summaryrefslogtreecommitdiffstats
path: root/net
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2023-06-28 16:43:10 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2023-06-28 16:43:10 -0700
commit3a8a670eeeaa40d87bd38a587438952741980c18 (patch)
treed5546d311271503eadf75b45d87e12720e72899f /net
parent6a8cbd9253abc1bd0df4d60c4c24fa555190376d (diff)
parentae230642190a51b85656d6da2df744d534d59544 (diff)
downloadlinux-3a8a670eeeaa40d87bd38a587438952741980c18.tar.gz
linux-3a8a670eeeaa40d87bd38a587438952741980c18.tar.bz2
linux-3a8a670eeeaa40d87bd38a587438952741980c18.zip
Merge tag 'net-next-6.5' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next
Pull networking changes from Jakub Kicinski: "WiFi 7 and sendpage changes are the biggest pieces of work for this release. The latter will definitely require fixes but I think that we got it to a reasonable point. Core: - Rework the sendpage & splice implementations Instead of feeding data into sockets page by page extend sendmsg handlers to support taking a reference on the data, controlled by a new flag called MSG_SPLICE_PAGES Rework the handling of unexpected-end-of-file to invoke an additional callback instead of trying to predict what the right combination of MORE/NOTLAST flags is Remove the MSG_SENDPAGE_NOTLAST flag completely - Implement SCM_PIDFD, a new type of CMSG type analogous to SCM_CREDENTIALS, but it contains pidfd instead of plain pid - Enable socket busy polling with CONFIG_RT - Improve reliability and efficiency of reporting for ref_tracker - Auto-generate a user space C library for various Netlink families Protocols: - Allow TCP to shrink the advertised window when necessary, prevent sk_rcvbuf auto-tuning from growing the window all the way up to tcp_rmem[2] - Use per-VMA locking for "page-flipping" TCP receive zerocopy - Prepare TCP for device-to-device data transfers, by making sure that payloads are always attached to skbs as page frags - Make the backoff time for the first N TCP SYN retransmissions linear. Exponential backoff is unnecessarily conservative - Create a new MPTCP getsockopt to retrieve all info (MPTCP_FULL_INFO) - Avoid waking up applications using TLS sockets until we have a full record - Allow using kernel memory for protocol ioctl callbacks, paving the way to issuing ioctls over io_uring - Add nolocalbypass option to VxLAN, forcing packets to be fully encapsulated even if they are destined for a local IP address - Make TCPv4 use consistent hash in TIME_WAIT and SYN_RECV. Ensure in-kernel ECMP implementation (e.g. Open vSwitch) select the same link for all packets. Support L4 symmetric hashing in Open vSwitch - PPPoE: make number of hash bits configurable - Allow DNS to be overwritten by DHCPACK in the in-kernel DHCP client (ipconfig) - Add layer 2 miss indication and filtering, allowing higher layers (e.g. ACL filters) to make forwarding decisions based on whether packet matched forwarding state in lower devices (bridge) - Support matching on Connectivity Fault Management (CFM) packets - Hide the "link becomes ready" IPv6 messages by demoting their printk level to debug - HSR: don't enable promiscuous mode if device offloads the proto - Support active scanning in IEEE 802.15.4 - Continue work on Multi-Link Operation for WiFi 7 BPF: - Add precision propagation for subprogs and callbacks. This allows maintaining verification efficiency when subprograms are used, or in fact passing the verifier at all for complex programs, especially those using open-coded iterators - Improve BPF's {g,s}setsockopt() length handling. Previously BPF assumed the length is always equal to the amount of written data. But some protos allow passing a NULL buffer to discover what the output buffer *should* be, without writing anything - Accept dynptr memory as memory arguments passed to helpers - Add routing table ID to bpf_fib_lookup BPF helper - Support O_PATH FDs in BPF_OBJ_PIN and BPF_OBJ_GET commands - Drop bpf_capable() check in BPF_MAP_FREEZE command (used to mark maps as read-only) - Show target_{obj,btf}_id in tracing link fdinfo - Addition of several new kfuncs (most of the names are self-explanatory): - Add a set of new dynptr kfuncs: bpf_dynptr_adjust(), bpf_dynptr_is_null(), bpf_dynptr_is_rdonly(), bpf_dynptr_size() and bpf_dynptr_clone(). - bpf_task_under_cgroup() - bpf_sock_destroy() - force closing sockets - bpf_cpumask_first_and(), rework bpf_cpumask_any*() kfuncs Netfilter: - Relax set/map validation checks in nf_tables. Allow checking presence of an entry in a map without using the value - Increase ip_vs_conn_tab_bits range for 64BIT builds - Allow updating size of a set - Improve NAT tuple selection when connection is closing Driver API: - Integrate netdev with LED subsystem, to allow configuring HW "offloaded" blinking of LEDs based on link state and activity (i.e. packets coming in and out) - Support configuring rate selection pins of SFP modules - Factor Clause 73 auto-negotiation code out of the drivers, provide common helper routines - Add more fool-proof helpers for managing lifetime of MDIO devices associated with the PCS layer - Allow drivers to report advanced statistics related to Time Aware scheduler offload (taprio) - Allow opting out of VF statistics in link dump, to allow more VFs to fit into the message - Split devlink instance and devlink port operations New hardware / drivers: - Ethernet: - Synopsys EMAC4 IP support (stmmac) - Marvell 88E6361 8 port (5x1GE + 3x2.5GE) switches - Marvell 88E6250 7 port switches - Microchip LAN8650/1 Rev.B0 PHYs - MediaTek MT7981/MT7988 built-in 1GE PHY driver - WiFi: - Realtek RTL8192FU, 2.4 GHz, b/g/n mode, 2T2R, 300 Mbps - Realtek RTL8723DS (SDIO variant) - Realtek RTL8851BE - CAN: - Fintek F81604 Drivers: - Ethernet NICs: - Intel (100G, ice): - support dynamic interrupt allocation - use meta data match instead of VF MAC addr on slow-path - nVidia/Mellanox: - extend link aggregation to handle 4, rather than just 2 ports - spawn sub-functions without any features by default - OcteonTX2: - support HTB (Tx scheduling/QoS) offload - make RSS hash generation configurable - support selecting Rx queue using TC filters - Wangxun (ngbe/txgbe): - add basic Tx/Rx packet offloads - add phylink support (SFP/PCS control) - Freescale/NXP (enetc): - report TAPRIO packet statistics - Solarflare/AMD: - support matching on IP ToS and UDP source port of outer header - VxLAN and GENEVE tunnel encapsulation over IPv4 or IPv6 - add devlink dev info support for EF10 - Virtual NICs: - Microsoft vNIC: - size the Rx indirection table based on requested configuration - support VLAN tagging - Amazon vNIC: - try to reuse Rx buffers if not fully consumed, useful for ARM servers running with 16kB pages - Google vNIC: - support TCP segmentation of >64kB frames - Ethernet embedded switches: - Marvell (mv88e6xxx): - enable USXGMII (88E6191X) - Microchip: - lan966x: add support for Egress Stage 0 ACL engine - lan966x: support mapping packet priority to internal switch priority (based on PCP or DSCP) - Ethernet PHYs: - Broadcom PHYs: - support for Wake-on-LAN for BCM54210E/B50212E - report LPI counter - Microsemi PHYs: support RGMII delay configuration (VSC85xx) - Micrel PHYs: receive timestamp in the frame (LAN8841) - Realtek PHYs: support optional external PHY clock - Altera TSE PCS: merge the driver into Lynx PCS which it is a variant of - CAN: Kvaser PCIEcan: - support packet timestamping - WiFi: - Intel (iwlwifi): - major update for new firmware and Multi-Link Operation (MLO) - configuration rework to drop test devices and split the different families - support for segmented PNVM images and power tables - new vendor entries for PPAG (platform antenna gain) feature - Qualcomm 802.11ax (ath11k): - Multiple Basic Service Set Identifier (MBSSID) and Enhanced MBSSID Advertisement (EMA) support in AP mode - support factory test mode - RealTek (rtw89): - add RSSI based antenna diversity - support U-NII-4 channels on 5 GHz band - RealTek (rtl8xxxu): - AP mode support for 8188f - support USB RX aggregation for the newer chips" * tag 'net-next-6.5' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (1602 commits) net: scm: introduce and use scm_recv_unix helper af_unix: Skip SCM_PIDFD if scm->pid is NULL. net: lan743x: Simplify comparison netlink: Add __sock_i_ino() for __netlink_diag_dump(). net: dsa: avoid suspicious RCU usage for synced VLAN-aware MAC addresses Revert "af_unix: Call scm_recv() only after scm_set_cred()." phylink: ReST-ify the phylink_pcs_neg_mode() kdoc libceph: Partially revert changes to support MSG_SPLICE_PAGES net: phy: mscc: fix packet loss due to RGMII delays net: mana: use vmalloc_array and vcalloc net: enetc: use vmalloc_array and vcalloc ionic: use vmalloc_array and vcalloc pds_core: use vmalloc_array and vcalloc gve: use vmalloc_array and vcalloc octeon_ep: use vmalloc_array and vcalloc net: usb: qmi_wwan: add u-blox 0x1312 composition perf trace: fix MSG_SPLICE_PAGES build error ipvlan: Fix return value of ipvlan_queue_xmit() netfilter: nf_tables: fix underflow in chain reference counter netfilter: nf_tables: unbind non-anonymous set if rule construction fails ...
Diffstat (limited to 'net')
-rw-r--r--net/Kconfig2
-rw-r--r--net/appletalk/ddp.c1
-rw-r--r--net/atm/pvc.c1
-rw-r--r--net/atm/svc.c1
-rw-r--r--net/ax25/af_ax25.c1
-rw-r--r--net/bpf/test_run.c204
-rw-r--r--net/bpfilter/bpfilter_kern.c2
-rw-r--r--net/bridge/br_device.c1
-rw-r--r--net/bridge/br_forward.c3
-rw-r--r--net/bridge/br_input.c1
-rw-r--r--net/bridge/br_private.h27
-rw-r--r--net/caif/caif_socket.c2
-rw-r--r--net/can/bcm.c1
-rw-r--r--net/can/isotp.c6
-rw-r--r--net/can/j1939/socket.c1
-rw-r--r--net/can/raw.c1
-rw-r--r--net/ceph/messenger_v1.c30
-rw-r--r--net/ceph/messenger_v2.c19
-rw-r--r--net/core/Makefile2
-rw-r--r--net/core/dev.c158
-rw-r--r--net/core/filter.c212
-rw-r--r--net/core/flow_dissector.c40
-rw-r--r--net/core/gro.c114
-rw-r--r--net/core/gso.c273
-rw-r--r--net/core/net_namespace.c4
-rw-r--r--net/core/netdev-genl-gen.c2
-rw-r--r--net/core/netdev-genl-gen.h2
-rw-r--r--net/core/netpoll.c5
-rw-r--r--net/core/pktgen.c13
-rw-r--r--net/core/rtnetlink.c187
-rw-r--r--net/core/skbuff.c308
-rw-r--r--net/core/sock.c160
-rw-r--r--net/core/sock_map.c4
-rw-r--r--net/dccp/dccp.h2
-rw-r--r--net/dccp/ipv4.c1
-rw-r--r--net/dccp/ipv6.c1
-rw-r--r--net/dccp/proto.c12
-rw-r--r--net/devlink/health.c2
-rw-r--r--net/devlink/leftover.c196
-rw-r--r--net/dsa/dsa.c2
-rw-r--r--net/dsa/port.c32
-rw-r--r--net/dsa/slave.c84
-rw-r--r--net/dsa/switch.c4
-rw-r--r--net/dsa/switch.h3
-rw-r--r--net/ethtool/ioctl.c15
-rw-r--r--net/ethtool/netlink.c12
-rw-r--r--net/handshake/genl.c2
-rw-r--r--net/handshake/genl.h2
-rw-r--r--net/hsr/hsr_device.c5
-rw-r--r--net/hsr/hsr_main.h1
-rw-r--r--net/hsr/hsr_slave.c15
-rw-r--r--net/ieee802154/header_ops.c36
-rw-r--r--net/ieee802154/nl802154.c13
-rw-r--r--net/ieee802154/socket.c17
-rw-r--r--net/ipv4/af_inet.c56
-rw-r--r--net/ipv4/bpfilter/sockopt.c11
-rw-r--r--net/ipv4/esp4_offload.c1
-rw-r--r--net/ipv4/fou_nl.c2
-rw-r--r--net/ipv4/fou_nl.h2
-rw-r--r--net/ipv4/gre_offload.c1
-rw-r--r--net/ipv4/inet_connection_sock.c21
-rw-r--r--net/ipv4/ip_gre.c8
-rw-r--r--net/ipv4/ip_output.c170
-rw-r--r--net/ipv4/ipconfig.c10
-rw-r--r--net/ipv4/ipmr.c63
-rw-r--r--net/ipv4/ping.c56
-rw-r--r--net/ipv4/raw.c26
-rw-r--r--net/ipv4/syncookies.c4
-rw-r--r--net/ipv4/sysctl_net_ipv4.c19
-rw-r--r--net/ipv4/tcp.c334
-rw-r--r--net/ipv4/tcp_bpf.c73
-rw-r--r--net/ipv4/tcp_input.c2
-rw-r--r--net/ipv4/tcp_ipv4.c26
-rw-r--r--net/ipv4/tcp_minisocks.c2
-rw-r--r--net/ipv4/tcp_offload.c8
-rw-r--r--net/ipv4/tcp_output.c195
-rw-r--r--net/ipv4/tcp_timer.c17
-rw-r--r--net/ipv4/udp.c375
-rw-r--r--net/ipv4/udp_impl.h2
-rw-r--r--net/ipv4/udp_offload.c1
-rw-r--r--net/ipv4/udplite.c1
-rw-r--r--net/ipv6/addrconf.c4
-rw-r--r--net/ipv6/af_inet6.c6
-rw-r--r--net/ipv6/esp6_offload.c1
-rw-r--r--net/ipv6/exthdrs.c36
-rw-r--r--net/ipv6/ip6_offload.c1
-rw-r--r--net/ipv6/ip6_output.c19
-rw-r--r--net/ipv6/ip6mr.c44
-rw-r--r--net/ipv6/raw.c17
-rw-r--r--net/ipv6/route.c25
-rw-r--r--net/ipv6/rpl.c7
-rw-r--r--net/ipv6/seg6_iptunnel.c3
-rw-r--r--net/ipv6/tcp_ipv6.c12
-rw-r--r--net/ipv6/tcpv6_offload.c3
-rw-r--r--net/ipv6/udp.c15
-rw-r--r--net/ipv6/udp_offload.c1
-rw-r--r--net/kcm/kcmsock.c339
-rw-r--r--net/key/af_key.c1
-rw-r--r--net/l2tp/l2tp_core.h2
-rw-r--r--net/l2tp/l2tp_ip.c10
-rw-r--r--net/l2tp/l2tp_ip6.c1
-rw-r--r--net/llc/af_llc.c1
-rw-r--r--net/mac80211/agg-tx.c14
-rw-r--r--net/mac80211/cfg.c102
-rw-r--r--net/mac80211/chan.c13
-rw-r--r--net/mac80211/debug.h8
-rw-r--r--net/mac80211/debugfs_netdev.c21
-rw-r--r--net/mac80211/debugfs_sta.c185
-rw-r--r--net/mac80211/driver-ops.h10
-rw-r--r--net/mac80211/eht.c5
-rw-r--r--net/mac80211/he.c3
-rw-r--r--net/mac80211/ht.c5
-rw-r--r--net/mac80211/ibss.c38
-rw-r--r--net/mac80211/ieee80211_i.h69
-rw-r--r--net/mac80211/iface.c48
-rw-r--r--net/mac80211/key.c8
-rw-r--r--net/mac80211/link.c57
-rw-r--r--net/mac80211/main.c7
-rw-r--r--net/mac80211/mesh.c40
-rw-r--r--net/mac80211/mesh.h19
-rw-r--r--net/mac80211/mesh_hwmp.c6
-rw-r--r--net/mac80211/mesh_plink.c37
-rw-r--r--net/mac80211/mesh_ps.c7
-rw-r--r--net/mac80211/mlme.c568
-rw-r--r--net/mac80211/ocb.c10
-rw-r--r--net/mac80211/offchannel.c4
-rw-r--r--net/mac80211/rx.c47
-rw-r--r--net/mac80211/scan.c95
-rw-r--r--net/mac80211/sta_info.c240
-rw-r--r--net/mac80211/status.c6
-rw-r--r--net/mac80211/tdls.c276
-rw-r--r--net/mac80211/trace.h10
-rw-r--r--net/mac80211/tx.c73
-rw-r--r--net/mac80211/util.c312
-rw-r--r--net/mac802154/ieee802154_i.h21
-rw-r--r--net/mac802154/main.c2
-rw-r--r--net/mac802154/rx.c70
-rw-r--r--net/mac802154/scan.c68
-rw-r--r--net/mctp/af_mctp.c1
-rw-r--r--net/mctp/route.c3
-rw-r--r--net/mpls/af_mpls.c1
-rw-r--r--net/mpls/mpls_gso.c1
-rw-r--r--net/mptcp/mib.c6
-rw-r--r--net/mptcp/mib.h18
-rw-r--r--net/mptcp/options.c19
-rw-r--r--net/mptcp/pm.c47
-rw-r--r--net/mptcp/pm_netlink.c142
-rw-r--r--net/mptcp/pm_userspace.c5
-rw-r--r--net/mptcp/protocol.c65
-rw-r--r--net/mptcp/protocol.h20
-rw-r--r--net/mptcp/sockopt.c153
-rw-r--r--net/mptcp/subflow.c2
-rw-r--r--net/ncsi/ncsi-rsp.c93
-rw-r--r--net/netfilter/ipset/ip_set_core.c2
-rw-r--r--net/netfilter/ipvs/Kconfig27
-rw-r--r--net/netfilter/ipvs/ip_vs_conn.c26
-rw-r--r--net/netfilter/ipvs/ip_vs_xmit.c4
-rw-r--r--net/netfilter/nf_conntrack_proto_dccp.c52
-rw-r--r--net/netfilter/nf_conntrack_proto_gre.c1
-rw-r--r--net/netfilter/nf_conntrack_sip.c2
-rw-r--r--net/netfilter/nf_flow_table_core.c24
-rw-r--r--net/netfilter/nf_flow_table_ip.c232
-rw-r--r--net/netfilter/nf_nat_core.c92
-rw-r--r--net/netfilter/nf_tables_api.c89
-rw-r--r--net/netfilter/nfnetlink_queue.c1
-rw-r--r--net/netfilter/nft_bitwise.c2
-rw-r--r--net/netfilter/nft_byteorder.c6
-rw-r--r--net/netfilter/nft_ct.c2
-rw-r--r--net/netfilter/nft_dynset.c2
-rw-r--r--net/netfilter/nft_exthdr.c110
-rw-r--r--net/netfilter/nft_flow_offload.c12
-rw-r--r--net/netfilter/nft_fwd_netdev.c2
-rw-r--r--net/netfilter/nft_hash.c2
-rw-r--r--net/netfilter/nft_lookup.c23
-rw-r--r--net/netfilter/nft_meta.c2
-rw-r--r--net/netfilter/nft_payload.c3
-rw-r--r--net/netfilter/nft_range.c2
-rw-r--r--net/netfilter/nft_reject.c2
-rw-r--r--net/netfilter/nft_rt.c2
-rw-r--r--net/netfilter/nft_set_pipapo.c6
-rw-r--r--net/netfilter/nft_socket.c4
-rw-r--r--net/netfilter/nft_tproxy.c2
-rw-r--r--net/netfilter/nft_tunnel.c4
-rw-r--r--net/netfilter/nft_xfrm.c4
-rw-r--r--net/netlabel/netlabel_domainhash.h2
-rw-r--r--net/netlink/af_netlink.c8
-rw-r--r--net/netlink/diag.c7
-rw-r--r--net/netlink/genetlink.c2
-rw-r--r--net/netrom/af_netrom.c1
-rw-r--r--net/nfc/llcp.h1
-rw-r--r--net/nfc/llcp_commands.c15
-rw-r--r--net/nfc/llcp_core.c49
-rw-r--r--net/nfc/llcp_sock.c18
-rw-r--r--net/nfc/netlink.c20
-rw-r--r--net/nfc/nfc.h1
-rw-r--r--net/nsh/nsh.c1
-rw-r--r--net/openvswitch/actions.c13
-rw-r--r--net/openvswitch/datapath.c1
-rw-r--r--net/openvswitch/flow_netlink.c2
-rw-r--r--net/openvswitch/meter.c4
-rw-r--r--net/packet/af_packet.c2
-rw-r--r--net/phonet/datagram.c11
-rw-r--r--net/phonet/pep.c11
-rw-r--r--net/phonet/socket.c4
-rw-r--r--net/qrtr/af_qrtr.c1
-rw-r--r--net/rds/af_rds.c1
-rw-r--r--net/rds/tcp_send.c23
-rw-r--r--net/rose/af_rose.c1
-rw-r--r--net/rxrpc/af_rxrpc.c1
-rw-r--r--net/sched/act_pedit.c4
-rw-r--r--net/sched/act_police.c1
-rw-r--r--net/sched/cls_flower.c132
-rw-r--r--net/sched/sch_cake.c1
-rw-r--r--net/sched/sch_htb.c7
-rw-r--r--net/sched/sch_netem.c60
-rw-r--r--net/sched/sch_taprio.c90
-rw-r--r--net/sched/sch_tbf.c1
-rw-r--r--net/sctp/offload.c1
-rw-r--r--net/sctp/protocol.c5
-rw-r--r--net/sctp/socket.c26
-rw-r--r--net/sctp/stream_sched.c9
-rw-r--r--net/smc/af_smc.c29
-rw-r--r--net/smc/smc_stats.c2
-rw-r--r--net/smc/smc_stats.h1
-rw-r--r--net/smc/smc_tx.c19
-rw-r--r--net/smc/smc_tx.h2
-rw-r--r--net/socket.c86
-rw-r--r--net/sunrpc/svcsock.c38
-rw-r--r--net/tipc/bearer.c18
-rw-r--r--net/tipc/bearer.h4
-rw-r--r--net/tipc/socket.c3
-rw-r--r--net/tipc/udp_media.c4
-rw-r--r--net/tls/tls.h8
-rw-r--r--net/tls/tls_device.c110
-rw-r--r--net/tls/tls_device_fallback.c2
-rw-r--r--net/tls/tls_main.c70
-rw-r--r--net/tls/tls_sw.c249
-rw-r--r--net/unix/Kconfig6
-rw-r--r--net/unix/af_unix.c226
-rw-r--r--net/vmw_vsock/af_vsock.c3
-rw-r--r--net/wireless/core.c174
-rw-r--r--net/wireless/core.h14
-rw-r--r--net/wireless/nl80211.c119
-rw-r--r--net/wireless/pmsr.c4
-rw-r--r--net/wireless/rdev-ops.h27
-rw-r--r--net/wireless/reg.c20
-rw-r--r--net/wireless/scan.c1263
-rw-r--r--net/wireless/sme.c19
-rw-r--r--net/wireless/sysfs.c8
-rw-r--r--net/wireless/trace.h47
-rw-r--r--net/wireless/util.c110
-rw-r--r--net/wireless/wext-core.c6
-rw-r--r--net/wireless/wext-sme.c4
-rw-r--r--net/x25/af_x25.c1
-rw-r--r--net/xdp/xsk.c1
-rw-r--r--net/xdp/xsk_buff_pool.c7
-rw-r--r--net/xdp/xskmap.c4
-rw-r--r--net/xfrm/espintcp.c14
-rw-r--r--net/xfrm/xfrm_device.c1
-rw-r--r--net/xfrm/xfrm_interface_core.c1
-rw-r--r--net/xfrm/xfrm_ipcomp.c5
-rw-r--r--net/xfrm/xfrm_output.c1
262 files changed, 6923 insertions, 4447 deletions
diff --git a/net/Kconfig b/net/Kconfig
index 7d39c1773eb4..2fb25b534df5 100644
--- a/net/Kconfig
+++ b/net/Kconfig
@@ -324,7 +324,7 @@ config CGROUP_NET_CLASSID
config NET_RX_BUSY_POLL
bool
- default y if !PREEMPT_RT
+ default y if !PREEMPT_RT || (PREEMPT_RT && !NETCONSOLE)
config BQL
bool
diff --git a/net/appletalk/ddp.c b/net/appletalk/ddp.c
index a06f4d4a6f47..8978fb6212ff 100644
--- a/net/appletalk/ddp.c
+++ b/net/appletalk/ddp.c
@@ -1929,7 +1929,6 @@ static const struct proto_ops atalk_dgram_ops = {
.sendmsg = atalk_sendmsg,
.recvmsg = atalk_recvmsg,
.mmap = sock_no_mmap,
- .sendpage = sock_no_sendpage,
};
static struct notifier_block ddp_notifier = {
diff --git a/net/atm/pvc.c b/net/atm/pvc.c
index 53e7d3f39e26..66d9a9bd5896 100644
--- a/net/atm/pvc.c
+++ b/net/atm/pvc.c
@@ -126,7 +126,6 @@ static const struct proto_ops pvc_proto_ops = {
.sendmsg = vcc_sendmsg,
.recvmsg = vcc_recvmsg,
.mmap = sock_no_mmap,
- .sendpage = sock_no_sendpage,
};
diff --git a/net/atm/svc.c b/net/atm/svc.c
index d83556d8beb9..36a814f1fbd1 100644
--- a/net/atm/svc.c
+++ b/net/atm/svc.c
@@ -654,7 +654,6 @@ static const struct proto_ops svc_proto_ops = {
.sendmsg = vcc_sendmsg,
.recvmsg = vcc_recvmsg,
.mmap = sock_no_mmap,
- .sendpage = sock_no_sendpage,
};
diff --git a/net/ax25/af_ax25.c b/net/ax25/af_ax25.c
index d8da400cb4de..5db805d5f74d 100644
--- a/net/ax25/af_ax25.c
+++ b/net/ax25/af_ax25.c
@@ -2022,7 +2022,6 @@ static const struct proto_ops ax25_proto_ops = {
.sendmsg = ax25_sendmsg,
.recvmsg = ax25_recvmsg,
.mmap = sock_no_mmap,
- .sendpage = sock_no_sendpage,
};
/*
diff --git a/net/bpf/test_run.c b/net/bpf/test_run.c
index e79e3a415ca9..2321bd2f9964 100644
--- a/net/bpf/test_run.c
+++ b/net/bpf/test_run.c
@@ -561,29 +561,6 @@ __bpf_kfunc int bpf_modify_return_test(int a, int *b)
return a + *b;
}
-__bpf_kfunc u64 bpf_kfunc_call_test1(struct sock *sk, u32 a, u64 b, u32 c, u64 d)
-{
- return a + b + c + d;
-}
-
-__bpf_kfunc int bpf_kfunc_call_test2(struct sock *sk, u32 a, u32 b)
-{
- return a + b;
-}
-
-__bpf_kfunc struct sock *bpf_kfunc_call_test3(struct sock *sk)
-{
- return sk;
-}
-
-long noinline bpf_kfunc_call_test4(signed char a, short b, int c, long d)
-{
- /* Provoke the compiler to assume that the caller has sign-extended a,
- * b and c on platforms where this is required (e.g. s390x).
- */
- return (long)a + (long)b + (long)c + d;
-}
-
int noinline bpf_fentry_shadow_test(int a)
{
return a + 1;
@@ -606,32 +583,6 @@ struct prog_test_ref_kfunc {
refcount_t cnt;
};
-static struct prog_test_ref_kfunc prog_test_struct = {
- .a = 42,
- .b = 108,
- .next = &prog_test_struct,
- .cnt = REFCOUNT_INIT(1),
-};
-
-__bpf_kfunc struct prog_test_ref_kfunc *
-bpf_kfunc_call_test_acquire(unsigned long *scalar_ptr)
-{
- refcount_inc(&prog_test_struct.cnt);
- return &prog_test_struct;
-}
-
-__bpf_kfunc void bpf_kfunc_call_test_offset(struct prog_test_ref_kfunc *p)
-{
- WARN_ON_ONCE(1);
-}
-
-__bpf_kfunc struct prog_test_member *
-bpf_kfunc_call_memb_acquire(void)
-{
- WARN_ON_ONCE(1);
- return NULL;
-}
-
__bpf_kfunc void bpf_kfunc_call_test_release(struct prog_test_ref_kfunc *p)
{
refcount_dec(&p->cnt);
@@ -641,134 +592,6 @@ __bpf_kfunc void bpf_kfunc_call_memb_release(struct prog_test_member *p)
{
}
-__bpf_kfunc void bpf_kfunc_call_memb1_release(struct prog_test_member1 *p)
-{
- WARN_ON_ONCE(1);
-}
-
-static int *__bpf_kfunc_call_test_get_mem(struct prog_test_ref_kfunc *p, const int size)
-{
- if (size > 2 * sizeof(int))
- return NULL;
-
- return (int *)p;
-}
-
-__bpf_kfunc int *bpf_kfunc_call_test_get_rdwr_mem(struct prog_test_ref_kfunc *p,
- const int rdwr_buf_size)
-{
- return __bpf_kfunc_call_test_get_mem(p, rdwr_buf_size);
-}
-
-__bpf_kfunc int *bpf_kfunc_call_test_get_rdonly_mem(struct prog_test_ref_kfunc *p,
- const int rdonly_buf_size)
-{
- return __bpf_kfunc_call_test_get_mem(p, rdonly_buf_size);
-}
-
-/* the next 2 ones can't be really used for testing expect to ensure
- * that the verifier rejects the call.
- * Acquire functions must return struct pointers, so these ones are
- * failing.
- */
-__bpf_kfunc int *bpf_kfunc_call_test_acq_rdonly_mem(struct prog_test_ref_kfunc *p,
- const int rdonly_buf_size)
-{
- return __bpf_kfunc_call_test_get_mem(p, rdonly_buf_size);
-}
-
-__bpf_kfunc void bpf_kfunc_call_int_mem_release(int *p)
-{
-}
-
-struct prog_test_pass1 {
- int x0;
- struct {
- int x1;
- struct {
- int x2;
- struct {
- int x3;
- };
- };
- };
-};
-
-struct prog_test_pass2 {
- int len;
- short arr1[4];
- struct {
- char arr2[4];
- unsigned long arr3[8];
- } x;
-};
-
-struct prog_test_fail1 {
- void *p;
- int x;
-};
-
-struct prog_test_fail2 {
- int x8;
- struct prog_test_pass1 x;
-};
-
-struct prog_test_fail3 {
- int len;
- char arr1[2];
- char arr2[];
-};
-
-__bpf_kfunc void bpf_kfunc_call_test_pass_ctx(struct __sk_buff *skb)
-{
-}
-
-__bpf_kfunc void bpf_kfunc_call_test_pass1(struct prog_test_pass1 *p)
-{
-}
-
-__bpf_kfunc void bpf_kfunc_call_test_pass2(struct prog_test_pass2 *p)
-{
-}
-
-__bpf_kfunc void bpf_kfunc_call_test_fail1(struct prog_test_fail1 *p)
-{
-}
-
-__bpf_kfunc void bpf_kfunc_call_test_fail2(struct prog_test_fail2 *p)
-{
-}
-
-__bpf_kfunc void bpf_kfunc_call_test_fail3(struct prog_test_fail3 *p)
-{
-}
-
-__bpf_kfunc void bpf_kfunc_call_test_mem_len_pass1(void *mem, int mem__sz)
-{
-}
-
-__bpf_kfunc void bpf_kfunc_call_test_mem_len_fail1(void *mem, int len)
-{
-}
-
-__bpf_kfunc void bpf_kfunc_call_test_mem_len_fail2(u64 *mem, int len)
-{
-}
-
-__bpf_kfunc void bpf_kfunc_call_test_ref(struct prog_test_ref_kfunc *p)
-{
- /* p != NULL, but p->cnt could be 0 */
-}
-
-__bpf_kfunc void bpf_kfunc_call_test_destructive(void)
-{
-}
-
-__bpf_kfunc static u32 bpf_kfunc_call_test_static_unused_arg(u32 arg, u32 unused)
-{
- return arg;
-}
-
__diag_pop();
BTF_SET8_START(bpf_test_modify_return_ids)
@@ -782,32 +605,8 @@ static const struct btf_kfunc_id_set bpf_test_modify_return_set = {
};
BTF_SET8_START(test_sk_check_kfunc_ids)
-BTF_ID_FLAGS(func, bpf_kfunc_call_test1)
-BTF_ID_FLAGS(func, bpf_kfunc_call_test2)
-BTF_ID_FLAGS(func, bpf_kfunc_call_test3)
-BTF_ID_FLAGS(func, bpf_kfunc_call_test4)
-BTF_ID_FLAGS(func, bpf_kfunc_call_test_acquire, KF_ACQUIRE | KF_RET_NULL)
-BTF_ID_FLAGS(func, bpf_kfunc_call_memb_acquire, KF_ACQUIRE | KF_RET_NULL)
BTF_ID_FLAGS(func, bpf_kfunc_call_test_release, KF_RELEASE)
BTF_ID_FLAGS(func, bpf_kfunc_call_memb_release, KF_RELEASE)
-BTF_ID_FLAGS(func, bpf_kfunc_call_memb1_release, KF_RELEASE)
-BTF_ID_FLAGS(func, bpf_kfunc_call_test_get_rdwr_mem, KF_RET_NULL)
-BTF_ID_FLAGS(func, bpf_kfunc_call_test_get_rdonly_mem, KF_RET_NULL)
-BTF_ID_FLAGS(func, bpf_kfunc_call_test_acq_rdonly_mem, KF_ACQUIRE | KF_RET_NULL)
-BTF_ID_FLAGS(func, bpf_kfunc_call_int_mem_release, KF_RELEASE)
-BTF_ID_FLAGS(func, bpf_kfunc_call_test_pass_ctx)
-BTF_ID_FLAGS(func, bpf_kfunc_call_test_pass1)
-BTF_ID_FLAGS(func, bpf_kfunc_call_test_pass2)
-BTF_ID_FLAGS(func, bpf_kfunc_call_test_fail1)
-BTF_ID_FLAGS(func, bpf_kfunc_call_test_fail2)
-BTF_ID_FLAGS(func, bpf_kfunc_call_test_fail3)
-BTF_ID_FLAGS(func, bpf_kfunc_call_test_mem_len_pass1)
-BTF_ID_FLAGS(func, bpf_kfunc_call_test_mem_len_fail1)
-BTF_ID_FLAGS(func, bpf_kfunc_call_test_mem_len_fail2)
-BTF_ID_FLAGS(func, bpf_kfunc_call_test_ref, KF_TRUSTED_ARGS | KF_RCU)
-BTF_ID_FLAGS(func, bpf_kfunc_call_test_destructive, KF_DESTRUCTIVE)
-BTF_ID_FLAGS(func, bpf_kfunc_call_test_static_unused_arg)
-BTF_ID_FLAGS(func, bpf_kfunc_call_test_offset)
BTF_SET8_END(test_sk_check_kfunc_ids)
static void *bpf_test_init(const union bpf_attr *kattr, u32 user_size,
@@ -1415,11 +1214,10 @@ int bpf_prog_test_run_xdp(struct bpf_prog *prog, const union bpf_attr *kattr,
}
frag = &sinfo->frags[sinfo->nr_frags++];
- __skb_frag_set_page(frag, page);
data_len = min_t(u32, kattr->test.data_size_in - size,
PAGE_SIZE);
- skb_frag_size_set(frag, data_len);
+ skb_frag_fill_page_desc(frag, page, 0, data_len);
if (copy_from_user(page_address(page), data_in + size,
data_len)) {
diff --git a/net/bpfilter/bpfilter_kern.c b/net/bpfilter/bpfilter_kern.c
index 422ec6e7ccff..97e129e3f31c 100644
--- a/net/bpfilter/bpfilter_kern.c
+++ b/net/bpfilter/bpfilter_kern.c
@@ -21,7 +21,7 @@ static void shutdown_umh(void)
if (tgid) {
kill_pid(tgid, SIGKILL, 1);
wait_event(tgid->wait_pidfd, thread_group_exited(tgid));
- bpfilter_umh_cleanup(info);
+ umd_cleanup_helper(info);
}
}
diff --git a/net/bridge/br_device.c b/net/bridge/br_device.c
index 8eca8a5c80c6..9a5ea06236bd 100644
--- a/net/bridge/br_device.c
+++ b/net/bridge/br_device.c
@@ -39,6 +39,7 @@ netdev_tx_t br_dev_xmit(struct sk_buff *skb, struct net_device *dev)
u16 vid = 0;
memset(skb->cb, 0, sizeof(struct br_input_skb_cb));
+ br_tc_skb_miss_set(skb, false);
rcu_read_lock();
nf_ops = rcu_dereference(nf_br_ops);
diff --git a/net/bridge/br_forward.c b/net/bridge/br_forward.c
index 84d6dd5e5b1a..6116eba1bd89 100644
--- a/net/bridge/br_forward.c
+++ b/net/bridge/br_forward.c
@@ -203,6 +203,8 @@ void br_flood(struct net_bridge *br, struct sk_buff *skb,
struct net_bridge_port *prev = NULL;
struct net_bridge_port *p;
+ br_tc_skb_miss_set(skb, pkt_type != BR_PKT_BROADCAST);
+
list_for_each_entry_rcu(p, &br->port_list, list) {
/* Do not flood unicast traffic to ports that turn it off, nor
* other traffic if flood off, except for traffic we originate
@@ -295,6 +297,7 @@ void br_multicast_flood(struct net_bridge_mdb_entry *mdst,
allow_mode_include = false;
} else {
p = NULL;
+ br_tc_skb_miss_set(skb, true);
}
while (p || rp) {
diff --git a/net/bridge/br_input.c b/net/bridge/br_input.c
index fc17b9fd93e6..c34a0b0901b0 100644
--- a/net/bridge/br_input.c
+++ b/net/bridge/br_input.c
@@ -334,6 +334,7 @@ static rx_handler_result_t br_handle_frame(struct sk_buff **pskb)
return RX_HANDLER_CONSUMED;
memset(skb->cb, 0, sizeof(struct br_input_skb_cb));
+ br_tc_skb_miss_set(skb, false);
p = br_port_get_rcu(skb->dev);
if (p->flags & BR_VLAN_TUNNEL)
diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h
index 2119729ded2b..a63b32c1638e 100644
--- a/net/bridge/br_private.h
+++ b/net/bridge/br_private.h
@@ -15,6 +15,7 @@
#include <linux/u64_stats_sync.h>
#include <net/route.h>
#include <net/ip6_fib.h>
+#include <net/pkt_cls.h>
#include <linux/if_vlan.h>
#include <linux/rhashtable.h>
#include <linux/refcount.h>
@@ -754,6 +755,32 @@ void br_boolopt_multi_get(const struct net_bridge *br,
struct br_boolopt_multi *bm);
void br_opt_toggle(struct net_bridge *br, enum net_bridge_opts opt, bool on);
+#if IS_ENABLED(CONFIG_NET_TC_SKB_EXT)
+static inline void br_tc_skb_miss_set(struct sk_buff *skb, bool miss)
+{
+ struct tc_skb_ext *ext;
+
+ if (!tc_skb_ext_tc_enabled())
+ return;
+
+ ext = skb_ext_find(skb, TC_SKB_EXT);
+ if (ext) {
+ ext->l2_miss = miss;
+ return;
+ }
+ if (!miss)
+ return;
+ ext = tc_skb_ext_alloc(skb);
+ if (!ext)
+ return;
+ ext->l2_miss = true;
+}
+#else
+static inline void br_tc_skb_miss_set(struct sk_buff *skb, bool miss)
+{
+}
+#endif
+
/* br_device.c */
void br_dev_setup(struct net_device *dev);
void br_dev_delete(struct net_device *dev, struct list_head *list);
diff --git a/net/caif/caif_socket.c b/net/caif/caif_socket.c
index 4eebcc66c19a..9c82698da4f5 100644
--- a/net/caif/caif_socket.c
+++ b/net/caif/caif_socket.c
@@ -976,7 +976,6 @@ static const struct proto_ops caif_seqpacket_ops = {
.sendmsg = caif_seqpkt_sendmsg,
.recvmsg = caif_seqpkt_recvmsg,
.mmap = sock_no_mmap,
- .sendpage = sock_no_sendpage,
};
static const struct proto_ops caif_stream_ops = {
@@ -996,7 +995,6 @@ static const struct proto_ops caif_stream_ops = {
.sendmsg = caif_stream_sendmsg,
.recvmsg = caif_stream_recvmsg,
.mmap = sock_no_mmap,
- .sendpage = sock_no_sendpage,
};
/* This function is called when a socket is finally destroyed. */
diff --git a/net/can/bcm.c b/net/can/bcm.c
index a962ec2b8ba5..9ba35685b043 100644
--- a/net/can/bcm.c
+++ b/net/can/bcm.c
@@ -1703,7 +1703,6 @@ static const struct proto_ops bcm_ops = {
.sendmsg = bcm_sendmsg,
.recvmsg = bcm_recvmsg,
.mmap = sock_no_mmap,
- .sendpage = sock_no_sendpage,
};
static struct proto bcm_proto __read_mostly = {
diff --git a/net/can/isotp.c b/net/can/isotp.c
index 84f9aba02901..99770ed28531 100644
--- a/net/can/isotp.c
+++ b/net/can/isotp.c
@@ -1112,8 +1112,9 @@ wait_free_buffer:
if (err)
goto err_event_drop;
- if (sk->sk_err)
- return -sk->sk_err;
+ err = sock_error(sk);
+ if (err)
+ return err;
}
return size;
@@ -1699,7 +1700,6 @@ static const struct proto_ops isotp_ops = {
.sendmsg = isotp_sendmsg,
.recvmsg = isotp_recvmsg,
.mmap = sock_no_mmap,
- .sendpage = sock_no_sendpage,
};
static struct proto isotp_proto __read_mostly = {
diff --git a/net/can/j1939/socket.c b/net/can/j1939/socket.c
index 35970c25496a..feaec4ad6d16 100644
--- a/net/can/j1939/socket.c
+++ b/net/can/j1939/socket.c
@@ -1306,7 +1306,6 @@ static const struct proto_ops j1939_ops = {
.sendmsg = j1939_sk_sendmsg,
.recvmsg = j1939_sk_recvmsg,
.mmap = sock_no_mmap,
- .sendpage = sock_no_sendpage,
};
static struct proto j1939_proto __read_mostly = {
diff --git a/net/can/raw.c b/net/can/raw.c
index f64469b98260..15c79b079184 100644
--- a/net/can/raw.c
+++ b/net/can/raw.c
@@ -962,7 +962,6 @@ static const struct proto_ops raw_ops = {
.sendmsg = raw_sendmsg,
.recvmsg = raw_recvmsg,
.mmap = sock_no_mmap,
- .sendpage = sock_no_sendpage,
};
static struct proto raw_proto __read_mostly = {
diff --git a/net/ceph/messenger_v1.c b/net/ceph/messenger_v1.c
index d664cb1593a7..3d57bb48a2b4 100644
--- a/net/ceph/messenger_v1.c
+++ b/net/ceph/messenger_v1.c
@@ -75,18 +75,19 @@ static int ceph_tcp_sendmsg(struct socket *sock, struct kvec *iov,
}
/*
- * @more: either or both of MSG_MORE and MSG_SENDPAGE_NOTLAST
+ * @more: MSG_MORE or 0.
*/
static int ceph_tcp_sendpage(struct socket *sock, struct page *page,
int offset, size_t size, int more)
{
- ssize_t (*sendpage)(struct socket *sock, struct page *page,
- int offset, size_t size, int flags);
- int flags = MSG_DONTWAIT | MSG_NOSIGNAL | more;
+ struct msghdr msg = {
+ .msg_flags = MSG_DONTWAIT | MSG_NOSIGNAL | more,
+ };
+ struct bio_vec bvec;
int ret;
/*
- * sendpage cannot properly handle pages with page_count == 0,
+ * MSG_SPLICE_PAGES cannot properly handle pages with page_count == 0,
* we need to fall back to sendmsg if that's the case.
*
* Same goes for slab pages: skb_can_coalesce() allows
@@ -94,11 +95,12 @@ static int ceph_tcp_sendpage(struct socket *sock, struct page *page,
* triggers one of hardened usercopy checks.
*/
if (sendpage_ok(page))
- sendpage = sock->ops->sendpage;
- else
- sendpage = sock_no_sendpage;
+ msg.msg_flags |= MSG_SPLICE_PAGES;
+
+ bvec_set_page(&bvec, page, size, offset);
+ iov_iter_bvec(&msg.msg_iter, ITER_SOURCE, &bvec, 1, size);
- ret = sendpage(sock, page, offset, size, flags);
+ ret = sock_sendmsg(sock, &msg);
if (ret == -EAGAIN)
ret = 0;
@@ -464,7 +466,6 @@ static int write_partial_message_data(struct ceph_connection *con)
struct ceph_msg *msg = con->out_msg;
struct ceph_msg_data_cursor *cursor = &msg->cursor;
bool do_datacrc = !ceph_test_opt(from_msgr(con->msgr), NOCRC);
- int more = MSG_MORE | MSG_SENDPAGE_NOTLAST;
u32 crc;
dout("%s %p msg %p\n", __func__, con, msg);
@@ -493,10 +494,8 @@ static int write_partial_message_data(struct ceph_connection *con)
}
page = ceph_msg_data_next(cursor, &page_offset, &length);
- if (length == cursor->total_resid)
- more = MSG_MORE;
ret = ceph_tcp_sendpage(con->sock, page, page_offset, length,
- more);
+ MSG_MORE);
if (ret <= 0) {
if (do_datacrc)
msg->footer.data_crc = cpu_to_le32(crc);
@@ -526,17 +525,14 @@ static int write_partial_message_data(struct ceph_connection *con)
*/
static int write_partial_skip(struct ceph_connection *con)
{
- int more = MSG_MORE | MSG_SENDPAGE_NOTLAST;
int ret;
dout("%s %p %d left\n", __func__, con, con->v1.out_skip);
while (con->v1.out_skip > 0) {
size_t size = min(con->v1.out_skip, (int)PAGE_SIZE);
- if (size == con->v1.out_skip)
- more = MSG_MORE;
ret = ceph_tcp_sendpage(con->sock, ceph_zero_page, 0, size,
- more);
+ MSG_MORE);
if (ret <= 0)
goto out;
con->v1.out_skip -= ret;
diff --git a/net/ceph/messenger_v2.c b/net/ceph/messenger_v2.c
index 301a991dc6a6..1a888b86a494 100644
--- a/net/ceph/messenger_v2.c
+++ b/net/ceph/messenger_v2.c
@@ -155,7 +155,7 @@ static int do_try_sendpage(struct socket *sock, struct iov_iter *it)
it->bvec->bv_offset + it->iov_offset);
/*
- * sendpage cannot properly handle pages with
+ * MSG_SPLICE_PAGES cannot properly handle pages with
* page_count == 0, we need to fall back to sendmsg if
* that's the case.
*
@@ -163,14 +163,13 @@ static int do_try_sendpage(struct socket *sock, struct iov_iter *it)
* coalescing neighboring slab objects into a single frag
* which triggers one of hardened usercopy checks.
*/
- if (sendpage_ok(bv.bv_page)) {
- ret = sock->ops->sendpage(sock, bv.bv_page,
- bv.bv_offset, bv.bv_len,
- CEPH_MSG_FLAGS);
- } else {
- iov_iter_bvec(&msg.msg_iter, ITER_SOURCE, &bv, 1, bv.bv_len);
- ret = sock_sendmsg(sock, &msg);
- }
+ if (sendpage_ok(bv.bv_page))
+ msg.msg_flags |= MSG_SPLICE_PAGES;
+ else
+ msg.msg_flags &= ~MSG_SPLICE_PAGES;
+
+ iov_iter_bvec(&msg.msg_iter, ITER_SOURCE, &bv, 1, bv.bv_len);
+ ret = sock_sendmsg(sock, &msg);
if (ret <= 0) {
if (ret == -EAGAIN)
ret = 0;
@@ -185,7 +184,7 @@ static int do_try_sendpage(struct socket *sock, struct iov_iter *it)
/*
* Write as much as possible. The socket is expected to be corked,
- * so we don't bother with MSG_MORE/MSG_SENDPAGE_NOTLAST here.
+ * so we don't bother with MSG_MORE here.
*
* Return:
* 1 - done, nothing (else) to write
diff --git a/net/core/Makefile b/net/core/Makefile
index 8f367813bc68..731db2eaa610 100644
--- a/net/core/Makefile
+++ b/net/core/Makefile
@@ -13,7 +13,7 @@ obj-y += dev.o dev_addr_lists.o dst.o netevent.o \
neighbour.o rtnetlink.o utils.o link_watch.o filter.o \
sock_diag.o dev_ioctl.o tso.o sock_reuseport.o \
fib_notifier.o xdp.o flow_offload.o gro.o \
- netdev-genl.o netdev-genl-gen.o
+ netdev-genl.o netdev-genl-gen.o gso.o
obj-$(CONFIG_NETDEV_ADDR_LIST_TEST) += dev_addr_lists_test.o
diff --git a/net/core/dev.c b/net/core/dev.c
index c29f3e1db3ca..69a3e544676c 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -758,29 +758,43 @@ struct net_device *dev_get_by_name_rcu(struct net *net, const char *name)
}
EXPORT_SYMBOL(dev_get_by_name_rcu);
+/* Deprecated for new users, call netdev_get_by_name() instead */
+struct net_device *dev_get_by_name(struct net *net, const char *name)
+{
+ struct net_device *dev;
+
+ rcu_read_lock();
+ dev = dev_get_by_name_rcu(net, name);
+ dev_hold(dev);
+ rcu_read_unlock();
+ return dev;
+}
+EXPORT_SYMBOL(dev_get_by_name);
+
/**
- * dev_get_by_name - find a device by its name
+ * netdev_get_by_name() - find a device by its name
* @net: the applicable net namespace
* @name: name to find
+ * @tracker: tracking object for the acquired reference
+ * @gfp: allocation flags for the tracker
*
* Find an interface by name. This can be called from any
* context and does its own locking. The returned handle has
- * the usage count incremented and the caller must use dev_put() to
+ * the usage count incremented and the caller must use netdev_put() to
* release it when it is no longer needed. %NULL is returned if no
* matching device is found.
*/
-
-struct net_device *dev_get_by_name(struct net *net, const char *name)
+struct net_device *netdev_get_by_name(struct net *net, const char *name,
+ netdevice_tracker *tracker, gfp_t gfp)
{
struct net_device *dev;
- rcu_read_lock();
- dev = dev_get_by_name_rcu(net, name);
- dev_hold(dev);
- rcu_read_unlock();
+ dev = dev_get_by_name(net, name);
+ if (dev)
+ netdev_tracker_alloc(dev, tracker, gfp);
return dev;
}
-EXPORT_SYMBOL(dev_get_by_name);
+EXPORT_SYMBOL(netdev_get_by_name);
/**
* __dev_get_by_index - find a device by its ifindex
@@ -831,29 +845,42 @@ struct net_device *dev_get_by_index_rcu(struct net *net, int ifindex)
}
EXPORT_SYMBOL(dev_get_by_index_rcu);
+/* Deprecated for new users, call netdev_get_by_index() instead */
+struct net_device *dev_get_by_index(struct net *net, int ifindex)
+{
+ struct net_device *dev;
+
+ rcu_read_lock();
+ dev = dev_get_by_index_rcu(net, ifindex);
+ dev_hold(dev);
+ rcu_read_unlock();
+ return dev;
+}
+EXPORT_SYMBOL(dev_get_by_index);
/**
- * dev_get_by_index - find a device by its ifindex
+ * netdev_get_by_index() - find a device by its ifindex
* @net: the applicable net namespace
* @ifindex: index of device
+ * @tracker: tracking object for the acquired reference
+ * @gfp: allocation flags for the tracker
*
* Search for an interface by index. Returns NULL if the device
* is not found or a pointer to the device. The device returned has
* had a reference added and the pointer is safe until the user calls
- * dev_put to indicate they have finished with it.
+ * netdev_put() to indicate they have finished with it.
*/
-
-struct net_device *dev_get_by_index(struct net *net, int ifindex)
+struct net_device *netdev_get_by_index(struct net *net, int ifindex,
+ netdevice_tracker *tracker, gfp_t gfp)
{
struct net_device *dev;
- rcu_read_lock();
- dev = dev_get_by_index_rcu(net, ifindex);
- dev_hold(dev);
- rcu_read_unlock();
+ dev = dev_get_by_index(net, ifindex);
+ if (dev)
+ netdev_tracker_alloc(dev, tracker, gfp);
return dev;
}
-EXPORT_SYMBOL(dev_get_by_index);
+EXPORT_SYMBOL(netdev_get_by_index);
/**
* dev_get_by_napi_id - find a device by napi_id
@@ -3209,7 +3236,7 @@ static u16 skb_tx_hash(const struct net_device *dev,
return (u16) reciprocal_scale(skb_get_hash(skb), qcount) + qoffset;
}
-static void skb_warn_bad_offload(const struct sk_buff *skb)
+void skb_warn_bad_offload(const struct sk_buff *skb)
{
static const netdev_features_t null_features;
struct net_device *dev = skb->dev;
@@ -3338,74 +3365,6 @@ __be16 skb_network_protocol(struct sk_buff *skb, int *depth)
return vlan_get_protocol_and_depth(skb, type, depth);
}
-/* openvswitch calls this on rx path, so we need a different check.
- */
-static inline bool skb_needs_check(struct sk_buff *skb, bool tx_path)
-{
- if (tx_path)
- return skb->ip_summed != CHECKSUM_PARTIAL &&
- skb->ip_summed != CHECKSUM_UNNECESSARY;
-
- return skb->ip_summed == CHECKSUM_NONE;
-}
-
-/**
- * __skb_gso_segment - Perform segmentation on skb.
- * @skb: buffer to segment
- * @features: features for the output path (see dev->features)
- * @tx_path: whether it is called in TX path
- *
- * This function segments the given skb and returns a list of segments.
- *
- * It may return NULL if the skb requires no segmentation. This is
- * only possible when GSO is used for verifying header integrity.
- *
- * Segmentation preserves SKB_GSO_CB_OFFSET bytes of previous skb cb.
- */
-struct sk_buff *__skb_gso_segment(struct sk_buff *skb,
- netdev_features_t features, bool tx_path)
-{
- struct sk_buff *segs;
-
- if (unlikely(skb_needs_check(skb, tx_path))) {
- int err;
-
- /* We're going to init ->check field in TCP or UDP header */
- err = skb_cow_head(skb, 0);
- if (err < 0)
- return ERR_PTR(err);
- }
-
- /* Only report GSO partial support if it will enable us to
- * support segmentation on this frame without needing additional
- * work.
- */
- if (features & NETIF_F_GSO_PARTIAL) {
- netdev_features_t partial_features = NETIF_F_GSO_ROBUST;
- struct net_device *dev = skb->dev;
-
- partial_features |= dev->features & dev->gso_partial_features;
- if (!skb_gso_ok(skb, features | partial_features))
- features &= ~NETIF_F_GSO_PARTIAL;
- }
-
- BUILD_BUG_ON(SKB_GSO_CB_OFFSET +
- sizeof(*SKB_GSO_CB(skb)) > sizeof(skb->cb));
-
- SKB_GSO_CB(skb)->mac_offset = skb_headroom(skb);
- SKB_GSO_CB(skb)->encap_level = 0;
-
- skb_reset_mac_header(skb);
- skb_reset_mac_len(skb);
-
- segs = skb_mac_gso_segment(skb, features);
-
- if (segs != skb && unlikely(skb_needs_check(skb, tx_path) && !IS_ERR(segs)))
- skb_warn_bad_offload(skb);
-
- return segs;
-}
-EXPORT_SYMBOL(__skb_gso_segment);
/* Take action when hardware reception checksum errors are detected. */
#ifdef CONFIG_BUG
@@ -6199,7 +6158,8 @@ restart:
if (!napi)
goto out;
- preempt_disable();
+ if (!IS_ENABLED(CONFIG_PREEMPT_RT))
+ preempt_disable();
for (;;) {
int work = 0;
@@ -6241,7 +6201,8 @@ count:
if (unlikely(need_resched())) {
if (napi_poll)
busy_poll_stop(napi, have_poll_lock, prefer_busy_poll, budget);
- preempt_enable();
+ if (!IS_ENABLED(CONFIG_PREEMPT_RT))
+ preempt_enable();
rcu_read_unlock();
cond_resched();
if (loop_end(loop_end_arg, start_time))
@@ -6252,7 +6213,8 @@ count:
}
if (napi_poll)
busy_poll_stop(napi, have_poll_lock, prefer_busy_poll, budget);
- preempt_enable();
+ if (!IS_ENABLED(CONFIG_PREEMPT_RT))
+ preempt_enable();
out:
rcu_read_unlock();
}
@@ -8822,9 +8784,11 @@ int dev_set_mac_address(struct net_device *dev, struct sockaddr *sa,
err = dev_pre_changeaddr_notify(dev, sa->sa_data, extack);
if (err)
return err;
- err = ops->ndo_set_mac_address(dev, sa);
- if (err)
- return err;
+ if (memcmp(dev->dev_addr, sa->sa_data, dev->addr_len)) {
+ err = ops->ndo_set_mac_address(dev, sa);
+ if (err)
+ return err;
+ }
dev->addr_assign_type = NET_ADDR_SET;
call_netdevice_notifiers(NETDEV_CHANGEADDR, dev);
add_device_randomness(dev->dev_addr, dev->addr_len);
@@ -10570,8 +10534,10 @@ void netdev_sw_irq_coalesce_default_on(struct net_device *dev)
{
WARN_ON(dev->reg_state == NETREG_REGISTERED);
- dev->gro_flush_timeout = 20000;
- dev->napi_defer_hard_irqs = 1;
+ if (!IS_ENABLED(CONFIG_PREEMPT_RT)) {
+ dev->gro_flush_timeout = 20000;
+ dev->napi_defer_hard_irqs = 1;
+ }
}
EXPORT_SYMBOL_GPL(netdev_sw_irq_coalesce_default_on);
@@ -10632,7 +10598,7 @@ struct net_device *alloc_netdev_mqs(int sizeof_priv, const char *name,
dev = PTR_ALIGN(p, NETDEV_ALIGN);
dev->padded = (char *)dev - (char *)p;
- ref_tracker_dir_init(&dev->refcnt_tracker, 128);
+ ref_tracker_dir_init(&dev->refcnt_tracker, 128, name);
#ifdef CONFIG_PCPU_DEV_REFCNT
dev->pcpu_refcnt = alloc_percpu(int);
if (!dev->pcpu_refcnt)
diff --git a/net/core/filter.c b/net/core/filter.c
index d9ce04ca22ce..06ba0e56e369 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -3948,20 +3948,21 @@ void bpf_xdp_copy_buf(struct xdp_buff *xdp, unsigned long off,
void *bpf_xdp_pointer(struct xdp_buff *xdp, u32 offset, u32 len)
{
- struct skb_shared_info *sinfo = xdp_get_shared_info_from_buff(xdp);
u32 size = xdp->data_end - xdp->data;
+ struct skb_shared_info *sinfo;
void *addr = xdp->data;
int i;
if (unlikely(offset > 0xffff || len > 0xffff))
return ERR_PTR(-EFAULT);
- if (offset + len > xdp_get_buff_len(xdp))
+ if (unlikely(offset + len > xdp_get_buff_len(xdp)))
return ERR_PTR(-EINVAL);
- if (offset < size) /* linear area */
+ if (likely(offset < size)) /* linear area */
goto out;
+ sinfo = xdp_get_shared_info_from_buff(xdp);
offset -= size;
for (i = 0; i < sinfo->nr_frags; i++) { /* paged area */
u32 frag_size = skb_frag_size(&sinfo->frags[i]);
@@ -5803,6 +5804,12 @@ static int bpf_ipv4_fib_lookup(struct net *net, struct bpf_fib_lookup *params,
u32 tbid = l3mdev_fib_table_rcu(dev) ? : RT_TABLE_MAIN;
struct fib_table *tb;
+ if (flags & BPF_FIB_LOOKUP_TBID) {
+ tbid = params->tbid;
+ /* zero out for vlan output */
+ params->tbid = 0;
+ }
+
tb = fib_get_table(net, tbid);
if (unlikely(!tb))
return BPF_FIB_LKUP_RET_NOT_FWDED;
@@ -5936,6 +5943,12 @@ static int bpf_ipv6_fib_lookup(struct net *net, struct bpf_fib_lookup *params,
u32 tbid = l3mdev_fib_table_rcu(dev) ? : RT_TABLE_MAIN;
struct fib6_table *tb;
+ if (flags & BPF_FIB_LOOKUP_TBID) {
+ tbid = params->tbid;
+ /* zero out for vlan output */
+ params->tbid = 0;
+ }
+
tb = ipv6_stub->fib6_get_table(net, tbid);
if (unlikely(!tb))
return BPF_FIB_LKUP_RET_NOT_FWDED;
@@ -6008,7 +6021,7 @@ set_fwd_params:
#endif
#define BPF_FIB_LOOKUP_MASK (BPF_FIB_LOOKUP_DIRECT | BPF_FIB_LOOKUP_OUTPUT | \
- BPF_FIB_LOOKUP_SKIP_NEIGH)
+ BPF_FIB_LOOKUP_SKIP_NEIGH | BPF_FIB_LOOKUP_TBID)
BPF_CALL_4(bpf_xdp_fib_lookup, struct xdp_buff *, ctx,
struct bpf_fib_lookup *, params, int, plen, u32, flags)
@@ -6555,12 +6568,11 @@ static struct sock *sk_lookup(struct net *net, struct bpf_sock_tuple *tuple,
static struct sock *
__bpf_skc_lookup(struct sk_buff *skb, struct bpf_sock_tuple *tuple, u32 len,
struct net *caller_net, u32 ifindex, u8 proto, u64 netns_id,
- u64 flags)
+ u64 flags, int sdif)
{
struct sock *sk = NULL;
struct net *net;
u8 family;
- int sdif;
if (len == sizeof(tuple->ipv4))
family = AF_INET;
@@ -6572,10 +6584,12 @@ __bpf_skc_lookup(struct sk_buff *skb, struct bpf_sock_tuple *tuple, u32 len,
if (unlikely(flags || !((s32)netns_id < 0 || netns_id <= S32_MAX)))
goto out;
- if (family == AF_INET)
- sdif = inet_sdif(skb);
- else
- sdif = inet6_sdif(skb);
+ if (sdif < 0) {
+ if (family == AF_INET)
+ sdif = inet_sdif(skb);
+ else
+ sdif = inet6_sdif(skb);
+ }
if ((s32)netns_id < 0) {
net = caller_net;
@@ -6595,10 +6609,11 @@ out:
static struct sock *
__bpf_sk_lookup(struct sk_buff *skb, struct bpf_sock_tuple *tuple, u32 len,
struct net *caller_net, u32 ifindex, u8 proto, u64 netns_id,
- u64 flags)
+ u64 flags, int sdif)
{
struct sock *sk = __bpf_skc_lookup(skb, tuple, len, caller_net,
- ifindex, proto, netns_id, flags);
+ ifindex, proto, netns_id, flags,
+ sdif);
if (sk) {
struct sock *sk2 = sk_to_full_sk(sk);
@@ -6638,7 +6653,7 @@ bpf_skc_lookup(struct sk_buff *skb, struct bpf_sock_tuple *tuple, u32 len,
}
return __bpf_skc_lookup(skb, tuple, len, caller_net, ifindex, proto,
- netns_id, flags);
+ netns_id, flags, -1);
}
static struct sock *
@@ -6727,6 +6742,78 @@ static const struct bpf_func_proto bpf_sk_lookup_udp_proto = {
.arg5_type = ARG_ANYTHING,
};
+BPF_CALL_5(bpf_tc_skc_lookup_tcp, struct sk_buff *, skb,
+ struct bpf_sock_tuple *, tuple, u32, len, u64, netns_id, u64, flags)
+{
+ struct net_device *dev = skb->dev;
+ int ifindex = dev->ifindex, sdif = dev_sdif(dev);
+ struct net *caller_net = dev_net(dev);
+
+ return (unsigned long)__bpf_skc_lookup(skb, tuple, len, caller_net,
+ ifindex, IPPROTO_TCP, netns_id,
+ flags, sdif);
+}
+
+static const struct bpf_func_proto bpf_tc_skc_lookup_tcp_proto = {
+ .func = bpf_tc_skc_lookup_tcp,
+ .gpl_only = false,
+ .pkt_access = true,
+ .ret_type = RET_PTR_TO_SOCK_COMMON_OR_NULL,
+ .arg1_type = ARG_PTR_TO_CTX,
+ .arg2_type = ARG_PTR_TO_MEM | MEM_RDONLY,
+ .arg3_type = ARG_CONST_SIZE,
+ .arg4_type = ARG_ANYTHING,
+ .arg5_type = ARG_ANYTHING,
+};
+
+BPF_CALL_5(bpf_tc_sk_lookup_tcp, struct sk_buff *, skb,
+ struct bpf_sock_tuple *, tuple, u32, len, u64, netns_id, u64, flags)
+{
+ struct net_device *dev = skb->dev;
+ int ifindex = dev->ifindex, sdif = dev_sdif(dev);
+ struct net *caller_net = dev_net(dev);
+
+ return (unsigned long)__bpf_sk_lookup(skb, tuple, len, caller_net,
+ ifindex, IPPROTO_TCP, netns_id,
+ flags, sdif);
+}
+
+static const struct bpf_func_proto bpf_tc_sk_lookup_tcp_proto = {
+ .func = bpf_tc_sk_lookup_tcp,
+ .gpl_only = false,
+ .pkt_access = true,
+ .ret_type = RET_PTR_TO_SOCKET_OR_NULL,
+ .arg1_type = ARG_PTR_TO_CTX,
+ .arg2_type = ARG_PTR_TO_MEM | MEM_RDONLY,
+ .arg3_type = ARG_CONST_SIZE,
+ .arg4_type = ARG_ANYTHING,
+ .arg5_type = ARG_ANYTHING,
+};
+
+BPF_CALL_5(bpf_tc_sk_lookup_udp, struct sk_buff *, skb,
+ struct bpf_sock_tuple *, tuple, u32, len, u64, netns_id, u64, flags)
+{
+ struct net_device *dev = skb->dev;
+ int ifindex = dev->ifindex, sdif = dev_sdif(dev);
+ struct net *caller_net = dev_net(dev);
+
+ return (unsigned long)__bpf_sk_lookup(skb, tuple, len, caller_net,
+ ifindex, IPPROTO_UDP, netns_id,
+ flags, sdif);
+}
+
+static const struct bpf_func_proto bpf_tc_sk_lookup_udp_proto = {
+ .func = bpf_tc_sk_lookup_udp,
+ .gpl_only = false,
+ .pkt_access = true,
+ .ret_type = RET_PTR_TO_SOCKET_OR_NULL,
+ .arg1_type = ARG_PTR_TO_CTX,
+ .arg2_type = ARG_PTR_TO_MEM | MEM_RDONLY,
+ .arg3_type = ARG_CONST_SIZE,
+ .arg4_type = ARG_ANYTHING,
+ .arg5_type = ARG_ANYTHING,
+};
+
BPF_CALL_1(bpf_sk_release, struct sock *, sk)
{
if (sk && sk_is_refcounted(sk))
@@ -6744,12 +6831,13 @@ static const struct bpf_func_proto bpf_sk_release_proto = {
BPF_CALL_5(bpf_xdp_sk_lookup_udp, struct xdp_buff *, ctx,
struct bpf_sock_tuple *, tuple, u32, len, u32, netns_id, u64, flags)
{
- struct net *caller_net = dev_net(ctx->rxq->dev);
- int ifindex = ctx->rxq->dev->ifindex;
+ struct net_device *dev = ctx->rxq->dev;
+ int ifindex = dev->ifindex, sdif = dev_sdif(dev);
+ struct net *caller_net = dev_net(dev);
return (unsigned long)__bpf_sk_lookup(NULL, tuple, len, caller_net,
ifindex, IPPROTO_UDP, netns_id,
- flags);
+ flags, sdif);
}
static const struct bpf_func_proto bpf_xdp_sk_lookup_udp_proto = {
@@ -6767,12 +6855,13 @@ static const struct bpf_func_proto bpf_xdp_sk_lookup_udp_proto = {
BPF_CALL_5(bpf_xdp_skc_lookup_tcp, struct xdp_buff *, ctx,
struct bpf_sock_tuple *, tuple, u32, len, u32, netns_id, u64, flags)
{
- struct net *caller_net = dev_net(ctx->rxq->dev);
- int ifindex = ctx->rxq->dev->ifindex;
+ struct net_device *dev = ctx->rxq->dev;
+ int ifindex = dev->ifindex, sdif = dev_sdif(dev);
+ struct net *caller_net = dev_net(dev);
return (unsigned long)__bpf_skc_lookup(NULL, tuple, len, caller_net,
ifindex, IPPROTO_TCP, netns_id,
- flags);
+ flags, sdif);
}
static const struct bpf_func_proto bpf_xdp_skc_lookup_tcp_proto = {
@@ -6790,12 +6879,13 @@ static const struct bpf_func_proto bpf_xdp_skc_lookup_tcp_proto = {
BPF_CALL_5(bpf_xdp_sk_lookup_tcp, struct xdp_buff *, ctx,
struct bpf_sock_tuple *, tuple, u32, len, u32, netns_id, u64, flags)
{
- struct net *caller_net = dev_net(ctx->rxq->dev);
- int ifindex = ctx->rxq->dev->ifindex;
+ struct net_device *dev = ctx->rxq->dev;
+ int ifindex = dev->ifindex, sdif = dev_sdif(dev);
+ struct net *caller_net = dev_net(dev);
return (unsigned long)__bpf_sk_lookup(NULL, tuple, len, caller_net,
ifindex, IPPROTO_TCP, netns_id,
- flags);
+ flags, sdif);
}
static const struct bpf_func_proto bpf_xdp_sk_lookup_tcp_proto = {
@@ -6815,7 +6905,8 @@ BPF_CALL_5(bpf_sock_addr_skc_lookup_tcp, struct bpf_sock_addr_kern *, ctx,
{
return (unsigned long)__bpf_skc_lookup(NULL, tuple, len,
sock_net(ctx->sk), 0,
- IPPROTO_TCP, netns_id, flags);
+ IPPROTO_TCP, netns_id, flags,
+ -1);
}
static const struct bpf_func_proto bpf_sock_addr_skc_lookup_tcp_proto = {
@@ -6834,7 +6925,7 @@ BPF_CALL_5(bpf_sock_addr_sk_lookup_tcp, struct bpf_sock_addr_kern *, ctx,
{
return (unsigned long)__bpf_sk_lookup(NULL, tuple, len,
sock_net(ctx->sk), 0, IPPROTO_TCP,
- netns_id, flags);
+ netns_id, flags, -1);
}
static const struct bpf_func_proto bpf_sock_addr_sk_lookup_tcp_proto = {
@@ -6853,7 +6944,7 @@ BPF_CALL_5(bpf_sock_addr_sk_lookup_udp, struct bpf_sock_addr_kern *, ctx,
{
return (unsigned long)__bpf_sk_lookup(NULL, tuple, len,
sock_net(ctx->sk), 0, IPPROTO_UDP,
- netns_id, flags);
+ netns_id, flags, -1);
}
static const struct bpf_func_proto bpf_sock_addr_sk_lookup_udp_proto = {
@@ -6916,6 +7007,8 @@ u32 bpf_tcp_sock_convert_ctx_access(enum bpf_access_type type,
FIELD)); \
} while (0)
+ BTF_TYPE_EMIT(struct bpf_tcp_sock);
+
switch (si->off) {
case offsetof(struct bpf_tcp_sock, rtt_min):
BUILD_BUG_ON(sizeof_field(struct tcp_sock, rtt_min) !=
@@ -7980,9 +8073,9 @@ tc_cls_act_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
#endif
#ifdef CONFIG_INET
case BPF_FUNC_sk_lookup_tcp:
- return &bpf_sk_lookup_tcp_proto;
+ return &bpf_tc_sk_lookup_tcp_proto;
case BPF_FUNC_sk_lookup_udp:
- return &bpf_sk_lookup_udp_proto;
+ return &bpf_tc_sk_lookup_udp_proto;
case BPF_FUNC_sk_release:
return &bpf_sk_release_proto;
case BPF_FUNC_tcp_sock:
@@ -7990,7 +8083,7 @@ tc_cls_act_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
case BPF_FUNC_get_listener_sock:
return &bpf_get_listener_sock_proto;
case BPF_FUNC_skc_lookup_tcp:
- return &bpf_skc_lookup_tcp_proto;
+ return &bpf_tc_skc_lookup_tcp_proto;
case BPF_FUNC_tcp_check_syncookie:
return &bpf_tcp_check_syncookie_proto;
case BPF_FUNC_skb_ecn_set_ce:
@@ -11721,3 +11814,66 @@ static int __init bpf_kfunc_init(void)
return ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_XDP, &bpf_kfunc_set_xdp);
}
late_initcall(bpf_kfunc_init);
+
+/* Disables missing prototype warnings */
+__diag_push();
+__diag_ignore_all("-Wmissing-prototypes",
+ "Global functions as their definitions will be in vmlinux BTF");
+
+/* bpf_sock_destroy: Destroy the given socket with ECONNABORTED error code.
+ *
+ * The function expects a non-NULL pointer to a socket, and invokes the
+ * protocol specific socket destroy handlers.
+ *
+ * The helper can only be called from BPF contexts that have acquired the socket
+ * locks.
+ *
+ * Parameters:
+ * @sock: Pointer to socket to be destroyed
+ *
+ * Return:
+ * On error, may return EPROTONOSUPPORT, EINVAL.
+ * EPROTONOSUPPORT if protocol specific destroy handler is not supported.
+ * 0 otherwise
+ */
+__bpf_kfunc int bpf_sock_destroy(struct sock_common *sock)
+{
+ struct sock *sk = (struct sock *)sock;
+
+ /* The locking semantics that allow for synchronous execution of the
+ * destroy handlers are only supported for TCP and UDP.
+ * Supporting protocols will need to acquire sock lock in the BPF context
+ * prior to invoking this kfunc.
+ */
+ if (!sk->sk_prot->diag_destroy || (sk->sk_protocol != IPPROTO_TCP &&
+ sk->sk_protocol != IPPROTO_UDP))
+ return -EOPNOTSUPP;
+
+ return sk->sk_prot->diag_destroy(sk, ECONNABORTED);
+}
+
+__diag_pop()
+
+BTF_SET8_START(bpf_sk_iter_kfunc_ids)
+BTF_ID_FLAGS(func, bpf_sock_destroy, KF_TRUSTED_ARGS)
+BTF_SET8_END(bpf_sk_iter_kfunc_ids)
+
+static int tracing_iter_filter(const struct bpf_prog *prog, u32 kfunc_id)
+{
+ if (btf_id_set8_contains(&bpf_sk_iter_kfunc_ids, kfunc_id) &&
+ prog->expected_attach_type != BPF_TRACE_ITER)
+ return -EACCES;
+ return 0;
+}
+
+static const struct btf_kfunc_id_set bpf_sk_iter_kfunc_set = {
+ .owner = THIS_MODULE,
+ .set = &bpf_sk_iter_kfunc_ids,
+ .filter = tracing_iter_filter,
+};
+
+static int init_subsystem(void)
+{
+ return register_btf_kfunc_id_set(BPF_PROG_TYPE_TRACING, &bpf_sk_iter_kfunc_set);
+}
+late_initcall(init_subsystem);
diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c
index 25fb0bbc310f..85a2d0d9bd39 100644
--- a/net/core/flow_dissector.c
+++ b/net/core/flow_dissector.c
@@ -27,6 +27,7 @@
#include <linux/tcp.h>
#include <linux/ptp_classify.h>
#include <net/flow_dissector.h>
+#include <net/pkt_cls.h>
#include <scsi/fc/fc_fcoe.h>
#include <uapi/linux/batadv_packet.h>
#include <linux/bpf.h>
@@ -241,6 +242,15 @@ void skb_flow_dissect_meta(const struct sk_buff *skb,
FLOW_DISSECTOR_KEY_META,
target_container);
meta->ingress_ifindex = skb->skb_iif;
+#if IS_ENABLED(CONFIG_NET_TC_SKB_EXT)
+ if (tc_skb_ext_tc_enabled()) {
+ struct tc_skb_ext *ext;
+
+ ext = skb_ext_find(skb, TC_SKB_EXT);
+ if (ext)
+ meta->l2_miss = ext->l2_miss;
+ }
+#endif
}
EXPORT_SYMBOL(skb_flow_dissect_meta);
@@ -548,6 +558,30 @@ __skb_flow_dissect_arp(const struct sk_buff *skb,
}
static enum flow_dissect_ret
+__skb_flow_dissect_cfm(const struct sk_buff *skb,
+ struct flow_dissector *flow_dissector,
+ void *target_container, const void *data,
+ int nhoff, int hlen)
+{
+ struct flow_dissector_key_cfm *key, *hdr, _hdr;
+
+ if (!dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_CFM))
+ return FLOW_DISSECT_RET_OUT_GOOD;
+
+ hdr = __skb_header_pointer(skb, nhoff, sizeof(*key), data, hlen, &_hdr);
+ if (!hdr)
+ return FLOW_DISSECT_RET_OUT_BAD;
+
+ key = skb_flow_dissector_target(flow_dissector, FLOW_DISSECTOR_KEY_CFM,
+ target_container);
+
+ key->mdl_ver = hdr->mdl_ver;
+ key->opcode = hdr->opcode;
+
+ return FLOW_DISSECT_RET_OUT_GOOD;
+}
+
+static enum flow_dissect_ret
__skb_flow_dissect_gre(const struct sk_buff *skb,
struct flow_dissector_key_control *key_control,
struct flow_dissector *flow_dissector,
@@ -1390,6 +1424,12 @@ proto_again:
break;
}
+ case htons(ETH_P_CFM):
+ fdret = __skb_flow_dissect_cfm(skb, flow_dissector,
+ target_container, data,
+ nhoff, hlen);
+ break;
+
default:
fdret = FLOW_DISSECT_RET_OUT_BAD;
break;
diff --git a/net/core/gro.c b/net/core/gro.c
index 2d84165cb4f1..0759277dc14e 100644
--- a/net/core/gro.c
+++ b/net/core/gro.c
@@ -10,7 +10,7 @@
#define GRO_MAX_HEAD (MAX_HEADER + 128)
static DEFINE_SPINLOCK(offload_lock);
-static struct list_head offload_base __read_mostly = LIST_HEAD_INIT(offload_base);
+struct list_head offload_base __read_mostly = LIST_HEAD_INIT(offload_base);
/* Maximum number of GRO_NORMAL skbs to batch up for list-RX */
int gro_normal_batch __read_mostly = 8;
@@ -92,63 +92,6 @@ void dev_remove_offload(struct packet_offload *po)
}
EXPORT_SYMBOL(dev_remove_offload);
-/**
- * skb_eth_gso_segment - segmentation handler for ethernet protocols.
- * @skb: buffer to segment
- * @features: features for the output path (see dev->features)
- * @type: Ethernet Protocol ID
- */
-struct sk_buff *skb_eth_gso_segment(struct sk_buff *skb,
- netdev_features_t features, __be16 type)
-{
- struct sk_buff *segs = ERR_PTR(-EPROTONOSUPPORT);
- struct packet_offload *ptype;
-
- rcu_read_lock();
- list_for_each_entry_rcu(ptype, &offload_base, list) {
- if (ptype->type == type && ptype->callbacks.gso_segment) {
- segs = ptype->callbacks.gso_segment(skb, features);
- break;
- }
- }
- rcu_read_unlock();
-
- return segs;
-}
-EXPORT_SYMBOL(skb_eth_gso_segment);
-
-/**
- * skb_mac_gso_segment - mac layer segmentation handler.
- * @skb: buffer to segment
- * @features: features for the output path (see dev->features)
- */
-struct sk_buff *skb_mac_gso_segment(struct sk_buff *skb,
- netdev_features_t features)
-{
- struct sk_buff *segs = ERR_PTR(-EPROTONOSUPPORT);
- struct packet_offload *ptype;
- int vlan_depth = skb->mac_len;
- __be16 type = skb_network_protocol(skb, &vlan_depth);
-
- if (unlikely(!type))
- return ERR_PTR(-EINVAL);
-
- __skb_pull(skb, vlan_depth);
-
- rcu_read_lock();
- list_for_each_entry_rcu(ptype, &offload_base, list) {
- if (ptype->type == type && ptype->callbacks.gso_segment) {
- segs = ptype->callbacks.gso_segment(skb, features);
- break;
- }
- }
- rcu_read_unlock();
-
- __skb_push(skb, skb->data - skb_mac_header(skb));
-
- return segs;
-}
-EXPORT_SYMBOL(skb_mac_gso_segment);
int skb_gro_receive(struct sk_buff *p, struct sk_buff *skb)
{
@@ -239,9 +182,7 @@ int skb_gro_receive(struct sk_buff *p, struct sk_buff *skb)
pinfo->nr_frags = nr_frags + 1 + skbinfo->nr_frags;
- __skb_frag_set_page(frag, page);
- skb_frag_off_set(frag, first_offset);
- skb_frag_size_set(frag, first_size);
+ skb_frag_fill_page_desc(frag, page, first_offset, first_size);
memcpy(frag + 1, skbinfo->frags, sizeof(*frag) * skbinfo->nr_frags);
/* We dont need to clear skbinfo->nr_frags here */
@@ -363,6 +304,24 @@ void napi_gro_flush(struct napi_struct *napi, bool flush_old)
}
EXPORT_SYMBOL(napi_gro_flush);
+static unsigned long gro_list_prepare_tc_ext(const struct sk_buff *skb,
+ const struct sk_buff *p,
+ unsigned long diffs)
+{
+#if IS_ENABLED(CONFIG_NET_TC_SKB_EXT)
+ struct tc_skb_ext *skb_ext;
+ struct tc_skb_ext *p_ext;
+
+ skb_ext = skb_ext_find(skb, TC_SKB_EXT);
+ p_ext = skb_ext_find(p, TC_SKB_EXT);
+
+ diffs |= (!!p_ext) ^ (!!skb_ext);
+ if (!diffs && unlikely(skb_ext))
+ diffs |= p_ext->chain ^ skb_ext->chain;
+#endif
+ return diffs;
+}
+
static void gro_list_prepare(const struct list_head *head,
const struct sk_buff *skb)
{
@@ -397,23 +356,11 @@ static void gro_list_prepare(const struct list_head *head,
* avoid trying too hard to skip each of them individually
*/
if (!diffs && unlikely(skb->slow_gro | p->slow_gro)) {
-#if IS_ENABLED(CONFIG_SKB_EXTENSIONS) && IS_ENABLED(CONFIG_NET_TC_SKB_EXT)
- struct tc_skb_ext *skb_ext;
- struct tc_skb_ext *p_ext;
-#endif
-
diffs |= p->sk != skb->sk;
diffs |= skb_metadata_dst_cmp(p, skb);
diffs |= skb_get_nfct(p) ^ skb_get_nfct(skb);
-#if IS_ENABLED(CONFIG_SKB_EXTENSIONS) && IS_ENABLED(CONFIG_NET_TC_SKB_EXT)
- skb_ext = skb_ext_find(skb, TC_SKB_EXT);
- p_ext = skb_ext_find(p, TC_SKB_EXT);
-
- diffs |= (!!p_ext) ^ (!!skb_ext);
- if (!diffs && unlikely(skb_ext))
- diffs |= p_ext->chain ^ skb_ext->chain;
-#endif
+ diffs |= gro_list_prepare_tc_ext(skb, p, diffs);
}
NAPI_GRO_CB(p)->same_flow = !diffs;
@@ -460,6 +407,14 @@ static void gro_pull_from_frag0(struct sk_buff *skb, int grow)
}
}
+static void gro_try_pull_from_frag0(struct sk_buff *skb)
+{
+ int grow = skb_gro_offset(skb) - skb_headlen(skb);
+
+ if (grow > 0)
+ gro_pull_from_frag0(skb, grow);
+}
+
static void gro_flush_oldest(struct napi_struct *napi, struct list_head *head)
{
struct sk_buff *oldest;
@@ -489,7 +444,6 @@ static enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff
struct sk_buff *pp = NULL;
enum gro_result ret;
int same_flow;
- int grow;
if (netif_elide_gro(skb->dev))
goto normal;
@@ -564,17 +518,14 @@ found_ptype:
else
gro_list->count++;
+ /* Must be called before setting NAPI_GRO_CB(skb)->{age|last} */
+ gro_try_pull_from_frag0(skb);
NAPI_GRO_CB(skb)->age = jiffies;
NAPI_GRO_CB(skb)->last = skb;
if (!skb_is_gso(skb))
skb_shinfo(skb)->gso_size = skb_gro_len(skb);
list_add(&skb->list, &gro_list->list);
ret = GRO_HELD;
-
-pull:
- grow = skb_gro_offset(skb) - skb_headlen(skb);
- if (grow > 0)
- gro_pull_from_frag0(skb, grow);
ok:
if (gro_list->count) {
if (!test_bit(bucket, &napi->gro_bitmask))
@@ -587,7 +538,8 @@ ok:
normal:
ret = GRO_NORMAL;
- goto pull;
+ gro_try_pull_from_frag0(skb);
+ goto ok;
}
struct packet_offload *gro_find_receive_by_type(__be16 type)
diff --git a/net/core/gso.c b/net/core/gso.c
new file mode 100644
index 000000000000..9e1803bfc9c6
--- /dev/null
+++ b/net/core/gso.c
@@ -0,0 +1,273 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+#include <linux/skbuff.h>
+#include <linux/sctp.h>
+#include <net/gso.h>
+#include <net/gro.h>
+
+/**
+ * skb_eth_gso_segment - segmentation handler for ethernet protocols.
+ * @skb: buffer to segment
+ * @features: features for the output path (see dev->features)
+ * @type: Ethernet Protocol ID
+ */
+struct sk_buff *skb_eth_gso_segment(struct sk_buff *skb,
+ netdev_features_t features, __be16 type)
+{
+ struct sk_buff *segs = ERR_PTR(-EPROTONOSUPPORT);
+ struct packet_offload *ptype;
+
+ rcu_read_lock();
+ list_for_each_entry_rcu(ptype, &offload_base, list) {
+ if (ptype->type == type && ptype->callbacks.gso_segment) {
+ segs = ptype->callbacks.gso_segment(skb, features);
+ break;
+ }
+ }
+ rcu_read_unlock();
+
+ return segs;
+}
+EXPORT_SYMBOL(skb_eth_gso_segment);
+
+/**
+ * skb_mac_gso_segment - mac layer segmentation handler.
+ * @skb: buffer to segment
+ * @features: features for the output path (see dev->features)
+ */
+struct sk_buff *skb_mac_gso_segment(struct sk_buff *skb,
+ netdev_features_t features)
+{
+ struct sk_buff *segs = ERR_PTR(-EPROTONOSUPPORT);
+ struct packet_offload *ptype;
+ int vlan_depth = skb->mac_len;
+ __be16 type = skb_network_protocol(skb, &vlan_depth);
+
+ if (unlikely(!type))
+ return ERR_PTR(-EINVAL);
+
+ __skb_pull(skb, vlan_depth);
+
+ rcu_read_lock();
+ list_for_each_entry_rcu(ptype, &offload_base, list) {
+ if (ptype->type == type && ptype->callbacks.gso_segment) {
+ segs = ptype->callbacks.gso_segment(skb, features);
+ break;
+ }
+ }
+ rcu_read_unlock();
+
+ __skb_push(skb, skb->data - skb_mac_header(skb));
+
+ return segs;
+}
+EXPORT_SYMBOL(skb_mac_gso_segment);
+/* openvswitch calls this on rx path, so we need a different check.
+ */
+static bool skb_needs_check(const struct sk_buff *skb, bool tx_path)
+{
+ if (tx_path)
+ return skb->ip_summed != CHECKSUM_PARTIAL &&
+ skb->ip_summed != CHECKSUM_UNNECESSARY;
+
+ return skb->ip_summed == CHECKSUM_NONE;
+}
+
+/**
+ * __skb_gso_segment - Perform segmentation on skb.
+ * @skb: buffer to segment
+ * @features: features for the output path (see dev->features)
+ * @tx_path: whether it is called in TX path
+ *
+ * This function segments the given skb and returns a list of segments.
+ *
+ * It may return NULL if the skb requires no segmentation. This is
+ * only possible when GSO is used for verifying header integrity.
+ *
+ * Segmentation preserves SKB_GSO_CB_OFFSET bytes of previous skb cb.
+ */
+struct sk_buff *__skb_gso_segment(struct sk_buff *skb,
+ netdev_features_t features, bool tx_path)
+{
+ struct sk_buff *segs;
+
+ if (unlikely(skb_needs_check(skb, tx_path))) {
+ int err;
+
+ /* We're going to init ->check field in TCP or UDP header */
+ err = skb_cow_head(skb, 0);
+ if (err < 0)
+ return ERR_PTR(err);
+ }
+
+ /* Only report GSO partial support if it will enable us to
+ * support segmentation on this frame without needing additional
+ * work.
+ */
+ if (features & NETIF_F_GSO_PARTIAL) {
+ netdev_features_t partial_features = NETIF_F_GSO_ROBUST;
+ struct net_device *dev = skb->dev;
+
+ partial_features |= dev->features & dev->gso_partial_features;
+ if (!skb_gso_ok(skb, features | partial_features))
+ features &= ~NETIF_F_GSO_PARTIAL;
+ }
+
+ BUILD_BUG_ON(SKB_GSO_CB_OFFSET +
+ sizeof(*SKB_GSO_CB(skb)) > sizeof(skb->cb));
+
+ SKB_GSO_CB(skb)->mac_offset = skb_headroom(skb);
+ SKB_GSO_CB(skb)->encap_level = 0;
+
+ skb_reset_mac_header(skb);
+ skb_reset_mac_len(skb);
+
+ segs = skb_mac_gso_segment(skb, features);
+
+ if (segs != skb && unlikely(skb_needs_check(skb, tx_path) && !IS_ERR(segs)))
+ skb_warn_bad_offload(skb);
+
+ return segs;
+}
+EXPORT_SYMBOL(__skb_gso_segment);
+
+/**
+ * skb_gso_transport_seglen - Return length of individual segments of a gso packet
+ *
+ * @skb: GSO skb
+ *
+ * skb_gso_transport_seglen is used to determine the real size of the
+ * individual segments, including Layer4 headers (TCP/UDP).
+ *
+ * The MAC/L2 or network (IP, IPv6) headers are not accounted for.
+ */
+static unsigned int skb_gso_transport_seglen(const struct sk_buff *skb)
+{
+ const struct skb_shared_info *shinfo = skb_shinfo(skb);
+ unsigned int thlen = 0;
+
+ if (skb->encapsulation) {
+ thlen = skb_inner_transport_header(skb) -
+ skb_transport_header(skb);
+
+ if (likely(shinfo->gso_type & (SKB_GSO_TCPV4 | SKB_GSO_TCPV6)))
+ thlen += inner_tcp_hdrlen(skb);
+ } else if (likely(shinfo->gso_type & (SKB_GSO_TCPV4 | SKB_GSO_TCPV6))) {
+ thlen = tcp_hdrlen(skb);
+ } else if (unlikely(skb_is_gso_sctp(skb))) {
+ thlen = sizeof(struct sctphdr);
+ } else if (shinfo->gso_type & SKB_GSO_UDP_L4) {
+ thlen = sizeof(struct udphdr);
+ }
+ /* UFO sets gso_size to the size of the fragmentation
+ * payload, i.e. the size of the L4 (UDP) header is already
+ * accounted for.
+ */
+ return thlen + shinfo->gso_size;
+}
+
+/**
+ * skb_gso_network_seglen - Return length of individual segments of a gso packet
+ *
+ * @skb: GSO skb
+ *
+ * skb_gso_network_seglen is used to determine the real size of the
+ * individual segments, including Layer3 (IP, IPv6) and L4 headers (TCP/UDP).
+ *
+ * The MAC/L2 header is not accounted for.
+ */
+static unsigned int skb_gso_network_seglen(const struct sk_buff *skb)
+{
+ unsigned int hdr_len = skb_transport_header(skb) -
+ skb_network_header(skb);
+
+ return hdr_len + skb_gso_transport_seglen(skb);
+}
+
+/**
+ * skb_gso_mac_seglen - Return length of individual segments of a gso packet
+ *
+ * @skb: GSO skb
+ *
+ * skb_gso_mac_seglen is used to determine the real size of the
+ * individual segments, including MAC/L2, Layer3 (IP, IPv6) and L4
+ * headers (TCP/UDP).
+ */
+static unsigned int skb_gso_mac_seglen(const struct sk_buff *skb)
+{
+ unsigned int hdr_len = skb_transport_header(skb) - skb_mac_header(skb);
+
+ return hdr_len + skb_gso_transport_seglen(skb);
+}
+
+/**
+ * skb_gso_size_check - check the skb size, considering GSO_BY_FRAGS
+ *
+ * There are a couple of instances where we have a GSO skb, and we
+ * want to determine what size it would be after it is segmented.
+ *
+ * We might want to check:
+ * - L3+L4+payload size (e.g. IP forwarding)
+ * - L2+L3+L4+payload size (e.g. sanity check before passing to driver)
+ *
+ * This is a helper to do that correctly considering GSO_BY_FRAGS.
+ *
+ * @skb: GSO skb
+ *
+ * @seg_len: The segmented length (from skb_gso_*_seglen). In the
+ * GSO_BY_FRAGS case this will be [header sizes + GSO_BY_FRAGS].
+ *
+ * @max_len: The maximum permissible length.
+ *
+ * Returns true if the segmented length <= max length.
+ */
+static inline bool skb_gso_size_check(const struct sk_buff *skb,
+ unsigned int seg_len,
+ unsigned int max_len) {
+ const struct skb_shared_info *shinfo = skb_shinfo(skb);
+ const struct sk_buff *iter;
+
+ if (shinfo->gso_size != GSO_BY_FRAGS)
+ return seg_len <= max_len;
+
+ /* Undo this so we can re-use header sizes */
+ seg_len -= GSO_BY_FRAGS;
+
+ skb_walk_frags(skb, iter) {
+ if (seg_len + skb_headlen(iter) > max_len)
+ return false;
+ }
+
+ return true;
+}
+
+/**
+ * skb_gso_validate_network_len - Will a split GSO skb fit into a given MTU?
+ *
+ * @skb: GSO skb
+ * @mtu: MTU to validate against
+ *
+ * skb_gso_validate_network_len validates if a given skb will fit a
+ * wanted MTU once split. It considers L3 headers, L4 headers, and the
+ * payload.
+ */
+bool skb_gso_validate_network_len(const struct sk_buff *skb, unsigned int mtu)
+{
+ return skb_gso_size_check(skb, skb_gso_network_seglen(skb), mtu);
+}
+EXPORT_SYMBOL_GPL(skb_gso_validate_network_len);
+
+/**
+ * skb_gso_validate_mac_len - Will a split GSO skb fit in a given length?
+ *
+ * @skb: GSO skb
+ * @len: length to validate against
+ *
+ * skb_gso_validate_mac_len validates if a given skb will fit a wanted
+ * length once split, including L2, L3 and L4 headers and the payload.
+ */
+bool skb_gso_validate_mac_len(const struct sk_buff *skb, unsigned int len)
+{
+ return skb_gso_size_check(skb, skb_gso_mac_seglen(skb), len);
+}
+EXPORT_SYMBOL_GPL(skb_gso_validate_mac_len);
+
diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c
index 3e3598cd49f2..f4183c4c1ec8 100644
--- a/net/core/net_namespace.c
+++ b/net/core/net_namespace.c
@@ -308,7 +308,7 @@ EXPORT_SYMBOL_GPL(get_net_ns_by_id);
/* init code that must occur even if setup_net() is not called. */
static __net_init void preinit_net(struct net *net)
{
- ref_tracker_dir_init(&net->notrefcnt_tracker, 128);
+ ref_tracker_dir_init(&net->notrefcnt_tracker, 128, "net notrefcnt");
}
/*
@@ -322,7 +322,7 @@ static __net_init int setup_net(struct net *net, struct user_namespace *user_ns)
LIST_HEAD(net_exit_list);
refcount_set(&net->ns.count, 1);
- ref_tracker_dir_init(&net->refcnt_tracker, 128);
+ ref_tracker_dir_init(&net->refcnt_tracker, 128, "net refcnt");
refcount_set(&net->passive, 1);
get_random_bytes(&net->hash_mix, sizeof(u32));
diff --git a/net/core/netdev-genl-gen.c b/net/core/netdev-genl-gen.c
index de17ca2f7dbf..ea9231378aa6 100644
--- a/net/core/netdev-genl-gen.c
+++ b/net/core/netdev-genl-gen.c
@@ -8,7 +8,7 @@
#include "netdev-genl-gen.h"
-#include <linux/netdev.h>
+#include <uapi/linux/netdev.h>
/* NETDEV_CMD_DEV_GET - do */
static const struct nla_policy netdev_dev_get_nl_policy[NETDEV_A_DEV_IFINDEX + 1] = {
diff --git a/net/core/netdev-genl-gen.h b/net/core/netdev-genl-gen.h
index 74d74fc23167..7b370c073e7d 100644
--- a/net/core/netdev-genl-gen.h
+++ b/net/core/netdev-genl-gen.h
@@ -9,7 +9,7 @@
#include <net/netlink.h>
#include <net/genetlink.h>
-#include <linux/netdev.h>
+#include <uapi/linux/netdev.h>
int netdev_nl_dev_get_doit(struct sk_buff *skb, struct genl_info *info);
int netdev_nl_dev_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb);
diff --git a/net/core/netpoll.c b/net/core/netpoll.c
index e6a739b1afa9..543007f159f9 100644
--- a/net/core/netpoll.c
+++ b/net/core/netpoll.c
@@ -690,7 +690,7 @@ int netpoll_setup(struct netpoll *np)
err = -ENODEV;
goto unlock;
}
- dev_hold(ndev);
+ netdev_hold(ndev, &np->dev_tracker, GFP_KERNEL);
if (netdev_master_upper_dev_get(ndev)) {
np_err(np, "%s is a slave device, aborting\n", np->dev_name);
@@ -783,12 +783,11 @@ put_noaddr:
err = __netpoll_setup(np, ndev);
if (err)
goto put;
- netdev_tracker_alloc(ndev, &np->dev_tracker, GFP_KERNEL);
rtnl_unlock();
return 0;
put:
- dev_put(ndev);
+ netdev_put(ndev, &np->dev_tracker);
unlock:
rtnl_unlock();
return err;
diff --git a/net/core/pktgen.c b/net/core/pktgen.c
index 760238196db1..f56b8d697014 100644
--- a/net/core/pktgen.c
+++ b/net/core/pktgen.c
@@ -2785,14 +2785,17 @@ static void pktgen_finalize_skb(struct pktgen_dev *pkt_dev, struct sk_buff *skb,
break;
}
get_page(pkt_dev->page);
- skb_frag_set_page(skb, i, pkt_dev->page);
- skb_frag_off_set(&skb_shinfo(skb)->frags[i], 0);
+
/*last fragment, fill rest of data*/
if (i == (frags - 1))
- skb_frag_size_set(&skb_shinfo(skb)->frags[i],
- (datalen < PAGE_SIZE ? datalen : PAGE_SIZE));
+ skb_frag_fill_page_desc(&skb_shinfo(skb)->frags[i],
+ pkt_dev->page, 0,
+ (datalen < PAGE_SIZE ?
+ datalen : PAGE_SIZE));
else
- skb_frag_size_set(&skb_shinfo(skb)->frags[i], frag_len);
+ skb_frag_fill_page_desc(&skb_shinfo(skb)->frags[i],
+ pkt_dev->page, 0, frag_len);
+
datalen -= skb_frag_size(&skb_shinfo(skb)->frags[i]);
skb->len += skb_frag_size(&skb_shinfo(skb)->frags[i]);
skb->data_len += skb_frag_size(&skb_shinfo(skb)->frags[i]);
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index 41de3a2f29e1..3ad4e030846d 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -961,24 +961,27 @@ static inline int rtnl_vfinfo_size(const struct net_device *dev,
nla_total_size(sizeof(struct ifla_vf_rate)) +
nla_total_size(sizeof(struct ifla_vf_link_state)) +
nla_total_size(sizeof(struct ifla_vf_rss_query_en)) +
- nla_total_size(0) + /* nest IFLA_VF_STATS */
- /* IFLA_VF_STATS_RX_PACKETS */
- nla_total_size_64bit(sizeof(__u64)) +
- /* IFLA_VF_STATS_TX_PACKETS */
- nla_total_size_64bit(sizeof(__u64)) +
- /* IFLA_VF_STATS_RX_BYTES */
- nla_total_size_64bit(sizeof(__u64)) +
- /* IFLA_VF_STATS_TX_BYTES */
- nla_total_size_64bit(sizeof(__u64)) +
- /* IFLA_VF_STATS_BROADCAST */
- nla_total_size_64bit(sizeof(__u64)) +
- /* IFLA_VF_STATS_MULTICAST */
- nla_total_size_64bit(sizeof(__u64)) +
- /* IFLA_VF_STATS_RX_DROPPED */
- nla_total_size_64bit(sizeof(__u64)) +
- /* IFLA_VF_STATS_TX_DROPPED */
- nla_total_size_64bit(sizeof(__u64)) +
nla_total_size(sizeof(struct ifla_vf_trust)));
+ if (~ext_filter_mask & RTEXT_FILTER_SKIP_STATS) {
+ size += num_vfs *
+ (nla_total_size(0) + /* nest IFLA_VF_STATS */
+ /* IFLA_VF_STATS_RX_PACKETS */
+ nla_total_size_64bit(sizeof(__u64)) +
+ /* IFLA_VF_STATS_TX_PACKETS */
+ nla_total_size_64bit(sizeof(__u64)) +
+ /* IFLA_VF_STATS_RX_BYTES */
+ nla_total_size_64bit(sizeof(__u64)) +
+ /* IFLA_VF_STATS_TX_BYTES */
+ nla_total_size_64bit(sizeof(__u64)) +
+ /* IFLA_VF_STATS_BROADCAST */
+ nla_total_size_64bit(sizeof(__u64)) +
+ /* IFLA_VF_STATS_MULTICAST */
+ nla_total_size_64bit(sizeof(__u64)) +
+ /* IFLA_VF_STATS_RX_DROPPED */
+ nla_total_size_64bit(sizeof(__u64)) +
+ /* IFLA_VF_STATS_TX_DROPPED */
+ nla_total_size_64bit(sizeof(__u64)));
+ }
return size;
} else
return 0;
@@ -1270,7 +1273,8 @@ static noinline_for_stack int rtnl_fill_stats(struct sk_buff *skb,
static noinline_for_stack int rtnl_fill_vfinfo(struct sk_buff *skb,
struct net_device *dev,
int vfs_num,
- struct nlattr *vfinfo)
+ struct nlattr *vfinfo,
+ u32 ext_filter_mask)
{
struct ifla_vf_rss_query_en vf_rss_query_en;
struct nlattr *vf, *vfstats, *vfvlanlist;
@@ -1376,33 +1380,35 @@ static noinline_for_stack int rtnl_fill_vfinfo(struct sk_buff *skb,
goto nla_put_vf_failure;
}
nla_nest_end(skb, vfvlanlist);
- memset(&vf_stats, 0, sizeof(vf_stats));
- if (dev->netdev_ops->ndo_get_vf_stats)
- dev->netdev_ops->ndo_get_vf_stats(dev, vfs_num,
- &vf_stats);
- vfstats = nla_nest_start_noflag(skb, IFLA_VF_STATS);
- if (!vfstats)
- goto nla_put_vf_failure;
- if (nla_put_u64_64bit(skb, IFLA_VF_STATS_RX_PACKETS,
- vf_stats.rx_packets, IFLA_VF_STATS_PAD) ||
- nla_put_u64_64bit(skb, IFLA_VF_STATS_TX_PACKETS,
- vf_stats.tx_packets, IFLA_VF_STATS_PAD) ||
- nla_put_u64_64bit(skb, IFLA_VF_STATS_RX_BYTES,
- vf_stats.rx_bytes, IFLA_VF_STATS_PAD) ||
- nla_put_u64_64bit(skb, IFLA_VF_STATS_TX_BYTES,
- vf_stats.tx_bytes, IFLA_VF_STATS_PAD) ||
- nla_put_u64_64bit(skb, IFLA_VF_STATS_BROADCAST,
- vf_stats.broadcast, IFLA_VF_STATS_PAD) ||
- nla_put_u64_64bit(skb, IFLA_VF_STATS_MULTICAST,
- vf_stats.multicast, IFLA_VF_STATS_PAD) ||
- nla_put_u64_64bit(skb, IFLA_VF_STATS_RX_DROPPED,
- vf_stats.rx_dropped, IFLA_VF_STATS_PAD) ||
- nla_put_u64_64bit(skb, IFLA_VF_STATS_TX_DROPPED,
- vf_stats.tx_dropped, IFLA_VF_STATS_PAD)) {
- nla_nest_cancel(skb, vfstats);
- goto nla_put_vf_failure;
+ if (~ext_filter_mask & RTEXT_FILTER_SKIP_STATS) {
+ memset(&vf_stats, 0, sizeof(vf_stats));
+ if (dev->netdev_ops->ndo_get_vf_stats)
+ dev->netdev_ops->ndo_get_vf_stats(dev, vfs_num,
+ &vf_stats);
+ vfstats = nla_nest_start_noflag(skb, IFLA_VF_STATS);
+ if (!vfstats)
+ goto nla_put_vf_failure;
+ if (nla_put_u64_64bit(skb, IFLA_VF_STATS_RX_PACKETS,
+ vf_stats.rx_packets, IFLA_VF_STATS_PAD) ||
+ nla_put_u64_64bit(skb, IFLA_VF_STATS_TX_PACKETS,
+ vf_stats.tx_packets, IFLA_VF_STATS_PAD) ||
+ nla_put_u64_64bit(skb, IFLA_VF_STATS_RX_BYTES,
+ vf_stats.rx_bytes, IFLA_VF_STATS_PAD) ||
+ nla_put_u64_64bit(skb, IFLA_VF_STATS_TX_BYTES,
+ vf_stats.tx_bytes, IFLA_VF_STATS_PAD) ||
+ nla_put_u64_64bit(skb, IFLA_VF_STATS_BROADCAST,
+ vf_stats.broadcast, IFLA_VF_STATS_PAD) ||
+ nla_put_u64_64bit(skb, IFLA_VF_STATS_MULTICAST,
+ vf_stats.multicast, IFLA_VF_STATS_PAD) ||
+ nla_put_u64_64bit(skb, IFLA_VF_STATS_RX_DROPPED,
+ vf_stats.rx_dropped, IFLA_VF_STATS_PAD) ||
+ nla_put_u64_64bit(skb, IFLA_VF_STATS_TX_DROPPED,
+ vf_stats.tx_dropped, IFLA_VF_STATS_PAD)) {
+ nla_nest_cancel(skb, vfstats);
+ goto nla_put_vf_failure;
+ }
+ nla_nest_end(skb, vfstats);
}
- nla_nest_end(skb, vfstats);
nla_nest_end(skb, vf);
return 0;
@@ -1435,7 +1441,7 @@ static noinline_for_stack int rtnl_fill_vf(struct sk_buff *skb,
return -EMSGSIZE;
for (i = 0; i < num_vfs; i++) {
- if (rtnl_fill_vfinfo(skb, dev, i, vfinfo))
+ if (rtnl_fill_vfinfo(skb, dev, i, vfinfo, ext_filter_mask))
return -EMSGSIZE;
}
@@ -2377,45 +2383,43 @@ static int rtnl_set_vf_rate(struct net_device *dev, int vf, int min_tx_rate,
static int validate_linkmsg(struct net_device *dev, struct nlattr *tb[],
struct netlink_ext_ack *extack)
{
- if (dev) {
- if (tb[IFLA_ADDRESS] &&
- nla_len(tb[IFLA_ADDRESS]) < dev->addr_len)
- return -EINVAL;
+ if (tb[IFLA_ADDRESS] &&
+ nla_len(tb[IFLA_ADDRESS]) < dev->addr_len)
+ return -EINVAL;
- if (tb[IFLA_BROADCAST] &&
- nla_len(tb[IFLA_BROADCAST]) < dev->addr_len)
- return -EINVAL;
+ if (tb[IFLA_BROADCAST] &&
+ nla_len(tb[IFLA_BROADCAST]) < dev->addr_len)
+ return -EINVAL;
- if (tb[IFLA_GSO_MAX_SIZE] &&
- nla_get_u32(tb[IFLA_GSO_MAX_SIZE]) > dev->tso_max_size) {
- NL_SET_ERR_MSG(extack, "too big gso_max_size");
- return -EINVAL;
- }
+ if (tb[IFLA_GSO_MAX_SIZE] &&
+ nla_get_u32(tb[IFLA_GSO_MAX_SIZE]) > dev->tso_max_size) {
+ NL_SET_ERR_MSG(extack, "too big gso_max_size");
+ return -EINVAL;
+ }
- if (tb[IFLA_GSO_MAX_SEGS] &&
- (nla_get_u32(tb[IFLA_GSO_MAX_SEGS]) > GSO_MAX_SEGS ||
- nla_get_u32(tb[IFLA_GSO_MAX_SEGS]) > dev->tso_max_segs)) {
- NL_SET_ERR_MSG(extack, "too big gso_max_segs");
- return -EINVAL;
- }
+ if (tb[IFLA_GSO_MAX_SEGS] &&
+ (nla_get_u32(tb[IFLA_GSO_MAX_SEGS]) > GSO_MAX_SEGS ||
+ nla_get_u32(tb[IFLA_GSO_MAX_SEGS]) > dev->tso_max_segs)) {
+ NL_SET_ERR_MSG(extack, "too big gso_max_segs");
+ return -EINVAL;
+ }
- if (tb[IFLA_GRO_MAX_SIZE] &&
- nla_get_u32(tb[IFLA_GRO_MAX_SIZE]) > GRO_MAX_SIZE) {
- NL_SET_ERR_MSG(extack, "too big gro_max_size");
- return -EINVAL;
- }
+ if (tb[IFLA_GRO_MAX_SIZE] &&
+ nla_get_u32(tb[IFLA_GRO_MAX_SIZE]) > GRO_MAX_SIZE) {
+ NL_SET_ERR_MSG(extack, "too big gro_max_size");
+ return -EINVAL;
+ }
- if (tb[IFLA_GSO_IPV4_MAX_SIZE] &&
- nla_get_u32(tb[IFLA_GSO_IPV4_MAX_SIZE]) > dev->tso_max_size) {
- NL_SET_ERR_MSG(extack, "too big gso_ipv4_max_size");
- return -EINVAL;
- }
+ if (tb[IFLA_GSO_IPV4_MAX_SIZE] &&
+ nla_get_u32(tb[IFLA_GSO_IPV4_MAX_SIZE]) > dev->tso_max_size) {
+ NL_SET_ERR_MSG(extack, "too big gso_ipv4_max_size");
+ return -EINVAL;
+ }
- if (tb[IFLA_GRO_IPV4_MAX_SIZE] &&
- nla_get_u32(tb[IFLA_GRO_IPV4_MAX_SIZE]) > GRO_MAX_SIZE) {
- NL_SET_ERR_MSG(extack, "too big gro_ipv4_max_size");
- return -EINVAL;
- }
+ if (tb[IFLA_GRO_IPV4_MAX_SIZE] &&
+ nla_get_u32(tb[IFLA_GRO_IPV4_MAX_SIZE]) > GRO_MAX_SIZE) {
+ NL_SET_ERR_MSG(extack, "too big gro_ipv4_max_size");
+ return -EINVAL;
}
if (tb[IFLA_AF_SPEC]) {
@@ -2736,10 +2740,6 @@ static int do_setlink(const struct sk_buff *skb,
char ifname[IFNAMSIZ];
int err;
- err = validate_linkmsg(dev, tb, extack);
- if (err < 0)
- return err;
-
if (tb[IFLA_IFNAME])
nla_strscpy(ifname, tb[IFLA_IFNAME], IFNAMSIZ);
else
@@ -3156,6 +3156,10 @@ static int rtnl_setlink(struct sk_buff *skb, struct nlmsghdr *nlh,
goto errout;
}
+ err = validate_linkmsg(dev, tb, extack);
+ if (err < 0)
+ goto errout;
+
err = do_setlink(skb, dev, ifm, extack, tb, 0);
errout:
return err;
@@ -3399,6 +3403,9 @@ static int rtnl_group_changelink(const struct sk_buff *skb,
for_each_netdev_safe(net, dev, aux) {
if (dev->group == group) {
+ err = validate_linkmsg(dev, tb, extack);
+ if (err < 0)
+ return err;
err = do_setlink(skb, dev, ifm, extack, tb, 0);
if (err < 0)
return err;
@@ -3556,10 +3563,6 @@ replay:
m_ops = master_dev->rtnl_link_ops;
}
- err = validate_linkmsg(dev, tb, extack);
- if (err < 0)
- return err;
-
if (tb[IFLA_LINKINFO]) {
err = nla_parse_nested_deprecated(linkinfo, IFLA_INFO_MAX,
tb[IFLA_LINKINFO],
@@ -3623,6 +3626,10 @@ replay:
if (nlh->nlmsg_flags & NLM_F_REPLACE)
return -EOPNOTSUPP;
+ err = validate_linkmsg(dev, tb, extack);
+ if (err < 0)
+ return err;
+
if (linkinfo[IFLA_INFO_DATA]) {
if (!ops || ops != dev->rtnl_link_ops ||
!ops->changelink)
@@ -4090,7 +4097,7 @@ static int nlmsg_populate_fdb_fill(struct sk_buff *skb,
ndm->ndm_ifindex = dev->ifindex;
ndm->ndm_state = ndm_state;
- if (nla_put(skb, NDA_LLADDR, ETH_ALEN, addr))
+ if (nla_put(skb, NDA_LLADDR, dev->addr_len, addr))
goto nla_put_failure;
if (vid)
if (nla_put(skb, NDA_VLAN, sizeof(u16), &vid))
@@ -4104,10 +4111,10 @@ nla_put_failure:
return -EMSGSIZE;
}
-static inline size_t rtnl_fdb_nlmsg_size(void)
+static inline size_t rtnl_fdb_nlmsg_size(const struct net_device *dev)
{
return NLMSG_ALIGN(sizeof(struct ndmsg)) +
- nla_total_size(ETH_ALEN) + /* NDA_LLADDR */
+ nla_total_size(dev->addr_len) + /* NDA_LLADDR */
nla_total_size(sizeof(u16)) + /* NDA_VLAN */
0;
}
@@ -4119,7 +4126,7 @@ static void rtnl_fdb_notify(struct net_device *dev, u8 *addr, u16 vid, int type,
struct sk_buff *skb;
int err = -ENOBUFS;
- skb = nlmsg_new(rtnl_fdb_nlmsg_size(), GFP_ATOMIC);
+ skb = nlmsg_new(rtnl_fdb_nlmsg_size(dev), GFP_ATOMIC);
if (!skb)
goto errout;
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index cea28d30abb5..6c5915efbc17 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -67,6 +67,7 @@
#include <net/dst.h>
#include <net/sock.h>
#include <net/checksum.h>
+#include <net/gso.h>
#include <net/ip6_checksum.h>
#include <net/xfrm.h>
#include <net/mpls.h>
@@ -92,15 +93,7 @@ static struct kmem_cache *skbuff_fclone_cache __ro_after_init;
static struct kmem_cache *skbuff_ext_cache __ro_after_init;
#endif
-/* skb_small_head_cache and related code is only supported
- * for CONFIG_SLAB and CONFIG_SLUB.
- * As soon as SLOB is removed from the kernel, we can clean up this.
- */
-#if !defined(CONFIG_SLOB)
-# define HAVE_SKB_SMALL_HEAD_CACHE 1
-#endif
-#ifdef HAVE_SKB_SMALL_HEAD_CACHE
static struct kmem_cache *skb_small_head_cache __ro_after_init;
#define SKB_SMALL_HEAD_SIZE SKB_HEAD_ALIGN(MAX_TCP_HEADER)
@@ -117,7 +110,6 @@ static struct kmem_cache *skb_small_head_cache __ro_after_init;
#define SKB_SMALL_HEAD_HEADROOM \
SKB_WITH_OVERHEAD(SKB_SMALL_HEAD_CACHE_SIZE)
-#endif /* HAVE_SKB_SMALL_HEAD_CACHE */
int sysctl_max_skb_frags __read_mostly = MAX_SKB_FRAGS;
EXPORT_SYMBOL(sysctl_max_skb_frags);
@@ -562,7 +554,6 @@ static void *kmalloc_reserve(unsigned int *size, gfp_t flags, int node,
void *obj;
obj_size = SKB_HEAD_ALIGN(*size);
-#ifdef HAVE_SKB_SMALL_HEAD_CACHE
if (obj_size <= SKB_SMALL_HEAD_CACHE_SIZE &&
!(flags & KMALLOC_NOT_NORMAL_BITS)) {
obj = kmem_cache_alloc_node(skb_small_head_cache,
@@ -576,7 +567,6 @@ static void *kmalloc_reserve(unsigned int *size, gfp_t flags, int node,
obj = kmem_cache_alloc_node(skb_small_head_cache, flags, node);
goto out;
}
-#endif
*size = obj_size = kmalloc_size_roundup(obj_size);
/*
* Try a regular allocation, when that fails and we're not entitled
@@ -898,11 +888,9 @@ static bool skb_pp_recycle(struct sk_buff *skb, void *data, bool napi_safe)
static void skb_kfree_head(void *head, unsigned int end_offset)
{
-#ifdef HAVE_SKB_SMALL_HEAD_CACHE
if (end_offset == SKB_SMALL_HEAD_HEADROOM)
kmem_cache_free(skb_small_head_cache, head);
else
-#endif
kfree(head);
}
@@ -2160,7 +2148,6 @@ int __skb_unclone_keeptruesize(struct sk_buff *skb, gfp_t pri)
if (likely(skb_end_offset(skb) == saved_end_offset))
return 0;
-#ifdef HAVE_SKB_SMALL_HEAD_CACHE
/* We can not change skb->end if the original or new value
* is SKB_SMALL_HEAD_HEADROOM, as it might break skb_kfree_head().
