMS(25000, SR, Full), - __DEFINE_LINK_MODE_PARAMS(50000, CR2, Full), - __DEFINE_LINK_MODE_PARAMS(50000, KR2, Full), - __DEFINE_LINK_MODE_PARAMS(100000, KR4, Full), - __DEFINE_LINK_MODE_PARAMS(100000, SR4, Full), - __DEFINE_LINK_MODE_PARAMS(100000, CR4, Full), - __DEFINE_LINK_MODE_PARAMS(100000, LR4_ER4, Full), - __DEFINE_LINK_MODE_PARAMS(50000, SR2, Full), - __DEFINE_LINK_MODE_PARAMS(1000, X, Full), - __DEFINE_LINK_MODE_PARAMS(10000, CR, Full), - __DEFINE_LINK_MODE_PARAMS(10000, SR, Full), - __DEFINE_LINK_MODE_PARAMS(10000, LR, Full), - __DEFINE_LINK_MODE_PARAMS(10000, LRM, Full), - __DEFINE_LINK_MODE_PARAMS(10000, ER, Full), - __DEFINE_LINK_MODE_PARAMS(2500, T, Full), - __DEFINE_LINK_MODE_PARAMS(5000, T, Full), - __DEFINE_SPECIAL_MODE_PARAMS(FEC_NONE), - __DEFINE_SPECIAL_MODE_PARAMS(FEC_RS), - __DEFINE_SPECIAL_MODE_PARAMS(FEC_BASER), - __DEFINE_LINK_MODE_PARAMS(50000, KR, Full), - __DEFINE_LINK_MODE_PARAMS(50000, SR, Full), - __DEFINE_LINK_MODE_PARAMS(50000, CR, Full), - __DEFINE_LINK_MODE_PARAMS(50000, LR_ER_FR, Full), - __DEFINE_LINK_MODE_PARAMS(50000, DR, Full), - __DEFINE_LINK_MODE_PARAMS(100000, KR2, Full), - __DEFINE_LINK_MODE_PARAMS(100000, SR2, Full), - __DEFINE_LINK_MODE_PARAMS(100000, CR2, Full), - __DEFINE_LINK_MODE_PARAMS(100000, LR2_ER2_FR2, Full), - __DEFINE_LINK_MODE_PARAMS(100000, DR2, Full), - __DEFINE_LINK_MODE_PARAMS(200000, KR4, Full), - __DEFINE_LINK_MODE_PARAMS(200000, SR4, Full), - __DEFINE_LINK_MODE_PARAMS(200000, LR4_ER4_FR4, Full), - __DEFINE_LINK_MODE_PARAMS(200000, DR4, Full), - __DEFINE_LINK_MODE_PARAMS(200000, CR4, Full), - __DEFINE_LINK_MODE_PARAMS(100, T1, Full), - __DEFINE_LINK_MODE_PARAMS(1000, T1, Full), - __DEFINE_LINK_MODE_PARAMS(400000, KR8, Full), - __DEFINE_LINK_MODE_PARAMS(400000, SR8, Full), - __DEFINE_LINK_MODE_PARAMS(400000, LR8_ER8_FR8, Full), - __DEFINE_LINK_MODE_PARAMS(400000, DR8, Full), - __DEFINE_LINK_MODE_PARAMS(400000, CR8, Full), - __DEFINE_SPECIAL_MODE_PARAMS(FEC_LLRS), - __DEFINE_LINK_MODE_PARAMS(100000, KR, Full), - __DEFINE_LINK_MODE_PARAMS(100000, SR, Full), - __DEFINE_LINK_MODE_PARAMS(100000, LR_ER_FR, Full), - __DEFINE_LINK_MODE_PARAMS(100000, DR, Full), - __DEFINE_LINK_MODE_PARAMS(100000, CR, Full), - __DEFINE_LINK_MODE_PARAMS(200000, KR2, Full), - __DEFINE_LINK_MODE_PARAMS(200000, SR2, Full), - __DEFINE_LINK_MODE_PARAMS(200000, LR2_ER2_FR2, Full), - __DEFINE_LINK_MODE_PARAMS(200000, DR2, Full), - __DEFINE_LINK_MODE_PARAMS(200000, CR2, Full), - __DEFINE_LINK_MODE_PARAMS(400000, KR4, Full), - __DEFINE_LINK_MODE_PARAMS(400000, SR4, Full), - __DEFINE_LINK_MODE_PARAMS(400000, LR4_ER4_FR4, Full), - __DEFINE_LINK_MODE_PARAMS(400000, DR4, Full), - __DEFINE_LINK_MODE_PARAMS(400000, CR4, Full), - __DEFINE_LINK_MODE_PARAMS(100, FX, Half), - __DEFINE_LINK_MODE_PARAMS(100, FX, Full), -}; - const struct nla_policy ethnl_linkmodes_set_policy[] = { [ETHTOOL_A_LINKMODES_HEADER] = NLA_POLICY_NESTED(ethnl_header_policy), @@ -274,25 +168,23 @@ const struct nla_policy ethnl_linkmodes_set_policy[] = { [ETHTOOL_A_LINKMODES_SPEED] = { .type = NLA_U32 }, [ETHTOOL_A_LINKMODES_DUPLEX] = { .type = NLA_U8 }, [ETHTOOL_A_LINKMODES_MASTER_SLAVE_CFG] = { .type = NLA_U8 }, + [ETHTOOL_A_LINKMODES_LANES] = NLA_POLICY_RANGE(NLA_U32, 1, 8), }; -/* Set advertised link modes to all supported modes matching requested speed - * and duplex values. Called when autonegotiation is on, speed or duplex is - * requested but no link mode change. This is done in userspace with ioctl() - * interface, move it into kernel for netlink. +/* Set advertised link modes to all supported modes matching requested speed, + * lanes and duplex values. Called when autonegotiation is on, speed, lanes or + * duplex is requested but no link mode change. This is done in userspace with + * ioctl() interface, move it into kernel for netlink. * Returns true if advertised modes bitmap was modified. */ static bool ethnl_auto_linkmodes(struct ethtool_link_ksettings *ksettings, - bool req_speed, bool req_duplex) + bool req_speed, bool req_lanes, bool req_duplex) { unsigned long *advertising = ksettings->link_modes.advertising; unsigned long *supported = ksettings->link_modes.supported; DECLARE_BITMAP(old_adv, __ETHTOOL_LINK_MODE_MASK_NBITS); unsigned int i; - BUILD_BUG_ON(ARRAY_SIZE(link_mode_params) != - __ETHTOOL_LINK_MODE_MASK_NBITS); - bitmap_copy(old_adv, advertising, __ETHTOOL_LINK_MODE_MASK_NBITS); for (i = 0; i < __ETHTOOL_LINK_MODE_MASK_NBITS; i++) { @@ -302,6 +194,7 @@ static bool ethnl_auto_linkmodes(struct ethtool_link_ksettings *ksettings, continue; if (test_bit(i, supported) && (!req_speed || info->speed == ksettings->base.speed) && + (!req_lanes || info->lanes == ksettings->lanes) && (!req_duplex || info->duplex == ksettings->base.duplex)) set_bit(i, advertising); else @@ -325,38 +218,72 @@ static bool ethnl_validate_master_slave_cfg(u8 cfg) return false; } +static int ethnl_check_linkmodes(struct genl_info *info, struct nlattr **tb) +{ + const struct nlattr *master_slave_cfg, *lanes_cfg; + + master_slave_cfg = tb[ETHTOOL_A_LINKMODES_MASTER_SLAVE_CFG]; + if (master_slave_cfg && + !ethnl_validate_master_slave_cfg(nla_get_u8(master_slave_cfg))) { + NL_SET_ERR_MSG_ATTR(info->extack, master_slave_cfg, + "master/slave value is invalid"); + return -EOPNOTSUPP; + } + + lanes_cfg = tb[ETHTOOL_A_LINKMODES_LANES]; + if (lanes_cfg && !is_power_of_2(nla_get_u32(lanes_cfg))) { + NL_SET_ERR_MSG_ATTR(info->extack, lanes_cfg, + "lanes value is invalid"); + return -EINVAL; + } + + return 0; +} + static int ethnl_update_linkmodes(struct genl_info *info, struct nlattr **tb, struct ethtool_link_ksettings *ksettings, - bool *mod) + bool *mod, const struct net_device *dev) { struct ethtool_link_settings *lsettings = &ksettings->base; - bool req_speed, req_duplex; - const struct nlattr *master_slave_cfg; + bool req_speed, req_lanes, req_duplex; + const struct nlattr *master_slave_cfg, *lanes_cfg; int ret; master_slave_cfg = tb[ETHTOOL_A_LINKMODES_MASTER_SLAVE_CFG]; if (master_slave_cfg) { - u8 cfg = nla_get_u8(master_slave_cfg); - if (lsettings->master_slave_cfg == MASTER_SLAVE_CFG_UNSUPPORTED) { NL_SET_ERR_MSG_ATTR(info->extack, master_slave_cfg, "master/slave configuration not supported by device"); return -EOPNOTSUPP; } - - if (!ethnl_validate_master_slave_cfg(cfg)) { - NL_SET_ERR_MSG_ATTR(info->extack, master_slave_cfg, - "master/slave value is invalid"); - return -EOPNOTSUPP; - } } *mod = false; req_speed = tb[ETHTOOL_A_LINKMODES_SPEED]; + req_lanes = tb[ETHTOOL_A_LINKMODES_LANES]; req_duplex = tb[ETHTOOL_A_LINKMODES_DUPLEX]; ethnl_update_u8(&lsettings->autoneg, tb[ETHTOOL_A_LINKMODES_AUTONEG], mod); + + lanes_cfg = tb[ETHTOOL_A_LINKMODES_LANES]; + if (lanes_cfg) { + /* If autoneg is off and lanes parameter is not supported by the + * driver, return an error. + */ + if (!lsettings->autoneg && + !dev->ethtool_ops->cap_link_lanes_supported) { + NL_SET_ERR_MSG_ATTR(info->extack, lanes_cfg, + "lanes configuration not supported by device"); + return -EOPNOTSUPP; + } + } else if (!lsettings->autoneg) { + /* If autoneg is off and lanes parameter is not passed from user, + * set the lanes parameter to 0. + */ + ksettings->lanes = 0; + } + ret = ethnl_update_bitset(ksettings->link_modes.advertising, __ETHTOOL_LINK_MODE_MASK_NBITS, tb[ETHTOOL_A_LINKMODES_OURS], link_mode_names, @@ -365,13 +292,14 @@ static int ethnl_update_linkmodes(struct genl_info *info, struct nlattr **tb, return ret; ethnl_update_u32(&lsettings->speed, tb[ETHTOOL_A_LINKMODES_SPEED], mod); + ethnl_update_u32(&ksettings->lanes, lanes_cfg, mod); ethnl_update_u8(&lsettings->duplex, tb[ETHTOOL_A_LINKMODES_DUPLEX], mod); ethnl_update_u8(&lsettings->master_slave_cfg, master_slave_cfg, mod); if (!tb[ETHTOOL_A_LINKMODES_OURS] && lsettings->autoneg && - (req_speed || req_duplex) && - ethnl_auto_linkmodes(ksettings, req_speed, req_duplex)) + (req_speed || req_lanes || req_duplex) && + ethnl_auto_linkmodes(ksettings, req_speed, req_lanes, req_duplex)) *mod = true; return 0; @@ -386,6 +314,10 @@ int ethnl_set_linkmodes(struct sk_buff *skb, struct genl_info *info) bool mod = false; int ret; + ret = ethnl_check_linkmodes(info, tb); + if (ret < 0) + return ret; + ret = ethnl_parse_header_dev_get(&req_info, tb[ETHTOOL_A_LINKMODES_HEADER], genl_info_net(info), info->extack, @@ -409,7 +341,7 @@ int ethnl_set_linkmodes(struct sk_buff *skb, struct genl_info *info) goto out_ops; } - ret = ethnl_update_linkmodes(info, tb, &ksettings, &mod); + ret = ethnl_update_linkmodes(info, tb, &ksettings, &mod, dev); if (ret < 0) goto out_ops; diff --git a/net/ethtool/netlink.h b/net/ethtool/netlink.h index d8efec516d86..6eabd58d81bf 100644 --- a/net/ethtool/netlink.h +++ b/net/ethtool/netlink.h @@ -351,7 +351,7 @@ extern const struct nla_policy ethnl_strset_get_policy[ETHTOOL_A_STRSET_COUNTS_O extern const struct nla_policy ethnl_linkinfo_get_policy[ETHTOOL_A_LINKINFO_HEADER + 1]; extern const struct nla_policy ethnl_linkinfo_set_policy[ETHTOOL_A_LINKINFO_TP_MDIX_CTRL + 1]; extern const struct nla_policy ethnl_linkmodes_get_policy[ETHTOOL_A_LINKMODES_HEADER + 1]; -extern const struct nla_policy ethnl_linkmodes_set_policy[ETHTOOL_A_LINKMODES_MASTER_SLAVE_CFG + 1]; +extern const struct nla_policy ethnl_linkmodes_set_policy[ETHTOOL_A_LINKMODES_LANES + 1]; extern const struct nla_policy ethnl_linkstate_get_policy[ETHTOOL_A_LINKSTATE_HEADER + 1]; extern const struct nla_policy ethnl_debug_get_policy[ETHTOOL_A_DEBUG_HEADER + 1]; extern const struct nla_policy ethnl_debug_set_policy[ETHTOOL_A_DEBUG_MSGMASK + 1]; diff --git a/net/hsr/hsr_device.c b/net/hsr/hsr_device.c index ab953a1a0d6c..7444ec6e298e 100644 --- a/net/hsr/hsr_device.c +++ b/net/hsr/hsr_device.c @@ -230,7 +230,7 @@ static const struct header_ops hsr_header_ops = { .parse = eth_header_parse, }; -static struct sk_buff *hsr_init_skb(struct hsr_port *master, u16 proto) +static struct sk_buff *hsr_init_skb(struct hsr_port *master) { struct hsr_priv *hsr = master->hsr; struct sk_buff *skb; @@ -242,8 +242,7 @@ static struct sk_buff *hsr_init_skb(struct hsr_port *master, u16 proto) * being, for PRP it is a trailer and for HSR it is a * header */ - skb = dev_alloc_skb(sizeof(struct hsr_tag) + - sizeof(struct hsr_sup_tag) + + skb = dev_alloc_skb(sizeof(struct hsr_sup_tag) + sizeof(struct hsr_sup_payload) + hlen + tlen); if (!skb) @@ -251,10 +250,9 @@ static struct sk_buff *hsr_init_skb(struct hsr_port *master, u16 proto) skb_reserve(skb, hlen); skb->dev = master->dev; - skb->protocol = htons(proto); skb->priority = TC_PRIO_CONTROL; - if (dev_hard_header(skb, skb->dev, proto, + if (dev_hard_header(skb, skb->dev, ETH_P_PRP, hsr->sup_multicast_addr, skb->dev->dev_addr, skb->len) <= 0) goto out; @@ -275,12 +273,10 @@ static void send_hsr_supervision_frame(struct hsr_port *master, { struct hsr_priv *hsr = master->hsr; __u8 type = HSR_TLV_LIFE_CHECK; - struct hsr_tag *hsr_tag = NULL; struct hsr_sup_payload *hsr_sp; struct hsr_sup_tag *hsr_stag; unsigned long irqflags; struct sk_buff *skb; - u16 proto; *interval = msecs_to_jiffies(HSR_LIFE_CHECK_INTERVAL); if (hsr->announce_count < 3 && hsr->prot_version == 0) { @@ -289,23 +285,12 @@ static void send_hsr_supervision_frame(struct hsr_port *master, hsr->announce_count++; } - if (!hsr->prot_version) - proto = ETH_P_PRP; - else - proto = ETH_P_HSR; - - skb = hsr_init_skb(master, proto); + skb = hsr_init_skb(master); if (!skb) { WARN_ONCE(1, "HSR: Could not send supervision frame\n"); return; } - if (hsr->prot_version > 0) { - hsr_tag = skb_put(skb, sizeof(struct hsr_tag)); - hsr_tag->encap_proto = htons(ETH_P_PRP); - set_hsr_tag_LSDU_size(hsr_tag, HSR_V1_SUP_LSDUSIZE); - } - hsr_stag = skb_put(skb, sizeof(struct hsr_sup_tag)); set_hsr_stag_path(hsr_stag, (hsr->prot_version ? 0x0 : 0xf)); set_hsr_stag_HSR_ver(hsr_stag, hsr->prot_version); @@ -315,8 +300,6 @@ static void send_hsr_supervision_frame(struct hsr_port *master, if (hsr->prot_version > 0) { hsr_stag->sequence_nr = htons(hsr->sup_sequence_nr); hsr->sup_sequence_nr++; - hsr_tag->sequence_nr = htons(hsr->sequence_nr); - hsr->sequence_nr++; } else { hsr_stag->sequence_nr = htons(hsr->sequence_nr); hsr->sequence_nr++; @@ -332,7 +315,7 @@ static void send_hsr_supervision_frame(struct hsr_port *master, hsr_sp = skb_put(skb, sizeof(struct hsr_sup_payload)); ether_addr_copy(hsr_sp->macaddress_A, master->dev->dev_addr); - if (skb_put_padto(skb, ETH_ZLEN + HSR_HLEN)) + if (skb_put_padto(skb, ETH_ZLEN)) return; hsr_forward_skb(skb, master); @@ -348,10 +331,8 @@ static void send_prp_supervision_frame(struct hsr_port *master, struct hsr_sup_tag *hsr_stag; unsigned long irqflags; struct sk_buff *skb; - struct prp_rct *rct; - u8 *tail; - skb = hsr_init_skb(master, ETH_P_PRP); + skb = hsr_init_skb(master); if (!skb) { WARN_ONCE(1, "PRP: Could not send supervision frame\n"); return; @@ -373,17 +354,11 @@ static void send_prp_supervision_frame(struct hsr_port *master, hsr_sp = skb_put(skb, sizeof(struct hsr_sup_payload)); ether_addr_copy(hsr_sp->macaddress_A, master->dev->dev_addr); - if (skb_put_padto(skb, ETH_ZLEN + HSR_HLEN)) { + if (skb_put_padto(skb, ETH_ZLEN)) { spin_unlock_irqrestore(&master->hsr->seqnr_lock, irqflags); return; } - tail = skb_tail_pointer(skb) - HSR_HLEN; - rct = (struct prp_rct *)tail; - rct->PRP_suffix = htons(ETH_P_PRP); - set_prp_LSDU_size(rct, HSR_V1_SUP_LSDUSIZE); - rct->sequence_nr = htons(hsr->sequence_nr); - hsr->sequence_nr++; spin_unlock_irqrestore(&master->hsr->seqnr_lock, irqflags); hsr_forward_skb(skb, master); @@ -442,6 +417,7 @@ static struct hsr_proto_ops hsr_ops = { .send_sv_frame = send_hsr_supervision_frame, .create_tagged_frame = hsr_create_tagged_frame, .get_untagged_frame = hsr_get_untagged_frame, + .drop_frame = hsr_drop_frame, .fill_frame_info = hsr_fill_frame_info, .invalid_dan_ingress_frame = hsr_invalid_dan_ingress_frame, }; @@ -489,10 +465,11 @@ void hsr_dev_setup(struct net_device *dev) /* Return true if dev is a HSR master; return false otherwise. */ -inline bool is_hsr_master(struct net_device *dev) +bool is_hsr_master(struct net_device *dev) { return (dev->netdev_ops->ndo_start_xmit == hsr_dev_xmit); } +EXPORT_SYMBOL(is_hsr_master); /* Default multicast address for HSR Supervision frames */ static const unsigned char def_multicast_addr[ETH_ALEN] __aligned(2) = { @@ -545,16 +522,6 @@ int hsr_dev_finalize(struct net_device *hsr_dev, struct net_device *slave[2], hsr->prot_version = protocol_version; - /* FIXME: should I modify the value of these? - * - * - hsr_dev->flags - i.e. - * IFF_MASTER/SLAVE? - * - hsr_dev->priv_flags - i.e. - * IFF_EBRIDGE? - * IFF_TX_SKB_SHARING? - * IFF_HSR_MASTER/SLAVE? - */ - /* Make sure the 1st call to netif_carrier_on() gets through */ netif_carrier_off(hsr_dev); diff --git a/net/hsr/hsr_device.h b/net/hsr/hsr_device.h index 868373822ee4..9060c92168f9 100644 --- a/net/hsr/hsr_device.h +++ b/net/hsr/hsr_device.h @@ -19,6 +19,5 @@ int hsr_dev_finalize(struct net_device *hsr_dev, struct net_device *slave[2], unsigned char multicast_spec, u8 protocol_version, struct netlink_ext_ack *extack); void hsr_check_carrier_and_operstate(struct hsr_priv *hsr); -bool is_hsr_master(struct net_device *dev); int hsr_get_max_mtu(struct hsr_priv *hsr); #endif /* __HSR_DEVICE_H */ diff --git a/net/hsr/hsr_forward.c b/net/hsr/hsr_forward.c index cadfccd7876e..ed82a470b6e1 100644 --- a/net/hsr/hsr_forward.c +++ b/net/hsr/hsr_forward.c @@ -186,6 +186,7 @@ static struct sk_buff *prp_fill_rct(struct sk_buff *skb, set_prp_LSDU_size(trailer, lsdu_size); trailer->sequence_nr = htons(frame->sequence_nr); trailer->PRP_suffix = htons(ETH_P_PRP); + skb->protocol = eth_hdr(skb)->h_proto; return skb; } @@ -226,6 +227,7 @@ static struct sk_buff *hsr_fill_tag(struct sk_buff *skb, hsr_ethhdr->hsr_tag.encap_proto = hsr_ethhdr->ethhdr.h_proto; hsr_ethhdr->ethhdr.h_proto = htons(proto_version ? ETH_P_HSR : ETH_P_PRP); + skb->protocol = hsr_ethhdr->ethhdr.h_proto; return skb; } @@ -247,6 +249,8 @@ struct sk_buff *hsr_create_tagged_frame(struct hsr_frame_info *frame, /* set the lane id properly */ hsr_set_path_id(hsr_ethhdr, port); return skb_clone(frame->skb_hsr, GFP_ATOMIC); + } else if (port->dev->features & NETIF_F_HW_HSR_TAG_INS) { + return skb_clone(frame->skb_std, GFP_ATOMIC); } /* Create the new skb with enough headroom to fit the HSR tag */ @@ -289,6 +293,8 @@ struct sk_buff *prp_create_tagged_frame(struct hsr_frame_info *frame, return NULL; } return skb_clone(frame->skb_prp, GFP_ATOMIC); + } else if (port->dev->features & NETIF_F_HW_HSR_TAG_INS) { + return skb_clone(frame->skb_std, GFP_ATOMIC); } skb = skb_copy_expand(frame->skb_std, 0, @@ -341,6 +347,14 @@ bool prp_drop_frame(struct hsr_frame_info *frame, struct hsr_port *port) port->type == HSR_PT_SLAVE_A)); } +bool hsr_drop_frame(struct hsr_frame_info *frame, struct hsr_port *port) +{ + if (port->dev->features & NETIF_F_HW_HSR_FWD) + return prp_drop_frame(frame, port); + + return false; +} + /* Forward the frame through all devices except: * - Back through the receiving device * - If it's a HSR frame: through a device where it has passed before @@ -357,6 +371,7 @@ static void hsr_forward_do(struct hsr_frame_info *frame) { struct hsr_port *port; struct sk_buff *skb; + bool sent = false; hsr_for_each_port(frame->port_rcv->hsr, port) { struct hsr_priv *hsr = port->hsr; @@ -372,6 +387,12 @@ static void hsr_forward_do(struct hsr_frame_info *frame) if (port->type != HSR_PT_MASTER && frame->is_local_exclusive) continue; + /* If hardware duplicate generation is enabled, only send out + * one port. + */ + if ((port->dev->features & NETIF_F_HW_HSR_DUP) && sent) + continue; + /* Don't send frame over port where it has been sent before. * Also fro SAN, this shouldn't be done. */ @@ -403,10 +424,12 @@ static void hsr_forward_do(struct hsr_frame_info *frame) } skb->dev = port->dev; - if (port->type == HSR_PT_MASTER) + if (port->type == HSR_PT_MASTER) { hsr_deliver_master(skb, port->dev, frame->node_src); - else - hsr_xmit(skb, port, frame); + } else { + if (!hsr_xmit(skb, port, frame)) + sent = true; + } } } @@ -454,7 +477,11 @@ static void handle_std_frame(struct sk_buff *skb, void hsr_fill_frame_info(__be16 proto, struct sk_buff *skb, struct hsr_frame_info *frame) { - if (proto == htons(ETH_P_PRP) || + struct hsr_port *port = frame->port_rcv; + struct hsr_priv *hsr = port->hsr; + + /* HSRv0 supervisory frames double as a tag so treat them as tagged. */ + if ((!hsr->prot_version && proto == htons(ETH_P_PRP)) || proto == htons(ETH_P_HSR)) { /* HSR tagged frame :- Data or Supervision */ frame->skb_std = NULL; diff --git a/net/hsr/hsr_forward.h b/net/hsr/hsr_forward.h index 618140d484ad..b6acaafa83fc 100644 --- a/net/hsr/hsr_forward.h +++ b/net/hsr/hsr_forward.h @@ -23,6 +23,7 @@ struct sk_buff *hsr_get_untagged_frame(struct hsr_frame_info *frame, struct sk_buff *prp_get_untagged_frame(struct hsr_frame_info *frame, struct hsr_port *port); bool prp_drop_frame(struct hsr_frame_info *frame, struct hsr_port *port); +bool hsr_drop_frame(struct hsr_frame_info *frame, struct hsr_port *port); void prp_fill_frame_info(__be16 proto, struct sk_buff *skb, struct hsr_frame_info *frame); void hsr_fill_frame_info(__be16 proto, struct sk_buff *skb, diff --git a/net/hsr/hsr_framereg.c b/net/hsr/hsr_framereg.c index 5c97de459905..f9a8cc82ae2e 100644 --- a/net/hsr/hsr_framereg.c +++ b/net/hsr/hsr_framereg.c @@ -277,6 +277,8 @@ void hsr_handle_sup_frame(struct hsr_frame_info *frame) skb = frame->skb_hsr; else if (frame->skb_prp) skb = frame->skb_prp; + else if (frame->skb_std) + skb = frame->skb_std; if (!skb) return; diff --git a/net/hsr/hsr_main.c b/net/hsr/hsr_main.c index 2fd1976e5b1c..f7e284f23b1f 100644 --- a/net/hsr/hsr_main.c +++ b/net/hsr/hsr_main.c @@ -131,6 +131,17 @@ struct hsr_port *hsr_port_get_hsr(struct hsr_priv *hsr, enum hsr_port_type pt) return NULL; } +int hsr_get_version(struct net_device *dev, enum hsr_version *ver) +{ + struct hsr_priv *hsr; + + hsr = netdev_priv(dev); + *ver = hsr->prot_version; + + return 0; +} +EXPORT_SYMBOL(hsr_get_version); + static struct notifier_block hsr_nb = { .notifier_call = hsr_netdev_notify, /* Slave event notifications */ }; diff --git a/net/hsr/hsr_main.h b/net/hsr/hsr_main.h index a9c30a608e35..a169808ee78a 100644 --- a/net/hsr/hsr_main.h +++ b/net/hsr/hsr_main.h @@ -13,6 +13,7 @@ #include <linux/netdevice.h> #include <linux/list.h> #include <linux/if_vlan.h> +#include <linux/if_hsr.h> /* Time constants as specified in the HSR specification (IEC-62439-3 2010) * Table 8. @@ -171,13 +172,6 @@ struct hsr_port { enum hsr_port_type type; }; -/* used by driver internally to differentiate various protocols */ -enum hsr_version { - HSR_V0 = 0, - HSR_V1, - PRP_V1, -}; - struct hsr_frame_info; struct hsr_node; diff --git a/net/hsr/hsr_slave.c b/net/hsr/hsr_slave.c index 36d5fcf09c61..c5227d42faf5 100644 --- a/net/hsr/hsr_slave.c +++ b/net/hsr/hsr_slave.c @@ -48,12 +48,14 @@ static rx_handler_result_t hsr_handle_frame(struct sk_buff **pskb) goto finish_consume; } - /* For HSR, only tagged frames are expected, but for PRP - * there could be non tagged frames as well from Single - * attached nodes (SANs). + /* For HSR, only tagged frames are expected (unless the device offloads + * HSR tag removal), but for PRP there could be non tagged frames as + * well from Single attached nodes (SANs). */ protocol = eth_hdr(skb)->h_proto; - if (hsr->proto_ops->invalid_dan_ingress_frame && + + if (!(port->dev->features & NETIF_F_HW_HSR_TAG_RM) && + hsr->proto_ops->invalid_dan_ingress_frame && hsr->proto_ops->invalid_dan_ingress_frame(protocol)) goto finish_pass; diff --git a/net/ife/Kconfig b/net/ife/Kconfig index bcf650564db4..de36a5b91e50 100644 --- a/net/ife/Kconfig +++ b/net/ife/Kconfig @@ -4,7 +4,6 @@ # menuconfig NET_IFE - depends on NET tristate "Inter-FE based on IETF ForCES InterFE LFB" default n help diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index b94fa8eb831b..a02ce89b56b5 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -438,6 +438,7 @@ EXPORT_SYMBOL(inet_release); int inet_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) { struct sock *sk = sock->sk; + u32 flags = BIND_WITH_LOCK; int err; /* If the socket has its own bind function then use it. (RAW) */ @@ -450,11 +451,12 @@ int inet_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) /* BPF prog is run before any checks are done so that if the prog * changes context in a wrong way it will be caught. */ - err = BPF_CGROUP_RUN_PROG_INET4_BIND_LOCK(sk, uaddr); + err = BPF_CGROUP_RUN_PROG_INET_BIND_LOCK(sk, uaddr, + BPF_CGROUP_INET4_BIND, &flags); if (err) return err; - return __inet_bind(sk, uaddr, addr_len, BIND_WITH_LOCK); + return __inet_bind(sk, uaddr, addr_len, flags); } EXPORT_SYMBOL(inet_bind); @@ -499,7 +501,8 @@ int __inet_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len, snum = ntohs(addr->sin_port); err = -EACCES; - if (snum && inet_port_requires_bind_service(net, snum) && + if (!(flags & BIND_NO_CAP_NET_BIND_SERVICE) && + snum && inet_port_requires_bind_service(net, snum) && !ns_capable(net->user_ns, CAP_NET_BIND_SERVICE)) goto out; @@ -777,18 +780,19 @@ int inet_getname(struct socket *sock, struct sockaddr *uaddr, return -ENOTCONN; sin->sin_port = inet->inet_dport; sin->sin_addr.s_addr = inet->inet_daddr; + BPF_CGROUP_RUN_SA_PROG_LOCK(sk, (struct sockaddr *)sin, + BPF_CGROUP_INET4_GETPEERNAME, + NULL); } else { __be32 addr = inet->inet_rcv_saddr; if (!addr) addr = inet->inet_saddr; sin->sin_port = inet->inet_sport; sin->sin_addr.s_addr = addr; - } - if (cgroup_bpf_enabled) BPF_CGROUP_RUN_SA_PROG_LOCK(sk, (struct sockaddr *)sin, - peer ? BPF_CGROUP_INET4_GETPEERNAME : - BPF_CGROUP_INET4_GETSOCKNAME, + BPF_CGROUP_INET4_GETSOCKNAME, NULL); + } memset(sin->sin_zero, 0, sizeof(sin->sin_zero)); return sizeof(*sin); } @@ -1419,7 +1423,6 @@ struct sk_buff *inet_gso_segment(struct sk_buff *skb, out: return segs; } -EXPORT_SYMBOL(inet_gso_segment); static struct sk_buff *ipip_gso_segment(struct sk_buff *skb, netdev_features_t features) @@ -1550,7 +1553,6 @@ out: return pp; } -EXPORT_SYMBOL(inet_gro_receive); static struct sk_buff *ipip_gro_receive(struct list_head *head, struct sk_buff *skb) @@ -1636,7 +1638,6 @@ out_unlock: return err; } -EXPORT_SYMBOL(inet_gro_complete); static int ipip_gro_complete(struct sk_buff *skb, int nhoff) { @@ -1871,6 +1872,8 @@ static __net_init int inet_init_net(struct net *net) net->ipv4.sysctl_igmp_llm_reports = 1; net->ipv4.sysctl_igmp_qrv = 2; + net->ipv4.sysctl_fib_notify_on_flag_change = 0; + return 0; } diff --git a/net/ipv4/esp4_offload.c b/net/ipv4/esp4_offload.c index 5bda5aeda579..601f5fbfc63f 100644 --- a/net/ipv4/esp4_offload.c +++ b/net/ipv4/esp4_offload.c @@ -285,7 +285,7 @@ static int esp_xmit(struct xfrm_state *x, struct sk_buff *skb, netdev_features_ esp.esph = ip_esp_hdr(skb); - if (!hw_offload || (hw_offload && !skb_is_gso(skb))) { + if (!hw_offload || !skb_is_gso(skb)) { esp.nfrags = esp_output_head(x, skb, &esp); if (esp.nfrags < 0) return esp.nfrags; diff --git a/net/ipv4/fib_lookup.h b/net/ipv4/fib_lookup.h index 818916b2a04d..b58db1ca4bfb 100644 --- a/net/ipv4/fib_lookup.h +++ b/net/ipv4/fib_lookup.h @@ -18,7 +18,8 @@ struct fib_alias { s16 fa_default; u8 offload:1, trap:1, - unused:6; + offload_failed:1, + unused:5; struct rcu_head rcu; }; @@ -39,9 +40,10 @@ int fib_nh_match(struct net *net, struct fib_config *cfg, struct fib_info *fi, struct netlink_ext_ack *extack); bool fib_metrics_match(struct fib_config *cfg, struct fib_info *fi); int fib_dump_info(struct sk_buff *skb, u32 pid, u32 seq, int event, - struct fib_rt_info *fri, unsigned int flags); + const struct fib_rt_info *fri, unsigned int flags); void rtmsg_fib(int event, __be32 key, struct fib_alias *fa, int dst_len, u32 tb_id, const struct nl_info *info, unsigned int nlm_flags); +size_t fib_nlmsg_size(struct fib_info *fi); static inline void fib_result_assign(struct fib_result *res, struct fib_info *fi) diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c index b5400cec4f69..a632b66bc13a 100644 --- a/net/ipv4/fib_semantics.c +++ b/net/ipv4/fib_semantics.c @@ -452,7 +452,7 @@ int ip_fib_check_default(__be32 gw, struct net_device *dev) return -1; } -static inline size_t fib_nlmsg_size(struct fib_info *fi) +size_t fib_nlmsg_size(struct fib_info *fi) { size_t payload = NLMSG_ALIGN(sizeof(struct rtmsg)) + nla_total_size(4) /* RTA_TABLE */ @@ -521,6 +521,7 @@ void rtmsg_fib(int event, __be32 key, struct fib_alias *fa, fri.type = fa->fa_type; fri.offload = fa->offload; fri.trap = fa->trap; + fri.offload_failed = fa->offload_failed; err = fib_dump_info(skb, info->portid, seq, event, &fri, nlm_flags); if (err < 0) { /* -EMSGSIZE implies BUG in fib_nlmsg_size() */ @@ -1733,7 +1734,7 @@ static int fib_add_multipath(struct sk_buff *skb, struct fib_info *fi) #endif int fib_dump_info(struct sk_buff *skb, u32 portid, u32 seq, int event, - struct fib_rt_info *fri, unsigned int flags) + const struct fib_rt_info *fri, unsigned int flags) { unsigned int nhs = fib_info_num_path(fri->fi); struct fib_info *fi = fri->fi; @@ -1811,6 +1812,8 @@ offload: rtm->rtm_flags |= RTM_F_OFFLOAD; if (fri->trap) rtm->rtm_flags |= RTM_F_TRAP; + if (fri->offload_failed) + rtm->rtm_flags |= RTM_F_OFFLOAD_FAILED; nlmsg_end(skb, nlh); return 0; diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c index 28117c05dc35..25cf387cca5b 100644 --- a/net/ipv4/fib_trie.c +++ b/net/ipv4/fib_trie.c @@ -1038,6 +1038,8 @@ fib_find_matching_alias(struct net *net, const struct fib_rt_info *fri) void fib_alias_hw_flags_set(struct net *net, const struct fib_rt_info *fri) { struct fib_alias *fa_match; + struct sk_buff *skb; + int err; rcu_read_lock(); @@ -1045,9 +1047,42 @@ void fib_alias_hw_flags_set(struct net *net, const struct fib_rt_info *fri) if (!fa_match) goto out; + if (fa_match->offload == fri->offload && fa_match->trap == fri->trap && + fa_match->offload_failed == fri->offload_failed) + goto out; + fa_match->offload = fri->offload; fa_match->trap = fri->trap; + /* 2 means send notifications only if offload_failed was changed. */ + if (net->ipv4.sysctl_fib_notify_on_flag_change == 2 && + fa_match->offload_failed == fri->offload_failed) + goto out; + + fa_match->offload_failed = fri->offload_failed; + + if (!net->ipv4.sysctl_fib_notify_on_flag_change) + goto out; + + skb = nlmsg_new(fib_nlmsg_size(fa_match->fa_info), GFP_ATOMIC); + if (!skb) { + err = -ENOBUFS; + goto errout; + } + + err = fib_dump_info(skb, 0, 0, RTM_NEWROUTE, fri, 0); + if (err < 0) { + /* -EMSGSIZE implies BUG in fib_nlmsg_size() */ + WARN_ON(err == -EMSGSIZE); + kfree_skb(skb); + goto errout; + } + + rtnl_notify(skb, net, 0, RTNLGRP_IPV4_ROUTE, NULL, GFP_ATOMIC); + goto out; + +errout: + rtnl_set_sk_err(net, RTNLGRP_IPV4_ROUTE, err); out: rcu_read_unlock(); } @@ -1263,6 +1298,7 @@ int fib_table_insert(struct net *net, struct fib_table *tb, new_fa->fa_default = -1; new_fa->offload = 0; new_fa->trap = 0; + new_fa->offload_failed = 0; hlist_replace_rcu(&fa->fa_list, &new_fa->fa_list); @@ -1323,6 +1359,7 @@ int fib_table_insert(struct net *net, struct fib_table *tb, new_fa->fa_default = -1; new_fa->offload = 0; new_fa->trap = 0; + new_fa->offload_failed = 0; /* Insert new entry to the list. */ err = fib_insert_alias(t, tp, l, new_fa, fa, key); @@ -2262,6 +2299,7 @@ static int fn_trie_dump_leaf(struct key_vector *l, struct fib_table *tb, fri.type = fa->fa_type; fri.offload = fa->offload; fri.trap = fa->trap; + fri.offload_failed = fa->offload_failed; err = fib_dump_info(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, diff --git a/net/ipv4/gre_offload.c b/net/ipv4/gre_offload.c index e0a246575887..1121a9d5fed9 100644 --- a/net/ipv4/gre_offload.c +++ b/net/ipv4/gre_offload.c @@ -15,7 +15,7 @@ static struct sk_buff *gre_gso_segment(struct sk_buff *skb, netdev_features_t features) { int tnl_hlen = skb_inner_mac_header(skb) - skb_transport_header(skb); - bool need_csum, need_recompute_csum, gso_partial; + bool need_csum, offload_csum, gso_partial, need_ipsec; struct sk_buff *segs = ERR_PTR(-EINVAL); u16 mac_offset = skb->mac_header; __be16 protocol = skb->protocol; @@ -41,10 +41,16 @@ static struct sk_buff *gre_gso_segment(struct sk_buff *skb, skb->protocol = skb->inner_protocol; need_csum = !!(skb_shinfo(skb)->gso_type & SKB_GSO_GRE_CSUM); - need_recompute_csum = skb->csum_not_inet; skb->encap_hdr_csum = need_csum; features &= skb->dev->hw_enc_features; + if (need_csum) + features &= ~NETIF_F_SCTP_CRC; + + need_ipsec = skb_dst(skb) && dst_xfrm(skb_dst(skb)); + /* Try to offload checksum if possible */ + offload_csum = !!(need_csum && !need_ipsec && + (skb->dev->features & NETIF_F_HW_CSUM)); /* segment inner packet. */ segs = skb_mac_gso_segment(skb, features); @@ -99,14 +105,12 @@ static struct sk_buff *gre_gso_segment(struct sk_buff *skb, } *(pcsum + 1) = 0; - if (need_recompute_csum && !skb_is_gso(skb)) { - __wsum csum; - - csum = skb_checksum(skb, gre_offset, - skb->len - gre_offset, 0); - *pcsum = csum_fold(csum); - } else { + if (skb->encapsulation || !offload_csum) { *pcsum = gso_make_checksum(skb, 0); + } else { + skb->ip_summed = CHECKSUM_PARTIAL; + skb->csum_start = skb_transport_header(skb) - skb->head; + skb->csum_offset = sizeof(*greh); } } while ((skb = skb->next)); out: diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c index 45fb450b4522..c96866a53a66 100644 --- a/net/ipv4/inet_hashtables.c +++ b/net/ipv4/inet_hashtables.c @@ -709,6 +709,17 @@ unlock: } EXPORT_SYMBOL_GPL(inet_unhash); +/* RFC 6056 3.3.4. Algorithm 4: Double-Hash Port Selection Algorithm + * Note that we use 32bit integers (vs RFC 'short integers') + * because 2^16 is not a multiple of num_ephemeral and this + * property might be used by clever attacker. + * RFC claims using TABLE_LENGTH=10 buckets gives an improvement, + * we use 256 instead to really give more isolation and + * privacy, this only consumes 1 KB of kernel memory. + */ +#define INET_TABLE_PERTURB_SHIFT 8 +static u32 table_perturb[1 << INET_TABLE_PERTURB_SHIFT]; + int __inet_hash_connect(struct inet_timewait_death_row *death_row, struct sock *sk, u32 port_offset, int (*check_established)(struct inet_timewait_death_row *, @@ -722,8 +733,8 @@ int __inet_hash_connect(struct inet_timewait_death_row *death_row, struct inet_bind_bucket *tb; u32 remaining, offset; int ret, i, low, high; - static u32 hint; int l3mdev; + u32 index; if (port) { head = &hinfo->bhash[inet_bhashfn(net, port, @@ -750,7 +761,10 @@ int __inet_hash_connect(struct inet_timewait_death_row *death_row, if (likely(remaining > 1)) remaining &= ~1U; - offset = (hint + port_offset) % remaining; + net_get_random_once(table_perturb, sizeof(table_perturb)); + index = hash_32(port_offset, INET_TABLE_PERTURB_SHIFT); + + offset = (READ_ONCE(table_perturb[index]) + port_offset) % remaining; /* In first pass we try ports of @low parity. * inet_csk_get_port() does the opposite choice. */ @@ -804,7 +818,12 @@ next_port: return -EADDRNOTAVAIL; ok: - hint += i + 2; + /* If our first attempt found a candidate, skip next candidate + * in 1/16 of cases to add some noise. + */ + if (!i && !(prandom_u32() % 16)) + i = 2; + WRITE_ONCE(table_perturb[index], READ_ONCE(table_perturb[index]) + i + 2); /* Head lock still held and bh's disabled */ inet_bind_hash(sk, tb, port); diff --git a/net/ipv4/ip_input.c b/net/ipv4/ip_input.c index b0c244af1e4d..3a025c011971 100644 --- a/net/ipv4/ip_input.c +++ b/net/ipv4/ip_input.c @@ -253,6 +253,7 @@ int ip_local_deliver(struct sk_buff *skb) net, NULL, skb, skb->dev, NULL, ip_local_deliver_finish); } +EXPORT_SYMBOL(ip_local_deliver); static inline bool ip_rcv_options(struct sk_buff *skb, struct net_device *dev) { diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index 2ed0b01f72f0..3aab53beb4ea 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -434,6 +434,7 @@ int ip_output(struct net *net, struct sock *sk, struct sk_buff *skb) ip_finish_output, !(IPCB(skb)->flags & IPSKB_REROUTED)); } +EXPORT_SYMBOL(ip_output); /* * copy saddr and daddr, possibly using 64bit load/stores @@ -1018,7 +1019,7 @@ static int __ip_append_data(struct sock *sk, csummode = CHECKSUM_PARTIAL; if (flags & MSG_ZEROCOPY && length && sock_flag(sk, SOCK_ZEROCOPY)) { - uarg = sock_zerocopy_realloc(sk, length, skb_zcopy(skb)); + uarg = msg_zerocopy_realloc(sk, length, skb_zcopy(skb)); if (!uarg) return -ENOBUFS; extra_uref = !skb_zcopy(skb); /* only ref on new uarg */ @@ -1230,8 +1231,7 @@ alloc_new_skb: error_efault: err = -EFAULT; error: - if (uarg) - sock_zerocopy_put_abort(uarg, extra_uref); + net_zcopy_put_abort(uarg, extra_uref); cork->length -= length; IP_INC_STATS(sock_net(sk), IPSTATS_MIB_OUTDISCARDS); refcount_add(wmem_alloc_delta, &sk->sk_wmem_alloc); diff --git a/net/ipv4/ip_tunnel_core.c b/net/ipv4/ip_tunnel_core.c index 7ca338fbe8ba..6b2dc7b2b612 100644 --- a/net/ipv4/ip_tunnel_core.c +++ b/net/ipv4/ip_tunnel_core.c @@ -222,7 +222,7 @@ static int iptunnel_pmtud_build_icmp(struct sk_buff *skb, int mtu) .code = ICMP_FRAG_NEEDED, .checksum = 0, .un.frag.__unused = 0, - .un.frag.mtu = ntohs(mtu), + .un.frag.mtu = htons(mtu), }; icmph->checksum = ip_compute_csum(icmph, len); skb_reset_transport_header(skb); @@ -245,7 +245,7 @@ static int iptunnel_pmtud_build_icmp(struct sk_buff *skb, int mtu) skb->ip_summed = CHECKSUM_NONE; - eth_header(skb, skb->dev, htons(eh.h_proto), eh.h_source, eh.h_dest, 0); + eth_header(skb, skb->dev, ntohs(eh.h_proto), eh.h_source, eh.h_dest, 0); skb_reset_mac_header(skb); return skb->len; @@ -338,7 +338,7 @@ static int iptunnel_pmtud_build_icmpv6(struct sk_buff *skb, int mtu) skb->ip_summed = CHECKSUM_NONE; - eth_header(skb, skb->dev, htons(eh.h_proto), eh.h_source, eh.h_dest, 0); + eth_header(skb, skb->dev, ntohs(eh.h_proto), eh.h_source, eh.h_dest, 0); skb_reset_mac_header(skb); return skb->len; @@ -583,8 +583,9 @@ static int ip_tun_parse_opts_erspan(struct nlattr *attr, static int ip_tun_parse_opts(struct nlattr *attr, struct ip_tunnel_info *info, struct netlink_ext_ack *extack) { - int err, rem, opt_len, opts_len = 0, type = 0; + int err, rem, opt_len, opts_len = 0; struct nlattr *nla; + __be16 type = 0; if (!attr) return 0; diff --git a/net/ipv4/ipconfig.c b/net/ipv4/ipconfig.c index 3cd13e1bc6a7..47db1bfdaaa0 100644 --- a/net/ipv4/ipconfig.c +++ b/net/ipv4/ipconfig.c @@ -61,7 +61,6 @@ #include <linux/export.h> #include <net/net_namespace.h> #include <net/arp.h> -#include <net/dsa.h> #include <net/ip.h> #include <net/ipconfig.h> #include <net/route.h> @@ -218,9 +217,9 @@ static int __init ic_open_devs(void) last = &ic_first_dev; rtnl_lock(); - /* bring loopback and DSA master network devices up first */ + /* bring loopback device up first */ for_each_netdev(&init_net, dev) { - if (!(dev->flags & IFF_LOOPBACK) && !netdev_uses_dsa(dev)) + if (!(dev->flags & IFF_LOOPBACK)) continue; if (dev_change_flags(dev, dev->flags | IFF_UP, NULL) < 0) pr_err("IP-Config: Failed to open %s\n", dev->name); @@ -305,17 +304,32 @@ have_carrier: return 0; } +/* Close all network interfaces except the one we've autoconfigured, and its + * lowers, in case it's a stacked virtual interface. + */ static void __init ic_close_devs(void) { + struct net_device *selected_dev = ic_dev->dev; struct ic_device *d, *next; struct net_device *dev; rtnl_lock(); next = ic_first_dev; while ((d = next)) { + bool bring_down = (d != ic_dev); + struct net_device *lower_dev; + struct list_head *iter; + next = d->next; dev = d->dev; - if (d != ic_dev && !netdev_uses_dsa(dev)) { + + netdev_for_each_lower_dev(selected_dev, lower_dev, iter) { + if (dev == lower_dev) { + bring_down = false; + break; + } + } + if (bring_down) { pr_debug("IP-Config: Downing %s\n", dev->name); dev_change_flags(dev, d->flags, NULL); } diff --git a/net/ipv4/netfilter/nft_dup_ipv4.c b/net/ipv4/netfilter/nft_dup_ipv4.c index bcdb37f86a94..aeb631760eb9 100644 --- a/net/ipv4/netfilter/nft_dup_ipv4.c +++ b/net/ipv4/netfilter/nft_dup_ipv4.c @@ -13,8 +13,8 @@ #include <net/netfilter/ipv4/nf_dup_ipv4.h> struct nft_dup_ipv4 { - enum nft_registers sreg_addr:8; - enum nft_registers sreg_dev:8; + u8 sreg_addr; + u8 sreg_dev; }; static void nft_dup_ipv4_eval(const struct nft_expr *expr, @@ -40,16 +40,16 @@ static int nft_dup_ipv4_init(const struct nft_ctx *ctx, if (tb[NFTA_DUP_SREG_ADDR] == NULL) return -EINVAL; - priv->sreg_addr = nft_parse_register(tb[NFTA_DUP_SREG_ADDR]); - err = nft_validate_register_load(priv->sreg_addr, sizeof(struct in_addr)); + err = nft_parse_register_load(tb[NFTA_DUP_SREG_ADDR], &priv->sreg_addr, + sizeof(struct in_addr)); if (err < 0) return err; - if (tb[NFTA_DUP_SREG_DEV] != NULL) { - priv->sreg_dev = nft_parse_register(tb[NFTA_DUP_SREG_DEV]); - return nft_validate_register_load(priv->sreg_dev, sizeof(int)); - } - return 0; + if (tb[NFTA_DUP_SREG_DEV]) + err = nft_parse_register_load(tb[NFTA_DUP_SREG_DEV], + &priv->sreg_dev, sizeof(int)); + + return err; } static int nft_dup_ipv4_dump(struct sk_buff *skb, const struct nft_expr *expr) diff --git a/net/ipv4/nexthop.c b/net/ipv4/nexthop.c index e53e43aef785..f1c6cbdb9e43 100644 --- a/net/ipv4/nexthop.c +++ b/net/ipv4/nexthop.c @@ -22,7 +22,7 @@ static void remove_nexthop(struct net *net, struct nexthop *nh, #define NH_DEV_HASHBITS 8 #define NH_DEV_HASHSIZE (1U << NH_DEV_HASHBITS) -static const struct nla_policy rtm_nh_policy[NHA_MAX + 1] = { +static const struct nla_policy rtm_nh_policy_new[] = { [NHA_ID] = { .type = NLA_U32 }, [NHA_GROUP] = { .type = NLA_BINARY }, [NHA_GROUP_TYPE] = { .type = NLA_U16 }, @@ -31,6 +31,15 @@ static const struct nla_policy rtm_nh_policy[NHA_MAX + 1] = { [NHA_GATEWAY] = { .type = NLA_BINARY }, [NHA_ENCAP_TYPE] = { .type = NLA_U16 }, [NHA_ENCAP] = { .type = NLA_NESTED }, + [NHA_FDB] = { .type = NLA_FLAG }, +}; + +static const struct nla_policy rtm_nh_policy_get[] = { + [NHA_ID] = { .type = NLA_U32 }, +}; + +static const struct nla_policy rtm_nh_policy_dump[] = { + [NHA_OIF] = { .type = NLA_U32 }, [NHA_GROUPS] = { .type = NLA_FLAG }, [NHA_MASTER] = { .type = NLA_U32 }, [NHA_FDB] = { .type = NLA_FLAG }, @@ -62,6 +71,7 @@ __nh_notifier_single_info_init(struct nh_notifier_single_info *nh_info, static int nh_notifier_single_info_init(struct nh_notifier_info *info, const struct nexthop *nh) { + info->type = NH_NOTIFIER_INFO_TYPE_SINGLE; info->nh = kzalloc(sizeof(*info->nh), GFP_KERNEL); if (!info->nh) return -ENOMEM; @@ -76,13 +86,13 @@ static void nh_notifier_single_info_fini(struct nh_notifier_info *info) kfree(info->nh); } -static int nh_notifier_grp_info_init(struct nh_notifier_info *info, - const struct nexthop *nh) +static int nh_notifier_mp_info_init(struct nh_notifier_info *info, + struct nh_group *nhg) { - struct nh_group *nhg = rtnl_dereference(nh->nh_grp); u16 num_nh = nhg->num_nh; int i; + info->type = NH_NOTIFIER_INFO_TYPE_GRP; info->nh_grp = kzalloc(struct_size(info->nh_grp, nh_entries, num_nh), GFP_KERNEL); if (!info->nh_grp) @@ -103,27 +113,41 @@ static int nh_notifier_grp_info_init(struct nh_notifier_info *info, return 0; } -static void nh_notifier_grp_info_fini(struct nh_notifier_info *info) +static int nh_notifier_grp_info_init(struct nh_notifier_info *info, + const struct nexthop *nh) +{ + struct nh_group *nhg = rtnl_dereference(nh->nh_grp); + + if (nhg->mpath) + return nh_notifier_mp_info_init(info, nhg); + return -EINVAL; +} + +static void nh_notifier_grp_info_fini(struct nh_notifier_info *info, + const struct nexthop *nh) { - kfree(info->nh_grp); + struct nh_group *nhg = rtnl_dereference(nh->nh_grp); + + if (nhg->mpath) + kfree(info->nh_grp); } static int nh_notifier_info_init(struct nh_notifier_info *info, const struct nexthop *nh) { info->id = nh->id; - info->is_grp = nh->is_group; - if (info->is_grp) + if (nh->is_group) return nh_notifier_grp_info_init(info, nh); else return nh_notifier_single_info_init(info, nh); } -static void nh_notifier_info_fini(struct nh_notifier_info *info) +static void nh_notifier_info_fini(struct nh_notifier_info *info, + const struct nexthop *nh) { - if (info->is_grp) - nh_notifier_grp_info_fini(info); + if (nh->is_group) + nh_notifier_grp_info_fini(info, nh); else nh_notifier_single_info_fini(info); } @@ -152,7 +176,7 @@ static int call_nexthop_notifiers(struct net *net, err = blocking_notifier_call_chain(&net->nexthop.notifier_chain, event_type, &info); - nh_notifier_info_fini(&info); + nh_notifier_info_fini(&info, nh); return notifier_to_errno(err); } @@ -173,7 +197,7 @@ static int call_nexthop_notifier(struct notifier_block *nb, struct net *net, return err; err = nb->notifier_call(nb, event_type, &info); - nh_notifier_info_fini(&info); + nh_notifier_info_fini(&info, nh); return notifier_to_errno(err); } @@ -200,7 +224,7 @@ static void nexthop_devhash_add(struct net *net, struct nh_info *nhi) hlist_add_head(&nhi->dev_hash, head); } -static void nexthop_free_mpath(struct nexthop *nh) +static void nexthop_free_group(struct nexthop *nh) { struct nh_group *nhg; int i; @@ -240,7 +264,7 @@ void nexthop_free_rcu(struct rcu_head *head) struct nexthop *nh = container_of(head, struct nexthop, rcu); if (nh->is_group) - nexthop_free_mpath(nh); + nexthop_free_group(nh); else nexthop_free_single(nh); @@ -565,7 +589,8 @@ static int nh_check_attr_fdb_group(struct nexthop *nh, u8 *nh_family, return 0; } -static int nh_check_attr_group(struct net *net, struct nlattr *tb[], +static int nh_check_attr_group(struct net *net, + struct nlattr *tb[], size_t tb_size, struct netlink_ext_ack *extack) { unsigned int len = nla_len(tb[NHA_GROUP]); @@ -624,7 +649,7 @@ static int nh_check_attr_group(struct net *net, struct nlattr *tb[], return -EINVAL; } } - for (i = NHA_GROUP_TYPE + 1; i < __NHA_MAX; ++i) { + for (i = NHA_GROUP_TYPE + 1; i < tb_size; ++i) { if (!tb[i]) continue; if (i == NHA_FDB) @@ -670,21 +695,16 @@ static bool ipv4_good_nh(const struct fib_nh *nh) return !!(state & NUD_VALID); } -struct nexthop *nexthop_select_path(struct nexthop *nh, int hash) +static struct nexthop *nexthop_select_path_mp(struct nh_group *nhg, int hash) { struct nexthop *rc = NULL; - struct nh_group *nhg; int i; - if (!nh->is_group) - return nh; - - nhg = rcu_dereference(nh->nh_grp); for (i = 0; i < nhg->num_nh; ++i) { struct nh_grp_entry *nhge = &nhg->nh_entries[i]; struct nh_info *nhi; - if (hash > atomic_read(&nhge->upper_bound)) + if (hash > atomic_read(&nhge->mpath.upper_bound)) continue; nhi = rcu_dereference(nhge->nh->nh_info); @@ -711,6 +731,21 @@ struct nexthop *nexthop_select_path(struct nexthop *nh, int hash) return rc; } + +struct nexthop *nexthop_select_path(struct nexthop *nh, int hash) +{ + struct nh_group *nhg; + + if (!nh->is_group) + return nh; + + nhg = rcu_dereference(nh->nh_grp); + if (nhg->mpath) + return nexthop_select_path_mp(nhg, hash); + + /* Unreachable. */ + return NULL; +} EXPORT_SYMBOL_GPL(nexthop_select_path); int nexthop_for_each_fib6_nh(struct nexthop *nh, @@ -904,7 +939,7 @@ static void nh_group_rebalance(struct nh_group *nhg) w += nhge->weight; upper_bound = DIV_ROUND_CLOSEST_ULL((u64)w << 31, total) - 1; - atomic_set(&nhge->upper_bound, upper_bound); + atomic_set(&nhge->mpath.upper_bound, upper_bound); } } @@ -1446,10 +1481,13 @@ static struct nexthop *nexthop_create_group(struct net *net, nhg->nh_entries[i].nh_parent = nh; } - if (cfg->nh_grp_type == NEXTHOP_GRP_TYPE_MPATH) { + if (cfg->nh_grp_type == NEXTHOP_GRP_TYPE_MPATH) nhg->mpath = 1; + + WARN_ON_ONCE(nhg->mpath != 1); + + if (nhg->mpath) nh_group_rebalance(nhg); - } if (cfg->nh_fdb) nhg->fdb_nh = 1; @@ -1643,11 +1681,12 @@ static int rtm_to_nh_config(struct net *net, struct sk_buff *skb, struct netlink_ext_ack *extack) { struct nhmsg *nhm = nlmsg_data(nlh); - struct nlattr *tb[NHA_MAX + 1]; + struct nlattr *tb[ARRAY_SIZE(rtm_nh_policy_new)]; int err; - err = nlmsg_parse(nlh, sizeof(*nhm), tb, NHA_MAX, rtm_nh_policy, - extack); + err = nlmsg_parse(nlh, sizeof(*nhm), tb, + ARRAY_SIZE(rtm_nh_policy_new) - 1, + rtm_nh_policy_new, extack); if (err < 0) return err; @@ -1674,11 +1713,6 @@ static int rtm_to_nh_config(struct net *net, struct sk_buff *skb, goto out; } - if (tb[NHA_GROUPS] || tb[NHA_MASTER]) { - NL_SET_ERR_MSG(extack, "Invalid attributes in request"); - goto out; - } - memset(cfg, 0, sizeof(*cfg)); cfg->nlflags = nlh->nlmsg_flags; cfg->nlinfo.portid = NETLINK_CB(skb).portid; @@ -1720,7 +1754,7 @@ static int rtm_to_nh_config(struct net *net, struct sk_buff *skb, NL_SET_ERR_MSG(extack, "Invalid group type"); goto out; } - err = nh_check_attr_group(net, tb, extack); + err = nh_check_attr_group(net, tb, ARRAY_SIZE(tb), extack); /* no other attributes should be set */ goto out; @@ -1838,49 +1872,44 @@ static int rtm_new_nexthop(struct sk_buff *skb, struct nlmsghdr *nlh, return err; } -static int nh_valid_get_del_req(struct nlmsghdr *nlh, u32 *id, - struct netlink_ext_ack *extack) +static int __nh_valid_get_del_req(const struct nlmsghdr *nlh, + struct nlattr **tb, u32 *id, + struct netlink_ext_ack *extack) { struct nhmsg *nhm = nlmsg_data(nlh); - struct nlattr *tb[NHA_MAX + 1]; - int err, i; - - err = nlmsg_parse(nlh, sizeof(*nhm), tb, NHA_MAX, rtm_nh_policy, - extack); - if (err < 0) - return err; - err = -EINVAL; - for (i = 0; i < __NHA_MAX; ++i) { - if (!tb[i]) - continue; - - switch (i) { - case NHA_ID: - break; - default: - NL_SET_ERR_MSG_ATTR(extack, tb[i], - "Unexpected attribute in request"); - goto out; - } - } if (nhm->nh_protocol || nhm->resvd || nhm->nh_scope || nhm->nh_flags) { NL_SET_ERR_MSG(extack, "Invalid values in header"); - goto out; + return -EINVAL; } if (!tb[NHA_ID]) { NL_SET_ERR_MSG(extack, "Nexthop id is missing"); - goto out; + return -EINVAL; } *id = nla_get_u32(tb[NHA_ID]); - if (!(*id)) + if (!(*id)) { NL_SET_ERR_MSG(extack, "Invalid nexthop id"); - else - err = 0; -out: - return err; + return -EINVAL; + } + + return 0; +} + +static int nh_valid_get_del_req(const struct nlmsghdr *nlh, u32 *id, + struct netlink_ext_ack *extack) +{ + struct nlattr *tb[ARRAY_SIZE(rtm_nh_policy_get)]; + int err; + + err = nlmsg_parse(nlh, sizeof(struct nhmsg), tb, + ARRAY_SIZE(rtm_nh_policy_get) - 1, + rtm_nh_policy_get, extack); + if (err < 0) + return err; + + return __nh_valid_get_del_req(nlh, tb, id, extack); } /* rtnl */ @@ -1949,16 +1978,23 @@ errout_free: goto out; } -static bool nh_dump_filtered(struct nexthop *nh, int dev_idx, int master_idx, - bool group_filter, u8 family) +struct nh_dump_filter { + int dev_idx; + int master_idx; + bool group_filter; + bool fdb_filter; +}; + +static bool nh_dump_filtered(struct nexthop *nh, + struct nh_dump_filter *filter, u8 family) { const struct net_device *dev; const struct nh_info *nhi; - if (group_filter && !nh->is_group) + if (filter->group_filter && !nh->is_group) return true; - if (!dev_idx && !master_idx && !family) + if (!filter->dev_idx && !filter->master_idx && !family) return false; if (nh->is_group) @@ -1969,70 +2005,48 @@ static bool nh_dump_filtered(struct nexthop *nh, int dev_idx, int master_idx, return true; dev = nhi->fib_nhc.nhc_dev; - if (dev_idx && (!dev || dev->ifindex != dev_idx)) + if (filter->dev_idx && (!dev || dev->ifindex != filter->dev_idx)) return true; - if (master_idx) { + if (filter->master_idx) { struct net_device *master; if (!dev) return true; master = netdev_master_upper_dev_get((struct net_device *)dev); - if (!master || master->ifindex != master_idx) + if (!master || master->ifindex != filter->master_idx) return true; } return false; } -static int nh_valid_dump_req(const struct nlmsghdr *nlh, int *dev_idx, - int *master_idx, bool *group_filter, - bool *fdb_filter, struct netlink_callback *cb) +static int __nh_valid_dump_req(const struct nlmsghdr *nlh, struct nlattr **tb, + struct nh_dump_filter *filter, + struct netlink_ext_ack *extack) { - struct netlink_ext_ack *extack = cb->extack; - struct nlattr *tb[NHA_MAX + 1]; struct nhmsg *nhm; - int err, i; u32 idx; - err = nlmsg_parse(nlh, sizeof(*nhm), tb, NHA_MAX, rtm_nh_policy, - NULL); - if (err < 0) - return err; - - for (i = 0; i <= NHA_MAX; ++i) { - if (!tb[i]) - continue; - - switch (i) { - case NHA_OIF: - idx = nla_get_u32(tb[i]); - if (idx > INT_MAX) { - NL_SET_ERR_MSG(extack, "Invalid device index"); - return -EINVAL; - } - *dev_idx = idx; - break; - case NHA_MASTER: - idx = nla_get_u32(tb[i]); - if (idx > INT_MAX) { - NL_SET_ERR_MSG(extack, "Invalid master device index"); - return -EINVAL; - } - *master_idx = idx; - break; - case NHA_GROUPS: - *group_filter = true; - break; - case NHA_FDB: - *fdb_filter = true; - break; - default: - NL_SET_ERR_MSG(extack, "Unsupported attribute in dump request"); + if (tb[NHA_OIF]) { + idx = nla_get_u32(tb[NHA_OIF]); + if (idx > INT_MAX) { + NL_SET_ERR_MSG(extack, "Invalid device index"); + return -EINVAL; + } + filter->dev_idx = idx; + } + if (tb[NHA_MASTER]) { + idx = nla_get_u32(tb[NHA_MASTER]); + if (idx > INT_MAX) { + NL_SET_ERR_MSG(extack, "Invalid master device index"); return -EINVAL; } + filter->master_idx = idx; } + filter->group_filter = nla_get_flag(tb[NHA_GROUPS]); + filter->fdb_filter = nla_get_flag(tb[NHA_FDB]); nhm = nlmsg_data(nlh); if (nhm->nh_protocol || nhm->resvd || nhm->nh_scope || nhm->nh_flags) { @@ -2043,24 +2057,49 @@ static int nh_valid_dump_req(const struct nlmsghdr *nlh, int *dev_idx, return 0; } -/* rtnl */ -static int rtm_dump_nexthop(struct sk_buff *skb, struct netlink_callback *cb) +static int nh_valid_dump_req(const struct nlmsghdr *nlh, + struct nh_dump_filter *filter, + struct netlink_callback *cb) { - bool group_filter = false, fdb_filter = false; - struct nhmsg *nhm = nlmsg_data(cb->nlh); - int dev_filter_idx = 0, master_idx = 0; - struct net *net = sock_net(skb->sk); - struct rb_root *root = &net->nexthop.rb_root; - struct rb_node *node; - int idx = 0, s_idx; + struct nlattr *tb[ARRAY_SIZE(rtm_nh_policy_dump)]; int err; - err = nh_valid_dump_req(cb->nlh, &dev_filter_idx, &master_idx, - &group_filter, &fdb_filter, cb); + err = nlmsg_parse(nlh, sizeof(struct nhmsg), tb, + ARRAY_SIZE(rtm_nh_policy_dump) - 1, + rtm_nh_policy_dump, cb->extack); if (err < 0) return err; - s_idx = cb->args[0]; + return __nh_valid_dump_req(nlh, tb, filter, cb->extack); +} + +struct rtm_dump_nh_ctx { + u32 idx; +}; + +static struct rtm_dump_nh_ctx * +rtm_dump_nh_ctx(struct netlink_callback *cb) +{ + struct rtm_dump_nh_ctx *ctx = (void *)cb->ctx; + + BUILD_BUG_ON(sizeof(*ctx) > sizeof(cb->ctx)); + return ctx; +} + +static int rtm_dump_walk_nexthops(struct sk_buff *skb, + struct netlink_callback *cb, + struct rb_root *root, + struct rtm_dump_nh_ctx *ctx, + int (*nh_cb)(struct sk_buff *skb, + struct netlink_callback *cb, + struct nexthop *nh, void *data), + void *data) +{ + struct rb_node *node; + int idx = 0, s_idx; + int err; + + s_idx = ctx->idx; for (node = rb_first(root); node; node = rb_next(node)) { struct nexthop *nh; @@ -2068,30 +2107,58 @@ static int rtm_dump_nexthop(struct sk_buff *skb, struct netlink_callback *cb) goto cont; nh = rb_entry(node, struct nexthop, rb_node); - if (nh_dump_filtered(nh, dev_filter_idx, master_idx, - group_filter, nhm->nh_family)) - goto cont; - - err = nh_fill_node(skb, nh, RTM_NEWNEXTHOP, - NETLINK_CB(cb->skb).portid, - cb->nlh->nlmsg_seq, NLM_F_MULTI); - if (err < 0) { - if (likely(skb->len)) - goto out; - - goto out_err; - } + ctx->idx = idx; + err = nh_cb(skb, cb, nh, data); + if (err) + return err; cont: idx++; } + ctx->idx = idx; + return 0; +} + +static int rtm_dump_nexthop_cb(struct sk_buff *skb, struct netlink_callback *cb, + struct nexthop *nh, void *data) +{ + struct nhmsg *nhm = nlmsg_data(cb->nlh); + struct nh_dump_filter *filter = data; + + if (nh_dump_filtered(nh, filter, nhm->nh_family)) + return 0; + + return nh_fill_node(skb, nh, RTM_NEWNEXTHOP, + NETLINK_CB(cb->skb).portid, + cb->nlh->nlmsg_seq, NLM_F_MULTI); +} + +/* rtnl */ +static int rtm_dump_nexthop(struct sk_buff *skb, struct netlink_callback *cb) +{ + struct rtm_dump_nh_ctx *ctx = rtm_dump_nh_ctx(cb); + struct net *net = sock_net(skb->sk); + struct rb_root *root = &net->nexthop.rb_root; + struct nh_dump_filter filter = {}; + int err; + + err = nh_valid_dump_req(cb->nlh, &filter, cb); + if (err < 0) + return err; + + err = rtm_dump_walk_nexthops(skb, cb, root, ctx, + &rtm_dump_nexthop_cb, &filter); + if (err < 0) { + if (likely(skb->len)) + goto out; + goto out_err; + } + out: err = skb->len; out_err: - cb->args[0] = idx; cb->seq = net->nexthop.seq; nl_dump_check_consistent(cb, nlmsg_hdr(skb)); - return err; } diff --git a/net/ipv4/proc.c b/net/ipv4/proc.c index 63cd370ea29d..6d46297a99f8 100644 --- a/net/ipv4/proc.c +++ b/net/ipv4/proc.c @@ -464,30 +464,52 @@ static int snmp_seq_show(struct seq_file *seq, void *v) */ static int netstat_seq_show(struct seq_file *seq, void *v) { - int i; + const int ip_cnt = ARRAY_SIZE(snmp4_ipextstats_list) - 1; + const int tcp_cnt = ARRAY_SIZE(snmp4_net_list) - 1; struct net *net = seq->private; + unsigned long *buff; + int i; seq_puts(seq, "TcpExt:"); - for (i = 0; snmp4_net_list[i].name; i++) + for (i = 0; i < tcp_cnt; i++) seq_printf(seq, " %s", snmp4_net_list[i].name); seq_puts(seq, "\nTcpExt:"); - for (i = 0; snmp4_net_list[i].name; i++) - seq_printf(seq, " %lu", - snmp_fold_field(net->mib.net_statistics, - snmp4_net_list[i].entry)); - + buff = kzalloc(max(tcp_cnt * sizeof(long), ip_cnt * sizeof(u64)), + GFP_KERNEL); + if (buff) { + snmp_get_cpu_field_batch(buff, snmp4_net_list, + net->mib.net_statistics); + for (i = 0; i < tcp_cnt; i++) + seq_printf(seq, " %lu", buff[i]); + } else { + for (i = 0; i < tcp_cnt; i++) + seq_printf(seq, " %lu", + snmp_fold_field(net->mib.net_statistics, + snmp4_net_list[i].entry)); + } seq_puts(seq, "\nIpExt:"); - for (i = 0; snmp4_ipextstats_list[i].name; i++) + for (i = 0; i < ip_cnt; i++) seq_printf(seq, " %s", snmp4_ipextstats_list[i].name); seq_puts(seq, "\nIpExt:"); - for (i = 0; snmp4_ipextstats_list[i].name; i++) - seq_printf(seq, " %llu", - snmp_fold_field64(net->mib.ip_statistics, - snmp4_ipextstats_list[i].entry, - offsetof(struct ipstats_mib, syncp))); - + if (buff) { + u64 *buff64 = (u64 *)buff; + + memset(buff64, 0, ip_cnt * sizeof(u64)); + snmp_get_cpu_field64_batch(buff64, snmp4_ipextstats_list, + net->mib.ip_statistics, + offsetof(struct ipstats_mib, syncp)); + for (i = 0; i < ip_cnt; i++) + seq_printf(seq, " %llu", buff64[i]); + } else { + for (i = 0; i < ip_cnt; i++) + seq_printf(seq, " %llu", + snmp_fold_field64(net->mib.ip_statistics, + snmp4_ipextstats_list[i].entry, + offsetof(struct ipstats_mib, syncp))); + } + kfree(buff); seq_putc(seq, '\n'); mptcp_seq_show(seq); return 0; diff --git a/net/ipv4/route.c b/net/ipv4/route.c index e26652ff7059..02d81d79deeb 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -133,9 +133,11 @@ static int ip_rt_gc_timeout __read_mostly = RT_GC_TIMEOUT; * Interface to generic destination cache. */ -static struct dst_entry *ipv4_dst_check(struct dst_entry *dst, u32 cookie); +INDIRECT_CALLABLE_SCOPE +struct dst_entry *ipv4_dst_check(struct dst_entry *dst, u32 cookie); static unsigned int ipv4_default_advmss(const struct dst_entry *dst); -static unsigned int ipv4_mtu(const struct dst_entry *dst); +INDIRECT_CALLABLE_SCOPE +unsigned int ipv4_mtu(const struct dst_entry *dst); static struct dst_entry *ipv4_negative_advice(struct dst_entry *dst); static void ipv4_link_failure(struct sk_buff *skb); static void ip_rt_update_pmtu(struct dst_entry *dst, struct sock *sk, @@ -1187,7 +1189,8 @@ void ipv4_sk_redirect(struct sk_buff *skb, struct sock *sk) } EXPORT_SYMBOL_GPL(ipv4_sk_redirect); -static struct dst_entry *ipv4_dst_check(struct dst_entry *dst, u32 cookie) +INDIRECT_CALLABLE_SCOPE struct dst_entry *ipv4_dst_check(struct dst_entry *dst, + u32 cookie) { struct rtable *rt = (struct rtable *) dst; @@ -1203,6 +1206,7 @@ static struct dst_entry *ipv4_dst_check(struct dst_entry *dst, u32 cookie) return NULL; return dst; } +EXPORT_INDIRECT_CALLABLE(ipv4_dst_check); static void ipv4_send_dest_unreach(struct sk_buff *skb) { @@ -1311,7 +1315,7 @@ static unsigned int ipv4_default_advmss(const struct dst_entry *dst) return min(advmss, IPV4_MAX_PMTU - header_size); } -static unsigned int ipv4_mtu(const struct dst_entry *dst) +INDIRECT_CALLABLE_SCOPE unsigned int ipv4_mtu(const struct dst_entry *dst) { const struct rtable *rt = (const struct rtable *)dst; unsigned int mtu = rt->rt_pmtu; @@ -1333,6 +1337,7 @@ static unsigned int ipv4_mtu(const struct dst_entry *dst) return mtu - lwtunnel_headroom(dst->lwtstate, mtu); } +EXPORT_INDIRECT_CALLABLE(ipv4_mtu); static void ip_del_fnhe(struct fib_nh_common *nhc, __be32 daddr) { @@ -3299,6 +3304,7 @@ static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh, fri.type = rt->rt_type; fri.offload = 0; fri.trap = 0; + fri.offload_failed = 0; if (res.fa_head) { struct fib_alias *fa; diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c index 3e5f4f2e705e..f55095d3ed16 100644 --- a/net/ipv4/sysctl_net_ipv4.c +++ b/net/ipv4/sysctl_net_ipv4.c @@ -1354,6 +1354,15 @@ static struct ctl_table ipv4_net_table[] = { .proc_handler = proc_dointvec_minmax, .extra1 = SYSCTL_ONE }, + { + .procname = "fib_notify_on_flag_change", + .data = &init_net.ipv4.sysctl_fib_notify_on_flag_change, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = SYSCTL_ZERO, + .extra2 = &two, + }, { } }; diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 32545ecf2ab1..a3422e42784e 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -280,6 +280,12 @@ #include <asm/ioctls.h> #include <net/busy_poll.h> +/* Track pending CMSGs. */ +enum { + TCP_CMSG_INQ = 1, + TCP_CMSG_TS = 2 +}; + struct percpu_counter tcp_orphan_count; EXPORT_SYMBOL_GPL(tcp_orphan_count); @@ -475,19 +481,11 @@ static void tcp_tx_timestamp(struct sock *sk, u16 tsflags) } } -static inline bool tcp_stream_is_readable(const struct tcp_sock *tp, - int target, struct sock *sk) +static bool tcp_stream_is_readable(struct sock *sk, int target) { - int avail = READ_ONCE(tp->rcv_nxt) - READ_ONCE(tp->copied_seq); - - if (avail > 0) { - if (avail >= target) - return true; - if (tcp_rmem_pressure(sk)) - return true; - if (tcp_receive_window(tp) <= inet_csk(sk)->icsk_ack.rcv_mss) - return true; - } + if (tcp_epollin_ready(sk, target)) + return true; + if (sk->sk_prot->stream_memory_read) return sk->sk_prot->stream_memory_read(sk); return false; @@ -562,7 +560,7 @@ __poll_t tcp_poll(struct file *file, struct socket *sock, poll_table *wait) tp->urg_data) target++; - if (tcp_stream_is_readable(tp, target, sk)) + if (tcp_stream_is_readable(sk, target)) mask |= EPOLLIN | EPOLLRDNORM; if (!(sk->sk_shutdown & SEND_SHUTDOWN)) { @@ -1010,7 +1008,7 @@ new_segment: } if (!(flags & MSG_NO_SHARED_FRAGS)) - skb_shinfo(skb)->tx_flags |= SKBTX_SHARED_FRAG; + skb_shinfo(skb)->flags |= SKBFL_SHARED_FRAG; skb->len += copy; skb->data_len += copy; @@ -1217,7 +1215,7 @@ int tcp_sendmsg_locked(struct sock *sk, struct msghdr *msg, size_t size) if (flags & MSG_ZEROCOPY && size && sock_flag(sk, SOCK_ZEROCOPY)) { skb = tcp_write_queue_tail(sk); - uarg = sock_zerocopy_realloc(sk, size, skb_zcopy(skb)); + uarg = msg_zerocopy_realloc(sk, size, skb_zcopy(skb)); if (!uarg) { err = -ENOBUFS; goto out_err; @@ -1429,7 +1427,7 @@ out: tcp_push(sk, flags, mss_now, tp->nonagle, size_goal); } out_nopush: - sock_zerocopy_put(uarg); + net_zcopy_put(uarg); return copied + copied_syn; do_error: @@ -1440,7 +1438,7 @@ do_fault: if (copied + copied_syn) goto out; out_err: - sock_zerocopy_put_abort(uarg, true); + net_zcopy_put_abort(uarg, true); err = sk_stream_error(sk, flags, err); /* make sure we wake any epoll edge trigger waiter */ if (unlikely(tcp_rtx_and_write_queues_empty(sk) && err == -EAGAIN)) { @@ -1739,6 +1737,20 @@ int tcp_set_rcvlowat(struct sock *sk, int val) } EXPORT_SYMBOL(tcp_set_rcvlowat); +static void tcp_update_recv_tstamps(struct sk_buff *skb, + struct scm_timestamping_internal *tss) +{ + if (skb->tstamp) + tss->ts[0] = ktime_to_timespec64(skb->tstamp); + else + tss->ts[0] = (struct timespec64) {0}; + + if (skb_hwtstamps(skb)->hwtstamp) + tss->ts[2] = ktime_to_timespec64(skb_hwtstamps(skb)->hwtstamp); + else + tss->ts[2] = (struct timespec64) {0}; +} + #ifdef CONFIG_MMU static const struct vm_operations_struct tcp_vm_ops = { }; @@ -1842,13 +1854,13 @@ static int tcp_recvmsg_locked(struct sock *sk, struct msghdr *msg, size_t len, struct scm_timestamping_internal *tss, int *cmsg_flags); static int receive_fallback_to_copy(struct sock *sk, - struct tcp_zerocopy_receive *zc, int inq) + struct tcp_zerocopy_receive *zc, int inq, + struct scm_timestamping_internal *tss) { unsigned long copy_address = (unsigned long)zc->copybuf_address; - struct scm_timestamping_internal tss_unused; - int err, cmsg_flags_unused; struct msghdr msg = {}; struct iovec iov; + int err; zc->length = 0; zc->recv_skip_hint = 0; @@ -1862,7 +1874,7 @@ static int receive_fallback_to_copy(struct sock *sk, return err; err = tcp_recvmsg_locked(sk, &msg, inq, /*nonblock=*/1, /*flags=*/0, - &tss_unused, &cmsg_flags_unused); + tss, &zc->msg_flags); if (err < 0) return err; @@ -1903,21 +1915,27 @@ static int tcp_copy_straggler_data(struct tcp_zerocopy_receive *zc, return (__s32)copylen; } -static int tcp_zerocopy_handle_leftover_data(struct tcp_zerocopy_receive *zc, - struct sock *sk, - struct sk_buff *skb, - u32 *seq, - s32 copybuf_len) +static int tcp_zc_handle_leftover(struct tcp_zerocopy_receive *zc, + struct sock *sk, + struct sk_buff *skb, + u32 *seq, + s32 copybuf_len, + struct scm_timestamping_internal *tss) { u32 offset, copylen = min_t(u32, copybuf_len, zc->recv_skip_hint); if (!copylen) return 0; /* skb is null if inq < PAGE_SIZE. */ - if (skb) + if (skb) { offset = *seq - TCP_SKB_CB(skb)->seq; - else + } else { skb = tcp_recv_skb(sk, *seq, &offset); + if (TCP_SKB_CB(skb)->has_rxtstamp) { + tcp_update_recv_tstamps(skb, tss); + zc->msg_flags |= TCP_CMSG_TS; + } + } zc->copybuf_len = tcp_copy_straggler_data(zc, skb, copylen, &offset, seq); @@ -2004,9 +2022,38 @@ static int tcp_zerocopy_vm_insert_batch(struct vm_area_struct *vma, err); } +#define TCP_VALID_ZC_MSG_FLAGS (TCP_CMSG_TS) +static void tcp_recv_timestamp(struct msghdr *msg, const struct sock *sk, + struct scm_timestamping_internal *tss); +static void tcp_zc_finalize_rx_tstamp(struct sock *sk, + struct tcp_zerocopy_receive *zc, + struct scm_timestamping_internal *tss) +{ + unsigned long msg_control_addr; + struct msghdr cmsg_dummy; + + msg_control_addr = (unsigned long)zc->msg_control; + cmsg_dummy.msg_control = (void *)msg_control_addr; + cmsg_dummy.msg_controllen = + (__kernel_size_t)zc->msg_controllen; + cmsg_dummy.msg_flags = in_compat_syscall() + ? MSG_CMSG_COMPAT : 0; + zc->msg_flags = 0; + if (zc->msg_control == msg_control_addr && + zc->msg_controllen == cmsg_dummy.msg_controllen) { + tcp_recv_timestamp(&cmsg_dummy, sk, tss); + zc->msg_control = (__u64) + ((uintptr_t)cmsg_dummy.msg_control); + zc->msg_controllen = + (__u64)cmsg_dummy.msg_controllen; + zc->msg_flags = (__u32)cmsg_dummy.msg_flags; + } +} + #define TCP_ZEROCOPY_PAGE_BATCH_SIZE 32 static int tcp_zerocopy_receive(struct sock *sk, - struct tcp_zerocopy_receive *zc) + struct tcp_zerocopy_receive *zc, + struct scm_timestamping_internal *tss) { u32 length = 0, offset, vma_len, avail_len, copylen = 0; unsigned long address = (unsigned long)zc->address; @@ -2023,6 +2070,7 @@ static int tcp_zerocopy_receive(struct sock *sk, int ret; zc->copybuf_len = 0; + zc->msg_flags = 0; if (address & (PAGE_SIZE - 1) || address != zc->address) return -EINVAL; @@ -2033,7 +2081,7 @@ static int tcp_zerocopy_receive(struct sock *sk, sock_rps_record_flow(sk); if (inq && inq <= copybuf_len) - return receive_fallback_to_copy(sk, zc, inq); + return receive_fallback_to_copy(sk, zc, inq, tss); if (inq < PAGE_SIZE) { zc->length = 0; @@ -2078,6 +2126,11 @@ static int tcp_zerocopy_receive(struct sock *sk, } else { skb = tcp_recv_skb(sk, seq, &offset); } + + if (TCP_SKB_CB(skb)->has_rxtstamp) { + tcp_update_recv_tstamps(skb, tss); + zc->msg_flags |= TCP_CMSG_TS; + } zc->recv_skip_hint = skb->len - offset; frags = skb_advance_to_frag(skb, offset, &offset_frag); if (!frags || offset_frag) @@ -2120,8 +2173,7 @@ out: mmap_read_unlock(current->mm); /* Try to copy straggler data. */ if (!ret) - copylen = tcp_zerocopy_handle_leftover_data(zc, sk, skb, &seq, - copybuf_len); + copylen = tcp_zc_handle_leftover(zc, sk, skb, &seq, copybuf_len, tss); if (length + copylen) { WRITE_ONCE(tp->copied_seq, seq); @@ -2142,20 +2194,6 @@ out: } #endif -static void tcp_update_recv_tstamps(struct sk_buff *skb, - struct scm_timestamping_internal *tss) -{ - if (skb->tstamp) - tss->ts[0] = ktime_to_timespec64(skb->tstamp); - else - tss->ts[0] = (struct timespec64) {0}; - - if (skb_hwtstamps(skb)->hwtstamp) - tss->ts[2] = ktime_to_timespec64(skb_hwtstamps(skb)->hwtstamp); - else - tss->ts[2] = (struct timespec64) {0}; -} - /* Similar to __sock_recv_timestamp, but does not require an skb */ static void tcp_recv_timestamp(struct msghdr *msg, const struct sock *sk, struct scm_timestamping_internal *tss) @@ -2272,7 +2310,7 @@ static int tcp_recvmsg_locked(struct sock *sk, struct msghdr *msg, size_t len, goto out; if (tp->recvmsg_inq) - *cmsg_flags = 1; + *cmsg_flags = TCP_CMSG_INQ; timeo = sock_rcvtimeo(sk, nonblock); /* Urgent data needs to be handled specially. */ @@ -2453,7 +2491,7 @@ skip_copy: if (TCP_SKB_CB(skb)->has_rxtstamp) { tcp_update_recv_tstamps(skb, tss); - *cmsg_flags |= 2; + *cmsg_flags |= TCP_CMSG_TS; } if (used + offset < skb->len) @@ -2513,9 +2551,9 @@ int tcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int nonblock, release_sock(sk); if (cmsg_flags && ret >= 0) { - if (cmsg_flags & 2) + if (cmsg_flags & TCP_CMSG_TS) tcp_recv_timestamp(msg, sk, &tss); - if (cmsg_flags & 1) { + if (cmsg_flags & TCP_CMSG_INQ) { inq = tcp_inq_hint(sk); put_cmsg(msg, SOL_TCP, TCP_CM_INQ, sizeof(inq), &inq); } @@ -3767,11 +3805,24 @@ static size_t tcp_opt_stats_get_size(void) nla_total_size(sizeof(u16)) + /* TCP_NLA_TIMEOUT_REHASH */ nla_total_size(sizeof(u32)) + /* TCP_NLA_BYTES_NOTSENT */ nla_total_size_64bit(sizeof(u64)) + /* TCP_NLA_EDT */ + nla_total_size(sizeof(u8)) + /* TCP_NLA_TTL */ 0; } +/* Returns TTL or hop limit of an incoming packet from skb. */ +static u8 tcp_skb_ttl_or_hop_limit(const struct sk_buff *skb) +{ + if (skb->protocol == htons(ETH_P_IP)) + return ip_hdr(skb)->ttl; + else if (skb->protocol == htons(ETH_P_IPV6)) + return ipv6_hdr(skb)->hop_limit; + else + return 0; +} + struct sk_buff *tcp_get_timestamping_opt_stats(const struct sock *sk, - const struct sk_buff *orig_skb) + const struct sk_buff *orig_skb, + const struct sk_buff *ack_skb) { const struct tcp_sock *tp = tcp_sk(sk); struct sk_buff *stats; @@ -3827,6 +3878,9 @@ struct sk_buff *tcp_get_timestamping_opt_stats(const struct sock *sk, max_t(int, 0, tp->write_seq - tp->snd_nxt)); nla_put_u64_64bit(stats, TCP_NLA_EDT, orig_skb->skb_mstamp_ns, TCP_NLA_PAD); + if (ack_skb) + nla_put_u8(stats, TCP_NLA_TTL, + tcp_skb_ttl_or_hop_limit(ack_skb)); return stats; } @@ -4083,6 +4137,7 @@ static int do_tcp_getsockopt(struct sock *sk, int level, } #ifdef CONFIG_MMU case TCP_ZEROCOPY_RECEIVE: { + struct scm_timestamping_internal tss; struct tcp_zerocopy_receive zc = {}; int err; @@ -4090,19 +4145,36 @@ static int do_tcp_getsockopt(struct sock *sk, int level, return -EFAULT; if (len < offsetofend(struct tcp_zerocopy_receive, length)) return -EINVAL; - if (len > sizeof(zc)) { + if (unlikely(len > sizeof(zc))) { + err = check_zeroed_user(optval + sizeof(zc), + len - sizeof(zc)); + if (err < 1) + return err == 0 ? -EINVAL : err; len = sizeof(zc); if (put_user(len, optlen)) return -EFAULT; } if (copy_from_user(&zc, optval, len)) return -EFAULT; + if (zc.reserved) + return -EINVAL; + if (zc.msg_flags & ~(TCP_VALID_ZC_MSG_FLAGS)) + return -EINVAL; lock_sock(sk); - err = tcp_zerocopy_receive(sk, &zc); + err = tcp_zerocopy_receive(sk, &zc, &tss); + err = BPF_CGROUP_RUN_PROG_GETSOCKOPT_KERN(sk, level, optname, + &zc, &len, err); release_sock(sk); - if (len >= offsetofend(struct tcp_zerocopy_receive, err)) - goto zerocopy_rcv_sk_err; + if (len >= offsetofend(struct tcp_zerocopy_receive, msg_flags)) + goto zerocopy_rcv_cmsg; switch (len) { + case offsetofend(struct tcp_zerocopy_receive, msg_flags): + goto zerocopy_rcv_cmsg; + case offsetofend(struct tcp_zerocopy_receive, msg_controllen): + case offsetofend(struct tcp_zerocopy_receive, msg_control): + case offsetofend(struct tcp_zerocopy_receive, flags): + case offsetofend(struct tcp_zerocopy_receive, copybuf_len): + case offsetofend(struct tcp_zerocopy_receive, copybuf_address): case offsetofend(struct tcp_zerocopy_receive, err): goto zerocopy_rcv_sk_err; case offsetofend(struct tcp_zerocopy_receive, inq): @@ -4111,6 +4183,11 @@ static int do_tcp_getsockopt(struct sock *sk, int level, default: goto zerocopy_rcv_out; } +zerocopy_rcv_cmsg: + if (zc.msg_flags & TCP_CMSG_TS) + tcp_zc_finalize_rx_tstamp(sk, &zc, &tss); + else + zc.msg_flags = 0; zerocopy_rcv_sk_err: if (!err) zc.err = sock_error(sk); @@ -4133,6 +4210,18 @@ zerocopy_rcv_out: return 0; } +bool tcp_bpf_bypass_getsockopt(int level, int optname) +{ + /* TCP do_tcp_getsockopt has optimized getsockopt implementation + * to avoid extra socket lock for TCP_ZEROCOPY_RECEIVE. + */ + if (level == SOL_TCP && optname == TCP_ZEROCOPY_RECEIVE) + return true; + + return false; +} +EXPORT_SYMBOL(tcp_bpf_bypass_getsockopt); + int tcp_getsockopt(struct sock *sk, int level, int optname, char __user *optval, int __user *optlen) { diff --git a/net/ipv4/tcp_cubic.c b/net/ipv4/tcp_cubic.c index c7bf5b26bf0c..ffcbe46dacdb 100644 --- a/net/ipv4/tcp_cubic.c +++ b/net/ipv4/tcp_cubic.c @@ -104,16 +104,7 @@ struct bictcp { static inline void bictcp_reset(struct bictcp *ca) { - ca->cnt = 0; - ca->last_max_cwnd = 0; - ca->last_cwnd = 0; - ca->last_time = 0; - ca->bic_origin_point = 0; - ca->bic_K = 0; - ca->delay_min = 0; - ca->epoch_start = 0; - ca->ack_cnt = 0; - ca->tcp_cwnd = 0; + memset(ca, 0, offsetof(struct bictcp, unused)); ca->found = 0; } diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 9b44caa4b956..69a545db80d2 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -3146,7 +3146,7 @@ static u32 tcp_tso_acked(struct sock *sk, struct sk_buff *skb) } static void tcp_ack_tstamp(struct sock *sk, struct sk_buff *skb, - u32 prior_snd_una) + const struct sk_buff *ack_skb, u32 prior_snd_una) { const struct skb_shared_info *shinfo; @@ -3158,7 +3158,7 @@ static void tcp_ack_tstamp(struct sock *sk, struct sk_buff *skb, if (!before(shinfo->tskey, prior_snd_una) && before(shinfo->tskey, tcp_sk(sk)->snd_una)) { tcp_skb_tsorted_save(skb) { - __skb_tstamp_tx(skb, NULL, sk, SCM_TSTAMP_ACK); + __skb_tstamp_tx(skb, ack_skb, NULL, sk, SCM_TSTAMP_ACK); } tcp_skb_tsorted_restore(skb); } } @@ -3167,8 +3167,8 @@ static void tcp_ack_tstamp(struct sock *sk, struct sk_buff *skb, * is before the ack sequence we can discard it as it's confirmed to have * arrived at the other end. */ -static int tcp_clean_rtx_queue(struct sock *sk, u32 prior_fack, - u32 prior_snd_una, +static int tcp_clean_rtx_queue(struct sock *sk, const struct sk_buff *ack_skb, + u32 prior_fack, u32 prior_snd_una, struct tcp_sacktag_state *sack, bool ece_ack) { const struct inet_connection_sock *icsk = inet_csk(sk); @@ -3257,7 +3257,7 @@ static int tcp_clean_rtx_queue(struct sock *sk, u32 prior_fack, if (!fully_acked) break; - tcp_ack_tstamp(sk, skb, prior_snd_una); + tcp_ack_tstamp(sk, skb, ack_skb, prior_snd_una); next = skb_rb_next(skb); if (unlikely(skb == tp->retransmit_skb_hint)) @@ -3275,7 +3275,7 @@ static int tcp_clean_rtx_queue(struct sock *sk, u32 prior_fack, tp->snd_up = tp->snd_una; if (skb) { - tcp_ack_tstamp(sk, skb, prior_snd_una); + tcp_ack_tstamp(sk, skb, ack_skb, prior_snd_una); if (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_ACKED) flag |= FLAG_SACK_RENEGING; } @@ -3810,8 +3810,8 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag) goto no_queue; /* See if we can take anything off of the retransmit queue. */ - flag |= tcp_clean_rtx_queue(sk, prior_fack, prior_snd_una, &sack_state, - flag & FLAG_ECE); + flag |= tcp_clean_rtx_queue(sk, skb, prior_fack, prior_snd_una, + &sack_state, flag & FLAG_ECE); tcp_rack_update_reo_wnd(sk, &rs); @@ -4924,15 +4924,8 @@ err: void tcp_data_ready(struct sock *sk) { - const struct tcp_sock *tp = tcp_sk(sk); - int avail = tp->rcv_nxt - tp->copied_seq; - - if (avail < sk->sk_rcvlowat && !tcp_rmem_pressure(sk) && - !sock_flag(sk, SOCK_DONE) && - tcp_receive_window(tp) > inet_csk(sk)->icsk_ack.rcv_mss) - return; - - sk->sk_data_ready(sk); + if (tcp_epollin_ready(sk, sk->sk_rcvlowat) || sock_flag(sk, SOCK_DONE)) + sk->sk_data_ready(sk); } static void tcp_data_queue(struct sock *sk, struct sk_buff *skb) diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 777306b5bc22..daad4f99db32 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -1649,6 +1649,8 @@ u16 tcp_v4_get_syncookie(struct sock *sk, struct iphdr *iph, return mss; } +INDIRECT_CALLABLE_DECLARE(struct dst_entry *ipv4_dst_check(struct dst_entry *, + u32)); /* The socket must have it's spinlock held when we get * here, unless it is a TCP_LISTEN socket. * @@ -1668,7 +1670,8 @@ int tcp_v4_do_rcv(struct sock *sk, struct sk_buff *skb) sk_mark_napi_id(sk, skb); if (dst) { if (inet_sk(sk)->rx_dst_ifindex != skb->skb_iif || - !dst->ops->check(dst, 0)) { + !INDIRECT_CALL_1(dst->ops->check, ipv4_dst_check, + dst, 0)) { dst_release(dst); sk->sk_rx_dst = NULL; } @@ -2793,6 +2796,7 @@ struct proto tcp_prot = { .shutdown = tcp_shutdown, .setsockopt = tcp_setsockopt, .getsockopt = tcp_getsockopt, + .bpf_bypass_getsockopt = tcp_bpf_bypass_getsockopt, .keepalive = tcp_set_keepalive, .recvmsg = tcp_recvmsg, .sendmsg = tcp_sendmsg, diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 8478cf749821..fbf140a770d8 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -1319,7 +1319,6 @@ static int __tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, skb_orphan(skb); skb->sk = sk; skb->destructor = skb_is_tcp_pure_ack(skb) ? __sock_wfree : tcp_wfree; - skb_set_hash_from_sk(skb, sk); refcount_add(skb->truesize, &sk->sk_wmem_alloc); skb_set_dst_pending_confirm(skb, sk->sk_dst_pending_confirm); @@ -1390,6 +1389,7 @@ static int __tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, tcp_skb_pcount(skb)); tp->segs_out += tcp_skb_pcount(skb); + skb_set_hash_from_sk(skb, sk); /* OK, its time to fill skb_shinfo(skb)->gso_{segs|size} */ skb_shinfo(skb)->gso_segs = tcp_skb_pcount(skb); skb_shinfo(skb)->gso_size = tcp_skb_mss(skb); diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 69ea76578abb..4a0478b17243 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -596,6 +596,12 @@ void udp_encap_enable(void) } EXPORT_SYMBOL(udp_encap_enable); +void udp_encap_disable(void) +{ + static_branch_dec(&udp_encap_needed_key); +} +EXPORT_SYMBOL(udp_encap_disable); + /* Handler for tunnels with arbitrary destination ports: no socket lookup, go * through error handlers in encapsulations looking for a match. */ @@ -1124,7 +1130,7 @@ int udp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) rcu_read_unlock(); } - if (cgroup_bpf_enabled && !connected) { + if (cgroup_bpf_enabled(BPF_CGROUP_UDP4_SENDMSG) && !connected) { err = BPF_CGROUP_RUN_PROG_UDP4_SENDMSG_LOCK(sk, (struct sockaddr *)usin, &ipc.addr); if (err) @@ -1858,9 +1864,8 @@ try_again: memset(sin->sin_zero, 0, sizeof(sin->sin_zero)); *addr_len = sizeof(*sin); - if (cgroup_bpf_enabled) - BPF_CGROUP_RUN_PROG_UDP4_RECVMSG_LOCK(sk, - (struct sockaddr *)sin); + BPF_CGROUP_RUN_PROG_UDP4_RECVMSG_LOCK(sk, + (struct sockaddr *)sin); } if (udp_sk(sk)->gro_enabled) diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c index cfc872689b99..b76c48efd37e 100644 --- a/net/ipv4/udp_offload.c +++ b/net/ipv4/udp_offload.c @@ -68,8 +68,8 @@ static struct sk_buff *__skb_udp_tunnel_segment(struct sk_buff *skb, (NETIF_F_HW_CSUM | NETIF_F_IP_CSUM)))); features &= skb->dev->hw_enc_features; - /* CRC checksum can't be handled by HW when it's a UDP tunneling packet. */ - features &= ~NETIF_F_SCTP_CRC; + if (need_csum) + features &= ~NETIF_F_SCTP_CRC; /* The only checksum offload we care about from here on out is the * outer one so strip the existing checksum feature flags and @@ -519,7 +519,8 @@ struct sk_buff *udp_gro_receive(struct list_head *head, struct sk_buff *skb, if (skb->dev->features & NETIF_F_GRO_FRAGLIST) NAPI_GRO_CB(skb)->is_flist = sk ? !udp_sk(sk)->gro_enabled: 1; - if ((sk && udp_sk(sk)->gro_enabled) || NAPI_GRO_CB(skb)->is_flist) { + if ((!sk && (skb->dev->features & NETIF_F_GRO_UDP_FWD)) || + (sk && udp_sk(sk)->gro_enabled) || NAPI_GRO_CB(skb)->is_flist) { pp = call_gro_receive(udp_gro_receive_segment, head, skb); return pp; } diff --git a/net/ipv4/udp_tunnel_core.c b/net/ipv4/udp_tunnel_core.c index 3eecba0874aa..b97e3635acf5 100644 --- a/net/ipv4/udp_tunnel_core.c +++ b/net/ipv4/udp_tunnel_core.c @@ -90,15 +90,11 @@ void udp_tunnel_push_rx_port(struct net_device *dev, struct socket *sock, struct sock *sk = sock->sk; struct udp_tunnel_info ti; - if (!dev->netdev_ops->ndo_udp_tunnel_add || - !