*/
@@ -2174,7 +2161,6 @@ int __skb_unclone_keeptruesize(struct sk_buff *skb, gfp_t pri)
WARN_ON_ONCE(1);
return 0;
}
-#endif
shinfo = skb_shinfo(skb);
@@ -3003,32 +2989,32 @@ int skb_splice_bits(struct sk_buff *skb, struct sock *sk, unsigned int offset,
}
EXPORT_SYMBOL_GPL(skb_splice_bits);
-static int sendmsg_unlocked(struct sock *sk, struct msghdr *msg,
- struct kvec *vec, size_t num, size_t size)
+static int sendmsg_locked(struct sock *sk, struct msghdr *msg)
{
struct socket *sock = sk->sk_socket;
+ size_t size = msg_data_left(msg);
if (!sock)
return -EINVAL;
- return kernel_sendmsg(sock, msg, vec, num, size);
+
+ if (!sock->ops->sendmsg_locked)
+ return sock_no_sendmsg_locked(sk, msg, size);
+
+ return sock->ops->sendmsg_locked(sk, msg, size);
}
-static int sendpage_unlocked(struct sock *sk, struct page *page, int offset,
- size_t size, int flags)
+static int sendmsg_unlocked(struct sock *sk, struct msghdr *msg)
{
struct socket *sock = sk->sk_socket;
if (!sock)
return -EINVAL;
- return kernel_sendpage(sock, page, offset, size, flags);
+ return sock_sendmsg(sock, msg);
}
-typedef int (*sendmsg_func)(struct sock *sk, struct msghdr *msg,
- struct kvec *vec, size_t num, size_t size);
-typedef int (*sendpage_func)(struct sock *sk, struct page *page, int offset,
- size_t size, int flags);
+typedef int (*sendmsg_func)(struct sock *sk, struct msghdr *msg);
static int __skb_send_sock(struct sock *sk, struct sk_buff *skb, int offset,
- int len, sendmsg_func sendmsg, sendpage_func sendpage)
+ int len, sendmsg_func sendmsg)
{
unsigned int orig_len = len;
struct sk_buff *head = skb;
@@ -3048,8 +3034,9 @@ do_frag_list:
memset(&msg, 0, sizeof(msg));
msg.msg_flags = MSG_DONTWAIT;
- ret = INDIRECT_CALL_2(sendmsg, kernel_sendmsg_locked,
- sendmsg_unlocked, sk, &msg, &kv, 1, slen);
+ iov_iter_kvec(&msg.msg_iter, ITER_SOURCE, &kv, 1, slen);
+ ret = INDIRECT_CALL_2(sendmsg, sendmsg_locked,
+ sendmsg_unlocked, sk, &msg);
if (ret <= 0)
goto error;
@@ -3080,11 +3067,18 @@ do_frag_list:
slen = min_t(size_t, len, skb_frag_size(frag) - offset);
while (slen) {
- ret = INDIRECT_CALL_2(sendpage, kernel_sendpage_locked,
- sendpage_unlocked, sk,
- skb_frag_page(frag),
- skb_frag_off(frag) + offset,
- slen, MSG_DONTWAIT);
+ struct bio_vec bvec;
+ struct msghdr msg = {
+ .msg_flags = MSG_SPLICE_PAGES | MSG_DONTWAIT,
+ };
+
+ bvec_set_page(&bvec, skb_frag_page(frag), slen,
+ skb_frag_off(frag) + offset);
+ iov_iter_bvec(&msg.msg_iter, ITER_SOURCE, &bvec, 1,
+ slen);
+
+ ret = INDIRECT_CALL_2(sendmsg, sendmsg_locked,
+ sendmsg_unlocked, sk, &msg);
if (ret <= 0)
goto error;
@@ -3121,16 +3115,14 @@ error:
int skb_send_sock_locked(struct sock *sk, struct sk_buff *skb, int offset,
int len)
{
- return __skb_send_sock(sk, skb, offset, len, kernel_sendmsg_locked,
- kernel_sendpage_locked);
+ return __skb_send_sock(sk, skb, offset, len, sendmsg_locked);
}
EXPORT_SYMBOL_GPL(skb_send_sock_locked);
/* Send skb data on a socket. Socket must be unlocked. */
int skb_send_sock(struct sock *sk, struct sk_buff *skb, int offset, int len)
{
- return __skb_send_sock(sk, skb, offset, len, sendmsg_unlocked,
- sendpage_unlocked);
+ return __skb_send_sock(sk, skb, offset, len, sendmsg_unlocked);
}
/**
@@ -4203,13 +4195,13 @@ unsigned int skb_find_text(struct sk_buff *skb, unsigned int from,
EXPORT_SYMBOL(skb_find_text);
int skb_append_pagefrags(struct sk_buff *skb, struct page *page,
- int offset, size_t size)
+ int offset, size_t size, size_t max_frags)
{
int i = skb_shinfo(skb)->nr_frags;
if (skb_can_coalesce(skb, i, page, offset)) {
skb_frag_size_add(&skb_shinfo(skb)->frags[i - 1], size);
- } else if (i < MAX_SKB_FRAGS) {
+ } else if (i < max_frags) {
skb_zcopy_downgrade_managed(skb);
get_page(page);
skb_fill_page_desc_noacc(skb, i, page, offset, size);
@@ -4249,10 +4241,9 @@ static inline skb_frag_t skb_head_frag_to_page_desc(struct sk_buff *frag_skb)
struct page *page;
page = virt_to_head_page(frag_skb->head);
- __skb_frag_set_page(&head_frag, page);
- skb_frag_off_set(&head_frag, frag_skb->data -
- (unsigned char *)page_address(page));
- skb_frag_size_set(&head_frag, skb_headlen(frag_skb));
+ skb_frag_fill_page_desc(&head_frag, page, frag_skb->data -
+ (unsigned char *)page_address(page),
+ skb_headlen(frag_skb));
return head_frag;
}
@@ -4768,7 +4759,6 @@ void __init skb_init(void)
0,
SLAB_HWCACHE_ALIGN|SLAB_PANIC,
NULL);
-#ifdef HAVE_SKB_SMALL_HEAD_CACHE
/* usercopy should only access first SKB_SMALL_HEAD_HEADROOM bytes.
* struct skb_shared_info is located at the end of skb->head,
* and should not be copied to/from user.
@@ -4780,7 +4770,6 @@ void __init skb_init(void)
0,
SKB_SMALL_HEAD_HEADROOM,
NULL);
-#endif
skb_extensions_init();
}
@@ -5784,147 +5773,6 @@ void skb_scrub_packet(struct sk_buff *skb, bool xnet)
}
EXPORT_SYMBOL_GPL(skb_scrub_packet);
-/**
- * skb_gso_transport_seglen - Return length of individual segments of a gso packet
- *
- * @skb: GSO skb
- *
- * skb_gso_transport_seglen is used to determine the real size of the
- * individual segments, including Layer4 headers (TCP/UDP).
- *
- * The MAC/L2 or network (IP, IPv6) headers are not accounted for.
- */
-static unsigned int skb_gso_transport_seglen(const struct sk_buff *skb)
-{
- const struct skb_shared_info *shinfo = skb_shinfo(skb);
- unsigned int thlen = 0;
-
- if (skb->encapsulation) {
- thlen = skb_inner_transport_header(skb) -
- skb_transport_header(skb);
-
- if (likely(shinfo->gso_type & (SKB_GSO_TCPV4 | SKB_GSO_TCPV6)))
- thlen += inner_tcp_hdrlen(skb);
- } else if (likely(shinfo->gso_type & (SKB_GSO_TCPV4 | SKB_GSO_TCPV6))) {
- thlen = tcp_hdrlen(skb);
- } else if (unlikely(skb_is_gso_sctp(skb))) {
- thlen = sizeof(struct sctphdr);
- } else if (shinfo->gso_type & SKB_GSO_UDP_L4) {
- thlen = sizeof(struct udphdr);
- }
- /* UFO sets gso_size to the size of the fragmentation
- * payload, i.e. the size of the L4 (UDP) header is already
- * accounted for.
- */
- return thlen + shinfo->gso_size;
-}
-
-/**
- * skb_gso_network_seglen - Return length of individual segments of a gso packet
- *
- * @skb: GSO skb
- *
- * skb_gso_network_seglen is used to determine the real size of the
- * individual segments, including Layer3 (IP, IPv6) and L4 headers (TCP/UDP).
- *
- * The MAC/L2 header is not accounted for.
- */
-static unsigned int skb_gso_network_seglen(const struct sk_buff *skb)
-{
- unsigned int hdr_len = skb_transport_header(skb) -
- skb_network_header(skb);
-
- return hdr_len + skb_gso_transport_seglen(skb);
-}
-
-/**
- * skb_gso_mac_seglen - Return length of individual segments of a gso packet
- *
- * @skb: GSO skb
- *
- * skb_gso_mac_seglen is used to determine the real size of the
- * individual segments, including MAC/L2, Layer3 (IP, IPv6) and L4
- * headers (TCP/UDP).
- */
-static unsigned int skb_gso_mac_seglen(const struct sk_buff *skb)
-{
- unsigned int hdr_len = skb_transport_header(skb) - skb_mac_header(skb);
-
- return hdr_len + skb_gso_transport_seglen(skb);
-}
-
-/**
- * skb_gso_size_check - check the skb size, considering GSO_BY_FRAGS
- *
- * There are a couple of instances where we have a GSO skb, and we
- * want to determine what size it would be after it is segmented.
- *
- * We might want to check:
- * - L3+L4+payload size (e.g. IP forwarding)
- * - L2+L3+L4+payload size (e.g. sanity check before passing to driver)
- *
- * This is a helper to do that correctly considering GSO_BY_FRAGS.
- *
- * @skb: GSO skb
- *
- * @seg_len: The segmented length (from skb_gso_*_seglen). In the
- * GSO_BY_FRAGS case this will be [header sizes + GSO_BY_FRAGS].
- *
- * @max_len: The maximum permissible length.
- *
- * Returns true if the segmented length <= max length.
- */
-static inline bool skb_gso_size_check(const struct sk_buff *skb,
- unsigned int seg_len,
- unsigned int max_len) {
- const struct skb_shared_info *shinfo = skb_shinfo(skb);
- const struct sk_buff *iter;
-
- if (shinfo->gso_size != GSO_BY_FRAGS)
- return seg_len <= max_len;
-
- /* Undo this so we can re-use header sizes */
- seg_len -= GSO_BY_FRAGS;
-
- skb_walk_frags(skb, iter) {
- if (seg_len + skb_headlen(iter) > max_len)
- return false;
- }
-
- return true;
-}
-
-/**
- * skb_gso_validate_network_len - Will a split GSO skb fit into a given MTU?
- *
- * @skb: GSO skb
- * @mtu: MTU to validate against
- *
- * skb_gso_validate_network_len validates if a given skb will fit a
- * wanted MTU once split. It considers L3 headers, L4 headers, and the
- * payload.
- */
-bool skb_gso_validate_network_len(const struct sk_buff *skb, unsigned int mtu)
-{
- return skb_gso_size_check(skb, skb_gso_network_seglen(skb), mtu);
-}
-EXPORT_SYMBOL_GPL(skb_gso_validate_network_len);
-
-/**
- * skb_gso_validate_mac_len - Will a split GSO skb fit in a given length?
- *
- * @skb: GSO skb
- * @len: length to validate against
- *
- * skb_gso_validate_mac_len validates if a given skb will fit a wanted
- * length once split, including L2, L3 and L4 headers and the payload.
- */
-bool skb_gso_validate_mac_len(const struct sk_buff *skb, unsigned int len)
-{
- return skb_gso_size_check(skb, skb_gso_mac_seglen(skb), len);
-}
-EXPORT_SYMBOL_GPL(skb_gso_validate_mac_len);
-
static struct sk_buff *skb_reorder_vlan_header(struct sk_buff *skb)
{
int mac_len, meta_len;
@@ -6912,3 +6760,91 @@ nodefer: __kfree_skb(skb);
if (unlikely(kick) && !cmpxchg(&sd->defer_ipi_scheduled, 0, 1))
smp_call_function_single_async(cpu, &sd->defer_csd);
}
+
+static void skb_splice_csum_page(struct sk_buff *skb, struct page *page,
+ size_t offset, size_t len)
+{
+ const char *kaddr;
+ __wsum csum;
+
+ kaddr = kmap_local_page(page);
+ csum = csum_partial(kaddr + offset, len, 0);
+ kunmap_local(kaddr);
+ skb->csum = csum_block_add(skb->csum, csum, skb->len);
+}
+
+/**
+ * skb_splice_from_iter - Splice (or copy) pages to skbuff
+ * @skb: The buffer to add pages to
+ * @iter: Iterator representing the pages to be added
+ * @maxsize: Maximum amount of pages to be added
+ * @gfp: Allocation flags
+ *
+ * This is a common helper function for supporting MSG_SPLICE_PAGES. It
+ * extracts pages from an iterator and adds them to the socket buffer if
+ * possible, copying them to fragments if not possible (such as if they're slab
+ * pages).
+ *
+ * Returns the amount of data spliced/copied or -EMSGSIZE if there's
+ * insufficient space in the buffer to transfer anything.
+ */
+ssize_t skb_splice_from_iter(struct sk_buff *skb, struct iov_iter *iter,
+ ssize_t maxsize, gfp_t gfp)
+{
+ size_t frag_limit = READ_ONCE(sysctl_max_skb_frags);
+ struct page *pages[8], **ppages = pages;
+ ssize_t spliced = 0, ret = 0;
+ unsigned int i;
+
+ while (iter->count > 0) {
+ ssize_t space, nr, len;
+ size_t off;
+
+ ret = -EMSGSIZE;
+ space = frag_limit - skb_shinfo(skb)->nr_frags;
+ if (space < 0)
+ break;
+
+ /* We might be able to coalesce without increasing nr_frags */
+ nr = clamp_t(size_t, space, 1, ARRAY_SIZE(pages));
+
+ len = iov_iter_extract_pages(iter, &ppages, maxsize, nr, 0, &off);
+ if (len <= 0) {
+ ret = len ?: -EIO;
+ break;
+ }
+
+ i = 0;
+ do {
+ struct page *page = pages[i++];
+ size_t part = min_t(size_t, PAGE_SIZE - off, len);
+
+ ret = -EIO;
+ if (WARN_ON_ONCE(!sendpage_ok(page)))
+ goto out;
+
+ ret = skb_append_pagefrags(skb, page, off, part,
+ frag_limit);
+ if (ret < 0) {
+ iov_iter_revert(iter, len);
+ goto out;
+ }
+
+ if (skb->ip_summed == CHECKSUM_NONE)
+ skb_splice_csum_page(skb, page, off, part);
+
+ off = 0;
+ spliced += part;
+ maxsize -= part;
+ len -= part;
+ } while (len > 0);
+
+ if (maxsize <= 0)
+ break;
+ }
+
+out:
+ skb_len_add(skb, spliced);
+ return spliced ?: ret;
+}
+EXPORT_SYMBOL(skb_splice_from_iter);
diff --git a/net/core/sock.c b/net/core/sock.c
index 6e5662ca00fe..9370fd50aa2c 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -114,6 +114,9 @@
#include <linux/memcontrol.h>
#include <linux/prefetch.h>
#include <linux/compat.h>
+#include <linux/mroute.h>
+#include <linux/mroute6.h>
+#include <linux/icmpv6.h>
#include <linux/uaccess.h>
@@ -138,6 +141,7 @@
#include <net/tcp.h>
#include <net/busy_poll.h>
+#include <net/phonet/phonet.h>
#include <linux/ethtool.h>
@@ -1246,6 +1250,13 @@ set_sndbuf:
clear_bit(SOCK_PASSCRED, &sock->flags);
break;
+ case SO_PASSPIDFD:
+ if (valbool)
+ set_bit(SOCK_PASSPIDFD, &sock->flags);
+ else
+ clear_bit(SOCK_PASSPIDFD, &sock->flags);
+ break;
+
case SO_TIMESTAMP_OLD:
case SO_TIMESTAMP_NEW:
case SO_TIMESTAMPNS_OLD:
@@ -1726,6 +1737,10 @@ int sk_getsockopt(struct sock *sk, int level, int optname,
v.val = !!test_bit(SOCK_PASSCRED, &sock->flags);
break;
+ case SO_PASSPIDFD:
+ v.val = !!test_bit(SOCK_PASSPIDFD, &sock->flags);
+ break;
+
case SO_PEERCRED:
{
struct ucred peercred;
@@ -1741,6 +1756,39 @@ int sk_getsockopt(struct sock *sk, int level, int optname,
goto lenout;
}
+ case SO_PEERPIDFD:
+ {
+ struct pid *peer_pid;
+ struct file *pidfd_file = NULL;
+ int pidfd;
+
+ if (len > sizeof(pidfd))
+ len = sizeof(pidfd);
+
+ spin_lock(&sk->sk_peer_lock);
+ peer_pid = get_pid(sk->sk_peer_pid);
+ spin_unlock(&sk->sk_peer_lock);
+
+ if (!peer_pid)
+ return -ESRCH;
+
+ pidfd = pidfd_prepare(peer_pid, 0, &pidfd_file);
+ put_pid(peer_pid);
+ if (pidfd < 0)
+ return pidfd;
+
+ if (copy_to_sockptr(optval, &pidfd, len) ||
+ copy_to_sockptr(optlen, &len, sizeof(int))) {
+ put_unused_fd(pidfd);
+ fput(pidfd_file);
+
+ return -EFAULT;
+ }
+
+ fd_install(pidfd, pidfd_file);
+ return 0;
+ }
+
case SO_PEERGROUPS:
{
const struct cred *cred;
@@ -2550,13 +2598,24 @@ kuid_t sock_i_uid(struct sock *sk)
}
EXPORT_SYMBOL(sock_i_uid);
-unsigned long sock_i_ino(struct sock *sk)
+unsigned long __sock_i_ino(struct sock *sk)
{
unsigned long ino;
- read_lock_bh(&sk->sk_callback_lock);
+ read_lock(&sk->sk_callback_lock);
ino = sk->sk_socket ? SOCK_INODE(sk->sk_socket)->i_ino : 0;
- read_unlock_bh(&sk->sk_callback_lock);
+ read_unlock(&sk->sk_callback_lock);
+ return ino;
+}
+EXPORT_SYMBOL(__sock_i_ino);
+
+unsigned long sock_i_ino(struct sock *sk)
+{
+ unsigned long ino;
+
+ local_bh_disable();
+ ino = __sock_i_ino(sk);
+ local_bh_enable();
return ino;
}
EXPORT_SYMBOL(sock_i_ino);
@@ -3213,36 +3272,6 @@ void __receive_sock(struct file *file)
}
}
-ssize_t sock_no_sendpage(struct socket *sock, struct page *page, int offset, size_t size, int flags)
-{
- ssize_t res;
- struct msghdr msg = {.msg_flags = flags};
- struct kvec iov;
- char *kaddr = kmap(page);
- iov.iov_base = kaddr + offset;
- iov.iov_len = size;
- res = kernel_sendmsg(sock, &msg, &iov, 1, size);
- kunmap(page);
- return res;
-}
-EXPORT_SYMBOL(sock_no_sendpage);
-
-ssize_t sock_no_sendpage_locked(struct sock *sk, struct page *page,
- int offset, size_t size, int flags)
-{
- ssize_t res;
- struct msghdr msg = {.msg_flags = flags};
- struct kvec iov;
- char *kaddr = kmap(page);
-
- iov.iov_base = kaddr + offset;
- iov.iov_len = size;
- res = kernel_sendmsg_locked(sk, &msg, &iov, 1, size);
- kunmap(page);
- return res;
-}
-EXPORT_SYMBOL(sock_no_sendpage_locked);
-
/*
* Default Socket Callbacks
*/
@@ -3998,7 +4027,7 @@ static void proto_seq_printf(struct seq_file *seq, struct proto *proto)
{
seq_printf(seq, "%-9s %4u %6d %6ld %-3s %6u %-3s %-10s "
- "%2c %2c %2c %2c %2c %2c %2c %2c %2c %2c %2c %2c %2c %2c %2c %2c %2c %2c %2c\n",
+ "%2c %2c %2c %2c %2c %2c %2c %2c %2c %2c %2c %2c %2c %2c %2c %2c %2c %2c\n",
proto->name,
proto->obj_size,
sock_prot_inuse_get(seq_file_net(seq), proto),
@@ -4019,7 +4048,6 @@ static void proto_seq_printf(struct seq_file *seq, struct proto *proto)
proto_method_implemented(proto->getsockopt),
proto_method_implemented(proto->sendmsg),
proto_method_implemented(proto->recvmsg),
- proto_method_implemented(proto->sendpage),
proto_method_implemented(proto->bind),
proto_method_implemented(proto->backlog_rcv),
proto_method_implemented(proto->hash),
@@ -4040,7 +4068,7 @@ static int proto_seq_show(struct seq_file *seq, void *v)
"maxhdr",
"slab",
"module",
- "cl co di ac io in de sh ss gs se re sp bi br ha uh gp em\n");
+ "cl co di ac io in de sh ss gs se re bi br ha uh gp em\n");
else
proto_seq_printf(seq, list_entry(v, struct proto, node));
return 0;
@@ -4100,3 +4128,63 @@ int sock_bind_add(struct sock *sk, struct sockaddr *addr, int addr_len)
return sk->sk_prot->bind_add(sk, addr, addr_len);
}
EXPORT_SYMBOL(sock_bind_add);
+
+/* Copy 'size' bytes from userspace and return `size` back to userspace */
+int sock_ioctl_inout(struct sock *sk, unsigned int cmd,
+ void __user *arg, void *karg, size_t size)
+{
+ int ret;
+
+ if (copy_from_user(karg, arg, size))
+ return -EFAULT;
+
+ ret = READ_ONCE(sk->sk_prot)->ioctl(sk, cmd, karg);
+ if (ret)
+ return ret;
+
+ if (copy_to_user(arg, karg, size))
+ return -EFAULT;
+
+ return 0;
+}
+EXPORT_SYMBOL(sock_ioctl_inout);
+
+/* This is the most common ioctl prep function, where the result (4 bytes) is
+ * copied back to userspace if the ioctl() returns successfully. No input is
+ * copied from userspace as input argument.
+ */
+static int sock_ioctl_out(struct sock *sk, unsigned int cmd, void __user *arg)
+{
+ int ret, karg = 0;
+
+ ret = READ_ONCE(sk->sk_prot)->ioctl(sk, cmd, &karg);
+ if (ret)
+ return ret;
+
+ return put_user(karg, (int __user *)arg);
+}
+
+/* A wrapper around sock ioctls, which copies the data from userspace
+ * (depending on the protocol/ioctl), and copies back the result to userspace.
+ * The main motivation for this function is to pass kernel memory to the
+ * protocol ioctl callbacks, instead of userspace memory.
+ */
+int sk_ioctl(struct sock *sk, unsigned int cmd, void __user *arg)
+{
+ int rc = 1;
+
+ if (sk->sk_type == SOCK_RAW && sk->sk_family == AF_INET)
+ rc = ipmr_sk_ioctl(sk, cmd, arg);
+ else if (sk->sk_type == SOCK_RAW && sk->sk_family == AF_INET6)
+ rc = ip6mr_sk_ioctl(sk, cmd, arg);
+ else if (sk_is_phonet(sk))
+ rc = phonet_sk_ioctl(sk, cmd, arg);
+
+ /* If ioctl was processed, returns its value */
+ if (rc <= 0)
+ return rc;
+
+ /* Otherwise call the default handler */
+ return sock_ioctl_out(sk, cmd, arg);
+}
+EXPORT_SYMBOL(sk_ioctl);
diff --git a/net/core/sock_map.c b/net/core/sock_map.c
index 00afb66cd095..19538d628714 100644
--- a/net/core/sock_map.c
+++ b/net/core/sock_map.c
@@ -32,8 +32,6 @@ static struct bpf_map *sock_map_alloc(union bpf_attr *attr)
{
struct bpf_stab *stab;
- if (!capable(CAP_NET_ADMIN))
- return ERR_PTR(-EPERM);
if (attr->max_entries == 0 ||
attr->key_size != 4 ||
(attr->value_size != sizeof(u32) &&
@@ -1085,8 +1083,6 @@ static struct bpf_map *sock_hash_alloc(union bpf_attr *attr)
struct bpf_shtab *htab;
int i, err;
- if (!capable(CAP_NET_ADMIN))
- return ERR_PTR(-EPERM);
if (attr->max_entries == 0 ||
attr->key_size == 0 ||
(attr->value_size != sizeof(u32) &&
diff --git a/net/dccp/dccp.h b/net/dccp/dccp.h
index 9ddc3a9e89e4..1f748ed1279d 100644
--- a/net/dccp/dccp.h
+++ b/net/dccp/dccp.h
@@ -292,7 +292,7 @@ int dccp_getsockopt(struct sock *sk, int level, int optname,
char __user *optval, int __user *optlen);
int dccp_setsockopt(struct sock *sk, int level, int optname,
sockptr_t optval, unsigned int optlen);
-int dccp_ioctl(struct sock *sk, int cmd, unsigned long arg);
+int dccp_ioctl(struct sock *sk, int cmd, int *karg);
int dccp_sendmsg(struct sock *sk, struct msghdr *msg, size_t size);
int dccp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int flags,
int *addr_len);
diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c
index 3ab68415d121..fa8079303cb0 100644
--- a/net/dccp/ipv4.c
+++ b/net/dccp/ipv4.c
@@ -1010,7 +1010,6 @@ static const struct proto_ops inet_dccp_ops = {
.sendmsg = inet_sendmsg,
.recvmsg = sock_common_recvmsg,
.mmap = sock_no_mmap,
- .sendpage = sock_no_sendpage,
};
static struct inet_protosw dccp_v4_protosw = {
diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c
index 93c98990d726..7249ef218178 100644
--- a/net/dccp/ipv6.c
+++ b/net/dccp/ipv6.c
@@ -1087,7 +1087,6 @@ static const struct proto_ops inet6_dccp_ops = {
.sendmsg = inet_sendmsg,
.recvmsg = sock_common_recvmsg,
.mmap = sock_no_mmap,
- .sendpage = sock_no_sendpage,
#ifdef CONFIG_COMPAT
.compat_ioctl = inet6_compat_ioctl,
#endif
diff --git a/net/dccp/proto.c b/net/dccp/proto.c
index b0ebf853cb07..f331e5977a84 100644
--- a/net/dccp/proto.c
+++ b/net/dccp/proto.c
@@ -362,7 +362,7 @@ __poll_t dccp_poll(struct file *file, struct socket *sock,
EXPORT_SYMBOL_GPL(dccp_poll);
-int dccp_ioctl(struct sock *sk, int cmd, unsigned long arg)
+int dccp_ioctl(struct sock *sk, int cmd, int *karg)
{
int rc = -ENOTCONN;
@@ -373,17 +373,17 @@ int dccp_ioctl(struct sock *sk, int cmd, unsigned long arg)
switch (cmd) {
case SIOCOUTQ: {
- int amount = sk_wmem_alloc_get(sk);
+ *karg = sk_wmem_alloc_get(sk);
/* Using sk_wmem_alloc here because sk_wmem_queued is not used by DCCP and
* always 0, comparably to UDP.
*/
- rc = put_user(amount, (int __user *)arg);
+ rc = 0;
}
break;
case SIOCINQ: {
struct sk_buff *skb;
- unsigned long amount = 0;
+ *karg = 0;
skb = skb_peek(&sk->sk_receive_queue);
if (skb != NULL) {
@@ -391,9 +391,9 @@ int dccp_ioctl(struct sock *sk, int cmd, unsigned long arg)
* We will only return the amount of this packet since
* that is all that will be read.
*/
- amount = skb->len;
+ *karg = skb->len;
}
- rc = put_user(amount, (int __user *)arg);
+ rc = 0;
}
break;
default:
diff --git a/net/devlink/health.c b/net/devlink/health.c
index 0839706d5741..194340a8bb86 100644
--- a/net/devlink/health.c
+++ b/net/devlink/health.c
@@ -480,7 +480,7 @@ static void devlink_recover_notify(struct devlink_health_reporter *reporter,
int err;
WARN_ON(cmd != DEVLINK_CMD_HEALTH_REPORTER_RECOVER);
- WARN_ON(!xa_get_mark(&devlinks, devlink->index, DEVLINK_REGISTERED));
+ ASSERT_DEVLINK_REGISTERED(devlink);
msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
if (!msg)
diff --git a/net/devlink/leftover.c b/net/devlink/leftover.c
index cd0254968076..1f00f874471f 100644
--- a/net/devlink/leftover.c
+++ b/net/devlink/leftover.c
@@ -447,18 +447,18 @@ static void devlink_port_fn_cap_fill(struct nla_bitfield32 *caps,
caps->value |= cap;
}
-static int devlink_port_fn_roce_fill(const struct devlink_ops *ops,
- struct devlink_port *devlink_port,
+static int devlink_port_fn_roce_fill(struct devlink_port *devlink_port,
struct nla_bitfield32 *caps,
struct netlink_ext_ack *extack)
{
bool is_enable;
int err;
- if (!ops->port_fn_roce_get)
+ if (!devlink_port->ops->port_fn_roce_get)
return 0;
- err = ops->port_fn_roce_get(devlink_port, &is_enable, extack);
+ err = devlink_port->ops->port_fn_roce_get(devlink_port, &is_enable,
+ extack);
if (err) {
if (err == -EOPNOTSUPP)
return 0;
@@ -469,19 +469,19 @@ static int devlink_port_fn_roce_fill(const struct devlink_ops *ops,
return 0;
}
-static int devlink_port_fn_migratable_fill(const struct devlink_ops *ops,
- struct devlink_port *devlink_port,
+static int devlink_port_fn_migratable_fill(struct devlink_port *devlink_port,
struct nla_bitfield32 *caps,
struct netlink_ext_ack *extack)
{
bool is_enable;
int err;
- if (!ops->port_fn_migratable_get ||
+ if (!devlink_port->ops->port_fn_migratable_get ||
devlink_port->attrs.flavour != DEVLINK_PORT_FLAVOUR_PCI_VF)
return 0;
- err = ops->port_fn_migratable_get(devlink_port, &is_enable, extack);
+ err = devlink_port->ops->port_fn_migratable_get(devlink_port,
+ &is_enable, extack);
if (err) {
if (err == -EOPNOTSUPP)
return 0;
@@ -492,8 +492,7 @@ static int devlink_port_fn_migratable_fill(const struct devlink_ops *ops,
return 0;
}
-static int devlink_port_fn_caps_fill(const struct devlink_ops *ops,
- struct devlink_port *devlink_port,
+static int devlink_port_fn_caps_fill(struct devlink_port *devlink_port,
struct sk_buff *msg,
struct netlink_ext_ack *extack,
bool *msg_updated)
@@ -501,11 +500,11 @@ static int devlink_port_fn_caps_fill(const struct devlink_ops *ops,
struct nla_bitfield32 caps = {};
int err;
- err = devlink_port_fn_roce_fill(ops, devlink_port, &caps, extack);
+ err = devlink_port_fn_roce_fill(devlink_port, &caps, extack);
if (err)
return err;
- err = devlink_port_fn_migratable_fill(ops, devlink_port, &caps, extack);
+ err = devlink_port_fn_migratable_fill(devlink_port, &caps, extack);
if (err)
return err;
@@ -691,8 +690,7 @@ static int devlink_nl_port_attrs_put(struct sk_buff *msg,
return 0;
}
-static int devlink_port_fn_hw_addr_fill(const struct devlink_ops *ops,
- struct devlink_port *port,
+static int devlink_port_fn_hw_addr_fill(struct devlink_port *port,
struct sk_buff *msg,
struct netlink_ext_ack *extack,
bool *msg_updated)
@@ -701,10 +699,10 @@ static int devlink_port_fn_hw_addr_fill(const struct devlink_ops *ops,
int hw_addr_len;
int err;
- if (!ops->port_function_hw_addr_get)
+ if (!port->ops->port_fn_hw_addr_get)
return 0;
- err = ops->port_function_hw_addr_get(port, hw_addr, &hw_addr_len,
+ err = port->ops->port_fn_hw_addr_get(port, hw_addr, &hw_addr_len,
extack);
if (err) {
if (err == -EOPNOTSUPP)
@@ -789,8 +787,7 @@ devlink_port_fn_opstate_valid(enum devlink_port_fn_opstate opstate)
opstate == DEVLINK_PORT_FN_OPSTATE_ATTACHED;
}
-static int devlink_port_fn_state_fill(const struct devlink_ops *ops,
- struct devlink_port *port,
+static int devlink_port_fn_state_fill(struct devlink_port *port,
struct sk_buff *msg,
struct netlink_ext_ack *extack,
bool *msg_updated)
@@ -799,10 +796,10 @@ static int devlink_port_fn_state_fill(const struct devlink_ops *ops,
enum devlink_port_fn_state state;
int err;
- if (!ops->port_fn_state_get)
+ if (!port->ops->port_fn_state_get)
return 0;
- err = ops->port_fn_state_get(port, &state, &opstate, extack);
+ err = port->ops->port_fn_state_get(port, &state, &opstate, extack);
if (err) {
if (err == -EOPNOTSUPP)
return 0;
@@ -829,18 +826,16 @@ static int
devlink_port_fn_mig_set(struct devlink_port *devlink_port, bool enable,
struct netlink_ext_ack *extack)
{
- const struct devlink_ops *ops = devlink_port->devlink->ops;
-
- return ops->port_fn_migratable_set(devlink_port, enable, extack);
+ return devlink_port->ops->port_fn_migratable_set(devlink_port, enable,
+ extack);
}
static int
devlink_port_fn_roce_set(struct devlink_port *devlink_port, bool enable,
struct netlink_ext_ack *extack)
{
- const struct devlink_ops *ops = devlink_port->devlink->ops;
-
- return ops->port_fn_roce_set(devlink_port, enable, extack);
+ return devlink_port->ops->port_fn_roce_set(devlink_port, enable,
+ extack);
}
static int devlink_port_fn_caps_set(struct devlink_port *devlink_port,
@@ -874,7 +869,6 @@ static int
devlink_nl_port_function_attrs_put(struct sk_buff *msg, struct devlink_port *port,
struct netlink_ext_ack *extack)
{
- const struct devlink_ops *ops;
struct nlattr *function_attr;
bool msg_updated = false;
int err;
@@ -883,16 +877,13 @@ devlink_nl_port_function_attrs_put(struct sk_buff *msg, struct devlink_port *por
if (!function_attr)
return -EMSGSIZE;
- ops = port->devlink->ops;
- err = devlink_port_fn_hw_addr_fill(ops, port, msg, extack,
- &msg_updated);
+ err = devlink_port_fn_hw_addr_fill(port, msg, extack, &msg_updated);
if (err)
goto out;
- err = devlink_port_fn_caps_fill(ops, port, msg, extack,
- &msg_updated);
+ err = devlink_port_fn_caps_fill(port, msg, extack, &msg_updated);
if (err)
goto out;
- err = devlink_port_fn_state_fill(ops, port, msg, extack, &msg_updated);
+ err = devlink_port_fn_state_fill(port, msg, extack, &msg_updated);
out:
if (err || !msg_updated)
nla_nest_cancel(msg, function_attr);
@@ -1137,14 +1128,13 @@ static int devlink_port_type_set(struct devlink_port *devlink_port,
{
int err;
- if (!devlink_port->devlink->ops->port_type_set)
+ if (!devlink_port->ops->port_type_set)
return -EOPNOTSUPP;
if (port_type == devlink_port->type)
return 0;
- err = devlink_port->devlink->ops->port_type_set(devlink_port,
- port_type);
+ err = devlink_port->ops->port_type_set(devlink_port, port_type);
if (err)
return err;
@@ -1157,7 +1147,6 @@ static int devlink_port_function_hw_addr_set(struct devlink_port *port,
const struct nlattr *attr,
struct netlink_ext_ack *extack)
{
- const struct devlink_ops *ops = port->devlink->ops;
const u8 *hw_addr;
int hw_addr_len;
@@ -1178,7 +1167,7 @@ static int devlink_port_function_hw_addr_set(struct devlink_port *port,
}
}
- return ops->port_function_hw_addr_set(port, hw_addr, hw_addr_len,
+ return port->ops->port_fn_hw_addr_set(port, hw_addr, hw_addr_len,
extack);
}
@@ -1187,22 +1176,20 @@ static int devlink_port_fn_state_set(struct devlink_port *port,
struct netlink_ext_ack *extack)
{
enum devlink_port_fn_state state;
- const struct devlink_ops *ops;
state = nla_get_u8(attr);
- ops = port->devlink->ops;
- return ops->port_fn_state_set(port, state, extack);
+ return port->ops->port_fn_state_set(port, state, extack);
}
static int devlink_port_function_validate(struct devlink_port *devlink_port,
struct nlattr **tb,
struct netlink_ext_ack *extack)
{
- const struct devlink_ops *ops = devlink_port->devlink->ops;
+ const struct devlink_port_ops *ops = devlink_port->ops;
struct nlattr *attr;
if (tb[DEVLINK_PORT_FUNCTION_ATTR_HW_ADDR] &&
- !ops->port_function_hw_addr_set) {
+ !ops->port_fn_hw_addr_set) {
NL_SET_ERR_MSG_ATTR(extack, tb[DEVLINK_PORT_FUNCTION_ATTR_HW_ADDR],
"Port doesn't support function attributes");
return -EOPNOTSUPP;
@@ -1320,7 +1307,7 @@ static int devlink_nl_cmd_port_split_doit(struct sk_buff *skb,
if (GENL_REQ_ATTR_CHECK(info, DEVLINK_ATTR_PORT_SPLIT_COUNT))
return -EINVAL;
- if (!devlink->ops->port_split)
+ if (!devlink_port->ops->port_split)
return -EOPNOTSUPP;
count = nla_get_u32(info->attrs[DEVLINK_ATTR_PORT_SPLIT_COUNT]);
@@ -1339,8 +1326,8 @@ static int devlink_nl_cmd_port_split_doit(struct sk_buff *skb,
return -EINVAL;
}
- return devlink->ops->port_split(devlink, devlink_port, count,
- info->extack);
+ return devlink_port->ops->port_split(devlink, devlink_port, count,
+ info->extack);
}
static int devlink_nl_cmd_port_unsplit_doit(struct sk_buff *skb,
@@ -1349,40 +1336,9 @@ static int devlink_nl_cmd_port_unsplit_doit(struct sk_buff *skb,
struct devlink_port *devlink_port = info->user_ptr[1];
struct devlink *devlink = info->user_ptr[0];
- if (!devlink->ops->port_unsplit)
+ if (!devlink_port->ops->port_unsplit)
return -EOPNOTSUPP;
- return devlink->ops->port_unsplit(devlink, devlink_port, info->extack);
-}
-
-static int devlink_port_new_notify(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;
-
- lockdep_assert_held(&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_port, DEVLINK_CMD_NEW,
- info->snd_portid, info->snd_seq, 0, NULL);
- if (err)
- goto out;
-
- return genlmsg_reply(msg, info);
-
-out:
- nlmsg_free(msg);
- return err;
+ return devlink_port->ops->port_unsplit(devlink, devlink_port, info->extack);
}
static int devlink_nl_cmd_port_new_doit(struct sk_buff *skb,
@@ -1391,10 +1347,11 @@ static int devlink_nl_cmd_port_new_doit(struct sk_buff *skb,
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;
+ struct devlink_port *devlink_port;
+ struct sk_buff *msg;
int err;
- if (!devlink->ops->port_new || !devlink->ops->port_del)
+ if (!devlink->ops->port_new)
return -EOPNOTSUPP;
if (!info->attrs[DEVLINK_ATTR_PORT_FLAVOUR] ||
@@ -1423,36 +1380,43 @@ static int devlink_nl_cmd_port_new_doit(struct sk_buff *skb,
new_attrs.sfnum_valid = true;
}
- err = devlink->ops->port_new(devlink, &new_attrs, extack,
- &new_port_index);
+ err = devlink->ops->port_new(devlink, &new_attrs,
+ extack, &devlink_port);
if (err)
return err;
- err = devlink_port_new_notify(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);
+ msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
+ if (!msg) {
+ err = -ENOMEM;
+ goto err_out_port_del;
}
+ err = devlink_nl_port_fill(msg, devlink_port, DEVLINK_CMD_NEW,
+ info->snd_portid, info->snd_seq, 0, NULL);
+ if (WARN_ON_ONCE(err))
+ goto err_out_msg_free;
+ err = genlmsg_reply(msg, info);
+ if (err)
+ goto err_out_port_del;
+ return 0;
+
+err_out_msg_free:
+ nlmsg_free(msg);
+err_out_port_del:
+ devlink_port->ops->port_del(devlink, devlink_port, NULL);
return err;
}
static int devlink_nl_cmd_port_del_doit(struct sk_buff *skb,
struct genl_info *info)
{
+ struct devlink_port *devlink_port = info->user_ptr[1];
struct netlink_ext_ack *extack = info->extack;
struct devlink *devlink = info->user_ptr[0];
- unsigned int port_index;
- if (!devlink->ops->port_del)
+ if (!devlink_port->ops->port_del)
return -EOPNOTSUPP;
- if (GENL_REQ_ATTR_CHECK(info, DEVLINK_ATTR_PORT_INDEX)) {
- NL_SET_ERR_MSG(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);
+ return devlink_port->ops->port_del(devlink, devlink_port, extack);
}
static int
@@ -6384,6 +6348,7 @@ const struct genl_small_ops devlink_nl_ops[56] = {
.cmd = DEVLINK_CMD_PORT_DEL,
.doit = devlink_nl_cmd_port_del_doit,
.flags = GENL_ADMIN_PERM,
+ .internal_flags = DEVLINK_NL_FLAG_NEED_PORT,
},
{
.cmd = DEVLINK_CMD_LINECARD_GET,
@@ -6772,7 +6737,10 @@ void devlink_notify_unregister(struct devlink *devlink)
static void devlink_port_type_warn(struct work_struct *work)
{
- WARN(true, "Type was not set for devlink port.");
+ struct devlink_port *port = container_of(to_delayed_work(work),
+ struct devlink_port,
+ type_warn_dw);
+ dev_warn(port->devlink->dev, "Type was not set for devlink port.");
}
static bool devlink_port_type_should_warn(struct devlink_port *devlink_port)
@@ -6809,7 +6777,7 @@ static void devlink_port_type_warn_cancel(struct devlink_port *devlink_port)
* @devlink: devlink
* @devlink_port: devlink port
*
- * Initialize essencial stuff that is needed for functions
+ * Initialize essential stuff that is needed for functions
* that may be called before devlink port registration.
* Call to this function is optional and not needed
* in case the driver does not use such functions.
@@ -6830,7 +6798,7 @@ EXPORT_SYMBOL_GPL(devlink_port_init);
*
* @devlink_port: devlink port
*
- * Deinitialize essencial stuff that is in use for functions
+ * Deinitialize essential stuff that is in use for functions
* that may be called after devlink port unregistration.
* Call to this function is optional and not needed
* in case the driver does not use such functions.
@@ -6841,12 +6809,15 @@ void devlink_port_fini(struct devlink_port *devlink_port)
}
EXPORT_SYMBOL_GPL(devlink_port_fini);
+static const struct devlink_port_ops devlink_port_dummy_ops = {};
+
/**
- * devl_port_register() - Register devlink port
+ * devl_port_register_with_ops() - Register devlink port
*
* @devlink: devlink
* @devlink_port: devlink port
* @port_index: driver-specific numerical identifier of the port
+ * @ops: port ops
*
* Register devlink port with provided port index. User can use
* any indexing, even hw-related one. devlink_port structure
@@ -6854,9 +6825,10 @@ EXPORT_SYMBOL_GPL(devlink_port_fini);
* Note that the caller should take care of zeroing the devlink_port
* structure.
*/
-int devl_port_register(struct devlink *devlink,
- struct devlink_port *devlink_port,
- unsigned int port_index)
+int devl_port_register_with_ops(struct devlink *devlink,
+ struct devlink_port *devlink_port,
+ unsigned int port_index,
+ const struct devlink_port_ops *ops)
{
int err;
@@ -6867,6 +6839,7 @@ int devl_port_register(struct devlink *devlink,
devlink_port_init(devlink, devlink_port);
devlink_port->registered = true;
devlink_port->index = port_index;
+ devlink_port->ops = ops ? ops : &devlink_port_dummy_ops;
spin_lock_init(&devlink_port->type_lock);
INIT_LIST_HEAD(&devlink_port->reporter_list);
err = xa_insert(&devlink->ports, port_index, devlink_port, GFP_KERNEL);
@@ -6878,14 +6851,15 @@ int devl_port_register(struct devlink *devlink,
devlink_port_notify(devlink_port, DEVLINK_CMD_PORT_NEW);
return 0;
}
-EXPORT_SYMBOL_GPL(devl_port_register);
+EXPORT_SYMBOL_GPL(devl_port_register_with_ops);
/**
- * devlink_port_register - Register devlink port
+ * devlink_port_register_with_ops - Register devlink port
*
* @devlink: devlink
* @devlink_port: devlink port
* @port_index: driver-specific numerical identifier of the port
+ * @ops: port ops
*
* Register devlink port with provided port index. User can use
* any indexing, even hw-related one. devlink_port structure
@@ -6895,18 +6869,20 @@ EXPORT_SYMBOL_GPL(devl_port_register);
*
* Context: Takes and release devlink->lock <mutex>.
*/
-int devlink_port_register(struct devlink *devlink,
- struct devlink_port *devlink_port,
- unsigned int port_index)
+int devlink_port_register_with_ops(struct devlink *devlink,
+ struct devlink_port *devlink_port,
+ unsigned int port_index,
+ const struct devlink_port_ops *ops)
{
int err;
devl_lock(devlink);
- err = devl_port_register(devlink, devlink_port, port_index);
+ err = devl_port_register_with_ops(devlink, devlink_port,
+ port_index, ops);
devl_unlock(devlink);
return err;
}
-EXPORT_SYMBOL_GPL(devlink_port_register);
+EXPORT_SYMBOL_GPL(devlink_port_register_with_ops);
/**
* devl_port_unregister() - Unregister devlink port
diff --git a/net/dsa/dsa.c b/net/dsa/dsa.c
index 1afed89e03c0..ccbdb98109f8 100644
--- a/net/dsa/dsa.c
+++ b/net/dsa/dsa.c
@@ -1106,7 +1106,7 @@ static struct dsa_port *dsa_port_touch(struct dsa_switch *ds, int index)
mutex_init(&dp->vlans_lock);
INIT_LIST_HEAD(&dp->fdbs);
INIT_LIST_HEAD(&dp->mdbs);
- INIT_LIST_HEAD(&dp->vlans);
+ INIT_LIST_HEAD(&dp->vlans); /* also initializes &dp->user_vlans */
INIT_LIST_HEAD(&dp->list);
list_add_tail(&dp->list, &dst->ports);
diff --git a/net/dsa/port.c b/net/dsa/port.c
index 71ba30538411..0ce8fd311c78 100644
--- a/net/dsa/port.c
+++ b/net/dsa/port.c
@@ -1603,6 +1603,21 @@ dsa_port_phylink_mac_select_pcs(struct phylink_config *config,
return pcs;
}
+static int dsa_port_phylink_mac_prepare(struct phylink_config *config,
+ unsigned int mode,
+ phy_interface_t interface)
+{
+ struct dsa_port *dp = container_of(config, struct dsa_port, pl_config);
+ struct dsa_switch *ds = dp->ds;
+ int err = 0;
+
+ if (ds->ops->phylink_mac_prepare)
+ err = ds->ops->phylink_mac_prepare(ds, dp->index, mode,
+ interface);
+
+ return err;
+}
+
static void dsa_port_phylink_mac_config(struct phylink_config *config,
unsigned int mode,
const struct phylink_link_state *state)
@@ -1616,6 +1631,21 @@ static void dsa_port_phylink_mac_config(struct phylink_config *config,
ds->ops->phylink_mac_config(ds, dp->index, mode, state);
}
+static int dsa_port_phylink_mac_finish(struct phylink_config *config,
+ unsigned int mode,
+ phy_interface_t interface)
+{
+ struct dsa_port *dp = container_of(config, struct dsa_port, pl_config);
+ struct dsa_switch *ds = dp->ds;
+ int err = 0;
+
+ if (ds->ops->phylink_mac_finish)
+ err = ds->ops->phylink_mac_finish(ds, dp->index, mode,
+ interface);
+
+ return err;
+}
+
static void dsa_port_phylink_mac_an_restart(struct phylink_config *config)
{
struct dsa_port *dp = container_of(config, struct dsa_port, pl_config);
@@ -1671,7 +1701,9 @@ static const struct phylink_mac_ops dsa_port_phylink_mac_ops = {
.validate = dsa_port_phylink_validate,
.mac_select_pcs = dsa_port_phylink_mac_select_pcs,
.mac_pcs_get_state = dsa_port_phylink_mac_pcs_get_state,
+ .mac_prepare = dsa_port_phylink_mac_prepare,
.mac_config = dsa_port_phylink_mac_config,
+ .mac_finish = dsa_port_phylink_mac_finish,
.mac_an_restart = dsa_port_phylink_mac_an_restart,
.mac_link_down = dsa_port_phylink_mac_link_down,
.mac_link_up = dsa_port_phylink_mac_link_up,
diff --git a/net/dsa/slave.c b/net/dsa/slave.c
index 165bb2cb8431..527b1d576460 100644
--- a/net/dsa/slave.c
+++ b/net/dsa/slave.c
@@ -27,6 +27,7 @@
#include "master.h"
#include "netlink.h"
#include "slave.h"
+#include "switch.h"
#include "tag.h"
struct dsa_switchdev_event_work {
@@ -161,8 +162,7 @@ static int dsa_slave_schedule_standalone_work(struct net_device *dev,
return 0;
}
-static int dsa_slave_host_vlan_rx_filtering(struct net_device *vdev, int vid,
- void *arg)
+static int dsa_slave_host_vlan_rx_filtering(void *arg, int vid)
{
struct dsa_host_vlan_rx_filtering_ctx *ctx = arg;
@@ -170,6 +170,28 @@ static int dsa_slave_host_vlan_rx_filtering(struct net_device *vdev, int vid,
ctx->addr, vid);
}
+static int dsa_slave_vlan_for_each(struct net_device *dev,
+ int (*cb)(void *arg, int vid), void *arg)
+{
+ struct dsa_port *dp = dsa_slave_to_port(dev);
+ struct dsa_vlan *v;
+ int err;
+
+ lockdep_assert_held(&dev->addr_list_lock);
+
+ err = cb(arg, 0);
+ if (err)
+ return err;
+
+ list_for_each_entry(v, &dp->user_vlans, list) {
+ err = cb(arg, v->vid);
+ if (err)
+ return err;
+ }
+
+ return 0;
+}
+
static int dsa_slave_sync_uc(struct net_device *dev,
const unsigned char *addr)
{
@@ -180,18 +202,14 @@ static int dsa_slave_sync_uc(struct net_device *dev,
.addr = addr,
.event = DSA_UC_ADD,
};
- int err;
dev_uc_add(master, addr);
if (!dsa_switch_supports_uc_filtering(dp->ds))
return 0;
- err = dsa_slave_schedule_standalone_work(dev, DSA_UC_ADD, addr, 0);
- if (err)
- return err;
-
- return vlan_for_each(dev, dsa_slave_host_vlan_rx_filtering, &ctx);
+ return dsa_slave_vlan_for_each(dev, dsa_slave_host_vlan_rx_filtering,
+ &ctx);
}
static int dsa_slave_unsync_uc(struct net_device *dev,
@@ -204,18 +222,14 @@ static int dsa_slave_unsync_uc(struct net_device *dev,
.addr = addr,
.event = DSA_UC_DEL,
};
- int err;
dev_uc_del(master, addr);
if (!dsa_switch_supports_uc_filtering(dp->ds))
return 0;
- err = dsa_slave_schedule_standalone_work(dev, DSA_UC_DEL, addr, 0);
- if (err)
- return err;
-
- return vlan_for_each(dev, dsa_slave_host_vlan_rx_filtering, &ctx);
+ return dsa_slave_vlan_for_each(dev, dsa_slave_host_vlan_rx_filtering,
+ &ctx);
}
static int dsa_slave_sync_mc(struct net_device *dev,
@@ -228,18 +242,14 @@ static int dsa_slave_sync_mc(struct net_device *dev,
.addr = addr,
.event = DSA_MC_ADD,
};
- int err;
dev_mc_add(master, addr);
if (!dsa_switch_supports_mc_filtering(dp->ds))
return 0;
- err = dsa_slave_schedule_standalone_work(dev, DSA_MC_ADD, addr, 0);
- if (err)
- return err;
-
- return vlan_for_each(dev, dsa_slave_host_vlan_rx_filtering, &ctx);
+ return dsa_slave_vlan_for_each(dev, dsa_slave_host_vlan_rx_filtering,
+ &ctx);
}
static int dsa_slave_unsync_mc(struct net_device *dev,
@@ -252,18 +262,14 @@ static int dsa_slave_unsync_mc(struct net_device *dev,
.addr = addr,
.event = DSA_MC_DEL,
};
- int err;
dev_mc_del(master, addr);
if (!dsa_switch_supports_mc_filtering(dp->ds))
return 0;
- err = dsa_slave_schedule_standalone_work(dev, DSA_MC_DEL, addr, 0);
- if (err)
- return err;
-
- return vlan_for_each(dev, dsa_slave_host_vlan_rx_filtering, &ctx);
+ return dsa_slave_vlan_for_each(dev, dsa_slave_host_vlan_rx_filtering,
+ &ctx);
}
void dsa_slave_sync_ha(struct net_device *dev)
@@ -1759,6 +1765,7 @@ static int dsa_slave_vlan_rx_add_vid(struct net_device *dev, __be16 proto,
struct netlink_ext_ack extack = {0};
struct dsa_switch *ds = dp->ds;
struct netdev_hw_addr *ha;
+ struct dsa_vlan *v;
int ret;
/* User port... */
@@ -1782,8 +1789,17 @@ static int dsa_slave_vlan_rx_add_vid(struct net_device *dev, __be16 proto,
!dsa_switch_supports_mc_filtering(ds))
return 0;
+ v = kzalloc(sizeof(*v), GFP_KERNEL);
+ if (!v) {
+ ret = -ENOMEM;
+ goto rollback;
+ }
+
netif_addr_lock_bh(dev);
+ v->vid = vid;
+ list_add_tail(&v->list, &dp->user_vlans);
+
if (dsa_switch_supports_mc_filtering(ds)) {
netdev_for_each_synced_mc_addr(ha, dev) {
dsa_slave_schedule_standalone_work(dev, DSA_MC_ADD,
@@ -1803,6 +1819,12 @@ static int dsa_slave_vlan_rx_add_vid(struct net_device *dev, __be16 proto,
dsa_flush_workqueue();
return 0;
+
+rollback:
+ dsa_port_host_vlan_del(dp, &vlan);
+ dsa_port_vlan_del(dp, &vlan);
+
+ return ret;
}
static int dsa_slave_vlan_rx_kill_vid(struct net_device *dev, __be16 proto,
@@ -1816,6 +1838,7 @@ static int dsa_slave_vlan_rx_kill_vid(struct net_device *dev, __be16 proto,
};
struct dsa_switch *ds = dp->ds;
struct netdev_hw_addr *ha;
+ struct dsa_vlan *v;
int err;
err = dsa_port_vlan_del(dp, &vlan);
@@ -1832,6 +1855,15 @@ static int dsa_slave_vlan_rx_kill_vid(struct net_device *dev, __be16 proto,
netif_addr_lock_bh(dev);
+ v = dsa_vlan_find(&dp->user_vlans, &vlan);
+ if (!v) {
+ netif_addr_unlock_bh(dev);
+ return -ENOENT;
+ }
+
+ list_del(&v->list);
+ kfree(v);
+
if (dsa_switch_supports_mc_filtering(ds)) {
netdev_for_each_synced_mc_addr(ha, dev) {
dsa_slave_schedule_standalone_work(dev, DSA_MC_DEL,
diff --git a/net/dsa/switch.c b/net/dsa/switch.c
index 8c9a9f94b756..1a42f9317334 100644
--- a/net/dsa/switch.c
+++ b/net/dsa/switch.c
@@ -673,8 +673,8 @@ static bool dsa_port_host_vlan_match(struct dsa_port *dp,
return false;
}
-static struct dsa_vlan *dsa_vlan_find(struct list_head *vlan_list,
- const struct switchdev_obj_port_vlan *vlan)
+struct dsa_vlan *dsa_vlan_find(struct list_head *vlan_list,
+ const struct switchdev_obj_port_vlan *vlan)
{
struct dsa_vlan *v;
diff --git a/net/dsa/switch.h b/net/dsa/switch.h
index 15e67b95eb6e..ea034677da15 100644
--- a/net/dsa/switch.h
+++ b/net/dsa/switch.h
@@ -111,6 +111,9 @@ struct dsa_notifier_master_state_info {
bool operational;
};
+struct dsa_vlan *dsa_vlan_find(struct list_head *vlan_list,
+ const struct switchdev_obj_port_vlan *vlan);
+
int dsa_tree_notify(struct dsa_switch_tree *dst, unsigned long e, void *v);
int dsa_broadcast(unsigned long e, void *v);
diff --git a/net/ethtool/ioctl.c b/net/ethtool/ioctl.c
index 6bb778e10461..4a51e0ec295c 100644
--- a/net/ethtool/ioctl.c
+++ b/net/ethtool/ioctl.c
@@ -1436,15 +1436,26 @@ static int ethtool_get_wol(struct net_device *dev, char __user *useraddr)
static int ethtool_set_wol(struct net_device *dev, char __user *useraddr)
{
- struct ethtool_wolinfo wol;
+ struct ethtool_wolinfo wol, cur_wol;
int ret;
- if (!dev->ethtool_ops->set_wol)
+ if (!dev->ethtool_ops->get_wol || !dev->ethtool_ops->set_wol)
return -EOPNOTSUPP;
+ memset(&cur_wol, 0, sizeof(struct ethtool_wolinfo));
+ cur_wol.cmd = ETHTOOL_GWOL;
+ dev->ethtool_ops->get_wol(dev, &cur_wol);
+
if (copy_from_user(&wol, useraddr, sizeof(wol)))
return -EFAULT;
+ if (wol.wolopts & ~cur_wol.supported)
+ return -EINVAL;
+
+ if (wol.wolopts == cur_wol.wolopts &&
+ !memcmp(wol.sopass, cur_wol.sopass, sizeof(wol.sopass)))
+ return 0;
+
ret = dev->ethtool_ops->set_wol(dev, &wol);
if (ret)
return ret;
diff --git a/net/ethtool/netlink.c b/net/ethtool/netlink.c
index 08120095cc68..39a459b0111b 100644
--- a/net/ethtool/netlink.c
+++ b/net/ethtool/netlink.c
@@ -96,6 +96,8 @@ int ethnl_parse_header_dev_get(struct ethnl_req_info *req_info,
int ret;
if (!header) {
+ if (!require_dev)
+ return 0;
NL_SET_ERR_MSG(extack, "request header missing");
return -EINVAL;
}
@@ -113,7 +115,8 @@ int ethnl_parse_header_dev_get(struct ethnl_req_info *req_info,
if (tb[ETHTOOL_A_HEADER_DEV_INDEX]) {
u32 ifindex = nla_get_u32(tb[ETHTOOL_A_HEADER_DEV_INDEX]);
- dev = dev_get_by_index(net, ifindex);
+ dev = netdev_get_by_index(net, ifindex, &req_info->dev_tracker,
+ GFP_KERNEL);
if (!dev) {
NL_SET_ERR_MSG_ATTR(extack,
tb[ETHTOOL_A_HEADER_DEV_INDEX],
@@ -123,13 +126,14 @@ int ethnl_parse_header_dev_get(struct ethnl_req_info *req_info,
/* if both ifindex and ifname are passed, they must match */
if (devname_attr &&
strncmp(dev->name, nla_data(devname_attr), IFNAMSIZ)) {
- dev_put(dev);
+ netdev_put(dev, &req_info->dev_tracker);
NL_SET_ERR_MSG_ATTR(extack, header,
"ifindex and name do not match");
return -ENODEV;
}
} else if (devname_attr) {
- dev = dev_get_by_name(net, nla_data(devname_attr));
+ dev = netdev_get_by_name(net, nla_data(devname_attr),
+ &req_info->dev_tracker, GFP_KERNEL);
if (!dev) {
NL_SET_ERR_MSG_ATTR(extack, devname_attr,
"no device matches name");
@@ -142,8 +146,6 @@ int ethnl_parse_header_dev_get(struct ethnl_req_info *req_info,
}
req_info->dev = dev;
- if (dev)
- netdev_tracker_alloc(dev, &req_info->dev_tracker, GFP_KERNEL);
req_info->flags = flags;
return 0;
}
diff --git a/net/handshake/genl.c b/net/handshake/genl.c
index 9f29efb1493e..233be5cbfec9 100644
--- a/net/handshake/genl.c
+++ b/net/handshake/genl.c
@@ -8,7 +8,7 @@
#include "genl.h"
-#include <linux/handshake.h>
+#include <uapi/linux/handshake.h>
/* HANDSHAKE_CMD_ACCEPT - do */
static const struct nla_policy handshake_accept_nl_policy[HANDSHAKE_A_ACCEPT_HANDLER_CLASS + 1] = {
diff --git a/net/handshake/genl.h b/net/handshake/genl.h
index 2c1f1aa6a02a..ae72a596f6cc 100644
--- a/net/handshake/genl.h
+++ b/net/handshake/genl.h
@@ -9,7 +9,7 @@
#include <net/netlink.h>
#include <net/genetlink.h>
-#include <linux/handshake.h>
+#include <uapi/linux/handshake.h>
int handshake_nl_accept_doit(struct sk_buff *skb, struct genl_info *info);
int handshake_nl_done_doit(struct sk_buff *skb, struct genl_info *info);
diff --git a/net/hsr/hsr_device.c b/net/hsr/hsr_device.c
index 5a236aae2366..306f942c3b28 100644
--- a/net/hsr/hsr_device.c
+++ b/net/hsr/hsr_device.c
@@ -531,6 +531,11 @@ int hsr_dev_finalize(struct net_device *hsr_dev, struct net_device *slave[2],
if (res)
goto err_add_master;
+ /* HSR forwarding offload supported in lower device? */
+ if ((slave[0]->features & NETIF_F_HW_HSR_FWD) &&
+ (slave[1]->features & NETIF_F_HW_HSR_FWD))
+ hsr->fwd_offloaded = true;
+
res = register_netdevice(hsr_dev);
if (res)
goto err_unregister;
diff --git a/net/hsr/hsr_main.h b/net/hsr/hsr_main.h
index 5584c80a5c79..6851e33df7d1 100644
--- a/net/hsr/hsr_main.h
+++ b/net/hsr/hsr_main.h
@@ -208,6 +208,7 @@ struct hsr_priv {
u8 net_id; /* for PRP, it occupies most significant 3 bits
* of lan_id
*/
+ bool fwd_offloaded; /* Forwarding offloaded to HW */
unsigned char sup_multicast_addr[ETH_ALEN] __aligned(sizeof(u16));
/* Align to u16 boundary to avoid unaligned access
* in ether_addr_equal
diff --git a/net/hsr/hsr_slave.c b/net/hsr/hsr_slave.c
index b70e6bbf6021..e5742f2a2d52 100644
--- a/net/hsr/hsr_slave.c
+++ b/net/hsr/hsr_slave.c
@@ -131,9 +131,14 @@ static int hsr_portdev_setup(struct hsr_priv *hsr, struct net_device *dev,
struct hsr_port *master;
int res;
- res = dev_set_promiscuity(dev, 1);
- if (res)
- return res;
+ /* Don't use promiscuous mode for offload since L2 frame forward
+ * happens at the offloaded hardware.
+ */
+ if (!port->hsr->fwd_offloaded) {
+ res = dev_set_promiscuity(dev, 1);
+ if (res)
+ return res;
+ }
master = hsr_port_get_hsr(hsr, HSR_PT_MASTER);
hsr_dev = master->dev;
@@ -152,7 +157,9 @@ static int hsr_portdev_setup(struct hsr_priv *hsr, struct net_device *dev,
fail_rx_handler:
netdev_upper_dev_unlink(dev, hsr_dev);
fail_upper_dev_link:
- dev_set_promiscuity(dev, -1);
+ if (!port->hsr->fwd_offloaded)
+ dev_set_promiscuity(dev, -1);
+
return res;
}
diff --git a/net/ieee802154/header_ops.c b/net/ieee802154/header_ops.c
index 35d384dfe29d..41a556be1017 100644
--- a/net/ieee802154/header_ops.c
+++ b/net/ieee802154/header_ops.c
@@ -120,6 +120,29 @@ ieee802154_hdr_push(struct sk_buff *skb, struct ieee802154_hdr *hdr)
}
EXPORT_SYMBOL_GPL(ieee802154_hdr_push);
+int ieee802154_mac_cmd_push(struct sk_buff *skb, void *f,
+ const void *pl, unsigned int pl_len)
+{
+ struct ieee802154_mac_cmd_frame *frame = f;
+ struct ieee802154_mac_cmd_pl *mac_pl = &frame->mac_pl;
+ struct ieee802154_hdr *mhr = &frame->mhr;
+ int ret;
+
+ skb_reserve(skb, sizeof(*mhr));
+ ret = ieee802154_hdr_push(skb, mhr);
+ if (ret < 0)
+ return ret;
+
+ skb_reset_mac_header(skb);
+ skb->mac_len = ret;
+
+ skb_put_data(skb, mac_pl, sizeof(*mac_pl));
+ skb_put_data(skb, pl, pl_len);
+
+ return 0;
+}
+EXPORT_SYMBOL_GPL(ieee802154_mac_cmd_push);
+
int ieee802154_beacon_push(struct sk_buff *skb,
struct ieee802154_beacon_frame *beacon)
{
@@ -284,6 +307,19 @@ ieee802154_hdr_pull(struct sk_buff *skb, struct ieee802154_hdr *hdr)
}
EXPORT_SYMBOL_GPL(ieee802154_hdr_pull);
+int ieee802154_mac_cmd_pl_pull(struct sk_buff *skb,
+ struct ieee802154_mac_cmd_pl *mac_pl)
+{
+ if (!pskb_may_pull(skb, sizeof(*mac_pl)))
+ return -EINVAL;
+
+ memcpy(mac_pl, skb->data, sizeof(*mac_pl));
+ skb_pull(skb, sizeof(*mac_pl));
+
+ return 0;
+}
+EXPORT_SYMBOL_GPL(ieee802154_mac_cmd_pl_pull);
+
int
ieee802154_hdr_peek_addrs(const struct sk_buff *skb, struct ieee802154_hdr *hdr)
{
diff --git a/net/ieee802154/nl802154.c b/net/ieee802154/nl802154.c
index 832e3c50816c..d610c1886160 100644
--- a/net/ieee802154/nl802154.c
+++ b/net/ieee802154/nl802154.c
@@ -233,7 +233,7 @@ static const struct nla_policy nl802154_policy[NL802154_ATTR_MAX+1] = {
NLA_POLICY_RANGE(NLA_U8, NL802154_SCAN_DONE_REASON_FINISHED,
NL802154_SCAN_DONE_REASON_ABORTED),
[NL802154_ATTR_BEACON_INTERVAL] =
- NLA_POLICY_MAX(NLA_U8, IEEE802154_MAX_SCAN_DURATION),
+ NLA_POLICY_MAX(NLA_U8, IEEE802154_ACTIVE_SCAN_DURATION),
#ifdef CONFIG_IEEE802154_NL802154_EXPERIMENTAL
[NL802154_ATTR_SEC_ENABLED] = { .type = NLA_U8, },
@@ -1417,6 +1417,11 @@ static int nl802154_trigger_scan(struct sk_buff *skb, struct genl_info *info)
return -EINVAL;
}
+ if (wpan_phy->flags & WPAN_PHY_FLAG_DATAGRAMS_ONLY) {
+ NL_SET_ERR_MSG(info->extack, "PHY only supports datagrams");
+ return -EOPNOTSUPP;
+ }
+
request = kzalloc(sizeof(*request), GFP_KERNEL);
if (!request)
return -ENOMEM;
@@ -1426,6 +1431,7 @@ static int nl802154_trigger_scan(struct sk_buff *skb, struct genl_info *info)
type = nla_get_u8(info->attrs[NL802154_ATTR_SCAN_TYPE]);
switch (type) {
+ case NL802154_SCAN_ACTIVE:
case NL802154_SCAN_PASSIVE:
request->type = type;
break;
@@ -1583,6 +1589,11 @@ nl802154_send_beacons(struct sk_buff *skb, struct genl_info *info)
return -EPERM;
}
+ if (wpan_phy->flags & WPAN_PHY_FLAG_DATAGRAMS_ONLY) {
+ NL_SET_ERR_MSG(info->extack, "PHY only supports datagrams");
+ return -EOPNOTSUPP;
+ }
+
request = kzalloc(sizeof(*request), GFP_KERNEL);
if (!request)
return -ENOMEM;
diff --git a/net/ieee802154/socket.c b/net/ieee802154/socket.c
index 1fa2fe041ec0..00302e8b9615 100644
--- a/net/ieee802154/socket.c
+++ b/net/ieee802154/socket.c
@@ -162,7 +162,7 @@ static int ieee802154_sock_ioctl(struct socket *sock, unsigned int cmd,
default:
if (!sk->sk_prot->ioctl)
return -ENOIOCTLCMD;
- return sk->sk_prot->ioctl(sk, cmd, arg);
+ return sk_ioctl(sk, cmd, (void __user *)arg);
}
}
@@ -426,7 +426,6 @@ static const struct proto_ops ieee802154_raw_ops = {
.sendmsg = ieee802154_sock_sendmsg,
.recvmsg = sock_common_recvmsg,
.mmap = sock_no_mmap,
- .sendpage = sock_no_sendpage,
};
/* DGRAM Sockets (802.15.4 dataframes) */
@@ -531,22 +530,21 @@ out:
return err;
}
-static int dgram_ioctl(struct sock *sk, int cmd, unsigned long arg)
+static int dgram_ioctl(struct sock *sk, int cmd, int *karg)
{
switch (cmd) {
case SIOCOUTQ:
{
- int amount = sk_wmem_alloc_get(sk);
+ *karg = sk_wmem_alloc_get(sk);
- return put_user(amount, (int __user *)arg);
+ return 0;
}
case SIOCINQ:
{
struct sk_buff *skb;
- unsigned long amount;
- amount = 0;
+ *karg = 0;
spin_lock_bh(&sk->sk_receive_queue.lock);
skb = skb_peek(&sk->sk_receive_queue);
if (skb) {
@@ -554,10 +552,10 @@ static int dgram_ioctl(struct sock *sk, int cmd, unsigned long arg)
* of this packet since that is all
* that will be read.
*/
- amount = skb->len - ieee802154_hdr_length(skb);
+ *karg = skb->len - ieee802154_hdr_length(skb);
}
spin_unlock_bh(&sk->sk_receive_queue.lock);
- return put_user(amount, (int __user *)arg);
+ return 0;
}
}
@@ -990,7 +988,6 @@ static const struct proto_ops ieee802154_dgram_ops = {
.sendmsg = ieee802154_sock_sendmsg,
.recvmsg = sock_common_recvmsg,
.mmap = sock_no_mmap,
- .sendpage = sock_no_sendpage,
};
static void ieee802154_sock_destruct(struct sock *sk)
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index 4a76ebf793b8..9b2ca2fcc5a1 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -100,6 +100,7 @@
#include <net/ip_fib.h>
#include <net/inet_connection_sock.h>
#include <net/gro.h>
+#include <net/gso.h>
#include <net/tcp.h>
#include <net/udp.h>
#include <net/udplite.h>
@@ -732,6 +733,20 @@ int inet_stream_connect(struct socket *sock, struct sockaddr *uaddr,
}
EXPORT_SYMBOL(inet_stream_connect);
+void __inet_accept(struct socket *sock, struct socket *newsock, struct sock *newsk)
+{
+ sock_rps_record_flow(newsk);
+ WARN_ON(!((1 << newsk->sk_state) &
+ (TCPF_ESTABLISHED | TCPF_SYN_RECV |
+ TCPF_CLOSE_WAIT | TCPF_CLOSE)));
+
+ if (test_bit(SOCK_SUPPORT_ZC, &sock->flags))
+ set_bit(SOCK_SUPPORT_ZC, &newsock->flags);
+ sock_graft(newsk, newsock);
+
+ newsock->state = SS_CONNECTED;
+}
+
/*
* Accept a pending connection. The TCP layer now gives BSD semantics.
*/
@@ -745,24 +760,12 @@ int inet_accept(struct socket *sock, struct socket *newsock, int flags,
/* IPV6_ADDRFORM can change sk->sk_prot under us. */
sk2 = READ_ONCE(sk1->sk_prot)->accept(sk1, flags, &err, kern);
if (!sk2)
- goto do_err;
+ return err;
lock_sock(sk2);
-
- sock_rps_record_flow(sk2);
- WARN_ON(!((1 << sk2->sk_state) &
- (TCPF_ESTABLISHED | TCPF_SYN_RECV |
- TCPF_CLOSE_WAIT | TCPF_CLOSE)));
-
- if (test_bit(SOCK_SUPPORT_ZC, &sock->flags))
- set_bit(SOCK_SUPPORT_ZC, &newsock->flags);
- sock_graft(sk2, newsock);
-
- newsock->state = SS_CONNECTED;
- err = 0;
+ __inet_accept(sock, newsock, sk2);
release_sock(sk2);
-do_err:
- return err;
+ return 0;
}
EXPORT_SYMBOL(inet_accept);
@@ -829,22 +832,20 @@ int inet_sendmsg(struct socket *sock, struct msghdr *msg, size_t size)
}
EXPORT_SYMBOL(inet_sendmsg);
-ssize_t inet_sendpage(struct socket *sock, struct page *page, int offset,
- size_t size, int flags)
+void inet_splice_eof(struct socket *sock)
{
- struct sock *sk = sock->sk;
const struct proto *prot;
+ struct sock *sk = sock->sk;
if (unlikely(inet_send_prepare(sk)))
- return -EAGAIN;
+ return;
/* IPV6_ADDRFORM can change sk->sk_prot under us. */
prot = READ_ONCE(sk->sk_prot);
- if (prot->sendpage)
- return prot->sendpage(sk, page, offset, size, flags);
- return sock_no_sendpage(sock, page, offset, size, flags);
+ if (prot->splice_eof)
+ prot->splice_eof(sock);
}
-EXPORT_SYMBOL(inet_sendpage);
+EXPORT_SYMBOL_GPL(inet_splice_eof);
INDIRECT_CALLABLE_DECLARE(int udp_recvmsg(struct sock *, struct msghdr *,
size_t, int, int *));
@@ -980,7 +981,7 @@ int inet_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg)
break;
default:
if (sk->sk_prot->ioctl)
- err = sk->sk_prot->ioctl(sk, cmd, arg);
+ err = sk_ioctl(sk, cmd, (void __user *)arg);
else
err = -ENOIOCTLCMD;
break;
@@ -1048,12 +1049,11 @@ const struct proto_ops inet_stream_ops = {
#ifdef CONFIG_MMU
.mmap = tcp_mmap,
#endif
- .sendpage = inet_sendpage,
+ .splice_eof = inet_splice_eof,
.splice_read = tcp_splice_read,
.read_sock = tcp_read_sock,
.read_skb = tcp_read_skb,
.sendmsg_locked = tcp_sendmsg_locked,
- .sendpage_locked = tcp_sendpage_locked,
.peek_len = tcp_peek_len,
#ifdef CONFIG_COMPAT
.compat_ioctl = inet_compat_ioctl,
@@ -1082,7 +1082,7 @@ const struct proto_ops inet_dgram_ops = {
.read_skb = udp_read_skb,
.recvmsg = inet_recvmsg,
.mmap = sock_no_mmap,
- .sendpage = inet_sendpage,
+ .splice_eof = inet_splice_eof,
.set_peek_off = sk_set_peek_off,
#ifdef CONFIG_COMPAT
.compat_ioctl = inet_compat_ioctl,
@@ -1113,7 +1113,7 @@ static const struct proto_ops inet_sockraw_ops = {
.sendmsg = inet_sendmsg,
.recvmsg = inet_recvmsg,
.mmap = sock_no_mmap,
- .sendpage = inet_sendpage,
+ .splice_eof = inet_splice_eof,
#ifdef CONFIG_COMPAT
.compat_ioctl = inet_compat_ioctl,
#endif
diff --git a/net/ipv4/bpfilter/sockopt.c b/net/ipv4/bpfilter/sockopt.c
index 1b34cb9a7708..193bcc2acccc 100644
--- a/net/ipv4/bpfilter/sockopt.c
+++ b/net/ipv4/bpfilter/sockopt.c
@@ -12,15 +12,6 @@
struct bpfilter_umh_ops bpfilter_ops;
EXPORT_SYMBOL_GPL(bpfilter_ops);
-void bpfilter_umh_cleanup(struct umd_info *info)
-{
- fput(info->pipe_to_umh);
- fput(info->pipe_from_umh);
- put_pid(info->tgid);
- info->tgid = NULL;
-}
-EXPORT_SYMBOL_GPL(bpfilter_umh_cleanup);
-
static int bpfilter_mbox_request(struct sock *sk, int optname, sockptr_t optval,
unsigned int optlen, bool is_set)
{
@@ -38,7 +29,7 @@ static int bpfilter_mbox_request(struct sock *sk, int optname, sockptr_t optval,
}
if (bpfilter_ops.info.tgid &&
thread_group_exited(bpfilter_ops.info.tgid))
- bpfilter_umh_cleanup(&bpfilter_ops.info);
+ umd_cleanup_helper(&bpfilter_ops.info);
if (!bpfilter_ops.info.tgid) {
err = bpfilter_ops.start();
diff --git a/net/ipv4/esp4_offload.c b/net/ipv4/esp4_offload.c
index ee848be59e65..10e96ed6c9e3 100644
--- a/net/ipv4/esp4_offload.c
+++ b/net/ipv4/esp4_offload.c
@@ -17,6 +17,7 @@
#include <linux/err.h>
#include <linux/module.h>
#include <net/gro.h>
+#include <net/gso.h>
#include <net/ip.h>
#include <net/xfrm.h>
#include <net/esp.h>
diff --git a/net/ipv4/fou_nl.c b/net/ipv4/fou_nl.c
index 6c37c4f98cca..98b90107b5ab 100644
--- a/net/ipv4/fou_nl.c
+++ b/net/ipv4/fou_nl.c
@@ -8,7 +8,7 @@
#include "fou_nl.h"
-#include <linux/fou.h>
+#include <uapi/linux/fou.h>
/* Global operation policy for fou */
const struct nla_policy fou_nl_policy[FOU_ATTR_IFINDEX + 1] = {
diff --git a/net/ipv4/fou_nl.h b/net/ipv4/fou_nl.h
index dbd0780a5d34..63a6c4ed803d 100644
--- a/net/ipv4/fou_nl.h
+++ b/net/ipv4/fou_nl.h
@@ -9,7 +9,7 @@
#include <net/netlink.h>
#include <net/genetlink.h>
-#include <linux/fou.h>
+#include <uapi/linux/fou.h>
/* Global operation policy for fou */
extern const struct nla_policy fou_nl_policy[FOU_ATTR_IFINDEX + 1];
diff --git a/net/ipv4/gre_offload.c b/net/ipv4/gre_offload.c
index 2b9cb5398335..311e70bfce40 100644
--- a/net/ipv4/gre_offload.c
+++ b/net/ipv4/gre_offload.c
@@ -11,6 +11,7 @@
#include <net/protocol.h>
#include <net/gre.h>
#include <net/gro.h>
+#include <net/gso.h>
static struct sk_buff *gre_gso_segment(struct sk_buff *skb,
netdev_features_t features)
diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index 1386787eaf1a..0cc19cfbb673 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -706,20 +706,23 @@ struct sock *inet_csk_accept(struct sock *sk, int flags, int *err, bool kern)
out:
release_sock(sk);
if (newsk && mem_cgroup_sockets_enabled) {
- int amt;
+ int amt = 0;
/* atomically get the memory usage, set and charge the
* newsk->sk_memcg.
*/
lock_sock(newsk);
- /* The socket has not been accepted yet, no need to look at
- * newsk->sk_wmem_queued.
- */
- amt = sk_mem_pages(newsk->sk_forward_alloc +
- atomic_read(&newsk->sk_rmem_alloc));
mem_cgroup_sk_alloc(newsk);
- if (newsk->sk_memcg && amt)
+ if (newsk->sk_memcg) {
+ /* The socket has not been accepted yet, no need
+ * to look at newsk->sk_wmem_queued.
+ */
+ amt = sk_mem_pages(newsk->sk_forward_alloc +
+ atomic_read(&newsk->sk_rmem_alloc));
+ }
+
+ if (amt)
mem_cgroup_charge_skmem(newsk->sk_memcg, amt,
GFP_KERNEL | __GFP_NOFAIL);
@@ -792,7 +795,7 @@ struct dst_entry *inet_csk_route_req(const struct sock *sk,
opt = rcu_dereference(ireq->ireq_opt);
flowi4_init_output(fl4, ireq->ir_iif, ireq->ir_mark,
- RT_CONN_FLAGS(sk), RT_SCOPE_UNIVERSE,
+ ip_sock_rt_tos(sk), ip_sock_rt_scope(sk),
sk->sk_protocol, inet_sk_flowi_flags(sk),
(opt && opt->opt.srr) ? opt->opt.faddr : ireq->ir_rmt_addr,
ireq->ir_loc_addr, ireq->ir_rmt_port,
@@ -830,7 +833,7 @@ struct dst_entry *inet_csk_route_child_sock(const struct sock *sk,
fl4 = &newinet->cork.fl.u.ip4;
flowi4_init_output(fl4, ireq->ir_iif, ireq->ir_mark,
- RT_CONN_FLAGS(sk), RT_SCOPE_UNIVERSE,
+ ip_sock_rt_tos(sk), ip_sock_rt_scope(sk),
sk->sk_protocol, inet_sk_flowi_flags(sk),
(opt && opt->opt.srr) ? opt->opt.faddr : ireq->ir_rmt_addr,
ireq->ir_loc_addr, ireq->ir_rmt_port,
diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c
index e55a20264960..81a1cce1a7d1 100644
--- a/net/ipv4/ip_gre.c
+++ b/net/ipv4/ip_gre.c
@@ -189,10 +189,10 @@ static int ipgre_err(struct sk_buff *skb, u32 info,
}
#if IS_ENABLED(CONFIG_IPV6)
- if (tpi->proto == htons(ETH_P_IPV6) &&
- !ip6_err_gen_icmpv6_unreach(skb, iph->ihl * 4 + tpi->hdr_len,
- type, data_len))
- return 0;
+ if (tpi->proto == htons(ETH_P_IPV6) &&
+ !ip6_err_gen_icmpv6_unreach(skb, iph->ihl * 4 + tpi->hdr_len,
+ type, data_len))
+ return 0;
#endif
if (t->parms.iph.daddr == 0 ||
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index 61892268e8a6..6e70839257f7 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -73,6 +73,7 @@
#include <net/arp.h>
#include <net/icmp.h>
#include <net/checksum.h>
+#include <net/gso.h>
#include <net/inetpeer.h>
#include <net/inet_ecn.h>
#include <net/lwtunnel.h>
@@ -946,17 +947,6 @@ ip_generic_getfrag(void *from, char *to, int offset, int len, int odd, struct sk
}
EXPORT_SYMBOL(ip_generic_getfrag);
-static inline __wsum
-csum_page(struct page *page, int offset, int copy)
-{
- char *kaddr;
- __wsum csum;
- kaddr = kmap(page);
- csum = csum_partial(kaddr + offset, copy, 0);
- kunmap(page);
- return csum;
-}
-
static int __ip_append_data(struct sock *sk,
struct flowi4 *fl4,
struct sk_buff_head *queue,
@@ -1048,6 +1038,15 @@ static int __ip_append_data(struct sock *sk,
skb_zcopy_set(skb, uarg, &extra_uref);
}
}
+ } else if ((flags & MSG_SPLICE_PAGES) && length) {
+ if (inet->hdrincl)
+ return -EPERM;
+ if (rt->dst.dev->features & NETIF_F_SG &&
+ getfrag == ip_generic_getfrag)
+ /* We need an empty buffer to attach stuff to */
+ paged = true;
+ else
+ flags &= ~MSG_SPLICE_PAGES;
}
cork->length += length;
@@ -1207,6 +1206,15 @@ alloc_new_skb:
err = -EFAULT;
goto error;
}
+ } else if (flags & MSG_SPLICE_PAGES) {
+ struct msghdr *msg = from;
+
+ err = skb_splice_from_iter(skb, &msg->msg_iter, copy,
+ sk->sk_allocation);
+ if (err < 0)
+ goto error;
+ copy = err;
+ wmem_alloc_delta += copy;
} else if (!zc) {
int i = skb_shinfo(skb)->nr_frags;
@@ -1310,10 +1318,10 @@ static int ip_setup_cork(struct sock *sk, struct inet_cork *cork,
}
/*
- * ip_append_data() and ip_append_page() can make one large IP datagram
- * from many pieces of data. Each pieces will be holded on the socket
- * until ip_push_pending_frames() is called. Each piece can be a page
- * or non-page data.
+ * ip_append_data() can make one large IP datagram from many pieces of
+ * data. Each piece will be held on the socket until
+ * ip_push_pending_frames() is called. Each piece can be a page or
+ * non-page data.
*
* Not only UDP, other transport protocols - e.g. raw sockets - can use
* this interface potentially.
@@ -1346,134 +1354,6 @@ int ip_append_data(struct sock *sk, struct flowi4 *fl4,
from, length, transhdrlen, flags);
}
-ssize_t ip_append_page(struct sock *sk, struct flowi4 *fl4, struct page *page,
- int offset, size_t size, int flags)
-{
- struct inet_sock *inet = inet_sk(sk);
- struct sk_buff *skb;
- struct rtable *rt;
- struct ip_options *opt = NULL;
- struct inet_cork *cork;
- int hh_len;
- int mtu;
- int len;
- int err;
- unsigned int maxfraglen, fragheaderlen, fraggap, maxnonfragsize;
-
- if (inet->hdrincl)
- return -EPERM;
-
- if (flags&MSG_PROBE)
- return 0;
-
- if (skb_queue_empty(&sk->sk_write_queue))
- return -EINVAL;
-
- cork = &inet->cork.base;
- rt = (struct rtable *)cork->dst;
- if (cork->flags & IPCORK_OPT)
- opt = cork->opt;
-
- if (!(rt->dst.dev->features & NETIF_F_SG))
- return -EOPNOTSUPP;
-
- hh_len = LL_RESERVED_SPACE(rt->dst.dev);
- mtu = cork->gso_size ? IP_MAX_MTU : cork->fragsize;
-
- fragheaderlen = sizeof(struct iphdr) + (opt ? opt->optlen : 0);
- maxfraglen = ((mtu - fragheaderlen) & ~7) + fragheaderlen;
- maxnonfragsize = ip_sk_ignore_df(sk) ? 0xFFFF : mtu;
-
- if (cork->length + size > maxnonfragsize - fragheaderlen) {
- ip_local_error(sk, EMSGSIZE, fl4->daddr, inet->inet_dport,
- mtu - (opt ? opt->optlen : 0));
- return -EMSGSIZE;
- }
-
- skb = skb_peek_tail(&sk->sk_write_queue);
- if (!skb)
- return -EINVAL;
-
- cork->length += size;
-
- while (size > 0) {
- /* Check if the remaining data fits into current packet. */
- len = mtu - skb->len;
- if (len < size)
- len = maxfraglen - skb->len;
-
- if (len <= 0) {
- struct sk_buff *skb_prev;
- int alloclen;
-
- skb_prev = skb;
- fraggap = skb_prev->len - maxfraglen;
-
- alloclen = fragheaderlen + hh_len + fraggap + 15;
- skb = sock_wmalloc(sk, alloclen, 1, sk->sk_allocation);
- if (unlikely(!skb)) {
- err = -ENOBUFS;
- goto error;
- }
-
- /*
- * Fill in the control structures
- */
- skb->ip_summed = CHECKSUM_NONE;
- skb->csum = 0;
- skb_reserve(skb, hh_len);
-
- /*
- * Find where to start putting bytes.
- */
- skb_put(skb, fragheaderlen + fraggap);
- skb_reset_network_header(skb);
- skb->transport_header = (skb->network_header +
- fragheaderlen);
- if (fraggap) {
- skb->csum = skb_copy_and_csum_bits(skb_prev,
- maxfraglen,
- skb_transport_header(skb),
- fraggap);
- skb_prev->csum = csum_sub(skb_prev->csum,
- skb->csum);
- pskb_trim_unique(skb_prev, maxfraglen);
- }
-
- /*
- * Put the packet on the pending queue.
- */
- __skb_queue_tail(&sk->sk_write_queue, skb);
- continue;
- }
-
- if (len > size)
- len = size;
-
- if (skb_append_pagefrags(skb, page, offset, len)) {
- err = -EMSGSIZE;
- goto error;
- }
-
- if (skb->ip_summed == CHECKSUM_NONE) {
- __wsum csum;
- csum = csum_page(page, offset, len);
- skb->csum = csum_block_add(skb->csum, csum, skb->len);
- }
-
- skb_len_add(skb, len);
- refcount_add(len, &sk->sk_wmem_alloc);
- offset += len;
- size -= len;
- }
- return 0;
-
-error:
- cork->length -= size;
- IP_INC_STATS(sock_net(sk), IPSTATS_MIB_OUTDISCARDS);
- return err;
-}
-
static void ip_cork_release(struct inet_cork *cork)
{
cork->flags &= ~IPCORK_OPT;
@@ -1692,7 +1572,7 @@ void ip_send_unicast_reply(struct sock *sk, struct sk_buff *skb,
const struct ip_options *sopt,
__be32 daddr, __be32 saddr,
const struct ip_reply_arg *arg,
- unsigned int len, u64 transmit_time)
+ unsigned int len, u64 transmit_time, u32 txhash)
{
struct ip_options_data replyopts;
struct ipcm_cookie ipc;
@@ -1755,6 +1635,8 @@ void ip_send_unicast_reply(struct sock *sk, struct sk_buff *skb,
arg->csum));
nskb->ip_summed = CHECKSUM_NONE;
nskb->mono_delivery_time = !!transmit_time;
+ if (txhash)
+ skb_set_hash(nskb, txhash, PKT_HASH_TYPE_L4);
ip_push_pending_frames(sk, &fl4);
}
out:
diff --git a/net/ipv4/ipconfig.c b/net/ipv4/ipconfig.c
index e90bc0aa85c7..c56b6fe6f0d7 100644
--- a/net/ipv4/ipconfig.c
+++ b/net/ipv4/ipconfig.c
@@ -665,6 +665,9 @@ static struct packet_type bootp_packet_type __initdata = {
.func = ic_bootp_recv,
};
+/* DHCPACK can overwrite DNS if fallback was set upon first BOOTP reply */
+static int ic_nameservers_fallback __initdata;
+
/*
* Initialize DHCP/BOOTP extension fields in the request.
*/
@@ -938,7 +941,8 @@ static void __init ic_do_bootp_ext(u8 *ext)
if (servers > CONF_NAMESERVERS_MAX)
servers = CONF_NAMESERVERS_MAX;
for (i = 0; i < servers; i++) {
- if (ic_nameservers[i] == NONE)
+ if (ic_nameservers[i] == NONE ||
+ ic_nameservers_fallback)
memcpy(&ic_nameservers[i], ext+1+4*i, 4);
}
break;
@@ -1158,8 +1162,10 @@ static int __init ic_bootp_recv(struct sk_buff *skb, struct net_device *dev, str
ic_addrservaddr = b->iph.saddr;
if (ic_gateway == NONE && b->relay_ip)
ic_gateway = b->relay_ip;
- if (ic_nameservers[0] == NONE)
+ if (ic_nameservers[0] == NONE) {
ic_nameservers[0] = ic_servaddr;
+ ic_nameservers_fallback = 1;
+ }
ic_got_reply = IC_BOOTP;
drop_unlock:
diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c
index eec1f6df80d8..3f0c6d602fb7 100644
--- a/net/ipv4/ipmr.c
+++ b/net/ipv4/ipmr.c
@@ -1547,6 +1547,28 @@ out:
return ret;
}
+/* Execute if this ioctl is a special mroute ioctl */
+int ipmr_sk_ioctl(struct sock *sk, unsigned int cmd, void __user *arg)
+{
+ switch (cmd) {
+ /* These userspace buffers will be consumed by ipmr_ioctl() */
+ case SIOCGETVIFCNT: {
+ struct sioc_vif_req buffer;
+
+ return sock_ioctl_inout(sk, cmd, arg, &buffer,
+ sizeof(buffer));
+ }
+ case SIOCGETSGCNT: {
+ struct sioc_sg_req buffer;
+
+ return sock_ioctl_inout(sk, cmd, arg, &buffer,
+ sizeof(buffer));
+ }
+ }
+ /* return code > 0 means that the ioctl was not executed */
+ return 1;
+}
+
/* Getsock opt support for the multicast routing system. */
int ip_mroute_getsockopt(struct sock *sk, int optname, sockptr_t optval,
sockptr_t optlen)
@@ -1593,13 +1615,13 @@ int ip_mroute_getsockopt(struct sock *sk, int optname, sockptr_t optval,
}
/* The IP multicast ioctl support routines. */
-int ipmr_ioctl(struct sock *sk, int cmd, void __user *arg)
+int ipmr_ioctl(struct sock *sk, int cmd, void *arg)
{
- struct sioc_sg_req sr;
- struct sioc_vif_req vr;
struct vif_device *vif;
struct mfc_cache *c;
struct net *net = sock_net(sk);
+ struct sioc_vif_req *vr;
+ struct sioc_sg_req *sr;
struct mr_table *mrt;
mrt = ipmr_get_table(net, raw_sk(sk)->ipmr_table ? : RT_TABLE_DEFAULT);
@@ -1608,40 +1630,33 @@ int ipmr_ioctl(struct sock *sk, int cmd, void __user *arg)
switch (cmd) {
case SIOCGETVIFCNT:
- if (copy_from_user(&vr, arg, sizeof(vr)))
- return -EFAULT;
- if (vr.vifi >= mrt->maxvif)
+ vr = (struct sioc_vif_req *)arg;
+ if (vr->vifi >= mrt->maxvif)
return -EINVAL;
- vr.vifi = array_index_nospec(vr.vifi, mrt->maxvif);
+ vr->vifi = array_index_nospec(vr->vifi, mrt->maxvif);
rcu_read_lock();
- vif = &mrt->vif_table[vr.vifi];
- if (VIF_EXISTS(mrt, vr.vifi)) {
- vr.icount = READ_ONCE(vif->pkt_in);
- vr.ocount = READ_ONCE(vif->pkt_out);
- vr.ibytes = READ_ONCE(vif->bytes_in);
- vr.obytes = READ_ONCE(vif->bytes_out);
+ vif = &mrt->vif_table[vr->vifi];
+ if (VIF_EXISTS(mrt, vr->vifi)) {
+ vr->icount = READ_ONCE(vif->pkt_in);
+ vr->ocount = READ_ONCE(vif->pkt_out);
+ vr->ibytes = READ_ONCE(vif->bytes_in);
+ vr->obytes = READ_ONCE(vif->bytes_out);
rcu_read_unlock();
- if (copy_to_user(arg, &vr, sizeof(vr)))
- return -EFAULT;
return 0;
}
rcu_read_unlock();
return -EADDRNOTAVAIL;
case SIOCGETSGCNT:
- if (copy_from_user(&sr, arg, sizeof(sr)))
- return -EFAULT;
+ sr = (struct sioc_sg_req *)arg;
rcu_read_lock();
- c = ipmr_cache_find(mrt, sr.src.s_addr, sr.grp.s_addr);
+ c = ipmr_cache_find(mrt, sr->src.s_addr, sr->grp.s_addr);
if (c) {
- sr.pktcnt = c->_c.mfc_un.res.pkt;
- sr.bytecnt = c->_c.mfc_un.res.bytes;
- sr.wrong_if = c->_c.mfc_un.res.wrong_if;
+ sr->pktcnt = c->_c.mfc_un.res.pkt;
+ sr->bytecnt = c->_c.mfc_un.res.bytes;
+ sr->wrong_if = c->_c.mfc_un.res.wrong_if;
rcu_read_unlock();
-
- if (copy_to_user(arg, &sr, sizeof(sr)))
- return -EFAULT;
return 0;
}
rcu_read_unlock();
diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c
index 5178a3f3cb53..25dd78cee179 100644
--- a/net/ipv4/ping.c
+++ b/net/ipv4/ping.c
@@ -49,13 +49,8 @@
#include <net/transp_v6.h>
#endif
-#define ping_portaddr_for_each_entry(__sk, node, list) \
- hlist_nulls_for_each_entry(__sk, node, list, sk_nulls_node)
-#define ping_portaddr_for_each_entry_rcu(__sk, node, list) \
- hlist_nulls_for_each_entry_rcu(__sk, node, list, sk_nulls_node)
-
struct ping_table {
- struct hlist_nulls_head hash[PING_HTABLE_SIZE];
+ struct hlist_head hash[PING_HTABLE_SIZE];
spinlock_t lock;
};
@@ -74,17 +69,16 @@ static inline u32 ping_hashfn(const struct net *net, u32 num, u32 mask)
}
EXPORT_SYMBOL_GPL(ping_hash);
-static inline struct hlist_nulls_head *ping_hashslot(struct ping_table *table,
- struct net *net, unsigned int num)
+static inline struct hlist_head *ping_hashslot(struct ping_table *table,
+ struct net *net, unsigned int num)
{
return &table->hash[ping_hashfn(net, num, PING_HTABLE_MASK)];
}
int ping_get_port(struct sock *sk, unsigned short ident)
{
- struct hlist_nulls_node *node;
- struct hlist_nulls_head *hlist;
struct inet_sock *isk, *isk2;
+ struct hlist_head *hlist;
struct sock *sk2 = NULL;
isk = inet_sk(sk);
@@ -98,7 +92,7 @@ int ping_get_port(struct sock *sk, unsigned short ident)
result++; /* avoid zero */
hlist = ping_hashslot(&ping_table, sock_net(sk),
result);
- ping_portaddr_for_each_entry(sk2, node, hlist) {
+ sk_for_each(sk2, hlist) {
isk2 = inet_sk(sk2);
if (isk2->inet_num == result)
@@ -115,7 +109,7 @@ next_port:
goto fail;
} else {
hlist = ping_hashslot(&ping_table, sock_net(sk), ident);
- ping_portaddr_for_each_entry(sk2, node, hlist) {
+ sk_for_each(sk2, hlist) {
isk2 = inet_sk(sk2);
/* BUG? Why is this reuse and not reuseaddr? ping.c
@@ -133,9 +127,8 @@ next_port:
isk->inet_num = ident;
if (sk_unhashed(sk)) {
pr_debug("was not hashed\n");
- sock_hold(sk);
+ sk_add_node_rcu(sk, hlist);
sock_set_flag(sk, SOCK_RCU_FREE);
- hlist_nulls_add_head_rcu(&sk->sk_nulls_node, hlist);
sock_prot_inuse_add(sock_net(sk), sk->sk_prot, 1);
}
spin_unlock(&ping_table.lock);
@@ -161,9 +154,7 @@ void ping_unhash(struct sock *sk)
pr_debug("ping_unhash(isk=%p,isk->num=%u)\n", isk, isk->inet_num);
spin_lock(&ping_table.lock);
- if (sk_hashed(sk)) {
- hlist_nulls_del_init_rcu(&sk->sk_nulls_node);
- sock_put(sk);
+ if (sk_del_node_init_rcu(sk)) {
isk->inet_num = 0;
isk->inet_sport = 0;
sock_prot_inuse_add(sock_net(sk), sk->sk_prot, -1);
@@ -175,10 +166,9 @@ EXPORT_SYMBOL_GPL(ping_unhash);
/* Called under rcu_read_lock() */
static struct sock *ping_lookup(struct net *net, struct sk_buff *skb, u16 ident)
{
- struct hlist_nulls_head *hslot = ping_hashslot(&ping_table, net, ident);
+ struct hlist_head *hslot = ping_hashslot(&ping_table, net, ident);
struct sock *sk = NULL;
struct inet_sock *isk;
- struct hlist_nulls_node *hnode;
int dif, sdif;
if (skb->protocol == htons(ETH_P_IP)) {
@@ -197,7 +187,7 @@ static struct sock *ping_lookup(struct net *net, struct sk_buff *skb, u16 ident)
return NULL;
}
- ping_portaddr_for_each_entry_rcu(sk, hnode, hslot) {
+ sk_for_each_rcu(sk, hslot) {
isk = inet_sk(sk);
pr_debug("iterate\n");
@@ -715,7 +705,7 @@ static int ping_v4_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
struct ip_options_data opt_copy;
int free = 0;
__be32 saddr, daddr, faddr;
- u8 tos;
+ u8 tos, scope;
int err;
pr_debug("ping_v4_sendmsg(sk=%p,sk->num=%u)\n", inet, inet->inet_num);
@@ -779,11 +769,7 @@ static int ping_v4_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
faddr = ipc.opt->opt.faddr;
}
tos = get_rttos(&ipc, inet);
- if (sock_flag(sk, SOCK_LOCALROUTE) ||
- (msg->msg_flags & MSG_DONTROUTE) ||
- (ipc.opt && ipc.opt->opt.is_strictroute)) {
- tos |= RTO_ONLINK;
- }
+ scope = ip_sendmsg_scope(inet, &ipc, msg);
if (ipv4_is_multicast(daddr)) {
if (!ipc.oif || netif_index_is_l3_master(sock_net(sk), ipc.oif))
@@ -793,10 +779,9 @@ static int ping_v4_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
} else if (!ipc.oif)
ipc.oif = inet->uc_index;
- flowi4_init_output(&fl4, ipc.oif, ipc.sockc.mark, tos,
- RT_SCOPE_UNIVERSE, sk->sk_protocol,
- inet_sk_flowi_flags(sk), faddr, saddr, 0, 0,
- sk->sk_uid);
+ flowi4_init_output(&fl4, ipc.oif, ipc.sockc.mark, tos, scope,
+ sk->sk_protocol, inet_sk_flowi_flags(sk), faddr,
+ saddr, 0, 0, sk->sk_uid);
fl4.fl4_icmp_type = user_icmph.type;
fl4.fl4_icmp_code = user_icmph.code;
@@ -1045,15 +1030,14 @@ static struct sock *ping_get_first(struct seq_file *seq, int start)
for (state->bucket = start; state->bucket < PING_HTABLE_SIZE;
++state->bucket) {
- struct hlist_nulls_node *node;
- struct hlist_nulls_head *hslot;
+ struct hlist_head *hslot;
hslot = &ping_table.hash[state->bucket];
- if (hlist_nulls_empty(hslot))
+ if (hlist_empty(hslot))
continue;
- sk_nulls_for_each(sk, node, hslot) {
+ sk_for_each(sk, hslot) {
if (net_eq(sock_net(sk), net) &&
sk->sk_family == state->family)
goto found;
@@ -1070,7 +1054,7 @@ static struct sock *ping_get_next(struct seq_file *seq, struct sock *sk)
struct net *net = seq_file_net(seq);
do {
- sk = sk_nulls_next(sk);
+ sk = sk_next(sk);
} while (sk && (!net_eq(sock_net(sk), net)));
if (!sk)
@@ -1206,6 +1190,6 @@ void __init ping_init(void)
int i;
for (i = 0; i < PING_HTABLE_SIZE; i++)
- INIT_HLIST_NULLS_HEAD(&ping_table.hash[i], i);
+ INIT_HLIST_HEAD(&ping_table.hash[i]);
spin_lock_init(&ping_table.lock);
}
diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c
index eadf1c9ef7e4..7782ff5e6539 100644
--- a/net/ipv4/raw.c
+++ b/net/ipv4/raw.c
@@ -476,10 +476,10 @@ static int raw_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
struct ipcm_cookie ipc;
struct rtable *rt = NULL;
struct flowi4 fl4;
+ u8 tos, scope;
int free = 0;
__be32 daddr;
__be32 saddr;
- u8 tos;
int err;
struct ip_options_data opt_copy;
struct raw_frag_vec rfv;
@@ -575,9 +575,8 @@ static int raw_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
daddr = ipc.opt->opt.faddr;
}
}
- tos = get_rtconn_flags(&ipc, sk);
- if (msg->msg_flags & MSG_DONTROUTE)
- tos |= RTO_ONLINK;
+ tos = get_rttos(&ipc, inet);
+ scope = ip_sendmsg_scope(inet, &ipc, msg);
if (ipv4_is_multicast(daddr)) {
if (!ipc.oif || netif_index_is_l3_master(sock_net(sk), ipc.oif))
@@ -600,8 +599,7 @@ static int raw_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
}
}
- flowi4_init_output(&fl4, ipc.oif, ipc.sockc.mark, tos,
- RT_SCOPE_UNIVERSE,
+ flowi4_init_output(&fl4, ipc.oif, ipc.sockc.mark, tos, scope,
hdrincl ? ipc.protocol : sk->sk_protocol,
inet_sk_flowi_flags(sk) |
(hdrincl ? FLOWI_FLAG_KNOWN_NH : 0),
@@ -858,29 +856,29 @@ static int raw_getsockopt(struct sock *sk, int level, int optname,
return do_raw_getsockopt(sk, level, optname, optval, optlen);
}
-static int raw_ioctl(struct sock *sk, int cmd, unsigned long arg)
+static int raw_ioctl(struct sock *sk, int cmd, int *karg)
{
switch (cmd) {
case SIOCOUTQ: {
- int amount = sk_wmem_alloc_get(sk);
-
- return put_user(amount, (int __user *)arg);
+ *karg = sk_wmem_alloc_get(sk);
+ return 0;
}
case SIOCINQ: {
struct sk_buff *skb;
- int amount = 0;
spin_lock_bh(&sk->sk_receive_queue.lock);
skb = skb_peek(&sk->sk_receive_queue);
if (skb)
- amount = skb->len;
+ *karg = skb->len;
+ else
+ *karg = 0;
spin_unlock_bh(&sk->sk_receive_queue.lock);
- return put_user(amount, (int __user *)arg);
+ return 0;
}
default:
#ifdef CONFIG_IP_MROUTE
- return ipmr_ioctl(sk, cmd, (void __user *)arg);
+ return ipmr_ioctl(sk, cmd, karg);
#else
return -ENOIOCTLCMD;
#endif
diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c
index 26fb97d1d4d9..dc478a0574cb 100644
--- a/net/ipv4/syncookies.c
+++ b/net/ipv4/syncookies.c
@@ -418,8 +418,8 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb)
* no easy way to do this.
*/
flowi4_init_output(&fl4, ireq->ir_iif, ireq->ir_mark,
- RT_CONN_FLAGS(sk), RT_SCOPE_UNIVERSE, IPPROTO_TCP,
- inet_sk_flowi_flags(sk),
+ ip_sock_rt_tos(sk), ip_sock_rt_scope(sk),
+ IPPROTO_TCP, inet_sk_flowi_flags(sk),
opt->srr ? opt->faddr : ireq->ir_rmt_addr,
ireq->ir_loc_addr, th->source, th->dest, sk->sk_uid);
security_req_classify_flow(req, flowi4_to_flowi_common(&fl4));
diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c
index 88dfe51e68f3..2afb0870648b 100644
--- a/net/ipv4/sysctl_net_ipv4.c
+++ b/net/ipv4/sysctl_net_ipv4.c
@@ -34,6 +34,7 @@ static int ip_ttl_min = 1;
static int ip_ttl_max = 255;
static int tcp_syn_retries_min = 1;
static int tcp_syn_retries_max = MAX_TCP_SYNCNT;
+static int tcp_syn_linear_timeouts_max = MAX_TCP_SYNCNT;
static unsigned long ip_ping_group_range_min[] = { 0, 0 };
static unsigned long ip_ping_group_range_max[] = { GID_T_MAX, GID_T_MAX };
static u32 u32_max_div_HZ = UINT_MAX / HZ;
@@ -1470,6 +1471,24 @@ static struct ctl_table ipv4_net_table[] = {
.extra1 = SYSCTL_ZERO,
.extra2 = &tcp_plb_max_cong_thresh,
},
+ {
+ .procname = "tcp_syn_linear_timeouts",
+ .data = &init_net.ipv4.sysctl_tcp_syn_linear_timeouts,
+ .maxlen = sizeof(u8),
+ .mode = 0644,
+ .proc_handler = proc_dou8vec_minmax,
+ .extra1 = SYSCTL_ZERO,
+ .extra2 = &tcp_syn_linear_timeouts_max,
+ },
+ {
+ .procname = "tcp_shrink_window",
+ .data = &init_net.ipv4.sysctl_tcp_shrink_window,
+ .maxlen = sizeof(u8),
+ .mode = 0644,
+ .proc_handler = proc_dou8vec_minmax,
+ .extra1 = SYSCTL_ZERO,
+ .extra2 = SYSCTL_ONE,
+ },
{ }
};
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 8d20d9221238..e03e08745308 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -599,7 +599,7 @@ __poll_t tcp_poll(struct file *file, struct socket *sock, poll_table *wait)
}
EXPORT_SYMBOL(tcp_poll);
-int tcp_ioctl(struct sock *sk, int cmd, unsigned long arg)
+int tcp_ioctl(struct sock *sk, int cmd, int *karg)
{
struct tcp_sock *tp = tcp_sk(sk);
int answ;
@@ -641,7 +641,8 @@ int tcp_ioctl(struct sock *sk, int cmd, unsigned long arg)
return -ENOIOCTLCMD;
}
- return put_user(answ, (int __user *)arg);
+ *karg = answ;
+ return 0;
}
EXPORT_SYMBOL(tcp_ioctl);
@@ -838,7 +839,7 @@ ssize_t tcp_splice_read(struct socket *sock, loff_t *ppos,
tss.len -= ret;
spliced += ret;
- if (!timeo)
+ if (!tss.len || !timeo)
break;
release_sock(sk);
lock_sock(sk);
@@ -858,12 +859,12 @@ ssize_t tcp_splice_read(struct socket *sock, loff_t *ppos,
}
EXPORT_SYMBOL(tcp_splice_read);
-struct sk_buff *tcp_stream_alloc_skb(struct sock *sk, int size, gfp_t gfp,
+struct sk_buff *tcp_stream_alloc_skb(struct sock *sk, gfp_t gfp,
bool force_schedule)
{
struct sk_buff *skb;
- skb = alloc_skb_fclone(size + MAX_TCP_HEADER, gfp);
+ skb = alloc_skb_fclone(MAX_TCP_HEADER, gfp);
if (likely(skb)) {
bool mem_scheduled;
@@ -922,11 +923,10 @@ int tcp_send_mss(struct sock *sk, int *size_goal, int flags)
return mss_now;
}
-/* In some cases, both sendpage() and sendmsg() could have added
- * an skb to the write queue, but failed adding payload on it.
- * We need to remove it to consume less memory, but more
- * importantly be able to generate EPOLLOUT for Edge Trigger epoll()
- * users.
+/* In some cases, both sendmsg() could have added an skb to the write queue,
+ * but failed adding payload on it. We need to remove it to consume less
+ * memory, but more importantly be able to generate EPOLLOUT for Edge Trigger
+ * epoll() users.
*/
void tcp_remove_empty_skb(struct sock *sk)
{
@@ -957,7 +957,7 @@ static int tcp_downgrade_zcopy_pure(struct sock *sk, struct sk_buff *skb)
}
-static int tcp_wmem_schedule(struct sock *sk, int copy)
+int tcp_wmem_schedule(struct sock *sk, int copy)
{
int left;
@@ -974,191 +974,6 @@ static int tcp_wmem_schedule(struct sock *sk, int copy)
return min(copy, sk->sk_forward_alloc);
}
-static struct sk_buff *tcp_build_frag(struct sock *sk, int size_goal, int flags,
- struct page *page, int offset, size_t *size)
-{
- struct sk_buff *skb = tcp_write_queue_tail(sk);
- struct tcp_sock *tp = tcp_sk(sk);
- bool can_coalesce;
- int copy, i;
-
- if (!skb || (copy = size_goal - skb->len) <= 0 ||
- !tcp_skb_can_collapse_to(skb)) {
-new_segment:
- if (!sk_stream_memory_free(sk))
- return NULL;
-
- skb = tcp_stream_alloc_skb(sk, 0, sk->sk_allocation,
- tcp_rtx_and_write_queues_empty(sk));
- if (!skb)
- return NULL;
-
-#ifdef CONFIG_TLS_DEVICE
- skb->decrypted = !!(flags & MSG_SENDPAGE_DECRYPTED);
-#endif
- tcp_skb_entail(sk, skb);
- copy = size_goal;
- }
-
- if (copy > *size)
- copy = *size;
-
- i = skb_shinfo(skb)->nr_frags;
- can_coalesce = skb_can_coalesce(skb, i, page, offset);
- if (!can_coalesce && i >= READ_ONCE(sysctl_max_skb_frags)) {
- tcp_mark_push(tp, skb);
- goto new_segment;
- }
- if (tcp_downgrade_zcopy_pure(sk, skb))
- return NULL;
-
- copy = tcp_wmem_schedule(sk, copy);
- if (!copy)
- return NULL;
-
- if (can_coalesce) {
- skb_frag_size_add(&skb_shinfo(skb)->frags[i - 1], copy);
- } else {
- get_page(page);
- skb_fill_page_desc_noacc(skb, i, page, offset, copy);
- }
-
- if (!(flags & MSG_NO_SHARED_FRAGS))
- skb_shinfo(skb)->flags |= SKBFL_SHARED_FRAG;
-
- skb->len += copy;
- skb->data_len += copy;
- skb->truesize += copy;
- sk_wmem_queued_add(sk, copy);
- sk_mem_charge(sk, copy);
- WRITE_ONCE(tp->write_seq, tp->write_seq + copy);
- TCP_SKB_CB(skb)->end_seq += copy;
- tcp_skb_pcount_set(skb, 0);
-
- *size = copy;
- return skb;
-}
-
-ssize_t do_tcp_sendpages(struct sock *sk, struct page *page, int offset,
- size_t size, int flags)
-{
- struct tcp_sock *tp = tcp_sk(sk);
- int mss_now, size_goal;
- int err;
- ssize_t copied;
- long timeo = sock_sndtimeo(sk, flags & MSG_DONTWAIT);
-
- if (IS_ENABLED(CONFIG_DEBUG_VM) &&
- WARN_ONCE(!sendpage_ok(page),
- "page must not be a Slab one and have page_count > 0"))
- return -EINVAL;
-
- /* Wait for a connection to finish. One exception is TCP Fast Open
- * (passive side) where data is allowed to be sent before a connection
- * is fully established.
- */
- if (((1 << sk->sk_state) & ~(TCPF_ESTABLISHED | TCPF_CLOSE_WAIT)) &&
- !tcp_passive_fastopen(sk)) {
- err = sk_stream_wait_connect(sk, &timeo);
- if (err != 0)
- goto out_err;
- }
-
- sk_clear_bit(SOCKWQ_ASYNC_NOSPACE, sk);
-
- mss_now = tcp_send_mss(sk, &size_goal, flags);
- copied = 0;
-
- err = -EPIPE;
- if (sk->sk_err || (sk->sk_shutdown & SEND_SHUTDOWN))
- goto out_err;
-
- while (size > 0) {
- struct sk_buff *skb;
- size_t copy = size;
-
- skb = tcp_build_frag(sk, size_goal, flags, page, offset, &copy);
- if (!skb)
- goto wait_for_space;
-
- if (!copied)
- TCP_SKB_CB(skb)->tcp_flags &= ~TCPHDR_PSH;
-
- copied += copy;
- offset += copy;
- size -= copy;
- if (!size)
- goto out;
-
- if (skb->len < size_goal || (flags & MSG_OOB))
- continue;
-
- if (forced_push(tp)) {
- tcp_mark_push(tp, skb);
- __tcp_push_pending_frames(sk, mss_now, TCP_NAGLE_PUSH);
- } else if (skb == tcp_send_head(sk))
- tcp_push_one(sk, mss_now);
- continue;
-
-wait_for_space:
- set_bit(SOCK_NOSPACE, &sk->sk_socket->flags);
- tcp_push(sk, flags & ~MSG_MORE, mss_now,
- TCP_NAGLE_PUSH, size_goal);
-
- err = sk_stream_wait_memory(sk, &timeo);
- if (err != 0)
- goto do_error;
-
- mss_now = tcp_send_mss(sk, &size_goal, flags);
- }
-
-out:
- if (copied) {
- tcp_tx_timestamp(sk, sk->sk_tsflags);
- if (!(flags & MSG_SENDPAGE_NOTLAST))
- tcp_push(sk, flags, mss_now, tp->nonagle, size_goal);
- }
- return copied;
-
-do_error:
- tcp_remove_empty_skb(sk);
- if (copied)
- goto out;
-out_err:
- /* make sure we wake any epoll edge trigger waiter */
- if (unlikely(tcp_rtx_and_write_queues_empty(sk) && err == -EAGAIN)) {
- sk->sk_write_space(sk);
- tcp_chrono_stop(sk, TCP_CHRONO_SNDBUF_LIMITED);
- }
- return sk_stream_error(sk, flags, err);
-}
-EXPORT_SYMBOL_GPL(do_tcp_sendpages);
-
-int tcp_sendpage_locked(struct sock *sk, struct page *page, int offset,
- size_t size, int flags)
-{
- if (!(sk->sk_route_caps & NETIF_F_SG))
- return sock_no_sendpage_locked(sk, page, offset, size, flags);
-
- tcp_rate_check_app_limited(sk); /* is sending application-limited? */
-
- return do_tcp_sendpages(sk, page, offset, size, flags);
-}
-EXPORT_SYMBOL_GPL(tcp_sendpage_locked);
-
-int tcp_sendpage(struct sock *sk, struct page *page, int offset,
- size_t size, int flags)
-{
- int ret;
-
- lock_sock(sk);
- ret = tcp_sendpage_locked(sk, page, offset, size, flags);
- release_sock(sk);
-
- return ret;
-}
-EXPORT_SYMBOL(tcp_sendpage);
-
void tcp_free_fastopen_req(struct tcp_sock *tp)
{
if (tp->fastopen_req) {
@@ -1223,28 +1038,31 @@ int tcp_sendmsg_locked(struct sock *sk, struct msghdr *msg, size_t size)
int flags, err, copied = 0;
int mss_now = 0, size_goal, copied_syn = 0;
int process_backlog = 0;
- bool zc = false;
+ int zc = 0;
long timeo;
flags = msg->msg_flags;
if ((flags & MSG_ZEROCOPY) && size) {
- skb = tcp_write_queue_tail(sk);
-
if (msg->msg_ubuf) {
uarg = msg->msg_ubuf;
- net_zcopy_get(uarg);
- zc = sk->sk_route_caps & NETIF_F_SG;
+ if (sk->sk_route_caps & NETIF_F_SG)
+ zc = MSG_ZEROCOPY;
} else if (sock_flag(sk, SOCK_ZEROCOPY)) {
+ skb = tcp_write_queue_tail(sk);
uarg = msg_zerocopy_realloc(sk, size, skb_zcopy(skb));
if (!uarg) {
err = -ENOBUFS;
goto out_err;
}
- zc = sk->sk_route_caps & NETIF_F_SG;
- if (!zc)
+ if (sk->sk_route_caps & NETIF_F_SG)
+ zc = MSG_ZEROCOPY;
+ else
uarg_to_msgzc(uarg)->zerocopy = 0;
}
+ } else if (unlikely(msg->msg_flags & MSG_SPLICE_PAGES) && size) {
+ if (sk->sk_route_caps & NETIF_F_SG)
+ zc = MSG_SPLICE_PAGES;
}
if (unlikely(flags & MSG_FASTOPEN || inet_sk(sk)->defer_connect) &&
@@ -1307,7 +1125,7 @@ restart:
goto do_error;
while (msg_data_left(msg)) {
- int copy = 0;
+ ssize_t copy = 0;
skb = tcp_write_queue_tail(sk);
if (skb)
@@ -1326,7 +1144,7 @@ new_segment:
goto restart;
}
first_skb = tcp_rtx_and_write_queues_empty(sk);
- skb = tcp_stream_alloc_skb(sk, 0, sk->sk_allocation,
+ skb = tcp_stream_alloc_skb(sk, sk->sk_allocation,
first_skb);
if (!skb)
goto wait_for_space;
@@ -1348,7 +1166,7 @@ new_segment:
if (copy > msg_data_left(msg))
copy = msg_data_left(msg);
- if (!zc) {
+ if (zc == 0) {
bool merge = true;
int i = skb_shinfo(skb)->nr_frags;
struct page_frag *pfrag = sk_page_frag(sk);
@@ -1393,7 +1211,7 @@ new_segment:
page_ref_inc(pfrag->page);
}
pfrag->offset += copy;
- } else {
+ } else if (zc == MSG_ZEROCOPY) {
/* First append to a fragless skb builds initial
* pure zerocopy skb
*/
@@ -1414,6 +1232,30 @@ new_segment:
if (err < 0)
goto do_error;
copy = err;
+ } else if (zc == MSG_SPLICE_PAGES) {
+ /* Splice in data if we can; copy if we can't. */
+ if (tcp_downgrade_zcopy_pure(sk, skb))
+ goto wait_for_space;
+ copy = tcp_wmem_schedule(sk, copy);
+ if (!copy)
+ goto wait_for_space;
+
+ err = skb_splice_from_iter(skb, &msg->msg_iter, copy,
+ sk->sk_allocation);
+ if (err < 0) {
+ if (err == -EMSGSIZE) {
+ tcp_mark_push(tp, skb);
+ goto new_segment;
+ }
+ goto do_error;
+ }
+ copy = err;
+
+ if (!(flags & MSG_NO_SHARED_FRAGS))
+ skb_shinfo(skb)->flags |= SKBFL_SHARED_FRAG;
+
+ sk_wmem_queued_add(sk, copy);
+ sk_mem_charge(sk, copy);
}
if (!copied)
@@ -1459,7 +1301,9 @@ out:
tcp_push(sk, flags, mss_now, tp->nonagle, size_goal);
}
out_nopush:
- net_zcopy_put(uarg);
+ /* msg->msg_ubuf is pinned by the caller so we don't take extra refs */
+ if (uarg && !msg->msg_ubuf)
+ net_zcopy_put(uarg);
return copied + copied_syn;
do_error:
@@ -1468,7 +1312,9 @@ do_error:
if (copied + copied_syn)
goto out;
out_err:
- net_zcopy_put_abort(uarg, true);
+ /* msg->msg_ubuf is pinned by the caller so we don't take extra refs */
+ if (uarg && !msg->msg_ubuf)
+ 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)) {
@@ -1491,6 +1337,22 @@ int tcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t size)
}
EXPORT_SYMBOL(tcp_sendmsg);
+void tcp_splice_eof(struct socket *sock)
+{
+ struct sock *sk = sock->sk;
+ struct tcp_sock *tp = tcp_sk(sk);
+ int mss_now, size_goal;
+
+ if (!tcp_write_queue_tail(sk))
+ return;
+
+ lock_sock(sk);
+ mss_now = tcp_send_mss(sk, &size_goal, 0);
+ tcp_push(sk, 0, mss_now, tp->nonagle, size_goal);
+ release_sock(sk);
+}
+EXPORT_SYMBOL_GPL(tcp_splice_eof);
+
/*
* Handle reading urgent data. BSD has very simple semantics for
* this, no blocking and very strange errors 8)
@@ -1877,7 +1739,7 @@ void tcp_update_recv_tstamps(struct sk_buff *skb,
}
#ifdef CONFIG_MMU
-static const struct vm_operations_struct tcp_vm_ops = {
+const struct vm_operations_struct tcp_vm_ops = {
};
int tcp_mmap(struct file *file, struct socket *sock,
@@ -2176,6 +2038,34 @@ static void tcp_zc_finalize_rx_tstamp(struct sock *sk,
}
}
+static struct vm_area_struct *find_tcp_vma(struct mm_struct *mm,
+ unsigned long address,
+ bool *mmap_locked)
+{
+ struct vm_area_struct *vma = NULL;
+
+#ifdef CONFIG_PER_VMA_LOCK
+ vma = lock_vma_under_rcu(mm, address);
+#endif
+ if (vma) {
+ if (!vma_is_tcp(vma)) {
+ vma_end_read(vma);
+ return NULL;
+ }
+ *mmap_locked = false;
+ return vma;
+ }
+
+ mmap_read_lock(mm);
+ vma = vma_lookup(mm, address);
+ if (!vma || !vma_is_tcp(vma)) {
+ mmap_read_unlock(mm);
+ return NULL;
+ }
+ *mmap_locked = true;
+ return vma;
+}
+
#define TCP_ZEROCOPY_PAGE_BATCH_SIZE 32
static int tcp_zerocopy_receive(struct sock *sk,
struct tcp_zerocopy_receive *zc,
@@ -2193,6 +2083,7 @@ static int tcp_zerocopy_receive(struct sock *sk,
u32 seq = tp->copied_seq;
u32 total_bytes_to_map;
int inq = tcp_inq(sk);
+ bool mmap_locked;
int ret;
zc->copybuf_len = 0;
@@ -2217,13 +2108,10 @@ static int tcp_zerocopy_receive(struct sock *sk,
return 0;
}
- mmap_read_lock(current->mm);
-
- vma = vma_lookup(current->mm, address);
- if (!vma || vma->vm_ops != &tcp_vm_ops) {
- mmap_read_unlock(current->mm);
+ vma = find_tcp_vma(current->mm, address, &mmap_locked);
+ if (!vma)
return -EINVAL;
- }
+
vma_len = min_t(unsigned long, zc->length, vma->vm_end - address);
avail_len = min_t(u32, vma_len, inq);
total_bytes_to_map = avail_len & ~(PAGE_SIZE - 1);
@@ -2297,7 +2185,10 @@ static int tcp_zerocopy_receive(struct sock *sk,
zc, total_bytes_to_map);
}
out:
- mmap_read_unlock(current->mm);
+ if (mmap_locked)
+ mmap_read_unlock(current->mm);
+ else
+ vma_end_read(vma);
/* Try to copy straggler data. */
if (!ret)
copylen = tcp_zc_handle_leftover(zc, sk, skb, &seq, copybuf_len, tss);
@@ -4680,8 +4571,10 @@ int tcp_abort(struct sock *sk, int err)
return 0;
}
- /* Don't race with userspace socket closes such as tcp_close. */
- lock_sock(sk);
+ /* BPF context ensures sock locking. */
+ if (!has_current_bpf_ctx())
+ /* Don't race with userspace socket closes such as tcp_close. */
+ lock_sock(sk);
if (sk->sk_state == TCP_LISTEN) {
tcp_set_state(sk, TCP_CLOSE);
@@ -4705,7 +4598,8 @@ int tcp_abort(struct sock *sk, int err)
bh_unlock_sock(sk);
local_bh_enable();
tcp_write_queue_purge(sk);
- release_sock(sk);
+ if (!has_current_bpf_ctx())
+ release_sock(sk);
return 0;
}
EXPORT_SYMBOL_GPL(tcp_abort);
diff --git a/net/ipv4/tcp_bpf.c b/net/ipv4/tcp_bpf.c
index 5f93918c063c..81f0dff69e0b 100644
--- a/net/ipv4/tcp_bpf.c
+++ b/net/ipv4/tcp_bpf.c
@@ -88,6 +88,7 @@ static int bpf_tcp_ingress(struct sock *sk, struct sk_psock *psock,
static int tcp_bpf_push(struct sock *sk, struct sk_msg *msg, u32 apply_bytes,
int flags, bool uncharge)
{
+ struct msghdr msghdr = {};
bool apply = apply_bytes;
struct scatterlist *sge;
struct page *page;
@@ -95,6 +96,7 @@ static int tcp_bpf_push(struct sock *sk, struct sk_msg *msg, u32 apply_bytes,
u32 off;
while (1) {
+ struct bio_vec bvec;
bool has_tx_ulp;
sge = sk_msg_elem(msg, msg->sg.start);
@@ -105,17 +107,20 @@ static int tcp_bpf_push(struct sock *sk, struct sk_msg *msg, u32 apply_bytes,
tcp_rate_check_app_limited(sk);
retry:
+ msghdr.msg_flags = flags | MSG_SPLICE_PAGES;
has_tx_ulp = tls_sw_has_ctx_tx(sk);
- if (has_tx_ulp) {
- flags |= MSG_SENDPAGE_NOPOLICY;
- ret = kernel_sendpage_locked(sk,
- page, off, size, flags);
- } else {
- ret = do_tcp_sendpages(sk, page, off, size, flags);
- }
+ if (has_tx_ulp)
+ msghdr.msg_flags |= MSG_SENDPAGE_NOPOLICY;
+
+ if (size < sge->length && msg->sg.start != msg->sg.end)
+ msghdr.msg_flags |= MSG_MORE;
+ bvec_set_page(&bvec, page, size, off);
+ iov_iter_bvec(&msghdr.msg_iter, ITER_SOURCE, &bvec, 1, size);
+ ret = tcp_sendmsg_locked(sk, &msghdr, size);
if (ret <= 0)
return ret;
+
if (apply)
apply_bytes -= ret;
msg->sg.size -= ret;
@@ -481,7 +486,7 @@ static int tcp_bpf_sendmsg(struct sock *sk, struct msghdr *msg, size_t size)
long timeo;
int flags;
- /* Don't let internal do_tcp_sendpages() flags through */
+ /* Don't let internal flags through */
flags = (msg->msg_flags & ~MSG_SENDPAGE_DECRYPTED);
flags |= MSG_NO_SHARED_FRAGS;
@@ -561,54 +566,6 @@ out_err:
return copied ? copied : err;
}
-static int tcp_bpf_sendpage(struct sock *sk, struct page *page, int offset,
- size_t size, int flags)
-{
- struct sk_msg tmp, *msg = NULL;
- int err = 0, copied = 0;
- struct sk_psock *psock;
- bool enospc = false;
-
- psock = sk_psock_get(sk);
- if (unlikely(!psock))
- return tcp_sendpage(sk, page, offset, size, flags);
-
- lock_sock(sk);
- if (psock->cork) {
- msg = psock->cork;
- } else {
- msg = &tmp;
- sk_msg_init(msg);
- }
-
- /* Catch case where ring is full and sendpage is stalled. */
- if (unlikely(sk_msg_full(msg)))
- goto out_err;
-
- sk_msg_page_add(msg, page, size, offset);
- sk_mem_charge(sk, size);
- copied = size;
- if (sk_msg_full(msg))
- enospc = true;
- if (psock->cork_bytes) {
- if (size > psock->cork_bytes)
- psock->cork_bytes = 0;
- else
- psock->cork_bytes -= size;
- if (psock->cork_bytes && !enospc)
- goto out_err;
- /* All cork bytes are accounted, rerun the prog. */
- psock->eval = __SK_NONE;
- psock->cork_bytes = 0;
- }
-
- err = tcp_bpf_send_verdict(sk, psock, msg, &copied, flags);
-out_err:
- release_sock(sk);
- sk_psock_put(sk, psock);
- return copied ? copied : err;
-}
-
enum {
TCP_BPF_IPV4,
TCP_BPF_IPV6,
@@ -638,7 +595,6 @@ static void tcp_bpf_rebuild_protos(struct proto prot[TCP_BPF_NUM_CFGS],
prot[TCP_BPF_TX] = prot[TCP_BPF_BASE];
prot[TCP_BPF_TX].sendmsg = tcp_bpf_sendmsg;
- prot[TCP_BPF_TX].sendpage = tcp_bpf_sendpage;
prot[TCP_BPF_RX] = prot[TCP_BPF_BASE];
prot[TCP_BPF_RX].recvmsg = tcp_bpf_recvmsg_parser;
@@ -673,8 +629,7 @@ static int tcp_bpf_assert_proto_ops(struct proto *ops)
* indeed valid assumptions.
*/
return ops->recvmsg == tcp_recvmsg &&
- ops->sendmsg == tcp_sendmsg &&
- ops->sendpage == tcp_sendpage ? 0 : -ENOTSUPP;
+ ops->sendmsg == tcp_sendmsg ? 0 : -ENOTSUPP;
}
int tcp_bpf_update_proto(struct sock *sk, struct sk_psock *psock, bool restore)
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index bf8b22218dd4..6f072095211e 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -2867,7 +2867,7 @@ static void tcp_process_loss(struct sock *sk, int flag, int num_dupack,
}
if (tcp_is_reno(tp)) {
/* A Reno DUPACK means new data in F-RTO step 2.b above are
- * delivered. Lower inflight to clock out (re)tranmissions.
+ * delivered. Lower inflight to clock out (re)transmissions.
*/
if (after(tp->snd_nxt, tp->high_seq) && num_dupack)
tcp_add_reno_sack(sk, num_dupack, flag & FLAG_ECE);
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 06d2573685ca..fd365de4d5ff 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -692,6 +692,7 @@ static void tcp_v4_send_reset(const struct sock *sk, struct sk_buff *skb)
u64 transmit_time = 0;
struct sock *ctl_sk;
struct net *net;
+ u32 txhash = 0;
/* Never send a reset in response to a reset. */
if (th->rst)
@@ -829,6 +830,8 @@ static void tcp_v4_send_reset(const struct sock *sk, struct sk_buff *skb)
inet_twsk(sk)->tw_priority : sk->sk_priority;
transmit_time = tcp_transmit_time(sk);
xfrm_sk_clone_policy(ctl_sk, sk);
+ txhash = (sk->sk_state == TCP_TIME_WAIT) ?
+ inet_twsk(sk)->tw_txhash : sk->sk_txhash;
} else {
ctl_sk->sk_mark = 0;
ctl_sk->sk_priority = 0;
@@ -837,7 +840,7 @@ static void tcp_v4_send_reset(const struct sock *sk, struct sk_buff *skb)
skb, &TCP_SKB_CB(skb)->header.h4.opt,
ip_hdr(skb)->saddr, ip_hdr(skb)->daddr,
&arg, arg.iov[0].iov_len,
- transmit_time);
+ transmit_time, txhash);
xfrm_sk_free_policy(ctl_sk);
sock_net_set(ctl_sk, &init_net);
@@ -859,7 +862,7 @@ static void tcp_v4_send_ack(const struct sock *sk,
struct sk_buff *skb, u32 seq, u32 ack,
u32 win, u32 tsval, u32 tsecr, int oif,
struct tcp_md5sig_key *key,
- int reply_flags, u8 tos)
+ int reply_flags, u8 tos, u32 txhash)
{
const struct tcphdr *th = tcp_hdr(skb);
struct {
@@ -935,7 +938,7 @@ static void tcp_v4_send_ack(const struct sock *sk,
skb, &TCP_SKB_CB(skb)->header.h4.opt,
ip_hdr(skb)->saddr, ip_hdr(skb)->daddr,
&arg, arg.iov[0].iov_len,
- transmit_time);
+ transmit_time, txhash);
sock_net_set(ctl_sk, &init_net);
__TCP_INC_STATS(net, TCP_MIB_OUTSEGS);
@@ -955,7 +958,8 @@ static void tcp_v4_timewait_ack(struct sock *sk, struct sk_buff *skb)
tw->tw_bound_dev_if,
tcp_twsk_md5_key(tcptw),
tw->tw_transparent ? IP_REPLY_ARG_NOSRCCHECK : 0,
- tw->tw_tos
+ tw->tw_tos,
+ tw->tw_txhash
);
inet_twsk_put(tw);
@@ -988,7 +992,7 @@ static void tcp_v4_reqsk_send_ack(const struct sock *sk, struct sk_buff *skb,
0,
tcp_md5_do_lookup(sk, l3index, addr, AF_INET),
inet_rsk(req)->no_srccheck ? IP_REPLY_ARG_NOSRCCHECK : 0,
- ip_hdr(skb)->tos);
+ ip_hdr(skb)->tos, tcp_rsk(req)->txhash);
}
/*
@@ -2963,7 +2967,6 @@ static int bpf_iter_tcp_seq_show(struct seq_file *seq, void *v)
struct bpf_iter_meta meta;
struct bpf_prog *prog;
struct sock *sk = v;
- bool slow;
uid_t uid;
int ret;
@@ -2971,7 +2974,7 @@ static int bpf_iter_tcp_seq_show(struct seq_file *seq, void *v)
return 0;
if (sk_fullsock(sk))
- slow = lock_sock_fast(sk);
+ lock_sock(sk);
if (unlikely(sk_unhashed(sk))) {
ret = SEQ_SKIP;
@@ -2995,7 +2998,7 @@ static int bpf_iter_tcp_seq_show(struct seq_file *seq, void *v)
unlock:
if (sk_fullsock(sk))
- unlock_sock_fast(sk, slow);
+ release_sock(sk);
return ret;
}
@@ -3113,7 +3116,7 @@ struct proto tcp_prot = {
.keepalive = tcp_set_keepalive,
.recvmsg = tcp_recvmsg,
.sendmsg = tcp_sendmsg,
- .sendpage = tcp_sendpage,
+ .splice_eof = tcp_splice_eof,
.backlog_rcv = tcp_v4_do_rcv,
.release_cb = tcp_release_cb,
.hash = inet_hash,
@@ -3276,6 +3279,9 @@ static int __net_init tcp_sk_init(struct net *net)
else
net->ipv4.tcp_congestion_control = &tcp_reno;
+ net->ipv4.sysctl_tcp_syn_linear_timeouts = 4;
+ net->ipv4.sysctl_tcp_shrink_window = 0;
+
return 0;
}
@@ -3356,7 +3362,7 @@ static struct bpf_iter_reg tcp_reg_info = {
.ctx_arg_info_size = 1,
.ctx_arg_info = {
{ offsetof(struct bpf_iter__tcp, sk_common),
- PTR_TO_BTF_ID_OR_NULL },
+ PTR_TO_BTF_ID_OR_NULL | PTR_TRUSTED },
},
.get_func_proto = bpf_iter_tcp_get_func_proto,
.seq_info = &tcp_seq_info,
diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c
index dac0d62120e6..04fc328727e6 100644
--- a/net/ipv4/tcp_minisocks.c
+++ b/net/ipv4/tcp_minisocks.c
@@ -303,6 +303,7 @@ void tcp_time_wait(struct sock *sk, int state, int timeo)
tcptw->tw_ts_offset = tp->tsoffset;
tcptw->tw_last_oow_ack_time = 0;
tcptw->tw_tx_delay = tp->tcp_tx_delay;
+ tw->tw_txhash = sk->sk_txhash;
#if IS_ENABLED(CONFIG_IPV6)
if (tw->tw_family == PF_INET6) {
struct ipv6_pinfo *np = inet6_sk(sk);
@@ -311,7 +312,6 @@ void tcp_time_wait(struct sock *sk, int state, int timeo)
tw->tw_v6_rcv_saddr = sk->sk_v6_rcv_saddr;
tw->tw_tclass = np->tclass;
tw->tw_flowlabel = be32_to_cpu(np->flow_label & IPV6_FLOWLABEL_MASK);
- tw->tw_txhash = sk->sk_txhash;
tw->tw_ipv6only = sk->sk_ipv6only;
}
#endif
diff --git a/net/ipv4/tcp_offload.c b/net/ipv4/tcp_offload.c
index 4851211aa60d..8311c38267b5 100644
--- a/net/ipv4/tcp_offload.c
+++ b/net/ipv4/tcp_offload.c
@@ -9,6 +9,7 @@
#include <linux/indirect_call_wrapper.h>
#include <linux/skbuff.h>
#include <net/gro.h>
+#include <net/gso.h>
#include <net/tcp.h>
#include <net/protocol.h>
@@ -295,7 +296,7 @@ out:
return pp;
}
-int tcp_gro_complete(struct sk_buff *skb)
+void tcp_gro_complete(struct sk_buff *skb)
{
struct tcphdr *th = tcp_hdr(skb);
@@ -310,8 +311,6 @@ int tcp_gro_complete(struct sk_buff *skb)
if (skb->encapsulation)
skb->inner_transport_header = skb->transport_header;
-
- return 0;
}
EXPORT_SYMBOL(tcp_gro_complete);
@@ -341,7 +340,8 @@ INDIRECT_CALLABLE_SCOPE int tcp4_gro_complete(struct sk_buff *skb, int thoff)
if (NAPI_GRO_CB(skb)->is_atomic)
skb_shinfo(skb)->gso_type |= SKB_GSO_TCP_FIXEDID;
- return tcp_gro_complete(skb);
+ tcp_gro_complete(skb);
+ return 0;
}
static const struct net_offload tcpv4_offload = {
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index cfe128b81a01..2cb39b6dad02 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -260,8 +260,8 @@ static u16 tcp_select_window(struct sock *sk)
u32 old_win = tp->rcv_wnd;
u32 cur_win = tcp_receive_window(tp);
u32 new_win = __tcp_select_window(sk);
+ struct net *net = sock_net(sk);
- /* Never shrink the offered window */
if (new_win < cur_win) {
/* Danger Will Robinson!
* Don't update rcv_wup/rcv_wnd here or else
@@ -270,11 +270,14 @@ static u16 tcp_select_window(struct sock *sk)
*
* Relax Will Robinson.
*/
- if (new_win == 0)
- NET_INC_STATS(sock_net(sk),
- LINUX_MIB_TCPWANTZEROWINDOWADV);
- new_win = ALIGN(cur_win, 1 << tp->rx_opt.rcv_wscale);
+ if (!READ_ONCE(net->ipv4.sysctl_tcp_shrink_window) || !tp->rx_opt.rcv_wscale) {
+ /* Never shrink the offered window */
+ if (new_win == 0)
+ NET_INC_STATS(net, LINUX_MIB_TCPWANTZEROWINDOWADV);
+ new_win = ALIGN(cur_win, 1 << tp->rx_opt.rcv_wscale);
+ }
}
+
tp->rcv_wnd = new_win;
tp->rcv_wup = tp->rcv_nxt;
@@ -282,7 +285,7 @@ static u16 tcp_select_window(struct sock *sk)
* scaled window.
*/
if (!tp->rx_opt.rcv_wscale &&
- READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_workaround_signed_windows))
+ READ_ONCE(net->ipv4.sysctl_tcp_workaround_signed_windows))
new_win = min(new_win, MAX_TCP_WINDOW);
else
new_win = min(new_win, (65535U << tp->rx_opt.rcv_wscale));
@@ -294,10 +297,9 @@ static u16 tcp_select_window(struct sock *sk)
if (new_win == 0) {
tp->pred_flags = 0;
if (old_win)
- NET_INC_STATS(sock_net(sk),
- LINUX_MIB_TCPTOZEROWINDOWADV);
+ NET_INC_STATS(net, LINUX_MIB_TCPTOZEROWINDOWADV);
} else if (old_win == 0) {
- NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPFROMZEROWINDOWADV);
+ NET_INC_STATS(net, LINUX_MIB_TCPFROMZEROWINDOWADV);
}
return new_win;
@@ -1530,7 +1532,7 @@ int tcp_fragment(struct sock *sk, enum tcp_queue tcp_queue,
{
struct tcp_sock *tp = tcp_sk(sk);
struct sk_buff *buff;
- int nsize, old_factor;
+ int old_factor;
long limit;
int nlen;
u8 flags;
@@ -1538,9 +1540,7 @@ int tcp_fragment(struct sock *sk, enum tcp_queue tcp_queue,
if (WARN_ON(len > skb->len))
return -EINVAL;
- nsize = skb_headlen(skb) - len;
- if (nsize < 0)
- nsize = 0;
+ DEBUG_NET_WARN_ON_ONCE(skb_headlen(skb));
/* tcp_sendmsg() can overshoot sk_wmem_queued by one full size skb.
* We need some allowance to not penalize applications setting small
@@ -1560,7 +1560,7 @@ int tcp_fragment(struct sock *sk, enum tcp_queue tcp_queue,
return -ENOMEM;
/* Get a new skb... force flag on. */
- buff = tcp_stream_alloc_skb(sk, nsize, gfp, true);
+ buff = tcp_stream_alloc_skb(sk, gfp, true);
if (!buff)
return -ENOMEM; /* We'll just try again later. */
skb_copy_decrypted(buff, skb);
@@ -1568,7 +1568,7 @@ int tcp_fragment(struct sock *sk, enum tcp_queue tcp_queue,
sk_wmem_queued_add(sk, buff->truesize);
sk_mem_charge(sk, buff->truesize);
- nlen = skb->len - len - nsize;
+ nlen = skb->len - len;
buff->truesize += nlen;
skb->truesize -= nlen;
@@ -1626,13 +1626,7 @@ static int __pskb_trim_head(struct sk_buff *skb, int len)
struct skb_shared_info *shinfo;
int i, k, eat;
- eat = min_t(int, len, skb_headlen(skb));
- if (eat) {
- __skb_pull(skb, eat);
- len -= eat;
- if (!len)
- return 0;
- }
+ DEBUG_NET_WARN_ON_ONCE(skb_headlen(skb));
eat = len;
k = 0;
shinfo = skb_shinfo(skb);
@@ -1671,12 +1665,10 @@ int tcp_trim_head(struct sock *sk, struct sk_buff *skb, u32 len)
TCP_SKB_CB(skb)->seq += len;
- if (delta_truesize) {
- skb->truesize -= delta_truesize;
- sk_wmem_queued_add(sk, -delta_truesize);
- if (!skb_zcopy_pure(skb))
- sk_mem_uncharge(sk, delta_truesize);
- }
+ skb->truesize -= delta_truesize;
+ sk_wmem_queued_add(sk, -delta_truesize);
+ if (!skb_zcopy_pure(skb))
+ sk_mem_uncharge(sk, delta_truesize);
/* Any change of skb->len requires recalculation of tso factor. */
if (tcp_skb_pcount(skb) > 1)
@@ -2126,11 +2118,9 @@ static int tso_fragment(struct sock *sk, struct sk_buff *skb, unsigned int len,
u8 flags;
/* All of a TSO frame must be composed of paged data. */
- if (skb->len != skb->data_len)
- return tcp_fragment(sk, TCP_FRAG_IN_WRITE_QUEUE,
- skb, len, mss_now, gfp);
+ DEBUG_NET_WARN_ON_ONCE(skb->len != skb->data_len);
- buff = tcp_stream_alloc_skb(sk, 0, gfp, true);
+ buff = tcp_stream_alloc_skb(sk, gfp, true);
if (unlikely(!buff))
return -ENOMEM;
skb_copy_decrypted(buff, skb);
@@ -2319,6 +2309,57 @@ static bool tcp_can_coalesce_send_queue_head(struct sock *sk, int len)
return true;
}
+static int tcp_clone_payload(struct sock *sk, struct sk_buff *to,
+ int probe_size)
+{
+ skb_frag_t *lastfrag = NULL, *fragto = skb_shinfo(to)->frags;
+ int i, todo, len = 0, nr_frags = 0;
+ const struct sk_buff *skb;
+
+ if (!sk_wmem_schedule(sk, to->truesize + probe_size))
+ return -ENOMEM;
+
+ skb_queue_walk(&sk->sk_write_queue, skb) {
+ const skb_frag_t *fragfrom = skb_shinfo(skb)->frags;
+
+ if (skb_headlen(skb))
+ return -EINVAL;
+
+ for (i = 0; i < skb_shinfo(skb)->nr_frags; i++, fragfrom++) {
+ if (len >= probe_size)
+ goto commit;
+ todo = min_t(int, skb_frag_size(fragfrom),
+ probe_size - len);
+ len += todo;
+ if (lastfrag &&
+ skb_frag_page(fragfrom) == skb_frag_page(lastfrag) &&
+ skb_frag_off(fragfrom) == skb_frag_off(lastfrag) +
+ skb_frag_size(lastfrag)) {
+ skb_frag_size_add(lastfrag, todo);
+ continue;
+ }
+ if (unlikely(nr_frags == MAX_SKB_FRAGS))
+ return -E2BIG;
+ skb_frag_page_copy(fragto, fragfrom);
+ skb_frag_off_copy(fragto, fragfrom);
+ skb_frag_size_set(fragto, todo);
+ nr_frags++;
+ lastfrag = fragto++;
+ }
+ }
+commit:
+ WARN_ON_ONCE(len != probe_size);
+ for (i = 0; i < nr_frags; i++)
+ skb_frag_ref(to, i);
+
+ skb_shinfo(to)->nr_frags = nr_frags;
+ to->truesize += probe_size;
+ to->len += probe_size;
+ to->data_len += probe_size;
+ __skb_header_release(to);
+ return 0;
+}
+
/* Create a new MTU probe if we are ready.
* MTU probe is regularly attempting to increase the path MTU by
* deliberately sending larger packets. This discovers routing
@@ -2395,9 +2436,15 @@ static int tcp_mtu_probe(struct sock *sk)
return -1;
/* We're allowed to probe. Build it now. */
- nskb = tcp_stream_alloc_skb(sk, probe_size, GFP_ATOMIC, false);
+ nskb = tcp_stream_alloc_skb(sk, GFP_ATOMIC, false);
if (!nskb)
return -1;
+
+ /* build the payload, and be prepared to abort if this fails. */
+ if (tcp_clone_payload(sk, nskb, probe_size)) {
+ consume_skb(nskb);
+ return -1;
+ }
sk_wmem_queued_add(sk, nskb->truesize);
sk_mem_charge(sk, nskb->truesize);
@@ -2415,7 +2462,6 @@ static int tcp_mtu_probe(struct sock *sk)
len = 0;
tcp_for_write_queue_from_safe(skb, next, sk) {
copy = min_t(int, skb->len, probe_size - len);
- skb_copy_bits(skb, 0, skb_put(nskb, copy), copy);
if (skb->len <= copy) {
/* We've eaten all the data from this skb.
@@ -2431,12 +2477,8 @@ static int tcp_mtu_probe(struct sock *sk)
} else {
TCP_SKB_CB(nskb)->tcp_flags |= TCP_SKB_CB(skb)->tcp_flags &
~(TCPHDR_FIN|TCPHDR_PSH);
- if (!skb_shinfo(skb)->nr_frags) {
- skb_pull(skb, copy);
- } else {
- __pskb_trim_head(skb, copy);
- tcp_set_skb_tso_segs(skb, mss_now);
- }
+ __pskb_trim_head(skb, copy);
+ tcp_set_skb_tso_segs(skb, mss_now);
TCP_SKB_CB(skb)->seq += copy;
}
@@ -2947,6 +2989,7 @@ u32 __tcp_select_window(struct sock *sk)
{
struct inet_connection_sock *icsk = inet_csk(sk);
struct tcp_sock *tp = tcp_sk(sk);
+ struct net *net = sock_net(sk);
/* MSS for the peer's data. Previous versions used mss_clamp
* here. I don't know if the value based on our guesses
* of peer's MSS is better for the performance. It's more correct
@@ -2968,6 +3011,15 @@ u32 __tcp_select_window(struct sock *sk)
if (mss <= 0)
return 0;
}
+
+ /* Only allow window shrink if the sysctl is enabled and we have
+ * a non-zero scaling factor in effect.
+ */
+ if (READ_ONCE(net->ipv4.sysctl_tcp_shrink_window) && tp->rx_opt.rcv_wscale)
+ goto shrink_window_allowed;
+
+ /* do not allow window to shrink */
+
if (free_space < (full_space >> 1)) {
icsk->icsk_ack.quick = 0;
@@ -3022,6 +3074,36 @@ u32 __tcp_select_window(struct sock *sk)
}
return window;
+
+shrink_window_allowed:
+ /* new window should always be an exact multiple of scaling factor */
+ free_space = round_down(free_space, 1 << tp->rx_opt.rcv_wscale);
+
+ if (free_space < (full_space >> 1)) {
+ icsk->icsk_ack.quick = 0;
+
+ if (tcp_under_memory_pressure(sk))
+ tcp_adjust_rcv_ssthresh(sk);
+
+ /* if free space is too low, return a zero window */
+ if (free_space < (allowed_space >> 4) || free_space < mss ||
+ free_space < (1 << tp->rx_opt.rcv_wscale))
+ return 0;
+ }
+
+ if (free_space > tp->rcv_ssthresh) {
+ free_space = tp->rcv_ssthresh;
+ /* new window should always be an exact multiple of scaling factor
+ *
+ * For this case, we ALIGN "up" (increase free_space) because
+ * we know free_space is not zero here, it has been reduced from
+ * the memory-based limit, and rcv_ssthresh is not a hard limit
+ * (unlike sk_rcvbuf).
+ */
+ free_space = ALIGN(free_space, (1 << tp->rx_opt.rcv_wscale));
+ }
+
+ return free_space;
}
void tcp_skb_collapse_tstamp(struct sk_buff *skb,
@@ -3746,8 +3828,9 @@ static int tcp_send_syn_data(struct sock *sk, struct sk_buff *syn)
struct inet_connection_sock *icsk = inet_csk(sk);
struct tcp_sock *tp = tcp_sk(sk);
struct tcp_fastopen_request *fo = tp->fastopen_req;
- int space, err = 0;
+ struct page_frag *pfrag = sk_page_frag(sk);
struct sk_buff *syn_data;
+ int space, err = 0;
tp->rx_opt.mss_clamp = tp->advmss; /* If MSS is not cached */
if (!tcp_fastopen_cookie_check(sk, &tp->rx_opt.mss_clamp, &fo->cookie))
@@ -3766,25 +3849,31 @@ static int tcp_send_syn_data(struct sock *sk, struct sk_buff *syn)
space = min_t(size_t, space, fo->size);
- /* limit to order-0 allocations */
- space = min_t(size_t, space, SKB_MAX_HEAD(MAX_TCP_HEADER));
-
- syn_data = tcp_stream_alloc_skb(sk, space, sk->sk_allocation, false);
+ if (space &&
+ !skb_page_frag_refill(min_t(size_t, space, PAGE_SIZE),
+ pfrag, sk->sk_allocation))
+ goto fallback;
+ syn_data = tcp_stream_alloc_skb(sk, sk->sk_allocation, false);
if (!syn_data)
goto fallback;
memcpy(syn_data->cb, syn->cb, sizeof(syn->cb));
if (space) {
- int copied = copy_from_iter(skb_put(syn_data, space), space,
- &fo->data->msg_iter);
- if (unlikely(!copied)) {
+ space = min_t(size_t, space, pfrag->size - pfrag->offset);
+ space = tcp_wmem_schedule(sk, space);
+ }
+ if (space) {
+ space = copy_page_from_iter(pfrag->page, pfrag->offset,
+ space, &fo->data->msg_iter);
+ if (unlikely(!space)) {
tcp_skb_tsorted_anchor_cleanup(syn_data);
kfree_skb(syn_data);
goto fallback;
}
- if (copied != space) {
- skb_trim(syn_data, copied);
- space = copied;
- }
+ skb_fill_page_desc(syn_data, 0, pfrag->page,
+ pfrag->offset, space);
+ page_ref_inc(pfrag->page);
+ pfrag->offset += space;
+ skb_len_add(syn_data, space);
skb_zcopy_set(syn_data, fo->uarg, NULL);
}
/* No more data pending in inet_wait_for_connect() */
@@ -3849,7 +3938,7 @@ int tcp_connect(struct sock *sk)
return 0;
}
- buff = tcp_stream_alloc_skb(sk, 0, sk->sk_allocation, true);
+ buff = tcp_stream_alloc_skb(sk, sk->sk_allocation, true);
if (unlikely(!buff))
return -ENOBUFS;
diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c
index 39eb947fe392..470f581eedd4 100644
--- a/net/ipv4/tcp_timer.c
+++ b/net/ipv4/tcp_timer.c
@@ -234,14 +234,19 @@ static int tcp_write_timeout(struct sock *sk)
struct tcp_sock *tp = tcp_sk(sk);
struct net *net = sock_net(sk);
bool expired = false, do_reset;
- int retry_until;
+ int retry_until, max_retransmits;
if ((1 << sk->sk_state) & (TCPF_SYN_SENT | TCPF_SYN_RECV)) {
if (icsk->icsk_retransmits)
__dst_negative_advice(sk);
retry_until = icsk->icsk_syn_retries ? :
READ_ONCE(net->ipv4.sysctl_tcp_syn_retries);
- expired = icsk->icsk_retransmits >= retry_until;
+
+ max_retransmits = retry_until;
+ if (sk->sk_state == TCP_SYN_SENT)
+ max_retransmits += READ_ONCE(net->ipv4.sysctl_tcp_syn_linear_timeouts);
+
+ expired = icsk->icsk_retransmits >= max_retransmits;
} else {
if (retransmits_timed_out(sk, READ_ONCE(net->ipv4.sysctl_tcp_retries1), 0)) {
/* Black hole detection */
@@ -587,8 +592,12 @@ out_reset_timer:
icsk->icsk_retransmits <= TCP_THIN_LINEAR_RETRIES) {
icsk->icsk_backoff = 0;
icsk->icsk_rto = min(__tcp_set_rto(tp), TCP_RTO_MAX);
- } else {
- /* Use normal (exponential) backoff */
+ } else if (sk->sk_state != TCP_SYN_SENT ||
+ icsk->icsk_backoff >
+ READ_ONCE(net->ipv4.sysctl_tcp_syn_linear_timeouts)) {
+ /* Use normal (exponential) backoff unless linear timeouts are
+ * activated.
+ */
icsk->icsk_rto = min(icsk->icsk_rto << 1, TCP_RTO_MAX);
}
inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS,
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 9482def1f310..42a96b3547c9 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -103,6 +103,7 @@
#include <net/ip_tunnels.h>
#include <net/route.h>
#include <net/checksum.h>
+#include <net/gso.h>
#include <net/xfrm.h>
#include <trace/events/udp.h>
#include <linux/static_key.h>
@@ -1062,8 +1063,8 @@ int udp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
int free = 0;
int connected = 0;
__be32 daddr, faddr, saddr;
+ u8 tos, scope;
__be16 dport;
- u8 tos;
int err, is_udplite = IS_UDPLITE(sk);
int corkreq = READ_ONCE(up->corkflag) || msg->msg_flags&MSG_MORE;
int (*getfrag)(void *, char *, int, int, int, struct sk_buff *);
@@ -1183,12 +1184,9 @@ int udp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
connected = 0;
}
tos = get_rttos(&ipc, inet);
- if (sock_flag(sk, SOCK_LOCALROUTE) ||
- (msg->msg_flags & MSG_DONTROUTE) ||
- (ipc.opt && ipc.opt->opt.is_strictroute)) {
- tos |= RTO_ONLINK;
+ scope = ip_sendmsg_scope(inet, &ipc, msg);
+ if (scope == RT_SCOPE_LINK)
connected = 0;
- }
if (ipv4_is_multicast(daddr)) {
if (!ipc.oif || netif_index_is_l3_master(sock_net(sk), ipc.oif))
@@ -1221,11 +1219,9 @@ int udp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
fl4 = &fl4_stack;
- flowi4_init_output(fl4, ipc.oif, ipc.sockc.mark, tos,
- RT_SCOPE_UNIVERSE, sk->sk_protocol,
- flow_flags,
- faddr, saddr, dport, inet->inet_sport,
- sk->sk_uid);
+ flowi4_init_output(fl4, ipc.oif, ipc.sockc.mark, tos, scope,
+ sk->sk_protocol, flow_flags, faddr, saddr,
+ dport, inet->inet_sport, sk->sk_uid);
security_sk_classify_flow(sk, flowi4_to_flowi_common(fl4));
rt = ip_route_output_flow(net, fl4, sk);
@@ -1329,58 +1325,20 @@ do_confirm:
}
EXPORT_SYMBOL(udp_sendmsg);
-int udp_sendpage(struct sock *sk, struct page *page, int offset,
- size_t size, int flags)
+void udp_splice_eof(struct socket *sock)
{
- struct inet_sock *inet = inet_sk(sk);
+ struct sock *sk = sock->sk;
struct udp_sock *up = udp_sk(sk);
- int ret;
-
- if (flags & MSG_SENDPAGE_NOTLAST)
- flags |= MSG_MORE;
- if (!up->pending) {
- struct msghdr msg = { .msg_flags = flags|MSG_MORE };
-
- /* Call udp_sendmsg to specify destination address which
- * sendpage interface can't pass.
- * This will succeed only when the socket is connected.
- */
- ret = udp_sendmsg(sk, &msg, 0);
- if (ret < 0)
- return ret;
- }
+ if (!up->pending || READ_ONCE(up->corkflag))
+ return;
lock_sock(sk);
-
- if (unlikely(!up->pending)) {
- release_sock(sk);
-
- net_dbg_ratelimited("cork failed\n");
- return -EINVAL;
- }
-
- ret = ip_append_page(sk, &inet->cork.fl.u.ip4,
- page, offset, size, flags);
- if (ret == -EOPNOTSUPP) {
- release_sock(sk);
- return sock_no_sendpage(sk->sk_socket, page, offset,
- size, flags);
- }
- if (ret < 0) {
- udp_flush_pending_frames(sk);
- goto out;
- }
-
- up->len += size;
- if (!(READ_ONCE(up->corkflag) || (flags&MSG_MORE)))
- ret = udp_push_pending_frames(sk);
- if (!ret)
- ret = size;
-out:
+ if (up->pending && !READ_ONCE(up->corkflag))
+ udp_push_pending_frames(sk);
release_sock(sk);
- return ret;
}
+EXPORT_SYMBOL_GPL(udp_splice_eof);
#define UDP_SKB_IS_STATELESS 0x80000000
@@ -1720,21 +1678,19 @@ static int first_packet_length(struct sock *sk)
* IOCTL requests applicable to the UDP protocol
*/
-int udp_ioctl(struct sock *sk, int cmd, unsigned long arg)
+int udp_ioctl(struct sock *sk, int cmd, int *karg)
{
switch (cmd) {
case SIOCOUTQ:
{
- int amount = sk_wmem_alloc_get(sk);
-
- return put_user(amount, (int __user *)arg);
+ *karg = sk_wmem_alloc_get(sk);
+ return 0;
}
case SIOCINQ:
{
- int amount = max_t(int, 0, first_packet_length(sk));
-
- return put_user(amount, (int __user *)arg);
+ *karg = max_t(int, 0, first_packet_length(sk));
+ return 0;
}
default:
@@ -2927,7 +2883,8 @@ EXPORT_SYMBOL(udp_poll);
int udp_abort(struct sock *sk, int err)
{
- lock_sock(sk);
+ if (!has_current_bpf_ctx())
+ lock_sock(sk);
/* udp{v6}_destroy_sock() sets it under the sk lock, avoid racing
* with close()
@@ -2940,7 +2897,8 @@ int udp_abort(struct sock *sk, int err)
__udp_disconnect(sk, 0);
out:
- release_sock(sk);
+ if (!has_current_bpf_ctx())
+ release_sock(sk);
return 0;
}
@@ -2960,7 +2918,7 @@ struct proto udp_prot = {
.getsockopt = udp_getsockopt,
.sendmsg = udp_sendmsg,
.recvmsg = udp_recvmsg,
- .sendpage = udp_sendpage,
+ .splice_eof = udp_splice_eof,
.release_cb = ip4_datagram_release_cb,
.hash = udp_lib_hash,
.unhash = udp_lib_unhash,
@@ -2985,9 +2943,30 @@ EXPORT_SYMBOL(udp_prot);
/* ------------------------------------------------------------------------ */
#ifdef CONFIG_PROC_FS
-static struct udp_table *udp_get_table_afinfo(struct udp_seq_afinfo *afinfo,
- struct net *net)
+static unsigned short seq_file_family(const struct seq_file *seq);
+static bool seq_sk_match(struct seq_file *seq, const struct sock *sk)
{
+ unsigned short family = seq_file_family(seq);
+
+ /* AF_UNSPEC is used as a match all */
+ return ((family == AF_UNSPEC || family == sk->sk_family) &&
+ net_eq(sock_net(sk), seq_file_net(seq)));
+}
+
+#ifdef CONFIG_BPF_SYSCALL
+static const struct seq_operations bpf_iter_udp_seq_ops;
+#endif
+static struct udp_table *udp_get_table_seq(struct seq_file *seq,
+ struct net *net)
+{
+ const struct udp_seq_afinfo *afinfo;
+
+#ifdef CONFIG_BPF_SYSCALL
+ if (seq->op == &bpf_iter_udp_seq_ops)
+ return net->ipv4.udp_table;
+#endif
+
+ afinfo = pde_data(file_inode(seq->file));
return afinfo->udp_table ? : net->ipv4.udp_table;
}
@@ -2995,16 +2974,10 @@ static struct sock *udp_get_first(struct seq_file *seq, int start)
{
struct udp_iter_state *state = seq->private;
struct net *net = seq_file_net(seq);
- struct udp_seq_afinfo *afinfo;
struct udp_table *udptable;
struct sock *sk;
- if (state->bpf_seq_afinfo)
- afinfo = state->bpf_seq_afinfo;
- else
- afinfo = pde_data(file_inode(seq->file));
-
- udptable = udp_get_table_afinfo(afinfo, net);
+ udptable = udp_get_table_seq(seq, net);
for (state->bucket = start; state->bucket <= udptable->mask;
++state->bucket) {
@@ -3015,10 +2988,7 @@ static struct sock *udp_get_first(struct seq_file *seq, int start)
spin_lock_bh(&hslot->lock);
sk_for_each(sk, &hslot->head) {
- if (!net_eq(sock_net(sk), net))
- continue;
- if (afinfo->family == AF_UNSPEC ||
- sk->sk_family == afinfo->family)
+ if (seq_sk_match(seq, sk))
goto found;
}
spin_unlock_bh(&hslot->lock);
@@ -3032,22 +3002,14 @@ static struct sock *udp_get_next(struct seq_file *seq, struct sock *sk)
{
struct udp_iter_state *state = seq->private;
struct net *net = seq_file_net(seq);
- struct udp_seq_afinfo *afinfo;
struct udp_table *udptable;
- if (state->bpf_seq_afinfo)
- afinfo = state->bpf_seq_afinfo;
- else
- afinfo = pde_data(file_inode(seq->file));
-
do {
sk = sk_next(sk);
- } while (sk && (!net_eq(sock_net(sk), net) ||
- (afinfo->family != AF_UNSPEC &&
- sk->sk_family != afinfo->family)));
+ } while (sk && !seq_sk_match(seq, sk));
if (!sk) {
- udptable = udp_get_table_afinfo(afinfo, net);
+ udptable = udp_get_table_seq(seq, net);
if (state->bucket <= udptable->mask)
spin_unlock_bh(&udptable->hash[state->bucket].lock);
@@ -3093,15 +3055,9 @@ EXPORT_SYMBOL(udp_seq_next);
void udp_seq_stop(struct seq_file *seq, void *v)
{
struct udp_iter_state *state = seq->private;
- struct udp_seq_afinfo *afinfo;
struct udp_table *udptable;
- if (state->bpf_seq_afinfo)
- afinfo = state->bpf_seq_afinfo;
- else
- afinfo = pde_data(file_inode(seq->file));
-
- udptable = udp_get_table_afinfo(afinfo, seq_file_net(seq));
+ udptable = udp_get_table_seq(seq, seq_file_net(seq));
if (state->bucket <= udptable->mask)
spin_unlock_bh(&udptable->hash[state->bucket].lock);
@@ -3154,6 +3110,143 @@ struct bpf_iter__udp {
int bucket __aligned(8);
};
+struct bpf_udp_iter_state {
+ struct udp_iter_state state;
+ unsigned int cur_sk;
+ unsigned int end_sk;
+ unsigned int max_sk;
+ int offset;
+ struct sock **batch;
+ bool st_bucket_done;
+};
+
+static int bpf_iter_udp_realloc_batch(struct bpf_udp_iter_state *iter,
+ unsigned int new_batch_sz);
+static struct sock *bpf_iter_udp_batch(struct seq_file *seq)
+{
+ struct bpf_udp_iter_state *iter = seq->private;
+ struct udp_iter_state *state = &iter->state;
+ struct net *net = seq_file_net(seq);
+ struct udp_table *udptable;
+ unsigned int batch_sks = 0;
+ bool resized = false;
+ struct sock *sk;
+
+ /* The current batch is done, so advance the bucket. */
+ if (iter->st_bucket_done) {
+ state->bucket++;
+ iter->offset = 0;
+ }
+
+ udptable = udp_get_table_seq(seq, net);
+
+again:
+ /* New batch for the next bucket.
+ * Iterate over the hash table to find a bucket with sockets matching
+ * the iterator attributes, and return the first matching socket from
+ * the bucket. The remaining matched sockets from the bucket are batched
+ * before releasing the bucket lock. This allows BPF programs that are
+ * called in seq_show to acquire the bucket lock if needed.
+ */
+ iter->cur_sk = 0;
+ iter->end_sk = 0;
+ iter->st_bucket_done = false;
+ batch_sks = 0;
+
+ for (; state->bucket <= udptable->mask; state->bucket++) {
+ struct udp_hslot *hslot2 = &udptable->hash2[state->bucket];
+
+ if (hlist_empty(&hslot2->head)) {
+ iter->offset = 0;
+ continue;
+ }
+
+ spin_lock_bh(&hslot2->lock);
+ udp_portaddr_for_each_entry(sk, &hslot2->head) {
+ if (seq_sk_match(seq, sk)) {
+ /* Resume from the last iterated socket at the
+ * offset in the bucket before iterator was stopped.
+ */
+ if (iter->offset) {
+ --iter->offset;
+ continue;
+ }
+ if (iter->end_sk < iter->max_sk) {
+ sock_hold(sk);
+ iter->batch[iter->end_sk++] = sk;
+ }
+ batch_sks++;
+ }
+ }
+ spin_unlock_bh(&hslot2->lock);
+
+ if (iter->end_sk)
+ break;
+
+ /* Reset the current bucket's offset before moving to the next bucket. */
+ iter->offset = 0;
+ }
+
+ /* All done: no batch made. */
+ if (!iter->end_sk)
+ return NULL;
+
+ if (iter->end_sk == batch_sks) {
+ /* Batching is done for the current bucket; return the first
+ * socket to be iterated from the batch.
+ */
+ iter->st_bucket_done = true;
+ goto done;
+ }
+ if (!resized && !bpf_iter_udp_realloc_batch(iter, batch_sks * 3 / 2)) {
+ resized = true;
+ /* After allocating a larger batch, retry one more time to grab
+ * the whole bucket.
+ */
+ state->bucket--;
+ goto again;
+ }
+done:
+ return iter->batch[0];
+}
+
+static void *bpf_iter_udp_seq_next(struct seq_file *seq, void *v, loff_t *pos)
+{
+ struct bpf_udp_iter_state *iter = seq->private;
+ struct sock *sk;
+
+ /* Whenever seq_next() is called, the iter->cur_sk is
+ * done with seq_show(), so unref the iter->cur_sk.
+ */
+ if (iter->cur_sk < iter->end_sk) {
+ sock_put(iter->batch[iter->cur_sk++]);
+ ++iter->offset;
+ }
+
+ /* After updating iter->cur_sk, check if there are more sockets
+ * available in the current bucket batch.
+ */
+ if (iter->cur_sk < iter->end_sk)
+ sk = iter->batch[iter->cur_sk];
+ else
+ /* Prepare a new batch. */
+ sk = bpf_iter_udp_batch(seq);
+
+ ++*pos;
+ return sk;
+}
+
+static void *bpf_iter_udp_seq_start(struct seq_file *seq, loff_t *pos)
+{
+ /* bpf iter does not support lseek, so it always
+ * continue from where it was stop()-ped.
+ */
+ if (*pos)
+ return bpf_iter_udp_batch(seq);
+
+ return SEQ_START_TOKEN;
+}
+
static int udp_prog_seq_show(struct bpf_prog *prog, struct bpf_iter_meta *meta,
struct udp_sock *udp_sk, uid_t uid, int bucket)
{
@@ -3174,18 +3267,37 @@ static int bpf_iter_udp_seq_show(struct seq_file *seq, void *v)
struct bpf_prog *prog;
struct sock *sk = v;
uid_t uid;
+ int ret;
if (v == SEQ_START_TOKEN)
return 0;
+ lock_sock(sk);
+
+ if (unlikely(sk_unhashed(sk))) {
+ ret = SEQ_SKIP;
+ goto unlock;
+ }
+
uid = from_kuid_munged(seq_user_ns(seq), sock_i_uid(sk));
meta.seq = seq;
prog = bpf_iter_get_info(&meta, false);
- return udp_prog_seq_show(prog, &meta, v, uid, state->bucket);
+ ret = udp_prog_seq_show(prog, &meta, v, uid, state->bucket);
+
+unlock:
+ release_sock(sk);
+ return ret;
+}
+
+static void bpf_iter_udp_put_batch(struct bpf_udp_iter_state *iter)
+{
+ while (iter->cur_sk < iter->end_sk)
+ sock_put(iter->batch[iter->cur_sk++]);
}
static void bpf_iter_udp_seq_stop(struct seq_file *seq, void *v)
{
+ struct bpf_udp_iter_state *iter = seq->private;
struct bpf_iter_meta meta;
struct bpf_prog *prog;
@@ -3196,17 +3308,35 @@ static void bpf_iter_udp_seq_stop(struct seq_file *seq, void *v)
(void)udp_prog_seq_show(prog, &meta, v, 0, 0);
}
- udp_seq_stop(seq, v);
+ if (iter->cur_sk < iter->end_sk) {
+ bpf_iter_udp_put_batch(iter);
+ iter->st_bucket_done = false;
+ }
}
static const struct seq_operations bpf_iter_udp_seq_ops = {
- .start = udp_seq_start,
- .next = udp_seq_next,
+ .start = bpf_iter_udp_seq_start,
+ .next = bpf_iter_udp_seq_next,
.stop = bpf_iter_udp_seq_stop,
.show = bpf_iter_udp_seq_show,
};
#endif
+static unsigned short seq_file_family(const struct seq_file *seq)
+{
+ const struct udp_seq_afinfo *afinfo;
+
+#ifdef CONFIG_BPF_SYSCALL
+ /* BPF iterator: bpf programs to filter sockets. */
+ if (seq->op == &bpf_iter_udp_seq_ops)
+ return AF_UNSPEC;
+#endif
+
+ /* Proc fs iterator */
+ afinfo = pde_data(file_inode(seq->file));
+ return afinfo->family;
+}
+
const struct seq_operations udp_seq_ops = {
.start = udp_seq_start,
.next = udp_seq_next,
@@ -3415,38 +3545,55 @@ static struct pernet_operations __net_initdata udp_sysctl_ops = {
DEFINE_BPF_ITER_FUNC(udp, struct bpf_iter_meta *meta,
struct udp_sock *udp_sk, uid_t uid, int bucket)
-static int bpf_iter_init_udp(void *priv_data, struct bpf_iter_aux_info *aux)
+static int bpf_iter_udp_realloc_batch(struct bpf_udp_iter_state *iter,
+ unsigned int new_batch_sz)
{
- struct udp_iter_state *st = priv_data;
- struct udp_seq_afinfo *afinfo;
- int ret;
+ struct sock **new_batch;
- afinfo = kmalloc(sizeof(*afinfo), GFP_USER | __GFP_NOWARN);
- if (!afinfo)
+ new_batch = kvmalloc_array(new_batch_sz, sizeof(*new_batch),
+ GFP_USER | __GFP_NOWARN);
+ if (!new_batch)
return -ENOMEM;
- afinfo->family = AF_UNSPEC;
- afinfo->udp_table = NULL;
- st->bpf_seq_afinfo = afinfo;
+ bpf_iter_udp_put_batch(iter);
+ kvfree(iter->batch);
+ iter->batch = new_batch;
+ iter->max_sk = new_batch_sz;
+
+ return 0;
+}
+
+#define INIT_BATCH_SZ 16
+
+static int bpf_iter_init_udp(void *priv_data, struct bpf_iter_aux_info *aux)
+{
+ struct bpf_udp_iter_state *iter = priv_data;
+ int ret;
+
ret = bpf_iter_init_seq_net(priv_data, aux);
if (ret)
- kfree(afinfo);
+ return ret;
+
+ ret = bpf_iter_udp_realloc_batch(iter, INIT_BATCH_SZ);
+ if (ret)
+ bpf_iter_fini_seq_net(priv_data);
+
return ret;
}
static void bpf_iter_fini_udp(void *priv_data)
{
- struct udp_iter_state *st = priv_data;
+ struct bpf_udp_iter_state *iter = priv_data;
- kfree(st->bpf_seq_afinfo);
bpf_iter_fini_seq_net(priv_data);
+ kvfree(iter->batch);
}
static const struct bpf_iter_seq_info udp_seq_info = {
.seq_ops = &bpf_iter_udp_seq_ops,
.init_seq_private = bpf_iter_init_udp,
.fini_seq_private = bpf_iter_fini_udp,
- .seq_priv_size = sizeof(struct udp_iter_state),
+ .seq_priv_size = sizeof(struct bpf_udp_iter_state),
};
static struct bpf_iter_reg udp_reg_info = {
@@ -3454,7 +3601,7 @@ static struct bpf_iter_reg udp_reg_info = {
.ctx_arg_info_size = 1,
.ctx_arg_info = {
{ offsetof(struct bpf_iter__udp, udp_sk),
- PTR_TO_BTF_ID_OR_NULL },
+ PTR_TO_BTF_ID_OR_NULL | PTR_TRUSTED },
},
.seq_info = &udp_seq_info,
};
diff --git a/net/ipv4/udp_impl.h b/net/ipv4/udp_impl.h
index 4ba7a88a1b1d..e1ff3a375996 100644
--- a/net/ipv4/udp_impl.h
+++ b/net/ipv4/udp_impl.h
@@ -19,8 +19,6 @@ int udp_getsockopt(struct sock *sk, int level, int optname,
int udp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int flags,
int *addr_len);
-int udp_sendpage(struct sock *sk, struct page *page, int offset, size_t size,
- int flags);
void udp_destroy_sock(struct sock *sk);
#ifdef CONFIG_PROC_FS
diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c
index 1f01e15ca24f..75aa4de5b731 100644
--- a/net/ipv4/udp_offload.c
+++ b/net/ipv4/udp_offload.c
@@ -8,6 +8,7 @@
#include <linux/skbuff.h>
#include <net/gro.h>
+#include <net/gso.h>
#include <net/udp.h>
#include <net/protocol.h>
#include <net/inet_common.h>
diff --git a/net/ipv4/udplite.c b/net/ipv4/udplite.c
index 143f93a12f25..39ecdad1b50c 100644
--- a/net/ipv4/udplite.c
+++ b/net/ipv4/udplite.c
@@ -56,7 +56,6 @@ struct proto udplite_prot = {
.getsockopt = udp_getsockopt,
.sendmsg = udp_sendmsg,
.recvmsg = udp_recvmsg,
- .sendpage = udp_sendpage,
.hash = udp_lib_hash,
.unhash = udp_lib_unhash,
.rehash = udp_v4_rehash,
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index 3797917237d0..5479da08ef40 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -3633,8 +3633,8 @@ static int addrconf_notify(struct notifier_block *this, unsigned long event,
idev->if_flags |= IF_READY;
}
- pr_info("ADDRCONF(NETDEV_CHANGE): %s: link becomes ready\n",
- dev->name);
+ pr_debug("ADDRCONF(NETDEV_CHANGE): %s: link becomes ready\n",
+ dev->name);
run_pending = 1;
}
diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c
index 2bbf13216a3d..5d593ddc0347 100644
--- a/net/ipv6/af_inet6.c
+++ b/net/ipv6/af_inet6.c
@@ -579,7 +579,7 @@ int inet6_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg)
prot = READ_ONCE(sk->sk_prot);
if (!prot->ioctl)
return -ENOIOCTLCMD;
- return prot->ioctl(sk, cmd, arg);
+ return sk_ioctl(sk, cmd, (void __user *)arg);
}
/*NOTREACHED*/
return 0;
@@ -695,9 +695,8 @@ const struct proto_ops inet6_stream_ops = {
#ifdef CONFIG_MMU
.mmap = tcp_mmap,
#endif
- .sendpage = inet_sendpage,
+ .splice_eof = inet_splice_eof,
.sendmsg_locked = tcp_sendmsg_locked,
- .sendpage_locked = tcp_sendpage_locked,
.splice_read = tcp_splice_read,
.read_sock = tcp_read_sock,
.read_skb = tcp_read_skb,
@@ -728,7 +727,6 @@ const struct proto_ops inet6_dgram_ops = {
.recvmsg = inet6_recvmsg, /* retpoline's sake */
.read_skb = udp_read_skb,
.mmap = sock_no_mmap,
- .sendpage = sock_no_sendpage,
.set_peek_off = sk_set_peek_off,
#ifdef CONFIG_COMPAT
.compat_ioctl = inet6_compat_ioctl,
diff --git a/net/ipv6/esp6_offload.c b/net/ipv6/esp6_offload.c
index 772340268997..a189e08370a5 100644
--- a/net/ipv6/esp6_offload.c
+++ b/net/ipv6/esp6_offload.c
@@ -17,6 +17,7 @@
#include <linux/err.h>
#include <linux/module.h>
#include <net/gro.h>
+#include <net/gso.h>
#include <net/ip.h>
#include <net/xfrm.h>
#include <net/esp.h>
diff --git a/net/ipv6/exthdrs.c b/net/ipv6/exthdrs.c
index 5fa0e37305d9..202fc3aaa83c 100644
--- a/net/ipv6/exthdrs.c
+++ b/net/ipv6/exthdrs.c
@@ -126,9 +126,6 @@ static bool ip6_parse_tlv(bool hopbyhop,
max_count = -max_count;
}
- if (skb_transport_offset(skb) + len > skb_headlen(skb))
- goto bad;
-
off += 2;
len -= 2;
@@ -402,11 +399,7 @@ looped_back:
skb_postpull_rcsum(skb, skb_network_header(skb),
skb_network_header_len(skb));
-
- if (!pskb_pull(skb, offset)) {
- kfree_skb(skb);
- return -1;
- }
+ skb_pull(skb, offset);
skb_postpull_rcsum(skb, skb_transport_header(skb),
offset);
@@ -444,9 +437,9 @@ looped_back:
kfree_skb(skb);
return -1;
}
- }
- hdr = (struct ipv6_sr_hdr *)skb_transport_header(skb);
+ hdr = (struct ipv6_sr_hdr *)skb_transport_header(skb);
+ }
hdr->segments_left--;
addr = hdr->segments + hdr->segments_left;
@@ -458,8 +451,6 @@ looped_back:
ipv6_hdr(skb)->daddr = *addr;
- skb_dst_drop(skb);
-
ip6_route_input(skb);
if (skb_dst(skb)->error) {
@@ -519,11 +510,7 @@ looped_back:
skb_postpull_rcsum(skb, skb_network_header(skb),
skb_network_header_len(skb));
-
- if (!pskb_pull(skb, offset)) {
- kfree_skb(skb);
- return -1;
- }
+ skb_pull(skb, offset);
skb_postpull_rcsum(skb, skb_transport_header(skb),
offset);
@@ -545,11 +532,6 @@ looped_back:
return 1;
}
- if (!pskb_may_pull(skb, sizeof(*hdr))) {
- kfree_skb(skb);
- return -1;
- }
-
n = (hdr->hdrlen << 3) - hdr->pad - (16 - hdr->cmpre);
r = do_div(n, (16 - hdr->cmpri));
/* checks if calculation was without remainder and n fits into
@@ -569,12 +551,6 @@ looped_back:
return -1;
}
- if (!pskb_may_pull(skb, ipv6_rpl_srh_size(n, hdr->cmpri,
- hdr->cmpre))) {
- kfree_skb(skb);
- return -1;
- }
-
hdr->segments_left--;
i = n - hdr->segments_left;
@@ -588,8 +564,7 @@ looped_back:
ipv6_rpl_srh_decompress(ohdr, hdr, &ipv6_hdr(skb)->daddr, n);
chdr = (struct ipv6_rpl_sr_hdr *)(buf + ((ohdr->hdrlen + 1) << 3));
- if ((ipv6_addr_type(&ipv6_hdr(skb)->daddr) & IPV6_ADDR_MULTICAST) ||
- (ipv6_addr_type(&ohdr->rpl_segaddr[i]) & IPV6_ADDR_MULTICAST)) {
+ if (ipv6_addr_is_multicast(&ohdr->rpl_segaddr[i])) {
kfree_skb(skb);
kfree(buf);
return -1;
@@ -827,7 +802,6 @@ looped_back:
*addr = ipv6_hdr(skb)->daddr;
ipv6_hdr(skb)->daddr = daddr;
- skb_dst_drop(skb);
ip6_route_input(skb);
if (skb_dst(skb)->error) {
skb_push(skb, skb->data - skb_network_header(skb));
diff --git a/net/ipv6/ip6_offload.c b/net/ipv6/ip6_offload.c
index 00dc2e3b0184..d6314287338d 100644
--- a/net/ipv6/ip6_offload.c
+++ b/net/ipv6/ip6_offload.c
@@ -16,6 +16,7 @@
#include <net/tcp.h>
#include <net/udp.h>
#include <net/gro.h>
+#include <net/gso.h>
#include "ip6_offload.h"
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index 9554cf46ed88..1e8c90e97608 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -42,6 +42,7 @@
#include <net/sock.h>
#include <net/snmp.h>
+#include <net/gso.h>
#include <net/ipv6.h>
#include <net/ndisc.h>
#include <net/protocol.h>
@@ -1589,6 +1590,15 @@ emsgsize:
skb_zcopy_set(skb, uarg, &extra_uref);
}
}
+ } else if ((flags & MSG_SPLICE_PAGES) && length) {
+ if (inet_sk(sk)->hdrincl)
+ return -EPERM;
+ if (rt->dst.dev->features & NETIF_F_SG &&
+ getfrag == ip_generic_getfrag)
+ /* We need an empty buffer to attach stuff to */
+ paged = true;
+ else
+ flags &= ~MSG_SPLICE_PAGES;
}
/*
@@ -1778,6 +1788,15 @@ alloc_new_skb:
err = -EFAULT;
goto error;
}
+ } else if (flags & MSG_SPLICE_PAGES) {
+ struct msghdr *msg = from;
+
+ err = skb_splice_from_iter(skb, &msg->msg_iter, copy,
+ sk->sk_allocation);
+ if (err < 0)
+ goto error;
+ copy = err;
+ wmem_alloc_delta += copy;
} else if (!zc) {
int i = skb_shinfo(skb)->nr_frags;
diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c
index 51cf37abd142..cc3d5ad17257 100644
--- a/net/ipv6/ip6mr.c
+++ b/net/ipv6/ip6mr.c
@@ -1879,11 +1879,10 @@ int ip6_mroute_getsockopt(struct sock *sk, int optname, sockptr_t optval,
/*
* The IP multicast ioctl support routines.
*/
-
-int ip6mr_ioctl(struct sock *sk, int cmd, void __user *arg)
+int ip6mr_ioctl(struct sock *sk, int cmd, void *arg)
{
- struct sioc_sg_req6 sr;
- struct sioc_mif_req6 vr;
+ struct sioc_sg_req6 *sr;
+ struct sioc_mif_req6 *vr;
struct vif_device *vif;
struct mfc6_cache *c;
struct net *net = sock_net(sk);
@@ -1895,40 +1894,33 @@ int ip6mr_ioctl(struct sock *sk, int cmd, void __user *arg)
switch (cmd) {
case SIOCGETMIFCNT_IN6:
- if (copy_from_user(&vr, arg, sizeof(vr)))
- return -EFAULT;
- if (vr.mifi >= mrt->maxvif)
+ vr = (struct sioc_mif_req6 *)arg;
+ if (vr->mifi >= mrt->maxvif)
return -EINVAL;
- vr.mifi = array_index_nospec(vr.mifi, mrt->maxvif);
+ vr->mifi = array_index_nospec(vr->mifi, mrt->maxvif);
rcu_read_lock();
- vif = &mrt->vif_table[vr.mifi];
- if (VIF_EXISTS(mrt, vr.mifi)) {
- vr.icount = READ_ONCE(vif->pkt_in);
- vr.ocount = READ_ONCE(vif->pkt_out);
- vr.ibytes = READ_ONCE(vif->bytes_in);
- vr.obytes = READ_ONCE(vif->bytes_out);
+ vif = &mrt->vif_table[vr->mifi];
+ if (VIF_EXISTS(mrt, vr->mifi)) {
+ vr->icount = READ_ONCE(vif->pkt_in);
+ vr->ocount = READ_ONCE(vif->pkt_out);
+ vr->ibytes = READ_ONCE(vif->bytes_in);
+ vr->obytes = READ_ONCE(vif->bytes_out);
rcu_read_unlock();
-
- if (copy_to_user(arg, &vr, sizeof(vr)))
- return -EFAULT;
return 0;
}
rcu_read_unlock();
return -EADDRNOTAVAIL;
case SIOCGETSGCNT_IN6:
- if (copy_from_user(&sr, arg, sizeof(sr)))
- return -EFAULT;
+ sr = (struct sioc_sg_req6 *)arg;
rcu_read_lock();
- c = ip6mr_cache_find(mrt, &sr.src.sin6_addr, &sr.grp.sin6_addr);
+ c = ip6mr_cache_find(mrt, &sr->src.sin6_addr,
+ &sr->grp.sin6_addr);
if (c) {
- sr.pktcnt = c->_c.mfc_un.res.pkt;
- sr.bytecnt = c->_c.mfc_un.res.bytes;
- sr.wrong_if = c->_c.mfc_un.res.wrong_if;
+ sr->pktcnt = c->_c.mfc_un.res.pkt;
+ sr->bytecnt = c->_c.mfc_un.res.bytes;
+ sr->wrong_if = c->_c.mfc_un.res.wrong_if;
rcu_read_unlock();
-
- if (copy_to_user(arg, &sr, sizeof(sr)))
- return -EFAULT;
return 0;
}
rcu_read_unlock();
diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c
index 44ee7a2e72ac..ac1cef094c5f 100644
--- a/net/ipv6/raw.c
+++ b/net/ipv6/raw.c
@@ -1118,29 +1118,29 @@ static int rawv6_getsockopt(struct sock *sk, int level, int optname,
return do_rawv6_getsockopt(sk, level, optname, optval, optlen);
}
-static int rawv6_ioctl(struct sock *sk, int cmd, unsigned long arg)
+static int rawv6_ioctl(struct sock *sk, int cmd, int *karg)
{
switch (cmd) {
case SIOCOUTQ: {
- int amount = sk_wmem_alloc_get(sk);
-
- return put_user(amount, (int __user *)arg);
+ *karg = sk_wmem_alloc_get(sk);
+ return 0;
}
case SIOCINQ: {
struct sk_buff *skb;
- int amount = 0;
spin_lock_bh(&sk->sk_receive_queue.lock);
skb = skb_peek(&sk->sk_receive_queue);
if (skb)
- amount = skb->len;
+ *karg = skb->len;
+ else
+ *karg = 0;
spin_unlock_bh(&sk->sk_receive_queue.lock);
- return put_user(amount, (int __user *)arg);
+ return 0;
}
default:
#ifdef CONFIG_IPV6_MROUTE
- return ip6mr_ioctl(sk, cmd, (void __user *)arg);
+ return ip6mr_ioctl(sk, cmd, karg);
#else
return -ENOIOCTLCMD;
#endif
@@ -1296,7 +1296,6 @@ const struct proto_ops inet6_sockraw_ops = {
.sendmsg = inet_sendmsg, /* ok */
.recvmsg = sock_common_recvmsg, /* ok */
.mmap = sock_no_mmap,
- .sendpage = sock_no_sendpage,
#ifdef CONFIG_COMPAT
.compat_ioctl = inet6_compat_ioctl,
#endif
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 392aaa373b66..64e873f5895f 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -3360,6 +3360,7 @@ static int ip6_route_check_nh_onlink(struct net *net,
static int ip6_route_check_nh(struct net *net,
struct fib6_config *cfg,
struct net_device **_dev,
+ netdevice_tracker *dev_tracker,
struct inet6_dev **idev)
{
const struct in6_addr *gw_addr = &cfg->fc_gateway;
@@ -3404,7 +3405,7 @@ static int ip6_route_check_nh(struct net *net,
err = -EHOSTUNREACH;
} else {
*_dev = dev = res.nh->fib_nh_dev;
- dev_hold(dev);
+ netdev_hold(dev, dev_tracker, GFP_ATOMIC);
*idev = in6_dev_get(dev);
}
@@ -3412,7 +3413,9 @@ static int ip6_route_check_nh(struct net *net,
}
static int ip6_validate_gw(struct net *net, struct fib6_config *cfg,
- struct net_device **_dev, struct inet6_dev **idev,
+ struct net_device **_dev,
+ netdevice_tracker *dev_tracker,
+ struct inet6_dev **idev,
struct netlink_ext_ack *extack)
{
const struct in6_addr *gw_addr = &cfg->fc_gateway;
@@ -3453,7 +3456,8 @@ static int ip6_validate_gw(struct net *net, struct fib6_config *cfg,
if (cfg->fc_flags & RTNH_F_ONLINK)
err = ip6_route_check_nh_onlink(net, cfg, dev, extack);
else
- err = ip6_route_check_nh(net, cfg, _dev, idev);
+ err = ip6_route_check_nh(net, cfg, _dev, dev_tracker,
+ idev);
rcu_read_unlock();
@@ -3503,6 +3507,7 @@ int fib6_nh_init(struct net *net, struct fib6_nh *fib6_nh,
struct fib6_config *cfg, gfp_t gfp_flags,
struct netlink_ext_ack *extack)
{
+ netdevice_tracker *dev_tracker = &fib6_nh->fib_nh_dev_tracker;
struct net_device *dev = NULL;
struct inet6_dev *idev = NULL;
int addr_type;
@@ -3520,7 +3525,8 @@ int fib6_nh_init(struct net *net, struct fib6_nh *fib6_nh,
err = -ENODEV;
if (cfg->fc_ifindex) {
- dev = dev_get_by_index(net, cfg->fc_ifindex);
+ dev = netdev_get_by_index(net, cfg->fc_ifindex,
+ dev_tracker, gfp_flags);
if (!dev)
goto out;
idev = in6_dev_get(dev);
@@ -3554,11 +3560,11 @@ int fib6_nh_init(struct net *net, struct fib6_nh *fib6_nh,
/* hold loopback dev/idev if we haven't done so. */
if (dev != net->loopback_dev) {
if (dev) {
- dev_put(dev);
+ netdev_put(dev, dev_tracker);
in6_dev_put(idev);
}
dev = net->loopback_dev;
- dev_hold(dev);
+ netdev_hold(dev, dev_tracker, gfp_flags);
idev = in6_dev_get(dev);
if (!idev) {
err = -ENODEV;
@@ -3569,7 +3575,8 @@ int fib6_nh_init(struct net *net, struct fib6_nh *fib6_nh,
}
if (cfg->fc_flags & RTF_GATEWAY) {
- err = ip6_validate_gw(net, cfg, &dev, &idev, extack);
+ err = ip6_validate_gw(net, cfg, &dev, dev_tracker,
+ &idev, extack);
if (err)
goto out;
@@ -3610,8 +3617,6 @@ pcpu_alloc:
}
fib6_nh->fib_nh_dev = dev;
- netdev_tracker_alloc(dev, &fib6_nh->fib_nh_dev_tracker, gfp_flags);
-
fib6_nh->fib_nh_oif = dev->ifindex;
err = 0;
out:
@@ -3621,7 +3626,7 @@ out:
if (err) {
lwtstate_put(fib6_nh->fib_nh_lws);
fib6_nh->fib_nh_lws = NULL;
- dev_put(dev);
+ netdev_put(dev, dev_tracker);
}
return err;
diff --git a/net/ipv6/rpl.c b/net/ipv6/rpl.c
index d1876f192225..e186998bfbf7 100644
--- a/net/ipv6/rpl.c
+++ b/net/ipv6/rpl.c
@@ -29,13 +29,6 @@ static void *ipv6_rpl_segdata_pos(const struct ipv6_rpl_sr_hdr *hdr, int i)
return (void *)&hdr->rpl_segdata[i * IPV6_PFXTAIL_LEN(hdr->cmpri)];
}
-size_t ipv6_rpl_srh_size(unsigned char n, unsigned char cmpri,
- unsigned char cmpre)
-{
- return sizeof(struct ipv6_rpl_sr_hdr) + (n * IPV6_PFXTAIL_LEN(cmpri)) +
- IPV6_PFXTAIL_LEN(cmpre);
-}
-
void ipv6_rpl_srh_decompress(struct ipv6_rpl_sr_hdr *outhdr,
const struct ipv6_rpl_sr_hdr *inhdr,
const struct in6_addr *daddr, unsigned char n)
diff --git a/net/ipv6/seg6_iptunnel.c b/net/ipv6/seg6_iptunnel.c
index 34db881204d2..03b877ff4558 100644
--- a/net/ipv6/seg6_iptunnel.c
+++ b/net/ipv6/seg6_iptunnel.c
@@ -470,8 +470,6 @@ static int seg6_input_core(struct net *net, struct sock *sk,
dst = dst_cache_get(&slwt->cache);
preempt_enable();
- skb_dst_drop(skb);
-
if (!dst) {
ip6_route_input(skb);
dst = skb_dst(skb);
@@ -482,6 +480,7 @@ static int seg6_input_core(struct net *net, struct sock *sk,
preempt_enable();
}
} else {
+ skb_dst_drop(skb);
skb_dst_set(skb, dst);
}
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 7132eb213a7a..40dd92a2f480 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -93,12 +93,8 @@ static struct tcp_md5sig_key *tcp_v6_md5_do_lookup(const struct sock *sk,
* This avoids a dereference and allow compiler optimizations.
* It is a specialized version of inet6_sk_generic().
*/
-static struct ipv6_pinfo *tcp_inet6_sk(const struct sock *sk)
-{
- unsigned int offset = sizeof(struct tcp6_sock) - sizeof(struct ipv6_pinfo);
-
- return (struct ipv6_pinfo *)(((u8 *)sk) + offset);
-}
+#define tcp_inet6_sk(sk) (&container_of_const(tcp_sk(sk), \
+ struct tcp6_sock, tcp)->inet6)
static void inet6_sk_rx_dst_set(struct sock *sk, const struct sk_buff *skb)
{
@@ -533,7 +529,7 @@ static int tcp_v6_send_synack(const struct sock *sk, struct dst_entry *dst,
struct sk_buff *syn_skb)
{
struct inet_request_sock *ireq = inet_rsk(req);
- struct ipv6_pinfo *np = tcp_inet6_sk(sk);
+ const struct ipv6_pinfo *np = tcp_inet6_sk(sk);
struct ipv6_txoptions *opt;
struct flowi6 *fl6 = &fl->u.ip6;
struct sk_buff *skb;
@@ -2154,7 +2150,7 @@ struct proto tcpv6_prot = {
.keepalive = tcp_set_keepalive,
.recvmsg = tcp_recvmsg,
.sendmsg = tcp_sendmsg,
- .sendpage = tcp_sendpage,
+ .splice_eof = tcp_splice_eof,
.backlog_rcv = tcp_v6_do_rcv,
.release_cb = tcp_release_cb,
.hash = inet6_hash,
diff --git a/net/ipv6/tcpv6_offload.c b/net/ipv6/tcpv6_offload.c
index 39db5a226855..bf0c957e4b5e 100644
--- a/net/ipv6/tcpv6_offload.c
+++ b/net/ipv6/tcpv6_offload.c
@@ -36,7 +36,8 @@ INDIRECT_CALLABLE_SCOPE int tcp6_gro_complete(struct sk_buff *skb, int thoff)
&iph->daddr, 0);
skb_shinfo(skb)->gso_type |= SKB_GSO_TCPV6;
- return tcp_gro_complete(skb);
+ tcp_gro_complete(skb);
+ return 0;
}
static struct sk_buff *tcp6_gso_segment(struct sk_buff *skb,
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index e5a337e6b970..317b01c9bc39 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -1653,6 +1653,20 @@ do_confirm:
}
EXPORT_SYMBOL(udpv6_sendmsg);
+static void udpv6_splice_eof(struct socket *sock)
+{
+ struct sock *sk = sock->sk;
+ struct udp_sock *up = udp_sk(sk);
+
+ if (!up->pending || READ_ONCE(up->corkflag))
+ return;
+
+ lock_sock(sk);
+ if (up->pending && !READ_ONCE(up->corkflag))
+ udp_v6_push_pending_frames(sk);
+ release_sock(sk);
+}
+
void udpv6_destroy_sock(struct sock *sk)
{
struct udp_sock *up = udp_sk(sk);
@@ -1764,6 +1778,7 @@ struct proto udpv6_prot = {
.getsockopt = udpv6_getsockopt,
.sendmsg = udpv6_sendmsg,
.recvmsg = udpv6_recvmsg,
+ .splice_eof = udpv6_splice_eof,
.release_cb = ip6_datagram_release_cb,
.hash = udp_lib_hash,
.unhash = udp_lib_unhash,
diff --git a/net/ipv6/udp_offload.c b/net/ipv6/udp_offload.c
index c39c1e32f980..ad3b8726873e 100644
--- a/net/ipv6/udp_offload.c
+++ b/net/ipv6/udp_offload.c
@@ -14,6 +14,7 @@
#include <net/ip6_checksum.h>
#include "ip6_offload.h"
#include <net/gro.h>
+#include <net/gso.h>
static struct sk_buff *udp6_ufo_fragment(struct sk_buff *skb,
netdev_features_t features)
diff --git a/net/kcm/kcmsock.c b/net/kcm/kcmsock.c
index cfe828bd7fc6..393f01b2a7e6 100644
--- a/net/kcm/kcmsock.c
+++ b/net/kcm/kcmsock.c
@@ -581,12 +581,10 @@ static void kcm_report_tx_retry(struct kcm_sock *kcm)
*/
static int kcm_write_msgs(struct kcm_sock *kcm)
{
+ unsigned int total_sent = 0;
struct sock *sk = &kcm->sk;
struct kcm_psock *psock;
- struct sk_buff *skb, *head;
- struct kcm_tx_msg *txm;
- unsigned short fragidx, frag_offset;
- unsigned int sent, total_sent = 0;
+ struct sk_buff *head;
int ret = 0;
kcm->tx_wait_more = false;
@@ -600,72 +598,57 @@ static int kcm_write_msgs(struct kcm_sock *kcm)
if (skb_queue_empty(&sk->sk_write_queue))
return 0;
- kcm_tx_msg(skb_peek(&sk->sk_write_queue))->sent = 0;
-
- } else if (skb_queue_empty(&sk->sk_write_queue)) {
- return 0;
+ kcm_tx_msg(skb_peek(&sk->sk_write_queue))->started_tx = false;
}
- head = skb_peek(&sk->sk_write_queue);
- txm = kcm_tx_msg(head);
+retry:
+ while ((head = skb_peek(&sk->sk_write_queue))) {
+ struct msghdr msg = {
+ .msg_flags = MSG_DONTWAIT | MSG_SPLICE_PAGES,
+ };
+ struct kcm_tx_msg *txm = kcm_tx_msg(head);
+ struct sk_buff *skb;
+ unsigned int msize;
+ int i;
- if (txm->sent) {
- /* Send of first skbuff in queue already in progress */
- if (WARN_ON(!psock)) {
- ret = -EINVAL;
- goto out;
+ if (!txm->started_tx) {
+ psock = reserve_psock(kcm);
+ if (!psock)
+ goto out;
+ skb = head;
+ txm->frag_offset = 0;
+ txm->sent = 0;
+ txm->started_tx = true;
+ } else {
+ if (WARN_ON(!psock)) {
+ ret = -EINVAL;
+ goto out;
+ }
+ skb = txm->frag_skb;
}
- sent = txm->sent;
- frag_offset = txm->frag_offset;
- fragidx = txm->fragidx;
- skb = txm->frag_skb;
- goto do_frag;
- }
-
-try_again:
- psock = reserve_psock(kcm);
- if (!psock)
- goto out;
-
- do {
- skb = head;
- txm = kcm_tx_msg(head);
- sent = 0;
-
-do_frag_list:
if (WARN_ON(!skb_shinfo(skb)->nr_frags)) {
ret = -EINVAL;
goto out;
}
- for (fragidx = 0; fragidx < skb_shinfo(skb)->nr_frags;
- fragidx++) {
- skb_frag_t *frag;
+ msize = 0;
+ for (i = 0; i < skb_shinfo(skb)->nr_frags; i++)
+ msize += skb_shinfo(skb)->frags[i].bv_len;
- frag_offset = 0;
-do_frag:
- frag = &skb_shinfo(skb)->frags[fragidx];
- if (WARN_ON(!skb_frag_size(frag))) {
- ret = -EINVAL;
- goto out;
- }
+ iov_iter_bvec(&msg.msg_iter, ITER_SOURCE,
+ skb_shinfo(skb)->frags, skb_shinfo(skb)->nr_frags,
+ msize);
+ iov_iter_advance(&msg.msg_iter, txm->frag_offset);
- ret = kernel_sendpage(psock->sk->sk_socket,
- skb_frag_page(frag),
- skb_frag_off(frag) + frag_offset,
- skb_frag_size(frag) - frag_offset,
- MSG_DONTWAIT);
+ do {
+ ret = sock_sendmsg(psock->sk->sk_socket, &msg);
if (ret <= 0) {
if (ret == -EAGAIN) {
/* Save state to try again when there's
* write space on the socket
*/
- txm->sent = sent;
- txm->frag_offset = frag_offset;
- txm->fragidx = fragidx;
txm->frag_skb = skb;
-
ret = 0;
goto out;
}
@@ -678,45 +661,44 @@ do_frag:
kcm_abort_tx_psock(psock, ret ? -ret : EPIPE,
true);
unreserve_psock(kcm);
+ psock = NULL;
- txm->sent = 0;
+ txm->started_tx = false;
kcm_report_tx_retry(kcm);
ret = 0;
-
- goto try_again;
+ goto retry;
}
- sent += ret;
- frag_offset += ret;
+ txm->sent += ret;
+ txm->frag_offset += ret;
KCM_STATS_ADD(psock->stats.tx_bytes, ret);
- if (frag_offset < skb_frag_size(frag)) {
- /* Not finished with this frag */
- goto do_frag;
- }
- }
+ } while (msg.msg_iter.count > 0);
if (skb == head) {
if (skb_has_frag_list(skb)) {
- skb = skb_shinfo(skb)->frag_list;
- goto do_frag_list;
+ txm->frag_skb = skb_shinfo(skb)->frag_list;
+ txm->frag_offset = 0;
+ continue;
}
} else if (skb->next) {
- skb = skb->next;
- goto do_frag_list;
+ txm->frag_skb = skb->next;
+ txm->frag_offset = 0;
+ continue;
}
/* Successfully sent the whole packet, account for it. */
+ sk->sk_wmem_queued -= txm->sent;
+ total_sent += txm->sent;
skb_dequeue(&sk->sk_write_queue);
kfree_skb(head);
- sk->sk_wmem_queued -= sent;
- total_sent += sent;
KCM_STATS_INCR(psock->stats.tx_msgs);
- } while ((head = skb_peek(&sk->sk_write_queue)));
+ }
out:
if (!head) {
/* Done with all queued messages. */
WARN_ON(!skb_queue_empty(&sk->sk_write_queue));
- unreserve_psock(kcm);
+ if (psock)
+ unreserve_psock(kcm);
}
/* Check if write space is available */
@@ -761,149 +743,6 @@ static void kcm_push(struct kcm_sock *kcm)
kcm_write_msgs(kcm);
}
-static ssize_t kcm_sendpage(struct socket *sock, struct page *page,
- int offset, size_t size, int flags)
-
-{
- struct sock *sk = sock->sk;
- struct kcm_sock *kcm = kcm_sk(sk);
- struct sk_buff *skb = NULL, *head = NULL;
- long timeo = sock_sndtimeo(sk, flags & MSG_DONTWAIT);
- bool eor;
- int err = 0;
- int i;
-
- if (flags & MSG_SENDPAGE_NOTLAST)
- flags |= MSG_MORE;
-
- /* No MSG_EOR from splice, only look at MSG_MORE */
- eor = !(flags & MSG_MORE);
-
- lock_sock(sk);
-
- sk_clear_bit(SOCKWQ_ASYNC_NOSPACE, sk);
-
- err = -EPIPE;
- if (sk->sk_err)
- goto out_error;
-
- if (kcm->seq_skb) {
- /* Previously opened message */
- head = kcm->seq_skb;
- skb = kcm_tx_msg(head)->last_skb;
- i = skb_shinfo(skb)->nr_frags;
-
- if (skb_can_coalesce(skb, i, page, offset)) {
- skb_frag_size_add(&skb_shinfo(skb)->frags[i - 1], size);
- skb_shinfo(skb)->flags |= SKBFL_SHARED_FRAG;
- goto coalesced;
- }
-
- if (i >= MAX_SKB_FRAGS) {
- struct sk_buff *tskb;
-
- tskb = alloc_skb(0, sk->sk_allocation);
- while (!tskb) {
- kcm_push(kcm);
- err = sk_stream_wait_memory(sk, &timeo);
- if (err)
- goto out_error;
- }
-
- if (head == skb)
- skb_shinfo(head)->frag_list = tskb;
- else
- skb->next = tskb;
-
- skb = tskb;
- skb->ip_summed = CHECKSUM_UNNECESSARY;
- i = 0;
- }
- } else {
- /* Call the sk_stream functions to manage the sndbuf mem. */
- if (!sk_stream_memory_free(sk)) {
- kcm_push(kcm);
- set_bit(SOCK_NOSPACE, &sk->sk_socket->flags);
- err = sk_stream_wait_memory(sk, &timeo);
- if (err)
- goto out_error;
- }
-
- head = alloc_skb(0, sk->sk_allocation);
- while (!head) {
- kcm_push(kcm);
- err = sk_stream_wait_memory(sk, &timeo);
- if (err)
- goto out_error;
- }
-
- skb = head;
- i = 0;
- }
-
- get_page(page);
- skb_fill_page_desc_noacc(skb, i, page, offset, size);
- skb_shinfo(skb)->flags |= SKBFL_SHARED_FRAG;
-
-coalesced:
- skb->len += size;
- skb->data_len += size;
- skb->truesize += size;
- sk->sk_wmem_queued += size;
- sk_mem_charge(sk, size);
-
- if (head != skb) {
- head->len += size;
- head->data_len += size;
- head->truesize += size;
- }
-
- if (eor) {
- bool not_busy = skb_queue_empty(&sk->sk_write_queue);
-
- /* Message complete, queue it on send buffer */
- __skb_queue_tail(&sk->sk_write_queue, head);
- kcm->seq_skb = NULL;
- KCM_STATS_INCR(kcm->stats.tx_msgs);
-
- if (flags & MSG_BATCH) {
- kcm->tx_wait_more = true;
- } else if (kcm->tx_wait_more || not_busy) {
- err = kcm_write_msgs(kcm);
- if (err < 0) {
- /* We got a hard error in write_msgs but have
- * already queued this message. Report an error
- * in the socket, but don't affect return value
- * from sendmsg
- */
- pr_warn("KCM: Hard failure on kcm_write_msgs\n");
- report_csk_error(&kcm->sk, -err);
- }
- }
- } else {
- /* Message not complete, save state */
- kcm->seq_skb = head;
- kcm_tx_msg(head)->last_skb = skb;
- }
-
- KCM_STATS_ADD(kcm->stats.tx_bytes, size);
-
- release_sock(sk);
- return size;
-
-out_error:
- kcm_push(kcm);
-
- err = sk_stream_error(sk, flags, err);
-
- /* make sure we wake any epoll edge trigger waiter */
- if (unlikely(skb_queue_len(&sk->sk_write_queue) == 0 && err == -EAGAIN))
- sk->sk_write_space(sk);
-
- release_sock(sk);
- return err;
-}
-
static int kcm_sendmsg(struct socket *sock, struct msghdr *msg, size_t len)
{
struct sock *sk = sock->sk;
@@ -989,29 +828,52 @@ start:
merge = false;
}
- copy = min_t(int, msg_data_left(msg),
- pfrag->size - pfrag->offset);
+ if (msg->msg_flags & MSG_SPLICE_PAGES) {
+ copy = msg_data_left(msg);
+ if (!sk_wmem_schedule(sk, copy))
+ goto wait_for_memory;
- if (!sk_wmem_schedule(sk, copy))
- goto wait_for_memory;
+ err = skb_splice_from_iter(skb, &msg->msg_iter, copy,
+ sk->sk_allocation);
+ if (err < 0) {
+ if (err == -EMSGSIZE)
+ goto wait_for_memory;
+ goto out_error;
+ }
- err = skb_copy_to_page_nocache(sk, &msg->msg_iter, skb,
- pfrag->page,
- pfrag->offset,
- copy);
- if (err)
- goto out_error;
+ copy = err;
+ skb_shinfo(skb)->flags |= SKBFL_SHARED_FRAG;
+ sk_wmem_queued_add(sk, copy);
+ sk_mem_charge(sk, copy);
- /* Update the skb. */
- if (merge) {
- skb_frag_size_add(&skb_shinfo(skb)->frags[i - 1], copy);
+ if (head != skb)
+ head->truesize += copy;
} else {
- skb_fill_page_desc(skb, i, pfrag->page,
- pfrag->offset, copy);
- get_page(pfrag->page);
+ copy = min_t(int, msg_data_left(msg),
+ pfrag->size - pfrag->offset);
+ if (!sk_wmem_schedule(sk, copy))
+ goto wait_for_memory;
+
+ err = skb_copy_to_page_nocache(sk, &msg->msg_iter, skb,
+ pfrag->page,
+ pfrag->offset,
+ copy);
+ if (err)
+ goto out_error;
+
+ /* Update the skb. */
+ if (merge) {
+ skb_frag_size_add(
+ &skb_shinfo(skb)->frags[i - 1], copy);
+ } else {
+ skb_fill_page_desc(skb, i, pfrag->page,
+ pfrag->offset, copy);
+ get_page(pfrag->page);
+ }
+
+ pfrag->offset += copy;
}
- pfrag->offset += copy;
copied += copy;
if (head != skb) {
head->len += copy;
@@ -1088,6 +950,19 @@ out_error:
return err;
}
+static void kcm_splice_eof(struct socket *sock)
+{
+ struct sock *sk = sock->sk;
+ struct kcm_sock *kcm = kcm_sk(sk);
+
+ if (skb_queue_empty_lockless(&sk->sk_write_queue))
+ return;
+
+ lock_sock(sk);
+ kcm_write_msgs(kcm);
+ release_sock(sk);
+}
+
static int kcm_recvmsg(struct socket *sock, struct msghdr *msg,
size_t len, int flags)
{
@@ -1875,7 +1750,7 @@ static const struct proto_ops kcm_dgram_ops = {
.sendmsg = kcm_sendmsg,
.recvmsg = kcm_recvmsg,
.mmap = sock_no_mmap,
- .sendpage = kcm_sendpage,
+ .splice_eof = kcm_splice_eof,
};
static const struct proto_ops kcm_seqpacket_ops = {
@@ -1896,7 +1771,7 @@ static const struct proto_ops kcm_seqpacket_ops = {
.sendmsg = kcm_sendmsg,
.recvmsg = kcm_recvmsg,
.mmap = sock_no_mmap,
- .sendpage = kcm_sendpage,
+ .splice_eof = kcm_splice_eof,
.splice_read = kcm_splice_read,
};
diff --git a/net/key/af_key.c b/net/key/af_key.c
index 31ab12fd720a..ede3c6a60353 100644
--- a/net/key/af_key.c
+++ b/net/key/af_key.c
@@ -3761,7 +3761,6 @@ static const struct proto_ops pfkey_ops = {
.listen = sock_no_listen,
.shutdown = sock_no_shutdown,
.mmap = sock_no_mmap,
- .sendpage = sock_no_sendpage,
/* Now the operations that really occur. */
.release = pfkey_release,
diff --git a/net/l2tp/l2tp_core.h b/net/l2tp/l2tp_core.h
index a88e070b431d..91ebf0a3f499 100644
--- a/net/l2tp/l2tp_core.h
+++ b/net/l2tp/l2tp_core.h
@@ -272,7 +272,7 @@ int l2tp_nl_register_ops(enum l2tp_pwtype pw_type, const struct l2tp_nl_cmd_ops
void l2tp_nl_unregister_ops(enum l2tp_pwtype pw_type);
/* IOCTL helper for IP encap modules. */
-int l2tp_ioctl(struct sock *sk, int cmd, unsigned long arg);
+int l2tp_ioctl(struct sock *sk, int cmd, int *karg);
/* Extract the tunnel structure from a socket's sk_user_data pointer,
* validating the tunnel magic feather.
diff --git a/net/l2tp/l2tp_ip.c b/net/l2tp/l2tp_ip.c
index 41a74fc84ca1..f9073bc7281f 100644
--- a/net/l2tp/l2tp_ip.c
+++ b/net/l2tp/l2tp_ip.c
@@ -562,19 +562,18 @@ out:
return err ? err : copied;
}
-int l2tp_ioctl(struct sock *sk, int cmd, unsigned long arg)
+int l2tp_ioctl(struct sock *sk, int cmd, int *karg)
{
struct sk_buff *skb;
- int amount;
switch (cmd) {
case SIOCOUTQ:
- amount = sk_wmem_alloc_get(sk);
+ *karg = sk_wmem_alloc_get(sk);
break;
case SIOCINQ:
spin_lock_bh(&sk->sk_receive_queue.lock);
skb = skb_peek(&sk->sk_receive_queue);
- amount = skb ? skb->len : 0;
+ *karg = skb ? skb->len : 0;
spin_unlock_bh(&sk->sk_receive_queue.lock);
break;
@@ -582,7 +581,7 @@ int l2tp_ioctl(struct sock *sk, int cmd, unsigned long arg)
return -ENOIOCTLCMD;
}
- return put_user(amount, (int __user *)arg);
+ return 0;
}
EXPORT_SYMBOL_GPL(l2tp_ioctl);
@@ -625,7 +624,6 @@ static const struct proto_ops l2tp_ip_ops = {
.sendmsg = inet_sendmsg,
.recvmsg = sock_common_recvmsg,
.mmap = sock_no_mmap,
- .sendpage = sock_no_sendpage,
};
static struct inet_protosw l2tp_ip_protosw = {
diff --git a/net/l2tp/l2tp_ip6.c b/net/l2tp/l2tp_ip6.c
index 5137ea1861ce..b1623f9c4f92 100644
--- a/net/l2tp/l2tp_ip6.c
+++ b/net/l2tp/l2tp_ip6.c
@@ -751,7 +751,6 @@ static const struct proto_ops l2tp_ip6_ops = {
.sendmsg = inet_sendmsg,
.recvmsg = sock_common_recvmsg,
.mmap = sock_no_mmap,
- .sendpage = sock_no_sendpage,
#ifdef CONFIG_COMPAT
.compat_ioctl = inet6_compat_ioctl,
#endif
diff --git a/net/llc/af_llc.c b/net/llc/af_llc.c
index 9ffbc667be6c..57c35c960b2c 100644
--- a/net/llc/af_llc.c
+++ b/net/llc/af_llc.c
@@ -1232,7 +1232,6 @@ static const struct proto_ops llc_ui_ops = {
.sendmsg = llc_ui_sendmsg,
.recvmsg = llc_ui_recvmsg,
.mmap = sock_no_mmap,
- .sendpage = sock_no_sendpage,
};
static const char llc_proc_err_msg[] __initconst =
diff --git a/net/mac80211/agg-tx.c b/net/mac80211/agg-tx.c
index 3b651e7f5a73..b6b772685881 100644
--- a/net/mac80211/agg-tx.c
+++ b/net/mac80211/agg-tx.c
@@ -9,7 +9,7 @@
* Copyright 2007, Michael Wu <flamingice@sourmilk.net>
* Copyright 2007-2010, Intel Corporation
* Copyright(c) 2015-2017 Intel Deutschland GmbH
- * Copyright (C) 2018 - 2022 Intel Corporation
+ * Copyright (C) 2018 - 2023 Intel Corporation
*/
#include <linux/ieee80211.h>
@@ -457,6 +457,12 @@ static void ieee80211_send_addba_with_timeout(struct sta_info *sta,
u8 tid = tid_tx->tid;
u16 buf_size;
+ if (WARN_ON_ONCE(test_bit(HT_AGG_STATE_STOPPING, &tid_tx->state) ||
+ test_bit(HT_AGG_STATE_WANT_STOP, &tid_tx->state)))
+ return;
+
+ lockdep_assert_held(&sta->ampdu_mlme.mtx);
+
/* activate the timer for the recipient's addBA response */
mod_timer(&tid_tx->addba_resp_timer, jiffies + ADDBA_RESP_INTERVAL);
ht_dbg(sdata, "activated addBA response timer on %pM tid %d\n",
@@ -795,9 +801,15 @@ void ieee80211_start_tx_ba_cb(struct sta_info *sta, int tid,
struct ieee80211_sub_if_data *sdata = sta->sdata;
struct ieee80211_local *local = sdata->local;
+ lockdep_assert_held(&sta->ampdu_mlme.mtx);
+
if (WARN_ON(test_and_set_bit(HT_AGG_STATE_DRV_READY, &tid_tx->state)))
return;
+ if (test_bit(HT_AGG_STATE_STOPPING, &tid_tx->state) ||
+ test_bit(HT_AGG_STATE_WANT_STOP, &tid_tx->state))
+ return;
+
if (!test_bit(HT_AGG_STATE_SENT_ADDBA, &tid_tx->state)) {
ieee80211_send_addba_with_timeout(sta, tid_tx);
/* RESPONSE_RECEIVED state whould trigger the flow again */
diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c
index f2d08dbccfb7..e7ac24603892 100644
--- a/net/mac80211/cfg.c
+++ b/net/mac80211/cfg.c
@@ -35,7 +35,7 @@ ieee80211_link_or_deflink(struct ieee80211_sub_if_data *sdata, int link_id,
* the return value at all (if it's not a pairwise key),
* so in that case (require_valid==false) don't error.