(dev->features & NETIF_F_RX_UDP_TUNNEL_PORT)) - return; - ti.type = type; ti.sa_family = sk->sk_family; ti.port = inet_sk(sk)->inet_sport; - dev->netdev_ops->ndo_udp_tunnel_add(dev, &ti); + udp_tunnel_nic_add_port(dev, &ti); } EXPORT_SYMBOL_GPL(udp_tunnel_push_rx_port); @@ -108,15 +104,11 @@ void udp_tunnel_drop_rx_port(struct net_device *dev, struct socket *sock, struct sock *sk = sock->sk; struct udp_tunnel_info ti; - if (!dev->netdev_ops->ndo_udp_tunnel_del || - !(dev->features & NETIF_F_RX_UDP_TUNNEL_PORT)) - return; - ti.type = type; ti.sa_family = sk->sk_family; ti.port = inet_sk(sk)->inet_sport; - dev->netdev_ops->ndo_udp_tunnel_del(dev, &ti); + udp_tunnel_nic_del_port(dev, &ti); } EXPORT_SYMBOL_GPL(udp_tunnel_drop_rx_port); @@ -134,11 +126,7 @@ void udp_tunnel_notify_add_rx_port(struct socket *sock, unsigned short type) rcu_read_lock(); for_each_netdev_rcu(net, dev) { - if (!dev->netdev_ops->ndo_udp_tunnel_add) - continue; - if (!(dev->features & NETIF_F_RX_UDP_TUNNEL_PORT)) - continue; - dev->netdev_ops->ndo_udp_tunnel_add(dev, &ti); + udp_tunnel_nic_add_port(dev, &ti); } rcu_read_unlock(); } @@ -158,11 +146,7 @@ void udp_tunnel_notify_del_rx_port(struct socket *sock, unsigned short type) rcu_read_lock(); for_each_netdev_rcu(net, dev) { - if (!dev->netdev_ops->ndo_udp_tunnel_del) - continue; - if (!(dev->features & NETIF_F_RX_UDP_TUNNEL_PORT)) - continue; - dev->netdev_ops->ndo_udp_tunnel_del(dev, &ti); + udp_tunnel_nic_del_port(dev, &ti); } rcu_read_unlock(); } diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 9edc5bb2d531..f2337fb756ac 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -205,6 +205,7 @@ static struct ipv6_devconf ipv6_devconf __read_mostly = { .max_desync_factor = MAX_DESYNC_FACTOR, .max_addresses = IPV6_MAX_ADDRESSES, .accept_ra_defrtr = 1, + .ra_defrtr_metric = IP6_RT_PRIO_USER, .accept_ra_from_local = 0, .accept_ra_min_hop_limit= 1, .accept_ra_pinfo = 1, @@ -260,6 +261,7 @@ static struct ipv6_devconf ipv6_devconf_dflt __read_mostly = { .max_desync_factor = MAX_DESYNC_FACTOR, .max_addresses = IPV6_MAX_ADDRESSES, .accept_ra_defrtr = 1, + .ra_defrtr_metric = IP6_RT_PRIO_USER, .accept_ra_from_local = 0, .accept_ra_min_hop_limit= 1, .accept_ra_pinfo = 1, @@ -5476,6 +5478,7 @@ static inline void ipv6_store_devconf(struct ipv6_devconf *cnf, array[DEVCONF_MAX_DESYNC_FACTOR] = cnf->max_desync_factor; array[DEVCONF_MAX_ADDRESSES] = cnf->max_addresses; array[DEVCONF_ACCEPT_RA_DEFRTR] = cnf->accept_ra_defrtr; + array[DEVCONF_RA_DEFRTR_METRIC] = cnf->ra_defrtr_metric; array[DEVCONF_ACCEPT_RA_MIN_HOP_LIMIT] = cnf->accept_ra_min_hop_limit; array[DEVCONF_ACCEPT_RA_PINFO] = cnf->accept_ra_pinfo; #ifdef CONFIG_IPV6_ROUTER_PREF @@ -6669,6 +6672,14 @@ static const struct ctl_table addrconf_sysctl[] = { .proc_handler = proc_dointvec, }, { + .procname = "ra_defrtr_metric", + .data = &ipv6_devconf.ra_defrtr_metric, + .maxlen = sizeof(u32), + .mode = 0644, + .proc_handler = proc_douintvec_minmax, + .extra1 = (void *)SYSCTL_ONE, + }, + { .procname = "accept_ra_min_hop_limit", .data = &ipv6_devconf.accept_ra_min_hop_limit, .maxlen = sizeof(int), diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c index 8e9c3e9ea36e..1fb75f01756c 100644 --- a/net/ipv6/af_inet6.c +++ b/net/ipv6/af_inet6.c @@ -295,7 +295,8 @@ static int __inet6_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len, return -EINVAL; snum = ntohs(addr->sin6_port); - if (snum && inet_port_requires_bind_service(net, snum) && + if (!(flags & BIND_NO_CAP_NET_BIND_SERVICE) && + snum && inet_port_requires_bind_service(net, snum) && !ns_capable(net->user_ns, CAP_NET_BIND_SERVICE)) return -EACCES; @@ -439,6 +440,7 @@ out_unlock: int inet6_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) { struct sock *sk = sock->sk; + u32 flags = BIND_WITH_LOCK; int err = 0; /* If the socket has its own bind function then use it. */ @@ -451,11 +453,12 @@ int inet6_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) /* BPF prog is run before any checks are done so that if the prog * changes context in a wrong way it will be caught. */ - err = BPF_CGROUP_RUN_PROG_INET6_BIND_LOCK(sk, uaddr); + err = BPF_CGROUP_RUN_PROG_INET_BIND_LOCK(sk, uaddr, + BPF_CGROUP_INET6_BIND, &flags); if (err) return err; - return __inet6_bind(sk, uaddr, addr_len, BIND_WITH_LOCK); + return __inet6_bind(sk, uaddr, addr_len, flags); } EXPORT_SYMBOL(inet6_bind); @@ -527,18 +530,19 @@ int inet6_getname(struct socket *sock, struct sockaddr *uaddr, sin->sin6_addr = sk->sk_v6_daddr; if (np->sndflow) sin->sin6_flowinfo = np->flow_label; + BPF_CGROUP_RUN_SA_PROG_LOCK(sk, (struct sockaddr *)sin, + BPF_CGROUP_INET6_GETPEERNAME, + NULL); } else { if (ipv6_addr_any(&sk->sk_v6_rcv_saddr)) sin->sin6_addr = np->saddr; else sin->sin6_addr = sk->sk_v6_rcv_saddr; sin->sin6_port = inet->inet_sport; - } - if (cgroup_bpf_enabled) BPF_CGROUP_RUN_SA_PROG_LOCK(sk, (struct sockaddr *)sin, - peer ? BPF_CGROUP_INET6_GETPEERNAME : - BPF_CGROUP_INET6_GETSOCKNAME, + BPF_CGROUP_INET6_GETSOCKNAME, NULL); + } sin->sin6_scope_id = ipv6_iface_scope_id(&sin->sin6_addr, sk->sk_bound_dev_if); return sizeof(*sin); @@ -954,6 +958,7 @@ static int __net_init inet6_net_init(struct net *net) net->ipv6.sysctl.max_hbh_opts_cnt = IP6_DEFAULT_MAX_HBH_OPTS_CNT; net->ipv6.sysctl.max_dst_opts_len = IP6_DEFAULT_MAX_DST_OPTS_LEN; net->ipv6.sysctl.max_hbh_opts_len = IP6_DEFAULT_MAX_HBH_OPTS_LEN; + net->ipv6.sysctl.fib_notify_on_flag_change = 0; atomic_set(&net->ipv6.fib6_sernum, 1); err = ipv6_init_mibs(net); diff --git a/net/ipv6/esp6.c b/net/ipv6/esp6.c index 2b804fcebcc6..153ad103ba74 100644 --- a/net/ipv6/esp6.c +++ b/net/ipv6/esp6.c @@ -788,7 +788,7 @@ int esp6_input_done2(struct sk_buff *skb, int err) int hlen = sizeof(struct ip_esp_hdr) + crypto_aead_ivsize(aead); int hdr_len = skb_network_header_len(skb); - if (!xo || (xo && !(xo->flags & CRYPTO_DONE))) + if (!xo || !(xo->flags & CRYPTO_DONE)) kfree(ESP_SKB_CB(skb)->tmp); if (unlikely(err)) diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c index f43e27555725..ef9d022e693f 100644 --- a/net/ipv6/ip6_fib.c +++ b/net/ipv6/ip6_fib.c @@ -499,7 +499,7 @@ int fib6_tables_dump(struct net *net, struct notifier_block *nb, hlist_for_each_entry_rcu(tb, head, tb6_hlist) { err = fib6_table_dump(net, tb, w); - if (err < 0) + if (err) goto out; } } @@ -507,7 +507,8 @@ int fib6_tables_dump(struct net *net, struct notifier_block *nb, out: kfree(w); - return err; + /* The tree traversal function should never return a positive value. */ + return err > 0 ? -EINVAL : err; } static int fib6_dump_node(struct fib6_walker *w) diff --git a/net/ipv6/ip6_input.c b/net/ipv6/ip6_input.c index e96304d8a4a7..e9d2a4a409aa 100644 --- a/net/ipv6/ip6_input.c +++ b/net/ipv6/ip6_input.c @@ -32,6 +32,7 @@ #include <net/sock.h> #include <net/snmp.h> +#include <net/udp.h> #include <net/ipv6.h> #include <net/protocol.h> @@ -44,7 +45,6 @@ #include <net/inet_ecn.h> #include <net/dst_metadata.h> -INDIRECT_CALLABLE_DECLARE(void udp_v6_early_demux(struct sk_buff *)); INDIRECT_CALLABLE_DECLARE(void tcp_v6_early_demux(struct sk_buff *)); static void ip6_rcv_finish_core(struct net *net, struct sock *sk, struct sk_buff *skb) @@ -352,7 +352,6 @@ void ipv6_list_rcv(struct list_head *head, struct packet_type *pt, ip6_sublist_rcv(&sublist, curr_dev, curr_net); } -INDIRECT_CALLABLE_DECLARE(int udpv6_rcv(struct sk_buff *)); INDIRECT_CALLABLE_DECLARE(int tcp_v6_rcv(struct sk_buff *)); /* diff --git a/net/ipv6/ip6_offload.c b/net/ipv6/ip6_offload.c index a80f90bf3ae7..1b9827ff8ccf 100644 --- a/net/ipv6/ip6_offload.c +++ b/net/ipv6/ip6_offload.c @@ -15,6 +15,7 @@ #include <net/inet_common.h> #include <net/tcp.h> #include <net/udp.h> +#include <net/gro.h> #include "ip6_offload.h" diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index 077d43af8226..ff4f9ebcf7f6 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -217,6 +217,7 @@ int ip6_output(struct net *net, struct sock *sk, struct sk_buff *skb) ip6_finish_output, !(IP6CB(skb)->flags & IP6SKB_REROUTED)); } +EXPORT_SYMBOL(ip6_output); bool ip6_autoflowlabel(struct net *net, const struct ipv6_pinfo *np) { @@ -1510,7 +1511,7 @@ emsgsize: csummode = CHECKSUM_PARTIAL; if (flags & MSG_ZEROCOPY && length && sock_flag(sk, SOCK_ZEROCOPY)) { - uarg = sock_zerocopy_realloc(sk, length, skb_zcopy(skb)); + uarg = msg_zerocopy_realloc(sk, length, skb_zcopy(skb)); if (!uarg) return -ENOBUFS; extra_uref = !skb_zcopy(skb); /* only ref on new uarg */ @@ -1754,8 +1755,7 @@ alloc_new_skb: error_efault: err = -EFAULT; error: - if (uarg) - sock_zerocopy_put_abort(uarg, extra_uref); + net_zcopy_put_abort(uarg, extra_uref); cork->length -= length; IP6_INC_STATS(sock_net(sk), rt->rt6i_idev, IPSTATS_MIB_OUTDISCARDS); refcount_add(wmem_alloc_delta, &sk->sk_wmem_alloc); diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c index 76717478f173..c467c6419893 100644 --- a/net/ipv6/ndisc.c +++ b/net/ipv6/ndisc.c @@ -1173,6 +1173,7 @@ static void ndisc_router_discovery(struct sk_buff *skb) struct neighbour *neigh = NULL; struct inet6_dev *in6_dev; struct fib6_info *rt = NULL; + u32 defrtr_usr_metric; struct net *net; int lifetime; struct ndisc_options ndopts; @@ -1303,18 +1304,21 @@ static void ndisc_router_discovery(struct sk_buff *skb) return; } } - if (rt && lifetime == 0) { + /* Set default route metric as specified by user */ + defrtr_usr_metric = in6_dev->cnf.ra_defrtr_metric; + /* delete the route if lifetime is 0 or if metric needs change */ + if (rt && (lifetime == 0 || rt->fib6_metric != defrtr_usr_metric)) { ip6_del_rt(net, rt, false); rt = NULL; } - ND_PRINTK(3, info, "RA: rt: %p lifetime: %d, for dev: %s\n", - rt, lifetime, skb->dev->name); + ND_PRINTK(3, info, "RA: rt: %p lifetime: %d, metric: %d, for dev: %s\n", + rt, lifetime, defrtr_usr_metric, skb->dev->name); if (!rt && lifetime) { ND_PRINTK(3, info, "RA: adding default router\n"); rt = rt6_add_dflt_router(net, &ipv6_hdr(skb)->saddr, - skb->dev, pref); + skb->dev, pref, defrtr_usr_metric); if (!rt) { ND_PRINTK(0, err, "RA: %s failed to add default route\n", diff --git a/net/ipv6/netfilter/nft_dup_ipv6.c b/net/ipv6/netfilter/nft_dup_ipv6.c index 8b5193efb1f1..3a00d95e964e 100644 --- a/net/ipv6/netfilter/nft_dup_ipv6.c +++ b/net/ipv6/netfilter/nft_dup_ipv6.c @@ -13,8 +13,8 @@ #include <net/netfilter/ipv6/nf_dup_ipv6.h> struct nft_dup_ipv6 { - enum nft_registers sreg_addr:8; - enum nft_registers sreg_dev:8; + u8 sreg_addr; + u8 sreg_dev; }; static void nft_dup_ipv6_eval(const struct nft_expr *expr, @@ -38,16 +38,16 @@ static int nft_dup_ipv6_init(const struct nft_ctx *ctx, if (tb[NFTA_DUP_SREG_ADDR] == NULL) return -EINVAL; - priv->sreg_addr = nft_parse_register(tb[NFTA_DUP_SREG_ADDR]); - err = nft_validate_register_load(priv->sreg_addr, sizeof(struct in6_addr)); + err = nft_parse_register_load(tb[NFTA_DUP_SREG_ADDR], &priv->sreg_addr, + sizeof(struct in6_addr)); if (err < 0) return err; - if (tb[NFTA_DUP_SREG_DEV] != NULL) { - priv->sreg_dev = nft_parse_register(tb[NFTA_DUP_SREG_DEV]); - return nft_validate_register_load(priv->sreg_dev, sizeof(int)); - } - return 0; + if (tb[NFTA_DUP_SREG_DEV]) + err = nft_parse_register_load(tb[NFTA_DUP_SREG_DEV], + &priv->sreg_dev, sizeof(int)); + + return err; } static int nft_dup_ipv6_dump(struct sk_buff *skb, const struct nft_expr *expr) diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 188e114b29b4..1536f4948e86 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -81,9 +81,11 @@ enum rt6_nud_state { RT6_NUD_SUCCEED = 1 }; -static struct dst_entry *ip6_dst_check(struct dst_entry *dst, u32 cookie); +INDIRECT_CALLABLE_SCOPE +struct dst_entry *ip6_dst_check(struct dst_entry *dst, u32 cookie); static unsigned int ip6_default_advmss(const struct dst_entry *dst); -static unsigned int ip6_mtu(const struct dst_entry *dst); +INDIRECT_CALLABLE_SCOPE +unsigned int ip6_mtu(const struct dst_entry *dst); static struct dst_entry *ip6_negative_advice(struct dst_entry *); static void ip6_dst_destroy(struct dst_entry *); static void ip6_dst_ifdown(struct dst_entry *, @@ -2611,7 +2613,8 @@ static struct dst_entry *rt6_dst_from_check(struct rt6_info *rt, return NULL; } -static struct dst_entry *ip6_dst_check(struct dst_entry *dst, u32 cookie) +INDIRECT_CALLABLE_SCOPE struct dst_entry *ip6_dst_check(struct dst_entry *dst, + u32 cookie) { struct dst_entry *dst_ret; struct fib6_info *from; @@ -2641,6 +2644,7 @@ static struct dst_entry *ip6_dst_check(struct dst_entry *dst, u32 cookie) return dst_ret; } +EXPORT_INDIRECT_CALLABLE(ip6_dst_check); static struct dst_entry *ip6_negative_advice(struct dst_entry *dst) { @@ -3089,7 +3093,7 @@ static unsigned int ip6_default_advmss(const struct dst_entry *dst) return mtu; } -static unsigned int ip6_mtu(const struct dst_entry *dst) +INDIRECT_CALLABLE_SCOPE unsigned int ip6_mtu(const struct dst_entry *dst) { struct inet6_dev *idev; unsigned int mtu; @@ -3111,6 +3115,7 @@ out: return mtu - lwtunnel_headroom(dst->lwtstate, mtu); } +EXPORT_INDIRECT_CALLABLE(ip6_mtu); /* MTU selection: * 1. mtu on route is locked - use it @@ -4252,11 +4257,12 @@ struct fib6_info *rt6_get_dflt_router(struct net *net, struct fib6_info *rt6_add_dflt_router(struct net *net, const struct in6_addr *gwaddr, struct net_device *dev, - unsigned int pref) + unsigned int pref, + u32 defrtr_usr_metric) { struct fib6_config cfg = { .fc_table = l3mdev_fib_table(dev) ? : RT6_TABLE_DFLT, - .fc_metric = IP6_RT_PRIO_USER, + .fc_metric = defrtr_usr_metric, .fc_ifindex = dev->ifindex, .fc_flags = RTF_GATEWAY | RTF_ADDRCONF | RTF_DEFAULT | RTF_UP | RTF_EXPIRES | RTF_PREF(pref), @@ -5613,6 +5619,8 @@ static int rt6_fill_node(struct net *net, struct sk_buff *skb, rtm->rtm_flags |= RTM_F_OFFLOAD; if (rt->trap) rtm->rtm_flags |= RTM_F_TRAP; + if (rt->offload_failed) + rtm->rtm_flags |= RTM_F_OFFLOAD_FAILED; } if (rtnl_put_cacheinfo(skb, dst, 0, expires, dst ? dst->error : 0) < 0) @@ -6063,6 +6071,58 @@ errout: rtnl_set_sk_err(net, RTNLGRP_IPV6_ROUTE, err); } +void fib6_info_hw_flags_set(struct net *net, struct fib6_info *f6i, + bool offload, bool trap, bool offload_failed) +{ + struct sk_buff *skb; + int err; + + if (f6i->offload == offload && f6i->trap == trap && + f6i->offload_failed == offload_failed) + return; + + f6i->offload = offload; + f6i->trap = trap; + + /* 2 means send notifications only if offload_failed was changed. */ + if (net->ipv6.sysctl.fib_notify_on_flag_change == 2 && + f6i->offload_failed == offload_failed) + return; + + f6i->offload_failed = offload_failed; + + if (!rcu_access_pointer(f6i->fib6_node)) + /* The route was removed from the tree, do not send + * notfication. + */ + return; + + if (!net->ipv6.sysctl.fib_notify_on_flag_change) + return; + + skb = nlmsg_new(rt6_nlmsg_size(f6i), GFP_KERNEL); + if (!skb) { + err = -ENOBUFS; + goto errout; + } + + err = rt6_fill_node(net, skb, f6i, NULL, NULL, NULL, 0, RTM_NEWROUTE, 0, + 0, 0); + if (err < 0) { + /* -EMSGSIZE implies BUG in rt6_nlmsg_size() */ + WARN_ON(err == -EMSGSIZE); + kfree_skb(skb); + goto errout; + } + + rtnl_notify(skb, net, 0, RTNLGRP_IPV6_ROUTE, NULL, GFP_KERNEL); + return; + +errout: + rtnl_set_sk_err(net, RTNLGRP_IPV6_ROUTE, err); +} +EXPORT_SYMBOL(fib6_info_hw_flags_set); + static int ip6_route_dev_notify(struct notifier_block *this, unsigned long event, void *ptr) { diff --git a/net/ipv6/seg6_local.c b/net/ipv6/seg6_local.c index b07f7c1c82a4..c2a0c78e84d4 100644 --- a/net/ipv6/seg6_local.c +++ b/net/ipv6/seg6_local.c @@ -31,6 +31,8 @@ #include <linux/etherdevice.h> #include <linux/bpf.h> +#define SEG6_F_ATTR(i) BIT(i) + struct seg6_local_lwt; /* callbacks used for customizing the creation and destruction of a behavior */ @@ -660,8 +662,8 @@ seg6_end_dt_mode seg6_end_dt6_parse_mode(struct seg6_local_lwt *slwt) unsigned long parsed_optattrs = slwt->parsed_optattrs; bool legacy, vrfmode; - legacy = !!(parsed_optattrs & (1 << SEG6_LOCAL_TABLE)); - vrfmode = !!(parsed_optattrs & (1 << SEG6_LOCAL_VRFTABLE)); + legacy = !!(parsed_optattrs & SEG6_F_ATTR(SEG6_LOCAL_TABLE)); + vrfmode = !!(parsed_optattrs & SEG6_F_ATTR(SEG6_LOCAL_VRFTABLE)); if (!(legacy ^ vrfmode)) /* both are absent or present: invalid DT6 mode */ @@ -883,32 +885,32 @@ static struct seg6_action_desc seg6_action_table[] = { }, { .action = SEG6_LOCAL_ACTION_END_X, - .attrs = (1 << SEG6_LOCAL_NH6), + .attrs = SEG6_F_ATTR(SEG6_LOCAL_NH6), .input = input_action_end_x, }, { .action = SEG6_LOCAL_ACTION_END_T, - .attrs = (1 << SEG6_LOCAL_TABLE), + .attrs = SEG6_F_ATTR(SEG6_LOCAL_TABLE), .input = input_action_end_t, }, { .action = SEG6_LOCAL_ACTION_END_DX2, - .attrs = (1 << SEG6_LOCAL_OIF), + .attrs = SEG6_F_ATTR(SEG6_LOCAL_OIF), .input = input_action_end_dx2, }, { .action = SEG6_LOCAL_ACTION_END_DX6, - .attrs = (1 << SEG6_LOCAL_NH6), + .attrs = SEG6_F_ATTR(SEG6_LOCAL_NH6), .input = input_action_end_dx6, }, { .action = SEG6_LOCAL_ACTION_END_DX4, - .attrs = (1 << SEG6_LOCAL_NH4), + .attrs = SEG6_F_ATTR(SEG6_LOCAL_NH4), .input = input_action_end_dx4, }, { .action = SEG6_LOCAL_ACTION_END_DT4, - .attrs = (1 << SEG6_LOCAL_VRFTABLE), + .attrs = SEG6_F_ATTR(SEG6_LOCAL_VRFTABLE), #ifdef CONFIG_NET_L3_MASTER_DEV .input = input_action_end_dt4, .slwt_ops = { @@ -920,30 +922,30 @@ static struct seg6_action_desc seg6_action_table[] = { .action = SEG6_LOCAL_ACTION_END_DT6, #ifdef CONFIG_NET_L3_MASTER_DEV .attrs = 0, - .optattrs = (1 << SEG6_LOCAL_TABLE) | - (1 << SEG6_LOCAL_VRFTABLE), + .optattrs = SEG6_F_ATTR(SEG6_LOCAL_TABLE) | + SEG6_F_ATTR(SEG6_LOCAL_VRFTABLE), .slwt_ops = { .build_state = seg6_end_dt6_build, }, #else - .attrs = (1 << SEG6_LOCAL_TABLE), + .attrs = SEG6_F_ATTR(SEG6_LOCAL_TABLE), #endif .input = input_action_end_dt6, }, { .action = SEG6_LOCAL_ACTION_END_B6, - .attrs = (1 << SEG6_LOCAL_SRH), + .attrs = SEG6_F_ATTR(SEG6_LOCAL_SRH), .input = input_action_end_b6, }, { .action = SEG6_LOCAL_ACTION_END_B6_ENCAP, - .attrs = (1 << SEG6_LOCAL_SRH), + .attrs = SEG6_F_ATTR(SEG6_LOCAL_SRH), .input = input_action_end_b6_encap, .static_headroom = sizeof(struct ipv6hdr), }, { .action = SEG6_LOCAL_ACTION_END_BPF, - .attrs = (1 << SEG6_LOCAL_BPF), + .attrs = SEG6_F_ATTR(SEG6_LOCAL_BPF), .input = input_action_end_bpf, }, @@ -1366,7 +1368,7 @@ static void __destroy_attrs(unsigned long parsed_attrs, int max_parsed, * attribute; otherwise, we call the destroy() callback. */ for (i = 0; i < max_parsed; ++i) { - if (!(parsed_attrs & (1 << i))) + if (!(parsed_attrs & SEG6_F_ATTR(i))) continue; param = &seg6_action_params[i]; @@ -1395,7 +1397,7 @@ static int parse_nla_optional_attrs(struct nlattr **attrs, int err, i; for (i = 0; i < SEG6_LOCAL_MAX + 1; ++i) { - if (!(desc->optattrs & (1 << i)) || !attrs[i]) + if (!(desc->optattrs & SEG6_F_ATTR(i)) || !attrs[i]) continue; /* once here, the i-th attribute is provided by the @@ -1408,7 +1410,7 @@ static int parse_nla_optional_attrs(struct nlattr **attrs, goto parse_optattrs_err; /* current attribute has been correctly parsed */ - parsed_optattrs |= (1 << i); + parsed_optattrs |= SEG6_F_ATTR(i); } /* store in the tunnel state all the optional attributed successfully @@ -1494,7 +1496,7 @@ static int parse_nla_action(struct nlattr **attrs, struct seg6_local_lwt *slwt) /* parse the required attributes */ for (i = 0; i < SEG6_LOCAL_MAX + 1; i++) { - if (desc->attrs & (1 << i)) { + if (desc->attrs & SEG6_F_ATTR(i)) { if (!attrs[i]) return -EINVAL; @@ -1599,7 +1601,7 @@ static int seg6_local_fill_encap(struct sk_buff *skb, attrs = slwt->desc->attrs | slwt->parsed_optattrs; for (i = 0; i < SEG6_LOCAL_MAX + 1; i++) { - if (attrs & (1 << i)) { + if (attrs & SEG6_F_ATTR(i)) { param = &seg6_action_params[i]; err = param->put(skb, slwt); if (err < 0) @@ -1620,30 +1622,30 @@ static int seg6_local_get_encap_size(struct lwtunnel_state *lwt) attrs = slwt->desc->attrs | slwt->parsed_optattrs; - if (attrs & (1 << SEG6_LOCAL_SRH)) + if (attrs & SEG6_F_ATTR(SEG6_LOCAL_SRH)) nlsize += nla_total_size((slwt->srh->hdrlen + 1) << 3); - if (attrs & (1 << SEG6_LOCAL_TABLE)) + if (attrs & SEG6_F_ATTR(SEG6_LOCAL_TABLE)) nlsize += nla_total_size(4); - if (attrs & (1 << SEG6_LOCAL_NH4)) + if (attrs & SEG6_F_ATTR(SEG6_LOCAL_NH4)) nlsize += nla_total_size(4); - if (attrs & (1 << SEG6_LOCAL_NH6)) + if (attrs & SEG6_F_ATTR(SEG6_LOCAL_NH6)) nlsize += nla_total_size(16); - if (attrs & (1 << SEG6_LOCAL_IIF)) + if (attrs & SEG6_F_ATTR(SEG6_LOCAL_IIF)) nlsize += nla_total_size(4); - if (attrs & (1 << SEG6_LOCAL_OIF)) + if (attrs & SEG6_F_ATTR(SEG6_LOCAL_OIF)) nlsize += nla_total_size(4); - if (attrs & (1 << SEG6_LOCAL_BPF)) + if (attrs & SEG6_F_ATTR(SEG6_LOCAL_BPF)) nlsize += nla_total_size(sizeof(struct nlattr)) + nla_total_size(MAX_PROG_NAME) + nla_total_size(4); - if (attrs & (1 << SEG6_LOCAL_VRFTABLE)) + if (attrs & SEG6_F_ATTR(SEG6_LOCAL_VRFTABLE)) nlsize += nla_total_size(4); return nlsize; @@ -1670,7 +1672,7 @@ static int seg6_local_cmp_encap(struct lwtunnel_state *a, return 1; for (i = 0; i < SEG6_LOCAL_MAX + 1; i++) { - if (attrs_a & (1 << i)) { + if (attrs_a & SEG6_F_ATTR(i)) { param = &seg6_action_params[i]; if (param->cmp(slwt_a, slwt_b)) return 1; @@ -1692,6 +1694,15 @@ static const struct lwtunnel_encap_ops seg6_local_ops = { int __init seg6_local_init(void) { + /* If the max total number of defined attributes is reached, then your + * kernel build stops here. + * + * This check is required to avoid arithmetic overflows when processing + * behavior attributes and the maximum number of defined attributes + * exceeds the allowed value. + */ + BUILD_BUG_ON(SEG6_LOCAL_MAX + 1 > BITS_PER_TYPE(unsigned long)); + return lwtunnel_encap_add_ops(&seg6_local_ops, LWTUNNEL_ENCAP_SEG6_LOCAL); } diff --git a/net/ipv6/sysctl_net_ipv6.c b/net/ipv6/sysctl_net_ipv6.c index 5b60a4bdd36a..263ab43ed06b 100644 --- a/net/ipv6/sysctl_net_ipv6.c +++ b/net/ipv6/sysctl_net_ipv6.c @@ -160,6 +160,15 @@ static struct ctl_table ipv6_table_template[] = { .mode = 0644, .proc_handler = proc_dointvec }, + { + .procname = "fib_notify_on_flag_change", + .data = &init_net.ipv6.sysctl.fib_notify_on_flag_change, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = SYSCTL_ZERO, + .extra2 = &two, + }, { } }; diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 0e1509b02cb3..bd44ded7e50c 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -1420,6 +1420,8 @@ out: return NULL; } +INDIRECT_CALLABLE_DECLARE(struct dst_entry *ipv4_dst_check(struct dst_entry *, + u32)); /* The socket must have it's spinlock held when we get * here, unless it is a TCP_LISTEN socket. * @@ -1473,7 +1475,8 @@ static int tcp_v6_do_rcv(struct sock *sk, struct sk_buff *skb) sk_mark_napi_id(sk, skb); if (dst) { if (inet_sk(sk)->rx_dst_ifindex != skb->skb_iif || - dst->ops->check(dst, np->rx_dst_cookie) == NULL) { + INDIRECT_CALL_1(dst->ops->check, ip6_dst_check, + dst, np->rx_dst_cookie) == NULL) { dst_release(dst); sk->sk_rx_dst = NULL; } @@ -2121,6 +2124,7 @@ struct proto tcpv6_prot = { .shutdown = tcp_shutdown, .setsockopt = tcp_setsockopt, .getsockopt = tcp_getsockopt, + .bpf_bypass_getsockopt = tcp_bpf_bypass_getsockopt, .keepalive = tcp_set_keepalive, .recvmsg = tcp_recvmsg, .sendmsg = tcp_sendmsg, diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index b9f3dfdd2383..d25e5a9252fd 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -409,9 +409,8 @@ try_again: } *addr_len = sizeof(*sin6); - if (cgroup_bpf_enabled) - BPF_CGROUP_RUN_PROG_UDP6_RECVMSG_LOCK(sk, - (struct sockaddr *)sin6); + BPF_CGROUP_RUN_PROG_UDP6_RECVMSG_LOCK(sk, + (struct sockaddr *)sin6); } if (udp_sk(sk)->gro_enabled) @@ -1462,7 +1461,7 @@ do_udp_sendmsg: fl6.saddr = np->saddr; fl6.fl6_sport = inet->inet_sport; - if (cgroup_bpf_enabled && !connected) { + if (cgroup_bpf_enabled(BPF_CGROUP_UDP6_SENDMSG) && !connected) { err = BPF_CGROUP_RUN_PROG_UDP6_SENDMSG_LOCK(sk, (struct sockaddr *)sin6, &fl6.saddr); if (err) @@ -1608,8 +1607,10 @@ void udpv6_destroy_sock(struct sock *sk) if (encap_destroy) encap_destroy(sk); } - if (up->encap_enabled) + if (up->encap_enabled) { static_branch_dec(&udpv6_encap_needed_key); + udp_encap_disable(); + } } inet6_destroy_sock(sk); diff --git a/net/iucv/af_iucv.c b/net/iucv/af_iucv.c index 882f028992c3..6092d5cb7168 100644 --- a/net/iucv/af_iucv.c +++ b/net/iucv/af_iucv.c @@ -89,7 +89,7 @@ static struct sock *iucv_accept_dequeue(struct sock *parent, static void iucv_sock_kill(struct sock *sk); static void iucv_sock_close(struct sock *sk); -static void afiucv_hs_callback_txnotify(struct sk_buff *, enum iucv_tx_notify); +static void afiucv_hs_callback_txnotify(struct sock *sk, enum iucv_tx_notify); /* Call Back functions */ static void iucv_callback_rx(struct iucv_path *, struct iucv_message *); @@ -182,7 +182,7 @@ static inline int iucv_below_msglim(struct sock *sk) if (sk->sk_state != IUCV_CONNECTED) return 1; if (iucv->transport == AF_IUCV_TRANS_IUCV) - return (skb_queue_len(&iucv->send_skb_q) < iucv->path->msglim); + return (atomic_read(&iucv->skbs_in_xmit) < iucv->path->msglim); else return ((atomic_read(&iucv->msg_sent) < iucv->msglimit_peer) && (atomic_read(&iucv->pendings) <= 0)); @@ -211,7 +211,6 @@ static int afiucv_hs_send(struct iucv_message *imsg, struct sock *sock, { struct iucv_sock *iucv = iucv_sk(sock); struct af_iucv_trans_hdr *phs_hdr; - struct sk_buff *nskb; int err, confirm_recv = 0; phs_hdr = skb_push(skb, sizeof(*phs_hdr)); @@ -257,22 +256,16 @@ static int afiucv_hs_send(struct iucv_message *imsg, struct sock *sock, err = -EMSGSIZE; goto err_free; } - skb_trim(skb, skb->dev->mtu); + err = pskb_trim(skb, skb->dev->mtu); + if (err) + goto err_free; } skb->protocol = cpu_to_be16(ETH_P_AF_IUCV); - __skb_header_release(skb); - nskb = skb_clone(skb, GFP_ATOMIC); - if (!nskb) { - err = -ENOMEM; - goto err_free; - } - - skb_queue_tail(&iucv->send_skb_q, nskb); + atomic_inc(&iucv->skbs_in_xmit); err = dev_queue_xmit(skb); if (net_xmit_eval(err)) { - skb_unlink(nskb, &iucv->send_skb_q); - kfree_skb(nskb); + atomic_dec(&iucv->skbs_in_xmit); } else { atomic_sub(confirm_recv, &iucv->msg_recv); WARN_ON(atomic_read(&iucv->msg_recv) < 0); @@ -424,7 +417,7 @@ static void iucv_sock_close(struct sock *sk) sk->sk_state = IUCV_CLOSING; sk->sk_state_change(sk); - if (!err && !skb_queue_empty(&iucv->send_skb_q)) { + if (!err && atomic_read(&iucv->skbs_in_xmit) > 0) { if (sock_flag(sk, SOCK_LINGER) && sk->sk_lingertime) timeo = sk->sk_lingertime; else @@ -491,6 +484,7 @@ static struct sock *iucv_sock_alloc(struct socket *sock, int proto, gfp_t prio, atomic_set(&iucv->pendings, 0); iucv->flags = 0; iucv->msglimit = 0; + atomic_set(&iucv->skbs_in_xmit, 0); atomic_set(&iucv->msg_sent, 0); atomic_set(&iucv->msg_recv, 0); iucv->path = NULL; @@ -1004,7 +998,7 @@ static int iucv_sock_sendmsg(struct socket *sock, struct msghdr *msg, if (iucv->transport == AF_IUCV_TRANS_HIPER) { headroom = sizeof(struct af_iucv_trans_hdr) + LL_RESERVED_SPACE(iucv->hs_dev); - linear = len; + linear = min(len, PAGE_SIZE - headroom); } else { if (len < PAGE_SIZE) { linear = len; @@ -1055,6 +1049,7 @@ static int iucv_sock_sendmsg(struct socket *sock, struct msghdr *msg, } } else { /* Classic VM IUCV transport */ skb_queue_tail(&iucv->send_skb_q, skb); + atomic_inc(&iucv->skbs_in_xmit); if (((iucv->path->flags & IUCV_IPRMDATA) & iucv->flags) && skb->len <= 7) { @@ -1063,6 +1058,7 @@ static int iucv_sock_sendmsg(struct socket *sock, struct msghdr *msg, /* on success: there is no message_complete callback */ /* for an IPRMDATA msg; remove skb from send queue */ if (err == 0) { + atomic_dec(&iucv->skbs_in_xmit); skb_unlink(skb, &iucv->send_skb_q); kfree_skb(skb); } @@ -1071,6 +1067,7 @@ static int iucv_sock_sendmsg(struct socket *sock, struct msghdr *msg, /* IUCV_IPRMDATA path flag is set... sever path */ if (err == 0x15) { pr_iucv->path_sever(iucv->path, NULL); + atomic_dec(&iucv->skbs_in_xmit); skb_unlink(skb, &iucv->send_skb_q); err = -EPIPE; goto fail; @@ -1109,6 +1106,8 @@ static int iucv_sock_sendmsg(struct socket *sock, struct msghdr *msg, } else { err = -EPIPE; } + + atomic_dec(&iucv->skbs_in_xmit); skb_unlink(skb, &iucv->send_skb_q); goto fail; } @@ -1748,10 +1747,14 @@ static void iucv_callback_txdone(struct iucv_path *path, { struct sock *sk = path->private; struct sk_buff *this = NULL; - struct sk_buff_head *list = &iucv_sk(sk)->send_skb_q; + struct sk_buff_head *list; struct sk_buff *list_skb; + struct iucv_sock *iucv; unsigned long flags; + iucv = iucv_sk(sk); + list = &iucv->send_skb_q; + bh_lock_sock(sk); spin_lock_irqsave(&list->lock, flags); @@ -1761,8 +1764,11 @@ static void iucv_callback_txdone(struct iucv_path *path, break; } } - if (this) + if (this) { + atomic_dec(&iucv->skbs_in_xmit); __skb_unlink(this, list); + } + spin_unlock_irqrestore(&list->lock, flags); if (this) { @@ -1772,7 +1778,7 @@ static void iucv_callback_txdone(struct iucv_path *path, } if (sk->sk_state == IUCV_CLOSING) { - if (skb_queue_empty(&iucv_sk(sk)->send_skb_q)) { + if (atomic_read(&iucv->skbs_in_xmit) == 0) { sk->sk_state = IUCV_CLOSED; sk->sk_state_change(sk); } @@ -2036,7 +2042,6 @@ static int afiucv_hs_rcv(struct sk_buff *skb, struct net_device *dev, char nullstring[8]; if (!pskb_may_pull(skb, sizeof(*trans_hdr))) { - WARN_ONCE(1, "AF_IUCV failed to receive skb, len=%u", skb->len); kfree_skb(skb); return NET_RX_SUCCESS; } @@ -2132,73 +2137,40 @@ static int afiucv_hs_rcv(struct sk_buff *skb, struct net_device *dev, * afiucv_hs_callback_txnotify() - handle send notifcations from HiperSockets * transport **/ -static void afiucv_hs_callback_txnotify(struct sk_buff *skb, - enum iucv_tx_notify n) +static void afiucv_hs_callback_txnotify(struct sock *sk, enum iucv_tx_notify n) { - struct sock *isk = skb->sk; - struct sock *sk = NULL; - struct iucv_sock *iucv = NULL; - struct sk_buff_head *list; - struct sk_buff *list_skb; - struct sk_buff *nskb; - unsigned long flags; - - read_lock_irqsave(&iucv_sk_list.lock, flags); - sk_for_each(sk, &iucv_sk_list.head) - if (sk == isk) { - iucv = iucv_sk(sk); - break; - } - read_unlock_irqrestore(&iucv_sk_list.lock, flags); + struct iucv_sock *iucv = iucv_sk(sk); - if (!iucv || sock_flag(sk, SOCK_ZAPPED)) + if (sock_flag(sk, SOCK_ZAPPED)) return; - list = &iucv->send_skb_q; - spin_lock_irqsave(&list->lock, flags); - skb_queue_walk_safe(list, list_skb, nskb) { - if (skb_shinfo(list_skb) == skb_shinfo(skb)) { - switch (n) { - case TX_NOTIFY_OK: - __skb_unlink(list_skb, list); - kfree_skb(list_skb); - iucv_sock_wake_msglim(sk); - break; - case TX_NOTIFY_PENDING: - atomic_inc(&iucv->pendings); - break; - case TX_NOTIFY_DELAYED_OK: - __skb_unlink(list_skb, list); - atomic_dec(&iucv->pendings); - if (atomic_read(&iucv->pendings) <= 0) - iucv_sock_wake_msglim(sk); - kfree_skb(list_skb); - break; - case TX_NOTIFY_UNREACHABLE: - case TX_NOTIFY_DELAYED_UNREACHABLE: - case TX_NOTIFY_TPQFULL: /* not yet used */ - case TX_NOTIFY_GENERALERROR: - case TX_NOTIFY_DELAYED_GENERALERROR: - __skb_unlink(list_skb, list); - kfree_skb(list_skb); - if (sk->sk_state == IUCV_CONNECTED) { - sk->sk_state = IUCV_DISCONN; - sk->sk_state_change(sk); - } - break; - } - break; + switch (n) { + case TX_NOTIFY_OK: + atomic_dec(&iucv->skbs_in_xmit); + iucv_sock_wake_msglim(sk); + break; + case TX_NOTIFY_PENDING: + atomic_inc(&iucv->pendings); + break; + case TX_NOTIFY_DELAYED_OK: + atomic_dec(&iucv->skbs_in_xmit); + if (atomic_dec_return(&iucv->pendings) <= 0) + iucv_sock_wake_msglim(sk); + break; + default: + atomic_dec(&iucv->skbs_in_xmit); + if (sk->sk_state == IUCV_CONNECTED) { + sk->sk_state = IUCV_DISCONN; + sk->sk_state_change(sk); } } - spin_unlock_irqrestore(&list->lock, flags); if (sk->sk_state == IUCV_CLOSING) { - if (skb_queue_empty(&iucv_sk(sk)->send_skb_q)) { + if (atomic_read(&iucv->skbs_in_xmit) == 0) { sk->sk_state = IUCV_CLOSED; sk->sk_state_change(sk); } } - } /* diff --git a/net/kcm/kcmsock.c b/net/kcm/kcmsock.c index 56dad9565bc9..d0b56ffbb057 100644 --- a/net/kcm/kcmsock.c +++ b/net/kcm/kcmsock.c @@ -786,7 +786,7 @@ static ssize_t kcm_sendpage(struct socket *sock, struct page *page, if (skb_can_coalesce(skb, i, page, offset)) { skb_frag_size_add(&skb_shinfo(skb)->frags[i - 1], size); - skb_shinfo(skb)->tx_flags |= SKBTX_SHARED_FRAG; + skb_shinfo(skb)->flags |= SKBFL_SHARED_FRAG; goto coalesced; } @@ -834,7 +834,7 @@ static ssize_t kcm_sendpage(struct socket *sock, struct page *page, get_page(page); skb_fill_page_desc(skb, i, page, offset, size); - skb_shinfo(skb)->tx_flags |= SKBTX_SHARED_FRAG; + skb_shinfo(skb)->flags |= SKBFL_SHARED_FRAG; coalesced: skb->len += size; @@ -1496,7 +1496,7 @@ static int kcm_attach_ioctl(struct socket *sock, struct kcm_attach *info) return 0; out: - fput(csock->file); + sockfd_put(csock); return err; } @@ -1644,7 +1644,7 @@ static int kcm_unattach_ioctl(struct socket *sock, struct kcm_unattach *info) spin_unlock_bh(&mux->lock); out: - fput(csock->file); + sockfd_put(csock); return err; } diff --git a/net/l3mdev/Makefile b/net/l3mdev/Makefile index 59755a9e2f9b..9e7da0acc58c 100644 --- a/net/l3mdev/Makefile +++ b/net/l3mdev/Makefile @@ -3,4 +3,4 @@ # Makefile for the L3 device API # -obj-$(CONFIG_NET_L3_MASTER_DEV) += l3mdev.o +obj-y += l3mdev.o diff --git a/net/llc/Kconfig b/net/llc/Kconfig index b0e646ac47eb..7f79f5e134f9 100644 --- a/net/llc/Kconfig +++ b/net/llc/Kconfig @@ -1,7 +1,6 @@ # SPDX-License-Identifier: GPL-2.0-only config LLC tristate - depends on NET config LLC2 tristate "ANSI/IEEE 802.2 LLC type 2 Support" diff --git a/net/mac80211/Makefile b/net/mac80211/Makefile index ad04c361cba5..23d25e8b2358 100644 --- a/net/mac80211/Makefile +++ b/net/mac80211/Makefile @@ -56,11 +56,9 @@ mac80211-$(CONFIG_PM) += pm.o CFLAGS_trace.o := -I$(src) rc80211_minstrel-y := \ - rc80211_minstrel.o \ rc80211_minstrel_ht.o rc80211_minstrel-$(CONFIG_MAC80211_DEBUGFS) += \ - rc80211_minstrel_debugfs.o \ rc80211_minstrel_ht_debugfs.o mac80211-$(CONFIG_MAC80211_RC_MINSTREL) += $(rc80211_minstrel-y) diff --git a/net/mac80211/debugfs.c b/net/mac80211/debugfs.c index 9e723d943421..5296898875ff 100644 --- a/net/mac80211/debugfs.c +++ b/net/mac80211/debugfs.c @@ -281,6 +281,56 @@ static const struct file_operations aql_txq_limit_ops = { .llseek = default_llseek, }; +static ssize_t aql_enable_read(struct file *file, char __user *user_buf, + size_t count, loff_t *ppos) +{ + char buf[3]; + int len; + + len = scnprintf(buf, sizeof(buf), "%d\n", + !static_key_false(&aql_disable.key)); + + return simple_read_from_buffer(user_buf, count, ppos, buf, len); +} + +static ssize_t aql_enable_write(struct file *file, const char __user *user_buf, + size_t count, loff_t *ppos) +{ + bool aql_disabled = static_key_false(&aql_disable.key); + char buf[3]; + size_t len; + + if (count > sizeof(buf)) + return -EINVAL; + + if (copy_from_user(buf, user_buf, count)) + return -EFAULT; + + buf[sizeof(buf) - 1] = '\0'; + len = strlen(buf); + if (len > 0 && buf[len - 1] == '\n') + buf[len - 1] = 0; + + if (buf[0] == '0' && buf[1] == '\0') { + if (!aql_disabled) + static_branch_inc(&aql_disable); + } else if (buf[0] == '1' && buf[1] == '\0') { + if (aql_disabled) + static_branch_dec(&aql_disable); + } else { + return -EINVAL; + } + + return count; +} + +static const struct file_operations aql_enable_ops = { + .write = aql_enable_write, + .read = aql_enable_read, + .open = simple_open, + .llseek = default_llseek, +}; + static ssize_t force_tx_status_read(struct file *file, char __user *user_buf, size_t count, @@ -405,6 +455,7 @@ static const char *hw_flag_names[] = { FLAG(SUPPORTS_ONLY_HE_MULTI_BSSID), FLAG(AMPDU_KEYBORDER_SUPPORT), FLAG(SUPPORTS_TX_ENCAP_OFFLOAD), + FLAG(SUPPORTS_RX_DECAP_OFFLOAD), #undef FLAG }; @@ -568,6 +619,7 @@ void debugfs_hw_add(struct ieee80211_local *local) DEBUGFS_ADD(power); DEBUGFS_ADD(hw_conf); DEBUGFS_ADD_MODE(force_tx_status, 0600); + DEBUGFS_ADD_MODE(aql_enable, 0600); if (local->ops->wake_tx_queue) DEBUGFS_ADD_MODE(aqm, 0600); diff --git a/net/mac80211/debugfs_sta.c b/net/mac80211/debugfs_sta.c index eb4bb79d936a..5a27c61a7b38 100644 --- a/net/mac80211/debugfs_sta.c +++ b/net/mac80211/debugfs_sta.c @@ -79,6 +79,7 @@ static const char * const sta_flag_names[] = { FLAG(MPSP_RECIPIENT), FLAG(PS_DELIVER), FLAG(USES_ENCRYPTION), + FLAG(DECAP_OFFLOAD), #undef FLAG }; diff --git a/net/mac80211/driver-ops.h b/net/mac80211/driver-ops.h index bcdfd19a596b..604ca59937f0 100644 --- a/net/mac80211/driver-ops.h +++ b/net/mac80211/driver-ops.h @@ -1413,4 +1413,20 @@ static inline void drv_sta_set_4addr(struct ieee80211_local *local, trace_drv_return_void(local); } +static inline void drv_sta_set_decap_offload(struct ieee80211_local *local, + struct ieee80211_sub_if_data *sdata, + struct ieee80211_sta *sta, + bool enabled) +{ + sdata = get_bss_sdata(sdata); + if (!check_sdata_in_driver(sdata)) + return; + + trace_drv_sta_set_decap_offload(local, sdata, sta, enabled); + if (local->ops->sta_set_decap_offload) + local->ops->sta_set_decap_offload(&local->hw, &sdata->vif, sta, + enabled); + trace_drv_return_void(local); +} + #endif /* __MAC80211_DRIVER_OPS */ diff --git a/net/mac80211/he.c b/net/mac80211/he.c index cc26f239838b..0c0b970835ce 100644 --- a/net/mac80211/he.c +++ b/net/mac80211/he.c @@ -52,6 +52,57 @@ ieee80211_update_from_he_6ghz_capa(const struct ieee80211_he_6ghz_capa *he_6ghz_ sta->sta.he_6ghz_capa = *he_6ghz_capa; } +static void ieee80211_he_mcs_disable(__le16 *he_mcs) +{ + u32 i; + + for (i = 0; i < 8; i++) + *he_mcs |= cpu_to_le16(IEEE80211_HE_MCS_NOT_SUPPORTED << i * 2); +} + +static void ieee80211_he_mcs_intersection(__le16 *he_own_rx, __le16 *he_peer_rx, + __le16 *he_own_tx, __le16 *he_peer_tx) +{ + u32 i; + u16 own_rx, own_tx, peer_rx, peer_tx; + + for (i = 0; i < 8; i++) { + own_rx = le16_to_cpu(*he_own_rx); + own_rx = (own_rx >> i * 2) & IEEE80211_HE_MCS_NOT_SUPPORTED; + + own_tx = le16_to_cpu(*he_own_tx); + own_tx = (own_tx >> i * 2) & IEEE80211_HE_MCS_NOT_SUPPORTED; + + peer_rx = le16_to_cpu(*he_peer_rx); + peer_rx = (peer_rx >> i * 2) & IEEE80211_HE_MCS_NOT_SUPPORTED; + + peer_tx = le16_to_cpu(*he_peer_tx); + peer_tx = (peer_tx >> i * 2) & IEEE80211_HE_MCS_NOT_SUPPORTED; + + if (peer_tx != IEEE80211_HE_MCS_NOT_SUPPORTED) { + if (own_rx == IEEE80211_HE_MCS_NOT_SUPPORTED) + peer_tx = IEEE80211_HE_MCS_NOT_SUPPORTED; + else if (own_rx < peer_tx) + peer_tx = own_rx; + } + + if (peer_rx != IEEE80211_HE_MCS_NOT_SUPPORTED) { + if (own_tx == IEEE80211_HE_MCS_NOT_SUPPORTED) + peer_rx = IEEE80211_HE_MCS_NOT_SUPPORTED; + else if (own_tx < peer_rx) + peer_rx = own_tx; + } + + *he_peer_rx &= + ~cpu_to_le16(IEEE80211_HE_MCS_NOT_SUPPORTED << i * 2); + *he_peer_rx |= cpu_to_le16(peer_rx << i * 2); + + *he_peer_tx &= + ~cpu_to_le16(IEEE80211_HE_MCS_NOT_SUPPORTED << i * 2); + *he_peer_tx |= cpu_to_le16(peer_tx << i * 2); + } +} + void ieee80211_he_cap_ie_to_sta_he_cap(struct ieee80211_sub_if_data *sdata, struct ieee80211_supported_band *sband, @@ -60,10 +111,12 @@ ieee80211_he_cap_ie_to_sta_he_cap(struct ieee80211_sub_if_data *sdata, struct sta_info *sta) { struct ieee80211_sta_he_cap *he_cap = &sta->sta.he_cap; + struct ieee80211_sta_he_cap own_he_cap = sband->iftype_data->he_cap; struct ieee80211_he_cap_elem *he_cap_ie_elem = (void *)he_cap_ie; u8 he_ppe_size; u8 mcs_nss_size; u8 he_total_size; + bool own_160, peer_160, own_80p80, peer_80p80; memset(he_cap, 0, sizeof(*he_cap)); @@ -101,6 +154,45 @@ ieee80211_he_cap_ie_to_sta_he_cap(struct ieee80211_sub_if_data *sdata, if (sband->band == NL80211_BAND_6GHZ && he_6ghz_capa) ieee80211_update_from_he_6ghz_capa(he_6ghz_capa, sta); + + ieee80211_he_mcs_intersection(&own_he_cap.he_mcs_nss_supp.rx_mcs_80, + &he_cap->he_mcs_nss_supp.rx_mcs_80, + &own_he_cap.he_mcs_nss_supp.tx_mcs_80, + &he_cap->he_mcs_nss_supp.tx_mcs_80); + + own_160 = own_he_cap.he_cap_elem.phy_cap_info[0] & + IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_160MHZ_IN_5G; + peer_160 = he_cap->he_cap_elem.phy_cap_info[0] & + IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_160MHZ_IN_5G; + + if (peer_160 && own_160) { + ieee80211_he_mcs_intersection(&own_he_cap.he_mcs_nss_supp.rx_mcs_160, + &he_cap->he_mcs_nss_supp.rx_mcs_160, + &own_he_cap.he_mcs_nss_supp.tx_mcs_160, + &he_cap->he_mcs_nss_supp.tx_mcs_160); + } else if (peer_160 && !own_160) { + ieee80211_he_mcs_disable(&he_cap->he_mcs_nss_supp.rx_mcs_160); + ieee80211_he_mcs_disable(&he_cap->he_mcs_nss_supp.tx_mcs_160); + he_cap->he_cap_elem.phy_cap_info[0] &= + ~IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_160MHZ_IN_5G; + } + + own_80p80 = own_he_cap.he_cap_elem.phy_cap_info[0] & + IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_80PLUS80_MHZ_IN_5G; + peer_80p80 = he_cap->he_cap_elem.phy_cap_info[0] & + IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_80PLUS80_MHZ_IN_5G; + + if (peer_80p80 && own_80p80) { + ieee80211_he_mcs_intersection(&own_he_cap.he_mcs_nss_supp.rx_mcs_80p80, + &he_cap->he_mcs_nss_supp.rx_mcs_80p80, + &own_he_cap.he_mcs_nss_supp.tx_mcs_80p80, + &he_cap->he_mcs_nss_supp.tx_mcs_80p80); + } else if (peer_80p80 && !own_80p80) { + ieee80211_he_mcs_disable(&he_cap->he_mcs_nss_supp.rx_mcs_80p80); + ieee80211_he_mcs_disable(&he_cap->he_mcs_nss_supp.tx_mcs_80p80); + he_cap->he_cap_elem.phy_cap_info[0] &= + ~IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_80PLUS80_MHZ_IN_5G; + } } void diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h index 8e281c2e644d..ecda126a7026 100644 --- a/net/mac80211/ieee80211_i.h +++ b/net/mac80211/ieee80211_i.h @@ -848,7 +848,6 @@ enum txq_info_flags { */ struct txq_info { struct fq_tin tin; - struct fq_flow def_flow; struct codel_vars def_cvars; struct codel_stats cstats; struct sk_buff_head frags; @@ -1144,6 +1143,8 @@ enum mac80211_scan_state { SCAN_ABORT, }; +DECLARE_STATIC_KEY_FALSE(aql_disable); + struct ieee80211_local { /* embed the driver visible part. * don't cast (use the static inlines below), but we keep diff --git a/net/mac80211/iface.c b/net/mac80211/iface.c index b31417f40bd5..b80c9b016b2b 100644 --- a/net/mac80211/iface.c +++ b/net/mac80211/iface.c @@ -357,11 +357,14 @@ static int ieee80211_open(struct net_device *dev) if (err) return err; - return ieee80211_do_open(&sdata->wdev, true); + wiphy_lock(sdata->local->hw.wiphy); + err = ieee80211_do_open(&sdata->wdev, true); + wiphy_unlock(sdata->local->hw.wiphy); + + return err; } -static void ieee80211_do_stop(struct ieee80211_sub_if_data *sdata, - bool going_down) +static void ieee80211_do_stop(struct ieee80211_sub_if_data *sdata, bool going_down) { struct ieee80211_local *local = sdata->local; unsigned long flags; @@ -637,7 +640,9 @@ static int ieee80211_stop(struct net_device *dev) { struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); + wiphy_lock(sdata->local->hw.wiphy); ieee80211_do_stop(sdata, true); + wiphy_unlock(sdata->local->hw.wiphy); return 0; } @@ -765,7 +770,7 @@ static const struct net_device_ops ieee80211_dataif_8023_ops = { .ndo_get_stats64 = ieee80211_get_stats64, }; -static bool ieee80211_iftype_supports_encap_offload(enum nl80211_iftype iftype) +static bool ieee80211_iftype_supports_hdr_offload(enum nl80211_iftype iftype) { switch (iftype) { /* P2P GO and client are mapped to AP/STATION types */ @@ -785,7 +790,7 @@ static bool ieee80211_set_sdata_offload_flags(struct ieee80211_sub_if_data *sdat flags = sdata->vif.offload_flags; if (ieee80211_hw_check(&local->hw, SUPPORTS_TX_ENCAP_OFFLOAD) && - ieee80211_iftype_supports_encap_offload(sdata->vif.type)) { + ieee80211_iftype_supports_hdr_offload(sdata->vif.type)) { flags |= IEEE80211_OFFLOAD_ENCAP_ENABLED; if (!ieee80211_hw_check(&local->hw, SUPPORTS_TX_FRAG) && @@ -798,10 +803,21 @@ static bool ieee80211_set_sdata_offload_flags(struct ieee80211_sub_if_data *sdat flags &= ~IEEE80211_OFFLOAD_ENCAP_ENABLED; } + if (ieee80211_hw_check(&local->hw, SUPPORTS_RX_DECAP_OFFLOAD) && + ieee80211_iftype_supports_hdr_offload(sdata->vif.type)) { + flags |= IEEE80211_OFFLOAD_DECAP_ENABLED; + + if (local->monitors) + flags &= ~IEEE80211_OFFLOAD_DECAP_ENABLED; + } else { + flags &= ~IEEE80211_OFFLOAD_DECAP_ENABLED; + } + if (sdata->vif.offload_flags == flags) return false; sdata->vif.offload_flags = flags; + ieee80211_check_fast_rx_iface(sdata); return true; } @@ -819,7 +835,7 @@ static void ieee80211_set_vif_encap_ops(struct ieee80211_sub_if_data *sdata) } if (!ieee80211_hw_check(&local->hw, SUPPORTS_TX_ENCAP_OFFLOAD) || - !ieee80211_iftype_supports_encap_offload(bss->vif.type)) + !ieee80211_iftype_supports_hdr_offload(bss->vif.type)) return; enabled = bss->vif.offload_flags & IEEE80211_OFFLOAD_ENCAP_ENABLED; @@ -1971,7 +1987,7 @@ int ieee80211_if_add(struct ieee80211_local *local, const char *name, ndev->min_mtu = 256; ndev->max_mtu = local->hw.max_mtu; - ret = register_netdevice(ndev); + ret = cfg80211_register_netdevice(ndev); if (ret) { free_netdev(ndev); return ret; @@ -2001,10 +2017,9 @@ void ieee80211_if_remove(struct ieee80211_sub_if_data *sdata) synchronize_rcu(); - if (sdata->dev) { - unregister_netdevice(sdata->dev); - } else { - cfg80211_unregister_wdev(&sdata->wdev); + cfg80211_unregister_wdev(&sdata->wdev); + + if (!sdata->dev) { ieee80211_teardown_sdata(sdata); kfree(sdata); } @@ -2053,13 +2068,16 @@ void ieee80211_remove_interfaces(struct ieee80211_local *local) list_add(&sdata->list, &wdev_list); } mutex_unlock(&local->iflist_mtx); + unregister_netdevice_many(&unreg_list); + wiphy_lock(local->hw.wiphy); list_for_each_entry_safe(sdata, tmp, &wdev_list, list) { list_del(&sdata->list); cfg80211_unregister_wdev(&sdata->wdev); kfree(sdata); } + wiphy_unlock(local->hw.wiphy); } static int netdev_notify(struct notifier_block *nb, diff --git a/net/mac80211/key.c b/net/mac80211/key.c index a4817aa4b171..56c068cb49c4 100644 --- a/net/mac80211/key.c +++ b/net/mac80211/key.c @@ -887,7 +887,7 @@ void ieee80211_reenable_keys(struct ieee80211_sub_if_data *sdata) struct ieee80211_key *key; struct ieee80211_sub_if_data *vlan; - ASSERT_RTNL(); + lockdep_assert_wiphy(sdata->local->hw.wiphy); mutex_lock(&sdata->local->key_mtx); @@ -924,7 +924,7 @@ void ieee80211_iter_keys(struct ieee80211_hw *hw, struct ieee80211_key *key, *tmp; struct ieee80211_sub_if_data *sdata; - ASSERT_RTNL(); + lockdep_assert_wiphy(hw->wiphy); mutex_lock(&local->key_mtx); if (vif) { diff --git a/net/mac80211/main.c b/net/mac80211/main.c index dee88ec566ad..4f3f8bb58e76 100644 --- a/net/mac80211/main.c +++ b/net/mac80211/main.c @@ -261,7 +261,9 @@ static void ieee80211_restart_work(struct work_struct *work) "%s called with hardware scan in progress\n", __func__); flush_work(&local->radar_detected_work); + /* we might do interface manipulations, so need both */ rtnl_lock(); + wiphy_lock(local->hw.wiphy); list_for_each_entry(sdata, &local->interfaces, list) { /* * XXX: there may be more work for other vif types and even @@ -293,6 +295,7 @@ static void ieee80211_restart_work(struct work_struct *work) synchronize_net(); ieee80211_reconfig(local); + wiphy_unlock(local->hw.wiphy); rtnl_unlock(); } @@ -1272,6 +1275,7 @@ int ieee80211_register_hw(struct ieee80211_hw *hw) rate_control_add_debugfs(local); rtnl_lock(); + wiphy_lock(hw->wiphy); /* add one default STA interface if supported */ if (local->hw.wiphy->interface_modes & BIT(NL80211_IFTYPE_STATION) && @@ -1285,6 +1289,7 @@ int ieee80211_register_hw(struct ieee80211_hw *hw) "Failed to add default virtual iface\n"); } + wiphy_unlock(hw->wiphy); rtnl_unlock(); #ifdef CONFIG_INET diff --git a/net/mac80211/mesh_hwmp.c b/net/mac80211/mesh_hwmp.c index 313eee12410e..3db514c4c63a 100644 --- a/net/mac80211/mesh_hwmp.c +++ b/net/mac80211/mesh_hwmp.c @@ -356,7 +356,7 @@ u32 airtime_link_metric_get(struct ieee80211_local *local, */ tx_time = (device_constant + 10 * test_frame_len / rate); estimated_retx = ((1 << (2 * ARITH_SHIFT)) / (s_unit - err)); - result = (tx_time * estimated_retx) >> (2 * ARITH_SHIFT); + result = ((u64)tx_time * estimated_retx) >> (2 * ARITH_SHIFT); return (u32)result; } diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c index 0e4d950cf907..2e33a1263518 100644 --- a/net/mac80211/mlme.c +++ b/net/mac80211/mlme.c @@ -5754,6 +5754,9 @@ int ieee80211_mgd_assoc(struct ieee80211_sub_if_data *sdata, if (req->flags & ASSOC_REQ_DISABLE_VHT) ifmgd->flags |= IEEE80211_STA_DISABLE_VHT; + if (req->flags & ASSOC_REQ_DISABLE_HE) + ifmgd->flags |= IEEE80211_STA_DISABLE_HE; + err = ieee80211_prep_connection(sdata, req->bss, true, override); if (err) goto err_clear; diff --git a/net/mac80211/pm.c b/net/mac80211/pm.c index ae378a41c927..7809a906d7fe 100644 --- a/net/mac80211/pm.c +++ b/net/mac80211/pm.c @@ -1,4 +1,8 @@ // SPDX-License-Identifier: GPL-2.0 +/* + * Portions + * Copyright (C) 2020-2021 Intel Corporation + */ #include <net/mac80211.h> #include <net/rtnetlink.h> @@ -11,7 +15,7 @@ static void ieee80211_sched_scan_cancel(struct ieee80211_local *local) { if (ieee80211_request_sched_scan_stop(local)) return; - cfg80211_sched_scan_stopped_rtnl(local->hw.wiphy, 0); + cfg80211_sched_scan_stopped_locked(local->hw.wiphy, 0); } int __ieee80211_suspend(struct ieee80211_hw *hw, struct cfg80211_wowlan *wowlan) diff --git a/net/mac80211/rc80211_minstrel.c b/net/mac80211/rc80211_minstrel.c deleted file mode 100644 index b13b1da19386..000000000000 --- a/net/mac80211/rc80211_minstrel.c +++ /dev/null @@ -1,574 +0,0 @@ -/* - * Copyright (C) 2008 Felix Fietkau <nbd@openwrt.org> - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - * - * Based on minstrel.c: - * Copyright (C) 2005-2007 Derek Smithies <derek@indranet.co.nz> - * Sponsored by Indranet Technologies Ltd - * - * Based on sample.c: - * Copyright (c) 2005 John Bicket - * All rights reserved. - * - * Redistribution and use in source and binary forms, with or without - * modification, are permitted provided that the following conditions - * are met: - * 1. Redistributions of source code must retain the above copyright - * notice, this list of conditions and the following disclaimer, - * without modification. - * 2. Redistributions in binary form must reproduce at minimum a disclaimer - * similar to the "NO WARRANTY" disclaimer below ("Disclaimer") and any - * redistribution must be conditioned upon including a substantially - * similar Disclaimer requirement for further binary redistribution. - * 3. Neither the names of the above-listed copyright holders nor the names - * of any contributors may be used to endorse or promote products derived - * from this software without specific prior written permission. - * - * Alternatively, this software may be distributed under the terms of the - * GNU General Public License ("GPL") version 2 as published by the Free - * Software Foundation. - * - * NO WARRANTY - * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS - * ``AS IS'' AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT - * LIMITED TO, THE IMPLIED WARRANTIES OF NONINFRINGEMENT, MERCHANTIBILITY - * AND FITNESS FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL - * THE COPYRIGHT HOLDERS OR CONTRIBUTORS BE LIABLE FOR SPECIAL, EXEMPLARY, - * OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF - * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS - * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER - * IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) - * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF - * THE POSSIBILITY OF SUCH DAMAGES. - */ -#include <linux/netdevice.h> -#include <linux/types.h> -#include <linux/skbuff.h> -#include <linux/debugfs.h> -#include <linux/random.h> -#include <linux/ieee80211.h> -#include <linux/slab.h> -#include <net/mac80211.h> -#include "rate.h" -#include "rc80211_minstrel.h" - -#define SAMPLE_TBL(_mi, _idx, _col) \ - _mi->sample_table[(_idx * SAMPLE_COLUMNS) + _col] - -/* convert mac80211 rate index to local array index */ -static inline int -rix_to_ndx(struct minstrel_sta_info *mi, int rix) -{ - int i = rix; - for (i = rix; i >= 0; i--) - if (mi->r[i].rix == rix) - break; - return i; -} - -/* return current EMWA throughput */ -int minstrel_get_tp_avg(struct minstrel_rate *mr, int prob_avg) -{ - int usecs; - - usecs = mr->perfect_tx_time; - if (!usecs) - usecs = 1000000; - - /* reset thr. below 10% success */ - if (mr->stats.prob_avg < MINSTREL_FRAC(10, 100)) - return 0; - - if (prob_avg > MINSTREL_FRAC(90, 100)) - return MINSTREL_TRUNC(100000 * (MINSTREL_FRAC(90, 100) / usecs)); - else - return MINSTREL_TRUNC(100000 * (prob_avg / usecs)); -} - -/* find & sort topmost throughput rates */ -static inline void -minstrel_sort_best_tp_rates(struct minstrel_sta_info *mi, int i, u8 *tp_list) -{ - int j; - struct minstrel_rate_stats *tmp_mrs; - struct minstrel_rate_stats *cur_mrs = &mi->r[i].stats; - - for (j = MAX_THR_RATES; j > 0; --j) { - tmp_mrs = &mi->r[tp_list[j - 1]].stats; - if (minstrel_get_tp_avg(&mi->r[i], cur_mrs->prob_avg) <= - minstrel_get_tp_avg(&mi->r[tp_list[j - 1]], tmp_mrs->prob_avg)) - break; - } - - if (j < MAX_THR_RATES - 1) - memmove(&tp_list[j + 1], &tp_list[j], MAX_THR_RATES - (j + 1)); - if (j < MAX_THR_RATES) - tp_list[j] = i; -} - -static void -minstrel_set_rate(struct minstrel_sta_info *mi, struct ieee80211_sta_rates *ratetbl, - int offset, int idx) -{ - struct minstrel_rate *r = &mi->r[idx]; - - ratetbl->rate[offset].idx = r->rix; - ratetbl->rate[offset].count = r->adjusted_retry_count; - ratetbl->rate[offset].count_cts = r->retry_count_cts; - ratetbl->rate[offset].count_rts = r->stats.retry_count_rtscts; -} - -static void -minstrel_update_rates(struct minstrel_priv *mp, struct minstrel_sta_info *mi) -{ - struct ieee80211_sta_rates *ratetbl; - int i = 0; - - ratetbl = kzalloc(sizeof(*ratetbl), GFP_ATOMIC); - if (!ratetbl) - return; - - /* Start with max_tp_rate */ - minstrel_set_rate(mi, ratetbl, i++, mi->max_tp_rate[0]); - - if (mp->hw->max_rates >= 3) { - /* At least 3 tx rates supported, use max_tp_rate2 next */ - minstrel_set_rate(mi, ratetbl, i++, mi->max_tp_rate[1]); - } - - if (mp->hw->max_rates >= 2) { - /* At least 2 tx rates supported, use max_prob_rate next */ - minstrel_set_rate(mi, ratetbl, i++, mi->max_prob_rate); - } - - /* Use lowest rate last */ - ratetbl->rate[i].idx = mi->lowest_rix; - ratetbl->rate[i].count = mp->max_retry; - ratetbl->rate[i].count_cts = mp->max_retry; - ratetbl->rate[i].count_rts = mp->max_retry; - - rate_control_set_rates(mp->hw, mi->sta, ratetbl); -} - -/* -* Recalculate statistics and counters of a given rate -*/ -void -minstrel_calc_rate_stats(struct minstrel_priv *mp, - struct minstrel_rate_stats *mrs) -{ - unsigned int cur_prob; - - if (unlikely(mrs->attempts > 0)) { - mrs->sample_skipped = 0; - cur_prob = MINSTREL_FRAC(mrs->success, mrs->attempts); - if (mp->new_avg) { - minstrel_filter_avg_add(&mrs->prob_avg, - &mrs->prob_avg_1, cur_prob); - } else if (unlikely(!mrs->att_hist)) { - mrs->prob_avg = cur_prob; - } else { - /*update exponential weighted moving avarage */ - mrs->prob_avg = minstrel_ewma(mrs->prob_avg, - cur_prob, - EWMA_LEVEL); - } - mrs->att_hist += mrs->attempts; - mrs->succ_hist += mrs->success; - } else { - mrs->sample_skipped++; - } - - mrs->last_success = mrs->success; - mrs->last_attempts = mrs->attempts; - mrs->success = 0; - mrs->attempts = 0; -} - -static void -minstrel_update_stats(struct minstrel_priv *mp, struct minstrel_sta_info *mi) -{ - u8 tmp_tp_rate[MAX_THR_RATES]; - u8 tmp_prob_rate = 0; - int i, tmp_cur_tp, tmp_prob_tp; - - for (i = 0; i < MAX_THR_RATES; i++) - tmp_tp_rate[i] = 0; - - for (i = 0; i < mi->n_rates; i++) { - struct minstrel_rate *mr = &mi->r[i]; - struct minstrel_rate_stats *mrs = &mi->r[i].stats; - struct minstrel_rate_stats *tmp_mrs = &mi->r[tmp_prob_rate].stats; - - /* Update statistics of success probability per rate */ - minstrel_calc_rate_stats(mp, mrs); - - /* Sample less often below the 10% chance of success. - * Sample less often above the 95% chance of success. */ - if (mrs->prob_avg > MINSTREL_FRAC(95, 100) || - mrs->prob_avg < MINSTREL_FRAC(10, 100)) { - mr->adjusted_retry_count = mrs->retry_count >> 1; - if (mr->adjusted_retry_count > 2) - mr->adjusted_retry_count = 2; - mr->sample_limit = 4; - } else { - mr->sample_limit = -1; - mr->adjusted_retry_count = mrs->retry_count; - } - if (!mr->adjusted_retry_count) - mr->adjusted_retry_count = 2; - - minstrel_sort_best_tp_rates(mi, i, tmp_tp_rate); - - /* To determine the most robust rate (max_prob_rate) used at - * 3rd mmr stage we distinct between two cases: - * (1) if any success probabilitiy >= 95%, out of those rates - * choose the maximum throughput rate as max_prob_rate - * (2) if all success probabilities < 95%, the rate with - * highest success probability is chosen as max_prob_rate */ - if (mrs->prob_avg >= MINSTREL_FRAC(95, 100)) { - tmp_cur_tp = minstrel_get_tp_avg(mr, mrs->prob_avg); - tmp_prob_tp = minstrel_get_tp_avg(&mi->r[tmp_prob_rate], - tmp_mrs->prob_avg); - if (tmp_cur_tp >= tmp_prob_tp) - tmp_prob_rate = i; - } else { - if (mrs->prob_avg >= tmp_mrs->prob_avg) - tmp_prob_rate = i; - } - } - - /* Assign the new rate set */ - memcpy(mi->max_tp_rate, tmp_tp_rate, sizeof(mi->max_tp_rate)); - mi->max_prob_rate = tmp_prob_rate; - -#ifdef CONFIG_MAC80211_DEBUGFS - /* use fixed index if set */ - if (mp->fixed_rate_idx != -1) { - mi->max_tp_rate[0] = mp->fixed_rate_idx; - mi->max_tp_rate[1] = mp->fixed_rate_idx; - mi->max_prob_rate = mp->fixed_rate_idx; - } -#endif - - /* Reset update timer */ - mi->last_stats_update = jiffies; - - minstrel_update_rates(mp, mi); -} - -static void -minstrel_tx_status(void *priv, struct ieee80211_supported_band *sband, - void *priv_sta, struct ieee80211_tx_status *st) -{ - struct ieee80211_tx_info *info = st->info; - struct minstrel_priv *mp = priv; - struct minstrel_sta_info *mi = priv_sta; - struct ieee80211_tx_rate *ar = info->status.rates; - int i, ndx; - int success; - - success = !!(info->flags & IEEE80211_TX_STAT_ACK); - - for (i = 0; i < IEEE80211_TX_MAX_RATES; i++) { - if (ar[i].idx < 0 || !ar[i].count) - break; - - ndx = rix_to_ndx(mi, ar[i].idx); - if (ndx < 0) - continue; - - mi->r[ndx].stats.attempts += ar[i].count; - - if ((i != IEEE80211_TX_MAX_RATES - 1) && (ar[i + 1].idx < 0)) - mi->r[ndx].stats.success += success; - } - - if (time_after(jiffies, mi->last_stats_update + - mp->update_interval / (mp->new_avg ? 2 : 1))) - minstrel_update_stats(mp, mi); -} - - -static inline unsigned int -minstrel_get_retry_count(struct minstrel_rate *mr, - struct ieee80211_tx_info *info) -{ - u8 retry = mr->adjusted_retry_count; - - if (info->control.use_rts) - retry = max_t(u8, 2, min(mr->stats.retry_count_rtscts, retry)); - else if (info->control.use_cts_prot) - retry = max_t(u8, 2, min(mr->retry_count_cts, retry)); - return retry; -} - - -static int -minstrel_get_next_sample(struct minstrel_sta_info *mi) -{ - unsigned int sample_ndx; - sample_ndx = SAMPLE_TBL(mi, mi->sample_row, mi->sample_column); - mi->sample_row++; - if ((int) mi->sample_row >= mi->n_rates) { - mi->sample_row = 0; - mi->sample_column++; - if (mi->sample_column >= SAMPLE_COLUMNS) - mi->sample_column = 0; - } - return sample_ndx; -} - -static void -minstrel_get_rate(void *priv, struct ieee80211_sta *sta, - void *priv_sta, struct ieee80211_tx_rate_control *txrc) -{ - struct sk_buff *skb = txrc->skb; - struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb); - struct minstrel_sta_info *mi = priv_sta; - struct minstrel_priv *mp = priv; - struct ieee80211_tx_rate *rate = &info->control.rates[0]; - struct minstrel_rate *msr, *mr; - unsigned int ndx; - bool mrr_capable; - bool prev_sample; - int delta; - int sampling_ratio; - - /* check multi-rate-retry capabilities & adjust lookaround_rate */ - mrr_capable = mp->has_mrr && - !txrc->rts && - !txrc->bss_conf->use_cts_prot; - if (mrr_capable) - sampling_ratio = mp->lookaround_rate_mrr; - else - sampling_ratio = mp->lookaround_rate; - - /* increase sum packet counter */ - mi->total_packets++; - -#ifdef CONFIG_MAC80211_DEBUGFS - if (mp->fixed_rate_idx != -1) - return; -#endif - - /* Don't use EAPOL frames for sampling on non-mrr hw */ - if (mp->hw->max_rates == 1 && - (info->control.flags & IEEE80211_TX_CTRL_PORT_CTRL_PROTO)) - return; - - delta = (mi->total_packets * sampling_ratio / 100) - - mi->sample_packets; - - /* delta < 0: no sampling required */ - prev_sample = mi->prev_sample; - mi->prev_sample = false; - if (delta < 0 || (!mrr_capable && prev_sample)) - return; - - if (mi->total_packets >= 10000) { - mi->sample_packets = 0; - mi->total_packets = 0; - } else if (delta > mi->n_rates * 2) { - /* With multi-rate retry, not every planned sample - * attempt actually gets used, due to the way the retry - * chain is set up - [max_tp,sample,prob,lowest] for - * sample_rate < max_tp. - * - * If there's too much sampling backlog and the link - * starts getting worse, minstrel would start bursting - * out lots of sampling frames, which would result - * in a large throughput loss. */ - mi->sample_packets += (delta - mi->n_rates * 2); - } - - /* get next random rate sample */ - ndx = minstrel_get_next_sample(mi); - msr = &mi->r[ndx]; - mr = &mi->r[mi->max_tp_rate[0]]; - - /* Decide if direct ( 1st mrr stage) or indirect (2nd mrr stage) - * rate sampling method should be used. - * Respect such rates that are not sampled for 20 interations. - */ - if (msr->perfect_tx_time < mr->perfect_tx_time || - msr->stats.sample_skipped >= 20) { - if (!msr->sample_limit) - return; - - mi->sample_packets++; - if (msr->sample_limit > 0) - msr->sample_limit--; - } - - /* If we're not using MRR and the sampling rate already - * has a probability of >95%, we shouldn't be attempting - * to use it, as this only wastes precious airtime */ - if (!mrr_capable && - (mi->r[ndx].stats.prob_avg > MINSTREL_FRAC(95, 100))) - return; - - mi->prev_sample = true; - - rate->idx = mi->r[ndx].rix; - rate->count = minstrel_get_retry_count(&mi->r[ndx], info); - info->flags |= IEEE80211_TX_CTL_RATE_CTRL_PROBE; -} - - -static void -calc_rate_durations(enum nl80211_band band, - struct minstrel_rate *d, - struct ieee80211_rate *rate, - struct cfg80211_chan_def *chandef) -{ - int erp = !!(rate->flags & IEEE80211_RATE_ERP_G); - int shift = ieee80211_chandef_get_shift(chandef); - - d->perfect_tx_time = ieee80211_frame_duration(band, 1200, - DIV_ROUND_UP(rate->bitrate, 1 << shift), erp, 1, - shift); - d->ack_time = ieee80211_frame_duration(band, 10, - DIV_ROUND_UP(rate->bitrate, 1 << shift), erp, 1, - shift); -} - -static void -init_sample_table(struct minstrel_sta_info *mi) -{ - unsigned int i, col, new_idx; - u8 rnd[8]; - - mi->sample_column = 0; - mi->sample_row = 0; - memset(mi->sample_table, 0xff, SAMPLE_COLUMNS * mi->n_rates); - - for (col = 0; col < SAMPLE_COLUMNS; col++) { - prandom_bytes(rnd, sizeof(rnd)); - for (i = 0; i < mi->n_rates; i++) { - new_idx = (i + rnd[i & 7]) % mi->n_rates; - while (SAMPLE_TBL(mi, new_idx, col) != 0xff) - new_idx = (new_idx + 1) % mi->n_rates; - - SAMPLE_TBL(mi, new_idx, col) = i; - } - } -} - -static void -minstrel_rate_init(void *priv, struct ieee80211_supported_band *sband, - struct cfg80211_chan_def *chandef, - struct ieee80211_sta *sta, void *priv_sta) -{ - struct minstrel_sta_info *mi = priv_sta; - struct minstrel_priv *mp = priv; - struct ieee80211_rate *ctl_rate; - unsigned int i, n = 0; - unsigned int t_slot = 9; /* FIXME: get real slot time */ - u32 rate_flags; - - mi->sta = sta; - mi->lowest_rix = rate_lowest_index(sband, sta); - ctl_rate = &sband->bitrates[mi->lowest_rix]; - mi->sp_ack_dur = ieee80211_frame_duration(sband->band, 10, - ctl_rate->bitrate, - !!(ctl_rate->flags & IEEE80211_RATE_ERP_G), 1, - ieee80211_chandef_get_shift(chandef)); - - rate_flags = ieee80211_chandef_rate_flags(&mp->hw->conf.chandef); - memset(mi->max_tp_rate, 0, sizeof(mi->max_tp_rate)); - mi->max_prob_rate = 0; - - for (i = 0; i < sband->n_bitrates; i++) { - struct minstrel_rate *mr = &mi->r[n]; - struct minstrel_rate_stats *mrs = &mi->r[n].stats; - unsigned int tx_time = 0, tx_time_cts = 0, tx_time_rtscts = 0; - unsigned int tx_time_single; - unsigned int cw = mp->cw_min; - int shift; - - if (!rate_supported(sta, sband->band, i)) - continue; - if ((rate_flags & sband->bitrates[i].flags) != rate_flags) - continue; - - n++; - memset(mr, 0, sizeof(*mr)); - memset(mrs, 0, sizeof(*mrs)); - - mr->rix = i; - shift = ieee80211_chandef_get_shift(chandef); - mr->bitrate = DIV_ROUND_UP(sband->bitrates[i].bitrate, - (1 << shift) * 5); - calc_rate_durations(sband->band, mr, &sband->bitrates[i], - chandef); - - /* calculate maximum number of retransmissions before - * fallback (based on maximum segment size) */ - mr->sample_limit = -1; - mrs->retry_count = 1; - mr->retry_count_cts = 1; - mrs->retry_count_rtscts = 1; - tx_time = mr->perfect_tx_time + mi->sp_ack_dur; - do { - /* add one retransmission */ - tx_time_single = mr->ack_time + mr->perfect_tx_time; - - /* contention window */ - tx_time_single += (t_slot * cw) >> 1; - cw = min((cw << 1) | 1, mp->cw_max); - - tx_time += tx_time_single; - tx_time_cts += tx_time_single + mi->sp_ack_dur; - tx_time_rtscts += tx_time_single + 2 * mi->sp_ack_dur; - if ((tx_time_cts < mp->segment_size) && - (mr->retry_count_cts < mp->max_retry)) - mr->retry_count_cts++; - if ((tx_time_rtscts < mp->segment_size) && - (mrs->retry_count_rtscts < mp->max_retry)) - mrs->retry_count_rtscts++; - } while ((tx_time < mp->segment_size) && - (++mr->stats.retry_count < mp->max_retry)); - mr->adjusted_retry_count = mrs->retry_count; - if (!(sband->bitrates[i].flags & IEEE80211_RATE_ERP_G)) - mr->retry_count_cts = mrs->retry_count; - } - - for (i = n; i < sband->n_bitrates; i++) { - struct minstrel_rate *mr = &mi->r[i]; - mr->rix = -1; - } - - mi->n_rates = n; - mi->last_stats_update = jiffies; - - init_sample_table(mi); - minstrel_update_rates(mp, mi); -} - -static u32 minstrel_get_expected_throughput(void *priv_sta) -{ - struct minstrel_sta_info *mi = priv_sta; - struct minstrel_rate_stats *tmp_mrs; - int idx = mi->max_tp_rate[0]; - int tmp_cur_tp; - - /* convert pkt per sec in kbps (1200 is the average pkt size used for - * computing cur_tp - */ - tmp_mrs = &mi->r[idx].stats; - tmp_cur_tp = minstrel_get_tp_avg(&mi->r[idx], tmp_mrs->prob_avg) * 10; - tmp_cur_tp = tmp_cur_tp * 1200 * 8 / 1024; - - return tmp_cur_tp; -} - -const struct rate_control_ops mac80211_minstrel = { - .tx_status_ext = minstrel_tx_status, - .get_rate = minstrel_get_rate, - .rate_init = minstrel_rate_init, - .get_expected_throughput = minstrel_get_expected_throughput, -}; diff --git a/net/mac80211/rc80211_minstrel.h b/net/mac80211/rc80211_minstrel.h deleted file mode 100644 index 86cd80b3ffde..000000000000 --- a/net/mac80211/rc80211_minstrel.h +++ /dev/null @@ -1,184 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* - * Copyright (C) 2008 Felix Fietkau <nbd@openwrt.org> - */ - -#ifndef __RC_MINSTREL_H -#define __RC_MINSTREL_H - -#define EWMA_LEVEL 96 /* ewma weighting factor [/EWMA_DIV] */ -#define EWMA_DIV 128 -#define SAMPLE_COLUMNS 10 /* number of columns in sample table */ - -/* scaled fraction values */ -#define MINSTREL_SCALE 12 -#define MINSTREL_FRAC(val, div) (((val) << MINSTREL_SCALE) / div) -#define MINSTREL_TRUNC(val) ((val) >> MINSTREL_SCALE) - -/* number of highest throughput rates to consider*/ -#define MAX_THR_RATES 4 - -/* - * Coefficients for moving average with noise filter (period=16), - * scaled by 10 bits - * - * a1 = exp(-pi * sqrt(2) / period) - * coeff2 = 2 * a1 * cos(sqrt(2) * 2 * pi / period) - * coeff3 = -sqr(a1) - * coeff1 = 1 - coeff2 - coeff3 - */ -#define MINSTREL_AVG_COEFF1 (MINSTREL_FRAC(1, 1) - \ - MINSTREL_AVG_COEFF2 - \ - MINSTREL_AVG_COEFF3) -#define MINSTREL_AVG_COEFF2 0x00001499 -#define MINSTREL_AVG_COEFF3 -0x0000092e - -/* - * Perform EWMA (Exponentially Weighted Moving Average) calculation - */ -static inline int -minstrel_ewma(int old, int new, int weight) -{ - int diff, incr; - - diff = new - old; - incr = (EWMA_DIV - weight) * diff / EWMA_DIV; - - return old + incr; -} - -static inline int minstrel_filter_avg_add(u16 *prev_1, u16 *prev_2, s32 in) -{ - s32 out_1 = *prev_1; - s32 out_2 = *prev_2; - s32 val; - - if (!in) - in += 1; - - if (!out_1) { - val = out_1 = in; - goto out; - } - - val = MINSTREL_AVG_COEFF1 * in; - val += MINSTREL_AVG_COEFF2 * out_1; - val += MINSTREL_AVG_COEFF3 * out_2; - val >>= MINSTREL_SCALE; - - if (val > 1 << MINSTREL_SCALE) - val = 1 << MINSTREL_SCALE; - if (val < 0) - val = 1; - -out: - *prev_2 = out_1; - *prev_1 = val; - - return val; -} - -struct minstrel_rate_stats { - /* current / last sampling period attempts/success counters */ - u16 attempts, last_attempts; - u16 success, last_success; - - /* total attempts/success counters */ - u32 att_hist, succ_hist; - - /* prob_avg - moving average of prob */ - u16 prob_avg; - u16 prob_avg_1; - - /* maximum retry counts */ - u8 retry_count; - u8 retry_count_rtscts; - - u8 sample_skipped; - bool retry_updated; -}; - -struct minstrel_rate { - int bitrate; - - s8 rix; - u8 retry_count_cts; - u8 adjusted_retry_count; - - unsigned int perfect_tx_time; - unsigned int ack_time; - - int sample_limit; - - struct minstrel_rate_stats stats; -}; - -struct minstrel_sta_info { - struct ieee80211_sta *sta; - - unsigned long last_stats_update; - unsigned int sp_ack_dur; - unsigned int rate_avg; - - unsigned int lowest_rix; - - u8 max_tp_rate[MAX_THR_RATES]; - u8 max_prob_rate; - unsigned int total_packets; - unsigned int sample_packets; - - unsigned int sample_row; - unsigned int sample_column; - - int n_rates; - struct minstrel_rate *r; - bool prev_sample; - - /* sampling table */ - u8 *sample_table; -}; - -struct minstrel_priv { - struct ieee80211_hw *hw; - bool has_mrr; - bool new_avg; - u32 sample_switch; - unsigned int cw_min; - unsigned int cw_max; - unsigned int max_retry; - unsigned int segment_size; - unsigned int update_interval; - unsigned int lookaround_rate; - unsigned int lookaround_rate_mrr; - - u8 cck_rates[4]; - -#ifdef CONFIG_MAC80211_DEBUGFS - /* - * enable fixed rate processing per RC - * - write static index to debugfs:ieee80211/phyX/rc/fixed_rate_idx - * - write -1 to enable RC processing again - * - setting will be applied on next update - */ - u32 fixed_rate_idx; -#endif -}; - -struct minstrel_debugfs_info { - size_t len; - char buf[]; -}; - -extern const struct rate_control_ops mac80211_minstrel; -void minstrel_add_sta_debugfs(void *priv, void *priv_sta, struct dentry *dir); - -/* Recalculate success probabilities and counters for a given rate using EWMA */ -void minstrel_calc_rate_stats(struct minstrel_priv *mp, - struct minstrel_rate_stats *mrs); -int minstrel_get_tp_avg(struct minstrel_rate *mr, int prob_avg); - -/* debugfs */ -int minstrel_stats_open(struct inode *inode, struct file *file); -int minstrel_stats_csv_open(struct inode *inode, struct file *file); - -#endif diff --git a/net/mac80211/rc80211_minstrel_debugfs.c b/net/mac80211/rc80211_minstrel_debugfs.c deleted file mode 100644 index 9b8e0daeb7bb..000000000000 --- a/net/mac80211/rc80211_minstrel_debugfs.c +++ /dev/null @@ -1,172 +0,0 @@ -/* - * Copyright (C) 2008 Felix Fietkau <nbd@openwrt.org> - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - * - * Based on minstrel.c: - * Copyright (C) 2005-2007 Derek Smithies <derek@indranet.co.nz> - * Sponsored by Indranet Technologies Ltd - * - * Based on sample.c: - * Copyright (c) 2005 John Bicket - * All rights reserved. - * - * Redistribution and use in source and binary forms, with or without - * modification, are permitted provided that the following conditions - * are met: - * 1. Redistributions of source code must retain the above copyright - * notice, this list of conditions and the following disclaimer, - * without modification. - * 2. Redistributions in binary form must reproduce at minimum a disclaimer - * similar to the "NO WARRANTY" disclaimer below ("Disclaimer") and any - * redistribution must be conditioned upon including a substantially - * similar Disclaimer requirement for further binary redistribution. - * 3. Neither the names of the above-listed copyright holders nor the names - * of any contributors may be used to endorse or promote products derived - * from this software without specific prior written permission. - * - * Alternatively, this software may be distributed under the terms of the - * GNU General Public License ("GPL") version 2 as published by the Free - * Software Foundation. - * - * NO WARRANTY - * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS - * ``AS IS'' AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT - * LIMITED TO, THE IMPLIED WARRANTIES OF NONINFRINGEMENT, MERCHANTIBILITY - * AND FITNESS FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL - * THE COPYRIGHT HOLDERS OR CONTRIBUTORS BE LIABLE FOR SPECIAL, EXEMPLARY, - * OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF - * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS - * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER - * IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) - * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF - * THE POSSIBILITY OF SUCH DAMAGES. - */ -#include <linux/netdevice.h> -#include <linux/types.h> -#include <linux/skbuff.h> -#include <linux/debugfs.h> -#include <linux/ieee80211.h> -#include <linux/slab.h> -#include <linux/export.h> -#include <net/mac80211.h> -#include "rc80211_minstrel.h" - -int -minstrel_stats_open(struct inode *inode, struct file *file) -{ - struct minstrel_sta_info *mi = inode->i_private; - struct minstrel_debugfs_info *ms; - unsigned int i, tp_max, tp_avg, eprob; - char *p; - - ms = kmalloc(2048, GFP_KERNEL); - if (!ms) - return -ENOMEM; - - file->private_data = ms; - p = ms->buf; - p += sprintf(p, "\n"); - p += sprintf(p, - "best __________rate_________ ____statistics___ ____last_____ ______sum-of________\n"); - p += sprintf(p, - "rate [name idx airtime max_tp] [avg(tp) avg(prob)] [retry|suc|att] [#success | #attempts]\n"); - - for (i = 0; i < mi->n_rates; i++) { - struct minstrel_rate *mr = &mi->r[i]; - struct minstrel_rate_stats *mrs = &mi->r[i].stats; - - *(p++) = (i == mi->max_tp_rate[0]) ? 'A' : ' '; - *(p++) = (i == mi->max_tp_rate[1]) ? 'B' : ' '; - *(p++) = (i == mi->max_tp_rate[2]) ? 'C' : ' '; - *(p++) = (i == mi->max_tp_rate[3]) ? 'D' : ' '; - *(p++) = (i == mi->max_prob_rate) ? 'P' : ' '; - - p += sprintf(p, " %3u%s ", mr->bitrate / 2, - (mr->bitrate & 1 ? ".5" : " ")); - p += sprintf(p, "%3u ", i); - p += sprintf(p, "%6u ", mr->perfect_tx_time); - - tp_max = minstrel_get_tp_avg(mr, MINSTREL_FRAC(100,100)); - tp_avg = minstrel_get_tp_avg(mr, mrs->prob_avg); - eprob = MINSTREL_TRUNC(mrs->prob_avg * 1000); - - p += sprintf(p, "%4u.%1u %4u.%1u %3u.%1u" - " %3u %3u %-3u " - "%9llu %-9llu\n", - tp_max / 10, tp_max % 10, - tp_avg / 10, tp_avg % 10, - eprob / 10, eprob % 10, - mrs->retry_count, - mrs->last_success, - mrs->last_attempts, - (unsigned long long)mrs->succ_hist, - (unsigned long long)mrs->att_hist); - } - p += sprintf(p, "\nTotal packet count:: ideal %d " - "lookaround %d\n\n", - mi->total_packets - mi->sample_packets, - mi->sample_packets); - ms->len = p - ms->buf; - - WARN_ON(ms->len + sizeof(*ms) > 2048); - - return 0; -} - -int -minstrel_stats_csv_open(struct inode *inode, struct file *file) -{ - struct minstrel_sta_info *mi = inode->i_private; - struct minstrel_debugfs_info *ms; - unsigned int i, tp_max, tp_avg, eprob; - char *p; - - ms = kmalloc(2048, GFP_KERNEL); - if (!ms) - return -ENOMEM; - - file->private_data = ms; - p = ms->buf; - - for (i = 0; i < mi->n_rates; i++) { - struct minstrel_rate *mr = &mi->r[i]; - struct minstrel_rate_stats *mrs = &mi->r[i].stats; - - p += sprintf(p, "%s" ,((i == mi->max_tp_rate[0]) ? "A" : "")); - p += sprintf(p, "%s" ,((i == mi->max_tp_rate[1]) ? "B" : "")); - p += sprintf(p, "%s" ,((i == mi->max_tp_rate[2]) ? "C" : "")); - p += sprintf(p, "%s" ,((i == mi->max_tp_rate[3]) ? "D" : "")); - p += sprintf(p, "%s" ,((i == mi->max_prob_rate) ? "P" : "")); - - p += sprintf(p, ",%u%s", mr->bitrate / 2, - (mr->bitrate & 1 ? ".5," : ",")); - p += sprintf(p, "%u,", i); - p += sprintf(p, "%u,",mr->perfect_tx_time); - - tp_max = minstrel_get_tp_avg(mr, MINSTREL_FRAC(100,100)); - tp_avg = minstrel_get_tp_avg(mr, mrs->prob_avg); - eprob = MINSTREL_TRUNC(mrs->prob_avg * 1000); - - p += sprintf(p, "%u.%u,%u.%u,%u.%u,%u,%u,%u," - "%llu,%llu,%d,%d\n", - tp_max / 10, tp_max % 10, - tp_avg / 10, tp_avg % 10, - eprob / 10, eprob % 10, - mrs->retry_count, - mrs->last_success, - mrs->last_attempts, - (unsigned long long)mrs->succ_hist, - (unsigned long long)mrs->att_hist, - mi->total_packets - mi->sample_packets, - mi->sample_packets); - - } - ms->len = p - ms->buf; - - WARN_ON(ms->len + sizeof(*ms) > 2048); - - return 0; -} diff --git a/net/mac80211/rc80211_minstrel_ht.c b/net/mac80211/rc80211_minstrel_ht.c index b11a2af55b06..2f44f4919789 100644 --- a/net/mac80211/rc80211_minstrel_ht.c +++ b/net/mac80211/rc80211_minstrel_ht.c @@ -13,7 +13,6 @@ #include <net/mac80211.h> #include "rate.h" #include "sta_info.h" -#include "rc80211_minstrel.h" #include "rc80211_minstrel_ht.h" #define AVG_AMPDU_SIZE 16 @@ -136,20 +135,16 @@ __VHT_GROUP(_streams, _sgi, _bw, \ VHT_GROUP_SHIFT(_streams, _sgi, _bw)) -#define CCK_DURATION(_bitrate, _short, _len) \ +#define CCK_DURATION(_bitrate, _short) \ (1000 * (10 /* SIFS */ + \ (_short ? 72 + 24 : 144 + 48) + \ - (8 * (_len + 4) * 10) / (_bitrate))) - -#define CCK_ACK_DURATION(_bitrate, _short) \ - (CCK_DURATION((_bitrate > 10 ? 20 : 10), false, 60) + \ - CCK_DURATION(_bitrate, _short, AVG_PKT_SIZE)) + (8 * (AVG_PKT_SIZE + 4) * 10) / (_bitrate))) #define CCK_DURATION_LIST(_short, _s) \ - CCK_ACK_DURATION(10, _short) >> _s, \ - CCK_ACK_DURATION(20, _short) >> _s, \ - CCK_ACK_DURATION(55, _short) >> _s, \ - CCK_ACK_DURATION(110, _short) >> _s + CCK_DURATION(10, _short) >> _s, \ + CCK_DURATION(20, _short) >> _s, \ + CCK_DURATION(55, _short) >> _s, \ + CCK_DURATION(110, _short) >> _s #define __CCK_GROUP(_s) \ [MINSTREL_CCK_GROUP] = { \ @@ -163,10 +158,42 @@ } #define CCK_GROUP_SHIFT \ - GROUP_SHIFT(CCK_ACK_DURATION(10, false)) + GROUP_SHIFT(CCK_DURATION(10, false)) #define CCK_GROUP __CCK_GROUP(CCK_GROUP_SHIFT) +#define OFDM_DURATION(_bitrate) \ + (1000 * (16 /* SIFS + signal ext */ + \ + 16 /* T_PREAMBLE */ + \ + 4 /* T_SIGNAL */ + \ + 4 * (((16 + 80 * (AVG_PKT_SIZE + 4) + 6) / \ + ((_bitrate) * 4))))) + +#define OFDM_DURATION_LIST(_s) \ + OFDM_DURATION(60) >> _s, \ + OFDM_DURATION(90) >> _s, \ + OFDM_DURATION(120) >> _s, \ + OFDM_DURATION(180) >> _s, \ + OFDM_DURATION(240) >> _s, \ + OFDM_DURATION(360) >> _s, \ + OFDM_DURATION(480) >> _s, \ + OFDM_DURATION(540) >> _s + +#define __OFDM_GROUP(_s) \ + [MINSTREL_OFDM_GROUP] = { \ + .streams = 1, \ + .flags = 0, \ + .shift = _s, \ + .duration = { \ + OFDM_DURATION_LIST(_s), \ + } \ + } + +#define OFDM_GROUP_SHIFT \ + GROUP_SHIFT(OFDM_DURATION(60)) + +#define OFDM_GROUP __OFDM_GROUP(OFDM_GROUP_SHIFT) + static bool minstrel_vht_only = true; module_param(minstrel_vht_only, bool, 0644); @@ -203,6 +230,7 @@ const struct mcs_group minstrel_mcs_groups[] = { MCS_GROUP(4, 1, BW_40), CCK_GROUP, + OFDM_GROUP, VHT_GROUP(1, 0, BW_20), VHT_GROUP(2, 0, BW_20), @@ -235,7 +263,17 @@ const struct mcs_group minstrel_mcs_groups[] = { VHT_GROUP(4, 1, BW_80), }; +const s16 minstrel_cck_bitrates[4] = { 10, 20, 55, 110 }; +const s16 minstrel_ofdm_bitrates[8] = { 60, 90, 120, 180, 240, 360, 480, 540 }; static u8 sample_table[SAMPLE_COLUMNS][MCS_GROUP_RATES] __read_mostly; +static const u8 minstrel_sample_seq[] = { + MINSTREL_SAMPLE_TYPE_INC, + MINSTREL_SAMPLE_TYPE_JUMP, + MINSTREL_SAMPLE_TYPE_INC, + MINSTREL_SAMPLE_TYPE_JUMP, + MINSTREL_SAMPLE_TYPE_INC, + MINSTREL_SAMPLE_TYPE_SLOW, +}; static void minstrel_ht_update_rates(struct minstrel_priv *mp, struct minstrel_ht_sta *mi); @@ -279,6 +317,13 @@ minstrel_get_valid_vht_rates(int bw, int nss, __le16 mcs_map) return 0x3ff & ~mask; } +static bool +minstrel_ht_is_legacy_group(int group) +{ + return group == MINSTREL_CCK_GROUP || + group == MINSTREL_OFDM_GROUP; +} + /* * Look up an MCS group index based on mac80211 rate information */ @@ -308,37 +353,74 @@ minstrel_ht_get_stats(struct minstrel_priv *mp, struct minstrel_ht_sta *mi, if (rate->flags & IEEE80211_TX_RC_MCS) { group = minstrel_ht_get_group_idx(rate); idx = rate->idx % 8; - } else if (rate->flags & IEEE80211_TX_RC_VHT_MCS) { + goto out; + } + + if (rate->flags & IEEE80211_TX_RC_VHT_MCS) { group = minstrel_vht_get_group_idx(rate); idx = ieee80211_rate_get_vht_mcs(rate); - } else { - group = MINSTREL_CCK_GROUP; + goto out; + } - for (idx = 0; idx < ARRAY_SIZE(mp->cck_rates); idx++) - if (rate->idx == mp->cck_rates[idx]) - break; + group = MINSTREL_CCK_GROUP; + for (idx = 0; idx < ARRAY_SIZE(mp->cck_rates); idx++) { + if (rate->idx != mp->cck_rates[idx]) + continue; /* short preamble */ if ((mi->supported[group] & BIT(idx + 4)) && (rate->flags & IEEE80211_TX_RC_USE_SHORT_PREAMBLE)) - idx += 4; + idx += 4; + goto out; } + + group = MINSTREL_OFDM_GROUP; + for (idx = 0; idx < ARRAY_SIZE(mp->ofdm_rates[0]); idx++) + if (rate->idx == mp->ofdm_rates[mi->band][idx]) + goto out; + + idx = 0; +out: return &mi->groups[group].rates[idx]; } static inline struct minstrel_rate_stats * minstrel_get_ratestats(struct minstrel_ht_sta *mi, int index) { - return &mi->groups[index / MCS_GROUP_RATES].rates[index % MCS_GROUP_RATES]; + return &mi->groups[MI_RATE_GROUP(index)].rates[MI_RATE_IDX(index)]; +} + +static inline int minstrel_get_duration(int index) +{ + const struct mcs_group *group = &minstrel_mcs_groups[MI_RATE_GROUP(index)]; + unsigned int duration = group->duration[MI_RATE_IDX(index)]; + + return duration << group->shift; } static unsigned int minstrel_ht_avg_ampdu_len(struct minstrel_ht_sta *mi) { - if (!mi->avg_ampdu_len) - return AVG_AMPDU_SIZE; + int duration; + + if (mi->avg_ampdu_len) + return MINSTREL_TRUNC(mi->avg_ampdu_len); + + if (minstrel_ht_is_legacy_group(MI_RATE_GROUP(mi->max_tp_rate[0]))) + return 1; + + duration = minstrel_get_duration(mi->max_tp_rate[0]); - return MINSTREL_TRUNC(mi->avg_ampdu_len); + if (duration > 400 * 1000) + return 2; + + if (duration > 250 * 1000) + return 4; + + if (duration > 150 * 1000) + return 8; + + return 16; } /* @@ -349,15 +431,19 @@ int minstrel_ht_get_tp_avg(struct minstrel_ht_sta *mi, int group, int rate, int prob_avg) { - unsigned int nsecs = 0; + unsigned int nsecs = 0, overhead = mi->overhead; + unsigned int ampdu_len = 1; /* do not account throughput if sucess prob is below 10% */ if (prob_avg < MINSTREL_FRAC(10, 100)) return 0; - if (group != MINSTREL_CCK_GROUP) - nsecs = 1000 * mi->overhead / minstrel_ht_avg_ampdu_len(mi); + if (minstrel_ht_is_legacy_group(group)) + overhead = mi->overhead_legacy; + else + ampdu_len = minstrel_ht_avg_ampdu_len(mi); + nsecs = 1000 * overhead / ampdu_len; nsecs += minstrel_mcs_groups[group].duration[rate] << minstrel_mcs_groups[group].shift; @@ -367,10 +453,9 @@ minstrel_ht_get_tp_avg(struct minstrel_ht_sta *mi, int group, int rate, * (prob is scaled - see MINSTREL_FRAC above) */ if (prob_avg > MINSTREL_FRAC(90, 100)) - return MINSTREL_TRUNC(100000 * ((MINSTREL_FRAC(90, 100) * 1000) - / nsecs)); - else - return MINSTREL_TRUNC(100000 * ((prob_avg * 1000) / nsecs)); + prob_avg = MINSTREL_FRAC(90, 100); + + return MINSTREL_TRUNC(100 * ((prob_avg * 1000000) / nsecs)); } /* @@ -388,14 +473,14 @@ minstrel_ht_sort_best_tp_rates(struct minstrel_ht_sta *mi, u16 index, int tmp_group, tmp_idx, tmp_tp_avg, tmp_prob; int j = MAX_THR_RATES; - cur_group = index / MCS_GROUP_RATES; - cur_idx = index % MCS_GROUP_RATES; + cur_group = MI_RATE_GROUP(index); + cur_idx = MI_RATE_IDX(index); cur_prob = mi->groups[cur_group].rates[cur_idx].prob_avg; cur_tp_avg = minstrel_ht_get_tp_avg(mi, cur_group, cur_idx, cur_prob); do { - tmp_group = tp_list[j - 1] / MCS_GROUP_RATES; - tmp_idx = tp_list[j - 1] % MCS_GROUP_RATES; + tmp_group = MI_RATE_GROUP(tp_list[j - 1]); + tmp_idx = MI_RATE_IDX(tp_list[j - 1]); tmp_prob = mi->groups[tmp_group].rates[tmp_idx].prob_avg; tmp_tp_avg = minstrel_ht_get_tp_avg(mi, tmp_group, tmp_idx, tmp_prob); @@ -417,41 +502,50 @@ minstrel_ht_sort_best_tp_rates(struct minstrel_ht_sta *mi, u16 index, * Find and set the topmost probability rate per sta and per group */ static void -minstrel_ht_set_best_prob_rate(struct minstrel_ht_sta *mi, u16 index) +minstrel_ht_set_best_prob_rate(struct minstrel_ht_sta *mi, u16 *dest, u16 index) { struct minstrel_mcs_group_data *mg; struct minstrel_rate_stats *mrs; int tmp_group, tmp_idx, tmp_tp_avg, tmp_prob; - int max_tp_group, cur_tp_avg, cur_group, cur_idx; + int max_tp_group, max_tp_idx, max_tp_prob; + int cur_tp_avg, cur_group, cur_idx; int max_gpr_group, max_gpr_idx; int max_gpr_tp_avg, max_gpr_prob; - cur_group = index / MCS_GROUP_RATES; - cur_idx = index % MCS_GROUP_RATES; - mg = &mi->groups[index / MCS_GROUP_RATES]; - mrs = &mg->rates[index % MCS_GROUP_RATES]; + cur_group = MI_RATE_GROUP(index); + cur_idx = MI_RATE_IDX(index); + mg = &mi->groups[cur_group]; + mrs = &mg->rates[cur_idx]; - tmp_group = mi->max_prob_rate / MCS_GROUP_RATES; - tmp_idx = mi->max_prob_rate % MCS_GROUP_RATES; + tmp_group = MI_RATE_GROUP(*dest); + tmp_idx = MI_RATE_IDX(*dest); tmp_prob = mi->groups[tmp_group].rates[tmp_idx].prob_avg; tmp_tp_avg = minstrel_ht_get_tp_avg(mi, tmp_group, tmp_idx, tmp_prob); /* if max_tp_rate[0] is from MCS_GROUP max_prob_rate get selected from * MCS_GROUP as well as CCK_GROUP rates do not allow aggregation */ - max_tp_group = mi->max_tp_rate[0] / MCS_GROUP_RATES; - if((index / MCS_GROUP_RATES == MINSTREL_CCK_GROUP) && - (max_tp_group != MINSTREL_CCK_GROUP)) + max_tp_group = MI_RATE_GROUP(mi->max_tp_rate[0]); + max_tp_idx = MI_RATE_IDX(mi->max_tp_rate[0]); + max_tp_prob = mi->groups[max_tp_group].rates[max_tp_idx].prob_avg; + + if (minstrel_ht_is_legacy_group(MI_RATE_GROUP(index)) && + !minstrel_ht_is_legacy_group(max_tp_group)) + return; + + /* skip rates faster than max tp rate with lower prob */ + if (minstrel_get_duration(mi->max_tp_rate[0]) > minstrel_get_duration(index) && + mrs->prob_avg < max_tp_prob) return; - max_gpr_group = mg->max_group_prob_rate / MCS_GROUP_RATES; - max_gpr_idx = mg->max_group_prob_rate % MCS_GROUP_RATES; + max_gpr_group = MI_RATE_GROUP(mg->max_group_prob_rate); + max_gpr_idx = MI_RATE_IDX(mg->max_group_prob_rate); max_gpr_prob = mi->groups[max_gpr_group].rates[max_gpr_idx].prob_avg; if (mrs->prob_avg > MINSTREL_FRAC(75, 100)) { cur_tp_avg = minstrel_ht_get_tp_avg(mi, cur_group, cur_idx, mrs->prob_avg); if (cur_tp_avg > tmp_tp_avg) - mi->max_prob_rate = index; + *dest = index; max_gpr_tp_avg = minstrel_ht_get_tp_avg(mi, max_gpr_group, max_gpr_idx, @@ -460,7 +554,7 @@ minstrel_ht_set_best_prob_rate(struct minstrel_ht_sta *mi, u16 index) mg->max_group_prob_rate = index; } else { if (mrs->prob_avg > tmp_prob) - mi->max_prob_rate = index; + *dest = index; if (mrs->prob_avg > max_gpr_prob) mg->max_group_prob_rate = index; } @@ -476,24 +570,24 @@ minstrel_ht_set_best_prob_rate(struct minstrel_ht_sta *mi, u16 index) static void minstrel_ht_assign_best_tp_rates(struct minstrel_ht_sta *mi, u16 tmp_mcs_tp_rate[MAX_THR_RATES], - u16 tmp_cck_tp_rate[MAX_THR_RATES]) + u16 tmp_legacy_tp_rate[MAX_THR_RATES]) { unsigned int tmp_group, tmp_idx, tmp_cck_tp, tmp_mcs_tp, tmp_prob; int i; - tmp_group = tmp_cck_tp_rate[0] / MCS_GROUP_RATES; - tmp_idx = tmp_cck_tp_rate[0] % MCS_GROUP_RATES; + tmp_group = MI_RATE_GROUP(tmp_legacy_tp_rate[0]); + tmp_idx = MI_RATE_IDX(tmp_legacy_tp_rate[0]); tmp_prob = mi->groups[tmp_group].rates[tmp_idx].prob_avg; tmp_cck_tp = minstrel_ht_get_tp_avg(mi, tmp_group, tmp_idx, tmp_prob); - tmp_group = tmp_mcs_tp_rate[0] / MCS_GROUP_RATES; - tmp_idx = tmp_mcs_tp_rate[0] % MCS_GROUP_RATES; + tmp_group = MI_RATE_GROUP(tmp_mcs_tp_rate[0]); + tmp_idx = MI_RATE_IDX(tmp_mcs_tp_rate[0]); tmp_prob = mi->groups[tmp_group].rates[tmp_idx].prob_avg; tmp_mcs_tp = minstrel_ht_get_tp_avg(mi, tmp_group, tmp_idx, tmp_prob); if (tmp_cck_tp > tmp_mcs_tp) { for(i = 0; i < MAX_THR_RATES; i++) { - minstrel_ht_sort_best_tp_rates(mi, tmp_cck_tp_rate[i], + minstrel_ht_sort_best_tp_rates(mi, tmp_legacy_tp_rate[i], tmp_mcs_tp_rate); } } @@ -511,14 +605,17 @@ minstrel_ht_prob_rate_reduce_streams(struct minstrel_ht_sta *mi) int tmp_max_streams, group, tmp_idx, tmp_prob; int tmp_tp = 0; - tmp_max_streams = minstrel_mcs_groups[mi->max_tp_rate[0] / - MCS_GROUP_RATES].streams; + if (!mi->sta->ht_cap.ht_supported) + return; + + group = MI_RATE_GROUP(mi->max_tp_rate[0]); + tmp_max_streams = minstrel_mcs_groups[group].streams; for (group = 0; group < ARRAY_SIZE(minstrel_mcs_groups); group++) { mg = &mi->groups[group]; if (!mi->supported[group] || group == MINSTREL_CCK_GROUP) continue; - tmp_idx = mg->max_group_prob_rate % MCS_GROUP_RATES; + tmp_idx = MI_RATE_IDX(mg->max_group_prob_rate); tmp_prob = mi->groups[group].rates[tmp_idx].prob_avg; if (tmp_tp < minstrel_ht_get_tp_avg(mi, group, tmp_idx, tmp_prob) && @@ -531,133 +628,359 @@ minstrel_ht_prob_rate_reduce_streams(struct minstrel_ht_sta *mi) } } +static u16 +__minstrel_ht_get_sample_rate(struct minstrel_ht_sta *mi, + enum minstrel_sample_type type) +{ + u16 *rates = mi->sample[type].sample_rates; + u16 cur; + int i; + + for (i = 0; i < MINSTREL_SAMPLE_RATES; i++) { + if (!rates[i]) + continue; + + cur = rates[i]; + rates[i] = 0; + return cur; + } + + return 0; +} + static inline int -minstrel_get_duration(int index) +minstrel_ewma(int old, int new, int weight) { - const struct mcs_group *group = &minstrel_mcs_groups[index / MCS_GROUP_RATES]; - unsigned int duration = group->duration[index % MCS_GROUP_RATES]; - return duration << group->shift; + int diff, incr; + + diff = new - old; + incr = (EWMA_DIV - weight) * diff / EWMA_DIV; + + return old + incr; } -static bool -minstrel_ht_probe_group(struct minstrel_ht_sta *mi, const struct mcs_group *tp_group, - int tp_idx, const struct mcs_group *group) +static inline int minstrel_filter_avg_add(u16 *prev_1, u16 *prev_2, s32 in) { - if (group->bw < tp_group->bw) - return false; + s32 out_1 = *prev_1; + s32 out_2 = *prev_2; + s32 val; - if (group->streams == tp_group->streams) - return true; + if (!in) + in += 1; - if (tp_idx < 4 && group->streams == tp_group->streams - 1) - return true; + if (!out_1) { + val = out_1 = in; + goto out; + } + + val = MINSTREL_AVG_COEFF1 * in; + val += MINSTREL_AVG_COEFF2 * out_1; + val += MINSTREL_AVG_COEFF3 * out_2; + val >>= MINSTREL_SCALE; + + if (val > 1 << MINSTREL_SCALE) + val = 1 << MINSTREL_SCALE; + if (val < 0) + val = 1; + +out: + *prev_2 = out_1; + *prev_1 = val; - return group->streams == tp_group->streams + 1; + return val; } +/* +* Recalculate statistics and counters of a given rate +*/ static void -minstrel_ht_find_probe_rates(struct minstrel_ht_sta *mi, u16 *rates, int *n_rates, - bool faster_rate) +minstrel_ht_calc_rate_stats(struct minstrel_priv *mp, + struct minstrel_rate_stats *mrs) { - const struct mcs_group *group, *tp_group; - int i, g, max_dur; - int tp_idx; + unsigned int cur_prob; + + if (unlikely(mrs->attempts > 0)) { + cur_prob = MINSTREL_FRAC(mrs->success, mrs->attempts); + minstrel_filter_avg_add(&mrs->prob_avg, + &mrs->prob_avg_1, cur_prob); + mrs->att_hist += mrs->attempts; + mrs->succ_hist += mrs->success; + } - tp_group = &minstrel_mcs_groups[mi->max_tp_rate[0] / MCS_GROUP_RATES]; - tp_idx = mi->max_tp_rate[0] % MCS_GROUP_RATES; + mrs->last_success = mrs->success; + mrs->last_attempts = mrs->attempts; + mrs->success = 0; + mrs->attempts = 0; +} - max_dur = minstrel_get_duration(mi->max_tp_rate[0]); - if (faster_rate) - max_dur -= max_dur / 16; +static bool +minstrel_ht_find_sample_rate(struct minstrel_ht_sta *mi, int type, int idx) +{ + int i; - for (g = 0; g < MINSTREL_GROUPS_NB; g++) { - u16 supported = mi->supported[g]; + for (i = 0; i < MINSTREL_SAMPLE_RATES; i++) { + u16 cur = mi->sample[type].sample_rates[i]; - if (!supported) - continue; + if (cur == idx) + return true; - group = &minstrel_mcs_groups[g]; - if (!minstrel_ht_probe_group(mi, tp_group, tp_idx, group)) - continue; + if (!cur) + break; + } - for (i = 0; supported; supported >>= 1, i++) { - int idx; + return false; +} - if (!(supported & 1)) - continue; +static int +minstrel_ht_move_sample_rates(struct minstrel_ht_sta *mi, int type, + u32 fast_rate_dur, u32 slow_rate_dur) +{ + u16 *rates = mi->sample[type].sample_rates; + int i, j; - if ((group->duration[i] << group->shift) > max_dur) - continue; + for (i = 0, j = 0; i < MINSTREL_SAMPLE_RATES; i++) { + u32 duration; + bool valid = false; + u16 cur; - idx = g * MCS_GROUP_RATES + i; - if (idx == mi->max_tp_rate[0]) - continue; + cur = rates[i]; + if (!cur) + continue; - rates[(*n_rates)++] = idx; + duration = minstrel_get_duration(cur); + switch (type) { + case MINSTREL_SAMPLE_TYPE_SLOW: + valid = duration > fast_rate_dur && + duration < slow_rate_dur; + break; + case MINSTREL_SAMPLE_TYPE_INC: + case MINSTREL_SAMPLE_TYPE_JUMP: + valid = duration < fast_rate_dur; + break; + default: + valid = false; break; } + + if (!valid) { + rates[i] = 0; + continue; + } + + if (i == j) + continue; + + rates[j++] = cur; + rates[i] = 0; } + + return j; } -static void -minstrel_ht_rate_sample_switch(struct minstrel_priv *mp, - struct minstrel_ht_sta *mi) +static int +minstrel_ht_group_min_rate_offset(struct minstrel_ht_sta *mi, int group, + u32 max_duration) { - struct minstrel_rate_stats *mrs; - u16 rates[MINSTREL_GROUPS_NB]; - int n_rates = 0; - int probe_rate = 0; - bool faster_rate; + u16 supported = mi->supported[group]; int i; - u8 random; - /* - * Use rate switching instead of probing packets for devices with - * little control over retry fallback behavior - */ - if (mp->hw->max_rates > 1) - return; + for (i = 0; i < MCS_GROUP_RATES && supported; i++, supported >>= 1) { + if (!(supported & BIT(0))) + continue; - /* - * If the current EWMA prob is >75%, look for a rate that's 6.25% - * faster than the max tp rate. - * If that fails, look again for a rate that is at least as fast - */ - mrs = minstrel_get_ratestats(mi, mi->max_tp_rate[0]); - faster_rate = mrs->prob_avg > MINSTREL_FRAC(75, 100); - minstrel_ht_find_probe_rates(mi, rates, &n_rates, faster_rate); - if (!n_rates && faster_rate) - minstrel_ht_find_probe_rates(mi, rates, &n_rates, false); - - /* If no suitable rate was found, try to pick the next one in the group */ - if (!n_rates) { - int g_idx = mi->max_tp_rate[0] / MCS_GROUP_RATES; - u16 supported = mi->supported[g_idx]; - - supported >>= mi->max_tp_rate[0] % MCS_GROUP_RATES; - for (i = 0; supported; supported >>= 1, i++) { - if (!(supported & 1)) - continue; + if (minstrel_get_duration(MI_RATE(group, i)) >= max_duration) + continue; - probe_rate = mi->max_tp_rate[0] + i; + return i; + } + + return -1; +} + +/* + * Incremental update rates: + * Flip through groups and pick the first group rate that is faster than the + * highest currently selected rate + */ +static u16 +minstrel_ht_next_inc_rate(struct minstrel_ht_sta *mi, u32 fast_rate_dur) +{ + struct minstrel_mcs_group_data *mg; + u8 type = MINSTREL_SAMPLE_TYPE_INC; + int i, index = 0; + u8 group; + + group = mi->sample[type].sample_group; + for (i = 0; i < ARRAY_SIZE(minstrel_mcs_groups); i++) { + group = (group + 1) % ARRAY_SIZE(minstrel_mcs_groups); + mg = &mi->groups[group]; + + index = minstrel_ht_group_min_rate_offset(mi, group, + fast_rate_dur); + if (index < 0) + continue; + + index = MI_RATE(group, index & 0xf); + if (!minstrel_ht_find_sample_rate(mi, type, index)) goto out; + } + index = 0; + +out: + mi->sample[type].sample_group = group; + + return index; +} + +static int +minstrel_ht_next_group_sample_rate(struct minstrel_ht_sta *mi, int group, + u16 supported, int offset) +{ + struct minstrel_mcs_group_data *mg = &mi->groups[group]; + u16 idx; + int i; + + for (i = 0; i < MCS_GROUP_RATES; i++) { + idx = sample_table[mg->column][mg->index]; + if (++mg->index >= MCS_GROUP_RATES) { + mg->index = 0; + if (++mg->column >= ARRAY_SIZE(sample_table)) + mg->column = 0; } - return; + if (idx < offset) + continue; + + if (!(supported & BIT(idx))) + continue; + + return MI_RATE(group, idx); } - i = 0; - if (n_rates > 1) { - random = prandom_u32(); - i = random % n_rates; + return -1; +} + +/* + * Jump rates: + * Sample random rates, use those that are faster than the highest + * currently selected rate. Rates between the fastest and the slowest + * get sorted into the slow sample bucket, but only if it has room + */ +static u16 +minstrel_ht_next_jump_rate(struct minstrel_ht_sta *mi, u32 fast_rate_dur, + u32 slow_rate_dur, int *slow_rate_ofs) +{ + struct minstrel_mcs_group_data *mg; + struct minstrel_rate_stats *mrs; + u32 max_duration = slow_rate_dur; + int i, index, offset; + u16 *slow_rates; + u16 supported; + u32 duration; + u8 group; + + if (*slow_rate_ofs >= MINSTREL_SAMPLE_RATES) + max_duration = fast_rate_dur; + + slow_rates = mi->sample[MINSTREL_SAMPLE_TYPE_SLOW].sample_rates; + group = mi->sample[MINSTREL_SAMPLE_TYPE_JUMP].sample_group; + for (i = 0; i < ARRAY_SIZE(minstrel_mcs_groups); i++) { + u8 type; + + group = (group + 1) % ARRAY_SIZE(minstrel_mcs_groups); + mg = &mi->groups[group]; + + supported = mi->supported[group]; + if (!supported) + continue; + + offset = minstrel_ht_group_min_rate_offset(mi, group, + max_duration); + if (offset < 0) + continue; + + index = minstrel_ht_next_group_sample_rate(mi, group, supported, + offset); + if (index < 0) + continue; + + duration = minstrel_get_duration(index); + if (duration < fast_rate_dur) + type = MINSTREL_SAMPLE_TYPE_JUMP; + else + type = MINSTREL_SAMPLE_TYPE_SLOW; + + if (minstrel_ht_find_sample_rate(mi, type, index)) + continue; + + if (type == MINSTREL_SAMPLE_TYPE_JUMP) + goto found; + + if (*slow_rate_ofs >= MINSTREL_SAMPLE_RATES) + continue; + + if (duration >= slow_rate_dur) + continue; + + /* skip slow rates with high success probability */ + mrs = minstrel_get_ratestats(mi, index); + if (mrs->prob_avg > MINSTREL_FRAC(95, 100)) + continue; + + slow_rates[(*slow_rate_ofs)++] = index; + if (*slow_rate_ofs >= MINSTREL_SAMPLE_RATES) + max_duration = fast_rate_dur; } - probe_rate = rates[i]; + index = 0; -out: - mi->sample_rate = probe_rate; - mi->sample_mode = MINSTREL_SAMPLE_ACTIVE; +found: + mi->sample[MINSTREL_SAMPLE_TYPE_JUMP].sample_group = group; + + return index; +} + +static void +minstrel_ht_refill_sample_rates(struct minstrel_ht_sta *mi) +{ + u32 prob_dur = minstrel_get_duration(mi->max_prob_rate); + u32 tp_dur = minstrel_get_duration(mi->max_tp_rate[0]); + u32 tp2_dur = minstrel_get_duration(mi->max_tp_rate[1]); + u32 fast_rate_dur = min(min(tp_dur, tp2_dur), prob_dur); + u32 slow_rate_dur = max(max(tp_dur, tp2_dur), prob_dur); + u16 *rates; + int i, j; + + rates = mi->sample[MINSTREL_SAMPLE_TYPE_INC].sample_rates; + i = minstrel_ht_move_sample_rates(mi, MINSTREL_SAMPLE_TYPE_INC, + fast_rate_dur, slow_rate_dur); + while (i < MINSTREL_SAMPLE_RATES) { + rates[i] = minstrel_ht_next_inc_rate(mi, tp_dur); + if (!rates[i]) + break; + + i++; + } + + rates = mi->sample[MINSTREL_SAMPLE_TYPE_JUMP].sample_rates; + i = minstrel_ht_move_sample_rates(mi, MINSTREL_SAMPLE_TYPE_JUMP, + fast_rate_dur, slow_rate_dur); + j = minstrel_ht_move_sample_rates(mi, MINSTREL_SAMPLE_TYPE_SLOW, + fast_rate_dur, slow_rate_dur); + while (i < MINSTREL_SAMPLE_RATES) { + rates[i] = minstrel_ht_next_jump_rate(mi, fast_rate_dur, + slow_rate_dur, &j); + if (!rates[i]) + break; + + i++; + } + + for (i = 0; i < ARRAY_SIZE(mi->sample); i++) + memcpy(mi->sample[i].cur_sample_rates, mi->sample[i].sample_rates, + sizeof(mi->sample[i].cur_sample_rates)); } + /* * Update rate statistics and select new primary rates * @@ -668,26 +991,15 @@ out: * higher throughput rates, even if the probablity is a bit lower */ static void -minstrel_ht_update_stats(struct minstrel_priv *mp, struct minstrel_ht_sta *mi, - bool sample) +minstrel_ht_update_stats(struct minstrel_priv *mp, struct minstrel_ht_sta *mi) { struct minstrel_mcs_group_data *mg; struct minstrel_rate_stats *mrs; int group, i, j, cur_prob; u16 tmp_mcs_tp_rate[MAX_THR_RATES], tmp_group_tp_rate[MAX_THR_RATES]; - u16 tmp_cck_tp_rate[MAX_THR_RATES], index; - - mi->sample_mode = MINSTREL_SAMPLE_IDLE; - - if (sample) { - mi->total_packets_cur = mi->total_packets - - mi->total_packets_last; - mi->total_packets_last = mi->total_packets; - } - if (!mp->sample_switch) - sample = false; - if (mi->total_packets_cur < SAMPLE_SWITCH_THR && mp->sample_switch != 1) - sample = false; + u16 tmp_legacy_tp_rate[MAX_THR_RATES], tmp_max_prob_rate; + u16 index; + bool ht_supported = mi->sta->ht_cap.ht_supported; if (mi->ampdu_packets > 0) { if (!ieee80211_hw_check(mp->hw, TX_STATUS_NO_AMPDU_LEN)) @@ -700,65 +1012,72 @@ minstrel_ht_update_stats(struct minstrel_priv *mp, struct minstrel_ht_sta *mi, mi->ampdu_packets = 0; } - mi->sample_slow = 0; - mi->sample_count = 0; - - memset(tmp_mcs_tp_rate, 0, sizeof(tmp_mcs_tp_rate)); - memset(tmp_cck_tp_rate, 0, sizeof(tmp_cck_tp_rate)); if (mi->supported[MINSTREL_CCK_GROUP]) - for (j = 0; j < ARRAY_SIZE(tmp_cck_tp_rate); j++) - tmp_cck_tp_rate[j] = MINSTREL_CCK_GROUP * MCS_GROUP_RATES; + group = MINSTREL_CCK_GROUP; + else if (mi->supported[MINSTREL_OFDM_GROUP]) + group = MINSTREL_OFDM_GROUP; + else + group = 0; + + index = MI_RATE(group, 0); + for (j = 0; j < ARRAY_SIZE(tmp_legacy_tp_rate); j++) + tmp_legacy_tp_rate[j] = index; if (mi->supported[MINSTREL_VHT_GROUP_0]) - index = MINSTREL_VHT_GROUP_0 * MCS_GROUP_RATES; + group = MINSTREL_VHT_GROUP_0; + else if (ht_supported) + group = MINSTREL_HT_GROUP_0; + else if (mi->supported[MINSTREL_CCK_GROUP]) + group = MINSTREL_CCK_GROUP; else - index = MINSTREL_HT_GROUP_0 * MCS_GROUP_RATES; + group = MINSTREL_OFDM_GROUP; + index = MI_RATE(group, 0); + tmp_max_prob_rate = index; for (j = 0; j < ARRAY_SIZE(tmp_mcs_tp_rate); j++) tmp_mcs_tp_rate[j] = index; /* Find best rate sets within all MCS groups*/ for (group = 0; group < ARRAY_SIZE(minstrel_mcs_groups); group++) { + u16 *tp_rate = tmp_mcs_tp_rate; + u16 last_prob = 0; mg = &mi->groups[group]; if (!mi->supported[group]) continue; - mi->sample_count++; - /* (re)Initialize group rate indexes */ for(j = 0; j < MAX_THR_RATES; j++) - tmp_group_tp_rate[j] = MCS_GROUP_RATES * group; + tmp_group_tp_rate[j] = MI_RATE(group, 0); - for (i = 0; i < MCS_GROUP_RATES; i++) { + if (group == MINSTREL_CCK_GROUP && ht_supported) + tp_rate = tmp_legacy_tp_rate; + + for (i = MCS_GROUP_RATES - 1; i >= 0; i--) { if (!(mi->supported[group] & BIT(i))) continue; - index = MCS_GROUP_RATES * group + i; + index = MI_RATE(group, i); mrs = &mg->rates[i]; mrs->retry_updated = false; - minstrel_calc_rate_stats(mp, mrs); + minstrel_ht_calc_rate_stats(mp, mrs); + + if (mrs->att_hist) + last_prob = max(last_prob, mrs->prob_avg); + else + mrs->prob_avg = max(last_prob, mrs->prob_avg); cur_prob = mrs->prob_avg; if (minstrel_ht_get_tp_avg(mi, group, i, cur_prob) == 0) continue; /* Find max throughput rate set */ - if (group != MINSTREL_CCK_GROUP) { - minstrel_ht_sort_best_tp_rates(mi, index, - tmp_mcs_tp_rate); - } else if (group == MINSTREL_CCK_GROUP) { - minstrel_ht_sort_best_tp_rates(mi, index, - tmp_cck_tp_rate); - } + minstrel_ht_sort_best_tp_rates(mi, index, tp_rate); /* Find max throughput rate set within a group */ minstrel_ht_sort_best_tp_rates(mi, index, tmp_group_tp_rate); - - /* Find max probability rate per group and global */ - minstrel_ht_set_best_prob_rate(mi, index); } memcpy(mg->max_group_tp_rate, tmp_group_tp_rate, @@ -766,19 +1085,34 @@ minstrel_ht_update_stats(struct minstrel_priv *mp, struct minstrel_ht_sta *mi, } /* Assign new rate set per sta */ - minstrel_ht_assign_best_tp_rates(mi, tmp_mcs_tp_rate, tmp_cck_tp_rate); + minstrel_ht_assign_best_tp_rates(mi, tmp_mcs_tp_rate, + tmp_legacy_tp_rate); memcpy(mi->max_tp_rate, tmp_mcs_tp_rate, sizeof(mi->max_tp_rate)); - /* Try to increase robustness of max_prob_rate*/ - minstrel_ht_prob_rate_reduce_streams(mi); + for (group = 0; group < ARRAY_SIZE(minstrel_mcs_groups); group++) { + if (!mi->supported[group]) + continue; + + mg = &mi->groups[group]; + mg->max_group_prob_rate = MI_RATE(group, 0); + + for (i = 0; i < MCS_GROUP_RATES; i++) { + if (!(mi->supported[group] & BIT(i))) + continue; + + index = MI_RATE(group, i); + + /* Find max probability rate per group and global */ + minstrel_ht_set_best_prob_rate(mi, &tmp_max_prob_rate, + index); + } + } - /* try to sample all available rates during each interval */ - mi->sample_count *= 8; - if (mp->new_avg) - mi->sample_count /= 2; + mi->max_prob_rate = tmp_max_prob_rate; - if (sample) - minstrel_ht_rate_sample_switch(mp, mi); + /* Try to increase robustness of max_prob_rate*/ + minstrel_ht_prob_rate_reduce_streams(mi); + minstrel_ht_refill_sample_rates(mi); #ifdef CONFIG_MAC80211_DEBUGFS /* use fixed index if set */ @@ -786,17 +1120,20 @@ minstrel_ht_update_stats(struct minstrel_priv *mp, struct minstrel_ht_sta *mi, for (i = 0; i < 4; i++) mi->max_tp_rate[i] = mp->fixed_rate_idx; mi->max_prob_rate = mp->fixed_rate_idx; - mi->sample_mode = MINSTREL_SAMPLE_IDLE; } #endif /* Reset update timer */ mi->last_stats_update = jiffies; + mi->sample_time = jiffies; } static bool -minstrel_ht_txstat_valid(struct minstrel_priv *mp, struct ieee80211_tx_rate *rate) +minstrel_ht_txstat_valid(struct minstrel_priv *mp, struct minstrel_ht_sta *mi, + struct ieee80211_tx_rate *rate) { + int i; + if (rate->idx < 0) return false; @@ -807,32 +1144,15 @@ minstrel_ht_txstat_valid(struct minstrel_priv *mp, struct ieee80211_tx_rate *rat rate->flags & IEEE80211_TX_RC_VHT_MCS) return true; - return rate->idx == mp->cck_rates[0] || - rate->idx == mp->cck_rates[1] || - rate->idx == mp->cck_rates[2] || - rate->idx == mp->cck_rates[3]; -} - -static void -minstrel_set_next_sample_idx(struct minstrel_ht_sta *mi) -{ - struct minstrel_mcs_group_data *mg; - - for (;;) { - mi->sample_group++; - mi->sample_group %= ARRAY_SIZE(minstrel_mcs_groups); - mg = &mi->groups[mi->sample_group]; + for (i = 0; i < ARRAY_SIZE(mp->cck_rates); i++) + if (rate->idx == mp->cck_rates[i]) + return true; - if (!mi->supported[mi->sample_group]) - continue; + for (i = 0; i < ARRAY_SIZE(mp->ofdm_rates[0]); i++) + if (rate->idx == mp->ofdm_rates[mi->band][i]) + return true; - if (++mg->index >= MCS_GROUP_RATES) { - mg->index = 0; - if (++mg->column >= ARRAY_SIZE(sample_table)) - mg->column = 0; - } - break; - } + return false; } static void @@ -840,7 +1160,7 @@ minstrel_downgrade_rate(struct minstrel_ht_sta *mi, u16 *idx, bool primary) { int group, orig_group; - orig_group = group = *idx / MCS_GROUP_RATES; + orig_group = group = MI_RATE_GROUP(*idx); while (group > 0) { group--; @@ -887,21 +1207,14 @@ minstrel_ht_tx_status(void *priv, struct ieee80211_supported_band *sband, void *priv_sta, struct ieee80211_tx_status *st) { struct ieee80211_tx_info *info = st->info; - struct minstrel_ht_sta_priv *msp = priv_sta; - struct minstrel_ht_sta *mi = &msp->ht; + struct minstrel_ht_sta *mi = priv_sta; struct ieee80211_tx_rate *ar = info->status.rates; - struct minstrel_rate_stats *rate, *rate2, *rate_sample = NULL; + struct minstrel_rate_stats *rate, *rate2; struct minstrel_priv *mp = priv; - u32 update_interval = mp->update_interval / 2; + u32 update_interval = mp->update_interval; bool last, update = false; - bool sample_status = false; int i; - if (!msp->is_ht) - return mac80211_minstrel.tx_status_ext(priv, sband, - &msp->legacy, st); - - /* This packet was aggregated but doesn't carry status info */ if ((info->flags & IEEE80211_TX_CTL_AMPDU) && !(info->flags & IEEE80211_TX_STAT_AMPDU)) @@ -913,64 +1226,31 @@ minstrel_ht_tx_status(void *priv, struct ieee80211_supported_band *sband, info->status.ampdu_len = 1; } - mi->ampdu_packets++; - mi->ampdu_len += info->status.ampdu_len; - - if (!mi->sample_wait && !mi->sample_tries && mi->sample_count > 0) { - int avg_ampdu_len = minstrel_ht_avg_ampdu_len(mi); - - mi->sample_wait = 16 + 2 * avg_ampdu_len; - mi->sample_tries = 1; - mi->sample_count--; + /* wraparound */ + if (mi->total_packets >= ~0 - info->status.ampdu_len) { + mi->total_packets = 0; + mi->sample_packets = 0; } + mi->total_packets += info->status.ampdu_len; if (info->flags & IEEE80211_TX_CTL_RATE_CTRL_PROBE) mi->sample_packets += info->status.ampdu_len; - if (mi->sample_mode != MINSTREL_SAMPLE_IDLE) - rate_sample = minstrel_get_ratestats(mi, mi->sample_rate); + mi->ampdu_packets++; + mi->ampdu_len += info->status.ampdu_len; - last = !minstrel_ht_txstat_valid(mp, &ar[0]); + last = !minstrel_ht_txstat_valid(mp, mi, &ar[0]); for (i = 0; !last; i++) { last = (i == IEEE80211_TX_MAX_RATES - 1) || - !minstrel_ht_txstat_valid(mp, &ar[i + 1]); + !minstrel_ht_txstat_valid(mp, mi, &ar[i + 1]); rate = minstrel_ht_get_stats(mp, mi, &ar[i]); - if (rate == rate_sample) - sample_status = true; - if (last) rate->success += info->status.ampdu_ack_len; rate->attempts += ar[i].count * info->status.ampdu_len; } - switch (mi->sample_mode) { - case MINSTREL_SAMPLE_IDLE: - if (mp->new_avg && - (mp->hw->max_rates > 1 || - mi->total_packets_cur < SAMPLE_SWITCH_THR)) - update_interval /= 2; - break; - - case MINSTREL_SAMPLE_ACTIVE: - if (!sample_status) - break; - - mi->sample_mode = MINSTREL_SAMPLE_PENDING; - update = true; - break; - - case MINSTREL_SAMPLE_PENDING: - if (sample_status) - break; - - update = true; - minstrel_ht_update_stats(mp, mi, false); - break; - } - - if (mp->hw->max_rates > 1) { /* * check for sudden death of spatial multiplexing, @@ -993,7 +1273,7 @@ minstrel_ht_tx_status(void *priv, struct ieee80211_supported_band *sband, if (time_after(jiffies, mi->last_stats_update + update_interval)) { update = true; - minstrel_ht_update_stats(mp, mi, true); + minstrel_ht_update_stats(mp, mi); } if (update) @@ -1031,7 +1311,10 @@ minstrel_calc_retransmit(struct minstrel_priv *mp, struct minstrel_ht_sta *mi, ctime += (t_slot * cw) >> 1; cw = min((cw << 1) | 1, mp->cw_max); - if (index / MCS_GROUP_RATES != MINSTREL_CCK_GROUP) { + if (minstrel_ht_is_legacy_group(MI_RATE_GROUP(index))) { + overhead = mi->overhead_legacy; + overhead_rtscts = mi->overhead_legacy_rtscts; + } else { overhead = mi->overhead; overhead_rtscts = mi->overhead_rtscts; } @@ -1061,7 +1344,8 @@ static void minstrel_ht_set_rate(struct minstrel_priv *mp, struct minstrel_ht_sta *mi, struct ieee80211_sta_rates *ratetbl, int offset, int index) { - const struct mcs_group *group = &minstrel_mcs_groups[index / MCS_GROUP_RATES]; + int group_idx = MI_RATE_GROUP(index); + const struct mcs_group *group = &minstrel_mcs_groups[group_idx]; struct minstrel_rate_stats *mrs; u8 idx; u16 flags = group->flags; @@ -1080,13 +1364,17 @@ minstrel_ht_set_rate(struct minstrel_priv *mp, struct minstrel_ht_sta *mi, ratetbl->rate[offset].count_rts = mrs->retry_count_rtscts; } - if (index / MCS_GROUP_RATES == MINSTREL_CCK_GROUP) + index = MI_RATE_IDX(index); + if (group_idx == MINSTREL_CCK_GROUP) idx = mp->cck_rates[index % ARRAY_SIZE(mp->cck_rates)]; + else if (group_idx == MINSTREL_OFDM_GROUP) + idx = mp->ofdm_rates[mi->band][index % + ARRAY_SIZE(mp->ofdm_rates[0])]; else if (flags & IEEE80211_TX_RC_VHT_MCS) idx = ((group->streams - 1) << 4) | - ((index % MCS_GROUP_RATES) & 0xF); + (index & 0xF); else - idx = index % MCS_GROUP_RATES + (group->streams - 1) * 8; + idx = index + (group->streams - 1) * 8; /* enable RTS/CTS if needed: * - if station is in dynamic SMPS (and streams > 1) @@ -1106,17 +1394,17 @@ minstrel_ht_set_rate(struct minstrel_priv *mp, struct minstrel_ht_sta *mi, static inline int minstrel_ht_get_prob_avg(struct minstrel_ht_sta *mi, int rate) { - int group = rate / MCS_GROUP_RATES; - rate %= MCS_GROUP_RATES; + int group = MI_RATE_GROUP(rate); + rate = MI_RATE_IDX(rate); return mi->groups[group].rates[rate].prob_avg; } static int minstrel_ht_get_max_amsdu_len(struct minstrel_ht_sta *mi) { - int group = mi->max_prob_rate / MCS_GROUP_RATES; + int group = MI_RATE_GROUP(mi->max_prob_rate); const struct mcs_group *g = &minstrel_mcs_groups[group]; - int rate = mi->max_prob_rate % MCS_GROUP_RATES; + int rate = MI_RATE_IDX(mi->max_prob_rate); unsigned int duration; /* Disable A-MSDU if max_prob_rate is bad */ @@ -1164,18 +1452,14 @@ static void minstrel_ht_update_rates(struct minstrel_priv *mp, struct minstrel_ht_sta *mi) { struct ieee80211_sta_rates *rates; - u16 first_rate = mi->max_tp_rate[0]; int i = 0; - if (mi->sample_mode == MINSTREL_SAMPLE_ACTIVE) - first_rate = mi->sample_rate; - rates = kzalloc(sizeof(*rates), GFP_ATOMIC); if (!rates) return; /* Start with max_tp_rate[0] */ - minstrel_ht_set_rate(mp, mi, rates, i++, first_rate); + minstrel_ht_set_rate(mp, mi, rates, i++, mi->max_tp_rate[0]); if (mp->hw->max_rates >= 3) { /* At least 3 tx rates supported, use max_tp_rate[1] next */ @@ -1191,102 +1475,20 @@ minstrel_ht_update_rates(struct minstrel_priv *mp, struct minstrel_ht_sta *mi) rate_control_set_rates(mp->hw, mi->sta, rates); } -static int -minstrel_get_sample_rate(struct minstrel_priv *mp, struct minstrel_ht_sta *mi) +static u16 +minstrel_ht_get_sample_rate(struct minstrel_priv *mp, struct minstrel_ht_sta *mi) { - struct minstrel_rate_stats *mrs; - struct minstrel_mcs_group_data *mg; - unsigned int sample_dur, sample_group, cur_max_tp_streams; - int tp_rate1, tp_rate2; - int sample_idx = 0; - - if (mp->hw->max_rates == 1 && mp->sample_switch && - (mi->total_packets_cur >= SAMPLE_SWITCH_THR || - mp->sample_switch == 1)) - return -1; - - if (mi->sample_wait > 0) { - mi->sample_wait--; - return -1; - } - - if (!mi->sample_tries) - return -1; - - sample_group = mi->sample_group; - mg = &mi->groups[sample_group]; - sample_idx = sample_table[mg->column][mg->index]; - minstrel_set_next_sample_idx(mi); + u8 seq; - if (!(mi->supported[sample_group] & BIT(sample_idx))) - return -1; - - mrs = &mg->rates[sample_idx]; - sample_idx += sample_group * MCS_GROUP_RATES; - - /* Set tp_rate1, tp_rate2 to the highest / second highest max_tp_rate */ - if (minstrel_get_duration(mi->max_tp_rate[0]) > - minstrel_get_duration(mi->max_tp_rate[1])) { - tp_rate1 = mi->max_tp_rate[1]; - tp_rate2 = mi->max_tp_rate[0]; + if (mp->hw->max_rates > 1) { + seq = mi->sample_seq; + mi->sample_seq = (seq + 1) % ARRAY_SIZE(minstrel_sample_seq); + seq = minstrel_sample_seq[seq]; } else { - tp_rate1 = mi->max_tp_rate[0]; - tp_rate2 = mi->max_tp_rate[1]; + seq = MINSTREL_SAMPLE_TYPE_INC; } - /* - * Sampling might add some overhead (RTS, no aggregation) - * to the frame. Hence, don't use sampling for the highest currently - * used highest throughput or probability rate. - */ - if (sample_idx == mi->max_tp_rate[0] || sample_idx == mi->max_prob_rate) - return -1; - - /* - * Do not sample if the probability is already higher than 95%, - * or if the rate is 3 times slower than the current max probability - * rate, to avoid wasting airtime. - */ - sample_dur = minstrel_get_duration(sample_idx); - if (mrs->prob_avg > MINSTREL_FRAC(95, 100) || - minstrel_get_duration(mi->max_prob_rate) * 3 < sample_dur) - return -1; - - - /* - * For devices with no configurable multi-rate retry, skip sampling - * below the per-group max throughput rate, and only use one sampling - * attempt per rate - */ - if (mp->hw->max_rates == 1 && - (minstrel_get_duration(mg->max_group_tp_rate[0]) < sample_dur || - mrs->attempts)) - return -1; - - /* Skip already sampled slow rates */ - if (sample_dur >= minstrel_get_duration(tp_rate1) && mrs->attempts) - return -1; - - /* - * Make sure that lower rates get sampled only occasionally, - * if the link is working perfectly. - */ - - cur_max_tp_streams = minstrel_mcs_groups[tp_rate1 / - MCS_GROUP_RATES].streams; - if (sample_dur >= minstrel_get_duration(tp_rate2) && - (cur_max_tp_streams - 1 < - minstrel_mcs_groups[sample_group].streams || - sample_dur >= minstrel_get_duration(mi->max_prob_rate))) { - if (mrs->sample_skipped < 20) - return -1; - - if (mi->sample_slow++ > 2) - return -1; - } - mi->sample_tries--; - - return sample_idx; + return __minstrel_ht_get_sample_rate(mi, seq); } static void @@ -1296,16 +1498,12 @@ minstrel_ht_get_rate(void *priv, struct ieee80211_sta *sta, void *priv_sta, const struct mcs_group *sample_group; struct ieee80211_tx_info *info = IEEE80211_SKB_CB(txrc->skb); struct ieee80211_tx_rate *rate = &info->status.rates[0]; - struct minstrel_ht_sta_priv *msp = priv_sta; - struct minstrel_ht_sta *mi = &msp->ht; + struct minstrel_ht_sta *mi = priv_sta; struct minstrel_priv *mp = priv; - int sample_idx; - - if (!msp->is_ht) - return mac80211_minstrel.get_rate(priv, sta, &msp->legacy, txrc); + u16 sample_idx; if (!(info->flags & IEEE80211_TX_CTL_AMPDU) && - mi->max_prob_rate / MCS_GROUP_RATES != MINSTREL_CCK_GROUP) + !minstrel_ht_is_legacy_group(MI_RATE_GROUP(mi->max_prob_rate))) minstrel_aggr_check(sta, txrc->skb); info->flags |= mi->tx_flags; @@ -1318,23 +1516,18 @@ minstrel_ht_get_rate(void *priv, struct ieee80211_sta *sta, void *priv_sta, /* Don't use EAPOL frames for sampling on non-mrr hw */ if (mp->hw->max_rates == 1 && (info->control.flags & IEEE80211_TX_CTRL_PORT_CTRL_PROTO)) - sample_idx = -1; - else - sample_idx = minstrel_get_sample_rate(mp, mi); - - mi->total_packets++; + return; - /* wraparound */ - if (mi->total_packets == ~0) { - mi->total_packets = 0; - mi->sample_packets = 0; - } + if (time_is_before_jiffies(mi->sample_time)) + return; - if (sample_idx < 0) + mi->sample_time = jiffies + MINSTREL_SAMPLE_INTERVAL; + sample_idx = minstrel_ht_get_sample_rate(mp, mi); + if (!sample_idx) return; - sample_group = &minstrel_mcs_groups[sample_idx / MCS_GROUP_RATES]; - sample_idx %= MCS_GROUP_RATES; + sample_group = &minstrel_mcs_groups[MI_RATE_GROUP(sample_idx)]; + sample_idx = MI_RATE_IDX(sample_idx); if (sample_group == &minstrel_mcs_groups[MINSTREL_CCK_GROUP] && (sample_idx >= 4) != txrc->short_preamble) @@ -1346,8 +1539,11 @@ minstrel_ht_get_rate(void *priv, struct ieee80211_sta *sta, void *priv_sta, if (sample_group == &minstrel_mcs_groups[MINSTREL_CCK_GROUP]) { int idx = sample_idx % ARRAY_SIZE(mp->cck_rates); rate->idx = mp->cck_rates[idx]; + } else if (sample_group == &minstrel_mcs_groups[MINSTREL_OFDM_GROUP]) { + int idx = sample_idx % ARRAY_SIZE(mp->ofdm_rates[0]); + rate->idx = mp->ofdm_rates[mi->band][idx]; } else if (sample_group->flags & IEEE80211_TX_RC_VHT_MCS) { - ieee80211_rate_set_vht(rate, sample_idx % MCS_GROUP_RATES, + ieee80211_rate_set_vht(rate, MI_RATE_IDX(sample_idx), sample_group->streams); } else { rate->idx = sample_idx + (sample_group->streams - 1) * 8; @@ -1366,44 +1562,59 @@ minstrel_ht_update_cck(struct minstrel_priv *mp, struct minstrel_ht_sta *mi, if (sband->band != NL80211_BAND_2GHZ) return; - if (!ieee80211_hw_check(mp->hw, SUPPORTS_HT_CCK_RATES)) + if (sta->ht_cap.ht_supported && + !ieee80211_hw_check(mp->hw, SUPPORTS_HT_CCK_RATES)) return; - mi->cck_supported = 0; - mi->cck_supported_short = 0; for (i = 0; i < 4; i++) { - if (!rate_supported(sta, sband->band, mp->cck_rates[i])) + if (mp->cck_rates[i] == 0xff || + !rate_supported(sta, sband->band, mp->cck_rates[i])) continue; - mi->cck_supported |= BIT(i); + mi->supported[MINSTREL_CCK_GROUP] |= BIT(i); if (sband->bitrates[i].flags & IEEE80211_RATE_SHORT_PREAMBLE) - mi->cck_supported_short |= BIT(i); + mi->supported[MINSTREL_CCK_GROUP] |= BIT(i + 4); } +} + +static void +minstrel_ht_update_ofdm(struct minstrel_priv *mp, struct minstrel_ht_sta *mi, + struct ieee80211_supported_band *sband, + struct ieee80211_sta *sta) +{ + const u8 *rates; + int i; - mi->supported[MINSTREL_CCK_GROUP] = mi->cck_supported; + if (sta->ht_cap.ht_supported) + return; + + rates = mp->ofdm_rates[sband->band]; + for (i = 0; i < ARRAY_SIZE(mp->ofdm_rates[0]); i++) { + if (rates[i] == 0xff || + !rate_supported(sta, sband->band, rates[i])) + continue; + + mi->supported[MINSTREL_OFDM_GROUP] |= BIT(i); + } } static void minstrel_ht_update_caps(void *priv, struct ieee80211_supported_band *sband, struct cfg80211_chan_def *chandef, - struct ieee80211_sta *sta, void *priv_sta) + struct ieee80211_sta *sta, void *priv_sta) { struct minstrel_priv *mp = priv; - struct minstrel_ht_sta_priv *msp = priv_sta; - struct minstrel_ht_sta *mi = &msp->ht; + struct minstrel_ht_sta *mi = priv_sta; struct ieee80211_mcs_info *mcs = &sta->ht_cap.mcs; u16 ht_cap = sta->ht_cap.cap; struct ieee80211_sta_vht_cap *vht_cap = &sta->vht_cap; + const struct ieee80211_rate *ctl_rate; + bool ldpc, erp; int use_vht; int n_supported = 0; int ack_dur; int stbc; int i; - bool ldpc; - - /* fall back to the old minstrel for legacy stations */ - if (!sta->ht_cap.ht_supported) - goto use_legacy; BUILD_BUG_ON(ARRAY_SIZE(minstrel_mcs_groups) != MINSTREL_GROUPS_NB); @@ -1412,10 +1623,10 @@ minstrel_ht_update_caps(void *priv, struct ieee80211_supported_band *sband, else use_vht = 0; - msp->is_ht = true; memset(mi, 0, sizeof(*mi)); mi->sta = sta; + mi->band = sband->band; mi->last_stats_update = jiffies; ack_dur = ieee80211_frame_duration(sband->band, 10, 60, 1, 1, 0); @@ -1423,17 +1634,15 @@ minstrel_ht_update_caps(void *priv, struct ieee80211_supported_band *sband, mi->overhead += ack_dur; mi->overhead_rtscts = mi->overhead + 2 * ack_dur; - mi->avg_ampdu_len = MINSTREL_FRAC(1, 1); + ctl_rate = &sband->bitrates[rate_lowest_index(sband, sta)]; + erp = ctl_rate->flags & IEEE80211_RATE_ERP_G; + ack_dur = ieee80211_frame_duration(sband->band, 10, + ctl_rate->bitrate, erp, 1, + ieee80211_chandef_get_shift(chandef)); + mi->overhead_legacy = ack_dur; + mi->overhead_legacy_rtscts = mi->overhead_legacy + 2 * ack_dur; - /* When using MRR, sample more on the first attempt, without delay */ - if (mp->has_mrr) { - mi->sample_count = 16; - mi->sample_wait = 0; - } else { - mi->sample_count = 8; - mi->sample_wait = 8; - } - mi->sample_tries = 4; + mi->avg_ampdu_len = MINSTREL_FRAC(1, 1); if (!use_vht) { stbc = (ht_cap & IEEE80211_HT_CAP_RX_STBC) >> @@ -1456,10 +1665,8 @@ minstrel_ht_update_caps(void *priv, struct ieee80211_supported_band *sband, int bw, nss; mi->supported[i] = 0; - if (i == MINSTREL_CCK_GROUP) { - minstrel_ht_update_cck(mp, mi, sband, sta); + if (minstrel_ht_is_legacy_group(i)) continue; - } if (gflags & IEEE80211_TX_RC_SHORT_GI) { if (gflags & IEEE80211_TX_RC_40_MHZ_WIDTH) { @@ -1520,24 +1727,12 @@ minstrel_ht_update_caps(void *priv, struct ieee80211_supported_band *sband, n_supported++; } - if (!n_supported) - goto use_legacy; - - mi->supported[MINSTREL_CCK_GROUP] |= mi->cck_supported_short << 4; + minstrel_ht_update_cck(mp, mi, sband, sta); + minstrel_ht_update_ofdm(mp, mi, sband, sta); /* create an initial rate table with the lowest supported rates */ - minstrel_ht_update_stats(mp, mi, true); + minstrel_ht_update_stats(mp, mi); minstrel_ht_update_rates(mp, mi); - - return; - -use_legacy: - msp->is_ht = false; - memset(&msp->legacy, 0, sizeof(msp->legacy)); - msp->legacy.r = msp->ratelist; - msp->legacy.sample_table = msp->sample_table; - return mac80211_minstrel.rate_init(priv, sband, chandef, sta, - &msp->legacy); } static void @@ -1561,7 +1756,7 @@ static void * minstrel_ht_alloc_sta(void *priv, struct ieee80211_sta *sta, gfp_t gfp) { struct ieee80211_supported_band *sband; - struct minstrel_ht_sta_priv *msp; + struct minstrel_ht_sta *mi; struct minstrel_priv *mp = priv; struct ieee80211_hw *hw = mp->hw; int max_rates = 0; @@ -1573,91 +1768,91 @@ minstrel_ht_alloc_sta(void *priv, struct ieee80211_sta *sta, gfp_t gfp) max_rates = sband->n_bitrates; } - msp = kzalloc(sizeof(*msp), gfp); - if (!msp) - return NULL; - - msp->ratelist = kcalloc(max_rates, sizeof(struct minstrel_rate), gfp); - if (!msp->ratelist) - goto error; - - msp->sample_table = kmalloc_array(max_rates, SAMPLE_COLUMNS, gfp); - if (!msp->sample_table) - goto error1; - - return msp; - -error1: - kfree(msp->ratelist); -error: - kfree(msp); - return NULL; + return kzalloc(sizeof(*mi), gfp); } static void minstrel_ht_free_sta(void *priv, struct ieee80211_sta *sta, void *priv_sta) { - struct minstrel_ht_sta_priv *msp = priv_sta; - - kfree(msp->sample_table); - kfree(msp->ratelist); - kfree(msp); + kfree(priv_sta); } static void -minstrel_ht_init_cck_rates(struct minstrel_priv *mp) +minstrel_ht_fill_rate_array(u8 *dest, struct ieee80211_supported_band *sband, + const s16 *bitrates, int n_rates, u32 rate_flags) { - static const int bitrates[4] = { 10, 20, 55, 110 }; - struct ieee80211_supported_band *sband; - u32 rate_flags = ieee80211_chandef_rate_flags(&mp->hw->conf.chandef); int i, j; - sband = mp->hw->wiphy->bands[NL80211_BAND_2GHZ]; - if (!sband) - return; - for (i = 0; i < sband->n_bitrates; i++) { struct ieee80211_rate *rate = &sband->bitrates[i]; - if (rate->flags & IEEE80211_RATE_ERP_G) - continue; - if ((rate_flags & sband->bitrates[i].flags) != rate_flags) continue; - for (j = 0; j < ARRAY_SIZE(bitrates); j++) { + for (j = 0; j < n_rates; j++) { if (rate->bitrate != bitrates[j]) continue; - mp->cck_rates[j] = i; + dest[j] = i; break; } } } +static void +minstrel_ht_init_cck_rates(struct minstrel_priv *mp) +{ + static const s16 bitrates[4] = { 10, 20, 55, 110 }; + struct ieee80211_supported_band *sband; + u32 rate_flags = ieee80211_chandef_rate_flags(&mp->hw->conf.chandef); + + memset(mp->cck_rates, 0xff, sizeof(mp->cck_rates)); + sband = mp->hw->wiphy->bands[NL80211_BAND_2GHZ]; + if (!sband) + return; + + BUILD_BUG_ON(ARRAY_SIZE(mp->cck_rates) != ARRAY_SIZE(bitrates)); + minstrel_ht_fill_rate_array(mp->cck_rates, sband, + minstrel_cck_bitrates, + ARRAY_SIZE(minstrel_cck_bitrates), + rate_flags); +} + +static void +minstrel_ht_init_ofdm_rates(struct minstrel_priv *mp, enum nl80211_band band) +{ + static const s16 bitrates[8] = { 60, 90, 120, 180, 240, 360, 480, 540 }; + struct ieee80211_supported_band *sband; + u32 rate_flags = ieee80211_chandef_rate_flags(&mp->hw->conf.chandef); + + memset(mp->ofdm_rates[band], 0xff, sizeof(mp->ofdm_rates[band])); + sband = mp->hw->wiphy->bands[band]; + if (!sband) + return; + + BUILD_BUG_ON(ARRAY_SIZE(mp->ofdm_rates[band]) != ARRAY_SIZE(bitrates)); + minstrel_ht_fill_rate_array(mp->ofdm_rates[band], sband, + minstrel_ofdm_bitrates, + ARRAY_SIZE(minstrel_ofdm_bitrates), + rate_flags); +} + static void * minstrel_ht_alloc(struct ieee80211_hw *hw) { struct minstrel_priv *mp; + int i; mp = kzalloc(sizeof(struct minstrel_priv), GFP_ATOMIC); if (!mp) return NULL; - mp->sample_switch = -1; - /* contention window settings * Just an approximation. Using the per-queue values would complicate * the calculations and is probably unnecessary */ mp->cw_min = 15; mp->cw_max = 1023; - /* number of packets (in %) to use for sampling other rates - * sample less often for non-mrr packets, because the overhead - * is much higher than with mrr */ - mp->lookaround_rate = 5; - mp->lookaround_rate_mrr = 10; - /* maximum time that the hw is allowed to stay in one MRR segment */ mp->segment_size = 6000; @@ -1671,10 +1866,11 @@ minstrel_ht_alloc(struct ieee80211_hw *hw) mp->has_mrr = true; mp->hw = hw; - mp->update_interval = HZ / 10; - mp->new_avg = true; + mp->update_interval = HZ / 20; minstrel_ht_init_cck_rates(mp); + for (i = 0; i < ARRAY_SIZE(mp->hw->wiphy->bands); i++) + minstrel_ht_init_ofdm_rates(mp, i); return mp; } @@ -1688,10 +1884,6 @@ static void minstrel_ht_add_debugfs(struct ieee80211_hw *hw, void *priv, mp->fixed_rate_idx = (u32) -1; debugfs_create_u32("fixed_rate_idx", S_IRUGO | S_IWUGO, debugfsdir, &mp->fixed_rate_idx); - debugfs_create_u32("sample_switch", S_IRUGO | S_IWUSR, debugfsdir, - &mp->sample_switch); - debugfs_create_bool("new_avg", S_IRUGO | S_IWUSR, debugfsdir, - &mp->new_avg); } #endif @@ -1703,15 +1895,11 @@ minstrel_ht_free(void *priv) static u32 minstrel_ht_get_expected_throughput(void *priv_sta) { - struct minstrel_ht_sta_priv *msp = priv_sta; - struct minstrel_ht_sta *mi = &msp->ht; + struct minstrel_ht_sta *mi = priv_sta; int i, j, prob, tp_avg; - if (!msp->is_ht) - return mac80211_minstrel.get_expected_throughput(priv_sta); - - i = mi->max_tp_rate[0] / MCS_GROUP_RATES; - j = mi->max_tp_rate[0] % MCS_GROUP_RATES; + i = MI_RATE_GROUP(mi->max_tp_rate[0]); + j = MI_RATE_IDX(mi->max_tp_rate[0]); prob = mi->groups[i].rates[j].prob_avg; /* convert tp_avg from pkt per second in kbps */ diff --git a/net/mac80211/rc80211_minstrel_ht.h b/net/mac80211/rc80211_minstrel_ht.h index 53ea3c29debf..06e7126727ad 100644 --- a/net/mac80211/rc80211_minstrel_ht.h +++ b/net/mac80211/rc80211_minstrel_ht.h @@ -6,6 +6,35 @@ #ifndef __RC_MINSTREL_HT_H #define __RC_MINSTREL_HT_H +#include <linux/bitfield.h> + +/* number of highest throughput rates to consider*/ +#define MAX_THR_RATES 4 +#define SAMPLE_COLUMNS 10 /* number of columns in sample table */ + +/* scaled fraction values */ +#define MINSTREL_SCALE 12 +#define MINSTREL_FRAC(val, div) (((val) << MINSTREL_SCALE) / div) +#define MINSTREL_TRUNC(val) ((val) >> MINSTREL_SCALE) + +#define EWMA_LEVEL 96 /* ewma weighting factor [/EWMA_DIV] */ +#define EWMA_DIV 128 + +/* + * Coefficients for moving average with noise filter (period=16), + * scaled by 10 bits + * + * a1 = exp(-pi * sqrt(2) / period) + * coeff2 = 2 * a1 * cos(sqrt(2) * 2 * pi / period) + * coeff3 = -sqr(a1) + * coeff1 = 1 - coeff2 - coeff3 + */ +#define MINSTREL_AVG_COEFF1 (MINSTREL_FRAC(1, 1) - \ + MINSTREL_AVG_COEFF2 - \ + MINSTREL_AVG_COEFF3) +#define MINSTREL_AVG_COEFF2 0x00001499 +#define MINSTREL_AVG_COEFF3 -0x0000092e + /* * The number of streams can be changed to 2 to reduce code * size and memory footprint. @@ -18,17 +47,55 @@ MINSTREL_HT_STREAM_GROUPS) #define MINSTREL_VHT_GROUPS_NB (MINSTREL_MAX_STREAMS * \ MINSTREL_VHT_STREAM_GROUPS) -#define MINSTREL_CCK_GROUPS_NB 1 +#define MINSTREL_LEGACY_GROUPS_NB 2 #define MINSTREL_GROUPS_NB (MINSTREL_HT_GROUPS_NB + \ MINSTREL_VHT_GROUPS_NB + \ - MINSTREL_CCK_GROUPS_NB) + MINSTREL_LEGACY_GROUPS_NB) #define MINSTREL_HT_GROUP_0 0 #define MINSTREL_CCK_GROUP (MINSTREL_HT_GROUP_0 + MINSTREL_HT_GROUPS_NB) -#define MINSTREL_VHT_GROUP_0 (MINSTREL_CCK_GROUP + 1) +#define MINSTREL_OFDM_GROUP (MINSTREL_CCK_GROUP + 1) +#define MINSTREL_VHT_GROUP_0 (MINSTREL_OFDM_GROUP + 1) #define MCS_GROUP_RATES 10 +#define MI_RATE_IDX_MASK GENMASK(3, 0) +#define MI_RATE_GROUP_MASK GENMASK(15, 4) + +#define MI_RATE(_group, _idx) \ + (FIELD_PREP(MI_RATE_GROUP_MASK, _group) | \ + FIELD_PREP(MI_RATE_IDX_MASK, _idx)) + +#define MI_RATE_IDX(_rate) FIELD_GET(MI_RATE_IDX_MASK, _rate) +#define MI_RATE_GROUP(_rate) FIELD_GET(MI_RATE_GROUP_MASK, _rate) + +#define MINSTREL_SAMPLE_RATES 5 /* rates per sample type */ +#define MINSTREL_SAMPLE_INTERVAL (HZ / 50) + +struct minstrel_priv { + struct ieee80211_hw *hw; + bool has_mrr; + unsigned int cw_min; + unsigned int cw_max; + unsigned int max_retry; + unsigned int segment_size; + unsigned int update_interval; + + u8 cck_rates[4]; + u8 ofdm_rates[NUM_NL80211_BANDS][8]; + +#ifdef CONFIG_MAC80211_DEBUGFS + /* + * enable fixed rate processing per RC + * - write static index to debugfs:ieee80211/phyX/rc/fixed_rate_idx + * - write -1 to enable RC processing again + * - setting will be applied on next update + */ + u32 fixed_rate_idx; +#endif +}; + + struct mcs_group { u16 flags; u8 streams; @@ -37,8 +104,36 @@ struct mcs_group { u16 duration[MCS_GROUP_RATES]; }; +extern const s16 minstrel_cck_bitrates[4]; +extern const s16 minstrel_ofdm_bitrates[8]; extern const struct mcs_group minstrel_mcs_groups[]; +struct minstrel_rate_stats { + /* current / last sampling period attempts/success counters */ + u16 attempts, last_attempts; + u16 success, last_success; + + /* total attempts/success counters */ + u32 att_hist, succ_hist; + + /* prob_avg - moving average of prob */ + u16 prob_avg; + u16 prob_avg_1; + + /* maximum retry counts */ + u8 retry_count; + u8 retry_count_rtscts; + + bool retry_updated; +}; + +enum minstrel_sample_type { + MINSTREL_SAMPLE_TYPE_INC, + MINSTREL_SAMPLE_TYPE_JUMP, + MINSTREL_SAMPLE_TYPE_SLOW, + __MINSTREL_SAMPLE_TYPE_MAX +}; + struct minstrel_mcs_group_data { u8 index; u8 column; @@ -51,10 +146,10 @@ struct minstrel_mcs_group_data { struct minstrel_rate_stats rates[MCS_GROUP_RATES]; }; -enum minstrel_sample_mode { - MINSTREL_SAMPLE_IDLE, - MINSTREL_SAMPLE_ACTIVE, - MINSTREL_SAMPLE_PENDING, +struct minstrel_sample_category { + u8 sample_group; + u16 sample_rates[MINSTREL_SAMPLE_RATES]; + u16 cur_sample_rates[MINSTREL_SAMPLE_RATES]; }; struct minstrel_ht_sta { @@ -77,28 +172,22 @@ struct minstrel_ht_sta { /* overhead time in usec for each frame */ unsigned int overhead; unsigned int overhead_rtscts; + unsigned int overhead_legacy; + unsigned int overhead_legacy_rtscts; - unsigned int total_packets_last; - unsigned int total_packets_cur; unsigned int total_packets; unsigned int sample_packets; /* tx flags to add for frames for this sta */ u32 tx_flags; - u8 sample_wait; - u8 sample_tries; - u8 sample_count; - u8 sample_slow; + u8 band; - enum minstrel_sample_mode sample_mode; + u8 sample_seq; u16 sample_rate; - /* current MCS group to be sampled */ - u8 sample_group; - - u8 cck_supported; - u8 cck_supported_short; + unsigned long sample_time; + struct minstrel_sample_category sample[__MINSTREL_SAMPLE_TYPE_MAX]; /* Bitfield of supported MCS rates of all groups */ u16 supported[MINSTREL_GROUPS_NB]; @@ -107,16 +196,6 @@ struct minstrel_ht_sta { struct minstrel_mcs_group_data groups[MINSTREL_GROUPS_NB]; }; -struct minstrel_ht_sta_priv { - union { - struct minstrel_ht_sta ht; - struct minstrel_sta_info legacy; - }; - void *ratelist; - void *sample_table; - bool is_ht; -}; - void minstrel_ht_add_sta_debugfs(void *priv, void *priv_sta, struct dentry *dir); int minstrel_ht_get_tp_avg(struct minstrel_ht_sta *mi, int group, int rate, int prob_avg); diff --git a/net/mac80211/rc80211_minstrel_ht_debugfs.c b/net/mac80211/rc80211_minstrel_ht_debugfs.c index bebb71917742..25b8a67a63a4 100644 --- a/net/mac80211/rc80211_minstrel_ht_debugfs.c +++ b/net/mac80211/rc80211_minstrel_ht_debugfs.c @@ -9,9 +9,13 @@ #include <linux/ieee80211.h> #include <linux/export.h> #include <net/mac80211.h> -#include "rc80211_minstrel.h" #include "rc80211_minstrel_ht.h" +struct minstrel_debugfs_info { + size_t len; + char buf[]; +}; + static ssize_t minstrel_stats_read(struct file *file, char __user *buf, size_t len, loff_t *ppos) { @@ -28,6 +32,18 @@ minstrel_stats_release(struct inode *inode, struct file *file) return 0; } +static bool +minstrel_ht_is_sample_rate(struct minstrel_ht_sta *mi, int idx) +{ + int type, i; + + for (type = 0; type < ARRAY_SIZE(mi->sample); type++) + for (i = 0; i < MINSTREL_SAMPLE_RATES; i++) + if (mi->sample[type].cur_sample_rates[i] == idx) + return true; + return false; +} + static char * minstrel_ht_stats_dump(struct minstrel_ht_sta *mi, int i, char *p) { @@ -52,8 +68,7 @@ minstrel_ht_stats_dump(struct minstrel_ht_sta *mi, int i, char *p) for (j = 0; j < MCS_GROUP_RATES; j++) { struct minstrel_rate_stats *mrs = &mi->groups[i].rates[j]; - static const int bitrates[4] = { 10, 20, 55, 110 }; - int idx = i * MCS_GROUP_RATES + j; + int idx = MI_RATE(i, j); unsigned int duration; if (!