*/
- if (require_valid && sdata->vif.valid_links)
+ if (require_valid && ieee80211_vif_is_mld(&sdata->vif))
return ERR_PTR(-EINVAL);
return &sdata->deflink;
@@ -228,7 +228,7 @@ static int ieee80211_change_iface(struct wiphy *wiphy,
return 0;
/* FIXME: no support for 4-addr MLO yet */
- if (sdata->vif.valid_links)
+ if (ieee80211_vif_is_mld(&sdata->vif))
return -EOPNOTSUPP;
sdata->u.mgd.use_4addr = params->use_4addr;
@@ -913,24 +913,30 @@ static int ieee80211_set_monitor_channel(struct wiphy *wiphy,
if (cfg80211_chandef_identical(&local->monitor_chandef, chandef))
return 0;
- mutex_lock(&local->mtx);
if (local->use_chanctx) {
sdata = wiphy_dereference(local->hw.wiphy,
local->monitor_sdata);
if (sdata) {
+ sdata_lock(sdata);
+ mutex_lock(&local->mtx);
ieee80211_link_release_channel(&sdata->deflink);
ret = ieee80211_link_use_channel(&sdata->deflink,
chandef,
IEEE80211_CHANCTX_EXCLUSIVE);
+ mutex_unlock(&local->mtx);
+ sdata_unlock(sdata);
+ }
+ } else {
+ mutex_lock(&local->mtx);
+ if (local->open_count == local->monitors) {
+ local->_oper_chandef = *chandef;
+ ieee80211_hw_config(local, 0);
}
- } else if (local->open_count == local->monitors) {
- local->_oper_chandef = *chandef;
- ieee80211_hw_config(local, 0);
+ mutex_unlock(&local->mtx);
}
if (ret == 0)
local->monitor_chandef = *chandef;
- mutex_unlock(&local->mtx);
return ret;
}
@@ -1101,18 +1107,20 @@ ieee80211_copy_rnr_beacon(u8 *pos, struct cfg80211_rnr_elems *dst,
return offset;
}
-static int ieee80211_assign_beacon(struct ieee80211_sub_if_data *sdata,
- struct ieee80211_link_data *link,
- struct cfg80211_beacon_data *params,
- const struct ieee80211_csa_settings *csa,
- const struct ieee80211_color_change_settings *cca)
+static int
+ieee80211_assign_beacon(struct ieee80211_sub_if_data *sdata,
+ struct ieee80211_link_data *link,
+ struct cfg80211_beacon_data *params,
+ const struct ieee80211_csa_settings *csa,
+ const struct ieee80211_color_change_settings *cca,
+ u64 *changed)
{
struct cfg80211_mbssid_elems *mbssid = NULL;
struct cfg80211_rnr_elems *rnr = NULL;
struct beacon_data *new, *old;
int new_head_len, new_tail_len;
int size, err;
- u32 changed = BSS_CHANGED_BEACON;
+ u64 _changed = BSS_CHANGED_BEACON;
struct ieee80211_bss_conf *link_conf = link->conf;
old = sdata_dereference(link->u.ap.beacon, sdata);
@@ -1219,7 +1227,7 @@ static int ieee80211_assign_beacon(struct ieee80211_sub_if_data *sdata,
return err;
}
if (err == 0)
- changed |= BSS_CHANGED_AP_PROBE_RESP;
+ _changed |= BSS_CHANGED_AP_PROBE_RESP;
if (params->ftm_responder != -1) {
link_conf->ftm_responder = params->ftm_responder;
@@ -1235,7 +1243,7 @@ static int ieee80211_assign_beacon(struct ieee80211_sub_if_data *sdata,
return err;
}
- changed |= BSS_CHANGED_FTM_RESPONDER;
+ _changed |= BSS_CHANGED_FTM_RESPONDER;
}
rcu_assign_pointer(link->u.ap.beacon, new);
@@ -1244,7 +1252,8 @@ static int ieee80211_assign_beacon(struct ieee80211_sub_if_data *sdata,
if (old)
kfree_rcu(old, rcu_head);
- return changed;
+ *changed |= _changed;
+ return 0;
}
static int ieee80211_start_ap(struct wiphy *wiphy, struct net_device *dev,
@@ -1446,10 +1455,10 @@ static int ieee80211_start_ap(struct wiphy *wiphy, struct net_device *dev,
if (ieee80211_hw_check(&local->hw, HAS_RATE_CONTROL))
link_conf->beacon_tx_rate = params->beacon_rate;
- err = ieee80211_assign_beacon(sdata, link, &params->beacon, NULL, NULL);
+ err = ieee80211_assign_beacon(sdata, link, &params->beacon, NULL, NULL,
+ &changed);
if (err < 0)
goto error;
- changed |= err;
if (params->fils_discovery.max_interval) {
err = ieee80211_set_fils_discovery(sdata,
@@ -1506,6 +1515,7 @@ static int ieee80211_change_beacon(struct wiphy *wiphy, struct net_device *dev,
struct beacon_data *old;
int err;
struct ieee80211_bss_conf *link_conf;
+ u64 changed = 0;
sdata_assert_lock(sdata);
@@ -1525,17 +1535,18 @@ static int ieee80211_change_beacon(struct wiphy *wiphy, struct net_device *dev,
if (!old)
return -ENOENT;
- err = ieee80211_assign_beacon(sdata, link, params, NULL, NULL);
+ err = ieee80211_assign_beacon(sdata, link, params, NULL, NULL,
+ &changed);
if (err < 0)
return err;
if (params->he_bss_color_valid &&
params->he_bss_color.enabled != link_conf->he_bss_color.enabled) {
link_conf->he_bss_color.enabled = params->he_bss_color.enabled;
- err |= BSS_CHANGED_HE_BSS_COLOR;
+ changed |= BSS_CHANGED_HE_BSS_COLOR;
}
- ieee80211_link_info_change_notify(sdata, link, err);
+ ieee80211_link_info_change_notify(sdata, link, changed);
return 0;
}
@@ -1718,7 +1729,7 @@ static void sta_apply_mesh_params(struct ieee80211_local *local,
{
#ifdef CONFIG_MAC80211_MESH
struct ieee80211_sub_if_data *sdata = sta->sdata;
- u32 changed = 0;
+ u64 changed = 0;
if (params->sta_modify_mask & STATION_PARAM_APPLY_PLINK_STATE) {
switch (params->plink_state) {
@@ -2665,7 +2676,7 @@ static int ieee80211_change_bss(struct wiphy *wiphy,
struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev);
struct ieee80211_link_data *link;
struct ieee80211_supported_band *sband;
- u32 changed = 0;
+ u64 changed = 0;
link = ieee80211_link_or_deflink(sdata, params->link_id, true);
if (IS_ERR(link))
@@ -3585,7 +3596,7 @@ void ieee80211_channel_switch_disconnect(struct ieee80211_vif *vif, bool block_t
sdata->deflink.csa_block_tx = block_tx;
sdata_info(sdata, "channel switch failed, disconnecting\n");
- ieee80211_queue_work(&local->hw, &ifmgd->csa_connection_drop_work);
+ wiphy_work_queue(local->hw.wiphy, &ifmgd->csa_connection_drop_work);
}
EXPORT_SYMBOL(ieee80211_channel_switch_disconnect);
@@ -3601,25 +3612,22 @@ static int ieee80211_set_after_csa_beacon(struct ieee80211_sub_if_data *sdata,
err = ieee80211_assign_beacon(sdata, &sdata->deflink,
sdata->deflink.u.ap.next_beacon,
- NULL, NULL);
+ NULL, NULL, changed);
ieee80211_free_next_beacon(&sdata->deflink);
if (err < 0)
return err;
- *changed |= err;
break;
case NL80211_IFTYPE_ADHOC:
- err = ieee80211_ibss_finish_csa(sdata);
+ err = ieee80211_ibss_finish_csa(sdata, changed);
if (err < 0)
return err;
- *changed |= err;
break;
#ifdef CONFIG_MAC80211_MESH
case NL80211_IFTYPE_MESH_POINT:
- err = ieee80211_mesh_finish_csa(sdata);
+ err = ieee80211_mesh_finish_csa(sdata, changed);
if (err < 0)
return err;
- *changed |= err;
break;
#endif
default:
@@ -3730,7 +3738,7 @@ unlock:
static int ieee80211_set_csa_beacon(struct ieee80211_sub_if_data *sdata,
struct cfg80211_csa_settings *params,
- u32 *changed)
+ u64 *changed)
{
struct ieee80211_csa_settings csa = {};
int err;
@@ -3777,12 +3785,11 @@ static int ieee80211_set_csa_beacon(struct ieee80211_sub_if_data *sdata,
err = ieee80211_assign_beacon(sdata, &sdata->deflink,
&params->beacon_csa, &csa,
- NULL);
+ NULL, changed);
if (err < 0) {
ieee80211_free_next_beacon(&sdata->deflink);
return err;
}
- *changed |= err;
break;
case NL80211_IFTYPE_ADHOC:
@@ -3814,10 +3821,9 @@ static int ieee80211_set_csa_beacon(struct ieee80211_sub_if_data *sdata,
/* see comments in the NL80211_IFTYPE_AP block */
if (params->count > 1) {
- err = ieee80211_ibss_csa_beacon(sdata, params);
+ err = ieee80211_ibss_csa_beacon(sdata, params, changed);
if (err < 0)
return err;
- *changed |= err;
}
ieee80211_send_action_csa(sdata, params);
@@ -3842,12 +3848,11 @@ static int ieee80211_set_csa_beacon(struct ieee80211_sub_if_data *sdata,
/* see comments in the NL80211_IFTYPE_AP block */
if (params->count > 1) {
- err = ieee80211_mesh_csa_beacon(sdata, params);
+ err = ieee80211_mesh_csa_beacon(sdata, params, changed);
if (err < 0) {
ifmsh->csa_role = IEEE80211_MESH_CSA_ROLE_NONE;
return err;
}
- *changed |= err;
}
if (ifmsh->csa_role == IEEE80211_MESH_CSA_ROLE_INIT)
@@ -3881,7 +3886,7 @@ __ieee80211_channel_switch(struct wiphy *wiphy, struct net_device *dev,
struct ieee80211_channel_switch ch_switch;
struct ieee80211_chanctx_conf *conf;
struct ieee80211_chanctx *chanctx;
- u32 changed = 0;
+ u64 changed = 0;
int err;
sdata_assert_lock(sdata);
@@ -4614,7 +4619,7 @@ static int ieee80211_set_sar_specs(struct wiphy *wiphy,
static int
ieee80211_set_after_color_change_beacon(struct ieee80211_sub_if_data *sdata,
- u32 *changed)
+ u64 *changed)
{
switch (sdata->vif.type) {
case NL80211_IFTYPE_AP: {
@@ -4625,13 +4630,12 @@ ieee80211_set_after_color_change_beacon(struct ieee80211_sub_if_data *sdata,
ret = ieee80211_assign_beacon(sdata, &sdata->deflink,
sdata->deflink.u.ap.next_beacon,
- NULL, NULL);
+ NULL, NULL, changed);
ieee80211_free_next_beacon(&sdata->deflink);
if (ret < 0)
return ret;
- *changed |= ret;
break;
}
default:
@@ -4645,7 +4649,7 @@ ieee80211_set_after_color_change_beacon(struct ieee80211_sub_if_data *sdata,
static int
ieee80211_set_color_change_beacon(struct ieee80211_sub_if_data *sdata,
struct cfg80211_color_change_settings *params,
- u32 *changed)
+ u64 *changed)
{
struct ieee80211_color_change_settings color_change = {};
int err;
@@ -4668,12 +4672,11 @@ ieee80211_set_color_change_beacon(struct ieee80211_sub_if_data *sdata,
err = ieee80211_assign_beacon(sdata, &sdata->deflink,
&params->beacon_color_change,
- NULL, &color_change);
+ NULL, &color_change, changed);
if (err < 0) {
ieee80211_free_next_beacon(&sdata->deflink);
return err;
}
- *changed |= err;
break;
default:
return -EOPNOTSUPP;
@@ -4684,7 +4687,7 @@ ieee80211_set_color_change_beacon(struct ieee80211_sub_if_data *sdata,
static void
ieee80211_color_change_bss_config_notify(struct ieee80211_sub_if_data *sdata,
- u8 color, int enable, u32 changed)
+ u8 color, int enable, u64 changed)
{
sdata->vif.bss_conf.he_bss_color.color = color;
sdata->vif.bss_conf.he_bss_color.enabled = enable;
@@ -4712,7 +4715,7 @@ ieee80211_color_change_bss_config_notify(struct ieee80211_sub_if_data *sdata,
static int ieee80211_color_change_finalize(struct ieee80211_sub_if_data *sdata)
{
struct ieee80211_local *local = sdata->local;
- u32 changed = 0;
+ u64 changed = 0;
int err;
sdata_assert_lock(sdata);
@@ -4809,7 +4812,7 @@ ieee80211_color_change(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;
- u32 changed = 0;
+ u64 changed = 0;
int err;
sdata_assert_lock(sdata);
@@ -4871,7 +4874,7 @@ static int ieee80211_add_intf_link(struct wiphy *wiphy,
return -EOPNOTSUPP;
mutex_lock(&sdata->local->mtx);
- res = ieee80211_vif_set_links(sdata, wdev->valid_links);
+ res = ieee80211_vif_set_links(sdata, wdev->valid_links, 0);
mutex_unlock(&sdata->local->mtx);
return res;
@@ -4884,7 +4887,7 @@ static void ieee80211_del_intf_link(struct wiphy *wiphy,
struct ieee80211_sub_if_data *sdata = IEEE80211_WDEV_TO_SUB_IF(wdev);
mutex_lock(&sdata->local->mtx);
- ieee80211_vif_set_links(sdata, wdev->valid_links);
+ ieee80211_vif_set_links(sdata, wdev->valid_links, 0);
mutex_unlock(&sdata->local->mtx);
}
@@ -5053,6 +5056,7 @@ const struct cfg80211_ops mac80211_config_ops = {
.join_ocb = ieee80211_join_ocb,
.leave_ocb = ieee80211_leave_ocb,
.change_bss = ieee80211_change_bss,
+ .inform_bss = ieee80211_inform_bss,
.set_txq_params = ieee80211_set_txq_params,
.set_monitor_channel = ieee80211_set_monitor_channel,
.suspend = ieee80211_suspend,
diff --git a/net/mac80211/chan.c b/net/mac80211/chan.c
index 77c90ed8f5d7..68952752b599 100644
--- a/net/mac80211/chan.c
+++ b/net/mac80211/chan.c
@@ -802,6 +802,11 @@ void ieee80211_recalc_chanctx_chantype(struct ieee80211_local *local,
}
}
+ if (WARN_ON_ONCE(!compat)) {
+ rcu_read_unlock();
+ return;
+ }
+
/* TDLS peers can sometimes affect the chandef width */
list_for_each_entry_rcu(sta, &local->sta_list, list) {
if (!sta->uploaded ||
@@ -1205,8 +1210,8 @@ ieee80211_link_chanctx_reservation_complete(struct ieee80211_link_data *link)
&link->csa_finalize_work);
break;
case NL80211_IFTYPE_STATION:
- ieee80211_queue_work(&sdata->local->hw,
- &link->u.mgd.chswitch_work);
+ wiphy_delayed_work_queue(sdata->local->hw.wiphy,
+ &link->u.mgd.chswitch_work, 0);
break;
case NL80211_IFTYPE_UNSPECIFIED:
case NL80211_IFTYPE_AP_VLAN:
@@ -1257,7 +1262,7 @@ ieee80211_link_use_reserved_reassign(struct ieee80211_link_data *link)
struct ieee80211_vif_chanctx_switch vif_chsw[1] = {};
struct ieee80211_chanctx *old_ctx, *new_ctx;
const struct cfg80211_chan_def *chandef;
- u32 changed = 0;
+ u64 changed = 0;
int err;
lockdep_assert_held(&local->mtx);
@@ -1653,7 +1658,7 @@ static int ieee80211_vif_use_reserved_switch(struct ieee80211_local *local)
reserved_chanctx_list) {
struct ieee80211_sub_if_data *sdata = link->sdata;
struct ieee80211_bss_conf *link_conf = link->conf;
- u32 changed = 0;
+ u64 changed = 0;
if (!ieee80211_link_has_in_place_reservation(link))
continue;
diff --git a/net/mac80211/debug.h b/net/mac80211/debug.h
index b4c20f5e778e..d49894df2351 100644
--- a/net/mac80211/debug.h
+++ b/net/mac80211/debug.h
@@ -1,7 +1,7 @@
/* SPDX-License-Identifier: GPL-2.0 */
/*
* Portions
- * Copyright (C) 2022 Intel Corporation
+ * Copyright (C) 2022 - 2023 Intel Corporation
*/
#ifndef __MAC80211_DEBUG_H
#define __MAC80211_DEBUG_H
@@ -136,7 +136,7 @@ do { \
#define link_info(link, fmt, ...) \
do { \
- if ((link)->sdata->vif.valid_links) \
+ if (ieee80211_vif_is_mld(&(link)->sdata->vif)) \
_sdata_info((link)->sdata, "[link %d] " fmt, \
(link)->link_id, \
##__VA_ARGS__); \
@@ -145,7 +145,7 @@ do { \
} while (0)
#define link_err(link, fmt, ...) \
do { \
- if ((link)->sdata->vif.valid_links) \
+ if (ieee80211_vif_is_mld(&(link)->sdata->vif)) \
_sdata_err((link)->sdata, "[link %d] " fmt, \
(link)->link_id, \
##__VA_ARGS__); \
@@ -154,7 +154,7 @@ do { \
} while (0)
#define link_dbg(link, fmt, ...) \
do { \
- if ((link)->sdata->vif.valid_links) \
+ if (ieee80211_vif_is_mld(&(link)->sdata->vif)) \
_sdata_dbg(1, (link)->sdata, "[link %d] " fmt, \
(link)->link_id, \
##__VA_ARGS__); \
diff --git a/net/mac80211/debugfs_netdev.c b/net/mac80211/debugfs_netdev.c
index b0cef37eb394..63250286dc8b 100644
--- a/net/mac80211/debugfs_netdev.c
+++ b/net/mac80211/debugfs_netdev.c
@@ -2,7 +2,7 @@
/*
* Copyright (c) 2006 Jiri Benc <jbenc@suse.cz>
* Copyright 2007 Johannes Berg <johannes@sipsolutions.net>
- * Copyright (C) 2020-2022 Intel Corporation
+ * Copyright (C) 2020-2023 Intel Corporation
*/
#include <linux/kernel.h>
@@ -267,6 +267,9 @@ static int ieee80211_set_smps(struct ieee80211_link_data *link,
struct ieee80211_local *local = sdata->local;
int err;
+ if (sdata->vif.driver_flags & IEEE80211_VIF_DISABLE_SMPS_OVERRIDE)
+ return -EOPNOTSUPP;
+
if (!(local->hw.wiphy->features & NL80211_FEATURE_STATIC_SMPS) &&
smps_mode == IEEE80211_SMPS_STATIC)
return -EINVAL;
@@ -690,6 +693,19 @@ IEEE80211_IF_FILE(dot11MeshConnectedToAuthServer,
debugfs_create_file(#name, mode, sdata->vif.debugfs_dir, \
sdata, &name##_ops)
+#define DEBUGFS_ADD_X(_bits, _name, _mode) \
+ debugfs_create_x##_bits(#_name, _mode, sdata->vif.debugfs_dir, \
+ &sdata->vif._name)
+
+#define DEBUGFS_ADD_X8(_name, _mode) \
+ DEBUGFS_ADD_X(8, _name, _mode)
+
+#define DEBUGFS_ADD_X16(_name, _mode) \
+ DEBUGFS_ADD_X(16, _name, _mode)
+
+#define DEBUGFS_ADD_X32(_name, _mode) \
+ DEBUGFS_ADD_X(32, _name, _mode)
+
#define DEBUGFS_ADD(name) DEBUGFS_ADD_MODE(name, 0400)
static void add_common_files(struct ieee80211_sub_if_data *sdata)
@@ -717,8 +733,9 @@ static void add_sta_files(struct ieee80211_sub_if_data *sdata)
DEBUGFS_ADD_MODE(uapsd_queues, 0600);
DEBUGFS_ADD_MODE(uapsd_max_sp_len, 0600);
DEBUGFS_ADD_MODE(tdls_wider_bw, 0600);
- DEBUGFS_ADD_MODE(valid_links, 0200);
+ DEBUGFS_ADD_MODE(valid_links, 0400);
DEBUGFS_ADD_MODE(active_links, 0600);
+ DEBUGFS_ADD_X16(dormant_links, 0400);
}
static void add_ap_files(struct ieee80211_sub_if_data *sdata)
diff --git a/net/mac80211/debugfs_sta.c b/net/mac80211/debugfs_sta.c
index f1914bf39f0e..5a97fb248c85 100644
--- a/net/mac80211/debugfs_sta.c
+++ b/net/mac80211/debugfs_sta.c
@@ -1035,6 +1035,190 @@ out:
}
LINK_STA_OPS(he_capa);
+static ssize_t link_sta_eht_capa_read(struct file *file, char __user *userbuf,
+ size_t count, loff_t *ppos)
+{
+ char *buf, *p;
+ size_t buf_sz = PAGE_SIZE;
+ struct link_sta_info *link_sta = file->private_data;
+ struct ieee80211_sta_eht_cap *bec = &link_sta->pub->eht_cap;
+ struct ieee80211_eht_cap_elem_fixed *fixed = &bec->eht_cap_elem;
+ struct ieee80211_eht_mcs_nss_supp *nss = &bec->eht_mcs_nss_supp;
+ u8 *cap;
+ int i;
+ ssize_t ret;
+ static const char *mcs_desc[] = { "0-7", "8-9", "10-11", "12-13"};
+
+ buf = kmalloc(buf_sz, GFP_KERNEL);
+ if (!buf)
+ return -ENOMEM;
+ p = buf;
+
+ p += scnprintf(p, buf_sz + buf - p, "EHT %ssupported\n",
+ bec->has_eht ? "" : "not ");
+ if (!bec->has_eht)
+ goto out;
+
+ p += scnprintf(p, buf_sz + buf - p,
+ "MAC-CAP: %#.2x %#.2x\n",
+ fixed->mac_cap_info[0], fixed->mac_cap_info[1]);
+ p += scnprintf(p, buf_sz + buf - p,
+ "PHY-CAP: %#.2x %#.2x %#.2x %#.2x %#.2x %#.2x %#.2x %#.2x %#.2x\n",
+ fixed->phy_cap_info[0], fixed->phy_cap_info[1],
+ fixed->phy_cap_info[2], fixed->phy_cap_info[3],
+ fixed->phy_cap_info[4], fixed->phy_cap_info[5],
+ fixed->phy_cap_info[6], fixed->phy_cap_info[7],
+ fixed->phy_cap_info[8]);
+
+#define PRINT(fmt, ...) \
+ p += scnprintf(p, buf_sz + buf - p, "\t\t" fmt "\n", \
+ ##__VA_ARGS__)
+
+#define PFLAG(t, n, a, b) \
+ do { \
+ if (cap[n] & IEEE80211_EHT_##t##_CAP##n##_##a) \
+ PRINT("%s", b); \
+ } while (0)
+
+ cap = fixed->mac_cap_info;
+ PFLAG(MAC, 0, EPCS_PRIO_ACCESS, "EPCS-PRIO-ACCESS");
+ PFLAG(MAC, 0, OM_CONTROL, "OM-CONTROL");
+ PFLAG(MAC, 0, TRIG_TXOP_SHARING_MODE1, "TRIG-TXOP-SHARING-MODE1");
+ PFLAG(MAC, 0, TRIG_TXOP_SHARING_MODE2, "TRIG-TXOP-SHARING-MODE2");
+ PFLAG(MAC, 0, RESTRICTED_TWT, "RESTRICTED-TWT");
+ PFLAG(MAC, 0, SCS_TRAFFIC_DESC, "SCS-TRAFFIC-DESC");
+ switch ((cap[0] & 0xc0) >> 6) {
+ case IEEE80211_EHT_MAC_CAP0_MAX_MPDU_LEN_3895:
+ PRINT("MAX-MPDU-LEN: 3985");
+ break;
+ case IEEE80211_EHT_MAC_CAP0_MAX_MPDU_LEN_7991:
+ PRINT("MAX-MPDU-LEN: 7991");
+ break;
+ case IEEE80211_EHT_MAC_CAP0_MAX_MPDU_LEN_11454:
+ PRINT("MAX-MPDU-LEN: 11454");
+ break;
+ }
+
+ cap = fixed->phy_cap_info;
+ PFLAG(PHY, 0, 320MHZ_IN_6GHZ, "320MHZ-IN-6GHZ");
+ PFLAG(PHY, 0, 242_TONE_RU_GT20MHZ, "242-TONE-RU-GT20MHZ");
+ PFLAG(PHY, 0, NDP_4_EHT_LFT_32_GI, "NDP-4-EHT-LFT-32-GI");
+ PFLAG(PHY, 0, PARTIAL_BW_UL_MU_MIMO, "PARTIAL-BW-UL-MU-MIMO");
+ PFLAG(PHY, 0, SU_BEAMFORMER, "SU-BEAMFORMER");
+ PFLAG(PHY, 0, SU_BEAMFORMEE, "SU-BEAMFORMEE");
+ i = cap[0] >> 7;
+ i |= (cap[1] & 0x3) << 1;
+ PRINT("BEAMFORMEE-80-NSS: %i", i);
+ PRINT("BEAMFORMEE-160-NSS: %i", (cap[1] >> 2) & 0x7);
+ PRINT("BEAMFORMEE-320-NSS: %i", (cap[1] >> 5) & 0x7);
+ PRINT("SOUNDING-DIM-80-NSS: %i", (cap[2] & 0x7));
+ PRINT("SOUNDING-DIM-160-NSS: %i", (cap[2] >> 3) & 0x7);
+ i = cap[2] >> 6;
+ i |= (cap[3] & 0x1) << 3;
+ PRINT("SOUNDING-DIM-320-NSS: %i", i);
+
+ PFLAG(PHY, 3, NG_16_SU_FEEDBACK, "NG-16-SU-FEEDBACK");
+ PFLAG(PHY, 3, NG_16_MU_FEEDBACK, "NG-16-MU-FEEDBACK");
+ PFLAG(PHY, 3, CODEBOOK_4_2_SU_FDBK, "CODEBOOK-4-2-SU-FDBK");
+ PFLAG(PHY, 3, CODEBOOK_7_5_MU_FDBK, "CODEBOOK-7-5-MU-FDBK");
+ PFLAG(PHY, 3, TRIG_SU_BF_FDBK, "TRIG-SU-BF-FDBK");
+ PFLAG(PHY, 3, TRIG_MU_BF_PART_BW_FDBK, "TRIG-MU-BF-PART-BW-FDBK");
+ PFLAG(PHY, 3, TRIG_CQI_FDBK, "TRIG-CQI-FDBK");
+
+ PFLAG(PHY, 4, PART_BW_DL_MU_MIMO, "PART-BW-DL-MU-MIMO");
+ PFLAG(PHY, 4, PSR_SR_SUPP, "PSR-SR-SUPP");
+ PFLAG(PHY, 4, POWER_BOOST_FACT_SUPP, "POWER-BOOST-FACT-SUPP");
+ PFLAG(PHY, 4, EHT_MU_PPDU_4_EHT_LTF_08_GI, "EHT-MU-PPDU-4-EHT-LTF-08-GI");
+ PRINT("MAX_NC: %i", cap[4] >> 4);
+
+ PFLAG(PHY, 5, NON_TRIG_CQI_FEEDBACK, "NON-TRIG-CQI-FEEDBACK");
+ PFLAG(PHY, 5, TX_LESS_242_TONE_RU_SUPP, "TX-LESS-242-TONE-RU-SUPP");
+ PFLAG(PHY, 5, RX_LESS_242_TONE_RU_SUPP, "RX-LESS-242-TONE-RU-SUPP");
+ PFLAG(PHY, 5, PPE_THRESHOLD_PRESENT, "PPE_THRESHOLD_PRESENT");
+ switch (cap[5] >> 4 & 0x3) {
+ case IEEE80211_EHT_PHY_CAP5_COMMON_NOMINAL_PKT_PAD_0US:
+ PRINT("NOMINAL_PKT_PAD: 0us");
+ break;
+ case IEEE80211_EHT_PHY_CAP5_COMMON_NOMINAL_PKT_PAD_8US:
+ PRINT("NOMINAL_PKT_PAD: 8us");
+ break;
+ case IEEE80211_EHT_PHY_CAP5_COMMON_NOMINAL_PKT_PAD_16US:
+ PRINT("NOMINAL_PKT_PAD: 16us");
+ break;
+ case IEEE80211_EHT_PHY_CAP5_COMMON_NOMINAL_PKT_PAD_20US:
+ PRINT("NOMINAL_PKT_PAD: 20us");
+ break;
+ }
+ i = cap[5] >> 6;
+ i |= cap[6] & 0x7;
+ PRINT("MAX-NUM-SUPP-EHT-LTF: %i", i);
+ PFLAG(PHY, 5, SUPP_EXTRA_EHT_LTF, "SUPP-EXTRA-EHT-LTF");
+
+ i = (cap[6] >> 3) & 0xf;
+ PRINT("MCS15-SUPP-MASK: %i", i);
+ PFLAG(PHY, 6, EHT_DUP_6GHZ_SUPP, "EHT-DUP-6GHZ-SUPP");
+
+ PFLAG(PHY, 7, 20MHZ_STA_RX_NDP_WIDER_BW, "20MHZ-STA-RX-NDP-WIDER-BW");
+ PFLAG(PHY, 7, NON_OFDMA_UL_MU_MIMO_80MHZ, "NON-OFDMA-UL-MU-MIMO-80MHZ");
+ PFLAG(PHY, 7, NON_OFDMA_UL_MU_MIMO_160MHZ, "NON-OFDMA-UL-MU-MIMO-160MHZ");
+ PFLAG(PHY, 7, NON_OFDMA_UL_MU_MIMO_320MHZ, "NON-OFDMA-UL-MU-MIMO-320MHZ");
+ PFLAG(PHY, 7, MU_BEAMFORMER_80MHZ, "MU-BEAMFORMER-80MHZ");
+ PFLAG(PHY, 7, MU_BEAMFORMER_160MHZ, "MU-BEAMFORMER-160MHZ");
+ PFLAG(PHY, 7, MU_BEAMFORMER_320MHZ, "MU-BEAMFORMER-320MHZ");
+ PFLAG(PHY, 7, TB_SOUNDING_FDBK_RATE_LIMIT, "TB-SOUNDING-FDBK-RATE-LIMIT");
+
+ PFLAG(PHY, 8, RX_1024QAM_WIDER_BW_DL_OFDMA, "RX-1024QAM-WIDER-BW-DL-OFDMA");
+ PFLAG(PHY, 8, RX_4096QAM_WIDER_BW_DL_OFDMA, "RX-4096QAM-WIDER-BW-DL-OFDMA");
+
+#undef PFLAG
+
+ PRINT(""); /* newline */
+ if (!(link_sta->pub->he_cap.he_cap_elem.phy_cap_info[0] &
+ IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_MASK_ALL)) {
+ u8 *mcs_vals = (u8 *)(&nss->only_20mhz);
+
+ for (i = 0; i < 4; i++)
+ PRINT("EHT bw=20 MHz, max NSS for MCS %s: Rx=%u, Tx=%u",
+ mcs_desc[i],
+ mcs_vals[i] & 0xf, mcs_vals[i] >> 4);
+ } else {
+ u8 *mcs_vals = (u8 *)(&nss->bw._80);
+
+ for (i = 0; i < 3; i++)
+ PRINT("EHT bw <= 80 MHz, max NSS for MCS %s: Rx=%u, Tx=%u",
+ mcs_desc[i + 1],
+ mcs_vals[i] & 0xf, mcs_vals[i] >> 4);
+
+ mcs_vals = (u8 *)(&nss->bw._160);
+ for (i = 0; i < 3; i++)
+ PRINT("EHT bw <= 160 MHz, max NSS for MCS %s: Rx=%u, Tx=%u",
+ mcs_desc[i + 1],
+ mcs_vals[i] & 0xf, mcs_vals[i] >> 4);
+
+ mcs_vals = (u8 *)(&nss->bw._320);
+ for (i = 0; i < 3; i++)
+ PRINT("EHT bw <= 320 MHz, max NSS for MCS %s: Rx=%u, Tx=%u",
+ mcs_desc[i + 1],
+ mcs_vals[i] & 0xf, mcs_vals[i] >> 4);
+ }
+
+ if (cap[5] & IEEE80211_EHT_PHY_CAP5_PPE_THRESHOLD_PRESENT) {
+ u8 ppe_size = ieee80211_eht_ppe_size(bec->eht_ppe_thres[0], cap);
+
+ p += scnprintf(p, buf_sz + buf - p, "EHT PPE Thresholds: ");
+ for (i = 0; i < ppe_size; i++)
+ p += scnprintf(p, buf_sz + buf - p, "0x%02x ",
+ bec->eht_ppe_thres[i]);
+ PRINT(""); /* newline */
+ }
+
+out:
+ ret = simple_read_from_buffer(userbuf, count, ppos, buf, p - buf);
+ kfree(buf);
+ return ret;
+}
+LINK_STA_OPS(eht_capa);
+
#define DEBUGFS_ADD(name) \
debugfs_create_file(#name, 0400, \
sta->debugfs_dir, sta, &sta_ ##name## _ops)
@@ -1128,6 +1312,7 @@ void ieee80211_link_sta_debugfs_add(struct link_sta_info *link_sta)
DEBUGFS_ADD(ht_capa);
DEBUGFS_ADD(vht_capa);
DEBUGFS_ADD(he_capa);
+ DEBUGFS_ADD(eht_capa);
DEBUGFS_ADD_COUNTER(rx_duplicates, rx_stats.num_duplicates);
DEBUGFS_ADD_COUNTER(rx_fragments, rx_stats.fragments);
diff --git a/net/mac80211/driver-ops.h b/net/mac80211/driver-ops.h
index 45d3e53c7383..c4505593ba7a 100644
--- a/net/mac80211/driver-ops.h
+++ b/net/mac80211/driver-ops.h
@@ -2,7 +2,7 @@
/*
* Portions of this file
* Copyright(c) 2016 Intel Deutschland GmbH
-* Copyright (C) 2018 - 2019, 2021 Intel Corporation
+* Copyright (C) 2018 - 2019, 2021 - 2023 Intel Corporation
*/
#ifndef __MAC80211_DRIVER_OPS
@@ -13,9 +13,11 @@
#include "trace.h"
#define check_sdata_in_driver(sdata) ({ \
- !WARN_ONCE(!(sdata->flags & IEEE80211_SDATA_IN_DRIVER), \
- "%s: Failed check-sdata-in-driver check, flags: 0x%x\n", \
- sdata->dev ? sdata->dev->name : sdata->name, sdata->flags); \
+ WARN_ONCE(!sdata->local->reconfig_failure && \
+ !(sdata->flags & IEEE80211_SDATA_IN_DRIVER), \
+ "%s: Failed check-sdata-in-driver check, flags: 0x%x\n", \
+ sdata->dev ? sdata->dev->name : sdata->name, sdata->flags); \
+ !!(sdata->flags & IEEE80211_SDATA_IN_DRIVER); \
})
static inline struct ieee80211_sub_if_data *
diff --git a/net/mac80211/eht.c b/net/mac80211/eht.c
index 18bc6b78b267..ddc7acc68335 100644
--- a/net/mac80211/eht.c
+++ b/net/mac80211/eht.c
@@ -2,7 +2,7 @@
/*
* EHT handling
*
- * Copyright(c) 2021-2022 Intel Corporation
+ * Copyright(c) 2021-2023 Intel Corporation
*/
#include "ieee80211_i.h"
@@ -25,8 +25,7 @@ ieee80211_eht_cap_ie_to_sta_eht_cap(struct ieee80211_sub_if_data *sdata,
memset(eht_cap, 0, sizeof(*eht_cap));
if (!eht_cap_ie_elem ||
- !ieee80211_get_eht_iftype_cap(sband,
- ieee80211_vif_type_p2p(&sdata->vif)))
+ !ieee80211_get_eht_iftype_cap_vif(sband, &sdata->vif))
return;
mcs_nss_size = ieee80211_eht_mcs_nss_size(he_cap_ie_elem,
diff --git a/net/mac80211/he.c b/net/mac80211/he.c
index 0322abae0825..9f5ffdc9db28 100644
--- a/net/mac80211/he.c
+++ b/net/mac80211/he.c
@@ -128,8 +128,7 @@ ieee80211_he_cap_ie_to_sta_he_cap(struct ieee80211_sub_if_data *sdata,
return;
own_he_cap_ptr =
- ieee80211_get_he_iftype_cap(sband,
- ieee80211_vif_type_p2p(&sdata->vif));
+ ieee80211_get_he_iftype_cap_vif(sband, &sdata->vif);
if (!own_he_cap_ptr)
return;
diff --git a/net/mac80211/ht.c b/net/mac80211/ht.c
index 5315ab750280..33729870ad8a 100644
--- a/net/mac80211/ht.c
+++ b/net/mac80211/ht.c
@@ -9,7 +9,7 @@
* Copyright 2007, Michael Wu <flamingice@sourmilk.net>
* Copyright 2007-2010, Intel Corporation
* Copyright 2017 Intel Deutschland GmbH
- * Copyright(c) 2020-2022 Intel Corporation
+ * Copyright(c) 2020-2023 Intel Corporation
*/
#include <linux/ieee80211.h>
@@ -602,7 +602,8 @@ void ieee80211_request_smps(struct ieee80211_vif *vif, unsigned int link_id,
goto out;
link->u.mgd.driver_smps_mode = smps_mode;
- ieee80211_queue_work(&sdata->local->hw, &link->u.mgd.request_smps_work);
+ wiphy_work_queue(sdata->local->hw.wiphy,
+ &link->u.mgd.request_smps_work);
out:
rcu_read_unlock();
}
diff --git a/net/mac80211/ibss.c b/net/mac80211/ibss.c
index 9dffc3079588..e1900077bc4b 100644
--- a/net/mac80211/ibss.c
+++ b/net/mac80211/ibss.c
@@ -9,7 +9,7 @@
* Copyright 2009, Johannes Berg <johannes@sipsolutions.net>
* Copyright 2013-2014 Intel Mobile Communications GmbH
* Copyright(c) 2016 Intel Deutschland GmbH
- * Copyright(c) 2018-2022 Intel Corporation
+ * Copyright(c) 2018-2023 Intel Corporation
*/
#include <linux/delay.h>
@@ -226,7 +226,7 @@ static void __ieee80211_sta_join_ibss(struct ieee80211_sub_if_data *sdata,
struct ieee80211_local *local = sdata->local;
struct ieee80211_mgmt *mgmt;
struct cfg80211_bss *bss;
- u32 bss_change;
+ u64 bss_change;
struct cfg80211_chan_def chandef;
struct ieee80211_channel *chan;
struct beacon_data *presp;
@@ -478,7 +478,8 @@ static void ieee80211_sta_join_ibss(struct ieee80211_sub_if_data *sdata,
}
int ieee80211_ibss_csa_beacon(struct ieee80211_sub_if_data *sdata,
- struct cfg80211_csa_settings *csa_settings)
+ struct cfg80211_csa_settings *csa_settings,
+ u64 *changed)
{
struct ieee80211_if_ibss *ifibss = &sdata->u.ibss;
struct beacon_data *presp, *old_presp;
@@ -520,10 +521,11 @@ int ieee80211_ibss_csa_beacon(struct ieee80211_sub_if_data *sdata,
if (old_presp)
kfree_rcu(old_presp, rcu_head);
- return BSS_CHANGED_BEACON;
+ *changed |= BSS_CHANGED_BEACON;
+ return 0;
}
-int ieee80211_ibss_finish_csa(struct ieee80211_sub_if_data *sdata)
+int ieee80211_ibss_finish_csa(struct ieee80211_sub_if_data *sdata, u64 *changed)
{
struct ieee80211_if_ibss *ifibss = &sdata->u.ibss;
struct cfg80211_bss *cbss;
@@ -552,14 +554,15 @@ int ieee80211_ibss_finish_csa(struct ieee80211_sub_if_data *sdata)
ifibss->chandef = sdata->deflink.csa_chandef;
/* generate the beacon */
- return ieee80211_ibss_csa_beacon(sdata, NULL);
+ return ieee80211_ibss_csa_beacon(sdata, NULL, changed);
}
void ieee80211_ibss_stop(struct ieee80211_sub_if_data *sdata)
{
struct ieee80211_if_ibss *ifibss = &sdata->u.ibss;
- cancel_work_sync(&ifibss->csa_connection_drop_work);
+ wiphy_work_cancel(sdata->local->hw.wiphy,
+ &ifibss->csa_connection_drop_work);
}
static struct sta_info *ieee80211_ibss_finish_sta(struct sta_info *sta)
@@ -728,7 +731,8 @@ static void ieee80211_ibss_disconnect(struct ieee80211_sub_if_data *sdata)
mutex_unlock(&local->mtx);
}
-static void ieee80211_csa_connection_drop_work(struct work_struct *work)
+static void ieee80211_csa_connection_drop_work(struct wiphy *wiphy,
+ struct wiphy_work *work)
{
struct ieee80211_sub_if_data *sdata =
container_of(work, struct ieee80211_sub_if_data,
@@ -741,7 +745,7 @@ static void ieee80211_csa_connection_drop_work(struct work_struct *work)
skb_queue_purge(&sdata->skb_queue);
/* trigger a scan to find another IBSS network to join */
- ieee80211_queue_work(&sdata->local->hw, &sdata->work);
+ wiphy_work_queue(sdata->local->hw.wiphy, &sdata->work);
sdata_unlock(sdata);
}
@@ -894,8 +898,8 @@ ieee80211_ibss_process_chanswitch(struct ieee80211_sub_if_data *sdata,
return true;
disconnect:
ibss_dbg(sdata, "Can't handle channel switch, disconnect\n");
- ieee80211_queue_work(&sdata->local->hw,
- &ifibss->csa_connection_drop_work);
+ wiphy_work_queue(sdata->local->hw.wiphy,
+ &ifibss->csa_connection_drop_work);
ieee80211_ibss_csa_mark_radar(sdata);
@@ -1242,7 +1246,7 @@ void ieee80211_ibss_rx_no_sta(struct ieee80211_sub_if_data *sdata,
spin_lock(&ifibss->incomplete_lock);
list_add(&sta->list, &ifibss->incomplete_stations);
spin_unlock(&ifibss->incomplete_lock);
- ieee80211_queue_work(&local->hw, &sdata->work);
+ wiphy_work_queue(local->hw.wiphy, &sdata->work);
}
static void ieee80211_ibss_sta_expire(struct ieee80211_sub_if_data *sdata)
@@ -1721,7 +1725,7 @@ static void ieee80211_ibss_timer(struct timer_list *t)
struct ieee80211_sub_if_data *sdata =
from_timer(sdata, t, u.ibss.timer);
- ieee80211_queue_work(&sdata->local->hw, &sdata->work);
+ wiphy_work_queue(sdata->local->hw.wiphy, &sdata->work);
}
void ieee80211_ibss_setup_sdata(struct ieee80211_sub_if_data *sdata)
@@ -1731,8 +1735,8 @@ void ieee80211_ibss_setup_sdata(struct ieee80211_sub_if_data *sdata)
timer_setup(&ifibss->timer, ieee80211_ibss_timer, 0);
INIT_LIST_HEAD(&ifibss->incomplete_stations);
spin_lock_init(&ifibss->incomplete_lock);
- INIT_WORK(&ifibss->csa_connection_drop_work,
- ieee80211_csa_connection_drop_work);
+ wiphy_work_init(&ifibss->csa_connection_drop_work,
+ ieee80211_csa_connection_drop_work);
}
/* scan finished notification */
@@ -1754,7 +1758,7 @@ void ieee80211_ibss_notify_scan_completed(struct ieee80211_local *local)
int ieee80211_ibss_join(struct ieee80211_sub_if_data *sdata,
struct cfg80211_ibss_params *params)
{
- u32 changed = 0;
+ u64 changed = 0;
u32 rate_flags;
struct ieee80211_supported_band *sband;
enum ieee80211_chanctx_mode chanmode;
@@ -1856,7 +1860,7 @@ int ieee80211_ibss_join(struct ieee80211_sub_if_data *sdata,
sdata->deflink.needed_rx_chains = local->rx_chains;
sdata->control_port_over_nl80211 = params->control_port_over_nl80211;
- ieee80211_queue_work(&local->hw, &sdata->work);
+ wiphy_work_queue(local->hw.wiphy, &sdata->work);
return 0;
}
diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h
index 4159fb65038b..91633a0b723e 100644
--- a/net/mac80211/ieee80211_i.h
+++ b/net/mac80211/ieee80211_i.h
@@ -410,6 +410,8 @@ struct ieee80211_mgd_assoc_data {
ieee80211_conn_flags_t conn_flags;
u16 status;
+
+ bool disabled;
} link[IEEE80211_MLD_MAX_NUM_LINKS];
u8 ap_addr[ETH_ALEN] __aligned(2);
@@ -466,8 +468,8 @@ struct ieee80211_if_managed {
struct timer_list conn_mon_timer;
struct timer_list bcn_mon_timer;
struct work_struct monitor_work;
- struct work_struct beacon_connection_loss_work;
- struct work_struct csa_connection_drop_work;
+ struct wiphy_work beacon_connection_loss_work;
+ struct wiphy_work csa_connection_drop_work;
unsigned long beacon_timeout;
unsigned long probe_timeout;
@@ -549,11 +551,14 @@ struct ieee80211_if_managed {
*/
u8 *assoc_req_ies;
size_t assoc_req_ies_len;
+
+ struct wiphy_delayed_work ml_reconf_work;
+ u16 removed_links;
};
struct ieee80211_if_ibss {
struct timer_list timer;
- struct work_struct csa_connection_drop_work;
+ struct wiphy_work csa_connection_drop_work;
unsigned long last_scan_completed;
@@ -918,10 +923,9 @@ struct ieee80211_link_data_managed {
bool csa_waiting_bcn;
bool csa_ignored_same_chan;
- struct timer_list chswitch_timer;
- struct work_struct chswitch_work;
+ struct wiphy_delayed_work chswitch_work;
- struct work_struct request_smps_work;
+ struct wiphy_work request_smps_work;
bool beacon_crc_valid;
u32 beacon_crc;
struct ewma_beacon_signal ave_beacon_signal;
@@ -947,6 +951,8 @@ struct ieee80211_link_data_managed {
int wmm_last_param_set;
int mu_edca_last_param_set;
+ u8 bss_param_ch_cnt;
+
struct cfg80211_bss *bss;
};
@@ -1061,7 +1067,7 @@ struct ieee80211_sub_if_data {
/* used to reconfigure hardware SM PS */
struct work_struct recalc_smps;
- struct work_struct work;
+ struct wiphy_work work;
struct sk_buff_head skb_queue;
struct sk_buff_head status_queue;
@@ -1394,6 +1400,9 @@ struct ieee80211_local {
/* device is during a HW reconfig */
bool in_reconfig;
+ /* reconfiguration failed ... suppress some warnings etc. */
+ bool reconfig_failure;
+
/* wowlan is enabled -- don't reconfig on resume */
bool wowlan;
@@ -1612,7 +1621,7 @@ ieee80211_get_sband(struct ieee80211_sub_if_data *sdata)
struct ieee80211_chanctx_conf *chanctx_conf;
enum nl80211_band band;
- WARN_ON(sdata->vif.valid_links);
+ WARN_ON(ieee80211_vif_is_mld(&sdata->vif));
rcu_read_lock();
chanctx_conf = rcu_dereference(sdata->vif.bss_conf.chanctx_conf);
@@ -1722,7 +1731,8 @@ struct ieee802_11_elems {
const struct ieee80211_aid_response_ie *aid_resp;
const struct ieee80211_eht_cap_elem *eht_cap;
const struct ieee80211_eht_operation *eht_operation;
- const struct ieee80211_multi_link_elem *multi_link;
+ const struct ieee80211_multi_link_elem *ml_basic;
+ const struct ieee80211_multi_link_elem *ml_reconf;
/* length of them, respectively */
u8 ext_capab_len;
@@ -1747,7 +1757,14 @@ struct ieee802_11_elems {
u8 eht_cap_len;
/* mult-link element can be de-fragmented and thus u8 is not sufficient */
- size_t multi_link_len;
+ size_t ml_basic_len;
+ size_t ml_reconf_len;
+
+ /* The basic Multi-Link element in the original IEs */
+ const struct element *ml_basic_elem;
+
+ /* The reconfiguration Multi-Link element in the original IEs */
+ const struct element *ml_reconf_elem;
/*
* store the per station profile pointer and length in case that the
@@ -1827,7 +1844,7 @@ void ieee80211_link_info_change_notify(struct ieee80211_sub_if_data *sdata,
struct ieee80211_link_data *link,
u64 changed);
void ieee80211_configure_filter(struct ieee80211_local *local);
-u32 ieee80211_reset_erp_info(struct ieee80211_sub_if_data *sdata);
+u64 ieee80211_reset_erp_info(struct ieee80211_sub_if_data *sdata);
u64 ieee80211_mgmt_tx_cookie(struct ieee80211_local *local);
int ieee80211_attach_ack_skb(struct ieee80211_local *local, struct sk_buff *skb,
@@ -1887,8 +1904,10 @@ void ieee80211_ibss_work(struct ieee80211_sub_if_data *sdata);
void ieee80211_ibss_rx_queued_mgmt(struct ieee80211_sub_if_data *sdata,
struct sk_buff *skb);
int ieee80211_ibss_csa_beacon(struct ieee80211_sub_if_data *sdata,
- struct cfg80211_csa_settings *csa_settings);
-int ieee80211_ibss_finish_csa(struct ieee80211_sub_if_data *sdata);
+ struct cfg80211_csa_settings *csa_settings,
+ u64 *changed);
+int ieee80211_ibss_finish_csa(struct ieee80211_sub_if_data *sdata,
+ u64 *changed);
void ieee80211_ibss_stop(struct ieee80211_sub_if_data *sdata);
/* OCB code */
@@ -1905,8 +1924,10 @@ void ieee80211_mesh_work(struct ieee80211_sub_if_data *sdata);
void ieee80211_mesh_rx_queued_mgmt(struct ieee80211_sub_if_data *sdata,
struct sk_buff *skb);
int ieee80211_mesh_csa_beacon(struct ieee80211_sub_if_data *sdata,
- struct cfg80211_csa_settings *csa_settings);
-int ieee80211_mesh_finish_csa(struct ieee80211_sub_if_data *sdata);
+ struct cfg80211_csa_settings *csa_settings,
+ u64 *changed);
+int ieee80211_mesh_finish_csa(struct ieee80211_sub_if_data *sdata,
+ u64 *changed);
/* scan/BSS handling */
void ieee80211_scan_work(struct work_struct *work);
@@ -1921,6 +1942,9 @@ void ieee80211_scan_cancel(struct ieee80211_local *local);
void ieee80211_run_deferred_scan(struct ieee80211_local *local);
void ieee80211_scan_rx(struct ieee80211_local *local, struct sk_buff *skb);
+void ieee80211_inform_bss(struct wiphy *wiphy, struct cfg80211_bss *bss,
+ const struct cfg80211_bss_ies *ies, void *data);
+
void ieee80211_mlme_notify_scan_completed(struct ieee80211_local *local);
struct ieee80211_bss *
ieee80211_bss_info_update(struct ieee80211_local *local,
@@ -2013,8 +2037,9 @@ void ieee80211_link_init(struct ieee80211_sub_if_data *sdata,
struct ieee80211_bss_conf *link_conf);
void ieee80211_link_stop(struct ieee80211_link_data *link);
int ieee80211_vif_set_links(struct ieee80211_sub_if_data *sdata,
- u16 new_links);
+ u16 new_links, u16 dormant_links);
void ieee80211_vif_clear_links(struct ieee80211_sub_if_data *sdata);
+int __ieee80211_set_active_links(struct ieee80211_vif *vif, u16 active_links);
/* tx handling */
void ieee80211_clear_tx_pending(struct ieee80211_local *local);
@@ -2269,8 +2294,6 @@ static inline void ieee80211_tx_skb(struct ieee80211_sub_if_data *sdata,
* (or re-association) response frame if this is given
* @from_ap: frame is received from an AP (currently used only
* for EHT capabilities parsing)
- * @scratch_len: if non zero, specifies the requested length of the scratch
- * buffer; otherwise, 'len' is used.
*/
struct ieee80211_elems_parse_params {
const u8 *start;
@@ -2281,7 +2304,6 @@ struct ieee80211_elems_parse_params {
struct cfg80211_bss *bss;
int link_id;
bool from_ap;
- size_t scratch_len;
};
struct ieee802_11_elems *
@@ -2421,6 +2443,7 @@ void ieee80211_send_deauth_disassoc(struct ieee80211_sub_if_data *sdata,
const u8 *da, const u8 *bssid,
u16 stype, u16 reason,
bool send_frame, u8 *frame_buf);
+u8 *ieee80211_write_he_6ghz_cap(u8 *pos, __le16 cap, u8 *end);
enum {
IEEE80211_PROBE_FLAG_DIRECTED = BIT(0),
@@ -2560,10 +2583,10 @@ void ieee80211_recalc_chanctx_chantype(struct ieee80211_local *local,
/* TDLS */
int ieee80211_tdls_mgmt(struct wiphy *wiphy, struct net_device *dev,
- const u8 *peer, u8 action_code, u8 dialog_token,
- u16 status_code, u32 peer_capability,
- bool initiator, const u8 *extra_ies,
- size_t extra_ies_len);
+ const u8 *peer, int link_id,
+ u8 action_code, u8 dialog_token, u16 status_code,
+ u32 peer_capability, bool initiator,
+ const u8 *extra_ies, size_t extra_ies_len);
int ieee80211_tdls_oper(struct wiphy *wiphy, struct net_device *dev,
const u8 *peer, enum nl80211_tdls_operation oper);
void ieee80211_tdls_peer_del_work(struct work_struct *wk);
diff --git a/net/mac80211/iface.c b/net/mac80211/iface.c
index bd2c48870add..be586bc0b5b7 100644
--- a/net/mac80211/iface.c
+++ b/net/mac80211/iface.c
@@ -8,7 +8,7 @@
* Copyright 2008, Johannes Berg <johannes@sipsolutions.net>
* Copyright 2013-2014 Intel Mobile Communications GmbH
* Copyright (c) 2016 Intel Deutschland GmbH
- * Copyright (C) 2018-2022 Intel Corporation
+ * Copyright (C) 2018-2023 Intel Corporation
*/
#include <linux/slab.h>
#include <linux/kernel.h>
@@ -43,7 +43,7 @@
* by either the RTNL, the iflist_mtx or RCU.
*/
-static void ieee80211_iface_work(struct work_struct *work);
+static void ieee80211_iface_work(struct wiphy *wiphy, struct wiphy_work *work);
bool __ieee80211_recalc_txpower(struct ieee80211_sub_if_data *sdata)
{
@@ -521,7 +521,7 @@ static void ieee80211_do_stop(struct ieee80211_sub_if_data *sdata, bool going_do
cancel_work_sync(&sdata->recalc_smps);
sdata_lock(sdata);
- WARN(sdata->vif.valid_links,
+ WARN(ieee80211_vif_is_mld(&sdata->vif),
"destroying interface with valid links 0x%04x\n",
sdata->vif.valid_links);
@@ -614,7 +614,7 @@ static void ieee80211_do_stop(struct ieee80211_sub_if_data *sdata, bool going_do
RCU_INIT_POINTER(local->p2p_sdata, NULL);
fallthrough;
default:
- cancel_work_sync(&sdata->work);
+ wiphy_work_cancel(sdata->local->hw.wiphy, &sdata->work);
/*
* When we get here, the interface is marked down.
* Free the remaining keys, if there are any
@@ -1133,6 +1133,7 @@ int ieee80211_add_virtual_monitor(struct ieee80211_local *local)
snprintf(sdata->name, IFNAMSIZ, "%s-monitor",
wiphy_name(local->hw.wiphy));
sdata->wdev.iftype = NL80211_IFTYPE_MONITOR;
+ mutex_init(&sdata->wdev.mtx);
ieee80211_sdata_init(local, sdata);
@@ -1157,23 +1158,26 @@ int ieee80211_add_virtual_monitor(struct ieee80211_local *local)
rcu_assign_pointer(local->monitor_sdata, sdata);
mutex_unlock(&local->iflist_mtx);
+ sdata_lock(sdata);
mutex_lock(&local->mtx);
ret = ieee80211_link_use_channel(&sdata->deflink, &local->monitor_chandef,
IEEE80211_CHANCTX_EXCLUSIVE);
mutex_unlock(&local->mtx);
+ sdata_unlock(sdata);
if (ret) {
mutex_lock(&local->iflist_mtx);
RCU_INIT_POINTER(local->monitor_sdata, NULL);
mutex_unlock(&local->iflist_mtx);
synchronize_net();
drv_remove_interface(local, sdata);
+ mutex_destroy(&sdata->wdev.mtx);
kfree(sdata);
return ret;
}
skb_queue_head_init(&sdata->skb_queue);
skb_queue_head_init(&sdata->status_queue);
- INIT_WORK(&sdata->work, ieee80211_iface_work);
+ wiphy_work_init(&sdata->work, ieee80211_iface_work);
return 0;
}
@@ -1202,12 +1206,15 @@ void ieee80211_del_virtual_monitor(struct ieee80211_local *local)
synchronize_net();
+ sdata_lock(sdata);
mutex_lock(&local->mtx);
ieee80211_link_release_channel(&sdata->deflink);
mutex_unlock(&local->mtx);
+ sdata_unlock(sdata);
drv_remove_interface(local, sdata);
+ mutex_destroy(&sdata->wdev.mtx);
kfree(sdata);
}
@@ -1221,7 +1228,7 @@ int ieee80211_do_open(struct wireless_dev *wdev, bool coming_up)
struct ieee80211_sub_if_data *sdata = IEEE80211_WDEV_TO_SUB_IF(wdev);
struct net_device *dev = wdev->netdev;
struct ieee80211_local *local = sdata->local;
- u32 changed = 0;
+ u64 changed = 0;
int res;
u32 hw_reconf_flags = 0;
@@ -1281,6 +1288,9 @@ int ieee80211_do_open(struct wireless_dev *wdev, bool coming_up)
}
if (local->open_count == 0) {
+ /* here we can consider everything in good order (again) */
+ local->reconfig_failure = false;
+
res = drv_start(local);
if (res)
goto err_del_bss;
@@ -1622,7 +1632,7 @@ static void ieee80211_iface_process_status(struct ieee80211_sub_if_data *sdata,
}
}
-static void ieee80211_iface_work(struct work_struct *work)
+static void ieee80211_iface_work(struct wiphy *wiphy, struct wiphy_work *work)
{
struct ieee80211_sub_if_data *sdata =
container_of(work, struct ieee80211_sub_if_data, work);
@@ -1734,7 +1744,7 @@ static void ieee80211_setup_sdata(struct ieee80211_sub_if_data *sdata,
skb_queue_head_init(&sdata->skb_queue);
skb_queue_head_init(&sdata->status_queue);
- INIT_WORK(&sdata->work, ieee80211_iface_work);
+ wiphy_work_init(&sdata->work, ieee80211_iface_work);
INIT_WORK(&sdata->recalc_smps, ieee80211_recalc_smps_work);
INIT_WORK(&sdata->activate_links_work, ieee80211_activate_links_work);
@@ -1812,7 +1822,7 @@ static int ieee80211_runtime_change_iftype(struct ieee80211_sub_if_data *sdata,
return -EBUSY;
/* for now, don't support changing while links exist */
- if (sdata->vif.valid_links)
+ if (ieee80211_vif_is_mld(&sdata->vif))
return -EBUSY;
switch (sdata->vif.type) {
@@ -2255,7 +2265,6 @@ void ieee80211_remove_interfaces(struct ieee80211_local *local)
{
struct ieee80211_sub_if_data *sdata, *tmp;
LIST_HEAD(unreg_list);
- LIST_HEAD(wdev_list);
ASSERT_RTNL();
@@ -2278,23 +2287,18 @@ void ieee80211_remove_interfaces(struct ieee80211_local *local)
ieee80211_txq_teardown_flows(local);
mutex_lock(&local->iflist_mtx);
- list_for_each_entry_safe(sdata, tmp, &local->interfaces, list) {
- list_del(&sdata->list);
-
- if (sdata->dev)
- unregister_netdevice_queue(sdata->dev, &unreg_list);
- else
- list_add(&sdata->list, &wdev_list);
- }
+ list_splice_init(&local->interfaces, &unreg_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_for_each_entry_safe(sdata, tmp, &unreg_list, list) {
+ bool netdev = sdata->dev;
+
list_del(&sdata->list);
cfg80211_unregister_wdev(&sdata->wdev);
- kfree(sdata);
+
+ if (!netdev)
+ kfree(sdata);
}
wiphy_unlock(local->hw.wiphy);
}
diff --git a/net/mac80211/key.c b/net/mac80211/key.c
index e8f6c1e5eabf..21cf5a208910 100644
--- a/net/mac80211/key.c
+++ b/net/mac80211/key.c
@@ -6,7 +6,7 @@
* Copyright 2007-2008 Johannes Berg <johannes@sipsolutions.net>
* Copyright 2013-2014 Intel Mobile Communications GmbH
* Copyright 2015-2017 Intel Deutschland GmbH
- * Copyright 2018-2020, 2022 Intel Corporation
+ * Copyright 2018-2020, 2022-2023 Intel Corporation
*/
#include <linux/if_ether.h>
@@ -510,8 +510,12 @@ static int ieee80211_key_replace(struct ieee80211_sub_if_data *sdata,
ret = ieee80211_key_enable_hw_accel(new);
}
} else {
- if (!new->local->wowlan)
+ if (!new->local->wowlan) {
ret = ieee80211_key_enable_hw_accel(new);
+ } else {
+ assert_key_lock(new->local);
+ new->flags |= KEY_FLAG_UPLOADED_TO_HARDWARE;
+ }
}
if (ret)
diff --git a/net/mac80211/link.c b/net/mac80211/link.c
index 40f030b8ece9..6148208b320e 100644
--- a/net/mac80211/link.c
+++ b/net/mac80211/link.c
@@ -142,25 +142,34 @@ static int ieee80211_check_dup_link_addrs(struct ieee80211_sub_if_data *sdata)
}
static void ieee80211_set_vif_links_bitmaps(struct ieee80211_sub_if_data *sdata,
- u16 links)
+ u16 valid_links, u16 dormant_links)
{
- sdata->vif.valid_links = links;
-
- if (!links) {
+ sdata->vif.valid_links = valid_links;
+ sdata->vif.dormant_links = dormant_links;
+
+ if (!valid_links ||
+ WARN((~valid_links & dormant_links) ||
+ !(valid_links & ~dormant_links),
+ "Invalid links: valid=0x%x, dormant=0x%x",
+ valid_links, dormant_links)) {
sdata->vif.active_links = 0;
+ sdata->vif.dormant_links = 0;
return;
}
switch (sdata->vif.type) {
case NL80211_IFTYPE_AP:
/* in an AP all links are always active */
- sdata->vif.active_links = links;
+ sdata->vif.active_links = valid_links;
+
+ /* AP links are not expected to be disabled */
+ WARN_ON(dormant_links);
break;
case NL80211_IFTYPE_STATION:
if (sdata->vif.active_links)
break;
- WARN_ON(hweight16(links) > 1);
- sdata->vif.active_links = links;
+ sdata->vif.active_links = valid_links & ~dormant_links;
+ WARN_ON(hweight16(sdata->vif.active_links) > 1);
break;
default:
WARN_ON(1);
@@ -169,7 +178,7 @@ static void ieee80211_set_vif_links_bitmaps(struct ieee80211_sub_if_data *sdata,
static int ieee80211_vif_update_links(struct ieee80211_sub_if_data *sdata,
struct link_container **to_free,
- u16 new_links)
+ u16 new_links, u16 dormant_links)
{
u16 old_links = sdata->vif.valid_links;
u16 old_active = sdata->vif.active_links;
@@ -245,7 +254,7 @@ static int ieee80211_vif_update_links(struct ieee80211_sub_if_data *sdata,
/* for keys we will not be able to undo this */
ieee80211_tear_down_links(sdata, to_free, rem);
- ieee80211_set_vif_links_bitmaps(sdata, new_links);
+ ieee80211_set_vif_links_bitmaps(sdata, new_links, dormant_links);
/* tell the driver */
ret = drv_change_vif_links(sdata->local, sdata,
@@ -258,7 +267,7 @@ static int ieee80211_vif_update_links(struct ieee80211_sub_if_data *sdata,
/* restore config */
memcpy(sdata->link, old_data, sizeof(old_data));
memcpy(sdata->vif.link_conf, old, sizeof(old));
- ieee80211_set_vif_links_bitmaps(sdata, old_links);
+ ieee80211_set_vif_links_bitmaps(sdata, old_links, dormant_links);
/* and free (only) the newly allocated links */
memset(to_free, 0, sizeof(links));
goto free;
@@ -282,12 +291,13 @@ deinit:
}
int ieee80211_vif_set_links(struct ieee80211_sub_if_data *sdata,
- u16 new_links)
+ u16 new_links, u16 dormant_links)
{
struct link_container *links[IEEE80211_MLD_MAX_NUM_LINKS];
int ret;
- ret = ieee80211_vif_update_links(sdata, links, new_links);
+ ret = ieee80211_vif_update_links(sdata, links, new_links,
+ dormant_links);
ieee80211_free_links(sdata, links);
return ret;
@@ -304,7 +314,7 @@ void ieee80211_vif_clear_links(struct ieee80211_sub_if_data *sdata)
*/
sdata_lock(sdata);
- ieee80211_vif_update_links(sdata, links, 0);
+ ieee80211_vif_update_links(sdata, links, 0, 0);
sdata_unlock(sdata);
ieee80211_free_links(sdata, links);
@@ -328,8 +338,7 @@ static int _ieee80211_set_active_links(struct ieee80211_sub_if_data *sdata,
if (sdata->vif.type != NL80211_IFTYPE_STATION)
return -EINVAL;
- /* cannot activate links that don't exist */
- if (active_links & ~sdata->vif.valid_links)
+ if (active_links & ~ieee80211_vif_usable_links(&sdata->vif))
return -EINVAL;
/* nothing to do */
@@ -438,14 +447,14 @@ static int _ieee80211_set_active_links(struct ieee80211_sub_if_data *sdata,
return 0;
}
-int ieee80211_set_active_links(struct ieee80211_vif *vif, u16 active_links)
+int __ieee80211_set_active_links(struct ieee80211_vif *vif, u16 active_links)
{
struct ieee80211_sub_if_data *sdata = vif_to_sdata(vif);
struct ieee80211_local *local = sdata->local;
u16 old_active;
int ret;
- sdata_lock(sdata);
+ sdata_assert_lock(sdata);
mutex_lock(&local->sta_mtx);
mutex_lock(&local->mtx);
mutex_lock(&local->key_mtx);
@@ -467,6 +476,17 @@ int ieee80211_set_active_links(struct ieee80211_vif *vif, u16 active_links)
mutex_unlock(&local->key_mtx);
mutex_unlock(&local->mtx);
mutex_unlock(&local->sta_mtx);
+
+ return ret;
+}
+
+int ieee80211_set_active_links(struct ieee80211_vif *vif, u16 active_links)
+{
+ struct ieee80211_sub_if_data *sdata = vif_to_sdata(vif);
+ int ret;
+
+ sdata_lock(sdata);
+ ret = __ieee80211_set_active_links(vif, active_links);
sdata_unlock(sdata);
return ret;
@@ -484,8 +504,7 @@ void ieee80211_set_active_links_async(struct ieee80211_vif *vif,
if (sdata->vif.type != NL80211_IFTYPE_STATION)
return;
- /* cannot activate links that don't exist */
- if (active_links & ~sdata->vif.valid_links)
+ if (active_links & ~ieee80211_vif_usable_links(&sdata->vif))
return;
/* nothing to do */
diff --git a/net/mac80211/main.c b/net/mac80211/main.c
index 55cdfaef0f5d..24315d7b3126 100644
--- a/net/mac80211/main.c
+++ b/net/mac80211/main.c
@@ -5,7 +5,7 @@
* Copyright 2006-2007 Jiri Benc <jbenc@suse.cz>
* Copyright 2013-2014 Intel Mobile Communications GmbH
* Copyright (C) 2017 Intel Deutschland GmbH
- * Copyright (C) 2018-2022 Intel Corporation
+ * Copyright (C) 2018-2023 Intel Corporation
*/
#include <net/mac80211.h>
@@ -291,7 +291,7 @@ void ieee80211_link_info_change_notify(struct ieee80211_sub_if_data *sdata,
drv_link_info_changed(local, sdata, link->conf, link->link_id, changed);
}
-u32 ieee80211_reset_erp_info(struct ieee80211_sub_if_data *sdata)
+u64 ieee80211_reset_erp_info(struct ieee80211_sub_if_data *sdata)
{
sdata->vif.bss_conf.use_cts_prot = false;
sdata->vif.bss_conf.use_short_preamble = false;
@@ -364,7 +364,8 @@ static void ieee80211_restart_work(struct work_struct *work)
* The exception is ieee80211_chswitch_done.
* Then we can have a race...
*/
- cancel_work_sync(&sdata->u.mgd.csa_connection_drop_work);
+ wiphy_work_cancel(local->hw.wiphy,
+ &sdata->u.mgd.csa_connection_drop_work);
if (sdata->vif.bss_conf.csa_active) {
sdata_lock(sdata);
ieee80211_sta_connection_lost(sdata,
diff --git a/net/mac80211/mesh.c b/net/mac80211/mesh.c
index f72333201903..af8c5fc2db14 100644
--- a/net/mac80211/mesh.c
+++ b/net/mac80211/mesh.c
@@ -1,7 +1,7 @@
// SPDX-License-Identifier: GPL-2.0-only
/*
* Copyright (c) 2008, 2009 open80211s Ltd.
- * Copyright (C) 2018 - 2022 Intel Corporation
+ * Copyright (C) 2018 - 2023 Intel Corporation
* Authors: Luis Carlos Cobo <luisca@cozybit.com>
* Javier Cardona <javier@cozybit.com>
*/
@@ -45,7 +45,7 @@ static void ieee80211_mesh_housekeeping_timer(struct timer_list *t)
set_bit(MESH_WORK_HOUSEKEEPING, &ifmsh->wrkq_flags);
- ieee80211_queue_work(&local->hw, &sdata->work);
+ wiphy_work_queue(local->hw.wiphy, &sdata->work);
}
/**
@@ -133,10 +133,10 @@ bool mesh_peer_accepts_plinks(struct ieee802_11_elems *ie)
*
* Returns: beacon changed flag if the beacon content changed.
*/
-u32 mesh_accept_plinks_update(struct ieee80211_sub_if_data *sdata)
+u64 mesh_accept_plinks_update(struct ieee80211_sub_if_data *sdata)
{
bool free_plinks;
- u32 changed = 0;
+ u64 changed = 0;
/* In case mesh_plink_free_count > 0 and mesh_plinktbl_capacity == 0,
* the mesh interface might be able to establish plinks with peers that
@@ -162,7 +162,7 @@ u32 mesh_accept_plinks_update(struct ieee80211_sub_if_data *sdata)
void mesh_sta_cleanup(struct sta_info *sta)
{
struct ieee80211_sub_if_data *sdata = sta->sdata;
- u32 changed = mesh_plink_deactivate(sta);
+ u64 changed = mesh_plink_deactivate(sta);
if (changed)
ieee80211_mbss_info_change_notify(sdata, changed);
@@ -703,7 +703,7 @@ static void ieee80211_mesh_path_timer(struct timer_list *t)
struct ieee80211_sub_if_data *sdata =
from_timer(sdata, t, u.mesh.mesh_path_timer);
- ieee80211_queue_work(&sdata->local->hw, &sdata->work);
+ wiphy_work_queue(sdata->local->hw.wiphy, &sdata->work);
}
static void ieee80211_mesh_path_root_timer(struct timer_list *t)
@@ -714,7 +714,7 @@ static void ieee80211_mesh_path_root_timer(struct timer_list *t)
set_bit(MESH_WORK_ROOT, &ifmsh->wrkq_flags);
- ieee80211_queue_work(&sdata->local->hw, &sdata->work);
+ wiphy_work_queue(sdata->local->hw.wiphy, &sdata->work);
}
void ieee80211_mesh_root_setup(struct ieee80211_if_mesh *ifmsh)
@@ -923,7 +923,7 @@ unsigned int ieee80211_new_mesh_header(struct ieee80211_sub_if_data *sdata,
static void ieee80211_mesh_housekeeping(struct ieee80211_sub_if_data *sdata)
{
struct ieee80211_if_mesh *ifmsh = &sdata->u.mesh;
- u32 changed;
+ u64 changed;
if (ifmsh->mshcfg.plink_timeout > 0)
ieee80211_sta_expire(sdata, ifmsh->mshcfg.plink_timeout * HZ);
@@ -1164,7 +1164,7 @@ ieee80211_mesh_rebuild_beacon(struct ieee80211_sub_if_data *sdata)
}
void ieee80211_mbss_info_change_notify(struct ieee80211_sub_if_data *sdata,
- u32 changed)
+ u64 changed)
{
struct ieee80211_if_mesh *ifmsh = &sdata->u.mesh;
unsigned long bits = changed;
@@ -1177,14 +1177,14 @@ void ieee80211_mbss_info_change_notify(struct ieee80211_sub_if_data *sdata,
for_each_set_bit(bit, &bits, sizeof(changed) * BITS_PER_BYTE)
set_bit(bit, &ifmsh->mbss_changed);
set_bit(MESH_WORK_MBSS_CHANGED, &ifmsh->wrkq_flags);
- ieee80211_queue_work(&sdata->local->hw, &sdata->work);
+ wiphy_work_queue(sdata->local->hw.wiphy, &sdata->work);
}
int ieee80211_start_mesh(struct ieee80211_sub_if_data *sdata)
{
struct ieee80211_if_mesh *ifmsh = &sdata->u.mesh;
struct ieee80211_local *local = sdata->local;
- u32 changed = BSS_CHANGED_BEACON |
+ u64 changed = BSS_CHANGED_BEACON |
BSS_CHANGED_BEACON_ENABLED |
BSS_CHANGED_HT |
BSS_CHANGED_BASIC_RATES |
@@ -1202,7 +1202,7 @@ int ieee80211_start_mesh(struct ieee80211_sub_if_data *sdata)
ifmsh->sync_offset_clockdrift_max = 0;
set_bit(MESH_WORK_HOUSEKEEPING, &ifmsh->wrkq_flags);
ieee80211_mesh_root_setup(ifmsh);
- ieee80211_queue_work(&local->hw, &sdata->work);
+ wiphy_work_queue(local->hw.wiphy, &sdata->work);
sdata->vif.bss_conf.ht_operation_mode =
ifmsh->mshcfg.ht_opmode;
sdata->vif.bss_conf.enable_beacon = true;
@@ -1525,12 +1525,11 @@ free:
kfree(elems);
}
-int ieee80211_mesh_finish_csa(struct ieee80211_sub_if_data *sdata)
+int ieee80211_mesh_finish_csa(struct ieee80211_sub_if_data *sdata, u64 *changed)
{
struct ieee80211_if_mesh *ifmsh = &sdata->u.mesh;
struct mesh_csa_settings *tmp_csa_settings;
int ret = 0;
- int changed = 0;
/* Reset the TTL value and Initiator flag */
ifmsh->csa_role = IEEE80211_MESH_CSA_ROLE_NONE;
@@ -1545,15 +1544,16 @@ int ieee80211_mesh_finish_csa(struct ieee80211_sub_if_data *sdata)
if (ret)
return -EINVAL;
- changed |= BSS_CHANGED_BEACON;
+ *changed |= BSS_CHANGED_BEACON;
mcsa_dbg(sdata, "complete switching to center freq %d MHz",
sdata->vif.bss_conf.chandef.chan->center_freq);
- return changed;
+ return 0;
}
int ieee80211_mesh_csa_beacon(struct ieee80211_sub_if_data *sdata,
- struct cfg80211_csa_settings *csa_settings)
+ struct cfg80211_csa_settings *csa_settings,
+ u64 *changed)
{
struct ieee80211_if_mesh *ifmsh = &sdata->u.mesh;
struct mesh_csa_settings *tmp_csa_settings;
@@ -1579,7 +1579,8 @@ int ieee80211_mesh_csa_beacon(struct ieee80211_sub_if_data *sdata,
return ret;
}
- return BSS_CHANGED_BEACON;
+ *changed |= BSS_CHANGED_BEACON;
+ return 0;
}
static int mesh_fwd_csa_frame(struct ieee80211_sub_if_data *sdata,
@@ -1720,7 +1721,8 @@ out:
static void mesh_bss_info_changed(struct ieee80211_sub_if_data *sdata)
{
struct ieee80211_if_mesh *ifmsh = &sdata->u.mesh;
- u32 bit, changed = 0;
+ u32 bit;
+ u64 changed = 0;
for_each_set_bit(bit, &ifmsh->mbss_changed,
sizeof(changed) * BITS_PER_BYTE) {
diff --git a/net/mac80211/mesh.h b/net/mac80211/mesh.h
index 022f41292a05..6c94222a9df5 100644
--- a/net/mac80211/mesh.h
+++ b/net/mac80211/mesh.h
@@ -1,6 +1,7 @@
/* SPDX-License-Identifier: GPL-2.0-only */
/*
* Copyright (c) 2008, 2009 open80211s Ltd.
+ * Copyright (C) 2023 Intel Corporation
* Authors: Luis Carlos Cobo <luisca@cozybit.com>
* Javier Cardona <javier@cozybit.com>
*/
@@ -252,11 +253,11 @@ void ieee80211_mesh_root_setup(struct ieee80211_if_mesh *ifmsh);
const struct ieee80211_mesh_sync_ops *ieee80211_mesh_sync_ops_get(u8 method);
/* wrapper for ieee80211_bss_info_change_notify() */
void ieee80211_mbss_info_change_notify(struct ieee80211_sub_if_data *sdata,
- u32 changed);
+ u64 changed);
/* mesh power save */
-u32 ieee80211_mps_local_status_update(struct ieee80211_sub_if_data *sdata);
-u32 ieee80211_mps_set_sta_local_pm(struct sta_info *sta,
+u64 ieee80211_mps_local_status_update(struct ieee80211_sub_if_data *sdata);
+u64 ieee80211_mps_set_sta_local_pm(struct sta_info *sta,
enum nl80211_mesh_power_mode pm);
void ieee80211_mps_set_frame_flags(struct ieee80211_sub_if_data *sdata,
struct sta_info *sta,
@@ -303,12 +304,12 @@ void mesh_neighbour_update(struct ieee80211_sub_if_data *sdata,
u8 *hw_addr, struct ieee802_11_elems *ie,
struct ieee80211_rx_status *rx_status);
bool mesh_peer_accepts_plinks(struct ieee802_11_elems *ie);
-u32 mesh_accept_plinks_update(struct ieee80211_sub_if_data *sdata);
+u64 mesh_accept_plinks_update(struct ieee80211_sub_if_data *sdata);
void mesh_plink_timer(struct timer_list *t);
void mesh_plink_broken(struct sta_info *sta);
-u32 mesh_plink_deactivate(struct sta_info *sta);
-u32 mesh_plink_open(struct sta_info *sta);
-u32 mesh_plink_block(struct sta_info *sta);
+u64 mesh_plink_deactivate(struct sta_info *sta);
+u64 mesh_plink_open(struct sta_info *sta);
+u64 mesh_plink_block(struct sta_info *sta);
void mesh_rx_plink_frame(struct ieee80211_sub_if_data *sdata,
struct ieee80211_mgmt *mgmt, size_t len,
struct ieee80211_rx_status *rx_status);
@@ -349,14 +350,14 @@ void mesh_path_refresh(struct ieee80211_sub_if_data *sdata,
#ifdef CONFIG_MAC80211_MESH
static inline
-u32 mesh_plink_inc_estab_count(struct ieee80211_sub_if_data *sdata)
+u64 mesh_plink_inc_estab_count(struct ieee80211_sub_if_data *sdata)
{
atomic_inc(&sdata->u.mesh.estab_plinks);
return mesh_accept_plinks_update(sdata) | BSS_CHANGED_BEACON;
}
static inline
-u32 mesh_plink_dec_estab_count(struct ieee80211_sub_if_data *sdata)
+u64 mesh_plink_dec_estab_count(struct ieee80211_sub_if_data *sdata)
{
atomic_dec(&sdata->u.mesh.estab_plinks);
return mesh_accept_plinks_update(sdata) | BSS_CHANGED_BEACON;
diff --git a/net/mac80211/mesh_hwmp.c b/net/mac80211/mesh_hwmp.c
index 5217e1d97dd6..51369072984e 100644
--- a/net/mac80211/mesh_hwmp.c
+++ b/net/mac80211/mesh_hwmp.c
@@ -1,7 +1,7 @@
// SPDX-License-Identifier: GPL-2.0-only
/*
* Copyright (c) 2008, 2009 open80211s Ltd.
- * Copyright (C) 2019, 2021-2022 Intel Corporation
+ * Copyright (C) 2019, 2021-2023 Intel Corporation
* Author: Luis Carlos Cobo <luisca@cozybit.com>
*/
@@ -1026,14 +1026,14 @@ static void mesh_queue_preq(struct mesh_path *mpath, u8 flags)
spin_unlock_bh(&ifmsh->mesh_preq_queue_lock);
if (time_after(jiffies, ifmsh->last_preq + min_preq_int_jiff(sdata)))
- ieee80211_queue_work(&sdata->local->hw, &sdata->work);
+ wiphy_work_queue(sdata->local->hw.wiphy, &sdata->work);
else if (time_before(jiffies, ifmsh->last_preq)) {
/* avoid long wait if did not send preqs for a long time
* and jiffies wrapped around
*/
ifmsh->last_preq = jiffies - min_preq_int_jiff(sdata) - 1;
- ieee80211_queue_work(&sdata->local->hw, &sdata->work);
+ wiphy_work_queue(sdata->local->hw.wiphy, &sdata->work);
} else
mod_timer(&ifmsh->mesh_path_timer, ifmsh->last_preq +
min_preq_int_jiff(sdata));
diff --git a/net/mac80211/mesh_plink.c b/net/mac80211/mesh_plink.c
index 8f168bc4e4b8..f3d5bb0a59f1 100644
--- a/net/mac80211/mesh_plink.c
+++ b/net/mac80211/mesh_plink.c
@@ -1,7 +1,7 @@
// SPDX-License-Identifier: GPL-2.0-only
/*
* Copyright (c) 2008, 2009 open80211s Ltd.
- * Copyright (C) 2019, 2021-2022 Intel Corporation
+ * Copyright (C) 2019, 2021-2023 Intel Corporation
* Author: Luis Carlos Cobo <luisca@cozybit.com>
*/
#include <linux/gfp.h>
@@ -90,12 +90,13 @@ static inline void mesh_plink_fsm_restart(struct sta_info *sta)
*
* Returns BSS_CHANGED_ERP_SLOT or 0 for no change.
*/
-static u32 mesh_set_short_slot_time(struct ieee80211_sub_if_data *sdata)
+static u64 mesh_set_short_slot_time(struct ieee80211_sub_if_data *sdata)
{
struct ieee80211_local *local = sdata->local;
struct ieee80211_supported_band *sband;
struct sta_info *sta;
- u32 erp_rates = 0, changed = 0;
+ u32 erp_rates = 0;
+ u64 changed = 0;
int i;
bool short_slot = false;
@@ -153,7 +154,7 @@ out:
* is selected if all peers in our 20/40MHz MBSS support HT and at least one
* HT20 peer is present. Otherwise no-protection mode is selected.
*/
-static u32 mesh_set_ht_prot_mode(struct ieee80211_sub_if_data *sdata)
+static u64 mesh_set_ht_prot_mode(struct ieee80211_sub_if_data *sdata)
{
struct ieee80211_local *local = sdata->local;
struct sta_info *sta;
@@ -365,10 +366,10 @@ free:
*
* Locking: the caller must hold sta->mesh->plink_lock
*/
-static u32 __mesh_plink_deactivate(struct sta_info *sta)
+static u64 __mesh_plink_deactivate(struct sta_info *sta)
{
struct ieee80211_sub_if_data *sdata = sta->sdata;
- u32 changed = 0;
+ u64 changed = 0;
lockdep_assert_held(&sta->mesh->plink_lock);
@@ -390,10 +391,10 @@ static u32 __mesh_plink_deactivate(struct sta_info *sta)
*
* All mesh paths with this peer as next hop will be flushed
*/
-u32 mesh_plink_deactivate(struct sta_info *sta)
+u64 mesh_plink_deactivate(struct sta_info *sta)
{
struct ieee80211_sub_if_data *sdata = sta->sdata;
- u32 changed;
+ u64 changed;
spin_lock_bh(&sta->mesh->plink_lock);
changed = __mesh_plink_deactivate(sta);
@@ -622,7 +623,7 @@ void mesh_neighbour_update(struct ieee80211_sub_if_data *sdata,
struct ieee80211_rx_status *rx_status)
{
struct sta_info *sta;
- u32 changed = 0;
+ u64 changed = 0;
sta = mesh_sta_info_get(sdata, hw_addr, elems, rx_status);
if (!sta)
@@ -775,10 +776,10 @@ static u16 mesh_get_new_llid(struct ieee80211_sub_if_data *sdata)
return llid;
}
-u32 mesh_plink_open(struct sta_info *sta)
+u64 mesh_plink_open(struct sta_info *sta)
{
struct ieee80211_sub_if_data *sdata = sta->sdata;
- u32 changed;
+ u64 changed;
if (!test_sta_flag(sta, WLAN_STA_AUTH))
return 0;
@@ -805,9 +806,9 @@ u32 mesh_plink_open(struct sta_info *sta)
return changed;
}
-u32 mesh_plink_block(struct sta_info *sta)
+u64 mesh_plink_block(struct sta_info *sta)
{
- u32 changed;
+ u64 changed;
spin_lock_bh(&sta->mesh->plink_lock);
changed = __mesh_plink_deactivate(sta);
@@ -831,11 +832,11 @@ static void mesh_plink_close(struct ieee80211_sub_if_data *sdata,
mod_plink_timer(sta, mshcfg->dot11MeshHoldingTimeout);
}
-static u32 mesh_plink_establish(struct ieee80211_sub_if_data *sdata,
+static u64 mesh_plink_establish(struct ieee80211_sub_if_data *sdata,
struct sta_info *sta)
{
struct mesh_config *mshcfg = &sdata->u.mesh.mshcfg;
- u32 changed = 0;
+ u64 changed = 0;
del_timer(&sta->mesh->plink_timer);
sta->mesh->plink_state = NL80211_PLINK_ESTAB;
@@ -857,12 +858,12 @@ static u32 mesh_plink_establish(struct ieee80211_sub_if_data *sdata,
*
* Return: changed MBSS flags
*/
-static u32 mesh_plink_fsm(struct ieee80211_sub_if_data *sdata,
+static u64 mesh_plink_fsm(struct ieee80211_sub_if_data *sdata,
struct sta_info *sta, enum plink_event event)
{
struct mesh_config *mshcfg = &sdata->u.mesh.mshcfg;
enum ieee80211_self_protected_actioncode action = 0;
- u32 changed = 0;
+ u64 changed = 0;
bool flush = false;
mpl_dbg(sdata, "peer %pM in state %s got event %s\n", sta->sta.addr,
@@ -1117,7 +1118,7 @@ mesh_process_plink_frame(struct ieee80211_sub_if_data *sdata,
struct sta_info *sta;
enum plink_event event;
enum ieee80211_self_protected_actioncode ftype;
- u32 changed = 0;
+ u64 changed = 0;
u8 ie_len = elems->peering_len;
u16 plid, llid = 0;
diff --git a/net/mac80211/mesh_ps.c b/net/mac80211/mesh_ps.c
index 3fbd0b9ff913..35eacca43e49 100644
--- a/net/mac80211/mesh_ps.c
+++ b/net/mac80211/mesh_ps.c
@@ -3,6 +3,7 @@
* Copyright 2012-2013, Marco Porsch <marco.porsch@s2005.tu-chemnitz.de>
* Copyright 2012-2013, cozybit Inc.
* Copyright (C) 2021 Intel Corporation
+ * Copyright (C) 2023 Intel Corporation
*/
#include "mesh.h"
@@ -77,14 +78,14 @@ static void mps_qos_null_tx(struct sta_info *sta)
* sets the non-peer power mode and triggers the driver PS (re-)configuration
* Return BSS_CHANGED_BEACON if a beacon update is necessary.
*/
-u32 ieee80211_mps_local_status_update(struct ieee80211_sub_if_data *sdata)
+u64 ieee80211_mps_local_status_update(struct ieee80211_sub_if_data *sdata)
{
struct ieee80211_if_mesh *ifmsh = &sdata->u.mesh;
struct sta_info *sta;
bool peering = false;
int light_sleep_cnt = 0;
int deep_sleep_cnt = 0;
- u32 changed = 0;
+ u64 changed = 0;
enum nl80211_mesh_power_mode nonpeer_pm;
rcu_read_lock();
@@ -148,7 +149,7 @@ u32 ieee80211_mps_local_status_update(struct ieee80211_sub_if_data *sdata)
* @pm: the power mode to set
* Return BSS_CHANGED_BEACON if a beacon update is in order.
*/
-u32 ieee80211_mps_set_sta_local_pm(struct sta_info *sta,
+u64 ieee80211_mps_set_sta_local_pm(struct sta_info *sta,
enum nl80211_mesh_power_mode pm)
{
struct ieee80211_sub_if_data *sdata = sta->sdata;
diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c
index 5a4303130ef2..f93eb38ae0b8 100644
--- a/net/mac80211/mlme.c
+++ b/net/mac80211/mlme.c
@@ -511,16 +511,14 @@ static int ieee80211_config_bw(struct ieee80211_link_data *link,
/* don't check HE if we associated as non-HE station */
if (link->u.mgd.conn_flags & IEEE80211_CONN_DISABLE_HE ||
- !ieee80211_get_he_iftype_cap(sband,
- ieee80211_vif_type_p2p(&sdata->vif))) {
+ !ieee80211_get_he_iftype_cap_vif(sband, &sdata->vif)) {
he_oper = NULL;
eht_oper = NULL;
}
/* don't check EHT if we associated as non-EHT station */
if (link->u.mgd.conn_flags & IEEE80211_CONN_DISABLE_EHT ||
- !ieee80211_get_eht_iftype_cap(sband,
- ieee80211_vif_type_p2p(&sdata->vif)))
+ !ieee80211_get_eht_iftype_cap_vif(sband, &sdata->vif))
eht_oper = NULL;
/*
@@ -776,8 +774,7 @@ static void ieee80211_add_he_ie(struct ieee80211_sub_if_data *sdata,
const struct ieee80211_sta_he_cap *he_cap;
u8 he_cap_size;
- he_cap = ieee80211_get_he_iftype_cap(sband,
- ieee80211_vif_type_p2p(&sdata->vif));
+ he_cap = ieee80211_get_he_iftype_cap_vif(sband, &sdata->vif);
if (WARN_ON(!he_cap))
return;
@@ -806,10 +803,8 @@ static void ieee80211_add_eht_ie(struct ieee80211_sub_if_data *sdata,
const struct ieee80211_sta_eht_cap *eht_cap;
u8 eht_cap_size;
- he_cap = ieee80211_get_he_iftype_cap(sband,
- ieee80211_vif_type_p2p(&sdata->vif));
- eht_cap = ieee80211_get_eht_iftype_cap(sband,
- ieee80211_vif_type_p2p(&sdata->vif));
+ he_cap = ieee80211_get_he_iftype_cap_vif(sband, &sdata->vif);
+ eht_cap = ieee80211_get_eht_iftype_cap_vif(sband, &sdata->vif);
/*
* EHT capabilities element is only added if the HE capabilities element
@@ -1287,7 +1282,7 @@ static void ieee80211_assoc_add_ml_elem(struct ieee80211_sub_if_data *sdata,
u8 *ml_elem_len;
void *capab_pos;
- if (!sdata->vif.valid_links)
+ if (!ieee80211_vif_is_mld(&sdata->vif))
return;
ift_ext_capa = cfg80211_get_iftype_ext_capa(local->hw.wiphy,
@@ -1462,7 +1457,7 @@ static int ieee80211_send_assoc(struct ieee80211_sub_if_data *sdata)
capab |= WLAN_CAPABILITY_PRIVACY;
}
- if (sdata->vif.valid_links) {
+ if (ieee80211_vif_is_mld(&sdata->vif)) {
/* consider the multi-link element with STA profile */
size += sizeof(struct ieee80211_multi_link_elem);
/* max common info field in basic multi-link element */
@@ -1680,10 +1675,12 @@ void ieee80211_send_4addr_nullfunc(struct ieee80211_local *local,
}
/* spectrum management related things */
-static void ieee80211_chswitch_work(struct work_struct *work)
+static void ieee80211_chswitch_work(struct wiphy *wiphy,
+ struct wiphy_work *work)
{
struct ieee80211_link_data *link =
- container_of(work, struct ieee80211_link_data, u.mgd.chswitch_work);
+ container_of(work, struct ieee80211_link_data,
+ u.mgd.chswitch_work.work);
struct ieee80211_sub_if_data *sdata = link->sdata;
struct ieee80211_local *local = sdata->local;
struct ieee80211_if_managed *ifmgd = &sdata->u.mgd;
@@ -1723,8 +1720,8 @@ static void ieee80211_chswitch_work(struct work_struct *work)
sdata_info(sdata,
"failed to use reserved channel context, disconnecting (err=%d)\n",
ret);
- ieee80211_queue_work(&sdata->local->hw,
- &ifmgd->csa_connection_drop_work);
+ wiphy_work_queue(sdata->local->hw.wiphy,
+ &ifmgd->csa_connection_drop_work);
goto out;
}
@@ -1735,8 +1732,8 @@ static void ieee80211_chswitch_work(struct work_struct *work)
&link->csa_chandef)) {
sdata_info(sdata,
"failed to finalize channel switch, disconnecting\n");
- ieee80211_queue_work(&sdata->local->hw,
- &ifmgd->csa_connection_drop_work);
+ wiphy_work_queue(sdata->local->hw.wiphy,
+ &ifmgd->csa_connection_drop_work);
goto out;
}
@@ -1780,8 +1777,8 @@ static void ieee80211_chswitch_post_beacon(struct ieee80211_link_data *link)
if (ret) {
sdata_info(sdata,
"driver post channel switch failed, disconnecting\n");
- ieee80211_queue_work(&local->hw,
- &ifmgd->csa_connection_drop_work);
+ wiphy_work_queue(sdata->local->hw.wiphy,
+ &ifmgd->csa_connection_drop_work);
return;
}
@@ -1793,31 +1790,23 @@ void ieee80211_chswitch_done(struct ieee80211_vif *vif, bool success)
struct ieee80211_sub_if_data *sdata = vif_to_sdata(vif);
struct ieee80211_if_managed *ifmgd = &sdata->u.mgd;
- if (WARN_ON(sdata->vif.valid_links))
+ if (WARN_ON(ieee80211_vif_is_mld(&sdata->vif)))
success = false;
trace_api_chswitch_done(sdata, success);
if (!success) {
sdata_info(sdata,
"driver channel switch failed, disconnecting\n");
- ieee80211_queue_work(&sdata->local->hw,
- &ifmgd->csa_connection_drop_work);
+ wiphy_work_queue(sdata->local->hw.wiphy,
+ &ifmgd->csa_connection_drop_work);
} else {
- ieee80211_queue_work(&sdata->local->hw,
- &sdata->deflink.u.mgd.chswitch_work);
+ wiphy_delayed_work_queue(sdata->local->hw.wiphy,
+ &sdata->deflink.u.mgd.chswitch_work,
+ 0);
}
}
EXPORT_SYMBOL(ieee80211_chswitch_done);
-static void ieee80211_chswitch_timer(struct timer_list *t)
-{
- struct ieee80211_link_data *link =
- from_timer(link, t, u.mgd.chswitch_timer);
-
- ieee80211_queue_work(&link->sdata->local->hw,
- &link->u.mgd.chswitch_work);
-}
-
static void
ieee80211_sta_abort_chanswitch(struct ieee80211_link_data *link)
{
@@ -1861,6 +1850,7 @@ ieee80211_sta_process_chanswitch(struct ieee80211_link_data *link,
struct ieee80211_csa_ie csa_ie;
struct ieee80211_channel_switch ch_switch;
struct ieee80211_bss *bss;
+ unsigned long timeout;
int res;
sdata_assert_lock(sdata);
@@ -1868,9 +1858,6 @@ ieee80211_sta_process_chanswitch(struct ieee80211_link_data *link,
if (!cbss)
return;
- if (local->scanning)
- return;
-
current_band = cbss->channel->band;
bss = (void *)cbss->priv;
res = ieee80211_parse_ch_switch_ie(sdata, elems, current_band,
@@ -1994,8 +1981,9 @@ ieee80211_sta_process_chanswitch(struct ieee80211_link_data *link,
IEEE80211_QUEUE_STOP_REASON_CSA);
mutex_unlock(&local->mtx);
- cfg80211_ch_switch_started_notify(sdata->dev, &csa_ie.chandef, 0,
- csa_ie.count, csa_ie.mode, 0);
+ cfg80211_ch_switch_started_notify(sdata->dev, &csa_ie.chandef,
+ link->link_id, csa_ie.count,
+ csa_ie.mode, 0);
if (local->ops->channel_switch) {
/* use driver's channel switch callback */
@@ -2004,12 +1992,11 @@ ieee80211_sta_process_chanswitch(struct ieee80211_link_data *link,
}
/* channel switch handled in software */
- if (csa_ie.count <= 1)
- ieee80211_queue_work(&local->hw, &link->u.mgd.chswitch_work);
- else
- mod_timer(&link->u.mgd.chswitch_timer,
- TU_TO_EXP_TIME((csa_ie.count - 1) *
- cbss->beacon_interval));
+ timeout = TU_TO_JIFFIES((max_t(int, csa_ie.count, 1) - 1) *
+ cbss->beacon_interval);
+ wiphy_delayed_work_queue(local->hw.wiphy,
+ &link->u.mgd.chswitch_work,
+ timeout);
return;
lock_and_drop_connection:
mutex_lock(&local->mtx);
@@ -2025,7 +2012,8 @@ ieee80211_sta_process_chanswitch(struct ieee80211_link_data *link,
link->conf->csa_active = true;
link->csa_block_tx = csa_ie.mode;
- ieee80211_queue_work(&local->hw, &ifmgd->csa_connection_drop_work);
+ wiphy_work_queue(sdata->local->hw.wiphy,
+ &ifmgd->csa_connection_drop_work);
mutex_unlock(&local->chanctx_mtx);
mutex_unlock(&local->mtx);
}
@@ -2116,7 +2104,7 @@ static void ieee80211_find_cisco_dtpc(struct ieee80211_sub_if_data *sdata,
*pwr_level = (__s8)cisco_dtpc_ie[4];
}
-static u32 ieee80211_handle_pwr_constr(struct ieee80211_link_data *link,
+static u64 ieee80211_handle_pwr_constr(struct ieee80211_link_data *link,
struct ieee80211_channel *channel,
struct ieee80211_mgmt *mgmt,
const u8 *country_ie, u8 country_ie_len,
@@ -2650,9 +2638,9 @@ ieee80211_sta_wmm_params(struct ieee80211_local *local,
params[ac].aifs = pos[0] & 0x0f;
if (params[ac].aifs < 2) {
- sdata_info(sdata,
- "AP has invalid WMM params (AIFSN=%d for ACI %d), will use 2\n",
- params[ac].aifs, aci);
+ link_info(link,
+ "AP has invalid WMM params (AIFSN=%d for ACI %d), will use 2\n",
+ params[ac].aifs, aci);
params[ac].aifs = 2;
}
params[ac].cw_max = ecw2cw((pos[1] & 0xf0) >> 4);
@@ -2663,9 +2651,9 @@ ieee80211_sta_wmm_params(struct ieee80211_local *local,
if (params[ac].cw_min == 0 ||
params[ac].cw_min > params[ac].cw_max) {
- sdata_info(sdata,
- "AP has invalid WMM params (CWmin/max=%d/%d for ACI %d), using defaults\n",
- params[ac].cw_min, params[ac].cw_max, aci);
+ link_info(link,
+ "AP has invalid WMM params (CWmin/max=%d/%d for ACI %d), using defaults\n",
+ params[ac].cw_min, params[ac].cw_max, aci);
return false;
}
ieee80211_regulatory_limit_wmm_params(sdata, &params[ac], ac);
@@ -2674,9 +2662,9 @@ ieee80211_sta_wmm_params(struct ieee80211_local *local,
/* WMM specification requires all 4 ACIs. */
for (ac = 0; ac < IEEE80211_NUM_ACS; ac++) {
if (params[ac].cw_min == 0) {
- sdata_info(sdata,
- "AP has invalid WMM params (missing AC %d), using defaults\n",
- ac);
+ link_info(link,
+ "AP has invalid WMM params (missing AC %d), using defaults\n",
+ ac);
return false;
}
}
@@ -2706,12 +2694,12 @@ static void ieee80211_stop_poll(struct ieee80211_sub_if_data *sdata)
mutex_unlock(&sdata->local->mtx);
}
-static u32 ieee80211_handle_bss_capability(struct ieee80211_link_data *link,
+static u64 ieee80211_handle_bss_capability(struct ieee80211_link_data *link,
u16 capab, bool erp_valid, u8 erp)
{
struct ieee80211_bss_conf *bss_conf = link->conf;
struct ieee80211_supported_band *sband;
- u32 changed = 0;
+ u64 changed = 0;
bool use_protection;
bool use_short_preamble;
bool use_short_slot;
@@ -2757,7 +2745,7 @@ static u64 ieee80211_link_set_associated(struct ieee80211_link_data *link,
struct ieee80211_sub_if_data *sdata = link->sdata;
struct ieee80211_bss_conf *bss_conf = link->conf;
struct ieee80211_bss *bss = (void *)cbss->priv;
- u32 changed = BSS_CHANGED_QOS;
+ u64 changed = BSS_CHANGED_QOS;
/* not really used in MLO */
sdata->u.mgd.beacon_timeout =
@@ -2831,6 +2819,10 @@ static void ieee80211_set_associated(struct ieee80211_sub_if_data *sdata,
assoc_data->link[link_id].status != WLAN_STATUS_SUCCESS)
continue;
+ if (ieee80211_vif_is_mld(&sdata->vif) &&
+ !(ieee80211_vif_usable_links(&sdata->vif) & BIT(link_id)))
+ continue;
+
link = sdata_dereference(sdata->link[link_id], sdata);
if (WARN_ON(!link))
return;
@@ -2849,7 +2841,7 @@ static void ieee80211_set_associated(struct ieee80211_sub_if_data *sdata,
if (vif_cfg->arp_addr_cnt)
vif_changed |= BSS_CHANGED_ARP_FILTER;
- if (sdata->vif.valid_links) {
+ if (ieee80211_vif_is_mld(&sdata->vif)) {
for (link_id = 0;
link_id < IEEE80211_MLD_MAX_NUM_LINKS;
link_id++) {
@@ -2857,6 +2849,8 @@ static void ieee80211_set_associated(struct ieee80211_sub_if_data *sdata,
struct cfg80211_bss *cbss = assoc_data->link[link_id].bss;
if (!cbss ||
+ !(BIT(link_id) &
+ ieee80211_vif_usable_links(&sdata->vif)) ||
assoc_data->link[link_id].status != WLAN_STATUS_SUCCESS)
continue;
@@ -2881,7 +2875,7 @@ static void ieee80211_set_associated(struct ieee80211_sub_if_data *sdata,
mutex_unlock(&local->iflist_mtx);
/* leave this here to not change ordering in non-MLO cases */
- if (!sdata->vif.valid_links)
+ if (!ieee80211_vif_is_mld(&sdata->vif))
ieee80211_recalc_smps(sdata, &sdata->deflink);
ieee80211_recalc_ps_vif(sdata);
@@ -2895,7 +2889,7 @@ static void ieee80211_set_disassoc(struct ieee80211_sub_if_data *sdata,
struct ieee80211_if_managed *ifmgd = &sdata->u.mgd;
struct ieee80211_local *local = sdata->local;
unsigned int link_id;
- u32 changed = 0;
+ u64 changed = 0;
struct ieee80211_prep_tx_info info = {
.subtype = stype,
};
@@ -2977,7 +2971,7 @@ static void ieee80211_set_disassoc(struct ieee80211_sub_if_data *sdata,
sta_info_flush(sdata);
/* finally reset all BSS / config parameters */
- if (!sdata->vif.valid_links)
+ if (!ieee80211_vif_is_mld(&sdata->vif))
changed |= ieee80211_reset_erp_info(sdata);
ieee80211_led_assoc(local, 0);
@@ -3002,7 +2996,7 @@ static void ieee80211_set_disassoc(struct ieee80211_sub_if_data *sdata,
sizeof(sdata->vif.bss_conf.mu_group.membership));
memset(sdata->vif.bss_conf.mu_group.position, 0,
sizeof(sdata->vif.bss_conf.mu_group.position));
- if (!sdata->vif.valid_links)
+ if (!ieee80211_vif_is_mld(&sdata->vif))
changed |= BSS_CHANGED_MU_GROUPS;
sdata->vif.bss_conf.mu_mimo_owner = false;
@@ -3016,7 +3010,7 @@ static void ieee80211_set_disassoc(struct ieee80211_sub_if_data *sdata,
changed |= BSS_CHANGED_ARP_FILTER;
sdata->vif.bss_conf.qos = false;
- if (!sdata->vif.valid_links) {
+ if (!ieee80211_vif_is_mld(&sdata->vif)) {
changed |= BSS_CHANGED_QOS;
/* The BSSID (not really interesting) and HT changed */
changed |= BSS_CHANGED_BSSID | BSS_CHANGED_HT;
@@ -3031,7 +3025,6 @@ static void ieee80211_set_disassoc(struct ieee80211_sub_if_data *sdata,
del_timer_sync(&sdata->u.mgd.conn_mon_timer);
del_timer_sync(&sdata->u.mgd.bcn_mon_timer);
del_timer_sync(&sdata->u.mgd.timer);
- del_timer_sync(&sdata->deflink.u.mgd.chswitch_timer);
sdata->vif.bss_conf.dtim_period = 0;
sdata->vif.bss_conf.beacon_rate = NULL;
@@ -3072,7 +3065,7 @@ static void ieee80211_set_disassoc(struct ieee80211_sub_if_data *sdata,
memset(sdata->vif.bss_conf.tx_pwr_env, 0,
sizeof(sdata->vif.bss_conf.tx_pwr_env));
- ieee80211_vif_set_links(sdata, 0);
+ ieee80211_vif_set_links(sdata, 0, 0);
}
static void ieee80211_reset_ap_probe(struct ieee80211_sub_if_data *sdata)
@@ -3162,7 +3155,7 @@ void ieee80211_sta_tx_notify(struct ieee80211_sub_if_data *sdata,
sdata->u.mgd.probe_send_count = 0;
else
sdata->u.mgd.nullfunc_failed = true;
- ieee80211_queue_work(&sdata->local->hw, &sdata->work);
+ wiphy_work_queue(sdata->local->hw.wiphy, &sdata->work);
}
static void ieee80211_mlme_send_probe_req(struct ieee80211_sub_if_data *sdata,
@@ -3186,7 +3179,7 @@ static void ieee80211_mgd_probe_ap_send(struct ieee80211_sub_if_data *sdata)
u8 unicast_limit = max(1, max_probe_tries - 3);
struct sta_info *sta;
- if (WARN_ON(sdata->vif.valid_links))
+ if (WARN_ON(ieee80211_vif_is_mld(&sdata->vif)))
return;
/*
@@ -3234,7 +3227,7 @@ static void ieee80211_mgd_probe_ap(struct ieee80211_sub_if_data *sdata,
struct ieee80211_if_managed *ifmgd = &sdata->u.mgd;
bool already = false;
- if (WARN_ON_ONCE(sdata->vif.valid_links))
+ if (WARN_ON_ONCE(ieee80211_vif_is_mld(&sdata->vif)))
return;
if (!ieee80211_sdata_running(sdata))
@@ -3309,7 +3302,7 @@ struct sk_buff *ieee80211_ap_probereq_get(struct ieee80211_hw *hw,
int ssid_len;
if (WARN_ON(sdata->vif.type != NL80211_IFTYPE_STATION ||
- sdata->vif.valid_links))
+ ieee80211_vif_is_mld(&sdata->vif)))
return NULL;
sdata_assert_lock(sdata);
@@ -3360,21 +3353,19 @@ static void ieee80211_report_disconnect(struct ieee80211_sub_if_data *sdata,
drv_event_callback(sdata->local, sdata, &event);
}
-static void __ieee80211_disconnect(struct ieee80211_sub_if_data *sdata)
+static void ___ieee80211_disconnect(struct ieee80211_sub_if_data *sdata)
{
struct ieee80211_local *local = sdata->local;
struct ieee80211_if_managed *ifmgd = &sdata->u.mgd;
u8 frame_buf[IEEE80211_DEAUTH_FRAME_LEN];
bool tx;
- sdata_lock(sdata);
- if (!ifmgd->associated) {
- sdata_unlock(sdata);
+ if (!ifmgd->associated)
return;
- }
/* in MLO assume we have a link where we can TX the frame */
- tx = sdata->vif.valid_links || !sdata->deflink.csa_block_tx;
+ tx = ieee80211_vif_is_mld(&sdata->vif) ||
+ !sdata->deflink.csa_block_tx;
if (!ifmgd->driver_disconnect) {
unsigned int link_id;
@@ -3419,11 +3410,17 @@ static void __ieee80211_disconnect(struct ieee80211_sub_if_data *sdata)
WLAN_REASON_DISASSOC_DUE_TO_INACTIVITY,
ifmgd->reconnect);
ifmgd->reconnect = false;
+}
+static void __ieee80211_disconnect(struct ieee80211_sub_if_data *sdata)
+{
+ sdata_lock(sdata);
+ ___ieee80211_disconnect(sdata);
sdata_unlock(sdata);
}
-static void ieee80211_beacon_connection_loss_work(struct work_struct *work)
+static void ieee80211_beacon_connection_loss_work(struct wiphy *wiphy,
+ struct wiphy_work *work)
{
struct ieee80211_sub_if_data *sdata =
container_of(work, struct ieee80211_sub_if_data,
@@ -3448,7 +3445,8 @@ static void ieee80211_beacon_connection_loss_work(struct work_struct *work)
}
}
-static void ieee80211_csa_connection_drop_work(struct work_struct *work)
+static void ieee80211_csa_connection_drop_work(struct wiphy *wiphy,
+ struct wiphy_work *work)
{
struct ieee80211_sub_if_data *sdata =
container_of(work, struct ieee80211_sub_if_data,
@@ -3465,7 +3463,7 @@ void ieee80211_beacon_loss(struct ieee80211_vif *vif)
trace_api_beacon_loss(sdata);
sdata->u.mgd.connection_loss = false;
- ieee80211_queue_work(hw, &sdata->u.mgd.beacon_connection_loss_work);
+ wiphy_work_queue(hw->wiphy, &sdata->u.mgd.beacon_connection_loss_work);
}
EXPORT_SYMBOL(ieee80211_beacon_loss);
@@ -3477,7 +3475,7 @@ void ieee80211_connection_loss(struct ieee80211_vif *vif)
trace_api_connection_loss(sdata);
sdata->u.mgd.connection_loss = true;
- ieee80211_queue_work(hw, &sdata->u.mgd.beacon_connection_loss_work);
+ wiphy_work_queue(hw->wiphy, &sdata->u.mgd.beacon_connection_loss_work);
}
EXPORT_SYMBOL(ieee80211_connection_loss);
@@ -3493,7 +3491,7 @@ void ieee80211_disconnect(struct ieee80211_vif *vif, bool reconnect)
sdata->u.mgd.driver_disconnect = true;
sdata->u.mgd.reconnect = reconnect;
- ieee80211_queue_work(hw, &sdata->u.mgd.beacon_connection_loss_work);
+ wiphy_work_queue(hw->wiphy, &sdata->u.mgd.beacon_connection_loss_work);
}
EXPORT_SYMBOL(ieee80211_disconnect);
@@ -3522,7 +3520,7 @@ static void ieee80211_destroy_auth_data(struct ieee80211_sub_if_data *sdata,
mutex_lock(&sdata->local->mtx);
ieee80211_link_release_channel(&sdata->deflink);
- ieee80211_vif_set_links(sdata, 0);
+ ieee80211_vif_set_links(sdata, 0, 0);
mutex_unlock(&sdata->local->mtx);
}
@@ -3573,7 +3571,7 @@ static void ieee80211_destroy_assoc_data(struct ieee80211_sub_if_data *sdata,
for (i = 0; i < ARRAY_SIZE(data.bss); i++)
data.bss[i] = assoc_data->link[i].bss;
- if (sdata->vif.valid_links)
+ if (ieee80211_vif_is_mld(&sdata->vif))
data.ap_mld_addr = assoc_data->ap_addr;
cfg80211_assoc_failure(sdata->dev, &data);
@@ -3581,7 +3579,7 @@ static void ieee80211_destroy_assoc_data(struct ieee80211_sub_if_data *sdata,
mutex_lock(&sdata->local->mtx);
ieee80211_link_release_channel(&sdata->deflink);
- ieee80211_vif_set_links(sdata, 0);
+ ieee80211_vif_set_links(sdata, 0, 0);
mutex_unlock(&sdata->local->mtx);
}
@@ -3909,8 +3907,8 @@ static void ieee80211_get_rates(struct ieee80211_supported_band *sband,
*have_higher_than_11mbit = true;
/*
- * Skip HT, VHT, HE and SAE H2E only BSS membership selectors
- * since they're not rates.
+ * Skip HT, VHT, HE, EHT and SAE H2E only BSS membership
+ * selectors since they're not rates.
*
* Note: Even though the membership selector and the basic
* rate flag share the same bit, they are not exactly
@@ -3919,6 +3917,7 @@ static void ieee80211_get_rates(struct ieee80211_supported_band *sband,
if (supp_rates[i] == (0x80 | BSS_MEMBERSHIP_SELECTOR_HT_PHY) ||
supp_rates[i] == (0x80 | BSS_MEMBERSHIP_SELECTOR_VHT_PHY) ||
supp_rates[i] == (0x80 | BSS_MEMBERSHIP_SELECTOR_HE_PHY) ||
+ supp_rates[i] == (0x80 | BSS_MEMBERSHIP_SELECTOR_EHT_PHY) ||
supp_rates[i] == (0x80 | BSS_MEMBERSHIP_SELECTOR_SAE_H2E))
continue;
@@ -3949,8 +3948,7 @@ static bool ieee80211_twt_req_supported(struct ieee80211_sub_if_data *sdata,
const struct ieee802_11_elems *elems)
{
const struct ieee80211_sta_he_cap *own_he_cap =
- ieee80211_get_he_iftype_cap(sband,
- ieee80211_vif_type_p2p(&sdata->vif));
+ ieee80211_get_he_iftype_cap_vif(sband, &sdata->vif);
if (elems->ext_capab_len < 10)
return false;
@@ -3965,7 +3963,7 @@ static bool ieee80211_twt_req_supported(struct ieee80211_sub_if_data *sdata,
IEEE80211_HE_MAC_CAP0_TWT_REQ);
}
-static int ieee80211_recalc_twt_req(struct ieee80211_sub_if_data *sdata,
+static u64 ieee80211_recalc_twt_req(struct ieee80211_sub_if_data *sdata,
struct ieee80211_supported_band *sband,
struct ieee80211_link_data *link,
struct link_sta_info *link_sta,
@@ -3986,8 +3984,7 @@ static bool ieee80211_twt_bcast_support(struct ieee80211_sub_if_data *sdata,
struct link_sta_info *link_sta)
{
const struct ieee80211_sta_he_cap *own_he_cap =
- ieee80211_get_he_iftype_cap(sband,
- ieee80211_vif_type_p2p(&sdata->vif));
+ ieee80211_get_he_iftype_cap_vif(sband, &sdata->vif);
return bss_conf->he_support &&
(link_sta->pub->he_cap.he_cap_elem.mac_cap_info[2] &
@@ -4021,6 +4018,8 @@ static bool ieee80211_assoc_config_link(struct ieee80211_link_data *link,
const struct cfg80211_bss_ies *bss_ies = NULL;
struct ieee80211_supported_band *sband;
struct ieee802_11_elems *elems;
+ const __le16 prof_bss_param_ch_present =
+ cpu_to_le16(IEEE80211_MLE_STA_CONTROL_BSS_PARAM_CHANGE_CNT_PRESENT);
u16 capab_info;
bool ret;
@@ -4036,7 +4035,17 @@ static bool ieee80211_assoc_config_link(struct ieee80211_link_data *link,
* successful, so set the status directly to success
*/
assoc_data->link[link_id].status = WLAN_STATUS_SUCCESS;
- } else if (!elems->prof) {
+ if (elems->ml_basic) {
+ if (!(elems->ml_basic->control &
+ cpu_to_le16(IEEE80211_MLC_BASIC_PRES_BSS_PARAM_CH_CNT))) {
+ ret = false;
+ goto out;
+ }
+ link->u.mgd.bss_param_ch_cnt =
+ ieee80211_mle_get_bss_param_ch_cnt(elems->ml_basic);
+ }
+ } else if (!elems->prof ||
+ !(elems->prof->control & prof_bss_param_ch_present)) {
ret = false;
goto out;
} else {
@@ -4049,6 +4058,8 @@ static bool ieee80211_assoc_config_link(struct ieee80211_link_data *link,
*/
capab_info = get_unaligned_le16(ptr);
assoc_data->link[link_id].status = get_unaligned_le16(ptr + 2);
+ link->u.mgd.bss_param_ch_cnt =
+ ieee80211_mle_basic_sta_prof_bss_param_ch_cnt(elems->prof);
if (assoc_data->link[link_id].status != WLAN_STATUS_SUCCESS) {
link_info(link, "association response status code=%u\n",
@@ -4624,8 +4635,7 @@ ieee80211_verify_sta_he_mcs_support(struct ieee80211_sub_if_data *sdata,
const struct ieee80211_he_operation *he_op)
{
const struct ieee80211_sta_he_cap *sta_he_cap =
- ieee80211_get_he_iftype_cap(sband,
- ieee80211_vif_type_p2p(&sdata->vif));
+ ieee80211_get_he_iftype_cap_vif(sband, &sdata->vif);
u16 ap_min_req_set;
int i;
@@ -4698,6 +4708,89 @@ ieee80211_verify_sta_he_mcs_support(struct ieee80211_sub_if_data *sdata,
return false;
}
+static u8
+ieee80211_get_eht_cap_mcs_nss(const struct ieee80211_sta_he_cap *sta_he_cap,
+ const struct ieee80211_sta_eht_cap *sta_eht_cap,
+ unsigned int idx, int bw)
+{
+ u8 he_phy_cap0 = sta_he_cap->he_cap_elem.phy_cap_info[0];
+ u8 eht_phy_cap0 = sta_eht_cap->eht_cap_elem.phy_cap_info[0];
+
+ /* handle us being a 20 MHz-only EHT STA - with four values
+ * for MCS 0-7, 8-9, 10-11, 12-13.
+ */
+ if (!(he_phy_cap0 & IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_MASK_ALL))
+ return sta_eht_cap->eht_mcs_nss_supp.only_20mhz.rx_tx_max_nss[idx];
+
+ /* the others have MCS 0-9 together, rather than separately from 0-7 */
+ if (idx > 0)
+ idx--;
+
+ switch (bw) {
+ case 0:
+ return sta_eht_cap->eht_mcs_nss_supp.bw._80.rx_tx_max_nss[idx];
+ case 1:
+ if (!(he_phy_cap0 &
+ (IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_160MHZ_IN_5G |
+ IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_80PLUS80_MHZ_IN_5G)))
+ return 0xff; /* pass check */
+ return sta_eht_cap->eht_mcs_nss_supp.bw._160.rx_tx_max_nss[idx];
+ case 2:
+ if (!(eht_phy_cap0 & IEEE80211_EHT_PHY_CAP0_320MHZ_IN_6GHZ))
+ return 0xff; /* pass check */
+ return sta_eht_cap->eht_mcs_nss_supp.bw._320.rx_tx_max_nss[idx];
+ }
+
+ WARN_ON(1);
+ return 0;
+}
+
+static bool
+ieee80211_verify_sta_eht_mcs_support(struct ieee80211_sub_if_data *sdata,
+ struct ieee80211_supported_band *sband,
+ const struct ieee80211_eht_operation *eht_op)
+{
+ const struct ieee80211_sta_he_cap *sta_he_cap =
+ ieee80211_get_he_iftype_cap_vif(sband, &sdata->vif);
+ const struct ieee80211_sta_eht_cap *sta_eht_cap =
+ ieee80211_get_eht_iftype_cap_vif(sband, &sdata->vif);
+ const struct ieee80211_eht_mcs_nss_supp_20mhz_only *req;
+ unsigned int i;
+
+ if (!sta_he_cap || !sta_eht_cap || !eht_op)
+ return false;
+
+ req = &eht_op->basic_mcs_nss;
+
+ for (i = 0; i < ARRAY_SIZE(req->rx_tx_max_nss); i++) {
+ u8 req_rx_nss, req_tx_nss;
+ unsigned int bw;
+
+ req_rx_nss = u8_get_bits(req->rx_tx_max_nss[i],
+ IEEE80211_EHT_MCS_NSS_RX);
+ req_tx_nss = u8_get_bits(req->rx_tx_max_nss[i],
+ IEEE80211_EHT_MCS_NSS_TX);
+
+ for (bw = 0; bw < 3; bw++) {
+ u8 have, have_rx_nss, have_tx_nss;
+
+ have = ieee80211_get_eht_cap_mcs_nss(sta_he_cap,
+ sta_eht_cap,
+ i, bw);
+ have_rx_nss = u8_get_bits(have,
+ IEEE80211_EHT_MCS_NSS_RX);
+ have_tx_nss = u8_get_bits(have,
+ IEEE80211_EHT_MCS_NSS_TX);
+
+ if (req_rx_nss > have_rx_nss ||
+ req_tx_nss > have_tx_nss)
+ return false;
+ }
+ }
+
+ return true;
+}
+
static int ieee80211_prep_channel(struct ieee80211_sub_if_data *sdata,
struct ieee80211_link_data *link,
struct cfg80211_bss *cbss,
@@ -4716,7 +4809,6 @@ static int ieee80211_prep_channel(struct ieee80211_sub_if_data *sdata,
bool is_5ghz = cbss->channel->band == NL80211_BAND_5GHZ;
struct ieee80211_bss *bss = (void *)cbss->priv;
struct ieee80211_elems_parse_params parse_params = {
- .bss = cbss,
.link_id = -1,
.from_ap = true,
};
@@ -4759,15 +4851,13 @@ static int ieee80211_prep_channel(struct ieee80211_sub_if_data *sdata,
*conn_flags |= IEEE80211_CONN_DISABLE_EHT;
}
- if (!ieee80211_get_he_iftype_cap(sband,
- ieee80211_vif_type_p2p(&sdata->vif))) {
+ if (!ieee80211_get_he_iftype_cap_vif(sband, &sdata->vif)) {
mlme_dbg(sdata, "HE not supported, disabling HE and EHT\n");
*conn_flags |= IEEE80211_CONN_DISABLE_HE;
*conn_flags |= IEEE80211_CONN_DISABLE_EHT;
}
- if (!ieee80211_get_eht_iftype_cap(sband,
- ieee80211_vif_type_p2p(&sdata->vif))) {
+ if (!ieee80211_get_eht_iftype_cap_vif(sband, &sdata->vif)) {
mlme_dbg(sdata, "EHT not supported, disabling EHT\n");
*conn_flags |= IEEE80211_CONN_DISABLE_EHT;
}
@@ -4844,6 +4934,7 @@ static int ieee80211_prep_channel(struct ieee80211_sub_if_data *sdata,
IEEE80211_CONN_DISABLE_EHT)) &&
he_oper) {
const struct cfg80211_bss_ies *cbss_ies;
+ const struct element *eht_ml_elem;
const u8 *eht_oper_ie;
cbss_ies = rcu_dereference(cbss->ies);
@@ -4854,6 +4945,24 @@ static int ieee80211_prep_channel(struct ieee80211_sub_if_data *sdata,
eht_oper = (void *)(eht_oper_ie + 3);
else
eht_oper = NULL;
+
+ if (!ieee80211_verify_sta_eht_mcs_support(sdata, sband, eht_oper))
+ *conn_flags |= IEEE80211_CONN_DISABLE_EHT;
+
+ eht_ml_elem = cfg80211_find_ext_elem(WLAN_EID_EXT_EHT_MULTI_LINK,
+ cbss_ies->data, cbss_ies->len);
+
+ /* data + 1 / datalen - 1 since it's an extended element */
+ if (!(*conn_flags & IEEE80211_CONN_DISABLE_EHT) &&
+ eht_ml_elem &&
+ ieee80211_mle_type_ok(eht_ml_elem->data + 1,
+ IEEE80211_ML_CONTROL_TYPE_BASIC,
+ eht_ml_elem->datalen - 1)) {
+ sdata->vif.cfg.eml_cap =
+ ieee80211_mle_get_eml_cap(eht_ml_elem->data + 1);
+ sdata->vif.cfg.eml_med_sync_delay =
+ ieee80211_mle_get_eml_med_sync_delay(eht_ml_elem->data + 1);
+ }
}
/* Allow VHT if at least one channel on the sband supports 80 MHz */
@@ -4980,7 +5089,7 @@ static bool ieee80211_assoc_success(struct ieee80211_sub_if_data *sdata,
unsigned int link_id;
struct sta_info *sta;
u64 changed[IEEE80211_MLD_MAX_NUM_LINKS] = {};
- u16 valid_links = 0;
+ u16 valid_links = 0, dormant_links = 0;
int err;
mutex_lock(&sdata->local->sta_mtx);
@@ -4992,20 +5101,22 @@ static bool ieee80211_assoc_success(struct ieee80211_sub_if_data *sdata,
if (WARN_ON(!sta))
goto out_err;
- if (sdata->vif.valid_links) {
+ if (ieee80211_vif_is_mld(&sdata->vif)) {
for (link_id = 0; link_id < IEEE80211_MLD_MAX_NUM_LINKS; link_id++) {
if (!assoc_data->link[link_id].bss)
continue;
- valid_links |= BIT(link_id);
- if (link_id != assoc_data->assoc_link_id) {
+ valid_links |= BIT(link_id);
+ if (assoc_data->link[link_id].disabled) {
+ dormant_links |= BIT(link_id);
+ } else if (link_id != assoc_data->assoc_link_id) {
err = ieee80211_sta_allocate_link(sta, link_id);
if (err)
goto out_err;
}
}
- ieee80211_vif_set_links(sdata, valid_links);
+ ieee80211_vif_set_links(sdata, valid_links, dormant_links);
}
for (link_id = 0; link_id < IEEE80211_MLD_MAX_NUM_LINKS; link_id++) {
@@ -5013,14 +5124,14 @@ static bool ieee80211_assoc_success(struct ieee80211_sub_if_data *sdata,
struct ieee80211_link_data *link;
struct link_sta_info *link_sta;
- if (!cbss)
+ if (!cbss || assoc_data->link[link_id].disabled)
continue;
link = sdata_dereference(sdata->link[link_id], sdata);
if (WARN_ON(!link))
goto out_err;
- if (sdata->vif.valid_links)
+ if (ieee80211_vif_is_mld(&sdata->vif))
link_info(link,
"local address %pM, AP link address %pM%s\n",
link->conf->addr,
@@ -5085,7 +5196,7 @@ static bool ieee80211_assoc_success(struct ieee80211_sub_if_data *sdata,
}
/* links might have changed due to rejected ones, set them again */
- ieee80211_vif_set_links(sdata, valid_links);
+ ieee80211_vif_set_links(sdata, valid_links, dormant_links);
rate_control_rate_init(sta);
@@ -5269,25 +5380,25 @@ static void ieee80211_rx_mgmt_assoc_resp(struct ieee80211_sub_if_data *sdata,
ifmgd->broken_ap = true;
}
- if (sdata->vif.valid_links) {
- if (!elems->multi_link) {
+ if (ieee80211_vif_is_mld(&sdata->vif)) {
+ if (!elems->ml_basic) {
sdata_info(sdata,
"MLO association with %pM but no multi-link element in response!\n",
assoc_data->ap_addr);
goto abandon_assoc;
}
- if (le16_get_bits(elems->multi_link->control,
+ if (le16_get_bits(elems->ml_basic->control,
IEEE80211_ML_CONTROL_TYPE) !=
IEEE80211_ML_CONTROL_TYPE_BASIC) {
sdata_info(sdata,
"bad multi-link element (control=0x%x)\n",
- le16_to_cpu(elems->multi_link->control));
+ le16_to_cpu(elems->ml_basic->control));
goto abandon_assoc;
} else {
struct ieee80211_mle_basic_common_info *common;
- common = (void *)elems->multi_link->variable;
+ common = (void *)elems->ml_basic->variable;
if (memcmp(assoc_data->ap_addr,
common->mld_mac_addr, ETH_ALEN)) {
@@ -5336,7 +5447,7 @@ static void ieee80211_rx_mgmt_assoc_resp(struct ieee80211_sub_if_data *sdata,
resp.uapsd_queues |= ieee80211_ac_to_qos_mask[ac];
}
- if (sdata->vif.valid_links) {
+ if (ieee80211_vif_is_mld(&sdata->vif)) {
ether_addr_copy(ap_mld_addr, sdata->vif.cfg.ap_addr);
resp.ap_mld_addr = ap_mld_addr;
}
@@ -5598,6 +5709,169 @@ static bool ieee80211_config_puncturing(struct ieee80211_link_data *link,
return true;
}
+static void ieee80211_ml_reconf_work(struct wiphy *wiphy,
+ struct wiphy_work *work)
+{
+ struct ieee80211_sub_if_data *sdata =
+ container_of(work, struct ieee80211_sub_if_data,
+ u.mgd.ml_reconf_work.work);
+ u16 new_valid_links, new_active_links, new_dormant_links;
+ int ret;
+
+ sdata_lock(sdata);
+ if (!sdata->u.mgd.removed_links) {
+ sdata_unlock(sdata);
+ return;
+ }
+
+ sdata_info(sdata,
+ "MLO Reconfiguration: work: valid=0x%x, removed=0x%x\n",
+ sdata->vif.valid_links, sdata->u.mgd.removed_links);
+
+ new_valid_links = sdata->vif.valid_links & ~sdata->u.mgd.removed_links;
+ if (new_valid_links == sdata->vif.valid_links) {
+ sdata_unlock(sdata);
+ return;
+ }
+
+ if (!new_valid_links ||
+ !(new_valid_links & ~sdata->vif.dormant_links)) {
+ sdata_info(sdata, "No valid links after reconfiguration\n");
+ ret = -EINVAL;
+ goto out;
+ }
+
+ new_active_links = sdata->vif.active_links & ~sdata->u.mgd.removed_links;
+ if (new_active_links != sdata->vif.active_links) {
+ if (!new_active_links)
+ new_active_links =
+ BIT(ffs(new_valid_links &
+ ~sdata->vif.dormant_links) - 1);
+
+ ret = __ieee80211_set_active_links(&sdata->vif,
+ new_active_links);
+ if (ret) {
+ sdata_info(sdata,
+ "Failed setting active links\n");
+ goto out;
+ }
+ }
+
+ new_dormant_links = sdata->vif.dormant_links & ~sdata->u.mgd.removed_links;
+
+ ret = ieee80211_vif_set_links(sdata, new_valid_links,
+ new_dormant_links);
+ if (ret)
+ sdata_info(sdata, "Failed setting valid links\n");
+
+out:
+ if (!ret)
+ cfg80211_links_removed(sdata->dev, sdata->u.mgd.removed_links);
+ else
+ ___ieee80211_disconnect(sdata);
+
+ sdata->u.mgd.removed_links = 0;
+
+ sdata_unlock(sdata);
+}
+
+static void ieee80211_ml_reconfiguration(struct ieee80211_sub_if_data *sdata,
+ struct ieee802_11_elems *elems)
+{
+ const struct ieee80211_multi_link_elem *ml;
+ const struct element *sub;
+ size_t ml_len;
+ unsigned long removed_links = 0;
+ u16 link_removal_timeout[IEEE80211_MLD_MAX_NUM_LINKS] = {};
+ u8 link_id;
+ u32 delay;
+
+ if (!ieee80211_vif_is_mld(&sdata->vif) || !elems->ml_reconf)
+ return;
+
+ ml_len = cfg80211_defragment_element(elems->ml_reconf_elem,
+ elems->ie_start,
+ elems->total_len,
+ elems->scratch_pos,
+ elems->scratch + elems->scratch_len -
+ elems->scratch_pos,
+ WLAN_EID_FRAGMENT);
+
+ elems->ml_reconf = (const void *)elems->scratch_pos;
+ elems->ml_reconf_len = ml_len;
+ ml = elems->ml_reconf;
+
+ /* Directly parse the sub elements as the common information doesn't
+ * hold any useful information.
+ */
+ for_each_mle_subelement(sub, (u8 *)ml, ml_len) {
+ struct ieee80211_mle_per_sta_profile *prof = (void *)sub->data;
+ u8 *pos = prof->variable;
+ u16 control;
+
+ if (sub->id != IEEE80211_MLE_SUBELEM_PER_STA_PROFILE)
+ continue;
+
+ if (!ieee80211_mle_reconf_sta_prof_size_ok(sub->data,
+ sub->datalen))
+ return;
+
+ control = le16_to_cpu(prof->control);
+ link_id = control & IEEE80211_MLE_STA_RECONF_CONTROL_LINK_ID;
+
+ removed_links |= BIT(link_id);
+
+ /* the MAC address should not be included, but handle it */
+ if (control &
+ IEEE80211_MLE_STA_RECONF_CONTROL_STA_MAC_ADDR_PRESENT)
+ pos += 6;
+
+ /* According to Draft P802.11be_D3.0, the control should
+ * include the AP Removal Timer present. If the AP Removal Timer
+ * is not present assume immediate removal.
+ */
+ if (control &
+ IEEE80211_MLE_STA_RECONF_CONTROL_AP_REM_TIMER_PRESENT)
+ link_removal_timeout[link_id] = le16_to_cpu(*(__le16 *)pos);
+ }
+
+ removed_links &= sdata->vif.valid_links;
+ if (!removed_links) {
+ /* In case the removal was cancelled, abort it */
+ if (sdata->u.mgd.removed_links) {
+ sdata->u.mgd.removed_links = 0;
+ wiphy_delayed_work_cancel(sdata->local->hw.wiphy,
+ &sdata->u.mgd.ml_reconf_work);
+ }
+ return;
+ }
+
+ delay = 0;
+ for_each_set_bit(link_id, &removed_links, IEEE80211_MLD_MAX_NUM_LINKS) {
+ struct ieee80211_bss_conf *link_conf =
+ sdata_dereference(sdata->vif.link_conf[link_id], sdata);
+ u32 link_delay;
+
+ if (!link_conf) {
+ removed_links &= ~BIT(link_id);
+ continue;
+ }
+
+ link_delay = link_conf->beacon_int *
+ link_removal_timeout[link_id];
+
+ if (!delay)
+ delay = link_delay;
+ else
+ delay = min(delay, link_delay);
+ }
+
+ sdata->u.mgd.removed_links = removed_links;
+ wiphy_delayed_work_queue(sdata->local->hw.wiphy,
+ &sdata->u.mgd.ml_reconf_work,
+ TU_TO_JIFFIES(delay));
+}
+
static void ieee80211_rx_mgmt_beacon(struct ieee80211_link_data *link,
struct ieee80211_hdr *hdr, size_t len,
struct ieee80211_rx_status *rx_status)
@@ -5662,7 +5936,7 @@ static void ieee80211_rx_mgmt_beacon(struct ieee80211_link_data *link,
rcu_read_unlock();
if (ifmgd->assoc_data && ifmgd->assoc_data->need_beacon &&
- !WARN_ON(sdata->vif.valid_links) &&
+ !WARN_ON(ieee80211_vif_is_mld(&sdata->vif)) &&
ieee80211_rx_our_beacon(bssid, ifmgd->assoc_data->link[0].bss)) {
parse_params.bss = ifmgd->assoc_data->link[0].bss;
elems = ieee802_11_parse_elems_full(&parse_params);
@@ -5927,6 +6201,8 @@ static void ieee80211_rx_mgmt_beacon(struct ieee80211_link_data *link,
}
}
+ ieee80211_ml_reconfiguration(sdata, elems);
+
ieee80211_link_info_change_notify(sdata, link, changed);
free:
kfree(elems);
@@ -5997,6 +6273,10 @@ void ieee80211_sta_rx_queued_mgmt(struct ieee80211_sub_if_data *sdata,
ieee80211_rx_mgmt_assoc_resp(sdata, mgmt, skb->len);
break;
case IEEE80211_STYPE_ACTION:
+ if (!sdata->u.mgd.associated ||
+ !ether_addr_equal(mgmt->bssid, sdata->vif.cfg.ap_addr))
+ break;
+
if (mgmt->u.action.category == WLAN_CATEGORY_SPECTRUM_MGMT) {
struct ieee802_11_elems *elems;
@@ -6060,7 +6340,7 @@ static void ieee80211_sta_timer(struct timer_list *t)
struct ieee80211_sub_if_data *sdata =
from_timer(sdata, t, u.mgd.timer);
- ieee80211_queue_work(&sdata->local->hw, &sdata->work);
+ wiphy_work_queue(sdata->local->hw.wiphy, &sdata->work);
}
void ieee80211_sta_connection_lost(struct ieee80211_sub_if_data *sdata,
@@ -6204,7 +6484,7 @@ void ieee80211_mgd_conn_tx_status(struct ieee80211_sub_if_data *sdata,
sdata->u.mgd.status_acked = acked;
sdata->u.mgd.status_received = true;
- ieee80211_queue_work(&local->hw, &sdata->work);
+ wiphy_work_queue(local->hw.wiphy, &sdata->work);
}
void ieee80211_sta_work(struct ieee80211_sub_if_data *sdata)
@@ -6356,7 +6636,7 @@ static void ieee80211_sta_bcn_mon_timer(struct timer_list *t)
struct ieee80211_sub_if_data *sdata =
from_timer(sdata, t, u.mgd.bcn_mon_timer);
- if (WARN_ON(sdata->vif.valid_links))
+ if (WARN_ON(ieee80211_vif_is_mld(&sdata->vif)))
return;
if (sdata->vif.bss_conf.csa_active &&
@@ -6367,8 +6647,8 @@ static void ieee80211_sta_bcn_mon_timer(struct timer_list *t)
return;
sdata->u.mgd.connection_loss = false;
- ieee80211_queue_work(&sdata->local->hw,
- &sdata->u.mgd.beacon_connection_loss_work);
+ wiphy_work_queue(sdata->local->hw.wiphy,
+ &sdata->u.mgd.beacon_connection_loss_work);
}
static void ieee80211_sta_conn_mon_timer(struct timer_list *t)
@@ -6380,7 +6660,7 @@ static void ieee80211_sta_conn_mon_timer(struct timer_list *t)
struct sta_info *sta;
unsigned long timeout;
- if (WARN_ON(sdata->vif.valid_links))
+ if (WARN_ON(ieee80211_vif_is_mld(&sdata->vif)))
return;
if (sdata->vif.bss_conf.csa_active &&
@@ -6524,7 +6804,8 @@ void ieee80211_sta_restart(struct ieee80211_sub_if_data *sdata)
sdata_unlock(sdata);
}
-static void ieee80211_request_smps_mgd_work(struct work_struct *work)
+static void ieee80211_request_smps_mgd_work(struct wiphy *wiphy,
+ struct wiphy_work *work)
{
struct ieee80211_link_data *link =
container_of(work, struct ieee80211_link_data,
@@ -6542,12 +6823,14 @@ void ieee80211_sta_setup_sdata(struct ieee80211_sub_if_data *sdata)
struct ieee80211_if_managed *ifmgd = &sdata->u.mgd;
INIT_WORK(&ifmgd->monitor_work, ieee80211_sta_monitor_work);
- INIT_WORK(&ifmgd->beacon_connection_loss_work,
- ieee80211_beacon_connection_loss_work);
- INIT_WORK(&ifmgd->csa_connection_drop_work,
- ieee80211_csa_connection_drop_work);
+ wiphy_work_init(&ifmgd->beacon_connection_loss_work,
+ ieee80211_beacon_connection_loss_work);
+ wiphy_work_init(&ifmgd->csa_connection_drop_work,
+ ieee80211_csa_connection_drop_work);
INIT_DELAYED_WORK(&ifmgd->tdls_peer_del_work,
ieee80211_tdls_peer_del_work);
+ wiphy_delayed_work_init(&ifmgd->ml_reconf_work,
+ ieee80211_ml_reconf_work);
timer_setup(&ifmgd->timer, ieee80211_sta_timer, 0);
timer_setup(&ifmgd->bcn_mon_timer, ieee80211_sta_bcn_mon_timer, 0);
timer_setup(&ifmgd->conn_mon_timer, ieee80211_sta_conn_mon_timer, 0);
@@ -6574,15 +6857,15 @@ void ieee80211_mgd_setup_link(struct ieee80211_link_data *link)
link->u.mgd.conn_flags = 0;
link->conf->bssid = link->u.mgd.bssid;
- INIT_WORK(&link->u.mgd.request_smps_work,
- ieee80211_request_smps_mgd_work);
+ wiphy_work_init(&link->u.mgd.request_smps_work,
+ ieee80211_request_smps_mgd_work);
if (local->hw.wiphy->features & NL80211_FEATURE_DYNAMIC_SMPS)
link->u.mgd.req_smps = IEEE80211_SMPS_AUTOMATIC;
else
link->u.mgd.req_smps = IEEE80211_SMPS_OFF;
- INIT_WORK(&link->u.mgd.chswitch_work, ieee80211_chswitch_work);
- timer_setup(&link->u.mgd.chswitch_timer, ieee80211_chswitch_timer, 0);
+ wiphy_delayed_work_init(&link->u.mgd.chswitch_work,
+ ieee80211_chswitch_work);
if (sdata->u.mgd.assoc_data)
ether_addr_copy(link->conf->addr,
@@ -6623,12 +6906,12 @@ static int ieee80211_prep_connection(struct ieee80211_sub_if_data *sdata,
mlo = true;
if (WARN_ON(!ap_mld_addr))
return -EINVAL;
- err = ieee80211_vif_set_links(sdata, BIT(link_id));
+ err = ieee80211_vif_set_links(sdata, BIT(link_id), 0);
} else {
if (WARN_ON(ap_mld_addr))
return -EINVAL;
ap_mld_addr = cbss->bssid;
- err = ieee80211_vif_set_links(sdata, 0);
+ err = ieee80211_vif_set_links(sdata, 0, 0);
link_id = 0;
mlo = false;
}
@@ -6780,7 +7063,7 @@ static int ieee80211_prep_connection(struct ieee80211_sub_if_data *sdata,
out_err:
ieee80211_link_release_channel(&sdata->deflink);
- ieee80211_vif_set_links(sdata, 0);
+ ieee80211_vif_set_links(sdata, 0, 0);
return err;
}
@@ -6935,7 +7218,7 @@ int ieee80211_mgd_auth(struct ieee80211_sub_if_data *sdata,
return 0;
err_clear:
- if (!sdata->vif.valid_links) {
+ if (!ieee80211_vif_is_mld(&sdata->vif)) {
eth_zero_addr(sdata->deflink.u.mgd.bssid);
ieee80211_link_info_change_notify(sdata, &sdata->deflink,
BSS_CHANGED_BSSID);
@@ -7320,10 +7603,11 @@ int ieee80211_mgd_assoc(struct ieee80211_sub_if_data *sdata,
for (i = 0; i < ARRAY_SIZE(assoc_data->link); i++) {
assoc_data->link[i].conn_flags = conn_flags;
assoc_data->link[i].bss = req->links[i].bss;
+ assoc_data->link[i].disabled = req->links[i].disabled;
}
/* if there was no authentication, set up the link */
- err = ieee80211_vif_set_links(sdata, BIT(assoc_link_id));
+ err = ieee80211_vif_set_links(sdata, BIT(assoc_link_id), 0);
if (err)
goto err_clear;
} else {
@@ -7538,8 +7822,10 @@ int ieee80211_mgd_disassoc(struct ieee80211_sub_if_data *sdata,
void ieee80211_mgd_stop_link(struct ieee80211_link_data *link)
{
- cancel_work_sync(&link->u.mgd.request_smps_work);
- cancel_work_sync(&link->u.mgd.chswitch_work);
+ wiphy_work_cancel(link->sdata->local->hw.wiphy,
+ &link->u.mgd.request_smps_work);
+ wiphy_delayed_work_cancel(link->sdata->local->hw.wiphy,
+ &link->u.mgd.chswitch_work);
}
void ieee80211_mgd_stop(struct ieee80211_sub_if_data *sdata)
@@ -7552,9 +7838,13 @@ void ieee80211_mgd_stop(struct ieee80211_sub_if_data *sdata)
* cancelled when disconnecting.
*/
cancel_work_sync(&ifmgd->monitor_work);
- cancel_work_sync(&ifmgd->beacon_connection_loss_work);
- cancel_work_sync(&ifmgd->csa_connection_drop_work);
+ wiphy_work_cancel(sdata->local->hw.wiphy,
+ &ifmgd->beacon_connection_loss_work);
+ wiphy_work_cancel(sdata->local->hw.wiphy,
+ &ifmgd->csa_connection_drop_work);
cancel_delayed_work_sync(&ifmgd->tdls_peer_del_work);
+ wiphy_delayed_work_cancel(sdata->local->hw.wiphy,
+ &ifmgd->ml_reconf_work);
sdata_lock(sdata);
if (ifmgd->assoc_data)
diff --git a/net/mac80211/ocb.c b/net/mac80211/ocb.c
index a57dcbe99a0d..b44896e14522 100644
--- a/net/mac80211/ocb.c
+++ b/net/mac80211/ocb.c
@@ -4,7 +4,7 @@
*
* Copyright: (c) 2014 Czech Technical University in Prague
* (c) 2014 Volkswagen Group Research
- * Copyright (C) 2022 Intel Corporation
+ * Copyright (C) 2022 - 2023 Intel Corporation
* Author: Rostislav Lisovy <rostislav.lisovy@fel.cvut.cz>
* Funded by: Volkswagen Group Research
*/
@@ -81,7 +81,7 @@ void ieee80211_ocb_rx_no_sta(struct ieee80211_sub_if_data *sdata,
spin_lock(&ifocb->incomplete_lock);
list_add(&sta->list, &ifocb->incomplete_stations);
spin_unlock(&ifocb->incomplete_lock);
- ieee80211_queue_work(&local->hw, &sdata->work);
+ wiphy_work_queue(local->hw.wiphy, &sdata->work);
}
static struct sta_info *ieee80211_ocb_finish_sta(struct sta_info *sta)
@@ -157,7 +157,7 @@ static void ieee80211_ocb_housekeeping_timer(struct timer_list *t)
set_bit(OCB_WORK_HOUSEKEEPING, &ifocb->wrkq_flags);
- ieee80211_queue_work(&local->hw, &sdata->work);
+ wiphy_work_queue(local->hw.wiphy, &sdata->work);
}
void ieee80211_ocb_setup_sdata(struct ieee80211_sub_if_data *sdata)
@@ -175,7 +175,7 @@ int ieee80211_ocb_join(struct ieee80211_sub_if_data *sdata,
{
struct ieee80211_local *local = sdata->local;
struct ieee80211_if_ocb *ifocb = &sdata->u.ocb;
- u32 changed = BSS_CHANGED_OCB | BSS_CHANGED_BSSID;
+ u64 changed = BSS_CHANGED_OCB | BSS_CHANGED_BSSID;
int err;
if (ifocb->joined == true)
@@ -197,7 +197,7 @@ int ieee80211_ocb_join(struct ieee80211_sub_if_data *sdata,
ifocb->joined = true;
set_bit(OCB_WORK_HOUSEKEEPING, &ifocb->wrkq_flags);
- ieee80211_queue_work(&local->hw, &sdata->work);
+ wiphy_work_queue(local->hw.wiphy, &sdata->work);
netif_carrier_on(sdata->dev);
return 0;
diff --git a/net/mac80211/offchannel.c b/net/mac80211/offchannel.c
index d78c82d6b696..cdf991e74ab9 100644
--- a/net/mac80211/offchannel.c
+++ b/net/mac80211/offchannel.c
@@ -8,7 +8,7 @@
* Copyright 2006-2007 Jiri Benc <jbenc@suse.cz>
* Copyright 2007, Michael Wu <flamingice@sourmilk.net>
* Copyright 2009 Johannes Berg <johannes@sipsolutions.net>
- * Copyright (C) 2019, 2022 Intel Corporation
+ * Copyright (C) 2019, 2022-2023 Intel Corporation
*/
#include <linux/export.h>
#include <net/mac80211.h>
@@ -1014,7 +1014,7 @@ void ieee80211_roc_purge(struct ieee80211_local *local,
if (roc->started) {
if (local->ops->remain_on_channel) {
/* can race, so ignore return value */
- drv_cancel_remain_on_channel(local, sdata);
+ drv_cancel_remain_on_channel(local, roc->sdata);
ieee80211_roc_notify_destroy(roc);
} else {
roc->abort = true;
diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c
index fc6e130364da..4f707d2a160f 100644
--- a/net/mac80211/rx.c
+++ b/net/mac80211/rx.c
@@ -6,7 +6,7 @@
* Copyright 2007-2010 Johannes Berg <johannes@sipsolutions.net>
* Copyright 2013-2014 Intel Mobile Communications GmbH
* Copyright(c) 2015 - 2017 Intel Deutschland GmbH
- * Copyright (C) 2018-2022 Intel Corporation
+ * Copyright (C) 2018-2023 Intel Corporation
*/
#include <linux/jiffies.h>
@@ -229,7 +229,7 @@ static void __ieee80211_queue_skb_to_iface(struct ieee80211_sub_if_data *sdata,
}
skb_queue_tail(&sdata->skb_queue, skb);
- ieee80211_queue_work(&sdata->local->hw, &sdata->work);
+ wiphy_work_queue(sdata->local->hw.wiphy, &sdata->work);
if (sta)
sta->deflink.rx_stats.packets++;
}
@@ -1732,7 +1732,7 @@ ieee80211_rx_h_sta_process(struct ieee80211_rx_data *rx)
if (ether_addr_equal(bssid, rx->sdata->u.ibss.bssid) &&
test_sta_flag(sta, WLAN_STA_AUTHORIZED)) {
link_sta->rx_stats.last_rx = jiffies;
- if (ieee80211_is_data(hdr->frame_control) &&
+ if (ieee80211_is_data_present(hdr->frame_control) &&
!is_multicast_ether_addr(hdr->addr1))
link_sta->rx_stats.last_rate =
sta_stats_encode_rate(status);
@@ -1746,7 +1746,7 @@ ieee80211_rx_h_sta_process(struct ieee80211_rx_data *rx)
* match the current local configuration when processed.
*/
link_sta->rx_stats.last_rx = jiffies;
- if (ieee80211_is_data(hdr->frame_control))
+ if (ieee80211_is_data_present(hdr->frame_control))
link_sta->rx_stats.last_rate = sta_stats_encode_rate(status);
}
@@ -2405,9 +2405,9 @@ static int ieee80211_drop_unencrypted(struct ieee80211_rx_data *rx, __le16 fc)
static int ieee80211_drop_unencrypted_mgmt(struct ieee80211_rx_data *rx)
{
- struct ieee80211_hdr *hdr = (struct ieee80211_hdr *)rx->skb->data;
struct ieee80211_rx_status *status = IEEE80211_SKB_RXCB(rx->skb);
- __le16 fc = hdr->frame_control;
+ struct ieee80211_mgmt *mgmt = (void *)rx->skb->data;
+ __le16 fc = mgmt->frame_control;
/*
* Pass through unencrypted frames if the hardware has
@@ -2416,15 +2416,27 @@ static int ieee80211_drop_unencrypted_mgmt(struct ieee80211_rx_data *rx)
if (status->flag & RX_FLAG_DECRYPTED)
return 0;
+ /* drop unicast protected dual (that wasn't protected) */
+ if (ieee80211_is_action(fc) &&
+ mgmt->u.action.category == WLAN_CATEGORY_PROTECTED_DUAL_OF_ACTION)
+ return -EACCES;
+
if (rx->sta && test_sta_flag(rx->sta, WLAN_STA_MFP)) {
if (unlikely(!ieee80211_has_protected(fc) &&
- ieee80211_is_unicast_robust_mgmt_frame(rx->skb) &&
- rx->key)) {
+ ieee80211_is_unicast_robust_mgmt_frame(rx->skb))) {
if (ieee80211_is_deauth(fc) ||
- ieee80211_is_disassoc(fc))
+ ieee80211_is_disassoc(fc)) {
+ /*
+ * Permit unprotected deauth/disassoc frames
+ * during 4-way-HS (key is installed after HS).
+ */
+ if (!rx->key)
+ return 0;
+
cfg80211_rx_unprot_mlme_mgmt(rx->sdata->dev,
rx->skb->data,
rx->skb->len);
+ }
return -EACCES;
}
/* BIP does not use Protected field, so need to check MMIE */
@@ -2451,6 +2463,12 @@ static int ieee80211_drop_unencrypted_mgmt(struct ieee80211_rx_data *rx)
if (unlikely(ieee80211_is_action(fc) && !rx->key &&
ieee80211_is_robust_mgmt_frame(rx->skb)))
return -EACCES;
+
+ /* drop unicast public action frames when using MPF */
+ if (is_unicast_ether_addr(mgmt->da) &&
+ ieee80211_is_public_action((void *)rx->skb->data,
+ rx->skb->len))
+ return -EACCES;
}
return 0;
@@ -2505,7 +2523,7 @@ bool ieee80211_is_our_addr(struct ieee80211_sub_if_data *sdata,
if (ether_addr_equal(sdata->vif.addr, addr))
return true;
- if (!sdata->vif.valid_links)
+ if (!ieee80211_vif_is_mld(&sdata->vif))
return false;
for (link_id = 0; link_id < ARRAY_SIZE(sdata->vif.link_conf); link_id++) {
@@ -3356,6 +3374,11 @@ ieee80211_rx_h_mgmt_check(struct ieee80211_rx_data *rx)
if (!ieee80211_is_mgmt(mgmt->frame_control))
return RX_DROP_MONITOR;
+ /* drop too small action frames */
+ if (ieee80211_is_action(mgmt->frame_control) &&
+ rx->skb->len < IEEE80211_MIN_ACTION_SIZE)
+ return RX_DROP_UNUSABLE;
+
if (rx->sdata->vif.type == NL80211_IFTYPE_AP &&
ieee80211_is_beacon(mgmt->frame_control) &&
!(rx->flags & IEEE80211_RX_BEACON_REPORTED)) {
@@ -3445,10 +3468,6 @@ ieee80211_rx_h_action(struct ieee80211_rx_data *rx)
if (!ieee80211_is_action(mgmt->frame_control))
return RX_CONTINUE;
- /* drop too small frames */
- if (len < IEEE80211_MIN_ACTION_SIZE)
- return RX_DROP_UNUSABLE;
-
if (!rx->sta && mgmt->u.action.category != WLAN_CATEGORY_PUBLIC &&
mgmt->u.action.category != WLAN_CATEGORY_SELF_PROTECTED &&
mgmt->u.action.category != WLAN_CATEGORY_SPECTRUM_MGMT)
diff --git a/net/mac80211/scan.c b/net/mac80211/scan.c
index 32fa8aca7005..0805aa8603c6 100644
--- a/net/mac80211/scan.c
+++ b/net/mac80211/scan.c
@@ -9,7 +9,7 @@
* Copyright 2007, Michael Wu <flamingice@sourmilk.net>
* Copyright 2013-2015 Intel Mobile Communications GmbH
* Copyright 2016-2017 Intel Deutschland GmbH
- * Copyright (C) 2018-2022 Intel Corporation
+ * Copyright (C) 2018-2023 Intel Corporation
*/
#include <linux/if_arp.h>
@@ -55,27 +55,45 @@ static bool is_uapsd_supported(struct ieee802_11_elems *elems)
return qos_info & IEEE80211_WMM_IE_AP_QOSINFO_UAPSD;
}
-static void
-ieee80211_update_bss_from_elems(struct ieee80211_local *local,
- struct ieee80211_bss *bss,
- struct ieee802_11_elems *elems,
- struct ieee80211_rx_status *rx_status,
- bool beacon)
+struct inform_bss_update_data {
+ struct ieee80211_rx_status *rx_status;
+ bool beacon;
+};
+
+void ieee80211_inform_bss(struct wiphy *wiphy,
+ struct cfg80211_bss *cbss,
+ const struct cfg80211_bss_ies *ies,
+ void *data)
{
+ struct ieee80211_local *local = wiphy_priv(wiphy);
+ struct inform_bss_update_data *update_data = data;
+ struct ieee80211_bss *bss = (void *)cbss->priv;
+ struct ieee80211_rx_status *rx_status;
+ struct ieee802_11_elems *elems;
int clen, srlen;
- if (beacon)
+ /* This happens while joining an IBSS */
+ if (!update_data)
+ return;
+
+ elems = ieee802_11_parse_elems(ies->data, ies->len, false, NULL);
+ if (!elems)
+ return;
+
+ rx_status = update_data->rx_status;
+
+ if (update_data->beacon)
bss->device_ts_beacon = rx_status->device_timestamp;
else
bss->device_ts_presp = rx_status->device_timestamp;
if (elems->parse_error) {
- if (beacon)
+ if (update_data->beacon)
bss->corrupt_data |= IEEE80211_BSS_CORRUPT_BEACON;
else
bss->corrupt_data |= IEEE80211_BSS_CORRUPT_PROBE_RESP;
} else {
- if (beacon)
+ if (update_data->beacon)
bss->corrupt_data &= ~IEEE80211_BSS_CORRUPT_BEACON;
else
bss->corrupt_data &= ~IEEE80211_BSS_CORRUPT_PROBE_RESP;
@@ -124,7 +142,7 @@ ieee80211_update_bss_from_elems(struct ieee80211_local *local,
bss->valid_data |= IEEE80211_BSS_VALID_WMM;
}
- if (beacon) {
+ if (update_data->beacon) {
struct ieee80211_supported_band *sband =
local->hw.wiphy->bands[rx_status->band];
if (!(rx_status->encoding == RX_ENC_HT) &&
@@ -138,6 +156,8 @@ ieee80211_update_bss_from_elems(struct ieee80211_local *local,
le32_to_cpu(elems->vht_cap_elem->vht_cap_info);
else
bss->vht_cap_info = 0;
+
+ kfree(elems);
}
struct ieee80211_bss *
@@ -148,16 +168,17 @@ ieee80211_bss_info_update(struct ieee80211_local *local,
{
bool beacon = ieee80211_is_beacon(mgmt->frame_control) ||
ieee80211_is_s1g_beacon(mgmt->frame_control);
- struct cfg80211_bss *cbss, *non_tx_cbss;
- struct ieee80211_bss *bss, *non_tx_bss;
+ struct cfg80211_bss *cbss;
+ struct inform_bss_update_data update_data = {
+ .rx_status = rx_status,
+ .beacon = beacon,
+ };
struct cfg80211_inform_bss bss_meta = {
.boottime_ns = rx_status->boottime_ns,
+ .drv_data = (void *)&update_data,
};
bool signal_valid;
struct ieee80211_sub_if_data *scan_sdata;
- struct ieee802_11_elems *elems;
- size_t baselen;
- u8 *elements;
if (rx_status->flag & RX_FLAG_NO_SIGNAL_VAL)
bss_meta.signal = 0; /* invalid signal indication */
@@ -192,50 +213,12 @@ ieee80211_bss_info_update(struct ieee80211_local *local,
if (!cbss)
return NULL;
- if (ieee80211_is_probe_resp(mgmt->frame_control)) {
- elements = mgmt->u.probe_resp.variable;
- baselen = offsetof(struct ieee80211_mgmt,
- u.probe_resp.variable);
- } else if (ieee80211_is_s1g_beacon(mgmt->frame_control)) {
- struct ieee80211_ext *ext = (void *) mgmt;
-
- baselen = offsetof(struct ieee80211_ext, u.s1g_beacon.variable);
- elements = ext->u.s1g_beacon.variable;
- } else {
- baselen = offsetof(struct ieee80211_mgmt, u.beacon.variable);
- elements = mgmt->u.beacon.variable;
- }
-
- if (baselen > len)
- return NULL;
-
- elems = ieee802_11_parse_elems(elements, len - baselen, false, cbss);
- if (!elems)
- return NULL;
-
/* In case the signal is invalid update the status */
signal_valid = channel == cbss->channel;
if (!signal_valid)
rx_status->flag |= RX_FLAG_NO_SIGNAL_VAL;
- bss = (void *)cbss->priv;
- ieee80211_update_bss_from_elems(local, bss, elems, rx_status, beacon);
- kfree(elems);
-
- list_for_each_entry(non_tx_cbss, &cbss->nontrans_list, nontrans_list) {
- non_tx_bss = (void *)non_tx_cbss->priv;
-
- elems = ieee802_11_parse_elems(elements, len - baselen, false,
- non_tx_cbss);
- if (!elems)
- continue;
-
- ieee80211_update_bss_from_elems(local, non_tx_bss, elems,
- rx_status, beacon);
- kfree(elems);
- }
-
- return bss;
+ return (void *)cbss->priv;
}
static bool ieee80211_scan_accept_presp(struct ieee80211_sub_if_data *sdata,
@@ -502,7 +485,7 @@ static void __ieee80211_scan_completed(struct ieee80211_hw *hw, bool aborted)
*/
list_for_each_entry_rcu(sdata, &local->interfaces, list) {
if (ieee80211_sdata_running(sdata))
- ieee80211_queue_work(&sdata->local->hw, &sdata->work);
+ wiphy_work_queue(sdata->local->hw.wiphy, &sdata->work);
}
if (was_scanning)
diff --git a/net/mac80211/sta_info.c b/net/mac80211/sta_info.c
index 1400512e0dde..7751f8ba960e 100644
--- a/net/mac80211/sta_info.c
+++ b/net/mac80211/sta_info.c
@@ -4,7 +4,7 @@
* Copyright 2006-2007 Jiri Benc <jbenc@suse.cz>
* Copyright 2013-2014 Intel Mobile Communications GmbH
* Copyright (C) 2015 - 2017 Intel Deutschland GmbH
- * Copyright (C) 2018-2022 Intel Corporation
+ * Copyright (C) 2018-2023 Intel Corporation
*/
#include <linux/module.h>
@@ -355,8 +355,9 @@ static void sta_remove_link(struct sta_info *sta, unsigned int link_id,
struct sta_link_alloc *alloc = NULL;
struct link_sta_info *link_sta;
- link_sta = rcu_dereference_protected(sta->link[link_id],
- lockdep_is_held(&sta->local->sta_mtx));
+ link_sta = rcu_access_pointer(sta->link[link_id]);
+ if (link_sta != &sta->deflink)
+ lockdep_assert_held(&sta->local->sta_mtx);
if (WARN_ON(!link_sta))
return;
@@ -1274,7 +1275,117 @@ static int __must_check __sta_info_destroy_part1(struct sta_info *sta)
return 0;
}
-static void __sta_info_destroy_part2(struct sta_info *sta)
+static int _sta_info_move_state(struct sta_info *sta,
+ enum ieee80211_sta_state new_state,
+ bool recalc)
+{
+ might_sleep();
+
+ if (sta->sta_state == new_state)
+ return 0;
+
+ /* check allowed transitions first */
+
+ switch (new_state) {
+ case IEEE80211_STA_NONE:
+ if (sta->sta_state != IEEE80211_STA_AUTH)
+ return -EINVAL;
+ break;
+ case IEEE80211_STA_AUTH:
+ if (sta->sta_state != IEEE80211_STA_NONE &&
+ sta->sta_state != IEEE80211_STA_ASSOC)
+ return -EINVAL;
+ break;
+ case IEEE80211_STA_ASSOC:
+ if (sta->sta_state != IEEE80211_STA_AUTH &&
+ sta->sta_state != IEEE80211_STA_AUTHORIZED)
+ return -EINVAL;
+ break;
+ case IEEE80211_STA_AUTHORIZED:
+ if (sta->sta_state != IEEE80211_STA_ASSOC)
+ return -EINVAL;
+ break;
+ default:
+ WARN(1, "invalid state %d", new_state);
+ return -EINVAL;
+ }
+
+ sta_dbg(sta->sdata, "moving STA %pM to state %d\n",
+ sta->sta.addr, new_state);
+
+ /* notify the driver before the actual changes so it can
+ * fail the transition
+ */
+ if (test_sta_flag(sta, WLAN_STA_INSERTED)) {
+ int err = drv_sta_state(sta->local, sta->sdata, sta,
+ sta->sta_state, new_state);
+ if (err)
+ return err;
+ }
+
+ /* reflect the change in all state variables */
+
+ switch (new_state) {
+ case IEEE80211_STA_NONE:
+ if (sta->sta_state == IEEE80211_STA_AUTH)
+ clear_bit(WLAN_STA_AUTH, &sta->_flags);
+ break;
+ case IEEE80211_STA_AUTH:
+ if (sta->sta_state == IEEE80211_STA_NONE) {
+ set_bit(WLAN_STA_AUTH, &sta->_flags);
+ } else if (sta->sta_state == IEEE80211_STA_ASSOC) {
+ clear_bit(WLAN_STA_ASSOC, &sta->_flags);
+ if (recalc) {
+ ieee80211_recalc_min_chandef(sta->sdata, -1);
+ if (!sta->sta.support_p2p_ps)
+ ieee80211_recalc_p2p_go_ps_allowed(sta->sdata);
+ }
+ }
+ break;
+ case IEEE80211_STA_ASSOC:
+ if (sta->sta_state == IEEE80211_STA_AUTH) {
+ set_bit(WLAN_STA_ASSOC, &sta->_flags);
+ sta->assoc_at = ktime_get_boottime_ns();
+ if (recalc) {
+ ieee80211_recalc_min_chandef(sta->sdata, -1);
+ if (!sta->sta.support_p2p_ps)
+ ieee80211_recalc_p2p_go_ps_allowed(sta->sdata);
+ }
+ } else if (sta->sta_state == IEEE80211_STA_AUTHORIZED) {
+ ieee80211_vif_dec_num_mcast(sta->sdata);
+ clear_bit(WLAN_STA_AUTHORIZED, &sta->_flags);
+ ieee80211_clear_fast_xmit(sta);
+ ieee80211_clear_fast_rx(sta);
+ }
+ break;
+ case IEEE80211_STA_AUTHORIZED:
+ if (sta->sta_state == IEEE80211_STA_ASSOC) {
+ ieee80211_vif_inc_num_mcast(sta->sdata);
+ set_bit(WLAN_STA_AUTHORIZED, &sta->_flags);
+ ieee80211_check_fast_xmit(sta);
+ ieee80211_check_fast_rx(sta);
+ }
+ if (sta->sdata->vif.type == NL80211_IFTYPE_AP_VLAN ||
+ sta->sdata->vif.type == NL80211_IFTYPE_AP)
+ cfg80211_send_layer2_update(sta->sdata->dev,
+ sta->sta.addr);
+ break;
+ default:
+ break;
+ }
+
+ sta->sta_state = new_state;
+
+ return 0;
+}
+
+int sta_info_move_state(struct sta_info *sta,
+ enum ieee80211_sta_state new_state)
+{
+ return _sta_info_move_state(sta, new_state, true);
+}
+
+static void __sta_info_destroy_part2(struct sta_info *sta, bool recalc)
{
struct ieee80211_local *local = sta->local;
struct ieee80211_sub_if_data *sdata = sta->sdata;
@@ -1290,7 +1401,7 @@ static void __sta_info_destroy_part2(struct sta_info *sta)
lockdep_assert_held(&local->sta_mtx);
if (sta->sta_state == IEEE80211_STA_AUTHORIZED) {
- ret = sta_info_move_state(sta, IEEE80211_STA_ASSOC);
+ ret = _sta_info_move_state(sta, IEEE80211_STA_ASSOC, recalc);
WARN_ON_ONCE(ret);
}
@@ -1318,7 +1429,7 @@ static void __sta_info_destroy_part2(struct sta_info *sta)
local->sta_generation++;
while (sta->sta_state > IEEE80211_STA_NONE) {
- ret = sta_info_move_state(sta, sta->sta_state - 1);
+ ret = _sta_info_move_state(sta, sta->sta_state - 1, recalc);
if (ret) {
WARN_ON_ONCE(1);
break;
@@ -1355,7 +1466,7 @@ int __must_check __sta_info_destroy(struct sta_info *sta)
synchronize_net();
- __sta_info_destroy_part2(sta);
+ __sta_info_destroy_part2(sta, true);
return 0;
}
@@ -1462,9 +1573,18 @@ int __sta_info_flush(struct ieee80211_sub_if_data *sdata, bool vlans)
}
if (!list_empty(&free_list)) {
+ bool support_p2p_ps = true;
+
synchronize_net();
- list_for_each_entry_safe(sta, tmp, &free_list, free_list)
- __sta_info_destroy_part2(sta);
+ list_for_each_entry_safe(sta, tmp, &free_list, free_list) {
+ if (!sta->sta.support_p2p_ps)
+ support_p2p_ps = false;
+ __sta_info_destroy_part2(sta, false);
+ }
+
+ ieee80211_recalc_min_chandef(sdata, -1);
+ if (!support_p2p_ps)
+ ieee80211_recalc_p2p_go_ps_allowed(sdata);
}
mutex_unlock(&local->sta_mtx);
@@ -2252,106 +2372,6 @@ void ieee80211_sta_update_pending_airtime(struct ieee80211_local *local,
}
}
-int sta_info_move_state(struct sta_info *sta,
- enum ieee80211_sta_state new_state)
-{
- might_sleep();
-
- if (sta->sta_state == new_state)
- return 0;
-
- /* check allowed transitions first */
-
- switch (new_state) {
- case IEEE80211_STA_NONE:
- if (sta->sta_state != IEEE80211_STA_AUTH)
- return -EINVAL;
- break;
- case IEEE80211_STA_AUTH:
- if (sta->sta_state != IEEE80211_STA_NONE &&
- sta->sta_state != IEEE80211_STA_ASSOC)
- return -EINVAL;
- break;
- case IEEE80211_STA_ASSOC:
- if (sta->sta_state != IEEE80211_STA_AUTH &&
- sta->sta_state != IEEE80211_STA_AUTHORIZED)
- return -EINVAL;
- break;
- case IEEE80211_STA_AUTHORIZED:
- if (sta->sta_state != IEEE80211_STA_ASSOC)
- return -EINVAL;
- break;
- default:
- WARN(1, "invalid state %d", new_state);
- return -EINVAL;
- }
-
- sta_dbg(sta->sdata, "moving STA %pM to state %d\n",
- sta->sta.addr, new_state);
-
- /*
- * notify the driver before the actual changes so it can
- * fail the transition
- */
- if (test_sta_flag(sta, WLAN_STA_INSERTED)) {
- int err = drv_sta_state(sta->local, sta->sdata, sta,
- sta->sta_state, new_state);
- if (err)
- return err;
- }
-
- /* reflect the change in all state variables */
-
- switch (new_state) {
- case IEEE80211_STA_NONE:
- if (sta->sta_state == IEEE80211_STA_AUTH)
- clear_bit(WLAN_STA_AUTH, &sta->_flags);
- break;
- case IEEE80211_STA_AUTH:
- if (sta->sta_state == IEEE80211_STA_NONE) {
- set_bit(WLAN_STA_AUTH, &sta->_flags);
- } else if (sta->sta_state == IEEE80211_STA_ASSOC) {
- clear_bit(WLAN_STA_ASSOC, &sta->_flags);
- ieee80211_recalc_min_chandef(sta->sdata, -1);
- if (!sta->sta.support_p2p_ps)
- ieee80211_recalc_p2p_go_ps_allowed(sta->sdata);
- }
- break;
- case IEEE80211_STA_ASSOC:
- if (sta->sta_state == IEEE80211_STA_AUTH) {
- set_bit(WLAN_STA_ASSOC, &sta->_flags);
- sta->assoc_at = ktime_get_boottime_ns();
- ieee80211_recalc_min_chandef(sta->sdata, -1);
- if (!sta->sta.support_p2p_ps)
- ieee80211_recalc_p2p_go_ps_allowed(sta->sdata);
- } else if (sta->sta_state == IEEE80211_STA_AUTHORIZED) {
- ieee80211_vif_dec_num_mcast(sta->sdata);
- clear_bit(WLAN_STA_AUTHORIZED, &sta->_flags);
- ieee80211_clear_fast_xmit(sta);
- ieee80211_clear_fast_rx(sta);
- }
- break;
- case IEEE80211_STA_AUTHORIZED:
- if (sta->sta_state == IEEE80211_STA_ASSOC) {
- ieee80211_vif_inc_num_mcast(sta->sdata);
- set_bit(WLAN_STA_AUTHORIZED, &sta->_flags);
- ieee80211_check_fast_xmit(sta);
- ieee80211_check_fast_rx(sta);
- }
- if (sta->sdata->vif.type == NL80211_IFTYPE_AP_VLAN ||
- sta->sdata->vif.type == NL80211_IFTYPE_AP)
- cfg80211_send_layer2_update(sta->sdata->dev,
- sta->sta.addr);
- break;
- default:
- break;
- }
-
- sta->sta_state = new_state;
-
- return 0;
-}
-
static struct ieee80211_sta_rx_stats *
sta_get_last_rx_stats(struct sta_info *sta)
{
@@ -2913,6 +2933,8 @@ int ieee80211_sta_activate_link(struct sta_info *sta, unsigned int link_id)
if (!test_sta_flag(sta, WLAN_STA_INSERTED))
goto hash;
+ ieee80211_recalc_min_chandef(sdata, link_id);
+
/* Ensure the values are updated for the driver,
* redone by sta_remove_link on failure.
*/
diff --git a/net/mac80211/status.c b/net/mac80211/status.c
index 2b13a52ce96c..44d83da60aee 100644
--- a/net/mac80211/status.c
+++ b/net/mac80211/status.c
@@ -5,7 +5,7 @@
* Copyright 2006-2007 Jiri Benc <jbenc@suse.cz>
* Copyright 2008-2010 Johannes Berg <johannes@sipsolutions.net>
* Copyright 2013-2014 Intel Mobile Communications GmbH
- * Copyright 2021-2022 Intel Corporation
+ * Copyright 2021-2023 Intel Corporation
*/
#include <linux/export.h>
@@ -747,8 +747,8 @@ static void ieee80211_report_used_skb(struct ieee80211_local *local,
if (qskb) {
skb_queue_tail(&sdata->status_queue,
qskb);
- ieee80211_queue_work(&local->hw,
- &sdata->work);
+ wiphy_work_queue(local->hw.wiphy,
+ &sdata->work);
}
}
} else {
diff --git a/net/mac80211/tdls.c b/net/mac80211/tdls.c
index b255f3b5bf01..a4af3b7675ef 100644
--- a/net/mac80211/tdls.c
+++ b/net/mac80211/tdls.c
@@ -6,7 +6,7 @@
* Copyright 2014, Intel Corporation
* Copyright 2014 Intel Mobile Communications GmbH
* Copyright 2015 - 2016 Intel Deutschland GmbH
- * Copyright (C) 2019, 2021-2022 Intel Corporation
+ * Copyright (C) 2019, 2021-2023 Intel Corporation
*/
#include <linux/ieee80211.h>
@@ -39,9 +39,10 @@ void ieee80211_tdls_peer_del_work(struct work_struct *wk)
mutex_unlock(&local->mtx);
}
-static void ieee80211_tdls_add_ext_capab(struct ieee80211_sub_if_data *sdata,
+static void ieee80211_tdls_add_ext_capab(struct ieee80211_link_data *link,
struct sk_buff *skb)
{
+ struct ieee80211_sub_if_data *sdata = link->sdata;
struct ieee80211_local *local = sdata->local;
struct ieee80211_if_managed *ifmgd = &sdata->u.mgd;
bool chan_switch = local->hw.wiphy->features &
@@ -50,7 +51,7 @@ static void ieee80211_tdls_add_ext_capab(struct ieee80211_sub_if_data *sdata,
!ifmgd->tdls_wider_bw_prohibited;
bool buffer_sta = ieee80211_hw_check(&local->hw,
SUPPORTS_TDLS_BUFFER_STA);
- struct ieee80211_supported_band *sband = ieee80211_get_sband(sdata);
+ struct ieee80211_supported_band *sband = ieee80211_get_link_sband(link);
bool vht = sband && sband->vht_cap.vht_supported;
u8 *pos = skb_put(skb, 10);
@@ -152,13 +153,13 @@ ieee80211_tdls_add_supp_channels(struct ieee80211_sub_if_data *sdata,
*pos = 2 * subband_cnt;
}
-static void ieee80211_tdls_add_oper_classes(struct ieee80211_sub_if_data *sdata,
+static void ieee80211_tdls_add_oper_classes(struct ieee80211_link_data *link,
struct sk_buff *skb)
{
u8 *pos;
u8 op_class;
- if (!ieee80211_chandef_to_operating_class(&sdata->vif.bss_conf.chandef,
+ if (!ieee80211_chandef_to_operating_class(&link->conf->chandef,
&op_class))
return;
@@ -180,7 +181,7 @@ static void ieee80211_tdls_add_bss_coex_ie(struct sk_buff *skb)
*pos++ = WLAN_BSS_COEX_INFORMATION_REQUEST;
}
-static u16 ieee80211_get_tdls_sta_capab(struct ieee80211_sub_if_data *sdata,
+static u16 ieee80211_get_tdls_sta_capab(struct ieee80211_link_data *link,
u16 status_code)
{
struct ieee80211_supported_band *sband;
@@ -189,7 +190,8 @@ static u16 ieee80211_get_tdls_sta_capab(struct ieee80211_sub_if_data *sdata,
if (status_code != 0)
return 0;
- sband = ieee80211_get_sband(sdata);
+ sband = ieee80211_get_link_sband(link);
+
if (sband && sband->band == NL80211_BAND_2GHZ) {
return WLAN_CAPABILITY_SHORT_SLOT_TIME |
WLAN_CAPABILITY_SHORT_PREAMBLE;
@@ -198,10 +200,11 @@ static u16 ieee80211_get_tdls_sta_capab(struct ieee80211_sub_if_data *sdata,
return 0;
}
-static void ieee80211_tdls_add_link_ie(struct ieee80211_sub_if_data *sdata,
+static void ieee80211_tdls_add_link_ie(struct ieee80211_link_data *link,
struct sk_buff *skb, const u8 *peer,
bool initiator)
{
+ struct ieee80211_sub_if_data *sdata = link->sdata;
struct ieee80211_tdls_lnkie *lnkid;
const u8 *init_addr, *rsp_addr;
@@ -218,7 +221,7 @@ static void ieee80211_tdls_add_link_ie(struct ieee80211_sub_if_data *sdata,
lnkid->ie_type = WLAN_EID_LINK_ID;
lnkid->ie_len = sizeof(struct ieee80211_tdls_lnkie) - 2;
- memcpy(lnkid->bssid, sdata->deflink.u.mgd.bssid, ETH_ALEN);
+ memcpy(lnkid->bssid, link->u.mgd.bssid, ETH_ALEN);
memcpy(lnkid->init_sta, init_addr, ETH_ALEN);
memcpy(lnkid->resp_sta, rsp_addr, ETH_ALEN);
}
@@ -359,21 +362,24 @@ ieee80211_tdls_chandef_vht_upgrade(struct ieee80211_sub_if_data *sdata,
}
static void
-ieee80211_tdls_add_setup_start_ies(struct ieee80211_sub_if_data *sdata,
+ieee80211_tdls_add_setup_start_ies(struct ieee80211_link_data *link,
struct sk_buff *skb, const u8 *peer,
u8 action_code, bool initiator,
const u8 *extra_ies, size_t extra_ies_len)
{
+ struct ieee80211_sub_if_data *sdata = link->sdata;
struct ieee80211_supported_band *sband;
struct ieee80211_local *local = sdata->local;
struct ieee80211_sta_ht_cap ht_cap;
struct ieee80211_sta_vht_cap vht_cap;
+ const struct ieee80211_sta_he_cap *he_cap;
+ const struct ieee80211_sta_eht_cap *eht_cap;
struct sta_info *sta = NULL;
size_t offset = 0, noffset;
u8 *pos;
- sband = ieee80211_get_sband(sdata);
- if (!sband)
+ sband = ieee80211_get_link_sband(link);
+ if (WARN_ON_ONCE(!sband))
return;
ieee80211_add_srates_ie(sdata, skb, false, sband->band);
@@ -397,7 +403,7 @@ ieee80211_tdls_add_setup_start_ies(struct ieee80211_sub_if_data *sdata,
offset = noffset;
}
- ieee80211_tdls_add_ext_capab(sdata, skb);
+ ieee80211_tdls_add_ext_capab(link, skb);
/* add the QoS element if we support it */
if (local->hw.queues >= IEEE80211_NUM_ACS &&
@@ -426,20 +432,16 @@ ieee80211_tdls_add_setup_start_ies(struct ieee80211_sub_if_data *sdata,
offset = noffset;
}
- mutex_lock(&local->sta_mtx);
-
/* we should have the peer STA if we're already responding */
if (action_code == WLAN_TDLS_SETUP_RESPONSE) {
sta = sta_info_get(sdata, peer);
- if (WARN_ON_ONCE(!sta)) {
- mutex_unlock(&local->sta_mtx);
+ if (WARN_ON_ONCE(!sta))
return;
- }
- sta->tdls_chandef = sdata->vif.bss_conf.chandef;
+ sta->tdls_chandef = link->conf->chandef;
}
- ieee80211_tdls_add_oper_classes(sdata, skb);
+ ieee80211_tdls_add_oper_classes(link, skb);
/*
* with TDLS we can switch channels, and HT-caps are not necessarily
@@ -472,7 +474,7 @@ ieee80211_tdls_add_setup_start_ies(struct ieee80211_sub_if_data *sdata,
(ht_cap.cap & IEEE80211_HT_CAP_SUP_WIDTH_20_40))
ieee80211_tdls_add_bss_coex_ie(skb);
- ieee80211_tdls_add_link_ie(sdata, skb, peer, initiator);
+ ieee80211_tdls_add_link_ie(link, skb, peer, initiator);
/* add any custom IEs that go before VHT capabilities */
if (extra_ies_len) {
@@ -497,17 +499,21 @@ ieee80211_tdls_add_setup_start_ies(struct ieee80211_sub_if_data *sdata,
offset = noffset;
}
- /* build the VHT-cap similarly to the HT-cap */
+ /* add AID if VHT, HE or EHT capabilities supported */
memcpy(&vht_cap, &sband->vht_cap, sizeof(vht_cap));
+ he_cap = ieee80211_get_he_iftype_cap_vif(sband, &sdata->vif);
+ eht_cap = ieee80211_get_eht_iftype_cap_vif(sband, &sdata->vif);
+ if ((vht_cap.vht_supported || he_cap || eht_cap) &&
+ (action_code == WLAN_TDLS_SETUP_REQUEST ||
+ action_code == WLAN_TDLS_SETUP_RESPONSE))
+ ieee80211_tdls_add_aid(sdata, skb);
+
+ /* build the VHT-cap similarly to the HT-cap */
if ((action_code == WLAN_TDLS_SETUP_REQUEST ||
action_code == WLAN_PUB_ACTION_TDLS_DISCOVER_RES) &&
vht_cap.vht_supported) {
ieee80211_apply_vhtcap_overrides(sdata, &vht_cap);
- /* the AID is present only when VHT is implemented */
- if (action_code == WLAN_TDLS_SETUP_REQUEST)
- ieee80211_tdls_add_aid(sdata, skb);
-
pos = skb_put(skb, sizeof(struct ieee80211_vht_cap) + 2);
ieee80211_ie_build_vht_cap(pos, &vht_cap, vht_cap.cap);
} else if (action_code == WLAN_TDLS_SETUP_RESPONSE &&
@@ -515,9 +521,6 @@ ieee80211_tdls_add_setup_start_ies(struct ieee80211_sub_if_data *sdata,
/* the peer caps are already intersected with our own */
memcpy(&vht_cap, &sta->sta.deflink.vht_cap, sizeof(vht_cap));
- /* the AID is present only when VHT is implemented */
- ieee80211_tdls_add_aid(sdata, skb);
-
pos = skb_put(skb, sizeof(struct ieee80211_vht_cap) + 2);
ieee80211_ie_build_vht_cap(pos, &vht_cap, vht_cap.cap);
@@ -529,7 +532,80 @@ ieee80211_tdls_add_setup_start_ies(struct ieee80211_sub_if_data *sdata,
ieee80211_tdls_chandef_vht_upgrade(sdata, sta);
}
- mutex_unlock(&local->sta_mtx);
+ /* add any custom IEs that go before HE capabilities */
+ if (extra_ies_len) {
+ static const u8 before_he_cap[] = {
+ WLAN_EID_EXTENSION,
+ WLAN_EID_EXT_FILS_REQ_PARAMS,
+ WLAN_EID_AP_CSN,
+ };
+ noffset = ieee80211_ie_split(extra_ies, extra_ies_len,
+ before_he_cap,
+ ARRAY_SIZE(before_he_cap),
+ offset);
+ skb_put_data(skb, extra_ies + offset, noffset - offset);
+ offset = noffset;
+ }
+
+ /* build the HE-cap from sband */
+ if (he_cap &&
+ (action_code == WLAN_TDLS_SETUP_REQUEST ||
+ action_code == WLAN_TDLS_SETUP_RESPONSE ||
+ action_code == WLAN_PUB_ACTION_TDLS_DISCOVER_RES)) {
+ __le16 he_6ghz_capa;
+ u8 cap_size;
+
+ cap_size =
+ 2 + 1 + sizeof(he_cap->he_cap_elem) +
+ ieee80211_he_mcs_nss_size(&he_cap->he_cap_elem) +
+ ieee80211_he_ppe_size(he_cap->ppe_thres[0],
+ he_cap->he_cap_elem.phy_cap_info);
+ pos = skb_put(skb, cap_size);
+ pos = ieee80211_ie_build_he_cap(0, pos, he_cap, pos + cap_size);
+
+ /* Build HE 6Ghz capa IE from sband */
+ if (sband->band == NL80211_BAND_6GHZ) {
+ cap_size = 2 + 1 + sizeof(struct ieee80211_he_6ghz_capa);
+ pos = skb_put(skb, cap_size);
+ he_6ghz_capa =
+ ieee80211_get_he_6ghz_capa_vif(sband, &sdata->vif);
+ pos = ieee80211_write_he_6ghz_cap(pos, he_6ghz_capa,
+ pos + cap_size);
+ }
+ }
+
+ /* add any custom IEs that go before EHT capabilities */
+ if (extra_ies_len) {
+ static const u8 before_he_cap[] = {
+ WLAN_EID_EXTENSION,
+ WLAN_EID_EXT_FILS_REQ_PARAMS,
+ WLAN_EID_AP_CSN,
+ };
+
+ noffset = ieee80211_ie_split(extra_ies, extra_ies_len,
+ before_he_cap,
+ ARRAY_SIZE(before_he_cap),
+ offset);
+ skb_put_data(skb, extra_ies + offset, noffset - offset);
+ offset = noffset;
+ }
+
+ /* build the EHT-cap from sband */
+ if (he_cap && eht_cap &&
+ (action_code == WLAN_TDLS_SETUP_REQUEST ||
+ action_code == WLAN_TDLS_SETUP_RESPONSE ||
+ action_code == WLAN_PUB_ACTION_TDLS_DISCOVER_RES)) {
+ u8 cap_size;
+
+ cap_size =
+ 2 + 1 + sizeof(eht_cap->eht_cap_elem) +
+ ieee80211_eht_mcs_nss_size(&he_cap->he_cap_elem,
+ &eht_cap->eht_cap_elem, false) +
+ ieee80211_eht_ppe_size(eht_cap->eht_ppe_thres[0],
+ eht_cap->eht_cap_elem.phy_cap_info);
+ pos = skb_put(skb, cap_size);
+ ieee80211_ie_build_eht_cap(pos, he_cap, eht_cap, pos + cap_size, false);
+ }
/* add any remaining IEs */
if (extra_ies_len) {
@@ -540,31 +616,29 @@ ieee80211_tdls_add_setup_start_ies(struct ieee80211_sub_if_data *sdata,
}
static void
-ieee80211_tdls_add_setup_cfm_ies(struct ieee80211_sub_if_data *sdata,
+ieee80211_tdls_add_setup_cfm_ies(struct ieee80211_link_data *link,
struct sk_buff *skb, const u8 *peer,
bool initiator, const u8 *extra_ies,
size_t extra_ies_len)
{
+ struct ieee80211_sub_if_data *sdata = link->sdata;
struct ieee80211_local *local = sdata->local;
size_t offset = 0, noffset;
struct sta_info *sta, *ap_sta;
struct ieee80211_supported_band *sband;
u8 *pos;
- sband = ieee80211_get_sband(sdata);
- if (!sband)
+ sband = ieee80211_get_link_sband(link);
+ if (WARN_ON_ONCE(!sband))
return;
- mutex_lock(&local->sta_mtx);
-
sta = sta_info_get(sdata, peer);
- ap_sta = sta_info_get(sdata, sdata->deflink.u.mgd.bssid);
- if (WARN_ON_ONCE(!sta || !ap_sta)) {
- mutex_unlock(&local->sta_mtx);
+ ap_sta = sta_info_get(sdata, sdata->vif.cfg.ap_addr);
+
+ if (WARN_ON_ONCE(!sta || !ap_sta))
return;
- }
- sta->tdls_chandef = sdata->vif.bss_conf.chandef;
+ sta->tdls_chandef = link->conf->chandef;
/* add any custom IEs that go before the QoS IE */
if (extra_ies_len) {
@@ -610,11 +684,11 @@ ieee80211_tdls_add_setup_cfm_ies(struct ieee80211_sub_if_data *sdata,
pos = skb_put(skb, 2 + sizeof(struct ieee80211_ht_operation));
ieee80211_ie_build_ht_oper(pos, &sta->sta.deflink.ht_cap,
- &sdata->vif.bss_conf.chandef, prot,
+ &link->conf->chandef, prot,
true);
}
- ieee80211_tdls_add_link_ie(sdata, skb, peer, initiator);
+ ieee80211_tdls_add_link_ie(link, skb, peer, initiator);
/* only include VHT-operation if not on the 2.4GHz band */
if (sband->band != NL80211_BAND_2GHZ &&
@@ -631,8 +705,6 @@ ieee80211_tdls_add_setup_cfm_ies(struct ieee80211_sub_if_data *sdata,
&sta->tdls_chandef);
}
- mutex_unlock(&local->sta_mtx);
-
/* add any remaining IEs */
if (extra_ies_len) {
noffset = extra_ies_len;
@@ -641,7 +713,7 @@ ieee80211_tdls_add_setup_cfm_ies(struct ieee80211_sub_if_data *sdata,
}
static void
-ieee80211_tdls_add_chan_switch_req_ies(struct ieee80211_sub_if_data *sdata,
+ieee80211_tdls_add_chan_switch_req_ies(struct ieee80211_link_data *link,
struct sk_buff *skb, const u8 *peer,
bool initiator, const u8 *extra_ies,
size_t extra_ies_len, u8 oper_class,
@@ -670,7 +742,7 @@ ieee80211_tdls_add_chan_switch_req_ies(struct ieee80211_sub_if_data *sdata,
offset = noffset;
}
- ieee80211_tdls_add_link_ie(sdata, skb, peer, initiator);
+ ieee80211_tdls_add_link_ie(link, skb, peer, initiator);
/* add any remaining IEs */
if (extra_ies_len) {
@@ -680,20 +752,20 @@ ieee80211_tdls_add_chan_switch_req_ies(struct ieee80211_sub_if_data *sdata,
}
static void
-ieee80211_tdls_add_chan_switch_resp_ies(struct ieee80211_sub_if_data *sdata,
+ieee80211_tdls_add_chan_switch_resp_ies(struct ieee80211_link_data *link,
struct sk_buff *skb, const u8 *peer,
u16 status_code, bool initiator,
const u8 *extra_ies,
size_t extra_ies_len)
{
if (status_code == 0)
- ieee80211_tdls_add_link_ie(sdata, skb, peer, initiator);
+ ieee80211_tdls_add_link_ie(link, skb, peer, initiator);
if (extra_ies_len)
skb_put_data(skb, extra_ies, extra_ies_len);
}
-static void ieee80211_tdls_add_ies(struct ieee80211_sub_if_data *sdata,
+static void ieee80211_tdls_add_ies(struct ieee80211_link_data *link,
struct sk_buff *skb, const u8 *peer,
u8 action_code, u16 status_code,
bool initiator, const u8 *extra_ies,
@@ -705,7 +777,8 @@ static void ieee80211_tdls_add_ies(struct ieee80211_sub_if_data *sdata,
case WLAN_TDLS_SETUP_RESPONSE:
case WLAN_PUB_ACTION_TDLS_DISCOVER_RES:
if (status_code == 0)
- ieee80211_tdls_add_setup_start_ies(sdata, skb, peer,
+ ieee80211_tdls_add_setup_start_ies(link,
+ skb, peer,
action_code,
initiator,
extra_ies,
@@ -713,7 +786,7 @@ static void ieee80211_tdls_add_ies(struct ieee80211_sub_if_data *sdata,
break;
case WLAN_TDLS_SETUP_CONFIRM:
if (status_code == 0)
- ieee80211_tdls_add_setup_cfm_ies(sdata, skb, peer,
+ ieee80211_tdls_add_setup_cfm_ies(link, skb, peer,
initiator, extra_ies,
extra_ies_len);
break;
@@ -722,16 +795,17 @@ static void ieee80211_tdls_add_ies(struct ieee80211_sub_if_data *sdata,
if (extra_ies_len)
skb_put_data(skb, extra_ies, extra_ies_len);
if (status_code == 0 || action_code == WLAN_TDLS_TEARDOWN)
- ieee80211_tdls_add_link_ie(sdata, skb, peer, initiator);
+ ieee80211_tdls_add_link_ie(link, skb,
+ peer, initiator);
break;
case WLAN_TDLS_CHANNEL_SWITCH_REQUEST:
- ieee80211_tdls_add_chan_switch_req_ies(sdata, skb, peer,
+ ieee80211_tdls_add_chan_switch_req_ies(link, skb, peer,
initiator, extra_ies,
extra_ies_len,
oper_class, chandef);
break;
case WLAN_TDLS_CHANNEL_SWITCH_RESPONSE:
- ieee80211_tdls_add_chan_switch_resp_ies(sdata, skb, peer,
+ ieee80211_tdls_add_chan_switch_resp_ies(link, skb, peer,
status_code,
initiator, extra_ies,
extra_ies_len);
@@ -742,6 +816,7 @@ static void ieee80211_tdls_add_ies(struct ieee80211_sub_if_data *sdata,
static int
ieee80211_prep_tdls_encap_data(struct wiphy *wiphy, struct net_device *dev,
+ struct ieee80211_link_data *link,
const u8 *peer, u8 action_code, u8 dialog_token,
u16 status_code, struct sk_buff *skb)
{
@@ -766,7 +841,7 @@ ieee80211_prep_tdls_encap_data(struct wiphy *wiphy, struct net_device *dev,
skb_put(skb, sizeof(tf->u.setup_req));
tf->u.setup_req.dialog_token = dialog_token;
tf->u.setup_req.capability =
- cpu_to_le16(ieee80211_get_tdls_sta_capab(sdata,
+ cpu_to_le16(ieee80211_get_tdls_sta_capab(link,
status_code));
break;
case WLAN_TDLS_SETUP_RESPONSE:
@@ -777,7 +852,7 @@ ieee80211_prep_tdls_encap_data(struct wiphy *wiphy, struct net_device *dev,
tf->u.setup_resp.status_code = cpu_to_le16(status_code);
tf->u.setup_resp.dialog_token = dialog_token;
tf->u.setup_resp.capability =
- cpu_to_le16(ieee80211_get_tdls_sta_capab(sdata,
+ cpu_to_le16(ieee80211_get_tdls_sta_capab(link,
status_code));
break;
case WLAN_TDLS_SETUP_CONFIRM:
@@ -824,7 +899,8 @@ ieee80211_prep_tdls_encap_data(struct wiphy *wiphy, struct net_device *dev,
static int
ieee80211_prep_tdls_direct(struct wiphy *wiphy, struct net_device *dev,
- const u8 *peer, u8 action_code, u8 dialog_token,
+ const u8 *peer, struct ieee80211_link_data *link,
+ u8 action_code, u8 dialog_token,
u16 status_code, struct sk_buff *skb)
{
struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev);
@@ -833,8 +909,7 @@ ieee80211_prep_tdls_direct(struct wiphy *wiphy, struct net_device *dev,
mgmt = skb_put_zero(skb, 24);
memcpy(mgmt->da, peer, ETH_ALEN);
memcpy(mgmt->sa, sdata->vif.addr, ETH_ALEN);
- memcpy(mgmt->bssid, sdata->deflink.u.mgd.bssid, ETH_ALEN);
-
+ memcpy(mgmt->bssid, link->u.mgd.bssid, ETH_ALEN);
mgmt->frame_control = cpu_to_le16(IEEE80211_FTYPE_MGMT |
IEEE80211_STYPE_ACTION);
@@ -847,7 +922,7 @@ ieee80211_prep_tdls_direct(struct wiphy *wiphy, struct net_device *dev,
mgmt->u.action.u.tdls_discover_resp.dialog_token =
dialog_token;
mgmt->u.action.u.tdls_discover_resp.capability =
- cpu_to_le16(ieee80211_get_tdls_sta_capab(sdata,
+ cpu_to_le16(ieee80211_get_tdls_sta_capab(link,
status_code));
break;
default:
@@ -859,15 +934,23 @@ ieee80211_prep_tdls_direct(struct wiphy *wiphy, struct net_device *dev,
static struct sk_buff *
ieee80211_tdls_build_mgmt_packet_data(struct ieee80211_sub_if_data *sdata,
- const u8 *peer, u8 action_code,
- u8 dialog_token, u16 status_code,
- bool initiator, const u8 *extra_ies,
- size_t extra_ies_len, u8 oper_class,
+ const u8 *peer, int link_id,
+ u8 action_code, u8 dialog_token,
+ u16 status_code, bool initiator,
+ const u8 *extra_ies, size_t extra_ies_len,
+ u8 oper_class,
struct cfg80211_chan_def *chandef)
{
struct ieee80211_local *local = sdata->local;
struct sk_buff *skb;
int ret;
+ struct ieee80211_link_data *link;
+
+ link_id = link_id >= 0 ? link_id : 0;
+ rcu_read_lock();
+ link = rcu_dereference(sdata->link[link_id]);
+ if (WARN_ON(!link))
+ goto unlock;
skb = netdev_alloc_skb(sdata->dev,
local->hw.extra_tx_headroom +
@@ -880,6 +963,13 @@ ieee80211_tdls_build_mgmt_packet_data(struct ieee80211_sub_if_data *sdata,
sizeof(struct ieee80211_ht_operation)) +
2 + max(sizeof(struct ieee80211_vht_cap),
sizeof(struct ieee80211_vht_operation)) +
+ 2 + 1 + sizeof(struct ieee80211_he_cap_elem) +
+ sizeof(struct ieee80211_he_mcs_nss_supp) +
+ IEEE80211_HE_PPE_THRES_MAX_LEN +
+ 2 + 1 + sizeof(struct ieee80211_he_6ghz_capa) +
+ 2 + 1 + sizeof(struct ieee80211_eht_cap_elem) +
+ sizeof(struct ieee80211_eht_mcs_nss_supp) +
+ IEEE80211_EHT_PPE_THRES_MAX_LEN +
50 + /* supported channels */
3 + /* 40/20 BSS coex */
4 + /* AID */
@@ -887,7 +977,7 @@ ieee80211_tdls_build_mgmt_packet_data(struct ieee80211_sub_if_data *sdata,
extra_ies_len +
sizeof(struct ieee80211_tdls_lnkie));
if (!skb)
- return NULL;
+ goto unlock;
skb_reserve(skb, local->hw.extra_tx_headroom);
@@ -900,13 +990,13 @@ ieee80211_tdls_build_mgmt_packet_data(struct ieee80211_sub_if_data *sdata,
case WLAN_TDLS_CHANNEL_SWITCH_REQUEST:
case WLAN_TDLS_CHANNEL_SWITCH_RESPONSE:
ret = ieee80211_prep_tdls_encap_data(local->hw.wiphy,
- sdata->dev, peer,
+ sdata->dev, link, peer,
action_code, dialog_token,
status_code, skb);
break;
case WLAN_PUB_ACTION_TDLS_DISCOVER_RES:
ret = ieee80211_prep_tdls_direct(local->hw.wiphy, sdata->dev,
- peer, action_code,
+ peer, link, action_code,
dialog_token, status_code,
skb);
break;
@@ -918,19 +1008,23 @@ ieee80211_tdls_build_mgmt_packet_data(struct ieee80211_sub_if_data *sdata,
if (ret < 0)
goto fail;
- ieee80211_tdls_add_ies(sdata, skb, peer, action_code, status_code,
+ ieee80211_tdls_add_ies(link, skb, peer, action_code, status_code,
initiator, extra_ies, extra_ies_len, oper_class,
chandef);
+ rcu_read_unlock();
return skb;
fail:
dev_kfree_skb(skb);
+unlock:
+ rcu_read_unlock();
return NULL;
}
static int
ieee80211_tdls_prep_mgmt_packet(struct wiphy *wiphy, struct net_device *dev,
- const u8 *peer, u8 action_code, u8 dialog_token,
+ const u8 *peer, int link_id,
+ u8 action_code, u8 dialog_token,
u16 status_code, u32 peer_capability,
bool initiator, const u8 *extra_ies,
size_t extra_ies_len, u8 oper_class,
@@ -988,7 +1082,8 @@ ieee80211_tdls_prep_mgmt_packet(struct wiphy *wiphy, struct net_device *dev,
if (ret < 0)
goto fail;
- skb = ieee80211_tdls_build_mgmt_packet_data(sdata, peer, action_code,
+ skb = ieee80211_tdls_build_mgmt_packet_data(sdata, peer,
+ link_id, action_code,
dialog_token, status_code,
initiator, extra_ies,
extra_ies_len, oper_class,
@@ -999,7 +1094,7 @@ ieee80211_tdls_prep_mgmt_packet(struct wiphy *wiphy, struct net_device *dev,
}
if (action_code == WLAN_PUB_ACTION_TDLS_DISCOVER_RES) {
- ieee80211_tx_skb(sdata, skb);
+ ieee80211_tx_skb_tid(sdata, skb, 7, link_id);
return 0;
}
@@ -1066,7 +1161,8 @@ fail:
static int
ieee80211_tdls_mgmt_setup(struct wiphy *wiphy, struct net_device *dev,
- const u8 *peer, u8 action_code, u8 dialog_token,
+ const u8 *peer, int link_id,
+ u8 action_code, u8 dialog_token,
u16 status_code, u32 peer_capability, bool initiator,
const u8 *extra_ies, size_t extra_ies_len)
{
@@ -1115,7 +1211,8 @@ ieee80211_tdls_mgmt_setup(struct wiphy *wiphy, struct net_device *dev,
mutex_unlock(&local->mtx);
/* we cannot take the mutex while preparing the setup packet */
- ret = ieee80211_tdls_prep_mgmt_packet(wiphy, dev, peer, action_code,
+ ret = ieee80211_tdls_prep_mgmt_packet(wiphy, dev, peer,
+ link_id, action_code,
dialog_token, status_code,
peer_capability, initiator,
extra_ies, extra_ies_len, 0,
@@ -1139,7 +1236,8 @@ out_unlock:
static int
ieee80211_tdls_mgmt_teardown(struct wiphy *wiphy, struct net_device *dev,
- const u8 *peer, u8 action_code, u8 dialog_token,
+ const u8 *peer, int link_id,
+ u8 action_code, u8 dialog_token,
u16 status_code, u32 peer_capability,
bool initiator, const u8 *extra_ies,
size_t extra_ies_len)
@@ -1159,7 +1257,8 @@ ieee80211_tdls_mgmt_teardown(struct wiphy *wiphy, struct net_device *dev,
IEEE80211_QUEUE_STOP_REASON_TDLS_TEARDOWN);
ieee80211_flush_queues(local, sdata, false);
- ret = ieee80211_tdls_prep_mgmt_packet(wiphy, dev, peer, action_code,
+ ret = ieee80211_tdls_prep_mgmt_packet(wiphy, dev, peer,
+ link_id, action_code,
dialog_token, status_code,
peer_capability, initiator,
extra_ies, extra_ies_len, 0,
@@ -1185,10 +1284,10 @@ ieee80211_tdls_mgmt_teardown(struct wiphy *wiphy, struct net_device *dev,
}
int ieee80211_tdls_mgmt(struct wiphy *wiphy, struct net_device *dev,
- const u8 *peer, u8 action_code, u8 dialog_token,
- u16 status_code, u32 peer_capability,
- bool initiator, const u8 *extra_ies,
- size_t extra_ies_len)
+ const u8 *peer, int link_id,
+ u8 action_code, u8 dialog_token, u16 status_code,
+ u32 peer_capability, bool initiator,
+ const u8 *extra_ies, size_t extra_ies_len)
{
struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev);
int ret;
@@ -1204,13 +1303,14 @@ int ieee80211_tdls_mgmt(struct wiphy *wiphy, struct net_device *dev,
switch (action_code) {
case WLAN_TDLS_SETUP_REQUEST:
case WLAN_TDLS_SETUP_RESPONSE:
- ret = ieee80211_tdls_mgmt_setup(wiphy, dev, peer, action_code,
+ ret = ieee80211_tdls_mgmt_setup(wiphy, dev, peer,
+ link_id, action_code,
dialog_token, status_code,
peer_capability, initiator,
extra_ies, extra_ies_len);
break;
case WLAN_TDLS_TEARDOWN:
- ret = ieee80211_tdls_mgmt_teardown(wiphy, dev, peer,
+ ret = ieee80211_tdls_mgmt_teardown(wiphy, dev, peer, link_id,
action_code, dialog_token,
status_code,
peer_capability, initiator,
@@ -1228,7 +1328,7 @@ int ieee80211_tdls_mgmt(struct wiphy *wiphy, struct net_device *dev,
case WLAN_PUB_ACTION_TDLS_DISCOVER_RES:
/* no special handling */
ret = ieee80211_tdls_prep_mgmt_packet(wiphy, dev, peer,
- action_code,
+ link_id, action_code,
dialog_token,
status_code,
peer_capability,
@@ -1240,8 +1340,8 @@ int ieee80211_tdls_mgmt(struct wiphy *wiphy, struct net_device *dev,
break;
}
- tdls_dbg(sdata, "TDLS mgmt action %d peer %pM status %d\n",
- action_code, peer, ret);
+ tdls_dbg(sdata, "TDLS mgmt action %d peer %pM link_id %d status %d\n",
+ action_code, peer, link_id, ret);
return ret;
}
@@ -1431,8 +1531,8 @@ int ieee80211_tdls_oper(struct wiphy *wiphy, struct net_device *dev,
}
if (ret == 0)
- ieee80211_queue_work(&sdata->local->hw,
- &sdata->deflink.u.mgd.request_smps_work);
+ wiphy_work_queue(sdata->local->hw.wiphy,
+ &sdata->deflink.u.mgd.request_smps_work);
mutex_unlock(&local->mtx);
sdata_unlock(sdata);
@@ -1497,6 +1597,7 @@ ieee80211_tdls_ch_sw_tmpl_get(struct sta_info *sta, u8 oper_class,
int extra_ies_len = 2 + sizeof(struct ieee80211_ch_switch_timing);
u8 *pos = extra_ies;
struct sk_buff *skb;
+ int link_id = sta->sta.valid_links ? ffs(sta->sta.valid_links) - 1 : 0;
/*
* if chandef points to a wide channel add a Secondary-Channel
@@ -1524,6 +1625,7 @@ ieee80211_tdls_ch_sw_tmpl_get(struct sta_info *sta, u8 oper_class,
iee80211_tdls_add_ch_switch_timing(pos, 0, 0);
skb = ieee80211_tdls_build_mgmt_packet_data(sdata, sta->sta.addr,
+ link_id,
WLAN_TDLS_CHANNEL_SWITCH_REQUEST,
0, 0, !sta->sta.tdls_initiator,
extra_ies, extra_ies_len,
@@ -1644,11 +1746,13 @@ ieee80211_tdls_ch_sw_resp_tmpl_get(struct sta_info *sta,
struct ieee80211_sub_if_data *sdata = sta->sdata;
struct sk_buff *skb;
u8 extra_ies[2 + sizeof(struct ieee80211_ch_switch_timing)];
+ int link_id = sta->sta.valid_links ? ffs(sta->sta.valid_links) - 1 : 0;
/* initial timing are always zero in the template */
iee80211_tdls_add_ch_switch_timing(extra_ies, 0, 0);
skb = ieee80211_tdls_build_mgmt_packet_data(sdata, sta->sta.addr,
+ link_id,
WLAN_TDLS_CHANNEL_SWITCH_RESPONSE,
0, 0, !sta->sta.tdls_initiator,
extra_ies, sizeof(extra_ies), 0, NULL);
diff --git a/net/mac80211/trace.h b/net/mac80211/trace.h
index db0d0132c58c..b8c53b4a710b 100644
--- a/net/mac80211/trace.h
+++ b/net/mac80211/trace.h
@@ -2,7 +2,7 @@
/*
* Portions of this file
* Copyright(c) 2016-2017 Intel Deutschland GmbH
- * Copyright (C) 2018 - 2022 Intel Corporation
+ * Copyright (C) 2018 - 2023 Intel Corporation
*/
#if !defined(__MAC80211_DRIVER_TRACE) || defined(TRACE_HEADER_MULTI_READ)
@@ -17,7 +17,7 @@
#define MAXNAME 32
#define LOCAL_ENTRY __array(char, wiphy_name, 32)
-#define LOCAL_ASSIGN strlcpy(__entry->wiphy_name, wiphy_name(local->hw.wiphy), MAXNAME)
+#define LOCAL_ASSIGN strscpy(__entry->wiphy_name, wiphy_name(local->hw.wiphy), MAXNAME)
#define LOCAL_PR_FMT "%s"
#define LOCAL_PR_ARG __entry->wiphy_name
@@ -634,6 +634,7 @@ TRACE_EVENT(drv_set_key,
LOCAL_ENTRY
VIF_ENTRY
STA_ENTRY
+ __field(u32, cmd)
KEY_ENTRY
),
@@ -641,12 +642,13 @@ TRACE_EVENT(drv_set_key,
LOCAL_ASSIGN;
VIF_ASSIGN;
STA_ASSIGN;
+ __entry->cmd = cmd;
KEY_ASSIGN(key);
),
TP_printk(
- LOCAL_PR_FMT VIF_PR_FMT STA_PR_FMT KEY_PR_FMT,
- LOCAL_PR_ARG, VIF_PR_ARG, STA_PR_ARG, KEY_PR_ARG
+ LOCAL_PR_FMT VIF_PR_FMT STA_PR_FMT " cmd: %d" KEY_PR_FMT,
+ LOCAL_PR_ARG, VIF_PR_ARG, STA_PR_ARG, __entry->cmd, KEY_PR_ARG
)
);
diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c
index 13b522dab0a3..7fe7280e8437 100644
--- a/net/mac80211/tx.c
+++ b/net/mac80211/tx.c
@@ -26,6 +26,7 @@
#include <net/codel_impl.h>
#include <asm/unaligned.h>
#include <net/fq_impl.h>
+#include <net/gso.h>
#include "ieee80211_i.h"
#include "driver-ops.h"
@@ -581,25 +582,9 @@ ieee80211_select_link_key(struct ieee80211_tx_data *tx)
{
struct ieee80211_hdr *hdr = (struct ieee80211_hdr *)tx->skb->data;
struct ieee80211_tx_info *info = IEEE80211_SKB_CB(tx->skb);
- enum {
- USE_NONE,
- USE_MGMT_KEY,
- USE_MCAST_KEY,
- } which_key = USE_NONE;
struct ieee80211_link_data *link;
unsigned int link_id;
- if (ieee80211_is_group_privacy_action(tx->skb))
- which_key = USE_MCAST_KEY;
- else if (ieee80211_is_mgmt(hdr->frame_control) &&
- is_multicast_ether_addr(hdr->addr1) &&
- ieee80211_is_robust_mgmt_frame(tx->skb))
- which_key = USE_MGMT_KEY;
- else if (is_multicast_ether_addr(hdr->addr1))
- which_key = USE_MCAST_KEY;
- else
- return NULL;
-
link_id = u32_get_bits(info->control.flags, IEEE80211_TX_CTRL_MLO_LINK);
if (link_id == IEEE80211_LINK_UNSPECIFIED) {
link = &tx->sdata->deflink;
@@ -609,14 +594,14 @@ ieee80211_select_link_key(struct ieee80211_tx_data *tx)
return NULL;
}
- switch (which_key) {
- case USE_NONE:
- break;
- case USE_MGMT_KEY:
+ if (ieee80211_is_group_privacy_action(tx->skb))
+ return rcu_dereference(link->default_multicast_key);
+ else if (ieee80211_is_mgmt(hdr->frame_control) &&
+ is_multicast_ether_addr(hdr->addr1) &&
+ ieee80211_is_robust_mgmt_frame(tx->skb))
return rcu_dereference(link->default_mgmt_key);
- case USE_MCAST_KEY:
+ else if (is_multicast_ether_addr(hdr->addr1))
return rcu_dereference(link->default_multicast_key);
- }
return NULL;
}
@@ -860,7 +845,7 @@ ieee80211_tx_h_sequence(struct ieee80211_tx_data *tx)
/* SNS11 from 802.11be 10.3.2.14 */
if (unlikely(is_multicast_ether_addr(hdr->addr1) &&
- info->control.vif->valid_links &&
+ ieee80211_vif_is_mld(info->control.vif) &&
info->control.vif->type == NL80211_IFTYPE_AP)) {
if (info->control.flags & IEEE80211_TX_CTRL_MCAST_MLO_FIRST_TX)
tx->sdata->mld_mcast_seq += 0x10;
@@ -2626,7 +2611,7 @@ static struct sk_buff *ieee80211_build_hdr(struct ieee80211_sub_if_data *sdata,
ethertype = (skb->data[12] << 8) | skb->data[13];
fc = cpu_to_le16(IEEE80211_FTYPE_DATA | IEEE80211_STYPE_DATA);
- if (!sdata->vif.valid_links)
+ if (!ieee80211_vif_is_mld(&sdata->vif))
chanctx_conf =
rcu_dereference(sdata->vif.bss_conf.chanctx_conf);
@@ -2643,7 +2628,7 @@ static struct sk_buff *ieee80211_build_hdr(struct ieee80211_sub_if_data *sdata,
authorized = test_sta_flag(sta, WLAN_STA_AUTHORIZED);
wme_sta = sta->sta.wme;
}
- if (!sdata->vif.valid_links) {
+ if (!ieee80211_vif_is_mld(&sdata->vif)) {
struct ieee80211_sub_if_data *ap_sdata;
/* override chanctx_conf from AP (we don't have one) */
@@ -2661,7 +2646,7 @@ static struct sk_buff *ieee80211_build_hdr(struct ieee80211_sub_if_data *sdata,
/* DA BSSID SA */
memcpy(hdr.addr1, skb->data, ETH_ALEN);
- if (sdata->vif.valid_links && sta && !sta->sta.mlo) {
+ if (ieee80211_vif_is_mld(&sdata->vif) && sta && !sta->sta.mlo) {
struct ieee80211_link_data *link;
link_id = sta->deflink.link_id;
@@ -2769,10 +2754,20 @@ static struct sk_buff *ieee80211_build_hdr(struct ieee80211_sub_if_data *sdata,
tdls_peer = test_sta_flag(sta, WLAN_STA_TDLS_PEER);
if (tdls_peer) {
+ /* For TDLS only one link can be valid with peer STA */
+ int tdls_link_id = sta->sta.valid_links ?
+ __ffs(sta->sta.valid_links) : 0;
+ struct ieee80211_link_data *link;
+
/* DA SA BSSID */
memcpy(hdr.addr1, skb->data, ETH_ALEN);
memcpy(hdr.addr2, skb->data + ETH_ALEN, ETH_ALEN);
- memcpy(hdr.addr3, sdata->deflink.u.mgd.bssid, ETH_ALEN);
+ link = rcu_dereference(sdata->link[tdls_link_id]);
+ if (WARN_ON_ONCE(!link)) {
+ ret = -EINVAL;
+ goto free;
+ }
+ memcpy(hdr.addr3, link->u.mgd.bssid, ETH_ALEN);
hdrlen = 24;
} else if (sdata->u.mgd.use_4addr &&
cpu_to_be16(ethertype) != sdata->control_port_protocol) {
@@ -2813,7 +2808,7 @@ static struct sk_buff *ieee80211_build_hdr(struct ieee80211_sub_if_data *sdata,
}
if (!chanctx_conf) {
- if (!sdata->vif.valid_links) {
+ if (!ieee80211_vif_is_mld(&sdata->vif)) {
ret = -ENOTCONN;
goto free;
}
@@ -3055,7 +3050,7 @@ void ieee80211_check_fast_xmit(struct sta_info *sta)
!ieee80211_hw_check(&local->hw, SUPPORTS_TX_FRAG))
goto out;
- if (!sdata->vif.valid_links) {
+ if (!ieee80211_vif_is_mld(&sdata->vif)) {
rcu_read_lock();
chanctx_conf =
rcu_dereference(sdata->vif.bss_conf.chanctx_conf);
@@ -3082,10 +3077,18 @@ void ieee80211_check_fast_xmit(struct sta_info *sta)
break;
case NL80211_IFTYPE_STATION:
if (test_sta_flag(sta, WLAN_STA_TDLS_PEER)) {
+ /* For TDLS only one link can be valid with peer STA */
+ int tdls_link_id = sta->sta.valid_links ?
+ __ffs(sta->sta.valid_links) : 0;
+ struct ieee80211_link_data *link;
+
/* DA SA BSSID */
build.da_offs = offsetof(struct ieee80211_hdr, addr1);
build.sa_offs = offsetof(struct ieee80211_hdr, addr2);
- memcpy(hdr->addr3, sdata->deflink.u.mgd.bssid, ETH_ALEN);
+ link = rcu_dereference(sdata->link[tdls_link_id]);
+ if (WARN_ON_ONCE(!link))
+ break;
+ memcpy(hdr->addr3, link->u.mgd.bssid, ETH_ALEN);
build.hdr_len = 24;
break;
}
@@ -3126,7 +3129,7 @@ void ieee80211_check_fast_xmit(struct sta_info *sta)
fc |= cpu_to_le16(IEEE80211_FCTL_FROMDS);
/* DA BSSID SA */
build.da_offs = offsetof(struct ieee80211_hdr, addr1);
- if (sta->sta.mlo || !sdata->vif.valid_links) {
+ if (sta->sta.mlo || !ieee80211_vif_is_mld(&sdata->vif)) {
memcpy(hdr->addr2, sdata->vif.addr, ETH_ALEN);
} else {
unsigned int link_id = sta->deflink.link_id;
@@ -4495,7 +4498,7 @@ netdev_tx_t ieee80211_subif_start_xmit(struct sk_buff *skb,
__ieee80211_subif_start_xmit(skb, dev, 0,
IEEE80211_TX_CTRL_MLO_LINK_UNSPEC,
NULL);
- } else if (sdata->vif.valid_links &&
+ } else if (ieee80211_vif_is_mld(&sdata->vif) &&
sdata->vif.type == NL80211_IFTYPE_AP &&
!ieee80211_hw_check(&sdata->local->hw, MLO_MCAST_MULTI_LINK_TX)) {
ieee80211_mlo_multicast_tx(dev, skb);
@@ -4771,7 +4774,7 @@ static bool ieee80211_tx_pending_skb(struct ieee80211_local *local,
if (info->control.flags & IEEE80211_TX_INTCFL_NEED_TXPROCESSING) {
/* update band only for non-MLD */
- if (!sdata->vif.valid_links) {
+ if (!ieee80211_vif_is_mld(&sdata->vif)) {
chanctx_conf =
rcu_dereference(sdata->vif.bss_conf.chanctx_conf);
if (unlikely(!chanctx_conf)) {
@@ -6018,7 +6021,7 @@ void __ieee80211_tx_skb_tid_band(struct ieee80211_sub_if_data *sdata,
BUILD_BUG_ON(!FIELD_FIT(IEEE80211_TX_CTRL_MLO_LINK,
IEEE80211_LINK_UNSPECIFIED));
- if (!sdata->vif.valid_links) {
+ if (!ieee80211_vif_is_mld(&sdata->vif)) {
link = 0;
} else if (link_id >= 0) {
link = link_id;
@@ -6064,7 +6067,7 @@ void ieee80211_tx_skb_tid(struct ieee80211_sub_if_data *sdata,
enum nl80211_band band;
rcu_read_lock();
- if (!sdata->vif.valid_links) {
+ if (!ieee80211_vif_is_mld(&sdata->vif)) {
WARN_ON(link_id >= 0);
chanctx_conf =
rcu_dereference(sdata->vif.bss_conf.chanctx_conf);
diff --git a/net/mac80211/util.c b/net/mac80211/util.c
index 3bd07a0a782f..8a6917cf63cf 100644
--- a/net/mac80211/util.c
+++ b/net/mac80211/util.c
@@ -6,7 +6,7 @@
* Copyright 2007 Johannes Berg <johannes@sipsolutions.net>
* Copyright 2013-2014 Intel Mobile Communications GmbH
* Copyright (C) 2015-2017 Intel Deutschland GmbH
- * Copyright (C) 2018-2022 Intel Corporation
+ * Copyright (C) 2018-2023 Intel Corporation
*
* utilities for mac80211
*/
@@ -918,6 +918,7 @@ ieee80211_parse_extension_element(u32 *crc,
struct ieee80211_elems_parse_params *params)
{
const void *data = elem->data + 1;
+ bool calc_crc = false;
u8 len;
if (!elem->datalen)
@@ -927,12 +928,9 @@ ieee80211_parse_extension_element(u32 *crc,
switch (elem->data[0]) {
case WLAN_EID_EXT_HE_MU_EDCA:
- if (len >= sizeof(*elems->mu_edca_param_set)) {
+ calc_crc = true;
+ if (len >= sizeof(*elems->mu_edca_param_set))
elems->mu_edca_param_set = data;
- if (crc)
- *crc = crc32_be(*crc, (void *)elem,
- elem->datalen + 2);
- }
break;
case WLAN_EID_EXT_HE_CAPABILITY:
if (ieee80211_he_capa_size_ok(data, len)) {
@@ -941,13 +939,10 @@ ieee80211_parse_extension_element(u32 *crc,
}
break;
case WLAN_EID_EXT_HE_OPERATION:
+ calc_crc = true;
if (len >= sizeof(*elems->he_operation) &&
- len >= ieee80211_he_oper_size(data) - 1) {
- if (crc)
- *crc = crc32_be(*crc, (void *)elem,
- elem->datalen + 2);
+ len >= ieee80211_he_oper_size(data) - 1)
elems->he_operation = data;
- }
break;
case WLAN_EID_EXT_UORA:
if (len >= 1)
@@ -981,14 +976,36 @@ ieee80211_parse_extension_element(u32 *crc,
case WLAN_EID_EXT_EHT_OPERATION:
if (ieee80211_eht_oper_size_ok(data, len))
elems->eht_operation = data;
+ calc_crc = true;
break;
case WLAN_EID_EXT_EHT_MULTI_LINK:
+ calc_crc = true;
+
if (ieee80211_mle_size_ok(data, len)) {
- elems->multi_link = (void *)data;
- elems->multi_link_len = len;
+ const struct ieee80211_multi_link_elem *mle =
+ (void *)data;
+
+ switch (le16_get_bits(mle->control,
+ IEEE80211_ML_CONTROL_TYPE)) {
+ case IEEE80211_ML_CONTROL_TYPE_BASIC:
+ elems->ml_basic_elem = (void *)elem;
+ elems->ml_basic = data;
+ elems->ml_basic_len = len;
+ break;
+ case IEEE80211_ML_CONTROL_TYPE_RECONF:
+ elems->ml_reconf_elem = (void *)elem;
+ elems->ml_reconf = data;
+ elems->ml_reconf_len = len;
+ break;
+ default:
+ break;
+ }
}
break;
}
+
+ if (crc && calc_crc)
+ *crc = crc32_be(*crc, (void *)elem, elem->datalen + 2);
}
static u32
@@ -1458,56 +1475,11 @@ static size_t ieee802_11_find_bssid_profile(const u8 *start, size_t len,
return found ? profile_len : 0;
}
-static void ieee80211_defragment_element(struct ieee802_11_elems *elems,
- void **elem_ptr, size_t *len,
- size_t total_len, u8 frag_id)
-{
- u8 *data = *elem_ptr, *pos, *start;
- const struct element *elem;
-
- /*
- * Since 'data' points to the data of the element, not the element
- * itself, allow 254 in case it was an extended element where the
- * extended ID isn't part of the data we see here and thus not part of
- * 'len' either.
- */
- if (!data || (*len != 254 && *len != 255))
- return;
-
- start = elems->scratch_pos;
-
- if (WARN_ON(*len > (elems->scratch + elems->scratch_len -
- elems->scratch_pos)))
- return;
-
- memcpy(elems->scratch_pos, data, *len);
- elems->scratch_pos += *len;
-
- pos = data + *len;
- total_len -= *len;
- for_each_element(elem, pos, total_len) {
- if (elem->id != frag_id)
- break;
-
- if (WARN_ON(elem->datalen >
- (elems->scratch + elems->scratch_len -
- elems->scratch_pos)))
- return;
-
- memcpy(elems->scratch_pos, elem->data, elem->datalen);
- elems->scratch_pos += elem->datalen;
-
- *len += elem->datalen;
- }
-
- *elem_ptr = start;
-}
-
static void ieee80211_mle_get_sta_prof(struct ieee802_11_elems *elems,
u8 link_id)
{
- const struct ieee80211_multi_link_elem *ml = elems->multi_link;
- size_t ml_len = elems->multi_link_len;
+ const struct ieee80211_multi_link_elem *ml = elems->ml_basic;
+ ssize_t ml_len = elems->ml_basic_len;
const struct element *sub;
if (!ml || !ml_len)
@@ -1519,12 +1491,14 @@ static void ieee80211_mle_get_sta_prof(struct ieee802_11_elems *elems,
for_each_mle_subelement(sub, (u8 *)ml, ml_len) {
struct ieee80211_mle_per_sta_profile *prof = (void *)sub->data;
+ ssize_t sta_prof_len;
u16 control;
if (sub->id != IEEE80211_MLE_SUBELEM_PER_STA_PROFILE)
continue;
- if (!ieee80211_mle_sta_prof_size_ok(sub->data, sub->datalen))
+ if (!ieee80211_mle_basic_sta_prof_size_ok(sub->data,
+ sub->datalen))
return;
control = le16_to_cpu(prof->control);
@@ -1536,14 +1510,23 @@ static void ieee80211_mle_get_sta_prof(struct ieee802_11_elems *elems,
if (!(control & IEEE80211_MLE_STA_CONTROL_COMPLETE_PROFILE))
return;
- elems->prof = prof;
- elems->sta_prof_len = sub->datalen;
-
/* the sub element can be fragmented */
- ieee80211_defragment_element(elems, (void **)&elems->prof,
- &elems->sta_prof_len,
- ml_len - (sub->data - (u8 *)ml),
- IEEE80211_MLE_SUBELEM_FRAGMENT);
+ sta_prof_len =
+ cfg80211_defragment_element(sub,
+ (u8 *)ml, ml_len,
+ elems->scratch_pos,
+ elems->scratch +
+ elems->scratch_len -
+ elems->scratch_pos,
+ IEEE80211_MLE_SUBELEM_FRAGMENT);
+
+ if (sta_prof_len < 0)
+ return;
+
+ elems->prof = (void *)elems->scratch_pos;
+ elems->sta_prof_len = sta_prof_len;
+ elems->scratch_pos += sta_prof_len;
+
return;
}
}
@@ -1557,17 +1540,27 @@ static void ieee80211_mle_parse_link(struct ieee802_11_elems *elems,
.from_ap = params->from_ap,
.link_id = -1,
};
+ ssize_t ml_len = elems->ml_basic_len;
const struct element *non_inherit = NULL;
const u8 *end;
if (params->link_id == -1)
return;
- ieee80211_defragment_element(elems, (void **)&elems->multi_link,
- &elems->multi_link_len,
- elems->total_len - ((u8 *)elems->multi_link -
- elems->ie_start),
- WLAN_EID_FRAGMENT);
+ ml_len = cfg80211_defragment_element(elems->ml_basic_elem,
+ elems->ie_start,
+ elems->total_len,
+ elems->scratch_pos,
+ elems->scratch +
+ elems->scratch_len -
+ elems->scratch_pos,
+ WLAN_EID_FRAGMENT);
+
+ if (ml_len < 0)
+ return;
+
+ elems->ml_basic = (const void *)elems->scratch_pos;
+ elems->ml_basic_len = ml_len;
ieee80211_mle_get_sta_prof(elems, params->link_id);
prof = elems->prof;
@@ -1604,7 +1597,7 @@ ieee802_11_parse_elems_full(struct ieee80211_elems_parse_params *params)
const struct element *non_inherit = NULL;
u8 *nontransmitted_profile;
int nontransmitted_profile_len = 0;
- size_t scratch_len = params->scratch_len ?: 3 * params->len;
+ size_t scratch_len = 3 * params->len;
elems = kzalloc(sizeof(*elems) + scratch_len, GFP_ATOMIC);
if (!elems)
@@ -1824,7 +1817,7 @@ void ieee80211_send_auth(struct ieee80211_sub_if_data *sdata,
struct ieee80211_local *local = sdata->local;
struct sk_buff *skb;
struct ieee80211_mgmt *mgmt;
- bool multi_link = sdata->vif.valid_links;
+ bool multi_link = ieee80211_vif_is_mld(&sdata->vif);
struct {
u8 id;
u8 len;
@@ -1918,7 +1911,7 @@ void ieee80211_send_deauth_disassoc(struct ieee80211_sub_if_data *sdata,
}
}
-static u8 *ieee80211_write_he_6ghz_cap(u8 *pos, __le16 cap, u8 *end)
+u8 *ieee80211_write_he_6ghz_cap(u8 *pos, __le16 cap, u8 *end)
{
if ((end - pos) < 5)
return pos;
@@ -2121,8 +2114,7 @@ static int ieee80211_build_preq_ies_band(struct ieee80211_sub_if_data *sdata,
*offset = noffset;
}
- he_cap = ieee80211_get_he_iftype_cap(sband,
- ieee80211_vif_type_p2p(&sdata->vif));
+ he_cap = ieee80211_get_he_iftype_cap_vif(sband, &sdata->vif);
if (he_cap &&
cfg80211_any_usable_channels(local->hw.wiphy, BIT(sband->band),
IEEE80211_CHAN_NO_HE)) {
@@ -2131,8 +2123,7 @@ static int ieee80211_build_preq_ies_band(struct ieee80211_sub_if_data *sdata,
goto out_err;
}
- eht_cap = ieee80211_get_eht_iftype_cap(sband,
- ieee80211_vif_type_p2p(&sdata->vif));
+ eht_cap = ieee80211_get_eht_iftype_cap_vif(sband, &sdata->vif);
if (eht_cap &&
cfg80211_any_usable_channels(local->hw.wiphy, BIT(sband->band),
@@ -2150,8 +2141,7 @@ static int ieee80211_build_preq_ies_band(struct ieee80211_sub_if_data *sdata,
struct ieee80211_supported_band *sband6;
sband6 = local->hw.wiphy->bands[NL80211_BAND_6GHZ];
- he_cap = ieee80211_get_he_iftype_cap(sband6,
- ieee80211_vif_type_p2p(&sdata->vif));
+ he_cap = ieee80211_get_he_iftype_cap_vif(sband6, &sdata->vif);
if (he_cap) {
enum nl80211_iftype iftype =
@@ -2373,6 +2363,7 @@ static void ieee80211_handle_reconfig_failure(struct ieee80211_local *local)
local->resuming = false;
local->suspended = false;
local->in_reconfig = false;
+ local->reconfig_failure = true;
ieee80211_flush_completed_scan(local, true);
@@ -2475,6 +2466,35 @@ static int ieee80211_reconfig_nan(struct ieee80211_sub_if_data *sdata)
return 0;
}
+static void ieee80211_reconfig_ap_links(struct ieee80211_local *local,
+ struct ieee80211_sub_if_data *sdata,
+ u64 changed)
+{
+ int link_id;
+
+ for (link_id = 0; link_id < ARRAY_SIZE(sdata->link); link_id++) {
+ struct ieee80211_link_data *link;
+
+ if (!(sdata->vif.active_links & BIT(link_id)))
+ continue;
+
+ link = sdata_dereference(sdata->link[link_id], sdata);
+ if (!link)
+ continue;
+
+ if (rcu_access_pointer(link->u.ap.beacon))
+ drv_start_ap(local, sdata, link->conf);
+
+ if (!link->conf->enable_beacon)
+ continue;
+
+ changed |= BSS_CHANGED_BEACON |
+ BSS_CHANGED_BEACON_ENABLED;
+
+ ieee80211_link_info_change_notify(sdata, link, changed);
+ }
+}
+
int ieee80211_reconfig(struct ieee80211_local *local)
{
struct ieee80211_hw *hw = &local->hw;
@@ -2624,21 +2644,55 @@ int ieee80211_reconfig(struct ieee80211_local *local)
/* Finally also reconfigure all the BSS information */
list_for_each_entry(sdata, &local->interfaces, list) {
+ /* common change flags for all interface types - link only */
+ u64 changed = BSS_CHANGED_ERP_CTS_PROT |
+ BSS_CHANGED_ERP_PREAMBLE |
+ BSS_CHANGED_ERP_SLOT |
+ BSS_CHANGED_HT |
+ BSS_CHANGED_BASIC_RATES |
+ BSS_CHANGED_BEACON_INT |
+ BSS_CHANGED_BSSID |
+ BSS_CHANGED_CQM |
+ BSS_CHANGED_QOS |
+ BSS_CHANGED_TXPOWER |
+ BSS_CHANGED_MCAST_RATE;
+ struct ieee80211_link_data *link = NULL;
unsigned int link_id;
- u32 changed;
+ u32 active_links = 0;
if (!ieee80211_sdata_running(sdata))
continue;
sdata_lock(sdata);
+ if (ieee80211_vif_is_mld(&sdata->vif)) {
+ struct ieee80211_bss_conf *old[IEEE80211_MLD_MAX_NUM_LINKS] = {
+ [0] = &sdata->vif.bss_conf,
+ };
+
+ if (sdata->vif.type == NL80211_IFTYPE_STATION) {
+ /* start with a single active link */
+ active_links = sdata->vif.active_links;
+ link_id = ffs(active_links) - 1;
+ sdata->vif.active_links = BIT(link_id);
+ }
+
+ drv_change_vif_links(local, sdata, 0,
+ sdata->vif.active_links,
+ old);
+ }
+
for (link_id = 0;
link_id < ARRAY_SIZE(sdata->vif.link_conf);
link_id++) {
- struct ieee80211_link_data *link;
+ if (ieee80211_vif_is_mld(&sdata->vif) &&
+ !(sdata->vif.active_links & BIT(link_id)))
+ continue;
link = sdata_dereference(sdata->link[link_id], sdata);
- if (link)
- ieee80211_assign_chanctx(local, sdata, link);
+ if (!link)
+ continue;
+
+ ieee80211_assign_chanctx(local, sdata, link);
}
switch (sdata->vif.type) {
@@ -2658,42 +2712,42 @@ int ieee80211_reconfig(struct ieee80211_local *local)
&sdata->deflink.tx_conf[i]);
break;
}
- sdata_unlock(sdata);
-
- /* common change flags for all interface types */
- changed = BSS_CHANGED_ERP_CTS_PROT |
- BSS_CHANGED_ERP_PREAMBLE |
- BSS_CHANGED_ERP_SLOT |
- BSS_CHANGED_HT |
- BSS_CHANGED_BASIC_RATES |
- BSS_CHANGED_BEACON_INT |
- BSS_CHANGED_BSSID |
- BSS_CHANGED_CQM |
- BSS_CHANGED_QOS |
- BSS_CHANGED_IDLE |
- BSS_CHANGED_TXPOWER |
- BSS_CHANGED_MCAST_RATE;
if (sdata->vif.bss_conf.mu_mimo_owner)
changed |= BSS_CHANGED_MU_GROUPS;
+ if (!ieee80211_vif_is_mld(&sdata->vif))
+ changed |= BSS_CHANGED_IDLE;
+
switch (sdata->vif.type) {
case NL80211_IFTYPE_STATION:
- changed |= BSS_CHANGED_ASSOC |
- BSS_CHANGED_ARP_FILTER |
- BSS_CHANGED_PS;
-
- /* Re-send beacon info report to the driver */
- if (sdata->deflink.u.mgd.have_beacon)
- changed |= BSS_CHANGED_BEACON_INFO;
-
- if (sdata->vif.bss_conf.max_idle_period ||
- sdata->vif.bss_conf.protected_keep_alive)
- changed |= BSS_CHANGED_KEEP_ALIVE;
-
- sdata_lock(sdata);
- ieee80211_bss_info_change_notify(sdata, changed);
- sdata_unlock(sdata);
+ if (!ieee80211_vif_is_mld(&sdata->vif)) {
+ changed |= BSS_CHANGED_ASSOC |
+ BSS_CHANGED_ARP_FILTER |
+ BSS_CHANGED_PS;
+
+ /* Re-send beacon info report to the driver */
+ if (sdata->deflink.u.mgd.have_beacon)
+ changed |= BSS_CHANGED_BEACON_INFO;
+
+ if (sdata->vif.bss_conf.max_idle_period ||
+ sdata->vif.bss_conf.protected_keep_alive)
+ changed |= BSS_CHANGED_KEEP_ALIVE;
+
+ if (sdata->vif.bss_conf.eht_puncturing)
+ changed |= BSS_CHANGED_EHT_PUNCTURING;
+
+ ieee80211_bss_info_change_notify(sdata,
+ changed);
+ } else if (!WARN_ON(!link)) {
+ ieee80211_link_info_change_notify(sdata, link,
+ changed);
+ changed = BSS_CHANGED_ASSOC |
+ BSS_CHANGED_IDLE |
+ BSS_CHANGED_PS |
+ BSS_CHANGED_ARP_FILTER;
+ ieee80211_vif_cfg_change_notify(sdata, changed);
+ }
break;
case NL80211_IFTYPE_OCB:
changed |= BSS_CHANGED_OCB;
@@ -2703,7 +2757,13 @@ int ieee80211_reconfig(struct ieee80211_local *local)
changed |= BSS_CHANGED_IBSS;
fallthrough;
case NL80211_IFTYPE_AP:
- changed |= BSS_CHANGED_SSID | BSS_CHANGED_P2P_PS;
+ changed |= BSS_CHANGED_P2P_PS;
+
+ if (ieee80211_vif_is_mld(&sdata->vif))
+ ieee80211_vif_cfg_change_notify(sdata,
+ BSS_CHANGED_SSID);
+ else
+ changed |= BSS_CHANGED_SSID;
if (sdata->vif.bss_conf.ftm_responder == 1 &&
wiphy_ext_feature_isset(sdata->local->hw.wiphy,
@@ -2713,6 +2773,13 @@ int ieee80211_reconfig(struct ieee80211_local *local)
if (sdata->vif.type == NL80211_IFTYPE_AP) {
changed |= BSS_CHANGED_AP_PROBE_RESP;
+ if (ieee80211_vif_is_mld(&sdata->vif)) {
+ ieee80211_reconfig_ap_links(local,
+ sdata,
+ changed);
+ break;
+ }
+
if (rcu_access_pointer(sdata->deflink.u.ap.beacon))
drv_start_ap(local, sdata,
sdata->deflink.conf);
@@ -2728,6 +2795,7 @@ int ieee80211_reconfig(struct ieee80211_local *local)
case NL80211_IFTYPE_NAN:
res = ieee80211_reconfig_nan(sdata);
if (res < 0) {
+ sdata_unlock(sdata);
ieee80211_handle_reconfig_failure(local);
return res;
}
@@ -2745,6 +2813,10 @@ int ieee80211_reconfig(struct ieee80211_local *local)
WARN_ON(1);
break;
}
+ sdata_unlock(sdata);
+
+ if (active_links)
+ ieee80211_set_active_links(&sdata->vif, active_links);
}
ieee80211_recalc_ps(local);
@@ -2860,7 +2932,7 @@ int ieee80211_reconfig(struct ieee80211_local *local)
/* Requeue all works */
list_for_each_entry(sdata, &local->interfaces, list)
- ieee80211_queue_work(&local->hw, &sdata->work);
+ wiphy_work_queue(local->hw.wiphy, &sdata->work);
}
ieee80211_wake_queues_by_reason(hw, IEEE80211_MAX_QUEUE_MAP,
@@ -3801,10 +3873,8 @@ bool ieee80211_chandef_he_6ghz_oper(struct ieee80211_sub_if_data *sdata,
}
eht_cap = ieee80211_get_eht_iftype_cap(sband, iftype);
- if (!eht_cap) {
- sdata_info(sdata, "Missing iftype sband data/EHT cap");
+ if (!eht_cap)
eht_oper = NULL;
- }
he_6ghz_oper = ieee80211_he_6ghz_oper(he_oper);
diff --git a/net/mac802154/ieee802154_i.h b/net/mac802154/ieee802154_i.h
index 63bab99ed368..c347ec9ff8c9 100644
--- a/net/mac802154/ieee802154_i.h
+++ b/net/mac802154/ieee802154_i.h
@@ -58,6 +58,7 @@ struct ieee802154_local {
/* Scanning */
u8 scan_page;
u8 scan_channel;
+ struct ieee802154_beacon_req_frame scan_beacon_req;
struct cfg802154_scan_request __rcu *scan_req;
struct delayed_work scan_work;
@@ -70,6 +71,8 @@ struct ieee802154_local {
/* Asynchronous tasks */
struct list_head rx_beacon_list;
struct work_struct rx_beacon_work;
+ struct list_head rx_mac_cmd_list;
+ struct work_struct rx_mac_cmd_work;
bool started;
bool suspended;
@@ -154,6 +157,22 @@ ieee802154_sdata_running(struct ieee802154_sub_if_data *sdata)
return test_bit(SDATA_STATE_RUNNING, &sdata->state);
}
+static inline int ieee802154_get_mac_cmd(struct sk_buff *skb, u8 *mac_cmd)
+{
+ struct ieee802154_mac_cmd_pl mac_pl;
+ int ret;
+
+ if (mac_cb(skb)->type != IEEE802154_FC_TYPE_MAC_CMD)
+ return -EINVAL;
+
+ ret = ieee802154_mac_cmd_pl_pull(skb, &mac_pl);
+ if (ret)
+ return ret;
+
+ *mac_cmd = mac_pl.cmd_id;
+ return 0;
+}
+
extern struct ieee802154_mlme_ops mac802154_mlme_wpan;
void ieee802154_rx(struct ieee802154_local *local, struct sk_buff *skb);
@@ -275,6 +294,8 @@ static inline bool mac802154_is_beaconing(struct ieee802154_local *local)
return test_bit(IEEE802154_IS_BEACONING, &local->ongoing);
}
+void mac802154_rx_mac_cmd_worker(struct work_struct *work);
+
/* interface handling */
int ieee802154_iface_init(void);
void ieee802154_iface_exit(void);
diff --git a/net/mac802154/main.c b/net/mac802154/main.c
index ee23e234b998..357ece67432b 100644
--- a/net/mac802154/main.c
+++ b/net/mac802154/main.c
@@ -90,6 +90,7 @@ ieee802154_alloc_hw(size_t priv_data_len, const struct ieee802154_ops *ops)
INIT_LIST_HEAD(&local->interfaces);
INIT_LIST_HEAD(&local->rx_beacon_list);
+ INIT_LIST_HEAD(&local->rx_mac_cmd_list);
mutex_init(&local->iflist_mtx);
tasklet_setup(&local->tasklet, ieee802154_tasklet_handler);
@@ -100,6 +101,7 @@ ieee802154_alloc_hw(size_t priv_data_len, const struct ieee802154_ops *ops)
INIT_DELAYED_WORK(&local->scan_work, mac802154_scan_worker);
INIT_WORK(&local->rx_beacon_work, mac802154_rx_beacon_worker);
INIT_DELAYED_WORK(&local->beacon_work, mac802154_beacon_worker);
+ INIT_WORK(&local->rx_mac_cmd_work, mac802154_rx_mac_cmd_worker);
/* init supported flags with 802.15.4 default ranges */
phy->supported.max_minbe = 8;
diff --git a/net/mac802154/rx.c b/net/mac802154/rx.c
index da0628ee3c89..e2434b4fe514 100644
--- a/net/mac802154/rx.c
+++ b/net/mac802154/rx.c
@@ -47,6 +47,62 @@ void mac802154_rx_beacon_worker(struct work_struct *work)
kfree(mac_pkt);
}
+static bool mac802154_should_answer_beacon_req(struct ieee802154_local *local)
+{
+ struct cfg802154_beacon_request *beacon_req;
+ unsigned int interval;
+
+ rcu_read_lock();
+ beacon_req = rcu_dereference(local->beacon_req);
+ if (!beacon_req) {
+ rcu_read_unlock();
+ return false;
+ }
+
+ interval = beacon_req->interval;
+ rcu_read_unlock();
+
+ if (!mac802154_is_beaconing(local))
+ return false;
+
+ return interval == IEEE802154_ACTIVE_SCAN_DURATION;
+}
+
+void mac802154_rx_mac_cmd_worker(struct work_struct *work)
+{
+ struct ieee802154_local *local =
+ container_of(work, struct ieee802154_local, rx_mac_cmd_work);
+ struct cfg802154_mac_pkt *mac_pkt;
+ u8 mac_cmd;
+ int rc;
+
+ mac_pkt = list_first_entry_or_null(&local->rx_mac_cmd_list,
+ struct cfg802154_mac_pkt, node);
+ if (!mac_pkt)
+ return;
+
+ rc = ieee802154_get_mac_cmd(mac_pkt->skb, &mac_cmd);
+ if (rc)
+ goto out;
+
+ switch (mac_cmd) {
+ case IEEE802154_CMD_BEACON_REQ:
+ dev_dbg(&mac_pkt->sdata->dev->dev, "processing BEACON REQ\n");
+ if (!mac802154_should_answer_beacon_req(local))
+ break;
+
+ queue_delayed_work(local->mac_wq, &local->beacon_work, 0);
+ break;
+ default:
+ break;
+ }
+
+out:
+ list_del(&mac_pkt->node);
+ kfree_skb(mac_pkt->skb);
+ kfree(mac_pkt);
+}
+
static int
ieee802154_subif_frame(struct ieee802154_sub_if_data *sdata,
struct sk_buff *skb, const struct ieee802154_hdr *hdr)
@@ -140,8 +196,20 @@ ieee802154_subif_frame(struct ieee802154_sub_if_data *sdata,
list_add_tail(&mac_pkt->node, &sdata->local->rx_beacon_list);
queue_work(sdata->local->mac_wq, &sdata->local->rx_beacon_work);
return NET_RX_SUCCESS;
- case IEEE802154_FC_TYPE_ACK:
+
case IEEE802154_FC_TYPE_MAC_CMD:
+ dev_dbg(&sdata->dev->dev, "MAC COMMAND received\n");
+ mac_pkt = kzalloc(sizeof(*mac_pkt), GFP_ATOMIC);
+ if (!mac_pkt)
+ goto fail;
+
+ mac_pkt->skb = skb_get(skb);
+ mac_pkt->sdata = sdata;
+ list_add_tail(&mac_pkt->node, &sdata->local->rx_mac_cmd_list);
+ queue_work(sdata->local->mac_wq, &sdata->local->rx_mac_cmd_work);
+ return NET_RX_SUCCESS;
+
+ case IEEE802154_FC_TYPE_ACK:
goto fail;
case IEEE802154_FC_TYPE_DATA:
diff --git a/net/mac802154/scan.c b/net/mac802154/scan.c
index 5c191bedd72c..d9658f2c4ae6 100644
--- a/net/mac802154/scan.c
+++ b/net/mac802154/scan.c
@@ -18,8 +18,12 @@
#define IEEE802154_BEACON_MHR_SZ 13
#define IEEE802154_BEACON_PL_SZ 4
+#define IEEE802154_MAC_CMD_MHR_SZ 23
+#define IEEE802154_MAC_CMD_PL_SZ 1
#define IEEE802154_BEACON_SKB_SZ (IEEE802154_BEACON_MHR_SZ + \
IEEE802154_BEACON_PL_SZ)
+#define IEEE802154_MAC_CMD_SKB_SZ (IEEE802154_MAC_CMD_MHR_SZ + \
+ IEEE802154_MAC_CMD_PL_SZ)
/* mac802154_scan_cleanup_locked() must be called upon scan completion or abort.