(mi->supported[i] & BIT(j))) @@ -67,6 +82,9 @@ minstrel_ht_stats_dump(struct minstrel_ht_sta *mi, int i, char *p) p += sprintf(p, "VHT%c0 ", htmode); p += sprintf(p, "%cGI ", gimode); p += sprintf(p, "%d ", mg->streams); + } else if (i == MINSTREL_OFDM_GROUP) { + p += sprintf(p, "OFDM "); + p += sprintf(p, "1 "); } else { p += sprintf(p, "CCK "); p += sprintf(p, "%cP ", j < 4 ? 'L' : 'S'); @@ -78,13 +96,19 @@ minstrel_ht_stats_dump(struct minstrel_ht_sta *mi, int i, char *p) *(p++) = (idx == mi->max_tp_rate[2]) ? 'C' : ' '; *(p++) = (idx == mi->max_tp_rate[3]) ? 'D' : ' '; *(p++) = (idx == mi->max_prob_rate) ? 'P' : ' '; + *(p++) = minstrel_ht_is_sample_rate(mi, idx) ? 'S' : ' '; if (gflags & IEEE80211_TX_RC_MCS) { p += sprintf(p, " MCS%-2u", (mg->streams - 1) * 8 + j); } else if (gflags & IEEE80211_TX_RC_VHT_MCS) { p += sprintf(p, " MCS%-1u/%1u", j, mg->streams); } else { - int r = bitrates[j % 4]; + int r; + + if (i == MINSTREL_OFDM_GROUP) + r = minstrel_ofdm_bitrates[j % 8]; + else + r = minstrel_cck_bitrates[j % 4]; p += sprintf(p, " %2u.%1uM", r / 10, r % 10); } @@ -120,20 +144,11 @@ minstrel_ht_stats_dump(struct minstrel_ht_sta *mi, int i, char *p) static int minstrel_ht_stats_open(struct inode *inode, struct file *file) { - struct minstrel_ht_sta_priv *msp = inode->i_private; - struct minstrel_ht_sta *mi = &msp->ht; + struct minstrel_ht_sta *mi = inode->i_private; struct minstrel_debugfs_info *ms; unsigned int i; - int ret; char *p; - if (!msp->is_ht) { - inode->i_private = &msp->legacy; - ret = minstrel_stats_open(inode, file); - inode->i_private = msp; - return ret; - } - ms = kmalloc(32768, GFP_KERNEL); if (!ms) return -ENOMEM; @@ -143,9 +158,9 @@ minstrel_ht_stats_open(struct inode *inode, struct file *file) p += sprintf(p, "\n"); p += sprintf(p, - " best ____________rate__________ ____statistics___ _____last____ ______sum-of________\n"); + " best ____________rate__________ ____statistics___ _____last____ ______sum-of________\n"); p += sprintf(p, - "mode guard # rate [name idx airtime max_tp] [avg(tp) avg(prob)] [retry|suc|att] [#success | #attempts]\n"); + "mode guard # rate [name idx airtime max_tp] [avg(tp) avg(prob)] [retry|suc|att] [#success | #attempts]\n"); p = minstrel_ht_stats_dump(mi, MINSTREL_CCK_GROUP, p); for (i = 0; i < MINSTREL_CCK_GROUP; i++) @@ -199,8 +214,7 @@ minstrel_ht_stats_csv_dump(struct minstrel_ht_sta *mi, int i, char *p) for (j = 0; j < MCS_GROUP_RATES; j++) { struct minstrel_rate_stats *mrs = &mi->groups[i].rates[j]; - static const int bitrates[4] = { 10, 20, 55, 110 }; - int idx = i * MCS_GROUP_RATES + j; + int idx = MI_RATE(i, j); unsigned int duration; if (!(mi->supported[i] & BIT(j))) @@ -214,6 +228,8 @@ minstrel_ht_stats_csv_dump(struct minstrel_ht_sta *mi, int i, char *p) p += sprintf(p, "VHT%c0,", htmode); p += sprintf(p, "%cGI,", gimode); p += sprintf(p, "%d,", mg->streams); + } else if (i == MINSTREL_OFDM_GROUP) { + p += sprintf(p, "OFDM,,1,"); } else { p += sprintf(p, "CCK,"); p += sprintf(p, "%cP,", j < 4 ? 'L' : 'S'); @@ -225,13 +241,20 @@ minstrel_ht_stats_csv_dump(struct minstrel_ht_sta *mi, int i, char *p) p += sprintf(p, "%s" ,((idx == mi->max_tp_rate[2]) ? "C" : "")); p += sprintf(p, "%s" ,((idx == mi->max_tp_rate[3]) ? "D" : "")); p += sprintf(p, "%s" ,((idx == mi->max_prob_rate) ? "P" : "")); + p += sprintf(p, "%s", (minstrel_ht_is_sample_rate(mi, idx) ? "S" : "")); if (gflags & IEEE80211_TX_RC_MCS) { p += sprintf(p, ",MCS%-2u,", (mg->streams - 1) * 8 + j); } else if (gflags & IEEE80211_TX_RC_VHT_MCS) { p += sprintf(p, ",MCS%-1u/%1u,", j, mg->streams); } else { - int r = bitrates[j % 4]; + int r; + + if (i == MINSTREL_OFDM_GROUP) + r = minstrel_ofdm_bitrates[j % 8]; + else + r = minstrel_cck_bitrates[j % 4]; + p += sprintf(p, ",%2u.%1uM,", r / 10, r % 10); } @@ -270,22 +293,12 @@ minstrel_ht_stats_csv_dump(struct minstrel_ht_sta *mi, int i, char *p) static int minstrel_ht_stats_csv_open(struct inode *inode, struct file *file) { - struct minstrel_ht_sta_priv *msp = inode->i_private; - struct minstrel_ht_sta *mi = &msp->ht; + struct minstrel_ht_sta *mi = inode->i_private; struct minstrel_debugfs_info *ms; unsigned int i; - int ret; char *p; - if (!msp->is_ht) { - inode->i_private = &msp->legacy; - ret = minstrel_stats_csv_open(inode, file); - inode->i_private = msp; - return ret; - } - ms = kmalloc(32768, GFP_KERNEL); - if (!ms) return -ENOMEM; @@ -316,10 +329,8 @@ static const struct file_operations minstrel_ht_stat_csv_fops = { void minstrel_ht_add_sta_debugfs(void *priv, void *priv_sta, struct dentry *dir) { - struct minstrel_ht_sta_priv *msp = priv_sta; - - debugfs_create_file("rc_stats", 0444, dir, msp, + debugfs_create_file("rc_stats", 0444, dir, priv_sta, &minstrel_ht_stat_fops); - debugfs_create_file("rc_stats_csv", 0444, dir, msp, + debugfs_create_file("rc_stats_csv", 0444, dir, priv_sta, &minstrel_ht_stat_csv_fops); } diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c index 972895e9f22d..c1343c028b76 100644 --- a/net/mac80211/rx.c +++ b/net/mac80211/rx.c @@ -4095,7 +4095,9 @@ void ieee80211_check_fast_rx(struct sta_info *sta) .vif_type = sdata->vif.type, .control_port_protocol = sdata->control_port_protocol, }, *old, *new = NULL; + bool set_offload = false; bool assign = false; + bool offload; /* use sparse to check that we don't return without updating */ __acquire(check_fast_rx); @@ -4208,6 +4210,17 @@ void ieee80211_check_fast_rx(struct sta_info *sta) if (assign) new = kmemdup(&fastrx, sizeof(fastrx), GFP_KERNEL); + offload = assign && + (sdata->vif.offload_flags & IEEE80211_OFFLOAD_DECAP_ENABLED); + + if (offload) + set_offload = !test_and_set_sta_flag(sta, WLAN_STA_DECAP_OFFLOAD); + else + set_offload = test_and_clear_sta_flag(sta, WLAN_STA_DECAP_OFFLOAD); + + if (set_offload) + drv_sta_set_decap_offload(local, sdata, &sta->sta, assign); + spin_lock_bh(&sta->lock); old = rcu_dereference_protected(sta->fast_rx, true); rcu_assign_pointer(sta->fast_rx, new); @@ -4254,6 +4267,104 @@ void ieee80211_check_fast_rx_iface(struct ieee80211_sub_if_data *sdata) mutex_unlock(&local->sta_mtx); } +static void ieee80211_rx_8023(struct ieee80211_rx_data *rx, + struct ieee80211_fast_rx *fast_rx, + int orig_len) +{ + struct ieee80211_sta_rx_stats *stats; + struct ieee80211_rx_status *status = IEEE80211_SKB_RXCB(rx->skb); + struct sta_info *sta = rx->sta; + struct sk_buff *skb = rx->skb; + void *sa = skb->data + ETH_ALEN; + void *da = skb->data; + + stats = &sta->rx_stats; + if (fast_rx->uses_rss) + stats = this_cpu_ptr(sta->pcpu_rx_stats); + + /* statistics part of ieee80211_rx_h_sta_process() */ + if (!(status->flag & RX_FLAG_NO_SIGNAL_VAL)) { + stats->last_signal = status->signal; + if (!fast_rx->uses_rss) + ewma_signal_add(&sta->rx_stats_avg.signal, + -status->signal); + } + + if (status->chains) { + int i; + + stats->chains = status->chains; + for (i = 0; i < ARRAY_SIZE(status->chain_signal); i++) { + int signal = status->chain_signal[i]; + + if (!(status->chains & BIT(i))) + continue; + + stats->chain_signal_last[i] = signal; + if (!fast_rx->uses_rss) + ewma_signal_add(&sta->rx_stats_avg.chain_signal[i], + -signal); + } + } + /* end of statistics */ + + stats->last_rx = jiffies; + stats->last_rate = sta_stats_encode_rate(status); + + stats->fragments++; + stats->packets++; + + skb->dev = fast_rx->dev; + + dev_sw_netstats_rx_add(fast_rx->dev, skb->len); + + /* The seqno index has the same property as needed + * for the rx_msdu field, i.e. it is IEEE80211_NUM_TIDS + * for non-QoS-data frames. Here we know it's a data + * frame, so count MSDUs. + */ + u64_stats_update_begin(&stats->syncp); + stats->msdu[rx->seqno_idx]++; + stats->bytes += orig_len; + u64_stats_update_end(&stats->syncp); + + if (fast_rx->internal_forward) { + struct sk_buff *xmit_skb = NULL; + if (is_multicast_ether_addr(da)) { + xmit_skb = skb_copy(skb, GFP_ATOMIC); + } else if (!ether_addr_equal(da, sa) && + sta_info_get(rx->sdata, da)) { + xmit_skb = skb; + skb = NULL; + } + + if (xmit_skb) { + /* + * Send to wireless media and increase priority by 256 + * to keep the received priority instead of + * reclassifying the frame (see cfg80211_classify8021d). + */ + xmit_skb->priority += 256; + xmit_skb->protocol = htons(ETH_P_802_3); + skb_reset_network_header(xmit_skb); + skb_reset_mac_header(xmit_skb); + dev_queue_xmit(xmit_skb); + } + + if (!skb) + return; + } + + /* deliver to local stack */ + skb->protocol = eth_type_trans(skb, fast_rx->dev); + memset(skb->cb, 0, sizeof(skb->cb)); + if (rx->list) + list_add_tail(&skb->list, rx->list); + else + netif_receive_skb(skb); + +} + static bool ieee80211_invoke_fast_rx(struct ieee80211_rx_data *rx, struct ieee80211_fast_rx *fast_rx) { @@ -4274,9 +4385,6 @@ static bool ieee80211_invoke_fast_rx(struct ieee80211_rx_data *rx, } addrs __aligned(2); struct ieee80211_sta_rx_stats *stats = &sta->rx_stats; - if (fast_rx->uses_rss) - stats = this_cpu_ptr(sta->pcpu_rx_stats); - /* for parallel-rx, we need to have DUP_VALIDATED, otherwise we write * to a common data structure; drivers can implement that per queue * but we don't have that information in mac80211 @@ -4350,32 +4458,6 @@ static bool ieee80211_invoke_fast_rx(struct ieee80211_rx_data *rx, pskb_trim(skb, skb->len - fast_rx->icv_len)) goto drop; - /* statistics part of ieee80211_rx_h_sta_process() */ - if (!(status->flag & RX_FLAG_NO_SIGNAL_VAL)) { - stats->last_signal = status->signal; - if (!fast_rx->uses_rss) - ewma_signal_add(&sta->rx_stats_avg.signal, - -status->signal); - } - - if (status->chains) { - int i; - - stats->chains = status->chains; - for (i = 0; i < ARRAY_SIZE(status->chain_signal); i++) { - int signal = status->chain_signal[i]; - - if (!(status->chains & BIT(i))) - continue; - - stats->chain_signal_last[i] = signal; - if (!fast_rx->uses_rss) - ewma_signal_add(&sta->rx_stats_avg.chain_signal[i], - -signal); - } - } - /* end of statistics */ - if (rx->key && !ieee80211_has_protected(hdr->frame_control)) goto drop; @@ -4387,12 +4469,6 @@ static bool ieee80211_invoke_fast_rx(struct ieee80211_rx_data *rx, return true; } - stats->last_rx = jiffies; - stats->last_rate = sta_stats_encode_rate(status); - - stats->fragments++; - stats->packets++; - /* do the header conversion - first grab the addresses */ ether_addr_copy(addrs.da, skb->data + fast_rx->da_offs); ether_addr_copy(addrs.sa, skb->data + fast_rx->sa_offs); @@ -4401,58 +4477,14 @@ static bool ieee80211_invoke_fast_rx(struct ieee80211_rx_data *rx, /* push the addresses in front */ memcpy(skb_push(skb, sizeof(addrs)), &addrs, sizeof(addrs)); - skb->dev = fast_rx->dev; - - dev_sw_netstats_rx_add(fast_rx->dev, skb->len); - - /* The seqno index has the same property as needed - * for the rx_msdu field, i.e. it is IEEE80211_NUM_TIDS - * for non-QoS-data frames. Here we know it's a data - * frame, so count MSDUs. - */ - u64_stats_update_begin(&stats->syncp); - stats->msdu[rx->seqno_idx]++; - stats->bytes += orig_len; - u64_stats_update_end(&stats->syncp); - - if (fast_rx->internal_forward) { - struct sk_buff *xmit_skb = NULL; - if (is_multicast_ether_addr(addrs.da)) { - xmit_skb = skb_copy(skb, GFP_ATOMIC); - } else if (!ether_addr_equal(addrs.da, addrs.sa) && - sta_info_get(rx->sdata, addrs.da)) { - xmit_skb = skb; - skb = NULL; - } - - if (xmit_skb) { - /* - * Send to wireless media and increase priority by 256 - * to keep the received priority instead of - * reclassifying the frame (see cfg80211_classify8021d). - */ - xmit_skb->priority += 256; - xmit_skb->protocol = htons(ETH_P_802_3); - skb_reset_network_header(xmit_skb); - skb_reset_mac_header(xmit_skb); - dev_queue_xmit(xmit_skb); - } - - if (!skb) - return true; - } - - /* deliver to local stack */ - skb->protocol = eth_type_trans(skb, fast_rx->dev); - memset(skb->cb, 0, sizeof(skb->cb)); - if (rx->list) - list_add_tail(&skb->list, rx->list); - else - netif_receive_skb(skb); + ieee80211_rx_8023(rx, fast_rx, orig_len); return true; drop: dev_kfree_skb(skb); + if (fast_rx->uses_rss) + stats = this_cpu_ptr(sta->pcpu_rx_stats); + stats->dropped++; return true; } @@ -4506,6 +4538,43 @@ static bool ieee80211_prepare_and_rx_handle(struct ieee80211_rx_data *rx, return true; } +static void __ieee80211_rx_handle_8023(struct ieee80211_hw *hw, + struct ieee80211_sta *pubsta, + struct sk_buff *skb, + struct list_head *list) +{ + struct ieee80211_local *local = hw_to_local(hw); + struct ieee80211_fast_rx *fast_rx; + struct ieee80211_rx_data rx; + + memset(&rx, 0, sizeof(rx)); + rx.skb = skb; + rx.local = local; + rx.list = list; + + I802_DEBUG_INC(local->dot11ReceivedFragmentCount); + + /* drop frame if too short for header */ + if (skb->len < sizeof(struct ethhdr)) + goto drop; + + if (!pubsta) + goto drop; + + rx.sta = container_of(pubsta, struct sta_info, sta); + rx.sdata = rx.sta->sdata; + + fast_rx = rcu_dereference(rx.sta->fast_rx); + if (!fast_rx) + goto drop; + + ieee80211_rx_8023(&rx, fast_rx, skb->len); + return; + +drop: + dev_kfree_skb(skb); +} + /* * This is the actual Rx frames handler. as it belongs to Rx path it must * be called with rcu_read_lock protection. @@ -4737,13 +4806,17 @@ void ieee80211_rx_list(struct ieee80211_hw *hw, struct ieee80211_sta *pubsta, * if it was previously present. * Also, frames with less than 16 bytes are dropped. */ - skb = ieee80211_rx_monitor(local, skb, rate); + if (!(status->flag & RX_FLAG_8023)) + skb = ieee80211_rx_monitor(local, skb, rate); if (skb) { ieee80211_tpt_led_trig_rx(local, ((struct ieee80211_hdr *)skb->data)->frame_control, skb->len); - __ieee80211_rx_handle_packet(hw, pubsta, skb, list); + if (status->flag & RX_FLAG_8023) + __ieee80211_rx_handle_8023(hw, pubsta, skb, list); + else + __ieee80211_rx_handle_packet(hw, pubsta, skb, list); } kcov_remote_stop(); diff --git a/net/mac80211/sta_info.h b/net/mac80211/sta_info.h index 7afd07636b81..78b9d0c7cc58 100644 --- a/net/mac80211/sta_info.h +++ b/net/mac80211/sta_info.h @@ -71,6 +71,7 @@ * until pending frames are delivered * @WLAN_STA_USES_ENCRYPTION: This station was configured for encryption, * so drop all packets without a key later. + * @WLAN_STA_DECAP_OFFLOAD: This station uses rx decap offload * * @NUM_WLAN_STA_FLAGS: number of defined flags */ @@ -102,6 +103,7 @@ enum ieee80211_sta_info_flags { WLAN_STA_MPSP_RECIPIENT, WLAN_STA_PS_DELIVER, WLAN_STA_USES_ENCRYPTION, + WLAN_STA_DECAP_OFFLOAD, NUM_WLAN_STA_FLAGS, }; diff --git a/net/mac80211/status.c b/net/mac80211/status.c index 3485610755ef..9baf185ee4c7 100644 --- a/net/mac80211/status.c +++ b/net/mac80211/status.c @@ -628,16 +628,12 @@ static void ieee80211_report_ack_skb(struct ieee80211_local *local, u64 cookie = IEEE80211_SKB_CB(skb)->ack.cookie; struct ieee80211_sub_if_data *sdata; struct ieee80211_hdr *hdr = (void *)skb->data; - __be16 ethertype = 0; - - if (skb->len >= ETH_HLEN && skb->protocol == cpu_to_be16(ETH_P_802_3)) - skb_copy_bits(skb, 2 * ETH_ALEN, ðertype, ETH_TLEN); rcu_read_lock(); sdata = ieee80211_sdata_from_skb(local, skb); if (sdata) { - if (ethertype == sdata->control_port_protocol || - ethertype == cpu_to_be16(ETH_P_PREAUTH)) + if (skb->protocol == sdata->control_port_protocol || + skb->protocol == cpu_to_be16(ETH_P_PREAUTH)) cfg80211_control_port_tx_status(&sdata->wdev, cookie, skb->data, diff --git a/net/mac80211/tdls.c b/net/mac80211/tdls.c index e01e4daeb8cd..f91d02b81b92 100644 --- a/net/mac80211/tdls.c +++ b/net/mac80211/tdls.c @@ -1927,7 +1927,7 @@ ieee80211_process_tdls_channel_switch(struct ieee80211_sub_if_data *sdata, struct ieee80211_tdls_data *tf = (void *)skb->data; struct wiphy *wiphy = sdata->local->hw.wiphy; - ASSERT_RTNL(); + lockdep_assert_wiphy(wiphy); /* make sure the driver supports it */ if (!(wiphy->features & NL80211_FEATURE_TDLS_CHANNEL_SWITCH)) @@ -1979,7 +1979,7 @@ void ieee80211_tdls_chsw_work(struct work_struct *wk) struct sk_buff *skb; struct ieee80211_tdls_data *tf; - rtnl_lock(); + wiphy_lock(local->hw.wiphy); while ((skb = skb_dequeue(&local->skb_queue_tdls_chsw))) { tf = (struct ieee80211_tdls_data *)skb->data; list_for_each_entry(sdata, &local->interfaces, list) { @@ -1994,7 +1994,7 @@ void ieee80211_tdls_chsw_work(struct work_struct *wk) kfree_skb(skb); } - rtnl_unlock(); + wiphy_unlock(local->hw.wiphy); } void ieee80211_tdls_handle_disconnect(struct ieee80211_sub_if_data *sdata, diff --git a/net/mac80211/trace.h b/net/mac80211/trace.h index 601322e16957..8fcc39056402 100644 --- a/net/mac80211/trace.h +++ b/net/mac80211/trace.h @@ -2761,7 +2761,7 @@ DEFINE_EVENT(local_sdata_addr_evt, drv_update_vif_offload, TP_ARGS(local, sdata) ); -TRACE_EVENT(drv_sta_set_4addr, +DECLARE_EVENT_CLASS(sta_flag_evt, TP_PROTO(struct ieee80211_local *local, struct ieee80211_sub_if_data *sdata, struct ieee80211_sta *sta, bool enabled), @@ -2788,6 +2788,22 @@ TRACE_EVENT(drv_sta_set_4addr, ) ); +DEFINE_EVENT(sta_flag_evt, drv_sta_set_4addr, + TP_PROTO(struct ieee80211_local *local, + struct ieee80211_sub_if_data *sdata, + struct ieee80211_sta *sta, bool enabled), + + TP_ARGS(local, sdata, sta, enabled) +); + +DEFINE_EVENT(sta_flag_evt, drv_sta_set_decap_offload, + TP_PROTO(struct ieee80211_local *local, + struct ieee80211_sub_if_data *sdata, + struct ieee80211_sta *sta, bool enabled), + + TP_ARGS(local, sdata, sta, enabled) +); + #endif /* !__MAC80211_DRIVER_TRACE || TRACE_HEADER_MULTI_READ */ #undef TRACE_INCLUDE_PATH diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c index ebb3228ce971..5d06de61047a 100644 --- a/net/mac80211/tx.c +++ b/net/mac80211/tx.c @@ -1182,9 +1182,7 @@ ieee80211_tx_prepare(struct ieee80211_sub_if_data *sdata, tx->sta = rcu_dereference(sdata->u.vlan.sta); if (!tx->sta && sdata->wdev.use_4addr) return TX_DROP; - } else if (info->flags & (IEEE80211_TX_INTFL_NL80211_FRAME_TX | - IEEE80211_TX_CTL_INJECTED) || - tx->sdata->control_port_protocol == tx->skb->protocol) { + } else if (tx->sdata->control_port_protocol == tx->skb->protocol) { tx->sta = sta_info_get_bss(sdata, hdr->addr1); } if (!tx->sta && !is_multicast_ether_addr(hdr->addr1)) @@ -1309,7 +1307,7 @@ static struct sk_buff *codel_dequeue_func(struct codel_vars *cvars, fq = &local->fq; if (cvars == &txqi->def_cvars) - flow = &txqi->def_flow; + flow = &txqi->tin.default_flow; else flow = &fq->flows[cvars - local->cvars]; @@ -1352,7 +1350,7 @@ static struct sk_buff *fq_tin_dequeue_func(struct fq *fq, cparams = &local->cparams; } - if (flow == &txqi->def_flow) + if (flow == &tin->default_flow) cvars = &txqi->def_cvars; else cvars = &local->cvars[flow - fq->flows]; @@ -1379,17 +1377,6 @@ static void fq_skb_free_func(struct fq *fq, ieee80211_free_txskb(&local->hw, skb); } -static struct fq_flow *fq_flow_get_default_func(struct fq *fq, - struct fq_tin *tin, - int idx, - struct sk_buff *skb) -{ - struct txq_info *txqi; - - txqi = container_of(tin, struct txq_info, tin); - return &txqi->def_flow; -} - static void ieee80211_txq_enqueue(struct ieee80211_local *local, struct txq_info *txqi, struct sk_buff *skb) @@ -1402,8 +1389,7 @@ static void ieee80211_txq_enqueue(struct ieee80211_local *local, spin_lock_bh(&fq->lock); fq_tin_enqueue(fq, tin, flow_idx, skb, - fq_skb_free_func, - fq_flow_get_default_func); + fq_skb_free_func); spin_unlock_bh(&fq->lock); } @@ -1446,7 +1432,6 @@ void ieee80211_txq_init(struct ieee80211_sub_if_data *sdata, struct txq_info *txqi, int tid) { fq_tin_init(&txqi->tin); - fq_flow_init(&txqi->def_flow); codel_vars_init(&txqi->def_cvars); codel_stats_init(&txqi->cstats); __skb_queue_head_init(&txqi->frags); @@ -2133,6 +2118,19 @@ bool ieee80211_parse_tx_radiotap(struct sk_buff *skb, if (mcs_known & IEEE80211_RADIOTAP_MCS_HAVE_BW && mcs_bw == IEEE80211_RADIOTAP_MCS_BW_40) rate_flags |= IEEE80211_TX_RC_40_MHZ_WIDTH; + + if (mcs_known & IEEE80211_RADIOTAP_MCS_HAVE_FEC && + mcs_flags & IEEE80211_RADIOTAP_MCS_FEC_LDPC) + info->flags |= IEEE80211_TX_CTL_LDPC; + + if (mcs_known & IEEE80211_RADIOTAP_MCS_HAVE_STBC) { + u8 stbc = u8_get_bits(mcs_flags, + IEEE80211_RADIOTAP_MCS_STBC_MASK); + + info->flags |= + u32_encode_bits(stbc, + IEEE80211_TX_CTL_STBC); + } break; case IEEE80211_RADIOTAP_VHT: @@ -3283,8 +3281,7 @@ static bool ieee80211_amsdu_aggregate(struct ieee80211_sub_if_data *sdata, */ tin = &txqi->tin; - flow = fq_flow_classify(fq, tin, flow_idx, skb, - fq_flow_get_default_func); + flow = fq_flow_classify(fq, tin, flow_idx, skb); head = skb_peek_tail(&flow->queue); if (!head || skb_is_gso(head)) goto out; @@ -3351,8 +3348,6 @@ out_recalc: if (head->len != orig_len) { flow->backlog += head->len - orig_len; tin->backlog_bytes += head->len - orig_len; - - fq_recalc_backlog(fq, tin, flow); } out: spin_unlock_bh(&fq->lock); @@ -3823,6 +3818,8 @@ void __ieee80211_schedule_txq(struct ieee80211_hw *hw, } EXPORT_SYMBOL(__ieee80211_schedule_txq); +DEFINE_STATIC_KEY_FALSE(aql_disable); + bool ieee80211_txq_airtime_check(struct ieee80211_hw *hw, struct ieee80211_txq *txq) { @@ -3832,6 +3829,9 @@ bool ieee80211_txq_airtime_check(struct ieee80211_hw *hw, if (!wiphy_ext_feature_isset(local->hw.wiphy, NL80211_EXT_FEATURE_AQL)) return true; + if (static_branch_unlikely(&aql_disable)) + return true; + if (!txq->sta) return true; @@ -5411,6 +5411,7 @@ int ieee80211_tx_control_port(struct wiphy *wiphy, struct net_device *dev, { struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); struct ieee80211_local *local = sdata->local; + struct sta_info *sta; struct sk_buff *skb; struct ethhdr *ehdr; u32 ctrl_flags = 0; @@ -5433,8 +5434,7 @@ int ieee80211_tx_control_port(struct wiphy *wiphy, struct net_device *dev, if (cookie) ctrl_flags |= IEEE80211_TX_CTL_REQ_TX_STATUS; - flags |= IEEE80211_TX_INTFL_NL80211_FRAME_TX | - IEEE80211_TX_CTL_INJECTED; + flags |= IEEE80211_TX_INTFL_NL80211_FRAME_TX; skb = dev_alloc_skb(local->hw.extra_tx_headroom + sizeof(struct ethhdr) + len); @@ -5451,10 +5451,25 @@ int ieee80211_tx_control_port(struct wiphy *wiphy, struct net_device *dev, ehdr->h_proto = proto; skb->dev = dev; - skb->protocol = htons(ETH_P_802_3); + skb->protocol = proto; skb_reset_network_header(skb); skb_reset_mac_header(skb); + /* update QoS header to prioritize control port frames if possible, + * priorization also happens for control port frames send over + * AF_PACKET + */ + rcu_read_lock(); + + if (ieee80211_lookup_ra_sta(sdata, skb, &sta) == 0 && !IS_ERR(sta)) { + u16 queue = __ieee80211_select_queue(sdata, sta, skb); + + skb_set_queue_mapping(skb, queue); + skb_get_hash(skb); + } + + rcu_read_unlock(); + /* mutex lock is only needed for incrementing the cookie counter */ mutex_lock(&local->mtx); diff --git a/net/mac80211/util.c b/net/mac80211/util.c index 8d3ae6b2f95f..f080fcf60e45 100644 --- a/net/mac80211/util.c +++ b/net/mac80211/util.c @@ -832,7 +832,7 @@ void ieee80211_iterate_active_interfaces_atomic( } EXPORT_SYMBOL_GPL(ieee80211_iterate_active_interfaces_atomic); -void ieee80211_iterate_active_interfaces_rtnl( +void ieee80211_iterate_active_interfaces_mtx( struct ieee80211_hw *hw, u32 iter_flags, void (*iterator)(void *data, u8 *mac, struct ieee80211_vif *vif), @@ -840,12 +840,12 @@ void ieee80211_iterate_active_interfaces_rtnl( { struct ieee80211_local *local = hw_to_local(hw); - ASSERT_RTNL(); + lockdep_assert_wiphy(hw->wiphy); __iterate_interfaces(local, iter_flags | IEEE80211_IFACE_ITER_ACTIVE, iterator, data); } -EXPORT_SYMBOL_GPL(ieee80211_iterate_active_interfaces_rtnl); +EXPORT_SYMBOL_GPL(ieee80211_iterate_active_interfaces_mtx); static void __iterate_stations(struct ieee80211_local *local, void (*iterator)(void *data, @@ -2595,7 +2595,7 @@ int ieee80211_reconfig(struct ieee80211_local *local) mutex_unlock(&local->mtx); if (sched_scan_stopped) - cfg80211_sched_scan_stopped_rtnl(local->hw.wiphy, 0); + cfg80211_sched_scan_stopped_locked(local->hw.wiphy, 0); wake_up: @@ -3811,7 +3811,7 @@ void ieee80211_dfs_cac_cancel(struct ieee80211_local *local) struct cfg80211_chan_def chandef; /* for interface list, to avoid linking iflist_mtx and chanctx_mtx */ - ASSERT_RTNL(); + lockdep_assert_wiphy(local->hw.wiphy); mutex_lock(&local->mtx); list_for_each_entry(sdata, &local->interfaces, list) { @@ -3851,9 +3851,9 @@ void ieee80211_dfs_radar_detected_work(struct work_struct *work) } mutex_unlock(&local->chanctx_mtx); - rtnl_lock(); + wiphy_lock(local->hw.wiphy); ieee80211_dfs_cac_cancel(local); - rtnl_unlock(); + wiphy_unlock(local->hw.wiphy); if (num_chanctx > 1) /* XXX: multi-channel is not supported yet */ diff --git a/net/mac80211/vht.c b/net/mac80211/vht.c index c3ca97373774..e856f9092137 100644 --- a/net/mac80211/vht.c +++ b/net/mac80211/vht.c @@ -484,6 +484,7 @@ enum ieee80211_sta_rx_bandwidth ieee80211_sta_cur_vht_bw(struct sta_info *sta) void ieee80211_sta_set_rx_nss(struct sta_info *sta) { u8 ht_rx_nss = 0, vht_rx_nss = 0, he_rx_nss = 0, rx_nss; + bool support_160; /* if we received a notification already don't overwrite it */ if (sta->sta.rx_nss) @@ -514,7 +515,13 @@ void ieee80211_sta_set_rx_nss(struct sta_info *sta) } } - he_rx_nss = min(rx_mcs_80, rx_mcs_160); + support_160 = he_cap->he_cap_elem.phy_cap_info[0] & + IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_160MHZ_IN_5G; + + if (support_160) + he_rx_nss = min(rx_mcs_80, rx_mcs_160); + else + he_rx_nss = rx_mcs_80; } if (sta->sta.ht_cap.ht_supported) { diff --git a/net/mptcp/mib.c b/net/mptcp/mib.c index b921cbdd9aaa..3780c29c321d 100644 --- a/net/mptcp/mib.c +++ b/net/mptcp/mib.c @@ -29,8 +29,16 @@ static const struct snmp_mib mptcp_snmp_list[] = { SNMP_MIB_ITEM("DuplicateData", MPTCP_MIB_DUPDATA), SNMP_MIB_ITEM("AddAddr", MPTCP_MIB_ADDADDR), SNMP_MIB_ITEM("EchoAdd", MPTCP_MIB_ECHOADD), + SNMP_MIB_ITEM("PortAdd", MPTCP_MIB_PORTADD), + SNMP_MIB_ITEM("MPJoinPortSynRx", MPTCP_MIB_JOINPORTSYNRX), + SNMP_MIB_ITEM("MPJoinPortSynAckRx", MPTCP_MIB_JOINPORTSYNACKRX), + SNMP_MIB_ITEM("MPJoinPortAckRx", MPTCP_MIB_JOINPORTACKRX), + SNMP_MIB_ITEM("MismatchPortSynRx", MPTCP_MIB_MISMATCHPORTSYNRX), + SNMP_MIB_ITEM("MismatchPortAckRx", MPTCP_MIB_MISMATCHPORTACKRX), SNMP_MIB_ITEM("RmAddr", MPTCP_MIB_RMADDR), SNMP_MIB_ITEM("RmSubflow", MPTCP_MIB_RMSUBFLOW), + SNMP_MIB_ITEM("MPPrioTx", MPTCP_MIB_MPPRIOTX), + SNMP_MIB_ITEM("MPPrioRx", MPTCP_MIB_MPPRIORX), SNMP_MIB_SENTINEL }; diff --git a/net/mptcp/mib.h b/net/mptcp/mib.h index 47bcecce1106..72afbc135f8e 100644 --- a/net/mptcp/mib.h +++ b/net/mptcp/mib.h @@ -22,8 +22,16 @@ enum linux_mptcp_mib_field { MPTCP_MIB_DUPDATA, /* Segments discarded due to duplicate DSS */ MPTCP_MIB_ADDADDR, /* Received ADD_ADDR with echo-flag=0 */ MPTCP_MIB_ECHOADD, /* Received ADD_ADDR with echo-flag=1 */ + MPTCP_MIB_PORTADD, /* Received ADD_ADDR with a port-number */ + MPTCP_MIB_JOINPORTSYNRX, /* Received a SYN MP_JOIN with a different port-number */ + MPTCP_MIB_JOINPORTSYNACKRX, /* Received a SYNACK MP_JOIN with a different port-number */ + MPTCP_MIB_JOINPORTACKRX, /* Received an ACK MP_JOIN with a different port-number */ + MPTCP_MIB_MISMATCHPORTSYNRX, /* Received a SYN MP_JOIN with a mismatched port-number */ + MPTCP_MIB_MISMATCHPORTACKRX, /* Received an ACK MP_JOIN with a mismatched port-number */ MPTCP_MIB_RMADDR, /* Received RM_ADDR */ MPTCP_MIB_RMSUBFLOW, /* Remove a subflow */ + MPTCP_MIB_MPPRIOTX, /* Transmit a MP_PRIO */ + MPTCP_MIB_MPPRIORX, /* Received a MP_PRIO */ __MPTCP_MIB_MAX }; diff --git a/net/mptcp/mptcp_diag.c b/net/mptcp/mptcp_diag.c index b70ae4ba3000..f16d9b5ee978 100644 --- a/net/mptcp/mptcp_diag.c +++ b/net/mptcp/mptcp_diag.c @@ -128,11 +128,13 @@ static void mptcp_diag_get_info(struct sock *sk, struct inet_diag_msg *r, info->mptcpi_subflows = READ_ONCE(msk->pm.subflows); info->mptcpi_add_addr_signal = READ_ONCE(msk->pm.add_addr_signaled); info->mptcpi_add_addr_accepted = READ_ONCE(msk->pm.add_addr_accepted); - info->mptcpi_subflows_max = READ_ONCE(msk->pm.subflows_max); - val = READ_ONCE(msk->pm.add_addr_signal_max); + info->mptcpi_local_addr_used = READ_ONCE(msk->pm.local_addr_used); + info->mptcpi_subflows_max = mptcp_pm_get_subflows_max(msk); + val = mptcp_pm_get_add_addr_signal_max(msk); info->mptcpi_add_addr_signal_max = val; - val = READ_ONCE(msk->pm.add_addr_accept_max); + val = mptcp_pm_get_add_addr_accept_max(msk); info->mptcpi_add_addr_accepted_max = val; + info->mptcpi_local_addr_max = mptcp_pm_get_local_addr_max(msk); if (test_bit(MPTCP_FALLBACK_DONE, &msk->flags)) flags |= MPTCP_INFO_FLAG_FALLBACK; if (READ_ONCE(msk->can_ack)) diff --git a/net/mptcp/options.c b/net/mptcp/options.c index 8fec3dabe109..444a38681e93 100644 --- a/net/mptcp/options.c +++ b/net/mptcp/options.c @@ -282,6 +282,15 @@ static void mptcp_parse_option(const struct sk_buff *skb, pr_debug("RM_ADDR: id=%d", mp_opt->rm_id); break; + case MPTCPOPT_MP_PRIO: + if (opsize != TCPOLEN_MPTCP_PRIO) + break; + + mp_opt->mp_prio = 1; + mp_opt->backup = *ptr++ & MPTCP_PRIO_BKUP; + pr_debug("MP_PRIO: prio=%d", mp_opt->backup); + break; + case MPTCPOPT_MP_FASTCLOSE: if (opsize != TCPOLEN_MPTCP_FASTCLOSE) break; @@ -313,6 +322,7 @@ void mptcp_get_options(const struct sk_buff *skb, mp_opt->port = 0; mp_opt->rm_addr = 0; mp_opt->dss = 0; + mp_opt->mp_prio = 0; length = (th->doff * 4) - sizeof(struct tcphdr); ptr = (const unsigned char *)(th + 1); @@ -401,6 +411,7 @@ static void clear_3rdack_retransmission(struct sock *sk) } static bool mptcp_established_options_mp(struct sock *sk, struct sk_buff *skb, + bool snd_data_fin_enable, unsigned int *size, unsigned int remaining, struct mptcp_out_options *opts) @@ -418,9 +429,10 @@ static bool mptcp_established_options_mp(struct sock *sk, struct sk_buff *skb, if (!skb) return false; - /* MPC/MPJ needed only on 3rd ack packet */ - if (subflow->fully_established || - subflow->snd_isn != TCP_SKB_CB(skb)->seq) + /* MPC/MPJ needed only on 3rd ack packet, DATA_FIN and TCP shutdown take precedence */ + if (subflow->fully_established || snd_data_fin_enable || + subflow->snd_isn != TCP_SKB_CB(skb)->seq || + sk->sk_state != TCP_ESTABLISHED) return false; if (subflow->mp_capable) { @@ -492,20 +504,20 @@ static void mptcp_write_data_fin(struct mptcp_subflow_context *subflow, } static bool mptcp_established_options_dss(struct sock *sk, struct sk_buff *skb, + bool snd_data_fin_enable, unsigned int *size, unsigned int remaining, struct mptcp_out_options *opts) { struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk); struct mptcp_sock *msk = mptcp_sk(subflow->conn); - u64 snd_data_fin_enable, ack_seq; unsigned int dss_size = 0; struct mptcp_ext *mpext; unsigned int ack_size; bool ret = false; + u64 ack_seq; mpext = skb ? mptcp_get_ext(skb) : NULL; - snd_data_fin_enable = mptcp_data_fin_enabled(msk); if (!skb || (mpext && mpext->use_map) || snd_data_fin_enable) { unsigned int map_size; @@ -680,16 +692,42 @@ static bool mptcp_established_options_rm_addr(struct sock *sk, return true; } +static bool mptcp_established_options_mp_prio(struct sock *sk, + unsigned int *size, + unsigned int remaining, + struct mptcp_out_options *opts) +{ + struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk); + + if (!subflow->send_mp_prio) + return false; + + /* account for the trailing 'nop' option */ + if (remaining < TCPOLEN_MPTCP_PRIO_ALIGN) + return false; + + *size = TCPOLEN_MPTCP_PRIO_ALIGN; + opts->suboptions |= OPTION_MPTCP_PRIO; + opts->backup = subflow->request_bkup; + + pr_debug("prio=%d", opts->backup); + + return true; +} + bool mptcp_established_options(struct sock *sk, struct sk_buff *skb, unsigned int *size, unsigned int remaining, struct mptcp_out_options *opts) { + struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk); + struct mptcp_sock *msk = mptcp_sk(subflow->conn); unsigned int opt_size = 0; + bool snd_data_fin; bool ret = false; opts->suboptions = 0; - if (unlikely(mptcp_check_fallback(sk))) + if (unlikely(__mptcp_check_fallback(msk))) return false; /* prevent adding of any MPTCP related options on reset packet @@ -698,10 +736,10 @@ bool mptcp_established_options(struct sock *sk, struct sk_buff *skb, if (unlikely(skb && TCP_SKB_CB(skb)->tcp_flags & TCPHDR_RST)) return false; - if (mptcp_established_options_mp(sk, skb, &opt_size, remaining, opts)) + snd_data_fin = mptcp_data_fin_enabled(msk); + if (mptcp_established_options_mp(sk, skb, snd_data_fin, &opt_size, remaining, opts)) ret = true; - else if (mptcp_established_options_dss(sk, skb, &opt_size, remaining, - opts)) + else if (mptcp_established_options_dss(sk, skb, snd_data_fin, &opt_size, remaining, opts)) ret = true; /* we reserved enough space for the above options, and exceeding the @@ -722,6 +760,12 @@ bool mptcp_established_options(struct sock *sk, struct sk_buff *skb, ret = true; } + if (mptcp_established_options_mp_prio(sk, &opt_size, remaining, opts)) { + *size += opt_size; + remaining -= opt_size; + ret = true; + } + return ret; } @@ -829,7 +873,7 @@ fully_established: clear_3rdack_retransmission(ssk); mptcp_pm_subflow_established(msk, subflow); } else { - mptcp_pm_fully_established(msk); + mptcp_pm_fully_established(msk, ssk, GFP_ATOMIC); } return true; @@ -986,6 +1030,10 @@ void mptcp_incoming_options(struct sock *sk, struct sk_buff *skb) mptcp_pm_del_add_timer(msk, &addr); MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_ECHOADD); } + + if (mp_opt.port) + MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_PORTADD); + mp_opt.add_addr = 0; } @@ -994,6 +1042,12 @@ void mptcp_incoming_options(struct sock *sk, struct sk_buff *skb) mp_opt.rm_addr = 0; } + if (mp_opt.mp_prio) { + mptcp_pm_mp_prio_received(sk, mp_opt.backup); + MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_MPPRIORX); + mp_opt.mp_prio = 0; + } + if (!mp_opt.dss) return; @@ -1168,6 +1222,18 @@ mp_capable_done: 0, opts->rm_id); } + if (OPTION_MPTCP_PRIO & opts->suboptions) { + const struct sock *ssk = (const struct sock *)tp; + struct mptcp_subflow_context *subflow; + + subflow = mptcp_subflow_ctx(ssk); + subflow->send_mp_prio = 0; + + *ptr++ = mptcp_option(MPTCPOPT_MP_PRIO, + TCPOLEN_MPTCP_PRIO, + opts->backup, TCPOPT_NOP); + } + if (OPTION_MPTCP_MPJ_SYN & opts->suboptions) { *ptr++ = mptcp_option(MPTCPOPT_MP_JOIN, TCPOLEN_MPTCP_MPJ_SYN, diff --git a/net/mptcp/pm.c b/net/mptcp/pm.c index da2ed576f289..6fd4b2c1b076 100644 --- a/net/mptcp/pm.c +++ b/net/mptcp/pm.c @@ -20,6 +20,8 @@ int mptcp_pm_announce_addr(struct mptcp_sock *msk, pr_debug("msk=%p, local_id=%d", msk, addr->id); + lockdep_assert_held(&msk->pm.lock); + if (add_addr) { pr_warn("addr_signal error, add_addr=%d", add_addr); return -EINVAL; @@ -66,22 +68,26 @@ int mptcp_pm_remove_subflow(struct mptcp_sock *msk, u8 local_id) /* path manager event handlers */ -void mptcp_pm_new_connection(struct mptcp_sock *msk, int server_side) +void mptcp_pm_new_connection(struct mptcp_sock *msk, const struct sock *ssk, int server_side) { struct mptcp_pm_data *pm = &msk->pm; pr_debug("msk=%p, token=%u side=%d", msk, msk->token, server_side); WRITE_ONCE(pm->server_side, server_side); + mptcp_event(MPTCP_EVENT_CREATED, msk, ssk, GFP_ATOMIC); } bool mptcp_pm_allow_new_subflow(struct mptcp_sock *msk) { struct mptcp_pm_data *pm = &msk->pm; + unsigned int subflows_max; int ret = 0; + subflows_max = mptcp_pm_get_subflows_max(msk); + pr_debug("msk=%p subflows=%d max=%d allow=%d", msk, pm->subflows, - pm->subflows_max, READ_ONCE(pm->accept_subflow)); + subflows_max, READ_ONCE(pm->accept_subflow)); /* try to avoid acquiring the lock below */ if (!READ_ONCE(pm->accept_subflow)) @@ -89,8 +95,8 @@ bool mptcp_pm_allow_new_subflow(struct mptcp_sock *msk) spin_lock_bh(&pm->lock); if (READ_ONCE(pm->accept_subflow)) { - ret = pm->subflows < pm->subflows_max; - if (ret && ++pm->subflows == pm->subflows_max) + ret = pm->subflows < subflows_max; + if (ret && ++pm->subflows == subflows_max) WRITE_ONCE(pm->accept_subflow, false); } spin_unlock_bh(&pm->lock); @@ -114,16 +120,13 @@ static bool mptcp_pm_schedule_work(struct mptcp_sock *msk, return true; } -void mptcp_pm_fully_established(struct mptcp_sock *msk) +void mptcp_pm_fully_established(struct mptcp_sock *msk, const struct sock *ssk, gfp_t gfp) { struct mptcp_pm_data *pm = &msk->pm; + bool announce = false; pr_debug("msk=%p", msk); - /* try to avoid acquiring the lock below */ - if (!READ_ONCE(pm->work_pending)) - return; - spin_lock_bh(&pm->lock); /* mptcp_pm_fully_established() can be invoked by multiple @@ -133,9 +136,15 @@ void mptcp_pm_fully_established(struct mptcp_sock *msk) if (READ_ONCE(pm->work_pending) && !(msk->pm.status & BIT(MPTCP_PM_ALREADY_ESTABLISHED))) mptcp_pm_schedule_work(msk, MPTCP_PM_ESTABLISHED); - msk->pm.status |= BIT(MPTCP_PM_ALREADY_ESTABLISHED); + if ((msk->pm.status & BIT(MPTCP_PM_ALREADY_ESTABLISHED)) == 0) + announce = true; + + msk->pm.status |= BIT(MPTCP_PM_ALREADY_ESTABLISHED); spin_unlock_bh(&pm->lock); + + if (announce) + mptcp_event(MPTCP_EVENT_ESTABLISHED, msk, ssk, gfp); } void mptcp_pm_connection_closed(struct mptcp_sock *msk) @@ -174,6 +183,8 @@ void mptcp_pm_add_addr_received(struct mptcp_sock *msk, pr_debug("msk=%p remote_id=%d accept=%d", msk, addr->id, READ_ONCE(pm->accept_addr)); + mptcp_event_addr_announced(msk, addr); + spin_lock_bh(&pm->lock); if (!READ_ONCE(pm->accept_addr)) { @@ -188,8 +199,7 @@ void mptcp_pm_add_addr_received(struct mptcp_sock *msk, void mptcp_pm_add_addr_send_ack(struct mptcp_sock *msk) { - if (!mptcp_pm_should_add_signal_ipv6(msk) && - !mptcp_pm_should_add_signal_port(msk)) + if (!mptcp_pm_should_add_signal(msk)) return; mptcp_pm_schedule_work(msk, MPTCP_PM_ADD_ADDR_SEND_ACK); @@ -201,12 +211,24 @@ void mptcp_pm_rm_addr_received(struct mptcp_sock *msk, u8 rm_id) pr_debug("msk=%p remote_id=%d", msk, rm_id); + mptcp_event_addr_removed(msk, rm_id); + spin_lock_bh(&pm->lock); mptcp_pm_schedule_work(msk, MPTCP_PM_RM_ADDR_RECEIVED); pm->rm_id = rm_id; spin_unlock_bh(&pm->lock); } +void mptcp_pm_mp_prio_received(struct sock *sk, u8 bkup) +{ + struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk); + + pr_debug("subflow->backup=%d, bkup=%d\n", subflow->backup, bkup); + subflow->backup = bkup; + + mptcp_event(MPTCP_EVENT_SUB_PRIORITY, mptcp_sk(subflow->conn), sk, GFP_ATOMIC); +} + /* path manager helpers */ bool mptcp_pm_add_addr_signal(struct mptcp_sock *msk, unsigned int remaining, diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c index a6d983d80576..8e8e35fa4002 100644 --- a/net/mptcp/pm_netlink.c +++ b/net/mptcp/pm_netlink.c @@ -26,6 +26,7 @@ struct mptcp_pm_addr_entry { struct list_head list; struct mptcp_addr_info addr; struct rcu_head rcu; + struct socket *lsk; }; struct mptcp_pm_add_entry { @@ -36,6 +37,9 @@ struct mptcp_pm_add_entry { u8 retrans_times; }; +#define MAX_ADDR_ID 255 +#define BITMAP_SZ DIV_ROUND_UP(MAX_ADDR_ID + 1, BITS_PER_LONG) + struct pm_nl_pernet { /* protects pernet updates */ spinlock_t lock; @@ -46,25 +50,33 @@ struct pm_nl_pernet { unsigned int local_addr_max; unsigned int subflows_max; unsigned int next_id; + unsigned long id_bitmap[BITMAP_SZ]; }; #define MPTCP_PM_ADDR_MAX 8 #define ADD_ADDR_RETRANS_MAX 3 +static void mptcp_pm_nl_add_addr_send_ack(struct mptcp_sock *msk); + static bool addresses_equal(const struct mptcp_addr_info *a, struct mptcp_addr_info *b, bool use_port) { bool addr_equals = false; - if (a->family != b->family) - return false; - - if (a->family == AF_INET) - addr_equals = a->addr.s_addr == b->addr.s_addr; + if (a->family == b->family) { + if (a->family == AF_INET) + addr_equals = a->addr.s_addr == b->addr.s_addr; #if IS_ENABLED(CONFIG_MPTCP_IPV6) - else - addr_equals = !ipv6_addr_cmp(&a->addr6, &b->addr6); + else + addr_equals = !ipv6_addr_cmp(&a->addr6, &b->addr6); + } else if (a->family == AF_INET) { + if (ipv6_addr_v4mapped(&b->addr6)) + addr_equals = a->addr.s_addr == b->addr6.s6_addr32[3]; + } else if (b->family == AF_INET) { + if (ipv6_addr_v4mapped(&a->addr6)) + addr_equals = a->addr6.s6_addr32[3] == b->addr.s_addr; #endif + } if (!addr_equals) return false; @@ -81,14 +93,14 @@ static bool address_zero(const struct mptcp_addr_info *addr) memset(&zero, 0, sizeof(zero)); zero.family = addr->family; - return addresses_equal(addr, &zero, false); + return addresses_equal(addr, &zero, true); } static void local_address(const struct sock_common *skc, struct mptcp_addr_info *addr) { - addr->port = 0; addr->family = skc->skc_family; + addr->port = htons(skc->skc_num); if (addr->family == AF_INET) addr->addr.s_addr = skc->skc_rcv_saddr; #if IS_ENABLED(CONFIG_MPTCP_IPV6) @@ -121,7 +133,7 @@ static bool lookup_subflow_by_saddr(const struct list_head *list, skc = (struct sock_common *)mptcp_subflow_tcp_sock(subflow); local_address(skc, &cur); - if (addresses_equal(&cur, saddr, false)) + if (addresses_equal(&cur, saddr, saddr->port)) return true; } @@ -133,6 +145,9 @@ select_local_address(const struct pm_nl_pernet *pernet, struct mptcp_sock *msk) { struct mptcp_pm_addr_entry *entry, *ret = NULL; + struct sock *sk = (struct sock *)msk; + + msk_owned_by_me(msk); rcu_read_lock(); __mptcp_flush_join_list(msk); @@ -140,11 +155,20 @@ select_local_address(const struct pm_nl_pernet *pernet, if (!(entry->addr.flags & MPTCP_PM_ADDR_FLAG_SUBFLOW)) continue; + if (entry->addr.family != sk->sk_family) { +#if IS_ENABLED(CONFIG_MPTCP_IPV6) + if ((entry->addr.family == AF_INET && + !ipv6_addr_v4mapped(&sk->sk_v6_daddr)) || + (sk->sk_family == AF_INET && + !ipv6_addr_v4mapped(&entry->addr.addr6))) +#endif + continue; + } + /* avoid any address already in use by subflows and * pending join */ - if (entry->addr.family == ((struct sock *)msk)->sk_family && - !lookup_subflow_by_saddr(&msk->conn_list, &entry->addr)) { + if (!lookup_subflow_by_saddr(&msk->conn_list, &entry->addr)) { ret = entry; break; } @@ -177,11 +201,47 @@ select_signal_address(struct pm_nl_pernet *pernet, unsigned int pos) return ret; } +unsigned int mptcp_pm_get_add_addr_signal_max(struct mptcp_sock *msk) +{ + struct pm_nl_pernet *pernet; + + pernet = net_generic(sock_net((struct sock *)msk), pm_nl_pernet_id); + return READ_ONCE(pernet->add_addr_signal_max); +} +EXPORT_SYMBOL_GPL(mptcp_pm_get_add_addr_signal_max); + +unsigned int mptcp_pm_get_add_addr_accept_max(struct mptcp_sock *msk) +{ + struct pm_nl_pernet *pernet; + + pernet = net_generic(sock_net((struct sock *)msk), pm_nl_pernet_id); + return READ_ONCE(pernet->add_addr_accept_max); +} +EXPORT_SYMBOL_GPL(mptcp_pm_get_add_addr_accept_max); + +unsigned int mptcp_pm_get_subflows_max(struct mptcp_sock *msk) +{ + struct pm_nl_pernet *pernet; + + pernet = net_generic(sock_net((struct sock *)msk), pm_nl_pernet_id); + return READ_ONCE(pernet->subflows_max); +} +EXPORT_SYMBOL_GPL(mptcp_pm_get_subflows_max); + +unsigned int mptcp_pm_get_local_addr_max(struct mptcp_sock *msk) +{ + struct pm_nl_pernet *pernet; + + pernet = net_generic(sock_net((struct sock *)msk), pm_nl_pernet_id); + return READ_ONCE(pernet->local_addr_max); +} +EXPORT_SYMBOL_GPL(mptcp_pm_get_local_addr_max); + static void check_work_pending(struct mptcp_sock *msk) { - if (msk->pm.add_addr_signaled == msk->pm.add_addr_signal_max && - (msk->pm.local_addr_used == msk->pm.local_addr_max || - msk->pm.subflows == msk->pm.subflows_max)) + if (msk->pm.add_addr_signaled == mptcp_pm_get_add_addr_signal_max(msk) && + (msk->pm.local_addr_used == mptcp_pm_get_local_addr_max(msk) || + msk->pm.subflows == mptcp_pm_get_subflows_max(msk))) WRITE_ONCE(msk->pm.work_pending, false); } @@ -191,14 +251,37 @@ lookup_anno_list_by_saddr(struct mptcp_sock *msk, { struct mptcp_pm_add_entry *entry; + lockdep_assert_held(&msk->pm.lock); + list_for_each_entry(entry, &msk->pm.anno_list, list) { - if (addresses_equal(&entry->addr, addr, false)) + if (addresses_equal(&entry->addr, addr, true)) return entry; } return NULL; } +bool mptcp_pm_sport_in_anno_list(struct mptcp_sock *msk, const struct sock *sk) +{ + struct mptcp_pm_add_entry *entry; + struct mptcp_addr_info saddr; + bool ret = false; + + local_address((struct sock_common *)sk, &saddr); + + spin_lock_bh(&msk->pm.lock); + list_for_each_entry(entry, &msk->pm.anno_list, list) { + if (addresses_equal(&entry->addr, &saddr, true)) { + ret = true; + goto out; + } + } + +out: + spin_unlock_bh(&msk->pm.lock); + return ret; +} + static void mptcp_pm_add_timer(struct timer_list *timer) { struct mptcp_pm_add_entry *entry = from_timer(entry, timer, add_timer); @@ -266,6 +349,8 @@ static bool mptcp_pm_alloc_anno_list(struct mptcp_sock *msk, struct sock *sk = (struct sock *)msk; struct net *net = sock_net(sk); + lockdep_assert_held(&msk->pm.lock); + if (lookup_anno_list_by_saddr(msk, &entry->addr)) return false; @@ -306,20 +391,26 @@ void mptcp_pm_free_anno_list(struct mptcp_sock *msk) static void mptcp_pm_create_subflow_or_signal_addr(struct mptcp_sock *msk) { - struct mptcp_addr_info remote = { 0 }; struct sock *sk = (struct sock *)msk; struct mptcp_pm_addr_entry *local; + unsigned int add_addr_signal_max; + unsigned int local_addr_max; struct pm_nl_pernet *pernet; + unsigned int subflows_max; pernet = net_generic(sock_net(sk), pm_nl_pernet_id); + add_addr_signal_max = mptcp_pm_get_add_addr_signal_max(msk); + local_addr_max = mptcp_pm_get_local_addr_max(msk); + subflows_max = mptcp_pm_get_subflows_max(msk); + pr_debug("local %d:%d signal %d:%d subflows %d:%d\n", - msk->pm.local_addr_used, msk->pm.local_addr_max, - msk->pm.add_addr_signaled, msk->pm.add_addr_signal_max, - msk->pm.subflows, msk->pm.subflows_max); + msk->pm.local_addr_used, local_addr_max, + msk->pm.add_addr_signaled, add_addr_signal_max, + msk->pm.subflows, subflows_max); /* check first for announce */ - if (msk->pm.add_addr_signaled < msk->pm.add_addr_signal_max) { + if (msk->pm.add_addr_signaled < add_addr_signal_max) { local = select_signal_address(pernet, msk->pm.add_addr_signaled); @@ -331,22 +422,23 @@ static void mptcp_pm_create_subflow_or_signal_addr(struct mptcp_sock *msk) } } else { /* pick failed, avoid fourther attempts later */ - msk->pm.local_addr_used = msk->pm.add_addr_signal_max; + msk->pm.local_addr_used = add_addr_signal_max; } check_work_pending(msk); } /* check if should create a new subflow */ - if (msk->pm.local_addr_used < msk->pm.local_addr_max && - msk->pm.subflows < msk->pm.subflows_max) { - remote_address((struct sock_common *)sk, &remote); - + if (msk->pm.local_addr_used < local_addr_max && + msk->pm.subflows < subflows_max) { local = select_local_address(pernet, msk); if (local) { + struct mptcp_addr_info remote = { 0 }; + msk->pm.local_addr_used++; msk->pm.subflows++; check_work_pending(msk); + remote_address((struct sock_common *)sk, &remote); spin_unlock_bh(&msk->pm.lock); __mptcp_subflow_connect(sk, &local->addr, &remote); spin_lock_bh(&msk->pm.lock); @@ -354,35 +446,40 @@ static void mptcp_pm_create_subflow_or_signal_addr(struct mptcp_sock *msk) } /* lookup failed, avoid fourther attempts later */ - msk->pm.local_addr_used = msk->pm.local_addr_max; + msk->pm.local_addr_used = local_addr_max; check_work_pending(msk); } } -void mptcp_pm_nl_fully_established(struct mptcp_sock *msk) +static void mptcp_pm_nl_fully_established(struct mptcp_sock *msk) { mptcp_pm_create_subflow_or_signal_addr(msk); } -void mptcp_pm_nl_subflow_established(struct mptcp_sock *msk) +static void mptcp_pm_nl_subflow_established(struct mptcp_sock *msk) { mptcp_pm_create_subflow_or_signal_addr(msk); } -void mptcp_pm_nl_add_addr_received(struct mptcp_sock *msk) +static void mptcp_pm_nl_add_addr_received(struct mptcp_sock *msk) { struct sock *sk = (struct sock *)msk; + unsigned int add_addr_accept_max; struct mptcp_addr_info remote; struct mptcp_addr_info local; + unsigned int subflows_max; bool use_port = false; + add_addr_accept_max = mptcp_pm_get_add_addr_accept_max(msk); + subflows_max = mptcp_pm_get_subflows_max(msk); + pr_debug("accepted %d:%d remote family %d", - msk->pm.add_addr_accepted, msk->pm.add_addr_accept_max, + msk->pm.add_addr_accepted, add_addr_accept_max, msk->pm.remote.family); msk->pm.add_addr_accepted++; msk->pm.subflows++; - if (msk->pm.add_addr_accepted >= msk->pm.add_addr_accept_max || - msk->pm.subflows >= msk->pm.subflows_max) + if (msk->pm.add_addr_accepted >= add_addr_accept_max || + msk->pm.subflows >= subflows_max) WRITE_ONCE(msk->pm.accept_addr, false); /* connect to the specified remote address, using whatever @@ -404,12 +501,14 @@ void mptcp_pm_nl_add_addr_received(struct mptcp_sock *msk) mptcp_pm_nl_add_addr_send_ack(msk); } -void mptcp_pm_nl_add_addr_send_ack(struct mptcp_sock *msk) +static void mptcp_pm_nl_add_addr_send_ack(struct mptcp_sock *msk) { struct mptcp_subflow_context *subflow; - if (!mptcp_pm_should_add_signal_ipv6(msk) && - !mptcp_pm_should_add_signal_port(msk)) + msk_owned_by_me(msk); + lockdep_assert_held(&msk->pm.lock); + + if (!mptcp_pm_should_add_signal(msk)) return; __mptcp_flush_join_list(msk); @@ -419,10 +518,9 @@ void mptcp_pm_nl_add_addr_send_ack(struct mptcp_sock *msk) u8 add_addr; spin_unlock_bh(&msk->pm.lock); - if (mptcp_pm_should_add_signal_ipv6(msk)) - pr_debug("send ack for add_addr6"); - if (mptcp_pm_should_add_signal_port(msk)) - pr_debug("send ack for add_addr_port"); + pr_debug("send ack for add_addr%s%s", + mptcp_pm_should_add_signal_ipv6(msk) ? " [ipv6]" : "", + mptcp_pm_should_add_signal_port(msk) ? " [port]" : ""); lock_sock(ssk); tcp_send_ack(ssk); @@ -438,13 +536,50 @@ void mptcp_pm_nl_add_addr_send_ack(struct mptcp_sock *msk) } } -void mptcp_pm_nl_rm_addr_received(struct mptcp_sock *msk) +int mptcp_pm_nl_mp_prio_send_ack(struct mptcp_sock *msk, + struct mptcp_addr_info *addr, + u8 bkup) +{ + struct mptcp_subflow_context *subflow; + + pr_debug("bkup=%d", bkup); + + mptcp_for_each_subflow(msk, subflow) { + struct sock *ssk = mptcp_subflow_tcp_sock(subflow); + struct sock *sk = (struct sock *)msk; + struct mptcp_addr_info local; + + local_address((struct sock_common *)ssk, &local); + if (!addresses_equal(&local, addr, addr->port)) + continue; + + subflow->backup = bkup; + subflow->send_mp_prio = 1; + subflow->request_bkup = bkup; + __MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_MPPRIOTX); + + spin_unlock_bh(&msk->pm.lock); + pr_debug("send ack for mp_prio"); + lock_sock(ssk); + tcp_send_ack(ssk); + release_sock(ssk); + spin_lock_bh(&msk->pm.lock); + + return 0; + } + + return -EINVAL; +} + +static void mptcp_pm_nl_rm_addr_received(struct mptcp_sock *msk) { struct mptcp_subflow_context *subflow, *tmp; struct sock *sk = (struct sock *)msk; pr_debug("address rm_id %d", msk->pm.rm_id); + msk_owned_by_me(msk); + if (!msk->pm.rm_id) return; @@ -460,7 +595,7 @@ void mptcp_pm_nl_rm_addr_received(struct mptcp_sock *msk) spin_unlock_bh(&msk->pm.lock); mptcp_subflow_shutdown(sk, ssk, how); - __mptcp_close_ssk(sk, ssk, subflow); + mptcp_close_ssk(sk, ssk, subflow); spin_lock_bh(&msk->pm.lock); msk->pm.add_addr_accepted--; @@ -473,6 +608,39 @@ void mptcp_pm_nl_rm_addr_received(struct mptcp_sock *msk) } } +void mptcp_pm_nl_work(struct mptcp_sock *msk) +{ + struct mptcp_pm_data *pm = &msk->pm; + + msk_owned_by_me(msk); + + spin_lock_bh(&msk->pm.lock); + + pr_debug("msk=%p status=%x", msk, pm->status); + if (pm->status & BIT(MPTCP_PM_ADD_ADDR_RECEIVED)) { + pm->status &= ~BIT(MPTCP_PM_ADD_ADDR_RECEIVED); + mptcp_pm_nl_add_addr_received(msk); + } + if (pm->status & BIT(MPTCP_PM_ADD_ADDR_SEND_ACK)) { + pm->status &= ~BIT(MPTCP_PM_ADD_ADDR_SEND_ACK); + mptcp_pm_nl_add_addr_send_ack(msk); + } + if (pm->status & BIT(MPTCP_PM_RM_ADDR_RECEIVED)) { + pm->status &= ~BIT(MPTCP_PM_RM_ADDR_RECEIVED); + mptcp_pm_nl_rm_addr_received(msk); + } + if (pm->status & BIT(MPTCP_PM_ESTABLISHED)) { + pm->status &= ~BIT(MPTCP_PM_ESTABLISHED); + mptcp_pm_nl_fully_established(msk); + } + if (pm->status & BIT(MPTCP_PM_SUBFLOW_ESTABLISHED)) { + pm->status &= ~BIT(MPTCP_PM_SUBFLOW_ESTABLISHED); + mptcp_pm_nl_subflow_established(msk); + } + + spin_unlock_bh(&msk->pm.lock); +} + void mptcp_pm_nl_rm_subflow_received(struct mptcp_sock *msk, u8 rm_id) { struct mptcp_subflow_context *subflow, *tmp; @@ -480,6 +648,8 @@ void mptcp_pm_nl_rm_subflow_received(struct mptcp_sock *msk, u8 rm_id) pr_debug("subflow rm_id %d", rm_id); + msk_owned_by_me(msk); + if (!rm_id) return; @@ -495,7 +665,7 @@ void mptcp_pm_nl_rm_subflow_received(struct mptcp_sock *msk, u8 rm_id) spin_unlock_bh(&msk->pm.lock); mptcp_subflow_shutdown(sk, ssk, how); - __mptcp_close_ssk(sk, ssk, subflow); + mptcp_close_ssk(sk, ssk, subflow); spin_lock_bh(&msk->pm.lock); msk->pm.local_addr_used--; @@ -518,16 +688,19 @@ static int mptcp_pm_nl_append_new_local_addr(struct pm_nl_pernet *pernet, struct mptcp_pm_addr_entry *entry) { struct mptcp_pm_addr_entry *cur; + unsigned int addr_max; int ret = -EINVAL; spin_lock_bh(&pernet->lock); /* to keep the code simple, don't do IDR-like allocation for address ID, * just bail when we exceed limits */ - if (pernet->next_id > 255) - goto out; + if (pernet->next_id == MAX_ADDR_ID) + pernet->next_id = 1; if (pernet->addrs >= MPTCP_PM_ADDR_MAX) goto out; + if (test_bit(entry->addr.id, pernet->id_bitmap)) + goto out; /* do not insert duplicate address, differentiate on port only * singled addresses @@ -539,12 +712,34 @@ static int mptcp_pm_nl_append_new_local_addr(struct pm_nl_pernet *pernet, goto out; } - if (entry->addr.flags & MPTCP_PM_ADDR_FLAG_SIGNAL) - pernet->add_addr_signal_max++; - if (entry->addr.flags & MPTCP_PM_ADDR_FLAG_SUBFLOW) - pernet->local_addr_max++; + if (!entry->addr.id) { +find_next: + entry->addr.id = find_next_zero_bit(pernet->id_bitmap, + MAX_ADDR_ID + 1, + pernet->next_id); + if ((!entry->addr.id || entry->addr.id > MAX_ADDR_ID) && + pernet->next_id != 1) { + pernet->next_id = 1; + goto find_next; + } + } + + if (!entry->addr.id || entry->addr.id > MAX_ADDR_ID) + goto out; + + __set_bit(entry->addr.id, pernet->id_bitmap); + if (entry->addr.id > pernet->next_id) + pernet->next_id = entry->addr.id; + + if (entry->addr.flags & MPTCP_PM_ADDR_FLAG_SIGNAL) { + addr_max = pernet->add_addr_signal_max; + WRITE_ONCE(pernet->add_addr_signal_max, addr_max + 1); + } + if (entry->addr.flags & MPTCP_PM_ADDR_FLAG_SUBFLOW) { + addr_max = pernet->local_addr_max; + WRITE_ONCE(pernet->local_addr_max, addr_max + 1); + } - entry->addr.id = pernet->next_id++; pernet->addrs++; list_add_tail_rcu(&entry->list, &pernet->local_addr_list); ret = entry->addr.id; @@ -554,6 +749,53 @@ out: return ret; } +static int mptcp_pm_nl_create_listen_socket(struct sock *sk, + struct mptcp_pm_addr_entry *entry) +{ + struct sockaddr_storage addr; + struct mptcp_sock *msk; + struct socket *ssock; + int backlog = 1024; + int err; + + err = sock_create_kern(sock_net(sk), entry->addr.family, + SOCK_STREAM, IPPROTO_MPTCP, &entry->lsk); + if (err) + return err; + + msk = mptcp_sk(entry->lsk->sk); + if (!msk) { + err = -EINVAL; + goto out; + } + + ssock = __mptcp_nmpc_socket(msk); + if (!ssock) { + err = -EINVAL; + goto out; + } + + mptcp_info2sockaddr(&entry->addr, &addr, entry->addr.family); + err = kernel_bind(ssock, (struct sockaddr *)&addr, + sizeof(struct sockaddr_in)); + if (err) { + pr_warn("kernel_bind error, err=%d", err); + goto out; + } + + err = kernel_listen(ssock, backlog); + if (err) { + pr_warn("kernel_listen error, err=%d", err); + goto out; + } + + return 0; + +out: + sock_release(entry->lsk); + return err; +} + int mptcp_pm_nl_get_local_id(struct mptcp_sock *msk, struct sock_common *skc) { struct mptcp_pm_addr_entry *entry; @@ -580,7 +822,7 @@ int mptcp_pm_nl_get_local_id(struct mptcp_sock *msk, struct sock_common *skc) rcu_read_lock(); list_for_each_entry_rcu(entry, &pernet->local_addr_list, list) { - if (addresses_equal(&entry->addr, &skc_local, false)) { + if (addresses_equal(&entry->addr, &skc_local, entry->addr.port)) { ret = entry->addr.id; break; } @@ -597,6 +839,9 @@ int mptcp_pm_nl_get_local_id(struct mptcp_sock *msk, struct sock_common *skc) entry->addr = skc_local; entry->addr.ifindex = 0; entry->addr.flags = 0; + entry->addr.id = 0; + entry->addr.port = 0; + entry->lsk = NULL; ret = mptcp_pm_nl_append_new_local_addr(pernet, entry); if (ret < 0) kfree(entry); @@ -607,26 +852,23 @@ int mptcp_pm_nl_get_local_id(struct mptcp_sock *msk, struct sock_common *skc) void mptcp_pm_nl_data_init(struct mptcp_sock *msk) { struct mptcp_pm_data *pm = &msk->pm; - struct pm_nl_pernet *pernet; bool subflows; - pernet = net_generic(sock_net((struct sock *)msk), pm_nl_pernet_id); - - pm->add_addr_signal_max = READ_ONCE(pernet->add_addr_signal_max); - pm->add_addr_accept_max = READ_ONCE(pernet->add_addr_accept_max); - pm->local_addr_max = READ_ONCE(pernet->local_addr_max); - pm->subflows_max = READ_ONCE(pernet->subflows_max); - subflows = !!pm->subflows_max; - WRITE_ONCE(pm->work_pending, (!!pm->local_addr_max && subflows) || - !!pm->add_addr_signal_max); - WRITE_ONCE(pm->accept_addr, !!pm->add_addr_accept_max && subflows); + subflows = !!mptcp_pm_get_subflows_max(msk); + WRITE_ONCE(pm->work_pending, (!!mptcp_pm_get_local_addr_max(msk) && subflows) || + !!mptcp_pm_get_add_addr_signal_max(msk)); + WRITE_ONCE(pm->accept_addr, !!mptcp_pm_get_add_addr_accept_max(msk) && subflows); WRITE_ONCE(pm->accept_subflow, subflows); } -#define MPTCP_PM_CMD_GRP_OFFSET 0 +#define MPTCP_PM_CMD_GRP_OFFSET 0 +#define MPTCP_PM_EV_GRP_OFFSET 1 static const struct genl_multicast_group mptcp_pm_mcgrps[] = { [MPTCP_PM_CMD_GRP_OFFSET] = { .name = MPTCP_PM_CMD_GRP_NAME, }, + [MPTCP_PM_EV_GRP_OFFSET] = { .name = MPTCP_PM_EV_GRP_NAME, + .flags = GENL_UNS_ADMIN_PERM, + }, }; static const struct nla_policy @@ -722,6 +964,9 @@ skip_family: if (tb[MPTCP_PM_ADDR_ATTR_FLAGS]) entry->addr.flags = nla_get_u32(tb[MPTCP_PM_ADDR_ATTR_FLAGS]); + if (tb[MPTCP_PM_ADDR_ATTR_PORT]) + entry->addr.port = htons(nla_get_u16(tb[MPTCP_PM_ADDR_ATTR_PORT])); + return 0; } @@ -730,6 +975,31 @@ static struct pm_nl_pernet *genl_info_pm_nl(struct genl_info *info) return net_generic(genl_info_net(info), pm_nl_pernet_id); } +static int mptcp_nl_add_subflow_or_signal_addr(struct net *net) +{ + struct mptcp_sock *msk; + long s_slot = 0, s_num = 0; + + while ((msk = mptcp_token_iter_next(net, &s_slot, &s_num)) != NULL) { + struct sock *sk = (struct sock *)msk; + + if (!READ_ONCE(msk->fully_established)) + goto next; + + lock_sock(sk); + spin_lock_bh(&msk->pm.lock); + mptcp_pm_create_subflow_or_signal_addr(msk); + spin_unlock_bh(&msk->pm.lock); + release_sock(sk); + +next: + sock_put(sk); + cond_resched(); + } + + return 0; +} + static int mptcp_nl_cmd_add_addr(struct sk_buff *skb, struct genl_info *info) { struct nlattr *attr = info->attrs[MPTCP_PM_ATTR_ADDR]; @@ -748,13 +1018,25 @@ static int mptcp_nl_cmd_add_addr(struct sk_buff *skb, struct genl_info *info) } *entry = addr; + if (entry->addr.port) { + ret = mptcp_pm_nl_create_listen_socket(skb->sk, entry); + if (ret) { + GENL_SET_ERR_MSG(info, "create listen socket error"); + kfree(entry); + return ret; + } + } ret = mptcp_pm_nl_append_new_local_addr(pernet, entry); if (ret < 0) { GENL_SET_ERR_MSG(info, "too many addresses or duplicate one"); + if (entry->lsk) + sock_release(entry->lsk); kfree(entry); return ret; } + mptcp_nl_add_subflow_or_signal_addr(sock_net(skb->sk)); + return 0; } @@ -832,11 +1114,44 @@ next: return 0; } +struct addr_entry_release_work { + struct rcu_work rwork; + struct mptcp_pm_addr_entry *entry; +}; + +static void mptcp_pm_release_addr_entry(struct work_struct *work) +{ + struct addr_entry_release_work *w; + struct mptcp_pm_addr_entry *entry; + + w = container_of(to_rcu_work(work), struct addr_entry_release_work, rwork); + entry = w->entry; + if (entry) { + if (entry->lsk) + sock_release(entry->lsk); + kfree(entry); + } + kfree(w); +} + +static void mptcp_pm_free_addr_entry(struct mptcp_pm_addr_entry *entry) +{ + struct addr_entry_release_work *w; + + w = kmalloc(sizeof(*w), GFP_ATOMIC); + if (w) { + INIT_RCU_WORK(&w->rwork, mptcp_pm_release_addr_entry); + w->entry = entry; + queue_rcu_work(system_wq, &w->rwork); + } +} + static int mptcp_nl_cmd_del_addr(struct sk_buff *skb, struct genl_info *info) { struct nlattr *attr = info->attrs[MPTCP_PM_ATTR_ADDR]; struct pm_nl_pernet *pernet = genl_info_pm_nl(info); struct mptcp_pm_addr_entry addr, *entry; + unsigned int addr_max; int ret; ret = mptcp_pm_parse_addr(attr, info, false, &addr); @@ -850,17 +1165,22 @@ static int mptcp_nl_cmd_del_addr(struct sk_buff *skb, struct genl_info *info) spin_unlock_bh(&pernet->lock); return -EINVAL; } - if (entry->addr.flags & MPTCP_PM_ADDR_FLAG_SIGNAL) - pernet->add_addr_signal_max--; - if (entry->addr.flags & MPTCP_PM_ADDR_FLAG_SUBFLOW) - pernet->local_addr_max--; + if (entry->addr.flags & MPTCP_PM_ADDR_FLAG_SIGNAL) { + addr_max = pernet->add_addr_signal_max; + WRITE_ONCE(pernet->add_addr_signal_max, addr_max - 1); + } + if (entry->addr.flags & MPTCP_PM_ADDR_FLAG_SUBFLOW) { + addr_max = pernet->local_addr_max; + WRITE_ONCE(pernet->local_addr_max, addr_max - 1); + } pernet->addrs--; list_del_rcu(&entry->list); + __clear_bit(entry->addr.id, pernet->id_bitmap); spin_unlock_bh(&pernet->lock); mptcp_nl_remove_subflow_and_signal_addr(sock_net(skb->sk), &entry->addr); - kfree_rcu(entry, rcu); + mptcp_pm_free_addr_entry(entry); return ret; } @@ -874,15 +1194,15 @@ static void __flush_addrs(struct net *net, struct list_head *list) struct mptcp_pm_addr_entry, list); mptcp_nl_remove_subflow_and_signal_addr(net, &cur->addr); list_del_rcu(&cur->list); - kfree_rcu(cur, rcu); + mptcp_pm_free_addr_entry(cur); } } static void __reset_counters(struct pm_nl_pernet *pernet) { - pernet->add_addr_signal_max = 0; - pernet->add_addr_accept_max = 0; - pernet->local_addr_max = 0; + WRITE_ONCE(pernet->add_addr_signal_max, 0); + WRITE_ONCE(pernet->add_addr_accept_max, 0); + WRITE_ONCE(pernet->local_addr_max, 0); pernet->addrs = 0; } @@ -894,6 +1214,8 @@ static int mptcp_nl_cmd_flush_addrs(struct sk_buff *skb, struct genl_info *info) spin_lock_bh(&pernet->lock); list_splice_init(&pernet->local_addr_list, &free_list); __reset_counters(pernet); + pernet->next_id = 1; + bitmap_zero(pernet->id_bitmap, MAX_ADDR_ID + 1); spin_unlock_bh(&pernet->lock); __flush_addrs(sock_net(skb->sk), &free_list); return 0; @@ -911,6 +1233,8 @@ static int mptcp_nl_fill_addr(struct sk_buff *skb, if (nla_put_u16(skb, MPTCP_PM_ADDR_ATTR_FAMILY, addr->family)) goto nla_put_failure; + if (nla_put_u16(skb, MPTCP_PM_ADDR_ATTR_PORT, ntohs(addr->port))) + goto nla_put_failure; if (nla_put_u8(skb, MPTCP_PM_ADDR_ATTR_ID, addr->id)) goto nla_put_failure; if (nla_put_u32(skb, MPTCP_PM_ADDR_ATTR_FLAGS, entry->addr.flags)) @@ -994,27 +1318,34 @@ static int mptcp_nl_cmd_dump_addrs(struct sk_buff *msg, struct pm_nl_pernet *pernet; int id = cb->args[0]; void *hdr; + int i; pernet = net_generic(net, pm_nl_pernet_id); spin_lock_bh(&pernet->lock); - list_for_each_entry(entry, &pernet->local_addr_list, list) { - if (entry->addr.id <= id) - continue; - - hdr = genlmsg_put(msg, NETLINK_CB(cb->skb).portid, - cb->nlh->nlmsg_seq, &mptcp_genl_family, - NLM_F_MULTI, MPTCP_PM_CMD_GET_ADDR); - if (!hdr) - break; + for (i = id; i < MAX_ADDR_ID + 1; i++) { + if (test_bit(i, pernet->id_bitmap)) { + entry = __lookup_addr_by_id(pernet, i); + if (!entry) + break; + + if (entry->addr.id <= id) + continue; + + hdr = genlmsg_put(msg, NETLINK_CB(cb->skb).portid, + cb->nlh->nlmsg_seq, &mptcp_genl_family, + NLM_F_MULTI, MPTCP_PM_CMD_GET_ADDR); + if (!hdr) + break; + + if (mptcp_nl_fill_addr(msg, entry) < 0) { + genlmsg_cancel(msg, hdr); + break; + } - if (mptcp_nl_fill_addr(msg, entry) < 0) { - genlmsg_cancel(msg, hdr); - break; + id = entry->addr.id; + genlmsg_end(msg, hdr); } - - id = entry->addr.id; - genlmsg_end(msg, hdr); } spin_unlock_bh(&pernet->lock); @@ -1096,6 +1427,321 @@ fail: return -EMSGSIZE; } +static int mptcp_nl_addr_backup(struct net *net, + struct mptcp_addr_info *addr, + u8 bkup) +{ + long s_slot = 0, s_num = 0; + struct mptcp_sock *msk; + int ret = -EINVAL; + + while ((msk = mptcp_token_iter_next(net, &s_slot, &s_num)) != NULL) { + struct sock *sk = (struct sock *)msk; + + if (list_empty(&msk->conn_list)) + goto next; + + lock_sock(sk); + spin_lock_bh(&msk->pm.lock); + ret = mptcp_pm_nl_mp_prio_send_ack(msk, addr, bkup); + spin_unlock_bh(&msk->pm.lock); + release_sock(sk); + +next: + sock_put(sk); + cond_resched(); + } + + return ret; +} + +static int mptcp_nl_cmd_set_flags(struct sk_buff *skb, struct genl_info *info) +{ + struct nlattr *attr = info->attrs[MPTCP_PM_ATTR_ADDR]; + struct pm_nl_pernet *pernet = genl_info_pm_nl(info); + struct mptcp_pm_addr_entry addr, *entry; + struct net *net = sock_net(skb->sk); + u8 bkup = 0; + int ret; + + ret = mptcp_pm_parse_addr(attr, info, true, &addr); + if (ret < 0) + return ret; + + if (addr.addr.flags & MPTCP_PM_ADDR_FLAG_BACKUP) + bkup = 1; + + list_for_each_entry(entry, &pernet->local_addr_list, list) { + if (addresses_equal(&entry->addr, &addr.addr, true)) { + ret = mptcp_nl_addr_backup(net, &entry->addr, bkup); + if (ret) + return ret; + + if (bkup) + entry->addr.flags |= MPTCP_PM_ADDR_FLAG_BACKUP; + else + entry->addr.flags &= ~MPTCP_PM_ADDR_FLAG_BACKUP; + } + } + + return 0; +} + +static void mptcp_nl_mcast_send(struct net *net, struct sk_buff *nlskb, gfp_t gfp) +{ + genlmsg_multicast_netns(&mptcp_genl_family, net, + nlskb, 0, MPTCP_PM_EV_GRP_OFFSET, gfp); +} + +static int mptcp_event_add_subflow(struct sk_buff *skb, const struct sock *ssk) +{ + const struct inet_sock *issk = inet_sk(ssk); + const struct mptcp_subflow_context *sf; + + if (nla_put_u16(skb, MPTCP_ATTR_FAMILY, ssk->sk_family)) + return -EMSGSIZE; + + switch (ssk->sk_family) { + case AF_INET: + if (nla_put_in_addr(skb, MPTCP_ATTR_SADDR4, issk->inet_saddr)) + return -EMSGSIZE; + if (nla_put_in_addr(skb, MPTCP_ATTR_DADDR4, issk->inet_daddr)) + return -EMSGSIZE; + break; +#if IS_ENABLED(CONFIG_MPTCP_IPV6) + case AF_INET6: { + const struct ipv6_pinfo *np = inet6_sk(ssk); + + if (nla_put_in6_addr(skb, MPTCP_ATTR_SADDR6, &np->saddr)) + return -EMSGSIZE; + if (nla_put_in6_addr(skb, MPTCP_ATTR_DADDR6, &ssk->sk_v6_daddr)) + return -EMSGSIZE; + break; + } +#endif + default: + WARN_ON_ONCE(1); + return -EMSGSIZE; + } + + if (nla_put_be16(skb, MPTCP_ATTR_SPORT, issk->inet_sport)) + return -EMSGSIZE; + if (nla_put_be16(skb, MPTCP_ATTR_DPORT, issk->inet_dport)) + return -EMSGSIZE; + + sf = mptcp_subflow_ctx(ssk); + if (WARN_ON_ONCE(!sf)) + return -EINVAL; + + if (nla_put_u8(skb, MPTCP_ATTR_LOC_ID, sf->local_id)) + return -EMSGSIZE; + + if (nla_put_u8(skb, MPTCP_ATTR_REM_ID, sf->remote_id)) + return -EMSGSIZE; + + return 0; +} + +static int mptcp_event_put_token_and_ssk(struct sk_buff *skb, + const struct mptcp_sock *msk, + const struct sock *ssk) +{ + const struct sock *sk = (const struct sock *)msk; + const struct mptcp_subflow_context *sf; + u8 sk_err; + + if (nla_put_u32(skb, MPTCP_ATTR_TOKEN, msk->token)) + return -EMSGSIZE; + + if (mptcp_event_add_subflow(skb, ssk)) + return -EMSGSIZE; + + sf = mptcp_subflow_ctx(ssk); + if (WARN_ON_ONCE(!sf)) + return -EINVAL; + + if (nla_put_u8(skb, MPTCP_ATTR_BACKUP, sf->backup)) + return -EMSGSIZE; + + if (ssk->sk_bound_dev_if && + nla_put_s32(skb, MPTCP_ATTR_IF_IDX, ssk->sk_bound_dev_if)) + return -EMSGSIZE; + + sk_err = ssk->sk_err; + if (sk_err && sk->sk_state == TCP_ESTABLISHED && + nla_put_u8(skb, MPTCP_ATTR_ERROR, sk_err)) + return -EMSGSIZE; + + return 0; +} + +static int mptcp_event_sub_established(struct sk_buff *skb, + const struct mptcp_sock *msk, + const struct sock *ssk) +{ + return mptcp_event_put_token_and_ssk(skb, msk, ssk); +} + +static int mptcp_event_sub_closed(struct sk_buff *skb, + const struct mptcp_sock *msk, + const struct sock *ssk) +{ + if (mptcp_event_put_token_and_ssk(skb, msk, ssk)) + return -EMSGSIZE; + + return 0; +} + +static int mptcp_event_created(struct sk_buff *skb, + const struct mptcp_sock *msk, + const struct sock *ssk) +{ + int err = nla_put_u32(skb, MPTCP_ATTR_TOKEN, msk->token); + + if (err) + return err; + + return mptcp_event_add_subflow(skb, ssk); +} + +void mptcp_event_addr_removed(const struct mptcp_sock *msk, uint8_t id) +{ + struct net *net = sock_net((const struct sock *)msk); + struct nlmsghdr *nlh; + struct sk_buff *skb; + + if (!genl_has_listeners(&mptcp_genl_family, net, MPTCP_PM_EV_GRP_OFFSET)) + return; + + skb = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_ATOMIC); + if (!skb) + return; + + nlh = genlmsg_put(skb, 0, 0, &mptcp_genl_family, 0, MPTCP_EVENT_REMOVED); + if (!nlh) + goto nla_put_failure; + + if (nla_put_u32(skb, MPTCP_ATTR_TOKEN, msk->token)) + goto nla_put_failure; + + if (nla_put_u8(skb, MPTCP_ATTR_REM_ID, id)) + goto nla_put_failure; + + genlmsg_end(skb, nlh); + mptcp_nl_mcast_send(net, skb, GFP_ATOMIC); + return; + +nla_put_failure: + kfree_skb(skb); +} + +void mptcp_event_addr_announced(const struct mptcp_sock *msk, + const struct mptcp_addr_info *info) +{ + struct net *net = sock_net((const struct sock *)msk); + struct nlmsghdr *nlh; + struct sk_buff *skb; + + if (!genl_has_listeners(&mptcp_genl_family, net, MPTCP_PM_EV_GRP_OFFSET)) + return; + + skb = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_ATOMIC); + if (!skb) + return; + + nlh = genlmsg_put(skb, 0, 0, &mptcp_genl_family, 0, + MPTCP_EVENT_ANNOUNCED); + if (!nlh) + goto nla_put_failure; + + if (nla_put_u32(skb, MPTCP_ATTR_TOKEN, msk->token)) + goto nla_put_failure; + + if (nla_put_u8(skb, MPTCP_ATTR_REM_ID, info->id)) + goto nla_put_failure; + + if (nla_put_be16(skb, MPTCP_ATTR_DPORT, info->port)) + goto nla_put_failure; + + switch (info->family) { + case AF_INET: + if (nla_put_in_addr(skb, MPTCP_ATTR_DADDR4, info->addr.s_addr)) + goto nla_put_failure; + break; +#if IS_ENABLED(CONFIG_MPTCP_IPV6) + case AF_INET6: + if (nla_put_in6_addr(skb, MPTCP_ATTR_DADDR6, &info->addr6)) + goto nla_put_failure; + break; +#endif + default: + WARN_ON_ONCE(1); + goto nla_put_failure; + } + + genlmsg_end(skb, nlh); + mptcp_nl_mcast_send(net, skb, GFP_ATOMIC); + return; + +nla_put_failure: + kfree_skb(skb); +} + +void mptcp_event(enum mptcp_event_type type, const struct mptcp_sock *msk, + const struct sock *ssk, gfp_t gfp) +{ + struct net *net = sock_net((const struct sock *)msk); + struct nlmsghdr *nlh; + struct sk_buff *skb; + + if (!genl_has_listeners(&mptcp_genl_family, net, MPTCP_PM_EV_GRP_OFFSET)) + return; + + skb = nlmsg_new(NLMSG_DEFAULT_SIZE, gfp); + if (!skb) + return; + + nlh = genlmsg_put(skb, 0, 0, &mptcp_genl_family, 0, type); + if (!nlh) + goto nla_put_failure; + + switch (type) { + case MPTCP_EVENT_UNSPEC: + WARN_ON_ONCE(1); + break; + case MPTCP_EVENT_CREATED: + case MPTCP_EVENT_ESTABLISHED: + if (mptcp_event_created(skb, msk, ssk) < 0) + goto nla_put_failure; + break; + case MPTCP_EVENT_CLOSED: + if (nla_put_u32(skb, MPTCP_ATTR_TOKEN, msk->token) < 0) + goto nla_put_failure; + break; + case MPTCP_EVENT_ANNOUNCED: + case MPTCP_EVENT_REMOVED: + /* call mptcp_event_addr_announced()/removed instead */ + WARN_ON_ONCE(1); + break; + case MPTCP_EVENT_SUB_ESTABLISHED: + case MPTCP_EVENT_SUB_PRIORITY: + if (mptcp_event_sub_established(skb, msk, ssk) < 0) + goto nla_put_failure; + break; + case MPTCP_EVENT_SUB_CLOSED: + if (mptcp_event_sub_closed(skb, msk, ssk) < 0) + goto nla_put_failure; + break; + } + + genlmsg_end(skb, nlh); + mptcp_nl_mcast_send(net, skb, gfp); + return; + +nla_put_failure: + kfree_skb(skb); +} + static const struct genl_small_ops mptcp_pm_ops[] = { { .cmd = MPTCP_PM_CMD_ADD_ADDR, @@ -1126,6 +1772,11 @@ static const struct genl_small_ops mptcp_pm_ops[] = { .cmd = MPTCP_PM_CMD_GET_LIMITS, .doit = mptcp_nl_cmd_get_limits, }, + { + .cmd = MPTCP_PM_CMD_SET_FLAGS, + .doit = mptcp_nl_cmd_set_flags, + .flags = GENL_ADMIN_PERM, + }, }; static struct genl_family mptcp_genl_family __ro_after_init = { @@ -1148,6 +1799,7 @@ static int __net_init pm_nl_init_net(struct net *net) INIT_LIST_HEAD_RCU(&pernet->local_addr_list); __reset_counters(pernet); pernet->next_id = 1; + bitmap_zero(pernet->id_bitmap, MAX_ADDR_ID + 1); spin_lock_init(&pernet->lock); return 0; } diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index 06da6ad31c87..c5d5e68940ea 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -11,6 +11,7 @@ #include <linux/netdevice.h> #include <linux/sched/signal.h> #include <linux/atomic.h> +#include <linux/igmp.h> #include <net/sock.h> #include <net/inet_common.h> #include <net/inet_hashtables.h> @@ -19,6 +20,7 @@ #include <net/tcp_states.h> #if IS_ENABLED(CONFIG_MPTCP_IPV6) #include <net/transp_v6.h> +#include <net/addrconf.h> #endif #include <net/mptcp.h> #include <net/xfrm.h> @@ -45,11 +47,14 @@ static struct percpu_counter mptcp_sockets_allocated; static void __mptcp_destroy_sock(struct sock *sk); static void __mptcp_check_send_data_fin(struct sock *sk); +DEFINE_PER_CPU(struct mptcp_delegated_action, mptcp_delegated_actions); +static struct net_device mptcp_napi_dev; + /* If msk has an initial subflow socket, and the MP_CAPABLE handshake has not * completed yet or has failed, return the subflow socket. * Otherwise return NULL. */ -static struct socket *__mptcp_nmpc_socket(const struct mptcp_sock *msk) +struct socket *__mptcp_nmpc_socket(const struct mptcp_sock *msk) { if (!msk->subflow || READ_ONCE(msk->can_ack)) return NULL; @@ -114,11 +119,7 @@ static int __mptcp_socket_create(struct mptcp_sock *msk) list_add(&subflow->node, &msk->conn_list); sock_hold(ssock->sk); subflow->request_mptcp = 1; - - /* accept() will wait on first subflow sk_wq, and we always wakes up - * via msk->sk_socket - */ - RCU_INIT_POINTER(msk->first->sk_wq, &sk->sk_socket->wq); + mptcp_sock_graft(msk->first, sk->sk_socket); return 0; } @@ -743,10 +744,14 @@ wake: void __mptcp_flush_join_list(struct mptcp_sock *msk) { + struct mptcp_subflow_context *subflow; + if (likely(list_empty(&msk->join_list))) return; spin_lock_bh(&msk->join_list_lock); + list_for_each_entry(subflow, &msk->join_list, node) + mptcp_propagate_sndbuf((struct sock *)msk, mptcp_subflow_tcp_sock(subflow)); list_splice_tail_init(&msk->join_list, &msk->conn_list); spin_unlock_bh(&msk->join_list_lock); } @@ -1046,13 +1051,6 @@ out: __mptcp_update_wmem(sk); sk_mem_reclaim_partial(sk); } - - if (sk_stream_is_writeable(sk)) { - /* pairs with memory barrier in mptcp_poll */ - smp_mb(); - if (test_and_clear_bit(MPTCP_NOSPACE, &msk->flags)) - sk_stream_write_space(sk); - } } if (snd_una == READ_ONCE(msk->snd_nxt)) { @@ -1371,8 +1369,7 @@ struct subflow_send_info { u64 ratio; }; -static struct sock *mptcp_subflow_get_send(struct mptcp_sock *msk, - u32 *sndbuf) +static struct sock *mptcp_subflow_get_send(struct mptcp_sock *msk) { struct subflow_send_info send_info[2]; struct mptcp_subflow_context *subflow; @@ -1383,24 +1380,17 @@ static struct sock *mptcp_subflow_get_send(struct mptcp_sock *msk, sock_owned_by_me((struct sock *)msk); - *sndbuf = 0; if (__mptcp_check_fallback(msk)) { if (!msk->first) return NULL; - *sndbuf = msk->first->sk_sndbuf; return sk_stream_memory_free(msk->first) ? msk->first : NULL; } /* re-use last subflow, if the burst allow that */ if (msk->last_snd && msk->snd_burst > 0 && sk_stream_memory_free(msk->last_snd) && - mptcp_subflow_active(mptcp_subflow_ctx(msk->last_snd))) { - mptcp_for_each_subflow(msk, subflow) { - ssk = mptcp_subflow_tcp_sock(subflow); - *sndbuf = max(tcp_sk(ssk)->snd_wnd, *sndbuf); - } + mptcp_subflow_active(mptcp_subflow_ctx(msk->last_snd))) return msk->last_snd; - } /* pick the subflow with the lower wmem/wspace ratio */ for (i = 0; i < 2; ++i) { @@ -1413,8 +1403,7 @@ static struct sock *mptcp_subflow_get_send(struct mptcp_sock *msk, continue; nr_active += !subflow->backup; - *sndbuf = max(tcp_sk(ssk)->snd_wnd, *sndbuf); - if (!sk_stream_memory_free(subflow->tcp_sock)) + if (!sk_stream_memory_free(subflow->tcp_sock) || !tcp_sk(ssk)->snd_wnd) continue; pace = READ_ONCE(ssk->sk_pacing_rate); @@ -1440,9 +1429,10 @@ static struct sock *mptcp_subflow_get_send(struct mptcp_sock *msk, if (send_info[0].ssk) { msk->last_snd = send_info[0].ssk; msk->snd_burst = min_t(int, MPTCP_SEND_BURST_SIZE, - sk_stream_wspace(msk->last_snd)); + tcp_sk(msk->last_snd)->snd_wnd); return msk->last_snd; } + return NULL; } @@ -1463,7 +1453,6 @@ static void mptcp_push_pending(struct sock *sk, unsigned int flags) }; struct mptcp_data_frag *dfrag; int len, copied = 0; - u32 sndbuf; while ((dfrag = mptcp_send_head(sk))) { info.sent = dfrag->already_sent; @@ -1474,12 +1463,7 @@ static void mptcp_push_pending(struct sock *sk, unsigned int flags) prev_ssk = ssk; __mptcp_flush_join_list(msk); - ssk = mptcp_subflow_get_send(msk, &sndbuf); - - /* do auto tuning */ - if (!