* - Completions are asynchronous, not locked by the rtnl and decided by the
@@ -131,6 +135,42 @@ static int mac802154_scan_find_next_chan(struct ieee802154_local *local,
return 0;
}
+static int mac802154_scan_prepare_beacon_req(struct ieee802154_local *local)
+{
+ memset(&local->scan_beacon_req, 0, sizeof(local->scan_beacon_req));
+ local->scan_beacon_req.mhr.fc.type = IEEE802154_FC_TYPE_MAC_CMD;
+ local->scan_beacon_req.mhr.fc.dest_addr_mode = IEEE802154_SHORT_ADDRESSING;
+ local->scan_beacon_req.mhr.fc.version = IEEE802154_2003_STD;
+ local->scan_beacon_req.mhr.fc.source_addr_mode = IEEE802154_NO_ADDRESSING;
+ local->scan_beacon_req.mhr.dest.mode = IEEE802154_ADDR_SHORT;
+ local->scan_beacon_req.mhr.dest.pan_id = cpu_to_le16(IEEE802154_PANID_BROADCAST);
+ local->scan_beacon_req.mhr.dest.short_addr = cpu_to_le16(IEEE802154_ADDR_BROADCAST);
+ local->scan_beacon_req.mac_pl.cmd_id = IEEE802154_CMD_BEACON_REQ;
+
+ return 0;
+}
+
+static int mac802154_transmit_beacon_req(struct ieee802154_local *local,
+ struct ieee802154_sub_if_data *sdata)
+{
+ struct sk_buff *skb;
+ int ret;
+
+ skb = alloc_skb(IEEE802154_MAC_CMD_SKB_SZ, GFP_KERNEL);
+ if (!skb)
+ return -ENOBUFS;
+
+ skb->dev = sdata->dev;
+
+ ret = ieee802154_mac_cmd_push(skb, &local->scan_beacon_req, NULL, 0);
+ if (ret) {
+ kfree_skb(skb);
+ return ret;
+ }
+
+ return ieee802154_mlme_tx(local, sdata, skb);
+}
+
void mac802154_scan_worker(struct work_struct *work)
{
struct ieee802154_local *local =
@@ -206,6 +246,13 @@ void mac802154_scan_worker(struct work_struct *work)
goto end_scan;
}
+ if (scan_req->type == NL802154_SCAN_ACTIVE) {
+ ret = mac802154_transmit_beacon_req(local, sdata);
+ if (ret)
+ dev_err(&sdata->dev->dev,
+ "Error when transmitting beacon request (%d)\n", ret);
+ }
+
ieee802154_configure_durations(wpan_phy, page, channel);
scan_duration = mac802154_scan_get_channel_time(scan_req_duration,
wpan_phy->symbol_duration);
@@ -231,8 +278,8 @@ int mac802154_trigger_scan_locked(struct ieee802154_sub_if_data *sdata,
if (mac802154_is_scanning(local))
return -EBUSY;
- /* TODO: support other scanning type */
- if (request->type != NL802154_SCAN_PASSIVE)
+ if (request->type != NL802154_SCAN_PASSIVE &&
+ request->type != NL802154_SCAN_ACTIVE)
return -EOPNOTSUPP;
/* Store scanning parameters */
@@ -247,6 +294,8 @@ int mac802154_trigger_scan_locked(struct ieee802154_sub_if_data *sdata,
local->scan_page = request->page;
local->scan_channel = -1;
set_bit(IEEE802154_IS_SCANNING, &local->ongoing);
+ if (request->type == NL802154_SCAN_ACTIVE)
+ mac802154_scan_prepare_beacon_req(local);
nl802154_scan_started(request->wpan_phy, request->wpan_dev);
@@ -354,6 +403,7 @@ void mac802154_beacon_worker(struct work_struct *work)
struct cfg802154_beacon_request *beacon_req;
struct ieee802154_sub_if_data *sdata;
struct wpan_dev *wpan_dev;
+ u8 interval;
int ret;
rcu_read_lock();
@@ -374,6 +424,7 @@ void mac802154_beacon_worker(struct work_struct *work)
}
wpan_dev = beacon_req->wpan_dev;
+ interval = beacon_req->interval;
rcu_read_unlock();
@@ -383,8 +434,9 @@ void mac802154_beacon_worker(struct work_struct *work)
dev_err(&sdata->dev->dev,
"Beacon could not be transmitted (%d)\n", ret);
- queue_delayed_work(local->mac_wq, &local->beacon_work,
- local->beacon_interval);
+ if (interval < IEEE802154_ACTIVE_SCAN_DURATION)
+ queue_delayed_work(local->mac_wq, &local->beacon_work,
+ local->beacon_interval);
}
int mac802154_stop_beacons_locked(struct ieee802154_local *local,
@@ -439,13 +491,17 @@ int mac802154_send_beacons_locked(struct ieee802154_sub_if_data *sdata,
local->beacon.mhr.source.pan_id = request->wpan_dev->pan_id;
local->beacon.mhr.source.extended_addr = request->wpan_dev->extended_addr;
local->beacon.mac_pl.beacon_order = request->interval;
- local->beacon.mac_pl.superframe_order = request->interval;
+ if (request->interval <= IEEE802154_MAX_SCAN_DURATION)
+ local->beacon.mac_pl.superframe_order = request->interval;
local->beacon.mac_pl.final_cap_slot = 0xf;
local->beacon.mac_pl.battery_life_ext = 0;
- /* TODO: Fill this field depending on the coordinator capacity */
+ /* TODO: Fill this field with the coordinator situation in the network */
local->beacon.mac_pl.pan_coordinator = 1;
local->beacon.mac_pl.assoc_permit = 1;
+ if (request->interval == IEEE802154_ACTIVE_SCAN_DURATION)
+ return 0;
+
/* Start the beacon work */
local->beacon_interval =
mac802154_scan_get_channel_time(request->interval,
diff --git a/net/mctp/af_mctp.c b/net/mctp/af_mctp.c
index bb4bd0b6a4f7..f6be58b68c6f 100644
--- a/net/mctp/af_mctp.c
+++ b/net/mctp/af_mctp.c
@@ -485,7 +485,6 @@ static const struct proto_ops mctp_dgram_ops = {
.sendmsg = mctp_sendmsg,
.recvmsg = mctp_recvmsg,
.mmap = sock_no_mmap,
- .sendpage = sock_no_sendpage,
#ifdef CONFIG_COMPAT
.compat_ioctl = mctp_compat_ioctl,
#endif
diff --git a/net/mctp/route.c b/net/mctp/route.c
index f51a05ec7162..ab62fe447038 100644
--- a/net/mctp/route.c
+++ b/net/mctp/route.c
@@ -1249,9 +1249,6 @@ static int mctp_newroute(struct sk_buff *skb, struct nlmsghdr *nlh,
mtu = nla_get_u32(tbx[RTAX_MTU]);
}
- if (rtm->rtm_type != RTN_UNICAST)
- return -EINVAL;
-
rc = mctp_route_add(mdev, daddr_start, rtm->rtm_dst_len, mtu,
rtm->rtm_type);
return rc;
diff --git a/net/mpls/af_mpls.c b/net/mpls/af_mpls.c
index dc5165d3eec4..bf6e81d56263 100644
--- a/net/mpls/af_mpls.c
+++ b/net/mpls/af_mpls.c
@@ -12,6 +12,7 @@
#include <linux/nospec.h>
#include <linux/vmalloc.h>
#include <linux/percpu.h>
+#include <net/gso.h>
#include <net/ip.h>
#include <net/dst.h>
#include <net/sock.h>
diff --git a/net/mpls/mpls_gso.c b/net/mpls/mpls_gso.c
index 1482259de9b5..533d082f0701 100644
--- a/net/mpls/mpls_gso.c
+++ b/net/mpls/mpls_gso.c
@@ -14,6 +14,7 @@
#include <linux/netdev_features.h>
#include <linux/netdevice.h>
#include <linux/skbuff.h>
+#include <net/gso.h>
#include <net/mpls.h>
static struct sk_buff *mpls_gso_segment(struct sk_buff *skb,
diff --git a/net/mptcp/mib.c b/net/mptcp/mib.c
index 0dac2863c6e1..a0990c365a2e 100644
--- a/net/mptcp/mib.c
+++ b/net/mptcp/mib.c
@@ -34,7 +34,11 @@ static const struct snmp_mib mptcp_snmp_list[] = {
SNMP_MIB_ITEM("NoDSSInWindow", MPTCP_MIB_NODSSWINDOW),
SNMP_MIB_ITEM("DuplicateData", MPTCP_MIB_DUPDATA),
SNMP_MIB_ITEM("AddAddr", MPTCP_MIB_ADDADDR),
+ SNMP_MIB_ITEM("AddAddrTx", MPTCP_MIB_ADDADDRTX),
+ SNMP_MIB_ITEM("AddAddrTxDrop", MPTCP_MIB_ADDADDRTXDROP),
SNMP_MIB_ITEM("EchoAdd", MPTCP_MIB_ECHOADD),
+ SNMP_MIB_ITEM("EchoAddTx", MPTCP_MIB_ECHOADDTX),
+ SNMP_MIB_ITEM("EchoAddTxDrop", MPTCP_MIB_ECHOADDTXDROP),
SNMP_MIB_ITEM("PortAdd", MPTCP_MIB_PORTADD),
SNMP_MIB_ITEM("AddAddrDrop", MPTCP_MIB_ADDADDRDROP),
SNMP_MIB_ITEM("MPJoinPortSynRx", MPTCP_MIB_JOINPORTSYNRX),
@@ -44,6 +48,8 @@ static const struct snmp_mib mptcp_snmp_list[] = {
SNMP_MIB_ITEM("MismatchPortAckRx", MPTCP_MIB_MISMATCHPORTACKRX),
SNMP_MIB_ITEM("RmAddr", MPTCP_MIB_RMADDR),
SNMP_MIB_ITEM("RmAddrDrop", MPTCP_MIB_RMADDRDROP),
+ SNMP_MIB_ITEM("RmAddrTx", MPTCP_MIB_RMADDRTX),
+ SNMP_MIB_ITEM("RmAddrTxDrop", MPTCP_MIB_RMADDRTXDROP),
SNMP_MIB_ITEM("RmSubflow", MPTCP_MIB_RMSUBFLOW),
SNMP_MIB_ITEM("MPPrioTx", MPTCP_MIB_MPPRIOTX),
SNMP_MIB_ITEM("MPPrioRx", MPTCP_MIB_MPPRIORX),
diff --git a/net/mptcp/mib.h b/net/mptcp/mib.h
index 2be3596374f4..cae71d947252 100644
--- a/net/mptcp/mib.h
+++ b/net/mptcp/mib.h
@@ -27,7 +27,15 @@ enum linux_mptcp_mib_field {
MPTCP_MIB_NODSSWINDOW, /* Segments not in MPTCP windows */
MPTCP_MIB_DUPDATA, /* Segments discarded due to duplicate DSS */
MPTCP_MIB_ADDADDR, /* Received ADD_ADDR with echo-flag=0 */
+ MPTCP_MIB_ADDADDRTX, /* Sent ADD_ADDR with echo-flag=0 */
+ MPTCP_MIB_ADDADDRTXDROP, /* ADD_ADDR with echo-flag=0 not send due to
+ * resource exhaustion
+ */
MPTCP_MIB_ECHOADD, /* Received ADD_ADDR with echo-flag=1 */
+ MPTCP_MIB_ECHOADDTX, /* Send ADD_ADDR with echo-flag=1 */
+ MPTCP_MIB_ECHOADDTXDROP, /* ADD_ADDR with echo-flag=1 not send due
+ * to resource exhaustion
+ */
MPTCP_MIB_PORTADD, /* Received ADD_ADDR with a port-number */
MPTCP_MIB_ADDADDRDROP, /* Dropped incoming ADD_ADDR */
MPTCP_MIB_JOINPORTSYNRX, /* Received a SYN MP_JOIN with a different port-number */
@@ -37,6 +45,8 @@ enum linux_mptcp_mib_field {
MPTCP_MIB_MISMATCHPORTACKRX, /* Received an ACK MP_JOIN with a mismatched port-number */
MPTCP_MIB_RMADDR, /* Received RM_ADDR */
MPTCP_MIB_RMADDRDROP, /* Dropped incoming RM_ADDR */
+ MPTCP_MIB_RMADDRTX, /* Sent RM_ADDR */
+ MPTCP_MIB_RMADDRTXDROP, /* RM_ADDR not sent due to resource exhaustion */
MPTCP_MIB_RMSUBFLOW, /* Remove a subflow */
MPTCP_MIB_MPPRIOTX, /* Transmit a MP_PRIO */
MPTCP_MIB_MPPRIORX, /* Received a MP_PRIO */
@@ -63,6 +73,14 @@ struct mptcp_mib {
unsigned long mibs[LINUX_MIB_MPTCP_MAX];
};
+static inline void MPTCP_ADD_STATS(struct net *net,
+ enum linux_mptcp_mib_field field,
+ int val)
+{
+ if (likely(net->mib.mptcp_statistics))
+ SNMP_ADD_STATS(net->mib.mptcp_statistics, field, val);
+}
+
static inline void MPTCP_INC_STATS(struct net *net,
enum linux_mptcp_mib_field field)
{
diff --git a/net/mptcp/options.c b/net/mptcp/options.c
index 19a01b6566f1..c254accb14de 100644
--- a/net/mptcp/options.c
+++ b/net/mptcp/options.c
@@ -687,9 +687,12 @@ static bool mptcp_established_options_add_addr(struct sock *sk, struct sk_buff *
}
opts->suboptions |= OPTION_MPTCP_ADD_ADDR;
if (!echo) {
+ MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_ADDADDRTX);
opts->ahmac = add_addr_generate_hmac(msk->local_key,
msk->remote_key,
&opts->addr);
+ } else {
+ MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_ECHOADDTX);
}
pr_debug("addr_id=%d, ahmac=%llu, echo=%d, port=%d",
opts->addr.id, opts->ahmac, echo, ntohs(opts->addr.port));
@@ -723,7 +726,7 @@ static bool mptcp_established_options_rm_addr(struct sock *sk,
for (i = 0; i < opts->rm_list.nr; i++)
pr_debug("rm_list_ids[%d]=%d", i, opts->rm_list.ids[i]);
-
+ MPTCP_ADD_STATS(sock_net(sk), MPTCP_MIB_RMADDRTX, opts->rm_list.nr);
return true;
}
@@ -1023,6 +1026,12 @@ u64 __mptcp_expand_seq(u64 old_seq, u64 cur_seq)
return cur_seq;
}
+static void __mptcp_snd_una_update(struct mptcp_sock *msk, u64 new_snd_una)
+{
+ msk->bytes_acked += new_snd_una - msk->snd_una;
+ msk->snd_una = new_snd_una;
+}
+
static void ack_update_msk(struct mptcp_sock *msk,
struct sock *ssk,
struct mptcp_options_received *mp_opt)
@@ -1054,7 +1063,7 @@ static void ack_update_msk(struct mptcp_sock *msk,
__mptcp_check_push(sk, ssk);
if (after64(new_snd_una, old_snd_una)) {
- msk->snd_una = new_snd_una;
+ __mptcp_snd_una_update(msk, new_snd_una);
__mptcp_data_acked(sk);
}
mptcp_data_unlock(sk);
@@ -1116,6 +1125,12 @@ bool mptcp_incoming_options(struct sock *sk, struct sk_buff *skb)
mptcp_data_lock(subflow->conn);
if (sk_stream_memory_free(sk))
__mptcp_check_push(subflow->conn, sk);
+
+ /* on fallback we just need to ignore the msk-level snd_una, as
+ * this is really plain TCP
+ */
+ __mptcp_snd_una_update(msk, READ_ONCE(msk->snd_nxt));
+
__mptcp_data_acked(subflow->conn);
mptcp_data_unlock(subflow->conn);
return true;
diff --git a/net/mptcp/pm.c b/net/mptcp/pm.c
index 76612bca275a..7dbbad1e4f55 100644
--- a/net/mptcp/pm.c
+++ b/net/mptcp/pm.c
@@ -26,7 +26,8 @@ int mptcp_pm_announce_addr(struct mptcp_sock *msk,
if (add_addr &
(echo ? BIT(MPTCP_ADD_ADDR_ECHO) : BIT(MPTCP_ADD_ADDR_SIGNAL))) {
- pr_warn("addr_signal error, add_addr=%d, echo=%d", add_addr, echo);
+ MPTCP_INC_STATS(sock_net((struct sock *)msk),
+ echo ? MPTCP_MIB_ECHOADDTXDROP : MPTCP_MIB_ADDADDRTXDROP);
return -EINVAL;
}
@@ -48,7 +49,8 @@ int mptcp_pm_remove_addr(struct mptcp_sock *msk, const struct mptcp_rm_list *rm_
pr_debug("msk=%p, rm_list_nr=%d", msk, rm_list->nr);
if (rm_addr) {
- pr_warn("addr_signal error, rm_addr=%d", rm_addr);
+ MPTCP_ADD_STATS(sock_net((struct sock *)msk),
+ MPTCP_MIB_RMADDRTXDROP, rm_list->nr);
return -EINVAL;
}
@@ -413,7 +415,46 @@ out_unlock:
int mptcp_pm_get_local_id(struct mptcp_sock *msk, struct sock_common *skc)
{
- return mptcp_pm_nl_get_local_id(msk, skc);
+ struct mptcp_addr_info skc_local;
+ struct mptcp_addr_info msk_local;
+
+ if (WARN_ON_ONCE(!msk))
+ return -1;
+
+ /* The 0 ID mapping is defined by the first subflow, copied into the msk
+ * addr
+ */
+ mptcp_local_address((struct sock_common *)msk, &msk_local);
+ mptcp_local_address((struct sock_common *)skc, &skc_local);
+ if (mptcp_addresses_equal(&msk_local, &skc_local, false))
+ return 0;
+
+ if (mptcp_pm_is_userspace(msk))
+ return mptcp_userspace_pm_get_local_id(msk, &skc_local);
+ return mptcp_pm_nl_get_local_id(msk, &skc_local);
+}
+
+int mptcp_pm_get_flags_and_ifindex_by_id(struct mptcp_sock *msk, unsigned int id,
+ u8 *flags, int *ifindex)
+{
+ *flags = 0;
+ *ifindex = 0;
+
+ if (!id)
+ return 0;
+
+ if (mptcp_pm_is_userspace(msk))
+ return mptcp_userspace_pm_get_flags_and_ifindex_by_id(msk, id, flags, ifindex);
+ return mptcp_pm_nl_get_flags_and_ifindex_by_id(msk, id, flags, ifindex);
+}
+
+int mptcp_pm_set_flags(struct net *net, struct nlattr *token,
+ struct mptcp_pm_addr_entry *loc,
+ struct mptcp_pm_addr_entry *rem, u8 bkup)
+{
+ if (token)
+ return mptcp_userspace_pm_set_flags(net, token, loc, rem, bkup);
+ return mptcp_pm_nl_set_flags(net, loc, bkup);
}
void mptcp_pm_subflow_chk_stale(const struct mptcp_sock *msk, struct sock *ssk)
diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c
index 1224dfca5bf3..5692daf57a4d 100644
--- a/net/mptcp/pm_netlink.c
+++ b/net/mptcp/pm_netlink.c
@@ -25,9 +25,9 @@ static int pm_nl_pernet_id;
struct mptcp_pm_add_entry {
struct list_head list;
struct mptcp_addr_info addr;
+ u8 retrans_times;
struct timer_list add_timer;
struct mptcp_sock *sock;
- u8 retrans_times;
};
struct pm_nl_pernet {
@@ -86,8 +86,7 @@ bool mptcp_addresses_equal(const struct mptcp_addr_info *a,
return a->port == b->port;
}
-static void local_address(const struct sock_common *skc,
- struct mptcp_addr_info *addr)
+void mptcp_local_address(const struct sock_common *skc, struct mptcp_addr_info *addr)
{
addr->family = skc->skc_family;
addr->port = htons(skc->skc_num);
@@ -122,7 +121,7 @@ static bool lookup_subflow_by_saddr(const struct list_head *list,
list_for_each_entry(subflow, list, node) {
skc = (struct sock_common *)mptcp_subflow_tcp_sock(subflow);
- local_address(skc, &cur);
+ mptcp_local_address(skc, &cur);
if (mptcp_addresses_equal(&cur, saddr, saddr->port))
return true;
}
@@ -263,7 +262,7 @@ bool mptcp_pm_sport_in_anno_list(struct mptcp_sock *msk, const struct sock *sk)
struct mptcp_addr_info saddr;
bool ret = false;
- local_address((struct sock_common *)sk, &saddr);
+ mptcp_local_address((struct sock_common *)sk, &saddr);
spin_lock_bh(&msk->pm.lock);
list_for_each_entry(entry, &msk->pm.anno_list, list) {
@@ -342,7 +341,7 @@ mptcp_pm_del_add_timer(struct mptcp_sock *msk,
}
bool mptcp_pm_alloc_anno_list(struct mptcp_sock *msk,
- const struct mptcp_pm_addr_entry *entry)
+ const struct mptcp_addr_info *addr)
{
struct mptcp_pm_add_entry *add_entry = NULL;
struct sock *sk = (struct sock *)msk;
@@ -350,7 +349,7 @@ bool mptcp_pm_alloc_anno_list(struct mptcp_sock *msk,
lockdep_assert_held(&msk->pm.lock);
- add_entry = mptcp_lookup_anno_list_by_saddr(msk, &entry->addr);
+ add_entry = mptcp_lookup_anno_list_by_saddr(msk, addr);
if (add_entry) {
if (mptcp_pm_is_kernel(msk))
@@ -367,7 +366,7 @@ bool mptcp_pm_alloc_anno_list(struct mptcp_sock *msk,
list_add(&add_entry->list, &msk->pm.anno_list);
- add_entry->addr = entry->addr;
+ add_entry->addr = *addr;
add_entry->sock = msk;
add_entry->retrans_times = 0;
@@ -541,7 +540,7 @@ static void mptcp_pm_create_subflow_or_signal_addr(struct mptcp_sock *msk)
struct mptcp_addr_info mpc_addr;
bool backup = false;
- local_address((struct sock_common *)msk->first, &mpc_addr);
+ mptcp_local_address((struct sock_common *)msk->first, &mpc_addr);
rcu_read_lock();
entry = __lookup_addr(pernet, &mpc_addr, false);
if (entry) {
@@ -577,7 +576,7 @@ static void mptcp_pm_create_subflow_or_signal_addr(struct mptcp_sock *msk)
return;
if (local) {
- if (mptcp_pm_alloc_anno_list(msk, local)) {
+ if (mptcp_pm_alloc_anno_list(msk, &local->addr)) {
__clear_bit(local->addr.id, msk->pm.id_avail_bitmap);
msk->pm.add_addr_signaled++;
mptcp_pm_announce_addr(msk, &local->addr, false);
@@ -752,7 +751,7 @@ int mptcp_pm_nl_mp_prio_send_ack(struct mptcp_sock *msk,
struct sock *ssk = mptcp_subflow_tcp_sock(subflow);
struct mptcp_addr_info local, remote;
- local_address((struct sock_common *)ssk, &local);
+ mptcp_local_address((struct sock_common *)ssk, &local);
if (!mptcp_addresses_equal(&local, addr, addr->port))
continue;
@@ -1057,33 +1056,17 @@ static int mptcp_pm_nl_create_listen_socket(struct sock *sk,
return 0;
}
-int mptcp_pm_nl_get_local_id(struct mptcp_sock *msk, struct sock_common *skc)
+int mptcp_pm_nl_get_local_id(struct mptcp_sock *msk, struct mptcp_addr_info *skc)
{
struct mptcp_pm_addr_entry *entry;
- struct mptcp_addr_info skc_local;
- struct mptcp_addr_info msk_local;
struct pm_nl_pernet *pernet;
int ret = -1;
- if (WARN_ON_ONCE(!msk))
- return -1;
-
- /* The 0 ID mapping is defined by the first subflow, copied into the msk
- * addr
- */
- local_address((struct sock_common *)msk, &msk_local);
- local_address((struct sock_common *)skc, &skc_local);
- if (mptcp_addresses_equal(&msk_local, &skc_local, false))
- return 0;
-
- if (mptcp_pm_is_userspace(msk))
- return mptcp_userspace_pm_get_local_id(msk, &skc_local);
-
pernet = pm_nl_get_pernet_from_msk(msk);
rcu_read_lock();
list_for_each_entry_rcu(entry, &pernet->local_addr_list, list) {
- if (mptcp_addresses_equal(&entry->addr, &skc_local, entry->addr.port)) {
+ if (mptcp_addresses_equal(&entry->addr, skc, entry->addr.port)) {
ret = entry->addr.id;
break;
}
@@ -1097,7 +1080,7 @@ int mptcp_pm_nl_get_local_id(struct mptcp_sock *msk, struct sock_common *skc)
if (!entry)
return -ENOMEM;
- entry->addr = skc_local;
+ entry->addr = *skc;
entry->addr.id = 0;
entry->addr.port = 0;
entry->ifindex = 0;
@@ -1374,31 +1357,20 @@ out_free:
return ret;
}
-int mptcp_pm_get_flags_and_ifindex_by_id(struct mptcp_sock *msk, unsigned int id,
- u8 *flags, int *ifindex)
+int mptcp_pm_nl_get_flags_and_ifindex_by_id(struct mptcp_sock *msk, unsigned int id,
+ u8 *flags, int *ifindex)
{
struct mptcp_pm_addr_entry *entry;
struct sock *sk = (struct sock *)msk;
struct net *net = sock_net(sk);
- *flags = 0;
- *ifindex = 0;
-
- if (id) {
- if (mptcp_pm_is_userspace(msk))
- return mptcp_userspace_pm_get_flags_and_ifindex_by_id(msk,
- id,
- flags,
- ifindex);
-
- rcu_read_lock();
- entry = __lookup_addr_by_id(pm_nl_get_pernet(net), id);
- if (entry) {
- *flags = entry->flags;
- *ifindex = entry->ifindex;
- }
- rcu_read_unlock();
+ rcu_read_lock();
+ entry = __lookup_addr_by_id(pm_nl_get_pernet(net), id);
+ if (entry) {
+ *flags = entry->flags;
+ *ifindex = entry->ifindex;
}
+ rcu_read_unlock();
return 0;
}
@@ -1492,7 +1464,7 @@ static int mptcp_nl_remove_id_zero_address(struct net *net,
if (list_empty(&msk->conn_list) || mptcp_pm_is_userspace(msk))
goto next;
- local_address((struct sock_common *)msk, &msk_local);
+ mptcp_local_address((struct sock_common *)msk, &msk_local);
if (!mptcp_addresses_equal(&msk_local, addr, addr->port))
goto next;
@@ -1911,18 +1883,50 @@ next:
return ret;
}
+int mptcp_pm_nl_set_flags(struct net *net, struct mptcp_pm_addr_entry *addr, u8 bkup)
+{
+ struct pm_nl_pernet *pernet = pm_nl_get_pernet(net);
+ u8 changed, mask = MPTCP_PM_ADDR_FLAG_BACKUP |
+ MPTCP_PM_ADDR_FLAG_FULLMESH;
+ struct mptcp_pm_addr_entry *entry;
+ u8 lookup_by_id = 0;
+
+ if (addr->addr.family == AF_UNSPEC) {
+ lookup_by_id = 1;
+ if (!addr->addr.id)
+ return -EOPNOTSUPP;
+ }
+
+ spin_lock_bh(&pernet->lock);
+ entry = __lookup_addr(pernet, &addr->addr, lookup_by_id);
+ if (!entry) {
+ spin_unlock_bh(&pernet->lock);
+ return -EINVAL;
+ }
+ if ((addr->flags & MPTCP_PM_ADDR_FLAG_FULLMESH) &&
+ (entry->flags & MPTCP_PM_ADDR_FLAG_SIGNAL)) {
+ spin_unlock_bh(&pernet->lock);
+ return -EINVAL;
+ }
+
+ changed = (addr->flags ^ entry->flags) & mask;
+ entry->flags = (entry->flags & ~mask) | (addr->flags & mask);
+ *addr = *entry;
+ spin_unlock_bh(&pernet->lock);
+
+ mptcp_nl_set_flags(net, &addr->addr, bkup, changed);
+ return 0;
+}
+
static int mptcp_nl_cmd_set_flags(struct sk_buff *skb, struct genl_info *info)
{
- struct mptcp_pm_addr_entry addr = { .addr = { .family = AF_UNSPEC }, }, *entry;
struct mptcp_pm_addr_entry remote = { .addr = { .family = AF_UNSPEC }, };
+ struct mptcp_pm_addr_entry addr = { .addr = { .family = AF_UNSPEC }, };
struct nlattr *attr_rem = info->attrs[MPTCP_PM_ATTR_ADDR_REMOTE];
struct nlattr *token = info->attrs[MPTCP_PM_ATTR_TOKEN];
struct nlattr *attr = info->attrs[MPTCP_PM_ATTR_ADDR];
- struct pm_nl_pernet *pernet = genl_info_pm_nl(info);
- u8 changed, mask = MPTCP_PM_ADDR_FLAG_BACKUP |
- MPTCP_PM_ADDR_FLAG_FULLMESH;
struct net *net = sock_net(skb->sk);
- u8 bkup = 0, lookup_by_id = 0;
+ u8 bkup = 0;
int ret;
ret = mptcp_pm_parse_entry(attr, info, false, &addr);
@@ -1937,34 +1941,8 @@ static int mptcp_nl_cmd_set_flags(struct sk_buff *skb, struct genl_info *info)
if (addr.flags & MPTCP_PM_ADDR_FLAG_BACKUP)
bkup = 1;
- if (addr.addr.family == AF_UNSPEC) {
- lookup_by_id = 1;
- if (!addr.addr.id)
- return -EOPNOTSUPP;
- }
-
- if (token)
- return mptcp_userspace_pm_set_flags(net, token, &addr, &remote, bkup);
- spin_lock_bh(&pernet->lock);
- entry = __lookup_addr(pernet, &addr.addr, lookup_by_id);
- if (!entry) {
- spin_unlock_bh(&pernet->lock);
- return -EINVAL;
- }
- if ((addr.flags & MPTCP_PM_ADDR_FLAG_FULLMESH) &&
- (entry->flags & MPTCP_PM_ADDR_FLAG_SIGNAL)) {
- spin_unlock_bh(&pernet->lock);
- return -EINVAL;
- }
-
- changed = (addr.flags ^ entry->flags) & mask;
- entry->flags = (entry->flags & ~mask) | (addr.flags & mask);
- addr = *entry;
- spin_unlock_bh(&pernet->lock);
-
- mptcp_nl_set_flags(net, &addr.addr, bkup, changed);
- return 0;
+ return mptcp_pm_set_flags(net, token, &addr, &remote, bkup);
}
static void mptcp_nl_mcast_send(struct net *net, struct sk_buff *nlskb, gfp_t gfp)
diff --git a/net/mptcp/pm_userspace.c b/net/mptcp/pm_userspace.c
index b06aa58dfcf2..b5a8aa4c1ebd 100644
--- a/net/mptcp/pm_userspace.c
+++ b/net/mptcp/pm_userspace.c
@@ -111,9 +111,6 @@ int mptcp_userspace_pm_get_flags_and_ifindex_by_id(struct mptcp_sock *msk,
{
struct mptcp_pm_addr_entry *entry, *match = NULL;
- *flags = 0;
- *ifindex = 0;
-
spin_lock_bh(&msk->pm.lock);
list_for_each_entry(entry, &msk->pm.userspace_pm_local_addr_list, list) {
if (id == entry->addr.id) {
@@ -196,7 +193,7 @@ int mptcp_nl_cmd_announce(struct sk_buff *skb, struct genl_info *info)
lock_sock((struct sock *)msk);
spin_lock_bh(&msk->pm.lock);
- if (mptcp_pm_alloc_anno_list(msk, &addr_val)) {
+ if (mptcp_pm_alloc_anno_list(msk, &addr_val.addr)) {
msk->pm.add_addr_signaled++;
mptcp_pm_announce_addr(msk, &addr_val.addr, false);
mptcp_pm_nl_addr_send_ack(msk);
diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index a6c7f2d24909..e892673deb73 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -96,6 +96,7 @@ static int __mptcp_socket_create(struct mptcp_sock *msk)
list_add(&subflow->node, &msk->conn_list);
sock_hold(ssock->sk);
subflow->request_mptcp = 1;
+ subflow->subflow_id = msk->subflow_id++;
/* This is the first subflow, always with id 0 */
subflow->local_id_valid = 1;
@@ -377,6 +378,7 @@ static bool __mptcp_move_skb(struct mptcp_sock *msk, struct sock *ssk,
if (MPTCP_SKB_CB(skb)->map_seq == msk->ack_seq) {
/* in sequence */
+ msk->bytes_received += copy_len;
WRITE_ONCE(msk->ack_seq, msk->ack_seq + copy_len);
tail = skb_peek_tail(&sk->sk_receive_queue);
if (tail && mptcp_try_coalesce(sk, tail, skb))
@@ -757,6 +759,7 @@ static bool __mptcp_ofo_queue(struct mptcp_sock *msk)
MPTCP_SKB_CB(skb)->map_seq += delta;
__skb_queue_tail(&sk->sk_receive_queue, skb);
}
+ msk->bytes_received += end_seq - msk->ack_seq;
msk->ack_seq = end_seq;
moved = true;
}
@@ -842,6 +845,7 @@ static bool __mptcp_finish_join(struct mptcp_sock *msk, struct sock *ssk)
if (sk->sk_socket && !ssk->sk_socket)
mptcp_sock_graft(ssk, sk->sk_socket);
+ mptcp_subflow_ctx(ssk)->subflow_id = msk->subflow_id++;
mptcp_sockopt_sync_locked(msk, ssk);
mptcp_subflow_joined(msk, ssk);
return true;
@@ -958,12 +962,6 @@ static void __mptcp_clean_una(struct sock *sk)
struct mptcp_data_frag *dtmp, *dfrag;
u64 snd_una;
- /* on fallback we just need to ignore snd_una, as this is really
- * plain TCP
- */
- if (__mptcp_check_fallback(msk))
- msk->snd_una = READ_ONCE(msk->snd_nxt);
-
snd_una = msk->snd_una;
list_for_each_entry_safe(dfrag, dtmp, &msk->rtx_queue, list) {
if (after64(dfrag->data_seq + dfrag->data_len, snd_una))
@@ -1491,8 +1489,10 @@ static void mptcp_update_post_push(struct mptcp_sock *msk,
* that has been handed to the subflow for transmission
* and skip update in case it was old dfrag.
*/
- if (likely(after64(snd_nxt_new, msk->snd_nxt)))
+ if (likely(after64(snd_nxt_new, msk->snd_nxt))) {
+ msk->bytes_sent += snd_nxt_new - msk->snd_nxt;
msk->snd_nxt = snd_nxt_new;
+ }
}
void mptcp_check_and_set_pending(struct sock *sk)
@@ -2549,6 +2549,7 @@ static void __mptcp_retrans(struct sock *sk)
}
if (copied) {
dfrag->already_sent = max(dfrag->already_sent, info.sent);
+ msk->bytes_retrans += copied;
tcp_push(ssk, 0, info.mss_now, tcp_sk(ssk)->nonagle,
info.size_goal);
WRITE_ONCE(msk->allow_infinite_fallback, false);
@@ -2607,6 +2608,7 @@ static void mptcp_do_fastclose(struct sock *sk)
struct mptcp_subflow_context *subflow, *tmp;
struct mptcp_sock *msk = mptcp_sk(sk);
+ inet_sk_state_store(sk, TCP_CLOSE);
mptcp_for_each_subflow_safe(msk, subflow, tmp)
__mptcp_close_ssk(sk, mptcp_subflow_tcp_sock(subflow),
subflow, MPTCP_CF_FASTCLOSE);
@@ -2640,10 +2642,9 @@ static void mptcp_worker(struct work_struct *work)
* even if it is orphaned and in FIN_WAIT2 state
*/
if (sock_flag(sk, SOCK_DEAD)) {
- if (mptcp_should_close(sk)) {
- inet_sk_state_store(sk, TCP_CLOSE);
+ if (mptcp_should_close(sk))
mptcp_do_fastclose(sk);
- }
+
if (sk->sk_state == TCP_CLOSE) {
__mptcp_destroy_sock(sk);
goto unlock;
@@ -2682,6 +2683,7 @@ static int __mptcp_init_sock(struct sock *sk)
WRITE_ONCE(msk->csum_enabled, mptcp_is_checksum_enabled(sock_net(sk)));
WRITE_ONCE(msk->allow_infinite_fallback, true);
msk->recovery = false;
+ msk->subflow_id = 1;
mptcp_pm_data_init(msk);
@@ -2878,7 +2880,6 @@ static void __mptcp_destroy_sock(struct sock *sk)
void __mptcp_unaccepted_force_close(struct sock *sk)
{
sock_set_flag(sk, SOCK_DEAD);
- inet_sk_state_store(sk, TCP_CLOSE);
mptcp_do_fastclose(sk);
__mptcp_destroy_sock(sk);
}
@@ -2934,7 +2935,6 @@ bool __mptcp_close(struct sock *sk, long timeout)
/* If the msk has read data, or the caller explicitly ask it,
* do the MPTCP equivalent of TCP reset, aka MPTCP fastclose
*/
- inet_sk_state_store(sk, TCP_CLOSE);
mptcp_do_fastclose(sk);
timeout = 0;
} else if (mptcp_close_state(sk)) {
@@ -3069,6 +3069,10 @@ static int mptcp_disconnect(struct sock *sk, int flags)
WRITE_ONCE(msk->csum_enabled, mptcp_is_checksum_enabled(sock_net(sk)));
mptcp_pm_data_reset(msk);
mptcp_ca_reset(sk);
+ msk->bytes_acked = 0;
+ msk->bytes_received = 0;
+ msk->bytes_sent = 0;
+ msk->bytes_retrans = 0;
WRITE_ONCE(sk->sk_shutdown, 0);
sk_error_report(sk);
@@ -3119,6 +3123,9 @@ struct sock *mptcp_sk_clone_init(const struct sock *sk,
msk->wnd_end = msk->snd_nxt + req->rsk_rcv_wnd;
msk->setsockopt_seq = mptcp_sk(sk)->setsockopt_seq;
+ /* passive msk is created after the first/MPC subflow */
+ msk->subflow_id = 2;
+
sock_reset_flag(nsk, SOCK_RCU_FREE);
security_inet_csk_clone(nsk, req);
@@ -3538,11 +3545,10 @@ static int mptcp_ioctl_outq(const struct mptcp_sock *msk, u64 v)
return (int)delta;
}
-static int mptcp_ioctl(struct sock *sk, int cmd, unsigned long arg)
+static int mptcp_ioctl(struct sock *sk, int cmd, int *karg)
{
struct mptcp_sock *msk = mptcp_sk(sk);
bool slow;
- int answ;
switch (cmd) {
case SIOCINQ:
@@ -3551,24 +3557,24 @@ static int mptcp_ioctl(struct sock *sk, int cmd, unsigned long arg)
lock_sock(sk);
__mptcp_move_skbs(msk);
- answ = mptcp_inq_hint(sk);
+ *karg = mptcp_inq_hint(sk);
release_sock(sk);
break;
case SIOCOUTQ:
slow = lock_sock_fast(sk);
- answ = mptcp_ioctl_outq(msk, READ_ONCE(msk->snd_una));
+ *karg = mptcp_ioctl_outq(msk, READ_ONCE(msk->snd_una));
unlock_sock_fast(sk, slow);
break;
case SIOCOUTQNSD:
slow = lock_sock_fast(sk);
- answ = mptcp_ioctl_outq(msk, msk->snd_nxt);
+ *karg = mptcp_ioctl_outq(msk, msk->snd_nxt);
unlock_sock_fast(sk, slow);
break;
default:
return -ENOIOCTLCMD;
}
- return put_user(answ, (int __user *)arg);
+ return 0;
}
static void mptcp_subflow_early_fallback(struct mptcp_sock *msk,
@@ -3726,6 +3732,7 @@ static int mptcp_stream_accept(struct socket *sock, struct socket *newsock,
{
struct mptcp_sock *msk = mptcp_sk(sock->sk);
struct socket *ssock;
+ struct sock *newsk;
int err;
pr_debug("msk=%p", msk);
@@ -3737,17 +3744,20 @@ static int mptcp_stream_accept(struct socket *sock, struct socket *newsock,
if (!ssock)
return -EINVAL;
- err = ssock->ops->accept(sock, newsock, flags, kern);
- if (err == 0 && !mptcp_is_tcpsk(newsock->sk)) {
- struct mptcp_sock *msk = mptcp_sk(newsock->sk);
+ newsk = mptcp_accept(sock->sk, flags, &err, kern);
+ if (!newsk)
+ return err;
+
+ lock_sock(newsk);
+
+ __inet_accept(sock, newsock, newsk);
+ if (!mptcp_is_tcpsk(newsock->sk)) {
+ struct mptcp_sock *msk = mptcp_sk(newsk);
struct mptcp_subflow_context *subflow;
- struct sock *newsk = newsock->sk;
set_bit(SOCK_CUSTOM_SOCKOPT, &newsock->flags);
msk->in_accept_queue = 0;
- lock_sock(newsk);
-
/* set ssk->sk_socket of accept()ed flows to mptcp socket.
* This is needed so NOSPACE flag can be set from tcp stack.
*/
@@ -3768,11 +3778,10 @@ static int mptcp_stream_accept(struct socket *sock, struct socket *newsock,
if (unlikely(list_empty(&msk->conn_list)))
inet_sk_state_store(newsk, TCP_CLOSE);
}
-
- release_sock(newsk);
}
+ release_sock(newsk);
- return err;
+ return 0;
}
static __poll_t mptcp_check_writeable(struct mptcp_sock *msk)
@@ -3857,7 +3866,6 @@ static const struct proto_ops mptcp_stream_ops = {
.sendmsg = inet_sendmsg,
.recvmsg = inet_recvmsg,
.mmap = sock_no_mmap,
- .sendpage = inet_sendpage,
};
static struct inet_protosw mptcp_protosw = {
@@ -3952,7 +3960,6 @@ static const struct proto_ops mptcp_v6_stream_ops = {
.sendmsg = inet6_sendmsg,
.recvmsg = inet6_recvmsg,
.mmap = sock_no_mmap,
- .sendpage = inet_sendpage,
#ifdef CONFIG_COMPAT
.compat_ioctl = inet6_compat_ioctl,
#endif
diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h
index d3783a7056e1..37fbe22e2433 100644
--- a/net/mptcp/protocol.h
+++ b/net/mptcp/protocol.h
@@ -261,10 +261,13 @@ struct mptcp_sock {
u64 local_key;
u64 remote_key;
u64 write_seq;
+ u64 bytes_sent;
u64 snd_nxt;
+ u64 bytes_received;
u64 ack_seq;
atomic64_t rcv_wnd_sent;
u64 rcv_data_fin_seq;
+ u64 bytes_retrans;
int rmem_fwd_alloc;
struct sock *last_snd;
int snd_burst;
@@ -273,6 +276,7 @@ struct mptcp_sock {
* recovery related fields are under data_lock
* protection
*/
+ u64 bytes_acked;
u64 snd_una;
u64 wnd_end;
unsigned long timer_ival;
@@ -318,7 +322,8 @@ struct mptcp_sock {
u64 rtt_us; /* last maximum rtt of subflows */
} rcvq_space;
- u32 setsockopt_seq;
+ u32 subflow_id;
+ u32 setsockopt_seq;
char ca_name[TCP_CA_NAME_MAX];
struct mptcp_sock *dl_next;
};
@@ -498,6 +503,8 @@ struct mptcp_subflow_context {
u8 reset_reason:4;
u8 stale_count;
+ u32 subflow_id;
+
long delegated_status;
unsigned long fail_tout;
@@ -636,6 +643,7 @@ void mptcp_set_owner_r(struct sk_buff *skb, struct sock *sk);
bool mptcp_addresses_equal(const struct mptcp_addr_info *a,
const struct mptcp_addr_info *b, bool use_port);
+void mptcp_local_address(const struct sock_common *skc, struct mptcp_addr_info *addr);
/* called with sk socket lock held */
int __mptcp_subflow_connect(struct sock *sk, const struct mptcp_addr_info *loc,
@@ -806,7 +814,7 @@ int mptcp_pm_nl_mp_prio_send_ack(struct mptcp_sock *msk,
struct mptcp_addr_info *rem,
u8 bkup);
bool mptcp_pm_alloc_anno_list(struct mptcp_sock *msk,
- const struct mptcp_pm_addr_entry *entry);
+ const struct mptcp_addr_info *addr);
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 *
@@ -818,9 +826,15 @@ mptcp_lookup_anno_list_by_saddr(const struct mptcp_sock *msk,
int mptcp_pm_get_flags_and_ifindex_by_id(struct mptcp_sock *msk,
unsigned int id,
u8 *flags, int *ifindex);
+int mptcp_pm_nl_get_flags_and_ifindex_by_id(struct mptcp_sock *msk, unsigned int id,
+ u8 *flags, int *ifindex);
int mptcp_userspace_pm_get_flags_and_ifindex_by_id(struct mptcp_sock *msk,
unsigned int id,
u8 *flags, int *ifindex);
+int mptcp_pm_set_flags(struct net *net, struct nlattr *token,
+ struct mptcp_pm_addr_entry *loc,
+ struct mptcp_pm_addr_entry *rem, u8 bkup);
+int mptcp_pm_nl_set_flags(struct net *net, struct mptcp_pm_addr_entry *addr, u8 bkup);
int mptcp_userspace_pm_set_flags(struct net *net, struct nlattr *token,
struct mptcp_pm_addr_entry *loc,
struct mptcp_pm_addr_entry *rem, u8 bkup);
@@ -913,13 +927,13 @@ bool mptcp_pm_add_addr_signal(struct mptcp_sock *msk, const struct sk_buff *skb,
bool mptcp_pm_rm_addr_signal(struct mptcp_sock *msk, unsigned int remaining,
struct mptcp_rm_list *rm_list);
int mptcp_pm_get_local_id(struct mptcp_sock *msk, struct sock_common *skc);
+int mptcp_pm_nl_get_local_id(struct mptcp_sock *msk, struct mptcp_addr_info *skc);
int mptcp_userspace_pm_get_local_id(struct mptcp_sock *msk, struct mptcp_addr_info *skc);
void __init mptcp_pm_nl_init(void);
void mptcp_pm_nl_work(struct mptcp_sock *msk);
void mptcp_pm_nl_rm_subflow_received(struct mptcp_sock *msk,
const struct mptcp_rm_list *rm_list);
-int mptcp_pm_nl_get_local_id(struct mptcp_sock *msk, struct sock_common *skc);
unsigned int mptcp_pm_get_add_addr_signal_max(const struct mptcp_sock *msk);
unsigned int mptcp_pm_get_add_addr_accept_max(const struct mptcp_sock *msk);
unsigned int mptcp_pm_get_subflows_max(const struct mptcp_sock *msk);
diff --git a/net/mptcp/sockopt.c b/net/mptcp/sockopt.c
index d4258869ac48..63f7a09335c5 100644
--- a/net/mptcp/sockopt.c
+++ b/net/mptcp/sockopt.c
@@ -14,7 +14,8 @@
#include <net/mptcp.h>
#include "protocol.h"
-#define MIN_INFO_OPTLEN_SIZE 16
+#define MIN_INFO_OPTLEN_SIZE 16
+#define MIN_FULL_INFO_OPTLEN_SIZE 40
static struct sock *__mptcp_tcp_fallback(struct mptcp_sock *msk)
{
@@ -355,6 +356,7 @@ static int mptcp_setsockopt_sol_socket(struct mptcp_sock *msk, int optname,
case SO_BROADCAST:
case SO_BSDCOMPAT:
case SO_PASSCRED:
+ case SO_PASSPIDFD:
case SO_PASSSEC:
case SO_RXQ_OVFL:
case SO_WIFI_STATUS:
@@ -888,7 +890,9 @@ out:
void mptcp_diag_fill_info(struct mptcp_sock *msk, struct mptcp_info *info)
{
+ struct sock *sk = (struct sock *)msk;
u32 flags = 0;
+ bool slow;
memset(info, 0, sizeof(*info));
@@ -897,6 +901,9 @@ void mptcp_diag_fill_info(struct mptcp_sock *msk, struct mptcp_info *info)
info->mptcpi_add_addr_accepted = READ_ONCE(msk->pm.add_addr_accepted);
info->mptcpi_local_addr_used = READ_ONCE(msk->pm.local_addr_used);
+ if (inet_sk_state_load(sk) == TCP_LISTEN)
+ return;
+
/* The following limits only make sense for the in-kernel PM */
if (mptcp_pm_is_kernel(msk)) {
info->mptcpi_subflows_max =
@@ -914,11 +921,21 @@ void mptcp_diag_fill_info(struct mptcp_sock *msk, struct mptcp_info *info)
if (READ_ONCE(msk->can_ack))
flags |= MPTCP_INFO_FLAG_REMOTE_KEY_RECEIVED;
info->mptcpi_flags = flags;
- info->mptcpi_token = READ_ONCE(msk->token);
- info->mptcpi_write_seq = READ_ONCE(msk->write_seq);
- info->mptcpi_snd_una = READ_ONCE(msk->snd_una);
- info->mptcpi_rcv_nxt = READ_ONCE(msk->ack_seq);
- info->mptcpi_csum_enabled = READ_ONCE(msk->csum_enabled);
+ mptcp_data_lock(sk);
+ info->mptcpi_snd_una = msk->snd_una;
+ info->mptcpi_rcv_nxt = msk->ack_seq;
+ info->mptcpi_bytes_acked = msk->bytes_acked;
+ mptcp_data_unlock(sk);
+
+ slow = lock_sock_fast(sk);
+ info->mptcpi_csum_enabled = msk->csum_enabled;
+ info->mptcpi_token = msk->token;
+ info->mptcpi_write_seq = msk->write_seq;
+ info->mptcpi_retransmits = inet_csk(sk)->icsk_retransmits;
+ info->mptcpi_bytes_sent = msk->bytes_sent;
+ info->mptcpi_bytes_received = msk->bytes_received;
+ info->mptcpi_bytes_retrans = msk->bytes_retrans;
+ unlock_sock_fast(sk, slow);
}
EXPORT_SYMBOL_GPL(mptcp_diag_fill_info);
@@ -965,7 +982,8 @@ static int mptcp_put_subflow_data(struct mptcp_subflow_data *sfd,
}
static int mptcp_get_subflow_data(struct mptcp_subflow_data *sfd,
- char __user *optval, int __user *optlen)
+ char __user *optval,
+ int __user *optlen)
{
int len, copylen;
@@ -1146,6 +1164,125 @@ static int mptcp_getsockopt_subflow_addrs(struct mptcp_sock *msk, char __user *o
return 0;
}
+static int mptcp_get_full_info(struct mptcp_full_info *mfi,
+ char __user *optval,
+ int __user *optlen)
+{
+ int len;
+
+ BUILD_BUG_ON(offsetof(struct mptcp_full_info, mptcp_info) !=
+ MIN_FULL_INFO_OPTLEN_SIZE);
+
+ if (get_user(len, optlen))
+ return -EFAULT;
+
+ if (len < MIN_FULL_INFO_OPTLEN_SIZE)
+ return -EINVAL;
+
+ memset(mfi, 0, sizeof(*mfi));
+ if (copy_from_user(mfi, optval, MIN_FULL_INFO_OPTLEN_SIZE))
+ return -EFAULT;
+
+ if (mfi->size_tcpinfo_kernel ||
+ mfi->size_sfinfo_kernel ||
+ mfi->num_subflows)
+ return -EINVAL;
+
+ if (mfi->size_sfinfo_user > INT_MAX ||
+ mfi->size_tcpinfo_user > INT_MAX)
+ return -EINVAL;
+
+ return len - MIN_FULL_INFO_OPTLEN_SIZE;
+}
+
+static int mptcp_put_full_info(struct mptcp_full_info *mfi,
+ char __user *optval,
+ u32 copylen,
+ int __user *optlen)
+{
+ copylen += MIN_FULL_INFO_OPTLEN_SIZE;
+ if (put_user(copylen, optlen))
+ return -EFAULT;
+
+ if (copy_to_user(optval, mfi, copylen))
+ return -EFAULT;
+ return 0;
+}
+
+static int mptcp_getsockopt_full_info(struct mptcp_sock *msk, char __user *optval,
+ int __user *optlen)
+{
+ unsigned int sfcount = 0, copylen = 0;
+ struct mptcp_subflow_context *subflow;
+ struct sock *sk = (struct sock *)msk;
+ void __user *tcpinfoptr, *sfinfoptr;
+ struct mptcp_full_info mfi;
+ int len;
+
+ len = mptcp_get_full_info(&mfi, optval, optlen);
+ if (len < 0)
+ return len;
+
+ /* don't bother filling the mptcp info if there is not enough
+ * user-space-provided storage
+ */
+ if (len > 0) {
+ mptcp_diag_fill_info(msk, &mfi.mptcp_info);
+ copylen += min_t(unsigned int, len, sizeof(struct mptcp_info));
+ }
+
+ mfi.size_tcpinfo_kernel = sizeof(struct tcp_info);
+ mfi.size_tcpinfo_user = min_t(unsigned int, mfi.size_tcpinfo_user,
+ sizeof(struct tcp_info));
+ sfinfoptr = u64_to_user_ptr(mfi.subflow_info);
+ mfi.size_sfinfo_kernel = sizeof(struct mptcp_subflow_info);
+ mfi.size_sfinfo_user = min_t(unsigned int, mfi.size_sfinfo_user,
+ sizeof(struct mptcp_subflow_info));
+ tcpinfoptr = u64_to_user_ptr(mfi.tcp_info);
+
+ lock_sock(sk);
+ mptcp_for_each_subflow(msk, subflow) {
+ struct sock *ssk = mptcp_subflow_tcp_sock(subflow);
+ struct mptcp_subflow_info sfinfo;
+ struct tcp_info tcp_info;
+
+ if (sfcount++ >= mfi.size_arrays_user)
+ continue;
+
+ /* fetch addr/tcp_info only if the user space buffers
+ * are wide enough
+ */
+ memset(&sfinfo, 0, sizeof(sfinfo));
+ sfinfo.id = subflow->subflow_id;
+ if (mfi.size_sfinfo_user >
+ offsetof(struct mptcp_subflow_info, addrs))
+ mptcp_get_sub_addrs(ssk, &sfinfo.addrs);
+ if (copy_to_user(sfinfoptr, &sfinfo, mfi.size_sfinfo_user))
+ goto fail_release;
+
+ if (mfi.size_tcpinfo_user) {
+ tcp_get_info(ssk, &tcp_info);
+ if (copy_to_user(tcpinfoptr, &tcp_info,
+ mfi.size_tcpinfo_user))
+ goto fail_release;
+ }
+
+ tcpinfoptr += mfi.size_tcpinfo_user;
+ sfinfoptr += mfi.size_sfinfo_user;
+ }
+ release_sock(sk);
+
+ mfi.num_subflows = sfcount;
+ if (mptcp_put_full_info(&mfi, optval, copylen, optlen))
+ return -EFAULT;
+
+ return 0;
+
+fail_release:
+ release_sock(sk);
+ return -EFAULT;
+}
+
static int mptcp_put_int_option(struct mptcp_sock *msk, char __user *optval,
int __user *optlen, int val)
{
@@ -1219,6 +1356,8 @@ static int mptcp_getsockopt_sol_mptcp(struct mptcp_sock *msk, int optname,
switch (optname) {
case MPTCP_INFO:
return mptcp_getsockopt_info(msk, optval, optlen);
+ case MPTCP_FULL_INFO:
+ return mptcp_getsockopt_full_info(msk, optval, optlen);
case MPTCP_TCPINFO:
return mptcp_getsockopt_tcpinfo(msk, optval, optlen);
case MPTCP_SUBFLOW_ADDRS:
diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c
index 8ff5c9fab55b..9ee3b7abbaf6 100644
--- a/net/mptcp/subflow.c
+++ b/net/mptcp/subflow.c
@@ -819,6 +819,7 @@ create_child:
if (!ctx->conn)
goto fallback;
+ ctx->subflow_id = 1;
owner = mptcp_sk(ctx->conn);
mptcp_pm_new_connection(owner, child, 1);
@@ -1574,6 +1575,7 @@ 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 = !!(flags & MPTCP_PM_ADDR_FLAG_BACKUP);
+ subflow->subflow_id = msk->subflow_id++;
mptcp_info2sockaddr(remote, &addr, ssk->sk_family);
sock_hold(ssk);
diff --git a/net/ncsi/ncsi-rsp.c b/net/ncsi/ncsi-rsp.c
index 6447a09932f5..069c2659074b 100644
--- a/net/ncsi/ncsi-rsp.c
+++ b/net/ncsi/ncsi-rsp.c
@@ -611,14 +611,14 @@ static int ncsi_rsp_handler_snfc(struct ncsi_request *nr)
return 0;
}
-/* Response handler for Mellanox command Get Mac Address */
-static int ncsi_rsp_handler_oem_mlx_gma(struct ncsi_request *nr)
+/* Response handler for Get Mac Address command */
+static int ncsi_rsp_handler_oem_gma(struct ncsi_request *nr, int mfr_id)
{
struct ncsi_dev_priv *ndp = nr->ndp;
struct net_device *ndev = ndp->ndev.dev;
- const struct net_device_ops *ops = ndev->netdev_ops;
struct ncsi_rsp_oem_pkt *rsp;
struct sockaddr saddr;
+ u32 mac_addr_off = 0;
int ret = 0;
/* Get the response header */
@@ -626,11 +626,25 @@ static int ncsi_rsp_handler_oem_mlx_gma(struct ncsi_request *nr)
saddr.sa_family = ndev->type;
ndev->priv_flags |= IFF_LIVE_ADDR_CHANGE;
- memcpy(saddr.sa_data, &rsp->data[MLX_MAC_ADDR_OFFSET], ETH_ALEN);
+ if (mfr_id == NCSI_OEM_MFR_BCM_ID)
+ mac_addr_off = BCM_MAC_ADDR_OFFSET;
+ else if (mfr_id == NCSI_OEM_MFR_MLX_ID)
+ mac_addr_off = MLX_MAC_ADDR_OFFSET;
+ else if (mfr_id == NCSI_OEM_MFR_INTEL_ID)
+ mac_addr_off = INTEL_MAC_ADDR_OFFSET;
+
+ memcpy(saddr.sa_data, &rsp->data[mac_addr_off], ETH_ALEN);
+ if (mfr_id == NCSI_OEM_MFR_BCM_ID || mfr_id == NCSI_OEM_MFR_INTEL_ID)
+ eth_addr_inc((u8 *)saddr.sa_data);
+ if (!is_valid_ether_addr((const u8 *)saddr.sa_data))
+ return -ENXIO;
+
/* Set the flag for GMA command which should only be called once */
ndp->gma_flag = 1;
- ret = ops->ndo_set_mac_address(ndev, &saddr);
+ rtnl_lock();
+ ret = dev_set_mac_address(ndev, &saddr, NULL);
+ rtnl_unlock();
if (ret < 0)
netdev_warn(ndev, "NCSI: 'Writing mac address to device failed\n");
@@ -649,41 +663,10 @@ static int ncsi_rsp_handler_oem_mlx(struct ncsi_request *nr)
if (mlx->cmd == NCSI_OEM_MLX_CMD_GMA &&
mlx->param == NCSI_OEM_MLX_CMD_GMA_PARAM)
- return ncsi_rsp_handler_oem_mlx_gma(nr);
+ return ncsi_rsp_handler_oem_gma(nr, NCSI_OEM_MFR_MLX_ID);
return 0;
}
-/* Response handler for Broadcom command Get Mac Address */
-static int ncsi_rsp_handler_oem_bcm_gma(struct ncsi_request *nr)
-{
- struct ncsi_dev_priv *ndp = nr->ndp;
- struct net_device *ndev = ndp->ndev.dev;
- const struct net_device_ops *ops = ndev->netdev_ops;
- struct ncsi_rsp_oem_pkt *rsp;
- struct sockaddr saddr;
- int ret = 0;
-
- /* Get the response header */
- rsp = (struct ncsi_rsp_oem_pkt *)skb_network_header(nr->rsp);
-
- saddr.sa_family = ndev->type;
- ndev->priv_flags |= IFF_LIVE_ADDR_CHANGE;
- memcpy(saddr.sa_data, &rsp->data[BCM_MAC_ADDR_OFFSET], ETH_ALEN);
- /* Increase mac address by 1 for BMC's address */
- eth_addr_inc((u8 *)saddr.sa_data);
- if (!is_valid_ether_addr((const u8 *)saddr.sa_data))
- return -ENXIO;
-
- /* Set the flag for GMA command which should only be called once */
- ndp->gma_flag = 1;
-
- ret = ops->ndo_set_mac_address(ndev, &saddr);
- if (ret < 0)
- netdev_warn(ndev, "NCSI: 'Writing mac address to device failed\n");
-
- return ret;
-}
-
/* Response handler for Broadcom card */
static int ncsi_rsp_handler_oem_bcm(struct ncsi_request *nr)
{
@@ -695,42 +678,10 @@ static int ncsi_rsp_handler_oem_bcm(struct ncsi_request *nr)
bcm = (struct ncsi_rsp_oem_bcm_pkt *)(rsp->data);
if (bcm->type == NCSI_OEM_BCM_CMD_GMA)
- return ncsi_rsp_handler_oem_bcm_gma(nr);
+ return ncsi_rsp_handler_oem_gma(nr, NCSI_OEM_MFR_BCM_ID);
return 0;
}
-/* Response handler for Intel command Get Mac Address */
-static int ncsi_rsp_handler_oem_intel_gma(struct ncsi_request *nr)
-{
- struct ncsi_dev_priv *ndp = nr->ndp;
- struct net_device *ndev = ndp->ndev.dev;
- const struct net_device_ops *ops = ndev->netdev_ops;
- struct ncsi_rsp_oem_pkt *rsp;
- struct sockaddr saddr;
- int ret = 0;
-
- /* Get the response header */
- rsp = (struct ncsi_rsp_oem_pkt *)skb_network_header(nr->rsp);
-
- saddr.sa_family = ndev->type;
- ndev->priv_flags |= IFF_LIVE_ADDR_CHANGE;
- memcpy(saddr.sa_data, &rsp->data[INTEL_MAC_ADDR_OFFSET], ETH_ALEN);
- /* Increase mac address by 1 for BMC's address */
- eth_addr_inc((u8 *)saddr.sa_data);
- if (!is_valid_ether_addr((const u8 *)saddr.sa_data))
- return -ENXIO;
-
- /* Set the flag for GMA command which should only be called once */
- ndp->gma_flag = 1;
-
- ret = ops->ndo_set_mac_address(ndev, &saddr);
- if (ret < 0)
- netdev_warn(ndev,
- "NCSI: 'Writing mac address to device failed\n");
-
- return ret;
-}
-
/* Response handler for Intel card */
static int ncsi_rsp_handler_oem_intel(struct ncsi_request *nr)
{
@@ -742,7 +693,7 @@ static int ncsi_rsp_handler_oem_intel(struct ncsi_request *nr)
intel = (struct ncsi_rsp_oem_intel_pkt *)(rsp->data);
if (intel->cmd == NCSI_OEM_INTEL_CMD_GMA)
- return ncsi_rsp_handler_oem_intel_gma(nr);
+ return ncsi_rsp_handler_oem_gma(nr, NCSI_OEM_MFR_INTEL_ID);
return 0;
}
diff --git a/net/netfilter/ipset/ip_set_core.c b/net/netfilter/ipset/ip_set_core.c
index 9a6b64779e64..0b68e2e2824e 100644
--- a/net/netfilter/ipset/ip_set_core.c
+++ b/net/netfilter/ipset/ip_set_core.c
@@ -739,9 +739,7 @@ ip_set_test(ip_set_id_t index, const struct sk_buff *skb,
!(opt->family == set->family || set->family == NFPROTO_UNSPEC))
return 0;
- rcu_read_lock_bh();
ret = set->variant->kadt(set, skb, par, IPSET_TEST, opt);
- rcu_read_unlock_bh();
if (ret == -EAGAIN) {
/* Type requests element to be completed */
diff --git a/net/netfilter/ipvs/Kconfig b/net/netfilter/ipvs/Kconfig
index 271da8447b29..2a3017b9c001 100644
--- a/net/netfilter/ipvs/Kconfig
+++ b/net/netfilter/ipvs/Kconfig
@@ -44,7 +44,8 @@ config IP_VS_DEBUG
config IP_VS_TAB_BITS
int "IPVS connection table size (the Nth power of 2)"
- range 8 20
+ range 8 20 if !64BIT
+ range 8 27 if 64BIT
default 12
help
The IPVS connection hash table uses the chaining scheme to handle
@@ -54,24 +55,24 @@ config IP_VS_TAB_BITS
Note the table size must be power of 2. The table size will be the
value of 2 to the your input number power. The number to choose is
- from 8 to 20, the default number is 12, which means the table size
- is 4096. Don't input the number too small, otherwise you will lose
- performance on it. You can adapt the table size yourself, according
- to your virtual server application. It is good to set the table size
- not far less than the number of connections per second multiplying
- average lasting time of connection in the table. For example, your
- virtual server gets 200 connections per second, the connection lasts
- for 200 seconds in average in the connection table, the table size
- should be not far less than 200x200, it is good to set the table
- size 32768 (2**15).
+ from 8 to 27 for 64BIT(20 otherwise), the default number is 12,
+ which means the table size is 4096. Don't input the number too
+ small, otherwise you will lose performance on it. You can adapt the
+ table size yourself, according to your virtual server application.
+ It is good to set the table size not far less than the number of
+ connections per second multiplying average lasting time of
+ connection in the table. For example, your virtual server gets 200
+ connections per second, the connection lasts for 200 seconds in
+ average in the connection table, the table size should be not far
+ less than 200x200, it is good to set the table size 32768 (2**15).
Another note that each connection occupies 128 bytes effectively and
each hash entry uses 8 bytes, so you can estimate how much memory is
needed for your box.
You can overwrite this number setting conn_tab_bits module parameter
- or by appending ip_vs.conn_tab_bits=? to the kernel command line
- if IP VS was compiled built-in.
+ or by appending ip_vs.conn_tab_bits=? to the kernel command line if
+ IP VS was compiled built-in.
comment "IPVS transport protocol load balancing support"
diff --git a/net/netfilter/ipvs/ip_vs_conn.c b/net/netfilter/ipvs/ip_vs_conn.c
index 928e64653837..9065da3cdd12 100644
--- a/net/netfilter/ipvs/ip_vs_conn.c
+++ b/net/netfilter/ipvs/ip_vs_conn.c
@@ -26,7 +26,6 @@
#include <linux/net.h>
#include <linux/kernel.h>
#include <linux/module.h>
-#include <linux/vmalloc.h>
#include <linux/proc_fs.h> /* for proc_net_* */
#include <linux/slab.h>
#include <linux/seq_file.h>
@@ -1482,13 +1481,21 @@ void __net_exit ip_vs_conn_net_cleanup(struct netns_ipvs *ipvs)
int __init ip_vs_conn_init(void)
{
size_t tab_array_size;
+ int max_avail;
+#if BITS_PER_LONG > 32
+ int max = 27;
+#else
+ int max = 20;
+#endif
+ int min = 8;
int idx;
- /* Compute size and mask */
- if (ip_vs_conn_tab_bits < 8 || ip_vs_conn_tab_bits > 20) {
- pr_info("conn_tab_bits not in [8, 20]. Using default value\n");
- ip_vs_conn_tab_bits = CONFIG_IP_VS_TAB_BITS;
- }
+ max_avail = order_base_2(totalram_pages()) + PAGE_SHIFT;
+ max_avail -= 2; /* ~4 in hash row */
+ max_avail -= 1; /* IPVS up to 1/2 of mem */
+ max_avail -= order_base_2(sizeof(struct ip_vs_conn));
+ max = clamp(max, min, max_avail);
+ ip_vs_conn_tab_bits = clamp_val(ip_vs_conn_tab_bits, min, max);
ip_vs_conn_tab_size = 1 << ip_vs_conn_tab_bits;
ip_vs_conn_tab_mask = ip_vs_conn_tab_size - 1;
@@ -1497,7 +1504,8 @@ int __init ip_vs_conn_init(void)
*/
tab_array_size = array_size(ip_vs_conn_tab_size,
sizeof(*ip_vs_conn_tab));
- ip_vs_conn_tab = vmalloc(tab_array_size);
+ ip_vs_conn_tab = kvmalloc_array(ip_vs_conn_tab_size,
+ sizeof(*ip_vs_conn_tab), GFP_KERNEL);
if (!ip_vs_conn_tab)
return -ENOMEM;
@@ -1506,7 +1514,7 @@ int __init ip_vs_conn_init(void)
sizeof(struct ip_vs_conn), 0,
SLAB_HWCACHE_ALIGN, NULL);
if (!ip_vs_conn_cachep) {
- vfree(ip_vs_conn_tab);
+ kvfree(ip_vs_conn_tab);
return -ENOMEM;
}
@@ -1534,5 +1542,5 @@ void ip_vs_conn_cleanup(void)
rcu_barrier();
/* Release the empty cache */
kmem_cache_destroy(ip_vs_conn_cachep);
- vfree(ip_vs_conn_tab);
+ kvfree(ip_vs_conn_tab);
}
diff --git a/net/netfilter/ipvs/ip_vs_xmit.c b/net/netfilter/ipvs/ip_vs_xmit.c
index a80b960223e1..9193e109e6b3 100644
--- a/net/netfilter/ipvs/ip_vs_xmit.c
+++ b/net/netfilter/ipvs/ip_vs_xmit.c
@@ -139,7 +139,7 @@ retry:
if (PTR_ERR(rt) == -EINVAL && *saddr &&
rt_mode & IP_VS_RT_MODE_CONNECT && !loop) {
*saddr = 0;
- flowi4_update_output(&fl4, 0, 0, daddr, 0);
+ flowi4_update_output(&fl4, 0, daddr, 0);
goto retry;
}
IP_VS_DBG_RL("ip_route_output error, dest: %pI4\n", &daddr);
@@ -147,7 +147,7 @@ retry:
} else if (!*saddr && rt_mode & IP_VS_RT_MODE_CONNECT && fl4.saddr) {
ip_rt_put(rt);
*saddr = fl4.saddr;
- flowi4_update_output(&fl4, 0, 0, daddr, fl4.saddr);
+ flowi4_update_output(&fl4, 0, daddr, fl4.saddr);
loop = true;
goto retry;
}
diff --git a/net/netfilter/nf_conntrack_proto_dccp.c b/net/netfilter/nf_conntrack_proto_dccp.c
index c1557d47ccd1..d4fd626d2b8c 100644
--- a/net/netfilter/nf_conntrack_proto_dccp.c
+++ b/net/netfilter/nf_conntrack_proto_dccp.c
@@ -432,9 +432,19 @@ static bool dccp_error(const struct dccp_hdr *dh,
struct sk_buff *skb, unsigned int dataoff,
const struct nf_hook_state *state)
{
+ static const unsigned long require_seq48 = 1 << DCCP_PKT_REQUEST |
+ 1 << DCCP_PKT_RESPONSE |
+ 1 << DCCP_PKT_CLOSEREQ |
+ 1 << DCCP_PKT_CLOSE |
+ 1 << DCCP_PKT_RESET |
+ 1 << DCCP_PKT_SYNC |
+ 1 << DCCP_PKT_SYNCACK;
unsigned int dccp_len = skb->len - dataoff;
unsigned int cscov;
const char *msg;
+ u8 type;
+
+ BUILD_BUG_ON(DCCP_PKT_INVALID >= BITS_PER_LONG);
if (dh->dccph_doff * 4 < sizeof(struct dccp_hdr) ||
dh->dccph_doff * 4 > dccp_len) {
@@ -459,34 +469,70 @@ static bool dccp_error(const struct dccp_hdr *dh,
goto out_invalid;
}
- if (dh->dccph_type >= DCCP_PKT_INVALID) {
+ type = dh->dccph_type;
+ if (type >= DCCP_PKT_INVALID) {
msg = "nf_ct_dccp: reserved packet type ";
goto out_invalid;
}
+
+ if (test_bit(type, &require_seq48) && !dh->dccph_x) {
+ msg = "nf_ct_dccp: type lacks 48bit sequence numbers";
+ goto out_invalid;
+ }
+
return false;
out_invalid:
nf_l4proto_log_invalid(skb, state, IPPROTO_DCCP, "%s", msg);
return true;
}
+struct nf_conntrack_dccp_buf {
+ struct dccp_hdr dh; /* generic header part */
+ struct dccp_hdr_ext ext; /* optional depending dh->dccph_x */
+ union { /* depends on header type */
+ struct dccp_hdr_ack_bits ack;
+ struct dccp_hdr_request req;
+ struct dccp_hdr_response response;
+ struct dccp_hdr_reset rst;
+ } u;
+};
+
+static struct dccp_hdr *
+dccp_header_pointer(const struct sk_buff *skb, int offset, const struct dccp_hdr *dh,
+ struct nf_conntrack_dccp_buf *buf)
+{
+ unsigned int hdrlen = __dccp_hdr_len(dh);
+
+ if (hdrlen > sizeof(*buf))
+ return NULL;
+
+ return skb_header_pointer(skb, offset, hdrlen, buf);
+}
+
int nf_conntrack_dccp_packet(struct nf_conn *ct, struct sk_buff *skb,
unsigned int dataoff,
enum ip_conntrack_info ctinfo,
const struct nf_hook_state *state)
{
enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo);
- struct dccp_hdr _dh, *dh;
+ struct nf_conntrack_dccp_buf _dh;
u_int8_t type, old_state, new_state;
enum ct_dccp_roles role;
unsigned int *timeouts;
+ struct dccp_hdr *dh;
- dh = skb_header_pointer(skb, dataoff, sizeof(_dh), &_dh);
+ dh = skb_header_pointer(skb, dataoff, sizeof(*dh), &_dh.dh);
if (!dh)
return NF_DROP;
if (dccp_error(dh, skb, dataoff, state))
return -NF_ACCEPT;
+ /* pull again, including possible 48 bit sequences and subtype header */
+ dh = dccp_header_pointer(skb, dataoff, dh, &_dh);
+ if (!dh)
+ return NF_DROP;
+
type = dh->dccph_type;
if (!nf_ct_is_confirmed(ct) && !dccp_new(ct, skb, dh, state))
return -NF_ACCEPT;
diff --git a/net/netfilter/nf_conntrack_proto_gre.c b/net/netfilter/nf_conntrack_proto_gre.c
index 728eeb0aea87..ad6f0ca40cd2 100644
--- a/net/netfilter/nf_conntrack_proto_gre.c
+++ b/net/netfilter/nf_conntrack_proto_gre.c
@@ -296,6 +296,7 @@ void nf_conntrack_gre_init_net(struct net *net)
/* protocol helper struct */
const struct nf_conntrack_l4proto nf_conntrack_l4proto_gre = {
.l4proto = IPPROTO_GRE,
+ .allow_clash = true,
#ifdef CONFIG_NF_CONNTRACK_PROCFS
.print_conntrack = gre_print_conntrack,
#endif
diff --git a/net/netfilter/nf_conntrack_sip.c b/net/netfilter/nf_conntrack_sip.c
index 77f5e82d8e3f..d0eac27f6ba0 100644
--- a/net/netfilter/nf_conntrack_sip.c
+++ b/net/netfilter/nf_conntrack_sip.c
@@ -611,7 +611,7 @@ int ct_sip_parse_numerical_param(const struct nf_conn *ct, const char *dptr,
start += strlen(name);
*val = simple_strtoul(start, &end, 0);
if (start == end)
- return 0;
+ return -1;
if (matchoff && matchlen) {
*matchoff = start - dptr;
*matchlen = end - start;
diff --git a/net/netfilter/nf_flow_table_core.c b/net/netfilter/nf_flow_table_core.c
index b0ef48b21dcb..1d34d700bd09 100644
--- a/net/netfilter/nf_flow_table_core.c
+++ b/net/netfilter/nf_flow_table_core.c
@@ -125,9 +125,6 @@ static int flow_offload_fill_route(struct flow_offload *flow,
break;
case FLOW_OFFLOAD_XMIT_XFRM:
case FLOW_OFFLOAD_XMIT_NEIGH:
- if (!dst_hold_safe(route->tuple[dir].dst))
- return -1;
-
flow_tuple->dst_cache = dst;
flow_tuple->dst_cookie = flow_offload_dst_cookie(flow_tuple);
break;
@@ -148,27 +145,12 @@ static void nft_flow_dst_release(struct flow_offload *flow,
dst_release(flow->tuplehash[dir].tuple.dst_cache);
}
-int flow_offload_route_init(struct flow_offload *flow,
+void flow_offload_route_init(struct flow_offload *flow,
const struct nf_flow_route *route)
{
- int err;
-
- err = flow_offload_fill_route(flow, route, FLOW_OFFLOAD_DIR_ORIGINAL);
- if (err < 0)
- return err;
-
- err = flow_offload_fill_route(flow, route, FLOW_OFFLOAD_DIR_REPLY);
- if (err < 0)
- goto err_route_reply;
-
+ flow_offload_fill_route(flow, route, FLOW_OFFLOAD_DIR_ORIGINAL);
+ flow_offload_fill_route(flow, route, FLOW_OFFLOAD_DIR_REPLY);
flow->type = NF_FLOW_OFFLOAD_ROUTE;
-
- return 0;
-
-err_route_reply:
- nft_flow_dst_release(flow, FLOW_OFFLOAD_DIR_ORIGINAL);
-
- return err;
}
EXPORT_SYMBOL_GPL(flow_offload_route_init);
diff --git a/net/netfilter/nf_flow_table_ip.c b/net/netfilter/nf_flow_table_ip.c
index 3bbaf9c7ea46..e45fade76409 100644
--- a/net/netfilter/nf_flow_table_ip.c
+++ b/net/netfilter/nf_flow_table_ip.c
@@ -8,6 +8,7 @@
#include <linux/ipv6.h>
#include <linux/netdevice.h>
#include <linux/if_ether.h>
+#include <net/gso.h>
#include <net/ip.h>
#include <net/ipv6.h>
#include <net/ip6_route.h>
@@ -163,38 +164,43 @@ static void nf_flow_tuple_encap(struct sk_buff *skb,
}
}
-static int nf_flow_tuple_ip(struct sk_buff *skb, const struct net_device *dev,
- struct flow_offload_tuple *tuple, u32 *hdrsize,
- u32 offset)
+struct nf_flowtable_ctx {
+ const struct net_device *in;
+ u32 offset;
+ u32 hdrsize;
+};
+
+static int nf_flow_tuple_ip(struct nf_flowtable_ctx *ctx, struct sk_buff *skb,
+ struct flow_offload_tuple *tuple)
{
struct flow_ports *ports;
unsigned int thoff;
struct iphdr *iph;
u8 ipproto;
- if (!pskb_may_pull(skb, sizeof(*iph) + offset))
+ if (!pskb_may_pull(skb, sizeof(*iph) + ctx->offset))
return -1;
- iph = (struct iphdr *)(skb_network_header(skb) + offset);
+ iph = (struct iphdr *)(skb_network_header(skb) + ctx->offset);
thoff = (iph->ihl * 4);
if (ip_is_fragment(iph) ||
unlikely(ip_has_options(thoff)))
return -1;
- thoff += offset;
+ thoff += ctx->offset;
ipproto = iph->protocol;
switch (ipproto) {
case IPPROTO_TCP:
- *hdrsize = sizeof(struct tcphdr);
+ ctx->hdrsize = sizeof(struct tcphdr);
break;
case IPPROTO_UDP:
- *hdrsize = sizeof(struct udphdr);
+ ctx->hdrsize = sizeof(struct udphdr);
break;
#ifdef CONFIG_NF_CT_PROTO_GRE
case IPPROTO_GRE:
- *hdrsize = sizeof(struct gre_base_hdr);
+ ctx->hdrsize = sizeof(struct gre_base_hdr);
break;
#endif
default:
@@ -204,7 +210,7 @@ static int nf_flow_tuple_ip(struct sk_buff *skb, const struct net_device *dev,
if (iph->ttl <= 1)
return -1;
- if (!pskb_may_pull(skb, thoff + *hdrsize))
+ if (!pskb_may_pull(skb, thoff + ctx->hdrsize))
return -1;
switch (ipproto) {
@@ -224,13 +230,13 @@ static int nf_flow_tuple_ip(struct sk_buff *skb, const struct net_device *dev,
}
}
- iph = (struct iphdr *)(skb_network_header(skb) + offset);
+ iph = (struct iphdr *)(skb_network_header(skb) + ctx->offset);
tuple->src_v4.s_addr = iph->saddr;
tuple->dst_v4.s_addr = iph->daddr;
tuple->l3proto = AF_INET;
tuple->l4proto = ipproto;
- tuple->iifidx = dev->ifindex;
+ tuple->iifidx = ctx->in->ifindex;
nf_flow_tuple_encap(skb, tuple);
return 0;
@@ -336,58 +342,56 @@ static unsigned int nf_flow_queue_xmit(struct net *net, struct sk_buff *skb,
return NF_STOLEN;
}
-unsigned int
-nf_flow_offload_ip_hook(void *priv, struct sk_buff *skb,
- const struct nf_hook_state *state)
+static struct flow_offload_tuple_rhash *
+nf_flow_offload_lookup(struct nf_flowtable_ctx *ctx,
+ struct nf_flowtable *flow_table, struct sk_buff *skb)
{
- struct flow_offload_tuple_rhash *tuplehash;
- struct nf_flowtable *flow_table = priv;
struct flow_offload_tuple tuple = {};
- enum flow_offload_tuple_dir dir;
- struct flow_offload *flow;
- struct net_device *outdev;
- u32 hdrsize, offset = 0;
- unsigned int thoff, mtu;
- struct rtable *rt;
- struct iphdr *iph;
- __be32 nexthop;
- int ret;
if (skb->protocol != htons(ETH_P_IP) &&
- !nf_flow_skb_encap_protocol(skb, htons(ETH_P_IP), &offset))
- return NF_ACCEPT;
+ !nf_flow_skb_encap_protocol(skb, htons(ETH_P_IP), &ctx->offset))
+ return NULL;
- if (nf_flow_tuple_ip(skb, state->in, &tuple, &hdrsize, offset) < 0)
- return NF_ACCEPT;
+ if (nf_flow_tuple_ip(ctx, skb, &tuple) < 0)
+ return NULL;
- tuplehash = flow_offload_lookup(flow_table, &tuple);
- if (tuplehash == NULL)
- return NF_ACCEPT;
+ return flow_offload_lookup(flow_table, &tuple);
+}
+
+static int nf_flow_offload_forward(struct nf_flowtable_ctx *ctx,
+ struct nf_flowtable *flow_table,
+ struct flow_offload_tuple_rhash *tuplehash,
+ struct sk_buff *skb)
+{
+ enum flow_offload_tuple_dir dir;
+ struct flow_offload *flow;
+ unsigned int thoff, mtu;
+ struct iphdr *iph;
dir = tuplehash->tuple.dir;
flow = container_of(tuplehash, struct flow_offload, tuplehash[dir]);
- mtu = flow->tuplehash[dir].tuple.mtu + offset;
+ mtu = flow->tuplehash[dir].tuple.mtu + ctx->offset;
if (unlikely(nf_flow_exceeds_mtu(skb, mtu)))
- return NF_ACCEPT;
+ return 0;
- iph = (struct iphdr *)(skb_network_header(skb) + offset);
- thoff = (iph->ihl * 4) + offset;
+ iph = (struct iphdr *)(skb_network_header(skb) + ctx->offset);
+ thoff = (iph->ihl * 4) + ctx->offset;
if (nf_flow_state_check(flow, iph->protocol, skb, thoff))
- return NF_ACCEPT;
+ return 0;
if (!nf_flow_dst_check(&tuplehash->tuple)) {
flow_offload_teardown(flow);
- return NF_ACCEPT;
+ return 0;
}
- if (skb_try_make_writable(skb, thoff + hdrsize))
- return NF_DROP;
+ if (skb_try_make_writable(skb, thoff + ctx->hdrsize))
+ return -1;
flow_offload_refresh(flow_table, flow, false);
nf_flow_encap_pop(skb, tuplehash);
- thoff -= offset;
+ thoff -= ctx->offset;
iph = ip_hdr(skb);
nf_flow_nat_ip(flow, skb, thoff, dir, iph);
@@ -398,6 +402,35 @@ nf_flow_offload_ip_hook(void *priv, struct sk_buff *skb,
if (flow_table->flags & NF_FLOWTABLE_COUNTER)
nf_ct_acct_update(flow->ct, tuplehash->tuple.dir, skb->len);
+ return 1;
+}
+
+unsigned int
+nf_flow_offload_ip_hook(void *priv, struct sk_buff *skb,
+ const struct nf_hook_state *state)
+{
+ struct flow_offload_tuple_rhash *tuplehash;
+ struct nf_flowtable *flow_table = priv;
+ enum flow_offload_tuple_dir dir;
+ struct nf_flowtable_ctx ctx = {
+ .in = state->in,
+ };
+ struct flow_offload *flow;
+ struct net_device *outdev;
+ struct rtable *rt;
+ __be32 nexthop;
+ int ret;
+
+ tuplehash = nf_flow_offload_lookup(&ctx, flow_table, skb);
+ if (!tuplehash)
+ return NF_ACCEPT;
+
+ ret = nf_flow_offload_forward(&ctx, flow_table, tuplehash, skb);
+ if (ret < 0)
+ return NF_DROP;
+ else if (ret == 0)
+ return NF_ACCEPT;
+
if (unlikely(tuplehash->tuple.xmit_type == FLOW_OFFLOAD_XMIT_XFRM)) {
rt = (struct rtable *)tuplehash->tuple.dst_cache;
memset(skb->cb, 0, sizeof(struct inet_skb_parm));
@@ -406,6 +439,9 @@ nf_flow_offload_ip_hook(void *priv, struct sk_buff *skb,
return nf_flow_xmit_xfrm(skb, state, &rt->dst);
}
+ dir = tuplehash->tuple.dir;
+ flow = container_of(tuplehash, struct flow_offload, tuplehash[dir]);
+
switch (tuplehash->tuple.xmit_type) {
case FLOW_OFFLOAD_XMIT_NEIGH:
rt = (struct rtable *)tuplehash->tuple.dst_cache;
@@ -535,32 +571,31 @@ static void nf_flow_nat_ipv6(const struct flow_offload *flow,
}
}
-static int nf_flow_tuple_ipv6(struct sk_buff *skb, const struct net_device *dev,
- struct flow_offload_tuple *tuple, u32 *hdrsize,
- u32 offset)
+static int nf_flow_tuple_ipv6(struct nf_flowtable_ctx *ctx, struct sk_buff *skb,
+ struct flow_offload_tuple *tuple)
{
struct flow_ports *ports;
struct ipv6hdr *ip6h;
unsigned int thoff;
u8 nexthdr;
- thoff = sizeof(*ip6h) + offset;
+ thoff = sizeof(*ip6h) + ctx->offset;
if (!pskb_may_pull(skb, thoff))
return -1;
- ip6h = (struct ipv6hdr *)(skb_network_header(skb) + offset);
+ ip6h = (struct ipv6hdr *)(skb_network_header(skb) + ctx->offset);
nexthdr = ip6h->nexthdr;
switch (nexthdr) {
case IPPROTO_TCP:
- *hdrsize = sizeof(struct tcphdr);
+ ctx->hdrsize = sizeof(struct tcphdr);
break;
case IPPROTO_UDP:
- *hdrsize = sizeof(struct udphdr);
+ ctx->hdrsize = sizeof(struct udphdr);
break;
#ifdef CONFIG_NF_CT_PROTO_GRE
case IPPROTO_GRE:
- *hdrsize = sizeof(struct gre_base_hdr);
+ ctx->hdrsize = sizeof(struct gre_base_hdr);
break;
#endif
default:
@@ -570,7 +605,7 @@ static int nf_flow_tuple_ipv6(struct sk_buff *skb, const struct net_device *dev,
if (ip6h->hop_limit <= 1)
return -1;
- if (!pskb_may_pull(skb, thoff + *hdrsize))
+ if (!pskb_may_pull(skb, thoff + ctx->hdrsize))
return -1;
switch (nexthdr) {
@@ -590,65 +625,47 @@ static int nf_flow_tuple_ipv6(struct sk_buff *skb, const struct net_device *dev,
}
}
- ip6h = (struct ipv6hdr *)(skb_network_header(skb) + offset);
+ ip6h = (struct ipv6hdr *)(skb_network_header(skb) + ctx->offset);
tuple->src_v6 = ip6h->saddr;
tuple->dst_v6 = ip6h->daddr;
tuple->l3proto = AF_INET6;
tuple->l4proto = nexthdr;
- tuple->iifidx = dev->ifindex;
+ tuple->iifidx = ctx->in->ifindex;
nf_flow_tuple_encap(skb, tuple);
return 0;
}
-unsigned int
-nf_flow_offload_ipv6_hook(void *priv, struct sk_buff *skb,
- const struct nf_hook_state *state)
+static int nf_flow_offload_ipv6_forward(struct nf_flowtable_ctx *ctx,
+ struct nf_flowtable *flow_table,
+ struct flow_offload_tuple_rhash *tuplehash,
+ struct sk_buff *skb)
{
- struct flow_offload_tuple_rhash *tuplehash;
- struct nf_flowtable *flow_table = priv;
- struct flow_offload_tuple tuple = {};
enum flow_offload_tuple_dir dir;
- const struct in6_addr *nexthop;
struct flow_offload *flow;
- struct net_device *outdev;
unsigned int thoff, mtu;
- u32 hdrsize, offset = 0;
struct ipv6hdr *ip6h;
- struct rt6_info *rt;
- int ret;
-
- if (skb->protocol != htons(ETH_P_IPV6) &&
- !nf_flow_skb_encap_protocol(skb, htons(ETH_P_IPV6), &offset))
- return NF_ACCEPT;
-
- if (nf_flow_tuple_ipv6(skb, state->in, &tuple, &hdrsize, offset) < 0)
- return NF_ACCEPT;
-
- tuplehash = flow_offload_lookup(flow_table, &tuple);
- if (tuplehash == NULL)
- return NF_ACCEPT;
dir = tuplehash->tuple.dir;
flow = container_of(tuplehash, struct flow_offload, tuplehash[dir]);
- mtu = flow->tuplehash[dir].tuple.mtu + offset;
+ mtu = flow->tuplehash[dir].tuple.mtu + ctx->offset;
if (unlikely(nf_flow_exceeds_mtu(skb, mtu)))
- return NF_ACCEPT;
+ return 0;
- ip6h = (struct ipv6hdr *)(skb_network_header(skb) + offset);
- thoff = sizeof(*ip6h) + offset;
+ ip6h = (struct ipv6hdr *)(skb_network_header(skb) + ctx->offset);
+ thoff = sizeof(*ip6h) + ctx->offset;
if (nf_flow_state_check(flow, ip6h->nexthdr, skb, thoff))
- return NF_ACCEPT;
+ return 0;
if (!nf_flow_dst_check(&tuplehash->tuple)) {
flow_offload_teardown(flow);
- return NF_ACCEPT;
+ return 0;
}
- if (skb_try_make_writable(skb, thoff + hdrsize))
- return NF_DROP;
+ if (skb_try_make_writable(skb, thoff + ctx->hdrsize))
+ return -1;
flow_offload_refresh(flow_table, flow, false);
@@ -663,6 +680,52 @@ nf_flow_offload_ipv6_hook(void *priv, struct sk_buff *skb,
if (flow_table->flags & NF_FLOWTABLE_COUNTER)
nf_ct_acct_update(flow->ct, tuplehash->tuple.dir, skb->len);
+ return 1;
+}
+
+static struct flow_offload_tuple_rhash *
+nf_flow_offload_ipv6_lookup(struct nf_flowtable_ctx *ctx,
+ struct nf_flowtable *flow_table,
+ struct sk_buff *skb)
+{
+ struct flow_offload_tuple tuple = {};
+
+ if (skb->protocol != htons(ETH_P_IPV6) &&
+ !nf_flow_skb_encap_protocol(skb, htons(ETH_P_IPV6), &ctx->offset))
+ return NULL;
+
+ if (nf_flow_tuple_ipv6(ctx, skb, &tuple) < 0)
+ return NULL;
+
+ return flow_offload_lookup(flow_table, &tuple);
+}
+
+unsigned int
+nf_flow_offload_ipv6_hook(void *priv, struct sk_buff *skb,
+ const struct nf_hook_state *state)
+{
+ struct flow_offload_tuple_rhash *tuplehash;
+ struct nf_flowtable *flow_table = priv;
+ enum flow_offload_tuple_dir dir;
+ struct nf_flowtable_ctx ctx = {
+ .in = state->in,
+ };
+ const struct in6_addr *nexthop;
+ struct flow_offload *flow;
+ struct net_device *outdev;
+ struct rt6_info *rt;
+ int ret;
+
+ tuplehash = nf_flow_offload_ipv6_lookup(&ctx, flow_table, skb);
+ if (tuplehash == NULL)
+ return NF_ACCEPT;
+
+ ret = nf_flow_offload_ipv6_forward(&ctx, flow_table, tuplehash, skb);
+ if (ret < 0)
+ return NF_DROP;
+ else if (ret == 0)
+ return NF_ACCEPT;
+
if (unlikely(tuplehash->tuple.xmit_type == FLOW_OFFLOAD_XMIT_XFRM)) {
rt = (struct rt6_info *)tuplehash->tuple.dst_cache;
memset(skb->cb, 0, sizeof(struct inet6_skb_parm));
@@ -671,6 +734,9 @@ nf_flow_offload_ipv6_hook(void *priv, struct sk_buff *skb,
return nf_flow_xmit_xfrm(skb, state, &rt->dst);
}
+ dir = tuplehash->tuple.dir;
+ flow = container_of(tuplehash, struct flow_offload, tuplehash[dir]);
+
switch (tuplehash->tuple.xmit_type) {
case FLOW_OFFLOAD_XMIT_NEIGH:
rt = (struct rt6_info *)tuplehash->tuple.dst_cache;
diff --git a/net/netfilter/nf_nat_core.c b/net/netfilter/nf_nat_core.c
index ce829d434f13..fadbd4ed3dc0 100644
--- a/net/netfilter/nf_nat_core.c
+++ b/net/netfilter/nf_nat_core.c
@@ -27,6 +27,9 @@
#include "nf_internals.h"
+#define NF_NAT_MAX_ATTEMPTS 128
+#define NF_NAT_HARDER_THRESH (NF_NAT_MAX_ATTEMPTS / 4)
+
static spinlock_t nf_nat_locks[CONNTRACK_LOCKS];
static DEFINE_MUTEX(nf_nat_proto_mutex);
@@ -197,6 +200,88 @@ nf_nat_used_tuple(const struct nf_conntrack_tuple *tuple,
return nf_conntrack_tuple_taken(&reply, ignored_conntrack);
}
+static bool nf_nat_may_kill(struct nf_conn *ct, unsigned long flags)
+{
+ static const unsigned long flags_refuse = IPS_FIXED_TIMEOUT |
+ IPS_DYING;
+ static const unsigned long flags_needed = IPS_SRC_NAT;
+ enum tcp_conntrack old_state;
+
+ old_state = READ_ONCE(ct->proto.tcp.state);
+ if (old_state < TCP_CONNTRACK_TIME_WAIT)
+ return false;
+
+ if (flags & flags_refuse)
+ return false;
+
+ return (flags & flags_needed) == flags_needed;
+}
+
+/* reverse direction will send packets to new source, so
+ * make sure such packets are invalid.
+ */
+static bool nf_seq_has_advanced(const struct nf_conn *old, const struct nf_conn *new)
+{
+ return (__s32)(new->proto.tcp.seen[0].td_end -
+ old->proto.tcp.seen[0].td_end) > 0;
+}
+
+static int
+nf_nat_used_tuple_harder(const struct nf_conntrack_tuple *tuple,
+ const struct nf_conn *ignored_conntrack,
+ unsigned int attempts_left)
+{
+ static const unsigned long flags_offload = IPS_OFFLOAD | IPS_HW_OFFLOAD;
+ struct nf_conntrack_tuple_hash *thash;
+ const struct nf_conntrack_zone *zone;
+ struct nf_conntrack_tuple reply;
+ unsigned long flags;
+ struct nf_conn *ct;
+ bool taken = true;
+ struct net *net;
+
+ nf_ct_invert_tuple(&reply, tuple);
+
+ if (attempts_left > NF_NAT_HARDER_THRESH ||
+ tuple->dst.protonum != IPPROTO_TCP ||
+ ignored_conntrack->proto.tcp.state != TCP_CONNTRACK_SYN_SENT)
+ return nf_conntrack_tuple_taken(&reply, ignored_conntrack);
+
+ /* :ast few attempts to find a free tcp port. Destructive
+ * action: evict colliding if its in timewait state and the
+ * tcp sequence number has advanced past the one used by the
+ * old entry.
+ */
+ net = nf_ct_net(ignored_conntrack);
+ zone = nf_ct_zone(ignored_conntrack);
+
+ thash = nf_conntrack_find_get(net, zone, &reply);
+ if (!thash)
+ return false;
+
+ ct = nf_ct_tuplehash_to_ctrack(thash);
+
+ if (thash->tuple.dst.dir == IP_CT_DIR_ORIGINAL)
+ goto out;
+
+ if (WARN_ON_ONCE(ct == ignored_conntrack))
+ goto out;
+
+ flags = READ_ONCE(ct->status);
+ if (!nf_nat_may_kill(ct, flags))
+ goto out;
+
+ if (!nf_seq_has_advanced(ct, ignored_conntrack))
+ goto out;
+
+ /* Even if we can evict do not reuse if entry is offloaded. */
+ if (nf_ct_kill(ct))
+ taken = flags & flags_offload;
+out:
+ nf_ct_put(ct);
+ return taken;
+}
+
static bool nf_nat_inet_in_range(const struct nf_conntrack_tuple *t,
const struct nf_nat_range2 *range)
{
@@ -385,7 +470,6 @@ static void nf_nat_l4proto_unique_tuple(struct nf_conntrack_tuple *tuple,
unsigned int range_size, min, max, i, attempts;
__be16 *keyptr;
u16 off;
- static const unsigned int max_attempts = 128;
switch (tuple->dst.protonum) {
case IPPROTO_ICMP:
@@ -471,8 +555,8 @@ find_free_id:
off = get_random_u16();
attempts = range_size;
- if (attempts > max_attempts)
- attempts = max_attempts;
+ if (attempts > NF_NAT_MAX_ATTEMPTS)
+ attempts = NF_NAT_MAX_ATTEMPTS;
/* We are in softirq; doing a search of the entire range risks
* soft lockup when all tuples are already used.
@@ -483,7 +567,7 @@ find_free_id:
another_round:
for (i = 0; i < attempts; i++, off++) {
*keyptr = htons(min + off % range_size);
- if (!nf_nat_used_tuple(tuple, ct))
+ if (!nf_nat_used_tuple_harder(tuple, ct, attempts - i))
return;
}
diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index 4c7937fd803f..9573a8fcad79 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -567,6 +567,7 @@ static int __nft_trans_set_add(const struct nft_ctx *ctx, int msg_type,
nft_trans_set_update(trans) = true;
nft_trans_set_gc_int(trans) = desc->gc_int;
nft_trans_set_timeout(trans) = desc->timeout;
+ nft_trans_set_size(trans) = desc->size;
}
nft_trans_commit_list_add_tail(ctx->net, trans);
@@ -5343,6 +5344,8 @@ void nf_tables_deactivate_set(const struct nft_ctx *ctx, struct nft_set *set,
nft_set_trans_unbind(ctx, set);
if (nft_set_is_anonymous(set))
nft_deactivate_next(ctx->net, set);
+ else
+ list_del_rcu(&binding->list);
set->use--;
break;
@@ -5442,7 +5445,8 @@ static const struct nla_policy nft_set_elem_list_policy[NFTA_SET_ELEM_LIST_MAX +
static int nft_set_elem_expr_dump(struct sk_buff *skb,
const struct nft_set *set,
- const struct nft_set_ext *ext)
+ const struct nft_set_ext *ext,
+ bool reset)
{
struct nft_set_elem_expr *elem_expr;
u32 size, num_exprs = 0;
@@ -5455,7 +5459,7 @@ static int nft_set_elem_expr_dump(struct sk_buff *skb,
if (num_exprs == 1) {
expr = nft_setelem_expr_at(elem_expr, 0);
- if (nft_expr_dump(skb, NFTA_SET_ELEM_EXPR, expr, false) < 0)
+ if (nft_expr_dump(skb, NFTA_SET_ELEM_EXPR, expr, reset) < 0)
return -1;
return 0;
@@ -5466,7 +5470,7 @@ static int nft_set_elem_expr_dump(struct sk_buff *skb,
nft_setelem_expr_foreach(expr, elem_expr, size) {
expr = nft_setelem_expr_at(elem_expr, size);
- if (nft_expr_dump(skb, NFTA_LIST_ELEM, expr, false) < 0)
+ if (nft_expr_dump(skb, NFTA_LIST_ELEM, expr, reset) < 0)
goto nla_put_failure;
}
nla_nest_end(skb, nest);
@@ -5479,11 +5483,13 @@ nla_put_failure:
static int nf_tables_fill_setelem(struct sk_buff *skb,
const struct nft_set *set,
- const struct nft_set_elem *elem)
+ const struct nft_set_elem *elem,
+ bool reset)
{
const struct nft_set_ext *ext = nft_set_elem_ext(set, elem->priv);
unsigned char *b = skb_tail_pointer(skb);
struct nlattr *nest;
+ u64 timeout = 0;
nest = nla_nest_start_noflag(skb, NFTA_LIST_ELEM);
if (nest == NULL)
@@ -5506,7 +5512,7 @@ static int nf_tables_fill_setelem(struct sk_buff *skb,
goto nla_put_failure;
if (nft_set_ext_exists(ext, NFT_SET_EXT_EXPRESSIONS) &&
- nft_set_elem_expr_dump(skb, set, ext))
+ nft_set_elem_expr_dump(skb, set, ext, reset))
goto nla_put_failure;
if (nft_set_ext_exists(ext, NFT_SET_EXT_OBJREF) &&
@@ -5519,11 +5525,15 @@ static int nf_tables_fill_setelem(struct sk_buff *skb,
htonl(*nft_set_ext_flags(ext))))
goto nla_put_failure;
- if (nft_set_ext_exists(ext, NFT_SET_EXT_TIMEOUT) &&
- nla_put_be64(skb, NFTA_SET_ELEM_TIMEOUT,
- nf_jiffies64_to_msecs(*nft_set_ext_timeout(ext)),
- NFTA_SET_ELEM_PAD))
- goto nla_put_failure;
+ if (nft_set_ext_exists(ext, NFT_SET_EXT_TIMEOUT)) {
+ timeout = *nft_set_ext_timeout(ext);
+ if (nla_put_be64(skb, NFTA_SET_ELEM_TIMEOUT,
+ nf_jiffies64_to_msecs(timeout),
+ NFTA_SET_ELEM_PAD))
+ goto nla_put_failure;
+ } else if (set->flags & NFT_SET_TIMEOUT) {
+ timeout = READ_ONCE(set->timeout);
+ }
if (nft_set_ext_exists(ext, NFT_SET_EXT_EXPIRATION)) {
u64 expires, now = get_jiffies_64();
@@ -5538,6 +5548,9 @@ static int nf_tables_fill_setelem(struct sk_buff *skb,
nf_jiffies64_to_msecs(expires),
NFTA_SET_ELEM_PAD))
goto nla_put_failure;
+
+ if (reset)
+ *nft_set_ext_expiration(ext) = now + timeout;
}
if (nft_set_ext_exists(ext, NFT_SET_EXT_USERDATA)) {
@@ -5561,6 +5574,7 @@ struct nft_set_dump_args {
const struct netlink_callback *cb;
struct nft_set_iter iter;
struct sk_buff *skb;
+ bool reset;
};
static int nf_tables_dump_setelem(const struct nft_ctx *ctx,
@@ -5571,7 +5585,7 @@ static int nf_tables_dump_setelem(const struct nft_ctx *ctx,
struct nft_set_dump_args *args;
args = container_of(iter, struct nft_set_dump_args, iter);
- return nf_tables_fill_setelem(args->skb, set, elem);
+ return nf_tables_fill_setelem(args->skb, set, elem, args->reset);
}
struct nft_set_dump_ctx {
@@ -5580,7 +5594,7 @@ struct nft_set_dump_ctx {
};
static int nft_set_catchall_dump(struct net *net, struct sk_buff *skb,
- const struct nft_set *set)
+ const struct nft_set *set, bool reset)
{
struct nft_set_elem_catchall *catchall;
u8 genmask = nft_genmask_cur(net);
@@ -5595,7 +5609,7 @@ static int nft_set_catchall_dump(struct net *net, struct sk_buff *skb,
continue;
elem.priv = catchall->elem;
- ret = nf_tables_fill_setelem(skb, set, &elem);
+ ret = nf_tables_fill_setelem(skb, set, &elem, reset);
break;
}
@@ -5613,6 +5627,7 @@ static int nf_tables_dump_set(struct sk_buff *skb, struct netlink_callback *cb)
bool set_found = false;
struct nlmsghdr *nlh;
struct nlattr *nest;
+ bool reset = false;
u32 portid, seq;
int event;
@@ -5660,8 +5675,12 @@ static int nf_tables_dump_set(struct sk_buff *skb, struct netlink_callback *cb)
if (nest == NULL)
goto nla_put_failure;
+ if (NFNL_MSG_TYPE(cb->nlh->nlmsg_type) == NFT_MSG_GETSETELEM_RESET)
+ reset = true;
+
args.cb = cb;
args.skb = skb;
+ args.reset = reset;
args.iter.genmask = nft_genmask_cur(net);
args.iter.skip = cb->args[0];
args.iter.count = 0;
@@ -5670,7 +5689,7 @@ static int nf_tables_dump_set(struct sk_buff *skb, struct netlink_callback *cb)
set->ops->walk(&dump_ctx->ctx, set, &args.iter);
if (!args.iter.err && args.iter.count == cb->args[0])
- args.iter.err = nft_set_catchall_dump(net, skb, set);
+ args.iter.err = nft_set_catchall_dump(net, skb, set, reset);
rcu_read_unlock();
nla_nest_end(skb, nest);
@@ -5708,7 +5727,8 @@ static int nf_tables_fill_setelem_info(struct sk_buff *skb,
const struct nft_ctx *ctx, u32 seq,
u32 portid, int event, u16 flags,
const struct nft_set *set,
- const struct nft_set_elem *elem)
+ const struct nft_set_elem *elem,
+ bool reset)
{
struct nlmsghdr *nlh;
struct nlattr *nest;
@@ -5729,7 +5749,7 @@ static int nf_tables_fill_setelem_info(struct sk_buff *skb,
if (nest == NULL)
goto nla_put_failure;
- err = nf_tables_fill_setelem(skb, set, elem);
+ err = nf_tables_fill_setelem(skb, set, elem, reset);
if (err < 0)
goto nla_put_failure;
@@ -5835,7 +5855,7 @@ static int nft_setelem_get(struct nft_ctx *ctx, struct nft_set *set,
}
static int nft_get_set_elem(struct nft_ctx *ctx, struct nft_set *set,
- const struct nlattr *attr)
+ const struct nlattr *attr, bool reset)
{
struct nlattr *nla[NFTA_SET_ELEM_MAX + 1];
struct nft_set_elem elem;
@@ -5879,7 +5899,8 @@ static int nft_get_set_elem(struct nft_ctx *ctx, struct nft_set *set,
return err;
err = nf_tables_fill_setelem_info(skb, ctx, ctx->seq, ctx->portid,
- NFT_MSG_NEWSETELEM, 0, set, &elem);
+ NFT_MSG_NEWSETELEM, 0, set, &elem,
+ reset);
if (err < 0)
goto err_fill_setelem;
@@ -5903,6 +5924,7 @@ static int nf_tables_getsetelem(struct sk_buff *skb,
struct nft_set *set;
struct nlattr *attr;
struct nft_ctx ctx;
+ bool reset = false;
int rem, err = 0;
table = nft_table_lookup(net, nla[NFTA_SET_ELEM_LIST_TABLE], family,
@@ -5937,8 +5959,11 @@ static int nf_tables_getsetelem(struct sk_buff *skb,
if (!nla[NFTA_SET_ELEM_LIST_ELEMENTS])
return -EINVAL;
+ if (NFNL_MSG_TYPE(info->nlh->nlmsg_type) == NFT_MSG_GETSETELEM_RESET)
+ reset = true;
+
nla_for_each_nested(attr, nla[NFTA_SET_ELEM_LIST_ELEMENTS], rem) {
- err = nft_get_set_elem(&ctx, set, attr);
+ err = nft_get_set_elem(&ctx, set, attr, reset);
if (err < 0) {
NL_SET_BAD_ATTR(extack, attr);
break;
@@ -5971,7 +5996,7 @@ static void nf_tables_setelem_notify(const struct nft_ctx *ctx,
flags |= ctx->flags & (NLM_F_CREATE | NLM_F_EXCL);
err = nf_tables_fill_setelem_info(skb, ctx, 0, portid, event, flags,
- set, elem);
+ set, elem, false);
if (err < 0) {
kfree_skb(skb);
goto err;
@@ -6754,10 +6779,13 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set,
goto err_element_clash;
}
- if (!(flags & NFT_SET_ELEM_CATCHALL) && set->size &&
- !atomic_add_unless(&set->nelems, 1, set->size + set->ndeact)) {
- err = -ENFILE;
- goto err_set_full;
+ if (!(flags & NFT_SET_ELEM_CATCHALL)) {
+ unsigned int max = set->size ? set->size + set->ndeact : UINT_MAX;
+
+ if (!atomic_add_unless(&set->nelems, 1, max)) {
+ err = -ENFILE;
+ goto err_set_full;
+ }
}
nft_trans_elem(trans) = elem;
@@ -6769,7 +6797,9 @@ err_set_full:
err_element_clash:
kfree(trans);
err_elem_free:
- nft_set_elem_destroy(set, elem.priv, true);
+ nf_tables_set_elem_destroy(ctx, set, elem.priv);
+ if (obj)
+ obj->use--;
err_parse_data:
if (nla[NFTA_SET_ELEM_DATA] != NULL)
nft_data_release(&elem.data.val, desc.type);
@@ -8917,6 +8947,12 @@ static const struct nfnl_callback nf_tables_cb[NFT_MSG_MAX] = {
.attr_count = NFTA_SET_ELEM_LIST_MAX,
.policy = nft_set_elem_list_policy,
},
+ [NFT_MSG_GETSETELEM_RESET] = {
+ .call = nf_tables_getsetelem,
+ .type = NFNL_CB_RCU,
+ .attr_count = NFTA_SET_ELEM_LIST_MAX,
+ .policy = nft_set_elem_list_policy,
+ },
[NFT_MSG_DELSETELEM] = {
.call = nf_tables_delsetelem,
.type = NFNL_CB_BATCH,
@@ -9667,6 +9703,9 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb)
WRITE_ONCE(set->timeout, nft_trans_set_timeout(trans));
WRITE_ONCE(set->gc_int, nft_trans_set_gc_int(trans));
+
+ if (nft_trans_set_size(trans))
+ WRITE_ONCE(set->size, nft_trans_set_size(trans));
} else {
nft_clear(net, nft_trans_set(trans));
/* This avoids hitting -EBUSY when deleting the table
diff --git a/net/netfilter/nfnetlink_queue.c b/net/netfilter/nfnetlink_queue.c
index e311462f6d98..556bc902af00 100644
--- a/net/netfilter/nfnetlink_queue.c
+++ b/net/netfilter/nfnetlink_queue.c
@@ -30,6 +30,7 @@
#include <linux/netfilter/nf_conntrack_common.h>
#include <linux/list.h>
#include <linux/cgroup-defs.h>
+#include <net/gso.h>
#include <net/sock.h>
#include <net/tcp_states.h>
#include <net/netfilter/nf_queue.h>
diff --git a/net/netfilter/nft_bitwise.c b/net/netfilter/nft_bitwise.c
index 2527a01486ef..ca857afbf061 100644
--- a/net/netfilter/nft_bitwise.c
+++ b/net/netfilter/nft_bitwise.c
@@ -86,7 +86,7 @@ static const struct nla_policy nft_bitwise_policy[NFTA_BITWISE_MAX + 1] = {
[NFTA_BITWISE_LEN] = { .type = NLA_U32 },
[NFTA_BITWISE_MASK] = { .type = NLA_NESTED },
[NFTA_BITWISE_XOR] = { .type = NLA_NESTED },
- [NFTA_BITWISE_OP] = { .type = NLA_U32 },
+ [NFTA_BITWISE_OP] = NLA_POLICY_MAX(NLA_BE32, 255),
[NFTA_BITWISE_DATA] = { .type = NLA_NESTED },
};
diff --git a/net/netfilter/nft_byteorder.c b/net/netfilter/nft_byteorder.c
index b66647a5a171..9a85e797ed58 100644
--- a/net/netfilter/nft_byteorder.c
+++ b/net/netfilter/nft_byteorder.c
@@ -88,9 +88,9 @@ void nft_byteorder_eval(const struct nft_expr *expr,
static const struct nla_policy nft_byteorder_policy[NFTA_BYTEORDER_MAX + 1] = {
[NFTA_BYTEORDER_SREG] = { .type = NLA_U32 },
[NFTA_BYTEORDER_DREG] = { .type = NLA_U32 },
- [NFTA_BYTEORDER_OP] = { .type = NLA_U32 },
- [NFTA_BYTEORDER_LEN] = { .type = NLA_U32 },
- [NFTA_BYTEORDER_SIZE] = { .type = NLA_U32 },
+ [NFTA_BYTEORDER_OP] = NLA_POLICY_MAX(NLA_BE32, 255),
+ [NFTA_BYTEORDER_LEN] = NLA_POLICY_MAX(NLA_BE32, 255),
+ [NFTA_BYTEORDER_SIZE] = NLA_POLICY_MAX(NLA_BE32, 255),
};
static int nft_byteorder_init(const struct nft_ctx *ctx,
diff --git a/net/netfilter/nft_ct.c b/net/netfilter/nft_ct.c
index b9c84499438b..38958e067aa8 100644
--- a/net/netfilter/nft_ct.c
+++ b/net/netfilter/nft_ct.c
@@ -332,7 +332,7 @@ static void nft_ct_set_eval(const struct nft_expr *expr,
static const struct nla_policy nft_ct_policy[NFTA_CT_MAX + 1] = {
[NFTA_CT_DREG] = { .type = NLA_U32 },
- [NFTA_CT_KEY] = { .type = NLA_U32 },
+ [NFTA_CT_KEY] = NLA_POLICY_MAX(NLA_BE32, 255),
[NFTA_CT_DIRECTION] = { .type = NLA_U8 },
[NFTA_CT_SREG] = { .type = NLA_U32 },
};
diff --git a/net/netfilter/nft_dynset.c b/net/netfilter/nft_dynset.c
index bd19c7aec92e..4fb34d76dbea 100644
--- a/net/netfilter/nft_dynset.c
+++ b/net/netfilter/nft_dynset.c
@@ -148,7 +148,7 @@ static const struct nla_policy nft_dynset_policy[NFTA_DYNSET_MAX + 1] = {
[NFTA_DYNSET_SET_NAME] = { .type = NLA_STRING,
.len = NFT_SET_MAXNAMELEN - 1 },
[NFTA_DYNSET_SET_ID] = { .type = NLA_U32 },
- [NFTA_DYNSET_OP] = { .type = NLA_U32 },
+ [NFTA_DYNSET_OP] = NLA_POLICY_MAX(NLA_BE32, 255),
[NFTA_DYNSET_SREG_KEY] = { .type = NLA_U32 },
[NFTA_DYNSET_SREG_DATA] = { .type = NLA_U32 },
[NFTA_DYNSET_TIMEOUT] = { .type = NLA_U64 },
diff --git a/net/netfilter/nft_exthdr.c b/net/netfilter/nft_exthdr.c
index a54a7f772cec..7f856ceb3a66 100644
--- a/net/netfilter/nft_exthdr.c
+++ b/net/netfilter/nft_exthdr.c
@@ -10,6 +10,7 @@
#include <linux/netlink.h>
#include <linux/netfilter.h>
#include <linux/netfilter/nf_tables.h>
+#include <linux/dccp.h>
#include <linux/sctp.h>
#include <net/netfilter/nf_tables_core.h>
#include <net/netfilter/nf_tables.h>
@@ -406,13 +407,89 @@ err:
regs->verdict.code = NFT_BREAK;
}
+static void nft_exthdr_dccp_eval(const struct nft_expr *expr,
+ struct nft_regs *regs,
+ const struct nft_pktinfo *pkt)
+{
+ struct nft_exthdr *priv = nft_expr_priv(expr);
+ unsigned int thoff, dataoff, optoff, optlen, i;
+ u32 *dest = &regs->data[priv->dreg];
+ const struct dccp_hdr *dh;
+ struct dccp_hdr _dh;
+
+ if (pkt->tprot != IPPROTO_DCCP || pkt->fragoff)
+ goto err;
+
+ thoff = nft_thoff(pkt);
+
+ dh = skb_header_pointer(pkt->skb, thoff, sizeof(_dh), &_dh);
+ if (!dh)
+ goto err;
+
+ dataoff = dh->dccph_doff * sizeof(u32);
+ optoff = __dccp_hdr_len(dh);
+ if (dataoff <= optoff)
+ goto err;
+
+ optlen = dataoff - optoff;
+
+ for (i = 0; i < optlen; ) {
+ /* Options 0 (DCCPO_PADDING) - 31 (DCCPO_MAX_RESERVED) are 1B in
+ * the length; the remaining options are at least 2B long. In
+ * all cases, the first byte contains the option type. In
+ * multi-byte options, the second byte contains the option
+ * length, which must be at least two: 1 for the type plus 1 for
+ * the length plus 0-253 for any following option data. We
+ * aren't interested in the option data, only the type and the
+ * length, so we don't need to read more than two bytes at a
+ * time.
+ */
+ unsigned int buflen = optlen - i;
+ u8 buf[2], *bufp;
+ u8 type, len;
+
+ if (buflen > sizeof(buf))
+ buflen = sizeof(buf);
+
+ bufp = skb_header_pointer(pkt->skb, thoff + optoff + i, buflen,
+ &buf);
+ if (!bufp)
+ goto err;
+
+ type = bufp[0];
+
+ if (type == priv->type) {
+ *dest = 1;
+ return;
+ }
+
+ if (type <= DCCPO_MAX_RESERVED) {
+ i++;
+ continue;
+ }
+
+ if (buflen < 2)
+ goto err;
+
+ len = bufp[1];
+
+ if (len < 2)
+ goto err;
+
+ i += len;
+ }
+
+err:
+ *dest = 0;
+}
+
static const struct nla_policy nft_exthdr_policy[NFTA_EXTHDR_MAX + 1] = {
[NFTA_EXTHDR_DREG] = { .type = NLA_U32 },
[NFTA_EXTHDR_TYPE] = { .type = NLA_U8 },
[NFTA_EXTHDR_OFFSET] = { .type = NLA_U32 },
- [NFTA_EXTHDR_LEN] = { .type = NLA_U32 },
+ [NFTA_EXTHDR_LEN] = NLA_POLICY_MAX(NLA_BE32, 255),
[NFTA_EXTHDR_FLAGS] = { .type = NLA_U32 },
- [NFTA_EXTHDR_OP] = { .type = NLA_U32 },
+ [NFTA_EXTHDR_OP] = NLA_POLICY_MAX(NLA_BE32, 255),
[NFTA_EXTHDR_SREG] = { .type = NLA_U32 },
};
@@ -557,6 +634,22 @@ static int nft_exthdr_ipv4_init(const struct nft_ctx *ctx,
return 0;
}
+static int nft_exthdr_dccp_init(const struct nft_ctx *ctx,
+ const struct nft_expr *expr,
+ const struct nlattr * const tb[])
+{
+ struct nft_exthdr *priv = nft_expr_priv(expr);
+ int err = nft_exthdr_init(ctx, expr, tb);
+
+ if (err < 0)
+ return err;
+
+ if (!(priv->flags & NFT_EXTHDR_F_PRESENT))
+ return -EOPNOTSUPP;
+
+ return 0;
+}
+
static int nft_exthdr_dump_common(struct sk_buff *skb, const struct nft_exthdr *priv)
{
if (nla_put_u8(skb, NFTA_EXTHDR_TYPE, priv->type))
@@ -686,6 +779,15 @@ static const struct nft_expr_ops nft_exthdr_sctp_ops = {
.reduce = nft_exthdr_reduce,
};
+static const struct nft_expr_ops nft_exthdr_dccp_ops = {
+ .type = &nft_exthdr_type,
+ .size = NFT_EXPR_SIZE(sizeof(struct nft_exthdr)),
+ .eval = nft_exthdr_dccp_eval,
+ .init = nft_exthdr_dccp_init,
+ .dump = nft_exthdr_dump,
+ .reduce = nft_exthdr_reduce,
+};
+
static const struct nft_expr_ops *
nft_exthdr_select_ops(const struct nft_ctx *ctx,
const struct nlattr * const tb[])
@@ -720,6 +822,10 @@ nft_exthdr_select_ops(const struct nft_ctx *ctx,
if (tb[NFTA_EXTHDR_DREG])
return &nft_exthdr_sctp_ops;
break;
+ case NFT_EXTHDR_OP_DCCP:
+ if (tb[NFTA_EXTHDR_DREG])
+ return &nft_exthdr_dccp_ops;
+ break;
}
return ERR_PTR(-EOPNOTSUPP);
diff --git a/net/netfilter/nft_flow_offload.c b/net/netfilter/nft_flow_offload.c
index e860d8fe0e5e..5ef9146e74ad 100644
--- a/net/netfilter/nft_flow_offload.c
+++ b/net/netfilter/nft_flow_offload.c
@@ -250,9 +250,14 @@ static int nft_flow_route(const struct nft_pktinfo *pkt,
break;
}
+ if (!dst_hold_safe(this_dst))
+ return -ENOENT;
+
nf_route(nft_net(pkt), &other_dst, &fl, false, nft_pf(pkt));
- if (!other_dst)
+ if (!other_dst) {
+ dst_release(this_dst);
return -ENOENT;
+ }
nft_default_forward_path(route, this_dst, dir);
nft_default_forward_path(route, other_dst, !dir);
@@ -349,8 +354,7 @@ static void nft_flow_offload_eval(const struct nft_expr *expr,
if (!flow)
goto err_flow_alloc;
- if (flow_offload_route_init(flow, &route) < 0)
- goto err_flow_add;
+ flow_offload_route_init(flow, &route);
if (tcph) {
ct->proto.tcp.seen[0].flags |= IP_CT_TCP_FLAG_BE_LIBERAL;
@@ -361,12 +365,12 @@ static void nft_flow_offload_eval(const struct nft_expr *expr,
if (ret < 0)
goto err_flow_add;
- dst_release(route.tuple[!dir].dst);
return;
err_flow_add:
flow_offload_free(flow);
err_flow_alloc:
+ dst_release(route.tuple[dir].dst);
dst_release(route.tuple[!dir].dst);
err_flow_route:
clear_bit(IPS_OFFLOAD_BIT, &ct->status);
diff --git a/net/netfilter/nft_fwd_netdev.c b/net/netfilter/nft_fwd_netdev.c
index 7b9d4d1bd17c..a5268e6dd32f 100644
--- a/net/netfilter/nft_fwd_netdev.c
+++ b/net/netfilter/nft_fwd_netdev.c
@@ -40,7 +40,7 @@ static void nft_fwd_netdev_eval(const struct nft_expr *expr,
static const struct nla_policy nft_fwd_netdev_policy[NFTA_FWD_MAX + 1] = {
[NFTA_FWD_SREG_DEV] = { .type = NLA_U32 },
[NFTA_FWD_SREG_ADDR] = { .type = NLA_U32 },
- [NFTA_FWD_NFPROTO] = { .type = NLA_U32 },
+ [NFTA_FWD_NFPROTO] = NLA_POLICY_MAX(NLA_BE32, 255),
};
static int nft_fwd_netdev_init(const struct nft_ctx *ctx,
diff --git a/net/netfilter/nft_hash.c b/net/netfilter/nft_hash.c
index ee8d487b69c0..92d47e469204 100644
--- a/net/netfilter/nft_hash.c
+++ b/net/netfilter/nft_hash.c
@@ -59,7 +59,7 @@ static void nft_symhash_eval(const struct nft_expr *expr,
static const struct nla_policy nft_hash_policy[NFTA_HASH_MAX + 1] = {
[NFTA_HASH_SREG] = { .type = NLA_U32 },
[NFTA_HASH_DREG] = { .type = NLA_U32 },
- [NFTA_HASH_LEN] = { .type = NLA_U32 },
+ [NFTA_HASH_LEN] = NLA_POLICY_MAX(NLA_BE32, 255),
[NFTA_HASH_MODULUS] = { .type = NLA_U32 },
[NFTA_HASH_SEED] = { .type = NLA_U32 },
[NFTA_HASH_OFFSET] = { .type = NLA_U32 },
diff --git a/net/netfilter/nft_lookup.c b/net/netfilter/nft_lookup.c
index 03ef4fdaa460..29ac48cdd6db 100644
--- a/net/netfilter/nft_lookup.c
+++ b/net/netfilter/nft_lookup.c
@@ -19,6 +19,7 @@ struct nft_lookup {
struct nft_set *set;
u8 sreg;
u8 dreg;
+ bool dreg_set;
bool invert;
struct nft_set_binding binding;
};
@@ -75,7 +76,7 @@ void nft_lookup_eval(const struct nft_expr *expr,
}
if (ext) {
- if (set->flags & NFT_SET_MAP)
+ if (priv->dreg_set)
nft_data_copy(&regs->data[priv->dreg],
nft_set_ext_data(ext), set->dlen);
@@ -122,11 +123,8 @@ static int nft_lookup_init(const struct nft_ctx *ctx,
if (flags & ~NFT_LOOKUP_F_INV)
return -EINVAL;
- if (flags & NFT_LOOKUP_F_INV) {
- if (set->flags & NFT_SET_MAP)
- return -EINVAL;
+ if (flags & NFT_LOOKUP_F_INV)
priv->invert = true;
- }
}
if (tb[NFTA_LOOKUP_DREG] != NULL) {
@@ -140,8 +138,17 @@ static int nft_lookup_init(const struct nft_ctx *ctx,
set->dlen);
if (err < 0)
return err;
- } else if (set->flags & NFT_SET_MAP)
- return -EINVAL;
+ priv->dreg_set = true;
+ } else if (set->flags & NFT_SET_MAP) {
+ /* Map given, but user asks for lookup only (i.e. to
+ * ignore value assoicated with key).
+ *
+ * This makes no sense for anonymous maps since they are
+ * scoped to the rule, but for named sets this can be useful.
+ */
+ if (set->flags & NFT_SET_ANONYMOUS)
+ return -EINVAL;
+ }
priv->binding.flags = set->flags & NFT_SET_MAP;
@@ -188,7 +195,7 @@ static int nft_lookup_dump(struct sk_buff *skb,
goto nla_put_failure;
if (nft_dump_register(skb, NFTA_LOOKUP_SREG, priv->sreg))
goto nla_put_failure;
- if (priv->set->flags & NFT_SET_MAP)
+ if (priv->dreg_set)
if (nft_dump_register(skb, NFTA_LOOKUP_DREG, priv->dreg))
goto nla_put_failure;
if (nla_put_be32(skb, NFTA_LOOKUP_FLAGS, htonl(flags)))
diff --git a/net/netfilter/nft_meta.c b/net/netfilter/nft_meta.c
index e384e0de7a54..8fdc7318c03c 100644
--- a/net/netfilter/nft_meta.c
+++ b/net/netfilter/nft_meta.c
@@ -458,7 +458,7 @@ EXPORT_SYMBOL_GPL(nft_meta_set_eval);
const struct nla_policy nft_meta_policy[NFTA_META_MAX + 1] = {
[NFTA_META_DREG] = { .type = NLA_U32 },
- [NFTA_META_KEY] = { .type = NLA_U32 },
+ [NFTA_META_KEY] = NLA_POLICY_MAX(NLA_BE32, 255),
[NFTA_META_SREG] = { .type = NLA_U32 },
};
EXPORT_SYMBOL_GPL(nft_meta_policy);
diff --git a/net/netfilter/nft_payload.c b/net/netfilter/nft_payload.c
index 3a3c7746e88f..8cb800989947 100644
--- a/net/netfilter/nft_payload.c
+++ b/net/netfilter/nft_payload.c
@@ -171,7 +171,8 @@ void nft_payload_eval(const struct nft_expr *expr,
if (!skb_mac_header_was_set(skb))
goto err;
- if (skb_vlan_tag_present(skb)) {
+ if (skb_vlan_tag_present(skb) &&
+ priv->offset >= offsetof(struct ethhdr, h_proto)) {
if (!nft_payload_copy_vlan(dest, skb,
priv->offset, priv->len))
goto err;
diff --git a/net/netfilter/nft_range.c b/net/netfilter/nft_range.c
index 0566d6aaf1e5..51ae64cd268f 100644
--- a/net/netfilter/nft_range.c
+++ b/net/netfilter/nft_range.c
@@ -42,7 +42,7 @@ void nft_range_eval(const struct nft_expr *expr,
static const struct nla_policy nft_range_policy[NFTA_RANGE_MAX + 1] = {
[NFTA_RANGE_SREG] = { .type = NLA_U32 },
- [NFTA_RANGE_OP] = { .type = NLA_U32 },
+ [NFTA_RANGE_OP] = NLA_POLICY_MAX(NLA_BE32, 255),
[NFTA_RANGE_FROM_DATA] = { .type = NLA_NESTED },
[NFTA_RANGE_TO_DATA] = { .type = NLA_NESTED },
};
diff --git a/net/netfilter/nft_reject.c b/net/netfilter/nft_reject.c
index f2addc844dd2..ed2e668474d6 100644
--- a/net/netfilter/nft_reject.c
+++ b/net/netfilter/nft_reject.c
@@ -18,7 +18,7 @@
#include <linux/icmpv6.h>
const struct nla_policy nft_reject_policy[NFTA_REJECT_MAX + 1] = {
- [NFTA_REJECT_TYPE] = { .type = NLA_U32 },
+ [NFTA_REJECT_TYPE] = NLA_POLICY_MAX(NLA_BE32, 255),
[NFTA_REJECT_ICMP_CODE] = { .type = NLA_U8 },
};
EXPORT_SYMBOL_GPL(nft_reject_policy);
diff --git a/net/netfilter/nft_rt.c b/net/netfilter/nft_rt.c
index 5990fdd7b3cc..35a2c28caa60 100644
--- a/net/netfilter/nft_rt.c
+++ b/net/netfilter/nft_rt.c
@@ -104,7 +104,7 @@ err:
static const struct nla_policy nft_rt_policy[NFTA_RT_MAX + 1] = {
[NFTA_RT_DREG] = { .type = NLA_U32 },
- [NFTA_RT_KEY] = { .type = NLA_U32 },
+ [NFTA_RT_KEY] = NLA_POLICY_MAX(NLA_BE32, 255),
};
static int nft_rt_get_init(const struct nft_ctx *ctx,
diff --git a/net/netfilter/nft_set_pipapo.c b/net/netfilter/nft_set_pipapo.c
index 0452ee586c1c..db526cb7a485 100644
--- a/net/netfilter/nft_set_pipapo.c
+++ b/net/netfilter/nft_set_pipapo.c
@@ -1274,8 +1274,7 @@ static struct nft_pipapo_match *pipapo_clone(struct nft_pipapo_match *old)
struct nft_pipapo_match *new;
int i;
- new = kmalloc(sizeof(*new) + sizeof(*dst) * old->field_count,
- GFP_KERNEL);
+ new = kmalloc(struct_size(new, f, old->field_count), GFP_KERNEL);
if (!new)
return ERR_PTR(-ENOMEM);
@@ -2084,8 +2083,7 @@ static int nft_pipapo_init(const struct nft_set *set,
if (field_count > NFT_PIPAPO_MAX_FIELDS)
return -EINVAL;
- m = kmalloc(sizeof(*priv->match) + sizeof(*f) * field_count,
- GFP_KERNEL);
+ m = kmalloc(struct_size(m, f, field_count), GFP_KERNEL);
if (!m)
return -ENOMEM;
diff --git a/net/netfilter/nft_socket.c b/net/netfilter/nft_socket.c
index 85f8df87efda..84def74698b7 100644
--- a/net/netfilter/nft_socket.c
+++ b/net/netfilter/nft_socket.c
@@ -138,9 +138,9 @@ static void nft_socket_eval(const struct nft_expr *expr,
}
static const struct nla_policy nft_socket_policy[NFTA_SOCKET_MAX + 1] = {
- [NFTA_SOCKET_KEY] = { .type = NLA_U32 },
+ [NFTA_SOCKET_KEY] = NLA_POLICY_MAX(NLA_BE32, 255),
[NFTA_SOCKET_DREG] = { .type = NLA_U32 },
- [NFTA_SOCKET_LEVEL] = { .type = NLA_U32 },
+ [NFTA_SOCKET_LEVEL] = NLA_POLICY_MAX(NLA_BE32, 255),
};
static int nft_socket_init(const struct nft_ctx *ctx,
diff --git a/net/netfilter/nft_tproxy.c b/net/netfilter/nft_tproxy.c
index ea83f661417e..ae15cd693f0e 100644
--- a/net/netfilter/nft_tproxy.c
+++ b/net/netfilter/nft_tproxy.c
@@ -183,7 +183,7 @@ static void nft_tproxy_eval(const struct nft_expr *expr,
}
static const struct nla_policy nft_tproxy_policy[NFTA_TPROXY_MAX + 1] = {
- [NFTA_TPROXY_FAMILY] = { .type = NLA_U32 },
+ [NFTA_TPROXY_FAMILY] = NLA_POLICY_MAX(NLA_BE32, 255),
[NFTA_TPROXY_REG_ADDR] = { .type = NLA_U32 },
[NFTA_TPROXY_REG_PORT] = { .type = NLA_U32 },
};
diff --git a/net/netfilter/nft_tunnel.c b/net/netfilter/nft_tunnel.c
index b059aa541798..9f21953c7433 100644
--- a/net/netfilter/nft_tunnel.c
+++ b/net/netfilter/nft_tunnel.c
@@ -66,9 +66,9 @@ static void nft_tunnel_get_eval(const struct nft_expr *expr,
}
static const struct nla_policy nft_tunnel_policy[NFTA_TUNNEL_MAX + 1] = {
- [NFTA_TUNNEL_KEY] = { .type = NLA_U32 },
+ [NFTA_TUNNEL_KEY] = NLA_POLICY_MAX(NLA_BE32, 255),
[NFTA_TUNNEL_DREG] = { .type = NLA_U32 },
- [NFTA_TUNNEL_MODE] = { .type = NLA_U32 },
+ [NFTA_TUNNEL_MODE] = NLA_POLICY_MAX(NLA_BE32, 255),
};
static int nft_tunnel_get_init(const struct nft_ctx *ctx,
diff --git a/net/netfilter/nft_xfrm.c b/net/netfilter/nft_xfrm.c
index c88fd078a9ae..452f8587adda 100644
--- a/net/netfilter/nft_xfrm.c
+++ b/net/netfilter/nft_xfrm.c
@@ -16,9 +16,9 @@
#include <net/xfrm.h>
static const struct nla_policy nft_xfrm_policy[NFTA_XFRM_MAX + 1] = {
- [NFTA_XFRM_KEY] = { .type = NLA_U32 },
+ [NFTA_XFRM_KEY] = NLA_POLICY_MAX(NLA_BE32, 255),
[NFTA_XFRM_DIR] = { .type = NLA_U8 },
- [NFTA_XFRM_SPNUM] = { .type = NLA_U32 },
+ [NFTA_XFRM_SPNUM] = NLA_POLICY_MAX(NLA_BE32, 255),
[NFTA_XFRM_DREG] = { .type = NLA_U32 },
};
diff --git a/net/netlabel/netlabel_domainhash.h b/net/netlabel/netlabel_domainhash.h
index 9f80972ae39b..7eaa35fdd9bd 100644
--- a/net/netlabel/netlabel_domainhash.h
+++ b/net/netlabel/netlabel_domainhash.h
@@ -57,8 +57,8 @@ struct netlbl_domaddr6_map {
struct netlbl_dom_map {
char *domain;
- u16 family;
struct netlbl_dommap_def def;
+ u16 family;
u32 valid;
struct list_head list;
diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c
index 3a1e0fd5bf14..383631873748 100644
--- a/net/netlink/af_netlink.c
+++ b/net/netlink/af_netlink.c
@@ -1600,6 +1600,7 @@ out:
int netlink_set_err(struct sock *ssk, u32 portid, u32 group, int code)
{
struct netlink_set_err_data info;
+ unsigned long flags;
struct sock *sk;
int ret = 0;
@@ -1609,12 +1610,12 @@ int netlink_set_err(struct sock *ssk, u32 portid, u32 group, int code)
/* sk->sk_err wants a positive error value */
info.code = -code;
- read_lock(&nl_table_lock);
+ read_lock_irqsave(&nl_table_lock, flags);
sk_for_each_bound(sk, &nl_table[ssk->sk_protocol].mc_list)
ret += do_one_set_err(sk, &info);
- read_unlock(&nl_table_lock);
+ read_unlock_irqrestore(&nl_table_lock, flags);
return ret;
}
EXPORT_SYMBOL(netlink_set_err);
@@ -2360,7 +2361,9 @@ int __netlink_dump_start(struct sock *ssk, struct sk_buff *skb,
cb->strict_check = !!(nlk2->flags & NETLINK_F_STRICT_CHK);
if (control->start) {
+ cb->extack = control->extack;
ret = control->start(cb);
+ cb->extack = NULL;
if (ret)
goto error_put;
}
@@ -2813,7 +2816,6 @@ static const struct proto_ops netlink_ops = {
.sendmsg = netlink_sendmsg,
.recvmsg = netlink_recvmsg,
.mmap = sock_no_mmap,
- .sendpage = sock_no_sendpage,
};
static const struct net_proto_family netlink_family_ops = {
diff --git a/net/netlink/diag.c b/net/netlink/diag.c
index c6255eac305c..e4f21b1067bc 100644
--- a/net/netlink/diag.c
+++ b/net/netlink/diag.c
@@ -94,6 +94,7 @@ static int __netlink_diag_dump(struct sk_buff *skb, struct netlink_callback *cb,
struct net *net = sock_net(skb->sk);
struct netlink_diag_req *req;
struct netlink_sock *nlsk;
+ unsigned long flags;
struct sock *sk;
int num = 2;
int ret = 0;
@@ -152,7 +153,7 @@ static int __netlink_diag_dump(struct sk_buff *skb, struct netlink_callback *cb,
num++;
mc_list:
- read_lock(&nl_table_lock);
+ read_lock_irqsave(&nl_table_lock, flags);
sk_for_each_bound(sk, &tbl->mc_list) {
if (sk_hashed(sk))
continue;
@@ -167,13 +168,13 @@ mc_list:
NETLINK_CB(cb->skb).portid,
cb->nlh->nlmsg_seq,
NLM_F_MULTI,
- sock_i_ino(sk)) < 0) {
+ __sock_i_ino(sk)) < 0) {
ret = 1;
break;
}
num++;
}
- read_unlock(&nl_table_lock);
+ read_unlock_irqrestore(&nl_table_lock, flags);
done:
cb->args[0] = num;
diff --git a/net/netlink/genetlink.c b/net/netlink/genetlink.c
index 04c4036bf406..a157247a1e45 100644
--- a/net/netlink/genetlink.c
+++ b/net/netlink/genetlink.c
@@ -912,6 +912,7 @@ static int genl_family_rcv_msg_dumpit(const struct genl_family *family,
.start = genl_start,
.dump = genl_lock_dumpit,
.done = genl_lock_done,
+ .extack = extack,
};
genl_unlock();
@@ -924,6 +925,7 @@ static int genl_family_rcv_msg_dumpit(const struct genl_family *family,
.start = genl_start,
.dump = ops->dumpit,
.done = genl_parallel_done,
+ .extack = extack,
};
err = __netlink_dump_start(net->genl_sock, skb, nlh, &c);
diff --git a/net/netrom/af_netrom.c b/net/netrom/af_netrom.c
index 5a4cb796150f..eb8ccbd58df7 100644
--- a/net/netrom/af_netrom.c
+++ b/net/netrom/af_netrom.c
@@ -1364,7 +1364,6 @@ static const struct proto_ops nr_proto_ops = {
.sendmsg = nr_sendmsg,
.recvmsg = nr_recvmsg,
.mmap = sock_no_mmap,
- .sendpage = sock_no_sendpage,
};
static struct notifier_block nr_dev_notifier = {
diff --git a/net/nfc/llcp.h b/net/nfc/llcp.h
index c1d9be636933..d8345ed57c95 100644
--- a/net/nfc/llcp.h
+++ b/net/nfc/llcp.h
@@ -201,7 +201,6 @@ void nfc_llcp_sock_link(struct llcp_sock_list *l, struct sock *s);
void nfc_llcp_sock_unlink(struct llcp_sock_list *l, struct sock *s);
void nfc_llcp_socket_remote_param_init(struct nfc_llcp_sock *sock);
struct nfc_llcp_local *nfc_llcp_find_local(struct nfc_dev *dev);
-struct nfc_llcp_local *nfc_llcp_local_get(struct nfc_llcp_local *local);
int nfc_llcp_local_put(struct nfc_llcp_local *local);
u8 nfc_llcp_get_sdp_ssap(struct nfc_llcp_local *local,
struct nfc_llcp_sock *sock);
diff --git a/net/nfc/llcp_commands.c b/net/nfc/llcp_commands.c
index 41e3a20c8935..e2680a3bef79 100644
--- a/net/nfc/llcp_commands.c
+++ b/net/nfc/llcp_commands.c
@@ -359,6 +359,7 @@ int nfc_llcp_send_symm(struct nfc_dev *dev)
struct sk_buff *skb;
struct nfc_llcp_local *local;
u16 size = 0;
+ int err;
local = nfc_llcp_find_local(dev);
if (local == NULL)
@@ -368,8 +369,10 @@ int nfc_llcp_send_symm(struct nfc_dev *dev)
size += dev->tx_headroom + dev->tx_tailroom + NFC_HEADER_SIZE;
skb = alloc_skb(size, GFP_KERNEL);
- if (skb == NULL)
- return -ENOMEM;
+ if (skb == NULL) {
+ err = -ENOMEM;
+ goto out;
+ }
skb_reserve(skb, dev->tx_headroom + NFC_HEADER_SIZE);
@@ -379,8 +382,11 @@ int nfc_llcp_send_symm(struct nfc_dev *dev)
nfc_llcp_send_to_raw_sock(local, skb, NFC_DIRECTION_TX);
- return nfc_data_exchange(dev, local->target_idx, skb,
+ err = nfc_data_exchange(dev, local->target_idx, skb,
nfc_llcp_recv, local);
+out:
+ nfc_llcp_local_put(local);
+ return err;
}
int nfc_llcp_send_connect(struct nfc_llcp_sock *sock)
@@ -390,7 +396,8 @@ int nfc_llcp_send_connect(struct nfc_llcp_sock *sock)
const u8 *service_name_tlv = NULL;
const u8 *miux_tlv = NULL;
const u8 *rw_tlv = NULL;
- u8 service_name_tlv_length, miux_tlv_length, rw_tlv_length, rw;
+ u8 service_name_tlv_length = 0;
+ u8 miux_tlv_length, rw_tlv_length, rw;
int err;
u16 size = 0;
__be16 miux;
diff --git a/net/nfc/llcp_core.c b/net/nfc/llcp_core.c
index a27e1842b2a0..f60e424e0607 100644
--- a/net/nfc/llcp_core.c
+++ b/net/nfc/llcp_core.c
@@ -17,6 +17,8 @@
static u8 llcp_magic[3] = {0x46, 0x66, 0x6d};
static LIST_HEAD(llcp_devices);
+/* Protects llcp_devices list */
+static DEFINE_SPINLOCK(llcp_devices_lock);
static void nfc_llcp_rx_skb(struct nfc_llcp_local *local, struct sk_buff *skb);
@@ -141,7 +143,7 @@ static void nfc_llcp_socket_release(struct nfc_llcp_local *local, bool device,
write_unlock(&local->raw_sockets.lock);
}
-struct nfc_llcp_local *nfc_llcp_local_get(struct nfc_llcp_local *local)
+static struct nfc_llcp_local *nfc_llcp_local_get(struct nfc_llcp_local *local)
{
kref_get(&local->ref);
@@ -169,7 +171,6 @@ static void local_release(struct kref *ref)
local = container_of(ref, struct nfc_llcp_local, ref);
- list_del(&local->list);
local_cleanup(local);
kfree(local);
}
@@ -282,12 +283,33 @@ static void nfc_llcp_sdreq_timer(struct timer_list *t)
struct nfc_llcp_local *nfc_llcp_find_local(struct nfc_dev *dev)
{
struct nfc_llcp_local *local;
+ struct nfc_llcp_local *res = NULL;
+ spin_lock(&llcp_devices_lock);
list_for_each_entry(local, &llcp_devices, list)
- if (local->dev == dev)
+ if (local->dev == dev) {
+ res = nfc_llcp_local_get(local);
+ break;
+ }
+ spin_unlock(&llcp_devices_lock);
+
+ return res;
+}
+
+static struct nfc_llcp_local *nfc_llcp_remove_local(struct nfc_dev *dev)
+{
+ struct nfc_llcp_local *local, *tmp;
+
+ spin_lock(&llcp_devices_lock);
+ list_for_each_entry_safe(local, tmp, &llcp_devices, list)
+ if (local->dev == dev) {
+ list_del(&local->list);
+ spin_unlock(&llcp_devices_lock);
return local;
+ }
+ spin_unlock(&llcp_devices_lock);
- pr_debug("No device found\n");
+ pr_warn("Shutting down device not found\n");
return NULL;
}
@@ -608,12 +630,15 @@ u8 *nfc_llcp_general_bytes(struct nfc_dev *dev, size_t *general_bytes_len)
*general_bytes_len = local->gb_len;
+ nfc_llcp_local_put(local);
+
return local->gb;
}
int nfc_llcp_set_remote_gb(struct nfc_dev *dev, const u8 *gb, u8 gb_len)
{
struct nfc_llcp_local *local;
+ int err;
if (gb_len < 3 || gb_len > NFC_MAX_GT_LEN)
return -EINVAL;
@@ -630,12 +655,16 @@ int nfc_llcp_set_remote_gb(struct nfc_dev *dev, const u8 *gb, u8 gb_len)
if (memcmp(local->remote_gb, llcp_magic, 3)) {
pr_err("MAC does not support LLCP\n");
- return -EINVAL;
+ err = -EINVAL;
+ goto out;
}
- return nfc_llcp_parse_gb_tlv(local,
+ err = nfc_llcp_parse_gb_tlv(local,
&local->remote_gb[3],
local->remote_gb_len - 3);
+out:
+ nfc_llcp_local_put(local);
+ return err;
}
static u8 nfc_llcp_dsap(const struct sk_buff *pdu)
@@ -1517,6 +1546,8 @@ int nfc_llcp_data_received(struct nfc_dev *dev, struct sk_buff *skb)
__nfc_llcp_recv(local, skb);
+ nfc_llcp_local_put(local);
+
return 0;
}
@@ -1533,6 +1564,8 @@ void nfc_llcp_mac_is_down(struct nfc_dev *dev)
/* Close and purge all existing sockets */
nfc_llcp_socket_release(local, true, 0);
+
+ nfc_llcp_local_put(local);
}
void nfc_llcp_mac_is_up(struct nfc_dev *dev, u32 target_idx,
@@ -1558,6 +1591,8 @@ void nfc_llcp_mac_is_up(struct nfc_dev *dev, u32 target_idx,
mod_timer(&local->link_timer,
jiffies + msecs_to_jiffies(local->remote_lto));
}
+
+ nfc_llcp_local_put(local);
}
int nfc_llcp_register_device(struct nfc_dev *ndev)
@@ -1608,7 +1643,7 @@ int nfc_llcp_register_device(struct nfc_dev *ndev)
void nfc_llcp_unregister_device(struct nfc_dev *dev)
{
- struct nfc_llcp_local *local = nfc_llcp_find_local(dev);
+ struct nfc_llcp_local *local = nfc_llcp_remove_local(dev);
if (local == NULL) {
pr_debug("No such device\n");
diff --git a/net/nfc/llcp_sock.c b/net/nfc/llcp_sock.c
index 77642d18a3b4..645677f84dba 100644
--- a/net/nfc/llcp_sock.c
+++ b/net/nfc/llcp_sock.c
@@ -99,7 +99,7 @@ static int llcp_sock_bind(struct socket *sock, struct sockaddr *addr, int alen)
}
llcp_sock->dev = dev;
- llcp_sock->local = nfc_llcp_local_get(local);
+ llcp_sock->local = local;
llcp_sock->nfc_protocol = llcp_addr.nfc_protocol;
llcp_sock->service_name_len = min_t(unsigned int,
llcp_addr.service_name_len,
@@ -186,7 +186,7 @@ static int llcp_raw_sock_bind(struct socket *sock, struct sockaddr *addr,
}
llcp_sock->dev = dev;
- llcp_sock->local = nfc_llcp_local_get(local);
+ llcp_sock->local = local;
llcp_sock->nfc_protocol = llcp_addr.nfc_protocol;
nfc_llcp_sock_link(&local->raw_sockets, sk);
@@ -696,22 +696,22 @@ static int llcp_sock_connect(struct socket *sock, struct sockaddr *_addr,
if (dev->dep_link_up == false) {
ret = -ENOLINK;
device_unlock(&dev->dev);
- goto put_dev;
+ goto sock_llcp_put_local;
}
device_unlock(&dev->dev);
if (local->rf_mode == NFC_RF_INITIATOR &&
addr->target_idx != local->target_idx) {
ret = -ENOLINK;
- goto put_dev;
+ goto sock_llcp_put_local;
}
llcp_sock->dev = dev;
- llcp_sock->local = nfc_llcp_local_get(local);
+ llcp_sock->local = local;
llcp_sock->ssap = nfc_llcp_get_local_ssap(local);
if (llcp_sock->ssap == LLCP_SAP_MAX) {
ret = -ENOMEM;
- goto sock_llcp_put_local;
+ goto sock_llcp_nullify;
}
llcp_sock->reserved_ssap = llcp_sock->ssap;
@@ -757,11 +757,13 @@ sock_unlink:
sock_llcp_release:
nfc_llcp_put_ssap(local, llcp_sock->ssap);
-sock_llcp_put_local:
- nfc_llcp_local_put(llcp_sock->local);
+sock_llcp_nullify:
llcp_sock->local = NULL;
llcp_sock->dev = NULL;
+sock_llcp_put_local:
+ nfc_llcp_local_put(local);
+
put_dev:
nfc_put_device(dev);
diff --git a/net/nfc/netlink.c b/net/nfc/netlink.c
index b9264e730fd9..e9ac6a6f934e 100644
--- a/net/nfc/netlink.c
+++ b/net/nfc/netlink.c
@@ -1039,11 +1039,14 @@ static int nfc_genl_llc_get_params(struct sk_buff *skb, struct genl_info *info)
msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
if (!msg) {
rc = -ENOMEM;
- goto exit;
+ goto put_local;
}
rc = nfc_genl_send_params(msg, local, info->snd_portid, info->snd_seq);
+put_local:
+ nfc_llcp_local_put(local);
+
exit:
device_unlock(&dev->dev);
@@ -1105,7 +1108,7 @@ static int nfc_genl_llc_set_params(struct sk_buff *skb, struct genl_info *info)
if (info->attrs[NFC_ATTR_LLC_PARAM_LTO]) {
if (dev->dep_link_up) {
rc = -EINPROGRESS;
- goto exit;
+ goto put_local;
}
local->lto = nla_get_u8(info->attrs[NFC_ATTR_LLC_PARAM_LTO]);
@@ -1117,6 +1120,9 @@ static int nfc_genl_llc_set_params(struct sk_buff *skb, struct genl_info *info)
if (info->attrs[NFC_ATTR_LLC_PARAM_MIUX])
local->miux = cpu_to_be16(miux);
+put_local:
+ nfc_llcp_local_put(local);
+
exit:
device_unlock(&dev->dev);
@@ -1172,7 +1178,7 @@ static int nfc_genl_llc_sdreq(struct sk_buff *skb, struct genl_info *info)
if (rc != 0) {
rc = -EINVAL;
- goto exit;
+ goto put_local;
}
if (!sdp_attrs[NFC_SDP_ATTR_URI])
@@ -1191,7 +1197,7 @@ static int nfc_genl_llc_sdreq(struct sk_buff *skb, struct genl_info *info)
sdreq = nfc_llcp_build_sdreq_tlv(tid, uri, uri_len);
if (sdreq == NULL) {
rc = -ENOMEM;
- goto exit;
+ goto put_local;
}
tlvs_len += sdreq->tlv_len;
@@ -1201,10 +1207,14 @@ static int nfc_genl_llc_sdreq(struct sk_buff *skb, struct genl_info *info)
if (hlist_empty(&sdreq_list)) {
rc = -EINVAL;
- goto exit;
+ goto put_local;
}
rc = nfc_llcp_send_snl_sdreq(local, &sdreq_list, tlvs_len);
+
+put_local:
+ nfc_llcp_local_put(local);
+
exit:
device_unlock(&dev->dev);
diff --git a/net/nfc/nfc.h b/net/nfc/nfc.h
index de2ec66d7e83..0b1e6466f4fb 100644
--- a/net/nfc/nfc.h
+++ b/net/nfc/nfc.h
@@ -52,6 +52,7 @@ int nfc_llcp_set_remote_gb(struct nfc_dev *dev, const u8 *gb, u8 gb_len);
u8 *nfc_llcp_general_bytes(struct nfc_dev *dev, size_t *general_bytes_len);
int nfc_llcp_data_received(struct nfc_dev *dev, struct sk_buff *skb);
struct nfc_llcp_local *nfc_llcp_find_local(struct nfc_dev *dev);
+int nfc_llcp_local_put(struct nfc_llcp_local *local);
int __init nfc_llcp_init(void);
void nfc_llcp_exit(void);
void nfc_llcp_free_sdp_tlv(struct nfc_llcp_sdp_tlv *sdp);
diff --git a/net/nsh/nsh.c b/net/nsh/nsh.c
index 0f23e5e8e03e..f4a38bd6a7e0 100644
--- a/net/nsh/nsh.c
+++ b/net/nsh/nsh.c
@@ -8,6 +8,7 @@
#include <linux/module.h>
#include <linux/netdevice.h>
#include <linux/skbuff.h>
+#include <net/gso.h>
#include <net/nsh.h>
#include <net/tun_proto.h>
diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c
index a8cf9a88758e..cab1e02b63e0 100644
--- a/net/openvswitch/actions.c
+++ b/net/openvswitch/actions.c
@@ -17,6 +17,7 @@
#include <linux/if_vlan.h>
#include <net/dst.h>
+#include <net/gso.h>
#include <net/ip.h>
#include <net/ipv6.h>
#include <net/ip6_fib.h>
@@ -1072,8 +1073,16 @@ static void execute_hash(struct sk_buff *skb, struct sw_flow_key *key,
struct ovs_action_hash *hash_act = nla_data(attr);
u32 hash = 0;
- /* OVS_HASH_ALG_L4 is the only possible hash algorithm. */
- hash = skb_get_hash(skb);
+ if (hash_act->hash_alg == OVS_HASH_ALG_L4) {
+ /* OVS_HASH_ALG_L4 hasing type. */
+ hash = skb_get_hash(skb);
+ } else if (hash_act->hash_alg == OVS_HASH_ALG_SYM_L4) {
+ /* OVS_HASH_ALG_SYM_L4 hashing type. NOTE: this doesn't
+ * extend past an encapsulated header.
+ */
+ hash = __skb_get_hash_symmetric(skb);
+ }
+
hash = jhash_1word(hash, hash_act->hash_basis);
if (!hash)
hash = 0x1;
diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c
index 58f530f60172..a6d2a0b1aa21 100644
--- a/net/openvswitch/datapath.c
+++ b/net/openvswitch/datapath.c
@@ -35,6 +35,7 @@
#include <linux/rculist.h>
#include <linux/dmi.h>
#include <net/genetlink.h>
+#include <net/gso.h>
#include <net/net_namespace.h>
#include <net/netns/generic.h>
#include <net/pkt_cls.h>
diff --git a/net/openvswitch/flow_netlink.c b/net/openvswitch/flow_netlink.c
index ead5418c126e..41116361433d 100644
--- a/net/openvswitch/flow_netlink.c
+++ b/net/openvswitch/flow_netlink.c
@@ -3221,6 +3221,8 @@ static int __ovs_nla_copy_actions(struct net *net, const struct nlattr *attr,
switch (act_hash->hash_alg) {
case OVS_HASH_ALG_L4:
+ fallthrough;
+ case OVS_HASH_ALG_SYM_L4:
break;
default:
return -EINVAL;
diff --git a/net/openvswitch/meter.c b/net/openvswitch/meter.c
index f2698d2316df..c4ebf810e4b1 100644
--- a/net/openvswitch/meter.c
+++ b/net/openvswitch/meter.c
@@ -69,9 +69,7 @@ static struct dp_meter_instance *dp_meter_instance_alloc(const u32 size)
{
struct dp_meter_instance *ti;
- ti = kvzalloc(sizeof(*ti) +
- sizeof(struct dp_meter *) * size,
- GFP_KERNEL);
+ ti = kvzalloc(struct_size(ti, dp_meters, size), GFP_KERNEL);
if (!ti)
return NULL;
diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index a2dbeb264f26..85ff90a03b0c 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -4621,7 +4621,6 @@ static const struct proto_ops packet_ops_spkt = {
.sendmsg = packet_sendmsg_spkt,
.recvmsg = packet_recvmsg,
.mmap = sock_no_mmap,
- .sendpage = sock_no_sendpage,
};
static const struct proto_ops packet_ops = {
@@ -4643,7 +4642,6 @@ static const struct proto_ops packet_ops = {
.sendmsg = packet_sendmsg,
.recvmsg = packet_recvmsg,
.mmap = packet_mmap,
- .sendpage = sock_no_sendpage,
};
static const struct net_proto_family packet_family_ops = {
diff --git a/net/phonet/datagram.c b/net/phonet/datagram.c
index ff5f49ab236e..3aa50dc7535b 100644
--- a/net/phonet/datagram.c
+++ b/net/phonet/datagram.c
@@ -28,24 +28,21 @@ static void pn_sock_close(struct sock *sk, long timeout)
sk_common_release(sk);
}
-static int pn_ioctl(struct sock *sk, int cmd, unsigned long arg)
+static int pn_ioctl(struct sock *sk, int cmd, int *karg)
{
struct sk_buff *skb;
- int answ;
switch (cmd) {
case SIOCINQ:
lock_sock(sk);
skb = skb_peek(&sk->sk_receive_queue);
- answ = skb ? skb->len : 0;
+ *karg = skb ? skb->len : 0;
release_sock(sk);
- return put_user(answ, (int __user *)arg);
+ return 0;
case SIOCPNADDRESOURCE:
case SIOCPNDELRESOURCE: {
- u32 res;
- if (get_user(res, (u32 __user *)arg))
- return -EFAULT;
+ u32 res = *karg;
if (res >= 256)
return -EINVAL;
if (cmd == SIOCPNADDRESOURCE)
diff --git a/net/phonet/pep.c b/net/phonet/pep.c
index 83ea13a50690..faba31f2eff2 100644
--- a/net/phonet/pep.c
+++ b/net/phonet/pep.c
@@ -917,10 +917,9 @@ static int pep_sock_enable(struct sock *sk, struct sockaddr *addr, int len)
return 0;
}
-static int pep_ioctl(struct sock *sk, int cmd, unsigned long arg)
+static int pep_ioctl(struct sock *sk, int cmd, int *karg)
{
struct pep_sock *pn = pep_sk(sk);
- int answ;
int ret = -ENOIOCTLCMD;
switch (cmd) {
@@ -933,13 +932,13 @@ static int pep_ioctl(struct sock *sk, int cmd, unsigned long arg)
lock_sock(sk);
if (sock_flag(sk, SOCK_URGINLINE) &&
!skb_queue_empty(&pn->ctrlreq_queue))
- answ = skb_peek(&pn->ctrlreq_queue)->len;
+ *karg = skb_peek(&pn->ctrlreq_queue)->len;
else if (!skb_queue_empty(&sk->sk_receive_queue))
- answ = skb_peek(&sk->sk_receive_queue)->len;
+ *karg = skb_peek(&sk->sk_receive_queue)->len;
else
- answ = 0;
+ *karg = 0;
release_sock(sk);
- ret = put_user(answ, (int __user *)arg);
+ ret = 0;
break;
case SIOCPNENABLEPIPE:
diff --git a/net/phonet/socket.c b/net/phonet/socket.c
index 71e2caf6ab85..1018340d89a7 100644
--- a/net/phonet/socket.c
+++ b/net/phonet/socket.c
@@ -387,7 +387,7 @@ static int pn_socket_ioctl(struct socket *sock, unsigned int cmd,
return put_user(handle, (__u16 __user *)arg);
}
- return sk->sk_prot->ioctl(sk, cmd, arg);
+ return sk_ioctl(sk, cmd, (void __user *)arg);
}
static int pn_socket_listen(struct socket *sock, int backlog)
@@ -441,7 +441,6 @@ const struct proto_ops phonet_dgram_ops = {
.sendmsg = pn_socket_sendmsg,
.recvmsg = sock_common_recvmsg,
.mmap = sock_no_mmap,
- .sendpage = sock_no_sendpage,
};
const struct proto_ops phonet_stream_ops = {
@@ -462,7 +461,6 @@ const struct proto_ops phonet_stream_ops = {
.sendmsg = pn_socket_sendmsg,
.recvmsg = sock_common_recvmsg,
.mmap = sock_no_mmap,
- .sendpage = sock_no_sendpage,
};
EXPORT_SYMBOL(phonet_stream_ops);
diff --git a/net/qrtr/af_qrtr.c b/net/qrtr/af_qrtr.c
index 76f0434d3d06..78beb74146e7 100644
--- a/net/qrtr/af_qrtr.c
+++ b/net/qrtr/af_qrtr.c
@@ -1244,7 +1244,6 @@ static const struct proto_ops qrtr_proto_ops = {
.shutdown = sock_no_shutdown,
.release = qrtr_release,
.mmap = sock_no_mmap,
- .sendpage = sock_no_sendpage,
};
static struct proto qrtr_proto = {
diff --git a/net/rds/af_rds.c b/net/rds/af_rds.c
index 3ff6995244e5..01c4cdfef45d 100644
--- a/net/rds/af_rds.c
+++ b/net/rds/af_rds.c
@@ -653,7 +653,6 @@ static const struct proto_ops rds_proto_ops = {
.sendmsg = rds_sendmsg,
.recvmsg = rds_recvmsg,
.mmap = sock_no_mmap,
- .sendpage = sock_no_sendpage,
};
static void rds_sock_destruct(struct sock *sk)
diff --git a/net/rds/tcp_send.c b/net/rds/tcp_send.c
index 8c4d1d6e9249..7d284ac7e81a 100644
--- a/net/rds/tcp_send.c
+++ b/net/rds/tcp_send.c
@@ -72,9 +72,10 @@ int rds_tcp_xmit(struct rds_connection *conn, struct rds_message *rm,
{
struct rds_conn_path *cp = rm->m_inc.i_conn_path;
struct rds_tcp_connection *tc = cp->cp_transport_data;
+ struct msghdr msg = {};
+ struct bio_vec bvec;
int done = 0;
int ret = 0;
- int more;
if (hdr_off == 0) {
/*
@@ -111,15 +112,17 @@ int rds_tcp_xmit(struct rds_connection *conn, struct rds_message *rm,
goto out;
}
- more = rm->data.op_nents > 1 ? (MSG_MORE | MSG_SENDPAGE_NOTLAST) : 0;
while (sg < rm->data.op_nents) {
- int flags = MSG_DONTWAIT | MSG_NOSIGNAL | more;
-
- ret = tc->t_sock->ops->sendpage(tc->t_sock,
- sg_page(&rm->data.op_sg[sg]),
- rm->data.op_sg[sg].offset + off,
- rm->data.op_sg[sg].length - off,
- flags);
+ msg.msg_flags = MSG_SPLICE_PAGES | MSG_DONTWAIT | MSG_NOSIGNAL;
+ if (sg + 1 < rm->data.op_nents)
+ msg.msg_flags |= MSG_MORE;
+
+ bvec_set_page(&bvec, sg_page(&rm->data.op_sg[sg]),
+ rm->data.op_sg[sg].length - off,
+ rm->data.op_sg[sg].offset + off);
+ iov_iter_bvec(&msg.msg_iter, ITER_SOURCE, &bvec, 1,
+ rm->data.op_sg[sg].length - off);
+ ret = sock_sendmsg(tc->t_sock, &msg);
rdsdebug("tcp sendpage %p:%u:%u ret %d\n", (void *)sg_page(&rm->data.op_sg[sg]),
rm->data.op_sg[sg].offset + off, rm->data.op_sg[sg].length - off,
ret);
@@ -132,8 +135,6 @@ int rds_tcp_xmit(struct rds_connection *conn, struct rds_message *rm,
off = 0;
sg++;
}
- if (sg == rm->data.op_nents - 1)
- more = 0;
}
out:
diff --git a/net/rose/af_rose.c b/net/rose/af_rose.c
index ca2b17f32670..49dafe9ac72f 100644
--- a/net/rose/af_rose.c
+++ b/net/rose/af_rose.c
@@ -1496,7 +1496,6 @@ static const struct proto_ops rose_proto_ops = {
.sendmsg = rose_sendmsg,
.recvmsg = rose_recvmsg,
.mmap = sock_no_mmap,
- .sendpage = sock_no_sendpage,
};
static struct notifier_block rose_dev_notifier = {
diff --git a/net/rxrpc/af_rxrpc.c b/net/rxrpc/af_rxrpc.c
index 4c471fa7e09a..fa8aec78f63d 100644
--- a/net/rxrpc/af_rxrpc.c
+++ b/net/rxrpc/af_rxrpc.c
@@ -954,7 +954,6 @@ static const struct proto_ops rxrpc_rpc_ops = {
.sendmsg = rxrpc_sendmsg,
.recvmsg = rxrpc_recvmsg,
.mmap = sock_no_mmap,
- .sendpage = sock_no_sendpage,
};
static struct proto rxrpc_proto = {
diff --git a/net/sched/act_pedit.c b/net/sched/act_pedit.c
index c819b812a899..b562fc2bb5b1 100644
--- a/net/sched/act_pedit.c
+++ b/net/sched/act_pedit.c
@@ -245,14 +245,12 @@ static int tcf_pedit_init(struct net *net, struct nlattr *nla,
nparms->tcfp_flags = parm->flags;
nparms->tcfp_nkeys = parm->nkeys;
- nparms->tcfp_keys = kmalloc(ksize, GFP_KERNEL);
+ nparms->tcfp_keys = kmemdup(parm->keys, ksize, GFP_KERNEL);
if (!nparms->tcfp_keys) {
ret = -ENOMEM;
goto put_chain;
}
- memcpy(nparms->tcfp_keys, parm->keys, ksize);
-
for (i = 0; i < nparms->tcfp_nkeys; ++i) {
u32 offmask = nparms->tcfp_keys[i].offmask;
u32 cur = nparms->tcfp_keys[i].off;
diff --git a/net/sched/act_police.c b/net/sched/act_police.c
index 2e9dce03d1ec..f3121c5a85e9 100644
--- a/net/sched/act_police.c
+++ b/net/sched/act_police.c
@@ -16,6 +16,7 @@
#include <linux/init.h>
#include <linux/slab.h>
#include <net/act_api.h>
+#include <net/gso.h>
#include <net/netlink.h>
#include <net/pkt_cls.h>
#include <net/tc_act/tc_police.h>
diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c
index 815c3e416bc5..56065cc5a661 100644
--- a/net/sched/cls_flower.c
+++ b/net/sched/cls_flower.c
@@ -11,6 +11,7 @@
#include <linux/rhashtable.h>
#include <linux/workqueue.h>
#include <linux/refcount.h>
+#include <linux/bitfield.h>
#include <linux/if_ether.h>
#include <linux/in6.h>
@@ -71,6 +72,7 @@ struct fl_flow_key {
struct flow_dissector_key_num_of_vlans num_of_vlans;
struct flow_dissector_key_pppoe pppoe;
struct flow_dissector_key_l2tpv3 l2tpv3;
+ struct flow_dissector_key_cfm cfm;
} __aligned(BITS_PER_LONG / 8); /* Ensure that we can do comparisons as longs. */
struct fl_flow_mask_range {
@@ -120,6 +122,7 @@ struct cls_fl_filter {
u32 handle;
u32 flags;
u32 in_hw_count;
+ u8 needs_tc_skb_ext:1;
struct rcu_work rwork;
struct net_device *hw_dev;
/* Flower classifier is unlocked, which means that its reference counter
@@ -415,6 +418,8 @@ static struct cls_fl_head *fl_head_dereference(struct tcf_proto *tp)
static void __fl_destroy_filter(struct cls_fl_filter *f)
{
+ if (f->needs_tc_skb_ext)
+ tc_skb_ext_tc_disable();
tcf_exts_destroy(&f->exts);
tcf_exts_put_net(&f->exts);
kfree(f);
@@ -615,7 +620,8 @@ static void *fl_get(struct tcf_proto *tp, u32 handle)
}
static const struct nla_policy fl_policy[TCA_FLOWER_MAX + 1] = {
- [TCA_FLOWER_UNSPEC] = { .type = NLA_UNSPEC },
+ [TCA_FLOWER_UNSPEC] = { .strict_start_type =
+ TCA_FLOWER_L2_MISS },
[TCA_FLOWER_CLASSID] = { .type = NLA_U32 },
[TCA_FLOWER_INDEV] = { .type = NLA_STRING,
.len = IFNAMSIZ },
@@ -720,7 +726,8 @@ static const struct nla_policy fl_policy[TCA_FLOWER_MAX + 1] = {
[TCA_FLOWER_KEY_PPPOE_SID] = { .type = NLA_U16 },
[TCA_FLOWER_KEY_PPP_PROTO] = { .type = NLA_U16 },
[TCA_FLOWER_KEY_L2TPV3_SID] = { .type = NLA_U32 },
-
+ [TCA_FLOWER_L2_MISS] = NLA_POLICY_MAX(NLA_U8, 1),
+ [TCA_FLOWER_KEY_CFM] = { .type = NLA_NESTED },
};
static const struct nla_policy
@@ -769,6 +776,12 @@ mpls_stack_entry_policy[TCA_FLOWER_KEY_MPLS_OPT_LSE_MAX + 1] = {
[TCA_FLOWER_KEY_MPLS_OPT_LSE_LABEL] = { .type = NLA_U32 },
};
+static const struct nla_policy cfm_opt_policy[TCA_FLOWER_KEY_CFM_OPT_MAX] = {
+ [TCA_FLOWER_KEY_CFM_MD_LEVEL] = NLA_POLICY_MAX(NLA_U8,
+ FLOW_DIS_CFM_MDL_MAX),
+ [TCA_FLOWER_KEY_CFM_OPCODE] = { .type = NLA_U8 },
+};
+
static void fl_set_key_val(struct nlattr **tb,
void *val, int val_type,
void *mask, int mask_type, int len)
@@ -1656,6 +1669,53 @@ static bool is_vlan_key(struct nlattr *tb, __be16 *ethertype,
return false;
}
+static void fl_set_key_cfm_md_level(struct nlattr **tb,
+ struct fl_flow_key *key,
+ struct fl_flow_key *mask,
+ struct netlink_ext_ack *extack)
+{
+ u8 level;
+
+ if (!tb[TCA_FLOWER_KEY_CFM_MD_LEVEL])
+ return;
+
+ level = nla_get_u8(tb[TCA_FLOWER_KEY_CFM_MD_LEVEL]);
+ key->cfm.mdl_ver = FIELD_PREP(FLOW_DIS_CFM_MDL_MASK, level);
+ mask->cfm.mdl_ver = FLOW_DIS_CFM_MDL_MASK;
+}
+
+static void fl_set_key_cfm_opcode(struct nlattr **tb,
+ struct fl_flow_key *key,
+ struct fl_flow_key *mask,
+ struct netlink_ext_ack *extack)
+{
+ fl_set_key_val(tb, &key->cfm.opcode, TCA_FLOWER_KEY_CFM_OPCODE,
+ &mask->cfm.opcode, TCA_FLOWER_UNSPEC,
+ sizeof(key->cfm.opcode));
+}
+
+static int fl_set_key_cfm(struct nlattr **tb,
+ struct fl_flow_key *key,
+ struct fl_flow_key *mask,
+ struct netlink_ext_ack *extack)
+{
+ struct nlattr *nla_cfm_opt[TCA_FLOWER_KEY_CFM_OPT_MAX];
+ int err;
+
+ if (!tb[TCA_FLOWER_KEY_CFM])
+ return 0;
+
+ err = nla_parse_nested(nla_cfm_opt, TCA_FLOWER_KEY_CFM_OPT_MAX,
+ tb[TCA_FLOWER_KEY_CFM], cfm_opt_policy, extack);
+ if (err < 0)
+ return err;
+
+ fl_set_key_cfm_opcode(nla_cfm_opt, key, mask, extack);
+ fl_set_key_cfm_md_level(nla_cfm_opt, key, mask, extack);
+
+ return 0;
+}
+
static int fl_set_key(struct net *net, struct nlattr **tb,
struct fl_flow_key *key, struct fl_flow_key *mask,
struct netlink_ext_ack *extack)
@@ -1671,6 +1731,10 @@ static int fl_set_key(struct net *net, struct nlattr **tb,
mask->meta.ingress_ifindex = 0xffffffff;
}
+ fl_set_key_val(tb, &key->meta.l2_miss, TCA_FLOWER_L2_MISS,
+ &mask->meta.l2_miss, TCA_FLOWER_UNSPEC,
+ sizeof(key->meta.l2_miss));
+
fl_set_key_val(tb, key->eth.dst, TCA_FLOWER_KEY_ETH_DST,
mask->eth.dst, TCA_FLOWER_KEY_ETH_DST_MASK,
sizeof(key->eth.dst));
@@ -1806,6 +1870,10 @@ static int fl_set_key(struct net *net, struct nlattr **tb,
TCA_FLOWER_KEY_L2TPV3_SID,
&mask->l2tpv3.session_id, TCA_FLOWER_UNSPEC,
sizeof(key->l2tpv3.session_id));
+ } else if (key->basic.n_proto == htons(ETH_P_CFM)) {
+ ret = fl_set_key_cfm(tb, key, mask, extack);
+ if (ret)
+ return ret;
}
if (key->basic.ip_proto == IPPROTO_TCP ||
@@ -1988,6 +2056,8 @@ static void fl_init_dissector(struct flow_dissector *dissector,
FLOW_DISSECTOR_KEY_PPPOE, pppoe);
FL_KEY_SET_IF_MASKED(mask, keys, cnt,
FLOW_DISSECTOR_KEY_L2TPV3, l2tpv3);
+ FL_KEY_SET_IF_MASKED(mask, keys, cnt,
+ FLOW_DISSECTOR_KEY_CFM, cfm);
skb_flow_dissector_init(dissector, keys, cnt);
}
@@ -2088,6 +2158,11 @@ errout_cleanup:
return ret;
}
+static bool fl_needs_tc_skb_ext(const struct fl_flow_key *mask)
+{
+ return mask->meta.l2_miss;
+}
+
static int fl_set_parms(struct net *net, struct tcf_proto *tp,
struct cls_fl_filter *f, struct fl_flow_mask *mask,
unsigned long base, struct nlattr **tb,
@@ -2124,6 +2199,14 @@ static int fl_set_parms(struct net *net, struct tcf_proto *tp,
return -EINVAL;
}
+ /* Enable tc skb extension if filter matches on data extracted from
+ * this extension.
+ */
+ if (fl_needs_tc_skb_ext(&mask->key)) {
+ f->needs_tc_skb_ext = 1;
+ tc_skb_ext_tc_enable();
+ }
+
return 0;
}
@@ -3008,6 +3091,43 @@ nla_put_failure:
return -EMSGSIZE;
}
+static int fl_dump_key_cfm(struct sk_buff *skb,
+ struct flow_dissector_key_cfm *key,
+ struct flow_dissector_key_cfm *mask)
+{
+ struct nlattr *opts;
+ int err;
+ u8 mdl;
+
+ if (!memchr_inv(mask, 0, sizeof(*mask)))
+ return 0;
+
+ opts = nla_nest_start(skb, TCA_FLOWER_KEY_CFM);
+ if (!opts)
+ return -EMSGSIZE;
+
+ if (FIELD_GET(FLOW_DIS_CFM_MDL_MASK, mask->mdl_ver)) {
+ mdl = FIELD_GET(FLOW_DIS_CFM_MDL_MASK, key->mdl_ver);
+ err = nla_put_u8(skb, TCA_FLOWER_KEY_CFM_MD_LEVEL, mdl);
+ if (err)
+ goto err_cfm_opts;
+ }
+
+ if (mask->opcode) {
+ err = nla_put_u8(skb, TCA_FLOWER_KEY_CFM_OPCODE, key->opcode);
+ if (err)
+ goto err_cfm_opts;
+ }
+
+ nla_nest_end(skb, opts);
+
+ return 0;
+
+err_cfm_opts:
+ nla_nest_cancel(skb, opts);
+ return err;
+}
+
static int fl_dump_key_options(struct sk_buff *skb, int enc_opt_type,
struct flow_dissector_key_enc_opts *enc_opts)
{
@@ -3077,6 +3197,11 @@ static int fl_dump_key(struct sk_buff *skb, struct net *net,
goto nla_put_failure;
}
+ if (fl_dump_key_val(skb, &key->meta.l2_miss,
+ TCA_FLOWER_L2_MISS, &mask->meta.l2_miss,
+ TCA_FLOWER_UNSPEC, sizeof(key->meta.l2_miss)))
+ goto nla_put_failure;
+
if (fl_dump_key_val(skb, key->eth.dst, TCA_FLOWER_KEY_ETH_DST,
mask->eth.dst, TCA_FLOWER_KEY_ETH_DST_MASK,
sizeof(key->eth.dst)) ||
@@ -3290,6 +3415,9 @@ static int fl_dump_key(struct sk_buff *skb, struct net *net,
sizeof(key->hash.hash)))
goto nla_put_failure;
+ if (fl_dump_key_cfm(skb, &key->cfm, &mask->cfm))
+ goto nla_put_failure;
+
return 0;
nla_put_failure:
diff --git a/net/sched/sch_cake.c b/net/sched/sch_cake.c
index 891e007d5c0b..9cff99558694 100644
--- a/net/sched/sch_cake.c
+++ b/net/sched/sch_cake.c
@@ -65,6 +65,7 @@
#include <linux/reciprocal_div.h>
#include <net/netlink.h>
#include <linux/if_vlan.h>
+#include <net/gso.h>
#include <net/pkt_sched.h>
#include <net/pkt_cls.h>
#include <net/tcp.h>
diff --git a/net/sched/sch_htb.c b/net/sched/sch_htb.c
index 8aef7dd9fb88..325c29041c7d 100644
--- a/net/sched/sch_htb.c
+++ b/net/sched/sch_htb.c
@@ -1814,10 +1814,6 @@ static int htb_change_class(struct Qdisc *sch, u32 classid,
NL_SET_ERR_MSG(extack, "HTB offload doesn't support the quantum parameter");
goto failure;
}
- if (hopt->prio) {
- NL_SET_ERR_MSG(extack, "HTB offload doesn't support the prio parameter");
- goto failure;
- }
}
/* Keeping backward compatible with rate_table based iproute2 tc */
@@ -1913,6 +1909,7 @@ static int htb_change_class(struct Qdisc *sch, u32 classid,
TC_HTB_CLASSID_ROOT,
.rate = max_t(u64, hopt->rate.rate, rate64),
.ceil = max_t(u64, hopt->ceil.rate, ceil64),
+ .prio = hopt->prio,
.extack = extack,
};
err = htb_offload(dev, &offload_opt);
@@ -1933,6 +1930,7 @@ static int htb_change_class(struct Qdisc *sch, u32 classid,
TC_H_MIN(parent->common.classid),
.rate = max_t(u64, hopt->rate.rate, rate64),
.ceil = max_t(u64, hopt->ceil.rate, ceil64),
+ .prio = hopt->prio,
.extack = extack,
};
err = htb_offload(dev, &offload_opt);
@@ -2018,6 +2016,7 @@ static int htb_change_class(struct Qdisc *sch, u32 classid,
.classid = cl->common.classid,
.rate = max_t(u64, hopt->rate.rate, rate64),
.ceil = max_t(u64, hopt->ceil.rate, ceil64),
+ .prio = hopt->prio,
.extack = extack,
};
err = htb_offload(dev, &offload_opt);
diff --git a/net/sched/sch_netem.c b/net/sched/sch_netem.c
index e79be1b3e74d..38d9aa0cd30e 100644
--- a/net/sched/sch_netem.c
+++ b/net/sched/sch_netem.c
@@ -21,6 +21,7 @@
#include <linux/reciprocal_div.h>
#include <linux/rbtree.h>
+#include <net/gso.h>
#include <net/netlink.h>
#include <net/pkt_sched.h>
#include <net/inet_ecn.h>
@@ -773,12 +774,10 @@ static void dist_free(struct disttable *d)
* signed 16 bit values.
*/
-static int get_dist_table(struct Qdisc *sch, struct disttable **tbl,
- const struct nlattr *attr)
+static int get_dist_table(struct disttable **tbl, const struct nlattr *attr)
{
size_t n = nla_len(attr)/sizeof(__s16);
const __s16 *data = nla_data(attr);
- spinlock_t *root_lock;
struct disttable *d;
int i;
@@ -793,13 +792,7 @@ static int get_dist_table(struct Qdisc *sch, struct disttable **tbl,
for (i = 0; i < n; i++)
d->table[i] = data[i];
- root_lock = qdisc_root_sleeping_lock(sch);
-
- spin_lock_bh(root_lock);
- swap(*tbl, d);
- spin_unlock_bh(root_lock);
-
- dist_free(d);
+ *tbl = d;
return 0;
}
@@ -956,6 +949,8 @@ static int netem_change(struct Qdisc *sch, struct nlattr *opt,
{
struct netem_sched_data *q = qdisc_priv(sch);
struct nlattr *tb[TCA_NETEM_MAX + 1];
+ struct disttable *delay_dist = NULL;
+ struct disttable *slot_dist = NULL;
struct tc_netem_qopt *qopt;
struct clgstate old_clg;
int old_loss_model = CLG_RANDOM;
@@ -966,6 +961,18 @@ static int netem_change(struct Qdisc *sch, struct nlattr *opt,
if (ret < 0)
return ret;
+ if (tb[TCA_NETEM_DELAY_DIST]) {
+ ret = get_dist_table(&delay_dist, tb[TCA_NETEM_DELAY_DIST]);
+ if (ret)
+ goto table_free;
+ }
+
+ if (tb[TCA_NETEM_SLOT_DIST]) {
+ ret = get_dist_table(&slot_dist, tb[TCA_NETEM_SLOT_DIST]);
+ if (ret)
+ goto table_free;
+ }
+
sch_tree_lock(sch);
/* backup q->clg and q->loss_model */
old_clg = q->clg;
@@ -975,26 +982,17 @@ static int netem_change(struct Qdisc *sch, struct nlattr *opt,
ret = get_loss_clg(q, tb[TCA_NETEM_LOSS]);
if (ret) {
q->loss_model = old_loss_model;
+ q->clg = old_clg;
goto unlock;
}
} else {
q->loss_model = CLG_RANDOM;
}
- if (tb[TCA_NETEM_DELAY_DIST]) {
- ret = get_dist_table(sch, &q->delay_dist,
- tb[TCA_NETEM_DELAY_DIST]);
- if (ret)
- goto get_table_failure;
- }
-
- if (tb[TCA_NETEM_SLOT_DIST]) {
- ret = get_dist_table(sch, &q->slot_dist,
- tb[TCA_NETEM_SLOT_DIST]);
- if (ret)
- goto get_table_failure;
- }
-
+ if (delay_dist)
+ swap(q->delay_dist, delay_dist);
+ if (slot_dist)
+ swap(q->slot_dist, slot_dist);
sch->limit = qopt->limit;
q->latency = PSCHED_TICKS2NS(qopt->latency);
@@ -1044,17 +1042,11 @@ static int netem_change(struct Qdisc *sch, struct nlattr *opt,
unlock:
sch_tree_unlock(sch);
- return ret;
-get_table_failure:
- /* recover clg and loss_model, in case of
- * q->clg and q->loss_model were modified
- * in get_loss_clg()
- */
- q->clg = old_clg;
- q->loss_model = old_loss_model;
-
- goto unlock;
+table_free:
+ dist_free(delay_dist);
+ dist_free(slot_dist);
+ return ret;
}
static int netem_init(struct Qdisc *sch, struct nlattr *opt,
diff --git a/net/sched/sch_taprio.c b/net/sched/sch_taprio.c
index cf0e61ed9225..717ae51d94a0 100644
--- a/net/sched/sch_taprio.c
+++ b/net/sched/sch_taprio.c
@@ -20,6 +20,7 @@
#include <linux/spinlock.h>
#include <linux/rcupdate.h>
#include <linux/time.h>
+#include <net/gso.h>
#include <net/netlink.h>
#include <net/pkt_sched.h>
#include <net/pkt_cls.h>
@@ -27,6 +28,8 @@
#include <net/sock.h>
#include <net/tcp.h>
+#define TAPRIO_STAT_NOT_SET (~0ULL)
+
#include "sch_mqprio_lib.h"
static LIST_HEAD(taprio_list);
@@ -1527,7 +1530,7 @@ static int taprio_enable_offload(struct net_device *dev,
"Not enough memory for enabling offload mode");
return -ENOMEM;
}
- offload->enable = 1;
+ offload->cmd = TAPRIO_CMD_REPLACE;
offload->extack = extack;
mqprio_qopt_reconstruct(dev, &offload->mqprio.qopt);
offload->mqprio.extack = extack;
@@ -1575,7 +1578,7 @@ static int taprio_disable_offload(struct net_device *dev,
"Not enough memory to disable offload mode");
return -ENOMEM;
}
- offload->enable = 0;
+ offload->cmd = TAPRIO_CMD_DESTROY;
err = ops->ndo_setup_tc(dev, TC_SETUP_QDISC_TAPRIO, offload);
if (err < 0) {
@@ -2292,6 +2295,72 @@ nla_put_failure:
return -EMSGSIZE;
}
+static int taprio_put_stat(struct sk_buff *skb, u64 val, u16 attrtype)
+{
+ if (val == TAPRIO_STAT_NOT_SET)
+ return 0;
+ if (nla_put_u64_64bit(skb, attrtype, val, TCA_TAPRIO_OFFLOAD_STATS_PAD))
+ return -EMSGSIZE;
+ return 0;
+}
+
+static int taprio_dump_xstats(struct Qdisc *sch, struct gnet_dump *d,
+ struct tc_taprio_qopt_offload *offload,
+ struct tc_taprio_qopt_stats *stats)
+{
+ struct net_device *dev = qdisc_dev(sch);
+ const struct net_device_ops *ops;
+ struct sk_buff *skb = d->skb;
+ struct nlattr *xstats;
+ int err;
+
+ ops = qdisc_dev(sch)->netdev_ops;
+
+ /* FIXME I could use qdisc_offload_dump_helper(), but that messes
+ * with sch->flags depending on whether the device reports taprio
+ * stats, and I'm not sure whether that's a good idea, considering
+ * that stats are optional to the offload itself
+ */
+ if (!ops->ndo_setup_tc)
+ return 0;
+
+ memset(stats, 0xff, sizeof(*stats));
+
+ err = ops->ndo_setup_tc(dev, TC_SETUP_QDISC_TAPRIO, offload);
+ if (err == -EOPNOTSUPP)
+ return 0;
+ if (err)
+ return err;
+
+ xstats = nla_nest_start(skb, TCA_STATS_APP);
+ if (!xstats)
+ goto err;
+
+ if (taprio_put_stat(skb, stats->window_drops,
+ TCA_TAPRIO_OFFLOAD_STATS_WINDOW_DROPS) ||
+ taprio_put_stat(skb, stats->tx_overruns,
+ TCA_TAPRIO_OFFLOAD_STATS_TX_OVERRUNS))
+ goto err_cancel;
+
+ nla_nest_end(skb, xstats);
+
+ return 0;
+
+err_cancel:
+ nla_nest_cancel(skb, xstats);
+err:
+ return -EMSGSIZE;
+}
+
+static int taprio_dump_stats(struct Qdisc *sch, struct gnet_dump *d)
+{
+ struct tc_taprio_qopt_offload offload = {
+ .cmd = TAPRIO_CMD_STATS,
+ };
+
+ return taprio_dump_xstats(sch, d, &offload, &offload.stats);
+}
+
static int taprio_dump(struct Qdisc *sch, struct sk_buff *skb)
{
struct taprio_sched *q = qdisc_priv(sch);
@@ -2391,12 +2460,20 @@ static int taprio_dump_class_stats(struct Qdisc *sch, unsigned long cl,
__acquires(d->lock)
{
struct netdev_queue *dev_queue = taprio_queue_get(sch, cl);
+ struct tc_taprio_qopt_offload offload = {
+ .cmd = TAPRIO_CMD_QUEUE_STATS,
+ .queue_stats = {
+ .queue = cl - 1,
+ },
+ };
+ struct Qdisc *child;
- sch = rtnl_dereference(dev_queue->qdisc_sleeping);
- if (gnet_stats_copy_basic(d, NULL, &sch->bstats, true) < 0 ||
- qdisc_qstats_copy(d, sch) < 0)
+ child = rtnl_dereference(dev_queue->qdisc_sleeping);
+ if (gnet_stats_copy_basic(d, NULL, &child->bstats, true) < 0 ||
+ qdisc_qstats_copy(d, child) < 0)
return -1;
- return 0;
+
+ return taprio_dump_xstats(sch, d, &offload, &offload.queue_stats.stats);
}
static void taprio_walk(struct Qdisc *sch, struct qdisc_walker *arg)
@@ -2443,6 +2520,7 @@ static struct Qdisc_ops taprio_qdisc_ops __read_mostly = {
.dequeue = taprio_dequeue,
.enqueue = taprio_enqueue,
.dump = taprio_dump,
+ .dump_stats = taprio_dump_stats,
.owner = THIS_MODULE,
};
diff --git a/net/sched/sch_tbf.c b/net/sched/sch_tbf.c
index 277ad11f4d61..17d2d00ddb18 100644
--- a/net/sched/sch_tbf.c
+++ b/net/sched/sch_tbf.c
@@ -13,6 +13,7 @@
#include <linux/string.h>
#include <linux/errno.h>
#include <linux/skbuff.h>
+#include <net/gso.h>
#include <net/netlink.h>
#include <net/sch_generic.h>
#include <net/pkt_cls.h>
diff --git a/net/sctp/offload.c b/net/sctp/offload.c
index eb874e3c399a..502095173d88 100644
--- a/net/sctp/offload.c
+++ b/net/sctp/offload.c
@@ -22,6 +22,7 @@
#include <net/sctp/sctp.h>
#include <net/sctp/checksum.h>
#include <net/protocol.h>
+#include <net/gso.h>
static __le32 sctp_gso_make_checksum(struct sk_buff *skb)
{
diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c
index c365df24ad33..274d07bd774f 100644
--- a/net/sctp/protocol.c
+++ b/net/sctp/protocol.c
@@ -500,9 +500,7 @@ static void sctp_v4_get_dst(struct sctp_transport *t, union sctp_addr *saddr,
continue;
fl4->fl4_sport = laddr->a.v4.sin_port;
- flowi4_update_output(fl4,
- asoc->base.sk->sk_bound_dev_if,
- RT_CONN_FLAGS_TOS(asoc->base.sk, tos),
+ flowi4_update_output(fl4, asoc->base.sk->sk_bound_dev_if,
daddr->v4.sin_addr.s_addr,
laddr->a.v4.sin_addr.s_addr);
@@ -1135,7 +1133,6 @@ static const struct proto_ops inet_seqpacket_ops = {
.sendmsg = inet_sendmsg,
.recvmsg = inet_recvmsg,
.mmap = sock_no_mmap,
- .sendpage = sock_no_sendpage,
};
/* Registration with AF_INET family. */
diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index cda8c2874691..6554a357fe33 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -4895,7 +4895,7 @@ out:
}
/* The SCTP ioctl handler. */
-static int sctp_ioctl(struct sock *sk, int cmd, unsigned long arg)
+static int sctp_ioctl(struct sock *sk, int cmd, int *karg)
{
int rc = -ENOTCONN;
@@ -4911,7 +4911,7 @@ static int sctp_ioctl(struct sock *sk, int cmd, unsigned long arg)
switch (cmd) {
case SIOCINQ: {
struct sk_buff *skb;
- unsigned int amount = 0;
+ *karg = 0;
skb = skb_peek(&sk->sk_receive_queue);
if (skb != NULL) {
@@ -4919,9 +4919,9 @@ static int sctp_ioctl(struct sock *sk, int cmd, unsigned long arg)
* We will only return the amount of this packet since
* that is all that will be read.
*/
- amount = skb->len;
+ *karg = skb->len;
}
- rc = put_user(amount, (int __user *)arg);
+ rc = 0;
break;
}
default:
@@ -8281,6 +8281,22 @@ static int sctp_getsockopt(struct sock *sk, int level, int optname,
return retval;
}
+static bool sctp_bpf_bypass_getsockopt(int level, int optname)
+{
+ if (level == SOL_SCTP) {
+ switch (optname) {
+ case SCTP_SOCKOPT_PEELOFF:
+ case SCTP_SOCKOPT_PEELOFF_FLAGS:
+ case SCTP_SOCKOPT_CONNECTX3:
+ return true;
+ default:
+ return false;
+ }
+ }
+
+ return false;
+}
+
static int sctp_hash(struct sock *sk)
{
/* STUB */
@@ -9650,6 +9666,7 @@ struct proto sctp_prot = {
.shutdown = sctp_shutdown,
.setsockopt = sctp_setsockopt,
.getsockopt = sctp_getsockopt,
+ .bpf_bypass_getsockopt = sctp_bpf_bypass_getsockopt,
.sendmsg = sctp_sendmsg,
.recvmsg = sctp_recvmsg,
.bind = sctp_bind,
@@ -9705,6 +9722,7 @@ struct proto sctpv6_prot = {
.shutdown = sctp_shutdown,
.setsockopt = sctp_setsockopt,
.getsockopt = sctp_getsockopt,
+ .bpf_bypass_getsockopt = sctp_bpf_bypass_getsockopt,
.sendmsg = sctp_sendmsg,
.recvmsg = sctp_recvmsg,
.bind = sctp_bind,
diff --git a/net/sctp/stream_sched.c b/net/sctp/stream_sched.c
index e843760e9aaa..54afbe4fb087 100644
--- a/net/sctp/stream_sched.c
+++ b/net/sctp/stream_sched.c
@@ -148,18 +148,19 @@ static void sctp_sched_free_sched(struct sctp_stream *stream)
int sctp_sched_set_sched(struct sctp_association *asoc,
enum sctp_sched_type sched)
{
- struct sctp_sched_ops *n = sctp_sched_ops[sched];
struct sctp_sched_ops *old = asoc->outqueue.sched;
struct sctp_datamsg *msg = NULL;
+ struct sctp_sched_ops *n;
struct sctp_chunk *ch;
int i, ret = 0;
- if (old == n)
- return ret;
-
if (sched > SCTP_SS_MAX)
return -EINVAL;
+ n = sctp_sched_ops[sched];
+ if (old == n)
+ return ret;
+
if (old)
sctp_sched_free_sched(&asoc->stream);
diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c
index 538e9c6ec8c9..a7f887d91d89 100644
--- a/net/smc/af_smc.c
+++ b/net/smc/af_smc.c
@@ -3133,34 +3133,6 @@ static int smc_ioctl(struct socket *sock, unsigned int cmd,
return put_user(answ, (int __user *)arg);
}
-static ssize_t smc_sendpage(struct socket *sock, struct page *page,
- int offset, size_t size, int flags)
-{
- struct sock *sk = sock->sk;
- struct smc_sock *smc;
- int rc = -EPIPE;
-
- smc = smc_sk(sk);
- lock_sock(sk);
- if (sk->sk_state != SMC_ACTIVE) {
- release_sock(sk);
- goto out;
- }
- release_sock(sk);
- if (smc->use_fallback) {
- rc = kernel_sendpage(smc->clcsock, page, offset,
- size, flags);
- } else {
- lock_sock(sk);
- rc = smc_tx_sendpage(smc, page, offset, size, flags);
- release_sock(sk);
- SMC_STAT_INC(smc, sendpage_cnt);
- }
-
-out:
- return rc;
-}
-
/* Map the affected portions of the rmbe into an spd, note the number of bytes
* to splice in conn->splice_pending, and press 'go'. Delays consumer cursor
* updates till whenever a respective page has been fully processed.
@@ -3232,7 +3204,6 @@ static const struct proto_ops smc_sock_ops = {
.sendmsg = smc_sendmsg,
.recvmsg = smc_recvmsg,
.mmap = sock_no_mmap,
- .sendpage = smc_sendpage,
.splice_read = smc_splice_read,
};
diff --git a/net/smc/smc_stats.c b/net/smc/smc_stats.c
index e80e34f7ac15..ca14c0f3a07d 100644
--- a/net/smc/smc_stats.c
+++ b/net/smc/smc_stats.c
@@ -227,7 +227,7 @@ static int smc_nl_fill_stats_tech_data(struct sk_buff *skb,
SMC_NLA_STATS_PAD))
goto errattr;
if (nla_put_u64_64bit(skb, SMC_NLA_STATS_T_SENDPAGE_CNT,
- smc_tech->sendpage_cnt,
+ 0,
SMC_NLA_STATS_PAD))
goto errattr;
if (nla_put_u64_64bit(skb, SMC_NLA_STATS_T_CORK_CNT,
diff --git a/net/smc/smc_stats.h b/net/smc/smc_stats.h
index 84b7ecd8c05c..b60fe1eb37ab 100644
--- a/net/smc/smc_stats.h
+++ b/net/smc/smc_stats.h
@@ -71,7 +71,6 @@ struct smc_stats_tech {
u64 clnt_v2_succ_cnt;
u64 srv_v1_succ_cnt;
u64 srv_v2_succ_cnt;
- u64 sendpage_cnt;
u64 urg_data_cnt;
u64 splice_cnt;
u64 cork_cnt;
diff --git a/net/smc/smc_tx.c b/net/smc/smc_tx.c
index 45128443f1f1..3b0ff3b589c7 100644
--- a/net/smc/smc_tx.c
+++ b/net/smc/smc_tx.c
@@ -168,8 +168,7 @@ static bool smc_tx_should_cork(struct smc_sock *smc, struct msghdr *msg)
* should known how/when to uncork it.
*/
if ((msg->msg_flags & MSG_MORE ||
- smc_tx_is_corked(smc) ||
- msg->msg_flags & MSG_SENDPAGE_NOTLAST) &&
+ smc_tx_is_corked(smc)) &&
atomic_read(&conn->sndbuf_space))
return true;
@@ -298,22 +297,6 @@ out_err:
return rc;
}
-int smc_tx_sendpage(struct smc_sock *smc, struct page *page, int offset,
- size_t size, int flags)
-{
- struct msghdr msg = {.msg_flags = flags};
- char *kaddr = kmap(page);
- struct kvec iov;
- int rc;
-
- iov.iov_base = kaddr + offset;
- iov.iov_len = size;
- iov_iter_kvec(&msg.msg_iter, ITER_SOURCE, &iov, 1, size);
- rc = smc_tx_sendmsg(smc, &msg, size);
- kunmap(page);
- return rc;
-}
-
/***************************** sndbuf consumer *******************************/
/* sndbuf consumer: actual data transfer of one target chunk with ISM write */
diff --git a/net/smc/smc_tx.h b/net/smc/smc_tx.h
index 34b578498b1f..a59f370b8b43 100644
--- a/net/smc/smc_tx.h
+++ b/net/smc/smc_tx.h
@@ -31,8 +31,6 @@ void smc_tx_pending(struct smc_connection *conn);
void smc_tx_work(struct work_struct *work);
void smc_tx_init(struct smc_sock *smc);
int smc_tx_sendmsg(struct smc_sock *smc, struct msghdr *msg, size_t len);
-int smc_tx_sendpage(struct smc_sock *smc, struct page *page, int offset,
- size_t size, int flags);
int smc_tx_sndbuf_nonempty(struct smc_connection *conn);
void smc_tx_sndbuf_nonfull(struct smc_sock *smc);
void smc_tx_consumer_update(struct smc_connection *conn, bool force);
diff --git a/net/socket.c b/net/socket.c
index e46b162f1182..2b0e54b2405c 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -57,6 +57,7 @@
#include <linux/mm.h>
#include <linux/socket.h>
#include <linux/file.h>
+#include <linux/splice.h>
#include <linux/net.h>
#include <linux/interrupt.h>
#include <linux/thread_info.h>
@@ -126,11 +127,10 @@ static long compat_sock_ioctl(struct file *file,
unsigned int cmd, unsigned long arg);
#endif
static int sock_fasync(int fd, struct file *filp, int on);
-static ssize_t sock_sendpage(struct file *file, struct page *page,
- int offset, size_t size, loff_t *ppos, int more);
static ssize_t sock_splice_read(struct file *file, loff_t *ppos,
struct pipe_inode_info *pipe, size_t len,
unsigned int flags);
+static void sock_splice_eof(struct file *file);
#ifdef CONFIG_PROC_FS
static void sock_show_fdinfo(struct seq_file *m, struct file *f)
@@ -162,9 +162,9 @@ static const struct file_operations socket_file_ops = {
.mmap = sock_mmap,
.release = sock_close,
.fasync = sock_fasync,
- .sendpage = sock_sendpage,
- .splice_write = generic_splice_sendpage,
+ .splice_write = splice_to_socket,
.splice_read = sock_splice_read,
+ .splice_eof = sock_splice_eof,
.show_fdinfo = sock_show_fdinfo,
};
@@ -1067,26 +1067,6 @@ int kernel_recvmsg(struct socket *sock, struct msghdr *msg,
}
EXPORT_SYMBOL(kernel_recvmsg);
-static ssize_t sock_sendpage(struct file *file, struct page *page,
- int offset, size_t size, loff_t *ppos, int more)
-{
- struct socket *sock;
- int flags;
- int ret;
-
- sock = file->private_data;
-
- flags = (file->f_flags & O_NONBLOCK) ? MSG_DONTWAIT : 0;
- /* more is a combination of MSG_MORE and MSG_SENDPAGE_NOTLAST */
- flags |= more;
-
- ret = kernel_sendpage(sock, page, offset, size, flags);
-
- if (trace_sock_send_length_enabled())
- call_trace_sock_send_length(sock->sk, ret, 0);
- return ret;
-}
-
static ssize_t sock_splice_read(struct file *file, loff_t *ppos,
struct pipe_inode_info *pipe, size_t len,
unsigned int flags)
@@ -1099,6 +1079,14 @@ static ssize_t sock_splice_read(struct file *file, loff_t *ppos,
return sock->ops->splice_read(sock, ppos, pipe, len, flags);
}
+static void sock_splice_eof(struct file *file)
+{
+ struct socket *sock = file->private_data;
+
+ if (sock->ops->splice_eof)
+ sock->ops->splice_eof(sock);
+}
+
static ssize_t sock_read_iter(struct kiocb *iocb, struct iov_iter *to)
{
struct file *file = iocb->ki_filp;
@@ -2139,6 +2127,7 @@ int __sys_sendto(int fd, void __user *buff, size_t len, unsigned int flags,
msg.msg_name = (struct sockaddr *)&address;
msg.msg_namelen = addr_len;
}
+ flags &= ~MSG_INTERNAL_SENDMSG_FLAGS;
if (sock->file->f_flags & O_NONBLOCK)
flags |= MSG_DONTWAIT;
msg.msg_flags = flags;
@@ -2484,6 +2473,7 @@ static int ____sys_sendmsg(struct socket *sock, struct msghdr *msg_sys,
msg_sys->msg_control = ctl_buf;
msg_sys->msg_control_is_user = false;
}
+ flags &= ~MSG_INTERNAL_SENDMSG_FLAGS;
msg_sys->msg_flags = flags;
if (sock->file->f_flags & O_NONBLOCK)
@@ -3564,54 +3554,6 @@ int kernel_getpeername(struct socket *sock, struct sockaddr *addr)
EXPORT_SYMBOL(kernel_getpeername);
/**
- * kernel_sendpage - send a &page through a socket (kernel space)
- * @sock: socket
- * @page: page
- * @offset: page offset
- * @size: total size in bytes
- * @flags: flags (MSG_DONTWAIT, ...)
- *
- * Returns the total amount sent in bytes or an error.
- */
-
-int kernel_sendpage(struct socket *sock, struct page *page, int offset,
- size_t size, int flags)
-{
- if (sock->ops->sendpage) {
- /* Warn in case the improper page to zero-copy send */
- WARN_ONCE(!sendpage_ok(page), "improper page for zero-copy send");
- return sock->ops->sendpage(sock, page, offset, size, flags);
- }
- return sock_no_sendpage(sock, page, offset, size, flags);
-}
-EXPORT_SYMBOL(kernel_sendpage);
-
-/**
- * kernel_sendpage_locked - send a &page through the locked sock (kernel space)
- * @sk: sock
- * @page: page
- * @offset: page offset
- * @size: total size in bytes
- * @flags: flags (MSG_DONTWAIT, ...)
- *
- * Returns the total amount sent in bytes or an error.
- * Caller must hold @sk.
- */
-
-int kernel_sendpage_locked(struct sock *sk, struct page *page, int offset,
- size_t size, int flags)
-{
- struct socket *sock = sk->sk_socket;
-
- if (sock->ops->sendpage_locked)
- return sock->ops->sendpage_locked(sk, page, offset, size,
- flags);
-
- return sock_no_sendpage_locked(sk, page, offset, size, flags);
-}
-EXPORT_SYMBOL(kernel_sendpage_locked);
-
-/**
* kernel_sock_shutdown - shut down part of a full-duplex connection (kernel space)
* @sock: socket
* @how: connection part
diff --git a/net/sunrpc/svcsock.c b/net/sunrpc/svcsock.c
index 5f519fc0541b..e43f26382411 100644
--- a/net/sunrpc/svcsock.c
+++ b/net/sunrpc/svcsock.c
@@ -1197,13 +1197,14 @@ err_noclose:
static int svc_tcp_send_kvec(struct socket *sock, const struct kvec *vec,
int flags)
{
- return kernel_sendpage(sock, virt_to_page(vec->iov_base),
- offset_in_page(vec->iov_base),
- vec->iov_len, flags);
+ struct msghdr msg = { .msg_flags = MSG_SPLICE_PAGES | flags, };
+
+ iov_iter_kvec(&msg.msg_iter, ITER_SOURCE, vec, 1, vec->iov_len);
+ return sock_sendmsg(sock, &msg);
}
/*
- * kernel_sendpage() is used exclusively to reduce the number of
+ * MSG_SPLICE_PAGES is used exclusively to reduce the number of
* copy operations in this path. Therefore the caller must ensure
* that the pages backing @xdr are unchanging.
*
@@ -1243,28 +1244,13 @@ static int svc_tcp_sendmsg(struct socket *sock, struct xdr_buf *xdr,
if (ret != head->iov_len)
goto out;
- if (xdr->page_len) {
- unsigned int offset, len, remaining;
- struct bio_vec *bvec;
-
- bvec = xdr->bvec + (xdr->page_base >> PAGE_SHIFT);
- offset = offset_in_page(xdr->page_base);
- remaining = xdr->page_len;
- while (remaining > 0) {
- len = min(remaining, bvec->bv_len - offset);
- ret = kernel_sendpage(sock, bvec->bv_page,
- bvec->bv_offset + offset,
- len, 0);
- if (ret < 0)
- return ret;
- *sentp += ret;
- if (ret != len)
- goto out;
- remaining -= len;
- offset = 0;
- bvec++;
- }
- }
+ msg.msg_flags = MSG_SPLICE_PAGES;
+ iov_iter_bvec(&msg.msg_iter, ITER_SOURCE, xdr->bvec,
+ xdr_buf_pagecount(xdr), xdr->page_len);
+ ret = sock_sendmsg(sock, &msg);
+ if (ret < 0)
+ return ret;
+ *sentp += ret;
if (tail->iov_len) {
ret = svc_tcp_send_kvec(sock, tail, 0);
diff --git a/net/tipc/bearer.c b/net/tipc/bearer.c
index cdcd2731860b..2cde375477e3 100644
--- a/net/tipc/bearer.c
+++ b/net/tipc/bearer.c
@@ -176,7 +176,7 @@ static int bearer_name_validate(const char *name,
*/
struct tipc_bearer *tipc_bearer_find(struct net *net, const char *name)
{
- struct tipc_net *tn = net_generic(net, tipc_net_id);
+ struct tipc_net *tn = tipc_net(net);
struct tipc_bearer *b;
u32 i;
@@ -211,11 +211,10 @@ int tipc_bearer_get_name(struct net *net, char *name, u32 bearer_id)
void tipc_bearer_add_dest(struct net *net, u32 bearer_id, u32 dest)
{
- struct tipc_net *tn = net_generic(net, tipc_net_id);
struct tipc_bearer *b;
rcu_read_lock();
- b = rcu_dereference(tn->bearer_list[bearer_id]);
+ b = bearer_get(net, bearer_id);
if (b)
tipc_disc_add_dest(b->disc);
rcu_read_unlock();
@@ -223,11 +222,10 @@ void tipc_bearer_add_dest(struct net *net, u32 bearer_id, u32 dest)
void tipc_bearer_remove_dest(struct net *net, u32 bearer_id, u32 dest)
{
- struct tipc_net *tn = net_generic(net, tipc_net_id);
struct tipc_bearer *b;
rcu_read_lock();
- b = rcu_dereference(tn->bearer_list[bearer_id]);
+ b = bearer_get(net, bearer_id);
if (b)
tipc_disc_remove_dest(b->disc);
rcu_read_unlock();
@@ -431,7 +429,7 @@ int tipc_enable_l2_media(struct net *net, struct tipc_bearer *b,
dev = dev_get_by_name(net, dev_name);
if (!dev)
return -ENODEV;
- if (tipc_mtu_bad(dev, 0)) {
+ if (tipc_mtu_bad(dev)) {
dev_put(dev);
return -EINVAL;
}
@@ -534,7 +532,7 @@ int tipc_bearer_mtu(struct net *net, u32 bearer_id)
struct tipc_bearer *b;
rcu_read_lock();
- b = rcu_dereference(tipc_net(net)->bearer_list[bearer_id]);
+ b = bearer_get(net, bearer_id);
if (b)
mtu = b->mtu;
rcu_read_unlock();
@@ -708,7 +706,7 @@ static int tipc_l2_device_event(struct notifier_block *nb, unsigned long evt,
test_and_set_bit_lock(0, &b->up);
break;
case NETDEV_CHANGEMTU:
- if (tipc_mtu_bad(dev, 0)) {
+ if (tipc_mtu_bad(dev)) {
bearer_disable(net, b);
break;
}
@@ -745,7 +743,7 @@ void tipc_bearer_cleanup(void)
void tipc_bearer_stop(struct net *net)
{
- struct tipc_net *tn = net_generic(net, tipc_net_id);
+ struct tipc_net *tn = tipc_net(net);
struct tipc_bearer *b;
u32 i;
@@ -881,7 +879,7 @@ int tipc_nl_bearer_dump(struct sk_buff *skb, struct netlink_callback *cb)
struct tipc_bearer *bearer;
struct tipc_nl_msg msg;
struct net *net = sock_net(skb->sk);
- struct tipc_net *tn = net_generic(net, tipc_net_id);
+ struct tipc_net *tn = tipc_net(net);
if (i == MAX_BEARERS)
return 0;
diff --git a/net/tipc/bearer.h b/net/tipc/bearer.h
index bd0cc5c287ef..1ee60649bd17 100644
--- a/net/tipc/bearer.h
+++ b/net/tipc/bearer.h
@@ -257,9 +257,9 @@ static inline void tipc_loopback_trace(struct net *net,
}
/* check if device MTU is too low for tipc headers */
-static inline bool tipc_mtu_bad(struct net_device *dev, unsigned int reserve)
+static inline bool tipc_mtu_bad(struct net_device *dev)
{
- if (dev->mtu >= TIPC_MIN_BEARER_MTU + reserve)
+ if (dev->mtu >= TIPC_MIN_BEARER_MTU)
return false;
netdev_warn(dev, "MTU too low for tipc bearer\n");
return true;
diff --git a/net/tipc/socket.c b/net/tipc/socket.c
index dd73d71c02a9..ef8e5139a873 100644
--- a/net/tipc/socket.c
+++ b/net/tipc/socket.c
@@ -3375,7 +3375,6 @@ static const struct proto_ops msg_ops = {
.sendmsg = tipc_sendmsg,
.recvmsg = tipc_recvmsg,
.mmap = sock_no_mmap,
- .sendpage = sock_no_sendpage
};
static const struct proto_ops packet_ops = {
@@ -3396,7 +3395,6 @@ static const struct proto_ops packet_ops = {
.sendmsg = tipc_send_packet,
.recvmsg = tipc_recvmsg,
.mmap = sock_no_mmap,
- .sendpage = sock_no_sendpage
};
static const struct proto_ops stream_ops = {
@@ -3417,7 +3415,6 @@ static const struct proto_ops stream_ops = {
.sendmsg = tipc_sendstream,
.recvmsg = tipc_recvstream,
.mmap = sock_no_mmap,
- .sendpage = sock_no_sendpage
};
static const struct net_proto_family tipc_family_ops = {
diff --git a/net/tipc/udp_media.c b/net/tipc/udp_media.c
index 0a85244fd618..926232557e77 100644
--- a/net/tipc/udp_media.c
+++ b/net/tipc/udp_media.c
@@ -739,10 +739,6 @@ static int tipc_udp_enable(struct net *net, struct tipc_bearer *b,
udp_conf.use_udp_checksums = false;
ub->ifindex = dev->ifindex;
b->encap_hlen = sizeof(struct iphdr) + sizeof(struct udphdr);
- if (tipc_mtu_bad(dev, b->encap_hlen)) {
- err = -EINVAL;
- goto err;
- }
b->mtu = b->media->mtu;
#if IS_ENABLED(CONFIG_IPV6)
} else if (local.proto == htons(ETH_P_IPV6)) {
diff --git a/net/tls/tls.h b/net/tls/tls.h
index 0672acab2773..86cef1c68e03 100644
--- a/net/tls/tls.h
+++ b/net/tls/tls.h
@@ -97,10 +97,7 @@ void tls_update_rx_zc_capable(struct tls_context *tls_ctx);
void tls_sw_strparser_arm(struct sock *sk, struct tls_context *ctx);
void tls_sw_strparser_done(struct tls_context *tls_ctx);
int tls_sw_sendmsg(struct sock *sk, struct msghdr *msg, size_t size);
-int tls_sw_sendpage_locked(struct sock *sk, struct page *page,
- int offset, size_t size, int flags);
-int tls_sw_sendpage(struct sock *sk, struct page *page,
- int offset, size_t size, int flags);
+void tls_sw_splice_eof(struct socket *sock);
void tls_sw_cancel_work_tx(struct tls_context *tls_ctx);
void tls_sw_release_resources_tx(struct sock *sk);
void tls_sw_free_ctx_tx(struct tls_context *tls_ctx);
@@ -115,8 +112,7 @@ ssize_t tls_sw_splice_read(struct socket *sock, loff_t *ppos,
size_t len, unsigned int flags);
int tls_device_sendmsg(struct sock *sk, struct msghdr *msg, size_t size);
-int tls_device_sendpage(struct sock *sk, struct page *page,
- int offset, size_t size, int flags);
+void tls_device_splice_eof(struct socket *sock);
int tls_tx_records(struct sock *sk, int flags);
void tls_sw_write_space(struct sock *sk, struct tls_context *ctx);
diff --git a/net/tls/tls_device.c b/net/tls/tls_device.c
index bf69c9d6d06c..2021fe557e50 100644
--- a/net/tls/tls_device.c
+++ b/net/tls/tls_device.c
@@ -268,9 +268,8 @@ static void tls_append_frag(struct tls_record_info *record,
skb_frag_size_add(frag, size);
} else {
++frag;
- __skb_frag_set_page(frag, pfrag->page);
- skb_frag_off_set(frag, pfrag->offset);
- skb_frag_size_set(frag, size);
+ skb_frag_fill_page_desc(frag, pfrag->page, pfrag->offset,
+ size);
++record->num_frags;
get_page(pfrag->page);
}
@@ -357,9 +356,8 @@ static int tls_create_new_record(struct tls_offload_context_tx *offload_ctx,
return -ENOMEM;
frag = &record->frags[0];
- __skb_frag_set_page(frag, pfrag->page);
- skb_frag_off_set(frag, pfrag->offset);
- skb_frag_size_set(frag, prepend_size);
+ skb_frag_fill_page_desc(frag, pfrag->page, pfrag->offset,
+ prepend_size);
get_page(pfrag->page);
pfrag->offset += prepend_size;
@@ -424,16 +422,10 @@ static int tls_device_copy_data(void *addr, size_t bytes, struct iov_iter *i)
return 0;
}
-union tls_iter_offset {
- struct iov_iter *msg_iter;
- int offset;
-};
-
static int tls_push_data(struct sock *sk,
- union tls_iter_offset iter_offset,
+ struct iov_iter *iter,
size_t size, int flags,
- unsigned char record_type,
- struct page *zc_page)
+ unsigned char record_type)
{
struct tls_context *tls_ctx = tls_get_ctx(sk);
struct tls_prot_info *prot = &tls_ctx->prot_info;
@@ -449,14 +441,14 @@ static int tls_push_data(struct sock *sk,
long timeo;
if (flags &
- ~(MSG_MORE | MSG_DONTWAIT | MSG_NOSIGNAL | MSG_SENDPAGE_NOTLAST))
+ ~(MSG_MORE | MSG_DONTWAIT | MSG_NOSIGNAL | MSG_SPLICE_PAGES))
return -EOPNOTSUPP;
if (unlikely(sk->sk_err))
return -sk->sk_err;
flags |= MSG_SENDPAGE_DECRYPTED;
- tls_push_record_flags = flags | MSG_SENDPAGE_NOTLAST;
+ tls_push_record_flags = flags | MSG_MORE;
timeo = sock_sndtimeo(sk, flags & MSG_DONTWAIT);
if (tls_is_partially_sent_record(tls_ctx)) {
@@ -501,21 +493,35 @@ handle_error:
record = ctx->open_record;
copy = min_t(size_t, size, max_open_record_len - record->len);
- if (copy && zc_page) {
+ if (copy && (flags & MSG_SPLICE_PAGES)) {
struct page_frag zc_pfrag;
+ struct page **pages = &zc_pfrag.page;
+ size_t off;
+
+ rc = iov_iter_extract_pages(iter, &pages,
+ copy, 1, 0, &off);
+ if (rc <= 0) {
+ if (rc == 0)
+ rc = -EIO;
+ goto handle_error;
+ }
+ copy = rc;
+
+ if (WARN_ON_ONCE(!sendpage_ok(zc_pfrag.page))) {
+ iov_iter_revert(iter, copy);
+ rc = -EIO;
+ goto handle_error;
+ }
- zc_pfrag.page = zc_page;
- zc_pfrag.offset = iter_offset.offset;
+ zc_pfrag.offset = off;
zc_pfrag.size = copy;
tls_append_frag(record, &zc_pfrag, copy);
-
- iter_offset.offset += copy;
} else if (copy) {
copy = min_t(size_t, copy, pfrag->size - pfrag->offset);
rc = tls_device_copy_data(page_address(pfrag->page) +
pfrag->offset, copy,
- iter_offset.msg_iter);
+ iter);
if (rc)
goto handle_error;
tls_append_frag(record, pfrag, copy);
@@ -525,7 +531,7 @@ handle_error:
if (!size) {
last_record:
tls_push_record_flags = flags;
- if (flags & (MSG_SENDPAGE_NOTLAST | MSG_MORE)) {
+ if (flags & MSG_MORE) {
more = true;
break;
}
@@ -570,9 +576,11 @@ int tls_device_sendmsg(struct sock *sk, struct msghdr *msg, size_t size)
{
unsigned char record_type = TLS_RECORD_TYPE_DATA;
struct tls_context *tls_ctx = tls_get_ctx(sk);
- union tls_iter_offset iter;
int rc;
+ if (!tls_ctx->zerocopy_sendfile)
+ msg->msg_flags &= ~MSG_SPLICE_PAGES;
+
mutex_lock(&tls_ctx->tx_lock);
lock_sock(sk);
@@ -582,8 +590,8 @@ int tls_device_sendmsg(struct sock *sk, struct msghdr *msg, size_t size)
goto out;
}
- iter.msg_iter = &msg->msg_iter;
- rc = tls_push_data(sk, iter, size, msg->msg_flags, record_type, NULL);
+ rc = tls_push_data(sk, &msg->msg_iter, size, msg->msg_flags,
+ record_type);
out:
release_sock(sk);
@@ -591,47 +599,25 @@ out:
return rc;
}
-int tls_device_sendpage(struct sock *sk, struct page *page,
- int offset, size_t size, int flags)
+void tls_device_splice_eof(struct socket *sock)
{
+ struct sock *sk = sock->sk;
struct tls_context *tls_ctx = tls_get_ctx(sk);
- union tls_iter_offset iter_offset;
- struct iov_iter msg_iter;
- char *kaddr;
- struct kvec iov;
- int rc;
+ struct iov_iter iter = {};
- if (flags & MSG_SENDPAGE_NOTLAST)
- flags |= MSG_MORE;
+ if (!tls_is_partially_sent_record(tls_ctx))
+ return;
mutex_lock(&tls_ctx->tx_lock);
lock_sock(sk);
- if (flags & MSG_OOB) {
- rc = -EOPNOTSUPP;
- goto out;
- }
-
- if (tls_ctx->zerocopy_sendfile) {
- iter_offset.offset = offset;
- rc = tls_push_data(sk, iter_offset, size,
- flags, TLS_RECORD_TYPE_DATA, page);
- goto out;
+ if (tls_is_partially_sent_record(tls_ctx)) {
+ iov_iter_bvec(&iter, ITER_SOURCE, NULL, 0, 0);
+ tls_push_data(sk, &iter, 0, 0, TLS_RECORD_TYPE_DATA);
}
- kaddr = kmap(page);
- iov.iov_base = kaddr + offset;
- iov.iov_len = size;
- iov_iter_kvec(&msg_iter, ITER_SOURCE, &iov, 1, size);
- iter_offset.msg_iter = &msg_iter;
- rc = tls_push_data(sk, iter_offset, size, flags, TLS_RECORD_TYPE_DATA,
- NULL);
- kunmap(page);
-
-out:
release_sock(sk);
mutex_unlock(&tls_ctx->tx_lock);
- return rc;
}
struct tls_record_info *tls_get_record(struct tls_offload_context_tx *context,
@@ -696,12 +682,10 @@ EXPORT_SYMBOL(tls_get_record);
static int tls_device_push_pending_record(struct sock *sk, int flags)
{
- union tls_iter_offset iter;
- struct iov_iter msg_iter;
+ struct iov_iter iter;
- iov_iter_kvec(&msg_iter, ITER_SOURCE, NULL, 0, 0);
- iter.msg_iter = &msg_iter;
- return tls_push_data(sk, iter, 0, flags, TLS_RECORD_TYPE_DATA, NULL);
+ iov_iter_kvec(&iter, ITER_SOURCE, NULL, 0, 0);
+ return tls_push_data(sk, &iter, 0, flags, TLS_RECORD_TYPE_DATA);
}
void tls_device_write_space(struct sock *sk, struct tls_context *ctx)
@@ -1217,7 +1201,7 @@ int tls_set_device_offload(struct sock *sk, struct tls_context *ctx)
tls_device_attach(ctx, sk, netdev);
up_read(&device_offload_lock);
- /* following this assignment tls_is_sk_tx_device_offloaded
+ /* following this assignment tls_is_skb_tx_device_offloaded
* will return true and the context might be accessed
* by the netdev's xmit function.
*/
@@ -1370,7 +1354,7 @@ static int tls_device_down(struct net_device *netdev)
list_for_each_entry_safe(ctx, tmp, &list, list) {
/* Stop offloaded TX and switch to the fallback.
- * tls_is_sk_tx_device_offloaded will return false.
+ * tls_is_skb_tx_device_offloaded will return false.
*/
WRITE_ONCE(ctx->sk->sk_validate_xmit_skb, tls_validate_xmit_skb_sw);
diff --git a/net/tls/tls_device_fallback.c b/net/tls/tls_device_fallback.c
index 7fbb1d0b69b3..b28c5e296dfd 100644
--- a/net/tls/tls_device_fallback.c
+++ b/net/tls/tls_device_fallback.c
@@ -271,7 +271,7 @@ static int fill_sg_in(struct scatterlist *sg_in,
* There is a corner case where the packet contains
* both an acked and a non-acked record.
* We currently don't handle that case and rely
- * on TCP to retranmit a packet that doesn't contain
+ * on TCP to retransmit a packet that doesn't contain
* already acked payload.
*/
if (!is_start_marker)
diff --git a/net/tls/tls_main.c b/net/tls/tls_main.c
index f2e7302a4d96..b6896126bb92 100644
--- a/net/tls/tls_main.c
+++ b/net/tls/tls_main.c
@@ -125,7 +125,10 @@ int tls_push_sg(struct sock *sk,
u16 first_offset,
int flags)
{
- int sendpage_flags = flags | MSG_SENDPAGE_NOTLAST;
+ struct bio_vec bvec;
+ struct msghdr msg = {
+ .msg_flags = MSG_SPLICE_PAGES | flags,
+ };
int ret = 0;
struct page *p;
size_t size;
@@ -134,16 +137,19 @@ int tls_push_sg(struct sock *sk,
size = sg->length - offset;
offset += sg->offset;
- ctx->in_tcp_sendpages = true;
+ ctx->splicing_pages = true;
while (1) {
if (sg_is_last(sg))
- sendpage_flags = flags;
+ msg.msg_flags = flags;
/* is sending application-limited? */
tcp_rate_check_app_limited(sk);
p = sg_page(sg);
retry:
- ret = do_tcp_sendpages(sk, p, offset, size, sendpage_flags);
+ bvec_set_page(&bvec, p, size, offset);
+ iov_iter_bvec(&msg.msg_iter, ITER_SOURCE, &bvec, 1, size);
+
+ ret = tcp_sendmsg_locked(sk, &msg, size);
if (ret != size) {
if (ret > 0) {
@@ -155,7 +161,7 @@ retry:
offset -= sg->offset;
ctx->partially_sent_offset = offset;
ctx->partially_sent_record = (void *)sg;
- ctx->in_tcp_sendpages = false;
+ ctx->splicing_pages = false;
return ret;
}
@@ -169,7 +175,7 @@ retry:
size = sg->length;
}
- ctx->in_tcp_sendpages = false;
+ ctx->splicing_pages = false;
return 0;
}
@@ -247,11 +253,11 @@ static void tls_write_space(struct sock *sk)
{
struct tls_context *ctx = tls_get_ctx(sk);
- /* If in_tcp_sendpages call lower protocol write space handler
+ /* If splicing_pages call lower protocol write space handler
* to ensure we wake up any waiting operations there. For example
- * if do_tcp_sendpages where to call sk_wait_event.
+ * if splicing pages where to call sk_wait_event.
*/
- if (ctx->in_tcp_sendpages) {
+ if (ctx->splicing_pages) {
ctx->sk_write_space(sk);
return;
}
@@ -352,6 +358,39 @@ static void tls_sk_proto_close(struct sock *sk, long timeout)
tls_ctx_free(sk, ctx);
}
+static __poll_t tls_sk_poll(struct file *file, struct socket *sock,
+ struct poll_table_struct *wait)
+{
+ struct tls_sw_context_rx *ctx;
+ struct tls_context *tls_ctx;
+ struct sock *sk = sock->sk;
+ struct sk_psock *psock;
+ __poll_t mask = 0;
+ u8 shutdown;
+ int state;
+
+ mask = tcp_poll(file, sock, wait);
+
+ state = inet_sk_state_load(sk);
+ shutdown = READ_ONCE(sk->sk_shutdown);
+ if (unlikely(state != TCP_ESTABLISHED || shutdown & RCV_SHUTDOWN))
+ return mask;
+
+ tls_ctx = tls_get_ctx(sk);
+ ctx = tls_sw_ctx_rx(tls_ctx);
+ psock = sk_psock_get(sk);
+
+ if (skb_queue_empty_lockless(&ctx->rx_list) &&
+ !tls_strp_msg_ready(ctx) &&
+ sk_psock_queue_empty(psock))
+ mask &= ~(EPOLLIN | EPOLLRDNORM);
+
+ if (psock)
+ sk_psock_put(sk, psock);
+
+ return mask;
+}
+
static int do_tls_getsockopt_conf(struct sock *sk, char __user *optval,
int __user *optlen, int tx)
{
@@ -918,27 +957,26 @@ static void build_proto_ops(struct proto_ops ops[TLS_NUM_CONFIG][TLS_NUM_CONFIG]
ops[TLS_BASE][TLS_BASE] = *base;
ops[TLS_SW ][TLS_BASE] = ops[TLS_BASE][TLS_BASE];
- ops[TLS_SW ][TLS_BASE].sendpage_locked = tls_sw_sendpage_locked;
+ ops[TLS_SW ][TLS_BASE].splice_eof = tls_sw_splice_eof;
ops[TLS_BASE][TLS_SW ] = ops[TLS_BASE][TLS_BASE];
ops[TLS_BASE][TLS_SW ].splice_read = tls_sw_splice_read;
+ ops[TLS_BASE][TLS_SW ].poll = tls_sk_poll;
ops[TLS_SW ][TLS_SW ] = ops[TLS_SW ][TLS_BASE];
ops[TLS_SW ][TLS_SW ].splice_read = tls_sw_splice_read;
+ ops[TLS_SW ][TLS_SW ].poll = tls_sk_poll;
#ifdef CONFIG_TLS_DEVICE
ops[TLS_HW ][TLS_BASE] = ops[TLS_BASE][TLS_BASE];
- ops[TLS_HW ][TLS_BASE].sendpage_locked = NULL;
ops[TLS_HW ][TLS_SW ] = ops[TLS_BASE][TLS_SW ];
- ops[TLS_HW ][TLS_SW ].sendpage_locked = NULL;
ops[TLS_BASE][TLS_HW ] = ops[TLS_BASE][TLS_SW ];
ops[TLS_SW ][TLS_HW ] = ops[TLS_SW ][TLS_SW ];
ops[TLS_HW ][TLS_HW ] = ops[TLS_HW ][TLS_SW ];
- ops[TLS_HW ][TLS_HW ].sendpage_locked = NULL;
#endif
#ifdef CONFIG_TLS_TOE
ops[TLS_HW_RECORD][TLS_HW_RECORD] = *base;
@@ -986,7 +1024,7 @@ static void build_protos(struct proto prot[TLS_NUM_CONFIG][TLS_NUM_CONFIG],
prot[TLS_SW][TLS_BASE] = prot[TLS_BASE][TLS_BASE];
prot[TLS_SW][TLS_BASE].sendmsg = tls_sw_sendmsg;
- prot[TLS_SW][TLS_BASE].sendpage = tls_sw_sendpage;
+ prot[TLS_SW][TLS_BASE].splice_eof = tls_sw_splice_eof;
prot[TLS_BASE][TLS_SW] = prot[TLS_BASE][TLS_BASE];
prot[TLS_BASE][TLS_SW].recvmsg = tls_sw_recvmsg;
@@ -1001,11 +1039,11 @@ static void build_protos(struct proto prot[TLS_NUM_CONFIG][TLS_NUM_CONFIG],
#ifdef CONFIG_TLS_DEVICE
prot[TLS_HW][TLS_BASE] = prot[TLS_BASE][TLS_BASE];
prot[TLS_HW][TLS_BASE].sendmsg = tls_device_sendmsg;
- prot[TLS_HW][TLS_BASE].sendpage = tls_device_sendpage;
+ prot[TLS_HW][TLS_BASE].splice_eof = tls_device_splice_eof;
prot[TLS_HW][TLS_SW] = prot[TLS_BASE][TLS_SW];
prot[TLS_HW][TLS_SW].sendmsg = tls_device_sendmsg;
- prot[TLS_HW][TLS_SW].sendpage = tls_device_sendpage;
+ prot[TLS_HW][TLS_SW].splice_eof = tls_device_splice_eof;
prot[TLS_BASE][TLS_HW] = prot[TLS_BASE][TLS_SW];
diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c
index 1a53c8f481e9..53f944e6d8ef 100644
--- a/net/tls/tls_sw.c
+++ b/net/tls/tls_sw.c
@@ -931,7 +931,37 @@ static int tls_sw_push_pending_record(struct sock *sk, int flags)
&copied, flags);
}
-int tls_sw_sendmsg(struct sock *sk, struct msghdr *msg, size_t size)
+static int tls_sw_sendmsg_splice(struct sock *sk, struct msghdr *msg,
+ struct sk_msg *msg_pl, size_t try_to_copy,
+ ssize_t *copied)
+{
+ struct page *page = NULL, **pages = &page;
+
+ do {
+ ssize_t part;
+ size_t off;
+
+ part = iov_iter_extract_pages(&msg->msg_iter, &pages,
+ try_to_copy, 1, 0, &off);
+ if (part <= 0)
+ return part ?: -EIO;
+
+ if (WARN_ON_ONCE(!sendpage_ok(page))) {
+ iov_iter_revert(&msg->msg_iter, part);
+ return -EIO;
+ }
+
+ sk_msg_page_add(msg_pl, page, part, off);
+ sk_mem_charge(sk, part);
+ *copied += part;
+ try_to_copy -= part;
+ } while (try_to_copy && !sk_msg_full(msg_pl));
+
+ return 0;
+}
+
+static int tls_sw_sendmsg_locked(struct sock *sk, struct msghdr *msg,
+ size_t size)
{
long timeo = sock_sndtimeo(sk, msg->msg_flags & MSG_DONTWAIT);
struct tls_context *tls_ctx = tls_get_ctx(sk);
@@ -954,15 +984,6 @@ int tls_sw_sendmsg(struct sock *sk, struct msghdr *msg, size_t size)
int ret = 0;
int pending;
- if (msg->msg_flags & ~(MSG_MORE | MSG_DONTWAIT | MSG_NOSIGNAL |
- MSG_CMSG_COMPAT))
- return -EOPNOTSUPP;
-
- ret = mutex_lock_interruptible(&tls_ctx->tx_lock);
- if (ret)
- return ret;
- lock_sock(sk);
-
if (unlikely(msg->msg_controllen)) {
ret = tls_process_cmsg(sk, msg, &record_type);
if (ret) {
@@ -1020,6 +1041,17 @@ alloc_encrypted:
full_record = true;
}
+ if (try_to_copy && (msg->msg_flags & MSG_SPLICE_PAGES)) {
+ ret = tls_sw_sendmsg_splice(sk, msg, msg_pl,
+ try_to_copy, &copied);
+ if (ret < 0)
+ goto send_end;
+ tls_ctx->pending_open_record_frags = true;
+ if (full_record || eor || sk_msg_full(msg_pl))
+ goto copied;
+ continue;
+ }
+
if (!is_kvec && (full_record || eor) && !async_capable) {
u32 first = msg_pl->sg.end;
@@ -1084,6 +1116,7 @@ fallback_to_reg_send:
*/
tls_ctx->pending_open_record_frags = true;
copied += try_to_copy;
+copied:
if (full_record || eor) {
ret = bpf_exec_tx_verdict(msg_pl, sk, full_record,
record_type, &copied,
@@ -1151,157 +1184,101 @@ trim_sgl:
send_end:
ret = sk_stream_error(sk, msg->msg_flags, ret);
+ return copied > 0 ? copied : ret;
+}
+
+int tls_sw_sendmsg(struct sock *sk, struct msghdr *msg, size_t size)
+{
+ struct tls_context *tls_ctx = tls_get_ctx(sk);
+ int ret;
+ if (msg->msg_flags & ~(MSG_MORE | MSG_DONTWAIT | MSG_NOSIGNAL |
+ MSG_CMSG_COMPAT | MSG_SPLICE_PAGES |
+ MSG_SENDPAGE_NOPOLICY))
+ return -EOPNOTSUPP;
+
+ ret = mutex_lock_interruptible(&tls_ctx->tx_lock);
+ if (ret)
+ return ret;
+ lock_sock(sk);
+ ret = tls_sw_sendmsg_locked(sk, msg, size);
release_sock(sk);
mutex_unlock(&tls_ctx->tx_lock);
- return copied > 0 ? copied : ret;
+ return ret;
}
-static int tls_sw_do_sendpage(struct sock *sk, struct page *page,
- int offset, size_t size, int flags)
+/*
+ * Handle unexpected EOF during splice without SPLICE_F_MORE set.
+ */
+void tls_sw_splice_eof(struct socket *sock)
{
- long timeo = sock_sndtimeo(sk, flags & MSG_DONTWAIT);
+ struct sock *sk = sock->sk;
struct tls_context *tls_ctx = tls_get_ctx(sk);
struct tls_sw_context_tx *ctx = tls_sw_ctx_tx(tls_ctx);
- struct tls_prot_info *prot = &tls_ctx->prot_info;
- unsigned char record_type = TLS_RECORD_TYPE_DATA;
- struct sk_msg *msg_pl;
struct tls_rec *rec;
- int num_async = 0;
+ struct sk_msg *msg_pl;
ssize_t copied = 0;
- bool full_record;
- int record_room;
+ bool retrying = false;
int ret = 0;
- bool eor;
-
- eor = !(flags & MSG_SENDPAGE_NOTLAST);
- sk_clear_bit(SOCKWQ_ASYNC_NOSPACE, sk);
-
- /* Call the sk_stream functions to manage the sndbuf mem. */
- while (size > 0) {
- size_t copy, required_size;
-
- if (sk->sk_err) {
- ret = -sk->sk_err;
- goto sendpage_end;
- }
-
- if (ctx->open_rec)
- rec = ctx->open_rec;
- else
- rec = ctx->open_rec = tls_get_rec(sk);
- if (!rec) {
- ret = -ENOMEM;
- goto sendpage_end;
- }
-
- msg_pl = &rec->msg_plaintext;
-
- full_record = false;
- record_room = TLS_MAX_PAYLOAD_SIZE - msg_pl->sg.size;
- copy = size;
- if (copy >= record_room) {
- copy = record_room;
- full_record = true;
- }
-
- required_size = msg_pl->sg.size + copy + prot->overhead_size;
-
- if (!sk_stream_memory_free(sk))
- goto wait_for_sndbuf;
-alloc_payload:
- ret = tls_alloc_encrypted_msg(sk, required_size);
- if (ret) {
- if (ret != -ENOSPC)
- goto wait_for_memory;
+ int pending;
- /* Adjust copy according to the amount that was
- * actually allocated. The difference is due
- * to max sg elements limit
- */
- copy -= required_size - msg_pl->sg.size;
- full_record = true;
- }
+ if (!ctx->open_rec)
+ return;
- sk_msg_page_add(msg_pl, page, copy, offset);
- sk_mem_charge(sk, copy);
+ mutex_lock(&tls_ctx->tx_lock);
+ lock_sock(sk);
- offset += copy;
- size -= copy;
- copied += copy;
+retry:
+ rec = ctx->open_rec;
+ if (!rec)
+ goto unlock;
- tls_ctx->pending_open_record_frags = true;
- if (full_record || eor || sk_msg_full(msg_pl)) {
- ret = bpf_exec_tx_verdict(msg_pl, sk, full_record,
- record_type, &copied, flags);
- if (ret) {
- if (ret == -EINPROGRESS)
- num_async++;
- else if (ret == -ENOMEM)
- goto wait_for_memory;
- else if (ret != -EAGAIN) {
- if (ret == -ENOSPC)
- ret = 0;
- goto sendpage_end;
- }
- }
- }
- continue;
-wait_for_sndbuf:
- set_bit(SOCK_NOSPACE, &sk->sk_socket->flags);
-wait_for_memory:
- ret = sk_stream_wait_memory(sk, &timeo);
- if (ret) {
- if (ctx->open_rec)
- tls_trim_both_msgs(sk, msg_pl->sg.size);
- goto sendpage_end;
- }
+ msg_pl = &rec->msg_plaintext;
- if (ctx->open_rec)
- goto alloc_payload;
+ /* Check the BPF advisor and perform transmission. */
+ ret = bpf_exec_tx_verdict(msg_pl, sk, false, TLS_RECORD_TYPE_DATA,
+ &copied, 0);
+ switch (ret) {
+ case 0:
+ case -EAGAIN:
+ if (retrying)
+ goto unlock;
+ retrying = true;
+ goto retry;
+ case -EINPROGRESS:
+ break;
+ default:
+ goto unlock;
}
- if (num_async) {
- /* Transmit if any encryptions have completed */
- if (test_and_clear_bit(BIT_TX_SCHEDULED, &ctx->tx_bitmask)) {
- cancel_delayed_work(&ctx->tx_work.work);
- tls_tx_records(sk, flags);
- }
- }
-sendpage_end:
- ret = sk_stream_error(sk, flags, ret);
- return copied > 0 ? copied : ret;
-}
+ /* Wait for pending encryptions to get completed */
+ spin_lock_bh(&ctx->encrypt_compl_lock);
+ ctx->async_notify = true;
-int tls_sw_sendpage_locked(struct sock *sk, struct page *page,
- int offset, size_t size, int flags)
-{
- if (flags & ~(MSG_MORE | MSG_DONTWAIT | MSG_NOSIGNAL |
- MSG_SENDPAGE_NOTLAST | MSG_SENDPAGE_NOPOLICY |
- MSG_NO_SHARED_FRAGS))
- return -EOPNOTSUPP;
+ pending = atomic_read(&ctx->encrypt_pending);
+ spin_unlock_bh(&ctx->encrypt_compl_lock);
+ if (pending)
+ crypto_wait_req(-EINPROGRESS, &ctx->async_wait);
+ else
+ reinit_completion(&ctx->async_wait.completion);
- return tls_sw_do_sendpage(sk, page, offset, size, flags);
-}
+ /* There can be no concurrent accesses, since we have no pending
+ * encrypt operations
+ */
+ WRITE_ONCE(ctx->async_notify, false);
-int tls_sw_sendpage(struct sock *sk, struct page *page,
- int offset, size_t size, int flags)
-{
- struct tls_context *tls_ctx = tls_get_ctx(sk);
- int ret;
+ if (ctx->async_wait.err)
+ goto unlock;
- if (flags & ~(MSG_MORE | MSG_DONTWAIT | MSG_NOSIGNAL |
- MSG_SENDPAGE_NOTLAST | MSG_SENDPAGE_NOPOLICY))
- return -EOPNOTSUPP;
+ /* Transmit if any encryptions have completed */
+ if (test_and_clear_bit(BIT_TX_SCHEDULED, &ctx->tx_bitmask)) {
+ cancel_delayed_work(&ctx->tx_work.work);
+ tls_tx_records(sk, 0);
+ }
- ret = mutex_lock_interruptible(&tls_ctx->tx_lock);
- if (ret)
- return ret;
- lock_sock(sk);
- ret = tls_sw_do_sendpage(sk, page, offset, size, flags);
+unlock:
release_sock(sk);
mutex_unlock(&tls_ctx->tx_lock);
- return ret;
}
static int
diff --git a/net/unix/Kconfig b/net/unix/Kconfig
index b7f811216820..28b232f281ab 100644
--- a/net/unix/Kconfig
+++ b/net/unix/Kconfig
@@ -4,7 +4,7 @@
#
config UNIX
- tristate "Unix domain sockets"
+ bool "Unix domain sockets"
help
If you say Y here, you will include support for Unix domain sockets;
sockets are the standard Unix mechanism for establishing and
@@ -14,10 +14,6 @@ config UNIX
an embedded system or something similar, you therefore definitely
want to say Y here.
- To compile this driver as a module, choose M here: the module will be
- called unix. Note that several important services won't work
- correctly if you say M here and then neglect to load the module.