(sk->sk_userlocks & SOCK_SNDBUF_LOCK) && - sndbuf > READ_ONCE(sk->sk_sndbuf)) - WRITE_ONCE(sk->sk_sndbuf, sndbuf); + ssk = mptcp_subflow_get_send(msk); /* try to keep the subflow socket lock across * consecutive xmit on the same socket @@ -1536,7 +1520,9 @@ static void __mptcp_subflow_push_pending(struct sock *sk, struct sock *ssk) struct mptcp_sock *msk = mptcp_sk(sk); struct mptcp_sendmsg_info info; struct mptcp_data_frag *dfrag; + struct sock *xmit_ssk; int len, copied = 0; + bool first = true; info.flags = 0; while ((dfrag = mptcp_send_head(sk))) { @@ -1546,10 +1532,17 @@ static void __mptcp_subflow_push_pending(struct sock *sk, struct sock *ssk) while (len > 0) { int ret = 0; - /* do auto tuning */ - if (!(sk->sk_userlocks & SOCK_SNDBUF_LOCK) && - ssk->sk_sndbuf > READ_ONCE(sk->sk_sndbuf)) - WRITE_ONCE(sk->sk_sndbuf, ssk->sk_sndbuf); + /* the caller already invoked the packet scheduler, + * check for a different subflow usage only after + * spooling the first chunk of data + */ + xmit_ssk = first ? ssk : mptcp_subflow_get_send(mptcp_sk(sk)); + if (!xmit_ssk) + goto out; + if (xmit_ssk != ssk) { + mptcp_subflow_delegate(mptcp_subflow_ctx(xmit_ssk)); + goto out; + } if (unlikely(mptcp_must_reclaim_memory(sk, ssk))) { __mptcp_update_wmem(sk); @@ -1569,6 +1562,7 @@ static void __mptcp_subflow_push_pending(struct sock *sk, struct sock *ssk) msk->tx_pending_data -= ret; copied += ret; len -= ret; + first = false; } WRITE_ONCE(msk->first_pending, mptcp_send_next(sk)); } @@ -1591,6 +1585,15 @@ out: } } +static void mptcp_set_nospace(struct sock *sk) +{ + /* enable autotune */ + set_bit(SOCK_NOSPACE, &sk->sk_socket->flags); + + /* will be cleared on avail space */ + set_bit(MPTCP_NOSPACE, &mptcp_sk(sk)->flags); +} + static int mptcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) { struct mptcp_sock *msk = mptcp_sk(sk); @@ -1692,7 +1695,7 @@ static int mptcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) continue; wait_for_memory: - set_bit(MPTCP_NOSPACE, &msk->flags); + mptcp_set_nospace(sk); mptcp_push_pending(sk, msg->msg_flags); ret = sk_stream_wait_memory(sk, &timeo); if (ret) @@ -2120,12 +2123,9 @@ static struct sock *mptcp_subflow_get_retrans(const struct mptcp_sock *msk) * so we need to use tcp_close() after detaching them from the mptcp * parent socket. */ -void __mptcp_close_ssk(struct sock *sk, struct sock *ssk, - struct mptcp_subflow_context *subflow) +static void __mptcp_close_ssk(struct sock *sk, struct sock *ssk, + struct mptcp_subflow_context *subflow) { - bool dispose_socket = false; - struct socket *sock; - list_del(&subflow->node); lock_sock_nested(ssk, SINGLE_DEPTH_NESTING); @@ -2133,11 +2133,8 @@ void __mptcp_close_ssk(struct sock *sk, struct sock *ssk, /* if we are invoked by the msk cleanup code, the subflow is * already orphaned */ - sock = ssk->sk_socket; - if (sock) { - dispose_socket = sock != sk->sk_socket; + if (ssk->sk_socket) sock_orphan(ssk); - } subflow->disposable = 1; @@ -2155,59 +2152,40 @@ void __mptcp_close_ssk(struct sock *sk, struct sock *ssk, __sock_put(ssk); } release_sock(ssk); - if (dispose_socket) - iput(SOCK_INODE(sock)); sock_put(ssk); } -static unsigned int mptcp_sync_mss(struct sock *sk, u32 pmtu) +void mptcp_close_ssk(struct sock *sk, struct sock *ssk, + struct mptcp_subflow_context *subflow) { - return 0; + if (sk->sk_state == TCP_ESTABLISHED) + mptcp_event(MPTCP_EVENT_SUB_CLOSED, mptcp_sk(sk), ssk, GFP_KERNEL); + __mptcp_close_ssk(sk, ssk, subflow); } -static void pm_work(struct mptcp_sock *msk) +static unsigned int mptcp_sync_mss(struct sock *sk, u32 pmtu) { - struct mptcp_pm_data *pm = &msk->pm; - - spin_lock_bh(&msk->pm.lock); - - pr_debug("msk=%p status=%x", msk, pm->status); - if (pm->status & BIT(MPTCP_PM_ADD_ADDR_RECEIVED)) { - pm->status &= ~BIT(MPTCP_PM_ADD_ADDR_RECEIVED); - mptcp_pm_nl_add_addr_received(msk); - } - if (pm->status & BIT(MPTCP_PM_ADD_ADDR_SEND_ACK)) { - pm->status &= ~BIT(MPTCP_PM_ADD_ADDR_SEND_ACK); - mptcp_pm_nl_add_addr_send_ack(msk); - } - if (pm->status & BIT(MPTCP_PM_RM_ADDR_RECEIVED)) { - pm->status &= ~BIT(MPTCP_PM_RM_ADDR_RECEIVED); - mptcp_pm_nl_rm_addr_received(msk); - } - if (pm->status & BIT(MPTCP_PM_ESTABLISHED)) { - pm->status &= ~BIT(MPTCP_PM_ESTABLISHED); - mptcp_pm_nl_fully_established(msk); - } - if (pm->status & BIT(MPTCP_PM_SUBFLOW_ESTABLISHED)) { - pm->status &= ~BIT(MPTCP_PM_SUBFLOW_ESTABLISHED); - mptcp_pm_nl_subflow_established(msk); - } - - spin_unlock_bh(&msk->pm.lock); + return 0; } static void __mptcp_close_subflow(struct mptcp_sock *msk) { struct mptcp_subflow_context *subflow, *tmp; + might_sleep(); + list_for_each_entry_safe(subflow, tmp, &msk->conn_list, node) { struct sock *ssk = mptcp_subflow_tcp_sock(subflow); if (inet_sk_state_load(ssk) != TCP_CLOSE) continue; - __mptcp_close_ssk((struct sock *)msk, ssk, subflow); + /* 'subflow_data_ready' will re-sched once rx queue is empty */ + if (!skb_queue_empty_lockless(&ssk->sk_receive_queue)) + continue; + + mptcp_close_ssk((struct sock *)msk, ssk, subflow); } } @@ -2279,11 +2257,8 @@ static void mptcp_worker(struct work_struct *work) mptcp_check_fastclose(msk); - if (test_and_clear_bit(MPTCP_WORK_CLOSE_SUBFLOW, &msk->flags)) - __mptcp_close_subflow(msk); - if (msk->pm.status) - pm_work(msk); + mptcp_pm_nl_work(msk); if (test_and_clear_bit(MPTCP_WORK_EOF, &msk->flags)) mptcp_check_for_eof(msk); @@ -2291,18 +2266,20 @@ static void mptcp_worker(struct work_struct *work) __mptcp_check_send_data_fin(sk); mptcp_check_data_fin(sk); - /* if the msk data is completely acked, or the socket timedout, - * there is no point in keeping around an orphaned sk + /* There is no point in keeping around an orphaned sk timedout or + * closed, but we need the msk around to reply to incoming DATA_FIN, + * even if it is orphaned and in FIN_WAIT2 state */ if (sock_flag(sk, SOCK_DEAD) && - (mptcp_check_close_timeout(sk) || - (state != sk->sk_state && - ((1 << inet_sk_state_load(sk)) & (TCPF_CLOSE | TCPF_FIN_WAIT2))))) { + (mptcp_check_close_timeout(sk) || sk->sk_state == TCP_CLOSE)) { inet_sk_state_store(sk, TCP_CLOSE); __mptcp_destroy_sock(sk); goto unlock; } + if (test_and_clear_bit(MPTCP_WORK_CLOSE_SUBFLOW, &msk->flags)) + __mptcp_close_subflow(msk); + if (!test_and_clear_bit(MPTCP_WORK_RTX, &msk->flags)) goto unlock; @@ -2544,6 +2521,14 @@ static void __mptcp_destroy_sock(struct sock *sk) pr_debug("msk=%p", msk); + might_sleep(); + + /* dispose the ancillatory tcp socket, if any */ + if (msk->subflow) { + iput(SOCK_INODE(msk->subflow)); + msk->subflow = NULL; + } + /* be sure to always acquire the join list lock, to sync vs * mptcp_finish_join(). */ @@ -2594,20 +2579,10 @@ cleanup: inet_csk(sk)->icsk_mtup.probe_timestamp = tcp_jiffies32; list_for_each_entry(subflow, &mptcp_sk(sk)->conn_list, node) { struct sock *ssk = mptcp_subflow_tcp_sock(subflow); - bool slow, dispose_socket; - struct socket *sock; + bool slow = lock_sock_fast(ssk); - slow = lock_sock_fast(ssk); - sock = ssk->sk_socket; - dispose_socket = sock && sock != sk->sk_socket; sock_orphan(ssk); unlock_sock_fast(ssk, slow); - - /* for the outgoing subflows we additionally need to free - * the associated socket - */ - if (dispose_socket) - iput(SOCK_INODE(sock)); } sock_orphan(sk); @@ -2622,6 +2597,10 @@ cleanup: release_sock(sk); if (do_cancel_work) mptcp_cancel_work(sk); + + if (mptcp_sk(sk)->token) + mptcp_event(MPTCP_EVENT_CLOSED, mptcp_sk(sk), NULL, GFP_KERNEL); + sock_put(sk); } @@ -2936,10 +2915,16 @@ void __mptcp_check_push(struct sock *sk, struct sock *ssk) if (!mptcp_send_head(sk)) return; - if (!sock_owned_by_user(sk)) - __mptcp_subflow_push_pending(sk, ssk); - else + if (!sock_owned_by_user(sk)) { + struct sock *xmit_ssk = mptcp_subflow_get_send(mptcp_sk(sk)); + + if (xmit_ssk == ssk) + __mptcp_subflow_push_pending(sk, ssk); + else if (xmit_ssk) + mptcp_subflow_delegate(mptcp_subflow_ctx(xmit_ssk)); + } else { set_bit(MPTCP_PUSH_PENDING, &mptcp_sk(sk)->flags); + } } #define MPTCP_DEFERRED_ALL (TCPF_WRITE_TIMER_DEFERRED) @@ -2989,6 +2974,20 @@ static void mptcp_release_cb(struct sock *sk) } } +void mptcp_subflow_process_delegated(struct sock *ssk) +{ + struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk); + struct sock *sk = subflow->conn; + + mptcp_data_lock(sk); + if (!sock_owned_by_user(sk)) + __mptcp_subflow_push_pending(sk, ssk); + else + set_bit(MPTCP_PUSH_PENDING, &mptcp_sk(sk)->flags); + mptcp_data_unlock(sk); + mptcp_subflow_delegated_done(subflow); +} + static int mptcp_hash(struct sock *sk) { /* should never be called, @@ -3046,12 +3045,12 @@ void mptcp_finish_connect(struct sock *ssk) WRITE_ONCE(msk->can_ack, 1); WRITE_ONCE(msk->snd_una, msk->write_seq); - mptcp_pm_new_connection(msk, 0); + mptcp_pm_new_connection(msk, ssk, 0); mptcp_rcv_space_init(msk, ssk); } -static void mptcp_sock_graft(struct sock *sk, struct socket *parent) +void mptcp_sock_graft(struct sock *sk, struct socket *parent) { write_lock_bh(&sk->sk_callback_lock); rcu_assign_pointer(sk->sk_wq, &parent->wq); @@ -3075,7 +3074,7 @@ bool mptcp_finish_join(struct sock *ssk) return false; if (!msk->pm.server_side) - return true; + goto out; if (!mptcp_pm_allow_new_subflow(msk)) return false; @@ -3102,6 +3101,8 @@ bool mptcp_finish_join(struct sock *ssk) if (parent_sock && !ssk->sk_socket) mptcp_sock_graft(ssk, parent_sock); subflow->map_seq = READ_ONCE(msk->ack_seq); +out: + mptcp_event(MPTCP_EVENT_SUB_ESTABLISHED, msk, ssk, GFP_ATOMIC); return true; } @@ -3278,9 +3279,8 @@ static int mptcp_stream_accept(struct socket *sock, struct socket *newsock, struct mptcp_sock *msk = mptcp_sk(newsock->sk); struct mptcp_subflow_context *subflow; struct sock *newsk = newsock->sk; - bool slowpath; - slowpath = lock_sock_fast(newsk); + lock_sock(newsk); /* PM/worker can now acquire the first subflow socket * lock without racing with listener queue cleanup, @@ -3290,10 +3290,11 @@ static int mptcp_stream_accept(struct socket *sock, struct socket *newsock, list_add(&subflow->node, &msk->conn_list); sock_hold(msk->first); if (mptcp_is_fully_established(newsk)) - mptcp_pm_fully_established(msk); + mptcp_pm_fully_established(msk, msk->first, GFP_KERNEL); mptcp_copy_inaddrs(newsk, msk->first); mptcp_rcv_space_init(msk, msk->first); + mptcp_propagate_sndbuf(newsk, msk->first); /* set ssk->sk_socket of accept()ed flows to mptcp socket. * This is needed so NOSPACE flag can be set from tcp stack. @@ -3305,7 +3306,7 @@ static int mptcp_stream_accept(struct socket *sock, struct socket *newsock, if (!ssk->sk_socket) mptcp_sock_graft(ssk, newsock); } - unlock_sock_fast(newsk, slowpath); + release_sock(newsk); } if (inet_csk_listen_poll(ssock->sk)) @@ -3334,7 +3335,7 @@ static __poll_t mptcp_check_writeable(struct mptcp_sock *msk) if (sk_stream_is_writeable(sk)) return EPOLLOUT | EPOLLWRNORM; - set_bit(MPTCP_NOSPACE, &msk->flags); + mptcp_set_nospace(sk); smp_mb__after_atomic(); /* msk->flags is changed by write_space cb */ if (sk_stream_is_writeable(sk)) return EPOLLOUT | EPOLLWRNORM; @@ -3375,10 +3376,34 @@ static __poll_t mptcp_poll(struct file *file, struct socket *sock, return mask; } +static int mptcp_release(struct socket *sock) +{ + struct mptcp_subflow_context *subflow; + struct sock *sk = sock->sk; + struct mptcp_sock *msk; + + if (!sk) + return 0; + + lock_sock(sk); + + msk = mptcp_sk(sk); + + mptcp_for_each_subflow(msk, subflow) { + struct sock *ssk = mptcp_subflow_tcp_sock(subflow); + + ip_mc_drop_socket(ssk); + } + + release_sock(sk); + + return inet_release(sock); +} + static const struct proto_ops mptcp_stream_ops = { .family = PF_INET, .owner = THIS_MODULE, - .release = inet_release, + .release = mptcp_release, .bind = mptcp_bind, .connect = mptcp_stream_connect, .socketpair = sock_no_socketpair, @@ -3405,13 +3430,58 @@ static struct inet_protosw mptcp_protosw = { .flags = INET_PROTOSW_ICSK, }; +static int mptcp_napi_poll(struct napi_struct *napi, int budget) +{ + struct mptcp_delegated_action *delegated; + struct mptcp_subflow_context *subflow; + int work_done = 0; + + delegated = container_of(napi, struct mptcp_delegated_action, napi); + while ((subflow = mptcp_subflow_delegated_next(delegated)) != NULL) { + struct sock *ssk = mptcp_subflow_tcp_sock(subflow); + + bh_lock_sock_nested(ssk); + if (!sock_owned_by_user(ssk) && + mptcp_subflow_has_delegated_action(subflow)) + mptcp_subflow_process_delegated(ssk); + /* ... elsewhere tcp_release_cb_override already processed + * the action or will do at next release_sock(). + * In both case must dequeue the subflow here - on the same + * CPU that scheduled it. + */ + bh_unlock_sock(ssk); + sock_put(ssk); + + if (++work_done == budget) + return budget; + } + + /* always provide a 0 'work_done' argument, so that napi_complete_done + * will not try accessing the NULL napi->dev ptr + */ + napi_complete_done(napi, 0); + return work_done; +} + void __init mptcp_proto_init(void) { + struct mptcp_delegated_action *delegated; + int cpu; + mptcp_prot.h.hashinfo = tcp_prot.h.hashinfo; if (percpu_counter_init(&mptcp_sockets_allocated, 0, GFP_KERNEL)) panic("Failed to allocate MPTCP pcpu counter\n"); + init_dummy_netdev(&mptcp_napi_dev); + for_each_possible_cpu(cpu) { + delegated = per_cpu_ptr(&mptcp_delegated_actions, cpu); + INIT_LIST_HEAD(&delegated->head); + netif_tx_napi_add(&mptcp_napi_dev, &delegated->napi, mptcp_napi_poll, + NAPI_POLL_WEIGHT); + napi_enable(&delegated->napi); + } + mptcp_subflow_init(); mptcp_pm_init(); mptcp_token_init(); @@ -3425,10 +3495,35 @@ void __init mptcp_proto_init(void) } #if IS_ENABLED(CONFIG_MPTCP_IPV6) +static int mptcp6_release(struct socket *sock) +{ + struct mptcp_subflow_context *subflow; + struct mptcp_sock *msk; + struct sock *sk = sock->sk; + + if (!sk) + return 0; + + lock_sock(sk); + + msk = mptcp_sk(sk); + + mptcp_for_each_subflow(msk, subflow) { + struct sock *ssk = mptcp_subflow_tcp_sock(subflow); + + ip_mc_drop_socket(ssk); + ipv6_sock_mc_close(ssk); + ipv6_sock_ac_close(ssk); + } + + release_sock(sk); + return inet6_release(sock); +} + static const struct proto_ops mptcp_v6_stream_ops = { .family = PF_INET6, .owner = THIS_MODULE, - .release = inet6_release, + .release = mptcp6_release, .bind = mptcp_bind, .connect = mptcp_stream_connect, .socketpair = sock_no_socketpair, diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h index 8d9f0ff10cb8..91827d949766 100644 --- a/net/mptcp/protocol.h +++ b/net/mptcp/protocol.h @@ -10,6 +10,7 @@ #include <linux/random.h> #include <net/tcp.h> #include <net/inet_connection_sock.h> +#include <uapi/linux/mptcp.h> #define MPTCP_SUPPORTED_VERSION 1 @@ -24,6 +25,7 @@ #define OPTION_MPTCP_ADD_ADDR6 BIT(7) #define OPTION_MPTCP_RM_ADDR BIT(8) #define OPTION_MPTCP_FASTCLOSE BIT(9) +#define OPTION_MPTCP_PRIO BIT(10) /* MPTCP option subtypes */ #define MPTCPOPT_MP_CAPABLE 0 @@ -59,6 +61,8 @@ #define TCPOLEN_MPTCP_ADD_ADDR6_BASE_PORT 24 #define TCPOLEN_MPTCP_PORT_LEN 4 #define TCPOLEN_MPTCP_RM_ADDR_BASE 4 +#define TCPOLEN_MPTCP_PRIO 3 +#define TCPOLEN_MPTCP_PRIO_ALIGN 4 #define TCPOLEN_MPTCP_FASTCLOSE 12 /* MPTCP MP_JOIN flags */ @@ -86,6 +90,9 @@ #define MPTCP_ADDR_IPVERSION_4 4 #define MPTCP_ADDR_IPVERSION_6 6 +/* MPTCP MP_PRIO flags */ +#define MPTCP_PRIO_BKUP BIT(0) + /* MPTCP socket flags */ #define MPTCP_DATA_READY 0 #define MPTCP_NOSPACE 1 @@ -117,6 +124,7 @@ struct mptcp_options_received { dss : 1, add_addr : 1, rm_addr : 1, + mp_prio : 1, family : 4, echo : 1, backup : 1; @@ -197,10 +205,6 @@ struct mptcp_pm_data { u8 add_addr_accepted; u8 local_addr_used; u8 subflows; - u8 add_addr_signal_max; - u8 add_addr_accept_max; - u8 local_addr_max; - u8 subflows_max; u8 status; u8 rm_id; }; @@ -285,6 +289,11 @@ struct mptcp_sock { #define mptcp_for_each_subflow(__msk, __subflow) \ list_for_each_entry(__subflow, &((__msk)->conn_list), node) +static inline void msk_owned_by_me(const struct mptcp_sock *msk) +{ + sock_owned_by_me((const struct sock *)msk); +} + static inline struct mptcp_sock *mptcp_sk(const struct sock *sk) { return (struct mptcp_sock *)sk; @@ -365,6 +374,15 @@ enum mptcp_data_avail { MPTCP_SUBFLOW_OOO_DATA }; +struct mptcp_delegated_action { + struct napi_struct napi; + struct list_head head; +}; + +DECLARE_PER_CPU(struct mptcp_delegated_action, mptcp_delegated_actions); + +#define MPTCP_DELEGATE_SEND 0 + /* MPTCP subflow context */ struct mptcp_subflow_context { struct list_head node;/* conn_list of subflows */ @@ -389,6 +407,7 @@ struct mptcp_subflow_context { map_valid : 1, mpc_map : 1, backup : 1, + send_mp_prio : 1, rx_eof : 1, can_ack : 1, /* only after processing the remote a key */ disposable : 1; /* ctx can be free at ulp release time */ @@ -401,6 +420,9 @@ struct mptcp_subflow_context { u8 local_id; u8 remote_id; + long delegated_status; + struct list_head delegated_node; /* link into delegated_action, protected by local BH */ + struct sock *tcp_sock; /* tcp sk backpointer */ struct sock *conn; /* parent mptcp_sock */ const struct inet_connection_sock_af_ops *icsk_af_ops; @@ -450,6 +472,61 @@ static inline void mptcp_add_pending_subflow(struct mptcp_sock *msk, spin_unlock_bh(&msk->join_list_lock); } +void mptcp_subflow_process_delegated(struct sock *ssk); + +static inline void mptcp_subflow_delegate(struct mptcp_subflow_context *subflow) +{ + struct mptcp_delegated_action *delegated; + bool schedule; + + /* The implied barrier pairs with mptcp_subflow_delegated_done(), and + * ensures the below list check sees list updates done prior to status + * bit changes + */ + if (!test_and_set_bit(MPTCP_DELEGATE_SEND, &subflow->delegated_status)) { + /* still on delegated list from previous scheduling */ + if (!list_empty(&subflow->delegated_node)) + return; + + /* the caller held the subflow bh socket lock */ + lockdep_assert_in_softirq(); + + delegated = this_cpu_ptr(&mptcp_delegated_actions); + schedule = list_empty(&delegated->head); + list_add_tail(&subflow->delegated_node, &delegated->head); + sock_hold(mptcp_subflow_tcp_sock(subflow)); + if (schedule) + napi_schedule(&delegated->napi); + } +} + +static inline struct mptcp_subflow_context * +mptcp_subflow_delegated_next(struct mptcp_delegated_action *delegated) +{ + struct mptcp_subflow_context *ret; + + if (list_empty(&delegated->head)) + return NULL; + + ret = list_first_entry(&delegated->head, struct mptcp_subflow_context, delegated_node); + list_del_init(&ret->delegated_node); + return ret; +} + +static inline bool mptcp_subflow_has_delegated_action(const struct mptcp_subflow_context *subflow) +{ + return test_bit(MPTCP_DELEGATE_SEND, &subflow->delegated_status); +} + +static inline void mptcp_subflow_delegated_done(struct mptcp_subflow_context *subflow) +{ + /* pairs with mptcp_subflow_delegate, ensures delegate_node is updated before + * touching the status bit + */ + smp_wmb(); + clear_bit(MPTCP_DELEGATE_SEND, &subflow->delegated_status); +} + int mptcp_is_enabled(struct net *net); unsigned int mptcp_get_add_addr_timeout(struct net *net); void mptcp_subflow_fully_established(struct mptcp_subflow_context *subflow, @@ -457,14 +534,19 @@ void mptcp_subflow_fully_established(struct mptcp_subflow_context *subflow, bool mptcp_subflow_data_available(struct sock *sk); void __init mptcp_subflow_init(void); void mptcp_subflow_shutdown(struct sock *sk, struct sock *ssk, int how); -void __mptcp_close_ssk(struct sock *sk, struct sock *ssk, - struct mptcp_subflow_context *subflow); +void mptcp_close_ssk(struct sock *sk, struct sock *ssk, + struct mptcp_subflow_context *subflow); void mptcp_subflow_reset(struct sock *ssk); +void mptcp_sock_graft(struct sock *sk, struct socket *parent); +struct socket *__mptcp_nmpc_socket(const struct mptcp_sock *msk); /* called with sk socket lock held */ int __mptcp_subflow_connect(struct sock *sk, const struct mptcp_addr_info *loc, const struct mptcp_addr_info *remote); int mptcp_subflow_create_socket(struct sock *sk, struct socket **new_sock); +void mptcp_info2sockaddr(const struct mptcp_addr_info *info, + struct sockaddr_storage *addr, + unsigned short family); static inline void mptcp_subflow_tcp_fallback(struct sock *sk, struct mptcp_subflow_context *ctx) @@ -510,6 +592,25 @@ static inline bool mptcp_data_fin_enabled(const struct mptcp_sock *msk) READ_ONCE(msk->write_seq) == READ_ONCE(msk->snd_nxt); } +static inline bool mptcp_propagate_sndbuf(struct sock *sk, struct sock *ssk) +{ + if ((sk->sk_userlocks & SOCK_SNDBUF_LOCK) || ssk->sk_sndbuf <= READ_ONCE(sk->sk_sndbuf)) + return false; + + WRITE_ONCE(sk->sk_sndbuf, ssk->sk_sndbuf); + return true; +} + +static inline void mptcp_write_space(struct sock *sk) +{ + if (sk_stream_is_writeable(sk)) { + /* pairs with memory barrier in mptcp_poll */ + smp_mb(); + if (test_and_clear_bit(MPTCP_NOSPACE, &mptcp_sk(sk)->flags)) + sk_stream_write_space(sk); + } +} + void mptcp_destroy_common(struct mptcp_sock *msk); void __init mptcp_token_init(void); @@ -535,8 +636,8 @@ void mptcp_crypto_hmac_sha(u64 key1, u64 key2, u8 *msg, int len, void *hmac); void __init mptcp_pm_init(void); void mptcp_pm_data_init(struct mptcp_sock *msk); -void mptcp_pm_new_connection(struct mptcp_sock *msk, int server_side); -void mptcp_pm_fully_established(struct mptcp_sock *msk); +void mptcp_pm_new_connection(struct mptcp_sock *msk, const struct sock *ssk, int server_side); +void mptcp_pm_fully_established(struct mptcp_sock *msk, const struct sock *ssk, gfp_t gfp); bool mptcp_pm_allow_new_subflow(struct mptcp_sock *msk); void mptcp_pm_connection_closed(struct mptcp_sock *msk); void mptcp_pm_subflow_established(struct mptcp_sock *msk, @@ -546,7 +647,12 @@ void mptcp_pm_add_addr_received(struct mptcp_sock *msk, const struct mptcp_addr_info *addr); void mptcp_pm_add_addr_send_ack(struct mptcp_sock *msk); void mptcp_pm_rm_addr_received(struct mptcp_sock *msk, u8 rm_id); +void mptcp_pm_mp_prio_received(struct sock *sk, u8 bkup); +int mptcp_pm_nl_mp_prio_send_ack(struct mptcp_sock *msk, + struct mptcp_addr_info *addr, + u8 bkup); void mptcp_pm_free_anno_list(struct mptcp_sock *msk); +bool mptcp_pm_sport_in_anno_list(struct mptcp_sock *msk, const struct sock *sk); struct mptcp_pm_add_entry * mptcp_pm_del_add_timer(struct mptcp_sock *msk, struct mptcp_addr_info *addr); @@ -557,6 +663,11 @@ int mptcp_pm_announce_addr(struct mptcp_sock *msk, int mptcp_pm_remove_addr(struct mptcp_sock *msk, u8 local_id); int mptcp_pm_remove_subflow(struct mptcp_sock *msk, u8 local_id); +void mptcp_event(enum mptcp_event_type type, const struct mptcp_sock *msk, + const struct sock *ssk, gfp_t gfp); +void mptcp_event_addr_announced(const struct mptcp_sock *msk, const struct mptcp_addr_info *info); +void mptcp_event_addr_removed(const struct mptcp_sock *msk, u8 id); + static inline bool mptcp_pm_should_add_signal(struct mptcp_sock *msk) { return READ_ONCE(msk->pm.addr_signal) & BIT(MPTCP_ADD_ADDR_SIGNAL); @@ -604,13 +715,13 @@ int mptcp_pm_get_local_id(struct mptcp_sock *msk, struct sock_common *skc); void __init mptcp_pm_nl_init(void); void mptcp_pm_nl_data_init(struct mptcp_sock *msk); -void mptcp_pm_nl_fully_established(struct mptcp_sock *msk); -void mptcp_pm_nl_subflow_established(struct mptcp_sock *msk); -void mptcp_pm_nl_add_addr_received(struct mptcp_sock *msk); -void mptcp_pm_nl_add_addr_send_ack(struct mptcp_sock *msk); -void mptcp_pm_nl_rm_addr_received(struct mptcp_sock *msk); +void mptcp_pm_nl_work(struct mptcp_sock *msk); void mptcp_pm_nl_rm_subflow_received(struct mptcp_sock *msk, u8 rm_id); int mptcp_pm_nl_get_local_id(struct mptcp_sock *msk, struct sock_common *skc); +unsigned int mptcp_pm_get_add_addr_signal_max(struct mptcp_sock *msk); +unsigned int mptcp_pm_get_add_addr_accept_max(struct mptcp_sock *msk); +unsigned int mptcp_pm_get_subflows_max(struct mptcp_sock *msk); +unsigned int mptcp_pm_get_local_addr_max(struct mptcp_sock *msk); static inline struct mptcp_ext *mptcp_get_ext(struct sk_buff *skb) { diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c index 8b2338dfdc80..e1fbcab257e6 100644 --- a/net/mptcp/subflow.c +++ b/net/mptcp/subflow.c @@ -18,12 +18,15 @@ #include <net/tcp.h> #if IS_ENABLED(CONFIG_MPTCP_IPV6) #include <net/ip6_route.h> +#include <net/transp_v6.h> #endif #include <net/mptcp.h> #include <uapi/linux/mptcp.h> #include "protocol.h" #include "mib.h" +static void mptcp_subflow_ops_undo_override(struct sock *ssk); + static void SUBFLOW_REQ_INC_STATS(struct request_sock *req, enum linux_mptcp_mib_field field) { @@ -61,11 +64,23 @@ static bool mptcp_can_accept_new_subflow(const struct mptcp_sock *msk) } /* validate received token and create truncated hmac and nonce for SYN-ACK */ -static struct mptcp_sock *subflow_token_join_request(struct request_sock *req, - const struct sk_buff *skb) +static void subflow_req_create_thmac(struct mptcp_subflow_request_sock *subflow_req) { - struct mptcp_subflow_request_sock *subflow_req = mptcp_subflow_rsk(req); + struct mptcp_sock *msk = subflow_req->msk; u8 hmac[SHA256_DIGEST_SIZE]; + + get_random_bytes(&subflow_req->local_nonce, sizeof(u32)); + + subflow_generate_hmac(msk->local_key, msk->remote_key, + subflow_req->local_nonce, + subflow_req->remote_nonce, hmac); + + subflow_req->thmac = get_unaligned_be64(hmac); +} + +static struct mptcp_sock *subflow_token_join_request(struct request_sock *req) +{ + struct mptcp_subflow_request_sock *subflow_req = mptcp_subflow_rsk(req); struct mptcp_sock *msk; int local_id; @@ -82,13 +97,6 @@ static struct mptcp_sock *subflow_token_join_request(struct request_sock *req, } subflow_req->local_id = local_id; - get_random_bytes(&subflow_req->local_nonce, sizeof(u32)); - - subflow_generate_hmac(msk->local_key, msk->remote_key, - subflow_req->local_nonce, - subflow_req->remote_nonce, hmac); - - subflow_req->thmac = get_unaligned_be64(hmac); return msk; } @@ -102,6 +110,11 @@ static void subflow_init_req(struct request_sock *req, const struct sock *sk_lis mptcp_token_init_request(req); } +static bool subflow_use_different_sport(struct mptcp_sock *msk, const struct sock *sk) +{ + return inet_sk(sk)->inet_sport != inet_sk((struct sock *)msk)->inet_sport; +} + /* Init mptcp request socket. * * Returns an error code if a JOIN has failed and a TCP reset @@ -171,12 +184,30 @@ again: subflow_req->remote_id = mp_opt.join_id; subflow_req->token = mp_opt.token; subflow_req->remote_nonce = mp_opt.nonce; - subflow_req->msk = subflow_token_join_request(req, skb); + subflow_req->msk = subflow_token_join_request(req); /* Can't fall back to TCP in this case. */ if (!subflow_req->msk) return -EPERM; + if (subflow_use_different_sport(subflow_req->msk, sk_listener)) { + pr_debug("syn inet_sport=%d %d", + ntohs(inet_sk(sk_listener)->inet_sport), + ntohs(inet_sk((struct sock *)subflow_req->msk)->inet_sport)); + if (!mptcp_pm_sport_in_anno_list(subflow_req->msk, sk_listener)) { + sock_put((struct sock *)subflow_req->msk); + mptcp_token_destroy_request(req); + tcp_request_sock_ops.destructor(req); + subflow_req->msk = NULL; + subflow_req->mp_join = 0; + SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_MISMATCHPORTSYNRX); + return -EPERM; + } + SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_JOINPORTSYNRX); + } + + subflow_req_create_thmac(subflow_req); + if (unlikely(req->syncookie)) { if (mptcp_can_accept_new_subflow(subflow_req->msk)) subflow_init_req_cookie_join_save(subflow_req, skb); @@ -318,6 +349,11 @@ void mptcp_subflow_reset(struct sock *ssk) sock_put(sk); } +static bool subflow_use_different_dport(struct mptcp_sock *msk, const struct sock *sk) +{ + return inet_sk(sk)->inet_dport != inet_sk((struct sock *)msk)->inet_dport; +} + static void subflow_finish_connect(struct sock *sk, const struct sk_buff *skb) { struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk); @@ -335,6 +371,7 @@ static void subflow_finish_connect(struct sock *sk, const struct sk_buff *skb) if (subflow->conn_finished) return; + mptcp_propagate_sndbuf(parent, sk); subflow->rel_write_seq = 1; subflow->conn_finished = 1; subflow->ssn_offset = TCP_SKB_CB(skb)->seq; @@ -383,6 +420,13 @@ static void subflow_finish_connect(struct sock *sk, const struct sk_buff *skb) subflow->mp_join = 1; MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_JOINSYNACKRX); + + if (subflow_use_different_dport(mptcp_sk(parent), sk)) { + pr_debug("synack inet_dport=%d %d", + ntohs(inet_sk(sk)->inet_dport), + ntohs(inet_sk(parent)->inet_dport)); + MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_JOINPORTSYNACKRX); + } } else if (mptcp_check_fallback(sk)) { fallback: mptcp_rcv_space_init(mptcp_sk(parent), sk); @@ -419,6 +463,7 @@ drop: static struct tcp_request_sock_ops subflow_request_sock_ipv6_ops; static struct inet_connection_sock_af_ops subflow_v6_specific; static struct inet_connection_sock_af_ops subflow_v6m_specific; +static struct proto tcpv6_prot_override; static int subflow_v6_conn_request(struct sock *sk, struct sk_buff *skb) { @@ -500,6 +545,8 @@ static void subflow_ulp_fallback(struct sock *sk, icsk->icsk_ulp_ops = NULL; rcu_assign_pointer(icsk->icsk_ulp_data, NULL); tcp_sk(sk)->is_mptcp = 0; + + mptcp_subflow_ops_undo_override(sk); } static void subflow_drop_ctx(struct sock *ssk) @@ -620,7 +667,7 @@ create_child: * created mptcp socket */ new_msk->sk_destruct = mptcp_sock_destruct; - mptcp_pm_new_connection(mptcp_sk(new_msk), 1); + mptcp_pm_new_connection(mptcp_sk(new_msk), child, 1); mptcp_token_accept(subflow_req, mptcp_sk(new_msk)); ctx->conn = new_msk; new_msk = NULL; @@ -645,6 +692,17 @@ create_child: SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_JOINACKRX); tcp_rsk(req)->drop_req = true; + + if (subflow_use_different_sport(owner, sk)) { + pr_debug("ack inet_sport=%d %d", + ntohs(inet_sk(sk)->inet_sport), + ntohs(inet_sk((struct sock *)owner)->inet_sport)); + if (!mptcp_pm_sport_in_anno_list(owner, sk)) { + SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_MISMATCHPORTACKRX); + goto out; + } + SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_JOINPORTACKRX); + } } } @@ -673,6 +731,7 @@ dispose_child: } static struct inet_connection_sock_af_ops subflow_specific; +static struct proto tcp_prot_override; enum mapping_status { MAPPING_OK, @@ -886,6 +945,22 @@ static void mptcp_subflow_discard_data(struct sock *ssk, struct sk_buff *skb, subflow->map_valid = 0; } +/* sched mptcp worker to remove the subflow if no more data is pending */ +static void subflow_sched_work_if_closed(struct mptcp_sock *msk, struct sock *ssk) +{ + struct sock *sk = (struct sock *)msk; + + if (likely(ssk->sk_state != TCP_CLOSE)) + return; + + if (skb_queue_empty(&ssk->sk_receive_queue) && + !test_and_set_bit(MPTCP_WORK_CLOSE_SUBFLOW, &msk->flags)) { + sock_hold(sk); + if (!schedule_work(&msk->work)) + sock_put(sk); + } +} + static bool subflow_check_data_avail(struct sock *ssk) { struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk); @@ -924,11 +999,11 @@ static bool subflow_check_data_avail(struct sock *ssk) } if (status != MAPPING_OK) - return false; + goto no_data; skb = skb_peek(&ssk->sk_receive_queue); if (WARN_ON_ONCE(!skb)) - return false; + goto no_data; /* if msk lacks the remote key, this subflow must provide an * MP_CAPABLE-based mapping @@ -962,6 +1037,9 @@ static bool subflow_check_data_avail(struct sock *ssk) } return true; +no_data: + subflow_sched_work_if_closed(msk, ssk); + return false; fatal: /* fatal protocol error, close the socket */ /* This barrier is coupled with smp_rmb() in tcp_poll() */ @@ -1018,6 +1096,12 @@ static void subflow_data_ready(struct sock *sk) msk = mptcp_sk(parent); if (state & TCPF_LISTEN) { + /* MPJ subflow are removed from accept queue before reaching here, + * avoid stray wakeups + */ + if (reqsk_queue_empty(&inet_csk(sk)->icsk_accept_queue)) + return; + set_bit(MPTCP_DATA_READY, &msk->flags); parent->sk_data_ready(parent); return; @@ -1032,7 +1116,10 @@ static void subflow_data_ready(struct sock *sk) static void subflow_write_space(struct sock *ssk) { - /* we take action in __mptcp_clean_una() */ + struct sock *sk = mptcp_subflow_ctx(ssk)->conn; + + mptcp_propagate_sndbuf(sk, ssk); + mptcp_write_space(sk); } void __mptcp_error_report(struct sock *sk) @@ -1105,22 +1192,32 @@ void mptcpv6_handle_mapped(struct sock *sk, bool mapped) } #endif -static void mptcp_info2sockaddr(const struct mptcp_addr_info *info, - struct sockaddr_storage *addr) +void mptcp_info2sockaddr(const struct mptcp_addr_info *info, + struct sockaddr_storage *addr, + unsigned short family) { memset(addr, 0, sizeof(*addr)); - addr->ss_family = info->family; + addr->ss_family = family; if (addr->ss_family == AF_INET) { struct sockaddr_in *in_addr = (struct sockaddr_in *)addr; - in_addr->sin_addr = info->addr; + if (info->family == AF_INET) + in_addr->sin_addr = info->addr; +#if IS_ENABLED(CONFIG_MPTCP_IPV6) + else if (ipv6_addr_v4mapped(&info->addr6)) + in_addr->sin_addr.s_addr = info->addr6.s6_addr32[3]; +#endif in_addr->sin_port = info->port; } #if IS_ENABLED(CONFIG_MPTCP_IPV6) else if (addr->ss_family == AF_INET6) { struct sockaddr_in6 *in6_addr = (struct sockaddr_in6 *)addr; - in6_addr->sin6_addr = info->addr6; + if (info->family == AF_INET) + ipv6_addr_set_v4mapped(info->addr.s_addr, + &in6_addr->sin6_addr); + else + in6_addr->sin6_addr = info->addr6; in6_addr->sin6_port = info->port; } #endif @@ -1164,11 +1261,11 @@ int __mptcp_subflow_connect(struct sock *sk, const struct mptcp_addr_info *loc, subflow->remote_key = msk->remote_key; subflow->local_key = msk->local_key; subflow->token = msk->token; - mptcp_info2sockaddr(loc, &addr); + mptcp_info2sockaddr(loc, &addr, ssk->sk_family); addrlen = sizeof(struct sockaddr_in); #if IS_ENABLED(CONFIG_MPTCP_IPV6) - if (loc->family == AF_INET6) + if (addr.ss_family == AF_INET6) addrlen = sizeof(struct sockaddr_in6); #endif ssk->sk_bound_dev_if = loc->ifindex; @@ -1184,13 +1281,16 @@ int __mptcp_subflow_connect(struct sock *sk, const struct mptcp_addr_info *loc, subflow->remote_id = remote_id; subflow->request_join = 1; subflow->request_bkup = !!(loc->flags & MPTCP_PM_ADDR_FLAG_BACKUP); - mptcp_info2sockaddr(remote, &addr); + mptcp_info2sockaddr(remote, &addr, ssk->sk_family); mptcp_add_pending_subflow(msk, subflow); err = kernel_connect(sf, (struct sockaddr *)&addr, addrlen, O_NONBLOCK); if (err && err != -EINPROGRESS) goto failed_unlink; + /* discard the subflow socket */ + mptcp_sock_graft(ssk, sk->sk_socket); + iput(SOCK_INODE(sf)); return err; failed_unlink: @@ -1228,6 +1328,25 @@ static void mptcp_attach_cgroup(struct sock *parent, struct sock *child) #endif /* CONFIG_SOCK_CGROUP_DATA */ } +static void mptcp_subflow_ops_override(struct sock *ssk) +{ +#if IS_ENABLED(CONFIG_MPTCP_IPV6) + if (ssk->sk_prot == &tcpv6_prot) + ssk->sk_prot = &tcpv6_prot_override; + else +#endif + ssk->sk_prot = &tcp_prot_override; +} + +static void mptcp_subflow_ops_undo_override(struct sock *ssk) +{ +#if IS_ENABLED(CONFIG_MPTCP_IPV6) + if (ssk->sk_prot == &tcpv6_prot_override) + ssk->sk_prot = &tcpv6_prot; + else +#endif + ssk->sk_prot = &tcp_prot; +} int mptcp_subflow_create_socket(struct sock *sk, struct socket **new_sock) { struct mptcp_subflow_context *subflow; @@ -1283,6 +1402,7 @@ int mptcp_subflow_create_socket(struct sock *sk, struct socket **new_sock) *new_sock = sf; sock_hold(sk); subflow->conn = sk; + mptcp_subflow_ops_override(sf->sk); return 0; } @@ -1299,6 +1419,7 @@ static struct mptcp_subflow_context *subflow_create_ctx(struct sock *sk, rcu_assign_pointer(icsk->icsk_ulp_data, ctx); INIT_LIST_HEAD(&ctx->node); + INIT_LIST_HEAD(&ctx->delegated_node); pr_debug("subflow=%p", ctx); @@ -1331,6 +1452,7 @@ static void subflow_state_change(struct sock *sk) __subflow_state_change(sk); if (subflow_simultaneous_connect(sk)) { + mptcp_propagate_sndbuf(parent, sk); mptcp_do_fallback(sk); mptcp_rcv_space_init(mptcp_sk(parent), sk); pr_fallback(mptcp_sk(parent)); @@ -1348,6 +1470,8 @@ static void subflow_state_change(struct sock *sk) if (mptcp_subflow_data_available(sk)) mptcp_data_ready(parent, sk); + subflow_sched_work_if_closed(mptcp_sk(parent), sk); + if (__mptcp_check_fallback(mptcp_sk(parent)) && !subflow->rx_eof && subflow_is_done(sk)) { subflow->rx_eof = 1; @@ -1412,6 +1536,7 @@ static void subflow_ulp_release(struct sock *ssk) sock_put(sk); } + mptcp_subflow_ops_undo_override(ssk); if (release) kfree_rcu(ctx, rcu); } @@ -1466,6 +1591,16 @@ static void subflow_ulp_clone(const struct request_sock *req, } } +static void tcp_release_cb_override(struct sock *ssk) +{ + struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk); + + if (mptcp_subflow_has_delegated_action(subflow)) + mptcp_subflow_process_delegated(ssk); + + tcp_release_cb(ssk); +} + static struct tcp_ulp_ops subflow_ulp_ops __read_mostly = { .name = "mptcp", .owner = THIS_MODULE, @@ -1506,6 +1641,9 @@ void __init mptcp_subflow_init(void) subflow_specific.syn_recv_sock = subflow_syn_recv_sock; subflow_specific.sk_rx_dst_set = subflow_finish_connect; + tcp_prot_override = tcp_prot; + tcp_prot_override.release_cb = tcp_release_cb_override; + #if IS_ENABLED(CONFIG_MPTCP_IPV6) subflow_request_sock_ipv6_ops = tcp_request_sock_ipv6_ops; subflow_request_sock_ipv6_ops.route_req = subflow_v6_route_req; @@ -1521,6 +1659,9 @@ void __init mptcp_subflow_init(void) subflow_v6m_specific.net_header_len = ipv4_specific.net_header_len; subflow_v6m_specific.mtu_reduced = ipv4_specific.mtu_reduced; subflow_v6m_specific.net_frag_header_len = 0; + + tcpv6_prot_override = tcpv6_prot; + tcpv6_prot_override.release_cb = tcp_release_cb_override; #endif mptcp_diag_subflow_init(&subflow_ulp_ops); diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig index 49fbef0d99be..1a92063c73a4 100644 --- a/net/netfilter/Kconfig +++ b/net/netfilter/Kconfig @@ -1,6 +1,6 @@ # SPDX-License-Identifier: GPL-2.0-only menu "Core Netfilter Configuration" - depends on NET && INET && NETFILTER + depends on INET && NETFILTER config NETFILTER_INGRESS bool "Netfilter ingress support" diff --git a/net/netfilter/ipvs/Kconfig b/net/netfilter/ipvs/Kconfig index eb0e329f9b8d..d61886874940 100644 --- a/net/netfilter/ipvs/Kconfig +++ b/net/netfilter/ipvs/Kconfig @@ -4,7 +4,7 @@ # menuconfig IP_VS tristate "IP virtual server support" - depends on NET && INET && NETFILTER + depends on INET && NETFILTER depends on (NF_CONNTRACK || NF_CONNTRACK=n) help IP Virtual Server support will let you build a high-performance @@ -271,6 +271,17 @@ config IP_VS_NQ If you want to compile it in kernel, say Y. To compile it as a module, choose M here. If unsure, say N. +config IP_VS_TWOS + tristate "weighted random twos choice least-connection scheduling" + help + The weighted random twos choice least-connection scheduling + algorithm picks two random real servers and directs network + connections to the server with the least active connections + normalized by the server weight. + + If you want to compile it in kernel, say Y. To compile it as a + module, choose M here. If unsure, say N. + comment 'IPVS SH scheduler' config IP_VS_SH_TAB_BITS diff --git a/net/netfilter/ipvs/Makefile b/net/netfilter/ipvs/Makefile index bfce2677fda2..bb5d8125c82a 100644 --- a/net/netfilter/ipvs/Makefile +++ b/net/netfilter/ipvs/Makefile @@ -36,6 +36,7 @@ obj-$(CONFIG_IP_VS_SH) += ip_vs_sh.o obj-$(CONFIG_IP_VS_MH) += ip_vs_mh.o obj-$(CONFIG_IP_VS_SED) += ip_vs_sed.o obj-$(CONFIG_IP_VS_NQ) += ip_vs_nq.o +obj-$(CONFIG_IP_VS_TWOS) += ip_vs_twos.o # IPVS application helpers obj-$(CONFIG_IP_VS_FTP) += ip_vs_ftp.o diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c index 54e086c65721..0c132ff9b446 100644 --- a/net/netfilter/ipvs/ip_vs_core.c +++ b/net/netfilter/ipvs/ip_vs_core.c @@ -68,18 +68,6 @@ EXPORT_SYMBOL(ip_vs_get_debug_level); #endif EXPORT_SYMBOL(ip_vs_new_conn_out); -#ifdef CONFIG_IP_VS_PROTO_TCP -INDIRECT_CALLABLE_DECLARE(int - tcp_snat_handler(struct sk_buff *skb, struct ip_vs_protocol *pp, - struct ip_vs_conn *cp, struct ip_vs_iphdr *iph)); -#endif - -#ifdef CONFIG_IP_VS_PROTO_UDP -INDIRECT_CALLABLE_DECLARE(int - udp_snat_handler(struct sk_buff *skb, struct ip_vs_protocol *pp, - struct ip_vs_conn *cp, struct ip_vs_iphdr *iph)); -#endif - #if defined(CONFIG_IP_VS_PROTO_TCP) && defined(CONFIG_IP_VS_PROTO_UDP) #define SNAT_CALL(f, ...) \ INDIRECT_CALL_2(f, tcp_snat_handler, udp_snat_handler, __VA_ARGS__) diff --git a/net/netfilter/ipvs/ip_vs_twos.c b/net/netfilter/ipvs/ip_vs_twos.c new file mode 100644 index 000000000000..acb55d8393ef --- /dev/null +++ b/net/netfilter/ipvs/ip_vs_twos.c @@ -0,0 +1,139 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* IPVS: Power of Twos Choice Scheduling module + * + * Authors: Darby Payne <darby.payne@applovin.com> + */ + +#define KMSG_COMPONENT "IPVS" +#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt + +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/random.h> + +#include <net/ip_vs.h> + +/* Power of Twos Choice scheduling, algorithm originally described by + * Michael Mitzenmacher. + * + * Randomly picks two destinations and picks the one with the least + * amount of connections + * + * The algorithm calculates a few variables + * - total_weight = sum of all weights + * - rweight1 = random number between [0,total_weight] + * - rweight2 = random number between [0,total_weight] + * + * For each destination + * decrement rweight1 and rweight2 by the destination weight + * pick choice1 when rweight1 is <= 0 + * pick choice2 when rweight2 is <= 0 + * + * Return choice2 if choice2 has less connections than choice 1 normalized + * by weight + * + * References + * ---------- + * + * [Mitzenmacher 2016] + * The Power of Two Random Choices: A Survey of Techniques and Results + * Michael Mitzenmacher, Andrea W. Richa y, Ramesh Sitaraman + * http://www.eecs.harvard.edu/~michaelm/NEWWORK/postscripts/twosurvey.pdf + * + */ +static struct ip_vs_dest *ip_vs_twos_schedule(struct ip_vs_service *svc, + const struct sk_buff *skb, + struct ip_vs_iphdr *iph) +{ + struct ip_vs_dest *dest, *choice1 = NULL, *choice2 = NULL; + int rweight1, rweight2, weight1 = -1, weight2 = -1, overhead1 = 0; + int overhead2, total_weight = 0, weight; + + IP_VS_DBG(6, "%s(): Scheduling...\n", __func__); + + /* Generate a random weight between [0,sum of all weights) */ + list_for_each_entry_rcu(dest, &svc->destinations, n_list) { + if (!(dest->flags & IP_VS_DEST_F_OVERLOAD)) { + weight = atomic_read(&dest->weight); + if (weight > 0) { + total_weight += weight; + choice1 = dest; + } + } + } + + if (!choice1) { + ip_vs_scheduler_err(svc, "no destination available"); + return NULL; + } + + /* Add 1 to total_weight so that the random weights are inclusive + * from 0 to total_weight + */ + total_weight += 1; + rweight1 = prandom_u32() % total_weight; + rweight2 = prandom_u32() % total_weight; + + /* Pick two weighted servers */ + list_for_each_entry_rcu(dest, &svc->destinations, n_list) { + if (dest->flags & IP_VS_DEST_F_OVERLOAD) + continue; + + weight = atomic_read(&dest->weight); + if (weight <= 0) + continue; + + rweight1 -= weight; + rweight2 -= weight; + + if (rweight1 <= 0 && weight1 == -1) { + choice1 = dest; + weight1 = weight; + overhead1 = ip_vs_dest_conn_overhead(dest); + } + + if (rweight2 <= 0 && weight2 == -1) { + choice2 = dest; + weight2 = weight; + overhead2 = ip_vs_dest_conn_overhead(dest); + } + + if (weight1 != -1 && weight2 != -1) + goto nextstage; + } + +nextstage: + if (choice2 && (weight2 * overhead1) > (weight1 * overhead2)) + choice1 = choice2; + + IP_VS_DBG_BUF(6, "twos: server %s:%u conns %d refcnt %d weight %d\n", + IP_VS_DBG_ADDR(choice1->af, &choice1->addr), + ntohs(choice1->port), atomic_read(&choice1->activeconns), + refcount_read(&choice1->refcnt), + atomic_read(&choice1->weight)); + + return choice1; +} + +static struct ip_vs_scheduler ip_vs_twos_scheduler = { + .name = "twos", + .refcnt = ATOMIC_INIT(0), + .module = THIS_MODULE, + .n_list = LIST_HEAD_INIT(ip_vs_twos_scheduler.n_list), + .schedule = ip_vs_twos_schedule, +}; + +static int __init ip_vs_twos_init(void) +{ + return register_ip_vs_scheduler(&ip_vs_twos_scheduler); +} + +static void __exit ip_vs_twos_cleanup(void) +{ + unregister_ip_vs_scheduler(&ip_vs_twos_scheduler); + synchronize_rcu(); +} + +module_init(ip_vs_twos_init); +module_exit(ip_vs_twos_cleanup); +MODULE_LICENSE("GPL"); diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c index 84caf3316946..1469365bac7e 100644 --- a/net/netfilter/nf_conntrack_netlink.c +++ b/net/netfilter/nf_conntrack_netlink.c @@ -2686,12 +2686,6 @@ ctnetlink_glue_build_size(const struct nf_conn *ct) ; } -static struct nf_conn *ctnetlink_glue_get_ct(const struct sk_buff *skb, - enum ip_conntrack_info *ctinfo) -{ - return nf_ct_get(skb, ctinfo); -} - static int __ctnetlink_glue_build(struct sk_buff *skb, struct nf_conn *ct) { const struct nf_conntrack_zone *zone; @@ -2925,7 +2919,6 @@ static void ctnetlink_glue_seqadj(struct sk_buff *skb, struct nf_conn *ct, } static struct nfnl_ct_hook ctnetlink_glue_hook = { - .get_ct = ctnetlink_glue_get_ct, .build_size = ctnetlink_glue_build_size, .build = ctnetlink_glue_build, .parse = ctnetlink_glue_parse, diff --git a/net/netfilter/nf_flow_table_core.c b/net/netfilter/nf_flow_table_core.c index 4a4acbba78ff..5fa657b8e03d 100644 --- a/net/netfilter/nf_flow_table_core.c +++ b/net/netfilter/nf_flow_table_core.c @@ -191,14 +191,14 @@ static u32 flow_offload_hash(const void *data, u32 len, u32 seed) { const struct flow_offload_tuple *tuple = data; - return jhash(tuple, offsetof(struct flow_offload_tuple, dir), seed); + return jhash(tuple, offsetof(struct flow_offload_tuple, __hash), seed); } static u32 flow_offload_hash_obj(const void *data, u32 len, u32 seed) { const struct flow_offload_tuple_rhash *tuplehash = data; - return jhash(&tuplehash->tuple, offsetof(struct flow_offload_tuple, dir), seed); + return jhash(&tuplehash->tuple, offsetof(struct flow_offload_tuple, __hash), seed); } static int flow_offload_hash_cmp(struct rhashtable_compare_arg *arg, @@ -207,7 +207,7 @@ static int flow_offload_hash_cmp(struct rhashtable_compare_arg *arg, const struct flow_offload_tuple *tuple = arg->key; const struct flow_offload_tuple_rhash *x = ptr; - if (memcmp(&x->tuple, tuple, offsetof(struct flow_offload_tuple, dir))) + if (memcmp(&x->tuple, tuple, offsetof(struct flow_offload_tuple, __hash))) return 1; return 0; diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 8ee9f40cc0ea..c1eb5cdb3033 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -508,7 +508,7 @@ static int nft_delflowtable(struct nft_ctx *ctx, static struct nft_table *nft_table_lookup(const struct net *net, const struct nlattr *nla, - u8 family, u8 genmask) + u8 family, u8 genmask, u32 nlpid) { struct nft_table *table; @@ -519,8 +519,13 @@ static struct nft_table *nft_table_lookup(const struct net *net, lockdep_is_held(&net->nft.commit_mutex)) { if (!nla_strcmp(nla, table->name) && table->family == family && - nft_active_genmask(table, genmask)) + nft_active_genmask(table, genmask)) { + if (nft_table_has_owner(table) && + table->nlpid != nlpid) + return ERR_PTR(-EPERM); + return table; + } } return ERR_PTR(-ENOENT); @@ -679,6 +684,9 @@ static int nf_tables_fill_table_info(struct sk_buff *skb, struct net *net, nla_put_be64(skb, NFTA_TABLE_HANDLE, cpu_to_be64(table->handle), NFTA_TABLE_PAD)) goto nla_put_failure; + if (nft_table_has_owner(table) && + nla_put_be32(skb, NFTA_TABLE_OWNER, htonl(table->nlpid))) + goto nla_put_failure; if (table->udata) { if (nla_put(skb, NFTA_TABLE_USERDATA, table->udlen, table->udata)) @@ -821,7 +829,7 @@ static int nf_tables_gettable(struct net *net, struct sock *nlsk, return nft_netlink_dump_start_rcu(nlsk, skb, nlh, &c); } - table = nft_table_lookup(net, nla[NFTA_TABLE_NAME], family, genmask); + table = nft_table_lookup(net, nla[NFTA_TABLE_NAME], family, genmask, 0); if (IS_ERR(table)) { NL_SET_BAD_ATTR(extack, nla[NFTA_TABLE_NAME]); return PTR_ERR(table); @@ -902,8 +910,8 @@ static int nf_tables_updtable(struct nft_ctx *ctx) return 0; flags = ntohl(nla_get_be32(ctx->nla[NFTA_TABLE_FLAGS])); - if (flags & ~NFT_TABLE_F_DORMANT) - return -EINVAL; + if (flags & ~NFT_TABLE_F_MASK) + return -EOPNOTSUPP; if (flags == ctx->table->flags) return 0; @@ -1003,7 +1011,8 @@ static int nf_tables_newtable(struct net *net, struct sock *nlsk, lockdep_assert_held(&net->nft.commit_mutex); attr = nla[NFTA_TABLE_NAME]; - table = nft_table_lookup(net, attr, family, genmask); + table = nft_table_lookup(net, attr, family, genmask, + NETLINK_CB(skb).portid); if (IS_ERR(table)) { if (PTR_ERR(table) != -ENOENT) return PTR_ERR(table); @@ -1021,8 +1030,8 @@ static int nf_tables_newtable(struct net *net, struct sock *nlsk, if (nla[NFTA_TABLE_FLAGS]) { flags = ntohl(nla_get_be32(nla[NFTA_TABLE_FLAGS])); - if (flags & ~NFT_TABLE_F_DORMANT) - return -EINVAL; + if (flags & ~NFT_TABLE_F_MASK) + return -EOPNOTSUPP; } err = -ENOMEM; @@ -1053,6 +1062,8 @@ static int nf_tables_newtable(struct net *net, struct sock *nlsk, table->family = family; table->flags = flags; table->handle = ++table_handle; + if (table->flags & NFT_TABLE_F_OWNER) + table->nlpid = NETLINK_CB(skb).portid; nft_ctx_init(&ctx, net, skb, nlh, family, table, NULL, nla); err = nft_trans_table_add(&ctx, NFT_MSG_NEWTABLE); @@ -1160,6 +1171,9 @@ static int nft_flush(struct nft_ctx *ctx, int family) if (!nft_is_active_next(ctx->net, table)) continue; + if (nft_table_has_owner(table) && table->nlpid != ctx->portid) + continue; + if (nla[NFTA_TABLE_NAME] && nla_strcmp(nla[NFTA_TABLE_NAME], table->name) != 0) continue; @@ -1196,7 +1210,8 @@ static int nf_tables_deltable(struct net *net, struct sock *nlsk, table = nft_table_lookup_byhandle(net, attr, genmask); } else { attr = nla[NFTA_TABLE_NAME]; - table = nft_table_lookup(net, attr, family, genmask); + table = nft_table_lookup(net, attr, family, genmask, + NETLINK_CB(skb).portid); } if (IS_ERR(table)) { @@ -1579,7 +1594,7 @@ static int nf_tables_getchain(struct net *net, struct sock *nlsk, return nft_netlink_dump_start_rcu(nlsk, skb, nlh, &c); } - table = nft_table_lookup(net, nla[NFTA_CHAIN_TABLE], family, genmask); + table = nft_table_lookup(net, nla[NFTA_CHAIN_TABLE], family, genmask, 0); if (IS_ERR(table)) { NL_SET_BAD_ATTR(extack, nla[NFTA_CHAIN_TABLE]); return PTR_ERR(table); @@ -2299,7 +2314,8 @@ static int nf_tables_newchain(struct net *net, struct sock *nlsk, lockdep_assert_held(&net->nft.commit_mutex); - table = nft_table_lookup(net, nla[NFTA_CHAIN_TABLE], family, genmask); + table = nft_table_lookup(net, nla[NFTA_CHAIN_TABLE], family, genmask, + NETLINK_CB(skb).portid); if (IS_ERR(table)) { NL_SET_BAD_ATTR(extack, nla[NFTA_CHAIN_TABLE]); return PTR_ERR(table); @@ -2395,7 +2411,8 @@ static int nf_tables_delchain(struct net *net, struct sock *nlsk, u32 use; int err; - table = nft_table_lookup(net, nla[NFTA_CHAIN_TABLE], family, genmask); + table = nft_table_lookup(net, nla[NFTA_CHAIN_TABLE], family, genmask, + NETLINK_CB(skb).portid); if (IS_ERR(table)) { NL_SET_BAD_ATTR(extack, nla[NFTA_CHAIN_TABLE]); return PTR_ERR(table); @@ -3041,7 +3058,7 @@ static int nf_tables_getrule(struct net *net, struct sock *nlsk, return nft_netlink_dump_start_rcu(nlsk, skb, nlh, &c); } - table = nft_table_lookup(net, nla[NFTA_RULE_TABLE], family, genmask); + table = nft_table_lookup(net, nla[NFTA_RULE_TABLE], family, genmask, 0); if (IS_ERR(table)) { NL_SET_BAD_ATTR(extack, nla[NFTA_RULE_TABLE]); return PTR_ERR(table); @@ -3179,7 +3196,8 @@ static int nf_tables_newrule(struct net *net, struct sock *nlsk, lockdep_assert_held(&net->nft.commit_mutex); - table = nft_table_lookup(net, nla[NFTA_RULE_TABLE], family, genmask); + table = nft_table_lookup(net, nla[NFTA_RULE_TABLE], family, genmask, + NETLINK_CB(skb).portid); if (IS_ERR(table)) { NL_SET_BAD_ATTR(extack, nla[NFTA_RULE_TABLE]); return PTR_ERR(table); @@ -3403,7 +3421,8 @@ static int nf_tables_delrule(struct net *net, struct sock *nlsk, int family = nfmsg->nfgen_family, err = 0; struct nft_ctx ctx; - table = nft_table_lookup(net, nla[NFTA_RULE_TABLE], family, genmask); + table = nft_table_lookup(net, nla[NFTA_RULE_TABLE], family, genmask, + NETLINK_CB(skb).portid); if (IS_ERR(table)) { NL_SET_BAD_ATTR(extack, nla[NFTA_RULE_TABLE]); return PTR_ERR(table); @@ -3584,7 +3603,7 @@ static int nft_ctx_init_from_setattr(struct nft_ctx *ctx, struct net *net, const struct nlmsghdr *nlh, const struct nlattr * const nla[], struct netlink_ext_ack *extack, - u8 genmask) + u8 genmask, u32 nlpid) { const struct nfgenmsg *nfmsg = nlmsg_data(nlh); int family = nfmsg->nfgen_family; @@ -3592,7 +3611,7 @@ static int nft_ctx_init_from_setattr(struct nft_ctx *ctx, struct net *net, if (nla[NFTA_SET_TABLE] != NULL) { table = nft_table_lookup(net, nla[NFTA_SET_TABLE], family, - genmask); + genmask, nlpid); if (IS_ERR(table)) { NL_SET_BAD_ATTR(extack, nla[NFTA_SET_TABLE]); return PTR_ERR(table); @@ -4007,7 +4026,7 @@ static int nf_tables_getset(struct net *net, struct sock *nlsk, /* Verify existence before starting dump */ err = nft_ctx_init_from_setattr(&ctx, net, skb, nlh, nla, extack, - genmask); + genmask, 0); if (err < 0) return err; @@ -4236,7 +4255,8 @@ static int nf_tables_newset(struct net *net, struct sock *nlsk, if (nla[NFTA_SET_EXPR] || nla[NFTA_SET_EXPRESSIONS]) desc.expr = true; - table = nft_table_lookup(net, nla[NFTA_SET_TABLE], family, genmask); + table = nft_table_lookup(net, nla[NFTA_SET_TABLE], family, genmask, + NETLINK_CB(skb).portid); if (IS_ERR(table)) { NL_SET_BAD_ATTR(extack, nla[NFTA_SET_TABLE]); return PTR_ERR(table); @@ -4413,7 +4433,7 @@ static int nf_tables_delset(struct net *net, struct sock *nlsk, return -EINVAL; err = nft_ctx_init_from_setattr(&ctx, net, skb, nlh, nla, extack, - genmask); + genmask, NETLINK_CB(skb).portid); if (err < 0) return err; @@ -4438,6 +4458,12 @@ static int nf_tables_delset(struct net *net, struct sock *nlsk, return nft_delset(&ctx, set); } +static int nft_validate_register_store(const struct nft_ctx *ctx, + enum nft_registers reg, + const struct nft_data *data, + enum nft_data_types type, + unsigned int len); + static int nf_tables_bind_check_setelem(const struct nft_ctx *ctx, struct nft_set *set, const struct nft_set_iter *iter, @@ -4602,14 +4628,14 @@ static int nft_ctx_init_from_elemattr(struct nft_ctx *ctx, struct net *net, const struct nlmsghdr *nlh, const struct nlattr * const nla[], struct netlink_ext_ack *extack, - u8 genmask) + u8 genmask, u32 nlpid) { const struct nfgenmsg *nfmsg = nlmsg_data(nlh); int family = nfmsg->nfgen_family; struct nft_table *table; table = nft_table_lookup(net, nla[NFTA_SET_ELEM_LIST_TABLE], family, - genmask); + genmask, nlpid); if (IS_ERR(table)) { NL_SET_BAD_ATTR(extack, nla[NFTA_SET_ELEM_LIST_TABLE]); return PTR_ERR(table); @@ -5026,7 +5052,7 @@ static int nf_tables_getsetelem(struct net *net, struct sock *nlsk, int rem, err = 0; err = nft_ctx_init_from_elemattr(&ctx, net, skb, nlh, nla, extack, - genmask); + genmask, NETLINK_CB(skb).portid); if (err < 0) return err; @@ -5607,7 +5633,7 @@ static int nf_tables_newsetelem(struct net *net, struct sock *nlsk, return -EINVAL; err = nft_ctx_init_from_elemattr(&ctx, net, skb, nlh, nla, extack, - genmask); + genmask, NETLINK_CB(skb).portid); if (err < 0) return err; @@ -5815,7 +5841,7 @@ static int nf_tables_delsetelem(struct net *net, struct sock *nlsk, int rem, err = 0; err = nft_ctx_init_from_elemattr(&ctx, net, skb, nlh, nla, extack, - genmask); + genmask, NETLINK_CB(skb).portid); if (err < 0) return err; @@ -6118,7 +6144,8 @@ static int nf_tables_newobj(struct net *net, struct sock *nlsk, !nla[NFTA_OBJ_DATA]) return -EINVAL; - table = nft_table_lookup(net, nla[NFTA_OBJ_TABLE], family, genmask); + table = nft_table_lookup(net, nla[NFTA_OBJ_TABLE], family, genmask, + NETLINK_CB(skb).portid); if (IS_ERR(table)) { NL_SET_BAD_ATTR(extack, nla[NFTA_OBJ_TABLE]); return PTR_ERR(table); @@ -6388,7 +6415,7 @@ static int nf_tables_getobj(struct net *net, struct sock *nlsk, !nla[NFTA_OBJ_TYPE]) return -EINVAL; - table = nft_table_lookup(net, nla[NFTA_OBJ_TABLE], family, genmask); + table = nft_table_lookup(net, nla[NFTA_OBJ_TABLE], family, genmask, 0); if (IS_ERR(table)) { NL_SET_BAD_ATTR(extack, nla[NFTA_OBJ_TABLE]); return PTR_ERR(table); @@ -6462,7 +6489,8 @@ static int nf_tables_delobj(struct net *net, struct sock *nlsk, (!nla[NFTA_OBJ_NAME] && !nla[NFTA_OBJ_HANDLE])) return -EINVAL; - table = nft_table_lookup(net, nla[NFTA_OBJ_TABLE], family, genmask); + table = nft_table_lookup(net, nla[NFTA_OBJ_TABLE], family, genmask, + NETLINK_CB(skb).portid); if (IS_ERR(table)) { NL_SET_BAD_ATTR(extack, nla[NFTA_OBJ_TABLE]); return PTR_ERR(table); @@ -6879,7 +6907,7 @@ static int nf_tables_newflowtable(struct net *net, struct sock *nlsk, return -EINVAL; table = nft_table_lookup(net, nla[NFTA_FLOWTABLE_TABLE], family, - genmask); + genmask, NETLINK_CB(skb).portid); if (IS_ERR(table)) { NL_SET_BAD_ATTR(extack, nla[NFTA_FLOWTABLE_TABLE]); return PTR_ERR(table); @@ -7063,7 +7091,7 @@ static int nf_tables_delflowtable(struct net *net, struct sock *nlsk, return -EINVAL; table = nft_table_lookup(net, nla[NFTA_FLOWTABLE_TABLE], family, - genmask); + genmask, NETLINK_CB(skb).portid); if (IS_ERR(table)) { NL_SET_BAD_ATTR(extack, nla[NFTA_FLOWTABLE_TABLE]); return PTR_ERR(table); @@ -7271,7 +7299,7 @@ static int nf_tables_getflowtable(struct net *net, struct sock *nlsk, return -EINVAL; table = nft_table_lookup(net, nla[NFTA_FLOWTABLE_TABLE], family, - genmask); + genmask, 0); if (IS_ERR(table)) return PTR_ERR(table); @@ -8590,7 +8618,7 @@ EXPORT_SYMBOL_GPL(nft_parse_u32_check); * Registers used to be 128 bit wide, these register numbers will be * mapped to the corresponding 32 bit register numbers. */ -unsigned int nft_parse_register(const struct nlattr *attr) +static unsigned int nft_parse_register(const struct nlattr *attr) { unsigned int reg; @@ -8602,7 +8630,6 @@ unsigned int nft_parse_register(const struct nlattr *attr) return reg + NFT_REG_SIZE / NFT_REG32_SIZE - NFT_REG32_00; } } -EXPORT_SYMBOL_GPL(nft_parse_register); /** * nft_dump_register - dump a register value to a netlink attribute @@ -8635,7 +8662,7 @@ EXPORT_SYMBOL_GPL(nft_dump_register); * Validate that the input register is one of the general purpose * registers and that the length of the load is within the bounds. */ -int nft_validate_register_load(enum nft_registers reg, unsigned int len) +static int nft_validate_register_load(enum nft_registers reg, unsigned int len) { if (reg < NFT_REG_1 * NFT_REG_SIZE / NFT_REG32_SIZE) return -EINVAL; @@ -8646,7 +8673,21 @@ int nft_validate_register_load(enum nft_registers reg, unsigned int len) return 0; } -EXPORT_SYMBOL_GPL(nft_validate_register_load); + +int nft_parse_register_load(const struct nlattr *attr, u8 *sreg, u32 len) +{ + u32 reg; + int err; + + reg = nft_parse_register(attr); + err = nft_validate_register_load(reg, len); + if (err < 0) + return err; + + *sreg = reg; + return 0; +} +EXPORT_SYMBOL_GPL(nft_parse_register_load); /** * nft_validate_register_store - validate an expressions' register store @@ -8662,10 +8703,11 @@ EXPORT_SYMBOL_GPL(nft_validate_register_load); * A value of NULL for the data means that its runtime gathered * data. */ -int nft_validate_register_store(const struct nft_ctx *ctx, - enum nft_registers reg, - const struct nft_data *data, - enum nft_data_types type, unsigned int len) +static int nft_validate_register_store(const struct nft_ctx *ctx, + enum nft_registers reg, + const struct nft_data *data, + enum nft_data_types type, + unsigned int len) { int err; @@ -8697,7 +8739,24 @@ int nft_validate_register_store(const struct nft_ctx *ctx, return 0; } } -EXPORT_SYMBOL_GPL(nft_validate_register_store); + +int nft_parse_register_store(const struct nft_ctx *ctx, + const struct nlattr *attr, u8 *dreg, + const struct nft_data *data, + enum nft_data_types type, unsigned int len) +{ + int err; + u32 reg; + + reg = nft_parse_register(attr); + err = nft_validate_register_store(ctx, reg, data, type, len); + if (err < 0) + return err; + + *dreg = reg; + return 0; +} +EXPORT_SYMBOL_GPL(nft_parse_register_store); static const struct nla_policy nft_verdict_policy[NFTA_VERDICT_MAX + 1] = { [NFTA_VERDICT_CODE] = { .type = NLA_U32 }, @@ -8951,21 +9010,25 @@ int __nft_release_basechain(struct nft_ctx *ctx) } EXPORT_SYMBOL_GPL(__nft_release_basechain); +static void __nft_release_hook(struct net *net, struct nft_table *table) +{ + struct nft_chain *chain; + + list_for_each_entry(chain, &table->chains, list) + nf_tables_unregister_hook(net, table, chain); +} + static