-
Say Y unless you know what you are doing.
config UNIX_SCM
diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index e7728b57a8c7..123b35ddfd71 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -758,8 +758,6 @@ static int unix_compat_ioctl(struct socket *sock, unsigned int cmd, unsigned lon
static int unix_shutdown(struct socket *, int);
static int unix_stream_sendmsg(struct socket *, struct msghdr *, size_t);
static int unix_stream_recvmsg(struct socket *, struct msghdr *, size_t, int);
-static ssize_t unix_stream_sendpage(struct socket *, struct page *, int offset,
- size_t size, int flags);
static ssize_t unix_stream_splice_read(struct socket *, loff_t *ppos,
struct pipe_inode_info *, size_t size,
unsigned int flags);
@@ -852,7 +850,6 @@ static const struct proto_ops unix_stream_ops = {
.recvmsg = unix_stream_recvmsg,
.read_skb = unix_stream_read_skb,
.mmap = sock_no_mmap,
- .sendpage = unix_stream_sendpage,
.splice_read = unix_stream_splice_read,
.set_peek_off = unix_set_peek_off,
.show_fdinfo = unix_show_fdinfo,
@@ -878,7 +875,6 @@ static const struct proto_ops unix_dgram_ops = {
.read_skb = unix_read_skb,
.recvmsg = unix_dgram_recvmsg,
.mmap = sock_no_mmap,
- .sendpage = sock_no_sendpage,
.set_peek_off = unix_set_peek_off,
.show_fdinfo = unix_show_fdinfo,
};
@@ -902,7 +898,6 @@ static const struct proto_ops unix_seqpacket_ops = {
.sendmsg = unix_seqpacket_sendmsg,
.recvmsg = unix_seqpacket_recvmsg,
.mmap = sock_no_mmap,
- .sendpage = sock_no_sendpage,
.set_peek_off = unix_set_peek_off,
.show_fdinfo = unix_show_fdinfo,
};
@@ -921,11 +916,26 @@ static void unix_unhash(struct sock *sk)
*/
}
+static bool unix_bpf_bypass_getsockopt(int level, int optname)
+{
+ if (level == SOL_SOCKET) {
+ switch (optname) {
+ case SO_PEERPIDFD:
+ return true;
+ default:
+ return false;
+ }
+ }
+
+ return false;
+}
+
struct proto unix_dgram_proto = {
.name = "UNIX",
.owner = THIS_MODULE,
.obj_size = sizeof(struct unix_sock),
.close = unix_close,
+ .bpf_bypass_getsockopt = unix_bpf_bypass_getsockopt,
#ifdef CONFIG_BPF_SYSCALL
.psock_update_sk_prot = unix_dgram_bpf_update_proto,
#endif
@@ -937,6 +947,7 @@ struct proto unix_stream_proto = {
.obj_size = sizeof(struct unix_sock),
.close = unix_close,
.unhash = unix_unhash,
+ .bpf_bypass_getsockopt = unix_bpf_bypass_getsockopt,
#ifdef CONFIG_BPF_SYSCALL
.psock_update_sk_prot = unix_stream_bpf_update_proto,
#endif
@@ -1361,7 +1372,8 @@ static int unix_dgram_connect(struct socket *sock, struct sockaddr *addr,
if (err)
goto out;
- if (test_bit(SOCK_PASSCRED, &sock->flags) &&
+ if ((test_bit(SOCK_PASSCRED, &sock->flags) ||
+ test_bit(SOCK_PASSPIDFD, &sock->flags)) &&
!unix_sk(sk)->addr) {
err = unix_autobind(sk);
if (err)
@@ -1469,7 +1481,8 @@ static int unix_stream_connect(struct socket *sock, struct sockaddr *uaddr,
if (err)
goto out;
- if (test_bit(SOCK_PASSCRED, &sock->flags) && !u->addr) {
+ if ((test_bit(SOCK_PASSCRED, &sock->flags) ||
+ test_bit(SOCK_PASSPIDFD, &sock->flags)) && !u->addr) {
err = unix_autobind(sk);
if (err)
goto out;
@@ -1670,6 +1683,8 @@ static void unix_sock_inherit_flags(const struct socket *old,
{
if (test_bit(SOCK_PASSCRED, &old->flags))
set_bit(SOCK_PASSCRED, &new->flags);
+ if (test_bit(SOCK_PASSPIDFD, &old->flags))
+ set_bit(SOCK_PASSPIDFD, &new->flags);
if (test_bit(SOCK_PASSSEC, &old->flags))
set_bit(SOCK_PASSSEC, &new->flags);
}
@@ -1819,8 +1834,10 @@ static bool unix_passcred_enabled(const struct socket *sock,
const struct sock *other)
{
return test_bit(SOCK_PASSCRED, &sock->flags) ||
+ test_bit(SOCK_PASSPIDFD, &sock->flags) ||
!other->sk_socket ||
- test_bit(SOCK_PASSCRED, &other->sk_socket->flags);
+ test_bit(SOCK_PASSCRED, &other->sk_socket->flags) ||
+ test_bit(SOCK_PASSPIDFD, &other->sk_socket->flags);
}
/*
@@ -1839,24 +1856,6 @@ static void maybe_add_creds(struct sk_buff *skb, const struct socket *sock,
}
}
-static int maybe_init_creds(struct scm_cookie *scm,
- struct socket *socket,
- const struct sock *other)
-{
- int err;
- struct msghdr msg = { .msg_controllen = 0 };
-
- err = scm_send(socket, &msg, scm, false);
- if (err)
- return err;
-
- if (unix_passcred_enabled(socket, other)) {
- scm->pid = get_pid(task_tgid(current));
- current_uid_gid(&scm->creds.uid, &scm->creds.gid);
- }
- return err;
-}
-
static bool unix_skb_scm_eq(struct sk_buff *skb,
struct scm_cookie *scm)
{
@@ -1922,7 +1921,8 @@ static int unix_dgram_sendmsg(struct socket *sock, struct msghdr *msg,
goto out;
}
- if (test_bit(SOCK_PASSCRED, &sock->flags) && !u->addr) {
+ if ((test_bit(SOCK_PASSCRED, &sock->flags) ||
+ test_bit(SOCK_PASSPIDFD, &sock->flags)) && !u->addr) {
err = unix_autobind(sk);
if (err)
goto out;
@@ -2200,19 +2200,25 @@ static int unix_stream_sendmsg(struct socket *sock, struct msghdr *msg,
while (sent < len) {
size = len - sent;
- /* Keep two messages in the pipe so it schedules better */
- size = min_t(int, size, (sk->sk_sndbuf >> 1) - 64);
+ if (unlikely(msg->msg_flags & MSG_SPLICE_PAGES)) {
+ skb = sock_alloc_send_pskb(sk, 0, 0,
+ msg->msg_flags & MSG_DONTWAIT,
+ &err, 0);
+ } else {
+ /* Keep two messages in the pipe so it schedules better */
+ size = min_t(int, size, (sk->sk_sndbuf >> 1) - 64);
- /* allow fallback to order-0 allocations */
- size = min_t(int, size, SKB_MAX_HEAD(0) + UNIX_SKB_FRAGS_SZ);
+ /* allow fallback to order-0 allocations */
+ size = min_t(int, size, SKB_MAX_HEAD(0) + UNIX_SKB_FRAGS_SZ);
- data_len = max_t(int, 0, size - SKB_MAX_HEAD(0));
+ data_len = max_t(int, 0, size - SKB_MAX_HEAD(0));
- data_len = min_t(size_t, size, PAGE_ALIGN(data_len));
+ data_len = min_t(size_t, size, PAGE_ALIGN(data_len));
- skb = sock_alloc_send_pskb(sk, size - data_len, data_len,
- msg->msg_flags & MSG_DONTWAIT, &err,
- get_order(UNIX_SKB_FRAGS_SZ));
+ skb = sock_alloc_send_pskb(sk, size - data_len, data_len,
+ msg->msg_flags & MSG_DONTWAIT, &err,
+ get_order(UNIX_SKB_FRAGS_SZ));
+ }
if (!skb)
goto out_err;
@@ -2224,13 +2230,24 @@ static int unix_stream_sendmsg(struct socket *sock, struct msghdr *msg,
}
fds_sent = true;
- skb_put(skb, size - data_len);
- skb->data_len = data_len;
- skb->len = size;
- err = skb_copy_datagram_from_iter(skb, 0, &msg->msg_iter, size);
- if (err) {
- kfree_skb(skb);
- goto out_err;
+ if (unlikely(msg->msg_flags & MSG_SPLICE_PAGES)) {
+ err = skb_splice_from_iter(skb, &msg->msg_iter, size,
+ sk->sk_allocation);
+ if (err < 0) {
+ kfree_skb(skb);
+ goto out_err;
+ }
+ size = err;
+ refcount_add(size, &sk->sk_wmem_alloc);
+ } else {
+ skb_put(skb, size - data_len);
+ skb->data_len = data_len;
+ skb->len = size;
+ err = skb_copy_datagram_from_iter(skb, 0, &msg->msg_iter, size);
+ if (err) {
+ kfree_skb(skb);
+ goto out_err;
+ }
}
unix_state_lock(other);
@@ -2272,122 +2289,6 @@ out_err:
return sent ? : err;
}
-static ssize_t unix_stream_sendpage(struct socket *socket, struct page *page,
- int offset, size_t size, int flags)
-{
- int err;
- bool send_sigpipe = false;
- bool init_scm = true;
- struct scm_cookie scm;
- struct sock *other, *sk = socket->sk;
- struct sk_buff *skb, *newskb = NULL, *tail = NULL;
-
- if (flags & MSG_OOB)
- return -EOPNOTSUPP;
-
- other = unix_peer(sk);
- if (!other || sk->sk_state != TCP_ESTABLISHED)
- return -ENOTCONN;
-
- if (false) {
-alloc_skb:
- unix_state_unlock(other);
- mutex_unlock(&unix_sk(other)->iolock);
- newskb = sock_alloc_send_pskb(sk, 0, 0, flags & MSG_DONTWAIT,
- &err, 0);
- if (!newskb)
- goto err;
- }
-
- /* we must acquire iolock as we modify already present
- * skbs in the sk_receive_queue and mess with skb->len
- */
- err = mutex_lock_interruptible(&unix_sk(other)->iolock);
- if (err) {
- err = flags & MSG_DONTWAIT ? -EAGAIN : -ERESTARTSYS;
- goto err;
- }
-
- if (sk->sk_shutdown & SEND_SHUTDOWN) {
- err = -EPIPE;
- send_sigpipe = true;
- goto err_unlock;
- }
-
- unix_state_lock(other);
-
- if (sock_flag(other, SOCK_DEAD) ||
- other->sk_shutdown & RCV_SHUTDOWN) {
- err = -EPIPE;
- send_sigpipe = true;
- goto err_state_unlock;
- }
-
- if (init_scm) {
- err = maybe_init_creds(&scm, socket, other);
- if (err)
- goto err_state_unlock;
- init_scm = false;
- }
-
- skb = skb_peek_tail(&other->sk_receive_queue);
- if (tail && tail == skb) {
- skb = newskb;
- } else if (!skb || !unix_skb_scm_eq(skb, &scm)) {
- if (newskb) {
- skb = newskb;
- } else {
- tail = skb;
- goto alloc_skb;
- }
- } else if (newskb) {
- /* this is fast path, we don't necessarily need to
- * call to kfree_skb even though with newskb == NULL
- * this - does no harm
- */
- consume_skb(newskb);
- newskb = NULL;
- }
-
- if (skb_append_pagefrags(skb, page, offset, size)) {
- tail = skb;
- goto alloc_skb;
- }
-
- skb->len += size;
- skb->data_len += size;
- skb->truesize += size;
- refcount_add(size, &sk->sk_wmem_alloc);
-
- if (newskb) {
- err = unix_scm_to_skb(&scm, skb, false);
- if (err)
- goto err_state_unlock;
- spin_lock(&other->sk_receive_queue.lock);
- __skb_queue_tail(&other->sk_receive_queue, newskb);
- spin_unlock(&other->sk_receive_queue.lock);
- }
-
- unix_state_unlock(other);
- mutex_unlock(&unix_sk(other)->iolock);
-
- other->sk_data_ready(other);
- scm_destroy(&scm);
- return size;
-
-err_state_unlock:
- unix_state_unlock(other);
-err_unlock:
- mutex_unlock(&unix_sk(other)->iolock);
-err:
- kfree_skb(newskb);
- if (send_sigpipe && !(flags & MSG_NOSIGNAL))
- send_sig(SIGPIPE, current, 0);
- if (!init_scm)
- scm_destroy(&scm);
- return err;
-}
-
static int unix_seqpacket_sendmsg(struct socket *sock, struct msghdr *msg,
size_t len)
{
@@ -2526,7 +2427,7 @@ int __unix_dgram_recvmsg(struct sock *sk, struct msghdr *msg, size_t size,
}
err = (flags & MSG_TRUNC) ? skb->len - skip : size;
- scm_recv(sock, msg, &scm, flags);
+ scm_recv_unix(sock, msg, &scm, flags);
out_free:
skb_free_datagram(sk, skb);
@@ -2821,7 +2722,8 @@ unlock:
/* Never glue messages from different writers */
if (!unix_skb_scm_eq(skb, &scm))
break;
- } else if (test_bit(SOCK_PASSCRED, &sock->flags)) {
+ } else if (test_bit(SOCK_PASSCRED, &sock->flags) ||
+ test_bit(SOCK_PASSPIDFD, &sock->flags)) {
/* Copy credentials */
scm_set_cred(&scm, UNIXCB(skb).pid, UNIXCB(skb).uid, UNIXCB(skb).gid);
unix_set_secdata(&scm, skb);
@@ -2906,7 +2808,7 @@ unlock:
mutex_unlock(&u->iolock);
if (state->msg)
- scm_recv(sock, state->msg, &scm, flags);
+ scm_recv_unix(sock, state->msg, &scm, flags);
else
scm_destroy(&scm);
out:
diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c
index efb8a0937a13..020cf17ab7e4 100644
--- a/net/vmw_vsock/af_vsock.c
+++ b/net/vmw_vsock/af_vsock.c
@@ -1306,7 +1306,6 @@ static const struct proto_ops vsock_dgram_ops = {
.sendmsg = vsock_dgram_sendmsg,
.recvmsg = vsock_dgram_recvmsg,
.mmap = sock_no_mmap,
- .sendpage = sock_no_sendpage,
.read_skb = vsock_read_skb,
};
@@ -2234,7 +2233,6 @@ static const struct proto_ops vsock_stream_ops = {
.sendmsg = vsock_connectible_sendmsg,
.recvmsg = vsock_connectible_recvmsg,
.mmap = sock_no_mmap,
- .sendpage = sock_no_sendpage,
.set_rcvlowat = vsock_set_rcvlowat,
.read_skb = vsock_read_skb,
};
@@ -2257,7 +2255,6 @@ static const struct proto_ops vsock_seqpacket_ops = {
.sendmsg = vsock_connectible_sendmsg,
.recvmsg = vsock_connectible_recvmsg,
.mmap = sock_no_mmap,
- .sendpage = sock_no_sendpage,
.read_skb = vsock_read_skb,
};
diff --git a/net/wireless/core.c b/net/wireless/core.c
index b3ec9eaec36b..25bc2e50a061 100644
--- a/net/wireless/core.c
+++ b/net/wireless/core.c
@@ -129,6 +129,7 @@ int cfg80211_dev_rename(struct cfg80211_registered_device *rdev,
int result;
ASSERT_RTNL();
+ lockdep_assert_wiphy(&rdev->wiphy);
/* Ignore nop renames */
if (strcmp(newname, wiphy_name(&rdev->wiphy)) == 0)
@@ -195,6 +196,8 @@ int cfg80211_switch_netns(struct cfg80211_registered_device *rdev,
continue;
nl80211_notify_iface(rdev, wdev, NL80211_CMD_DEL_INTERFACE);
}
+
+ wiphy_lock(&rdev->wiphy);
nl80211_notify_wiphy(rdev, NL80211_CMD_DEL_WIPHY);
wiphy_net_set(&rdev->wiphy, net);
@@ -203,6 +206,8 @@ int cfg80211_switch_netns(struct cfg80211_registered_device *rdev,
WARN_ON(err);
nl80211_notify_wiphy(rdev, NL80211_CMD_NEW_WIPHY);
+ wiphy_unlock(&rdev->wiphy);
+
list_for_each_entry(wdev, &rdev->wiphy.wdev_list, list) {
if (!wdev->netdev)
continue;
@@ -360,7 +365,8 @@ static void cfg80211_destroy_iface_wk(struct work_struct *work)
rtnl_unlock();
}
-static void cfg80211_sched_scan_stop_wk(struct work_struct *work)
+static void cfg80211_sched_scan_stop_wk(struct wiphy *wiphy,
+ struct wiphy_work *work)
{
struct cfg80211_registered_device *rdev;
struct cfg80211_sched_scan_request *req, *tmp;
@@ -368,12 +374,10 @@ static void cfg80211_sched_scan_stop_wk(struct work_struct *work)
rdev = container_of(work, struct cfg80211_registered_device,
sched_scan_stop_wk);
- wiphy_lock(&rdev->wiphy);
list_for_each_entry_safe(req, tmp, &rdev->sched_scan_req_list, list) {
if (req->nl_owner_dead)
cfg80211_stop_sched_scan_req(rdev, req, false);
}
- wiphy_unlock(&rdev->wiphy);
}
static void cfg80211_propagate_radar_detect_wk(struct work_struct *work)
@@ -408,6 +412,34 @@ static void cfg80211_propagate_cac_done_wk(struct work_struct *work)
rtnl_unlock();
}
+static void cfg80211_wiphy_work(struct work_struct *work)
+{
+ struct cfg80211_registered_device *rdev;
+ struct wiphy_work *wk;
+
+ rdev = container_of(work, struct cfg80211_registered_device, wiphy_work);
+
+ wiphy_lock(&rdev->wiphy);
+ if (rdev->suspended)
+ goto out;
+
+ spin_lock_irq(&rdev->wiphy_work_lock);
+ wk = list_first_entry_or_null(&rdev->wiphy_work_list,
+ struct wiphy_work, entry);
+ if (wk) {
+ list_del_init(&wk->entry);
+ if (!list_empty(&rdev->wiphy_work_list))
+ schedule_work(work);
+ spin_unlock_irq(&rdev->wiphy_work_lock);
+
+ wk->func(&rdev->wiphy, wk);
+ } else {
+ spin_unlock_irq(&rdev->wiphy_work_lock);
+ }
+out:
+ wiphy_unlock(&rdev->wiphy);
+}
+
/* exported functions */
struct wiphy *wiphy_new_nm(const struct cfg80211_ops *ops, int sizeof_priv,
@@ -495,7 +527,7 @@ use_default_name:
spin_lock_init(&rdev->bss_lock);
INIT_LIST_HEAD(&rdev->bss_list);
INIT_LIST_HEAD(&rdev->sched_scan_req_list);
- INIT_WORK(&rdev->scan_done_wk, __cfg80211_scan_done);
+ wiphy_work_init(&rdev->scan_done_wk, __cfg80211_scan_done);
INIT_DELAYED_WORK(&rdev->dfs_update_channels_wk,
cfg80211_dfs_channels_update_work);
#ifdef CONFIG_CFG80211_WEXT
@@ -508,7 +540,7 @@ use_default_name:
device_enable_async_suspend(&rdev->wiphy.dev);
INIT_WORK(&rdev->destroy_work, cfg80211_destroy_iface_wk);
- INIT_WORK(&rdev->sched_scan_stop_wk, cfg80211_sched_scan_stop_wk);
+ wiphy_work_init(&rdev->sched_scan_stop_wk, cfg80211_sched_scan_stop_wk);
INIT_WORK(&rdev->sched_scan_res_wk, cfg80211_sched_scan_results_wk);
INIT_WORK(&rdev->propagate_radar_detect_wk,
cfg80211_propagate_radar_detect_wk);
@@ -533,6 +565,9 @@ use_default_name:
return NULL;
}
+ INIT_WORK(&rdev->wiphy_work, cfg80211_wiphy_work);
+ INIT_LIST_HEAD(&rdev->wiphy_work_list);
+ spin_lock_init(&rdev->wiphy_work_lock);
INIT_WORK(&rdev->rfkill_block, cfg80211_rfkill_block_work);
INIT_WORK(&rdev->conn_work, cfg80211_conn_work);
INIT_WORK(&rdev->event_work, cfg80211_event_work);
@@ -721,22 +756,6 @@ int wiphy_register(struct wiphy *wiphy)
return -EINVAL;
}
- /*
- * if a wiphy has unsupported modes for regulatory channel enforcement,
- * opt-out of enforcement checking
- */
- if (wiphy->interface_modes & ~(BIT(NL80211_IFTYPE_STATION) |
- BIT(NL80211_IFTYPE_P2P_CLIENT) |
- BIT(NL80211_IFTYPE_AP) |
- BIT(NL80211_IFTYPE_MESH_POINT) |
- BIT(NL80211_IFTYPE_P2P_GO) |
- BIT(NL80211_IFTYPE_ADHOC) |
- BIT(NL80211_IFTYPE_P2P_DEVICE) |
- BIT(NL80211_IFTYPE_NAN) |
- BIT(NL80211_IFTYPE_AP_VLAN) |
- BIT(NL80211_IFTYPE_MONITOR)))
- wiphy->regulatory_flags |= REGULATORY_IGNORE_STALE_KICKOFF;
-
if (WARN_ON((wiphy->regulatory_flags & REGULATORY_WIPHY_SELF_MANAGED) &&
(wiphy->regulatory_flags &
(REGULATORY_CUSTOM_REG |
@@ -941,8 +960,10 @@ int wiphy_register(struct wiphy *wiphy)
rdev->wiphy.features |= NL80211_FEATURE_SCAN_FLUSH;
rtnl_lock();
+ wiphy_lock(&rdev->wiphy);
res = device_add(&rdev->wiphy.dev);
if (res) {
+ wiphy_unlock(&rdev->wiphy);
rtnl_unlock();
return res;
}
@@ -956,6 +977,7 @@ int wiphy_register(struct wiphy *wiphy)
cfg80211_debugfs_rdev_add(rdev);
nl80211_notify_wiphy(rdev, NL80211_CMD_NEW_WIPHY);
+ wiphy_unlock(&rdev->wiphy);
/* set up regulatory info */
wiphy_regulatory_register(wiphy);
@@ -1027,6 +1049,31 @@ void wiphy_rfkill_start_polling(struct wiphy *wiphy)
}
EXPORT_SYMBOL(wiphy_rfkill_start_polling);
+void cfg80211_process_wiphy_works(struct cfg80211_registered_device *rdev)
+{
+ unsigned int runaway_limit = 100;
+ unsigned long flags;
+
+ lockdep_assert_held(&rdev->wiphy.mtx);
+
+ spin_lock_irqsave(&rdev->wiphy_work_lock, flags);
+ while (!list_empty(&rdev->wiphy_work_list)) {
+ struct wiphy_work *wk;
+
+ wk = list_first_entry(&rdev->wiphy_work_list,
+ struct wiphy_work, entry);
+ list_del_init(&wk->entry);
+ spin_unlock_irqrestore(&rdev->wiphy_work_lock, flags);
+
+ wk->func(&rdev->wiphy, wk);
+
+ spin_lock_irqsave(&rdev->wiphy_work_lock, flags);
+ if (WARN_ON(--runaway_limit == 0))
+ INIT_LIST_HEAD(&rdev->wiphy_work_list);
+ }
+ spin_unlock_irqrestore(&rdev->wiphy_work_lock, flags);
+}
+
void wiphy_unregister(struct wiphy *wiphy)
{
struct cfg80211_registered_device *rdev = wiphy_to_rdev(wiphy);
@@ -1065,25 +1112,29 @@ void wiphy_unregister(struct wiphy *wiphy)
cfg80211_rdev_list_generation++;
device_del(&rdev->wiphy.dev);
+#ifdef CONFIG_PM
+ if (rdev->wiphy.wowlan_config && rdev->ops->set_wakeup)
+ rdev_set_wakeup(rdev, false);
+#endif
+
+ /* surely nothing is reachable now, clean up work */
+ cfg80211_process_wiphy_works(rdev);
wiphy_unlock(&rdev->wiphy);
rtnl_unlock();
- flush_work(&rdev->scan_done_wk);
+ /* this has nothing to do now but make sure it's gone */
+ cancel_work_sync(&rdev->wiphy_work);
+
cancel_work_sync(&rdev->conn_work);
flush_work(&rdev->event_work);
cancel_delayed_work_sync(&rdev->dfs_update_channels_wk);
cancel_delayed_work_sync(&rdev->background_cac_done_wk);
flush_work(&rdev->destroy_work);
- flush_work(&rdev->sched_scan_stop_wk);
flush_work(&rdev->propagate_radar_detect_wk);
flush_work(&rdev->propagate_cac_done_wk);
flush_work(&rdev->mgmt_registrations_update_wk);
flush_work(&rdev->background_cac_abort_wk);
-#ifdef CONFIG_PM
- if (rdev->wiphy.wowlan_config && rdev->ops->set_wakeup)
- rdev_set_wakeup(rdev, false);
-#endif
cfg80211_rdev_free_wowlan(rdev);
cfg80211_rdev_free_coalesce(rdev);
}
@@ -1145,8 +1196,6 @@ static void _cfg80211_unregister_wdev(struct wireless_dev *wdev,
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;
@@ -1178,10 +1227,6 @@ static void _cfg80211_unregister_wdev(struct wireless_dev *wdev,
kfree_sensitive(wdev->wext.keys);
wdev->wext.keys = NULL;
#endif
- /* only initialized if we have a netdev */
- if (wdev->netdev)
- flush_work(&wdev->disconnect_wk);
-
cfg80211_cqm_config_free(wdev);
/*
@@ -1455,6 +1500,9 @@ static int cfg80211_netdev_notifier_call(struct notifier_block *nb,
cfg80211_leave(rdev, wdev);
cfg80211_remove_links(wdev);
wiphy_unlock(&rdev->wiphy);
+ /* since we just did cfg80211_leave() nothing to do there */
+ cancel_work_sync(&wdev->disconnect_wk);
+ cancel_work_sync(&wdev->pmsr_free_wk);
break;
case NETDEV_DOWN:
wiphy_lock(&rdev->wiphy);
@@ -1564,6 +1612,66 @@ static struct pernet_operations cfg80211_pernet_ops = {
.exit = cfg80211_pernet_exit,
};
+void wiphy_work_queue(struct wiphy *wiphy, struct wiphy_work *work)
+{
+ struct cfg80211_registered_device *rdev = wiphy_to_rdev(wiphy);
+ unsigned long flags;
+
+ spin_lock_irqsave(&rdev->wiphy_work_lock, flags);
+ if (list_empty(&work->entry))
+ list_add_tail(&work->entry, &rdev->wiphy_work_list);
+ spin_unlock_irqrestore(&rdev->wiphy_work_lock, flags);
+
+ schedule_work(&rdev->wiphy_work);
+}
+EXPORT_SYMBOL_GPL(wiphy_work_queue);
+
+void wiphy_work_cancel(struct wiphy *wiphy, struct wiphy_work *work)
+{
+ struct cfg80211_registered_device *rdev = wiphy_to_rdev(wiphy);
+ unsigned long flags;
+
+ lockdep_assert_held(&wiphy->mtx);
+
+ spin_lock_irqsave(&rdev->wiphy_work_lock, flags);
+ if (!list_empty(&work->entry))
+ list_del_init(&work->entry);
+ spin_unlock_irqrestore(&rdev->wiphy_work_lock, flags);
+}
+EXPORT_SYMBOL_GPL(wiphy_work_cancel);
+
+void wiphy_delayed_work_timer(struct timer_list *t)
+{
+ struct wiphy_delayed_work *dwork = from_timer(dwork, t, timer);
+
+ wiphy_work_queue(dwork->wiphy, &dwork->work);
+}
+EXPORT_SYMBOL(wiphy_delayed_work_timer);
+
+void wiphy_delayed_work_queue(struct wiphy *wiphy,
+ struct wiphy_delayed_work *dwork,
+ unsigned long delay)
+{
+ if (!delay) {
+ wiphy_work_queue(wiphy, &dwork->work);
+ return;
+ }
+
+ dwork->wiphy = wiphy;
+ mod_timer(&dwork->timer, jiffies + delay);
+}
+EXPORT_SYMBOL_GPL(wiphy_delayed_work_queue);
+
+void wiphy_delayed_work_cancel(struct wiphy *wiphy,
+ struct wiphy_delayed_work *dwork)
+{
+ lockdep_assert_held(&wiphy->mtx);
+
+ del_timer_sync(&dwork->timer);
+ wiphy_work_cancel(wiphy, &dwork->work);
+}
+EXPORT_SYMBOL_GPL(wiphy_delayed_work_cancel);
+
static int __init cfg80211_init(void)
{
int err;
diff --git a/net/wireless/core.h b/net/wireless/core.h
index 7c61752f6d83..8a807b609ef7 100644
--- a/net/wireless/core.h
+++ b/net/wireless/core.h
@@ -75,7 +75,7 @@ struct cfg80211_registered_device {
struct sk_buff *scan_msg;
struct list_head sched_scan_req_list;
time64_t suspend_at;
- struct work_struct scan_done_wk;
+ struct wiphy_work scan_done_wk;
struct genl_info *cur_cmd_info;
@@ -95,7 +95,7 @@ struct cfg80211_registered_device {
struct cfg80211_coalesce *coalesce;
struct work_struct destroy_work;
- struct work_struct sched_scan_stop_wk;
+ struct wiphy_work sched_scan_stop_wk;
struct work_struct sched_scan_res_wk;
struct cfg80211_chan_def radar_chandef;
@@ -108,6 +108,12 @@ struct cfg80211_registered_device {
/* lock for all wdev lists */
spinlock_t mgmt_registrations_lock;
+ struct work_struct wiphy_work;
+ struct list_head wiphy_work_list;
+ /* protects the list above */
+ spinlock_t wiphy_work_lock;
+ bool suspended;
+
/* must be last because of the way we do wiphy_priv(),
* and it should at least be aligned to NETDEV_ALIGN */
struct wiphy wiphy __aligned(NETDEV_ALIGN);
@@ -435,7 +441,7 @@ bool cfg80211_valid_key_idx(struct cfg80211_registered_device *rdev,
int cfg80211_validate_key_settings(struct cfg80211_registered_device *rdev,
struct key_params *params, int key_idx,
bool pairwise, const u8 *mac_addr);
-void __cfg80211_scan_done(struct work_struct *wk);
+void __cfg80211_scan_done(struct wiphy *wiphy, struct wiphy_work *wk);
void ___cfg80211_scan_done(struct cfg80211_registered_device *rdev,
bool send_message);
void cfg80211_add_sched_scan_req(struct cfg80211_registered_device *rdev,
@@ -453,6 +459,7 @@ int cfg80211_change_iface(struct cfg80211_registered_device *rdev,
struct net_device *dev, enum nl80211_iftype ntype,
struct vif_params *params);
void cfg80211_process_rdev_events(struct cfg80211_registered_device *rdev);
+void cfg80211_process_wiphy_works(struct cfg80211_registered_device *rdev);
void cfg80211_process_wdev_events(struct wireless_dev *wdev);
bool cfg80211_does_bw_fit_range(const struct ieee80211_freq_range *freq_range,
@@ -569,5 +576,6 @@ void cfg80211_remove_link(struct wireless_dev *wdev, unsigned int link_id);
void cfg80211_remove_links(struct wireless_dev *wdev);
int cfg80211_remove_virtual_intf(struct cfg80211_registered_device *rdev,
struct wireless_dev *wdev);
+void cfg80211_wdev_release_link_bsses(struct wireless_dev *wdev, u16 link_mask);
#endif /* __NET_WIRELESS_CORE_H */
diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index 087d60c0f6e4..0da2e6a2a7ea 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -5,7 +5,7 @@
* Copyright 2006-2010 Johannes Berg <johannes@sipsolutions.net>
* Copyright 2013-2014 Intel Mobile Communications GmbH
* Copyright 2015-2017 Intel Deutschland GmbH
- * Copyright (C) 2018-2022 Intel Corporation
+ * Copyright (C) 2018-2023 Intel Corporation
*/
#include <linux/if.h>
@@ -816,6 +816,7 @@ static const struct nla_policy nl80211_policy[NUM_NL80211_ATTR] = {
[NL80211_ATTR_MAX_HW_TIMESTAMP_PEERS] = { .type = NLA_U16 },
[NL80211_ATTR_HW_TIMESTAMP_ENABLED] = { .type = NLA_FLAG },
[NL80211_ATTR_EMA_RNR_ELEMS] = { .type = NLA_NESTED },
+ [NL80211_ATTR_MLO_LINK_DISABLED] = { .type = NLA_FLAG },
};
/* policy for the key attributes */
@@ -3081,6 +3082,7 @@ static int nl80211_dump_wiphy(struct sk_buff *skb, struct netlink_callback *cb)
if (state->filter_wiphy != -1 &&
state->filter_wiphy != rdev->wiphy_idx)
continue;
+ wiphy_lock(&rdev->wiphy);
/* attempt to fit multiple wiphy data chunks into the skb */
do {
ret = nl80211_send_wiphy(rdev, NL80211_CMD_NEW_WIPHY,
@@ -3107,6 +3109,7 @@ static int nl80211_dump_wiphy(struct sk_buff *skb, struct netlink_callback *cb)
cb->min_dump_alloc < 4096) {
cb->min_dump_alloc = 4096;
state->split_start = 0;
+ wiphy_unlock(&rdev->wiphy);
rtnl_unlock();
return 1;
}
@@ -3114,6 +3117,7 @@ static int nl80211_dump_wiphy(struct sk_buff *skb, struct netlink_callback *cb)
break;
}
} while (state->split_start > 0);
+ wiphy_unlock(&rdev->wiphy);
break;
}
rtnl_unlock();
@@ -6365,12 +6369,27 @@ bool nl80211_put_sta_rate(struct sk_buff *msg, struct rate_info *info, int attr)
return false;
switch (info->bw) {
+ case RATE_INFO_BW_1:
+ rate_flg = NL80211_RATE_INFO_1_MHZ_WIDTH;
+ break;
+ case RATE_INFO_BW_2:
+ rate_flg = NL80211_RATE_INFO_2_MHZ_WIDTH;
+ break;
+ case RATE_INFO_BW_4:
+ rate_flg = NL80211_RATE_INFO_4_MHZ_WIDTH;
+ break;
case RATE_INFO_BW_5:
rate_flg = NL80211_RATE_INFO_5_MHZ_WIDTH;
break;
+ case RATE_INFO_BW_8:
+ rate_flg = NL80211_RATE_INFO_8_MHZ_WIDTH;
+ break;
case RATE_INFO_BW_10:
rate_flg = NL80211_RATE_INFO_10_MHZ_WIDTH;
break;
+ case RATE_INFO_BW_16:
+ rate_flg = NL80211_RATE_INFO_16_MHZ_WIDTH;
+ break;
default:
WARN_ON(1);
fallthrough;
@@ -6429,6 +6448,14 @@ bool nl80211_put_sta_rate(struct sk_buff *msg, struct rate_info *info, int attr)
nla_put_u8(msg, NL80211_RATE_INFO_HE_RU_ALLOC,
info->he_ru_alloc))
return false;
+ } else if (info->flags & RATE_INFO_FLAGS_S1G_MCS) {
+ if (nla_put_u8(msg, NL80211_RATE_INFO_S1G_MCS, info->mcs))
+ return false;
+ if (nla_put_u8(msg, NL80211_RATE_INFO_S1G_NSS, info->nss))
+ return false;
+ if (info->flags & RATE_INFO_FLAGS_SHORT_GI &&
+ nla_put_flag(msg, NL80211_RATE_INFO_SHORT_GI))
+ return false;
} else if (info->flags & RATE_INFO_FLAGS_EHT_MCS) {
if (nla_put_u8(msg, NL80211_RATE_INFO_EHT_MCS, info->mcs))
return false;
@@ -11112,6 +11139,9 @@ static int nl80211_associate(struct sk_buff *skb, struct genl_info *info)
goto free;
}
}
+
+ req.links[link_id].disabled =
+ nla_get_flag(attrs[NL80211_ATTR_MLO_LINK_DISABLED]);
}
if (!req.links[req.link_id].bss) {
@@ -11126,6 +11156,13 @@ static int nl80211_associate(struct sk_buff *skb, struct genl_info *info)
goto free;
}
+ if (req.links[req.link_id].disabled) {
+ GENL_SET_ERR_MSG(info,
+ "cannot have assoc link disabled");
+ err = -EINVAL;
+ goto free;
+ }
+
kfree(attrs);
attrs = NULL;
} else {
@@ -12225,6 +12262,7 @@ static int nl80211_tdls_mgmt(struct sk_buff *skb, struct genl_info *info)
u32 peer_capability = 0;
u16 status_code;
u8 *peer;
+ int link_id;
bool initiator;
if (!(rdev->wiphy.flags & WIPHY_FLAG_SUPPORTS_TDLS) ||
@@ -12246,8 +12284,9 @@ static int nl80211_tdls_mgmt(struct sk_buff *skb, struct genl_info *info)
if (info->attrs[NL80211_ATTR_TDLS_PEER_CAPABILITY])
peer_capability =
nla_get_u32(info->attrs[NL80211_ATTR_TDLS_PEER_CAPABILITY]);
+ link_id = nl80211_link_id_or_invalid(info->attrs);
- return rdev_tdls_mgmt(rdev, dev, peer, action_code,
+ return rdev_tdls_mgmt(rdev, dev, peer, link_id, action_code,
dialog_token, status_code, peer_capability,
initiator,
nla_data(info->attrs[NL80211_ATTR_IE]),
@@ -17114,7 +17153,8 @@ 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 = IFLAGS(NL80211_FLAG_NEED_NETDEV_UP),
+ .internal_flags = IFLAGS(NL80211_FLAG_NEED_NETDEV_UP |
+ NL80211_FLAG_MLO_VALID_LINK_ID),
},
{
.cmd = NL80211_CMD_TDLS_OPER,
@@ -18248,6 +18288,76 @@ void nl80211_send_disconnected(struct cfg80211_registered_device *rdev,
nlmsg_free(msg);
}
+void cfg80211_links_removed(struct net_device *dev, u16 link_mask)
+{
+ struct wireless_dev *wdev = dev->ieee80211_ptr;
+ struct wiphy *wiphy = wdev->wiphy;
+ struct cfg80211_registered_device *rdev = wiphy_to_rdev(wiphy);
+ struct sk_buff *msg;
+ struct nlattr *links;
+ void *hdr;
+
+ ASSERT_WDEV_LOCK(wdev);
+ trace_cfg80211_links_removed(dev, link_mask);
+
+ if (WARN_ON(wdev->iftype != NL80211_IFTYPE_STATION &&
+ wdev->iftype != NL80211_IFTYPE_P2P_CLIENT))
+ return;
+
+ if (WARN_ON(!wdev->valid_links || !link_mask ||
+ (wdev->valid_links & link_mask) != link_mask ||
+ wdev->valid_links == link_mask))
+ return;
+
+ cfg80211_wdev_release_link_bsses(wdev, link_mask);
+ wdev->valid_links &= ~link_mask;
+
+ msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
+ if (!msg)
+ return;
+
+ hdr = nl80211hdr_put(msg, 0, 0, 0, NL80211_CMD_LINKS_REMOVED);
+ if (!hdr) {
+ nlmsg_free(msg);
+ return;
+ }
+
+ if (nla_put_u32(msg, NL80211_ATTR_WIPHY, rdev->wiphy_idx) ||
+ nla_put_u32(msg, NL80211_ATTR_IFINDEX, dev->ifindex))
+ goto nla_put_failure;
+
+ links = nla_nest_start(msg, NL80211_ATTR_MLO_LINKS);
+ if (!links)
+ goto nla_put_failure;
+
+ while (link_mask) {
+ struct nlattr *link;
+ int link_id = __ffs(link_mask);
+
+ link = nla_nest_start(msg, link_id + 1);
+ if (!link)
+ goto nla_put_failure;
+
+ if (nla_put_u8(msg, NL80211_ATTR_MLO_LINK_ID, link_id))
+ goto nla_put_failure;
+
+ nla_nest_end(msg, link);
+ link_mask &= ~(1 << link_id);
+ }
+
+ nla_nest_end(msg, links);
+
+ genlmsg_end(msg, hdr);
+
+ genlmsg_multicast_netns(&nl80211_fam, wiphy_net(&rdev->wiphy), msg, 0,
+ NL80211_MCGRP_MLME, GFP_KERNEL);
+ return;
+
+ nla_put_failure:
+ nlmsg_free(msg);
+}
+EXPORT_SYMBOL(cfg80211_links_removed);
+
void nl80211_send_ibss_bssid(struct cfg80211_registered_device *rdev,
struct net_device *netdev, const u8 *bssid,
gfp_t gfp)
@@ -19774,7 +19884,8 @@ static int nl80211_netlink_notify(struct notifier_block * nb,
list) {
if (sched_scan_req->owner_nlportid == notify->portid) {
sched_scan_req->nl_owner_dead = true;
- schedule_work(&rdev->sched_scan_stop_wk);
+ wiphy_work_queue(&rdev->wiphy,
+ &rdev->sched_scan_stop_wk);
}
}
diff --git a/net/wireless/pmsr.c b/net/wireless/pmsr.c
index 2bc647720cda..77000a264855 100644
--- a/net/wireless/pmsr.c
+++ b/net/wireless/pmsr.c
@@ -1,6 +1,6 @@
/* SPDX-License-Identifier: GPL-2.0 */
/*
- * Copyright (C) 2018 - 2021 Intel Corporation
+ * Copyright (C) 2018 - 2021, 2023 Intel Corporation
*/
#include <net/cfg80211.h>
#include "core.h"
@@ -623,9 +623,11 @@ void cfg80211_pmsr_free_wk(struct work_struct *work)
struct wireless_dev *wdev = container_of(work, struct wireless_dev,
pmsr_free_wk);
+ wiphy_lock(wdev->wiphy);
wdev_lock(wdev);
cfg80211_pmsr_process_abort(wdev);
wdev_unlock(wdev);
+ wiphy_unlock(wdev->wiphy);
}
void cfg80211_pmsr_wdev_down(struct wireless_dev *wdev)
diff --git a/net/wireless/rdev-ops.h b/net/wireless/rdev-ops.h
index 69b508743e57..90bb7ac4b930 100644
--- a/net/wireless/rdev-ops.h
+++ b/net/wireless/rdev-ops.h
@@ -407,6 +407,18 @@ static inline int rdev_change_bss(struct cfg80211_registered_device *rdev,
return ret;
}
+static inline void rdev_inform_bss(struct cfg80211_registered_device *rdev,
+ struct cfg80211_bss *bss,
+ const struct cfg80211_bss_ies *ies,
+ void *drv_data)
+
+{
+ trace_rdev_inform_bss(&rdev->wiphy, bss);
+ if (rdev->ops->inform_bss)
+ rdev->ops->inform_bss(&rdev->wiphy, bss, ies, drv_data);
+ trace_rdev_return_void(&rdev->wiphy);
+}
+
static inline int rdev_set_txq_params(struct cfg80211_registered_device *rdev,
struct net_device *dev,
struct ieee80211_txq_params *params)
@@ -899,17 +911,18 @@ static inline int rdev_set_rekey_data(struct cfg80211_registered_device *rdev,
static inline int rdev_tdls_mgmt(struct cfg80211_registered_device *rdev,
struct net_device *dev, u8 *peer,
- u8 action_code, u8 dialog_token,
- u16 status_code, u32 peer_capability,
- bool initiator, const u8 *buf, size_t len)
+ int link_id, u8 action_code,
+ u8 dialog_token, u16 status_code,
+ u32 peer_capability, bool initiator,
+ const u8 *buf, size_t len)
{
int ret;
- trace_rdev_tdls_mgmt(&rdev->wiphy, dev, peer, action_code,
+ trace_rdev_tdls_mgmt(&rdev->wiphy, dev, peer, link_id, action_code,
dialog_token, status_code, peer_capability,
initiator, buf, len);
- ret = rdev->ops->tdls_mgmt(&rdev->wiphy, dev, peer, action_code,
- dialog_token, status_code, peer_capability,
- initiator, buf, len);
+ ret = rdev->ops->tdls_mgmt(&rdev->wiphy, dev, peer, link_id,
+ action_code, dialog_token, status_code,
+ peer_capability, initiator, buf, len);
trace_rdev_return_int(&rdev->wiphy, ret);
return ret;
}
diff --git a/net/wireless/reg.c b/net/wireless/reg.c
index 26f11e4746c0..0317cf9da307 100644
--- a/net/wireless/reg.c
+++ b/net/wireless/reg.c
@@ -5,7 +5,7 @@
* Copyright 2008-2011 Luis R. Rodriguez <mcgrof@qca.qualcomm.com>
* Copyright 2013-2014 Intel Mobile Communications GmbH
* Copyright 2017 Intel Deutschland GmbH
- * Copyright (C) 2018 - 2022 Intel Corporation
+ * Copyright (C) 2018 - 2023 Intel Corporation
*
* Permission to use, copy, modify, and/or distribute this software for any
* purpose with or without fee is hereby granted, provided that the above
@@ -1587,6 +1587,8 @@ static u32 map_regdom_flags(u32 rd_flags)
channel_flags |= IEEE80211_CHAN_NO_HE;
if (rd_flags & NL80211_RRF_NO_320MHZ)
channel_flags |= IEEE80211_CHAN_NO_320MHZ;
+ if (rd_flags & NL80211_RRF_NO_EHT)
+ channel_flags |= IEEE80211_CHAN_NO_EHT;
return channel_flags;
}
@@ -2352,7 +2354,7 @@ static bool reg_wdev_chan_valid(struct wiphy *wiphy, struct wireless_dev *wdev)
if (!wdev->valid_links && link > 0)
break;
- if (!(wdev->valid_links & BIT(link)))
+ if (wdev->valid_links && !(wdev->valid_links & BIT(link)))
continue;
switch (iftype) {
case NL80211_IFTYPE_AP:
@@ -2391,9 +2393,17 @@ static bool reg_wdev_chan_valid(struct wiphy *wiphy, struct wireless_dev *wdev)
case NL80211_IFTYPE_P2P_DEVICE:
/* no enforcement required */
break;
+ case NL80211_IFTYPE_OCB:
+ if (!wdev->u.ocb.chandef.chan)
+ continue;
+ chandef = wdev->u.ocb.chandef;
+ break;
+ case NL80211_IFTYPE_NAN:
+ /* we have no info, but NAN is also pretty universal */
+ continue;
default:
/* others not implemented for now */
- WARN_ON(1);
+ WARN_ON_ONCE(1);
break;
}
@@ -2452,9 +2462,7 @@ static void reg_check_chans_work(struct work_struct *work)
rtnl_lock();
list_for_each_entry(rdev, &cfg80211_rdev_list, list)
- if (!(rdev->wiphy.regulatory_flags &
- REGULATORY_IGNORE_STALE_KICKOFF))
- reg_leave_invalid_chans(&rdev->wiphy);
+ reg_leave_invalid_chans(&rdev->wiphy);
rtnl_unlock();
}
diff --git a/net/wireless/scan.c b/net/wireless/scan.c
index c501db7bbdb3..8bf00caf5d29 100644
--- a/net/wireless/scan.c
+++ b/net/wireless/scan.c
@@ -96,6 +96,7 @@ MODULE_PARM_DESC(bss_entries_limit,
* colocated and can be discovered via legacy bands.
* @short_ssid_valid: short_ssid is valid and can be used
* @short_ssid: the short SSID for this SSID
+ * @psd_20: The 20MHz PSD EIRP of the primary 20MHz channel for the reported AP
*/
struct cfg80211_colocated_ap {
struct list_head list;
@@ -111,6 +112,7 @@ struct cfg80211_colocated_ap {
transmitted_bssid:1,
colocated_ess:1,
short_ssid_valid:1;
+ s8 psd_20;
};
static void bss_free(struct cfg80211_internal_bss *bss)
@@ -218,6 +220,10 @@ bool cfg80211_is_element_inherited(const struct element *elem,
if (elem->id == WLAN_EID_MULTIPLE_BSSID)
return false;
+ if (elem->id == WLAN_EID_EXTENSION && elem->datalen > 1 &&
+ elem->data[0] == WLAN_EID_EXT_EHT_MULTI_LINK)
+ return false;
+
if (!non_inherit_elem || non_inherit_elem->datalen < 2)
return true;
@@ -259,117 +265,152 @@ bool cfg80211_is_element_inherited(const struct element *elem,
}
EXPORT_SYMBOL(cfg80211_is_element_inherited);
-static size_t cfg80211_gen_new_ie(const u8 *ie, size_t ielen,
- const u8 *subelement, size_t subie_len,
- u8 *new_ie, gfp_t gfp)
+static size_t cfg80211_copy_elem_with_frags(const struct element *elem,
+ const u8 *ie, size_t ie_len,
+ u8 **pos, u8 *buf, size_t buf_len)
{
- u8 *pos, *tmp;
- const u8 *tmp_old, *tmp_new;
- const struct element *non_inherit_elem;
- u8 *sub_copy;
+ if (WARN_ON((u8 *)elem < ie || elem->data > ie + ie_len ||
+ elem->data + elem->datalen > ie + ie_len))
+ return 0;
- /* copy subelement as we need to change its content to
- * mark an ie after it is processed.
- */
- sub_copy = kmemdup(subelement, subie_len, gfp);
- if (!sub_copy)
+ if (elem->datalen + 2 > buf + buf_len - *pos)
return 0;
- pos = &new_ie[0];
+ memcpy(*pos, elem, elem->datalen + 2);
+ *pos += elem->datalen + 2;
+
+ /* Finish if it is not fragmented */
+ if (elem->datalen != 255)
+ return *pos - buf;
+
+ ie_len = ie + ie_len - elem->data - elem->datalen;
+ ie = (const u8 *)elem->data + elem->datalen;
+
+ for_each_element(elem, ie, ie_len) {
+ if (elem->id != WLAN_EID_FRAGMENT)
+ break;
+
+ if (elem->datalen + 2 > buf + buf_len - *pos)
+ return 0;
+
+ memcpy(*pos, elem, elem->datalen + 2);
+ *pos += elem->datalen + 2;
- /* set new ssid */
- tmp_new = cfg80211_find_ie(WLAN_EID_SSID, sub_copy, subie_len);
- if (tmp_new) {
- memcpy(pos, tmp_new, tmp_new[1] + 2);
- pos += (tmp_new[1] + 2);
+ if (elem->datalen != 255)
+ break;
}
- /* get non inheritance list if exists */
- non_inherit_elem =
- cfg80211_find_ext_elem(WLAN_EID_EXT_NON_INHERITANCE,
- sub_copy, subie_len);
+ return *pos - buf;
+}
- /* go through IEs in ie (skip SSID) and subelement,
- * merge them into new_ie
+static size_t cfg80211_gen_new_ie(const u8 *ie, size_t ielen,
+ const u8 *subie, size_t subie_len,
+ u8 *new_ie, size_t new_ie_len)
+{
+ const struct element *non_inherit_elem, *parent, *sub;
+ u8 *pos = new_ie;
+ u8 id, ext_id;
+ unsigned int match_len;
+
+ non_inherit_elem = cfg80211_find_ext_elem(WLAN_EID_EXT_NON_INHERITANCE,
+ subie, subie_len);
+
+ /* We copy the elements one by one from the parent to the generated
+ * elements.
+ * If they are not inherited (included in subie or in the non
+ * inheritance element), then we copy all occurrences the first time
+ * we see this element type.
*/
- tmp_old = cfg80211_find_ie(WLAN_EID_SSID, ie, ielen);
- tmp_old = (tmp_old) ? tmp_old + tmp_old[1] + 2 : ie;
-
- while (tmp_old + 2 - ie <= ielen &&
- tmp_old + tmp_old[1] + 2 - ie <= ielen) {
- if (tmp_old[0] == 0) {
- tmp_old++;
+ for_each_element(parent, ie, ielen) {
+ if (parent->id == WLAN_EID_FRAGMENT)
continue;
+
+ if (parent->id == WLAN_EID_EXTENSION) {
+ if (parent->datalen < 1)
+ continue;
+
+ id = WLAN_EID_EXTENSION;
+ ext_id = parent->data[0];
+ match_len = 1;
+ } else {
+ id = parent->id;
+ match_len = 0;
}
- if (tmp_old[0] == WLAN_EID_EXTENSION)
- tmp = (u8 *)cfg80211_find_ext_ie(tmp_old[2], sub_copy,
- subie_len);
- else
- tmp = (u8 *)cfg80211_find_ie(tmp_old[0], sub_copy,
- subie_len);
+ /* Find first occurrence in subie */
+ sub = cfg80211_find_elem_match(id, subie, subie_len,
+ &ext_id, match_len, 0);
- if (!tmp) {
- const struct element *old_elem = (void *)tmp_old;
+ /* Copy from parent if not in subie and inherited */
+ if (!sub &&
+ cfg80211_is_element_inherited(parent, non_inherit_elem)) {
+ if (!cfg80211_copy_elem_with_frags(parent,
+ ie, ielen,
+ &pos, new_ie,
+ new_ie_len))
+ return 0;
- /* ie in old ie but not in subelement */
- if (cfg80211_is_element_inherited(old_elem,
- non_inherit_elem)) {
- memcpy(pos, tmp_old, tmp_old[1] + 2);
- pos += tmp_old[1] + 2;
- }
- } else {
- /* ie in transmitting ie also in subelement,
- * copy from subelement and flag the ie in subelement
- * as copied (by setting eid field to WLAN_EID_SSID,
- * which is skipped anyway).
- * For vendor ie, compare OUI + type + subType to
- * determine if they are the same ie.
- */
- if (tmp_old[0] == WLAN_EID_VENDOR_SPECIFIC) {
- if (tmp_old[1] >= 5 && tmp[1] >= 5 &&
- !memcmp(tmp_old + 2, tmp + 2, 5)) {
- /* same vendor ie, copy from
- * subelement
- */
- memcpy(pos, tmp, tmp[1] + 2);
- pos += tmp[1] + 2;
- tmp[0] = WLAN_EID_SSID;
- } else {
- memcpy(pos, tmp_old, tmp_old[1] + 2);
- pos += tmp_old[1] + 2;
- }
- } else {
- /* copy ie from subelement into new ie */
- memcpy(pos, tmp, tmp[1] + 2);
- pos += tmp[1] + 2;
- tmp[0] = WLAN_EID_SSID;
- }
+ continue;
}
- if (tmp_old + tmp_old[1] + 2 - ie == ielen)
- break;
+ /* Already copied if an earlier element had the same type */
+ if (cfg80211_find_elem_match(id, ie, (u8 *)parent - ie,
+ &ext_id, match_len, 0))
+ continue;
- tmp_old += tmp_old[1] + 2;
+ /* Not inheriting, copy all similar elements from subie */
+ while (sub) {
+ if (!cfg80211_copy_elem_with_frags(sub,
+ subie, subie_len,
+ &pos, new_ie,
+ new_ie_len))
+ return 0;
+
+ sub = cfg80211_find_elem_match(id,
+ sub->data + sub->datalen,
+ subie_len + subie -
+ (sub->data +
+ sub->datalen),
+ &ext_id, match_len, 0);
+ }
}
- /* go through subelement again to check if there is any ie not
- * copied to new ie, skip ssid, capability, bssid-index ie
+ /* The above misses elements that are included in subie but not in the
+ * parent, so do a pass over subie and append those.
+ * Skip the non-tx BSSID caps and non-inheritance element.
*/
- tmp_new = sub_copy;
- while (tmp_new + 2 - sub_copy <= subie_len &&
- tmp_new + tmp_new[1] + 2 - sub_copy <= subie_len) {
- if (!(tmp_new[0] == WLAN_EID_NON_TX_BSSID_CAP ||
- tmp_new[0] == WLAN_EID_SSID)) {
- memcpy(pos, tmp_new, tmp_new[1] + 2);
- pos += tmp_new[1] + 2;
+ for_each_element(sub, subie, subie_len) {
+ if (sub->id == WLAN_EID_NON_TX_BSSID_CAP)
+ continue;
+
+ if (sub->id == WLAN_EID_FRAGMENT)
+ continue;
+
+ if (sub->id == WLAN_EID_EXTENSION) {
+ if (sub->datalen < 1)
+ continue;
+
+ id = WLAN_EID_EXTENSION;
+ ext_id = sub->data[0];
+ match_len = 1;
+
+ if (ext_id == WLAN_EID_EXT_NON_INHERITANCE)
+ continue;
+ } else {
+ id = sub->id;
+ match_len = 0;
}
- if (tmp_new + tmp_new[1] + 2 - sub_copy == subie_len)
- break;
- tmp_new += tmp_new[1] + 2;
+
+ /* Processed if one was included in the parent */
+ if (cfg80211_find_elem_match(id, ie, ielen,
+ &ext_id, match_len, 0))
+ continue;
+
+ if (!cfg80211_copy_elem_with_frags(sub, subie, subie_len,
+ &pos, new_ie, new_ie_len))
+ return 0;
}
- kfree(sub_copy);
return pos - new_ie;
}
@@ -535,39 +576,58 @@ static void cfg80211_free_coloc_ap_list(struct list_head *coloc_ap_list)
static int cfg80211_parse_ap_info(struct cfg80211_colocated_ap *entry,
const u8 *pos, u8 length,
const struct element *ssid_elem,
- int s_ssid_tmp)
+ u32 s_ssid_tmp)
{
- /* skip the TBTT offset */
- pos++;
+ u8 bss_params;
- /* ignore entries with invalid BSSID */
- if (!is_valid_ether_addr(pos))
- return -EINVAL;
+ entry->psd_20 = IEEE80211_RNR_TBTT_PARAMS_PSD_RESERVED;
- memcpy(entry->bssid, pos, ETH_ALEN);
- pos += ETH_ALEN;
+ /* The length is already verified by the caller to contain bss_params */
+ if (length > sizeof(struct ieee80211_tbtt_info_7_8_9)) {
+ struct ieee80211_tbtt_info_ge_11 *tbtt_info = (void *)pos;
- if (length >= IEEE80211_TBTT_INFO_OFFSET_BSSID_SSSID_BSS_PARAM) {
- memcpy(&entry->short_ssid, pos,
- sizeof(entry->short_ssid));
+ memcpy(entry->bssid, tbtt_info->bssid, ETH_ALEN);
+ entry->short_ssid = le32_to_cpu(tbtt_info->short_ssid);
entry->short_ssid_valid = true;
- pos += 4;
+
+ bss_params = tbtt_info->bss_params;
+
+ /* Ignore disabled links */
+ if (length >= offsetofend(typeof(*tbtt_info), mld_params)) {
+ if (le16_get_bits(tbtt_info->mld_params.params,
+ IEEE80211_RNR_MLD_PARAMS_DISABLED_LINK))
+ return -EINVAL;
+ }
+
+ if (length >= offsetofend(struct ieee80211_tbtt_info_ge_11,
+ psd_20))
+ entry->psd_20 = tbtt_info->psd_20;
+ } else {
+ struct ieee80211_tbtt_info_7_8_9 *tbtt_info = (void *)pos;
+
+ memcpy(entry->bssid, tbtt_info->bssid, ETH_ALEN);
+
+ bss_params = tbtt_info->bss_params;
+
+ if (length == offsetofend(struct ieee80211_tbtt_info_7_8_9,
+ psd_20))
+ entry->psd_20 = tbtt_info->psd_20;
}
+ /* ignore entries with invalid BSSID */
+ if (!is_valid_ether_addr(entry->bssid))
+ return -EINVAL;
+
/* skip non colocated APs */
- if (!cfg80211_parse_bss_param(*pos, entry))
+ if (!cfg80211_parse_bss_param(bss_params, entry))
return -EINVAL;
- pos++;
- if (length == IEEE80211_TBTT_INFO_OFFSET_BSSID_BSS_PARAM) {
- /*
- * no information about the short ssid. Consider the entry valid
- * for now. It would later be dropped in case there are explicit
- * SSIDs that need to be matched
- */
- if (!entry->same_ssid)
- return 0;
- }
+ /* no information about the short ssid. Consider the entry valid
+ * for now. It would later be dropped in case there are explicit
+ * SSIDs that need to be matched
+ */
+ if (!entry->same_ssid && !entry->short_ssid_valid)
+ return 0;
if (entry->same_ssid) {
entry->short_ssid = s_ssid_tmp;
@@ -578,10 +638,10 @@ static int cfg80211_parse_ap_info(struct cfg80211_colocated_ap *entry,
* cfg80211_parse_colocated_ap(), before calling this
* function.
*/
- memcpy(&entry->ssid, &ssid_elem->data,
- ssid_elem->datalen);
+ memcpy(&entry->ssid, &ssid_elem->data, ssid_elem->datalen);
entry->ssid_len = ssid_elem->datalen;
}
+
return 0;
}
@@ -595,79 +655,89 @@ static int cfg80211_parse_colocated_ap(const struct cfg80211_bss_ies *ies,
int n_coloc = 0, ret;
LIST_HEAD(ap_list);
- elem = cfg80211_find_elem(WLAN_EID_REDUCED_NEIGHBOR_REPORT, ies->data,
- ies->len);
- if (!elem)
- return 0;
-
- pos = elem->data;
- end = pos + elem->datalen;
-
ret = cfg80211_calc_short_ssid(ies, &ssid_elem, &s_ssid_tmp);
if (ret)
return ret;
- /* RNR IE may contain more than one NEIGHBOR_AP_INFO */
- while (pos + sizeof(*ap_info) <= end) {
- enum nl80211_band band;
- int freq;
- u8 length, i, count;
+ for_each_element_id(elem, WLAN_EID_REDUCED_NEIGHBOR_REPORT,
+ ies->data, ies->len) {
+ pos = elem->data;
+ end = elem->data + elem->datalen;
- ap_info = (void *)pos;
- count = u8_get_bits(ap_info->tbtt_info_hdr,
- IEEE80211_AP_INFO_TBTT_HDR_COUNT) + 1;
- length = ap_info->tbtt_info_len;
+ /* RNR IE may contain more than one NEIGHBOR_AP_INFO */
+ while (pos + sizeof(*ap_info) <= end) {
+ enum nl80211_band band;
+ int freq;
+ u8 length, i, count;
- pos += sizeof(*ap_info);
+ ap_info = (void *)pos;
+ count = u8_get_bits(ap_info->tbtt_info_hdr,
+ IEEE80211_AP_INFO_TBTT_HDR_COUNT) + 1;
+ length = ap_info->tbtt_info_len;
- if (!ieee80211_operating_class_to_band(ap_info->op_class,
- &band))
- break;
+ pos += sizeof(*ap_info);
- freq = ieee80211_channel_to_frequency(ap_info->channel, band);
+ if (!ieee80211_operating_class_to_band(ap_info->op_class,
+ &band))
+ break;
- if (end - pos < count * length)
- break;
+ freq = ieee80211_channel_to_frequency(ap_info->channel,
+ band);
- /*
- * TBTT info must include bss param + BSSID +
- * (short SSID or same_ssid bit to be set).
- * ignore other options, and move to the
- * next AP info
- */
- if (band != NL80211_BAND_6GHZ ||
- (length != IEEE80211_TBTT_INFO_OFFSET_BSSID_BSS_PARAM &&
- length < IEEE80211_TBTT_INFO_OFFSET_BSSID_SSSID_BSS_PARAM)) {
- pos += count * length;
- continue;
- }
+ if (end - pos < count * length)
+ break;
+
+ if (u8_get_bits(ap_info->tbtt_info_hdr,
+ IEEE80211_AP_INFO_TBTT_HDR_TYPE) !=
+ IEEE80211_TBTT_INFO_TYPE_TBTT) {
+ pos += count * length;
+ continue;
+ }
- for (i = 0; i < count; i++) {
- struct cfg80211_colocated_ap *entry;
+ /* TBTT info must include bss param + BSSID +
+ * (short SSID or same_ssid bit to be set).
+ * ignore other options, and move to the
+ * next AP info
+ */
+ if (band != NL80211_BAND_6GHZ ||
+ !(length == offsetofend(struct ieee80211_tbtt_info_7_8_9,
+ bss_params) ||
+ length == sizeof(struct ieee80211_tbtt_info_7_8_9) ||
+ length >= offsetofend(struct ieee80211_tbtt_info_ge_11,
+ bss_params))) {
+ pos += count * length;
+ continue;
+ }
- entry = kzalloc(sizeof(*entry) + IEEE80211_MAX_SSID_LEN,
- GFP_ATOMIC);
+ for (i = 0; i < count; i++) {
+ struct cfg80211_colocated_ap *entry;
- if (!entry)
- break;
+ entry = kzalloc(sizeof(*entry) + IEEE80211_MAX_SSID_LEN,
+ GFP_ATOMIC);
- entry->center_freq = freq;
+ if (!entry)
+ goto error;
- if (!cfg80211_parse_ap_info(entry, pos, length,
- ssid_elem, s_ssid_tmp)) {
- n_coloc++;
- list_add_tail(&entry->list, &ap_list);
- } else {
- kfree(entry);
- }
+ entry->center_freq = freq;
- pos += length;
+ if (!cfg80211_parse_ap_info(entry, pos, length,
+ ssid_elem,
+ s_ssid_tmp)) {
+ n_coloc++;
+ list_add_tail(&entry->list, &ap_list);
+ } else {
+ kfree(entry);
+ }
+
+ pos += length;
+ }
}
- }
- if (pos != end) {
- cfg80211_free_coloc_ap_list(&ap_list);
- return 0;
+error:
+ if (pos != end) {
+ cfg80211_free_coloc_ap_list(&ap_list);
+ return 0;
+ }
}
list_splice_tail(&ap_list, list);
@@ -846,6 +916,7 @@ static int cfg80211_scan_6ghz(struct cfg80211_registered_device *rdev)
scan_6ghz_params->short_ssid = ap->short_ssid;
scan_6ghz_params->short_ssid_valid = ap->short_ssid_valid;
scan_6ghz_params->unsolicited_probe = ap->unsolicited_probe;
+ scan_6ghz_params->psd_20 = ap->psd_20;
/*
* If a PSC channel is added to the scan and 'need_scan_psc' is
@@ -1004,16 +1075,9 @@ void ___cfg80211_scan_done(struct cfg80211_registered_device *rdev,
nl80211_send_scan_msg(rdev, msg);
}
-void __cfg80211_scan_done(struct work_struct *wk)
+void __cfg80211_scan_done(struct wiphy *wiphy, struct wiphy_work *wk)
{
- struct cfg80211_registered_device *rdev;
-
- rdev = container_of(wk, struct cfg80211_registered_device,
- scan_done_wk);
-
- wiphy_lock(&rdev->wiphy);
- ___cfg80211_scan_done(rdev, true);
- wiphy_unlock(&rdev->wiphy);
+ ___cfg80211_scan_done(wiphy_to_rdev(wiphy), true);
}
void cfg80211_scan_done(struct cfg80211_scan_request *request,
@@ -1039,7 +1103,8 @@ void cfg80211_scan_done(struct cfg80211_scan_request *request,
}
request->notified = true;
- queue_work(cfg80211_wq, &wiphy_to_rdev(request->wiphy)->scan_done_wk);
+ wiphy_work_queue(request->wiphy,
+ &wiphy_to_rdev(request->wiphy)->scan_done_wk);
}
EXPORT_SYMBOL(cfg80211_scan_done);
@@ -1604,12 +1669,6 @@ static bool cfg80211_combine_bsses(struct cfg80211_registered_device *rdev,
return true;
}
-struct cfg80211_non_tx_bss {
- struct cfg80211_bss *tx_bss;
- u8 max_bssid_indicator;
- u8 bssid_index;
-};
-
static void cfg80211_update_hidden_bsses(struct cfg80211_internal_bss *known,
const struct cfg80211_bss_ies *new_ies,
const struct cfg80211_bss_ies *old_ies)
@@ -1707,10 +1766,10 @@ cfg80211_update_known_bss(struct cfg80211_registered_device *rdev,
}
/* Returned bss is reference counted and must be cleaned up appropriately. */
-struct cfg80211_internal_bss *
-cfg80211_bss_update(struct cfg80211_registered_device *rdev,
- struct cfg80211_internal_bss *tmp,
- bool signal_valid, unsigned long ts)
+static struct cfg80211_internal_bss *
+__cfg80211_bss_update(struct cfg80211_registered_device *rdev,
+ struct cfg80211_internal_bss *tmp,
+ bool signal_valid, unsigned long ts)
{
struct cfg80211_internal_bss *found = NULL;
@@ -1719,10 +1778,7 @@ cfg80211_bss_update(struct cfg80211_registered_device *rdev,
tmp->ts = ts;
- spin_lock_bh(&rdev->bss_lock);
-
if (WARN_ON(!rcu_access_pointer(tmp->pub.ies))) {
- spin_unlock_bh(&rdev->bss_lock);
return NULL;
}
@@ -1730,7 +1786,7 @@ cfg80211_bss_update(struct cfg80211_registered_device *rdev,
if (found) {
if (!cfg80211_update_known_bss(rdev, found, tmp, signal_valid))
- goto drop;
+ return NULL;
} else {
struct cfg80211_internal_bss *new;
struct cfg80211_internal_bss *hidden;
@@ -1750,7 +1806,7 @@ cfg80211_bss_update(struct cfg80211_registered_device *rdev,
ies = (void *)rcu_dereference(tmp->pub.proberesp_ies);
if (ies)
kfree_rcu(ies, rcu_head);
- goto drop;
+ return NULL;
}
memcpy(new, tmp, sizeof(*new));
new->refcount = 1;
@@ -1781,14 +1837,14 @@ cfg80211_bss_update(struct cfg80211_registered_device *rdev,
*/
if (!cfg80211_combine_bsses(rdev, new)) {
bss_ref_put(rdev, new);
- goto drop;
+ return NULL;
}
}
if (rdev->bss_entries >= bss_entries_limit &&
!cfg80211_bss_expire_oldest(rdev)) {
bss_ref_put(rdev, new);
- goto drop;
+ return NULL;
}
/* This must be before the call to bss_ref_get */
@@ -1805,12 +1861,22 @@ cfg80211_bss_update(struct cfg80211_registered_device *rdev,
rdev->bss_generation++;
bss_ref_get(rdev, found);
- spin_unlock_bh(&rdev->bss_lock);
return found;
- drop:
+}
+
+struct cfg80211_internal_bss *
+cfg80211_bss_update(struct cfg80211_registered_device *rdev,
+ struct cfg80211_internal_bss *tmp,
+ bool signal_valid, unsigned long ts)
+{
+ struct cfg80211_internal_bss *res;
+
+ spin_lock_bh(&rdev->bss_lock);
+ res = __cfg80211_bss_update(rdev, tmp, signal_valid, ts);
spin_unlock_bh(&rdev->bss_lock);
- return NULL;
+
+ return res;
}
int cfg80211_get_ies_channel_number(const u8 *ie, size_t ielen,
@@ -1930,17 +1996,36 @@ cfg80211_get_bss_channel(struct wiphy *wiphy, const u8 *ie, size_t ielen,
return alt_channel;
}
+struct cfg80211_inform_single_bss_data {
+ struct cfg80211_inform_bss *drv_data;
+ enum cfg80211_bss_frame_type ftype;
+ struct ieee80211_channel *channel;
+ u8 bssid[ETH_ALEN];
+ u64 tsf;
+ u16 capability;
+ u16 beacon_interval;
+ const u8 *ie;
+ size_t ielen;
+
+ enum {
+ BSS_SOURCE_DIRECT = 0,
+ BSS_SOURCE_MBSSID,
+ BSS_SOURCE_STA_PROFILE,
+ } bss_source;
+ /* Set if reporting bss_source != BSS_SOURCE_DIRECT */
+ struct cfg80211_bss *source_bss;
+ u8 max_bssid_indicator;
+ u8 bssid_index;
+};
+
/* Returned bss is reference counted and must be cleaned up appropriately. */
static struct cfg80211_bss *
cfg80211_inform_single_bss_data(struct wiphy *wiphy,
- struct cfg80211_inform_bss *data,
- enum cfg80211_bss_frame_type ftype,
- const u8 *bssid, u64 tsf, u16 capability,
- u16 beacon_interval, const u8 *ie, size_t ielen,
- struct cfg80211_non_tx_bss *non_tx_data,
+ struct cfg80211_inform_single_bss_data *data,
gfp_t gfp)
{
struct cfg80211_registered_device *rdev = wiphy_to_rdev(wiphy);
+ struct cfg80211_inform_bss *drv_data = data->drv_data;
struct cfg80211_bss_ies *ies;
struct ieee80211_channel *channel;
struct cfg80211_internal_bss tmp = {}, *res;
@@ -1952,31 +2037,53 @@ cfg80211_inform_single_bss_data(struct wiphy *wiphy,
return NULL;
if (WARN_ON(wiphy->signal_type == CFG80211_SIGNAL_TYPE_UNSPEC &&
- (data->signal < 0 || data->signal > 100)))
+ (drv_data->signal < 0 || drv_data->signal > 100)))
return NULL;
- channel = cfg80211_get_bss_channel(wiphy, ie, ielen, data->chan,
- data->scan_width);
+ if (WARN_ON(data->bss_source != BSS_SOURCE_DIRECT && !data->source_bss))
+ return NULL;
+
+ channel = data->channel;
+ if (!channel)
+ channel = cfg80211_get_bss_channel(wiphy, data->ie, data->ielen,
+ drv_data->chan,
+ drv_data->scan_width);
if (!channel)
return NULL;
- memcpy(tmp.pub.bssid, bssid, ETH_ALEN);
+ memcpy(tmp.pub.bssid, data->bssid, ETH_ALEN);
tmp.pub.channel = channel;
- tmp.pub.scan_width = data->scan_width;
- tmp.pub.signal = data->signal;
- tmp.pub.beacon_interval = beacon_interval;
- tmp.pub.capability = capability;
- tmp.ts_boottime = data->boottime_ns;
- tmp.parent_tsf = data->parent_tsf;
- ether_addr_copy(tmp.parent_bssid, data->parent_bssid);
-
- if (non_tx_data) {
- tmp.pub.transmitted_bss = non_tx_data->tx_bss;
- ts = bss_from_pub(non_tx_data->tx_bss)->ts;
- tmp.pub.bssid_index = non_tx_data->bssid_index;
- tmp.pub.max_bssid_indicator = non_tx_data->max_bssid_indicator;
+ tmp.pub.scan_width = drv_data->scan_width;
+ if (data->bss_source != BSS_SOURCE_STA_PROFILE)
+ tmp.pub.signal = drv_data->signal;
+ else
+ tmp.pub.signal = 0;
+ tmp.pub.beacon_interval = data->beacon_interval;
+ tmp.pub.capability = data->capability;
+ tmp.ts_boottime = drv_data->boottime_ns;
+ tmp.parent_tsf = drv_data->parent_tsf;
+ ether_addr_copy(tmp.parent_bssid, drv_data->parent_bssid);
+
+ if (data->bss_source != BSS_SOURCE_DIRECT) {
+ tmp.pub.transmitted_bss = data->source_bss;
+ ts = bss_from_pub(data->source_bss)->ts;
+ tmp.pub.bssid_index = data->bssid_index;
+ tmp.pub.max_bssid_indicator = data->max_bssid_indicator;
} else {
ts = jiffies;
+
+ if (channel->band == NL80211_BAND_60GHZ) {
+ bss_type = data->capability &
+ WLAN_CAPABILITY_DMG_TYPE_MASK;
+ if (bss_type == WLAN_CAPABILITY_DMG_TYPE_AP ||
+ bss_type == WLAN_CAPABILITY_DMG_TYPE_PBSS)
+ regulatory_hint_found_beacon(wiphy, channel,
+ gfp);
+ } else {
+ if (data->capability & WLAN_CAPABILITY_ESS)
+ regulatory_hint_found_beacon(wiphy, channel,
+ gfp);
+ }
}
/*
@@ -1987,15 +2094,15 @@ cfg80211_inform_single_bss_data(struct wiphy *wiphy,
* override the IEs pointer should we have received an earlier
* indication of Probe Response data.
*/
- ies = kzalloc(sizeof(*ies) + ielen, gfp);
+ ies = kzalloc(sizeof(*ies) + data->ielen, gfp);
if (!ies)
return NULL;
- ies->len = ielen;
- ies->tsf = tsf;
+ ies->len = data->ielen;
+ ies->tsf = data->tsf;
ies->from_beacon = false;
- memcpy(ies->data, ie, ielen);
+ memcpy(ies->data, data->ie, data->ielen);
- switch (ftype) {
+ switch (data->ftype) {
case CFG80211_BSS_FTYPE_BEACON:
ies->from_beacon = true;
fallthrough;
@@ -2008,42 +2115,37 @@ cfg80211_inform_single_bss_data(struct wiphy *wiphy,
}
rcu_assign_pointer(tmp.pub.ies, ies);
- signal_valid = data->chan == channel;
- res = cfg80211_bss_update(wiphy_to_rdev(wiphy), &tmp, signal_valid, ts);
+ signal_valid = drv_data->chan == channel;
+ spin_lock_bh(&rdev->bss_lock);
+ res = __cfg80211_bss_update(rdev, &tmp, signal_valid, ts);
if (!res)
- return NULL;
+ goto drop;
- if (channel->band == NL80211_BAND_60GHZ) {
- bss_type = res->pub.capability & WLAN_CAPABILITY_DMG_TYPE_MASK;
- if (bss_type == WLAN_CAPABILITY_DMG_TYPE_AP ||
- bss_type == WLAN_CAPABILITY_DMG_TYPE_PBSS)
- regulatory_hint_found_beacon(wiphy, channel, gfp);
- } else {
- if (res->pub.capability & WLAN_CAPABILITY_ESS)
- regulatory_hint_found_beacon(wiphy, channel, gfp);
- }
+ rdev_inform_bss(rdev, &res->pub, ies, data->drv_data);
- if (non_tx_data) {
+ if (data->bss_source == BSS_SOURCE_MBSSID) {
/* this is a nontransmitting bss, we need to add it to
* transmitting bss' list if it is not there
*/
- spin_lock_bh(&rdev->bss_lock);
- if (cfg80211_add_nontrans_list(non_tx_data->tx_bss,
- &res->pub)) {
+ if (cfg80211_add_nontrans_list(data->source_bss, &res->pub)) {
if (__cfg80211_unlink_bss(rdev, res)) {
rdev->bss_generation++;
res = NULL;
}
}
- spin_unlock_bh(&rdev->bss_lock);
if (!res)
- return NULL;
+ goto drop;
}
+ spin_unlock_bh(&rdev->bss_lock);
trace_cfg80211_return_bss(&res->pub);
- /* cfg80211_bss_update gives us a referenced result */
+ /* __cfg80211_bss_update gives us a referenced result */
return &res->pub;
+
+drop:
+ spin_unlock_bh(&rdev->bss_lock);
+ return NULL;
}
static const struct element
@@ -2118,43 +2220,48 @@ size_t cfg80211_merge_profile(const u8 *ie, size_t ielen,
}
EXPORT_SYMBOL(cfg80211_merge_profile);
-static void cfg80211_parse_mbssid_data(struct wiphy *wiphy,
- struct cfg80211_inform_bss *data,
- enum cfg80211_bss_frame_type ftype,
- const u8 *bssid, u64 tsf,
- u16 beacon_interval, const u8 *ie,
- size_t ielen,
- struct cfg80211_non_tx_bss *non_tx_data,
- gfp_t gfp)
-{
+static void
+cfg80211_parse_mbssid_data(struct wiphy *wiphy,
+ struct cfg80211_inform_single_bss_data *tx_data,
+ struct cfg80211_bss *source_bss,
+ gfp_t gfp)
+{
+ struct cfg80211_inform_single_bss_data data = {
+ .drv_data = tx_data->drv_data,
+ .ftype = tx_data->ftype,
+ .tsf = tx_data->tsf,
+ .beacon_interval = tx_data->beacon_interval,
+ .source_bss = source_bss,
+ .bss_source = BSS_SOURCE_MBSSID,
+ };
const u8 *mbssid_index_ie;
const struct element *elem, *sub;
- size_t new_ie_len;
- u8 new_bssid[ETH_ALEN];
u8 *new_ie, *profile;
u64 seen_indices = 0;
- u16 capability;
struct cfg80211_bss *bss;
- if (!non_tx_data)
+ if (!source_bss)
return;
- if (!cfg80211_find_elem(WLAN_EID_MULTIPLE_BSSID, ie, ielen))
+ if (!cfg80211_find_elem(WLAN_EID_MULTIPLE_BSSID,
+ tx_data->ie, tx_data->ielen))
return;
if (!wiphy->support_mbssid)
return;
if (wiphy->support_only_he_mbssid &&
- !cfg80211_find_ext_elem(WLAN_EID_EXT_HE_CAPABILITY, ie, ielen))
+ !cfg80211_find_ext_elem(WLAN_EID_EXT_HE_CAPABILITY,
+ tx_data->ie, tx_data->ielen))
return;
new_ie = kmalloc(IEEE80211_MAX_DATA_LEN, gfp);
if (!new_ie)
return;
- profile = kmalloc(ielen, gfp);
+ profile = kmalloc(tx_data->ielen, gfp);
if (!profile)
goto out;
- for_each_element_id(elem, WLAN_EID_MULTIPLE_BSSID, ie, ielen) {
+ for_each_element_id(elem, WLAN_EID_MULTIPLE_BSSID,
+ tx_data->ie, tx_data->ielen) {
if (elem->datalen < 4)
continue;
if (elem->data[0] < 1 || (int)elem->data[0] > 8)
@@ -2176,12 +2283,13 @@ static void cfg80211_parse_mbssid_data(struct wiphy *wiphy,
continue;
}
- memset(profile, 0, ielen);
- profile_len = cfg80211_merge_profile(ie, ielen,
+ memset(profile, 0, tx_data->ielen);
+ profile_len = cfg80211_merge_profile(tx_data->ie,
+ tx_data->ielen,
elem,
sub,
profile,
- ielen);
+ tx_data->ielen);
/* found a Nontransmitted BSSID Profile */
mbssid_index_ie = cfg80211_find_ie
@@ -2201,31 +2309,27 @@ static void cfg80211_parse_mbssid_data(struct wiphy *wiphy,
seen_indices |= BIT_ULL(mbssid_index_ie[2]);
- non_tx_data->bssid_index = mbssid_index_ie[2];
- non_tx_data->max_bssid_indicator = elem->data[0];
+ data.bssid_index = mbssid_index_ie[2];
+ data.max_bssid_indicator = elem->data[0];
+
+ cfg80211_gen_new_bssid(tx_data->bssid,
+ data.max_bssid_indicator,
+ data.bssid_index,
+ data.bssid);
- cfg80211_gen_new_bssid(bssid,
- non_tx_data->max_bssid_indicator,
- non_tx_data->bssid_index,
- new_bssid);
memset(new_ie, 0, IEEE80211_MAX_DATA_LEN);
- new_ie_len = cfg80211_gen_new_ie(ie, ielen,
+ data.ie = new_ie;
+ data.ielen = cfg80211_gen_new_ie(tx_data->ie,
+ tx_data->ielen,
profile,
- profile_len, new_ie,
- gfp);
- if (!new_ie_len)
+ profile_len,
+ new_ie,
+ IEEE80211_MAX_DATA_LEN);
+ if (!data.ielen)
continue;
- capability = get_unaligned_le16(profile + 2);
- bss = cfg80211_inform_single_bss_data(wiphy, data,
- ftype,
- new_bssid, tsf,
- capability,
- beacon_interval,
- new_ie,
- new_ie_len,
- non_tx_data,
- gfp);
+ data.capability = get_unaligned_le16(profile + 2);
+ bss = cfg80211_inform_single_bss_data(wiphy, &data, gfp);
if (!bss)
break;
cfg80211_put_bss(wiphy, bss);
@@ -2237,142 +2341,425 @@ out:
kfree(profile);
}
-struct cfg80211_bss *
-cfg80211_inform_bss_data(struct wiphy *wiphy,
- struct cfg80211_inform_bss *data,
- enum cfg80211_bss_frame_type ftype,
- const u8 *bssid, u64 tsf, u16 capability,
- u16 beacon_interval, const u8 *ie, size_t ielen,
- gfp_t gfp)
+ssize_t cfg80211_defragment_element(const struct element *elem, const u8 *ies,
+ size_t ieslen, u8 *data, size_t data_len,
+ u8 frag_id)
{
- struct cfg80211_bss *res;
- struct cfg80211_non_tx_bss non_tx_data;
+ const struct element *next;
+ ssize_t copied;
+ u8 elem_datalen;
+
+ if (!elem)
+ return -EINVAL;
+
+ /* elem might be invalid after the memmove */
+ next = (void *)(elem->data + elem->datalen);
+
+ elem_datalen = elem->datalen;
+ if (elem->id == WLAN_EID_EXTENSION) {
+ copied = elem->datalen - 1;
+ if (copied > data_len)
+ return -ENOSPC;
+
+ memmove(data, elem->data + 1, copied);
+ } else {
+ copied = elem->datalen;
+ if (copied > data_len)
+ return -ENOSPC;
+
+ memmove(data, elem->data, copied);
+ }
+
+ /* Fragmented elements must have 255 bytes */
+ if (elem_datalen < 255)
+ return copied;
+
+ for (elem = next;
+ elem->data < ies + ieslen &&
+ elem->data + elem->datalen < ies + ieslen;
+ elem = next) {
+ /* elem might be invalid after the memmove */
+ next = (void *)(elem->data + elem->datalen);
+
+ if (elem->id != frag_id)
+ break;
+
+ elem_datalen = elem->datalen;
+
+ if (copied + elem_datalen > data_len)
+ return -ENOSPC;
+
+ memmove(data + copied, elem->data, elem_datalen);
+ copied += elem_datalen;
+
+ /* Only the last fragment may be short */
+ if (elem_datalen != 255)
+ break;
+ }
- res = cfg80211_inform_single_bss_data(wiphy, data, ftype, bssid, tsf,
- capability, beacon_interval, ie,
- ielen, NULL, gfp);
+ return copied;
+}
+EXPORT_SYMBOL(cfg80211_defragment_element);
+
+struct cfg80211_mle {
+ struct ieee80211_multi_link_elem *mle;
+ struct ieee80211_mle_per_sta_profile
+ *sta_prof[IEEE80211_MLD_MAX_NUM_LINKS];
+ ssize_t sta_prof_len[IEEE80211_MLD_MAX_NUM_LINKS];
+
+ u8 data[];
+};
+
+static struct cfg80211_mle *
+cfg80211_defrag_mle(const struct element *mle, const u8 *ie, size_t ielen,
+ gfp_t gfp)
+{
+ const struct element *elem;
+ struct cfg80211_mle *res;
+ size_t buf_len;
+ ssize_t mle_len;
+ u8 common_size, idx;
+
+ if (!mle || !ieee80211_mle_size_ok(mle->data + 1, mle->datalen - 1))
+ return NULL;
+
+ /* Required length for first defragmentation */
+ buf_len = mle->datalen - 1;
+ for_each_element(elem, mle->data + mle->datalen,
+ ielen - sizeof(*mle) + mle->datalen) {
+ if (elem->id != WLAN_EID_FRAGMENT)
+ break;
+
+ buf_len += elem->datalen;
+ }
+
+ res = kzalloc(struct_size(res, data, buf_len), gfp);
if (!res)
return NULL;
- non_tx_data.tx_bss = res;
- cfg80211_parse_mbssid_data(wiphy, data, ftype, bssid, tsf,
- beacon_interval, ie, ielen, &non_tx_data,
- gfp);
+
+ mle_len = cfg80211_defragment_element(mle, ie, ielen,
+ res->data, buf_len,
+ WLAN_EID_FRAGMENT);
+ if (mle_len < 0)
+ goto error;
+
+ res->mle = (void *)res->data;
+
+ /* Find the sub-element area in the buffer */
+ common_size = ieee80211_mle_common_size((u8 *)res->mle);
+ ie = res->data + common_size;
+ ielen = mle_len - common_size;
+
+ idx = 0;
+ for_each_element_id(elem, IEEE80211_MLE_SUBELEM_PER_STA_PROFILE,
+ ie, ielen) {
+ res->sta_prof[idx] = (void *)elem->data;
+ res->sta_prof_len[idx] = elem->datalen;
+
+ idx++;
+ if (idx >= IEEE80211_MLD_MAX_NUM_LINKS)
+ break;
+ }
+ if (!for_each_element_completed(elem, ie, ielen))
+ goto error;
+
+ /* Defragment sta_info in-place */
+ for (idx = 0; idx < IEEE80211_MLD_MAX_NUM_LINKS && res->sta_prof[idx];
+ idx++) {
+ if (res->sta_prof_len[idx] < 255)
+ continue;
+
+ elem = (void *)res->sta_prof[idx] - 2;
+
+ if (idx + 1 < ARRAY_SIZE(res->sta_prof) &&
+ res->sta_prof[idx + 1])
+ buf_len = (u8 *)res->sta_prof[idx + 1] -
+ (u8 *)res->sta_prof[idx];
+ else
+ buf_len = ielen + ie - (u8 *)elem;
+
+ res->sta_prof_len[idx] =
+ cfg80211_defragment_element(elem,
+ (u8 *)elem, buf_len,
+ (u8 *)res->sta_prof[idx],
+ buf_len,
+ IEEE80211_MLE_SUBELEM_FRAGMENT);
+ if (res->sta_prof_len[idx] < 0)
+ goto error;
+ }
+
return res;
+
+error:
+ kfree(res);
+ return NULL;
}
-EXPORT_SYMBOL(cfg80211_inform_bss_data);
-static void
-cfg80211_parse_mbssid_frame_data(struct wiphy *wiphy,
- struct cfg80211_inform_bss *data,
- struct ieee80211_mgmt *mgmt, size_t len,
- struct cfg80211_non_tx_bss *non_tx_data,
- gfp_t gfp)
+static bool
+cfg80211_tbtt_info_for_mld_ap(const u8 *ie, size_t ielen, u8 mld_id, u8 link_id,
+ const struct ieee80211_neighbor_ap_info **ap_info,
+ const u8 **tbtt_info)
{
- enum cfg80211_bss_frame_type ftype;
- const u8 *ie = mgmt->u.probe_resp.variable;
- size_t ielen = len - offsetof(struct ieee80211_mgmt,
- u.probe_resp.variable);
+ const struct ieee80211_neighbor_ap_info *info;
+ const struct element *rnr;
+ const u8 *pos, *end;
- ftype = ieee80211_is_beacon(mgmt->frame_control) ?
- CFG80211_BSS_FTYPE_BEACON : CFG80211_BSS_FTYPE_PRESP;
+ for_each_element_id(rnr, WLAN_EID_REDUCED_NEIGHBOR_REPORT, ie, ielen) {
+ pos = rnr->data;
+ end = rnr->data + rnr->datalen;
+
+ /* RNR IE may contain more than one NEIGHBOR_AP_INFO */
+ while (sizeof(*info) <= end - pos) {
+ const struct ieee80211_rnr_mld_params *mld_params;
+ u16 params;
+ u8 length, i, count, mld_params_offset;
+ u8 type, lid;
+
+ info = (void *)pos;
+ count = u8_get_bits(info->tbtt_info_hdr,
+ IEEE80211_AP_INFO_TBTT_HDR_COUNT) + 1;
+ length = info->tbtt_info_len;
+
+ pos += sizeof(*info);
+
+ if (count * length > end - pos)
+ return false;
+
+ type = u8_get_bits(info->tbtt_info_hdr,
+ IEEE80211_AP_INFO_TBTT_HDR_TYPE);
+
+ /* Only accept full TBTT information. NSTR mobile APs
+ * use the shortened version, but we ignore them here.
+ */
+ if (type == IEEE80211_TBTT_INFO_TYPE_TBTT &&
+ length >=
+ offsetofend(struct ieee80211_tbtt_info_ge_11,
+ mld_params)) {
+ mld_params_offset =
+ offsetof(struct ieee80211_tbtt_info_ge_11, mld_params);
+ } else {
+ pos += count * length;
+ continue;
+ }
+
+ for (i = 0; i < count; i++) {
+ mld_params = (void *)pos + mld_params_offset;
+ params = le16_to_cpu(mld_params->params);
- cfg80211_parse_mbssid_data(wiphy, data, ftype, mgmt->bssid,
- le64_to_cpu(mgmt->u.probe_resp.timestamp),
- le16_to_cpu(mgmt->u.probe_resp.beacon_int),
- ie, ielen, non_tx_data, gfp);
+ lid = u16_get_bits(params,
+ IEEE80211_RNR_MLD_PARAMS_LINK_ID);
+
+ if (mld_id == mld_params->mld_id &&
+ link_id == lid) {
+ *ap_info = info;
+ *tbtt_info = pos;
+
+ return true;
+ }
+
+ pos += length;
+ }
+ }
+ }
+
+ return false;
}
-static void
-cfg80211_update_notlisted_nontrans(struct wiphy *wiphy,
- struct cfg80211_bss *nontrans_bss,
- struct ieee80211_mgmt *mgmt, size_t len)
-{
- u8 *ie, *new_ie, *pos;
- const struct element *nontrans_ssid;
- const u8 *trans_ssid, *mbssid;
- size_t ielen = len - offsetof(struct ieee80211_mgmt,
- u.probe_resp.variable);
- size_t new_ie_len;
- struct cfg80211_bss_ies *new_ies;
- const struct cfg80211_bss_ies *old;
- size_t cpy_len;
-
- lockdep_assert_held(&wiphy_to_rdev(wiphy)->bss_lock);
-
- ie = mgmt->u.probe_resp.variable;
-
- new_ie_len = ielen;
- trans_ssid = cfg80211_find_ie(WLAN_EID_SSID, ie, ielen);
- if (!trans_ssid)
+static void cfg80211_parse_ml_sta_data(struct wiphy *wiphy,
+ struct cfg80211_inform_single_bss_data *tx_data,
+ struct cfg80211_bss *source_bss,
+ gfp_t gfp)
+{
+ struct cfg80211_inform_single_bss_data data = {
+ .drv_data = tx_data->drv_data,
+ .ftype = tx_data->ftype,
+ .source_bss = source_bss,
+ .bss_source = BSS_SOURCE_STA_PROFILE,
+ };
+ struct ieee80211_multi_link_elem *ml_elem;
+ const struct element *elem;
+ struct cfg80211_mle *mle;
+ u16 control;
+ u8 *new_ie;
+ struct cfg80211_bss *bss;
+ int mld_id;
+ u16 seen_links = 0;
+ const u8 *pos;
+ u8 i;
+
+ if (!source_bss)
return;
- new_ie_len -= trans_ssid[1];
- mbssid = cfg80211_find_ie(WLAN_EID_MULTIPLE_BSSID, ie, ielen);
- /*
- * It's not valid to have the MBSSID element before SSID
- * ignore if that happens - the code below assumes it is
- * after (while copying things inbetween).
- */
- if (!mbssid || mbssid < trans_ssid)
+
+ if (tx_data->ftype != CFG80211_BSS_FTYPE_PRESP)
return;
- new_ie_len -= mbssid[1];
- nontrans_ssid = ieee80211_bss_get_elem(nontrans_bss, WLAN_EID_SSID);
- if (!nontrans_ssid)
+ elem = cfg80211_find_ext_elem(WLAN_EID_EXT_EHT_MULTI_LINK,
+ tx_data->ie, tx_data->ielen);
+ if (!elem || !ieee80211_mle_size_ok(elem->data + 1, elem->datalen - 1))
return;
- new_ie_len += nontrans_ssid->datalen;
+ ml_elem = (void *)elem->data + 1;
+ control = le16_to_cpu(ml_elem->control);
+ if (u16_get_bits(control, IEEE80211_ML_CONTROL_TYPE) !=
+ IEEE80211_ML_CONTROL_TYPE_BASIC)
+ return;
- /* generate new ie for nontrans BSS
- * 1. replace SSID with nontrans BSS' SSID
- * 2. skip MBSSID IE
- */
- new_ie = kzalloc(new_ie_len, GFP_ATOMIC);
- if (!new_ie)
+ /* Must be present when transmitted by an AP (in a probe response) */
+ if (!(control & IEEE80211_MLC_BASIC_PRES_BSS_PARAM_CH_CNT) ||
+ !(control & IEEE80211_MLC_BASIC_PRES_LINK_ID) ||
+ !(control & IEEE80211_MLC_BASIC_PRES_MLD_CAPA_OP))
return;
- new_ies = kzalloc(sizeof(*new_ies) + new_ie_len, GFP_ATOMIC);
- if (!new_ies)
- goto out_free;
-
- pos = new_ie;
-
- /* copy the nontransmitted SSID */
- cpy_len = nontrans_ssid->datalen + 2;
- memcpy(pos, nontrans_ssid, cpy_len);
- pos += cpy_len;
- /* copy the IEs between SSID and MBSSID */
- cpy_len = trans_ssid[1] + 2;
- memcpy(pos, (trans_ssid + cpy_len), (mbssid - (trans_ssid + cpy_len)));
- pos += (mbssid - (trans_ssid + cpy_len));
- /* copy the IEs after MBSSID */
- cpy_len = mbssid[1] + 2;
- memcpy(pos, mbssid + cpy_len, ((ie + ielen) - (mbssid + cpy_len)));
-
- /* update ie */
- new_ies->len = new_ie_len;
- new_ies->tsf = le64_to_cpu(mgmt->u.probe_resp.timestamp);
- new_ies->from_beacon = ieee80211_is_beacon(mgmt->frame_control);
- memcpy(new_ies->data, new_ie, new_ie_len);
- if (ieee80211_is_probe_resp(mgmt->frame_control)) {
- old = rcu_access_pointer(nontrans_bss->proberesp_ies);
- rcu_assign_pointer(nontrans_bss->proberesp_ies, new_ies);
- rcu_assign_pointer(nontrans_bss->ies, new_ies);
- if (old)
- kfree_rcu((struct cfg80211_bss_ies *)old, rcu_head);
+ /* length + MLD MAC address + link ID info + BSS Params Change Count */
+ pos = ml_elem->variable + 1 + 6 + 1 + 1;
+
+ if (u16_get_bits(control, IEEE80211_MLC_BASIC_PRES_MED_SYNC_DELAY))
+ pos += 2;
+ if (u16_get_bits(control, IEEE80211_MLC_BASIC_PRES_EML_CAPA))
+ pos += 2;
+
+ /* MLD capabilities and operations */
+ pos += 2;
+
+ /* Not included when the (nontransmitted) AP is responding itself,
+ * but defined to zero then (Draft P802.11be_D3.0, 9.4.2.170.2)
+ */
+ if (u16_get_bits(control, IEEE80211_MLC_BASIC_PRES_MLD_ID)) {
+ mld_id = *pos;
+ pos += 1;
} else {
- old = rcu_access_pointer(nontrans_bss->beacon_ies);
- rcu_assign_pointer(nontrans_bss->beacon_ies, new_ies);
- cfg80211_update_hidden_bsses(bss_from_pub(nontrans_bss),
- new_ies, old);
- rcu_assign_pointer(nontrans_bss->ies, new_ies);
- if (old)
- kfree_rcu((struct cfg80211_bss_ies *)old, rcu_head);
+ mld_id = 0;
+ }
+
+ /* Extended MLD capabilities and operations */
+ pos += 2;
+
+ /* Fully defrag the ML element for sta information/profile iteration */
+ mle = cfg80211_defrag_mle(elem, tx_data->ie, tx_data->ielen, gfp);
+ if (!mle)
+ return;
+
+ new_ie = kmalloc(IEEE80211_MAX_DATA_LEN, gfp);
+ if (!new_ie)
+ goto out;
+
+ for (i = 0; i < ARRAY_SIZE(mle->sta_prof) && mle->sta_prof[i]; i++) {
+ const struct ieee80211_neighbor_ap_info *ap_info;
+ enum nl80211_band band;
+ u32 freq;
+ const u8 *profile;
+ const u8 *tbtt_info;
+ ssize_t profile_len;
+ u8 link_id;
+
+ if (!ieee80211_mle_basic_sta_prof_size_ok((u8 *)mle->sta_prof[i],
+ mle->sta_prof_len[i]))
+ continue;
+
+ control = le16_to_cpu(mle->sta_prof[i]->control);
+
+ if (!(control & IEEE80211_MLE_STA_CONTROL_COMPLETE_PROFILE))
+ continue;
+
+ link_id = u16_get_bits(control,
+ IEEE80211_MLE_STA_CONTROL_LINK_ID);
+ if (seen_links & BIT(link_id))
+ break;
+ seen_links |= BIT(link_id);
+
+ if (!(control & IEEE80211_MLE_STA_CONTROL_BEACON_INT_PRESENT) ||
+ !(control & IEEE80211_MLE_STA_CONTROL_TSF_OFFS_PRESENT) ||
+ !(control & IEEE80211_MLE_STA_CONTROL_STA_MAC_ADDR_PRESENT))
+ continue;
+
+ memcpy(data.bssid, mle->sta_prof[i]->variable, ETH_ALEN);
+ data.beacon_interval =
+ get_unaligned_le16(mle->sta_prof[i]->variable + 6);
+ data.tsf = tx_data->tsf +
+ get_unaligned_le64(mle->sta_prof[i]->variable + 8);
+
+ /* sta_info_len counts itself */
+ profile = mle->sta_prof[i]->variable +
+ mle->sta_prof[i]->sta_info_len - 1;
+ profile_len = (u8 *)mle->sta_prof[i] + mle->sta_prof_len[i] -
+ profile;
+
+ if (profile_len < 2)
+ continue;
+
+ data.capability = get_unaligned_le16(profile);
+ profile += 2;
+ profile_len -= 2;
+
+ /* Find in RNR to look up channel information */
+ if (!cfg80211_tbtt_info_for_mld_ap(tx_data->ie, tx_data->ielen,
+ mld_id, link_id,
+ &ap_info, &tbtt_info))
+ continue;
+
+ /* We could sanity check the BSSID is included */
+
+ if (!ieee80211_operating_class_to_band(ap_info->op_class,
+ &band))
+ continue;
+
+ freq = ieee80211_channel_to_freq_khz(ap_info->channel, band);
+ data.channel = ieee80211_get_channel_khz(wiphy, freq);
+
+ /* Generate new elements */
+ memset(new_ie, 0, IEEE80211_MAX_DATA_LEN);
+ data.ie = new_ie;
+ data.ielen = cfg80211_gen_new_ie(tx_data->ie, tx_data->ielen,
+ profile, profile_len,
+ new_ie,
+ IEEE80211_MAX_DATA_LEN);
+ if (!data.ielen)
+ continue;
+
+ bss = cfg80211_inform_single_bss_data(wiphy, &data, gfp);
+ if (!bss)
+ break;
+ cfg80211_put_bss(wiphy, bss);
}
-out_free:
+out:
kfree(new_ie);
+ kfree(mle);
}
+struct cfg80211_bss *
+cfg80211_inform_bss_data(struct wiphy *wiphy,
+ struct cfg80211_inform_bss *data,
+ enum cfg80211_bss_frame_type ftype,
+ const u8 *bssid, u64 tsf, u16 capability,
+ u16 beacon_interval, const u8 *ie, size_t ielen,
+ gfp_t gfp)
+{
+ struct cfg80211_inform_single_bss_data inform_data = {
+ .drv_data = data,
+ .ftype = ftype,
+ .tsf = tsf,
+ .capability = capability,
+ .beacon_interval = beacon_interval,
+ .ie = ie,
+ .ielen = ielen,
+ };
+ struct cfg80211_bss *res;
+
+ memcpy(inform_data.bssid, bssid, ETH_ALEN);
+
+ res = cfg80211_inform_single_bss_data(wiphy, &inform_data, gfp);
+ if (!res)
+ return NULL;
+
+ cfg80211_parse_mbssid_data(wiphy, &inform_data, res, gfp);
+
+ cfg80211_parse_ml_sta_data(wiphy, &inform_data, res, gfp);
+
+ return res;
+}
+EXPORT_SYMBOL(cfg80211_inform_bss_data);
+
/* cfg80211_inform_bss_width_frame helper */
static struct cfg80211_bss *
cfg80211_inform_single_bss_frame_data(struct wiphy *wiphy,
@@ -2380,6 +2767,7 @@ cfg80211_inform_single_bss_frame_data(struct wiphy *wiphy,
struct ieee80211_mgmt *mgmt, size_t len,
gfp_t gfp)
{
+ struct cfg80211_registered_device *rdev = wiphy_to_rdev(wiphy);
struct cfg80211_internal_bss tmp = {}, *res;
struct cfg80211_bss_ies *ies;
struct ieee80211_channel *channel;
@@ -2451,6 +2839,16 @@ cfg80211_inform_single_bss_frame_data(struct wiphy *wiphy,
capability = le16_to_cpu(mgmt->u.probe_resp.capab_info);
}
+ if (channel->band == NL80211_BAND_60GHZ) {
+ bss_type = capability & WLAN_CAPABILITY_DMG_TYPE_MASK;
+ if (bss_type == WLAN_CAPABILITY_DMG_TYPE_AP ||
+ bss_type == WLAN_CAPABILITY_DMG_TYPE_PBSS)
+ regulatory_hint_found_beacon(wiphy, channel, gfp);
+ } else {
+ if (capability & WLAN_CAPABILITY_ESS)
+ regulatory_hint_found_beacon(wiphy, channel, gfp);
+ }
+
ies = kzalloc(sizeof(*ies) + ielen, gfp);
if (!ies)
return NULL;
@@ -2479,24 +2877,22 @@ cfg80211_inform_single_bss_frame_data(struct wiphy *wiphy,
ether_addr_copy(tmp.parent_bssid, data->parent_bssid);
signal_valid = data->chan == channel;
- res = cfg80211_bss_update(wiphy_to_rdev(wiphy), &tmp, signal_valid,
- jiffies);
+ spin_lock_bh(&rdev->bss_lock);
+ res = __cfg80211_bss_update(rdev, &tmp, signal_valid, jiffies);
if (!res)
- return NULL;
+ goto drop;
- if (channel->band == NL80211_BAND_60GHZ) {
- bss_type = res->pub.capability & WLAN_CAPABILITY_DMG_TYPE_MASK;
- if (bss_type == WLAN_CAPABILITY_DMG_TYPE_AP ||
- bss_type == WLAN_CAPABILITY_DMG_TYPE_PBSS)
- regulatory_hint_found_beacon(wiphy, channel, gfp);
- } else {
- if (res->pub.capability & WLAN_CAPABILITY_ESS)
- regulatory_hint_found_beacon(wiphy, channel, gfp);
- }
+ rdev_inform_bss(rdev, &res->pub, ies, data->drv_data);
+
+ spin_unlock_bh(&rdev->bss_lock);
trace_cfg80211_return_bss(&res->pub);
- /* cfg80211_bss_update gives us a referenced result */
+ /* __cfg80211_bss_update gives us a referenced result */
return &res->pub;
+
+drop:
+ spin_unlock_bh(&rdev->bss_lock);
+ return NULL;
}
struct cfg80211_bss *
@@ -2505,51 +2901,34 @@ cfg80211_inform_bss_frame_data(struct wiphy *wiphy,
struct ieee80211_mgmt *mgmt, size_t len,
gfp_t gfp)
{
- struct cfg80211_bss *res, *tmp_bss;
- const u8 *ie = mgmt->u.probe_resp.variable;
- const struct cfg80211_bss_ies *ies1, *ies2;
- size_t ielen = len - offsetof(struct ieee80211_mgmt,
- u.probe_resp.variable);
- struct cfg80211_non_tx_bss non_tx_data = {};
+ struct cfg80211_inform_single_bss_data inform_data = {
+ .drv_data = data,
+ .ie = mgmt->u.probe_resp.variable,
+ .ielen = len - offsetof(struct ieee80211_mgmt,
+ u.probe_resp.variable),
+ };
+ struct cfg80211_bss *res;
res = cfg80211_inform_single_bss_frame_data(wiphy, data, mgmt,
len, gfp);
+ if (!res)
+ return NULL;
- /* don't do any further MBSSID handling for S1G */
+ /* don't do any further MBSSID/ML handling for S1G */
if (ieee80211_is_s1g_beacon(mgmt->frame_control))
return res;
- if (!res || !wiphy->support_mbssid ||
- !cfg80211_find_elem(WLAN_EID_MULTIPLE_BSSID, ie, ielen))
- return res;
- if (wiphy->support_only_he_mbssid &&
- !cfg80211_find_ext_elem(WLAN_EID_EXT_HE_CAPABILITY, ie, ielen))
- return res;
+ inform_data.ftype = ieee80211_is_beacon(mgmt->frame_control) ?
+ CFG80211_BSS_FTYPE_BEACON : CFG80211_BSS_FTYPE_PRESP;
+ memcpy(inform_data.bssid, mgmt->bssid, ETH_ALEN);
+ inform_data.tsf = le64_to_cpu(mgmt->u.probe_resp.timestamp);
+ inform_data.beacon_interval =
+ le16_to_cpu(mgmt->u.probe_resp.beacon_int);
- non_tx_data.tx_bss = res;
/* process each non-transmitting bss */
- cfg80211_parse_mbssid_frame_data(wiphy, data, mgmt, len,
- &non_tx_data, gfp);
-
- spin_lock_bh(&wiphy_to_rdev(wiphy)->bss_lock);
+ cfg80211_parse_mbssid_data(wiphy, &inform_data, res, gfp);
- /* check if the res has other nontransmitting bss which is not
- * in MBSSID IE
- */
- ies1 = rcu_access_pointer(res->ies);
-
- /* go through nontrans_list, if the timestamp of the BSS is
- * earlier than the timestamp of the transmitting BSS then
- * update it
- */
- list_for_each_entry(tmp_bss, &res->nontrans_list,
- nontrans_list) {
- ies2 = rcu_access_pointer(tmp_bss->ies);
- if (ies2->tsf < ies1->tsf)
- cfg80211_update_notlisted_nontrans(wiphy, tmp_bss,
- mgmt, len);
- }
- spin_unlock_bh(&wiphy_to_rdev(wiphy)->bss_lock);
+ cfg80211_parse_ml_sta_data(wiphy, &inform_data, res, gfp);
return res;
}
diff --git a/net/wireless/sme.c b/net/wireless/sme.c
index 7bdeb8eea92d..9bba233b5a6e 100644
--- a/net/wireless/sme.c
+++ b/net/wireless/sme.c
@@ -5,7 +5,7 @@
* (for nl80211's connect() and wext)
*
* Copyright 2009 Johannes Berg <johannes@sipsolutions.net>
- * Copyright (C) 2009, 2020, 2022 Intel Corporation. All rights reserved.
+ * Copyright (C) 2009, 2020, 2022-2023 Intel Corporation. All rights reserved.
* Copyright 2017 Intel Deutschland GmbH
*/
@@ -491,6 +491,21 @@ static void cfg80211_wdev_release_bsses(struct wireless_dev *wdev)
}
}
+void cfg80211_wdev_release_link_bsses(struct wireless_dev *wdev, u16 link_mask)
+{
+ unsigned int link;
+
+ for_each_valid_link(wdev, link) {
+ if (!wdev->links[link].client.current_bss ||
+ !(link_mask & BIT(link)))
+ continue;
+ cfg80211_unhold_bss(wdev->links[link].client.current_bss);
+ cfg80211_put_bss(wdev->wiphy,
+ &wdev->links[link].client.current_bss->pub);
+ wdev->links[link].client.current_bss = NULL;
+ }
+}
+
static int cfg80211_sme_get_conn_ies(struct wireless_dev *wdev,
const u8 *ies, size_t ies_len,
const u8 **out_ies, size_t *out_ies_len)
@@ -1569,6 +1584,7 @@ void cfg80211_autodisconnect_wk(struct work_struct *work)
container_of(work, struct wireless_dev, disconnect_wk);
struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy);
+ wiphy_lock(wdev->wiphy);
wdev_lock(wdev);
if (wdev->conn_owner_nlportid) {
@@ -1607,4 +1623,5 @@ void cfg80211_autodisconnect_wk(struct work_struct *work)
}
wdev_unlock(wdev);
+ wiphy_unlock(wdev->wiphy);
}
diff --git a/net/wireless/sysfs.c b/net/wireless/sysfs.c
index 268f670835e9..c629bac3f298 100644
--- a/net/wireless/sysfs.c
+++ b/net/wireless/sysfs.c
@@ -5,7 +5,7 @@
*
* Copyright 2005-2006 Jiri Benc <jbenc@suse.cz>
* Copyright 2006 Johannes Berg <johannes@sipsolutions.net>
- * Copyright (C) 2020-2021 Intel Corporation
+ * Copyright (C) 2020-2021, 2023 Intel Corporation
*/
#include <linux/device.h>
@@ -105,14 +105,18 @@ static int wiphy_suspend(struct device *dev)
cfg80211_leave_all(rdev);
cfg80211_process_rdev_events(rdev);
}
+ cfg80211_process_wiphy_works(rdev);
if (rdev->ops->suspend)
ret = rdev_suspend(rdev, rdev->wiphy.wowlan_config);
if (ret == 1) {
/* Driver refuse to configure wowlan */
cfg80211_leave_all(rdev);
cfg80211_process_rdev_events(rdev);
+ cfg80211_process_wiphy_works(rdev);
ret = rdev_suspend(rdev, NULL);
}
+ if (ret == 0)
+ rdev->suspended = true;
}
wiphy_unlock(&rdev->wiphy);
rtnl_unlock();
@@ -132,6 +136,8 @@ static int wiphy_resume(struct device *dev)
wiphy_lock(&rdev->wiphy);
if (rdev->wiphy.registered && rdev->ops->resume)
ret = rdev_resume(rdev);
+ rdev->suspended = false;
+ schedule_work(&rdev->wiphy_work);
wiphy_unlock(&rdev->wiphy);
if (ret)
diff --git a/net/wireless/trace.h b/net/wireless/trace.h
index 716a1fa70069..617c0d0dfa96 100644
--- a/net/wireless/trace.h
+++ b/net/wireless/trace.h
@@ -22,7 +22,7 @@
#define MAXNAME 32
#define WIPHY_ENTRY __array(char, wiphy_name, 32)
-#define WIPHY_ASSIGN strlcpy(__entry->wiphy_name, wiphy_name(wiphy), MAXNAME)
+#define WIPHY_ASSIGN strscpy(__entry->wiphy_name, wiphy_name(wiphy), MAXNAME)
#define WIPHY_PR_FMT "%s"
#define WIPHY_PR_ARG __entry->wiphy_name
@@ -1159,6 +1159,23 @@ TRACE_EVENT(rdev_change_bss,
__entry->ap_isolate, __entry->ht_opmode)
);
+TRACE_EVENT(rdev_inform_bss,
+ TP_PROTO(struct wiphy *wiphy, struct cfg80211_bss *bss),
+ TP_ARGS(wiphy, bss),
+ TP_STRUCT__entry(
+ WIPHY_ENTRY
+ MAC_ENTRY(bssid)
+ CHAN_ENTRY
+ ),
+ TP_fast_assign(
+ WIPHY_ASSIGN;
+ MAC_ASSIGN(bssid, bss->bssid);
+ CHAN_ASSIGN(bss->channel);
+ ),
+ TP_printk(WIPHY_PR_FMT ", %pM, " CHAN_PR_FMT,
+ WIPHY_PR_ARG, __entry->bssid, CHAN_PR_ARG)
+);
+
TRACE_EVENT(rdev_set_txq_params,
TP_PROTO(struct wiphy *wiphy, struct net_device *netdev,
struct ieee80211_txq_params *params),
@@ -1779,15 +1796,16 @@ DEFINE_EVENT(wiphy_netdev_id_evt, rdev_sched_scan_stop,
TRACE_EVENT(rdev_tdls_mgmt,
TP_PROTO(struct wiphy *wiphy, struct net_device *netdev,
- u8 *peer, u8 action_code, u8 dialog_token,
+ u8 *peer, int link_id, u8 action_code, u8 dialog_token,
u16 status_code, u32 peer_capability,
bool initiator, const u8 *buf, size_t len),
- TP_ARGS(wiphy, netdev, peer, action_code, dialog_token, status_code,
- peer_capability, initiator, buf, len),
+ TP_ARGS(wiphy, netdev, peer, link_id, action_code, dialog_token,
+ status_code, peer_capability, initiator, buf, len),
TP_STRUCT__entry(
WIPHY_ENTRY
NETDEV_ENTRY
MAC_ENTRY(peer)
+ __field(int, link_id)
__field(u8, action_code)
__field(u8, dialog_token)
__field(u16, status_code)
@@ -1799,6 +1817,7 @@ TRACE_EVENT(rdev_tdls_mgmt,
WIPHY_ASSIGN;
NETDEV_ASSIGN;
MAC_ASSIGN(peer, peer);
+ __entry->link_id = link_id;
__entry->action_code = action_code;
__entry->dialog_token = dialog_token;
__entry->status_code = status_code;
@@ -1806,11 +1825,12 @@ TRACE_EVENT(rdev_tdls_mgmt,
__entry->initiator = initiator;
memcpy(__get_dynamic_array(buf), buf, len);
),
- TP_printk(WIPHY_PR_FMT ", " NETDEV_PR_FMT ", %pM, action_code: %u, "
+ TP_printk(WIPHY_PR_FMT ", " NETDEV_PR_FMT ", %pM"
+ ", link_id: %d, action_code: %u "
"dialog_token: %u, status_code: %u, peer_capability: %u "
"initiator: %s buf: %#.2x ",
WIPHY_PR_ARG, NETDEV_PR_ARG, __entry->peer,
- __entry->action_code, __entry->dialog_token,
+ __entry->link_id, __entry->action_code, __entry->dialog_token,
__entry->status_code, __entry->peer_capability,
BOOL_TO_STR(__entry->initiator),
((u8 *)__get_dynamic_array(buf))[0])
@@ -3946,6 +3966,21 @@ TRACE_EVENT(rdev_set_hw_timestamp,
__entry->enable)
);
+TRACE_EVENT(cfg80211_links_removed,
+ TP_PROTO(struct net_device *netdev, u16 link_mask),
+ TP_ARGS(netdev, link_mask),
+ TP_STRUCT__entry(
+ NETDEV_ENTRY
+ __field(u16, link_mask)
+ ),
+ TP_fast_assign(
+ NETDEV_ASSIGN;
+ __entry->link_mask = link_mask;
+ ),
+ TP_printk(NETDEV_PR_FMT ", link_mask:%u", NETDEV_PR_ARG,
+ __entry->link_mask)
+);
+
#endif /* !__RDEV_OPS_TRACE || TRACE_HEADER_MULTI_READ */
#undef TRACE_INCLUDE_PATH
diff --git a/net/wireless/util.c b/net/wireless/util.c
index 9755ef281040..89c9ad6c886e 100644
--- a/net/wireless/util.c
+++ b/net/wireless/util.c
@@ -1646,6 +1646,114 @@ static u32 cfg80211_calculate_bitrate_eht(struct rate_info *rate)
return result / 10000;
}
+static u32 cfg80211_calculate_bitrate_s1g(struct rate_info *rate)
+{
+ /* For 1, 2, 4, 8 and 16 MHz channels */
+ static const u32 base[5][11] = {
+ { 300000,
+ 600000,
+ 900000,
+ 1200000,
+ 1800000,
+ 2400000,
+ 2700000,
+ 3000000,
+ 3600000,
+ 4000000,
+ /* MCS 10 supported in 1 MHz only */
+ 150000,
+ },
+ { 650000,
+ 1300000,
+ 1950000,
+ 2600000,
+ 3900000,
+ 5200000,
+ 5850000,
+ 6500000,
+ 7800000,
+ /* MCS 9 not valid */
+ },
+ { 1350000,
+ 2700000,
+ 4050000,
+ 5400000,
+ 8100000,
+ 10800000,
+ 12150000,
+ 13500000,
+ 16200000,
+ 18000000,
+ },
+ { 2925000,
+ 5850000,
+ 8775000,
+ 11700000,
+ 17550000,
+ 23400000,
+ 26325000,
+ 29250000,
+ 35100000,
+ 39000000,
+ },
+ { 8580000,
+ 11700000,
+ 17550000,
+ 23400000,
+ 35100000,
+ 46800000,
+ 52650000,
+ 58500000,
+ 70200000,
+ 78000000,
+ },
+ };
+ u32 bitrate;
+ /* default is 1 MHz index */
+ int idx = 0;
+
+ if (rate->mcs >= 11)
+ goto warn;
+
+ switch (rate->bw) {
+ case RATE_INFO_BW_16:
+ idx = 4;
+ break;
+ case RATE_INFO_BW_8:
+ idx = 3;
+ break;
+ case RATE_INFO_BW_4:
+ idx = 2;
+ break;
+ case RATE_INFO_BW_2:
+ idx = 1;
+ break;
+ case RATE_INFO_BW_1:
+ idx = 0;
+ break;
+ case RATE_INFO_BW_5:
+ case RATE_INFO_BW_10:
+ case RATE_INFO_BW_20:
+ case RATE_INFO_BW_40:
+ case RATE_INFO_BW_80:
+ case RATE_INFO_BW_160:
+ default:
+ goto warn;
+ }
+
+ bitrate = base[idx][rate->mcs];
+ bitrate *= rate->nss;
+
+ if (rate->flags & RATE_INFO_FLAGS_SHORT_GI)
+ bitrate = (bitrate / 9) * 10;
+ /* do NOT round down here */
+ return (bitrate + 50000) / 100000;
+warn:
+ WARN_ONCE(1, "invalid rate bw=%d, mcs=%d, nss=%d\n",
+ rate->bw, rate->mcs, rate->nss);
+ return 0;
+}
+
u32 cfg80211_calculate_bitrate(struct rate_info *rate)
{
if (rate->flags & RATE_INFO_FLAGS_MCS)
@@ -1662,6 +1770,8 @@ u32 cfg80211_calculate_bitrate(struct rate_info *rate)
return cfg80211_calculate_bitrate_he(rate);
if (rate->flags & RATE_INFO_FLAGS_EHT_MCS)
return cfg80211_calculate_bitrate_eht(rate);
+ if (rate->flags & RATE_INFO_FLAGS_S1G_MCS)
+ return cfg80211_calculate_bitrate_s1g(rate);
return rate->legacy;
}
diff --git a/net/wireless/wext-core.c b/net/wireless/wext-core.c
index a125fd1fa134..a161c64d1765 100644
--- a/net/wireless/wext-core.c
+++ b/net/wireless/wext-core.c
@@ -815,6 +815,12 @@ static int ioctl_standard_iw_point(struct iw_point *iwp, unsigned int cmd,
}
}
+ /* Sanity-check to ensure we never end up _allocating_ zero
+ * bytes of data for extra.
+ */
+ if (extra_size <= 0)
+ return -EFAULT;
+
/* kzalloc() ensures NULL-termination for essid_compat. */
extra = kzalloc(extra_size, GFP_KERNEL);
if (!extra)
diff --git a/net/wireless/wext-sme.c b/net/wireless/wext-sme.c
index f231207ca210..f3eaa3388694 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, 2020-2022 Intel Corporation
+ * Copyright (C) 2009, 2020-2023 Intel Corporation
*/
#include <linux/export.h>
@@ -338,6 +338,7 @@ int cfg80211_wext_siwgenie(struct net_device *dev,
if (!ie_len)
ie = NULL;
+ wiphy_lock(wdev->wiphy);
wdev_lock(wdev);
/* no change */
@@ -370,6 +371,7 @@ int cfg80211_wext_siwgenie(struct net_device *dev,
err = 0;
out:
wdev_unlock(wdev);
+ wiphy_unlock(wdev->wiphy);
return err;
}
diff --git a/net/x25/af_x25.c b/net/x25/af_x25.c
index 5c7ad301d742..0fb5143bec7a 100644
--- a/net/x25/af_x25.c
+++ b/net/x25/af_x25.c
@@ -1757,7 +1757,6 @@ static const struct proto_ops x25_proto_ops = {
.sendmsg = x25_sendmsg,
.recvmsg = x25_recvmsg,
.mmap = sock_no_mmap,
- .sendpage = sock_no_sendpage,
};
static struct packet_type x25_packet_type __read_mostly = {
diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c
index cc1e7f15fa73..5a8c0dd250af 100644
--- a/net/xdp/xsk.c
+++ b/net/xdp/xsk.c
@@ -1389,7 +1389,6 @@ static const struct proto_ops xsk_proto_ops = {
.sendmsg = xsk_sendmsg,
.recvmsg = xsk_recvmsg,
.mmap = xsk_mmap,
- .sendpage = sock_no_sendpage,
};
static void xsk_destruct(struct sock *sk)
diff --git a/net/xdp/xsk_buff_pool.c b/net/xdp/xsk_buff_pool.c
index b2df1e0f8153..26f6d304451e 100644
--- a/net/xdp/xsk_buff_pool.c
+++ b/net/xdp/xsk_buff_pool.c
@@ -350,7 +350,7 @@ void xp_dma_unmap(struct xsk_buff_pool *pool, unsigned long attrs)
{
struct xsk_dma_map *dma_map;
- if (pool->dma_pages_cnt == 0)
+ if (!pool->dma_pages)
return;
dma_map = xp_find_dma_map(pool);
@@ -364,6 +364,7 @@ void xp_dma_unmap(struct xsk_buff_pool *pool, unsigned long attrs)
__xp_dma_unmap(dma_map, attrs);
kvfree(pool->dma_pages);
+ pool->dma_pages = NULL;
pool->dma_pages_cnt = 0;
pool->dev = NULL;
}
@@ -503,7 +504,7 @@ static struct xdp_buff_xsk *__xp_alloc(struct xsk_buff_pool *pool)
if (pool->unaligned) {
xskb = pool->free_heads[--pool->free_heads_cnt];
xp_init_xskb_addr(xskb, pool, addr);
- if (pool->dma_pages_cnt)
+ if (pool->dma_pages)
xp_init_xskb_dma(xskb, pool, pool->dma_pages, addr);
} else {
xskb = &pool->heads[xp_aligned_extract_idx(pool, addr)];
@@ -569,7 +570,7 @@ static u32 xp_alloc_new_from_fq(struct xsk_buff_pool *pool, struct xdp_buff **xd
if (pool->unaligned) {
xskb = pool->free_heads[--pool->free_heads_cnt];
xp_init_xskb_addr(xskb, pool, addr);
- if (pool->dma_pages_cnt)
+ if (pool->dma_pages)
xp_init_xskb_dma(xskb, pool, pool->dma_pages, addr);
} else {
xskb = &pool->heads[xp_aligned_extract_idx(pool, addr)];
diff --git a/net/xdp/xskmap.c b/net/xdp/xskmap.c
index 2c1427074a3b..e1c526f97ce3 100644
--- a/net/xdp/xskmap.c
+++ b/net/xdp/xskmap.c
@@ -5,7 +5,6 @@
#include <linux/bpf.h>
#include <linux/filter.h>
-#include <linux/capability.h>
#include <net/xdp_sock.h>
#include <linux/slab.h>
#include <linux/sched.h>
@@ -68,9 +67,6 @@ static struct bpf_map *xsk_map_alloc(union bpf_attr *attr)
int numa_node;
u64 size;
- if (!capable(CAP_NET_ADMIN))
- return ERR_PTR(-EPERM);
-
if (attr->max_entries == 0 || attr->key_size != 4 ||
attr->value_size != 4 ||
attr->map_flags & ~(BPF_F_NUMA_NODE | BPF_F_RDONLY | BPF_F_WRONLY))
diff --git a/net/xfrm/espintcp.c b/net/xfrm/espintcp.c
index 872b80188e83..d3b3f9e720b3 100644
--- a/net/xfrm/espintcp.c
+++ b/net/xfrm/espintcp.c
@@ -205,26 +205,32 @@ static int espintcp_sendskb_locked(struct sock *sk, struct espintcp_msg *emsg,
static int espintcp_sendskmsg_locked(struct sock *sk,
struct espintcp_msg *emsg, int flags)
{
+ struct msghdr msghdr = {
+ .msg_flags = flags | MSG_SPLICE_PAGES | MSG_MORE,
+ };
struct sk_msg *skmsg = &emsg->skmsg;
+ bool more = flags & MSG_MORE;
struct scatterlist *sg;
int done = 0;
int ret;
- flags |= MSG_SENDPAGE_NOTLAST;
sg = &skmsg->sg.data[skmsg->sg.start];
do {
+ struct bio_vec bvec;
size_t size = sg->length - emsg->offset;
int offset = sg->offset + emsg->offset;
struct page *p;
emsg->offset = 0;
- if (sg_is_last(sg))
- flags &= ~MSG_SENDPAGE_NOTLAST;
+ if (sg_is_last(sg) && !more)
+ msghdr.msg_flags &= ~MSG_MORE;
p = sg_page(sg);
retry:
- ret = do_tcp_sendpages(sk, p, offset, size, flags);
+ bvec_set_page(&bvec, p, size, offset);
+ iov_iter_bvec(&msghdr.msg_iter, ITER_SOURCE, &bvec, 1, size);
+ ret = tcp_sendmsg_locked(sk, &msghdr, size);
if (ret < 0) {
emsg->offset = offset - sg->offset;
skmsg->sg.start += done;
diff --git a/net/xfrm/xfrm_device.c b/net/xfrm/xfrm_device.c
index 408f5e55744e..533697e2488f 100644
--- a/net/xfrm/xfrm_device.c
+++ b/net/xfrm/xfrm_device.c
@@ -15,6 +15,7 @@
#include <linux/slab.h>
#include <linux/spinlock.h>
#include <net/dst.h>
+#include <net/gso.h>
#include <net/xfrm.h>
#include <linux/notifier.h>
diff --git a/net/xfrm/xfrm_interface_core.c b/net/xfrm/xfrm_interface_core.c
index 35279c220bd7..a3319965470a 100644
--- a/net/xfrm/xfrm_interface_core.c
+++ b/net/xfrm/xfrm_interface_core.c
@@ -33,6 +33,7 @@
#include <linux/uaccess.h>
#include <linux/atomic.h>
+#include <net/gso.h>
#include <net/icmp.h>
#include <net/ip.h>
#include <net/ipv6.h>
diff --git a/net/xfrm/xfrm_ipcomp.c b/net/xfrm/xfrm_ipcomp.c
index 80143360bf09..9c0fa0e1786a 100644
--- a/net/xfrm/xfrm_ipcomp.c
+++ b/net/xfrm/xfrm_ipcomp.c
@@ -74,14 +74,11 @@ static int ipcomp_decompress(struct xfrm_state *x, struct sk_buff *skb)
if (!page)
return -ENOMEM;
- __skb_frag_set_page(frag, page);
-
len = PAGE_SIZE;
if (dlen < len)
len = dlen;
- skb_frag_off_set(frag, 0);
- skb_frag_size_set(frag, len);
+ skb_frag_fill_page_desc(frag, page, 0, len);
memcpy(skb_frag_address(frag), scratch, len);
skb->truesize += len;
diff --git a/net/xfrm/xfrm_output.c b/net/xfrm/xfrm_output.c
index 369e5de8558f..662c83beb345 100644
--- a/net/xfrm/xfrm_output.c
+++ b/net/xfrm/xfrm_output.c
@@ -13,6 +13,7 @@
#include <linux/slab.h>
#include <linux/spinlock.h>
#include <net/dst.h>
+#include <net/gso.h>
#include <net/icmp.h>
#include <net/inet_ecn.h>
#include <net/xfrm.h>