void __nft_release_hooks(struct net *net) { struct nft_table *table; - struct nft_chain *chain; - list_for_each_entry(table, &net->nft.tables, list) { - list_for_each_entry(chain, &table->chains, list) - nf_tables_unregister_hook(net, table, chain); - } + list_for_each_entry(table, &net->nft.tables, list) + __nft_release_hook(net, table); } -static void __nft_release_tables(struct net *net) +static void __nft_release_table(struct net *net, struct nft_table *table) { struct nft_flowtable *flowtable, *nf; - struct nft_table *table, *nt; struct nft_chain *chain, *nc; struct nft_object *obj, *ne; struct nft_rule *rule, *nr; @@ -8975,43 +9038,90 @@ static void __nft_release_tables(struct net *net) .family = NFPROTO_NETDEV, }; - list_for_each_entry_safe(table, nt, &net->nft.tables, list) { - ctx.family = table->family; - ctx.table = table; - list_for_each_entry(chain, &table->chains, list) { - ctx.chain = chain; - list_for_each_entry_safe(rule, nr, &chain->rules, list) { - list_del(&rule->list); - chain->use--; - nf_tables_rule_release(&ctx, rule); - } - } - list_for_each_entry_safe(flowtable, nf, &table->flowtables, list) { - list_del(&flowtable->list); - table->use--; - nf_tables_flowtable_destroy(flowtable); - } - list_for_each_entry_safe(set, ns, &table->sets, list) { - list_del(&set->list); - table->use--; - nft_set_destroy(&ctx, set); + ctx.family = table->family; + ctx.table = table; + list_for_each_entry(chain, &table->chains, list) { + ctx.chain = chain; + list_for_each_entry_safe(rule, nr, &chain->rules, list) { + list_del(&rule->list); + chain->use--; + nf_tables_rule_release(&ctx, rule); } - list_for_each_entry_safe(obj, ne, &table->objects, list) { - nft_obj_del(obj); - table->use--; - nft_obj_destroy(&ctx, obj); + } + list_for_each_entry_safe(flowtable, nf, &table->flowtables, list) { + list_del(&flowtable->list); + table->use--; + nf_tables_flowtable_destroy(flowtable); + } + list_for_each_entry_safe(set, ns, &table->sets, list) { + list_del(&set->list); + table->use--; + nft_set_destroy(&ctx, set); + } + list_for_each_entry_safe(obj, ne, &table->objects, list) { + nft_obj_del(obj); + table->use--; + nft_obj_destroy(&ctx, obj); + } + list_for_each_entry_safe(chain, nc, &table->chains, list) { + ctx.chain = chain; + nft_chain_del(chain); + table->use--; + nf_tables_chain_destroy(&ctx); + } + list_del(&table->list); + nf_tables_table_destroy(&ctx); +} + +static void __nft_release_tables(struct net *net, u32 nlpid) +{ + struct nft_table *table, *nt; + + list_for_each_entry_safe(table, nt, &net->nft.tables, list) { + if (nft_table_has_owner(table) && + nlpid != table->nlpid) + continue; + + __nft_release_table(net, table); + } +} + +static int nft_rcv_nl_event(struct notifier_block *this, unsigned long event, + void *ptr) +{ + struct netlink_notify *n = ptr; + struct nft_table *table, *nt; + struct net *net = n->net; + bool release = false; + + if (event != NETLINK_URELEASE || n->protocol != NETLINK_NETFILTER) + return NOTIFY_DONE; + + mutex_lock(&net->nft.commit_mutex); + list_for_each_entry(table, &net->nft.tables, list) { + if (nft_table_has_owner(table) && + n->portid == table->nlpid) { + __nft_release_hook(net, table); + release = true; } - list_for_each_entry_safe(chain, nc, &table->chains, list) { - ctx.chain = chain; - nft_chain_del(chain); - table->use--; - nf_tables_chain_destroy(&ctx); + } + if (release) { + synchronize_rcu(); + list_for_each_entry_safe(table, nt, &net->nft.tables, list) { + if (nft_table_has_owner(table) && + n->portid == table->nlpid) + __nft_release_table(net, table); } - list_del(&table->list); - nf_tables_table_destroy(&ctx); } + mutex_unlock(&net->nft.commit_mutex); + + return NOTIFY_DONE; } +static struct notifier_block nft_nl_notifier = { + .notifier_call = nft_rcv_nl_event, +}; + static int __net_init nf_tables_init_net(struct net *net) { INIT_LIST_HEAD(&net->nft.tables); @@ -9035,7 +9145,7 @@ static void __net_exit nf_tables_exit_net(struct net *net) mutex_lock(&net->nft.commit_mutex); if (!list_empty(&net->nft.commit_list)) __nf_tables_abort(net, NFNL_ABORT_NONE); - __nft_release_tables(net); + __nft_release_tables(net, 0); mutex_unlock(&net->nft.commit_mutex); WARN_ON_ONCE(!list_empty(&net->nft.tables)); WARN_ON_ONCE(!list_empty(&net->nft.module_list)); @@ -9059,43 +9169,50 @@ static int __init nf_tables_module_init(void) err = nft_chain_filter_init(); if (err < 0) - goto err1; + goto err_chain_filter; err = nf_tables_core_module_init(); if (err < 0) - goto err2; + goto err_core_module; err = register_netdevice_notifier(&nf_tables_flowtable_notifier); if (err < 0) - goto err3; + goto err_netdev_notifier; err = rhltable_init(&nft_objname_ht, &nft_objname_ht_params); if (err < 0) - goto err4; + goto err_rht_objname; err = nft_offload_init(); if (err < 0) - goto err5; + goto err_offload; + + err = netlink_register_notifier(&nft_nl_notifier); + if (err < 0) + goto err_netlink_notifier; /* must be last */ err = nfnetlink_subsys_register(&nf_tables_subsys); if (err < 0) - goto err6; + goto err_nfnl_subsys; nft_chain_route_init(); return err; -err6: + +err_nfnl_subsys: + netlink_unregister_notifier(&nft_nl_notifier); +err_netlink_notifier: nft_offload_exit(); -err5: +err_offload: rhltable_destroy(&nft_objname_ht); -err4: +err_rht_objname: unregister_netdevice_notifier(&nf_tables_flowtable_notifier); -err3: +err_netdev_notifier: nf_tables_core_module_exit(); -err2: +err_core_module: nft_chain_filter_fini(); -err1: +err_chain_filter: unregister_pernet_subsys(&nf_tables_net_ops); return err; } @@ -9103,6 +9220,7 @@ err1: static void __exit nf_tables_module_exit(void) { nfnetlink_subsys_unregister(&nf_tables_subsys); + netlink_unregister_notifier(&nft_nl_notifier); nft_offload_exit(); unregister_netdevice_notifier(&nf_tables_flowtable_notifier); nft_chain_filter_fini(); diff --git a/net/netfilter/nfnetlink_log.c b/net/netfilter/nfnetlink_log.c index b35e8d9a5b37..26776b88a539 100644 --- a/net/netfilter/nfnetlink_log.c +++ b/net/netfilter/nfnetlink_log.c @@ -43,6 +43,10 @@ #include "../bridge/br_private.h" #endif +#if IS_ENABLED(CONFIG_NF_CONNTRACK) +#include <net/netfilter/nf_conntrack.h> +#endif + #define NFULNL_COPY_DISABLED 0xff #define NFULNL_NLBUFSIZ_DEFAULT NLMSG_GOODSIZE #define NFULNL_TIMEOUT_DEFAULT 100 /* every second */ @@ -733,14 +737,16 @@ nfulnl_log_packet(struct net *net, size += nla_total_size(sizeof(u_int32_t)); if (inst->flags & NFULNL_CFG_F_SEQ_GLOBAL) size += nla_total_size(sizeof(u_int32_t)); +#if IS_ENABLED(CONFIG_NF_CONNTRACK) if (inst->flags & NFULNL_CFG_F_CONNTRACK) { nfnl_ct = rcu_dereference(nfnl_ct_hook); if (nfnl_ct != NULL) { - ct = nfnl_ct->get_ct(skb, &ctinfo); + ct = nf_ct_get(skb, &ctinfo); if (ct != NULL) size += nfnl_ct->build_size(ct); } } +#endif if (pf == NFPROTO_NETDEV || pf == NFPROTO_BRIDGE) size += nfulnl_get_bridge_size(skb); diff --git a/net/netfilter/nfnetlink_queue.c b/net/netfilter/nfnetlink_queue.c index d1d8bca03b4f..48a07914fd94 100644 --- a/net/netfilter/nfnetlink_queue.c +++ b/net/netfilter/nfnetlink_queue.c @@ -444,13 +444,15 @@ nfqnl_build_packet_message(struct net *net, struct nfqnl_instance *queue, nfnl_ct = rcu_dereference(nfnl_ct_hook); +#if IS_ENABLED(CONFIG_NF_CONNTRACK) if (queue->flags & NFQA_CFG_F_CONNTRACK) { if (nfnl_ct != NULL) { - ct = nfnl_ct->get_ct(entskb, &ctinfo); + ct = nf_ct_get(entskb, &ctinfo); if (ct != NULL) size += nfnl_ct->build_size(ct); } } +#endif if (queue->flags & NFQA_CFG_F_UID_GID) { size += (nla_total_size(sizeof(u_int32_t)) /* uid */ @@ -1104,9 +1106,10 @@ static struct nf_conn *nfqnl_ct_parse(struct nfnl_ct_hook *nfnl_ct, struct nf_queue_entry *entry, enum ip_conntrack_info *ctinfo) { +#if IS_ENABLED(CONFIG_NF_CONNTRACK) struct nf_conn *ct; - ct = nfnl_ct->get_ct(entry->skb, ctinfo); + ct = nf_ct_get(entry->skb, ctinfo); if (ct == NULL) return NULL; @@ -1118,6 +1121,9 @@ static struct nf_conn *nfqnl_ct_parse(struct nfnl_ct_hook *nfnl_ct, NETLINK_CB(entry->skb).portid, nlmsg_report(nlh)); return ct; +#else + return NULL; +#endif } static int nfqa_parse_bridge(struct nf_queue_entry *entry, diff --git a/net/netfilter/nft_bitwise.c b/net/netfilter/nft_bitwise.c index bbd773d74377..47b0dba95054 100644 --- a/net/netfilter/nft_bitwise.c +++ b/net/netfilter/nft_bitwise.c @@ -16,8 +16,8 @@ #include <net/netfilter/nf_tables_offload.h> struct nft_bitwise { - enum nft_registers sreg:8; - enum nft_registers dreg:8; + u8 sreg; + u8 dreg; enum nft_bitwise_ops op:8; u8 len; struct nft_data mask; @@ -169,14 +169,14 @@ static int nft_bitwise_init(const struct nft_ctx *ctx, priv->len = len; - priv->sreg = nft_parse_register(tb[NFTA_BITWISE_SREG]); - err = nft_validate_register_load(priv->sreg, priv->len); + err = nft_parse_register_load(tb[NFTA_BITWISE_SREG], &priv->sreg, + priv->len); if (err < 0) return err; - priv->dreg = nft_parse_register(tb[NFTA_BITWISE_DREG]); - err = nft_validate_register_store(ctx, priv->dreg, NULL, - NFT_DATA_VALUE, priv->len); + err = nft_parse_register_store(ctx, tb[NFTA_BITWISE_DREG], + &priv->dreg, NULL, NFT_DATA_VALUE, + priv->len); if (err < 0) return err; @@ -315,14 +315,13 @@ static int nft_bitwise_fast_init(const struct nft_ctx *ctx, struct nft_bitwise_fast_expr *priv = nft_expr_priv(expr); int err; - priv->sreg = nft_parse_register(tb[NFTA_BITWISE_SREG]); - err = nft_validate_register_load(priv->sreg, sizeof(u32)); + err = nft_parse_register_load(tb[NFTA_BITWISE_SREG], &priv->sreg, + sizeof(u32)); if (err < 0) return err; - priv->dreg = nft_parse_register(tb[NFTA_BITWISE_DREG]); - err = nft_validate_register_store(ctx, priv->dreg, NULL, - NFT_DATA_VALUE, sizeof(u32)); + err = nft_parse_register_store(ctx, tb[NFTA_BITWISE_DREG], &priv->dreg, + NULL, NFT_DATA_VALUE, sizeof(u32)); if (err < 0) return err; diff --git a/net/netfilter/nft_byteorder.c b/net/netfilter/nft_byteorder.c index 12bed3f7bbc6..9d5947ab8d4e 100644 --- a/net/netfilter/nft_byteorder.c +++ b/net/netfilter/nft_byteorder.c @@ -16,8 +16,8 @@ #include <net/netfilter/nf_tables.h> struct nft_byteorder { - enum nft_registers sreg:8; - enum nft_registers dreg:8; + u8 sreg; + u8 dreg; enum nft_byteorder_ops op:8; u8 len; u8 size; @@ -131,20 +131,20 @@ static int nft_byteorder_init(const struct nft_ctx *ctx, return -EINVAL; } - priv->sreg = nft_parse_register(tb[NFTA_BYTEORDER_SREG]); err = nft_parse_u32_check(tb[NFTA_BYTEORDER_LEN], U8_MAX, &len); if (err < 0) return err; priv->len = len; - err = nft_validate_register_load(priv->sreg, priv->len); + err = nft_parse_register_load(tb[NFTA_BYTEORDER_SREG], &priv->sreg, + priv->len); if (err < 0) return err; - priv->dreg = nft_parse_register(tb[NFTA_BYTEORDER_DREG]); - return nft_validate_register_store(ctx, priv->dreg, NULL, - NFT_DATA_VALUE, priv->len); + return nft_parse_register_store(ctx, tb[NFTA_BYTEORDER_DREG], + &priv->dreg, NULL, NFT_DATA_VALUE, + priv->len); } static int nft_byteorder_dump(struct sk_buff *skb, const struct nft_expr *expr) diff --git a/net/netfilter/nft_cmp.c b/net/netfilter/nft_cmp.c index 00e563a72d3d..eb6a43a180bb 100644 --- a/net/netfilter/nft_cmp.c +++ b/net/netfilter/nft_cmp.c @@ -18,7 +18,7 @@ struct nft_cmp_expr { struct nft_data data; - enum nft_registers sreg:8; + u8 sreg; u8 len; enum nft_cmp_ops op:8; }; @@ -87,8 +87,7 @@ static int nft_cmp_init(const struct nft_ctx *ctx, const struct nft_expr *expr, return err; } - priv->sreg = nft_parse_register(tb[NFTA_CMP_SREG]); - err = nft_validate_register_load(priv->sreg, desc.len); + err = nft_parse_register_load(tb[NFTA_CMP_SREG], &priv->sreg, desc.len); if (err < 0) return err; @@ -174,8 +173,7 @@ static int nft_cmp_fast_init(const struct nft_ctx *ctx, if (err < 0) return err; - priv->sreg = nft_parse_register(tb[NFTA_CMP_SREG]); - err = nft_validate_register_load(priv->sreg, desc.len); + err = nft_parse_register_load(tb[NFTA_CMP_SREG], &priv->sreg, desc.len); if (err < 0) return err; @@ -268,10 +266,8 @@ nft_cmp_select_ops(const struct nft_ctx *ctx, const struct nlattr * const tb[]) if (err < 0) return ERR_PTR(err); - if (desc.type != NFT_DATA_VALUE) { - err = -EINVAL; + if (desc.type != NFT_DATA_VALUE) goto err1; - } if (desc.len <= sizeof(u32) && (op == NFT_CMP_EQ || op == NFT_CMP_NEQ)) return &nft_cmp_fast_ops; diff --git a/net/netfilter/nft_ct.c b/net/netfilter/nft_ct.c index 8bcd49f14797..882fe8648653 100644 --- a/net/netfilter/nft_ct.c +++ b/net/netfilter/nft_ct.c @@ -27,8 +27,8 @@ struct nft_ct { enum nft_ct_keys key:8; enum ip_conntrack_dir dir:8; union { - enum nft_registers dreg:8; - enum nft_registers sreg:8; + u8 dreg; + u8 sreg; }; }; @@ -498,9 +498,8 @@ static int nft_ct_get_init(const struct nft_ctx *ctx, } } - priv->dreg = nft_parse_register(tb[NFTA_CT_DREG]); - err = nft_validate_register_store(ctx, priv->dreg, NULL, - NFT_DATA_VALUE, len); + err = nft_parse_register_store(ctx, tb[NFTA_CT_DREG], &priv->dreg, NULL, + NFT_DATA_VALUE, len); if (err < 0) return err; @@ -600,8 +599,7 @@ static int nft_ct_set_init(const struct nft_ctx *ctx, } } - priv->sreg = nft_parse_register(tb[NFTA_CT_SREG]); - err = nft_validate_register_load(priv->sreg, len); + err = nft_parse_register_load(tb[NFTA_CT_SREG], &priv->sreg, len); if (err < 0) goto err1; diff --git a/net/netfilter/nft_dup_netdev.c b/net/netfilter/nft_dup_netdev.c index 40788b3f1071..bbf3fcba3df4 100644 --- a/net/netfilter/nft_dup_netdev.c +++ b/net/netfilter/nft_dup_netdev.c @@ -14,7 +14,7 @@ #include <net/netfilter/nf_dup_netdev.h> struct nft_dup_netdev { - enum nft_registers sreg_dev:8; + u8 sreg_dev; }; static void nft_dup_netdev_eval(const struct nft_expr *expr, @@ -40,8 +40,8 @@ static int nft_dup_netdev_init(const struct nft_ctx *ctx, if (tb[NFTA_DUP_SREG_DEV] == NULL) return -EINVAL; - priv->sreg_dev = nft_parse_register(tb[NFTA_DUP_SREG_DEV]); - return nft_validate_register_load(priv->sreg_dev, sizeof(int)); + return nft_parse_register_load(tb[NFTA_DUP_SREG_DEV], &priv->sreg_dev, + sizeof(int)); } static int nft_dup_netdev_dump(struct sk_buff *skb, const struct nft_expr *expr) diff --git a/net/netfilter/nft_dynset.c b/net/netfilter/nft_dynset.c index d164ef9e6843..d44a70c11b3f 100644 --- a/net/netfilter/nft_dynset.c +++ b/net/netfilter/nft_dynset.c @@ -16,8 +16,8 @@ struct nft_dynset { struct nft_set *set; struct nft_set_ext_tmpl tmpl; enum nft_dynset_ops op:8; - enum nft_registers sreg_key:8; - enum nft_registers sreg_data:8; + u8 sreg_key; + u8 sreg_data; bool invert; bool expr; u8 num_exprs; @@ -219,8 +219,8 @@ static int nft_dynset_init(const struct nft_ctx *ctx, return err; } - priv->sreg_key = nft_parse_register(tb[NFTA_DYNSET_SREG_KEY]); - err = nft_validate_register_load(priv->sreg_key, set->klen); + err = nft_parse_register_load(tb[NFTA_DYNSET_SREG_KEY], &priv->sreg_key, + set->klen); if (err < 0) return err; @@ -230,8 +230,8 @@ static int nft_dynset_init(const struct nft_ctx *ctx, if (set->dtype == NFT_DATA_VERDICT) return -EOPNOTSUPP; - priv->sreg_data = nft_parse_register(tb[NFTA_DYNSET_SREG_DATA]); - err = nft_validate_register_load(priv->sreg_data, set->dlen); + err = nft_parse_register_load(tb[NFTA_DYNSET_SREG_DATA], + &priv->sreg_data, set->dlen); if (err < 0) return err; } else if (set->flags & NFT_SET_MAP) diff --git a/net/netfilter/nft_exthdr.c b/net/netfilter/nft_exthdr.c index 3c48cdc8935d..f64f0017e9a5 100644 --- a/net/netfilter/nft_exthdr.c +++ b/net/netfilter/nft_exthdr.c @@ -19,8 +19,8 @@ struct nft_exthdr { u8 offset; u8 len; u8 op; - enum nft_registers dreg:8; - enum nft_registers sreg:8; + u8 dreg; + u8 sreg; u8 flags; }; @@ -350,12 +350,12 @@ static int nft_exthdr_init(const struct nft_ctx *ctx, priv->type = nla_get_u8(tb[NFTA_EXTHDR_TYPE]); priv->offset = offset; priv->len = len; - priv->dreg = nft_parse_register(tb[NFTA_EXTHDR_DREG]); priv->flags = flags; priv->op = op; - return nft_validate_register_store(ctx, priv->dreg, NULL, - NFT_DATA_VALUE, priv->len); + return nft_parse_register_store(ctx, tb[NFTA_EXTHDR_DREG], + &priv->dreg, NULL, NFT_DATA_VALUE, + priv->len); } static int nft_exthdr_tcp_set_init(const struct nft_ctx *ctx, @@ -400,11 +400,11 @@ static int nft_exthdr_tcp_set_init(const struct nft_ctx *ctx, priv->type = nla_get_u8(tb[NFTA_EXTHDR_TYPE]); priv->offset = offset; priv->len = len; - priv->sreg = nft_parse_register(tb[NFTA_EXTHDR_SREG]); priv->flags = flags; priv->op = op; - return nft_validate_register_load(priv->sreg, priv->len); + return nft_parse_register_load(tb[NFTA_EXTHDR_SREG], &priv->sreg, + priv->len); } static int nft_exthdr_ipv4_init(const struct nft_ctx *ctx, diff --git a/net/netfilter/nft_fib.c b/net/netfilter/nft_fib.c index 4dfdaeaf09a5..b10ce732b337 100644 --- a/net/netfilter/nft_fib.c +++ b/net/netfilter/nft_fib.c @@ -86,7 +86,6 @@ int nft_fib_init(const struct nft_ctx *ctx, const struct nft_expr *expr, return -EINVAL; priv->result = ntohl(nla_get_be32(tb[NFTA_FIB_RESULT])); - priv->dreg = nft_parse_register(tb[NFTA_FIB_DREG]); switch (priv->result) { case NFT_FIB_RESULT_OIF: @@ -106,8 +105,8 @@ int nft_fib_init(const struct nft_ctx *ctx, const struct nft_expr *expr, return -EINVAL; } - err = nft_validate_register_store(ctx, priv->dreg, NULL, - NFT_DATA_VALUE, len); + err = nft_parse_register_store(ctx, tb[NFTA_FIB_DREG], &priv->dreg, + NULL, NFT_DATA_VALUE, len); if (err < 0) return err; diff --git a/net/netfilter/nft_fwd_netdev.c b/net/netfilter/nft_fwd_netdev.c index b77985986b24..cd59afde5b2f 100644 --- a/net/netfilter/nft_fwd_netdev.c +++ b/net/netfilter/nft_fwd_netdev.c @@ -18,7 +18,7 @@ #include <net/ip.h> struct nft_fwd_netdev { - enum nft_registers sreg_dev:8; + u8 sreg_dev; }; static void nft_fwd_netdev_eval(const struct nft_expr *expr, @@ -50,8 +50,8 @@ static int nft_fwd_netdev_init(const struct nft_ctx *ctx, if (tb[NFTA_FWD_SREG_DEV] == NULL) return -EINVAL; - priv->sreg_dev = nft_parse_register(tb[NFTA_FWD_SREG_DEV]); - return nft_validate_register_load(priv->sreg_dev, sizeof(int)); + return nft_parse_register_load(tb[NFTA_FWD_SREG_DEV], &priv->sreg_dev, + sizeof(int)); } static int nft_fwd_netdev_dump(struct sk_buff *skb, const struct nft_expr *expr) @@ -78,8 +78,8 @@ static int nft_fwd_netdev_offload(struct nft_offload_ctx *ctx, } struct nft_fwd_neigh { - enum nft_registers sreg_dev:8; - enum nft_registers sreg_addr:8; + u8 sreg_dev; + u8 sreg_addr; u8 nfproto; }; @@ -157,8 +157,6 @@ static int nft_fwd_neigh_init(const struct nft_ctx *ctx, !tb[NFTA_FWD_NFPROTO]) return -EINVAL; - priv->sreg_dev = nft_parse_register(tb[NFTA_FWD_SREG_DEV]); - priv->sreg_addr = nft_parse_register(tb[NFTA_FWD_SREG_ADDR]); priv->nfproto = ntohl(nla_get_be32(tb[NFTA_FWD_NFPROTO])); switch (priv->nfproto) { @@ -172,11 +170,13 @@ static int nft_fwd_neigh_init(const struct nft_ctx *ctx, return -EOPNOTSUPP; } - err = nft_validate_register_load(priv->sreg_dev, sizeof(int)); + err = nft_parse_register_load(tb[NFTA_FWD_SREG_DEV], &priv->sreg_dev, + sizeof(int)); if (err < 0) return err; - return nft_validate_register_load(priv->sreg_addr, addr_len); + return nft_parse_register_load(tb[NFTA_FWD_SREG_ADDR], &priv->sreg_addr, + addr_len); } static int nft_fwd_neigh_dump(struct sk_buff *skb, const struct nft_expr *expr) diff --git a/net/netfilter/nft_hash.c b/net/netfilter/nft_hash.c index 96371d878e7e..f829f5289e16 100644 --- a/net/netfilter/nft_hash.c +++ b/net/netfilter/nft_hash.c @@ -14,8 +14,8 @@ #include <linux/jhash.h> struct nft_jhash { - enum nft_registers sreg:8; - enum nft_registers dreg:8; + u8 sreg; + u8 dreg; u8 len; bool autogen_seed:1; u32 modulus; @@ -38,7 +38,7 @@ static void nft_jhash_eval(const struct nft_expr *expr, } struct nft_symhash { - enum nft_registers dreg:8; + u8 dreg; u32 modulus; u32 offset; }; @@ -83,9 +83,6 @@ static int nft_jhash_init(const struct nft_ctx *ctx, if (tb[NFTA_HASH_OFFSET]) priv->offset = ntohl(nla_get_be32(tb[NFTA_HASH_OFFSET])); - priv->sreg = nft_parse_register(tb[NFTA_HASH_SREG]); - priv->dreg = nft_parse_register(tb[NFTA_HASH_DREG]); - err = nft_parse_u32_check(tb[NFTA_HASH_LEN], U8_MAX, &len); if (err < 0) return err; @@ -94,6 +91,10 @@ static int nft_jhash_init(const struct nft_ctx *ctx, priv->len = len; + err = nft_parse_register_load(tb[NFTA_HASH_SREG], &priv->sreg, len); + if (err < 0) + return err; + priv->modulus = ntohl(nla_get_be32(tb[NFTA_HASH_MODULUS])); if (priv->modulus < 1) return -ERANGE; @@ -108,9 +109,8 @@ static int nft_jhash_init(const struct nft_ctx *ctx, get_random_bytes(&priv->seed, sizeof(priv->seed)); } - return nft_validate_register_load(priv->sreg, len) && - nft_validate_register_store(ctx, priv->dreg, NULL, - NFT_DATA_VALUE, sizeof(u32)); + return nft_parse_register_store(ctx, tb[NFTA_HASH_DREG], &priv->dreg, + NULL, NFT_DATA_VALUE, sizeof(u32)); } static int nft_symhash_init(const struct nft_ctx *ctx, @@ -126,8 +126,6 @@ static int nft_symhash_init(const struct nft_ctx *ctx, if (tb[NFTA_HASH_OFFSET]) priv->offset = ntohl(nla_get_be32(tb[NFTA_HASH_OFFSET])); - priv->dreg = nft_parse_register(tb[NFTA_HASH_DREG]); - priv->modulus = ntohl(nla_get_be32(tb[NFTA_HASH_MODULUS])); if (priv->modulus < 1) return -ERANGE; @@ -135,8 +133,9 @@ static int nft_symhash_init(const struct nft_ctx *ctx, if (priv->offset + priv->modulus - 1 < priv->offset) return -EOVERFLOW; - return nft_validate_register_store(ctx, priv->dreg, NULL, - NFT_DATA_VALUE, sizeof(u32)); + return nft_parse_register_store(ctx, tb[NFTA_HASH_DREG], + &priv->dreg, NULL, NFT_DATA_VALUE, + sizeof(u32)); } static int nft_jhash_dump(struct sk_buff *skb, diff --git a/net/netfilter/nft_immediate.c b/net/netfilter/nft_immediate.c index c63eb3b17178..90c64d27ae53 100644 --- a/net/netfilter/nft_immediate.c +++ b/net/netfilter/nft_immediate.c @@ -48,9 +48,9 @@ static int nft_immediate_init(const struct nft_ctx *ctx, priv->dlen = desc.len; - priv->dreg = nft_parse_register(tb[NFTA_IMMEDIATE_DREG]); - err = nft_validate_register_store(ctx, priv->dreg, &priv->data, - desc.type, desc.len); + err = nft_parse_register_store(ctx, tb[NFTA_IMMEDIATE_DREG], + &priv->dreg, &priv->data, desc.type, + desc.len); if (err < 0) goto err1; diff --git a/net/netfilter/nft_lookup.c b/net/netfilter/nft_lookup.c index f1363b8aabba..b0f558b4fea5 100644 --- a/net/netfilter/nft_lookup.c +++ b/net/netfilter/nft_lookup.c @@ -17,8 +17,8 @@ struct nft_lookup { struct nft_set *set; - enum nft_registers sreg:8; - enum nft_registers dreg:8; + u8 sreg; + u8 dreg; bool invert; struct nft_set_binding binding; }; @@ -76,8 +76,8 @@ static int nft_lookup_init(const struct nft_ctx *ctx, if (IS_ERR(set)) return PTR_ERR(set); - priv->sreg = nft_parse_register(tb[NFTA_LOOKUP_SREG]); - err = nft_validate_register_load(priv->sreg, set->klen); + err = nft_parse_register_load(tb[NFTA_LOOKUP_SREG], &priv->sreg, + set->klen); if (err < 0) return err; @@ -100,9 +100,9 @@ static int nft_lookup_init(const struct nft_ctx *ctx, if (!(set->flags & NFT_SET_MAP)) return -EINVAL; - priv->dreg = nft_parse_register(tb[NFTA_LOOKUP_DREG]); - err = nft_validate_register_store(ctx, priv->dreg, NULL, - set->dtype, set->dlen); + err = nft_parse_register_store(ctx, tb[NFTA_LOOKUP_DREG], + &priv->dreg, NULL, set->dtype, + set->dlen); if (err < 0) return err; } else if (set->flags & NFT_SET_MAP) diff --git a/net/netfilter/nft_masq.c b/net/netfilter/nft_masq.c index 71390b727040..9953e8053753 100644 --- a/net/netfilter/nft_masq.c +++ b/net/netfilter/nft_masq.c @@ -15,8 +15,8 @@ struct nft_masq { u32 flags; - enum nft_registers sreg_proto_min:8; - enum nft_registers sreg_proto_max:8; + u8 sreg_proto_min; + u8 sreg_proto_max; }; static const struct nla_policy nft_masq_policy[NFTA_MASQ_MAX + 1] = { @@ -54,19 +54,15 @@ static int nft_masq_init(const struct nft_ctx *ctx, } if (tb[NFTA_MASQ_REG_PROTO_MIN]) { - priv->sreg_proto_min = - nft_parse_register(tb[NFTA_MASQ_REG_PROTO_MIN]); - - err = nft_validate_register_load(priv->sreg_proto_min, plen); + err = nft_parse_register_load(tb[NFTA_MASQ_REG_PROTO_MIN], + &priv->sreg_proto_min, plen); if (err < 0) return err; if (tb[NFTA_MASQ_REG_PROTO_MAX]) { - priv->sreg_proto_max = - nft_parse_register(tb[NFTA_MASQ_REG_PROTO_MAX]); - - err = nft_validate_register_load(priv->sreg_proto_max, - plen); + err = nft_parse_register_load(tb[NFTA_MASQ_REG_PROTO_MAX], + &priv->sreg_proto_max, + plen); if (err < 0) return err; } else { diff --git a/net/netfilter/nft_meta.c b/net/netfilter/nft_meta.c index bf4b3ad5314c..a7e01e9952f1 100644 --- a/net/netfilter/nft_meta.c +++ b/net/netfilter/nft_meta.c @@ -535,9 +535,8 @@ int nft_meta_get_init(const struct nft_ctx *ctx, return -EOPNOTSUPP; } - priv->dreg = nft_parse_register(tb[NFTA_META_DREG]); - return nft_validate_register_store(ctx, priv->dreg, NULL, - NFT_DATA_VALUE, len); + return nft_parse_register_store(ctx, tb[NFTA_META_DREG], &priv->dreg, + NULL, NFT_DATA_VALUE, len); } EXPORT_SYMBOL_GPL(nft_meta_get_init); @@ -661,8 +660,7 @@ int nft_meta_set_init(const struct nft_ctx *ctx, return -EOPNOTSUPP; } - priv->sreg = nft_parse_register(tb[NFTA_META_SREG]); - err = nft_validate_register_load(priv->sreg, len); + err = nft_parse_register_load(tb[NFTA_META_SREG], &priv->sreg, len); if (err < 0) return err; diff --git a/net/netfilter/nft_nat.c b/net/netfilter/nft_nat.c index 4bcf33b049c4..0840c635b752 100644 --- a/net/netfilter/nft_nat.c +++ b/net/netfilter/nft_nat.c @@ -21,10 +21,10 @@ #include <net/ip.h> struct nft_nat { - enum nft_registers sreg_addr_min:8; - enum nft_registers sreg_addr_max:8; - enum nft_registers sreg_proto_min:8; - enum nft_registers sreg_proto_max:8; + u8 sreg_addr_min; + u8 sreg_addr_max; + u8 sreg_proto_min; + u8 sreg_proto_max; enum nf_nat_manip_type type:8; u8 family; u16 flags; @@ -206,18 +206,15 @@ static int nft_nat_init(const struct nft_ctx *ctx, const struct nft_expr *expr, priv->family = family; if (tb[NFTA_NAT_REG_ADDR_MIN]) { - priv->sreg_addr_min = - nft_parse_register(tb[NFTA_NAT_REG_ADDR_MIN]); - err = nft_validate_register_load(priv->sreg_addr_min, alen); + err = nft_parse_register_load(tb[NFTA_NAT_REG_ADDR_MIN], + &priv->sreg_addr_min, alen); if (err < 0) return err; if (tb[NFTA_NAT_REG_ADDR_MAX]) { - priv->sreg_addr_max = - nft_parse_register(tb[NFTA_NAT_REG_ADDR_MAX]); - - err = nft_validate_register_load(priv->sreg_addr_max, - alen); + err = nft_parse_register_load(tb[NFTA_NAT_REG_ADDR_MAX], + &priv->sreg_addr_max, + alen); if (err < 0) return err; } else { @@ -229,19 +226,15 @@ static int nft_nat_init(const struct nft_ctx *ctx, const struct nft_expr *expr, plen = sizeof_field(struct nf_nat_range, min_addr.all); if (tb[NFTA_NAT_REG_PROTO_MIN]) { - priv->sreg_proto_min = - nft_parse_register(tb[NFTA_NAT_REG_PROTO_MIN]); - - err = nft_validate_register_load(priv->sreg_proto_min, plen); + err = nft_parse_register_load(tb[NFTA_NAT_REG_PROTO_MIN], + &priv->sreg_proto_min, plen); if (err < 0) return err; if (tb[NFTA_NAT_REG_PROTO_MAX]) { - priv->sreg_proto_max = - nft_parse_register(tb[NFTA_NAT_REG_PROTO_MAX]); - - err = nft_validate_register_load(priv->sreg_proto_max, - plen); + err = nft_parse_register_load(tb[NFTA_NAT_REG_PROTO_MAX], + &priv->sreg_proto_max, + plen); if (err < 0) return err; } else { diff --git a/net/netfilter/nft_numgen.c b/net/netfilter/nft_numgen.c index f1fc824f9737..722cac1e90e0 100644 --- a/net/netfilter/nft_numgen.c +++ b/net/netfilter/nft_numgen.c @@ -16,7 +16,7 @@ static DEFINE_PER_CPU(struct rnd_state, nft_numgen_prandom_state); struct nft_ng_inc { - enum nft_registers dreg:8; + u8 dreg; u32 modulus; atomic_t counter; u32 offset; @@ -66,11 +66,10 @@ static int nft_ng_inc_init(const struct nft_ctx *ctx, if (priv->offset + priv->modulus - 1 < priv->offset) return -EOVERFLOW; - priv->dreg = nft_parse_register(tb[NFTA_NG_DREG]); atomic_set(&priv->counter, priv->modulus - 1); - return nft_validate_register_store(ctx, priv->dreg, NULL, - NFT_DATA_VALUE, sizeof(u32)); + return nft_parse_register_store(ctx, tb[NFTA_NG_DREG], &priv->dreg, + NULL, NFT_DATA_VALUE, sizeof(u32)); } static int nft_ng_dump(struct sk_buff *skb, enum nft_registers dreg, @@ -100,7 +99,7 @@ static int nft_ng_inc_dump(struct sk_buff *skb, const struct nft_expr *expr) } struct nft_ng_random { - enum nft_registers dreg:8; + u8 dreg; u32 modulus; u32 offset; }; @@ -140,10 +139,8 @@ static int nft_ng_random_init(const struct nft_ctx *ctx, prandom_init_once(&nft_numgen_prandom_state); - priv->dreg = nft_parse_register(tb[NFTA_NG_DREG]); - - return nft_validate_register_store(ctx, priv->dreg, NULL, - NFT_DATA_VALUE, sizeof(u32)); + return nft_parse_register_store(ctx, tb[NFTA_NG_DREG], &priv->dreg, + NULL, NFT_DATA_VALUE, sizeof(u32)); } static int nft_ng_random_dump(struct sk_buff *skb, const struct nft_expr *expr) diff --git a/net/netfilter/nft_objref.c b/net/netfilter/nft_objref.c index 5f9207a9f485..bc104d36d3bb 100644 --- a/net/netfilter/nft_objref.c +++ b/net/netfilter/nft_objref.c @@ -95,7 +95,7 @@ static const struct nft_expr_ops nft_objref_ops = { struct nft_objref_map { struct nft_set *set; - enum nft_registers sreg:8; + u8 sreg; struct nft_set_binding binding; }; @@ -137,8 +137,8 @@ static int nft_objref_map_init(const struct nft_ctx *ctx, if (!(set->flags & NFT_SET_OBJECT)) return -EINVAL; - priv->sreg = nft_parse_register(tb[NFTA_OBJREF_SET_SREG]); - err = nft_validate_register_load(priv->sreg, set->klen); + err = nft_parse_register_load(tb[NFTA_OBJREF_SET_SREG], &priv->sreg, + set->klen); if (err < 0) return err; diff --git a/net/netfilter/nft_osf.c b/net/netfilter/nft_osf.c index c261d57a666a..ac61f708b82d 100644 --- a/net/netfilter/nft_osf.c +++ b/net/netfilter/nft_osf.c @@ -6,7 +6,7 @@ #include <linux/netfilter/nfnetlink_osf.h> struct nft_osf { - enum nft_registers dreg:8; + u8 dreg; u8 ttl; u32 flags; }; @@ -78,9 +78,9 @@ static int nft_osf_init(const struct nft_ctx *ctx, priv->flags = flags; } - priv->dreg = nft_parse_register(tb[NFTA_OSF_DREG]); - err = nft_validate_register_store(ctx, priv->dreg, NULL, - NFT_DATA_VALUE, NFT_OSF_MAXGENRELEN); + err = nft_parse_register_store(ctx, tb[NFTA_OSF_DREG], &priv->dreg, + NULL, NFT_DATA_VALUE, + NFT_OSF_MAXGENRELEN); if (err < 0) return err; diff --git a/net/netfilter/nft_payload.c b/net/netfilter/nft_payload.c index 47d4e0e21651..cb1c8c231880 100644 --- a/net/netfilter/nft_payload.c +++ b/net/netfilter/nft_payload.c @@ -144,10 +144,10 @@ static int nft_payload_init(const struct nft_ctx *ctx, priv->base = ntohl(nla_get_be32(tb[NFTA_PAYLOAD_BASE])); priv->offset = ntohl(nla_get_be32(tb[NFTA_PAYLOAD_OFFSET])); priv->len = ntohl(nla_get_be32(tb[NFTA_PAYLOAD_LEN])); - priv->dreg = nft_parse_register(tb[NFTA_PAYLOAD_DREG]); - return nft_validate_register_store(ctx, priv->dreg, NULL, - NFT_DATA_VALUE, priv->len); + return nft_parse_register_store(ctx, tb[NFTA_PAYLOAD_DREG], + &priv->dreg, NULL, NFT_DATA_VALUE, + priv->len); } static int nft_payload_dump(struct sk_buff *skb, const struct nft_expr *expr) @@ -658,7 +658,6 @@ static int nft_payload_set_init(const struct nft_ctx *ctx, priv->base = ntohl(nla_get_be32(tb[NFTA_PAYLOAD_BASE])); priv->offset = ntohl(nla_get_be32(tb[NFTA_PAYLOAD_OFFSET])); priv->len = ntohl(nla_get_be32(tb[NFTA_PAYLOAD_LEN])); - priv->sreg = nft_parse_register(tb[NFTA_PAYLOAD_SREG]); if (tb[NFTA_PAYLOAD_CSUM_TYPE]) priv->csum_type = @@ -691,7 +690,8 @@ static int nft_payload_set_init(const struct nft_ctx *ctx, return -EOPNOTSUPP; } - return nft_validate_register_load(priv->sreg, priv->len); + return nft_parse_register_load(tb[NFTA_PAYLOAD_SREG], &priv->sreg, + priv->len); } static int nft_payload_set_dump(struct sk_buff *skb, const struct nft_expr *expr) diff --git a/net/netfilter/nft_queue.c b/net/netfilter/nft_queue.c index 23265d757acb..9ba1de51ac07 100644 --- a/net/netfilter/nft_queue.c +++ b/net/netfilter/nft_queue.c @@ -19,10 +19,10 @@ static u32 jhash_initval __read_mostly; struct nft_queue { - enum nft_registers sreg_qnum:8; - u16 queuenum; - u16 queues_total; - u16 flags; + u8 sreg_qnum; + u16 queuenum; + u16 queues_total; + u16 flags; }; static void nft_queue_eval(const struct nft_expr *expr, @@ -111,8 +111,8 @@ static int nft_queue_sreg_init(const struct nft_ctx *ctx, struct nft_queue *priv = nft_expr_priv(expr); int err; - priv->sreg_qnum = nft_parse_register(tb[NFTA_QUEUE_SREG_QNUM]); - err = nft_validate_register_load(priv->sreg_qnum, sizeof(u32)); + err = nft_parse_register_load(tb[NFTA_QUEUE_SREG_QNUM], + &priv->sreg_qnum, sizeof(u32)); if (err < 0) return err; diff --git a/net/netfilter/nft_range.c b/net/netfilter/nft_range.c index 89efcc5a533d..e4a1c44d7f51 100644 --- a/net/netfilter/nft_range.c +++ b/net/netfilter/nft_range.c @@ -15,7 +15,7 @@ struct nft_range_expr { struct nft_data data_from; struct nft_data data_to; - enum nft_registers sreg:8; + u8 sreg; u8 len; enum nft_range_ops op:8; }; @@ -86,8 +86,8 @@ static int nft_range_init(const struct nft_ctx *ctx, const struct nft_expr *expr goto err2; } - priv->sreg = nft_parse_register(tb[NFTA_RANGE_SREG]); - err = nft_validate_register_load(priv->sreg, desc_from.len); + err = nft_parse_register_load(tb[NFTA_RANGE_SREG], &priv->sreg, + desc_from.len); if (err < 0) goto err2; diff --git a/net/netfilter/nft_redir.c b/net/netfilter/nft_redir.c index 2056051c0af0..ba09890dddb5 100644 --- a/net/netfilter/nft_redir.c +++ b/net/netfilter/nft_redir.c @@ -14,8 +14,8 @@ #include <net/netfilter/nf_tables.h> struct nft_redir { - enum nft_registers sreg_proto_min:8; - enum nft_registers sreg_proto_max:8; + u8 sreg_proto_min; + u8 sreg_proto_max; u16 flags; }; @@ -50,19 +50,15 @@ static int nft_redir_init(const struct nft_ctx *ctx, plen = sizeof_field(struct nf_nat_range, min_addr.all); if (tb[NFTA_REDIR_REG_PROTO_MIN]) { - priv->sreg_proto_min = - nft_parse_register(tb[NFTA_REDIR_REG_PROTO_MIN]); - - err = nft_validate_register_load(priv->sreg_proto_min, plen); + err = nft_parse_register_load(tb[NFTA_REDIR_REG_PROTO_MIN], + &priv->sreg_proto_min, plen); if (err < 0) return err; if (tb[NFTA_REDIR_REG_PROTO_MAX]) { - priv->sreg_proto_max = - nft_parse_register(tb[NFTA_REDIR_REG_PROTO_MAX]); - - err = nft_validate_register_load(priv->sreg_proto_max, - plen); + err = nft_parse_register_load(tb[NFTA_REDIR_REG_PROTO_MAX], + &priv->sreg_proto_max, + plen); if (err < 0) return err; } else { diff --git a/net/netfilter/nft_rt.c b/net/netfilter/nft_rt.c index 7cfcb0e2f7ee..bcd01a63e38f 100644 --- a/net/netfilter/nft_rt.c +++ b/net/netfilter/nft_rt.c @@ -15,7 +15,7 @@ struct nft_rt { enum nft_rt_keys key:8; - enum nft_registers dreg:8; + u8 dreg; }; static u16 get_tcpmss(const struct nft_pktinfo *pkt, const struct dst_entry *skbdst) @@ -141,9 +141,8 @@ static int nft_rt_get_init(const struct nft_ctx *ctx, return -EOPNOTSUPP; } - priv->dreg = nft_parse_register(tb[NFTA_RT_DREG]); - return nft_validate_register_store(ctx, priv->dreg, NULL, - NFT_DATA_VALUE, len); + return nft_parse_register_store(ctx, tb[NFTA_RT_DREG], &priv->dreg, + NULL, NFT_DATA_VALUE, len); } static int nft_rt_get_dump(struct sk_buff *skb, diff --git a/net/netfilter/nft_socket.c b/net/netfilter/nft_socket.c index a28aca5124ce..c9b8a2b03b71 100644 --- a/net/netfilter/nft_socket.c +++ b/net/netfilter/nft_socket.c @@ -10,7 +10,7 @@ struct nft_socket { enum nft_socket_keys key:8; union { - enum nft_registers dreg:8; + u8 dreg; }; }; @@ -133,9 +133,8 @@ static int nft_socket_init(const struct nft_ctx *ctx, return -EOPNOTSUPP; } - priv->dreg = nft_parse_register(tb[NFTA_SOCKET_DREG]); - return nft_validate_register_store(ctx, priv->dreg, NULL, - NFT_DATA_VALUE, len); + return nft_parse_register_store(ctx, tb[NFTA_SOCKET_DREG], &priv->dreg, + NULL, NFT_DATA_VALUE, len); } static int nft_socket_dump(struct sk_buff *skb, diff --git a/net/netfilter/nft_tproxy.c b/net/netfilter/nft_tproxy.c index d67f83a0958d..43a5a780a6d3 100644 --- a/net/netfilter/nft_tproxy.c +++ b/net/netfilter/nft_tproxy.c @@ -13,9 +13,9 @@ #endif struct nft_tproxy { - enum nft_registers sreg_addr:8; - enum nft_registers sreg_port:8; - u8 family; + u8 sreg_addr; + u8 sreg_port; + u8 family; }; static void nft_tproxy_eval_v4(const struct nft_expr *expr, @@ -247,15 +247,15 @@ static int nft_tproxy_init(const struct nft_ctx *ctx, } if (tb[NFTA_TPROXY_REG_ADDR]) { - priv->sreg_addr = nft_parse_register(tb[NFTA_TPROXY_REG_ADDR]); - err = nft_validate_register_load(priv->sreg_addr, alen); + err = nft_parse_register_load(tb[NFTA_TPROXY_REG_ADDR], + &priv->sreg_addr, alen); if (err < 0) return err; } if (tb[NFTA_TPROXY_REG_PORT]) { - priv->sreg_port = nft_parse_register(tb[NFTA_TPROXY_REG_PORT]); - err = nft_validate_register_load(priv->sreg_port, sizeof(u16)); + err = nft_parse_register_load(tb[NFTA_TPROXY_REG_PORT], + &priv->sreg_port, sizeof(u16)); if (err < 0) return err; } diff --git a/net/netfilter/nft_tunnel.c b/net/netfilter/nft_tunnel.c index d3eb953d0333..3b27926d5382 100644 --- a/net/netfilter/nft_tunnel.c +++ b/net/netfilter/nft_tunnel.c @@ -15,7 +15,7 @@ struct nft_tunnel { enum nft_tunnel_keys key:8; - enum nft_registers dreg:8; + u8 dreg; enum nft_tunnel_mode mode:8; }; @@ -93,8 +93,6 @@ static int nft_tunnel_get_init(const struct nft_ctx *ctx, return -EOPNOTSUPP; } - priv->dreg = nft_parse_register(tb[NFTA_TUNNEL_DREG]); - if (tb[NFTA_TUNNEL_MODE]) { priv->mode = ntohl(nla_get_be32(tb[NFTA_TUNNEL_MODE])); if (priv->mode > NFT_TUNNEL_MODE_MAX) @@ -103,8 +101,8 @@ static int nft_tunnel_get_init(const struct nft_ctx *ctx, priv->mode = NFT_TUNNEL_MODE_NONE; } - return nft_validate_register_store(ctx, priv->dreg, NULL, - NFT_DATA_VALUE, len); + return nft_parse_register_store(ctx, tb[NFTA_TUNNEL_DREG], &priv->dreg, + NULL, NFT_DATA_VALUE, len); } static int nft_tunnel_get_dump(struct sk_buff *skb, diff --git a/net/netfilter/nft_xfrm.c b/net/netfilter/nft_xfrm.c index 06d5cabf1d7c..cbbbc4ecad3a 100644 --- a/net/netfilter/nft_xfrm.c +++ b/net/netfilter/nft_xfrm.c @@ -24,7 +24,7 @@ static const struct nla_policy nft_xfrm_policy[NFTA_XFRM_MAX + 1] = { struct nft_xfrm { enum nft_xfrm_keys key:8; - enum nft_registers dreg:8; + u8 dreg; u8 dir; u8 spnum; }; @@ -86,9 +86,8 @@ static int nft_xfrm_get_init(const struct nft_ctx *ctx, priv->spnum = spnum; - priv->dreg = nft_parse_register(tb[NFTA_XFRM_DREG]); - return nft_validate_register_store(ctx, priv->dreg, NULL, - NFT_DATA_VALUE, len); + return nft_parse_register_store(ctx, tb[NFTA_XFRM_DREG], &priv->dreg, + NULL, NFT_DATA_VALUE, len); } /* Return true if key asks for daddr/saddr and current diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index daca50d6bb12..dd488938447f 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -67,6 +67,8 @@ #include <net/sock.h> #include <net/scm.h> #include <net/netlink.h> +#define CREATE_TRACE_POINTS +#include <trace/events/netlink.h> #include "af_netlink.h" @@ -147,6 +149,12 @@ static BLOCKING_NOTIFIER_HEAD(netlink_chain); static const struct rhashtable_params netlink_rhashtable_params; +void do_trace_netlink_extack(const char *msg) +{ + trace_netlink_extack(msg); +} +EXPORT_SYMBOL(do_trace_netlink_extack); + static inline u32 netlink_group_mask(u32 group) { return group ? 1 << (group - 1) : 0; diff --git a/net/netlink/genetlink.c b/net/netlink/genetlink.c index c992424e4d63..2d6fdf40df66 100644 --- a/net/netlink/genetlink.c +++ b/net/netlink/genetlink.c @@ -1360,11 +1360,43 @@ static struct genl_family genl_ctrl __ro_after_init = { .netnsok = true, }; +static int genl_bind(struct net *net, int group) +{ + const struct genl_family *family; + unsigned int id; + int ret = 0; + + genl_lock_all(); + + idr_for_each_entry(&genl_fam_idr, family, id) { + const struct genl_multicast_group *grp; + int i; + + if (family->n_mcgrps == 0) + continue; + + i = group - family->mcgrp_offset; + if (i < 0 || i >= family->n_mcgrps) + continue; + + grp = &family->mcgrps[i]; + if ((grp->flags & GENL_UNS_ADMIN_PERM) && + !ns_capable(net->user_ns, CAP_NET_ADMIN)) + ret = -EPERM; + + break; + } + + genl_unlock_all(); + return ret; +} + static int __net_init genl_pernet_init(struct net *net) { struct netlink_kernel_cfg cfg = { .input = genl_rcv, .flags = NL_CFG_F_NONROOT_RECV, + .bind = genl_bind, }; /* we'll bump the group number right afterwards */ diff --git a/net/nfc/Kconfig b/net/nfc/Kconfig index 96b91674dd37..466a0279b93e 100644 --- a/net/nfc/Kconfig +++ b/net/nfc/Kconfig @@ -4,7 +4,6 @@ # menuconfig NFC - depends on NET depends on RFKILL || !RFKILL tristate "NFC subsystem support" default n diff --git a/net/nfc/hci/llc_shdlc.c b/net/nfc/hci/llc_shdlc.c index 0eb4ddc056e7..c0c8fea3a186 100644 --- a/net/nfc/hci/llc_shdlc.c +++ b/net/nfc/hci/llc_shdlc.c @@ -236,7 +236,7 @@ static void llc_shdlc_rcv_i_frame(struct llc_shdlc *shdlc, goto exit; } - if (shdlc->t1_active == false) { + if (!shdlc->t1_active) { shdlc->t1_active = true; mod_timer(&shdlc->t1_timer, jiffies + msecs_to_jiffies(SHDLC_T1_VALUE_MS(shdlc->w))); diff --git a/net/nfc/nci/core.c b/net/nfc/nci/core.c index 02a1f13f0798..59257400697d 100644 --- a/net/nfc/nci/core.c +++ b/net/nfc/nci/core.c @@ -579,11 +579,11 @@ static int nci_close_device(struct nci_dev *ndev) clear_bit(NCI_INIT, &ndev->flags); - del_timer_sync(&ndev->cmd_timer); - /* Flush cmd wq */ flush_workqueue(ndev->cmd_wq); + del_timer_sync(&ndev->cmd_timer); + /* Clear flags */ ndev->flags = 0; diff --git a/net/nfc/nci/uart.c b/net/nfc/nci/uart.c index 11b554ce07ff..1204c438e87d 100644 --- a/net/nfc/nci/uart.c +++ b/net/nfc/nci/uart.c @@ -292,7 +292,8 @@ static int nci_uart_tty_ioctl(struct tty_struct *tty, struct file *file, /* We don't provide read/write/poll interface for user space. */ static ssize_t nci_uart_tty_read(struct tty_struct *tty, struct file *file, - unsigned char __user *buf, size_t nr) + unsigned char *buf, size_t nr, + void **cookie, unsigned long offset) { return 0; } diff --git a/net/nfc/netlink.c b/net/nfc/netlink.c index e161ef2d4720..722f7ef891e1 100644 --- a/net/nfc/netlink.c +++ b/net/nfc/netlink.c @@ -1820,9 +1820,9 @@ static int nfc_genl_rcv_nl_event(struct notifier_block *this, w = kmalloc(sizeof(*w), GFP_ATOMIC); if (w) { - INIT_WORK((struct work_struct *) w, nfc_urelease_event_work); + INIT_WORK(&w->w, nfc_urelease_event_work); w->portid = n->portid; - schedule_work((struct work_struct *) w); + schedule_work(&w->w); } out: diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c index e8902a7e60f2..92a0b67b2728 100644 --- a/net/openvswitch/actions.c +++ b/net/openvswitch/actions.c @@ -957,14 +957,14 @@ static int output_userspace(struct datapath *dp, struct sk_buff *skb, static int dec_ttl_exception_handler(struct datapath *dp, struct sk_buff *skb, struct sw_flow_key *key, - const struct nlattr *attr, bool last) + const struct nlattr *attr) { /* The first attribute is always 'OVS_DEC_TTL_ATTR_ACTION'. */ struct nlattr *actions = nla_data(attr); if (nla_len(actions)) return clone_execute(dp, skb, key, 0, nla_data(actions), - nla_len(actions), last, false); + nla_len(actions), true, false); consume_skb(skb); return 0; @@ -1418,11 +1418,9 @@ static int do_execute_actions(struct datapath *dp, struct sk_buff *skb, case OVS_ACTION_ATTR_DEC_TTL: err = execute_dec_ttl(skb, key); - if (err == -EHOSTUNREACH) { - err = dec_ttl_exception_handler(dp, skb, key, - a, true); - return err; - } + if (err == -EHOSTUNREACH) + return dec_ttl_exception_handler(dp, skb, + key, a); break; } diff --git a/net/openvswitch/flow_netlink.c b/net/openvswitch/flow_netlink.c index 4c5c2331e764..fd1f809e9bc1 100644 --- a/net/openvswitch/flow_netlink.c +++ b/net/openvswitch/flow_netlink.c @@ -2515,15 +2515,25 @@ static int validate_and_copy_dec_ttl(struct net *net, if (type > OVS_DEC_TTL_ATTR_MAX) continue; - if (!type || attrs[type]) + if (!type || attrs[type]) { + OVS_NLERR(log, "Duplicate or invalid key (type %d).", + type); return -EINVAL; + } attrs[type] = a; } + if (rem) { + OVS_NLERR(log, "Message has %d unknown bytes.", rem); + return -EINVAL; + } + actions = attrs[OVS_DEC_TTL_ATTR_ACTION]; - if (rem || !actions || (nla_len(actions) && nla_len(actions) < NLA_HDRLEN)) + if (!actions || (nla_len(actions) && nla_len(actions) < NLA_HDRLEN)) { + OVS_NLERR(log, "Missing valid actions attribute."); return -EINVAL; + } start = add_nested_action_start(sfa, OVS_ACTION_ATTR_DEC_TTL, log); if (start < 0) diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index 6bbc7a448593..e24b2841c643 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -135,11 +135,11 @@ Resume On transmit: ------------ -dev->header_ops != NULL +dev_has_header(dev) == true mac_header -> ll header data -> ll header -dev->header_ops == NULL (ll header is invisible to us) +dev_has_header(dev) == false (ll header is invisible to us) mac_header -> data data -> data diff --git a/net/packet/internal.h b/net/packet/internal.h index baafc3f3fa25..5f61e59ebbff 100644 --- a/net/packet/internal.h +++ b/net/packet/internal.h @@ -139,7 +139,7 @@ struct packet_sock { atomic_t tp_drops ____cacheline_aligned_in_smp; }; -static struct packet_sock *pkt_sk(struct sock *sk) +static inline struct packet_sock *pkt_sk(struct sock *sk) { return (struct packet_sock *)sk; } diff --git a/net/psample/Kconfig b/net/psample/Kconfig index 028f514a9c60..be0b839209ba 100644 --- a/net/psample/Kconfig +++ b/net/psample/Kconfig @@ -4,7 +4,6 @@ # menuconfig PSAMPLE - depends on NET tristate "Packet-sampling netlink channel" default n help diff --git a/net/rxrpc/Kconfig b/net/rxrpc/Kconfig index d706bb408365..0885b22e5c0e 100644 --- a/net/rxrpc/Kconfig +++ b/net/rxrpc/Kconfig @@ -8,6 +8,7 @@ config AF_RXRPC depends on INET select CRYPTO select KEYS + select NET_UDP_TUNNEL help Say Y or M here to include support for RxRPC session sockets (just the transport part, not the presentation part: (un)marshalling is diff --git a/net/rxrpc/local_object.c b/net/rxrpc/local_object.c index 8c2881054266..a4111408ffd0 100644 --- a/net/rxrpc/local_object.c +++ b/net/rxrpc/local_object.c @@ -16,6 +16,7 @@ #include <linux/hashtable.h> #include <net/sock.h> #include <net/udp.h> +#include <net/udp_tunnel.h> #include <net/af_rxrpc.h> #include "ar-internal.h" @@ -106,58 +107,44 @@ static struct rxrpc_local *rxrpc_alloc_local(struct rxrpc_net *rxnet, */ static int rxrpc_open_socket(struct rxrpc_local *local, struct net *net) { + struct udp_tunnel_sock_cfg tuncfg = {NULL}; + struct sockaddr_rxrpc *srx = &local->srx; + struct udp_port_cfg udp_conf = {0}; struct sock *usk; int ret; _enter("%p{%d,%d}", - local, local->srx.transport_type, local->srx.transport.family); + local, srx->transport_type, srx->transport.family); - /* create a socket to represent the local endpoint */ - ret = sock_create_kern(net, local->srx.transport.family, - local->srx.transport_type, 0, &local->socket); + udp_conf.family = srx->transport.family; + if (udp_conf.family == AF_INET) { + udp_conf.local_ip = srx->transport.sin.sin_addr; + udp_conf.local_udp_port = srx->transport.sin.sin_port; +#if IS_ENABLED(CONFIG_AF_RXRPC_IPV6) + } else { + udp_conf.local_ip6 = srx->transport.sin6.sin6_addr; + udp_conf.local_udp_port = srx->transport.sin6.sin6_port; +#endif + } + ret = udp_sock_create(net, &udp_conf, &local->socket); if (ret < 0) { _leave(" = %d [socket]", ret); return ret; } + tuncfg.encap_type = UDP_ENCAP_RXRPC; + tuncfg.encap_rcv = rxrpc_input_packet; + tuncfg.sk_user_data = local; + setup_udp_tunnel_sock(net, local->socket, &tuncfg); + /* set the socket up */ usk = local->socket->sk; - inet_sk(usk)->mc_loop = 0; - - /* Enable CHECKSUM_UNNECESSARY to CHECKSUM_COMPLETE conversion */ - inet_inc_convert_csum(usk); - - rcu_assign_sk_user_data(usk, local); - - udp_sk(usk)->encap_type = UDP_ENCAP_RXRPC; - udp_sk(usk)->encap_rcv = rxrpc_input_packet; - udp_sk(usk)->encap_destroy = NULL; - udp_sk(usk)->gro_receive = NULL; - udp_sk(usk)->gro_complete = NULL; - - udp_encap_enable(); -#if IS_ENABLED(CONFIG_AF_RXRPC_IPV6) - if (local->srx.transport.family == AF_INET6) - udpv6_encap_enable(); -#endif usk->sk_error_report = rxrpc_error_report; - /* if a local address was supplied then bind it */ - if (local->srx.transport_len > sizeof(sa_family_t)) { - _debug("bind"); - ret = kernel_bind(local->socket, - (struct sockaddr *)&local->srx.transport, - local->srx.transport_len); - if (ret < 0) { - _debug("bind failed %d", ret); - goto error; - } - } - - switch (local->srx.transport.family) { + switch (srx->transport.family) { case AF_INET6: /* we want to receive ICMPv6 errors */ - ip6_sock_set_recverr(local->socket->sk); + ip6_sock_set_recverr(usk); /* Fall through and set IPv4 options too otherwise we don't get * errors from IPv4 packets sent through the IPv6 socket. @@ -165,13 +152,13 @@ static int rxrpc_open_socket(struct rxrpc_local *local, struct net *net) fallthrough; case AF_INET: /* we want to receive ICMP errors */ - ip_sock_set_recverr(local->socket->sk); + ip_sock_set_recverr(usk); /* we want to set the don't fragment bit */ - ip_sock_set_mtu_discover(local->socket->sk, IP_PMTUDISC_DO); + ip_sock_set_mtu_discover(usk, IP_PMTUDISC_DO); /* We want receive timestamps. */ - sock_enable_timestamps(local->socket->sk); + sock_enable_timestamps(usk); break; default: @@ -180,15 +167,6 @@ static int rxrpc_open_socket(struct rxrpc_local *local, struct net *net) _leave(" = 0"); return 0; - -error: - kernel_sock_shutdown(local->socket, SHUT_RDWR); - local->socket->sk->sk_user_data = NULL; - sock_release(local->socket); - local->socket = NULL; - - _leave(" = %d", ret); - return ret; } /* diff --git a/net/sched/act_api.c b/net/sched/act_api.c index ebc8f1413078..b919826939e0 100644 --- a/net/sched/act_api.c +++ b/net/sched/act_api.c @@ -928,19 +928,13 @@ void tcf_idr_insert_many(struct tc_action *actions[]) } } -struct tc_action *tcf_action_init_1(struct net *net, struct tcf_proto *tp, - struct nlattr *nla, struct nlattr *est, - char *name, int ovr, int bind, - bool rtnl_held, - struct netlink_ext_ack *extack) +struct tc_action_ops *tc_action_load_ops(char *name, struct nlattr *nla, + bool rtnl_held, + struct netlink_ext_ack *extack) { - struct nla_bitfield32 flags = { 0, 0 }; - u8 hw_stats = TCA_ACT_HW_STATS_ANY; - struct tc_action *a; + struct nlattr *tb[TCA_ACT_MAX + 1]; struct tc_action_ops *a_o; - struct tc_cookie *cookie = NULL; char act_name[IFNAMSIZ]; - struct nlattr *tb[TCA_ACT_MAX + 1]; struct nlattr *kind; int err; @@ -948,33 +942,21 @@ struct tc_action *tcf_action_init_1(struct net *net, struct tcf_proto *tp, err = nla_parse_nested_deprecated(tb, TCA_ACT_MAX, nla, tcf_action_policy, extack); if (err < 0) - goto err_out; + return ERR_PTR(err); err = -EINVAL; kind = tb[TCA_ACT_KIND]; if (!kind) { NL_SET_ERR_MSG(extack, "TC action kind must be specified"); - goto err_out; + return ERR_PTR(err); } if (nla_strscpy(act_name, kind, IFNAMSIZ) < 0) { NL_SET_ERR_MSG(extack, "TC action name too long"); - goto err_out; - } - if (tb[TCA_ACT_COOKIE]) { - cookie = nla_memdup_cookie(tb); - if (!cookie) { - NL_SET_ERR_MSG(extack, "No memory to generate TC cookie"); - err = -ENOMEM; - goto err_out; - } + return ERR_PTR(err); } - hw_stats = tcf_action_hw_stats_get(tb[TCA_ACT_HW_STATS]); - if (tb[TCA_ACT_FLAGS]) - flags = nla_get_bitfield32(tb[TCA_ACT_FLAGS]); } else { if (strlcpy(act_name, name, IFNAMSIZ) >= IFNAMSIZ) { NL_SET_ERR_MSG(extack, "TC action name too long"); - err = -EINVAL; - goto err_out; + return ERR_PTR(-EINVAL); } } @@ -996,24 +978,56 @@ struct tc_action *tcf_action_init_1(struct net *net, struct tcf_proto *tp, * indicate this using -EAGAIN. */ if (a_o != NULL) { - err = -EAGAIN; - goto err_mod; + module_put(a_o->owner); + return ERR_PTR(-EAGAIN); } #endif NL_SET_ERR_MSG(extack, "Failed to load TC action module"); - err = -ENOENT; - goto err_free; + return ERR_PTR(-ENOENT); } + return a_o; +} + +struct tc_action *tcf_action_init_1(struct net *net, struct tcf_proto *tp, + struct nlattr *nla, struct nlattr *est, + char *name, int ovr, int bind, + struct tc_action_ops *a_o, bool rtnl_held, + struct netlink_ext_ack *extack) +{ + struct nla_bitfield32 flags = { 0, 0 }; + u8 hw_stats = TCA_ACT_HW_STATS_ANY; + struct nlattr *tb[TCA_ACT_MAX + 1]; + struct tc_cookie *cookie = NULL; + struct tc_action *a; + int err; + /* backward compatibility for policer */ - if (name == NULL) + if (name == NULL) { + err = nla_parse_nested_deprecated(tb, TCA_ACT_MAX, nla, + tcf_action_policy, extack); + if (err < 0) + return ERR_PTR(err); + if (tb[TCA_ACT_COOKIE]) { + cookie = nla_memdup_cookie(tb); + if (!cookie) { + NL_SET_ERR_MSG(extack, "No memory to generate TC cookie"); + err = -ENOMEM; + goto err_out; + } + } + hw_stats = tcf_action_hw_stats_get(tb[TCA_ACT_HW_STATS]); + if (tb[TCA_ACT_FLAGS]) + flags = nla_get_bitfield32(tb[TCA_ACT_FLAGS]); + err = a_o->init(net, tb[TCA_ACT_OPTIONS], est, &a, ovr, bind, rtnl_held, tp, flags.value, extack); - else + } else { err = a_o->init(net, nla, est, &a, ovr, bind, rtnl_held, tp, flags.value, extack); + } if (err < 0) - goto err_mod; + goto err_out; if (!name && tb[TCA_ACT_COOKIE]) tcf_set_action_cookie(&a->act_cookie, cookie); @@ -1030,14 +1044,11 @@ struct tc_action *tcf_action_init_1(struct net *net, struct tcf_proto *tp, return a; -err_mod: - module_put(a_o->owner); -err_free: +err_out: if (cookie) { kfree(cookie->data); kfree(cookie); } -err_out: return ERR_PTR(err); } @@ -1048,6 +1059,7 @@ int tcf_action_init(struct net *net, struct tcf_proto *tp, struct nlattr *nla, struct tc_action *actions[], size_t *attr_size, bool rtnl_held, struct netlink_ext_ack *extack) { + struct tc_action_ops *ops[TCA_ACT_MAX_PRIO] = {}; struct nlattr *tb[TCA_ACT_MAX_PRIO + 1]; struct tc_action *act; size_t sz = 0; @@ -1060,8 +1072,19 @@ int tcf_action_init(struct net *net, struct tcf_proto *tp, struct nlattr *nla, return err; for (i = 1; i <= TCA_ACT_MAX_PRIO && tb[i]; i++) { + struct tc_action_ops *a_o; + + a_o = tc_action_load_ops(name, tb[i], rtnl_held, extack); + if (IS_ERR(a_o)) { + err = PTR_ERR(a_o); + goto err_mod; + } + ops[i - 1] = a_o; + } + + for (i = 1; i <= TCA_ACT_MAX_PRIO && tb[i]; i++) { act = tcf_action_init_1(net, tp, tb[i], est, name, ovr, bind, - rtnl_held, extack); + ops[i - 1], rtnl_held, extack); if (IS_ERR(act)) { err = PTR_ERR(act); goto err; @@ -1081,6 +1104,11 @@ int tcf_action_init(struct net *net, struct tcf_proto *tp, struct nlattr *nla, err: tcf_action_destroy(actions, bind); +err_mod: + for (i = 0; i < TCA_ACT_MAX_PRIO; i++) { + if (ops[i]) + module_put(ops[i]->owner); + } return err; } diff --git a/net/sched/act_ct.c b/net/sched/act_ct.c index 83a5c6722a06..f0a0aa125b00 100644 --- a/net/sched/act_ct.c +++ b/net/sched/act_ct.c @@ -183,6 +183,7 @@ static void tcf_ct_flow_table_add_action_meta(struct nf_conn *ct, IP_CT_ESTABLISHED_REPLY; /* aligns with the CT reference on the SKB nf_ct_set */ entry->ct_metadata.cookie = (unsigned long)ct | ctinfo; + entry->ct_metadata.orig_dir = dir == IP_CT_DIR_ORIGINAL; act_ct_labels = entry->ct_metadata.labels; ct_labels = nf_ct_labels_find(ct); @@ -1030,6 +1031,7 @@ out_push: out: tcf_action_update_bstats(&c->common, skb); + qdisc_skb_cb(skb)->post_ct = true; if (defrag) qdisc_skb_cb(skb)->pkt_len = skb->len; return retval; diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index 0b3900dd2354..e37556cc37ab 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -3043,12 +3043,19 @@ int tcf_exts_validate(struct net *net, struct tcf_proto *tp, struct nlattr **tb, size_t attr_size = 0; if (exts->police && tb[exts->police]) { + struct tc_action_ops *a_o; + + a_o = tc_action_load_ops("police", tb[exts->police], rtnl_held, extack); + if (IS_ERR(a_o)) + return PTR_ERR(a_o); act = tcf_action_init_1(net, tp, tb[exts->police], rate_tlv, "police", ovr, - TCA_ACT_BIND, rtnl_held, + TCA_ACT_BIND, a_o, rtnl_held, extack); - if (IS_ERR(act)) + if (IS_ERR(act)) { + module_put(a_o->owner); return PTR_ERR(act); + } act->type = exts->type = TCA_OLD_COMPAT; exts->actions[0] = act; diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c index 46c1b3e9f66a..2409e522c68f 100644 --- a/net/sched/cls_flower.c +++ b/net/sched/cls_flower.c @@ -296,9 +296,11 @@ static u16 fl_ct_info_to_flower_map[] = { [IP_CT_RELATED] = TCA_FLOWER_KEY_CT_FLAGS_TRACKED | TCA_FLOWER_KEY_CT_FLAGS_RELATED, [IP_CT_ESTABLISHED_REPLY] = TCA_FLOWER_KEY_CT_FLAGS_TRACKED | - TCA_FLOWER_KEY_CT_FLAGS_ESTABLISHED, + TCA_FLOWER_KEY_CT_FLAGS_ESTABLISHED | + TCA_FLOWER_KEY_CT_FLAGS_REPLY, [IP_CT_RELATED_REPLY] = TCA_FLOWER_KEY_CT_FLAGS_TRACKED | - TCA_FLOWER_KEY_CT_FLAGS_RELATED, + TCA_FLOWER_KEY_CT_FLAGS_RELATED | + TCA_FLOWER_KEY_CT_FLAGS_REPLY, [IP_CT_NEW] = TCA_FLOWER_KEY_CT_FLAGS_TRACKED | TCA_FLOWER_KEY_CT_FLAGS_NEW, }; @@ -307,6 +309,7 @@ static int fl_classify(struct sk_buff *skb, const struct tcf_proto *tp, struct tcf_result *res) { struct cls_fl_head *head = rcu_dereference_bh(tp->root); + bool post_ct = qdisc_skb_cb(skb)->post_ct; struct fl_flow_key skb_key; struct fl_flow_mask *mask; struct cls_fl_filter *f; @@ -323,7 +326,8 @@ static int fl_classify(struct sk_buff *skb, const struct tcf_proto *tp, skb_flow_dissect_tunnel_info(skb, &mask->dissector, &skb_key); skb_flow_dissect_ct(skb, &mask->dissector, &skb_key, fl_ct_info_to_flower_map, - ARRAY_SIZE(fl_ct_info_to_flower_map)); + ARRAY_SIZE(fl_ct_info_to_flower_map), + post_ct); skb_flow_dissect_hash(skb, &mask->dissector, &skb_key); skb_flow_dissect(skb, &mask->dissector, &skb_key, 0); diff --git a/net/sched/em_nbyte.c b/net/sched/em_nbyte.c index 2c1192a2ee5e..a83b237cbeb0 100644 --- a/net/sched/em_nbyte.c +++ b/net/sched/em_nbyte.c @@ -31,7 +31,7 @@ static int em_nbyte_change(struct net *net, void *data, int data_len, em->datalen = sizeof(*nbyte) + nbyte->len; em->data = (unsigned long)kmemdup(data, em->datalen, GFP_KERNEL); if (em->data == 0UL) - return -ENOBUFS; + return -ENOMEM; return 0; } diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c index 6fe4e5cc807c..e2e4353db8a7 100644 --- a/net/sched/sch_api.c +++ b/net/sched/sch_api.c @@ -1866,7 +1866,8 @@ static int tclass_notify(struct net *net, struct sk_buff *oskb, static int tclass_del_notify(struct net *net, const struct Qdisc_class_ops *cops, struct sk_buff *oskb, struct nlmsghdr *n, - struct Qdisc *q, unsigned long cl) + struct Qdisc *q, unsigned long cl, + struct netlink_ext_ack *extack) { u32 portid = oskb ? NETLINK_CB(oskb).portid : 0; struct sk_buff *skb; @@ -1885,7 +1886,7 @@ static int tclass_del_notify(struct net *net, return -EINVAL; } - err = cops->delete(q, cl); + err = cops->delete(q, cl, extack); if (err) { kfree_skb(skb); return err; @@ -2088,7 +2089,7 @@ static int tc_ctl_tclass(struct sk_buff *skb, struct nlmsghdr *n, goto out; break; case RTM_DELTCLASS: - err = tclass_del_notify(net, cops, skb, n, q, cl); + err = tclass_del_notify(net, cops, skb, n, q, cl, extack); /* Unbind the class with flilters with 0 */ tc_bind_tclass(q, portid, clid, 0); goto out; diff --git a/net/sched/sch_atm.c b/net/sched/sch_atm.c index 007bd2d9f1ff..d0c9a57398fc 100644 --- a/net/sched/sch_atm.c +++ b/net/sched/sch_atm.c @@ -320,7 +320,8 @@ err_out: return error; } -static int atm_tc_delete(struct Qdisc *sch, unsigned long arg) +static int atm_tc_delete(struct Qdisc *sch, unsigned long arg, + struct netlink_ext_ack *extack) { struct atm_qdisc_data *p = qdisc_priv(sch); struct atm_flow_data *flow = (struct atm_flow_data *)arg; diff --git a/net/sched/sch_cbq.c b/net/sched/sch_cbq.c index 53d45e029c36..320b3d31fa97 100644 --- a/net/sched/sch_cbq.c +++ b/net/sched/sch_cbq.c @@ -1675,7 +1675,8 @@ failure: return err; } -static int cbq_delete(struct Qdisc *sch, unsigned long arg) +static int cbq_delete(struct Qdisc *sch, unsigned long arg, + struct netlink_ext_ack *extack) { struct cbq_sched_data *q = qdisc_priv(sch); struct cbq_class *cl = (struct cbq_class *)arg; diff --git a/net/sched/sch_drr.c b/net/sched/sch_drr.c index dde564670ad8..fc1e47069593 100644 --- a/net/sched/sch_drr.c +++ b/net/sched/sch_drr.c @@ -146,7 +146,8 @@ static void drr_destroy_class(struct Qdisc *sch, struct drr_class *cl) kfree(cl); } -static int drr_delete_class(struct Qdisc *sch, unsigned long arg) +static int drr_delete_class(struct Qdisc *sch, unsigned long arg, + struct netlink_ext_ack *extack) { struct drr_sched *q = qdisc_priv(sch); struct drr_class *cl = (struct drr_class *)arg; diff --git a/net/sched/sch_dsmark.c b/net/sched/sch_dsmark.c index 2b88710994d7..cd2748e2d4a2 100644 --- a/net/sched/sch_dsmark.c +++ b/net/sched/sch_dsmark.c @@ -150,7 +150,8 @@ errout: return err; } -static int dsmark_delete(struct Qdisc *sch, unsigned long arg) +static int dsmark_delete(struct Qdisc *sch, unsigned long arg, + struct netlink_ext_ack *extack) { struct dsmark_qdisc_data *p = qdisc_priv(sch); diff --git a/net/sched/sch_hfsc.c b/net/sched/sch_hfsc.c index d1902fca9844..bf0034c66e35 100644 --- a/net/sched/sch_hfsc.c +++ b/net/sched/sch_hfsc.c @@ -1090,7 +1090,8 @@ hfsc_destroy_class(struct Qdisc *sch, struct hfsc_class *cl) } static int -hfsc_delete_class(struct Qdisc *sch, unsigned long arg) +hfsc_delete_class(struct Qdisc *sch, unsigned long arg, + struct netlink_ext_ack *extack) { struct hfsc_sched *q = qdisc_priv(sch); struct hfsc_class *cl = (struct hfsc_class *)arg; diff --git a/net/sched/sch_htb.c b/net/sched/sch_htb.c index cd70dbcbd72f..dff3adf5a915 100644 --- a/net/sched/sch_htb.c +++ b/net/sched/sch_htb.c @@ -114,6 +114,7 @@ struct htb_class { * Written often fields */ struct gnet_stats_basic_packed bstats; + struct gnet_stats_basic_packed bstats_bias; struct tc_htb_xstats xstats; /* our special stats */ /* token bucket parameters */ @@ -174,6 +175,11 @@ struct htb_sched { int row_mask[TC_HTB_MAXDEPTH]; struct htb_level hlevel[TC_HTB_MAXDEPTH]; + + struct Qdisc **direct_qdiscs; + unsigned int num_direct_qdiscs; + + bool offload; }; /* find class in global hash table using given handle */ @@ -957,7 +963,7 @@ static void htb_reset(struct Qdisc *sch) if (cl->level) memset(&cl->inner, 0, sizeof(cl->inner)); else { - if (cl->leaf.q) + if (cl->leaf.q && !q->offload) qdisc_reset(cl->leaf.q); } cl->prio_activity = 0; @@ -980,6 +986,7 @@ static const struct nla_policy htb_policy[TCA_HTB_MAX + 1] = { [TCA_HTB_DIRECT_QLEN] = { .type = NLA_U32 }, [TCA_HTB_RATE64] = { .type = NLA_U64 }, [TCA_HTB_CEIL64] = { .type = NLA_U64 }, + [TCA_HTB_OFFLOAD] = { .type = NLA_FLAG }, }; static void htb_work_func(struct work_struct *work) @@ -992,12 +999,27 @@ static void htb_work_func(struct work_struct *work) rcu_read_unlock(); } +static void htb_set_lockdep_class_child(struct Qdisc *q) +{ + static struct lock_class_key child_key; + + lockdep_set_class(qdisc_lock(q), &child_key); +} + +static int htb_offload(struct net_device *dev, struct tc_htb_qopt_offload *opt) +{ + return dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_QDISC_HTB, opt); +} + static int htb_init(struct Qdisc *sch, struct nlattr *opt, struct netlink_ext_ack *extack) { + struct net_device *dev = qdisc_dev(sch); + struct tc_htb_qopt_offload offload_opt; struct htb_sched *q = qdisc_priv(sch); struct nlattr *tb[TCA_HTB_MAX + 1]; struct tc_htb_glob *gopt; + unsigned int ntx; int err; qdisc_watchdog_init(&q->watchdog, sch); @@ -1022,9 +1044,26 @@ static int htb_init(struct Qdisc *sch, struct nlattr *opt, if (gopt->version != HTB_VER >> 16) return -EINVAL; + q->offload = nla_get_flag(tb[TCA_HTB_OFFLOAD]); + + if (q->offload) { + if (sch->parent != TC_H_ROOT) + return -EOPNOTSUPP; + + if (!tc_can_offload(dev) || !dev->netdev_ops->ndo_setup_tc) + return -EOPNOTSUPP; + + q->num_direct_qdiscs = dev->real_num_tx_queues; + q->direct_qdiscs = kcalloc(q->num_direct_qdiscs, + sizeof(*q->direct_qdiscs), + GFP_KERNEL); + if (!q->direct_qdiscs) + return -ENOMEM; + } + err = qdisc_class_hash_init(&q->clhash); if (err < 0) - return err; + goto err_free_direct_qdiscs; qdisc_skb_head_init(&q->direct_queue); @@ -1037,7 +1076,107 @@ static int htb_init(struct Qdisc *sch, struct nlattr *opt, q->rate2quantum = 1; q->defcls = gopt->defcls; + if (!q->offload) + return 0; + + for (ntx = 0; ntx < q->num_direct_qdiscs; ntx++) { + struct netdev_queue *dev_queue = netdev_get_tx_queue(dev, ntx); + struct Qdisc *qdisc; + + qdisc = qdisc_create_dflt(dev_queue, &pfifo_qdisc_ops, + TC_H_MAKE(sch->handle, 0), extack); + if (!qdisc) { + err = -ENOMEM; + goto err_free_qdiscs; + } + + htb_set_lockdep_class_child(qdisc); + q->direct_qdiscs[ntx] = qdisc; + qdisc->flags |= TCQ_F_ONETXQUEUE | TCQ_F_NOPARENT; + } + + sch->flags |= TCQ_F_MQROOT; + + offload_opt = (struct tc_htb_qopt_offload) { + .command = TC_HTB_CREATE, + .parent_classid = TC_H_MAJ(sch->handle) >> 16, + .classid = TC_H_MIN(q->defcls), + .extack = extack, + }; + err = htb_offload(dev, &offload_opt); + if (err) + goto err_free_qdiscs; + return 0; + +err_free_qdiscs: + /* TC_HTB_CREATE call failed, avoid any further calls to the driver. */ + q->offload = false; + + for (ntx = 0; ntx < q->num_direct_qdiscs && q->direct_qdiscs[ntx]; + ntx++) + qdisc_put(q->direct_qdiscs[ntx]); + + qdisc_class_hash_destroy(&q->clhash); + /* Prevent use-after-free and double-free when htb_destroy gets called. + */ + q->clhash.hash = NULL; + q->clhash.hashsize = 0; + +err_free_direct_qdiscs: + kfree(q->direct_qdiscs); + q->direct_qdiscs = NULL; + return err; +} + +static void htb_attach_offload(struct Qdisc *sch) +{ + struct net_device *dev = qdisc_dev(sch); + struct htb_sched *q = qdisc_priv(sch); + unsigned int ntx; + + for (ntx = 0; ntx < q->num_direct_qdiscs; ntx++) { + struct Qdisc *old, *qdisc = q->direct_qdiscs[ntx]; + + old = dev_graft_qdisc(qdisc->dev_queue, qdisc); + qdisc_put(old); + qdisc_hash_add(qdisc, false); + } + for (ntx = q->num_direct_qdiscs; ntx < dev->num_tx_queues; ntx++) { + struct netdev_queue *dev_queue = netdev_get_tx_queue(dev, ntx); + struct Qdisc *old = dev_graft_qdisc(dev_queue, NULL); + + qdisc_put(old); + } + + kfree(q->direct_qdiscs); + q->direct_qdiscs = NULL; +} + +static void htb_attach_software(struct Qdisc *sch) +{ + struct net_device *dev = qdisc_dev(sch); + unsigned int ntx; + + /* Resemble qdisc_graft behavior. */ + for (ntx = 0; ntx < dev->num_tx_queues; ntx++) { + struct netdev_queue *dev_queue = netdev_get_tx_queue(dev, ntx); + struct Qdisc *old = dev_graft_qdisc(dev_queue, sch); + + qdisc_refcount_inc(sch); + + qdisc_put(old); + } +} + +static void htb_attach(struct Qdisc *sch) +{ + struct htb_sched *q = qdisc_priv(sch); + + if (q->offload) + htb_attach_offload(sch); + else + htb_attach_software(sch); } static int htb_dump(struct Qdisc *sch, struct sk_buff *skb) @@ -1046,6 +1185,11 @@ static int htb_dump(struct Qdisc *sch, struct sk_buff *skb) struct nlattr *nest; struct tc_htb_glob gopt; + if (q->offload) + sch->flags |= TCQ_F_OFFLOADED; + else + sch->flags &= ~TCQ_F_OFFLOADED; + sch->qstats.overlimits = q->overlimits; /* Its safe to not acquire qdisc lock. As we hold RTNL, * no change can happen on the qdisc parameters. @@ -1063,6 +1207,8 @@ static int htb_dump(struct Qdisc *sch, struct sk_buff *skb) if (nla_put(skb, TCA_HTB_INIT, sizeof(gopt), &gopt) || nla_put_u32(skb, TCA_HTB_DIRECT_QLEN, q->direct_qlen)) goto nla_put_failure; + if (q->offload && nla_put_flag(skb, TCA_HTB_OFFLOAD)) + goto nla_put_failure; return nla_nest_end(skb, nest); @@ -1075,6 +1221,7 @@ static int htb_dump_class(struct Qdisc *sch, unsigned long arg, struct sk_buff *skb, struct tcmsg *tcm) { struct htb_class *cl = (struct htb_class *)arg; + struct htb_sched *q = qdisc_priv(sch); struct nlattr *nest; struct tc_htb_opt opt; @@ -1101,6 +1248,8 @@ static int htb_dump_class(struct Qdisc *sch, unsigned long arg, opt.level = cl->level; if (nla_put(skb, TCA_HTB_PARMS, sizeof(opt), &opt)) goto nla_put_failure; + if (q->offload && nla_put_flag(skb, TCA_HTB_OFFLOAD)) + goto nla_put_failure; if ((cl->rate.rate_bytes_ps >= (1ULL << 32)) && nla_put_u64_64bit(skb, TCA_HTB_RATE64, cl->rate.rate_bytes_ps, TCA_HTB_PAD)) @@ -1117,10 +1266,39 @@ nla_put_failure: return -1; } +static void htb_offload_aggregate_stats(struct htb_sched *q, + struct htb_class *cl) +{ + struct htb_class *c; + unsigned int i; + + memset(&cl->bstats, 0, sizeof(cl->bstats)); + + for (i = 0; i < q->clhash.hashsize; i++) { + hlist_for_each_entry(c, &q->clhash.hash[i], common.hnode) { + struct htb_class *p = c; + + while (p && p->level < cl->level) + p = p->parent; + + if (p != cl) + continue; + + cl->bstats.bytes += c->bstats_bias.bytes; + cl->bstats.packets += c->bstats_bias.packets; + if (c->level == 0) { + cl->bstats.bytes += c->leaf.q->bstats.bytes; + cl->bstats.packets += c->leaf.q->bstats.packets; + } + } + } +} + static int htb_dump_class_stats(struct Qdisc *sch, unsigned long arg, struct gnet_dump *d) { struct htb_class *cl = (struct htb_class *)arg; + struct htb_sched *q = qdisc_priv(sch); struct gnet_stats_queue qs = { .drops = cl->drops, .overlimits = cl->overlimits, @@ -1135,6 +1313,19 @@ htb_dump_class_stats(struct Qdisc *sch, unsigned long arg, struct gnet_dump *d) cl->xstats.ctokens = clamp_t(s64, PSCHED_NS2TICKS(cl->ctokens), INT_MIN, INT_MAX); + if (q->offload) { + if (!cl->level) { + if (cl->leaf.q) + cl->bstats = cl->leaf.q->bstats; + else + memset(&cl->bstats, 0, sizeof(cl->bstats)); + cl->bstats.bytes += cl->bstats_bias.bytes; + cl->bstats.packets += cl->bstats_bias.packets; + } else { + htb_offload_aggregate_stats(q, cl); + } + } + if (gnet_stats_copy_basic(qdisc_root_sleeping_running(sch), d, NULL, &cl->bstats) < 0 || gnet_stats_copy_rate_est(d, &cl->rate_est) < 0 || @@ -1144,19 +1335,97 @@ htb_dump_class_stats(struct Qdisc *sch, unsigned long arg, struct gnet_dump *d) return gnet_stats_copy_app(d, &cl->xstats, sizeof(cl->xstats)); } +static struct netdev_queue * +htb_select_queue(struct Qdisc *sch, struct tcmsg *tcm) +{ + struct net_device *dev = qdisc_dev(sch); + struct tc_htb_qopt_offload offload_opt; + int err; + + offload_opt = (struct tc_htb_qopt_offload) { + .command = TC_HTB_LEAF_QUERY_QUEUE, + .classid = TC_H_MIN(tcm->tcm_parent), + }; + err = htb_offload(dev, &offload_opt); + if (err || offload_opt.qid >= dev->num_tx_queues) + return NULL; + return netdev_get_tx_queue(dev, offload_opt.qid); +} + +static struct Qdisc * +htb_graft_helper(struct netdev_queue *dev_queue, struct Qdisc *new_q) +{ + struct net_device *dev = dev_queue->dev; + struct Qdisc *old_q; + + if (dev->flags & IFF_UP) + dev_deactivate(dev); + old_q = dev_graft_qdisc(dev_queue, new_q); + if (new_q) + new_q->flags |= TCQ_F_ONETXQUEUE | TCQ_F_NOPARENT; + if (dev->flags & IFF_UP) + dev_activate(dev); + + return old_q; +} + +static void htb_offload_move_qdisc(struct Qdisc *sch, u16 qid_old, u16 qid_new) +{ + struct netdev_queue *queue_old, *queue_new; + struct net_device *dev = qdisc_dev(sch); + struct Qdisc *qdisc; + + queue_old = netdev_get_tx_queue(dev, qid_old); + queue_new = netdev_get_tx_queue(dev, qid_new); + + if (dev->flags & IFF_UP) + dev_deactivate(dev); + qdisc = dev_graft_qdisc(queue_old, NULL); + qdisc->dev_queue = queue_new; + qdisc = dev_graft_qdisc(queue_new, qdisc); + if (dev->flags & IFF_UP) + dev_activate(dev); + + WARN_ON(!(qdisc->flags & TCQ_F_BUILTIN)); +} + static int htb_graft(struct Qdisc *sch, unsigned long arg, struct Qdisc *new, struct Qdisc **old, struct netlink_ext_ack *extack) { + struct netdev_queue *dev_queue = sch->dev_queue; struct htb_class *cl = (struct htb_class *)arg; + struct htb_sched *q = qdisc_priv(sch); + struct Qdisc *old_q; if (cl->level) return -EINVAL; - if (new == NULL && - (new = qdisc_create_dflt(sch->dev_queue, &pfifo_qdisc_ops, - cl->common.classid, extack)) == NULL) - return -ENOBUFS; + + if (q->offload) { + dev_queue = new->dev_queue; + WARN_ON(dev_queue != cl->leaf.q->dev_queue); + } + + if (!new) { + new = qdisc_create_dflt(dev_queue, &pfifo_qdisc_ops, + cl->common.classid, extack); + if (!new) + return -ENOBUFS; + } + + if (q->offload) { + htb_set_lockdep_class_child(new); + /* One ref for cl->leaf.q, the other for dev_queue->qdisc. */ + qdisc_refcount_inc(new); + old_q = htb_graft_helper(dev_queue, new); + } *old = qdisc_replace(sch, new, &cl->leaf.q); + + if (q->offload) { + WARN_ON(old_q != *old); + qdisc_put(old_q); + } + return 0; } @@ -1184,9 +1453,10 @@ static inline int htb_parent_last_child(struct htb_class *cl) return 1; } -static void htb_parent_to_leaf(struct htb_sched *q, struct htb_class *cl, +static void htb_parent_to_leaf(struct Qdisc *sch, struct htb_class *cl, struct Qdisc *new_q) { + struct htb_sched *q = qdisc_priv(sch); struct htb_class *parent = cl->parent; WARN_ON(cl->level || !cl->leaf.q || cl->prio_activity); @@ -1204,6 +1474,76 @@ static void htb_parent_to_leaf(struct htb_sched *q, struct htb_class *cl, parent->cmode = HTB_CAN_SEND; } +static void htb_parent_to_leaf_offload(struct Qdisc *sch, + struct netdev_queue *dev_queue, + struct Qdisc *new_q) +{ + struct Qdisc *old_q; + + /* One ref for cl->leaf.q, the other for dev_queue->qdisc. */ + qdisc_refcount_inc(new_q); + old_q = htb_graft_helper(dev_queue, new_q); + WARN_ON(!(old_q->flags & TCQ_F_BUILTIN)); +} + +static int htb_destroy_class_offload(struct Qdisc *sch, struct htb_class *cl, + bool last_child, bool destroying, + struct netlink_ext_ack *extack) +{ + struct tc_htb_qopt_offload offload_opt; + struct Qdisc *q = cl->leaf.q; + struct Qdisc *old = NULL; + int err; + + if (cl->level) + return -EINVAL; + + WARN_ON(!q); + if (!destroying) { + /* On destroy of HTB, two cases are possible: + * 1. q is a normal qdisc, but q->dev_queue has noop qdisc. + * 2. q is a noop qdisc (for nodes that were inner), + * q->dev_queue is noop_netdev_queue. + */ + old = htb_graft_helper(q->dev_queue, NULL); + WARN_ON(!old); + WARN_ON(old != q); + } + + if (cl->parent) { + cl->parent->bstats_bias.bytes += q->bstats.bytes; + cl->parent->bstats_bias.packets += q->bstats.packets; + } + + offload_opt = (struct tc_htb_qopt_offload) { + .command = !last_child ? TC_HTB_LEAF_DEL : + destroying ? TC_HTB_LEAF_DEL_LAST_FORCE : + TC_HTB_LEAF_DEL_LAST, + .classid = cl->common.classid, + .extack = extack, + }; + err = htb_offload(qdisc_dev(sch), &offload_opt); + + if (!err || destroying) + qdisc_put(old); + else + htb_graft_helper(q->dev_queue, old); + + if (last_child) + return err; + + if (!err && offload_opt.moved_qid != 0) { + if (destroying) + q->dev_queue = netdev_get_tx_queue(qdisc_dev(sch), + offload_opt.qid); + else + htb_offload_move_qdisc(sch, offload_opt.moved_qid, + offload_opt.qid); + } + + return err; +} + static void htb_destroy_class(struct Qdisc *sch, struct htb_class *cl) { if (!cl->level) { @@ -1217,8 +1557,11 @@ static void htb_destroy_class(struct Qdisc *sch, struct htb_class *cl) static void htb_destroy(struct Qdisc *sch) { + struct net_device *dev = qdisc_dev(sch); + struct tc_htb_qopt_offload offload_opt; struct htb_sched *q = qdisc_priv(sch); struct hlist_node *next; + bool nonempty, changed; struct htb_class *cl; unsigned int i; @@ -1237,21 +1580,68 @@ static void htb_destroy(struct Qdisc *sch) cl->block = NULL; } } - for (i = 0; i < q->clhash.hashsize; i++) { - hlist_for_each_entry_safe(cl, next, &q->clhash.hash[i], - common.hnode) - htb_destroy_class(sch, cl); - } + + do { + nonempty = false; + changed = false; + for (i = 0; i < q->clhash.hashsize; i++) { + hlist_for_each_entry_safe(cl, next, &q->clhash.hash[i], + common.hnode) { + bool last_child; + + if (!q->offload) { + htb_destroy_class(sch, cl); + continue; + } + + nonempty = true; + + if (cl->level) + continue; + + changed = true; + + last_child = htb_parent_last_child(cl); + htb_destroy_class_offload(sch, cl, last_child, + true, NULL); + qdisc_class_hash_remove(&q->clhash, + &cl->common); + if (cl->parent) + cl->parent->children--; + if (last_child) + htb_parent_to_leaf(sch, cl, NULL); + htb_destroy_class(sch, cl); + } + } + } while (changed); + WARN_ON(nonempty); + qdisc_class_hash_destroy(&q->clhash); __qdisc_reset_queue(&q->direct_queue); + + if (!q->offload) + return; + + offload_opt = (struct tc_htb_qopt_offload) { + .command = TC_HTB_DESTROY, + }; + htb_offload(dev, &offload_opt); + + if (!q->direct_qdiscs) + return; + for (i = 0; i < q->num_direct_qdiscs && q->direct_qdiscs[i]; i++) + qdisc_put(q->direct_qdiscs[i]); + kfree(q->direct_qdiscs); } -static int htb_delete(struct Qdisc *sch, unsigned long arg) +static int htb_delete(struct Qdisc *sch, unsigned long arg, + struct netlink_ext_ack *extack) { struct htb_sched *q = qdisc_priv(sch); struct htb_class *cl = (struct htb_class *)arg; struct Qdisc *new_q = NULL; int last_child = 0; + int err; /* TODO: why don't allow to delete subtree ? references ? does * tc subsys guarantee us that in htb_destroy it holds no class @@ -1260,11 +1650,28 @@ static int htb_delete(struct Qdisc *sch, unsigned long arg) if (cl->children || cl->filter_cnt) return -EBUSY; - if (!cl->level && htb_parent_last_child(cl)) { - new_q = qdisc_create_dflt(sch->dev_queue, &pfifo_qdisc_ops, + if (!cl->level && htb_parent_last_child(cl)) + last_child = 1; + + if (q->offload) { + err = htb_destroy_class_offload(sch, cl, last_child, false, + extack); + if (err) + return err; + } + + if (last_child) { + struct netdev_queue *dev_queue; + + dev_queue = q->offload ? cl->leaf.q->dev_queue : sch->dev_queue; + new_q = qdisc_create_dflt(dev_queue, &pfifo_qdisc_ops, cl->parent->common.classid, NULL); - last_child = 1; + if (q->offload) { + if (new_q) + htb_set_lockdep_class_child(new_q); + htb_parent_to_leaf_offload(sch, dev_queue, new_q); + } } sch_tree_lock(sch); @@ -1285,7 +1692,7 @@ static int htb_delete(struct Qdisc *sch, unsigned long arg) &q->hlevel[cl->level].wait_pq); if (last_child) - htb_parent_to_leaf(q, cl, new_q); + htb_parent_to_leaf(sch, cl, new_q); sch_tree_unlock(sch); @@ -1300,9 +1707,11 @@ static int htb_change_class(struct Qdisc *sch, u32 classid, int err = -EINVAL; struct htb_sched *q = qdisc_priv(sch); struct htb_class *cl = (struct htb_class *)*arg, *parent; + struct tc_htb_qopt_offload offload_opt; struct nlattr *opt = tca[TCA_OPTIONS]; struct nlattr *tb[TCA_HTB_MAX + 1]; struct Qdisc *parent_qdisc = NULL; + struct netdev_queue *dev_queue; struct tc_htb_opt *hopt; u64 rate64, ceil64; int warn = 0; @@ -1335,8 +1744,12 @@ static int htb_change_class(struct Qdisc *sch, u32 classid, qdisc_put_rtab(qdisc_get_rtab(&hopt->ceil, tb[TCA_HTB_CTAB], NULL)); + rate64 = tb[TCA_HTB_RATE64] ? nla_get_u64(tb[TCA_HTB_RATE64]) : 0; + ceil64 = tb[TCA_HTB_CEIL64] ? nla_get_u64(tb[TCA_HTB_CEIL64]) : 0; + if (!cl) { /* new class */ - struct Qdisc *new_q; + struct net_device *dev = qdisc_dev(sch); + struct Qdisc *new_q, *old_q; int prio; struct { struct nlattr nla; @@ -1379,11 +1792,8 @@ static int htb_change_class(struct Qdisc *sch, u32 classid, NULL, qdisc_root_sleeping_running(sch), tca[TCA_RATE] ? : &est.nla); - if (err) { - tcf_block_put(cl->block); - kfree(cl); - goto failure; - } + if (err) + goto err_block_put; } cl->children = 0; @@ -1392,12 +1802,76 @@ static int htb_change_class(struct Qdisc *sch, u32 classid, for (prio = 0; prio < TC_HTB_NUMPRIO; prio++) RB_CLEAR_NODE(&cl->node[prio]); + cl->common.classid = classid; + + /* Make sure nothing interrupts us in between of two + * ndo_setup_tc calls. + */ + ASSERT_RTNL(); + /* create leaf qdisc early because it uses kmalloc(GFP_KERNEL) * so that can't be used inside of sch_tree_lock * -- thanks to Karlis Peisenieks */ - new_q = qdisc_create_dflt(sch->dev_queue, &pfifo_qdisc_ops, + if (!q->offload) { + dev_queue = sch->dev_queue; + } else if (!(parent && !parent->level)) { + /* Assign a dev_queue to this classid. */ + offload_opt = (struct tc_htb_qopt_offload) { + .command = TC_HTB_LEAF_ALLOC_QUEUE, + .classid = cl->common.classid, + .parent_classid = parent ? + TC_H_MIN(parent->common.classid) : + TC_HTB_CLASSID_ROOT, + .rate = max_t(u64, hopt->rate.rate, rate64), + .ceil = max_t(u64, hopt->ceil.rate, ceil64), + .extack = extack, + }; + err = htb_offload(dev, &offload_opt); + if (err) { + pr_err("htb: TC_HTB_LEAF_ALLOC_QUEUE failed with err = %d\n", + err); + goto err_kill_estimator; + } + dev_queue = netdev_get_tx_queue(dev, offload_opt.qid); + } else { /* First child. */ + dev_queue = parent->leaf.q->dev_queue; + old_q = htb_graft_helper(dev_queue, NULL); + WARN_ON(old_q != parent->leaf.q); + offload_opt = (struct tc_htb_qopt_offload) { + .command = TC_HTB_LEAF_TO_INNER, + .classid = cl->common.classid, + .parent_classid = + TC_H_MIN(parent->common.classid), + .rate = max_t(u64, hopt->rate.rate, rate64), + .ceil = max_t(u64, hopt->ceil.rate, ceil64), + .extack = extack, + }; + err = htb_offload(dev, &offload_opt); + if (err) { + pr_err("htb: TC_HTB_LEAF_TO_INNER failed with err = %d\n", + err); + htb_graft_helper(dev_queue, old_q); + goto err_kill_estimator; + } + parent->bstats_bias.bytes += old_q->bstats.bytes; + parent->bstats_bias.packets += old_q->bstats.packets; + qdisc_put(old_q); + } + new_q = qdisc_create_dflt(dev_queue, &pfifo_qdisc_ops, classid, NULL); + if (q->offload) { + if (new_q) { + htb_set_lockdep_class_child(new_q); + /* One ref for cl->leaf.q, the other for + * dev_queue->qdisc. + */ + qdisc_refcount_inc(new_q); + } + old_q = htb_graft_helper(dev_queue, new_q); + /* No qdisc_put needed. */ + WARN_ON(!(old_q->flags & TCQ_F_BUILTIN)); + } sch_tree_lock(sch); if (parent && !parent->level) { /* turn parent into inner node */ @@ -1415,10 +1889,10 @@ static int htb_change_class(struct Qdisc *sch, u32 classid, : TC_HTB_MAXDEPTH) - 1; memset(&parent->inner, 0, sizeof(parent->inner)); } + /* leaf (we) needs elementary qdisc */ cl->leaf.q = new_q ? new_q : &noop_qdisc; - cl->common.classid = classid; cl->parent = parent; /* set class to be in HTB_CAN_SEND state */ @@ -1444,12 +1918,30 @@ static int htb_change_class(struct Qdisc *sch, u32 classid, if (err) return err; } - sch_tree_lock(sch); - } - rate64 = tb[TCA_HTB_RATE64] ? nla_get_u64(tb[TCA_HTB_RATE64]) : 0; + if (q->offload) { + struct net_device *dev = qdisc_dev(sch); + + offload_opt = (struct tc_htb_qopt_offload) { + .command = TC_HTB_NODE_MODIFY, + .classid = cl->common.classid, + .rate = max_t(u64, hopt->rate.rate, rate64), + .ceil = max_t(u64, hopt->ceil.rate, ceil64), + .extack = extack, + }; + err = htb_offload(dev, &offload_opt); + if (err) + /* Estimator was replaced, and rollback may fail + * as well, so we don't try to recover it, and + * the estimator won't work property with the + * offload anyway, because bstats are updated + * only when the stats are queried. + */ + return err; + } - ceil64 = tb[TCA_HTB_CEIL64] ? nla_get_u64(tb[TCA_HTB_CEIL64]) : 0; + sch_tree_lock(sch); + } psched_ratecfg_precompute(&cl->rate, &hopt->rate, rate64); psched_ratecfg_precompute(&cl->ceil, &hopt->ceil, ceil64); @@ -1492,6 +1984,11 @@ static int htb_change_class(struct Qdisc *sch, u32 classid, *arg = (unsigned long)cl; return 0; +err_kill_estimator: + gen_kill_estimator(&cl->rate_est); +err_block_put: + tcf_block_put(cl->block); + kfree(cl); failure: return err; } @@ -1557,6 +2054,7 @@ static void htb_walk(struct Qdisc *sch, struct qdisc_walker *arg) } static const struct Qdisc_class_ops htb_class_ops = { + .select_queue = htb_select_queue, .graft = htb_graft, .leaf = htb_leaf, .qlen_notify = htb_qlen_notify, @@ -1579,6 +2077,7 @@ static struct Qdisc_ops htb_qdisc_ops __read_mostly = { .dequeue = htb_dequeue, .peek = qdisc_peek_dequeued, .init = htb_init, + .attach = htb_attach, .reset = htb_reset, .destroy = htb_destroy, .dump = htb_dump, diff --git a/net/sched/sch_qfq.c b/net/sched/sch_qfq.c index 6335230a971e..1db9d4a2ef5e 100644 --- a/net/sched/sch_qfq.c +++ b/net/sched/sch_qfq.c @@ -529,7 +529,8 @@ static void qfq_destroy_class(struct Qdisc *sch, struct qfq_class *cl) kfree(cl); } -static int qfq_delete_class(struct Qdisc *sch, unsigned long arg) +static int qfq_delete_class(struct Qdisc *sch, unsigned long arg, + struct netlink_ext_ack *extack) { struct qfq_sched *q = qdisc_priv(sch); struct qfq_class *cl = (struct qfq_class *)arg; diff --git a/net/sched/sch_sfb.c b/net/sched/sch_sfb.c index da047a37a3bf..dde829d4b9f8 100644 --- a/net/sched/sch_sfb.c +++ b/net/sched/sch_sfb.c @@ -649,7 +649,8 @@ static int sfb_change_class(struct Qdisc *sch, u32 classid, u32 parentid, return -ENOSYS; } -static int sfb_delete(struct Qdisc *sch, unsigned long cl) +static int sfb_delete(struct Qdisc *sch, unsigned long cl, + struct netlink_ext_ack *extack) { return -ENOSYS; } diff --git a/net/sched/sch_taprio.c b/net/sched/sch_taprio.c index 6f775275826a..8287894541e3 100644 --- a/net/sched/sch_taprio.c +++ b/net/sched/sch_taprio.c @@ -241,7 +241,7 @@ static struct sched_entry *find_entry_to_transmit(struct sk_buff *skb, /* Here, we are just trying to find out the * first available interval in the next cycle. */ - entry_available = 1; + entry_available = true; entry_found = entry; *interval_start = ktime_add_ns(curr_intv_start, cycle); *interval_end = ktime_add_ns(curr_intv_end, cycle); @@ -372,7 +372,7 @@ static long get_packet_txtime(struct sk_buff *skb, struct Qdisc *sch) packet_transmit_time = length_to_duration(q, len); do { - sched_changed = 0; + sched_changed = false; entry = find_entry_to_transmit(skb, sch, sched, admin, minimum_time, @@ -390,7 +390,7 @@ static long get_packet_txtime(struct sk_buff *skb, struct Qdisc *sch) if (admin && admin != sched && ktime_after(txtime, admin->base_time)) { sched = admin; - sched_changed = 1; + sched_changed = true; continue; } diff --git a/net/sctp/offload.c b/net/sctp/offload.c index ce281a9a2875..eb874e3c399a 100644 --- a/net/sctp/offload.c +++ b/net/sctp/offload.c @@ -68,7 +68,7 @@ static struct sk_buff *sctp_gso_segment(struct sk_buff *skb, goto out; } - segs = skb_segment(skb, features | NETIF_F_HW_CSUM | NETIF_F_SG); + segs = skb_segment(skb, (features | NETIF_F_HW_CSUM) & ~NETIF_F_SG); if (IS_ERR(segs)) goto out; diff --git a/net/socket.c b/net/socket.c index 33e8b6c4e1d3..7f0617ab5437 100644 --- a/net/socket.c +++ b/net/socket.c @@ -2126,6 +2126,9 @@ SYSCALL_DEFINE5(setsockopt, int, fd, int, level, int, optname, return __sys_setsockopt(fd, level, optname, optval, optlen); } +INDIRECT_CALLABLE_DECLARE(bool tcp_bpf_bypass_getsockopt(int level, + int optname)); + /* * Get a socket option. Because we don't know the option lengths we have * to pass a user mode parameter for the protocols to sort out. diff --git a/net/sunrpc/svc.c b/net/sunrpc/svc.c index 4187745887f0..61fb8a18552c 100644 --- a/net/sunrpc/svc.c +++ b/net/sunrpc/svc.c @@ -559,7 +559,7 @@ EXPORT_SYMBOL_GPL(svc_destroy); /* * Allocate an RPC server's buffer space. - * We allocate pages and place them in rq_argpages. + * We allocate pages and place them in rq_pages. */ static int svc_init_buffer(struct svc_rqst *rqstp, unsigned int size, int node) diff --git a/net/sunrpc/xprtrdma/svc_rdma.c b/net/sunrpc/xprtrdma/svc_rdma.c index 526da5d4710b..5bc20e9d09cd 100644 --- a/net/sunrpc/xprtrdma/svc_rdma.c +++ b/net/sunrpc/xprtrdma/svc_rdma.c @@ -62,51 +62,47 @@ static unsigned int max_max_requests = 16384; unsigned int svcrdma_max_req_size = RPCRDMA_DEF_INLINE_THRESH; static unsigned int min_max_inline = RPCRDMA_DEF_INLINE_THRESH; static unsigned int max_max_inline = RPCRDMA_MAX_INLINE_THRESH; +static unsigned int svcrdma_stat_unused; +static unsigned int zero; -atomic_t rdma_stat_recv; -atomic_t rdma_stat_read; -atomic_t rdma_stat_write; -atomic_t rdma_stat_sq_starve; -atomic_t rdma_stat_rq_starve; -atomic_t rdma_stat_rq_poll; -atomic_t rdma_stat_rq_prod; -atomic_t rdma_stat_sq_poll; -atomic_t rdma_stat_sq_prod; +struct percpu_counter svcrdma_stat_read; +struct percpu_counter svcrdma_stat_recv; +struct percpu_counter svcrdma_stat_sq_starve; +struct percpu_counter svcrdma_stat_write; -/* - * This function implements reading and resetting an atomic_t stat - * variable through read/write to a proc file. Any write to the file - * resets the associated statistic to zero. Any read returns it's - * current value. - */ -static int read_reset_stat(struct ctl_table *table, int write, - void *buffer, size_t *lenp, loff_t *ppos) +enum { + SVCRDMA_COUNTER_BUFSIZ = sizeof(unsigned long long), +}; + +static int svcrdma_counter_handler(struct ctl_table *table, int write, + void *buffer, size_t *lenp, loff_t *ppos) { - atomic_t *stat = (atomic_t *)table->data; - - if (!stat) - return -EINVAL; - - if (write) - atomic_set(stat, 0); - else { - char str_buf[32]; - int len = snprintf(str_buf, 32, "%d\n", atomic_read(stat)); - if (len >= 32) - return -EFAULT; - len = strlen(str_buf); - if (*ppos > len) { - *lenp = 0; - return 0; - } - len -= *ppos; - if (len > *lenp) - len = *lenp; - if (len) - memcpy(buffer, str_buf, len); - *lenp = len; - *ppos += len; + struct percpu_counter *stat = (struct percpu_counter *)table->data; + char tmp[SVCRDMA_COUNTER_BUFSIZ + 1]; + int len; + + if (write) { + percpu_counter_set(stat, 0); + return 0; } + + len = snprintf(tmp, SVCRDMA_COUNTER_BUFSIZ, "%lld\n", + percpu_counter_sum_positive(stat)); + if (len >= SVCRDMA_COUNTER_BUFSIZ) + return -EFAULT; + len = strlen(tmp); + if (*ppos > len) { + *lenp = 0; + return 0; + } + len -= *ppos; + if (len > *lenp) + len = *lenp; + if (len) + memcpy(buffer, tmp, len); + *lenp = len; + *ppos += len; + return 0; } @@ -142,66 +138,76 @@ static struct ctl_table svcrdma_parm_table[] = { { .procname = "rdma_stat_read", - .data = &rdma_stat_read, - .maxlen = sizeof(atomic_t), + .data = &svcrdma_stat_read, + .maxlen = SVCRDMA_COUNTER_BUFSIZ, .mode = 0644, - .proc_handler = read_reset_stat, + .proc_handler = svcrdma_counter_handler, }, { .procname = "rdma_stat_recv", - .data = &rdma_stat_recv, - .maxlen = sizeof(atomic_t), + .data = &svcrdma_stat_recv, + .maxlen = SVCRDMA_COUNTER_BUFSIZ, .mode = 0644, - .proc_handler = read_reset_stat, + .proc_handler = svcrdma_counter_handler, }, { .procname = "rdma_stat_write", - .data = &rdma_stat_write, - .maxlen = sizeof(atomic_t), + .data = &svcrdma_stat_write, + .maxlen = SVCRDMA_COUNTER_BUFSIZ, .mode = 0644, - .proc_handler = read_reset_stat, + .proc_handler = svcrdma_counter_handler, }, { .procname = "rdma_stat_sq_starve", - .data = &rdma_stat_sq_starve, - .maxlen = sizeof(atomic_t), + .data = &svcrdma_stat_sq_starve, + .maxlen = SVCRDMA_COUNTER_BUFSIZ, .mode = 0644, - .proc_handler = read_reset_stat, + .proc_handler = svcrdma_counter_handler, }, { .procname = "rdma_stat_rq_starve", - .data = &rdma_stat_rq_starve, - .maxlen = sizeof(atomic_t), + .data = &svcrdma_stat_unused, + .maxlen = sizeof(unsigned int), .mode = 0644, - .proc_handler = read_reset_stat, + .proc_handler = proc_dointvec_minmax, + .extra1 = &zero, + .extra2 = &zero, }, { .procname = "rdma_stat_rq_poll", - .data = &rdma_stat_rq_poll, - .maxlen = sizeof(atomic_t), + .data = &svcrdma_stat_unused, + .maxlen = sizeof(unsigned int), .mode = 0644, - .proc_handler = read_reset_stat, + .proc_handler = proc_dointvec_minmax, + .extra1 = &zero, + .extra2 = &zero, }, { .procname = "rdma_stat_rq_prod", - .data = &rdma_stat_rq_prod, - .maxlen = sizeof(atomic_t), + .data = &svcrdma_stat_unused, + .maxlen = sizeof(unsigned int), .mode = 0644, - .proc_handler = read_reset_stat, + .proc_handler = proc_dointvec_minmax, + .extra1 = &zero, + .extra2 = &zero, }, { .procname = "rdma_stat_sq_poll", - .data = &rdma_stat_sq_poll, - .maxlen = sizeof(atomic_t), + .data = &svcrdma_stat_unused, + .maxlen = sizeof(unsigned int), .mode = 0644, - .proc_handler = read_reset_stat, + .proc_handler = proc_dointvec_minmax, + .extra1 = &zero, + .extra2 = &zero, }, { .procname = "rdma_stat_sq_prod", - .data = &rdma_stat_sq_prod, - .maxlen = sizeof(atomic_t), + .data = &svcrdma_stat_unused, + .maxlen = sizeof(unsigned int), .mode = 0644, - .proc_handler = read_reset_stat, + .proc_handler = proc_dointvec_minmax, + .extra1 = &zero, + .extra2 = &zero, }, { }, }; @@ -224,27 +230,69 @@ static struct ctl_table svcrdma_root_table[] = { { }, }; +static void svc_rdma_proc_cleanup(void) +{ + if (!svcrdma_table_header) + return; + unregister_sysctl_table(svcrdma_table_header); + svcrdma_table_header = NULL; + + percpu_counter_destroy(&svcrdma_stat_write); + percpu_counter_destroy(&svcrdma_stat_sq_starve); + percpu_counter_destroy(&svcrdma_stat_recv); + percpu_counter_destroy(&svcrdma_stat_read); +} + +static int svc_rdma_proc_init(void) +{ + int rc; + + if (svcrdma_table_header) + return 0; + + rc = percpu_counter_init(&svcrdma_stat_read, 0, GFP_KERNEL); + if (rc) + goto out_err; + rc = percpu_counter_init(&svcrdma_stat_recv, 0, GFP_KERNEL); + if (rc) + goto out_err; + rc = percpu_counter_init(&svcrdma_stat_sq_starve, 0, GFP_KERNEL); + if (rc) + goto out_err; + rc = percpu_counter_init(&svcrdma_stat_write, 0, GFP_KERNEL); + if (rc) + goto out_err; + + svcrdma_table_header = register_sysctl_table(svcrdma_root_table); + return 0; + +out_err: + percpu_counter_destroy(&svcrdma_stat_sq_starve); + percpu_counter_destroy(&svcrdma_stat_recv); + percpu_counter_destroy(&svcrdma_stat_read); + return rc; +} + void svc_rdma_cleanup(void) { dprintk("SVCRDMA Module Removed, deregister RPC RDMA transport\n"); - if (svcrdma_table_header) { - unregister_sysctl_table(svcrdma_table_header); - svcrdma_table_header = NULL; - } svc_unreg_xprt_class(&svc_rdma_class); + svc_rdma_proc_cleanup(); } int svc_rdma_init(void) { + int rc; + dprintk("SVCRDMA Module Init, register RPC RDMA transport\n"); dprintk("\tsvcrdma_ord : %d\n", svcrdma_ord); dprintk("\tmax_requests : %u\n", svcrdma_max_requests); dprintk("\tmax_bc_requests : %u\n", svcrdma_max_bc_requests); dprintk("\tmax_inline : %d\n", svcrdma_max_req_size); - if (!svcrdma_table_header) - svcrdma_table_header = - register_sysctl_table(svcrdma_root_table); + rc = svc_rdma_proc_init(); + if (rc) + return rc; /* Register RDMA with the SVC transport switch */ svc_reg_xprt_class(&svc_rdma_class); diff --git a/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c b/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c index cbdb71247755..6d28f23ceb35 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c +++ b/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c @@ -266,33 +266,46 @@ void svc_rdma_release_rqst(struct svc_rqst *rqstp) svc_rdma_recv_ctxt_put(rdma, ctxt); } -static int __svc_rdma_post_recv(struct svcxprt_rdma *rdma, - struct svc_rdma_recv_ctxt *ctxt) +static bool svc_rdma_refresh_recvs(struct svcxprt_rdma *rdma, + unsigned int wanted, bool temp) { + const struct ib_recv_wr *bad_wr = NULL; + struct svc_rdma_recv_ctxt *ctxt; + struct ib_recv_wr *recv_chain; int ret; - trace_svcrdma_post_recv(ctxt); - ret = ib_post_recv(rdma->sc_qp, &ctxt->rc_recv_wr, NULL); + recv_chain = NULL; + while (wanted--) { + ctxt = svc_rdma_recv_ctxt_get(rdma); + if (!ctxt) + break; + + trace_svcrdma_post_recv(ctxt); + ctxt->rc_temp = temp; + ctxt->rc_recv_wr.next = recv_chain; + recv_chain = &ctxt->rc_recv_wr; + rdma->sc_pending_recvs++; + } + if (!recv_chain) + return false; + + ret = ib_post_recv(rdma->sc_qp, recv_chain, &bad_wr); if (ret) goto err_post; - return 0; + return true; err_post: - trace_svcrdma_rq_post_err(rdma, ret); - svc_rdma_recv_ctxt_put(rdma, ctxt); - return ret; -} - -static int svc_rdma_post_recv(struct svcxprt_rdma *rdma) -{ - struct svc_rdma_recv_ctxt *ctxt; + while (bad_wr) { + ctxt = container_of(bad_wr, struct svc_rdma_recv_ctxt, + rc_recv_wr); + bad_wr = bad_wr->next; + svc_rdma_recv_ctxt_put(rdma, ctxt); + } - if (test_bit(XPT_CLOSE, &rdma->sc_xprt.xpt_flags)) - return 0; - ctxt = svc_rdma_recv_ctxt_get(rdma); - if (!ctxt) - return -ENOMEM; - return __svc_rdma_post_recv(rdma, ctxt); + trace_svcrdma_rq_post_err(rdma, ret); + /* Since we're destroying the xprt, no need to reset + * sc_pending_recvs. */ + return false; } /** @@ -303,20 +316,7 @@ static int svc_rdma_post_recv(struct svcxprt_rdma *rdma) */ bool svc_rdma_post_recvs(struct svcxprt_rdma *rdma) { - struct svc_rdma_recv_ctxt *ctxt; - unsigned int i; - int ret; - - for (i = 0; i < rdma->sc_max_requests; i++) { - ctxt = svc_rdma_recv_ctxt_get(rdma); - if (!ctxt) - return false; - ctxt->rc_temp = true; - ret = __svc_rdma_post_recv(rdma, ctxt); - if (ret) - return false; - } - return true; + return svc_rdma_refresh_recvs(rdma, rdma->sc_max_requests, true); } /** @@ -324,8 +324,6 @@ bool svc_rdma_post_recvs(struct svcxprt_rdma *rdma) * @cq: Completion Queue context * @wc: Work Completion object * - * NB: The svc_xprt/svcxprt_rdma is pinned whenever it's possible that - * the Receive completion handler could be running. */ static void svc_rdma_wc_receive(struct ib_cq *cq, struct ib_wc *wc) { @@ -333,6 +331,8 @@ static void svc_rdma_wc_receive(struct ib_cq *cq, struct ib_wc *wc) struct ib_cqe *cqe = wc->wr_cqe; struct svc_rdma_recv_ctxt *ctxt; + rdma->sc_pending_recvs--; + /* WARNING: Only wc->wr_cqe and wc->status are reliable */ ctxt = container_of(cqe, struct svc_rdma_recv_ctxt, rc_cqe); @@ -340,14 +340,8 @@ static void svc_rdma_wc_receive(struct ib_cq *cq, struct ib_wc *wc) if (wc->status != IB_WC_SUCCESS) goto flushed; - if (svc_rdma_post_recv(rdma)) - goto post_err; - /* All wc fields are now known to be valid */ ctxt->rc_byte_len = wc->byte_len; - ib_dma_sync_single_for_cpu(rdma->sc_pd->device, - ctxt->rc_recv_sge.addr, - wc->byte_len, DMA_FROM_DEVICE); spin_lock(&rdma->sc_rq_dto_lock); list_add_tail(&ctxt->rc_list, &rdma->sc_rq_dto_q); @@ -356,11 +350,18 @@ static void svc_rdma_wc_receive(struct ib_cq *cq, struct ib_wc *wc) spin_unlock(&rdma->sc_rq_dto_lock); if (!test_bit(RDMAXPRT_CONN_PENDING, &rdma->sc_flags)) svc_xprt_enqueue(&rdma->sc_xprt); + + if (!test_bit(XPT_CLOSE, &rdma->sc_xprt.xpt_flags) && + rdma->sc_pending_recvs < rdma->sc_max_requests) + if (!svc_rdma_refresh_recvs(rdma, RPCRDMA_MAX_RECV_BATCH, + false)) + goto post_err; + return; flushed: -post_err: svc_rdma_recv_ctxt_put(rdma, ctxt); +post_err: set_bit(XPT_CLOSE, &rdma->sc_xprt.xpt_flags); svc_xprt_enqueue(&rdma->sc_xprt); } @@ -845,9 +846,11 @@ int svc_rdma_recvfrom(struct svc_rqst *rqstp) } list_del(&ctxt->rc_list); spin_unlock(&rdma_xprt->sc_rq_dto_lock); + percpu_counter_inc(&svcrdma_stat_recv); - atomic_inc(&rdma_stat_recv); - + ib_dma_sync_single_for_cpu(rdma_xprt->sc_pd->device, + ctxt->rc_recv_sge.addr, ctxt->rc_byte_len, + DMA_FROM_DEVICE); svc_rdma_build_arg_xdr(rqstp, ctxt); /* Prevent svc_xprt_release from releasing pages in rq_pages diff --git a/net/sunrpc/xprtrdma/svc_rdma_rw.c b/net/sunrpc/xprtrdma/svc_rdma_rw.c index 0b63e1321d74..693d139a8633 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_rw.c +++ b/net/sunrpc/xprtrdma/svc_rdma_rw.c @@ -364,6 +364,7 @@ static int svc_rdma_post_chunk_ctxt(struct svc_rdma_chunk_ctxt *cc) return 0; } + percpu_counter_inc(&svcrdma_stat_sq_starve); trace_svcrdma_sq_full(rdma); atomic_add(cc->cc_sqecount, &rdma->sc_sq_avail); wait_event(rdma->sc_send_wait, @@ -468,6 +469,7 @@ svc_rdma_build_writes(struct svc_rdma_write_info *info, DMA_TO_DEVICE); if (ret < 0) return -EIO; + percpu_counter_inc(&svcrdma_stat_write); list_add(&ctxt->rw_list, &cc->cc_rwctxts); cc->cc_sqecount += ret; @@ -718,6 +720,7 @@ static int svc_rdma_build_read_segment(struct svc_rdma_read_info *info, segment->rs_handle, DMA_FROM_DEVICE); if (ret < 0) return -EIO; + percpu_counter_inc(&svcrdma_stat_read); list_add(&ctxt->rw_list, &cc->cc_rwctxts); cc->cc_sqecount += ret; diff --git a/net/sunrpc/xprtrdma/svc_rdma_sendto.c b/net/sunrpc/xprtrdma/svc_rdma_sendto.c index 68af79d4f04f..52c759a8543e 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_sendto.c +++ b/net/sunrpc/xprtrdma/svc_rdma_sendto.c @@ -317,7 +317,7 @@ int svc_rdma_send(struct svcxprt_rdma *rdma, struct svc_rdma_send_ctxt *ctxt) /* If the SQ is full, wait until an SQ entry is available */ while (1) { if ((atomic_dec_return(&rdma->sc_sq_avail) < 0)) { - atomic_inc(&rdma_stat_sq_starve); + percpu_counter_inc(&svcrdma_stat_sq_starve); trace_svcrdma_sq_full(rdma); atomic_inc(&rdma->sc_sq_avail); wait_event(rdma->sc_send_wait, diff --git a/net/switchdev/Makefile b/net/switchdev/Makefile index bd69a3136e76..c5561d7f3a7c 100644 --- a/net/switchdev/Makefile +++ b/net/switchdev/Makefile @@ -3,4 +3,4 @@ # Makefile for the Switch device API # -obj-$(CONFIG_NET_SWITCHDEV) += switchdev.o +obj-y += switchdev.o diff --git a/net/switchdev/switchdev.c b/net/switchdev/switchdev.c index 2c1ffc9ba2eb..89a36db47ab4 100644 --- a/net/switchdev/switchdev.c +++ b/net/switchdev/switchdev.c @@ -101,19 +101,18 @@ static int switchdev_deferred_enqueue(struct net_device *dev, static int switchdev_port_attr_notify(enum switchdev_notifier_type nt, struct net_device *dev, const struct switchdev_attr *attr, - struct switchdev_trans *trans) + struct netlink_ext_ack *extack) { int err; int rc; struct switchdev_notifier_port_attr_info attr_info = { .attr = attr, - .trans = trans, .handled = false, }; rc = call_switchdev_blocking_notifiers(nt, dev, - &attr_info.info, NULL); + &attr_info.info, extack); err = notifier_to_errno(rc); if (err) { WARN_ON(!attr_info.handled); @@ -127,36 +126,11 @@ static int switchdev_port_attr_notify(enum switchdev_notifier_type nt, } static int switchdev_port_attr_set_now(struct net_device *dev, - const struct switchdev_attr *attr) + const struct switchdev_attr *attr, + struct netlink_ext_ack *extack) { - struct switchdev_trans trans; - int err; - - /* Phase I: prepare for attr set. Driver/device should fail - * here if there are going to be issues in the commit phase, - * such as lack of resources or support. The driver/device - * should reserve resources needed for the commit phase here, - * but should not commit the attr. - */ - - trans.ph_prepare = true; - err = switchdev_port_attr_notify(SWITCHDEV_PORT_ATTR_SET, dev, attr, - &trans); - if (err) - return err; - - /* Phase II: commit attr set. This cannot fail as a fault - * of driver/device. If it does, it's a bug in the driver/device - * because the driver said everythings was OK in phase I. - */ - - trans.ph_prepare = false; - err = switchdev_port_attr_notify(SWITCHDEV_PORT_ATTR_SET, dev, attr, - &trans); - WARN(err, "%s: Commit of attribute (id=%d) failed.\n", - dev->name, attr->id); - - return err; + return switchdev_port_attr_notify(SWITCHDEV_PORT_ATTR_SET, dev, attr, + extack); } static void switchdev_port_attr_set_deferred(struct net_device *dev, @@ -165,7 +139,7 @@ static void switchdev_port_attr_set_deferred(struct net_device *dev, const struct switchdev_attr *attr = data; int err; - err = switchdev_port_attr_set_now(dev, attr); + err = switchdev_port_attr_set_now(dev, attr, NULL); if (err && err != -EOPNOTSUPP) netdev_err(dev, "failed (err=%d) to set attribute (id=%d)\n", err, attr->id); @@ -185,21 +159,19 @@ static int switchdev_port_attr_set_defer(struct net_device *dev, * * @dev: port device * @attr: attribute to set - * - * Use a 2-phase prepare-commit transaction model to ensure - * system is not left in a partially updated state due to - * failure from driver/device. + * @extack: netlink extended ack, for error message propagation * * rtnl_lock must be held and must not be in atomic section, * in case SWITCHDEV_F_DEFER flag is not set. */ int switchdev_port_attr_set(struct net_device *dev, - const struct switchdev_attr *attr) + const struct switchdev_attr *attr, + struct netlink_ext_ack *extack) { if (attr->flags & SWITCHDEV_F_DEFER) return switchdev_port_attr_set_defer(dev, attr); ASSERT_RTNL(); - return switchdev_port_attr_set_now(dev, attr); + return switchdev_port_attr_set_now(dev, attr, extack); } EXPORT_SYMBOL_GPL(switchdev_port_attr_set); @@ -221,7 +193,6 @@ static size_t switchdev_obj_size(const struct switchdev_obj *obj) static int switchdev_port_obj_notify(enum switchdev_notifier_type nt, struct net_device *dev, const struct switchdev_obj *obj, - struct switchdev_trans *trans, struct netlink_ext_ack *extack) { int rc; @@ -229,7 +200,6 @@ static int switchdev_port_obj_notify(enum switchdev_notifier_type nt, struct switchdev_notifier_port_obj_info obj_info = { .obj = obj, - .trans = trans, .handled = false, }; @@ -244,48 +214,15 @@ static int switchdev_port_obj_notify(enum switchdev_notifier_type nt, return 0; } -static int switchdev_port_obj_add_now(struct net_device *dev, - const struct switchdev_obj *obj, - struct netlink_ext_ack *extack) -{ - struct switchdev_trans trans; - int err; - - ASSERT_RTNL(); - - /* Phase I: prepare for obj add. Driver/device should fail - * here if there are going to be issues in the commit phase, - * such as lack of resources or support. The driver/device - * should reserve resources needed for the commit phase here, - * but should not commit the obj. - */ - - trans.ph_prepare = true; - err = switchdev_port_obj_notify(SWITCHDEV_PORT_OBJ_ADD, - dev, obj, &trans, extack); - if (err) - return err; - - /* Phase II: commit obj add. This cannot fail as a fault - * of driver/device. If it does, it's a bug in the driver/device - * because the driver said everythings was OK in phase I. - */ - - trans.ph_prepare = false; - err = switchdev_port_obj_notify(SWITCHDEV_PORT_OBJ_ADD, - dev, obj, &trans, extack); - WARN(err, "%s: Commit of object (id=%d) failed.\n", dev->name, obj->id); - - return err; -} - static void switchdev_port_obj_add_deferred(struct net_device *dev, const void *data) { const struct switchdev_obj *obj = data; int err; - err = switchdev_port_obj_add_now(dev, obj, NULL); + ASSERT_RTNL(); + err = switchdev_port_obj_notify(SWITCHDEV_PORT_OBJ_ADD, + dev, obj, NULL); if (err && err != -EOPNOTSUPP) netdev_err(dev, "failed (err=%d) to add object (id=%d)\n", err, obj->id); @@ -307,10 +244,6 @@ static int switchdev_port_obj_add_defer(struct net_device *dev, * @obj: object to add * @extack: netlink extended ack * - * Use a 2-phase prepare-commit transaction model to ensure - * system is not left in a partially updated state due to - * failure from driver/device. - * * rtnl_lock must be held and must not be in atomic section, * in case SWITCHDEV_F_DEFER flag is not set. */ @@ -321,7 +254,8 @@ int switchdev_port_obj_add(struct net_device *dev, if (obj->flags & SWITCHDEV_F_DEFER) return switchdev_port_obj_add_defer(dev, obj); ASSERT_RTNL(); - return switchdev_port_obj_add_now(dev, obj, extack); + return switchdev_port_obj_notify(SWITCHDEV_PORT_OBJ_ADD, + dev, obj, extack); } EXPORT_SYMBOL_GPL(switchdev_port_obj_add); @@ -329,7 +263,7 @@ static int switchdev_port_obj_del_now(struct net_device *dev, const struct switchdev_obj *obj) { return switchdev_port_obj_notify(SWITCHDEV_PORT_OBJ_DEL, - dev, obj, NULL, NULL); + dev, obj, NULL); } static void switchdev_port_obj_del_deferred(struct net_device *dev, @@ -449,7 +383,6 @@ static int __switchdev_handle_port_obj_add(struct net_device *dev, bool (*check_cb)(const struct net_device *dev), int (*add_cb)(struct net_device *dev, const struct switchdev_obj *obj, - struct switchdev_trans *trans, struct netlink_ext_ack *extack)) { struct netlink_ext_ack *extack; @@ -460,8 +393,7 @@ static int __switchdev_handle_port_obj_add(struct net_device *dev, extack = switchdev_notifier_info_to_extack(&port_obj_info->info); if (check_cb(dev)) { - err = add_cb(dev, port_obj_info->obj, port_obj_info->trans, - extack); + err = add_cb(dev, port_obj_info->obj, extack); if (err != -EOPNOTSUPP) port_obj_info->handled = true; return err; @@ -492,7 +424,6 @@ int switchdev_handle_port_obj_add(struct net_device *dev, bool (*check_cb)(const struct net_device *dev), int (*add_cb)(struct net_device *dev, const struct switchdev_obj *obj, - struct switchdev_trans *trans, struct netlink_ext_ack *extack)) { int err; @@ -563,14 +494,17 @@ static int __switchdev_handle_port_attr_set(struct net_device *dev, bool (*check_cb)(const struct net_device *dev), int (*set_cb)(struct net_device *dev, const struct switchdev_attr *attr, - struct switchdev_trans *trans)) + struct netlink_ext_ack *extack)) { + struct netlink_ext_ack *extack; struct net_device *lower_dev; struct list_head *iter; int err = -EOPNOTSUPP; + extack = switchdev_notifier_info_to_extack(&port_attr_info->info); + if (check_cb(dev)) { - err = set_cb(dev, port_attr_info->attr, port_attr_info->trans); + err = set_cb(dev, port_attr_info->attr, extack); if (err != -EOPNOTSUPP) port_attr_info->handled = true; return err; @@ -601,7 +535,7 @@ int switchdev_handle_port_attr_set(struct net_device *dev, bool (*check_cb)(const struct net_device *dev), int (*set_cb)(struct net_device *dev, const struct switchdev_attr *attr, - struct switchdev_trans *trans)) + struct netlink_ext_ack *extack)) { int err; diff --git a/net/tipc/monitor.c b/net/tipc/monitor.c index 6dce2abf436e..48fac3b17e40 100644 --- a/net/tipc/monitor.c +++ b/net/tipc/monitor.c @@ -108,7 +108,7 @@ const int tipc_max_domain_size = sizeof(struct tipc_mon_domain); */ static int dom_rec_len(struct tipc_mon_domain *dom, u16 mcnt) { - return ((void *)&dom->members - (void *)dom) + (mcnt * sizeof(u32)); + return (offsetof(struct tipc_mon_domain, members)) + (mcnt * sizeof(u32)); } /* dom_size() : calculate size of own domain based on number of peers diff --git a/net/tipc/msg.c b/net/tipc/msg.c index 2aca86021df5..e9263280a2d4 100644 --- a/net/tipc/msg.c +++ b/net/tipc/msg.c @@ -117,10 +117,6 @@ struct sk_buff *tipc_msg_create(uint user, uint type, msg_set_origport(msg, oport); msg_set_destport(msg, dport); msg_set_errcode(msg, errcode); - if (hdr_sz > SHORT_H_SIZE) { - msg_set_orignode(msg, onode); - msg_set_destnode(msg, dnode); - } return buf; } diff --git a/net/tls/Kconfig b/net/tls/Kconfig index fa0724fd84b4..0cdc1f7b6b08 100644 --- a/net/tls/Kconfig +++ b/net/tls/Kconfig @@ -21,6 +21,7 @@ config TLS_DEVICE bool "Transport Layer Security HW offload" depends on TLS select SOCK_VALIDATE_XMIT + select SOCK_RX_QUEUE_MAPPING default n help Enable kernel support for HW offload of the TLS protocol. diff --git a/net/tls/tls_device.c b/net/tls/tls_device.c index f7fb7d2c1de1..d9cd229aa111 100644 --- a/net/tls/tls_device.c +++ b/net/tls/tls_device.c @@ -113,7 +113,7 @@ static struct net_device *get_netdev_for_sock(struct sock *sk) struct net_device *netdev = NULL; if (likely(dst)) { - netdev = dst->dev; + netdev = netdev_sk_get_lowest_dev(dst->dev, sk); dev_hold(netdev); } @@ -1329,6 +1329,8 @@ static int tls_dev_event(struct notifier_block *this, unsigned long event, switch (event) { case NETDEV_REGISTER: case NETDEV_FEAT_CHANGE: + if (netif_is_bond_master(dev)) + return NOTIFY_DONE; if ((dev->features & NETIF_F_HW_TLS_RX) && !dev->tlsdev_ops->tls_dev_resync) return NOTIFY_BAD; diff --git a/net/tls/tls_device_fallback.c b/net/tls/tls_device_fallback.c index d946817ed065..cacf040872c7 100644 --- a/net/tls/tls_device_fallback.c +++ b/net/tls/tls_device_fallback.c @@ -424,7 +424,7 @@ struct sk_buff *tls_validate_xmit_skb(struct sock *sk, struct net_device *dev, struct sk_buff *skb) { - if (dev == tls_get_ctx(sk)->netdev) + if (dev == tls_get_ctx(sk)->netdev || netif_is_bond_master(dev)) return skb; return tls_sw_fallback(sk, skb); diff --git a/net/wireless/chan.c b/net/wireless/chan.c index e4030f1fbc60..285b8076054b 100644 --- a/net/wireless/chan.c +++ b/net/wireless/chan.c @@ -1093,7 +1093,7 @@ static bool cfg80211_ir_permissive_chan(struct wiphy *wiphy, struct wireless_dev *wdev; struct cfg80211_registered_device *rdev = wiphy_to_rdev(wiphy); - ASSERT_RTNL(); + lockdep_assert_held(&rdev->wiphy.mtx); if (!IS_ENABLED(CONFIG_CFG80211_REG_RELAX_NO_IR) || !(wiphy->regulatory_flags & REGULATORY_ENABLE_RELAX_NO_IR)) @@ -1216,9 +1216,10 @@ bool cfg80211_reg_can_beacon_relax(struct wiphy *wiphy, struct cfg80211_chan_def *chandef, enum nl80211_iftype iftype) { + struct cfg80211_registered_device *rdev = wiphy_to_rdev(wiphy); bool check_no_ir; - ASSERT_RTNL(); + lockdep_assert_held(&rdev->wiphy.mtx); /* * Under certain conditions suggested by some regulatory bodies a diff --git a/net/wireless/core.c b/net/wireless/core.c index 4b1f35e976e7..a2785379df6e 100644 --- a/net/wireless/core.c +++ b/net/wireless/core.c @@ -222,7 +222,7 @@ static void cfg80211_rfkill_poll(struct rfkill *rfkill, void *data) void cfg80211_stop_p2p_device(struct cfg80211_registered_device *rdev, struct wireless_dev *wdev) { - ASSERT_RTNL(); + lockdep_assert_held(&rdev->wiphy.mtx); if (WARN_ON(wdev->iftype != NL80211_IFTYPE_P2P_DEVICE)) return; @@ -247,7 +247,7 @@ void cfg80211_stop_p2p_device(struct cfg80211_registered_device *rdev, void cfg80211_stop_nan(struct cfg80211_registered_device *rdev, struct wireless_dev *wdev) { - ASSERT_RTNL(); + lockdep_assert_held(&rdev->wiphy.mtx); if (WARN_ON(wdev->iftype != NL80211_IFTYPE_NAN)) return; @@ -273,7 +273,11 @@ void cfg80211_shutdown_all_interfaces(struct wiphy *wiphy) dev_close(wdev->netdev); continue; } + /* otherwise, check iftype */ + + wiphy_lock(wiphy); + switch (wdev->iftype) { case NL80211_IFTYPE_P2P_DEVICE: cfg80211_stop_p2p_device(rdev, wdev); @@ -284,6 +288,8 @@ void cfg80211_shutdown_all_interfaces(struct wiphy *wiphy) default: break; } + + wiphy_unlock(wiphy); } } EXPORT_SYMBOL_GPL(cfg80211_shutdown_all_interfaces); @@ -318,9 +324,9 @@ static void cfg80211_event_work(struct work_struct *work) rdev = container_of(work, struct cfg80211_registered_device, event_work); - rtnl_lock(); + wiphy_lock(&rdev->wiphy); cfg80211_process_rdev_events(rdev); - rtnl_unlock(); + wiphy_unlock(&rdev->wiphy); } void cfg80211_destroy_ifaces(struct cfg80211_registered_device *rdev) @@ -328,6 +334,7 @@ void cfg80211_destroy_ifaces(struct cfg80211_registered_device *rdev) struct wireless_dev *wdev, *tmp; ASSERT_RTNL(); + lockdep_assert_wiphy(&rdev->wiphy); list_for_each_entry_safe(wdev, tmp, &rdev->wiphy.wdev_list, list) { if (wdev->nl_owner_dead) @@ -343,7 +350,9 @@ static void cfg80211_destroy_iface_wk(struct work_struct *work) destroy_work); rtnl_lock(); + wiphy_lock(&rdev->wiphy); cfg80211_destroy_ifaces(rdev); + wiphy_unlock(&rdev->wiphy); rtnl_unlock(); } @@ -475,6 +484,7 @@ use_default_name: } } + mutex_init(&rdev->wiphy.mtx); INIT_LIST_HEAD(&rdev->wiphy.wdev_list); INIT_LIST_HEAD(&rdev->beacon_registrations); spin_lock_init(&rdev->beacon_registrations_lock); @@ -1007,15 +1017,16 @@ void wiphy_unregister(struct wiphy *wiphy) wait_event(rdev->dev_wait, ({ int __count; - rtnl_lock(); + wiphy_lock(&rdev->wiphy); __count = rdev->opencount; - rtnl_unlock(); + wiphy_unlock(&rdev->wiphy); __count == 0; })); if (rdev->rfkill) rfkill_unregister(rdev->rfkill); rtnl_lock(); + wiphy_lock(&rdev->wiphy); nl80211_notify_wiphy(rdev, NL80211_CMD_DEL_WIPHY); rdev->wiphy.registered = false; @@ -1038,6 +1049,7 @@ void wiphy_unregister(struct wiphy *wiphy) cfg80211_rdev_list_generation++; device_del(&rdev->wiphy.dev); + wiphy_unlock(&rdev->wiphy); rtnl_unlock(); flush_work(&rdev->scan_done_wk); @@ -1070,6 +1082,7 @@ void cfg80211_dev_free(struct cfg80211_registered_device *rdev) } list_for_each_entry_safe(scan, tmp, &rdev->bss_list, list) cfg80211_put_bss(&rdev->wiphy, &scan->pub); + mutex_destroy(&rdev->wiphy.mtx); kfree(rdev); } @@ -1094,19 +1107,28 @@ void cfg80211_cqm_config_free(struct wireless_dev *wdev) wdev->cqm_config = NULL; } -static void __cfg80211_unregister_wdev(struct wireless_dev *wdev, bool sync) +static void _cfg80211_unregister_wdev(struct wireless_dev *wdev, + bool unregister_netdev) { struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); ASSERT_RTNL(); + lockdep_assert_held(&rdev->wiphy.mtx); flush_work(&wdev->pmsr_free_wk); nl80211_notify_iface(rdev, wdev, NL80211_CMD_DEL_INTERFACE); + wdev->registered = false; + + if (wdev->netdev) { + sysfs_remove_link(&wdev->netdev->dev.kobj, "phy80211"); + if (unregister_netdev) + unregister_netdevice(wdev->netdev); + } + list_del_rcu(&wdev->list); - if (sync) - synchronize_rcu(); + synchronize_net(); rdev->devlist_generation++; cfg80211_mlme_purge_registrations(wdev); @@ -1131,14 +1153,23 @@ static void __cfg80211_unregister_wdev(struct wireless_dev *wdev, bool sync) flush_work(&wdev->disconnect_wk); cfg80211_cqm_config_free(wdev); + + /* + * Ensure that all events have been processed and + * freed. + */ + cfg80211_process_wdev_events(wdev); + + if (WARN_ON(wdev->current_bss)) { + cfg80211_unhold_bss(wdev->current_bss); + cfg80211_put_bss(wdev->wiphy, &wdev->current_bss->pub); + wdev->current_bss = NULL; + } } void cfg80211_unregister_wdev(struct wireless_dev *wdev) { - if (WARN_ON(wdev->netdev)) - return; - - __cfg80211_unregister_wdev(wdev, true); + _cfg80211_unregister_wdev(wdev, true); } EXPORT_SYMBOL(cfg80211_unregister_wdev); @@ -1149,7 +1180,7 @@ static const struct device_type wiphy_type = { void cfg80211_update_iface_num(struct cfg80211_registered_device *rdev, enum nl80211_iftype iftype, int num) { - ASSERT_RTNL(); + lockdep_assert_held(&rdev->wiphy.mtx); rdev->num_running_ifaces += num; if (iftype == NL80211_IFTYPE_MONITOR) @@ -1162,7 +1193,7 @@ void __cfg80211_leave(struct cfg80211_registered_device *rdev, struct net_device *dev = wdev->netdev; struct cfg80211_sched_scan_request *pos, *tmp; - ASSERT_RTNL(); + lockdep_assert_held(&rdev->wiphy.mtx); ASSERT_WDEV_LOCK(wdev); cfg80211_pmsr_wdev_down(wdev); @@ -1279,6 +1310,9 @@ void cfg80211_init_wdev(struct wireless_dev *wdev) void cfg80211_register_wdev(struct cfg80211_registered_device *rdev, struct wireless_dev *wdev) { + ASSERT_RTNL(); + lockdep_assert_held(&rdev->wiphy.mtx); + /* * We get here also when the interface changes network namespaces, * as it's registered into the new one, but we don't want it to @@ -1290,10 +1324,51 @@ void cfg80211_register_wdev(struct cfg80211_registered_device *rdev, wdev->identifier = ++rdev->wdev_id; list_add_rcu(&wdev->list, &rdev->wiphy.wdev_list); rdev->devlist_generation++; + wdev->registered = true; nl80211_notify_iface(rdev, wdev, NL80211_CMD_NEW_INTERFACE); } +int cfg80211_register_netdevice(struct net_device *dev) +{ + struct wireless_dev *wdev = dev->ieee80211_ptr; + struct cfg80211_registered_device *rdev; + int ret; + + ASSERT_RTNL(); + + if (WARN_ON(!wdev)) + return -EINVAL; + + rdev = wiphy_to_rdev(wdev->wiphy); + + lockdep_assert_held(&rdev->wiphy.mtx); + + /* we'll take care of this */ + wdev->registered = true; + wdev->registering = true; + ret = register_netdevice(dev); + if (ret) + goto out; + + if (sysfs_create_link(&dev->dev.kobj, &rdev->wiphy.dev.kobj, + "phy80211")) { + pr_err("failed to add phy80211 symlink to netdev!\n"); + unregister_netdevice(dev); + ret = -EINVAL; + goto out; + } + + cfg80211_register_wdev(rdev, wdev); + ret = 0; +out: + wdev->registering = false; + if (ret) + wdev->registered = false; + return ret; +} +EXPORT_SYMBOL(cfg80211_register_netdevice); + static int cfg80211_netdev_notifier_call(struct notifier_block *nb, unsigned long state, void *ptr) { @@ -1319,22 +1394,30 @@ static int cfg80211_netdev_notifier_call(struct notifier_block *nb, cfg80211_init_wdev(wdev); break; case NETDEV_REGISTER: + if (!wdev->registered) { + wiphy_lock(&rdev->wiphy); + cfg80211_register_wdev(rdev, wdev); + wiphy_unlock(&rdev->wiphy); + } + break; + case NETDEV_UNREGISTER: /* - * NB: cannot take rdev->mtx here because this may be - * called within code protected by it when interfaces - * are added with nl80211. + * It is possible to get NETDEV_UNREGISTER multiple times, + * so check wdev->registered. */ - if (sysfs_create_link(&dev->dev.kobj, &rdev->wiphy.dev.kobj, - "phy80211")) { - pr_err("failed to add phy80211 symlink to netdev!\n"); + if (wdev->registered && !wdev->registering) { + wiphy_lock(&rdev->wiphy); + _cfg80211_unregister_wdev(wdev, false); + wiphy_unlock(&rdev->wiphy); } - - cfg80211_register_wdev(rdev, wdev); break; case NETDEV_GOING_DOWN: + wiphy_lock(&rdev->wiphy); cfg80211_leave(rdev, wdev); + wiphy_unlock(&rdev->wiphy); break; case NETDEV_DOWN: + wiphy_lock(&rdev->wiphy); cfg80211_update_iface_num(rdev, wdev->iftype, -1); if (rdev->scan_req && rdev->scan_req->wdev == wdev) { if (WARN_ON(!rdev->scan_req->notified && @@ -1351,9 +1434,11 @@ static int cfg80211_netdev_notifier_call(struct notifier_block *nb, } rdev->opencount--; + wiphy_unlock(&rdev->wiphy); wake_up(&rdev->dev_wait); break; case NETDEV_UP: + wiphy_lock(&rdev->wiphy); cfg80211_update_iface_num(rdev, wdev->iftype, 1); wdev_lock(wdev); switch (wdev->iftype) { @@ -1400,38 +1485,7 @@ static int cfg80211_netdev_notifier_call(struct notifier_block *nb, /* assume this means it's off */ wdev->ps = false; } - break; - case NETDEV_UNREGISTER: - /* - * It is possible to get NETDEV_UNREGISTER - * multiple times. To detect that, check - * that the interface is still on the list - * of registered interfaces, and only then - * remove and clean it up. - */ - if (!list_empty(&wdev->list)) { - __cfg80211_unregister_wdev(wdev, false); - sysfs_remove_link(&dev->dev.kobj, "phy80211"); - } - /* - * synchronise (so that we won't find this netdev - * from other code any more) and then clear the list - * head so that the above code can safely check for - * !list_empty() to avoid double-cleanup. - */ - synchronize_rcu(); - INIT_LIST_HEAD(&wdev->list); - /* - * Ensure that all events have been processed and - * freed. - */ - cfg80211_process_wdev_events(wdev); - - if (WARN_ON(wdev->current_bss)) { - cfg80211_unhold_bss(wdev->current_bss); - cfg80211_put_bss(wdev->wiphy, &wdev->current_bss->pub); - wdev->current_bss = NULL; - } + wiphy_unlock(&rdev->wiphy); break; case NETDEV_PRE_UP: if (!cfg80211_iftype_allowed(wdev->wiphy, wdev->iftype, diff --git a/net/wireless/core.h b/net/wireless/core.h index 7df91f940212..a7d19b4b40ac 100644 --- a/net/wireless/core.h +++ b/net/wireless/core.h @@ -231,7 +231,7 @@ static inline void wdev_unlock(struct wireless_dev *wdev) static inline bool cfg80211_has_monitors_only(struct cfg80211_registered_device *rdev) { - ASSERT_RTNL(); + lockdep_assert_held(&rdev->wiphy.mtx); return rdev->num_running_ifaces == rdev->num_running_monitor_ifaces && rdev->num_running_ifaces > 0; diff --git a/net/wireless/debugfs.c b/net/wireless/debugfs.c index 76b845f68ac8..aab43469a2f0 100644 --- a/net/wireless/debugfs.c +++ b/net/wireless/debugfs.c @@ -73,8 +73,6 @@ static ssize_t ht40allow_map_read(struct file *file, if (!buf) return -ENOMEM; - rtnl_lock(); - for (band = 0; band < NUM_NL80211_BANDS; band++) { sband = wiphy->bands[band]; if (!sband) @@ -84,8 +82,6 @@ static ssize_t ht40allow_map_read(struct file *file, buf, buf_size, offset); } - rtnl_unlock(); - r = simple_read_from_buffer(user_buf, count, ppos, buf, offset); kfree(buf); diff --git a/net/wireless/ibss.c b/net/wireless/ibss.c index a0621bb76d8e..8f98e546becf 100644 --- a/net/wireless/ibss.c +++ b/net/wireless/ibss.c @@ -3,6 +3,7 @@ * Some IBSS support code for cfg80211. * * Copyright 2009 Johannes Berg <johannes@sipsolutions.net> + * Copyright (C) 2020-2021 Intel Corporation */ #include <linux/etherdevice.h> @@ -92,7 +93,7 @@ int __cfg80211_join_ibss(struct cfg80211_registered_device *rdev, struct wireless_dev *wdev = dev->ieee80211_ptr; int err; - ASSERT_RTNL(); + lockdep_assert_held(&rdev->wiphy.mtx); ASSERT_WDEV_LOCK(wdev); if (wdev->ssid_len) diff --git a/net/wireless/mlme.c b/net/wireless/mlme.c index e1e90761dc00..3aa69b375a10 100644 --- a/net/wireless/mlme.c +++ b/net/wireless/mlme.c @@ -450,7 +450,7 @@ static void cfg80211_mgmt_registrations_update(struct wireless_dev *wdev) struct cfg80211_mgmt_registration *reg; struct mgmt_frame_regs upd = {}; - ASSERT_RTNL(); + lockdep_assert_held(&rdev->wiphy.mtx); spin_lock_bh(&wdev->mgmt_registrations_lock); if (!wdev->mgmt_registrations_need_update) { @@ -492,10 +492,10 @@ void cfg80211_mgmt_registrations_update_wk(struct work_struct *wk) rdev = container_of(wk, struct cfg80211_registered_device, mgmt_registrations_update_wk); - rtnl_lock(); + wiphy_lock(&rdev->wiphy); list_for_each_entry(wdev, &rdev->wiphy.wdev_list, list) cfg80211_mgmt_registrations_update(wdev); - rtnl_unlock(); + wiphy_unlock(&rdev->wiphy); } int cfg80211_mlme_register_mgmt(struct wireless_dev *wdev, u32 snd_portid, diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 775d0c4d86c3..521d36bb0803 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -64,9 +64,9 @@ static const struct genl_multicast_group nl80211_mcgrps[] = { /* returns ERR_PTR values */ static struct wireless_dev * -__cfg80211_wdev_from_attrs(struct net *netns, struct nlattr **attrs) +__cfg80211_wdev_from_attrs(struct cfg80211_registered_device *rdev, + struct net *netns, struct nlattr **attrs) { - struct cfg80211_registered_device *rdev; struct wireless_dev *result = NULL; bool have_ifidx = attrs[NL80211_ATTR_IFINDEX]; bool have_wdev_id = attrs[NL80211_ATTR_WDEV]; @@ -74,8 +74,6 @@ __cfg80211_wdev_from_attrs(struct net *netns, struct nlattr **attrs) int wiphy_idx = -1; int ifidx = -1; - ASSERT_RTNL(); - if (!have_ifidx && !have_wdev_id) return ERR_PTR(-EINVAL); @@ -86,6 +84,28 @@ __cfg80211_wdev_from_attrs(struct net *netns, struct nlattr **attrs) wiphy_idx = wdev_id >> 32; } + if (rdev) { + struct wireless_dev *wdev; + + lockdep_assert_held(&rdev->wiphy.mtx); + + list_for_each_entry(wdev, &rdev->wiphy.wdev_list, list) { + if (have_ifidx && wdev->netdev && + wdev->netdev->ifindex == ifidx) { + result = wdev; + break; + } + if (have_wdev_id && wdev->identifier == (u32)wdev_id) { + result = wdev; + break; + } + } + + return result ?: ERR_PTR(-ENODEV); + } + + ASSERT_RTNL(); + list_for_each_entry(rdev, &cfg80211_rdev_list, list) { struct wireless_dev *wdev; @@ -732,6 +752,7 @@ static const struct nla_policy nl80211_policy[NUM_NL80211_ATTR] = { NL80211_SAE_PWE_BOTH), [NL80211_ATTR_RECONNECT_REQUESTED] = { .type = NLA_REJECT }, [NL80211_ATTR_SAR_SPEC] = NLA_POLICY_NESTED(sar_policy), + [NL80211_ATTR_DISABLE_HE] = { .type = NLA_FLAG }, }; /* policy for the key attributes */ @@ -914,22 +935,31 @@ int nl80211_prepare_wdev_dump(struct netlink_callback *cb, return err; } - *wdev = __cfg80211_wdev_from_attrs(sock_net(cb->skb->sk), + rtnl_lock(); + *wdev = __cfg80211_wdev_from_attrs(NULL, sock_net(cb->skb->sk), attrbuf); kfree(attrbuf); - if (IS_ERR(*wdev)) + if (IS_ERR(*wdev)) { + rtnl_unlock(); return PTR_ERR(*wdev); + } *rdev = wiphy_to_rdev((*wdev)->wiphy); + mutex_lock(&(*rdev)->wiphy.mtx); + rtnl_unlock(); /* 0 is the first index - add 1 to parse only once */ cb->args[0] = (*rdev)->wiphy_idx + 1; cb->args[1] = (*wdev)->identifier; } else { /* subtract the 1 again here */ - struct wiphy *wiphy = wiphy_idx_to_wiphy(cb->args[0] - 1); + struct wiphy *wiphy; struct wireless_dev *tmp; - if (!wiphy) + rtnl_lock(); + wiphy = wiphy_idx_to_wiphy(cb->args[0] - 1); + if (!wiphy) { + rtnl_unlock(); return -ENODEV; + } *rdev = wiphy_to_rdev(wiphy); *wdev = NULL; @@ -940,8 +970,12 @@ int nl80211_prepare_wdev_dump(struct netlink_callback *cb, } } - if (!*wdev) + if (!*wdev) { + rtnl_unlock(); return -ENODEV; + } + mutex_lock(&(*rdev)->wiphy.mtx); + rtnl_unlock(); } return 0; @@ -3141,7 +3175,7 @@ static int nl80211_set_channel(struct sk_buff *skb, struct genl_info *info) static int nl80211_set_wiphy(struct sk_buff *skb, struct genl_info *info) { - struct cfg80211_registered_device *rdev; + struct cfg80211_registered_device *rdev = NULL; struct net_device *netdev = NULL; struct wireless_dev *wdev; int result = 0, rem_txq_params = 0; @@ -3152,8 +3186,7 @@ static int nl80211_set_wiphy(struct sk_buff *skb, struct genl_info *info) u8 coverage_class = 0; u32 txq_limit = 0, txq_memory_limit = 0, txq_quantum = 0; - ASSERT_RTNL(); - + rtnl_lock(); /* * Try to find the wiphy and netdev. Normally this * function shouldn't need the netdev, but this is @@ -3177,14 +3210,18 @@ static int nl80211_set_wiphy(struct sk_buff *skb, struct genl_info *info) if (!netdev) { rdev = __cfg80211_rdev_from_attrs(genl_info_net(info), info->attrs); - if (IS_ERR(rdev)) + if (IS_ERR(rdev)) { + rtnl_unlock(); return PTR_ERR(rdev); + } wdev = NULL; netdev = NULL; result = 0; } else wdev = netdev->ieee80211_ptr; + wiphy_lock(&rdev->wiphy); + /* * end workaround code, by now the rdev is available * and locked, and wdev may or may not be NULL. @@ -3193,26 +3230,35 @@ static int nl80211_set_wiphy(struct sk_buff *skb, struct genl_info *info) if (info->attrs[NL80211_ATTR_WIPHY_NAME]) result = cfg80211_dev_rename( rdev, nla_data(info->attrs[NL80211_ATTR_WIPHY_NAME])); + rtnl_unlock(); if (result) - return result; + goto out; if (info->attrs[NL80211_ATTR_WIPHY_TXQ_PARAMS]) { struct ieee80211_txq_params txq_params; struct nlattr *tb[NL80211_TXQ_ATTR_MAX + 1]; - if (!rdev->ops->set_txq_params) - return -EOPNOTSUPP; + if (!rdev->ops->set_txq_params) { + result = -EOPNOTSUPP; + goto out; + } - if (!netdev) - return -EINVAL; + if (!netdev) { + result = -EINVAL; + goto out; + } if (netdev->ieee80211_ptr->iftype != NL80211_IFTYPE_AP && - netdev->ieee80211_ptr->iftype != NL80211_IFTYPE_P2P_GO) - return -EINVAL; + netdev->ieee80211_ptr->iftype != NL80211_IFTYPE_P2P_GO) { + result = -EINVAL; + goto out; + } - if (!netif_running(netdev)) - return -ENETDOWN; + if (!netif_running(netdev)) { + result = -ENETDOWN; + goto out; + } nla_for_each_nested(nl_txq_params, info->attrs[NL80211_ATTR_WIPHY_TXQ_PARAMS], @@ -3223,15 +3269,15 @@ static int nl80211_set_wiphy(struct sk_buff *skb, struct genl_info *info) txq_params_policy, info->extack); if (result) - return result; + goto out; result = parse_txq_params(tb, &txq_params); if (result) - return result; + goto out; result = rdev_set_txq_params(rdev, netdev, &txq_params); if (result) - return result; + goto out; } } @@ -3241,7 +3287,7 @@ static int nl80211_set_wiphy(struct sk_buff *skb, struct genl_info *info) nl80211_can_set_dev_channel(wdev) ? netdev : NULL, info); if (result) - return result; + goto out; } if (info->attrs[NL80211_ATTR_WIPHY_TX_POWER_SETTING]) { @@ -3252,15 +3298,19 @@ static int nl80211_set_wiphy(struct sk_buff *skb, struct genl_info *info) if (!(rdev->wiphy.features & NL80211_FEATURE_VIF_TXPOWER)) txp_wdev = NULL; - if (!rdev->ops->set_tx_power) - return -EOPNOTSUPP; + if (!rdev->ops->set_tx_power) { + result = -EOPNOTSUPP; + goto out; + } idx = NL80211_ATTR_WIPHY_TX_POWER_SETTING; type = nla_get_u32(info->attrs[idx]); if (!info->attrs[NL80211_ATTR_WIPHY_TX_POWER_LEVEL] && - (type != NL80211_TX_POWER_AUTOMATIC)) - return -EINVAL; + (type != NL80211_TX_POWER_AUTOMATIC)) { + result = -EINVAL; + goto out; + } if (type != NL80211_TX_POWER_AUTOMATIC) { idx = NL80211_ATTR_WIPHY_TX_POWER_LEVEL; @@ -3269,7 +3319,7 @@ static int nl80211_set_wiphy(struct sk_buff *skb, struct genl_info *info) result = rdev_set_tx_power(rdev, txp_wdev, type, mbm); if (result) - return result; + goto out; } if (info->attrs[NL80211_ATTR_WIPHY_ANTENNA_TX] && @@ -3278,8 +3328,10 @@ static int nl80211_set_wiphy(struct sk_buff *skb, struct genl_info *info) if ((!rdev->wiphy.available_antennas_tx && !rdev->wiphy.available_antennas_rx) || - !rdev->ops->set_antenna) - return -EOPNOTSUPP; + !rdev->ops->set_antenna) { + result = -EOPNOTSUPP; + goto out; + } tx_ant = nla_get_u32(info->attrs[NL80211_ATTR_WIPHY_ANTENNA_TX]); rx_ant = nla_get_u32(info->attrs[NL80211_ATTR_WIPHY_ANTENNA_RX]); @@ -3287,15 +3339,17 @@ static int nl80211_set_wiphy(struct sk_buff *skb, struct genl_info *info) /* reject antenna configurations which don't match the * available antenna masks, except for the "all" mask */ if ((~tx_ant && (tx_ant & ~rdev->wiphy.available_antennas_tx)) || - (~rx_ant && (rx_ant & ~rdev->wiphy.available_antennas_rx))) - return -EINVAL; + (~rx_ant && (rx_ant & ~rdev->wiphy.available_antennas_rx))) { + result = -EINVAL; + goto out; + } tx_ant = tx_ant & rdev->wiphy.available_antennas_tx; rx_ant = rx_ant & rdev->wiphy.available_antennas_rx; result = rdev_set_antenna(rdev, tx_ant, rx_ant); if (result) - return result; + goto out; } changed = 0; @@ -3317,8 +3371,10 @@ static int nl80211_set_wiphy(struct sk_buff *skb, struct genl_info *info) if (info->attrs[NL80211_ATTR_WIPHY_FRAG_THRESHOLD]) { frag_threshold = nla_get_u32( info->attrs[NL80211_ATTR_WIPHY_FRAG_THRESHOLD]); - if (frag_threshold < 256) - return -EINVAL; + if (frag_threshold < 256) { + result = -EINVAL; + goto out; + } if (frag_threshold != (u32) -1) { /* @@ -3339,8 +3395,10 @@ static int nl80211_set_wiphy(struct sk_buff *skb, struct genl_info *info) } if (info->attrs[NL80211_ATTR_WIPHY_COVERAGE_CLASS]) { - if (info->attrs[NL80211_ATTR_WIPHY_DYN_ACK]) - return -EINVAL; + if (info->attrs[NL80211_ATTR_WIPHY_DYN_ACK]) { + result = -EINVAL; + goto out; + } coverage_class = nla_get_u8( info->attrs[NL80211_ATTR_WIPHY_COVERAGE_CLASS]); @@ -3348,16 +3406,20 @@ static int nl80211_set_wiphy(struct sk_buff *skb, struct genl_info *info) } if (info->attrs[NL80211_ATTR_WIPHY_DYN_ACK]) { - if (!(rdev->wiphy.features & NL80211_FEATURE_ACKTO_ESTIMATION)) - return -EOPNOTSUPP; + if (!(rdev->wiphy.features & NL80211_FEATURE_ACKTO_ESTIMATION)) { + result = -EOPNOTSUPP; + goto out; + } changed |= WIPHY_PARAM_DYN_ACK; } if (info->attrs[NL80211_ATTR_TXQ_LIMIT]) { if (!wiphy_ext_feature_isset(&rdev->wiphy, - NL80211_EXT_FEATURE_TXQS)) - return -EOPNOTSUPP; + NL80211_EXT_FEATURE_TXQS)) { + result = -EOPNOTSUPP; + goto out; + } txq_limit = nla_get_u32( info->attrs[NL80211_ATTR_TXQ_LIMIT]); changed |= WIPHY_PARAM_TXQ_LIMIT; @@ -3365,8 +3427,10 @@ static int nl80211_set_wiphy(struct sk_buff *skb, struct genl_info *info) if (info->attrs[NL80211_ATTR_TXQ_MEMORY_LIMIT]) { if (!wiphy_ext_feature_isset(&rdev->wiphy, - NL80211_EXT_FEATURE_TXQS)) - return -EOPNOTSUPP; + NL80211_EXT_FEATURE_TXQS)) { + result = -EOPNOTSUPP; + goto out; + } txq_memory_limit = nla_get_u32( info->attrs[NL80211_ATTR_TXQ_MEMORY_LIMIT]); changed |= WIPHY_PARAM_TXQ_MEMORY_LIMIT; @@ -3374,8 +3438,10 @@ static int nl80211_set_wiphy(struct sk_buff *skb, struct genl_info *info) if (info->attrs[NL80211_ATTR_TXQ_QUANTUM]) { if (!wiphy_ext_feature_isset(&rdev->wiphy, - NL80211_EXT_FEATURE_TXQS)) - return -EOPNOTSUPP; + NL80211_EXT_FEATURE_TXQS)) { + result = -EOPNOTSUPP; + goto out; + } txq_quantum = nla_get_u32( info->attrs[NL80211_ATTR_TXQ_QUANTUM]); changed |= WIPHY_PARAM_TXQ_QUANTUM; @@ -3387,8 +3453,10 @@ static int nl80211_set_wiphy(struct sk_buff *skb, struct genl_info *info) u8 old_coverage_class; u32 old_txq_limit, old_txq_memory_limit, old_txq_quantum; - if (!rdev->ops->set_wiphy_params) - return -EOPNOTSUPP; + if (!rdev->ops->set_wiphy_params) { + result = -EOPNOTSUPP; + goto out; + } old_retry_short = rdev->wiphy.retry_short; old_retry_long = rdev->wiphy.retry_long; @@ -3426,10 +3494,15 @@ static int nl80211_set_wiphy(struct sk_buff *skb, struct genl_info *info) rdev->wiphy.txq_limit = old_txq_limit; rdev->wiphy.txq_memory_limit = old_txq_memory_limit; rdev->wiphy.txq_quantum = old_txq_quantum; - return result; + goto out; } } - return 0; + + result = 0; + +out: + wiphy_unlock(&rdev->wiphy); + return result; } static int nl80211_send_chandef(struct sk_buff *msg, @@ -3960,6 +4033,17 @@ static int nl80211_del_interface(struct sk_buff *skb, struct genl_info *info) return -EOPNOTSUPP; /* + * We hold RTNL, so this is safe, without RTNL opencount cannot + * reach 0, and thus the rdev cannot be deleted. + * + * We need to do it for the dev_close(), since that will call + * the netdev notifiers, and we need to acquire the mutex there + * but don't know if we get there from here or from some other + * place (e.g. "ip link set ... down"). + */ + mutex_unlock(&rdev->wiphy.mtx); + + /* * If we remove a wireless device without a netdev then clear * user_ptr[1] so that nl80211_post_doit won't dereference it * to check if it needs to do dev_put(). Otherwise it crashes @@ -3968,6 +4052,10 @@ static int nl80211_del_interface(struct sk_buff *skb, struct genl_info *info) */ if (!wdev->netdev) info->user_ptr[1] = NULL; + else + dev_close(wdev->netdev); + + mutex_lock(&rdev->wiphy.mtx); return rdev_del_virtual_intf(rdev, wdev); } @@ -5884,10 +5972,11 @@ static int nl80211_dump_station(struct sk_buff *skb, int sta_idx = cb->args[2]; int err; - rtnl_lock(); err = nl80211_prepare_wdev_dump(cb, &rdev, &wdev); if (err) - goto out_err; + return err; + /* nl80211_prepare_wdev_dump acquired it in the successful case */ + __acquire(&rdev->wiphy.mtx); if (!wdev->netdev) { err = -EINVAL; @@ -5922,7 +6011,7 @@ static int nl80211_dump_station(struct sk_buff *skb, cb->args[2] = sta_idx; err = skb->len; out_err: - rtnl_unlock(); + wiphy_unlock(&rdev->wiphy); return err; } @@ -6780,10 +6869,11 @@ static int nl80211_dump_mpath(struct sk_buff *skb, int path_idx = cb->args[2]; int err; - rtnl_lock(); err = nl80211_prepare_wdev_dump(cb, &rdev, &wdev); if (err) - goto out_err; + return err; + /* nl80211_prepare_wdev_dump acquired it in the successful case */ + __acquire(&rdev->wiphy.mtx); if (!rdev->ops->dump_mpath) { err = -EOPNOTSUPP; @@ -6816,7 +6906,7 @@ static int nl80211_dump_mpath(struct sk_buff *skb, cb->args[2] = path_idx; err = skb->len; out_err: - rtnl_unlock(); + wiphy_unlock(&rdev->wiphy); return err; } @@ -6979,10 +7069,11 @@ static int nl80211_dump_mpp(struct sk_buff *skb, int path_idx = cb->args[2]; int err; - rtnl_lock(); err = nl80211_prepare_wdev_dump(cb, &rdev, &wdev); if (err) - goto out_err; + return err; + /* nl80211_prepare_wdev_dump acquired it in the successful case */ + __acquire(&rdev->wiphy.mtx); if (!rdev->ops->dump_mpp) { err = -EOPNOTSUPP; @@ -7015,7 +7106,7 @@ static int nl80211_dump_mpp(struct sk_buff *skb, cb->args[2] = path_idx; err = skb->len; out_err: - rtnl_unlock(); + wiphy_unlock(&rdev->wiphy); return err; } @@ -7634,12 +7725,15 @@ static int nl80211_get_reg_do(struct sk_buff *skb, struct genl_info *info) if (!hdr) goto put_failure; + rtnl_lock(); + if (info->attrs[NL80211_ATTR_WIPHY]) { bool self_managed; rdev = cfg80211_get_dev_from_info(genl_info_net(info), info); if (IS_ERR(rdev)) { nlmsg_free(msg); + rtnl_unlock(); return PTR_ERR(rdev); } @@ -7651,6 +7745,7 @@ static int nl80211_get_reg_do(struct sk_buff *skb, struct genl_info *info) /* a self-managed-reg device must have a private regdom */ if (WARN_ON(!regdom && self_managed)) { nlmsg_free(msg); + rtnl_unlock(); return -EINVAL; } @@ -7675,11 +7770,13 @@ static int nl80211_get_reg_do(struct sk_buff *skb, struct genl_info *info) rcu_read_unlock(); genlmsg_end(msg, hdr); + rtnl_unlock(); return genlmsg_reply(msg, info); nla_put_failure_rcu: rcu_read_unlock(); nla_put_failure: + rtnl_unlock(); put_failure: nlmsg_free(msg); return -EMSGSIZE; @@ -7842,12 +7939,17 @@ static int nl80211_set_reg(struct sk_buff *skb, struct genl_info *info) return -EINVAL; } - if (!reg_is_valid_request(alpha2)) - return -EINVAL; + rtnl_lock(); + if (!reg_is_valid_request(alpha2)) { + r = -EINVAL; + goto out; + } rd = kzalloc(struct_size(rd, reg_rules, num_rules), GFP_KERNEL); - if (!rd) - return -ENOMEM; + if (!rd) { + r = -ENOMEM; + goto out; + } rd->n_reg_rules = num_rules; rd->alpha2[0] = alpha2[0]; @@ -7879,10 +7981,13 @@ static int nl80211_set_reg(struct sk_buff *skb, struct genl_info *info) } } + r = set_regdom(rd, REGD_SOURCE_CRDA); /* set_regdom takes ownership of rd */ - return set_regdom(rd, REGD_SOURCE_CRDA); + rd = NULL; bad_reg: kfree(rd); + out: + rtnl_unlock(); return r; } #endif /* CONFIG_CFG80211_CRDA_SUPPORT */ @@ -9050,10 +9155,7 @@ static int nl80211_channel_switch(struct sk_buff *skb, struct genl_info *info) struct net_device *dev = info->user_ptr[1]; struct wireless_dev *wdev = dev->ieee80211_ptr; struct cfg80211_csa_settings params; - /* csa_attrs is defined static to avoid waste of stack size - this - * function is called under RTNL lock, so this should not be a problem. - */ - static struct nlattr *csa_attrs[NL80211_ATTR_MAX+1]; + struct nlattr **csa_attrs = NULL; int err; bool need_new_beacon = false; bool need_handle_dfs_flag = true; @@ -9118,28 +9220,39 @@ static int nl80211_channel_switch(struct sk_buff *skb, struct genl_info *info) if (err) return err; + csa_attrs = kcalloc(NL80211_ATTR_MAX + 1, sizeof(*csa_attrs), + GFP_KERNEL); + if (!csa_attrs) + return -ENOMEM; + err = nla_parse_nested_deprecated(csa_attrs, NL80211_ATTR_MAX, info->attrs[NL80211_ATTR_CSA_IES], nl80211_policy, info->extack); if (err) - return err; + goto free; err = nl80211_parse_beacon(rdev, csa_attrs, ¶ms.beacon_csa); if (err) - return err; + goto free; - if (!csa_attrs[NL80211_ATTR_CNTDWN_OFFS_BEACON]) - return -EINVAL; + if (!csa_attrs[NL80211_ATTR_CNTDWN_OFFS_BEACON]) { + err = -EINVAL; + goto free; + } len = nla_len(csa_attrs[NL80211_ATTR_CNTDWN_OFFS_BEACON]); - if (!len || (len % sizeof(u16))) - return -EINVAL; + if (!len || (len % sizeof(u16))) { + err = -EINVAL; + goto free; + } params.n_counter_offsets_beacon = len / sizeof(u16); if (rdev->wiphy.max_num_csa_counters && (params.n_counter_offsets_beacon > - rdev->wiphy.max_num_csa_counters)) - return -EINVAL; + rdev->wiphy.max_num_csa_counters)) { + err = -EINVAL; + goto free; + } params.counter_offsets_beacon = nla_data(csa_attrs[NL80211_ATTR_CNTDWN_OFFS_BEACON]); @@ -9148,23 +9261,31 @@ static int nl80211_channel_switch(struct sk_buff *skb, struct genl_info *info) for (i = 0; i < params.n_counter_offsets_beacon; i++) { u16 offset = params.counter_offsets_beacon[i]; - if (offset >= params.beacon_csa.tail_len) - return -EINVAL; + if (offset >= params.beacon_csa.tail_len) { + err = -EINVAL; + goto free; + } - if (params.beacon_csa.tail[offset] != params.count) - return -EINVAL; + if (params.beacon_csa.tail[offset] != params.count) { + err = -EINVAL; + goto free; + } } if (csa_attrs[NL80211_ATTR_CNTDWN_OFFS_PRESP]) { len = nla_len(csa_attrs[NL80211_ATTR_CNTDWN_OFFS_PRESP]); - if (!len || (len % sizeof(u16))) - return -EINVAL; + if (!len || (len % sizeof(u16))) { + err = -EINVAL; + goto free; + } params.n_counter_offsets_presp = len / sizeof(u16); if (rdev->wiphy.max_num_csa_counters && (params.n_counter_offsets_presp > - rdev->wiphy.max_num_csa_counters)) - return -EINVAL; + rdev->wiphy.max_num_csa_counters)) { + err = -EINVAL; + goto free; + } params.counter_offsets_presp = nla_data(csa_attrs[NL80211_ATTR_CNTDWN_OFFS_PRESP]); @@ -9173,35 +9294,42 @@ static int nl80211_channel_switch(struct sk_buff *skb, struct genl_info *info) for (i = 0; i < params.n_counter_offsets_presp; i++) { u16 offset = params.counter_offsets_presp[i]; - if (offset >= params.beacon_csa.probe_resp_len) - return -EINVAL; + if (offset >= params.beacon_csa.probe_resp_len) { + err = -EINVAL; + goto free; + } if (params.beacon_csa.probe_resp[offset] != - params.count) - return -EINVAL; + params.count) { + err = -EINVAL; + goto free; + } } } skip_beacons: err = nl80211_parse_chandef(rdev, info, ¶ms.chandef); if (err) - return err; + goto free; if (!cfg80211_reg_can_beacon_relax(&rdev->wiphy, ¶ms.chandef, - wdev->iftype)) - return -EINVAL; + wdev->iftype)) { + err = -EINVAL; + goto free; + } err = cfg80211_chandef_dfs_required(wdev->wiphy, ¶ms.chandef, wdev->iftype); if (err < 0) - return err; + goto free; if (err > 0) { params.radar_required = true; if (need_handle_dfs_flag && !nla_get_flag(info->attrs[NL80211_ATTR_HANDLE_DFS])) { - return -EINVAL; + err = -EINVAL; + goto free; } } @@ -9212,6 +9340,8 @@ skip_beacons: err = rdev_channel_switch(rdev, dev, ¶ms); wdev_unlock(wdev); +free: + kfree(csa_attrs); return err; } @@ -9362,12 +9492,11 @@ static int nl80211_dump_scan(struct sk_buff *skb, struct netlink_callback *cb) int start = cb->args[2], idx = 0; int err; - rtnl_lock(); err = nl80211_prepare_wdev_dump(cb, &rdev, &wdev); - if (err) { - rtnl_unlock(); + if (err) return err; - } + /* nl80211_prepare_wdev_dump acquired it in the successful case */ + __acquire(&rdev->wiphy.mtx); wdev_lock(wdev); spin_lock_bh(&rdev->bss_lock); @@ -9398,7 +9527,7 @@ static int nl80211_dump_scan(struct sk_buff *skb, struct netlink_callback *cb) wdev_unlock(wdev); cb->args[2] = idx; - rtnl_unlock(); + wiphy_unlock(&rdev->wiphy); return skb->len; } @@ -9496,10 +9625,13 @@ static int nl80211_dump_survey(struct sk_buff *skb, struct netlink_callback *cb) if (!attrbuf) return -ENOMEM; - rtnl_lock(); res = nl80211_prepare_wdev_dump(cb, &rdev, &wdev); - if (res) - goto out_err; + if (res) { + kfree(attrbuf); + return res; + } + /* nl80211_prepare_wdev_dump acquired it in the successful case */ + __acquire(&rdev->wiphy.mtx); /* prepare_wdev_dump parsed the attributes */ radio_stats = attrbuf[NL80211_ATTR_SURVEY_RADIO_STATS]; @@ -9541,7 +9673,7 @@ static int nl80211_dump_survey(struct sk_buff *skb, struct netlink_callback *cb) res = skb->len; out_err: kfree(attrbuf); - rtnl_unlock(); + wiphy_unlock(&rdev->wiphy); return res; } @@ -9888,6 +10020,9 @@ static int nl80211_associate(struct sk_buff *skb, struct genl_info *info) if (nla_get_flag(info->attrs[NL80211_ATTR_DISABLE_VHT])) req.flags |= ASSOC_REQ_DISABLE_VHT; + if (nla_get_flag(info->attrs[NL80211_ATTR_DISABLE_HE])) + req.flags |= ASSOC_REQ_DISABLE_HE; + if (info->attrs[NL80211_ATTR_VHT_CAPABILITY_MASK]) memcpy(&req.vht_capa_mask, nla_data(info->attrs[NL80211_ATTR_VHT_CAPABILITY_MASK]), @@ -10403,10 +10538,14 @@ EXPORT_SYMBOL(__cfg80211_send_event_skb); static int nl80211_testmode_do(struct sk_buff *skb, struct genl_info *info) { struct cfg80211_registered_device *rdev = info->user_ptr[0]; - struct wireless_dev *wdev = - __cfg80211_wdev_from_attrs(genl_info_net(info), info->attrs); + struct wireless_dev *wdev; int err; + lockdep_assert_held(&rdev->wiphy.mtx); + + wdev = __cfg80211_wdev_from_attrs(rdev, genl_info_net(info), + info->attrs); + if (!rdev->ops->testmode_cmd) return -EOPNOTSUPP; @@ -10667,6 +10806,9 @@ static int nl80211_connect(struct sk_buff *skb, struct genl_info *info) if (nla_get_flag(info->attrs[NL80211_ATTR_DISABLE_VHT])) connect.flags |= ASSOC_REQ_DISABLE_VHT; + if (nla_get_flag(info->attrs[NL80211_ATTR_DISABLE_HE])) + connect.flags |= ASSOC_REQ_DISABLE_HE; + if (info->attrs[NL80211_ATTR_VHT_CAPABILITY_MASK]) memcpy(&connect.vht_capa_mask, nla_data(info->attrs[NL80211_ATTR_VHT_CAPABILITY_MASK]), @@ -13591,7 +13733,8 @@ static int nl80211_vendor_cmd(struct sk_buff *skb, struct genl_info *info) { struct cfg80211_registered_device *rdev = info->user_ptr[0]; struct wireless_dev *wdev = - __cfg80211_wdev_from_attrs(genl_info_net(info), info->attrs); + __cfg80211_wdev_from_attrs(rdev, genl_info_net(info), + info->attrs); int i, err; u32 vid, subcmd; @@ -13715,7 +13858,7 @@ static int nl80211_prepare_vendor_dump(struct sk_buff *skb, goto out; } - *wdev = __cfg80211_wdev_from_attrs(sock_net(skb->sk), attrbuf); + *wdev = __cfg80211_wdev_from_attrs(NULL, sock_net(skb->sk), attrbuf); if (IS_ERR(*wdev)) *wdev = NULL; @@ -14650,31 +14793,24 @@ bad_tid_conf: static int nl80211_pre_doit(const struct genl_ops *ops, struct sk_buff *skb, struct genl_info *info) { - struct cfg80211_registered_device *rdev; + struct cfg80211_registered_device *rdev = NULL; struct wireless_dev *wdev; struct net_device *dev; - bool rtnl = ops->internal_flags & NL80211_FLAG_NEED_RTNL; - - if (rtnl) - rtnl_lock(); + rtnl_lock(); if (ops->internal_flags & NL80211_FLAG_NEED_WIPHY) { rdev = cfg80211_get_dev_from_info(genl_info_net(info), info); if (IS_ERR(rdev)) { - if (rtnl) - rtnl_unlock(); + rtnl_unlock(); return PTR_ERR(rdev); } info->user_ptr[0] = rdev; } else if (ops->internal_flags & NL80211_FLAG_NEED_NETDEV || ops->internal_flags & NL80211_FLAG_NEED_WDEV) { - ASSERT_RTNL(); - - wdev = __cfg80211_wdev_from_attrs(genl_info_net(info), + wdev = __cfg80211_wdev_from_attrs(NULL, genl_info_net(info), info->attrs); if (IS_ERR(wdev)) { - if (rtnl) - rtnl_unlock(); + rtnl_unlock(); return PTR_ERR(wdev); } @@ -14683,8 +14819,7 @@ static int nl80211_pre_doit(const struct genl_ops *ops, struct sk_buff *skb, if (ops->internal_flags & NL80211_FLAG_NEED_NETDEV) { if (!dev) { - if (rtnl) - rtnl_unlock(); + rtnl_unlock(); return -EINVAL; } @@ -14695,8 +14830,7 @@ static int nl80211_pre_doit(const struct genl_ops *ops, struct sk_buff *skb, if (ops->internal_flags & NL80211_FLAG_CHECK_NETDEV_UP && !wdev_running(wdev)) { - if (rtnl) - rtnl_unlock(); + rtnl_unlock(); return -ENETDOWN; } @@ -14706,6 +14840,14 @@ static int nl80211_pre_doit(const struct genl_ops *ops, struct sk_buff *skb, info->user_ptr[0] = rdev; } + if (rdev) { + wiphy_lock(&rdev->wiphy); + /* we keep the mutex locked until post_doit */ + __release(&rdev->wiphy.mtx); + } + if (!(ops->internal_flags & NL80211_FLAG_NEED_RTNL)) + rtnl_unlock(); + return 0; } @@ -14723,6 +14865,14 @@ static void nl80211_post_doit(const struct genl_ops *ops, struct sk_buff *skb, } } + if (info->user_ptr[0]) { + struct cfg80211_registered_device *rdev = info->user_ptr[0]; + + /* we kept the mutex locked since pre_doit */ + __acquire(&rdev->wiphy.mtx); + wiphy_unlock(&rdev->wiphy); + } + if (ops->internal_flags & NL80211_FLAG_NEED_RTNL) rtnl_unlock(); @@ -14851,8 +15001,7 @@ static const struct genl_ops nl80211_ops[] = { .dumpit = nl80211_dump_wiphy, .done = nl80211_dump_wiphy_done, /* can be retrieved by unprivileged users */ - .internal_flags = NL80211_FLAG_NEED_WIPHY | - NL80211_FLAG_NEED_RTNL, + .internal_flags = NL80211_FLAG_NEED_WIPHY, }, }; @@ -14862,7 +15011,6 @@ static const struct genl_small_ops nl80211_small_ops[] = { .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = nl80211_set_wiphy, .flags = GENL_UNS_ADMIN_PERM, - .internal_flags = NL80211_FLAG_NEED_RTNL, }, { .cmd = NL80211_CMD_GET_INTERFACE, @@ -14870,8 +15018,7 @@ static const struct genl_small_ops nl80211_small_ops[] = { .doit = nl80211_get_interface, .dumpit = nl80211_dump_interface, /* can be retrieved by unprivileged users */ - .internal_flags = NL80211_FLAG_NEED_WDEV | - NL80211_FLAG_NEED_RTNL, + .internal_flags = NL80211_FLAG_NEED_WDEV, }, { .cmd = NL80211_CMD_SET_INTERFACE, @@ -14902,8 +15049,7 @@ static const struct genl_small_ops nl80211_small_ops[] = { .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = nl80211_get_key, .flags = GENL_UNS_ADMIN_PERM, - .internal_flags = NL80211_FLAG_NEED_NETDEV_UP | - NL80211_FLAG_NEED_RTNL, + .internal_flags = NL80211_FLAG_NEED_NETDEV_UP, }, { .cmd = NL80211_CMD_SET_KEY, @@ -14911,7 +15057,6 @@ static const struct genl_small_ops nl80211_small_ops[] = { .doit = nl80211_set_key, .flags = GENL_UNS_ADMIN_PERM, .internal_flags = NL80211_FLAG_NEED_NETDEV_UP | - NL80211_FLAG_NEED_RTNL | NL80211_FLAG_CLEAR_SKB, }, { @@ -14920,7 +15065,6 @@ static const struct genl_small_ops nl80211_small_ops[] = { .doit = nl80211_new_key, .flags = GENL_UNS_ADMIN_PERM, .internal_flags = NL80211_FLAG_NEED_NETDEV_UP | - NL80211_FLAG_NEED_RTNL | NL80211_FLAG_CLEAR_SKB, }, { @@ -14928,64 +15072,56 @@ static const struct genl_small_ops nl80211_small_ops[] = { .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = nl80211_del_key, .flags = GENL_UNS_ADMIN_PERM, - .internal_flags = NL80211_FLAG_NEED_NETDEV_UP | - NL80211_FLAG_NEED_RTNL, + .internal_flags = NL80211_FLAG_NEED_NETDEV_UP, }, { .cmd = NL80211_CMD_SET_BEACON, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .flags = GENL_UNS_ADMIN_PERM, .doit = nl80211_set_beacon, - .internal_flags = NL80211_FLAG_NEED_NETDEV_UP | - NL80211_FLAG_NEED_RTNL, + .internal_flags = NL80211_FLAG_NEED_NETDEV_UP, }, { .cmd = NL80211_CMD_START_AP, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .flags = GENL_UNS_ADMIN_PERM, .doit = nl80211_start_ap, - .internal_flags = NL80211_FLAG_NEED_NETDEV_UP | - NL80211_FLAG_NEED_RTNL, + .internal_flags = NL80211_FLAG_NEED_NETDEV_UP, }, { .cmd = NL80211_CMD_STOP_AP, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .flags = GENL_UNS_ADMIN_PERM, .doit = nl80211_stop_ap, - .internal_flags = NL80211_FLAG_NEED_NETDEV_UP | - NL80211_FLAG_NEED_RTNL, + .internal_flags = NL80211_FLAG_NEED_NETDEV_UP, }, { .cmd = NL80211_CMD_GET_STATION, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = nl80211_get_station, .dumpit = nl80211_dump_station, - .internal_flags = NL80211_FLAG_NEED_NETDEV | - NL80211_FLAG_NEED_RTNL, + .internal_flags = NL80211_FLAG_NEED_NETDEV, }, { .cmd = NL80211_CMD_SET_STATION, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = nl80211_set_station, .flags = GENL_UNS_ADMIN_PERM, - .internal_flags = NL80211_FLAG_NEED_NETDEV_UP | - NL80211_FLAG_NEED_RTNL, + .internal_flags = NL80211_FLAG_NEED_NETDEV_UP, }, { .cmd = NL80211_CMD_NEW_STATION, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = nl80211_new_station, .flags = GENL_UNS_ADMIN_PERM, - .internal_flags = NL80211_FLAG_NEED_NETDEV_UP | - NL80211_FLAG_NEED_RTNL, + .internal_flags = NL80211_FLAG_NEED_NETDEV_UP, }, { .cmd = NL80211_CMD_DEL_STATION, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = nl80211_del_station, .flags = GENL_UNS_ADMIN_PERM, - .internal_flags = NL80211_FLAG_NEED_NETDEV_UP | - NL80211_FLAG_NEED_RTNL, + .internal_flags = NL80211_FLAG_NEED_NETDEV_UP, }, { .cmd = NL80211_CMD_GET_MPATH, @@ -14993,8 +15129,7 @@ static const struct genl_small_ops nl80211_small_ops[] = { .doit = nl80211_get_mpath, .dumpit = nl80211_dump_mpath, .flags = GENL_UNS_ADMIN_PERM, - .internal_flags = NL80211_FLAG_NEED_NETDEV_UP | - NL80211_FLAG_NEED_RTNL, + .internal_flags = NL80211_FLAG_NEED_NETDEV_UP, }, { .cmd = NL80211_CMD_GET_MPP, @@ -15002,47 +15137,42 @@ static const struct genl_small_ops nl80211_small_ops[] = { .doit = nl80211_get_mpp, .dumpit = nl80211_dump_mpp, .flags = GENL_UNS_ADMIN_PERM, - .internal_flags = NL80211_FLAG_NEED_NETDEV_UP | - NL80211_FLAG_NEED_RTNL, + .internal_flags = NL80211_FLAG_NEED_NETDEV_UP, }, { .cmd = NL80211_CMD_SET_MPATH, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = nl80211_set_mpath, .flags = GENL_UNS_ADMIN_PERM, - .internal_flags = NL80211_FLAG_NEED_NETDEV_UP | - NL80211_FLAG_NEED_RTNL, + .internal_flags = NL80211_FLAG_NEED_NETDEV_UP, }, { .cmd = NL80211_CMD_NEW_MPATH, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = nl80211_new_mpath, .flags = GENL_UNS_ADMIN_PERM, - .internal_flags = NL80211_FLAG_NEED_NETDEV_UP | - NL80211_FLAG_NEED_RTNL, + .internal_flags = NL80211_FLAG_NEED_NETDEV_UP, }, { .cmd = NL80211_CMD_DEL_MPATH, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = nl80211_del_mpath, .flags = GENL_UNS_ADMIN_PERM, - .internal_flags = NL80211_FLAG_NEED_NETDEV_UP | - NL80211_FLAG_NEED_RTNL, + .internal_flags = NL80211_FLAG_NEED_NETDEV_UP, }, { .cmd = NL80211_CMD_SET_BSS, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = nl80211_set_bss, .flags = GENL_UNS_ADMIN_PERM, - .internal_flags = NL80211_FLAG_NEED_NETDEV_UP | - NL80211_FLAG_NEED_RTNL, + .internal_flags = NL80211_FLAG_NEED_NETDEV_UP, }, { .cmd = NL80211_CMD_GET_REG, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = nl80211_get_reg_do, .dumpit = nl80211_get_reg_dump, - .internal_flags = NL80211_FLAG_NEED_RTNL, + .internal_flags = 0, /* can be retrieved by unprivileged users */ }, #ifdef CONFIG_CFG80211_CRDA_SUPPORT @@ -15051,7 +15181,7 @@ static const struct genl_small_ops nl80211_small_ops[] = { .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = nl80211_set_reg, .flags = GENL_ADMIN_PERM, - .internal_flags = NL80211_FLAG_NEED_RTNL, + .internal_flags = 0, }, #endif { @@ -15071,32 +15201,28 @@ static const struct genl_small_ops nl80211_small_ops[] = { .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = nl80211_get_mesh_config, /* can be retrieved by unprivileged users */ - .internal_flags = NL80211_FLAG_NEED_NETDEV_UP | - NL80211_FLAG_NEED_RTNL, + .internal_flags = NL80211_FLAG_NEED_NETDEV_UP, }, { .cmd = NL80211_CMD_SET_MESH_CONFIG, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = nl80211_update_mesh_config, .flags = GENL_UNS_ADMIN_PERM, - .internal_flags = NL80211_FLAG_NEED_NETDEV_UP | - NL80211_FLAG_NEED_RTNL, + .internal_flags = NL80211_FLAG_NEED_NETDEV_UP, }, { .cmd = NL80211_CMD_TRIGGER_SCAN, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = nl80211_trigger_scan, .flags = GENL_UNS_ADMIN_PERM, - .internal_flags = NL80211_FLAG_NEED_WDEV_UP | - NL80211_FLAG_NEED_RTNL, + .internal_flags = NL80211_FLAG_NEED_WDEV_UP, }, { .cmd = NL80211_CMD_ABORT_SCAN, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = nl80211_abort_scan, .flags = GENL_UNS_ADMIN_PERM, - .internal_flags = NL80211_FLAG_NEED_WDEV_UP | - NL80211_FLAG_NEED_RTNL, + .internal_flags = NL80211_FLAG_NEED_WDEV_UP, }, { .cmd = NL80211_CMD_GET_SCAN, @@ -15108,16 +15234,14 @@ static const struct genl_small_ops nl80211_small_ops[] = { .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = nl80211_start_sched_scan, .flags = GENL_UNS_ADMIN_PERM, - .internal_flags = NL80211_FLAG_NEED_NETDEV_UP | - NL80211_FLAG_NEED_RTNL, + .internal_flags = NL80211_FLAG_NEED_NETDEV_UP, }, { .cmd = NL80211_CMD_STOP_SCHED_SCAN, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = nl80211_stop_sched_scan, .flags = GENL_UNS_ADMIN_PERM, - .internal_flags = NL80211_FLAG_NEED_NETDEV_UP | - NL80211_FLAG_NEED_RTNL, + .internal_flags = NL80211_FLAG_NEED_NETDEV_UP, }, { .cmd = NL80211_CMD_AUTHENTICATE, @@ -15125,7 +15249,7 @@ static const struct genl_small_ops nl80211_small_ops[] = { .doit = nl80211_authenticate, .flags = GENL_UNS_ADMIN_PERM, .internal_flags = NL80211_FLAG_NEED_NETDEV_UP | - NL80211_FLAG_NEED_RTNL | + 0 | NL80211_FLAG_CLEAR_SKB, }, { @@ -15134,7 +15258,7 @@ static const struct genl_small_ops nl80211_small_ops[] = { .doit = nl80211_associate, .flags = GENL_UNS_ADMIN_PERM, .internal_flags = NL80211_FLAG_NEED_NETDEV_UP | - NL80211_FLAG_NEED_RTNL | + 0 | NL80211_FLAG_CLEAR_SKB, }, { @@ -15142,32 +15266,28 @@ static const struct genl_small_ops nl80211_small_ops[] = { .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = nl80211_deauthenticate, .flags = GENL_UNS_ADMIN_PERM, - .internal_flags = NL80211_FLAG_NEED_NETDEV_UP | - NL80211_FLAG_NEED_RTNL, + .internal_flags = NL80211_FLAG_NEED_NETDEV_UP, }, { .cmd = NL80211_CMD_DISASSOCIATE, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = nl80211_disassociate, .flags = GENL_UNS_ADMIN_PERM, - .internal_flags = NL80211_FLAG_NEED_NETDEV_UP | - NL80211_FLAG_NEED_RTNL, + .internal_flags = NL80211_FLAG_NEED_NETDEV_UP, }, { .cmd = NL80211_CMD_JOIN_IBSS, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = nl80211_join_ibss, .flags = GENL_UNS_ADMIN_PERM, - .internal_flags = NL80211_FLAG_NEED_NETDEV_UP | - NL80211_FLAG_NEED_RTNL, + .internal_flags = NL80211_FLAG_NEED_NETDEV_UP, }, { .cmd = NL80211_CMD_LEAVE_IBSS, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = nl80211_leave_ibss, .flags = GENL_UNS_ADMIN_PERM, - .internal_flags = NL80211_FLAG_NEED_NETDEV_UP | - NL80211_FLAG_NEED_RTNL, + .internal_flags = NL80211_FLAG_NEED_NETDEV_UP, }, #ifdef CONFIG_NL80211_TESTMODE { @@ -15176,8 +15296,7 @@ static const struct genl_small_ops nl80211_small_ops[] = { .doit = nl80211_testmode_do, .dumpit = nl80211_testmode_dump, .flags = GENL_UNS_ADMIN_PERM, - .internal_flags = NL80211_FLAG_NEED_WIPHY | - NL80211_FLAG_NEED_RTNL, + .internal_flags = NL80211_FLAG_NEED_WIPHY, }, #endif { @@ -15186,7 +15305,7 @@ static const struct genl_small_ops nl80211_small_ops[] = { .doit = nl80211_connect, .flags = GENL_UNS_ADMIN_PERM, .internal_flags = NL80211_FLAG_NEED_NETDEV_UP | - NL80211_FLAG_NEED_RTNL | + 0 | NL80211_FLAG_CLEAR_SKB, }, { @@ -15195,7 +15314,7 @@ static const struct genl_small_ops nl80211_small_ops[] = { .doit = nl80211_update_connect_params, .flags = GENL_ADMIN_PERM, .internal_flags = NL80211_FLAG_NEED_NETDEV_UP | - NL80211_FLAG_NEED_RTNL | + 0 | NL80211_FLAG_CLEAR_SKB, }, { @@ -15203,16 +15322,14 @@ static const struct genl_small_ops nl80211_small_ops[] = { .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = nl80211_disconnect, .flags = GENL_UNS_ADMIN_PERM, - .internal_flags = NL80211_FLAG_NEED_NETDEV_UP | - NL80211_FLAG_NEED_RTNL, + .internal_flags = NL80211_FLAG_NEED_NETDEV_UP, }, { .cmd = NL80211_CMD_SET_WIPHY_NETNS, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = nl80211_wiphy_netns, .flags = GENL_UNS_ADMIN_PERM, - .internal_flags = NL80211_FLAG_NEED_WIPHY | - NL80211_FLAG_NEED_RTNL, + .internal_flags = NL80211_FLAG_NEED_WIPHY, }, { .cmd = NL80211_CMD_GET_SURVEY, @@ -15225,7 +15342,7 @@ static const struct genl_small_ops nl80211_small_ops[] = { .doit = nl80211_setdel_pmksa, .flags = GENL_UNS_ADMIN_PERM, .internal_flags = NL80211_FLAG_NEED_NETDEV_UP | - NL80211_FLAG_NEED_RTNL | + 0 | NL80211_FLAG_CLEAR_SKB, }, { @@ -15233,128 +15350,112 @@ static const struct genl_small_ops nl80211_small_ops[] = { .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = nl80211_setdel_pmksa, .flags = GENL_UNS_ADMIN_PERM, - .internal_flags = NL80211_FLAG_NEED_NETDEV_UP | - NL80211_FLAG_NEED_RTNL, + .internal_flags = NL80211_FLAG_NEED_NETDEV_UP, }, { .cmd = NL80211_CMD_FLUSH_PMKSA, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = nl80211_flush_pmksa, .flags = GENL_UNS_ADMIN_PERM, - .internal_flags = NL80211_FLAG_NEED_NETDEV_UP | - NL80211_FLAG_NEED_RTNL, + .internal_flags = NL80211_FLAG_NEED_NETDEV_UP, }, { .cmd = NL80211_CMD_REMAIN_ON_CHANNEL, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = nl80211_remain_on_channel, .flags = GENL_UNS_ADMIN_PERM, - .internal_flags = NL80211_FLAG_NEED_WDEV_UP | - NL80211_FLAG_NEED_RTNL, + .internal_flags = NL80211_FLAG_NEED_WDEV_UP, }, { .cmd = NL80211_CMD_CANCEL_REMAIN_ON_CHANNEL, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = nl80211_cancel_remain_on_channel, .flags = GENL_UNS_ADMIN_PERM, - .internal_flags = NL80211_FLAG_NEED_WDEV_UP | - NL80211_FLAG_NEED_RTNL, + .internal_flags = NL80211_FLAG_NEED_WDEV_UP, }, { .cmd = NL80211_CMD_SET_TX_BITRATE_MASK, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = nl80211_set_tx_bitrate_mask, .flags = GENL_UNS_ADMIN_PERM, - .internal_flags = NL80211_FLAG_NEED_NETDEV | - NL80211_FLAG_NEED_RTNL, + .internal_flags = NL80211_FLAG_NEED_NETDEV, }, { .cmd = NL80211_CMD_REGISTER_FRAME, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = nl80211_register_mgmt, .flags = GENL_UNS_ADMIN_PERM, - .internal_flags = NL80211_FLAG_NEED_WDEV | - NL80211_FLAG_NEED_RTNL, + .internal_flags = NL80211_FLAG_NEED_WDEV, }, { .cmd = NL80211_CMD_FRAME, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = nl80211_tx_mgmt, .flags = GENL_UNS_ADMIN_PERM, - .internal_flags = NL80211_FLAG_NEED_WDEV_UP | - NL80211_FLAG_NEED_RTNL, + .internal_flags = NL80211_FLAG_NEED_WDEV_UP, }, { .cmd = NL80211_CMD_FRAME_WAIT_CANCEL, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = nl80211_tx_mgmt_cancel_wait, .flags = GENL_UNS_ADMIN_PERM, - .internal_flags = NL80211_FLAG_NEED_WDEV_UP | - NL80211_FLAG_NEED_RTNL, + .internal_flags = NL80211_FLAG_NEED_WDEV_UP, }, { .cmd = NL80211_CMD_SET_POWER_SAVE, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = nl80211_set_power_save, .flags = GENL_UNS_ADMIN_PERM, - .internal_flags = NL80211_FLAG_NEED_NETDEV | - NL80211_FLAG_NEED_RTNL, + .internal_flags = NL80211_FLAG_NEED_NETDEV, }, { .cmd = NL80211_CMD_GET_POWER_SAVE, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = nl80211_get_power_save, /* can be retrieved by unprivileged users */ - .internal_flags = NL80211_FLAG_NEED_NETDEV | - NL80211_FLAG_NEED_RTNL, + .internal_flags = NL80211_FLAG_NEED_NETDEV, }, { .cmd = NL80211_CMD_SET_CQM, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = nl80211_set_cqm, .flags = GENL_UNS_ADMIN_PERM, - .internal_flags = NL80211_FLAG_NEED_NETDEV | - NL80211_FLAG_NEED_RTNL, + .internal_flags = NL80211_FLAG_NEED_NETDEV, }, { .cmd = NL80211_CMD_SET_CHANNEL, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = nl80211_set_channel, .flags = GENL_UNS_ADMIN_PERM, - .internal_flags = NL80211_FLAG_NEED_NETDEV | - NL80211_FLAG_NEED_RTNL, + .internal_flags = NL80211_FLAG_NEED_NETDEV, }, { .cmd = NL80211_CMD_JOIN_MESH, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = nl80211_join_mesh, .flags = GENL_UNS_ADMIN_PERM, - .internal_flags = NL80211_FLAG_NEED_NETDEV_UP | - NL80211_FLAG_NEED_RTNL, + .internal_flags = NL80211_FLAG_NEED_NETDEV_UP, }, { .cmd = NL80211_CMD_LEAVE_MESH, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = nl80211_leave_mesh, .flags = GENL_UNS_ADMIN_PERM, - .internal_flags = NL80211_FLAG_NEED_NETDEV_UP | - NL80211_FLAG_NEED_RTNL, + .internal_flags = NL80211_FLAG_NEED_NETDEV_UP, }, { .cmd = NL80211_CMD_JOIN_OCB, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = nl80211_join_ocb, .flags = GENL_UNS_ADMIN_PERM, - .internal_flags = NL80211_FLAG_NEED_NETDEV_UP | - NL80211_FLAG_NEED_RTNL, + .internal_flags = NL80211_FLAG_NEED_NETDEV_UP, }, { .cmd = NL80211_CMD_LEAVE_OCB, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = nl80211_leave_ocb, .flags = GENL_UNS_ADMIN_PERM, - .internal_flags = NL80211_FLAG_NEED_NETDEV_UP | - NL80211_FLAG_NEED_RTNL, + .internal_flags = NL80211_FLAG_NEED_NETDEV_UP, }, #ifdef CONFIG_PM { @@ -15362,16 +15463,14 @@ static const struct genl_small_ops nl80211_small_ops[] = { .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = nl80211_get_wowlan, /* can be retrieved by unprivileged users */ - .internal_flags = NL80211_FLAG_NEED_WIPHY | - NL80211_FLAG_NEED_RTNL, + .internal_flags = NL80211_FLAG_NEED_WIPHY, }, { .cmd = NL80211_CMD_SET_WOWLAN, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = nl80211_set_wowlan, .flags = GENL_UNS_ADMIN_PERM, - .internal_flags = NL80211_FLAG_NEED_WIPHY | - NL80211_FLAG_NEED_RTNL, + .internal_flags = NL80211_FLAG_NEED_WIPHY, }, #endif { @@ -15380,7 +15479,7 @@ static const struct genl_small_ops nl80211_small_ops[] = { .doit = nl80211_set_rekey_data, .flags = GENL_UNS_ADMIN_PERM, .internal_flags = NL80211_FLAG_NEED_NETDEV_UP | - NL80211_FLAG_NEED_RTNL | + 0 | NL80211_FLAG_CLEAR_SKB, }, { @@ -15388,48 +15487,42 @@ static const struct genl_small_ops nl80211_small_ops[] = { .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = nl80211_tdls_mgmt, .flags = GENL_UNS_ADMIN_PERM, - .internal_flags = NL80211_FLAG_NEED_NETDEV_UP | - NL80211_FLAG_NEED_RTNL, + .internal_flags = NL80211_FLAG_NEED_NETDEV_UP, }, { .cmd = NL80211_CMD_TDLS_OPER, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = nl80211_tdls_oper, .flags = GENL_UNS_ADMIN_PERM, - .internal_flags = NL80211_FLAG_NEED_NETDEV_UP | - NL80211_FLAG_NEED_RTNL, + .internal_flags = NL80211_FLAG_NEED_NETDEV_UP, }, { .cmd = NL80211_CMD_UNEXPECTED_FRAME, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = nl80211_register_unexpected_frame, .flags = GENL_UNS_ADMIN_PERM, - .internal_flags = NL80211_FLAG_NEED_NETDEV | - NL80211_FLAG_NEED_RTNL, + .internal_flags = NL80211_FLAG_NEED_NETDEV, }, { .cmd = NL80211_CMD_PROBE_CLIENT, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = nl80211_probe_client, .flags = GENL_UNS_ADMIN_PERM, - .internal_flags = NL80211_FLAG_NEED_NETDEV_UP | - NL80211_FLAG_NEED_RTNL, + .internal_flags = NL80211_FLAG_NEED_NETDEV_UP, }, { .cmd = NL80211_CMD_REGISTER_BEACONS, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = nl80211_register_beacons, .flags = GENL_UNS_ADMIN_PERM, - .internal_flags = NL80211_FLAG_NEED_WIPHY | - NL80211_FLAG_NEED_RTNL, + .internal_flags = NL80211_FLAG_NEED_WIPHY, }, { .cmd = NL80211_CMD_SET_NOACK_MAP, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = nl80211_set_noack_map, .flags = GENL_UNS_ADMIN_PERM, - .internal_flags = NL80211_FLAG_NEED_NETDEV | - NL80211_FLAG_NEED_RTNL, + .internal_flags = NL80211_FLAG_NEED_NETDEV, }, { .cmd = NL80211_CMD_START_P2P_DEVICE, @@ -15468,48 +15561,42 @@ static const struct genl_small_ops nl80211_small_ops[] = { .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = nl80211_nan_add_func, .flags = GENL_ADMIN_PERM, - .internal_flags = NL80211_FLAG_NEED_WDEV_UP | - NL80211_FLAG_NEED_RTNL, + .internal_flags = NL80211_FLAG_NEED_WDEV_UP, }, { .cmd = NL80211_CMD_DEL_NAN_FUNCTION, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = nl80211_nan_del_func, .flags = GENL_ADMIN_PERM, - .internal_flags = NL80211_FLAG_NEED_WDEV_UP | - NL80211_FLAG_NEED_RTNL, + .internal_flags = NL80211_FLAG_NEED_WDEV_UP, }, { .cmd = NL80211_CMD_CHANGE_NAN_CONFIG, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = nl80211_nan_change_config, .flags = GENL_ADMIN_PERM, - .internal_flags = NL80211_FLAG_NEED_WDEV_UP | - NL80211_FLAG_NEED_RTNL, + .internal_flags = NL80211_FLAG_NEED_WDEV_UP, }, { .cmd = NL80211_CMD_SET_MCAST_RATE, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = nl80211_set_mcast_rate, .flags = GENL_UNS_ADMIN_PERM, - .internal_flags = NL80211_FLAG_NEED_NETDEV | - NL80211_FLAG_NEED_RTNL, + .internal_flags = NL80211_FLAG_NEED_NETDEV, }, { .cmd = NL80211_CMD_SET_MAC_ACL, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = nl80211_set_mac_acl, .flags = GENL_UNS_ADMIN_PERM, - .internal_flags = NL80211_FLAG_NEED_NETDEV | - NL80211_FLAG_NEED_RTNL, + .internal_flags = NL80211_FLAG_NEED_NETDEV, }, { .cmd = NL80211_CMD_RADAR_DETECT, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = nl80211_start_radar_detection, .flags = GENL_UNS_ADMIN_PERM, - .internal_flags = NL80211_FLAG_NEED_NETDEV_UP | - NL80211_FLAG_NEED_RTNL, + .internal_flags = NL80211_FLAG_NEED_NETDEV_UP, }, { .cmd = NL80211_CMD_GET_PROTOCOL_FEATURES, @@ -15521,47 +15608,41 @@ static const struct genl_small_ops nl80211_small_ops[] = { .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = nl80211_update_ft_ies, .flags = GENL_UNS_ADMIN_PERM, - .internal_flags = NL80211_FLAG_NEED_NETDEV_UP | - NL80211_FLAG_NEED_RTNL, + .internal_flags = NL80211_FLAG_NEED_NETDEV_UP, }, { .cmd = NL80211_CMD_CRIT_PROTOCOL_START, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = nl80211_crit_protocol_start, .flags = GENL_UNS_ADMIN_PERM, - .internal_flags = NL80211_FLAG_NEED_WDEV_UP | - NL80211_FLAG_NEED_RTNL, + .internal_flags = NL80211_FLAG_NEED_WDEV_UP, }, { .cmd = NL80211_CMD_CRIT_PROTOCOL_STOP, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = nl80211_crit_protocol_stop, .flags = GENL_UNS_ADMIN_PERM, - .internal_flags = NL80211_FLAG_NEED_WDEV_UP | - NL80211_FLAG_NEED_RTNL, + .internal_flags = NL80211_FLAG_NEED_WDEV_UP, }, { .cmd = NL80211_CMD_GET_COALESCE, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = nl80211_get_coalesce, - .internal_flags = NL80211_FLAG_NEED_WIPHY | - NL80211_FLAG_NEED_RTNL, + .internal_flags = NL80211_FLAG_NEED_WIPHY, }, { .cmd = NL80211_CMD_SET_COALESCE, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = nl80211_set_coalesce, .flags = GENL_UNS_ADMIN_PERM, - .internal_flags = NL80211_FLAG_NEED_WIPHY | - NL80211_FLAG_NEED_RTNL, + .internal_flags = NL80211_FLAG_NEED_WIPHY, }, { .cmd = NL80211_CMD_CHANNEL_SWITCH, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = nl80211_channel_switch, .flags = GENL_UNS_ADMIN_PERM, - .internal_flags = NL80211_FLAG_NEED_NETDEV_UP | - NL80211_FLAG_NEED_RTNL, + .internal_flags = NL80211_FLAG_NEED_NETDEV_UP, }, { .cmd = NL80211_CMD_VENDOR, @@ -15570,7 +15651,7 @@ static const struct genl_small_ops nl80211_small_ops[] = { .dumpit = nl80211_vendor_cmd_dump, .flags = GENL_UNS_ADMIN_PERM, .internal_flags = NL80211_FLAG_NEED_WIPHY | - NL80211_FLAG_NEED_RTNL | + 0 | NL80211_FLAG_CLEAR_SKB, }, { @@ -15578,123 +15659,108 @@ static const struct genl_small_ops nl80211_small_ops[] = { .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = nl80211_set_qos_map, .flags = GENL_UNS_ADMIN_PERM, - .internal_flags = NL80211_FLAG_NEED_NETDEV_UP | - NL80211_FLAG_NEED_RTNL, + .internal_flags = NL80211_FLAG_NEED_NETDEV_UP, }, { .cmd = NL80211_CMD_ADD_TX_TS, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = nl80211_add_tx_ts, .flags = GENL_UNS_ADMIN_PERM, - .internal_flags = NL80211_FLAG_NEED_NETDEV_UP | - NL80211_FLAG_NEED_RTNL, + .internal_flags = NL80211_FLAG_NEED_NETDEV_UP, }, { .cmd = NL80211_CMD_DEL_TX_TS, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = nl80211_del_tx_ts, .flags = GENL_UNS_ADMIN_PERM, - .internal_flags = NL80211_FLAG_NEED_NETDEV_UP | - NL80211_FLAG_NEED_RTNL, + .internal_flags = NL80211_FLAG_NEED_NETDEV_UP, }, { .cmd = NL80211_CMD_TDLS_CHANNEL_SWITCH, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = nl80211_tdls_channel_switch, .flags = GENL_UNS_ADMIN_PERM, - .internal_flags = NL80211_FLAG_NEED_NETDEV_UP | - NL80211_FLAG_NEED_RTNL, + .internal_flags = NL80211_FLAG_NEED_NETDEV_UP, }, { .cmd = NL80211_CMD_TDLS_CANCEL_CHANNEL_SWITCH, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = nl80211_tdls_cancel_channel_switch, .flags = GENL_UNS_ADMIN_PERM, - .internal_flags = NL80211_FLAG_NEED_NETDEV_UP | - NL80211_FLAG_NEED_RTNL, + .internal_flags = NL80211_FLAG_NEED_NETDEV_UP, }, { .cmd = NL80211_CMD_SET_MULTICAST_TO_UNICAST, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = nl80211_set_multicast_to_unicast, .flags = GENL_UNS_ADMIN_PERM, - .internal_flags = NL80211_FLAG_NEED_NETDEV | - NL80211_FLAG_NEED_RTNL, + .internal_flags = NL80211_FLAG_NEED_NETDEV, }, { .cmd = NL80211_CMD_SET_PMK, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = nl80211_set_pmk, .internal_flags = NL80211_FLAG_NEED_NETDEV_UP | - NL80211_FLAG_NEED_RTNL | + 0 | NL80211_FLAG_CLEAR_SKB, }, { .cmd = NL80211_CMD_DEL_PMK, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = nl80211_del_pmk, - .internal_flags = NL80211_FLAG_NEED_NETDEV_UP | - NL80211_FLAG_NEED_RTNL, + .internal_flags = NL80211_FLAG_NEED_NETDEV_UP, }, { .cmd = NL80211_CMD_EXTERNAL_AUTH, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = nl80211_external_auth, .flags = GENL_ADMIN_PERM, - .internal_flags = NL80211_FLAG_NEED_NETDEV_UP | - NL80211_FLAG_NEED_RTNL, + .internal_flags = NL80211_FLAG_NEED_NETDEV_UP, }, { .cmd = NL80211_CMD_CONTROL_PORT_FRAME, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = nl80211_tx_control_port, .flags = GENL_UNS_ADMIN_PERM, - .internal_flags = NL80211_FLAG_NEED_NETDEV_UP | - NL80211_FLAG_NEED_RTNL, + .internal_flags = NL80211_FLAG_NEED_NETDEV_UP, }, { .cmd = NL80211_CMD_GET_FTM_RESPONDER_STATS, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = nl80211_get_ftm_responder_stats, - .internal_flags = NL80211_FLAG_NEED_NETDEV | - NL80211_FLAG_NEED_RTNL, + .internal_flags = NL80211_FLAG_NEED_NETDEV, }, { .cmd = NL80211_CMD_PEER_MEASUREMENT_START, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = nl80211_pmsr_start, .flags = GENL_UNS_ADMIN_PERM, - .internal_flags = NL80211_FLAG_NEED_WDEV_UP | - NL80211_FLAG_NEED_RTNL, + .internal_flags = NL80211_FLAG_NEED_WDEV_UP, }, { .cmd = NL80211_CMD_NOTIFY_RADAR, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = nl80211_notify_radar_detection, .flags = GENL_UNS_ADMIN_PERM, - .internal_flags = NL80211_FLAG_NEED_NETDEV_UP | - NL80211_FLAG_NEED_RTNL, + .internal_flags = NL80211_FLAG_NEED_NETDEV_UP, }, { .cmd = NL80211_CMD_UPDATE_OWE_INFO, .doit = nl80211_update_owe_info, .flags = GENL_ADMIN_PERM, - .internal_flags = NL80211_FLAG_NEED_NETDEV_UP | - NL80211_FLAG_NEED_RTNL, + .internal_flags = NL80211_FLAG_NEED_NETDEV_UP, }, { .cmd = NL80211_CMD_PROBE_MESH_LINK, .doit = nl80211_probe_mesh_link, .flags = GENL_UNS_ADMIN_PERM, - .internal_flags = NL80211_FLAG_NEED_NETDEV_UP | - NL80211_FLAG_NEED_RTNL, + .internal_flags = NL80211_FLAG_NEED_NETDEV_UP, }, { .cmd = NL80211_CMD_SET_TID_CONFIG, .doit = nl80211_set_tid_config, .flags = GENL_UNS_ADMIN_PERM, - .internal_flags = NL80211_FLAG_NEED_NETDEV | - NL80211_FLAG_NEED_RTNL, + .internal_flags = NL80211_FLAG_NEED_NETDEV, }, { .cmd = NL80211_CMD_SET_SAR_SPECS, diff --git a/net/wireless/reg.c b/net/wireless/reg.c index 8114bba8556c..21536c48deec 100644 --- a/net/wireless/reg.c +++ b/net/wireless/reg.c @@ -142,12 +142,15 @@ static const struct ieee80211_regdomain *get_cfg80211_regdom(void) /* * Returns the regulatory domain associated with the wiphy. * - * Requires either RTNL or RCU protection + * Requires any of RTNL, wiphy mutex or RCU protection. */ const struct ieee80211_regdomain *get_wiphy_regdom(struct wiphy *wiphy) { - return rcu_dereference_rtnl(wiphy->regd); + return rcu_dereference_check(wiphy->regd, + lockdep_is_held(&wiphy->mtx) || + lockdep_rtnl_is_held()); } +EXPORT_SYMBOL(get_wiphy_regdom); static const char *reg_dfs_region_str(enum nl80211_dfs_regions dfs_region) { @@ -169,7 +172,9 @@ enum nl80211_dfs_regions reg_get_dfs_region(struct wiphy *wiphy) const struct ieee80211_regdomain *regd = NULL; const struct ieee80211_regdomain *wiphy_regd = NULL; + rcu_read_lock(); regd = get_cfg80211_regdom(); + if (!wiphy) goto out; @@ -186,6 +191,8 @@ enum nl80211_dfs_regions reg_get_dfs_region(struct wiphy *wiphy) reg_dfs_region_str(regd->dfs_region)); out: + rcu_read_unlock(); + return regd->dfs_region; } @@ -1622,7 +1629,7 @@ __freq_reg_info(struct wiphy *wiphy, u32 center_freq, u32 min_bw) { const struct ieee80211_regdomain *regd = reg_get_regdomain(wiphy); static const u32 bws[] = {0, 1, 2, 4, 5, 8, 10, 16, 20}; - const struct ieee80211_reg_rule *reg_rule; + const struct ieee80211_reg_rule *reg_rule = ERR_PTR(-ERANGE); int i = ARRAY_SIZE(bws) - 1; u32 bw; @@ -2577,11 +2584,13 @@ void wiphy_apply_custom_regulatory(struct wiphy *wiphy, return; rtnl_lock(); + wiphy_lock(wiphy); tmp = get_wiphy_regdom(wiphy); rcu_assign_pointer(wiphy->regd, new_regd); rcu_free_regdom(tmp); + wiphy_unlock(wiphy); rtnl_unlock(); } EXPORT_SYMBOL(wiphy_apply_custom_regulatory); @@ -2744,7 +2753,10 @@ reg_process_hint_driver(struct wiphy *wiphy, return REG_REQ_IGNORE; tmp = get_wiphy_regdom(wiphy); + ASSERT_RTNL(); + wiphy_lock(wiphy); rcu_assign_pointer(wiphy->regd, regd); + wiphy_unlock(wiphy); rcu_free_regdom(tmp); } @@ -3076,41 +3088,52 @@ static void reg_process_pending_beacon_hints(void) spin_unlock_bh(®_pending_beacons_lock); } -static void reg_process_self_managed_hints(void) +static void reg_process_self_managed_hint(struct wiphy *wiphy) { - struct cfg80211_registered_device *rdev; - struct wiphy *wiphy; + struct cfg80211_registered_device *rdev = wiphy_to_rdev(wiphy); const struct ieee80211_regdomain *tmp; const struct ieee80211_regdomain *regd; enum nl80211_band band; struct regulatory_request request = {}; - list_for_each_entry(rdev, &cfg80211_rdev_list, list) { - wiphy = &rdev->wiphy; + ASSERT_RTNL(); + lockdep_assert_wiphy(wiphy); - spin_lock(®_requests_lock); - regd = rdev->requested_regd; - rdev->requested_regd = NULL; - spin_unlock(®_requests_lock); + spin_lock(®_requests_lock); + regd = rdev->requested_regd; + rdev->requested_regd = NULL; + spin_unlock(®_requests_lock); - if (regd == NULL) - continue; + if (!regd) + return; - tmp = get_wiphy_regdom(wiphy); - rcu_assign_pointer(wiphy->regd, regd); - rcu_free_regdom(tmp); + tmp = get_wiphy_regdom(wiphy); + rcu_assign_pointer(wiphy->regd, regd); + rcu_free_regdom(tmp); + + for (band = 0; band < NUM_NL80211_BANDS; band++) + handle_band_custom(wiphy, wiphy->bands[band], regd); - for (band = 0; band < NUM_NL80211_BANDS; band++) - handle_band_custom(wiphy, wiphy->bands[band], regd); + reg_process_ht_flags(wiphy); - reg_process_ht_flags(wiphy); + request.wiphy_idx = get_wiphy_idx(wiphy); + request.alpha2[0] = regd->alpha2[0]; + request.alpha2[1] = regd->alpha2[1]; + request.initiator = NL80211_REGDOM_SET_BY_DRIVER; - request.wiphy_idx = get_wiphy_idx(wiphy); - request.alpha2[0] = regd->alpha2[0]; - request.alpha2[1] = regd->alpha2[1]; - request.initiator = NL80211_REGDOM_SET_BY_DRIVER; + nl80211_send_wiphy_reg_change_event(&request); +} - nl80211_send_wiphy_reg_change_event(&request); +static void reg_process_self_managed_hints(void) +{ + struct cfg80211_registered_device *rdev; + + ASSERT_RTNL(); + + list_for_each_entry(rdev, &cfg80211_rdev_list, list) { + wiphy_lock(&rdev->wiphy); + reg_process_self_managed_hint(&rdev->wiphy); + wiphy_unlock(&rdev->wiphy); } reg_check_channels(); @@ -3789,14 +3812,21 @@ static int reg_set_rd_driver(const struct ieee80211_regdomain *rd, return -ENODEV; if (!driver_request->intersect) { - if (request_wiphy->regd) + ASSERT_RTNL(); + wiphy_lock(request_wiphy); + if (request_wiphy->regd) { + wiphy_unlock(request_wiphy); return -EALREADY; + } regd = reg_copy_regd(rd); - if (IS_ERR(regd)) + if (IS_ERR(regd)) { + wiphy_unlock(request_wiphy); return PTR_ERR(regd); + } rcu_assign_pointer(request_wiphy->regd, regd); + wiphy_unlock(request_wiphy); reset_regdomains(false, rd); return 0; } @@ -3978,8 +4008,8 @@ int regulatory_set_wiphy_regd(struct wiphy *wiphy, } EXPORT_SYMBOL(regulatory_set_wiphy_regd); -int regulatory_set_wiphy_regd_sync_rtnl(struct wiphy *wiphy, - struct ieee80211_regdomain *rd) +int regulatory_set_wiphy_regd_sync(struct wiphy *wiphy, + struct ieee80211_regdomain *rd) { int ret; @@ -3990,10 +4020,11 @@ int regulatory_set_wiphy_regd_sync_rtnl(struct wiphy *wiphy, return ret; /* process the request immediately */ - reg_process_self_managed_hints(); + reg_process_self_managed_hint(wiphy); + reg_check_channels(); return 0; } -EXPORT_SYMBOL(regulatory_set_wiphy_regd_sync_rtnl); +EXPORT_SYMBOL(regulatory_set_wiphy_regd_sync); void wiphy_regulatory_register(struct wiphy *wiphy) { diff --git a/net/wireless/reg.h b/net/wireless/reg.h index f9e83031a40a..f3707f729024 100644 --- a/net/wireless/reg.h +++ b/net/wireless/reg.h @@ -63,7 +63,6 @@ unsigned int reg_get_max_bandwidth(const struct ieee80211_regdomain *rd, const struct ieee80211_reg_rule *rule); bool reg_last_request_cell_base(void); -const struct ieee80211_regdomain *get_wiphy_regdom(struct wiphy *wiphy); /** * regulatory_hint_found_beacon - hints a beacon was found on a channel diff --git a/net/wireless/scan.c b/net/wireless/scan.c index 1b7fec3b53cd..019952d4fc7d 100644 --- a/net/wireless/scan.c +++ b/net/wireless/scan.c @@ -918,7 +918,7 @@ void ___cfg80211_scan_done(struct cfg80211_registered_device *rdev, union iwreq_data wrqu; #endif - ASSERT_RTNL(); + lockdep_assert_held(&rdev->wiphy.mtx); if (rdev->scan_msg) { nl80211_send_scan_msg(rdev, rdev->scan_msg); @@ -987,9 +987,9 @@ void __cfg80211_scan_done(struct work_struct *wk) rdev = container_of(wk, struct cfg80211_registered_device, scan_done_wk); - rtnl_lock(); + wiphy_lock(&rdev->wiphy); ___cfg80211_scan_done(rdev, true); - rtnl_unlock(); + wiphy_unlock(&rdev->wiphy); } void cfg80211_scan_done(struct cfg80211_scan_request *request, @@ -1022,7 +1022,7 @@ EXPORT_SYMBOL(cfg80211_scan_done); void cfg80211_add_sched_scan_req(struct cfg80211_registered_device *rdev, struct cfg80211_sched_scan_request *req) { - ASSERT_RTNL(); + lockdep_assert_held(&rdev->wiphy.mtx); list_add_rcu(&req->list, &rdev->sched_scan_req_list); } @@ -1030,7 +1030,7 @@ void cfg80211_add_sched_scan_req(struct cfg80211_registered_device *rdev, static void cfg80211_del_sched_scan_req(struct cfg80211_registered_device *rdev, struct cfg80211_sched_scan_request *req) { - ASSERT_RTNL(); + lockdep_assert_held(&rdev->wiphy.mtx); list_del_rcu(&req->list); kfree_rcu(req, rcu_head); @@ -1042,7 +1042,7 @@ cfg80211_find_sched_scan_req(struct cfg80211_registered_device *rdev, u64 reqid) struct cfg80211_sched_scan_request *pos; list_for_each_entry_rcu(pos, &rdev->sched_scan_req_list, list, - lockdep_rtnl_is_held()) { + lockdep_is_held(&rdev->wiphy.mtx)) { if (pos->reqid == reqid) return pos; } @@ -1090,7 +1090,7 @@ void cfg80211_sched_scan_results_wk(struct work_struct *work) rdev = container_of(work, struct cfg80211_registered_device, sched_scan_res_wk); - rtnl_lock(); + wiphy_lock(&rdev->wiphy); list_for_each_entry_safe(req, tmp, &rdev->sched_scan_req_list, list) { if (req->report_results) { req->report_results = false; @@ -1105,7 +1105,7 @@ void cfg80211_sched_scan_results_wk(struct work_struct *work) NL80211_CMD_SCHED_SCAN_RESULTS); } } - rtnl_unlock(); + wiphy_unlock(&rdev->wiphy); } void cfg80211_sched_scan_results(struct wiphy *wiphy, u64 reqid) @@ -1126,23 +1126,23 @@ void cfg80211_sched_scan_results(struct wiphy *wiphy, u64 reqid) } EXPORT_SYMBOL(cfg80211_sched_scan_results); -void cfg80211_sched_scan_stopped_rtnl(struct wiphy *wiphy, u64 reqid) +void cfg80211_sched_scan_stopped_locked(struct wiphy *wiphy, u64 reqid) { struct cfg80211_registered_device *rdev = wiphy_to_rdev(wiphy); - ASSERT_RTNL(); + lockdep_assert_held(&wiphy->mtx); trace_cfg80211_sched_scan_stopped(wiphy, reqid); __cfg80211_stop_sched_scan(rdev, reqid, true); } -EXPORT_SYMBOL(cfg80211_sched_scan_stopped_rtnl); +EXPORT_SYMBOL(cfg80211_sched_scan_stopped_locked); void cfg80211_sched_scan_stopped(struct wiphy *wiphy, u64 reqid) { - rtnl_lock(); - cfg80211_sched_scan_stopped_rtnl(wiphy, reqid); - rtnl_unlock(); + wiphy_lock(wiphy); + cfg80211_sched_scan_stopped_locked(wiphy, reqid); + wiphy_unlock(wiphy); } EXPORT_SYMBOL(cfg80211_sched_scan_stopped); @@ -1150,7 +1150,7 @@ int cfg80211_stop_sched_scan_req(struct cfg80211_registered_device *rdev, struct cfg80211_sched_scan_request *req, bool driver_initiated) { - ASSERT_RTNL(); + lockdep_assert_held(&rdev->wiphy.mtx); if (!driver_initiated) { int err = rdev_sched_scan_stop(rdev, req->dev, req->reqid); @@ -1170,7 +1170,7 @@ int __cfg80211_stop_sched_scan(struct cfg80211_registered_device *rdev, { struct cfg80211_sched_scan_request *sched_scan_req; - ASSERT_RTNL(); + lockdep_assert_held(&rdev->wiphy.mtx); sched_scan_req = cfg80211_find_sched_scan_req(rdev, reqid); if (!sched_scan_req) @@ -2774,6 +2774,8 @@ int cfg80211_wext_siwscan(struct net_device *dev, eth_broadcast_addr(creq->bssid); + wiphy_lock(&rdev->wiphy); + rdev->scan_req = creq; err = rdev_scan(rdev, creq); if (err) { @@ -2785,6 +2787,7 @@ int cfg80211_wext_siwscan(struct net_device *dev, creq = NULL; dev_hold(dev); } + wiphy_unlock(&rdev->wiphy); out: kfree(creq); return err; diff --git a/net/wireless/sme.c b/net/wireless/sme.c index 38df713f2e2e..07756ca5e3b5 100644 --- a/net/wireless/sme.c +++ b/net/wireless/sme.c @@ -67,7 +67,6 @@ static int cfg80211_conn_scan(struct wireless_dev *wdev) struct cfg80211_scan_request *request; int n_channels, err; - ASSERT_RTNL(); ASSERT_WDEV_LOCK(wdev); if (rdev->scan_req || rdev->scan_msg) @@ -233,7 +232,7 @@ void cfg80211_conn_work(struct work_struct *work) u8 bssid_buf[ETH_ALEN], *bssid = NULL; enum nl80211_timeout_reason treason; - rtnl_lock(); + wiphy_lock(&rdev->wiphy); list_for_each_entry(wdev, &rdev->wiphy.wdev_list, list) { if (!wdev->netdev) @@ -266,7 +265,7 @@ void cfg80211_conn_work(struct work_struct *work) wdev_unlock(wdev); } - rtnl_unlock(); + wiphy_unlock(&rdev->wiphy); } /* Returned bss is reference counted and must be cleaned up appropriately. */ diff --git a/net/wireless/sysfs.c b/net/wireless/sysfs.c index 3ac1f48195d2..9b959e3b09c6 100644 --- a/net/wireless/sysfs.c +++ b/net/wireless/sysfs.c @@ -5,6 +5,7 @@ * * Copyright 2005-2006 Jiri Benc <jbenc@suse.cz> * Copyright 2006 Johannes Berg <johannes@sipsolutions.net> + * Copyright (C) 2020-2021 Intel Corporation */ #include <linux/device.h> @@ -81,12 +82,6 @@ static void wiphy_dev_release(struct device *dev) cfg80211_dev_free(rdev); } -static int wiphy_uevent(struct device *dev, struct kobj_uevent_env *env) -{ - /* TODO, we probably need stuff here */ - return 0; -} - #ifdef CONFIG_PM_SLEEP static void cfg80211_leave_all(struct cfg80211_registered_device *rdev) { @@ -104,6 +99,7 @@ static int wiphy_suspend(struct device *dev) rdev->suspend_at = ktime_get_boottime_seconds(); rtnl_lock(); + wiphy_lock(&rdev->wiphy); if (rdev->wiphy.registered) { if (!rdev->wiphy.wowlan_config) { cfg80211_leave_all(rdev); @@ -118,6 +114,7 @@ static int wiphy_suspend(struct device *dev) ret = rdev_suspend(rdev, NULL); } } + wiphy_unlock(&rdev->wiphy); rtnl_unlock(); return ret; @@ -132,8 +129,10 @@ static int wiphy_resume(struct device *dev) cfg80211_bss_age(rdev, ktime_get_boottime_seconds() - rdev->suspend_at); rtnl_lock(); + wiphy_lock(&rdev->wiphy); if (rdev->wiphy.registered && rdev->ops->resume) ret = rdev_resume(rdev); + wiphy_unlock(&rdev->wiphy); rtnl_unlock(); return ret; @@ -157,7 +156,6 @@ struct class ieee80211_class = { .owner = THIS_MODULE, .dev_release = wiphy_dev_release, .dev_groups = ieee80211_groups, - .dev_uevent = wiphy_uevent, .pm = WIPHY_PM_OPS, .ns_type = &net_ns_type_operations, .namespace = wiphy_namespace, diff --git a/net/wireless/util.c b/net/wireless/util.c index b4acc805114b..1bf0200f562a 100644 --- a/net/wireless/util.c +++ b/net/wireless/util.c @@ -997,7 +997,7 @@ void cfg80211_process_rdev_events(struct cfg80211_registered_device *rdev) { struct wireless_dev *wdev; - ASSERT_RTNL(); + lockdep_assert_held(&rdev->wiphy.mtx); list_for_each_entry(wdev, &rdev->wiphy.wdev_list, list) cfg80211_process_wdev_events(wdev); @@ -1010,7 +1010,7 @@ int cfg80211_change_iface(struct cfg80211_registered_device *rdev, int err; enum nl80211_iftype otype = dev->ieee80211_ptr->iftype; - ASSERT_RTNL(); + lockdep_assert_held(&rdev->wiphy.mtx); /* don't support changing VLANs, you just re-create them */ if (otype == NL80211_IFTYPE_AP_VLAN) @@ -1188,6 +1188,25 @@ static u32 cfg80211_calculate_bitrate_dmg(struct rate_info *rate) return __mcs2bitrate[rate->mcs]; } +static u32 cfg80211_calculate_bitrate_extended_sc_dmg(struct rate_info *rate) +{ + static const u32 __mcs2bitrate[] = { + [6 - 6] = 26950, /* MCS 9.1 : 2695.0 mbps */ + [7 - 6] = 50050, /* MCS 12.1 */ + [8 - 6] = 53900, + [9 - 6] = 57750, + [10 - 6] = 63900, + [11 - 6] = 75075, + [12 - 6] = 80850, + }; + + /* Extended SC MCS not defined for base MCS below 6 or above 12 */ + if (WARN_ON_ONCE(rate->mcs < 6 || rate->mcs > 12)) + return 0; + + return __mcs2bitrate[rate->mcs - 6]; +} + static u32 cfg80211_calculate_bitrate_edmg(struct rate_info *rate) { static const u32 __mcs2bitrate[] = { @@ -1224,7 +1243,7 @@ static u32 cfg80211_calculate_bitrate_edmg(struct rate_info *rate) static u32 cfg80211_calculate_bitrate_vht(struct rate_info *rate) { - static const u32 base[4][10] = { + static const u32 base[4][12] = { { 6500000, 13000000, 19500000, @@ -1235,7 +1254,9 @@ static u32 cfg80211_calculate_bitrate_vht(struct rate_info *rate) 65000000, 78000000, /* not in the spec, but some devices use this: */ - 86500000, + 86700000, + 97500000, + 108300000, }, { 13500000, 27000000, @@ -1247,6 +1268,8 @@ static u32 cfg80211_calculate_bitrate_vht(struct rate_info *rate) 135000000, 162000000, 180000000, + 202500000, + 225000000, }, { 29300000, 58500000, @@ -1258,6 +1281,8 @@ static u32 cfg80211_calculate_bitrate_vht(struct rate_info *rate) 292500000, 351000000, 390000000, + 438800000, + 487500000, }, { 58500000, 117000000, @@ -1269,12 +1294,14 @@ static u32 cfg80211_calculate_bitrate_vht(struct rate_info *rate) 585000000, 702000000, 780000000, + 877500000, + 975000000, }, }; u32 bitrate; int idx; - if (rate->mcs > 9) + if (rate->mcs > 11) goto warn; switch (rate->bw) { @@ -1398,6 +1425,8 @@ u32 cfg80211_calculate_bitrate(struct rate_info *rate) return cfg80211_calculate_bitrate_ht(rate); if (rate->flags & RATE_INFO_FLAGS_DMG) return cfg80211_calculate_bitrate_dmg(rate); + if (rate->flags & RATE_INFO_FLAGS_EXTENDED_SC_DMG) + return cfg80211_calculate_bitrate_extended_sc_dmg(rate); if (rate->flags & RATE_INFO_FLAGS_EDMG) return cfg80211_calculate_bitrate_edmg(rate); if (rate->flags & RATE_INFO_FLAGS_VHT_MCS) diff --git a/net/wireless/wext-compat.c b/net/wireless/wext-compat.c index fd9ad74972fb..a8320dc59af7 100644 --- a/net/wireless/wext-compat.c +++ b/net/wireless/wext-compat.c @@ -7,7 +7,7 @@ * we directly assign the wireless handlers of wireless interfaces. * * Copyright 2008-2009 Johannes Berg <johannes@sipsolutions.net> - * Copyright (C) 2019 Intel Corporation + * Copyright (C) 2019-2021 Intel Corporation */ #include <linux/export.h> @@ -39,6 +39,7 @@ int cfg80211_wext_siwmode(struct net_device *dev, struct iw_request_info *info, struct cfg80211_registered_device *rdev; struct vif_params vifparams; enum nl80211_iftype type; + int ret; rdev = wiphy_to_rdev(wdev->wiphy); @@ -61,7 +62,11 @@ int cfg80211_wext_siwmode(struct net_device *dev, struct iw_request_info *info, memset(&vifparams, 0, sizeof(vifparams)); - return cfg80211_change_iface(rdev, dev, type, &vifparams); + wiphy_lock(wdev->wiphy); + ret = cfg80211_change_iface(rdev, dev, type, &vifparams); + wiphy_unlock(wdev->wiphy); + + return ret; } EXPORT_WEXT_HANDLER(cfg80211_wext_siwmode); @@ -253,17 +258,23 @@ int cfg80211_wext_siwrts(struct net_device *dev, u32 orts = wdev->wiphy->rts_threshold; int err; - if (rts->disabled || !rts->fixed) + wiphy_lock(&rdev->wiphy); + if (rts->disabled || !rts->fixed) { wdev->wiphy->rts_threshold = (u32) -1; - else if (rts->value < 0) - return -EINVAL; - else + } else if (rts->value < 0) { + err = -EINVAL; + goto out; + } else { wdev->wiphy->rts_threshold = rts->value; + } err = rdev_set_wiphy_params(rdev, WIPHY_PARAM_RTS_THRESHOLD); + if (err) wdev->wiphy->rts_threshold = orts; +out: + wiphy_unlock(&rdev->wiphy); return err; } EXPORT_WEXT_HANDLER(cfg80211_wext_siwrts); @@ -291,11 +302,13 @@ int cfg80211_wext_siwfrag(struct net_device *dev, u32 ofrag = wdev->wiphy->frag_threshold; int err; - if (frag->disabled || !frag->fixed) + wiphy_lock(&rdev->wiphy); + if (frag->disabled || !frag->fixed) { wdev->wiphy->frag_threshold = (u32) -1; - else if (frag->value < 256) - return -EINVAL; - else { + } else if (frag->value < 256) { + err = -EINVAL; + goto out; + } else { /* Fragment length must be even, so strip LSB. */ wdev->wiphy->frag_threshold = frag->value & ~0x1; } @@ -303,6 +316,8 @@ int cfg80211_wext_siwfrag(struct net_device *dev, err = rdev_set_wiphy_params(rdev, WIPHY_PARAM_FRAG_THRESHOLD); if (err) wdev->wiphy->frag_threshold = ofrag; +out: + wiphy_unlock(&rdev->wiphy); return err; } @@ -337,6 +352,7 @@ static int cfg80211_wext_siwretry(struct net_device *dev, (retry->flags & IW_RETRY_TYPE) != IW_RETRY_LIMIT) return -EINVAL; + wiphy_lock(&rdev->wiphy); if (retry->flags & IW_RETRY_LONG) { wdev->wiphy->retry_long = retry->value; changed |= WIPHY_PARAM_RETRY_LONG; @@ -355,6 +371,7 @@ static int cfg80211_wext_siwretry(struct net_device *dev, wdev->wiphy->retry_short = oshort; wdev->wiphy->retry_long = olong; } + wiphy_unlock(&rdev->wiphy); return err; } @@ -577,15 +594,18 @@ static int cfg80211_wext_siwencode(struct net_device *dev, !rdev->ops->set_default_key) return -EOPNOTSUPP; + wiphy_lock(&rdev->wiphy); idx = erq->flags & IW_ENCODE_INDEX; if (idx == 0) { idx = wdev->wext.default_key; if (idx < 0) idx = 0; - } else if (idx < 1 || idx > 4) - return -EINVAL; - else + } else if (idx < 1 || idx > 4) { + err = -EINVAL; + goto out; + } else { idx--; + } if (erq->flags & IW_ENCODE_DISABLED) remove = true; @@ -599,22 +619,28 @@ static int cfg80211_wext_siwencode(struct net_device *dev, if (!err) wdev->wext.default_key = idx; wdev_unlock(wdev); - return err; + goto out; } memset(¶ms, 0, sizeof(params)); params.key = keybuf; params.key_len = erq->length; - if (erq->length == 5) + if (erq->length == 5) { params.cipher = WLAN_CIPHER_SUITE_WEP40; - else if (erq->length == 13) + } else if (erq->length == 13) { params.cipher = WLAN_CIPHER_SUITE_WEP104; - else if (!remove) - return -EINVAL; + } else if (!remove) { + err = -EINVAL; + goto out; + } + + err = cfg80211_set_encryption(rdev, dev, false, NULL, remove, + wdev->wext.default_key == -1, + idx, ¶ms); +out: + wiphy_unlock(&rdev->wiphy); - return cfg80211_set_encryption(rdev, dev, false, NULL, remove, - wdev->wext.default_key == -1, - idx, ¶ms); + return err; } static int cfg80211_wext_siwencodeext(struct net_device *dev, @@ -629,6 +655,7 @@ static int cfg80211_wext_siwencodeext(struct net_device *dev, bool remove = false; struct key_params params; u32 cipher; + int ret; if (wdev->iftype != NL80211_IFTYPE_STATION && wdev->iftype != NL80211_IFTYPE_ADHOC) @@ -700,12 +727,16 @@ static int cfg80211_wext_siwencodeext(struct net_device *dev, params.seq_len = 6; } - return cfg80211_set_encryption( + wiphy_lock(wdev->wiphy); + ret = cfg80211_set_encryption( rdev, dev, !(ext->ext_flags & IW_ENCODE_EXT_GROUP_KEY), addr, remove, ext->ext_flags & IW_ENCODE_EXT_SET_TX_KEY, idx, ¶ms); + wiphy_unlock(wdev->wiphy); + + return ret; } static int cfg80211_wext_giwencode(struct net_device *dev, @@ -754,38 +785,61 @@ static int cfg80211_wext_siwfreq(struct net_device *dev, struct cfg80211_chan_def chandef = { .width = NL80211_CHAN_WIDTH_20_NOHT, }; - int freq; + int freq, ret; + + wiphy_lock(&rdev->wiphy); switch (wdev->iftype) { case NL80211_IFTYPE_STATION: - return cfg80211_mgd_wext_siwfreq(dev, info, wextfreq, extra); + ret = cfg80211_mgd_wext_siwfreq(dev, info, wextfreq, extra); + break; case NL80211_IFTYPE_ADHOC: - return cfg80211_ibss_wext_siwfreq(dev, info, wextfreq, extra); + ret = cfg80211_ibss_wext_siwfreq(dev, info, wextfreq, extra); + break; case NL80211_IFTYPE_MONITOR: freq = cfg80211_wext_freq(wextfreq); - if (freq < 0) - return freq; - if (freq == 0) - return -EINVAL; + if (freq < 0) { + ret = freq; + break; + } + if (freq == 0) { + ret = -EINVAL; + break; + } chandef.center_freq1 = freq; chandef.chan = ieee80211_get_channel(&rdev->wiphy, freq); - if (!chandef.chan) - return -EINVAL; - return cfg80211_set_monitor_channel(rdev, &chandef); + if (!chandef.chan) { + ret = -EINVAL; + break; + } + ret = cfg80211_set_monitor_channel(rdev, &chandef); + break; case NL80211_IFTYPE_MESH_POINT: freq = cfg80211_wext_freq(wextfreq); - if (freq < 0) - return freq; - if (freq == 0) - return -EINVAL; + if (freq < 0) { + ret = freq; + break; + } + if (freq == 0) { + ret = -EINVAL; + break; + } chandef.center_freq1 = freq; chandef.chan = ieee80211_get_channel(&rdev->wiphy, freq); - if (!chandef.chan) - return -EINVAL; - return cfg80211_set_mesh_channel(rdev, wdev, &chandef); + if (!chandef.chan) { + ret = -EINVAL; + break; + } + ret = cfg80211_set_mesh_channel(rdev, wdev, &chandef); + break; default: - return -EOPNOTSUPP; + ret = -EOPNOTSUPP; + break; } + + wiphy_unlock(&rdev->wiphy); + + return ret; } static int cfg80211_wext_giwfreq(struct net_device *dev, @@ -797,24 +851,35 @@ static int cfg80211_wext_giwfreq(struct net_device *dev, struct cfg80211_chan_def chandef = {}; int ret; + wiphy_lock(&rdev->wiphy); switch (wdev->iftype) { case NL80211_IFTYPE_STATION: - return cfg80211_mgd_wext_giwfreq(dev, info, freq, extra); + ret = cfg80211_mgd_wext_giwfreq(dev, info, freq, extra); + break; case NL80211_IFTYPE_ADHOC: - return cfg80211_ibss_wext_giwfreq(dev, info, freq, extra); + ret = cfg80211_ibss_wext_giwfreq(dev, info, freq, extra); + break; case NL80211_IFTYPE_MONITOR: - if (!rdev->ops->get_channel) - return -EINVAL; + if (!rdev->ops->get_channel) { + ret = -EINVAL; + break; + } ret = rdev_get_channel(rdev, wdev, &chandef); if (ret) - return ret; + break; freq->m = chandef.chan->center_freq; freq->e = 6; - return 0; + ret = 0; + break; default: - return -EINVAL; + ret = -EINVAL; + break; } + + wiphy_unlock(&rdev->wiphy); + + return ret; } static int cfg80211_wext_siwtxpower(struct net_device *dev, @@ -825,6 +890,7 @@ static int cfg80211_wext_siwtxpower(struct net_device *dev, struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); enum nl80211_tx_power_setting type; int dbm = 0; + int ret; if ((data->txpower.flags & IW_TXPOW_TYPE) != IW_TXPOW_DBM) return -EINVAL; @@ -866,7 +932,11 @@ static int cfg80211_wext_siwtxpower(struct net_device *dev, return 0; } - return rdev_set_tx_power(rdev, wdev, type, DBM_TO_MBM(dbm)); + wiphy_lock(&rdev->wiphy); + ret = rdev_set_tx_power(rdev, wdev, type, DBM_TO_MBM(dbm)); + wiphy_unlock(&rdev->wiphy); + + return ret; } static int cfg80211_wext_giwtxpower(struct net_device *dev, @@ -885,7 +955,9 @@ static int cfg80211_wext_giwtxpower(struct net_device *dev, if (!rdev->ops->get_tx_power) return -EOPNOTSUPP; + wiphy_lock(&rdev->wiphy); err = rdev_get_tx_power(rdev, wdev, &val); + wiphy_unlock(&rdev->wiphy); if (err) return err; @@ -1125,7 +1197,9 @@ static int cfg80211_wext_siwpower(struct net_device *dev, timeout = wrq->value / 1000; } + wiphy_lock(&rdev->wiphy); err = rdev_set_power_mgmt(rdev, dev, ps, timeout); + wiphy_unlock(&rdev->wiphy); if (err) return err; @@ -1156,7 +1230,7 @@ static int cfg80211_wext_siwrate(struct net_device *dev, struct cfg80211_bitrate_mask mask; u32 fixed, maxrate; struct ieee80211_supported_band *sband; - int band, ridx; + int band, ridx, ret; bool match = false; if (!rdev->ops->set_bitrate_mask) @@ -1195,7 +1269,11 @@ static int cfg80211_wext_siwrate(struct net_device *dev, if (!match) return -EINVAL; - return rdev_set_bitrate_mask(rdev, dev, NULL, &mask); + wiphy_lock(&rdev->wiphy); + ret = rdev_set_bitrate_mask(rdev, dev, NULL, &mask); + wiphy_unlock(&rdev->wiphy); + + return ret; } static int cfg80211_wext_giwrate(struct net_device *dev, @@ -1224,7 +1302,9 @@ static int cfg80211_wext_giwrate(struct net_device *dev, if (err) return err; + wiphy_lock(&rdev->wiphy); err = rdev_get_station(rdev, dev, addr, &sinfo); + wiphy_unlock(&rdev->wiphy); if (err) return err; @@ -1249,6 +1329,7 @@ static struct iw_statistics *cfg80211_wireless_stats(struct net_device *dev) static struct iw_statistics wstats; static struct station_info sinfo = {}; u8 bssid[ETH_ALEN]; + int ret; if (dev->ieee80211_ptr->iftype != NL80211_IFTYPE_STATION) return NULL; @@ -1267,7 +1348,11 @@ static struct iw_statistics *cfg80211_wireless_stats(struct net_device *dev) memset(&sinfo, 0, sizeof(sinfo)); - if (rdev_get_station(rdev, dev, bssid, &sinfo)) + wiphy_lock(&rdev->wiphy); + ret = rdev_get_station(rdev, dev, bssid, &sinfo); + wiphy_unlock(&rdev->wiphy); + + if (ret) return NULL; memset(&wstats, 0, sizeof(wstats)); @@ -1318,15 +1403,24 @@ static int cfg80211_wext_siwap(struct net_device *dev, struct sockaddr *ap_addr, char *extra) { struct wireless_dev *wdev = dev->ieee80211_ptr; + struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); + int ret; + wiphy_lock(&rdev->wiphy); switch (wdev->iftype) { case NL80211_IFTYPE_ADHOC: - return cfg80211_ibss_wext_siwap(dev, info, ap_addr, extra); + ret = cfg80211_ibss_wext_siwap(dev, info, ap_addr, extra); + break; case NL80211_IFTYPE_STATION: - return cfg80211_mgd_wext_siwap(dev, info, ap_addr, extra); + ret = cfg80211_mgd_wext_siwap(dev, info, ap_addr, extra); + break; default: - return -EOPNOTSUPP; + ret = -EOPNOTSUPP; + break; } + wiphy_unlock(&rdev->wiphy); + + return ret; } static int cfg80211_wext_giwap(struct net_device *dev, @@ -1334,15 +1428,24 @@ static int cfg80211_wext_giwap(struct net_device *dev, struct sockaddr *ap_addr, char *extra) { struct wireless_dev *wdev = dev->ieee80211_ptr; + struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); + int ret; + wiphy_lock(&rdev->wiphy); switch (wdev->iftype) { case NL80211_IFTYPE_ADHOC: - return cfg80211_ibss_wext_giwap(dev, info, ap_addr, extra); + ret = cfg80211_ibss_wext_giwap(dev, info, ap_addr, extra); + break; case NL80211_IFTYPE_STATION: - return cfg80211_mgd_wext_giwap(dev, info, ap_addr, extra); + ret = cfg80211_mgd_wext_giwap(dev, info, ap_addr, extra); + break; default: - return -EOPNOTSUPP; + ret = -EOPNOTSUPP; + break; } + wiphy_unlock(&rdev->wiphy); + + return ret; } static int cfg80211_wext_siwessid(struct net_device *dev, @@ -1350,15 +1453,24 @@ static int cfg80211_wext_siwessid(struct net_device *dev, struct iw_point *data, char *ssid) { struct wireless_dev *wdev = dev->ieee80211_ptr; + struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); + int ret; + wiphy_lock(&rdev->wiphy); switch (wdev->iftype) { case NL80211_IFTYPE_ADHOC: - return cfg80211_ibss_wext_siwessid(dev, info, data, ssid); + ret = cfg80211_ibss_wext_siwessid(dev, info, data, ssid); + break; case NL80211_IFTYPE_STATION: - return cfg80211_mgd_wext_siwessid(dev, info, data, ssid); + ret = cfg80211_mgd_wext_siwessid(dev, info, data, ssid); + break; default: - return -EOPNOTSUPP; + ret = -EOPNOTSUPP; + break; } + wiphy_unlock(&rdev->wiphy); + + return ret; } static int cfg80211_wext_giwessid(struct net_device *dev, @@ -1366,18 +1478,27 @@ static int cfg80211_wext_giwessid(struct net_device *dev, struct iw_point *data, char *ssid) { struct wireless_dev *wdev = dev->ieee80211_ptr; + struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); + int ret; data->flags = 0; data->length = 0; + wiphy_lock(&rdev->wiphy); switch (wdev->iftype) { case NL80211_IFTYPE_ADHOC: - return cfg80211_ibss_wext_giwessid(dev, info, data, ssid); + ret = cfg80211_ibss_wext_giwessid(dev, info, data, ssid); + break; case NL80211_IFTYPE_STATION: - return cfg80211_mgd_wext_giwessid(dev, info, data, ssid); + ret = cfg80211_mgd_wext_giwessid(dev, info, data, ssid); + break; default: - return -EOPNOTSUPP; + ret = -EOPNOTSUPP; + break; } + wiphy_unlock(&rdev->wiphy); + + return ret; } static int cfg80211_wext_siwpmksa(struct net_device *dev, @@ -1388,6 +1509,7 @@ static int cfg80211_wext_siwpmksa(struct net_device *dev, struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); struct cfg80211_pmksa cfg_pmksa; struct iw_pmksa *pmksa = (struct iw_pmksa *)extra; + int ret; memset(&cfg_pmksa, 0, sizeof(struct cfg80211_pmksa)); @@ -1397,28 +1519,39 @@ static int cfg80211_wext_siwpmksa(struct net_device *dev, cfg_pmksa.bssid = pmksa->bssid.sa_data; cfg_pmksa.pmkid = pmksa->pmkid; + wiphy_lock(&rdev->wiphy); switch (pmksa->cmd) { case IW_PMKSA_ADD: - if (!rdev->ops->set_pmksa) - return -EOPNOTSUPP; - - return rdev_set_pmksa(rdev, dev, &cfg_pmksa); + if (!rdev->ops->set_pmksa) { + ret = -EOPNOTSUPP; + break; + } + ret = rdev_set_pmksa(rdev, dev, &cfg_pmksa); + break; case IW_PMKSA_REMOVE: - if (!rdev->ops->del_pmksa) - return -EOPNOTSUPP; - - return rdev_del_pmksa(rdev, dev, &cfg_pmksa); + if (!rdev->ops->del_pmksa) { + ret = -EOPNOTSUPP; + break; + } + ret = rdev_del_pmksa(rdev, dev, &cfg_pmksa); + break; case IW_PMKSA_FLUSH: - if (!rdev->ops->flush_pmksa) - return -EOPNOTSUPP; - - return rdev_flush_pmksa(rdev, dev); + if (!rdev->ops->flush_pmksa) { + ret = -EOPNOTSUPP; + break; + } + ret = rdev_flush_pmksa(rdev, dev); + break; default: - return -EOPNOTSUPP; + ret = -EOPNOTSUPP; + break; } + wiphy_unlock(&rdev->wiphy); + + return ret; } #define DEFINE_WEXT_COMPAT_STUB(func, type) \ diff --git a/net/wireless/wext-sme.c b/net/wireless/wext-sme.c index 73df23570d43..193a18a53142 100644 --- a/net/wireless/wext-sme.c +++ b/net/wireless/wext-sme.c @@ -3,7 +3,7 @@ * cfg80211 wext compat for managed mode. * * Copyright 2009 Johannes Berg <johannes@sipsolutions.net> - * Copyright (C) 2009 Intel Corporation. All rights reserved. + * Copyright (C) 2009, 2020-2021 Intel Corporation. */ #include <linux/export.h> @@ -379,6 +379,7 @@ int cfg80211_wext_siwmlme(struct net_device *dev, if (mlme->addr.sa_family != ARPHRD_ETHER) return -EINVAL; + wiphy_lock(&rdev->wiphy); wdev_lock(wdev); switch (mlme->cmd) { case IW_MLME_DEAUTH: @@ -390,6 +391,7 @@ int cfg80211_wext_siwmlme(struct net_device *dev, break; } wdev_unlock(wdev); + wiphy_unlock(&rdev->wiphy); return err; } diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c index 4a83117507f5..4faabd1ecfd1 100644 --- a/net/xdp/xsk.c +++ b/net/xdp/xsk.c @@ -184,12 +184,13 @@ static void xsk_copy_xdp(struct xdp_buff *to, struct xdp_buff *from, u32 len) memcpy(to_buf, from_buf, len + metalen); } -static int __xsk_rcv(struct xdp_sock *xs, struct xdp_buff *xdp, u32 len, - bool explicit_free) +static int __xsk_rcv(struct xdp_sock *xs, struct xdp_buff *xdp) { struct xdp_buff *xsk_xdp; int err; + u32 len; + len = xdp->data_end - xdp->data; if (len > xsk_pool_get_rx_frame_size(xs->pool)) { xs->rx_dropped++; return -ENOSPC; @@ -207,8 +208,6 @@ static int __xsk_rcv(struct xdp_sock *xs, struct xdp_buff *xdp, u32 len, xsk_buff_free(xsk_xdp); return err; } - if (explicit_free) - xdp_return_buff(xdp); return 0; } @@ -230,11 +229,8 @@ static bool xsk_is_bound(struct xdp_sock *xs) return false; } -static int xsk_rcv(struct xdp_sock *xs, struct xdp_buff *xdp, - bool explicit_free) +static int xsk_rcv_check(struct xdp_sock *xs, struct xdp_buff *xdp) { - u32 len; - if (!xsk_is_bound(xs)) return -EINVAL; @@ -242,11 +238,7 @@ static int xsk_rcv(struct xdp_sock *xs, struct xdp_buff *xdp, return -EINVAL; sk_mark_napi_id_once_xdp(&xs->sk, xdp); - len = xdp->data_end - xdp->data; - - return xdp->rxq->mem.type == MEM_TYPE_XSK_BUFF_POOL ? - __xsk_rcv_zc(xs, xdp, len) : - __xsk_rcv(xs, xdp, len, explicit_free); + return 0; } static void xsk_flush(struct xdp_sock *xs) @@ -261,18 +253,41 @@ int xsk_generic_rcv(struct xdp_sock *xs, struct xdp_buff *xdp) int err; spin_lock_bh(&xs->rx_lock); - err = xsk_rcv(xs, xdp, false); - xsk_flush(xs); + err = xsk_rcv_check(xs, xdp); + if (!err) { + err = __xsk_rcv(xs, xdp); + xsk_flush(xs); + } spin_unlock_bh(&xs->rx_lock); return err; } +static int xsk_rcv(struct xdp_sock *xs, struct xdp_buff *xdp) +{ + int err; + u32 len; + + err = xsk_rcv_check(xs, xdp); + if (err) + return err; + + if (xdp->rxq->mem.type == MEM_TYPE_XSK_BUFF_POOL) { + len = xdp->data_end - xdp->data; + return __xsk_rcv_zc(xs, xdp, len); + } + + err = __xsk_rcv(xs, xdp); + if (!err) + xdp_return_buff(xdp); + return err; +} + int __xsk_map_redirect(struct xdp_sock *xs, struct xdp_buff *xdp) { struct list_head *flush_list = this_cpu_ptr(&xskmap_flush_list); int err; - err = xsk_rcv(xs, xdp, true); + err = xsk_rcv(xs, xdp); if (err) return err; diff --git a/net/xdp/xsk_buff_pool.c b/net/xdp/xsk_buff_pool.c index 20598eea658c..8de01aaac4a0 100644 --- a/net/xdp/xsk_buff_pool.c +++ b/net/xdp/xsk_buff_pool.c @@ -119,8 +119,8 @@ static void xp_disable_drv_zc(struct xsk_buff_pool *pool) } } -static int __xp_assign_dev(struct xsk_buff_pool *pool, - struct net_device *netdev, u16 queue_id, u16 flags) +int xp_assign_dev(struct xsk_buff_pool *pool, + struct net_device *netdev, u16 queue_id, u16 flags) { bool force_zc, force_copy; struct netdev_bpf bpf; @@ -191,12 +191,6 @@ err_unreg_pool: return err; } -int xp_assign_dev(struct xsk_buff_pool *pool, struct net_device *dev, - u16 queue_id, u16 flags) -{ - return __xp_assign_dev(pool, dev, queue_id, flags); -} - int xp_assign_dev_shared(struct xsk_buff_pool *pool, struct xdp_umem *umem, struct net_device *dev, u16 queue_id) { @@ -210,7 +204,7 @@ int xp_assign_dev_shared(struct xsk_buff_pool *pool, struct xdp_umem *umem, if (pool->uses_need_wakeup) flags |= XDP_USE_NEED_WAKEUP; - return __xp_assign_dev(pool, dev, queue_id, flags); + return xp_assign_dev(pool, dev, queue_id, flags); } void xp_clear_dev(struct xsk_buff_pool *pool) diff --git a/net/xfrm/xfrm_interface.c b/net/xfrm/xfrm_interface.c index 697cdcfbb5e1..495b1f5c979b 100644 --- a/net/xfrm/xfrm_interface.c +++ b/net/xfrm/xfrm_interface.c @@ -296,7 +296,8 @@ xfrmi_xmit2(struct sk_buff *skb, struct net_device *dev, struct flowi *fl) } mtu = dst_mtu(dst); - if (skb->len > mtu) { + if ((!skb_is_gso(skb) && skb->len > mtu) || + (skb_is_gso(skb) && !skb_gso_validate_network_len(skb, mtu))) { skb_dst_update_pmtu_no_confirm(skb, mtu); if (skb->protocol == htons(ETH_P_IPV6)) { @@ -564,6 +565,11 @@ static void xfrmi_dev_setup(struct net_device *dev) eth_broadcast_addr(dev->broadcast); } +#define XFRMI_FEATURES (NETIF_F_SG | \ + NETIF_F_FRAGLIST | \ + NETIF_F_GSO_SOFTWARE | \ + NETIF_F_HW_CSUM) + static int xfrmi_dev_init(struct net_device *dev) { struct xfrm_if *xi = netdev_priv(dev); @@ -581,6 +587,8 @@ static int xfrmi_dev_init(struct net_device *dev) } dev->features |= NETIF_F_LLTX; + dev->features |= XFRMI_FEATURES; + dev->hw_features |= XFRMI_FEATURES; if (phydev) { dev->needed_headroom = phydev->needed_headroom; diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c index 0727ac853b55..5a0ef4361e43 100644 --- a/net/xfrm/xfrm_user.c +++ b/net/xfrm/xfrm_user.c @@ -2504,7 +2504,7 @@ static int xfrm_do_migrate(struct sk_buff *skb, struct nlmsghdr *nlh, encap = kmemdup(nla_data(attrs[XFRMA_ENCAP]), sizeof(*encap), GFP_KERNEL); if (!encap) - return 0; + return -ENOMEM; } err = xfrm_migrate(&pi->sel, pi->dir, type, m, n, kmp, net, encap); |